Merge remote-tracking branches 'spi/topic/s3c64xx', 'spi/topic/sg', 'spi/topic/sh-msiof', 'spi/topic/spidev' and 'spi/topic/stats' into spi-next
diff --git a/.get_maintainer.ignore b/.get_maintainer.ignore
new file mode 100644
index 0000000..cca6d87
--- /dev/null
+++ b/.get_maintainer.ignore
@@ -0,0 +1 @@
+Christoph Hellwig <hch@lst.de>
diff --git a/.mailmap b/.mailmap
index 977f958..4b31af5 100644
--- a/.mailmap
+++ b/.mailmap
@@ -17,6 +17,7 @@
 Al Viro <viro@ftp.linux.org.uk>
 Al Viro <viro@zenIV.linux.org.uk>
 Andreas Herrmann <aherrman@de.ibm.com>
+Andrey Ryabinin <ryabinin.a.a@gmail.com> <a.ryabinin@samsung.com>
 Andrew Morton <akpm@linux-foundation.org>
 Andrew Vasquez <andrew.vasquez@qlogic.com>
 Andy Adamson <andros@citi.umich.edu>
@@ -116,6 +117,7 @@
 Simon Kelley <simon@thekelleys.org.uk>
 Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
 Stephen Hemminger <shemminger@osdl.org>
+Sudeep Holla <sudeep.holla@arm.com> Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
 Sumit Semwal <sumit.semwal@ti.com>
 Tejun Heo <htejun@gmail.com>
 Thomas Graf <tgraf@suug.ch>
@@ -125,7 +127,9 @@
 Uwe Kleine-König <ukl@pengutronix.de>
 Uwe Kleine-König <Uwe.Kleine-Koenig@digi.com>
 Valdis Kletnieks <Valdis.Kletnieks@vt.edu>
-Viresh Kumar <viresh.linux@gmail.com> <viresh.kumar@st.com>
+Viresh Kumar <vireshk@kernel.org> <viresh.kumar@st.com>
+Viresh Kumar <vireshk@kernel.org> <viresh.linux@gmail.com>
+Viresh Kumar <vireshk@kernel.org> <viresh.kumar2@arm.com>
 Takashi YOSHII <takashi.yoshii.zj@renesas.com>
 Yusuke Goda <goda.yusuke@renesas.com>
 Gustavo Padovan <gustavo@las.ic.unicamp.br>
diff --git a/Documentation/ABI/testing/sysfs-bus-iio b/Documentation/ABI/testing/sysfs-bus-iio
index bbed111..70c9b1a 100644
--- a/Documentation/ABI/testing/sysfs-bus-iio
+++ b/Documentation/ABI/testing/sysfs-bus-iio
@@ -1234,10 +1234,8 @@
 		object is near the sensor, usually be observing
 		reflectivity of infrared or ultrasound emitted.
 		Often these sensors are unit less and as such conversion
-		to SI units is not possible.  Where it is, the units should
-		be meters.  If such a conversion is not possible, the reported
-		values should behave in the same way as a distance, i.e. lower
-		values indicate something is closer to the sensor.
+		to SI units is not possible. Higher proximity measurements
+		indicate closer objects, and vice versa.
 
 What:		/sys/.../iio:deviceX/in_illuminance_input
 What:		/sys/.../iio:deviceX/in_illuminance_raw
diff --git a/Documentation/DocBook/drm.tmpl b/Documentation/DocBook/drm.tmpl
index c0312cb..2fb9a54 100644
--- a/Documentation/DocBook/drm.tmpl
+++ b/Documentation/DocBook/drm.tmpl
@@ -3383,7 +3383,7 @@
 	<td valign="top" >TBD</td>
 	</tr>
 	<tr>
-	<td rowspan="2" valign="top" >omap</td>
+	<td valign="top" >omap</td>
 	<td valign="top" >Generic</td>
 	<td valign="top" >“zorder”</td>
 	<td valign="top" >RANGE</td>
diff --git a/Documentation/arm/SPEAr/overview.txt b/Documentation/arm/SPEAr/overview.txt
index 65610bf..1b049be 100644
--- a/Documentation/arm/SPEAr/overview.txt
+++ b/Documentation/arm/SPEAr/overview.txt
@@ -60,4 +60,4 @@
   Document Author
   ---------------
 
-  Viresh Kumar <viresh.linux@gmail.com>, (c) 2010-2012 ST Microelectronics
+  Viresh Kumar <vireshk@kernel.org>, (c) 2010-2012 ST Microelectronics
diff --git a/Documentation/arm/sunxi/README b/Documentation/arm/sunxi/README
index 1fe2d7f..5e38e158 100644
--- a/Documentation/arm/sunxi/README
+++ b/Documentation/arm/sunxi/README
@@ -36,7 +36,7 @@
         + User Manual
           http://dl.linux-sunxi.org/A20/A20%20User%20Manual%202013-03-22.pdf
 
-      - Allwinner A23
+      - Allwinner A23 (sun8i)
         + Datasheet
           http://dl.linux-sunxi.org/A23/A23%20Datasheet%20V1.0%2020130830.pdf
         + User Manual
@@ -55,7 +55,23 @@
         + User Manual
           http://dl.linux-sunxi.org/A31/A3x_release_document/A31s/IC/A31s%20User%20Manual%20%20V1.0%2020130322.pdf
 
+      - Allwinner A33 (sun8i)
+        + Datasheet
+          http://dl.linux-sunxi.org/A33/A33%20Datasheet%20release%201.1.pdf
+        + User Manual
+          http://dl.linux-sunxi.org/A33/A33%20user%20manual%20release%201.1.pdf
+
+      - Allwinner H3 (sun8i)
+        + Datasheet
+          http://dl.linux-sunxi.org/H3/Allwinner_H3_Datasheet_V1.0.pdf
+
     * Quad ARM Cortex-A15, Quad ARM Cortex-A7 based SoCs
       - Allwinner A80
         + Datasheet
 	  http://dl.linux-sunxi.org/A80/A80_Datasheet_Revision_1.0_0404.pdf
+
+    * Octa ARM Cortex-A7 based SoCs
+      - Allwinner A83T
+        + Not Supported
+        + Datasheet
+          http://dl.linux-sunxi.org/A83T/A83T_datasheet_Revision_1.1.pdf
diff --git a/Documentation/device-mapper/cache.txt b/Documentation/device-mapper/cache.txt
index 82960cf..785eab8 100644
--- a/Documentation/device-mapper/cache.txt
+++ b/Documentation/device-mapper/cache.txt
@@ -258,6 +258,12 @@
 	no further I/O will be permitted and the status will just
 	contain the string 'Fail'.  The userspace recovery tools
 	should then be used.
+needs_check		 : 'needs_check' if set, '-' if not set
+	A metadata operation has failed, resulting in the needs_check
+	flag being set in the metadata's superblock.  The metadata
+	device must be deactivated and checked/repaired before the
+	cache can be made fully operational again.  '-' indicates
+	needs_check is not set.
 
 Messages
 --------
diff --git a/Documentation/device-mapper/thin-provisioning.txt b/Documentation/device-mapper/thin-provisioning.txt
index 4f67578..1699a55 100644
--- a/Documentation/device-mapper/thin-provisioning.txt
+++ b/Documentation/device-mapper/thin-provisioning.txt
@@ -296,7 +296,7 @@
 	underlying device.  When this is enabled when loading the table,
 	it can get disabled if the underlying device doesn't support it.
 
-    ro|rw
+    ro|rw|out_of_data_space
 	If the pool encounters certain types of device failures it will
 	drop into a read-only metadata mode in which no changes to
 	the pool metadata (like allocating new blocks) are permitted.
@@ -314,6 +314,13 @@
 	module parameter can be used to change this timeout -- it
 	defaults to 60 seconds but may be disabled using a value of 0.
 
+    needs_check
+	A metadata operation has failed, resulting in the needs_check
+	flag being set in the metadata's superblock.  The metadata
+	device must be deactivated and checked/repaired before the
+	thin-pool can be made fully operational again.  '-' indicates
+	needs_check is not set.
+
 iii) Messages
 
     create_thin <dev id>
diff --git a/Documentation/devicetree/bindings/arm/cpus.txt b/Documentation/devicetree/bindings/arm/cpus.txt
index d6b794c..91e6e5c 100644
--- a/Documentation/devicetree/bindings/arm/cpus.txt
+++ b/Documentation/devicetree/bindings/arm/cpus.txt
@@ -199,6 +199,7 @@
 			    "qcom,kpss-acc-v1"
 			    "qcom,kpss-acc-v2"
 			    "rockchip,rk3066-smp"
+			    "ste,dbx500-smp"
 
 	- cpu-release-addr
 		Usage: required for systems that have an "enable-method"
diff --git a/Documentation/devicetree/bindings/arm/sunxi.txt b/Documentation/devicetree/bindings/arm/sunxi.txt
index 42941fd..67da205 100644
--- a/Documentation/devicetree/bindings/arm/sunxi.txt
+++ b/Documentation/devicetree/bindings/arm/sunxi.txt
@@ -9,4 +9,6 @@
   allwinner,sun6i-a31
   allwinner,sun7i-a20
   allwinner,sun8i-a23
+  allwinner,sun8i-a33
+  allwinner,sun8i-h3
   allwinner,sun9i-a80
diff --git a/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt b/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt
index d305876..c53e0b0 100644
--- a/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt
+++ b/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt
@@ -35,7 +35,7 @@
 			device_type = "dma";
 			reg = <0x0 0x1f270000 0x0 0x10000>,
 			      <0x0 0x1f200000 0x0 0x10000>,
-			      <0x0 0x1b008000 0x0 0x2000>,
+			      <0x0 0x1b000000 0x0 0x400000>,
 			      <0x0 0x1054a000 0x0 0x100>;
 			interrupts = <0x0 0x82 0x4>,
 				     <0x0 0xb8 0x4>,
diff --git a/Documentation/devicetree/bindings/drm/imx/fsl-imx-drm.txt b/Documentation/devicetree/bindings/drm/imx/fsl-imx-drm.txt
index e75f0e5..971c3ee 100644
--- a/Documentation/devicetree/bindings/drm/imx/fsl-imx-drm.txt
+++ b/Documentation/devicetree/bindings/drm/imx/fsl-imx-drm.txt
@@ -65,8 +65,10 @@
 - edid: verbatim EDID data block describing attached display.
 - ddc: phandle describing the i2c bus handling the display data
   channel
-- port: A port node with endpoint definitions as defined in
+- port@[0-1]: Port nodes with endpoint definitions as defined in
   Documentation/devicetree/bindings/media/video-interfaces.txt.
+  Port 0 is the input port connected to the IPU display interface,
+  port 1 is the output port connected to a panel.
 
 example:
 
@@ -75,9 +77,29 @@
 	edid = [edid-data];
 	interface-pix-fmt = "rgb24";
 
-	port {
+	port@0 {
+		reg = <0>;
+
 		display_in: endpoint {
 			remote-endpoint = <&ipu_di0_disp0>;
 		};
 	};
+
+	port@1 {
+		reg = <1>;
+
+		display_out: endpoint {
+			remote-endpoint = <&panel_in>;
+		};
+	};
+};
+
+panel {
+	...
+
+	port {
+		panel_in: endpoint {
+			remote-endpoint = <&display_out>;
+		};
+	};
 };
diff --git a/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt b/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
index c03eec1..3443e0f 100644
--- a/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
+++ b/Documentation/devicetree/bindings/iommu/arm,smmu-v3.txt
@@ -35,3 +35,6 @@
 
                       NOTE: this only applies to the SMMU itself, not
                       masters connected upstream of the SMMU.
+
+- hisilicon,broken-prefetch-cmd
+                    : Avoid sending CMD_PREFETCH_* commands to the SMMU.
diff --git a/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt b/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt
index 938f8e1..0db6047 100644
--- a/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt
+++ b/Documentation/devicetree/bindings/memory-controllers/ti/emif.txt
@@ -8,6 +8,7 @@
 Required properties:
 - compatible	: Should be of the form "ti,emif-<ip-rev>" where <ip-rev>
   is the IP revision of the specific EMIF instance.
+		  For am437x should be ti,emif-am4372.
 
 - phy-type	: <u32> indicating the DDR phy type. Following are the
   allowed values
diff --git a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
index 5d0376b..211e778 100644
--- a/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
+++ b/Documentation/devicetree/bindings/mmc/fsl-imx-esdhc.txt
@@ -17,7 +17,6 @@
 	       "fsl,imx6sx-usdhc"
 
 Optional properties:
-- fsl,cd-controller : Indicate to use controller internal card detection
 - fsl,wp-controller : Indicate to use controller internal write protection
 - fsl,delay-line : Specify the number of delay cells for override mode.
   This is used to set the clock delay for DLL(Delay Line) on override mode
@@ -35,7 +34,6 @@
 	compatible = "fsl,imx51-esdhc";
 	reg = <0x70004000 0x4000>;
 	interrupts = <1>;
-	fsl,cd-controller;
 	fsl,wp-controller;
 };
 
diff --git a/Documentation/devicetree/bindings/phy/ti-phy.txt b/Documentation/devicetree/bindings/phy/ti-phy.txt
index 305e3df..9cf9446 100644
--- a/Documentation/devicetree/bindings/phy/ti-phy.txt
+++ b/Documentation/devicetree/bindings/phy/ti-phy.txt
@@ -82,6 +82,9 @@
  - id: If there are multiple instance of the same type, in order to
    differentiate between each instance "id" can be used (e.g., multi-lane PCIe
    PHY). If "id" is not provided, it is set to default value of '1'.
+ - syscon-pllreset: Handle to system control region that contains the
+   CTRL_CORE_SMA_SW_0 register and register offset to the CTRL_CORE_SMA_SW_0
+   register that contains the SATA_PLL_SOFT_RESET bit. Only valid for sata_phy.
 
 This is usually a subnode of ocp2scp to which it is connected.
 
@@ -100,3 +103,16 @@
 			"sysclk",
 			"refclk";
 };
+
+sata_phy: phy@4A096000 {
+	compatible = "ti,phy-pipe3-sata";
+	reg = <0x4A096000 0x80>, /* phy_rx */
+	      <0x4A096400 0x64>, /* phy_tx */
+	      <0x4A096800 0x40>; /* pll_ctrl */
+	reg-names = "phy_rx", "phy_tx", "pll_ctrl";
+	ctrl-module = <&omap_control_sata>;
+	clocks = <&sys_clkin1>, <&sata_ref_clk>;
+	clock-names = "sysclk", "refclk";
+	syscon-pllreset = <&scm_conf 0x3fc>;
+	#phy-cells = <0>;
+};
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt b/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt
index 8832e87..6478175 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt
@@ -6,14 +6,14 @@
 For PSC in UART mode the needed PSC serial devices
 are specified by fsl,mpc5121-psc-uart nodes in the
 fsl,mpc5121-immr SoC node. Additionally the PSC FIFO
-Controller node fsl,mpc5121-psc-fifo is requered there:
+Controller node fsl,mpc5121-psc-fifo is required there:
 
-fsl,mpc5121-psc-uart nodes
+fsl,mpc512x-psc-uart nodes
 --------------------------
 
 Required properties :
- - compatible : Should contain "fsl,mpc5121-psc-uart" and "fsl,mpc5121-psc"
- - cell-index : Index of the PSC in hardware
+ - compatible : Should contain "fsl,<soc>-psc-uart" and "fsl,<soc>-psc"
+   Supported <soc>s: mpc5121, mpc5125
  - reg : Offset and length of the register set for the PSC device
  - interrupts : <a b> where a is the interrupt number of the
    PSC FIFO Controller and b is a field that represents an
@@ -25,12 +25,21 @@
  - fsl,rx-fifo-size : the size of the RX fifo slice (a multiple of 4)
  - fsl,tx-fifo-size : the size of the TX fifo slice (a multiple of 4)
 
+PSC in SPI mode
+---------------
 
-fsl,mpc5121-psc-fifo node
+Similar to the UART mode a PSC can be operated in SPI mode. The compatible used
+for that is fsl,mpc5121-psc-spi. It requires a fsl,mpc5121-psc-fifo as well.
+The required and recommended properties are identical to the
+fsl,mpc5121-psc-uart nodes, just use spi instead of uart in the compatible
+string.
+
+fsl,mpc512x-psc-fifo node
 -------------------------
 
 Required properties :
- - compatible : Should be "fsl,mpc5121-psc-fifo"
+ - compatible : Should be "fsl,<soc>-psc-fifo"
+   Supported <soc>s: mpc5121, mpc5125
  - reg : Offset and length of the register set for the PSC
          FIFO Controller
  - interrupts : <a b> where a is the interrupt number of the
@@ -39,6 +48,9 @@
  - interrupt-parent : the phandle for the interrupt controller that
    services interrupts for this device.
 
+Recommended properties :
+ - clocks : specifies the clock needed to operate the fifo controller
+ - clock-names : name(s) for the clock(s) listed in clocks
 
 Example for a board using PSC0 and PSC1 devices in serial mode:
 
diff --git a/Documentation/devicetree/bindings/sound/mt8173-max98090.txt b/Documentation/devicetree/bindings/sound/mt8173-max98090.txt
index 829bd26..519e97c 100644
--- a/Documentation/devicetree/bindings/sound/mt8173-max98090.txt
+++ b/Documentation/devicetree/bindings/sound/mt8173-max98090.txt
@@ -3,11 +3,13 @@
 Required properties:
 - compatible : "mediatek,mt8173-max98090"
 - mediatek,audio-codec: the phandle of the MAX98090 audio codec
+- mediatek,platform: the phandle of MT8173 ASoC platform
 
 Example:
 
 	sound {
 		compatible = "mediatek,mt8173-max98090";
 		mediatek,audio-codec = <&max98090>;
+		mediatek,platform = <&afe>;
 	};
 
diff --git a/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt b/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt
index 61e98c9..f205ce9 100644
--- a/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt
+++ b/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt
@@ -3,11 +3,13 @@
 Required properties:
 - compatible : "mediatek,mt8173-rt5650-rt5676"
 - mediatek,audio-codec: the phandles of rt5650 and rt5676 codecs
+- mediatek,platform: the phandle of MT8173 ASoC platform
 
 Example:
 
 	sound {
 		compatible = "mediatek,mt8173-rt5650-rt5676";
 		mediatek,audio-codec = <&rt5650 &rt5676>;
+		mediatek,platform = <&afe>;
 	};
 
diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
index bd99193..204b311 100644
--- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
+++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
@@ -10,6 +10,8 @@
 Optional properties:
 - cs-gpios : Specifies the gpio pis to be used for chipselects.
 - num-cs : The number of chipselects. If omitted, this will default to 4.
+- reg-io-width : The I/O register width (in bytes) implemented by this
+  device.  Supported values are 2 or 4 (the default).
 
 Child nodes as per the generic SPI binding.
 
diff --git a/Documentation/devicetree/bindings/spi/spi-ath79.txt b/Documentation/devicetree/bindings/spi/spi-ath79.txt
index f1ad9c3..9c696fa 100644
--- a/Documentation/devicetree/bindings/spi/spi-ath79.txt
+++ b/Documentation/devicetree/bindings/spi/spi-ath79.txt
@@ -3,7 +3,7 @@
 Required properties:
 - compatible: has to be "qca,<soc-type>-spi", "qca,ar7100-spi" as fallback.
 - reg: Base address and size of the controllers memory area
-- clocks: phandle to the AHB clock.
+- clocks: phandle of the AHB clock.
 - clock-names: has to be "ahb".
 - #address-cells: <1>, as required by generic SPI binding.
 - #size-cells: <0>, also as required by generic SPI binding.
@@ -12,9 +12,9 @@
 
 Example:
 
-	spi@1F000000 {
+	spi@1f000000 {
 		compatible = "qca,ar9132-spi", "qca,ar7100-spi";
-		reg = <0x1F000000 0x10>;
+		reg = <0x1f000000 0x10>;
 
 		clocks = <&pll 2>;
 		clock-names = "ahb";
diff --git a/Documentation/devicetree/bindings/spi/spi-davinci.txt b/Documentation/devicetree/bindings/spi/spi-davinci.txt
index 12ecfe9..d1e914a 100644
--- a/Documentation/devicetree/bindings/spi/spi-davinci.txt
+++ b/Documentation/devicetree/bindings/spi/spi-davinci.txt
@@ -12,6 +12,8 @@
 - compatible:
 	- "ti,dm6441-spi" for SPI used similar to that on DM644x SoC family
 	- "ti,da830-spi" for SPI used similar to that on DA8xx SoC family
+	- "ti,keystone-spi" for SPI used similar to that on Keystone2 SoC
+		family
 - reg: Offset and length of SPI controller register space
 - num-cs: Number of chip selects. This includes internal as well as
 	GPIO chip selects.
diff --git a/Documentation/devicetree/bindings/spi/spi-img-spfi.txt b/Documentation/devicetree/bindings/spi/spi-img-spfi.txt
index e02fbf1..494db60 100644
--- a/Documentation/devicetree/bindings/spi/spi-img-spfi.txt
+++ b/Documentation/devicetree/bindings/spi/spi-img-spfi.txt
@@ -21,6 +21,7 @@
 Optional properties:
 - img,supports-quad-mode: Should be set if the interface supports quad mode
   SPI transfers.
+- spfi-max-frequency: Maximum speed supported by the spfi block.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/spi/spi-mt65xx.txt b/Documentation/devicetree/bindings/spi/spi-mt65xx.txt
new file mode 100644
index 0000000..dcefc43
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi-mt65xx.txt
@@ -0,0 +1,51 @@
+Binding for MTK SPI controller
+
+Required properties:
+- compatible: should be one of the following.
+    - mediatek,mt8173-spi: for mt8173 platforms
+    - mediatek,mt8135-spi: for mt8135 platforms
+    - mediatek,mt6589-spi: for mt6589 platforms
+
+- #address-cells: should be 1.
+
+- #size-cells: should be 0.
+
+- reg: Address and length of the register set for the device
+
+- interrupts: Should contain spi interrupt
+
+- clocks: phandles to input clocks.
+  The first should be <&topckgen CLK_TOP_SPI_SEL>.
+  The second should be one of the following.
+   -  <&clk26m>: specify parent clock 26MHZ.
+   -  <&topckgen CLK_TOP_SYSPLL3_D2>: specify parent clock 109MHZ.
+				      It's the default one.
+   -  <&topckgen CLK_TOP_SYSPLL4_D2>: specify parent clock 78MHZ.
+   -  <&topckgen CLK_TOP_UNIVPLL2_D4>: specify parent clock 104MHZ.
+   -  <&topckgen CLK_TOP_UNIVPLL1_D8>: specify parent clock 78MHZ.
+
+- clock-names: shall be "spi-clk" for the controller clock, and
+  "parent-clk" for the parent clock.
+
+Optional properties:
+- mediatek,pad-select: specify which pins group(ck/mi/mo/cs) spi
+  controller used, this value should be 0~3, only required for MT8173.
+    0: specify GPIO69,70,71,72 for spi pins.
+    1: specify GPIO102,103,104,105 for spi pins.
+    2: specify GPIO128,129,130,131 for spi pins.
+    3: specify GPIO5,6,7,8 for spi pins.
+
+Example:
+
+- SoC Specific Portion:
+spi: spi@1100a000 {
+	compatible = "mediatek,mt8173-spi";
+	#address-cells = <1>;
+	#size-cells = <0>;
+	reg = <0 0x1100a000 0 0x1000>;
+	interrupts = <GIC_SPI 110 IRQ_TYPE_LEVEL_LOW>;
+	clocks = <&topckgen CLK_TOP_SPI_SEL>, <&topckgen CLK_TOP_SYSPLL3_D2>;
+	clock-names = "spi-clk", "parent-clk";
+	mediatek,pad-select = <0>;
+	status = "disabled";
+};
diff --git a/Documentation/hwmon/nct7904 b/Documentation/hwmon/nct7904
index 014f112..57fffe3 100644
--- a/Documentation/hwmon/nct7904
+++ b/Documentation/hwmon/nct7904
@@ -35,11 +35,11 @@
 temp[2-9]_input		CPU temperatures (1/1000 degree,
 			0.125 degree resolution)
 
-fan[1-4]_mode		R/W, 0/1 for manual or SmartFan mode
+pwm[1-4]_enable		R/W, 1/2 for manual or SmartFan mode
 			Setting SmartFan mode is supported only if it has been
 			previously configured by BIOS (or configuration EEPROM)
 
-fan[1-4]_pwm		R/O in SmartFan mode, R/W in manual control mode
+pwm[1-4]		R/O in SmartFan mode, R/W in manual control mode
 
 The driver checks sensor control registers and does not export the sensors
 that are not enabled. Anyway, a sensor that is enabled may actually be not
diff --git a/Documentation/input/alps.txt b/Documentation/input/alps.txt
index c86f2f1..1fec113 100644
--- a/Documentation/input/alps.txt
+++ b/Documentation/input/alps.txt
@@ -119,8 +119,10 @@
  byte 5:  0   z6   z5   z4   z3   z2   z1   z0
 
 Protocol Version 2 DualPoint devices send standard PS/2 mouse packets for
-the DualPoint Stick. For non interleaved dualpoint devices the pointingstick
-buttons get reported separately in the PSM, PSR and PSL bits.
+the DualPoint Stick. The M, R and L bits signal the combined status of both
+the pointingstick and touchpad buttons, except for Dell dualpoint devices
+where the pointingstick buttons get reported separately in the PSM, PSR
+and PSL bits.
 
 Dualpoint device -- interleaved packet format
 ---------------------------------------------
diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt
index e63b446..13f888a 100644
--- a/Documentation/kbuild/makefiles.txt
+++ b/Documentation/kbuild/makefiles.txt
@@ -952,6 +952,14 @@
 	$(KBUILD_ARFLAGS) set by the top level Makefile to "D" (deterministic
 	mode) if this option is supported by $(AR).
 
+    ARCH_CPPFLAGS, ARCH_AFLAGS, ARCH_CFLAGS   Overrides the kbuild defaults
+
+	These variables are appended to the KBUILD_CPPFLAGS,
+	KBUILD_AFLAGS, and KBUILD_CFLAGS, respectively, after the
+	top-level Makefile has set any other flags. This provides a
+	means for an architecture to override the defaults.
+
+
 --- 6.2 Add prerequisites to archheaders:
 
 	The archheaders: rule is used to generate header files that
diff --git a/Documentation/power/swsusp.txt b/Documentation/power/swsusp.txt
index f732a83..8cc17ca 100644
--- a/Documentation/power/swsusp.txt
+++ b/Documentation/power/swsusp.txt
@@ -410,8 +410,17 @@
 
 Q: Can I suspend-to-disk using a swap partition under LVM?
 
-A: No. You can suspend successfully, but you'll not be able to
-resume. uswsusp should be able to work with LVM. See suspend.sf.net.
+A: Yes and No.  You can suspend successfully, but the kernel will not be able
+to resume on its own.  You need an initramfs that can recognize the resume
+situation, activate the logical volume containing the swap volume (but not
+touch any filesystems!), and eventually call
+
+echo -n "$major:$minor" > /sys/power/resume
+
+where $major and $minor are the respective major and minor device numbers of
+the swap volume.
+
+uswsusp works with LVM, too.  See http://suspend.sourceforge.net/
 
 Q: I upgraded the kernel from 2.6.15 to 2.6.16. Both kernels were
 compiled with the similar configuration files. Anyway I found that
diff --git a/Documentation/target/tcm_mod_builder.py b/Documentation/target/tcm_mod_builder.py
index 949de19..cda56df 100755
--- a/Documentation/target/tcm_mod_builder.py
+++ b/Documentation/target/tcm_mod_builder.py
@@ -199,7 +199,8 @@
 	buf += "#include <linux/string.h>\n"
 	buf += "#include <linux/configfs.h>\n"
 	buf += "#include <linux/ctype.h>\n"
-	buf += "#include <asm/unaligned.h>\n\n"
+	buf += "#include <asm/unaligned.h>\n"
+	buf += "#include <scsi/scsi_proto.h>\n\n"
 	buf += "#include <target/target_core_base.h>\n"
 	buf += "#include <target/target_core_fabric.h>\n"
 	buf += "#include <target/target_core_fabric_configfs.h>\n"
@@ -230,8 +231,14 @@
 	buf += "	}\n"
 	buf += "	tpg->" + fabric_mod_port + " = " + fabric_mod_port + ";\n"
 	buf += "	tpg->" + fabric_mod_port + "_tpgt = tpgt;\n\n"
-	buf += "	ret = core_tpg_register(&" + fabric_mod_name + "_ops, wwn,\n"
-	buf += "				&tpg->se_tpg, SCSI_PROTOCOL_SAS);\n"
+
+	if proto_ident == "FC":
+		buf += "	ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_FCP);\n"
+	elif proto_ident == "SAS":
+		buf += "	ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_SAS);\n"
+	elif proto_ident == "iSCSI":
+		buf += "	ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_ISCSI);\n"
+
 	buf += "	if (ret < 0) {\n"
 	buf += "		kfree(tpg);\n"
 	buf += "		return NULL;\n"
@@ -292,7 +299,7 @@
 
 	buf += "static const struct target_core_fabric_ops " + fabric_mod_name + "_ops = {\n"
 	buf += "	.module				= THIS_MODULE,\n"
-	buf += "	.name				= " + fabric_mod_name + ",\n"
+	buf += "	.name				= \"" + fabric_mod_name + "\",\n"
 	buf += "	.get_fabric_name		= " + fabric_mod_name + "_get_fabric_name,\n"
 	buf += "	.tpg_get_wwn			= " + fabric_mod_name + "_get_fabric_wwn,\n"
 	buf += "	.tpg_get_tag			= " + fabric_mod_name + "_get_tag,\n"
@@ -322,17 +329,17 @@
 	buf += "	.fabric_make_tpg		= " + fabric_mod_name + "_make_tpg,\n"
 	buf += "	.fabric_drop_tpg		= " + fabric_mod_name + "_drop_tpg,\n"
 	buf += "\n"
-	buf += "	.tfc_wwn_attrs			= " + fabric_mod_name + "_wwn_attrs;\n"
+	buf += "	.tfc_wwn_attrs			= " + fabric_mod_name + "_wwn_attrs,\n"
 	buf += "};\n\n"
 
 	buf += "static int __init " + fabric_mod_name + "_init(void)\n"
 	buf += "{\n"
-	buf += "	return target_register_template(" + fabric_mod_name + "_ops);\n"
+	buf += "	return target_register_template(&" + fabric_mod_name + "_ops);\n"
 	buf += "};\n\n"
 
 	buf += "static void __exit " + fabric_mod_name + "_exit(void)\n"
 	buf += "{\n"
-	buf += "	target_unregister_template(" + fabric_mod_name + "_ops);\n"
+	buf += "	target_unregister_template(&" + fabric_mod_name + "_ops);\n"
 	buf += "};\n\n"
 
 	buf += "MODULE_DESCRIPTION(\"" + fabric_mod_name.upper() + " series fabric driver\");\n"
diff --git a/MAINTAINERS b/MAINTAINERS
index 8133cef..569568f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -361,11 +361,11 @@
 F:	drivers/input/touchscreen/ad7879.c
 
 ADDRESS SPACE LAYOUT RANDOMIZATION (ASLR)
-M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jiri Kosina <jkosina@suse.com>
 S:	Maintained
 
 ADM1025 HARDWARE MONITOR DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/adm1025
@@ -430,7 +430,7 @@
 F:	drivers/macintosh/therm_adt746x.c
 
 ADT7475 HARDWARE MONITOR DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/adt7475
@@ -445,7 +445,7 @@
 
 ADVANSYS SCSI DRIVER
 M:	Matthew Wilcox <matthew@wil.cx>
-M:	Hannes Reinecke <hare@suse.de>
+M:	Hannes Reinecke <hare@suse.com>
 L:	linux-scsi@vger.kernel.org
 S:	Maintained
 F:	Documentation/scsi/advansys.txt
@@ -506,7 +506,7 @@
 F:	drivers/scsi/pcmcia/aha152x*
 
 AIC7XXX / AIC79XX SCSI DRIVER
-M:	Hannes Reinecke <hare@suse.de>
+M:	Hannes Reinecke <hare@suse.com>
 L:	linux-scsi@vger.kernel.org
 S:	Maintained
 F:	drivers/scsi/aic7xxx/
@@ -746,7 +746,7 @@
 F:	sound/aoa/
 
 APM DRIVER
-M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jiri Kosina <jkosina@suse.com>
 S:	Odd fixes
 F:	arch/x86/kernel/apm_32.c
 F:	include/linux/apm_bios.h
@@ -1001,6 +1001,7 @@
 M:	Baruch Siach <baruch@tkos.co.il>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
+F:	arch/arm/boot/dts/cx92755*
 N:	digicolor
 
 ARM/EBSA110 MACHINE SUPPORT
@@ -1324,7 +1325,7 @@
 F:	arch/arm/mach-pxa/palmtc.c
 
 ARM/PALM TREO SUPPORT
-M:	Tomas Cech <sleep_walker@suse.cz>
+M:	Tomas Cech <sleep_walker@suse.com>
 L:	linux-arm-kernel@lists.infradead.org
 W:	http://hackndev.com
 S:	Maintained
@@ -1614,6 +1615,7 @@
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/boot/dts/vexpress*
+F:	arch/arm64/boot/dts/arm/vexpress*
 F:	arch/arm/mach-vexpress/
 F:	*/*/vexpress*
 F:	*/*/*/vexpress*
@@ -2404,7 +2406,7 @@
 BTRFS FILE SYSTEM
 M:	Chris Mason <clm@fb.com>
 M:	Josef Bacik <jbacik@fb.com>
-M:	David Sterba <dsterba@suse.cz>
+M:	David Sterba <dsterba@suse.com>
 L:	linux-btrfs@vger.kernel.org
 W:	http://btrfs.wiki.kernel.org/
 Q:	http://patchwork.kernel.org/project/linux-btrfs/list/
@@ -2562,19 +2564,31 @@
 F:	arch/powerpc/oprofile/*cell*
 F:	arch/powerpc/platforms/cell/
 
-CEPH DISTRIBUTED FILE SYSTEM CLIENT
+CEPH COMMON CODE (LIBCEPH)
+M:	Ilya Dryomov <idryomov@gmail.com>
 M:	"Yan, Zheng" <zyan@redhat.com>
 M:	Sage Weil <sage@redhat.com>
 L:	ceph-devel@vger.kernel.org
 W:	http://ceph.com/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+T:	git git://github.com/ceph/ceph-client.git
 S:	Supported
-F:	Documentation/filesystems/ceph.txt
-F:	fs/ceph/
 F:	net/ceph/
 F:	include/linux/ceph/
 F:	include/linux/crush/
 
+CEPH DISTRIBUTED FILE SYSTEM CLIENT (CEPH)
+M:	"Yan, Zheng" <zyan@redhat.com>
+M:	Sage Weil <sage@redhat.com>
+M:	Ilya Dryomov <idryomov@gmail.com>
+L:	ceph-devel@vger.kernel.org
+W:	http://ceph.com/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+T:	git git://github.com/ceph/ceph-client.git
+S:	Supported
+F:	Documentation/filesystems/ceph.txt
+F:	fs/ceph/
+
 CERTIFIED WIRELESS USB (WUSB) SUBSYSTEM:
 L:	linux-usb@vger.kernel.org
 S:	Orphan
@@ -2735,7 +2749,7 @@
 M:	Julia Lawall <Julia.Lawall@lip6.fr>
 M:	Gilles Muller <Gilles.Muller@lip6.fr>
 M:	Nicolas Palix <nicolas.palix@imag.fr>
-M:	Michal Marek <mmarek@suse.cz>
+M:	Michal Marek <mmarek@suse.com>
 L:	cocci@systeme.lip6.fr (moderated for non-subscribers)
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git misc
 W:	http://coccinelle.lip6.fr/
@@ -2851,7 +2865,7 @@
 
 CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
 M:	Johannes Weiner <hannes@cmpxchg.org>
-M:	Michal Hocko <mhocko@suse.cz>
+M:	Michal Hocko <mhocko@kernel.org>
 L:	cgroups@vger.kernel.org
 L:	linux-mm@kvack.org
 S:	Maintained
@@ -2932,7 +2946,7 @@
 F:	arch/x86/kernel/msr.c
 
 CPU POWER MONITORING SUBSYSTEM
-M:	Thomas Renninger <trenn@suse.de>
+M:	Thomas Renninger <trenn@suse.com>
 L:	linux-pm@vger.kernel.org
 S:	Maintained
 F:	tools/power/cpupower/
@@ -3162,7 +3176,7 @@
 F:	drivers/net/ethernet/dec/tulip/dmfe.c
 
 DC390/AM53C974 SCSI driver
-M:	Hannes Reinecke <hare@suse.de>
+M:	Hannes Reinecke <hare@suse.com>
 L:	linux-scsi@vger.kernel.org
 S:	Maintained
 F:	drivers/scsi/am53c974.c
@@ -3366,7 +3380,7 @@
 S:	Maintained
 
 DISKQUOTA
-M:	Jan Kara <jack@suse.cz>
+M:	Jan Kara <jack@suse.com>
 S:	Maintained
 F:	Documentation/filesystems/quota.txt
 F:	fs/quota/
@@ -3422,7 +3436,7 @@
 F:	drivers/hwmon/dme1737.c
 
 DMI/SMBIOS SUPPORT
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 S:	Maintained
 T:	quilt http://jdelvare.nerim.net/devel/linux/jdelvare-dmi/
 F:	Documentation/ABI/testing/sysfs-firmware-dmi-tables
@@ -3573,6 +3587,15 @@
 F:	drivers/gpu/drm/rockchip/
 F:	Documentation/devicetree/bindings/video/rockchip*
 
+DRM DRIVERS FOR STI
+M:	Benjamin Gaignard <benjamin.gaignard@linaro.org>
+M:	Vincent Abriou <vincent.abriou@st.com>
+L:	dri-devel@lists.freedesktop.org
+T:	git http://git.linaro.org/people/benjamin.gaignard/kernel.git
+S:	Maintained
+F:	drivers/gpu/drm/sti
+F:	Documentation/devicetree/bindings/gpu/st,stih4xx.txt
+
 DSBR100 USB FM RADIO DRIVER
 M:	Alexey Klimov <klimov.linux@gmail.com>
 L:	linux-media@vger.kernel.org
@@ -4038,7 +4061,7 @@
 F:	drivers/of/of_net.c
 
 EXT2 FILE SYSTEM
-M:	Jan Kara <jack@suse.cz>
+M:	Jan Kara <jack@suse.com>
 L:	linux-ext4@vger.kernel.org
 S:	Maintained
 F:	Documentation/filesystems/ext2.txt
@@ -4046,7 +4069,7 @@
 F:	include/linux/ext2*
 
 EXT3 FILE SYSTEM
-M:	Jan Kara <jack@suse.cz>
+M:	Jan Kara <jack@suse.com>
 M:	Andrew Morton <akpm@linux-foundation.org>
 M:	Andreas Dilger <adilger.kernel@dilger.ca>
 L:	linux-ext4@vger.kernel.org
@@ -4096,7 +4119,7 @@
 F:	include/video/exynos_mipi*
 
 F71805F HARDWARE MONITORING DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/f71805f
@@ -4231,7 +4254,7 @@
 F:	drivers/block/rsxx/
 
 FLOPPY DRIVER
-M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jiri Kosina <jkosina@suse.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/floppy.git
 S:	Odd fixes
 F:	drivers/block/floppy.c
@@ -4652,7 +4675,7 @@
 
 H8/300 ARCHITECTURE
 M:	Yoshinori Sato <ysato@users.sourceforge.jp>
-L:	uclinux-h8-devel@lists.sourceforge.jp
+L:	uclinux-h8-devel@lists.sourceforge.jp (moderated for non-subscribers)
 W:	http://uclinux-h8.sourceforge.jp
 T:	git git://git.sourceforge.jp/gitroot/uclinux-h8/linux.git
 S:	Maintained
@@ -4699,7 +4722,7 @@
 F:	drivers/media/usb/hackrf/
 
 HARDWARE MONITORING
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	lm-sensors@lm-sensors.org
 W:	http://www.lm-sensors.org/
@@ -4802,7 +4825,7 @@
 F:	arch/*/include/asm/suspend*.h
 
 HID CORE LAYER
-M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jiri Kosina <jkosina@suse.com>
 L:	linux-input@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git
 S:	Maintained
@@ -4811,7 +4834,7 @@
 F:	include/uapi/linux/hid*
 
 HID SENSOR HUB DRIVERS
-M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jiri Kosina <jkosina@suse.com>
 M:	Jonathan Cameron <jic23@kernel.org>
 M:	Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
 L:	linux-input@vger.kernel.org
@@ -4945,7 +4968,7 @@
 F:	tools/hv/
 
 I2C OVER PARALLEL PORT
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	Documentation/i2c/busses/i2c-parport
@@ -4954,7 +4977,7 @@
 F:	drivers/i2c/busses/i2c-parport-light.c
 
 I2C/SMBUS CONTROLLER DRIVERS FOR PC
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	Documentation/i2c/busses/i2c-ali1535
@@ -4995,7 +5018,7 @@
 F:	Documentation/i2c/busses/i2c-ismt
 
 I2C/SMBUS STUB DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/i2c-stub.c
@@ -5022,7 +5045,7 @@
 S:	Maintained
 
 I2C-TAOS-EVM DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	Documentation/i2c/busses/i2c-taos-evm
@@ -5551,8 +5574,8 @@
 F:	net/netfilter/ipvs/
 
 IPWIRELESS DRIVER
-M:	Jiri Kosina <jkosina@suse.cz>
-M:	David Sterba <dsterba@suse.cz>
+M:	Jiri Kosina <jkosina@suse.com>
+M:	David Sterba <dsterba@suse.com>
 S:	Odd Fixes
 F:	drivers/tty/ipwireless/
 
@@ -5586,6 +5609,7 @@
 IRQCHIP DRIVERS
 M:	Thomas Gleixner <tglx@linutronix.de>
 M:	Jason Cooper <jason@lakedaemon.net>
+M:	Marc Zyngier <marc.zyngier@arm.com>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core
@@ -5594,11 +5618,14 @@
 F:	drivers/irqchip/
 
 IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY)
-M:	Benjamin Herrenschmidt <benh@kernel.crashing.org>
+M:	Jiang Liu <jiang.liu@linux.intel.com>
+M:	Marc Zyngier <marc.zyngier@arm.com>
 S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core
 F:	Documentation/IRQ-domain.txt
 F:	include/linux/irqdomain.h
 F:	kernel/irq/irqdomain.c
+F:	kernel/irq/msi.c
 
 ISAPNP
 M:	Jaroslav Kysela <perex@perex.cz>
@@ -5672,7 +5699,7 @@
 F:	drivers/isdn/hardware/eicon/
 
 IT87 HARDWARE MONITORING DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/it87
@@ -5739,7 +5766,7 @@
 
 JOURNALLING LAYER FOR BLOCK DEVICES (JBD)
 M:	Andrew Morton <akpm@linux-foundation.org>
-M:	Jan Kara <jack@suse.cz>
+M:	Jan Kara <jack@suse.com>
 L:	linux-ext4@vger.kernel.org
 S:	Maintained
 F:	fs/jbd/
@@ -5803,7 +5830,7 @@
 F:	fs/autofs4/
 
 KERNEL BUILD + files below scripts/ (unless maintained elsewhere)
-M:	Michal Marek <mmarek@suse.cz>
+M:	Michal Marek <mmarek@suse.com>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git for-next
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild.git rc-fixes
 L:	linux-kbuild@vger.kernel.org
@@ -5867,7 +5894,7 @@
 F:	arch/x86/kvm/svm.c
 
 KERNEL VIRTUAL MACHINE (KVM) FOR POWERPC
-M:	Alexander Graf <agraf@suse.de>
+M:	Alexander Graf <agraf@suse.com>
 L:	kvm-ppc@vger.kernel.org
 W:	http://kvm.qumranet.com
 T:	git git://github.com/agraf/linux-2.6.git
@@ -5885,7 +5912,6 @@
 F:	Documentation/s390/kvm.txt
 F:	arch/s390/include/asm/kvm*
 F:	arch/s390/kvm/
-F:	drivers/s390/kvm/
 
 KERNEL VIRTUAL MACHINE (KVM) FOR ARM
 M:	Christoffer Dall <christoffer.dall@linaro.org>
@@ -6024,7 +6050,7 @@
 F:	include/linux/leds.h
 
 LEGACY EEPROM DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 S:	Maintained
 F:	Documentation/misc-devices/eeprom
 F:	drivers/misc/eeprom/eeprom.c
@@ -6077,7 +6103,7 @@
 F:	include/linux/libata.h
 
 LIBATA PATA ARASAN COMPACT FLASH CONTROLLER
-M:	Viresh Kumar <viresh.linux@gmail.com>
+M:	Viresh Kumar <vireshk@kernel.org>
 L:	linux-ide@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tj/libata.git
 S:	Maintained
@@ -6147,6 +6173,7 @@
 Q:	https://patchwork.kernel.org/project/linux-nvdimm/list/
 S:	Supported
 F:	drivers/nvdimm/pmem.c
+F:	include/linux/pmem.h
 
 LINUX FOR IBM pSERIES (RS/6000)
 M:	Paul Mackerras <paulus@au.ibm.com>
@@ -6161,7 +6188,7 @@
 W:	http://www.penguinppc.org/
 L:	linuxppc-dev@lists.ozlabs.org
 Q:	http://patchwork.ozlabs.org/project/linuxppc-dev/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git
 S:	Supported
 F:	Documentation/powerpc/
 F:	arch/powerpc/
@@ -6237,8 +6264,8 @@
 LIVE PATCHING
 M:	Josh Poimboeuf <jpoimboe@redhat.com>
 M:	Seth Jennings <sjenning@redhat.com>
-M:	Jiri Kosina <jkosina@suse.cz>
-M:	Vojtech Pavlik <vojtech@suse.cz>
+M:	Jiri Kosina <jkosina@suse.com>
+M:	Vojtech Pavlik <vojtech@suse.com>
 S:	Maintained
 F:	kernel/livepatch/
 F:	include/linux/livepatch.h
@@ -6264,21 +6291,21 @@
 F:	drivers/hwmon/lm73.c
 
 LM78 HARDWARE MONITOR DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/lm78
 F:	drivers/hwmon/lm78.c
 
 LM83 HARDWARE MONITOR DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/lm83
 F:	drivers/hwmon/lm83.c
 
 LM90 HARDWARE MONITOR DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/lm90
@@ -6824,6 +6851,12 @@
 S:	Maintained
 F:	drivers/media/usb/msi2500/
 
+MSYSTEMS DISKONCHIP G3 MTD DRIVER
+M:	Robert Jarzmik <robert.jarzmik@free.fr>
+L:	linux-mtd@lists.infradead.org
+S:	Maintained
+F:	drivers/mtd/devices/docg3*
+
 MT9M032 APTINA SENSOR DRIVER
 M:	Laurent Pinchart <laurent.pinchart@ideasonboard.com>
 L:	linux-media@vger.kernel.org
@@ -7005,6 +7038,7 @@
 F:	net/*/netfilter.c
 F:	net/*/netfilter/
 F:	net/netfilter/
+F:	net/bridge/br_netfilter*.c
 
 NETLABEL
 M:	Paul Moore <paul@paul-moore.com>
@@ -7704,7 +7738,7 @@
 F:	drivers/char/pc8736x_gpio.c
 
 PC87427 HARDWARE MONITORING DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/pc87427
@@ -7981,7 +8015,7 @@
 F:	drivers/pinctrl/samsung/
 
 PIN CONTROLLER - ST SPEAR
-M:	Viresh Kumar <viresh.linux@gmail.com>
+M:	Viresh Kumar <vireshk@kernel.org>
 L:	spear-devel@list.st.com
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 W:	http://www.st.com/spear
@@ -7989,7 +8023,7 @@
 F:	drivers/pinctrl/spear/
 
 PKTCDVD DRIVER
-M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jiri Kosina <jkosina@suse.com>
 S:	Maintained
 F:	drivers/block/pktcdvd.c
 F:	include/linux/pktcdvd.h
@@ -8366,10 +8400,12 @@
 M:	Ilya Dryomov <idryomov@gmail.com>
 M:	Sage Weil <sage@redhat.com>
 M:	Alex Elder <elder@kernel.org>
-M:	ceph-devel@vger.kernel.org
+L:	ceph-devel@vger.kernel.org
 W:	http://ceph.com/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/sage/ceph-client.git
+T:	git git://github.com/ceph/ceph-client.git
 S:	Supported
+F:	Documentation/ABI/testing/sysfs-bus-rbd
 F:	drivers/block/rbd.c
 F:	drivers/block/rbd_types.h
 
@@ -8878,7 +8914,7 @@
 F:	drivers/tty/serial/
 
 SYNOPSYS DESIGNWARE DMAC DRIVER
-M:	Viresh Kumar <viresh.linux@gmail.com>
+M:	Viresh Kumar <vireshk@kernel.org>
 M:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 S:	Maintained
 F:	include/linux/dma/dw.h
@@ -9045,7 +9081,7 @@
 F:	drivers/mmc/host/sdhci-s3c*
 
 SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) ST SPEAR DRIVER
-M:	Viresh Kumar <viresh.linux@gmail.com>
+M:	Viresh Kumar <vireshk@kernel.org>
 L:	spear-devel@list.st.com
 L:	linux-mmc@vger.kernel.org
 S:	Maintained
@@ -9407,7 +9443,7 @@
 F:	drivers/hwmon/sch5627.c
 
 SMSC47B397 HARDWARE MONITOR DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	Documentation/hwmon/smsc47b397
@@ -9456,7 +9492,7 @@
 F:	drivers/media/pci/solo6x10/
 
 SOFTWARE RAID (Multiple Disks) SUPPORT
-M:	Neil Brown <neilb@suse.de>
+M:	Neil Brown <neilb@suse.com>
 L:	linux-raid@vger.kernel.org
 S:	Supported
 F:	drivers/md/
@@ -9499,7 +9535,7 @@
 
 SOUND
 M:	Jaroslav Kysela <perex@perex.cz>
-M:	Takashi Iwai <tiwai@suse.de>
+M:	Takashi Iwai <tiwai@suse.com>
 L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
 W:	http://www.alsa-project.org/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git
@@ -9583,7 +9619,7 @@
 F:	include/linux/compiler.h
 
 SPEAR PLATFORM SUPPORT
-M:	Viresh Kumar <viresh.linux@gmail.com>
+M:	Viresh Kumar <vireshk@kernel.org>
 M:	Shiraz Hashim <shiraz.linux.kernel@gmail.com>
 L:	spear-devel@list.st.com
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
@@ -9592,7 +9628,7 @@
 F:	arch/arm/mach-spear/
 
 SPEAR CLOCK FRAMEWORK SUPPORT
-M:	Viresh Kumar <viresh.linux@gmail.com>
+M:	Viresh Kumar <vireshk@kernel.org>
 L:	spear-devel@list.st.com
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 W:	http://www.st.com/spear
@@ -10382,7 +10418,7 @@
 
 TTY LAYER
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-M:	Jiri Slaby <jslaby@suse.cz>
+M:	Jiri Slaby <jslaby@suse.com>
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty.git
 F:	Documentation/serial/
@@ -10456,7 +10492,7 @@
 F:	arch/m68k/include/asm/*_no.*
 
 UDF FILESYSTEM
-M:	Jan Kara <jack@suse.cz>
+M:	Jan Kara <jack@suse.com>
 S:	Maintained
 F:	Documentation/filesystems/udf.txt
 F:	fs/udf/
@@ -10599,7 +10635,7 @@
 F:	include/linux/usb/gadget*
 
 USB HID/HIDBP DRIVERS (USB KEYBOARDS, MICE, REMOTE CONTROLS, ...)
-M:	Jiri Kosina <jkosina@suse.cz>
+M:	Jiri Kosina <jkosina@suse.com>
 L:	linux-usb@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jikos/hid.git
 S:	Maintained
@@ -10724,7 +10760,7 @@
 F:	drivers/usb/host/uhci*
 
 USB "USBNET" DRIVER FRAMEWORK
-M:	Oliver Neukum <oneukum@suse.de>
+M:	Oliver Neukum <oneukum@suse.com>
 L:	netdev@vger.kernel.org
 W:	http://www.linux-usb.org/usbnet
 S:	Maintained
@@ -10878,6 +10914,15 @@
 F:	include/linux/virtio_*.h
 F:	include/uapi/linux/virtio_*.h
 
+VIRTIO DRIVERS FOR S390
+M:	Christian Borntraeger <borntraeger@de.ibm.com>
+M:	Cornelia Huck <cornelia.huck@de.ibm.com>
+L:	linux-s390@vger.kernel.org
+L:	virtualization@lists.linux-foundation.org
+L:	kvm@vger.kernel.org
+S:	Supported
+F:	drivers/s390/virtio/
+
 VIRTIO GPU DRIVER
 M:	David Airlie <airlied@linux.ie>
 M:	Gerd Hoffmann <kraxel@redhat.com>
@@ -11051,7 +11096,7 @@
 F:	drivers/hwmon/w83793.c
 
 W83795 HARDWARE MONITORING DRIVER
-M:	Jean Delvare <jdelvare@suse.de>
+M:	Jean Delvare <jdelvare@suse.com>
 L:	lm-sensors@lm-sensors.org
 S:	Maintained
 F:	drivers/hwmon/w83795.c
diff --git a/Makefile b/Makefile
index 13270c0..246053f 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 2
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc8
 NAME = Hurr durr I'ma sheep
 
 # *DOCUMENTATION*
@@ -597,6 +597,11 @@
 # Defaults to vmlinux, but the arch makefile usually adds further targets
 all: vmlinux
 
+# The arch Makefile can set ARCH_{CPP,A,C}FLAGS to override the default
+# values of the respective KBUILD_* variables
+ARCH_CPPFLAGS :=
+ARCH_AFLAGS :=
+ARCH_CFLAGS :=
 include arch/$(SRCARCH)/Makefile
 
 KBUILD_CFLAGS	+= $(call cc-option,-fno-delete-null-pointer-checks,)
@@ -780,10 +785,11 @@
 include scripts/Makefile.kasan
 include scripts/Makefile.extrawarn
 
-# Add user supplied CPPFLAGS, AFLAGS and CFLAGS as the last assignments
-KBUILD_CPPFLAGS += $(KCPPFLAGS)
-KBUILD_AFLAGS += $(KAFLAGS)
-KBUILD_CFLAGS += $(KCFLAGS)
+# Add any arch overrides and user supplied CPPFLAGS, AFLAGS and CFLAGS as the
+# last assignments
+KBUILD_CPPFLAGS += $(ARCH_CPPFLAGS) $(KCPPFLAGS)
+KBUILD_AFLAGS   += $(ARCH_AFLAGS)   $(KAFLAGS)
+KBUILD_CFLAGS   += $(ARCH_CFLAGS)   $(KCFLAGS)
 
 # Use --build-id when available.
 LDFLAGS_BUILD_ID = $(patsubst -Wl$(comma)%,%,\
@@ -847,10 +853,10 @@
 mod_compress_cmd = true
 ifdef CONFIG_MODULE_COMPRESS
   ifdef CONFIG_MODULE_COMPRESS_GZIP
-    mod_compress_cmd = gzip -n
+    mod_compress_cmd = gzip -n -f
   endif # CONFIG_MODULE_COMPRESS_GZIP
   ifdef CONFIG_MODULE_COMPRESS_XZ
-    mod_compress_cmd = xz
+    mod_compress_cmd = xz -f
   endif # CONFIG_MODULE_COMPRESS_XZ
 endif # CONFIG_MODULE_COMPRESS
 export mod_compress_cmd
diff --git a/arch/Kconfig b/arch/Kconfig
index bec6666..8a8ea71 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -221,6 +221,10 @@
 config ARCH_THREAD_INFO_ALLOCATOR
 	bool
 
+# Select if arch wants to size task_struct dynamically via arch_task_struct_size:
+config ARCH_WANTS_DYNAMIC_TASK_STRUCT
+	bool
+
 config HAVE_REGS_AND_STACK_ACCESS_API
 	bool
 	help
diff --git a/arch/alpha/include/asm/Kbuild b/arch/alpha/include/asm/Kbuild
index cde23cd..ffd9cf5 100644
--- a/arch/alpha/include/asm/Kbuild
+++ b/arch/alpha/include/asm/Kbuild
@@ -5,6 +5,7 @@
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += preempt.h
 generic-y += sections.h
 generic-y += trace_clock.h
diff --git a/arch/alpha/include/asm/mm-arch-hooks.h b/arch/alpha/include/asm/mm-arch-hooks.h
deleted file mode 100644
index b07fd86..0000000
--- a/arch/alpha/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_ALPHA_MM_ARCH_HOOKS_H
-#define _ASM_ALPHA_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_ALPHA_MM_ARCH_HOOKS_H */
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index e7cee0a..bd4670d 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -115,6 +115,7 @@
 
 config ARC_CPU_750D
 	bool "ARC750D"
+	select ARC_CANT_LLSC
 	help
 	  Support for ARC750 core
 
@@ -312,11 +313,11 @@
 
 config ARC_PAGE_SIZE_16K
 	bool "16KB"
-	depends on ARC_MMU_V3
+	depends on ARC_MMU_V3 || ARC_MMU_V4
 
 config ARC_PAGE_SIZE_4K
 	bool "4KB"
-	depends on ARC_MMU_V3
+	depends on ARC_MMU_V3 || ARC_MMU_V4
 
 endchoice
 
@@ -362,7 +363,12 @@
 config ARC_HAS_LLSC
 	bool "Insn: LLOCK/SCOND (efficient atomic ops)"
 	default y
-	depends on !ARC_CPU_750D && !ARC_CANT_LLSC
+	depends on !ARC_CANT_LLSC
+
+config ARC_STAR_9000923308
+	bool "Workaround for llock/scond livelock"
+	default y
+	depends on ISA_ARCV2 && SMP && ARC_HAS_LLSC
 
 config ARC_HAS_SWAPE
 	bool "Insn: SWAPE (endian-swap)"
@@ -378,6 +384,10 @@
 	  dest operands with 2 possible source operands.
 	default y
 
+config ARC_HAS_DIV_REM
+	bool "Insn: div, divu, rem, remu"
+	default y
+
 config ARC_HAS_RTC
 	bool "Local 64-bit r/o cycle counter"
 	default n
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 6107062..8a27a48 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -36,8 +36,16 @@
 cflags-$(CONFIG_ARC_HAS_LLSC)		+= -mlock
 cflags-$(CONFIG_ARC_HAS_SWAPE)		+= -mswape
 
+ifdef CONFIG_ISA_ARCV2
+
 ifndef CONFIG_ARC_HAS_LL64
-cflags-$(CONFIG_ISA_ARCV2)		+= -mno-ll64
+cflags-y				+= -mno-ll64
+endif
+
+ifndef CONFIG_ARC_HAS_DIV_REM
+cflags-y				+= -mno-div-rem
+endif
+
 endif
 
 cflags-$(CONFIG_ARC_DW2_UNWIND)		+= -fasynchronous-unwind-tables
@@ -49,7 +57,8 @@
 
 ifndef CONFIG_CC_OPTIMIZE_FOR_SIZE
 # Generic build system uses -O2, we want -O3
-cflags-y  += -O3
+# Note: No need to add to cflags-y as that happens anyways
+ARCH_CFLAGS += -O3
 endif
 
 # small data is default for elf32 tool-chain. If not usable, disable it
diff --git a/arch/arc/boot/dts/axc003.dtsi b/arch/arc/boot/dts/axc003.dtsi
index 15c8d62..1cd5e82 100644
--- a/arch/arc/boot/dts/axc003.dtsi
+++ b/arch/arc/boot/dts/axc003.dtsi
@@ -12,7 +12,7 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <75000000>;
+	clock-frequency = <90000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/boot/dts/axc003_idu.dtsi b/arch/arc/boot/dts/axc003_idu.dtsi
index 199d428..2f0b332 100644
--- a/arch/arc/boot/dts/axc003_idu.dtsi
+++ b/arch/arc/boot/dts/axc003_idu.dtsi
@@ -12,7 +12,7 @@
 
 / {
 	compatible = "snps,arc";
-	clock-frequency = <75000000>;
+	clock-frequency = <90000000>;
 	#address-cells = <1>;
 	#size-cells = <1>;
 
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 1a80cc9..7611b10 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -22,6 +22,7 @@
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += param.h
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index 070f588..c8f57b8 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -89,11 +89,10 @@
 #define ECR_C_BIT_DTLB_LD_MISS		8
 #define ECR_C_BIT_DTLB_ST_MISS		9
 
-
 /* Auxiliary registers */
 #define AUX_IDENTITY		4
 #define AUX_INTR_VEC_BASE	0x25
-
+#define AUX_NON_VOL		0x5e
 
 /*
  * Floating Pt Registers
@@ -240,9 +239,9 @@
 
 struct bcr_perip {
 #ifdef CONFIG_CPU_BIG_ENDIAN
-	unsigned int start:8, pad2:8, sz:8, pad:8;
+	unsigned int start:8, pad2:8, sz:8, ver:8;
 #else
-	unsigned int pad:8, sz:8, pad2:8, start:8;
+	unsigned int ver:8, sz:8, pad2:8, start:8;
 #endif
 };
 
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 03484cb..87d18ae 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -23,33 +23,60 @@
 
 #define atomic_set(v, i) (((v)->counter) = (i))
 
-#ifdef CONFIG_ISA_ARCV2
-#define PREFETCHW	"	prefetchw   [%1]	\n"
-#else
-#define PREFETCHW
+#ifdef CONFIG_ARC_STAR_9000923308
+
+#define SCOND_FAIL_RETRY_VAR_DEF						\
+	unsigned int delay = 1, tmp;						\
+
+#define SCOND_FAIL_RETRY_ASM							\
+	"	bz	4f			\n"				\
+	"   ; --- scond fail delay ---		\n"				\
+	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
+	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
+	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
+	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
+	"	b	1b			\n"	/* start over */	\
+	"4: ; --- success ---			\n"				\
+
+#define SCOND_FAIL_RETRY_VARS							\
+	  ,[delay] "+&r" (delay),[tmp] "=&r"	(tmp)				\
+
+#else	/* !CONFIG_ARC_STAR_9000923308 */
+
+#define SCOND_FAIL_RETRY_VAR_DEF
+
+#define SCOND_FAIL_RETRY_ASM							\
+	"	bnz     1b			\n"				\
+
+#define SCOND_FAIL_RETRY_VARS
+
 #endif
 
 #define ATOMIC_OP(op, c_op, asm_op)					\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
-	unsigned int temp;						\
+	unsigned int val;				                \
+	SCOND_FAIL_RETRY_VAR_DEF                                        \
 									\
 	__asm__ __volatile__(						\
-	"1:				\n"				\
-	PREFETCHW							\
-	"	llock   %0, [%1]	\n"				\
-	"	" #asm_op " %0, %0, %2	\n"				\
-	"	scond   %0, [%1]	\n"				\
-	"	bnz     1b		\n"				\
-	: "=&r"(temp)	/* Early clobber, to prevent reg reuse */	\
-	: "r"(&v->counter), "ir"(i)					\
+	"1:	llock   %[val], [%[ctr]]		\n"		\
+	"	" #asm_op " %[val], %[val], %[i]	\n"		\
+	"	scond   %[val], [%[ctr]]		\n"		\
+	"						\n"		\
+	SCOND_FAIL_RETRY_ASM						\
+									\
+	: [val]	"=&r"	(val) /* Early clobber to prevent reg reuse */	\
+	  SCOND_FAIL_RETRY_VARS						\
+	: [ctr]	"r"	(&v->counter), /* Not "m": llock only supports reg direct addr mode */	\
+	  [i]	"ir"	(i)						\
 	: "cc");							\
 }									\
 
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
 static inline int atomic_##op##_return(int i, atomic_t *v)		\
 {									\
-	unsigned int temp;						\
+	unsigned int val;				                \
+	SCOND_FAIL_RETRY_VAR_DEF                                        \
 									\
 	/*								\
 	 * Explicit full memory barrier needed before/after as		\
@@ -58,19 +85,21 @@
 	smp_mb();							\
 									\
 	__asm__ __volatile__(						\
-	"1:				\n"				\
-	PREFETCHW							\
-	"	llock   %0, [%1]	\n"				\
-	"	" #asm_op " %0, %0, %2	\n"				\
-	"	scond   %0, [%1]	\n"				\
-	"	bnz     1b		\n"				\
-	: "=&r"(temp)							\
-	: "r"(&v->counter), "ir"(i)					\
+	"1:	llock   %[val], [%[ctr]]		\n"		\
+	"	" #asm_op " %[val], %[val], %[i]	\n"		\
+	"	scond   %[val], [%[ctr]]		\n"		\
+	"						\n"		\
+	SCOND_FAIL_RETRY_ASM						\
+									\
+	: [val]	"=&r"	(val)						\
+	  SCOND_FAIL_RETRY_VARS						\
+	: [ctr]	"r"	(&v->counter),					\
+	  [i]	"ir"	(i)						\
 	: "cc");							\
 									\
 	smp_mb();							\
 									\
-	return temp;							\
+	return val;							\
 }
 
 #else	/* !CONFIG_ARC_HAS_LLSC */
@@ -150,6 +179,9 @@
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
+#undef SCOND_FAIL_RETRY_VAR_DEF
+#undef SCOND_FAIL_RETRY_ASM
+#undef SCOND_FAIL_RETRY_VARS
 
 /**
  * __atomic_add_unless - add unless the number is a given value
diff --git a/arch/arc/include/asm/bitops.h b/arch/arc/include/asm/bitops.h
index 99fe118..57c1f33 100644
--- a/arch/arc/include/asm/bitops.h
+++ b/arch/arc/include/asm/bitops.h
@@ -50,8 +50,7 @@
 	 * done for const @nr, but no code is generated due to gcc	\
 	 * const prop.							\
 	 */								\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
+	nr &= 0x1f;							\
 									\
 	__asm__ __volatile__(						\
 	"1:	llock       %0, [%1]		\n"			\
@@ -82,8 +81,7 @@
 									\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
+	nr &= 0x1f;							\
 									\
 	/*								\
 	 * Explicit full memory barrier needed before/after as		\
@@ -129,16 +127,13 @@
 	unsigned long temp, flags;					\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	/*								\
 	 * spin lock/unlock provide the needed smp_mb() before/after	\
 	 */								\
 	bitops_lock(flags);						\
 									\
 	temp = *m;							\
-	*m = temp c_op (1UL << nr);					\
+	*m = temp c_op (1UL << (nr & 0x1f));					\
 									\
 	bitops_unlock(flags);						\
 }
@@ -149,17 +144,14 @@
 	unsigned long old, flags;					\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	bitops_lock(flags);						\
 									\
 	old = *m;							\
-	*m = old c_op (1 << nr);					\
+	*m = old c_op (1UL << (nr & 0x1f));				\
 									\
 	bitops_unlock(flags);						\
 									\
-	return (old & (1 << nr)) != 0;					\
+	return (old & (1UL << (nr & 0x1f))) != 0;			\
 }
 
 #endif /* CONFIG_ARC_HAS_LLSC */
@@ -174,11 +166,8 @@
 	unsigned long temp;						\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	temp = *m;							\
-	*m = temp c_op (1UL << nr);					\
+	*m = temp c_op (1UL << (nr & 0x1f));				\
 }
 
 #define __TEST_N_BIT_OP(op, c_op, asm_op)				\
@@ -187,13 +176,10 @@
 	unsigned long old;						\
 	m += nr >> 5;							\
 									\
-	if (__builtin_constant_p(nr))					\
-		nr &= 0x1f;						\
-									\
 	old = *m;							\
-	*m = old c_op (1 << nr);					\
+	*m = old c_op (1UL << (nr & 0x1f));				\
 									\
-	return (old & (1 << nr)) != 0;					\
+	return (old & (1UL << (nr & 0x1f))) != 0;			\
 }
 
 #define BIT_OPS(op, c_op, asm_op)					\
@@ -224,10 +210,7 @@
 
 	addr += nr >> 5;
 
-	if (__builtin_constant_p(nr))
-		nr &= 0x1f;
-
-	mask = 1 << nr;
+	mask = 1UL << (nr & 0x1f);
 
 	return ((mask & *addr) != 0);
 }
diff --git a/arch/arc/include/asm/futex.h b/arch/arc/include/asm/futex.h
index 05b5aaf..70cfe16 100644
--- a/arch/arc/include/asm/futex.h
+++ b/arch/arc/include/asm/futex.h
@@ -16,12 +16,15 @@
 #include <linux/uaccess.h>
 #include <asm/errno.h>
 
+#ifdef CONFIG_ARC_HAS_LLSC
+
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\
 							\
 	__asm__ __volatile__(				\
-	"1:	ld  %1, [%2]			\n"	\
+	"1:	llock	%1, [%2]		\n"	\
 		insn				"\n"	\
-	"2:	st  %0, [%2]			\n"	\
+	"2:	scond	%0, [%2]		\n"	\
+	"	bnz	1b			\n"	\
 	"	mov %0, 0			\n"	\
 	"3:					\n"	\
 	"	.section .fixup,\"ax\"		\n"	\
@@ -39,6 +42,33 @@
 	: "r" (uaddr), "r" (oparg), "ir" (-EFAULT)	\
 	: "cc", "memory")
 
+#else	/* !CONFIG_ARC_HAS_LLSC */
+
+#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)\
+							\
+	__asm__ __volatile__(				\
+	"1:	ld	%1, [%2]		\n"	\
+		insn				"\n"	\
+	"2:	st	%0, [%2]		\n"	\
+	"	mov %0, 0			\n"	\
+	"3:					\n"	\
+	"	.section .fixup,\"ax\"		\n"	\
+	"	.align  4			\n"	\
+	"4:	mov %0, %4			\n"	\
+	"	b   3b				\n"	\
+	"	.previous			\n"	\
+	"	.section __ex_table,\"a\"	\n"	\
+	"	.align  4			\n"	\
+	"	.word   1b, 4b			\n"	\
+	"	.word   2b, 4b			\n"	\
+	"	.previous			\n"	\
+							\
+	: "=&r" (ret), "=&r" (oldval)			\
+	: "r" (uaddr), "r" (oparg), "ir" (-EFAULT)	\
+	: "cc", "memory")
+
+#endif
+
 static inline int futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
 {
 	int op = (encoded_op >> 28) & 7;
@@ -123,11 +153,17 @@
 
 	pagefault_disable();
 
-	/* TBD : can use llock/scond */
 	__asm__ __volatile__(
-	"1:	ld    %0, [%3]	\n"
-	"	brne  %0, %1, 3f	\n"
-	"2:	st    %2, [%3]	\n"
+#ifdef CONFIG_ARC_HAS_LLSC
+	"1:	llock	%0, [%3]		\n"
+	"	brne	%0, %1, 3f		\n"
+	"2:	scond	%2, [%3]		\n"
+	"	bnz	1b			\n"
+#else
+	"1:	ld	%0, [%3]		\n"
+	"	brne	%0, %1, 3f		\n"
+	"2:	st	%2, [%3]		\n"
+#endif
 	"3:	\n"
 	"	.section .fixup,\"ax\"	\n"
 	"4:	mov %0, %4	\n"
diff --git a/arch/arc/include/asm/mm-arch-hooks.h b/arch/arc/include/asm/mm-arch-hooks.h
deleted file mode 100644
index c37541c..0000000
--- a/arch/arc/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_ARC_MM_ARCH_HOOKS_H
-#define _ASM_ARC_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_ARC_MM_ARCH_HOOKS_H */
diff --git a/arch/arc/include/asm/ptrace.h b/arch/arc/include/asm/ptrace.h
index 9175597..69095da 100644
--- a/arch/arc/include/asm/ptrace.h
+++ b/arch/arc/include/asm/ptrace.h
@@ -20,20 +20,20 @@
 struct pt_regs {
 
 	/* Real registers */
-	long bta;	/* bta_l1, bta_l2, erbta */
+	unsigned long bta;	/* bta_l1, bta_l2, erbta */
 
-	long lp_start, lp_end, lp_count;
+	unsigned long lp_start, lp_end, lp_count;
 
-	long status32;	/* status32_l1, status32_l2, erstatus */
-	long ret;	/* ilink1, ilink2 or eret */
-	long blink;
-	long fp;
-	long r26;	/* gp */
+	unsigned long status32;	/* status32_l1, status32_l2, erstatus */
+	unsigned long ret;	/* ilink1, ilink2 or eret */
+	unsigned long blink;
+	unsigned long fp;
+	unsigned long r26;	/* gp */
 
-	long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+	unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
 
-	long sp;	/* user/kernel sp depending on where we came from  */
-	long orig_r0;
+	unsigned long sp;	/* User/Kernel depending on where we came from */
+	unsigned long orig_r0;
 
 	/*
 	 * To distinguish bet excp, syscall, irq
@@ -55,13 +55,13 @@
 		unsigned long event;
 	};
 
-	long user_r25;
+	unsigned long user_r25;
 };
 #else
 
 struct pt_regs {
 
-	long orig_r0;
+	unsigned long orig_r0;
 
 	union {
 		struct {
@@ -76,26 +76,26 @@
 		unsigned long event;
 	};
 
-	long bta;	/* bta_l1, bta_l2, erbta */
+	unsigned long bta;	/* bta_l1, bta_l2, erbta */
 
-	long user_r25;
+	unsigned long user_r25;
 
-	long r26;	/* gp */
-	long fp;
-	long sp;	/* user/kernel sp depending on where we came from  */
+	unsigned long r26;	/* gp */
+	unsigned long fp;
+	unsigned long sp;	/* user/kernel sp depending on where we came from  */
 
-	long r12;
+	unsigned long r12;
 
 	/*------- Below list auto saved by h/w -----------*/
-	long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
+	unsigned long r0, r1, r2, r3, r4, r5, r6, r7, r8, r9, r10, r11;
 
-	long blink;
-	long lp_end, lp_start, lp_count;
+	unsigned long blink;
+	unsigned long lp_end, lp_start, lp_count;
 
-	long ei, ldi, jli;
+	unsigned long ei, ldi, jli;
 
-	long ret;
-	long status32;
+	unsigned long ret;
+	unsigned long status32;
 };
 
 #endif
@@ -103,7 +103,7 @@
 /* Callee saved registers - need to be saved only when you are scheduled out */
 
 struct callee_regs {
-	long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
+	unsigned long r25, r24, r23, r22, r21, r20, r19, r18, r17, r16, r15, r14, r13;
 };
 
 #define instruction_pointer(regs)	((regs)->ret)
@@ -142,7 +142,7 @@
 
 static inline long regs_return_value(struct pt_regs *regs)
 {
-	return regs->r0;
+	return (long)regs->r0;
 }
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/arc/include/asm/spinlock.h b/arch/arc/include/asm/spinlock.h
index e1651df..db8c59d 100644
--- a/arch/arc/include/asm/spinlock.h
+++ b/arch/arc/include/asm/spinlock.h
@@ -18,9 +18,518 @@
 #define arch_spin_unlock_wait(x) \
 	do { while (arch_spin_is_locked(x)) cpu_relax(); } while (0)
 
+#ifdef CONFIG_ARC_HAS_LLSC
+
+/*
+ * A normal LLOCK/SCOND based system, w/o need for livelock workaround
+ */
+#ifndef CONFIG_ARC_STAR_9000923308
+
 static inline void arch_spin_lock(arch_spinlock_t *lock)
 {
-	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
+	unsigned int val;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 1b	\n"	/* spin while LOCKED */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [slock]	"r"	(&(lock->slock)),
+	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+	unsigned int val, got_it = 0;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 4f	\n"	/* already LOCKED, just bail */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bnz	1b			\n"
+	"	mov	%[got_it], 1		\n"
+	"4:					\n"
+	"					\n"
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [slock]	"r"	(&(lock->slock)),
+	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+	smp_mb();
+
+	lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
+
+	smp_mb();
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
+ */
+
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * zero means writer holds the lock exclusively, deny Reader.
+	 * Otherwise grant lock to first/subseq reader
+	 *
+	 * 	if (rw->counter > 0) {
+	 *		rw->counter--;
+	 *		ret = 1;
+	 *	}
+	 */
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 1b\n"	/* <= 0: spin while write locked */
+	"	sub	%[val], %[val], 1	\n"	/* reader lock */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+	unsigned int val, got_it = 0;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 4f\n"	/* <= 0: already write locked, bail */
+	"	sub	%[val], %[val], 1	\n"	/* counter-- */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"	/* retry if collided with someone */
+	"	mov	%[got_it], 1		\n"
+	"					\n"
+	"4: ; --- done ---			\n"
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
+	 * deny writer. Otherwise if unlocked grant to writer
+	 * Hence the claim that Linux rwlocks are unfair to writers.
+	 * (can be starved for an indefinite time by readers).
+	 *
+	 *	if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) {
+	 *		rw->counter = 0;
+	 *		ret = 1;
+	 *	}
+	 */
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 1b	\n"	/* while !UNLOCKED spin */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+	unsigned int val, got_it = 0;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 4f	\n"	/* !UNLOCKED, bail */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"	/* retry if collided with someone */
+	"	mov	%[got_it], 1		\n"
+	"					\n"
+	"4: ; --- done ---			\n"
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * rw->counter++;
+	 */
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	add	%[val], %[val], 1	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter))
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	smp_mb();
+
+	rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
+
+	smp_mb();
+}
+
+#else	/* CONFIG_ARC_STAR_9000923308 */
+
+/*
+ * HS38x4 could get into a LLOCK/SCOND livelock in case of multiple overlapping
+ * coherency transactions in the SCU. The exclusive line state keeps rotating
+ * among contenting cores leading to a never ending cycle. So break the cycle
+ * by deferring the retry of failed exclusive access (SCOND). The actual delay
+ * needed is function of number of contending cores as well as the unrelated
+ * coherency traffic from other cores. To keep the code simple, start off with
+ * small delay of 1 which would suffice most cases and in case of contention
+ * double the delay. Eventually the delay is sufficient such that the coherency
+ * pipeline is drained, thus a subsequent exclusive access would succeed.
+ */
+
+#define SCOND_FAIL_RETRY_VAR_DEF						\
+	unsigned int delay, tmp;						\
+
+#define SCOND_FAIL_RETRY_ASM							\
+	"   ; --- scond fail delay ---		\n"				\
+	"	mov	%[tmp], %[delay]	\n"	/* tmp = delay */	\
+	"2: 	brne.d	%[tmp], 0, 2b		\n"	/* while (tmp != 0) */	\
+	"	sub	%[tmp], %[tmp], 1	\n"	/* tmp-- */		\
+	"	rol	%[delay], %[delay]	\n"	/* delay *= 2 */	\
+	"	b	1b			\n"	/* start over */	\
+	"					\n"				\
+	"4: ; --- done ---			\n"				\
+
+#define SCOND_FAIL_RETRY_VARS							\
+	  ,[delay] "=&r" (delay), [tmp] "=&r"	(tmp)				\
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+	unsigned int val;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 0b	\n"	/* spin while LOCKED */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bz	4f			\n"	/* done */
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val)
+	  SCOND_FAIL_RETRY_VARS
+	: [slock]	"r"	(&(lock->slock)),
+	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_spin_trylock(arch_spinlock_t *lock)
+{
+	unsigned int val, got_it = 0;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[slock]]	\n"
+	"	breq	%[val], %[LOCKED], 4f	\n"	/* already LOCKED, just bail */
+	"	scond	%[LOCKED], [%[slock]]	\n"	/* acquire */
+	"	bz.d	4f			\n"
+	"	mov.z	%[got_it], 1		\n"	/* got it */
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	  SCOND_FAIL_RETRY_VARS
+	: [slock]	"r"	(&(lock->slock)),
+	  [LOCKED]	"r"	(__ARCH_SPIN_LOCK_LOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_spin_unlock(arch_spinlock_t *lock)
+{
+	smp_mb();
+
+	lock->slock = __ARCH_SPIN_LOCK_UNLOCKED__;
+
+	smp_mb();
+}
+
+/*
+ * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
+ */
+
+static inline void arch_read_lock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	/*
+	 * zero means writer holds the lock exclusively, deny Reader.
+	 * Otherwise grant lock to first/subseq reader
+	 *
+	 * 	if (rw->counter > 0) {
+	 *		rw->counter--;
+	 *		ret = 1;
+	 *	}
+	 */
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 0b\n"	/* <= 0: spin while write locked */
+	"	sub	%[val], %[val], 1	\n"	/* reader lock */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bz	4f			\n"	/* done */
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val)
+	  SCOND_FAIL_RETRY_VARS
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_read_trylock(arch_rwlock_t *rw)
+{
+	unsigned int val, got_it = 0;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brls	%[val], %[WR_LOCKED], 4f\n"	/* <= 0: already write locked, bail */
+	"	sub	%[val], %[val], 1	\n"	/* counter-- */
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bz.d	4f			\n"
+	"	mov.z	%[got_it], 1		\n"	/* got it */
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	  SCOND_FAIL_RETRY_VARS
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_write_lock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	/*
+	 * If reader(s) hold lock (lock < __ARCH_RW_LOCK_UNLOCKED__),
+	 * deny writer. Otherwise if unlocked grant to writer
+	 * Hence the claim that Linux rwlocks are unfair to writers.
+	 * (can be starved for an indefinite time by readers).
+	 *
+	 *	if (rw->counter == __ARCH_RW_LOCK_UNLOCKED__) {
+	 *		rw->counter = 0;
+	 *		ret = 1;
+	 *	}
+	 */
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 0b	\n"	/* while !UNLOCKED spin */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bz	4f			\n"
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val)
+	  SCOND_FAIL_RETRY_VARS
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+/* 1 - lock taken successfully */
+static inline int arch_write_trylock(arch_rwlock_t *rw)
+{
+	unsigned int val, got_it = 0;
+	SCOND_FAIL_RETRY_VAR_DEF;
+
+	smp_mb();
+
+	__asm__ __volatile__(
+	"0:	mov	%[delay], 1		\n"
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	brne	%[val], %[UNLOCKED], 4f	\n"	/* !UNLOCKED, bail */
+	"	mov	%[val], %[WR_LOCKED]	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bz.d	4f			\n"
+	"	mov.z	%[got_it], 1		\n"	/* got it */
+	"					\n"
+	SCOND_FAIL_RETRY_ASM
+
+	: [val]		"=&r"	(val),
+	  [got_it]	"+&r"	(got_it)
+	  SCOND_FAIL_RETRY_VARS
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"ir"	(__ARCH_RW_LOCK_UNLOCKED__),
+	  [WR_LOCKED]	"ir"	(0)
+	: "memory", "cc");
+
+	smp_mb();
+
+	return got_it;
+}
+
+static inline void arch_read_unlock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * rw->counter++;
+	 */
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	add	%[val], %[val], 1	\n"
+	"	scond	%[val], [%[rwlock]]	\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter))
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+static inline void arch_write_unlock(arch_rwlock_t *rw)
+{
+	unsigned int val;
+
+	smp_mb();
+
+	/*
+	 * rw->counter = __ARCH_RW_LOCK_UNLOCKED__;
+	 */
+	__asm__ __volatile__(
+	"1:	llock	%[val], [%[rwlock]]	\n"
+	"	scond	%[UNLOCKED], [%[rwlock]]\n"
+	"	bnz	1b			\n"
+	"					\n"
+	: [val]		"=&r"	(val)
+	: [rwlock]	"r"	(&(rw->counter)),
+	  [UNLOCKED]	"r"	(__ARCH_RW_LOCK_UNLOCKED__)
+	: "memory", "cc");
+
+	smp_mb();
+}
+
+#undef SCOND_FAIL_RETRY_VAR_DEF
+#undef SCOND_FAIL_RETRY_ASM
+#undef SCOND_FAIL_RETRY_VARS
+
+#endif	/* CONFIG_ARC_STAR_9000923308 */
+
+#else	/* !CONFIG_ARC_HAS_LLSC */
+
+static inline void arch_spin_lock(arch_spinlock_t *lock)
+{
+	unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
 
 	/*
 	 * This smp_mb() is technically superfluous, we only need the one
@@ -33,7 +542,7 @@
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
 	"	breq  %0, %2, 1b	\n"
-	: "+&r" (tmp)
+	: "+&r" (val)
 	: "r"(&(lock->slock)), "ir"(__ARCH_SPIN_LOCK_LOCKED__)
 	: "memory");
 
@@ -48,26 +557,27 @@
 	smp_mb();
 }
 
+/* 1 - lock taken successfully */
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
 {
-	unsigned int tmp = __ARCH_SPIN_LOCK_LOCKED__;
+	unsigned int val = __ARCH_SPIN_LOCK_LOCKED__;
 
 	smp_mb();
 
 	__asm__ __volatile__(
 	"1:	ex  %0, [%1]		\n"
-	: "+r" (tmp)
+	: "+r" (val)
 	: "r"(&(lock->slock))
 	: "memory");
 
 	smp_mb();
 
-	return (tmp == __ARCH_SPIN_LOCK_UNLOCKED__);
+	return (val == __ARCH_SPIN_LOCK_UNLOCKED__);
 }
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-	unsigned int tmp = __ARCH_SPIN_LOCK_UNLOCKED__;
+	unsigned int val = __ARCH_SPIN_LOCK_UNLOCKED__;
 
 	/*
 	 * RELEASE barrier: given the instructions avail on ARCv2, full barrier
@@ -77,7 +587,7 @@
 
 	__asm__ __volatile__(
 	"	ex  %0, [%1]		\n"
-	: "+r" (tmp)
+	: "+r" (val)
 	: "r"(&(lock->slock))
 	: "memory");
 
@@ -90,19 +600,12 @@
 
 /*
  * Read-write spinlocks, allowing multiple readers but only one writer.
+ * Unfair locking as Writers could be starved indefinitely by Reader(s)
  *
  * The spinlock itself is contained in @counter and access to it is
  * serialized with @lock_mutex.
- *
- * Unfair locking as Writers could be starved indefinitely by Reader(s)
  */
 
-/* Would read_trylock() succeed? */
-#define arch_read_can_lock(x)	((x)->counter > 0)
-
-/* Would write_trylock() succeed? */
-#define arch_write_can_lock(x)	((x)->counter == __ARCH_RW_LOCK_UNLOCKED__)
-
 /* 1 - lock taken successfully */
 static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
@@ -173,6 +676,11 @@
 	arch_spin_unlock(&(rw->lock_mutex));
 }
 
+#endif
+
+#define arch_read_can_lock(x)	((x)->counter > 0)
+#define arch_write_can_lock(x)	((x)->counter == __ARCH_RW_LOCK_UNLOCKED__)
+
 #define arch_read_lock_flags(lock, flags)	arch_read_lock(lock)
 #define arch_write_lock_flags(lock, flags)	arch_write_lock(lock)
 
diff --git a/arch/arc/include/asm/spinlock_types.h b/arch/arc/include/asm/spinlock_types.h
index 662627c..4e1ef5f 100644
--- a/arch/arc/include/asm/spinlock_types.h
+++ b/arch/arc/include/asm/spinlock_types.h
@@ -26,7 +26,9 @@
  */
 typedef struct {
 	volatile unsigned int	counter;
+#ifndef CONFIG_ARC_HAS_LLSC
 	arch_spinlock_t		lock_mutex;
+#endif
 } arch_rwlock_t;
 
 #define __ARCH_RW_LOCK_UNLOCKED__	0x01000000
diff --git a/arch/arc/include/uapi/asm/ptrace.h b/arch/arc/include/uapi/asm/ptrace.h
index 76a7739..0b3ef63 100644
--- a/arch/arc/include/uapi/asm/ptrace.h
+++ b/arch/arc/include/uapi/asm/ptrace.h
@@ -32,20 +32,20 @@
 */
 struct user_regs_struct {
 
-	long pad;
+	unsigned long pad;
 	struct {
-		long bta, lp_start, lp_end, lp_count;
-		long status32, ret, blink, fp, gp;
-		long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
-		long sp;
+		unsigned long bta, lp_start, lp_end, lp_count;
+		unsigned long status32, ret, blink, fp, gp;
+		unsigned long r12, r11, r10, r9, r8, r7, r6, r5, r4, r3, r2, r1, r0;
+		unsigned long sp;
 	} scratch;
-	long pad2;
+	unsigned long pad2;
 	struct {
-		long r25, r24, r23, r22, r21, r20;
-		long r19, r18, r17, r16, r15, r14, r13;
+		unsigned long r25, r24, r23, r22, r21, r20;
+		unsigned long r19, r18, r17, r16, r15, r14, r13;
 	} callee;
-	long efa;	/* break pt addr, for break points in delay slots */
-	long stop_pc;	/* give dbg stop_pc after ensuring brkpt trap */
+	unsigned long efa;	/* break pt addr, for break points in delay slots */
+	unsigned long stop_pc;	/* give dbg stop_pc after ensuring brkpt trap */
 };
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/arc/kernel/intc-arcv2.c b/arch/arc/kernel/intc-arcv2.c
index 6208c63..26c1568 100644
--- a/arch/arc/kernel/intc-arcv2.c
+++ b/arch/arc/kernel/intc-arcv2.c
@@ -12,7 +12,6 @@
 #include <linux/of.h>
 #include <linux/irqdomain.h>
 #include <linux/irqchip.h>
-#include "../../drivers/irqchip/irqchip.h"
 #include <asm/irq.h>
 
 /*
diff --git a/arch/arc/kernel/intc-compact.c b/arch/arc/kernel/intc-compact.c
index fcdddb6..039fac3 100644
--- a/arch/arc/kernel/intc-compact.c
+++ b/arch/arc/kernel/intc-compact.c
@@ -12,7 +12,6 @@
 #include <linux/of.h>
 #include <linux/irqdomain.h>
 #include <linux/irqchip.h>
-#include "../../drivers/irqchip/irqchip.h"
 #include <asm/irq.h>
 
 /*
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index 30284e8..2fb8658 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -175,7 +175,6 @@
 #include <linux/irqchip.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
-#include "../../drivers/irqchip/irqchip.h"
 
 /*
  * Set the DEST for @cmn_irq to @cpu_mask (1 bit per core)
@@ -218,11 +217,28 @@
 	raw_spin_unlock_irqrestore(&mcip_lock, flags);
 }
 
+#ifdef CONFIG_SMP
 static int
-idu_irq_set_affinity(struct irq_data *d, const struct cpumask *cpumask, bool f)
+idu_irq_set_affinity(struct irq_data *data, const struct cpumask *cpumask,
+		     bool force)
 {
+	unsigned long flags;
+	cpumask_t online;
+
+	/* errout if no online cpu per @cpumask */
+	if (!cpumask_and(&online, cpumask, cpu_online_mask))
+		return -EINVAL;
+
+	raw_spin_lock_irqsave(&mcip_lock, flags);
+
+	idu_set_dest(data->hwirq, cpumask_bits(&online)[0]);
+	idu_set_mode(data->hwirq, IDU_M_TRIG_LEVEL, IDU_M_DISTRI_RR);
+
+	raw_spin_unlock_irqrestore(&mcip_lock, flags);
+
 	return IRQ_SET_MASK_OK;
 }
+#endif
 
 static struct irq_chip idu_irq_chip = {
 	.name			= "MCIP IDU Intc",
@@ -330,8 +346,7 @@
 		if (!i)
 			idu_first_irq = irq;
 
-		irq_set_handler_data(irq, domain);
-		irq_set_chained_handler(irq, idu_cascade_isr);
+		irq_set_chained_handler_and_data(irq, idu_cascade_isr, domain);
 	}
 
 	__mcip_cmd(CMD_IDU_ENABLE, 0);
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index a3d1862..cabde9d 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -47,6 +47,7 @@
 	struct bcr_perip uncached_space;
 	struct bcr_generic bcr;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
+	unsigned long perip_space;
 	FIX_PTR(cpu);
 
 	READ_BCR(AUX_IDENTITY, cpu->core);
@@ -56,7 +57,12 @@
 	cpu->vec_base = read_aux_reg(AUX_INTR_VEC_BASE);
 
 	READ_BCR(ARC_REG_D_UNCACH_BCR, uncached_space);
-	BUG_ON((uncached_space.start << 24) != ARC_UNCACHED_ADDR_SPACE);
+        if (uncached_space.ver < 3)
+		perip_space = uncached_space.start << 24;
+	else
+		perip_space = read_aux_reg(AUX_NON_VOL) & 0xF0000000;
+
+	BUG_ON(perip_space != ARC_UNCACHED_ADDR_SPACE);
 
 	READ_BCR(ARC_REG_MUL_BCR, cpu->extn_mpy);
 
@@ -142,17 +148,22 @@
 }
 
 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},
-	{ {0x50, "ARC HS38"	}, 0x51},
+#else
+	{ {0x50, "ARC HS38 R2.0"}, 0x51},
+	{ {0x52, "ARC HS38 R2.1"}, 0x52},
+#endif
 	{ {0x00, NULL		} }
 };
 
-#define IS_AVAIL1(v, str)	((v) ? str : "")
-#define IS_USED(cfg)		(IS_ENABLED(cfg) ? "" : "(not used) ")
-#define IS_AVAIL2(v, str, cfg)  IS_AVAIL1(v, str), IS_AVAIL1(v, IS_USED(cfg))
+#define IS_AVAIL1(v, s)		((v) ? s : "")
+#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))
 
 static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 {
@@ -226,7 +237,7 @@
 			n += scnprintf(buf + n, len - n, "mpy[opt %d] ", opt);
 		}
 		n += scnprintf(buf + n, len - n, "%s",
-			       IS_USED(CONFIG_ARC_HAS_HW_MPY));
+			       IS_USED_CFG(CONFIG_ARC_HAS_HW_MPY));
 	}
 
 	n += scnprintf(buf + n, len - n, "%s%s%s%s%s%s%s%s\n",
@@ -325,6 +336,10 @@
 		pr_warn("CONFIG_ARC_FPU_SAVE_RESTORE needed for working apps\n");
 	else if (!cpu->extn.fpu_dp && fpu_enabled)
 		panic("FPU non-existent, disable CONFIG_ARC_FPU_SAVE_RESTORE\n");
+
+	if (is_isa_arcv2() && IS_ENABLED(CONFIG_SMP) && cpu->isa.atomic &&
+	    !IS_ENABLED(CONFIG_ARC_STAR_9000923308))
+		panic("llock/scond livelock workaround missing\n");
 }
 
 /*
diff --git a/arch/arc/kernel/time.c b/arch/arc/kernel/time.c
index 3364d2b..4294761 100644
--- a/arch/arc/kernel/time.c
+++ b/arch/arc/kernel/time.c
@@ -203,34 +203,24 @@
 	return 0;
 }
 
-static void arc_clkevent_set_mode(enum clock_event_mode mode,
-				  struct clock_event_device *dev)
+static int arc_clkevent_set_periodic(struct clock_event_device *dev)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_PERIODIC:
-                /*
-                 * At X Hz, 1 sec = 1000ms -> X cycles;
-                 *                    10ms -> X / 100 cycles
-                 */
-		arc_timer_event_setup(arc_get_core_freq() / HZ);
-		break;
-	case CLOCK_EVT_MODE_ONESHOT:
-		break;
-	default:
-		break;
-	}
-
-	return;
+	/*
+	 * At X Hz, 1 sec = 1000ms -> X cycles;
+	 *		      10ms -> X / 100 cycles
+	 */
+	arc_timer_event_setup(arc_get_core_freq() / HZ);
+	return 0;
 }
 
 static DEFINE_PER_CPU(struct clock_event_device, arc_clockevent_device) = {
-	.name		= "ARC Timer0",
-	.features	= CLOCK_EVT_FEAT_ONESHOT | CLOCK_EVT_FEAT_PERIODIC,
-	.mode		= CLOCK_EVT_MODE_UNUSED,
-	.rating		= 300,
-	.irq		= TIMER0_IRQ,	/* hardwired, no need for resources */
-	.set_next_event = arc_clkevent_set_next_event,
-	.set_mode	= arc_clkevent_set_mode,
+	.name			= "ARC Timer0",
+	.features		= CLOCK_EVT_FEAT_ONESHOT |
+				  CLOCK_EVT_FEAT_PERIODIC,
+	.rating			= 300,
+	.irq			= TIMER0_IRQ,	/* hardwired, no need for resources */
+	.set_next_event		= arc_clkevent_set_next_event,
+	.set_state_periodic	= arc_clkevent_set_periodic,
 };
 
 static irqreturn_t timer_irq_handler(int irq, void *dev_id)
@@ -240,7 +230,7 @@
 	 * irq_set_chip_and_handler() asked for handle_percpu_devid_irq()
 	 */
 	struct clock_event_device *evt = this_cpu_ptr(&arc_clockevent_device);
-	int irq_reenable = evt->mode == CLOCK_EVT_MODE_PERIODIC;
+	int irq_reenable = clockevent_state_periodic(evt);
 
 	/*
 	 * Any write to CTRL reg ACks the interrupt, we rewrite the
diff --git a/arch/arc/kernel/troubleshoot.c b/arch/arc/kernel/troubleshoot.c
index 807f7d6..a6f91e8 100644
--- a/arch/arc/kernel/troubleshoot.c
+++ b/arch/arc/kernel/troubleshoot.c
@@ -58,7 +58,6 @@
 
 static void print_task_path_n_nm(struct task_struct *tsk, char *buf)
 {
-	struct path path;
 	char *path_nm = NULL;
 	struct mm_struct *mm;
 	struct file *exe_file;
diff --git a/arch/arc/lib/memcpy-archs.S b/arch/arc/lib/memcpy-archs.S
index 1b2b3ac..0cab0b8 100644
--- a/arch/arc/lib/memcpy-archs.S
+++ b/arch/arc/lib/memcpy-archs.S
@@ -206,7 +206,7 @@
 	ld.ab	r6, [r1, 4]
 	prefetch [r1, 28]	;Prefetch the next read location
 	ld.ab	r8, [r1,4]
-	prefetch [r3, 32]	;Prefetch the next write location
+	prefetchw [r3, 32]	;Prefetch the next write location
 
 	SHIFT_1	(r7, r6, 8)
 	or	r7, r7, r5
diff --git a/arch/arc/lib/memset-archs.S b/arch/arc/lib/memset-archs.S
index 92d573c..365b183 100644
--- a/arch/arc/lib/memset-archs.S
+++ b/arch/arc/lib/memset-archs.S
@@ -10,12 +10,6 @@
 
 #undef PREALLOC_NOT_AVAIL
 
-#ifdef PREALLOC_NOT_AVAIL
-#define PREWRITE(A,B)	prefetchw [(A),(B)]
-#else
-#define PREWRITE(A,B)	prealloc [(A),(B)]
-#endif
-
 ENTRY(memset)
 	prefetchw [r0]		; Prefetch the write location
 	mov.f	0, r2
@@ -51,9 +45,15 @@
 
 ;;; Convert len to Dwords, unfold x8
 	lsr.f	lp_count, lp_count, 6
+
 	lpnz	@.Lset64bytes
 	;; LOOP START
-	PREWRITE(r3, 64)	;Prefetch the next write location
+#ifdef PREALLOC_NOT_AVAIL
+	prefetchw [r3, 64]	;Prefetch the next write location
+#else
+	prealloc  [r3, 64]
+#endif
+#ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
@@ -62,16 +62,45 @@
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
+#else
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+#endif
 .Lset64bytes:
 
 	lsr.f	lp_count, r2, 5 ;Last remaining  max 124 bytes
 	lpnz	.Lset32bytes
 	;; LOOP START
 	prefetchw   [r3, 32]	;Prefetch the next write location
+#ifdef CONFIG_ARC_HAS_LL64
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
 	std.ab	r4, [r3, 8]
+#else
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+	st.ab	r4, [r3, 4]
+#endif
 .Lset32bytes:
 
 	and.f	lp_count, r2, 0x1F ;Last remaining 31 bytes
diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c
index b29d62e..1cd6695 100644
--- a/arch/arc/mm/cache.c
+++ b/arch/arc/mm/cache.c
@@ -468,10 +468,18 @@
 noinline void slc_op(unsigned long paddr, unsigned long sz, const int op)
 {
 #ifdef CONFIG_ISA_ARCV2
+	/*
+	 * SLC is shared between all cores and concurrent aux operations from
+	 * multiple cores need to be serialized using a spinlock
+	 * A concurrent operation can be silently ignored and/or the old/new
+	 * operation can remain incomplete forever (lockup in SLC_CTRL_BUSY loop
+	 * below)
+	 */
+	static DEFINE_SPINLOCK(lock);
 	unsigned long flags;
 	unsigned int ctrl;
 
-	local_irq_save(flags);
+	spin_lock_irqsave(&lock, flags);
 
 	/*
 	 * The Region Flush operation is specified by CTRL.RGN_OP[11..9]
@@ -504,7 +512,7 @@
 
 	while (read_aux_reg(ARC_REG_SLC_CTRL) & SLC_CTRL_BUSY);
 
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&lock, flags);
 #endif
 }
 
diff --git a/arch/arc/mm/dma.c b/arch/arc/mm/dma.c
index 74a637a..57706a9 100644
--- a/arch/arc/mm/dma.c
+++ b/arch/arc/mm/dma.c
@@ -60,8 +60,8 @@
 
 	/* This is kernel Virtual address (0x7000_0000 based) */
 	kvaddr = ioremap_nocache((unsigned long)paddr, size);
-	if (kvaddr != NULL)
-		memset(kvaddr, 0, size);
+	if (kvaddr == NULL)
+		return NULL;
 
 	/* This is bus address, platform dependent */
 	*dma_handle = (dma_addr_t)paddr;
diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c
index 99f7da5..e7769c3 100644
--- a/arch/arc/plat-axs10x/axs10x.c
+++ b/arch/arc/plat-axs10x/axs10x.c
@@ -389,6 +389,21 @@
 
 static void __init axs103_early_init(void)
 {
+	/*
+	 * AXS103 configurations for SMP/QUAD configurations share device tree
+	 * which defaults to 90 MHz. However recent failures of Quad config
+	 * revealed P&R timing violations so clamp it down to safe 50 MHz
+	 * Instead of duplicating defconfig/DT for SMP/QUAD, add a small hack
+	 *
+	 * This hack is really hacky as of now. Fix it properly by getting the
+	 * number of cores as return value of platform's early SMP callback
+	 */
+#ifdef CONFIG_ARC_MCIP
+	unsigned int num_cores = (read_aux_reg(ARC_REG_MCIP_BCR) >> 16) & 0x3F;
+	if (num_cores > 2)
+		arc_set_core_freq(50 * 1000000);
+#endif
+
 	switch (arc_get_core_freq()/1000000) {
 	case 33:
 		axs103_set_freq(1, 1, 1);
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index a750c14..1c50210 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1693,6 +1693,12 @@
 config HIGHPTE
 	bool "Allocate 2nd-level pagetables from highmem"
 	depends on HIGHMEM
+	help
+	  The VM uses one page of physical memory for each page table.
+	  For systems with a lot of processes, this can use a lot of
+	  precious low memory, eventually leading to low memory being
+	  consumed by page tables.  Setting this option will allow
+	  user-space 2nd level page tables to reside in high memory.
 
 config HW_PERF_EVENTS
 	bool "Enable hardware performance counter support for perf events"
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index f1b1579..a2e16f9 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -1635,7 +1635,7 @@
 
 config DEBUG_SET_MODULE_RONX
 	bool "Set loadable kernel module data as NX and text as RO"
-	depends on MODULES
+	depends on MODULES && MMU
 	---help---
 	  This option helps catch unintended modifications to loadable
 	  kernel module's text and read-only data. It also prevents execution
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 07ab3d2..7451b44 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -312,6 +312,9 @@
 
 PHONY += bzImage $(BOOT_TARGETS) $(INSTALL_TARGETS)
 
+bootpImage uImage: zImage
+zImage: Image
+
 $(BOOT_TARGETS): vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) MACHINE=$(MACHINE) $(boot)/$@
 
diff --git a/arch/arm/boot/dts/am335x-boneblack.dts b/arch/arm/boot/dts/am335x-boneblack.dts
index 901739f..5c42d25 100644
--- a/arch/arm/boot/dts/am335x-boneblack.dts
+++ b/arch/arm/boot/dts/am335x-boneblack.dts
@@ -80,3 +80,7 @@
 		status = "okay";
 	};
 };
+
+&rtc {
+	system-power-controller;
+};
diff --git a/arch/arm/boot/dts/am335x-pepper.dts b/arch/arm/boot/dts/am335x-pepper.dts
index 0d35ab6..7106114 100644
--- a/arch/arm/boot/dts/am335x-pepper.dts
+++ b/arch/arm/boot/dts/am335x-pepper.dts
@@ -74,6 +74,7 @@
 	audio_codec: tlv320aic3106@1b {
 		compatible = "ti,tlv320aic3106";
 		reg = <0x1b>;
+		ai3x-micbias-vg = <0x2>;
 	};
 
 	accel: lis331dlh@1d {
@@ -153,7 +154,7 @@
 	ti,audio-routing =
 		"Headphone Jack",	"HPLOUT",
 		"Headphone Jack",	"HPROUT",
-		"LINE1L",		"Line In";
+		"MIC3L",		"Mic3L Switch";
 };
 
 &mcasp0 {
@@ -438,41 +439,50 @@
 	regulators {
 		dcdc1_reg: regulator@0 {
 			/* VDD_1V8 system supply */
+			regulator-always-on;
 		};
 
 		dcdc2_reg: regulator@1 {
 			/* VDD_CORE voltage limits 0.95V - 1.26V with +/-4% tolerance */
 			regulator-name = "vdd_core";
 			regulator-min-microvolt = <925000>;
-			regulator-max-microvolt = <1325000>;
+			regulator-max-microvolt = <1150000>;
 			regulator-boot-on;
+			regulator-always-on;
 		};
 
 		dcdc3_reg: regulator@2 {
 			/* VDD_MPU voltage limits 0.95V - 1.1V with +/-4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <925000>;
-			regulator-max-microvolt = <1150000>;
+			regulator-max-microvolt = <1325000>;
 			regulator-boot-on;
+			regulator-always-on;
 		};
 
 		ldo1_reg: regulator@3 {
 			/* VRTC 1.8V always-on supply */
+			regulator-name = "vrtc,vdds";
 			regulator-always-on;
 		};
 
 		ldo2_reg: regulator@4 {
 			/* 3.3V rail */
+			regulator-name = "vdd_3v3aux";
+			regulator-always-on;
 		};
 
 		ldo3_reg: regulator@5 {
 			/* VDD_3V3A 3.3V rail */
+			regulator-name = "vdd_3v3a";
 			regulator-min-microvolt = <3300000>;
 			regulator-max-microvolt = <3300000>;
 		};
 
 		ldo4_reg: regulator@6 {
 			/* VDD_3V3B 3.3V rail */
+			regulator-name = "vdd_3v3b";
+			regulator-always-on;
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index c80a3e2..ade28c79 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -132,6 +132,12 @@
 			};
 		};
 
+		emif: emif@4c000000 {
+			compatible = "ti,emif-am4372";
+			reg = <0x4c000000 0x1000000>;
+			ti,hwmods = "emif";
+		};
+
 		edma: edma@49000000 {
 			compatible = "ti,edma3";
 			ti,hwmods = "tpcc", "tptc0", "tptc1", "tptc2";
@@ -941,6 +947,7 @@
 				ti,hwmods = "dss_rfbi";
 				clocks = <&disp_clk>;
 				clock-names = "fck";
+				status = "disabled";
 			};
 		};
 
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts
index a42cc37..a63bf78 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15.dts
+++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts
@@ -605,6 +605,10 @@
 	phy-supply = <&ldousb_reg>;
 };
 
+&usb2_phy2 {
+	phy-supply = <&ldousb_reg>;
+};
+
 &usb1 {
 	dr_mode = "host";
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/atlas7.dtsi b/arch/arm/boot/dts/atlas7.dtsi
index 5dfd3a4..3e21311 100644
--- a/arch/arm/boot/dts/atlas7.dtsi
+++ b/arch/arm/boot/dts/atlas7.dtsi
@@ -135,6 +135,1025 @@
 			compatible = "sirf,atlas7-ioc";
 			reg = <0x18880000 0x1000>,
 				<0x10E40000 0x1000>;
+
+			audio_ac97_pmx: audio_ac97@0 {
+				audio_ac97 {
+					groups = "audio_ac97_grp";
+					function = "audio_ac97";
+				};
+			};
+
+			audio_func_dbg_pmx: audio_func_dbg@0 {
+				audio_func_dbg {
+					groups = "audio_func_dbg_grp";
+					function = "audio_func_dbg";
+				};
+			};
+
+			audio_i2s_pmx: audio_i2s@0 {
+				audio_i2s {
+					groups = "audio_i2s_grp";
+					function = "audio_i2s";
+				};
+			};
+
+			audio_i2s_2ch_pmx: audio_i2s_2ch@0 {
+				audio_i2s_2ch {
+					groups = "audio_i2s_2ch_grp";
+					function = "audio_i2s_2ch";
+				};
+			};
+
+			audio_i2s_extclk_pmx: audio_i2s_extclk@0 {
+				audio_i2s_extclk {
+					groups = "audio_i2s_extclk_grp";
+					function = "audio_i2s_extclk";
+				};
+			};
+
+			audio_uart0_pmx: audio_uart0@0 {
+				audio_uart0 {
+					groups = "audio_uart0_grp";
+					function = "audio_uart0";
+				};
+			};
+
+			audio_uart1_pmx: audio_uart1@0 {
+				audio_uart1 {
+					groups = "audio_uart1_grp";
+					function = "audio_uart1";
+				};
+			};
+
+			audio_uart2_pmx0: audio_uart2@0 {
+				audio_uart2_0 {
+					groups = "audio_uart2_grp0";
+					function = "audio_uart2_m0";
+				};
+			};
+
+			audio_uart2_pmx1: audio_uart2@1 {
+				audio_uart2_1 {
+					groups = "audio_uart2_grp1";
+					function = "audio_uart2_m1";
+				};
+			};
+
+			c_can_trnsvr_pmx: c_can_trnsvr@0 {
+				c_can_trnsvr {
+					groups = "c_can_trnsvr_grp";
+					function = "c_can_trnsvr";
+				};
+			};
+
+			c0_can_pmx0: c0_can@0 {
+				c0_can_0 {
+					groups = "c0_can_grp0";
+					function = "c0_can_m0";
+				};
+			};
+
+			c0_can_pmx1: c0_can@1 {
+				c0_can_1 {
+					groups = "c0_can_grp1";
+					function = "c0_can_m1";
+				};
+			};
+
+			c1_can_pmx0: c1_can@0 {
+				c1_can_0 {
+					groups = "c1_can_grp0";
+					function = "c1_can_m0";
+				};
+			};
+
+			c1_can_pmx1: c1_can@1 {
+				c1_can_1 {
+					groups = "c1_can_grp1";
+					function = "c1_can_m1";
+				};
+			};
+
+			c1_can_pmx2: c1_can@2 {
+				c1_can_2 {
+					groups = "c1_can_grp2";
+					function = "c1_can_m2";
+				};
+			};
+
+			ca_audio_lpc_pmx: ca_audio_lpc@0 {
+				ca_audio_lpc {
+					groups = "ca_audio_lpc_grp";
+					function = "ca_audio_lpc";
+				};
+			};
+
+			ca_bt_lpc_pmx: ca_bt_lpc@0 {
+				ca_bt_lpc {
+					groups = "ca_bt_lpc_grp";
+					function = "ca_bt_lpc";
+				};
+			};
+
+			ca_coex_pmx: ca_coex@0 {
+				ca_coex {
+					groups = "ca_coex_grp";
+					function = "ca_coex";
+				};
+			};
+
+			ca_curator_lpc_pmx: ca_curator_lpc@0 {
+				ca_curator_lpc {
+					groups = "ca_curator_lpc_grp";
+					function = "ca_curator_lpc";
+				};
+			};
+
+			ca_pcm_debug_pmx: ca_pcm_debug@0 {
+				ca_pcm_debug {
+					groups = "ca_pcm_debug_grp";
+					function = "ca_pcm_debug";
+				};
+			};
+
+			ca_pio_pmx: ca_pio@0 {
+				ca_pio {
+					groups = "ca_pio_grp";
+					function = "ca_pio";
+				};
+			};
+
+			ca_sdio_debug_pmx: ca_sdio_debug@0 {
+				ca_sdio_debug {
+					groups = "ca_sdio_debug_grp";
+					function = "ca_sdio_debug";
+				};
+			};
+
+			ca_spi_pmx: ca_spi@0 {
+				ca_spi {
+					groups = "ca_spi_grp";
+					function = "ca_spi";
+				};
+			};
+
+			ca_trb_pmx: ca_trb@0 {
+				ca_trb {
+					groups = "ca_trb_grp";
+					function = "ca_trb";
+				};
+			};
+
+			ca_uart_debug_pmx: ca_uart_debug@0 {
+				ca_uart_debug {
+					groups = "ca_uart_debug_grp";
+					function = "ca_uart_debug";
+				};
+			};
+
+			clkc_pmx0: clkc@0 {
+				clkc_0 {
+					groups = "clkc_grp0";
+					function = "clkc_m0";
+				};
+			};
+
+			clkc_pmx1: clkc@1 {
+				clkc_1 {
+					groups = "clkc_grp1";
+					function = "clkc_m1";
+				};
+			};
+
+			gn_gnss_i2c_pmx: gn_gnss_i2c@0 {
+				gn_gnss_i2c {
+					groups = "gn_gnss_i2c_grp";
+					function = "gn_gnss_i2c";
+				};
+			};
+
+			gn_gnss_uart_nopause_pmx: gn_gnss_uart_nopause@0 {
+				gn_gnss_uart_nopause {
+					groups = "gn_gnss_uart_nopause_grp";
+					function = "gn_gnss_uart_nopause";
+				};
+			};
+
+			gn_gnss_uart_pmx: gn_gnss_uart@0 {
+				gn_gnss_uart {
+					groups = "gn_gnss_uart_grp";
+					function = "gn_gnss_uart";
+				};
+			};
+
+			gn_trg_spi_pmx0: gn_trg_spi@0 {
+				gn_trg_spi_0 {
+					groups = "gn_trg_spi_grp0";
+					function = "gn_trg_spi_m0";
+				};
+			};
+
+			gn_trg_spi_pmx1: gn_trg_spi@1 {
+				gn_trg_spi_1 {
+					groups = "gn_trg_spi_grp1";
+					function = "gn_trg_spi_m1";
+				};
+			};
+
+			cvbs_dbg_pmx: cvbs_dbg@0 {
+				cvbs_dbg {
+					groups = "cvbs_dbg_grp";
+					function = "cvbs_dbg";
+				};
+			};
+
+			cvbs_dbg_test_pmx0: cvbs_dbg_test@0 {
+				cvbs_dbg_test_0 {
+					groups = "cvbs_dbg_test_grp0";
+					function = "cvbs_dbg_test_m0";
+				};
+			};
+
+			cvbs_dbg_test_pmx1: cvbs_dbg_test@1 {
+				cvbs_dbg_test_1 {
+					groups = "cvbs_dbg_test_grp1";
+					function = "cvbs_dbg_test_m1";
+				};
+			};
+
+			cvbs_dbg_test_pmx2: cvbs_dbg_test@2 {
+				cvbs_dbg_test_2 {
+					groups = "cvbs_dbg_test_grp2";
+					function = "cvbs_dbg_test_m2";
+				};
+			};
+
+			cvbs_dbg_test_pmx3: cvbs_dbg_test@3 {
+				cvbs_dbg_test_3 {
+					groups = "cvbs_dbg_test_grp3";
+					function = "cvbs_dbg_test_m3";
+				};
+			};
+
+			cvbs_dbg_test_pmx4: cvbs_dbg_test@4 {
+				cvbs_dbg_test_4 {
+					groups = "cvbs_dbg_test_grp4";
+					function = "cvbs_dbg_test_m4";
+				};
+			};
+
+			cvbs_dbg_test_pmx5: cvbs_dbg_test@5 {
+				cvbs_dbg_test_5 {
+					groups = "cvbs_dbg_test_grp5";
+					function = "cvbs_dbg_test_m5";
+				};
+			};
+
+			cvbs_dbg_test_pmx6: cvbs_dbg_test@6 {
+				cvbs_dbg_test_6 {
+					groups = "cvbs_dbg_test_grp6";
+					function = "cvbs_dbg_test_m6";
+				};
+			};
+
+			cvbs_dbg_test_pmx7: cvbs_dbg_test@7 {
+				cvbs_dbg_test_7 {
+					groups = "cvbs_dbg_test_grp7";
+					function = "cvbs_dbg_test_m7";
+				};
+			};
+
+			cvbs_dbg_test_pmx8: cvbs_dbg_test@8 {
+				cvbs_dbg_test_8 {
+					groups = "cvbs_dbg_test_grp8";
+					function = "cvbs_dbg_test_m8";
+				};
+			};
+
+			cvbs_dbg_test_pmx9: cvbs_dbg_test@9 {
+				cvbs_dbg_test_9 {
+					groups = "cvbs_dbg_test_grp9";
+					function = "cvbs_dbg_test_m9";
+				};
+			};
+
+			cvbs_dbg_test_pmx10: cvbs_dbg_test@10 {
+				cvbs_dbg_test_10 {
+					groups = "cvbs_dbg_test_grp10";
+					function = "cvbs_dbg_test_m10";
+				};
+			};
+
+			cvbs_dbg_test_pmx11: cvbs_dbg_test@11 {
+				cvbs_dbg_test_11 {
+					groups = "cvbs_dbg_test_grp11";
+					function = "cvbs_dbg_test_m11";
+				};
+			};
+
+			cvbs_dbg_test_pmx12: cvbs_dbg_test@12 {
+				cvbs_dbg_test_12 {
+					groups = "cvbs_dbg_test_grp12";
+					function = "cvbs_dbg_test_m12";
+				};
+			};
+
+			cvbs_dbg_test_pmx13: cvbs_dbg_test@13 {
+				cvbs_dbg_test_13 {
+					groups = "cvbs_dbg_test_grp13";
+					function = "cvbs_dbg_test_m13";
+				};
+			};
+
+			cvbs_dbg_test_pmx14: cvbs_dbg_test@14 {
+				cvbs_dbg_test_14 {
+					groups = "cvbs_dbg_test_grp14";
+					function = "cvbs_dbg_test_m14";
+				};
+			};
+
+			cvbs_dbg_test_pmx15: cvbs_dbg_test@15 {
+				cvbs_dbg_test_15 {
+					groups = "cvbs_dbg_test_grp15";
+					function = "cvbs_dbg_test_m15";
+				};
+			};
+
+			gn_gnss_power_pmx: gn_gnss_power@0 {
+				gn_gnss_power {
+					groups = "gn_gnss_power_grp";
+					function = "gn_gnss_power";
+				};
+			};
+
+			gn_gnss_sw_status_pmx: gn_gnss_sw_status@0 {
+				gn_gnss_sw_status {
+					groups = "gn_gnss_sw_status_grp";
+					function = "gn_gnss_sw_status";
+				};
+			};
+
+			gn_gnss_eclk_pmx: gn_gnss_eclk@0 {
+				gn_gnss_eclk {
+					groups = "gn_gnss_eclk_grp";
+					function = "gn_gnss_eclk";
+				};
+			};
+
+			gn_gnss_irq1_pmx0: gn_gnss_irq1@0 {
+				gn_gnss_irq1_0 {
+					groups = "gn_gnss_irq1_grp0";
+					function = "gn_gnss_irq1_m0";
+				};
+			};
+
+			gn_gnss_irq2_pmx0: gn_gnss_irq2@0 {
+				gn_gnss_irq2_0 {
+					groups = "gn_gnss_irq2_grp0";
+					function = "gn_gnss_irq2_m0";
+				};
+			};
+
+			gn_gnss_tm_pmx: gn_gnss_tm@0 {
+				gn_gnss_tm {
+					groups = "gn_gnss_tm_grp";
+					function = "gn_gnss_tm";
+				};
+			};
+
+			gn_gnss_tsync_pmx: gn_gnss_tsync@0 {
+				gn_gnss_tsync {
+					groups = "gn_gnss_tsync_grp";
+					function = "gn_gnss_tsync";
+				};
+			};
+
+			gn_io_gnsssys_sw_cfg_pmx: gn_io_gnsssys_sw_cfg@0 {
+				gn_io_gnsssys_sw_cfg {
+					groups = "gn_io_gnsssys_sw_cfg_grp";
+					function = "gn_io_gnsssys_sw_cfg";
+				};
+			};
+
+			gn_trg_pmx0: gn_trg@0 {
+				gn_trg_0 {
+					groups = "gn_trg_grp0";
+					function = "gn_trg_m0";
+				};
+			};
+
+			gn_trg_pmx1: gn_trg@1 {
+				gn_trg_1 {
+					groups = "gn_trg_grp1";
+					function = "gn_trg_m1";
+				};
+			};
+
+			gn_trg_shutdown_pmx0: gn_trg_shutdown@0 {
+				gn_trg_shutdown_0 {
+					groups = "gn_trg_shutdown_grp0";
+					function = "gn_trg_shutdown_m0";
+				};
+			};
+
+			gn_trg_shutdown_pmx1: gn_trg_shutdown@1 {
+				gn_trg_shutdown_1 {
+					groups = "gn_trg_shutdown_grp1";
+					function = "gn_trg_shutdown_m1";
+				};
+			};
+
+			gn_trg_shutdown_pmx2: gn_trg_shutdown@2 {
+				gn_trg_shutdown_2 {
+					groups = "gn_trg_shutdown_grp2";
+					function = "gn_trg_shutdown_m2";
+				};
+			};
+
+			gn_trg_shutdown_pmx3: gn_trg_shutdown@3 {
+				gn_trg_shutdown_3 {
+					groups = "gn_trg_shutdown_grp3";
+					function = "gn_trg_shutdown_m3";
+				};
+			};
+
+			i2c0_pmx: i2c0@0 {
+				i2c0 {
+					groups = "i2c0_grp";
+					function = "i2c0";
+				};
+			};
+
+			i2c1_pmx: i2c1@0 {
+				i2c1 {
+					groups = "i2c1_grp";
+					function = "i2c1";
+				};
+			};
+
+			jtag_pmx0: jtag@0 {
+				jtag_0 {
+					groups = "jtag_grp0";
+					function = "jtag_m0";
+				};
+			};
+
+			ks_kas_spi_pmx0: ks_kas_spi@0 {
+				ks_kas_spi_0 {
+					groups = "ks_kas_spi_grp0";
+					function = "ks_kas_spi_m0";
+				};
+			};
+
+			ld_ldd_pmx: ld_ldd@0 {
+				ld_ldd {
+					groups = "ld_ldd_grp";
+					function = "ld_ldd";
+				};
+			};
+
+			ld_ldd_16bit_pmx: ld_ldd_16bit@0 {
+				ld_ldd_16bit {
+					groups = "ld_ldd_16bit_grp";
+					function = "ld_ldd_16bit";
+				};
+			};
+
+			ld_ldd_fck_pmx: ld_ldd_fck@0 {
+				ld_ldd_fck {
+					groups = "ld_ldd_fck_grp";
+					function = "ld_ldd_fck";
+				};
+			};
+
+			ld_ldd_lck_pmx: ld_ldd_lck@0 {
+				ld_ldd_lck {
+					groups = "ld_ldd_lck_grp";
+					function = "ld_ldd_lck";
+				};
+			};
+
+			lr_lcdrom_pmx: lr_lcdrom@0 {
+				lr_lcdrom {
+					groups = "lr_lcdrom_grp";
+					function = "lr_lcdrom";
+				};
+			};
+
+			lvds_analog_pmx: lvds_analog@0 {
+				lvds_analog {
+					groups = "lvds_analog_grp";
+					function = "lvds_analog";
+				};
+			};
+
+			nd_df_pmx: nd_df@0 {
+				nd_df {
+					groups = "nd_df_grp";
+					function = "nd_df";
+				};
+			};
+
+			nd_df_nowp_pmx: nd_df_nowp@0 {
+				nd_df_nowp {
+					groups = "nd_df_nowp_grp";
+					function = "nd_df_nowp";
+				};
+			};
+
+			ps_pmx: ps@0 {
+				ps {
+					groups = "ps_grp";
+					function = "ps";
+				};
+			};
+
+			pwc_core_on_pmx: pwc_core_on@0 {
+				pwc_core_on {
+					groups = "pwc_core_on_grp";
+					function = "pwc_core_on";
+				};
+			};
+
+			pwc_ext_on_pmx: pwc_ext_on@0 {
+				pwc_ext_on {
+					groups = "pwc_ext_on_grp";
+					function = "pwc_ext_on";
+				};
+			};
+
+			pwc_gpio3_clk_pmx: pwc_gpio3_clk@0 {
+				pwc_gpio3_clk {
+					groups = "pwc_gpio3_clk_grp";
+					function = "pwc_gpio3_clk";
+				};
+			};
+
+			pwc_io_on_pmx: pwc_io_on@0 {
+				pwc_io_on {
+					groups = "pwc_io_on_grp";
+					function = "pwc_io_on";
+				};
+			};
+
+			pwc_lowbatt_b_pmx0: pwc_lowbatt_b@0 {
+				pwc_lowbatt_b_0 {
+					groups = "pwc_lowbatt_b_grp0";
+					function = "pwc_lowbatt_b_m0";
+				};
+			};
+
+			pwc_mem_on_pmx: pwc_mem_on@0 {
+				pwc_mem_on {
+					groups = "pwc_mem_on_grp";
+					function = "pwc_mem_on";
+				};
+			};
+
+			pwc_on_key_b_pmx0: pwc_on_key_b@0 {
+				pwc_on_key_b_0 {
+					groups = "pwc_on_key_b_grp0";
+					function = "pwc_on_key_b_m0";
+				};
+			};
+
+			pwc_wakeup_src0_pmx: pwc_wakeup_src0@0 {
+				pwc_wakeup_src0 {
+					groups = "pwc_wakeup_src0_grp";
+					function = "pwc_wakeup_src0";
+				};
+			};
+
+			pwc_wakeup_src1_pmx: pwc_wakeup_src1@0 {
+				pwc_wakeup_src1 {
+					groups = "pwc_wakeup_src1_grp";
+					function = "pwc_wakeup_src1";
+				};
+			};
+
+			pwc_wakeup_src2_pmx: pwc_wakeup_src2@0 {
+				pwc_wakeup_src2 {
+					groups = "pwc_wakeup_src2_grp";
+					function = "pwc_wakeup_src2";
+				};
+			};
+
+			pwc_wakeup_src3_pmx: pwc_wakeup_src3@0 {
+				pwc_wakeup_src3 {
+					groups = "pwc_wakeup_src3_grp";
+					function = "pwc_wakeup_src3";
+				};
+			};
+
+			pw_cko0_pmx0: pw_cko0@0 {
+				pw_cko0_0 {
+					groups = "pw_cko0_grp0";
+					function = "pw_cko0_m0";
+				};
+			};
+
+			pw_cko0_pmx1: pw_cko0@1 {
+				pw_cko0_1 {
+					groups = "pw_cko0_grp1";
+					function = "pw_cko0_m1";
+				};
+			};
+
+			pw_cko0_pmx2: pw_cko0@2 {
+				pw_cko0_2 {
+					groups = "pw_cko0_grp2";
+					function = "pw_cko0_m2";
+				};
+			};
+
+			pw_cko1_pmx0: pw_cko1@0 {
+				pw_cko1_0 {
+					groups = "pw_cko1_grp0";
+					function = "pw_cko1_m0";
+				};
+			};
+
+			pw_cko1_pmx1: pw_cko1@1 {
+				pw_cko1_1 {
+					groups = "pw_cko1_grp1";
+					function = "pw_cko1_m1";
+				};
+			};
+
+			pw_i2s01_clk_pmx0: pw_i2s01_clk@0 {
+				pw_i2s01_clk_0 {
+					groups = "pw_i2s01_clk_grp0";
+					function = "pw_i2s01_clk_m0";
+				};
+			};
+
+			pw_i2s01_clk_pmx1: pw_i2s01_clk@1 {
+				pw_i2s01_clk_1 {
+					groups = "pw_i2s01_clk_grp1";
+					function = "pw_i2s01_clk_m1";
+				};
+			};
+
+			pw_pwm0_pmx: pw_pwm0@0 {
+				pw_pwm0 {
+					groups = "pw_pwm0_grp";
+					function = "pw_pwm0";
+				};
+			};
+
+			pw_pwm1_pmx: pw_pwm1@0 {
+				pw_pwm1 {
+					groups = "pw_pwm1_grp";
+					function = "pw_pwm1";
+				};
+			};
+
+			pw_pwm2_pmx0: pw_pwm2@0 {
+				pw_pwm2_0 {
+					groups = "pw_pwm2_grp0";
+					function = "pw_pwm2_m0";
+				};
+			};
+
+			pw_pwm2_pmx1: pw_pwm2@1 {
+				pw_pwm2_1 {
+					groups = "pw_pwm2_grp1";
+					function = "pw_pwm2_m1";
+				};
+			};
+
+			pw_pwm3_pmx0: pw_pwm3@0 {
+				pw_pwm3_0 {
+					groups = "pw_pwm3_grp0";
+					function = "pw_pwm3_m0";
+				};
+			};
+
+			pw_pwm3_pmx1: pw_pwm3@1 {
+				pw_pwm3_1 {
+					groups = "pw_pwm3_grp1";
+					function = "pw_pwm3_m1";
+				};
+			};
+
+			pw_pwm_cpu_vol_pmx0: pw_pwm_cpu_vol@0 {
+				pw_pwm_cpu_vol_0 {
+					groups = "pw_pwm_cpu_vol_grp0";
+					function = "pw_pwm_cpu_vol_m0";
+				};
+			};
+
+			pw_pwm_cpu_vol_pmx1: pw_pwm_cpu_vol@1 {
+				pw_pwm_cpu_vol_1 {
+					groups = "pw_pwm_cpu_vol_grp1";
+					function = "pw_pwm_cpu_vol_m1";
+				};
+			};
+
+			pw_backlight_pmx0: pw_backlight@0 {
+				pw_backlight_0 {
+					groups = "pw_backlight_grp0";
+					function = "pw_backlight_m0";
+				};
+			};
+
+			pw_backlight_pmx1: pw_backlight@1 {
+				pw_backlight_1 {
+					groups = "pw_backlight_grp1";
+					function = "pw_backlight_m1";
+				};
+			};
+
+			rg_eth_mac_pmx: rg_eth_mac@0 {
+				rg_eth_mac {
+					groups = "rg_eth_mac_grp";
+					function = "rg_eth_mac";
+				};
+			};
+
+			rg_gmac_phy_intr_n_pmx: rg_gmac_phy_intr_n@0 {
+				rg_gmac_phy_intr_n {
+					groups = "rg_gmac_phy_intr_n_grp";
+					function = "rg_gmac_phy_intr_n";
+				};
+			};
+
+			rg_rgmii_mac_pmx: rg_rgmii_mac@0 {
+				rg_rgmii_mac {
+					groups = "rg_rgmii_mac_grp";
+					function = "rg_rgmii_mac";
+				};
+			};
+
+			rg_rgmii_phy_ref_clk_pmx0: rg_rgmii_phy_ref_clk@0 {
+				rg_rgmii_phy_ref_clk_0 {
+					groups =
+						"rg_rgmii_phy_ref_clk_grp0";
+					function =
+						"rg_rgmii_phy_ref_clk_m0";
+				};
+			};
+
+			rg_rgmii_phy_ref_clk_pmx1: rg_rgmii_phy_ref_clk@1 {
+				rg_rgmii_phy_ref_clk_1 {
+					groups =
+						"rg_rgmii_phy_ref_clk_grp1";
+					function =
+						"rg_rgmii_phy_ref_clk_m1";
+				};
+			};
+
+			sd0_pmx: sd0@0 {
+				sd0 {
+					groups = "sd0_grp";
+					function = "sd0";
+				};
+			};
+
+			sd0_4bit_pmx: sd0_4bit@0 {
+				sd0_4bit {
+					groups = "sd0_4bit_grp";
+					function = "sd0_4bit";
+				};
+			};
+
+			sd1_pmx: sd1@0 {
+				sd1 {
+					groups = "sd1_grp";
+					function = "sd1";
+				};
+			};
+
+			sd1_4bit_pmx0: sd1_4bit@0 {
+				sd1_4bit_0 {
+					groups = "sd1_4bit_grp0";
+					function = "sd1_4bit_m0";
+				};
+			};
+
+			sd1_4bit_pmx1: sd1_4bit@1 {
+				sd1_4bit_1 {
+					groups = "sd1_4bit_grp1";
+					function = "sd1_4bit_m1";
+				};
+			};
+
+			sd2_pmx0: sd2@0 {
+				sd2_0 {
+					groups = "sd2_grp0";
+					function = "sd2_m0";
+				};
+			};
+
+			sd2_no_cdb_pmx0: sd2_no_cdb@0 {
+				sd2_no_cdb_0 {
+					groups = "sd2_no_cdb_grp0";
+					function = "sd2_no_cdb_m0";
+				};
+			};
+
+			sd3_pmx: sd3@0 {
+				sd3 {
+					groups = "sd3_grp";
+					function = "sd3";
+				};
+			};
+
+			sd5_pmx: sd5@0 {
+				sd5 {
+					groups = "sd5_grp";
+					function = "sd5";
+				};
+			};
+
+			sd6_pmx0: sd6@0 {
+				sd6_0 {
+					groups = "sd6_grp0";
+					function = "sd6_m0";
+				};
+			};
+
+			sd6_pmx1: sd6@1 {
+				sd6_1 {
+					groups = "sd6_grp1";
+					function = "sd6_m1";
+				};
+			};
+
+			sp0_ext_ldo_on_pmx: sp0_ext_ldo_on@0 {
+				sp0_ext_ldo_on {
+					groups = "sp0_ext_ldo_on_grp";
+					function = "sp0_ext_ldo_on";
+				};
+			};
+
+			sp0_qspi_pmx: sp0_qspi@0 {
+				sp0_qspi {
+					groups = "sp0_qspi_grp";
+					function = "sp0_qspi";
+				};
+			};
+
+			sp1_spi_pmx: sp1_spi@0 {
+				sp1_spi {
+					groups = "sp1_spi_grp";
+					function = "sp1_spi";
+				};
+			};
+
+			tpiu_trace_pmx: tpiu_trace@0 {
+				tpiu_trace {
+					groups = "tpiu_trace_grp";
+					function = "tpiu_trace";
+				};
+			};
+
+			uart0_pmx: uart0@0 {
+				uart0 {
+					groups = "uart0_grp";
+					function = "uart0";
+				};
+			};
+
+			uart0_nopause_pmx: uart0_nopause@0 {
+				uart0_nopause {
+					groups = "uart0_nopause_grp";
+					function = "uart0_nopause";
+				};
+			};
+
+			uart1_pmx: uart1@0 {
+				uart1 {
+					groups = "uart1_grp";
+					function = "uart1";
+				};
+			};
+
+			uart2_pmx: uart2@0 {
+				uart2 {
+					groups = "uart2_grp";
+					function = "uart2";
+				};
+			};
+
+			uart3_pmx0: uart3@0 {
+				uart3_0 {
+					groups = "uart3_grp0";
+					function = "uart3_m0";
+				};
+			};
+
+			uart3_pmx1: uart3@1 {
+				uart3_1 {
+					groups = "uart3_grp1";
+					function = "uart3_m1";
+				};
+			};
+
+			uart3_pmx2: uart3@2 {
+				uart3_2 {
+					groups = "uart3_grp2";
+					function = "uart3_m2";
+				};
+			};
+
+			uart3_pmx3: uart3@3 {
+				uart3_3 {
+					groups = "uart3_grp3";
+					function = "uart3_m3";
+				};
+			};
+
+			uart3_nopause_pmx0: uart3_nopause@0 {
+				uart3_nopause_0 {
+					groups = "uart3_nopause_grp0";
+					function = "uart3_nopause_m0";
+				};
+			};
+
+			uart3_nopause_pmx1: uart3_nopause@1 {
+				uart3_nopause_1 {
+					groups = "uart3_nopause_grp1";
+					function = "uart3_nopause_m1";
+				};
+			};
+
+			uart4_pmx0: uart4@0 {
+				uart4_0 {
+					groups = "uart4_grp0";
+					function = "uart4_m0";
+				};
+			};
+
+			uart4_pmx1: uart4@1 {
+				uart4_1 {
+					groups = "uart4_grp1";
+					function = "uart4_m1";
+				};
+			};
+
+			uart4_pmx2: uart4@2 {
+				uart4_2 {
+					groups = "uart4_grp2";
+					function = "uart4_m2";
+				};
+			};
+
+			uart4_nopause_pmx: uart4_nopause@0 {
+				uart4_nopause {
+					groups = "uart4_nopause_grp";
+					function = "uart4_nopause";
+				};
+			};
+
+			usb0_drvvbus_pmx: usb0_drvvbus@0 {
+				usb0_drvvbus {
+					groups = "usb0_drvvbus_grp";
+					function = "usb0_drvvbus";
+				};
+			};
+
+			usb1_drvvbus_pmx: usb1_drvvbus@0 {
+				usb1_drvvbus {
+					groups = "usb1_drvvbus_grp";
+					function = "usb1_drvvbus";
+				};
+			};
+
+			visbus_dout_pmx: visbus_dout@0 {
+				visbus_dout {
+					groups = "visbus_dout_grp";
+					function = "visbus_dout";
+				};
+			};
+
+			vi_vip1_pmx: vi_vip1@0 {
+				vi_vip1 {
+					groups = "vi_vip1_grp";
+					function = "vi_vip1";
+				};
+			};
+
+			vi_vip1_ext_pmx: vi_vip1_ext@0 {
+				vi_vip1_ext {
+					groups = "vi_vip1_ext_grp";
+					function = "vi_vip1_ext";
+				};
+			};
+
+			vi_vip1_low8bit_pmx: vi_vip1_low8bit@0 {
+				vi_vip1_low8bit {
+					groups = "vi_vip1_low8bit_grp";
+					function = "vi_vip1_low8bit";
+				};
+			};
+
+			vi_vip1_high8bit_pmx: vi_vip1_high8bit@0 {
+				vi_vip1_high8bit {
+					groups = "vi_vip1_high8bit_grp";
+					function = "vi_vip1_high8bit";
+				};
+			};
 		};
 
 		pmipc {
@@ -356,6 +1375,12 @@
 				clock-names = "gpio0_io";
 				gpio-controller;
 				interrupt-controller;
+
+				gpio-banks = <2>;
+				gpio-ranges = <&pinctrl 0 0 0>,
+						<&pinctrl 32 0 0>;
+				gpio-ranges-group-names = "lvds_gpio_grp",
+							"uart_nand_gpio_grp";
 			};
 
 			nand@17050000 {
@@ -461,11 +1486,22 @@
 				#interrupt-cells = <2>;
 				compatible = "sirf,atlas7-gpio";
 				reg = <0x13300000 0x1000>;
-				interrupts = <0 43 0>, <0 44 0>, <0 45 0>;
+				interrupts = <0 43 0>, <0 44 0>,
+						<0 45 0>, <0 46 0>;
 				clocks = <&car 84>;
 				clock-names = "gpio1_io";
 				gpio-controller;
 				interrupt-controller;
+
+				gpio-banks = <4>;
+				gpio-ranges = <&pinctrl 0 0 0>,
+						<&pinctrl 32 0 0>,
+						<&pinctrl 64 0 0>,
+						<&pinctrl 96 0 0>;
+				gpio-ranges-group-names = "gnss_gpio_grp",
+							"lcd_vip_gpio_grp",
+							"sdio_i2s_gpio_grp",
+							"sp_rgmii_gpio_grp";
 			};
 
 			sd2: sdhci@14200000 {
@@ -744,6 +1780,10 @@
 				interrupts = <0 47 0>;
 				gpio-controller;
 				interrupt-controller;
+
+				gpio-banks = <1>;
+				gpio-ranges = <&pinctrl 0 0 0>;
+				gpio-ranges-group-names = "rtc_gpio_grp";
 			};
 
 			rtc-iobg@18840000 {
diff --git a/arch/arm/boot/dts/cros-ec-keyboard.dtsi b/arch/arm/boot/dts/cros-ec-keyboard.dtsi
index 9c7fb0a..4e42f30c 100644
--- a/arch/arm/boot/dts/cros-ec-keyboard.dtsi
+++ b/arch/arm/boot/dts/cros-ec-keyboard.dtsi
@@ -22,6 +22,7 @@
 			MATRIX_KEY(0x00, 0x02, KEY_F1)
 			MATRIX_KEY(0x00, 0x03, KEY_B)
 			MATRIX_KEY(0x00, 0x04, KEY_F10)
+			MATRIX_KEY(0x00, 0x05, KEY_RO)
 			MATRIX_KEY(0x00, 0x06, KEY_N)
 			MATRIX_KEY(0x00, 0x08, KEY_EQUAL)
 			MATRIX_KEY(0x00, 0x0a, KEY_RIGHTALT)
@@ -34,6 +35,7 @@
 			MATRIX_KEY(0x01, 0x08, KEY_APOSTROPHE)
 			MATRIX_KEY(0x01, 0x09, KEY_F9)
 			MATRIX_KEY(0x01, 0x0b, KEY_BACKSPACE)
+			MATRIX_KEY(0x01, 0x0c, KEY_HENKAN)
 
 			MATRIX_KEY(0x02, 0x00, KEY_LEFTCTRL)
 			MATRIX_KEY(0x02, 0x01, KEY_TAB)
@@ -45,6 +47,7 @@
 			MATRIX_KEY(0x02, 0x07, KEY_102ND)
 			MATRIX_KEY(0x02, 0x08, KEY_LEFTBRACE)
 			MATRIX_KEY(0x02, 0x09, KEY_F8)
+			MATRIX_KEY(0x02, 0x0a, KEY_YEN)
 
 			MATRIX_KEY(0x03, 0x01, KEY_GRAVE)
 			MATRIX_KEY(0x03, 0x02, KEY_F2)
@@ -53,6 +56,7 @@
 			MATRIX_KEY(0x03, 0x06, KEY_6)
 			MATRIX_KEY(0x03, 0x08, KEY_MINUS)
 			MATRIX_KEY(0x03, 0x0b, KEY_BACKSLASH)
+			MATRIX_KEY(0x03, 0x0c, KEY_MUHENKAN)
 
 			MATRIX_KEY(0x04, 0x00, KEY_RIGHTCTRL)
 			MATRIX_KEY(0x04, 0x01, KEY_A)
diff --git a/arch/arm/boot/dts/dra7-evm.dts b/arch/arm/boot/dts/dra7-evm.dts
index aa46590..096f68b 100644
--- a/arch/arm/boot/dts/dra7-evm.dts
+++ b/arch/arm/boot/dts/dra7-evm.dts
@@ -686,7 +686,8 @@
 
 &dcan1 {
 	status = "ok";
-	pinctrl-names = "default", "sleep";
-	pinctrl-0 = <&dcan1_pins_default>;
+	pinctrl-names = "default", "sleep", "active";
+	pinctrl-0 = <&dcan1_pins_sleep>;
 	pinctrl-1 = <&dcan1_pins_sleep>;
+	pinctrl-2 = <&dcan1_pins_default>;
 };
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 8f1e25b..1e29ccf 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -116,7 +116,7 @@
 				ranges = <0 0x2000 0x2000>;
 
 				scm_conf: scm_conf@0 {
-					compatible = "syscon";
+					compatible = "syscon", "simple-bus";
 					reg = <0x0 0x1400>;
 					#address-cells = <1>;
 					#size-cells = <1>;
@@ -1140,6 +1140,7 @@
 				ctrl-module = <&omap_control_sata>;
 				clocks = <&sys_clkin1>, <&sata_ref_clk>;
 				clock-names = "sysclk", "refclk";
+				syscon-pllreset = <&scm_conf 0x3fc>;
 				#phy-cells = <0>;
 			};
 
diff --git a/arch/arm/boot/dts/dra72-evm.dts b/arch/arm/boot/dts/dra72-evm.dts
index 4e1b605..8037384 100644
--- a/arch/arm/boot/dts/dra72-evm.dts
+++ b/arch/arm/boot/dts/dra72-evm.dts
@@ -587,9 +587,10 @@
 
 &dcan1 {
 	status = "ok";
-	pinctrl-names = "default", "sleep";
-	pinctrl-0 = <&dcan1_pins_default>;
+	pinctrl-names = "default", "sleep", "active";
+	pinctrl-0 = <&dcan1_pins_sleep>;
 	pinctrl-1 = <&dcan1_pins_sleep>;
+	pinctrl-2 = <&dcan1_pins_default>;
 };
 
 &qspi {
diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi
index d720133..2db9943 100644
--- a/arch/arm/boot/dts/exynos3250.dtsi
+++ b/arch/arm/boot/dts/exynos3250.dtsi
@@ -138,8 +138,8 @@
 
 		mipi_phy: video-phy@10020710 {
 			compatible = "samsung,s5pv210-mipi-video-phy";
-			reg = <0x10020710 8>;
 			#phy-cells = <1>;
+			syscon = <&pmu_system_controller>;
 		};
 
 		pd_cam: cam-power-domain@10023C00 {
diff --git a/arch/arm/boot/dts/exynos4210-origen.dts b/arch/arm/boot/dts/exynos4210-origen.dts
index e0abfc3..e050d85 100644
--- a/arch/arm/boot/dts/exynos4210-origen.dts
+++ b/arch/arm/boot/dts/exynos4210-origen.dts
@@ -127,6 +127,10 @@
 	};
 };
 
+&cpu0 {
+	cpu0-supply = <&buck1_reg>;
+};
+
 &fimd {
 	pinctrl-0 = <&lcd_en &lcd_clk &lcd_data24 &pwm0_out>;
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/exynos4210-trats.dts b/arch/arm/boot/dts/exynos4210-trats.dts
index 98f3ce6..ba34886 100644
--- a/arch/arm/boot/dts/exynos4210-trats.dts
+++ b/arch/arm/boot/dts/exynos4210-trats.dts
@@ -188,6 +188,10 @@
 	};
 };
 
+&cpu0 {
+	cpu0-supply = <&varm_breg>;
+};
+
 &dsi_0 {
 	vddcore-supply = <&vusb_reg>;
 	vddio-supply = <&vmipi_reg>;
diff --git a/arch/arm/boot/dts/exynos4210-universal_c210.dts b/arch/arm/boot/dts/exynos4210-universal_c210.dts
index d4f2b11..775892b 100644
--- a/arch/arm/boot/dts/exynos4210-universal_c210.dts
+++ b/arch/arm/boot/dts/exynos4210-universal_c210.dts
@@ -548,6 +548,10 @@
 	};
 };
 
+&cpu0 {
+	cpu0-supply = <&vdd_arm_reg>;
+};
+
 &pinctrl_1 {
 	hdmi_hpd: hdmi-hpd {
 		samsung,pins = "gpx3-7";
diff --git a/arch/arm/boot/dts/exynos4210.dtsi b/arch/arm/boot/dts/exynos4210.dtsi
index 10d3c17..3e5ba66 100644
--- a/arch/arm/boot/dts/exynos4210.dtsi
+++ b/arch/arm/boot/dts/exynos4210.dtsi
@@ -40,6 +40,18 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0x900>;
+			clocks = <&clock CLK_ARM_CLK>;
+			clock-names = "cpu";
+			clock-latency = <160000>;
+
+			operating-points = <
+				1200000 1250000
+				1000000 1150000
+				800000	1075000
+				500000	975000
+				400000	975000
+				200000	950000
+			>;
 			cooling-min-level = <4>;
 			cooling-max-level = <2>;
 			#cooling-cells = <2>; /* min followed by max */
diff --git a/arch/arm/boot/dts/imx23.dtsi b/arch/arm/boot/dts/imx23.dtsi
index c892d58..b995333 100644
--- a/arch/arm/boot/dts/imx23.dtsi
+++ b/arch/arm/boot/dts/imx23.dtsi
@@ -468,6 +468,7 @@
 				interrupts = <36 37 38 39 40 41 42 43 44>;
 				status = "disabled";
 				clocks = <&clks 26>;
+				#io-channel-cells = <1>;
 			};
 
 			spdif@80054000 {
diff --git a/arch/arm/boot/dts/imx25-pdk.dts b/arch/arm/boot/dts/imx25-pdk.dts
index dd45e69..9351296 100644
--- a/arch/arm/boot/dts/imx25-pdk.dts
+++ b/arch/arm/boot/dts/imx25-pdk.dts
@@ -10,6 +10,7 @@
  */
 
 /dts-v1/;
+#include <dt-bindings/gpio/gpio.h>
 #include <dt-bindings/input/input.h>
 #include "imx25.dtsi"
 
@@ -114,8 +115,8 @@
 &esdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
-	cd-gpios = <&gpio2 1 0>;
-	wp-gpios = <&gpio2 0 0>;
+	cd-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 0 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx27.dtsi b/arch/arm/boot/dts/imx27.dtsi
index bc215e4..b69be5c 100644
--- a/arch/arm/boot/dts/imx27.dtsi
+++ b/arch/arm/boot/dts/imx27.dtsi
@@ -108,7 +108,7 @@
 			};
 
 			gpt1: timer@10003000 {
-				compatible = "fsl,imx27-gpt", "fsl,imx1-gpt";
+				compatible = "fsl,imx27-gpt", "fsl,imx21-gpt";
 				reg = <0x10003000 0x1000>;
 				interrupts = <26>;
 				clocks = <&clks IMX27_CLK_GPT1_IPG_GATE>,
@@ -117,7 +117,7 @@
 			};
 
 			gpt2: timer@10004000 {
-				compatible = "fsl,imx27-gpt", "fsl,imx1-gpt";
+				compatible = "fsl,imx27-gpt", "fsl,imx21-gpt";
 				reg = <0x10004000 0x1000>;
 				interrupts = <25>;
 				clocks = <&clks IMX27_CLK_GPT2_IPG_GATE>,
@@ -126,7 +126,7 @@
 			};
 
 			gpt3: timer@10005000 {
-				compatible = "fsl,imx27-gpt", "fsl,imx1-gpt";
+				compatible = "fsl,imx27-gpt", "fsl,imx21-gpt";
 				reg = <0x10005000 0x1000>;
 				interrupts = <24>;
 				clocks = <&clks IMX27_CLK_GPT3_IPG_GATE>,
@@ -376,7 +376,7 @@
 			};
 
 			gpt4: timer@10019000 {
-				compatible = "fsl,imx27-gpt", "fsl,imx1-gpt";
+				compatible = "fsl,imx27-gpt", "fsl,imx21-gpt";
 				reg = <0x10019000 0x1000>;
 				interrupts = <4>;
 				clocks = <&clks IMX27_CLK_GPT4_IPG_GATE>,
@@ -385,7 +385,7 @@
 			};
 
 			gpt5: timer@1001a000 {
-				compatible = "fsl,imx27-gpt", "fsl,imx1-gpt";
+				compatible = "fsl,imx27-gpt", "fsl,imx21-gpt";
 				reg = <0x1001a000 0x1000>;
 				interrupts = <3>;
 				clocks = <&clks IMX27_CLK_GPT5_IPG_GATE>,
@@ -436,7 +436,7 @@
 			};
 
 			gpt6: timer@1001f000 {
-				compatible = "fsl,imx27-gpt", "fsl,imx1-gpt";
+				compatible = "fsl,imx27-gpt", "fsl,imx21-gpt";
 				reg = <0x1001f000 0x1000>;
 				interrupts = <2>;
 				clocks = <&clks IMX27_CLK_GPT6_IPG_GATE>,
diff --git a/arch/arm/boot/dts/imx35.dtsi b/arch/arm/boot/dts/imx35.dtsi
index b6478e9..e6540b5 100644
--- a/arch/arm/boot/dts/imx35.dtsi
+++ b/arch/arm/boot/dts/imx35.dtsi
@@ -286,8 +286,8 @@
 			can1: can@53fe4000 {
 				compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan";
 				reg = <0x53fe4000 0x1000>;
-				clocks = <&clks 33>;
-				clock-names = "ipg";
+				clocks = <&clks 33>, <&clks 33>;
+				clock-names = "ipg", "per";
 				interrupts = <43>;
 				status = "disabled";
 			};
@@ -295,8 +295,8 @@
 			can2: can@53fe8000 {
 				compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan";
 				reg = <0x53fe8000 0x1000>;
-				clocks = <&clks 34>;
-				clock-names = "ipg";
+				clocks = <&clks 34>, <&clks 34>;
+				clock-names = "ipg", "per";
 				interrupts = <44>;
 				status = "disabled";
 			};
diff --git a/arch/arm/boot/dts/imx51-apf51dev.dts b/arch/arm/boot/dts/imx51-apf51dev.dts
index 93d3ea1..0f3fe29 100644
--- a/arch/arm/boot/dts/imx51-apf51dev.dts
+++ b/arch/arm/boot/dts/imx51-apf51dev.dts
@@ -98,7 +98,7 @@
 &esdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
-	cd-gpios = <&gpio2 29 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio2 29 GPIO_ACTIVE_LOW>;
 	bus-width = <4>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx53-ard.dts b/arch/arm/boot/dts/imx53-ard.dts
index e9337ad..3bc1883 100644
--- a/arch/arm/boot/dts/imx53-ard.dts
+++ b/arch/arm/boot/dts/imx53-ard.dts
@@ -103,8 +103,8 @@
 &esdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
-	cd-gpios = <&gpio1 1 0>;
-	wp-gpios = <&gpio1 9 0>;
+	cd-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio1 9 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx53-m53evk.dts b/arch/arm/boot/dts/imx53-m53evk.dts
index d0e0f57..53f4088 100644
--- a/arch/arm/boot/dts/imx53-m53evk.dts
+++ b/arch/arm/boot/dts/imx53-m53evk.dts
@@ -124,8 +124,8 @@
 &esdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
-	cd-gpios = <&gpio1 1 0>;
-	wp-gpios = <&gpio1 9 0>;
+	cd-gpios = <&gpio1 1 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio1 9 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx53-qsb-common.dtsi b/arch/arm/boot/dts/imx53-qsb-common.dtsi
index 181ae5e..b0d5542 100644
--- a/arch/arm/boot/dts/imx53-qsb-common.dtsi
+++ b/arch/arm/boot/dts/imx53-qsb-common.dtsi
@@ -147,8 +147,8 @@
 &esdhc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc3>;
-	cd-gpios = <&gpio3 11 0>;
-	wp-gpios = <&gpio3 12 0>;
+	cd-gpios = <&gpio3 11 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio3 12 GPIO_ACTIVE_HIGH>;
 	bus-width = <8>;
 	status = "okay";
 };
@@ -295,9 +295,10 @@
 &tve {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_vga_sync>;
+	ddc-i2c-bus = <&i2c2>;
 	fsl,tve-mode = "vga";
-	fsl,hsync-pin = <4>;
-	fsl,vsync-pin = <6>;
+	fsl,hsync-pin = <7>;	/* IPU DI1 PIN7 via EIM_OE */
+	fsl,vsync-pin = <8>;	/* IPU DI1 PIN8 via EIM_RW */
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx53-smd.dts b/arch/arm/boot/dts/imx53-smd.dts
index 1d32557..fc89ce1 100644
--- a/arch/arm/boot/dts/imx53-smd.dts
+++ b/arch/arm/boot/dts/imx53-smd.dts
@@ -41,8 +41,8 @@
 &esdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
-	cd-gpios = <&gpio3 13 0>;
-	wp-gpios = <&gpio4 11 0>;
+	cd-gpios = <&gpio3 13 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio4 11 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx53-tqma53.dtsi b/arch/arm/boot/dts/imx53-tqma53.dtsi
index 4f1f0e2..e03373a 100644
--- a/arch/arm/boot/dts/imx53-tqma53.dtsi
+++ b/arch/arm/boot/dts/imx53-tqma53.dtsi
@@ -41,8 +41,8 @@
 	pinctrl-0 = <&pinctrl_esdhc2>,
 		    <&pinctrl_esdhc2_cdwp>;
 	vmmc-supply = <&reg_3p3v>;
-	wp-gpios = <&gpio1 2 0>;
-	cd-gpios = <&gpio1 4 0>;
+	wp-gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
 	status = "disabled";
 };
 
diff --git a/arch/arm/boot/dts/imx53-tx53.dtsi b/arch/arm/boot/dts/imx53-tx53.dtsi
index 704bd72..d3e50b2 100644
--- a/arch/arm/boot/dts/imx53-tx53.dtsi
+++ b/arch/arm/boot/dts/imx53-tx53.dtsi
@@ -183,7 +183,7 @@
 };
 
 &esdhc1 {
-	cd-gpios = <&gpio3 24 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>;
 	fsl,wp-controller;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
@@ -191,7 +191,7 @@
 };
 
 &esdhc2 {
-	cd-gpios = <&gpio3 25 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio3 25 GPIO_ACTIVE_LOW>;
 	fsl,wp-controller;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc2>;
diff --git a/arch/arm/boot/dts/imx53-voipac-bsb.dts b/arch/arm/boot/dts/imx53-voipac-bsb.dts
index c17d3ad..fc51b87 100644
--- a/arch/arm/boot/dts/imx53-voipac-bsb.dts
+++ b/arch/arm/boot/dts/imx53-voipac-bsb.dts
@@ -119,8 +119,8 @@
 &esdhc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc2>;
-	cd-gpios = <&gpio3 25 0>;
-	wp-gpios = <&gpio2 19 0>;
+	cd-gpios = <&gpio3 25 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 19 GPIO_ACTIVE_HIGH>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6dl-riotboard.dts b/arch/arm/boot/dts/imx6dl-riotboard.dts
index 43cb3fd..5111f51 100644
--- a/arch/arm/boot/dts/imx6dl-riotboard.dts
+++ b/arch/arm/boot/dts/imx6dl-riotboard.dts
@@ -305,8 +305,8 @@
 &usdhc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc2>;
-	cd-gpios = <&gpio1 4 0>;
-	wp-gpios = <&gpio1 2 0>;
+	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
@@ -314,8 +314,8 @@
 &usdhc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
-	cd-gpios = <&gpio7 0 0>;
-	wp-gpios = <&gpio7 1 0>;
+	cd-gpios = <&gpio7 0 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio7 1 GPIO_ACTIVE_HIGH>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6q-arm2.dts b/arch/arm/boot/dts/imx6q-arm2.dts
index 78df05e..d6515f7 100644
--- a/arch/arm/boot/dts/imx6q-arm2.dts
+++ b/arch/arm/boot/dts/imx6q-arm2.dts
@@ -11,6 +11,7 @@
  */
 
 /dts-v1/;
+#include <dt-bindings/gpio/gpio.h>
 #include "imx6q.dtsi"
 
 / {
@@ -196,8 +197,8 @@
 };
 
 &usdhc3 {
-	cd-gpios = <&gpio6 11 0>;
-	wp-gpios = <&gpio6 14 0>;
+	cd-gpios = <&gpio6 11 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio6 14 GPIO_ACTIVE_HIGH>;
 	vmmc-supply = <&reg_3p3v>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3
diff --git a/arch/arm/boot/dts/imx6q-gk802.dts b/arch/arm/boot/dts/imx6q-gk802.dts
index 703539c..00bd63e 100644
--- a/arch/arm/boot/dts/imx6q-gk802.dts
+++ b/arch/arm/boot/dts/imx6q-gk802.dts
@@ -7,6 +7,7 @@
  */
 
 /dts-v1/;
+#include <dt-bindings/gpio/gpio.h>
 #include "imx6q.dtsi"
 
 / {
@@ -161,7 +162,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
 	bus-width = <4>;
-	cd-gpios = <&gpio6 11 0>;
+	cd-gpios = <&gpio6 11 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6q-tbs2910.dts b/arch/arm/boot/dts/imx6q-tbs2910.dts
index a43abfa..5645d52 100644
--- a/arch/arm/boot/dts/imx6q-tbs2910.dts
+++ b/arch/arm/boot/dts/imx6q-tbs2910.dts
@@ -251,7 +251,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc2>;
 	bus-width = <4>;
-	cd-gpios = <&gpio2 2 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio2 2 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
@@ -260,7 +260,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
 	bus-width = <4>;
-	cd-gpios = <&gpio2 0 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>;
 	wp-gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi b/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi
index e6d9195..f4d6ae5 100644
--- a/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-aristainetos.dtsi
@@ -173,7 +173,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc1>;
 	vmmc-supply = <&reg_3p3v>;
-	cd-gpios = <&gpio4 7 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio4 7 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
@@ -181,7 +181,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc2>;
 	vmmc-supply = <&reg_3p3v>;
-	cd-gpios = <&gpio4 8 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio4 8 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi
index 1d85de2..a47a039 100644
--- a/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-aristainetos2.dtsi
@@ -392,7 +392,7 @@
 &usdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc1>;
-	cd-gpios = <&gpio1 27 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio1 27 GPIO_ACTIVE_LOW>;
 	no-1-8-v;
 	status = "okay";
 };
@@ -400,7 +400,7 @@
 &usdhc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc2>;
-	cd-gpios = <&gpio4 5 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio4 5 GPIO_ACTIVE_LOW>;
 	wp-gpios = <&gpio2 10 GPIO_ACTIVE_HIGH>;
 	no-1-8-v;
 	status = "okay";
diff --git a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
index 59e5d15..ff41f83 100644
--- a/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-cubox-i.dtsi
@@ -258,6 +258,6 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_cubox_i_usdhc2_aux &pinctrl_cubox_i_usdhc2>;
 	vmmc-supply = <&reg_3p3v>;
-	cd-gpios = <&gpio1 4 0>;
+	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-dfi-fs700-m60.dtsi b/arch/arm/boot/dts/imx6qdl-dfi-fs700-m60.dtsi
index 2c253d6..45e7c39 100644
--- a/arch/arm/boot/dts/imx6qdl-dfi-fs700-m60.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-dfi-fs700-m60.dtsi
@@ -1,3 +1,5 @@
+#include <dt-bindings/gpio/gpio.h>
+
 / {
 	regulators {
 		compatible = "simple-bus";
@@ -181,7 +183,7 @@
 &usdhc2 { /* module slot */
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc2>;
-	cd-gpios = <&gpio2 2 0>;
+	cd-gpios = <&gpio2 2 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi
index b5756c2..4493f6e 100644
--- a/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw52xx.dtsi
@@ -318,7 +318,7 @@
 &usdhc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
-	cd-gpios = <&gpio7 0 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio7 0 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi
index 86f03c1..a857d12 100644
--- a/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw53xx.dtsi
@@ -324,7 +324,7 @@
 &usdhc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
-	cd-gpios = <&gpio7 0 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio7 0 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi
index 4a8d97f..1afe338 100644
--- a/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-gw54xx.dtsi
@@ -417,7 +417,7 @@
 &usdhc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
-	cd-gpios = <&gpio7 0 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio7 0 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-hummingboard.dtsi b/arch/arm/boot/dts/imx6qdl-hummingboard.dtsi
index 62a82f3..6dd0b76 100644
--- a/arch/arm/boot/dts/imx6qdl-hummingboard.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-hummingboard.dtsi
@@ -299,6 +299,6 @@
 		&pinctrl_hummingboard_usdhc2
 	>;
 	vmmc-supply = <&reg_3p3v>;
-	cd-gpios = <&gpio1 4 0>;
+	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi b/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
index 3af16df..d7fe667 100644
--- a/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-nitrogen6x.dtsi
@@ -453,7 +453,7 @@
 &usdhc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
-	cd-gpios = <&gpio7 0 0>;
+	cd-gpios = <&gpio7 0 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
@@ -461,7 +461,7 @@
 &usdhc4 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc4>;
-	cd-gpios = <&gpio2 6 0>;
+	cd-gpios = <&gpio2 6 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
index 1ce6133..9e6ecd9 100644
--- a/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-phytec-pfla02.dtsi
@@ -409,8 +409,8 @@
 &usdhc2 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc2>;
-	cd-gpios = <&gpio1 4 0>;
-	wp-gpios = <&gpio1 2 0>;
+	cd-gpios = <&gpio1 4 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio1 2 GPIO_ACTIVE_HIGH>;
 	status = "disabled";
 };
 
@@ -418,7 +418,7 @@
         pinctrl-names = "default";
         pinctrl-0 = <&pinctrl_usdhc3
 		     &pinctrl_usdhc3_cdwp>;
-        cd-gpios = <&gpio1 27 0>;
-        wp-gpios = <&gpio1 29 0>;
+	cd-gpios = <&gpio1 27 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio1 29 GPIO_ACTIVE_HIGH>;
         status = "disabled";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-rex.dtsi b/arch/arm/boot/dts/imx6qdl-rex.dtsi
index 488a640..3373fd9 100644
--- a/arch/arm/boot/dts/imx6qdl-rex.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-rex.dtsi
@@ -342,7 +342,7 @@
 	pinctrl-0 = <&pinctrl_usdhc2>;
 	bus-width = <4>;
 	cd-gpios = <&gpio2 2 GPIO_ACTIVE_LOW>;
-	wp-gpios = <&gpio2 3 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 3 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
@@ -351,6 +351,6 @@
 	pinctrl-0 = <&pinctrl_usdhc3>;
 	bus-width = <4>;
 	cd-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>;
-	wp-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
index 3b24b126..e329ca5 100644
--- a/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabreauto.dtsi
@@ -467,8 +467,8 @@
 	pinctrl-0 = <&pinctrl_usdhc3>;
 	pinctrl-1 = <&pinctrl_usdhc3_100mhz>;
 	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
-	cd-gpios = <&gpio6 15 0>;
-	wp-gpios = <&gpio1 13 0>;
+	cd-gpios = <&gpio6 15 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio1 13 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi b/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi
index e00c44f..7823793 100644
--- a/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabrelite.dtsi
@@ -448,8 +448,8 @@
 &usdhc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
-	cd-gpios = <&gpio7 0 0>;
-	wp-gpios = <&gpio7 1 0>;
+	cd-gpios = <&gpio7 0 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio7 1 GPIO_ACTIVE_HIGH>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
@@ -457,7 +457,7 @@
 &usdhc4 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc4>;
-	cd-gpios = <&gpio2 6 0>;
+	cd-gpios = <&gpio2 6 GPIO_ACTIVE_LOW>;
 	vmmc-supply = <&reg_3p3v>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
index a626e6d..944eb81 100644
--- a/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-sabresd.dtsi
@@ -562,8 +562,8 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc2>;
 	bus-width = <8>;
-	cd-gpios = <&gpio2 2 0>;
-	wp-gpios = <&gpio2 3 0>;
+	cd-gpios = <&gpio2 2 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 3 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
@@ -571,8 +571,8 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
 	bus-width = <8>;
-	cd-gpios = <&gpio2 0 0>;
-	wp-gpios = <&gpio2 1 0>;
+	cd-gpios = <&gpio2 0 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio2 1 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/imx6qdl-tx6.dtsi b/arch/arm/boot/dts/imx6qdl-tx6.dtsi
index f02b80b..da08de3 100644
--- a/arch/arm/boot/dts/imx6qdl-tx6.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-tx6.dtsi
@@ -680,7 +680,7 @@
 	pinctrl-0 = <&pinctrl_usdhc1>;
 	bus-width = <4>;
 	no-1-8-v;
-	cd-gpios = <&gpio7 2 0>;
+	cd-gpios = <&gpio7 2 GPIO_ACTIVE_LOW>;
 	fsl,wp-controller;
 	status = "okay";
 };
@@ -690,7 +690,7 @@
 	pinctrl-0 = <&pinctrl_usdhc2>;
 	bus-width = <4>;
 	no-1-8-v;
-	cd-gpios = <&gpio7 3 0>;
+	cd-gpios = <&gpio7 3 GPIO_ACTIVE_LOW>;
 	fsl,wp-controller;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl-wandboard.dtsi b/arch/arm/boot/dts/imx6qdl-wandboard.dtsi
index 5fb0916..9e096d8 100644
--- a/arch/arm/boot/dts/imx6qdl-wandboard.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-wandboard.dtsi
@@ -9,6 +9,8 @@
  *
  */
 
+#include <dt-bindings/gpio/gpio.h>
+
 / {
 	regulators {
 		compatible = "simple-bus";
@@ -250,13 +252,13 @@
 &usdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc1>;
-	cd-gpios = <&gpio1 2 0>;
+	cd-gpios = <&gpio1 2 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
 
 &usdhc3 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc3>;
-	cd-gpios = <&gpio3 9 0>;
+	cd-gpios = <&gpio3 9 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6qdl.dtsi b/arch/arm/boot/dts/imx6qdl.dtsi
index e6d1359..b57033e 100644
--- a/arch/arm/boot/dts/imx6qdl.dtsi
+++ b/arch/arm/boot/dts/imx6qdl.dtsi
@@ -181,10 +181,10 @@
 			interrupt-names = "msi";
 			#interrupt-cells = <1>;
 			interrupt-map-mask = <0 0 0 0x7>;
-			interrupt-map = <0 0 0 1 &intc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
-			                <0 0 0 2 &intc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
-			                <0 0 0 3 &intc GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
-			                <0 0 0 4 &intc GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
+			interrupt-map = <0 0 0 1 &gpc GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>,
+			                <0 0 0 2 &gpc GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
+			                <0 0 0 3 &gpc GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
+			                <0 0 0 4 &gpc GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&clks IMX6QDL_CLK_PCIE_AXI>,
 				 <&clks IMX6QDL_CLK_LVDS1_GATE>,
 				 <&clks IMX6QDL_CLK_PCIE_REF_125M>;
diff --git a/arch/arm/boot/dts/imx6sl-evk.dts b/arch/arm/boot/dts/imx6sl-evk.dts
index 945887d..b84dff2 100644
--- a/arch/arm/boot/dts/imx6sl-evk.dts
+++ b/arch/arm/boot/dts/imx6sl-evk.dts
@@ -617,8 +617,8 @@
 	pinctrl-1 = <&pinctrl_usdhc1_100mhz>;
 	pinctrl-2 = <&pinctrl_usdhc1_200mhz>;
 	bus-width = <8>;
-	cd-gpios = <&gpio4 7 0>;
-	wp-gpios = <&gpio4 6 0>;
+	cd-gpios = <&gpio4 7 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio4 6 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
@@ -627,8 +627,8 @@
 	pinctrl-0 = <&pinctrl_usdhc2>;
 	pinctrl-1 = <&pinctrl_usdhc2_100mhz>;
 	pinctrl-2 = <&pinctrl_usdhc2_200mhz>;
-	cd-gpios = <&gpio5 0 0>;
-	wp-gpios = <&gpio4 29 0>;
+	cd-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio4 29 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
 
@@ -637,6 +637,6 @@
 	pinctrl-0 = <&pinctrl_usdhc3>;
 	pinctrl-1 = <&pinctrl_usdhc3_100mhz>;
 	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
-	cd-gpios = <&gpio3 22 0>;
+	cd-gpios = <&gpio3 22 GPIO_ACTIVE_LOW>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx6sx-sabreauto.dts b/arch/arm/boot/dts/imx6sx-sabreauto.dts
index e3c0b63..115f3fd 100644
--- a/arch/arm/boot/dts/imx6sx-sabreauto.dts
+++ b/arch/arm/boot/dts/imx6sx-sabreauto.dts
@@ -49,7 +49,7 @@
 	pinctrl-1 = <&pinctrl_usdhc3_100mhz>;
 	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
 	bus-width = <8>;
-	cd-gpios = <&gpio7 10 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio7 10 GPIO_ACTIVE_LOW>;
 	wp-gpios = <&gpio3 19 GPIO_ACTIVE_HIGH>;
 	keep-power-in-suspend;
 	enable-sdio-wakeup;
@@ -61,7 +61,7 @@
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc4>;
 	bus-width = <8>;
-	cd-gpios = <&gpio7 11 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio7 11 GPIO_ACTIVE_LOW>;
 	no-1-8-v;
 	keep-power-in-suspend;
 	enable-sdio-wakup;
diff --git a/arch/arm/boot/dts/imx6sx-sdb.dtsi b/arch/arm/boot/dts/imx6sx-sdb.dtsi
index cef04ce..ac88c34 100644
--- a/arch/arm/boot/dts/imx6sx-sdb.dtsi
+++ b/arch/arm/boot/dts/imx6sx-sdb.dtsi
@@ -293,7 +293,7 @@
 	pinctrl-1 = <&pinctrl_usdhc3_100mhz>;
 	pinctrl-2 = <&pinctrl_usdhc3_200mhz>;
 	bus-width = <8>;
-	cd-gpios = <&gpio2 10 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio2 10 GPIO_ACTIVE_LOW>;
 	wp-gpios = <&gpio2 15 GPIO_ACTIVE_HIGH>;
 	keep-power-in-suspend;
 	enable-sdio-wakeup;
@@ -304,7 +304,7 @@
 &usdhc4 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc4>;
-	cd-gpios = <&gpio6 21 GPIO_ACTIVE_HIGH>;
+	cd-gpios = <&gpio6 21 GPIO_ACTIVE_LOW>;
 	wp-gpios = <&gpio6 20 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
diff --git a/arch/arm/boot/dts/imx7d-sdb.dts b/arch/arm/boot/dts/imx7d-sdb.dts
index 4d1a4b9..fdd1d7c 100644
--- a/arch/arm/boot/dts/imx7d-sdb.dts
+++ b/arch/arm/boot/dts/imx7d-sdb.dts
@@ -234,8 +234,8 @@
 &usdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_usdhc1>;
-	cd-gpios = <&gpio5 0 0>;
-	wp-gpios = <&gpio5 1 0>;
+	cd-gpios = <&gpio5 0 GPIO_ACTIVE_LOW>;
+	wp-gpios = <&gpio5 1 GPIO_ACTIVE_HIGH>;
 	enable-sdio-wakeup;
 	keep-power-in-suspend;
 	status = "okay";
diff --git a/arch/arm/boot/dts/k2e-clocks.dtsi b/arch/arm/boot/dts/k2e-clocks.dtsi
index 4773d6a..d56d68f 100644
--- a/arch/arm/boot/dts/k2e-clocks.dtsi
+++ b/arch/arm/boot/dts/k2e-clocks.dtsi
@@ -13,9 +13,8 @@
 		#clock-cells = <0>;
 		compatible = "ti,keystone,main-pll-clock";
 		clocks = <&refclksys>;
-		reg = <0x02620350 4>, <0x02310110 4>;
-		reg-names = "control", "multiplier";
-		fixed-postdiv = <2>;
+		reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+		reg-names = "control", "multiplier", "post-divider";
 	};
 
 	papllclk: papllclk@2620358 {
diff --git a/arch/arm/boot/dts/k2e.dtsi b/arch/arm/boot/dts/k2e.dtsi
index 50e555e..675fb8e 100644
--- a/arch/arm/boot/dts/k2e.dtsi
+++ b/arch/arm/boot/dts/k2e.dtsi
@@ -86,7 +86,7 @@
 			gpio,syscon-dev = <&devctrl 0x240>;
 		};
 
-		pcie@21020000 {
+		pcie1: pcie@21020000 {
 			compatible = "ti,keystone-pcie","snps,dw-pcie";
 			clocks = <&clkpcie1>;
 			clock-names = "pcie";
@@ -96,6 +96,7 @@
 			ranges = <0x81000000 0 0 0x23260000 0x4000 0x4000
 				0x82000000 0 0x60000000 0x60000000 0 0x10000000>;
 
+			status = "disabled";
 			device_type = "pci";
 			num-lanes = <2>;
 
@@ -130,10 +131,17 @@
 					<GIC_SPI 376 IRQ_TYPE_EDGE_RISING>;
 			};
 		};
+
+		mdio: mdio@24200f00 {
+			compatible	= "ti,keystone_mdio", "ti,davinci_mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x24200f00 0x100>;
+			status = "disabled";
+			clocks = <&clkcpgmac>;
+			clock-names = "fck";
+			bus_freq	= <2500000>;
+		};
 		/include/ "k2e-netcp.dtsi"
 	};
 };
-
-&mdio {
-	reg = <0x24200f00 0x100>;
-};
diff --git a/arch/arm/boot/dts/k2hk-clocks.dtsi b/arch/arm/boot/dts/k2hk-clocks.dtsi
index d5adee3..af9b719 100644
--- a/arch/arm/boot/dts/k2hk-clocks.dtsi
+++ b/arch/arm/boot/dts/k2hk-clocks.dtsi
@@ -22,9 +22,8 @@
 		#clock-cells = <0>;
 		compatible = "ti,keystone,main-pll-clock";
 		clocks = <&refclksys>;
-		reg = <0x02620350 4>, <0x02310110 4>;
-		reg-names = "control", "multiplier";
-		fixed-postdiv = <2>;
+		reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+		reg-names = "control", "multiplier", "post-divider";
 	};
 
 	papllclk: papllclk@2620358 {
diff --git a/arch/arm/boot/dts/k2hk.dtsi b/arch/arm/boot/dts/k2hk.dtsi
index ae64724..d0810a5 100644
--- a/arch/arm/boot/dts/k2hk.dtsi
+++ b/arch/arm/boot/dts/k2hk.dtsi
@@ -98,6 +98,17 @@
 			#gpio-cells = <2>;
 			gpio,syscon-dev = <&devctrl 0x25c>;
 		};
+
+		mdio: mdio@02090300 {
+			compatible	= "ti,keystone_mdio", "ti,davinci_mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x02090300 0x100>;
+			status = "disabled";
+			clocks = <&clkcpgmac>;
+			clock-names = "fck";
+			bus_freq	= <2500000>;
+		};
 		/include/ "k2hk-netcp.dtsi"
 	};
 };
diff --git a/arch/arm/boot/dts/k2l-clocks.dtsi b/arch/arm/boot/dts/k2l-clocks.dtsi
index eb1e3e2..ef8464b 100644
--- a/arch/arm/boot/dts/k2l-clocks.dtsi
+++ b/arch/arm/boot/dts/k2l-clocks.dtsi
@@ -22,9 +22,8 @@
 		#clock-cells = <0>;
 		compatible = "ti,keystone,main-pll-clock";
 		clocks = <&refclksys>;
-		reg = <0x02620350 4>, <0x02310110 4>;
-		reg-names = "control", "multiplier";
-		fixed-postdiv = <2>;
+		reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+		reg-names = "control", "multiplier", "post-divider";
 	};
 
 	papllclk: papllclk@2620358 {
diff --git a/arch/arm/boot/dts/k2l.dtsi b/arch/arm/boot/dts/k2l.dtsi
index 0e00748..49fd414 100644
--- a/arch/arm/boot/dts/k2l.dtsi
+++ b/arch/arm/boot/dts/k2l.dtsi
@@ -29,7 +29,6 @@
 	};
 
 	soc {
-
 		/include/ "k2l-clocks.dtsi"
 
 		uart2: serial@02348400 {
@@ -79,6 +78,17 @@
 			#gpio-cells = <2>;
 			gpio,syscon-dev = <&devctrl 0x24c>;
 		};
+
+		mdio: mdio@26200f00 {
+			compatible	= "ti,keystone_mdio", "ti,davinci_mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x26200f00 0x100>;
+			status = "disabled";
+			clocks = <&clkcpgmac>;
+			clock-names = "fck";
+			bus_freq	= <2500000>;
+		};
 		/include/ "k2l-netcp.dtsi"
 	};
 };
@@ -96,7 +106,3 @@
        /* Pin muxed. Enabled and configured by Bootloader */
        status = "disabled";
 };
-
-&mdio {
-	reg = <0x26200f00 0x100>;
-};
diff --git a/arch/arm/boot/dts/keystone.dtsi b/arch/arm/boot/dts/keystone.dtsi
index c06542b..72816d6 100644
--- a/arch/arm/boot/dts/keystone.dtsi
+++ b/arch/arm/boot/dts/keystone.dtsi
@@ -267,17 +267,6 @@
 				  1 0 0x21000A00 0x00000100>;
 		};
 
-		mdio: mdio@02090300 {
-			compatible	= "ti,keystone_mdio", "ti,davinci_mdio";
-			#address-cells = <1>;
-			#size-cells = <0>;
-			reg		= <0x02090300 0x100>;
-			status = "disabled";
-			clocks = <&clkpa>;
-			clock-names = "fck";
-			bus_freq	= <2500000>;
-		};
-
 		kirq0: keystone_irq@26202a0 {
 			compatible = "ti,keystone-irq";
 			interrupts = <GIC_SPI 4 IRQ_TYPE_EDGE_RISING>;
@@ -286,7 +275,7 @@
 			ti,syscon-dev = <&devctrl 0x2a0>;
 		};
 
-		pcie@21800000 {
+		pcie0: pcie@21800000 {
 			compatible = "ti,keystone-pcie", "snps,dw-pcie";
 			clocks = <&clkpcie>;
 			clock-names = "pcie";
@@ -296,6 +285,7 @@
 			ranges = <0x81000000 0 0 0x23250000 0 0x4000
 				0x82000000 0 0x50000000 0x50000000 0 0x10000000>;
 
+			status = "disabled";
 			device_type = "pci";
 			num-lanes = <2>;
 
diff --git a/arch/arm/boot/dts/omap2430.dtsi b/arch/arm/boot/dts/omap2430.dtsi
index 11a7963..2390f38 100644
--- a/arch/arm/boot/dts/omap2430.dtsi
+++ b/arch/arm/boot/dts/omap2430.dtsi
@@ -51,7 +51,8 @@
 				};
 
 				scm_conf: scm_conf@270 {
-					compatible = "syscon";
+					compatible = "syscon",
+						     "simple-bus";
 					reg = <0x270 0x240>;
 					#address-cells = <1>;
 					#size-cells = <1>;
diff --git a/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi b/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi
index 233c69e..df8908a 100644
--- a/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-common-lcd35.dtsi
@@ -120,7 +120,7 @@
 
 	lcd0: display@0 {
 		compatible = "lgphilips,lb035q02";
-		label = "lcd";
+		label = "lcd35";
 
 		reg = <1>;					/* CS1 */
 		spi-max-frequency = <10000000>;
diff --git a/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi b/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi
index f5395b7..048fd21 100644
--- a/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi
+++ b/arch/arm/boot/dts/omap3-overo-common-lcd43.dtsi
@@ -98,7 +98,7 @@
 
 	lcd0: display@0 {
 		compatible = "samsung,lte430wq-f0c", "panel-dpi";
-		label = "lcd";
+		label = "lcd43";
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&lte430_pins>;
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index f884d6a..abc4473 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -191,7 +191,8 @@
 				};
 
 				omap4_padconf_global: omap4_padconf_global@5a0 {
-					compatible = "syscon";
+					compatible = "syscon",
+						     "simple-bus";
 					reg = <0x5a0 0x170>;
 					#address-cells = <1>;
 					#size-cells = <1>;
@@ -551,6 +552,7 @@
 			reg = <0x4a066000 0x100>;
 			interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "mmu_dsp";
+			#iommu-cells = <0>;
 		};
 
 		mmu_ipu: mmu@55082000 {
@@ -558,6 +560,7 @@
 			reg = <0x55082000 0x100>;
 			interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "mmu_ipu";
+			#iommu-cells = <0>;
 			ti,iommu-bus-err-back;
 		};
 
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index 7d24ae0..b1a1263 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -180,7 +180,8 @@
 				};
 
 				omap5_padconf_global: omap5_padconf_global@5a0 {
-					compatible = "syscon";
+					compatible = "syscon",
+						     "simple-bus";
 					reg = <0x5a0 0xec>;
 					#address-cells = <1>;
 					#size-cells = <1>;
@@ -612,6 +613,7 @@
 			reg = <0x4a066000 0x100>;
 			interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "mmu_dsp";
+			#iommu-cells = <0>;
 		};
 
 		mmu_ipu: mmu@55082000 {
@@ -619,6 +621,7 @@
 			reg = <0x55082000 0x100>;
 			interrupts = <GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>;
 			ti,hwmods = "mmu_ipu";
+			#iommu-cells = <0>;
 			ti,iommu-bus-err-back;
 		};
 
diff --git a/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts b/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts
index 71468a7..5e17fd1 100644
--- a/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts
+++ b/arch/arm/boot/dts/socfpga_cyclone5_sockit.dts
@@ -60,6 +60,22 @@
 	rxc-skew-ps = <2000>;
 };
 
+&gpio2 {
+	status = "okay";
+};
+
+&i2c1 {
+	status = "okay";
+
+	accel1: accelerometer@53 {
+		compatible = "adi,adxl345";
+		reg = <0x53>;
+
+		interrupt-parent = <&portc>;
+		interrupts = <3 2>;
+	};
+};
+
 &mmc0 {
 	vmmc-supply = <&regulator_3_3v>;
 	vqmmc-supply = <&regulator_3_3v>;
@@ -68,19 +84,3 @@
 &usb1 {
 	status = "okay";
 };
-
-&gpio2 {
-	status = "okay";
-};
-
-&i2c1{
-	status = "okay";
-
-	accel1: accel1@53{
-		compatible = "adxl34x";
-		reg = <0x53>;
-
-		interrupt-parent = < &portc >;
-		interrupts = <3 2>;
-	};
-};
diff --git a/arch/arm/boot/dts/spear1310-evb.dts b/arch/arm/boot/dts/spear1310-evb.dts
index d42c84b..e488572 100644
--- a/arch/arm/boot/dts/spear1310-evb.dts
+++ b/arch/arm/boot/dts/spear1310-evb.dts
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr1310 Evaluation Baord
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear1310.dtsi b/arch/arm/boot/dts/spear1310.dtsi
index 9d34292..54bc6d3 100644
--- a/arch/arm/boot/dts/spear1310.dtsi
+++ b/arch/arm/boot/dts/spear1310.dtsi
@@ -1,7 +1,7 @@
 /*
  * DTS file for all SPEAr1310 SoCs
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear1340-evb.dts b/arch/arm/boot/dts/spear1340-evb.dts
index b23e05e..c611f56 100644
--- a/arch/arm/boot/dts/spear1340-evb.dts
+++ b/arch/arm/boot/dts/spear1340-evb.dts
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr1340 Evaluation Baord
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear1340.dtsi b/arch/arm/boot/dts/spear1340.dtsi
index 13e1aa3..df2232d 100644
--- a/arch/arm/boot/dts/spear1340.dtsi
+++ b/arch/arm/boot/dts/spear1340.dtsi
@@ -1,7 +1,7 @@
 /*
  * DTS file for all SPEAr1340 SoCs
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear13xx.dtsi b/arch/arm/boot/dts/spear13xx.dtsi
index 40accc8..14594ce 100644
--- a/arch/arm/boot/dts/spear13xx.dtsi
+++ b/arch/arm/boot/dts/spear13xx.dtsi
@@ -1,7 +1,7 @@
 /*
  * DTS file for all SPEAr13xx SoCs
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear300-evb.dts b/arch/arm/boot/dts/spear300-evb.dts
index 5de1431..e859e82 100644
--- a/arch/arm/boot/dts/spear300-evb.dts
+++ b/arch/arm/boot/dts/spear300-evb.dts
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr300 Evaluation Baord
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear300.dtsi b/arch/arm/boot/dts/spear300.dtsi
index f79b3df..f4e92e5 100644
--- a/arch/arm/boot/dts/spear300.dtsi
+++ b/arch/arm/boot/dts/spear300.dtsi
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr300 SoC
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear310-evb.dts b/arch/arm/boot/dts/spear310-evb.dts
index b096329..070f2c1 100644
--- a/arch/arm/boot/dts/spear310-evb.dts
+++ b/arch/arm/boot/dts/spear310-evb.dts
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr310 Evaluation Baord
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear310.dtsi b/arch/arm/boot/dts/spear310.dtsi
index 9537208..da210b4 100644
--- a/arch/arm/boot/dts/spear310.dtsi
+++ b/arch/arm/boot/dts/spear310.dtsi
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr310 SoC
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear320-evb.dts b/arch/arm/boot/dts/spear320-evb.dts
index fdedbb5..1b10344 100644
--- a/arch/arm/boot/dts/spear320-evb.dts
+++ b/arch/arm/boot/dts/spear320-evb.dts
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr320 Evaluation Baord
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear320.dtsi b/arch/arm/boot/dts/spear320.dtsi
index ffea342..22be6e5 100644
--- a/arch/arm/boot/dts/spear320.dtsi
+++ b/arch/arm/boot/dts/spear320.dtsi
@@ -1,7 +1,7 @@
 /*
  * DTS file for SPEAr320 SoC
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/spear3xx.dtsi b/arch/arm/boot/dts/spear3xx.dtsi
index f0e3fcf..118135d 100644
--- a/arch/arm/boot/dts/spear3xx.dtsi
+++ b/arch/arm/boot/dts/spear3xx.dtsi
@@ -1,7 +1,7 @@
 /*
  * DTS file for all SPEAr3xx SoCs
  *
- * Copyright 2012 Viresh Kumar <viresh.linux@gmail.com>
+ * Copyright 2012 Viresh Kumar <vireshk@kernel.org>
  *
  * The code contained herein is licensed under the GNU General Public
  * License. You may obtain a copy of the GNU General Public License
diff --git a/arch/arm/boot/dts/ste-ccu8540.dts b/arch/arm/boot/dts/ste-ccu8540.dts
index 32dd55e..6eaaf63 100644
--- a/arch/arm/boot/dts/ste-ccu8540.dts
+++ b/arch/arm/boot/dts/ste-ccu8540.dts
@@ -17,6 +17,13 @@
 	model = "ST-Ericsson U8540 platform with Device Tree";
 	compatible = "st-ericsson,ccu8540", "st-ericsson,u8540";
 
+	/* This stablilizes the serial port enumeration */
+	aliases {
+		serial0 = &ux500_serial0;
+		serial1 = &ux500_serial1;
+		serial2 = &ux500_serial2;
+	};
+
 	memory@0 {
 		device_type = "memory";
 		reg = <0x20000000 0x1f000000>, <0xc0000000 0x3f000000>;
diff --git a/arch/arm/boot/dts/ste-ccu9540.dts b/arch/arm/boot/dts/ste-ccu9540.dts
index 651c56d..c8b8158 100644
--- a/arch/arm/boot/dts/ste-ccu9540.dts
+++ b/arch/arm/boot/dts/ste-ccu9540.dts
@@ -16,6 +16,13 @@
 	model = "ST-Ericsson CCU9540 platform with Device Tree";
 	compatible = "st-ericsson,ccu9540", "st-ericsson,u9540";
 
+	/* This stablilizes the serial port enumeration */
+	aliases {
+		serial0 = &ux500_serial0;
+		serial1 = &ux500_serial1;
+		serial2 = &ux500_serial2;
+	};
+
 	memory {
 		reg = <0x00000000 0x20000000>;
 	};
diff --git a/arch/arm/boot/dts/ste-dbx5x0.dtsi b/arch/arm/boot/dts/ste-dbx5x0.dtsi
index 853684a..b8f81fb 100644
--- a/arch/arm/boot/dts/ste-dbx5x0.dtsi
+++ b/arch/arm/boot/dts/ste-dbx5x0.dtsi
@@ -15,6 +15,33 @@
 #include "skeleton.dtsi"
 
 / {
+	cpus {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		enable-method = "ste,dbx500-smp";
+
+		cpu-map {
+			cluster0 {
+				core0 {
+					cpu = <&CPU0>;
+				};
+				core1 {
+					cpu = <&CPU1>;
+				};
+			};
+		};
+		CPU0: cpu@300 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <0x300>;
+		};
+		CPU1: cpu@301 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a9";
+			reg = <0x301>;
+		};
+	};
+
 	soc {
 		#address-cells = <1>;
 		#size-cells = <1>;
@@ -22,32 +49,6 @@
 		interrupt-parent = <&intc>;
 		ranges;
 
-		cpus {
-			#address-cells = <1>;
-			#size-cells = <0>;
-
-			cpu-map {
-				cluster0 {
-					core0 {
-						cpu = <&CPU0>;
-					};
-					core1 {
-						cpu = <&CPU1>;
-					};
-				};
-			};
-			CPU0: cpu@0 {
-				device_type = "cpu";
-				compatible = "arm,cortex-a9";
-				reg = <0>;
-			};
-			CPU1: cpu@1 {
-				device_type = "cpu";
-				compatible = "arm,cortex-a9";
-				reg = <1>;
-			};
-		};
-
 		ptm@801ae000 {
 			compatible = "arm,coresight-etm3x", "arm,primecell";
 			reg = <0x801ae000 0x1000>;
@@ -971,7 +972,7 @@
 			power-domains = <&pm_domains DOMAIN_VAPE>;
 		};
 
-		uart@80120000 {
+		ux500_serial0: uart@80120000 {
 			compatible = "arm,pl011", "arm,primecell";
 			reg = <0x80120000 0x1000>;
 			interrupts = <0 11 IRQ_TYPE_LEVEL_HIGH>;
@@ -986,7 +987,7 @@
 			status = "disabled";
 		};
 
-		uart@80121000 {
+		ux500_serial1: uart@80121000 {
 			compatible = "arm,pl011", "arm,primecell";
 			reg = <0x80121000 0x1000>;
 			interrupts = <0 19 IRQ_TYPE_LEVEL_HIGH>;
@@ -1001,7 +1002,7 @@
 			status = "disabled";
 		};
 
-		uart@80007000 {
+		ux500_serial2: uart@80007000 {
 			compatible = "arm,pl011", "arm,primecell";
 			reg = <0x80007000 0x1000>;
 			interrupts = <0 26 IRQ_TYPE_LEVEL_HIGH>;
diff --git a/arch/arm/boot/dts/ste-href.dtsi b/arch/arm/boot/dts/ste-href.dtsi
index 744c1e3..6d8ce15 100644
--- a/arch/arm/boot/dts/ste-href.dtsi
+++ b/arch/arm/boot/dts/ste-href.dtsi
@@ -32,11 +32,11 @@
 			status = "okay";
 		};
 
+		/* This UART is unused and thus left disabled */
 		uart@80121000 {
 			pinctrl-names = "default", "sleep";
 			pinctrl-0 = <&uart1_default_mode>;
 			pinctrl-1 = <&uart1_sleep_mode>;
-			status = "okay";
 		};
 
 		uart@80007000 {
diff --git a/arch/arm/boot/dts/ste-hrefprev60-stuib.dts b/arch/arm/boot/dts/ste-hrefprev60-stuib.dts
index 2b1cb5b..18e9795 100644
--- a/arch/arm/boot/dts/ste-hrefprev60-stuib.dts
+++ b/arch/arm/boot/dts/ste-hrefprev60-stuib.dts
@@ -17,6 +17,13 @@
 	model = "ST-Ericsson HREF (pre-v60) and ST UIB";
 	compatible = "st-ericsson,mop500", "st-ericsson,u8500";
 
+	/* This stablilizes the serial port enumeration */
+	aliases {
+		serial0 = &ux500_serial0;
+		serial1 = &ux500_serial1;
+		serial2 = &ux500_serial2;
+	};
+
 	soc {
 		/* Reset line for the BU21013 touchscreen */
 		i2c@80110000 {
diff --git a/arch/arm/boot/dts/ste-hrefprev60-tvk.dts b/arch/arm/boot/dts/ste-hrefprev60-tvk.dts
index 59523f8..2473991 100644
--- a/arch/arm/boot/dts/ste-hrefprev60-tvk.dts
+++ b/arch/arm/boot/dts/ste-hrefprev60-tvk.dts
@@ -16,4 +16,11 @@
 / {
 	model = "ST-Ericsson HREF (pre-v60) and TVK1281618 UIB";
 	compatible = "st-ericsson,mop500", "st-ericsson,u8500";
+
+	/* This stablilizes the serial port enumeration */
+	aliases {
+		serial0 = &ux500_serial0;
+		serial1 = &ux500_serial1;
+		serial2 = &ux500_serial2;
+	};
 };
diff --git a/arch/arm/boot/dts/ste-hrefprev60.dtsi b/arch/arm/boot/dts/ste-hrefprev60.dtsi
index 7f3975b..b0278f4 100644
--- a/arch/arm/boot/dts/ste-hrefprev60.dtsi
+++ b/arch/arm/boot/dts/ste-hrefprev60.dtsi
@@ -23,6 +23,11 @@
 	};
 
 	soc {
+		/* Enable UART1 on this board */
+		uart@80121000 {
+			status = "okay";
+		};
+
 		i2c@80004000 {
 			tps61052@33 {
 				compatible = "tps61052";
diff --git a/arch/arm/boot/dts/ste-hrefv60plus-stuib.dts b/arch/arm/boot/dts/ste-hrefv60plus-stuib.dts
index 8c6a2de..c2e1ba0 100644
--- a/arch/arm/boot/dts/ste-hrefv60plus-stuib.dts
+++ b/arch/arm/boot/dts/ste-hrefv60plus-stuib.dts
@@ -19,6 +19,13 @@
 	model = "ST-Ericsson HREF (v60+) and ST UIB";
 	compatible = "st-ericsson,hrefv60+", "st-ericsson,u8500";
 
+	/* This stablilizes the serial port enumeration */
+	aliases {
+		serial0 = &ux500_serial0;
+		serial1 = &ux500_serial1;
+		serial2 = &ux500_serial2;
+	};
+
 	soc {
 		/* Reset line for the BU21013 touchscreen */
 		i2c@80110000 {
diff --git a/arch/arm/boot/dts/ste-hrefv60plus-tvk.dts b/arch/arm/boot/dts/ste-hrefv60plus-tvk.dts
index d53cccd..ebd8547 100644
--- a/arch/arm/boot/dts/ste-hrefv60plus-tvk.dts
+++ b/arch/arm/boot/dts/ste-hrefv60plus-tvk.dts
@@ -18,4 +18,11 @@
 / {
 	model = "ST-Ericsson HREF (v60+) and TVK1281618 UIB";
 	compatible = "st-ericsson,hrefv60+", "st-ericsson,u8500";
+
+	/* This stablilizes the serial port enumeration */
+	aliases {
+		serial0 = &ux500_serial0;
+		serial1 = &ux500_serial1;
+		serial2 = &ux500_serial2;
+	};
 };
diff --git a/arch/arm/boot/dts/ste-hrefv60plus.dtsi b/arch/arm/boot/dts/ste-hrefv60plus.dtsi
index a4bc9e7..810cda7 100644
--- a/arch/arm/boot/dts/ste-hrefv60plus.dtsi
+++ b/arch/arm/boot/dts/ste-hrefv60plus.dtsi
@@ -43,15 +43,26 @@
 				  <&vaudio_hf_hrefv60_mode>,
 				  <&gbf_hrefv60_mode>,
 				  <&hdtv_hrefv60_mode>,
-				  <&touch_hrefv60_mode>;
+				  <&touch_hrefv60_mode>,
+				  <&gpios_hrefv60_mode>;
 
 			sdi0 {
-				/* SD card detect GPIO pin, extend default state */
 				sdi0_default_mode: sdi0_default {
+					/* SD card detect GPIO pin, extend default state */
 					default_hrefv60_cfg1 {
 						pins = "GPIO95_E8";
 						ste,config = <&gpio_in_pu>;
 					};
+					/* VMMCI level-shifter enable */
+					default_hrefv60_cfg2 {
+						pins = "GPIO169_D22";
+						ste,config = <&gpio_out_lo>;
+					};
+					/* VMMCI level-shifter voltage select */
+					default_hrefv60_cfg3 {
+						pins = "GPIO5_AG6";
+						ste,config = <&gpio_out_hi>;
+					};
 				};
 			};
 			ipgpio {
@@ -213,6 +224,16 @@
 					};
 				};
 			};
+			gpios {
+				/* Dangling GPIO pins */
+				gpios_hrefv60_mode: gpios_hrefv60 {
+					default_cfg1 {
+						/* Normally UART1 RXD, now dangling */
+						pins = "GPIO4_AH6";
+						ste,config = <&in_pu>;
+					};
+				};
+			};
 		};
 	};
 };
diff --git a/arch/arm/boot/dts/ste-nomadik-nhk15.dts b/arch/arm/boot/dts/ste-nomadik-nhk15.dts
index 3d0b875..3d25dba 100644
--- a/arch/arm/boot/dts/ste-nomadik-nhk15.dts
+++ b/arch/arm/boot/dts/ste-nomadik-nhk15.dts
@@ -17,6 +17,7 @@
 	};
 
 	aliases {
+		serial1 = &uart1;
 		stmpe-i2c0 = &stmpe0;
 		stmpe-i2c1 = &stmpe1;
 	};
diff --git a/arch/arm/boot/dts/ste-nomadik-s8815.dts b/arch/arm/boot/dts/ste-nomadik-s8815.dts
index 85d3b95..3c140d0 100644
--- a/arch/arm/boot/dts/ste-nomadik-s8815.dts
+++ b/arch/arm/boot/dts/ste-nomadik-s8815.dts
@@ -15,6 +15,10 @@
 		bootargs = "root=/dev/ram0 console=ttyAMA1,115200n8 earlyprintk";
 	};
 
+	aliases {
+		serial1 = &uart1;
+	};
+
 	src@101e0000 {
 		/* These chrystal drivers are not used on this board */
 		disable-sxtalo;
diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
index 9a5f2ba..ef794a3 100644
--- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
+++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
@@ -757,6 +757,7 @@
 			clock-names = "uartclk", "apb_pclk";
 			pinctrl-names = "default";
 			pinctrl-0 = <&uart0_default_mux>;
+			status = "disabled";
 		};
 
 		uart1: uart@101fb000 {
diff --git a/arch/arm/boot/dts/ste-snowball.dts b/arch/arm/boot/dts/ste-snowball.dts
index 9edadc3..32a5ccb 100644
--- a/arch/arm/boot/dts/ste-snowball.dts
+++ b/arch/arm/boot/dts/ste-snowball.dts
@@ -18,6 +18,13 @@
 	model = "Calao Systems Snowball platform with device tree";
 	compatible = "calaosystems,snowball-a9500", "st-ericsson,u9500";
 
+	/* This stablilizes the serial port enumeration */
+	aliases {
+		serial0 = &ux500_serial0;
+		serial1 = &ux500_serial1;
+		serial2 = &ux500_serial2;
+	};
+
 	memory {
 		reg = <0x00000000 0x20000000>;
 	};
@@ -223,11 +230,11 @@
 			status = "okay";
 		};
 
+		/* This UART is unused and thus left disabled */
 		uart@80121000 {
 			pinctrl-names = "default", "sleep";
 			pinctrl-0 = <&uart1_default_mode>;
 			pinctrl-1 = <&uart1_sleep_mode>;
-			status = "okay";
 		};
 
 		uart@80007000 {
@@ -452,7 +459,21 @@
 						pins = "GPIO21_AB3"; /* DAT31DIR */
 						ste,config = <&out_hi>;
 					};
-
+					/* SD card detect GPIO pin, extend default state */
+					snowball_cfg2 {
+						pins = "GPIO218_AH11";
+						ste,config = <&gpio_in_pu>;
+					};
+					/* VMMCI level-shifter enable */
+					snowball_cfg3 {
+						pins = "GPIO217_AH12";
+						ste,config = <&gpio_out_lo>;
+					};
+					/* VMMCI level-shifter voltage select */
+					snowball_cfg4 {
+						pins = "GPIO228_AJ6";
+						ste,config = <&gpio_out_hi>;
+					};
 				};
 			};
 			ssp0 {
diff --git a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
index 107395c..17f63f7 100644
--- a/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
+++ b/arch/arm/boot/dts/vexpress-v2p-ca15_a7.dts
@@ -150,6 +150,16 @@
 			interface-type = "ace";
 			reg = <0x5000 0x1000>;
 		};
+
+		pmu@9000 {
+			 compatible = "arm,cci-400-pmu,r0";
+			 reg = <0x9000 0x5000>;
+			 interrupts = <0 105 4>,
+				      <0 101 4>,
+				      <0 102 4>,
+				      <0 103 4>,
+				      <0 104 4>;
+		};
 	};
 
 	memory-controller@7ffd0000 {
@@ -187,11 +197,22 @@
 			     <1 10 0xf08>;
 	};
 
-	pmu {
+	pmu_a15 {
 		compatible = "arm,cortex-a15-pmu";
 		interrupts = <0 68 4>,
 			     <0 69 4>;
-		interrupt-affinity = <&cpu0>, <&cpu1>;
+		interrupt-affinity = <&cpu0>,
+				     <&cpu1>;
+	};
+
+	pmu_a7 {
+		compatible = "arm,cortex-a7-pmu";
+		interrupts = <0 128 4>,
+			     <0 129 4>,
+			     <0 130 4>;
+		interrupt-affinity = <&cpu2>,
+				     <&cpu3>,
+				     <&cpu4>;
 	};
 
 	oscclk6a: oscclk6a {
diff --git a/arch/arm/configs/multi_v7_defconfig b/arch/arm/configs/multi_v7_defconfig
index 6d83a1b..5fd8df6 100644
--- a/arch/arm/configs/multi_v7_defconfig
+++ b/arch/arm/configs/multi_v7_defconfig
@@ -353,7 +353,6 @@
 CONFIG_POWER_RESET_GPIO=y
 CONFIG_POWER_RESET_GPIO_RESTART=y
 CONFIG_POWER_RESET_KEYSTONE=y
-CONFIG_POWER_RESET_SUN6I=y
 CONFIG_POWER_RESET_RMOBILE=y
 CONFIG_SENSORS_LM90=y
 CONFIG_SENSORS_LM95245=y
diff --git a/arch/arm/configs/sunxi_defconfig b/arch/arm/configs/sunxi_defconfig
index 8ecba00..7ebc346b 100644
--- a/arch/arm/configs/sunxi_defconfig
+++ b/arch/arm/configs/sunxi_defconfig
@@ -2,6 +2,7 @@
 CONFIG_HIGH_RES_TIMERS=y
 CONFIG_BLK_DEV_INITRD=y
 CONFIG_PERF_EVENTS=y
+CONFIG_MODULES=y
 CONFIG_ARCH_SUNXI=y
 CONFIG_SMP=y
 CONFIG_NR_CPUS=8
@@ -77,7 +78,6 @@
 CONFIG_GPIO_SYSFS=y
 CONFIG_POWER_SUPPLY=y
 CONFIG_POWER_RESET=y
-CONFIG_POWER_RESET_SUN6I=y
 CONFIG_THERMAL=y
 CONFIG_CPU_THERMAL=y
 CONFIG_WATCHDOG=y
@@ -87,6 +87,10 @@
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_REGULATOR_AXP20X=y
 CONFIG_REGULATOR_GPIO=y
+CONFIG_FB=y
+CONFIG_FB_SIMPLE=y
+CONFIG_FRAMEBUFFER_CONSOLE=y
+CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY=y
 CONFIG_USB=y
 CONFIG_USB_EHCI_HCD=y
 CONFIG_USB_EHCI_HCD_PLATFORM=y
diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 83c5019..30b3bc1 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -13,6 +13,7 @@
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += msgbuf.h
 generic-y += param.h
 generic-y += parport.h
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 1c3938f..4859820 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -140,16 +140,11 @@
  * The _caller variety takes a __builtin_return_address(0) value for
  * /proc/vmalloc to use - and should only be used in non-inline functions.
  */
-extern void __iomem *__arm_ioremap_pfn_caller(unsigned long, unsigned long,
-	size_t, unsigned int, void *);
 extern void __iomem *__arm_ioremap_caller(phys_addr_t, size_t, unsigned int,
 	void *);
-
 extern void __iomem *__arm_ioremap_pfn(unsigned long, unsigned long, size_t, unsigned int);
-extern void __iomem *__arm_ioremap(phys_addr_t, size_t, unsigned int);
 extern void __iomem *__arm_ioremap_exec(phys_addr_t, size_t, bool cached);
 extern void __iounmap(volatile void __iomem *addr);
-extern void __arm_iounmap(volatile void __iomem *addr);
 
 extern void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t,
 	unsigned int, void *);
@@ -321,21 +316,24 @@
 static inline void memset_io(volatile void __iomem *dst, unsigned c,
 	size_t count)
 {
-	memset((void __force *)dst, c, count);
+	extern void mmioset(void *, unsigned int, size_t);
+	mmioset((void __force *)dst, c, count);
 }
 #define memset_io(dst,c,count) memset_io(dst,c,count)
 
 static inline void memcpy_fromio(void *to, const volatile void __iomem *from,
 	size_t count)
 {
-	memcpy(to, (const void __force *)from, count);
+	extern void mmiocpy(void *, const void *, size_t);
+	mmiocpy(to, (const void __force *)from, count);
 }
 #define memcpy_fromio(to,from,count) memcpy_fromio(to,from,count)
 
 static inline void memcpy_toio(volatile void __iomem *to, const void *from,
 	size_t count)
 {
-	memcpy((void __force *)to, from, count);
+	extern void mmiocpy(void *, const void *, size_t);
+	mmiocpy((void __force *)to, from, count);
 }
 #define memcpy_toio(to,from,count) memcpy_toio(to,from,count)
 
@@ -348,18 +346,61 @@
 #endif	/* readl */
 
 /*
- * ioremap and friends.
+ * ioremap() and friends.
  *
- * ioremap takes a PCI memory address, as specified in
- * Documentation/io-mapping.txt.
+ * ioremap() takes a resource address, and size.  Due to the ARM memory
+ * types, it is important to use the correct ioremap() function as each
+ * mapping has specific properties.
  *
+ * Function		Memory type	Cacheability	Cache hint
+ * ioremap()		Device		n/a		n/a
+ * ioremap_nocache()	Device		n/a		n/a
+ * ioremap_cache()	Normal		Writeback	Read allocate
+ * ioremap_wc()		Normal		Non-cacheable	n/a
+ * ioremap_wt()		Normal		Non-cacheable	n/a
+ *
+ * All device mappings have the following properties:
+ * - no access speculation
+ * - no repetition (eg, on return from an exception)
+ * - number, order and size of accesses are maintained
+ * - unaligned accesses are "unpredictable"
+ * - writes may be delayed before they hit the endpoint device
+ *
+ * ioremap_nocache() is the same as ioremap() as there are too many device
+ * drivers using this for device registers, and documentation which tells
+ * people to use it for such for this to be any different.  This is not a
+ * safe fallback for memory-like mappings, or memory regions where the
+ * compiler may generate unaligned accesses - eg, via inlining its own
+ * memcpy.
+ *
+ * All normal memory mappings have the following properties:
+ * - reads can be repeated with no side effects
+ * - repeated reads return the last value written
+ * - reads can fetch additional locations without side effects
+ * - writes can be repeated (in certain cases) with no side effects
+ * - writes can be merged before accessing the target
+ * - unaligned accesses can be supported
+ * - ordering is not guaranteed without explicit dependencies or barrier
+ *   instructions
+ * - writes may be delayed before they hit the endpoint memory
+ *
+ * The cache hint is only a performance hint: CPUs may alias these hints.
+ * Eg, a CPU not implementing read allocate but implementing write allocate
+ * will provide a write allocate mapping instead.
  */
-#define ioremap(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_nocache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE)
-#define ioremap_cache(cookie,size)	__arm_ioremap((cookie), (size), MT_DEVICE_CACHED)
-#define ioremap_wc(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE_WC)
-#define ioremap_wt(cookie,size)		__arm_ioremap((cookie), (size), MT_DEVICE)
-#define iounmap				__arm_iounmap
+void __iomem *ioremap(resource_size_t res_cookie, size_t size);
+#define ioremap ioremap
+#define ioremap_nocache ioremap
+
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size);
+#define ioremap_cache ioremap_cache
+
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size);
+#define ioremap_wc ioremap_wc
+#define ioremap_wt ioremap_wc
+
+void iounmap(volatile void __iomem *iomem_cookie);
+#define iounmap iounmap
 
 /*
  * io{read,write}{16,32}be() macros
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 3a72d69..b7f6fb4 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -275,7 +275,7 @@
  */
 #define __pa(x)			__virt_to_phys((unsigned long)(x))
 #define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
-#define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
+#define pfn_to_kaddr(pfn)	__va((phys_addr_t)(pfn) << PAGE_SHIFT)
 
 extern phys_addr_t (*arch_virt_to_idmap)(unsigned long x);
 
@@ -286,7 +286,7 @@
  */
 static inline phys_addr_t __virt_to_idmap(unsigned long x)
 {
-	if (arch_virt_to_idmap)
+	if (IS_ENABLED(CONFIG_MMU) && arch_virt_to_idmap)
 		return arch_virt_to_idmap(x);
 	else
 		return __virt_to_phys(x);
diff --git a/arch/arm/include/asm/mm-arch-hooks.h b/arch/arm/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 7056660..0000000
--- a/arch/arm/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_ARM_MM_ARCH_HOOKS_H
-#define _ASM_ARM_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_ARM_MM_ARCH_HOOKS_H */
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index bfd662e..aeddd28 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -129,7 +129,36 @@
 
 /*
  * These are the memory types, defined to be compatible with
- * pre-ARMv6 CPUs cacheable and bufferable bits:   XXCB
+ * pre-ARMv6 CPUs cacheable and bufferable bits: n/a,n/a,C,B
+ * ARMv6+ without TEX remapping, they are a table index.
+ * ARMv6+ with TEX remapping, they correspond to n/a,TEX(0),C,B
+ *
+ * MT type		Pre-ARMv6	ARMv6+ type / cacheable status
+ * UNCACHED		Uncached	Strongly ordered
+ * BUFFERABLE		Bufferable	Normal memory / non-cacheable
+ * WRITETHROUGH		Writethrough	Normal memory / write through
+ * WRITEBACK		Writeback	Normal memory / write back, read alloc
+ * MINICACHE		Minicache	N/A
+ * WRITEALLOC		Writeback	Normal memory / write back, write alloc
+ * DEV_SHARED		Uncached	Device memory (shared)
+ * DEV_NONSHARED	Uncached	Device memory (non-shared)
+ * DEV_WC		Bufferable	Normal memory / non-cacheable
+ * DEV_CACHED		Writeback	Normal memory / write back, read alloc
+ * VECTORS		Variable	Normal memory / variable
+ *
+ * All normal memory mappings have the following properties:
+ * - reads can be repeated with no side effects
+ * - repeated reads return the last value written
+ * - reads can fetch additional locations without side effects
+ * - writes can be repeated (in certain cases) with no side effects
+ * - writes can be merged before accessing the target
+ * - unaligned accesses can be supported
+ *
+ * All device mappings have the following properties:
+ * - no access speculation
+ * - no repetition (eg, on return from an exception)
+ * - number, order and size of accesses are maintained
+ * - unaligned accesses are "unpredictable"
  */
 #define L_PTE_MT_UNCACHED	(_AT(pteval_t, 0x00) << 2)	/* 0000 */
 #define L_PTE_MT_BUFFERABLE	(_AT(pteval_t, 0x01) << 2)	/* 0001 */
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index a88671c..5e5a51a 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -50,6 +50,9 @@
 
 extern void fpundefinstr(void);
 
+void mmioset(void *, unsigned int, size_t);
+void mmiocpy(void *, const void *, size_t);
+
 	/* platform dependent support */
 EXPORT_SYMBOL(arm_delay_ops);
 
@@ -88,6 +91,9 @@
 EXPORT_SYMBOL(memchr);
 EXPORT_SYMBOL(__memzero);
 
+EXPORT_SYMBOL(mmioset);
+EXPORT_SYMBOL(mmiocpy);
+
 #ifdef CONFIG_MMU
 EXPORT_SYMBOL(copy_page);
 
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 7dac308..cb4fb1e 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -410,7 +410,7 @@
 	zero_fp
 
 	.if	\trace
-#ifdef CONFIG_IRQSOFF_TRACER
+#ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_off
 #endif
 	ct_user_exit save = 0
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 92828a1..b48dd4f 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -61,6 +61,7 @@
 	movlt	scno, #(__NR_restart_syscall - __NR_SYSCALL_BASE)
 	ldmia	sp, {r0 - r6}			@ have to reload r0 - r6
 	b	local_restart			@ ... and off we go
+ENDPROC(ret_fast_syscall)
 
 /*
  * "slow" syscall return path.  "why" tells us if this was a real syscall.
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index bd755d9..29e2991 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -399,6 +399,9 @@
 	sub	lr, r4, r5			@ mmu has been enabled
 	add	r3, r7, lr
 	ldrd	r4, [r3, #0]			@ get secondary_data.pgdir
+ARM_BE8(eor	r4, r4, r5)			@ Swap r5 and r4 in BE:
+ARM_BE8(eor	r5, r4, r5)			@ it can be done in 3 steps
+ARM_BE8(eor	r4, r4, r5)			@ without using a temp reg.
 	ldr	r8, [r3, #8]			@ get secondary_data.swapper_pg_dir
 	badr	lr, __enable_mmu		@ return address
 	mov	r13, r12			@ __secondary_switched address
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 357f57e..54272e0 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -818,12 +818,13 @@
 			if (arch_find_n_match_cpu_physical_id(dn, cpu, NULL))
 				break;
 
-		of_node_put(dn);
 		if (cpu >= nr_cpu_ids) {
 			pr_warn("Failed to find logical CPU for %s\n",
 				dn->name);
+			of_node_put(dn);
 			break;
 		}
+		of_node_put(dn);
 
 		irqs[i] = cpu;
 		cpumask_set_cpu(cpu, &pmu->supported_cpus);
diff --git a/arch/arm/kernel/reboot.c b/arch/arm/kernel/reboot.c
index 1a4d232..3826935 100644
--- a/arch/arm/kernel/reboot.c
+++ b/arch/arm/kernel/reboot.c
@@ -50,7 +50,7 @@
 	flush_cache_all();
 
 	/* Switch to the identity mapping. */
-	phys_reset = (phys_reset_t)(unsigned long)virt_to_phys(cpu_reset);
+	phys_reset = (phys_reset_t)(unsigned long)virt_to_idmap(cpu_reset);
 	phys_reset((unsigned long)addr);
 
 	/* Should never get here. */
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 90dfbed..3d6b782 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -578,7 +578,7 @@
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
 	if ((unsigned)ipinr < NR_IPI) {
-		trace_ipi_entry(ipi_types[ipinr]);
+		trace_ipi_entry_rcuidle(ipi_types[ipinr]);
 		__inc_irq_stat(cpu, ipi_irqs[ipinr]);
 	}
 
@@ -637,7 +637,7 @@
 	}
 
 	if ((unsigned)ipinr < NR_IPI)
-		trace_ipi_exit(ipi_types[ipinr]);
+		trace_ipi_exit_rcuidle(ipi_types[ipinr]);
 	set_irq_regs(old_regs);
 }
 
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index efe17dd..54a5aea 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -296,7 +296,6 @@
  */
 void update_vsyscall(struct timekeeper *tk)
 {
-	struct timespec xtime_coarse;
 	struct timespec64 *wtm = &tk->wall_to_monotonic;
 
 	if (!cntvct_ok) {
@@ -308,10 +307,10 @@
 
 	vdso_write_begin(vdso_data);
 
-	xtime_coarse = __current_kernel_time();
 	vdso_data->tk_is_cntvct			= tk_is_cntvct(tk);
-	vdso_data->xtime_coarse_sec		= xtime_coarse.tv_sec;
-	vdso_data->xtime_coarse_nsec		= xtime_coarse.tv_nsec;
+	vdso_data->xtime_coarse_sec		= tk->xtime_sec;
+	vdso_data->xtime_coarse_nsec		= (u32)(tk->tkr_mono.xtime_nsec >>
+							tk->tkr_mono.shift);
 	vdso_data->wtm_clock_sec		= wtm->tv_sec;
 	vdso_data->wtm_clock_nsec		= wtm->tv_nsec;
 
diff --git a/arch/arm/lib/memcpy.S b/arch/arm/lib/memcpy.S
index 7797e81..64111bd 100644
--- a/arch/arm/lib/memcpy.S
+++ b/arch/arm/lib/memcpy.S
@@ -61,8 +61,10 @@
 
 /* Prototype: void *memcpy(void *dest, const void *src, size_t n); */
 
+ENTRY(mmiocpy)
 ENTRY(memcpy)
 
 #include "copy_template.S"
 
 ENDPROC(memcpy)
+ENDPROC(mmiocpy)
diff --git a/arch/arm/lib/memset.S b/arch/arm/lib/memset.S
index a4ee97b..3c65e3b 100644
--- a/arch/arm/lib/memset.S
+++ b/arch/arm/lib/memset.S
@@ -16,6 +16,7 @@
 	.text
 	.align	5
 
+ENTRY(mmioset)
 ENTRY(memset)
 UNWIND( .fnstart         )
 	ands	r3, r0, #3		@ 1 unaligned?
@@ -133,3 +134,4 @@
 	b	1b
 UNWIND( .fnend   )
 ENDPROC(memset)
+ENDPROC(mmioset)
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index 3e58d71..4b39af2 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -96,7 +96,7 @@
 	}
 
 	/* the mmap semaphore is taken only if not in an atomic context */
-	atomic = in_atomic();
+	atomic = faulthandler_disabled();
 
 	if (!atomic)
 		down_read(&current->mm->mmap_sem);
diff --git a/arch/arm/mach-davinci/devices-da8xx.c b/arch/arm/mach-davinci/devices-da8xx.c
index ddfdd82..29e08aa 100644
--- a/arch/arm/mach-davinci/devices-da8xx.c
+++ b/arch/arm/mach-davinci/devices-da8xx.c
@@ -1010,11 +1010,13 @@
 		.version	= SPI_VERSION_2,
 		.intr_line	= 1,
 		.dma_event_q	= EVENTQ_0,
+		.prescaler_limit = 2,
 	},
 	[1] = {
 		.version	= SPI_VERSION_2,
 		.intr_line	= 1,
 		.dma_event_q	= EVENTQ_0,
+		.prescaler_limit = 2,
 	},
 };
 
diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c
index 9cbeda7..567dc56 100644
--- a/arch/arm/mach-davinci/dm355.c
+++ b/arch/arm/mach-davinci/dm355.c
@@ -411,6 +411,7 @@
 	.num_chipselect = 2,
 	.cshold_bug	= true,
 	.dma_event_q	= EVENTQ_1,
+	.prescaler_limit = 1,
 };
 static struct platform_device dm355_spi0_device = {
 	.name = "spi_davinci",
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index e3a3c54..6a890a8 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -646,6 +646,7 @@
 	.version 	= SPI_VERSION_1,
 	.num_chipselect = 2,
 	.dma_event_q	= EVENTQ_3,
+	.prescaler_limit = 1,
 };
 
 static struct resource dm365_spi0_resources[] = {
diff --git a/arch/arm/mach-exynos/pm_domains.c b/arch/arm/mach-exynos/pm_domains.c
index 6001f1c..4a87e86 100644
--- a/arch/arm/mach-exynos/pm_domains.c
+++ b/arch/arm/mach-exynos/pm_domains.c
@@ -146,9 +146,8 @@
 		pd->base = of_iomap(np, 0);
 		if (!pd->base) {
 			pr_warn("%s: failed to map memory\n", __func__);
-			kfree(pd->pd.name);
+			kfree_const(pd->pd.name);
 			kfree(pd);
-			of_node_put(np);
 			continue;
 		}
 
diff --git a/arch/arm/mach-imx/gpc.c b/arch/arm/mach-imx/gpc.c
index 80bad29..8c4467f 100644
--- a/arch/arm/mach-imx/gpc.c
+++ b/arch/arm/mach-imx/gpc.c
@@ -291,8 +291,6 @@
 	}
 }
 
-#ifdef CONFIG_PM_GENERIC_DOMAINS
-
 static void _imx6q_pm_pu_power_off(struct generic_pm_domain *genpd)
 {
 	int iso, iso2sw;
@@ -399,7 +397,6 @@
 static int imx_gpc_genpd_init(struct device *dev, struct regulator *pu_reg)
 {
 	struct clk *clk;
-	bool is_off;
 	int i;
 
 	imx6q_pu_domain.reg = pu_reg;
@@ -416,18 +413,13 @@
 	}
 	imx6q_pu_domain.num_clks = i;
 
-	is_off = IS_ENABLED(CONFIG_PM);
-	if (is_off) {
-		_imx6q_pm_pu_power_off(&imx6q_pu_domain.base);
-	} else {
-		/*
-		 * Enable power if compiled without CONFIG_PM in case the
-		 * bootloader disabled it.
-		 */
-		imx6q_pm_pu_power_on(&imx6q_pu_domain.base);
-	}
+	/* Enable power always in case bootloader disabled it. */
+	imx6q_pm_pu_power_on(&imx6q_pu_domain.base);
 
-	pm_genpd_init(&imx6q_pu_domain.base, NULL, is_off);
+	if (!IS_ENABLED(CONFIG_PM_GENERIC_DOMAINS))
+		return 0;
+
+	pm_genpd_init(&imx6q_pu_domain.base, NULL, false);
 	return of_genpd_add_provider_onecell(dev->of_node,
 					     &imx_gpc_onecell_data);
 
@@ -437,13 +429,6 @@
 	return -EINVAL;
 }
 
-#else
-static inline int imx_gpc_genpd_init(struct device *dev, struct regulator *reg)
-{
-	return 0;
-}
-#endif /* CONFIG_PM_GENERIC_DOMAINS */
-
 static int imx_gpc_probe(struct platform_device *pdev)
 {
 	struct regulator *pu_reg;
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index ecc04ff..4a023e8 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -60,6 +60,7 @@
 	select ARM_GIC
 	select MACH_OMAP_GENERIC
 	select MIGHT_HAVE_CACHE_L2X0
+	select HAVE_ARM_SCU
 
 config SOC_DRA7XX
 	bool "TI DRA7XX"
diff --git a/arch/arm/mach-omap2/dma.c b/arch/arm/mach-omap2/dma.c
index e1a56d8..1ed4be1 100644
--- a/arch/arm/mach-omap2/dma.c
+++ b/arch/arm/mach-omap2/dma.c
@@ -117,7 +117,6 @@
 	u8 revision = dma_read(REVISION, 0) & 0xff;
 	printk(KERN_INFO "OMAP DMA hardware revision %d.%d\n",
 				revision >> 4, revision & 0xf);
-	return;
 }
 
 static unsigned configure_dma_errata(void)
diff --git a/arch/arm/mach-omap2/omap-wakeupgen.c b/arch/arm/mach-omap2/omap-wakeupgen.c
index 8e52621..e1d2e99 100644
--- a/arch/arm/mach-omap2/omap-wakeupgen.c
+++ b/arch/arm/mach-omap2/omap-wakeupgen.c
@@ -392,6 +392,7 @@
 	.irq_mask		= wakeupgen_mask,
 	.irq_unmask		= wakeupgen_unmask,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_set_type		= irq_chip_set_type_parent,
 	.flags			= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND,
 #ifdef CONFIG_SMP
 	.irq_set_affinity	= irq_chip_set_affinity_parent,
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index d78c12e..486cc4d 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2373,6 +2373,9 @@
  * registers.  This address is needed early so the OCP registers that
  * are part of the device's address space can be ioremapped properly.
  *
+ * If SYSC access is not needed, the registers will not be remapped
+ * and non-availability of MPU access is not treated as an error.
+ *
  * Returns 0 on success, -EINVAL if an invalid hwmod is passed, and
  * -ENXIO on absent or invalid register target address space.
  */
@@ -2387,6 +2390,11 @@
 
 	_save_mpu_port_index(oh);
 
+	/* if we don't need sysc access we don't need to ioremap */
+	if (!oh->class->sysc)
+		return 0;
+
+	/* we can't continue without MPU PORT if we need sysc access */
 	if (oh->_int_flags & _HWMOD_NO_MPU_PORT)
 		return -ENXIO;
 
@@ -2396,8 +2404,10 @@
 			 oh->name);
 
 		/* Extract the IO space from device tree blob */
-		if (!np)
+		if (!np) {
+			pr_err("omap_hwmod: %s: no dt node\n", oh->name);
 			return -ENXIO;
+		}
 
 		va_start = of_iomap(np, index + oh->mpu_rt_idx);
 	} else {
@@ -2456,13 +2466,11 @@
 				oh->name, np->name);
 	}
 
-	if (oh->class->sysc) {
-		r = _init_mpu_rt_base(oh, NULL, index, np);
-		if (r < 0) {
-			WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n",
-			     oh->name);
-			return 0;
-		}
+	r = _init_mpu_rt_base(oh, NULL, index, np);
+	if (r < 0) {
+		WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n",
+		     oh->name);
+		return 0;
 	}
 
 	r = _init_clocks(oh, NULL);
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 2606c66..562247b 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -827,8 +827,7 @@
 	.syss_offs	= 0x0014,
 	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_SIDLEMODE |
 			   SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
-	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
-			   SIDLE_SMART_WKUP),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
 	.sysc_fields	= &omap_hwmod_sysc_type1,
 };
 
@@ -844,7 +843,7 @@
 	.class		= &dra7xx_gpmc_hwmod_class,
 	.clkdm_name	= "l3main1_clkdm",
 	/* Skip reset for CONFIG_OMAP_GPMC_DEBUG for bootloader timings */
-	.flags		= HWMOD_SWSUP_SIDLE | DEBUG_OMAP_GPMC_HWMOD_FLAGS,
+	.flags		= DEBUG_OMAP_GPMC_HWMOD_FLAGS,
 	.main_clk	= "l3_iclk_div",
 	.prcm = {
 		.omap4 = {
diff --git a/arch/arm/mach-prima2/Kconfig b/arch/arm/mach-prima2/Kconfig
index e03d8b5..9ab8932 100644
--- a/arch/arm/mach-prima2/Kconfig
+++ b/arch/arm/mach-prima2/Kconfig
@@ -4,6 +4,7 @@
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_IRQ_CHIP
 	select NO_IOPORT_MAP
+	select REGMAP
 	select PINCTRL
 	select PINCTRL_SIRF
 	help
diff --git a/arch/arm/mach-prima2/rtciobrg.c b/arch/arm/mach-prima2/rtciobrg.c
index 8f66d8f..d4852d2 100644
--- a/arch/arm/mach-prima2/rtciobrg.c
+++ b/arch/arm/mach-prima2/rtciobrg.c
@@ -1,5 +1,5 @@
 /*
- * RTC I/O Bridge interfaces for CSR SiRFprimaII
+ * RTC I/O Bridge interfaces for CSR SiRFprimaII/atlas7
  * ARM access the registers of SYSRTC, GPSRTC and PWRC through this module
  *
  * Copyright (c) 2011 Cambridge Silicon Radio Limited, a CSR plc group company.
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/io.h>
+#include <linux/regmap.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
@@ -66,6 +67,7 @@
 {
 	unsigned long flags, val;
 
+	/* TODO: add hwspinlock to sync with M3 */
 	spin_lock_irqsave(&rtciobrg_lock, flags);
 
 	val = __sirfsoc_rtc_iobrg_readl(addr);
@@ -90,6 +92,7 @@
 {
 	unsigned long flags;
 
+	 /* TODO: add hwspinlock to sync with M3 */
 	spin_lock_irqsave(&rtciobrg_lock, flags);
 
 	sirfsoc_rtc_iobrg_pre_writel(val, addr);
@@ -102,6 +105,45 @@
 }
 EXPORT_SYMBOL_GPL(sirfsoc_rtc_iobrg_writel);
 
+
+static int regmap_iobg_regwrite(void *context, unsigned int reg,
+				   unsigned int val)
+{
+	sirfsoc_rtc_iobrg_writel(val, reg);
+	return 0;
+}
+
+static int regmap_iobg_regread(void *context, unsigned int reg,
+				  unsigned int *val)
+{
+	*val = (u32)sirfsoc_rtc_iobrg_readl(reg);
+	return 0;
+}
+
+static struct regmap_bus regmap_iobg = {
+	.reg_write = regmap_iobg_regwrite,
+	.reg_read = regmap_iobg_regread,
+};
+
+/**
+ * devm_regmap_init_iobg(): Initialise managed register map
+ *
+ * @iobg: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap.  The regmap will be automatically freed by the
+ * device management code.
+ */
+struct regmap *devm_regmap_init_iobg(struct device *dev,
+				    const struct regmap_config *config)
+{
+	const struct regmap_bus *bus = &regmap_iobg;
+
+	return devm_regmap_init(dev, bus, dev, config);
+}
+EXPORT_SYMBOL_GPL(devm_regmap_init_iobg);
+
 static const struct of_device_id rtciobrg_ids[] = {
 	{ .compatible = "sirf,prima2-rtciobg" },
 	{}
@@ -132,7 +174,7 @@
 }
 postcore_initcall(sirfsoc_rtciobrg_init);
 
-MODULE_AUTHOR("Zhiwu Song <zhiwu.song@csr.com>, "
-		"Barry Song <baohua.song@csr.com>");
+MODULE_AUTHOR("Zhiwu Song <zhiwu.song@csr.com>");
+MODULE_AUTHOR("Barry Song <baohua.song@csr.com>");
 MODULE_DESCRIPTION("CSR SiRFprimaII rtc io bridge");
 MODULE_LICENSE("GPL v2");
diff --git a/arch/arm/mach-pxa/capc7117.c b/arch/arm/mach-pxa/capc7117.c
index c092730..bf366b3 100644
--- a/arch/arm/mach-pxa/capc7117.c
+++ b/arch/arm/mach-pxa/capc7117.c
@@ -24,6 +24,7 @@
 #include <linux/ata_platform.h>
 #include <linux/serial_8250.h>
 #include <linux/gpio.h>
+#include <linux/regulator/machine.h>
 
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
@@ -144,6 +145,8 @@
 
 	capc7117_uarts_init();
 	capc7117_ide_init();
+
+	regulator_has_full_constraints();
 }
 
 MACHINE_START(CAPC7117,
diff --git a/arch/arm/mach-pxa/cm-x2xx.c b/arch/arm/mach-pxa/cm-x2xx.c
index bb99f59..a17a91e 100644
--- a/arch/arm/mach-pxa/cm-x2xx.c
+++ b/arch/arm/mach-pxa/cm-x2xx.c
@@ -13,6 +13,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/irq.h>
 #include <linux/gpio.h>
+#include <linux/regulator/machine.h>
 
 #include <linux/dm9000.h>
 #include <linux/leds.h>
@@ -466,6 +467,8 @@
 	cmx2xx_init_ac97();
 	cmx2xx_init_touchscreen();
 	cmx2xx_init_leds();
+
+	regulator_has_full_constraints();
 }
 
 static void __init cmx2xx_init_irq(void)
diff --git a/arch/arm/mach-pxa/cm-x300.c b/arch/arm/mach-pxa/cm-x300.c
index 4d3588d..5851f4c 100644
--- a/arch/arm/mach-pxa/cm-x300.c
+++ b/arch/arm/mach-pxa/cm-x300.c
@@ -835,6 +835,8 @@
 	cm_x300_init_ac97();
 	cm_x300_init_wi2wi();
 	cm_x300_init_bl();
+
+	regulator_has_full_constraints();
 }
 
 static void __init cm_x300_fixup(struct tag *tags, char **cmdline)
diff --git a/arch/arm/mach-pxa/colibri-pxa270.c b/arch/arm/mach-pxa/colibri-pxa270.c
index 5f9d930..3503826 100644
--- a/arch/arm/mach-pxa/colibri-pxa270.c
+++ b/arch/arm/mach-pxa/colibri-pxa270.c
@@ -18,6 +18,7 @@
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
 #include <linux/platform_device.h>
+#include <linux/regulator/machine.h>
 #include <linux/ucb1400.h>
 
 #include <asm/mach/arch.h>
@@ -294,6 +295,8 @@
 		printk(KERN_ERR "Illegal colibri_pxa270_baseboard type %d\n",
 				colibri_pxa270_baseboard);
 	}
+
+	regulator_has_full_constraints();
 }
 
 /* The "Income s.r.o. SH-Dmaster PXA270 SBC" board can be booted either
diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c
index 51531ec..9d7072b 100644
--- a/arch/arm/mach-pxa/em-x270.c
+++ b/arch/arm/mach-pxa/em-x270.c
@@ -1306,6 +1306,8 @@
 	em_x270_init_i2c();
 	em_x270_init_camera();
 	em_x270_userspace_consumers_init();
+
+	regulator_has_full_constraints();
 }
 
 MACHINE_START(EM_X270, "Compulab EM-X270")
diff --git a/arch/arm/mach-pxa/icontrol.c b/arch/arm/mach-pxa/icontrol.c
index c98511c..9b0eb02 100644
--- a/arch/arm/mach-pxa/icontrol.c
+++ b/arch/arm/mach-pxa/icontrol.c
@@ -26,6 +26,7 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/pxa2xx_spi.h>
 #include <linux/can/platform/mcp251x.h>
+#include <linux/regulator/machine.h>
 
 #include "generic.h"
 
@@ -185,6 +186,8 @@
 	mxm_8x10_mmc_init();
 
 	icontrol_can_init();
+
+	regulator_has_full_constraints();
 }
 
 MACHINE_START(ICONTROL, "iControl/SafeTcam boards using Embedian MXM-8x10 CoM")
diff --git a/arch/arm/mach-pxa/trizeps4.c b/arch/arm/mach-pxa/trizeps4.c
index 872dcb2..066e3a2 100644
--- a/arch/arm/mach-pxa/trizeps4.c
+++ b/arch/arm/mach-pxa/trizeps4.c
@@ -26,6 +26,7 @@
 #include <linux/dm9000.h>
 #include <linux/mtd/physmap.h>
 #include <linux/mtd/partitions.h>
+#include <linux/regulator/machine.h>
 #include <linux/i2c/pxa-i2c.h>
 
 #include <asm/types.h>
@@ -534,6 +535,8 @@
 
 	BCR_writew(trizeps_conxs_bcr);
 	board_backlight_power(1);
+
+	regulator_has_full_constraints();
 }
 
 static void __init trizeps4_map_io(void)
diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c
index aa89488..54122a9 100644
--- a/arch/arm/mach-pxa/vpac270.c
+++ b/arch/arm/mach-pxa/vpac270.c
@@ -24,6 +24,7 @@
 #include <linux/dm9000.h>
 #include <linux/ucb1400.h>
 #include <linux/ata_platform.h>
+#include <linux/regulator/machine.h>
 #include <linux/regulator/max1586.h>
 #include <linux/i2c/pxa-i2c.h>
 
@@ -711,6 +712,8 @@
 	vpac270_ts_init();
 	vpac270_rtc_init();
 	vpac270_ide_init();
+
+	regulator_has_full_constraints();
 }
 
 MACHINE_START(VPAC270, "Voipac PXA270")
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index ac2ae5c..6158566f 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -868,6 +868,8 @@
 	i2c_register_board_info(0, ARRAY_AND_SIZE(zeus_i2c_devices));
 	pxa2xx_set_spi_info(3, &pxa2xx_spi_ssp3_master_info);
 	spi_register_board_info(zeus_spi_board_info, ARRAY_SIZE(zeus_spi_board_info));
+
+	regulator_has_full_constraints();
 }
 
 static struct map_desc zeus_io_desc[] __initdata = {
diff --git a/arch/arm/mach-spear/generic.h b/arch/arm/mach-spear/generic.h
index a99d90a..0664091 100644
--- a/arch/arm/mach-spear/generic.h
+++ b/arch/arm/mach-spear/generic.h
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2009-2012 ST Microelectronics
  * Rajeev Kumar <rajeev-dlh.kumar@st.com>
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/include/mach/irqs.h b/arch/arm/mach-spear/include/mach/irqs.h
index 92da0a8..7058720 100644
--- a/arch/arm/mach-spear/include/mach/irqs.h
+++ b/arch/arm/mach-spear/include/mach/irqs.h
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2009-2012 ST Microelectronics
  * Rajeev Kumar <rajeev-dlh.kumar@st.com>
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/include/mach/misc_regs.h b/arch/arm/mach-spear/include/mach/misc_regs.h
index 935639c..cfaf7c6 100644
--- a/arch/arm/mach-spear/include/mach/misc_regs.h
+++ b/arch/arm/mach-spear/include/mach/misc_regs.h
@@ -4,7 +4,7 @@
  * Miscellaneous registers definitions for SPEAr3xx machine family
  *
  * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/include/mach/spear.h b/arch/arm/mach-spear/include/mach/spear.h
index f2d6a01..5ed841c 100644
--- a/arch/arm/mach-spear/include/mach/spear.h
+++ b/arch/arm/mach-spear/include/mach/spear.h
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2009,2012 ST Microelectronics
  * Rajeev Kumar<rajeev-dlh.kumar@st.com>
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/include/mach/uncompress.h b/arch/arm/mach-spear/include/mach/uncompress.h
index 51b2dc9..8439b9c 100644
--- a/arch/arm/mach-spear/include/mach/uncompress.h
+++ b/arch/arm/mach-spear/include/mach/uncompress.h
@@ -4,7 +4,7 @@
  * Serial port stubs for kernel decompress status messages
  *
  * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/pl080.c b/arch/arm/mach-spear/pl080.c
index cfa1199..b4529f3 100644
--- a/arch/arm/mach-spear/pl080.c
+++ b/arch/arm/mach-spear/pl080.c
@@ -4,7 +4,7 @@
  * DMAC pl080 definitions for SPEAr platform
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/pl080.h b/arch/arm/mach-spear/pl080.h
index eb6590d..608dec6 100644
--- a/arch/arm/mach-spear/pl080.h
+++ b/arch/arm/mach-spear/pl080.h
@@ -4,7 +4,7 @@
  * DMAC pl080 definitions for SPEAr platform
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/restart.c b/arch/arm/mach-spear/restart.c
index ce5e098..b434215 100644
--- a/arch/arm/mach-spear/restart.c
+++ b/arch/arm/mach-spear/restart.c
@@ -4,7 +4,7 @@
  * SPEAr platform specific restart functions
  *
  * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/spear1310.c b/arch/arm/mach-spear/spear1310.c
index d9ce4d8..cd5d375 100644
--- a/arch/arm/mach-spear/spear1310.c
+++ b/arch/arm/mach-spear/spear1310.c
@@ -4,7 +4,7 @@
  * SPEAr1310 machine source file
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/spear1340.c b/arch/arm/mach-spear/spear1340.c
index 3f3c0f1..94594d5 100644
--- a/arch/arm/mach-spear/spear1340.c
+++ b/arch/arm/mach-spear/spear1340.c
@@ -4,7 +4,7 @@
  * SPEAr1340 machine source file
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/spear13xx.c b/arch/arm/mach-spear/spear13xx.c
index 2e463a9..b7afce6 100644
--- a/arch/arm/mach-spear/spear13xx.c
+++ b/arch/arm/mach-spear/spear13xx.c
@@ -4,7 +4,7 @@
  * SPEAr13XX machines common source file
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/spear300.c b/arch/arm/mach-spear/spear300.c
index b52e48f..5b32edd 100644
--- a/arch/arm/mach-spear/spear300.c
+++ b/arch/arm/mach-spear/spear300.c
@@ -4,7 +4,7 @@
  * SPEAr300 machine source file
  *
  * Copyright (C) 2009-2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/spear310.c b/arch/arm/mach-spear/spear310.c
index ed2029d..86a44ac 100644
--- a/arch/arm/mach-spear/spear310.c
+++ b/arch/arm/mach-spear/spear310.c
@@ -4,7 +4,7 @@
  * SPEAr310 machine source file
  *
  * Copyright (C) 2009-2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/spear320.c b/arch/arm/mach-spear/spear320.c
index bf634b3..d45d751 100644
--- a/arch/arm/mach-spear/spear320.c
+++ b/arch/arm/mach-spear/spear320.c
@@ -4,7 +4,7 @@
  * SPEAr320 machine source file
  *
  * Copyright (C) 2009-2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-spear/spear3xx.c b/arch/arm/mach-spear/spear3xx.c
index bf3b1fd..23394ac 100644
--- a/arch/arm/mach-spear/spear3xx.c
+++ b/arch/arm/mach-spear/spear3xx.c
@@ -4,7 +4,7 @@
  * SPEAr3XX machines common source file
  *
  * Copyright (C) 2009-2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/arch/arm/mach-sunxi/Kconfig b/arch/arm/mach-sunxi/Kconfig
index 81502b9..4efe2d4 100644
--- a/arch/arm/mach-sunxi/Kconfig
+++ b/arch/arm/mach-sunxi/Kconfig
@@ -35,7 +35,7 @@
 	select SUN5I_HSTIMER
 
 config MACH_SUN8I
-	bool "Allwinner A23 (sun8i) SoCs support"
+	bool "Allwinner sun8i Family SoCs support"
 	default ARCH_SUNXI
 	select ARM_GIC
 	select MFD_SUN6I_PRCM
diff --git a/arch/arm/mach-sunxi/sunxi.c b/arch/arm/mach-sunxi/sunxi.c
index 1bc811a..65bab28 100644
--- a/arch/arm/mach-sunxi/sunxi.c
+++ b/arch/arm/mach-sunxi/sunxi.c
@@ -67,10 +67,13 @@
 
 static const char * const sun8i_board_dt_compat[] = {
 	"allwinner,sun8i-a23",
+	"allwinner,sun8i-a33",
+	"allwinner,sun8i-h3",
 	NULL,
 };
 
-DT_MACHINE_START(SUN8I_DT, "Allwinner sun8i (A23) Family")
+DT_MACHINE_START(SUN8I_DT, "Allwinner sun8i Family")
+	.init_time	= sun6i_timer_init,
 	.dt_compat	= sun8i_board_dt_compat,
 	.init_late	= sunxi_dt_cpufreq_init,
 MACHINE_END
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 1ced8a0..cba12f3 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1971,7 +1971,7 @@
 {
 	int next_bitmap;
 
-	if (mapping->nr_bitmaps > mapping->extensions)
+	if (mapping->nr_bitmaps >= mapping->extensions)
 		return -EINVAL;
 
 	next_bitmap = mapping->nr_bitmaps;
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index d1e5ad7..0c81056 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -255,7 +255,7 @@
 }
 #endif
 
-void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
+static void __iomem * __arm_ioremap_pfn_caller(unsigned long pfn,
 	unsigned long offset, size_t size, unsigned int mtype, void *caller)
 {
 	const struct mem_type *type;
@@ -363,7 +363,7 @@
 		  unsigned int mtype)
 {
 	return __arm_ioremap_pfn_caller(pfn, offset, size, mtype,
-			__builtin_return_address(0));
+					__builtin_return_address(0));
 }
 EXPORT_SYMBOL(__arm_ioremap_pfn);
 
@@ -371,13 +371,26 @@
 				      unsigned int, void *) =
 	__arm_ioremap_caller;
 
-void __iomem *
-__arm_ioremap(phys_addr_t phys_addr, size_t size, unsigned int mtype)
+void __iomem *ioremap(resource_size_t res_cookie, size_t size)
 {
-	return arch_ioremap_caller(phys_addr, size, mtype,
-		__builtin_return_address(0));
+	return arch_ioremap_caller(res_cookie, size, MT_DEVICE,
+				   __builtin_return_address(0));
 }
-EXPORT_SYMBOL(__arm_ioremap);
+EXPORT_SYMBOL(ioremap);
+
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size)
+{
+	return arch_ioremap_caller(res_cookie, size, MT_DEVICE_CACHED,
+				   __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_cache);
+
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size)
+{
+	return arch_ioremap_caller(res_cookie, size, MT_DEVICE_WC,
+				   __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wc);
 
 /*
  * Remap an arbitrary physical address space into the kernel virtual
@@ -431,11 +444,11 @@
 
 void (*arch_iounmap)(volatile void __iomem *) = __iounmap;
 
-void __arm_iounmap(volatile void __iomem *io_addr)
+void iounmap(volatile void __iomem *cookie)
 {
-	arch_iounmap(io_addr);
+	arch_iounmap(cookie);
 }
-EXPORT_SYMBOL(__arm_iounmap);
+EXPORT_SYMBOL(iounmap);
 
 #ifdef CONFIG_PCI
 static int pci_ioremap_mem_type = MT_DEVICE;
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 6ca7d9a..870838a 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1072,6 +1072,7 @@
 	int highmem = 0;
 	phys_addr_t vmalloc_limit = __pa(vmalloc_min - 1) + 1;
 	struct memblock_region *reg;
+	bool should_use_highmem = false;
 
 	for_each_memblock(memory, reg) {
 		phys_addr_t block_start = reg->base;
@@ -1090,6 +1091,7 @@
 				pr_notice("Ignoring RAM at %pa-%pa (!CONFIG_HIGHMEM)\n",
 					  &block_start, &block_end);
 				memblock_remove(reg->base, reg->size);
+				should_use_highmem = true;
 				continue;
 			}
 
@@ -1100,6 +1102,7 @@
 					  &block_start, &block_end, &vmalloc_limit);
 				memblock_remove(vmalloc_limit, overlap_size);
 				block_end = vmalloc_limit;
+				should_use_highmem = true;
 			}
 		}
 
@@ -1134,6 +1137,9 @@
 		}
 	}
 
+	if (should_use_highmem)
+		pr_notice("Consider using a HIGHMEM enabled kernel.\n");
+
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
 
 	/*
@@ -1494,6 +1500,7 @@
 	build_mem_type_table();
 	prepare_page_table();
 	map_lowmem();
+	memblock_set_current_limit(arm_lowmem_limit);
 	dma_contiguous_remap();
 	devicemaps_init(mdesc);
 	kmap_init();
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index afd7e05..1dd1093 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -351,30 +351,43 @@
 }
 EXPORT_SYMBOL(__arm_ioremap_pfn);
 
-void __iomem *__arm_ioremap_pfn_caller(unsigned long pfn, unsigned long offset,
-			   size_t size, unsigned int mtype, void *caller)
-{
-	return __arm_ioremap_pfn(pfn, offset, size, mtype);
-}
-
-void __iomem *__arm_ioremap(phys_addr_t phys_addr, size_t size,
-			    unsigned int mtype)
-{
-	return (void __iomem *)phys_addr;
-}
-EXPORT_SYMBOL(__arm_ioremap);
-
-void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);
-
 void __iomem *__arm_ioremap_caller(phys_addr_t phys_addr, size_t size,
 				   unsigned int mtype, void *caller)
 {
-	return __arm_ioremap(phys_addr, size, mtype);
+	return (void __iomem *)phys_addr;
 }
 
+void __iomem * (*arch_ioremap_caller)(phys_addr_t, size_t, unsigned int, void *);
+
+void __iomem *ioremap(resource_size_t res_cookie, size_t size)
+{
+	return __arm_ioremap_caller(res_cookie, size, MT_DEVICE,
+				    __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap);
+
+void __iomem *ioremap_cache(resource_size_t res_cookie, size_t size)
+{
+	return __arm_ioremap_caller(res_cookie, size, MT_DEVICE_CACHED,
+				    __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_cache);
+
+void __iomem *ioremap_wc(resource_size_t res_cookie, size_t size)
+{
+	return __arm_ioremap_caller(res_cookie, size, MT_DEVICE_WC,
+				    __builtin_return_address(0));
+}
+EXPORT_SYMBOL(ioremap_wc);
+
+void __iounmap(volatile void __iomem *addr)
+{
+}
+EXPORT_SYMBOL(__iounmap);
+
 void (*arch_iounmap)(volatile void __iomem *);
 
-void __arm_iounmap(volatile void __iomem *addr)
+void iounmap(volatile void __iomem *addr)
 {
 }
-EXPORT_SYMBOL(__arm_iounmap);
+EXPORT_SYMBOL(iounmap);
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 0716bbe..de2b246 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -274,7 +274,10 @@
 __v7_b15mp_setup:
 __v7_ca17mp_setup:
 	mov	r10, #0
-1:
+1:	adr	r12, __v7_setup_stack		@ the local stack
+	stmia	r12, {r0-r5, lr}		@ v7_invalidate_l1 touches r0-r6
+	bl      v7_invalidate_l1
+	ldmia	r12, {r0-r5, lr}
 #ifdef CONFIG_SMP
 	ALT_SMP(mrc	p15, 0, r0, c1, c0, 1)
 	ALT_UP(mov	r0, #(1 << 6))		@ fake it for UP
@@ -283,7 +286,7 @@
 	orreq	r0, r0, r10			@ Enable CPU-specific SMP bits
 	mcreq	p15, 0, r0, c1, c0, 1
 #endif
-	b	__v7_setup
+	b	__v7_setup_cont
 
 /*
  * Errata:
@@ -413,10 +416,11 @@
 
 __v7_setup:
 	adr	r12, __v7_setup_stack		@ the local stack
-	stmia	r12, {r0-r5, r7, r9, r11, lr}
+	stmia	r12, {r0-r5, lr}		@ v7_invalidate_l1 touches r0-r6
 	bl      v7_invalidate_l1
-	ldmia	r12, {r0-r5, r7, r9, r11, lr}
+	ldmia	r12, {r0-r5, lr}
 
+__v7_setup_cont:
 	and	r0, r9, #0xff000000		@ ARM?
 	teq	r0, #0x41000000
 	bne	__errata_finish
@@ -480,7 +484,7 @@
 
 	.align	2
 __v7_setup_stack:
-	.space	4 * 11				@ 11 registers
+	.space	4 * 7				@ 12 registers
 
 	__INITDATA
 
diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 4550d24..c011e22 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -74,32 +74,52 @@
 
 int bpf_jit_enable __read_mostly;
 
-static u64 jit_get_skb_b(struct sk_buff *skb, unsigned offset)
+static inline int call_neg_helper(struct sk_buff *skb, int offset, void *ret,
+		      unsigned int size)
+{
+	void *ptr = bpf_internal_load_pointer_neg_helper(skb, offset, size);
+
+	if (!ptr)
+		return -EFAULT;
+	memcpy(ret, ptr, size);
+	return 0;
+}
+
+static u64 jit_get_skb_b(struct sk_buff *skb, int offset)
 {
 	u8 ret;
 	int err;
 
-	err = skb_copy_bits(skb, offset, &ret, 1);
+	if (offset < 0)
+		err = call_neg_helper(skb, offset, &ret, 1);
+	else
+		err = skb_copy_bits(skb, offset, &ret, 1);
 
 	return (u64)err << 32 | ret;
 }
 
-static u64 jit_get_skb_h(struct sk_buff *skb, unsigned offset)
+static u64 jit_get_skb_h(struct sk_buff *skb, int offset)
 {
 	u16 ret;
 	int err;
 
-	err = skb_copy_bits(skb, offset, &ret, 2);
+	if (offset < 0)
+		err = call_neg_helper(skb, offset, &ret, 2);
+	else
+		err = skb_copy_bits(skb, offset, &ret, 2);
 
 	return (u64)err << 32 | ntohs(ret);
 }
 
-static u64 jit_get_skb_w(struct sk_buff *skb, unsigned offset)
+static u64 jit_get_skb_w(struct sk_buff *skb, int offset)
 {
 	u32 ret;
 	int err;
 
-	err = skb_copy_bits(skb, offset, &ret, 4);
+	if (offset < 0)
+		err = call_neg_helper(skb, offset, &ret, 4);
+	else
+		err = skb_copy_bits(skb, offset, &ret, 4);
 
 	return (u64)err << 32 | ntohl(ret);
 }
@@ -536,9 +556,6 @@
 		case BPF_LD | BPF_B | BPF_ABS:
 			load_order = 0;
 load:
-			/* the interpreter will deal with the negative K */
-			if ((int)k < 0)
-				return -ENOTSUPP;
 			emit_mov_i(r_off, k, ctx);
 load_common:
 			ctx->seen |= SEEN_DATA | SEEN_CALL;
@@ -547,12 +564,24 @@
 				emit(ARM_SUB_I(r_scratch, r_skb_hl,
 					       1 << load_order), ctx);
 				emit(ARM_CMP_R(r_scratch, r_off), ctx);
-				condt = ARM_COND_HS;
+				condt = ARM_COND_GE;
 			} else {
 				emit(ARM_CMP_R(r_skb_hl, r_off), ctx);
 				condt = ARM_COND_HI;
 			}
 
+			/*
+			 * test for negative offset, only if we are
+			 * currently scheduled to take the fast
+			 * path. this will update the flags so that
+			 * the slowpath instruction are ignored if the
+			 * offset is negative.
+			 *
+			 * for loard_order == 0 the HI condition will
+			 * make loads at offset 0 take the slow path too.
+			 */
+			_emit(condt, ARM_CMP_I(r_off, 0), ctx);
+
 			_emit(condt, ARM_ADD_R(r_scratch, r_off, r_skb_data),
 			      ctx);
 
@@ -860,9 +889,11 @@
 			off = offsetof(struct sk_buff, vlan_tci);
 			emit(ARM_LDRH_I(r_A, r_skb, off), ctx);
 			if (code == (BPF_ANC | SKF_AD_VLAN_TAG))
-				OP_IMM3(ARM_AND, r_A, r_A, VLAN_VID_MASK, ctx);
-			else
-				OP_IMM3(ARM_AND, r_A, r_A, VLAN_TAG_PRESENT, ctx);
+				OP_IMM3(ARM_AND, r_A, r_A, ~VLAN_TAG_PRESENT, ctx);
+			else {
+				OP_IMM3(ARM_LSR, r_A, r_A, 12, ctx);
+				OP_IMM3(ARM_AND, r_A, r_A, 0x1, ctx);
+			}
 			break;
 		case BPF_ANC | SKF_AD_QUEUE:
 			ctx->seen |= SEEN_SKB;
diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
index 9d259d9..1160434 100644
--- a/arch/arm/vdso/Makefile
+++ b/arch/arm/vdso/Makefile
@@ -14,7 +14,7 @@
 VDSO_LDFLAGS += -nostdlib -shared
 VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--hash-style=sysv)
 VDSO_LDFLAGS += $(call cc-ldoption, -Wl$(comma)--build-id)
-VDSO_LDFLAGS += $(call cc-option, -fuse-ld=bfd)
+VDSO_LDFLAGS += $(call cc-ldoption, -fuse-ld=bfd)
 
 obj-$(CONFIG_VDSO) += vdso.o
 extra-$(CONFIG_VDSO) += vdso.lds
diff --git a/arch/arm/vdso/vdsomunge.c b/arch/arm/vdso/vdsomunge.c
index 9005b07..aedec81 100644
--- a/arch/arm/vdso/vdsomunge.c
+++ b/arch/arm/vdso/vdsomunge.c
@@ -45,13 +45,11 @@
  * it does.
  */
 
-#define _GNU_SOURCE
-
 #include <byteswap.h>
 #include <elf.h>
 #include <errno.h>
-#include <error.h>
 #include <fcntl.h>
+#include <stdarg.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -82,11 +80,25 @@
 #define EF_ARM_ABI_FLOAT_HARD 0x400
 #endif
 
+static int failed;
+static const char *argv0;
 static const char *outfile;
 
+static void fail(const char *fmt, ...)
+{
+	va_list ap;
+
+	failed = 1;
+	fprintf(stderr, "%s: ", argv0);
+	va_start(ap, fmt);
+	vfprintf(stderr, fmt, ap);
+	va_end(ap);
+	exit(EXIT_FAILURE);
+}
+
 static void cleanup(void)
 {
-	if (error_message_count > 0 && outfile != NULL)
+	if (failed && outfile != NULL)
 		unlink(outfile);
 }
 
@@ -119,68 +131,66 @@
 	int infd;
 
 	atexit(cleanup);
+	argv0 = argv[0];
 
 	if (argc != 3)
-		error(EXIT_FAILURE, 0, "Usage: %s [infile] [outfile]", argv[0]);
+		fail("Usage: %s [infile] [outfile]\n", argv[0]);
 
 	infile = argv[1];
 	outfile = argv[2];
 
 	infd = open(infile, O_RDONLY);
 	if (infd < 0)
-		error(EXIT_FAILURE, errno, "Cannot open %s", infile);
+		fail("Cannot open %s: %s\n", infile, strerror(errno));
 
 	if (fstat(infd, &stat) != 0)
-		error(EXIT_FAILURE, errno, "Failed stat for %s", infile);
+		fail("Failed stat for %s: %s\n", infile, strerror(errno));
 
 	inbuf = mmap(NULL, stat.st_size, PROT_READ, MAP_PRIVATE, infd, 0);
 	if (inbuf == MAP_FAILED)
-		error(EXIT_FAILURE, errno, "Failed to map %s", infile);
+		fail("Failed to map %s: %s\n", infile, strerror(errno));
 
 	close(infd);
 
 	inhdr = inbuf;
 
 	if (memcmp(&inhdr->e_ident, ELFMAG, SELFMAG) != 0)
-		error(EXIT_FAILURE, 0, "Not an ELF file");
+		fail("Not an ELF file\n");
 
 	if (inhdr->e_ident[EI_CLASS] != ELFCLASS32)
-		error(EXIT_FAILURE, 0, "Unsupported ELF class");
+		fail("Unsupported ELF class\n");
 
 	swap = inhdr->e_ident[EI_DATA] != HOST_ORDER;
 
 	if (read_elf_half(inhdr->e_type, swap) != ET_DYN)
-		error(EXIT_FAILURE, 0, "Not a shared object");
+		fail("Not a shared object\n");
 
-	if (read_elf_half(inhdr->e_machine, swap) != EM_ARM) {
-		error(EXIT_FAILURE, 0, "Unsupported architecture %#x",
-		      inhdr->e_machine);
-	}
+	if (read_elf_half(inhdr->e_machine, swap) != EM_ARM)
+		fail("Unsupported architecture %#x\n", inhdr->e_machine);
 
 	e_flags = read_elf_word(inhdr->e_flags, swap);
 
 	if (EF_ARM_EABI_VERSION(e_flags) != EF_ARM_EABI_VER5) {
-		error(EXIT_FAILURE, 0, "Unsupported EABI version %#x",
-		      EF_ARM_EABI_VERSION(e_flags));
+		fail("Unsupported EABI version %#x\n",
+		     EF_ARM_EABI_VERSION(e_flags));
 	}
 
 	if (e_flags & EF_ARM_ABI_FLOAT_HARD)
-		error(EXIT_FAILURE, 0,
-		      "Unexpected hard-float flag set in e_flags");
+		fail("Unexpected hard-float flag set in e_flags\n");
 
 	clear_soft_float = !!(e_flags & EF_ARM_ABI_FLOAT_SOFT);
 
 	outfd = open(outfile, O_RDWR | O_CREAT | O_TRUNC, S_IRUSR | S_IWUSR);
 	if (outfd < 0)
-		error(EXIT_FAILURE, errno, "Cannot open %s", outfile);
+		fail("Cannot open %s: %s\n", outfile, strerror(errno));
 
 	if (ftruncate(outfd, stat.st_size) != 0)
-		error(EXIT_FAILURE, errno, "Cannot truncate %s", outfile);
+		fail("Cannot truncate %s: %s\n", outfile, strerror(errno));
 
 	outbuf = mmap(NULL, stat.st_size, PROT_READ | PROT_WRITE, MAP_SHARED,
 		      outfd, 0);
 	if (outbuf == MAP_FAILED)
-		error(EXIT_FAILURE, errno, "Failed to map %s", outfile);
+		fail("Failed to map %s: %s\n", outfile, strerror(errno));
 
 	close(outfd);
 
@@ -195,7 +205,7 @@
 	}
 
 	if (msync(outbuf, stat.st_size, MS_SYNC) != 0)
-		error(EXIT_FAILURE, errno, "Failed to sync %s", outfile);
+		fail("Failed to sync %s: %s\n", outfile, strerror(errno));
 
 	return EXIT_SUCCESS;
 }
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 0f6edb1..318175f 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -23,9 +23,9 @@
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select COMMON_CLK
-	select EDAC_SUPPORT
 	select CPU_PM if (SUSPEND || CPU_IDLE)
 	select DCACHE_WORD_ACCESS
+	select EDAC_SUPPORT
 	select GENERIC_ALLOCATOR
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
diff --git a/arch/arm64/boot/dts/apm/apm-mustang.dts b/arch/arm64/boot/dts/apm/apm-mustang.dts
index 83578e7..4c55833 100644
--- a/arch/arm64/boot/dts/apm/apm-mustang.dts
+++ b/arch/arm64/boot/dts/apm/apm-mustang.dts
@@ -23,6 +23,16 @@
 		device_type = "memory";
 		reg = < 0x1 0x00000000 0x0 0x80000000 >; /* Updated by bootloader */
 	};
+
+	gpio-keys {
+		compatible = "gpio-keys";
+		button@1 {
+			label = "POWER";
+			linux,code = <116>;
+			linux,input-type = <0x1>;
+			interrupts = <0x0 0x2d 0x1>;
+		};
+	};
 };
 
 &pcie0clk {
diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index 0689c3f..58093ed 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -823,7 +823,7 @@
 			device_type = "dma";
 			reg = <0x0 0x1f270000 0x0 0x10000>,
 			      <0x0 0x1f200000 0x0 0x10000>,
-			      <0x0 0x1b008000 0x0 0x2000>,
+			      <0x0 0x1b000000 0x0 0x400000>,
 			      <0x0 0x1054a000 0x0 0x100>;
 			interrupts = <0x0 0x82 0x4>,
 				     <0x0 0xb8 0x4>,
diff --git a/arch/arm64/boot/dts/arm/Makefile b/arch/arm64/boot/dts/arm/Makefile
index c5c98b9..bb3c072 100644
--- a/arch/arm64/boot/dts/arm/Makefile
+++ b/arch/arm64/boot/dts/arm/Makefile
@@ -1,6 +1,7 @@
 dtb-$(CONFIG_ARCH_VEXPRESS) += foundation-v8.dtb
 dtb-$(CONFIG_ARCH_VEXPRESS) += juno.dtb juno-r1.dtb
 dtb-$(CONFIG_ARCH_VEXPRESS) += rtsm_ve-aemv8a.dtb
+dtb-$(CONFIG_ARCH_VEXPRESS) += vexpress-v2f-1xv7-ca53x2.dtb
 
 always		:= $(dtb-y)
 subdir-y	:= $(dts-dirs)
diff --git a/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts b/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts
new file mode 100644
index 0000000..5b1d018
--- /dev/null
+++ b/arch/arm64/boot/dts/arm/vexpress-v2f-1xv7-ca53x2.dts
@@ -0,0 +1,191 @@
+/*
+ * ARM Ltd. Versatile Express
+ *
+ * LogicTile Express 20MG
+ * V2F-1XV7
+ *
+ * Cortex-A53 (2 cores) Soft Macrocell Model
+ *
+ * HBI-0247C
+ */
+
+/dts-v1/;
+
+#include <dt-bindings/interrupt-controller/arm-gic.h>
+
+/ {
+	model = "V2F-1XV7 Cortex-A53x2 SMM";
+	arm,hbi = <0x247>;
+	arm,vexpress,site = <0xf>;
+	compatible = "arm,vexpress,v2f-1xv7,ca53x2", "arm,vexpress,v2f-1xv7", "arm,vexpress";
+	interrupt-parent = <&gic>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+
+	chosen {
+		stdout-path = "serial0:38400n8";
+	};
+
+	aliases {
+		serial0 = &v2m_serial0;
+		serial1 = &v2m_serial1;
+		serial2 = &v2m_serial2;
+		serial3 = &v2m_serial3;
+		i2c0 = &v2m_i2c_dvi;
+		i2c1 = &v2m_i2c_pcie;
+	};
+
+	cpus {
+		#address-cells = <2>;
+		#size-cells = <0>;
+
+		cpu@0 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0 0>;
+			next-level-cache = <&L2_0>;
+		};
+
+		cpu@1 {
+			device_type = "cpu";
+			compatible = "arm,cortex-a53", "arm,armv8";
+			reg = <0 1>;
+			next-level-cache = <&L2_0>;
+		};
+
+		L2_0: l2-cache0 {
+			compatible = "cache";
+		};
+	};
+
+	memory@80000000 {
+		device_type = "memory";
+		reg = <0 0x80000000 0 0x80000000>; /* 2GB @ 2GB */
+	};
+
+	gic: interrupt-controller@2c001000 {
+		compatible = "arm,gic-400";
+		#interrupt-cells = <3>;
+		#address-cells = <0>;
+		interrupt-controller;
+		reg = <0 0x2c001000 0 0x1000>,
+		      <0 0x2c002000 0 0x2000>,
+		      <0 0x2c004000 0 0x2000>,
+		      <0 0x2c006000 0 0x2000>;
+		interrupts = <GIC_PPI 9 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_HIGH)>;
+	};
+
+	timer {
+		compatible = "arm,armv8-timer";
+		interrupts = <GIC_PPI 13 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 14 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>,
+			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(2) | IRQ_TYPE_LEVEL_LOW)>;
+	};
+
+	pmu {
+		compatible = "arm,armv8-pmuv3";
+		interrupts = <GIC_SPI 68 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 69 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	dcc {
+		compatible = "arm,vexpress,config-bus";
+		arm,vexpress,config-bridge = <&v2m_sysreg>;
+
+		smbclk: osc@4 {
+			/* SMC clock */
+			compatible = "arm,vexpress-osc";
+			arm,vexpress-sysreg,func = <1 4>;
+			freq-range = <40000000 40000000>;
+			#clock-cells = <0>;
+			clock-output-names = "smclk";
+		};
+
+		volt@0 {
+			/* VIO to expansion board above */
+			compatible = "arm,vexpress-volt";
+			arm,vexpress-sysreg,func = <2 0>;
+			regulator-name = "VIO_UP";
+			regulator-min-microvolt = <800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-always-on;
+		};
+
+		volt@1 {
+			/* 12V from power connector J6 */
+			compatible = "arm,vexpress-volt";
+			arm,vexpress-sysreg,func = <2 1>;
+			regulator-name = "12";
+			regulator-always-on;
+		};
+
+		temp@0 {
+			/* FPGA temperature */
+			compatible = "arm,vexpress-temp";
+			arm,vexpress-sysreg,func = <4 0>;
+			label = "FPGA";
+		};
+	};
+
+	smb {
+		compatible = "simple-bus";
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0 0x08000000 0x04000000>,
+			 <1 0 0 0x14000000 0x04000000>,
+			 <2 0 0 0x18000000 0x04000000>,
+			 <3 0 0 0x1c000000 0x04000000>,
+			 <4 0 0 0x0c000000 0x04000000>,
+			 <5 0 0 0x10000000 0x04000000>;
+
+		#interrupt-cells = <1>;
+		interrupt-map-mask = <0 0 63>;
+		interrupt-map = <0 0  0 &gic GIC_SPI  0 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  1 &gic GIC_SPI  1 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  2 &gic GIC_SPI  2 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  3 &gic GIC_SPI  3 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  4 &gic GIC_SPI  4 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  5 &gic GIC_SPI  5 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  6 &gic GIC_SPI  6 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  7 &gic GIC_SPI  7 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  8 &gic GIC_SPI  8 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0  9 &gic GIC_SPI  9 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 10 &gic GIC_SPI 10 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 11 &gic GIC_SPI 11 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 12 &gic GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 13 &gic GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 14 &gic GIC_SPI 14 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 15 &gic GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 16 &gic GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 17 &gic GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 18 &gic GIC_SPI 18 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 19 &gic GIC_SPI 19 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 20 &gic GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 21 &gic GIC_SPI 21 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 22 &gic GIC_SPI 22 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 23 &gic GIC_SPI 23 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 24 &gic GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 25 &gic GIC_SPI 25 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 26 &gic GIC_SPI 26 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 27 &gic GIC_SPI 27 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 28 &gic GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 29 &gic GIC_SPI 29 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 30 &gic GIC_SPI 30 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 31 &gic GIC_SPI 31 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 32 &gic GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 33 &gic GIC_SPI 33 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 34 &gic GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 35 &gic GIC_SPI 35 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 36 &gic GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 37 &gic GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 38 &gic GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 39 &gic GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 40 &gic GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 41 &gic GIC_SPI 41 IRQ_TYPE_LEVEL_HIGH>,
+				<0 0 42 &gic GIC_SPI 42 IRQ_TYPE_LEVEL_HIGH>;
+
+		/include/ "../../../../arm/boot/dts/vexpress-v2m-rs1.dtsi"
+	};
+};
diff --git a/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi b/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
index d8c0bdc..9cb7cf9 100644
--- a/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
+++ b/arch/arm64/boot/dts/cavium/thunder-88xx.dtsi
@@ -376,10 +376,19 @@
 		gic0: interrupt-controller@8010,00000000 {
 			compatible = "arm,gic-v3";
 			#interrupt-cells = <3>;
+			#address-cells = <2>;
+			#size-cells = <2>;
+			ranges;
 			interrupt-controller;
 			reg = <0x8010 0x00000000 0x0 0x010000>, /* GICD */
 			      <0x8010 0x80000000 0x0 0x600000>; /* GICR */
 			interrupts = <1 9 0xf04>;
+
+			its: gic-its@8010,00020000 {
+				compatible = "arm,gic-v3-its";
+				msi-controller;
+				reg = <0x8010 0x20000 0x0 0x200000>;
+			};
 		};
 
 		uaa0: serial@87e0,24000000 {
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index f38c94f..4e17e7e 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -83,6 +83,7 @@
 CONFIG_ATA=y
 CONFIG_SATA_AHCI=y
 CONFIG_SATA_AHCI_PLATFORM=y
+CONFIG_AHCI_CEVA=y
 CONFIG_AHCI_XGENE=y
 CONFIG_PATA_PLATFORM=y
 CONFIG_PATA_OF_PLATFORM=y
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index b112a39..70fd9ff 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -25,6 +25,7 @@
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += msi.h
diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index 39248d3..406485e 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -19,6 +19,14 @@
 #include <asm/psci.h>
 #include <asm/smp_plat.h>
 
+/* Macros for consistency checks of the GICC subtable of MADT */
+#define ACPI_MADT_GICC_LENGTH	\
+	(acpi_gbl_FADT.header.revision < 6 ? 76 : 80)
+
+#define BAD_MADT_GICC_ENTRY(entry, end)						\
+	(!(entry) || (unsigned long)(entry) + sizeof(*(entry)) > (end) ||	\
+	 (entry)->header.length != ACPI_MADT_GICC_LENGTH)
+
 /* Basic configuration for ACPI */
 #ifdef	CONFIG_ACPI
 /* ACPI table mapping after acpi_gbl_permanent_mmap is set */
diff --git a/arch/arm64/include/asm/mm-arch-hooks.h b/arch/arm64/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 562b655..0000000
--- a/arch/arm64/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_ARM64_MM_ARCH_HOOKS_H
-#define _ASM_ARM64_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_ARM64_MM_ARCH_HOOKS_H */
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 9d4aa18..e8ca6ea 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -122,12 +122,12 @@
 
 	/* Show what we know for posterity */
 	c16 = early_memremap(efi_to_phys(efi.systab->fw_vendor),
-			     sizeof(vendor));
+			     sizeof(vendor) * sizeof(efi_char16_t));
 	if (c16) {
 		for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i)
 			vendor[i] = c16[i];
 		vendor[i] = '\0';
-		early_memunmap(c16, sizeof(vendor));
+		early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t));
 	}
 
 	pr_info("EFI v%u.%.02u by %s\n",
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index a7691a3..e163518 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -352,8 +352,8 @@
 	// TODO: add support for undefined instructions in kernel mode
 	enable_dbg
 	mov	x0, sp
+	mov	x2, x1
 	mov	x1, #BAD_SYNC
-	mrs	x2, esr_el1
 	b	bad_mode
 ENDPROC(el1_sync)
 
@@ -553,7 +553,7 @@
 	ct_user_exit
 	mov	x0, sp
 	mov	x1, #BAD_SYNC
-	mrs	x2, esr_el1
+	mov	x2, x25
 	bl	bad_mode
 	b	ret_to_user
 ENDPROC(el0_sync)
@@ -585,7 +585,8 @@
  *
  */
 ENTRY(cpu_switch_to)
-	add	x8, x0, #THREAD_CPU_CONTEXT
+	mov	x10, #THREAD_CPU_CONTEXT
+	add	x8, x0, x10
 	mov	x9, sp
 	stp	x19, x20, [x8], #16		// store callee-saved registers
 	stp	x21, x22, [x8], #16
@@ -594,7 +595,7 @@
 	stp	x27, x28, [x8], #16
 	stp	x29, x9, [x8], #16
 	str	lr, [x8]
-	add	x8, x1, #THREAD_CPU_CONTEXT
+	add	x8, x1, x10
 	ldp	x19, x20, [x8], #16		// restore callee-saved registers
 	ldp	x21, x22, [x8], #16
 	ldp	x23, x24, [x8], #16
diff --git a/arch/arm64/kernel/entry32.S b/arch/arm64/kernel/entry32.S
index bd9bfaa..f332d5d 100644
--- a/arch/arm64/kernel/entry32.S
+++ b/arch/arm64/kernel/entry32.S
@@ -32,13 +32,11 @@
 
 ENTRY(compat_sys_sigreturn_wrapper)
 	mov	x0, sp
-	mov	x27, #0		// prevent syscall restart handling (why)
 	b	compat_sys_sigreturn
 ENDPROC(compat_sys_sigreturn_wrapper)
 
 ENTRY(compat_sys_rt_sigreturn_wrapper)
 	mov	x0, sp
-	mov	x27, #0		// prevent syscall restart handling (why)
 	b	compat_sys_rt_sigreturn
 ENDPROC(compat_sys_rt_sigreturn_wrapper)
 
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 240b75c..463fa2e 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -61,7 +61,7 @@
 static bool migrate_one_irq(struct irq_desc *desc)
 {
 	struct irq_data *d = irq_desc_get_irq_data(desc);
-	const struct cpumask *affinity = d->affinity;
+	const struct cpumask *affinity = irq_data_get_affinity_mask(d);
 	struct irq_chip *c;
 	bool ret = false;
 
@@ -81,7 +81,7 @@
 	if (!c->irq_set_affinity)
 		pr_debug("IRQ%u: unable to set affinity\n", d->irq);
 	else if (c->irq_set_affinity(d, affinity, false) == IRQ_SET_MASK_OK && ret)
-		cpumask_copy(d->affinity, affinity);
+		cpumask_copy(irq_data_get_affinity_mask(d), affinity);
 
 	return ret;
 }
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 1670f15..948f0ad 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -168,7 +168,8 @@
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitely for the right codes here.
 		 */
-		if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
+		if (from->si_signo == SIGBUS &&
+		    (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO))
 			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
 #endif
 		break;
@@ -201,8 +202,6 @@
 
 int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, __ARCH_SI_PREAMBLE_SIZE) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE))
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 695801a..50fb469 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -438,7 +438,7 @@
 	struct acpi_madt_generic_interrupt *processor;
 
 	processor = (struct acpi_madt_generic_interrupt *)header;
-	if (BAD_MADT_ENTRY(processor, end))
+	if (BAD_MADT_GICC_ENTRY(processor, end))
 		return -EINVAL;
 
 	acpi_table_print_madt_entry(header);
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index ec37ab3..97bc68f 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -199,16 +199,15 @@
  */
 void update_vsyscall(struct timekeeper *tk)
 {
-	struct timespec xtime_coarse;
 	u32 use_syscall = strcmp(tk->tkr_mono.clock->name, "arch_sys_counter");
 
 	++vdso_data->tb_seq_count;
 	smp_wmb();
 
-	xtime_coarse = __current_kernel_time();
 	vdso_data->use_syscall			= use_syscall;
-	vdso_data->xtime_coarse_sec		= xtime_coarse.tv_sec;
-	vdso_data->xtime_coarse_nsec		= xtime_coarse.tv_nsec;
+	vdso_data->xtime_coarse_sec		= tk->xtime_sec;
+	vdso_data->xtime_coarse_nsec		= tk->tkr_mono.xtime_nsec >>
+							tk->tkr_mono.shift;
 	vdso_data->wtm_clock_sec		= tk->wall_to_monotonic.tv_sec;
 	vdso_data->wtm_clock_nsec		= tk->wall_to_monotonic.tv_nsec;
 
diff --git a/arch/arm64/mm/Makefile b/arch/arm64/mm/Makefile
index 9d84feb..773d37a 100644
--- a/arch/arm64/mm/Makefile
+++ b/arch/arm64/mm/Makefile
@@ -4,5 +4,3 @@
 				   context.o proc.o pageattr.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_ARM64_PTDUMP)	+= dump.o
-
-CFLAGS_mmu.o			:= -I$(srctree)/scripts/dtc/libfdt/
diff --git a/arch/avr32/include/asm/Kbuild b/arch/avr32/include/asm/Kbuild
index 1d66afd..f61f2dd 100644
--- a/arch/avr32/include/asm/Kbuild
+++ b/arch/avr32/include/asm/Kbuild
@@ -12,6 +12,7 @@
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += param.h
 generic-y += percpu.h
 generic-y += preempt.h
diff --git a/arch/avr32/include/asm/mm-arch-hooks.h b/arch/avr32/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 145452f..0000000
--- a/arch/avr32/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_AVR32_MM_ARCH_HOOKS_H
-#define _ASM_AVR32_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_AVR32_MM_ARCH_HOOKS_H */
diff --git a/arch/avr32/kernel/time.c b/arch/avr32/kernel/time.c
index d0f771b..a124c55 100644
--- a/arch/avr32/kernel/time.c
+++ b/arch/avr32/kernel/time.c
@@ -18,6 +18,7 @@
 
 #include <mach/pm.h>
 
+static bool disable_cpu_idle_poll;
 
 static cycle_t read_cycle_count(struct clocksource *cs)
 {
@@ -80,45 +81,45 @@
 	return 0;
 }
 
-static void comparator_mode(enum clock_event_mode mode,
-		struct clock_event_device *evdev)
+static int comparator_shutdown(struct clock_event_device *evdev)
 {
-	switch (mode) {
-	case CLOCK_EVT_MODE_ONESHOT:
-		pr_debug("%s: start\n", evdev->name);
-		/* FALLTHROUGH */
-	case CLOCK_EVT_MODE_RESUME:
+	pr_debug("%s: %s\n", __func__, evdev->name);
+	sysreg_write(COMPARE, 0);
+
+	if (disable_cpu_idle_poll) {
+		disable_cpu_idle_poll = false;
 		/*
-		 * If we're using the COUNT and COMPARE registers we
-		 * need to force idle poll.
+		 * Only disable idle poll if we have forced that
+		 * in a previous call.
 		 */
-		cpu_idle_poll_ctrl(true);
-		break;
-	case CLOCK_EVT_MODE_UNUSED:
-	case CLOCK_EVT_MODE_SHUTDOWN:
-		sysreg_write(COMPARE, 0);
-		pr_debug("%s: stop\n", evdev->name);
-		if (evdev->mode == CLOCK_EVT_MODE_ONESHOT ||
-		    evdev->mode == CLOCK_EVT_MODE_RESUME) {
-			/*
-			 * Only disable idle poll if we have forced that
-			 * in a previous call.
-			 */
-			cpu_idle_poll_ctrl(false);
-		}
-		break;
-	default:
-		BUG();
+		cpu_idle_poll_ctrl(false);
 	}
+	return 0;
+}
+
+static int comparator_set_oneshot(struct clock_event_device *evdev)
+{
+	pr_debug("%s: %s\n", __func__, evdev->name);
+
+	disable_cpu_idle_poll = true;
+	/*
+	 * If we're using the COUNT and COMPARE registers we
+	 * need to force idle poll.
+	 */
+	cpu_idle_poll_ctrl(true);
+
+	return 0;
 }
 
 static struct clock_event_device comparator = {
-	.name		= "avr32_comparator",
-	.features	= CLOCK_EVT_FEAT_ONESHOT,
-	.shift		= 16,
-	.rating		= 50,
-	.set_next_event	= comparator_next_event,
-	.set_mode	= comparator_mode,
+	.name			= "avr32_comparator",
+	.features		= CLOCK_EVT_FEAT_ONESHOT,
+	.shift			= 16,
+	.rating			= 50,
+	.set_next_event		= comparator_next_event,
+	.set_state_shutdown	= comparator_shutdown,
+	.set_state_oneshot	= comparator_set_oneshot,
+	.tick_resume		= comparator_set_oneshot,
 };
 
 void read_persistent_clock(struct timespec *ts)
diff --git a/arch/avr32/mach-at32ap/clock.c b/arch/avr32/mach-at32ap/clock.c
index 23b1a97..52c179b 100644
--- a/arch/avr32/mach-at32ap/clock.c
+++ b/arch/avr32/mach-at32ap/clock.c
@@ -80,6 +80,9 @@
 {
 	unsigned long flags;
 
+	if (!clk)
+		return 0;
+
 	spin_lock_irqsave(&clk_lock, flags);
 	__clk_enable(clk);
 	spin_unlock_irqrestore(&clk_lock, flags);
@@ -106,6 +109,9 @@
 {
 	unsigned long flags;
 
+	if (IS_ERR_OR_NULL(clk))
+		return;
+
 	spin_lock_irqsave(&clk_lock, flags);
 	__clk_disable(clk);
 	spin_unlock_irqrestore(&clk_lock, flags);
@@ -117,6 +123,9 @@
 	unsigned long flags;
 	unsigned long rate;
 
+	if (!clk)
+		return 0;
+
 	spin_lock_irqsave(&clk_lock, flags);
 	rate = clk->get_rate(clk);
 	spin_unlock_irqrestore(&clk_lock, flags);
@@ -129,6 +138,9 @@
 {
 	unsigned long flags, actual_rate;
 
+	if (!clk)
+		return 0;
+
 	if (!clk->set_rate)
 		return -ENOSYS;
 
@@ -145,6 +157,9 @@
 	unsigned long flags;
 	long ret;
 
+	if (!clk)
+		return 0;
+
 	if (!clk->set_rate)
 		return -ENOSYS;
 
@@ -161,6 +176,9 @@
 	unsigned long flags;
 	int ret;
 
+	if (!clk)
+		return 0;
+
 	if (!clk->set_parent)
 		return -ENOSYS;
 
@@ -174,7 +192,7 @@
 
 struct clk *clk_get_parent(struct clk *clk)
 {
-	return clk->parent;
+	return !clk ? NULL : clk->parent;
 }
 EXPORT_SYMBOL(clk_get_parent);
 
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 07051a6..61cd1e7 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -21,6 +21,7 @@
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += mutex.h
diff --git a/arch/blackfin/include/asm/mm-arch-hooks.h b/arch/blackfin/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 1c5211e..0000000
--- a/arch/blackfin/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_BLACKFIN_MM_ARCH_HOOKS_H
-#define _ASM_BLACKFIN_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_BLACKFIN_MM_ARCH_HOOKS_H */
diff --git a/arch/c6x/include/asm/Kbuild b/arch/c6x/include/asm/Kbuild
index 7aeb322..f17c4dc 100644
--- a/arch/c6x/include/asm/Kbuild
+++ b/arch/c6x/include/asm/Kbuild
@@ -26,6 +26,7 @@
 generic-y += kmap_types.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += mmu.h
 generic-y += mmu_context.h
diff --git a/arch/c6x/include/asm/mm-arch-hooks.h b/arch/c6x/include/asm/mm-arch-hooks.h
deleted file mode 100644
index bb3c4a6..0000000
--- a/arch/c6x/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_C6X_MM_ARCH_HOOKS_H
-#define _ASM_C6X_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_C6X_MM_ARCH_HOOKS_H */
diff --git a/arch/cris/arch-v32/drivers/sync_serial.c b/arch/cris/arch-v32/drivers/sync_serial.c
index 4dda9bd..e989cee 100644
--- a/arch/cris/arch-v32/drivers/sync_serial.c
+++ b/arch/cris/arch-v32/drivers/sync_serial.c
@@ -1464,7 +1464,7 @@
 		if (port->write_ts_idx == NBR_IN_DESCR)
 			port->write_ts_idx = 0;
 		idx = port->write_ts_idx++;
-		do_posix_clock_monotonic_gettime(&port->timestamp[idx]);
+		ktime_get_ts(&port->timestamp[idx]);
 		port->in_buffer_len += port->inbufchunk;
 	}
 	spin_unlock_irqrestore(&port->lock, flags);
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index d294f6a..ad2244f 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -18,6 +18,7 @@
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += module.h
 generic-y += percpu.h
 generic-y += preempt.h
diff --git a/arch/cris/include/asm/mm-arch-hooks.h b/arch/cris/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 314f774..0000000
--- a/arch/cris/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_CRIS_MM_ARCH_HOOKS_H
-#define _ASM_CRIS_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_CRIS_MM_ARCH_HOOKS_H */
diff --git a/arch/frv/include/asm/Kbuild b/arch/frv/include/asm/Kbuild
index 30edce3..8e47b83 100644
--- a/arch/frv/include/asm/Kbuild
+++ b/arch/frv/include/asm/Kbuild
@@ -4,5 +4,6 @@
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += preempt.h
 generic-y += trace_clock.h
diff --git a/arch/frv/include/asm/mm-arch-hooks.h b/arch/frv/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 51d13a8..0000000
--- a/arch/frv/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_FRV_MM_ARCH_HOOKS_H
-#define _ASM_FRV_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_FRV_MM_ARCH_HOOKS_H */
diff --git a/arch/h8300/include/asm/Kbuild b/arch/h8300/include/asm/Kbuild
index 00379d6..70e6ae1 100644
--- a/arch/h8300/include/asm/Kbuild
+++ b/arch/h8300/include/asm/Kbuild
@@ -33,6 +33,7 @@
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += mmu.h
 generic-y += mmu_context.h
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 5ade4a1..daee37b 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -28,6 +28,7 @@
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += pci.h
diff --git a/arch/hexagon/include/asm/mm-arch-hooks.h b/arch/hexagon/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 05e8b93..0000000
--- a/arch/hexagon/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_HEXAGON_MM_ARCH_HOOKS_H
-#define _ASM_HEXAGON_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_HEXAGON_MM_ARCH_HOOKS_H */
diff --git a/arch/ia64/include/asm/Kbuild b/arch/ia64/include/asm/Kbuild
index ccff13d..9de3ba1 100644
--- a/arch/ia64/include/asm/Kbuild
+++ b/arch/ia64/include/asm/Kbuild
@@ -4,6 +4,7 @@
 generic-y += irq_work.h
 generic-y += kvm_para.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += preempt.h
 generic-y += trace_clock.h
 generic-y += vtime.h
diff --git a/arch/ia64/include/asm/mm-arch-hooks.h b/arch/ia64/include/asm/mm-arch-hooks.h
deleted file mode 100644
index ab4b5c6..0000000
--- a/arch/ia64/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_IA64_MM_ARCH_HOOKS_H
-#define _ASM_IA64_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_IA64_MM_ARCH_HOOKS_H */
diff --git a/arch/m32r/include/asm/Kbuild b/arch/m32r/include/asm/Kbuild
index ba1cdc0..e0eb704 100644
--- a/arch/m32r/include/asm/Kbuild
+++ b/arch/m32r/include/asm/Kbuild
@@ -4,6 +4,7 @@
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += module.h
 generic-y += preempt.h
 generic-y += sections.h
diff --git a/arch/m32r/include/asm/io.h b/arch/m32r/include/asm/io.h
index 0c3f25e..f8de767 100644
--- a/arch/m32r/include/asm/io.h
+++ b/arch/m32r/include/asm/io.h
@@ -174,6 +174,11 @@
 #define iowrite16 writew
 #define iowrite32 writel
 
+#define ioread16be(addr)	be16_to_cpu(readw(addr))
+#define ioread32be(addr)	be32_to_cpu(readl(addr))
+#define iowrite16be(v, addr)	writew(cpu_to_be16(v), (addr))
+#define iowrite32be(v, addr)	writel(cpu_to_be32(v), (addr))
+
 #define mmiowb()
 
 #define flush_write_buffers() do { } while (0)  /* M32R_FIXME */
diff --git a/arch/m32r/include/asm/mm-arch-hooks.h b/arch/m32r/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 6d60b47..0000000
--- a/arch/m32r/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_M32R_MM_ARCH_HOOKS_H
-#define _ASM_M32R_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_M32R_MM_ARCH_HOOKS_H */
diff --git a/arch/m68k/Kconfig.cpu b/arch/m68k/Kconfig.cpu
index 33013df..c496d48 100644
--- a/arch/m68k/Kconfig.cpu
+++ b/arch/m68k/Kconfig.cpu
@@ -125,6 +125,13 @@
 
 if COLDFIRE
 
+choice
+	prompt "ColdFire SoC type"
+	default M520x
+	help
+	  Select the type of ColdFire System-on-Chip (SoC) that you want
+	  to build for.
+
 config M5206
 	bool "MCF5206"
 	depends on !MMU
@@ -174,9 +181,6 @@
 	help
 	  Freescale (Motorola) Coldfire 5251/5253 processor support.
 
-config M527x
-	bool
-
 config M5271
 	bool "MCF5271"
 	depends on !MMU
@@ -223,9 +227,6 @@
 	help
 	  Motorola ColdFire 5307 processor support.
 
-config M53xx
-	bool
-
 config M532x
 	bool "MCF532x"
 	depends on !MMU
@@ -251,9 +252,6 @@
 	help
 	  Motorola ColdFire 5407 processor support.
 
-config M54xx
-	bool
-
 config M547x
 	bool "MCF547x"
 	select M54xx
@@ -280,6 +278,17 @@
 	help
 	  Freescale Coldfire 54410/54415/54416/54417/54418 processor support.
 
+endchoice
+
+config M527x
+	bool
+
+config M53xx
+	bool
+
+config M54xx
+	bool
+
 endif # COLDFIRE
 
 
@@ -416,22 +425,18 @@
 config HAVE_IPSBAR
 	bool
 
-config CLOCK_SET
-	bool "Enable setting the CPU clock frequency"
-	depends on COLDFIRE
-	default n
-	help
-	  On some CPU's you do not need to know what the core CPU clock
-	  frequency is. On these you can disable clock setting. On some
-	  traditional 68K parts, and on all ColdFire parts you need to set
-	  the appropriate CPU clock frequency. On these devices many of the
-	  onboard peripherals derive their timing from the master CPU clock
-	  frequency.
-
 config CLOCK_FREQ
 	int "Set the core clock frequency"
+	default "25000000" if M5206
+	default "54000000" if M5206e
+	default "166666666" if M520x
+	default "140000000" if M5249
+	default "150000000" if M527x || M523x
+	default "90000000" if M5307
+	default "50000000" if M5407
+	default "266000000" if M54xx
 	default "66666666"
-	depends on CLOCK_SET
+	depends on COLDFIRE
 	help
 	  Define the CPU clock frequency in use. This is the core clock
 	  frequency, it may or may not be the same as the external clock
diff --git a/arch/m68k/configs/m5208evb_defconfig b/arch/m68k/configs/m5208evb_defconfig
index e7292f4..4c7b793 100644
--- a/arch/m68k/configs/m5208evb_defconfig
+++ b/arch/m68k/configs/m5208evb_defconfig
@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -16,17 +12,12 @@
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
-CONFIG_M520x=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=166666666
-CONFIG_CLOCK_DIV=2
-CONFIG_M5208EVB=y
+# CONFIG_MMU is not set
 # CONFIG_4KSTACKS is not set
 CONFIG_RAMBASE=0x40000000
 CONFIG_RAMSIZE=0x2000000
 CONFIG_VECTORBASE=0x40000000
 CONFIG_KERNELBASE=0x40020000
-CONFIG_RAM16BIT=y
 CONFIG_BINFMT_FLAT=y
 CONFIG_NET=y
 CONFIG_PACKET=y
@@ -40,24 +31,19 @@
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_FEC=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_BAUDRATE=115200
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_UNIX98_PTYS is not set
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
@@ -68,8 +54,6 @@
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_FULLDEBUG=y
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
+CONFIG_FULLDEBUG=y
diff --git a/arch/m68k/configs/m5249evb_defconfig b/arch/m68k/configs/m5249evb_defconfig
index 0cd4b39..a782f36 100644
--- a/arch/m68k/configs/m5249evb_defconfig
+++ b/arch/m68k/configs/m5249evb_defconfig
@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -16,10 +12,8 @@
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
 CONFIG_M5249=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=140000000
-CONFIG_CLOCK_DIV=2
 CONFIG_M5249C3=y
 CONFIG_RAMBASE=0x00000000
 CONFIG_RAMSIZE=0x00800000
@@ -38,23 +32,18 @@
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 CONFIG_PPP=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_UNIX98_PTYS is not set
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
@@ -62,7 +51,5 @@
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
-# CONFIG_CRC32 is not set
diff --git a/arch/m68k/configs/m5272c3_defconfig b/arch/m68k/configs/m5272c3_defconfig
index a60cb35..6f5fb92 100644
--- a/arch/m68k/configs/m5272c3_defconfig
+++ b/arch/m68k/configs/m5272c3_defconfig
@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -16,8 +12,8 @@
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
 CONFIG_M5272=y
-CONFIG_CLOCK_SET=y
 CONFIG_M5272C3=y
 CONFIG_RAMBASE=0x00000000
 CONFIG_RAMSIZE=0x00800000
@@ -36,23 +32,18 @@
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_FEC=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_UNIX98_PTYS is not set
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
@@ -61,6 +52,5 @@
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
diff --git a/arch/m68k/configs/m5275evb_defconfig b/arch/m68k/configs/m5275evb_defconfig
index e6502ab..b5d7cd1 100644
--- a/arch/m68k/configs/m5275evb_defconfig
+++ b/arch/m68k/configs/m5275evb_defconfig
@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -16,11 +12,8 @@
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
 CONFIG_M5275=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=150000000
-CONFIG_CLOCK_DIV=2
-CONFIG_M5275EVB=y
 # CONFIG_4KSTACKS is not set
 CONFIG_RAMBASE=0x00000000
 CONFIG_RAMSIZE=0x00000000
@@ -39,24 +32,19 @@
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
 CONFIG_FEC=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 CONFIG_PPP=y
 # CONFIG_INPUT is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_UNIX98_PTYS is not set
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
@@ -65,8 +53,5 @@
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
-# CONFIG_CRC32 is not set
diff --git a/arch/m68k/configs/m5307c3_defconfig b/arch/m68k/configs/m5307c3_defconfig
index 023812a..1b4c094 100644
--- a/arch/m68k/configs/m5307c3_defconfig
+++ b/arch/m68k/configs/m5307c3_defconfig
@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -16,10 +12,8 @@
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
 CONFIG_M5307=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=90000000
-CONFIG_CLOCK_DIV=2
 CONFIG_M5307C3=y
 CONFIG_RAMBASE=0x00000000
 CONFIG_RAMSIZE=0x00800000
@@ -38,16 +32,11 @@
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 CONFIG_PPP=y
 CONFIG_SLIP=y
 CONFIG_SLIP_COMPRESSED=y
@@ -56,21 +45,17 @@
 # CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 # CONFIG_VT is not set
+# CONFIG_LEGACY_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_LEGACY_PTYS is not set
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
-# CONFIG_HID_SUPPORT is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_EXT2_FS=y
 # CONFIG_DNOTIFY is not set
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
-CONFIG_FULLDEBUG=y
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
-# CONFIG_CRC32 is not set
+CONFIG_FULLDEBUG=y
diff --git a/arch/m68k/configs/m5407c3_defconfig b/arch/m68k/configs/m5407c3_defconfig
index 557b39f..275ad543 100644
--- a/arch/m68k/configs/m5407c3_defconfig
+++ b/arch/m68k/configs/m5407c3_defconfig
@@ -1,10 +1,6 @@
-# CONFIG_MMU is not set
-CONFIG_EXPERIMENTAL=y
 CONFIG_LOG_BUF_SHIFT=14
-# CONFIG_CC_OPTIMIZE_FOR_SIZE is not set
 CONFIG_EXPERT=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -17,9 +13,8 @@
 # CONFIG_BLK_DEV_BSG is not set
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
+# CONFIG_MMU is not set
 CONFIG_M5407=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=50000000
 CONFIG_M5407C3=y
 CONFIG_RAMBASE=0x00000000
 CONFIG_RAMSIZE=0x00000000
@@ -38,22 +33,17 @@
 # CONFIG_IPV6 is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_RAM=y
 CONFIG_MTD_UCLINUX=y
 CONFIG_BLK_DEV_RAM=y
-# CONFIG_MISC_DEVICES is not set
 CONFIG_NETDEVICES=y
-CONFIG_NET_ETHERNET=y
-# CONFIG_NETDEV_1000 is not set
-# CONFIG_NETDEV_10000 is not set
 CONFIG_PPP=y
 # CONFIG_INPUT is not set
 # CONFIG_VT is not set
+# CONFIG_UNIX98_PTYS is not set
 CONFIG_SERIAL_MCF=y
 CONFIG_SERIAL_MCF_CONSOLE=y
-# CONFIG_UNIX98_PTYS is not set
 # CONFIG_HW_RANDOM is not set
 # CONFIG_HWMON is not set
 # CONFIG_USB_SUPPORT is not set
@@ -63,8 +53,5 @@
 CONFIG_ROMFS_FS=y
 CONFIG_ROMFS_BACKED_BY_MTD=y
 # CONFIG_NETWORK_FILESYSTEMS is not set
-# CONFIG_RCU_CPU_STALL_DETECTOR is not set
-CONFIG_SYSCTL_SYSCALL_CHECK=y
 CONFIG_BOOTPARAM=y
 CONFIG_BOOTPARAM_STRING="root=/dev/mtdblock0"
-# CONFIG_CRC32 is not set
diff --git a/arch/m68k/configs/m5475evb_defconfig b/arch/m68k/configs/m5475evb_defconfig
index c5018a6..4f4ccd13 100644
--- a/arch/m68k/configs/m5475evb_defconfig
+++ b/arch/m68k/configs/m5475evb_defconfig
@@ -1,11 +1,7 @@
-CONFIG_EXPERIMENTAL=y
 # CONFIG_SWAP is not set
 CONFIG_LOG_BUF_SHIFT=14
-CONFIG_SYSFS_DEPRECATED=y
-CONFIG_SYSFS_DEPRECATED_V2=y
 CONFIG_SYSCTL_SYSCALL=y
 # CONFIG_KALLSYMS is not set
-# CONFIG_HOTPLUG is not set
 # CONFIG_FUTEX is not set
 # CONFIG_EPOLL is not set
 # CONFIG_SIGNALFD is not set
@@ -20,19 +16,16 @@
 # CONFIG_IOSCHED_DEADLINE is not set
 # CONFIG_IOSCHED_CFQ is not set
 CONFIG_COLDFIRE=y
-CONFIG_M547x=y
-CONFIG_CLOCK_SET=y
-CONFIG_CLOCK_FREQ=266000000
 # CONFIG_4KSTACKS is not set
 CONFIG_RAMBASE=0x0
 CONFIG_RAMSIZE=0x2000000
 CONFIG_VECTORBASE=0x0
 CONFIG_MBAR=0xff000000
 CONFIG_KERNELBASE=0x20000
+CONFIG_PCI=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 # CONFIG_FW_LOADER is not set
 CONFIG_MTD=y
-CONFIG_MTD_CHAR=y
 CONFIG_MTD_BLOCK=y
 CONFIG_MTD_CFI=y
 CONFIG_MTD_JEDECPROBE=y
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 1555bc1..eb85bd9 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -18,6 +18,7 @@
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += mutex.h
 generic-y += percpu.h
diff --git a/arch/m68k/include/asm/coldfire.h b/arch/m68k/include/asm/coldfire.h
index c94557b..50aa4da 100644
--- a/arch/m68k/include/asm/coldfire.h
+++ b/arch/m68k/include/asm/coldfire.h
@@ -19,7 +19,7 @@
  *	in any case new boards come along from time to time that have yet
  *	another different clocking frequency.
  */
-#ifdef CONFIG_CLOCK_SET
+#ifdef CONFIG_CLOCK_FREQ
 #define	MCF_CLK		CONFIG_CLOCK_FREQ
 #else
 #error "Don't know what your ColdFire CPU clock frequency is??"
diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h
index 618c85d3..f55cad5 100644
--- a/arch/m68k/include/asm/io_mm.h
+++ b/arch/m68k/include/asm/io_mm.h
@@ -413,7 +413,8 @@
 #define writew(val, addr)	out_le16((addr), (val))
 #endif /* CONFIG_ATARI_ROM_ISA */
 
-#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA)
+#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA) && \
+    !(defined(CONFIG_PCI) && defined(CONFIG_COLDFIRE))
 /*
  * We need to define dummy functions for GENERIC_IOMAP support.
  */
diff --git a/arch/m68k/include/asm/mm-arch-hooks.h b/arch/m68k/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 7e8709b..0000000
--- a/arch/m68k/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_M68K_MM_ARCH_HOOKS_H
-#define _ASM_M68K_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_M68K_MM_ARCH_HOOKS_H */
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index 199320f..df31353 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -25,6 +25,7 @@
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += msgbuf.h
 generic-y += mutex.h
 generic-y += param.h
diff --git a/arch/metag/include/asm/mm-arch-hooks.h b/arch/metag/include/asm/mm-arch-hooks.h
deleted file mode 100644
index b0072b2..0000000
--- a/arch/metag/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_METAG_MM_ARCH_HOOKS_H
-#define _ASM_METAG_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_METAG_MM_ARCH_HOOKS_H */
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index 9989ddb..2f222f3 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -6,6 +6,7 @@
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += preempt.h
 generic-y += syscalls.h
 generic-y += trace_clock.h
diff --git a/arch/microblaze/include/asm/mm-arch-hooks.h b/arch/microblaze/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 5c40659..0000000
--- a/arch/microblaze/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_MICROBLAZE_MM_ARCH_HOOKS_H
-#define _ASM_MICROBLAZE_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_MICROBLAZE_MM_ARCH_HOOKS_H */
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 2a14585..199a835 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -151,7 +151,6 @@
 	select BCM7120_L2_IRQ
 	select BRCMSTB_L2_IRQ
 	select IRQ_MIPS_CPU
-	select RAW_IRQ_ACCESSORS
 	select DMA_NONCOHERENT
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -1427,6 +1426,7 @@
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_MSA
 	select GENERIC_CSUM
+	select MIPS_O32_FP64_SUPPORT if MIPS32_O32
 	help
 	  Choose this option to build a kernel for release 6 or later of the
 	  MIPS64 architecture.  New MIPS processors, starting with the Warrior
@@ -2231,7 +2231,7 @@
 
 config MIPS_CPS
 	bool "MIPS Coherent Processing System support"
-	depends on SYS_SUPPORTS_MIPS_CPS && !64BIT
+	depends on SYS_SUPPORTS_MIPS_CPS
 	select MIPS_CM
 	select MIPS_CPC
 	select MIPS_CPS_PM if HOTPLUG_CPU
@@ -2262,11 +2262,6 @@
 config MIPS_CPC
 	bool
 
-config SB1_PASS_1_WORKAROUNDS
-	bool
-	depends on CPU_SB1_PASS_1
-	default y
-
 config SB1_PASS_2_WORKAROUNDS
 	bool
 	depends on CPU_SB1 && (CPU_SB1_PASS_2_2 || CPU_SB1_PASS_2)
diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index ae2dd59..252e347 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -181,13 +181,6 @@
 cflags-$(CONFIG_CPU_R4400_WORKAROUNDS)	+= $(call cc-option,-mfix-r4400,)
 cflags-$(CONFIG_CPU_DADDI_WORKAROUNDS)	+= $(call cc-option,-mno-daddi,)
 
-ifdef CONFIG_CPU_SB1
-ifdef CONFIG_SB1_PASS_1_WORKAROUNDS
-KBUILD_AFLAGS_MODULE += -msb1-pass1-workarounds
-KBUILD_CFLAGS_MODULE += -msb1-pass1-workarounds
-endif
-endif
-
 # For smartmips configurations, there are hundreds of warnings due to ISA overrides
 # in assembly and header files. smartmips is only supported for MIPS32r1 onwards
 # and there is no support for 64-bit. Various '.set mips2' or '.set mips3' or
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index 01a644f..1ba2120 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -190,6 +190,7 @@
 {
 	return ATH79_MISC_IRQ(5);
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 56f5d08..b7fa9ae 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -42,7 +42,7 @@
 	cvmx_write_csr(CVMX_CIU_MBOX_CLRX(coreid), action);
 
 	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+		generic_smp_call_function_interrupt();
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 7fe5c61..1f85460 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -7,6 +7,7 @@
 generic-y += irq_work.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mutex.h
 generic-y += parport.h
 generic-y += percpu.h
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 084780b..1b06251 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -74,7 +74,7 @@
 		goto fr_common;
 
 	case FPU_64BIT:
-#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_CPU_MIPS32_R6) \
+#if !(defined(CONFIG_CPU_MIPSR2) || defined(CONFIG_CPU_MIPSR6) \
       || defined(CONFIG_64BIT))
 		/* we only have a 32-bit FPU */
 		return SIGFPE;
diff --git a/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h b/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h
deleted file mode 100644
index 11d3b57..0000000
--- a/arch/mips/include/asm/mach-bcm63xx/dma-coherence.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef __ASM_MACH_BCM63XX_DMA_COHERENCE_H
-#define __ASM_MACH_BCM63XX_DMA_COHERENCE_H
-
-#include <asm/bmips.h>
-
-#define plat_post_dma_flush	bmips_post_dma_flush
-
-#include <asm/mach-generic/dma-coherence.h>
-
-#endif /* __ASM_MACH_BCM63XX_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-loongson64/mmzone.h b/arch/mips/include/asm/mach-loongson64/mmzone.h
index 37c08a2..c9f7e23 100644
--- a/arch/mips/include/asm/mach-loongson64/mmzone.h
+++ b/arch/mips/include/asm/mach-loongson64/mmzone.h
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2010 Loongson Inc. & Lemote Inc. &
- *                    Insititute of Computing Technology
+ *                    Institute of Computing Technology
  * Author:  Xiang Gao, gaoxiang@ict.ac.cn
  *          Huacai Chen, chenhc@lemote.com
  *          Xiaofu Meng, Shuangshuang Zhang
diff --git a/arch/mips/include/asm/mach-sibyte/war.h b/arch/mips/include/asm/mach-sibyte/war.h
index 0a227d4..520f8fc 100644
--- a/arch/mips/include/asm/mach-sibyte/war.h
+++ b/arch/mips/include/asm/mach-sibyte/war.h
@@ -13,8 +13,7 @@
 #define R4600_V2_HIT_CACHEOP_WAR	0
 #define R5432_CP0_INTERRUPT_WAR		0
 
-#if defined(CONFIG_SB1_PASS_1_WORKAROUNDS) || \
-    defined(CONFIG_SB1_PASS_2_WORKAROUNDS)
+#if defined(CONFIG_SB1_PASS_2_WORKAROUNDS)
 
 #ifndef __ASSEMBLY__
 extern int sb1250_m3_workaround_needed(void);
diff --git a/arch/mips/include/asm/mm-arch-hooks.h b/arch/mips/include/asm/mm-arch-hooks.h
deleted file mode 100644
index b5609fe..0000000
--- a/arch/mips/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_MIPS_MM_ARCH_HOOKS_H
-#define _ASM_MIPS_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_MIPS_MM_ARCH_HOOKS_H */
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index 9d81067..ae85694 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -182,8 +182,39 @@
 		 * Make sure the buddy is global too (if it's !none,
 		 * it better already be global)
 		 */
+#ifdef CONFIG_SMP
+		/*
+		 * For SMP, multiple CPUs can race, so we need to do
+		 * this atomically.
+		 */
+#ifdef CONFIG_64BIT
+#define LL_INSN "lld"
+#define SC_INSN "scd"
+#else /* CONFIG_32BIT */
+#define LL_INSN "ll"
+#define SC_INSN "sc"
+#endif
+		unsigned long page_global = _PAGE_GLOBAL;
+		unsigned long tmp;
+
+		__asm__ __volatile__ (
+			"	.set	push\n"
+			"	.set	noreorder\n"
+			"1:	" LL_INSN "	%[tmp], %[buddy]\n"
+			"	bnez	%[tmp], 2f\n"
+			"	 or	%[tmp], %[tmp], %[global]\n"
+			"	" SC_INSN "	%[tmp], %[buddy]\n"
+			"	beqz	%[tmp], 1b\n"
+			"	 nop\n"
+			"2:\n"
+			"	.set pop"
+			: [buddy] "+m" (buddy->pte),
+			  [tmp] "=&r" (tmp)
+			: [global] "r" (page_global));
+#else /* !CONFIG_SMP */
 		if (pte_none(*buddy))
 			pte_val(*buddy) = pte_val(*buddy) | _PAGE_GLOBAL;
+#endif /* CONFIG_SMP */
 	}
 #endif
 }
diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index 2b25d1b..03722d4 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -23,6 +23,7 @@
 extern int smp_num_siblings;
 extern cpumask_t cpu_sibling_map[];
 extern cpumask_t cpu_core_map[];
+extern cpumask_t cpu_foreign_map;
 
 #define raw_smp_processor_id() (current_thread_info()->cpu)
 
@@ -82,8 +83,6 @@
 extern void play_dead(void);
 #endif
 
-extern asmlinkage void smp_call_function_interrupt(void);
-
 static inline void arch_send_call_function_single_ipi(int cpu)
 {
 	extern struct plat_smp_ops *mp_ops;	/* private */
diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h
index 28d6d93..a71da57 100644
--- a/arch/mips/include/asm/stackframe.h
+++ b/arch/mips/include/asm/stackframe.h
@@ -152,6 +152,31 @@
 		.set	noreorder
 		bltz	k0, 8f
 		 move	k1, sp
+#ifdef CONFIG_EVA
+		/*
+		 * Flush interAptiv's Return Prediction Stack (RPS) by writing
+		 * EntryHi. Toggling Config7.RPS is slower and less portable.
+		 *
+		 * The RPS isn't automatically flushed when exceptions are
+		 * taken, which can result in kernel mode speculative accesses
+		 * to user addresses if the RPS mispredicts. That's harmless
+		 * when user and kernel share the same address space, but with
+		 * EVA the same user segments may be unmapped to kernel mode,
+		 * even containing sensitive MMIO regions or invalid memory.
+		 *
+		 * This can happen when the kernel sets the return address to
+		 * ret_from_* and jr's to the exception handler, which looks
+		 * more like a tail call than a function call. If nested calls
+		 * don't evict the last user address in the RPS, it will
+		 * mispredict the return and fetch from a user controlled
+		 * address into the icache.
+		 *
+		 * More recent EVA-capable cores with MAAR to restrict
+		 * speculative accesses aren't affected.
+		 */
+		MFC0	k0, CP0_ENTRYHI
+		MTC0	k0, CP0_ENTRYHI
+#endif
 		.set	reorder
 		/* Called from user mode, new stack. */
 		get_saved_sp
diff --git a/arch/mips/include/uapi/asm/sigcontext.h b/arch/mips/include/uapi/asm/sigcontext.h
index 6c9906f..9081d88 100644
--- a/arch/mips/include/uapi/asm/sigcontext.h
+++ b/arch/mips/include/uapi/asm/sigcontext.h
@@ -16,7 +16,7 @@
 
 /*
  * Keep this struct definition in sync with the sigcontext fragment
- * in arch/mips/tools/offset.c
+ * in arch/mips/kernel/asm-offsets.c
  */
 struct sigcontext {
 	unsigned int		sc_regmask;	/* Unused */
@@ -46,7 +46,7 @@
 #include <linux/posix_types.h>
 /*
  * Keep this struct definition in sync with the sigcontext fragment
- * in arch/mips/tools/offset.c
+ * in arch/mips/kernel/asm-offsets.c
  *
  * Warning: this structure illdefined with sc_badvaddr being just an unsigned
  * int so it was changed to unsigned long in 2.6.0-test1.  This may break
diff --git a/arch/mips/kernel/asm-offsets.c b/arch/mips/kernel/asm-offsets.c
index beabe19..072fab1 100644
--- a/arch/mips/kernel/asm-offsets.c
+++ b/arch/mips/kernel/asm-offsets.c
@@ -1,5 +1,5 @@
 /*
- * offset.c: Calculate pt_regs and task_struct offsets.
+ * asm-offsets.c: Calculate pt_regs and task_struct offsets.
  *
  * Copyright (C) 1996 David S. Miller
  * Copyright (C) 1997, 1998, 1999, 2000, 2001, 2002, 2003 Ralf Baechle
diff --git a/arch/mips/kernel/branch.c b/arch/mips/kernel/branch.c
index c0c5e59..d8f9b35 100644
--- a/arch/mips/kernel/branch.c
+++ b/arch/mips/kernel/branch.c
@@ -600,7 +600,7 @@
 		break;
 
 	case blezl_op: /* not really i_format */
-		if (NO_R6EMU)
+		if (!insn.i_format.rt && NO_R6EMU)
 			goto sigill_r6;
 	case blez_op:
 		/*
@@ -635,7 +635,7 @@
 		break;
 
 	case bgtzl_op:
-		if (NO_R6EMU)
+		if (!insn.i_format.rt && NO_R6EMU)
 			goto sigill_r6;
 	case bgtz_op:
 		/*
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index 55b759a..1b6ca63 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -60,7 +60,7 @@
 	 nop
 
 	/* This is an NMI */
-	la	k0, nmi_handler
+	PTR_LA	k0, nmi_handler
 	jr	k0
 	 nop
 
@@ -107,10 +107,10 @@
 	mul	t1, t1, t0
 	mul	t1, t1, t2
 
-	li	a0, KSEG0
-	add	a1, a0, t1
+	li	a0, CKSEG0
+	PTR_ADD	a1, a0, t1
 1:	cache	Index_Store_Tag_I, 0(a0)
-	add	a0, a0, t0
+	PTR_ADD	a0, a0, t0
 	bne	a0, a1, 1b
 	 nop
 icache_done:
@@ -134,12 +134,12 @@
 	mul	t1, t1, t0
 	mul	t1, t1, t2
 
-	li	a0, KSEG0
-	addu	a1, a0, t1
-	subu	a1, a1, t0
+	li	a0, CKSEG0
+	PTR_ADDU a1, a0, t1
+	PTR_SUBU a1, a1, t0
 1:	cache	Index_Store_Tag_D, 0(a0)
 	bne	a0, a1, 1b
-	 add	a0, a0, t0
+	 PTR_ADD a0, a0, t0
 dcache_done:
 
 	/* Set Kseg0 CCA to that in s0 */
@@ -152,11 +152,11 @@
 
 	/* Enter the coherent domain */
 	li	t0, 0xff
-	sw	t0, GCR_CL_COHERENCE_OFS(v1)
+	PTR_S	t0, GCR_CL_COHERENCE_OFS(v1)
 	ehb
 
 	/* Jump to kseg0 */
-	la	t0, 1f
+	PTR_LA	t0, 1f
 	jr	t0
 	 nop
 
@@ -178,9 +178,9 @@
 	 nop
 
 	/* Off we go! */
-	lw	t1, VPEBOOTCFG_PC(v0)
-	lw	gp, VPEBOOTCFG_GP(v0)
-	lw	sp, VPEBOOTCFG_SP(v0)
+	PTR_L	t1, VPEBOOTCFG_PC(v0)
+	PTR_L	gp, VPEBOOTCFG_GP(v0)
+	PTR_L	sp, VPEBOOTCFG_SP(v0)
 	jr	t1
 	 nop
 	END(mips_cps_core_entry)
@@ -217,7 +217,7 @@
 
 .org 0x480
 LEAF(excep_ejtag)
-	la	k0, ejtag_debug_handler
+	PTR_LA	k0, ejtag_debug_handler
 	jr	k0
 	 nop
 	END(excep_ejtag)
@@ -229,7 +229,7 @@
 	 nop
 
 	.set	push
-	.set	mips32r2
+	.set	mips64r2
 	.set	mt
 
 	/* Only allow 1 TC per VPE to execute... */
@@ -237,7 +237,7 @@
 
 	/* ...and for the moment only 1 VPE */
 	dvpe
-	la	t1, 1f
+	PTR_LA	t1, 1f
 	jr.hb	t1
 	 nop
 
@@ -250,25 +250,25 @@
 	mfc0	t0, CP0_MVPCONF0
 	srl	t0, t0, MVPCONF0_PVPE_SHIFT
 	andi	t0, t0, (MVPCONF0_PVPE >> MVPCONF0_PVPE_SHIFT)
-	addiu	t7, t0, 1
+	addiu	ta3, t0, 1
 
 	/* If there's only 1, we're done */
 	beqz	t0, 2f
 	 nop
 
 	/* Loop through each VPE within this core */
-	li	t5, 1
+	li	ta1, 1
 
 1:	/* Operate on the appropriate TC */
-	mtc0	t5, CP0_VPECONTROL
+	mtc0	ta1, CP0_VPECONTROL
 	ehb
 
 	/* Bind TC to VPE (1:1 TC:VPE mapping) */
-	mttc0	t5, CP0_TCBIND
+	mttc0	ta1, CP0_TCBIND
 
 	/* Set exclusive TC, non-active, master */
 	li	t0, VPECONF0_MVP
-	sll	t1, t5, VPECONF0_XTC_SHIFT
+	sll	t1, ta1, VPECONF0_XTC_SHIFT
 	or	t0, t0, t1
 	mttc0	t0, CP0_VPECONF0
 
@@ -280,8 +280,8 @@
 	mttc0	t0, CP0_TCHALT
 
 	/* Next VPE */
-	addiu	t5, t5, 1
-	slt	t0, t5, t7
+	addiu	ta1, ta1, 1
+	slt	t0, ta1, ta3
 	bnez	t0, 1b
 	 nop
 
@@ -298,19 +298,19 @@
 
 LEAF(mips_cps_boot_vpes)
 	/* Retrieve CM base address */
-	la	t0, mips_cm_base
-	lw	t0, 0(t0)
+	PTR_LA	t0, mips_cm_base
+	PTR_L	t0, 0(t0)
 
 	/* Calculate a pointer to this cores struct core_boot_config */
-	lw	t0, GCR_CL_ID_OFS(t0)
+	PTR_L	t0, GCR_CL_ID_OFS(t0)
 	li	t1, COREBOOTCFG_SIZE
 	mul	t0, t0, t1
-	la	t1, mips_cps_core_bootcfg
-	lw	t1, 0(t1)
-	addu	t0, t0, t1
+	PTR_LA	t1, mips_cps_core_bootcfg
+	PTR_L	t1, 0(t1)
+	PTR_ADDU t0, t0, t1
 
 	/* Calculate this VPEs ID. If the core doesn't support MT use 0 */
-	has_mt	t6, 1f
+	has_mt	ta2, 1f
 	 li	t9, 0
 
 	/* Find the number of VPEs present in the core */
@@ -334,24 +334,24 @@
 1:	/* Calculate a pointer to this VPEs struct vpe_boot_config */
 	li	t1, VPEBOOTCFG_SIZE
 	mul	v0, t9, t1
-	lw	t7, COREBOOTCFG_VPECONFIG(t0)
-	addu	v0, v0, t7
+	PTR_L	ta3, COREBOOTCFG_VPECONFIG(t0)
+	PTR_ADDU v0, v0, ta3
 
 #ifdef CONFIG_MIPS_MT
 
 	/* If the core doesn't support MT then return */
-	bnez	t6, 1f
+	bnez	ta2, 1f
 	 nop
 	jr	ra
 	 nop
 
 	.set	push
-	.set	mips32r2
+	.set	mips64r2
 	.set	mt
 
 1:	/* Enter VPE configuration state */
 	dvpe
-	la	t1, 1f
+	PTR_LA	t1, 1f
 	jr.hb	t1
 	 nop
 1:	mfc0	t1, CP0_MVPCONTROL
@@ -360,12 +360,12 @@
 	ehb
 
 	/* Loop through each VPE */
-	lw	t6, COREBOOTCFG_VPEMASK(t0)
-	move	t8, t6
-	li	t5, 0
+	PTR_L	ta2, COREBOOTCFG_VPEMASK(t0)
+	move	t8, ta2
+	li	ta1, 0
 
 	/* Check whether the VPE should be running. If not, skip it */
-1:	andi	t0, t6, 1
+1:	andi	t0, ta2, 1
 	beqz	t0, 2f
 	 nop
 
@@ -373,7 +373,7 @@
 	mfc0	t0, CP0_VPECONTROL
 	ori	t0, t0, VPECONTROL_TARGTC
 	xori	t0, t0, VPECONTROL_TARGTC
-	or	t0, t0, t5
+	or	t0, t0, ta1
 	mtc0	t0, CP0_VPECONTROL
 	ehb
 
@@ -384,8 +384,8 @@
 
 	/* Calculate a pointer to the VPEs struct vpe_boot_config */
 	li	t0, VPEBOOTCFG_SIZE
-	mul	t0, t0, t5
-	addu	t0, t0, t7
+	mul	t0, t0, ta1
+	addu	t0, t0, ta3
 
 	/* Set the TC restart PC */
 	lw	t1, VPEBOOTCFG_PC(t0)
@@ -423,9 +423,9 @@
 	mttc0	t0, CP0_VPECONF0
 
 	/* Next VPE */
-2:	srl	t6, t6, 1
-	addiu	t5, t5, 1
-	bnez	t6, 1b
+2:	srl	ta2, ta2, 1
+	addiu	ta1, ta1, 1
+	bnez	ta2, 1b
 	 nop
 
 	/* Leave VPE configuration state */
@@ -445,7 +445,7 @@
 	/* This VPE should be offline, halt the TC */
 	li	t0, TCHALT_H
 	mtc0	t0, CP0_TCHALT
-	la	t0, 1f
+	PTR_LA	t0, 1f
 1:	jr.hb	t0
 	 nop
 
@@ -466,10 +466,10 @@
 	.set	noat
 	lw	$1, TI_CPU(gp)
 	sll	$1, $1, LONGLOG
-	la	\dest, __per_cpu_offset
+	PTR_LA	\dest, __per_cpu_offset
 	addu	$1, $1, \dest
 	lw	$1, 0($1)
-	la	\dest, cps_cpu_state
+	PTR_LA	\dest, cps_cpu_state
 	addu	\dest, \dest, $1
 	.set	pop
 	.endm
diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index af42e70..baa7b6f 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -407,7 +407,7 @@
 	.set	noat
 	SAVE_ALL
 	FEXPORT(handle_\exception\ext)
-	__BUILD_clear_\clear
+	__build_clear_\clear
 	.set	at
 	__BUILD_\verbose \exception
 	move	a0, sp
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index 3e4491a..789d7bf 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -154,7 +154,7 @@
 				      unsigned long __user *user_mask_ptr)
 {
 	unsigned int real_len;
-	cpumask_t mask;
+	cpumask_t allowed, mask;
 	int retval;
 	struct task_struct *p;
 
@@ -173,7 +173,8 @@
 	if (retval)
 		goto out_unlock;
 
-	cpumask_and(&mask, &p->thread.user_cpus_allowed, cpu_possible_mask);
+	cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed);
+	cpumask_and(&mask, &allowed, cpu_active_mask);
 
 out_unlock:
 	read_unlock(&tasklist_lock);
diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c
index b130033..5fcec30 100644
--- a/arch/mips/kernel/prom.c
+++ b/arch/mips/kernel/prom.c
@@ -38,7 +38,7 @@
 	return mips_machine_name;
 }
 
-#ifdef CONFIG_OF
+#ifdef CONFIG_USE_OF
 void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 {
 	return add_memory_region(base, size, BOOT_MEM_RAM);
diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S
index 74bab9d..c6bbf21 100644
--- a/arch/mips/kernel/relocate_kernel.S
+++ b/arch/mips/kernel/relocate_kernel.S
@@ -24,7 +24,7 @@
 
 process_entry:
 	PTR_L		s2, (s0)
-	PTR_ADD		s0, s0, SZREG
+	PTR_ADDIU	s0, s0, SZREG
 
 	/*
 	 * In case of a kdump/crash kernel, the indirection page is not
@@ -61,9 +61,9 @@
 	/* copy page word by word */
 	REG_L		s5, (s2)
 	REG_S		s5, (s4)
-	PTR_ADD		s4, s4, SZREG
-	PTR_ADD		s2, s2, SZREG
-	LONG_SUB	s6, s6, 1
+	PTR_ADDIU	s4, s4, SZREG
+	PTR_ADDIU	s2, s2, SZREG
+	LONG_ADDIU	s6, s6, -1
 	beq		s6, zero, process_entry
 	b		copy_word
 	b		process_entry
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 6e8de80..4cc1350 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -73,10 +73,11 @@
 	.set    noreorder
 	.set	nomacro
 
-1:	user_lw(t5, 16(t0))		# argument #5 from usp
-4:	user_lw(t6, 20(t0))		# argument #6 from usp
-3:	user_lw(t7, 24(t0))		# argument #7 from usp
-2:	user_lw(t8, 28(t0))		# argument #8 from usp
+load_a4: user_lw(t5, 16(t0))		# argument #5 from usp
+load_a5: user_lw(t6, 20(t0))		# argument #6 from usp
+load_a6: user_lw(t7, 24(t0))		# argument #7 from usp
+load_a7: user_lw(t8, 28(t0))		# argument #8 from usp
+loads_done:
 
 	sw	t5, 16(sp)		# argument #5 to ksp
 	sw	t6, 20(sp)		# argument #6 to ksp
@@ -85,10 +86,10 @@
 	.set	pop
 
 	.section __ex_table,"a"
-	PTR	1b,bad_stack
-	PTR	2b,bad_stack
-	PTR	3b,bad_stack
-	PTR	4b,bad_stack
+	PTR	load_a4, bad_stack_a4
+	PTR	load_a5, bad_stack_a5
+	PTR	load_a6, bad_stack_a6
+	PTR	load_a7, bad_stack_a7
 	.previous
 
 	lw	t0, TI_FLAGS($28)	# syscall tracing enabled?
@@ -153,8 +154,8 @@
 /* ------------------------------------------------------------------------ */
 
 	/*
-	 * The stackpointer for a call with more than 4 arguments is bad.
-	 * We probably should handle this case a bit more drastic.
+	 * Our open-coded access area sanity test for the stack pointer
+	 * failed. We probably should handle this case a bit more drastic.
 	 */
 bad_stack:
 	li	v0, EFAULT
@@ -163,6 +164,22 @@
 	sw	t0, PT_R7(sp)
 	j	o32_syscall_exit
 
+bad_stack_a4:
+	li	t5, 0
+	b	load_a5
+
+bad_stack_a5:
+	li	t6, 0
+	b	load_a6
+
+bad_stack_a6:
+	li	t7, 0
+	b	load_a7
+
+bad_stack_a7:
+	li	t8, 0
+	b	loads_done
+
 	/*
 	 * The system call does not exist in this kernel
 	 */
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index ad4d4463..a6f6b76 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -80,7 +80,7 @@
 	SAVE_STATIC
 	move	s0, t2
 	move	a0, sp
-	daddiu	a1, v0, __NR_64_Linux
+	move	a1, v0
 	jal	syscall_trace_enter
 
 	bltz	v0, 2f			# seccomp failed? Skip syscall
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 446cc65..4b20106 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -72,7 +72,7 @@
 	SAVE_STATIC
 	move	s0, t2
 	move	a0, sp
-	daddiu	a1, v0, __NR_N32_Linux
+	move	a1, v0
 	jal	syscall_trace_enter
 
 	bltz	v0, 2f			# seccomp failed? Skip syscall
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index d07b210..f543ff4 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -69,16 +69,17 @@
 	daddu	t1, t0, 32
 	bltz	t1, bad_stack
 
-1:	lw	a4, 16(t0)		# argument #5 from usp
-2:	lw	a5, 20(t0)		# argument #6 from usp
-3:	lw	a6, 24(t0)		# argument #7 from usp
-4:	lw	a7, 28(t0)		# argument #8 from usp (for indirect syscalls)
+load_a4: lw	a4, 16(t0)		# argument #5 from usp
+load_a5: lw	a5, 20(t0)		# argument #6 from usp
+load_a6: lw	a6, 24(t0)		# argument #7 from usp
+load_a7: lw	a7, 28(t0)		# argument #8 from usp
+loads_done:
 
 	.section __ex_table,"a"
-	PTR	1b, bad_stack
-	PTR	2b, bad_stack
-	PTR	3b, bad_stack
-	PTR	4b, bad_stack
+	PTR	load_a4, bad_stack_a4
+	PTR	load_a5, bad_stack_a5
+	PTR	load_a6, bad_stack_a6
+	PTR	load_a7, bad_stack_a7
 	.previous
 
 	li	t1, _TIF_WORK_SYSCALL_ENTRY
@@ -167,6 +168,22 @@
 	sd	t0, PT_R7(sp)
 	j	o32_syscall_exit
 
+bad_stack_a4:
+	li	a4, 0
+	b	load_a5
+
+bad_stack_a5:
+	li	a5, 0
+	b	load_a6
+
+bad_stack_a6:
+	li	a6, 0
+	b	load_a7
+
+bad_stack_a7:
+	li	a7, 0
+	b	loads_done
+
 not_o32_scall:
 	/*
 	 * This is not an o32 compatibility syscall, pass it on
@@ -383,7 +400,7 @@
 	PTR	sys_connect			/* 4170 */
 	PTR	sys_getpeername
 	PTR	sys_getsockname
-	PTR	sys_getsockopt
+	PTR	compat_sys_getsockopt
 	PTR	sys_listen
 	PTR	compat_sys_recv			/* 4175 */
 	PTR	compat_sys_recvfrom
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index be73c49..008b337 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -337,6 +337,11 @@
 			min_low_pfn = start;
 		if (end <= reserved_end)
 			continue;
+#ifdef CONFIG_BLK_DEV_INITRD
+		/* mapstart should be after initrd_end */
+		if (initrd_end && end <= (unsigned long)PFN_UP(__pa(initrd_end)))
+			continue;
+#endif
 		if (start >= mapstart)
 			continue;
 		mapstart = max(reserved_end, start);
@@ -366,14 +371,6 @@
 		max_low_pfn = PFN_DOWN(HIGHMEM_START);
 	}
 
-#ifdef CONFIG_BLK_DEV_INITRD
-	/*
-	 * mapstart should be after initrd_end
-	 */
-	if (initrd_end)
-		mapstart = max(mapstart, (unsigned long)PFN_UP(__pa(initrd_end)));
-#endif
-
 	/*
 	 * Initialize the boot-time allocator with low memory only.
 	 */
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index 19a7705..5d7f263 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -409,8 +409,6 @@
 
 int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, 3*sizeof(int)) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE32))
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 336708a..78cf8c2 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -284,7 +284,7 @@
 	if (action == 0)
 		scheduler_ipi();
 	else
-		smp_call_function_interrupt();
+		generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }
@@ -336,7 +336,7 @@
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+		generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }
diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
index 4251d39..c889377 100644
--- a/arch/mips/kernel/smp-cps.c
+++ b/arch/mips/kernel/smp-cps.c
@@ -133,7 +133,7 @@
 	/*
 	 * Patch the start of mips_cps_core_entry to provide:
 	 *
-	 * v0 = CM base address
+	 * v1 = CM base address
 	 * s0 = kseg0 CCA
 	 */
 	entry_code = (u32 *)&mips_cps_core_entry;
@@ -369,7 +369,7 @@
 
 static void wait_for_sibling_halt(void *ptr_cpu)
 {
-	unsigned cpu = (unsigned)ptr_cpu;
+	unsigned cpu = (unsigned long)ptr_cpu;
 	unsigned vpe_id = cpu_vpe_id(&cpu_data[cpu]);
 	unsigned halted;
 	unsigned long flags;
@@ -430,7 +430,7 @@
 		 */
 		err = smp_call_function_single(cpu_death_sibling,
 					       wait_for_sibling_halt,
-					       (void *)cpu, 1);
+					       (void *)(unsigned long)cpu, 1);
 		if (err)
 			panic("Failed to call remote sibling CPU\n");
 	}
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index faa46eb..a31896c 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -63,6 +63,13 @@
 cpumask_t cpu_core_map[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(cpu_core_map);
 
+/*
+ * A logcal cpu mask containing only one VPE per core to
+ * reduce the number of IPIs on large MT systems.
+ */
+cpumask_t cpu_foreign_map __read_mostly;
+EXPORT_SYMBOL(cpu_foreign_map);
+
 /* representing cpus for which sibling maps can be computed */
 static cpumask_t cpu_sibling_setup_map;
 
@@ -103,6 +110,29 @@
 	}
 }
 
+/*
+ * Calculate a new cpu_foreign_map mask whenever a
+ * new cpu appears or disappears.
+ */
+static inline void calculate_cpu_foreign_map(void)
+{
+	int i, k, core_present;
+	cpumask_t temp_foreign_map;
+
+	/* Re-calculate the mask */
+	for_each_online_cpu(i) {
+		core_present = 0;
+		for_each_cpu(k, &temp_foreign_map)
+			if (cpu_data[i].package == cpu_data[k].package &&
+			    cpu_data[i].core == cpu_data[k].core)
+				core_present = 1;
+		if (!core_present)
+			cpumask_set_cpu(i, &temp_foreign_map);
+	}
+
+	cpumask_copy(&cpu_foreign_map, &temp_foreign_map);
+}
+
 struct plat_smp_ops *mp_ops;
 EXPORT_SYMBOL(mp_ops);
 
@@ -146,6 +176,8 @@
 	set_cpu_sibling_map(cpu);
 	set_cpu_core_map(cpu);
 
+	calculate_cpu_foreign_map();
+
 	cpumask_set_cpu(cpu, &cpu_callin_map);
 
 	synchronise_count_slave(cpu);
@@ -160,22 +192,21 @@
 	cpu_startup_entry(CPUHP_ONLINE);
 }
 
-/*
- * Call into both interrupt handlers, as we share the IPI for them
- */
-void __irq_entry smp_call_function_interrupt(void)
-{
-	irq_enter();
-	generic_smp_call_function_interrupt();
-	irq_exit();
-}
-
 static void stop_this_cpu(void *dummy)
 {
 	/*
-	 * Remove this CPU:
+	 * Remove this CPU. Be a bit slow here and
+	 * set the bits for every online CPU so we don't miss
+	 * any IPI whilst taking this VPE down.
 	 */
+
+	cpumask_copy(&cpu_foreign_map, cpu_online_mask);
+
+	/* Make it visible to every other CPU */
+	smp_mb();
+
 	set_cpu_online(smp_processor_id(), false);
+	calculate_cpu_foreign_map();
 	local_irq_disable();
 	while (1);
 }
@@ -197,6 +228,7 @@
 	mp_ops->prepare_cpus(max_cpus);
 	set_cpu_sibling_map(0);
 	set_cpu_core_map(0);
+	calculate_cpu_foreign_map();
 #ifndef CONFIG_HOTPLUG_CPU
 	init_cpu_present(cpu_possible_mask);
 #endif
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 2a7b38e..8ea28e6 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -192,6 +192,7 @@
 void show_stack(struct task_struct *task, unsigned long *sp)
 {
 	struct pt_regs regs;
+	mm_segment_t old_fs = get_fs();
 	if (sp) {
 		regs.regs[29] = (unsigned long)sp;
 		regs.regs[31] = 0;
@@ -210,7 +211,13 @@
 			prepare_frametrace(&regs);
 		}
 	}
+	/*
+	 * show_stack() deals exclusively with kernel mode, so be sure to access
+	 * the stack in the kernel (not user) address space.
+	 */
+	set_fs(KERNEL_DS);
 	show_stacktrace(task, &regs);
+	set_fs(old_fs);
 }
 
 static void show_code(unsigned int __user *pc)
@@ -1519,6 +1526,7 @@
 	const int field = 2 * sizeof(unsigned long);
 	int multi_match = regs->cp0_status & ST0_TS;
 	enum ctx_state prev_state;
+	mm_segment_t old_fs = get_fs();
 
 	prev_state = exception_enter();
 	show_regs(regs);
@@ -1540,8 +1548,13 @@
 		dump_tlb_all();
 	}
 
+	if (!user_mode(regs))
+		set_fs(KERNEL_DS);
+
 	show_code((unsigned int __user *) regs->cp0_epc);
 
+	set_fs(old_fs);
+
 	/*
 	 * Some chips may have other causes of machine check (e.g. SB1
 	 * graduation timer)
@@ -2130,10 +2143,10 @@
 	BUG_ON(current->mm);
 	enter_lazy_tlb(&init_mm, current);
 
-		/* Boot CPU's cache setup in setup_arch(). */
-		if (!is_boot_cpu)
-			cpu_cache_init();
-		tlb_init();
+	/* Boot CPU's cache setup in setup_arch(). */
+	if (!is_boot_cpu)
+		cpu_cache_init();
+	tlb_init();
 	TLBMISS_HANDLER_SETUP();
 }
 
diff --git a/arch/mips/kernel/unaligned.c b/arch/mips/kernel/unaligned.c
index af84bef..eb3efd1 100644
--- a/arch/mips/kernel/unaligned.c
+++ b/arch/mips/kernel/unaligned.c
@@ -438,7 +438,7 @@
 		: "memory");                                \
 } while(0)
 
-#define     StoreDW(addr, value, res) \
+#define     _StoreDW(addr, value, res) \
 do {                                                        \
 		__asm__ __volatile__ (                      \
 			".set\tpush\n\t"		    \
diff --git a/arch/mips/lantiq/irq.c b/arch/mips/lantiq/irq.c
index 6ab1057..2c218c3 100644
--- a/arch/mips/lantiq/irq.c
+++ b/arch/mips/lantiq/irq.c
@@ -293,7 +293,7 @@
 
 static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 	return IRQ_HANDLED;
 }
 
@@ -466,6 +466,7 @@
 {
 	return ltq_perfcount_irq;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
diff --git a/arch/mips/loongson64/common/bonito-irq.c b/arch/mips/loongson64/common/bonito-irq.c
index cc0e4fd..4e116d2 100644
--- a/arch/mips/loongson64/common/bonito-irq.c
+++ b/arch/mips/loongson64/common/bonito-irq.c
@@ -3,7 +3,7 @@
  * Author: Jun Sun, jsun@mvista.com or jsun@junsun.net
  * Copyright (C) 2000, 2001 Ralf Baechle (ralf@gnu.org)
  *
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  *  This program is free software; you can redistribute	 it and/or modify it
diff --git a/arch/mips/loongson64/common/cmdline.c b/arch/mips/loongson64/common/cmdline.c
index 72fed00..01fbed1 100644
--- a/arch/mips/loongson64/common/cmdline.c
+++ b/arch/mips/loongson64/common/cmdline.c
@@ -6,7 +6,7 @@
  * Copyright 2003 ICT CAS
  * Author: Michael Guo <guoyi@ict.ac.cn>
  *
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  * Copyright (C) 2009 Lemote Inc.
diff --git a/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c b/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
index 12c75db..8750370 100644
--- a/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
+++ b/arch/mips/loongson64/common/cs5536/cs5536_mfgpt.c
@@ -1,7 +1,7 @@
 /*
  * CS5536 General timer functions
  *
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Yanhua, yanh@lemote.com
  *
  * Copyright (C) 2009 Lemote Inc.
diff --git a/arch/mips/loongson64/common/env.c b/arch/mips/loongson64/common/env.c
index 22f04ca..f6c44dd 100644
--- a/arch/mips/loongson64/common/env.c
+++ b/arch/mips/loongson64/common/env.c
@@ -6,7 +6,7 @@
  * Copyright 2003 ICT CAS
  * Author: Michael Guo <guoyi@ict.ac.cn>
  *
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  * Copyright (C) 2009 Lemote Inc.
diff --git a/arch/mips/loongson64/common/irq.c b/arch/mips/loongson64/common/irq.c
index 687003b..d36d969 100644
--- a/arch/mips/loongson64/common/irq.c
+++ b/arch/mips/loongson64/common/irq.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  *  This program is free software; you can redistribute	 it and/or modify it
diff --git a/arch/mips/loongson64/common/setup.c b/arch/mips/loongson64/common/setup.c
index d477dd6..2dc5122 100644
--- a/arch/mips/loongson64/common/setup.c
+++ b/arch/mips/loongson64/common/setup.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  *  This program is free software; you can redistribute	 it and/or modify it
diff --git a/arch/mips/loongson64/fuloong-2e/irq.c b/arch/mips/loongson64/fuloong-2e/irq.c
index ef5ec8f..892963f8 100644
--- a/arch/mips/loongson64/fuloong-2e/irq.c
+++ b/arch/mips/loongson64/fuloong-2e/irq.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2007 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2007 Lemote Inc. & Institute of Computing Technology
  * Author: Fuxin Zhang, zhangfx@lemote.com
  *
  *  This program is free software; you can redistribute	 it and/or modify it
diff --git a/arch/mips/loongson64/lemote-2f/clock.c b/arch/mips/loongson64/lemote-2f/clock.c
index 462e34d..a78fb65 100644
--- a/arch/mips/loongson64/lemote-2f/clock.c
+++ b/arch/mips/loongson64/lemote-2f/clock.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2006 - 2008 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2006 - 2008 Lemote Inc. & Institute of Computing Technology
  * Author: Yanhua, yanh@lemote.com
  *
  * This file is subject to the terms and conditions of the GNU General Public
@@ -15,7 +15,7 @@
 #include <linux/spinlock.h>
 
 #include <asm/clock.h>
-#include <asm/mach-loongson/loongson.h>
+#include <asm/mach-loongson64/loongson.h>
 
 static LIST_HEAD(clock_list);
 static DEFINE_SPINLOCK(clock_lock);
diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c
index 12d14ed..6f9e010 100644
--- a/arch/mips/loongson64/loongson-3/numa.c
+++ b/arch/mips/loongson64/loongson-3/numa.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2010 Loongson Inc. & Lemote Inc. &
- *                    Insititute of Computing Technology
+ *                    Institute of Computing Technology
  * Author:  Xiang Gao, gaoxiang@ict.ac.cn
  *          Huacai Chen, chenhc@lemote.com
  *          Xiaofu Meng, Shuangshuang Zhang
diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c
index 509877c..1a4738a 100644
--- a/arch/mips/loongson64/loongson-3/smp.c
+++ b/arch/mips/loongson64/loongson-3/smp.c
@@ -266,8 +266,11 @@
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
-	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+	if (action & SMP_CALL_FUNCTION) {
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
+	}
 
 	if (action & SMP_ASK_C0COUNT) {
 		BUG_ON(cpu != 0);
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 22b9b2c..712f17a 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -451,7 +451,7 @@
 			/* Fall through */
 		case jr_op:
 			/* For R6, JR already emulated in jalr_op */
-			if (NO_R6EMU && insn.r_format.opcode == jr_op)
+			if (NO_R6EMU && insn.r_format.func == jr_op)
 				break;
 			*contpc = regs->regs[insn.r_format.rs];
 			return 1;
@@ -551,7 +551,7 @@
 				dec_insn.next_pc_inc;
 		return 1;
 	case blezl_op:
-		if (NO_R6EMU)
+		if (!insn.i_format.rt && NO_R6EMU)
 			break;
 	case blez_op:
 
@@ -588,7 +588,7 @@
 				dec_insn.next_pc_inc;
 		return 1;
 	case bgtzl_op:
-		if (NO_R6EMU)
+		if (!insn.i_format.rt && NO_R6EMU)
 			break;
 	case bgtz_op:
 		/*
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 7f660dc..fbea443 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -37,6 +37,7 @@
 #include <asm/cacheflush.h> /* for run_uncached() */
 #include <asm/traps.h>
 #include <asm/dma-coherence.h>
+#include <asm/mips-cm.h>
 
 /*
  * Special Variant of smp_call_function for use by cache functions:
@@ -51,9 +52,16 @@
 {
 	preempt_disable();
 
-#ifndef CONFIG_MIPS_MT_SMP
-	smp_call_function(func, info, 1);
-#endif
+	/*
+	 * The Coherent Manager propagates address-based cache ops to other
+	 * cores but not index-based ops. However, r4k_on_each_cpu is used
+	 * in both cases so there is no easy way to tell what kind of op is
+	 * executed to the other cores. The best we can probably do is
+	 * to restrict that call when a CM is not present because both
+	 * CM-based SMP protocols (CMP & CPS) restrict index-based cache ops.
+	 */
+	if (!mips_cm_present())
+		smp_call_function_many(&cpu_foreign_map, func, info, 1);
 	func(info);
 	preempt_enable();
 }
@@ -937,7 +945,9 @@
 }
 
 static char *way_string[] = { NULL, "direct mapped", "2-way",
-	"3-way", "4-way", "5-way", "6-way", "7-way", "8-way"
+	"3-way", "4-way", "5-way", "6-way", "7-way", "8-way",
+	"9-way", "10-way", "11-way", "12-way",
+	"13-way", "14-way", "15-way", "16-way",
 };
 
 static void probe_pcache(void)
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index 77d96db..aab218c 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -160,18 +160,18 @@
 		protection_map[1]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
 		protection_map[2]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
 		protection_map[3]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
-		protection_map[4]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_READ);
+		protection_map[4]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 		protection_map[5]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
-		protection_map[6]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_READ);
+		protection_map[6]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 		protection_map[7]  = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 
 		protection_map[8]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
 		protection_map[9]  = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC);
 		protection_map[10] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE | _PAGE_NO_READ);
 		protection_map[11] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE);
-		protection_map[12] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_NO_READ);
+		protection_map[12] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
 		protection_map[13] = __pgprot(_page_cachable_default | _PAGE_PRESENT);
-		protection_map[14] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE  | _PAGE_NO_READ);
+		protection_map[14] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE);
 		protection_map[15] = __pgprot(_page_cachable_default | _PAGE_PRESENT | _PAGE_WRITE);
 
 	} else {
diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c
index 36c0f26..852a41c 100644
--- a/arch/mips/mm/fault.c
+++ b/arch/mips/mm/fault.c
@@ -133,7 +133,8 @@
 #endif
 				goto bad_area;
 			}
-			if (!(vma->vm_flags & VM_READ)) {
+			if (!(vma->vm_flags & VM_READ) &&
+			    exception_epc(regs) != address) {
 #if 0
 				pr_notice("Cpu%d[%s:%d:%0*lx:%ld:%0*lx] RI violation\n",
 					  raw_smp_processor_id(),
diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c
index d1392f8..fa8f591 100644
--- a/arch/mips/mti-malta/malta-int.c
+++ b/arch/mips/mti-malta/malta-int.c
@@ -222,7 +222,7 @@
 
 static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }
diff --git a/arch/mips/mti-malta/malta-time.c b/arch/mips/mti-malta/malta-time.c
index 185e682..b7bf721 100644
--- a/arch/mips/mti-malta/malta-time.c
+++ b/arch/mips/mti-malta/malta-time.c
@@ -119,18 +119,24 @@
 
 int get_c0_fdc_int(void)
 {
-	int mips_cpu_fdc_irq;
+	/*
+	 * Some cores claim the FDC is routable through the GIC, but it doesn't
+	 * actually seem to be connected for those Malta bitstreams.
+	 */
+	switch (current_cpu_type()) {
+	case CPU_INTERAPTIV:
+	case CPU_PROAPTIV:
+		return -1;
+	};
 
 	if (cpu_has_veic)
-		mips_cpu_fdc_irq = -1;
+		return -1;
 	else if (gic_present)
-		mips_cpu_fdc_irq = gic_get_c0_fdc_int();
+		return gic_get_c0_fdc_int();
 	else if (cp0_fdc_irq >= 0)
-		mips_cpu_fdc_irq = MIPS_CPU_IRQ_BASE + cp0_fdc_irq;
+		return MIPS_CPU_IRQ_BASE + cp0_fdc_irq;
 	else
-		mips_cpu_fdc_irq = -1;
-
-	return mips_cpu_fdc_irq;
+		return -1;
 }
 
 int get_c0_perfcount_int(void)
@@ -148,6 +154,7 @@
 
 	return mips_cpu_perf_irq;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
@@ -165,14 +172,17 @@
 
 static void __init init_rtc(void)
 {
-	/* stop the clock whilst setting it up */
-	CMOS_WRITE(RTC_SET | RTC_24H, RTC_CONTROL);
+	unsigned char freq, ctrl;
 
-	/* 32KHz time base */
-	CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT);
+	/* Set 32KHz time base if not already set */
+	freq = CMOS_READ(RTC_FREQ_SELECT);
+	if ((freq & RTC_DIV_CTL) != RTC_REF_CLCK_32KHZ)
+		CMOS_WRITE(RTC_REF_CLCK_32KHZ, RTC_FREQ_SELECT);
 
-	/* start the clock */
-	CMOS_WRITE(RTC_24H, RTC_CONTROL);
+	/* Ensure SET bit is clear so RTC can run */
+	ctrl = CMOS_READ(RTC_CONTROL);
+	if (ctrl & RTC_SET)
+		CMOS_WRITE(ctrl & ~RTC_SET, RTC_CONTROL);
 }
 
 void __init plat_time_init(void)
diff --git a/arch/mips/mti-sead3/sead3-time.c b/arch/mips/mti-sead3/sead3-time.c
index e1d6989..a120b7a 100644
--- a/arch/mips/mti-sead3/sead3-time.c
+++ b/arch/mips/mti-sead3/sead3-time.c
@@ -77,6 +77,7 @@
 		return MIPS_CPU_IRQ_BASE + cp0_perfcount_irq;
 	return -1;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c
index dc3e327..f5fff22 100644
--- a/arch/mips/netlogic/common/smp.c
+++ b/arch/mips/netlogic/common/smp.c
@@ -86,7 +86,7 @@
 {
 	clear_c0_eimr(irq);
 	ack_c0_eirr(irq);
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 	set_c0_eimr(irq);
 }
 
diff --git a/arch/mips/paravirt/paravirt-smp.c b/arch/mips/paravirt/paravirt-smp.c
index 42181c7..f8d3e08 100644
--- a/arch/mips/paravirt/paravirt-smp.c
+++ b/arch/mips/paravirt/paravirt-smp.c
@@ -114,7 +114,7 @@
 
 static irqreturn_t paravirt_function_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 	return IRQ_HANDLED;
 }
 
diff --git a/arch/mips/pistachio/init.c b/arch/mips/pistachio/init.c
index d2dc836..8bd8ebb 100644
--- a/arch/mips/pistachio/init.c
+++ b/arch/mips/pistachio/init.c
@@ -63,13 +63,19 @@
 	plat_setup_iocoherency();
 }
 
-#define DEFAULT_CPC_BASE_ADDR 0x1bde0000
+#define DEFAULT_CPC_BASE_ADDR	0x1bde0000
+#define DEFAULT_CDMM_BASE_ADDR	0x1bdd0000
 
 phys_addr_t mips_cpc_default_phys_base(void)
 {
 	return DEFAULT_CPC_BASE_ADDR;
 }
 
+phys_addr_t mips_cdmm_phys_base(void)
+{
+	return DEFAULT_CDMM_BASE_ADDR;
+}
+
 static void __init mips_nmi_setup(void)
 {
 	void *base;
diff --git a/arch/mips/pistachio/time.c b/arch/mips/pistachio/time.c
index 67889fc..8a37734 100644
--- a/arch/mips/pistachio/time.c
+++ b/arch/mips/pistachio/time.c
@@ -26,6 +26,12 @@
 {
 	return gic_get_c0_perfcount_int();
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
+
+int get_c0_fdc_int(void)
+{
+	return gic_get_c0_fdc_int();
+}
 
 void __init plat_time_init(void)
 {
diff --git a/arch/mips/pmcs-msp71xx/msp_smp.c b/arch/mips/pmcs-msp71xx/msp_smp.c
index 1017058..ffa0f71 100644
--- a/arch/mips/pmcs-msp71xx/msp_smp.c
+++ b/arch/mips/pmcs-msp71xx/msp_smp.c
@@ -44,7 +44,7 @@
 
 static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }
diff --git a/arch/mips/ralink/irq.c b/arch/mips/ralink/irq.c
index 53707aa..8c624a8 100644
--- a/arch/mips/ralink/irq.c
+++ b/arch/mips/ralink/irq.c
@@ -89,6 +89,7 @@
 {
 	return rt_perfcount_irq;
 }
+EXPORT_SYMBOL_GPL(get_c0_perfcount_int);
 
 unsigned int get_c0_compare_int(void)
 {
diff --git a/arch/mips/sgi-ip27/ip27-irq.c b/arch/mips/sgi-ip27/ip27-irq.c
index 3fbaef9..16ec4e1 100644
--- a/arch/mips/sgi-ip27/ip27-irq.c
+++ b/arch/mips/sgi-ip27/ip27-irq.c
@@ -107,10 +107,14 @@
 		scheduler_ipi();
 	} else if (pend0 & (1UL << CPU_CALL_A_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_CALL_A_IRQ);
-		smp_call_function_interrupt();
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
 	} else if (pend0 & (1UL << CPU_CALL_B_IRQ)) {
 		LOCAL_HUB_CLR_INTR(CPU_CALL_B_IRQ);
-		smp_call_function_interrupt();
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
 	} else
 #endif
 	{
diff --git a/arch/mips/sibyte/Kconfig b/arch/mips/sibyte/Kconfig
index a8bb972..cb9a095 100644
--- a/arch/mips/sibyte/Kconfig
+++ b/arch/mips/sibyte/Kconfig
@@ -81,11 +81,6 @@
 	prompt "SiByte SOC Stepping"
 	depends on SIBYTE_SB1xxx_SOC
 
-config CPU_SB1_PASS_1
-	bool "1250 Pass1"
-	depends on SIBYTE_SB1250
-	select CPU_HAS_PREFETCH
-
 config CPU_SB1_PASS_2_1250
 	bool "1250 An"
 	depends on SIBYTE_SB1250
diff --git a/arch/mips/sibyte/bcm1480/smp.c b/arch/mips/sibyte/bcm1480/smp.c
index af7d44e..4c71aea 100644
--- a/arch/mips/sibyte/bcm1480/smp.c
+++ b/arch/mips/sibyte/bcm1480/smp.c
@@ -29,8 +29,6 @@
 #include <asm/sibyte/bcm1480_regs.h>
 #include <asm/sibyte/bcm1480_int.h>
 
-extern void smp_call_function_interrupt(void);
-
 /*
  * These are routines for dealing with the bcm1480 smp capabilities
  * independent of board/firmware
@@ -184,6 +182,9 @@
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
-	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+	if (action & SMP_CALL_FUNCTION) {
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
+	}
 }
diff --git a/arch/mips/sibyte/common/bus_watcher.c b/arch/mips/sibyte/common/bus_watcher.c
index 5581844..41a1d22 100644
--- a/arch/mips/sibyte/common/bus_watcher.c
+++ b/arch/mips/sibyte/common/bus_watcher.c
@@ -81,10 +81,7 @@
 {
 	u32 status, l2_err, memio_err;
 
-#ifdef CONFIG_SB1_PASS_1_WORKAROUNDS
-	/* Destructive read, clears register and interrupt */
-	status = csr_in32(IOADDR(A_SCD_BUS_ERR_STATUS));
-#elif defined(CONFIG_SIBYTE_BCM112X) || defined(CONFIG_SIBYTE_SB1250)
+#if defined(CONFIG_SIBYTE_BCM112X) || defined(CONFIG_SIBYTE_SB1250)
 	/* Use non-destructive register */
 	status = csr_in32(IOADDR(A_SCD_BUS_ERR_STATUS_DEBUG));
 #elif defined(CONFIG_SIBYTE_BCM1x55) || defined(CONFIG_SIBYTE_BCM1x80)
diff --git a/arch/mips/sibyte/sb1250/setup.c b/arch/mips/sibyte/sb1250/setup.c
index 3c02b2a..9d3c24e 100644
--- a/arch/mips/sibyte/sb1250/setup.c
+++ b/arch/mips/sibyte/sb1250/setup.c
@@ -202,12 +202,10 @@
 
 	switch (war_pass) {
 	case K_SYS_REVISION_BCM1250_PASS1:
-#ifndef CONFIG_SB1_PASS_1_WORKAROUNDS
 		printk("@@@@ This is a BCM1250 A0-A2 (Pass 1) board, "
 			    "and the kernel doesn't have the proper "
 			    "workarounds compiled in. @@@@\n");
 		bad_config = 1;
-#endif
 		break;
 	case K_SYS_REVISION_BCM1250_PASS2:
 		/* Pass 2 - easiest as default for now - so many numbers */
diff --git a/arch/mips/sibyte/sb1250/smp.c b/arch/mips/sibyte/sb1250/smp.c
index c0c4b3f..1cf66f5 100644
--- a/arch/mips/sibyte/sb1250/smp.c
+++ b/arch/mips/sibyte/sb1250/smp.c
@@ -172,6 +172,9 @@
 	if (action & SMP_RESCHEDULE_YOURSELF)
 		scheduler_ipi();
 
-	if (action & SMP_CALL_FUNCTION)
-		smp_call_function_interrupt();
+	if (action & SMP_CALL_FUNCTION) {
+		irq_enter();
+		generic_smp_call_function_interrupt();
+		irq_exit();
+	}
 }
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index de30b0c..6edb9ee 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -5,6 +5,7 @@
 generic-y += exec.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += preempt.h
 generic-y += sections.h
 generic-y += trace_clock.h
diff --git a/arch/mn10300/include/asm/mm-arch-hooks.h b/arch/mn10300/include/asm/mm-arch-hooks.h
deleted file mode 100644
index e2029a6..0000000
--- a/arch/mn10300/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_MN10300_MM_ARCH_HOOKS_H
-#define _ASM_MN10300_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_MN10300_MM_ARCH_HOOKS_H */
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index 434639d..914864e 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -30,6 +30,7 @@
 generic-y += kvm_para.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += module.h
 generic-y += msgbuf.h
diff --git a/arch/nios2/include/asm/mm-arch-hooks.h b/arch/nios2/include/asm/mm-arch-hooks.h
deleted file mode 100644
index d7290dc..0000000
--- a/arch/nios2/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_NIOS2_MM_ARCH_HOOKS_H
-#define _ASM_NIOS2_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_NIOS2_MM_ARCH_HOOKS_H */
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index e5a693b..443f44d 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -17,6 +17,7 @@
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IOMAP
 	select GENERIC_CPU_DEVICES
+	select HAVE_UID16
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_STRNCPY_FROM_USER
@@ -31,9 +32,6 @@
 config HAVE_DMA_ATTRS
 	def_bool y
 
-config UID16
-	def_bool y
-
 config RWSEM_GENERIC_SPINLOCK
 	def_bool y
 
diff --git a/arch/openrisc/include/asm/Kbuild b/arch/openrisc/include/asm/Kbuild
index 2a2e39b..2832f03 100644
--- a/arch/openrisc/include/asm/Kbuild
+++ b/arch/openrisc/include/asm/Kbuild
@@ -36,6 +36,7 @@
 generic-y += kvm_para.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += module.h
 generic-y += msgbuf.h
diff --git a/arch/openrisc/include/asm/mm-arch-hooks.h b/arch/openrisc/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 6d33cb5..0000000
--- a/arch/openrisc/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_OPENRISC_MM_ARCH_HOOKS_H
-#define _ASM_OPENRISC_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_OPENRISC_MM_ARCH_HOOKS_H */
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index 12b341d..f9b3a81 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -15,6 +15,7 @@
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mutex.h
 generic-y += param.h
 generic-y += percpu.h
diff --git a/arch/parisc/include/asm/mm-arch-hooks.h b/arch/parisc/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 654ec63..0000000
--- a/arch/parisc/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_PARISC_MM_ARCH_HOOKS_H
-#define _ASM_PARISC_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_PARISC_MM_ARCH_HOOKS_H */
diff --git a/arch/parisc/include/asm/pgalloc.h b/arch/parisc/include/asm/pgalloc.h
index 3a08eae..3edbb9f 100644
--- a/arch/parisc/include/asm/pgalloc.h
+++ b/arch/parisc/include/asm/pgalloc.h
@@ -72,7 +72,7 @@
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
-	if(pmd_flag(*pmd) & PxD_FLAG_ATTACHED)
+	if (pmd_flag(*pmd) & PxD_FLAG_ATTACHED) {
 		/*
 		 * This is the permanent pmd attached to the pgd;
 		 * cannot free it.
@@ -81,6 +81,7 @@
 		 */
 		mm_inc_nr_pmds(mm);
 		return;
+	}
 	free_pages((unsigned long)pmd, PMD_ORDER);
 }
 
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 0a18375..f93c4a4 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -16,7 +16,7 @@
 #include <asm/processor.h>
 #include <asm/cache.h>
 
-extern spinlock_t pa_dbit_lock;
+extern spinlock_t pa_tlb_lock;
 
 /*
  * kern_addr_valid(ADDR) tests if ADDR is pointing to valid kernel
@@ -33,6 +33,19 @@
  */
 #define kern_addr_valid(addr)	(1)
 
+/* Purge data and instruction TLB entries.  Must be called holding
+ * the pa_tlb_lock.  The TLB purge instructions are slow on SMP
+ * machines since the purge must be broadcast to all CPUs.
+ */
+
+static inline void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
+{
+	mtsp(mm->context, 1);
+	pdtlb(addr);
+	if (unlikely(split_tlb))
+		pitlb(addr);
+}
+
 /* Certain architectures need to do special things when PTEs
  * within a page table are directly modified.  Thus, the following
  * hook is made available.
@@ -42,15 +55,20 @@
                 *(pteptr) = (pteval);                           \
         } while(0)
 
-extern void purge_tlb_entries(struct mm_struct *, unsigned long);
+#define pte_inserted(x)						\
+	((pte_val(x) & (_PAGE_PRESENT|_PAGE_ACCESSED))		\
+	 == (_PAGE_PRESENT|_PAGE_ACCESSED))
 
-#define set_pte_at(mm, addr, ptep, pteval)                      \
-	do {                                                    \
+#define set_pte_at(mm, addr, ptep, pteval)			\
+	do {							\
+		pte_t old_pte;					\
 		unsigned long flags;				\
-		spin_lock_irqsave(&pa_dbit_lock, flags);	\
-		set_pte(ptep, pteval);                          \
-		purge_tlb_entries(mm, addr);                    \
-		spin_unlock_irqrestore(&pa_dbit_lock, flags);	\
+		spin_lock_irqsave(&pa_tlb_lock, flags);		\
+		old_pte = *ptep;				\
+		set_pte(ptep, pteval);				\
+		if (pte_inserted(old_pte))			\
+			purge_tlb_entries(mm, addr);		\
+		spin_unlock_irqrestore(&pa_tlb_lock, flags);	\
 	} while (0)
 
 #endif /* !__ASSEMBLY__ */
@@ -268,7 +286,7 @@
 
 #define pte_none(x)     (pte_val(x) == 0)
 #define pte_present(x)	(pte_val(x) & _PAGE_PRESENT)
-#define pte_clear(mm,addr,xp)	do { pte_val(*(xp)) = 0; } while (0)
+#define pte_clear(mm, addr, xp)  set_pte_at(mm, addr, xp, __pte(0))
 
 #define pmd_flag(x)	(pmd_val(x) & PxD_FLAG_MASK)
 #define pmd_address(x)	((unsigned long)(pmd_val(x) &~ PxD_FLAG_MASK) << PxD_VALUE_SHIFT)
@@ -435,15 +453,15 @@
 	if (!pte_young(*ptep))
 		return 0;
 
-	spin_lock_irqsave(&pa_dbit_lock, flags);
+	spin_lock_irqsave(&pa_tlb_lock, flags);
 	pte = *ptep;
 	if (!pte_young(pte)) {
-		spin_unlock_irqrestore(&pa_dbit_lock, flags);
+		spin_unlock_irqrestore(&pa_tlb_lock, flags);
 		return 0;
 	}
 	set_pte(ptep, pte_mkold(pte));
 	purge_tlb_entries(vma->vm_mm, addr);
-	spin_unlock_irqrestore(&pa_dbit_lock, flags);
+	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 	return 1;
 }
 
@@ -453,11 +471,12 @@
 	pte_t old_pte;
 	unsigned long flags;
 
-	spin_lock_irqsave(&pa_dbit_lock, flags);
+	spin_lock_irqsave(&pa_tlb_lock, flags);
 	old_pte = *ptep;
-	pte_clear(mm,addr,ptep);
-	purge_tlb_entries(mm, addr);
-	spin_unlock_irqrestore(&pa_dbit_lock, flags);
+	set_pte(ptep, __pte(0));
+	if (pte_inserted(old_pte))
+		purge_tlb_entries(mm, addr);
+	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 
 	return old_pte;
 }
@@ -465,10 +484,10 @@
 static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	unsigned long flags;
-	spin_lock_irqsave(&pa_dbit_lock, flags);
+	spin_lock_irqsave(&pa_tlb_lock, flags);
 	set_pte(ptep, pte_wrprotect(*ptep));
 	purge_tlb_entries(mm, addr);
-	spin_unlock_irqrestore(&pa_dbit_lock, flags);
+	spin_unlock_irqrestore(&pa_tlb_lock, flags);
 }
 
 #define pte_same(A,B)	(pte_val(A) == pte_val(B))
diff --git a/arch/parisc/include/asm/tlbflush.h b/arch/parisc/include/asm/tlbflush.h
index 9d086a5..e84b964 100644
--- a/arch/parisc/include/asm/tlbflush.h
+++ b/arch/parisc/include/asm/tlbflush.h
@@ -13,6 +13,9 @@
  * active at any one time on the Merced bus.  This tlb purge
  * synchronisation is fairly lightweight and harmless so we activate
  * it on all systems not just the N class.
+
+ * It is also used to ensure PTE updates are atomic and consistent
+ * with the TLB.
  */
 extern spinlock_t pa_tlb_lock;
 
@@ -24,20 +27,24 @@
 
 #define smp_flush_tlb_all()	flush_tlb_all()
 
+int __flush_tlb_range(unsigned long sid,
+	unsigned long start, unsigned long end);
+
+#define flush_tlb_range(vma, start, end) \
+	__flush_tlb_range((vma)->vm_mm->context, start, end)
+
+#define flush_tlb_kernel_range(start, end) \
+	__flush_tlb_range(0, start, end)
+
 /*
  * flush_tlb_mm()
  *
- * XXX This code is NOT valid for HP-UX compatibility processes,
- * (although it will probably work 99% of the time). HP-UX
- * processes are free to play with the space id's and save them
- * over long periods of time, etc. so we have to preserve the
- * space and just flush the entire tlb. We need to check the
- * personality in order to do that, but the personality is not
- * currently being set correctly.
- *
- * Of course, Linux processes could do the same thing, but
- * we don't support that (and the compilers, dynamic linker,
- * etc. do not do that).
+ * The code to switch to a new context is NOT valid for processes
+ * which play with the space id's.  Thus, we have to preserve the
+ * space and just flush the entire tlb.  However, the compilers,
+ * dynamic linker, etc, do not manipulate space id's, so there
+ * could be a significant performance benefit in switching contexts
+ * and not flushing the whole tlb.
  */
 
 static inline void flush_tlb_mm(struct mm_struct *mm)
@@ -45,10 +52,18 @@
 	BUG_ON(mm == &init_mm); /* Should never happen */
 
 #if 1 || defined(CONFIG_SMP)
+	/* Except for very small threads, flushing the whole TLB is
+	 * faster than using __flush_tlb_range.  The pdtlb and pitlb
+	 * instructions are very slow because of the TLB broadcast.
+	 * It might be faster to do local range flushes on all CPUs
+	 * on PA 2.0 systems.
+	 */
 	flush_tlb_all();
 #else
 	/* FIXME: currently broken, causing space id and protection ids
-	 *  to go out of sync, resulting in faults on userspace accesses.
+	 * to go out of sync, resulting in faults on userspace accesses.
+	 * This approach needs further investigation since running many
+	 * small applications (e.g., GCC testsuite) is faster on HP-UX.
 	 */
 	if (mm) {
 		if (mm->context != 0)
@@ -65,22 +80,12 @@
 {
 	unsigned long flags, sid;
 
-	/* For one page, it's not worth testing the split_tlb variable */
-
-	mb();
 	sid = vma->vm_mm->context;
 	purge_tlb_start(flags);
 	mtsp(sid, 1);
 	pdtlb(addr);
-	pitlb(addr);
+	if (unlikely(split_tlb))
+		pitlb(addr);
 	purge_tlb_end(flags);
 }
-
-void __flush_tlb_range(unsigned long sid,
-	unsigned long start, unsigned long end);
-
-#define flush_tlb_range(vma,start,end) __flush_tlb_range((vma)->vm_mm->context,start,end)
-
-#define flush_tlb_kernel_range(start, end) __flush_tlb_range(0,start,end)
-
 #endif
diff --git a/arch/parisc/kernel/cache.c b/arch/parisc/kernel/cache.c
index f6448c7..cda6dbb 100644
--- a/arch/parisc/kernel/cache.c
+++ b/arch/parisc/kernel/cache.c
@@ -342,12 +342,15 @@
 EXPORT_SYMBOL(flush_kernel_icache_range_asm);
 
 #define FLUSH_THRESHOLD 0x80000 /* 0.5MB */
-int parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD;
+static unsigned long parisc_cache_flush_threshold __read_mostly = FLUSH_THRESHOLD;
+
+#define FLUSH_TLB_THRESHOLD (2*1024*1024) /* 2MB initial TLB threshold */
+static unsigned long parisc_tlb_flush_threshold __read_mostly = FLUSH_TLB_THRESHOLD;
 
 void __init parisc_setup_cache_timing(void)
 {
 	unsigned long rangetime, alltime;
-	unsigned long size;
+	unsigned long size, start;
 
 	alltime = mfctl(16);
 	flush_data_cache();
@@ -364,14 +367,43 @@
 	/* Racy, but if we see an intermediate value, it's ok too... */
 	parisc_cache_flush_threshold = size * alltime / rangetime;
 
-	parisc_cache_flush_threshold = (parisc_cache_flush_threshold + L1_CACHE_BYTES - 1) &~ (L1_CACHE_BYTES - 1); 
+	parisc_cache_flush_threshold = L1_CACHE_ALIGN(parisc_cache_flush_threshold);
 	if (!parisc_cache_flush_threshold)
 		parisc_cache_flush_threshold = FLUSH_THRESHOLD;
 
 	if (parisc_cache_flush_threshold > cache_info.dc_size)
 		parisc_cache_flush_threshold = cache_info.dc_size;
 
-	printk(KERN_INFO "Setting cache flush threshold to %x (%d CPUs online)\n", parisc_cache_flush_threshold, num_online_cpus());
+	printk(KERN_INFO "Setting cache flush threshold to %lu kB\n",
+		parisc_cache_flush_threshold/1024);
+
+	/* calculate TLB flush threshold */
+
+	alltime = mfctl(16);
+	flush_tlb_all();
+	alltime = mfctl(16) - alltime;
+
+	size = PAGE_SIZE;
+	start = (unsigned long) _text;
+	rangetime = mfctl(16);
+	while (start < (unsigned long) _end) {
+		flush_tlb_kernel_range(start, start + PAGE_SIZE);
+		start += PAGE_SIZE;
+		size += PAGE_SIZE;
+	}
+	rangetime = mfctl(16) - rangetime;
+
+	printk(KERN_DEBUG "Whole TLB flush %lu cycles, flushing %lu bytes %lu cycles\n",
+		alltime, size, rangetime);
+
+	parisc_tlb_flush_threshold = size * alltime / rangetime;
+	parisc_tlb_flush_threshold *= num_online_cpus();
+	parisc_tlb_flush_threshold = PAGE_ALIGN(parisc_tlb_flush_threshold);
+	if (!parisc_tlb_flush_threshold)
+		parisc_tlb_flush_threshold = FLUSH_TLB_THRESHOLD;
+
+	printk(KERN_INFO "Setting TLB flush threshold to %lu kB\n",
+		parisc_tlb_flush_threshold/1024);
 }
 
 extern void purge_kernel_dcache_page_asm(unsigned long);
@@ -403,48 +435,45 @@
 }
 EXPORT_SYMBOL(copy_user_page);
 
-void purge_tlb_entries(struct mm_struct *mm, unsigned long addr)
+/* __flush_tlb_range()
+ *
+ * returns 1 if all TLBs were flushed.
+ */
+int __flush_tlb_range(unsigned long sid, unsigned long start,
+		      unsigned long end)
 {
-	unsigned long flags;
+	unsigned long flags, size;
 
-	/* Note: purge_tlb_entries can be called at startup with
-	   no context.  */
-
-	purge_tlb_start(flags);
-	mtsp(mm->context, 1);
-	pdtlb(addr);
-	pitlb(addr);
-	purge_tlb_end(flags);
-}
-EXPORT_SYMBOL(purge_tlb_entries);
-
-void __flush_tlb_range(unsigned long sid, unsigned long start,
-		       unsigned long end)
-{
-	unsigned long npages;
-
-	npages = ((end - (start & PAGE_MASK)) + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
-	if (npages >= 512)  /* 2MB of space: arbitrary, should be tuned */
+	size = (end - start);
+	if (size >= parisc_tlb_flush_threshold) {
 		flush_tlb_all();
-	else {
-		unsigned long flags;
+		return 1;
+	}
 
+	/* Purge TLB entries for small ranges using the pdtlb and
+	   pitlb instructions.  These instructions execute locally
+	   but cause a purge request to be broadcast to other TLBs.  */
+	if (likely(!split_tlb)) {
+		while (start < end) {
+			purge_tlb_start(flags);
+			mtsp(sid, 1);
+			pdtlb(start);
+			purge_tlb_end(flags);
+			start += PAGE_SIZE;
+		}
+		return 0;
+	}
+
+	/* split TLB case */
+	while (start < end) {
 		purge_tlb_start(flags);
 		mtsp(sid, 1);
-		if (split_tlb) {
-			while (npages--) {
-				pdtlb(start);
-				pitlb(start);
-				start += PAGE_SIZE;
-			}
-		} else {
-			while (npages--) {
-				pdtlb(start);
-				start += PAGE_SIZE;
-			}
-		}
+		pdtlb(start);
+		pitlb(start);
 		purge_tlb_end(flags);
+		start += PAGE_SIZE;
 	}
+	return 0;
 }
 
 static void cacheflush_h_tmp_function(void *dummy)
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 7581961..c5ef408 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -45,7 +45,7 @@
 	.level 2.0
 #endif
 
-	.import         pa_dbit_lock,data
+	.import		pa_tlb_lock,data
 
 	/* space_to_prot macro creates a prot id from a space id */
 
@@ -420,8 +420,8 @@
 	SHLREG		%r9,PxD_VALUE_SHIFT,\pmd
 	extru		\va,31-PAGE_SHIFT,ASM_BITS_PER_PTE,\index
 	dep		%r0,31,PAGE_SHIFT,\pmd  /* clear offset */
-	shladd		\index,BITS_PER_PTE_ENTRY,\pmd,\pmd
-	LDREG		%r0(\pmd),\pte		/* pmd is now pte */
+	shladd		\index,BITS_PER_PTE_ENTRY,\pmd,\pmd /* pmd is now pte */
+	LDREG		%r0(\pmd),\pte
 	bb,>=,n		\pte,_PAGE_PRESENT_BIT,\fault
 	.endm
 
@@ -453,57 +453,53 @@
 	L2_ptep		\pgd,\pte,\index,\va,\fault
 	.endm
 
-	/* Acquire pa_dbit_lock lock. */
-	.macro		dbit_lock	spc,tmp,tmp1
+	/* Acquire pa_tlb_lock lock and recheck page is still present. */
+	.macro		tlb_lock	spc,ptp,pte,tmp,tmp1,fault
 #ifdef CONFIG_SMP
 	cmpib,COND(=),n	0,\spc,2f
-	load32		PA(pa_dbit_lock),\tmp
+	load32		PA(pa_tlb_lock),\tmp
 1:	LDCW		0(\tmp),\tmp1
 	cmpib,COND(=)	0,\tmp1,1b
 	nop
+	LDREG		0(\ptp),\pte
+	bb,<,n		\pte,_PAGE_PRESENT_BIT,2f
+	b		\fault
+	stw		 \spc,0(\tmp)
 2:
 #endif
 	.endm
 
-	/* Release pa_dbit_lock lock without reloading lock address. */
-	.macro		dbit_unlock0	spc,tmp
+	/* Release pa_tlb_lock lock without reloading lock address. */
+	.macro		tlb_unlock0	spc,tmp
 #ifdef CONFIG_SMP
 	or,COND(=)	%r0,\spc,%r0
 	stw             \spc,0(\tmp)
 #endif
 	.endm
 
-	/* Release pa_dbit_lock lock. */
-	.macro		dbit_unlock1	spc,tmp
+	/* Release pa_tlb_lock lock. */
+	.macro		tlb_unlock1	spc,tmp
 #ifdef CONFIG_SMP
-	load32		PA(pa_dbit_lock),\tmp
-	dbit_unlock0	\spc,\tmp
+	load32		PA(pa_tlb_lock),\tmp
+	tlb_unlock0	\spc,\tmp
 #endif
 	.endm
 
 	/* Set the _PAGE_ACCESSED bit of the PTE.  Be clever and
 	 * don't needlessly dirty the cache line if it was already set */
-	.macro		update_ptep	spc,ptep,pte,tmp,tmp1
-#ifdef CONFIG_SMP
-	or,COND(=)	%r0,\spc,%r0
-	LDREG		0(\ptep),\pte
-#endif
+	.macro		update_accessed	ptp,pte,tmp,tmp1
 	ldi		_PAGE_ACCESSED,\tmp1
 	or		\tmp1,\pte,\tmp
 	and,COND(<>)	\tmp1,\pte,%r0
-	STREG		\tmp,0(\ptep)
+	STREG		\tmp,0(\ptp)
 	.endm
 
 	/* Set the dirty bit (and accessed bit).  No need to be
 	 * clever, this is only used from the dirty fault */
-	.macro		update_dirty	spc,ptep,pte,tmp
-#ifdef CONFIG_SMP
-	or,COND(=)	%r0,\spc,%r0
-	LDREG		0(\ptep),\pte
-#endif
+	.macro		update_dirty	ptp,pte,tmp
 	ldi		_PAGE_ACCESSED|_PAGE_DIRTY,\tmp
 	or		\tmp,\pte,\pte
-	STREG		\pte,0(\ptep)
+	STREG		\pte,0(\ptp)
 	.endm
 
 	/* bitshift difference between a PFN (based on kernel's PAGE_SIZE)
@@ -1148,14 +1144,14 @@
 
 	L3_ptep		ptp,pte,t0,va,dtlb_check_alias_20w
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20w
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 	
 	idtlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1174,14 +1170,14 @@
 
 	L3_ptep		ptp,pte,t0,va,nadtlb_check_alias_20w
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20w
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	idtlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1202,20 +1198,20 @@
 
 	L2_ptep		ptp,pte,t0,va,dtlb_check_alias_11
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_11
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	idtlba		pte,(%sr1,va)
 	idtlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1235,21 +1231,20 @@
 
 	L2_ptep		ptp,pte,t0,va,nadtlb_check_alias_11
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_11
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	idtlba		pte,(%sr1,va)
 	idtlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1269,16 +1264,16 @@
 
 	L2_ptep		ptp,pte,t0,va,dtlb_check_alias_20
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dtlb_check_alias_20
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0
+	f_extend	pte,t1
 
 	idtlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1297,16 +1292,16 @@
 
 	L2_ptep		ptp,pte,t0,va,nadtlb_check_alias_20
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,nadtlb_check_alias_20
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0
+	f_extend	pte,t1
 	
-        idtlbt          pte,prot
-	dbit_unlock1	spc,t0
+	idtlbt		pte,prot
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1406,14 +1401,14 @@
 
 	L3_ptep		ptp,pte,t0,va,itlb_fault
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 	
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1430,14 +1425,14 @@
 
 	L3_ptep		ptp,pte,t0,va,naitlb_check_alias_20w
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20w
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1458,20 +1453,20 @@
 
 	L2_ptep		ptp,pte,t0,va,itlb_fault
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	iitlba		pte,(%sr1,va)
 	iitlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1482,20 +1477,20 @@
 
 	L2_ptep		ptp,pte,t0,va,naitlb_check_alias_11
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_11
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
-	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
+	mfsp		%sr1,t1  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
 
 	iitlba		pte,(%sr1,va)
 	iitlbp		prot,(%sr1,va)
 
-	mtsp		t0, %sr1	/* Restore sr1 */
-	dbit_unlock1	spc,t0
+	mtsp		t1, %sr1	/* Restore sr1 */
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1516,16 +1511,16 @@
 
 	L2_ptep		ptp,pte,t0,va,itlb_fault
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,itlb_fault
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0	
+	f_extend	pte,t1
 
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1536,16 +1531,16 @@
 
 	L2_ptep		ptp,pte,t0,va,naitlb_check_alias_20
 
-	dbit_lock	spc,t0,t1
-	update_ptep	spc,ptp,pte,t0,t1
+	tlb_lock	spc,ptp,pte,t0,t1,naitlb_check_alias_20
+	update_accessed	ptp,pte,t0,t1
 
 	make_insert_tlb	spc,pte,prot
 
-	f_extend	pte,t0
+	f_extend	pte,t1
 
 	iitlbt          pte,prot
-	dbit_unlock1	spc,t0
 
+	tlb_unlock1	spc,t0
 	rfir
 	nop
 
@@ -1568,14 +1563,14 @@
 
 	L3_ptep		ptp,pte,t0,va,dbit_fault
 
-	dbit_lock	spc,t0,t1
-	update_dirty	spc,ptp,pte,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
+	update_dirty	ptp,pte,t1
 
 	make_insert_tlb	spc,pte,prot
 		
 	idtlbt          pte,prot
-	dbit_unlock0	spc,t0
 
+	tlb_unlock0	spc,t0
 	rfir
 	nop
 #else
@@ -1588,8 +1583,8 @@
 
 	L2_ptep		ptp,pte,t0,va,dbit_fault
 
-	dbit_lock	spc,t0,t1
-	update_dirty	spc,ptp,pte,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
+	update_dirty	ptp,pte,t1
 
 	make_insert_tlb_11	spc,pte,prot
 
@@ -1600,8 +1595,8 @@
 	idtlbp		prot,(%sr1,va)
 
 	mtsp            t1, %sr1     /* Restore sr1 */
-	dbit_unlock0	spc,t0
 
+	tlb_unlock0	spc,t0
 	rfir
 	nop
 
@@ -1612,16 +1607,16 @@
 
 	L2_ptep		ptp,pte,t0,va,dbit_fault
 
-	dbit_lock	spc,t0,t1
-	update_dirty	spc,ptp,pte,t1
+	tlb_lock	spc,ptp,pte,t0,t1,dbit_fault
+	update_dirty	ptp,pte,t1
 
 	make_insert_tlb	spc,pte,prot
 
 	f_extend	pte,t1
 	
-        idtlbt          pte,prot
-	dbit_unlock0	spc,t0
+	idtlbt		pte,prot
 
+	tlb_unlock0	spc,t0
 	rfir
 	nop
 #endif
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 6548fd1..b99b39f 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -43,10 +43,6 @@
 
 #include "../math-emu/math-emu.h"	/* for handle_fpe() */
 
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
-DEFINE_SPINLOCK(pa_dbit_lock);
-#endif
-
 static void parisc_show_stack(struct task_struct *task, unsigned long *sp,
 	struct pt_regs *regs);
 
diff --git a/arch/powerpc/include/asm/mpc52xx_psc.h b/arch/powerpc/include/asm/mpc52xx_psc.h
index d0ece25..04c7e8f 100644
--- a/arch/powerpc/include/asm/mpc52xx_psc.h
+++ b/arch/powerpc/include/asm/mpc52xx_psc.h
@@ -150,7 +150,10 @@
 
 /* Structure of the hardware registers */
 struct mpc52xx_psc {
-	u8		mode;		/* PSC + 0x00 */
+	union {
+		u8	mode;		/* PSC + 0x00 */
+		u8	mr2;
+	};
 	u8		reserved0[3];
 	union {				/* PSC + 0x04 */
 		u16	status;
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index ccde8f0..112ccf4 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -52,6 +52,22 @@
 	.text
 
 /*
+ * Used by threads when the lock bit of core_idle_state is set.
+ * 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
+ */
+
+core_idle_lock_held:
+	HMT_LOW
+3:	lwz	r15,0(r14)
+	andi.   r15,r15,PNV_CORE_IDLE_LOCK_BIT
+	bne	3b
+	HMT_MEDIUM
+	lwarx	r15,0,r14
+	blr
+
+/*
  * Pass requested state in r3:
  *	r3 - PNV_THREAD_NAP/SLEEP/WINKLE
  *
@@ -150,6 +166,10 @@
 	ld	r14,PACA_CORE_IDLE_STATE_PTR(r13)
 lwarx_loop1:
 	lwarx	r15,0,r14
+
+	andi.   r9,r15,PNV_CORE_IDLE_LOCK_BIT
+	bnel	core_idle_lock_held
+
 	andc	r15,r15,r7			/* Clear thread bit */
 
 	andi.	r15,r15,PNV_CORE_IDLE_THREAD_BITS
@@ -294,7 +314,7 @@
 	 * workaround undo code or resyncing timebase or restoring context
 	 * In either case loop until the lock bit is cleared.
 	 */
-	bne	core_idle_lock_held
+	bnel	core_idle_lock_held
 
 	cmpwi	cr2,r15,0
 	lbz	r4,PACA_SUBCORE_SIBLING_MASK(r13)
@@ -319,15 +339,6 @@
 	isync
 	b	common_exit
 
-core_idle_lock_held:
-	HMT_LOW
-core_idle_lock_loop:
-	lwz	r15,0(14)
-	andi.   r9,r15,PNV_CORE_IDLE_LOCK_BIT
-	bne	core_idle_lock_loop
-	HMT_MEDIUM
-	b	lwarx_loop2
-
 first_thread_in_subcore:
 	/* First thread in subcore to wakeup */
 	ori	r15,r15,PNV_CORE_IDLE_LOCK_BIT
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index d3a831a..da50e0c 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -966,8 +966,6 @@
 
 int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, 3*sizeof(int)) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE32))
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index 6530f1b..37de90f 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -297,6 +297,8 @@
 
 	__this_cpu_inc(irq_stat.mce_exceptions);
 
+	add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
 	if (cur_cpu_spec && cur_cpu_spec->machine_check_early)
 		handled = cur_cpu_spec->machine_check_early(regs);
 	return handled;
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 6d53597..a67c6d7 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -529,6 +529,10 @@
 		printk(KERN_ALERT "Unable to handle kernel paging request for "
 			"instruction fetch\n");
 		break;
+	case 0x600:
+		printk(KERN_ALERT "Unable to handle kernel paging request for "
+			"unaligned access at address 0x%08lx\n", regs->dar);
+		break;
 	default:
 		printk(KERN_ALERT "Unable to handle kernel paging request for "
 			"unknown fault\n");
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index ec2eb20..df95629 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -320,6 +320,8 @@
 	if (!attr)
 		return NULL;
 
+	sysfs_attr_init(&attr->attr.attr);
+
 	attr->var = str;
 	attr->attr.attr.name = name;
 	attr->attr.attr.mode = 0444;
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 5cf5e6e..7cf0df8 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -1478,7 +1478,7 @@
 	}
 
 	/* Unmask the event */
-	if (eeh_enabled())
+	if (ret == EEH_NEXT_ERR_NONE && eeh_enabled())
 		enable_irq(eeh_event_irq);
 
 	return ret;
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index 4949ef0..37f959b 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -237,7 +237,7 @@
 	return elog;
 }
 
-static void elog_work_fn(struct work_struct *work)
+static irqreturn_t elog_event(int irq, void *data)
 {
 	__be64 size;
 	__be64 id;
@@ -251,7 +251,7 @@
 	rc = opal_get_elog_size(&id, &size, &type);
 	if (rc != OPAL_SUCCESS) {
 		pr_err("ELOG: OPAL log info read failed\n");
-		return;
+		return IRQ_HANDLED;
 	}
 
 	elog_size = be64_to_cpu(size);
@@ -270,16 +270,10 @@
 	 * entries.
 	 */
 	if (kset_find_obj(elog_kset, name))
-		return;
+		return IRQ_HANDLED;
 
 	create_elog_obj(log_id, elog_size, elog_type);
-}
 
-static DECLARE_WORK(elog_work, elog_work_fn);
-
-static irqreturn_t elog_event(int irq, void *data)
-{
-	schedule_work(&elog_work);
 	return IRQ_HANDLED;
 }
 
@@ -304,8 +298,8 @@
 		return irq;
 	}
 
-	rc = request_irq(irq, elog_event,
-			IRQ_TYPE_LEVEL_HIGH, "opal-elog", NULL);
+	rc = request_threaded_irq(irq, NULL, elog_event,
+			IRQF_TRIGGER_HIGH | IRQF_ONESHOT, "opal-elog", NULL);
 	if (rc) {
 		pr_err("%s: Can't request OPAL event irq (%d)\n",
 		       __func__, rc);
diff --git a/arch/powerpc/platforms/powernv/opal-prd.c b/arch/powerpc/platforms/powernv/opal-prd.c
index 46cb3fe..4ece8e4 100644
--- a/arch/powerpc/platforms/powernv/opal-prd.c
+++ b/arch/powerpc/platforms/powernv/opal-prd.c
@@ -112,6 +112,7 @@
 static int opal_prd_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	size_t addr, size;
+	pgprot_t page_prot;
 	int rc;
 
 	pr_devel("opal_prd_mmap(0x%016lx, 0x%016lx, 0x%lx, 0x%lx)\n",
@@ -125,13 +126,11 @@
 	if (!opal_prd_range_is_valid(addr, size))
 		return -EINVAL;
 
-	vma->vm_page_prot = __pgprot(pgprot_val(phys_mem_access_prot(file,
-						vma->vm_pgoff,
-						 size, vma->vm_page_prot))
-					| _PAGE_SPECIAL);
+	page_prot = phys_mem_access_prot(file, vma->vm_pgoff,
+					 size, vma->vm_page_prot);
 
 	rc = remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, size,
-			vma->vm_page_prot);
+				page_prot);
 
 	return rc;
 }
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 5738d31..85cbc96 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2220,7 +2220,7 @@
 
 static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift,
 		unsigned levels, unsigned long limit,
-		unsigned long *current_offset)
+		unsigned long *current_offset, unsigned long *total_allocated)
 {
 	struct page *tce_mem = NULL;
 	__be64 *addr, *tmp;
@@ -2236,6 +2236,7 @@
 	}
 	addr = page_address(tce_mem);
 	memset(addr, 0, allocated);
+	*total_allocated += allocated;
 
 	--levels;
 	if (!levels) {
@@ -2245,7 +2246,7 @@
 
 	for (i = 0; i < entries; ++i) {
 		tmp = pnv_pci_ioda2_table_do_alloc_pages(nid, shift,
-				levels, limit, current_offset);
+				levels, limit, current_offset, total_allocated);
 		if (!tmp)
 			break;
 
@@ -2267,7 +2268,7 @@
 		struct iommu_table *tbl)
 {
 	void *addr;
-	unsigned long offset = 0, level_shift;
+	unsigned long offset = 0, level_shift, total_allocated = 0;
 	const unsigned window_shift = ilog2(window_size);
 	unsigned entries_shift = window_shift - page_shift;
 	unsigned table_shift = max_t(unsigned, entries_shift + 3, PAGE_SHIFT);
@@ -2286,7 +2287,7 @@
 
 	/* Allocate TCE table */
 	addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
-			levels, tce_table_size, &offset);
+			levels, tce_table_size, &offset, &total_allocated);
 
 	/* addr==NULL means that the first level allocation failed */
 	if (!addr)
@@ -2308,7 +2309,7 @@
 			page_shift);
 	tbl->it_level_size = 1ULL << (level_shift - 3);
 	tbl->it_indirect_levels = levels - 1;
-	tbl->it_allocated_size = offset;
+	tbl->it_allocated_size = total_allocated;
 
 	pr_devel("Created TCE table: ws=%08llx ts=%lx @%08llx\n",
 			window_size, tce_table_size, bus_offset);
diff --git a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
index 2bc3367..87f9623 100644
--- a/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_hsta_msi.c
@@ -18,6 +18,7 @@
 #include <linux/pci.h>
 #include <linux/semaphore.h>
 #include <asm/msi_bitmap.h>
+#include <asm/ppc-pci.h>
 
 struct ppc4xx_hsta_msi {
 	struct device *dev;
diff --git a/arch/s390/include/asm/Kbuild b/arch/s390/include/asm/Kbuild
index dc5385e..5ad26dd 100644
--- a/arch/s390/include/asm/Kbuild
+++ b/arch/s390/include/asm/Kbuild
@@ -3,5 +3,6 @@
 generic-y += clkdev.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += preempt.h
 generic-y += trace_clock.h
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index cfad7fca..d7697ab 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -57,7 +57,10 @@
 		unsigned long lap  : 1; /* Low-address-protection control */
 		unsigned long	   : 4;
 		unsigned long edat : 1; /* Enhanced-DAT-enablement control */
-		unsigned long	   : 23;
+		unsigned long	   : 4;
+		unsigned long afp  : 1; /* AFP-register control */
+		unsigned long vx   : 1; /* Vector enablement control */
+		unsigned long	   : 17;
 	};
 };
 
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 0130d03..d9be7c0 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -14,6 +14,7 @@
 
 #define is_hugepage_only_range(mm, addr, len)	0
 #define hugetlb_free_pgd_range			free_pgd_range
+#define hugepages_supported()			(MACHINE_HAS_HPAGE)
 
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
diff --git a/arch/s390/include/asm/mm-arch-hooks.h b/arch/s390/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 07680b2..0000000
--- a/arch/s390/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_S390_MM_ARCH_HOOKS_H
-#define _ASM_S390_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_S390_MM_ARCH_HOOKS_H */
diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
index dd34523..53eacbd 100644
--- a/arch/s390/include/asm/page.h
+++ b/arch/s390/include/asm/page.h
@@ -17,10 +17,7 @@
 #define PAGE_DEFAULT_ACC	0
 #define PAGE_DEFAULT_KEY	(PAGE_DEFAULT_ACC << 4)
 
-#include <asm/setup.h>
-#ifndef __ASSEMBLY__
-
-extern int HPAGE_SHIFT;
+#define HPAGE_SHIFT	20
 #define HPAGE_SIZE	(1UL << HPAGE_SHIFT)
 #define HPAGE_MASK	(~(HPAGE_SIZE - 1))
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
@@ -30,6 +27,9 @@
 #define ARCH_HAS_PREPARE_HUGEPAGE
 #define ARCH_HAS_HUGEPAGE_CLEAR_FLUSH
 
+#include <asm/setup.h>
+#ifndef __ASSEMBLY__
+
 static inline void storage_key_init_range(unsigned long start, unsigned long end)
 {
 #if PAGE_DEFAULT_KEY
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index 4cb19fe..f897ec7 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -87,7 +87,15 @@
 } __packed;
 
 /* Perf hardware reserve and release functions */
+#ifdef CONFIG_PERF_EVENTS
 int perf_reserve_sampling(void);
 void perf_release_sampling(void);
+#else /* CONFIG_PERF_EVENTS */
+static inline int perf_reserve_sampling(void)
+{
+	return 0;
+}
+static inline void perf_release_sampling(void) {}
+#endif /* CONFIG_PERF_EVENTS */
 
 #endif /* _ASM_S390_PERF_EVENT_H */
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index c7d1b9d..a2da259 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -23,15 +23,15 @@
 
 int main(void)
 {
-	DEFINE(__THREAD_info, offsetof(struct task_struct, stack));
-	DEFINE(__THREAD_ksp, offsetof(struct task_struct, thread.ksp));
-	DEFINE(__THREAD_mm_segment, offsetof(struct task_struct, thread.mm_segment));
-	BLANK();
+	DEFINE(__TASK_thread_info, offsetof(struct task_struct, stack));
+	DEFINE(__TASK_thread, offsetof(struct task_struct, thread));
 	DEFINE(__TASK_pid, offsetof(struct task_struct, pid));
 	BLANK();
-	DEFINE(__THREAD_per_cause, offsetof(struct task_struct, thread.per_event.cause));
-	DEFINE(__THREAD_per_address, offsetof(struct task_struct, thread.per_event.address));
-	DEFINE(__THREAD_per_paid, offsetof(struct task_struct, thread.per_event.paid));
+	DEFINE(__THREAD_ksp, offsetof(struct thread_struct, ksp));
+	DEFINE(__THREAD_per_cause, offsetof(struct thread_struct, per_event.cause));
+	DEFINE(__THREAD_per_address, offsetof(struct thread_struct, per_event.address));
+	DEFINE(__THREAD_per_paid, offsetof(struct thread_struct, per_event.paid));
+	DEFINE(__THREAD_trap_tdb, offsetof(struct thread_struct, trap_tdb));
 	BLANK();
 	DEFINE(__TI_task, offsetof(struct thread_info, task));
 	DEFINE(__TI_flags, offsetof(struct thread_info, flags));
@@ -176,7 +176,6 @@
 	DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data));
 	DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap));
 	DEFINE(__LC_PGM_TDB, offsetof(struct _lowcore, pgm_tdb));
-	DEFINE(__THREAD_trap_tdb, offsetof(struct task_struct, thread.trap_tdb));
 	DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce));
 	DEFINE(__SIE_PROG0C, offsetof(struct kvm_s390_sie_block, prog0c));
 	DEFINE(__SIE_PROG20, offsetof(struct kvm_s390_sie_block, prog20));
diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c
index bff5e3b..8ba3243 100644
--- a/arch/s390/kernel/cache.c
+++ b/arch/s390/kernel/cache.c
@@ -138,6 +138,8 @@
 	union cache_topology ct;
 	enum cache_type ctype;
 
+	if (!test_facility(34))
+		return -EOPNOTSUPP;
 	if (!this_cpu_ci)
 		return -EINVAL;
 	ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0);
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 3238893..84062e7 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -178,17 +178,21 @@
  */
 ENTRY(__switch_to)
 	stmg	%r6,%r15,__SF_GPRS(%r15)	# store gprs of prev task
-	stg	%r15,__THREAD_ksp(%r2)		# store kernel stack of prev
-	lg	%r4,__THREAD_info(%r2)		# get thread_info of prev
-	lg	%r5,__THREAD_info(%r3)		# get thread_info of next
+	lgr	%r1,%r2
+	aghi	%r1,__TASK_thread		# thread_struct of prev task
+	lg	%r4,__TASK_thread_info(%r2)	# get thread_info of prev
+	lg	%r5,__TASK_thread_info(%r3)	# get thread_info of next
+	stg	%r15,__THREAD_ksp(%r1)		# store kernel stack of prev
+	lgr	%r1,%r3
+	aghi	%r1,__TASK_thread		# thread_struct of next task
 	lgr	%r15,%r5
 	aghi	%r15,STACK_INIT			# end of kernel stack of next
 	stg	%r3,__LC_CURRENT		# store task struct of next
 	stg	%r5,__LC_THREAD_INFO		# store thread info of next
 	stg	%r15,__LC_KERNEL_STACK		# store end of kernel stack
+	lg	%r15,__THREAD_ksp(%r1)		# load kernel stack of next
 	lctl	%c4,%c4,__TASK_pid(%r3)		# load pid to control reg. 4
 	mvc	__LC_CURRENT_PID+4(4,%r0),__TASK_pid(%r3) # store pid of next
-	lg	%r15,__THREAD_ksp(%r3)		# load kernel stack of next
 	lmg	%r6,%r15,__SF_GPRS(%r15)	# load gprs of next task
 	br	%r14
 
@@ -417,6 +421,7 @@
 	LAST_BREAK %r14
 	lg	%r15,__LC_KERNEL_STACK
 	lg	%r14,__TI_task(%r12)
+	aghi	%r14,__TASK_thread	# pointer to thread_struct
 	lghi	%r13,__LC_PGM_TDB
 	tm	__LC_PGM_ILC+2,0x02	# check for transaction abort
 	jz	2f
diff --git a/arch/s390/kernel/nmi.c b/arch/s390/kernel/nmi.c
index 505c17c..56b5508 100644
--- a/arch/s390/kernel/nmi.c
+++ b/arch/s390/kernel/nmi.c
@@ -21,6 +21,7 @@
 #include <asm/nmi.h>
 #include <asm/crw.h>
 #include <asm/switch_to.h>
+#include <asm/ctl_reg.h>
 
 struct mcck_struct {
 	int kill_task;
@@ -129,26 +130,30 @@
 	} else
 		asm volatile("lfpc 0(%0)" : : "a" (fpt_creg_save_area));
 
-	asm volatile(
-		"	ld	0,0(%0)\n"
-		"	ld	1,8(%0)\n"
-		"	ld	2,16(%0)\n"
-		"	ld	3,24(%0)\n"
-		"	ld	4,32(%0)\n"
-		"	ld	5,40(%0)\n"
-		"	ld	6,48(%0)\n"
-		"	ld	7,56(%0)\n"
-		"	ld	8,64(%0)\n"
-		"	ld	9,72(%0)\n"
-		"	ld	10,80(%0)\n"
-		"	ld	11,88(%0)\n"
-		"	ld	12,96(%0)\n"
-		"	ld	13,104(%0)\n"
-		"	ld	14,112(%0)\n"
-		"	ld	15,120(%0)\n"
-		: : "a" (fpt_save_area));
-	/* Revalidate vector registers */
-	if (MACHINE_HAS_VX && current->thread.vxrs) {
+	if (!MACHINE_HAS_VX) {
+		/* Revalidate floating point registers */
+		asm volatile(
+			"	ld	0,0(%0)\n"
+			"	ld	1,8(%0)\n"
+			"	ld	2,16(%0)\n"
+			"	ld	3,24(%0)\n"
+			"	ld	4,32(%0)\n"
+			"	ld	5,40(%0)\n"
+			"	ld	6,48(%0)\n"
+			"	ld	7,56(%0)\n"
+			"	ld	8,64(%0)\n"
+			"	ld	9,72(%0)\n"
+			"	ld	10,80(%0)\n"
+			"	ld	11,88(%0)\n"
+			"	ld	12,96(%0)\n"
+			"	ld	13,104(%0)\n"
+			"	ld	14,112(%0)\n"
+			"	ld	15,120(%0)\n"
+			: : "a" (fpt_save_area));
+	} else {
+		/* Revalidate vector registers */
+		union ctlreg0 cr0;
+
 		if (!mci->vr) {
 			/*
 			 * Vector registers can't be restored and therefore
@@ -156,8 +161,12 @@
 			 */
 			kill_task = 1;
 		}
+		cr0.val = S390_lowcore.cregs_save_area[0];
+		cr0.afp = cr0.vx = 1;
+		__ctl_load(cr0.val, 0, 0);
 		restore_vx_regs((__vector128 *)
-				S390_lowcore.vector_save_area_addr);
+				&S390_lowcore.vector_save_area);
+		__ctl_load(S390_lowcore.cregs_save_area[0], 0, 0);
 	}
 	/* Revalidate access registers */
 	asm volatile(
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index dc5edc2..8f587d8 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -163,7 +163,7 @@
 asmlinkage void execve_tail(void)
 {
 	current->thread.fp_regs.fpc = 0;
-	asm volatile("sfpc %0,%0" : : "d" (0));
+	asm volatile("sfpc %0" : : "d" (0));
 }
 
 /*
diff --git a/arch/s390/kernel/sclp.S b/arch/s390/kernel/sclp.S
index 43c3169..ada0c07 100644
--- a/arch/s390/kernel/sclp.S
+++ b/arch/s390/kernel/sclp.S
@@ -270,6 +270,8 @@
 	jno	.Lesa2
 	ahi	%r15,-80
 	stmh	%r6,%r15,96(%r15)		# store upper register halves
+	basr	%r13,0
+	lmh	%r0,%r15,.Lzeroes-.(%r13)	# clear upper register halves
 .Lesa2:
 	lr	%r10,%r2			# save string pointer
 	lhi	%r2,0
@@ -291,6 +293,8 @@
 .Lesa3:
 	lm	%r6,%r15,120(%r15)		# restore registers
 	br	%r14
+.Lzeroes:
+	.fill	64,4,0
 
 .LwritedataS4:
 	.long	0x00760005			# SCLP command for write data
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index f7f027c..ca070d2 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -885,8 +885,6 @@
 	 */
 	setup_hwcaps();
 
-	HPAGE_SHIFT = MACHINE_HAS_HPAGE ? 20 : 0;
-
 	/*
 	 * Create kernel page tables and switch to virtual addressing.
 	 */
diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 4d96c9f..7bea81d 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -259,7 +259,7 @@
 	}
 
 	/* get vector interrupt code from fpc */
-	asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc));
+	asm volatile("stfpc %0" : "=Q" (current->thread.fp_regs.fpc));
 	vic = (current->thread.fp_regs.fpc & 0xf00) >> 8;
 	switch (vic) {
 	case 1: /* invalid vector operation */
@@ -297,7 +297,7 @@
 
 	location = get_trap_ip(regs);
 
-	asm volatile("stfpc %0" : "=m" (current->thread.fp_regs.fpc));
+	asm volatile("stfpc %0" : "=Q" (current->thread.fp_regs.fpc));
 	/* Check for vector register enablement */
 	if (MACHINE_HAS_VX && !current->thread.vxrs &&
 	    (current->thread.fp_regs.fpc & FPC_DXC_MASK) == 0xfe00) {
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2078f92..f32f843 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1742,10 +1742,10 @@
 
 static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->requests)
-		return 0;
 retry:
 	kvm_s390_vcpu_request_handled(vcpu);
+	if (!vcpu->requests)
+		return 0;
 	/*
 	 * We use MMU_RELOAD just to re-arm the ipte notifier for the
 	 * guest prefix page. gmap_ipte_notify will wait on the ptl lock.
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 33082d0..b33f661 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -31,8 +31,6 @@
 #define ALLOC_ORDER	2
 #define FRAG_MASK	0x03
 
-int HPAGE_SHIFT;
-
 unsigned long *crst_table_alloc(struct mm_struct *mm)
 {
 	struct page *page = alloc_pages(GFP_KERNEL, ALLOC_ORDER);
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index fee782a..8d2e516 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -448,13 +448,13 @@
 		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
 			      BPF_REG_1, offsetof(struct sk_buff, data));
 	}
-	/* BPF compatibility: clear A (%b7) and X (%b8) registers */
-	if (REG_SEEN(BPF_REG_7))
-		/* lghi %b7,0 */
-		EMIT4_IMM(0xa7090000, BPF_REG_7, 0);
-	if (REG_SEEN(BPF_REG_8))
-		/* lghi %b8,0 */
-		EMIT4_IMM(0xa7090000, BPF_REG_8, 0);
+	/* BPF compatibility: clear A (%b0) and X (%b7) registers */
+	if (REG_SEEN(BPF_REG_A))
+		/* lghi %ba,0 */
+		EMIT4_IMM(0xa7090000, BPF_REG_A, 0);
+	if (REG_SEEN(BPF_REG_X))
+		/* lghi %bx,0 */
+		EMIT4_IMM(0xa7090000, BPF_REG_X, 0);
 }
 
 /*
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
index bc927a0..9cfa2ff 100644
--- a/arch/s390/oprofile/init.c
+++ b/arch/s390/oprofile/init.c
@@ -16,6 +16,7 @@
 #include <linux/fs.h>
 #include <linux/module.h>
 #include <asm/processor.h>
+#include <asm/perf_event.h>
 
 #include "../../../drivers/oprofile/oprof.h"
 
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index 138fb3d..92ffe39 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -7,6 +7,7 @@
 generic-y += cputime.h
 generic-y += irq_work.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += preempt.h
 generic-y += sections.h
 generic-y += trace_clock.h
diff --git a/arch/score/include/asm/mm-arch-hooks.h b/arch/score/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 5e38689..0000000
--- a/arch/score/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_SCORE_MM_ARCH_HOOKS_H
-#define _ASM_SCORE_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_SCORE_MM_ARCH_HOOKS_H */
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 9ac4626..aac452b 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -16,6 +16,7 @@
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += param.h
diff --git a/arch/sh/include/asm/mm-arch-hooks.h b/arch/sh/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 1808729..0000000
--- a/arch/sh/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_SH_MM_ARCH_HOOKS_H
-#define _ASM_SH_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_SH_MM_ARCH_HOOKS_H */
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index 2b2a69d..e9286188 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -12,6 +12,7 @@
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += module.h
 generic-y += mutex.h
 generic-y += preempt.h
diff --git a/arch/sparc/include/asm/mm-arch-hooks.h b/arch/sparc/include/asm/mm-arch-hooks.h
deleted file mode 100644
index b89ba44..0000000
--- a/arch/sparc/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_SPARC_MM_ARCH_HOOKS_H
-#define _ASM_SPARC_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_SPARC_MM_ARCH_HOOKS_H */
diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h
index 1f0aa20..6424249 100644
--- a/arch/sparc/include/asm/visasm.h
+++ b/arch/sparc/include/asm/visasm.h
@@ -28,16 +28,10 @@
  * Must preserve %o5 between VISEntryHalf and VISExitHalf */
 
 #define VISEntryHalf					\
-	rd		%fprs, %o5;			\
-	andcc		%o5, FPRS_FEF, %g0;		\
-	be,pt		%icc, 297f;			\
-	 sethi		%hi(298f), %g7;			\
-	sethi		%hi(VISenterhalf), %g1;		\
-	jmpl		%g1 + %lo(VISenterhalf), %g0;	\
-	 or		%g7, %lo(298f), %g7;		\
-	clr		%o5;				\
-297:	wr		%o5, FPRS_FEF, %fprs;		\
-298:
+	VISEntry
+
+#define VISExitHalf					\
+	VISExit
 
 #define VISEntryHalfFast(fail_label)			\
 	rd		%fprs, %o5;			\
@@ -47,7 +41,7 @@
 	ba,a,pt		%xcc, fail_label;		\
 297:	wr		%o5, FPRS_FEF, %fprs;
 
-#define VISExitHalf					\
+#define VISExitHalfFast					\
 	wr		%o5, 0, %fprs;
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 140527a..83aeeb1 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -240,8 +240,11 @@
 	add		%o0, 0x40, %o0
 	bne,pt		%icc, 1b
 	 LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
+#ifdef NON_USER_COPY
+	VISExitHalfFast
+#else
 	VISExitHalf
-
+#endif
 	brz,pn		%o2, .Lexit
 	 cmp		%o2, 19
 	ble,pn		%icc, .Lsmall_unaligned
diff --git a/arch/sparc/lib/VISsave.S b/arch/sparc/lib/VISsave.S
index b320ae9..a063d84 100644
--- a/arch/sparc/lib/VISsave.S
+++ b/arch/sparc/lib/VISsave.S
@@ -44,9 +44,8 @@
 
 	 stx		%g3, [%g6 + TI_GSR]
 2:	add		%g6, %g1, %g3
-	cmp		%o5, FPRS_DU
-	be,pn		%icc, 6f
-	 sll		%g1, 3, %g1
+	mov		FPRS_DU | FPRS_DL | FPRS_FEF, %o5
+	sll		%g1, 3, %g1
 	stb		%o5, [%g3 + TI_FPSAVED]
 	rd		%gsr, %g2
 	add		%g6, %g1, %g3
@@ -80,65 +79,3 @@
 	.align		32
 80:	jmpl		%g7 + %g0, %g0
 	 nop
-
-6:	ldub		[%g3 + TI_FPSAVED], %o5
-	or		%o5, FPRS_DU, %o5
-	add		%g6, TI_FPREGS+0x80, %g2
-	stb		%o5, [%g3 + TI_FPSAVED]
-
-	sll		%g1, 5, %g1
-	add		%g6, TI_FPREGS+0xc0, %g3
-	wr		%g0, FPRS_FEF, %fprs
-	membar		#Sync
-	stda		%f32, [%g2 + %g1] ASI_BLK_P
-	stda		%f48, [%g3 + %g1] ASI_BLK_P
-	membar		#Sync
-	ba,pt		%xcc, 80f
-	 nop
-
-	.align		32
-80:	jmpl		%g7 + %g0, %g0
-	 nop
-
-	.align		32
-VISenterhalf:
-	ldub		[%g6 + TI_FPDEPTH], %g1
-	brnz,a,pn	%g1, 1f
-	 cmp		%g1, 1
-	stb		%g0, [%g6 + TI_FPSAVED]
-	stx		%fsr, [%g6 + TI_XFSR]
-	clr		%o5
-	jmpl		%g7 + %g0, %g0
-	 wr		%g0, FPRS_FEF, %fprs
-
-1:	bne,pn		%icc, 2f
-	 srl		%g1, 1, %g1
-	ba,pt		%xcc, vis1
-	 sub		%g7, 8, %g7
-2:	addcc		%g6, %g1, %g3
-	sll		%g1, 3, %g1
-	andn		%o5, FPRS_DU, %g2
-	stb		%g2, [%g3 + TI_FPSAVED]
-
-	rd		%gsr, %g2
-	add		%g6, %g1, %g3
-	stx		%g2, [%g3 + TI_GSR]
-	add		%g6, %g1, %g2
-	stx		%fsr, [%g2 + TI_XFSR]
-	sll		%g1, 5, %g1
-3:	andcc		%o5, FPRS_DL, %g0
-	be,pn		%icc, 4f
-	 add		%g6, TI_FPREGS, %g2
-
-	add		%g6, TI_FPREGS+0x40, %g3
-	membar		#Sync
-	stda		%f0, [%g2 + %g1] ASI_BLK_P
-	stda		%f16, [%g3 + %g1] ASI_BLK_P
-	membar		#Sync
-	ba,pt		%xcc, 4f
-	 nop
-
-	.align		32
-4:	and		%o5, FPRS_DU, %o5
-	jmpl		%g7 + %g0, %g0
-	 wr		%o5, FPRS_FEF, %fprs
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 1d649a9..8069ce1 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -135,10 +135,6 @@
 void VISenter(void);
 EXPORT_SYMBOL(VISenter);
 
-/* CRYPTO code needs this */
-void VISenterhalf(void);
-EXPORT_SYMBOL(VISenterhalf);
-
 extern void xor_vis_2(unsigned long, unsigned long *, unsigned long *);
 extern void xor_vis_3(unsigned long, unsigned long *, unsigned long *,
 		unsigned long *);
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index d536544..d8a8431 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -19,6 +19,7 @@
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += msgbuf.h
 generic-y += mutex.h
 generic-y += param.h
diff --git a/arch/tile/include/asm/mm-arch-hooks.h b/arch/tile/include/asm/mm-arch-hooks.h
deleted file mode 100644
index d1709ea..0000000
--- a/arch/tile/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_TILE_MM_ARCH_HOOKS_H
-#define _ASM_TILE_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_TILE_MM_ARCH_HOOKS_H */
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index e8c2c04..c667e10 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -113,8 +113,6 @@
 	if (!access_ok(VERIFY_READ, from, sizeof(struct compat_siginfo)))
 		return -EFAULT;
 
-	memset(to, 0, sizeof(*to));
-
 	err = __get_user(to->si_signo, &from->si_signo);
 	err |= __get_user(to->si_errno, &from->si_errno);
 	err |= __get_user(to->si_code, &from->si_code);
diff --git a/arch/tile/kernel/setup.c b/arch/tile/kernel/setup.c
index 99c9ff8..6b755d1 100644
--- a/arch/tile/kernel/setup.c
+++ b/arch/tile/kernel/setup.c
@@ -1139,7 +1139,7 @@
 
 void __init free_initrd_mem(unsigned long begin, unsigned long end)
 {
-	free_bootmem(__pa(begin), end - begin);
+	free_bootmem_late(__pa(begin), end - begin);
 }
 
 static int __init setup_initrd(char *str)
diff --git a/arch/tile/lib/memcpy_user_64.c b/arch/tile/lib/memcpy_user_64.c
index 88c7016..97bbb60 100644
--- a/arch/tile/lib/memcpy_user_64.c
+++ b/arch/tile/lib/memcpy_user_64.c
@@ -28,7 +28,7 @@
 #define _ST(p, inst, v)						\
 	({							\
 		asm("1: " #inst " %0, %1;"			\
-		    ".pushsection .coldtext.memcpy,\"ax\";"	\
+		    ".pushsection .coldtext,\"ax\";"	\
 		    "2: { move r0, %2; jrp lr };"		\
 		    ".section __ex_table,\"a\";"		\
 		    ".align 8;"					\
@@ -41,7 +41,7 @@
 	({							\
 		unsigned long __v;				\
 		asm("1: " #inst " %0, %1;"			\
-		    ".pushsection .coldtext.memcpy,\"ax\";"	\
+		    ".pushsection .coldtext,\"ax\";"	\
 		    "2: { move r0, %2; jrp lr };"		\
 		    ".section __ex_table,\"a\";"		\
 		    ".align 8;"					\
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 3d63ff6..149ec55 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -16,6 +16,7 @@
 generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mutex.h
 generic-y += param.h
 generic-y += pci.h
diff --git a/arch/um/include/asm/mm-arch-hooks.h b/arch/um/include/asm/mm-arch-hooks.h
deleted file mode 100644
index a7c8b0d..0000000
--- a/arch/um/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_UM_MM_ARCH_HOOKS_H
-#define _ASM_UM_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_UM_MM_ARCH_HOOKS_H */
diff --git a/arch/unicore32/include/asm/Kbuild b/arch/unicore32/include/asm/Kbuild
index d12b377..1fc7a28 100644
--- a/arch/unicore32/include/asm/Kbuild
+++ b/arch/unicore32/include/asm/Kbuild
@@ -26,6 +26,7 @@
 generic-y += kmap_types.h
 generic-y += local.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += module.h
 generic-y += msgbuf.h
diff --git a/arch/unicore32/include/asm/mm-arch-hooks.h b/arch/unicore32/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 4d79a85..0000000
--- a/arch/unicore32/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_UNICORE32_MM_ARCH_HOOKS_H
-#define _ASM_UNICORE32_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_UNICORE32_MM_ARCH_HOOKS_H */
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 55bced1..b3a1a5d 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -41,6 +41,7 @@
 	select ARCH_USE_CMPXCHG_LOCKREF		if X86_64
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
+	select ARCH_WANTS_DYNAMIC_TASK_STRUCT
 	select ARCH_WANT_FRAME_POINTERS
 	select ARCH_WANT_IPC_PARSE_VERSION	if X86_32
 	select ARCH_WANT_OPTIONAL_GPIOLIB
@@ -254,6 +255,11 @@
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
 	def_bool y
 
+config KASAN_SHADOW_OFFSET
+	hex
+	depends on KASAN
+	default 0xdffffc0000000000
+
 config HAVE_INTEL_TXT
 	def_bool y
 	depends on INTEL_IOMMU && ACPI
@@ -2015,7 +2021,7 @@
 
 	  To compile command line arguments into the kernel,
 	  set this option to 'Y', then fill in the
-	  the boot arguments in CONFIG_CMDLINE.
+	  boot arguments in CONFIG_CMDLINE.
 
 	  Systems with fully functional boot loaders (i.e. non-embedded)
 	  should leave this option set to 'N'.
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index a15893d..d8c0d32 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -297,6 +297,18 @@
 
 	  If unsure, say N.
 
+config DEBUG_ENTRY
+	bool "Debug low-level entry code"
+	depends on DEBUG_KERNEL
+	---help---
+	  This option enables sanity checks in x86's low-level entry code.
+	  Some of these sanity checks may slow down kernel entries and
+	  exits or otherwise impact performance.
+
+	  This is currently used to help test NMI code.
+
+	  If unsure, say N.
+
 config DEBUG_NMI_SELFTEST
 	bool "NMI Selftest"
 	depends on DEBUG_KERNEL && X86_LOCAL_APIC
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 2c82bd1..7d69afd 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -1193,6 +1193,10 @@
 		unsigned int e820_type = 0;
 		unsigned long m = efi->efi_memmap;
 
+#ifdef CONFIG_X86_64
+		m |= (u64)efi->efi_memmap_hi << 32;
+#endif
+
 		d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size));
 		switch (d->type) {
 		case EFI_RESERVED_TYPE:
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 3bb2c43..8cb3e43 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1237,11 +1237,12 @@
 	 *  If the variable is not set and the stack is not the NMI
 	 *  stack then:
 	 *    o Set the special variable on the stack
-	 *    o Copy the interrupt frame into a "saved" location on the stack
-	 *    o Copy the interrupt frame into a "copy" location on the stack
+	 *    o Copy the interrupt frame into an "outermost" location on the
+	 *      stack
+	 *    o Copy the interrupt frame into an "iret" location on the stack
 	 *    o Continue processing the NMI
 	 *  If the variable is set or the previous stack is the NMI stack:
-	 *    o Modify the "copy" location to jump to the repeate_nmi
+	 *    o Modify the "iret" location to jump to the repeat_nmi
 	 *    o return back to the first NMI
 	 *
 	 * Now on exit of the first NMI, we first clear the stack variable
@@ -1250,31 +1251,151 @@
 	 * a nested NMI that updated the copy interrupt stack frame, a
 	 * jump will be made to the repeat_nmi code that will handle the second
 	 * NMI.
+	 *
+	 * However, espfix prevents us from directly returning to userspace
+	 * with a single IRET instruction.  Similarly, IRET to user mode
+	 * can fault.  We therefore handle NMIs from user space like
+	 * other IST entries.
 	 */
 
 	/* Use %rdx as our temp variable throughout */
 	pushq	%rdx
 
-	/*
-	 * If %cs was not the kernel segment, then the NMI triggered in user
-	 * space, which means it is definitely not nested.
-	 */
-	cmpl	$__KERNEL_CS, 16(%rsp)
-	jne	first_nmi
+	testb	$3, CS-RIP+8(%rsp)
+	jz	.Lnmi_from_kernel
 
 	/*
-	 * Check the special variable on the stack to see if NMIs are
-	 * executing.
+	 * NMI from user mode.  We need to run on the thread stack, but we
+	 * can't go through the normal entry paths: NMIs are masked, and
+	 * we don't want to enable interrupts, because then we'll end
+	 * up in an awkward situation in which IRQs are on but NMIs
+	 * are off.
+	 */
+
+	SWAPGS
+	cld
+	movq	%rsp, %rdx
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	pushq	5*8(%rdx)	/* pt_regs->ss */
+	pushq	4*8(%rdx)	/* pt_regs->rsp */
+	pushq	3*8(%rdx)	/* pt_regs->flags */
+	pushq	2*8(%rdx)	/* pt_regs->cs */
+	pushq	1*8(%rdx)	/* pt_regs->rip */
+	pushq   $-1		/* pt_regs->orig_ax */
+	pushq   %rdi		/* pt_regs->di */
+	pushq   %rsi		/* pt_regs->si */
+	pushq   (%rdx)		/* pt_regs->dx */
+	pushq   %rcx		/* pt_regs->cx */
+	pushq   %rax		/* pt_regs->ax */
+	pushq   %r8		/* pt_regs->r8 */
+	pushq   %r9		/* pt_regs->r9 */
+	pushq   %r10		/* pt_regs->r10 */
+	pushq   %r11		/* pt_regs->r11 */
+	pushq	%rbx		/* pt_regs->rbx */
+	pushq	%rbp		/* pt_regs->rbp */
+	pushq	%r12		/* pt_regs->r12 */
+	pushq	%r13		/* pt_regs->r13 */
+	pushq	%r14		/* pt_regs->r14 */
+	pushq	%r15		/* pt_regs->r15 */
+
+	/*
+	 * At this point we no longer need to worry about stack damage
+	 * due to nesting -- we're on the normal thread stack and we're
+	 * done with the NMI stack.
+	 */
+
+	movq	%rsp, %rdi
+	movq	$-1, %rsi
+	call	do_nmi
+
+	/*
+	 * Return back to user mode.  We must *not* do the normal exit
+	 * work, because we don't want to enable interrupts.  Fortunately,
+	 * do_nmi doesn't modify pt_regs.
+	 */
+	SWAPGS
+	jmp	restore_c_regs_and_iret
+
+.Lnmi_from_kernel:
+	/*
+	 * Here's what our stack frame will look like:
+	 * +---------------------------------------------------------+
+	 * | original SS                                             |
+	 * | original Return RSP                                     |
+	 * | original RFLAGS                                         |
+	 * | original CS                                             |
+	 * | original RIP                                            |
+	 * +---------------------------------------------------------+
+	 * | temp storage for rdx                                    |
+	 * +---------------------------------------------------------+
+	 * | "NMI executing" variable                                |
+	 * +---------------------------------------------------------+
+	 * | iret SS          } Copied from "outermost" frame        |
+	 * | iret Return RSP  } on each loop iteration; overwritten  |
+	 * | iret RFLAGS      } by a nested NMI to force another     |
+	 * | iret CS          } iteration if needed.                 |
+	 * | iret RIP         }                                      |
+	 * +---------------------------------------------------------+
+	 * | outermost SS          } initialized in first_nmi;       |
+	 * | outermost Return RSP  } will not be changed before      |
+	 * | outermost RFLAGS      } NMI processing is done.         |
+	 * | outermost CS          } Copied to "iret" frame on each  |
+	 * | outermost RIP         } iteration.                      |
+	 * +---------------------------------------------------------+
+	 * | pt_regs                                                 |
+	 * +---------------------------------------------------------+
+	 *
+	 * The "original" frame is used by hardware.  Before re-enabling
+	 * NMIs, we need to be done with it, and we need to leave enough
+	 * space for the asm code here.
+	 *
+	 * We return by executing IRET while RSP points to the "iret" frame.
+	 * That will either return for real or it will loop back into NMI
+	 * processing.
+	 *
+	 * The "outermost" frame is copied to the "iret" frame on each
+	 * iteration of the loop, so each iteration starts with the "iret"
+	 * frame pointing to the final return target.
+	 */
+
+	/*
+	 * Determine whether we're a nested NMI.
+	 *
+	 * If we interrupted kernel code between repeat_nmi and
+	 * end_repeat_nmi, then we are a nested NMI.  We must not
+	 * modify the "iret" frame because it's being written by
+	 * the outer NMI.  That's okay; the outer NMI handler is
+	 * about to about to call do_nmi anyway, so we can just
+	 * resume the outer NMI.
+	 */
+
+	movq	$repeat_nmi, %rdx
+	cmpq	8(%rsp), %rdx
+	ja	1f
+	movq	$end_repeat_nmi, %rdx
+	cmpq	8(%rsp), %rdx
+	ja	nested_nmi_out
+1:
+
+	/*
+	 * Now check "NMI executing".  If it's set, then we're nested.
+	 * This will not detect if we interrupted an outer NMI just
+	 * before IRET.
 	 */
 	cmpl	$1, -8(%rsp)
 	je	nested_nmi
 
 	/*
-	 * Now test if the previous stack was an NMI stack.
-	 * We need the double check. We check the NMI stack to satisfy the
-	 * race when the first NMI clears the variable before returning.
-	 * We check the variable because the first NMI could be in a
-	 * breakpoint routine using a breakpoint stack.
+	 * Now test if the previous stack was an NMI stack.  This covers
+	 * the case where we interrupt an outer NMI after it clears
+	 * "NMI executing" but before IRET.  We need to be careful, though:
+	 * there is one case in which RSP could point to the NMI stack
+	 * despite there being no NMI active: naughty userspace controls
+	 * RSP at the very beginning of the SYSCALL targets.  We can
+	 * pull a fast one on naughty userspace, though: we program
+	 * SYSCALL to mask DF, so userspace cannot cause DF to be set
+	 * if it controls the kernel's RSP.  We set DF before we clear
+	 * "NMI executing".
 	 */
 	lea	6*8(%rsp), %rdx
 	/* Compare the NMI stack (rdx) with the stack we came from (4*8(%rsp)) */
@@ -1286,25 +1407,20 @@
 	cmpq	%rdx, 4*8(%rsp)
 	/* If it is below the NMI stack, it is a normal NMI */
 	jb	first_nmi
-	/* Ah, it is within the NMI stack, treat it as nested */
+
+	/* Ah, it is within the NMI stack. */
+
+	testb	$(X86_EFLAGS_DF >> 8), (3*8 + 1)(%rsp)
+	jz	first_nmi	/* RSP was user controlled. */
+
+	/* This is a nested NMI. */
 
 nested_nmi:
 	/*
-	 * Do nothing if we interrupted the fixup in repeat_nmi.
-	 * It's about to repeat the NMI handler, so we are fine
-	 * with ignoring this one.
+	 * Modify the "iret" frame to point to repeat_nmi, forcing another
+	 * iteration of NMI handling.
 	 */
-	movq	$repeat_nmi, %rdx
-	cmpq	8(%rsp), %rdx
-	ja	1f
-	movq	$end_repeat_nmi, %rdx
-	cmpq	8(%rsp), %rdx
-	ja	nested_nmi_out
-
-1:
-	/* Set up the interrupted NMIs stack to jump to repeat_nmi */
-	leaq	-1*8(%rsp), %rdx
-	movq	%rdx, %rsp
+	subq	$8, %rsp
 	leaq	-10*8(%rsp), %rdx
 	pushq	$__KERNEL_DS
 	pushq	%rdx
@@ -1318,61 +1434,42 @@
 nested_nmi_out:
 	popq	%rdx
 
-	/* No need to check faults here */
+	/* We are returning to kernel mode, so this cannot result in a fault. */
 	INTERRUPT_RETURN
 
 first_nmi:
-	/*
-	 * Because nested NMIs will use the pushed location that we
-	 * stored in rdx, we must keep that space available.
-	 * Here's what our stack frame will look like:
-	 * +-------------------------+
-	 * | original SS             |
-	 * | original Return RSP     |
-	 * | original RFLAGS         |
-	 * | original CS             |
-	 * | original RIP            |
-	 * +-------------------------+
-	 * | temp storage for rdx    |
-	 * +-------------------------+
-	 * | NMI executing variable  |
-	 * +-------------------------+
-	 * | copied SS               |
-	 * | copied Return RSP       |
-	 * | copied RFLAGS           |
-	 * | copied CS               |
-	 * | copied RIP              |
-	 * +-------------------------+
-	 * | Saved SS                |
-	 * | Saved Return RSP        |
-	 * | Saved RFLAGS            |
-	 * | Saved CS                |
-	 * | Saved RIP               |
-	 * +-------------------------+
-	 * | pt_regs                 |
-	 * +-------------------------+
-	 *
-	 * The saved stack frame is used to fix up the copied stack frame
-	 * that a nested NMI may change to make the interrupted NMI iret jump
-	 * to the repeat_nmi. The original stack frame and the temp storage
-	 * is also used by nested NMIs and can not be trusted on exit.
-	 */
-	/* Do not pop rdx, nested NMIs will corrupt that part of the stack */
+	/* Restore rdx. */
 	movq	(%rsp), %rdx
 
-	/* Set the NMI executing variable on the stack. */
-	pushq	$1
+	/* Make room for "NMI executing". */
+	pushq	$0
 
-	/* Leave room for the "copied" frame */
+	/* Leave room for the "iret" frame */
 	subq	$(5*8), %rsp
 
-	/* Copy the stack frame to the Saved frame */
+	/* Copy the "original" frame to the "outermost" frame */
 	.rept 5
 	pushq	11*8(%rsp)
 	.endr
 
 	/* Everything up to here is safe from nested NMIs */
 
+#ifdef CONFIG_DEBUG_ENTRY
+	/*
+	 * For ease of testing, unmask NMIs right away.  Disabled by
+	 * default because IRET is very expensive.
+	 */
+	pushq	$0		/* SS */
+	pushq	%rsp		/* RSP (minus 8 because of the previous push) */
+	addq	$8, (%rsp)	/* Fix up RSP */
+	pushfq			/* RFLAGS */
+	pushq	$__KERNEL_CS	/* CS */
+	pushq	$1f		/* RIP */
+	INTERRUPT_RETURN	/* continues at repeat_nmi below */
+1:
+#endif
+
+repeat_nmi:
 	/*
 	 * If there was a nested NMI, the first NMI's iret will return
 	 * here. But NMIs are still enabled and we can take another
@@ -1381,16 +1478,20 @@
 	 * it will just return, as we are about to repeat an NMI anyway.
 	 * This makes it safe to copy to the stack frame that a nested
 	 * NMI will update.
+	 *
+	 * RSP is pointing to "outermost RIP".  gsbase is unknown, but, if
+	 * we're repeating an NMI, gsbase has the same value that it had on
+	 * the first iteration.  paranoid_entry will load the kernel
+	 * gsbase if needed before we call do_nmi.  "NMI executing"
+	 * is zero.
 	 */
-repeat_nmi:
-	/*
-	 * Update the stack variable to say we are still in NMI (the update
-	 * is benign for the non-repeat case, where 1 was pushed just above
-	 * to this very stack slot).
-	 */
-	movq	$1, 10*8(%rsp)
+	movq	$1, 10*8(%rsp)		/* Set "NMI executing". */
 
-	/* Make another copy, this one may be modified by nested NMIs */
+	/*
+	 * Copy the "outermost" frame to the "iret" frame.  NMIs that nest
+	 * here must not modify the "iret" frame while we're writing to
+	 * it or it will end up containing garbage.
+	 */
 	addq	$(10*8), %rsp
 	.rept 5
 	pushq	-6*8(%rsp)
@@ -1399,9 +1500,9 @@
 end_repeat_nmi:
 
 	/*
-	 * Everything below this point can be preempted by a nested
-	 * NMI if the first NMI took an exception and reset our iret stack
-	 * so that we repeat another NMI.
+	 * Everything below this point can be preempted by a nested NMI.
+	 * If this happens, then the inner NMI will change the "iret"
+	 * frame to point back to repeat_nmi.
 	 */
 	pushq	$-1				/* ORIG_RAX: no syscall to restart */
 	ALLOC_PT_GPREGS_ON_STACK
@@ -1415,28 +1516,11 @@
 	 */
 	call	paranoid_entry
 
-	/*
-	 * Save off the CR2 register. If we take a page fault in the NMI then
-	 * it could corrupt the CR2 value. If the NMI preempts a page fault
-	 * handler before it was able to read the CR2 register, and then the
-	 * NMI itself takes a page fault, the page fault that was preempted
-	 * will read the information from the NMI page fault and not the
-	 * origin fault. Save it off and restore it if it changes.
-	 * Use the r12 callee-saved register.
-	 */
-	movq	%cr2, %r12
-
 	/* paranoidentry do_nmi, 0; without TRACE_IRQS_OFF */
 	movq	%rsp, %rdi
 	movq	$-1, %rsi
 	call	do_nmi
 
-	/* Did the NMI take a page fault? Restore cr2 if it did */
-	movq	%cr2, %rcx
-	cmpq	%rcx, %r12
-	je	1f
-	movq	%r12, %cr2
-1:
 	testl	%ebx, %ebx			/* swapgs needed? */
 	jnz	nmi_restore
 nmi_swapgs:
@@ -1444,11 +1528,26 @@
 nmi_restore:
 	RESTORE_EXTRA_REGS
 	RESTORE_C_REGS
-	/* Pop the extra iret frame at once */
+
+	/* Point RSP at the "iret" frame. */
 	REMOVE_PT_GPREGS_FROM_STACK 6*8
 
-	/* Clear the NMI executing stack variable */
-	movq	$0, 5*8(%rsp)
+	/*
+	 * Clear "NMI executing".  Set DF first so that we can easily
+	 * distinguish the remaining code between here and IRET from
+	 * the SYSCALL entry and exit paths.  On a native kernel, we
+	 * could just inspect RIP, but, on paravirt kernels,
+	 * INTERRUPT_RETURN can translate into a jump into a
+	 * hypercall page.
+	 */
+	std
+	movq	$0, 5*8(%rsp)		/* clear "NMI executing" */
+
+	/*
+	 * INTERRUPT_RETURN reads the "iret" frame and exits the NMI
+	 * stack in a single instruction.  We are returning to kernel
+	 * mode, so this cannot result in a fault.
+	 */
 	INTERRUPT_RETURN
 END(nmi)
 
diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S
index bb187a6..a7e257d 100644
--- a/arch/x86/entry/entry_64_compat.S
+++ b/arch/x86/entry/entry_64_compat.S
@@ -140,6 +140,7 @@
 	 */
 	andl	$~TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
 	movl	RIP(%rsp), %ecx		/* User %eip */
+	movq    RAX(%rsp), %rax
 	RESTORE_RSI_RDI
 	xorl	%edx, %edx		/* Do not leak kernel information */
 	xorq	%r8, %r8
@@ -205,7 +206,6 @@
 	movl	RDX(%rsp), %edx		/* arg3 */
 	movl	RSI(%rsp), %ecx		/* arg4 */
 	movl	RDI(%rsp), %r8d		/* arg5 */
-	movl	%ebp, %r9d		/* arg6 */
 	.endm
 
 	.macro auditsys_exit exit
@@ -220,7 +220,6 @@
 1:	setbe	%al			/* 1 if error, 0 if not */
 	movzbl	%al, %edi		/* zero-extend that into %edi */
 	call	__audit_syscall_exit
-	movq	RAX(%rsp), %rax		/* reload syscall return value */
 	movl	$(_TIF_ALLWORK_MASK & ~_TIF_SYSCALL_AUDIT), %edi
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
@@ -236,6 +235,7 @@
 
 sysenter_auditsys:
 	auditsys_entry_common
+	movl	%ebp, %r9d		/* reload 6th syscall arg */
 	jmp	sysenter_dispatch
 
 sysexit_audit:
@@ -336,7 +336,7 @@
 	 * 32-bit zero extended:
 	 */
 	ASM_STAC
-1:	movl	(%r8), %ebp
+1:	movl	(%r8), %r9d
 	_ASM_EXTABLE(1b, ia32_badarg)
 	ASM_CLAC
 	orl	$TS_COMPAT, ASM_THREAD_INFO(TI_status, %rsp, SIZEOF_PTREGS)
@@ -346,7 +346,7 @@
 cstar_do_call:
 	/* 32-bit syscall -> 64-bit C ABI argument conversion */
 	movl	%edi, %r8d		/* arg5 */
-	movl	%ebp, %r9d		/* arg6 */
+	/* r9 already loaded */		/* arg6 */
 	xchg	%ecx, %esi		/* rsi:arg2, rcx:arg4 */
 	movl	%ebx, %edi		/* arg1 */
 	movl	%edx, %edx		/* arg3 (zero extension) */
@@ -358,7 +358,6 @@
 	call	*ia32_sys_call_table(, %rax, 8)
 	movq	%rax, RAX(%rsp)
 1:
-	movl	RCX(%rsp), %ebp
 	DISABLE_INTERRUPTS(CLBR_NONE)
 	TRACE_IRQS_OFF
 	testl	$_TIF_ALLWORK_MASK, ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
@@ -369,6 +368,7 @@
 	RESTORE_RSI_RDI_RDX
 	movl	RIP(%rsp), %ecx
 	movl	EFLAGS(%rsp), %r11d
+	movq    RAX(%rsp), %rax
 	xorq	%r10, %r10
 	xorq	%r9, %r9
 	xorq	%r8, %r8
@@ -392,7 +392,9 @@
 
 #ifdef CONFIG_AUDITSYSCALL
 cstar_auditsys:
+	movl	%r9d, R9(%rsp)		/* register to be clobbered by call */
 	auditsys_entry_common
+	movl	R9(%rsp), %r9d		/* reload 6th syscall arg */
 	jmp	cstar_dispatch
 
 sysretl_audit:
@@ -404,14 +406,16 @@
 	testl	$(_TIF_WORK_SYSCALL_ENTRY & ~_TIF_SYSCALL_AUDIT), ASM_THREAD_INFO(TI_flags, %rsp, SIZEOF_PTREGS)
 	jz	cstar_auditsys
 #endif
+	xchgl	%r9d, %ebp
 	SAVE_EXTRA_REGS
 	xorl	%eax, %eax		/* Do not leak kernel information */
 	movq	%rax, R11(%rsp)
 	movq	%rax, R10(%rsp)
-	movq	%rax, R9(%rsp)
+	movq	%r9, R9(%rsp)
 	movq	%rax, R8(%rsp)
 	movq	%rsp, %rdi		/* &pt_regs -> arg1 */
 	call	syscall_trace_enter
+	movl	R9(%rsp), %r9d
 
 	/* Reload arg registers from stack. (see sysenter_tracesys) */
 	movl	RCX(%rsp), %ecx
@@ -421,6 +425,7 @@
 	movl	%eax, %eax		/* zero extension */
 
 	RESTORE_EXTRA_REGS
+	xchgl	%ebp, %r9d
 	jmp	cstar_do_call
 END(entry_SYSCALL_compat)
 
diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 4dd1f2d..aeac434 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -9,3 +9,4 @@
 generic-y += dma-contiguous.h
 generic-y += early_ioremap.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index a0bf89f..4e10d73 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -280,21 +280,6 @@
 	set_ldt(NULL, 0);
 }
 
-/*
- * load one particular LDT into the current CPU
- */
-static inline void load_LDT_nolock(mm_context_t *pc)
-{
-	set_ldt(pc->ldt, pc->size);
-}
-
-static inline void load_LDT(mm_context_t *pc)
-{
-	preempt_disable();
-	load_LDT_nolock(pc);
-	preempt_enable();
-}
-
 static inline unsigned long get_desc_base(const struct desc_struct *desc)
 {
 	return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
diff --git a/arch/x86/include/asm/espfix.h b/arch/x86/include/asm/espfix.h
index 99efebb..ca3ce9a 100644
--- a/arch/x86/include/asm/espfix.h
+++ b/arch/x86/include/asm/espfix.h
@@ -9,7 +9,7 @@
 DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
 
 extern void init_espfix_bsp(void);
-extern void init_espfix_ap(void);
+extern void init_espfix_ap(int cpu);
 
 #endif /* CONFIG_X86_64 */
 
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 0637826..c49c517 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -189,6 +189,7 @@
 	struct fxregs_state		fxsave;
 	struct swregs_state		soft;
 	struct xregs_state		xsave;
+	u8 __padding[PAGE_SIZE];
 };
 
 /*
@@ -198,40 +199,6 @@
  */
 struct fpu {
 	/*
-	 * @state:
-	 *
-	 * In-memory copy of all FPU registers that we save/restore
-	 * over context switches. If the task is using the FPU then
-	 * the registers in the FPU are more recent than this state
-	 * copy. If the task context-switches away then they get
-	 * saved here and represent the FPU state.
-	 *
-	 * After context switches there may be a (short) time period
-	 * during which the in-FPU hardware registers are unchanged
-	 * and still perfectly match this state, if the tasks
-	 * scheduled afterwards are not using the FPU.
-	 *
-	 * This is the 'lazy restore' window of optimization, which
-	 * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'.
-	 *
-	 * We detect whether a subsequent task uses the FPU via setting
-	 * CR0::TS to 1, which causes any FPU use to raise a #NM fault.
-	 *
-	 * During this window, if the task gets scheduled again, we
-	 * might be able to skip having to do a restore from this
-	 * memory buffer to the hardware registers - at the cost of
-	 * incurring the overhead of #NM fault traps.
-	 *
-	 * Note that on modern CPUs that support the XSAVEOPT (or other
-	 * optimized XSAVE instructions), we don't use #NM traps anymore,
-	 * as the hardware can track whether FPU registers need saving
-	 * or not. On such CPUs we activate the non-lazy ('eagerfpu')
-	 * logic, which unconditionally saves/restores all FPU state
-	 * across context switches. (if FPU state exists.)
-	 */
-	union fpregs_state		state;
-
-	/*
 	 * @last_cpu:
 	 *
 	 * Records the last CPU on which this context was loaded into
@@ -288,6 +255,43 @@
 	 * deal with bursty apps that only use the FPU for a short time:
 	 */
 	unsigned char			counter;
+	/*
+	 * @state:
+	 *
+	 * In-memory copy of all FPU registers that we save/restore
+	 * over context switches. If the task is using the FPU then
+	 * the registers in the FPU are more recent than this state
+	 * copy. If the task context-switches away then they get
+	 * saved here and represent the FPU state.
+	 *
+	 * After context switches there may be a (short) time period
+	 * during which the in-FPU hardware registers are unchanged
+	 * and still perfectly match this state, if the tasks
+	 * scheduled afterwards are not using the FPU.
+	 *
+	 * This is the 'lazy restore' window of optimization, which
+	 * we track though 'fpu_fpregs_owner_ctx' and 'fpu->last_cpu'.
+	 *
+	 * We detect whether a subsequent task uses the FPU via setting
+	 * CR0::TS to 1, which causes any FPU use to raise a #NM fault.
+	 *
+	 * During this window, if the task gets scheduled again, we
+	 * might be able to skip having to do a restore from this
+	 * memory buffer to the hardware registers - at the cost of
+	 * incurring the overhead of #NM fault traps.
+	 *
+	 * Note that on modern CPUs that support the XSAVEOPT (or other
+	 * optimized XSAVE instructions), we don't use #NM traps anymore,
+	 * as the hardware can track whether FPU registers need saving
+	 * or not. On such CPUs we activate the non-lazy ('eagerfpu')
+	 * logic, which unconditionally saves/restores all FPU state
+	 * across context switches. (if FPU state exists.)
+	 */
+	union fpregs_state		state;
+	/*
+	 * WARNING: 'state' is dynamically-sized.  Do not put
+	 * anything after it here.
+	 */
 };
 
 #endif /* _ASM_X86_FPU_H */
diff --git a/arch/x86/include/asm/intel_pmc_ipc.h b/arch/x86/include/asm/intel_pmc_ipc.h
index 200ec2e..cd0310e 100644
--- a/arch/x86/include/asm/intel_pmc_ipc.h
+++ b/arch/x86/include/asm/intel_pmc_ipc.h
@@ -25,36 +25,9 @@
 
 #if IS_ENABLED(CONFIG_INTEL_PMC_IPC)
 
-/*
- * intel_pmc_ipc_simple_command
- * @cmd: command
- * @sub: sub type
- */
 int intel_pmc_ipc_simple_command(int cmd, int sub);
-
-/*
- * intel_pmc_ipc_raw_cmd
- * @cmd: command
- * @sub: sub type
- * @in: input data
- * @inlen: input length in bytes
- * @out: output data
- * @outlen: output length in dwords
- * @sptr: data writing to SPTR register
- * @dptr: data writing to DPTR register
- */
 int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen,
 		u32 *out, u32 outlen, u32 dptr, u32 sptr);
-
-/*
- * intel_pmc_ipc_command
- * @cmd: command
- * @sub: sub type
- * @in: input data
- * @inlen: input length in bytes
- * @out: output data
- * @outlen: output length in dwords
- */
 int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen,
 		u32 *out, u32 outlen);
 
diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h
index 8b22422..74a2a8d 100644
--- a/arch/x86/include/asm/kasan.h
+++ b/arch/x86/include/asm/kasan.h
@@ -14,15 +14,11 @@
 
 #ifndef __ASSEMBLY__
 
-extern pte_t kasan_zero_pte[];
-extern pte_t kasan_zero_pmd[];
-extern pte_t kasan_zero_pud[];
-
 #ifdef CONFIG_KASAN
-void __init kasan_map_early_shadow(pgd_t *pgd);
+void __init kasan_early_init(void);
 void __init kasan_init(void);
 #else
-static inline void kasan_map_early_shadow(pgd_t *pgd) { }
+static inline void kasan_early_init(void) { }
 static inline void kasan_init(void) { }
 #endif
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2a7f5d7..49ec903 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -604,6 +604,8 @@
 	bool iommu_noncoherent;
 #define __KVM_HAVE_ARCH_NONCOHERENT_DMA
 	atomic_t noncoherent_dma_count;
+#define __KVM_HAVE_ARCH_ASSIGNED_DEVICE
+	atomic_t assigned_device_count;
 	struct kvm_pic *vpic;
 	struct kvm_ioapic *vioapic;
 	struct kvm_pit *vpit;
diff --git a/arch/x86/include/asm/mm-arch-hooks.h b/arch/x86/include/asm/mm-arch-hooks.h
deleted file mode 100644
index 4e881a3..0000000
--- a/arch/x86/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_X86_MM_ARCH_HOOKS_H
-#define _ASM_X86_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_X86_MM_ARCH_HOOKS_H */
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 09b9620..364d274 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -9,8 +9,7 @@
  * we put the segment information here.
  */
 typedef struct {
-	void *ldt;
-	int size;
+	struct ldt_struct *ldt;
 
 #ifdef CONFIG_X86_64
 	/* True if mm supports a task running in 32 bit compatibility mode. */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 5e8daee..984abfe 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -23,7 +23,7 @@
 
 static inline void load_mm_cr4(struct mm_struct *mm)
 {
-	if (static_key_true(&rdpmc_always_available) ||
+	if (static_key_false(&rdpmc_always_available) ||
 	    atomic_read(&mm->context.perf_rdpmc_allowed))
 		cr4_set_bits(X86_CR4_PCE);
 	else
@@ -34,6 +34,50 @@
 #endif
 
 /*
+ * ldt_structs can be allocated, used, and freed, but they are never
+ * modified while live.
+ */
+struct ldt_struct {
+	/*
+	 * Xen requires page-aligned LDTs with special permissions.  This is
+	 * needed to prevent us from installing evil descriptors such as
+	 * call gates.  On native, we could merge the ldt_struct and LDT
+	 * allocations, but it's not worth trying to optimize.
+	 */
+	struct desc_struct *entries;
+	int size;
+};
+
+static inline void load_mm_ldt(struct mm_struct *mm)
+{
+	struct ldt_struct *ldt;
+
+	/* lockless_dereference synchronizes with smp_store_release */
+	ldt = lockless_dereference(mm->context.ldt);
+
+	/*
+	 * Any change to mm->context.ldt is followed by an IPI to all
+	 * CPUs with the mm active.  The LDT will not be freed until
+	 * after the IPI is handled by all such CPUs.  This means that,
+	 * if the ldt_struct changes before we return, the values we see
+	 * will be safe, and the new values will be loaded before we run
+	 * any user code.
+	 *
+	 * NB: don't try to convert this to use RCU without extreme care.
+	 * We would still need IRQs off, because we don't want to change
+	 * the local LDT after an IPI loaded a newer value than the one
+	 * that we can see.
+	 */
+
+	if (unlikely(ldt))
+		set_ldt(ldt->entries, ldt->size);
+	else
+		clear_LDT();
+
+	DEBUG_LOCKS_WARN_ON(preemptible());
+}
+
+/*
  * Used for LDT copy/destruction.
  */
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
@@ -78,12 +122,12 @@
 		 * was called and then modify_ldt changed
 		 * prev->context.ldt but suppressed an IPI to this CPU.
 		 * In this case, prev->context.ldt != NULL, because we
-		 * never free an LDT while the mm still exists.  That
-		 * means that next->context.ldt != prev->context.ldt,
-		 * because mms never share an LDT.
+		 * never set context.ldt to NULL while the mm still
+		 * exists.  That means that next->context.ldt !=
+		 * prev->context.ldt, because mms never share an LDT.
 		 */
 		if (unlikely(prev->context.ldt != next->context.ldt))
-			load_LDT_nolock(&next->context);
+			load_mm_ldt(next);
 	}
 #ifdef CONFIG_SMP
 	  else {
@@ -106,7 +150,7 @@
 			load_cr3(next->pgd);
 			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 			load_mm_cr4(next);
-			load_LDT_nolock(&next->context);
+			load_mm_ldt(next);
 		}
 	}
 #endif
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 43e6519..944f178 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -390,9 +390,6 @@
 #endif
 	unsigned long		gs;
 
-	/* Floating point and extended processor state */
-	struct fpu		fpu;
-
 	/* Save middle states of ptrace breakpoints */
 	struct perf_event	*ptrace_bps[HBP_NUM];
 	/* Debug status used for traps, single steps, etc... */
@@ -418,6 +415,13 @@
 	unsigned long		iopl;
 	/* Max allowed port in the bitmap, in bytes: */
 	unsigned		io_bitmap_max;
+
+	/* Floating point and extended processor state */
+	struct fpu		fpu;
+	/*
+	 * WARNING: 'fpu' is dynamically-sized.  It *MUST* be at
+	 * the end.
+	 */
 };
 
 /*
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index 6fe6b18..9dfce4e 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -57,9 +57,9 @@
 	unsigned long ip;
 	unsigned long flags;
 	unsigned short cs;
-	unsigned short __pad2;	/* Was called gs, but was always zero. */
-	unsigned short __pad1;	/* Was called fs, but was always zero. */
-	unsigned short ss;
+	unsigned short gs;
+	unsigned short fs;
+	unsigned short __pad0;
 	unsigned long err;
 	unsigned long trapno;
 	unsigned long oldmask;
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 751bf4b..d7f3b3b 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -79,12 +79,12 @@
 #else /* CONFIG_X86_32 */
 
 /* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT    "pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t"
+#define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
 
 #define __EXTRA_CLOBBER  \
 	, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
-	  "r12", "r13", "r14", "r15", "flags"
+	  "r12", "r13", "r14", "r15"
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 #define __switch_canary							  \
@@ -100,11 +100,7 @@
 #define __switch_canary_iparam
 #endif	/* CC_STACKPROTECTOR */
 
-/*
- * There is no need to save or restore flags, because flags are always
- * clean in kernel mode, with the possible exception of IOPL.  Kernel IOPL
- * has no effect.
- */
+/* Save restore flags to clear handle leaking NT */
 #define switch_to(prev, next, last) \
 	asm volatile(SAVE_CONTEXT					  \
 	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index 8fba544..f36d56b 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -108,6 +108,8 @@
 #define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE		(1 << 4)
 /* Support for a virtual guest idle state is available */
 #define HV_X64_GUEST_IDLE_STATE_AVAILABLE		(1 << 5)
+/* Guest crash data handler available */
+#define HV_X64_GUEST_CRASH_MSR_AVAILABLE		(1 << 10)
 
 /*
  * Implementation recommendations. Indicates which behaviors the hypervisor
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index a4ae82e..cd54147 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -354,7 +354,7 @@
 struct kvm_sync_regs {
 };
 
-#define KVM_QUIRK_LINT0_REENABLED	(1 << 0)
-#define KVM_QUIRK_CD_NW_CLEARED		(1 << 1)
+#define KVM_X86_QUIRK_LINT0_REENABLED	(1 << 0)
+#define KVM_X86_QUIRK_CD_NW_CLEARED	(1 << 1)
 
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h
index 0e8a973..40836a9 100644
--- a/arch/x86/include/uapi/asm/sigcontext.h
+++ b/arch/x86/include/uapi/asm/sigcontext.h
@@ -177,24 +177,9 @@
 	__u64 rip;
 	__u64 eflags;		/* RFLAGS */
 	__u16 cs;
-
-	/*
-	 * Prior to 2.5.64 ("[PATCH] x86-64 updates for 2.5.64-bk3"),
-	 * Linux saved and restored fs and gs in these slots.  This
-	 * was counterproductive, as fsbase and gsbase were never
-	 * saved, so arch_prctl was presumably unreliable.
-	 *
-	 * If these slots are ever needed for any other purpose, there
-	 * is some risk that very old 64-bit binaries could get
-	 * confused.  I doubt that many such binaries still work,
-	 * though, since the same patch in 2.5.64 also removed the
-	 * 64-bit set_thread_area syscall, so it appears that there is
-	 * no TLS API that works in both pre- and post-2.5.64 kernels.
-	 */
-	__u16 __pad2;		/* Was gs. */
-	__u16 __pad1;		/* Was fs. */
-
-	__u16 ss;
+	__u16 gs;
+	__u16 fs;
+	__u16 __pad0;
 	__u64 err;
 	__u64 trapno;
 	__u64 oldmask;
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 845dc0d..206052e 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -943,7 +943,7 @@
 	 */
 	if (irq < nr_legacy_irqs() && data->count == 1) {
 		if (info->ioapic_trigger != data->trigger)
-			mp_register_handler(irq, data->trigger);
+			mp_register_handler(irq, info->ioapic_trigger);
 		data->entry.trigger = data->trigger = info->ioapic_trigger;
 		data->entry.polarity = data->polarity = info->ioapic_polarity;
 	}
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 28eba2d..2683f36 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -322,7 +322,7 @@
 		irq_data->chip = &lapic_controller;
 		irq_data->chip_data = data;
 		irq_data->hwirq = virq + i;
-		err = assign_irq_vector_policy(virq, irq_data->node, data,
+		err = assign_irq_vector_policy(virq + i, irq_data->node, data,
 					       info);
 		if (err)
 			goto error;
@@ -409,12 +409,6 @@
 	int irq, vector;
 	struct apic_chip_data *data;
 
-	/*
-	 * vector_lock will make sure that we don't run into irq vector
-	 * assignments that might be happening on another cpu in parallel,
-	 * while we setup our initial vector to irq mappings.
-	 */
-	raw_spin_lock(&vector_lock);
 	/* Mark the inuse vectors */
 	for_each_active_irq(irq) {
 		data = apic_chip_data(irq_get_irq_data(irq));
@@ -436,16 +430,16 @@
 		if (!cpumask_test_cpu(cpu, data->domain))
 			per_cpu(vector_irq, cpu)[vector] = VECTOR_UNDEFINED;
 	}
-	raw_spin_unlock(&vector_lock);
 }
 
 /*
- * Setup the vector to irq mappings.
+ * Setup the vector to irq mappings. Must be called with vector_lock held.
  */
 void setup_vector_irq(int cpu)
 {
 	int irq;
 
+	lockdep_assert_held(&vector_lock);
 	/*
 	 * On most of the platforms, legacy PIC delivers the interrupts on the
 	 * boot cpu. But there are certain platforms where PIC interrupts are
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 922c5e0..cb9e5df 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1410,7 +1410,7 @@
 	load_sp0(t, &current->thread);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
-	load_LDT(&init_mm.context);
+	load_mm_ldt(&init_mm);
 
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
@@ -1459,7 +1459,7 @@
 	load_sp0(t, thread);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
-	load_LDT(&init_mm.context);
+	load_mm_ldt(&init_mm);
 
 	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3658de4..9469dfa 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2179,21 +2179,25 @@
 	int idx = segment >> 3;
 
 	if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+		struct ldt_struct *ldt;
+
 		if (idx > LDT_ENTRIES)
 			return 0;
 
-		if (idx > current->active_mm->context.size)
+		/* IRQs are off, so this synchronizes with smp_store_release */
+		ldt = lockless_dereference(current->active_mm->context.ldt);
+		if (!ldt || idx > ldt->size)
 			return 0;
 
-		desc = current->active_mm->context.ldt;
+		desc = &ldt->entries[idx];
 	} else {
 		if (idx > GDT_ENTRIES)
 			return 0;
 
-		desc = raw_cpu_ptr(gdt_page.gdt);
+		desc = raw_cpu_ptr(gdt_page.gdt) + idx;
 	}
 
-	return get_desc_base(desc + idx);
+	return get_desc_base(desc);
 }
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index b9826a9..6326ae2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2534,7 +2534,7 @@
 	if (x86_pmu.extra_regs || x86_pmu.lbr_sel_map) {
 		cpuc->shared_regs = allocate_shared_regs(cpu);
 		if (!cpuc->shared_regs)
-			return NOTIFY_BAD;
+			goto err;
 	}
 
 	if (x86_pmu.flags & PMU_FL_EXCL_CNTRS) {
@@ -2542,18 +2542,27 @@
 
 		cpuc->constraint_list = kzalloc(sz, GFP_KERNEL);
 		if (!cpuc->constraint_list)
-			return NOTIFY_BAD;
+			goto err_shared_regs;
 
 		cpuc->excl_cntrs = allocate_excl_cntrs(cpu);
-		if (!cpuc->excl_cntrs) {
-			kfree(cpuc->constraint_list);
-			kfree(cpuc->shared_regs);
-			return NOTIFY_BAD;
-		}
+		if (!cpuc->excl_cntrs)
+			goto err_constraint_list;
+
 		cpuc->excl_thread_id = 0;
 	}
 
 	return NOTIFY_OK;
+
+err_constraint_list:
+	kfree(cpuc->constraint_list);
+	cpuc->constraint_list = NULL;
+
+err_shared_regs:
+	kfree(cpuc->shared_regs);
+	cpuc->shared_regs = NULL;
+
+err:
+	return NOTIFY_BAD;
 }
 
 static void intel_pmu_cpu_starting(int cpu)
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 1880761..377e8f8 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -952,6 +952,14 @@
 		return 0;
 
 	/*
+	 * Getting up-to-date values requires an SMP IPI which is not
+	 * possible if we're being called in interrupt context. Return
+	 * the cached values instead.
+	 */
+	if (unlikely(in_interrupt()))
+		goto out;
+
+	/*
 	 * Notice that we don't perform the reading of an RMID
 	 * atomically, because we can't hold a spin lock across the
 	 * IPIs.
@@ -1247,7 +1255,7 @@
 	cpumask_set_cpu(cpu, &cqm_cpumask);
 }
 
-static void intel_cqm_cpu_prepare(unsigned int cpu)
+static void intel_cqm_cpu_starting(unsigned int cpu)
 {
 	struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -1288,13 +1296,11 @@
 	unsigned int cpu  = (unsigned long)hcpu;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-		intel_cqm_cpu_prepare(cpu);
-		break;
 	case CPU_DOWN_PREPARE:
 		intel_cqm_cpu_exit(cpu);
 		break;
 	case CPU_STARTING:
+		intel_cqm_cpu_starting(cpu);
 		cqm_pick_event_reader(cpu);
 		break;
 	}
@@ -1365,7 +1371,7 @@
 		goto out;
 
 	for_each_online_cpu(i) {
-		intel_cqm_cpu_prepare(i);
+		intel_cqm_cpu_starting(i);
 		cqm_pick_event_reader(i);
 	}
 
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 89427d8..eec40f5 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -175,7 +175,9 @@
 	}
 
 	if (*s) {
-		if (kstrtoul(s, 0, &baud) < 0 || baud == 0)
+		baud = simple_strtoull(s, &e, 0);
+
+		if (baud == 0 || s == e)
 			baud = DEFAULT_BAUD;
 	}
 
diff --git a/arch/x86/kernel/espfix_64.c b/arch/x86/kernel/espfix_64.c
index f5d0730..ce95676 100644
--- a/arch/x86/kernel/espfix_64.c
+++ b/arch/x86/kernel/espfix_64.c
@@ -131,25 +131,24 @@
 	init_espfix_random();
 
 	/* The rest is the same as for any other processor */
-	init_espfix_ap();
+	init_espfix_ap(0);
 }
 
-void init_espfix_ap(void)
+void init_espfix_ap(int cpu)
 {
-	unsigned int cpu, page;
+	unsigned int page;
 	unsigned long addr;
 	pud_t pud, *pud_p;
 	pmd_t pmd, *pmd_p;
 	pte_t pte, *pte_p;
-	int n;
+	int n, node;
 	void *stack_page;
 	pteval_t ptemask;
 
 	/* We only have to do this once... */
-	if (likely(this_cpu_read(espfix_stack)))
+	if (likely(per_cpu(espfix_stack, cpu)))
 		return;		/* Already initialized */
 
-	cpu = smp_processor_id();
 	addr = espfix_base_addr(cpu);
 	page = cpu/ESPFIX_STACKS_PER_PAGE;
 
@@ -165,12 +164,15 @@
 	if (stack_page)
 		goto unlock_done;
 
+	node = cpu_to_node(cpu);
 	ptemask = __supported_pte_mask;
 
 	pud_p = &espfix_pud_page[pud_index(addr)];
 	pud = *pud_p;
 	if (!pud_present(pud)) {
-		pmd_p = (pmd_t *)__get_free_page(PGALLOC_GFP);
+		struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0);
+
+		pmd_p = (pmd_t *)page_address(page);
 		pud = __pud(__pa(pmd_p) | (PGTABLE_PROT & ptemask));
 		paravirt_alloc_pmd(&init_mm, __pa(pmd_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PUD_CLONES; n++)
@@ -180,7 +182,9 @@
 	pmd_p = pmd_offset(&pud, addr);
 	pmd = *pmd_p;
 	if (!pmd_present(pmd)) {
-		pte_p = (pte_t *)__get_free_page(PGALLOC_GFP);
+		struct page *page = alloc_pages_node(node, PGALLOC_GFP, 0);
+
+		pte_p = (pte_t *)page_address(page);
 		pmd = __pmd(__pa(pte_p) | (PGTABLE_PROT & ptemask));
 		paravirt_alloc_pte(&init_mm, __pa(pte_p) >> PAGE_SHIFT);
 		for (n = 0; n < ESPFIX_PMD_CLONES; n++)
@@ -188,7 +192,7 @@
 	}
 
 	pte_p = pte_offset_kernel(&pmd, addr);
-	stack_page = (void *)__get_free_page(GFP_KERNEL);
+	stack_page = page_address(alloc_pages_node(node, GFP_KERNEL, 0));
 	pte = __pte(__pa(stack_page) | (__PAGE_KERNEL_RO & ptemask));
 	for (n = 0; n < ESPFIX_PTE_CLONES; n++)
 		set_pte(&pte_p[n*PTE_STRIDE], pte);
@@ -199,7 +203,7 @@
 unlock_done:
 	mutex_unlock(&espfix_init_mutex);
 done:
-	this_cpu_write(espfix_stack, addr);
-	this_cpu_write(espfix_waddr, (unsigned long)stack_page
-		       + (addr & ~PAGE_MASK));
+	per_cpu(espfix_stack, cpu) = addr;
+	per_cpu(espfix_waddr, cpu) = (unsigned long)stack_page
+				      + (addr & ~PAGE_MASK);
 }
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 79de954..d25097c 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -270,7 +270,7 @@
 	dst_fpu->fpregs_active = 0;
 	dst_fpu->last_cpu = -1;
 
-	if (src_fpu->fpstate_active)
+	if (src_fpu->fpstate_active && cpu_has_fpu)
 		fpu_copy(dst_fpu, src_fpu);
 
 	return 0;
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 3282679..d14e9ac 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -4,6 +4,8 @@
 #include <asm/fpu/internal.h>
 #include <asm/tlbflush.h>
 
+#include <linux/sched.h>
+
 /*
  * Initialize the TS bit in CR0 according to the style of context-switches
  * we are using:
@@ -38,7 +40,12 @@
 	write_cr0(cr0);
 
 	/* Flush out any pending x87 state: */
-	asm volatile ("fninit");
+#ifdef CONFIG_MATH_EMULATION
+	if (!cpu_has_fpu)
+		fpstate_init_soft(&current->thread.fpu.state.soft);
+	else
+#endif
+		asm volatile ("fninit");
 }
 
 /*
@@ -136,6 +143,43 @@
 unsigned int xstate_size;
 EXPORT_SYMBOL_GPL(xstate_size);
 
+/* Enforce that 'MEMBER' is the last field of 'TYPE': */
+#define CHECK_MEMBER_AT_END_OF(TYPE, MEMBER) \
+	BUILD_BUG_ON(sizeof(TYPE) != offsetofend(TYPE, MEMBER))
+
+/*
+ * We append the 'struct fpu' to the task_struct:
+ */
+static void __init fpu__init_task_struct_size(void)
+{
+	int task_size = sizeof(struct task_struct);
+
+	/*
+	 * Subtract off the static size of the register state.
+	 * It potentially has a bunch of padding.
+	 */
+	task_size -= sizeof(((struct task_struct *)0)->thread.fpu.state);
+
+	/*
+	 * Add back the dynamically-calculated register state
+	 * size.
+	 */
+	task_size += xstate_size;
+
+	/*
+	 * We dynamically size 'struct fpu', so we require that
+	 * it be at the end of 'thread_struct' and that
+	 * 'thread_struct' be at the end of 'task_struct'.  If
+	 * you hit a compile error here, check the structure to
+	 * see if something got added to the end.
+	 */
+	CHECK_MEMBER_AT_END_OF(struct fpu, state);
+	CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu);
+	CHECK_MEMBER_AT_END_OF(struct task_struct, thread);
+
+	arch_task_struct_size = task_size;
+}
+
 /*
  * Set up the xstate_size based on the legacy FPU context size.
  *
@@ -287,6 +331,7 @@
 	fpu__init_system_generic();
 	fpu__init_system_xstate_size_legacy();
 	fpu__init_system_xstate();
+	fpu__init_task_struct_size();
 
 	fpu__init_system_ctx_switch();
 }
@@ -311,9 +356,15 @@
 
 	setup_clear_cpu_cap(X86_FEATURE_XSAVE);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVEOPT);
+	setup_clear_cpu_cap(X86_FEATURE_XSAVEC);
 	setup_clear_cpu_cap(X86_FEATURE_XSAVES);
 	setup_clear_cpu_cap(X86_FEATURE_AVX);
 	setup_clear_cpu_cap(X86_FEATURE_AVX2);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512F);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512PF);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512ER);
+	setup_clear_cpu_cap(X86_FEATURE_AVX512CD);
+	setup_clear_cpu_cap(X86_FEATURE_MPX);
 
 	return 1;
 }
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 5a46681..f129a9a 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -161,11 +161,12 @@
 	/* Kill off the identity-map trampoline */
 	reset_early_page_tables();
 
-	kasan_map_early_shadow(early_level4_pgt);
-
-	/* clear bss before set_intr_gate with early_idt_handler */
 	clear_bss();
 
+	clear_page(init_level4_pgt);
+
+	kasan_early_init();
+
 	for (i = 0; i < NUM_EXCEPTION_VECTORS; i++)
 		set_intr_gate(i, early_idt_handler_array[i]);
 	load_idt((const struct desc_ptr *)&idt_descr);
@@ -177,12 +178,9 @@
 	 */
 	load_ucode_bsp();
 
-	clear_page(init_level4_pgt);
 	/* set init_level4_pgt kernel high mapping*/
 	init_level4_pgt[511] = early_level4_pgt[511];
 
-	kasan_map_early_shadow(init_level4_pgt);
-
 	x86_64_start_reservations(real_mode_data);
 }
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index e5c27f7..1d40ca8 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -516,38 +516,9 @@
 	/* This must match the first entry in level2_kernel_pgt */
 	.quad   0x0000000000000000
 
-#ifdef CONFIG_KASAN
-#define FILL(VAL, COUNT)				\
-	.rept (COUNT) ;					\
-	.quad	(VAL) ;					\
-	.endr
-
-NEXT_PAGE(kasan_zero_pte)
-	FILL(kasan_zero_page - __START_KERNEL_map + _KERNPG_TABLE, 512)
-NEXT_PAGE(kasan_zero_pmd)
-	FILL(kasan_zero_pte - __START_KERNEL_map + _KERNPG_TABLE, 512)
-NEXT_PAGE(kasan_zero_pud)
-	FILL(kasan_zero_pmd - __START_KERNEL_map + _KERNPG_TABLE, 512)
-
-#undef FILL
-#endif
-
-
 #include "../../x86/xen/xen-head.S"
 	
 	__PAGE_ALIGNED_BSS
 NEXT_PAGE(empty_zero_page)
 	.skip PAGE_SIZE
 
-#ifdef CONFIG_KASAN
-/*
- * This page used as early shadow. We don't use empty_zero_page
- * at early stages, stack instrumentation could write some garbage
- * to this page.
- * Latter we reuse it as zero shadow for large ranges of memory
- * that allowed to access, but not instrumented by kasan
- * (vmalloc/vmemmap ...).
- */
-NEXT_PAGE(kasan_zero_page)
-	.skip PAGE_SIZE
-#endif
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 88b36648..c7dfe1b 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -347,14 +347,22 @@
 			if (!desc)
 				continue;
 
+			/*
+			 * Protect against concurrent action removal,
+			 * affinity changes etc.
+			 */
+			raw_spin_lock(&desc->lock);
 			data = irq_desc_get_irq_data(desc);
 			cpumask_copy(&affinity_new, data->affinity);
 			cpumask_clear_cpu(this_cpu, &affinity_new);
 
 			/* Do not count inactive or per-cpu irqs. */
-			if (!irq_has_action(irq) || irqd_is_per_cpu(data))
+			if (!irq_has_action(irq) || irqd_is_per_cpu(data)) {
+				raw_spin_unlock(&desc->lock);
 				continue;
+			}
 
+			raw_spin_unlock(&desc->lock);
 			/*
 			 * A single irq may be mapped to multiple
 			 * cpu's vector_irq[] (for example IOAPIC cluster
@@ -385,6 +393,9 @@
 		 * vector. If the vector is marked in the used vectors
 		 * bitmap or an irq is assigned to it, we don't count
 		 * it as available.
+		 *
+		 * As this is an inaccurate snapshot anyway, we can do
+		 * this w/o holding vector_lock.
 		 */
 		for (vector = FIRST_EXTERNAL_VECTOR;
 		     vector < first_system_vector; vector++) {
@@ -486,6 +497,11 @@
 	 */
 	mdelay(1);
 
+	/*
+	 * We can walk the vector array of this cpu without holding
+	 * vector_lock because the cpu is already marked !online, so
+	 * nothing else will touch it.
+	 */
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
 		unsigned int irr;
 
@@ -497,9 +513,9 @@
 			irq = __this_cpu_read(vector_irq[vector]);
 
 			desc = irq_to_desc(irq);
+			raw_spin_lock(&desc->lock);
 			data = irq_desc_get_irq_data(desc);
 			chip = irq_data_get_irq_chip(data);
-			raw_spin_lock(&desc->lock);
 			if (chip->irq_retrigger) {
 				chip->irq_retrigger(data);
 				__this_cpu_write(vector_irq[vector], VECTOR_RETRIGGERED);
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index c37886d7..2bcc052 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -12,6 +12,7 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
 
@@ -20,82 +21,82 @@
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
 
-#ifdef CONFIG_SMP
+/* context.lock is held for us, so we don't need any locking. */
 static void flush_ldt(void *current_mm)
 {
-	if (current->active_mm == current_mm)
-		load_LDT(&current->active_mm->context);
+	mm_context_t *pc;
+
+	if (current->active_mm != current_mm)
+		return;
+
+	pc = &current->active_mm->context;
+	set_ldt(pc->ldt->entries, pc->ldt->size);
 }
-#endif
 
-static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
+/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
+static struct ldt_struct *alloc_ldt_struct(int size)
 {
-	void *oldldt, *newldt;
-	int oldsize;
+	struct ldt_struct *new_ldt;
+	int alloc_size;
 
-	if (mincount <= pc->size)
-		return 0;
-	oldsize = pc->size;
-	mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) &
-			(~(PAGE_SIZE / LDT_ENTRY_SIZE - 1));
-	if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE)
-		newldt = vmalloc(mincount * LDT_ENTRY_SIZE);
+	if (size > LDT_ENTRIES)
+		return NULL;
+
+	new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL);
+	if (!new_ldt)
+		return NULL;
+
+	BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct));
+	alloc_size = size * LDT_ENTRY_SIZE;
+
+	/*
+	 * Xen is very picky: it requires a page-aligned LDT that has no
+	 * trailing nonzero bytes in any page that contains LDT descriptors.
+	 * Keep it simple: zero the whole allocation and never allocate less
+	 * than PAGE_SIZE.
+	 */
+	if (alloc_size > PAGE_SIZE)
+		new_ldt->entries = vzalloc(alloc_size);
 	else
-		newldt = (void *)__get_free_page(GFP_KERNEL);
+		new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL);
 
-	if (!newldt)
-		return -ENOMEM;
-
-	if (oldsize)
-		memcpy(newldt, pc->ldt, oldsize * LDT_ENTRY_SIZE);
-	oldldt = pc->ldt;
-	memset(newldt + oldsize * LDT_ENTRY_SIZE, 0,
-	       (mincount - oldsize) * LDT_ENTRY_SIZE);
-
-	paravirt_alloc_ldt(newldt, mincount);
-
-#ifdef CONFIG_X86_64
-	/* CHECKME: Do we really need this ? */
-	wmb();
-#endif
-	pc->ldt = newldt;
-	wmb();
-	pc->size = mincount;
-	wmb();
-
-	if (reload) {
-#ifdef CONFIG_SMP
-		preempt_disable();
-		load_LDT(pc);
-		if (!cpumask_equal(mm_cpumask(current->mm),
-				   cpumask_of(smp_processor_id())))
-			smp_call_function(flush_ldt, current->mm, 1);
-		preempt_enable();
-#else
-		load_LDT(pc);
-#endif
+	if (!new_ldt->entries) {
+		kfree(new_ldt);
+		return NULL;
 	}
-	if (oldsize) {
-		paravirt_free_ldt(oldldt, oldsize);
-		if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE)
-			vfree(oldldt);
-		else
-			put_page(virt_to_page(oldldt));
-	}
-	return 0;
+
+	new_ldt->size = size;
+	return new_ldt;
 }
 
-static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
+/* After calling this, the LDT is immutable. */
+static void finalize_ldt_struct(struct ldt_struct *ldt)
 {
-	int err = alloc_ldt(new, old->size, 0);
-	int i;
+	paravirt_alloc_ldt(ldt->entries, ldt->size);
+}
 
-	if (err < 0)
-		return err;
+/* context.lock is held */
+static void install_ldt(struct mm_struct *current_mm,
+			struct ldt_struct *ldt)
+{
+	/* Synchronizes with lockless_dereference in load_mm_ldt. */
+	smp_store_release(&current_mm->context.ldt, ldt);
 
-	for (i = 0; i < old->size; i++)
-		write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE);
-	return 0;
+	/* Activate the LDT for all CPUs using current_mm. */
+	on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true);
+}
+
+static void free_ldt_struct(struct ldt_struct *ldt)
+{
+	if (likely(!ldt))
+		return;
+
+	paravirt_free_ldt(ldt->entries, ldt->size);
+	if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
+		vfree(ldt->entries);
+	else
+		kfree(ldt->entries);
+	kfree(ldt);
 }
 
 /*
@@ -104,17 +105,37 @@
  */
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
+	struct ldt_struct *new_ldt;
 	struct mm_struct *old_mm;
 	int retval = 0;
 
 	mutex_init(&mm->context.lock);
-	mm->context.size = 0;
 	old_mm = current->mm;
-	if (old_mm && old_mm->context.size > 0) {
-		mutex_lock(&old_mm->context.lock);
-		retval = copy_ldt(&mm->context, &old_mm->context);
-		mutex_unlock(&old_mm->context.lock);
+	if (!old_mm) {
+		mm->context.ldt = NULL;
+		return 0;
 	}
+
+	mutex_lock(&old_mm->context.lock);
+	if (!old_mm->context.ldt) {
+		mm->context.ldt = NULL;
+		goto out_unlock;
+	}
+
+	new_ldt = alloc_ldt_struct(old_mm->context.ldt->size);
+	if (!new_ldt) {
+		retval = -ENOMEM;
+		goto out_unlock;
+	}
+
+	memcpy(new_ldt->entries, old_mm->context.ldt->entries,
+	       new_ldt->size * LDT_ENTRY_SIZE);
+	finalize_ldt_struct(new_ldt);
+
+	mm->context.ldt = new_ldt;
+
+out_unlock:
+	mutex_unlock(&old_mm->context.lock);
 	return retval;
 }
 
@@ -125,53 +146,47 @@
  */
 void destroy_context(struct mm_struct *mm)
 {
-	if (mm->context.size) {
-#ifdef CONFIG_X86_32
-		/* CHECKME: Can this ever happen ? */
-		if (mm == current->active_mm)
-			clear_LDT();
-#endif
-		paravirt_free_ldt(mm->context.ldt, mm->context.size);
-		if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE)
-			vfree(mm->context.ldt);
-		else
-			put_page(virt_to_page(mm->context.ldt));
-		mm->context.size = 0;
-	}
+	free_ldt_struct(mm->context.ldt);
+	mm->context.ldt = NULL;
 }
 
 static int read_ldt(void __user *ptr, unsigned long bytecount)
 {
-	int err;
+	int retval;
 	unsigned long size;
 	struct mm_struct *mm = current->mm;
 
-	if (!mm->context.size)
-		return 0;
+	mutex_lock(&mm->context.lock);
+
+	if (!mm->context.ldt) {
+		retval = 0;
+		goto out_unlock;
+	}
+
 	if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES)
 		bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES;
 
-	mutex_lock(&mm->context.lock);
-	size = mm->context.size * LDT_ENTRY_SIZE;
+	size = mm->context.ldt->size * LDT_ENTRY_SIZE;
 	if (size > bytecount)
 		size = bytecount;
 
-	err = 0;
-	if (copy_to_user(ptr, mm->context.ldt, size))
-		err = -EFAULT;
-	mutex_unlock(&mm->context.lock);
-	if (err < 0)
-		goto error_return;
+	if (copy_to_user(ptr, mm->context.ldt->entries, size)) {
+		retval = -EFAULT;
+		goto out_unlock;
+	}
+
 	if (size != bytecount) {
-		/* zero-fill the rest */
-		if (clear_user(ptr + size, bytecount - size) != 0) {
-			err = -EFAULT;
-			goto error_return;
+		/* Zero-fill the rest and pretend we read bytecount bytes. */
+		if (clear_user(ptr + size, bytecount - size)) {
+			retval = -EFAULT;
+			goto out_unlock;
 		}
 	}
-	return bytecount;
-error_return:
-	return err;
+	retval = bytecount;
+
+out_unlock:
+	mutex_unlock(&mm->context.lock);
+	return retval;
 }
 
 static int read_default_ldt(void __user *ptr, unsigned long bytecount)
@@ -195,6 +210,8 @@
 	struct desc_struct ldt;
 	int error;
 	struct user_desc ldt_info;
+	int oldsize, newsize;
+	struct ldt_struct *new_ldt, *old_ldt;
 
 	error = -EINVAL;
 	if (bytecount != sizeof(ldt_info))
@@ -213,34 +230,39 @@
 			goto out;
 	}
 
-	mutex_lock(&mm->context.lock);
-	if (ldt_info.entry_number >= mm->context.size) {
-		error = alloc_ldt(&current->mm->context,
-				  ldt_info.entry_number + 1, 1);
-		if (error < 0)
-			goto out_unlock;
-	}
-
-	/* Allow LDTs to be cleared by the user. */
-	if (ldt_info.base_addr == 0 && ldt_info.limit == 0) {
-		if (oldmode || LDT_empty(&ldt_info)) {
-			memset(&ldt, 0, sizeof(ldt));
-			goto install;
+	if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) ||
+	    LDT_empty(&ldt_info)) {
+		/* The user wants to clear the entry. */
+		memset(&ldt, 0, sizeof(ldt));
+	} else {
+		if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+			error = -EINVAL;
+			goto out;
 		}
+
+		fill_ldt(&ldt, &ldt_info);
+		if (oldmode)
+			ldt.avl = 0;
 	}
 
-	if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
-		error = -EINVAL;
+	mutex_lock(&mm->context.lock);
+
+	old_ldt = mm->context.ldt;
+	oldsize = old_ldt ? old_ldt->size : 0;
+	newsize = max((int)(ldt_info.entry_number + 1), oldsize);
+
+	error = -ENOMEM;
+	new_ldt = alloc_ldt_struct(newsize);
+	if (!new_ldt)
 		goto out_unlock;
-	}
 
-	fill_ldt(&ldt, &ldt_info);
-	if (oldmode)
-		ldt.avl = 0;
+	if (old_ldt)
+		memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE);
+	new_ldt->entries[ldt_info.entry_number] = ldt;
+	finalize_ldt_struct(new_ldt);
 
-	/* Install the new entry ...  */
-install:
-	write_ldt_entry(mm->context.ldt, ldt_info.entry_number, &ldt);
+	install_ldt(mm, new_ldt);
+	free_ldt_struct(old_ldt);
 	error = 0;
 
 out_unlock:
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index c3e985d..d05bd2e 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -408,15 +408,15 @@
 NOKPROBE_SYMBOL(default_do_nmi);
 
 /*
- * NMIs can hit breakpoints which will cause it to lose its
- * NMI context with the CPU when the breakpoint does an iret.
- */
-#ifdef CONFIG_X86_32
-/*
- * For i386, NMIs use the same stack as the kernel, and we can
- * add a workaround to the iret problem in C (preventing nested
- * NMIs if an NMI takes a trap). Simply have 3 states the NMI
- * can be in:
+ * NMIs can page fault or hit breakpoints which will cause it to lose
+ * its NMI context with the CPU when the breakpoint or page fault does an IRET.
+ *
+ * As a result, NMIs can nest if NMIs get unmasked due an IRET during
+ * NMI processing.  On x86_64, the asm glue protects us from nested NMIs
+ * if the outer NMI came from kernel mode, but we can still nest if the
+ * outer NMI came from user mode.
+ *
+ * To handle these nested NMIs, we have three states:
  *
  *  1) not running
  *  2) executing
@@ -430,15 +430,14 @@
  * (Note, the latch is binary, thus multiple NMIs triggering,
  *  when one is running, are ignored. Only one NMI is restarted.)
  *
- * If an NMI hits a breakpoint that executes an iret, another
- * NMI can preempt it. We do not want to allow this new NMI
- * to run, but we want to execute it when the first one finishes.
- * We set the state to "latched", and the exit of the first NMI will
- * perform a dec_return, if the result is zero (NOT_RUNNING), then
- * it will simply exit the NMI handler. If not, the dec_return
- * would have set the state to NMI_EXECUTING (what we want it to
- * be when we are running). In this case, we simply jump back
- * to rerun the NMI handler again, and restart the 'latched' NMI.
+ * If an NMI executes an iret, another NMI can preempt it. We do not
+ * want to allow this new NMI to run, but we want to execute it when the
+ * first one finishes.  We set the state to "latched", and the exit of
+ * the first NMI will perform a dec_return, if the result is zero
+ * (NOT_RUNNING), then it will simply exit the NMI handler. If not, the
+ * dec_return would have set the state to NMI_EXECUTING (what we want it
+ * to be when we are running). In this case, we simply jump back to
+ * rerun the NMI handler again, and restart the 'latched' NMI.
  *
  * No trap (breakpoint or page fault) should be hit before nmi_restart,
  * thus there is no race between the first check of state for NOT_RUNNING
@@ -461,49 +460,36 @@
 static DEFINE_PER_CPU(enum nmi_states, nmi_state);
 static DEFINE_PER_CPU(unsigned long, nmi_cr2);
 
-#define nmi_nesting_preprocess(regs)					\
-	do {								\
-		if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {	\
-			this_cpu_write(nmi_state, NMI_LATCHED);		\
-			return;						\
-		}							\
-		this_cpu_write(nmi_state, NMI_EXECUTING);		\
-		this_cpu_write(nmi_cr2, read_cr2());			\
-	} while (0);							\
-	nmi_restart:
-
-#define nmi_nesting_postprocess()					\
-	do {								\
-		if (unlikely(this_cpu_read(nmi_cr2) != read_cr2()))	\
-			write_cr2(this_cpu_read(nmi_cr2));		\
-		if (this_cpu_dec_return(nmi_state))			\
-			goto nmi_restart;				\
-	} while (0)
-#else /* x86_64 */
+#ifdef CONFIG_X86_64
 /*
- * In x86_64 things are a bit more difficult. This has the same problem
- * where an NMI hitting a breakpoint that calls iret will remove the
- * NMI context, allowing a nested NMI to enter. What makes this more
- * difficult is that both NMIs and breakpoints have their own stack.
- * When a new NMI or breakpoint is executed, the stack is set to a fixed
- * point. If an NMI is nested, it will have its stack set at that same
- * fixed address that the first NMI had, and will start corrupting the
- * stack. This is handled in entry_64.S, but the same problem exists with
- * the breakpoint stack.
+ * In x86_64, we need to handle breakpoint -> NMI -> breakpoint.  Without
+ * some care, the inner breakpoint will clobber the outer breakpoint's
+ * stack.
  *
- * If a breakpoint is being processed, and the debug stack is being used,
- * if an NMI comes in and also hits a breakpoint, the stack pointer
- * will be set to the same fixed address as the breakpoint that was
- * interrupted, causing that stack to be corrupted. To handle this case,
- * check if the stack that was interrupted is the debug stack, and if
- * so, change the IDT so that new breakpoints will use the current stack
- * and not switch to the fixed address. On return of the NMI, switch back
- * to the original IDT.
+ * If a breakpoint is being processed, and the debug stack is being
+ * used, if an NMI comes in and also hits a breakpoint, the stack
+ * pointer will be set to the same fixed address as the breakpoint that
+ * was interrupted, causing that stack to be corrupted. To handle this
+ * case, check if the stack that was interrupted is the debug stack, and
+ * if so, change the IDT so that new breakpoints will use the current
+ * stack and not switch to the fixed address. On return of the NMI,
+ * switch back to the original IDT.
  */
 static DEFINE_PER_CPU(int, update_debug_stack);
+#endif
 
-static inline void nmi_nesting_preprocess(struct pt_regs *regs)
+dotraplinkage notrace void
+do_nmi(struct pt_regs *regs, long error_code)
 {
+	if (this_cpu_read(nmi_state) != NMI_NOT_RUNNING) {
+		this_cpu_write(nmi_state, NMI_LATCHED);
+		return;
+	}
+	this_cpu_write(nmi_state, NMI_EXECUTING);
+	this_cpu_write(nmi_cr2, read_cr2());
+nmi_restart:
+
+#ifdef CONFIG_X86_64
 	/*
 	 * If we interrupted a breakpoint, it is possible that
 	 * the nmi handler will have breakpoints too. We need to
@@ -514,22 +500,8 @@
 		debug_stack_set_zero();
 		this_cpu_write(update_debug_stack, 1);
 	}
-}
-
-static inline void nmi_nesting_postprocess(void)
-{
-	if (unlikely(this_cpu_read(update_debug_stack))) {
-		debug_stack_reset();
-		this_cpu_write(update_debug_stack, 0);
-	}
-}
 #endif
 
-dotraplinkage notrace void
-do_nmi(struct pt_regs *regs, long error_code)
-{
-	nmi_nesting_preprocess(regs);
-
 	nmi_enter();
 
 	inc_irq_stat(__nmi_count);
@@ -539,8 +511,17 @@
 
 	nmi_exit();
 
-	/* On i386, may loop back to preprocess */
-	nmi_nesting_postprocess();
+#ifdef CONFIG_X86_64
+	if (unlikely(this_cpu_read(update_debug_stack))) {
+		debug_stack_reset();
+		this_cpu_write(update_debug_stack, 0);
+	}
+#endif
+
+	if (unlikely(this_cpu_read(nmi_cr2) != read_cr2()))
+		write_cr2(this_cpu_read(nmi_cr2));
+	if (this_cpu_dec_return(nmi_state))
+		goto nmi_restart;
 }
 NOKPROBE_SYMBOL(do_nmi);
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 9cad694..c27cad7 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -81,7 +81,7 @@
  */
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
-	*dst = *src;
+	memcpy(dst, src, arch_task_struct_size);
 
 	return fpu__copy(&dst->thread.fpu, &src->thread.fpu);
 }
@@ -408,6 +408,7 @@
 static void mwait_idle(void)
 {
 	if (!current_set_polling_and_test()) {
+		trace_cpu_idle_rcuidle(1, smp_processor_id());
 		if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
 			smp_mb(); /* quirk */
 			clflush((void *)&current_thread_info()->flags);
@@ -419,6 +420,7 @@
 			__sti_mwait(0, 0);
 		else
 			local_irq_enable();
+		trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 	} else {
 		local_irq_enable();
 	}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 71d7849..f6b9163 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -121,11 +121,11 @@
 void release_thread(struct task_struct *dead_task)
 {
 	if (dead_task->mm) {
-		if (dead_task->mm->context.size) {
+		if (dead_task->mm->context.ldt) {
 			pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
 				dead_task->comm,
 				dead_task->mm->context.ldt,
-				dead_task->mm->context.size);
+				dead_task->mm->context.ldt->size);
 			BUG();
 		}
 	}
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 206996c..71820c4 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -93,8 +93,15 @@
 		COPY(r15);
 #endif /* CONFIG_X86_64 */
 
+#ifdef CONFIG_X86_32
 		COPY_SEG_CPL3(cs);
 		COPY_SEG_CPL3(ss);
+#else /* !CONFIG_X86_32 */
+		/* Kernel saves and restores only the CS segment register on signals,
+		 * which is the bare minimum needed to allow mixed 32/64-bit code.
+		 * App's signal handler can save/restore other segments if needed. */
+		COPY_SEG_CPL3(cs);
+#endif /* CONFIG_X86_32 */
 
 		get_user_ex(tmpflags, &sc->flags);
 		regs->flags = (regs->flags & ~FIX_EFLAGS) | (tmpflags & FIX_EFLAGS);
@@ -154,9 +161,8 @@
 #else /* !CONFIG_X86_32 */
 		put_user_ex(regs->flags, &sc->flags);
 		put_user_ex(regs->cs, &sc->cs);
-		put_user_ex(0, &sc->__pad2);
-		put_user_ex(0, &sc->__pad1);
-		put_user_ex(regs->ss, &sc->ss);
+		put_user_ex(0, &sc->gs);
+		put_user_ex(0, &sc->fs);
 #endif /* CONFIG_X86_32 */
 
 		put_user_ex(fpstate, &sc->fpstate);
@@ -451,19 +457,9 @@
 
 	regs->sp = (unsigned long)frame;
 
-	/*
-	 * Set up the CS and SS registers to run signal handlers in
-	 * 64-bit mode, even if the handler happens to be interrupting
-	 * 32-bit or 16-bit code.
-	 *
-	 * SS is subtle.  In 64-bit mode, we don't need any particular
-	 * SS descriptor, but we do need SS to be valid.  It's possible
-	 * that the old SS is entirely bogus -- this can happen if the
-	 * signal we're trying to deliver is #GP or #SS caused by a bad
-	 * SS value.
-	 */
+	/* Set up the CS register to run signal handlers in 64-bit mode,
+	   even if the handler happens to be interrupting 32-bit code. */
 	regs->cs = __USER_CS;
-	regs->ss = __USER_DS;
 
 	return 0;
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 8add66b..b1f3ed9c 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -171,11 +171,6 @@
 	apic_ap_setup();
 
 	/*
-	 * Need to setup vector mappings before we enable interrupts.
-	 */
-	setup_vector_irq(smp_processor_id());
-
-	/*
 	 * Save our processor parameters. Note: this information
 	 * is needed for clock calibration.
 	 */
@@ -239,18 +234,13 @@
 	check_tsc_sync_target();
 
 	/*
-	 * Enable the espfix hack for this CPU
-	 */
-#ifdef CONFIG_X86_ESPFIX64
-	init_espfix_ap();
-#endif
-
-	/*
-	 * We need to hold vector_lock so there the set of online cpus
-	 * does not change while we are assigning vectors to cpus.  Holding
-	 * this lock ensures we don't half assign or remove an irq from a cpu.
+	 * Lock vector_lock and initialize the vectors on this cpu
+	 * before setting the cpu online. We must set it online with
+	 * vector_lock held to prevent a concurrent setup/teardown
+	 * from seeing a half valid vector space.
 	 */
 	lock_vector_lock();
+	setup_vector_irq(smp_processor_id());
 	set_cpu_online(smp_processor_id(), true);
 	unlock_vector_lock();
 	cpu_set_state_online(smp_processor_id());
@@ -854,6 +844,13 @@
 	initial_code = (unsigned long)start_secondary;
 	stack_start  = idle->thread.sp;
 
+	/*
+	 * Enable the espfix hack for this CPU
+	*/
+#ifdef CONFIG_X86_ESPFIX64
+	init_espfix_ap(cpu);
+#endif
+
 	/* So we see what's up */
 	announce_cpu(cpu, apicid);
 
@@ -995,8 +992,17 @@
 
 	common_cpu_up(cpu, tidle);
 
+	/*
+	 * We have to walk the irq descriptors to setup the vector
+	 * space for the cpu which comes online.  Prevent irq
+	 * alloc/free across the bringup.
+	 */
+	irq_lock_sparse();
+
 	err = do_boot_cpu(apicid, cpu, tidle);
+
 	if (err) {
+		irq_unlock_sparse();
 		pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu);
 		return -EIO;
 	}
@@ -1014,6 +1020,8 @@
 		touch_nmi_watchdog();
 	}
 
+	irq_unlock_sparse();
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 9b4d51d..0ccb53a 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -5,6 +5,7 @@
 #include <linux/mm.h>
 #include <linux/ptrace.h>
 #include <asm/desc.h>
+#include <asm/mmu_context.h>
 
 unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs)
 {
@@ -27,13 +28,14 @@
 		struct desc_struct *desc;
 		unsigned long base;
 
-		seg &= ~7UL;
+		seg >>= 3;
 
 		mutex_lock(&child->mm->context.lock);
-		if (unlikely((seg >> 3) >= child->mm->context.size))
+		if (unlikely(!child->mm->context.ldt ||
+			     seg >= child->mm->context.ldt->size))
 			addr = -1L; /* bogus selector, access would fault */
 		else {
-			desc = child->mm->context.ldt + seg;
+			desc = &child->mm->context.ldt->entries[seg];
 			base = get_desc_base(desc);
 
 			/* 16-bit code segment? */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 5054497..7437b41 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -598,10 +598,19 @@
 			if (!pit_expect_msb(0xff-i, &delta, &d2))
 				break;
 
+			delta -= tsc;
+
+			/*
+			 * Extrapolate the error and fail fast if the error will
+			 * never be below 500 ppm.
+			 */
+			if (i == 1 &&
+			    d1 + d2 >= (delta * MAX_QUICK_PIT_ITERATIONS) >> 11)
+				return 0;
+
 			/*
 			 * Iterate until the error is less than 500 ppm
 			 */
-			delta -= tsc;
 			if (d1+d2 >= delta >> 11)
 				continue;
 
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 64dd467..2fbea25 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -98,6 +98,8 @@
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
 
 	vcpu->arch.eager_fpu = use_eager_fpu() || guest_cpuid_has_mpx(vcpu);
+	if (vcpu->arch.eager_fpu)
+		kvm_x86_ops->fpu_activate(vcpu);
 
 	/*
 	 * The existing code assumes virtual address is 48-bit in the canonical
diff --git a/arch/x86/kvm/iommu.c b/arch/x86/kvm/iommu.c
index 7dbced3..5c520eb 100644
--- a/arch/x86/kvm/iommu.c
+++ b/arch/x86/kvm/iommu.c
@@ -200,6 +200,7 @@
 			goto out_unmap;
 	}
 
+	kvm_arch_start_assignment(kvm);
 	pci_set_dev_assigned(pdev);
 
 	dev_info(&pdev->dev, "kvm assign device\n");
@@ -224,6 +225,7 @@
 	iommu_detach_device(domain, &pdev->dev);
 
 	pci_clear_dev_assigned(pdev);
+	kvm_arch_end_assignment(kvm);
 
 	dev_info(&pdev->dev, "kvm deassign device\n");
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 954e98a..2a5ca97 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1595,7 +1595,7 @@
 	for (i = 0; i < APIC_LVT_NUM; i++)
 		apic_set_reg(apic, APIC_LVTT + 0x10 * i, APIC_LVT_MASKED);
 	apic_update_lvtt(apic);
-	if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_LINT0_REENABLED))
+	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_LINT0_REENABLED))
 		apic_set_reg(apic, APIC_LVT0,
 			     SET_APIC_DELIVERY_MODE(0, APIC_MODE_EXTINT));
 	apic_manage_nmi_watchdog(apic, kvm_apic_get_reg(apic, APIC_LVT0));
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index f807496..4417146 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -2479,6 +2479,14 @@
 	return 0;
 }
 
+static bool kvm_is_mmio_pfn(pfn_t pfn)
+{
+	if (pfn_valid(pfn))
+		return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn));
+
+	return true;
+}
+
 static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		    unsigned pte_access, int level,
 		    gfn_t gfn, pfn_t pfn, bool speculative,
@@ -2506,7 +2514,7 @@
 		spte |= PT_PAGE_SIZE_MASK;
 	if (tdp_enabled)
 		spte |= kvm_x86_ops->get_mt_mask(vcpu, gfn,
-			kvm_is_reserved_pfn(pfn));
+			kvm_is_mmio_pfn(pfn));
 
 	if (host_writable)
 		spte |= SPTE_HOST_WRITEABLE;
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index de1d2d8..9e8bf13 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -120,6 +120,16 @@
 	return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK;
 }
 
+static u8 mtrr_disabled_type(void)
+{
+	/*
+	 * Intel SDM 11.11.2.2: all MTRRs are disabled when
+	 * IA32_MTRR_DEF_TYPE.E bit is cleared, and the UC
+	 * memory type is applied to all of physical memory.
+	 */
+	return MTRR_TYPE_UNCACHABLE;
+}
+
 /*
 * Three terms are used in the following code:
 * - segment, it indicates the address segments covered by fixed MTRRs.
@@ -434,6 +444,8 @@
 
 	/* output fields. */
 	int mem_type;
+	/* mtrr is completely disabled? */
+	bool mtrr_disabled;
 	/* [start, end) is not fully covered in MTRRs? */
 	bool partial_map;
 
@@ -549,7 +561,7 @@
 static void mtrr_lookup_start(struct mtrr_iter *iter)
 {
 	if (!mtrr_is_enabled(iter->mtrr_state)) {
-		iter->partial_map = true;
+		iter->mtrr_disabled = true;
 		return;
 	}
 
@@ -563,6 +575,7 @@
 	iter->mtrr_state = mtrr_state;
 	iter->start = start;
 	iter->end = end;
+	iter->mtrr_disabled = false;
 	iter->partial_map = false;
 	iter->fixed = false;
 	iter->range = NULL;
@@ -656,15 +669,19 @@
 		return MTRR_TYPE_WRBACK;
 	}
 
-	/* It is not covered by MTRRs. */
-	if (iter.partial_map) {
-		/*
-		 * We just check one page, partially covered by MTRRs is
-		 * impossible.
-		 */
-		WARN_ON(type != -1);
-		type = mtrr_default_type(mtrr_state);
-	}
+	if (iter.mtrr_disabled)
+		return mtrr_disabled_type();
+
+	/* not contained in any MTRRs. */
+	if (type == -1)
+		return mtrr_default_type(mtrr_state);
+
+	/*
+	 * We just check one page, partially covered by MTRRs is
+	 * impossible.
+	 */
+	WARN_ON(iter.partial_map);
+
 	return type;
 }
 EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type);
@@ -689,6 +706,9 @@
 			return false;
 	}
 
+	if (iter.mtrr_disabled)
+		return true;
+
 	if (!iter.partial_map)
 		return true;
 
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 602b974..8e0c084 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -865,6 +865,64 @@
 	set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
 }
 
+#define MTRR_TYPE_UC_MINUS	7
+#define MTRR2PROTVAL_INVALID 0xff
+
+static u8 mtrr2protval[8];
+
+static u8 fallback_mtrr_type(int mtrr)
+{
+	/*
+	 * WT and WP aren't always available in the host PAT.  Treat
+	 * them as UC and UC- respectively.  Everything else should be
+	 * there.
+	 */
+	switch (mtrr)
+	{
+	case MTRR_TYPE_WRTHROUGH:
+		return MTRR_TYPE_UNCACHABLE;
+	case MTRR_TYPE_WRPROT:
+		return MTRR_TYPE_UC_MINUS;
+	default:
+		BUG();
+	}
+}
+
+static void build_mtrr2protval(void)
+{
+	int i;
+	u64 pat;
+
+	for (i = 0; i < 8; i++)
+		mtrr2protval[i] = MTRR2PROTVAL_INVALID;
+
+	/* Ignore the invalid MTRR types.  */
+	mtrr2protval[2] = 0;
+	mtrr2protval[3] = 0;
+
+	/*
+	 * Use host PAT value to figure out the mapping from guest MTRR
+	 * values to nested page table PAT/PCD/PWT values.  We do not
+	 * want to change the host PAT value every time we enter the
+	 * guest.
+	 */
+	rdmsrl(MSR_IA32_CR_PAT, pat);
+	for (i = 0; i < 8; i++) {
+		u8 mtrr = pat >> (8 * i);
+
+		if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID)
+			mtrr2protval[mtrr] = __cm_idx2pte(i);
+	}
+
+	for (i = 0; i < 8; i++) {
+		if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) {
+			u8 fallback = fallback_mtrr_type(i);
+			mtrr2protval[i] = mtrr2protval[fallback];
+			BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID);
+		}
+	}
+}
+
 static __init int svm_hardware_setup(void)
 {
 	int cpu;
@@ -931,6 +989,7 @@
 	} else
 		kvm_disable_tdp();
 
+	build_mtrr2protval();
 	return 0;
 
 err:
@@ -1085,6 +1144,39 @@
 	return target_tsc - tsc;
 }
 
+static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+
+	/* Unlike Intel, AMD takes the guest's CR0.CD into account.
+	 *
+	 * AMD does not have IPAT.  To emulate it for the case of guests
+	 * with no assigned devices, just set everything to WB.  If guests
+	 * have assigned devices, however, we cannot force WB for RAM
+	 * pages only, so use the guest PAT directly.
+	 */
+	if (!kvm_arch_has_assigned_device(vcpu->kvm))
+		*g_pat = 0x0606060606060606;
+	else
+		*g_pat = vcpu->arch.pat;
+}
+
+static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
+{
+	u8 mtrr;
+
+	/*
+	 * 1. MMIO: trust guest MTRR, so same as item 3.
+	 * 2. No passthrough: always map as WB, and force guest PAT to WB as well
+	 * 3. Passthrough: can't guarantee the result, try to trust guest.
+	 */
+	if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm))
+		return 0;
+
+	mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
+	return mtrr2protval[mtrr];
+}
+
 static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -1180,6 +1272,7 @@
 		clr_cr_intercept(svm, INTERCEPT_CR3_READ);
 		clr_cr_intercept(svm, INTERCEPT_CR3_WRITE);
 		save->g_pat = svm->vcpu.arch.pat;
+		svm_set_guest_pat(svm, &save->g_pat);
 		save->cr3 = 0;
 		save->cr4 = 0;
 	}
@@ -1579,7 +1672,7 @@
 	 * does not do it - this results in some delay at
 	 * reboot
 	 */
-	if (!(vcpu->kvm->arch.disabled_quirks & KVM_QUIRK_CD_NW_CLEARED))
+	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
 		cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
 	svm->vmcb->save.cr0 = cr0;
 	mark_dirty(svm->vmcb, VMCB_CR);
@@ -3254,6 +3347,16 @@
 	case MSR_VM_IGNNE:
 		vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
 		break;
+	case MSR_IA32_CR_PAT:
+		if (npt_enabled) {
+			if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
+				return 1;
+			vcpu->arch.pat = data;
+			svm_set_guest_pat(svm, &svm->vmcb->save.g_pat);
+			mark_dirty(svm->vmcb, VMCB_NPT);
+			break;
+		}
+		/* fall through */
 	default:
 		return kvm_set_msr_common(vcpu, msr);
 	}
@@ -4088,11 +4191,6 @@
 	return true;
 }
 
-static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
-{
-	return 0;
-}
-
 static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 {
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e856dd5..83b7b5c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8632,22 +8632,17 @@
 	u64 ipat = 0;
 
 	/* For VT-d and EPT combination
-	 * 1. MMIO: always map as UC
+	 * 1. MMIO: guest may want to apply WC, trust it.
 	 * 2. EPT with VT-d:
 	 *   a. VT-d without snooping control feature: can't guarantee the
-	 *	result, try to trust guest.
+	 *	result, try to trust guest.  So the same as item 1.
 	 *   b. VT-d with snooping control feature: snooping control feature of
 	 *	VT-d engine can guarantee the cache correctness. Just set it
 	 *	to WB to keep consistent with host. So the same as item 3.
 	 * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
 	 *    consistent with host MTRR
 	 */
-	if (is_mmio) {
-		cache = MTRR_TYPE_UNCACHABLE;
-		goto exit;
-	}
-
-	if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+	if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
 		ipat = VMX_EPT_IPAT_BIT;
 		cache = MTRR_TYPE_WRBACK;
 		goto exit;
@@ -8655,7 +8650,10 @@
 
 	if (kvm_read_cr0(vcpu) & X86_CR0_CD) {
 		ipat = VMX_EPT_IPAT_BIT;
-		cache = MTRR_TYPE_UNCACHABLE;
+		if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
+			cache = MTRR_TYPE_WRBACK;
+		else
+			cache = MTRR_TYPE_UNCACHABLE;
 		goto exit;
 	}
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index bbaf44e..8f0f6ec 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2105,7 +2105,7 @@
 		if (guest_cpuid_has_tsc_adjust(vcpu)) {
 			if (!msr_info->host_initiated) {
 				s64 adj = data - vcpu->arch.ia32_tsc_adjust_msr;
-				kvm_x86_ops->adjust_tsc_offset(vcpu, adj, true);
+				adjust_tsc_offset_guest(vcpu, adj);
 			}
 			vcpu->arch.ia32_tsc_adjust_msr = data;
 		}
@@ -3157,8 +3157,7 @@
 			cpuid_count(XSTATE_CPUID, index,
 				    &size, &offset, &ecx, &edx);
 			memcpy(dest, src + offset, size);
-		} else
-			WARN_ON_ONCE(1);
+		}
 
 		valid -= feature;
 	}
@@ -6328,6 +6327,7 @@
 static void process_smi(struct kvm_vcpu *vcpu)
 {
 	struct kvm_segment cs, ds;
+	struct desc_ptr dt;
 	char buf[512];
 	u32 cr0;
 
@@ -6360,6 +6360,10 @@
 
 	kvm_x86_ops->set_cr4(vcpu, 0);
 
+	/* Undocumented: IDT limit is set to zero on entry to SMM.  */
+	dt.address = dt.size = 0;
+	kvm_x86_ops->set_idt(vcpu, &dt);
+
 	__kvm_set_dr(vcpu, 7, DR7_FIXED_1);
 
 	cs.selector = (vcpu->arch.smbase >> 4) & 0xffff;
@@ -7315,11 +7319,6 @@
 
 	vcpu = kvm_x86_ops->vcpu_create(kvm, id);
 
-	/*
-	 * Activate fpu unconditionally in case the guest needs eager FPU.  It will be
-	 * deactivated soon if it doesn't.
-	 */
-	kvm_x86_ops->fpu_activate(vcpu);
 	return vcpu;
 }
 
@@ -8218,6 +8217,24 @@
 			kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
+void kvm_arch_start_assignment(struct kvm *kvm)
+{
+	atomic_inc(&kvm->arch.assigned_device_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_start_assignment);
+
+void kvm_arch_end_assignment(struct kvm *kvm)
+{
+	atomic_dec(&kvm->arch.assigned_device_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_end_assignment);
+
+bool kvm_arch_has_assigned_device(struct kvm *kvm)
+{
+	return atomic_read(&kvm->arch.assigned_device_count);
+}
+EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device);
+
 void kvm_arch_register_noncoherent_dma(struct kvm *kvm)
 {
 	atomic_inc(&kvm->arch.noncoherent_dma_count);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index edc8cdc..0ca2f3e 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -147,6 +147,11 @@
 	return kvm_register_write(vcpu, reg, val);
 }
 
+static inline bool kvm_check_has_quirk(struct kvm *kvm, u64 quirk)
+{
+	return !(kvm->arch.disabled_quirks & quirk);
+}
+
 void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_set_pending_timer(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index ddf9ecb..e342586 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -20,7 +20,7 @@
 	unsigned long ret;
 
 	if (__range_not_ok(from, n, TASK_SIZE))
-		return 0;
+		return n;
 
 	/*
 	 * Even though this function is typically called from NMI/IRQ context
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index f37e84a..3d8f2e4 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -29,7 +29,6 @@
 
 #include <asm/uaccess.h>
 #include <asm/traps.h>
-#include <asm/desc.h>
 #include <asm/user.h>
 #include <asm/fpu/internal.h>
 
@@ -181,7 +180,7 @@
 			math_abort(FPU_info, SIGILL);
 		}
 
-		code_descriptor = LDT_DESCRIPTOR(FPU_CS);
+		code_descriptor = FPU_get_ldt_descriptor(FPU_CS);
 		if (SEG_D_SIZE(code_descriptor)) {
 			/* The above test may be wrong, the book is not clear */
 			/* Segmented 32 bit protected mode */
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index 9ccecb6..5e044d5 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -16,9 +16,24 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 
-/* s is always from a cpu register, and the cpu does bounds checking
- * during register load --> no further bounds checks needed */
-#define LDT_DESCRIPTOR(s)	(((struct desc_struct *)current->mm->context.ldt)[(s) >> 3])
+#include <asm/desc.h>
+#include <asm/mmu_context.h>
+
+static inline struct desc_struct FPU_get_ldt_descriptor(unsigned seg)
+{
+	static struct desc_struct zero_desc;
+	struct desc_struct ret = zero_desc;
+
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	seg >>= 3;
+	mutex_lock(&current->mm->context.lock);
+	if (current->mm->context.ldt && seg < current->mm->context.ldt->size)
+		ret = current->mm->context.ldt->entries[seg];
+	mutex_unlock(&current->mm->context.lock);
+#endif
+	return ret;
+}
+
 #define SEG_D_SIZE(x)		((x).b & (3 << 21))
 #define SEG_G_BIT(x)		((x).b & (1 << 23))
 #define SEG_GRANULARITY(x)	(((x).b & (1 << 23)) ? 4096 : 1)
diff --git a/arch/x86/math-emu/get_address.c b/arch/x86/math-emu/get_address.c
index 6ef5e99..8300db7 100644
--- a/arch/x86/math-emu/get_address.c
+++ b/arch/x86/math-emu/get_address.c
@@ -20,7 +20,6 @@
 #include <linux/stddef.h>
 
 #include <asm/uaccess.h>
-#include <asm/desc.h>
 
 #include "fpu_system.h"
 #include "exception.h"
@@ -158,7 +157,7 @@
 		addr->selector = PM_REG_(segment);
 	}
 
-	descriptor = LDT_DESCRIPTOR(PM_REG_(segment));
+	descriptor = FPU_get_ldt_descriptor(addr->selector);
 	base_address = SEG_BASE_ADDR(descriptor);
 	address = base_address + offset;
 	limit = base_address
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index cc5ccc4..b9c78f3 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -63,8 +63,6 @@
 		    !PageReserved(pfn_to_page(start_pfn + i)))
 			return 1;
 
-	WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn);
-
 	return 0;
 }
 
@@ -94,7 +92,6 @@
 	pgprot_t prot;
 	int retval;
 	void __iomem *ret_addr;
-	int ram_region;
 
 	/* Don't allow wraparound or zero size */
 	last_addr = phys_addr + size - 1;
@@ -117,23 +114,15 @@
 	/*
 	 * Don't allow anybody to remap normal RAM that we're using..
 	 */
-	/* First check if whole region can be identified as RAM or not */
-	ram_region = region_is_ram(phys_addr, size);
-	if (ram_region > 0) {
-		WARN_ONCE(1, "ioremap on RAM at 0x%lx - 0x%lx\n",
-				(unsigned long int)phys_addr,
-				(unsigned long int)last_addr);
+	pfn      = phys_addr >> PAGE_SHIFT;
+	last_pfn = last_addr >> PAGE_SHIFT;
+	if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
+					  __ioremap_check_ram) == 1) {
+		WARN_ONCE(1, "ioremap on RAM at %pa - %pa\n",
+			  &phys_addr, &last_addr);
 		return NULL;
 	}
 
-	/* If could not be identified(-1), check page by page */
-	if (ram_region < 0) {
-		pfn      = phys_addr >> PAGE_SHIFT;
-		last_pfn = last_addr >> PAGE_SHIFT;
-		if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL,
-					  __ioremap_check_ram) == 1)
-			return NULL;
-	}
 	/*
 	 * Mappings have to be page-aligned
 	 */
diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c
index 4860906..e1840f3 100644
--- a/arch/x86/mm/kasan_init_64.c
+++ b/arch/x86/mm/kasan_init_64.c
@@ -1,3 +1,4 @@
+#define pr_fmt(fmt) "kasan: " fmt
 #include <linux/bootmem.h>
 #include <linux/kasan.h>
 #include <linux/kdebug.h>
@@ -11,7 +12,19 @@
 extern pgd_t early_level4_pgt[PTRS_PER_PGD];
 extern struct range pfn_mapped[E820_X_MAX];
 
-extern unsigned char kasan_zero_page[PAGE_SIZE];
+static pud_t kasan_zero_pud[PTRS_PER_PUD] __page_aligned_bss;
+static pmd_t kasan_zero_pmd[PTRS_PER_PMD] __page_aligned_bss;
+static pte_t kasan_zero_pte[PTRS_PER_PTE] __page_aligned_bss;
+
+/*
+ * This page used as early shadow. We don't use empty_zero_page
+ * at early stages, stack instrumentation could write some garbage
+ * to this page.
+ * Latter we reuse it as zero shadow for large ranges of memory
+ * that allowed to access, but not instrumented by kasan
+ * (vmalloc/vmemmap ...).
+ */
+static unsigned char kasan_zero_page[PAGE_SIZE] __page_aligned_bss;
 
 static int __init map_range(struct range *range)
 {
@@ -36,7 +49,7 @@
 		pgd_clear(pgd_offset_k(start));
 }
 
-void __init kasan_map_early_shadow(pgd_t *pgd)
+static void __init kasan_map_early_shadow(pgd_t *pgd)
 {
 	int i;
 	unsigned long start = KASAN_SHADOW_START;
@@ -73,7 +86,7 @@
 	while (IS_ALIGNED(addr, PMD_SIZE) && addr + PMD_SIZE <= end) {
 		WARN_ON(!pmd_none(*pmd));
 		set_pmd(pmd, __pmd(__pa_nodebug(kasan_zero_pte)
-					| __PAGE_KERNEL_RO));
+					| _KERNPG_TABLE));
 		addr += PMD_SIZE;
 		pmd = pmd_offset(pud, addr);
 	}
@@ -99,7 +112,7 @@
 	while (IS_ALIGNED(addr, PUD_SIZE) && addr + PUD_SIZE <= end) {
 		WARN_ON(!pud_none(*pud));
 		set_pud(pud, __pud(__pa_nodebug(kasan_zero_pmd)
-					| __PAGE_KERNEL_RO));
+					| _KERNPG_TABLE));
 		addr += PUD_SIZE;
 		pud = pud_offset(pgd, addr);
 	}
@@ -124,7 +137,7 @@
 	while (IS_ALIGNED(addr, PGDIR_SIZE) && addr + PGDIR_SIZE <= end) {
 		WARN_ON(!pgd_none(*pgd));
 		set_pgd(pgd, __pgd(__pa_nodebug(kasan_zero_pud)
-					| __PAGE_KERNEL_RO));
+					| _KERNPG_TABLE));
 		addr += PGDIR_SIZE;
 		pgd = pgd_offset_k(addr);
 	}
@@ -166,6 +179,26 @@
 };
 #endif
 
+void __init kasan_early_init(void)
+{
+	int i;
+	pteval_t pte_val = __pa_nodebug(kasan_zero_page) | __PAGE_KERNEL;
+	pmdval_t pmd_val = __pa_nodebug(kasan_zero_pte) | _KERNPG_TABLE;
+	pudval_t pud_val = __pa_nodebug(kasan_zero_pmd) | _KERNPG_TABLE;
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		kasan_zero_pte[i] = __pte(pte_val);
+
+	for (i = 0; i < PTRS_PER_PMD; i++)
+		kasan_zero_pmd[i] = __pmd(pmd_val);
+
+	for (i = 0; i < PTRS_PER_PUD; i++)
+		kasan_zero_pud[i] = __pud(pud_val);
+
+	kasan_map_early_shadow(early_level4_pgt);
+	kasan_map_early_shadow(init_level4_pgt);
+}
+
 void __init kasan_init(void)
 {
 	int i;
@@ -176,6 +209,7 @@
 
 	memcpy(early_level4_pgt, init_level4_pgt, sizeof(early_level4_pgt));
 	load_cr3(early_level4_pgt);
+	__flush_tlb_all();
 
 	clear_pgds(KASAN_SHADOW_START, KASAN_SHADOW_END);
 
@@ -202,5 +236,8 @@
 	memset(kasan_zero_page, 0, PAGE_SIZE);
 
 	load_cr3(init_level4_pgt);
+	__flush_tlb_all();
 	init_task.kasan_depth = 0;
+
+	pr_info("Kernel address sanitizer initialized\n");
 }
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 9d518d6..844b06d 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -126,3 +126,10 @@
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 	}
 }
+
+const char *arch_vma_name(struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_MPX)
+		return "[mpx]";
+	return NULL;
+}
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 7a657f5..db1b0bc 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -20,20 +20,6 @@
 #define CREATE_TRACE_POINTS
 #include <asm/trace/mpx.h>
 
-static const char *mpx_mapping_name(struct vm_area_struct *vma)
-{
-	return "[mpx]";
-}
-
-static struct vm_operations_struct mpx_vma_ops = {
-	.name = mpx_mapping_name,
-};
-
-static int is_mpx_vma(struct vm_area_struct *vma)
-{
-	return (vma->vm_ops == &mpx_vma_ops);
-}
-
 static inline unsigned long mpx_bd_size_bytes(struct mm_struct *mm)
 {
 	if (is_64bit_mm(mm))
@@ -53,9 +39,6 @@
 /*
  * This is really a simplified "vm_mmap". it only handles MPX
  * bounds tables (the bounds directory is user-allocated).
- *
- * Later on, we use the vma->vm_ops to uniquely identify these
- * VMAs.
  */
 static unsigned long mpx_mmap(unsigned long len)
 {
@@ -101,7 +84,6 @@
 		ret = -ENOMEM;
 		goto out;
 	}
-	vma->vm_ops = &mpx_vma_ops;
 
 	if (vm_flags & VM_LOCKED) {
 		up_write(&mm->mmap_sem);
@@ -812,7 +794,7 @@
 		 * so stop immediately and return an error.  This
 		 * probably results in a SIGSEGV.
 		 */
-		if (!is_mpx_vma(vma))
+		if (!(vma->vm_flags & VM_MPX))
 			return -EINVAL;
 
 		len = min(vma->vm_end, end) - addr;
@@ -945,9 +927,9 @@
 	 * lots of tables even though we have no actual table
 	 * entries in use.
 	 */
-	while (next && is_mpx_vma(next))
+	while (next && (next->vm_flags & VM_MPX))
 		next = next->vm_next;
-	while (prev && is_mpx_vma(prev))
+	while (prev && (prev->vm_flags & VM_MPX))
 		prev = prev->vm_prev;
 	/*
 	 * We know 'start' and 'end' lie within an area controlled
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 3250f23..90b924a 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -117,7 +117,7 @@
 		} else {
 			unsigned long addr;
 			unsigned long nr_pages =
-				f->flush_end - f->flush_start / PAGE_SIZE;
+				(f->flush_end - f->flush_start) / PAGE_SIZE;
 			addr = f->flush_start;
 			while (addr < f->flush_end) {
 				__flush_tlb_single(addr);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 579a8fd..be2e7a2 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -269,7 +269,7 @@
 	EMIT4(0x48, 0x8B, 0x46,                   /* mov rax, qword ptr [rsi + 16] */
 	      offsetof(struct bpf_array, map.max_entries));
 	EMIT3(0x48, 0x39, 0xD0);                  /* cmp rax, rdx */
-#define OFFSET1 44 /* number of bytes to jump */
+#define OFFSET1 47 /* number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
 	label1 = cnt;
 
@@ -278,15 +278,15 @@
 	 */
 	EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 33
+#define OFFSET2 36
 	EMIT2(X86_JA, OFFSET2);                   /* ja out */
 	label2 = cnt;
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
 	EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */
 
 	/* prog = array->prog[index]; */
-	EMIT4(0x48, 0x8D, 0x44, 0xD6);            /* lea rax, [rsi + rdx * 8 + 0x50] */
-	EMIT1(offsetof(struct bpf_array, prog));
+	EMIT4_off32(0x48, 0x8D, 0x84, 0xD6,       /* lea rax, [rsi + rdx * 8 + offsetof(...)] */
+		    offsetof(struct bpf_array, prog));
 	EMIT3(0x48, 0x8B, 0x00);                  /* mov rax, qword ptr [rax] */
 
 	/* if (prog == NULL)
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index cfba30f..e4308fe 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -972,6 +972,11 @@
 
 static int __init arch_parse_efi_cmdline(char *str)
 {
+	if (!str) {
+		pr_warn("need at least one option\n");
+		return -EINVAL;
+	}
+
 	if (parse_option_str(str, "old_map"))
 		set_bit(EFI_OLD_MEMMAP, &efi.flags);
 	if (parse_option_str(str, "debug"))
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 0d7dd1f..9ab5279 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -22,6 +22,7 @@
 #include <asm/fpu/internal.h>
 #include <asm/debugreg.h>
 #include <asm/cpu.h>
+#include <asm/mmu_context.h>
 
 #ifdef CONFIG_X86_32
 __visible unsigned long saved_context_ebx;
@@ -153,7 +154,7 @@
 	syscall_init();				/* This sets MSR_*STAR and related */
 #endif
 	load_TR_desc();				/* This does ltr */
-	load_LDT(&current->active_mm->context);	/* This does lldt */
+	load_mm_ldt(current->active_mm);	/* This does lldt */
 
 	fpu__resume_cpu();
 }
diff --git a/arch/x86/xen/Kconfig b/arch/x86/xen/Kconfig
index e88fda8..4841453 100644
--- a/arch/x86/xen/Kconfig
+++ b/arch/x86/xen/Kconfig
@@ -8,7 +8,7 @@
 	select PARAVIRT_CLOCK
 	select XEN_HAVE_PVMMU
 	depends on X86_64 || (X86_32 && X86_PAE)
-	depends on X86_TSC
+	depends on X86_LOCAL_APIC && X86_TSC
 	help
 	  This is the Linux Xen port.  Enabling this will allow the
 	  kernel to boot in a paravirtualized environment under the
@@ -17,7 +17,7 @@
 config XEN_DOM0
 	def_bool y
 	depends on XEN && PCI_XEN && SWIOTLB_XEN
-	depends on X86_LOCAL_APIC && X86_IO_APIC && ACPI && PCI
+	depends on X86_IO_APIC && ACPI && PCI
 
 config XEN_PVHVM
 	def_bool y
diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile
index 7322755..4b6e29a 100644
--- a/arch/x86/xen/Makefile
+++ b/arch/x86/xen/Makefile
@@ -13,13 +13,13 @@
 obj-y		:= enlighten.o setup.o multicalls.o mmu.o irq.o \
 			time.o xen-asm.o xen-asm_$(BITS).o \
 			grant-table.o suspend.o platform-pci-unplug.o \
-			p2m.o
+			p2m.o apic.o
 
 obj-$(CONFIG_EVENT_TRACING) += trace.o
 
 obj-$(CONFIG_SMP)		+= smp.o
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o
 obj-$(CONFIG_XEN_DEBUG_FS)	+= debugfs.o
-obj-$(CONFIG_XEN_DOM0)		+= apic.o vga.o
+obj-$(CONFIG_XEN_DOM0)		+= vga.o
 obj-$(CONFIG_SWIOTLB_XEN)	+= pci-swiotlb-xen.o
 obj-$(CONFIG_XEN_EFI)		+= efi.o
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0b95c9b..11d6fb4 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -483,6 +483,7 @@
 	pte_t pte;
 	unsigned long pfn;
 	struct page *page;
+	unsigned char dummy;
 
 	ptep = lookup_address((unsigned long)v, &level);
 	BUG_ON(ptep == NULL);
@@ -492,6 +493,32 @@
 
 	pte = pfn_pte(pfn, prot);
 
+	/*
+	 * Careful: update_va_mapping() will fail if the virtual address
+	 * we're poking isn't populated in the page tables.  We don't
+	 * need to worry about the direct map (that's always in the page
+	 * tables), but we need to be careful about vmap space.  In
+	 * particular, the top level page table can lazily propagate
+	 * entries between processes, so if we've switched mms since we
+	 * vmapped the target in the first place, we might not have the
+	 * top-level page table entry populated.
+	 *
+	 * We disable preemption because we want the same mm active when
+	 * we probe the target and when we issue the hypercall.  We'll
+	 * have the same nominal mm, but if we're a kernel thread, lazy
+	 * mm dropping could change our pgd.
+	 *
+	 * Out of an abundance of caution, this uses __get_user() to fault
+	 * in the target address just in case there's some obscure case
+	 * in which the target address isn't readable.
+	 */
+
+	preempt_disable();
+
+	pagefault_disable();	/* Avoid warnings due to being atomic. */
+	__get_user(dummy, (unsigned char __user __force *)v);
+	pagefault_enable();
+
 	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
 		BUG();
 
@@ -503,6 +530,8 @@
 				BUG();
 	} else
 		kmap_flush_unused();
+
+	preempt_enable();
 }
 
 static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
@@ -510,6 +539,17 @@
 	const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
 	int i;
 
+	/*
+	 * We need to mark the all aliases of the LDT pages RO.  We
+	 * don't need to call vm_flush_aliases(), though, since that's
+	 * only responsible for flushing aliases out the TLBs, not the
+	 * page tables, and Xen will flush the TLB for us if needed.
+	 *
+	 * To avoid confusing future readers: none of this is necessary
+	 * to load the LDT.  The hypervisor only checks this when the
+	 * LDT is faulted in due to subsequent descriptor access.
+	 */
+
 	for(i = 0; i < entries; i += entries_per_page)
 		set_aliased_prot(ldt + i, PAGE_KERNEL_RO);
 }
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index c20fe29..2292721 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -101,17 +101,15 @@
 
 #ifdef CONFIG_XEN_DOM0
 void __init xen_init_vga(const struct dom0_vga_console_info *, size_t size);
-void __init xen_init_apic(void);
 #else
 static inline void __init xen_init_vga(const struct dom0_vga_console_info *info,
 				       size_t size)
 {
 }
-static inline void __init xen_init_apic(void)
-{
-}
 #endif
 
+void __init xen_init_apic(void);
+
 #ifdef CONFIG_XEN_EFI
 extern void xen_efi_init(void);
 #else
diff --git a/arch/xtensa/include/asm/Kbuild b/arch/xtensa/include/asm/Kbuild
index 14d15bf..5b478ac 100644
--- a/arch/xtensa/include/asm/Kbuild
+++ b/arch/xtensa/include/asm/Kbuild
@@ -19,6 +19,7 @@
 generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
+generic-y += mm-arch-hooks.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += resource.h
diff --git a/arch/xtensa/include/asm/mm-arch-hooks.h b/arch/xtensa/include/asm/mm-arch-hooks.h
deleted file mode 100644
index d2e5cfd..0000000
--- a/arch/xtensa/include/asm/mm-arch-hooks.h
+++ /dev/null
@@ -1,15 +0,0 @@
-/*
- * Architecture specific mm hooks
- *
- * Copyright (C) 2015, IBM Corporation
- * Author: Laurent Dufour <ldufour@linux.vnet.ibm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef _ASM_XTENSA_MM_ARCH_HOOKS_H
-#define _ASM_XTENSA_MM_ARCH_HOOKS_H
-
-#endif /* _ASM_XTENSA_MM_ARCH_HOOKS_H */
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 0436c21..719b715 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -51,7 +51,7 @@
 	unsigned long idx = BIO_POOL_NONE;
 	unsigned inline_vecs;
 
-	if (!bs) {
+	if (!bs || !bs->bio_integrity_pool) {
 		bip = kmalloc(sizeof(struct bio_integrity_payload) +
 			      sizeof(struct bio_vec) * nr_vecs, gfp_mask);
 		inline_vecs = nr_vecs;
@@ -104,7 +104,7 @@
 		kfree(page_address(bip->bip_vec->bv_page) +
 		      bip->bip_vec->bv_offset);
 
-	if (bs) {
+	if (bs && bs->bio_integrity_pool) {
 		if (bip->bip_slab != BIO_POOL_NONE)
 			bvec_free(bs->bvec_integrity_pool, bip->bip_vec,
 				  bip->bip_slab);
diff --git a/block/bio.c b/block/bio.c
index 2a00d34..d6e5ba3 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1831,8 +1831,9 @@
  * Allocates and returns a new bio which represents @sectors from the start of
  * @bio, and updates @bio to represent the remaining sectors.
  *
- * The newly allocated bio will point to @bio's bi_io_vec; it is the caller's
- * responsibility to ensure that @bio is not freed before the split.
+ * Unless this is a discard request the newly allocated bio will point
+ * to @bio's bi_io_vec; it is the caller's responsibility to ensure that
+ * @bio is not freed before the split.
  */
 struct bio *bio_split(struct bio *bio, int sectors,
 		      gfp_t gfp, struct bio_set *bs)
@@ -1842,7 +1843,15 @@
 	BUG_ON(sectors <= 0);
 	BUG_ON(sectors >= bio_sectors(bio));
 
-	split = bio_clone_fast(bio, gfp, bs);
+	/*
+	 * Discards need a mutable bio_vec to accommodate the payload
+	 * required by the DSM TRIM and UNMAP commands.
+	 */
+	if (bio->bi_rw & REQ_DISCARD)
+		split = bio_clone_bioset(bio, gfp, bs);
+	else
+		split = bio_clone_fast(bio, gfp, bs);
+
 	if (!split)
 		return NULL;
 
@@ -2009,6 +2018,7 @@
 	bio->bi_css = blkcg_css;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(bio_associate_blkcg);
 
 /**
  * bio_associate_current - associate a bio with %current
@@ -2039,6 +2049,7 @@
 	bio->bi_css = task_get_css(current, blkio_cgrp_id);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(bio_associate_current);
 
 /**
  * bio_disassociate_task - undo bio_associate_current()
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 9f97da5..d6283b3 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -29,6 +29,14 @@
 
 #define MAX_KEY_LEN 100
 
+/*
+ * blkcg_pol_mutex protects blkcg_policy[] and policy [de]activation.
+ * blkcg_pol_register_mutex nests outside of it and synchronizes entire
+ * policy [un]register operations including cgroup file additions /
+ * removals.  Putting cgroup file registration outside blkcg_pol_mutex
+ * allows grabbing it from cgroup callbacks.
+ */
+static DEFINE_MUTEX(blkcg_pol_register_mutex);
 static DEFINE_MUTEX(blkcg_pol_mutex);
 
 struct blkcg blkcg_root;
@@ -38,6 +46,8 @@
 
 static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
 
+static LIST_HEAD(all_blkcgs);		/* protected by blkcg_pol_mutex */
+
 static bool blkcg_policy_enabled(struct request_queue *q,
 				 const struct blkcg_policy *pol)
 {
@@ -453,20 +463,7 @@
 	struct blkcg_gq *blkg;
 	int i;
 
-	/*
-	 * XXX: We invoke cgroup_add/rm_cftypes() under blkcg_pol_mutex
-	 * which ends up putting cgroup's internal cgroup_tree_mutex under
-	 * it; however, cgroup_tree_mutex is nested above cgroup file
-	 * active protection and grabbing blkcg_pol_mutex from a cgroup
-	 * file operation creates a possible circular dependency.  cgroup
-	 * internal locking is planned to go through further simplification
-	 * and this issue should go away soon.  For now, let's trylock
-	 * blkcg_pol_mutex and restart the write on failure.
-	 *
-	 * http://lkml.kernel.org/g/5363C04B.4010400@oracle.com
-	 */
-	if (!mutex_trylock(&blkcg_pol_mutex))
-		return restart_syscall();
+	mutex_lock(&blkcg_pol_mutex);
 	spin_lock_irq(&blkcg->lock);
 
 	/*
@@ -721,8 +718,12 @@
 		return -EINVAL;
 
 	disk = get_gendisk(MKDEV(major, minor), &part);
-	if (!disk || part)
+	if (!disk)
 		return -EINVAL;
+	if (part) {
+		put_disk(disk);
+		return -EINVAL;
+	}
 
 	rcu_read_lock();
 	spin_lock_irq(disk->queue->queue_lock);
@@ -822,8 +823,17 @@
 {
 	struct blkcg *blkcg = css_to_blkcg(css);
 
-	if (blkcg != &blkcg_root)
+	mutex_lock(&blkcg_pol_mutex);
+	list_del(&blkcg->all_blkcgs_node);
+	mutex_unlock(&blkcg_pol_mutex);
+
+	if (blkcg != &blkcg_root) {
+		int i;
+
+		for (i = 0; i < BLKCG_MAX_POLS; i++)
+			kfree(blkcg->pd[i]);
 		kfree(blkcg);
+	}
 }
 
 static struct cgroup_subsys_state *
@@ -833,6 +843,8 @@
 	struct cgroup_subsys_state *ret;
 	int i;
 
+	mutex_lock(&blkcg_pol_mutex);
+
 	if (!parent_css) {
 		blkcg = &blkcg_root;
 		goto done;
@@ -875,14 +887,17 @@
 #ifdef CONFIG_CGROUP_WRITEBACK
 	INIT_LIST_HEAD(&blkcg->cgwb_list);
 #endif
+	list_add_tail(&blkcg->all_blkcgs_node, &all_blkcgs);
+
+	mutex_unlock(&blkcg_pol_mutex);
 	return &blkcg->css;
 
 free_pd_blkcg:
 	for (i--; i >= 0; i--)
 		kfree(blkcg->pd[i]);
-
 free_blkcg:
 	kfree(blkcg);
+	mutex_unlock(&blkcg_pol_mutex);
 	return ret;
 }
 
@@ -1037,10 +1052,8 @@
 			  const struct blkcg_policy *pol)
 {
 	LIST_HEAD(pds);
-	LIST_HEAD(cpds);
 	struct blkcg_gq *blkg;
 	struct blkg_policy_data *pd, *nd;
-	struct blkcg_policy_data *cpd, *cnd;
 	int cnt = 0, ret;
 
 	if (blkcg_policy_enabled(q, pol))
@@ -1053,10 +1066,7 @@
 		cnt++;
 	spin_unlock_irq(q->queue_lock);
 
-	/*
-	 * Allocate per-blkg and per-blkcg policy data
-	 * for all existing blkgs.
-	 */
+	/* allocate per-blkg policy data for all existing blkgs */
 	while (cnt--) {
 		pd = kzalloc_node(pol->pd_size, GFP_KERNEL, q->node);
 		if (!pd) {
@@ -1064,15 +1074,6 @@
 			goto out_free;
 		}
 		list_add_tail(&pd->alloc_node, &pds);
-
-		if (!pol->cpd_size)
-			continue;
-		cpd = kzalloc_node(pol->cpd_size, GFP_KERNEL, q->node);
-		if (!cpd) {
-			ret = -ENOMEM;
-			goto out_free;
-		}
-		list_add_tail(&cpd->alloc_node, &cpds);
 	}
 
 	/*
@@ -1082,32 +1083,17 @@
 	spin_lock_irq(q->queue_lock);
 
 	list_for_each_entry(blkg, &q->blkg_list, q_node) {
-		if (WARN_ON(list_empty(&pds)) ||
-		    WARN_ON(pol->cpd_size && list_empty(&cpds))) {
+		if (WARN_ON(list_empty(&pds))) {
 			/* umm... this shouldn't happen, just abort */
 			ret = -ENOMEM;
 			goto out_unlock;
 		}
-		cpd = list_first_entry(&cpds, struct blkcg_policy_data,
-				       alloc_node);
-		list_del_init(&cpd->alloc_node);
 		pd = list_first_entry(&pds, struct blkg_policy_data, alloc_node);
 		list_del_init(&pd->alloc_node);
 
 		/* grab blkcg lock too while installing @pd on @blkg */
 		spin_lock(&blkg->blkcg->lock);
 
-		if (!pol->cpd_size)
-			goto no_cpd;
-		if (!blkg->blkcg->pd[pol->plid]) {
-			/* Per-policy per-blkcg data */
-			blkg->blkcg->pd[pol->plid] = cpd;
-			cpd->plid = pol->plid;
-			pol->cpd_init_fn(blkg->blkcg);
-		} else { /* must free it as it has already been extracted */
-			kfree(cpd);
-		}
-no_cpd:
 		blkg->pd[pol->plid] = pd;
 		pd->blkg = blkg;
 		pd->plid = pol->plid;
@@ -1124,8 +1110,6 @@
 	blk_queue_bypass_end(q);
 	list_for_each_entry_safe(pd, nd, &pds, alloc_node)
 		kfree(pd);
-	list_for_each_entry_safe(cpd, cnd, &cpds, alloc_node)
-		kfree(cpd);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blkcg_activate_policy);
@@ -1162,8 +1146,6 @@
 
 		kfree(blkg->pd[pol->plid]);
 		blkg->pd[pol->plid] = NULL;
-		kfree(blkg->blkcg->pd[pol->plid]);
-		blkg->blkcg->pd[pol->plid] = NULL;
 
 		spin_unlock(&blkg->blkcg->lock);
 	}
@@ -1182,11 +1164,13 @@
  */
 int blkcg_policy_register(struct blkcg_policy *pol)
 {
+	struct blkcg *blkcg;
 	int i, ret;
 
 	if (WARN_ON(pol->pd_size < sizeof(struct blkg_policy_data)))
 		return -EINVAL;
 
+	mutex_lock(&blkcg_pol_register_mutex);
 	mutex_lock(&blkcg_pol_mutex);
 
 	/* find an empty slot */
@@ -1195,19 +1179,49 @@
 		if (!blkcg_policy[i])
 			break;
 	if (i >= BLKCG_MAX_POLS)
-		goto out_unlock;
+		goto err_unlock;
 
-	/* register and update blkgs */
+	/* register @pol */
 	pol->plid = i;
-	blkcg_policy[i] = pol;
+	blkcg_policy[pol->plid] = pol;
+
+	/* allocate and install cpd's */
+	if (pol->cpd_size) {
+		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
+			struct blkcg_policy_data *cpd;
+
+			cpd = kzalloc(pol->cpd_size, GFP_KERNEL);
+			if (!cpd) {
+				mutex_unlock(&blkcg_pol_mutex);
+				goto err_free_cpds;
+			}
+
+			blkcg->pd[pol->plid] = cpd;
+			cpd->plid = pol->plid;
+			pol->cpd_init_fn(blkcg);
+		}
+	}
+
+	mutex_unlock(&blkcg_pol_mutex);
 
 	/* everything is in place, add intf files for the new policy */
 	if (pol->cftypes)
 		WARN_ON(cgroup_add_legacy_cftypes(&blkio_cgrp_subsys,
 						  pol->cftypes));
-	ret = 0;
-out_unlock:
+	mutex_unlock(&blkcg_pol_register_mutex);
+	return 0;
+
+err_free_cpds:
+	if (pol->cpd_size) {
+		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
+			kfree(blkcg->pd[pol->plid]);
+			blkcg->pd[pol->plid] = NULL;
+		}
+	}
+	blkcg_policy[pol->plid] = NULL;
+err_unlock:
 	mutex_unlock(&blkcg_pol_mutex);
+	mutex_unlock(&blkcg_pol_register_mutex);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(blkcg_policy_register);
@@ -1220,7 +1234,9 @@
  */
 void blkcg_policy_unregister(struct blkcg_policy *pol)
 {
-	mutex_lock(&blkcg_pol_mutex);
+	struct blkcg *blkcg;
+
+	mutex_lock(&blkcg_pol_register_mutex);
 
 	if (WARN_ON(blkcg_policy[pol->plid] != pol))
 		goto out_unlock;
@@ -1229,9 +1245,19 @@
 	if (pol->cftypes)
 		cgroup_rm_cftypes(pol->cftypes);
 
-	/* unregister and update blkgs */
+	/* remove cpds and unregister */
+	mutex_lock(&blkcg_pol_mutex);
+
+	if (pol->cpd_size) {
+		list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) {
+			kfree(blkcg->pd[pol->plid]);
+			blkcg->pd[pol->plid] = NULL;
+		}
+	}
 	blkcg_policy[pol->plid] = NULL;
-out_unlock:
+
 	mutex_unlock(&blkcg_pol_mutex);
+out_unlock:
+	mutex_unlock(&blkcg_pol_register_mutex);
 }
 EXPORT_SYMBOL_GPL(blkcg_policy_unregister);
diff --git a/block/blk-core.c b/block/blk-core.c
index 82819e6..627ed0c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -3370,7 +3370,7 @@
 int __init blk_dev_init(void)
 {
 	BUILD_BUG_ON(__REQ_NR_BITS > 8 *
-			sizeof(((struct request *)0)->cmd_flags));
+			FIELD_SIZEOF(struct request, cmd_flags));
 
 	/* used for unplugging and affects IO latency/throughput - HIGHPRI */
 	kblockd_workqueue = alloc_workqueue("kblockd",
diff --git a/block/blk-mq.c b/block/blk-mq.c
index f537796..7d842db 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1998,7 +1998,7 @@
 		goto err_hctxs;
 
 	setup_timer(&q->timeout, blk_mq_rq_timer, (unsigned long) q);
-	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30000);
+	blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ);
 
 	q->nr_queues = nr_cpu_ids;
 	q->nr_hw_queues = set->nr_hw_queues;
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 12600bf..e0057d0 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -241,8 +241,8 @@
  * Description:
  *    Enables a low level driver to set a hard upper limit,
  *    max_hw_sectors, on the size of requests.  max_hw_sectors is set by
- *    the device driver based upon the combined capabilities of I/O
- *    controller and storage device.
+ *    the device driver based upon the capabilities of the I/O
+ *    controller.
  *
  *    max_sectors is a soft limit imposed by the block layer for
  *    filesystem type requests.  This value can be overridden on a
diff --git a/crypto/authencesn.c b/crypto/authencesn.c
index a3da677..b8efe36 100644
--- a/crypto/authencesn.c
+++ b/crypto/authencesn.c
@@ -393,8 +393,6 @@
 	struct scatterlist *cipher = areq_ctx->cipher;
 	struct scatterlist *hsg = areq_ctx->hsg;
 	struct scatterlist *tsg = areq_ctx->tsg;
-	struct scatterlist *assoc1;
-	struct scatterlist *assoc2;
 	unsigned int ivsize = crypto_aead_ivsize(authenc_esn);
 	unsigned int cryptlen = req->cryptlen;
 	struct page *dstp;
@@ -412,27 +410,19 @@
 		cryptlen += ivsize;
 	}
 
-	if (sg_is_last(assoc))
-		return -EINVAL;
-
-	assoc1 = assoc + 1;
-	if (sg_is_last(assoc1))
-		return -EINVAL;
-
-	assoc2 = assoc + 2;
-	if (!sg_is_last(assoc2))
+	if (assoc->length < 12)
 		return -EINVAL;
 
 	sg_init_table(hsg, 2);
-	sg_set_page(hsg, sg_page(assoc), assoc->length, assoc->offset);
-	sg_set_page(hsg + 1, sg_page(assoc2), assoc2->length, assoc2->offset);
+	sg_set_page(hsg, sg_page(assoc), 4, assoc->offset);
+	sg_set_page(hsg + 1, sg_page(assoc), 4, assoc->offset + 8);
 
 	sg_init_table(tsg, 1);
-	sg_set_page(tsg, sg_page(assoc1), assoc1->length, assoc1->offset);
+	sg_set_page(tsg, sg_page(assoc), 4, assoc->offset + 4);
 
 	areq_ctx->cryptlen = cryptlen;
-	areq_ctx->headlen = assoc->length + assoc2->length;
-	areq_ctx->trailen = assoc1->length;
+	areq_ctx->headlen = 8;
+	areq_ctx->trailen = 4;
 	areq_ctx->sg = dst;
 
 	areq_ctx->complete = authenc_esn_geniv_ahash_done;
@@ -563,8 +553,6 @@
 	struct scatterlist *cipher = areq_ctx->cipher;
 	struct scatterlist *hsg = areq_ctx->hsg;
 	struct scatterlist *tsg = areq_ctx->tsg;
-	struct scatterlist *assoc1;
-	struct scatterlist *assoc2;
 	unsigned int ivsize = crypto_aead_ivsize(authenc_esn);
 	struct page *srcp;
 	u8 *vsrc;
@@ -580,27 +568,19 @@
 		cryptlen += ivsize;
 	}
 
-	if (sg_is_last(assoc))
-		return -EINVAL;
-
-	assoc1 = assoc + 1;
-	if (sg_is_last(assoc1))
-		return -EINVAL;
-
-	assoc2 = assoc + 2;
-	if (!sg_is_last(assoc2))
+	if (assoc->length < 12)
 		return -EINVAL;
 
 	sg_init_table(hsg, 2);
-	sg_set_page(hsg, sg_page(assoc), assoc->length, assoc->offset);
-	sg_set_page(hsg + 1, sg_page(assoc2), assoc2->length, assoc2->offset);
+	sg_set_page(hsg, sg_page(assoc), 4, assoc->offset);
+	sg_set_page(hsg + 1, sg_page(assoc), 4, assoc->offset + 8);
 
 	sg_init_table(tsg, 1);
-	sg_set_page(tsg, sg_page(assoc1), assoc1->length, assoc1->offset);
+	sg_set_page(tsg, sg_page(assoc), 4, assoc->offset + 4);
 
 	areq_ctx->cryptlen = cryptlen;
-	areq_ctx->headlen = assoc->length + assoc2->length;
-	areq_ctx->trailen = assoc1->length;
+	areq_ctx->headlen = 8;
+	areq_ctx->trailen = 4;
 	areq_ctx->sg = src;
 
 	areq_ctx->complete = authenc_esn_verify_ahash_done;
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 569ee09..46b58ab 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -352,13 +352,16 @@
 				pdata->mmio_size = resource_size(rentry->res);
 			pdata->mmio_base = ioremap(rentry->res->start,
 						   pdata->mmio_size);
-			if (!pdata->mmio_base)
-				goto err_out;
 			break;
 		}
 
 	acpi_dev_free_resource_list(&resource_list);
 
+	if (!pdata->mmio_base) {
+		ret = -ENOMEM;
+		goto err_out;
+	}
+
 	pdata->dev_desc = dev_desc;
 
 	if (dev_desc->setup)
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 717afcd..88dbbb1 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -231,7 +231,7 @@
 		dev_warn(&device->dev, "Failed to change power state to %s\n",
 			 acpi_power_state_string(state));
 	} else {
-		device->power.state = state;
+		device->power.state = target_state;
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 				  "Device [%s] transitioned to %s\n",
 				  device->pnp.bus_id,
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index 2161fa1..628a42c 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -18,6 +18,7 @@
 #include <linux/list.h>
 #include <linux/acpi.h>
 #include <linux/sort.h>
+#include <linux/pmem.h>
 #include <linux/io.h>
 #include "nfit.h"
 
@@ -305,6 +306,23 @@
 	return true;
 }
 
+static bool add_flush(struct acpi_nfit_desc *acpi_desc,
+		struct acpi_nfit_flush_address *flush)
+{
+	struct device *dev = acpi_desc->dev;
+	struct nfit_flush *nfit_flush = devm_kzalloc(dev, sizeof(*nfit_flush),
+			GFP_KERNEL);
+
+	if (!nfit_flush)
+		return false;
+	INIT_LIST_HEAD(&nfit_flush->list);
+	nfit_flush->flush = flush;
+	list_add_tail(&nfit_flush->list, &acpi_desc->flushes);
+	dev_dbg(dev, "%s: nfit_flush handle: %d hint_count: %d\n", __func__,
+			flush->device_handle, flush->hint_count);
+	return true;
+}
+
 static void *add_table(struct acpi_nfit_desc *acpi_desc, void *table,
 		const void *end)
 {
@@ -338,7 +356,8 @@
 			return err;
 		break;
 	case ACPI_NFIT_TYPE_FLUSH_ADDRESS:
-		dev_dbg(dev, "%s: flush\n", __func__);
+		if (!add_flush(acpi_desc, table))
+			return err;
 		break;
 	case ACPI_NFIT_TYPE_SMBIOS:
 		dev_dbg(dev, "%s: smbios\n", __func__);
@@ -389,6 +408,7 @@
 {
 	u16 dcr = __to_nfit_memdev(nfit_mem)->region_index;
 	struct nfit_memdev *nfit_memdev;
+	struct nfit_flush *nfit_flush;
 	struct nfit_dcr *nfit_dcr;
 	struct nfit_bdw *nfit_bdw;
 	struct nfit_idt *nfit_idt;
@@ -442,6 +462,14 @@
 			nfit_mem->idt_bdw = nfit_idt->idt;
 			break;
 		}
+
+		list_for_each_entry(nfit_flush, &acpi_desc->flushes, list) {
+			if (nfit_flush->flush->device_handle !=
+					nfit_memdev->memdev->device_handle)
+				continue;
+			nfit_mem->nfit_flush = nfit_flush;
+			break;
+		}
 		break;
 	}
 
@@ -978,6 +1006,24 @@
 	return mmio->base_offset + line_offset + table_offset + sub_line_offset;
 }
 
+static void wmb_blk(struct nfit_blk *nfit_blk)
+{
+
+	if (nfit_blk->nvdimm_flush) {
+		/*
+		 * The first wmb() is needed to 'sfence' all previous writes
+		 * such that they are architecturally visible for the platform
+		 * buffer flush.  Note that we've already arranged for pmem
+		 * writes to avoid the cache via arch_memcpy_to_pmem().  The
+		 * final wmb() ensures ordering for the NVDIMM flush write.
+		 */
+		wmb();
+		writeq(1, nfit_blk->nvdimm_flush);
+		wmb();
+	} else
+		wmb_pmem();
+}
+
 static u64 read_blk_stat(struct nfit_blk *nfit_blk, unsigned int bw)
 {
 	struct nfit_blk_mmio *mmio = &nfit_blk->mmio[DCR];
@@ -1012,7 +1058,10 @@
 		offset = to_interleave_offset(offset, mmio);
 
 	writeq(cmd, mmio->base + offset);
-	/* FIXME: conditionally perform read-back if mandated by firmware */
+	wmb_blk(nfit_blk);
+
+	if (nfit_blk->dimm_flags & ND_BLK_DCR_LATCH)
+		readq(mmio->base + offset);
 }
 
 static int acpi_nfit_blk_single_io(struct nfit_blk *nfit_blk,
@@ -1026,7 +1075,6 @@
 
 	base_offset = nfit_blk->bdw_offset + dpa % L1_CACHE_BYTES
 		+ lane * mmio->size;
-	/* TODO: non-temporal access, flush hints, cache management etc... */
 	write_blk_ctl(nfit_blk, lane, dpa, len, rw);
 	while (len) {
 		unsigned int c;
@@ -1045,13 +1093,19 @@
 		}
 
 		if (rw)
-			memcpy(mmio->aperture + offset, iobuf + copied, c);
+			memcpy_to_pmem(mmio->aperture + offset,
+					iobuf + copied, c);
 		else
-			memcpy(iobuf + copied, mmio->aperture + offset, c);
+			memcpy_from_pmem(iobuf + copied,
+					mmio->aperture + offset, c);
 
 		copied += c;
 		len -= c;
 	}
+
+	if (rw)
+		wmb_blk(nfit_blk);
+
 	rc = read_blk_stat(nfit_blk, lane) ? -EIO : 0;
 	return rc;
 }
@@ -1124,7 +1178,7 @@
 }
 
 static void __iomem *__nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
-		struct acpi_nfit_system_address *spa)
+		struct acpi_nfit_system_address *spa, enum spa_map_type type)
 {
 	resource_size_t start = spa->address;
 	resource_size_t n = spa->length;
@@ -1152,8 +1206,15 @@
 	if (!res)
 		goto err_mem;
 
-	/* TODO: cacheability based on the spa type */
-	spa_map->iomem = ioremap_nocache(start, n);
+	if (type == SPA_MAP_APERTURE) {
+		/*
+		 * TODO: memremap_pmem() support, but that requires cache
+		 * flushing when the aperture is moved.
+		 */
+		spa_map->iomem = ioremap_wc(start, n);
+	} else
+		spa_map->iomem = ioremap_nocache(start, n);
+
 	if (!spa_map->iomem)
 		goto err_map;
 
@@ -1171,6 +1232,7 @@
  * nfit_spa_map - interleave-aware managed-mappings of acpi_nfit_system_address ranges
  * @nvdimm_bus: NFIT-bus that provided the spa table entry
  * @nfit_spa: spa table to map
+ * @type: aperture or control region
  *
  * In the case where block-data-window apertures and
  * dimm-control-regions are interleaved they will end up sharing a
@@ -1180,12 +1242,12 @@
  * unbound.
  */
 static void __iomem *nfit_spa_map(struct acpi_nfit_desc *acpi_desc,
-		struct acpi_nfit_system_address *spa)
+		struct acpi_nfit_system_address *spa, enum spa_map_type type)
 {
 	void __iomem *iomem;
 
 	mutex_lock(&acpi_desc->spa_map_mutex);
-	iomem = __nfit_spa_map(acpi_desc, spa);
+	iomem = __nfit_spa_map(acpi_desc, spa, type);
 	mutex_unlock(&acpi_desc->spa_map_mutex);
 
 	return iomem;
@@ -1206,12 +1268,35 @@
 	return 0;
 }
 
+static int acpi_nfit_blk_get_flags(struct nvdimm_bus_descriptor *nd_desc,
+		struct nvdimm *nvdimm, struct nfit_blk *nfit_blk)
+{
+	struct nd_cmd_dimm_flags flags;
+	int rc;
+
+	memset(&flags, 0, sizeof(flags));
+	rc = nd_desc->ndctl(nd_desc, nvdimm, ND_CMD_DIMM_FLAGS, &flags,
+			sizeof(flags));
+
+	if (rc >= 0 && flags.status == 0)
+		nfit_blk->dimm_flags = flags.flags;
+	else if (rc == -ENOTTY) {
+		/* fall back to a conservative default */
+		nfit_blk->dimm_flags = ND_BLK_DCR_LATCH;
+		rc = 0;
+	} else
+		rc = -ENXIO;
+
+	return rc;
+}
+
 static int acpi_nfit_blk_region_enable(struct nvdimm_bus *nvdimm_bus,
 		struct device *dev)
 {
 	struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
 	struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
 	struct nd_blk_region *ndbr = to_nd_blk_region(dev);
+	struct nfit_flush *nfit_flush;
 	struct nfit_blk_mmio *mmio;
 	struct nfit_blk *nfit_blk;
 	struct nfit_mem *nfit_mem;
@@ -1223,8 +1308,8 @@
 	if (!nfit_mem || !nfit_mem->dcr || !nfit_mem->bdw) {
 		dev_dbg(dev, "%s: missing%s%s%s\n", __func__,
 				nfit_mem ? "" : " nfit_mem",
-				nfit_mem->dcr ? "" : " dcr",
-				nfit_mem->bdw ? "" : " bdw");
+				(nfit_mem && nfit_mem->dcr) ? "" : " dcr",
+				(nfit_mem && nfit_mem->bdw) ? "" : " bdw");
 		return -ENXIO;
 	}
 
@@ -1237,7 +1322,8 @@
 	/* map block aperture memory */
 	nfit_blk->bdw_offset = nfit_mem->bdw->offset;
 	mmio = &nfit_blk->mmio[BDW];
-	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_bdw);
+	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_bdw,
+			SPA_MAP_APERTURE);
 	if (!mmio->base) {
 		dev_dbg(dev, "%s: %s failed to map bdw\n", __func__,
 				nvdimm_name(nvdimm));
@@ -1259,7 +1345,8 @@
 	nfit_blk->cmd_offset = nfit_mem->dcr->command_offset;
 	nfit_blk->stat_offset = nfit_mem->dcr->status_offset;
 	mmio = &nfit_blk->mmio[DCR];
-	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_dcr);
+	mmio->base = nfit_spa_map(acpi_desc, nfit_mem->spa_dcr,
+			SPA_MAP_CONTROL);
 	if (!mmio->base) {
 		dev_dbg(dev, "%s: %s failed to map dcr\n", __func__,
 				nvdimm_name(nvdimm));
@@ -1277,6 +1364,24 @@
 		return rc;
 	}
 
+	rc = acpi_nfit_blk_get_flags(nd_desc, nvdimm, nfit_blk);
+	if (rc < 0) {
+		dev_dbg(dev, "%s: %s failed get DIMM flags\n",
+				__func__, nvdimm_name(nvdimm));
+		return rc;
+	}
+
+	nfit_flush = nfit_mem->nfit_flush;
+	if (nfit_flush && nfit_flush->flush->hint_count != 0) {
+		nfit_blk->nvdimm_flush = devm_ioremap_nocache(dev,
+				nfit_flush->flush->hint_address[0], 8);
+		if (!nfit_blk->nvdimm_flush)
+			return -ENOMEM;
+	}
+
+	if (!arch_has_pmem_api() && !nfit_blk->nvdimm_flush)
+		dev_warn(dev, "unable to guarantee persistence of writes\n");
+
 	if (mmio->line_size == 0)
 		return 0;
 
@@ -1459,6 +1564,7 @@
 	INIT_LIST_HEAD(&acpi_desc->dcrs);
 	INIT_LIST_HEAD(&acpi_desc->bdws);
 	INIT_LIST_HEAD(&acpi_desc->idts);
+	INIT_LIST_HEAD(&acpi_desc->flushes);
 	INIT_LIST_HEAD(&acpi_desc->memdevs);
 	INIT_LIST_HEAD(&acpi_desc->dimms);
 	mutex_init(&acpi_desc->spa_map_mutex);
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index 81f2e8c5..79b6d83 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -40,6 +40,10 @@
 	NFIT_UUID_MAX,
 };
 
+enum {
+	ND_BLK_DCR_LATCH = 2,
+};
+
 struct nfit_spa {
 	struct acpi_nfit_system_address *spa;
 	struct list_head list;
@@ -60,6 +64,11 @@
 	struct list_head list;
 };
 
+struct nfit_flush {
+	struct acpi_nfit_flush_address *flush;
+	struct list_head list;
+};
+
 struct nfit_memdev {
 	struct acpi_nfit_memory_map *memdev;
 	struct list_head list;
@@ -77,6 +86,7 @@
 	struct acpi_nfit_system_address *spa_bdw;
 	struct acpi_nfit_interleave *idt_dcr;
 	struct acpi_nfit_interleave *idt_bdw;
+	struct nfit_flush *nfit_flush;
 	struct list_head list;
 	struct acpi_device *adev;
 	unsigned long dsm_mask;
@@ -88,6 +98,7 @@
 	struct mutex spa_map_mutex;
 	struct list_head spa_maps;
 	struct list_head memdevs;
+	struct list_head flushes;
 	struct list_head dimms;
 	struct list_head spas;
 	struct list_head dcrs;
@@ -109,7 +120,7 @@
 	struct nfit_blk_mmio {
 		union {
 			void __iomem *base;
-			void *aperture;
+			void __pmem  *aperture;
 		};
 		u64 size;
 		u64 base_offset;
@@ -123,6 +134,13 @@
 	u64 bdw_offset; /* post interleave offset */
 	u64 stat_offset;
 	u64 cmd_offset;
+	void __iomem *nvdimm_flush;
+	u32 dimm_flags;
+};
+
+enum spa_map_type {
+	SPA_MAP_CONTROL,
+	SPA_MAP_APERTURE,
 };
 
 struct nfit_spa_mapping {
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index c262e4a..3b8963f 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -175,10 +175,14 @@
 	if (!addr || !length)
 		return;
 
-	acpi_reserve_region(addr, length, gas->space_id, 0, desc);
+	/* Resources are never freed */
+	if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_IO)
+		request_region(addr, length, desc);
+	else if (gas->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
+		request_mem_region(addr, length, desc);
 }
 
-static void __init acpi_reserve_resources(void)
+static int __init acpi_reserve_resources(void)
 {
 	acpi_request_region(&acpi_gbl_FADT.xpm1a_event_block, acpi_gbl_FADT.pm1_event_length,
 		"ACPI PM1a_EVT_BLK");
@@ -207,7 +211,10 @@
 	if (!(acpi_gbl_FADT.gpe1_block_length & 0x1))
 		acpi_request_region(&acpi_gbl_FADT.xgpe1_block,
 			       acpi_gbl_FADT.gpe1_block_length, "ACPI GPE1_BLK");
+
+	return 0;
 }
+fs_initcall_sync(acpi_reserve_resources);
 
 void acpi_os_printf(const char *fmt, ...)
 {
@@ -1862,7 +1869,6 @@
 
 acpi_status __init acpi_os_initialize1(void)
 {
-	acpi_reserve_resources();
 	kacpid_wq = alloc_workqueue("kacpid", 0, 1);
 	kacpi_notify_wq = alloc_workqueue("kacpi_notify", 0, 1);
 	kacpi_hotplug_wq = alloc_ordered_workqueue("kacpi_hotplug", 0);
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index 10561ce..f1c966e 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -26,7 +26,6 @@
 #include <linux/device.h>
 #include <linux/export.h>
 #include <linux/ioport.h>
-#include <linux/list.h>
 #include <linux/slab.h>
 
 #ifdef CONFIG_X86
@@ -194,6 +193,7 @@
 	u8 iodec = attr->granularity == 0xfff ? ACPI_DECODE_10 : ACPI_DECODE_16;
 	bool wp = addr->info.mem.write_protect;
 	u64 len = attr->address_length;
+	u64 start, end, offset = 0;
 	struct resource *res = &win->res;
 
 	/*
@@ -205,9 +205,6 @@
 		pr_debug("ACPI: Invalid address space min_addr_fix %d, max_addr_fix %d, len %llx\n",
 			 addr->min_address_fixed, addr->max_address_fixed, len);
 
-	res->start = attr->minimum;
-	res->end = attr->maximum;
-
 	/*
 	 * For bridges that translate addresses across the bridge,
 	 * translation_offset is the offset that must be added to the
@@ -215,12 +212,22 @@
 	 * primary side. Non-bridge devices must list 0 for all Address
 	 * Translation offset bits.
 	 */
-	if (addr->producer_consumer == ACPI_PRODUCER) {
-		res->start += attr->translation_offset;
-		res->end += attr->translation_offset;
-	} else if (attr->translation_offset) {
+	if (addr->producer_consumer == ACPI_PRODUCER)
+		offset = attr->translation_offset;
+	else if (attr->translation_offset)
 		pr_debug("ACPI: translation_offset(%lld) is invalid for non-bridge device.\n",
 			 attr->translation_offset);
+	start = attr->minimum + offset;
+	end = attr->maximum + offset;
+
+	win->offset = offset;
+	res->start = start;
+	res->end = end;
+	if (sizeof(resource_size_t) < sizeof(u64) &&
+	    (offset != win->offset || start != res->start || end != res->end)) {
+		pr_warn("acpi resource window ([%#llx-%#llx] ignored, not CPU addressable)\n",
+			attr->minimum, attr->maximum);
+		return false;
 	}
 
 	switch (addr->resource_type) {
@@ -237,8 +244,6 @@
 		return false;
 	}
 
-	win->offset = attr->translation_offset;
-
 	if (addr->producer_consumer == ACPI_PRODUCER)
 		res->flags |= IORESOURCE_WINDOW;
 
@@ -622,164 +627,3 @@
 	return (type & types) ? 0 : 1;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_filter_resource_type);
-
-struct reserved_region {
-	struct list_head node;
-	u64 start;
-	u64 end;
-};
-
-static LIST_HEAD(reserved_io_regions);
-static LIST_HEAD(reserved_mem_regions);
-
-static int request_range(u64 start, u64 end, u8 space_id, unsigned long flags,
-			 char *desc)
-{
-	unsigned int length = end - start + 1;
-	struct resource *res;
-
-	res = space_id == ACPI_ADR_SPACE_SYSTEM_IO ?
-		request_region(start, length, desc) :
-		request_mem_region(start, length, desc);
-	if (!res)
-		return -EIO;
-
-	res->flags &= ~flags;
-	return 0;
-}
-
-static int add_region_before(u64 start, u64 end, u8 space_id,
-			     unsigned long flags, char *desc,
-			     struct list_head *head)
-{
-	struct reserved_region *reg;
-	int error;
-
-	reg = kmalloc(sizeof(*reg), GFP_KERNEL);
-	if (!reg)
-		return -ENOMEM;
-
-	error = request_range(start, end, space_id, flags, desc);
-	if (error) {
-		kfree(reg);
-		return error;
-	}
-
-	reg->start = start;
-	reg->end = end;
-	list_add_tail(&reg->node, head);
-	return 0;
-}
-
-/**
- * acpi_reserve_region - Reserve an I/O or memory region as a system resource.
- * @start: Starting address of the region.
- * @length: Length of the region.
- * @space_id: Identifier of address space to reserve the region from.
- * @flags: Resource flags to clear for the region after requesting it.
- * @desc: Region description (for messages).
- *
- * Reserve an I/O or memory region as a system resource to prevent others from
- * using it.  If the new region overlaps with one of the regions (in the given
- * address space) already reserved by this routine, only the non-overlapping
- * parts of it will be reserved.
- *
- * Returned is either 0 (success) or a negative error code indicating a resource
- * reservation problem.  It is the code of the first encountered error, but the
- * routine doesn't abort until it has attempted to request all of the parts of
- * the new region that don't overlap with other regions reserved previously.
- *
- * The resources requested by this routine are never released.
- */
-int acpi_reserve_region(u64 start, unsigned int length, u8 space_id,
-			unsigned long flags, char *desc)
-{
-	struct list_head *regions;
-	struct reserved_region *reg;
-	u64 end = start + length - 1;
-	int ret = 0, error = 0;
-
-	if (space_id == ACPI_ADR_SPACE_SYSTEM_IO)
-		regions = &reserved_io_regions;
-	else if (space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
-		regions = &reserved_mem_regions;
-	else
-		return -EINVAL;
-
-	if (list_empty(regions))
-		return add_region_before(start, end, space_id, flags, desc, regions);
-
-	list_for_each_entry(reg, regions, node)
-		if (reg->start == end + 1) {
-			/* The new region can be prepended to this one. */
-			ret = request_range(start, end, space_id, flags, desc);
-			if (!ret)
-				reg->start = start;
-
-			return ret;
-		} else if (reg->start > end) {
-			/* No overlap.  Add the new region here and get out. */
-			return add_region_before(start, end, space_id, flags,
-						 desc, &reg->node);
-		} else if (reg->end == start - 1) {
-			goto combine;
-		} else if (reg->end >= start) {
-			goto overlap;
-		}
-
-	/* The new region goes after the last existing one. */
-	return add_region_before(start, end, space_id, flags, desc, regions);
-
- overlap:
-	/*
-	 * The new region overlaps an existing one.
-	 *
-	 * The head part of the new region immediately preceding the existing
-	 * overlapping one can be combined with it right away.
-	 */
-	if (reg->start > start) {
-		error = request_range(start, reg->start - 1, space_id, flags, desc);
-		if (error)
-			ret = error;
-		else
-			reg->start = start;
-	}
-
- combine:
-	/*
-	 * The new region is adjacent to an existing one.  If it extends beyond
-	 * that region all the way to the next one, it is possible to combine
-	 * all three of them.
-	 */
-	while (reg->end < end) {
-		struct reserved_region *next = NULL;
-		u64 a = reg->end + 1, b = end;
-
-		if (!list_is_last(&reg->node, regions)) {
-			next = list_next_entry(reg, node);
-			if (next->start <= end)
-				b = next->start - 1;
-		}
-		error = request_range(a, b, space_id, flags, desc);
-		if (!error) {
-			if (next && next->start == b + 1) {
-				reg->end = next->end;
-				list_del(&next->node);
-				kfree(next);
-			} else {
-				reg->end = end;
-				break;
-			}
-		} else if (next) {
-			if (!ret)
-				ret = error;
-
-			reg = next;
-		} else {
-			break;
-		}
-	}
-
-	return ret ? ret : error;
-}
-EXPORT_SYMBOL_GPL(acpi_reserve_region);
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 2649a06..ec25635 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1019,6 +1019,29 @@
 	return false;
 }
 
+static bool __acpi_match_device_cls(const struct acpi_device_id *id,
+				    struct acpi_hardware_id *hwid)
+{
+	int i, msk, byte_shift;
+	char buf[3];
+
+	if (!id->cls)
+		return false;
+
+	/* Apply class-code bitmask, before checking each class-code byte */
+	for (i = 1; i <= 3; i++) {
+		byte_shift = 8 * (3 - i);
+		msk = (id->cls_msk >> byte_shift) & 0xFF;
+		if (!msk)
+			continue;
+
+		sprintf(buf, "%02x", (id->cls >> byte_shift) & msk);
+		if (strncmp(buf, &hwid->id[(i - 1) * 2], 2))
+			return false;
+	}
+	return true;
+}
+
 static const struct acpi_device_id *__acpi_match_device(
 	struct acpi_device *device,
 	const struct acpi_device_id *ids,
@@ -1036,9 +1059,12 @@
 
 	list_for_each_entry(hwid, &device->pnp.ids, list) {
 		/* First, check the ACPI/PNP IDs provided by the caller. */
-		for (id = ids; id->id[0]; id++)
-			if (!strcmp((char *) id->id, hwid->id))
+		for (id = ids; id->id[0] || id->cls; id++) {
+			if (id->id[0] && !strcmp((char *) id->id, hwid->id))
 				return id;
+			else if (id->cls && __acpi_match_device_cls(id, hwid))
+				return id;
+		}
 
 		/*
 		 * Next, check ACPI_DT_NAMESPACE_HID and try to match the
@@ -2101,6 +2127,8 @@
 		if (info->valid & ACPI_VALID_UID)
 			pnp->unique_id = kstrdup(info->unique_id.string,
 							GFP_KERNEL);
+		if (info->valid & ACPI_VALID_CLS)
+			acpi_add_id(pnp, info->class_code.string);
 
 		kfree(info);
 
diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
index 815f75e..2922f1f 100644
--- a/drivers/acpi/video_detect.c
+++ b/drivers/acpi/video_detect.c
@@ -32,6 +32,7 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/types.h>
+#include <linux/workqueue.h>
 #include <acpi/video.h>
 
 ACPI_MODULE_NAME("video");
@@ -41,6 +42,7 @@
 
 static bool backlight_notifier_registered;
 static struct notifier_block backlight_nb;
+static struct work_struct backlight_notify_work;
 
 static enum acpi_backlight_type acpi_backlight_cmdline = acpi_backlight_undef;
 static enum acpi_backlight_type acpi_backlight_dmi = acpi_backlight_undef;
@@ -262,6 +264,13 @@
 	{ },
 };
 
+/* This uses a workqueue to avoid various locking ordering issues */
+static void acpi_video_backlight_notify_work(struct work_struct *work)
+{
+	if (acpi_video_get_backlight_type() != acpi_backlight_video)
+		acpi_video_unregister_backlight();
+}
+
 static int acpi_video_backlight_notify(struct notifier_block *nb,
 				       unsigned long val, void *bd)
 {
@@ -269,9 +278,8 @@
 
 	/* A raw bl registering may change video -> native */
 	if (backlight->props.type == BACKLIGHT_RAW &&
-	    val == BACKLIGHT_REGISTERED &&
-	    acpi_video_get_backlight_type() != acpi_backlight_video)
-		acpi_video_unregister_backlight();
+	    val == BACKLIGHT_REGISTERED)
+		schedule_work(&backlight_notify_work);
 
 	return NOTIFY_OK;
 }
@@ -304,6 +312,8 @@
 		acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT,
 				    ACPI_UINT32_MAX, find_video, NULL,
 				    &video_caps, NULL);
+		INIT_WORK(&backlight_notify_work,
+			  acpi_video_backlight_notify_work);
 		backlight_nb.notifier_call = acpi_video_backlight_notify;
 		backlight_nb.priority = 0;
 		if (backlight_register_notifier(&backlight_nb) == 0)
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 6d17a3b..15e40ee 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -48,7 +48,7 @@
 
 config ATA_ACPI
 	bool "ATA ACPI Support"
-	depends on ACPI && PCI
+	depends on ACPI
 	default y
 	help
 	  This option adds support for ATA-related ACPI objects.
diff --git a/drivers/ata/ahci_brcmstb.c b/drivers/ata/ahci_brcmstb.c
index ce1e3a8..14b7305 100644
--- a/drivers/ata/ahci_brcmstb.c
+++ b/drivers/ata/ahci_brcmstb.c
@@ -92,7 +92,7 @@
 	 * Other architectures (e.g., ARM) either do not support big endian, or
 	 * else leave I/O in little endian mode.
 	 */
-	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(__BIG_ENDIAN))
+	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
 		return __raw_readl(addr);
 	else
 		return readl_relaxed(addr);
@@ -101,7 +101,7 @@
 static inline void brcm_sata_writereg(u32 val, void __iomem *addr)
 {
 	/* See brcm_sata_readreg() comments */
-	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(__BIG_ENDIAN))
+	if (IS_ENABLED(CONFIG_MIPS) && IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
 		__raw_writel(val, addr);
 	else
 		writel_relaxed(val, addr);
@@ -209,6 +209,7 @@
 			   priv->top_ctrl + SATA_TOP_CTRL_BUS_CTRL);
 }
 
+#ifdef CONFIG_PM_SLEEP
 static int brcm_ahci_suspend(struct device *dev)
 {
 	struct ata_host *host = dev_get_drvdata(dev);
@@ -231,6 +232,7 @@
 	brcm_sata_phys_enable(priv);
 	return ahci_platform_resume(dev);
 }
+#endif
 
 static struct scsi_host_template ahci_platform_sht = {
 	AHCI_SHT(DRV_NAME),
diff --git a/drivers/ata/ahci_platform.c b/drivers/ata/ahci_platform.c
index 614c78f..1befb11 100644
--- a/drivers/ata/ahci_platform.c
+++ b/drivers/ata/ahci_platform.c
@@ -20,6 +20,8 @@
 #include <linux/platform_device.h>
 #include <linux/libata.h>
 #include <linux/ahci_platform.h>
+#include <linux/acpi.h>
+#include <linux/pci_ids.h>
 #include "ahci.h"
 
 #define DRV_NAME "ahci"
@@ -79,12 +81,19 @@
 };
 MODULE_DEVICE_TABLE(of, ahci_of_match);
 
+static const struct acpi_device_id ahci_acpi_match[] = {
+	{ ACPI_DEVICE_CLASS(PCI_CLASS_STORAGE_SATA_AHCI, 0xffffff) },
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, ahci_acpi_match);
+
 static struct platform_driver ahci_driver = {
 	.probe = ahci_probe,
 	.remove = ata_platform_remove_one,
 	.driver = {
 		.name = DRV_NAME,
 		.of_match_table = ahci_of_match,
+		.acpi_match_table = ahci_acpi_match,
 		.pm = &ahci_pm_ops,
 	},
 };
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index e83fc3d..19bcb80 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -694,11 +694,11 @@
  *	RETURNS:
  *	Block address read from @tf.
  */
-u64 ata_tf_read_block(const struct ata_taskfile *tf, struct ata_device *dev)
+u64 ata_tf_read_block(struct ata_taskfile *tf, struct ata_device *dev)
 {
 	u64 block = 0;
 
-	if (!dev || tf->flags & ATA_TFLAG_LBA) {
+	if (tf->flags & ATA_TFLAG_LBA) {
 		if (tf->flags & ATA_TFLAG_LBA48) {
 			block |= (u64)tf->hob_lbah << 40;
 			block |= (u64)tf->hob_lbam << 32;
@@ -2147,24 +2147,6 @@
 	return 0;
 }
 
-static void ata_dev_config_sense_reporting(struct ata_device *dev)
-{
-	unsigned int err_mask;
-
-	if (!ata_id_has_sense_reporting(dev->id))
-		return;
-
-	if (ata_id_sense_reporting_enabled(dev->id))
-		return;
-
-	err_mask = ata_dev_set_feature(dev, SETFEATURE_SENSE_DATA, 0x1);
-	if (err_mask) {
-		ata_dev_dbg(dev,
-			    "failed to enable Sense Data Reporting, Emask 0x%x\n",
-			    err_mask);
-	}
-}
-
 /**
  *	ata_dev_configure - Configure the specified ATA/ATAPI device
  *	@dev: Target device to configure
@@ -2387,7 +2369,7 @@
 					dev->devslp_timing[i] = sata_setting[j];
 				}
 		}
-		ata_dev_config_sense_reporting(dev);
+
 		dev->cdb_len = 16;
 	}
 
@@ -2478,6 +2460,10 @@
 		dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_128,
 					 dev->max_sectors);
 
+	if (dev->horkage & ATA_HORKAGE_MAX_SEC_1024)
+		dev->max_sectors = min_t(unsigned int, ATA_MAX_SECTORS_1024,
+					 dev->max_sectors);
+
 	if (dev->horkage & ATA_HORKAGE_MAX_SEC_LBA48)
 		dev->max_sectors = ATA_MAX_SECTORS_LBA48;
 
@@ -4146,6 +4132,12 @@
 	{ "Slimtype DVD A  DS8A8SH", NULL,	ATA_HORKAGE_MAX_SEC_LBA48 },
 	{ "Slimtype DVD A  DS8A9SH", NULL,	ATA_HORKAGE_MAX_SEC_LBA48 },
 
+	/*
+	 * Causes silent data corruption with higher max sects.
+	 * http://lkml.kernel.org/g/x49wpy40ysk.fsf@segfault.boston.devel.redhat.com
+	 */
+	{ "ST380013AS",		"3.20",		ATA_HORKAGE_MAX_SEC_1024 },
+
 	/* Devices we expect to fail diagnostics */
 
 	/* Devices where NCQ should be avoided */
@@ -4174,9 +4166,10 @@
 	{ "ST3320[68]13AS",	"SD1[5-9]",	ATA_HORKAGE_NONCQ |
 						ATA_HORKAGE_FIRMWARE_WARN },
 
-	/* Seagate Momentus SpinPoint M8 seem to have FPMDA_AA issues */
+	/* drives which fail FPDMA_AA activation (some may freeze afterwards) */
 	{ "ST1000LM024 HN-M101MBB", "2AR10001",	ATA_HORKAGE_BROKEN_FPDMA_AA },
 	{ "ST1000LM024 HN-M101MBB", "2BA30001",	ATA_HORKAGE_BROKEN_FPDMA_AA },
+	{ "VB0250EAVER",	"HPG7",		ATA_HORKAGE_BROKEN_FPDMA_AA },
 
 	/* Blacklist entries taken from Silicon Image 3124/3132
 	   Windows driver .inf file - also several Linux problem reports */
@@ -4229,7 +4222,7 @@
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
 	{ "Crucial_CT*M500*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM |
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
-	{ "Micron_M5[15]0*",		"MU01",	ATA_HORKAGE_NO_NCQ_TRIM |
+	{ "Micron_M5[15]0_*",		"MU01",	ATA_HORKAGE_NO_NCQ_TRIM |
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
 	{ "Crucial_CT*M550*",		"MU01",	ATA_HORKAGE_NO_NCQ_TRIM |
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
@@ -4238,6 +4231,9 @@
 	{ "Samsung SSD 8*",		NULL,	ATA_HORKAGE_NO_NCQ_TRIM |
 						ATA_HORKAGE_ZERO_AFTER_TRIM, },
 
+	/* devices that don't properly handle TRIM commands */
+	{ "SuperSSpeed S238*",		NULL,	ATA_HORKAGE_NOTRIM, },
+
 	/*
 	 * As defined, the DRAT (Deterministic Read After Trim) and RZAT
 	 * (Return Zero After Trim) flags in the ATA Command Set are
@@ -4501,7 +4497,8 @@
 	else /* In the ancient relic department - skip all of this */
 		return 0;
 
-	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
+	/* On some disks, this command causes spin-up, so we need longer timeout */
+	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 15000);
 
 	DPRINTK("EXIT, err_mask=%x\n", err_mask);
 	return err_mask;
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 7465031..cb0508a 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -1592,8 +1592,6 @@
 	tf->hob_lbah = buf[10];
 	tf->nsect = buf[12];
 	tf->hob_nsect = buf[13];
-	if (ata_id_has_ncq_autosense(dev->id))
-		tf->auxiliary = buf[14] << 16 | buf[15] << 8 | buf[16];
 
 	return 0;
 }
@@ -1630,70 +1628,6 @@
 }
 
 /**
- *	ata_eh_request_sense - perform REQUEST_SENSE_DATA_EXT
- *	@dev: device to perform REQUEST_SENSE_SENSE_DATA_EXT to
- *	@sense_buf: result sense data buffer (SCSI_SENSE_BUFFERSIZE bytes long)
- *	@dfl_sense_key: default sense key to use
- *
- *	Perform REQUEST_SENSE_DATA_EXT after the device reported CHECK
- *	SENSE.  This function is EH helper.
- *
- *	LOCKING:
- *	Kernel thread context (may sleep).
- *
- *	RETURNS:
- *	encoded sense data on success, 0 on failure or if sense data
- *	is not available.
- */
-static u32 ata_eh_request_sense(struct ata_queued_cmd *qc,
-				struct scsi_cmnd *cmd)
-{
-	struct ata_device *dev = qc->dev;
-	struct ata_taskfile tf;
-	unsigned int err_mask;
-
-	if (!cmd)
-		return 0;
-
-	DPRINTK("ATA request sense\n");
-	ata_dev_warn(dev, "request sense\n");
-	if (!ata_id_sense_reporting_enabled(dev->id)) {
-		ata_dev_warn(qc->dev, "sense data reporting disabled\n");
-		return 0;
-	}
-	ata_tf_init(dev, &tf);
-
-	tf.flags |= ATA_TFLAG_ISADDR | ATA_TFLAG_DEVICE;
-	tf.flags |= ATA_TFLAG_LBA | ATA_TFLAG_LBA48;
-	tf.command = ATA_CMD_REQ_SENSE_DATA;
-	tf.protocol = ATA_PROT_NODATA;
-
-	err_mask = ata_exec_internal(dev, &tf, NULL, DMA_NONE, NULL, 0, 0);
-	/*
-	 * ACS-4 states:
-	 * The device may set the SENSE DATA AVAILABLE bit to one in the
-	 * STATUS field and clear the ERROR bit to zero in the STATUS field
-	 * to indicate that the command returned completion without an error
-	 * and the sense data described in table 306 is available.
-	 *
-	 * IOW the 'ATA_SENSE' bit might not be set even though valid
-	 * sense data is available.
-	 * So check for both.
-	 */
-	if ((tf.command & ATA_SENSE) ||
-		tf.lbah != 0 || tf.lbam != 0 || tf.lbal != 0) {
-		ata_scsi_set_sense(cmd, tf.lbah, tf.lbam, tf.lbal);
-		qc->flags |= ATA_QCFLAG_SENSE_VALID;
-		ata_dev_warn(dev, "sense data %02x/%02x/%02x\n",
-			     tf.lbah, tf.lbam, tf.lbal);
-	} else {
-		ata_dev_warn(dev, "request sense failed stat %02x emask %x\n",
-			     tf.command, err_mask);
-	}
-	return err_mask;
-}
-
-/**
  *	atapi_eh_request_sense - perform ATAPI REQUEST_SENSE
  *	@dev: device to perform REQUEST_SENSE to
  *	@sense_buf: result sense data buffer (SCSI_SENSE_BUFFERSIZE bytes long)
@@ -1855,19 +1789,6 @@
 	memcpy(&qc->result_tf, &tf, sizeof(tf));
 	qc->result_tf.flags = ATA_TFLAG_ISADDR | ATA_TFLAG_LBA | ATA_TFLAG_LBA48;
 	qc->err_mask |= AC_ERR_DEV | AC_ERR_NCQ;
-	if (qc->result_tf.auxiliary) {
-		char sense_key, asc, ascq;
-
-		sense_key = (qc->result_tf.auxiliary >> 16) & 0xff;
-		asc = (qc->result_tf.auxiliary >> 8) & 0xff;
-		ascq = qc->result_tf.auxiliary & 0xff;
-		ata_dev_dbg(dev, "NCQ Autosense %02x/%02x/%02x\n",
-			    sense_key, asc, ascq);
-		ata_scsi_set_sense(qc->scsicmd, sense_key, asc, ascq);
-		ata_scsi_set_sense_information(qc->scsicmd, &qc->result_tf);
-		qc->flags |= ATA_QCFLAG_SENSE_VALID;
-	}
-
 	ehc->i.err_mask &= ~AC_ERR_DEV;
 }
 
@@ -1897,27 +1818,6 @@
 		return ATA_EH_RESET;
 	}
 
-	/*
-	 * Sense data reporting does not work if the
-	 * device fault bit is set.
-	 */
-	if ((stat & ATA_SENSE) && !(stat & ATA_DF) &&
-	    !(qc->flags & ATA_QCFLAG_SENSE_VALID)) {
-		if (!(qc->ap->pflags & ATA_PFLAG_FROZEN)) {
-			tmp = ata_eh_request_sense(qc, qc->scsicmd);
-			if (tmp)
-				qc->err_mask |= tmp;
-			else
-				ata_scsi_set_sense_information(qc->scsicmd, tf);
-		} else {
-			ata_dev_warn(qc->dev, "sense data available but port frozen\n");
-		}
-	}
-
-	/* Set by NCQ autosense or request sense above */
-	if (qc->flags & ATA_QCFLAG_SENSE_VALID)
-		return 0;
-
 	if (stat & (ATA_ERR | ATA_DF))
 		qc->err_mask |= AC_ERR_DEV;
 	else
@@ -2661,15 +2561,14 @@
 
 #ifdef CONFIG_ATA_VERBOSE_ERROR
 		if (res->command & (ATA_BUSY | ATA_DRDY | ATA_DF | ATA_DRQ |
-				    ATA_SENSE | ATA_ERR)) {
+				    ATA_ERR)) {
 			if (res->command & ATA_BUSY)
 				ata_dev_err(qc->dev, "status: { Busy }\n");
 			else
-				ata_dev_err(qc->dev, "status: { %s%s%s%s%s}\n",
+				ata_dev_err(qc->dev, "status: { %s%s%s%s}\n",
 				  res->command & ATA_DRDY ? "DRDY " : "",
 				  res->command & ATA_DF ? "DF " : "",
 				  res->command & ATA_DRQ ? "DRQ " : "",
-				  res->command & ATA_SENSE ? "SENSE " : "",
 				  res->command & ATA_ERR ? "ERR " : "");
 		}
 
diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c
index 7ccc084..85aa761 100644
--- a/drivers/ata/libata-pmp.c
+++ b/drivers/ata/libata-pmp.c
@@ -460,6 +460,13 @@
 				       ATA_LFLAG_NO_SRST |
 				       ATA_LFLAG_ASSUME_ATA;
 		}
+	} else if (vendor == 0x11ab && devid == 0x4140) {
+		/* Marvell 4140 quirks */
+		ata_for_each_link(link, ap, EDGE) {
+			/* port 4 is for SEMB device and it doesn't like SRST */
+			if (link->pmp == 4)
+				link->flags |= ATA_LFLAG_DISABLED;
+		}
 	}
 }
 
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 3131adc..0d7f0da 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -270,28 +270,13 @@
 	    ata_scsi_park_show, ata_scsi_park_store);
 EXPORT_SYMBOL_GPL(dev_attr_unload_heads);
 
-void ata_scsi_set_sense(struct scsi_cmnd *cmd, u8 sk, u8 asc, u8 ascq)
+static void ata_scsi_set_sense(struct scsi_cmnd *cmd, u8 sk, u8 asc, u8 ascq)
 {
-	if (!cmd)
-		return;
-
 	cmd->result = (DRIVER_SENSE << 24) | SAM_STAT_CHECK_CONDITION;
 
 	scsi_build_sense_buffer(0, cmd->sense_buffer, sk, asc, ascq);
 }
 
-void ata_scsi_set_sense_information(struct scsi_cmnd *cmd,
-				    const struct ata_taskfile *tf)
-{
-	u64 information;
-
-	if (!cmd)
-		return;
-
-	information = ata_tf_read_block(tf, NULL);
-	scsi_set_sense_information(cmd->sense_buffer, information);
-}
-
 static ssize_t
 ata_scsi_em_message_store(struct device *dev, struct device_attribute *attr,
 			  const char *buf, size_t count)
@@ -1792,9 +1777,7 @@
 	    ((cdb[2] & 0x20) || need_sense)) {
 		ata_gen_passthru_sense(qc);
 	} else {
-		if (qc->flags & ATA_QCFLAG_SENSE_VALID) {
-			cmd->result = SAM_STAT_CHECK_CONDITION;
-		} else if (!need_sense) {
+		if (!need_sense) {
 			cmd->result = SAM_STAT_GOOD;
 		} else {
 			/* TODO: decide which descriptor format to use
@@ -2568,7 +2551,8 @@
 		rbuf[14] = (lowest_aligned >> 8) & 0x3f;
 		rbuf[15] = lowest_aligned;
 
-		if (ata_id_has_trim(args->id)) {
+		if (ata_id_has_trim(args->id) &&
+		    !(dev->horkage & ATA_HORKAGE_NOTRIM)) {
 			rbuf[14] |= 0x80; /* LBPME */
 
 			if (ata_id_has_zero_after_trim(args->id) &&
diff --git a/drivers/ata/libata-transport.c b/drivers/ata/libata-transport.c
index d6c37bc..e2d9497 100644
--- a/drivers/ata/libata-transport.c
+++ b/drivers/ata/libata-transport.c
@@ -569,6 +569,8 @@
 
 	if (!ata_id_has_trim(ata_dev->id))
 		mode = "unsupported";
+	else if (ata_dev->horkage & ATA_HORKAGE_NOTRIM)
+		mode = "forced_unsupported";
 	else if (ata_dev->horkage & ATA_HORKAGE_NO_NCQ_TRIM)
 			mode = "forced_unqueued";
 	else if (ata_fpdma_dsm_supported(ata_dev))
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index a998a17..f840ca1 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -67,8 +67,7 @@
 extern int ata_build_rw_tf(struct ata_taskfile *tf, struct ata_device *dev,
 			   u64 block, u32 n_block, unsigned int tf_flags,
 			   unsigned int tag);
-extern u64 ata_tf_read_block(const struct ata_taskfile *tf,
-			     struct ata_device *dev);
+extern u64 ata_tf_read_block(struct ata_taskfile *tf, struct ata_device *dev);
 extern unsigned ata_exec_internal(struct ata_device *dev,
 				  struct ata_taskfile *tf, const u8 *cdb,
 				  int dma_dir, void *buf, unsigned int buflen,
@@ -138,9 +137,6 @@
 			      struct scsi_host_template *sht);
 extern void ata_scsi_scan_host(struct ata_port *ap, int sync);
 extern int ata_scsi_offline_dev(struct ata_device *dev);
-extern void ata_scsi_set_sense(struct scsi_cmnd *cmd, u8 sk, u8 asc, u8 ascq);
-extern void ata_scsi_set_sense_information(struct scsi_cmnd *cmd,
-					   const struct ata_taskfile *tf);
 extern void ata_scsi_media_change_notify(struct ata_device *dev);
 extern void ata_scsi_hotplug(struct work_struct *work);
 extern void ata_schedule_scsi_eh(struct Scsi_Host *shost);
diff --git a/drivers/ata/pata_arasan_cf.c b/drivers/ata/pata_arasan_cf.c
index a9b0c82..5d9ee99 100644
--- a/drivers/ata/pata_arasan_cf.c
+++ b/drivers/ata/pata_arasan_cf.c
@@ -4,7 +4,7 @@
  * Arasan Compact Flash host controller source file
  *
  * Copyright (C) 2011 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
@@ -968,7 +968,7 @@
 
 module_platform_driver(arasan_cf_driver);
 
-MODULE_AUTHOR("Viresh Kumar <viresh.linux@gmail.com>");
+MODULE_AUTHOR("Viresh Kumar <vireshk@kernel.org>");
 MODULE_DESCRIPTION("Arasan ATA Compact Flash driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:" DRIVER_NAME);
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index 3a18a8a..fab504f 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -1238,8 +1238,12 @@
 	readl(mmio + PDC_SDRAM_CONTROL);
 
 	/* Turn on for ECC */
-	pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
-			  PDC_DIMM_SPD_TYPE, &spd0);
+	if (!pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
+			       PDC_DIMM_SPD_TYPE, &spd0)) {
+		pr_err("Failed in i2c read: device=%#x, subaddr=%#x\n",
+		       PDC_DIMM0_SPD_DEV_ADDRESS, PDC_DIMM_SPD_TYPE);
+		return 1;
+	}
 	if (spd0 == 0x02) {
 		data |= (0x01 << 16);
 		writel(data, mmio + PDC_SDRAM_CONTROL);
@@ -1380,8 +1384,12 @@
 
 	/* ECC initiliazation. */
 
-	pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
-			  PDC_DIMM_SPD_TYPE, &spd0);
+	if (!pdc20621_i2c_read(host, PDC_DIMM0_SPD_DEV_ADDRESS,
+			       PDC_DIMM_SPD_TYPE, &spd0)) {
+		pr_err("Failed in i2c read: device=%#x, subaddr=%#x\n",
+		       PDC_DIMM0_SPD_DEV_ADDRESS, PDC_DIMM_SPD_TYPE);
+		return 1;
+	}
 	if (spd0 == 0x02) {
 		void *buf;
 		VPRINTK("Start ECC initialization\n");
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 9c42883..894bda1 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -563,10 +563,8 @@
 	kfree(fw_priv);
 }
 
-static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env)
+static int do_firmware_uevent(struct firmware_priv *fw_priv, struct kobj_uevent_env *env)
 {
-	struct firmware_priv *fw_priv = to_firmware_priv(dev);
-
 	if (add_uevent_var(env, "FIRMWARE=%s", fw_priv->buf->fw_id))
 		return -ENOMEM;
 	if (add_uevent_var(env, "TIMEOUT=%i", loading_timeout))
@@ -577,6 +575,18 @@
 	return 0;
 }
 
+static int firmware_uevent(struct device *dev, struct kobj_uevent_env *env)
+{
+	struct firmware_priv *fw_priv = to_firmware_priv(dev);
+	int err = 0;
+
+	mutex_lock(&fw_lock);
+	if (fw_priv->buf)
+		err = do_firmware_uevent(fw_priv, env);
+	mutex_unlock(&fw_lock);
+	return err;
+}
+
 static struct class firmware_class = {
 	.name		= "firmware",
 	.class_attrs	= firmware_class_attrs,
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index cdd547b..0ee43c1 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -6,6 +6,7 @@
  * This file is released under the GPLv2.
  */
 
+#include <linux/delay.h>
 #include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
@@ -19,6 +20,8 @@
 #include <linux/suspend.h>
 #include <linux/export.h>
 
+#define GENPD_RETRY_MAX_MS	250		/* Approximate */
+
 #define GENPD_DEV_CALLBACK(genpd, type, callback, dev)		\
 ({								\
 	type (*__routine)(struct device *__d); 			\
@@ -2131,6 +2134,7 @@
 static void genpd_dev_pm_detach(struct device *dev, bool power_off)
 {
 	struct generic_pm_domain *pd;
+	unsigned int i;
 	int ret = 0;
 
 	pd = pm_genpd_lookup_dev(dev);
@@ -2139,10 +2143,12 @@
 
 	dev_dbg(dev, "removing from PM domain %s\n", pd->name);
 
-	while (1) {
+	for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
 		ret = pm_genpd_remove_device(pd, dev);
 		if (ret != -EAGAIN)
 			break;
+
+		mdelay(i);
 		cond_resched();
 	}
 
@@ -2183,6 +2189,7 @@
 {
 	struct of_phandle_args pd_args;
 	struct generic_pm_domain *pd;
+	unsigned int i;
 	int ret;
 
 	if (!dev->of_node)
@@ -2218,10 +2225,12 @@
 
 	dev_dbg(dev, "adding to PM domain %s\n", pd->name);
 
-	while (1) {
+	for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
 		ret = pm_genpd_add_device(pd, dev);
 		if (ret != -EAGAIN)
 			break;
+
+		mdelay(i);
 		cond_resched();
 	}
 
diff --git a/drivers/base/power/wakeirq.c b/drivers/base/power/wakeirq.c
index 7470004..eb6e674 100644
--- a/drivers/base/power/wakeirq.c
+++ b/drivers/base/power/wakeirq.c
@@ -45,14 +45,12 @@
 		return -EEXIST;
 	}
 
-	dev->power.wakeirq = wirq;
-	spin_unlock_irqrestore(&dev->power.lock, flags);
-
 	err = device_wakeup_attach_irq(dev, wirq);
-	if (err)
-		return err;
+	if (!err)
+		dev->power.wakeirq = wirq;
 
-	return 0;
+	spin_unlock_irqrestore(&dev->power.lock, flags);
+	return err;
 }
 
 /**
@@ -105,10 +103,10 @@
 		return;
 
 	spin_lock_irqsave(&dev->power.lock, flags);
+	device_wakeup_detach_irq(dev);
 	dev->power.wakeirq = NULL;
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 
-	device_wakeup_detach_irq(dev);
 	if (wirq->dedicated_irq)
 		free_irq(wirq->irq, wirq);
 	kfree(wirq);
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 40f7160..51f15bc 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -281,32 +281,25 @@
  * Attach a device wakeirq to the wakeup source so the device
  * wake IRQ can be configured automatically for suspend and
  * resume.
+ *
+ * Call under the device's power.lock lock.
  */
 int device_wakeup_attach_irq(struct device *dev,
 			     struct wake_irq *wakeirq)
 {
 	struct wakeup_source *ws;
-	int ret = 0;
 
-	spin_lock_irq(&dev->power.lock);
 	ws = dev->power.wakeup;
 	if (!ws) {
 		dev_err(dev, "forgot to call call device_init_wakeup?\n");
-		ret = -EINVAL;
-		goto unlock;
+		return -EINVAL;
 	}
 
-	if (ws->wakeirq) {
-		ret = -EEXIST;
-		goto unlock;
-	}
+	if (ws->wakeirq)
+		return -EEXIST;
 
 	ws->wakeirq = wakeirq;
-
-unlock:
-	spin_unlock_irq(&dev->power.lock);
-
-	return ret;
+	return 0;
 }
 
 /**
@@ -314,20 +307,16 @@
  * @dev: Device to handle
  *
  * Removes a device wakeirq from the wakeup source.
+ *
+ * Call under the device's power.lock lock.
  */
 void device_wakeup_detach_irq(struct device *dev)
 {
 	struct wakeup_source *ws;
 
-	spin_lock_irq(&dev->power.lock);
 	ws = dev->power.wakeup;
-	if (!ws)
-		goto unlock;
-
-	ws->wakeirq = NULL;
-
-unlock:
-	spin_unlock_irq(&dev->power.lock);
+	if (ws)
+		ws->wakeirq = NULL;
 }
 
 /**
diff --git a/drivers/base/regmap/regcache-rbtree.c b/drivers/base/regmap/regcache-rbtree.c
index 81751a4..56486d9 100644
--- a/drivers/base/regmap/regcache-rbtree.c
+++ b/drivers/base/regmap/regcache-rbtree.c
@@ -296,11 +296,20 @@
 	if (!blk)
 		return -ENOMEM;
 
-	present = krealloc(rbnode->cache_present,
-		    BITS_TO_LONGS(blklen) * sizeof(*present), GFP_KERNEL);
-	if (!present) {
-		kfree(blk);
-		return -ENOMEM;
+	if (BITS_TO_LONGS(blklen) > BITS_TO_LONGS(rbnode->blklen)) {
+		present = krealloc(rbnode->cache_present,
+				   BITS_TO_LONGS(blklen) * sizeof(*present),
+				   GFP_KERNEL);
+		if (!present) {
+			kfree(blk);
+			return -ENOMEM;
+		}
+
+		memset(present + BITS_TO_LONGS(rbnode->blklen), 0,
+		       (BITS_TO_LONGS(blklen) - BITS_TO_LONGS(rbnode->blklen))
+		       * sizeof(*present));
+	} else {
+		present = rbnode->cache_present;
 	}
 
 	/* insert the register value in the correct place in the rbnode block */
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 69de41a..3177b24 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -240,19 +240,19 @@
 	while ((entry = llist_del_all(&cq->list)) != NULL) {
 		entry = llist_reverse_order(entry);
 		do {
+			struct request_queue *q = NULL;
+
 			cmd = container_of(entry, struct nullb_cmd, ll_list);
 			entry = entry->next;
+			if (cmd->rq)
+				q = cmd->rq->q;
 			end_cmd(cmd);
 
-			if (cmd->rq) {
-				struct request_queue *q = cmd->rq->q;
-
-				if (!q->mq_ops && blk_queue_stopped(q)) {
-					spin_lock(q->queue_lock);
-					if (blk_queue_stopped(q))
-						blk_start_queue(q);
-					spin_unlock(q->queue_lock);
-				}
+			if (q && !q->mq_ops && blk_queue_stopped(q)) {
+				spin_lock(q->queue_lock);
+				if (blk_queue_stopped(q))
+					blk_start_queue(q);
+				spin_unlock(q->queue_lock);
 			}
 		} while (entry);
 	}
diff --git a/drivers/block/nvme-core.c b/drivers/block/nvme-core.c
index d1d6141..7920c27 100644
--- a/drivers/block/nvme-core.c
+++ b/drivers/block/nvme-core.c
@@ -2108,8 +2108,17 @@
 		goto out_free_disk;
 
 	add_disk(ns->disk);
-	if (ns->ms)
-		revalidate_disk(ns->disk);
+	if (ns->ms) {
+		struct block_device *bd = bdget_disk(ns->disk, 0);
+		if (!bd)
+			return;
+		if (blkdev_get(bd, FMODE_READ, NULL)) {
+			bdput(bd);
+			return;
+		}
+		blkdev_reread_part(bd);
+		blkdev_put(bd, FMODE_READ);
+	}
 	return;
  out_free_disk:
 	kfree(disk);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index d94529d..bc67a93 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -523,6 +523,7 @@
 #  define rbd_assert(expr)	((void) 0)
 #endif /* !RBD_DEBUG */
 
+static void rbd_osd_copyup_callback(struct rbd_obj_request *obj_request);
 static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request);
 static void rbd_img_parent_read(struct rbd_obj_request *obj_request);
 static void rbd_dev_remove_parent(struct rbd_device *rbd_dev);
@@ -1818,6 +1819,16 @@
 	obj_request_done_set(obj_request);
 }
 
+static void rbd_osd_call_callback(struct rbd_obj_request *obj_request)
+{
+	dout("%s: obj %p\n", __func__, obj_request);
+
+	if (obj_request_img_data_test(obj_request))
+		rbd_osd_copyup_callback(obj_request);
+	else
+		obj_request_done_set(obj_request);
+}
+
 static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
 				struct ceph_msg *msg)
 {
@@ -1866,6 +1877,8 @@
 		rbd_osd_discard_callback(obj_request);
 		break;
 	case CEPH_OSD_OP_CALL:
+		rbd_osd_call_callback(obj_request);
+		break;
 	case CEPH_OSD_OP_NOTIFY_ACK:
 	case CEPH_OSD_OP_WATCH:
 		rbd_osd_trivial_callback(obj_request);
@@ -2530,13 +2543,15 @@
 }
 
 static void
-rbd_img_obj_copyup_callback(struct rbd_obj_request *obj_request)
+rbd_osd_copyup_callback(struct rbd_obj_request *obj_request)
 {
 	struct rbd_img_request *img_request;
 	struct rbd_device *rbd_dev;
 	struct page **pages;
 	u32 page_count;
 
+	dout("%s: obj %p\n", __func__, obj_request);
+
 	rbd_assert(obj_request->type == OBJ_REQUEST_BIO ||
 		obj_request->type == OBJ_REQUEST_NODATA);
 	rbd_assert(obj_request_img_data_test(obj_request));
@@ -2563,9 +2578,7 @@
 	if (!obj_request->result)
 		obj_request->xferred = obj_request->length;
 
-	/* Finish up with the normal image object callback */
-
-	rbd_img_obj_callback(obj_request);
+	obj_request_done_set(obj_request);
 }
 
 static void
@@ -2650,7 +2663,6 @@
 
 	/* All set, send it off. */
 
-	orig_request->callback = rbd_img_obj_copyup_callback;
 	osdc = &rbd_dev->rbd_client->client->osdc;
 	img_result = rbd_obj_request_submit(osdc, orig_request);
 	if (!img_result)
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index ced9677..954c002 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -369,8 +369,8 @@
 		return;
 	}
 
-	if (work_pending(&blkif->persistent_purge_work)) {
-		pr_alert_ratelimited("Scheduled work from previous purge is still pending, cannot purge list\n");
+	if (work_busy(&blkif->persistent_purge_work)) {
+		pr_alert_ratelimited("Scheduled work from previous purge is still busy, cannot purge list\n");
 		return;
 	}
 
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 6d89ed3..7a8a73f 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -179,6 +179,7 @@
 	((_segs + SEGS_PER_INDIRECT_FRAME - 1)/SEGS_PER_INDIRECT_FRAME)
 
 static int blkfront_setup_indirect(struct blkfront_info *info);
+static int blkfront_gather_backend_features(struct blkfront_info *info);
 
 static int get_id_from_freelist(struct blkfront_info *info)
 {
@@ -1128,8 +1129,10 @@
 				 * Add the used indirect page back to the list of
 				 * available pages for indirect grefs.
 				 */
-				indirect_page = pfn_to_page(s->indirect_grants[i]->pfn);
-				list_add(&indirect_page->lru, &info->indirect_pages);
+				if (!info->feature_persistent) {
+					indirect_page = pfn_to_page(s->indirect_grants[i]->pfn);
+					list_add(&indirect_page->lru, &info->indirect_pages);
+				}
 				s->indirect_grants[i]->gref = GRANT_INVALID_REF;
 				list_add_tail(&s->indirect_grants[i]->node, &info->grants);
 			}
@@ -1519,7 +1522,7 @@
 	info->shadow_free = info->ring.req_prod_pvt;
 	info->shadow[BLK_RING_SIZE(info)-1].req.u.rw.id = 0x0fffffff;
 
-	rc = blkfront_setup_indirect(info);
+	rc = blkfront_gather_backend_features(info);
 	if (rc) {
 		kfree(copy);
 		return rc;
@@ -1720,20 +1723,13 @@
 
 static int blkfront_setup_indirect(struct blkfront_info *info)
 {
-	unsigned int indirect_segments, segs;
+	unsigned int segs;
 	int err, i;
 
-	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
-			    "feature-max-indirect-segments", "%u", &indirect_segments,
-			    NULL);
-	if (err) {
-		info->max_indirect_segments = 0;
+	if (info->max_indirect_segments == 0)
 		segs = BLKIF_MAX_SEGMENTS_PER_REQUEST;
-	} else {
-		info->max_indirect_segments = min(indirect_segments,
-						  xen_blkif_max_segments);
+	else
 		segs = info->max_indirect_segments;
-	}
 
 	err = fill_grant_buffer(info, (segs + INDIRECT_GREFS(segs)) * BLK_RING_SIZE(info));
 	if (err)
@@ -1797,6 +1793,68 @@
 }
 
 /*
+ * Gather all backend feature-*
+ */
+static int blkfront_gather_backend_features(struct blkfront_info *info)
+{
+	int err;
+	int barrier, flush, discard, persistent;
+	unsigned int indirect_segments;
+
+	info->feature_flush = 0;
+
+	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+			"feature-barrier", "%d", &barrier,
+			NULL);
+
+	/*
+	 * If there's no "feature-barrier" defined, then it means
+	 * we're dealing with a very old backend which writes
+	 * synchronously; nothing to do.
+	 *
+	 * If there are barriers, then we use flush.
+	 */
+	if (!err && barrier)
+		info->feature_flush = REQ_FLUSH | REQ_FUA;
+	/*
+	 * And if there is "feature-flush-cache" use that above
+	 * barriers.
+	 */
+	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+			"feature-flush-cache", "%d", &flush,
+			NULL);
+
+	if (!err && flush)
+		info->feature_flush = REQ_FLUSH;
+
+	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+			"feature-discard", "%d", &discard,
+			NULL);
+
+	if (!err && discard)
+		blkfront_setup_discard(info);
+
+	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+			"feature-persistent", "%u", &persistent,
+			NULL);
+	if (err)
+		info->feature_persistent = 0;
+	else
+		info->feature_persistent = persistent;
+
+	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+			    "feature-max-indirect-segments", "%u", &indirect_segments,
+			    NULL);
+	if (err)
+		info->max_indirect_segments = 0;
+	else
+		info->max_indirect_segments = min(indirect_segments,
+						  xen_blkif_max_segments);
+
+	return blkfront_setup_indirect(info);
+}
+
+/*
  * Invoked when the backend is finally 'ready' (and has told produced
  * the details about the physical device - #sectors, size, etc).
  */
@@ -1807,7 +1865,6 @@
 	unsigned int physical_sector_size;
 	unsigned int binfo;
 	int err;
-	int barrier, flush, discard, persistent;
 
 	switch (info->connected) {
 	case BLKIF_STATE_CONNECTED:
@@ -1864,48 +1921,7 @@
 	if (err != 1)
 		physical_sector_size = sector_size;
 
-	info->feature_flush = 0;
-
-	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
-			    "feature-barrier", "%d", &barrier,
-			    NULL);
-
-	/*
-	 * If there's no "feature-barrier" defined, then it means
-	 * we're dealing with a very old backend which writes
-	 * synchronously; nothing to do.
-	 *
-	 * If there are barriers, then we use flush.
-	 */
-	if (!err && barrier)
-		info->feature_flush = REQ_FLUSH | REQ_FUA;
-	/*
-	 * And if there is "feature-flush-cache" use that above
-	 * barriers.
-	 */
-	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
-			    "feature-flush-cache", "%d", &flush,
-			    NULL);
-
-	if (!err && flush)
-		info->feature_flush = REQ_FLUSH;
-
-	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
-			    "feature-discard", "%d", &discard,
-			    NULL);
-
-	if (!err && discard)
-		blkfront_setup_discard(info);
-
-	err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
-			    "feature-persistent", "%u", &persistent,
-			    NULL);
-	if (err)
-		info->feature_persistent = 0;
-	else
-		info->feature_persistent = persistent;
-
-	err = blkfront_setup_indirect(info);
+	err = blkfront_gather_backend_features(info);
 	if (err) {
 		xenbus_dev_fatal(info->xbdev, err, "setup_indirect at %s",
 				 info->xbdev->otherend);
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index fb655e8..763301c 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -496,10 +496,9 @@
 	kfree(meta);
 }
 
-static struct zram_meta *zram_meta_alloc(int device_id, u64 disksize)
+static struct zram_meta *zram_meta_alloc(char *pool_name, u64 disksize)
 {
 	size_t num_pages;
-	char pool_name[8];
 	struct zram_meta *meta = kmalloc(sizeof(*meta), GFP_KERNEL);
 
 	if (!meta)
@@ -512,7 +511,6 @@
 		goto out_error;
 	}
 
-	snprintf(pool_name, sizeof(pool_name), "zram%d", device_id);
 	meta->mem_pool = zs_create_pool(pool_name, GFP_NOIO | __GFP_HIGHMEM);
 	if (!meta->mem_pool) {
 		pr_err("Error creating memory pool\n");
@@ -1031,7 +1029,7 @@
 		return -EINVAL;
 
 	disksize = PAGE_ALIGN(disksize);
-	meta = zram_meta_alloc(zram->disk->first_minor, disksize);
+	meta = zram_meta_alloc(zram->disk->disk_name, disksize);
 	if (!meta)
 		return -ENOMEM;
 
diff --git a/drivers/bluetooth/btbcm.c b/drivers/bluetooth/btbcm.c
index 1e1a432..9ceb8ac 100644
--- a/drivers/bluetooth/btbcm.c
+++ b/drivers/bluetooth/btbcm.c
@@ -472,12 +472,11 @@
 
 	/* Read Verbose Config Version Info */
 	skb = btbcm_read_verbose_config(hdev);
-	if (IS_ERR(skb))
-		return PTR_ERR(skb);
-
-	BT_INFO("%s: BCM: chip id %u build %4.4u", hdev->name, skb->data[1],
-		get_unaligned_le16(skb->data + 5));
-	kfree_skb(skb);
+	if (!IS_ERR(skb)) {
+		BT_INFO("%s: BCM: chip id %u build %4.4u", hdev->name, skb->data[1],
+			get_unaligned_le16(skb->data + 5));
+		kfree_skb(skb);
+	}
 
 	set_bit(HCI_QUIRK_STRICT_DUPLICATE_FILTER, &hdev->quirks);
 
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index da8faf7..5643b65 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -429,7 +429,7 @@
 static void start_khwrngd(void)
 {
 	hwrng_fill = kthread_run(hwrng_fillfn, NULL, "hwrng");
-	if (hwrng_fill == ERR_PTR(-ENOMEM)) {
+	if (IS_ERR(hwrng_fill)) {
 		pr_err("hwrng_fill thread creation failed");
 		hwrng_fill = NULL;
 	}
diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c
index 283f00a..1082d4b 100644
--- a/drivers/char/tpm/tpm-chip.c
+++ b/drivers/char/tpm/tpm-chip.c
@@ -129,8 +129,9 @@
 
 	device_initialize(&chip->dev);
 
-	chip->cdev.owner = chip->pdev->driver->owner;
 	cdev_init(&chip->cdev, &tpm_fops);
+	chip->cdev.owner = chip->pdev->driver->owner;
+	chip->cdev.kobj.parent = &chip->dev.kobj;
 
 	return chip;
 }
diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c
index 44f9d20..1267322 100644
--- a/drivers/char/tpm/tpm_crb.c
+++ b/drivers/char/tpm/tpm_crb.c
@@ -233,6 +233,14 @@
 		return -ENODEV;
 	}
 
+	/* At least some versions of AMI BIOS have a bug that TPM2 table has
+	 * zero address for the control area and therefore we must fail.
+	*/
+	if (!buf->control_area_pa) {
+		dev_err(dev, "TPM2 ACPI table has a zero address for the control area\n");
+		return -EINVAL;
+	}
+
 	if (buf->hdr.length < sizeof(struct acpi_tpm2)) {
 		dev_err(dev, "TPM2 ACPI table has wrong size");
 		return -EINVAL;
diff --git a/drivers/clk/at91/clk-h32mx.c b/drivers/clk/at91/clk-h32mx.c
index 152dcb3..61566bc 100644
--- a/drivers/clk/at91/clk-h32mx.c
+++ b/drivers/clk/at91/clk-h32mx.c
@@ -116,8 +116,10 @@
 	h32mxclk->pmc = pmc;
 
 	clk = clk_register(NULL, &h32mxclk->hw);
-	if (!clk)
+	if (!clk) {
+		kfree(h32mxclk);
 		return;
+	}
 
 	of_clk_add_provider(np, of_clk_src_simple_get, clk);
 }
diff --git a/drivers/clk/at91/clk-main.c b/drivers/clk/at91/clk-main.c
index c240045..27dfa96 100644
--- a/drivers/clk/at91/clk-main.c
+++ b/drivers/clk/at91/clk-main.c
@@ -171,8 +171,10 @@
 	irq_set_status_flags(osc->irq, IRQ_NOAUTOEN);
 	ret = request_irq(osc->irq, clk_main_osc_irq_handler,
 			  IRQF_TRIGGER_HIGH, name, osc);
-	if (ret)
+	if (ret) {
+		kfree(osc);
 		return ERR_PTR(ret);
+	}
 
 	if (bypass)
 		pmc_write(pmc, AT91_CKGR_MOR,
diff --git a/drivers/clk/at91/clk-master.c b/drivers/clk/at91/clk-master.c
index f98eafe..5b3ded5 100644
--- a/drivers/clk/at91/clk-master.c
+++ b/drivers/clk/at91/clk-master.c
@@ -165,12 +165,16 @@
 	irq_set_status_flags(master->irq, IRQ_NOAUTOEN);
 	ret = request_irq(master->irq, clk_master_irq_handler,
 			  IRQF_TRIGGER_HIGH, "clk-master", master);
-	if (ret)
+	if (ret) {
+		kfree(master);
 		return ERR_PTR(ret);
+	}
 
 	clk = clk_register(NULL, &master->hw);
-	if (IS_ERR(clk))
+	if (IS_ERR(clk)) {
+		free_irq(master->irq, master);
 		kfree(master);
+	}
 
 	return clk;
 }
diff --git a/drivers/clk/at91/clk-pll.c b/drivers/clk/at91/clk-pll.c
index cbbe403..18b60f4 100644
--- a/drivers/clk/at91/clk-pll.c
+++ b/drivers/clk/at91/clk-pll.c
@@ -346,12 +346,16 @@
 	irq_set_status_flags(pll->irq, IRQ_NOAUTOEN);
 	ret = request_irq(pll->irq, clk_pll_irq_handler, IRQF_TRIGGER_HIGH,
 			  id ? "clk-pllb" : "clk-plla", pll);
-	if (ret)
+	if (ret) {
+		kfree(pll);
 		return ERR_PTR(ret);
+	}
 
 	clk = clk_register(NULL, &pll->hw);
-	if (IS_ERR(clk))
+	if (IS_ERR(clk)) {
+		free_irq(pll->irq, pll);
 		kfree(pll);
+	}
 
 	return clk;
 }
diff --git a/drivers/clk/at91/clk-system.c b/drivers/clk/at91/clk-system.c
index a76d03f..58008b3 100644
--- a/drivers/clk/at91/clk-system.c
+++ b/drivers/clk/at91/clk-system.c
@@ -130,13 +130,17 @@
 		irq_set_status_flags(sys->irq, IRQ_NOAUTOEN);
 		ret = request_irq(sys->irq, clk_system_irq_handler,
 				IRQF_TRIGGER_HIGH, name, sys);
-		if (ret)
+		if (ret) {
+			kfree(sys);
 			return ERR_PTR(ret);
+		}
 	}
 
 	clk = clk_register(NULL, &sys->hw);
-	if (IS_ERR(clk))
+	if (IS_ERR(clk)) {
+		free_irq(sys->irq, sys);
 		kfree(sys);
+	}
 
 	return clk;
 }
diff --git a/drivers/clk/at91/clk-utmi.c b/drivers/clk/at91/clk-utmi.c
index ae3263b..30dd697 100644
--- a/drivers/clk/at91/clk-utmi.c
+++ b/drivers/clk/at91/clk-utmi.c
@@ -118,12 +118,16 @@
 	irq_set_status_flags(utmi->irq, IRQ_NOAUTOEN);
 	ret = request_irq(utmi->irq, clk_utmi_irq_handler,
 			  IRQF_TRIGGER_HIGH, "clk-utmi", utmi);
-	if (ret)
+	if (ret) {
+		kfree(utmi);
 		return ERR_PTR(ret);
+	}
 
 	clk = clk_register(NULL, &utmi->hw);
-	if (IS_ERR(clk))
+	if (IS_ERR(clk)) {
+		free_irq(utmi->irq, utmi);
 		kfree(utmi);
+	}
 
 	return clk;
 }
diff --git a/drivers/clk/bcm/clk-iproc-asiu.c b/drivers/clk/bcm/clk-iproc-asiu.c
index e19c09c..f630e1b 100644
--- a/drivers/clk/bcm/clk-iproc-asiu.c
+++ b/drivers/clk/bcm/clk-iproc-asiu.c
@@ -222,10 +222,6 @@
 		struct iproc_asiu_clk *asiu_clk;
 		const char *clk_name;
 
-		clk_name = kzalloc(IPROC_CLK_NAME_LEN, GFP_KERNEL);
-		if (WARN_ON(!clk_name))
-			goto err_clk_register;
-
 		ret = of_property_read_string_index(node, "clock-output-names",
 						    i, &clk_name);
 		if (WARN_ON(ret))
@@ -259,7 +255,7 @@
 
 err_clk_register:
 	for (i = 0; i < num_clks; i++)
-		kfree(asiu->clks[i].name);
+		clk_unregister(asiu->clk_data.clks[i]);
 	iounmap(asiu->gate_base);
 
 err_iomap_gate:
diff --git a/drivers/clk/bcm/clk-iproc-pll.c b/drivers/clk/bcm/clk-iproc-pll.c
index 46fb84b..2dda4e8 100644
--- a/drivers/clk/bcm/clk-iproc-pll.c
+++ b/drivers/clk/bcm/clk-iproc-pll.c
@@ -366,7 +366,7 @@
 	val = readl(pll->pll_base + ctrl->ndiv_int.offset);
 	ndiv_int = (val >> ctrl->ndiv_int.shift) &
 		bit_mask(ctrl->ndiv_int.width);
-	ndiv = ndiv_int << ctrl->ndiv_int.shift;
+	ndiv = (u64)ndiv_int << ctrl->ndiv_int.shift;
 
 	if (ctrl->flags & IPROC_CLK_PLL_HAS_NDIV_FRAC) {
 		val = readl(pll->pll_base + ctrl->ndiv_frac.offset);
@@ -374,7 +374,8 @@
 			bit_mask(ctrl->ndiv_frac.width);
 
 		if (ndiv_frac != 0)
-			ndiv = (ndiv_int << ctrl->ndiv_int.shift) | ndiv_frac;
+			ndiv = ((u64)ndiv_int << ctrl->ndiv_int.shift) |
+				ndiv_frac;
 	}
 
 	val = readl(pll->pll_base + ctrl->pdiv.offset);
@@ -655,10 +656,6 @@
 		memset(&init, 0, sizeof(init));
 		parent_name = node->name;
 
-		clk_name = kzalloc(IPROC_CLK_NAME_LEN, GFP_KERNEL);
-		if (WARN_ON(!clk_name))
-			goto err_clk_register;
-
 		ret = of_property_read_string_index(node, "clock-output-names",
 						    i, &clk_name);
 		if (WARN_ON(ret))
@@ -690,10 +687,8 @@
 	return;
 
 err_clk_register:
-	for (i = 0; i < num_clks; i++) {
-		kfree(pll->clks[i].name);
+	for (i = 0; i < num_clks; i++)
 		clk_unregister(pll->clk_data.clks[i]);
-	}
 
 err_pll_register:
 	if (pll->asiu_base)
diff --git a/drivers/clk/clk-stm32f4.c b/drivers/clk/clk-stm32f4.c
index b9b12a7..3f6f7ad 100644
--- a/drivers/clk/clk-stm32f4.c
+++ b/drivers/clk/clk-stm32f4.c
@@ -268,7 +268,7 @@
 	memcpy(table, stm32f42xx_gate_map, sizeof(table));
 
 	/* only bits set in table can be used as indices */
-	if (WARN_ON(secondary > 8 * sizeof(table) ||
+	if (WARN_ON(secondary >= BITS_PER_BYTE * sizeof(table) ||
 		    0 == (table[BIT_ULL_WORD(secondary)] &
 			  BIT_ULL_MASK(secondary))))
 		return -EINVAL;
diff --git a/drivers/clk/mediatek/clk-mt8173.c b/drivers/clk/mediatek/clk-mt8173.c
index 4b9e04c..8b6523d 100644
--- a/drivers/clk/mediatek/clk-mt8173.c
+++ b/drivers/clk/mediatek/clk-mt8173.c
@@ -700,6 +700,22 @@
 	MUX(CLK_PERI_UART3_SEL, "uart3_ck_sel", uart_ck_sel_parents, 0x40c, 3, 1),
 };
 
+static struct clk_onecell_data *mt8173_top_clk_data __initdata;
+static struct clk_onecell_data *mt8173_pll_clk_data __initdata;
+
+static void __init mtk_clk_enable_critical(void)
+{
+	if (!mt8173_top_clk_data || !mt8173_pll_clk_data)
+		return;
+
+	clk_prepare_enable(mt8173_pll_clk_data->clks[CLK_APMIXED_ARMCA15PLL]);
+	clk_prepare_enable(mt8173_pll_clk_data->clks[CLK_APMIXED_ARMCA7PLL]);
+	clk_prepare_enable(mt8173_top_clk_data->clks[CLK_TOP_MEM_SEL]);
+	clk_prepare_enable(mt8173_top_clk_data->clks[CLK_TOP_DDRPHYCFG_SEL]);
+	clk_prepare_enable(mt8173_top_clk_data->clks[CLK_TOP_CCI400_SEL]);
+	clk_prepare_enable(mt8173_top_clk_data->clks[CLK_TOP_RTC_SEL]);
+}
+
 static void __init mtk_topckgen_init(struct device_node *node)
 {
 	struct clk_onecell_data *clk_data;
@@ -712,19 +728,19 @@
 		return;
 	}
 
-	clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK);
+	mt8173_top_clk_data = clk_data = mtk_alloc_clk_data(CLK_TOP_NR_CLK);
 
 	mtk_clk_register_factors(root_clk_alias, ARRAY_SIZE(root_clk_alias), clk_data);
 	mtk_clk_register_factors(top_divs, ARRAY_SIZE(top_divs), clk_data);
 	mtk_clk_register_composites(top_muxes, ARRAY_SIZE(top_muxes), base,
 			&mt8173_clk_lock, clk_data);
 
-	clk_prepare_enable(clk_data->clks[CLK_TOP_CCI400_SEL]);
-
 	r = of_clk_add_provider(node, of_clk_src_onecell_get, clk_data);
 	if (r)
 		pr_err("%s(): could not register clock provider: %d\n",
 			__func__, r);
+
+	mtk_clk_enable_critical();
 }
 CLK_OF_DECLARE(mtk_topckgen, "mediatek,mt8173-topckgen", mtk_topckgen_init);
 
@@ -818,13 +834,13 @@
 {
 	struct clk_onecell_data *clk_data;
 
-	clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK);
+	mt8173_pll_clk_data = clk_data = mtk_alloc_clk_data(CLK_APMIXED_NR_CLK);
 	if (!clk_data)
 		return;
 
 	mtk_clk_register_plls(node, plls, ARRAY_SIZE(plls), clk_data);
 
-	clk_prepare_enable(clk_data->clks[CLK_APMIXED_ARMCA15PLL]);
+	mtk_clk_enable_critical();
 }
 CLK_OF_DECLARE(mtk_apmixedsys, "mediatek,mt8173-apmixedsys",
 		mtk_apmixedsys_init);
diff --git a/drivers/clk/pxa/clk-pxa3xx.c b/drivers/clk/pxa/clk-pxa3xx.c
index 4b93a1e..ac03ba4 100644
--- a/drivers/clk/pxa/clk-pxa3xx.c
+++ b/drivers/clk/pxa/clk-pxa3xx.c
@@ -126,7 +126,7 @@
 PARENTS(pxa3xx_sbus) = { "ring_osc_60mhz", "system_bus" };
 PARENTS(pxa3xx_smemcbus) = { "ring_osc_60mhz", "smemc" };
 
-#define CKEN_AB(bit) ((CKEN_ ## bit > 31) ? &CKENA : &CKENB)
+#define CKEN_AB(bit) ((CKEN_ ## bit > 31) ? &CKENB : &CKENA)
 #define PXA3XX_CKEN(dev_id, con_id, parents, mult_lp, div_lp, mult_hp,	\
 		    div_hp, bit, is_lp, flags)				\
 	PXA_CKEN(dev_id, con_id, bit, parents, mult_lp, div_lp,		\
diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c
index b95d17f..92936f0 100644
--- a/drivers/clk/qcom/clk-rcg2.c
+++ b/drivers/clk/qcom/clk-rcg2.c
@@ -530,19 +530,16 @@
 	struct clk_rcg2 *rcg = to_clk_rcg2(hw);
 	struct freq_tbl f = *rcg->freq_tbl;
 	const struct frac_entry *frac = frac_table_pixel;
-	unsigned long request, src_rate;
+	unsigned long request;
 	int delta = 100000;
 	u32 mask = BIT(rcg->hid_width) - 1;
 	u32 hid_div;
-	int index = qcom_find_src_index(hw, rcg->parent_map, f.src);
-	struct clk *parent = clk_get_parent_by_index(hw->clk, index);
 
 	for (; frac->num; frac++) {
 		request = (rate * frac->den) / frac->num;
 
-		src_rate = __clk_round_rate(parent, request);
-		if ((src_rate < (request - delta)) ||
-			(src_rate > (request + delta)))
+		if ((parent_rate < (request - delta)) ||
+			(parent_rate > (request + delta)))
 			continue;
 
 		regmap_read(rcg->clkr.regmap, rcg->cmd_rcgr + CFG_REG,
diff --git a/drivers/clk/spear/clk-aux-synth.c b/drivers/clk/spear/clk-aux-synth.c
index bdfb4421..f271c35 100644
--- a/drivers/clk/spear/clk-aux-synth.c
+++ b/drivers/clk/spear/clk-aux-synth.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/spear/clk-frac-synth.c b/drivers/clk/spear/clk-frac-synth.c
index dffd4ce..58d678b 100644
--- a/drivers/clk/spear/clk-frac-synth.c
+++ b/drivers/clk/spear/clk-frac-synth.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/spear/clk-gpt-synth.c b/drivers/clk/spear/clk-gpt-synth.c
index 1afc18c..1a722e9 100644
--- a/drivers/clk/spear/clk-gpt-synth.c
+++ b/drivers/clk/spear/clk-gpt-synth.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/spear/clk-vco-pll.c b/drivers/clk/spear/clk-vco-pll.c
index 1b9b65b..5ebddc5 100644
--- a/drivers/clk/spear/clk-vco-pll.c
+++ b/drivers/clk/spear/clk-vco-pll.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/spear/clk.c b/drivers/clk/spear/clk.c
index 628b6d5..157fe09 100644
--- a/drivers/clk/spear/clk.c
+++ b/drivers/clk/spear/clk.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/spear/clk.h b/drivers/clk/spear/clk.h
index 9317376..9834944 100644
--- a/drivers/clk/spear/clk.h
+++ b/drivers/clk/spear/clk.h
@@ -2,7 +2,7 @@
  * Clock framework definitions for SPEAr platform
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/spear/spear1310_clock.c b/drivers/clk/spear/spear1310_clock.c
index 4daa597..222ce108 100644
--- a/drivers/clk/spear/spear1310_clock.c
+++ b/drivers/clk/spear/spear1310_clock.c
@@ -4,7 +4,7 @@
  * SPEAr1310 machine clock framework source file
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/spear/spear1340_clock.c b/drivers/clk/spear/spear1340_clock.c
index 5a5c664..973c9d3 100644
--- a/drivers/clk/spear/spear1340_clock.c
+++ b/drivers/clk/spear/spear1340_clock.c
@@ -4,7 +4,7 @@
  * SPEAr1340 machine clock framework source file
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/spear/spear3xx_clock.c b/drivers/clk/spear/spear3xx_clock.c
index bb5f387..404a55e 100644
--- a/drivers/clk/spear/spear3xx_clock.c
+++ b/drivers/clk/spear/spear3xx_clock.c
@@ -2,7 +2,7 @@
  * SPEAr3xx machines clock framework source file
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/spear/spear6xx_clock.c b/drivers/clk/spear/spear6xx_clock.c
index 4f649c9..231061f 100644
--- a/drivers/clk/spear/spear6xx_clock.c
+++ b/drivers/clk/spear/spear6xx_clock.c
@@ -2,7 +2,7 @@
  * SPEAr6xx machines clock framework source file
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/clk/st/clk-flexgen.c b/drivers/clk/st/clk-flexgen.c
index 657ca14..8dd8cce 100644
--- a/drivers/clk/st/clk-flexgen.c
+++ b/drivers/clk/st/clk-flexgen.c
@@ -190,7 +190,7 @@
 
 	init.name = name;
 	init.ops = &flexgen_ops;
-	init.flags = CLK_IS_BASIC | flexgen_flags;
+	init.flags = CLK_IS_BASIC | CLK_GET_RATE_NOCACHE | flexgen_flags;
 	init.parent_names = parent_names;
 	init.num_parents = num_parents;
 
@@ -303,6 +303,8 @@
 	if (!rlock)
 		goto err;
 
+	spin_lock_init(rlock);
+
 	for (i = 0; i < clk_data->clk_num; i++) {
 		struct clk *clk;
 		const char *clk_name;
diff --git a/drivers/clk/st/clkgen-fsyn.c b/drivers/clk/st/clkgen-fsyn.c
index e94197f..d9eb2e1 100644
--- a/drivers/clk/st/clkgen-fsyn.c
+++ b/drivers/clk/st/clkgen-fsyn.c
@@ -340,7 +340,7 @@
 		    CLKGEN_FIELD(0x30c, 0xf, 20),
 		    CLKGEN_FIELD(0x310, 0xf, 20) },
 	.lockstatus_present = true,
-	.lock_status = CLKGEN_FIELD(0x2A0, 0x1, 24),
+	.lock_status = CLKGEN_FIELD(0x2f0, 0x1, 24),
 	.powerup_polarity = 1,
 	.standby_polarity = 1,
 	.pll_ops	= &st_quadfs_pll_c32_ops,
@@ -489,7 +489,7 @@
 	struct st_clk_quadfs_pll *pll = to_quadfs_pll(hw);
 	u32 npda = CLKGEN_READ(pll, npda);
 
-	return !!npda;
+	return pll->data->powerup_polarity ? !npda : !!npda;
 }
 
 static int clk_fs660c32_vco_get_rate(unsigned long input, struct stm_fs *fs,
@@ -635,7 +635,7 @@
 
 	init.name = name;
 	init.ops = quadfs->pll_ops;
-	init.flags = CLK_IS_BASIC;
+	init.flags = CLK_IS_BASIC | CLK_GET_RATE_NOCACHE;
 	init.parent_names = &parent_name;
 	init.num_parents = 1;
 
@@ -774,7 +774,7 @@
 	if (fs->lock)
 		spin_lock_irqsave(fs->lock, flags);
 
-	CLKGEN_WRITE(fs, nsb[fs->chan], !fs->data->standby_polarity);
+	CLKGEN_WRITE(fs, nsb[fs->chan], fs->data->standby_polarity);
 
 	if (fs->lock)
 		spin_unlock_irqrestore(fs->lock, flags);
@@ -1082,10 +1082,6 @@
 		.compatible = "st,stih407-quadfs660-D",
 		.data = &st_fs660c32_D_407
 	},
-	{
-		.compatible = "st,stih407-quadfs660-D",
-		.data = (void *)&st_fs660c32_D_407
-	},
 	{}
 };
 
diff --git a/drivers/clk/st/clkgen-mux.c b/drivers/clk/st/clkgen-mux.c
index 4fbe6e0..717c4a9 100644
--- a/drivers/clk/st/clkgen-mux.c
+++ b/drivers/clk/st/clkgen-mux.c
@@ -237,7 +237,7 @@
 
 	init.name = name;
 	init.ops = &clkgena_divmux_ops;
-	init.flags = CLK_IS_BASIC;
+	init.flags = CLK_IS_BASIC | CLK_GET_RATE_NOCACHE;
 	init.parent_names = parent_names;
 	init.num_parents = num_parents;
 
@@ -513,7 +513,8 @@
 					  0, &clk_name))
 		return;
 
-	clk = clk_register_divider_table(NULL, clk_name, parent_name, 0,
+	clk = clk_register_divider_table(NULL, clk_name, parent_name,
+					 CLK_GET_RATE_NOCACHE,
 					 reg + data->offset, data->shift, 1,
 					 0, data->table, NULL);
 	if (IS_ERR(clk))
@@ -582,7 +583,7 @@
 };
 static struct clkgen_mux_data stih407_a9_mux_data = {
 	.offset = 0x1a4,
-	.shift = 1,
+	.shift = 0,
 	.width = 2,
 };
 
@@ -786,7 +787,8 @@
 					     &mux->hw, &clk_mux_ops,
 					     &div->hw, &clk_divider_ops,
 					     &gate->hw, &clk_gate_ops,
-					     data->clk_flags);
+					     data->clk_flags |
+					     CLK_GET_RATE_NOCACHE);
 		if (IS_ERR(clk)) {
 			kfree(gate);
 			kfree(div);
diff --git a/drivers/clk/st/clkgen-pll.c b/drivers/clk/st/clkgen-pll.c
index 1065322..72d1c27 100644
--- a/drivers/clk/st/clkgen-pll.c
+++ b/drivers/clk/st/clkgen-pll.c
@@ -406,7 +406,7 @@
 	init.name = clk_name;
 	init.ops = pll_data->ops;
 
-	init.flags = CLK_IS_BASIC;
+	init.flags = CLK_IS_BASIC | CLK_GET_RATE_NOCACHE;
 	init.parent_names = &parent_name;
 	init.num_parents  = 1;
 
diff --git a/drivers/clk/sunxi/clk-sunxi.c b/drivers/clk/sunxi/clk-sunxi.c
index 9a82f17..abf7b37 100644
--- a/drivers/clk/sunxi/clk-sunxi.c
+++ b/drivers/clk/sunxi/clk-sunxi.c
@@ -1391,6 +1391,7 @@
 CLK_OF_DECLARE(sun6i_a31_clk_init, "allwinner,sun6i-a31", sun6i_init_clocks);
 CLK_OF_DECLARE(sun6i_a31s_clk_init, "allwinner,sun6i-a31s", sun6i_init_clocks);
 CLK_OF_DECLARE(sun8i_a23_clk_init, "allwinner,sun8i-a23", sun6i_init_clocks);
+CLK_OF_DECLARE(sun8i_a33_clk_init, "allwinner,sun8i-a33", sun6i_init_clocks);
 
 static void __init sun9i_init_clocks(struct device_node *node)
 {
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index b8ff3c6..c96de14 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -661,6 +661,9 @@
 {
 	struct sh_cmt_channel *ch = cs_to_sh_cmt(cs);
 
+	if (!ch->cs_enabled)
+		return;
+
 	sh_cmt_stop(ch, FLAG_CLOCKSOURCE);
 	pm_genpd_syscore_poweroff(&ch->cmt->pdev->dev);
 }
@@ -669,6 +672,9 @@
 {
 	struct sh_cmt_channel *ch = cs_to_sh_cmt(cs);
 
+	if (!ch->cs_enabled)
+		return;
+
 	pm_genpd_syscore_poweron(&ch->cmt->pdev->dev);
 	sh_cmt_start(ch, FLAG_CLOCKSOURCE);
 }
diff --git a/drivers/clocksource/timer-imx-gpt.c b/drivers/clocksource/timer-imx-gpt.c
index 879c784..86c7eb6 100644
--- a/drivers/clocksource/timer-imx-gpt.c
+++ b/drivers/clocksource/timer-imx-gpt.c
@@ -462,6 +462,7 @@
 	BUG_ON(!imxtm->base);
 
 	imxtm->type = type;
+	imxtm->irq = irq;
 
 	_mxc_timer_init(imxtm);
 }
@@ -529,6 +530,7 @@
 
 CLOCKSOURCE_OF_DECLARE(imx1_timer, "fsl,imx1-gpt", imx1_timer_init_dt);
 CLOCKSOURCE_OF_DECLARE(imx21_timer, "fsl,imx21-gpt", imx21_timer_init_dt);
+CLOCKSOURCE_OF_DECLARE(imx27_timer, "fsl,imx27-gpt", imx21_timer_init_dt);
 CLOCKSOURCE_OF_DECLARE(imx31_timer, "fsl,imx31-gpt", imx31_timer_init_dt);
 CLOCKSOURCE_OF_DECLARE(imx25_timer, "fsl,imx25-gpt", imx31_timer_init_dt);
 CLOCKSOURCE_OF_DECLARE(imx50_timer, "fsl,imx50-gpt", imx31_timer_init_dt);
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index b612411..7a3c30c 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -169,6 +169,15 @@
 }
 EXPORT_SYMBOL_GPL(get_governor_parent_kobj);
 
+struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
+
+	return policy && !policy_is_inactive(policy) ?
+		policy->freq_table : NULL;
+}
+EXPORT_SYMBOL_GPL(cpufreq_frequency_get_table);
+
 static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 {
 	u64 idle_time;
@@ -993,7 +1002,7 @@
 	int ret = 0;
 
 	/* Some related CPUs might not be present (physically hotplugged) */
-	for_each_cpu_and(j, policy->related_cpus, cpu_present_mask) {
+	for_each_cpu(j, policy->real_cpus) {
 		if (j == policy->kobj_cpu)
 			continue;
 
@@ -1010,7 +1019,7 @@
 	unsigned int j;
 
 	/* Some related CPUs might not be present (physically hotplugged) */
-	for_each_cpu_and(j, policy->related_cpus, cpu_present_mask) {
+	for_each_cpu(j, policy->real_cpus) {
 		if (j == policy->kobj_cpu)
 			continue;
 
@@ -1132,6 +1141,7 @@
 
 		down_write(&policy->rwsem);
 		policy->cpu = cpu;
+		policy->governor = NULL;
 		up_write(&policy->rwsem);
 	}
 
@@ -1153,11 +1163,14 @@
 	if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL))
 		goto err_free_cpumask;
 
+	if (!zalloc_cpumask_var(&policy->real_cpus, GFP_KERNEL))
+		goto err_free_rcpumask;
+
 	ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, &dev->kobj,
 				   "cpufreq");
 	if (ret) {
 		pr_err("%s: failed to init policy->kobj: %d\n", __func__, ret);
-		goto err_free_rcpumask;
+		goto err_free_real_cpus;
 	}
 
 	INIT_LIST_HEAD(&policy->policy_list);
@@ -1174,6 +1187,8 @@
 
 	return policy;
 
+err_free_real_cpus:
+	free_cpumask_var(policy->real_cpus);
 err_free_rcpumask:
 	free_cpumask_var(policy->related_cpus);
 err_free_cpumask:
@@ -1224,6 +1239,7 @@
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
 	cpufreq_policy_put_kobj(policy, notify);
+	free_cpumask_var(policy->real_cpus);
 	free_cpumask_var(policy->related_cpus);
 	free_cpumask_var(policy->cpus);
 	kfree(policy);
@@ -1248,14 +1264,17 @@
 
 	pr_debug("adding CPU %u\n", cpu);
 
-	/*
-	 * Only possible if 'cpu' wasn't physically present earlier and we are
-	 * here from subsys_interface add callback. A hotplug notifier will
-	 * follow and we will handle it like logical CPU hotplug then. For now,
-	 * just create the sysfs link.
-	 */
-	if (cpu_is_offline(cpu))
-		return add_cpu_dev_symlink(per_cpu(cpufreq_cpu_data, cpu), cpu);
+	if (cpu_is_offline(cpu)) {
+		/*
+		 * Only possible if we are here from the subsys_interface add
+		 * callback.  A hotplug notifier will follow and we will handle
+		 * it as CPU online then.  For now, just create the sysfs link,
+		 * unless there is no policy or the link is already present.
+		 */
+		policy = per_cpu(cpufreq_cpu_data, cpu);
+		return policy && !cpumask_test_and_set_cpu(cpu, policy->real_cpus)
+			? add_cpu_dev_symlink(policy, cpu) : 0;
+	}
 
 	if (!down_read_trylock(&cpufreq_rwsem))
 		return 0;
@@ -1297,6 +1316,10 @@
 	/* related cpus should atleast have policy->cpus */
 	cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
 
+	/* Remember which CPUs have been present at the policy creation time. */
+	if (!recover_policy)
+		cpumask_and(policy->real_cpus, policy->cpus, cpu_present_mask);
+
 	/*
 	 * affected cpus must always be the one, which are online. We aren't
 	 * managing offline cpus here.
@@ -1410,8 +1433,7 @@
 	return ret;
 }
 
-static int __cpufreq_remove_dev_prepare(struct device *dev,
-					struct subsys_interface *sif)
+static int __cpufreq_remove_dev_prepare(struct device *dev)
 {
 	unsigned int cpu = dev->id;
 	int ret = 0;
@@ -1427,10 +1449,8 @@
 
 	if (has_target()) {
 		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
-		if (ret) {
+		if (ret)
 			pr_err("%s: Failed to stop governor\n", __func__);
-			return ret;
-		}
 	}
 
 	down_write(&policy->rwsem);
@@ -1463,8 +1483,7 @@
 	return ret;
 }
 
-static int __cpufreq_remove_dev_finish(struct device *dev,
-				       struct subsys_interface *sif)
+static int __cpufreq_remove_dev_finish(struct device *dev)
 {
 	unsigned int cpu = dev->id;
 	int ret;
@@ -1482,10 +1501,8 @@
 	/* If cpu is last user of policy, free policy */
 	if (has_target()) {
 		ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
-		if (ret) {
+		if (ret)
 			pr_err("%s: Failed to exit governor\n", __func__);
-			return ret;
-		}
 	}
 
 	/*
@@ -1496,10 +1513,6 @@
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
 
-	/* Free the policy only if the driver is getting removed. */
-	if (sif)
-		cpufreq_policy_free(policy, true);
-
 	return 0;
 }
 
@@ -1511,42 +1524,41 @@
 static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 {
 	unsigned int cpu = dev->id;
-	int ret;
+	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
-	/*
-	 * Only possible if 'cpu' is getting physically removed now. A hotplug
-	 * notifier should have already been called and we just need to remove
-	 * link or free policy here.
-	 */
-	if (cpu_is_offline(cpu)) {
-		struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
-		struct cpumask mask;
+	if (!policy)
+		return 0;
 
-		if (!policy)
-			return 0;
+	if (cpu_online(cpu)) {
+		__cpufreq_remove_dev_prepare(dev);
+		__cpufreq_remove_dev_finish(dev);
+	}
 
-		cpumask_copy(&mask, policy->related_cpus);
-		cpumask_clear_cpu(cpu, &mask);
+	cpumask_clear_cpu(cpu, policy->real_cpus);
 
-		/*
-		 * Free policy only if all policy->related_cpus are removed
-		 * physically.
-		 */
-		if (cpumask_intersects(&mask, cpu_present_mask)) {
-			remove_cpu_dev_symlink(policy, cpu);
-			return 0;
-		}
-
+	if (cpumask_empty(policy->real_cpus)) {
 		cpufreq_policy_free(policy, true);
 		return 0;
 	}
 
-	ret = __cpufreq_remove_dev_prepare(dev, sif);
+	if (cpu != policy->kobj_cpu) {
+		remove_cpu_dev_symlink(policy, cpu);
+	} else {
+		/*
+		 * The CPU owning the policy object is going away.  Move it to
+		 * another suitable CPU.
+		 */
+		unsigned int new_cpu = cpumask_first(policy->real_cpus);
+		struct device *new_dev = get_cpu_device(new_cpu);
 
-	if (!ret)
-		ret = __cpufreq_remove_dev_finish(dev, sif);
+		dev_dbg(dev, "%s: Moving policy object to CPU%u\n", __func__, new_cpu);
 
-	return ret;
+		sysfs_remove_link(&new_dev->kobj, "cpufreq");
+		policy->kobj_cpu = new_cpu;
+		WARN_ON(kobject_move(&policy->kobj, &new_dev->kobj));
+	}
+
+	return 0;
 }
 
 static void handle_update(struct work_struct *work)
@@ -2385,11 +2397,11 @@
 			break;
 
 		case CPU_DOWN_PREPARE:
-			__cpufreq_remove_dev_prepare(dev, NULL);
+			__cpufreq_remove_dev_prepare(dev);
 			break;
 
 		case CPU_POST_DEAD:
-			__cpufreq_remove_dev_finish(dev, NULL);
+			__cpufreq_remove_dev_finish(dev);
 			break;
 
 		case CPU_DOWN_FAILED:
diff --git a/drivers/cpufreq/exynos-cpufreq.c b/drivers/cpufreq/exynos-cpufreq.c
index ae5b2bd..fa3dd84 100644
--- a/drivers/cpufreq/exynos-cpufreq.c
+++ b/drivers/cpufreq/exynos-cpufreq.c
@@ -180,7 +180,7 @@
 		ret = exynos5250_cpufreq_init(exynos_info);
 	} else {
 		pr_err("%s: Unknown SoC type\n", __func__);
-		return -ENODEV;
+		ret = -ENODEV;
 	}
 
 	if (ret)
@@ -188,12 +188,14 @@
 
 	if (exynos_info->set_freq == NULL) {
 		dev_err(&pdev->dev, "No set_freq function (ERR)\n");
+		ret = -EINVAL;
 		goto err_vdd_arm;
 	}
 
 	arm_regulator = regulator_get(NULL, "vdd_arm");
 	if (IS_ERR(arm_regulator)) {
 		dev_err(&pdev->dev, "failed to get resource vdd_arm\n");
+		ret = -EINVAL;
 		goto err_vdd_arm;
 	}
 
@@ -225,7 +227,7 @@
 	regulator_put(arm_regulator);
 err_vdd_arm:
 	kfree(exynos_info);
-	return -EINVAL;
+	return ret;
 }
 
 static struct platform_driver exynos_cpufreq_platdrv = {
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index df14766..dfbbf981 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -297,15 +297,6 @@
 }
 EXPORT_SYMBOL_GPL(cpufreq_table_validate_and_show);
 
-struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu);
-
-struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu)
-{
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
-	return policy ? policy->freq_table : NULL;
-}
-EXPORT_SYMBOL_GPL(cpufreq_frequency_get_table);
-
 MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
 MODULE_DESCRIPTION("CPUfreq frequency table helpers");
 MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 15ada47..fcb929e 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -681,6 +681,7 @@
 		.get_max = core_get_max_pstate,
 		.get_min = core_get_min_pstate,
 		.get_turbo = knl_get_turbo_pstate,
+		.get_scaling = core_get_scaling,
 		.set = core_set_pstate,
 	},
 };
diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index fc897ba..cd593c1 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -3,7 +3,7 @@
  *
  * The 2E revision of loongson processor not support this feature.
  *
- * Copyright (C) 2006 - 2008 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2006 - 2008 Lemote Inc. & Institute of Computing Technology
  * Author: Yanhua, yanh@lemote.com
  *
  * This file is subject to the terms and conditions of the GNU General Public
@@ -20,7 +20,7 @@
 #include <asm/clock.h>
 #include <asm/idle.h>
 
-#include <asm/mach-loongson/loongson.h>
+#include <asm/mach-loongson64/loongson.h>
 
 static uint nowait;
 
diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c
index e8e2775..48b7228 100644
--- a/drivers/cpuidle/cpuidle.c
+++ b/drivers/cpuidle/cpuidle.c
@@ -112,7 +112,12 @@
 static void enter_freeze_proper(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev, int index)
 {
-	tick_freeze();
+	/*
+	 * trace_suspend_resume() called by tick_freeze() for the last CPU
+	 * executing it contains RCU usage regarded as invalid in the idle
+	 * context, so tell RCU about that.
+	 */
+	RCU_NONIDLE(tick_freeze());
 	/*
 	 * The state used here cannot be a "coupled" one, because the "coupled"
 	 * cpuidle mechanism enables interrupts and doing that with timekeeping
@@ -122,7 +127,7 @@
 	WARN_ON(!irqs_disabled());
 	/*
 	 * timekeeping_resume() that will be called by tick_unfreeze() for the
-	 * last CPU executing it calls functions containing RCU read-side
+	 * first CPU executing it calls functions containing RCU read-side
 	 * critical sections, so tell RCU about that.
 	 */
 	RCU_NONIDLE(tick_unfreeze());
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index dae1e80..f9c7875 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -909,13 +909,14 @@
 			  state->buflen_1;
 	u32 *sh_desc = ctx->sh_desc_fin, *desc;
 	dma_addr_t ptr = ctx->sh_desc_fin_dma;
-	int sec4_sg_bytes;
+	int sec4_sg_bytes, sec4_sg_src_index;
 	int digestsize = crypto_ahash_digestsize(ahash);
 	struct ahash_edesc *edesc;
 	int ret = 0;
 	int sh_len;
 
-	sec4_sg_bytes = (1 + (buflen ? 1 : 0)) * sizeof(struct sec4_sg_entry);
+	sec4_sg_src_index = 1 + (buflen ? 1 : 0);
+	sec4_sg_bytes = sec4_sg_src_index * sizeof(struct sec4_sg_entry);
 
 	/* allocate space for base edesc and hw desc commands, link tables */
 	edesc = kmalloc(sizeof(struct ahash_edesc) + DESC_JOB_IO_LEN +
@@ -942,7 +943,7 @@
 	state->buf_dma = try_buf_map_to_sec4_sg(jrdev, edesc->sec4_sg + 1,
 						buf, state->buf_dma, buflen,
 						last_buflen);
-	(edesc->sec4_sg + sec4_sg_bytes - 1)->len |= SEC4_SG_LEN_FIN;
+	(edesc->sec4_sg + sec4_sg_src_index - 1)->len |= SEC4_SG_LEN_FIN;
 
 	edesc->sec4_sg_dma = dma_map_single(jrdev, edesc->sec4_sg,
 					    sec4_sg_bytes, DMA_TO_DEVICE);
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 7ba495f..402631a 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -905,7 +905,6 @@
 		crypt->mode |= NPE_OP_NOT_IN_PLACE;
 		/* This was never tested by Intel
 		 * for more than one dst buffer, I think. */
-		BUG_ON(req->dst->length < nbytes);
 		req_ctx->dst = NULL;
 		if (!chainup_buffers(dev, req->dst, nbytes, &dst_hook,
 					flags, DMA_FROM_DEVICE))
diff --git a/drivers/crypto/nx/nx-aes-ccm.c b/drivers/crypto/nx/nx-aes-ccm.c
index 67f8081..e4311ce 100644
--- a/drivers/crypto/nx/nx-aes-ccm.c
+++ b/drivers/crypto/nx/nx-aes-ccm.c
@@ -494,8 +494,9 @@
 static int ccm4309_aes_nx_encrypt(struct aead_request *req)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
 	struct blkcipher_desc desc;
-	u8 *iv = nx_ctx->priv.ccm.iv;
+	u8 *iv = rctx->iv;
 
 	iv[0] = 3;
 	memcpy(iv + 1, nx_ctx->priv.ccm.nonce, 3);
@@ -525,8 +526,9 @@
 static int ccm4309_aes_nx_decrypt(struct aead_request *req)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
 	struct blkcipher_desc desc;
-	u8 *iv = nx_ctx->priv.ccm.iv;
+	u8 *iv = rctx->iv;
 
 	iv[0] = 3;
 	memcpy(iv + 1, nx_ctx->priv.ccm.nonce, 3);
diff --git a/drivers/crypto/nx/nx-aes-ctr.c b/drivers/crypto/nx/nx-aes-ctr.c
index 2617cd4..dd7e9f3 100644
--- a/drivers/crypto/nx/nx-aes-ctr.c
+++ b/drivers/crypto/nx/nx-aes-ctr.c
@@ -72,7 +72,7 @@
 	if (key_len < CTR_RFC3686_NONCE_SIZE)
 		return -EINVAL;
 
-	memcpy(nx_ctx->priv.ctr.iv,
+	memcpy(nx_ctx->priv.ctr.nonce,
 	       in_key + key_len - CTR_RFC3686_NONCE_SIZE,
 	       CTR_RFC3686_NONCE_SIZE);
 
@@ -131,14 +131,15 @@
 				unsigned int           nbytes)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_blkcipher_ctx(desc->tfm);
-	u8 *iv = nx_ctx->priv.ctr.iv;
+	u8 iv[16];
 
+	memcpy(iv, nx_ctx->priv.ctr.nonce, CTR_RFC3686_IV_SIZE);
 	memcpy(iv + CTR_RFC3686_NONCE_SIZE,
 	       desc->info, CTR_RFC3686_IV_SIZE);
 	iv[12] = iv[13] = iv[14] = 0;
 	iv[15] = 1;
 
-	desc->info = nx_ctx->priv.ctr.iv;
+	desc->info = iv;
 
 	return ctr_aes_nx_crypt(desc, dst, src, nbytes);
 }
diff --git a/drivers/crypto/nx/nx-aes-gcm.c b/drivers/crypto/nx/nx-aes-gcm.c
index 08ac6d4..92c993f 100644
--- a/drivers/crypto/nx/nx-aes-gcm.c
+++ b/drivers/crypto/nx/nx-aes-gcm.c
@@ -317,6 +317,7 @@
 static int gcm_aes_nx_crypt(struct aead_request *req, int enc)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	struct blkcipher_desc desc;
 	unsigned int nbytes = req->cryptlen;
@@ -326,7 +327,7 @@
 
 	spin_lock_irqsave(&nx_ctx->lock, irq_flags);
 
-	desc.info = nx_ctx->priv.gcm.iv;
+	desc.info = rctx->iv;
 	/* initialize the counter */
 	*(u32 *)(desc.info + NX_GCM_CTR_OFFSET) = 1;
 
@@ -424,8 +425,8 @@
 
 static int gcm_aes_nx_encrypt(struct aead_request *req)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
-	char *iv = nx_ctx->priv.gcm.iv;
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
+	char *iv = rctx->iv;
 
 	memcpy(iv, req->iv, 12);
 
@@ -434,8 +435,8 @@
 
 static int gcm_aes_nx_decrypt(struct aead_request *req)
 {
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
-	char *iv = nx_ctx->priv.gcm.iv;
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
+	char *iv = rctx->iv;
 
 	memcpy(iv, req->iv, 12);
 
@@ -445,7 +446,8 @@
 static int gcm4106_aes_nx_encrypt(struct aead_request *req)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
-	char *iv = nx_ctx->priv.gcm.iv;
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
+	char *iv = rctx->iv;
 	char *nonce = nx_ctx->priv.gcm.nonce;
 
 	memcpy(iv, nonce, NX_GCM4106_NONCE_LEN);
@@ -457,7 +459,8 @@
 static int gcm4106_aes_nx_decrypt(struct aead_request *req)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(req->base.tfm);
-	char *iv = nx_ctx->priv.gcm.iv;
+	struct nx_gcm_rctx *rctx = aead_request_ctx(req);
+	char *iv = rctx->iv;
 	char *nonce = nx_ctx->priv.gcm.nonce;
 
 	memcpy(iv, nonce, NX_GCM4106_NONCE_LEN);
diff --git a/drivers/crypto/nx/nx-aes-xcbc.c b/drivers/crypto/nx/nx-aes-xcbc.c
index 8c2faff..c2f7d4b 100644
--- a/drivers/crypto/nx/nx-aes-xcbc.c
+++ b/drivers/crypto/nx/nx-aes-xcbc.c
@@ -42,6 +42,7 @@
 			   unsigned int         key_len)
 {
 	struct nx_crypto_ctx *nx_ctx = crypto_shash_ctx(desc);
+	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 
 	switch (key_len) {
 	case AES_KEYSIZE_128:
@@ -51,7 +52,7 @@
 		return -EINVAL;
 	}
 
-	memcpy(nx_ctx->priv.xcbc.key, in_key, key_len);
+	memcpy(csbcpb->cpb.aes_xcbc.key, in_key, key_len);
 
 	return 0;
 }
@@ -148,32 +149,29 @@
 	return rc;
 }
 
-static int nx_xcbc_init(struct shash_desc *desc)
+static int nx_crypto_ctx_aes_xcbc_init2(struct crypto_tfm *tfm)
 {
-	struct xcbc_state *sctx = shash_desc_ctx(desc);
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
+	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
-	struct nx_sg *out_sg;
-	int len;
+	int err;
+
+	err = nx_crypto_ctx_aes_xcbc_init(tfm);
+	if (err)
+		return err;
 
 	nx_ctx_init(nx_ctx, HCOP_FC_AES);
 
-	memset(sctx, 0, sizeof *sctx);
-
 	NX_CPB_SET_KEY_SIZE(csbcpb, NX_KS_AES_128);
 	csbcpb->cpb.hdr.mode = NX_MODE_AES_XCBC_MAC;
 
-	memcpy(csbcpb->cpb.aes_xcbc.key, nx_ctx->priv.xcbc.key, AES_BLOCK_SIZE);
-	memset(nx_ctx->priv.xcbc.key, 0, sizeof *nx_ctx->priv.xcbc.key);
+	return 0;
+}
 
-	len = AES_BLOCK_SIZE;
-	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
-				  &len, nx_ctx->ap->sglen);
+static int nx_xcbc_init(struct shash_desc *desc)
+{
+	struct xcbc_state *sctx = shash_desc_ctx(desc);
 
-	if (len != AES_BLOCK_SIZE)
-		return -EINVAL;
-
-	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+	memset(sctx, 0, sizeof *sctx);
 
 	return 0;
 }
@@ -186,6 +184,7 @@
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = nx_ctx->csbcpb;
 	struct nx_sg *in_sg;
+	struct nx_sg *out_sg;
 	u32 to_process = 0, leftover, total;
 	unsigned int max_sg_len;
 	unsigned long irq_flags;
@@ -213,6 +212,17 @@
 	max_sg_len = min_t(u64, max_sg_len,
 				nx_ctx->ap->databytelen/NX_PAGE_SIZE);
 
+	data_len = AES_BLOCK_SIZE;
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
+				  &len, nx_ctx->ap->sglen);
+
+	if (data_len != AES_BLOCK_SIZE) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+
 	do {
 		to_process = total - to_process;
 		to_process = to_process & ~(AES_BLOCK_SIZE - 1);
@@ -235,8 +245,10 @@
 						(u8 *) sctx->buffer,
 						&data_len,
 						max_sg_len);
-			if (data_len != sctx->count)
-				return -EINVAL;
+			if (data_len != sctx->count) {
+				rc = -EINVAL;
+				goto out;
+			}
 		}
 
 		data_len = to_process - sctx->count;
@@ -245,8 +257,10 @@
 					&data_len,
 					max_sg_len);
 
-		if (data_len != to_process - sctx->count)
-			return -EINVAL;
+		if (data_len != to_process - sctx->count) {
+			rc = -EINVAL;
+			goto out;
+		}
 
 		nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) *
 					sizeof(struct nx_sg);
@@ -325,15 +339,19 @@
 	in_sg = nx_build_sg_list(nx_ctx->in_sg, (u8 *)sctx->buffer,
 				 &len, nx_ctx->ap->sglen);
 
-	if (len != sctx->count)
-		return -EINVAL;
+	if (len != sctx->count) {
+		rc = -EINVAL;
+		goto out;
+	}
 
 	len = AES_BLOCK_SIZE;
 	out_sg = nx_build_sg_list(nx_ctx->out_sg, out, &len,
 				  nx_ctx->ap->sglen);
 
-	if (len != AES_BLOCK_SIZE)
-		return -EINVAL;
+	if (len != AES_BLOCK_SIZE) {
+		rc = -EINVAL;
+		goto out;
+	}
 
 	nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
 	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
@@ -372,7 +390,7 @@
 		.cra_blocksize   = AES_BLOCK_SIZE,
 		.cra_module      = THIS_MODULE,
 		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-		.cra_init        = nx_crypto_ctx_aes_xcbc_init,
+		.cra_init        = nx_crypto_ctx_aes_xcbc_init2,
 		.cra_exit        = nx_crypto_ctx_exit,
 	}
 };
diff --git a/drivers/crypto/nx/nx-sha256.c b/drivers/crypto/nx/nx-sha256.c
index 4e91bdb..becb738 100644
--- a/drivers/crypto/nx/nx-sha256.c
+++ b/drivers/crypto/nx/nx-sha256.c
@@ -29,34 +29,28 @@
 #include "nx.h"
 
 
-static int nx_sha256_init(struct shash_desc *desc)
+static int nx_crypto_ctx_sha256_init(struct crypto_tfm *tfm)
 {
-	struct sha256_state *sctx = shash_desc_ctx(desc);
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
-	struct nx_sg *out_sg;
-	int len;
-	u32 max_sg_len;
+	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
+	int err;
+
+	err = nx_crypto_ctx_sha_init(tfm);
+	if (err)
+		return err;
 
 	nx_ctx_init(nx_ctx, HCOP_FC_SHA);
 
-	memset(sctx, 0, sizeof *sctx);
-
 	nx_ctx->ap = &nx_ctx->props[NX_PROPS_SHA256];
 
 	NX_CPB_SET_DIGEST_SIZE(nx_ctx->csbcpb, NX_DS_SHA256);
 
-	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
-			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
-	max_sg_len = min_t(u64, max_sg_len,
-			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+	return 0;
+}
 
-	len = SHA256_DIGEST_SIZE;
-	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
-				  &len, max_sg_len);
-	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+static int nx_sha256_init(struct shash_desc *desc) {
+	struct sha256_state *sctx = shash_desc_ctx(desc);
 
-	if (len != SHA256_DIGEST_SIZE)
-		return -EINVAL;
+	memset(sctx, 0, sizeof *sctx);
 
 	sctx->state[0] = __cpu_to_be32(SHA256_H0);
 	sctx->state[1] = __cpu_to_be32(SHA256_H1);
@@ -77,7 +71,7 @@
 	struct sha256_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
-	struct nx_sg *in_sg;
+	struct nx_sg *out_sg;
 	u64 to_process = 0, leftover, total;
 	unsigned long irq_flags;
 	int rc = 0;
@@ -102,24 +96,28 @@
 	NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
 	NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
 
-	in_sg = nx_ctx->in_sg;
 	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
 			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
 	max_sg_len = min_t(u64, max_sg_len,
 			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
 
+	data_len = SHA256_DIGEST_SIZE;
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
+				  &data_len, max_sg_len);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+
+	if (data_len != SHA256_DIGEST_SIZE) {
+		rc = -EINVAL;
+		goto out;
+	}
+
 	do {
-		/*
-		 * to_process: the SHA256_BLOCK_SIZE data chunk to process in
-		 * this update. This value is also restricted by the sg list
-		 * limits.
-		 */
-		to_process = total - to_process;
-		to_process = to_process & ~(SHA256_BLOCK_SIZE - 1);
+		int used_sgs = 0;
+		struct nx_sg *in_sg = nx_ctx->in_sg;
 
 		if (buf_len) {
 			data_len = buf_len;
-			in_sg = nx_build_sg_list(nx_ctx->in_sg,
+			in_sg = nx_build_sg_list(in_sg,
 						 (u8 *) sctx->buf,
 						 &data_len,
 						 max_sg_len);
@@ -128,15 +126,27 @@
 				rc = -EINVAL;
 				goto out;
 			}
+			used_sgs = in_sg - nx_ctx->in_sg;
 		}
 
+		/* to_process: SHA256_BLOCK_SIZE aligned chunk to be
+		 * processed in this iteration. This value is restricted
+		 * by sg list limits and number of sgs we already used
+		 * for leftover data. (see above)
+		 * In ideal case, we could allow NX_PAGE_SIZE * max_sg_len,
+		 * but because data may not be aligned, we need to account
+		 * for that too. */
+		to_process = min_t(u64, total,
+			(max_sg_len - 1 - used_sgs) * NX_PAGE_SIZE);
+		to_process = to_process & ~(SHA256_BLOCK_SIZE - 1);
+
 		data_len = to_process - buf_len;
 		in_sg = nx_build_sg_list(in_sg, (u8 *) data,
 					 &data_len, max_sg_len);
 
 		nx_ctx->op.inlen = (nx_ctx->in_sg - in_sg) * sizeof(struct nx_sg);
 
-		to_process = (data_len + buf_len);
+		to_process = data_len + buf_len;
 		leftover = total - to_process;
 
 		/*
@@ -282,7 +292,7 @@
 		.cra_blocksize   = SHA256_BLOCK_SIZE,
 		.cra_module      = THIS_MODULE,
 		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-		.cra_init        = nx_crypto_ctx_sha_init,
+		.cra_init        = nx_crypto_ctx_sha256_init,
 		.cra_exit        = nx_crypto_ctx_exit,
 	}
 };
diff --git a/drivers/crypto/nx/nx-sha512.c b/drivers/crypto/nx/nx-sha512.c
index e6a58d2..b6e183d 100644
--- a/drivers/crypto/nx/nx-sha512.c
+++ b/drivers/crypto/nx/nx-sha512.c
@@ -28,34 +28,29 @@
 #include "nx.h"
 
 
-static int nx_sha512_init(struct shash_desc *desc)
+static int nx_crypto_ctx_sha512_init(struct crypto_tfm *tfm)
 {
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
-	struct nx_sg *out_sg;
-	int len;
-	u32 max_sg_len;
+	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(tfm);
+	int err;
+
+	err = nx_crypto_ctx_sha_init(tfm);
+	if (err)
+		return err;
 
 	nx_ctx_init(nx_ctx, HCOP_FC_SHA);
 
-	memset(sctx, 0, sizeof *sctx);
-
 	nx_ctx->ap = &nx_ctx->props[NX_PROPS_SHA512];
 
 	NX_CPB_SET_DIGEST_SIZE(nx_ctx->csbcpb, NX_DS_SHA512);
 
-	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
-			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
-	max_sg_len = min_t(u64, max_sg_len,
-			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
+	return 0;
+}
 
-	len = SHA512_DIGEST_SIZE;
-	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
-				  &len, max_sg_len);
-	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+static int nx_sha512_init(struct shash_desc *desc)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
 
-	if (len != SHA512_DIGEST_SIZE)
-		return -EINVAL;
+	memset(sctx, 0, sizeof *sctx);
 
 	sctx->state[0] = __cpu_to_be64(SHA512_H0);
 	sctx->state[1] = __cpu_to_be64(SHA512_H1);
@@ -76,7 +71,7 @@
 	struct sha512_state *sctx = shash_desc_ctx(desc);
 	struct nx_crypto_ctx *nx_ctx = crypto_tfm_ctx(&desc->tfm->base);
 	struct nx_csbcpb *csbcpb = (struct nx_csbcpb *)nx_ctx->csbcpb;
-	struct nx_sg *in_sg;
+	struct nx_sg *out_sg;
 	u64 to_process, leftover = 0, total;
 	unsigned long irq_flags;
 	int rc = 0;
@@ -101,25 +96,28 @@
 	NX_CPB_FDM(csbcpb) |= NX_FDM_INTERMEDIATE;
 	NX_CPB_FDM(csbcpb) |= NX_FDM_CONTINUATION;
 
-	in_sg = nx_ctx->in_sg;
 	max_sg_len = min_t(u64, nx_ctx->ap->sglen,
 			nx_driver.of.max_sg_len/sizeof(struct nx_sg));
 	max_sg_len = min_t(u64, max_sg_len,
 			nx_ctx->ap->databytelen/NX_PAGE_SIZE);
 
+	data_len = SHA512_DIGEST_SIZE;
+	out_sg = nx_build_sg_list(nx_ctx->out_sg, (u8 *)sctx->state,
+				  &data_len, max_sg_len);
+	nx_ctx->op.outlen = (nx_ctx->out_sg - out_sg) * sizeof(struct nx_sg);
+
+	if (data_len != SHA512_DIGEST_SIZE) {
+		rc = -EINVAL;
+		goto out;
+	}
+
 	do {
-		/*
-		 * to_process: the SHA512_BLOCK_SIZE data chunk to process in
-		 * this update. This value is also restricted by the sg list
-		 * limits.
-		 */
-		to_process = total - leftover;
-		to_process = to_process & ~(SHA512_BLOCK_SIZE - 1);
-		leftover = total - to_process;
+		int used_sgs = 0;
+		struct nx_sg *in_sg = nx_ctx->in_sg;
 
 		if (buf_len) {
 			data_len = buf_len;
-			in_sg = nx_build_sg_list(nx_ctx->in_sg,
+			in_sg = nx_build_sg_list(in_sg,
 						 (u8 *) sctx->buf,
 						 &data_len, max_sg_len);
 
@@ -127,8 +125,20 @@
 				rc = -EINVAL;
 				goto out;
 			}
+			used_sgs = in_sg - nx_ctx->in_sg;
 		}
 
+		/* to_process: SHA512_BLOCK_SIZE aligned chunk to be
+		 * processed in this iteration. This value is restricted
+		 * by sg list limits and number of sgs we already used
+		 * for leftover data. (see above)
+		 * In ideal case, we could allow NX_PAGE_SIZE * max_sg_len,
+		 * but because data may not be aligned, we need to account
+		 * for that too. */
+		to_process = min_t(u64, total,
+			(max_sg_len - 1 - used_sgs) * NX_PAGE_SIZE);
+		to_process = to_process & ~(SHA512_BLOCK_SIZE - 1);
+
 		data_len = to_process - buf_len;
 		in_sg = nx_build_sg_list(in_sg, (u8 *) data,
 					 &data_len, max_sg_len);
@@ -140,7 +150,7 @@
 			goto out;
 		}
 
-		to_process = (data_len + buf_len);
+		to_process = data_len + buf_len;
 		leftover = total - to_process;
 
 		/*
@@ -288,7 +298,7 @@
 		.cra_blocksize   = SHA512_BLOCK_SIZE,
 		.cra_module      = THIS_MODULE,
 		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
-		.cra_init        = nx_crypto_ctx_sha_init,
+		.cra_init        = nx_crypto_ctx_sha512_init,
 		.cra_exit        = nx_crypto_ctx_exit,
 	}
 };
diff --git a/drivers/crypto/nx/nx.c b/drivers/crypto/nx/nx.c
index f6198f2..4369713 100644
--- a/drivers/crypto/nx/nx.c
+++ b/drivers/crypto/nx/nx.c
@@ -713,12 +713,15 @@
 /* entry points from the crypto tfm initializers */
 int nx_crypto_ctx_aes_ccm_init(struct crypto_tfm *tfm)
 {
+	crypto_aead_set_reqsize(__crypto_aead_cast(tfm),
+				sizeof(struct nx_ccm_rctx));
 	return nx_crypto_ctx_init(crypto_tfm_ctx(tfm), NX_FC_AES,
 				  NX_MODE_AES_CCM);
 }
 
 int nx_crypto_ctx_aes_gcm_init(struct crypto_aead *tfm)
 {
+	crypto_aead_set_reqsize(tfm, sizeof(struct nx_gcm_rctx));
 	return nx_crypto_ctx_init(crypto_aead_ctx(tfm), NX_FC_AES,
 				  NX_MODE_AES_GCM);
 }
diff --git a/drivers/crypto/nx/nx.h b/drivers/crypto/nx/nx.h
index de3ea87..cdff03a 100644
--- a/drivers/crypto/nx/nx.h
+++ b/drivers/crypto/nx/nx.h
@@ -2,6 +2,8 @@
 #ifndef __NX_H__
 #define __NX_H__
 
+#include <crypto/ctr.h>
+
 #define NX_NAME		"nx-crypto"
 #define NX_STRING	"IBM Power7+ Nest Accelerator Crypto Driver"
 #define NX_VERSION	"1.0"
@@ -91,8 +93,11 @@
 
 #define NX_GCM4106_NONCE_LEN		(4)
 #define NX_GCM_CTR_OFFSET		(12)
-struct nx_gcm_priv {
+struct nx_gcm_rctx {
 	u8 iv[16];
+};
+
+struct nx_gcm_priv {
 	u8 iauth_tag[16];
 	u8 nonce[NX_GCM4106_NONCE_LEN];
 };
@@ -100,8 +105,11 @@
 #define NX_CCM_AES_KEY_LEN		(16)
 #define NX_CCM4309_AES_KEY_LEN		(19)
 #define NX_CCM4309_NONCE_LEN		(3)
-struct nx_ccm_priv {
+struct nx_ccm_rctx {
 	u8 iv[16];
+};
+
+struct nx_ccm_priv {
 	u8 b0[16];
 	u8 iauth_tag[16];
 	u8 oauth_tag[16];
@@ -113,7 +121,7 @@
 };
 
 struct nx_ctr_priv {
-	u8 iv[16];
+	u8 nonce[CTR_RFC3686_NONCE_SIZE];
 };
 
 struct nx_crypto_ctx {
diff --git a/drivers/crypto/omap-des.c b/drivers/crypto/omap-des.c
index 4630709..0a70e46 100644
--- a/drivers/crypto/omap-des.c
+++ b/drivers/crypto/omap-des.c
@@ -536,9 +536,6 @@
 	dmaengine_terminate_all(dd->dma_lch_in);
 	dmaengine_terminate_all(dd->dma_lch_out);
 
-	dma_unmap_sg(dd->dev, dd->in_sg, dd->in_sg_len, DMA_TO_DEVICE);
-	dma_unmap_sg(dd->dev, dd->out_sg, dd->out_sg_len, DMA_FROM_DEVICE);
-
 	return err;
 }
 
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index 067402c..df427c0e 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -73,7 +73,8 @@
 				       ICP_QAT_HW_CIPHER_KEY_CONVERT, \
 				       ICP_QAT_HW_CIPHER_DECRYPT)
 
-static atomic_t active_dev;
+static DEFINE_MUTEX(algs_lock);
+static unsigned int active_devs;
 
 struct qat_alg_buf {
 	uint32_t len;
@@ -1280,7 +1281,10 @@
 
 int qat_algs_register(void)
 {
-	if (atomic_add_return(1, &active_dev) == 1) {
+	int ret = 0;
+
+	mutex_lock(&algs_lock);
+	if (++active_devs == 1) {
 		int i;
 
 		for (i = 0; i < ARRAY_SIZE(qat_algs); i++)
@@ -1289,21 +1293,25 @@
 				CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC :
 				CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC;
 
-		return crypto_register_algs(qat_algs, ARRAY_SIZE(qat_algs));
+		ret = crypto_register_algs(qat_algs, ARRAY_SIZE(qat_algs));
 	}
-	return 0;
+	mutex_unlock(&algs_lock);
+	return ret;
 }
 
 int qat_algs_unregister(void)
 {
-	if (atomic_sub_return(1, &active_dev) == 0)
-		return crypto_unregister_algs(qat_algs, ARRAY_SIZE(qat_algs));
-	return 0;
+	int ret = 0;
+
+	mutex_lock(&algs_lock);
+	if (--active_devs == 0)
+		ret = crypto_unregister_algs(qat_algs, ARRAY_SIZE(qat_algs));
+	mutex_unlock(&algs_lock);
+	return ret;
 }
 
 int qat_algs_init(void)
 {
-	atomic_set(&active_dev, 0);
 	crypto_get_default_rng();
 	return 0;
 }
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 59892126..d3629b7 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -48,6 +48,8 @@
 	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |\
 	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES))
 
+#define ATC_MAX_DSCR_TRIALS	10
+
 /*
  * Initial number of descriptors to allocate for each channel. This could
  * be increased during dma usage.
@@ -285,28 +287,19 @@
  *
  * @current_len: the number of bytes left before reading CTRLA
  * @ctrla: the value of CTRLA
- * @desc: the descriptor containing the transfer width
  */
-static inline int atc_calc_bytes_left(int current_len, u32 ctrla,
-					struct at_desc *desc)
+static inline int atc_calc_bytes_left(int current_len, u32 ctrla)
 {
-	return current_len - ((ctrla & ATC_BTSIZE_MAX) << desc->tx_width);
-}
+	u32 btsize = (ctrla & ATC_BTSIZE_MAX);
+	u32 src_width = ATC_REG_TO_SRC_WIDTH(ctrla);
 
-/**
- * atc_calc_bytes_left_from_reg - calculates the number of bytes left according
- * to the current value of CTRLA.
- *
- * @current_len: the number of bytes left before reading CTRLA
- * @atchan: the channel to read CTRLA for
- * @desc: the descriptor containing the transfer width
- */
-static inline int atc_calc_bytes_left_from_reg(int current_len,
-			struct at_dma_chan *atchan, struct at_desc *desc)
-{
-	u32 ctrla = channel_readl(atchan, CTRLA);
-
-	return atc_calc_bytes_left(current_len, ctrla, desc);
+	/*
+	 * According to the datasheet, when reading the Control A Register
+	 * (ctrla), the Buffer Transfer Size (btsize) bitfield refers to the
+	 * number of transfers completed on the Source Interface.
+	 * So btsize is always a number of source width transfers.
+	 */
+	return current_len - (btsize << src_width);
 }
 
 /**
@@ -320,7 +313,7 @@
 	struct at_desc *desc_first = atc_first_active(atchan);
 	struct at_desc *desc;
 	int ret;
-	u32 ctrla, dscr;
+	u32 ctrla, dscr, trials;
 
 	/*
 	 * If the cookie doesn't match to the currently running transfer then
@@ -346,15 +339,82 @@
 		 * the channel's DSCR register and compare it against the value
 		 * of the hardware linked list structure of each child
 		 * descriptor.
+		 *
+		 * The CTRLA register provides us with the amount of data
+		 * already read from the source for the current child
+		 * descriptor. So we can compute a more accurate residue by also
+		 * removing the number of bytes corresponding to this amount of
+		 * data.
+		 *
+		 * However, the DSCR and CTRLA registers cannot be read both
+		 * atomically. Hence a race condition may occur: the first read
+		 * register may refer to one child descriptor whereas the second
+		 * read may refer to a later child descriptor in the list
+		 * because of the DMA transfer progression inbetween the two
+		 * reads.
+		 *
+		 * One solution could have been to pause the DMA transfer, read
+		 * the DSCR and CTRLA then resume the DMA transfer. Nonetheless,
+		 * this approach presents some drawbacks:
+		 * - If the DMA transfer is paused, RX overruns or TX underruns
+		 *   are more likey to occur depending on the system latency.
+		 *   Taking the USART driver as an example, it uses a cyclic DMA
+		 *   transfer to read data from the Receive Holding Register
+		 *   (RHR) to avoid RX overruns since the RHR is not protected
+		 *   by any FIFO on most Atmel SoCs. So pausing the DMA transfer
+		 *   to compute the residue would break the USART driver design.
+		 * - The atc_pause() function masks interrupts but we'd rather
+		 *   avoid to do so for system latency purpose.
+		 *
+		 * Then we'd rather use another solution: the DSCR is read a
+		 * first time, the CTRLA is read in turn, next the DSCR is read
+		 * a second time. If the two consecutive read values of the DSCR
+		 * are the same then we assume both refers to the very same
+		 * child descriptor as well as the CTRLA value read inbetween
+		 * does. For cyclic tranfers, the assumption is that a full loop
+		 * is "not so fast".
+		 * If the two DSCR values are different, we read again the CTRLA
+		 * then the DSCR till two consecutive read values from DSCR are
+		 * equal or till the maxium trials is reach.
+		 * This algorithm is very unlikely not to find a stable value for
+		 * DSCR.
 		 */
 
-		ctrla = channel_readl(atchan, CTRLA);
-		rmb(); /* ensure CTRLA is read before DSCR */
 		dscr = channel_readl(atchan, DSCR);
+		rmb(); /* ensure DSCR is read before CTRLA */
+		ctrla = channel_readl(atchan, CTRLA);
+		for (trials = 0; trials < ATC_MAX_DSCR_TRIALS; ++trials) {
+			u32 new_dscr;
+
+			rmb(); /* ensure DSCR is read after CTRLA */
+			new_dscr = channel_readl(atchan, DSCR);
+
+			/*
+			 * If the DSCR register value has not changed inside the
+			 * DMA controller since the previous read, we assume
+			 * that both the dscr and ctrla values refers to the
+			 * very same descriptor.
+			 */
+			if (likely(new_dscr == dscr))
+				break;
+
+			/*
+			 * DSCR has changed inside the DMA controller, so the
+			 * previouly read value of CTRLA may refer to an already
+			 * processed descriptor hence could be outdated.
+			 * We need to update ctrla to match the current
+			 * descriptor.
+			 */
+			dscr = new_dscr;
+			rmb(); /* ensure DSCR is read before CTRLA */
+			ctrla = channel_readl(atchan, CTRLA);
+		}
+		if (unlikely(trials >= ATC_MAX_DSCR_TRIALS))
+			return -ETIMEDOUT;
 
 		/* for the first descriptor we can be more accurate */
 		if (desc_first->lli.dscr == dscr)
-			return atc_calc_bytes_left(ret, ctrla, desc_first);
+			return atc_calc_bytes_left(ret, ctrla);
 
 		ret -= desc_first->len;
 		list_for_each_entry(desc, &desc_first->tx_list, desc_node) {
@@ -365,16 +425,14 @@
 		}
 
 		/*
-		 * For the last descriptor in the chain we can calculate
+		 * For the current descriptor in the chain we can calculate
 		 * the remaining bytes using the channel's register.
-		 * Note that the transfer width of the first and last
-		 * descriptor may differ.
 		 */
-		if (!desc->lli.dscr)
-			ret = atc_calc_bytes_left_from_reg(ret, atchan, desc);
+		ret = atc_calc_bytes_left(ret, ctrla);
 	} else {
 		/* single transfer */
-		ret = atc_calc_bytes_left_from_reg(ret, atchan, desc_first);
+		ctrla = channel_readl(atchan, CTRLA);
+		ret = atc_calc_bytes_left(ret, ctrla);
 	}
 
 	return ret;
@@ -726,7 +784,6 @@
 
 	desc->txd.cookie = -EBUSY;
 	desc->total_len = desc->len = len;
-	desc->tx_width = dwidth;
 
 	/* set end-of-link to the last link descriptor of list*/
 	set_desc_eol(desc);
@@ -804,10 +861,6 @@
 	first->txd.cookie = -EBUSY;
 	first->total_len = len;
 
-	/* set transfer width for the calculation of the residue */
-	first->tx_width = src_width;
-	prev->tx_width = src_width;
-
 	/* set end-of-link to the last link descriptor of list*/
 	set_desc_eol(desc);
 
@@ -956,10 +1009,6 @@
 	first->txd.cookie = -EBUSY;
 	first->total_len = total_len;
 
-	/* set transfer width for the calculation of the residue */
-	first->tx_width = reg_width;
-	prev->tx_width = reg_width;
-
 	/* first link descriptor of list is responsible of flags */
 	first->txd.flags = flags; /* client is in control of this ack */
 
@@ -1077,12 +1126,6 @@
 		desc->txd.cookie = 0;
 		desc->len = len;
 
-		/*
-		 * Although we only need the transfer width for the first and
-		 * the last descriptor, its easier to set it to all descriptors.
-		 */
-		desc->tx_width = src_width;
-
 		atc_desc_chain(&first, &prev, desc);
 
 		/* update the lengths and addresses for the next loop cycle */
@@ -1256,7 +1299,6 @@
 	/* First descriptor of the chain embedds additional information */
 	first->txd.cookie = -EBUSY;
 	first->total_len = buf_len;
-	first->tx_width = reg_width;
 
 	return &first->txd;
 
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index bc8d5eb..7f5a082 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -112,6 +112,7 @@
 #define		ATC_SRC_WIDTH_BYTE	(0x0 << 24)
 #define		ATC_SRC_WIDTH_HALFWORD	(0x1 << 24)
 #define		ATC_SRC_WIDTH_WORD	(0x2 << 24)
+#define		ATC_REG_TO_SRC_WIDTH(r)	(((r) >> 24) & 0x3)
 #define	ATC_DST_WIDTH_MASK	(0x3 << 28)	/* Destination Single Transfer Size */
 #define		ATC_DST_WIDTH(x)	((x) << 28)
 #define		ATC_DST_WIDTH_BYTE	(0x0 << 28)
@@ -182,7 +183,6 @@
  * @txd: support for the async_tx api
  * @desc_node: node on the channed descriptors list
  * @len: descriptor byte count
- * @tx_width: transfer width
  * @total_len: total transaction byte count
  */
 struct at_desc {
@@ -194,7 +194,6 @@
 	struct dma_async_tx_descriptor	txd;
 	struct list_head		desc_node;
 	size_t				len;
-	u32				tx_width;
 	size_t				total_len;
 
 	/* Interleaved data */
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index cf1213d..40afa2a 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -359,18 +359,19 @@
 	 * descriptor view 2 since some fields of the configuration register
 	 * depend on transfer size and src/dest addresses.
 	 */
-	if (at_xdmac_chan_is_cyclic(atchan)) {
+	if (at_xdmac_chan_is_cyclic(atchan))
 		reg = AT_XDMAC_CNDC_NDVIEW_NDV1;
-		at_xdmac_chan_write(atchan, AT_XDMAC_CC, first->lld.mbr_cfg);
-	} else if (first->lld.mbr_ubc & AT_XDMAC_MBR_UBC_NDV3) {
+	else if (first->lld.mbr_ubc & AT_XDMAC_MBR_UBC_NDV3)
 		reg = AT_XDMAC_CNDC_NDVIEW_NDV3;
-	} else {
-		/*
-		 * No need to write AT_XDMAC_CC reg, it will be done when the
-		 * descriptor is fecthed.
-		 */
+	else
 		reg = AT_XDMAC_CNDC_NDVIEW_NDV2;
-	}
+	/*
+	 * Even if the register will be updated from the configuration in the
+	 * descriptor when using view 2 or higher, the PROT bit won't be set
+	 * properly. This bit can be modified only by using the channel
+	 * configuration register.
+	 */
+	at_xdmac_chan_write(atchan, AT_XDMAC_CC, first->lld.mbr_cfg);
 
 	reg |= AT_XDMAC_CNDC_NDDUP
 	       | AT_XDMAC_CNDC_NDSUP
@@ -681,15 +682,16 @@
 			desc->lld.mbr_sa = mem;
 			desc->lld.mbr_da = atchan->sconfig.dst_addr;
 		}
-		desc->lld.mbr_cfg = atchan->cfg;
-		dwidth = at_xdmac_get_dwidth(desc->lld.mbr_cfg);
+		dwidth = at_xdmac_get_dwidth(atchan->cfg);
 		fixed_dwidth = IS_ALIGNED(len, 1 << dwidth)
-			       ? at_xdmac_get_dwidth(desc->lld.mbr_cfg)
+			       ? dwidth
 			       : AT_XDMAC_CC_DWIDTH_BYTE;
 		desc->lld.mbr_ubc = AT_XDMAC_MBR_UBC_NDV2			/* next descriptor view */
 			| AT_XDMAC_MBR_UBC_NDEN					/* next descriptor dst parameter update */
 			| AT_XDMAC_MBR_UBC_NSEN					/* next descriptor src parameter update */
 			| (len >> fixed_dwidth);				/* microblock length */
+		desc->lld.mbr_cfg = (atchan->cfg & ~AT_XDMAC_CC_DWIDTH_MASK) |
+				    AT_XDMAC_CC_DWIDTH(fixed_dwidth);
 		dev_dbg(chan2dev(chan),
 			 "%s: lld: mbr_sa=%pad, mbr_da=%pad, mbr_ubc=0x%08x\n",
 			 __func__, &desc->lld.mbr_sa, &desc->lld.mbr_da, desc->lld.mbr_ubc);
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 4a4cce1..3ff284c 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -689,6 +689,10 @@
 	struct dma_chan *ch = dma_request_slave_channel_reason(dev, name);
 	if (IS_ERR(ch))
 		return NULL;
+
+	dma_cap_set(DMA_PRIVATE, ch->device->cap_mask);
+	ch->device->privatecnt++;
+
 	return ch;
 }
 EXPORT_SYMBOL_GPL(dma_request_slave_channel);
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index 1022c2e..cf1c87f 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -1746,4 +1746,4 @@
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Synopsys DesignWare DMA Controller core driver");
 MODULE_AUTHOR("Haavard Skinnemoen (Atmel)");
-MODULE_AUTHOR("Viresh Kumar <viresh.linux@gmail.com>");
+MODULE_AUTHOR("Viresh Kumar <vireshk@kernel.org>");
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index fbaf1ea..f1325f6 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -162,10 +162,11 @@
 	config &= ~0x7;
 	config |= op_mode;
 
-	if (IS_ENABLED(__BIG_ENDIAN))
-		config |= XOR_DESCRIPTOR_SWAP;
-	else
-		config &= ~XOR_DESCRIPTOR_SWAP;
+#if defined(__BIG_ENDIAN)
+	config |= XOR_DESCRIPTOR_SWAP;
+#else
+	config &= ~XOR_DESCRIPTOR_SWAP;
+#endif
 
 	writel_relaxed(config, XOR_CONFIG(chan));
 	chan->current_type = type;
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index f513f77..ecab4ea0 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2328,7 +2328,7 @@
 			desc->txd.callback = last->txd.callback;
 			desc->txd.callback_param = last->txd.callback_param;
 		}
-		last->last = false;
+		desc->last = false;
 
 		dma_cookie_assign(&desc->txd);
 
@@ -2623,6 +2623,7 @@
 		desc->rqcfg.brst_len = 1;
 
 	desc->rqcfg.brst_len = get_burst_len(desc, len);
+	desc->bytes_requested = len;
 
 	desc->txd.flags = flags;
 
diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c
index 7d2c17d..6f80432 100644
--- a/drivers/dma/virt-dma.c
+++ b/drivers/dma/virt-dma.c
@@ -29,7 +29,7 @@
 	spin_lock_irqsave(&vc->lock, flags);
 	cookie = dma_cookie_assign(tx);
 
-	list_move_tail(&vd->node, &vc->desc_submitted);
+	list_add_tail(&vd->node, &vc->desc_submitted);
 	spin_unlock_irqrestore(&vc->lock, flags);
 
 	dev_dbg(vc->chan.device->dev, "vchan %p: txd %p[%x]: submitted\n",
@@ -83,10 +83,8 @@
 		cb_data = vd->tx.callback_param;
 
 		list_del(&vd->node);
-		if (async_tx_test_ack(&vd->tx))
-			list_add(&vd->node, &vc->desc_allocated);
-		else
-			vc->desc_free(vd);
+
+		vc->desc_free(vd);
 
 		if (cb)
 			cb(cb_data);
@@ -98,13 +96,9 @@
 	while (!list_empty(head)) {
 		struct virt_dma_desc *vd = list_first_entry(head,
 			struct virt_dma_desc, node);
-		if (async_tx_test_ack(&vd->tx)) {
-			list_move_tail(&vd->node, &vc->desc_allocated);
-		} else {
-			dev_dbg(vc->chan.device->dev, "txd %p: freeing\n", vd);
-			list_del(&vd->node);
-			vc->desc_free(vd);
-		}
+		list_del(&vd->node);
+		dev_dbg(vc->chan.device->dev, "txd %p: freeing\n", vd);
+		vc->desc_free(vd);
 	}
 }
 EXPORT_SYMBOL_GPL(vchan_dma_desc_free_list);
@@ -114,7 +108,6 @@
 	dma_cookie_init(&vc->chan);
 
 	spin_lock_init(&vc->lock);
-	INIT_LIST_HEAD(&vc->desc_allocated);
 	INIT_LIST_HEAD(&vc->desc_submitted);
 	INIT_LIST_HEAD(&vc->desc_issued);
 	INIT_LIST_HEAD(&vc->desc_completed);
diff --git a/drivers/dma/virt-dma.h b/drivers/dma/virt-dma.h
index 189e75d..181b952 100644
--- a/drivers/dma/virt-dma.h
+++ b/drivers/dma/virt-dma.h
@@ -29,7 +29,6 @@
 	spinlock_t lock;
 
 	/* protected by vc.lock */
-	struct list_head desc_allocated;
 	struct list_head desc_submitted;
 	struct list_head desc_issued;
 	struct list_head desc_completed;
@@ -56,16 +55,11 @@
 	struct virt_dma_desc *vd, unsigned long tx_flags)
 {
 	extern dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *);
-	unsigned long flags;
 
 	dma_async_tx_descriptor_init(&vd->tx, &vc->chan);
 	vd->tx.flags = tx_flags;
 	vd->tx.tx_submit = vchan_tx_submit;
 
-	spin_lock_irqsave(&vc->lock, flags);
-	list_add_tail(&vd->node, &vc->desc_allocated);
-	spin_unlock_irqrestore(&vc->lock, flags);
-
 	return &vd->tx;
 }
 
@@ -128,8 +122,7 @@
 }
 
 /**
- * vchan_get_all_descriptors - obtain all allocated, submitted and issued
- *                             descriptors
+ * vchan_get_all_descriptors - obtain all submitted and issued descriptors
  * vc: virtual channel to get descriptors from
  * head: list of descriptors found
  *
@@ -141,7 +134,6 @@
 static inline void vchan_get_all_descriptors(struct virt_dma_chan *vc,
 	struct list_head *head)
 {
-	list_splice_tail_init(&vc->desc_allocated, head);
 	list_splice_tail_init(&vc->desc_submitted, head);
 	list_splice_tail_init(&vc->desc_issued, head);
 	list_splice_tail_init(&vc->desc_completed, head);
@@ -149,14 +141,11 @@
 
 static inline void vchan_free_chan_resources(struct virt_dma_chan *vc)
 {
-	struct virt_dma_desc *vd;
 	unsigned long flags;
 	LIST_HEAD(head);
 
 	spin_lock_irqsave(&vc->lock, flags);
 	vchan_get_all_descriptors(vc, &head);
-	list_for_each_entry(vd, &head, node)
-		async_tx_clear_ack(&vd->tx);
 	spin_unlock_irqrestore(&vc->lock, flags);
 
 	vchan_dma_desc_free_list(vc, &head);
diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c
index 620fd55ec..dff22ab 100644
--- a/drivers/dma/xgene-dma.c
+++ b/drivers/dma/xgene-dma.c
@@ -111,6 +111,7 @@
 #define XGENE_DMA_MEM_RAM_SHUTDOWN		0xD070
 #define XGENE_DMA_BLK_MEM_RDY			0xD074
 #define XGENE_DMA_BLK_MEM_RDY_VAL		0xFFFFFFFF
+#define XGENE_DMA_RING_CMD_SM_OFFSET		0x8000
 
 /* X-Gene SoC EFUSE csr register and bit defination */
 #define XGENE_SOC_JTAG1_SHADOW			0x18
@@ -1887,6 +1888,8 @@
 		return -ENOMEM;
 	}
 
+	pdma->csr_ring_cmd += XGENE_DMA_RING_CMD_SM_OFFSET;
+
 	/* Get efuse csr region */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 3);
 	if (!res) {
diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c
index 3515b381..711d8ad 100644
--- a/drivers/edac/ppc4xx_edac.c
+++ b/drivers/edac/ppc4xx_edac.c
@@ -920,7 +920,7 @@
 	 */
 
 	for (row = 0; row < mci->nr_csrows; row++) {
-		struct csrow_info *csi = &mci->csrows[row];
+		struct csrow_info *csi = mci->csrows[row];
 
 		/*
 		 * Get the configuration settings for this
diff --git a/drivers/extcon/extcon-palmas.c b/drivers/extcon/extcon-palmas.c
index 080d5cc..eebdf2a 100644
--- a/drivers/extcon/extcon-palmas.c
+++ b/drivers/extcon/extcon-palmas.c
@@ -200,7 +200,6 @@
 	status = devm_extcon_dev_register(&pdev->dev, palmas_usb->edev);
 	if (status) {
 		dev_err(&pdev->dev, "failed to register extcon device\n");
-		kfree(palmas_usb->edev->name);
 		return status;
 	}
 
@@ -214,7 +213,6 @@
 		if (status < 0) {
 			dev_err(&pdev->dev, "can't get IRQ %d, err %d\n",
 					palmas_usb->id_irq, status);
-			kfree(palmas_usb->edev->name);
 			return status;
 		}
 	}
@@ -229,7 +227,6 @@
 		if (status < 0) {
 			dev_err(&pdev->dev, "can't get IRQ %d, err %d\n",
 					palmas_usb->vbus_irq, status);
-			kfree(palmas_usb->edev->name);
 			return status;
 		}
 	}
@@ -239,15 +236,6 @@
 	return 0;
 }
 
-static int palmas_usb_remove(struct platform_device *pdev)
-{
-	struct palmas_usb *palmas_usb = platform_get_drvdata(pdev);
-
-	kfree(palmas_usb->edev->name);
-
-	return 0;
-}
-
 #ifdef CONFIG_PM_SLEEP
 static int palmas_usb_suspend(struct device *dev)
 {
@@ -288,7 +276,6 @@
 
 static struct platform_driver palmas_usb_driver = {
 	.probe = palmas_usb_probe,
-	.remove = palmas_usb_remove,
 	.driver = {
 		.name = "palmas-usb",
 		.of_match_table = of_palmas_match_tbl,
diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c
index 76157ab..43b57b0 100644
--- a/drivers/extcon/extcon.c
+++ b/drivers/extcon/extcon.c
@@ -124,25 +124,35 @@
 	return -EINVAL;
 }
 
-static int find_cable_index_by_name(struct extcon_dev *edev, const char *name)
+static int find_cable_id_by_name(struct extcon_dev *edev, const char *name)
 {
-	unsigned int id = EXTCON_NONE;
+	unsigned int id = -EINVAL;
 	int i = 0;
 
-	if (edev->max_supported == 0)
-		return -EINVAL;
-
-	/* Find the the number of extcon cable */
+	/* Find the id of extcon cable */
 	while (extcon_name[i]) {
 		if (!strncmp(extcon_name[i], name, CABLE_NAME_MAX)) {
 			id = i;
 			break;
 		}
+		i++;
 	}
 
-	if (id == EXTCON_NONE)
+	return id;
+}
+
+static int find_cable_index_by_name(struct extcon_dev *edev, const char *name)
+{
+	unsigned int id;
+
+	if (edev->max_supported == 0)
 		return -EINVAL;
 
+	/* Find the the number of extcon cable */
+	id = find_cable_id_by_name(edev, name);
+	if (id < 0)
+		return id;
+
 	return find_cable_index_by_id(edev, id);
 }
 
@@ -228,9 +238,11 @@
 	struct extcon_cable *cable = container_of(attr, struct extcon_cable,
 						  attr_state);
 
+	int i = cable->cable_index;
+
 	return sprintf(buf, "%d\n",
 		       extcon_get_cable_state_(cable->edev,
-					       cable->cable_index));
+					       cable->edev->supported_cable[i]));
 }
 
 /**
@@ -263,20 +275,25 @@
 	spin_lock_irqsave(&edev->lock, flags);
 
 	if (edev->state != ((edev->state & ~mask) | (state & mask))) {
+		u32 old_state;
+
 		if (check_mutually_exclusive(edev, (edev->state & ~mask) |
 						   (state & mask))) {
 			spin_unlock_irqrestore(&edev->lock, flags);
 			return -EPERM;
 		}
 
-		for (index = 0; index < edev->max_supported; index++) {
-			if (is_extcon_changed(edev->state, state, index, &attached))
-				raw_notifier_call_chain(&edev->nh[index], attached, edev);
-		}
-
+		old_state = edev->state;
 		edev->state &= ~mask;
 		edev->state |= state & mask;
 
+		for (index = 0; index < edev->max_supported; index++) {
+			if (is_extcon_changed(old_state, edev->state, index,
+					      &attached))
+				raw_notifier_call_chain(&edev->nh[index],
+							attached, edev);
+		}
+
 		/* This could be in interrupt handler */
 		prop_buf = (char *)get_zeroed_page(GFP_ATOMIC);
 		if (prop_buf) {
@@ -361,8 +378,13 @@
  */
 int extcon_get_cable_state(struct extcon_dev *edev, const char *cable_name)
 {
-	return extcon_get_cable_state_(edev, find_cable_index_by_name
-						(edev, cable_name));
+	unsigned int id;
+
+	id = find_cable_id_by_name(edev, cable_name);
+	if (id < 0)
+		return id;
+
+	return extcon_get_cable_state_(edev, id);
 }
 EXPORT_SYMBOL_GPL(extcon_get_cable_state);
 
@@ -404,8 +426,13 @@
 int extcon_set_cable_state(struct extcon_dev *edev,
 			const char *cable_name, bool cable_state)
 {
-	return extcon_set_cable_state_(edev, find_cable_index_by_name
-					(edev, cable_name), cable_state);
+	unsigned int id;
+
+	id = find_cable_id_by_name(edev, cable_name);
+	if (id < 0)
+		return id;
+
+	return extcon_set_cable_state_(edev, id, cable_state);
 }
 EXPORT_SYMBOL_GPL(extcon_set_cable_state);
 
diff --git a/drivers/firmware/broadcom/bcm47xx_nvram.c b/drivers/firmware/broadcom/bcm47xx_nvram.c
index 87add3f..e415945 100644
--- a/drivers/firmware/broadcom/bcm47xx_nvram.c
+++ b/drivers/firmware/broadcom/bcm47xx_nvram.c
@@ -245,4 +245,4 @@
 }
 EXPORT_SYMBOL(bcm47xx_nvram_get_contents);
 
-MODULE_LICENSE("GPLv2");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 4fd9961..d425374 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -305,10 +305,17 @@
 	return ret;
 }
 
-static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem)
+static void cper_print_mem(const char *pfx, const struct cper_sec_mem_err *mem,
+	int len)
 {
 	struct cper_mem_err_compact cmem;
 
+	/* Don't trust UEFI 2.1/2.2 structure with bad validation bits */
+	if (len == sizeof(struct cper_sec_mem_err_old) &&
+	    (mem->validation_bits & ~(CPER_MEM_VALID_RANK_NUMBER - 1))) {
+		pr_err(FW_WARN "valid bits set for fields beyond structure\n");
+		return;
+	}
 	if (mem->validation_bits & CPER_MEM_VALID_ERROR_STATUS)
 		printk("%s""error_status: 0x%016llx\n", pfx, mem->error_status);
 	if (mem->validation_bits & CPER_MEM_VALID_PA)
@@ -405,8 +412,10 @@
 	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) {
 		struct cper_sec_mem_err *mem_err = (void *)(gdata + 1);
 		printk("%s""section_type: memory error\n", newpfx);
-		if (gdata->error_data_length >= sizeof(*mem_err))
-			cper_print_mem(newpfx, mem_err);
+		if (gdata->error_data_length >=
+		    sizeof(struct cper_sec_mem_err_old))
+			cper_print_mem(newpfx, mem_err,
+				       gdata->error_data_length);
 		else
 			goto err_section_too_small;
 	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PCIE)) {
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 9fa8084..d6144e3 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -58,6 +58,11 @@
 
 static int __init parse_efi_cmdline(char *str)
 {
+	if (!str) {
+		pr_warn("need at least one option\n");
+		return -EINVAL;
+	}
+
 	if (parse_option_str(str, "noruntime"))
 		disable_runtime = true;
 
diff --git a/drivers/gpio/gpio-brcmstb.c b/drivers/gpio/gpio-brcmstb.c
index 7a3cb1f..4630a81 100644
--- a/drivers/gpio/gpio-brcmstb.c
+++ b/drivers/gpio/gpio-brcmstb.c
@@ -87,6 +87,15 @@
 	struct brcmstb_gpio_bank *bank;
 	int ret = 0;
 
+	if (!priv) {
+		dev_err(&pdev->dev, "called %s without drvdata!\n", __func__);
+		return -EFAULT;
+	}
+
+	/*
+	 * You can lose return values below, but we report all errors, and it's
+	 * more important to actually perform all of the steps.
+	 */
 	list_for_each(pos, &priv->bank_list) {
 		bank = list_entry(pos, struct brcmstb_gpio_bank, node);
 		ret = bgpio_remove(&bank->bgc);
@@ -143,6 +152,8 @@
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
+	platform_set_drvdata(pdev, priv);
+	INIT_LIST_HEAD(&priv->bank_list);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	reg_base = devm_ioremap_resource(dev, res);
@@ -153,7 +164,6 @@
 	priv->reg_base = reg_base;
 	priv->pdev = pdev;
 
-	INIT_LIST_HEAD(&priv->bank_list);
 	if (brcmstb_gpio_sanity_check_banks(dev, np, res))
 		return -EINVAL;
 
@@ -221,8 +231,6 @@
 	dev_info(dev, "Registered %d banks (GPIO(s): %d-%d)\n",
 			priv->num_banks, priv->gpio_base, gpio_base - 1);
 
-	platform_set_drvdata(pdev, priv);
-
 	return 0;
 
 fail:
diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c
index c5e05c8..c246ac3 100644
--- a/drivers/gpio/gpio-davinci.c
+++ b/drivers/gpio/gpio-davinci.c
@@ -578,15 +578,13 @@
 		writel_relaxed(~0, &g->clr_falling);
 		writel_relaxed(~0, &g->clr_rising);
 
-		/* set up all irqs in this bank */
-		irq_set_chained_handler(bank_irq, gpio_irq_handler);
-
 		/*
 		 * Each chip handles 32 gpios, and each irq bank consists of 16
 		 * gpio irqs. Pass the irq bank's corresponding controller to
 		 * the chained irq handler.
 		 */
-		irq_set_handler_data(bank_irq, &chips[gpio / 32]);
+		irq_set_chained_handler_and_data(bank_irq, gpio_irq_handler,
+						 &chips[gpio / 32]);
 
 		binten |= BIT(bank);
 	}
diff --git a/drivers/gpio/gpio-max732x.c b/drivers/gpio/gpio-max732x.c
index aed4ca93..7d3c90e 100644
--- a/drivers/gpio/gpio-max732x.c
+++ b/drivers/gpio/gpio-max732x.c
@@ -603,6 +603,7 @@
 	gc->base = gpio_start;
 	gc->ngpio = port;
 	gc->label = chip->client->name;
+	gc->dev = &chip->client->dev;
 	gc->owner = THIS_MODULE;
 
 	return port;
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index b0c57d5..61a731f 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -500,8 +500,10 @@
 
 	spin_lock_irqsave(&bank->lock, flags);
 	retval = omap_set_gpio_triggering(bank, offset, type);
-	if (retval)
+	if (retval) {
+		spin_unlock_irqrestore(&bank->lock, flags);
 		goto error;
+	}
 	omap_gpio_init_irq(bank, offset);
 	if (!omap_gpio_is_input(bank, offset)) {
 		spin_unlock_irqrestore(&bank->lock, flags);
@@ -1185,6 +1187,7 @@
 	bank->irq = res->start;
 	bank->dev = dev;
 	bank->chip.dev = dev;
+	bank->chip.owner = THIS_MODULE;
 	bank->dbck_flag = pdata->dbck_flag;
 	bank->stride = pdata->bank_stride;
 	bank->width = pdata->bank_width;
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index d233eb3..50caeb1 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -570,6 +570,10 @@
 				"could not connect irqchip to gpiochip\n");
 			return ret;
 		}
+
+		gpiochip_set_chained_irqchip(&chip->gpio_chip,
+					     &pca953x_irq_chip,
+					     client->irq, NULL);
 	}
 
 	return 0;
diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c
index 77fe5d3..d5284df 100644
--- a/drivers/gpio/gpio-xilinx.c
+++ b/drivers/gpio/gpio-xilinx.c
@@ -220,9 +220,9 @@
 	if (!chip->gpio_width[1])
 		return;
 
-	xgpio_writereg(mm_gc->regs + XGPIO_DATA_OFFSET + XGPIO_TRI_OFFSET,
+	xgpio_writereg(mm_gc->regs + XGPIO_DATA_OFFSET + XGPIO_CHANNEL_OFFSET,
 		       chip->gpio_state[1]);
-	xgpio_writereg(mm_gc->regs + XGPIO_TRI_OFFSET + XGPIO_TRI_OFFSET,
+	xgpio_writereg(mm_gc->regs + XGPIO_TRI_OFFSET + XGPIO_CHANNEL_OFFSET,
 		       chip->gpio_dir[1]);
 }
 
diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c
index 2e87c4b..a788823 100644
--- a/drivers/gpio/gpio-zynq.c
+++ b/drivers/gpio/gpio-zynq.c
@@ -757,6 +757,7 @@
 	gpiochip_remove(&gpio->chip);
 	clk_disable_unprepare(gpio->clk);
 	device_set_wakeup_capable(&pdev->dev, 0);
+	pm_runtime_disable(&pdev->dev);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 0165783..f7b49d5c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1130,6 +1130,9 @@
 	uint32_t			me_feature_version;
 	uint32_t			ce_feature_version;
 	uint32_t			pfp_feature_version;
+	uint32_t			rlc_feature_version;
+	uint32_t			mec_feature_version;
+	uint32_t			mec2_feature_version;
 	struct amdgpu_ring		gfx_ring[AMDGPU_MAX_GFX_RINGS];
 	unsigned			num_gfx_rings;
 	struct amdgpu_ring		compute_ring[AMDGPU_MAX_COMPUTE_RINGS];
@@ -1614,6 +1617,9 @@
 #define AMDGPU_MAX_VCE_HANDLES	16
 #define AMDGPU_VCE_FIRMWARE_OFFSET 256
 
+#define AMDGPU_VCE_HARVEST_VCE0 (1 << 0)
+#define AMDGPU_VCE_HARVEST_VCE1 (1 << 1)
+
 struct amdgpu_vce {
 	struct amdgpu_bo	*vcpu_bo;
 	uint64_t		gpu_addr;
@@ -1626,6 +1632,7 @@
 	const struct firmware	*fw;	/* VCE firmware */
 	struct amdgpu_ring	ring[AMDGPU_MAX_VCE_RINGS];
 	struct amdgpu_irq_src	irq;
+	unsigned		harvest_config;
 };
 
 /*
@@ -1635,6 +1642,7 @@
 	/* SDMA firmware */
 	const struct firmware	*fw;
 	uint32_t		fw_version;
+	uint32_t		feature_version;
 
 	struct amdgpu_ring	ring;
 };
@@ -1862,6 +1870,12 @@
 typedef uint32_t (*amdgpu_block_rreg_t)(struct amdgpu_device*, uint32_t, uint32_t);
 typedef void (*amdgpu_block_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t, uint32_t);
 
+struct amdgpu_ip_block_status {
+	bool valid;
+	bool sw;
+	bool hw;
+};
+
 struct amdgpu_device {
 	struct device			*dev;
 	struct drm_device		*ddev;
@@ -2004,7 +2018,7 @@
 
 	const struct amdgpu_ip_block_version *ip_blocks;
 	int				num_ip_blocks;
-	bool				*ip_block_enabled;
+	struct amdgpu_ip_block_status	*ip_block_status;
 	struct mutex	mn_lock;
 	DECLARE_HASHTABLE(mn_hash, 7);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index d63135b..1f040d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -669,6 +669,7 @@
 static int amdgpu_cs_dependencies(struct amdgpu_device *adev,
 				  struct amdgpu_cs_parser *p)
 {
+	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
 	struct amdgpu_ib *ib;
 	int i, j, r;
 
@@ -694,6 +695,7 @@
 		for (j = 0; j < num_deps; ++j) {
 			struct amdgpu_fence *fence;
 			struct amdgpu_ring *ring;
+			struct amdgpu_ctx *ctx;
 
 			r = amdgpu_cs_get_ring(adev, deps[j].ip_type,
 					       deps[j].ip_instance,
@@ -701,14 +703,21 @@
 			if (r)
 				return r;
 
+			ctx = amdgpu_ctx_get(fpriv, deps[j].ctx_id);
+			if (ctx == NULL)
+				return -EINVAL;
+
 			r = amdgpu_fence_recreate(ring, p->filp,
 						  deps[j].handle,
 						  &fence);
-			if (r)
+			if (r) {
+				amdgpu_ctx_put(ctx);
 				return r;
+			}
 
 			amdgpu_sync_fence(&ib->sync, fence);
 			amdgpu_fence_unref(&fence);
+			amdgpu_ctx_put(ctx);
 		}
 	}
 
@@ -808,12 +817,16 @@
 
 	r = amdgpu_cs_get_ring(adev, wait->in.ip_type, wait->in.ip_instance,
 			       wait->in.ring, &ring);
-	if (r)
+	if (r) {
+		amdgpu_ctx_put(ctx);
 		return r;
+	}
 
 	r = amdgpu_fence_recreate(ring, filp, wait->in.handle, &fence);
-	if (r)
+	if (r) {
+		amdgpu_ctx_put(ctx);
 		return r;
+	}
 
 	r = fence_wait_timeout(&fence->base, true, timeout);
 	amdgpu_fence_unref(&fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index ba46be3..99f158e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1191,8 +1191,9 @@
 		return -EINVAL;
 	}
 
-	adev->ip_block_enabled = kcalloc(adev->num_ip_blocks, sizeof(bool), GFP_KERNEL);
-	if (adev->ip_block_enabled == NULL)
+	adev->ip_block_status = kcalloc(adev->num_ip_blocks,
+					sizeof(struct amdgpu_ip_block_status), GFP_KERNEL);
+	if (adev->ip_block_status == NULL)
 		return -ENOMEM;
 
 	if (adev->ip_blocks == NULL) {
@@ -1203,14 +1204,19 @@
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if ((amdgpu_ip_block_mask & (1 << i)) == 0) {
 			DRM_ERROR("disabled ip block: %d\n", i);
-			adev->ip_block_enabled[i] = false;
+			adev->ip_block_status[i].valid = false;
 		} else {
 			if (adev->ip_blocks[i].funcs->early_init) {
 				r = adev->ip_blocks[i].funcs->early_init((void *)adev);
-				if (r)
+				if (r == -ENOENT)
+					adev->ip_block_status[i].valid = false;
+				else if (r)
 					return r;
+				else
+					adev->ip_block_status[i].valid = true;
+			} else {
+				adev->ip_block_status[i].valid = true;
 			}
-			adev->ip_block_enabled[i] = true;
 		}
 	}
 
@@ -1222,11 +1228,12 @@
 	int i, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].valid)
 			continue;
 		r = adev->ip_blocks[i].funcs->sw_init((void *)adev);
 		if (r)
 			return r;
+		adev->ip_block_status[i].sw = true;
 		/* need to do gmc hw init early so we can allocate gpu mem */
 		if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_GMC) {
 			r = amdgpu_vram_scratch_init(adev);
@@ -1238,11 +1245,12 @@
 			r = amdgpu_wb_init(adev);
 			if (r)
 				return r;
+			adev->ip_block_status[i].hw = true;
 		}
 	}
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].sw)
 			continue;
 		/* gmc hw init is done early */
 		if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_GMC)
@@ -1250,6 +1258,7 @@
 		r = adev->ip_blocks[i].funcs->hw_init((void *)adev);
 		if (r)
 			return r;
+		adev->ip_block_status[i].hw = true;
 	}
 
 	return 0;
@@ -1260,7 +1269,7 @@
 	int i = 0, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].valid)
 			continue;
 		/* enable clockgating to save power */
 		r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
@@ -1282,7 +1291,7 @@
 	int i, r;
 
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].hw)
 			continue;
 		if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_GMC) {
 			amdgpu_wb_fini(adev);
@@ -1295,14 +1304,16 @@
 			return r;
 		r = adev->ip_blocks[i].funcs->hw_fini((void *)adev);
 		/* XXX handle errors */
+		adev->ip_block_status[i].hw = false;
 	}
 
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].sw)
 			continue;
 		r = adev->ip_blocks[i].funcs->sw_fini((void *)adev);
 		/* XXX handle errors */
-		adev->ip_block_enabled[i] = false;
+		adev->ip_block_status[i].sw = false;
+		adev->ip_block_status[i].valid = false;
 	}
 
 	return 0;
@@ -1313,7 +1324,7 @@
 	int i, r;
 
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].valid)
 			continue;
 		/* ungate blocks so that suspend can properly shut them down */
 		r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
@@ -1331,7 +1342,7 @@
 	int i, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].valid)
 			continue;
 		r = adev->ip_blocks[i].funcs->resume(adev);
 		if (r)
@@ -1577,8 +1588,8 @@
 	amdgpu_fence_driver_fini(adev);
 	amdgpu_fbdev_fini(adev);
 	r = amdgpu_fini(adev);
-	kfree(adev->ip_block_enabled);
-	adev->ip_block_enabled = NULL;
+	kfree(adev->ip_block_status);
+	adev->ip_block_status = NULL;
 	adev->accel_working = false;
 	/* free i2c buses */
 	amdgpu_i2c_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 975edb1..4afc507 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -352,7 +352,7 @@
 	if (((int64_t)timeout_ns) < 0)
 		return MAX_SCHEDULE_TIMEOUT;
 
-	timeout = ktime_sub_ns(ktime_get(), timeout_ns);
+	timeout = ktime_sub(ns_to_ktime(timeout_ns), ktime_get());
 	if (ktime_to_ns(timeout) < 0)
 		return 0;
 
@@ -449,7 +449,7 @@
  * vital here, so they are not reported back to userspace.
  */
 static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
-				    struct amdgpu_bo_va *bo_va)
+				    struct amdgpu_bo_va *bo_va, uint32_t operation)
 {
 	struct ttm_validate_buffer tv, *entry;
 	struct amdgpu_bo_list_entry *vm_bos;
@@ -485,7 +485,9 @@
 	if (r)
 		goto error_unlock;
 
-	r = amdgpu_vm_bo_update(adev, bo_va, &bo_va->bo->tbo.mem);
+
+	if (operation == AMDGPU_VA_OP_MAP)
+		r = amdgpu_vm_bo_update(adev, bo_va, &bo_va->bo->tbo.mem);
 
 error_unlock:
 	mutex_unlock(&bo_va->vm->mutex);
@@ -580,7 +582,7 @@
 	}
 
 	if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE))
-		amdgpu_gem_va_update_vm(adev, bo_va);
+		amdgpu_gem_va_update_vm(adev, bo_va, args->operation);
 
 	drm_gem_object_unreference_unlocked(gobj);
 	return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 52dff75..bc0fac6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -180,17 +180,17 @@
 	if (vm) {
 		/* do context switch */
 		amdgpu_vm_flush(ring, vm, ib->sync.last_vm_update);
+
+		if (ring->funcs->emit_gds_switch)
+			amdgpu_ring_emit_gds_switch(ring, ib->vm->ids[ring->idx].id,
+						    ib->gds_base, ib->gds_size,
+						    ib->gws_base, ib->gws_size,
+						    ib->oa_base, ib->oa_size);
+
+		if (ring->funcs->emit_hdp_flush)
+			amdgpu_ring_emit_hdp_flush(ring);
 	}
 
-	if (vm && ring->funcs->emit_gds_switch)
-		amdgpu_ring_emit_gds_switch(ring, ib->vm->ids[ring->idx].id,
-					    ib->gds_base, ib->gds_size,
-					    ib->gws_base, ib->gws_size,
-					    ib->oa_base, ib->oa_size);
-
-	if (ring->funcs->emit_hdp_flush)
-		amdgpu_ring_emit_hdp_flush(ring);
-
 	old_ctx = ring->current_ctx;
 	for (i = 0; i < num_ibs; ++i) {
 		ib = &ibs[i];
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 5533434..3bfe67d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -235,7 +235,7 @@
 
 		for (i = 0; i < adev->num_ip_blocks; i++) {
 			if (adev->ip_blocks[i].type == type &&
-			    adev->ip_block_enabled[i]) {
+			    adev->ip_block_status[i].valid) {
 				ip.hw_ip_version_major = adev->ip_blocks[i].major;
 				ip.hw_ip_version_minor = adev->ip_blocks[i].minor;
 				ip.capabilities_flags = 0;
@@ -274,7 +274,7 @@
 
 		for (i = 0; i < adev->num_ip_blocks; i++)
 			if (adev->ip_blocks[i].type == type &&
-			    adev->ip_block_enabled[i] &&
+			    adev->ip_block_status[i].valid &&
 			    count < AMDGPU_HW_IP_INSTANCE_MAX_COUNT)
 				count++;
 
@@ -317,16 +317,17 @@
 			break;
 		case AMDGPU_INFO_FW_GFX_RLC:
 			fw_info.ver = adev->gfx.rlc_fw_version;
-			fw_info.feature = 0;
+			fw_info.feature = adev->gfx.rlc_feature_version;
 			break;
 		case AMDGPU_INFO_FW_GFX_MEC:
-			if (info->query_fw.index == 0)
+			if (info->query_fw.index == 0) {
 				fw_info.ver = adev->gfx.mec_fw_version;
-			else if (info->query_fw.index == 1)
+				fw_info.feature = adev->gfx.mec_feature_version;
+			} else if (info->query_fw.index == 1) {
 				fw_info.ver = adev->gfx.mec2_fw_version;
-			else
+				fw_info.feature = adev->gfx.mec2_feature_version;
+			} else
 				return -EINVAL;
-			fw_info.feature = 0;
 			break;
 		case AMDGPU_INFO_FW_SMC:
 			fw_info.ver = adev->pm.fw_version;
@@ -336,7 +337,7 @@
 			if (info->query_fw.index >= 2)
 				return -EINVAL;
 			fw_info.ver = adev->sdma[info->query_fw.index].fw_version;
-			fw_info.feature = 0;
+			fw_info.feature = adev->sdma[info->query_fw.index].feature_version;
 			break;
 		default:
 			return -EINVAL;
@@ -416,7 +417,7 @@
 		return n ? -EFAULT : 0;
 	}
 	case AMDGPU_INFO_DEV_INFO: {
-		struct drm_amdgpu_info_device dev_info;
+		struct drm_amdgpu_info_device dev_info = {};
 		struct amdgpu_cu_info cu_info;
 
 		dev_info.device_id = dev->pdev->device;
@@ -459,6 +460,7 @@
 		memcpy(&dev_info.cu_bitmap[0], &cu_info.bitmap[0], sizeof(cu_info.bitmap));
 		dev_info.vram_type = adev->mc.vram_type;
 		dev_info.vram_bit_width = adev->mc.vram_width;
+		dev_info.vce_harvest_config = adev->vce.harvest_config;
 
 		return copy_to_user(out, &dev_info,
 				    min((size_t)size, sizeof(dev_info))) ? -EFAULT : 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 2f7a5ef..f5c2255 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -374,7 +374,7 @@
 	unsigned height_in_mb = ALIGN(height / 16, 2);
 	unsigned fs_in_mb = width_in_mb * height_in_mb;
 
-	unsigned image_size, tmp, min_dpb_size, num_dpb_buffer;
+	unsigned image_size, tmp, min_dpb_size, num_dpb_buffer, min_ctx_size;
 
 	image_size = width * height;
 	image_size += image_size / 2;
@@ -466,6 +466,8 @@
 
 		num_dpb_buffer = (le32_to_cpu(msg[59]) & 0xff) + 2;
 		min_dpb_size = image_size * num_dpb_buffer;
+		min_ctx_size = ((width + 255) / 16) * ((height + 255) / 16)
+					   * 16 * num_dpb_buffer + 52 * 1024;
 		break;
 
 	default:
@@ -486,6 +488,7 @@
 
 	buf_sizes[0x1] = dpb_size;
 	buf_sizes[0x2] = image_size;
+	buf_sizes[0x4] = min_ctx_size;
 	return 0;
 }
 
@@ -628,6 +631,13 @@
 			return -EINVAL;
 		}
 
+	} else if (cmd == 0x206) {
+		if ((end - start) < ctx->buf_sizes[4]) {
+			DRM_ERROR("buffer (%d) to small (%d / %d)!\n", cmd,
+					  (unsigned)(end - start),
+					  ctx->buf_sizes[4]);
+			return -EINVAL;
+		}
 	} else if ((cmd != 0x100) && (cmd != 0x204)) {
 		DRM_ERROR("invalid UVD command %X!\n", cmd);
 		return -EINVAL;
@@ -755,9 +765,10 @@
 	struct amdgpu_uvd_cs_ctx ctx = {};
 	unsigned buf_sizes[] = {
 		[0x00000000]	=	2048,
-		[0x00000001]	=	32 * 1024 * 1024,
-		[0x00000002]	=	2048 * 1152 * 3,
+		[0x00000001]	=	0xFFFFFFFF,
+		[0x00000002]	=	0xFFFFFFFF,
 		[0x00000003]	=	2048,
+		[0x00000004]	=	0xFFFFFFFF,
 	};
 	struct amdgpu_ib *ib = &parser->ibs[ib_idx];
 	int r;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index ab83cc1..15df46c 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -500,6 +500,7 @@
 		amdgpu_ucode_print_sdma_hdr(&hdr->header);
 		fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
 		adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
+		adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
 		fw_data = (const __le32 *)
 			(adev->sdma[i].fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes));
 		WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
index f75a31d..ace870a 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_dpm.c
@@ -494,29 +494,67 @@
 	amdgpu_free_extended_power_table(adev);
 }
 
+#define ixSMUSVI_NB_CURRENTVID 0xD8230044
+#define CURRENT_NB_VID_MASK 0xff000000
+#define CURRENT_NB_VID__SHIFT 24
+#define ixSMUSVI_GFX_CURRENTVID  0xD8230048
+#define CURRENT_GFX_VID_MASK 0xff000000
+#define CURRENT_GFX_VID__SHIFT 24
+
 static void
 cz_dpm_debugfs_print_current_performance_level(struct amdgpu_device *adev,
 					       struct seq_file *m)
 {
+	struct cz_power_info *pi = cz_get_pi(adev);
 	struct amdgpu_clock_voltage_dependency_table *table =
 		&adev->pm.dpm.dyn_state.vddc_dependency_on_sclk;
-	u32 current_index =
-		(RREG32_SMC(ixTARGET_AND_CURRENT_PROFILE_INDEX) &
-		TARGET_AND_CURRENT_PROFILE_INDEX__CURR_SCLK_INDEX_MASK) >>
-		TARGET_AND_CURRENT_PROFILE_INDEX__CURR_SCLK_INDEX__SHIFT;
-	u32 sclk, tmp;
-	u16 vddc;
+	struct amdgpu_uvd_clock_voltage_dependency_table *uvd_table =
+		&adev->pm.dpm.dyn_state.uvd_clock_voltage_dependency_table;
+	struct amdgpu_vce_clock_voltage_dependency_table *vce_table =
+		&adev->pm.dpm.dyn_state.vce_clock_voltage_dependency_table;
+	u32 sclk_index = REG_GET_FIELD(RREG32_SMC(ixTARGET_AND_CURRENT_PROFILE_INDEX),
+				       TARGET_AND_CURRENT_PROFILE_INDEX, CURR_SCLK_INDEX);
+	u32 uvd_index = REG_GET_FIELD(RREG32_SMC(ixTARGET_AND_CURRENT_PROFILE_INDEX_2),
+				      TARGET_AND_CURRENT_PROFILE_INDEX_2, CURR_UVD_INDEX);
+	u32 vce_index = REG_GET_FIELD(RREG32_SMC(ixTARGET_AND_CURRENT_PROFILE_INDEX_2),
+				      TARGET_AND_CURRENT_PROFILE_INDEX_2, CURR_VCE_INDEX);
+	u32 sclk, vclk, dclk, ecclk, tmp;
+	u16 vddnb, vddgfx;
 
-	if (current_index >= NUM_SCLK_LEVELS) {
-		seq_printf(m, "invalid dpm profile %d\n", current_index);
+	if (sclk_index >= NUM_SCLK_LEVELS) {
+		seq_printf(m, "invalid sclk dpm profile %d\n", sclk_index);
 	} else {
-		sclk = table->entries[current_index].clk;
-		tmp = (RREG32_SMC(ixSMU_VOLTAGE_STATUS) &
-			SMU_VOLTAGE_STATUS__SMU_VOLTAGE_CURRENT_LEVEL_MASK) >>
-			SMU_VOLTAGE_STATUS__SMU_VOLTAGE_CURRENT_LEVEL__SHIFT;
-		vddc = cz_convert_8bit_index_to_voltage(adev, (u16)tmp);
-		seq_printf(m, "power level %d    sclk: %u vddc: %u\n",
-			   current_index, sclk, vddc);
+		sclk = table->entries[sclk_index].clk;
+		seq_printf(m, "%u sclk: %u\n", sclk_index, sclk);
+	}
+
+	tmp = (RREG32_SMC(ixSMUSVI_NB_CURRENTVID) &
+	       CURRENT_NB_VID_MASK) >> CURRENT_NB_VID__SHIFT;
+	vddnb = cz_convert_8bit_index_to_voltage(adev, (u16)tmp);
+	tmp = (RREG32_SMC(ixSMUSVI_GFX_CURRENTVID) &
+	       CURRENT_GFX_VID_MASK) >> CURRENT_GFX_VID__SHIFT;
+	vddgfx = cz_convert_8bit_index_to_voltage(adev, (u16)tmp);
+	seq_printf(m, "vddnb: %u vddgfx: %u\n", vddnb, vddgfx);
+
+	seq_printf(m, "uvd    %sabled\n", pi->uvd_power_gated ? "dis" : "en");
+	if (!pi->uvd_power_gated) {
+		if (uvd_index >= CZ_MAX_HARDWARE_POWERLEVELS) {
+			seq_printf(m, "invalid uvd dpm level %d\n", uvd_index);
+		} else {
+			vclk = uvd_table->entries[uvd_index].vclk;
+			dclk = uvd_table->entries[uvd_index].dclk;
+			seq_printf(m, "%u uvd vclk: %u dclk: %u\n", uvd_index, vclk, dclk);
+		}
+	}
+
+	seq_printf(m, "vce    %sabled\n", pi->vce_power_gated ? "dis" : "en");
+	if (!pi->vce_power_gated) {
+		if (vce_index >= CZ_MAX_HARDWARE_POWERLEVELS) {
+			seq_printf(m, "invalid vce dpm level %d\n", vce_index);
+		} else {
+			ecclk = vce_table->entries[vce_index].ecclk;
+			seq_printf(m, "%u vce ecclk: %u\n", vce_index, ecclk);
+		}
 	}
 }
 
@@ -1679,25 +1717,31 @@
 	if (ret)
 		return ret;
 
-	DRM_INFO("DPM unforce state min=%d, max=%d.\n",
-			pi->sclk_dpm.soft_min_clk,
-			pi->sclk_dpm.soft_max_clk);
+	DRM_DEBUG("DPM unforce state min=%d, max=%d.\n",
+		  pi->sclk_dpm.soft_min_clk,
+		  pi->sclk_dpm.soft_max_clk);
 
 	return 0;
 }
 
 static int cz_dpm_force_dpm_level(struct amdgpu_device *adev,
-				enum amdgpu_dpm_forced_level level)
+				  enum amdgpu_dpm_forced_level level)
 {
 	int ret = 0;
 
 	switch (level) {
 	case AMDGPU_DPM_FORCED_LEVEL_HIGH:
+		ret = cz_dpm_unforce_dpm_levels(adev);
+		if (ret)
+			return ret;
 		ret = cz_dpm_force_highest(adev);
 		if (ret)
 			return ret;
 		break;
 	case AMDGPU_DPM_FORCED_LEVEL_LOW:
+		ret = cz_dpm_unforce_dpm_levels(adev);
+		if (ret)
+			return ret;
 		ret = cz_dpm_force_lowest(adev);
 		if (ret)
 			return ret;
@@ -1711,6 +1755,8 @@
 		break;
 	}
 
+	adev->pm.dpm.forced_level = level;
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index 5cde635..e70a26f 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -2632,6 +2632,7 @@
 	struct drm_device *dev = crtc->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+	unsigned type;
 
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
@@ -2640,6 +2641,9 @@
 		dce_v10_0_vga_enable(crtc, true);
 		amdgpu_atombios_crtc_blank(crtc, ATOM_DISABLE);
 		dce_v10_0_vga_enable(crtc, false);
+		/* Make sure VBLANK interrupt is still enabled */
+		type = amdgpu_crtc_idx_to_irq_type(adev, amdgpu_crtc->crtc_id);
+		amdgpu_irq_update(adev, &adev->crtc_irq, type);
 		drm_vblank_post_modeset(dev, amdgpu_crtc->crtc_id);
 		dce_v10_0_crtc_load_lut(crtc);
 		break;
@@ -3403,19 +3407,25 @@
 
 	switch (entry->src_data) {
 	case 0: /* vblank */
-		if (disp_int & interrupt_status_offsets[crtc].vblank) {
+		if (disp_int & interrupt_status_offsets[crtc].vblank)
 			dce_v10_0_crtc_vblank_int_ack(adev, crtc);
-			if (amdgpu_irq_enabled(adev, source, irq_type)) {
-				drm_handle_vblank(adev->ddev, crtc);
-			}
-			DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
+		else
+			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+		if (amdgpu_irq_enabled(adev, source, irq_type)) {
+			drm_handle_vblank(adev->ddev, crtc);
 		}
+		DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
+
 		break;
 	case 1: /* vline */
-		if (disp_int & interrupt_status_offsets[crtc].vline) {
+		if (disp_int & interrupt_status_offsets[crtc].vline)
 			dce_v10_0_crtc_vline_int_ack(adev, crtc);
-			DRM_DEBUG("IH: D%d vline\n", crtc + 1);
-		}
+		else
+			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+		DRM_DEBUG("IH: D%d vline\n", crtc + 1);
+
 		break;
 	default:
 		DRM_DEBUG("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data);
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 95efd98..dcb402e 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -2631,6 +2631,7 @@
 	struct drm_device *dev = crtc->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+	unsigned type;
 
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
@@ -2639,6 +2640,9 @@
 		dce_v11_0_vga_enable(crtc, true);
 		amdgpu_atombios_crtc_blank(crtc, ATOM_DISABLE);
 		dce_v11_0_vga_enable(crtc, false);
+		/* Make sure VBLANK interrupt is still enabled */
+		type = amdgpu_crtc_idx_to_irq_type(adev, amdgpu_crtc->crtc_id);
+		amdgpu_irq_update(adev, &adev->crtc_irq, type);
 		drm_vblank_post_modeset(dev, amdgpu_crtc->crtc_id);
 		dce_v11_0_crtc_load_lut(crtc);
 		break;
@@ -3402,19 +3406,25 @@
 
 	switch (entry->src_data) {
 	case 0: /* vblank */
-		if (disp_int & interrupt_status_offsets[crtc].vblank) {
+		if (disp_int & interrupt_status_offsets[crtc].vblank)
 			dce_v11_0_crtc_vblank_int_ack(adev, crtc);
-			if (amdgpu_irq_enabled(adev, source, irq_type)) {
-				drm_handle_vblank(adev->ddev, crtc);
-			}
-			DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
+		else
+			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+		if (amdgpu_irq_enabled(adev, source, irq_type)) {
+			drm_handle_vblank(adev->ddev, crtc);
 		}
+		DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
+
 		break;
 	case 1: /* vline */
-		if (disp_int & interrupt_status_offsets[crtc].vline) {
+		if (disp_int & interrupt_status_offsets[crtc].vline)
 			dce_v11_0_crtc_vline_int_ack(adev, crtc);
-			DRM_DEBUG("IH: D%d vline\n", crtc + 1);
-		}
+		else
+			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+		DRM_DEBUG("IH: D%d vline\n", crtc + 1);
+
 		break;
 	default:
 		DRM_DEBUG("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data);
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index aaca8d6..cc050a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -2566,6 +2566,7 @@
 	struct drm_device *dev = crtc->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+	unsigned type;
 
 	switch (mode) {
 	case DRM_MODE_DPMS_ON:
@@ -2574,6 +2575,9 @@
 		dce_v8_0_vga_enable(crtc, true);
 		amdgpu_atombios_crtc_blank(crtc, ATOM_DISABLE);
 		dce_v8_0_vga_enable(crtc, false);
+		/* Make sure VBLANK interrupt is still enabled */
+		type = amdgpu_crtc_idx_to_irq_type(adev, amdgpu_crtc->crtc_id);
+		amdgpu_irq_update(adev, &adev->crtc_irq, type);
 		drm_vblank_post_modeset(dev, amdgpu_crtc->crtc_id);
 		dce_v8_0_crtc_load_lut(crtc);
 		break;
@@ -3237,19 +3241,25 @@
 
 	switch (entry->src_data) {
 	case 0: /* vblank */
-		if (disp_int & interrupt_status_offsets[crtc].vblank) {
+		if (disp_int & interrupt_status_offsets[crtc].vblank)
 			WREG32(mmLB_VBLANK_STATUS + crtc_offsets[crtc], LB_VBLANK_STATUS__VBLANK_ACK_MASK);
-			if (amdgpu_irq_enabled(adev, source, irq_type)) {
-				drm_handle_vblank(adev->ddev, crtc);
-			}
-			DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
+		else
+			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+		if (amdgpu_irq_enabled(adev, source, irq_type)) {
+			drm_handle_vblank(adev->ddev, crtc);
 		}
+		DRM_DEBUG("IH: D%d vblank\n", crtc + 1);
+
 		break;
 	case 1: /* vline */
-		if (disp_int & interrupt_status_offsets[crtc].vline) {
+		if (disp_int & interrupt_status_offsets[crtc].vline)
 			WREG32(mmLB_VLINE_STATUS + crtc_offsets[crtc], LB_VLINE_STATUS__VLINE_ACK_MASK);
-			DRM_DEBUG("IH: D%d vline\n", crtc + 1);
-		}
+		else
+			DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+		DRM_DEBUG("IH: D%d vline\n", crtc + 1);
+
 		break;
 	default:
 		DRM_DEBUG("Unhandled interrupt: %d %d\n", entry->src_id, entry->src_data);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 2c188fb..0d8bf2c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -2561,7 +2561,7 @@
  * sheduling on the ring.  This function schedules the IB
  * on the gfx ring for execution by the GPU.
  */
-static void gfx_v7_0_ring_emit_ib(struct amdgpu_ring *ring,
+static void gfx_v7_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 				  struct amdgpu_ib *ib)
 {
 	bool need_ctx_switch = ring->current_ctx != ib->ctx;
@@ -2569,15 +2569,10 @@
 	u32 next_rptr = ring->wptr + 5;
 
 	/* drop the CE preamble IB for the same context */
-	if ((ring->type == AMDGPU_RING_TYPE_GFX) &&
-	    (ib->flags & AMDGPU_IB_FLAG_PREAMBLE) &&
-	    !need_ctx_switch)
+	if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && !need_ctx_switch)
 		return;
 
-	if (ring->type == AMDGPU_RING_TYPE_COMPUTE)
-		control |= INDIRECT_BUFFER_VALID;
-
-	if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX)
+	if (need_ctx_switch)
 		next_rptr += 2;
 
 	next_rptr += 4;
@@ -2588,7 +2583,7 @@
 	amdgpu_ring_write(ring, next_rptr);
 
 	/* insert SWITCH_BUFFER packet before first IB in the ring frame */
-	if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX) {
+	if (need_ctx_switch) {
 		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
 		amdgpu_ring_write(ring, 0);
 	}
@@ -2611,6 +2606,35 @@
 	amdgpu_ring_write(ring, control);
 }
 
+static void gfx_v7_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
+				  struct amdgpu_ib *ib)
+{
+	u32 header, control = 0;
+	u32 next_rptr = ring->wptr + 5;
+
+	control |= INDIRECT_BUFFER_VALID;
+	next_rptr += 4;
+	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
+	amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM);
+	amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
+	amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
+	amdgpu_ring_write(ring, next_rptr);
+
+	header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
+
+	control |= ib->length_dw |
+			   (ib->vm ? (ib->vm->ids[ring->idx].id << 24) : 0);
+
+	amdgpu_ring_write(ring, header);
+	amdgpu_ring_write(ring,
+#ifdef __BIG_ENDIAN
+					  (2 << 0) |
+#endif
+					  (ib->gpu_addr & 0xFFFFFFFC));
+	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFFFF);
+	amdgpu_ring_write(ring, control);
+}
+
 /**
  * gfx_v7_0_ring_test_ib - basic ring IB test
  *
@@ -3056,6 +3080,8 @@
 	mec_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
 	amdgpu_ucode_print_gfx_hdr(&mec_hdr->header);
 	adev->gfx.mec_fw_version = le32_to_cpu(mec_hdr->header.ucode_version);
+	adev->gfx.mec_feature_version = le32_to_cpu(
+					mec_hdr->ucode_feature_version);
 
 	gfx_v7_0_cp_compute_enable(adev, false);
 
@@ -3078,6 +3104,8 @@
 		mec2_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec2_fw->data;
 		amdgpu_ucode_print_gfx_hdr(&mec2_hdr->header);
 		adev->gfx.mec2_fw_version = le32_to_cpu(mec2_hdr->header.ucode_version);
+		adev->gfx.mec2_feature_version = le32_to_cpu(
+				mec2_hdr->ucode_feature_version);
 
 		/* MEC2 */
 		fw_data = (const __le32 *)
@@ -4042,6 +4070,8 @@
 	hdr = (const struct rlc_firmware_header_v1_0 *)adev->gfx.rlc_fw->data;
 	amdgpu_ucode_print_rlc_hdr(&hdr->header);
 	adev->gfx.rlc_fw_version = le32_to_cpu(hdr->header.ucode_version);
+	adev->gfx.rlc_feature_version = le32_to_cpu(
+					hdr->ucode_feature_version);
 
 	gfx_v7_0_rlc_stop(adev);
 
@@ -5098,7 +5128,7 @@
 		dev_info(adev->dev, "  CP_HPD_EOP_CONTROL=0x%08X\n",
 			 RREG32(mmCP_HPD_EOP_CONTROL));
 
-		for (queue = 0; queue < 8; i++) {
+		for (queue = 0; queue < 8; queue++) {
 			cik_srbm_select(adev, me, pipe, queue, 0);
 			dev_info(adev->dev, "  queue: %d\n", queue);
 			dev_info(adev->dev, "  CP_PQ_WPTR_POLL_CNTL=0x%08X\n",
@@ -5555,7 +5585,7 @@
 	.get_wptr = gfx_v7_0_ring_get_wptr_gfx,
 	.set_wptr = gfx_v7_0_ring_set_wptr_gfx,
 	.parse_cs = NULL,
-	.emit_ib = gfx_v7_0_ring_emit_ib,
+	.emit_ib = gfx_v7_0_ring_emit_ib_gfx,
 	.emit_fence = gfx_v7_0_ring_emit_fence_gfx,
 	.emit_semaphore = gfx_v7_0_ring_emit_semaphore,
 	.emit_vm_flush = gfx_v7_0_ring_emit_vm_flush,
@@ -5571,7 +5601,7 @@
 	.get_wptr = gfx_v7_0_ring_get_wptr_compute,
 	.set_wptr = gfx_v7_0_ring_set_wptr_compute,
 	.parse_cs = NULL,
-	.emit_ib = gfx_v7_0_ring_emit_ib,
+	.emit_ib = gfx_v7_0_ring_emit_ib_compute,
 	.emit_fence = gfx_v7_0_ring_emit_fence_compute,
 	.emit_semaphore = gfx_v7_0_ring_emit_semaphore,
 	.emit_vm_flush = gfx_v7_0_ring_emit_vm_flush,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 7b683fb..20e2cfd 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -587,6 +587,7 @@
 	int err;
 	struct amdgpu_firmware_info *info = NULL;
 	const struct common_firmware_header *header = NULL;
+	const struct gfx_firmware_header_v1_0 *cp_hdr;
 
 	DRM_DEBUG("\n");
 
@@ -611,6 +612,9 @@
 	err = amdgpu_ucode_validate(adev->gfx.pfp_fw);
 	if (err)
 		goto out;
+	cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data;
+	adev->gfx.pfp_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
+	adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name);
 	err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev);
@@ -619,6 +623,9 @@
 	err = amdgpu_ucode_validate(adev->gfx.me_fw);
 	if (err)
 		goto out;
+	cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data;
+	adev->gfx.me_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
+	adev->gfx.me_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name);
 	err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev);
@@ -627,12 +634,18 @@
 	err = amdgpu_ucode_validate(adev->gfx.ce_fw);
 	if (err)
 		goto out;
+	cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data;
+	adev->gfx.ce_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
+	adev->gfx.ce_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name);
 	err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
 	err = amdgpu_ucode_validate(adev->gfx.rlc_fw);
+	cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.rlc_fw->data;
+	adev->gfx.rlc_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
+	adev->gfx.rlc_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name);
 	err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev);
@@ -641,6 +654,9 @@
 	err = amdgpu_ucode_validate(adev->gfx.mec_fw);
 	if (err)
 		goto out;
+	cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
+	adev->gfx.mec_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
+	adev->gfx.mec_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name);
 	err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev);
@@ -648,6 +664,12 @@
 		err = amdgpu_ucode_validate(adev->gfx.mec2_fw);
 		if (err)
 			goto out;
+		cp_hdr = (const struct gfx_firmware_header_v1_0 *)
+						adev->gfx.mec2_fw->data;
+		adev->gfx.mec2_fw_version = le32_to_cpu(
+						cp_hdr->header.ucode_version);
+		adev->gfx.mec2_feature_version = le32_to_cpu(
+						cp_hdr->ucode_feature_version);
 	} else {
 		err = 0;
 		adev->gfx.mec2_fw = NULL;
@@ -1813,10 +1835,7 @@
 	u32 data, mask;
 
 	data = RREG32(mmCC_RB_BACKEND_DISABLE);
-	if (data & 1)
-		data &= CC_RB_BACKEND_DISABLE__BACKEND_DISABLE_MASK;
-	else
-		data = 0;
+	data &= CC_RB_BACKEND_DISABLE__BACKEND_DISABLE_MASK;
 
 	data |= RREG32(mmGC_USER_RB_BACKEND_DISABLE);
 
@@ -1986,6 +2005,7 @@
 		adev->gfx.config.max_shader_engines = 1;
 		adev->gfx.config.max_tile_pipes = 2;
 		adev->gfx.config.max_sh_per_se = 1;
+		adev->gfx.config.max_backends_per_se = 2;
 
 		switch (adev->pdev->revision) {
 		case 0xc4:
@@ -1994,7 +2014,6 @@
 		case 0xcc:
 			/* B10 */
 			adev->gfx.config.max_cu_per_sh = 8;
-			adev->gfx.config.max_backends_per_se = 2;
 			break;
 		case 0xc5:
 		case 0x81:
@@ -2003,14 +2022,12 @@
 		case 0xcd:
 			/* B8 */
 			adev->gfx.config.max_cu_per_sh = 6;
-			adev->gfx.config.max_backends_per_se = 2;
 			break;
 		case 0xc6:
 		case 0xca:
 		case 0xce:
 			/* B6 */
 			adev->gfx.config.max_cu_per_sh = 6;
-			adev->gfx.config.max_backends_per_se = 2;
 			break;
 		case 0xc7:
 		case 0x87:
@@ -2018,7 +2035,6 @@
 		default:
 			/* B4 */
 			adev->gfx.config.max_cu_per_sh = 4;
-			adev->gfx.config.max_backends_per_se = 1;
 			break;
 		}
 
@@ -2278,7 +2294,6 @@
 
 	hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
 	amdgpu_ucode_print_rlc_hdr(&hdr->header);
-	adev->gfx.rlc_fw_version = le32_to_cpu(hdr->header.ucode_version);
 
 	fw_data = (const __le32 *)(adev->gfx.rlc_fw->data +
 			   le32_to_cpu(hdr->header.ucode_array_offset_bytes));
@@ -2364,12 +2379,6 @@
 	amdgpu_ucode_print_gfx_hdr(&pfp_hdr->header);
 	amdgpu_ucode_print_gfx_hdr(&ce_hdr->header);
 	amdgpu_ucode_print_gfx_hdr(&me_hdr->header);
-	adev->gfx.pfp_fw_version = le32_to_cpu(pfp_hdr->header.ucode_version);
-	adev->gfx.ce_fw_version = le32_to_cpu(ce_hdr->header.ucode_version);
-	adev->gfx.me_fw_version = le32_to_cpu(me_hdr->header.ucode_version);
-	adev->gfx.me_feature_version = le32_to_cpu(me_hdr->ucode_feature_version);
-	adev->gfx.ce_feature_version = le32_to_cpu(ce_hdr->ucode_feature_version);
-	adev->gfx.pfp_feature_version = le32_to_cpu(pfp_hdr->ucode_feature_version);
 
 	gfx_v8_0_cp_gfx_enable(adev, false);
 
@@ -2625,7 +2634,6 @@
 
 	mec_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
 	amdgpu_ucode_print_gfx_hdr(&mec_hdr->header);
-	adev->gfx.mec_fw_version = le32_to_cpu(mec_hdr->header.ucode_version);
 
 	fw_data = (const __le32 *)
 		(adev->gfx.mec_fw->data +
@@ -2644,7 +2652,6 @@
 
 		mec2_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec2_fw->data;
 		amdgpu_ucode_print_gfx_hdr(&mec2_hdr->header);
-		adev->gfx.mec2_fw_version = le32_to_cpu(mec2_hdr->header.ucode_version);
 
 		fw_data = (const __le32 *)
 			(adev->gfx.mec2_fw->data +
@@ -3128,7 +3135,7 @@
 				WREG32(mmCP_MEC_DOORBELL_RANGE_LOWER,
 				       AMDGPU_DOORBELL_KIQ << 2);
 				WREG32(mmCP_MEC_DOORBELL_RANGE_UPPER,
-						0x7FFFF << 2);
+				       AMDGPU_DOORBELL_MEC_RING7 << 2);
 			}
 			tmp = RREG32(mmCP_HQD_PQ_DOORBELL_CONTROL);
 			tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_DOORBELL_CONTROL,
@@ -3756,7 +3763,7 @@
 	amdgpu_ring_write(ring, 0x20); /* poll interval */
 }
 
-static void gfx_v8_0_ring_emit_ib(struct amdgpu_ring *ring,
+static void gfx_v8_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 				  struct amdgpu_ib *ib)
 {
 	bool need_ctx_switch = ring->current_ctx != ib->ctx;
@@ -3764,15 +3771,10 @@
 	u32 next_rptr = ring->wptr + 5;
 
 	/* drop the CE preamble IB for the same context */
-	if ((ring->type == AMDGPU_RING_TYPE_GFX) &&
-	    (ib->flags & AMDGPU_IB_FLAG_PREAMBLE) &&
-	    !need_ctx_switch)
+	if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && !need_ctx_switch)
 		return;
 
-	if (ring->type == AMDGPU_RING_TYPE_COMPUTE)
-		control |= INDIRECT_BUFFER_VALID;
-
-	if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX)
+	if (need_ctx_switch)
 		next_rptr += 2;
 
 	next_rptr += 4;
@@ -3783,7 +3785,7 @@
 	amdgpu_ring_write(ring, next_rptr);
 
 	/* insert SWITCH_BUFFER packet before first IB in the ring frame */
-	if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX) {
+	if (need_ctx_switch) {
 		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
 		amdgpu_ring_write(ring, 0);
 	}
@@ -3806,6 +3808,36 @@
 	amdgpu_ring_write(ring, control);
 }
 
+static void gfx_v8_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
+				  struct amdgpu_ib *ib)
+{
+	u32 header, control = 0;
+	u32 next_rptr = ring->wptr + 5;
+
+	control |= INDIRECT_BUFFER_VALID;
+
+	next_rptr += 4;
+	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
+	amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM);
+	amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
+	amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
+	amdgpu_ring_write(ring, next_rptr);
+
+	header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
+
+	control |= ib->length_dw |
+			   (ib->vm ? (ib->vm->ids[ring->idx].id << 24) : 0);
+
+	amdgpu_ring_write(ring, header);
+	amdgpu_ring_write(ring,
+#ifdef __BIG_ENDIAN
+					  (2 << 0) |
+#endif
+					  (ib->gpu_addr & 0xFFFFFFFC));
+	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFFFF);
+	amdgpu_ring_write(ring, control);
+}
+
 static void gfx_v8_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr,
 					 u64 seq, unsigned flags)
 {
@@ -4227,7 +4259,7 @@
 	.get_wptr = gfx_v8_0_ring_get_wptr_gfx,
 	.set_wptr = gfx_v8_0_ring_set_wptr_gfx,
 	.parse_cs = NULL,
-	.emit_ib = gfx_v8_0_ring_emit_ib,
+	.emit_ib = gfx_v8_0_ring_emit_ib_gfx,
 	.emit_fence = gfx_v8_0_ring_emit_fence_gfx,
 	.emit_semaphore = gfx_v8_0_ring_emit_semaphore,
 	.emit_vm_flush = gfx_v8_0_ring_emit_vm_flush,
@@ -4243,7 +4275,7 @@
 	.get_wptr = gfx_v8_0_ring_get_wptr_compute,
 	.set_wptr = gfx_v8_0_ring_set_wptr_compute,
 	.parse_cs = NULL,
-	.emit_ib = gfx_v8_0_ring_emit_ib,
+	.emit_ib = gfx_v8_0_ring_emit_ib_compute,
 	.emit_fence = gfx_v8_0_ring_emit_fence_compute,
 	.emit_semaphore = gfx_v8_0_ring_emit_semaphore,
 	.emit_vm_flush = gfx_v8_0_ring_emit_vm_flush,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index d789588..a988dfb 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -121,6 +121,7 @@
 	int err, i;
 	struct amdgpu_firmware_info *info = NULL;
 	const struct common_firmware_header *header = NULL;
+	const struct sdma_firmware_header_v1_0 *hdr;
 
 	DRM_DEBUG("\n");
 
@@ -142,6 +143,9 @@
 		err = amdgpu_ucode_validate(adev->sdma[i].fw);
 		if (err)
 			goto out;
+		hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
+		adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
+		adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
 
 		if (adev->firmware.smu_load) {
 			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i];
@@ -541,8 +545,6 @@
 			hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
 			amdgpu_ucode_print_sdma_hdr(&hdr->header);
 			fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
-			adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
-
 			fw_data = (const __le32 *)
 				(adev->sdma[i].fw->data +
 				 le32_to_cpu(hdr->header.ucode_array_offset_bytes));
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 7bb37b9..2b86569 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -159,6 +159,7 @@
 	int err, i;
 	struct amdgpu_firmware_info *info = NULL;
 	const struct common_firmware_header *header = NULL;
+	const struct sdma_firmware_header_v1_0 *hdr;
 
 	DRM_DEBUG("\n");
 
@@ -183,6 +184,9 @@
 		err = amdgpu_ucode_validate(adev->sdma[i].fw);
 		if (err)
 			goto out;
+		hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
+		adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
+		adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
 
 		if (adev->firmware.smu_load) {
 			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i];
@@ -630,8 +634,6 @@
 		hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
 		amdgpu_ucode_print_sdma_hdr(&hdr->header);
 		fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
-		adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
-
 		fw_data = (const __le32 *)
 			(adev->sdma[i].fw->data +
 				le32_to_cpu(hdr->header.ucode_array_offset_bytes));
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index d62c4002..d1064ca 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -35,6 +35,8 @@
 #include "oss/oss_2_0_d.h"
 #include "oss/oss_2_0_sh_mask.h"
 #include "gca/gfx_8_0_d.h"
+#include "smu/smu_7_1_2_d.h"
+#include "smu/smu_7_1_2_sh_mask.h"
 
 #define GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT	0x04
 #define GRBM_GFX_INDEX__VCE_INSTANCE_MASK	0x10
@@ -112,6 +114,10 @@
 
 	mutex_lock(&adev->grbm_idx_mutex);
 	for (idx = 0; idx < 2; ++idx) {
+
+		if (adev->vce.harvest_config & (1 << idx))
+			continue;
+
 		if(idx == 0)
 			WREG32_P(mmGRBM_GFX_INDEX, 0,
 				~GRBM_GFX_INDEX__VCE_INSTANCE_MASK);
@@ -190,10 +196,52 @@
 	return 0;
 }
 
+#define ixVCE_HARVEST_FUSE_MACRO__ADDRESS     0xC0014074
+#define VCE_HARVEST_FUSE_MACRO__SHIFT       27
+#define VCE_HARVEST_FUSE_MACRO__MASK        0x18000000
+
+static unsigned vce_v3_0_get_harvest_config(struct amdgpu_device *adev)
+{
+	u32 tmp;
+	unsigned ret;
+
+	if (adev->flags & AMDGPU_IS_APU)
+		tmp = (RREG32_SMC(ixVCE_HARVEST_FUSE_MACRO__ADDRESS) &
+		       VCE_HARVEST_FUSE_MACRO__MASK) >>
+			VCE_HARVEST_FUSE_MACRO__SHIFT;
+	else
+		tmp = (RREG32_SMC(ixCC_HARVEST_FUSES) &
+		       CC_HARVEST_FUSES__VCE_DISABLE_MASK) >>
+			CC_HARVEST_FUSES__VCE_DISABLE__SHIFT;
+
+	switch (tmp) {
+	case 1:
+		ret = AMDGPU_VCE_HARVEST_VCE0;
+		break;
+	case 2:
+		ret = AMDGPU_VCE_HARVEST_VCE1;
+		break;
+	case 3:
+		ret = AMDGPU_VCE_HARVEST_VCE0 | AMDGPU_VCE_HARVEST_VCE1;
+		break;
+	default:
+		ret = 0;
+	}
+
+	return ret;
+}
+
 static int vce_v3_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
+	adev->vce.harvest_config = vce_v3_0_get_harvest_config(adev);
+
+	if ((adev->vce.harvest_config &
+	     (AMDGPU_VCE_HARVEST_VCE0 | AMDGPU_VCE_HARVEST_VCE1)) ==
+	    (AMDGPU_VCE_HARVEST_VCE0 | AMDGPU_VCE_HARVEST_VCE1))
+		return -ENOENT;
+
 	vce_v3_0_set_ring_funcs(adev);
 	vce_v3_0_set_irq_funcs(adev);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index fa5a444..68552da 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -122,6 +122,32 @@
 	spin_unlock_irqrestore(&adev->smc_idx_lock, flags);
 }
 
+/* smu_8_0_d.h */
+#define mmMP0PUB_IND_INDEX                                                      0x180
+#define mmMP0PUB_IND_DATA                                                       0x181
+
+static u32 cz_smc_rreg(struct amdgpu_device *adev, u32 reg)
+{
+	unsigned long flags;
+	u32 r;
+
+	spin_lock_irqsave(&adev->smc_idx_lock, flags);
+	WREG32(mmMP0PUB_IND_INDEX, (reg));
+	r = RREG32(mmMP0PUB_IND_DATA);
+	spin_unlock_irqrestore(&adev->smc_idx_lock, flags);
+	return r;
+}
+
+static void cz_smc_wreg(struct amdgpu_device *adev, u32 reg, u32 v)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&adev->smc_idx_lock, flags);
+	WREG32(mmMP0PUB_IND_INDEX, (reg));
+	WREG32(mmMP0PUB_IND_DATA, (v));
+	spin_unlock_irqrestore(&adev->smc_idx_lock, flags);
+}
+
 static u32 vi_uvd_ctx_rreg(struct amdgpu_device *adev, u32 reg)
 {
 	unsigned long flags;
@@ -1222,8 +1248,13 @@
 	bool smc_enabled = false;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	adev->smc_rreg = &vi_smc_rreg;
-	adev->smc_wreg = &vi_smc_wreg;
+	if (adev->flags & AMDGPU_IS_APU) {
+		adev->smc_rreg = &cz_smc_rreg;
+		adev->smc_wreg = &cz_smc_wreg;
+	} else {
+		adev->smc_rreg = &vi_smc_rreg;
+		adev->smc_wreg = &vi_smc_wreg;
+	}
 	adev->pcie_rreg = &vi_pcie_rreg;
 	adev->pcie_wreg = &vi_pcie_wreg;
 	adev->uvd_ctx_rreg = &vi_uvd_ctx_rreg;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 8a1f999..9be0070 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -420,6 +420,12 @@
 	pqm_uninit(&p->pqm);
 
 	pdd = kfd_get_process_device_data(dev, p);
+
+	if (!pdd) {
+		mutex_unlock(&p->mutex);
+		return;
+	}
+
 	if (pdd->reset_wavefronts) {
 		dbgdev_wave_reset_wavefronts(pdd->dev, p);
 		pdd->reset_wavefronts = false;
@@ -431,8 +437,7 @@
 	 * We don't call amd_iommu_unbind_pasid() here
 	 * because the IOMMU called us.
 	 */
-	if (pdd)
-		pdd->bound = false;
+	pdd->bound = false;
 
 	mutex_unlock(&p->mutex);
 }
diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 42d2ffa..01ffe9b 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -531,8 +531,6 @@
 
 	drm_crtc_vblank_off(crtc);
 
-	crtc->mode = *adj;
-
 	val = dcrtc->dumb_ctrl & ~CFG_DUMB_ENA;
 	if (val != dcrtc->dumb_ctrl) {
 		dcrtc->dumb_ctrl = val;
diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c
index 580e10a..60a688e 100644
--- a/drivers/gpu/drm/armada/armada_gem.c
+++ b/drivers/gpu/drm/armada/armada_gem.c
@@ -69,8 +69,9 @@
 
 	if (dobj->obj.import_attach) {
 		/* We only ever display imported data */
-		dma_buf_unmap_attachment(dobj->obj.import_attach, dobj->sgt,
-					 DMA_TO_DEVICE);
+		if (dobj->sgt)
+			dma_buf_unmap_attachment(dobj->obj.import_attach,
+						 dobj->sgt, DMA_TO_DEVICE);
 		drm_prime_gem_destroy(&dobj->obj, NULL);
 	}
 
diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index c5b06fd..e939fab 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -7,6 +7,7 @@
  * published by the Free Software Foundation.
  */
 #include <drm/drmP.h>
+#include <drm/drm_plane_helper.h>
 #include "armada_crtc.h"
 #include "armada_drm.h"
 #include "armada_fb.h"
@@ -85,16 +86,8 @@
 
 	if (fb)
 		armada_drm_queue_unref_work(dcrtc->crtc.dev, fb);
-}
 
-static unsigned armada_limit(int start, unsigned size, unsigned max)
-{
-	int end = start + size;
-	if (end < 0)
-		return 0;
-	if (start < 0)
-		start = 0;
-	return (unsigned)end > max ? max - start : end - start;
+	wake_up(&dplane->vbl.wait);
 }
 
 static int
@@ -105,26 +98,39 @@
 {
 	struct armada_plane *dplane = drm_to_armada_plane(plane);
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct drm_rect src = {
+		.x1 = src_x,
+		.y1 = src_y,
+		.x2 = src_x + src_w,
+		.y2 = src_y + src_h,
+	};
+	struct drm_rect dest = {
+		.x1 = crtc_x,
+		.y1 = crtc_y,
+		.x2 = crtc_x + crtc_w,
+		.y2 = crtc_y + crtc_h,
+	};
+	const struct drm_rect clip = {
+		.x2 = crtc->mode.hdisplay,
+		.y2 = crtc->mode.vdisplay,
+	};
 	uint32_t val, ctrl0;
 	unsigned idx = 0;
+	bool visible;
 	int ret;
 
-	crtc_w = armada_limit(crtc_x, crtc_w, dcrtc->crtc.mode.hdisplay);
-	crtc_h = armada_limit(crtc_y, crtc_h, dcrtc->crtc.mode.vdisplay);
+	ret = drm_plane_helper_check_update(plane, crtc, fb, &src, &dest, &clip,
+					    0, INT_MAX, true, false, &visible);
+	if (ret)
+		return ret;
+
 	ctrl0 = CFG_DMA_FMT(drm_fb_to_armada_fb(fb)->fmt) |
 		CFG_DMA_MOD(drm_fb_to_armada_fb(fb)->mod) |
 		CFG_CBSH_ENA | CFG_DMA_HSMOOTH | CFG_DMA_ENA;
 
 	/* Does the position/size result in nothing to display? */
-	if (crtc_w == 0 || crtc_h == 0) {
+	if (!visible)
 		ctrl0 &= ~CFG_DMA_ENA;
-	}
-
-	/*
-	 * FIXME: if the starting point is off screen, we need to
-	 * adjust src_x, src_y, src_w, src_h appropriately, and
-	 * according to the scale.
-	 */
 
 	if (!dcrtc->plane) {
 		dcrtc->plane = plane;
@@ -134,15 +140,19 @@
 	/* FIXME: overlay on an interlaced display */
 	/* Just updating the position/size? */
 	if (plane->fb == fb && dplane->ctrl0 == ctrl0) {
-		val = (src_h & 0xffff0000) | src_w >> 16;
+		val = (drm_rect_height(&src) & 0xffff0000) |
+		      drm_rect_width(&src) >> 16;
 		dplane->src_hw = val;
 		writel_relaxed(val, dcrtc->base + LCD_SPU_DMA_HPXL_VLN);
-		val = crtc_h << 16 | crtc_w;
+
+		val = drm_rect_height(&dest) << 16 | drm_rect_width(&dest);
 		dplane->dst_hw = val;
 		writel_relaxed(val, dcrtc->base + LCD_SPU_DZM_HPXL_VLN);
-		val = crtc_y << 16 | crtc_x;
+
+		val = dest.y1 << 16 | dest.x1;
 		dplane->dst_yx = val;
 		writel_relaxed(val, dcrtc->base + LCD_SPU_DMA_OVSA_HPXL_VLN);
+
 		return 0;
 	} else if (~dplane->ctrl0 & ctrl0 & CFG_DMA_ENA) {
 		/* Power up the Y/U/V FIFOs on ENA 0->1 transitions */
@@ -150,15 +160,14 @@
 			       dcrtc->base + LCD_SPU_SRAM_PARA1);
 	}
 
-	ret = wait_event_timeout(dplane->vbl.wait,
-				 list_empty(&dplane->vbl.update.node),
-				 HZ/25);
-	if (ret < 0)
-		return ret;
+	wait_event_timeout(dplane->vbl.wait,
+			   list_empty(&dplane->vbl.update.node),
+			   HZ/25);
 
 	if (plane->fb != fb) {
 		struct armada_gem_object *obj = drm_fb_obj(fb);
-		uint32_t sy, su, sv;
+		uint32_t addr[3], pixel_format;
+		int i, num_planes, hsub;
 
 		/*
 		 * Take a reference on the new framebuffer - we want to
@@ -178,26 +187,39 @@
 							    older_fb);
 		}
 
-		src_y >>= 16;
-		src_x >>= 16;
-		sy = obj->dev_addr + fb->offsets[0] + src_y * fb->pitches[0] +
-			src_x * fb->bits_per_pixel / 8;
-		su = obj->dev_addr + fb->offsets[1] + src_y * fb->pitches[1] +
-			src_x;
-		sv = obj->dev_addr + fb->offsets[2] + src_y * fb->pitches[2] +
-			src_x;
+		src_y = src.y1 >> 16;
+		src_x = src.x1 >> 16;
 
-		armada_reg_queue_set(dplane->vbl.regs, idx, sy,
+		pixel_format = fb->pixel_format;
+		hsub = drm_format_horz_chroma_subsampling(pixel_format);
+		num_planes = drm_format_num_planes(pixel_format);
+
+		/*
+		 * Annoyingly, shifting a YUYV-format image by one pixel
+		 * causes the U/V planes to toggle.  Toggle the UV swap.
+		 * (Unfortunately, this causes momentary colour flickering.)
+		 */
+		if (src_x & (hsub - 1) && num_planes == 1)
+			ctrl0 ^= CFG_DMA_MOD(CFG_SWAPUV);
+
+		for (i = 0; i < num_planes; i++)
+			addr[i] = obj->dev_addr + fb->offsets[i] +
+				  src_y * fb->pitches[i] +
+				  src_x * drm_format_plane_cpp(pixel_format, i);
+		for (; i < ARRAY_SIZE(addr); i++)
+			addr[i] = 0;
+
+		armada_reg_queue_set(dplane->vbl.regs, idx, addr[0],
 				     LCD_SPU_DMA_START_ADDR_Y0);
-		armada_reg_queue_set(dplane->vbl.regs, idx, su,
+		armada_reg_queue_set(dplane->vbl.regs, idx, addr[1],
 				     LCD_SPU_DMA_START_ADDR_U0);
-		armada_reg_queue_set(dplane->vbl.regs, idx, sv,
+		armada_reg_queue_set(dplane->vbl.regs, idx, addr[2],
 				     LCD_SPU_DMA_START_ADDR_V0);
-		armada_reg_queue_set(dplane->vbl.regs, idx, sy,
+		armada_reg_queue_set(dplane->vbl.regs, idx, addr[0],
 				     LCD_SPU_DMA_START_ADDR_Y1);
-		armada_reg_queue_set(dplane->vbl.regs, idx, su,
+		armada_reg_queue_set(dplane->vbl.regs, idx, addr[1],
 				     LCD_SPU_DMA_START_ADDR_U1);
-		armada_reg_queue_set(dplane->vbl.regs, idx, sv,
+		armada_reg_queue_set(dplane->vbl.regs, idx, addr[2],
 				     LCD_SPU_DMA_START_ADDR_V1);
 
 		val = fb->pitches[0] << 16 | fb->pitches[0];
@@ -208,24 +230,27 @@
 				     LCD_SPU_DMA_PITCH_UV);
 	}
 
-	val = (src_h & 0xffff0000) | src_w >> 16;
+	val = (drm_rect_height(&src) & 0xffff0000) | drm_rect_width(&src) >> 16;
 	if (dplane->src_hw != val) {
 		dplane->src_hw = val;
 		armada_reg_queue_set(dplane->vbl.regs, idx, val,
 				     LCD_SPU_DMA_HPXL_VLN);
 	}
-	val = crtc_h << 16 | crtc_w;
+
+	val = drm_rect_height(&dest) << 16 | drm_rect_width(&dest);
 	if (dplane->dst_hw != val) {
 		dplane->dst_hw = val;
 		armada_reg_queue_set(dplane->vbl.regs, idx, val,
 				     LCD_SPU_DZM_HPXL_VLN);
 	}
-	val = crtc_y << 16 | crtc_x;
+
+	val = dest.y1 << 16 | dest.x1;
 	if (dplane->dst_yx != val) {
 		dplane->dst_yx = val;
 		armada_reg_queue_set(dplane->vbl.regs, idx, val,
 				     LCD_SPU_DMA_OVSA_HPXL_VLN);
 	}
+
 	if (dplane->ctrl0 != ctrl0) {
 		dplane->ctrl0 = ctrl0;
 		armada_reg_queue_mod(dplane->vbl.regs, idx, ctrl0,
@@ -279,7 +304,11 @@
 
 static void armada_plane_destroy(struct drm_plane *plane)
 {
-	kfree(plane);
+	struct armada_plane *dplane = drm_to_armada_plane(plane);
+
+	drm_plane_cleanup(plane);
+
+	kfree(dplane);
 }
 
 static int armada_plane_set_property(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
index f69b925..5ae5c69 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_crtc.c
@@ -355,6 +355,7 @@
 		planes->overlays[i]->base.possible_crtcs = 1 << crtc->id;
 
 	drm_crtc_helper_add(&crtc->base, &lcdc_crtc_helper_funcs);
+	drm_crtc_vblank_reset(&crtc->base);
 
 	dc->crtc = &crtc->base;
 
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
index 60b0c13..ef6182b 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
@@ -313,6 +313,12 @@
 
 	pm_runtime_enable(dev->dev);
 
+	ret = drm_vblank_init(dev, 1);
+	if (ret < 0) {
+		dev_err(dev->dev, "failed to initialize vblank\n");
+		goto err_periph_clk_disable;
+	}
+
 	ret = atmel_hlcdc_dc_modeset_init(dev);
 	if (ret < 0) {
 		dev_err(dev->dev, "failed to initialize mode setting\n");
@@ -321,12 +327,6 @@
 
 	drm_mode_config_reset(dev);
 
-	ret = drm_vblank_init(dev, 1);
-	if (ret < 0) {
-		dev_err(dev->dev, "failed to initialize vblank\n");
-		goto err_periph_clk_disable;
-	}
-
 	pm_runtime_get_sync(dev->dev);
 	ret = drm_irq_install(dev, dc->hlcdc->irq);
 	pm_runtime_put_sync(dev->dev);
@@ -559,7 +559,7 @@
 	return 0;
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 static int atmel_hlcdc_dc_drm_suspend(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 5b59d5ad..9dcc728 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -196,7 +196,12 @@
 	}
 
 	funcs = connector->helper_private;
-	new_encoder = funcs->best_encoder(connector);
+
+	if (funcs->atomic_best_encoder)
+		new_encoder = funcs->atomic_best_encoder(connector,
+							 connector_state);
+	else
+		new_encoder = funcs->best_encoder(connector);
 
 	if (!new_encoder) {
 		DRM_DEBUG_ATOMIC("No suitable encoder found for [CONNECTOR:%d:%s]\n",
@@ -229,6 +234,9 @@
 		}
 	}
 
+	if (WARN_ON(!connector_state->crtc))
+		return -EINVAL;
+
 	connector_state->best_encoder = new_encoder;
 	idx = drm_crtc_index(connector_state->crtc);
 
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index b9ba061..fed7483 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -2706,8 +2706,11 @@
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EINVAL;
 
-	/* For some reason crtc x/y offsets are signed internally. */
-	if (crtc_req->x > INT_MAX || crtc_req->y > INT_MAX)
+	/*
+	 * Universal plane src offsets are only 16.16, prevent havoc for
+	 * drivers using universal plane code internally.
+	 */
+	if (crtc_req->x & 0xffff0000 || crtc_req->y & 0xffff0000)
 		return -ERANGE;
 
 	drm_modeset_lock_all(dev);
@@ -5395,12 +5398,9 @@
 		if (encoder->funcs->reset)
 			encoder->funcs->reset(encoder);
 
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-		connector->status = connector_status_unknown;
-
+	list_for_each_entry(connector, &dev->mode_config.connector_list, head)
 		if (connector->funcs->reset)
 			connector->funcs->reset(connector);
-	}
 }
 EXPORT_SYMBOL(drm_mode_config_reset);
 
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 778bbb6..eb603f1de 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -873,9 +873,10 @@
 		   from an EDID retrieval */
 		if (port->connector) {
 			mutex_lock(&mgr->destroy_connector_lock);
-			list_add(&port->connector->destroy_list, &mgr->destroy_connector_list);
+			list_add(&port->next, &mgr->destroy_connector_list);
 			mutex_unlock(&mgr->destroy_connector_lock);
 			schedule_work(&mgr->destroy_connector_work);
+			return;
 		}
 		drm_dp_port_teardown_pdt(port, port->pdt);
 
@@ -1294,7 +1295,6 @@
 				goto retry;
 			}
 			DRM_DEBUG_KMS("failed to dpcd write %d %d\n", tosend, ret);
-			WARN(1, "fail\n");
 
 			return -EIO;
 		}
@@ -2660,7 +2660,7 @@
 static void drm_dp_destroy_connector_work(struct work_struct *work)
 {
 	struct drm_dp_mst_topology_mgr *mgr = container_of(work, struct drm_dp_mst_topology_mgr, destroy_connector_work);
-	struct drm_connector *connector;
+	struct drm_dp_mst_port *port;
 
 	/*
 	 * Not a regular list traverse as we have to drop the destroy
@@ -2669,15 +2669,21 @@
 	 */
 	for (;;) {
 		mutex_lock(&mgr->destroy_connector_lock);
-		connector = list_first_entry_or_null(&mgr->destroy_connector_list, struct drm_connector, destroy_list);
-		if (!connector) {
+		port = list_first_entry_or_null(&mgr->destroy_connector_list, struct drm_dp_mst_port, next);
+		if (!port) {
 			mutex_unlock(&mgr->destroy_connector_lock);
 			break;
 		}
-		list_del(&connector->destroy_list);
+		list_del(&port->next);
 		mutex_unlock(&mgr->destroy_connector_lock);
 
-		mgr->cbs->destroy_connector(mgr, connector);
+		mgr->cbs->destroy_connector(mgr, port->connector);
+
+		drm_dp_port_teardown_pdt(port, port->pdt);
+
+		if (!port->input && port->vcpi.vcpi > 0)
+			drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi);
+		kfree(port);
 	}
 }
 
diff --git a/drivers/gpu/drm/drm_ioc32.c b/drivers/gpu/drm/drm_ioc32.c
index aa8bbb4..9cfcd0a 100644
--- a/drivers/gpu/drm/drm_ioc32.c
+++ b/drivers/gpu/drm/drm_ioc32.c
@@ -70,6 +70,8 @@
 
 #define DRM_IOCTL_WAIT_VBLANK32		DRM_IOWR(0x3a, drm_wait_vblank32_t)
 
+#define DRM_IOCTL_MODE_ADDFB232		DRM_IOWR(0xb8, drm_mode_fb_cmd232_t)
+
 typedef struct drm_version_32 {
 	int version_major;	  /**< Major version */
 	int version_minor;	  /**< Minor version */
@@ -1016,6 +1018,63 @@
 	return 0;
 }
 
+typedef struct drm_mode_fb_cmd232 {
+	u32 fb_id;
+	u32 width;
+	u32 height;
+	u32 pixel_format;
+	u32 flags;
+	u32 handles[4];
+	u32 pitches[4];
+	u32 offsets[4];
+	u64 modifier[4];
+} __attribute__((packed)) drm_mode_fb_cmd232_t;
+
+static int compat_drm_mode_addfb2(struct file *file, unsigned int cmd,
+				  unsigned long arg)
+{
+	struct drm_mode_fb_cmd232 __user *argp = (void __user *)arg;
+	struct drm_mode_fb_cmd232 req32;
+	struct drm_mode_fb_cmd2 __user *req64;
+	int i;
+	int err;
+
+	if (copy_from_user(&req32, argp, sizeof(req32)))
+		return -EFAULT;
+
+	req64 = compat_alloc_user_space(sizeof(*req64));
+
+	if (!access_ok(VERIFY_WRITE, req64, sizeof(*req64))
+	    || __put_user(req32.width, &req64->width)
+	    || __put_user(req32.height, &req64->height)
+	    || __put_user(req32.pixel_format, &req64->pixel_format)
+	    || __put_user(req32.flags, &req64->flags))
+		return -EFAULT;
+
+	for (i = 0; i < 4; i++) {
+		if (__put_user(req32.handles[i], &req64->handles[i]))
+			return -EFAULT;
+		if (__put_user(req32.pitches[i], &req64->pitches[i]))
+			return -EFAULT;
+		if (__put_user(req32.offsets[i], &req64->offsets[i]))
+			return -EFAULT;
+		if (__put_user(req32.modifier[i], &req64->modifier[i]))
+			return -EFAULT;
+	}
+
+	err = drm_ioctl(file, DRM_IOCTL_MODE_ADDFB2, (unsigned long)req64);
+	if (err)
+		return err;
+
+	if (__get_user(req32.fb_id, &req64->fb_id))
+		return -EFAULT;
+
+	if (copy_to_user(argp, &req32, sizeof(req32)))
+		return -EFAULT;
+
+	return 0;
+}
+
 static drm_ioctl_compat_t *drm_compat_ioctls[] = {
 	[DRM_IOCTL_NR(DRM_IOCTL_VERSION32)] = compat_drm_version,
 	[DRM_IOCTL_NR(DRM_IOCTL_GET_UNIQUE32)] = compat_drm_getunique,
@@ -1048,6 +1107,7 @@
 	[DRM_IOCTL_NR(DRM_IOCTL_UPDATE_DRAW32)] = compat_drm_update_draw,
 #endif
 	[DRM_IOCTL_NR(DRM_IOCTL_WAIT_VBLANK32)] = compat_drm_wait_vblank,
+	[DRM_IOCTL_NR(DRM_IOCTL_MODE_ADDFB232)] = compat_drm_mode_addfb2,
 };
 
 /**
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index f9cc68f..b50fa0a 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -75,7 +75,7 @@
 module_param_named(timestamp_monotonic, drm_timestamp_monotonic, int, 0600);
 
 static void store_vblank(struct drm_device *dev, int crtc,
-			 unsigned vblank_count_inc,
+			 u32 vblank_count_inc,
 			 struct timeval *t_vblank)
 {
 	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimc.c b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
index 842d6b8..2a65235 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimc.c
@@ -1745,7 +1745,6 @@
 	spin_lock_init(&ctx->lock);
 	platform_set_drvdata(pdev, ctx);
 
-	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
 
 	ret = exynos_drm_ippdrv_register(ippdrv);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
index 8040ed2..f1c6b76 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
@@ -593,8 +593,7 @@
 
 	gsc_write(cfg, GSC_IN_CON);
 
-	ctx->rotation = cfg &
-		(GSC_IN_ROT_90 | GSC_IN_ROT_270) ? 1 : 0;
+	ctx->rotation = (cfg & GSC_IN_ROT_90) ? 1 : 0;
 	*swap = ctx->rotation;
 
 	return 0;
@@ -857,8 +856,7 @@
 
 	gsc_write(cfg, GSC_IN_CON);
 
-	ctx->rotation = cfg &
-		(GSC_IN_ROT_90 | GSC_IN_ROT_270) ? 1 : 0;
+	ctx->rotation = (cfg & GSC_IN_ROT_90) ? 1 : 0;
 	*swap = ctx->rotation;
 
 	return 0;
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 99e2864..4a00990 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -1064,6 +1064,7 @@
 {
 	struct hdmi_context *hdata = ctx_from_connector(connector);
 	struct edid *edid;
+	int ret;
 
 	if (!hdata->ddc_adpt)
 		return -ENODEV;
@@ -1079,7 +1080,11 @@
 
 	drm_mode_connector_update_edid_property(connector, edid);
 
-	return drm_add_edid_modes(connector, edid);
+	ret = drm_add_edid_modes(connector, edid);
+
+	kfree(edid);
+
+	return ret;
 }
 
 static int hdmi_find_phy_conf(struct hdmi_context *hdata, u32 pixel_clock)
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index cae98db..4706b56 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -718,6 +718,10 @@
 
 	/* handling VSYNC */
 	if (val & MXR_INT_STATUS_VSYNC) {
+		/* vsync interrupt use different bit for read and clear */
+		val |= MXR_INT_CLEAR_VSYNC;
+		val &= ~MXR_INT_STATUS_VSYNC;
+
 		/* interlace scan need to check shadow register */
 		if (ctx->interlace) {
 			base = mixer_reg_read(res, MXR_GRAPHIC_BASE(0));
@@ -743,11 +747,6 @@
 
 out:
 	/* clear interrupts */
-	if (~val & MXR_INT_EN_VSYNC) {
-		/* vsync interrupt use different bit for read and clear */
-		val &= ~MXR_INT_EN_VSYNC;
-		val |= MXR_INT_CLEAR_VSYNC;
-	}
 	mixer_reg_write(res, MXR_INT_STATUS, val);
 
 	spin_unlock(&res->reg_slock);
@@ -907,8 +906,8 @@
 	}
 
 	/* enable vsync interrupt */
-	mixer_reg_writemask(res, MXR_INT_EN, MXR_INT_EN_VSYNC,
-			MXR_INT_EN_VSYNC);
+	mixer_reg_writemask(res, MXR_INT_STATUS, ~0, MXR_INT_CLEAR_VSYNC);
+	mixer_reg_writemask(res, MXR_INT_EN, ~0, MXR_INT_EN_VSYNC);
 
 	return 0;
 }
@@ -918,7 +917,13 @@
 	struct mixer_context *mixer_ctx = crtc->ctx;
 	struct mixer_resources *res = &mixer_ctx->mixer_res;
 
+	if (!mixer_ctx->powered) {
+		mixer_ctx->int_en &= MXR_INT_EN_VSYNC;
+		return;
+	}
+
 	/* disable vsync interrupt */
+	mixer_reg_writemask(res, MXR_INT_STATUS, ~0, MXR_INT_CLEAR_VSYNC);
 	mixer_reg_writemask(res, MXR_INT_EN, 0, MXR_INT_EN_VSYNC);
 }
 
@@ -1047,6 +1052,8 @@
 
 	mixer_reg_writemask(res, MXR_STATUS, ~0, MXR_STATUS_SOFT_RESET);
 
+	if (ctx->int_en & MXR_INT_EN_VSYNC)
+		mixer_reg_writemask(res, MXR_INT_STATUS, ~0, MXR_INT_CLEAR_VSYNC);
 	mixer_reg_write(res, MXR_INT_EN, ctx->int_en);
 	mixer_win_reset(ctx);
 }
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index fe1599d..424228b 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -606,8 +606,6 @@
 tda998x_write_if(struct tda998x_priv *priv, uint8_t bit, uint16_t addr,
 		 uint8_t *buf, size_t size)
 {
-	buf[PB(0)] = tda998x_cksum(buf, size);
-
 	reg_clear(priv, REG_DIP_IF_FLAGS, bit);
 	reg_write_range(priv, addr, buf, size);
 	reg_set(priv, REG_DIP_IF_FLAGS, bit);
@@ -627,6 +625,8 @@
 	buf[PB(4)] = p->audio_frame[4];
 	buf[PB(5)] = p->audio_frame[5] & 0xf8; /* DM_INH + LSV */
 
+	buf[PB(0)] = tda998x_cksum(buf, sizeof(buf));
+
 	tda998x_write_if(priv, DIP_IF_FLAGS_IF4, REG_IF4_HB0, buf,
 			 sizeof(buf));
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 542fac6..fd1de45 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -826,6 +826,7 @@
 	struct kref ref;
 	int user_handle;
 	uint8_t remap_slice;
+	struct drm_i915_private *i915;
 	struct drm_i915_file_private *file_priv;
 	struct i915_ctx_hang_stats hang_stats;
 	struct i915_hw_ppgtt *ppgtt;
@@ -2036,8 +2037,6 @@
 	unsigned int cache_level:3;
 	unsigned int cache_dirty:1;
 
-	unsigned int has_dma_mapping:1;
-
 	unsigned int frontbuffer_bits:INTEL_FRONTBUFFER_BITS;
 
 	unsigned int pin_display;
@@ -3116,7 +3115,8 @@
 int i915_debugfs_connector_add(struct drm_connector *connector);
 void intel_display_crc_init(struct drm_device *dev);
 #else
-static inline int i915_debugfs_connector_add(struct drm_connector *connector) {}
+static inline int i915_debugfs_connector_add(struct drm_connector *connector)
+{ return 0; }
 static inline void intel_display_crc_init(struct drm_device *dev) {}
 #endif
 
@@ -3303,15 +3303,14 @@
 #define I915_READ64(reg)	dev_priv->uncore.funcs.mmio_readq(dev_priv, (reg), true)
 
 #define I915_READ64_2x32(lower_reg, upper_reg) ({			\
-		u32 upper = I915_READ(upper_reg);			\
-		u32 lower = I915_READ(lower_reg);			\
-		u32 tmp = I915_READ(upper_reg);				\
-		if (upper != tmp) {					\
-			upper = tmp;					\
-			lower = I915_READ(lower_reg);			\
-			WARN_ON(I915_READ(upper_reg) != upper);		\
-		}							\
-		(u64)upper << 32 | lower; })
+	u32 upper, lower, tmp;						\
+	tmp = I915_READ(upper_reg);					\
+	do {								\
+		upper = tmp;						\
+		lower = I915_READ(lower_reg);				\
+		tmp = I915_READ(upper_reg);				\
+	} while (upper != tmp);						\
+	(u64)upper << 32 | lower; })
 
 #define POSTING_READ(reg)	(void)I915_READ_NOTRACE(reg)
 #define POSTING_READ16(reg)	(void)I915_READ16_NOTRACE(reg)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 248fd1a..52b446b 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -213,7 +213,6 @@
 	sg_dma_len(sg) = obj->base.size;
 
 	obj->pages = st;
-	obj->has_dma_mapping = true;
 	return 0;
 }
 
@@ -265,8 +264,6 @@
 
 	sg_free_table(obj->pages);
 	kfree(obj->pages);
-
-	obj->has_dma_mapping = false;
 }
 
 static void
@@ -2139,6 +2136,8 @@
 		obj->base.read_domains = obj->base.write_domain = I915_GEM_DOMAIN_CPU;
 	}
 
+	i915_gem_gtt_finish_object(obj);
+
 	if (i915_gem_object_needs_bit17_swizzle(obj))
 		i915_gem_object_save_bit_17_swizzle(obj);
 
@@ -2199,6 +2198,7 @@
 	struct sg_page_iter sg_iter;
 	struct page *page;
 	unsigned long last_pfn = 0;	/* suppress gcc warning */
+	int ret;
 	gfp_t gfp;
 
 	/* Assert that the object is not currently in any GPU domain. As it
@@ -2246,8 +2246,10 @@
 			 */
 			i915_gem_shrink_all(dev_priv);
 			page = shmem_read_mapping_page(mapping, i);
-			if (IS_ERR(page))
+			if (IS_ERR(page)) {
+				ret = PTR_ERR(page);
 				goto err_pages;
+			}
 		}
 #ifdef CONFIG_SWIOTLB
 		if (swiotlb_nr_tbl()) {
@@ -2276,6 +2278,10 @@
 		sg_mark_end(sg);
 	obj->pages = st;
 
+	ret = i915_gem_gtt_prepare_object(obj);
+	if (ret)
+		goto err_pages;
+
 	if (i915_gem_object_needs_bit17_swizzle(obj))
 		i915_gem_object_do_bit_17_swizzle(obj);
 
@@ -2300,10 +2306,10 @@
 	 * space and so want to translate the error from shmemfs back to our
 	 * usual understanding of ENOMEM.
 	 */
-	if (PTR_ERR(page) == -ENOSPC)
-		return -ENOMEM;
-	else
-		return PTR_ERR(page);
+	if (ret == -ENOSPC)
+		ret = -ENOMEM;
+
+	return ret;
 }
 
 /* Ensure that the associated pages are gathered from the backing storage
@@ -2542,6 +2548,7 @@
 	}
 
 	request->emitted_jiffies = jiffies;
+	ring->last_submitted_seqno = request->seqno;
 	list_add_tail(&request->list, &ring->request_list);
 	request->file_priv = NULL;
 
@@ -3247,10 +3254,8 @@
 
 	/* Since the unbound list is global, only move to that list if
 	 * no more VMAs exist. */
-	if (list_empty(&obj->vma_list)) {
-		i915_gem_gtt_finish_object(obj);
+	if (list_empty(&obj->vma_list))
 		list_move_tail(&obj->global_list, &dev_priv->mm.unbound_list);
-	}
 
 	/* And finally now the object is completely decoupled from this vma,
 	 * we can drop its hold on the backing storage and allow it to be
@@ -3768,22 +3773,16 @@
 		goto err_remove_node;
 	}
 
-	ret = i915_gem_gtt_prepare_object(obj);
-	if (ret)
-		goto err_remove_node;
-
 	trace_i915_vma_bind(vma, flags);
 	ret = i915_vma_bind(vma, obj->cache_level, flags);
 	if (ret)
-		goto err_finish_gtt;
+		goto err_remove_node;
 
 	list_move_tail(&obj->global_list, &dev_priv->mm.bound_list);
 	list_add_tail(&vma->mm_list, &vm->inactive_list);
 
 	return vma;
 
-err_finish_gtt:
-	i915_gem_gtt_finish_object(obj);
 err_remove_node:
 	drm_mm_remove_node(&vma->node);
 err_free_vma:
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 8867818..48afa77 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -135,8 +135,7 @@
 
 void i915_gem_context_free(struct kref *ctx_ref)
 {
-	struct intel_context *ctx = container_of(ctx_ref,
-						 typeof(*ctx), ref);
+	struct intel_context *ctx = container_of(ctx_ref, typeof(*ctx), ref);
 
 	trace_i915_context_free(ctx);
 
@@ -157,9 +156,7 @@
 	struct drm_i915_gem_object *obj;
 	int ret;
 
-	obj = i915_gem_object_create_stolen(dev, size);
-	if (obj == NULL)
-		obj = i915_gem_alloc_object(dev, size);
+	obj = i915_gem_alloc_object(dev, size);
 	if (obj == NULL)
 		return ERR_PTR(-ENOMEM);
 
@@ -197,6 +194,7 @@
 
 	kref_init(&ctx->ref);
 	list_add_tail(&ctx->link, &dev_priv->context_list);
+	ctx->i915 = dev_priv;
 
 	if (dev_priv->hw_context_size) {
 		struct drm_i915_gem_object *obj =
diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
index 7998da2..e9c2bfd 100644
--- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
@@ -256,7 +256,6 @@
 		return PTR_ERR(sg);
 
 	obj->pages = sg;
-	obj->has_dma_mapping = true;
 	return 0;
 }
 
@@ -264,7 +263,6 @@
 {
 	dma_buf_unmap_attachment(obj->base.import_attach,
 				 obj->pages, DMA_BIDIRECTIONAL);
-	obj->has_dma_mapping = false;
 }
 
 static const struct drm_i915_gem_object_ops i915_gem_object_dmabuf_ops = {
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 9daa288..31e8269 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1723,9 +1723,6 @@
 
 int i915_gem_gtt_prepare_object(struct drm_i915_gem_object *obj)
 {
-	if (obj->has_dma_mapping)
-		return 0;
-
 	if (!dma_map_sg(&obj->base.dev->pdev->dev,
 			obj->pages->sgl, obj->pages->nents,
 			PCI_DMA_BIDIRECTIONAL))
@@ -1926,6 +1923,17 @@
 		vma->vm->insert_entries(vma->vm, pages,
 					vma->node.start,
 					cache_level, pte_flags);
+
+		/* Note the inconsistency here is due to absence of the
+		 * aliasing ppgtt on gen4 and earlier. Though we always
+		 * request PIN_USER for execbuffer (translated to LOCAL_BIND),
+		 * without the appgtt, we cannot honour that request and so
+		 * must substitute it with a global binding. Since we do this
+		 * behind the upper layers back, we need to explicitly set
+		 * the bound flag ourselves.
+		 */
+		vma->bound |= GLOBAL_BIND;
+
 	}
 
 	if (dev_priv->mm.aliasing_ppgtt && flags & LOCAL_BIND) {
@@ -1972,10 +1980,8 @@
 
 	interruptible = do_idling(dev_priv);
 
-	if (!obj->has_dma_mapping)
-		dma_unmap_sg(&dev->pdev->dev,
-			     obj->pages->sgl, obj->pages->nents,
-			     PCI_DMA_BIDIRECTIONAL);
+	dma_unmap_sg(&dev->pdev->dev, obj->pages->sgl, obj->pages->nents,
+		     PCI_DMA_BIDIRECTIONAL);
 
 	undo_idling(dev_priv, interruptible);
 }
@@ -2546,6 +2552,8 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj;
 	struct i915_address_space *vm;
+	struct i915_vma *vma;
+	bool flush;
 
 	i915_check_and_clear_faults(dev);
 
@@ -2555,17 +2563,24 @@
 				       dev_priv->gtt.base.total,
 				       true);
 
+	/* Cache flush objects bound into GGTT and rebind them. */
+	vm = &dev_priv->gtt.base;
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		struct i915_vma *vma = i915_gem_obj_to_vma(obj,
-							   &dev_priv->gtt.base);
-		if (!vma)
-			continue;
+		flush = false;
+		list_for_each_entry(vma, &obj->vma_list, vma_link) {
+			if (vma->vm != vm)
+				continue;
 
-		i915_gem_clflush_object(obj, obj->pin_display);
-		WARN_ON(i915_vma_bind(vma, obj->cache_level, PIN_UPDATE));
+			WARN_ON(i915_vma_bind(vma, obj->cache_level,
+					      PIN_UPDATE));
+
+			flush = true;
+		}
+
+		if (flush)
+			i915_gem_clflush_object(obj, obj->pin_display);
 	}
 
-
 	if (INTEL_INFO(dev)->gen >= 8) {
 		if (IS_CHERRYVIEW(dev) || IS_BROXTON(dev))
 			chv_setup_private_ppat(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 348ed5a..8b5b784 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -416,7 +416,6 @@
 	if (obj->pages == NULL)
 		goto cleanup;
 
-	obj->has_dma_mapping = true;
 	i915_gem_object_pin_pages(obj);
 	obj->stolen = stolen;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 633bd1f..d19c9db 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -464,7 +464,10 @@
 	}
 
 	/* Hide bit 17 from the user -- see comment in i915_gem_set_tiling */
-	args->phys_swizzle_mode = args->swizzle_mode;
+	if (dev_priv->quirks & QUIRK_PIN_SWIZZLED_PAGES)
+		args->phys_swizzle_mode = I915_BIT_6_SWIZZLE_UNKNOWN;
+	else
+		args->phys_swizzle_mode = args->swizzle_mode;
 	if (args->swizzle_mode == I915_BIT_6_SWIZZLE_9_17)
 		args->swizzle_mode = I915_BIT_6_SWIZZLE_9;
 	if (args->swizzle_mode == I915_BIT_6_SWIZZLE_9_10_17)
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 1f4e5a3..8fd431b 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -545,6 +545,26 @@
 	return ret;
 }
 
+static int
+__i915_gem_userptr_set_pages(struct drm_i915_gem_object *obj,
+			     struct page **pvec, int num_pages)
+{
+	int ret;
+
+	ret = st_set_pages(&obj->pages, pvec, num_pages);
+	if (ret)
+		return ret;
+
+	ret = i915_gem_gtt_prepare_object(obj);
+	if (ret) {
+		sg_free_table(obj->pages);
+		kfree(obj->pages);
+		obj->pages = NULL;
+	}
+
+	return ret;
+}
+
 static void
 __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 {
@@ -584,9 +604,12 @@
 	if (obj->userptr.work != &work->work) {
 		ret = 0;
 	} else if (pinned == num_pages) {
-		ret = st_set_pages(&obj->pages, pvec, num_pages);
+		ret = __i915_gem_userptr_set_pages(obj, pvec, num_pages);
 		if (ret == 0) {
 			list_add_tail(&obj->global_list, &to_i915(dev)->mm.unbound_list);
+			obj->get_page.sg = obj->pages->sgl;
+			obj->get_page.last = 0;
+
 			pinned = 0;
 		}
 	}
@@ -693,7 +716,7 @@
 			}
 		}
 	} else {
-		ret = st_set_pages(&obj->pages, pvec, num_pages);
+		ret = __i915_gem_userptr_set_pages(obj, pvec, num_pages);
 		if (ret == 0) {
 			obj->userptr.work = NULL;
 			pinned = 0;
@@ -715,6 +738,8 @@
 	if (obj->madv != I915_MADV_WILLNEED)
 		obj->dirty = 0;
 
+	i915_gem_gtt_finish_object(obj);
+
 	for_each_sg_page(obj->pages->sgl, &sg_iter, obj->pages->nents, 0) {
 		struct page *page = sg_page_iter_page(&sg_iter);
 
diff --git a/drivers/gpu/drm/i915/i915_ioc32.c b/drivers/gpu/drm/i915/i915_ioc32.c
index 176de63..23aa04c 100644
--- a/drivers/gpu/drm/i915/i915_ioc32.c
+++ b/drivers/gpu/drm/i915/i915_ioc32.c
@@ -204,7 +204,7 @@
 	drm_ioctl_compat_t *fn = NULL;
 	int ret;
 
-	if (nr < DRM_COMMAND_BASE)
+	if (nr < DRM_COMMAND_BASE || nr >= DRM_COMMAND_END)
 		return drm_compat_ioctl(filp, cmd, arg);
 
 	if (nr < DRM_COMMAND_BASE + ARRAY_SIZE(i915_compat_ioctls))
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index e6bb72d..984e2fe 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2706,18 +2706,11 @@
 	spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
 }
 
-static struct drm_i915_gem_request *
-ring_last_request(struct intel_engine_cs *ring)
-{
-	return list_entry(ring->request_list.prev,
-			  struct drm_i915_gem_request, list);
-}
-
 static bool
-ring_idle(struct intel_engine_cs *ring)
+ring_idle(struct intel_engine_cs *ring, u32 seqno)
 {
 	return (list_empty(&ring->request_list) ||
-		i915_gem_request_completed(ring_last_request(ring), false));
+		i915_seqno_passed(seqno, ring->last_submitted_seqno));
 }
 
 static bool
@@ -2939,7 +2932,7 @@
 		acthd = intel_ring_get_active_head(ring);
 
 		if (ring->hangcheck.seqno == seqno) {
-			if (ring_idle(ring)) {
+			if (ring_idle(ring, seqno)) {
 				ring->hangcheck.action = HANGCHECK_IDLE;
 
 				if (waitqueue_active(&ring->irq_queue)) {
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 497cba5..849a259 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -727,7 +727,7 @@
 	TP_fast_assign(
 			__entry->ctx = ctx;
 			__entry->vm = ctx->ppgtt ? &ctx->ppgtt->base : NULL;
-			__entry->dev = ctx->file_priv->dev_priv->dev->primary->index;
+			__entry->dev = ctx->i915->dev->primary->index;
 	),
 
 	TP_printk("dev=%u, ctx=%p, ctx_vm=%p",
diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c
index 7ed8033..8e35e0d 100644
--- a/drivers/gpu/drm/i915/intel_atomic.c
+++ b/drivers/gpu/drm/i915/intel_atomic.c
@@ -129,8 +129,9 @@
 			struct drm_atomic_state *state,
 			bool async)
 {
-	int ret;
-	int i;
+	struct drm_crtc_state *crtc_state;
+	struct drm_crtc *crtc;
+	int ret, i;
 
 	if (async) {
 		DRM_DEBUG_KMS("i915 does not yet support async commit\n");
@@ -142,48 +143,18 @@
 		return ret;
 
 	/* Point of no return */
-
-	/*
-	 * FIXME:  The proper sequence here will eventually be:
-	 *
-	 * drm_atomic_helper_swap_state(dev, state)
-	 * drm_atomic_helper_commit_modeset_disables(dev, state);
-	 * drm_atomic_helper_commit_planes(dev, state);
-	 * drm_atomic_helper_commit_modeset_enables(dev, state);
-	 * drm_atomic_helper_wait_for_vblanks(dev, state);
-	 * drm_atomic_helper_cleanup_planes(dev, state);
-	 * drm_atomic_state_free(state);
-	 *
-	 * once we have full atomic modeset.  For now, just manually update
-	 * plane states to avoid clobbering good states with dummy states
-	 * while nuclear pageflipping.
-	 */
-	for (i = 0; i < dev->mode_config.num_total_plane; i++) {
-		struct drm_plane *plane = state->planes[i];
-
-		if (!plane)
-			continue;
-
-		plane->state->state = state;
-		swap(state->plane_states[i], plane->state);
-		plane->state->state = NULL;
-	}
+	drm_atomic_helper_swap_state(dev, state);
 
 	/* swap crtc_scaler_state */
-	for (i = 0; i < dev->mode_config.num_crtc; i++) {
-		struct drm_crtc *crtc = state->crtcs[i];
-		if (!crtc) {
-			continue;
-		}
-
-		to_intel_crtc(crtc)->config->scaler_state =
-			to_intel_crtc_state(state->crtc_states[i])->scaler_state;
+	for_each_crtc_in_state(state, crtc, crtc_state, i) {
+		to_intel_crtc(crtc)->config = to_intel_crtc_state(crtc->state);
 
 		if (INTEL_INFO(dev)->gen >= 9)
 			skl_detach_scalers(to_intel_crtc(crtc));
+
+		drm_atomic_helper_commit_planes_on_crtc(crtc_state);
 	}
 
-	drm_atomic_helper_commit_planes(dev, state);
 	drm_atomic_helper_wait_for_vblanks(dev, state);
 	drm_atomic_helper_cleanup_planes(dev, state);
 	drm_atomic_state_free(state);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 1b61f98..87476ff 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -4854,6 +4854,9 @@
 	struct intel_plane *intel_plane;
 	int pipe = intel_crtc->pipe;
 
+	if (!intel_crtc->active)
+		return;
+
 	intel_crtc_wait_for_pending_flips(crtc);
 
 	intel_pre_disable_primary(crtc);
@@ -6312,9 +6315,6 @@
 	struct drm_connector *connector;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
-	/* crtc should still be enabled when we disable it. */
-	WARN_ON(!crtc->state->enable);
-
 	intel_crtc_disable_planes(crtc);
 	dev_priv->display.crtc_disable(crtc);
 	dev_priv->display.off(crtc);
@@ -7887,7 +7887,7 @@
 	int pipe = pipe_config->cpu_transcoder;
 	enum dpio_channel port = vlv_pipe_to_channel(pipe);
 	intel_clock_t clock;
-	u32 cmn_dw13, pll_dw0, pll_dw1, pll_dw2;
+	u32 cmn_dw13, pll_dw0, pll_dw1, pll_dw2, pll_dw3;
 	int refclk = 100000;
 
 	mutex_lock(&dev_priv->sb_lock);
@@ -7895,10 +7895,13 @@
 	pll_dw0 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW0(port));
 	pll_dw1 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW1(port));
 	pll_dw2 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW2(port));
+	pll_dw3 = vlv_dpio_read(dev_priv, pipe, CHV_PLL_DW3(port));
 	mutex_unlock(&dev_priv->sb_lock);
 
 	clock.m1 = (pll_dw1 & 0x7) == DPIO_CHV_M1_DIV_BY_2 ? 2 : 0;
-	clock.m2 = ((pll_dw0 & 0xff) << 22) | (pll_dw2 & 0x3fffff);
+	clock.m2 = (pll_dw0 & 0xff) << 22;
+	if (pll_dw3 & DPIO_CHV_FRAC_DIV_EN)
+		clock.m2 |= pll_dw2 & 0x3fffff;
 	clock.n = (pll_dw1 >> DPIO_CHV_N_DIV_SHIFT) & 0xf;
 	clock.p1 = (cmn_dw13 >> DPIO_CHV_P1_DIV_SHIFT) & 0x7;
 	clock.p2 = (cmn_dw13 >> DPIO_CHV_P2_DIV_SHIFT) & 0x1f;
@@ -11823,7 +11826,9 @@
 		goto encoder_retry;
 	}
 
-	pipe_config->dither = pipe_config->pipe_bpp != base_bpp;
+	/* Dithering seems to not pass-through bits correctly when it should, so
+	 * only enable it on 6bpc panels. */
+	pipe_config->dither = pipe_config->pipe_bpp == 6*3;
 	DRM_DEBUG_KMS("plane bpp: %i, pipe bpp: %i, dithering: %i\n",
 		      base_bpp, pipe_config->pipe_bpp, pipe_config->dither);
 
@@ -12585,7 +12590,8 @@
 			continue;
 
 		if (!crtc_state->enable) {
-			intel_crtc_disable(crtc);
+			if (crtc->state->enable)
+				intel_crtc_disable(crtc);
 		} else if (crtc->state->enable) {
 			intel_crtc_disable_planes(crtc);
 			dev_priv->display.crtc_disable(crtc);
@@ -12620,17 +12626,17 @@
 
 	modeset_update_crtc_power_domains(state);
 
-	drm_atomic_helper_commit_planes(dev, state);
-
 	/* Now enable the clocks, plane, pipe, and connectors that we set up. */
 	for_each_crtc_in_state(state, crtc, crtc_state, i) {
-		if (!needs_modeset(crtc->state) || !crtc->state->enable)
+		if (!needs_modeset(crtc->state) || !crtc->state->enable) {
+			drm_atomic_helper_commit_planes_on_crtc(crtc_state);
 			continue;
+		}
 
 		update_scanline_offset(to_intel_crtc(crtc));
 
 		dev_priv->display.crtc_enable(crtc);
-		intel_crtc_enable_planes(crtc);
+		drm_atomic_helper_commit_planes_on_crtc(crtc_state);
 	}
 
 	/* FIXME: add subpixel order */
@@ -12887,20 +12893,11 @@
 	return 0;
 }
 
-static bool primary_plane_visible(struct drm_crtc *crtc)
-{
-	struct intel_plane_state *plane_state =
-		to_intel_plane_state(crtc->primary->state);
-
-	return plane_state->visible;
-}
-
 static int intel_crtc_set_config(struct drm_mode_set *set)
 {
 	struct drm_device *dev;
 	struct drm_atomic_state *state = NULL;
 	struct intel_crtc_state *pipe_config;
-	bool primary_plane_was_visible;
 	int ret;
 
 	BUG_ON(!set);
@@ -12939,38 +12936,8 @@
 
 	intel_update_pipe_size(to_intel_crtc(set->crtc));
 
-	primary_plane_was_visible = primary_plane_visible(set->crtc);
-
 	ret = intel_set_mode_with_config(set->crtc, pipe_config, true);
 
-	if (ret == 0 &&
-	    pipe_config->base.enable &&
-	    pipe_config->base.planes_changed &&
-	    !needs_modeset(&pipe_config->base)) {
-		struct intel_crtc *intel_crtc = to_intel_crtc(set->crtc);
-
-		/*
-		 * We need to make sure the primary plane is re-enabled if it
-		 * has previously been turned off.
-		 */
-		if (ret == 0 && !primary_plane_was_visible &&
-		    primary_plane_visible(set->crtc)) {
-			WARN_ON(!intel_crtc->active);
-			intel_post_enable_primary(set->crtc);
-		}
-
-		/*
-		 * In the fastboot case this may be our only check of the
-		 * state after boot.  It would be better to only do it on
-		 * the first update, but we don't have a nice way of doing that
-		 * (and really, set_config isn't used much for high freq page
-		 * flipping, so increasing its cost here shouldn't be a big
-		 * deal).
-		 */
-		if (i915.fastboot && ret == 0)
-			intel_modeset_check_state(set->crtc->dev);
-	}
-
 	if (ret) {
 		DRM_DEBUG_KMS("failed to set mode on [CRTC:%d], err = %d\n",
 			      set->crtc->base.id, ret);
@@ -13270,7 +13237,7 @@
 	if (ret)
 		return ret;
 
-	if (intel_crtc->active) {
+	if (crtc_state ? crtc_state->base.active : intel_crtc->active) {
 		struct intel_plane_state *old_state =
 			to_intel_plane_state(plane->state);
 
@@ -13301,6 +13268,9 @@
 			 */
 			if (IS_BROADWELL(dev))
 				intel_crtc->atomic.wait_vblank = true;
+
+			if (crtc_state)
+				intel_crtc->atomic.post_enable_primary = true;
 		}
 
 		/*
@@ -13313,6 +13283,10 @@
 		if (!state->visible || !fb)
 			intel_crtc->atomic.disable_ips = true;
 
+		if (!state->visible && old_state->visible &&
+		    crtc_state && !needs_modeset(&crtc_state->base))
+			intel_crtc->atomic.pre_disable_primary = true;
+
 		intel_crtc->atomic.fb_bits |=
 			INTEL_FRONTBUFFER_PRIMARY(intel_crtc->pipe);
 
@@ -15030,6 +15004,7 @@
 		struct intel_plane_state *plane_state;
 
 		memset(crtc->config, 0, sizeof(*crtc->config));
+		crtc->config->base.crtc = &crtc->base;
 
 		crtc->config->quirks |= PIPE_CONFIG_QUIRK_INHERITED_MODE;
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 6e8faa2..1df0e1f 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -93,9 +93,6 @@
 
 static const int skl_rates[] = { 162000, 216000, 270000,
 				  324000, 432000, 540000 };
-static const int chv_rates[] = { 162000, 202500, 210000, 216000,
-				 243000, 270000, 324000, 405000,
-				 420000, 432000, 540000 };
 static const int default_rates[] = { 162000, 270000, 540000 };
 
 /**
@@ -1169,24 +1166,31 @@
 	return (intel_dp_max_link_bw(intel_dp) >> 3) + 1;
 }
 
+static bool intel_dp_source_supports_hbr2(struct drm_device *dev)
+{
+	/* WaDisableHBR2:skl */
+	if (IS_SKYLAKE(dev) && INTEL_REVID(dev) <= SKL_REVID_B0)
+		return false;
+
+	if ((IS_HASWELL(dev) && !IS_HSW_ULX(dev)) || IS_BROADWELL(dev) ||
+	    (INTEL_INFO(dev)->gen >= 9))
+		return true;
+	else
+		return false;
+}
+
 static int
 intel_dp_source_rates(struct drm_device *dev, const int **source_rates)
 {
 	if (IS_SKYLAKE(dev)) {
 		*source_rates = skl_rates;
 		return ARRAY_SIZE(skl_rates);
-	} else if (IS_CHERRYVIEW(dev)) {
-		*source_rates = chv_rates;
-		return ARRAY_SIZE(chv_rates);
 	}
 
 	*source_rates = default_rates;
 
-	if (IS_SKYLAKE(dev) && INTEL_REVID(dev) <= SKL_REVID_B0)
-		/* WaDisableHBR2:skl */
-		return (DP_LINK_BW_2_7 >> 3) + 1;
-	else if (INTEL_INFO(dev)->gen >= 8 ||
-	    (IS_HASWELL(dev) && !IS_HSW_ULX(dev)))
+	/* This depends on the fact that 5.4 is last value in the array */
+	if (intel_dp_source_supports_hbr2(dev))
 		return (DP_LINK_BW_5_4 >> 3) + 1;
 	else
 		return (DP_LINK_BW_2_7 >> 3) + 1;
@@ -3941,10 +3945,15 @@
 		}
 	}
 
-	/* Training Pattern 3 support, both source and sink */
+	/* Training Pattern 3 support, Intel platforms that support HBR2 alone
+	 * have support for TP3 hence that check is used along with dpcd check
+	 * to ensure TP3 can be enabled.
+	 * SKL < B0: due it's WaDisableHBR2 is the only exception where TP3 is
+	 * supported but still not enabled.
+	 */
 	if (intel_dp->dpcd[DP_DPCD_REV] >= 0x12 &&
 	    intel_dp->dpcd[DP_MAX_LANE_COUNT] & DP_TPS3_SUPPORTED &&
-	    (IS_HASWELL(dev_priv) || INTEL_INFO(dev_priv)->gen >= 8)) {
+	    intel_dp_source_supports_hbr2(dev)) {
 		intel_dp->use_tps3 = true;
 		DRM_DEBUG_KMS("Displayport TPS3 supported\n");
 	} else
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 6e4cc53..600afdb 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -357,6 +357,16 @@
 	return MODE_OK;
 }
 
+static struct drm_encoder *intel_mst_atomic_best_encoder(struct drm_connector *connector,
+							 struct drm_connector_state *state)
+{
+	struct intel_connector *intel_connector = to_intel_connector(connector);
+	struct intel_dp *intel_dp = intel_connector->mst_port;
+	struct intel_crtc *crtc = to_intel_crtc(state->crtc);
+
+	return &intel_dp->mst_encoders[crtc->pipe]->base.base;
+}
+
 static struct drm_encoder *intel_mst_best_encoder(struct drm_connector *connector)
 {
 	struct intel_connector *intel_connector = to_intel_connector(connector);
@@ -367,6 +377,7 @@
 static const struct drm_connector_helper_funcs intel_dp_mst_connector_helper_funcs = {
 	.get_modes = intel_dp_mst_get_modes,
 	.mode_valid = intel_dp_mst_mode_valid,
+	.atomic_best_encoder = intel_mst_atomic_best_encoder,
 	.best_encoder = intel_mst_best_encoder,
 };
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 9b74ffa..7f2161a 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1012,6 +1012,8 @@
 		ret = intel_pin_and_map_ringbuffer_obj(ring->dev, ringbuf);
 		if (ret)
 			goto unpin_ctx_obj;
+
+		ctx_obj->dirty = true;
 	}
 
 	return ret;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index e539314..4be66f6 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -275,6 +275,13 @@
 	 * Do we have some not yet emitted requests outstanding?
 	 */
 	struct drm_i915_gem_request *outstanding_lazy_request;
+	/**
+	 * Seqno of request most recently submitted to request_list.
+	 * Used exclusively by hang checker to avoid grabbing lock while
+	 * inspecting request list.
+	 */
+	u32 last_submitted_seqno;
+
 	bool gpu_caches_dirty;
 
 	wait_queue_head_t irq_queue;
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index a6d8a3e..260389a 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1274,10 +1274,12 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_reg_read *reg = data;
 	struct register_whitelist const *entry = whitelist;
+	unsigned size;
+	u64 offset;
 	int i, ret = 0;
 
 	for (i = 0; i < ARRAY_SIZE(whitelist); i++, entry++) {
-		if (entry->offset == reg->offset &&
+		if (entry->offset == (reg->offset & -entry->size) &&
 		    (1 << INTEL_INFO(dev)->gen & entry->gen_bitmask))
 			break;
 	}
@@ -1285,23 +1287,33 @@
 	if (i == ARRAY_SIZE(whitelist))
 		return -EINVAL;
 
+	/* We use the low bits to encode extra flags as the register should
+	 * be naturally aligned (and those that are not so aligned merely
+	 * limit the available flags for that register).
+	 */
+	offset = entry->offset;
+	size = entry->size;
+	size |= reg->offset ^ offset;
+
 	intel_runtime_pm_get(dev_priv);
 
-	switch (entry->size) {
+	switch (size) {
+	case 8 | 1:
+		reg->val = I915_READ64_2x32(offset, offset+4);
+		break;
 	case 8:
-		reg->val = I915_READ64(reg->offset);
+		reg->val = I915_READ64(offset);
 		break;
 	case 4:
-		reg->val = I915_READ(reg->offset);
+		reg->val = I915_READ(offset);
 		break;
 	case 2:
-		reg->val = I915_READ16(reg->offset);
+		reg->val = I915_READ16(offset);
 		break;
 	case 1:
-		reg->val = I915_READ8(reg->offset);
+		reg->val = I915_READ8(offset);
 		break;
 	default:
-		MISSING_CASE(entry->size);
 		ret = -EINVAL;
 		goto out;
 	}
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index 214ecee..e671ad3 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -301,7 +301,7 @@
 
 	switch (tve->mode) {
 	case TVE_MODE_VGA:
-		imx_drm_set_bus_format_pins(encoder, MEDIA_BUS_FMT_YUV8_1X24,
+		imx_drm_set_bus_format_pins(encoder, MEDIA_BUS_FMT_GBR888_1X24,
 					    tve->hsync_pin, tve->vsync_pin);
 		break;
 	case TVE_MODE_TVOUT:
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index 74a9ce4..b4deb9c 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -21,6 +21,7 @@
 #include <drm/drm_panel.h>
 #include <linux/videodev2.h>
 #include <video/of_display_timing.h>
+#include <linux/of_graph.h>
 
 #include "imx-drm.h"
 
@@ -208,7 +209,7 @@
 {
 	struct drm_device *drm = data;
 	struct device_node *np = dev->of_node;
-	struct device_node *panel_node;
+	struct device_node *port;
 	const u8 *edidp;
 	struct imx_parallel_display *imxpd;
 	int ret;
@@ -234,11 +235,19 @@
 			imxpd->bus_format = MEDIA_BUS_FMT_RGB666_1X24_CPADHI;
 	}
 
-	panel_node = of_parse_phandle(np, "fsl,panel", 0);
-	if (panel_node) {
-		imxpd->panel = of_drm_find_panel(panel_node);
-		if (!imxpd->panel)
-			return -EPROBE_DEFER;
+	/* port@1 is the output port */
+	port = of_graph_get_port_by_id(np, 1);
+	if (port) {
+		struct device_node *endpoint, *remote;
+
+		endpoint = of_get_child_by_name(port, "endpoint");
+		if (endpoint) {
+			remote = of_graph_get_remote_port_parent(endpoint);
+			if (remote)
+				imxpd->panel = of_drm_find_panel(remote);
+			if (!imxpd->panel)
+				return -EPROBE_DEFER;
+		}
 	}
 
 	imxpd->dev = dev;
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
index 0d1dbb7..247a424 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
@@ -220,13 +220,15 @@
 	uint32_t op_mode = 0;
 	uint32_t phasex_step = MDP4_VG_PHASE_STEP_DEFAULT;
 	uint32_t phasey_step = MDP4_VG_PHASE_STEP_DEFAULT;
-	enum mdp4_frame_format frame_type = mdp4_get_frame_format(fb);
+	enum mdp4_frame_format frame_type;
 
 	if (!(crtc && fb)) {
 		DBG("%s: disabled!", mdp4_plane->name);
 		return 0;
 	}
 
+	frame_type = mdp4_get_frame_format(fb);
+
 	/* src values are in Q16 fixed point, convert to integer: */
 	src_x = src_x >> 16;
 	src_y = src_y >> 16;
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
index 206f758..e253db5 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
@@ -76,7 +76,20 @@
 
 static void mdp5_complete_commit(struct msm_kms *kms, struct drm_atomic_state *state)
 {
+	int i;
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
+	int nplanes = mdp5_kms->dev->mode_config.num_total_plane;
+
+	for (i = 0; i < nplanes; i++) {
+		struct drm_plane *plane = state->planes[i];
+		struct drm_plane_state *plane_state = state->plane_states[i];
+
+		if (!plane)
+			continue;
+
+		mdp5_plane_complete_commit(plane, plane_state);
+	}
+
 	mdp5_disable(mdp5_kms);
 }
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
index e0eb245..e79ac09 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
@@ -227,6 +227,8 @@
 		struct drm_mode_object *obj);
 uint32_t mdp5_plane_get_flush(struct drm_plane *plane);
 void mdp5_plane_complete_flip(struct drm_plane *plane);
+void mdp5_plane_complete_commit(struct drm_plane *plane,
+	struct drm_plane_state *state);
 enum mdp5_pipe mdp5_plane_pipe(struct drm_plane *plane);
 struct drm_plane *mdp5_plane_init(struct drm_device *dev,
 		enum mdp5_pipe pipe, bool private_plane, uint32_t reg_offset);
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
index 57b8f56..2227556 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
@@ -31,8 +31,6 @@
 
 	uint32_t nformats;
 	uint32_t formats[32];
-
-	bool enabled;
 };
 #define to_mdp5_plane(x) container_of(x, struct mdp5_plane, base)
 
@@ -56,22 +54,6 @@
 	return state->fb && state->crtc;
 }
 
-static int mdp5_plane_disable(struct drm_plane *plane)
-{
-	struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane);
-	struct mdp5_kms *mdp5_kms = get_kms(plane);
-	enum mdp5_pipe pipe = mdp5_plane->pipe;
-
-	DBG("%s: disable", mdp5_plane->name);
-
-	if (mdp5_kms) {
-		/* Release the memory we requested earlier from the SMP: */
-		mdp5_smp_release(mdp5_kms->smp, pipe);
-	}
-
-	return 0;
-}
-
 static void mdp5_plane_destroy(struct drm_plane *plane)
 {
 	struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane);
@@ -224,7 +206,6 @@
 
 	if (!plane_enabled(state)) {
 		to_mdp5_plane_state(state)->pending = true;
-		mdp5_plane_disable(plane);
 	} else if (to_mdp5_plane_state(state)->mode_changed) {
 		int ret;
 		to_mdp5_plane_state(state)->pending = true;
@@ -602,6 +583,20 @@
 	return mdp5_plane->flush_mask;
 }
 
+/* called after vsync in thread context */
+void mdp5_plane_complete_commit(struct drm_plane *plane,
+	struct drm_plane_state *state)
+{
+	struct mdp5_kms *mdp5_kms = get_kms(plane);
+	struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane);
+	enum mdp5_pipe pipe = mdp5_plane->pipe;
+
+	if (!plane_enabled(plane->state)) {
+		DBG("%s: free SMP", mdp5_plane->name);
+		mdp5_smp_release(mdp5_kms->smp, pipe);
+	}
+}
+
 /* initialize plane */
 struct drm_plane *mdp5_plane_init(struct drm_device *dev,
 		enum mdp5_pipe pipe, bool private_plane, uint32_t reg_offset)
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c
index 16702ae..64a27d8 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c
@@ -34,22 +34,44 @@
  * and CANNOT be re-allocated (eg: MMB0 and MMB1 both tied to RGB0).
  *
  * For each block that can be dynamically allocated, it can be either
- * free, or pending/in-use by a client. The updates happen in three steps:
+ *     free:
+ *     The block is free.
+ *
+ *     pending:
+ *     The block is allocated to some client and not free.
+ *
+ *     configured:
+ *     The block is allocated to some client, and assigned to that
+ *     client in MDP5_MDP_SMP_ALLOC registers.
+ *
+ *     inuse:
+ *     The block is being actively used by a client.
+ *
+ * The updates happen in the following steps:
  *
  *  1) mdp5_smp_request():
  *     When plane scanout is setup, calculate required number of
- *     blocks needed per client, and request.  Blocks not inuse or
- *     pending by any other client are added to client's pending
- *     set.
+ *     blocks needed per client, and request. Blocks neither inuse nor
+ *     configured nor pending by any other client are added to client's
+ *     pending set.
+ *     For shrinking, blocks in pending but not in configured can be freed
+ *     directly, but those already in configured will be freed later by
+ *     mdp5_smp_commit.
  *
  *  2) mdp5_smp_configure():
  *     As hw is programmed, before FLUSH, MDP5_MDP_SMP_ALLOC registers
  *     are configured for the union(pending, inuse)
+ *     Current pending is copied to configured.
+ *     It is assumed that mdp5_smp_request and mdp5_smp_configure not run
+ *     concurrently for the same pipe.
  *
  *  3) mdp5_smp_commit():
- *     After next vblank, copy pending -> inuse.  Optionally update
+ *     After next vblank, copy configured -> inuse.  Optionally update
  *     MDP5_SMP_ALLOC registers if there are newly unused blocks
  *
+ *  4) mdp5_smp_release():
+ *     Must be called after the pipe is disabled and no longer uses any SMB
+ *
  * On the next vblank after changes have been committed to hw, the
  * client's pending blocks become it's in-use blocks (and no-longer
  * in-use blocks become available to other clients).
@@ -77,6 +99,9 @@
 	struct mdp5_client_smp_state client_state[MAX_CLIENTS];
 };
 
+static void update_smp_state(struct mdp5_smp *smp,
+		u32 cid, mdp5_smp_state_t *assigned);
+
 static inline
 struct mdp5_kms *get_kms(struct mdp5_smp *smp)
 {
@@ -149,7 +174,12 @@
 		for (i = cur_nblks; i > nblks; i--) {
 			int blk = find_first_bit(ps->pending, cnt);
 			clear_bit(blk, ps->pending);
-			/* don't clear in global smp_state until _commit() */
+
+			/* clear in global smp_state if not in configured
+			 * otherwise until _commit()
+			 */
+			if (!test_bit(blk, ps->configured))
+				clear_bit(blk, smp->state);
 		}
 	}
 
@@ -223,10 +253,33 @@
 /* Release SMP blocks for all clients of the pipe */
 void mdp5_smp_release(struct mdp5_smp *smp, enum mdp5_pipe pipe)
 {
-	int i, nblks;
+	int i;
+	unsigned long flags;
+	int cnt = smp->blk_cnt;
 
-	for (i = 0, nblks = 0; i < pipe2nclients(pipe); i++)
-		smp_request_block(smp, pipe2client(pipe, i), 0);
+	for (i = 0; i < pipe2nclients(pipe); i++) {
+		mdp5_smp_state_t assigned;
+		u32 cid = pipe2client(pipe, i);
+		struct mdp5_client_smp_state *ps = &smp->client_state[cid];
+
+		spin_lock_irqsave(&smp->state_lock, flags);
+
+		/* clear hw assignment */
+		bitmap_or(assigned, ps->inuse, ps->configured, cnt);
+		update_smp_state(smp, CID_UNUSED, &assigned);
+
+		/* free to global pool */
+		bitmap_andnot(smp->state, smp->state, ps->pending, cnt);
+		bitmap_andnot(smp->state, smp->state, assigned, cnt);
+
+		/* clear client's infor */
+		bitmap_zero(ps->pending, cnt);
+		bitmap_zero(ps->configured, cnt);
+		bitmap_zero(ps->inuse, cnt);
+
+		spin_unlock_irqrestore(&smp->state_lock, flags);
+	}
+
 	set_fifo_thresholds(smp, pipe, 0);
 }
 
@@ -274,12 +327,20 @@
 		u32 cid = pipe2client(pipe, i);
 		struct mdp5_client_smp_state *ps = &smp->client_state[cid];
 
-		bitmap_or(assigned, ps->inuse, ps->pending, cnt);
+		/*
+		 * if vblank has not happened since last smp_configure
+		 * skip the configure for now
+		 */
+		if (!bitmap_equal(ps->inuse, ps->configured, cnt))
+			continue;
+
+		bitmap_copy(ps->configured, ps->pending, cnt);
+		bitmap_or(assigned, ps->inuse, ps->configured, cnt);
 		update_smp_state(smp, cid, &assigned);
 	}
 }
 
-/* step #3: after vblank, copy pending -> inuse: */
+/* step #3: after vblank, copy configured -> inuse: */
 void mdp5_smp_commit(struct mdp5_smp *smp, enum mdp5_pipe pipe)
 {
 	int cnt = smp->blk_cnt;
@@ -295,7 +356,7 @@
 		 * using, which can be released and made available to other
 		 * clients:
 		 */
-		if (bitmap_andnot(released, ps->inuse, ps->pending, cnt)) {
+		if (bitmap_andnot(released, ps->inuse, ps->configured, cnt)) {
 			unsigned long flags;
 
 			spin_lock_irqsave(&smp->state_lock, flags);
@@ -306,7 +367,7 @@
 			update_smp_state(smp, CID_UNUSED, &released);
 		}
 
-		bitmap_copy(ps->inuse, ps->pending, cnt);
+		bitmap_copy(ps->inuse, ps->configured, cnt);
 	}
 }
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h
index e47179f..5b6c236 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h
@@ -23,6 +23,7 @@
 
 struct mdp5_client_smp_state {
 	mdp5_smp_state_t inuse;
+	mdp5_smp_state_t configured;
 	mdp5_smp_state_t pending;
 };
 
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index 1b22d8b..1ceb4f2 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -283,12 +283,8 @@
 
 	timeout = ktime_add_ms(ktime_get(), 1000);
 
-	ret = msm_wait_fence_interruptable(dev, c->fence, &timeout);
-	if (ret) {
-		WARN_ON(ret);  // TODO unswap state back?  or??
-		commit_destroy(c);
-		return ret;
-	}
+	/* uninterruptible wait */
+	msm_wait_fence(dev, c->fence, &timeout, false);
 
 	complete_commit(c);
 
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index b7ef56e..d3467b1 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -637,8 +637,8 @@
  * Fences:
  */
 
-int msm_wait_fence_interruptable(struct drm_device *dev, uint32_t fence,
-		ktime_t *timeout)
+int msm_wait_fence(struct drm_device *dev, uint32_t fence,
+		ktime_t *timeout , bool interruptible)
 {
 	struct msm_drm_private *priv = dev->dev_private;
 	int ret;
@@ -667,7 +667,12 @@
 			remaining_jiffies = timespec_to_jiffies(&ts);
 		}
 
-		ret = wait_event_interruptible_timeout(priv->fence_event,
+		if (interruptible)
+			ret = wait_event_interruptible_timeout(priv->fence_event,
+				fence_completed(dev, fence),
+				remaining_jiffies);
+		else
+			ret = wait_event_timeout(priv->fence_event,
 				fence_completed(dev, fence),
 				remaining_jiffies);
 
@@ -853,7 +858,7 @@
 		return -EINVAL;
 	}
 
-	return msm_wait_fence_interruptable(dev, args->fence, &timeout);
+	return msm_wait_fence(dev, args->fence, &timeout, true);
 }
 
 static const struct drm_ioctl_desc msm_ioctls[] = {
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index e7c5ea1..4ff0ec9 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -164,8 +164,8 @@
 
 int msm_register_mmu(struct drm_device *dev, struct msm_mmu *mmu);
 
-int msm_wait_fence_interruptable(struct drm_device *dev, uint32_t fence,
-		ktime_t *timeout);
+int msm_wait_fence(struct drm_device *dev, uint32_t fence,
+		ktime_t *timeout, bool interruptible);
 int msm_queue_fence_cb(struct drm_device *dev,
 		struct msm_fence_cb *cb, uint32_t fence);
 void msm_update_fence(struct drm_device *dev, uint32_t fence);
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index f211b80..c76cc85 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -460,7 +460,7 @@
 		if (op & MSM_PREP_NOSYNC)
 			timeout = NULL;
 
-		ret = msm_wait_fence_interruptable(dev, fence, timeout);
+		ret = msm_wait_fence(dev, fence, timeout, true);
 	}
 
 	/* TODO cache maintenance */
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index dd7a7ab..831461b 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -23,8 +23,12 @@
 struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
-	BUG_ON(!msm_obj->sgt);  /* should have already pinned! */
-	return msm_obj->sgt;
+	int npages = obj->size >> PAGE_SHIFT;
+
+	if (WARN_ON(!msm_obj->pages))  /* should have already pinned! */
+		return NULL;
+
+	return drm_prime_pages_to_sg(msm_obj->pages, npages);
 }
 
 void *msm_gem_prime_vmap(struct drm_gem_object *obj)
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 649024d..477cbb1 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -128,6 +128,7 @@
 	nvkm_vm_ref(NULL, &nvxx_client(&cli->base)->vm, NULL);
 	nvif_client_fini(&cli->base);
 	usif_client_fini(cli);
+	kfree(cli);
 }
 
 static void
@@ -865,8 +866,10 @@
 
 	pm_runtime_get_sync(dev->dev);
 
+	mutex_lock(&cli->mutex);
 	if (cli->abi16)
 		nouveau_abi16_fini(cli->abi16);
+	mutex_unlock(&cli->mutex);
 
 	mutex_lock(&drm->client.mutex);
 	list_del(&cli->head);
diff --git a/drivers/gpu/drm/nouveau/nouveau_platform.c b/drivers/gpu/drm/nouveau/nouveau_platform.c
index 775277f..dcfbbfa 100644
--- a/drivers/gpu/drm/nouveau/nouveau_platform.c
+++ b/drivers/gpu/drm/nouveau/nouveau_platform.c
@@ -92,6 +92,8 @@
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_IOMMU_API)
+
 static void nouveau_platform_probe_iommu(struct device *dev,
 					 struct nouveau_platform_gpu *gpu)
 {
@@ -158,6 +160,20 @@
 	}
 }
 
+#else
+
+static void nouveau_platform_probe_iommu(struct device *dev,
+					 struct nouveau_platform_gpu *gpu)
+{
+}
+
+static void nouveau_platform_remove_iommu(struct device *dev,
+					  struct nouveau_platform_gpu *gpu)
+{
+}
+
+#endif
+
 static int nouveau_platform_probe(struct platform_device *pdev)
 {
 	struct nouveau_platform_gpu *gpu;
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 18f4497..7464aef3 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -175,15 +175,24 @@
 	node->page_shift = 12;
 
 	switch (drm->device.info.family) {
+	case NV_DEVICE_INFO_V0_TNT:
+	case NV_DEVICE_INFO_V0_CELSIUS:
+	case NV_DEVICE_INFO_V0_KELVIN:
+	case NV_DEVICE_INFO_V0_RANKINE:
+	case NV_DEVICE_INFO_V0_CURIE:
+		break;
 	case NV_DEVICE_INFO_V0_TESLA:
 		if (drm->device.info.chipset != 0x50)
 			node->memtype = (nvbo->tile_flags & 0x7f00) >> 8;
 		break;
 	case NV_DEVICE_INFO_V0_FERMI:
 	case NV_DEVICE_INFO_V0_KEPLER:
+	case NV_DEVICE_INFO_V0_MAXWELL:
 		node->memtype = (nvbo->tile_flags & 0xff00) >> 8;
 		break;
 	default:
+		NV_WARN(drm, "%s: unhandled family type %x\n", __func__,
+			drm->device.info.family);
 		break;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nv04_fbcon.c b/drivers/gpu/drm/nouveau/nv04_fbcon.c
index 4ef602c..495c576 100644
--- a/drivers/gpu/drm/nouveau/nv04_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nv04_fbcon.c
@@ -203,7 +203,7 @@
 	if (ret)
 		return ret;
 
-	if (RING_SPACE(chan, 49)) {
+	if (RING_SPACE(chan, 49 + (device->info.chipset >= 0x11 ? 4 : 0))) {
 		nouveau_fbcon_gpu_lockup(info);
 		return 0;
 	}
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 7da7958..981342d 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -979,7 +979,7 @@
 {
 	struct nv50_mast *mast = nv50_mast(nv_crtc->base.dev);
 
-	if (show && nv_crtc->cursor.nvbo)
+	if (show && nv_crtc->cursor.nvbo && nv_crtc->base.enabled)
 		nv50_crtc_cursor_show(nv_crtc);
 	else
 		nv50_crtc_cursor_hide(nv_crtc);
diff --git a/drivers/gpu/drm/nouveau/nv50_fbcon.c b/drivers/gpu/drm/nouveau/nv50_fbcon.c
index 394c89a..901130b 100644
--- a/drivers/gpu/drm/nouveau/nv50_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nv50_fbcon.c
@@ -188,7 +188,7 @@
 	if (ret)
 		return ret;
 
-	ret = RING_SPACE(chan, 59);
+	ret = RING_SPACE(chan, 58);
 	if (ret) {
 		nouveau_fbcon_gpu_lockup(info);
 		return ret;
@@ -252,6 +252,7 @@
 	OUT_RING(chan, info->var.yres_virtual);
 	OUT_RING(chan, upper_32_bits(fb->vma.offset));
 	OUT_RING(chan, lower_32_bits(fb->vma.offset));
+	FIRE_RING(chan);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nvc0_fbcon.c b/drivers/gpu/drm/nouveau/nvc0_fbcon.c
index 6124667..fcd2e5f 100644
--- a/drivers/gpu/drm/nouveau/nvc0_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nvc0_fbcon.c
@@ -188,7 +188,7 @@
 		return -EINVAL;
 	}
 
-	ret = RING_SPACE(chan, 60);
+	ret = RING_SPACE(chan, 58);
 	if (ret) {
 		WARN_ON(1);
 		nouveau_fbcon_gpu_lockup(info);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c
index 9ef6728..7f2f05f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c
@@ -809,7 +809,7 @@
 		case 0x00000900: type = DCB_OUTPUT_DP; mask = 2; break;
 		default:
 			nv_error(priv, "unknown SOR mc 0x%08x\n", ctrl);
-			return 0x0000;
+			return NULL;
 		}
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index 5606c25..ca11ddb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -663,6 +663,37 @@
 		gf100_gr_zbc_clear_depth(priv, index);
 }
 
+/**
+ * Wait until GR goes idle. GR is considered idle if it is disabled by the
+ * MC (0x200) register, or GR is not busy and a context switch is not in
+ * progress.
+ */
+int
+gf100_gr_wait_idle(struct gf100_gr_priv *priv)
+{
+	unsigned long end_jiffies = jiffies + msecs_to_jiffies(2000);
+	bool gr_enabled, ctxsw_active, gr_busy;
+
+	do {
+		/*
+		 * required to make sure FIFO_ENGINE_STATUS (0x2640) is
+		 * up-to-date
+		 */
+		nv_rd32(priv, 0x400700);
+
+		gr_enabled = nv_rd32(priv, 0x200) & 0x1000;
+		ctxsw_active = nv_rd32(priv, 0x2640) & 0x8000;
+		gr_busy = nv_rd32(priv, 0x40060c) & 0x1;
+
+		if (!gr_enabled || (!gr_busy && !ctxsw_active))
+			return 0;
+	} while (time_before(jiffies, end_jiffies));
+
+	nv_error(priv, "wait for idle timeout (en: %d, ctxsw: %d, busy: %d)\n",
+		 gr_enabled, ctxsw_active, gr_busy);
+	return -EAGAIN;
+}
+
 void
 gf100_gr_mmio(struct gf100_gr_priv *priv, const struct gf100_gr_pack *p)
 {
@@ -699,7 +730,13 @@
 
 		while (addr < next) {
 			nv_wr32(priv, 0x400200, addr);
-			nv_wait(priv, 0x400700, 0x00000002, 0x00000000);
+			/**
+			 * Wait for GR to go idle after submitting a
+			 * GO_IDLE bundle
+			 */
+			if ((addr & 0xffff) == 0xe100)
+				gf100_gr_wait_idle(priv);
+			nv_wait(priv, 0x400700, 0x00000004, 0x00000000);
 			addr += init->pitch;
 		}
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
index 8af1a89..c9533fd 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
@@ -181,6 +181,7 @@
 	int ppc_nr;
 };
 
+int  gf100_gr_wait_idle(struct gf100_gr_priv *);
 void gf100_gr_mmio(struct gf100_gr_priv *, const struct gf100_gr_pack *);
 void gf100_gr_icmd(struct gf100_gr_priv *, const struct gf100_gr_pack *);
 void gf100_gr_mthd(struct gf100_gr_priv *, const struct gf100_gr_pack *);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c
index 2006c44..4cf36a3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c
@@ -332,9 +332,12 @@
 nvkm_perfctx_dtor(struct nvkm_object *object)
 {
 	struct nvkm_pm *ppm = (void *)object->engine;
+	struct nvkm_perfctx *ctx = (void *)object;
+
 	mutex_lock(&nv_subdev(ppm)->mutex);
-	nvkm_engctx_destroy(&ppm->context->base);
-	ppm->context = NULL;
+	nvkm_engctx_destroy(&ctx->base);
+	if (ppm->context == ctx)
+		ppm->context = NULL;
 	mutex_unlock(&nv_subdev(ppm)->mutex);
 }
 
@@ -355,12 +358,11 @@
 	mutex_lock(&nv_subdev(ppm)->mutex);
 	if (ppm->context == NULL)
 		ppm->context = ctx;
+	if (ctx != ppm->context)
+		ret = -EBUSY;
 	mutex_unlock(&nv_subdev(ppm)->mutex);
 
-	if (ctx != ppm->context)
-		return -EBUSY;
-
-	return 0;
+	return ret;
 }
 
 struct nvkm_oclass
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c
index f67cdae..f4611e3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c
@@ -1285,6 +1285,44 @@
 }
 
 /**
+ * INIT_PLL_INDIRECT - opcode 0x59
+ *
+ */
+static void
+init_pll_indirect(struct nvbios_init *init)
+{
+	struct nvkm_bios *bios = init->bios;
+	u32  reg = nv_ro32(bios, init->offset + 1);
+	u16 addr = nv_ro16(bios, init->offset + 5);
+	u32 freq = (u32)nv_ro16(bios, addr) * 1000;
+
+	trace("PLL_INDIRECT\tR[0x%06x] =PLL= VBIOS[%04x] = %dkHz\n",
+	      reg, addr, freq);
+	init->offset += 7;
+
+	init_prog_pll(init, reg, freq);
+}
+
+/**
+ * INIT_ZM_REG_INDIRECT - opcode 0x5a
+ *
+ */
+static void
+init_zm_reg_indirect(struct nvbios_init *init)
+{
+	struct nvkm_bios *bios = init->bios;
+	u32  reg = nv_ro32(bios, init->offset + 1);
+	u16 addr = nv_ro16(bios, init->offset + 5);
+	u32 data = nv_ro32(bios, addr);
+
+	trace("ZM_REG_INDIRECT\tR[0x%06x] = VBIOS[0x%04x] = 0x%08x\n",
+	      reg, addr, data);
+	init->offset += 7;
+
+	init_wr32(init, addr, data);
+}
+
+/**
  * INIT_SUB_DIRECT - opcode 0x5b
  *
  */
@@ -2145,6 +2183,8 @@
 	[0x56] = { init_condition_time },
 	[0x57] = { init_ltime },
 	[0x58] = { init_zm_reg_sequence },
+	[0x59] = { init_pll_indirect },
+	[0x5a] = { init_zm_reg_indirect },
 	[0x5b] = { init_sub_direct },
 	[0x5c] = { init_jump },
 	[0x5e] = { init_i2c_if },
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c
index 822d32a2..065e9f5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c
@@ -180,7 +180,8 @@
 	       struct gt215_clk_info *info)
 {
 	struct gt215_clk_priv *priv = (void *)clock;
-	u32 oclk, sclk, sdiv, diff;
+	u32 oclk, sclk, sdiv;
+	s32 diff;
 
 	info->clk = 0;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c
index c0fdb89..24dcdfb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c
@@ -38,6 +38,14 @@
 	nv_wr32(priv, 0x12004c, 0x4);
 	nv_wr32(priv, 0x122204, 0x2);
 	nv_rd32(priv, 0x122204);
+
+	/*
+	 * Bug: increase clock timeout to avoid operation failure at high
+	 * gpcclk rate.
+	 */
+	nv_wr32(priv, 0x122354, 0x800);
+	nv_wr32(priv, 0x128328, 0x800);
+	nv_wr32(priv, 0x124320, 0x800);
 }
 
 static void
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c
index 80614f1..282143f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c
@@ -50,7 +50,12 @@
 {
 	struct nv04_instmem_priv *priv = (void *)nvkm_instmem(object);
 	struct nv04_instobj_priv *node = (void *)object;
+	struct nvkm_subdev *subdev = (void *)priv;
+
+	mutex_lock(&subdev->mutex);
 	nvkm_mm_free(&priv->heap, &node->mem);
+	mutex_unlock(&subdev->mutex);
+
 	nvkm_instobj_destroy(&node->base);
 }
 
@@ -62,6 +67,7 @@
 	struct nv04_instmem_priv *priv = (void *)nvkm_instmem(parent);
 	struct nv04_instobj_priv *node;
 	struct nvkm_instobj_args *args = data;
+	struct nvkm_subdev *subdev = (void *)priv;
 	int ret;
 
 	if (!args->align)
@@ -72,8 +78,10 @@
 	if (ret)
 		return ret;
 
+	mutex_lock(&subdev->mutex);
 	ret = nvkm_mm_head(&priv->heap, 0, 1, args->size, args->size,
 			   args->align, &node->mem);
+	mutex_unlock(&subdev->mutex);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
index f2daad8..7841970 100644
--- a/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
+++ b/drivers/gpu/drm/omapdrm/omap_dmm_tiler.c
@@ -285,7 +285,7 @@
 
 	if (wait) {
 		if (!wait_for_completion_timeout(&engine->compl,
-				msecs_to_jiffies(1))) {
+				msecs_to_jiffies(100))) {
 			dev_err(dmm->dev, "timed out waiting for done\n");
 			ret = -ETIMEDOUT;
 		}
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.h b/drivers/gpu/drm/omapdrm/omap_drv.h
index ae2df41..12081e6 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.h
+++ b/drivers/gpu/drm/omapdrm/omap_drv.h
@@ -177,7 +177,7 @@
 		struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos);
 struct drm_gem_object *omap_framebuffer_bo(struct drm_framebuffer *fb, int p);
 int omap_framebuffer_pin(struct drm_framebuffer *fb);
-int omap_framebuffer_unpin(struct drm_framebuffer *fb);
+void omap_framebuffer_unpin(struct drm_framebuffer *fb);
 void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
 		struct omap_drm_window *win, struct omap_overlay_info *info);
 struct drm_connector *omap_framebuffer_get_next_connector(
@@ -211,7 +211,7 @@
 		enum dma_data_direction dir);
 int omap_gem_get_paddr(struct drm_gem_object *obj,
 		dma_addr_t *paddr, bool remap);
-int omap_gem_put_paddr(struct drm_gem_object *obj);
+void omap_gem_put_paddr(struct drm_gem_object *obj);
 int omap_gem_get_pages(struct drm_gem_object *obj, struct page ***pages,
 		bool remap);
 int omap_gem_put_pages(struct drm_gem_object *obj);
@@ -236,7 +236,7 @@
 	/* PVR needs alignment to 8 pixels.. right now that is the most
 	 * restrictive stride requirement..
 	 */
-	return ALIGN(pitch, 8 * bytespp);
+	return roundup(pitch, 8 * bytespp);
 }
 
 /* map crtc to vblank mask */
diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c
index 0b967e7..51b1219 100644
--- a/drivers/gpu/drm/omapdrm/omap_fb.c
+++ b/drivers/gpu/drm/omapdrm/omap_fb.c
@@ -287,10 +287,10 @@
 }
 
 /* unpin, no longer being scanned out: */
-int omap_framebuffer_unpin(struct drm_framebuffer *fb)
+void omap_framebuffer_unpin(struct drm_framebuffer *fb)
 {
 	struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb);
-	int ret, i, n = drm_format_num_planes(fb->pixel_format);
+	int i, n = drm_format_num_planes(fb->pixel_format);
 
 	mutex_lock(&omap_fb->lock);
 
@@ -298,24 +298,16 @@
 
 	if (omap_fb->pin_count > 0) {
 		mutex_unlock(&omap_fb->lock);
-		return 0;
+		return;
 	}
 
 	for (i = 0; i < n; i++) {
 		struct plane *plane = &omap_fb->planes[i];
-		ret = omap_gem_put_paddr(plane->bo);
-		if (ret)
-			goto fail;
+		omap_gem_put_paddr(plane->bo);
 		plane->paddr = 0;
 	}
 
 	mutex_unlock(&omap_fb->lock);
-
-	return 0;
-
-fail:
-	mutex_unlock(&omap_fb->lock);
-	return ret;
 }
 
 struct drm_gem_object *omap_framebuffer_bo(struct drm_framebuffer *fb, int p)
diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c
index 23b5a84..720d16b 100644
--- a/drivers/gpu/drm/omapdrm/omap_fbdev.c
+++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c
@@ -135,7 +135,7 @@
 	fbdev->ywrap_enabled = priv->has_dmm && ywrap_enabled;
 	if (fbdev->ywrap_enabled) {
 		/* need to align pitch to page size if using DMM scrolling */
-		mode_cmd.pitches[0] = ALIGN(mode_cmd.pitches[0], PAGE_SIZE);
+		mode_cmd.pitches[0] = PAGE_ALIGN(mode_cmd.pitches[0]);
 	}
 
 	/* allocate backing bo */
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 2ab7780..7ed08fdc 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -808,10 +808,10 @@
 /* Release physical address, when DMA is no longer being performed.. this
  * could potentially unpin and unmap buffers from TILER
  */
-int omap_gem_put_paddr(struct drm_gem_object *obj)
+void omap_gem_put_paddr(struct drm_gem_object *obj)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&obj->dev->struct_mutex);
 	if (omap_obj->paddr_cnt > 0) {
@@ -821,7 +821,6 @@
 			if (ret) {
 				dev_err(obj->dev->dev,
 					"could not unpin pages: %d\n", ret);
-				goto fail;
 			}
 			ret = tiler_release(omap_obj->block);
 			if (ret) {
@@ -832,9 +831,8 @@
 			omap_obj->block = NULL;
 		}
 	}
-fail:
+
 	mutex_unlock(&obj->dev->struct_mutex);
-	return ret;
 }
 
 /* Get rotated scanout address (only valid if already pinned), at the
@@ -1378,11 +1376,7 @@
 
 	omap_obj = kzalloc(sizeof(*omap_obj), GFP_KERNEL);
 	if (!omap_obj)
-		goto fail;
-
-	spin_lock(&priv->list_lock);
-	list_add(&omap_obj->mm_list, &priv->obj_list);
-	spin_unlock(&priv->list_lock);
+		return NULL;
 
 	obj = &omap_obj->base;
 
@@ -1392,11 +1386,19 @@
 		 */
 		omap_obj->vaddr =  dma_alloc_writecombine(dev->dev, size,
 				&omap_obj->paddr, GFP_KERNEL);
-		if (omap_obj->vaddr)
-			flags |= OMAP_BO_DMA;
+		if (!omap_obj->vaddr) {
+			kfree(omap_obj);
 
+			return NULL;
+		}
+
+		flags |= OMAP_BO_DMA;
 	}
 
+	spin_lock(&priv->list_lock);
+	list_add(&omap_obj->mm_list, &priv->obj_list);
+	spin_unlock(&priv->list_lock);
+
 	omap_obj->flags = flags;
 
 	if (flags & OMAP_BO_TILED) {
diff --git a/drivers/gpu/drm/omapdrm/omap_plane.c b/drivers/gpu/drm/omapdrm/omap_plane.c
index cfa8276..0989046 100644
--- a/drivers/gpu/drm/omapdrm/omap_plane.c
+++ b/drivers/gpu/drm/omapdrm/omap_plane.c
@@ -17,6 +17,7 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_plane_helper.h>
 
@@ -153,9 +154,34 @@
 	dispc_ovl_enable(omap_plane->id, false);
 }
 
+static int omap_plane_atomic_check(struct drm_plane *plane,
+				   struct drm_plane_state *state)
+{
+	struct drm_crtc_state *crtc_state;
+
+	if (!state->crtc)
+		return 0;
+
+	crtc_state = drm_atomic_get_crtc_state(state->state, state->crtc);
+	if (IS_ERR(crtc_state))
+		return PTR_ERR(crtc_state);
+
+	if (state->crtc_x < 0 || state->crtc_y < 0)
+		return -EINVAL;
+
+	if (state->crtc_x + state->crtc_w > crtc_state->adjusted_mode.hdisplay)
+		return -EINVAL;
+
+	if (state->crtc_y + state->crtc_h > crtc_state->adjusted_mode.vdisplay)
+		return -EINVAL;
+
+	return 0;
+}
+
 static const struct drm_plane_helper_funcs omap_plane_helper_funcs = {
 	.prepare_fb = omap_plane_prepare_fb,
 	.cleanup_fb = omap_plane_cleanup_fb,
+	.atomic_check = omap_plane_atomic_check,
 	.atomic_update = omap_plane_atomic_update,
 	.atomic_disable = omap_plane_atomic_disable,
 };
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index dd39f43..c387259 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -2299,8 +2299,7 @@
 	encoder_mode = atombios_get_encoder_mode(encoder);
 	if (connector && (radeon_audio != 0) &&
 	    ((encoder_mode == ATOM_ENCODER_MODE_HDMI) ||
-	     (ENCODER_MODE_IS_DP(encoder_mode) &&
-	      drm_detect_monitor_audio(radeon_connector_edid(connector)))))
+	     ENCODER_MODE_IS_DP(encoder_mode)))
 		radeon_audio_mode_set(encoder, adjusted_mode);
 }
 
diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index 8730562..4a09947 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -5818,7 +5818,7 @@
 			tmp |= DPM_ENABLED;
 			break;
 		default:
-			DRM_ERROR("Invalid PCC GPIO: %u!\n", gpio.shift);
+			DRM_DEBUG("Invalid PCC GPIO: %u!\n", gpio.shift);
 			break;
 		}
 		WREG32_SMC(CNB_PWRMGT_CNTL, tmp);
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 4ecf5ca..248953d 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -7964,23 +7964,27 @@
 		case 1: /* D1 vblank/vline */
 			switch (src_data) {
 			case 0: /* D1 vblank */
-				if (rdev->irq.stat_regs.cik.disp_int & LB_D1_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[0]) {
-						drm_handle_vblank(rdev->ddev, 0);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[0]))
-						radeon_crtc_handle_vblank(rdev, 0);
-					rdev->irq.stat_regs.cik.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D1 vblank\n");
+				if (!(rdev->irq.stat_regs.cik.disp_int & LB_D1_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[0]) {
+					drm_handle_vblank(rdev->ddev, 0);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[0]))
+					radeon_crtc_handle_vblank(rdev, 0);
+				rdev->irq.stat_regs.cik.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D1 vblank\n");
+
 				break;
 			case 1: /* D1 vline */
-				if (rdev->irq.stat_regs.cik.disp_int & LB_D1_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int &= ~LB_D1_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D1 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int & LB_D1_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int &= ~LB_D1_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D1 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -7990,23 +7994,27 @@
 		case 2: /* D2 vblank/vline */
 			switch (src_data) {
 			case 0: /* D2 vblank */
-				if (rdev->irq.stat_regs.cik.disp_int_cont & LB_D2_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[1]) {
-						drm_handle_vblank(rdev->ddev, 1);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[1]))
-						radeon_crtc_handle_vblank(rdev, 1);
-					rdev->irq.stat_regs.cik.disp_int_cont &= ~LB_D2_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D2 vblank\n");
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont & LB_D2_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[1]) {
+					drm_handle_vblank(rdev->ddev, 1);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[1]))
+					radeon_crtc_handle_vblank(rdev, 1);
+				rdev->irq.stat_regs.cik.disp_int_cont &= ~LB_D2_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D2 vblank\n");
+
 				break;
 			case 1: /* D2 vline */
-				if (rdev->irq.stat_regs.cik.disp_int_cont & LB_D2_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont &= ~LB_D2_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D2 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont & LB_D2_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont &= ~LB_D2_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D2 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -8016,23 +8024,27 @@
 		case 3: /* D3 vblank/vline */
 			switch (src_data) {
 			case 0: /* D3 vblank */
-				if (rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[2]) {
-						drm_handle_vblank(rdev->ddev, 2);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[2]))
-						radeon_crtc_handle_vblank(rdev, 2);
-					rdev->irq.stat_regs.cik.disp_int_cont2 &= ~LB_D3_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D3 vblank\n");
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[2]) {
+					drm_handle_vblank(rdev->ddev, 2);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[2]))
+					radeon_crtc_handle_vblank(rdev, 2);
+				rdev->irq.stat_regs.cik.disp_int_cont2 &= ~LB_D3_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D3 vblank\n");
+
 				break;
 			case 1: /* D3 vline */
-				if (rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont2 &= ~LB_D3_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D3 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont2 & LB_D3_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont2 &= ~LB_D3_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D3 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -8042,23 +8054,27 @@
 		case 4: /* D4 vblank/vline */
 			switch (src_data) {
 			case 0: /* D4 vblank */
-				if (rdev->irq.stat_regs.cik.disp_int_cont3 & LB_D4_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[3]) {
-						drm_handle_vblank(rdev->ddev, 3);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[3]))
-						radeon_crtc_handle_vblank(rdev, 3);
-					rdev->irq.stat_regs.cik.disp_int_cont3 &= ~LB_D4_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D4 vblank\n");
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont3 & LB_D4_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[3]) {
+					drm_handle_vblank(rdev->ddev, 3);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[3]))
+					radeon_crtc_handle_vblank(rdev, 3);
+				rdev->irq.stat_regs.cik.disp_int_cont3 &= ~LB_D4_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D4 vblank\n");
+
 				break;
 			case 1: /* D4 vline */
-				if (rdev->irq.stat_regs.cik.disp_int_cont3 & LB_D4_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont3 &= ~LB_D4_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D4 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont3 & LB_D4_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont3 &= ~LB_D4_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D4 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -8068,23 +8084,27 @@
 		case 5: /* D5 vblank/vline */
 			switch (src_data) {
 			case 0: /* D5 vblank */
-				if (rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[4]) {
-						drm_handle_vblank(rdev->ddev, 4);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[4]))
-						radeon_crtc_handle_vblank(rdev, 4);
-					rdev->irq.stat_regs.cik.disp_int_cont4 &= ~LB_D5_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D5 vblank\n");
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[4]) {
+					drm_handle_vblank(rdev->ddev, 4);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[4]))
+					radeon_crtc_handle_vblank(rdev, 4);
+				rdev->irq.stat_regs.cik.disp_int_cont4 &= ~LB_D5_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D5 vblank\n");
+
 				break;
 			case 1: /* D5 vline */
-				if (rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont4 &= ~LB_D5_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D5 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont4 & LB_D5_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont4 &= ~LB_D5_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D5 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -8094,23 +8114,27 @@
 		case 6: /* D6 vblank/vline */
 			switch (src_data) {
 			case 0: /* D6 vblank */
-				if (rdev->irq.stat_regs.cik.disp_int_cont5 & LB_D6_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[5]) {
-						drm_handle_vblank(rdev->ddev, 5);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[5]))
-						radeon_crtc_handle_vblank(rdev, 5);
-					rdev->irq.stat_regs.cik.disp_int_cont5 &= ~LB_D6_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D6 vblank\n");
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont5 & LB_D6_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[5]) {
+					drm_handle_vblank(rdev->ddev, 5);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[5]))
+					radeon_crtc_handle_vblank(rdev, 5);
+				rdev->irq.stat_regs.cik.disp_int_cont5 &= ~LB_D6_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D6 vblank\n");
+
 				break;
 			case 1: /* D6 vline */
-				if (rdev->irq.stat_regs.cik.disp_int_cont5 & LB_D6_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont5 &= ~LB_D6_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D6 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont5 & LB_D6_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont5 &= ~LB_D6_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D6 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -8130,88 +8154,112 @@
 		case 42: /* HPD hotplug */
 			switch (src_data) {
 			case 0:
-				if (rdev->irq.stat_regs.cik.disp_int & DC_HPD1_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int &= ~DC_HPD1_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD1\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int & DC_HPD1_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int &= ~DC_HPD1_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD1\n");
+
 				break;
 			case 1:
-				if (rdev->irq.stat_regs.cik.disp_int_cont & DC_HPD2_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont &= ~DC_HPD2_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD2\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont & DC_HPD2_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont &= ~DC_HPD2_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD2\n");
+
 				break;
 			case 2:
-				if (rdev->irq.stat_regs.cik.disp_int_cont2 & DC_HPD3_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont2 &= ~DC_HPD3_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD3\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont2 & DC_HPD3_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont2 &= ~DC_HPD3_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD3\n");
+
 				break;
 			case 3:
-				if (rdev->irq.stat_regs.cik.disp_int_cont3 & DC_HPD4_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont3 &= ~DC_HPD4_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD4\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont3 & DC_HPD4_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont3 &= ~DC_HPD4_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD4\n");
+
 				break;
 			case 4:
-				if (rdev->irq.stat_regs.cik.disp_int_cont4 & DC_HPD5_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont4 &= ~DC_HPD5_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD5\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont4 & DC_HPD5_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont4 &= ~DC_HPD5_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD5\n");
+
 				break;
 			case 5:
-				if (rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont5 &= ~DC_HPD6_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD6\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont5 &= ~DC_HPD6_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD6\n");
+
 				break;
 			case 6:
-				if (rdev->irq.stat_regs.cik.disp_int & DC_HPD1_RX_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int &= ~DC_HPD1_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 1\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int & DC_HPD1_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int &= ~DC_HPD1_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 1\n");
+
 				break;
 			case 7:
-				if (rdev->irq.stat_regs.cik.disp_int_cont & DC_HPD2_RX_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont &= ~DC_HPD2_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 2\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont & DC_HPD2_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont &= ~DC_HPD2_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 2\n");
+
 				break;
 			case 8:
-				if (rdev->irq.stat_regs.cik.disp_int_cont2 & DC_HPD3_RX_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont2 &= ~DC_HPD3_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 3\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont2 & DC_HPD3_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont2 &= ~DC_HPD3_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 3\n");
+
 				break;
 			case 9:
-				if (rdev->irq.stat_regs.cik.disp_int_cont3 & DC_HPD4_RX_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont3 &= ~DC_HPD4_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 4\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont3 & DC_HPD4_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont3 &= ~DC_HPD4_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 4\n");
+
 				break;
 			case 10:
-				if (rdev->irq.stat_regs.cik.disp_int_cont4 & DC_HPD5_RX_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont4 &= ~DC_HPD5_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 5\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont4 & DC_HPD5_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont4 &= ~DC_HPD5_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 5\n");
+
 				break;
 			case 11:
-				if (rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
-					rdev->irq.stat_regs.cik.disp_int_cont5 &= ~DC_HPD6_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 6\n");
-				}
+				if (!(rdev->irq.stat_regs.cik.disp_int_cont5 & DC_HPD6_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.cik.disp_int_cont5 &= ~DC_HPD6_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 6\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c
index 68fd9fc..44480c1 100644
--- a/drivers/gpu/drm/radeon/dce6_afmt.c
+++ b/drivers/gpu/drm/radeon/dce6_afmt.c
@@ -93,30 +93,26 @@
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	u32 offset;
 
-	if (!dig || !dig->afmt || !dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->pin)
 		return;
 
-	offset = dig->afmt->offset;
-
-	WREG32(AFMT_AUDIO_SRC_CONTROL + offset,
-	       AFMT_AUDIO_SRC_SELECT(dig->afmt->pin->id));
+	WREG32(AFMT_AUDIO_SRC_CONTROL +  dig->afmt->offset,
+	       AFMT_AUDIO_SRC_SELECT(dig->pin->id));
 }
 
 void dce6_afmt_write_latency_fields(struct drm_encoder *encoder,
-		struct drm_connector *connector, struct drm_display_mode *mode)
+				    struct drm_connector *connector,
+				    struct drm_display_mode *mode)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	u32 tmp = 0, offset;
+	u32 tmp = 0;
 
-	if (!dig || !dig->afmt || !dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->pin)
 		return;
 
-	offset = dig->afmt->pin->offset;
-
 	if (mode->flags & DRM_MODE_FLAG_INTERLACE) {
 		if (connector->latency_present[1])
 			tmp = VIDEO_LIPSYNC(connector->video_latency[1]) |
@@ -130,24 +126,24 @@
 		else
 			tmp = VIDEO_LIPSYNC(0) | AUDIO_LIPSYNC(0);
 	}
-	WREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC, tmp);
+	WREG32_ENDPOINT(dig->pin->offset,
+			AZ_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC, tmp);
 }
 
 void dce6_afmt_hdmi_write_speaker_allocation(struct drm_encoder *encoder,
-	u8 *sadb, int sad_count)
+					     u8 *sadb, int sad_count)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	u32 offset, tmp;
+	u32 tmp;
 
-	if (!dig || !dig->afmt || !dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->pin)
 		return;
 
-	offset = dig->afmt->pin->offset;
-
 	/* program the speaker allocation */
-	tmp = RREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER);
+	tmp = RREG32_ENDPOINT(dig->pin->offset,
+			      AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER);
 	tmp &= ~(DP_CONNECTION | SPEAKER_ALLOCATION_MASK);
 	/* set HDMI mode */
 	tmp |= HDMI_CONNECTION;
@@ -155,24 +151,24 @@
 		tmp |= SPEAKER_ALLOCATION(sadb[0]);
 	else
 		tmp |= SPEAKER_ALLOCATION(5); /* stereo */
-	WREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp);
+	WREG32_ENDPOINT(dig->pin->offset,
+			AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp);
 }
 
 void dce6_afmt_dp_write_speaker_allocation(struct drm_encoder *encoder,
-	u8 *sadb, int sad_count)
+					   u8 *sadb, int sad_count)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	u32 offset, tmp;
+	u32 tmp;
 
-	if (!dig || !dig->afmt || !dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->pin)
 		return;
 
-	offset = dig->afmt->pin->offset;
-
 	/* program the speaker allocation */
-	tmp = RREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER);
+	tmp = RREG32_ENDPOINT(dig->pin->offset,
+			      AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER);
 	tmp &= ~(HDMI_CONNECTION | SPEAKER_ALLOCATION_MASK);
 	/* set DP mode */
 	tmp |= DP_CONNECTION;
@@ -180,13 +176,13 @@
 		tmp |= SPEAKER_ALLOCATION(sadb[0]);
 	else
 		tmp |= SPEAKER_ALLOCATION(5); /* stereo */
-	WREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp);
+	WREG32_ENDPOINT(dig->pin->offset,
+			AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp);
 }
 
 void dce6_afmt_write_sad_regs(struct drm_encoder *encoder,
-	struct cea_sad *sads, int sad_count)
+			      struct cea_sad *sads, int sad_count)
 {
-	u32 offset;
 	int i;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
@@ -206,11 +202,9 @@
 		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR13, HDMI_AUDIO_CODING_TYPE_WMA_PRO },
 	};
 
-	if (!dig || !dig->afmt || !dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->pin)
 		return;
 
-	offset = dig->afmt->pin->offset;
-
 	for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) {
 		u32 value = 0;
 		u8 stereo_freqs = 0;
@@ -237,7 +231,7 @@
 
 		value |= SUPPORTED_FREQUENCIES_STEREO(stereo_freqs);
 
-		WREG32_ENDPOINT(offset, eld_reg_to_type[i][0], value);
+		WREG32_ENDPOINT(dig->pin->offset, eld_reg_to_type[i][0], value);
 	}
 }
 
@@ -253,7 +247,7 @@
 }
 
 void dce6_hdmi_audio_set_dto(struct radeon_device *rdev,
-	struct radeon_crtc *crtc, unsigned int clock)
+			     struct radeon_crtc *crtc, unsigned int clock)
 {
 	/* Two dtos; generally use dto0 for HDMI */
 	u32 value = 0;
@@ -272,7 +266,7 @@
 }
 
 void dce6_dp_audio_set_dto(struct radeon_device *rdev,
-	struct radeon_crtc *crtc, unsigned int clock)
+			   struct radeon_crtc *crtc, unsigned int clock)
 {
 	/* Two dtos; generally use dto1 for DP */
 	u32 value = 0;
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 3a6d483..0acde19 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -4924,7 +4924,7 @@
 		return IRQ_NONE;
 
 	rptr = rdev->ih.rptr;
-	DRM_DEBUG("r600_irq_process start: rptr %d, wptr %d\n", rptr, wptr);
+	DRM_DEBUG("evergreen_irq_process start: rptr %d, wptr %d\n", rptr, wptr);
 
 	/* Order reading of wptr vs. reading of IH ring data */
 	rmb();
@@ -4942,23 +4942,27 @@
 		case 1: /* D1 vblank/vline */
 			switch (src_data) {
 			case 0: /* D1 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[0]) {
-						drm_handle_vblank(rdev->ddev, 0);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[0]))
-						radeon_crtc_handle_vblank(rdev, 0);
-					rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D1 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D1 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[0]) {
+					drm_handle_vblank(rdev->ddev, 0);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[0]))
+					radeon_crtc_handle_vblank(rdev, 0);
+				rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D1 vblank\n");
+
 				break;
 			case 1: /* D1 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D1 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: D1 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D1 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -4968,23 +4972,27 @@
 		case 2: /* D2 vblank/vline */
 			switch (src_data) {
 			case 0: /* D2 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[1]) {
-						drm_handle_vblank(rdev->ddev, 1);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[1]))
-						radeon_crtc_handle_vblank(rdev, 1);
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D2 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D2 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[1]) {
+					drm_handle_vblank(rdev->ddev, 1);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[1]))
+					radeon_crtc_handle_vblank(rdev, 1);
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D2 vblank\n");
+
 				break;
 			case 1: /* D2 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D2 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: D2 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D2 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -4994,23 +5002,27 @@
 		case 3: /* D3 vblank/vline */
 			switch (src_data) {
 			case 0: /* D3 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[2]) {
-						drm_handle_vblank(rdev->ddev, 2);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[2]))
-						radeon_crtc_handle_vblank(rdev, 2);
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D3 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D3 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[2]) {
+					drm_handle_vblank(rdev->ddev, 2);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[2]))
+					radeon_crtc_handle_vblank(rdev, 2);
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D3 vblank\n");
+
 				break;
 			case 1: /* D3 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D3 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: D3 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D3 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -5020,23 +5032,27 @@
 		case 4: /* D4 vblank/vline */
 			switch (src_data) {
 			case 0: /* D4 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[3]) {
-						drm_handle_vblank(rdev->ddev, 3);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[3]))
-						radeon_crtc_handle_vblank(rdev, 3);
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D4 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D4 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[3]) {
+					drm_handle_vblank(rdev->ddev, 3);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[3]))
+					radeon_crtc_handle_vblank(rdev, 3);
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D4 vblank\n");
+
 				break;
 			case 1: /* D4 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D4 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: D4 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D4 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -5046,23 +5062,27 @@
 		case 5: /* D5 vblank/vline */
 			switch (src_data) {
 			case 0: /* D5 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[4]) {
-						drm_handle_vblank(rdev->ddev, 4);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[4]))
-						radeon_crtc_handle_vblank(rdev, 4);
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D5 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D5 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[4]) {
+					drm_handle_vblank(rdev->ddev, 4);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[4]))
+					radeon_crtc_handle_vblank(rdev, 4);
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D5 vblank\n");
+
 				break;
 			case 1: /* D5 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D5 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: D5 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D5 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -5072,23 +5092,27 @@
 		case 6: /* D6 vblank/vline */
 			switch (src_data) {
 			case 0: /* D6 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[5]) {
-						drm_handle_vblank(rdev->ddev, 5);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[5]))
-						radeon_crtc_handle_vblank(rdev, 5);
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D6 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D6 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[5]) {
+					drm_handle_vblank(rdev->ddev, 5);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[5]))
+					radeon_crtc_handle_vblank(rdev, 5);
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D6 vblank\n");
+
 				break;
 			case 1: /* D6 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D6 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: D6 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D6 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -5108,88 +5132,100 @@
 		case 42: /* HPD hotplug */
 			switch (src_data) {
 			case 0:
-				if (rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD1\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD1\n");
 				break;
 			case 1:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD2\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD2\n");
 				break;
 			case 2:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD3\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD3\n");
 				break;
 			case 3:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD4\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD4\n");
 				break;
 			case 4:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD5\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD5\n");
 				break;
 			case 5:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD6\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD6\n");
 				break;
 			case 6:
-				if (rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 1\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 1\n");
 				break;
 			case 7:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 2\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 2\n");
 				break;
 			case 8:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 3\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 3\n");
 				break;
 			case 9:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 4\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 4\n");
 				break;
 			case 10:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 5\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 5\n");
 				break;
 			case 11:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 6\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 6\n");
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -5199,46 +5235,52 @@
 		case 44: /* hdmi */
 			switch (src_data) {
 			case 0:
-				if (rdev->irq.stat_regs.evergreen.afmt_status1 & AFMT_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.evergreen.afmt_status1 &= ~AFMT_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI0\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.afmt_status1 & AFMT_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.afmt_status1 &= ~AFMT_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI0\n");
 				break;
 			case 1:
-				if (rdev->irq.stat_regs.evergreen.afmt_status2 & AFMT_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.evergreen.afmt_status2 &= ~AFMT_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI1\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.afmt_status2 & AFMT_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.afmt_status2 &= ~AFMT_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI1\n");
 				break;
 			case 2:
-				if (rdev->irq.stat_regs.evergreen.afmt_status3 & AFMT_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.evergreen.afmt_status3 &= ~AFMT_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI2\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.afmt_status3 & AFMT_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.afmt_status3 &= ~AFMT_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI2\n");
 				break;
 			case 3:
-				if (rdev->irq.stat_regs.evergreen.afmt_status4 & AFMT_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.evergreen.afmt_status4 &= ~AFMT_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI3\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.afmt_status4 & AFMT_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.afmt_status4 &= ~AFMT_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI3\n");
 				break;
 			case 4:
-				if (rdev->irq.stat_regs.evergreen.afmt_status5 & AFMT_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.evergreen.afmt_status5 &= ~AFMT_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI4\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.afmt_status5 & AFMT_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.afmt_status5 &= ~AFMT_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI4\n");
 				break;
 			case 5:
-				if (rdev->irq.stat_regs.evergreen.afmt_status6 & AFMT_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.evergreen.afmt_status6 &= ~AFMT_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI5\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.afmt_status6 & AFMT_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.afmt_status6 &= ~AFMT_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI5\n");
 				break;
 			default:
 				DRM_ERROR("Unhandled interrupt: %d %d\n", src_id, src_data);
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 8e5aeeb..158872e 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -2162,18 +2162,20 @@
 			DRM_ERROR("radeon: failed initializing UVD (%d).\n", r);
 	}
 
-	ring = &rdev->ring[TN_RING_TYPE_VCE1_INDEX];
-	if (ring->ring_size)
-		r = radeon_ring_init(rdev, ring, ring->ring_size, 0, 0x0);
+	if (rdev->family == CHIP_ARUBA) {
+		ring = &rdev->ring[TN_RING_TYPE_VCE1_INDEX];
+		if (ring->ring_size)
+			r = radeon_ring_init(rdev, ring, ring->ring_size, 0, 0x0);
 
-	ring = &rdev->ring[TN_RING_TYPE_VCE2_INDEX];
-	if (ring->ring_size)
-		r = radeon_ring_init(rdev, ring, ring->ring_size, 0, 0x0);
+		ring = &rdev->ring[TN_RING_TYPE_VCE2_INDEX];
+		if (ring->ring_size)
+			r = radeon_ring_init(rdev, ring, ring->ring_size, 0, 0x0);
 
-	if (!r)
-		r = vce_v1_0_init(rdev);
-	else if (r != -ENOENT)
-		DRM_ERROR("radeon: failed initializing VCE (%d).\n", r);
+		if (!r)
+			r = vce_v1_0_init(rdev);
+		if (r)
+			DRM_ERROR("radeon: failed initializing VCE (%d).\n", r);
+	}
 
 	r = radeon_ib_pool_init(rdev);
 	if (r) {
@@ -2396,7 +2398,8 @@
 	radeon_irq_kms_fini(rdev);
 	uvd_v1_0_fini(rdev);
 	radeon_uvd_fini(rdev);
-	radeon_vce_fini(rdev);
+	if (rdev->family == CHIP_ARUBA)
+		radeon_vce_fini(rdev);
 	cayman_pcie_gart_fini(rdev);
 	r600_vram_scratch_fini(rdev);
 	radeon_gem_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 35dafd7..4ea5b10 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -4086,23 +4086,27 @@
 		case 1: /* D1 vblank/vline */
 			switch (src_data) {
 			case 0: /* D1 vblank */
-				if (rdev->irq.stat_regs.r600.disp_int & LB_D1_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[0]) {
-						drm_handle_vblank(rdev->ddev, 0);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[0]))
-						radeon_crtc_handle_vblank(rdev, 0);
-					rdev->irq.stat_regs.r600.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D1 vblank\n");
+				if (!(rdev->irq.stat_regs.r600.disp_int & LB_D1_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D1 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[0]) {
+					drm_handle_vblank(rdev->ddev, 0);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[0]))
+					radeon_crtc_handle_vblank(rdev, 0);
+				rdev->irq.stat_regs.r600.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D1 vblank\n");
+
 				break;
 			case 1: /* D1 vline */
-				if (rdev->irq.stat_regs.r600.disp_int & LB_D1_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int &= ~LB_D1_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D1 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int & LB_D1_VLINE_INTERRUPT))
+				    DRM_DEBUG("IH: D1 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int &= ~LB_D1_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D1 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -4112,23 +4116,27 @@
 		case 5: /* D2 vblank/vline */
 			switch (src_data) {
 			case 0: /* D2 vblank */
-				if (rdev->irq.stat_regs.r600.disp_int & LB_D2_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[1]) {
-						drm_handle_vblank(rdev->ddev, 1);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[1]))
-						radeon_crtc_handle_vblank(rdev, 1);
-					rdev->irq.stat_regs.r600.disp_int &= ~LB_D2_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D2 vblank\n");
+				if (!(rdev->irq.stat_regs.r600.disp_int & LB_D2_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: D2 vblank - IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[1]) {
+					drm_handle_vblank(rdev->ddev, 1);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[1]))
+					radeon_crtc_handle_vblank(rdev, 1);
+				rdev->irq.stat_regs.r600.disp_int &= ~LB_D2_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D2 vblank\n");
+
 				break;
 			case 1: /* D1 vline */
-				if (rdev->irq.stat_regs.r600.disp_int & LB_D2_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int &= ~LB_D2_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D2 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int & LB_D2_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: D2 vline - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int &= ~LB_D2_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D2 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -4148,46 +4156,53 @@
 		case 19: /* HPD/DAC hotplug */
 			switch (src_data) {
 			case 0:
-				if (rdev->irq.stat_regs.r600.disp_int & DC_HPD1_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int &= ~DC_HPD1_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD1\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int & DC_HPD1_INTERRUPT))
+					DRM_DEBUG("IH: HPD1 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int &= ~DC_HPD1_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD1\n");
 				break;
 			case 1:
-				if (rdev->irq.stat_regs.r600.disp_int & DC_HPD2_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int &= ~DC_HPD2_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD2\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int & DC_HPD2_INTERRUPT))
+					DRM_DEBUG("IH: HPD2 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int &= ~DC_HPD2_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD2\n");
 				break;
 			case 4:
-				if (rdev->irq.stat_regs.r600.disp_int_cont & DC_HPD3_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int_cont &= ~DC_HPD3_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD3\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int_cont & DC_HPD3_INTERRUPT))
+					DRM_DEBUG("IH: HPD3 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int_cont &= ~DC_HPD3_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD3\n");
 				break;
 			case 5:
-				if (rdev->irq.stat_regs.r600.disp_int_cont & DC_HPD4_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int_cont &= ~DC_HPD4_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD4\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int_cont & DC_HPD4_INTERRUPT))
+					DRM_DEBUG("IH: HPD4 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int_cont &= ~DC_HPD4_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD4\n");
 				break;
 			case 10:
-				if (rdev->irq.stat_regs.r600.disp_int_cont2 & DC_HPD5_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int_cont2 &= ~DC_HPD5_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD5\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int_cont2 & DC_HPD5_INTERRUPT))
+					DRM_DEBUG("IH: HPD5 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int_cont2 &= ~DC_HPD5_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD5\n");
 				break;
 			case 12:
-				if (rdev->irq.stat_regs.r600.disp_int_cont2 & DC_HPD6_INTERRUPT) {
-					rdev->irq.stat_regs.r600.disp_int_cont2 &= ~DC_HPD6_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD6\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.disp_int_cont2 & DC_HPD6_INTERRUPT))
+					DRM_DEBUG("IH: HPD6 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.disp_int_cont2 &= ~DC_HPD6_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD6\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -4197,18 +4212,22 @@
 		case 21: /* hdmi */
 			switch (src_data) {
 			case 4:
-				if (rdev->irq.stat_regs.r600.hdmi0_status & HDMI0_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.r600.hdmi0_status &= ~HDMI0_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI0\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.hdmi0_status & HDMI0_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: HDMI0 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.hdmi0_status &= ~HDMI0_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI0\n");
+
 				break;
 			case 5:
-				if (rdev->irq.stat_regs.r600.hdmi1_status & HDMI0_AZ_FORMAT_WTRIG) {
-					rdev->irq.stat_regs.r600.hdmi1_status &= ~HDMI0_AZ_FORMAT_WTRIG;
-					queue_hdmi = true;
-					DRM_DEBUG("IH: HDMI1\n");
-				}
+				if (!(rdev->irq.stat_regs.r600.hdmi1_status & HDMI0_AZ_FORMAT_WTRIG))
+					DRM_DEBUG("IH: HDMI1 - IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.r600.hdmi1_status &= ~HDMI0_AZ_FORMAT_WTRIG;
+				queue_hdmi = true;
+				DRM_DEBUG("IH: HDMI1\n");
+
 				break;
 			default:
 				DRM_ERROR("Unhandled interrupt: %d %d\n", src_id, src_data);
diff --git a/drivers/gpu/drm/radeon/r600_cp.c b/drivers/gpu/drm/radeon/r600_cp.c
index 09e3f39..98f9ada 100644
--- a/drivers/gpu/drm/radeon/r600_cp.c
+++ b/drivers/gpu/drm/radeon/r600_cp.c
@@ -2483,7 +2483,7 @@
 	struct drm_buf *buf;
 	u32 *buffer;
 	const u8 __user *data;
-	int size, pass_size;
+	unsigned int size, pass_size;
 	u64 src_offset, dst_offset;
 
 	if (!radeon_check_offset(dev_priv, tex->offset)) {
diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c
index fa719c5..fbc8d88 100644
--- a/drivers/gpu/drm/radeon/radeon_audio.c
+++ b/drivers/gpu/drm/radeon/radeon_audio.c
@@ -245,6 +245,28 @@
 static void radeon_audio_enable(struct radeon_device *rdev,
 				struct r600_audio_pin *pin, u8 enable_mask)
 {
+	struct drm_encoder *encoder;
+	struct radeon_encoder *radeon_encoder;
+	struct radeon_encoder_atom_dig *dig;
+	int pin_count = 0;
+
+	if (!pin)
+		return;
+
+	if (rdev->mode_info.mode_config_initialized) {
+		list_for_each_entry(encoder, &rdev->ddev->mode_config.encoder_list, head) {
+			if (radeon_encoder_is_digital(encoder)) {
+				radeon_encoder = to_radeon_encoder(encoder);
+				dig = radeon_encoder->enc_priv;
+				if (dig->pin == pin)
+					pin_count++;
+			}
+		}
+
+		if ((pin_count > 1) && (enable_mask == 0))
+			return;
+	}
+
 	if (rdev->audio.funcs->enable)
 		rdev->audio.funcs->enable(rdev, pin, enable_mask);
 }
@@ -336,24 +358,13 @@
 
 static void radeon_audio_write_sad_regs(struct drm_encoder *encoder)
 {
-	struct radeon_encoder *radeon_encoder;
-	struct drm_connector *connector;
-	struct radeon_connector *radeon_connector = NULL;
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct cea_sad *sads;
 	int sad_count;
 
-	list_for_each_entry(connector,
-		&encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
-			radeon_connector = to_radeon_connector(connector);
-			break;
-		}
-	}
-
-	if (!radeon_connector) {
-		DRM_ERROR("Couldn't find encoder's connector\n");
+	if (!connector)
 		return;
-	}
 
 	sad_count = drm_edid_to_sad(radeon_connector_edid(connector), &sads);
 	if (sad_count <= 0) {
@@ -362,8 +373,6 @@
 	}
 	BUG_ON(!sads);
 
-	radeon_encoder = to_radeon_encoder(encoder);
-
 	if (radeon_encoder->audio && radeon_encoder->audio->write_sad_regs)
 		radeon_encoder->audio->write_sad_regs(encoder, sads, sad_count);
 
@@ -372,27 +381,16 @@
 
 static void radeon_audio_write_speaker_allocation(struct drm_encoder *encoder)
 {
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
-	struct drm_connector *connector;
-	struct radeon_connector *radeon_connector = NULL;
 	u8 *sadb = NULL;
 	int sad_count;
 
-	list_for_each_entry(connector,
-			    &encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
-			radeon_connector = to_radeon_connector(connector);
-			break;
-		}
-	}
-
-	if (!radeon_connector) {
-		DRM_ERROR("Couldn't find encoder's connector\n");
+	if (!connector)
 		return;
-	}
 
-	sad_count = drm_edid_to_speaker_allocation(
-		radeon_connector_edid(connector), &sadb);
+	sad_count = drm_edid_to_speaker_allocation(radeon_connector_edid(connector),
+						   &sadb);
 	if (sad_count < 0) {
 		DRM_DEBUG("Couldn't read Speaker Allocation Data Block: %d\n",
 			  sad_count);
@@ -406,26 +404,13 @@
 }
 
 static void radeon_audio_write_latency_fields(struct drm_encoder *encoder,
-	struct drm_display_mode *mode)
+					      struct drm_display_mode *mode)
 {
-	struct radeon_encoder *radeon_encoder;
-	struct drm_connector *connector;
-	struct radeon_connector *radeon_connector = 0;
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 
-	list_for_each_entry(connector,
-		&encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
-			radeon_connector = to_radeon_connector(connector);
-			break;
-		}
-	}
-
-	if (!radeon_connector) {
-		DRM_ERROR("Couldn't find encoder's connector\n");
+	if (!connector)
 		return;
-	}
-
-	radeon_encoder = to_radeon_encoder(encoder);
 
 	if (radeon_encoder->audio && radeon_encoder->audio->write_latency_fields)
 		radeon_encoder->audio->write_latency_fields(encoder, connector, mode);
@@ -451,29 +436,23 @@
 }
 
 void radeon_audio_detect(struct drm_connector *connector,
+			 struct drm_encoder *encoder,
 			 enum drm_connector_status status)
 {
-	struct radeon_device *rdev;
-	struct radeon_encoder *radeon_encoder;
+	struct drm_device *dev = connector->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig;
 
-	if (!connector || !connector->encoder)
-		return;
-
-	rdev = connector->encoder->dev->dev_private;
-
 	if (!radeon_audio_chipset_supported(rdev))
 		return;
 
-	radeon_encoder = to_radeon_encoder(connector->encoder);
+	if (!radeon_encoder_is_digital(encoder))
+		return;
+
 	dig = radeon_encoder->enc_priv;
 
 	if (status == connector_status_connected) {
-		if (!drm_detect_monitor_audio(radeon_connector_edid(connector))) {
-			radeon_encoder->audio = NULL;
-			return;
-		}
-
 		if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort) {
 			struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 
@@ -486,11 +465,17 @@
 			radeon_encoder->audio = rdev->audio.hdmi_funcs;
 		}
 
-		dig->afmt->pin = radeon_audio_get_pin(connector->encoder);
-		radeon_audio_enable(rdev, dig->afmt->pin, 0xf);
+		if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+			if (!dig->pin)
+				dig->pin = radeon_audio_get_pin(encoder);
+			radeon_audio_enable(rdev, dig->pin, 0xf);
+		} else {
+			radeon_audio_enable(rdev, dig->pin, 0);
+			dig->pin = NULL;
+		}
 	} else {
-		radeon_audio_enable(rdev, dig->afmt->pin, 0);
-		dig->afmt->pin = NULL;
+		radeon_audio_enable(rdev, dig->pin, 0);
+		dig->pin = NULL;
 	}
 }
 
@@ -518,29 +503,18 @@
 }
 
 static int radeon_audio_set_avi_packet(struct drm_encoder *encoder,
-	struct drm_display_mode *mode)
+				       struct drm_display_mode *mode)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	struct drm_connector *connector;
-	struct radeon_connector *radeon_connector = NULL;
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 	u8 buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AVI_INFOFRAME_SIZE];
 	struct hdmi_avi_infoframe frame;
 	int err;
 
-	list_for_each_entry(connector,
-		&encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
-			radeon_connector = to_radeon_connector(connector);
-			break;
-		}
-	}
-
-	if (!radeon_connector) {
-		DRM_ERROR("Couldn't find encoder's connector\n");
-		return -ENOENT;
-	}
+	if (!connector)
+		return -EINVAL;
 
 	err = drm_hdmi_avi_infoframe_from_display_mode(&frame, mode);
 	if (err < 0) {
@@ -563,8 +537,8 @@
 		return err;
 	}
 
-	if (dig && dig->afmt &&
-		radeon_encoder->audio && radeon_encoder->audio->set_avi_packet)
+	if (dig && dig->afmt && radeon_encoder->audio &&
+	    radeon_encoder->audio->set_avi_packet)
 		radeon_encoder->audio->set_avi_packet(rdev, dig->afmt->offset,
 			buffer, sizeof(buffer));
 
@@ -722,30 +696,41 @@
 {
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 
 	if (!dig || !dig->afmt)
 		return;
 
-	radeon_audio_set_mute(encoder, true);
-
-	radeon_audio_write_speaker_allocation(encoder);
-	radeon_audio_write_sad_regs(encoder);
-	radeon_audio_write_latency_fields(encoder, mode);
-	radeon_audio_set_dto(encoder, mode->clock);
-	radeon_audio_set_vbi_packet(encoder);
-	radeon_hdmi_set_color_depth(encoder);
-	radeon_audio_update_acr(encoder, mode->clock);
-	radeon_audio_set_audio_packet(encoder);
-	radeon_audio_select_pin(encoder);
-
-	if (radeon_audio_set_avi_packet(encoder, mode) < 0)
+	if (!connector)
 		return;
 
-	radeon_audio_set_mute(encoder, false);
+	if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+		radeon_audio_set_mute(encoder, true);
+
+		radeon_audio_write_speaker_allocation(encoder);
+		radeon_audio_write_sad_regs(encoder);
+		radeon_audio_write_latency_fields(encoder, mode);
+		radeon_audio_set_dto(encoder, mode->clock);
+		radeon_audio_set_vbi_packet(encoder);
+		radeon_hdmi_set_color_depth(encoder);
+		radeon_audio_update_acr(encoder, mode->clock);
+		radeon_audio_set_audio_packet(encoder);
+		radeon_audio_select_pin(encoder);
+
+		if (radeon_audio_set_avi_packet(encoder, mode) < 0)
+			return;
+
+		radeon_audio_set_mute(encoder, false);
+	} else {
+		radeon_hdmi_set_color_depth(encoder);
+
+		if (radeon_audio_set_avi_packet(encoder, mode) < 0)
+			return;
+	}
 }
 
 static void radeon_audio_dp_mode_set(struct drm_encoder *encoder,
-	struct drm_display_mode *mode)
+				     struct drm_display_mode *mode)
 {
 	struct drm_device *dev = encoder->dev;
 	struct radeon_device *rdev = dev->dev_private;
@@ -759,22 +744,27 @@
 	if (!dig || !dig->afmt)
 		return;
 
-	radeon_audio_write_speaker_allocation(encoder);
-	radeon_audio_write_sad_regs(encoder);
-	radeon_audio_write_latency_fields(encoder, mode);
-	if (rdev->clock.dp_extclk || ASIC_IS_DCE5(rdev))
-		radeon_audio_set_dto(encoder, rdev->clock.default_dispclk * 10);
-	else
-		radeon_audio_set_dto(encoder, dig_connector->dp_clock);
-	radeon_audio_set_audio_packet(encoder);
-	radeon_audio_select_pin(encoder);
-
-	if (radeon_audio_set_avi_packet(encoder, mode) < 0)
+	if (!connector)
 		return;
+
+	if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+		radeon_audio_write_speaker_allocation(encoder);
+		radeon_audio_write_sad_regs(encoder);
+		radeon_audio_write_latency_fields(encoder, mode);
+		if (rdev->clock.dp_extclk || ASIC_IS_DCE5(rdev))
+			radeon_audio_set_dto(encoder, rdev->clock.default_dispclk * 10);
+		else
+			radeon_audio_set_dto(encoder, dig_connector->dp_clock);
+		radeon_audio_set_audio_packet(encoder);
+		radeon_audio_select_pin(encoder);
+
+		if (radeon_audio_set_avi_packet(encoder, mode) < 0)
+			return;
+	}
 }
 
 void radeon_audio_mode_set(struct drm_encoder *encoder,
-	struct drm_display_mode *mode)
+			   struct drm_display_mode *mode)
 {
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 
diff --git a/drivers/gpu/drm/radeon/radeon_audio.h b/drivers/gpu/drm/radeon/radeon_audio.h
index 8438304..059cc30 100644
--- a/drivers/gpu/drm/radeon/radeon_audio.h
+++ b/drivers/gpu/drm/radeon/radeon_audio.h
@@ -68,7 +68,8 @@
 
 int radeon_audio_init(struct radeon_device *rdev);
 void radeon_audio_detect(struct drm_connector *connector,
-	enum drm_connector_status status);
+			 struct drm_encoder *encoder,
+			 enum drm_connector_status status);
 u32 radeon_audio_endpoint_rreg(struct radeon_device *rdev,
 	u32 offset, u32 reg);
 void radeon_audio_endpoint_wreg(struct radeon_device *rdev,
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index 3e5f6b7..c097d3a 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -1255,10 +1255,15 @@
 
 			if ((RBIOS16(tmp) == lvds->native_mode.hdisplay) &&
 			    (RBIOS16(tmp + 2) == lvds->native_mode.vdisplay)) {
+				u32 hss = (RBIOS16(tmp + 21) - RBIOS16(tmp + 19) - 1) * 8;
+
+				if (hss > lvds->native_mode.hdisplay)
+					hss = (10 - 1) * 8;
+
 				lvds->native_mode.htotal = lvds->native_mode.hdisplay +
 					(RBIOS16(tmp + 17) - RBIOS16(tmp + 19)) * 8;
 				lvds->native_mode.hsync_start = lvds->native_mode.hdisplay +
-					(RBIOS16(tmp + 21) - RBIOS16(tmp + 19) - 1) * 8;
+					hss;
 				lvds->native_mode.hsync_end = lvds->native_mode.hsync_start +
 					(RBIOS8(tmp + 23) * 8);
 
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index cebb65e..94b21ae 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1379,8 +1379,16 @@
 	/* updated in get modes as well since we need to know if it's analog or digital */
 	radeon_connector_update_scratch_regs(connector, ret);
 
-	if (radeon_audio != 0)
-		radeon_audio_detect(connector, ret);
+	if ((radeon_audio != 0) && radeon_connector->use_digital) {
+		const struct drm_connector_helper_funcs *connector_funcs =
+			connector->helper_private;
+
+		encoder = connector_funcs->best_encoder(connector);
+		if (encoder && (encoder->encoder_type == DRM_MODE_ENCODER_TMDS)) {
+			radeon_connector_get_edid(connector);
+			radeon_audio_detect(connector, encoder, ret);
+		}
+	}
 
 exit:
 	pm_runtime_mark_last_busy(connector->dev->dev);
@@ -1717,8 +1725,10 @@
 
 	radeon_connector_update_scratch_regs(connector, ret);
 
-	if (radeon_audio != 0)
-		radeon_audio_detect(connector, ret);
+	if ((radeon_audio != 0) && encoder) {
+		radeon_connector_get_edid(connector);
+		radeon_audio_detect(connector, encoder, ret);
+	}
 
 out:
 	pm_runtime_mark_last_busy(connector->dev->dev);
diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c
index 45e5406..afaf346 100644
--- a/drivers/gpu/drm/radeon/radeon_cursor.c
+++ b/drivers/gpu/drm/radeon/radeon_cursor.c
@@ -91,15 +91,34 @@
 	struct radeon_device *rdev = crtc->dev->dev_private;
 
 	if (ASIC_IS_DCE4(rdev)) {
+		WREG32(EVERGREEN_CUR_SURFACE_ADDRESS_HIGH + radeon_crtc->crtc_offset,
+		       upper_32_bits(radeon_crtc->cursor_addr));
+		WREG32(EVERGREEN_CUR_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
+		       lower_32_bits(radeon_crtc->cursor_addr));
 		WREG32(RADEON_MM_INDEX, EVERGREEN_CUR_CONTROL + radeon_crtc->crtc_offset);
 		WREG32(RADEON_MM_DATA, EVERGREEN_CURSOR_EN |
 		       EVERGREEN_CURSOR_MODE(EVERGREEN_CURSOR_24_8_PRE_MULT) |
 		       EVERGREEN_CURSOR_URGENT_CONTROL(EVERGREEN_CURSOR_URGENT_1_2));
 	} else if (ASIC_IS_AVIVO(rdev)) {
+		if (rdev->family >= CHIP_RV770) {
+			if (radeon_crtc->crtc_id)
+				WREG32(R700_D2CUR_SURFACE_ADDRESS_HIGH,
+				       upper_32_bits(radeon_crtc->cursor_addr));
+			else
+				WREG32(R700_D1CUR_SURFACE_ADDRESS_HIGH,
+				       upper_32_bits(radeon_crtc->cursor_addr));
+		}
+
+		WREG32(AVIVO_D1CUR_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
+		       lower_32_bits(radeon_crtc->cursor_addr));
 		WREG32(RADEON_MM_INDEX, AVIVO_D1CUR_CONTROL + radeon_crtc->crtc_offset);
 		WREG32(RADEON_MM_DATA, AVIVO_D1CURSOR_EN |
 		       (AVIVO_D1CURSOR_MODE_24BPP << AVIVO_D1CURSOR_MODE_SHIFT));
 	} else {
+		/* offset is from DISP(2)_BASE_ADDRESS */
+		WREG32(RADEON_CUR_OFFSET + radeon_crtc->crtc_offset,
+		       radeon_crtc->cursor_addr - radeon_crtc->legacy_display_base_addr);
+
 		switch (radeon_crtc->crtc_id) {
 		case 0:
 			WREG32(RADEON_MM_INDEX, RADEON_CRTC_GEN_CNTL);
@@ -205,8 +224,9 @@
 			| (x << 16)
 			| y));
 		/* offset is from DISP(2)_BASE_ADDRESS */
-		WREG32(RADEON_CUR_OFFSET + radeon_crtc->crtc_offset, (radeon_crtc->legacy_cursor_offset +
-								      (yorigin * 256)));
+		WREG32(RADEON_CUR_OFFSET + radeon_crtc->crtc_offset,
+		       radeon_crtc->cursor_addr - radeon_crtc->legacy_display_base_addr +
+		       yorigin * 256);
 	}
 
 	radeon_crtc->cursor_x = x;
@@ -227,53 +247,6 @@
 	return ret;
 }
 
-static int radeon_set_cursor(struct drm_crtc *crtc, struct drm_gem_object *obj)
-{
-	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
-	struct radeon_device *rdev = crtc->dev->dev_private;
-	struct radeon_bo *robj = gem_to_radeon_bo(obj);
-	uint64_t gpu_addr;
-	int ret;
-
-	ret = radeon_bo_reserve(robj, false);
-	if (unlikely(ret != 0))
-		goto fail;
-	/* Only 27 bit offset for legacy cursor */
-	ret = radeon_bo_pin_restricted(robj, RADEON_GEM_DOMAIN_VRAM,
-				       ASIC_IS_AVIVO(rdev) ? 0 : 1 << 27,
-				       &gpu_addr);
-	radeon_bo_unreserve(robj);
-	if (ret)
-		goto fail;
-
-	if (ASIC_IS_DCE4(rdev)) {
-		WREG32(EVERGREEN_CUR_SURFACE_ADDRESS_HIGH + radeon_crtc->crtc_offset,
-		       upper_32_bits(gpu_addr));
-		WREG32(EVERGREEN_CUR_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
-		       gpu_addr & 0xffffffff);
-	} else if (ASIC_IS_AVIVO(rdev)) {
-		if (rdev->family >= CHIP_RV770) {
-			if (radeon_crtc->crtc_id)
-				WREG32(R700_D2CUR_SURFACE_ADDRESS_HIGH, upper_32_bits(gpu_addr));
-			else
-				WREG32(R700_D1CUR_SURFACE_ADDRESS_HIGH, upper_32_bits(gpu_addr));
-		}
-		WREG32(AVIVO_D1CUR_SURFACE_ADDRESS + radeon_crtc->crtc_offset,
-		       gpu_addr & 0xffffffff);
-	} else {
-		radeon_crtc->legacy_cursor_offset = gpu_addr - radeon_crtc->legacy_display_base_addr;
-		/* offset is from DISP(2)_BASE_ADDRESS */
-		WREG32(RADEON_CUR_OFFSET + radeon_crtc->crtc_offset, radeon_crtc->legacy_cursor_offset);
-	}
-
-	return 0;
-
-fail:
-	drm_gem_object_unreference_unlocked(obj);
-
-	return ret;
-}
-
 int radeon_crtc_cursor_set2(struct drm_crtc *crtc,
 			    struct drm_file *file_priv,
 			    uint32_t handle,
@@ -283,7 +256,9 @@
 			    int32_t hot_y)
 {
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
+	struct radeon_device *rdev = crtc->dev->dev_private;
 	struct drm_gem_object *obj;
+	struct radeon_bo *robj;
 	int ret;
 
 	if (!handle) {
@@ -305,6 +280,23 @@
 		return -ENOENT;
 	}
 
+	robj = gem_to_radeon_bo(obj);
+	ret = radeon_bo_reserve(robj, false);
+	if (ret != 0) {
+		drm_gem_object_unreference_unlocked(obj);
+		return ret;
+	}
+	/* Only 27 bit offset for legacy cursor */
+	ret = radeon_bo_pin_restricted(robj, RADEON_GEM_DOMAIN_VRAM,
+				       ASIC_IS_AVIVO(rdev) ? 0 : 1 << 27,
+				       &radeon_crtc->cursor_addr);
+	radeon_bo_unreserve(robj);
+	if (ret) {
+		DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
+		drm_gem_object_unreference_unlocked(obj);
+		return ret;
+	}
+
 	radeon_crtc->cursor_width = width;
 	radeon_crtc->cursor_height = height;
 
@@ -323,13 +315,7 @@
 		radeon_crtc->cursor_hot_y = hot_y;
 	}
 
-	ret = radeon_set_cursor(crtc, obj);
-
-	if (ret)
-		DRM_ERROR("radeon_set_cursor returned %d, not changing cursor\n",
-			  ret);
-	else
-		radeon_show_cursor(crtc);
+	radeon_show_cursor(crtc);
 
 	radeon_lock_cursor(crtc, false);
 
@@ -341,8 +327,7 @@
 			radeon_bo_unpin(robj);
 			radeon_bo_unreserve(robj);
 		}
-		if (radeon_crtc->cursor_bo != obj)
-			drm_gem_object_unreference_unlocked(radeon_crtc->cursor_bo);
+		drm_gem_object_unreference_unlocked(radeon_crtc->cursor_bo);
 	}
 
 	radeon_crtc->cursor_bo = obj;
@@ -360,7 +345,6 @@
 void radeon_cursor_reset(struct drm_crtc *crtc)
 {
 	struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
-	int ret;
 
 	if (radeon_crtc->cursor_bo) {
 		radeon_lock_cursor(crtc, true);
@@ -368,12 +352,7 @@
 		radeon_cursor_move_locked(crtc, radeon_crtc->cursor_x,
 					  radeon_crtc->cursor_y);
 
-		ret = radeon_set_cursor(crtc, radeon_crtc->cursor_bo);
-		if (ret)
-			DRM_ERROR("radeon_set_cursor returned %d, not showing "
-				  "cursor\n", ret);
-		else
-			radeon_show_cursor(crtc);
+		radeon_show_cursor(crtc);
 
 		radeon_lock_cursor(crtc, false);
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 2593b11..d8319da 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1080,6 +1080,22 @@
 }
 
 /**
+ * Determine a sensible default GART size according to ASIC family.
+ *
+ * @family ASIC family name
+ */
+static int radeon_gart_size_auto(enum radeon_family family)
+{
+	/* default to a larger gart size on newer asics */
+	if (family >= CHIP_TAHITI)
+		return 2048;
+	else if (family >= CHIP_RV770)
+		return 1024;
+	else
+		return 512;
+}
+
+/**
  * radeon_check_arguments - validate module params
  *
  * @rdev: radeon_device pointer
@@ -1097,27 +1113,17 @@
 	}
 
 	if (radeon_gart_size == -1) {
-		/* default to a larger gart size on newer asics */
-		if (rdev->family >= CHIP_RV770)
-			radeon_gart_size = 1024;
-		else
-			radeon_gart_size = 512;
+		radeon_gart_size = radeon_gart_size_auto(rdev->family);
 	}
 	/* gtt size must be power of two and greater or equal to 32M */
 	if (radeon_gart_size < 32) {
 		dev_warn(rdev->dev, "gart size (%d) too small\n",
 				radeon_gart_size);
-		if (rdev->family >= CHIP_RV770)
-			radeon_gart_size = 1024;
-		else
-			radeon_gart_size = 512;
+		radeon_gart_size = radeon_gart_size_auto(rdev->family);
 	} else if (!radeon_check_pot_argument(radeon_gart_size)) {
 		dev_warn(rdev->dev, "gart size (%d) must be a power of 2\n",
 				radeon_gart_size);
-		if (rdev->family >= CHIP_RV770)
-			radeon_gart_size = 1024;
-		else
-			radeon_gart_size = 512;
+		radeon_gart_size = radeon_gart_size_auto(rdev->family);
 	}
 	rdev->mc.gtt_size = (uint64_t)radeon_gart_size << 20;
 
@@ -1572,11 +1578,21 @@
 		drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
 	}
 
-	/* unpin the front buffers */
+	/* unpin the front buffers and cursors */
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+		struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
 		struct radeon_framebuffer *rfb = to_radeon_framebuffer(crtc->primary->fb);
 		struct radeon_bo *robj;
 
+		if (radeon_crtc->cursor_bo) {
+			struct radeon_bo *robj = gem_to_radeon_bo(radeon_crtc->cursor_bo);
+			r = radeon_bo_reserve(robj, false);
+			if (r == 0) {
+				radeon_bo_unpin(robj);
+				radeon_bo_unreserve(robj);
+			}
+		}
+
 		if (rfb == NULL || rfb->obj == NULL) {
 			continue;
 		}
@@ -1639,6 +1655,7 @@
 {
 	struct drm_connector *connector;
 	struct radeon_device *rdev = dev->dev_private;
+	struct drm_crtc *crtc;
 	int r;
 
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
@@ -1678,6 +1695,27 @@
 
 	radeon_restore_bios_scratch_regs(rdev);
 
+	/* pin cursors */
+	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+		struct radeon_crtc *radeon_crtc = to_radeon_crtc(crtc);
+
+		if (radeon_crtc->cursor_bo) {
+			struct radeon_bo *robj = gem_to_radeon_bo(radeon_crtc->cursor_bo);
+			r = radeon_bo_reserve(robj, false);
+			if (r == 0) {
+				/* Only 27 bit offset for legacy cursor */
+				r = radeon_bo_pin_restricted(robj,
+							     RADEON_GEM_DOMAIN_VRAM,
+							     ASIC_IS_AVIVO(rdev) ?
+							     0 : 1 << 27,
+							     &radeon_crtc->cursor_addr);
+				if (r != 0)
+					DRM_ERROR("Failed to pin cursor BO (%d)\n", r);
+				radeon_bo_unreserve(robj);
+			}
+		}
+	}
+
 	/* init dig PHYs, disp eng pll */
 	if (rdev->is_atom_bios) {
 		radeon_atom_encoder_init(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_fb.c b/drivers/gpu/drm/radeon/radeon_fb.c
index 634793e..aeb6767 100644
--- a/drivers/gpu/drm/radeon/radeon_fb.c
+++ b/drivers/gpu/drm/radeon/radeon_fb.c
@@ -257,6 +257,7 @@
 	}
 
 	info->par = rfbdev;
+	info->skip_vt_switch = true;
 
 	ret = radeon_framebuffer_init(rdev->ddev, &rfbdev->rfb, &mode_cmd, gobj);
 	if (ret) {
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 5450fa9..c4777c8 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -260,8 +260,10 @@
 			}
 		}
 	}
-	mb();
-	radeon_gart_tlb_flush(rdev);
+	if (rdev->gart.ptr) {
+		mb();
+		radeon_gart_tlb_flush(rdev);
+	}
 }
 
 /**
@@ -306,8 +308,10 @@
 			page_base += RADEON_GPU_PAGE_SIZE;
 		}
 	}
-	mb();
-	radeon_gart_tlb_flush(rdev);
+	if (rdev->gart.ptr) {
+		mb();
+		radeon_gart_tlb_flush(rdev);
+	}
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index ac3c131..3dcc573 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -36,6 +36,7 @@
 	if (robj) {
 		if (robj->gem_base.import_attach)
 			drm_prime_gem_destroy(&robj->gem_base, robj->tbo.sg);
+		radeon_mn_unregister(robj);
 		radeon_bo_unref(&robj);
 	}
 }
@@ -428,7 +429,6 @@
 int radeon_gem_busy_ioctl(struct drm_device *dev, void *data,
 			  struct drm_file *filp)
 {
-	struct radeon_device *rdev = dev->dev_private;
 	struct drm_radeon_gem_busy *args = data;
 	struct drm_gem_object *gobj;
 	struct radeon_bo *robj;
@@ -440,10 +440,16 @@
 		return -ENOENT;
 	}
 	robj = gem_to_radeon_bo(gobj);
-	r = radeon_bo_wait(robj, &cur_placement, true);
+
+	r = reservation_object_test_signaled_rcu(robj->tbo.resv, true);
+	if (r == 0)
+		r = -EBUSY;
+	else
+		r = 0;
+
+	cur_placement = ACCESS_ONCE(robj->tbo.mem.mem_type);
 	args->domain = radeon_mem_type_to_domain(cur_placement);
 	drm_gem_object_unreference_unlocked(gobj);
-	r = radeon_gem_handle_lockup(rdev, r);
 	return r;
 }
 
@@ -471,6 +477,7 @@
 		r = ret;
 
 	/* Flush HDP cache via MMIO if necessary */
+	cur_placement = ACCESS_ONCE(robj->tbo.mem.mem_type);
 	if (rdev->asic->mmio_hdp_flush &&
 	    radeon_mem_type_to_domain(cur_placement) == RADEON_GEM_DOMAIN_VRAM)
 		robj->rdev->asic->mmio_hdp_flush(rdev);
diff --git a/drivers/gpu/drm/radeon/radeon_irq_kms.c b/drivers/gpu/drm/radeon/radeon_irq_kms.c
index 1162bfa..171d3e4 100644
--- a/drivers/gpu/drm/radeon/radeon_irq_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_irq_kms.c
@@ -79,6 +79,11 @@
 	struct drm_mode_config *mode_config = &dev->mode_config;
 	struct drm_connector *connector;
 
+	/* we can race here at startup, some boards seem to trigger
+	 * hotplug irqs when they shouldn't. */
+	if (!rdev->mode_info.mode_config_initialized)
+		return;
+
 	mutex_lock(&mode_config->mutex);
 	if (mode_config->num_connector) {
 		list_for_each_entry(connector, &mode_config->connector_list, head)
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 6de5459..aecc3e3 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -237,7 +237,6 @@
 	int offset;
 	bool last_buffer_filled_status;
 	int id;
-	struct r600_audio_pin *pin;
 };
 
 struct radeon_mode_info {
@@ -343,7 +342,6 @@
 	int max_cursor_width;
 	int max_cursor_height;
 	uint32_t legacy_display_base_addr;
-	uint32_t legacy_cursor_offset;
 	enum radeon_rmx_type rmx_type;
 	u8 h_border;
 	u8 v_border;
@@ -440,6 +438,7 @@
 	uint8_t backlight_level;
 	int panel_mode;
 	struct radeon_afmt *afmt;
+	struct r600_audio_pin *pin;
 	int active_mst_links;
 };
 
diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 318165d..6763627 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -75,7 +75,6 @@
 	bo = container_of(tbo, struct radeon_bo, tbo);
 
 	radeon_update_memory_usage(bo, bo->tbo.mem.mem_type, -1);
-	radeon_mn_unregister(bo);
 
 	mutex_lock(&bo->rdev->gem.mutex);
 	list_del_init(&bo->list);
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index ec10533..48d97c0 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -493,38 +493,35 @@
 	}
 
 	if (bo_va->it.start || bo_va->it.last) {
-		spin_lock(&vm->status_lock);
-		if (list_empty(&bo_va->vm_status)) {
-			/* add a clone of the bo_va to clear the old address */
-			struct radeon_bo_va *tmp;
-			spin_unlock(&vm->status_lock);
-			tmp = kzalloc(sizeof(struct radeon_bo_va), GFP_KERNEL);
-			if (!tmp) {
-				mutex_unlock(&vm->mutex);
-				r = -ENOMEM;
-				goto error_unreserve;
-			}
-			tmp->it.start = bo_va->it.start;
-			tmp->it.last = bo_va->it.last;
-			tmp->vm = vm;
-			tmp->bo = radeon_bo_ref(bo_va->bo);
-			spin_lock(&vm->status_lock);
-			list_add(&tmp->vm_status, &vm->freed);
+		/* add a clone of the bo_va to clear the old address */
+		struct radeon_bo_va *tmp;
+		tmp = kzalloc(sizeof(struct radeon_bo_va), GFP_KERNEL);
+		if (!tmp) {
+			mutex_unlock(&vm->mutex);
+			r = -ENOMEM;
+			goto error_unreserve;
 		}
-		spin_unlock(&vm->status_lock);
+		tmp->it.start = bo_va->it.start;
+		tmp->it.last = bo_va->it.last;
+		tmp->vm = vm;
+		tmp->bo = radeon_bo_ref(bo_va->bo);
 
 		interval_tree_remove(&bo_va->it, &vm->va);
+		spin_lock(&vm->status_lock);
 		bo_va->it.start = 0;
 		bo_va->it.last = 0;
+		list_del_init(&bo_va->vm_status);
+		list_add(&tmp->vm_status, &vm->freed);
+		spin_unlock(&vm->status_lock);
 	}
 
 	if (soffset || eoffset) {
+		spin_lock(&vm->status_lock);
 		bo_va->it.start = soffset;
 		bo_va->it.last = eoffset - 1;
-		interval_tree_insert(&bo_va->it, &vm->va);
-		spin_lock(&vm->status_lock);
 		list_add(&bo_va->vm_status, &vm->cleared);
 		spin_unlock(&vm->status_lock);
+		interval_tree_insert(&bo_va->it, &vm->va);
 	}
 
 	bo_va->flags = flags;
@@ -1158,7 +1155,8 @@
 
 	list_for_each_entry(bo_va, &bo->va, bo_list) {
 		spin_lock(&bo_va->vm->status_lock);
-		if (list_empty(&bo_va->vm_status))
+		if (list_empty(&bo_va->vm_status) &&
+		    (bo_va->it.start || bo_va->it.last))
 			list_add(&bo_va->vm_status, &bo_va->vm->invalidated);
 		spin_unlock(&bo_va->vm->status_lock);
 	}
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 26388b5..07037e3 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -6466,23 +6466,27 @@
 		case 1: /* D1 vblank/vline */
 			switch (src_data) {
 			case 0: /* D1 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[0]) {
-						drm_handle_vblank(rdev->ddev, 0);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[0]))
-						radeon_crtc_handle_vblank(rdev, 0);
-					rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D1 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[0]) {
+					drm_handle_vblank(rdev->ddev, 0);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[0]))
+					radeon_crtc_handle_vblank(rdev, 0);
+				rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D1 vblank\n");
+
 				break;
 			case 1: /* D1 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D1 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & LB_D1_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int &= ~LB_D1_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D1 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -6492,23 +6496,27 @@
 		case 2: /* D2 vblank/vline */
 			switch (src_data) {
 			case 0: /* D2 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[1]) {
-						drm_handle_vblank(rdev->ddev, 1);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[1]))
-						radeon_crtc_handle_vblank(rdev, 1);
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D2 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[1]) {
+					drm_handle_vblank(rdev->ddev, 1);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[1]))
+					radeon_crtc_handle_vblank(rdev, 1);
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D2 vblank\n");
+
 				break;
 			case 1: /* D2 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D2 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & LB_D2_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~LB_D2_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D2 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -6518,23 +6526,27 @@
 		case 3: /* D3 vblank/vline */
 			switch (src_data) {
 			case 0: /* D3 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[2]) {
-						drm_handle_vblank(rdev->ddev, 2);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[2]))
-						radeon_crtc_handle_vblank(rdev, 2);
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D3 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[2]) {
+					drm_handle_vblank(rdev->ddev, 2);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[2]))
+					radeon_crtc_handle_vblank(rdev, 2);
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D3 vblank\n");
+
 				break;
 			case 1: /* D3 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D3 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & LB_D3_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~LB_D3_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D3 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -6544,23 +6556,27 @@
 		case 4: /* D4 vblank/vline */
 			switch (src_data) {
 			case 0: /* D4 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[3]) {
-						drm_handle_vblank(rdev->ddev, 3);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[3]))
-						radeon_crtc_handle_vblank(rdev, 3);
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D4 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[3]) {
+					drm_handle_vblank(rdev->ddev, 3);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[3]))
+					radeon_crtc_handle_vblank(rdev, 3);
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D4 vblank\n");
+
 				break;
 			case 1: /* D4 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D4 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & LB_D4_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~LB_D4_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D4 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -6570,23 +6586,27 @@
 		case 5: /* D5 vblank/vline */
 			switch (src_data) {
 			case 0: /* D5 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[4]) {
-						drm_handle_vblank(rdev->ddev, 4);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[4]))
-						radeon_crtc_handle_vblank(rdev, 4);
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D5 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[4]) {
+					drm_handle_vblank(rdev->ddev, 4);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[4]))
+					radeon_crtc_handle_vblank(rdev, 4);
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D5 vblank\n");
+
 				break;
 			case 1: /* D5 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D5 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & LB_D5_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~LB_D5_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D5 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -6596,23 +6616,27 @@
 		case 6: /* D6 vblank/vline */
 			switch (src_data) {
 			case 0: /* D6 vblank */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VBLANK_INTERRUPT) {
-					if (rdev->irq.crtc_vblank_int[5]) {
-						drm_handle_vblank(rdev->ddev, 5);
-						rdev->pm.vblank_sync = true;
-						wake_up(&rdev->irq.vblank_queue);
-					}
-					if (atomic_read(&rdev->irq.pflip[5]))
-						radeon_crtc_handle_vblank(rdev, 5);
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VBLANK_INTERRUPT;
-					DRM_DEBUG("IH: D6 vblank\n");
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VBLANK_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				if (rdev->irq.crtc_vblank_int[5]) {
+					drm_handle_vblank(rdev->ddev, 5);
+					rdev->pm.vblank_sync = true;
+					wake_up(&rdev->irq.vblank_queue);
 				}
+				if (atomic_read(&rdev->irq.pflip[5]))
+					radeon_crtc_handle_vblank(rdev, 5);
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VBLANK_INTERRUPT;
+				DRM_DEBUG("IH: D6 vblank\n");
+
 				break;
 			case 1: /* D6 vline */
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VLINE_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VLINE_INTERRUPT;
-					DRM_DEBUG("IH: D6 vline\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & LB_D6_VLINE_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~LB_D6_VLINE_INTERRUPT;
+				DRM_DEBUG("IH: D6 vline\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
@@ -6632,88 +6656,112 @@
 		case 42: /* HPD hotplug */
 			switch (src_data) {
 			case 0:
-				if (rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD1\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD1\n");
+
 				break;
 			case 1:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD2\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD2\n");
+
 				break;
 			case 2:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD3\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD3\n");
+
 				break;
 			case 3:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD4\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD4\n");
+
 				break;
 			case 4:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD5\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD5\n");
+
 				break;
 			case 5:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_INTERRUPT;
-					queue_hotplug = true;
-					DRM_DEBUG("IH: HPD6\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_INTERRUPT;
+				queue_hotplug = true;
+				DRM_DEBUG("IH: HPD6\n");
+
 				break;
 			case 6:
-				if (rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 1\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int & DC_HPD1_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int &= ~DC_HPD1_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 1\n");
+
 				break;
 			case 7:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 2\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont & DC_HPD2_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont &= ~DC_HPD2_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 2\n");
+
 				break;
 			case 8:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 3\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont2 & DC_HPD3_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont2 &= ~DC_HPD3_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 3\n");
+
 				break;
 			case 9:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 4\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont3 & DC_HPD4_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont3 &= ~DC_HPD4_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 4\n");
+
 				break;
 			case 10:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 5\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont4 & DC_HPD5_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont4 &= ~DC_HPD5_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 5\n");
+
 				break;
 			case 11:
-				if (rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT) {
-					rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_RX_INTERRUPT;
-					queue_dp = true;
-					DRM_DEBUG("IH: HPD_RX 6\n");
-				}
+				if (!(rdev->irq.stat_regs.evergreen.disp_int_cont5 & DC_HPD6_RX_INTERRUPT))
+					DRM_DEBUG("IH: IH event w/o asserted irq bit?\n");
+
+				rdev->irq.stat_regs.evergreen.disp_int_cont5 &= ~DC_HPD6_RX_INTERRUPT;
+				queue_dp = true;
+				DRM_DEBUG("IH: HPD_RX 6\n");
+
 				break;
 			default:
 				DRM_DEBUG("Unhandled interrupt: %d %d\n", src_id, src_data);
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index 1dbdf32..787cd8f 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2926,6 +2926,7 @@
 	/* PITCAIRN - https://bugs.freedesktop.org/show_bug.cgi?id=76490 */
 	{ PCI_VENDOR_ID_ATI, 0x6810, 0x1462, 0x3036, 0, 120000 },
 	{ PCI_VENDOR_ID_ATI, 0x6811, 0x174b, 0xe271, 0, 120000 },
+	{ PCI_VENDOR_ID_ATI, 0x6810, 0x174b, 0xe271, 85000, 90000 },
 	{ 0, 0, 0, 0 },
 };
 
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
index 01b558f..9a0c291 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c
@@ -555,7 +555,6 @@
 	.probe = rockchip_drm_platform_probe,
 	.remove = rockchip_drm_platform_remove,
 	.driver = {
-		.owner = THIS_MODULE,
 		.name = "rockchip-drm",
 		.of_match_table = rockchip_drm_dt_ids,
 		.pm = &rockchip_drm_pm_ops,
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
index 77d5289..002645b 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
@@ -162,7 +162,8 @@
 	struct rockchip_drm_private *private = dev->dev_private;
 	struct drm_fb_helper *fb_helper = &private->fbdev_helper;
 
-	drm_fb_helper_hotplug_event(fb_helper);
+	if (fb_helper)
+		drm_fb_helper_hotplug_event(fb_helper);
 }
 
 static const struct drm_mode_config_funcs rockchip_drm_mode_config_funcs = {
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
index eb2282c..eba5f8a 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_gem.c
@@ -54,55 +54,56 @@
 		       &rk_obj->dma_attrs);
 }
 
+static int rockchip_drm_gem_object_mmap(struct drm_gem_object *obj,
+					struct vm_area_struct *vma)
+
+{
+	int ret;
+	struct rockchip_gem_object *rk_obj = to_rockchip_obj(obj);
+	struct drm_device *drm = obj->dev;
+
+	/*
+	 * dma_alloc_attrs() allocated a struct page table for rk_obj, so clear
+	 * VM_PFNMAP flag that was set by drm_gem_mmap_obj()/drm_gem_mmap().
+	 */
+	vma->vm_flags &= ~VM_PFNMAP;
+
+	ret = dma_mmap_attrs(drm->dev, vma, rk_obj->kvaddr, rk_obj->dma_addr,
+			     obj->size, &rk_obj->dma_attrs);
+	if (ret)
+		drm_gem_vm_close(vma);
+
+	return ret;
+}
+
 int rockchip_gem_mmap_buf(struct drm_gem_object *obj,
 			  struct vm_area_struct *vma)
 {
-	struct rockchip_gem_object *rk_obj = to_rockchip_obj(obj);
 	struct drm_device *drm = obj->dev;
-	unsigned long vm_size;
+	int ret;
 
-	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
-	vm_size = vma->vm_end - vma->vm_start;
+	mutex_lock(&drm->struct_mutex);
+	ret = drm_gem_mmap_obj(obj, obj->size, vma);
+	mutex_unlock(&drm->struct_mutex);
+	if (ret)
+		return ret;
 
-	if (vm_size > obj->size)
-		return -EINVAL;
-
-	return dma_mmap_attrs(drm->dev, vma, rk_obj->kvaddr, rk_obj->dma_addr,
-			     obj->size, &rk_obj->dma_attrs);
+	return rockchip_drm_gem_object_mmap(obj, vma);
 }
 
 /* drm driver mmap file operations */
 int rockchip_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 {
-	struct drm_file *priv = filp->private_data;
-	struct drm_device *dev = priv->minor->dev;
 	struct drm_gem_object *obj;
-	struct drm_vma_offset_node *node;
 	int ret;
 
-	if (drm_device_is_unplugged(dev))
-		return -ENODEV;
+	ret = drm_gem_mmap(filp, vma);
+	if (ret)
+		return ret;
 
-	mutex_lock(&dev->struct_mutex);
+	obj = vma->vm_private_data;
 
-	node = drm_vma_offset_exact_lookup(dev->vma_offset_manager,
-					   vma->vm_pgoff,
-					   vma_pages(vma));
-	if (!node) {
-		mutex_unlock(&dev->struct_mutex);
-		DRM_ERROR("failed to find vma node.\n");
-		return -EINVAL;
-	} else if (!drm_vma_node_is_allowed(node, filp)) {
-		mutex_unlock(&dev->struct_mutex);
-		return -EACCES;
-	}
-
-	obj = container_of(node, struct drm_gem_object, vma_node);
-	ret = rockchip_gem_mmap_buf(obj, vma);
-
-	mutex_unlock(&dev->struct_mutex);
-
-	return ret;
+	return rockchip_drm_gem_object_mmap(obj, vma);
 }
 
 struct rockchip_gem_object *
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index dc65161..34b78e7 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -170,6 +170,7 @@
 
 	struct vop_reg enable;
 	struct vop_reg format;
+	struct vop_reg rb_swap;
 	struct vop_reg act_info;
 	struct vop_reg dsp_info;
 	struct vop_reg dsp_st;
@@ -199,8 +200,12 @@
 static const uint32_t formats_01[] = {
 	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ABGR8888,
 	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
 	DRM_FORMAT_RGB565,
+	DRM_FORMAT_BGR565,
 	DRM_FORMAT_NV12,
 	DRM_FORMAT_NV16,
 	DRM_FORMAT_NV24,
@@ -209,8 +214,12 @@
 static const uint32_t formats_234[] = {
 	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ABGR8888,
 	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
 	DRM_FORMAT_RGB565,
+	DRM_FORMAT_BGR565,
 };
 
 static const struct vop_win_phy win01_data = {
@@ -218,6 +227,7 @@
 	.nformats = ARRAY_SIZE(formats_01),
 	.enable = VOP_REG(WIN0_CTRL0, 0x1, 0),
 	.format = VOP_REG(WIN0_CTRL0, 0x7, 1),
+	.rb_swap = VOP_REG(WIN0_CTRL0, 0x1, 12),
 	.act_info = VOP_REG(WIN0_ACT_INFO, 0x1fff1fff, 0),
 	.dsp_info = VOP_REG(WIN0_DSP_INFO, 0x0fff0fff, 0),
 	.dsp_st = VOP_REG(WIN0_DSP_ST, 0x1fff1fff, 0),
@@ -234,6 +244,7 @@
 	.nformats = ARRAY_SIZE(formats_234),
 	.enable = VOP_REG(WIN2_CTRL0, 0x1, 0),
 	.format = VOP_REG(WIN2_CTRL0, 0x7, 1),
+	.rb_swap = VOP_REG(WIN2_CTRL0, 0x1, 12),
 	.dsp_info = VOP_REG(WIN2_DSP_INFO0, 0x0fff0fff, 0),
 	.dsp_st = VOP_REG(WIN2_DSP_ST0, 0x1fff1fff, 0),
 	.yrgb_mst = VOP_REG(WIN2_MST0, 0xffffffff, 0),
@@ -242,15 +253,6 @@
 	.dst_alpha_ctl = VOP_REG(WIN2_DST_ALPHA_CTRL, 0xff, 0),
 };
 
-static const struct vop_win_phy cursor_data = {
-	.data_formats = formats_234,
-	.nformats = ARRAY_SIZE(formats_234),
-	.enable = VOP_REG(HWC_CTRL0, 0x1, 0),
-	.format = VOP_REG(HWC_CTRL0, 0x7, 1),
-	.dsp_st = VOP_REG(HWC_DSP_ST, 0x1fff1fff, 0),
-	.yrgb_mst = VOP_REG(HWC_MST, 0xffffffff, 0),
-};
-
 static const struct vop_ctrl ctrl_data = {
 	.standby = VOP_REG(SYS_CTRL, 0x1, 22),
 	.gate_en = VOP_REG(SYS_CTRL, 0x1, 23),
@@ -282,14 +284,14 @@
 /*
  * Note: rk3288 has a dedicated 'cursor' window, however, that window requires
  * special support to get alpha blending working.  For now, just use overlay
- * window 1 for the drm cursor.
+ * window 3 for the drm cursor.
+ *
  */
 static const struct vop_win_data rk3288_vop_win_data[] = {
 	{ .base = 0x00, .phy = &win01_data, .type = DRM_PLANE_TYPE_PRIMARY },
-	{ .base = 0x40, .phy = &win01_data, .type = DRM_PLANE_TYPE_CURSOR },
+	{ .base = 0x40, .phy = &win01_data, .type = DRM_PLANE_TYPE_OVERLAY },
 	{ .base = 0x00, .phy = &win23_data, .type = DRM_PLANE_TYPE_OVERLAY },
-	{ .base = 0x50, .phy = &win23_data, .type = DRM_PLANE_TYPE_OVERLAY },
-	{ .base = 0x00, .phy = &cursor_data, .type = DRM_PLANE_TYPE_OVERLAY },
+	{ .base = 0x50, .phy = &win23_data, .type = DRM_PLANE_TYPE_CURSOR },
 };
 
 static const struct vop_data rk3288_vop = {
@@ -352,15 +354,32 @@
 	}
 }
 
+static bool has_rb_swapped(uint32_t format)
+{
+	switch (format) {
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
+	case DRM_FORMAT_BGR888:
+	case DRM_FORMAT_BGR565:
+		return true;
+	default:
+		return false;
+	}
+}
+
 static enum vop_data_format vop_convert_format(uint32_t format)
 {
 	switch (format) {
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_XBGR8888:
+	case DRM_FORMAT_ABGR8888:
 		return VOP_FMT_ARGB8888;
 	case DRM_FORMAT_RGB888:
+	case DRM_FORMAT_BGR888:
 		return VOP_FMT_RGB888;
 	case DRM_FORMAT_RGB565:
+	case DRM_FORMAT_BGR565:
 		return VOP_FMT_RGB565;
 	case DRM_FORMAT_NV12:
 		return VOP_FMT_YUV420SP;
@@ -378,6 +397,7 @@
 {
 	switch (format) {
 	case DRM_FORMAT_ARGB8888:
+	case DRM_FORMAT_ABGR8888:
 		return true;
 	default:
 		return false;
@@ -588,6 +608,7 @@
 	enum vop_data_format format;
 	uint32_t val;
 	bool is_alpha;
+	bool rb_swap;
 	bool visible;
 	int ret;
 	struct drm_rect dest = {
@@ -621,6 +642,7 @@
 		return 0;
 
 	is_alpha = is_alpha_support(fb->pixel_format);
+	rb_swap = has_rb_swapped(fb->pixel_format);
 	format = vop_convert_format(fb->pixel_format);
 	if (format < 0)
 		return format;
@@ -689,6 +711,7 @@
 	val = (dsp_sty - 1) << 16;
 	val |= (dsp_stx - 1) & 0xffff;
 	VOP_WIN_SET(vop, win, dsp_st, val);
+	VOP_WIN_SET(vop, win, rb_swap, rb_swap);
 
 	if (is_alpha) {
 		VOP_WIN_SET(vop, win, dst_alpha_ctl,
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 882cccd..ac6fe40 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -490,7 +490,8 @@
 	else if (boot_cpu_data.x86 > 3)
 		tmp = pgprot_noncached(tmp);
 #endif
-#if defined(__ia64__) || defined(__arm__) || defined(__powerpc__)
+#if defined(__ia64__) || defined(__arm__) || defined(__aarch64__) || \
+    defined(__powerpc__)
 	if (caching_flags & TTM_PL_FLAG_WC)
 		tmp = pgprot_writecombine(tmp);
 	else
diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index 3077f15..624d941 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -963,14 +963,13 @@
 	} else {
 		pool->npages_free += count;
 		list_splice(&ttm_dma->pages_list, &pool->free_list);
-		npages = count;
-		if (pool->npages_free > _manager->options.max_size) {
+		/*
+		 * Wait to have at at least NUM_PAGES_TO_ALLOC number of pages
+		 * to free in order to minimize calls to set_memory_wb().
+		 */
+		if (pool->npages_free >= (_manager->options.max_size +
+					  NUM_PAGES_TO_ALLOC))
 			npages = pool->npages_free - _manager->options.max_size;
-			/* free at least NUM_PAGES_TO_ALLOC number of pages
-			 * to reduce calls to set_memory_wb */
-			if (npages < NUM_PAGES_TO_ALLOC)
-				npages = NUM_PAGES_TO_ALLOC;
-		}
 	}
 	spin_unlock_irqrestore(&pool->lock, irq_flags);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 654c8da..97ad3bc 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -2492,7 +2492,7 @@
 	ret = ttm_eu_reserve_buffers(&ticket, &sw_context->validate_nodes,
 				     true, NULL);
 	if (unlikely(ret != 0))
-		goto out_err;
+		goto out_err_nores;
 
 	ret = vmw_validate_buffers(dev_priv, sw_context);
 	if (unlikely(ret != 0))
@@ -2536,6 +2536,7 @@
 	vmw_resource_relocations_free(&sw_context->res_relocations);
 
 	vmw_fifo_commit(dev_priv, command_size);
+	mutex_unlock(&dev_priv->binding_mutex);
 
 	vmw_query_bo_switch_commit(dev_priv, sw_context);
 	ret = vmw_execbuf_fence_commands(file_priv, dev_priv,
@@ -2551,7 +2552,6 @@
 		DRM_ERROR("Fence submission error. Syncing.\n");
 
 	vmw_resource_list_unreserve(&sw_context->resource_list, false);
-	mutex_unlock(&dev_priv->binding_mutex);
 
 	ttm_eu_fence_buffer_objects(&ticket, &sw_context->validate_nodes,
 				    (void *) fence);
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 6d2f39d..00f2058 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -1107,6 +1107,9 @@
 		return ret;
 	}
 
+	for (i = 0; i < IPU_NUM_IRQS; i += 32)
+		ipu_cm_write(ipu, 0, IPU_INT_CTRL(i / 32));
+
 	for (i = 0; i < IPU_NUM_IRQS; i += 32) {
 		gc = irq_get_domain_generic_chip(ipu->domain, i);
 		gc->reg_base = ipu->cm_reg;
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index f822fd2..884d82f 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -546,6 +546,12 @@
 		.driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS),
 		.driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI),
+		.driver_data = APPLE_HAS_FN },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ISO),
+		.driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_JIS),
+		.driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI),
 		.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO),
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 157c627..e6fce23 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1782,6 +1782,9 @@
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ISO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ISO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_JIS) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS) },
@@ -2463,6 +2466,9 @@
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ISO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ISO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_JIS) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) },
 	{ }
diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c
index 3318de6..a2dbbbe 100644
--- a/drivers/hid/hid-cp2112.c
+++ b/drivers/hid/hid-cp2112.c
@@ -356,6 +356,8 @@
 	struct cp2112_force_read_report report;
 	int ret;
 
+	if (size > sizeof(dev->read_data))
+		size = sizeof(dev->read_data);
 	report.report = CP2112_DATA_READ_FORCE_SEND;
 	report.length = cpu_to_be16(size);
 
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index b04b082..b3b225b 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -142,6 +142,9 @@
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI	0x0290
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO	0x0291
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS	0x0292
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI	0x0272
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_ISO		0x0273
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_JIS		0x0274
 #define USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY	0x030a
 #define USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY	0x030b
 #define USB_DEVICE_ID_APPLE_IRCONTROL	0x8240
diff --git a/drivers/hid/hid-input.c b/drivers/hid/hid-input.c
index 3511bbab..e3c6364 100644
--- a/drivers/hid/hid-input.c
+++ b/drivers/hid/hid-input.c
@@ -462,12 +462,15 @@
 
 static void hidinput_cleanup_battery(struct hid_device *dev)
 {
+	const struct power_supply_desc *psy_desc;
+
 	if (!dev->battery)
 		return;
 
+	psy_desc = dev->battery->desc;
 	power_supply_unregister(dev->battery);
-	kfree(dev->battery->desc->name);
-	kfree(dev->battery->desc);
+	kfree(psy_desc->name);
+	kfree(psy_desc);
 	dev->battery = NULL;
 }
 #else  /* !CONFIG_HID_BATTERY_STRENGTH */
diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
index 6a9b05b..7c81125 100644
--- a/drivers/hid/hid-multitouch.c
+++ b/drivers/hid/hid-multitouch.c
@@ -778,9 +778,16 @@
 	/*
 	 * some egalax touchscreens have "application == HID_DG_TOUCHSCREEN"
 	 * for the stylus.
+	 * The check for mt_report_id ensures we don't process
+	 * HID_DG_CONTACTCOUNT from the pen report as it is outside the physical
+	 * collection, but within the report ID.
 	 */
 	if (field->physical == HID_DG_STYLUS)
 		return 0;
+	else if ((field->physical == 0) &&
+		 (field->report->id != td->mt_report_id) &&
+		 (td->mt_report_id != -1))
+		return 0;
 
 	if (field->application == HID_DG_TOUCHSCREEN ||
 	    field->application == HID_DG_TOUCHPAD)
diff --git a/drivers/hid/hid-uclogic.c b/drivers/hid/hid-uclogic.c
index 9416731..b905d50 100644
--- a/drivers/hid/hid-uclogic.c
+++ b/drivers/hid/hid-uclogic.c
@@ -858,7 +858,7 @@
 	for (p = drvdata->rdesc;
 	     p <= drvdata->rdesc + drvdata->rsize - 4;) {
 		if (p[0] == 0xFE && p[1] == 0xED && p[2] == 0x1D &&
-		    p[3] < sizeof(params)) {
+		    p[3] < ARRAY_SIZE(params)) {
 			v = params[p[3]];
 			put_unaligned(cpu_to_le32(v), (s32 *)p);
 			p += 4;
diff --git a/drivers/hid/usbhid/hid-quirks.c b/drivers/hid/usbhid/hid-quirks.c
index 53e7de7..20f9a65 100644
--- a/drivers/hid/usbhid/hid-quirks.c
+++ b/drivers/hid/usbhid/hid-quirks.c
@@ -87,6 +87,9 @@
 	{ USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C05A, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_LOGITECH_MOUSE_C06A, HID_QUIRK_ALWAYS_POLL },
 	{ USB_VENDOR_ID_MGE, USB_DEVICE_ID_MGE_UPS, HID_QUIRK_NOGET },
+	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_SURFACE_PRO_2, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_2, HID_QUIRK_NO_INIT_REPORTS },
+	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TOUCH_COVER_2, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_TYPE_COVER_3_JP, HID_QUIRK_NO_INIT_REPORTS },
 	{ USB_VENDOR_ID_MICROSOFT, USB_DEVICE_ID_MS_POWER_COVER, HID_QUIRK_NO_INIT_REPORTS },
diff --git a/drivers/hid/wacom_sys.c b/drivers/hid/wacom_sys.c
index 4c0ffca..01b937e 100644
--- a/drivers/hid/wacom_sys.c
+++ b/drivers/hid/wacom_sys.c
@@ -1271,17 +1271,52 @@
 	pad_input_dev = NULL;
 	wacom_wac->pad_registered = false;
 fail_register_pad_input:
-	input_unregister_device(touch_input_dev);
+	if (touch_input_dev)
+		input_unregister_device(touch_input_dev);
 	wacom_wac->touch_input = NULL;
 	wacom_wac->touch_registered = false;
 fail_register_touch_input:
-	input_unregister_device(pen_input_dev);
+	if (pen_input_dev)
+		input_unregister_device(pen_input_dev);
 	wacom_wac->pen_input = NULL;
 	wacom_wac->pen_registered = false;
 fail_register_pen_input:
 	return error;
 }
 
+/*
+ * Not all devices report physical dimensions from HID.
+ * Compute the default from hardcoded logical dimension
+ * and resolution before driver overwrites them.
+ */
+static void wacom_set_default_phy(struct wacom_features *features)
+{
+	if (features->x_resolution) {
+		features->x_phy = (features->x_max * 100) /
+					features->x_resolution;
+		features->y_phy = (features->y_max * 100) /
+					features->y_resolution;
+	}
+}
+
+static void wacom_calculate_res(struct wacom_features *features)
+{
+	/* set unit to "100th of a mm" for devices not reported by HID */
+	if (!features->unit) {
+		features->unit = 0x11;
+		features->unitExpo = -3;
+	}
+
+	features->x_resolution = wacom_calc_hid_res(features->x_max,
+						    features->x_phy,
+						    features->unit,
+						    features->unitExpo);
+	features->y_resolution = wacom_calc_hid_res(features->y_max,
+						    features->y_phy,
+						    features->unit,
+						    features->unitExpo);
+}
+
 static void wacom_wireless_work(struct work_struct *work)
 {
 	struct wacom *wacom = container_of(work, struct wacom, work);
@@ -1339,6 +1374,8 @@
 		if (wacom_wac1->features.type != INTUOSHT &&
 		    wacom_wac1->features.type != BAMBOO_PT)
 			wacom_wac1->features.device_type |= WACOM_DEVICETYPE_PAD;
+		wacom_set_default_phy(&wacom_wac1->features);
+		wacom_calculate_res(&wacom_wac1->features);
 		snprintf(wacom_wac1->pen_name, WACOM_NAME_MAX, "%s (WL) Pen",
 			 wacom_wac1->features.name);
 		snprintf(wacom_wac1->pad_name, WACOM_NAME_MAX, "%s (WL) Pad",
@@ -1357,7 +1394,9 @@
 			wacom_wac2->features =
 				*((struct wacom_features *)id->driver_data);
 			wacom_wac2->features.pktlen = WACOM_PKGLEN_BBTOUCH3;
+			wacom_set_default_phy(&wacom_wac2->features);
 			wacom_wac2->features.x_max = wacom_wac2->features.y_max = 4096;
+			wacom_calculate_res(&wacom_wac2->features);
 			snprintf(wacom_wac2->touch_name, WACOM_NAME_MAX,
 				 "%s (WL) Finger",wacom_wac2->features.name);
 			snprintf(wacom_wac2->pad_name, WACOM_NAME_MAX,
@@ -1405,39 +1444,6 @@
 	}
 }
 
-/*
- * Not all devices report physical dimensions from HID.
- * Compute the default from hardcoded logical dimension
- * and resolution before driver overwrites them.
- */
-static void wacom_set_default_phy(struct wacom_features *features)
-{
-	if (features->x_resolution) {
-		features->x_phy = (features->x_max * 100) /
-					features->x_resolution;
-		features->y_phy = (features->y_max * 100) /
-					features->y_resolution;
-	}
-}
-
-static void wacom_calculate_res(struct wacom_features *features)
-{
-	/* set unit to "100th of a mm" for devices not reported by HID */
-	if (!features->unit) {
-		features->unit = 0x11;
-		features->unitExpo = -3;
-	}
-
-	features->x_resolution = wacom_calc_hid_res(features->x_max,
-						    features->x_phy,
-						    features->unit,
-						    features->unitExpo);
-	features->y_resolution = wacom_calc_hid_res(features->y_max,
-						    features->y_phy,
-						    features->unit,
-						    features->unitExpo);
-}
-
 static size_t wacom_compute_pktlen(struct hid_device *hdev)
 {
 	struct hid_report_enum *report_enum;
diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
index 232da89..0d24423 100644
--- a/drivers/hid/wacom_wac.c
+++ b/drivers/hid/wacom_wac.c
@@ -2213,6 +2213,9 @@
 			features->x_max = 4096;
 			features->y_max = 4096;
 		}
+		else if (features->pktlen == WACOM_PKGLEN_BBTOUCH) {
+			features->device_type |= WACOM_DEVICETYPE_PAD;
+		}
 	}
 
 	/*
diff --git a/drivers/hwmon/dell-smm-hwmon.c b/drivers/hwmon/dell-smm-hwmon.c
index 37c16af..c848789 100644
--- a/drivers/hwmon/dell-smm-hwmon.c
+++ b/drivers/hwmon/dell-smm-hwmon.c
@@ -929,6 +929,21 @@
 
 MODULE_DEVICE_TABLE(dmi, i8k_dmi_table);
 
+static struct dmi_system_id i8k_blacklist_dmi_table[] __initdata = {
+	{
+		/*
+		 * CPU fan speed going up and down on Dell Studio XPS 8100
+		 * for unknown reasons.
+		 */
+		.ident = "Dell Studio XPS 8100",
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Studio XPS 8100"),
+		},
+	},
+	{ }
+};
+
 /*
  * Probe for the presence of a supported laptop.
  */
@@ -940,7 +955,8 @@
 	/*
 	 * Get DMI information
 	 */
-	if (!dmi_check_system(i8k_dmi_table)) {
+	if (!dmi_check_system(i8k_dmi_table) ||
+	    dmi_check_system(i8k_blacklist_dmi_table)) {
 		if (!ignore_dmi && !force)
 			return -ENODEV;
 
diff --git a/drivers/hwmon/g762.c b/drivers/hwmon/g762.c
index 9b55e67..85d106f 100644
--- a/drivers/hwmon/g762.c
+++ b/drivers/hwmon/g762.c
@@ -582,6 +582,7 @@
 	{ .compatible = "gmt,g763" },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, g762_dt_match);
 
 /*
  * Grab clock (a required property), enable it, get (fixed) clock frequency
diff --git a/drivers/hwmon/nct7802.c b/drivers/hwmon/nct7802.c
index 28fcb2e..fbfc02b 100644
--- a/drivers/hwmon/nct7802.c
+++ b/drivers/hwmon/nct7802.c
@@ -195,7 +195,7 @@
 }
 
 static int nct7802_write_voltage(struct nct7802_data *data, int nr, int index,
-				 unsigned int voltage)
+				 unsigned long voltage)
 {
 	int shift = 8 - REG_VOLTAGE_LIMIT_MSB_SHIFT[index - 1][nr];
 	int err;
diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index b77b82f..08ff89d 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -412,8 +412,9 @@
 	return sprintf(buf, "%d\n", val);
 }
 
-static ssize_t store_mode(struct device *dev, struct device_attribute *devattr,
-			  const char *buf, size_t count)
+static ssize_t store_enable(struct device *dev,
+			    struct device_attribute *devattr,
+			    const char *buf, size_t count)
 {
 	int index = to_sensor_dev_attr(devattr)->index;
 	struct nct7904_data *data = dev_get_drvdata(dev);
@@ -422,18 +423,18 @@
 
 	if (kstrtoul(buf, 10, &val) < 0)
 		return -EINVAL;
-	if (val > 1 || (val && !data->fan_mode[index]))
+	if (val < 1 || val > 2 || (val == 2 && !data->fan_mode[index]))
 		return -EINVAL;
 
 	ret = nct7904_write_reg(data, BANK_3, FANCTL1_FMR_REG + index,
-				val ? data->fan_mode[index] : 0);
+				val == 2 ? data->fan_mode[index] : 0);
 
 	return ret ? ret : count;
 }
 
-/* Return 0 for manual mode or 1 for SmartFan mode */
-static ssize_t show_mode(struct device *dev,
-			 struct device_attribute *devattr, char *buf)
+/* Return 1 for manual mode or 2 for SmartFan mode */
+static ssize_t show_enable(struct device *dev,
+			   struct device_attribute *devattr, char *buf)
 {
 	int index = to_sensor_dev_attr(devattr)->index;
 	struct nct7904_data *data = dev_get_drvdata(dev);
@@ -443,36 +444,36 @@
 	if (val < 0)
 		return val;
 
-	return sprintf(buf, "%d\n", val ? 1 : 0);
+	return sprintf(buf, "%d\n", val ? 2 : 1);
 }
 
 /* 2 attributes per channel: pwm and mode */
-static SENSOR_DEVICE_ATTR(fan1_pwm, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(pwm1, S_IRUGO | S_IWUSR,
 			show_pwm, store_pwm, 0);
-static SENSOR_DEVICE_ATTR(fan1_mode, S_IRUGO | S_IWUSR,
-			show_mode, store_mode, 0);
-static SENSOR_DEVICE_ATTR(fan2_pwm, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR,
+			show_enable, store_enable, 0);
+static SENSOR_DEVICE_ATTR(pwm2, S_IRUGO | S_IWUSR,
 			show_pwm, store_pwm, 1);
-static SENSOR_DEVICE_ATTR(fan2_mode, S_IRUGO | S_IWUSR,
-			show_mode, store_mode, 1);
-static SENSOR_DEVICE_ATTR(fan3_pwm, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(pwm2_enable, S_IRUGO | S_IWUSR,
+			show_enable, store_enable, 1);
+static SENSOR_DEVICE_ATTR(pwm3, S_IRUGO | S_IWUSR,
 			show_pwm, store_pwm, 2);
-static SENSOR_DEVICE_ATTR(fan3_mode, S_IRUGO | S_IWUSR,
-			show_mode, store_mode, 2);
-static SENSOR_DEVICE_ATTR(fan4_pwm, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(pwm3_enable, S_IRUGO | S_IWUSR,
+			show_enable, store_enable, 2);
+static SENSOR_DEVICE_ATTR(pwm4, S_IRUGO | S_IWUSR,
 			show_pwm, store_pwm, 3);
-static SENSOR_DEVICE_ATTR(fan4_mode, S_IRUGO | S_IWUSR,
-			show_mode, store_mode, 3);
+static SENSOR_DEVICE_ATTR(pwm4_enable, S_IRUGO | S_IWUSR,
+			show_enable, store_enable, 3);
 
 static struct attribute *nct7904_fanctl_attrs[] = {
-	&sensor_dev_attr_fan1_pwm.dev_attr.attr,
-	&sensor_dev_attr_fan1_mode.dev_attr.attr,
-	&sensor_dev_attr_fan2_pwm.dev_attr.attr,
-	&sensor_dev_attr_fan2_mode.dev_attr.attr,
-	&sensor_dev_attr_fan3_pwm.dev_attr.attr,
-	&sensor_dev_attr_fan3_mode.dev_attr.attr,
-	&sensor_dev_attr_fan4_pwm.dev_attr.attr,
-	&sensor_dev_attr_fan4_mode.dev_attr.attr,
+	&sensor_dev_attr_pwm1.dev_attr.attr,
+	&sensor_dev_attr_pwm1_enable.dev_attr.attr,
+	&sensor_dev_attr_pwm2.dev_attr.attr,
+	&sensor_dev_attr_pwm2_enable.dev_attr.attr,
+	&sensor_dev_attr_pwm3.dev_attr.attr,
+	&sensor_dev_attr_pwm3_enable.dev_attr.attr,
+	&sensor_dev_attr_pwm4.dev_attr.attr,
+	&sensor_dev_attr_pwm4_enable.dev_attr.attr,
 	NULL
 };
 
@@ -574,6 +575,7 @@
 	{"nct7904", 0},
 	{}
 };
+MODULE_DEVICE_TABLE(i2c, nct7904_id);
 
 static struct i2c_driver nct7904_driver = {
 	.class = I2C_CLASS_HWMON,
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index 35ac237..577d58d 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -633,6 +633,7 @@
 config I2C_MT65XX
 	tristate "MediaTek I2C adapter"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
+	depends on HAS_DMA
 	help
 	  This selects the MediaTek(R) Integrated Inter Circuit bus driver
 	  for MT65xx and MT81xx.
diff --git a/drivers/i2c/busses/i2c-bfin-twi.c b/drivers/i2c/busses/i2c-bfin-twi.c
index af162b4..025686d 100644
--- a/drivers/i2c/busses/i2c-bfin-twi.c
+++ b/drivers/i2c/busses/i2c-bfin-twi.c
@@ -692,7 +692,7 @@
 
 	platform_set_drvdata(pdev, iface);
 
-	dev_info(&pdev->dev, "Blackfin BF5xx on-chip I2C TWI Contoller, "
+	dev_info(&pdev->dev, "Blackfin BF5xx on-chip I2C TWI Controller, "
 		"regs_base@%p\n", iface->regs_base);
 
 	return 0;
@@ -735,6 +735,6 @@
 module_exit(i2c_bfin_twi_exit);
 
 MODULE_AUTHOR("Bryan Wu, Sonic Zhang");
-MODULE_DESCRIPTION("Blackfin BF5xx on-chip I2C TWI Contoller Driver");
+MODULE_DESCRIPTION("Blackfin BF5xx on-chip I2C TWI Controller Driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:i2c-bfin-twi");
diff --git a/drivers/i2c/busses/i2c-jz4780.c b/drivers/i2c/busses/i2c-jz4780.c
index 19b2d68..f325663 100644
--- a/drivers/i2c/busses/i2c-jz4780.c
+++ b/drivers/i2c/busses/i2c-jz4780.c
@@ -764,12 +764,15 @@
 	if (IS_ERR(i2c->clk))
 		return PTR_ERR(i2c->clk);
 
-	clk_prepare_enable(i2c->clk);
+	ret = clk_prepare_enable(i2c->clk);
+	if (ret)
+		return ret;
 
-	if (of_property_read_u32(pdev->dev.of_node, "clock-frequency",
-				 &clk_freq)) {
+	ret = of_property_read_u32(pdev->dev.of_node, "clock-frequency",
+				   &clk_freq);
+	if (ret) {
 		dev_err(&pdev->dev, "clock-frequency not specified in DT");
-		return clk_freq;
+		goto err;
 	}
 
 	i2c->speed = clk_freq / 1000;
@@ -790,10 +793,8 @@
 	i2c->irq = platform_get_irq(pdev, 0);
 	ret = devm_request_irq(&pdev->dev, i2c->irq, jz4780_i2c_irq, 0,
 			       dev_name(&pdev->dev), i2c);
-	if (ret) {
-		ret = -ENODEV;
+	if (ret)
 		goto err;
-	}
 
 	ret = i2c_add_adapter(&i2c->adap);
 	if (ret < 0) {
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index d1c22e3..fc9bf7f 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -1247,7 +1247,14 @@
 	u32 reg;
 
 	reg = omap_i2c_read_reg(dev, OMAP_I2C_SYSTEST_REG);
+	/* enable test mode */
 	reg |= OMAP_I2C_SYSTEST_ST_EN;
+	/* select SDA/SCL IO mode */
+	reg |= 3 << OMAP_I2C_SYSTEST_TMODE_SHIFT;
+	/* set SCL to high-impedance state (reset value is 0) */
+	reg |= OMAP_I2C_SYSTEST_SCL_O;
+	/* set SDA to high-impedance state (reset value is 0) */
+	reg |= OMAP_I2C_SYSTEST_SDA_O;
 	omap_i2c_write_reg(dev, OMAP_I2C_SYSTEST_REG, reg);
 }
 
@@ -1257,7 +1264,11 @@
 	u32 reg;
 
 	reg = omap_i2c_read_reg(dev, OMAP_I2C_SYSTEST_REG);
+	/* restore reset values */
 	reg &= ~OMAP_I2C_SYSTEST_ST_EN;
+	reg &= ~OMAP_I2C_SYSTEST_TMODE_MASK;
+	reg &= ~OMAP_I2C_SYSTEST_SCL_O;
+	reg &= ~OMAP_I2C_SYSTEST_SDA_O;
 	omap_i2c_write_reg(dev, OMAP_I2C_SYSTEST_REG, reg);
 }
 
diff --git a/drivers/i2c/busses/i2c-xgene-slimpro.c b/drivers/i2c/busses/i2c-xgene-slimpro.c
index dcca707..1c9cb65 100644
--- a/drivers/i2c/busses/i2c-xgene-slimpro.c
+++ b/drivers/i2c/busses/i2c-xgene-slimpro.c
@@ -419,6 +419,7 @@
 	rc = i2c_add_adapter(adapter);
 	if (rc) {
 		dev_err(&pdev->dev, "Adapter registeration failed\n");
+		mbox_free_channel(ctx->mbox_chan);
 		return rc;
 	}
 
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index 069a41f..c83e4d1 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -567,6 +567,9 @@
 	if (bri->prepare_recovery)
 		bri->prepare_recovery(adap);
 
+	bri->set_scl(adap, val);
+	ndelay(RECOVERY_NDELAY);
+
 	/*
 	 * By this time SCL is high, as we need to give 9 falling-rising edges
 	 */
@@ -597,7 +600,6 @@
 
 int i2c_generic_scl_recovery(struct i2c_adapter *adap)
 {
-	adap->bus_recovery_info->set_scl(adap, 1);
 	return i2c_generic_recovery(adap);
 }
 EXPORT_SYMBOL_GPL(i2c_generic_scl_recovery);
@@ -1012,6 +1014,8 @@
  */
 void i2c_unregister_device(struct i2c_client *client)
 {
+	if (client->dev.of_node)
+		of_node_clear_flag(client->dev.of_node, OF_POPULATED);
 	device_unregister(&client->dev);
 }
 EXPORT_SYMBOL_GPL(i2c_unregister_device);
@@ -1320,8 +1324,11 @@
 
 	dev_dbg(&adap->dev, "of_i2c: walking child nodes\n");
 
-	for_each_available_child_of_node(adap->dev.of_node, node)
+	for_each_available_child_of_node(adap->dev.of_node, node) {
+		if (of_node_test_and_set_flag(node, OF_POPULATED))
+			continue;
 		of_i2c_register_device(adap, node);
+	}
 }
 
 static int of_dev_node_match(struct device *dev, void *data)
@@ -1333,13 +1340,17 @@
 struct i2c_client *of_find_i2c_device_by_node(struct device_node *node)
 {
 	struct device *dev;
+	struct i2c_client *client;
 
-	dev = bus_find_device(&i2c_bus_type, NULL, node,
-					 of_dev_node_match);
+	dev = bus_find_device(&i2c_bus_type, NULL, node, of_dev_node_match);
 	if (!dev)
 		return NULL;
 
-	return i2c_verify_client(dev);
+	client = i2c_verify_client(dev);
+	if (!client)
+		put_device(dev);
+
+	return client;
 }
 EXPORT_SYMBOL(of_find_i2c_device_by_node);
 
@@ -1347,13 +1358,17 @@
 struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node)
 {
 	struct device *dev;
+	struct i2c_adapter *adapter;
 
-	dev = bus_find_device(&i2c_bus_type, NULL, node,
-					 of_dev_node_match);
+	dev = bus_find_device(&i2c_bus_type, NULL, node, of_dev_node_match);
 	if (!dev)
 		return NULL;
 
-	return i2c_verify_adapter(dev);
+	adapter = i2c_verify_adapter(dev);
+	if (!adapter)
+		put_device(dev);
+
+	return adapter;
 }
 EXPORT_SYMBOL(of_find_i2c_adapter_by_node);
 #else
@@ -1853,6 +1868,11 @@
 		if (adap == NULL)
 			return NOTIFY_OK;	/* not for us */
 
+		if (of_node_test_and_set_flag(rd->dn, OF_POPULATED)) {
+			put_device(&adap->dev);
+			return NOTIFY_OK;
+		}
+
 		client = of_i2c_register_device(adap, rd->dn);
 		put_device(&adap->dev);
 
@@ -1863,6 +1883,10 @@
 		}
 		break;
 	case OF_RECONFIG_CHANGE_REMOVE:
+		/* already depopulated? */
+		if (!of_node_check_flag(rd->dn, OF_POPULATED))
+			return NOTIFY_OK;
+
 		/* find our device by node */
 		client = of_find_i2c_device_by_node(rd->dn);
 		if (client == NULL)
diff --git a/drivers/i2c/i2c-slave-eeprom.c b/drivers/i2c/i2c-slave-eeprom.c
index 8223746..1da4496 100644
--- a/drivers/i2c/i2c-slave-eeprom.c
+++ b/drivers/i2c/i2c-slave-eeprom.c
@@ -80,9 +80,6 @@
 	struct eeprom_data *eeprom;
 	unsigned long flags;
 
-	if (off + count > attr->size)
-		return -EFBIG;
-
 	eeprom = dev_get_drvdata(container_of(kobj, struct device, kobj));
 
 	spin_lock_irqsave(&eeprom->buffer_lock, flags);
@@ -98,9 +95,6 @@
 	struct eeprom_data *eeprom;
 	unsigned long flags;
 
-	if (off + count > attr->size)
-		return -EFBIG;
-
 	eeprom = dev_get_drvdata(container_of(kobj, struct device, kobj));
 
 	spin_lock_irqsave(&eeprom->buffer_lock, flags);
diff --git a/drivers/iio/accel/bmc150-accel.c b/drivers/iio/accel/bmc150-accel.c
index 4e70f51..cc5a357 100644
--- a/drivers/iio/accel/bmc150-accel.c
+++ b/drivers/iio/accel/bmc150-accel.c
@@ -1464,7 +1464,7 @@
 {
 	int i;
 
-	for (i = from; i >= 0; i++) {
+	for (i = from; i >= 0; i--) {
 		if (data->triggers[i].indio_trig) {
 			iio_trigger_unregister(data->triggers[i].indio_trig);
 			data->triggers[i].indio_trig = NULL;
diff --git a/drivers/iio/accel/mma8452.c b/drivers/iio/accel/mma8452.c
index e8e2077..13ea1ea 100644
--- a/drivers/iio/accel/mma8452.c
+++ b/drivers/iio/accel/mma8452.c
@@ -557,21 +557,21 @@
 	if (src & MMA8452_TRANSIENT_SRC_XTRANSE)
 		iio_push_event(indio_dev,
 			       IIO_MOD_EVENT_CODE(IIO_ACCEL, 0, IIO_MOD_X,
-						  IIO_EV_TYPE_THRESH,
+						  IIO_EV_TYPE_MAG,
 						  IIO_EV_DIR_RISING),
 			       ts);
 
 	if (src & MMA8452_TRANSIENT_SRC_YTRANSE)
 		iio_push_event(indio_dev,
 			       IIO_MOD_EVENT_CODE(IIO_ACCEL, 0, IIO_MOD_Y,
-						  IIO_EV_TYPE_THRESH,
+						  IIO_EV_TYPE_MAG,
 						  IIO_EV_DIR_RISING),
 			       ts);
 
 	if (src & MMA8452_TRANSIENT_SRC_ZTRANSE)
 		iio_push_event(indio_dev,
 			       IIO_MOD_EVENT_CODE(IIO_ACCEL, 0, IIO_MOD_Z,
-						  IIO_EV_TYPE_THRESH,
+						  IIO_EV_TYPE_MAG,
 						  IIO_EV_DIR_RISING),
 			       ts);
 }
@@ -644,7 +644,7 @@
 
 static const struct iio_event_spec mma8452_transient_event[] = {
 	{
-		.type = IIO_EV_TYPE_THRESH,
+		.type = IIO_EV_TYPE_MAG,
 		.dir = IIO_EV_DIR_RISING,
 		.mask_separate = BIT(IIO_EV_INFO_ENABLE),
 		.mask_shared_by_type = BIT(IIO_EV_INFO_VALUE) |
diff --git a/drivers/iio/adc/Kconfig b/drivers/iio/adc/Kconfig
index 7c55658..eb0cd89 100644
--- a/drivers/iio/adc/Kconfig
+++ b/drivers/iio/adc/Kconfig
@@ -153,8 +153,7 @@
 
 config CC10001_ADC
 	tristate "Cosmic Circuits 10001 ADC driver"
-	depends on HAVE_CLK || REGULATOR
-	depends on HAS_IOMEM
+	depends on HAS_IOMEM && HAVE_CLK && REGULATOR
 	select IIO_BUFFER
 	select IIO_TRIGGERED_BUFFER
 	help
diff --git a/drivers/iio/adc/at91_adc.c b/drivers/iio/adc/at91_adc.c
index 8a0eb4a..7b40925 100644
--- a/drivers/iio/adc/at91_adc.c
+++ b/drivers/iio/adc/at91_adc.c
@@ -182,7 +182,7 @@
 	u8	ts_pen_detect_sensitivity;
 
 	/* startup time calculate function */
-	u32 (*calc_startup_ticks)(u8 startup_time, u32 adc_clk_khz);
+	u32 (*calc_startup_ticks)(u32 startup_time, u32 adc_clk_khz);
 
 	u8	num_channels;
 	struct at91_adc_reg_desc registers;
@@ -201,7 +201,7 @@
 	u8			num_channels;
 	void __iomem		*reg_base;
 	struct at91_adc_reg_desc *registers;
-	u8			startup_time;
+	u32			startup_time;
 	u8			sample_hold_time;
 	bool			sleep_mode;
 	struct iio_trigger	**trig;
@@ -779,7 +779,7 @@
 	return ret;
 }
 
-static u32 calc_startup_ticks_9260(u8 startup_time, u32 adc_clk_khz)
+static u32 calc_startup_ticks_9260(u32 startup_time, u32 adc_clk_khz)
 {
 	/*
 	 * Number of ticks needed to cover the startup time of the ADC
@@ -790,7 +790,7 @@
 	return round_up((startup_time * adc_clk_khz / 1000) - 1, 8) / 8;
 }
 
-static u32 calc_startup_ticks_9x5(u8 startup_time, u32 adc_clk_khz)
+static u32 calc_startup_ticks_9x5(u32 startup_time, u32 adc_clk_khz)
 {
 	/*
 	 * For sama5d3x and at91sam9x5, the formula changes to:
diff --git a/drivers/iio/adc/mcp320x.c b/drivers/iio/adc/mcp320x.c
index 8d9c9b9..d819823 100644
--- a/drivers/iio/adc/mcp320x.c
+++ b/drivers/iio/adc/mcp320x.c
@@ -299,6 +299,8 @@
 	indio_dev->channels = chip_info->channels;
 	indio_dev->num_channels = chip_info->num_channels;
 
+	adc->chip_info = chip_info;
+
 	adc->transfer[0].tx_buf = &adc->tx_buf;
 	adc->transfer[0].len = sizeof(adc->tx_buf);
 	adc->transfer[1].rx_buf = adc->rx_buf;
diff --git a/drivers/iio/adc/rockchip_saradc.c b/drivers/iio/adc/rockchip_saradc.c
index 8d4e019..9c311c1 100644
--- a/drivers/iio/adc/rockchip_saradc.c
+++ b/drivers/iio/adc/rockchip_saradc.c
@@ -349,3 +349,7 @@
 };
 
 module_platform_driver(rockchip_saradc_driver);
+
+MODULE_AUTHOR("Heiko Stuebner <heiko@sntech.de>");
+MODULE_DESCRIPTION("Rockchip SARADC driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iio/adc/twl4030-madc.c b/drivers/iio/adc/twl4030-madc.c
index 06f4792..ebe415f 100644
--- a/drivers/iio/adc/twl4030-madc.c
+++ b/drivers/iio/adc/twl4030-madc.c
@@ -833,7 +833,8 @@
 	irq = platform_get_irq(pdev, 0);
 	ret = devm_request_threaded_irq(&pdev->dev, irq, NULL,
 				   twl4030_madc_threaded_irq_handler,
-				   IRQF_TRIGGER_RISING, "twl4030_madc", madc);
+				   IRQF_TRIGGER_RISING | IRQF_ONESHOT,
+				   "twl4030_madc", madc);
 	if (ret) {
 		dev_err(&pdev->dev, "could not request irq\n");
 		goto err_i2c;
diff --git a/drivers/iio/adc/vf610_adc.c b/drivers/iio/adc/vf610_adc.c
index 480f335..819632b 100644
--- a/drivers/iio/adc/vf610_adc.c
+++ b/drivers/iio/adc/vf610_adc.c
@@ -635,7 +635,7 @@
 	struct vf610_adc *info = iio_priv(indio_dev);
 
 	if ((readval == NULL) ||
-		(!(reg % 4) || (reg > VF610_REG_ADC_PCTL)))
+		((reg % 4) || (reg > VF610_REG_ADC_PCTL)))
 		return -EINVAL;
 
 	*readval = readl(info->regs + reg);
diff --git a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
index 610fc98..5955110 100644
--- a/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
+++ b/drivers/iio/common/hid-sensors/hid-sensor-trigger.c
@@ -36,6 +36,8 @@
 	s32 poll_value = 0;
 
 	if (state) {
+		if (!atomic_read(&st->user_requested_state))
+			return 0;
 		if (sensor_hub_device_open(st->hsdev))
 			return -EIO;
 
@@ -52,8 +54,12 @@
 
 		poll_value = hid_sensor_read_poll_value(st);
 	} else {
-		if (!atomic_dec_and_test(&st->data_ready))
+		int val;
+
+		val = atomic_dec_if_positive(&st->data_ready);
+		if (val < 0)
 			return 0;
+
 		sensor_hub_device_close(st->hsdev);
 		state_val = hid_sensor_get_usage_index(st->hsdev,
 			st->power_state.report_id,
@@ -92,9 +98,11 @@
 
 int hid_sensor_power_state(struct hid_sensor_common *st, bool state)
 {
+
 #ifdef CONFIG_PM
 	int ret;
 
+	atomic_set(&st->user_requested_state, state);
 	if (state)
 		ret = pm_runtime_get_sync(&st->pdev->dev);
 	else {
@@ -109,6 +117,7 @@
 
  	return 0;
 #else
+	atomic_set(&st->user_requested_state, state);
 	return _hid_sensor_power_state(st, state);
 #endif
 }
diff --git a/drivers/iio/dac/ad5624r_spi.c b/drivers/iio/dac/ad5624r_spi.c
index 61bb9d4..e98428d 100644
--- a/drivers/iio/dac/ad5624r_spi.c
+++ b/drivers/iio/dac/ad5624r_spi.c
@@ -22,7 +22,7 @@
 #include "ad5624r.h"
 
 static int ad5624r_spi_write(struct spi_device *spi,
-			     u8 cmd, u8 addr, u16 val, u8 len)
+			     u8 cmd, u8 addr, u16 val, u8 shift)
 {
 	u32 data;
 	u8 msg[3];
@@ -35,7 +35,7 @@
 	 * 14-, 12-bit input code followed by 0, 2, or 4 don't care bits,
 	 * for the AD5664R, AD5644R, and AD5624R, respectively.
 	 */
-	data = (0 << 22) | (cmd << 19) | (addr << 16) | (val << (16 - len));
+	data = (0 << 22) | (cmd << 19) | (addr << 16) | (val << shift);
 	msg[0] = data >> 16;
 	msg[1] = data >> 8;
 	msg[2] = data;
diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
index 17d4bb1..65ce868 100644
--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
+++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_core.c
@@ -431,6 +431,23 @@
 	return -EINVAL;
 }
 
+static int inv_write_raw_get_fmt(struct iio_dev *indio_dev,
+				 struct iio_chan_spec const *chan, long mask)
+{
+	switch (mask) {
+	case IIO_CHAN_INFO_SCALE:
+		switch (chan->type) {
+		case IIO_ANGL_VEL:
+			return IIO_VAL_INT_PLUS_NANO;
+		default:
+			return IIO_VAL_INT_PLUS_MICRO;
+		}
+	default:
+		return IIO_VAL_INT_PLUS_MICRO;
+	}
+
+	return -EINVAL;
+}
 static int inv_mpu6050_write_accel_scale(struct inv_mpu6050_state *st, int val)
 {
 	int result, i;
@@ -696,6 +713,7 @@
 	.driver_module = THIS_MODULE,
 	.read_raw = &inv_mpu6050_read_raw,
 	.write_raw = &inv_mpu6050_write_raw,
+	.write_raw_get_fmt = &inv_write_raw_get_fmt,
 	.attrs = &inv_attribute_group,
 	.validate_trigger = inv_mpu6050_validate_trigger,
 };
diff --git a/drivers/iio/light/Kconfig b/drivers/iio/light/Kconfig
index e6198b7..a5c5925 100644
--- a/drivers/iio/light/Kconfig
+++ b/drivers/iio/light/Kconfig
@@ -188,6 +188,7 @@
 config LTR501
 	tristate "LTR-501ALS-01 light sensor"
 	depends on I2C
+	select REGMAP_I2C
 	select IIO_BUFFER
 	select IIO_TRIGGERED_BUFFER
 	help
@@ -201,6 +202,7 @@
 config STK3310
 	tristate "STK3310 ALS and proximity sensor"
 	depends on I2C
+	select REGMAP_I2C
 	help
 	 Say yes here to get support for the Sensortek STK3310 ambient light
 	 and proximity sensor. The STK3311 model is also supported by this
diff --git a/drivers/iio/light/cm3323.c b/drivers/iio/light/cm3323.c
index 869033e..a1d4905 100644
--- a/drivers/iio/light/cm3323.c
+++ b/drivers/iio/light/cm3323.c
@@ -123,7 +123,7 @@
 	for (i = 0; i < ARRAY_SIZE(cm3323_int_time); i++) {
 		if (val == cm3323_int_time[i].val &&
 		    val2 == cm3323_int_time[i].val2) {
-			reg_conf = data->reg_conf;
+			reg_conf = data->reg_conf & ~CM3323_CONF_IT_MASK;
 			reg_conf |= i << CM3323_CONF_IT_SHIFT;
 
 			ret = i2c_smbus_write_word_data(data->client,
diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c
index 1ef7d37..b5a0e66 100644
--- a/drivers/iio/light/ltr501.c
+++ b/drivers/iio/light/ltr501.c
@@ -1302,7 +1302,7 @@
 	if (ret < 0)
 		return ret;
 
-	data->als_contr = ret | data->chip_info->als_mode_active;
+	data->als_contr = status | data->chip_info->als_mode_active;
 
 	ret = regmap_read(data->regmap, LTR501_PS_CONTR, &status);
 	if (ret < 0)
diff --git a/drivers/iio/light/stk3310.c b/drivers/iio/light/stk3310.c
index fee4297..11a027a 100644
--- a/drivers/iio/light/stk3310.c
+++ b/drivers/iio/light/stk3310.c
@@ -43,7 +43,6 @@
 #define STK3311_CHIP_ID_VAL			0x1D
 #define STK3310_PSINT_EN			0x01
 #define STK3310_PS_MAX_VAL			0xFFFF
-#define STK3310_THRESH_MAX			0xFFFF
 
 #define STK3310_DRIVER_NAME			"stk3310"
 #define STK3310_REGMAP_NAME			"stk3310_regmap"
@@ -84,15 +83,13 @@
 				REG_FIELD(STK3310_REG_FLAG, 4, 4);
 static const struct reg_field stk3310_reg_field_flag_nf =
 				REG_FIELD(STK3310_REG_FLAG, 0, 0);
-/*
- * Maximum PS values with regard to scale. Used to export the 'inverse'
- * PS value (high values for far objects, low values for near objects).
- */
+
+/* Estimate maximum proximity values with regard to measurement scale. */
 static const int stk3310_ps_max[4] = {
-	STK3310_PS_MAX_VAL / 64,
-	STK3310_PS_MAX_VAL / 16,
-	STK3310_PS_MAX_VAL /  4,
-	STK3310_PS_MAX_VAL,
+	STK3310_PS_MAX_VAL / 640,
+	STK3310_PS_MAX_VAL / 160,
+	STK3310_PS_MAX_VAL /  40,
+	STK3310_PS_MAX_VAL /  10
 };
 
 static const int stk3310_scale_table[][2] = {
@@ -128,14 +125,14 @@
 	/* Proximity event */
 	{
 		.type = IIO_EV_TYPE_THRESH,
-		.dir = IIO_EV_DIR_FALLING,
+		.dir = IIO_EV_DIR_RISING,
 		.mask_separate = BIT(IIO_EV_INFO_VALUE) |
 				 BIT(IIO_EV_INFO_ENABLE),
 	},
 	/* Out-of-proximity event */
 	{
 		.type = IIO_EV_TYPE_THRESH,
-		.dir = IIO_EV_DIR_RISING,
+		.dir = IIO_EV_DIR_FALLING,
 		.mask_separate = BIT(IIO_EV_INFO_VALUE) |
 				 BIT(IIO_EV_INFO_ENABLE),
 	},
@@ -203,25 +200,18 @@
 			      int *val, int *val2)
 {
 	u8 reg;
-	u16 buf;
+	__be16 buf;
 	int ret;
-	unsigned int index;
 	struct stk3310_data *data = iio_priv(indio_dev);
 
 	if (info != IIO_EV_INFO_VALUE)
 		return -EINVAL;
 
-	/*
-	 * Only proximity interrupts are implemented at the moment.
-	 * Since we're inverting proximity values, the sensor's 'high'
-	 * threshold will become our 'low' threshold, associated with
-	 * 'near' events. Similarly, the sensor's 'low' threshold will
-	 * be our 'high' threshold, associated with 'far' events.
-	 */
+	/* Only proximity interrupts are implemented at the moment. */
 	if (dir == IIO_EV_DIR_RISING)
-		reg = STK3310_REG_THDL_PS;
-	else if (dir == IIO_EV_DIR_FALLING)
 		reg = STK3310_REG_THDH_PS;
+	else if (dir == IIO_EV_DIR_FALLING)
+		reg = STK3310_REG_THDL_PS;
 	else
 		return -EINVAL;
 
@@ -232,8 +222,7 @@
 		dev_err(&data->client->dev, "register read failed\n");
 		return ret;
 	}
-	regmap_field_read(data->reg_ps_gain, &index);
-	*val = swab16(stk3310_ps_max[index] - buf);
+	*val = be16_to_cpu(buf);
 
 	return IIO_VAL_INT;
 }
@@ -246,7 +235,7 @@
 			       int val, int val2)
 {
 	u8 reg;
-	u16 buf;
+	__be16 buf;
 	int ret;
 	unsigned int index;
 	struct stk3310_data *data = iio_priv(indio_dev);
@@ -257,13 +246,13 @@
 		return -EINVAL;
 
 	if (dir == IIO_EV_DIR_RISING)
-		reg = STK3310_REG_THDL_PS;
-	else if (dir == IIO_EV_DIR_FALLING)
 		reg = STK3310_REG_THDH_PS;
+	else if (dir == IIO_EV_DIR_FALLING)
+		reg = STK3310_REG_THDL_PS;
 	else
 		return -EINVAL;
 
-	buf = swab16(stk3310_ps_max[index] - val);
+	buf = cpu_to_be16(val);
 	ret = regmap_bulk_write(data->regmap, reg, &buf, 2);
 	if (ret < 0)
 		dev_err(&client->dev, "failed to set PS threshold!\n");
@@ -312,7 +301,7 @@
 			    int *val, int *val2, long mask)
 {
 	u8 reg;
-	u16 buf;
+	__be16 buf;
 	int ret;
 	unsigned int index;
 	struct stk3310_data *data = iio_priv(indio_dev);
@@ -333,15 +322,7 @@
 			mutex_unlock(&data->lock);
 			return ret;
 		}
-		*val = swab16(buf);
-		if (chan->type == IIO_PROXIMITY) {
-			/*
-			 * Invert the proximity data so we return low values
-			 * for close objects and high values for far ones.
-			 */
-			regmap_field_read(data->reg_ps_gain, &index);
-			*val = stk3310_ps_max[index] - *val;
-		}
+		*val = be16_to_cpu(buf);
 		mutex_unlock(&data->lock);
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_INT_TIME:
@@ -581,8 +562,8 @@
 	}
 	event = IIO_UNMOD_EVENT_CODE(IIO_PROXIMITY, 1,
 				     IIO_EV_TYPE_THRESH,
-				     (dir ? IIO_EV_DIR_RISING :
-					    IIO_EV_DIR_FALLING));
+				     (dir ? IIO_EV_DIR_FALLING :
+					    IIO_EV_DIR_RISING));
 	iio_push_event(indio_dev, event, data->timestamp);
 
 	/* Reset the interrupt flag */
@@ -627,13 +608,7 @@
 	if (ret < 0)
 		return ret;
 
-	ret = iio_device_register(indio_dev);
-	if (ret < 0) {
-		dev_err(&client->dev, "device_register failed\n");
-		stk3310_set_state(data, STK3310_STATE_STANDBY);
-	}
-
-	if (client->irq <= 0)
+	if (client->irq < 0)
 		client->irq = stk3310_gpio_probe(client);
 
 	if (client->irq >= 0) {
@@ -648,6 +623,12 @@
 					client->irq);
 	}
 
+	ret = iio_device_register(indio_dev);
+	if (ret < 0) {
+		dev_err(&client->dev, "device_register failed\n");
+		stk3310_set_state(data, STK3310_STATE_STANDBY);
+	}
+
 	return ret;
 }
 
diff --git a/drivers/iio/light/tcs3414.c b/drivers/iio/light/tcs3414.c
index 71c2bde..f8b1df0 100644
--- a/drivers/iio/light/tcs3414.c
+++ b/drivers/iio/light/tcs3414.c
@@ -185,7 +185,7 @@
 		if (val != 0)
 			return -EINVAL;
 		for (i = 0; i < ARRAY_SIZE(tcs3414_times); i++) {
-			if (val == tcs3414_times[i] * 1000) {
+			if (val2 == tcs3414_times[i] * 1000) {
 				data->timing &= ~TCS3414_INTEG_MASK;
 				data->timing |= i;
 				return i2c_smbus_write_byte_data(
diff --git a/drivers/iio/magnetometer/Kconfig b/drivers/iio/magnetometer/Kconfig
index dcadfc4..efb9350 100644
--- a/drivers/iio/magnetometer/Kconfig
+++ b/drivers/iio/magnetometer/Kconfig
@@ -90,6 +90,7 @@
 config BMC150_MAGN
 	tristate "Bosch BMC150 Magnetometer Driver"
 	depends on I2C
+	select REGMAP_I2C
 	select IIO_BUFFER
 	select IIO_TRIGGERED_BUFFER
 	help
diff --git a/drivers/iio/magnetometer/bmc150_magn.c b/drivers/iio/magnetometer/bmc150_magn.c
index d4c1788..1347a1f 100644
--- a/drivers/iio/magnetometer/bmc150_magn.c
+++ b/drivers/iio/magnetometer/bmc150_magn.c
@@ -706,11 +706,11 @@
 		goto err_poweroff;
 	}
 	if (chip_id != BMC150_MAGN_CHIP_ID_VAL) {
-		dev_err(&data->client->dev, "Invalid chip id 0x%x\n", ret);
+		dev_err(&data->client->dev, "Invalid chip id 0x%x\n", chip_id);
 		ret = -ENODEV;
 		goto err_poweroff;
 	}
-	dev_dbg(&data->client->dev, "Chip id %x\n", ret);
+	dev_dbg(&data->client->dev, "Chip id %x\n", chip_id);
 
 	preset = bmc150_magn_presets_table[BMC150_MAGN_DEFAULT_PRESET];
 	ret = bmc150_magn_set_odr(data, preset.odr);
diff --git a/drivers/iio/magnetometer/mmc35240.c b/drivers/iio/magnetometer/mmc35240.c
index 7a2ea71..706ebfd 100644
--- a/drivers/iio/magnetometer/mmc35240.c
+++ b/drivers/iio/magnetometer/mmc35240.c
@@ -84,10 +84,10 @@
 #define MMC35240_OTP_START_ADDR		0x1B
 
 enum mmc35240_resolution {
-	MMC35240_16_BITS_SLOW = 0, /* 100 Hz */
-	MMC35240_16_BITS_FAST,     /* 200 Hz */
-	MMC35240_14_BITS,          /* 333 Hz */
-	MMC35240_12_BITS,          /* 666 Hz */
+	MMC35240_16_BITS_SLOW = 0, /* 7.92 ms */
+	MMC35240_16_BITS_FAST,     /* 4.08 ms */
+	MMC35240_14_BITS,          /* 2.16 ms */
+	MMC35240_12_BITS,          /* 1.20 ms */
 };
 
 enum mmc35240_axis {
@@ -100,22 +100,22 @@
 	int sens[3]; /* sensitivity per X, Y, Z axis */
 	int nfo; /* null field output */
 } mmc35240_props_table[] = {
-	/* 16 bits, 100Hz ODR */
+	/* 16 bits, 125Hz ODR */
 	{
 		{1024, 1024, 1024},
 		32768,
 	},
-	/* 16 bits, 200Hz ODR */
+	/* 16 bits, 250Hz ODR */
 	{
 		{1024, 1024, 770},
 		32768,
 	},
-	/* 14 bits, 333Hz ODR */
+	/* 14 bits, 450Hz ODR */
 	{
 		{256, 256, 193},
 		8192,
 	},
-	/* 12 bits, 666Hz ODR */
+	/* 12 bits, 800Hz ODR */
 	{
 		{64, 64, 48},
 		2048,
@@ -133,9 +133,15 @@
 	int axis_scale[3];
 };
 
-static const int mmc35240_samp_freq[] = {100, 200, 333, 666};
+static const struct {
+	int val;
+	int val2;
+} mmc35240_samp_freq[] = { {1, 500000},
+			   {13, 0},
+			   {25, 0},
+			   {50, 0} };
 
-static IIO_CONST_ATTR_SAMP_FREQ_AVAIL("100 200 333 666");
+static IIO_CONST_ATTR_SAMP_FREQ_AVAIL("1.5 13 25 50");
 
 #define MMC35240_CHANNEL(_axis) { \
 	.type = IIO_MAGN, \
@@ -168,7 +174,8 @@
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(mmc35240_samp_freq); i++)
-		if (mmc35240_samp_freq[i] == val)
+		if (mmc35240_samp_freq[i].val == val &&
+		    mmc35240_samp_freq[i].val2 == val2)
 			return i;
 	return -EINVAL;
 }
@@ -195,8 +202,8 @@
 		coil_bit = MMC35240_CTRL0_RESET_BIT;
 
 	return regmap_update_bits(data->regmap, MMC35240_REG_CTRL0,
-				  MMC35240_CTRL0_REFILL_BIT,
-				  coil_bit);
+				  coil_bit, coil_bit);
+
 }
 
 static int mmc35240_init(struct mmc35240_data *data)
@@ -215,14 +222,15 @@
 
 	/*
 	 * make sure we restore sensor characteristics, by doing
-	 * a RESET/SET sequence
+	 * a SET/RESET sequence, the axis polarity being naturally
+	 * aligned after RESET
 	 */
-	ret = mmc35240_hw_set(data, false);
+	ret = mmc35240_hw_set(data, true);
 	if (ret < 0)
 		return ret;
 	usleep_range(MMC53240_WAIT_SET_RESET, MMC53240_WAIT_SET_RESET + 1);
 
-	ret = mmc35240_hw_set(data, true);
+	ret = mmc35240_hw_set(data, false);
 	if (ret < 0)
 		return ret;
 
@@ -378,9 +386,9 @@
 		if (i < 0 || i >= ARRAY_SIZE(mmc35240_samp_freq))
 			return -EINVAL;
 
-		*val = mmc35240_samp_freq[i];
-		*val2 = 0;
-		return IIO_VAL_INT;
+		*val = mmc35240_samp_freq[i].val;
+		*val2 = mmc35240_samp_freq[i].val2;
+		return IIO_VAL_INT_PLUS_MICRO;
 	default:
 		return -EINVAL;
 	}
@@ -496,6 +504,7 @@
 	}
 
 	data = iio_priv(indio_dev);
+	i2c_set_clientdata(client, indio_dev);
 	data->client = client;
 	data->regmap = regmap;
 	data->res = MMC35240_16_BITS_SLOW;
diff --git a/drivers/iio/proximity/sx9500.c b/drivers/iio/proximity/sx9500.c
index 2042e37..3d756bd 100644
--- a/drivers/iio/proximity/sx9500.c
+++ b/drivers/iio/proximity/sx9500.c
@@ -80,6 +80,7 @@
 #define SX9500_COMPSTAT_MASK		GENMASK(3, 0)
 
 #define SX9500_NUM_CHANNELS		4
+#define SX9500_CHAN_MASK		GENMASK(SX9500_NUM_CHANNELS - 1, 0)
 
 struct sx9500_data {
 	struct mutex mutex;
@@ -281,7 +282,7 @@
 	if (ret < 0)
 		return ret;
 
-	*val = 32767 - (s16)be16_to_cpu(regval);
+	*val = be16_to_cpu(regval);
 
 	return IIO_VAL_INT;
 }
@@ -329,27 +330,29 @@
 	else
 		ret = sx9500_wait_for_sample(data);
 
-	if (ret < 0)
-		return ret;
-
 	mutex_lock(&data->mutex);
 
+	if (ret < 0)
+		goto out_dec_data_rdy;
+
 	ret = sx9500_read_prox_data(data, chan, val);
 	if (ret < 0)
-		goto out;
-
-	ret = sx9500_dec_chan_users(data, chan->channel);
-	if (ret < 0)
-		goto out;
+		goto out_dec_data_rdy;
 
 	ret = sx9500_dec_data_rdy_users(data);
 	if (ret < 0)
+		goto out_dec_chan;
+
+	ret = sx9500_dec_chan_users(data, chan->channel);
+	if (ret < 0)
 		goto out;
 
 	ret = IIO_VAL_INT;
 
 	goto out;
 
+out_dec_data_rdy:
+	sx9500_dec_data_rdy_users(data);
 out_dec_chan:
 	sx9500_dec_chan_users(data, chan->channel);
 out:
@@ -679,7 +682,7 @@
 static int sx9500_buffer_preenable(struct iio_dev *indio_dev)
 {
 	struct sx9500_data *data = iio_priv(indio_dev);
-	int ret, i;
+	int ret = 0, i;
 
 	mutex_lock(&data->mutex);
 
@@ -703,7 +706,7 @@
 static int sx9500_buffer_predisable(struct iio_dev *indio_dev)
 {
 	struct sx9500_data *data = iio_priv(indio_dev);
-	int ret, i;
+	int ret = 0, i;
 
 	iio_triggered_buffer_predisable(indio_dev);
 
@@ -800,8 +803,7 @@
 	unsigned int val;
 
 	ret = regmap_update_bits(data->regmap, SX9500_REG_PROX_CTRL0,
-				 GENMASK(SX9500_NUM_CHANNELS, 0),
-				 GENMASK(SX9500_NUM_CHANNELS, 0));
+				 SX9500_CHAN_MASK, SX9500_CHAN_MASK);
 	if (ret < 0)
 		return ret;
 
@@ -821,7 +823,7 @@
 
 out:
 	regmap_update_bits(data->regmap, SX9500_REG_PROX_CTRL0,
-			   GENMASK(SX9500_NUM_CHANNELS, 0), 0);
+			   SX9500_CHAN_MASK, 0);
 	return ret;
 }
 
diff --git a/drivers/iio/temperature/mlx90614.c b/drivers/iio/temperature/mlx90614.c
index cb2e8ad..7a2b639 100644
--- a/drivers/iio/temperature/mlx90614.c
+++ b/drivers/iio/temperature/mlx90614.c
@@ -204,7 +204,7 @@
 		*val = ret;
 		return IIO_VAL_INT;
 	case IIO_CHAN_INFO_OFFSET:
-		*val = 13657;
+		*val = -13657;
 		*val2 = 500000;
 		return IIO_VAL_INT_PLUS_MICRO;
 	case IIO_CHAN_INFO_SCALE:
diff --git a/drivers/iio/temperature/tmp006.c b/drivers/iio/temperature/tmp006.c
index fcc49f8..8f21f32 100644
--- a/drivers/iio/temperature/tmp006.c
+++ b/drivers/iio/temperature/tmp006.c
@@ -132,6 +132,9 @@
 	struct tmp006_data *data = iio_priv(indio_dev);
 	int i;
 
+	if (mask != IIO_CHAN_INFO_SAMP_FREQ)
+		return -EINVAL;
+
 	for (i = 0; i < ARRAY_SIZE(tmp006_freqs); i++)
 		if ((val == tmp006_freqs[i][0]) &&
 		    (val2 == tmp006_freqs[i][1])) {
diff --git a/drivers/infiniband/core/agent.c b/drivers/infiniband/core/agent.c
index c7dcfe4..0429040 100644
--- a/drivers/infiniband/core/agent.c
+++ b/drivers/infiniband/core/agent.c
@@ -88,7 +88,7 @@
 	struct ib_ah *ah;
 	struct ib_mad_send_wr_private *mad_send_wr;
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH)
+	if (rdma_cap_ib_switch(device))
 		port_priv = ib_get_agent_port(device, 0);
 	else
 		port_priv = ib_get_agent_port(device, port_num);
@@ -122,7 +122,7 @@
 	memcpy(send_buf->mad, mad_hdr, resp_mad_len);
 	send_buf->ah = ah;
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH) {
+	if (rdma_cap_ib_switch(device)) {
 		mad_send_wr = container_of(send_buf,
 					   struct ib_mad_send_wr_private,
 					   send_buf);
diff --git a/drivers/infiniband/core/cm.c b/drivers/infiniband/core/cm.c
index dbddddd..3a972eb 100644
--- a/drivers/infiniband/core/cm.c
+++ b/drivers/infiniband/core/cm.c
@@ -169,6 +169,7 @@
 	struct ib_device *ib_device;
 	struct device *device;
 	u8 ack_delay;
+	int going_down;
 	struct cm_port *port[0];
 };
 
@@ -805,6 +806,11 @@
 {
 	int wait_time;
 	unsigned long flags;
+	struct cm_device *cm_dev;
+
+	cm_dev = ib_get_client_data(cm_id_priv->id.device, &cm_client);
+	if (!cm_dev)
+		return;
 
 	spin_lock_irqsave(&cm.lock, flags);
 	cm_cleanup_timewait(cm_id_priv->timewait_info);
@@ -818,8 +824,14 @@
 	 */
 	cm_id_priv->id.state = IB_CM_TIMEWAIT;
 	wait_time = cm_convert_to_ms(cm_id_priv->av.timeout);
-	queue_delayed_work(cm.wq, &cm_id_priv->timewait_info->work.work,
-			   msecs_to_jiffies(wait_time));
+
+	/* Check if the device started its remove_one */
+	spin_lock_irq(&cm.lock);
+	if (!cm_dev->going_down)
+		queue_delayed_work(cm.wq, &cm_id_priv->timewait_info->work.work,
+				   msecs_to_jiffies(wait_time));
+	spin_unlock_irq(&cm.lock);
+
 	cm_id_priv->timewait_info = NULL;
 }
 
@@ -3305,6 +3317,11 @@
 	struct cm_work *work;
 	unsigned long flags;
 	int ret = 0;
+	struct cm_device *cm_dev;
+
+	cm_dev = ib_get_client_data(cm_id->device, &cm_client);
+	if (!cm_dev)
+		return -ENODEV;
 
 	work = kmalloc(sizeof *work, GFP_ATOMIC);
 	if (!work)
@@ -3343,7 +3360,17 @@
 	work->remote_id = cm_id->remote_id;
 	work->mad_recv_wc = NULL;
 	work->cm_event.event = IB_CM_USER_ESTABLISHED;
-	queue_delayed_work(cm.wq, &work->work, 0);
+
+	/* Check if the device started its remove_one */
+	spin_lock_irq(&cm.lock);
+	if (!cm_dev->going_down) {
+		queue_delayed_work(cm.wq, &work->work, 0);
+	} else {
+		kfree(work);
+		ret = -ENODEV;
+	}
+	spin_unlock_irq(&cm.lock);
+
 out:
 	return ret;
 }
@@ -3394,6 +3421,7 @@
 	enum ib_cm_event_type event;
 	u16 attr_id;
 	int paths = 0;
+	int going_down = 0;
 
 	switch (mad_recv_wc->recv_buf.mad->mad_hdr.attr_id) {
 	case CM_REQ_ATTR_ID:
@@ -3452,7 +3480,19 @@
 	work->cm_event.event = event;
 	work->mad_recv_wc = mad_recv_wc;
 	work->port = port;
-	queue_delayed_work(cm.wq, &work->work, 0);
+
+	/* Check if the device started its remove_one */
+	spin_lock_irq(&cm.lock);
+	if (!port->cm_dev->going_down)
+		queue_delayed_work(cm.wq, &work->work, 0);
+	else
+		going_down = 1;
+	spin_unlock_irq(&cm.lock);
+
+	if (going_down) {
+		kfree(work);
+		ib_free_recv_mad(mad_recv_wc);
+	}
 }
 
 static int cm_init_qp_init_attr(struct cm_id_private *cm_id_priv,
@@ -3771,7 +3811,7 @@
 
 	cm_dev->ib_device = ib_device;
 	cm_get_ack_delay(cm_dev);
-
+	cm_dev->going_down = 0;
 	cm_dev->device = device_create(&cm_class, &ib_device->dev,
 				       MKDEV(0, 0), NULL,
 				       "%s", ib_device->name);
@@ -3864,14 +3904,23 @@
 	list_del(&cm_dev->list);
 	write_unlock_irqrestore(&cm.device_lock, flags);
 
+	spin_lock_irq(&cm.lock);
+	cm_dev->going_down = 1;
+	spin_unlock_irq(&cm.lock);
+
 	for (i = 1; i <= ib_device->phys_port_cnt; i++) {
 		if (!rdma_cap_ib_cm(ib_device, i))
 			continue;
 
 		port = cm_dev->port[i-1];
 		ib_modify_port(ib_device, port->port_num, 0, &port_modify);
-		ib_unregister_mad_agent(port->mad_agent);
+		/*
+		 * We flush the queue here after the going_down set, this
+		 * verify that no new works will be queued in the recv handler,
+		 * after that we can call the unregister_mad_agent
+		 */
 		flush_workqueue(cm.wq);
+		ib_unregister_mad_agent(port->mad_agent);
 		cm_remove_port_fs(port);
 	}
 	device_unregister(cm_dev->device);
diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index e6ffa2e..22a3abe 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -67,7 +67,8 @@
 		err_str = "Invalid port mapper client";
 		goto pid_query_error;
 	}
-	if (iwpm_registered_client(nl_client))
+	if (iwpm_check_registration(nl_client, IWPM_REG_VALID) ||
+			iwpm_user_pid == IWPM_PID_UNAVAILABLE)
 		return 0;
 	skb = iwpm_create_nlmsg(RDMA_NL_IWPM_REG_PID, &nlh, nl_client);
 	if (!skb) {
@@ -106,7 +107,6 @@
 	ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_IWPM, GFP_KERNEL);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
-		iwpm_set_registered(nl_client, 1);
 		iwpm_user_pid = IWPM_PID_UNAVAILABLE;
 		err_str = "Unable to send a nlmsg";
 		goto pid_query_error;
@@ -144,12 +144,12 @@
 		err_str = "Invalid port mapper client";
 		goto add_mapping_error;
 	}
-	if (!iwpm_registered_client(nl_client)) {
+	if (!iwpm_valid_pid())
+		return 0;
+	if (!iwpm_check_registration(nl_client, IWPM_REG_VALID)) {
 		err_str = "Unregistered port mapper client";
 		goto add_mapping_error;
 	}
-	if (!iwpm_valid_pid())
-		return 0;
 	skb = iwpm_create_nlmsg(RDMA_NL_IWPM_ADD_MAPPING, &nlh, nl_client);
 	if (!skb) {
 		err_str = "Unable to create a nlmsg";
@@ -214,12 +214,12 @@
 		err_str = "Invalid port mapper client";
 		goto query_mapping_error;
 	}
-	if (!iwpm_registered_client(nl_client)) {
+	if (!iwpm_valid_pid())
+		return 0;
+	if (!iwpm_check_registration(nl_client, IWPM_REG_VALID)) {
 		err_str = "Unregistered port mapper client";
 		goto query_mapping_error;
 	}
-	if (!iwpm_valid_pid())
-		return 0;
 	ret = -ENOMEM;
 	skb = iwpm_create_nlmsg(RDMA_NL_IWPM_QUERY_MAPPING, &nlh, nl_client);
 	if (!skb) {
@@ -288,12 +288,12 @@
 		err_str = "Invalid port mapper client";
 		goto remove_mapping_error;
 	}
-	if (!iwpm_registered_client(nl_client)) {
+	if (!iwpm_valid_pid())
+		return 0;
+	if (iwpm_check_registration(nl_client, IWPM_REG_UNDEF)) {
 		err_str = "Unregistered port mapper client";
 		goto remove_mapping_error;
 	}
-	if (!iwpm_valid_pid())
-		return 0;
 	skb = iwpm_create_nlmsg(RDMA_NL_IWPM_REMOVE_MAPPING, &nlh, nl_client);
 	if (!skb) {
 		ret = -ENOMEM;
@@ -388,7 +388,7 @@
 	pr_debug("%s: iWarp Port Mapper (pid = %d) is available!\n",
 			__func__, iwpm_user_pid);
 	if (iwpm_valid_client(nl_client))
-		iwpm_set_registered(nl_client, 1);
+		iwpm_set_registration(nl_client, IWPM_REG_VALID);
 register_pid_response_exit:
 	nlmsg_request->request_done = 1;
 	/* always for found nlmsg_request */
@@ -644,7 +644,6 @@
 {
 	struct nlattr *nltb[IWPM_NLA_MAPINFO_REQ_MAX];
 	const char *msg_type = "Mapping Info response";
-	int iwpm_pid;
 	u8 nl_client;
 	char *iwpm_name;
 	u16 iwpm_version;
@@ -669,14 +668,14 @@
 				__func__, nl_client);
 		return ret;
 	}
-	iwpm_set_registered(nl_client, 0);
+	iwpm_set_registration(nl_client, IWPM_REG_INCOMPL);
 	atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq);
+	iwpm_user_pid = cb->nlh->nlmsg_pid;
 	if (!iwpm_mapinfo_available())
 		return 0;
-	iwpm_pid = cb->nlh->nlmsg_pid;
 	pr_debug("%s: iWarp Port Mapper (pid = %d) is available!\n",
-		 __func__, iwpm_pid);
-	ret = iwpm_send_mapinfo(nl_client, iwpm_pid);
+		 __func__, iwpm_user_pid);
+	ret = iwpm_send_mapinfo(nl_client, iwpm_user_pid);
 	return ret;
 }
 EXPORT_SYMBOL(iwpm_mapping_info_cb);
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index a626795..5fb089e 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -78,6 +78,7 @@
 	mutex_unlock(&iwpm_admin_lock);
 	if (!ret) {
 		iwpm_set_valid(nl_client, 1);
+		iwpm_set_registration(nl_client, IWPM_REG_UNDEF);
 		pr_debug("%s: Mapinfo and reminfo tables are created\n",
 				__func__);
 	}
@@ -106,6 +107,7 @@
 	}
 	mutex_unlock(&iwpm_admin_lock);
 	iwpm_set_valid(nl_client, 0);
+	iwpm_set_registration(nl_client, IWPM_REG_UNDEF);
 	return 0;
 }
 EXPORT_SYMBOL(iwpm_exit);
@@ -397,17 +399,23 @@
 }
 
 /* valid client */
-int iwpm_registered_client(u8 nl_client)
+u32 iwpm_get_registration(u8 nl_client)
 {
 	return iwpm_admin.reg_list[nl_client];
 }
 
 /* valid client */
-void iwpm_set_registered(u8 nl_client, int reg)
+void iwpm_set_registration(u8 nl_client, u32 reg)
 {
 	iwpm_admin.reg_list[nl_client] = reg;
 }
 
+/* valid client */
+u32 iwpm_check_registration(u8 nl_client, u32 reg)
+{
+	return (iwpm_get_registration(nl_client) & reg);
+}
+
 int iwpm_compare_sockaddr(struct sockaddr_storage *a_sockaddr,
 				struct sockaddr_storage *b_sockaddr)
 {
diff --git a/drivers/infiniband/core/iwpm_util.h b/drivers/infiniband/core/iwpm_util.h
index ee2d9ff..b7b9e19 100644
--- a/drivers/infiniband/core/iwpm_util.h
+++ b/drivers/infiniband/core/iwpm_util.h
@@ -58,6 +58,10 @@
 #define IWPM_PID_UNDEFINED     -1
 #define IWPM_PID_UNAVAILABLE   -2
 
+#define IWPM_REG_UNDEF          0x01
+#define IWPM_REG_VALID          0x02
+#define IWPM_REG_INCOMPL        0x04
+
 struct iwpm_nlmsg_request {
 	struct list_head    inprocess_list;
 	__u32               nlmsg_seq;
@@ -88,7 +92,7 @@
 	atomic_t refcount;
 	atomic_t nlmsg_seq;
 	int      client_list[RDMA_NL_NUM_CLIENTS];
-	int      reg_list[RDMA_NL_NUM_CLIENTS];
+	u32      reg_list[RDMA_NL_NUM_CLIENTS];
 };
 
 /**
@@ -159,19 +163,31 @@
 void iwpm_set_valid(u8 nl_client, int valid);
 
 /**
- * iwpm_registered_client - Check if the port mapper client is registered
+ * iwpm_check_registration - Check if the client registration
+ *			      matches the given one
  * @nl_client: The index of the netlink client
+ * @reg: The given registration type to compare with
  *
  * Call iwpm_register_pid() to register a client
+ * Returns true if the client registration matches reg,
+ * otherwise returns false
  */
-int iwpm_registered_client(u8 nl_client);
+u32 iwpm_check_registration(u8 nl_client, u32 reg);
 
 /**
- * iwpm_set_registered - Set the port mapper client to registered or not
+ * iwpm_set_registration - Set the client registration
  * @nl_client: The index of the netlink client
- * @reg: 1 if registered or 0 if not
+ * @reg: Registration type to set
  */
-void iwpm_set_registered(u8 nl_client, int reg);
+void iwpm_set_registration(u8 nl_client, u32 reg);
+
+/**
+ * iwpm_get_registration
+ * @nl_client: The index of the netlink client
+ *
+ * Returns the client registration type
+ */
+u32 iwpm_get_registration(u8 nl_client);
 
 /**
  * iwpm_send_mapinfo - Send local and mapped IPv4/IPv6 address info of
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index a4b1466..786fc51 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -769,7 +769,7 @@
 	bool opa = rdma_cap_opa_mad(mad_agent_priv->qp_info->port_priv->device,
 				    mad_agent_priv->qp_info->port_priv->port_num);
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH &&
+	if (rdma_cap_ib_switch(device) &&
 	    smp->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
 		port_num = send_wr->wr.ud.port_num;
 	else
@@ -787,14 +787,15 @@
 		if ((opa_get_smp_direction(opa_smp)
 		     ? opa_smp->route.dr.dr_dlid : opa_smp->route.dr.dr_slid) ==
 		     OPA_LID_PERMISSIVE &&
-		     opa_smi_handle_dr_smp_send(opa_smp, device->node_type,
+		     opa_smi_handle_dr_smp_send(opa_smp,
+						rdma_cap_ib_switch(device),
 						port_num) == IB_SMI_DISCARD) {
 			ret = -EINVAL;
 			dev_err(&device->dev, "OPA Invalid directed route\n");
 			goto out;
 		}
 		opa_drslid = be32_to_cpu(opa_smp->route.dr.dr_slid);
-		if (opa_drslid != OPA_LID_PERMISSIVE &&
+		if (opa_drslid != be32_to_cpu(OPA_LID_PERMISSIVE) &&
 		    opa_drslid & 0xffff0000) {
 			ret = -EINVAL;
 			dev_err(&device->dev, "OPA Invalid dr_slid 0x%x\n",
@@ -810,7 +811,7 @@
 	} else {
 		if ((ib_get_smp_direction(smp) ? smp->dr_dlid : smp->dr_slid) ==
 		     IB_LID_PERMISSIVE &&
-		     smi_handle_dr_smp_send(smp, device->node_type, port_num) ==
+		     smi_handle_dr_smp_send(smp, rdma_cap_ib_switch(device), port_num) ==
 		     IB_SMI_DISCARD) {
 			ret = -EINVAL;
 			dev_err(&device->dev, "Invalid directed route\n");
@@ -2030,7 +2031,7 @@
 	struct ib_smp *smp = (struct ib_smp *)recv->mad;
 
 	if (smi_handle_dr_smp_recv(smp,
-				   port_priv->device->node_type,
+				   rdma_cap_ib_switch(port_priv->device),
 				   port_num,
 				   port_priv->device->phys_port_cnt) ==
 				   IB_SMI_DISCARD)
@@ -2042,13 +2043,13 @@
 
 	if (retsmi == IB_SMI_SEND) { /* don't forward */
 		if (smi_handle_dr_smp_send(smp,
-					   port_priv->device->node_type,
+					   rdma_cap_ib_switch(port_priv->device),
 					   port_num) == IB_SMI_DISCARD)
 			return IB_SMI_DISCARD;
 
 		if (smi_check_local_smp(smp, port_priv->device) == IB_SMI_DISCARD)
 			return IB_SMI_DISCARD;
-	} else if (port_priv->device->node_type == RDMA_NODE_IB_SWITCH) {
+	} else if (rdma_cap_ib_switch(port_priv->device)) {
 		/* forward case for switches */
 		memcpy(response, recv, mad_priv_size(response));
 		response->header.recv_wc.wc = &response->header.wc;
@@ -2115,7 +2116,7 @@
 	struct opa_smp *smp = (struct opa_smp *)recv->mad;
 
 	if (opa_smi_handle_dr_smp_recv(smp,
-				   port_priv->device->node_type,
+				   rdma_cap_ib_switch(port_priv->device),
 				   port_num,
 				   port_priv->device->phys_port_cnt) ==
 				   IB_SMI_DISCARD)
@@ -2127,7 +2128,7 @@
 
 	if (retsmi == IB_SMI_SEND) { /* don't forward */
 		if (opa_smi_handle_dr_smp_send(smp,
-					   port_priv->device->node_type,
+					   rdma_cap_ib_switch(port_priv->device),
 					   port_num) == IB_SMI_DISCARD)
 			return IB_SMI_DISCARD;
 
@@ -2135,7 +2136,7 @@
 		    IB_SMI_DISCARD)
 			return IB_SMI_DISCARD;
 
-	} else if (port_priv->device->node_type == RDMA_NODE_IB_SWITCH) {
+	} else if (rdma_cap_ib_switch(port_priv->device)) {
 		/* forward case for switches */
 		memcpy(response, recv, mad_priv_size(response));
 		response->header.recv_wc.wc = &response->header.wc;
@@ -2235,7 +2236,7 @@
 		goto out;
 	}
 
-	if (port_priv->device->node_type == RDMA_NODE_IB_SWITCH)
+	if (rdma_cap_ib_switch(port_priv->device))
 		port_num = wc->port_num;
 	else
 		port_num = port_priv->port_num;
@@ -3297,17 +3298,11 @@
 
 static void ib_mad_init_device(struct ib_device *device)
 {
-	int start, end, i;
+	int start, i;
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH) {
-		start = 0;
-		end   = 0;
-	} else {
-		start = 1;
-		end   = device->phys_port_cnt;
-	}
+	start = rdma_start_port(device);
 
-	for (i = start; i <= end; i++) {
+	for (i = start; i <= rdma_end_port(device); i++) {
 		if (!rdma_cap_ib_mad(device, i))
 			continue;
 
@@ -3342,17 +3337,9 @@
 
 static void ib_mad_remove_device(struct ib_device *device)
 {
-	int start, end, i;
+	int i;
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH) {
-		start = 0;
-		end   = 0;
-	} else {
-		start = 1;
-		end   = device->phys_port_cnt;
-	}
-
-	for (i = start; i <= end; i++) {
+	for (i = rdma_start_port(device); i <= rdma_end_port(device); i++) {
 		if (!rdma_cap_ib_mad(device, i))
 			continue;
 
diff --git a/drivers/infiniband/core/multicast.c b/drivers/infiniband/core/multicast.c
index 1244f02..2cb865c 100644
--- a/drivers/infiniband/core/multicast.c
+++ b/drivers/infiniband/core/multicast.c
@@ -812,12 +812,8 @@
 	if (!dev)
 		return;
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH)
-		dev->start_port = dev->end_port = 0;
-	else {
-		dev->start_port = 1;
-		dev->end_port = device->phys_port_cnt;
-	}
+	dev->start_port = rdma_start_port(device);
+	dev->end_port = rdma_end_port(device);
 
 	for (i = 0; i <= dev->end_port - dev->start_port; i++) {
 		if (!rdma_cap_ib_mcast(device, dev->start_port + i))
diff --git a/drivers/infiniband/core/opa_smi.h b/drivers/infiniband/core/opa_smi.h
index 62d91bf..3bfab35 100644
--- a/drivers/infiniband/core/opa_smi.h
+++ b/drivers/infiniband/core/opa_smi.h
@@ -39,12 +39,12 @@
 
 #include "smi.h"
 
-enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, u8 node_type,
+enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, bool is_switch,
 				       int port_num, int phys_port_cnt);
 int opa_smi_get_fwd_port(struct opa_smp *smp);
 extern enum smi_forward_action opa_smi_check_forward_dr_smp(struct opa_smp *smp);
 extern enum smi_action opa_smi_handle_dr_smp_send(struct opa_smp *smp,
-					      u8 node_type, int port_num);
+					      bool is_switch, int port_num);
 
 /*
  * Return IB_SMI_HANDLE if the SMP should be handled by the local SMA/SM
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 0fae850..ca919f4 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -1156,12 +1156,8 @@
 	int s, e, i;
 	int count = 0;
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH)
-		s = e = 0;
-	else {
-		s = 1;
-		e = device->phys_port_cnt;
-	}
+	s = rdma_start_port(device);
+	e = rdma_end_port(device);
 
 	sa_dev = kzalloc(sizeof *sa_dev +
 			 (e - s + 1) * sizeof (struct ib_sa_port),
diff --git a/drivers/infiniband/core/smi.c b/drivers/infiniband/core/smi.c
index 368a561..f19b238 100644
--- a/drivers/infiniband/core/smi.c
+++ b/drivers/infiniband/core/smi.c
@@ -41,7 +41,7 @@
 #include "smi.h"
 #include "opa_smi.h"
 
-static enum smi_action __smi_handle_dr_smp_send(u8 node_type, int port_num,
+static enum smi_action __smi_handle_dr_smp_send(bool is_switch, int port_num,
 						u8 *hop_ptr, u8 hop_cnt,
 						const u8 *initial_path,
 						const u8 *return_path,
@@ -64,7 +64,7 @@
 
 		/* C14-9:2 */
 		if (*hop_ptr && *hop_ptr < hop_cnt) {
-			if (node_type != RDMA_NODE_IB_SWITCH)
+			if (!is_switch)
 				return IB_SMI_DISCARD;
 
 			/* return_path set when received */
@@ -77,7 +77,7 @@
 		if (*hop_ptr == hop_cnt) {
 			/* return_path set when received */
 			(*hop_ptr)++;
-			return (node_type == RDMA_NODE_IB_SWITCH ||
+			return (is_switch ||
 				dr_dlid_is_permissive ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
@@ -96,7 +96,7 @@
 
 		/* C14-13:2 */
 		if (2 <= *hop_ptr && *hop_ptr <= hop_cnt) {
-			if (node_type != RDMA_NODE_IB_SWITCH)
+			if (!is_switch)
 				return IB_SMI_DISCARD;
 
 			(*hop_ptr)--;
@@ -108,7 +108,7 @@
 		if (*hop_ptr == 1) {
 			(*hop_ptr)--;
 			/* C14-13:3 -- SMPs destined for SM shouldn't be here */
-			return (node_type == RDMA_NODE_IB_SWITCH ||
+			return (is_switch ||
 				dr_slid_is_permissive ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
@@ -127,9 +127,9 @@
  * Return IB_SMI_DISCARD if the SMP should be discarded
  */
 enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp,
-				       u8 node_type, int port_num)
+				       bool is_switch, int port_num)
 {
-	return __smi_handle_dr_smp_send(node_type, port_num,
+	return __smi_handle_dr_smp_send(is_switch, port_num,
 					&smp->hop_ptr, smp->hop_cnt,
 					smp->initial_path,
 					smp->return_path,
@@ -139,9 +139,9 @@
 }
 
 enum smi_action opa_smi_handle_dr_smp_send(struct opa_smp *smp,
-				       u8 node_type, int port_num)
+				       bool is_switch, int port_num)
 {
-	return __smi_handle_dr_smp_send(node_type, port_num,
+	return __smi_handle_dr_smp_send(is_switch, port_num,
 					&smp->hop_ptr, smp->hop_cnt,
 					smp->route.dr.initial_path,
 					smp->route.dr.return_path,
@@ -152,7 +152,7 @@
 					OPA_LID_PERMISSIVE);
 }
 
-static enum smi_action __smi_handle_dr_smp_recv(u8 node_type, int port_num,
+static enum smi_action __smi_handle_dr_smp_recv(bool is_switch, int port_num,
 						int phys_port_cnt,
 						u8 *hop_ptr, u8 hop_cnt,
 						const u8 *initial_path,
@@ -173,7 +173,7 @@
 
 		/* C14-9:2 -- intermediate hop */
 		if (*hop_ptr && *hop_ptr < hop_cnt) {
-			if (node_type != RDMA_NODE_IB_SWITCH)
+			if (!is_switch)
 				return IB_SMI_DISCARD;
 
 			return_path[*hop_ptr] = port_num;
@@ -188,7 +188,7 @@
 				return_path[*hop_ptr] = port_num;
 			/* hop_ptr updated when sending */
 
-			return (node_type == RDMA_NODE_IB_SWITCH ||
+			return (is_switch ||
 				dr_dlid_is_permissive ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
@@ -208,7 +208,7 @@
 
 		/* C14-13:2 */
 		if (2 <= *hop_ptr && *hop_ptr <= hop_cnt) {
-			if (node_type != RDMA_NODE_IB_SWITCH)
+			if (!is_switch)
 				return IB_SMI_DISCARD;
 
 			/* hop_ptr updated when sending */
@@ -224,8 +224,7 @@
 				return IB_SMI_HANDLE;
 			}
 			/* hop_ptr updated when sending */
-			return (node_type == RDMA_NODE_IB_SWITCH ?
-				IB_SMI_HANDLE : IB_SMI_DISCARD);
+			return (is_switch ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-13:4 -- hop_ptr = 0 -> give to SM */
@@ -238,10 +237,10 @@
  * Adjust information for a received SMP
  * Return IB_SMI_DISCARD if the SMP should be dropped
  */
-enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, u8 node_type,
+enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, bool is_switch,
 				       int port_num, int phys_port_cnt)
 {
-	return __smi_handle_dr_smp_recv(node_type, port_num, phys_port_cnt,
+	return __smi_handle_dr_smp_recv(is_switch, port_num, phys_port_cnt,
 					&smp->hop_ptr, smp->hop_cnt,
 					smp->initial_path,
 					smp->return_path,
@@ -254,10 +253,10 @@
  * Adjust information for a received SMP
  * Return IB_SMI_DISCARD if the SMP should be dropped
  */
-enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, u8 node_type,
+enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, bool is_switch,
 					   int port_num, int phys_port_cnt)
 {
-	return __smi_handle_dr_smp_recv(node_type, port_num, phys_port_cnt,
+	return __smi_handle_dr_smp_recv(is_switch, port_num, phys_port_cnt,
 					&smp->hop_ptr, smp->hop_cnt,
 					smp->route.dr.initial_path,
 					smp->route.dr.return_path,
diff --git a/drivers/infiniband/core/smi.h b/drivers/infiniband/core/smi.h
index aff96ba..33c91c8 100644
--- a/drivers/infiniband/core/smi.h
+++ b/drivers/infiniband/core/smi.h
@@ -51,12 +51,12 @@
 	IB_SMI_FORWARD	/* SMP should be forwarded (for switches only) */
 };
 
-enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, u8 node_type,
+enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, bool is_switch,
 				       int port_num, int phys_port_cnt);
 int smi_get_fwd_port(struct ib_smp *smp);
 extern enum smi_forward_action smi_check_forward_dr_smp(struct ib_smp *smp);
 extern enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp,
-					      u8 node_type, int port_num);
+					      bool is_switch, int port_num);
 
 /*
  * Return IB_SMI_HANDLE if the SMP should be handled by the local SMA/SM
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index ed6b6c8..0b84a9c 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -870,7 +870,7 @@
 		goto err_put;
 	}
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH) {
+	if (rdma_cap_ib_switch(device)) {
 		ret = add_port(device, 0, port_callback);
 		if (ret)
 			goto err_put;
diff --git a/drivers/infiniband/core/ucm.c b/drivers/infiniband/core/ucm.c
index 62c24b1..0094810 100644
--- a/drivers/infiniband/core/ucm.c
+++ b/drivers/infiniband/core/ucm.c
@@ -1193,6 +1193,7 @@
 	return 0;
 }
 
+static DECLARE_BITMAP(overflow_map, IB_UCM_MAX_DEVICES);
 static void ib_ucm_release_dev(struct device *dev)
 {
 	struct ib_ucm_device *ucm_dev;
@@ -1202,7 +1203,7 @@
 	if (ucm_dev->devnum < IB_UCM_MAX_DEVICES)
 		clear_bit(ucm_dev->devnum, dev_map);
 	else
-		clear_bit(ucm_dev->devnum - IB_UCM_MAX_DEVICES, dev_map);
+		clear_bit(ucm_dev->devnum - IB_UCM_MAX_DEVICES, overflow_map);
 	kfree(ucm_dev);
 }
 
@@ -1226,7 +1227,6 @@
 static DEVICE_ATTR(ibdev, S_IRUGO, show_ibdev, NULL);
 
 static dev_t overflow_maj;
-static DECLARE_BITMAP(overflow_map, IB_UCM_MAX_DEVICES);
 static int find_overflow_devnum(void)
 {
 	int ret;
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index ad45469..29b2121 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -1354,10 +1354,10 @@
 	/* Acquire mutex's based on pointer comparison to prevent deadlock. */
 	if (file1 < file2) {
 		mutex_lock(&file1->mut);
-		mutex_lock(&file2->mut);
+		mutex_lock_nested(&file2->mut, SINGLE_DEPTH_NESTING);
 	} else {
 		mutex_lock(&file2->mut);
-		mutex_lock(&file1->mut);
+		mutex_lock_nested(&file1->mut, SINGLE_DEPTH_NESTING);
 	}
 }
 
@@ -1616,6 +1616,7 @@
 	device_remove_file(ucma_misc.this_device, &dev_attr_abi_version);
 	misc_deregister(&ucma_misc);
 	idr_destroy(&ctx_idr);
+	idr_destroy(&multicast_idr);
 }
 
 module_init(ucma_init);
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index b1b7323..bbbe018 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -736,6 +736,10 @@
 	/*
 	 * T3 only supports 32 bits of size.
 	 */
+	if (sizeof(phys_addr_t) > 4) {
+		pr_warn_once(MOD "Cannot support dma_mrs on this platform.\n");
+		return ERR_PTR(-ENOTSUPP);
+	}
 	bl.size = 0xffffffff;
 	bl.addr = 0;
 	kva = 0;
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index c7aab48..92d5183 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -814,7 +814,7 @@
 			printk(KERN_ERR MOD
 			       "Unexpected cqe_status 0x%x for QPID=0x%0x\n",
 			       CQE_STATUS(&cqe), CQE_QPID(&cqe));
-			ret = -EINVAL;
+			wc->status = IB_WC_FATAL_ERR;
 		}
 	}
 out:
diff --git a/drivers/infiniband/hw/ehca/ehca_sqp.c b/drivers/infiniband/hw/ehca/ehca_sqp.c
index 12b5bc2..376b031 100644
--- a/drivers/infiniband/hw/ehca/ehca_sqp.c
+++ b/drivers/infiniband/hw/ehca/ehca_sqp.c
@@ -226,8 +226,9 @@
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
 
-	BUG_ON(in_mad_size != sizeof(*in_mad) ||
-	       *out_mad_size != sizeof(*out_mad));
+	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
+			 *out_mad_size != sizeof(*out_mad)))
+		return IB_MAD_RESULT_FAILURE;
 
 	if (!port_num || port_num > ibdev->phys_port_cnt || !in_wc)
 		return IB_MAD_RESULT_FAILURE;
diff --git a/drivers/infiniband/hw/ipath/ipath_driver.c b/drivers/infiniband/hw/ipath/ipath_driver.c
index 2d7e503..871dbe5 100644
--- a/drivers/infiniband/hw/ipath/ipath_driver.c
+++ b/drivers/infiniband/hw/ipath/ipath_driver.c
@@ -31,6 +31,8 @@
  * SOFTWARE.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/sched.h>
 #include <linux/spinlock.h>
 #include <linux/idr.h>
@@ -399,8 +401,8 @@
 	u32 bar0 = 0, bar1 = 0;
 
 #ifdef CONFIG_X86_64
-	if (WARN(pat_enabled(),
-		 "ipath needs PAT disabled, boot with nopat kernel parameter\n")) {
+	if (pat_enabled()) {
+		pr_warn("ipath needs PAT disabled, boot with nopat kernel parameter\n");
 		ret = -ENODEV;
 		goto bail;
 	}
diff --git a/drivers/infiniband/hw/ipath/ipath_mad.c b/drivers/infiniband/hw/ipath/ipath_mad.c
index 948188e..ad3a926 100644
--- a/drivers/infiniband/hw/ipath/ipath_mad.c
+++ b/drivers/infiniband/hw/ipath/ipath_mad.c
@@ -1499,8 +1499,9 @@
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
 
-	BUG_ON(in_mad_size != sizeof(*in_mad) ||
-	       *out_mad_size != sizeof(*out_mad));
+	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
+			 *out_mad_size != sizeof(*out_mad)))
+		return IB_MAD_RESULT_FAILURE;
 
 	switch (in_mad->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:
diff --git a/drivers/infiniband/hw/ipath/ipath_verbs.c b/drivers/infiniband/hw/ipath/ipath_verbs.c
index 48253b8..30ba49c 100644
--- a/drivers/infiniband/hw/ipath/ipath_verbs.c
+++ b/drivers/infiniband/hw/ipath/ipath_verbs.c
@@ -2044,9 +2044,9 @@
 
 	spin_lock_init(&idev->qp_table.lock);
 	spin_lock_init(&idev->lk_table.lock);
-	idev->sm_lid = __constant_be16_to_cpu(IB_LID_PERMISSIVE);
+	idev->sm_lid = be16_to_cpu(IB_LID_PERMISSIVE);
 	/* Set the prefix to the default value (see ch. 4.1.1) */
-	idev->gid_prefix = __constant_cpu_to_be64(0xfe80000000000000ULL);
+	idev->gid_prefix = cpu_to_be64(0xfe80000000000000ULL);
 
 	ret = ipath_init_qp_table(idev, ib_ipath_qp_table_size);
 	if (ret)
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index 85a50df..68b3dfa 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -860,21 +860,31 @@
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
+	enum rdma_link_layer link = rdma_port_get_link_layer(ibdev, port_num);
 
-	BUG_ON(in_mad_size != sizeof(*in_mad) ||
-	       *out_mad_size != sizeof(*out_mad));
+	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
+			 *out_mad_size != sizeof(*out_mad)))
+		return IB_MAD_RESULT_FAILURE;
 
-	switch (rdma_port_get_link_layer(ibdev, port_num)) {
-	case IB_LINK_LAYER_INFINIBAND:
-		if (!mlx4_is_slave(dev->dev))
-			return ib_process_mad(ibdev, mad_flags, port_num, in_wc,
-					      in_grh, in_mad, out_mad);
-	case IB_LINK_LAYER_ETHERNET:
-		return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
-					  in_grh, in_mad, out_mad);
-	default:
-		return -EINVAL;
+	/* iboe_process_mad() which uses the HCA flow-counters to implement IB PMA
+	 * queries, should be called only by VFs and for that specific purpose
+	 */
+	if (link == IB_LINK_LAYER_INFINIBAND) {
+		if (mlx4_is_slave(dev->dev) &&
+		    in_mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_PERF_MGMT &&
+		    in_mad->mad_hdr.attr_id == IB_PMA_PORT_COUNTERS)
+			return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
+						in_grh, in_mad, out_mad);
+
+		return ib_process_mad(ibdev, mad_flags, port_num, in_wc,
+				      in_grh, in_mad, out_mad);
 	}
+
+	if (link == IB_LINK_LAYER_ETHERNET)
+		return iboe_process_mad(ibdev, mad_flags, port_num, in_wc,
+					in_grh, in_mad, out_mad);
+
+	return -EINVAL;
 }
 
 static void send_handler(struct ib_mad_agent *agent,
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index 067a691..8be6db8 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -253,14 +253,15 @@
 	props->hca_core_clock = dev->dev->caps.hca_core_clock * 1000UL;
 	props->timestamp_mask = 0xFFFFFFFFFFFFULL;
 
-	err = mlx4_get_internal_clock_params(dev->dev, &clock_params);
-	if (err)
-		goto out;
+	if (!mlx4_is_slave(dev->dev))
+		err = mlx4_get_internal_clock_params(dev->dev, &clock_params);
 
 	if (uhw->outlen >= resp.response_length + sizeof(resp.hca_core_clock_offset)) {
-		resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE;
 		resp.response_length += sizeof(resp.hca_core_clock_offset);
-		resp.comp_mask |= QUERY_DEVICE_RESP_MASK_TIMESTAMP;
+		if (!err && !mlx4_is_slave(dev->dev)) {
+			resp.comp_mask |= QUERY_DEVICE_RESP_MASK_TIMESTAMP;
+			resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE;
+		}
 	}
 
 	if (uhw->outlen) {
@@ -2669,31 +2670,33 @@
 	dm = kcalloc(ports, sizeof(*dm), GFP_ATOMIC);
 	if (!dm) {
 		pr_err("failed to allocate memory for tunneling qp update\n");
-		goto out;
+		return;
 	}
 
 	for (i = 0; i < ports; i++) {
 		dm[i] = kmalloc(sizeof (struct mlx4_ib_demux_work), GFP_ATOMIC);
 		if (!dm[i]) {
 			pr_err("failed to allocate memory for tunneling qp update work struct\n");
-			for (i = 0; i < dev->caps.num_ports; i++) {
-				if (dm[i])
-					kfree(dm[i]);
-			}
+			while (--i >= 0)
+				kfree(dm[i]);
 			goto out;
 		}
-	}
-	/* initialize or tear down tunnel QPs for the slave */
-	for (i = 0; i < ports; i++) {
 		INIT_WORK(&dm[i]->work, mlx4_ib_tunnels_update_work);
 		dm[i]->port = first_port + i + 1;
 		dm[i]->slave = slave;
 		dm[i]->do_init = do_init;
 		dm[i]->dev = ibdev;
-		spin_lock_irqsave(&ibdev->sriov.going_down_lock, flags);
-		if (!ibdev->sriov.is_going_down)
+	}
+	/* initialize or tear down tunnel QPs for the slave */
+	spin_lock_irqsave(&ibdev->sriov.going_down_lock, flags);
+	if (!ibdev->sriov.is_going_down) {
+		for (i = 0; i < ports; i++)
 			queue_work(ibdev->sriov.demux[i].ud_wq, &dm[i]->work);
 		spin_unlock_irqrestore(&ibdev->sriov.going_down_lock, flags);
+	} else {
+		spin_unlock_irqrestore(&ibdev->sriov.going_down_lock, flags);
+		for (i = 0; i < ports; i++)
+			kfree(dm[i]);
 	}
 out:
 	kfree(dm);
diff --git a/drivers/infiniband/hw/mlx5/mad.c b/drivers/infiniband/hw/mlx5/mad.c
index 01fc97d..b84d13a 100644
--- a/drivers/infiniband/hw/mlx5/mad.c
+++ b/drivers/infiniband/hw/mlx5/mad.c
@@ -68,8 +68,9 @@
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
 
-	BUG_ON(in_mad_size != sizeof(*in_mad) ||
-	       *out_mad_size != sizeof(*out_mad));
+	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
+			 *out_mad_size != sizeof(*out_mad)))
+		return IB_MAD_RESULT_FAILURE;
 
 	slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
 
diff --git a/drivers/infiniband/hw/mthca/mthca_mad.c b/drivers/infiniband/hw/mthca/mthca_mad.c
index 6b2418b..7c3f2fb 100644
--- a/drivers/infiniband/hw/mthca/mthca_mad.c
+++ b/drivers/infiniband/hw/mthca/mthca_mad.c
@@ -209,8 +209,9 @@
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
 
-	BUG_ON(in_mad_size != sizeof(*in_mad) ||
-	       *out_mad_size != sizeof(*out_mad));
+	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
+			 *out_mad_size != sizeof(*out_mad)))
+		return IB_MAD_RESULT_FAILURE;
 
 	/* Forward locally generated traps to the SM */
 	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP &&
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index 9047af4..8a3ad17 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -1520,8 +1520,9 @@
 	int rc = arpindex;
 	struct net_device *netdev;
 	struct nes_adapter *nesadapter = nesvnic->nesdev->nesadapter;
+	__be32 dst_ipaddr = htonl(dst_ip);
 
-	rt = ip_route_output(&init_net, htonl(dst_ip), 0, 0, 0);
+	rt = ip_route_output(&init_net, dst_ipaddr, nesvnic->local_ipaddr, 0, 0);
 	if (IS_ERR(rt)) {
 		printk(KERN_ERR "%s: ip_route_output_key failed for 0x%08X\n",
 		       __func__, dst_ip);
@@ -1533,7 +1534,7 @@
 	else
 		netdev = nesvnic->netdev;
 
-	neigh = neigh_lookup(&arp_tbl, &rt->rt_gateway, netdev);
+	neigh = dst_neigh_lookup(&rt->dst, &dst_ipaddr);
 
 	rcu_read_lock();
 	if (neigh) {
diff --git a/drivers/infiniband/hw/nes/nes_hw.c b/drivers/infiniband/hw/nes/nes_hw.c
index 02120d3..4713dd7 100644
--- a/drivers/infiniband/hw/nes/nes_hw.c
+++ b/drivers/infiniband/hw/nes/nes_hw.c
@@ -3861,7 +3861,7 @@
 				(((u32)mac_addr[2]) << 24) | (((u32)mac_addr[3]) << 16) |
 				(((u32)mac_addr[4]) << 8)  | (u32)mac_addr[5]);
 		cqp_wqe->wqe_words[NES_CQP_ARP_WQE_MAC_HIGH_IDX] = cpu_to_le32(
-				(((u32)mac_addr[0]) << 16) | (u32)mac_addr[1]);
+				(((u32)mac_addr[0]) << 8) | (u32)mac_addr[1]);
 	} else {
 		cqp_wqe->wqe_words[NES_CQP_ARP_WQE_MAC_ADDR_LOW_IDX] = 0;
 		cqp_wqe->wqe_words[NES_CQP_ARP_WQE_MAC_HIGH_IDX] = 0;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h
index b396344..6a36338 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_H__
 #define __OCRDMA_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_abi.h b/drivers/infiniband/hw/ocrdma/ocrdma_abi.h
index 1554cca..430b135 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_abi.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_abi.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_ABI_H__
 #define __OCRDMA_ABI_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
index 4bafa15..44766fe 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #include <net/neighbour.h>
 #include <net/netevent.h>
@@ -215,8 +230,9 @@
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
 
-	BUG_ON(in_mad_size != sizeof(*in_mad) ||
-	       *out_mad_size != sizeof(*out_mad));
+	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
+			 *out_mad_size != sizeof(*out_mad)))
+		return IB_MAD_RESULT_FAILURE;
 
 	switch (in_mad->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_PERF_MGMT:
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
index cf366fe..04a30ae 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_AH_H__
 #define __OCRDMA_AH_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
index 47615ff..aab391a 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) CNA Adapters.              *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #include <linux/sched.h>
 #include <linux/interrupt.h>
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.h b/drivers/infiniband/hw/ocrdma/ocrdma_hw.h
index e905972..7ed885c 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) CNA Adapters.              *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_HW_H__
 #define __OCRDMA_HW_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index 8a1398b..b119a34 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #include <linux/module.h>
 #include <linux/idr.h>
@@ -46,7 +61,7 @@
 MODULE_VERSION(OCRDMA_ROCE_DRV_VERSION);
 MODULE_DESCRIPTION(OCRDMA_ROCE_DRV_DESC " " OCRDMA_ROCE_DRV_VERSION);
 MODULE_AUTHOR("Emulex Corporation");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("Dual BSD/GPL");
 
 static LIST_HEAD(ocrdma_dev_list);
 static DEFINE_SPINLOCK(ocrdma_devlist_lock);
@@ -696,6 +711,7 @@
 	ocrdma_unregister_inet6addr_notifier();
 	ocrdma_unregister_inetaddr_notifier();
 	ocrdma_rem_debugfs();
+	idr_destroy(&ocrdma_dev_id);
 }
 
 module_init(ocrdma_init_module);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
index 02ad0ae..80006b2 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_SLI_H__
 #define __OCRDMA_SLI_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
index 48d7ef5..69334e2 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2014 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #include <rdma/ib_addr.h>
 #include <rdma/ib_pma.h>
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
index 091edd6..c9e58d0 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2014 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_STATS_H__
 #define __OCRDMA_STATS_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index 5bb61eb..bc84cd4 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #include <linux/dma-mapping.h>
 #include <rdma/ib_verbs.h>
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
index b15c608..eaccb2d 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_VERBS_H__
 #define __OCRDMA_VERBS_H__
diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c
index 05e3242..9625e7c 100644
--- a/drivers/infiniband/hw/qib/qib_mad.c
+++ b/drivers/infiniband/hw/qib/qib_mad.c
@@ -2412,8 +2412,9 @@
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
 	struct ib_mad *out_mad = (struct ib_mad *)out;
 
-	BUG_ON(in_mad_size != sizeof(*in_mad) ||
-	       *out_mad_size != sizeof(*out_mad));
+	if (WARN_ON_ONCE(in_mad_size != sizeof(*in_mad) ||
+			 *out_mad_size != sizeof(*out_mad)))
+		return IB_MAD_RESULT_FAILURE;
 
 	switch (in_mad->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index bd94b0a..79859c4 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -239,7 +239,7 @@
 	struct net_device   *dev;
 	struct ipoib_neigh  *neigh;
 	struct ipoib_path   *path;
-	struct ipoib_cm_tx_buf *tx_ring;
+	struct ipoib_tx_buf *tx_ring;
 	unsigned	     tx_head;
 	unsigned	     tx_tail;
 	unsigned long	     flags;
@@ -504,6 +504,33 @@
 void ipoib_mcast_dev_down(struct net_device *dev);
 void ipoib_mcast_dev_flush(struct net_device *dev);
 
+int ipoib_dma_map_tx(struct ib_device *ca, struct ipoib_tx_buf *tx_req);
+void ipoib_dma_unmap_tx(struct ipoib_dev_priv *priv,
+			struct ipoib_tx_buf *tx_req);
+
+static inline void ipoib_build_sge(struct ipoib_dev_priv *priv,
+				   struct ipoib_tx_buf *tx_req)
+{
+	int i, off;
+	struct sk_buff *skb = tx_req->skb;
+	skb_frag_t *frags = skb_shinfo(skb)->frags;
+	int nr_frags = skb_shinfo(skb)->nr_frags;
+	u64 *mapping = tx_req->mapping;
+
+	if (skb_headlen(skb)) {
+		priv->tx_sge[0].addr         = mapping[0];
+		priv->tx_sge[0].length       = skb_headlen(skb);
+		off = 1;
+	} else
+		off = 0;
+
+	for (i = 0; i < nr_frags; ++i) {
+		priv->tx_sge[i + off].addr = mapping[i + off];
+		priv->tx_sge[i + off].length = skb_frag_size(&frags[i]);
+	}
+	priv->tx_wr.num_sge	     = nr_frags + off;
+}
+
 #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
 struct ipoib_mcast_iter *ipoib_mcast_iter_init(struct net_device *dev);
 int ipoib_mcast_iter_next(struct ipoib_mcast_iter *iter);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index cf32a778..ee39be6 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -694,14 +694,12 @@
 static inline int post_send(struct ipoib_dev_priv *priv,
 			    struct ipoib_cm_tx *tx,
 			    unsigned int wr_id,
-			    u64 addr, int len)
+			    struct ipoib_tx_buf *tx_req)
 {
 	struct ib_send_wr *bad_wr;
 
-	priv->tx_sge[0].addr          = addr;
-	priv->tx_sge[0].length        = len;
+	ipoib_build_sge(priv, tx_req);
 
-	priv->tx_wr.num_sge	= 1;
 	priv->tx_wr.wr_id	= wr_id | IPOIB_OP_CM;
 
 	return ib_post_send(tx->qp, &priv->tx_wr, &bad_wr);
@@ -710,8 +708,7 @@
 void ipoib_cm_send(struct net_device *dev, struct sk_buff *skb, struct ipoib_cm_tx *tx)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
-	struct ipoib_cm_tx_buf *tx_req;
-	u64 addr;
+	struct ipoib_tx_buf *tx_req;
 	int rc;
 
 	if (unlikely(skb->len > tx->mtu)) {
@@ -735,24 +732,21 @@
 	 */
 	tx_req = &tx->tx_ring[tx->tx_head & (ipoib_sendq_size - 1)];
 	tx_req->skb = skb;
-	addr = ib_dma_map_single(priv->ca, skb->data, skb->len, DMA_TO_DEVICE);
-	if (unlikely(ib_dma_mapping_error(priv->ca, addr))) {
+
+	if (unlikely(ipoib_dma_map_tx(priv->ca, tx_req))) {
 		++dev->stats.tx_errors;
 		dev_kfree_skb_any(skb);
 		return;
 	}
 
-	tx_req->mapping = addr;
-
 	skb_orphan(skb);
 	skb_dst_drop(skb);
 
-	rc = post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1),
-		       addr, skb->len);
+	rc = post_send(priv, tx, tx->tx_head & (ipoib_sendq_size - 1), tx_req);
 	if (unlikely(rc)) {
 		ipoib_warn(priv, "post_send failed, error %d\n", rc);
 		++dev->stats.tx_errors;
-		ib_dma_unmap_single(priv->ca, addr, skb->len, DMA_TO_DEVICE);
+		ipoib_dma_unmap_tx(priv, tx_req);
 		dev_kfree_skb_any(skb);
 	} else {
 		dev->trans_start = jiffies;
@@ -777,7 +771,7 @@
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ipoib_cm_tx *tx = wc->qp->qp_context;
 	unsigned int wr_id = wc->wr_id & ~IPOIB_OP_CM;
-	struct ipoib_cm_tx_buf *tx_req;
+	struct ipoib_tx_buf *tx_req;
 	unsigned long flags;
 
 	ipoib_dbg_data(priv, "cm send completion: id %d, status: %d\n",
@@ -791,7 +785,7 @@
 
 	tx_req = &tx->tx_ring[wr_id];
 
-	ib_dma_unmap_single(priv->ca, tx_req->mapping, tx_req->skb->len, DMA_TO_DEVICE);
+	ipoib_dma_unmap_tx(priv, tx_req);
 
 	/* FIXME: is this right? Shouldn't we only increment on success? */
 	++dev->stats.tx_packets;
@@ -1036,6 +1030,9 @@
 
 	struct ib_qp *tx_qp;
 
+	if (dev->features & NETIF_F_SG)
+		attr.cap.max_send_sge = MAX_SKB_FRAGS + 1;
+
 	tx_qp = ib_create_qp(priv->pd, &attr);
 	if (PTR_ERR(tx_qp) == -EINVAL) {
 		ipoib_warn(priv, "can't use GFP_NOIO for QPs on device %s, using GFP_KERNEL\n",
@@ -1170,7 +1167,7 @@
 static void ipoib_cm_tx_destroy(struct ipoib_cm_tx *p)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(p->dev);
-	struct ipoib_cm_tx_buf *tx_req;
+	struct ipoib_tx_buf *tx_req;
 	unsigned long begin;
 
 	ipoib_dbg(priv, "Destroy active connection 0x%x head 0x%x tail 0x%x\n",
@@ -1197,8 +1194,7 @@
 
 	while ((int) p->tx_tail - (int) p->tx_head < 0) {
 		tx_req = &p->tx_ring[p->tx_tail & (ipoib_sendq_size - 1)];
-		ib_dma_unmap_single(priv->ca, tx_req->mapping, tx_req->skb->len,
-				    DMA_TO_DEVICE);
+		ipoib_dma_unmap_tx(priv, tx_req);
 		dev_kfree_skb_any(tx_req->skb);
 		++p->tx_tail;
 		netif_tx_lock_bh(p->dev);
@@ -1455,7 +1451,6 @@
 	spin_unlock_irq(&priv->lock);
 }
 
-
 static ssize_t show_mode(struct device *d, struct device_attribute *attr,
 			 char *buf)
 {
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index 63b92cb..d266667 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -263,8 +263,7 @@
 			   "for buf %d\n", wr_id);
 }
 
-static int ipoib_dma_map_tx(struct ib_device *ca,
-			    struct ipoib_tx_buf *tx_req)
+int ipoib_dma_map_tx(struct ib_device *ca, struct ipoib_tx_buf *tx_req)
 {
 	struct sk_buff *skb = tx_req->skb;
 	u64 *mapping = tx_req->mapping;
@@ -305,8 +304,8 @@
 	return -EIO;
 }
 
-static void ipoib_dma_unmap_tx(struct ib_device *ca,
-			       struct ipoib_tx_buf *tx_req)
+void ipoib_dma_unmap_tx(struct ipoib_dev_priv *priv,
+			struct ipoib_tx_buf *tx_req)
 {
 	struct sk_buff *skb = tx_req->skb;
 	u64 *mapping = tx_req->mapping;
@@ -314,7 +313,8 @@
 	int off;
 
 	if (skb_headlen(skb)) {
-		ib_dma_unmap_single(ca, mapping[0], skb_headlen(skb), DMA_TO_DEVICE);
+		ib_dma_unmap_single(priv->ca, mapping[0], skb_headlen(skb),
+				    DMA_TO_DEVICE);
 		off = 1;
 	} else
 		off = 0;
@@ -322,8 +322,8 @@
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; ++i) {
 		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
-		ib_dma_unmap_page(ca, mapping[i + off], skb_frag_size(frag),
-				  DMA_TO_DEVICE);
+		ib_dma_unmap_page(priv->ca, mapping[i + off],
+				  skb_frag_size(frag), DMA_TO_DEVICE);
 	}
 }
 
@@ -389,7 +389,7 @@
 
 	tx_req = &priv->tx_ring[wr_id];
 
-	ipoib_dma_unmap_tx(priv->ca, tx_req);
+	ipoib_dma_unmap_tx(priv, tx_req);
 
 	++dev->stats.tx_packets;
 	dev->stats.tx_bytes += tx_req->skb->len;
@@ -514,24 +514,10 @@
 			    void *head, int hlen)
 {
 	struct ib_send_wr *bad_wr;
-	int i, off;
 	struct sk_buff *skb = tx_req->skb;
-	skb_frag_t *frags = skb_shinfo(skb)->frags;
-	int nr_frags = skb_shinfo(skb)->nr_frags;
-	u64 *mapping = tx_req->mapping;
 
-	if (skb_headlen(skb)) {
-		priv->tx_sge[0].addr         = mapping[0];
-		priv->tx_sge[0].length       = skb_headlen(skb);
-		off = 1;
-	} else
-		off = 0;
+	ipoib_build_sge(priv, tx_req);
 
-	for (i = 0; i < nr_frags; ++i) {
-		priv->tx_sge[i + off].addr = mapping[i + off];
-		priv->tx_sge[i + off].length = skb_frag_size(&frags[i]);
-	}
-	priv->tx_wr.num_sge	     = nr_frags + off;
 	priv->tx_wr.wr_id 	     = wr_id;
 	priv->tx_wr.wr.ud.remote_qpn = qpn;
 	priv->tx_wr.wr.ud.ah 	     = address;
@@ -617,7 +603,7 @@
 		ipoib_warn(priv, "post_send failed, error %d\n", rc);
 		++dev->stats.tx_errors;
 		--priv->tx_outstanding;
-		ipoib_dma_unmap_tx(priv->ca, tx_req);
+		ipoib_dma_unmap_tx(priv, tx_req);
 		dev_kfree_skb_any(skb);
 		if (netif_queue_stopped(dev))
 			netif_wake_queue(dev);
@@ -868,7 +854,7 @@
 			while ((int) priv->tx_tail - (int) priv->tx_head < 0) {
 				tx_req = &priv->tx_ring[priv->tx_tail &
 							(ipoib_sendq_size - 1)];
-				ipoib_dma_unmap_tx(priv->ca, tx_req);
+				ipoib_dma_unmap_tx(priv, tx_req);
 				dev_kfree_skb_any(tx_req->skb);
 				++priv->tx_tail;
 				--priv->tx_outstanding;
@@ -985,20 +971,21 @@
 }
 
 static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
-				enum ipoib_flush_level level)
+				enum ipoib_flush_level level,
+				int nesting)
 {
 	struct ipoib_dev_priv *cpriv;
 	struct net_device *dev = priv->dev;
 	int result;
 
-	down_read(&priv->vlan_rwsem);
+	down_read_nested(&priv->vlan_rwsem, nesting);
 
 	/*
 	 * Flush any child interfaces too -- they might be up even if
 	 * the parent is down.
 	 */
 	list_for_each_entry(cpriv, &priv->child_intfs, list)
-		__ipoib_ib_dev_flush(cpriv, level);
+		__ipoib_ib_dev_flush(cpriv, level, nesting + 1);
 
 	up_read(&priv->vlan_rwsem);
 
@@ -1076,7 +1063,7 @@
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, flush_light);
 
-	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_LIGHT);
+	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_LIGHT, 0);
 }
 
 void ipoib_ib_dev_flush_normal(struct work_struct *work)
@@ -1084,7 +1071,7 @@
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, flush_normal);
 
-	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_NORMAL);
+	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_NORMAL, 0);
 }
 
 void ipoib_ib_dev_flush_heavy(struct work_struct *work)
@@ -1092,7 +1079,7 @@
 	struct ipoib_dev_priv *priv =
 		container_of(work, struct ipoib_dev_priv, flush_heavy);
 
-	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY);
+	__ipoib_ib_dev_flush(priv, IPOIB_FLUSH_HEAVY, 0);
 }
 
 void ipoib_ib_dev_cleanup(struct net_device *dev)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index da149c2..b2943c8 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -190,7 +190,7 @@
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
 	if (test_bit(IPOIB_FLAG_ADMIN_CM, &priv->flags))
-		features &= ~(NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO);
+		features &= ~(NETIF_F_IP_CSUM | NETIF_F_TSO);
 
 	return features;
 }
@@ -232,6 +232,7 @@
 		ipoib_warn(priv, "enabling connected mode "
 			   "will cause multicast packet drops\n");
 		netdev_update_features(dev);
+		dev_set_mtu(dev, ipoib_cm_max_mtu(dev));
 		rtnl_unlock();
 		priv->tx_wr.send_flags &= ~IB_SEND_IP_CSUM;
 
@@ -1577,7 +1578,8 @@
 	SET_NETDEV_DEV(priv->dev, hca->dma_device);
 	priv->dev->dev_id = port - 1;
 
-	if (!ib_query_port(hca, port, &attr))
+	result = ib_query_port(hca, port, &attr);
+	if (!result)
 		priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
 	else {
 		printk(KERN_WARNING "%s: ib_query_port %d failed\n",
@@ -1598,7 +1600,8 @@
 		goto device_init_failed;
 	}
 
-	if (ipoib_set_dev_features(priv, hca))
+	result = ipoib_set_dev_features(priv, hca);
+	if (result)
 		goto device_init_failed;
 
 	/*
@@ -1684,7 +1687,7 @@
 	struct list_head *dev_list;
 	struct net_device *dev;
 	struct ipoib_dev_priv *priv;
-	int s, e, p;
+	int p;
 	int count = 0;
 
 	dev_list = kmalloc(sizeof *dev_list, GFP_KERNEL);
@@ -1693,15 +1696,7 @@
 
 	INIT_LIST_HEAD(dev_list);
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH) {
-		s = 0;
-		e = 0;
-	} else {
-		s = 1;
-		e = device->phys_port_cnt;
-	}
-
-	for (p = s; p <= e; ++p) {
+	for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) {
 		if (!rdma_protocol_ib(device, p))
 			continue;
 		dev = ipoib_add_port("ib%d", device, p);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index 9e6ee82..851c821 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -177,7 +177,8 @@
 		else
 			size += ipoib_recvq_size * ipoib_max_conn_qp;
 	} else
-		goto out_free_wq;
+		if (ret != -ENOSYS)
+			goto out_free_wq;
 
 	cq_attr.cqe = size;
 	priv->recv_cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL,
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 7717009..d851e18 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -775,6 +775,17 @@
 	ret = isert_rdma_post_recvl(isert_conn);
 	if (ret)
 		goto out_conn_dev;
+	/*
+	 * Obtain the second reference now before isert_rdma_accept() to
+	 * ensure that any initiator generated REJECT CM event that occurs
+	 * asynchronously won't drop the last reference until the error path
+	 * in iscsi_target_login_sess_out() does it's ->iscsit_free_conn() ->
+	 * isert_free_conn() -> isert_put_conn() -> kref_put().
+	 */
+	if (!kref_get_unless_zero(&isert_conn->kref)) {
+		isert_warn("conn %p connect_release is running\n", isert_conn);
+		goto out_conn_dev;
+	}
 
 	ret = isert_rdma_accept(isert_conn);
 	if (ret)
@@ -836,11 +847,6 @@
 
 	isert_info("conn %p\n", isert_conn);
 
-	if (!kref_get_unless_zero(&isert_conn->kref)) {
-		isert_warn("conn %p connect_release is running\n", isert_conn);
-		return;
-	}
-
 	mutex_lock(&isert_conn->mutex);
 	if (isert_conn->state != ISER_CONN_FULL_FEATURE)
 		isert_conn->state = ISER_CONN_UP;
diff --git a/drivers/infiniband/ulp/srp/ib_srp.c b/drivers/infiniband/ulp/srp/ib_srp.c
index 267dc4f..31a20b4 100644
--- a/drivers/infiniband/ulp/srp/ib_srp.c
+++ b/drivers/infiniband/ulp/srp/ib_srp.c
@@ -161,13 +161,10 @@
 {
 	int tmo, res;
 
-	if (strncmp(val, "off", 3) != 0) {
-		res = kstrtoint(val, 0, &tmo);
-		if (res)
-			goto out;
-	} else {
-		tmo = -1;
-	}
+	res = srp_parse_tmo(&tmo, val);
+	if (res)
+		goto out;
+
 	if (kp->arg == &srp_reconnect_delay)
 		res = srp_tmo_valid(tmo, srp_fast_io_fail_tmo,
 				    srp_dev_loss_tmo);
@@ -3379,7 +3376,7 @@
 	struct srp_device *srp_dev;
 	struct ib_device_attr *dev_attr;
 	struct srp_host *host;
-	int mr_page_shift, s, e, p;
+	int mr_page_shift, p;
 	u64 max_pages_per_mr;
 
 	dev_attr = kmalloc(sizeof *dev_attr, GFP_KERNEL);
@@ -3443,15 +3440,7 @@
 	if (IS_ERR(srp_dev->mr))
 		goto err_pd;
 
-	if (device->node_type == RDMA_NODE_IB_SWITCH) {
-		s = 0;
-		e = 0;
-	} else {
-		s = 1;
-		e = device->phys_port_cnt;
-	}
-
-	for (p = s; p <= e; ++p) {
+	for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) {
 		host = srp_add_port(srp_dev, p);
 		if (host)
 			list_add_tail(&host->list, &srp_dev->dev_list);
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 82897ca..60ff0a2 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -302,7 +302,7 @@
 	int i;
 
 	ioui = (struct ib_dm_iou_info *)mad->data;
-	ioui->change_id = __constant_cpu_to_be16(1);
+	ioui->change_id = cpu_to_be16(1);
 	ioui->max_controllers = 16;
 
 	/* set present for slot 1 and empty for the rest */
@@ -330,13 +330,13 @@
 
 	if (!slot || slot > 16) {
 		mad->mad_hdr.status
-			= __constant_cpu_to_be16(DM_MAD_STATUS_INVALID_FIELD);
+			= cpu_to_be16(DM_MAD_STATUS_INVALID_FIELD);
 		return;
 	}
 
 	if (slot > 2) {
 		mad->mad_hdr.status
-			= __constant_cpu_to_be16(DM_MAD_STATUS_NO_IOC);
+			= cpu_to_be16(DM_MAD_STATUS_NO_IOC);
 		return;
 	}
 
@@ -348,10 +348,10 @@
 	iocp->device_version = cpu_to_be16(sdev->dev_attr.hw_ver);
 	iocp->subsys_vendor_id = cpu_to_be32(sdev->dev_attr.vendor_id);
 	iocp->subsys_device_id = 0x0;
-	iocp->io_class = __constant_cpu_to_be16(SRP_REV16A_IB_IO_CLASS);
-	iocp->io_subclass = __constant_cpu_to_be16(SRP_IO_SUBCLASS);
-	iocp->protocol = __constant_cpu_to_be16(SRP_PROTOCOL);
-	iocp->protocol_version = __constant_cpu_to_be16(SRP_PROTOCOL_VERSION);
+	iocp->io_class = cpu_to_be16(SRP_REV16A_IB_IO_CLASS);
+	iocp->io_subclass = cpu_to_be16(SRP_IO_SUBCLASS);
+	iocp->protocol = cpu_to_be16(SRP_PROTOCOL);
+	iocp->protocol_version = cpu_to_be16(SRP_PROTOCOL_VERSION);
 	iocp->send_queue_depth = cpu_to_be16(sdev->srq_size);
 	iocp->rdma_read_depth = 4;
 	iocp->send_size = cpu_to_be32(srp_max_req_size);
@@ -379,13 +379,13 @@
 
 	if (!slot || slot > 16) {
 		mad->mad_hdr.status
-			= __constant_cpu_to_be16(DM_MAD_STATUS_INVALID_FIELD);
+			= cpu_to_be16(DM_MAD_STATUS_INVALID_FIELD);
 		return;
 	}
 
 	if (slot > 2 || lo > hi || hi > 1) {
 		mad->mad_hdr.status
-			= __constant_cpu_to_be16(DM_MAD_STATUS_NO_IOC);
+			= cpu_to_be16(DM_MAD_STATUS_NO_IOC);
 		return;
 	}
 
@@ -436,7 +436,7 @@
 		break;
 	default:
 		rsp_mad->mad_hdr.status =
-		    __constant_cpu_to_be16(DM_MAD_STATUS_UNSUP_METHOD_ATTR);
+		    cpu_to_be16(DM_MAD_STATUS_UNSUP_METHOD_ATTR);
 		break;
 	}
 }
@@ -493,11 +493,11 @@
 		break;
 	case IB_MGMT_METHOD_SET:
 		dm_mad->mad_hdr.status =
-		    __constant_cpu_to_be16(DM_MAD_STATUS_UNSUP_METHOD_ATTR);
+		    cpu_to_be16(DM_MAD_STATUS_UNSUP_METHOD_ATTR);
 		break;
 	default:
 		dm_mad->mad_hdr.status =
-		    __constant_cpu_to_be16(DM_MAD_STATUS_UNSUP_METHOD);
+		    cpu_to_be16(DM_MAD_STATUS_UNSUP_METHOD);
 		break;
 	}
 
@@ -1535,7 +1535,7 @@
 	memset(srp_rsp, 0, sizeof *srp_rsp);
 	srp_rsp->opcode = SRP_RSP;
 	srp_rsp->req_lim_delta =
-		__constant_cpu_to_be32(1 + atomic_xchg(&ch->req_lim_delta, 0));
+		cpu_to_be32(1 + atomic_xchg(&ch->req_lim_delta, 0));
 	srp_rsp->tag = tag;
 	srp_rsp->status = status;
 
@@ -1585,8 +1585,8 @@
 	memset(srp_rsp, 0, sizeof *srp_rsp);
 
 	srp_rsp->opcode = SRP_RSP;
-	srp_rsp->req_lim_delta = __constant_cpu_to_be32(1
-				    + atomic_xchg(&ch->req_lim_delta, 0));
+	srp_rsp->req_lim_delta =
+		cpu_to_be32(1 + atomic_xchg(&ch->req_lim_delta, 0));
 	srp_rsp->tag = tag;
 
 	srp_rsp->flags |= SRP_RSP_FLAG_RSPVALID;
@@ -1630,7 +1630,7 @@
 	switch (len) {
 	case 8:
 		if ((*((__be64 *)lun) &
-		     __constant_cpu_to_be64(0x0000FFFFFFFFFFFFLL)) != 0)
+		     cpu_to_be64(0x0000FFFFFFFFFFFFLL)) != 0)
 			goto out_err;
 		break;
 	case 4:
@@ -2449,8 +2449,8 @@
 	}
 
 	if (it_iu_len > srp_max_req_size || it_iu_len < 64) {
-		rej->reason = __constant_cpu_to_be32(
-				SRP_LOGIN_REJ_REQ_IT_IU_LENGTH_TOO_LARGE);
+		rej->reason = cpu_to_be32(
+			      SRP_LOGIN_REJ_REQ_IT_IU_LENGTH_TOO_LARGE);
 		ret = -EINVAL;
 		pr_err("rejected SRP_LOGIN_REQ because its"
 		       " length (%d bytes) is out of range (%d .. %d)\n",
@@ -2459,8 +2459,8 @@
 	}
 
 	if (!sport->enabled) {
-		rej->reason = __constant_cpu_to_be32(
-			     SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
+		rej->reason = cpu_to_be32(
+			      SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
 		ret = -EINVAL;
 		pr_err("rejected SRP_LOGIN_REQ because the target port"
 		       " has not yet been enabled\n");
@@ -2505,8 +2505,8 @@
 	if (*(__be64 *)req->target_port_id != cpu_to_be64(srpt_service_guid)
 	    || *(__be64 *)(req->target_port_id + 8) !=
 	       cpu_to_be64(srpt_service_guid)) {
-		rej->reason = __constant_cpu_to_be32(
-				SRP_LOGIN_REJ_UNABLE_ASSOCIATE_CHANNEL);
+		rej->reason = cpu_to_be32(
+			      SRP_LOGIN_REJ_UNABLE_ASSOCIATE_CHANNEL);
 		ret = -ENOMEM;
 		pr_err("rejected SRP_LOGIN_REQ because it"
 		       " has an invalid target port identifier.\n");
@@ -2515,8 +2515,8 @@
 
 	ch = kzalloc(sizeof *ch, GFP_KERNEL);
 	if (!ch) {
-		rej->reason = __constant_cpu_to_be32(
-					SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
+		rej->reason = cpu_to_be32(
+			      SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
 		pr_err("rejected SRP_LOGIN_REQ because no memory.\n");
 		ret = -ENOMEM;
 		goto reject;
@@ -2552,8 +2552,8 @@
 
 	ret = srpt_create_ch_ib(ch);
 	if (ret) {
-		rej->reason = __constant_cpu_to_be32(
-				SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
+		rej->reason = cpu_to_be32(
+			      SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
 		pr_err("rejected SRP_LOGIN_REQ because creating"
 		       " a new RDMA channel failed.\n");
 		goto free_ring;
@@ -2561,8 +2561,7 @@
 
 	ret = srpt_ch_qp_rtr(ch, ch->qp);
 	if (ret) {
-		rej->reason = __constant_cpu_to_be32(
-				SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
+		rej->reason = cpu_to_be32(SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
 		pr_err("rejected SRP_LOGIN_REQ because enabling"
 		       " RTR failed (error code = %d)\n", ret);
 		goto destroy_ib;
@@ -2580,15 +2579,15 @@
 	if (!nacl) {
 		pr_info("Rejected login because no ACL has been"
 			" configured yet for initiator %s.\n", ch->sess_name);
-		rej->reason = __constant_cpu_to_be32(
-				SRP_LOGIN_REJ_CHANNEL_LIMIT_REACHED);
+		rej->reason = cpu_to_be32(
+			      SRP_LOGIN_REJ_CHANNEL_LIMIT_REACHED);
 		goto destroy_ib;
 	}
 
 	ch->sess = transport_init_session(TARGET_PROT_NORMAL);
 	if (IS_ERR(ch->sess)) {
-		rej->reason = __constant_cpu_to_be32(
-				SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
+		rej->reason = cpu_to_be32(
+			      SRP_LOGIN_REJ_INSUFFICIENT_RESOURCES);
 		pr_debug("Failed to create session\n");
 		goto deregister_session;
 	}
@@ -2604,8 +2603,8 @@
 	rsp->max_it_iu_len = req->req_it_iu_len;
 	rsp->max_ti_iu_len = req->req_it_iu_len;
 	ch->max_ti_iu_len = it_iu_len;
-	rsp->buf_fmt = __constant_cpu_to_be16(SRP_BUF_FORMAT_DIRECT
-					      | SRP_BUF_FORMAT_INDIRECT);
+	rsp->buf_fmt = cpu_to_be16(SRP_BUF_FORMAT_DIRECT
+				   | SRP_BUF_FORMAT_INDIRECT);
 	rsp->req_lim_delta = cpu_to_be32(ch->rq_size);
 	atomic_set(&ch->req_lim, ch->rq_size);
 	atomic_set(&ch->req_lim_delta, 0);
@@ -2655,8 +2654,8 @@
 reject:
 	rej->opcode = SRP_LOGIN_REJ;
 	rej->tag = req->tag;
-	rej->buf_fmt = __constant_cpu_to_be16(SRP_BUF_FORMAT_DIRECT
-					      | SRP_BUF_FORMAT_INDIRECT);
+	rej->buf_fmt = cpu_to_be16(SRP_BUF_FORMAT_DIRECT
+				   | SRP_BUF_FORMAT_INDIRECT);
 
 	ib_send_cm_rej(cm_id, IB_CM_REJ_CONSUMER_DEFINED, NULL, 0,
 			     (void *)rej, sizeof *rej);
diff --git a/drivers/input/input-leds.c b/drivers/input/input-leds.c
index 074a65e..766bf26 100644
--- a/drivers/input/input-leds.c
+++ b/drivers/input/input-leds.c
@@ -71,6 +71,18 @@
 {
 }
 
+static int input_leds_get_count(struct input_dev *dev)
+{
+	unsigned int led_code;
+	int count = 0;
+
+	for_each_set_bit(led_code, dev->ledbit, LED_CNT)
+		if (input_led_info[led_code].name)
+			count++;
+
+	return count;
+}
+
 static int input_leds_connect(struct input_handler *handler,
 			      struct input_dev *dev,
 			      const struct input_device_id *id)
@@ -81,7 +93,7 @@
 	int led_no;
 	int error;
 
-	num_leds = bitmap_weight(dev->ledbit, LED_CNT);
+	num_leds = input_leds_get_count(dev);
 	if (!num_leds)
 		return -ENXIO;
 
@@ -112,7 +124,7 @@
 		led->handle = &leds->handle;
 		led->code = led_code;
 
-		if (WARN_ON(!input_led_info[led_code].name))
+		if (!input_led_info[led_code].name)
 			continue;
 
 		led->cdev.name = kasprintf(GFP_KERNEL, "%s::%s",
diff --git a/drivers/input/joystick/turbografx.c b/drivers/input/joystick/turbografx.c
index 27b6a3c..891797a 100644
--- a/drivers/input/joystick/turbografx.c
+++ b/drivers/input/joystick/turbografx.c
@@ -196,7 +196,7 @@
 		if (n_buttons[i] < 1)
 			continue;
 
-		if (n_buttons[i] > 6) {
+		if (n_buttons[i] > ARRAY_SIZE(tgfx_buttons)) {
 			printk(KERN_ERR "turbografx.c: Invalid number of buttons %d\n", n_buttons[i]);
 			err = -EINVAL;
 			goto err_unreg_devs;
diff --git a/drivers/input/keyboard/gpio_keys_polled.c b/drivers/input/keyboard/gpio_keys_polled.c
index 097d721..c6dc644 100644
--- a/drivers/input/keyboard/gpio_keys_polled.c
+++ b/drivers/input/keyboard/gpio_keys_polled.c
@@ -246,7 +246,7 @@
 		 * convert it to descriptor.
 		 */
 		if (!button->gpiod && gpio_is_valid(button->gpio)) {
-			unsigned flags = 0;
+			unsigned flags = GPIOF_IN;
 
 			if (button->active_low)
 				flags |= GPIOF_ACTIVE_LOW;
diff --git a/drivers/input/misc/axp20x-pek.c b/drivers/input/misc/axp20x-pek.c
index 10e140a..1ac898d 100644
--- a/drivers/input/misc/axp20x-pek.c
+++ b/drivers/input/misc/axp20x-pek.c
@@ -292,3 +292,4 @@
 MODULE_DESCRIPTION("axp20x Power Button");
 MODULE_AUTHOR("Carlo Caione <carlo@caione.org>");
 MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:axp20x-pek");
diff --git a/drivers/input/misc/twl4030-vibra.c b/drivers/input/misc/twl4030-vibra.c
index fc17b95..10c4e3d 100644
--- a/drivers/input/misc/twl4030-vibra.c
+++ b/drivers/input/misc/twl4030-vibra.c
@@ -183,7 +183,8 @@
 	if (pdata && pdata->coexist)
 		return true;
 
-	if (of_find_node_by_name(node, "codec")) {
+	node = of_find_node_by_name(node, "codec");
+	if (node) {
 		of_node_put(node);
 		return true;
 	}
diff --git a/drivers/input/mouse/alps.c b/drivers/input/mouse/alps.c
index 113d6f1..4d24686 100644
--- a/drivers/input/mouse/alps.c
+++ b/drivers/input/mouse/alps.c
@@ -20,6 +20,7 @@
 #include <linux/input/mt.h>
 #include <linux/serio.h>
 #include <linux/libps2.h>
+#include <linux/dmi.h>
 
 #include "psmouse.h"
 #include "alps.h"
@@ -99,6 +100,7 @@
 #define ALPS_FOUR_BUTTONS	0x40	/* 4 direction button present */
 #define ALPS_PS2_INTERLEAVED	0x80	/* 3-byte PS/2 packet interleaved with
 					   6-byte ALPS packet */
+#define ALPS_DELL		0x100	/* device is a Dell laptop */
 #define ALPS_BUTTONPAD		0x200	/* device is a clickpad */
 
 static const struct alps_model_info alps_model_data[] = {
@@ -251,9 +253,9 @@
 		return;
 	}
 
-	/* Non interleaved V2 dualpoint has separate stick button bits */
+	/* Dell non interleaved V2 dualpoint has separate stick button bits */
 	if (priv->proto_version == ALPS_PROTO_V2 &&
-	    priv->flags == (ALPS_PASS | ALPS_DUALPOINT)) {
+	    priv->flags == (ALPS_DELL | ALPS_PASS | ALPS_DUALPOINT)) {
 		left |= packet[0] & 1;
 		right |= packet[0] & 2;
 		middle |= packet[0] & 4;
@@ -2550,6 +2552,8 @@
 	priv->byte0 = protocol->byte0;
 	priv->mask0 = protocol->mask0;
 	priv->flags = protocol->flags;
+	if (dmi_name_in_vendors("Dell"))
+		priv->flags |= ALPS_DELL;
 
 	priv->x_max = 2000;
 	priv->y_max = 1400;
diff --git a/drivers/input/mouse/bcm5974.c b/drivers/input/mouse/bcm5974.c
index b10709f..30e3442 100644
--- a/drivers/input/mouse/bcm5974.c
+++ b/drivers/input/mouse/bcm5974.c
@@ -2,6 +2,7 @@
  * Apple USB BCM5974 (Macbook Air and Penryn Macbook Pro) multitouch driver
  *
  * Copyright (C) 2008	   Henrik Rydberg (rydberg@euromail.se)
+ * Copyright (C) 2015      John Horan (knasher@gmail.com)
  *
  * The USB initialization and package decoding was made by
  * Scott Shawcroft as part of the touchd user-space driver project:
@@ -91,6 +92,10 @@
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI	0x0290
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO	0x0291
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS	0x0292
+/* MacbookPro12,1 (2015) */
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI	0x0272
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_ISO	0x0273
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_JIS	0x0274
 
 #define BCM5974_DEVICE(prod) {					\
 	.match_flags = (USB_DEVICE_ID_MATCH_DEVICE |		\
@@ -152,6 +157,10 @@
 	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI),
 	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING8_ISO),
 	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING8_JIS),
+	/* MacbookPro12,1 */
+	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI),
+	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING9_ISO),
+	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING9_JIS),
 	/* Terminating entry */
 	{}
 };
@@ -180,21 +189,47 @@
 enum tp_type {
 	TYPE1,			/* plain trackpad */
 	TYPE2,			/* button integrated in trackpad */
-	TYPE3			/* additional header fields since June 2013 */
+	TYPE3,			/* additional header fields since June 2013 */
+	TYPE4			/* additional header field for pressure data */
 };
 
 /* trackpad finger data offsets, le16-aligned */
-#define FINGER_TYPE1		(13 * sizeof(__le16))
-#define FINGER_TYPE2		(15 * sizeof(__le16))
-#define FINGER_TYPE3		(19 * sizeof(__le16))
+#define HEADER_TYPE1		(13 * sizeof(__le16))
+#define HEADER_TYPE2		(15 * sizeof(__le16))
+#define HEADER_TYPE3		(19 * sizeof(__le16))
+#define HEADER_TYPE4		(23 * sizeof(__le16))
 
 /* trackpad button data offsets */
+#define BUTTON_TYPE1		0
 #define BUTTON_TYPE2		15
 #define BUTTON_TYPE3		23
+#define BUTTON_TYPE4		31
 
 /* list of device capability bits */
 #define HAS_INTEGRATED_BUTTON	1
 
+/* trackpad finger data block size */
+#define FSIZE_TYPE1		(14 * sizeof(__le16))
+#define FSIZE_TYPE2		(14 * sizeof(__le16))
+#define FSIZE_TYPE3		(14 * sizeof(__le16))
+#define FSIZE_TYPE4		(15 * sizeof(__le16))
+
+/* offset from header to finger struct */
+#define DELTA_TYPE1		(0 * sizeof(__le16))
+#define DELTA_TYPE2		(0 * sizeof(__le16))
+#define DELTA_TYPE3		(0 * sizeof(__le16))
+#define DELTA_TYPE4		(1 * sizeof(__le16))
+
+/* usb control message mode switch data */
+#define USBMSG_TYPE1		8, 0x300, 0, 0, 0x1, 0x8
+#define USBMSG_TYPE2		8, 0x300, 0, 0, 0x1, 0x8
+#define USBMSG_TYPE3		8, 0x300, 0, 0, 0x1, 0x8
+#define USBMSG_TYPE4		2, 0x302, 2, 1, 0x1, 0x0
+
+/* Wellspring initialization constants */
+#define BCM5974_WELLSPRING_MODE_READ_REQUEST_ID		1
+#define BCM5974_WELLSPRING_MODE_WRITE_REQUEST_ID	9
+
 /* trackpad finger structure, le16-aligned */
 struct tp_finger {
 	__le16 origin;		/* zero when switching track finger */
@@ -207,14 +242,13 @@
 	__le16 orientation;	/* 16384 when point, else 15 bit angle */
 	__le16 touch_major;	/* touch area, major axis */
 	__le16 touch_minor;	/* touch area, minor axis */
-	__le16 unused[3];	/* zeros */
+	__le16 unused[2];	/* zeros */
+	__le16 pressure;	/* pressure on forcetouch touchpad */
 	__le16 multi;		/* one finger: varies, more fingers: constant */
 } __attribute__((packed,aligned(2)));
 
 /* trackpad finger data size, empirically at least ten fingers */
 #define MAX_FINGERS		16
-#define SIZEOF_FINGER		sizeof(struct tp_finger)
-#define SIZEOF_ALL_FINGERS	(MAX_FINGERS * SIZEOF_FINGER)
 #define MAX_FINGER_ORIENTATION	16384
 
 /* device-specific parameters */
@@ -232,8 +266,17 @@
 	int bt_datalen;		/* data length of the button interface */
 	int tp_ep;		/* the endpoint of the trackpad interface */
 	enum tp_type tp_type;	/* type of trackpad interface */
-	int tp_offset;		/* offset to trackpad finger data */
+	int tp_header;		/* bytes in header block */
 	int tp_datalen;		/* data length of the trackpad interface */
+	int tp_button;		/* offset to button data */
+	int tp_fsize;		/* bytes in single finger block */
+	int tp_delta;		/* offset from header to finger struct */
+	int um_size;		/* usb control message length */
+	int um_req_val;		/* usb control message value */
+	int um_req_idx;		/* usb control message index */
+	int um_switch_idx;	/* usb control message mode switch index */
+	int um_switch_on;	/* usb control message mode switch on */
+	int um_switch_off;	/* usb control message mode switch off */
 	struct bcm5974_param p;	/* finger pressure limits */
 	struct bcm5974_param w;	/* finger width limits */
 	struct bcm5974_param x;	/* horizontal limits */
@@ -259,6 +302,24 @@
 	int slots[MAX_FINGERS];				/* slot assignments */
 };
 
+/* trackpad finger block data, le16-aligned */
+static const struct tp_finger *get_tp_finger(const struct bcm5974 *dev, int i)
+{
+	const struct bcm5974_config *c = &dev->cfg;
+	u8 *f_base = dev->tp_data + c->tp_header + c->tp_delta;
+
+	return (const struct tp_finger *)(f_base + i * c->tp_fsize);
+}
+
+#define DATAFORMAT(type)				\
+	type,						\
+	HEADER_##type,					\
+	HEADER_##type + (MAX_FINGERS) * (FSIZE_##type),	\
+	BUTTON_##type,					\
+	FSIZE_##type,					\
+	DELTA_##type,					\
+	USBMSG_##type
+
 /* logical signal quality */
 #define SN_PRESSURE	45		/* pressure signal-to-noise ratio */
 #define SN_WIDTH	25		/* width signal-to-noise ratio */
@@ -273,7 +334,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING_JIS,
 		0,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE1, FINGER_TYPE1, FINGER_TYPE1 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE1),
 		{ SN_PRESSURE, 0, 256 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4824, 5342 },
@@ -286,7 +347,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING2_JIS,
 		0,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE1, FINGER_TYPE1, FINGER_TYPE1 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE1),
 		{ SN_PRESSURE, 0, 256 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4824, 4824 },
@@ -299,7 +360,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING3_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4460, 5166 },
@@ -312,7 +373,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING4_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4620, 5140 },
@@ -325,7 +386,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING4A_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4616, 5112 },
@@ -338,7 +399,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING5_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4415, 5050 },
@@ -351,7 +412,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING6_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4620, 5140 },
@@ -364,7 +425,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4750, 5280 },
@@ -377,7 +438,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING6A_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4620, 5140 },
@@ -390,7 +451,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING7_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4750, 5280 },
@@ -403,7 +464,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING7A_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4750, 5280 },
@@ -416,13 +477,26 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING8_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0, sizeof(struct bt_data),
-		0x83, TYPE3, FINGER_TYPE3, FINGER_TYPE3 + SIZEOF_ALL_FINGERS,
+		0x83, DATAFORMAT(TYPE3),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4620, 5140 },
 		{ SN_COORD, -150, 6600 },
 		{ SN_ORIENT, -MAX_FINGER_ORIENTATION, MAX_FINGER_ORIENTATION }
 	},
+	{
+		USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI,
+		USB_DEVICE_ID_APPLE_WELLSPRING9_ISO,
+		USB_DEVICE_ID_APPLE_WELLSPRING9_JIS,
+		HAS_INTEGRATED_BUTTON,
+		0, sizeof(struct bt_data),
+		0x83, DATAFORMAT(TYPE4),
+		{ SN_PRESSURE, 0, 300 },
+		{ SN_WIDTH, 0, 2048 },
+		{ SN_COORD, -4828, 5345 },
+		{ SN_COORD, -203, 6803 },
+		{ SN_ORIENT, -MAX_FINGER_ORIENTATION, MAX_FINGER_ORIENTATION }
+	},
 	{}
 };
 
@@ -549,19 +623,18 @@
 	struct input_dev *input = dev->input;
 	int raw_n, i, n = 0;
 
-	if (size < c->tp_offset || (size - c->tp_offset) % SIZEOF_FINGER != 0)
+	if (size < c->tp_header || (size - c->tp_header) % c->tp_fsize != 0)
 		return -EIO;
 
-	/* finger data, le16-aligned */
-	f = (const struct tp_finger *)(dev->tp_data + c->tp_offset);
-	raw_n = (size - c->tp_offset) / SIZEOF_FINGER;
+	raw_n = (size - c->tp_header) / c->tp_fsize;
 
 	for (i = 0; i < raw_n; i++) {
-		if (raw2int(f[i].touch_major) == 0)
+		f = get_tp_finger(dev, i);
+		if (raw2int(f->touch_major) == 0)
 			continue;
-		dev->pos[n].x = raw2int(f[i].abs_x);
-		dev->pos[n].y = c->y.min + c->y.max - raw2int(f[i].abs_y);
-		dev->index[n++] = &f[i];
+		dev->pos[n].x = raw2int(f->abs_x);
+		dev->pos[n].y = c->y.min + c->y.max - raw2int(f->abs_y);
+		dev->index[n++] = f;
 	}
 
 	input_mt_assign_slots(input, dev->slots, dev->pos, n, 0);
@@ -572,32 +645,22 @@
 
 	input_mt_sync_frame(input);
 
-	report_synaptics_data(input, c, f, raw_n);
+	report_synaptics_data(input, c, get_tp_finger(dev, 0), raw_n);
 
-	/* type 2 reports button events via ibt only */
-	if (c->tp_type == TYPE2) {
-		int ibt = raw2int(dev->tp_data[BUTTON_TYPE2]);
+	/* later types report button events via integrated button only */
+	if (c->caps & HAS_INTEGRATED_BUTTON) {
+		int ibt = raw2int(dev->tp_data[c->tp_button]);
 		input_report_key(input, BTN_LEFT, ibt);
 	}
 
-	if (c->tp_type == TYPE3)
-		input_report_key(input, BTN_LEFT, dev->tp_data[BUTTON_TYPE3]);
-
 	input_sync(input);
 
 	return 0;
 }
 
-/* Wellspring initialization constants */
-#define BCM5974_WELLSPRING_MODE_READ_REQUEST_ID		1
-#define BCM5974_WELLSPRING_MODE_WRITE_REQUEST_ID	9
-#define BCM5974_WELLSPRING_MODE_REQUEST_VALUE		0x300
-#define BCM5974_WELLSPRING_MODE_REQUEST_INDEX		0
-#define BCM5974_WELLSPRING_MODE_VENDOR_VALUE		0x01
-#define BCM5974_WELLSPRING_MODE_NORMAL_VALUE		0x08
-
 static int bcm5974_wellspring_mode(struct bcm5974 *dev, bool on)
 {
+	const struct bcm5974_config *c = &dev->cfg;
 	int retval = 0, size;
 	char *data;
 
@@ -605,7 +668,7 @@
 	if (dev->cfg.tp_type == TYPE3)
 		return 0;
 
-	data = kmalloc(8, GFP_KERNEL);
+	data = kmalloc(c->um_size, GFP_KERNEL);
 	if (!data) {
 		dev_err(&dev->intf->dev, "out of memory\n");
 		retval = -ENOMEM;
@@ -616,28 +679,24 @@
 	size = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
 			BCM5974_WELLSPRING_MODE_READ_REQUEST_ID,
 			USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE,
-			BCM5974_WELLSPRING_MODE_REQUEST_VALUE,
-			BCM5974_WELLSPRING_MODE_REQUEST_INDEX, data, 8, 5000);
+			c->um_req_val, c->um_req_idx, data, c->um_size, 5000);
 
-	if (size != 8) {
+	if (size != c->um_size) {
 		dev_err(&dev->intf->dev, "could not read from device\n");
 		retval = -EIO;
 		goto out;
 	}
 
 	/* apply the mode switch */
-	data[0] = on ?
-		BCM5974_WELLSPRING_MODE_VENDOR_VALUE :
-		BCM5974_WELLSPRING_MODE_NORMAL_VALUE;
+	data[c->um_switch_idx] = on ? c->um_switch_on : c->um_switch_off;
 
 	/* write configuration */
 	size = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
 			BCM5974_WELLSPRING_MODE_WRITE_REQUEST_ID,
 			USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE,
-			BCM5974_WELLSPRING_MODE_REQUEST_VALUE,
-			BCM5974_WELLSPRING_MODE_REQUEST_INDEX, data, 8, 5000);
+			c->um_req_val, c->um_req_idx, data, c->um_size, 5000);
 
-	if (size != 8) {
+	if (size != c->um_size) {
 		dev_err(&dev->intf->dev, "could not write to device\n");
 		retval = -EIO;
 		goto out;
diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
index 62641f2..5b5f403 100644
--- a/drivers/input/mouse/elan_i2c_core.c
+++ b/drivers/input/mouse/elan_i2c_core.c
@@ -771,7 +771,7 @@
  */
 static void elan_report_contact(struct elan_tp_data *data,
 				int contact_num, bool contact_valid,
-				bool hover_event, u8 *finger_data)
+				u8 *finger_data)
 {
 	struct input_dev *input = data->input;
 	unsigned int pos_x, pos_y;
@@ -815,9 +815,7 @@
 		input_mt_report_slot_state(input, MT_TOOL_FINGER, true);
 		input_report_abs(input, ABS_MT_POSITION_X, pos_x);
 		input_report_abs(input, ABS_MT_POSITION_Y, data->max_y - pos_y);
-		input_report_abs(input, ABS_MT_DISTANCE, hover_event);
-		input_report_abs(input, ABS_MT_PRESSURE,
-				 hover_event ? 0 : scaled_pressure);
+		input_report_abs(input, ABS_MT_PRESSURE, scaled_pressure);
 		input_report_abs(input, ABS_TOOL_WIDTH, mk_x);
 		input_report_abs(input, ABS_MT_TOUCH_MAJOR, major);
 		input_report_abs(input, ABS_MT_TOUCH_MINOR, minor);
@@ -839,14 +837,14 @@
 	hover_event = hover_info & 0x40;
 	for (i = 0; i < ETP_MAX_FINGERS; i++) {
 		contact_valid = tp_info & (1U << (3 + i));
-		elan_report_contact(data, i, contact_valid, hover_event,
-				    finger_data);
+		elan_report_contact(data, i, contact_valid, finger_data);
 
 		if (contact_valid)
 			finger_data += ETP_FINGER_DATA_LEN;
 	}
 
 	input_report_key(input, BTN_LEFT, tp_info & 0x01);
+	input_report_abs(input, ABS_DISTANCE, hover_event != 0);
 	input_mt_report_pointer_emulation(input, true);
 	input_sync(input);
 }
@@ -922,6 +920,7 @@
 	input_abs_set_res(input, ABS_Y, data->y_res);
 	input_set_abs_params(input, ABS_PRESSURE, 0, ETP_MAX_PRESSURE, 0, 0);
 	input_set_abs_params(input, ABS_TOOL_WIDTH, 0, ETP_FINGER_WIDTH, 0, 0);
+	input_set_abs_params(input, ABS_DISTANCE, 0, 1, 0, 0);
 
 	/* And MT parameters */
 	input_set_abs_params(input, ABS_MT_POSITION_X, 0, data->max_x, 0, 0);
@@ -934,7 +933,6 @@
 			     ETP_FINGER_WIDTH * max_width, 0, 0);
 	input_set_abs_params(input, ABS_MT_TOUCH_MINOR, 0,
 			     ETP_FINGER_WIDTH * min_width, 0, 0);
-	input_set_abs_params(input, ABS_MT_DISTANCE, 0, 1, 0, 0);
 
 	data->input = input;
 
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index ce3d400..2955f1d 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -783,19 +783,26 @@
 	struct elantech_data *etd = psmouse->private;
 	unsigned char *packet = psmouse->packet;
 	unsigned char packet_type = packet[3] & 0x03;
+	unsigned int ic_version;
 	bool sanity_check;
 
 	if (etd->tp_dev && (packet[3] & 0x0f) == 0x06)
 		return PACKET_TRACKPOINT;
 
+	/* This represents the version of IC body. */
+	ic_version = (etd->fw_version & 0x0f0000) >> 16;
+
 	/*
 	 * Sanity check based on the constant bits of a packet.
 	 * The constant bits change depending on the value of
-	 * the hardware flag 'crc_enabled' but are the same for
-	 * every packet, regardless of the type.
+	 * the hardware flag 'crc_enabled' and the version of
+	 * the IC body, but are the same for every packet,
+	 * regardless of the type.
 	 */
 	if (etd->crc_enabled)
 		sanity_check = ((packet[3] & 0x08) == 0x00);
+	else if (ic_version == 7 && etd->samples[1] == 0x2A)
+		sanity_check = ((packet[3] & 0x1c) == 0x10);
 	else
 		sanity_check = ((packet[0] & 0x0c) == 0x04 &&
 				(packet[3] & 0x1c) == 0x10);
@@ -1116,6 +1123,7 @@
  * Avatar AVIU-145A2       0x361f00        ?               clickpad
  * Fujitsu LIFEBOOK E544   0x470f00        d0, 12, 09      2 hw buttons
  * Fujitsu LIFEBOOK E554   0x570f01        40, 14, 0c      2 hw buttons
+ * Fujitsu T725            0x470f01        05, 12, 09      2 hw buttons
  * Fujitsu H730            0x570f00        c0, 14, 0c      3 hw buttons (**)
  * Gigabyte U2442          0x450f01        58, 17, 0c      2 hw buttons
  * Lenovo L430             0x350f02        b9, 15, 0c      2 hw buttons (*)
@@ -1167,7 +1175,7 @@
 	struct input_dev *dev = psmouse->dev;
 	struct elantech_data *etd = psmouse->private;
 	unsigned int x_min = 0, y_min = 0, x_max = 0, y_max = 0, width = 0;
-	unsigned int x_res = 0, y_res = 0;
+	unsigned int x_res = 31, y_res = 31;
 
 	if (elantech_set_range(psmouse, &x_min, &y_min, &x_max, &y_max, &width))
 		return -1;
@@ -1232,8 +1240,6 @@
 		/* For X to recognize me as touchpad. */
 		input_set_abs_params(dev, ABS_X, x_min, x_max, 0, 0);
 		input_set_abs_params(dev, ABS_Y, y_min, y_max, 0, 0);
-		input_abs_set_res(dev, ABS_X, x_res);
-		input_abs_set_res(dev, ABS_Y, y_res);
 		/*
 		 * range of pressure and width is the same as v2,
 		 * report ABS_PRESSURE, ABS_TOOL_WIDTH for compatibility.
@@ -1246,8 +1252,6 @@
 		input_mt_init_slots(dev, ETP_MAX_FINGERS, 0);
 		input_set_abs_params(dev, ABS_MT_POSITION_X, x_min, x_max, 0, 0);
 		input_set_abs_params(dev, ABS_MT_POSITION_Y, y_min, y_max, 0, 0);
-		input_abs_set_res(dev, ABS_MT_POSITION_X, x_res);
-		input_abs_set_res(dev, ABS_MT_POSITION_Y, y_res);
 		input_set_abs_params(dev, ABS_MT_PRESSURE, ETP_PMIN_V2,
 				     ETP_PMAX_V2, 0, 0);
 		/*
@@ -1259,6 +1263,13 @@
 		break;
 	}
 
+	input_abs_set_res(dev, ABS_X, x_res);
+	input_abs_set_res(dev, ABS_Y, y_res);
+	if (etd->hw_version > 1) {
+		input_abs_set_res(dev, ABS_MT_POSITION_X, x_res);
+		input_abs_set_res(dev, ABS_MT_POSITION_Y, y_res);
+	}
+
 	etd->y_max = y_max;
 	etd->width = width;
 
@@ -1648,6 +1659,16 @@
 		     etd->capabilities[0], etd->capabilities[1],
 		     etd->capabilities[2]);
 
+	if (etd->hw_version != 1) {
+		if (etd->send_cmd(psmouse, ETP_SAMPLE_QUERY, etd->samples)) {
+			psmouse_err(psmouse, "failed to query sample data\n");
+			goto init_fail;
+		}
+		psmouse_info(psmouse,
+			     "Elan sample query result %02x, %02x, %02x\n",
+			     etd->samples[0], etd->samples[1], etd->samples[2]);
+	}
+
 	if (elantech_set_absolute_mode(psmouse)) {
 		psmouse_err(psmouse,
 			    "failed to put touchpad into absolute mode.\n");
diff --git a/drivers/input/mouse/elantech.h b/drivers/input/mouse/elantech.h
index f965d15..e1cbf40 100644
--- a/drivers/input/mouse/elantech.h
+++ b/drivers/input/mouse/elantech.h
@@ -129,6 +129,7 @@
 	unsigned char reg_26;
 	unsigned char debug;
 	unsigned char capabilities[3];
+	unsigned char samples[3];
 	bool paritycheck;
 	bool jumpy_cursor;
 	bool reports_pressure;
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 35c8d0c..6025eb4 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -1199,7 +1199,7 @@
 					ABS_MT_POSITION_Y);
 		/* Image sensors can report per-contact pressure */
 		input_set_abs_params(dev, ABS_MT_PRESSURE, 0, 255, 0, 0);
-		input_mt_init_slots(dev, 3, INPUT_MT_POINTER | INPUT_MT_TRACK);
+		input_mt_init_slots(dev, 2, INPUT_MT_POINTER | INPUT_MT_TRACK);
 
 		/* Image sensors can signal 4 and 5 finger clicks */
 		__set_bit(BTN_TOOL_QUADTAP, dev->keybit);
@@ -1484,12 +1484,12 @@
 	priv->pkt_type = SYN_MODEL_NEWABS(priv->model_id) ? SYN_NEWABS : SYN_OLDABS;
 
 	psmouse_info(psmouse,
-		     "Touchpad model: %ld, fw: %ld.%ld, id: %#lx, caps: %#lx/%#lx/%#lx, board id: %lu, fw id: %lu\n",
+		     "Touchpad model: %ld, fw: %ld.%ld, id: %#lx, caps: %#lx/%#lx/%#lx/%#lx, board id: %lu, fw id: %lu\n",
 		     SYN_ID_MODEL(priv->identity),
 		     SYN_ID_MAJOR(priv->identity), SYN_ID_MINOR(priv->identity),
 		     priv->model_id,
 		     priv->capabilities, priv->ext_cap, priv->ext_cap_0c,
-		     priv->board_id, priv->firmware_id);
+		     priv->ext_cap_10, priv->board_id, priv->firmware_id);
 
 	set_input_params(psmouse, priv);
 
diff --git a/drivers/input/touchscreen/goodix.c b/drivers/input/touchscreen/goodix.c
index b4d12e2..e36162b 100644
--- a/drivers/input/touchscreen/goodix.c
+++ b/drivers/input/touchscreen/goodix.c
@@ -15,6 +15,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/dmi.h>
 #include <linux/i2c.h>
 #include <linux/input.h>
 #include <linux/input/mt.h>
@@ -34,6 +35,7 @@
 	int abs_y_max;
 	unsigned int max_touch_num;
 	unsigned int int_trigger_type;
+	bool rotated_screen;
 };
 
 #define GOODIX_MAX_HEIGHT		4096
@@ -60,6 +62,30 @@
 	IRQ_TYPE_LEVEL_HIGH,
 };
 
+/*
+ * Those tablets have their coordinates origin at the bottom right
+ * of the tablet, as if rotated 180 degrees
+ */
+static const struct dmi_system_id rotated_screen[] = {
+#if defined(CONFIG_DMI) && defined(CONFIG_X86)
+	{
+		.ident = "WinBook TW100",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "WinBook"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TW100")
+		}
+	},
+	{
+		.ident = "WinBook TW700",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "WinBook"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "TW700")
+		},
+	},
+#endif
+	{}
+};
+
 /**
  * goodix_i2c_read - read data from a register of the i2c slave device.
  *
@@ -129,6 +155,11 @@
 	int input_y = get_unaligned_le16(&coor_data[3]);
 	int input_w = get_unaligned_le16(&coor_data[5]);
 
+	if (ts->rotated_screen) {
+		input_x = ts->abs_x_max - input_x;
+		input_y = ts->abs_y_max - input_y;
+	}
+
 	input_mt_slot(ts->input_dev, id);
 	input_mt_report_slot_state(ts->input_dev, MT_TOOL_FINGER, true);
 	input_report_abs(ts->input_dev, ABS_MT_POSITION_X, input_x);
@@ -223,6 +254,11 @@
 		ts->abs_y_max = GOODIX_MAX_HEIGHT;
 		ts->max_touch_num = GOODIX_MAX_CONTACTS;
 	}
+
+	ts->rotated_screen = dmi_check_system(rotated_screen);
+	if (ts->rotated_screen)
+		dev_dbg(&ts->client->dev,
+			 "Applying '180 degrees rotated screen' quirk\n");
 }
 
 /**
diff --git a/drivers/input/touchscreen/usbtouchscreen.c b/drivers/input/touchscreen/usbtouchscreen.c
index f2c6c35..2c41107 100644
--- a/drivers/input/touchscreen/usbtouchscreen.c
+++ b/drivers/input/touchscreen/usbtouchscreen.c
@@ -627,6 +627,9 @@
 		goto err_out;
 	}
 
+	/* TSC-25 data sheet specifies a delay after the RESET command */
+	msleep(150);
+
 	/* set coordinate output rate */
 	buf[0] = buf[1] = 0xFF;
 	ret = usb_control_msg(dev, usb_rcvctrlpipe (dev, 0),
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index a57e9b7..658ee39 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -76,8 +76,6 @@
  * Domain for untranslated devices - only allocated
  * if iommu=pt passed on kernel cmd line.
  */
-static struct protection_domain *pt_domain;
-
 static const struct iommu_ops amd_iommu_ops;
 
 static ATOMIC_NOTIFIER_HEAD(ppr_notifier);
@@ -96,7 +94,7 @@
 	struct protection_domain *domain; /* Domain the device is bound to */
 	u16 devid;			  /* PCI Device ID */
 	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
-	bool passthrough;		  /* Default for device is pt_domain */
+	bool passthrough;		  /* Device is identity mapped */
 	struct {
 		bool enabled;
 		int qdep;
@@ -116,7 +114,6 @@
 struct kmem_cache *amd_iommu_irq_cache;
 
 static void update_domain(struct protection_domain *domain);
-static int alloc_passthrough_domain(void);
 static int protection_domain_init(struct protection_domain *domain);
 
 /****************************************************************************
@@ -2167,15 +2164,17 @@
 	dev_data = get_dev_data(dev);
 
 	if (domain->flags & PD_IOMMUV2_MASK) {
-		if (!dev_data->iommu_v2 || !dev_data->passthrough)
+		if (!dev_data->passthrough)
 			return -EINVAL;
 
-		if (pdev_iommuv2_enable(pdev) != 0)
-			return -EINVAL;
+		if (dev_data->iommu_v2) {
+			if (pdev_iommuv2_enable(pdev) != 0)
+				return -EINVAL;
 
-		dev_data->ats.enabled = true;
-		dev_data->ats.qdep    = pci_ats_queue_depth(pdev);
-		dev_data->pri_tlp     = pci_pri_tlp_required(pdev);
+			dev_data->ats.enabled = true;
+			dev_data->ats.qdep    = pci_ats_queue_depth(pdev);
+			dev_data->pri_tlp     = pci_pri_tlp_required(pdev);
+		}
 	} else if (amd_iommu_iotlb_sup &&
 		   pci_enable_ats(pdev, PAGE_SHIFT) == 0) {
 		dev_data->ats.enabled = true;
@@ -2221,15 +2220,6 @@
 	do_detach(head);
 
 	spin_unlock_irqrestore(&domain->lock, flags);
-
-	/*
-	 * If we run in passthrough mode the device must be assigned to the
-	 * passthrough domain if it is detached from any other domain.
-	 * Make sure we can deassign from the pt_domain itself.
-	 */
-	if (dev_data->passthrough &&
-	    (dev_data->domain == NULL && domain != pt_domain))
-		__attach_device(dev_data, pt_domain);
 }
 
 /*
@@ -2249,7 +2239,7 @@
 	__detach_device(dev_data);
 	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
 
-	if (domain->flags & PD_IOMMUV2_MASK)
+	if (domain->flags & PD_IOMMUV2_MASK && dev_data->iommu_v2)
 		pdev_iommuv2_disable(to_pci_dev(dev));
 	else if (dev_data->ats.enabled)
 		pci_disable_ats(to_pci_dev(dev));
@@ -2287,17 +2277,15 @@
 
 	BUG_ON(!dev_data);
 
-	if (dev_data->iommu_v2)
+	if (iommu_pass_through || dev_data->iommu_v2)
 		iommu_request_dm_for_dev(dev);
 
 	/* Domains are initialized for this device - have a look what we ended up with */
 	domain = iommu_get_domain_for_dev(dev);
-	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
+	if (domain->type == IOMMU_DOMAIN_IDENTITY)
 		dev_data->passthrough = true;
-		dev->archdata.dma_ops = &nommu_dma_ops;
-	} else {
+	else
 		dev->archdata.dma_ops = &amd_iommu_dma_ops;
-	}
 
 out:
 	iommu_completion_wait(iommu);
@@ -2862,8 +2850,17 @@
 
 int __init amd_iommu_init_dma_ops(void)
 {
+	swiotlb        = iommu_pass_through ? 1 : 0;
 	iommu_detected = 1;
-	swiotlb = 0;
+
+	/*
+	 * In case we don't initialize SWIOTLB (actually the common case
+	 * when AMD IOMMU is enabled), make sure there are global
+	 * dma_ops set as a fall-back for devices not handled by this
+	 * driver (for example non-PCI devices).
+	 */
+	if (!swiotlb)
+		dma_ops = &nommu_dma_ops;
 
 	amd_iommu_stats_init();
 
@@ -2947,21 +2944,6 @@
 	return NULL;
 }
 
-static int alloc_passthrough_domain(void)
-{
-	if (pt_domain != NULL)
-		return 0;
-
-	/* allocate passthrough domain */
-	pt_domain = protection_domain_alloc();
-	if (!pt_domain)
-		return -ENOMEM;
-
-	pt_domain->mode = PAGE_MODE_NONE;
-
-	return 0;
-}
-
 static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 {
 	struct protection_domain *pdomain;
@@ -3222,33 +3204,6 @@
  *
  *****************************************************************************/
 
-int __init amd_iommu_init_passthrough(void)
-{
-	struct iommu_dev_data *dev_data;
-	struct pci_dev *dev = NULL;
-	int ret;
-
-	ret = alloc_passthrough_domain();
-	if (ret)
-		return ret;
-
-	for_each_pci_dev(dev) {
-		if (!check_device(&dev->dev))
-			continue;
-
-		dev_data = get_dev_data(&dev->dev);
-		dev_data->passthrough = true;
-
-		attach_device(&dev->dev, pt_domain);
-	}
-
-	amd_iommu_stats_init();
-
-	pr_info("AMD-Vi: Initialized for Passthrough Mode\n");
-
-	return 0;
-}
-
 /* IOMMUv2 specific functions */
 int amd_iommu_register_ppr_notifier(struct notifier_block *nb)
 {
@@ -3363,7 +3318,12 @@
 		struct amd_iommu *iommu;
 		int qdep;
 
-		BUG_ON(!dev_data->ats.enabled);
+		/*
+		   There might be non-IOMMUv2 capable devices in an IOMMUv2
+		 * domain.
+		 */
+		if (!dev_data->ats.enabled)
+			continue;
 
 		qdep  = dev_data->ats.qdep;
 		iommu = amd_iommu_rlookup_table[dev_data->devid];
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index dbda9ae..a24495e 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -2026,14 +2026,6 @@
 	return true;
 }
 
-static int amd_iommu_init_dma(void)
-{
-	if (iommu_pass_through)
-		return amd_iommu_init_passthrough();
-	else
-		return amd_iommu_init_dma_ops();
-}
-
 /****************************************************************************
  *
  * AMD IOMMU Initialization State Machine
@@ -2073,7 +2065,7 @@
 		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_INTERRUPTS_EN;
 		break;
 	case IOMMU_INTERRUPTS_EN:
-		ret = amd_iommu_init_dma();
+		ret = amd_iommu_init_dma_ops();
 		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_DMA_OPS;
 		break;
 	case IOMMU_DMA_OPS:
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 3465faf..f7b875b 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -132,11 +132,19 @@
 
 static void free_device_state(struct device_state *dev_state)
 {
+	struct iommu_group *group;
+
 	/*
 	 * First detach device from domain - No more PRI requests will arrive
 	 * from that device after it is unbound from the IOMMUv2 domain.
 	 */
-	iommu_detach_device(dev_state->domain, &dev_state->pdev->dev);
+	group = iommu_group_get(&dev_state->pdev->dev);
+	if (WARN_ON(!group))
+		return;
+
+	iommu_detach_group(dev_state->domain, group);
+
+	iommu_group_put(group);
 
 	/* Everything is down now, free the IOMMUv2 domain */
 	iommu_domain_free(dev_state->domain);
@@ -731,6 +739,7 @@
 int amd_iommu_init_device(struct pci_dev *pdev, int pasids)
 {
 	struct device_state *dev_state;
+	struct iommu_group *group;
 	unsigned long flags;
 	int ret, tmp;
 	u16 devid;
@@ -776,10 +785,16 @@
 	if (ret)
 		goto out_free_domain;
 
-	ret = iommu_attach_device(dev_state->domain, &pdev->dev);
-	if (ret != 0)
+	group = iommu_group_get(&pdev->dev);
+	if (!group)
 		goto out_free_domain;
 
+	ret = iommu_attach_group(dev_state->domain, group);
+	if (ret != 0)
+		goto out_drop_group;
+
+	iommu_group_put(group);
+
 	spin_lock_irqsave(&state_lock, flags);
 
 	if (__get_device_state(devid) != NULL) {
@@ -794,6 +809,9 @@
 
 	return 0;
 
+out_drop_group:
+	iommu_group_put(group);
+
 out_free_domain:
 	iommu_domain_free(dev_state->domain);
 
diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c
index 8e9ec81..da902ba 100644
--- a/drivers/iommu/arm-smmu-v3.c
+++ b/drivers/iommu/arm-smmu-v3.c
@@ -199,9 +199,10 @@
  * Stream table.
  *
  * Linear: Enough to cover 1 << IDR1.SIDSIZE entries
- * 2lvl: 8k L1 entries, 256 lazy entries per table (each table covers a PCI bus)
+ * 2lvl: 128k L1 entries,
+ *       256 lazy entries per table (each table covers a PCI bus)
  */
-#define STRTAB_L1_SZ_SHIFT		16
+#define STRTAB_L1_SZ_SHIFT		20
 #define STRTAB_SPLIT			8
 
 #define STRTAB_L1_DESC_DWORDS		1
@@ -269,10 +270,10 @@
 #define ARM64_TCR_TG0_SHIFT		14
 #define ARM64_TCR_TG0_MASK		0x3UL
 #define CTXDESC_CD_0_TCR_IRGN0_SHIFT	8
-#define ARM64_TCR_IRGN0_SHIFT		24
+#define ARM64_TCR_IRGN0_SHIFT		8
 #define ARM64_TCR_IRGN0_MASK		0x3UL
 #define CTXDESC_CD_0_TCR_ORGN0_SHIFT	10
-#define ARM64_TCR_ORGN0_SHIFT		26
+#define ARM64_TCR_ORGN0_SHIFT		10
 #define ARM64_TCR_ORGN0_MASK		0x3UL
 #define CTXDESC_CD_0_TCR_SH0_SHIFT	12
 #define ARM64_TCR_SH0_SHIFT		12
@@ -542,6 +543,9 @@
 #define ARM_SMMU_FEAT_HYP		(1 << 12)
 	u32				features;
 
+#define ARM_SMMU_OPT_SKIP_PREFETCH	(1 << 0)
+	u32				options;
+
 	struct arm_smmu_cmdq		cmdq;
 	struct arm_smmu_evtq		evtq;
 	struct arm_smmu_priq		priq;
@@ -602,11 +606,35 @@
 static DEFINE_SPINLOCK(arm_smmu_devices_lock);
 static LIST_HEAD(arm_smmu_devices);
 
+struct arm_smmu_option_prop {
+	u32 opt;
+	const char *prop;
+};
+
+static struct arm_smmu_option_prop arm_smmu_options[] = {
+	{ ARM_SMMU_OPT_SKIP_PREFETCH, "hisilicon,broken-prefetch-cmd" },
+	{ 0, NULL},
+};
+
 static struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom)
 {
 	return container_of(dom, struct arm_smmu_domain, domain);
 }
 
+static void parse_driver_options(struct arm_smmu_device *smmu)
+{
+	int i = 0;
+
+	do {
+		if (of_property_read_bool(smmu->dev->of_node,
+						arm_smmu_options[i].prop)) {
+			smmu->options |= arm_smmu_options[i].opt;
+			dev_notice(smmu->dev, "option %s\n",
+				arm_smmu_options[i].prop);
+		}
+	} while (arm_smmu_options[++i].opt);
+}
+
 /* Low-level queue manipulation functions */
 static bool queue_full(struct arm_smmu_queue *q)
 {
@@ -1036,7 +1064,8 @@
 	arm_smmu_sync_ste_for_sid(smmu, sid);
 
 	/* It's likely that we'll want to use the new STE soon */
-	arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
+	if (!(smmu->options & ARM_SMMU_OPT_SKIP_PREFETCH))
+		arm_smmu_cmdq_issue_cmd(smmu, &prefetch_cmd);
 }
 
 static void arm_smmu_init_bypass_stes(u64 *strtab, unsigned int nent)
@@ -1064,7 +1093,7 @@
 		return 0;
 
 	size = 1 << (STRTAB_SPLIT + ilog2(STRTAB_STE_DWORDS) + 3);
-	strtab = &cfg->strtab[sid >> STRTAB_SPLIT << STRTAB_L1_DESC_DWORDS];
+	strtab = &cfg->strtab[(sid >> STRTAB_SPLIT) * STRTAB_L1_DESC_DWORDS];
 
 	desc->span = STRTAB_SPLIT + 1;
 	desc->l2ptr = dma_zalloc_coherent(smmu->dev, size, &desc->l2ptr_dma,
@@ -2020,21 +2049,23 @@
 {
 	void *strtab;
 	u64 reg;
-	u32 size;
+	u32 size, l1size;
 	int ret;
 	struct arm_smmu_strtab_cfg *cfg = &smmu->strtab_cfg;
 
 	/* Calculate the L1 size, capped to the SIDSIZE */
 	size = STRTAB_L1_SZ_SHIFT - (ilog2(STRTAB_L1_DESC_DWORDS) + 3);
 	size = min(size, smmu->sid_bits - STRTAB_SPLIT);
-	if (size + STRTAB_SPLIT < smmu->sid_bits)
+	cfg->num_l1_ents = 1 << size;
+
+	size += STRTAB_SPLIT;
+	if (size < smmu->sid_bits)
 		dev_warn(smmu->dev,
 			 "2-level strtab only covers %u/%u bits of SID\n",
-			 size + STRTAB_SPLIT, smmu->sid_bits);
+			 size, smmu->sid_bits);
 
-	cfg->num_l1_ents = 1 << size;
-	size = cfg->num_l1_ents * (STRTAB_L1_DESC_DWORDS << 3);
-	strtab = dma_zalloc_coherent(smmu->dev, size, &cfg->strtab_dma,
+	l1size = cfg->num_l1_ents * (STRTAB_L1_DESC_DWORDS << 3);
+	strtab = dma_zalloc_coherent(smmu->dev, l1size, &cfg->strtab_dma,
 				     GFP_KERNEL);
 	if (!strtab) {
 		dev_err(smmu->dev,
@@ -2055,8 +2086,7 @@
 	ret = arm_smmu_init_l1_strtab(smmu);
 	if (ret)
 		dma_free_coherent(smmu->dev,
-				  cfg->num_l1_ents *
-				  (STRTAB_L1_DESC_DWORDS << 3),
+				  l1size,
 				  strtab,
 				  cfg->strtab_dma);
 	return ret;
@@ -2573,6 +2603,8 @@
 	if (irq > 0)
 		smmu->gerr_irq = irq;
 
+	parse_driver_options(smmu);
+
 	/* Probe the h/w */
 	ret = arm_smmu_device_probe(smmu);
 	if (ret)
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index a98a7b2..0649b94 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -1830,8 +1830,9 @@
 
 static void domain_exit(struct dmar_domain *domain)
 {
+	struct dmar_drhd_unit *drhd;
+	struct intel_iommu *iommu;
 	struct page *freelist = NULL;
-	int i;
 
 	/* Domain 0 is reserved, so dont process it */
 	if (!domain)
@@ -1851,8 +1852,10 @@
 
 	/* clear attached or cached domains */
 	rcu_read_lock();
-	for_each_set_bit(i, domain->iommu_bmp, g_num_of_iommus)
-		iommu_detach_domain(domain, g_iommus[i]);
+	for_each_active_iommu(iommu, drhd)
+		if (domain_type_is_vm(domain) ||
+		    test_bit(iommu->seq_id, domain->iommu_bmp))
+			iommu_detach_domain(domain, iommu);
 	rcu_read_unlock();
 
 	dma_free_pagelist(freelist);
diff --git a/drivers/irqchip/irq-crossbar.c b/drivers/irqchip/irq-crossbar.c
index 692fe2b..c12bb93 100644
--- a/drivers/irqchip/irq-crossbar.c
+++ b/drivers/irqchip/irq-crossbar.c
@@ -68,7 +68,9 @@
 	.irq_mask		= irq_chip_mask_parent,
 	.irq_unmask		= irq_chip_unmask_parent,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
-	.irq_set_wake		= irq_chip_set_wake_parent,
+	.irq_set_type		= irq_chip_set_type_parent,
+	.flags			= IRQCHIP_MASK_ON_SUSPEND |
+				  IRQCHIP_SKIP_SET_WAKE,
 #ifdef CONFIG_SMP
 	.irq_set_affinity	= irq_chip_set_affinity_parent,
 #endif
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 1b7e155..c00e2db 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -75,6 +75,13 @@
 
 #define ITS_ITT_ALIGN		SZ_256
 
+struct event_lpi_map {
+	unsigned long		*lpi_map;
+	u16			*col_map;
+	irq_hw_number_t		lpi_base;
+	int			nr_lpis;
+};
+
 /*
  * The ITS view of a device - belongs to an ITS, a collection, owns an
  * interrupt translation table, and a list of interrupts.
@@ -82,11 +89,8 @@
 struct its_device {
 	struct list_head	entry;
 	struct its_node		*its;
-	struct its_collection	*collection;
+	struct event_lpi_map	event_map;
 	void			*itt;
-	unsigned long		*lpi_map;
-	irq_hw_number_t		lpi_base;
-	int			nr_lpis;
 	u32			nr_ites;
 	u32			device_id;
 };
@@ -99,6 +103,14 @@
 #define gic_data_rdist()		(raw_cpu_ptr(gic_rdists->rdist))
 #define gic_data_rdist_rd_base()	(gic_data_rdist()->rd_base)
 
+static struct its_collection *dev_event_to_col(struct its_device *its_dev,
+					       u32 event)
+{
+	struct its_node *its = its_dev->its;
+
+	return its->collections + its_dev->event_map.col_map[event];
+}
+
 /*
  * ITS command descriptors - parameters to be encoded in a command
  * block.
@@ -134,7 +146,7 @@
 		struct {
 			struct its_device *dev;
 			struct its_collection *col;
-			u32 id;
+			u32 event_id;
 		} its_movi_cmd;
 
 		struct {
@@ -241,7 +253,7 @@
 
 	its_fixup_cmd(cmd);
 
-	return desc->its_mapd_cmd.dev->collection;
+	return NULL;
 }
 
 static struct its_collection *its_build_mapc_cmd(struct its_cmd_block *cmd,
@@ -260,52 +272,72 @@
 static struct its_collection *its_build_mapvi_cmd(struct its_cmd_block *cmd,
 						  struct its_cmd_desc *desc)
 {
+	struct its_collection *col;
+
+	col = dev_event_to_col(desc->its_mapvi_cmd.dev,
+			       desc->its_mapvi_cmd.event_id);
+
 	its_encode_cmd(cmd, GITS_CMD_MAPVI);
 	its_encode_devid(cmd, desc->its_mapvi_cmd.dev->device_id);
 	its_encode_event_id(cmd, desc->its_mapvi_cmd.event_id);
 	its_encode_phys_id(cmd, desc->its_mapvi_cmd.phys_id);
-	its_encode_collection(cmd, desc->its_mapvi_cmd.dev->collection->col_id);
+	its_encode_collection(cmd, col->col_id);
 
 	its_fixup_cmd(cmd);
 
-	return desc->its_mapvi_cmd.dev->collection;
+	return col;
 }
 
 static struct its_collection *its_build_movi_cmd(struct its_cmd_block *cmd,
 						 struct its_cmd_desc *desc)
 {
+	struct its_collection *col;
+
+	col = dev_event_to_col(desc->its_movi_cmd.dev,
+			       desc->its_movi_cmd.event_id);
+
 	its_encode_cmd(cmd, GITS_CMD_MOVI);
 	its_encode_devid(cmd, desc->its_movi_cmd.dev->device_id);
-	its_encode_event_id(cmd, desc->its_movi_cmd.id);
+	its_encode_event_id(cmd, desc->its_movi_cmd.event_id);
 	its_encode_collection(cmd, desc->its_movi_cmd.col->col_id);
 
 	its_fixup_cmd(cmd);
 
-	return desc->its_movi_cmd.dev->collection;
+	return col;
 }
 
 static struct its_collection *its_build_discard_cmd(struct its_cmd_block *cmd,
 						    struct its_cmd_desc *desc)
 {
+	struct its_collection *col;
+
+	col = dev_event_to_col(desc->its_discard_cmd.dev,
+			       desc->its_discard_cmd.event_id);
+
 	its_encode_cmd(cmd, GITS_CMD_DISCARD);
 	its_encode_devid(cmd, desc->its_discard_cmd.dev->device_id);
 	its_encode_event_id(cmd, desc->its_discard_cmd.event_id);
 
 	its_fixup_cmd(cmd);
 
-	return desc->its_discard_cmd.dev->collection;
+	return col;
 }
 
 static struct its_collection *its_build_inv_cmd(struct its_cmd_block *cmd,
 						struct its_cmd_desc *desc)
 {
+	struct its_collection *col;
+
+	col = dev_event_to_col(desc->its_inv_cmd.dev,
+			       desc->its_inv_cmd.event_id);
+
 	its_encode_cmd(cmd, GITS_CMD_INV);
 	its_encode_devid(cmd, desc->its_inv_cmd.dev->device_id);
 	its_encode_event_id(cmd, desc->its_inv_cmd.event_id);
 
 	its_fixup_cmd(cmd);
 
-	return desc->its_inv_cmd.dev->collection;
+	return col;
 }
 
 static struct its_collection *its_build_invall_cmd(struct its_cmd_block *cmd,
@@ -497,7 +529,7 @@
 
 	desc.its_movi_cmd.dev = dev;
 	desc.its_movi_cmd.col = col;
-	desc.its_movi_cmd.id = id;
+	desc.its_movi_cmd.event_id = id;
 
 	its_send_single_command(dev->its, its_build_movi_cmd, &desc);
 }
@@ -528,7 +560,7 @@
 static inline u32 its_get_event_id(struct irq_data *d)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
-	return d->hwirq - its_dev->lpi_base;
+	return d->hwirq - its_dev->event_map.lpi_base;
 }
 
 static void lpi_set_config(struct irq_data *d, bool enable)
@@ -583,7 +615,7 @@
 
 	target_col = &its_dev->its->collections[cpu];
 	its_send_movi(its_dev, target_col, id);
-	its_dev->collection = target_col;
+	its_dev->event_map.col_map[id] = cpu;
 
 	return IRQ_SET_MASK_OK_DONE;
 }
@@ -713,8 +745,10 @@
 	return bitmap;
 }
 
-static void its_lpi_free(unsigned long *bitmap, int base, int nr_ids)
+static void its_lpi_free(struct event_lpi_map *map)
 {
+	int base = map->lpi_base;
+	int nr_ids = map->nr_lpis;
 	int lpi;
 
 	spin_lock(&lpi_lock);
@@ -731,7 +765,8 @@
 
 	spin_unlock(&lpi_lock);
 
-	kfree(bitmap);
+	kfree(map->lpi_map);
+	kfree(map->col_map);
 }
 
 /*
@@ -1099,11 +1134,11 @@
 	struct its_device *dev;
 	unsigned long *lpi_map;
 	unsigned long flags;
+	u16 *col_map = NULL;
 	void *itt;
 	int lpi_base;
 	int nr_lpis;
 	int nr_ites;
-	int cpu;
 	int sz;
 
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
@@ -1117,20 +1152,24 @@
 	sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
 	itt = kzalloc(sz, GFP_KERNEL);
 	lpi_map = its_lpi_alloc_chunks(nvecs, &lpi_base, &nr_lpis);
+	if (lpi_map)
+		col_map = kzalloc(sizeof(*col_map) * nr_lpis, GFP_KERNEL);
 
-	if (!dev || !itt || !lpi_map) {
+	if (!dev || !itt || !lpi_map || !col_map) {
 		kfree(dev);
 		kfree(itt);
 		kfree(lpi_map);
+		kfree(col_map);
 		return NULL;
 	}
 
 	dev->its = its;
 	dev->itt = itt;
 	dev->nr_ites = nr_ites;
-	dev->lpi_map = lpi_map;
-	dev->lpi_base = lpi_base;
-	dev->nr_lpis = nr_lpis;
+	dev->event_map.lpi_map = lpi_map;
+	dev->event_map.col_map = col_map;
+	dev->event_map.lpi_base = lpi_base;
+	dev->event_map.nr_lpis = nr_lpis;
 	dev->device_id = dev_id;
 	INIT_LIST_HEAD(&dev->entry);
 
@@ -1138,10 +1177,6 @@
 	list_add(&dev->entry, &its->its_device_list);
 	raw_spin_unlock_irqrestore(&its->lock, flags);
 
-	/* Bind the device to the first possible CPU */
-	cpu = cpumask_first(cpu_online_mask);
-	dev->collection = &its->collections[cpu];
-
 	/* Map device to its ITT */
 	its_send_mapd(dev, 1);
 
@@ -1163,12 +1198,13 @@
 {
 	int idx;
 
-	idx = find_first_zero_bit(dev->lpi_map, dev->nr_lpis);
-	if (idx == dev->nr_lpis)
+	idx = find_first_zero_bit(dev->event_map.lpi_map,
+				  dev->event_map.nr_lpis);
+	if (idx == dev->event_map.nr_lpis)
 		return -ENOSPC;
 
-	*hwirq = dev->lpi_base + idx;
-	set_bit(idx, dev->lpi_map);
+	*hwirq = dev->event_map.lpi_base + idx;
+	set_bit(idx, dev->event_map.lpi_map);
 
 	return 0;
 }
@@ -1288,7 +1324,8 @@
 		irq_domain_set_hwirq_and_chip(domain, virq + i,
 					      hwirq, &its_irq_chip, its_dev);
 		dev_dbg(info->scratchpad[1].ptr, "ID:%d pID:%d vID:%d\n",
-			(int)(hwirq - its_dev->lpi_base), (int)hwirq, virq + i);
+			(int)(hwirq - its_dev->event_map.lpi_base),
+			(int)hwirq, virq + i);
 	}
 
 	return 0;
@@ -1300,6 +1337,9 @@
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	u32 event = its_get_event_id(d);
 
+	/* Bind the LPI to the first possible CPU */
+	its_dev->event_map.col_map[event] = cpumask_first(cpu_online_mask);
+
 	/* Map the GIC IRQ and event to the device */
 	its_send_mapvi(its_dev, d->hwirq, event);
 }
@@ -1327,17 +1367,16 @@
 		u32 event = its_get_event_id(data);
 
 		/* Mark interrupt index as unused */
-		clear_bit(event, its_dev->lpi_map);
+		clear_bit(event, its_dev->event_map.lpi_map);
 
 		/* Nuke the entry in the domain */
 		irq_domain_reset_irq_data(data);
 	}
 
 	/* If all interrupts have been freed, start mopping the floor */
-	if (bitmap_empty(its_dev->lpi_map, its_dev->nr_lpis)) {
-		its_lpi_free(its_dev->lpi_map,
-			     its_dev->lpi_base,
-			     its_dev->nr_lpis);
+	if (bitmap_empty(its_dev->event_map.lpi_map,
+			 its_dev->event_map.nr_lpis)) {
+		its_lpi_free(&its_dev->event_map);
 
 		/* Unmap device/itt */
 		its_send_mapd(its_dev, 0);
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 8d7e1c8..4dd8826 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -1055,7 +1055,7 @@
 
 	processor = (struct acpi_madt_generic_interrupt *)header;
 
-	if (BAD_MADT_ENTRY(processor, end))
+	if (BAD_MADT_GICC_ENTRY(processor, end))
 		return -EINVAL;
 
 	/*
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 4400edd..ff4be05 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -257,16 +257,6 @@
 		return MIPS_CPU_IRQ_BASE + cp0_fdc_irq;
 	}
 
-	/*
-	 * Some cores claim the FDC is routable but it doesn't actually seem to
-	 * be connected.
-	 */
-	switch (current_cpu_type()) {
-	case CPU_INTERAPTIV:
-	case CPU_PROAPTIV:
-		return -1;
-	}
-
 	return irq_create_mapping(gic_irq_domain,
 				  GIC_LOCAL_TO_HWIRQ(GIC_LOCAL_INT_FDC));
 }
@@ -548,7 +538,7 @@
 
 static irqreturn_t ipi_call_interrupt(int irq, void *dev_id)
 {
-	smp_call_function_interrupt();
+	generic_smp_call_function_interrupt();
 
 	return IRQ_HANDLED;
 }
diff --git a/drivers/irqchip/spear-shirq.c b/drivers/irqchip/spear-shirq.c
index a451215..acb721b 100644
--- a/drivers/irqchip/spear-shirq.c
+++ b/drivers/irqchip/spear-shirq.c
@@ -2,7 +2,7 @@
  * SPEAr platform shared irq layer source file
  *
  * Copyright (C) 2009-2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * Copyright (C) 2012 ST Microelectronics
  * Shiraz Hashim <shiraz.linux.kernel@gmail.com>
diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c
index 8c91fd5eb..375be50 100644
--- a/drivers/isdn/gigaset/ser-gigaset.c
+++ b/drivers/isdn/gigaset/ser-gigaset.c
@@ -524,9 +524,18 @@
 	cs->hw.ser->tty = tty;
 	atomic_set(&cs->hw.ser->refcnt, 1);
 	init_completion(&cs->hw.ser->dead_cmp);
-
 	tty->disc_data = cs;
 
+	/* Set the amount of data we're willing to receive per call
+	 * from the hardware driver to half of the input buffer size
+	 * to leave some reserve.
+	 * Note: We don't do flow control towards the hardware driver.
+	 * If more data is received than will fit into the input buffer,
+	 * it will be dropped and an error will be logged. This should
+	 * never happen as the device is slow and the buffer size ample.
+	 */
+	tty->receive_room = RBUFSIZE/2;
+
 	/* OK.. Initialization of the datastructures and the HW is done.. Now
 	 * startup system and notify the LL that we are ready to run
 	 */
@@ -598,28 +607,6 @@
 }
 
 /*
- * Read on the tty.
- * Unused, received data goes only to the Gigaset driver.
- */
-static ssize_t
-gigaset_tty_read(struct tty_struct *tty, struct file *file,
-		 unsigned char __user *buf, size_t count)
-{
-	return -EAGAIN;
-}
-
-/*
- * Write on the tty.
- * Unused, transmit data comes only from the Gigaset driver.
- */
-static ssize_t
-gigaset_tty_write(struct tty_struct *tty, struct file *file,
-		  const unsigned char *buf, size_t count)
-{
-	return -EAGAIN;
-}
-
-/*
  * Ioctl on the tty.
  * Called in process context only.
  * May be re-entered by multiple ioctl calling threads.
@@ -752,8 +739,6 @@
 	.open		= gigaset_tty_open,
 	.close		= gigaset_tty_close,
 	.hangup		= gigaset_tty_hangup,
-	.read		= gigaset_tty_read,
-	.write		= gigaset_tty_write,
 	.ioctl		= gigaset_tty_ioctl,
 	.receive_buf	= gigaset_tty_receive,
 	.write_wakeup	= gigaset_tty_wakeup,
diff --git a/drivers/macintosh/ans-lcd.c b/drivers/macintosh/ans-lcd.c
index 1a57e88..cd35079 100644
--- a/drivers/macintosh/ans-lcd.c
+++ b/drivers/macintosh/ans-lcd.c
@@ -7,7 +7,7 @@
 #include <linux/kernel.h>
 #include <linux/miscdevice.h>
 #include <linux/fcntl.h>
-#include <linux/init.h>
+#include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/fs.h>
 
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index b597273..bfec3bd 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -259,7 +259,7 @@
 	  the ciphers you're going to use in the cryptoapi configuration.
 
 	  For further information on dm-crypt and userspace tools see:
-	  <http://code.google.com/p/cryptsetup/wiki/DMCrypt>
+	  <https://gitlab.com/cryptsetup/cryptsetup/wikis/DMCrypt>
 
 	  To compile this code as a module, choose M here: the module will
 	  be called dm-crypt.
diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h
index a08e3ee..79a6d63 100644
--- a/drivers/md/bcache/closure.h
+++ b/drivers/md/bcache/closure.h
@@ -320,7 +320,6 @@
 do {									\
 	set_closure_fn(_cl, _fn, _wq);					\
 	closure_sub(_cl, CLOSURE_RUNNING + 1);				\
-	return;								\
 } while (0)
 
 /**
@@ -349,7 +348,6 @@
 do {									\
 	set_closure_fn(_cl, _fn, _wq);					\
 	closure_queue(_cl);						\
-	return;								\
 } while (0)
 
 /**
@@ -365,7 +363,6 @@
 do {									\
 	set_closure_fn(_cl, _destructor, NULL);				\
 	closure_sub(_cl, CLOSURE_RUNNING - CLOSURE_DESTRUCTOR + 1);	\
-	return;								\
 } while (0)
 
 /**
diff --git a/drivers/md/bcache/io.c b/drivers/md/bcache/io.c
index cb64e64a..bf6a9ca 100644
--- a/drivers/md/bcache/io.c
+++ b/drivers/md/bcache/io.c
@@ -105,6 +105,7 @@
 	} while (n != bio);
 
 	continue_at(&s->cl, bch_bio_submit_split_done, NULL);
+	return;
 submit:
 	generic_make_request(bio);
 }
diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index ce64fc8..418607a 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -592,12 +592,14 @@
 
 	if (!w->need_write) {
 		closure_return_with_destructor(cl, journal_write_unlock);
+		return;
 	} else if (journal_full(&c->journal)) {
 		journal_reclaim(c);
 		spin_unlock(&c->journal.lock);
 
 		btree_flush_write(c);
 		continue_at(cl, journal_write, system_wq);
+		return;
 	}
 
 	c->journal.blocks_free -= set_blocks(w->data, block_bytes(c));
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 4afb2d2..f292790 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -88,8 +88,10 @@
 	if (journal_ref)
 		atomic_dec_bug(journal_ref);
 
-	if (!op->insert_data_done)
+	if (!op->insert_data_done) {
 		continue_at(cl, bch_data_insert_start, op->wq);
+		return;
+	}
 
 	bch_keylist_free(&op->insert_keys);
 	closure_return(cl);
@@ -216,8 +218,10 @@
 		/* 1 for the device pointer and 1 for the chksum */
 		if (bch_keylist_realloc(&op->insert_keys,
 					3 + (op->csum ? 1 : 0),
-					op->c))
+					op->c)) {
 			continue_at(cl, bch_data_insert_keys, op->wq);
+			return;
+		}
 
 		k = op->insert_keys.top;
 		bkey_init(k);
@@ -255,6 +259,7 @@
 
 	op->insert_data_done = true;
 	continue_at(cl, bch_data_insert_keys, op->wq);
+	return;
 err:
 	/* bch_alloc_sectors() blocks if s->writeback = true */
 	BUG_ON(op->writeback);
@@ -576,8 +581,10 @@
 	ret = bch_btree_map_keys(&s->op, s->iop.c,
 				 &KEY(s->iop.inode, bio->bi_iter.bi_sector, 0),
 				 cache_lookup_fn, MAP_END_KEY);
-	if (ret == -EAGAIN)
+	if (ret == -EAGAIN) {
 		continue_at(cl, cache_lookup, bcache_wq);
+		return;
+	}
 
 	closure_return(cl);
 }
@@ -1085,6 +1092,7 @@
 		continue_at_nobarrier(&s->cl,
 				      flash_dev_nodata,
 				      bcache_wq);
+		return;
 	} else if (rw) {
 		bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys,
 					&KEY(d->id, bio->bi_iter.bi_sector, 0),
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index ed2346d..e51de52 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -494,7 +494,7 @@
 	bitmap_super_t *sb;
 	unsigned long chunksize, daemon_sleep, write_behind;
 
-	bitmap->storage.sb_page = alloc_page(GFP_KERNEL);
+	bitmap->storage.sb_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
 	if (bitmap->storage.sb_page == NULL)
 		return -ENOMEM;
 	bitmap->storage.sb_page->index = 0;
@@ -541,6 +541,7 @@
 	sb->state = cpu_to_le32(bitmap->flags);
 	bitmap->events_cleared = bitmap->mddev->events;
 	sb->events_cleared = cpu_to_le64(bitmap->mddev->events);
+	bitmap->mddev->bitmap_info.nodes = 0;
 
 	kunmap_atomic(sb);
 
@@ -558,6 +559,7 @@
 	unsigned long sectors_reserved = 0;
 	int err = -EINVAL;
 	struct page *sb_page;
+	loff_t offset = bitmap->mddev->bitmap_info.offset;
 
 	if (!bitmap->storage.file && !bitmap->mddev->bitmap_info.offset) {
 		chunksize = 128 * 1024 * 1024;
@@ -584,9 +586,9 @@
 		bm_blocks = ((bm_blocks+7) >> 3) + sizeof(bitmap_super_t);
 		/* to 4k blocks */
 		bm_blocks = DIV_ROUND_UP_SECTOR_T(bm_blocks, 4096);
-		bitmap->mddev->bitmap_info.offset += bitmap->cluster_slot * (bm_blocks << 3);
+		offset = bitmap->mddev->bitmap_info.offset + (bitmap->cluster_slot * (bm_blocks << 3));
 		pr_info("%s:%d bm slot: %d offset: %llu\n", __func__, __LINE__,
-			bitmap->cluster_slot, (unsigned long long)bitmap->mddev->bitmap_info.offset);
+			bitmap->cluster_slot, offset);
 	}
 
 	if (bitmap->storage.file) {
@@ -597,7 +599,7 @@
 				bitmap, bytes, sb_page);
 	} else {
 		err = read_sb_page(bitmap->mddev,
-				   bitmap->mddev->bitmap_info.offset,
+				   offset,
 				   sb_page,
 				   0, sizeof(bitmap_super_t));
 	}
@@ -611,8 +613,16 @@
 	daemon_sleep = le32_to_cpu(sb->daemon_sleep) * HZ;
 	write_behind = le32_to_cpu(sb->write_behind);
 	sectors_reserved = le32_to_cpu(sb->sectors_reserved);
-	nodes = le32_to_cpu(sb->nodes);
-	strlcpy(bitmap->mddev->bitmap_info.cluster_name, sb->cluster_name, 64);
+	/* XXX: This is a hack to ensure that we don't use clustering
+	 *  in case:
+	 *	- dm-raid is in use and
+	 *	- the nodes written in bitmap_sb is erroneous.
+	 */
+	if (!bitmap->mddev->sync_super) {
+		nodes = le32_to_cpu(sb->nodes);
+		strlcpy(bitmap->mddev->bitmap_info.cluster_name,
+				sb->cluster_name, 64);
+	}
 
 	/* verify that the bitmap-specific fields are valid */
 	if (sb->magic != cpu_to_le32(BITMAP_MAGIC))
@@ -671,7 +681,7 @@
 	kunmap_atomic(sb);
 	/* Assiging chunksize is required for "re_read" */
 	bitmap->mddev->bitmap_info.chunksize = chunksize;
-	if (nodes && (bitmap->cluster_slot < 0)) {
+	if (err == 0 && nodes && (bitmap->cluster_slot < 0)) {
 		err = md_setup_cluster(bitmap->mddev, nodes);
 		if (err) {
 			pr_err("%s: Could not setup cluster service (%d)\n",
@@ -1866,10 +1876,6 @@
 	if (IS_ERR(bitmap))
 		return PTR_ERR(bitmap);
 
-	rv = bitmap_read_sb(bitmap);
-	if (rv)
-		goto err;
-
 	rv = bitmap_init_from_disk(bitmap, 0);
 	if (rv)
 		goto err;
diff --git a/drivers/md/dm-cache-policy-mq.c b/drivers/md/dm-cache-policy-mq.c
index 3281437..aa1b41c 100644
--- a/drivers/md/dm-cache-policy-mq.c
+++ b/drivers/md/dm-cache-policy-mq.c
@@ -1471,5 +1471,3 @@
 MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("mq cache policy");
-
-MODULE_ALIAS("dm-cache-default");
diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c
index b6f2265..200366c 100644
--- a/drivers/md/dm-cache-policy-smq.c
+++ b/drivers/md/dm-cache-policy-smq.c
@@ -1686,7 +1686,7 @@
 
 	if (from_cblock(cache_size)) {
 		mq->cache_hit_bits = alloc_bitset(from_cblock(cache_size));
-		if (!mq->cache_hit_bits && mq->cache_hit_bits) {
+		if (!mq->cache_hit_bits) {
 			DMERR("couldn't allocate cache hit bitset");
 			goto bad_cache_hit_bits;
 		}
@@ -1789,3 +1789,5 @@
 MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("smq cache policy");
+
+MODULE_ALIAS("dm-cache-default");
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 1b4e175..1fe93cf 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -1947,6 +1947,7 @@
 
 static void process_deferred_bios(struct cache *cache)
 {
+	bool prealloc_used = false;
 	unsigned long flags;
 	struct bio_list bios;
 	struct bio *bio;
@@ -1966,6 +1967,7 @@
 		 * this bio might require one, we pause until there are some
 		 * prepared mappings to process.
 		 */
+		prealloc_used = true;
 		if (prealloc_data_structs(cache, &structs)) {
 			spin_lock_irqsave(&cache->lock, flags);
 			bio_list_merge(&cache->deferred_bios, &bios);
@@ -1983,11 +1985,13 @@
 			process_bio(cache, &structs, bio);
 	}
 
-	prealloc_free_structs(cache, &structs);
+	if (prealloc_used)
+		prealloc_free_structs(cache, &structs);
 }
 
 static void process_deferred_cells(struct cache *cache)
 {
+	bool prealloc_used = false;
 	unsigned long flags;
 	struct dm_bio_prison_cell *cell, *tmp;
 	struct list_head cells;
@@ -2007,6 +2011,7 @@
 		 * this bio might require one, we pause until there are some
 		 * prepared mappings to process.
 		 */
+		prealloc_used = true;
 		if (prealloc_data_structs(cache, &structs)) {
 			spin_lock_irqsave(&cache->lock, flags);
 			list_splice(&cells, &cache->deferred_cells);
@@ -2017,7 +2022,8 @@
 		process_cell(cache, &structs, cell);
 	}
 
-	prealloc_free_structs(cache, &structs);
+	if (prealloc_used)
+		prealloc_free_structs(cache, &structs);
 }
 
 static void process_deferred_flush_bios(struct cache *cache, bool submit_bios)
@@ -2062,7 +2068,7 @@
 
 static void writeback_some_dirty_blocks(struct cache *cache)
 {
-	int r = 0;
+	bool prealloc_used = false;
 	dm_oblock_t oblock;
 	dm_cblock_t cblock;
 	struct prealloc structs;
@@ -2072,15 +2078,12 @@
 	memset(&structs, 0, sizeof(structs));
 
 	while (spare_migration_bandwidth(cache)) {
-		if (prealloc_data_structs(cache, &structs))
-			break;
+		if (policy_writeback_work(cache->policy, &oblock, &cblock, busy))
+			break; /* no work to do */
 
-		r = policy_writeback_work(cache->policy, &oblock, &cblock, busy);
-		if (r)
-			break;
-
-		r = get_cell(cache, oblock, &structs, &old_ocell);
-		if (r) {
+		prealloc_used = true;
+		if (prealloc_data_structs(cache, &structs) ||
+		    get_cell(cache, oblock, &structs, &old_ocell)) {
 			policy_set_dirty(cache->policy, oblock);
 			break;
 		}
@@ -2088,7 +2091,8 @@
 		writeback(cache, &structs, oblock, cblock, old_ocell);
 	}
 
-	prealloc_free_structs(cache, &structs);
+	if (prealloc_used)
+		prealloc_free_structs(cache, &structs);
 }
 
 /*----------------------------------------------------------------
@@ -3496,7 +3500,7 @@
  * <#demotions> <#promotions> <#dirty>
  * <#features> <features>*
  * <#core args> <core args>
- * <policy name> <#policy args> <policy args>* <cache metadata mode>
+ * <policy name> <#policy args> <policy args>* <cache metadata mode> <needs_check>
  */
 static void cache_status(struct dm_target *ti, status_type_t type,
 			 unsigned status_flags, char *result, unsigned maxlen)
@@ -3582,6 +3586,11 @@
 		else
 			DMEMIT("rw ");
 
+		if (dm_cache_metadata_needs_check(cache->cmd))
+			DMEMIT("needs_check ");
+		else
+			DMEMIT("- ");
+
 		break;
 
 	case STATUSTYPE_TABLE:
@@ -3820,7 +3829,7 @@
 
 static struct target_type cache_target = {
 	.name = "cache",
-	.version = {1, 7, 0},
+	.version = {1, 8, 0},
 	.module = THIS_MODULE,
 	.ctr = cache_ctr,
 	.dtr = cache_dtr,
diff --git a/drivers/md/dm-thin-metadata.c b/drivers/md/dm-thin-metadata.c
index 48dfe3c..6ba47cf 100644
--- a/drivers/md/dm-thin-metadata.c
+++ b/drivers/md/dm-thin-metadata.c
@@ -1293,8 +1293,8 @@
 		return r;
 
 	disk_super = dm_block_data(copy);
-	dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->data_mapping_root));
-	dm_sm_dec_block(pmd->metadata_sm, le64_to_cpu(disk_super->device_details_root));
+	dm_btree_del(&pmd->info, le64_to_cpu(disk_super->data_mapping_root));
+	dm_btree_del(&pmd->details_info, le64_to_cpu(disk_super->device_details_root));
 	dm_sm_dec_block(pmd->metadata_sm, held_root);
 
 	return dm_tm_unlock(pmd->tm, copy);
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index c33f61a4..d2bbe8c 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <linux/sort.h>
 #include <linux/rbtree.h>
 
@@ -268,7 +269,7 @@
 	process_mapping_fn process_prepared_mapping;
 	process_mapping_fn process_prepared_discard;
 
-	struct dm_bio_prison_cell *cell_sort_array[CELL_SORT_ARRAY_SIZE];
+	struct dm_bio_prison_cell **cell_sort_array;
 };
 
 static enum pool_mode get_pool_mode(struct pool *pool);
@@ -665,16 +666,21 @@
 	requeue_deferred_cells(tc);
 }
 
-static void error_retry_list(struct pool *pool)
+static void error_retry_list_with_code(struct pool *pool, int error)
 {
 	struct thin_c *tc;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(tc, &pool->active_thins, list)
-		error_thin_bio_list(tc, &tc->retry_on_resume_list, -EIO);
+		error_thin_bio_list(tc, &tc->retry_on_resume_list, error);
 	rcu_read_unlock();
 }
 
+static void error_retry_list(struct pool *pool)
+{
+	return error_retry_list_with_code(pool, -EIO);
+}
+
 /*
  * This section of code contains the logic for processing a thin device's IO.
  * Much of the code depends on pool object resources (lists, workqueues, etc)
@@ -2281,18 +2287,23 @@
 	queue_delayed_work(pool->wq, &pool->waker, COMMIT_PERIOD);
 }
 
+static void notify_of_pool_mode_change_to_oods(struct pool *pool);
+
 /*
  * We're holding onto IO to allow userland time to react.  After the
  * timeout either the pool will have been resized (and thus back in
- * PM_WRITE mode), or we degrade to PM_READ_ONLY and start erroring IO.
+ * PM_WRITE mode), or we degrade to PM_OUT_OF_DATA_SPACE w/ error_if_no_space.
  */
 static void do_no_space_timeout(struct work_struct *ws)
 {
 	struct pool *pool = container_of(to_delayed_work(ws), struct pool,
 					 no_space_timeout);
 
-	if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space)
-		set_pool_mode(pool, PM_READ_ONLY);
+	if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) {
+		pool->pf.error_if_no_space = true;
+		notify_of_pool_mode_change_to_oods(pool);
+		error_retry_list_with_code(pool, -ENOSPC);
+	}
 }
 
 /*----------------------------------------------------------------*/
@@ -2370,6 +2381,14 @@
 	       dm_device_name(pool->pool_md), new_mode);
 }
 
+static void notify_of_pool_mode_change_to_oods(struct pool *pool)
+{
+	if (!pool->pf.error_if_no_space)
+		notify_of_pool_mode_change(pool, "out-of-data-space (queue IO)");
+	else
+		notify_of_pool_mode_change(pool, "out-of-data-space (error IO)");
+}
+
 static bool passdown_enabled(struct pool_c *pt)
 {
 	return pt->adjusted_pf.discard_passdown;
@@ -2454,7 +2473,7 @@
 		 * frequently seeing this mode.
 		 */
 		if (old_mode != new_mode)
-			notify_of_pool_mode_change(pool, "out-of-data-space");
+			notify_of_pool_mode_change_to_oods(pool);
 		pool->process_bio = process_bio_read_only;
 		pool->process_discard = process_discard_bio;
 		pool->process_cell = process_cell_read_only;
@@ -2777,6 +2796,7 @@
 {
 	__pool_table_remove(pool);
 
+	vfree(pool->cell_sort_array);
 	if (dm_pool_metadata_close(pool->pmd) < 0)
 		DMWARN("%s: dm_pool_metadata_close() failed.", __func__);
 
@@ -2889,6 +2909,13 @@
 		goto bad_mapping_pool;
 	}
 
+	pool->cell_sort_array = vmalloc(sizeof(*pool->cell_sort_array) * CELL_SORT_ARRAY_SIZE);
+	if (!pool->cell_sort_array) {
+		*error = "Error allocating cell sort array";
+		err_p = ERR_PTR(-ENOMEM);
+		goto bad_sort_array;
+	}
+
 	pool->ref_count = 1;
 	pool->last_commit_jiffies = jiffies;
 	pool->pool_md = pool_md;
@@ -2897,6 +2924,8 @@
 
 	return pool;
 
+bad_sort_array:
+	mempool_destroy(pool->mapping_pool);
 bad_mapping_pool:
 	dm_deferred_set_destroy(pool->all_io_ds);
 bad_all_io_ds:
@@ -3714,6 +3743,7 @@
  * Status line is:
  *    <transaction id> <used metadata sectors>/<total metadata sectors>
  *    <used data sectors>/<total data sectors> <held metadata root>
+ *    <pool mode> <discard config> <no space config> <needs_check>
  */
 static void pool_status(struct dm_target *ti, status_type_t type,
 			unsigned status_flags, char *result, unsigned maxlen)
@@ -3815,6 +3845,11 @@
 		else
 			DMEMIT("queue_if_no_space ");
 
+		if (dm_pool_metadata_needs_check(pool->pmd))
+			DMEMIT("needs_check ");
+		else
+			DMEMIT("- ");
+
 		break;
 
 	case STATUSTYPE_TABLE:
@@ -3918,7 +3953,7 @@
 	.name = "thin-pool",
 	.features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE |
 		    DM_TARGET_IMMUTABLE,
-	.version = {1, 15, 0},
+	.version = {1, 16, 0},
 	.module = THIS_MODULE,
 	.ctr = pool_ctr,
 	.dtr = pool_dtr,
@@ -4305,7 +4340,7 @@
 
 static struct target_type thin_target = {
 	.name = "thin",
-	.version = {1, 15, 0},
+	.version = {1, 16, 0},
 	.module	= THIS_MODULE,
 	.ctr = thin_ctr,
 	.dtr = thin_dtr,
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index f331d88..0d7ab20 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1067,13 +1067,10 @@
  */
 static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
 {
-	int nr_requests_pending;
-
 	atomic_dec(&md->pending[rw]);
 
 	/* nudge anyone waiting on suspend queue */
-	nr_requests_pending = md_in_flight(md);
-	if (!nr_requests_pending)
+	if (!md_in_flight(md))
 		wake_up(&md->wait);
 
 	/*
@@ -1085,8 +1082,7 @@
 	if (run_queue) {
 		if (md->queue->mq_ops)
 			blk_mq_run_hw_queues(md->queue, true);
-		else if (!nr_requests_pending ||
-			 (nr_requests_pending >= md->queue->nr_congestion_on))
+		else
 			blk_run_queue_async(md->queue);
 	}
 
@@ -1733,7 +1729,8 @@
 	struct mapped_device *md = q->queuedata;
 	struct dm_table *map = dm_get_live_table_fast(md);
 	struct dm_target *ti;
-	sector_t max_sectors, max_size = 0;
+	sector_t max_sectors;
+	int max_size = 0;
 
 	if (unlikely(!map))
 		goto out;
@@ -1746,18 +1743,10 @@
 	 * Find maximum amount of I/O that won't need splitting
 	 */
 	max_sectors = min(max_io_len(bvm->bi_sector, ti),
-			  (sector_t) queue_max_sectors(q));
+			  (sector_t) BIO_MAX_SECTORS);
 	max_size = (max_sectors << SECTOR_SHIFT) - bvm->bi_size;
-
-	/*
-	 * FIXME: this stop-gap fix _must_ be cleaned up (by passing a sector_t
-	 * to the targets' merge function since it holds sectors not bytes).
-	 * Just doing this as an interim fix for stable@ because the more
-	 * comprehensive cleanup of switching to sector_t will impact every
-	 * DM target that implements a ->merge hook.
-	 */
-	if (max_size > INT_MAX)
-		max_size = INT_MAX;
+	if (max_size < 0)
+		max_size = 0;
 
 	/*
 	 * merge_bvec_fn() returns number of bytes
@@ -1765,13 +1754,13 @@
 	 * max is precomputed maximal io size
 	 */
 	if (max_size && ti->type->merge)
-		max_size = ti->type->merge(ti, bvm, biovec, (int) max_size);
+		max_size = ti->type->merge(ti, bvm, biovec, max_size);
 	/*
 	 * If the target doesn't support merge method and some of the devices
-	 * provided their merge_bvec method (we know this by looking for the
-	 * max_hw_sectors that dm_set_device_limits may set), then we can't
-	 * allow bios with multiple vector entries.  So always set max_size
-	 * to 0, and the code below allows just one page.
+	 * provided their merge_bvec method (we know this by looking at
+	 * queue_max_hw_sectors), then we can't allow bios with multiple vector
+	 * entries.  So always set max_size to 0, and the code below allows
+	 * just one page.
 	 */
 	else if (queue_max_hw_sectors(q) <= PAGE_SIZE >> 9)
 		max_size = 0;
@@ -2281,8 +2270,6 @@
 
 static void cleanup_mapped_device(struct mapped_device *md)
 {
-	cleanup_srcu_struct(&md->io_barrier);
-
 	if (md->wq)
 		destroy_workqueue(md->wq);
 	if (md->kworker_task)
@@ -2294,6 +2281,8 @@
 	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;
diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index fcfc4b9..0072190 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -44,6 +44,7 @@
 
 /* md_cluster_info flags */
 #define		MD_CLUSTER_WAITING_FOR_NEWDISK		1
+#define		MD_CLUSTER_SUSPEND_READ_BALANCING	2
 
 
 struct md_cluster_info {
@@ -275,6 +276,9 @@
 
 static void recover_prep(void *arg)
 {
+	struct mddev *mddev = arg;
+	struct md_cluster_info *cinfo = mddev->cluster_info;
+	set_bit(MD_CLUSTER_SUSPEND_READ_BALANCING, &cinfo->state);
 }
 
 static void recover_slot(void *arg, struct dlm_slot *slot)
@@ -307,6 +311,7 @@
 
 	cinfo->slot_number = our_slot;
 	complete(&cinfo->completion);
+	clear_bit(MD_CLUSTER_SUSPEND_READ_BALANCING, &cinfo->state);
 }
 
 static const struct dlm_lockspace_ops md_ls_ops = {
@@ -816,12 +821,17 @@
 	resync_send(mddev, RESYNCING, 0, 0);
 }
 
-static int area_resyncing(struct mddev *mddev, sector_t lo, sector_t hi)
+static int area_resyncing(struct mddev *mddev, int direction,
+		sector_t lo, sector_t hi)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
 	int ret = 0;
 	struct suspend_info *s;
 
+	if ((direction == READ) &&
+		test_bit(MD_CLUSTER_SUSPEND_READ_BALANCING, &cinfo->state))
+		return 1;
+
 	spin_lock_irq(&cinfo->suspend_lock);
 	if (list_empty(&cinfo->suspend_list))
 		goto out;
diff --git a/drivers/md/md-cluster.h b/drivers/md/md-cluster.h
index 6817ee0..00defe2 100644
--- a/drivers/md/md-cluster.h
+++ b/drivers/md/md-cluster.h
@@ -18,7 +18,7 @@
 	int (*metadata_update_start)(struct mddev *mddev);
 	int (*metadata_update_finish)(struct mddev *mddev);
 	int (*metadata_update_cancel)(struct mddev *mddev);
-	int (*area_resyncing)(struct mddev *mddev, sector_t lo, sector_t hi);
+	int (*area_resyncing)(struct mddev *mddev, int direction, sector_t lo, sector_t hi);
 	int (*add_new_disk_start)(struct mddev *mddev, struct md_rdev *rdev);
 	int (*add_new_disk_finish)(struct mddev *mddev);
 	int (*new_disk_ack)(struct mddev *mddev, bool ack);
diff --git a/drivers/md/md.c b/drivers/md/md.c
index d429c30..e25f00f 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5382,6 +5382,8 @@
 {
 	struct md_personality *pers = mddev->pers;
 	mddev_detach(mddev);
+	/* Ensure ->event_work is done */
+	flush_workqueue(md_misc_wq);
 	spin_lock(&mddev->lock);
 	mddev->ready = 0;
 	mddev->pers = NULL;
@@ -5757,7 +5759,7 @@
 	char *ptr;
 	int err;
 
-	file = kmalloc(sizeof(*file), GFP_NOIO);
+	file = kzalloc(sizeof(*file), GFP_NOIO);
 	if (!file)
 		return -ENOMEM;
 
@@ -7437,7 +7439,7 @@
 	err = request_module("md-cluster");
 	if (err) {
 		pr_err("md-cluster module not found.\n");
-		return err;
+		return -ENOENT;
 	}
 
 	spin_lock(&pers_lock);
diff --git a/drivers/md/persistent-data/dm-btree-internal.h b/drivers/md/persistent-data/dm-btree-internal.h
index bf2b80d..8731b6e 100644
--- a/drivers/md/persistent-data/dm-btree-internal.h
+++ b/drivers/md/persistent-data/dm-btree-internal.h
@@ -138,4 +138,10 @@
 
 extern struct dm_block_validator btree_node_validator;
 
+/*
+ * Value type for upper levels of multi-level btrees.
+ */
+extern void init_le64_type(struct dm_transaction_manager *tm,
+			   struct dm_btree_value_type *vt);
+
 #endif	/* DM_BTREE_INTERNAL_H */
diff --git a/drivers/md/persistent-data/dm-btree-remove.c b/drivers/md/persistent-data/dm-btree-remove.c
index e04cfd2..4222f77 100644
--- a/drivers/md/persistent-data/dm-btree-remove.c
+++ b/drivers/md/persistent-data/dm-btree-remove.c
@@ -309,8 +309,8 @@
 
 		if (s < 0 && nr_center < -s) {
 			/* not enough in central node */
-			shift(left, center, nr_center);
-			s = nr_center - target;
+			shift(left, center, -nr_center);
+			s += nr_center;
 			shift(left, right, s);
 			nr_right += s;
 		} else
@@ -323,7 +323,7 @@
 		if (s > 0 && nr_center < s) {
 			/* not enough in central node */
 			shift(center, right, nr_center);
-			s = target - nr_center;
+			s -= nr_center;
 			shift(left, right, s);
 			nr_left -= s;
 		} else
@@ -544,14 +544,6 @@
 	return r;
 }
 
-static struct dm_btree_value_type le64_type = {
-	.context = NULL,
-	.size = sizeof(__le64),
-	.inc = NULL,
-	.dec = NULL,
-	.equal = NULL
-};
-
 int dm_btree_remove(struct dm_btree_info *info, dm_block_t root,
 		    uint64_t *keys, dm_block_t *new_root)
 {
@@ -559,12 +551,14 @@
 	int index = 0, r = 0;
 	struct shadow_spine spine;
 	struct btree_node *n;
+	struct dm_btree_value_type le64_vt;
 
+	init_le64_type(info->tm, &le64_vt);
 	init_shadow_spine(&spine, info);
 	for (level = 0; level < info->levels; level++) {
 		r = remove_raw(&spine, info,
 			       (level == last_level ?
-				&info->value_type : &le64_type),
+				&info->value_type : &le64_vt),
 			       root, keys[level], (unsigned *)&index);
 		if (r < 0)
 			break;
@@ -654,11 +648,13 @@
 	int index = 0, r = 0;
 	struct shadow_spine spine;
 	struct btree_node *n;
+	struct dm_btree_value_type le64_vt;
 	uint64_t k;
 
+	init_le64_type(info->tm, &le64_vt);
 	init_shadow_spine(&spine, info);
 	for (level = 0; level < last_level; level++) {
-		r = remove_raw(&spine, info, &le64_type,
+		r = remove_raw(&spine, info, &le64_vt,
 			       root, keys[level], (unsigned *) &index);
 		if (r < 0)
 			goto out;
@@ -689,6 +685,7 @@
 					     value_ptr(n, index));
 
 		delete_at(n, index);
+		keys[last_level] = k + 1ull;
 
 	} else
 		r = -ENODATA;
diff --git a/drivers/md/persistent-data/dm-btree-spine.c b/drivers/md/persistent-data/dm-btree-spine.c
index 1b5e13e..0dee514 100644
--- a/drivers/md/persistent-data/dm-btree-spine.c
+++ b/drivers/md/persistent-data/dm-btree-spine.c
@@ -249,3 +249,40 @@
 {
 	return s->root;
 }
+
+static void le64_inc(void *context, const void *value_le)
+{
+	struct dm_transaction_manager *tm = context;
+	__le64 v_le;
+
+	memcpy(&v_le, value_le, sizeof(v_le));
+	dm_tm_inc(tm, le64_to_cpu(v_le));
+}
+
+static void le64_dec(void *context, const void *value_le)
+{
+	struct dm_transaction_manager *tm = context;
+	__le64 v_le;
+
+	memcpy(&v_le, value_le, sizeof(v_le));
+	dm_tm_dec(tm, le64_to_cpu(v_le));
+}
+
+static int le64_equal(void *context, const void *value1_le, const void *value2_le)
+{
+	__le64 v1_le, v2_le;
+
+	memcpy(&v1_le, value1_le, sizeof(v1_le));
+	memcpy(&v2_le, value2_le, sizeof(v2_le));
+	return v1_le == v2_le;
+}
+
+void init_le64_type(struct dm_transaction_manager *tm,
+		    struct dm_btree_value_type *vt)
+{
+	vt->context = tm;
+	vt->size = sizeof(__le64);
+	vt->inc = le64_inc;
+	vt->dec = le64_dec;
+	vt->equal = le64_equal;
+}
diff --git a/drivers/md/persistent-data/dm-btree.c b/drivers/md/persistent-data/dm-btree.c
index 200ac12..c7726ce 100644
--- a/drivers/md/persistent-data/dm-btree.c
+++ b/drivers/md/persistent-data/dm-btree.c
@@ -255,7 +255,7 @@
 	int r;
 	struct del_stack *s;
 
-	s = kmalloc(sizeof(*s), GFP_KERNEL);
+	s = kmalloc(sizeof(*s), GFP_NOIO);
 	if (!s)
 		return -ENOMEM;
 	s->info = info;
@@ -667,12 +667,7 @@
 	struct btree_node *n;
 	struct dm_btree_value_type le64_type;
 
-	le64_type.context = NULL;
-	le64_type.size = sizeof(__le64);
-	le64_type.inc = NULL;
-	le64_type.dec = NULL;
-	le64_type.equal = NULL;
-
+	init_le64_type(info->tm, &le64_type);
 	init_shadow_spine(&spine, info);
 
 	for (level = 0; level < (info->levels - 1); level++) {
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index f80f1af..967a4ed 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -336,7 +336,7 @@
 		spin_lock_irqsave(&conf->device_lock, flags);
 		if (r1_bio->mddev->degraded == conf->raid_disks ||
 		    (r1_bio->mddev->degraded == conf->raid_disks-1 &&
-		     !test_bit(Faulty, &conf->mirrors[mirror].rdev->flags)))
+		     test_bit(In_sync, &conf->mirrors[mirror].rdev->flags)))
 			uptodate = 1;
 		spin_unlock_irqrestore(&conf->device_lock, flags);
 	}
@@ -541,7 +541,7 @@
 
 	if ((conf->mddev->recovery_cp < this_sector + sectors) ||
 	    (mddev_is_clustered(conf->mddev) &&
-	    md_cluster_ops->area_resyncing(conf->mddev, this_sector,
+	    md_cluster_ops->area_resyncing(conf->mddev, READ, this_sector,
 		    this_sector + sectors)))
 		choose_first = 1;
 	else
@@ -1111,7 +1111,8 @@
 	    ((bio_end_sector(bio) > mddev->suspend_lo &&
 	    bio->bi_iter.bi_sector < mddev->suspend_hi) ||
 	    (mddev_is_clustered(mddev) &&
-	     md_cluster_ops->area_resyncing(mddev, bio->bi_iter.bi_sector, bio_end_sector(bio))))) {
+	     md_cluster_ops->area_resyncing(mddev, WRITE,
+		     bio->bi_iter.bi_sector, bio_end_sector(bio))))) {
 		/* As the suspend_* range is controlled by
 		 * userspace, we want an interruptible
 		 * wait.
@@ -1124,7 +1125,7 @@
 			if (bio_end_sector(bio) <= mddev->suspend_lo ||
 			    bio->bi_iter.bi_sector >= mddev->suspend_hi ||
 			    (mddev_is_clustered(mddev) &&
-			     !md_cluster_ops->area_resyncing(mddev,
+			     !md_cluster_ops->area_resyncing(mddev, WRITE,
 				     bio->bi_iter.bi_sector, bio_end_sector(bio))))
 				break;
 			schedule();
@@ -1475,6 +1476,7 @@
 {
 	char b[BDEVNAME_SIZE];
 	struct r1conf *conf = mddev->private;
+	unsigned long flags;
 
 	/*
 	 * If it is not operational, then we have already marked it as dead
@@ -1494,14 +1496,13 @@
 		return;
 	}
 	set_bit(Blocked, &rdev->flags);
+	spin_lock_irqsave(&conf->device_lock, flags);
 	if (test_and_clear_bit(In_sync, &rdev->flags)) {
-		unsigned long flags;
-		spin_lock_irqsave(&conf->device_lock, flags);
 		mddev->degraded++;
 		set_bit(Faulty, &rdev->flags);
-		spin_unlock_irqrestore(&conf->device_lock, flags);
 	} else
 		set_bit(Faulty, &rdev->flags);
+	spin_unlock_irqrestore(&conf->device_lock, flags);
 	/*
 	 * if recovery is running, make sure it aborts.
 	 */
@@ -1567,7 +1568,10 @@
 	 * Find all failed disks within the RAID1 configuration
 	 * and mark them readable.
 	 * Called under mddev lock, so rcu protection not needed.
+	 * device_lock used to avoid races with raid1_end_read_request
+	 * which expects 'In_sync' flags and ->degraded to be consistent.
 	 */
+	spin_lock_irqsave(&conf->device_lock, flags);
 	for (i = 0; i < conf->raid_disks; i++) {
 		struct md_rdev *rdev = conf->mirrors[i].rdev;
 		struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev;
@@ -1598,7 +1602,6 @@
 			sysfs_notify_dirent_safe(rdev->sysfs_state);
 		}
 	}
-	spin_lock_irqsave(&conf->device_lock, flags);
 	mddev->degraded -= count;
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 940f2f3..38c58e1 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3556,6 +3556,7 @@
 			/* far_copies must be 1 */
 			conf->prev.stride = conf->dev_sectors;
 	}
+	conf->reshape_safe = conf->reshape_progress;
 	spin_lock_init(&conf->device_lock);
 	INIT_LIST_HEAD(&conf->retry_list);
 
@@ -3760,7 +3761,6 @@
 		}
 		conf->offset_diff = min_offset_diff;
 
-		conf->reshape_safe = conf->reshape_progress;
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
 		set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery);
@@ -4103,6 +4103,7 @@
 		conf->reshape_progress = size;
 	} else
 		conf->reshape_progress = 0;
+	conf->reshape_safe = conf->reshape_progress;
 	spin_unlock_irq(&conf->device_lock);
 
 	if (mddev->delta_disks && mddev->bitmap) {
@@ -4170,6 +4171,7 @@
 		rdev->new_data_offset = rdev->data_offset;
 	smp_wmb();
 	conf->reshape_progress = MaxSector;
+	conf->reshape_safe = MaxSector;
 	mddev->reshape_position = MaxSector;
 	spin_unlock_irq(&conf->device_lock);
 	return ret;
@@ -4524,6 +4526,7 @@
 	md_finish_reshape(conf->mddev);
 	smp_wmb();
 	conf->reshape_progress = MaxSector;
+	conf->reshape_safe = MaxSector;
 	spin_unlock_irq(&conf->device_lock);
 
 	/* read-ahead size must cover two whole stripes, which is
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 59e44e9..f757023 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2162,6 +2162,9 @@
 	if (!sc)
 		return -ENOMEM;
 
+	/* Need to ensure auto-resizing doesn't interfere */
+	mutex_lock(&conf->cache_size_mutex);
+
 	for (i = conf->max_nr_stripes; i; i--) {
 		nsh = alloc_stripe(sc, GFP_KERNEL);
 		if (!nsh)
@@ -2178,6 +2181,7 @@
 			kmem_cache_free(sc, nsh);
 		}
 		kmem_cache_destroy(sc);
+		mutex_unlock(&conf->cache_size_mutex);
 		return -ENOMEM;
 	}
 	/* Step 2 - Must use GFP_NOIO now.
@@ -2224,6 +2228,7 @@
 	} else
 		err = -ENOMEM;
 
+	mutex_unlock(&conf->cache_size_mutex);
 	/* Step 4, return new stripes to service */
 	while(!list_empty(&newstripes)) {
 		nsh = list_entry(newstripes.next, struct stripe_head, lru);
@@ -2251,7 +2256,7 @@
 static int drop_one_stripe(struct r5conf *conf)
 {
 	struct stripe_head *sh;
-	int hash = (conf->max_nr_stripes - 1) % NR_STRIPE_HASH_LOCKS;
+	int hash = (conf->max_nr_stripes - 1) & STRIPE_HASH_LOCKS_MASK;
 
 	spin_lock_irq(conf->hash_locks + hash);
 	sh = get_free_stripe(conf, hash);
@@ -4061,8 +4066,10 @@
 				 &first_bad, &bad_sectors))
 			set_bit(R5_ReadRepl, &dev->flags);
 		else {
-			if (rdev)
+			if (rdev && !test_bit(Faulty, &rdev->flags))
 				set_bit(R5_NeedReplace, &dev->flags);
+			else
+				clear_bit(R5_NeedReplace, &dev->flags);
 			rdev = rcu_dereference(conf->disks[i].rdev);
 			clear_bit(R5_ReadRepl, &dev->flags);
 		}
@@ -5857,12 +5864,14 @@
 	pr_debug("%d stripes handled\n", handled);
 
 	spin_unlock_irq(&conf->device_lock);
-	if (test_and_clear_bit(R5_ALLOC_MORE, &conf->cache_state)) {
+	if (test_and_clear_bit(R5_ALLOC_MORE, &conf->cache_state) &&
+	    mutex_trylock(&conf->cache_size_mutex)) {
 		grow_one_stripe(conf, __GFP_NOWARN);
 		/* Set flag even if allocation failed.  This helps
 		 * slow down allocation requests when mem is short
 		 */
 		set_bit(R5_DID_ALLOC, &conf->cache_state);
+		mutex_unlock(&conf->cache_size_mutex);
 	}
 
 	async_tx_issue_pending_all();
@@ -5894,18 +5903,22 @@
 		return -EINVAL;
 
 	conf->min_nr_stripes = size;
+	mutex_lock(&conf->cache_size_mutex);
 	while (size < conf->max_nr_stripes &&
 	       drop_one_stripe(conf))
 		;
+	mutex_unlock(&conf->cache_size_mutex);
 
 
 	err = md_allow_write(mddev);
 	if (err)
 		return err;
 
+	mutex_lock(&conf->cache_size_mutex);
 	while (size > conf->max_nr_stripes)
 		if (!grow_one_stripe(conf, GFP_KERNEL))
 			break;
+	mutex_unlock(&conf->cache_size_mutex);
 
 	return 0;
 }
@@ -6371,11 +6384,19 @@
 				      struct shrink_control *sc)
 {
 	struct r5conf *conf = container_of(shrink, struct r5conf, shrinker);
-	int ret = 0;
-	while (ret < sc->nr_to_scan) {
-		if (drop_one_stripe(conf) == 0)
-			return SHRINK_STOP;
-		ret++;
+	unsigned long ret = SHRINK_STOP;
+
+	if (mutex_trylock(&conf->cache_size_mutex)) {
+		ret= 0;
+		while (ret < sc->nr_to_scan &&
+		       conf->max_nr_stripes > conf->min_nr_stripes) {
+			if (drop_one_stripe(conf) == 0) {
+				ret = SHRINK_STOP;
+				break;
+			}
+			ret++;
+		}
+		mutex_unlock(&conf->cache_size_mutex);
 	}
 	return ret;
 }
@@ -6444,6 +6465,7 @@
 		goto abort;
 	spin_lock_init(&conf->device_lock);
 	seqcount_init(&conf->gen_lock);
+	mutex_init(&conf->cache_size_mutex);
 	init_waitqueue_head(&conf->wait_for_quiescent);
 	for (i = 0; i < NR_STRIPE_HASH_LOCKS; i++) {
 		init_waitqueue_head(&conf->wait_for_stripe[i]);
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 02c3bf8..d051442 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -482,7 +482,8 @@
 	 */
 	int			active_name;
 	char			cache_name[2][32];
-	struct kmem_cache		*slab_cache; /* for allocating stripes */
+	struct kmem_cache	*slab_cache; /* for allocating stripes */
+	struct mutex		cache_size_mutex; /* Protect changes to cache size */
 
 	int			seq_flush, seq_write;
 	int			quiesce;
diff --git a/drivers/media/dvb-frontends/Kconfig b/drivers/media/dvb-frontends/Kconfig
index 0d35f58..5ab90f3 100644
--- a/drivers/media/dvb-frontends/Kconfig
+++ b/drivers/media/dvb-frontends/Kconfig
@@ -240,7 +240,7 @@
 
 config DVB_TS2020
 	tristate "Montage Tehnology TS2020 based tuners"
-	depends on DVB_CORE
+	depends on DVB_CORE && I2C
 	select REGMAP_I2C
 	default m if !MEDIA_SUBDRV_AUTOSELECT
 	help
diff --git a/drivers/media/pci/cobalt/Kconfig b/drivers/media/pci/cobalt/Kconfig
index 3be1b2c..6a1c008 100644
--- a/drivers/media/pci/cobalt/Kconfig
+++ b/drivers/media/pci/cobalt/Kconfig
@@ -2,6 +2,7 @@
 	tristate "Cisco Cobalt support"
 	depends on VIDEO_V4L2 && I2C && MEDIA_CONTROLLER
 	depends on PCI_MSI && MTD_COMPLEX_MAPPINGS && GPIOLIB
+	depends on SND
 	select I2C_ALGOBIT
 	select VIDEO_ADV7604
 	select VIDEO_ADV7511
diff --git a/drivers/media/pci/cobalt/cobalt-irq.c b/drivers/media/pci/cobalt/cobalt-irq.c
index dd4bff9..d1f5898 100644
--- a/drivers/media/pci/cobalt/cobalt-irq.c
+++ b/drivers/media/pci/cobalt/cobalt-irq.c
@@ -139,7 +139,7 @@
 	   also know about dropped frames. */
 	cb->vb.v4l2_buf.sequence = s->sequence++;
 	vb2_buffer_done(&cb->vb, (skip || s->unstable_frame) ?
-			VB2_BUF_STATE_QUEUED : VB2_BUF_STATE_DONE);
+			VB2_BUF_STATE_REQUEUEING : VB2_BUF_STATE_DONE);
 }
 
 irqreturn_t cobalt_irq_handler(int irq, void *dev_id)
diff --git a/drivers/media/pci/ivtv/ivtvfb.c b/drivers/media/pci/ivtv/ivtvfb.c
index 4cb365d..8b95eef 100644
--- a/drivers/media/pci/ivtv/ivtvfb.c
+++ b/drivers/media/pci/ivtv/ivtvfb.c
@@ -38,6 +38,8 @@
     Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/fb.h>
@@ -1171,6 +1173,13 @@
 {
 	int rc;
 
+#ifdef CONFIG_X86_64
+	if (pat_enabled()) {
+		pr_warn("ivtvfb needs PAT disabled, boot with nopat kernel parameter\n");
+		return -ENODEV;
+	}
+#endif
+
 	if (itv->osd_info) {
 		IVTVFB_ERR("Card %d already initialised\n", ivtvfb_card_id);
 		return -EBUSY;
@@ -1265,12 +1274,6 @@
 	int registered = 0;
 	int err;
 
-#ifdef CONFIG_X86_64
-	if (WARN(pat_enabled(),
-		 "ivtvfb needs PAT disabled, boot with nopat kernel parameter\n")) {
-		return -ENODEV;
-	}
-#endif
 
 	if (ivtvfb_card_id < -1 || ivtvfb_card_id >= IVTV_MAX_CARDS) {
 		printk(KERN_ERR "ivtvfb:  ivtvfb_card_id parameter is out of range (valid range: -1 - %d)\n",
diff --git a/drivers/media/pci/mantis/mantis_dma.c b/drivers/media/pci/mantis/mantis_dma.c
index 1d59c7e..87990ec 100644
--- a/drivers/media/pci/mantis/mantis_dma.c
+++ b/drivers/media/pci/mantis/mantis_dma.c
@@ -130,10 +130,11 @@
 
 int mantis_dma_init(struct mantis_pci *mantis)
 {
-	int err = 0;
+	int err;
 
 	dprintk(MANTIS_DEBUG, 1, "Mantis DMA init");
-	if (mantis_alloc_buffers(mantis) < 0) {
+	err = mantis_alloc_buffers(mantis);
+	if (err < 0) {
 		dprintk(MANTIS_ERROR, 1, "Error allocating DMA buffer");
 
 		/* Stop RISC Engine */
diff --git a/drivers/media/rc/ir-rc5-decoder.c b/drivers/media/rc/ir-rc5-decoder.c
index 8939ebd..84fa6e9 100644
--- a/drivers/media/rc/ir-rc5-decoder.c
+++ b/drivers/media/rc/ir-rc5-decoder.c
@@ -184,125 +184,9 @@
 	return -EINVAL;
 }
 
-static struct ir_raw_timings_manchester ir_rc5_timings = {
-	.leader			= RC5_UNIT,
-	.pulse_space_start	= 0,
-	.clock			= RC5_UNIT,
-	.trailer_space		= RC5_UNIT * 10,
-};
-
-static struct ir_raw_timings_manchester ir_rc5x_timings[2] = {
-	{
-		.leader			= RC5_UNIT,
-		.pulse_space_start	= 0,
-		.clock			= RC5_UNIT,
-		.trailer_space		= RC5X_SPACE,
-	},
-	{
-		.clock			= RC5_UNIT,
-		.trailer_space		= RC5_UNIT * 10,
-	},
-};
-
-static struct ir_raw_timings_manchester ir_rc5_sz_timings = {
-	.leader				= RC5_UNIT,
-	.pulse_space_start		= 0,
-	.clock				= RC5_UNIT,
-	.trailer_space			= RC5_UNIT * 10,
-};
-
-static int ir_rc5_validate_filter(const struct rc_scancode_filter *scancode,
-				  unsigned int important_bits)
-{
-	/* all important bits of scancode should be set in mask */
-	if (~scancode->mask & important_bits)
-		return -EINVAL;
-	/* extra bits in mask should be zero in data */
-	if (scancode->mask & scancode->data & ~important_bits)
-		return -EINVAL;
-	return 0;
-}
-
-/**
- * ir_rc5_encode() - Encode a scancode as a stream of raw events
- *
- * @protocols:	allowed protocols
- * @scancode:	scancode filter describing scancode (helps distinguish between
- *		protocol subtypes when scancode is ambiguous)
- * @events:	array of raw ir events to write into
- * @max:	maximum size of @events
- *
- * Returns:	The number of events written.
- *		-ENOBUFS if there isn't enough space in the array to fit the
- *		encoding. In this case all @max events will have been written.
- *		-EINVAL if the scancode is ambiguous or invalid.
- */
-static int ir_rc5_encode(u64 protocols,
-			 const struct rc_scancode_filter *scancode,
-			 struct ir_raw_event *events, unsigned int max)
-{
-	int ret;
-	struct ir_raw_event *e = events;
-	unsigned int data, xdata, command, commandx, system;
-
-	/* Detect protocol and convert scancode to raw data */
-	if (protocols & RC_BIT_RC5 &&
-	    !ir_rc5_validate_filter(scancode, 0x1f7f)) {
-		/* decode scancode */
-		command  = (scancode->data & 0x003f) >> 0;
-		commandx = (scancode->data & 0x0040) >> 6;
-		system   = (scancode->data & 0x1f00) >> 8;
-		/* encode data */
-		data = !commandx << 12 | system << 6 | command;
-
-		/* Modulate the data */
-		ret = ir_raw_gen_manchester(&e, max, &ir_rc5_timings, RC5_NBITS,
-					    data);
-		if (ret < 0)
-			return ret;
-	} else if (protocols & RC_BIT_RC5X &&
-		   !ir_rc5_validate_filter(scancode, 0x1f7f3f)) {
-		/* decode scancode */
-		xdata    = (scancode->data & 0x00003f) >> 0;
-		command  = (scancode->data & 0x003f00) >> 8;
-		commandx = (scancode->data & 0x004000) >> 14;
-		system   = (scancode->data & 0x1f0000) >> 16;
-		/* commandx and system overlap, bits must match when encoded */
-		if (commandx == (system & 0x1))
-			return -EINVAL;
-		/* encode data */
-		data = 1 << 18 | system << 12 | command << 6 | xdata;
-
-		/* Modulate the data */
-		ret = ir_raw_gen_manchester(&e, max, &ir_rc5x_timings[0],
-					CHECK_RC5X_NBITS,
-					data >> (RC5X_NBITS-CHECK_RC5X_NBITS));
-		if (ret < 0)
-			return ret;
-		ret = ir_raw_gen_manchester(&e, max - (e - events),
-					&ir_rc5x_timings[1],
-					RC5X_NBITS - CHECK_RC5X_NBITS,
-					data);
-		if (ret < 0)
-			return ret;
-	} else if (protocols & RC_BIT_RC5_SZ &&
-		   !ir_rc5_validate_filter(scancode, 0x2fff)) {
-		/* RC5-SZ scancode is raw enough for Manchester as it is */
-		ret = ir_raw_gen_manchester(&e, max, &ir_rc5_sz_timings,
-					RC5_SZ_NBITS, scancode->data & 0x2fff);
-		if (ret < 0)
-			return ret;
-	} else {
-		return -EINVAL;
-	}
-
-	return e - events;
-}
-
 static struct ir_raw_handler rc5_handler = {
 	.protocols	= RC_BIT_RC5 | RC_BIT_RC5X | RC_BIT_RC5_SZ,
 	.decode		= ir_rc5_decode,
-	.encode		= ir_rc5_encode,
 };
 
 static int __init ir_rc5_decode_init(void)
diff --git a/drivers/media/rc/ir-rc6-decoder.c b/drivers/media/rc/ir-rc6-decoder.c
index f9c70ba..d16bc67 100644
--- a/drivers/media/rc/ir-rc6-decoder.c
+++ b/drivers/media/rc/ir-rc6-decoder.c
@@ -291,133 +291,11 @@
 	return -EINVAL;
 }
 
-static struct ir_raw_timings_manchester ir_rc6_timings[4] = {
-	{
-		.leader			= RC6_PREFIX_PULSE,
-		.pulse_space_start	= 0,
-		.clock			= RC6_UNIT,
-		.invert			= 1,
-		.trailer_space		= RC6_PREFIX_SPACE,
-	},
-	{
-		.clock			= RC6_UNIT,
-		.invert			= 1,
-	},
-	{
-		.clock			= RC6_UNIT * 2,
-		.invert			= 1,
-	},
-	{
-		.clock			= RC6_UNIT,
-		.invert			= 1,
-		.trailer_space		= RC6_SUFFIX_SPACE,
-	},
-};
-
-static int ir_rc6_validate_filter(const struct rc_scancode_filter *scancode,
-				  unsigned int important_bits)
-{
-	/* all important bits of scancode should be set in mask */
-	if (~scancode->mask & important_bits)
-		return -EINVAL;
-	/* extra bits in mask should be zero in data */
-	if (scancode->mask & scancode->data & ~important_bits)
-		return -EINVAL;
-	return 0;
-}
-
-/**
- * ir_rc6_encode() - Encode a scancode as a stream of raw events
- *
- * @protocols:	allowed protocols
- * @scancode:	scancode filter describing scancode (helps distinguish between
- *		protocol subtypes when scancode is ambiguous)
- * @events:	array of raw ir events to write into
- * @max:	maximum size of @events
- *
- * Returns:	The number of events written.
- *		-ENOBUFS if there isn't enough space in the array to fit the
- *		encoding. In this case all @max events will have been written.
- *		-EINVAL if the scancode is ambiguous or invalid.
- */
-static int ir_rc6_encode(u64 protocols,
-			 const struct rc_scancode_filter *scancode,
-			 struct ir_raw_event *events, unsigned int max)
-{
-	int ret;
-	struct ir_raw_event *e = events;
-
-	if (protocols & RC_BIT_RC6_0 &&
-	    !ir_rc6_validate_filter(scancode, 0xffff)) {
-
-		/* Modulate the preamble */
-		ret = ir_raw_gen_manchester(&e, max, &ir_rc6_timings[0], 0, 0);
-		if (ret < 0)
-			return ret;
-
-		/* Modulate the header (Start Bit & Mode-0) */
-		ret = ir_raw_gen_manchester(&e, max - (e - events),
-					    &ir_rc6_timings[1],
-					    RC6_HEADER_NBITS, (1 << 3));
-		if (ret < 0)
-			return ret;
-
-		/* Modulate Trailer Bit */
-		ret = ir_raw_gen_manchester(&e, max - (e - events),
-					    &ir_rc6_timings[2], 1, 0);
-		if (ret < 0)
-			return ret;
-
-		/* Modulate rest of the data */
-		ret = ir_raw_gen_manchester(&e, max - (e - events),
-					    &ir_rc6_timings[3], RC6_0_NBITS,
-					    scancode->data);
-		if (ret < 0)
-			return ret;
-
-	} else if (protocols & (RC_BIT_RC6_6A_20 | RC_BIT_RC6_6A_24 |
-				RC_BIT_RC6_6A_32 | RC_BIT_RC6_MCE) &&
-		   !ir_rc6_validate_filter(scancode, 0x8fffffff)) {
-
-		/* Modulate the preamble */
-		ret = ir_raw_gen_manchester(&e, max, &ir_rc6_timings[0], 0, 0);
-		if (ret < 0)
-			return ret;
-
-		/* Modulate the header (Start Bit & Header-version 6 */
-		ret = ir_raw_gen_manchester(&e, max - (e - events),
-					    &ir_rc6_timings[1],
-					    RC6_HEADER_NBITS, (1 << 3 | 6));
-		if (ret < 0)
-			return ret;
-
-		/* Modulate Trailer Bit */
-		ret = ir_raw_gen_manchester(&e, max - (e - events),
-					    &ir_rc6_timings[2], 1, 0);
-		if (ret < 0)
-			return ret;
-
-		/* Modulate rest of the data */
-		ret = ir_raw_gen_manchester(&e, max - (e - events),
-					    &ir_rc6_timings[3],
-					    fls(scancode->mask),
-					    scancode->data);
-		if (ret < 0)
-			return ret;
-
-	} else {
-		return -EINVAL;
-	}
-
-	return e - events;
-}
-
 static struct ir_raw_handler rc6_handler = {
 	.protocols	= RC_BIT_RC6_0 | RC_BIT_RC6_6A_20 |
 			  RC_BIT_RC6_6A_24 | RC_BIT_RC6_6A_32 |
 			  RC_BIT_RC6_MCE,
 	.decode		= ir_rc6_decode,
-	.encode		= ir_rc6_encode,
 };
 
 static int __init ir_rc6_decode_init(void)
diff --git a/drivers/media/rc/nuvoton-cir.c b/drivers/media/rc/nuvoton-cir.c
index baeb597..85af7a8 100644
--- a/drivers/media/rc/nuvoton-cir.c
+++ b/drivers/media/rc/nuvoton-cir.c
@@ -526,130 +526,6 @@
 	return 0;
 }
 
-static int nvt_write_wakeup_codes(struct rc_dev *dev,
-				  const u8 *wakeup_sample_buf, int count)
-{
-	int i = 0;
-	u8 reg, reg_learn_mode;
-	unsigned long flags;
-	struct nvt_dev *nvt = dev->priv;
-
-	nvt_dbg_wake("writing wakeup samples");
-
-	reg = nvt_cir_wake_reg_read(nvt, CIR_WAKE_IRCON);
-	reg_learn_mode = reg & ~CIR_WAKE_IRCON_MODE0;
-	reg_learn_mode |= CIR_WAKE_IRCON_MODE1;
-
-	/* Lock the learn area to prevent racing with wake-isr */
-	spin_lock_irqsave(&nvt->nvt_lock, flags);
-
-	/* Enable fifo writes */
-	nvt_cir_wake_reg_write(nvt, reg_learn_mode, CIR_WAKE_IRCON);
-
-	/* Clear cir wake rx fifo */
-	nvt_clear_cir_wake_fifo(nvt);
-
-	if (count > WAKE_FIFO_LEN) {
-		nvt_dbg_wake("HW FIFO too small for all wake samples");
-		count = WAKE_FIFO_LEN;
-	}
-
-	if (count)
-		pr_info("Wake samples (%d) =", count);
-	else
-		pr_info("Wake sample fifo cleared");
-
-	/* Write wake samples to fifo */
-	for (i = 0; i < count; i++) {
-		pr_cont(" %02x", wakeup_sample_buf[i]);
-		nvt_cir_wake_reg_write(nvt, wakeup_sample_buf[i],
-				       CIR_WAKE_WR_FIFO_DATA);
-	}
-	pr_cont("\n");
-
-	/* Switch cir to wakeup mode and disable fifo writing */
-	nvt_cir_wake_reg_write(nvt, reg, CIR_WAKE_IRCON);
-
-	/* Set number of bytes needed for wake */
-	nvt_cir_wake_reg_write(nvt, count ? count :
-			       CIR_WAKE_FIFO_CMP_BYTES,
-			       CIR_WAKE_FIFO_CMP_DEEP);
-
-	spin_unlock_irqrestore(&nvt->nvt_lock, flags);
-
-	return 0;
-}
-
-static int nvt_ir_raw_set_wakeup_filter(struct rc_dev *dev,
-					struct rc_scancode_filter *sc_filter)
-{
-	u8 *reg_buf;
-	u8 buf_val;
-	int i, ret, count;
-	unsigned int val;
-	struct ir_raw_event *raw;
-	bool complete;
-
-	/* Require both mask and data to be set before actually committing */
-	if (!sc_filter->mask || !sc_filter->data)
-		return 0;
-
-	raw = kmalloc_array(WAKE_FIFO_LEN, sizeof(*raw), GFP_KERNEL);
-	if (!raw)
-		return -ENOMEM;
-
-	ret = ir_raw_encode_scancode(dev->enabled_wakeup_protocols, sc_filter,
-				     raw, WAKE_FIFO_LEN);
-	complete = (ret != -ENOBUFS);
-	if (!complete)
-		ret = WAKE_FIFO_LEN;
-	else if (ret < 0)
-		goto out_raw;
-
-	reg_buf = kmalloc_array(WAKE_FIFO_LEN, sizeof(*reg_buf), GFP_KERNEL);
-	if (!reg_buf) {
-		ret = -ENOMEM;
-		goto out_raw;
-	}
-
-	/* Inspect the ir samples */
-	for (i = 0, count = 0; i < ret && count < WAKE_FIFO_LEN; ++i) {
-		val = NS_TO_US((raw[i]).duration) / SAMPLE_PERIOD;
-
-		/* Split too large values into several smaller ones */
-		while (val > 0 && count < WAKE_FIFO_LEN) {
-
-			/* Skip last value for better comparison tolerance */
-			if (complete && i == ret - 1 && val < BUF_LEN_MASK)
-				break;
-
-			/* Clamp values to BUF_LEN_MASK at most */
-			buf_val = (val > BUF_LEN_MASK) ? BUF_LEN_MASK : val;
-
-			reg_buf[count] = buf_val;
-			val -= buf_val;
-			if ((raw[i]).pulse)
-				reg_buf[count] |= BUF_PULSE_BIT;
-			count++;
-		}
-	}
-
-	ret = nvt_write_wakeup_codes(dev, reg_buf, count);
-
-	kfree(reg_buf);
-out_raw:
-	kfree(raw);
-
-	return ret;
-}
-
-/* Dummy implementation. nuvoton is agnostic to the protocol used */
-static int nvt_ir_raw_change_wakeup_protocol(struct rc_dev *dev,
-					     u64 *rc_type)
-{
-	return 0;
-}
-
 /*
  * nvt_tx_ir
  *
@@ -1167,14 +1043,11 @@
 	/* Set up the rc device */
 	rdev->priv = nvt;
 	rdev->driver_type = RC_DRIVER_IR_RAW;
-	rdev->encode_wakeup = true;
 	rdev->allowed_protocols = RC_BIT_ALL;
 	rdev->open = nvt_open;
 	rdev->close = nvt_close;
 	rdev->tx_ir = nvt_tx_ir;
 	rdev->s_tx_carrier = nvt_set_tx_carrier;
-	rdev->s_wakeup_filter = nvt_ir_raw_set_wakeup_filter;
-	rdev->change_wakeup_protocol = nvt_ir_raw_change_wakeup_protocol;
 	rdev->input_name = "Nuvoton w836x7hg Infrared Remote Transceiver";
 	rdev->input_phys = "nuvoton/cir0";
 	rdev->input_id.bustype = BUS_HOST;
diff --git a/drivers/media/rc/nuvoton-cir.h b/drivers/media/rc/nuvoton-cir.h
index 9d0e161..e1cf23c 100644
--- a/drivers/media/rc/nuvoton-cir.h
+++ b/drivers/media/rc/nuvoton-cir.h
@@ -63,7 +63,6 @@
  */
 #define TX_BUF_LEN 256
 #define RX_BUF_LEN 32
-#define WAKE_FIFO_LEN 67
 
 struct nvt_dev {
 	struct pnp_dev *pdev;
diff --git a/drivers/media/rc/rc-core-priv.h b/drivers/media/rc/rc-core-priv.h
index 4b994aa..b68d4f76 100644
--- a/drivers/media/rc/rc-core-priv.h
+++ b/drivers/media/rc/rc-core-priv.h
@@ -25,8 +25,6 @@
 
 	u64 protocols; /* which are handled by this handler */
 	int (*decode)(struct rc_dev *dev, struct ir_raw_event event);
-	int (*encode)(u64 protocols, const struct rc_scancode_filter *scancode,
-		      struct ir_raw_event *events, unsigned int max);
 
 	/* These two should only be used by the lirc decoder */
 	int (*raw_register)(struct rc_dev *dev);
@@ -152,44 +150,10 @@
 #define TO_US(duration)			DIV_ROUND_CLOSEST((duration), 1000)
 #define TO_STR(is_pulse)		((is_pulse) ? "pulse" : "space")
 
-/* functions for IR encoders */
-
-static inline void init_ir_raw_event_duration(struct ir_raw_event *ev,
-					      unsigned int pulse,
-					      u32 duration)
-{
-	init_ir_raw_event(ev);
-	ev->duration = duration;
-	ev->pulse = pulse;
-}
-
-/**
- * struct ir_raw_timings_manchester - Manchester coding timings
- * @leader:		duration of leader pulse (if any) 0 if continuing
- *			existing signal (see @pulse_space_start)
- * @pulse_space_start:	1 for starting with pulse (0 for starting with space)
- * @clock:		duration of each pulse/space in ns
- * @invert:		if set clock logic is inverted
- *			(0 = space + pulse, 1 = pulse + space)
- * @trailer_space:	duration of trailer space in ns
- */
-struct ir_raw_timings_manchester {
-	unsigned int leader;
-	unsigned int pulse_space_start:1;
-	unsigned int clock;
-	unsigned int invert:1;
-	unsigned int trailer_space;
-};
-
-int ir_raw_gen_manchester(struct ir_raw_event **ev, unsigned int max,
-			  const struct ir_raw_timings_manchester *timings,
-			  unsigned int n, unsigned int data);
-
 /*
  * Routines from rc-raw.c to be used internally and by decoders
  */
 u64 ir_raw_get_allowed_protocols(void);
-u64 ir_raw_get_encode_protocols(void);
 int ir_raw_event_register(struct rc_dev *dev);
 void ir_raw_event_unregister(struct rc_dev *dev);
 int ir_raw_handler_register(struct ir_raw_handler *ir_raw_handler);
diff --git a/drivers/media/rc/rc-ir-raw.c b/drivers/media/rc/rc-ir-raw.c
index b9e4645..b732ac6 100644
--- a/drivers/media/rc/rc-ir-raw.c
+++ b/drivers/media/rc/rc-ir-raw.c
@@ -30,7 +30,6 @@
 static DEFINE_MUTEX(ir_raw_handler_lock);
 static LIST_HEAD(ir_raw_handler_list);
 static u64 available_protocols;
-static u64 encode_protocols;
 
 static int ir_raw_event_thread(void *data)
 {
@@ -241,146 +240,12 @@
 	return protocols;
 }
 
-/* used internally by the sysfs interface */
-u64
-ir_raw_get_encode_protocols(void)
-{
-	u64 protocols;
-
-	mutex_lock(&ir_raw_handler_lock);
-	protocols = encode_protocols;
-	mutex_unlock(&ir_raw_handler_lock);
-	return protocols;
-}
-
 static int change_protocol(struct rc_dev *dev, u64 *rc_type)
 {
 	/* the caller will update dev->enabled_protocols */
 	return 0;
 }
 
-/**
- * ir_raw_gen_manchester() - Encode data with Manchester (bi-phase) modulation.
- * @ev:		Pointer to pointer to next free event. *@ev is incremented for
- *		each raw event filled.
- * @max:	Maximum number of raw events to fill.
- * @timings:	Manchester modulation timings.
- * @n:		Number of bits of data.
- * @data:	Data bits to encode.
- *
- * Encodes the @n least significant bits of @data using Manchester (bi-phase)
- * modulation with the timing characteristics described by @timings, writing up
- * to @max raw IR events using the *@ev pointer.
- *
- * Returns:	0 on success.
- *		-ENOBUFS if there isn't enough space in the array to fit the
- *		full encoded data. In this case all @max events will have been
- *		written.
- */
-int ir_raw_gen_manchester(struct ir_raw_event **ev, unsigned int max,
-			  const struct ir_raw_timings_manchester *timings,
-			  unsigned int n, unsigned int data)
-{
-	bool need_pulse;
-	unsigned int i;
-	int ret = -ENOBUFS;
-
-	i = 1 << (n - 1);
-
-	if (timings->leader) {
-		if (!max--)
-			return ret;
-		if (timings->pulse_space_start) {
-			init_ir_raw_event_duration((*ev)++, 1, timings->leader);
-
-			if (!max--)
-				return ret;
-			init_ir_raw_event_duration((*ev), 0, timings->leader);
-		} else {
-			init_ir_raw_event_duration((*ev), 1, timings->leader);
-		}
-		i >>= 1;
-	} else {
-		/* continue existing signal */
-		--(*ev);
-	}
-	/* from here on *ev will point to the last event rather than the next */
-
-	while (n && i > 0) {
-		need_pulse = !(data & i);
-		if (timings->invert)
-			need_pulse = !need_pulse;
-		if (need_pulse == !!(*ev)->pulse) {
-			(*ev)->duration += timings->clock;
-		} else {
-			if (!max--)
-				goto nobufs;
-			init_ir_raw_event_duration(++(*ev), need_pulse,
-						   timings->clock);
-		}
-
-		if (!max--)
-			goto nobufs;
-		init_ir_raw_event_duration(++(*ev), !need_pulse,
-					   timings->clock);
-		i >>= 1;
-	}
-
-	if (timings->trailer_space) {
-		if (!(*ev)->pulse)
-			(*ev)->duration += timings->trailer_space;
-		else if (!max--)
-			goto nobufs;
-		else
-			init_ir_raw_event_duration(++(*ev), 0,
-						   timings->trailer_space);
-	}
-
-	ret = 0;
-nobufs:
-	/* point to the next event rather than last event before returning */
-	++(*ev);
-	return ret;
-}
-EXPORT_SYMBOL(ir_raw_gen_manchester);
-
-/**
- * ir_raw_encode_scancode() - Encode a scancode as raw events
- *
- * @protocols:		permitted protocols
- * @scancode:		scancode filter describing a single scancode
- * @events:		array of raw events to write into
- * @max:		max number of raw events
- *
- * Attempts to encode the scancode as raw events.
- *
- * Returns:	The number of events written.
- *		-ENOBUFS if there isn't enough space in the array to fit the
- *		encoding. In this case all @max events will have been written.
- *		-EINVAL if the scancode is ambiguous or invalid, or if no
- *		compatible encoder was found.
- */
-int ir_raw_encode_scancode(u64 protocols,
-			   const struct rc_scancode_filter *scancode,
-			   struct ir_raw_event *events, unsigned int max)
-{
-	struct ir_raw_handler *handler;
-	int ret = -EINVAL;
-
-	mutex_lock(&ir_raw_handler_lock);
-	list_for_each_entry(handler, &ir_raw_handler_list, list) {
-		if (handler->protocols & protocols && handler->encode) {
-			ret = handler->encode(protocols, scancode, events, max);
-			if (ret >= 0 || ret == -ENOBUFS)
-				break;
-		}
-	}
-	mutex_unlock(&ir_raw_handler_lock);
-
-	return ret;
-}
-EXPORT_SYMBOL(ir_raw_encode_scancode);
-
 /*
  * Used to (un)register raw event clients
  */
@@ -463,8 +328,6 @@
 		list_for_each_entry(raw, &ir_raw_client_list, list)
 			ir_raw_handler->raw_register(raw->dev);
 	available_protocols |= ir_raw_handler->protocols;
-	if (ir_raw_handler->encode)
-		encode_protocols |= ir_raw_handler->protocols;
 	mutex_unlock(&ir_raw_handler_lock);
 
 	return 0;
@@ -481,8 +344,6 @@
 		list_for_each_entry(raw, &ir_raw_client_list, list)
 			ir_raw_handler->raw_unregister(raw->dev);
 	available_protocols &= ~ir_raw_handler->protocols;
-	if (ir_raw_handler->encode)
-		encode_protocols &= ~ir_raw_handler->protocols;
 	mutex_unlock(&ir_raw_handler_lock);
 }
 EXPORT_SYMBOL(ir_raw_handler_unregister);
diff --git a/drivers/media/rc/rc-loopback.c b/drivers/media/rc/rc-loopback.c
index d8bdf63..63dace8 100644
--- a/drivers/media/rc/rc-loopback.c
+++ b/drivers/media/rc/rc-loopback.c
@@ -26,7 +26,6 @@
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/sched.h>
-#include <linux/slab.h>
 #include <media/rc-core.h>
 
 #define DRIVER_NAME	"rc-loopback"
@@ -177,39 +176,6 @@
 	return 0;
 }
 
-static int loop_set_wakeup_filter(struct rc_dev *dev,
-				  struct rc_scancode_filter *sc_filter)
-{
-	static const unsigned int max = 512;
-	struct ir_raw_event *raw;
-	int ret;
-	int i;
-
-	/* fine to disable filter */
-	if (!sc_filter->mask)
-		return 0;
-
-	/* encode the specified filter and loop it back */
-	raw = kmalloc_array(max, sizeof(*raw), GFP_KERNEL);
-	ret = ir_raw_encode_scancode(dev->enabled_wakeup_protocols, sc_filter,
-				     raw, max);
-	/* still loop back the partial raw IR even if it's incomplete */
-	if (ret == -ENOBUFS)
-		ret = max;
-	if (ret >= 0) {
-		/* do the loopback */
-		for (i = 0; i < ret; ++i)
-			ir_raw_event_store(dev, &raw[i]);
-		ir_raw_event_handle(dev);
-
-		ret = 0;
-	}
-
-	kfree(raw);
-
-	return ret;
-}
-
 static int __init loop_init(void)
 {
 	struct rc_dev *rc;
@@ -229,7 +195,6 @@
 	rc->map_name		= RC_MAP_EMPTY;
 	rc->priv		= &loopdev;
 	rc->driver_type		= RC_DRIVER_IR_RAW;
-	rc->encode_wakeup	= true;
 	rc->allowed_protocols	= RC_BIT_ALL;
 	rc->timeout		= 100 * 1000 * 1000; /* 100 ms */
 	rc->min_timeout		= 1;
@@ -244,7 +209,6 @@
 	rc->s_idle		= loop_set_idle;
 	rc->s_learning_mode	= loop_set_learning_mode;
 	rc->s_carrier_report	= loop_set_carrier_report;
-	rc->s_wakeup_filter	= loop_set_wakeup_filter;
 
 	loopdev.txmask		= RXMASK_REGULAR;
 	loopdev.txcarrier	= 36000;
diff --git a/drivers/media/rc/rc-main.c b/drivers/media/rc/rc-main.c
index 9d015db..0ff388a 100644
--- a/drivers/media/rc/rc-main.c
+++ b/drivers/media/rc/rc-main.c
@@ -865,8 +865,6 @@
 	} else {
 		enabled = dev->enabled_wakeup_protocols;
 		allowed = dev->allowed_wakeup_protocols;
-		if (dev->encode_wakeup && !allowed)
-			allowed = ir_raw_get_encode_protocols();
 	}
 
 	mutex_unlock(&dev->lock);
@@ -1408,16 +1406,13 @@
 		path ? path : "N/A");
 	kfree(path);
 
-	if (dev->driver_type == RC_DRIVER_IR_RAW || dev->encode_wakeup) {
+	if (dev->driver_type == RC_DRIVER_IR_RAW) {
 		/* Load raw decoders, if they aren't already */
 		if (!raw_init) {
 			IR_dprintk(1, "Loading raw decoders\n");
 			ir_raw_init();
 			raw_init = true;
 		}
-	}
-
-	if (dev->driver_type == RC_DRIVER_IR_RAW) {
 		/* calls ir_register_device so unlock mutex here*/
 		mutex_unlock(&dev->lock);
 		rc = ir_raw_event_register(dev);
diff --git a/drivers/media/v4l2-core/videobuf2-core.c b/drivers/media/v4l2-core/videobuf2-core.c
index 93b3154..a14c428 100644
--- a/drivers/media/v4l2-core/videobuf2-core.c
+++ b/drivers/media/v4l2-core/videobuf2-core.c
@@ -715,6 +715,7 @@
 		break;
 	case VB2_BUF_STATE_PREPARING:
 	case VB2_BUF_STATE_DEQUEUED:
+	case VB2_BUF_STATE_REQUEUEING:
 		/* nothing */
 		break;
 	}
@@ -1182,7 +1183,8 @@
 
 	if (WARN_ON(state != VB2_BUF_STATE_DONE &&
 		    state != VB2_BUF_STATE_ERROR &&
-		    state != VB2_BUF_STATE_QUEUED))
+		    state != VB2_BUF_STATE_QUEUED &&
+		    state != VB2_BUF_STATE_REQUEUEING))
 		state = VB2_BUF_STATE_ERROR;
 
 #ifdef CONFIG_VIDEO_ADV_DEBUG
@@ -1199,22 +1201,30 @@
 	for (plane = 0; plane < vb->num_planes; ++plane)
 		call_void_memop(vb, finish, vb->planes[plane].mem_priv);
 
-	/* Add the buffer to the done buffers list */
 	spin_lock_irqsave(&q->done_lock, flags);
-	vb->state = state;
-	if (state != VB2_BUF_STATE_QUEUED)
+	if (state == VB2_BUF_STATE_QUEUED ||
+	    state == VB2_BUF_STATE_REQUEUEING) {
+		vb->state = VB2_BUF_STATE_QUEUED;
+	} else {
+		/* Add the buffer to the done buffers list */
 		list_add_tail(&vb->done_entry, &q->done_list);
+		vb->state = state;
+	}
 	atomic_dec(&q->owned_by_drv_count);
 	spin_unlock_irqrestore(&q->done_lock, flags);
 
-	if (state == VB2_BUF_STATE_QUEUED) {
+	switch (state) {
+	case VB2_BUF_STATE_QUEUED:
+		return;
+	case VB2_BUF_STATE_REQUEUEING:
 		if (q->start_streaming_called)
 			__enqueue_in_driver(vb);
 		return;
+	default:
+		/* Inform any processes that may be waiting for buffers */
+		wake_up(&q->done_wq);
+		break;
 	}
-
-	/* Inform any processes that may be waiting for buffers */
-	wake_up(&q->done_wq);
 }
 EXPORT_SYMBOL_GPL(vb2_buffer_done);
 
@@ -1244,19 +1254,19 @@
 
 static void vb2_warn_zero_bytesused(struct vb2_buffer *vb)
 {
-	static bool __check_once __read_mostly;
+	static bool check_once;
 
-	if (__check_once)
+	if (check_once)
 		return;
 
-	__check_once = true;
-	__WARN();
+	check_once = true;
+	WARN_ON(1);
 
-	pr_warn_once("use of bytesused == 0 is deprecated and will be removed in the future,\n");
+	pr_warn("use of bytesused == 0 is deprecated and will be removed in the future,\n");
 	if (vb->vb2_queue->allow_zero_bytesused)
-		pr_warn_once("use VIDIOC_DECODER_CMD(V4L2_DEC_CMD_STOP) instead.\n");
+		pr_warn("use VIDIOC_DECODER_CMD(V4L2_DEC_CMD_STOP) instead.\n");
 	else
-		pr_warn_once("use the actual size instead.\n");
+		pr_warn("use the actual size instead.\n");
 }
 
 /**
diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c
index 8911e51..9426276 100644
--- a/drivers/memory/omap-gpmc.c
+++ b/drivers/memory/omap-gpmc.c
@@ -2074,14 +2074,8 @@
 			ret = gpmc_probe_nand_child(pdev, child);
 		else if (of_node_cmp(child->name, "onenand") == 0)
 			ret = gpmc_probe_onenand_child(pdev, child);
-		else if (of_node_cmp(child->name, "ethernet") == 0 ||
-			 of_node_cmp(child->name, "nor") == 0 ||
-			 of_node_cmp(child->name, "uart") == 0)
+		else
 			ret = gpmc_probe_generic_child(pdev, child);
-
-		if (WARN(ret < 0, "%s: probing gpmc child %s failed\n",
-			 __func__, child->full_name))
-			of_node_put(child);
 	}
 
 	return 0;
@@ -2251,6 +2245,9 @@
 {
 	int i;
 
+	if (!gpmc_base)
+		return;
+
 	gpmc_context.sysconfig = gpmc_read_reg(GPMC_SYSCONFIG);
 	gpmc_context.irqenable = gpmc_read_reg(GPMC_IRQENABLE);
 	gpmc_context.timeout_ctrl = gpmc_read_reg(GPMC_TIMEOUT_CONTROL);
@@ -2283,6 +2280,9 @@
 {
 	int i;
 
+	if (!gpmc_base)
+		return;
+
 	gpmc_write_reg(GPMC_SYSCONFIG, gpmc_context.sysconfig);
 	gpmc_write_reg(GPMC_IRQENABLE, gpmc_context.irqenable);
 	gpmc_write_reg(GPMC_TIMEOUT_CONTROL, gpmc_context.timeout_ctrl);
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 6538159..3f68dd2 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -115,7 +115,7 @@
 
 config MFD_CROS_EC_SPI
 	tristate "ChromeOS Embedded Controller (SPI)"
-	depends on MFD_CROS_EC && CROS_EC_PROTO && SPI && OF
+	depends on MFD_CROS_EC && CROS_EC_PROTO && SPI
 
 	---help---
 	  If you say Y here, you get support for talking to the ChromeOS EC
diff --git a/drivers/mfd/arizona-core.c b/drivers/mfd/arizona-core.c
index bebf58a..a72ddb29 100644
--- a/drivers/mfd/arizona-core.c
+++ b/drivers/mfd/arizona-core.c
@@ -651,7 +651,7 @@
 
 		arizona->has_fully_powered_off = true;
 
-		disable_irq(arizona->irq);
+		disable_irq_nosync(arizona->irq);
 		arizona_enable_reset(arizona);
 		regulator_bulk_disable(arizona->num_core_supplies,
 				       arizona->core_supplies);
@@ -1141,10 +1141,6 @@
 			     arizona->pdata.gpio_defaults[i]);
 	}
 
-	pm_runtime_set_autosuspend_delay(arizona->dev, 100);
-	pm_runtime_use_autosuspend(arizona->dev);
-	pm_runtime_enable(arizona->dev);
-
 	/* Chip default */
 	if (!arizona->pdata.clk32k_src)
 		arizona->pdata.clk32k_src = ARIZONA_32KZ_MCLK2;
@@ -1245,11 +1241,17 @@
 					   arizona->pdata.spk_fmt[i]);
 	}
 
+	pm_runtime_set_active(arizona->dev);
+	pm_runtime_enable(arizona->dev);
+
 	/* Set up for interrupts */
 	ret = arizona_irq_init(arizona);
 	if (ret != 0)
 		goto err_reset;
 
+	pm_runtime_set_autosuspend_delay(arizona->dev, 100);
+	pm_runtime_use_autosuspend(arizona->dev);
+
 	arizona_request_irq(arizona, ARIZONA_IRQ_CLKGEN_ERR, "CLKGEN error",
 			    arizona_clkgen_err, arizona);
 	arizona_request_irq(arizona, ARIZONA_IRQ_OVERCLOCKED, "Overclocked",
@@ -1278,10 +1280,6 @@
 		goto err_irq;
 	}
 
-#ifdef CONFIG_PM
-	regulator_disable(arizona->dcvdd);
-#endif
-
 	return 0;
 
 err_irq:
diff --git a/drivers/mfd/stmpe-i2c.c b/drivers/mfd/stmpe-i2c.c
index 5c05403..e14c8c9 100644
--- a/drivers/mfd/stmpe-i2c.c
+++ b/drivers/mfd/stmpe-i2c.c
@@ -6,7 +6,7 @@
  *
  * License Terms: GNU General Public License, version 2
  * Author: Rabin Vincent <rabin.vincent@stericsson.com> for ST-Ericsson
- * Author: Viresh Kumar <viresh.linux@gmail.com> for ST Microelectronics
+ * Author: Viresh Kumar <vireshk@kernel.org> for ST Microelectronics
  */
 
 #include <linux/i2c.h>
diff --git a/drivers/mfd/stmpe-spi.c b/drivers/mfd/stmpe-spi.c
index a81badb..6fdb30e 100644
--- a/drivers/mfd/stmpe-spi.c
+++ b/drivers/mfd/stmpe-spi.c
@@ -4,7 +4,7 @@
  * Copyright (C) ST Microelectronics SA 2011
  *
  * License Terms: GNU General Public License, version 2
- * Author: Viresh Kumar <viresh.linux@gmail.com> for ST Microelectronics
+ * Author: Viresh Kumar <vireshk@kernel.org> for ST Microelectronics
  */
 
 #include <linux/spi/spi.h>
@@ -146,4 +146,4 @@
 
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("STMPE MFD SPI Interface Driver");
-MODULE_AUTHOR("Viresh Kumar <viresh.linux@gmail.com>");
+MODULE_AUTHOR("Viresh Kumar <vireshk@kernel.org>");
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 0c77240..729e085 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -23,6 +23,7 @@
 
 	afu = cxl_pci_to_afu(dev);
 
+	get_device(&afu->dev);
 	ctx = cxl_context_alloc();
 	if (IS_ERR(ctx))
 		return ctx;
@@ -31,6 +32,7 @@
 	rc = cxl_context_init(ctx, afu, false, NULL);
 	if (rc) {
 		kfree(ctx);
+		put_device(&afu->dev);
 		return ERR_PTR(-ENOMEM);
 	}
 	cxl_assign_psn_space(ctx);
@@ -60,6 +62,8 @@
 	if (ctx->status != CLOSED)
 		return -EBUSY;
 
+	put_device(&ctx->afu->dev);
+
 	cxl_context_free(ctx);
 
 	return 0;
@@ -159,7 +163,6 @@
 	}
 
 	ctx->status = STARTED;
-	get_device(&ctx->afu->dev);
 out:
 	mutex_unlock(&ctx->status_mutex);
 	return rc;
@@ -175,12 +178,7 @@
 /* Stop a context.  Returns 0 on success, otherwise -Errno */
 int cxl_stop_context(struct cxl_context *ctx)
 {
-	int rc;
-
-	rc = __detach_context(ctx);
-	if (!rc)
-		put_device(&ctx->afu->dev);
-	return rc;
+	return __detach_context(ctx);
 }
 EXPORT_SYMBOL_GPL(cxl_stop_context);
 
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index 2a4c80a..1287148 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -113,11 +113,11 @@
 
 	if (ctx->afu->current_mode == CXL_MODE_DEDICATED) {
 		area = ctx->afu->psn_phys;
-		if (offset > ctx->afu->adapter->ps_size)
+		if (offset >= ctx->afu->adapter->ps_size)
 			return VM_FAULT_SIGBUS;
 	} else {
 		area = ctx->psn_phys;
-		if (offset > ctx->psn_size)
+		if (offset >= ctx->psn_size)
 			return VM_FAULT_SIGBUS;
 	}
 
@@ -145,8 +145,16 @@
  */
 int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma)
 {
+	u64 start = vma->vm_pgoff << PAGE_SHIFT;
 	u64 len = vma->vm_end - vma->vm_start;
-	len = min(len, ctx->psn_size);
+
+	if (ctx->afu->current_mode == CXL_MODE_DEDICATED) {
+		if (start + len > ctx->afu->adapter->ps_size)
+			return -EINVAL;
+	} else {
+		if (start + len > ctx->psn_size)
+			return -EINVAL;
+	}
 
 	if (ctx->afu->current_mode != CXL_MODE_DEDICATED) {
 		/* make sure there is a valid per process space for this AFU */
diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c
index 833348e..4a164ab 100644
--- a/drivers/misc/cxl/main.c
+++ b/drivers/misc/cxl/main.c
@@ -73,7 +73,7 @@
 		spin_lock(&adapter->afu_list_lock);
 		for (slice = 0; slice < adapter->slices; slice++) {
 			afu = adapter->afu[slice];
-			if (!afu->enabled)
+			if (!afu || !afu->enabled)
 				continue;
 			rcu_read_lock();
 			idr_for_each_entry(&afu->contexts_idr, ctx, id)
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index c68ef58..32ad097 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -539,7 +539,7 @@
 
 static void cxl_unmap_slice_regs(struct cxl_afu *afu)
 {
-	if (afu->p1n_mmio)
+	if (afu->p2n_mmio)
 		iounmap(afu->p2n_mmio);
 	if (afu->p1n_mmio)
 		iounmap(afu->p1n_mmio);
diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c
index b1d1983a..2eba002 100644
--- a/drivers/misc/cxl/vphb.c
+++ b/drivers/misc/cxl/vphb.c
@@ -112,9 +112,10 @@
 	unsigned long addr;
 
 	phb = pci_bus_to_host(bus);
-	afu = (struct cxl_afu *)phb->private_data;
 	if (phb == NULL)
 		return PCIBIOS_DEVICE_NOT_FOUND;
+	afu = (struct cxl_afu *)phb->private_data;
+
 	if (cxl_pcie_cfg_record(bus->number, devfn) > afu->crs_num)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 	if (offset >= (unsigned long)phb->cfg_data)
diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index 2d3db81..6ded3dc 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -438,9 +438,6 @@
 {
 	struct at24_data *at24;
 
-	if (unlikely(off >= attr->size))
-		return -EFBIG;
-
 	at24 = dev_get_drvdata(container_of(kobj, struct device, kobj));
 	return at24_write(at24, buf, off, count);
 }
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index 357b6ae..458aa5a 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -552,22 +552,6 @@
 	schedule_work(&device->event_work);
 }
 
-void mei_cl_bus_remove_devices(struct mei_device *dev)
-{
-	struct mei_cl *cl, *next;
-
-	mutex_lock(&dev->device_lock);
-	list_for_each_entry_safe(cl, next, &dev->device_list, device_link) {
-		if (cl->device)
-			mei_cl_remove_device(cl->device);
-
-		list_del(&cl->device_link);
-		mei_cl_unlink(cl);
-		kfree(cl);
-	}
-	mutex_unlock(&dev->device_lock);
-}
-
 int __init mei_cl_bus_init(void)
 {
 	return bus_register(&mei_cl_bus_type);
diff --git a/drivers/misc/mei/init.c b/drivers/misc/mei/init.c
index 94514b2..00c3865 100644
--- a/drivers/misc/mei/init.c
+++ b/drivers/misc/mei/init.c
@@ -333,8 +333,6 @@
 
 	mei_nfc_host_exit(dev);
 
-	mei_cl_bus_remove_devices(dev);
-
 	mutex_lock(&dev->device_lock);
 
 	mei_wd_stop(dev);
diff --git a/drivers/misc/mei/main.c b/drivers/misc/mei/main.c
index 8eb0a95..e9513d6 100644
--- a/drivers/misc/mei/main.c
+++ b/drivers/misc/mei/main.c
@@ -682,7 +682,7 @@
 	/* Fill in the data structures */
 	devno = MKDEV(MAJOR(mei_devt), dev->minor);
 	cdev_init(&dev->cdev, &mei_fops);
-	dev->cdev.owner = mei_fops.owner;
+	dev->cdev.owner = parent->driver->owner;
 
 	/* Add the device */
 	ret = cdev_add(&dev->cdev, devno, 1);
diff --git a/drivers/misc/mei/nfc.c b/drivers/misc/mei/nfc.c
index b983c4e..290ef30 100644
--- a/drivers/misc/mei/nfc.c
+++ b/drivers/misc/mei/nfc.c
@@ -402,11 +402,12 @@
 
 	cldev->priv_data = NULL;
 
-	mutex_lock(&dev->device_lock);
 	/* Need to remove the device here
 	 * since mei_nfc_free will unlink the clients
 	 */
 	mei_cl_remove_device(cldev);
+
+	mutex_lock(&dev->device_lock);
 	mei_nfc_free(ndev);
 	mutex_unlock(&dev->device_lock);
 }
diff --git a/drivers/misc/mic/scif/scif_nodeqp.c b/drivers/misc/mic/scif/scif_nodeqp.c
index 41e3bdb..6dfdae3 100644
--- a/drivers/misc/mic/scif/scif_nodeqp.c
+++ b/drivers/misc/mic/scif/scif_nodeqp.c
@@ -357,7 +357,7 @@
 }
 
 static struct scatterlist *
-scif_p2p_setsg(void __iomem *va, int page_size, int page_cnt)
+scif_p2p_setsg(phys_addr_t pa, int page_size, int page_cnt)
 {
 	struct scatterlist *sg;
 	struct page *page;
@@ -368,16 +368,11 @@
 		return NULL;
 	sg_init_table(sg, page_cnt);
 	for (i = 0; i < page_cnt; i++) {
-		page = vmalloc_to_page((void __force *)va);
-		if (!page)
-			goto p2p_sg_err;
+		page = pfn_to_page(pa >> PAGE_SHIFT);
 		sg_set_page(&sg[i], page, page_size, 0);
-		va += page_size;
+		pa += page_size;
 	}
 	return sg;
-p2p_sg_err:
-	kfree(sg);
-	return NULL;
 }
 
 /* Init p2p mappings required to access peerdev from scifdev */
@@ -395,14 +390,14 @@
 	p2p = kzalloc(sizeof(*p2p), GFP_KERNEL);
 	if (!p2p)
 		return NULL;
-	p2p->ppi_sg[SCIF_PPI_MMIO] = scif_p2p_setsg(psdev->mmio->va,
+	p2p->ppi_sg[SCIF_PPI_MMIO] = scif_p2p_setsg(psdev->mmio->pa,
 						    PAGE_SIZE, num_mmio_pages);
 	if (!p2p->ppi_sg[SCIF_PPI_MMIO])
 		goto free_p2p;
 	p2p->sg_nentries[SCIF_PPI_MMIO] = num_mmio_pages;
 	sg_page_shift = get_order(min(psdev->aper->len, (u64)(1 << 30)));
 	num_aper_chunks = num_aper_pages >> (sg_page_shift - PAGE_SHIFT);
-	p2p->ppi_sg[SCIF_PPI_APER] = scif_p2p_setsg(psdev->aper->va,
+	p2p->ppi_sg[SCIF_PPI_APER] = scif_p2p_setsg(psdev->aper->pa,
 						    1 << sg_page_shift,
 						    num_aper_chunks);
 	p2p->sg_nentries[SCIF_PPI_APER] = num_aper_chunks;
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index c9c3d20..a1b820f 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -208,6 +208,8 @@
 
 	ret = snprintf(buf, PAGE_SIZE, "%d\n", locked);
 
+	mmc_blk_put(md);
+
 	return ret;
 }
 
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index fd9a58e..6a0f9c7 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -779,6 +779,7 @@
 
 config MMC_MTK
 	tristate "MediaTek SD/MMC Card Interface support"
+	depends on HAS_DMA
 	help
 	  This selects the MediaTek(R) Secure digital and Multimedia card Interface.
 	  If you have a machine with a integrated SD/MMC card reader, say Y or M here.
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index b2b411d..4d12032 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -1062,9 +1062,14 @@
 
 		if (status & (CTO_EN | CCRC_EN))
 			end_cmd = 1;
+		if (host->data || host->response_busy) {
+			end_trans = !end_cmd;
+			host->response_busy = 0;
+		}
 		if (status & (CTO_EN | DTO_EN))
 			hsmmc_command_incomplete(host, -ETIMEDOUT, end_cmd);
-		else if (status & (CCRC_EN | DCRC_EN))
+		else if (status & (CCRC_EN | DCRC_EN | DEB_EN | CEB_EN |
+				   BADA_EN))
 			hsmmc_command_incomplete(host, -EILSEQ, end_cmd);
 
 		if (status & ACE_EN) {
@@ -1081,10 +1086,6 @@
 			}
 			dev_dbg(mmc_dev(host->mmc), "AC12 err: 0x%x\n", ac12);
 		}
-		if (host->data || host->response_busy) {
-			end_trans = !end_cmd;
-			host->response_busy = 0;
-		}
 	}
 
 	OMAP_HSMMC_WRITE(host->base, STAT, status);
diff --git a/drivers/mmc/host/sdhci-esdhc-imx.c b/drivers/mmc/host/sdhci-esdhc-imx.c
index faf0cb9..c6b9f64 100644
--- a/drivers/mmc/host/sdhci-esdhc-imx.c
+++ b/drivers/mmc/host/sdhci-esdhc-imx.c
@@ -581,13 +581,8 @@
 static unsigned int esdhc_pltfm_get_max_clock(struct sdhci_host *host)
 {
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
-	struct pltfm_imx_data *imx_data = pltfm_host->priv;
-	struct esdhc_platform_data *boarddata = &imx_data->boarddata;
 
-	if (boarddata->f_max && (boarddata->f_max < pltfm_host->clock))
-		return boarddata->f_max;
-	else
-		return pltfm_host->clock;
+	return pltfm_host->clock;
 }
 
 static unsigned int esdhc_pltfm_get_min_clock(struct sdhci_host *host)
@@ -878,34 +873,19 @@
 static int
 sdhci_esdhc_imx_probe_dt(struct platform_device *pdev,
 			 struct sdhci_host *host,
-			 struct esdhc_platform_data *boarddata)
+			 struct pltfm_imx_data *imx_data)
 {
 	struct device_node *np = pdev->dev.of_node;
-
-	if (!np)
-		return -ENODEV;
-
-	if (of_get_property(np, "non-removable", NULL))
-		boarddata->cd_type = ESDHC_CD_PERMANENT;
-
-	if (of_get_property(np, "fsl,cd-controller", NULL))
-		boarddata->cd_type = ESDHC_CD_CONTROLLER;
+	struct esdhc_platform_data *boarddata = &imx_data->boarddata;
+	int ret;
 
 	if (of_get_property(np, "fsl,wp-controller", NULL))
 		boarddata->wp_type = ESDHC_WP_CONTROLLER;
 
-	boarddata->cd_gpio = of_get_named_gpio(np, "cd-gpios", 0);
-	if (gpio_is_valid(boarddata->cd_gpio))
-		boarddata->cd_type = ESDHC_CD_GPIO;
-
 	boarddata->wp_gpio = of_get_named_gpio(np, "wp-gpios", 0);
 	if (gpio_is_valid(boarddata->wp_gpio))
 		boarddata->wp_type = ESDHC_WP_GPIO;
 
-	of_property_read_u32(np, "bus-width", &boarddata->max_bus_width);
-
-	of_property_read_u32(np, "max-frequency", &boarddata->f_max);
-
 	if (of_find_property(np, "no-1-8-v", NULL))
 		boarddata->support_vsel = false;
 	else
@@ -916,29 +896,119 @@
 
 	mmc_of_parse_voltage(np, &host->ocr_mask);
 
+	/* sdr50 and sdr104 needs work on 1.8v signal voltage */
+	if ((boarddata->support_vsel) && esdhc_is_usdhc(imx_data) &&
+	    !IS_ERR(imx_data->pins_default)) {
+		imx_data->pins_100mhz = pinctrl_lookup_state(imx_data->pinctrl,
+						ESDHC_PINCTRL_STATE_100MHZ);
+		imx_data->pins_200mhz = pinctrl_lookup_state(imx_data->pinctrl,
+						ESDHC_PINCTRL_STATE_200MHZ);
+		if (IS_ERR(imx_data->pins_100mhz) ||
+				IS_ERR(imx_data->pins_200mhz)) {
+			dev_warn(mmc_dev(host->mmc),
+				"could not get ultra high speed state, work on normal mode\n");
+			/*
+			 * fall back to not support uhs by specify no 1.8v quirk
+			 */
+			host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
+		}
+	} else {
+		host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
+	}
+
 	/* call to generic mmc_of_parse to support additional capabilities */
-	return mmc_of_parse(host->mmc);
+	ret = mmc_of_parse(host->mmc);
+	if (ret)
+		return ret;
+
+	if (!IS_ERR_VALUE(mmc_gpio_get_cd(host->mmc)))
+		host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
+
+	return 0;
 }
 #else
 static inline int
 sdhci_esdhc_imx_probe_dt(struct platform_device *pdev,
 			 struct sdhci_host *host,
-			 struct esdhc_platform_data *boarddata)
+			 struct pltfm_imx_data *imx_data)
 {
 	return -ENODEV;
 }
 #endif
 
+static int sdhci_esdhc_imx_probe_nondt(struct platform_device *pdev,
+			 struct sdhci_host *host,
+			 struct pltfm_imx_data *imx_data)
+{
+	struct esdhc_platform_data *boarddata = &imx_data->boarddata;
+	int err;
+
+	if (!host->mmc->parent->platform_data) {
+		dev_err(mmc_dev(host->mmc), "no board data!\n");
+		return -EINVAL;
+	}
+
+	imx_data->boarddata = *((struct esdhc_platform_data *)
+				host->mmc->parent->platform_data);
+	/* write_protect */
+	if (boarddata->wp_type == ESDHC_WP_GPIO) {
+		err = mmc_gpio_request_ro(host->mmc, boarddata->wp_gpio);
+		if (err) {
+			dev_err(mmc_dev(host->mmc),
+				"failed to request write-protect gpio!\n");
+			return err;
+		}
+		host->mmc->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
+	}
+
+	/* card_detect */
+	switch (boarddata->cd_type) {
+	case ESDHC_CD_GPIO:
+		err = mmc_gpio_request_cd(host->mmc, boarddata->cd_gpio, 0);
+		if (err) {
+			dev_err(mmc_dev(host->mmc),
+				"failed to request card-detect gpio!\n");
+			return err;
+		}
+		/* fall through */
+
+	case ESDHC_CD_CONTROLLER:
+		/* we have a working card_detect back */
+		host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
+		break;
+
+	case ESDHC_CD_PERMANENT:
+		host->mmc->caps |= MMC_CAP_NONREMOVABLE;
+		break;
+
+	case ESDHC_CD_NONE:
+		break;
+	}
+
+	switch (boarddata->max_bus_width) {
+	case 8:
+		host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_4_BIT_DATA;
+		break;
+	case 4:
+		host->mmc->caps |= MMC_CAP_4_BIT_DATA;
+		break;
+	case 1:
+	default:
+		host->quirks |= SDHCI_QUIRK_FORCE_1_BIT_DATA;
+		break;
+	}
+
+	return 0;
+}
+
 static int sdhci_esdhc_imx_probe(struct platform_device *pdev)
 {
 	const struct of_device_id *of_id =
 			of_match_device(imx_esdhc_dt_ids, &pdev->dev);
 	struct sdhci_pltfm_host *pltfm_host;
 	struct sdhci_host *host;
-	struct esdhc_platform_data *boarddata;
 	int err;
 	struct pltfm_imx_data *imx_data;
-	bool dt = true;
 
 	host = sdhci_pltfm_init(pdev, &sdhci_esdhc_imx_pdata, 0);
 	if (IS_ERR(host))
@@ -1030,84 +1100,12 @@
 	if (imx_data->socdata->flags & ESDHC_FLAG_ERR004536)
 		host->quirks |= SDHCI_QUIRK_BROKEN_ADMA;
 
-	boarddata = &imx_data->boarddata;
-	if (sdhci_esdhc_imx_probe_dt(pdev, host, boarddata) < 0) {
-		if (!host->mmc->parent->platform_data) {
-			dev_err(mmc_dev(host->mmc), "no board data!\n");
-			err = -EINVAL;
-			goto disable_clk;
-		}
-		imx_data->boarddata = *((struct esdhc_platform_data *)
-					host->mmc->parent->platform_data);
-		dt = false;
-	}
-	/* write_protect */
-	if (boarddata->wp_type == ESDHC_WP_GPIO && !dt) {
-		err = mmc_gpio_request_ro(host->mmc, boarddata->wp_gpio);
-		if (err) {
-			dev_err(mmc_dev(host->mmc),
-				"failed to request write-protect gpio!\n");
-			goto disable_clk;
-		}
-		host->mmc->caps2 |= MMC_CAP2_RO_ACTIVE_HIGH;
-	}
-
-	/* card_detect */
-	switch (boarddata->cd_type) {
-	case ESDHC_CD_GPIO:
-		if (dt)
-			break;
-		err = mmc_gpio_request_cd(host->mmc, boarddata->cd_gpio, 0);
-		if (err) {
-			dev_err(mmc_dev(host->mmc),
-				"failed to request card-detect gpio!\n");
-			goto disable_clk;
-		}
-		/* fall through */
-
-	case ESDHC_CD_CONTROLLER:
-		/* we have a working card_detect back */
-		host->quirks &= ~SDHCI_QUIRK_BROKEN_CARD_DETECTION;
-		break;
-
-	case ESDHC_CD_PERMANENT:
-		host->mmc->caps |= MMC_CAP_NONREMOVABLE;
-		break;
-
-	case ESDHC_CD_NONE:
-		break;
-	}
-
-	switch (boarddata->max_bus_width) {
-	case 8:
-		host->mmc->caps |= MMC_CAP_8_BIT_DATA | MMC_CAP_4_BIT_DATA;
-		break;
-	case 4:
-		host->mmc->caps |= MMC_CAP_4_BIT_DATA;
-		break;
-	case 1:
-	default:
-		host->quirks |= SDHCI_QUIRK_FORCE_1_BIT_DATA;
-		break;
-	}
-
-	/* sdr50 and sdr104 needs work on 1.8v signal voltage */
-	if ((boarddata->support_vsel) && esdhc_is_usdhc(imx_data) &&
-	    !IS_ERR(imx_data->pins_default)) {
-		imx_data->pins_100mhz = pinctrl_lookup_state(imx_data->pinctrl,
-						ESDHC_PINCTRL_STATE_100MHZ);
-		imx_data->pins_200mhz = pinctrl_lookup_state(imx_data->pinctrl,
-						ESDHC_PINCTRL_STATE_200MHZ);
-		if (IS_ERR(imx_data->pins_100mhz) ||
-				IS_ERR(imx_data->pins_200mhz)) {
-			dev_warn(mmc_dev(host->mmc),
-				"could not get ultra high speed state, work on normal mode\n");
-			/* fall back to not support uhs by specify no 1.8v quirk */
-			host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
-		}
-	} else {
-		host->quirks2 |= SDHCI_QUIRK2_NO_1_8_V;
-	}
+	if (of_id)
+		err = sdhci_esdhc_imx_probe_dt(pdev, host, imx_data);
+	else
+		err = sdhci_esdhc_imx_probe_nondt(pdev, host, imx_data);
+	if (err)
+		goto disable_clk;
 
 	err = sdhci_add_host(host);
 	if (err)
diff --git a/drivers/mmc/host/sdhci-esdhc.h b/drivers/mmc/host/sdhci-esdhc.h
index 3497cfa..a870c42 100644
--- a/drivers/mmc/host/sdhci-esdhc.h
+++ b/drivers/mmc/host/sdhci-esdhc.h
@@ -45,6 +45,6 @@
 #define ESDHC_DMA_SYSCTL	0x40c
 #define ESDHC_DMA_SNOOP		0x00000040
 
-#define ESDHC_HOST_CONTROL_RES	0x05
+#define ESDHC_HOST_CONTROL_RES	0x01
 
 #endif /* _DRIVERS_MMC_SDHCI_ESDHC_H */
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index 9cd5fc6..946d37f 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -411,6 +411,7 @@
 			goto err_of_parse;
 		sdhci_get_of_property(pdev);
 		pdata = pxav3_get_mmc_pdata(dev);
+		pdev->dev.platform_data = pdata;
 	} else if (pdata) {
 		/* on-chip device */
 		if (pdata->flags & PXA_FLAG_CARD_PERMANENT)
diff --git a/drivers/mmc/host/sdhci-spear.c b/drivers/mmc/host/sdhci-spear.c
index df08834..255a896 100644
--- a/drivers/mmc/host/sdhci-spear.c
+++ b/drivers/mmc/host/sdhci-spear.c
@@ -4,7 +4,7 @@
  * Support of SDHCI platform devices for spear soc family
  *
  * Copyright (C) 2010 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * Inspired by sdhci-pltfm.c
  *
@@ -211,5 +211,5 @@
 module_platform_driver(sdhci_driver);
 
 MODULE_DESCRIPTION("SPEAr Secure Digital Host Controller Interface driver");
-MODULE_AUTHOR("Viresh Kumar <viresh.linux@gmail.com>");
+MODULE_AUTHOR("Viresh Kumar <vireshk@kernel.org>");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index bc14452..1dbe932 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -2866,6 +2866,7 @@
 	u32 max_current_caps;
 	unsigned int ocr_avail;
 	unsigned int override_timeout_clk;
+	u32 max_clk;
 	int ret;
 
 	WARN_ON(host == NULL);
@@ -2978,8 +2979,11 @@
 						      GFP_KERNEL);
 		host->align_buffer = kmalloc(host->align_buffer_sz, GFP_KERNEL);
 		if (!host->adma_table || !host->align_buffer) {
-			dma_free_coherent(mmc_dev(mmc), host->adma_table_sz,
-					  host->adma_table, host->adma_addr);
+			if (host->adma_table)
+				dma_free_coherent(mmc_dev(mmc),
+						  host->adma_table_sz,
+						  host->adma_table,
+						  host->adma_addr);
 			kfree(host->align_buffer);
 			pr_warn("%s: Unable to allocate ADMA buffers - falling back to standard DMA\n",
 				mmc_hostname(mmc));
@@ -3047,18 +3051,22 @@
 	 * Set host parameters.
 	 */
 	mmc->ops = &sdhci_ops;
-	mmc->f_max = host->max_clk;
+	max_clk = host->max_clk;
+
 	if (host->ops->get_min_clock)
 		mmc->f_min = host->ops->get_min_clock(host);
 	else if (host->version >= SDHCI_SPEC_300) {
 		if (host->clk_mul) {
 			mmc->f_min = (host->max_clk * host->clk_mul) / 1024;
-			mmc->f_max = host->max_clk * host->clk_mul;
+			max_clk = host->max_clk * host->clk_mul;
 		} else
 			mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_300;
 	} else
 		mmc->f_min = host->max_clk / SDHCI_MAX_DIV_SPEC_200;
 
+	if (!mmc->f_max || (mmc->f_max && (mmc->f_max > max_clk)))
+		mmc->f_max = max_clk;
+
 	if (!(host->quirks & SDHCI_QUIRK_DATA_TIMEOUT_USES_SDCLK)) {
 		host->timeout_clk = (caps[0] & SDHCI_TIMEOUT_CLK_MASK) >>
 					SDHCI_TIMEOUT_CLK_SHIFT;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 19eb990..a98dd4f 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -625,6 +625,23 @@
 	call_netdevice_notifiers(NETDEV_CHANGEADDR, bond_dev);
 }
 
+static struct slave *bond_get_old_active(struct bonding *bond,
+					 struct slave *new_active)
+{
+	struct slave *slave;
+	struct list_head *iter;
+
+	bond_for_each_slave(bond, slave, iter) {
+		if (slave == new_active)
+			continue;
+
+		if (ether_addr_equal(bond->dev->dev_addr, slave->dev->dev_addr))
+			return slave;
+	}
+
+	return NULL;
+}
+
 /* bond_do_fail_over_mac
  *
  * Perform special MAC address swapping for fail_over_mac settings
@@ -652,6 +669,9 @@
 		if (!new_active)
 			return;
 
+		if (!old_active)
+			old_active = bond_get_old_active(bond, new_active);
+
 		if (old_active) {
 			ether_addr_copy(tmp_mac, new_active->dev->dev_addr);
 			ether_addr_copy(saddr.sa_data,
@@ -689,40 +709,57 @@
 
 }
 
-static bool bond_should_change_active(struct bonding *bond)
+static struct slave *bond_choose_primary_or_current(struct bonding *bond)
 {
 	struct slave *prim = rtnl_dereference(bond->primary_slave);
 	struct slave *curr = rtnl_dereference(bond->curr_active_slave);
 
-	if (!prim || !curr || curr->link != BOND_LINK_UP)
-		return true;
+	if (!prim || prim->link != BOND_LINK_UP) {
+		if (!curr || curr->link != BOND_LINK_UP)
+			return NULL;
+		return curr;
+	}
+
 	if (bond->force_primary) {
 		bond->force_primary = false;
-		return true;
+		return prim;
 	}
-	if (bond->params.primary_reselect == BOND_PRI_RESELECT_BETTER &&
-	    (prim->speed < curr->speed ||
-	     (prim->speed == curr->speed && prim->duplex <= curr->duplex)))
-		return false;
-	if (bond->params.primary_reselect == BOND_PRI_RESELECT_FAILURE)
-		return false;
-	return true;
+
+	if (!curr || curr->link != BOND_LINK_UP)
+		return prim;
+
+	/* At this point, prim and curr are both up */
+	switch (bond->params.primary_reselect) {
+	case BOND_PRI_RESELECT_ALWAYS:
+		return prim;
+	case BOND_PRI_RESELECT_BETTER:
+		if (prim->speed < curr->speed)
+			return curr;
+		if (prim->speed == curr->speed && prim->duplex <= curr->duplex)
+			return curr;
+		return prim;
+	case BOND_PRI_RESELECT_FAILURE:
+		return curr;
+	default:
+		netdev_err(bond->dev, "impossible primary_reselect %d\n",
+			   bond->params.primary_reselect);
+		return curr;
+	}
 }
 
 /**
- * find_best_interface - select the best available slave to be the active one
+ * bond_find_best_slave - select the best available slave to be the active one
  * @bond: our bonding struct
  */
 static struct slave *bond_find_best_slave(struct bonding *bond)
 {
-	struct slave *slave, *bestslave = NULL, *primary;
+	struct slave *slave, *bestslave = NULL;
 	struct list_head *iter;
 	int mintime = bond->params.updelay;
 
-	primary = rtnl_dereference(bond->primary_slave);
-	if (primary && primary->link == BOND_LINK_UP &&
-	    bond_should_change_active(bond))
-		return primary;
+	slave = bond_choose_primary_or_current(bond);
+	if (slave)
+		return slave;
 
 	bond_for_each_slave(bond, slave, iter) {
 		if (slave->link == BOND_LINK_UP)
@@ -749,6 +786,7 @@
 		   slave ? slave->dev->name : "NULL");
 
 	if (!slave || !bond->send_peer_notif ||
+	    !netif_carrier_ok(bond->dev) ||
 	    test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state))
 		return false;
 
@@ -1708,9 +1746,16 @@
 
 err_undo_flags:
 	/* Enslave of first slave has failed and we need to fix master's mac */
-	if (!bond_has_slaves(bond) &&
-	    ether_addr_equal_64bits(bond_dev->dev_addr, slave_dev->dev_addr))
-		eth_hw_addr_random(bond_dev);
+	if (!bond_has_slaves(bond)) {
+		if (ether_addr_equal_64bits(bond_dev->dev_addr,
+					    slave_dev->dev_addr))
+			eth_hw_addr_random(bond_dev);
+		if (bond_dev->type != ARPHRD_ETHER) {
+			ether_setup(bond_dev);
+			bond_dev->flags |= IFF_MASTER;
+			bond_dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+		}
+	}
 
 	return res;
 }
@@ -1899,6 +1944,7 @@
 		bond_dev->priv_flags |= IFF_DISABLE_NETPOLL;
 		netdev_info(bond_dev, "Destroying bond %s\n",
 			    bond_dev->name);
+		bond_remove_proc_entry(bond);
 		unregister_netdevice(bond_dev);
 	}
 	return ret;
diff --git a/drivers/net/can/at91_can.c b/drivers/net/can/at91_can.c
index f4e40aa..945c095 100644
--- a/drivers/net/can/at91_can.c
+++ b/drivers/net/can/at91_can.c
@@ -577,10 +577,10 @@
 
 	cf->can_id |= CAN_ERR_CRTL;
 	cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
-	netif_receive_skb(skb);
 
 	stats->rx_packets++;
 	stats->rx_bytes += cf->can_dlc;
+	netif_receive_skb(skb);
 }
 
 /**
@@ -642,10 +642,10 @@
 	}
 
 	at91_read_mb(dev, mb, cf);
-	netif_receive_skb(skb);
 
 	stats->rx_packets++;
 	stats->rx_bytes += cf->can_dlc;
+	netif_receive_skb(skb);
 
 	can_led_event(dev, CAN_LED_EVENT_RX);
 }
@@ -802,10 +802,10 @@
 		return 0;
 
 	at91_poll_err_frame(dev, cf, reg_sr);
-	netif_receive_skb(skb);
 
 	dev->stats.rx_packets++;
 	dev->stats.rx_bytes += cf->can_dlc;
+	netif_receive_skb(skb);
 
 	return 1;
 }
@@ -1067,10 +1067,10 @@
 		return;
 
 	at91_irq_err_state(dev, cf, new_state);
-	netif_rx(skb);
 
 	dev->stats.rx_packets++;
 	dev->stats.rx_bytes += cf->can_dlc;
+	netif_rx(skb);
 
 	priv->can.state = new_state;
 }
diff --git a/drivers/net/can/bfin_can.c b/drivers/net/can/bfin_can.c
index 27ad312..57dadd5 100644
--- a/drivers/net/can/bfin_can.c
+++ b/drivers/net/can/bfin_can.c
@@ -424,10 +424,9 @@
 		cf->data[6 - i] = (6 - i) < cf->can_dlc ? (val >> 8) : 0;
 	}
 
-	netif_rx(skb);
-
 	stats->rx_packets++;
 	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
 }
 
 static int bfin_can_err(struct net_device *dev, u16 isrc, u16 status)
@@ -508,10 +507,9 @@
 
 	priv->can.state = state;
 
-	netif_rx(skb);
-
 	stats->rx_packets++;
 	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
 
 	return 0;
 }
diff --git a/drivers/net/can/c_can/c_can.c b/drivers/net/can/c_can/c_can.c
index 041525d..5d214d1 100644
--- a/drivers/net/can/c_can/c_can.c
+++ b/drivers/net/can/c_can/c_can.c
@@ -592,6 +592,7 @@
 {
 	struct c_can_priv *priv = netdev_priv(dev);
 	int err;
+	struct pinctrl *p;
 
 	/* basic c_can configuration */
 	err = c_can_chip_config(dev);
@@ -604,8 +605,13 @@
 
 	priv->can.state = CAN_STATE_ERROR_ACTIVE;
 
-	/* activate pins */
-	pinctrl_pm_select_default_state(dev->dev.parent);
+	/* Attempt to use "active" if available else use "default" */
+	p = pinctrl_get_select(priv->device, "active");
+	if (!IS_ERR(p))
+		pinctrl_put(p);
+	else
+		pinctrl_pm_select_default_state(priv->device);
+
 	return 0;
 }
 
diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c
index c11d449..70a8cbb 100644
--- a/drivers/net/can/cc770/cc770.c
+++ b/drivers/net/can/cc770/cc770.c
@@ -504,10 +504,10 @@
 		for (i = 0; i < cf->can_dlc; i++)
 			cf->data[i] = cc770_read_reg(priv, msgobj[mo].data[i]);
 	}
-	netif_rx(skb);
 
 	stats->rx_packets++;
 	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
 }
 
 static int cc770_err(struct net_device *dev, u8 status)
@@ -584,10 +584,10 @@
 		}
 	}
 
-	netif_rx(skb);
 
 	stats->rx_packets++;
 	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
 
 	return 0;
 }
diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index e9b1810..aede704 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -440,9 +440,6 @@
 		struct can_frame *cf = (struct can_frame *)skb->data;
 		u8 dlc = cf->can_dlc;
 
-		if (!(skb->tstamp.tv64))
-			__net_timestamp(skb);
-
 		netif_rx(priv->echo_skb[idx]);
 		priv->echo_skb[idx] = NULL;
 
@@ -578,7 +575,6 @@
 	if (unlikely(!skb))
 		return NULL;
 
-	__net_timestamp(skb);
 	skb->protocol = htons(ETH_P_CAN);
 	skb->pkt_type = PACKET_BROADCAST;
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -589,6 +585,7 @@
 
 	can_skb_reserve(skb);
 	can_skb_prv(skb)->ifindex = dev->ifindex;
+	can_skb_prv(skb)->skbcnt = 0;
 
 	*cf = (struct can_frame *)skb_put(skb, sizeof(struct can_frame));
 	memset(*cf, 0, sizeof(struct can_frame));
@@ -607,7 +604,6 @@
 	if (unlikely(!skb))
 		return NULL;
 
-	__net_timestamp(skb);
 	skb->protocol = htons(ETH_P_CANFD);
 	skb->pkt_type = PACKET_BROADCAST;
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -618,6 +614,7 @@
 
 	can_skb_reserve(skb);
 	can_skb_prv(skb)->ifindex = dev->ifindex;
+	can_skb_prv(skb)->skbcnt = 0;
 
 	*cfd = (struct canfd_frame *)skb_put(skb, sizeof(struct canfd_frame));
 	memset(*cfd, 0, sizeof(struct canfd_frame));
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index 6201c5a..b1e8d72 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -577,10 +577,10 @@
 		return 0;
 
 	do_bus_err(dev, cf, reg_esr);
-	netif_receive_skb(skb);
 
 	dev->stats.rx_packets++;
 	dev->stats.rx_bytes += cf->can_dlc;
+	netif_receive_skb(skb);
 
 	return 1;
 }
@@ -622,10 +622,9 @@
 	if (unlikely(new_state == CAN_STATE_BUS_OFF))
 		can_bus_off(dev);
 
-	netif_receive_skb(skb);
-
 	dev->stats.rx_packets++;
 	dev->stats.rx_bytes += cf->can_dlc;
+	netif_receive_skb(skb);
 
 	return 1;
 }
@@ -670,10 +669,10 @@
 	}
 
 	flexcan_read_fifo(dev, cf);
-	netif_receive_skb(skb);
 
 	stats->rx_packets++;
 	stats->rx_bytes += cf->can_dlc;
+	netif_receive_skb(skb);
 
 	can_led_event(dev, CAN_LED_EVENT_RX);
 
diff --git a/drivers/net/can/grcan.c b/drivers/net/can/grcan.c
index e3d7e22..db9538d 100644
--- a/drivers/net/can/grcan.c
+++ b/drivers/net/can/grcan.c
@@ -1216,11 +1216,12 @@
 				cf->data[i] = (u8)(slot[j] >> shift);
 			}
 		}
-		netif_receive_skb(skb);
 
 		/* Update statistics and read pointer */
 		stats->rx_packets++;
 		stats->rx_bytes += cf->can_dlc;
+		netif_receive_skb(skb);
+
 		rd = grcan_ring_add(rd, GRCAN_MSG_SIZE, dma->rx.size);
 	}
 
diff --git a/drivers/net/can/rcar_can.c b/drivers/net/can/rcar_can.c
index 7deb80d..7bd5419 100644
--- a/drivers/net/can/rcar_can.c
+++ b/drivers/net/can/rcar_can.c
@@ -508,7 +508,8 @@
 
 	err = clk_prepare_enable(priv->clk);
 	if (err) {
-		netdev_err(ndev, "failed to enable periperal clock, error %d\n",
+		netdev_err(ndev,
+			   "failed to enable peripheral clock, error %d\n",
 			   err);
 		goto out;
 	}
@@ -526,7 +527,8 @@
 	napi_enable(&priv->napi);
 	err = request_irq(ndev->irq, rcar_can_interrupt, 0, ndev->name, ndev);
 	if (err) {
-		netdev_err(ndev, "error requesting interrupt %x\n", ndev->irq);
+		netdev_err(ndev, "request_irq(%d) failed, error %d\n",
+			   ndev->irq, err);
 		goto out_close;
 	}
 	can_led_event(ndev, CAN_LED_EVENT_OPEN);
@@ -758,8 +760,9 @@
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (!irq) {
+	if (irq < 0) {
 		dev_err(&pdev->dev, "No IRQ resource\n");
+		err = irq;
 		goto fail;
 	}
 
@@ -782,7 +785,8 @@
 	priv->clk = devm_clk_get(&pdev->dev, "clkp1");
 	if (IS_ERR(priv->clk)) {
 		err = PTR_ERR(priv->clk);
-		dev_err(&pdev->dev, "cannot get peripheral clock: %d\n", err);
+		dev_err(&pdev->dev, "cannot get peripheral clock, error %d\n",
+			err);
 		goto fail_clk;
 	}
 
@@ -794,7 +798,7 @@
 	priv->can_clk = devm_clk_get(&pdev->dev, clock_names[clock_select]);
 	if (IS_ERR(priv->can_clk)) {
 		err = PTR_ERR(priv->can_clk);
-		dev_err(&pdev->dev, "cannot get CAN clock: %d\n", err);
+		dev_err(&pdev->dev, "cannot get CAN clock, error %d\n", err);
 		goto fail_clk;
 	}
 
@@ -823,7 +827,7 @@
 
 	devm_can_led_init(ndev);
 
-	dev_info(&pdev->dev, "device registered (reg_base=%p, irq=%u)\n",
+	dev_info(&pdev->dev, "device registered (regs @ %p, IRQ%d)\n",
 		 priv->regs, ndev->irq);
 
 	return 0;
diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c
index 32bd7f4..7b92e91 100644
--- a/drivers/net/can/sja1000/sja1000.c
+++ b/drivers/net/can/sja1000/sja1000.c
@@ -377,10 +377,9 @@
 	/* release receive buffer */
 	sja1000_write_cmdreg(priv, CMD_RRB);
 
-	netif_rx(skb);
-
 	stats->rx_packets++;
 	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
 
 	can_led_event(dev, CAN_LED_EVENT_RX);
 }
@@ -484,10 +483,9 @@
 			can_bus_off(dev);
 	}
 
-	netif_rx(skb);
-
 	stats->rx_packets++;
 	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
 
 	return 0;
 }
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index f64f529..9a3f15c 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -207,7 +207,6 @@
 	if (!skb)
 		return;
 
-	__net_timestamp(skb);
 	skb->dev = sl->dev;
 	skb->protocol = htons(ETH_P_CAN);
 	skb->pkt_type = PACKET_BROADCAST;
@@ -215,13 +214,14 @@
 
 	can_skb_reserve(skb);
 	can_skb_prv(skb)->ifindex = sl->dev->ifindex;
+	can_skb_prv(skb)->skbcnt = 0;
 
 	memcpy(skb_put(skb, sizeof(struct can_frame)),
 	       &cf, sizeof(struct can_frame));
-	netif_rx_ni(skb);
 
 	sl->dev->stats.rx_packets++;
 	sl->dev->stats.rx_bytes += cf.can_dlc;
+	netif_rx_ni(skb);
 }
 
 /* parse tty input stream */
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index c1a95a3..b7e83c2 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -1086,8 +1086,8 @@
 	if (ret)
 		goto out_clk;
 
-	priv->power = devm_regulator_get(&spi->dev, "vdd");
-	priv->transceiver = devm_regulator_get(&spi->dev, "xceiver");
+	priv->power = devm_regulator_get_optional(&spi->dev, "vdd");
+	priv->transceiver = devm_regulator_get_optional(&spi->dev, "xceiver");
 	if ((PTR_ERR(priv->power) == -EPROBE_DEFER) ||
 	    (PTR_ERR(priv->transceiver) == -EPROBE_DEFER)) {
 		ret = -EPROBE_DEFER;
@@ -1222,17 +1222,16 @@
 	struct spi_device *spi = to_spi_device(dev);
 	struct mcp251x_priv *priv = spi_get_drvdata(spi);
 
-	if (priv->after_suspend & AFTER_SUSPEND_POWER) {
+	if (priv->after_suspend & AFTER_SUSPEND_POWER)
 		mcp251x_power_enable(priv->power, 1);
+
+	if (priv->after_suspend & AFTER_SUSPEND_UP) {
+		mcp251x_power_enable(priv->transceiver, 1);
 		queue_work(priv->wq, &priv->restart_work);
 	} else {
-		if (priv->after_suspend & AFTER_SUSPEND_UP) {
-			mcp251x_power_enable(priv->transceiver, 1);
-			queue_work(priv->wq, &priv->restart_work);
-		} else {
-			priv->after_suspend = 0;
-		}
+		priv->after_suspend = 0;
 	}
+
 	priv->force_quit = 0;
 	enable_irq(spi->irq);
 	return 0;
diff --git a/drivers/net/can/ti_hecc.c b/drivers/net/can/ti_hecc.c
index e95a9e1..cf345cb 100644
--- a/drivers/net/can/ti_hecc.c
+++ b/drivers/net/can/ti_hecc.c
@@ -747,9 +747,9 @@
 		}
 	}
 
-	netif_rx(skb);
 	stats->rx_packets++;
 	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
 
 	return 0;
 }
diff --git a/drivers/net/can/usb/ems_usb.c b/drivers/net/can/usb/ems_usb.c
index 866bac0..2d39038 100644
--- a/drivers/net/can/usb/ems_usb.c
+++ b/drivers/net/can/usb/ems_usb.c
@@ -324,10 +324,9 @@
 			cf->data[i] = msg->msg.can_msg.msg[i];
 	}
 
-	netif_rx(skb);
-
 	stats->rx_packets++;
 	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
 }
 
 static void ems_usb_rx_err(struct ems_usb *dev, struct ems_cpc_msg *msg)
@@ -400,10 +399,9 @@
 		stats->rx_errors++;
 	}
 
-	netif_rx(skb);
-
 	stats->rx_packets++;
 	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
 }
 
 /*
diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c
index 411c1af..0e5a449 100644
--- a/drivers/net/can/usb/esd_usb2.c
+++ b/drivers/net/can/usb/esd_usb2.c
@@ -301,13 +301,12 @@
 			cf->data[7] = rxerr;
 		}
 
-		netif_rx(skb);
-
 		priv->bec.txerr = txerr;
 		priv->bec.rxerr = rxerr;
 
 		stats->rx_packets++;
 		stats->rx_bytes += cf->can_dlc;
+		netif_rx(skb);
 	}
 }
 
@@ -347,10 +346,9 @@
 				cf->data[i] = msg->msg.rx.data[i];
 		}
 
-		netif_rx(skb);
-
 		stats->rx_packets++;
 		stats->rx_bytes += cf->can_dlc;
+		netif_rx(skb);
 	}
 
 	return;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index 72427f2..6b94007 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -526,9 +526,9 @@
 		hwts->hwtstamp = timeval_to_ktime(tv);
 	}
 
-	netif_rx(skb);
 	mc->netdev->stats.rx_packets++;
 	mc->netdev->stats.rx_bytes += cf->can_dlc;
+	netif_rx(skb);
 
 	return 0;
 }
@@ -659,12 +659,11 @@
 	hwts = skb_hwtstamps(skb);
 	hwts->hwtstamp = timeval_to_ktime(tv);
 
-	/* push the skb */
-	netif_rx(skb);
-
 	/* update statistics */
 	mc->netdev->stats.rx_packets++;
 	mc->netdev->stats.rx_bytes += cf->can_dlc;
+	/* push the skb */
+	netif_rx(skb);
 
 	return 0;
 
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
index dec5171..7d61b32 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
@@ -553,9 +553,9 @@
 	hwts = skb_hwtstamps(skb);
 	hwts->hwtstamp = timeval_to_ktime(tv);
 
-	netif_rx(skb);
 	netdev->stats.rx_packets++;
 	netdev->stats.rx_bytes += can_frame->can_dlc;
+	netif_rx(skb);
 
 	return 0;
 }
@@ -670,9 +670,9 @@
 	peak_usb_get_ts_tv(&usb_if->time_ref, le32_to_cpu(er->ts32), &tv);
 	hwts = skb_hwtstamps(skb);
 	hwts->hwtstamp = timeval_to_ktime(tv);
-	netif_rx(skb);
 	netdev->stats.rx_packets++;
 	netdev->stats.rx_bytes += can_frame->can_dlc;
+	netif_rx(skb);
 
 	return 0;
 }
diff --git a/drivers/net/can/usb/usb_8dev.c b/drivers/net/can/usb/usb_8dev.c
index dd52c7a..de95b1c 100644
--- a/drivers/net/can/usb/usb_8dev.c
+++ b/drivers/net/can/usb/usb_8dev.c
@@ -461,10 +461,9 @@
 	priv->bec.txerr = txerr;
 	priv->bec.rxerr = rxerr;
 
-	netif_rx(skb);
-
 	stats->rx_packets++;
 	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
 }
 
 /* Read data and status frames */
@@ -494,10 +493,9 @@
 		else
 			memcpy(cf->data, msg->data, cf->can_dlc);
 
-		netif_rx(skb);
-
 		stats->rx_packets++;
 		stats->rx_bytes += cf->can_dlc;
+		netif_rx(skb);
 
 		can_led_event(priv->netdev, CAN_LED_EVENT_RX);
 	} else {
diff --git a/drivers/net/can/vcan.c b/drivers/net/can/vcan.c
index 0ce868d..674f367 100644
--- a/drivers/net/can/vcan.c
+++ b/drivers/net/can/vcan.c
@@ -78,9 +78,6 @@
 	skb->dev       = dev;
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
 
-	if (!(skb->tstamp.tv64))
-		__net_timestamp(skb);
-
 	netif_rx_ni(skb);
 }
 
diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 972982f..079897b 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -696,9 +696,20 @@
 	}
 
 	/* Include the pseudo-PHY address and the broadcast PHY address to
-	 * divert reads towards our workaround
+	 * divert reads towards our workaround. This is only required for
+	 * 7445D0, since 7445E0 disconnects the internal switch pseudo-PHY such
+	 * that we can use the regular SWITCH_MDIO master controller instead.
+	 *
+	 * By default, DSA initializes ds->phys_mii_mask to ds->phys_port_mask
+	 * to have a 1:1 mapping between Port address and PHY address in order
+	 * to utilize the slave_mii_bus instance to read from Port PHYs. This is
+	 * not what we want here, so we initialize phys_mii_mask 0 to always
+	 * utilize the "master" MDIO bus backed by the "mdio-unimac" driver.
 	 */
-	ds->phys_mii_mask |= ((1 << BRCM_PSEUDO_PHY_ADDR) | (1 << 0));
+	if (of_machine_is_compatible("brcm,bcm7445d0"))
+		ds->phys_mii_mask |= ((1 << BRCM_PSEUDO_PHY_ADDR) | (1 << 0));
+	else
+		ds->phys_mii_mask = 0;
 
 	rev = reg_readl(priv, REG_SWITCH_REVISION);
 	priv->hw_params.top_rev = (rev >> SWITCH_TOP_REV_SHIFT) &
diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index fd8547c..5613424 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -1163,7 +1163,7 @@
 
 	newfid = __ffs(ps->fid_mask);
 	ps->fid[port] = newfid;
-	ps->fid_mask &= (1 << newfid);
+	ps->fid_mask &= ~(1 << newfid);
 	ps->bridge_mask[fid] &= ~(1 << port);
 	ps->bridge_mask[newfid] = 1 << port;
 
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 41095eb..753887d 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -1763,16 +1763,9 @@
 			vp->rx_ring[i].addr = cpu_to_le32(pci_map_single(VORTEX_PCI(vp), skb->data, PKT_BUF_SZ, PCI_DMA_FROMDEVICE));
 		}
 		if (i != RX_RING_SIZE) {
-			int j;
 			pr_emerg("%s: no memory for rx ring\n", dev->name);
-			for (j = 0; j < i; j++) {
-				if (vp->rx_skbuff[j]) {
-					dev_kfree_skb(vp->rx_skbuff[j]);
-					vp->rx_skbuff[j] = NULL;
-				}
-			}
 			retval = -ENOMEM;
-			goto err_free_irq;
+			goto err_free_skb;
 		}
 		/* Wrap the ring. */
 		vp->rx_ring[i-1].next = cpu_to_le32(vp->rx_ring_dma);
@@ -1782,7 +1775,13 @@
 	if (!retval)
 		goto out;
 
-err_free_irq:
+err_free_skb:
+	for (i = 0; i < RX_RING_SIZE; i++) {
+		if (vp->rx_skbuff[i]) {
+			dev_kfree_skb(vp->rx_skbuff[i]);
+			vp->rx_skbuff[i] = NULL;
+		}
+	}
 	free_irq(dev->irq, dev);
 err:
 	if (vortex_debug > 1)
@@ -2382,6 +2381,7 @@
 	void __iomem *ioaddr;
 	int status;
 	int work_done = max_interrupt_work;
+	int handled = 0;
 
 	ioaddr = vp->ioaddr;
 
@@ -2400,6 +2400,7 @@
 
 	if ((status & IntLatch) == 0)
 		goto handler_exit;		/* No interrupt: shared IRQs can cause this */
+	handled = 1;
 
 	if (status == 0xffff) {		/* h/w no longer present (hotplug)? */
 		if (vortex_debug > 1)
@@ -2501,7 +2502,7 @@
 handler_exit:
 	vp->handling_irq = 0;
 	spin_unlock(&vp->lock);
-	return IRQ_HANDLED;
+	return IRQ_RETVAL(handled);
 }
 
 static int vortex_rx(struct net_device *dev)
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
index 661cdaa..b3bc87f 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -303,7 +303,8 @@
 	get_page(pa->pages);
 	bd->pa = *pa;
 
-	bd->dma = pa->pages_dma + pa->pages_offset;
+	bd->dma_base = pa->pages_dma;
+	bd->dma_off = pa->pages_offset;
 	bd->dma_len = len;
 
 	pa->pages_offset += len;
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index 506e832..a4473d8 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -1110,6 +1110,7 @@
 	unsigned int rx_usecs = pdata->rx_usecs;
 	unsigned int rx_frames = pdata->rx_frames;
 	unsigned int inte;
+	dma_addr_t hdr_dma, buf_dma;
 
 	if (!rx_usecs && !rx_frames) {
 		/* No coalescing, interrupt for every descriptor */
@@ -1129,10 +1130,12 @@
 	 *   Set buffer 2 (hi) address to buffer dma address (hi) and
 	 *     set control bits OWN and INTE
 	 */
-	rdesc->desc0 = cpu_to_le32(lower_32_bits(rdata->rx.hdr.dma));
-	rdesc->desc1 = cpu_to_le32(upper_32_bits(rdata->rx.hdr.dma));
-	rdesc->desc2 = cpu_to_le32(lower_32_bits(rdata->rx.buf.dma));
-	rdesc->desc3 = cpu_to_le32(upper_32_bits(rdata->rx.buf.dma));
+	hdr_dma = rdata->rx.hdr.dma_base + rdata->rx.hdr.dma_off;
+	buf_dma = rdata->rx.buf.dma_base + rdata->rx.buf.dma_off;
+	rdesc->desc0 = cpu_to_le32(lower_32_bits(hdr_dma));
+	rdesc->desc1 = cpu_to_le32(upper_32_bits(hdr_dma));
+	rdesc->desc2 = cpu_to_le32(lower_32_bits(buf_dma));
+	rdesc->desc3 = cpu_to_le32(upper_32_bits(buf_dma));
 
 	XGMAC_SET_BITS_LE(rdesc->desc3, RX_NORMAL_DESC3, INTE, inte);
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 1e9c28d..aae9d5e 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -1765,8 +1765,9 @@
 	/* Start with the header buffer which may contain just the header
 	 * or the header plus data
 	 */
-	dma_sync_single_for_cpu(pdata->dev, rdata->rx.hdr.dma,
-				rdata->rx.hdr.dma_len, DMA_FROM_DEVICE);
+	dma_sync_single_range_for_cpu(pdata->dev, rdata->rx.hdr.dma_base,
+				      rdata->rx.hdr.dma_off,
+				      rdata->rx.hdr.dma_len, DMA_FROM_DEVICE);
 
 	packet = page_address(rdata->rx.hdr.pa.pages) +
 		 rdata->rx.hdr.pa.pages_offset;
@@ -1778,8 +1779,11 @@
 	len -= copy_len;
 	if (len) {
 		/* Add the remaining data as a frag */
-		dma_sync_single_for_cpu(pdata->dev, rdata->rx.buf.dma,
-					rdata->rx.buf.dma_len, DMA_FROM_DEVICE);
+		dma_sync_single_range_for_cpu(pdata->dev,
+					      rdata->rx.buf.dma_base,
+					      rdata->rx.buf.dma_off,
+					      rdata->rx.buf.dma_len,
+					      DMA_FROM_DEVICE);
 
 		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
 				rdata->rx.buf.pa.pages,
@@ -1945,8 +1949,9 @@
 				if (!skb)
 					error = 1;
 			} else if (rdesc_len) {
-				dma_sync_single_for_cpu(pdata->dev,
-							rdata->rx.buf.dma,
+				dma_sync_single_range_for_cpu(pdata->dev,
+							rdata->rx.buf.dma_base,
+							rdata->rx.buf.dma_off,
 							rdata->rx.buf.dma_len,
 							DMA_FROM_DEVICE);
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe.h b/drivers/net/ethernet/amd/xgbe/xgbe.h
index 63d72a1..717ce21 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe.h
+++ b/drivers/net/ethernet/amd/xgbe/xgbe.h
@@ -337,7 +337,8 @@
 	struct xgbe_page_alloc pa;
 	struct xgbe_page_alloc pa_unmap;
 
-	dma_addr_t dma;
+	dma_addr_t dma_base;
+	unsigned long dma_off;
 	unsigned int dma_len;
 };
 
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 909ad7a..4566cdf 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1793,7 +1793,7 @@
 	macaddr = of_get_mac_address(dn);
 	if (!macaddr || !is_valid_ether_addr(macaddr)) {
 		dev_warn(&pdev->dev, "using random Ethernet MAC\n");
-		random_ether_addr(dev->dev_addr);
+		eth_hw_addr_random(dev);
 	} else {
 		ether_addr_copy(dev->dev_addr, macaddr);
 	}
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index a90d736..f7fbdc9 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -262,9 +262,9 @@
 	if (likely(skb)) {
 		(*pkts_compl)++;
 		(*bytes_compl) += skb->len;
+		dev_kfree_skb_any(skb);
 	}
 
-	dev_kfree_skb_any(skb);
 	tx_buf->first_bd = 0;
 	tx_buf->skb = NULL;
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
index 76b9052..5907c82 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_ethtool.c
@@ -1718,6 +1718,22 @@
 		offset += sizeof(u32);
 		data_buf += sizeof(u32);
 		written_so_far += sizeof(u32);
+
+		/* At end of each 4Kb page, release nvram lock to allow MFW
+		 * chance to take it for its own use.
+		 */
+		if ((cmd_flags & MCPR_NVM_COMMAND_LAST) &&
+		    (written_so_far < buf_size)) {
+			DP(BNX2X_MSG_ETHTOOL | BNX2X_MSG_NVM,
+			   "Releasing NVM lock after offset 0x%x\n",
+			   (u32)(offset - sizeof(u32)));
+			bnx2x_release_nvram_lock(bp);
+			usleep_range(1000, 2000);
+			rc = bnx2x_acquire_nvram_lock(bp);
+			if (rc)
+				return rc;
+		}
+
 		cmd_flags = 0;
 	}
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index b43b2cb..64c1e9d 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1230,7 +1230,6 @@
 		new_skb = skb_realloc_headroom(skb, sizeof(*status));
 		dev_kfree_skb(skb);
 		if (!new_skb) {
-			dev->stats.tx_errors++;
 			dev->stats.tx_dropped++;
 			return NULL;
 		}
@@ -1465,7 +1464,6 @@
 
 		if (unlikely(!skb)) {
 			dev->stats.rx_dropped++;
-			dev->stats.rx_errors++;
 			goto next;
 		}
 
@@ -1493,7 +1491,6 @@
 		if (unlikely(!(dma_flag & DMA_EOP) || !(dma_flag & DMA_SOP))) {
 			netif_err(priv, rx_status, dev,
 				  "dropping fragmented packet!\n");
-			dev->stats.rx_dropped++;
 			dev->stats.rx_errors++;
 			dev_kfree_skb_any(skb);
 			goto next;
@@ -1515,7 +1512,6 @@
 				dev->stats.rx_frame_errors++;
 			if (dma_flag & DMA_RX_LG)
 				dev->stats.rx_length_errors++;
-			dev->stats.rx_dropped++;
 			dev->stats.rx_errors++;
 			dev_kfree_skb_any(skb);
 			goto next;
diff --git a/drivers/net/ethernet/broadcom/sb1250-mac.c b/drivers/net/ethernet/broadcom/sb1250-mac.c
index ac27e24..f557a2a 100644
--- a/drivers/net/ethernet/broadcom/sb1250-mac.c
+++ b/drivers/net/ethernet/broadcom/sb1250-mac.c
@@ -1508,16 +1508,7 @@
 	__raw_writeq(reg, port);
 	port = s->sbm_base + R_MAC_ETHERNET_ADDR;
 
-#ifdef CONFIG_SB1_PASS_1_WORKAROUNDS
-	/*
-	 * Pass1 SOCs do not receive packets addressed to the
-	 * destination address in the R_MAC_ETHERNET_ADDR register.
-	 * Set the value to zero.
-	 */
-	__raw_writeq(0, port);
-#else
 	__raw_writeq(reg, port);
-#endif
 
 	/*
 	 * Set the receive filter for no packets, and write values
diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index 0612b19..506047c 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -676,6 +676,7 @@
 			if (!next_cmpl->valid)
 				break;
 		}
+		packets++;
 
 		/* TODO: BNA_CQ_EF_LOCAL ? */
 		if (unlikely(flags & (BNA_CQ_EF_MAC_ERROR |
@@ -692,7 +693,6 @@
 		else
 			bnad_cq_setup_skb_frags(rcb, skb, sop_ci, nvecs, len);
 
-		packets++;
 		rcb->rxq->rx_packets++;
 		rcb->rxq->rx_bytes += totlen;
 		ccb->bytes_per_intr += totlen;
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index caeb395..bf9eb2e 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -104,6 +104,57 @@
 	return bp->rx_buffers + bp->rx_buffer_size * macb_rx_ring_wrap(index);
 }
 
+/* I/O accessors */
+static u32 hw_readl_native(struct macb *bp, int offset)
+{
+	return __raw_readl(bp->regs + offset);
+}
+
+static void hw_writel_native(struct macb *bp, int offset, u32 value)
+{
+	__raw_writel(value, bp->regs + offset);
+}
+
+static u32 hw_readl(struct macb *bp, int offset)
+{
+	return readl_relaxed(bp->regs + offset);
+}
+
+static void hw_writel(struct macb *bp, int offset, u32 value)
+{
+	writel_relaxed(value, bp->regs + offset);
+}
+
+/*
+ * Find the CPU endianness by using the loopback bit of NCR register. When the
+ * CPU is in big endian we need to program swaped mode for management
+ * descriptor access.
+ */
+static bool hw_is_native_io(void __iomem *addr)
+{
+	u32 value = MACB_BIT(LLB);
+
+	__raw_writel(value, addr + MACB_NCR);
+	value = __raw_readl(addr + MACB_NCR);
+
+	/* Write 0 back to disable everything */
+	__raw_writel(0, addr + MACB_NCR);
+
+	return value == MACB_BIT(LLB);
+}
+
+static bool hw_is_gem(void __iomem *addr, bool native_io)
+{
+	u32 id;
+
+	if (native_io)
+		id = __raw_readl(addr + MACB_MID);
+	else
+		id = readl_relaxed(addr + MACB_MID);
+
+	return MACB_BFEXT(IDNUM, id) >= 0x2;
+}
+
 static void macb_set_hwaddr(struct macb *bp)
 {
 	u32 bottom;
@@ -160,7 +211,7 @@
 		}
 	}
 
-	netdev_info(bp->dev, "invalid hw address, using random\n");
+	dev_info(&bp->pdev->dev, "invalid hw address, using random\n");
 	eth_hw_addr_random(bp->dev);
 }
 
@@ -252,7 +303,6 @@
 	struct macb *bp = netdev_priv(dev);
 	struct phy_device *phydev = bp->phy_dev;
 	unsigned long flags;
-
 	int status_change = 0;
 
 	spin_lock_irqsave(&bp->lock, flags);
@@ -449,14 +499,14 @@
 
 static void macb_update_stats(struct macb *bp)
 {
-	u32 __iomem *reg = bp->regs + MACB_PFR;
 	u32 *p = &bp->hw_stats.macb.rx_pause_frames;
 	u32 *end = &bp->hw_stats.macb.tx_pause_frames + 1;
+	int offset = MACB_PFR;
 
 	WARN_ON((unsigned long)(end - p - 1) != (MACB_TPF - MACB_PFR) / 4);
 
-	for(; p < end; p++, reg++)
-		*p += readl_relaxed(reg);
+	for(; p < end; p++, offset += 4)
+		*p += bp->macb_reg_readl(bp, offset);
 }
 
 static int macb_halt_tx(struct macb *bp)
@@ -1107,12 +1157,6 @@
 }
 #endif
 
-static inline unsigned int macb_count_tx_descriptors(struct macb *bp,
-						     unsigned int len)
-{
-	return (len + bp->max_tx_length - 1) / bp->max_tx_length;
-}
-
 static unsigned int macb_tx_map(struct macb *bp,
 				struct macb_queue *queue,
 				struct sk_buff *skb)
@@ -1263,11 +1307,11 @@
 	 * socket buffer: skb fragments of jumbo frames may need to be
 	 * splitted into many buffer descriptors.
 	 */
-	count = macb_count_tx_descriptors(bp, skb_headlen(skb));
+	count = DIV_ROUND_UP(skb_headlen(skb), bp->max_tx_length);
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	for (f = 0; f < nr_frags; f++) {
 		frag_size = skb_frag_size(&skb_shinfo(skb)->frags[f]);
-		count += macb_count_tx_descriptors(bp, frag_size);
+		count += DIV_ROUND_UP(frag_size, bp->max_tx_length);
 	}
 
 	spin_lock_irqsave(&bp->lock, flags);
@@ -1603,7 +1647,6 @@
 static void macb_configure_dma(struct macb *bp)
 {
 	u32 dmacfg;
-	u32 tmp, ncr;
 
 	if (macb_is_gem(bp)) {
 		dmacfg = gem_readl(bp, DMACFG) & ~GEM_BF(RXBS, -1L);
@@ -1613,22 +1656,11 @@
 		dmacfg |= GEM_BIT(TXPBMS) | GEM_BF(RXBMS, -1L);
 		dmacfg &= ~GEM_BIT(ENDIA_PKT);
 
-		/* Find the CPU endianness by using the loopback bit of net_ctrl
-		 * register. save it first. When the CPU is in big endian we
-		 * need to program swaped mode for management descriptor access.
-		 */
-		ncr = macb_readl(bp, NCR);
-		__raw_writel(MACB_BIT(LLB), bp->regs + MACB_NCR);
-		tmp =  __raw_readl(bp->regs + MACB_NCR);
-
-		if (tmp == MACB_BIT(LLB))
+		if (bp->native_io)
 			dmacfg &= ~GEM_BIT(ENDIA_DESC);
 		else
 			dmacfg |= GEM_BIT(ENDIA_DESC); /* CPU in big endian */
 
-		/* Restore net_ctrl */
-		macb_writel(bp, NCR, ncr);
-
 		if (bp->dev->features & NETIF_F_HW_CSUM)
 			dmacfg |= GEM_BIT(TXCOEN);
 		else
@@ -1897,19 +1929,19 @@
 
 static void gem_update_stats(struct macb *bp)
 {
-	int i;
+	unsigned int i;
 	u32 *p = &bp->hw_stats.gem.tx_octets_31_0;
 
 	for (i = 0; i < GEM_STATS_LEN; ++i, ++p) {
 		u32 offset = gem_statistics[i].offset;
-		u64 val = readl_relaxed(bp->regs + offset);
+		u64 val = bp->macb_reg_readl(bp, offset);
 
 		bp->ethtool_stats[i] += val;
 		*p += val;
 
 		if (offset == GEM_OCTTXL || offset == GEM_OCTRXL) {
 			/* Add GEM_OCTTXH, GEM_OCTRXH */
-			val = readl_relaxed(bp->regs + offset + 4);
+			val = bp->macb_reg_readl(bp, offset + 4);
 			bp->ethtool_stats[i] += ((u64)val) << 32;
 			*(++p) += val;
 		}
@@ -1976,7 +2008,7 @@
 
 static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p)
 {
-	int i;
+	unsigned int i;
 
 	switch (sset) {
 	case ETH_SS_STATS:
@@ -2190,7 +2222,7 @@
 	if (dt_conf)
 		bp->caps = dt_conf->caps;
 
-	if (macb_is_gem_hw(bp->regs)) {
+	if (hw_is_gem(bp->regs, bp->native_io)) {
 		bp->caps |= MACB_CAPS_MACB_IS_GEM;
 
 		dcfg = gem_readl(bp, DCFG1);
@@ -2201,10 +2233,11 @@
 			bp->caps |= MACB_CAPS_FIFO_MODE;
 	}
 
-	netdev_dbg(bp->dev, "Cadence caps 0x%08x\n", bp->caps);
+	dev_dbg(&bp->pdev->dev, "Cadence caps 0x%08x\n", bp->caps);
 }
 
 static void macb_probe_queues(void __iomem *mem,
+			      bool native_io,
 			      unsigned int *queue_mask,
 			      unsigned int *num_queues)
 {
@@ -2219,7 +2252,7 @@
 	 * we are early in the probe process and don't have the
 	 * MACB_CAPS_MACB_IS_GEM flag positioned
 	 */
-	if (!macb_is_gem_hw(mem))
+	if (!hw_is_gem(mem, native_io))
 		return;
 
 	/* bit 0 is never set but queue 0 always exists */
@@ -2786,6 +2819,7 @@
 	struct clk *pclk, *hclk, *tx_clk;
 	unsigned int queue_mask, num_queues;
 	struct macb_platform_data *pdata;
+	bool native_io;
 	struct phy_device *phydev;
 	struct net_device *dev;
 	struct resource *regs;
@@ -2794,6 +2828,11 @@
 	struct macb *bp;
 	int err;
 
+	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	mem = devm_ioremap_resource(&pdev->dev, regs);
+	if (IS_ERR(mem))
+		return PTR_ERR(mem);
+
 	if (np) {
 		const struct of_device_id *match;
 
@@ -2809,14 +2848,9 @@
 	if (err)
 		return err;
 
-	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	mem = devm_ioremap_resource(&pdev->dev, regs);
-	if (IS_ERR(mem)) {
-		err = PTR_ERR(mem);
-		goto err_disable_clocks;
-	}
+	native_io = hw_is_native_io(mem);
 
-	macb_probe_queues(mem, &queue_mask, &num_queues);
+	macb_probe_queues(mem, native_io, &queue_mask, &num_queues);
 	dev = alloc_etherdev_mq(sizeof(*bp), num_queues);
 	if (!dev) {
 		err = -ENOMEM;
@@ -2831,6 +2865,14 @@
 	bp->pdev = pdev;
 	bp->dev = dev;
 	bp->regs = mem;
+	bp->native_io = native_io;
+	if (native_io) {
+		bp->macb_reg_readl = hw_readl_native;
+		bp->macb_reg_writel = hw_writel_native;
+	} else {
+		bp->macb_reg_readl = hw_readl;
+		bp->macb_reg_writel = hw_writel;
+	}
 	bp->num_queues = num_queues;
 	bp->queue_mask = queue_mask;
 	if (macb_config)
@@ -2838,9 +2880,8 @@
 	bp->pclk = pclk;
 	bp->hclk = hclk;
 	bp->tx_clk = tx_clk;
-	if (macb_config->jumbo_max_len) {
+	if (macb_config)
 		bp->jumbo_max_len = macb_config->jumbo_max_len;
-	}
 
 	spin_lock_init(&bp->lock);
 
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index d746559..1895b6b 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -429,18 +429,12 @@
 	 | GEM_BF(name, value))
 
 /* Register access macros */
-#define macb_readl(port,reg)				\
-	readl_relaxed((port)->regs + MACB_##reg)
-#define macb_writel(port,reg,value)			\
-	writel_relaxed((value), (port)->regs + MACB_##reg)
-#define gem_readl(port, reg)				\
-	readl_relaxed((port)->regs + GEM_##reg)
-#define gem_writel(port, reg, value)			\
-	writel_relaxed((value), (port)->regs + GEM_##reg)
-#define queue_readl(queue, reg)				\
-	readl_relaxed((queue)->bp->regs + (queue)->reg)
-#define queue_writel(queue, reg, value)			\
-	writel_relaxed((value), (queue)->bp->regs + (queue)->reg)
+#define macb_readl(port, reg)		(port)->macb_reg_readl((port), MACB_##reg)
+#define macb_writel(port, reg, value)	(port)->macb_reg_writel((port), MACB_##reg, (value))
+#define gem_readl(port, reg)		(port)->macb_reg_readl((port), GEM_##reg)
+#define gem_writel(port, reg, value)	(port)->macb_reg_writel((port), GEM_##reg, (value))
+#define queue_readl(queue, reg)		(queue)->bp->macb_reg_readl((queue)->bp, (queue)->reg)
+#define queue_writel(queue, reg, value)	(queue)->bp->macb_reg_writel((queue)->bp, (queue)->reg, (value))
 
 /* Conditional GEM/MACB macros.  These perform the operation to the correct
  * register dependent on whether the device is a GEM or a MACB.  For registers
@@ -785,6 +779,11 @@
 
 struct macb {
 	void __iomem		*regs;
+	bool			native_io;
+
+	/* hardware IO accessors */
+	u32	(*macb_reg_readl)(struct macb *bp, int offset);
+	void	(*macb_reg_writel)(struct macb *bp, int offset, u32 value);
 
 	unsigned int		rx_tail;
 	unsigned int		rx_prepared_head;
@@ -817,9 +816,9 @@
 
 	struct mii_bus		*mii_bus;
 	struct phy_device	*phy_dev;
-	unsigned int 		link;
-	unsigned int 		speed;
-	unsigned int 		duplex;
+	int 			link;
+	int 			speed;
+	int 			duplex;
 
 	u32			caps;
 	unsigned int		dma_burst_length;
@@ -843,9 +842,4 @@
 	return !!(bp->caps & MACB_CAPS_MACB_IS_GEM);
 }
 
-static inline bool macb_is_gem_hw(void __iomem *addr)
-{
-	return !!(MACB_BFEXT(IDNUM, readl_relaxed(addr + MACB_MID)) >= 0x2);
-}
-
 #endif /* _MACB_H */
diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index c4d6bbe..02e23e6 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -16,7 +16,6 @@
 config THUNDER_NIC_PF
 	tristate "Thunder Physical function driver"
 	depends on 64BIT
-	default ARCH_THUNDER
 	select THUNDER_NIC_BGX
 	---help---
 	  This driver supports Thunder's NIC physical function.
@@ -29,14 +28,12 @@
 config THUNDER_NIC_VF
 	tristate "Thunder Virtual function driver"
 	depends on 64BIT
-	default ARCH_THUNDER
 	---help---
 	  This driver supports Thunder's NIC virtual function
 
 config	THUNDER_NIC_BGX
 	tristate "Thunder MAC interface driver (BGX)"
 	depends on 64BIT
-	default ARCH_THUNDER
 	---help---
 	  This driver supports programming and controlling of MAC
 	  interface from NIC physical function driver.
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index dda8a02..8aee250 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -125,6 +125,15 @@
  */
 #define NICPF_CLK_PER_INT_TICK		2
 
+/* Time to wait before we decide that a SQ is stuck.
+ *
+ * Since both pkt rx and tx notifications are done with same CQ,
+ * when packets are being received at very high rate (eg: L2 forwarding)
+ * then freeing transmitted skbs will be delayed and watchdog
+ * will kick in, resetting interface. Hence keeping this value high.
+ */
+#define	NICVF_TX_TIMEOUT		(50 * HZ)
+
 struct nicvf_cq_poll {
 	u8	cq_idx;		/* Completion queue index */
 	struct	napi_struct napi;
@@ -216,8 +225,9 @@
 	/* Tx */
 	u64 tx_frames_ok;
 	u64 tx_drops;
-	u64 tx_busy;
 	u64 tx_tso;
+	u64 txq_stop;
+	u64 txq_wake;
 };
 
 struct nicvf {
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index 16bd2d7..a4228e6 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -66,9 +66,10 @@
 	NICVF_DRV_STAT(rx_frames_jumbo),
 	NICVF_DRV_STAT(rx_drops),
 	NICVF_DRV_STAT(tx_frames_ok),
-	NICVF_DRV_STAT(tx_busy),
 	NICVF_DRV_STAT(tx_tso),
 	NICVF_DRV_STAT(tx_drops),
+	NICVF_DRV_STAT(txq_stop),
+	NICVF_DRV_STAT(txq_wake),
 };
 
 static const struct nicvf_stat nicvf_queue_stats[] = {
@@ -126,6 +127,7 @@
 
 static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 {
+	struct nicvf *nic = netdev_priv(netdev);
 	int stats, qidx;
 
 	if (sset != ETH_SS_STATS)
@@ -141,7 +143,7 @@
 		data += ETH_GSTRING_LEN;
 	}
 
-	for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) {
 		for (stats = 0; stats < nicvf_n_queue_stats; stats++) {
 			sprintf(data, "rxq%d: %s", qidx,
 				nicvf_queue_stats[stats].name);
@@ -149,7 +151,7 @@
 		}
 	}
 
-	for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) {
 		for (stats = 0; stats < nicvf_n_queue_stats; stats++) {
 			sprintf(data, "txq%d: %s", qidx,
 				nicvf_queue_stats[stats].name);
@@ -170,12 +172,14 @@
 
 static int nicvf_get_sset_count(struct net_device *netdev, int sset)
 {
+	struct nicvf *nic = netdev_priv(netdev);
+
 	if (sset != ETH_SS_STATS)
 		return -EINVAL;
 
 	return nicvf_n_hw_stats + nicvf_n_drv_stats +
 		(nicvf_n_queue_stats *
-		 (MAX_RCV_QUEUES_PER_QS + MAX_SND_QUEUES_PER_QS)) +
+		 (nic->qs->rq_cnt + nic->qs->sq_cnt)) +
 		BGX_RX_STATS_COUNT + BGX_TX_STATS_COUNT;
 }
 
@@ -197,13 +201,13 @@
 		*(data++) = ((u64 *)&nic->drv_stats)
 				[nicvf_drv_stats[stat].index];
 
-	for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) {
 		for (stat = 0; stat < nicvf_n_queue_stats; stat++)
 			*(data++) = ((u64 *)&nic->qs->rq[qidx].stats)
 					[nicvf_queue_stats[stat].index];
 	}
 
-	for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) {
 		for (stat = 0; stat < nicvf_n_queue_stats; stat++)
 			*(data++) = ((u64 *)&nic->qs->sq[qidx].stats)
 					[nicvf_queue_stats[stat].index];
@@ -543,6 +547,7 @@
 {
 	struct nicvf *nic = netdev_priv(dev);
 	int err = 0;
+	bool if_up = netif_running(dev);
 
 	if (!channel->rx_count || !channel->tx_count)
 		return -EINVAL;
@@ -551,6 +556,9 @@
 	if (channel->tx_count > MAX_SND_QUEUES_PER_QS)
 		return -EINVAL;
 
+	if (if_up)
+		nicvf_stop(dev);
+
 	nic->qs->rq_cnt = channel->rx_count;
 	nic->qs->sq_cnt = channel->tx_count;
 	nic->qs->cq_cnt = max(nic->qs->rq_cnt, nic->qs->sq_cnt);
@@ -559,11 +567,9 @@
 	if (err)
 		return err;
 
-	if (!netif_running(dev))
-		return err;
+	if (if_up)
+		nicvf_open(dev);
 
-	nicvf_stop(dev);
-	nicvf_open(dev);
 	netdev_info(dev, "Setting num Tx rings to %d, Rx rings to %d success\n",
 		    nic->qs->sq_cnt, nic->qs->rq_cnt);
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 8b119a0..3b90afb 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -234,7 +234,7 @@
 				    nic->duplex == DUPLEX_FULL ?
 				"Full duplex" : "Half duplex");
 			netif_carrier_on(nic->netdev);
-			netif_tx_wake_all_queues(nic->netdev);
+			netif_tx_start_all_queues(nic->netdev);
 		} else {
 			netdev_info(nic->netdev, "%s: Link is Down\n",
 				    nic->netdev->name);
@@ -425,6 +425,7 @@
 	if (skb) {
 		prefetch(skb);
 		dev_consume_skb_any(skb);
+		sq->skbuff[cqe_tx->sqe_ptr] = (u64)NULL;
 	}
 }
 
@@ -476,12 +477,13 @@
 static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
 				 struct napi_struct *napi, int budget)
 {
-	int processed_cqe, work_done = 0;
+	int processed_cqe, work_done = 0, tx_done = 0;
 	int cqe_count, cqe_head;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct queue_set *qs = nic->qs;
 	struct cmp_queue *cq = &qs->cq[cq_idx];
 	struct cqe_rx_t *cq_desc;
+	struct netdev_queue *txq;
 
 	spin_lock_bh(&cq->lock);
 loop:
@@ -496,8 +498,8 @@
 	cqe_head = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD, cq_idx) >> 9;
 	cqe_head &= 0xFFFF;
 
-	netdev_dbg(nic->netdev, "%s cqe_count %d cqe_head %d\n",
-		   __func__, cqe_count, cqe_head);
+	netdev_dbg(nic->netdev, "%s CQ%d cqe_count %d cqe_head %d\n",
+		   __func__, cq_idx, cqe_count, cqe_head);
 	while (processed_cqe < cqe_count) {
 		/* Get the CQ descriptor */
 		cq_desc = (struct cqe_rx_t *)GET_CQ_DESC(cq, cqe_head);
@@ -511,8 +513,8 @@
 			break;
 		}
 
-		netdev_dbg(nic->netdev, "cq_desc->cqe_type %d\n",
-			   cq_desc->cqe_type);
+		netdev_dbg(nic->netdev, "CQ%d cq_desc->cqe_type %d\n",
+			   cq_idx, cq_desc->cqe_type);
 		switch (cq_desc->cqe_type) {
 		case CQE_TYPE_RX:
 			nicvf_rcv_pkt_handler(netdev, napi, cq,
@@ -522,6 +524,7 @@
 		case CQE_TYPE_SEND:
 			nicvf_snd_pkt_handler(netdev, cq,
 					      (void *)cq_desc, CQE_TYPE_SEND);
+			tx_done++;
 		break;
 		case CQE_TYPE_INVALID:
 		case CQE_TYPE_RX_SPLIT:
@@ -532,8 +535,9 @@
 		}
 		processed_cqe++;
 	}
-	netdev_dbg(nic->netdev, "%s processed_cqe %d work_done %d budget %d\n",
-		   __func__, processed_cqe, work_done, budget);
+	netdev_dbg(nic->netdev,
+		   "%s CQ%d processed_cqe %d work_done %d budget %d\n",
+		   __func__, cq_idx, processed_cqe, work_done, budget);
 
 	/* Ring doorbell to inform H/W to reuse processed CQEs */
 	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_DOOR,
@@ -543,6 +547,19 @@
 		goto loop;
 
 done:
+	/* Wakeup TXQ if its stopped earlier due to SQ full */
+	if (tx_done) {
+		txq = netdev_get_tx_queue(netdev, cq_idx);
+		if (netif_tx_queue_stopped(txq)) {
+			netif_tx_start_queue(txq);
+			nic->drv_stats.txq_wake++;
+			if (netif_msg_tx_err(nic))
+				netdev_warn(netdev,
+					    "%s: Transmit queue wakeup SQ%d\n",
+					    netdev->name, cq_idx);
+		}
+	}
+
 	spin_unlock_bh(&cq->lock);
 	return work_done;
 }
@@ -554,15 +571,10 @@
 	struct net_device *netdev = napi->dev;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct nicvf_cq_poll *cq;
-	struct netdev_queue *txq;
 
 	cq = container_of(napi, struct nicvf_cq_poll, napi);
 	work_done = nicvf_cq_intr_handler(netdev, cq->cq_idx, napi, budget);
 
-	txq = netdev_get_tx_queue(netdev, cq->cq_idx);
-	if (netif_tx_queue_stopped(txq))
-		netif_tx_wake_queue(txq);
-
 	if (work_done < budget) {
 		/* Slow packet rate, exit polling */
 		napi_complete(napi);
@@ -833,9 +845,9 @@
 		return NETDEV_TX_OK;
 	}
 
-	if (!nicvf_sq_append_skb(nic, skb) && !netif_tx_queue_stopped(txq)) {
+	if (!netif_tx_queue_stopped(txq) && !nicvf_sq_append_skb(nic, skb)) {
 		netif_tx_stop_queue(txq);
-		nic->drv_stats.tx_busy++;
+		nic->drv_stats.txq_stop++;
 		if (netif_msg_tx_err(nic))
 			netdev_warn(netdev,
 				    "%s: Transmit ring full, stopping SQ%d\n",
@@ -859,7 +871,6 @@
 	nicvf_send_msg_to_pf(nic, &mbx);
 
 	netif_carrier_off(netdev);
-	netif_tx_disable(netdev);
 
 	/* Disable RBDR & QS error interrupts */
 	for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) {
@@ -894,6 +905,8 @@
 		kfree(cq_poll);
 	}
 
+	netif_tx_disable(netdev);
+
 	/* Free resources */
 	nicvf_config_data_transfer(nic, false);
 
@@ -988,6 +1001,9 @@
 	for (qidx = 0; qidx < qs->rbdr_cnt; qidx++)
 		nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx);
 
+	nic->drv_stats.txq_stop = 0;
+	nic->drv_stats.txq_wake = 0;
+
 	netif_carrier_on(netdev);
 	netif_tx_start_all_queues(netdev);
 
@@ -1278,6 +1294,7 @@
 	netdev->hw_features = netdev->features;
 
 	netdev->netdev_ops = &nicvf_netdev_ops;
+	netdev->watchdog_timeo = NICVF_TX_TIMEOUT;
 
 	INIT_WORK(&nic->reset_task, nicvf_reset_task);
 
@@ -1318,11 +1335,17 @@
 	pci_disable_device(pdev);
 }
 
+static void nicvf_shutdown(struct pci_dev *pdev)
+{
+	nicvf_remove(pdev);
+}
+
 static struct pci_driver nicvf_driver = {
 	.name = DRV_NAME,
 	.id_table = nicvf_id_table,
 	.probe = nicvf_probe,
 	.remove = nicvf_remove,
+	.shutdown = nicvf_shutdown,
 };
 
 static int __init nicvf_init_module(void)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index d69d228d..ca4240a 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -103,9 +103,11 @@
 
 	/* Allocate a new page */
 	if (!nic->rb_page) {
-		nic->rb_page = alloc_pages(gfp | __GFP_COMP, order);
+		nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
+					   order);
 		if (!nic->rb_page) {
-			netdev_err(nic->netdev, "Failed to allocate new rcv buffer\n");
+			netdev_err(nic->netdev,
+				   "Failed to allocate new rcv buffer\n");
 			return -ENOMEM;
 		}
 		nic->rb_page_offset = 0;
@@ -382,7 +384,8 @@
 		return;
 
 	if (sq->tso_hdrs)
-		dma_free_coherent(&nic->pdev->dev, sq->dmem.q_len,
+		dma_free_coherent(&nic->pdev->dev,
+				  sq->dmem.q_len * TSO_HEADER_SIZE,
 				  sq->tso_hdrs, sq->tso_hdrs_phys);
 
 	kfree(sq->skbuff);
@@ -863,10 +866,11 @@
 			continue;
 		}
 		skb = (struct sk_buff *)sq->skbuff[sq->head];
+		if (skb)
+			dev_kfree_skb_any(skb);
 		atomic64_add(1, (atomic64_t *)&netdev->stats.tx_packets);
 		atomic64_add(hdr->tot_len,
 			     (atomic64_t *)&netdev->stats.tx_bytes);
-		dev_kfree_skb_any(skb);
 		nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
 	}
 }
@@ -992,7 +996,7 @@
 
 	memset(gather, 0, SND_QUEUE_DESC_SIZE);
 	gather->subdesc_type = SQ_DESC_TYPE_GATHER;
-	gather->ld_type = NIC_SEND_LD_TYPE_E_LDWB;
+	gather->ld_type = NIC_SEND_LD_TYPE_E_LDD;
 	gather->size = size;
 	gather->addr = data;
 }
@@ -1048,7 +1052,7 @@
 		}
 		nicvf_sq_add_hdr_subdesc(sq, hdr_qentry,
 					 seg_subdescs - 1, skb, seg_len);
-		sq->skbuff[hdr_qentry] = 0;
+		sq->skbuff[hdr_qentry] = (u64)NULL;
 		qentry = nicvf_get_nxt_sqentry(sq, qentry);
 
 		desc_cnt += seg_subdescs;
@@ -1062,6 +1066,7 @@
 	/* Inform HW to xmit all TSO segments */
 	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR,
 			      skb_get_queue_mapping(skb), desc_cnt);
+	nic->drv_stats.tx_tso++;
 	return 1;
 }
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index 8341bdf..f0937b7 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -62,7 +62,7 @@
 #define SND_QUEUE_CNT		8
 #define CMP_QUEUE_CNT		8 /* Max of RCV and SND qcount */
 
-#define SND_QSIZE		SND_QUEUE_SIZE4
+#define SND_QSIZE		SND_QUEUE_SIZE2
 #define SND_QUEUE_LEN		(1ULL << (SND_QSIZE + 10))
 #define MAX_SND_QUEUE_LEN	(1ULL << (SND_QUEUE_SIZE6 + 10))
 #define SND_QUEUE_THRESH	2ULL
@@ -70,7 +70,10 @@
 /* Since timestamp not enabled, otherwise 2 */
 #define MAX_CQE_PER_PKT_XMIT		1
 
-#define CMP_QSIZE		CMP_QUEUE_SIZE4
+/* Keep CQ and SQ sizes same, if timestamping
+ * is enabled this equation will change.
+ */
+#define CMP_QSIZE		CMP_QUEUE_SIZE2
 #define CMP_QUEUE_LEN		(1ULL << (CMP_QSIZE + 10))
 #define CMP_QUEUE_CQE_THRESH	0
 #define CMP_QUEUE_TIMER_THRESH	220 /* 10usec */
@@ -87,7 +90,12 @@
 
 #define MAX_CQES_FOR_TX		((SND_QUEUE_LEN / MIN_SQ_DESC_PER_PKT_XMIT) * \
 				 MAX_CQE_PER_PKT_XMIT)
-#define RQ_CQ_DROP		((CMP_QUEUE_LEN - MAX_CQES_FOR_TX) / 256)
+/* Calculate number of CQEs to reserve for all SQEs.
+ * Its 1/256th level of CQ size.
+ * '+ 1' to account for pipelining
+ */
+#define RQ_CQ_DROP		((256 / (CMP_QUEUE_LEN / \
+				 (CMP_QUEUE_LEN - MAX_CQES_FOR_TX))) + 1)
 
 /* Descriptor size in bytes */
 #define SND_QUEUE_DESC_SIZE	16
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 633ec05..b961a89 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -673,7 +673,10 @@
 	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg);
 	bgx_flush_dmac_addrs(bgx, lmacid);
 
-	if (lmac->phydev)
+	if ((bgx->lmac_type != BGX_MODE_XFI) &&
+	    (bgx->lmac_type != BGX_MODE_XLAUI) &&
+	    (bgx->lmac_type != BGX_MODE_40G_KR) &&
+	    (bgx->lmac_type != BGX_MODE_10G_KR) && lmac->phydev)
 		phy_disconnect(lmac->phydev);
 
 	lmac->phydev = NULL;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 484eb8c..c3c7db4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -952,16 +952,23 @@
 		 * eventually have to put a format interpreter in here ...
 		 */
 		seq_printf(seq, "%10d  %15llu  %8s  %8s  ",
-			   e->seqno, e->timestamp,
+			   be32_to_cpu(e->seqno),
+			   be64_to_cpu(e->timestamp),
 			   (e->level < ARRAY_SIZE(devlog_level_strings)
 			    ? devlog_level_strings[e->level]
 			    : "UNKNOWN"),
 			   (e->facility < ARRAY_SIZE(devlog_facility_strings)
 			    ? devlog_facility_strings[e->facility]
 			    : "UNKNOWN"));
-		seq_printf(seq, e->fmt, e->params[0], e->params[1],
-			   e->params[2], e->params[3], e->params[4],
-			   e->params[5], e->params[6], e->params[7]);
+		seq_printf(seq, e->fmt,
+			   be32_to_cpu(e->params[0]),
+			   be32_to_cpu(e->params[1]),
+			   be32_to_cpu(e->params[2]),
+			   be32_to_cpu(e->params[3]),
+			   be32_to_cpu(e->params[4]),
+			   be32_to_cpu(e->params[5]),
+			   be32_to_cpu(e->params[6]),
+			   be32_to_cpu(e->params[7]));
 	}
 	return 0;
 }
@@ -1043,23 +1050,17 @@
 		return ret;
 	}
 
-	/* Translate log multi-byte integral elements into host native format
-	 * and determine where the first entry in the log is.
+	/* Find the earliest (lowest Sequence Number) log entry in the
+	 * circular Device Log.
 	 */
 	for (fseqno = ~((u32)0), index = 0; index < dinfo->nentries; index++) {
 		struct fw_devlog_e *e = &dinfo->log[index];
-		int i;
 		__u32 seqno;
 
 		if (e->timestamp == 0)
 			continue;
 
-		e->timestamp = (__force __be64)be64_to_cpu(e->timestamp);
 		seqno = be32_to_cpu(e->seqno);
-		for (i = 0; i < 8; i++)
-			e->params[i] =
-				(__force __be32)be32_to_cpu(e->params[i]);
-
 		if (seqno < fseqno) {
 			fseqno = seqno;
 			dinfo->first = index;
@@ -2331,10 +2332,11 @@
 					EXT_MEM1_SIZE_G(size));
 		}
 	} else {
-		if (i & EXT_MEM_ENABLE_F)
+		if (i & EXT_MEM_ENABLE_F) {
 			size = t4_read_reg(adap, MA_EXT_MEMORY_BAR_A);
 			add_debugfs_mem(adap, "mc", MEM_MC,
 					EXT_MEM_SIZE_G(size));
+		}
 	}
 
 	de = debugfs_create_file_size("flash", S_IRUSR, adap->debugfs_root, adap,
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index da2004e..918a8e4 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1170,7 +1170,7 @@
 						 wq_work_done,
 						 0 /* dont unmask intr */,
 						 0 /* dont reset intr timer */);
-		return rq_work_done;
+		return budget;
 	}
 
 	if (budget > 0)
@@ -1191,6 +1191,7 @@
 			0 /* don't reset intr timer */);
 
 	err = vnic_rq_fill(&enic->rq[0], enic_rq_alloc_buf);
+	enic_poll_unlock_napi(&enic->rq[cq_rq], napi);
 
 	/* Buffer allocation failed. Stay in polling
 	 * mode so we can try to fill the ring again.
@@ -1208,7 +1209,6 @@
 		napi_complete(napi);
 		vnic_intr_unmask(&enic->intr[intr]);
 	}
-	enic_poll_unlock_napi(&enic->rq[cq_rq], napi);
 
 	return rq_work_done;
 }
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index 2716e6f..00e3a6b 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -620,6 +620,11 @@
 					 BE_IF_FLAGS_VLAN_PROMISCUOUS |\
 					 BE_IF_FLAGS_MCAST_PROMISCUOUS)
 
+#define BE_IF_EN_FLAGS	(BE_IF_FLAGS_BROADCAST | BE_IF_FLAGS_PASS_L3L4_ERRORS |\
+			BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_UNTAGGED)
+
+#define BE_IF_ALL_FILT_FLAGS	(BE_IF_EN_FLAGS | BE_IF_FLAGS_ALL_PROMISCUOUS)
+
 /* An RX interface is an object with one or more MAC addresses and
  * filtering capabilities. */
 struct be_cmd_req_if_create {
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 6f64242..6ca693b 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -273,6 +273,10 @@
 	if (ether_addr_equal(addr->sa_data, netdev->dev_addr))
 		return 0;
 
+	/* if device is not running, copy MAC to netdev->dev_addr */
+	if (!netif_running(netdev))
+		goto done;
+
 	/* The PMAC_ADD cmd may fail if the VF doesn't have FILTMGMT
 	 * privilege or if PF did not provision the new MAC address.
 	 * On BE3, this cmd will always fail if the VF doesn't have the
@@ -307,9 +311,9 @@
 		status = -EPERM;
 		goto err;
 	}
-
-	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
-	dev_info(dev, "MAC address changed to %pM\n", mac);
+done:
+	ether_addr_copy(netdev->dev_addr, addr->sa_data);
+	dev_info(dev, "MAC address changed to %pM\n", addr->sa_data);
 	return 0;
 err:
 	dev_warn(dev, "MAC address change to %pM failed\n", addr->sa_data);
@@ -2447,10 +2451,24 @@
 	be_eq_notify(eqo->adapter, eqo->q.id, false, true, num, 0);
 }
 
+/* Free posted rx buffers that were not used */
+static void be_rxq_clean(struct be_rx_obj *rxo)
+{
+	struct be_queue_info *rxq = &rxo->q;
+	struct be_rx_page_info *page_info;
+
+	while (atomic_read(&rxq->used) > 0) {
+		page_info = get_rx_page_info(rxo);
+		put_page(page_info->page);
+		memset(page_info, 0, sizeof(*page_info));
+	}
+	BUG_ON(atomic_read(&rxq->used));
+	rxq->tail = 0;
+	rxq->head = 0;
+}
+
 static void be_rx_cq_clean(struct be_rx_obj *rxo)
 {
-	struct be_rx_page_info *page_info;
-	struct be_queue_info *rxq = &rxo->q;
 	struct be_queue_info *rx_cq = &rxo->cq;
 	struct be_rx_compl_info *rxcp;
 	struct be_adapter *adapter = rxo->adapter;
@@ -2487,16 +2505,6 @@
 
 	/* After cleanup, leave the CQ in unarmed state */
 	be_cq_notify(adapter, rx_cq->id, false, 0);
-
-	/* Then free posted rx buffers that were not used */
-	while (atomic_read(&rxq->used) > 0) {
-		page_info = get_rx_page_info(rxo);
-		put_page(page_info->page);
-		memset(page_info, 0, sizeof(*page_info));
-	}
-	BUG_ON(atomic_read(&rxq->used));
-	rxq->tail = 0;
-	rxq->head = 0;
 }
 
 static void be_tx_compl_clean(struct be_adapter *adapter)
@@ -2576,8 +2584,8 @@
 			be_cmd_q_destroy(adapter, &eqo->q, QTYPE_EQ);
 			napi_hash_del(&eqo->napi);
 			netif_napi_del(&eqo->napi);
+			free_cpumask_var(eqo->affinity_mask);
 		}
-		free_cpumask_var(eqo->affinity_mask);
 		be_queue_free(adapter, &eqo->q);
 	}
 }
@@ -2594,13 +2602,7 @@
 
 	for_all_evt_queues(adapter, eqo, i) {
 		int numa_node = dev_to_node(&adapter->pdev->dev);
-		if (!zalloc_cpumask_var(&eqo->affinity_mask, GFP_KERNEL))
-			return -ENOMEM;
-		cpumask_set_cpu(cpumask_local_spread(i, numa_node),
-				eqo->affinity_mask);
-		netif_napi_add(adapter->netdev, &eqo->napi, be_poll,
-			       BE_NAPI_WEIGHT);
-		napi_hash_add(&eqo->napi);
+
 		aic = &adapter->aic_obj[i];
 		eqo->adapter = adapter;
 		eqo->idx = i;
@@ -2616,6 +2618,14 @@
 		rc = be_cmd_eq_create(adapter, eqo);
 		if (rc)
 			return rc;
+
+		if (!zalloc_cpumask_var(&eqo->affinity_mask, GFP_KERNEL))
+			return -ENOMEM;
+		cpumask_set_cpu(cpumask_local_spread(i, numa_node),
+				eqo->affinity_mask);
+		netif_napi_add(adapter->netdev, &eqo->napi, be_poll,
+			       BE_NAPI_WEIGHT);
+		napi_hash_add(&eqo->napi);
 	}
 	return 0;
 }
@@ -3354,13 +3364,54 @@
 	for_all_rx_queues(adapter, rxo, i) {
 		q = &rxo->q;
 		if (q->created) {
+			/* If RXQs are destroyed while in an "out of buffer"
+			 * state, there is a possibility of an HW stall on
+			 * Lancer. So, post 64 buffers to each queue to relieve
+			 * the "out of buffer" condition.
+			 * Make sure there's space in the RXQ before posting.
+			 */
+			if (lancer_chip(adapter)) {
+				be_rx_cq_clean(rxo);
+				if (atomic_read(&q->used) == 0)
+					be_post_rx_frags(rxo, GFP_KERNEL,
+							 MAX_RX_POST);
+			}
+
 			be_cmd_rxq_destroy(adapter, q);
 			be_rx_cq_clean(rxo);
+			be_rxq_clean(rxo);
 		}
 		be_queue_free(adapter, q);
 	}
 }
 
+static void be_disable_if_filters(struct be_adapter *adapter)
+{
+	be_cmd_pmac_del(adapter, adapter->if_handle,
+			adapter->pmac_id[0], 0);
+
+	be_clear_uc_list(adapter);
+
+	/* The IFACE flags are enabled in the open path and cleared
+	 * in the close path. When a VF gets detached from the host and
+	 * assigned to a VM the following happens:
+	 *	- VF's IFACE flags get cleared in the detach path
+	 *	- IFACE create is issued by the VF in the attach path
+	 * Due to a bug in the BE3/Skyhawk-R FW
+	 * (Lancer FW doesn't have the bug), the IFACE capability flags
+	 * specified along with the IFACE create cmd issued by a VF are not
+	 * honoured by FW.  As a consequence, if a *new* driver
+	 * (that enables/disables IFACE flags in open/close)
+	 * is loaded in the host and an *old* driver is * used by a VM/VF,
+	 * the IFACE gets created *without* the needed flags.
+	 * To avoid this, disable RX-filter flags only for Lancer.
+	 */
+	if (lancer_chip(adapter)) {
+		be_cmd_rx_filter(adapter, BE_IF_ALL_FILT_FLAGS, OFF);
+		adapter->if_flags &= ~BE_IF_ALL_FILT_FLAGS;
+	}
+}
+
 static int be_close(struct net_device *netdev)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
@@ -3373,6 +3424,8 @@
 	if (!(adapter->flags & BE_FLAGS_SETUP_DONE))
 		return 0;
 
+	be_disable_if_filters(adapter);
+
 	be_roce_dev_close(adapter);
 
 	if (adapter->flags & BE_FLAGS_NAPI_ENABLED) {
@@ -3392,7 +3445,6 @@
 	be_tx_compl_clean(adapter);
 
 	be_rx_qs_destroy(adapter);
-	be_clear_uc_list(adapter);
 
 	for_all_evt_queues(adapter, eqo, i) {
 		if (msix_enabled(adapter))
@@ -3477,6 +3529,31 @@
 	return 0;
 }
 
+static int be_enable_if_filters(struct be_adapter *adapter)
+{
+	int status;
+
+	status = be_cmd_rx_filter(adapter, BE_IF_EN_FLAGS, ON);
+	if (status)
+		return status;
+
+	/* For BE3 VFs, the PF programs the initial MAC address */
+	if (!(BEx_chip(adapter) && be_virtfn(adapter))) {
+		status = be_cmd_pmac_add(adapter, adapter->netdev->dev_addr,
+					 adapter->if_handle,
+					 &adapter->pmac_id[0], 0);
+		if (status)
+			return status;
+	}
+
+	if (adapter->vlans_added)
+		be_vid_config(adapter);
+
+	be_set_rx_mode(adapter->netdev);
+
+	return 0;
+}
+
 static int be_open(struct net_device *netdev)
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
@@ -3490,6 +3567,10 @@
 	if (status)
 		goto err;
 
+	status = be_enable_if_filters(adapter);
+	if (status)
+		goto err;
+
 	status = be_irq_register(adapter);
 	if (status)
 		goto err;
@@ -3686,16 +3767,6 @@
 	}
 }
 
-static void be_mac_clear(struct be_adapter *adapter)
-{
-	if (adapter->pmac_id) {
-		be_cmd_pmac_del(adapter, adapter->if_handle,
-				adapter->pmac_id[0], 0);
-		kfree(adapter->pmac_id);
-		adapter->pmac_id = NULL;
-	}
-}
-
 #ifdef CONFIG_BE2NET_VXLAN
 static void be_disable_vxlan_offloads(struct be_adapter *adapter)
 {
@@ -3770,8 +3841,8 @@
 #ifdef CONFIG_BE2NET_VXLAN
 	be_disable_vxlan_offloads(adapter);
 #endif
-	/* delete the primary mac along with the uc-mac list */
-	be_mac_clear(adapter);
+	kfree(adapter->pmac_id);
+	adapter->pmac_id = NULL;
 
 	be_cmd_if_destroy(adapter, adapter->if_handle,  0);
 
@@ -3782,25 +3853,11 @@
 	return 0;
 }
 
-static int be_if_create(struct be_adapter *adapter, u32 *if_handle,
-			u32 cap_flags, u32 vf)
-{
-	u32 en_flags;
-
-	en_flags = BE_IF_FLAGS_UNTAGGED | BE_IF_FLAGS_BROADCAST |
-		   BE_IF_FLAGS_MULTICAST | BE_IF_FLAGS_PASS_L3L4_ERRORS |
-		   BE_IF_FLAGS_RSS | BE_IF_FLAGS_DEFQ_RSS;
-
-	en_flags &= cap_flags;
-
-	return be_cmd_if_create(adapter, cap_flags, en_flags, if_handle, vf);
-}
-
 static int be_vfs_if_create(struct be_adapter *adapter)
 {
 	struct be_resources res = {0};
+	u32 cap_flags, en_flags, vf;
 	struct be_vf_cfg *vf_cfg;
-	u32 cap_flags, vf;
 	int status;
 
 	/* If a FW profile exists, then cap_flags are updated */
@@ -3821,8 +3878,12 @@
 			}
 		}
 
-		status = be_if_create(adapter, &vf_cfg->if_handle,
-				      cap_flags, vf + 1);
+		en_flags = cap_flags & (BE_IF_FLAGS_UNTAGGED |
+					BE_IF_FLAGS_BROADCAST |
+					BE_IF_FLAGS_MULTICAST |
+					BE_IF_FLAGS_PASS_L3L4_ERRORS);
+		status = be_cmd_if_create(adapter, cap_flags, en_flags,
+					  &vf_cfg->if_handle, vf + 1);
 		if (status)
 			return status;
 	}
@@ -4194,15 +4255,8 @@
 
 		memcpy(adapter->netdev->dev_addr, mac, ETH_ALEN);
 		memcpy(adapter->netdev->perm_addr, mac, ETH_ALEN);
-	} else {
-		/* Maybe the HW was reset; dev_addr must be re-programmed */
-		memcpy(mac, adapter->netdev->dev_addr, ETH_ALEN);
 	}
 
-	/* For BE3-R VFs, the PF programs the initial MAC address */
-	if (!(BEx_chip(adapter) && be_virtfn(adapter)))
-		be_cmd_pmac_add(adapter, mac, adapter->if_handle,
-				&adapter->pmac_id[0], 0);
 	return 0;
 }
 
@@ -4342,6 +4396,7 @@
 static int be_setup(struct be_adapter *adapter)
 {
 	struct device *dev = &adapter->pdev->dev;
+	u32 en_flags;
 	int status;
 
 	status = be_func_init(adapter);
@@ -4364,8 +4419,11 @@
 	if (status)
 		goto err;
 
-	status = be_if_create(adapter, &adapter->if_handle,
-			      be_if_cap_flags(adapter), 0);
+	/* will enable all the needed filter flags in be_open() */
+	en_flags = BE_IF_FLAGS_RSS | BE_IF_FLAGS_DEFQ_RSS;
+	en_flags = en_flags & be_if_cap_flags(adapter);
+	status = be_cmd_if_create(adapter, be_if_cap_flags(adapter), en_flags,
+				  &adapter->if_handle, 0);
 	if (status)
 		goto err;
 
@@ -4391,11 +4449,6 @@
 		dev_err(dev, "Please upgrade firmware to version >= 4.0\n");
 	}
 
-	if (adapter->vlans_added)
-		be_vid_config(adapter);
-
-	be_set_rx_mode(adapter->netdev);
-
 	status = be_cmd_set_flow_control(adapter, adapter->tx_fc,
 					 adapter->rx_fc);
 	if (status)
@@ -5121,7 +5174,7 @@
 	struct device *dev = &adapter->pdev->dev;
 	int status;
 
-	if (lancer_chip(adapter) || BEx_chip(adapter))
+	if (lancer_chip(adapter) || BEx_chip(adapter) || be_is_mc(adapter))
 		return;
 
 	if (adapter->flags & BE_FLAGS_VXLAN_OFFLOADS) {
@@ -5168,7 +5221,7 @@
 {
 	struct be_adapter *adapter = netdev_priv(netdev);
 
-	if (lancer_chip(adapter) || BEx_chip(adapter))
+	if (lancer_chip(adapter) || BEx_chip(adapter) || be_is_mc(adapter))
 		return;
 
 	if (adapter->vxlan_port != port)
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 1eee73c..99d33e2 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -562,6 +562,7 @@
 };
 
 void fec_ptp_init(struct platform_device *pdev);
+void fec_ptp_stop(struct platform_device *pdev);
 void fec_ptp_start_cyclecounter(struct net_device *ndev);
 int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr);
 int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 1f89c59..271bb58 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
+#include <linux/pm_runtime.h>
 #include <linux/ptrace.h>
 #include <linux/errno.h>
 #include <linux/ioport.h>
@@ -77,6 +78,7 @@
 #define FEC_ENET_RAEM_V	0x8
 #define FEC_ENET_RAFL_V	0x8
 #define FEC_ENET_OPD_V	0xFFF0
+#define FEC_MDIO_PM_TIMEOUT  100 /* ms */
 
 static struct platform_device_id fec_devtype[] = {
 	{
@@ -1767,7 +1769,13 @@
 static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 {
 	struct fec_enet_private *fep = bus->priv;
+	struct device *dev = &fep->pdev->dev;
 	unsigned long time_left;
+	int ret = 0;
+
+	ret = pm_runtime_get_sync(dev);
+	if (IS_ERR_VALUE(ret))
+		return ret;
 
 	fep->mii_timeout = 0;
 	init_completion(&fep->mdio_done);
@@ -1783,18 +1791,30 @@
 	if (time_left == 0) {
 		fep->mii_timeout = 1;
 		netdev_err(fep->netdev, "MDIO read timeout\n");
-		return -ETIMEDOUT;
+		ret = -ETIMEDOUT;
+		goto out;
 	}
 
-	/* return value */
-	return FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA));
+	ret = FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA));
+
+out:
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
+	return ret;
 }
 
 static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 			   u16 value)
 {
 	struct fec_enet_private *fep = bus->priv;
+	struct device *dev = &fep->pdev->dev;
 	unsigned long time_left;
+	int ret = 0;
+
+	ret = pm_runtime_get_sync(dev);
+	if (IS_ERR_VALUE(ret))
+		return ret;
 
 	fep->mii_timeout = 0;
 	init_completion(&fep->mdio_done);
@@ -1811,10 +1831,13 @@
 	if (time_left == 0) {
 		fep->mii_timeout = 1;
 		netdev_err(fep->netdev, "MDIO write timeout\n");
-		return -ETIMEDOUT;
+		ret  = -ETIMEDOUT;
 	}
 
-	return 0;
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
+	return ret;
 }
 
 static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
@@ -1826,9 +1849,6 @@
 		ret = clk_prepare_enable(fep->clk_ahb);
 		if (ret)
 			return ret;
-		ret = clk_prepare_enable(fep->clk_ipg);
-		if (ret)
-			goto failed_clk_ipg;
 		if (fep->clk_enet_out) {
 			ret = clk_prepare_enable(fep->clk_enet_out);
 			if (ret)
@@ -1852,7 +1872,6 @@
 		}
 	} else {
 		clk_disable_unprepare(fep->clk_ahb);
-		clk_disable_unprepare(fep->clk_ipg);
 		if (fep->clk_enet_out)
 			clk_disable_unprepare(fep->clk_enet_out);
 		if (fep->clk_ptp) {
@@ -1874,8 +1893,6 @@
 	if (fep->clk_enet_out)
 		clk_disable_unprepare(fep->clk_enet_out);
 failed_clk_enet_out:
-		clk_disable_unprepare(fep->clk_ipg);
-failed_clk_ipg:
 		clk_disable_unprepare(fep->clk_ahb);
 
 	return ret;
@@ -2847,10 +2864,14 @@
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	int ret;
 
+	ret = pm_runtime_get_sync(&fep->pdev->dev);
+	if (IS_ERR_VALUE(ret))
+		return ret;
+
 	pinctrl_pm_select_default_state(&fep->pdev->dev);
 	ret = fec_enet_clk_enable(ndev, true);
 	if (ret)
-		return ret;
+		goto clk_enable;
 
 	/* I should reset the ring buffers here, but I don't yet know
 	 * a simple way to do that.
@@ -2881,6 +2902,9 @@
 	fec_enet_free_buffers(ndev);
 err_enet_alloc:
 	fec_enet_clk_enable(ndev, false);
+clk_enable:
+	pm_runtime_mark_last_busy(&fep->pdev->dev);
+	pm_runtime_put_autosuspend(&fep->pdev->dev);
 	pinctrl_pm_select_sleep_state(&fep->pdev->dev);
 	return ret;
 }
@@ -2903,6 +2927,9 @@
 
 	fec_enet_clk_enable(ndev, false);
 	pinctrl_pm_select_sleep_state(&fep->pdev->dev);
+	pm_runtime_mark_last_busy(&fep->pdev->dev);
+	pm_runtime_put_autosuspend(&fep->pdev->dev);
+
 	fec_enet_free_buffers(ndev);
 
 	return 0;
@@ -3115,8 +3142,8 @@
 			fep->bufdesc_size;
 
 	/* Allocate memory for buffer descriptors. */
-	cbd_base = dma_alloc_coherent(NULL, bd_size, &bd_dma,
-				      GFP_KERNEL);
+	cbd_base = dmam_alloc_coherent(&fep->pdev->dev, bd_size, &bd_dma,
+				       GFP_KERNEL);
 	if (!cbd_base) {
 		return -ENOMEM;
 	}
@@ -3388,6 +3415,10 @@
 	if (ret)
 		goto failed_clk;
 
+	ret = clk_prepare_enable(fep->clk_ipg);
+	if (ret)
+		goto failed_clk_ipg;
+
 	fep->reg_phy = devm_regulator_get(&pdev->dev, "phy");
 	if (!IS_ERR(fep->reg_phy)) {
 		ret = regulator_enable(fep->reg_phy);
@@ -3400,6 +3431,12 @@
 		fep->reg_phy = NULL;
 	}
 
+	pm_runtime_set_autosuspend_delay(&pdev->dev, FEC_MDIO_PM_TIMEOUT);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_get_noresume(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
 	fec_reset_phy(pdev);
 
 	if (fep->bufdesc_ex)
@@ -3447,6 +3484,10 @@
 
 	fep->rx_copybreak = COPYBREAK_DEFAULT;
 	INIT_WORK(&fep->tx_timeout_work, fec_enet_timeout_work);
+
+	pm_runtime_mark_last_busy(&pdev->dev);
+	pm_runtime_put_autosuspend(&pdev->dev);
+
 	return 0;
 
 failed_register:
@@ -3454,9 +3495,12 @@
 failed_mii_init:
 failed_irq:
 failed_init:
+	fec_ptp_stop(pdev);
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
 failed_regulator:
+	clk_disable_unprepare(fep->clk_ipg);
+failed_clk_ipg:
 	fec_enet_clk_enable(ndev, false);
 failed_clk:
 failed_phy:
@@ -3473,14 +3517,12 @@
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
-	cancel_delayed_work_sync(&fep->time_keep);
 	cancel_work_sync(&fep->tx_timeout_work);
+	fec_ptp_stop(pdev);
 	unregister_netdev(ndev);
 	fec_enet_mii_remove(fep);
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
-	if (fep->ptp_clock)
-		ptp_clock_unregister(fep->ptp_clock);
 	of_node_put(fep->phy_node);
 	free_netdev(ndev);
 
@@ -3568,7 +3610,28 @@
 	return ret;
 }
 
-static SIMPLE_DEV_PM_OPS(fec_pm_ops, fec_suspend, fec_resume);
+static int __maybe_unused fec_runtime_suspend(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	clk_disable_unprepare(fep->clk_ipg);
+
+	return 0;
+}
+
+static int __maybe_unused fec_runtime_resume(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	return clk_prepare_enable(fep->clk_ipg);
+}
+
+static const struct dev_pm_ops fec_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(fec_suspend, fec_resume)
+	SET_RUNTIME_PM_OPS(fec_runtime_suspend, fec_runtime_resume, NULL)
+};
 
 static struct platform_driver fec_driver = {
 	.driver	= {
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index a15663a..f457a23 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -604,6 +604,16 @@
 	schedule_delayed_work(&fep->time_keep, HZ);
 }
 
+void fec_ptp_stop(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	cancel_delayed_work_sync(&fep->time_keep);
+	if (fep->ptp_clock)
+		ptp_clock_unregister(fep->ptp_clock);
+}
+
 /**
  * fec_ptp_check_pps_event
  * @fep: the fec_enet_private structure handle
diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
index 56316db..cf8e546 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
+++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c
@@ -586,7 +586,8 @@
 	frag = skb_shinfo(skb)->frags;
 	while (nr_frags) {
 		CBDC_SC(bdp,
-			BD_ENET_TX_STATS | BD_ENET_TX_LAST | BD_ENET_TX_TC);
+			BD_ENET_TX_STATS | BD_ENET_TX_INTR | BD_ENET_TX_LAST |
+			BD_ENET_TX_TC);
 		CBDS_SC(bdp, BD_ENET_TX_READY);
 
 		if ((CBDR_SC(bdp) & BD_ENET_TX_WRAP) == 0)
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index b34214e..016743e 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -110,7 +110,7 @@
 }
 
 #define FEC_NAPI_RX_EVENT_MSK	(FEC_ENET_RXF | FEC_ENET_RXB)
-#define FEC_NAPI_TX_EVENT_MSK	(FEC_ENET_TXF | FEC_ENET_TXB)
+#define FEC_NAPI_TX_EVENT_MSK	(FEC_ENET_TXF)
 #define FEC_RX_EVENT		(FEC_ENET_RXF)
 #define FEC_TX_EVENT		(FEC_ENET_TXF)
 #define FEC_ERR_EVENT_MSK	(FEC_ENET_HBERR | FEC_ENET_BABR | \
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index ff87502..10b3bbbb 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -565,22 +565,6 @@
 	}
 }
 
-static void lock_tx_qs(struct gfar_private *priv)
-{
-	int i;
-
-	for (i = 0; i < priv->num_tx_queues; i++)
-		spin_lock(&priv->tx_queue[i]->txlock);
-}
-
-static void unlock_tx_qs(struct gfar_private *priv)
-{
-	int i;
-
-	for (i = 0; i < priv->num_tx_queues; i++)
-		spin_unlock(&priv->tx_queue[i]->txlock);
-}
-
 static int gfar_alloc_tx_queues(struct gfar_private *priv)
 {
 	int i;
@@ -1376,7 +1360,6 @@
 	priv->dev = &ofdev->dev;
 	SET_NETDEV_DEV(dev, &ofdev->dev);
 
-	spin_lock_init(&priv->bflock);
 	INIT_WORK(&priv->reset_task, gfar_reset_task);
 
 	platform_set_drvdata(ofdev, priv);
@@ -1470,9 +1453,8 @@
 		goto register_fail;
 	}
 
-	device_init_wakeup(&dev->dev,
-			   priv->device_flags &
-			   FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
+	device_set_wakeup_capable(&dev->dev, priv->device_flags &
+				  FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
 
 	/* fill out IRQ number and name fields */
 	for (i = 0; i < priv->num_grps; i++) {
@@ -1540,48 +1522,37 @@
 	struct gfar_private *priv = dev_get_drvdata(dev);
 	struct net_device *ndev = priv->ndev;
 	struct gfar __iomem *regs = priv->gfargrp[0].regs;
-	unsigned long flags;
 	u32 tempval;
-
 	int magic_packet = priv->wol_en &&
 			   (priv->device_flags &
 			    FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
 
+	if (!netif_running(ndev))
+		return 0;
+
+	disable_napi(priv);
+	netif_tx_lock(ndev);
 	netif_device_detach(ndev);
+	netif_tx_unlock(ndev);
 
-	if (netif_running(ndev)) {
+	gfar_halt(priv);
 
-		local_irq_save(flags);
-		lock_tx_qs(priv);
+	if (magic_packet) {
+		/* Enable interrupt on Magic Packet */
+		gfar_write(&regs->imask, IMASK_MAG);
 
-		gfar_halt_nodisable(priv);
+		/* Enable Magic Packet mode */
+		tempval = gfar_read(&regs->maccfg2);
+		tempval |= MACCFG2_MPEN;
+		gfar_write(&regs->maccfg2, tempval);
 
-		/* Disable Tx, and Rx if wake-on-LAN is disabled. */
+		/* re-enable the Rx block */
 		tempval = gfar_read(&regs->maccfg1);
-
-		tempval &= ~MACCFG1_TX_EN;
-
-		if (!magic_packet)
-			tempval &= ~MACCFG1_RX_EN;
-
+		tempval |= MACCFG1_RX_EN;
 		gfar_write(&regs->maccfg1, tempval);
 
-		unlock_tx_qs(priv);
-		local_irq_restore(flags);
-
-		disable_napi(priv);
-
-		if (magic_packet) {
-			/* Enable interrupt on Magic Packet */
-			gfar_write(&regs->imask, IMASK_MAG);
-
-			/* Enable Magic Packet mode */
-			tempval = gfar_read(&regs->maccfg2);
-			tempval |= MACCFG2_MPEN;
-			gfar_write(&regs->maccfg2, tempval);
-		} else {
-			phy_stop(priv->phydev);
-		}
+	} else {
+		phy_stop(priv->phydev);
 	}
 
 	return 0;
@@ -1592,37 +1563,26 @@
 	struct gfar_private *priv = dev_get_drvdata(dev);
 	struct net_device *ndev = priv->ndev;
 	struct gfar __iomem *regs = priv->gfargrp[0].regs;
-	unsigned long flags;
 	u32 tempval;
 	int magic_packet = priv->wol_en &&
 			   (priv->device_flags &
 			    FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
 
-	if (!netif_running(ndev)) {
-		netif_device_attach(ndev);
+	if (!netif_running(ndev))
 		return 0;
-	}
 
-	if (!magic_packet && priv->phydev)
+	if (magic_packet) {
+		/* Disable Magic Packet mode */
+		tempval = gfar_read(&regs->maccfg2);
+		tempval &= ~MACCFG2_MPEN;
+		gfar_write(&regs->maccfg2, tempval);
+	} else {
 		phy_start(priv->phydev);
-
-	/* Disable Magic Packet mode, in case something
-	 * else woke us up.
-	 */
-	local_irq_save(flags);
-	lock_tx_qs(priv);
-
-	tempval = gfar_read(&regs->maccfg2);
-	tempval &= ~MACCFG2_MPEN;
-	gfar_write(&regs->maccfg2, tempval);
+	}
 
 	gfar_start(priv);
 
-	unlock_tx_qs(priv);
-	local_irq_restore(flags);
-
 	netif_device_attach(ndev);
-
 	enable_napi(priv);
 
 	return 0;
@@ -2045,7 +2005,8 @@
 		/* Install our interrupt handlers for Error,
 		 * Transmit, and Receive
 		 */
-		err = request_irq(gfar_irq(grp, ER)->irq, gfar_error, 0,
+		err = request_irq(gfar_irq(grp, ER)->irq, gfar_error,
+				  IRQF_NO_SUSPEND,
 				  gfar_irq(grp, ER)->name, grp);
 		if (err < 0) {
 			netif_err(priv, intr, dev, "Can't get IRQ %d\n",
@@ -2068,7 +2029,8 @@
 			goto rx_irq_fail;
 		}
 	} else {
-		err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, 0,
+		err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt,
+				  IRQF_NO_SUSPEND,
 				  gfar_irq(grp, TX)->name, grp);
 		if (err < 0) {
 			netif_err(priv, intr, dev, "Can't get IRQ %d\n",
@@ -2140,6 +2102,11 @@
 	/* Start Rx/Tx DMA and enable the interrupts */
 	gfar_start(priv);
 
+	/* force link state update after mac reset */
+	priv->oldlink = 0;
+	priv->oldspeed = 0;
+	priv->oldduplex = -1;
+
 	phy_start(priv->phydev);
 
 	enable_napi(priv);
@@ -2169,8 +2136,6 @@
 	if (err)
 		return err;
 
-	device_set_wakeup_enable(&dev->dev, priv->wol_en);
-
 	return err;
 }
 
diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h
index daa1d37..5545e41 100644
--- a/drivers/net/ethernet/freescale/gianfar.h
+++ b/drivers/net/ethernet/freescale/gianfar.h
@@ -1145,9 +1145,6 @@
 	int oldduplex;
 	int oldlink;
 
-	/* Bitfield update lock */
-	spinlock_t bflock;
-
 	uint32_t msg_enable;
 
 	struct work_struct reset_task;
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index fda12fb..5b90fcf 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -653,7 +653,6 @@
 static int gfar_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct gfar_private *priv = netdev_priv(dev);
-	unsigned long flags;
 
 	if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) &&
 	    wol->wolopts != 0)
@@ -664,9 +663,7 @@
 
 	device_set_wakeup_enable(&dev->dev, wol->wolopts & WAKE_MAGIC);
 
-	spin_lock_irqsave(&priv->bflock, flags);
-	priv->wol_en =  !!device_may_wakeup(&dev->dev);
-	spin_unlock_irqrestore(&priv->bflock, flags);
+	priv->wol_en = !!device_may_wakeup(&dev->dev);
 
 	return 0;
 }
@@ -903,27 +900,6 @@
 	return 0;
 }
 
-static int gfar_comp_asc(const void *a, const void *b)
-{
-	return memcmp(a, b, 4);
-}
-
-static int gfar_comp_desc(const void *a, const void *b)
-{
-	return -memcmp(a, b, 4);
-}
-
-static void gfar_swap(void *a, void *b, int size)
-{
-	u32 *_a = a;
-	u32 *_b = b;
-
-	swap(_a[0], _b[0]);
-	swap(_a[1], _b[1]);
-	swap(_a[2], _b[2]);
-	swap(_a[3], _b[3]);
-}
-
 /* Write a mask to filer cache */
 static void gfar_set_mask(u32 mask, struct filer_table *tab)
 {
@@ -1273,310 +1249,6 @@
 	return 0;
 }
 
-/* Copy size filer entries */
-static void gfar_copy_filer_entries(struct gfar_filer_entry dst[0],
-				    struct gfar_filer_entry src[0], s32 size)
-{
-	while (size > 0) {
-		size--;
-		dst[size].ctrl = src[size].ctrl;
-		dst[size].prop = src[size].prop;
-	}
-}
-
-/* Delete the contents of the filer-table between start and end
- * and collapse them
- */
-static int gfar_trim_filer_entries(u32 begin, u32 end, struct filer_table *tab)
-{
-	int length;
-
-	if (end > MAX_FILER_CACHE_IDX || end < begin)
-		return -EINVAL;
-
-	end++;
-	length = end - begin;
-
-	/* Copy */
-	while (end < tab->index) {
-		tab->fe[begin].ctrl = tab->fe[end].ctrl;
-		tab->fe[begin++].prop = tab->fe[end++].prop;
-
-	}
-	/* Fill up with don't cares */
-	while (begin < tab->index) {
-		tab->fe[begin].ctrl = 0x60;
-		tab->fe[begin].prop = 0xFFFFFFFF;
-		begin++;
-	}
-
-	tab->index -= length;
-	return 0;
-}
-
-/* Make space on the wanted location */
-static int gfar_expand_filer_entries(u32 begin, u32 length,
-				     struct filer_table *tab)
-{
-	if (length == 0 || length + tab->index > MAX_FILER_CACHE_IDX ||
-	    begin > MAX_FILER_CACHE_IDX)
-		return -EINVAL;
-
-	gfar_copy_filer_entries(&(tab->fe[begin + length]), &(tab->fe[begin]),
-				tab->index - length + 1);
-
-	tab->index += length;
-	return 0;
-}
-
-static int gfar_get_next_cluster_start(int start, struct filer_table *tab)
-{
-	for (; (start < tab->index) && (start < MAX_FILER_CACHE_IDX - 1);
-	     start++) {
-		if ((tab->fe[start].ctrl & (RQFCR_AND | RQFCR_CLE)) ==
-		    (RQFCR_AND | RQFCR_CLE))
-			return start;
-	}
-	return -1;
-}
-
-static int gfar_get_next_cluster_end(int start, struct filer_table *tab)
-{
-	for (; (start < tab->index) && (start < MAX_FILER_CACHE_IDX - 1);
-	     start++) {
-		if ((tab->fe[start].ctrl & (RQFCR_AND | RQFCR_CLE)) ==
-		    (RQFCR_CLE))
-			return start;
-	}
-	return -1;
-}
-
-/* Uses hardwares clustering option to reduce
- * the number of filer table entries
- */
-static void gfar_cluster_filer(struct filer_table *tab)
-{
-	s32 i = -1, j, iend, jend;
-
-	while ((i = gfar_get_next_cluster_start(++i, tab)) != -1) {
-		j = i;
-		while ((j = gfar_get_next_cluster_start(++j, tab)) != -1) {
-			/* The cluster entries self and the previous one
-			 * (a mask) must be identical!
-			 */
-			if (tab->fe[i].ctrl != tab->fe[j].ctrl)
-				break;
-			if (tab->fe[i].prop != tab->fe[j].prop)
-				break;
-			if (tab->fe[i - 1].ctrl != tab->fe[j - 1].ctrl)
-				break;
-			if (tab->fe[i - 1].prop != tab->fe[j - 1].prop)
-				break;
-			iend = gfar_get_next_cluster_end(i, tab);
-			jend = gfar_get_next_cluster_end(j, tab);
-			if (jend == -1 || iend == -1)
-				break;
-
-			/* First we make some free space, where our cluster
-			 * element should be. Then we copy it there and finally
-			 * delete in from its old location.
-			 */
-			if (gfar_expand_filer_entries(iend, (jend - j), tab) ==
-			    -EINVAL)
-				break;
-
-			gfar_copy_filer_entries(&(tab->fe[iend + 1]),
-						&(tab->fe[jend + 1]), jend - j);
-
-			if (gfar_trim_filer_entries(jend - 1,
-						    jend + (jend - j),
-						    tab) == -EINVAL)
-				return;
-
-			/* Mask out cluster bit */
-			tab->fe[iend].ctrl &= ~(RQFCR_CLE);
-		}
-	}
-}
-
-/* Swaps the masked bits of a1<>a2 and b1<>b2 */
-static void gfar_swap_bits(struct gfar_filer_entry *a1,
-			   struct gfar_filer_entry *a2,
-			   struct gfar_filer_entry *b1,
-			   struct gfar_filer_entry *b2, u32 mask)
-{
-	u32 temp[4];
-	temp[0] = a1->ctrl & mask;
-	temp[1] = a2->ctrl & mask;
-	temp[2] = b1->ctrl & mask;
-	temp[3] = b2->ctrl & mask;
-
-	a1->ctrl &= ~mask;
-	a2->ctrl &= ~mask;
-	b1->ctrl &= ~mask;
-	b2->ctrl &= ~mask;
-
-	a1->ctrl |= temp[1];
-	a2->ctrl |= temp[0];
-	b1->ctrl |= temp[3];
-	b2->ctrl |= temp[2];
-}
-
-/* Generate a list consisting of masks values with their start and
- * end of validity and block as indicator for parts belonging
- * together (glued by ANDs) in mask_table
- */
-static u32 gfar_generate_mask_table(struct gfar_mask_entry *mask_table,
-				    struct filer_table *tab)
-{
-	u32 i, and_index = 0, block_index = 1;
-
-	for (i = 0; i < tab->index; i++) {
-
-		/* LSByte of control = 0 sets a mask */
-		if (!(tab->fe[i].ctrl & 0xF)) {
-			mask_table[and_index].mask = tab->fe[i].prop;
-			mask_table[and_index].start = i;
-			mask_table[and_index].block = block_index;
-			if (and_index >= 1)
-				mask_table[and_index - 1].end = i - 1;
-			and_index++;
-		}
-		/* cluster starts and ends will be separated because they should
-		 * hold their position
-		 */
-		if (tab->fe[i].ctrl & RQFCR_CLE)
-			block_index++;
-		/* A not set AND indicates the end of a depended block */
-		if (!(tab->fe[i].ctrl & RQFCR_AND))
-			block_index++;
-	}
-
-	mask_table[and_index - 1].end = i - 1;
-
-	return and_index;
-}
-
-/* Sorts the entries of mask_table by the values of the masks.
- * Important: The 0xFF80 flags of the first and last entry of a
- * block must hold their position (which queue, CLusterEnable, ReJEct,
- * AND)
- */
-static void gfar_sort_mask_table(struct gfar_mask_entry *mask_table,
-				 struct filer_table *temp_table, u32 and_index)
-{
-	/* Pointer to compare function (_asc or _desc) */
-	int (*gfar_comp)(const void *, const void *);
-
-	u32 i, size = 0, start = 0, prev = 1;
-	u32 old_first, old_last, new_first, new_last;
-
-	gfar_comp = &gfar_comp_desc;
-
-	for (i = 0; i < and_index; i++) {
-		if (prev != mask_table[i].block) {
-			old_first = mask_table[start].start + 1;
-			old_last = mask_table[i - 1].end;
-			sort(mask_table + start, size,
-			     sizeof(struct gfar_mask_entry),
-			     gfar_comp, &gfar_swap);
-
-			/* Toggle order for every block. This makes the
-			 * thing more efficient!
-			 */
-			if (gfar_comp == gfar_comp_desc)
-				gfar_comp = &gfar_comp_asc;
-			else
-				gfar_comp = &gfar_comp_desc;
-
-			new_first = mask_table[start].start + 1;
-			new_last = mask_table[i - 1].end;
-
-			gfar_swap_bits(&temp_table->fe[new_first],
-				       &temp_table->fe[old_first],
-				       &temp_table->fe[new_last],
-				       &temp_table->fe[old_last],
-				       RQFCR_QUEUE | RQFCR_CLE |
-				       RQFCR_RJE | RQFCR_AND);
-
-			start = i;
-			size = 0;
-		}
-		size++;
-		prev = mask_table[i].block;
-	}
-}
-
-/* Reduces the number of masks needed in the filer table to save entries
- * This is done by sorting the masks of a depended block. A depended block is
- * identified by gluing ANDs or CLE. The sorting order toggles after every
- * block. Of course entries in scope of a mask must change their location with
- * it.
- */
-static int gfar_optimize_filer_masks(struct filer_table *tab)
-{
-	struct filer_table *temp_table;
-	struct gfar_mask_entry *mask_table;
-
-	u32 and_index = 0, previous_mask = 0, i = 0, j = 0, size = 0;
-	s32 ret = 0;
-
-	/* We need a copy of the filer table because
-	 * we want to change its order
-	 */
-	temp_table = kmemdup(tab, sizeof(*temp_table), GFP_KERNEL);
-	if (temp_table == NULL)
-		return -ENOMEM;
-
-	mask_table = kcalloc(MAX_FILER_CACHE_IDX / 2 + 1,
-			     sizeof(struct gfar_mask_entry), GFP_KERNEL);
-
-	if (mask_table == NULL) {
-		ret = -ENOMEM;
-		goto end;
-	}
-
-	and_index = gfar_generate_mask_table(mask_table, tab);
-
-	gfar_sort_mask_table(mask_table, temp_table, and_index);
-
-	/* Now we can copy the data from our duplicated filer table to
-	 * the real one in the order the mask table says
-	 */
-	for (i = 0; i < and_index; i++) {
-		size = mask_table[i].end - mask_table[i].start + 1;
-		gfar_copy_filer_entries(&(tab->fe[j]),
-				&(temp_table->fe[mask_table[i].start]), size);
-		j += size;
-	}
-
-	/* And finally we just have to check for duplicated masks and drop the
-	 * second ones
-	 */
-	for (i = 0; i < tab->index && i < MAX_FILER_CACHE_IDX; i++) {
-		if (tab->fe[i].ctrl == 0x80) {
-			previous_mask = i++;
-			break;
-		}
-	}
-	for (; i < tab->index && i < MAX_FILER_CACHE_IDX; i++) {
-		if (tab->fe[i].ctrl == 0x80) {
-			if (tab->fe[i].prop == tab->fe[previous_mask].prop) {
-				/* Two identical ones found!
-				 * So drop the second one!
-				 */
-				gfar_trim_filer_entries(i, i, tab);
-			} else
-				/* Not identical! */
-				previous_mask = i;
-		}
-	}
-
-	kfree(mask_table);
-end:	kfree(temp_table);
-	return ret;
-}
-
 /* Write the bit-pattern from software's buffer to hardware registers */
 static int gfar_write_filer_table(struct gfar_private *priv,
 				  struct filer_table *tab)
@@ -1586,11 +1258,10 @@
 		return -EBUSY;
 
 	/* Fill regular entries */
-	for (; i < MAX_FILER_IDX - 1 && (tab->fe[i].ctrl | tab->fe[i].prop);
-	     i++)
+	for (; i < MAX_FILER_IDX && (tab->fe[i].ctrl | tab->fe[i].prop); i++)
 		gfar_write_filer(priv, i, tab->fe[i].ctrl, tab->fe[i].prop);
 	/* Fill the rest with fall-troughs */
-	for (; i < MAX_FILER_IDX - 1; i++)
+	for (; i < MAX_FILER_IDX; i++)
 		gfar_write_filer(priv, i, 0x60, 0xFFFFFFFF);
 	/* Last entry must be default accept
 	 * because that's what people expect
@@ -1624,7 +1295,6 @@
 {
 	struct ethtool_flow_spec_container *j;
 	struct filer_table *tab;
-	s32 i = 0;
 	s32 ret = 0;
 
 	/* So index is set to zero, too! */
@@ -1649,17 +1319,6 @@
 		}
 	}
 
-	i = tab->index;
-
-	/* Optimizations to save entries */
-	gfar_cluster_filer(tab);
-	gfar_optimize_filer_masks(tab);
-
-	pr_debug("\tSummary:\n"
-		 "\tData on hardware: %d\n"
-		 "\tCompression rate: %d%%\n",
-		 tab->index, 100 - (100 * tab->index) / i);
-
 	/* Write everything to hardware */
 	ret = gfar_write_filer_table(priv, tab);
 	if (ret == -EBUSY) {
@@ -1725,13 +1384,14 @@
 	}
 
 process:
+	priv->rx_list.count++;
 	ret = gfar_process_filer_changes(priv);
 	if (ret)
 		goto clean_list;
-	priv->rx_list.count++;
 	return ret;
 
 clean_list:
+	priv->rx_list.count--;
 	list_del(&temp->list);
 clean_mem:
 	kfree(temp);
diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
index 982fdcd..b5b2925 100644
--- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c
+++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c
@@ -216,7 +216,7 @@
 
 static inline bool fm10k_page_is_reserved(struct page *page)
 {
-	return (page_to_nid(page) != numa_mem_id()) || page->pfmemalloc;
+	return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page);
 }
 
 static bool fm10k_can_reuse_rx_page(struct fm10k_rx_buffer *rx_buffer,
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 2f70a9b..830466c 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -6566,7 +6566,7 @@
 
 static inline bool igb_page_is_reserved(struct page *page)
 {
-	return (page_to_nid(page) != numa_mem_id()) || page->pfmemalloc;
+	return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page);
 }
 
 static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 9aa6104..ae21e0b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -1832,7 +1832,7 @@
 
 static inline bool ixgbe_page_is_reserved(struct page *page)
 {
-	return (page_to_nid(page) != numa_mem_id()) || page->pfmemalloc;
+	return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index e71cdde..1d7b00b 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -765,7 +765,7 @@
 
 static inline bool ixgbevf_page_is_reserved(struct page *page)
 {
-	return (page_to_nid(page) != numa_mem_id()) || page->pfmemalloc;
+	return (page_to_nid(page) != numa_mem_id()) || page_is_pfmemalloc(page);
 }
 
 /**
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 370e20ed..62e48bc 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1462,7 +1462,7 @@
 		     struct mvneta_rx_queue *rxq)
 {
 	struct net_device *dev = pp->dev;
-	int rx_done, rx_filled;
+	int rx_done;
 	u32 rcvd_pkts = 0;
 	u32 rcvd_bytes = 0;
 
@@ -1473,7 +1473,6 @@
 		rx_todo = rx_done;
 
 	rx_done = 0;
-	rx_filled = 0;
 
 	/* Fairness NAPI loop */
 	while (rx_done < rx_todo) {
@@ -1484,7 +1483,6 @@
 		int rx_bytes, err;
 
 		rx_done++;
-		rx_filled++;
 		rx_status = rx_desc->status;
 		rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
 		data = (unsigned char *)rx_desc->buf_cookie;
@@ -1524,6 +1522,14 @@
 			continue;
 		}
 
+		/* Refill processing */
+		err = mvneta_rx_refill(pp, rx_desc);
+		if (err) {
+			netdev_err(dev, "Linux processing - Can't refill\n");
+			rxq->missed++;
+			goto err_drop_frame;
+		}
+
 		skb = build_skb(data, pp->frag_size > PAGE_SIZE ? 0 : pp->frag_size);
 		if (!skb)
 			goto err_drop_frame;
@@ -1543,14 +1549,6 @@
 		mvneta_rx_csum(pp, rx_status, skb);
 
 		napi_gro_receive(&pp->napi, skb);
-
-		/* Refill processing */
-		err = mvneta_rx_refill(pp, rx_desc);
-		if (err) {
-			netdev_err(dev, "Linux processing - Can't refill\n");
-			rxq->missed++;
-			rx_filled--;
-		}
 	}
 
 	if (rcvd_pkts) {
@@ -1563,7 +1561,7 @@
 	}
 
 	/* Update rxq management counters */
-	mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_filled);
+	mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_done);
 
 	return rx_done;
 }
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index 3e8b1bf..d9884fd 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -27,6 +27,8 @@
 #include <linux/of_address.h>
 #include <linux/phy.h>
 #include <linux/clk.h>
+#include <linux/hrtimer.h>
+#include <linux/ktime.h>
 #include <uapi/linux/ppp_defs.h>
 #include <net/ip.h>
 #include <net/ipv6.h>
@@ -299,6 +301,7 @@
 
 /* Coalescing */
 #define MVPP2_TXDONE_COAL_PKTS_THRESH	15
+#define MVPP2_TXDONE_HRTIMER_PERIOD_NS	1000000UL
 #define MVPP2_RX_COAL_PKTS		32
 #define MVPP2_RX_COAL_USEC		100
 
@@ -660,6 +663,14 @@
 	u64	tx_bytes;
 };
 
+/* Per-CPU port control */
+struct mvpp2_port_pcpu {
+	struct hrtimer tx_done_timer;
+	bool timer_scheduled;
+	/* Tasklet for egress finalization */
+	struct tasklet_struct tx_done_tasklet;
+};
+
 struct mvpp2_port {
 	u8 id;
 
@@ -679,6 +690,9 @@
 	u32 pending_cause_rx;
 	struct napi_struct napi;
 
+	/* Per-CPU port control */
+	struct mvpp2_port_pcpu __percpu *pcpu;
+
 	/* Flags */
 	unsigned long flags;
 
@@ -776,6 +790,9 @@
 	/* Array of transmitted skb */
 	struct sk_buff **tx_skb;
 
+	/* Array of transmitted buffers' physical addresses */
+	dma_addr_t *tx_buffs;
+
 	/* Index of last TX DMA descriptor that was inserted */
 	int txq_put_index;
 
@@ -913,8 +930,6 @@
 	/* Occupied buffers indicator */
 	atomic_t in_use;
 	int in_use_thresh;
-
-	spinlock_t lock;
 };
 
 struct mvpp2_buff_hdr {
@@ -963,9 +978,13 @@
 }
 
 static void mvpp2_txq_inc_put(struct mvpp2_txq_pcpu *txq_pcpu,
-			      struct sk_buff *skb)
+			      struct sk_buff *skb,
+			      struct mvpp2_tx_desc *tx_desc)
 {
 	txq_pcpu->tx_skb[txq_pcpu->txq_put_index] = skb;
+	if (skb)
+		txq_pcpu->tx_buffs[txq_pcpu->txq_put_index] =
+							 tx_desc->buf_phys_addr;
 	txq_pcpu->txq_put_index++;
 	if (txq_pcpu->txq_put_index == txq_pcpu->size)
 		txq_pcpu->txq_put_index = 0;
@@ -3376,7 +3395,6 @@
 	bm_pool->pkt_size = 0;
 	bm_pool->buf_num = 0;
 	atomic_set(&bm_pool->in_use, 0);
-	spin_lock_init(&bm_pool->lock);
 
 	return 0;
 }
@@ -3647,7 +3665,6 @@
 mvpp2_bm_pool_use(struct mvpp2_port *port, int pool, enum mvpp2_bm_type type,
 		  int pkt_size)
 {
-	unsigned long flags = 0;
 	struct mvpp2_bm_pool *new_pool = &port->priv->bm_pools[pool];
 	int num;
 
@@ -3656,8 +3673,6 @@
 		return NULL;
 	}
 
-	spin_lock_irqsave(&new_pool->lock, flags);
-
 	if (new_pool->type == MVPP2_BM_FREE)
 		new_pool->type = type;
 
@@ -3686,8 +3701,6 @@
 		if (num != pkts_num) {
 			WARN(1, "pool %d: %d of %d allocated\n",
 			     new_pool->id, num, pkts_num);
-			/* We need to undo the bufs_add() allocations */
-			spin_unlock_irqrestore(&new_pool->lock, flags);
 			return NULL;
 		}
 	}
@@ -3695,15 +3708,12 @@
 	mvpp2_bm_pool_bufsize_set(port->priv, new_pool,
 				  MVPP2_RX_BUF_SIZE(new_pool->pkt_size));
 
-	spin_unlock_irqrestore(&new_pool->lock, flags);
-
 	return new_pool;
 }
 
 /* Initialize pools for swf */
 static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port)
 {
-	unsigned long flags = 0;
 	int rxq;
 
 	if (!port->pool_long) {
@@ -3714,9 +3724,7 @@
 		if (!port->pool_long)
 			return -ENOMEM;
 
-		spin_lock_irqsave(&port->pool_long->lock, flags);
 		port->pool_long->port_map |= (1 << port->id);
-		spin_unlock_irqrestore(&port->pool_long->lock, flags);
 
 		for (rxq = 0; rxq < rxq_number; rxq++)
 			mvpp2_rxq_long_pool_set(port, rxq, port->pool_long->id);
@@ -3730,9 +3738,7 @@
 		if (!port->pool_short)
 			return -ENOMEM;
 
-		spin_lock_irqsave(&port->pool_short->lock, flags);
 		port->pool_short->port_map |= (1 << port->id);
-		spin_unlock_irqrestore(&port->pool_short->lock, flags);
 
 		for (rxq = 0; rxq < rxq_number; rxq++)
 			mvpp2_rxq_short_pool_set(port, rxq,
@@ -3806,7 +3812,6 @@
 
 	mvpp2_write(port->priv, MVPP2_ISR_RX_TX_MASK_REG(port->id),
 		    (MVPP2_CAUSE_MISC_SUM_MASK |
-		     MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK |
 		     MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK));
 }
 
@@ -4382,23 +4387,6 @@
 	rxq->time_coal = usec;
 }
 
-/* Set threshold for TX_DONE pkts coalescing */
-static void mvpp2_tx_done_pkts_coal_set(void *arg)
-{
-	struct mvpp2_port *port = arg;
-	int queue;
-	u32 val;
-
-	for (queue = 0; queue < txq_number; queue++) {
-		struct mvpp2_tx_queue *txq = port->txqs[queue];
-
-		val = (txq->done_pkts_coal << MVPP2_TRANSMITTED_THRESH_OFFSET) &
-		       MVPP2_TRANSMITTED_THRESH_MASK;
-		mvpp2_write(port->priv, MVPP2_TXQ_NUM_REG, txq->id);
-		mvpp2_write(port->priv, MVPP2_TXQ_THRESH_REG, val);
-	}
-}
-
 /* Free Tx queue skbuffs */
 static void mvpp2_txq_bufs_free(struct mvpp2_port *port,
 				struct mvpp2_tx_queue *txq,
@@ -4407,8 +4395,8 @@
 	int i;
 
 	for (i = 0; i < num; i++) {
-		struct mvpp2_tx_desc *tx_desc = txq->descs +
-							txq_pcpu->txq_get_index;
+		dma_addr_t buf_phys_addr =
+				    txq_pcpu->tx_buffs[txq_pcpu->txq_get_index];
 		struct sk_buff *skb = txq_pcpu->tx_skb[txq_pcpu->txq_get_index];
 
 		mvpp2_txq_inc_get(txq_pcpu);
@@ -4416,8 +4404,8 @@
 		if (!skb)
 			continue;
 
-		dma_unmap_single(port->dev->dev.parent, tx_desc->buf_phys_addr,
-				 tx_desc->data_size, DMA_TO_DEVICE);
+		dma_unmap_single(port->dev->dev.parent, buf_phys_addr,
+				 skb_headlen(skb), DMA_TO_DEVICE);
 		dev_kfree_skb_any(skb);
 	}
 }
@@ -4433,7 +4421,7 @@
 static inline struct mvpp2_tx_queue *mvpp2_get_tx_queue(struct mvpp2_port *port,
 							u32 cause)
 {
-	int queue = fls(cause >> 16) - 1;
+	int queue = fls(cause) - 1;
 
 	return port->txqs[queue];
 }
@@ -4460,6 +4448,29 @@
 			netif_tx_wake_queue(nq);
 }
 
+static unsigned int mvpp2_tx_done(struct mvpp2_port *port, u32 cause)
+{
+	struct mvpp2_tx_queue *txq;
+	struct mvpp2_txq_pcpu *txq_pcpu;
+	unsigned int tx_todo = 0;
+
+	while (cause) {
+		txq = mvpp2_get_tx_queue(port, cause);
+		if (!txq)
+			break;
+
+		txq_pcpu = this_cpu_ptr(txq->pcpu);
+
+		if (txq_pcpu->count) {
+			mvpp2_txq_done(port, txq, txq_pcpu);
+			tx_todo += txq_pcpu->count;
+		}
+
+		cause &= ~(1 << txq->log_id);
+	}
+	return tx_todo;
+}
+
 /* Rx/Tx queue initialization/cleanup methods */
 
 /* Allocate and initialize descriptors for aggr TXQ */
@@ -4649,12 +4660,13 @@
 		txq_pcpu->tx_skb = kmalloc(txq_pcpu->size *
 					   sizeof(*txq_pcpu->tx_skb),
 					   GFP_KERNEL);
-		if (!txq_pcpu->tx_skb) {
-			dma_free_coherent(port->dev->dev.parent,
-					  txq->size * MVPP2_DESC_ALIGNED_SIZE,
-					  txq->descs, txq->descs_phys);
-			return -ENOMEM;
-		}
+		if (!txq_pcpu->tx_skb)
+			goto error;
+
+		txq_pcpu->tx_buffs = kmalloc(txq_pcpu->size *
+					     sizeof(dma_addr_t), GFP_KERNEL);
+		if (!txq_pcpu->tx_buffs)
+			goto error;
 
 		txq_pcpu->count = 0;
 		txq_pcpu->reserved_num = 0;
@@ -4663,6 +4675,19 @@
 	}
 
 	return 0;
+
+error:
+	for_each_present_cpu(cpu) {
+		txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
+		kfree(txq_pcpu->tx_skb);
+		kfree(txq_pcpu->tx_buffs);
+	}
+
+	dma_free_coherent(port->dev->dev.parent,
+			  txq->size * MVPP2_DESC_ALIGNED_SIZE,
+			  txq->descs, txq->descs_phys);
+
+	return -ENOMEM;
 }
 
 /* Free allocated TXQ resources */
@@ -4675,6 +4700,7 @@
 	for_each_present_cpu(cpu) {
 		txq_pcpu = per_cpu_ptr(txq->pcpu, cpu);
 		kfree(txq_pcpu->tx_skb);
+		kfree(txq_pcpu->tx_buffs);
 	}
 
 	if (txq->descs)
@@ -4805,7 +4831,6 @@
 			goto err_cleanup;
 	}
 
-	on_each_cpu(mvpp2_tx_done_pkts_coal_set, port, 1);
 	on_each_cpu(mvpp2_txq_sent_counter_clear, port, 1);
 	return 0;
 
@@ -4887,6 +4912,49 @@
 	}
 }
 
+static void mvpp2_timer_set(struct mvpp2_port_pcpu *port_pcpu)
+{
+	ktime_t interval;
+
+	if (!port_pcpu->timer_scheduled) {
+		port_pcpu->timer_scheduled = true;
+		interval = ktime_set(0, MVPP2_TXDONE_HRTIMER_PERIOD_NS);
+		hrtimer_start(&port_pcpu->tx_done_timer, interval,
+			      HRTIMER_MODE_REL_PINNED);
+	}
+}
+
+static void mvpp2_tx_proc_cb(unsigned long data)
+{
+	struct net_device *dev = (struct net_device *)data;
+	struct mvpp2_port *port = netdev_priv(dev);
+	struct mvpp2_port_pcpu *port_pcpu = this_cpu_ptr(port->pcpu);
+	unsigned int tx_todo, cause;
+
+	if (!netif_running(dev))
+		return;
+	port_pcpu->timer_scheduled = false;
+
+	/* Process all the Tx queues */
+	cause = (1 << txq_number) - 1;
+	tx_todo = mvpp2_tx_done(port, cause);
+
+	/* Set the timer in case not all the packets were processed */
+	if (tx_todo)
+		mvpp2_timer_set(port_pcpu);
+}
+
+static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer)
+{
+	struct mvpp2_port_pcpu *port_pcpu = container_of(timer,
+							 struct mvpp2_port_pcpu,
+							 tx_done_timer);
+
+	tasklet_schedule(&port_pcpu->tx_done_tasklet);
+
+	return HRTIMER_NORESTART;
+}
+
 /* Main RX/TX processing routines */
 
 /* Display more error info */
@@ -5144,11 +5212,11 @@
 		if (i == (skb_shinfo(skb)->nr_frags - 1)) {
 			/* Last descriptor */
 			tx_desc->command = MVPP2_TXD_L_DESC;
-			mvpp2_txq_inc_put(txq_pcpu, skb);
+			mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc);
 		} else {
 			/* Descriptor in the middle: Not First, Not Last */
 			tx_desc->command = 0;
-			mvpp2_txq_inc_put(txq_pcpu, NULL);
+			mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc);
 		}
 	}
 
@@ -5214,12 +5282,12 @@
 		/* First and Last descriptor */
 		tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_L_DESC;
 		tx_desc->command = tx_cmd;
-		mvpp2_txq_inc_put(txq_pcpu, skb);
+		mvpp2_txq_inc_put(txq_pcpu, skb, tx_desc);
 	} else {
 		/* First but not Last */
 		tx_cmd |= MVPP2_TXD_F_DESC | MVPP2_TXD_PADDING_DISABLE;
 		tx_desc->command = tx_cmd;
-		mvpp2_txq_inc_put(txq_pcpu, NULL);
+		mvpp2_txq_inc_put(txq_pcpu, NULL, tx_desc);
 
 		/* Continue with other skb fragments */
 		if (mvpp2_tx_frag_process(port, skb, aggr_txq, txq)) {
@@ -5255,6 +5323,17 @@
 		dev_kfree_skb_any(skb);
 	}
 
+	/* Finalize TX processing */
+	if (txq_pcpu->count >= txq->done_pkts_coal)
+		mvpp2_txq_done(port, txq, txq_pcpu);
+
+	/* Set the timer in case not all frags were processed */
+	if (txq_pcpu->count <= frags && txq_pcpu->count > 0) {
+		struct mvpp2_port_pcpu *port_pcpu = this_cpu_ptr(port->pcpu);
+
+		mvpp2_timer_set(port_pcpu);
+	}
+
 	return NETDEV_TX_OK;
 }
 
@@ -5268,10 +5347,11 @@
 		netdev_err(dev, "tx fifo underrun error\n");
 }
 
-static void mvpp2_txq_done_percpu(void *arg)
+static int mvpp2_poll(struct napi_struct *napi, int budget)
 {
-	struct mvpp2_port *port = arg;
-	u32 cause_rx_tx, cause_tx, cause_misc;
+	u32 cause_rx_tx, cause_rx, cause_misc;
+	int rx_done = 0;
+	struct mvpp2_port *port = netdev_priv(napi->dev);
 
 	/* Rx/Tx cause register
 	 *
@@ -5285,7 +5365,7 @@
 	 */
 	cause_rx_tx = mvpp2_read(port->priv,
 				 MVPP2_ISR_RX_TX_CAUSE_REG(port->id));
-	cause_tx = cause_rx_tx & MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK;
+	cause_rx_tx &= ~MVPP2_CAUSE_TXQ_OCCUP_DESC_ALL_MASK;
 	cause_misc = cause_rx_tx & MVPP2_CAUSE_MISC_SUM_MASK;
 
 	if (cause_misc) {
@@ -5297,26 +5377,6 @@
 			    cause_rx_tx & ~MVPP2_CAUSE_MISC_SUM_MASK);
 	}
 
-	/* Release TX descriptors */
-	if (cause_tx) {
-		struct mvpp2_tx_queue *txq = mvpp2_get_tx_queue(port, cause_tx);
-		struct mvpp2_txq_pcpu *txq_pcpu = this_cpu_ptr(txq->pcpu);
-
-		if (txq_pcpu->count)
-			mvpp2_txq_done(port, txq, txq_pcpu);
-	}
-}
-
-static int mvpp2_poll(struct napi_struct *napi, int budget)
-{
-	u32 cause_rx_tx, cause_rx;
-	int rx_done = 0;
-	struct mvpp2_port *port = netdev_priv(napi->dev);
-
-	on_each_cpu(mvpp2_txq_done_percpu, port, 1);
-
-	cause_rx_tx = mvpp2_read(port->priv,
-				 MVPP2_ISR_RX_TX_CAUSE_REG(port->id));
 	cause_rx = cause_rx_tx & MVPP2_CAUSE_RXQ_OCCUP_DESC_ALL_MASK;
 
 	/* Process RX packets */
@@ -5561,6 +5621,8 @@
 static int mvpp2_stop(struct net_device *dev)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
+	struct mvpp2_port_pcpu *port_pcpu;
+	int cpu;
 
 	mvpp2_stop_dev(port);
 	mvpp2_phy_disconnect(port);
@@ -5569,6 +5631,13 @@
 	on_each_cpu(mvpp2_interrupts_mask, port, 1);
 
 	free_irq(port->irq, port);
+	for_each_present_cpu(cpu) {
+		port_pcpu = per_cpu_ptr(port->pcpu, cpu);
+
+		hrtimer_cancel(&port_pcpu->tx_done_timer);
+		port_pcpu->timer_scheduled = false;
+		tasklet_kill(&port_pcpu->tx_done_tasklet);
+	}
 	mvpp2_cleanup_rxqs(port);
 	mvpp2_cleanup_txqs(port);
 
@@ -5784,7 +5853,6 @@
 		txq->done_pkts_coal = c->tx_max_coalesced_frames;
 	}
 
-	on_each_cpu(mvpp2_tx_done_pkts_coal_set, port, 1);
 	return 0;
 }
 
@@ -6035,6 +6103,7 @@
 {
 	struct device_node *phy_node;
 	struct mvpp2_port *port;
+	struct mvpp2_port_pcpu *port_pcpu;
 	struct net_device *dev;
 	struct resource *res;
 	const char *dt_mac_addr;
@@ -6044,7 +6113,7 @@
 	int features;
 	int phy_mode;
 	int priv_common_regs_num = 2;
-	int err, i;
+	int err, i, cpu;
 
 	dev = alloc_etherdev_mqs(sizeof(struct mvpp2_port), txq_number,
 				 rxq_number);
@@ -6135,6 +6204,24 @@
 	}
 	mvpp2_port_power_up(port);
 
+	port->pcpu = alloc_percpu(struct mvpp2_port_pcpu);
+	if (!port->pcpu) {
+		err = -ENOMEM;
+		goto err_free_txq_pcpu;
+	}
+
+	for_each_present_cpu(cpu) {
+		port_pcpu = per_cpu_ptr(port->pcpu, cpu);
+
+		hrtimer_init(&port_pcpu->tx_done_timer, CLOCK_MONOTONIC,
+			     HRTIMER_MODE_REL_PINNED);
+		port_pcpu->tx_done_timer.function = mvpp2_hr_timer_cb;
+		port_pcpu->timer_scheduled = false;
+
+		tasklet_init(&port_pcpu->tx_done_tasklet, mvpp2_tx_proc_cb,
+			     (unsigned long)dev);
+	}
+
 	netif_napi_add(dev, &port->napi, mvpp2_poll, NAPI_POLL_WEIGHT);
 	features = NETIF_F_SG | NETIF_F_IP_CSUM;
 	dev->features = features | NETIF_F_RXCSUM;
@@ -6144,7 +6231,7 @@
 	err = register_netdev(dev);
 	if (err < 0) {
 		dev_err(&pdev->dev, "failed to register netdev\n");
-		goto err_free_txq_pcpu;
+		goto err_free_port_pcpu;
 	}
 	netdev_info(dev, "Using %s mac address %pM\n", mac_from, dev->dev_addr);
 
@@ -6153,6 +6240,8 @@
 	priv->port_list[id] = port;
 	return 0;
 
+err_free_port_pcpu:
+	free_percpu(port->pcpu);
 err_free_txq_pcpu:
 	for (i = 0; i < txq_number; i++)
 		free_percpu(port->txqs[i]->pcpu);
@@ -6171,6 +6260,7 @@
 	int i;
 
 	unregister_netdev(port->dev);
+	free_percpu(port->pcpu);
 	free_percpu(port->stats);
 	for (i = 0; i < txq_number; i++)
 		free_percpu(port->txqs[i]->pcpu);
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 8204013..0a32020 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -686,6 +686,7 @@
 {
 	struct mlx4_cmd *cmd = &mlx4_priv(dev)->cmd;
 	struct mlx4_cmd_context *context;
+	long ret_wait;
 	int err = 0;
 
 	down(&cmd->event_sem);
@@ -711,8 +712,20 @@
 	if (err)
 		goto out_reset;
 
-	if (!wait_for_completion_timeout(&context->done,
-					 msecs_to_jiffies(timeout))) {
+	if (op == MLX4_CMD_SENSE_PORT) {
+		ret_wait =
+			wait_for_completion_interruptible_timeout(&context->done,
+								  msecs_to_jiffies(timeout));
+		if (ret_wait < 0) {
+			context->fw_status = 0;
+			context->out_param = 0;
+			context->result = 0;
+		}
+	} else {
+		ret_wait = (long)wait_for_completion_timeout(&context->done,
+							     msecs_to_jiffies(timeout));
+	}
+	if (!ret_wait) {
 		mlx4_warn(dev, "command 0x%x timed out (go bit not cleared)\n",
 			  op);
 		if (op == MLX4_CMD_NOP) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 7a4f20b..9c145dd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -246,7 +246,6 @@
 
 static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring)
 {
-	BUG_ON((u32)(ring->prod - ring->cons) > ring->actual_size);
 	return ring->prod == ring->cons;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index aae13ad..8e81e53 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -601,7 +601,7 @@
 							continue;
 						mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN to slave: %d, port:%d\n",
 							 __func__, i, port);
-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
 							eqe->event.port_change.port =
 								cpu_to_be32(
@@ -640,7 +640,7 @@
 							continue;
 						if (i == mlx4_master_func_num(dev))
 							continue;
-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
 							eqe->event.port_change.port =
 								cpu_to_be32(
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 12fbfcb..29c2a01 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2273,6 +2273,11 @@
 		} else if (err == -ENOENT) {
 			err = 0;
 			continue;
+		} else if (mlx4_is_slave(dev) && err == -EINVAL) {
+			priv->def_counter[port] = MLX4_SINK_COUNTER_INDEX(dev);
+			mlx4_warn(dev, "can't allocate counter from old PF driver, using index %d\n",
+				  MLX4_SINK_COUNTER_INDEX(dev));
+			err = 0;
 		} else {
 			mlx4_err(dev, "%s: failed to allocate default counter port %d err %d\n",
 				 __func__, port + 1, err);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index afad529..06e3e1e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -391,6 +391,8 @@
 	/* disable cmdif checksum */
 	MLX5_SET(cmd_hca_cap, set_hca_cap, cmdif_checksum, 0);
 
+	MLX5_SET(cmd_hca_cap, set_hca_cap, log_uar_page_sz, PAGE_SHIFT - 12);
+
 	err = set_caps(dev, set_ctx, set_sz);
 
 query_ex:
diff --git a/drivers/net/ethernet/micrel/ks8842.c b/drivers/net/ethernet/micrel/ks8842.c
index f78909a..09d2e16 100644
--- a/drivers/net/ethernet/micrel/ks8842.c
+++ b/drivers/net/ethernet/micrel/ks8842.c
@@ -952,9 +952,8 @@
 
 	sg_dma_address(&tx_ctl->sg) = dma_map_single(adapter->dev,
 		tx_ctl->buf, DMA_BUFFER_SIZE, DMA_TO_DEVICE);
-	err = dma_mapping_error(adapter->dev,
-		sg_dma_address(&tx_ctl->sg));
-	if (err) {
+	if (dma_mapping_error(adapter->dev, sg_dma_address(&tx_ctl->sg))) {
+		err = -ENOMEM;
 		sg_dma_address(&tx_ctl->sg) = 0;
 		goto err;
 	}
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index 33669c2..753ea8b 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -1415,7 +1415,7 @@
 	if (fw->size & 0xF) {
 		addr = dest + size;
 		for (i = 0; i < (fw->size & 0xF); i++)
-			data[i] = temp[size + i];
+			data[i] = ((u8 *)temp)[size + i];
 		for (; i < 16; i++)
 			data[i] = 0;
 		ret = qlcnic_ms_mem_write128(adapter, addr,
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 3df51fa..f790f61 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -4875,10 +4875,12 @@
 	case RTL_GIGA_MAC_VER_46:
 	case RTL_GIGA_MAC_VER_47:
 	case RTL_GIGA_MAC_VER_48:
+		RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF);
+		break;
 	case RTL_GIGA_MAC_VER_49:
 	case RTL_GIGA_MAC_VER_50:
 	case RTL_GIGA_MAC_VER_51:
-		RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST | RX_EARLY_OFF);
+		RTL_W32(RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF);
 		break;
 	default:
 		RTL_W32(RxConfig, RX128_INT_EN | RX_DMA_BURST);
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index fd97457..78849dd 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -228,9 +228,7 @@
 	struct ravb_desc *desc = NULL;
 	int rx_ring_size = sizeof(*rx_desc) * priv->num_rx_ring[q];
 	int tx_ring_size = sizeof(*tx_desc) * priv->num_tx_ring[q];
-	struct sk_buff *skb;
 	dma_addr_t dma_addr;
-	void *buffer;
 	int i;
 
 	priv->cur_rx[q] = 0;
@@ -241,41 +239,28 @@
 	memset(priv->rx_ring[q], 0, rx_ring_size);
 	/* Build RX ring buffer */
 	for (i = 0; i < priv->num_rx_ring[q]; i++) {
-		priv->rx_skb[q][i] = NULL;
-		skb = netdev_alloc_skb(ndev, PKT_BUF_SZ + RAVB_ALIGN - 1);
-		if (!skb)
-			break;
-		ravb_set_buffer_align(skb);
 		/* RX descriptor */
 		rx_desc = &priv->rx_ring[q][i];
 		/* The size of the buffer should be on 16-byte boundary. */
 		rx_desc->ds_cc = cpu_to_le16(ALIGN(PKT_BUF_SZ, 16));
-		dma_addr = dma_map_single(&ndev->dev, skb->data,
+		dma_addr = dma_map_single(&ndev->dev, priv->rx_skb[q][i]->data,
 					  ALIGN(PKT_BUF_SZ, 16),
 					  DMA_FROM_DEVICE);
-		if (dma_mapping_error(&ndev->dev, dma_addr)) {
-			dev_kfree_skb(skb);
-			break;
-		}
-		priv->rx_skb[q][i] = skb;
+		/* We just set the data size to 0 for a failed mapping which
+		 * should prevent DMA from happening...
+		 */
+		if (dma_mapping_error(&ndev->dev, dma_addr))
+			rx_desc->ds_cc = cpu_to_le16(0);
 		rx_desc->dptr = cpu_to_le32(dma_addr);
 		rx_desc->die_dt = DT_FEMPTY;
 	}
 	rx_desc = &priv->rx_ring[q][i];
 	rx_desc->dptr = cpu_to_le32((u32)priv->rx_desc_dma[q]);
 	rx_desc->die_dt = DT_LINKFIX; /* type */
-	priv->dirty_rx[q] = (u32)(i - priv->num_rx_ring[q]);
 
 	memset(priv->tx_ring[q], 0, tx_ring_size);
 	/* Build TX ring buffer */
 	for (i = 0; i < priv->num_tx_ring[q]; i++) {
-		priv->tx_skb[q][i] = NULL;
-		priv->tx_buffers[q][i] = NULL;
-		buffer = kmalloc(PKT_BUF_SZ + RAVB_ALIGN - 1, GFP_KERNEL);
-		if (!buffer)
-			break;
-		/* Aligned TX buffer */
-		priv->tx_buffers[q][i] = buffer;
 		tx_desc = &priv->tx_ring[q][i];
 		tx_desc->die_dt = DT_EEMPTY;
 	}
@@ -298,7 +283,10 @@
 static int ravb_ring_init(struct net_device *ndev, int q)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
+	struct sk_buff *skb;
 	int ring_size;
+	void *buffer;
+	int i;
 
 	/* Allocate RX and TX skb rings */
 	priv->rx_skb[q] = kcalloc(priv->num_rx_ring[q],
@@ -308,12 +296,28 @@
 	if (!priv->rx_skb[q] || !priv->tx_skb[q])
 		goto error;
 
+	for (i = 0; i < priv->num_rx_ring[q]; i++) {
+		skb = netdev_alloc_skb(ndev, PKT_BUF_SZ + RAVB_ALIGN - 1);
+		if (!skb)
+			goto error;
+		ravb_set_buffer_align(skb);
+		priv->rx_skb[q][i] = skb;
+	}
+
 	/* Allocate rings for the aligned buffers */
 	priv->tx_buffers[q] = kcalloc(priv->num_tx_ring[q],
 				      sizeof(*priv->tx_buffers[q]), GFP_KERNEL);
 	if (!priv->tx_buffers[q])
 		goto error;
 
+	for (i = 0; i < priv->num_tx_ring[q]; i++) {
+		buffer = kmalloc(PKT_BUF_SZ + RAVB_ALIGN - 1, GFP_KERNEL);
+		if (!buffer)
+			goto error;
+		/* Aligned TX buffer */
+		priv->tx_buffers[q][i] = buffer;
+	}
+
 	/* Allocate all RX descriptors. */
 	ring_size = sizeof(struct ravb_ex_rx_desc) * (priv->num_rx_ring[q] + 1);
 	priv->rx_ring[q] = dma_alloc_coherent(NULL, ring_size,
@@ -524,6 +528,10 @@
 		if (--boguscnt < 0)
 			break;
 
+		/* We use 0-byte descriptors to mark the DMA mapping errors */
+		if (!pkt_len)
+			continue;
+
 		if (desc_status & MSC_MC)
 			stats->multicast++;
 
@@ -543,10 +551,9 @@
 
 			skb = priv->rx_skb[q][entry];
 			priv->rx_skb[q][entry] = NULL;
-			dma_sync_single_for_cpu(&ndev->dev,
-						le32_to_cpu(desc->dptr),
-						ALIGN(PKT_BUF_SZ, 16),
-						DMA_FROM_DEVICE);
+			dma_unmap_single(&ndev->dev, le32_to_cpu(desc->dptr),
+					 ALIGN(PKT_BUF_SZ, 16),
+					 DMA_FROM_DEVICE);
 			get_ts &= (q == RAVB_NC) ?
 					RAVB_RXTSTAMP_TYPE_V2_L2_EVENT :
 					~RAVB_RXTSTAMP_TYPE_V2_L2_EVENT;
@@ -584,17 +591,15 @@
 			if (!skb)
 				break;	/* Better luck next round. */
 			ravb_set_buffer_align(skb);
-			dma_unmap_single(&ndev->dev, le32_to_cpu(desc->dptr),
-					 ALIGN(PKT_BUF_SZ, 16),
-					 DMA_FROM_DEVICE);
 			dma_addr = dma_map_single(&ndev->dev, skb->data,
 						  le16_to_cpu(desc->ds_cc),
 						  DMA_FROM_DEVICE);
 			skb_checksum_none_assert(skb);
-			if (dma_mapping_error(&ndev->dev, dma_addr)) {
-				dev_kfree_skb_any(skb);
-				break;
-			}
+			/* We just set the data size to 0 for a failed mapping
+			 * which should prevent DMA  from happening...
+			 */
+			if (dma_mapping_error(&ndev->dev, dma_addr))
+				desc->ds_cc = cpu_to_le16(0);
 			desc->dptr = cpu_to_le32(dma_addr);
 			priv->rx_skb[q][entry] = skb;
 		}
@@ -1279,7 +1284,6 @@
 	u32 dma_addr;
 	void *buffer;
 	u32 entry;
-	u32 tccr;
 
 	spin_lock_irqsave(&priv->lock, flags);
 	if (priv->cur_tx[q] - priv->dirty_tx[q] >= priv->num_tx_ring[q]) {
@@ -1328,9 +1332,7 @@
 	dma_wmb();
 	desc->die_dt = DT_FSINGLE;
 
-	tccr = ravb_read(ndev, TCCR);
-	if (!(tccr & (TCCR_TSRQ0 << q)))
-		ravb_write(ndev, tccr | (TCCR_TSRQ0 << q), TCCR);
+	ravb_write(ndev, ravb_read(ndev, TCCR) | (TCCR_TSRQ0 << q), TCCR);
 
 	priv->cur_tx[q]++;
 	if (priv->cur_tx[q] - priv->dirty_tx[q] >= priv->num_tx_ring[q] &&
diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c
index 2d8578cade..2e7f9a2 100644
--- a/drivers/net/ethernet/rocker/rocker.c
+++ b/drivers/net/ethernet/rocker/rocker.c
@@ -4821,6 +4821,7 @@
 		rocker_port_ig_tbl(rocker_port, SWITCHDEV_TRANS_NONE,
 				   ROCKER_OP_FLAG_REMOVE);
 		unregister_netdev(rocker_port->dev);
+		free_netdev(rocker_port->dev);
 	}
 	kfree(rocker->ports);
 }
diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 8476434..605cc89 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -101,6 +101,11 @@
 	return resource_size(&efx->pci_dev->resource[bar]);
 }
 
+static bool efx_ef10_is_vf(struct efx_nic *efx)
+{
+	return efx->type->is_vf;
+}
+
 static int efx_ef10_get_pf_index(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_FUNCTION_INFO_OUT_LEN);
@@ -677,6 +682,48 @@
 	return efx_ef10_probe(efx);
 }
 
+int efx_ef10_vadaptor_alloc(struct efx_nic *efx, unsigned int port_id)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_ALLOC_IN_LEN);
+
+	MCDI_SET_DWORD(inbuf, VADAPTOR_ALLOC_IN_UPSTREAM_PORT_ID, port_id);
+	return efx_mcdi_rpc(efx, MC_CMD_VADAPTOR_ALLOC, inbuf, sizeof(inbuf),
+			    NULL, 0, NULL);
+}
+
+int efx_ef10_vadaptor_free(struct efx_nic *efx, unsigned int port_id)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_FREE_IN_LEN);
+
+	MCDI_SET_DWORD(inbuf, VADAPTOR_FREE_IN_UPSTREAM_PORT_ID, port_id);
+	return efx_mcdi_rpc(efx, MC_CMD_VADAPTOR_FREE, inbuf, sizeof(inbuf),
+			    NULL, 0, NULL);
+}
+
+int efx_ef10_vport_add_mac(struct efx_nic *efx,
+			   unsigned int port_id, u8 *mac)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_ADD_MAC_ADDRESS_IN_LEN);
+
+	MCDI_SET_DWORD(inbuf, VPORT_ADD_MAC_ADDRESS_IN_VPORT_ID, port_id);
+	ether_addr_copy(MCDI_PTR(inbuf, VPORT_ADD_MAC_ADDRESS_IN_MACADDR), mac);
+
+	return efx_mcdi_rpc(efx, MC_CMD_VPORT_ADD_MAC_ADDRESS, inbuf,
+			    sizeof(inbuf), NULL, 0, NULL);
+}
+
+int efx_ef10_vport_del_mac(struct efx_nic *efx,
+			   unsigned int port_id, u8 *mac)
+{
+	MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_DEL_MAC_ADDRESS_IN_LEN);
+
+	MCDI_SET_DWORD(inbuf, VPORT_DEL_MAC_ADDRESS_IN_VPORT_ID, port_id);
+	ether_addr_copy(MCDI_PTR(inbuf, VPORT_DEL_MAC_ADDRESS_IN_MACADDR), mac);
+
+	return efx_mcdi_rpc(efx, MC_CMD_VPORT_DEL_MAC_ADDRESS, inbuf,
+			    sizeof(inbuf), NULL, 0, NULL);
+}
+
 #ifdef CONFIG_SFC_SRIOV
 static int efx_ef10_probe_vf(struct efx_nic *efx)
 {
@@ -3804,6 +3851,72 @@
 	WARN_ON(remove_failed);
 }
 
+static int efx_ef10_vport_set_mac_address(struct efx_nic *efx)
+{
+	struct efx_ef10_nic_data *nic_data = efx->nic_data;
+	u8 mac_old[ETH_ALEN];
+	int rc, rc2;
+
+	/* Only reconfigure a PF-created vport */
+	if (is_zero_ether_addr(nic_data->vport_mac))
+		return 0;
+
+	efx_device_detach_sync(efx);
+	efx_net_stop(efx->net_dev);
+	down_write(&efx->filter_sem);
+	efx_ef10_filter_table_remove(efx);
+	up_write(&efx->filter_sem);
+
+	rc = efx_ef10_vadaptor_free(efx, nic_data->vport_id);
+	if (rc)
+		goto restore_filters;
+
+	ether_addr_copy(mac_old, nic_data->vport_mac);
+	rc = efx_ef10_vport_del_mac(efx, nic_data->vport_id,
+				    nic_data->vport_mac);
+	if (rc)
+		goto restore_vadaptor;
+
+	rc = efx_ef10_vport_add_mac(efx, nic_data->vport_id,
+				    efx->net_dev->dev_addr);
+	if (!rc) {
+		ether_addr_copy(nic_data->vport_mac, efx->net_dev->dev_addr);
+	} else {
+		rc2 = efx_ef10_vport_add_mac(efx, nic_data->vport_id, mac_old);
+		if (rc2) {
+			/* Failed to add original MAC, so clear vport_mac */
+			eth_zero_addr(nic_data->vport_mac);
+			goto reset_nic;
+		}
+	}
+
+restore_vadaptor:
+	rc2 = efx_ef10_vadaptor_alloc(efx, nic_data->vport_id);
+	if (rc2)
+		goto reset_nic;
+restore_filters:
+	down_write(&efx->filter_sem);
+	rc2 = efx_ef10_filter_table_probe(efx);
+	up_write(&efx->filter_sem);
+	if (rc2)
+		goto reset_nic;
+
+	rc2 = efx_net_open(efx->net_dev);
+	if (rc2)
+		goto reset_nic;
+
+	netif_device_attach(efx->net_dev);
+
+	return rc;
+
+reset_nic:
+	netif_err(efx, drv, efx->net_dev,
+		  "Failed to restore when changing MAC address - scheduling reset\n");
+	efx_schedule_reset(efx, RESET_TYPE_DATAPATH);
+
+	return rc ? rc : rc2;
+}
+
 static int efx_ef10_set_mac_address(struct efx_nic *efx)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_SET_MAC_IN_LEN);
@@ -3820,8 +3933,8 @@
 			efx->net_dev->dev_addr);
 	MCDI_SET_DWORD(inbuf, VADAPTOR_SET_MAC_IN_UPSTREAM_PORT_ID,
 		       nic_data->vport_id);
-	rc = efx_mcdi_rpc(efx, MC_CMD_VADAPTOR_SET_MAC, inbuf,
-			  sizeof(inbuf), NULL, 0, NULL);
+	rc = efx_mcdi_rpc_quiet(efx, MC_CMD_VADAPTOR_SET_MAC, inbuf,
+				sizeof(inbuf), NULL, 0, NULL);
 
 	efx_ef10_filter_table_probe(efx);
 	up_write(&efx->filter_sem);
@@ -3829,38 +3942,27 @@
 		efx_net_open(efx->net_dev);
 	netif_device_attach(efx->net_dev);
 
-#if !defined(CONFIG_SFC_SRIOV)
-	if (rc == -EPERM)
-		netif_err(efx, drv, efx->net_dev,
-			  "Cannot change MAC address; use sfboot to enable mac-spoofing"
-			  " on this interface\n");
-#else
-	if (rc == -EPERM) {
+#ifdef CONFIG_SFC_SRIOV
+	if (efx->pci_dev->is_virtfn && efx->pci_dev->physfn) {
 		struct pci_dev *pci_dev_pf = efx->pci_dev->physfn;
 
-		/* Switch to PF and change MAC address on vport */
-		if (efx->pci_dev->is_virtfn && pci_dev_pf) {
-			struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf);
+		if (rc == -EPERM) {
+			struct efx_nic *efx_pf;
 
-			if (!efx_ef10_sriov_set_vf_mac(efx_pf,
+			/* Switch to PF and change MAC address on vport */
+			efx_pf = pci_get_drvdata(pci_dev_pf);
+
+			rc = efx_ef10_sriov_set_vf_mac(efx_pf,
 						       nic_data->vf_index,
-						       efx->net_dev->dev_addr))
-				return 0;
-		}
-		netif_err(efx, drv, efx->net_dev,
-			  "Cannot change MAC address; use sfboot to enable mac-spoofing"
-			  " on this interface\n");
-	} else if (efx->pci_dev->is_virtfn) {
-		/* Successfully changed by VF (with MAC spoofing), so update the
-		 * parent PF if possible.
-		 */
-		struct pci_dev *pci_dev_pf = efx->pci_dev->physfn;
-
-		if (pci_dev_pf) {
+						       efx->net_dev->dev_addr);
+		} else if (!rc) {
 			struct efx_nic *efx_pf = pci_get_drvdata(pci_dev_pf);
 			struct efx_ef10_nic_data *nic_data = efx_pf->nic_data;
 			unsigned int i;
 
+			/* MAC address successfully changed by VF (with MAC
+			 * spoofing) so update the parent PF if possible.
+			 */
 			for (i = 0; i < efx_pf->vf_count; ++i) {
 				struct ef10_vf *vf = nic_data->vf + i;
 
@@ -3871,8 +3973,24 @@
 				}
 			}
 		}
-	}
+	} else
 #endif
+	if (rc == -EPERM) {
+		netif_err(efx, drv, efx->net_dev,
+			  "Cannot change MAC address; use sfboot to enable"
+			  " mac-spoofing on this interface\n");
+	} else if (rc == -ENOSYS && !efx_ef10_is_vf(efx)) {
+		/* If the active MCFW does not support MC_CMD_VADAPTOR_SET_MAC
+		 * fall-back to the method of changing the MAC address on the
+		 * vport.  This only applies to PFs because such versions of
+		 * MCFW do not support VFs.
+		 */
+		rc = efx_ef10_vport_set_mac_address(efx);
+	} else {
+		efx_mcdi_display_error(efx, MC_CMD_VADAPTOR_SET_MAC,
+				       sizeof(inbuf), NULL, 0, rc);
+	}
+
 	return rc;
 }
 
diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c
index 6c9b6e4..3c17f27 100644
--- a/drivers/net/ethernet/sfc/ef10_sriov.c
+++ b/drivers/net/ethernet/sfc/ef10_sriov.c
@@ -29,30 +29,6 @@
 			    NULL, 0, NULL);
 }
 
-static int efx_ef10_vport_add_mac(struct efx_nic *efx,
-				  unsigned int port_id, u8 *mac)
-{
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_ADD_MAC_ADDRESS_IN_LEN);
-
-	MCDI_SET_DWORD(inbuf, VPORT_ADD_MAC_ADDRESS_IN_VPORT_ID, port_id);
-	ether_addr_copy(MCDI_PTR(inbuf, VPORT_ADD_MAC_ADDRESS_IN_MACADDR), mac);
-
-	return efx_mcdi_rpc(efx, MC_CMD_VPORT_ADD_MAC_ADDRESS, inbuf,
-			    sizeof(inbuf), NULL, 0, NULL);
-}
-
-static int efx_ef10_vport_del_mac(struct efx_nic *efx,
-				  unsigned int port_id, u8 *mac)
-{
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_VPORT_DEL_MAC_ADDRESS_IN_LEN);
-
-	MCDI_SET_DWORD(inbuf, VPORT_DEL_MAC_ADDRESS_IN_VPORT_ID, port_id);
-	ether_addr_copy(MCDI_PTR(inbuf, VPORT_DEL_MAC_ADDRESS_IN_MACADDR), mac);
-
-	return efx_mcdi_rpc(efx, MC_CMD_VPORT_DEL_MAC_ADDRESS, inbuf,
-			    sizeof(inbuf), NULL, 0, NULL);
-}
-
 static int efx_ef10_vswitch_alloc(struct efx_nic *efx, unsigned int port_id,
 				  unsigned int vswitch_type)
 {
@@ -136,24 +112,6 @@
 			    NULL, 0, NULL);
 }
 
-static int efx_ef10_vadaptor_alloc(struct efx_nic *efx, unsigned int port_id)
-{
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_ALLOC_IN_LEN);
-
-	MCDI_SET_DWORD(inbuf, VADAPTOR_ALLOC_IN_UPSTREAM_PORT_ID, port_id);
-	return efx_mcdi_rpc(efx, MC_CMD_VADAPTOR_ALLOC, inbuf, sizeof(inbuf),
-			    NULL, 0, NULL);
-}
-
-static int efx_ef10_vadaptor_free(struct efx_nic *efx, unsigned int port_id)
-{
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_VADAPTOR_FREE_IN_LEN);
-
-	MCDI_SET_DWORD(inbuf, VADAPTOR_FREE_IN_UPSTREAM_PORT_ID, port_id);
-	return efx_mcdi_rpc(efx, MC_CMD_VADAPTOR_FREE, inbuf, sizeof(inbuf),
-			    NULL, 0, NULL);
-}
-
 static void efx_ef10_sriov_free_vf_vports(struct efx_nic *efx)
 {
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
@@ -640,21 +598,21 @@
 				  MC_CMD_VPORT_ALLOC_IN_VPORT_TYPE_NORMAL,
 				  vf->vlan, &vf->vport_id);
 	if (rc)
-		goto reset_nic;
+		goto reset_nic_up_write;
 
 restore_mac:
 	if (!is_zero_ether_addr(vf->mac)) {
 		rc2 = efx_ef10_vport_add_mac(efx, vf->vport_id, vf->mac);
 		if (rc2) {
 			eth_zero_addr(vf->mac);
-			goto reset_nic;
+			goto reset_nic_up_write;
 		}
 	}
 
 restore_evb_port:
 	rc2 = efx_ef10_evb_port_assign(efx, vf->vport_id, vf_i);
 	if (rc2)
-		goto reset_nic;
+		goto reset_nic_up_write;
 	else
 		vf->vport_assigned = 1;
 
@@ -662,14 +620,16 @@
 	if (vf->efx) {
 		rc2 = efx_ef10_vadaptor_alloc(vf->efx, EVB_PORT_ID_ASSIGNED);
 		if (rc2)
-			goto reset_nic;
+			goto reset_nic_up_write;
 	}
 
 restore_filters:
 	if (vf->efx) {
 		rc2 = vf->efx->type->filter_table_probe(vf->efx);
 		if (rc2)
-			goto reset_nic;
+			goto reset_nic_up_write;
+
+		up_write(&vf->efx->filter_sem);
 
 		up_write(&vf->efx->filter_sem);
 
@@ -681,9 +641,12 @@
 	}
 	return rc;
 
+reset_nic_up_write:
+	if (vf->efx)
+		up_write(&vf->efx->filter_sem);
+
 reset_nic:
 	if (vf->efx) {
-		up_write(&vf->efx->filter_sem);
 		netif_err(efx, drv, efx->net_dev,
 			  "Failed to restore VF - scheduling reset.\n");
 		efx_schedule_reset(vf->efx, RESET_TYPE_DATAPATH);
diff --git a/drivers/net/ethernet/sfc/ef10_sriov.h b/drivers/net/ethernet/sfc/ef10_sriov.h
index db4ef53..6d25b92 100644
--- a/drivers/net/ethernet/sfc/ef10_sriov.h
+++ b/drivers/net/ethernet/sfc/ef10_sriov.h
@@ -65,5 +65,11 @@
 int efx_ef10_vswitching_restore_vf(struct efx_nic *efx);
 void efx_ef10_vswitching_remove_pf(struct efx_nic *efx);
 void efx_ef10_vswitching_remove_vf(struct efx_nic *efx);
+int efx_ef10_vport_add_mac(struct efx_nic *efx,
+			   unsigned int port_id, u8 *mac);
+int efx_ef10_vport_del_mac(struct efx_nic *efx,
+			   unsigned int port_id, u8 *mac);
+int efx_ef10_vadaptor_alloc(struct efx_nic *efx, unsigned int port_id);
+int efx_ef10_vadaptor_free(struct efx_nic *efx, unsigned int port_id);
 
 #endif /* EF10_SRIOV_H */
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 804b9ad..03bc03b 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -245,11 +245,17 @@
  */
 static int efx_process_channel(struct efx_channel *channel, int budget)
 {
+	struct efx_tx_queue *tx_queue;
 	int spent;
 
 	if (unlikely(!channel->enabled))
 		return 0;
 
+	efx_for_each_channel_tx_queue(tx_queue, channel) {
+		tx_queue->pkts_compl = 0;
+		tx_queue->bytes_compl = 0;
+	}
+
 	spent = efx_nic_process_eventq(channel, budget);
 	if (spent && efx_channel_has_rx_queue(channel)) {
 		struct efx_rx_queue *rx_queue =
@@ -259,6 +265,14 @@
 		efx_fast_push_rx_descriptors(rx_queue, true);
 	}
 
+	/* Update BQL */
+	efx_for_each_channel_tx_queue(tx_queue, channel) {
+		if (tx_queue->bytes_compl) {
+			netdev_tx_completed_queue(tx_queue->core_txq,
+				tx_queue->pkts_compl, tx_queue->bytes_compl);
+		}
+	}
+
 	return spent;
 }
 
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index d72f522..47d1e3a 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -241,6 +241,8 @@
 	unsigned int read_count ____cacheline_aligned_in_smp;
 	unsigned int old_write_count;
 	unsigned int merge_events;
+	unsigned int bytes_compl;
+	unsigned int pkts_compl;
 
 	/* Members used only on the xmit path */
 	unsigned int insert_count ____cacheline_aligned_in_smp;
diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c
index aaf2987..1833a01 100644
--- a/drivers/net/ethernet/sfc/tx.c
+++ b/drivers/net/ethernet/sfc/tx.c
@@ -617,7 +617,8 @@
 	EFX_BUG_ON_PARANOID(index > tx_queue->ptr_mask);
 
 	efx_dequeue_buffers(tx_queue, index, &pkts_compl, &bytes_compl);
-	netdev_tx_completed_queue(tx_queue->core_txq, pkts_compl, bytes_compl);
+	tx_queue->pkts_compl += pkts_compl;
+	tx_queue->bytes_compl += bytes_compl;
 
 	if (pkts_compl > 1)
 		++tx_queue->merge_events;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
index 7e3129e..f0e4bb4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
@@ -42,7 +42,7 @@
 #define NSS_COMMON_CLK_DIV_MASK			0x7f
 
 #define NSS_COMMON_CLK_SRC_CTRL			0x14
-#define NSS_COMMON_CLK_SRC_CTRL_OFFSET(x)	(1 << x)
+#define NSS_COMMON_CLK_SRC_CTRL_OFFSET(x)	(x)
 /* Mode is coded on 1 bit but is different depending on the MAC ID:
  * MAC0: QSGMII=0 RGMII=1
  * MAC1: QSGMII=0 SGMII=0 RGMII=1
@@ -291,7 +291,7 @@
 
 	/* Configure the clock src according to the mode */
 	regmap_read(gmac->nss_common, NSS_COMMON_CLK_SRC_CTRL, &val);
-	val &= ~NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id);
+	val &= ~(1 << NSS_COMMON_CLK_SRC_CTRL_OFFSET(gmac->id));
 	switch (gmac->phy_mode) {
 	case PHY_INTERFACE_MODE_RGMII:
 		val |= NSS_COMMON_CLK_SRC_CTRL_RGMII(gmac->id) <<
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 50f7a7a..864b476 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2843,7 +2843,7 @@
 	if (res->mac)
 		memcpy(priv->dev->dev_addr, res->mac, ETH_ALEN);
 
-	dev_set_drvdata(device, priv);
+	dev_set_drvdata(device, priv->dev);
 
 	/* Verify driver arguments */
 	stmmac_verify_args();
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index f3918c7..bcdc895 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -413,3 +413,7 @@
 SIMPLE_DEV_PM_OPS(stmmac_pltfr_pm_ops, stmmac_pltfr_suspend,
 				       stmmac_pltfr_resume);
 EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops);
+
+MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet platform support");
+MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 0c5842a..ab6051a 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -6658,10 +6658,8 @@
 		struct sk_buff *skb_new;
 
 		skb_new = skb_realloc_headroom(skb, len);
-		if (!skb_new) {
-			rp->tx_errors++;
+		if (!skb_new)
 			goto out_drop;
-		}
 		kfree_skb(skb);
 		skb = skb_new;
 	} else
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 4628205..d155bf2 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -138,19 +138,6 @@
 #define CPSW_CMINTMAX_INTVL	(1000 / CPSW_CMINTMIN_CNT)
 #define CPSW_CMINTMIN_INTVL	((1000 / CPSW_CMINTMAX_CNT) + 1)
 
-#define cpsw_enable_irq(priv)	\
-	do {			\
-		u32 i;		\
-		for (i = 0; i < priv->num_irqs; i++) \
-			enable_irq(priv->irqs_table[i]); \
-	} while (0)
-#define cpsw_disable_irq(priv)	\
-	do {			\
-		u32 i;		\
-		for (i = 0; i < priv->num_irqs; i++) \
-			disable_irq_nosync(priv->irqs_table[i]); \
-	} while (0)
-
 #define cpsw_slave_index(priv)				\
 		((priv->data.dual_emac) ? priv->emac_port :	\
 		priv->data.active_slave)
@@ -509,9 +496,11 @@
 				(func)(slave++, ##arg);			\
 	} while (0)
 #define cpsw_get_slave_ndev(priv, __slave_no__)				\
-	(priv->slaves[__slave_no__].ndev)
+	((__slave_no__ < priv->data.slaves) ?				\
+		priv->slaves[__slave_no__].ndev : NULL)
 #define cpsw_get_slave_priv(priv, __slave_no__)				\
-	((priv->slaves[__slave_no__].ndev) ?				\
+	(((__slave_no__ < priv->data.slaves) &&				\
+		(priv->slaves[__slave_no__].ndev)) ?			\
 		netdev_priv(priv->slaves[__slave_no__].ndev) : NULL)	\
 
 #define cpsw_dual_emac_src_port_detect(status, priv, ndev, skb)		\
@@ -781,7 +770,7 @@
 
 	cpsw_intr_disable(priv);
 	if (priv->irq_enabled == true) {
-		cpsw_disable_irq(priv);
+		disable_irq_nosync(priv->irqs_table[0]);
 		priv->irq_enabled = false;
 	}
 
@@ -804,9 +793,7 @@
 static int cpsw_poll(struct napi_struct *napi, int budget)
 {
 	struct cpsw_priv	*priv = napi_to_priv(napi);
-	int			num_tx, num_rx;
-
-	num_tx = cpdma_chan_process(priv->txch, 128);
+	int			num_rx;
 
 	num_rx = cpdma_chan_process(priv->rxch, budget);
 	if (num_rx < budget) {
@@ -817,13 +804,12 @@
 		prim_cpsw = cpsw_get_slave_priv(priv, 0);
 		if (prim_cpsw->irq_enabled == false) {
 			prim_cpsw->irq_enabled = true;
-			cpsw_enable_irq(priv);
+			enable_irq(priv->irqs_table[0]);
 		}
 	}
 
-	if (num_rx || num_tx)
-		cpsw_dbg(priv, intr, "poll %d rx, %d tx pkts\n",
-			 num_rx, num_tx);
+	if (num_rx)
+		cpsw_dbg(priv, intr, "poll %d rx pkts\n", num_rx);
 
 	return num_rx;
 }
@@ -1333,7 +1319,7 @@
 	if (prim_cpsw->irq_enabled == false) {
 		if ((priv == prim_cpsw) || !netif_running(prim_cpsw->ndev)) {
 			prim_cpsw->irq_enabled = true;
-			cpsw_enable_irq(prim_cpsw);
+			enable_irq(prim_cpsw->irqs_table[0]);
 		}
 	}
 
diff --git a/drivers/net/ethernet/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h
index bbacf5c..bb1bb72 100644
--- a/drivers/net/ethernet/ti/netcp.h
+++ b/drivers/net/ethernet/ti/netcp.h
@@ -85,7 +85,6 @@
 	struct list_head	rxhook_list_head;
 	unsigned int		rx_queue_id;
 	void			*rx_fdq[KNAV_DMA_FDQ_PER_CHAN];
-	u32			rx_buffer_sizes[KNAV_DMA_FDQ_PER_CHAN];
 	struct napi_struct	rx_napi;
 	struct napi_struct	tx_napi;
 
@@ -223,6 +222,7 @@
 
 /* SGMII functions */
 int netcp_sgmii_reset(void __iomem *sgmii_ofs, int port);
+bool netcp_sgmii_rtreset(void __iomem *sgmii_ofs, int port, bool set);
 int netcp_sgmii_get_port_link(void __iomem *sgmii_ofs, int port);
 int netcp_sgmii_config(void __iomem *sgmii_ofs, int port, u32 interface);
 
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 5ec4ed3..4755838 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -34,6 +34,7 @@
 #define NETCP_SOP_OFFSET	(NET_IP_ALIGN + NET_SKB_PAD)
 #define NETCP_NAPI_WEIGHT	64
 #define NETCP_TX_TIMEOUT	(5 * HZ)
+#define NETCP_PACKET_SIZE	(ETH_FRAME_LEN + ETH_FCS_LEN)
 #define NETCP_MIN_PACKET_SIZE	ETH_ZLEN
 #define NETCP_MAX_MCAST_ADDR	16
 
@@ -804,30 +805,28 @@
 	if (likely(fdq == 0)) {
 		unsigned int primary_buf_len;
 		/* Allocate a primary receive queue entry */
-		buf_len = netcp->rx_buffer_sizes[0] + NETCP_SOP_OFFSET;
+		buf_len = NETCP_PACKET_SIZE + NETCP_SOP_OFFSET;
 		primary_buf_len = SKB_DATA_ALIGN(buf_len) +
 				SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
-		if (primary_buf_len <= PAGE_SIZE) {
-			bufptr = netdev_alloc_frag(primary_buf_len);
-			pad[1] = primary_buf_len;
-		} else {
-			bufptr = kmalloc(primary_buf_len, GFP_ATOMIC |
-					 GFP_DMA32 | __GFP_COLD);
-			pad[1] = 0;
-		}
+		bufptr = netdev_alloc_frag(primary_buf_len);
+		pad[1] = primary_buf_len;
 
 		if (unlikely(!bufptr)) {
-			dev_warn_ratelimited(netcp->ndev_dev, "Primary RX buffer alloc failed\n");
+			dev_warn_ratelimited(netcp->ndev_dev,
+					     "Primary RX buffer alloc failed\n");
 			goto fail;
 		}
 		dma = dma_map_single(netcp->dev, bufptr, buf_len,
 				     DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(netcp->dev, dma)))
+			goto fail;
+
 		pad[0] = (u32)bufptr;
 
 	} else {
 		/* Allocate a secondary receive queue entry */
-		page = alloc_page(GFP_ATOMIC | GFP_DMA32 | __GFP_COLD);
+		page = alloc_page(GFP_ATOMIC | GFP_DMA | __GFP_COLD);
 		if (unlikely(!page)) {
 			dev_warn_ratelimited(netcp->ndev_dev, "Secondary page alloc failed\n");
 			goto fail;
@@ -1010,7 +1009,7 @@
 
 	/* Map the linear buffer */
 	dma_addr = dma_map_single(dev, skb->data, pkt_len, DMA_TO_DEVICE);
-	if (unlikely(!dma_addr)) {
+	if (unlikely(dma_mapping_error(dev, dma_addr))) {
 		dev_err(netcp->ndev_dev, "Failed to map skb buffer\n");
 		return NULL;
 	}
@@ -1546,8 +1545,8 @@
 	knav_queue_disable_notify(netcp->rx_queue);
 
 	/* open Rx FDQs */
-	for (i = 0; i < KNAV_DMA_FDQ_PER_CHAN &&
-	     netcp->rx_queue_depths[i] && netcp->rx_buffer_sizes[i]; ++i) {
+	for (i = 0; i < KNAV_DMA_FDQ_PER_CHAN && netcp->rx_queue_depths[i];
+	     ++i) {
 		snprintf(name, sizeof(name), "rx-fdq-%s-%d", ndev->name, i);
 		netcp->rx_fdq[i] = knav_queue_open(name, KNAV_QUEUE_GP, 0);
 		if (IS_ERR_OR_NULL(netcp->rx_fdq[i])) {
@@ -1617,11 +1616,11 @@
 	}
 	mutex_unlock(&netcp_modules_lock);
 
-	netcp_rxpool_refill(netcp);
 	napi_enable(&netcp->rx_napi);
 	napi_enable(&netcp->tx_napi);
 	knav_queue_enable_notify(netcp->tx_compl_q);
 	knav_queue_enable_notify(netcp->rx_queue);
+	netcp_rxpool_refill(netcp);
 	netif_tx_wake_all_queues(ndev);
 	dev_dbg(netcp->ndev_dev, "netcp device %s opened\n", ndev->name);
 	return 0;
@@ -1941,14 +1940,6 @@
 		netcp->rx_queue_depths[0] = 128;
 	}
 
-	ret = of_property_read_u32_array(node_interface, "rx-buffer-size",
-					 netcp->rx_buffer_sizes,
-					 KNAV_DMA_FDQ_PER_CHAN);
-	if (ret) {
-		dev_err(dev, "missing \"rx-buffer-size\" parameter\n");
-		netcp->rx_buffer_sizes[0] = 1536;
-	}
-
 	ret = of_property_read_u32_array(node_interface, "rx-pool", temp, 2);
 	if (ret < 0) {
 		dev_err(dev, "missing \"rx-pool\" parameter\n");
@@ -2112,6 +2103,7 @@
 static int netcp_remove(struct platform_device *pdev)
 {
 	struct netcp_device *netcp_device = platform_get_drvdata(pdev);
+	struct netcp_intf *netcp_intf, *netcp_tmp;
 	struct netcp_inst_modpriv *inst_modpriv, *tmp;
 	struct netcp_module *module;
 
@@ -2123,10 +2115,17 @@
 		list_del(&inst_modpriv->inst_list);
 		kfree(inst_modpriv);
 	}
-	WARN(!list_empty(&netcp_device->interface_head), "%s interface list not empty!\n",
-	     pdev->name);
 
-	devm_kfree(&pdev->dev, netcp_device);
+	/* now that all modules are removed, clean up the interfaces */
+	list_for_each_entry_safe(netcp_intf, netcp_tmp,
+				 &netcp_device->interface_head,
+				 interface_list) {
+		netcp_delete_interface(netcp_device, netcp_intf->ndev);
+	}
+
+	WARN(!list_empty(&netcp_device->interface_head),
+	     "%s interface list not empty!\n", pdev->name);
+
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	platform_set_drvdata(pdev, NULL);
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 9b7e0a3..1974a8a 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -1901,11 +1901,28 @@
 	writel(slave->mac_control, GBE_REG_ADDR(slave, emac_regs, mac_control));
 }
 
+static void gbe_sgmii_rtreset(struct gbe_priv *priv,
+			      struct gbe_slave *slave, bool set)
+{
+	void __iomem *sgmii_port_regs;
+
+	if (SLAVE_LINK_IS_XGMII(slave))
+		return;
+
+	if ((priv->ss_version == GBE_SS_VERSION_14) && (slave->slave_num >= 2))
+		sgmii_port_regs = priv->sgmii_port34_regs;
+	else
+		sgmii_port_regs = priv->sgmii_port_regs;
+
+	netcp_sgmii_rtreset(sgmii_port_regs, slave->slave_num, set);
+}
+
 static void gbe_slave_stop(struct gbe_intf *intf)
 {
 	struct gbe_priv *gbe_dev = intf->gbe_dev;
 	struct gbe_slave *slave = intf->slave;
 
+	gbe_sgmii_rtreset(gbe_dev, slave, true);
 	gbe_port_reset(slave);
 	/* Disable forwarding */
 	cpsw_ale_control_set(gbe_dev->ale, slave->port_num,
@@ -1947,6 +1964,7 @@
 
 	gbe_sgmii_config(priv, slave);
 	gbe_port_reset(slave);
+	gbe_sgmii_rtreset(priv, slave, false);
 	gbe_port_config(priv, slave, priv->rx_packet_max);
 	gbe_set_slave_mac(slave, gbe_intf);
 	/* enable forwarding */
@@ -2490,10 +2508,9 @@
 {
 	struct gbe_slave *slave;
 
-	for (;;) {
+	while (!list_empty(&gbe_dev->secondary_slaves)) {
 		slave = first_sec_slave(gbe_dev);
-		if (!slave)
-			break;
+
 		if (slave->phy)
 			phy_disconnect(slave->phy);
 		list_del(&slave->slave_list);
@@ -2839,14 +2856,13 @@
 				      &gbe_dev->dma_chan_name);
 	if (ret < 0) {
 		dev_err(dev, "missing \"tx-channel\" parameter\n");
-		ret = -ENODEV;
-		goto quit;
+		return -EINVAL;
 	}
 
 	if (!strcmp(node->name, "gbe")) {
 		ret = get_gbe_resource_version(gbe_dev, node);
 		if (ret)
-			goto quit;
+			return ret;
 
 		dev_dbg(dev, "ss_version: 0x%08x\n", gbe_dev->ss_version);
 
@@ -2857,22 +2873,20 @@
 		else
 			ret = -ENODEV;
 
-		if (ret)
-			goto quit;
 	} else if (!strcmp(node->name, "xgbe")) {
 		ret = set_xgbe_ethss10_priv(gbe_dev, node);
 		if (ret)
-			goto quit;
+			return ret;
 		ret = netcp_xgbe_serdes_init(gbe_dev->xgbe_serdes_regs,
 					     gbe_dev->ss_regs);
-		if (ret)
-			goto quit;
 	} else {
 		dev_err(dev, "unknown GBE node(%s)\n", node->name);
 		ret = -ENODEV;
-		goto quit;
 	}
 
+	if (ret)
+		return ret;
+
 	interfaces = of_get_child_by_name(node, "interfaces");
 	if (!interfaces)
 		dev_err(dev, "could not find interfaces\n");
@@ -2880,11 +2894,11 @@
 	ret = netcp_txpipe_init(&gbe_dev->tx_pipe, netcp_device,
 				gbe_dev->dma_chan_name, gbe_dev->tx_queue_id);
 	if (ret)
-		goto quit;
+		return ret;
 
 	ret = netcp_txpipe_open(&gbe_dev->tx_pipe);
 	if (ret)
-		goto quit;
+		return ret;
 
 	/* Create network interfaces */
 	INIT_LIST_HEAD(&gbe_dev->gbe_intf_head);
@@ -2899,6 +2913,7 @@
 		if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves)
 			break;
 	}
+	of_node_put(interfaces);
 
 	if (!gbe_dev->num_slaves)
 		dev_warn(dev, "No network interface configured\n");
@@ -2911,9 +2926,10 @@
 	of_node_put(secondary_ports);
 
 	if (!gbe_dev->num_slaves) {
-		dev_err(dev, "No network interface or secondary ports configured\n");
+		dev_err(dev,
+			"No network interface or secondary ports configured\n");
 		ret = -ENODEV;
-		goto quit;
+		goto free_sec_ports;
 	}
 
 	memset(&ale_params, 0, sizeof(ale_params));
@@ -2927,7 +2943,7 @@
 	if (!gbe_dev->ale) {
 		dev_err(gbe_dev->dev, "error initializing ale engine\n");
 		ret = -ENODEV;
-		goto quit;
+		goto free_sec_ports;
 	} else {
 		dev_dbg(gbe_dev->dev, "Created a gbe ale engine\n");
 	}
@@ -2943,14 +2959,8 @@
 	*inst_priv = gbe_dev;
 	return 0;
 
-quit:
-	if (gbe_dev->hw_stats)
-		devm_kfree(dev, gbe_dev->hw_stats);
-	cpsw_ale_destroy(gbe_dev->ale);
-	if (gbe_dev->ss_regs)
-		devm_iounmap(dev, gbe_dev->ss_regs);
-	of_node_put(interfaces);
-	devm_kfree(dev, gbe_dev);
+free_sec_ports:
+	free_secondary_ports(gbe_dev);
 	return ret;
 }
 
@@ -3023,12 +3033,9 @@
 	free_secondary_ports(gbe_dev);
 
 	if (!list_empty(&gbe_dev->gbe_intf_head))
-		dev_alert(gbe_dev->dev, "unreleased ethss interfaces present\n");
+		dev_alert(gbe_dev->dev,
+			  "unreleased ethss interfaces present\n");
 
-	devm_kfree(gbe_dev->dev, gbe_dev->hw_stats);
-	devm_iounmap(gbe_dev->dev, gbe_dev->ss_regs);
-	memset(gbe_dev, 0x00, sizeof(*gbe_dev));
-	devm_kfree(gbe_dev->dev, gbe_dev);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/ti/netcp_sgmii.c b/drivers/net/ethernet/ti/netcp_sgmii.c
index dbeb142..5d8419f 100644
--- a/drivers/net/ethernet/ti/netcp_sgmii.c
+++ b/drivers/net/ethernet/ti/netcp_sgmii.c
@@ -18,6 +18,9 @@
 
 #include "netcp.h"
 
+#define SGMII_SRESET_RESET		BIT(0)
+#define SGMII_SRESET_RTRESET		BIT(1)
+
 #define SGMII_REG_STATUS_LOCK		BIT(4)
 #define	SGMII_REG_STATUS_LINK		BIT(0)
 #define SGMII_REG_STATUS_AUTONEG	BIT(2)
@@ -51,12 +54,35 @@
 int netcp_sgmii_reset(void __iomem *sgmii_ofs, int port)
 {
 	/* Soft reset */
-	sgmii_write_reg_bit(sgmii_ofs, SGMII_SRESET_REG(port), 0x1);
-	while (sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)) != 0x0)
+	sgmii_write_reg_bit(sgmii_ofs, SGMII_SRESET_REG(port),
+			    SGMII_SRESET_RESET);
+
+	while ((sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)) &
+		SGMII_SRESET_RESET) != 0x0)
 		;
+
 	return 0;
 }
 
+/* port is 0 based */
+bool netcp_sgmii_rtreset(void __iomem *sgmii_ofs, int port, bool set)
+{
+	u32 reg;
+	bool oldval;
+
+	/* Initiate a soft reset */
+	reg = sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port));
+	oldval = (reg & SGMII_SRESET_RTRESET) != 0x0;
+	if (set)
+		reg |= SGMII_SRESET_RTRESET;
+	else
+		reg &= ~SGMII_SRESET_RTRESET;
+	sgmii_write_reg(sgmii_ofs, SGMII_SRESET_REG(port), reg);
+	wmb();
+
+	return oldval;
+}
+
 int netcp_sgmii_get_port_link(void __iomem *sgmii_ofs, int port)
 {
 	u32 status = 0, link = 0;
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 4208dd7..d95f9aa 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1530,9 +1530,9 @@
 	/* Map device registers */
 	ethres = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	lp->regs = devm_ioremap_resource(&pdev->dev, ethres);
-	if (!lp->regs) {
+	if (IS_ERR(lp->regs)) {
 		dev_err(&pdev->dev, "could not map Axi Ethernet regs.\n");
-		ret = -ENOMEM;
+		ret = PTR_ERR(lp->regs);
 		goto free_netdev;
 	}
 
@@ -1599,9 +1599,9 @@
 		goto free_netdev;
 	}
 	lp->dma_regs = devm_ioremap_resource(&pdev->dev, &dmares);
-	if (!lp->dma_regs) {
+	if (IS_ERR(lp->dma_regs)) {
 		dev_err(&pdev->dev, "could not map DMA regs\n");
-		ret = -ENOMEM;
+		ret = PTR_ERR(lp->dma_regs);
 		goto free_netdev;
 	}
 	lp->rx_irq = irq_of_parse_and_map(np, 1);
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index 7856b6c..d95a50a 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -482,6 +482,7 @@
 	memcpy(dev->dev_addr,  &ax25_defaddr, AX25_ADDR_LEN);
 
 	dev->flags      = 0;
+	dev->features	= NETIF_F_LLTX;	/* Allow recursion */
 
 #if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE)
 	dev->header_ops      = &ax25_header_ops;
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index 2ffbf13..216bfd3 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -728,11 +728,12 @@
 	dev->type = ARPHRD_AX25;
 
 	/* Perform the low-level AX25 initialization. */
-	if ((err = ax_open(ax->dev))) {
+	err = ax_open(ax->dev);
+	if (err)
 		goto out_free_netdev;
-	}
 
-	if (register_netdev(dev))
+	err = register_netdev(dev);
+	if (err)
 		goto out_free_buffers;
 
 	/* after register_netdev() - because else printk smashes the kernel */
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index 953a974..9542b7b 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -67,8 +67,6 @@
 	struct ipvl_port	*port;
 	struct net_device	*phy_dev;
 	struct list_head	addrs;
-	int			ipv4cnt;
-	int			ipv6cnt;
 	struct ipvl_pcpu_stats	__percpu *pcpu_stats;
 	DECLARE_BITMAP(mac_filters, IPVLAN_MAC_FILTER_SIZE);
 	netdev_features_t	sfeatures;
@@ -106,6 +104,11 @@
 	return rcu_dereference(d->rx_handler_data);
 }
 
+static inline struct ipvl_port *ipvlan_port_get_rcu_bh(const struct net_device *d)
+{
+	return rcu_dereference_bh(d->rx_handler_data);
+}
+
 static inline struct ipvl_port *ipvlan_port_get_rtnl(const struct net_device *d)
 {
 	return rtnl_dereference(d->rx_handler_data);
@@ -124,5 +127,5 @@
 bool ipvlan_addr_busy(struct ipvl_port *port, void *iaddr, bool is_v6);
 struct ipvl_addr *ipvlan_ht_addr_lookup(const struct ipvl_port *port,
 					const void *iaddr, bool is_v6);
-void ipvlan_ht_addr_del(struct ipvl_addr *addr, bool sync);
+void ipvlan_ht_addr_del(struct ipvl_addr *addr);
 #endif /* __IPVLAN_H */
diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index 8afbeda..207f62e 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -85,11 +85,9 @@
 		hlist_add_head_rcu(&addr->hlnode, &port->hlhead[hash]);
 }
 
-void ipvlan_ht_addr_del(struct ipvl_addr *addr, bool sync)
+void ipvlan_ht_addr_del(struct ipvl_addr *addr)
 {
 	hlist_del_init_rcu(&addr->hlnode);
-	if (sync)
-		synchronize_rcu();
 }
 
 struct ipvl_addr *ipvlan_find_addr(const struct ipvl_dev *ipvlan,
@@ -531,7 +529,7 @@
 int ipvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
-	struct ipvl_port *port = ipvlan_port_get_rcu(ipvlan->phy_dev);
+	struct ipvl_port *port = ipvlan_port_get_rcu_bh(ipvlan->phy_dev);
 
 	if (!port)
 		goto out;
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 1acc283..20b58bd 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -153,10 +153,9 @@
 	else
 		dev->flags &= ~IFF_NOARP;
 
-	if (ipvlan->ipv6cnt > 0 || ipvlan->ipv4cnt > 0) {
-		list_for_each_entry(addr, &ipvlan->addrs, anode)
-			ipvlan_ht_addr_add(ipvlan, addr);
-	}
+	list_for_each_entry(addr, &ipvlan->addrs, anode)
+		ipvlan_ht_addr_add(ipvlan, addr);
+
 	return dev_uc_add(phy_dev, phy_dev->dev_addr);
 }
 
@@ -171,10 +170,9 @@
 
 	dev_uc_del(phy_dev, phy_dev->dev_addr);
 
-	if (ipvlan->ipv6cnt > 0 || ipvlan->ipv4cnt > 0) {
-		list_for_each_entry(addr, &ipvlan->addrs, anode)
-			ipvlan_ht_addr_del(addr, !dev->dismantle);
-	}
+	list_for_each_entry(addr, &ipvlan->addrs, anode)
+		ipvlan_ht_addr_del(addr);
+
 	return 0;
 }
 
@@ -471,8 +469,6 @@
 	ipvlan->port = port;
 	ipvlan->sfeatures = IPVLAN_FEATURES;
 	INIT_LIST_HEAD(&ipvlan->addrs);
-	ipvlan->ipv4cnt = 0;
-	ipvlan->ipv6cnt = 0;
 
 	/* TODO Probably put random address here to be presented to the
 	 * world but keep using the physical-dev address for the outgoing
@@ -508,12 +504,12 @@
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 	struct ipvl_addr *addr, *next;
 
-	if (ipvlan->ipv6cnt > 0 || ipvlan->ipv4cnt > 0) {
-		list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) {
-			ipvlan_ht_addr_del(addr, !dev->dismantle);
-			list_del(&addr->anode);
-		}
+	list_for_each_entry_safe(addr, next, &ipvlan->addrs, anode) {
+		ipvlan_ht_addr_del(addr);
+		list_del(&addr->anode);
+		kfree_rcu(addr, rcu);
 	}
+
 	list_del_rcu(&ipvlan->pnode);
 	unregister_netdevice_queue(dev, head);
 	netdev_upper_dev_unlink(ipvlan->phy_dev, dev);
@@ -627,7 +623,7 @@
 	memcpy(&addr->ip6addr, ip6_addr, sizeof(struct in6_addr));
 	addr->atype = IPVL_IPV6;
 	list_add_tail(&addr->anode, &ipvlan->addrs);
-	ipvlan->ipv6cnt++;
+
 	/* If the interface is not up, the address will be added to the hash
 	 * list by ipvlan_open.
 	 */
@@ -645,10 +641,8 @@
 	if (!addr)
 		return;
 
-	ipvlan_ht_addr_del(addr, true);
+	ipvlan_ht_addr_del(addr);
 	list_del(&addr->anode);
-	ipvlan->ipv6cnt--;
-	WARN_ON(ipvlan->ipv6cnt < 0);
 	kfree_rcu(addr, rcu);
 
 	return;
@@ -661,6 +655,10 @@
 	struct net_device *dev = (struct net_device *)if6->idev->dev;
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 
+	/* FIXME IPv6 autoconf calls us from bh without RTNL */
+	if (in_softirq())
+		return NOTIFY_DONE;
+
 	if (!netif_is_ipvlan(dev))
 		return NOTIFY_DONE;
 
@@ -699,7 +697,7 @@
 	memcpy(&addr->ip4addr, ip4_addr, sizeof(struct in_addr));
 	addr->atype = IPVL_IPV4;
 	list_add_tail(&addr->anode, &ipvlan->addrs);
-	ipvlan->ipv4cnt++;
+
 	/* If the interface is not up, the address will be added to the hash
 	 * list by ipvlan_open.
 	 */
@@ -717,10 +715,8 @@
 	if (!addr)
 		return;
 
-	ipvlan_ht_addr_del(addr, true);
+	ipvlan_ht_addr_del(addr);
 	list_del(&addr->anode);
-	ipvlan->ipv4cnt--;
-	WARN_ON(ipvlan->ipv4cnt < 0);
 	kfree_rcu(addr, rcu);
 
 	return;
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index f837080..edd7734 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -719,6 +719,7 @@
 	struct virtio_net_hdr vnet_hdr = { 0 };
 	int vnet_hdr_len = 0;
 	int copylen = 0;
+	int depth;
 	bool zerocopy = false;
 	size_t linear;
 	ssize_t n;
@@ -804,6 +805,12 @@
 
 	skb_probe_transport_header(skb, ETH_HLEN);
 
+	/* Move network header to the right position for VLAN tagged packets */
+	if ((skb->protocol == htons(ETH_P_8021Q) ||
+	     skb->protocol == htons(ETH_P_8021AD)) &&
+	    __vlan_get_protocol(skb, skb->protocol, &depth) != 0)
+		skb_set_network_header(skb, depth);
+
 	rcu_read_lock();
 	vlan = rcu_dereference(q->vlan);
 	/* copy skb_ubuf_info for callback when skb has no error */
@@ -1355,6 +1362,7 @@
 	class_unregister(macvtap_class);
 	cdev_del(&macvtap_cdev);
 	unregister_chrdev_region(macvtap_major, MACVTAP_NUM_DEVS);
+	idr_destroy(&minor_idr);
 }
 module_exit(macvtap_exit);
 
diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c
index 3cc316cb..d8757bf 100644
--- a/drivers/net/ntb_netdev.c
+++ b/drivers/net/ntb_netdev.c
@@ -102,6 +102,12 @@
 
 	netdev_dbg(ndev, "%s: %d byte payload received\n", __func__, len);
 
+	if (len < 0) {
+		ndev->stats.rx_errors++;
+		ndev->stats.rx_length_errors++;
+		goto enqueue_again;
+	}
+
 	skb_put(skb, len);
 	skb->protocol = eth_type_trans(skb, ndev);
 	skb->ip_summed = CHECKSUM_NONE;
@@ -121,6 +127,7 @@
 		return;
 	}
 
+enqueue_again:
 	rc = ntb_transport_rx_enqueue(qp, skb, skb->data, ndev->mtu + ETH_HLEN);
 	if (rc) {
 		dev_kfree_skb(skb);
@@ -184,7 +191,7 @@
 
 		rc = ntb_transport_rx_enqueue(dev->qp, skb, skb->data,
 					      ndev->mtu + ETH_HLEN);
-		if (rc == -EINVAL) {
+		if (rc) {
 			dev_kfree_skb(skb);
 			goto err;
 		}
diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index cf18940..cb86d7a 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -191,7 +191,7 @@
 
 config MDIO_BUS_MUX_MMIOREG
 	tristate "Support for MMIO device-controlled MDIO bus multiplexers"
-	depends on OF_MDIO
+	depends on OF_MDIO && HAS_IOMEM
 	select MDIO_BUS_MUX
 	help
 	  This module provides a driver for MDIO bus multiplexers that
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index c7a12e2..8a3bf54 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -164,7 +164,7 @@
 			return ret;
 	}
 
-	if ((phydev->interface >= PHY_INTERFACE_MODE_RGMII_ID) ||
+	if ((phydev->interface >= PHY_INTERFACE_MODE_RGMII_ID) &&
 	    (phydev->interface <= PHY_INTERFACE_MODE_RGMII_RXID)) {
 		val = phy_read_mmd_indirect(phydev, DP83867_RGMIICTL,
 					    DP83867_DEVADDR, phydev->addr);
diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c
index 095ef3f..46a14cb 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -421,6 +421,8 @@
 {
 	struct phy_device *phydev = to_phy_device(dev);
 	struct phy_driver *phydrv = to_phy_driver(drv);
+	const int num_ids = ARRAY_SIZE(phydev->c45_ids.device_ids);
+	int i;
 
 	if (of_driver_match_device(dev, drv))
 		return 1;
@@ -428,8 +430,21 @@
 	if (phydrv->match_phy_device)
 		return phydrv->match_phy_device(phydev);
 
-	return (phydrv->phy_id & phydrv->phy_id_mask) ==
-		(phydev->phy_id & phydrv->phy_id_mask);
+	if (phydev->is_c45) {
+		for (i = 1; i < num_ids; i++) {
+			if (!(phydev->c45_ids.devices_in_package & (1 << i)))
+				continue;
+
+			if ((phydrv->phy_id & phydrv->phy_id_mask) ==
+			    (phydev->c45_ids.device_ids[i] &
+			     phydrv->phy_id_mask))
+				return 1;
+		}
+		return 0;
+	} else {
+		return (phydrv->phy_id & phydrv->phy_id_mask) ==
+			(phydev->phy_id & phydrv->phy_id_mask);
+	}
 }
 
 #ifdef CONFIG_PM
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index b2197b5..1e1fbb0 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -811,6 +811,7 @@
 	bool needs_aneg = false, do_suspend = false;
 	enum phy_state old_state;
 	int err = 0;
+	int old_link;
 
 	mutex_lock(&phydev->lock);
 
@@ -896,11 +897,18 @@
 		phydev->adjust_link(phydev->attached_dev);
 		break;
 	case PHY_RUNNING:
-		/* Only register a CHANGE if we are
-		 * polling or ignoring interrupts
+		/* Only register a CHANGE if we are polling or ignoring
+		 * interrupts and link changed since latest checking.
 		 */
-		if (!phy_interrupt_is_valid(phydev))
-			phydev->state = PHY_CHANGELINK;
+		if (!phy_interrupt_is_valid(phydev)) {
+			old_link = phydev->link;
+			err = phy_read_status(phydev);
+			if (err)
+				break;
+
+			if (old_link != phydev->link)
+				phydev->state = PHY_CHANGELINK;
+		}
 		break;
 	case PHY_CHANGELINK:
 		err = phy_read_status(phydev);
diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c
index c0f6479e..70b0895 100644
--- a/drivers/net/phy/smsc.c
+++ b/drivers/net/phy/smsc.c
@@ -91,19 +91,18 @@
 }
 
 /*
- * The LAN8710/LAN8720 requires a minimum of 2 link pulses within 64ms of each
- * other in order to set the ENERGYON bit and exit EDPD mode.  If a link partner
- * does send the pulses within this interval, the PHY will remained powered
- * down.
- *
- * This workaround will manually toggle the PHY on/off upon calls to read_status
- * in order to generate link test pulses if the link is down.  If a link partner
- * is present, it will respond to the pulses, which will cause the ENERGYON bit
- * to be set and will cause the EDPD mode to be exited.
+ * The LAN87xx suffers from rare absence of the ENERGYON-bit when Ethernet cable
+ * plugs in while LAN87xx is in Energy Detect Power-Down mode. This leads to
+ * unstable detection of plugging in Ethernet cable.
+ * This workaround disables Energy Detect Power-Down mode and waiting for
+ * response on link pulses to detect presence of plugged Ethernet cable.
+ * The Energy Detect Power-Down mode is enabled again in the end of procedure to
+ * save approximately 220 mW of power if cable is unplugged.
  */
 static int lan87xx_read_status(struct phy_device *phydev)
 {
 	int err = genphy_read_status(phydev);
+	int i;
 
 	if (!phydev->link) {
 		/* Disable EDPD to wake up PHY */
@@ -116,8 +115,16 @@
 		if (rc < 0)
 			return rc;
 
-		/* Sleep 64 ms to allow ~5 link test pulses to be sent */
-		msleep(64);
+		/* Wait max 640 ms to detect energy */
+		for (i = 0; i < 64; i++) {
+			/* Sleep to allow link test pulses to be sent */
+			msleep(10);
+			rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS);
+			if (rc < 0)
+				return rc;
+			if (rc & MII_LAN83C185_ENERGYON)
+				break;
+		}
 
 		/* Re-enable EDPD */
 		rc = phy_read(phydev, MII_LAN83C185_CTRL_STATUS);
@@ -191,7 +198,7 @@
 
 	/* basic functions */
 	.config_aneg	= genphy_config_aneg,
-	.read_status	= genphy_read_status,
+	.read_status	= lan87xx_read_status,
 	.config_init	= smsc_phy_config_init,
 	.soft_reset	= smsc_phy_reset,
 
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 9d15566..fa8f504 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -269,9 +269,9 @@
 static void ppp_ccp_closed(struct ppp *ppp);
 static struct compressor *find_compressor(int type);
 static void ppp_get_stats(struct ppp *ppp, struct ppp_stats *st);
-static struct ppp *ppp_create_interface(struct net *net, int unit, int *retp);
+static struct ppp *ppp_create_interface(struct net *net, int unit,
+					struct file *file, int *retp);
 static void init_ppp_file(struct ppp_file *pf, int kind);
-static void ppp_shutdown_interface(struct ppp *ppp);
 static void ppp_destroy_interface(struct ppp *ppp);
 static struct ppp *ppp_find_unit(struct ppp_net *pn, int unit);
 static struct channel *ppp_find_channel(struct ppp_net *pn, int unit);
@@ -392,8 +392,10 @@
 		file->private_data = NULL;
 		if (pf->kind == INTERFACE) {
 			ppp = PF_TO_PPP(pf);
+			rtnl_lock();
 			if (file == ppp->owner)
-				ppp_shutdown_interface(ppp);
+				unregister_netdevice(ppp->dev);
+			rtnl_unlock();
 		}
 		if (atomic_dec_and_test(&pf->refcnt)) {
 			switch (pf->kind) {
@@ -593,8 +595,10 @@
 		mutex_lock(&ppp_mutex);
 		if (pf->kind == INTERFACE) {
 			ppp = PF_TO_PPP(pf);
+			rtnl_lock();
 			if (file == ppp->owner)
-				ppp_shutdown_interface(ppp);
+				unregister_netdevice(ppp->dev);
+			rtnl_unlock();
 		}
 		if (atomic_long_read(&file->f_count) < 2) {
 			ppp_release(NULL, file);
@@ -838,11 +842,10 @@
 		/* Create a new ppp unit */
 		if (get_user(unit, p))
 			break;
-		ppp = ppp_create_interface(net, unit, &err);
+		ppp = ppp_create_interface(net, unit, file, &err);
 		if (!ppp)
 			break;
 		file->private_data = &ppp->file;
-		ppp->owner = file;
 		err = -EFAULT;
 		if (put_user(ppp->file.index, p))
 			break;
@@ -916,6 +919,16 @@
 static __net_exit void ppp_exit_net(struct net *net)
 {
 	struct ppp_net *pn = net_generic(net, ppp_net_id);
+	struct ppp *ppp;
+	LIST_HEAD(list);
+	int id;
+
+	rtnl_lock();
+	idr_for_each_entry(&pn->units_idr, ppp, id)
+		unregister_netdevice_queue(ppp->dev, &list);
+
+	unregister_netdevice_many(&list);
+	rtnl_unlock();
 
 	idr_destroy(&pn->units_idr);
 }
@@ -1088,8 +1101,28 @@
 	return 0;
 }
 
+static void ppp_dev_uninit(struct net_device *dev)
+{
+	struct ppp *ppp = netdev_priv(dev);
+	struct ppp_net *pn = ppp_pernet(ppp->ppp_net);
+
+	ppp_lock(ppp);
+	ppp->closing = 1;
+	ppp_unlock(ppp);
+
+	mutex_lock(&pn->all_ppp_mutex);
+	unit_put(&pn->units_idr, ppp->file.index);
+	mutex_unlock(&pn->all_ppp_mutex);
+
+	ppp->owner = NULL;
+
+	ppp->file.dead = 1;
+	wake_up_interruptible(&ppp->file.rwait);
+}
+
 static const struct net_device_ops ppp_netdev_ops = {
 	.ndo_init	 = ppp_dev_init,
+	.ndo_uninit      = ppp_dev_uninit,
 	.ndo_start_xmit  = ppp_start_xmit,
 	.ndo_do_ioctl    = ppp_net_ioctl,
 	.ndo_get_stats64 = ppp_get_stats64,
@@ -2667,8 +2700,8 @@
  * or if there is already a unit with the requested number.
  * unit == -1 means allocate a new number.
  */
-static struct ppp *
-ppp_create_interface(struct net *net, int unit, int *retp)
+static struct ppp *ppp_create_interface(struct net *net, int unit,
+					struct file *file, int *retp)
 {
 	struct ppp *ppp;
 	struct ppp_net *pn;
@@ -2688,6 +2721,7 @@
 	ppp->mru = PPP_MRU;
 	init_ppp_file(&ppp->file, INTERFACE);
 	ppp->file.hdrlen = PPP_HDRLEN - 2;	/* don't count proto bytes */
+	ppp->owner = file;
 	for (i = 0; i < NUM_NP; ++i)
 		ppp->npmode[i] = NPMODE_PASS;
 	INIT_LIST_HEAD(&ppp->channels);
@@ -2776,34 +2810,6 @@
 }
 
 /*
- * Take down a ppp interface unit - called when the owning file
- * (the one that created the unit) is closed or detached.
- */
-static void ppp_shutdown_interface(struct ppp *ppp)
-{
-	struct ppp_net *pn;
-
-	pn = ppp_pernet(ppp->ppp_net);
-	mutex_lock(&pn->all_ppp_mutex);
-
-	/* This will call dev_close() for us. */
-	ppp_lock(ppp);
-	if (!ppp->closing) {
-		ppp->closing = 1;
-		ppp_unlock(ppp);
-		unregister_netdev(ppp->dev);
-		unit_put(&pn->units_idr, ppp->file.index);
-	} else
-		ppp_unlock(ppp);
-
-	ppp->file.dead = 1;
-	ppp->owner = NULL;
-	wake_up_interruptible(&ppp->file.rwait);
-
-	mutex_unlock(&pn->all_ppp_mutex);
-}
-
-/*
  * Free the memory used by a ppp unit.  This is only called once
  * there are no channels connected to the unit and no file structs
  * that reference the unit.
diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index 4545e78..35a2bff 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -523,6 +523,7 @@
 #define REALTEK_VENDOR_ID	0x0bda
 #define SAMSUNG_VENDOR_ID	0x04e8
 #define LENOVO_VENDOR_ID	0x17ef
+#define NVIDIA_VENDOR_ID	0x0955
 
 static const struct usb_device_id	products[] = {
 /* BLACKLIST !!
@@ -710,6 +711,13 @@
 	.driver_info = 0,
 },
 
+/* NVIDIA Tegra USB 3.0 Ethernet Adapters (based on Realtek RTL8153) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(NVIDIA_VENDOR_ID, 0x09ff, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* WHITELIST!!!
  *
  * CDC Ether uses two interfaces, not necessarily consecutive.
diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index e4b7a47a..efc18e0 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -158,7 +158,7 @@
 	if (!cdc_ncm_comm_intf_is_mbim(intf->cur_altsetting))
 		goto err;
 
-	ret = cdc_ncm_bind_common(dev, intf, data_altsetting);
+	ret = cdc_ncm_bind_common(dev, intf, data_altsetting, 0);
 	if (ret)
 		goto err;
 
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 8067b8f..db40175 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -6,7 +6,7 @@
  * Original author: Hans Petter Selasky <hans.petter.selasky@stericsson.com>
  *
  * USB Host Driver for Network Control Model (NCM)
- * http://www.usb.org/developers/devclass_docs/NCM10.zip
+ * http://www.usb.org/developers/docs/devclass_docs/NCM10_012011.zip
  *
  * The NCM encoding, decoding and initialization logic
  * derives from FreeBSD 8.x. if_cdce.c and if_cdcereg.h
@@ -684,10 +684,12 @@
 		ctx->tx_curr_skb = NULL;
 	}
 
+	kfree(ctx->delayed_ndp16);
+
 	kfree(ctx);
 }
 
-int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting)
+int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags)
 {
 	const struct usb_cdc_union_desc *union_desc = NULL;
 	struct cdc_ncm_ctx *ctx;
@@ -855,6 +857,17 @@
 	/* finish setting up the device specific data */
 	cdc_ncm_setup(dev);
 
+	/* Device-specific flags */
+	ctx->drvflags = drvflags;
+
+	/* Allocate the delayed NDP if needed. */
+	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) {
+		ctx->delayed_ndp16 = kzalloc(ctx->max_ndp_size, GFP_KERNEL);
+		if (!ctx->delayed_ndp16)
+			goto error2;
+		dev_info(&intf->dev, "NDP will be placed at end of frame for this device.");
+	}
+
 	/* override ethtool_ops */
 	dev->net->ethtool_ops = &cdc_ncm_ethtool_ops;
 
@@ -954,8 +967,11 @@
 	if (cdc_ncm_select_altsetting(intf) != CDC_NCM_COMM_ALTSETTING_NCM)
 		return -ENODEV;
 
-	/* The NCM data altsetting is fixed */
-	ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM);
+	/* The NCM data altsetting is fixed, so we hard-coded it.
+	 * Additionally, generic NCM devices are assumed to accept arbitrarily
+	 * placed NDP.
+	 */
+	ret = cdc_ncm_bind_common(dev, intf, CDC_NCM_DATA_ALTSETTING_NCM, 0);
 
 	/*
 	 * We should get an event when network connection is "connected" or
@@ -986,6 +1002,14 @@
 	struct usb_cdc_ncm_nth16 *nth16 = (void *)skb->data;
 	size_t ndpoffset = le16_to_cpu(nth16->wNdpIndex);
 
+	/* If NDP should be moved to the end of the NCM package, we can't follow the
+	* NTH16 header as we would normally do. NDP isn't written to the SKB yet, and
+	* the wNdpIndex field in the header is actually not consistent with reality. It will be later.
+	*/
+	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END)
+		if (ctx->delayed_ndp16->dwSignature == sign)
+			return ctx->delayed_ndp16;
+
 	/* follow the chain of NDPs, looking for a match */
 	while (ndpoffset) {
 		ndp16 = (struct usb_cdc_ncm_ndp16 *)(skb->data + ndpoffset);
@@ -995,7 +1019,8 @@
 	}
 
 	/* align new NDP */
-	cdc_ncm_align_tail(skb, ctx->tx_ndp_modulus, 0, ctx->tx_max);
+	if (!(ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END))
+		cdc_ncm_align_tail(skb, ctx->tx_ndp_modulus, 0, ctx->tx_max);
 
 	/* verify that there is room for the NDP and the datagram (reserve) */
 	if ((ctx->tx_max - skb->len - reserve) < ctx->max_ndp_size)
@@ -1008,7 +1033,11 @@
 		nth16->wNdpIndex = cpu_to_le16(skb->len);
 
 	/* push a new empty NDP */
-	ndp16 = (struct usb_cdc_ncm_ndp16 *)memset(skb_put(skb, ctx->max_ndp_size), 0, ctx->max_ndp_size);
+	if (!(ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END))
+		ndp16 = (struct usb_cdc_ncm_ndp16 *)memset(skb_put(skb, ctx->max_ndp_size), 0, ctx->max_ndp_size);
+	else
+		ndp16 = ctx->delayed_ndp16;
+
 	ndp16->dwSignature = sign;
 	ndp16->wLength = cpu_to_le16(sizeof(struct usb_cdc_ncm_ndp16) + sizeof(struct usb_cdc_ncm_dpe16));
 	return ndp16;
@@ -1023,6 +1052,15 @@
 	struct sk_buff *skb_out;
 	u16 n = 0, index, ndplen;
 	u8 ready2send = 0;
+	u32 delayed_ndp_size;
+
+	/* When our NDP gets written in cdc_ncm_ndp(), then skb_out->len gets updated
+	 * accordingly. Otherwise, we should check here.
+	 */
+	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END)
+		delayed_ndp_size = ctx->max_ndp_size;
+	else
+		delayed_ndp_size = 0;
 
 	/* if there is a remaining skb, it gets priority */
 	if (skb != NULL) {
@@ -1077,7 +1115,7 @@
 		cdc_ncm_align_tail(skb_out,  ctx->tx_modulus, ctx->tx_remainder, ctx->tx_max);
 
 		/* check if we had enough room left for both NDP and frame */
-		if (!ndp16 || skb_out->len + skb->len > ctx->tx_max) {
+		if (!ndp16 || skb_out->len + skb->len + delayed_ndp_size > ctx->tx_max) {
 			if (n == 0) {
 				/* won't fit, MTU problem? */
 				dev_kfree_skb_any(skb);
@@ -1150,6 +1188,17 @@
 		/* variables will be reset at next call */
 	}
 
+	/* If requested, put NDP at end of frame. */
+	if (ctx->drvflags & CDC_NCM_FLAG_NDP_TO_END) {
+		nth16 = (struct usb_cdc_ncm_nth16 *)skb_out->data;
+		cdc_ncm_align_tail(skb_out, ctx->tx_ndp_modulus, 0, ctx->tx_max);
+		nth16->wNdpIndex = cpu_to_le16(skb_out->len);
+		memcpy(skb_put(skb_out, ctx->max_ndp_size), ctx->delayed_ndp16, ctx->max_ndp_size);
+
+		/* Zero out delayed NDP - signature checking will naturally fail. */
+		ndp16 = memset(ctx->delayed_ndp16, 0, ctx->max_ndp_size);
+	}
+
 	/* If collected data size is less or equal ctx->min_tx_pkt
 	 * bytes, we send buffers as it is. If we get more data, it
 	 * would be more efficient for USB HS mobile device with DMA
diff --git a/drivers/net/usb/huawei_cdc_ncm.c b/drivers/net/usb/huawei_cdc_ncm.c
index 735f7da..2680a65 100644
--- a/drivers/net/usb/huawei_cdc_ncm.c
+++ b/drivers/net/usb/huawei_cdc_ncm.c
@@ -73,11 +73,14 @@
 	struct usb_driver *subdriver = ERR_PTR(-ENODEV);
 	int ret = -ENODEV;
 	struct huawei_cdc_ncm_state *drvstate = (void *)&usbnet_dev->data;
+	int drvflags = 0;
 
 	/* altsetting should always be 1 for NCM devices - so we hard-coded
-	 * it here
+	 * it here. Some huawei devices will need the NDP part of the NCM package to
+	 * be at the end of the frame.
 	 */
-	ret = cdc_ncm_bind_common(usbnet_dev, intf, 1);
+	drvflags |= CDC_NCM_FLAG_NDP_TO_END;
+	ret = cdc_ncm_bind_common(usbnet_dev, intf, 1, drvflags);
 	if (ret)
 		goto err;
 
diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index f603f36..64a60af 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -757,6 +757,7 @@
 	{QMI_FIXED_INTF(0x1199, 0x901c, 8)},    /* Sierra Wireless EM7700 */
 	{QMI_FIXED_INTF(0x1199, 0x901f, 8)},    /* Sierra Wireless EM7355 */
 	{QMI_FIXED_INTF(0x1199, 0x9041, 8)},	/* Sierra Wireless MC7305/MC7355 */
+	{QMI_FIXED_INTF(0x1199, 0x9041, 10)},	/* Sierra Wireless MC7305/MC7355 */
 	{QMI_FIXED_INTF(0x1199, 0x9051, 8)},	/* Netgear AirCard 340U */
 	{QMI_FIXED_INTF(0x1199, 0x9053, 8)},	/* Sierra Wireless Modem */
 	{QMI_FIXED_INTF(0x1199, 0x9054, 8)},	/* Sierra Wireless Modem */
@@ -784,6 +785,7 @@
 	{QMI_FIXED_INTF(0x413c, 0x81a4, 8)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81a8, 8)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */
 	{QMI_FIXED_INTF(0x413c, 0x81a9, 8)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
+	{QMI_FIXED_INTF(0x03f0, 0x4e1d, 8)},	/* HP lt4111 LTE/EV-DO/HSPA+ Gobi 4G Module */
 	{QMI_FIXED_INTF(0x03f0, 0x581d, 4)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Module (Huawei me906e) */
 
 	/* 4. Gobi 1000 devices */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index aafa1a1..ad8cbc6 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -27,7 +27,7 @@
 #include <linux/usb/cdc.h>
 
 /* Version Information */
-#define DRIVER_VERSION "v1.08.0 (2015/01/13)"
+#define DRIVER_VERSION "v1.08.1 (2015/07/28)"
 #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
 #define DRIVER_DESC "Realtek RTL8152/RTL8153 Based USB Ethernet Adapters"
 #define MODULENAME "r8152"
@@ -494,6 +494,7 @@
 #define VENDOR_ID_REALTEK		0x0bda
 #define VENDOR_ID_SAMSUNG		0x04e8
 #define VENDOR_ID_LENOVO		0x17ef
+#define VENDOR_ID_NVIDIA		0x0955
 
 #define MCU_TYPE_PLA			0x0100
 #define MCU_TYPE_USB			0x0000
@@ -1901,11 +1902,10 @@
 static void rtl8152_tx_timeout(struct net_device *netdev)
 {
 	struct r8152 *tp = netdev_priv(netdev);
-	int i;
 
 	netif_warn(tp, tx_err, netdev, "Tx timeout\n");
-	for (i = 0; i < RTL8152_MAX_TX; i++)
-		usb_unlink_urb(tp->tx_info[i].urb);
+
+	usb_queue_reset_device(tp->intf);
 }
 
 static void rtl8152_set_rx_mode(struct net_device *netdev)
@@ -2074,7 +2074,6 @@
 {
 	int i, ret = 0;
 
-	napi_disable(&tp->napi);
 	INIT_LIST_HEAD(&tp->rx_done);
 	for (i = 0; i < RTL8152_MAX_RX; i++) {
 		INIT_LIST_HEAD(&tp->rx_info[i].list);
@@ -2082,7 +2081,6 @@
 		if (ret)
 			break;
 	}
-	napi_enable(&tp->napi);
 
 	if (ret && ++i < RTL8152_MAX_RX) {
 		struct list_head rx_queue;
@@ -2165,6 +2163,7 @@
 	if (test_bit(RTL8152_UNPLUG, &tp->flags))
 		return -ENODEV;
 
+	usb_disable_lpm(tp->udev);
 	set_tx_qlen(tp);
 	rtl_set_eee_plus(tp);
 	r8153_set_rx_early_timeout(tp);
@@ -2336,11 +2335,61 @@
 		device_set_wakeup_enable(&tp->udev->dev, false);
 }
 
+static void r8153_u1u2en(struct r8152 *tp, bool enable)
+{
+	u8 u1u2[8];
+
+	if (enable)
+		memset(u1u2, 0xff, sizeof(u1u2));
+	else
+		memset(u1u2, 0x00, sizeof(u1u2));
+
+	usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2);
+}
+
+static void r8153_u2p3en(struct r8152 *tp, bool enable)
+{
+	u32 ocp_data;
+
+	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL);
+	if (enable && tp->version != RTL_VER_03 && tp->version != RTL_VER_04)
+		ocp_data |= U2P3_ENABLE;
+	else
+		ocp_data &= ~U2P3_ENABLE;
+	ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data);
+}
+
+static void r8153_power_cut_en(struct r8152 *tp, bool enable)
+{
+	u32 ocp_data;
+
+	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_POWER_CUT);
+	if (enable)
+		ocp_data |= PWR_EN | PHASE2_EN;
+	else
+		ocp_data &= ~(PWR_EN | PHASE2_EN);
+	ocp_write_word(tp, MCU_TYPE_USB, USB_POWER_CUT, ocp_data);
+
+	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0);
+	ocp_data &= ~PCUT_STATUS;
+	ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data);
+}
+
+static bool rtl_can_wakeup(struct r8152 *tp)
+{
+	struct usb_device *udev = tp->udev;
+
+	return (udev->actconfig->desc.bmAttributes & USB_CONFIG_ATT_WAKEUP);
+}
+
 static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable)
 {
 	if (enable) {
 		u32 ocp_data;
 
+		r8153_u1u2en(tp, false);
+		r8153_u2p3en(tp, false);
+
 		__rtl_set_wol(tp, WAKE_ANY);
 
 		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG);
@@ -2352,6 +2401,8 @@
 		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
 	} else {
 		__rtl_set_wol(tp, tp->saved_wolopts);
+		r8153_u2p3en(tp, true);
+		r8153_u1u2en(tp, true);
 	}
 }
 
@@ -2598,46 +2649,6 @@
 	set_bit(PHY_RESET, &tp->flags);
 }
 
-static void r8153_u1u2en(struct r8152 *tp, bool enable)
-{
-	u8 u1u2[8];
-
-	if (enable)
-		memset(u1u2, 0xff, sizeof(u1u2));
-	else
-		memset(u1u2, 0x00, sizeof(u1u2));
-
-	usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2);
-}
-
-static void r8153_u2p3en(struct r8152 *tp, bool enable)
-{
-	u32 ocp_data;
-
-	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL);
-	if (enable)
-		ocp_data |= U2P3_ENABLE;
-	else
-		ocp_data &= ~U2P3_ENABLE;
-	ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data);
-}
-
-static void r8153_power_cut_en(struct r8152 *tp, bool enable)
-{
-	u32 ocp_data;
-
-	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_POWER_CUT);
-	if (enable)
-		ocp_data |= PWR_EN | PHASE2_EN;
-	else
-		ocp_data &= ~(PWR_EN | PHASE2_EN);
-	ocp_write_word(tp, MCU_TYPE_USB, USB_POWER_CUT, ocp_data);
-
-	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0);
-	ocp_data &= ~PCUT_STATUS;
-	ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data);
-}
-
 static void r8153_first_init(struct r8152 *tp)
 {
 	u32 ocp_data;
@@ -2780,6 +2791,7 @@
 	r8153_disable_aldps(tp);
 	rtl_disable(tp);
 	r8153_enable_aldps(tp);
+	usb_enable_lpm(tp->udev);
 }
 
 static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u16 speed, u8 duplex)
@@ -2900,9 +2912,13 @@
 	if (test_bit(RTL8152_UNPLUG, &tp->flags))
 		return;
 
+	r8153_u1u2en(tp, false);
 	r8153_disable_aldps(tp);
 	r8153_first_init(tp);
 	r8153_enable_aldps(tp);
+	r8153_u2p3en(tp, true);
+	r8153_u1u2en(tp, true);
+	usb_enable_lpm(tp->udev);
 }
 
 static void rtl8153_down(struct r8152 *tp)
@@ -2913,6 +2929,7 @@
 	}
 
 	r8153_u1u2en(tp, false);
+	r8153_u2p3en(tp, false);
 	r8153_power_cut_en(tp, false);
 	r8153_disable_aldps(tp);
 	r8153_enter_oob(tp);
@@ -2931,8 +2948,10 @@
 		if (!netif_carrier_ok(netdev)) {
 			tp->rtl_ops.enable(tp);
 			set_bit(RTL8152_SET_RX_MODE, &tp->flags);
+			napi_disable(&tp->napi);
 			netif_carrier_on(netdev);
 			rtl_start_rx(tp);
+			napi_enable(&tp->napi);
 		}
 	} else {
 		if (netif_carrier_ok(netdev)) {
@@ -3251,6 +3270,7 @@
 		msleep(20);
 	}
 
+	usb_disable_lpm(tp->udev);
 	r8153_u2p3en(tp, false);
 
 	if (tp->version == RTL_VER_04) {
@@ -3318,6 +3338,59 @@
 	r8153_enable_aldps(tp);
 	r8152b_enable_fc(tp);
 	rtl_tally_reset(tp);
+	r8153_u2p3en(tp, true);
+}
+
+static int rtl8152_pre_reset(struct usb_interface *intf)
+{
+	struct r8152 *tp = usb_get_intfdata(intf);
+	struct net_device *netdev;
+
+	if (!tp)
+		return 0;
+
+	netdev = tp->netdev;
+	if (!netif_running(netdev))
+		return 0;
+
+	napi_disable(&tp->napi);
+	clear_bit(WORK_ENABLE, &tp->flags);
+	usb_kill_urb(tp->intr_urb);
+	cancel_delayed_work_sync(&tp->schedule);
+	if (netif_carrier_ok(netdev)) {
+		netif_stop_queue(netdev);
+		mutex_lock(&tp->control);
+		tp->rtl_ops.disable(tp);
+		mutex_unlock(&tp->control);
+	}
+
+	return 0;
+}
+
+static int rtl8152_post_reset(struct usb_interface *intf)
+{
+	struct r8152 *tp = usb_get_intfdata(intf);
+	struct net_device *netdev;
+
+	if (!tp)
+		return 0;
+
+	netdev = tp->netdev;
+	if (!netif_running(netdev))
+		return 0;
+
+	set_bit(WORK_ENABLE, &tp->flags);
+	if (netif_carrier_ok(netdev)) {
+		mutex_lock(&tp->control);
+		tp->rtl_ops.enable(tp);
+		rtl8152_set_rx_mode(netdev);
+		mutex_unlock(&tp->control);
+		netif_wake_queue(netdev);
+	}
+
+	napi_enable(&tp->napi);
+
+	return 0;
 }
 
 static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
@@ -3373,9 +3446,11 @@
 		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 			rtl_runtime_suspend_enable(tp, false);
 			clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+			napi_disable(&tp->napi);
 			set_bit(WORK_ENABLE, &tp->flags);
 			if (netif_carrier_ok(tp->netdev))
 				rtl_start_rx(tp);
+			napi_enable(&tp->napi);
 		} else {
 			tp->rtl_ops.up(tp);
 			rtl8152_set_speed(tp, AUTONEG_ENABLE,
@@ -3402,12 +3477,15 @@
 	if (usb_autopm_get_interface(tp->intf) < 0)
 		return;
 
-	mutex_lock(&tp->control);
-
-	wol->supported = WAKE_ANY;
-	wol->wolopts = __rtl_get_wol(tp);
-
-	mutex_unlock(&tp->control);
+	if (!rtl_can_wakeup(tp)) {
+		wol->supported = 0;
+		wol->wolopts = 0;
+	} else {
+		mutex_lock(&tp->control);
+		wol->supported = WAKE_ANY;
+		wol->wolopts = __rtl_get_wol(tp);
+		mutex_unlock(&tp->control);
+	}
 
 	usb_autopm_put_interface(tp->intf);
 }
@@ -3417,6 +3495,9 @@
 	struct r8152 *tp = netdev_priv(dev);
 	int ret;
 
+	if (!rtl_can_wakeup(tp))
+		return -EOPNOTSUPP;
+
 	ret = usb_autopm_get_interface(tp->intf);
 	if (ret < 0)
 		goto out_set_wol;
@@ -4058,6 +4139,9 @@
 		goto out1;
 	}
 
+	if (!rtl_can_wakeup(tp))
+		__rtl_set_wol(tp, 0);
+
 	tp->saved_wolopts = __rtl_get_wol(tp);
 	if (tp->saved_wolopts)
 		device_set_wakeup_enable(&udev->dev, true);
@@ -4117,6 +4201,7 @@
 	{REALTEK_USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x7205)},
 	{REALTEK_USB_DEVICE(VENDOR_ID_LENOVO,  0x304f)},
+	{REALTEK_USB_DEVICE(VENDOR_ID_NVIDIA,  0x09ff)},
 	{}
 };
 
@@ -4130,6 +4215,8 @@
 	.suspend =	rtl8152_suspend,
 	.resume =	rtl8152_resume,
 	.reset_resume =	rtl8152_resume,
+	.pre_reset =	rtl8152_pre_reset,
+	.post_reset =	rtl8152_post_reset,
 	.supports_autosuspend = 1,
 	.disable_hub_initiated_lpm = 1,
 };
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 63c7810..237f8e5 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1756,9 +1756,9 @@
 	/* Do we support "hardware" checksums? */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_CSUM)) {
 		/* This opens up the world of extra features. */
-		dev->hw_features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
+		dev->hw_features |= NETIF_F_HW_CSUM | NETIF_F_SG;
 		if (csum)
-			dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
+			dev->features |= NETIF_F_HW_CSUM | NETIF_F_SG;
 
 		if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) {
 			dev->hw_features |= NETIF_F_TSO | NETIF_F_UFO
@@ -1828,7 +1828,8 @@
 	else
 		vi->hdr_len = sizeof(struct virtio_net_hdr);
 
-	if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT))
+	if (virtio_has_feature(vdev, VIRTIO_F_ANY_LAYOUT) ||
+	    virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
 		vi->any_header_sg = true;
 
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_CTRL_VQ))
diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index da11bb5..46f4cad 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -1216,7 +1216,7 @@
 	static const u32 rxprod_reg[2] = {
 		VMXNET3_REG_RXPROD, VMXNET3_REG_RXPROD2
 	};
-	u32 num_rxd = 0;
+	u32 num_pkts = 0;
 	bool skip_page_frags = false;
 	struct Vmxnet3_RxCompDesc *rcd;
 	struct vmxnet3_rx_ctx *ctx = &rq->rx_ctx;
@@ -1235,13 +1235,12 @@
 		struct Vmxnet3_RxDesc *rxd;
 		u32 idx, ring_idx;
 		struct vmxnet3_cmd_ring	*ring = NULL;
-		if (num_rxd >= quota) {
+		if (num_pkts >= quota) {
 			/* we may stop even before we see the EOP desc of
 			 * the current pkt
 			 */
 			break;
 		}
-		num_rxd++;
 		BUG_ON(rcd->rqID != rq->qid && rcd->rqID != rq->qid2);
 		idx = rcd->rxdIdx;
 		ring_idx = rcd->rqID < adapter->num_rx_queues ? 0 : 1;
@@ -1413,6 +1412,7 @@
 				napi_gro_receive(&rq->napi, skb);
 
 			ctx->skb = NULL;
+			num_pkts++;
 		}
 
 rcd_done:
@@ -1443,7 +1443,7 @@
 				  &rq->comp_ring.base[rq->comp_ring.next2proc].rcd, &rxComp);
 	}
 
-	return num_rxd;
+	return num_pkts;
 }
 
 
diff --git a/drivers/net/wan/cosa.c b/drivers/net/wan/cosa.c
index 7193b73..848ea6a 100644
--- a/drivers/net/wan/cosa.c
+++ b/drivers/net/wan/cosa.c
@@ -589,7 +589,8 @@
 		chan->netdev->base_addr = chan->cosa->datareg;
 		chan->netdev->irq = chan->cosa->irq;
 		chan->netdev->dma = chan->cosa->dma;
-		if (register_hdlc_device(chan->netdev)) {
+		err = register_hdlc_device(chan->netdev);
+		if (err) {
 			netdev_warn(chan->netdev,
 				    "register_hdlc_device() failed\n");
 			free_netdev(chan->netdev);
diff --git a/drivers/net/wan/z85230.c b/drivers/net/wan/z85230.c
index feacc3b..2f0bd69 100644
--- a/drivers/net/wan/z85230.c
+++ b/drivers/net/wan/z85230.c
@@ -1044,7 +1044,7 @@
  *	@dev: The network device to attach
  *	@c: The Z8530 channel to configure in sync DMA mode.
  *
- *	Set up a Z85x30 device for synchronous DMA tranmission. One
+ *	Set up a Z85x30 device for synchronous DMA transmission. One
  *	ISA DMA channel must be available for this to work. The receive
  *	side is run in PIO mode, but then it has the bigger FIFO.
  */
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 5e15e8e..a31a680 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -279,6 +279,7 @@
 		return;
 	case AR9300_DEVID_QCA956X:
 		ah->hw_version.macVersion = AR_SREV_VERSION_9561;
+		return;
 	}
 
 	val = REG_READ(ah, AR_SREV) & AR_SREV_ID;
diff --git a/drivers/net/wireless/b43/tables_nphy.c b/drivers/net/wireless/b43/tables_nphy.c
index 25d1cbd..b2f0d24 100644
--- a/drivers/net/wireless/b43/tables_nphy.c
+++ b/drivers/net/wireless/b43/tables_nphy.c
@@ -3728,7 +3728,7 @@
 		switch (phy->rev) {
 		case 6:
 		case 5:
-			if (sprom->fem.ghz5.extpa_gain == 3)
+			if (sprom->fem.ghz2.extpa_gain == 3)
 				return b43_ntab_tx_gain_epa_rev3_hi_pwr_2g;
 			/* fall through */
 		case 4:
diff --git a/drivers/net/wireless/iwlwifi/iwl-fh.h b/drivers/net/wireless/iwlwifi/iwl-fh.h
index d560648..d45dc02 100644
--- a/drivers/net/wireless/iwlwifi/iwl-fh.h
+++ b/drivers/net/wireless/iwlwifi/iwl-fh.h
@@ -438,6 +438,12 @@
 #define RX_QUEUE_MASK                         255
 #define RX_QUEUE_SIZE_LOG                     8
 
+/*
+ * RX related structures and functions
+ */
+#define RX_FREE_BUFFERS 64
+#define RX_LOW_WATERMARK 8
+
 /**
  * struct iwl_rb_status - reserve buffer status
  * 	host memory mapped FH registers
diff --git a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
index 80fefe7..3b8e85e 100644
--- a/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/iwlwifi/iwl-nvm-parse.c
@@ -540,13 +540,11 @@
 		hw_addr = (const u8 *)(mac_override +
 				 MAC_ADDRESS_OVERRIDE_FAMILY_8000);
 
-		/* The byte order is little endian 16 bit, meaning 214365 */
-		data->hw_addr[0] = hw_addr[1];
-		data->hw_addr[1] = hw_addr[0];
-		data->hw_addr[2] = hw_addr[3];
-		data->hw_addr[3] = hw_addr[2];
-		data->hw_addr[4] = hw_addr[5];
-		data->hw_addr[5] = hw_addr[4];
+		/*
+		 * Store the MAC address from MAO section.
+		 * No byte swapping is required in MAO section
+		 */
+		memcpy(data->hw_addr, hw_addr, ETH_ALEN);
 
 		/*
 		 * Force the use of the OTP MAC address in case of reserved MAC
diff --git a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
index 5e4cbdb..737774a 100644
--- a/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
+++ b/drivers/net/wireless/iwlwifi/mvm/fw-api-scan.h
@@ -660,7 +660,8 @@
  * iwl_umac_scan_flags
  *@IWL_UMAC_SCAN_FLAG_PREEMPTIVE: scan process triggered by this scan request
  *	can be preempted by other scan requests with higher priority.
- *	The low priority scan is aborted.
+ *	The low priority scan will be resumed when the higher proirity scan is
+ *	completed.
  *@IWL_UMAC_SCAN_FLAG_START_NOTIF: notification will be sent to the driver
  *	when scan starts.
  */
diff --git a/drivers/net/wireless/iwlwifi/mvm/scan.c b/drivers/net/wireless/iwlwifi/mvm/scan.c
index 5de1449..5514ad6 100644
--- a/drivers/net/wireless/iwlwifi/mvm/scan.c
+++ b/drivers/net/wireless/iwlwifi/mvm/scan.c
@@ -1023,7 +1023,7 @@
 	cmd->scan_priority =
 		iwl_mvm_scan_priority(mvm, IWL_SCAN_PRIORITY_EXT_6);
 
-	if (iwl_mvm_scan_total_iterations(params) == 0)
+	if (iwl_mvm_scan_total_iterations(params) == 1)
 		cmd->ooc_priority =
 			iwl_mvm_scan_priority(mvm, IWL_SCAN_PRIORITY_EXT_6);
 	else
@@ -1109,6 +1109,9 @@
 	cmd->uid = cpu_to_le32(uid);
 	cmd->general_flags = cpu_to_le32(iwl_mvm_scan_umac_flags(mvm, params));
 
+	if (type == IWL_MVM_SCAN_SCHED)
+		cmd->flags = cpu_to_le32(IWL_UMAC_SCAN_FLAG_PREEMPTIVE);
+
 	if (iwl_mvm_scan_use_ebs(mvm, vif, n_iterations))
 		cmd->channel_flags = IWL_SCAN_CHANNEL_FLAG_EBS |
 				     IWL_SCAN_CHANNEL_FLAG_EBS_ACCURATE |
diff --git a/drivers/net/wireless/iwlwifi/mvm/sta.c b/drivers/net/wireless/iwlwifi/mvm/sta.c
index d68dc69..26f076e 100644
--- a/drivers/net/wireless/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/iwlwifi/mvm/sta.c
@@ -1401,6 +1401,7 @@
 	bool mcast = !(keyconf->flags & IEEE80211_KEY_FLAG_PAIRWISE);
 	u8 sta_id;
 	int ret;
+	static const u8 __maybe_unused zero_addr[ETH_ALEN] = {0};
 
 	lockdep_assert_held(&mvm->mutex);
 
@@ -1467,7 +1468,7 @@
 end:
 	IWL_DEBUG_WEP(mvm, "key: cipher=%x len=%d idx=%d sta=%pM ret=%d\n",
 		      keyconf->cipher, keyconf->keylen, keyconf->keyidx,
-		      sta->addr, ret);
+		      sta ? sta->addr : zero_addr, ret);
 	return ret;
 }
 
diff --git a/drivers/net/wireless/iwlwifi/mvm/time-event.c b/drivers/net/wireless/iwlwifi/mvm/time-event.c
index d24b6a8..e472729 100644
--- a/drivers/net/wireless/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/iwlwifi/mvm/time-event.c
@@ -86,7 +86,7 @@
 {
 	lockdep_assert_held(&mvm->time_event_lock);
 
-	if (te_data->id == TE_MAX)
+	if (!te_data->vif)
 		return;
 
 	list_del(&te_data->list);
diff --git a/drivers/net/wireless/iwlwifi/mvm/tx.c b/drivers/net/wireless/iwlwifi/mvm/tx.c
index 7ba7a118..8911686 100644
--- a/drivers/net/wireless/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/iwlwifi/mvm/tx.c
@@ -252,7 +252,7 @@
 
 	if (info->band == IEEE80211_BAND_2GHZ &&
 	    !iwl_mvm_bt_coex_is_shared_ant_avail(mvm))
-		rate_flags = BIT(mvm->cfg->non_shared_ant) << RATE_MCS_ANT_POS;
+		rate_flags = mvm->cfg->non_shared_ant << RATE_MCS_ANT_POS;
 	else
 		rate_flags =
 			BIT(mvm->mgmt_last_antenna_idx) << RATE_MCS_ANT_POS;
diff --git a/drivers/net/wireless/iwlwifi/pcie/drv.c b/drivers/net/wireless/iwlwifi/pcie/drv.c
index 2ed1e4d..9f65c1c 100644
--- a/drivers/net/wireless/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/iwlwifi/pcie/drv.c
@@ -368,12 +368,14 @@
 /* 3165 Series */
 	{IWL_PCI_DEVICE(0x3165, 0x4010, iwl3165_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x3165, 0x4012, iwl3165_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x3166, 0x4212, iwl3165_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x3165, 0x4410, iwl3165_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x3165, 0x4510, iwl3165_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x3165, 0x4110, iwl3165_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x3166, 0x4310, iwl3165_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x3166, 0x4210, iwl3165_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x3165, 0x8010, iwl3165_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x3165, 0x8110, iwl3165_2ac_cfg)},
 
 /* 7265 Series */
 	{IWL_PCI_DEVICE(0x095A, 0x5010, iwl7265_2ac_cfg)},
@@ -426,9 +428,8 @@
 	{IWL_PCI_DEVICE(0x24F4, 0x1130, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F4, 0x1030, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0xC010, iwl8260_2ac_cfg)},
+	{IWL_PCI_DEVICE(0x24F3, 0xC110, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0xD010, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F4, 0xC030, iwl8260_2ac_cfg)},
-	{IWL_PCI_DEVICE(0x24F4, 0xD030, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0xC050, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0xD050, iwl8260_2ac_cfg)},
 	{IWL_PCI_DEVICE(0x24F3, 0x8010, iwl8260_2ac_cfg)},
diff --git a/drivers/net/wireless/iwlwifi/pcie/internal.h b/drivers/net/wireless/iwlwifi/pcie/internal.h
index 31f72a6..376b84e 100644
--- a/drivers/net/wireless/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/iwlwifi/pcie/internal.h
@@ -44,15 +44,6 @@
 #include "iwl-io.h"
 #include "iwl-op-mode.h"
 
-/*
- * RX related structures and functions
- */
-#define RX_NUM_QUEUES 1
-#define RX_POST_REQ_ALLOC 2
-#define RX_CLAIM_REQ_ALLOC 8
-#define RX_POOL_SIZE ((RX_CLAIM_REQ_ALLOC - RX_POST_REQ_ALLOC) * RX_NUM_QUEUES)
-#define RX_LOW_WATERMARK 8
-
 struct iwl_host_cmd;
 
 /*This file includes the declaration that are internal to the
@@ -86,29 +77,29 @@
  * struct iwl_rxq - Rx queue
  * @bd: driver's pointer to buffer of receive buffer descriptors (rbd)
  * @bd_dma: bus address of buffer of receive buffer descriptors (rbd)
+ * @pool:
+ * @queue:
  * @read: Shared index to newest available Rx buffer
  * @write: Shared index to oldest written Rx packet
  * @free_count: Number of pre-allocated buffers in rx_free
- * @used_count: Number of RBDs handled to allocator to use for allocation
  * @write_actual:
- * @rx_free: list of RBDs with allocated RB ready for use
- * @rx_used: list of RBDs with no RB attached
+ * @rx_free: list of free SKBs for use
+ * @rx_used: List of Rx buffers with no SKB
  * @need_update: flag to indicate we need to update read/write index
  * @rb_stts: driver's pointer to receive buffer status
  * @rb_stts_dma: bus address of receive buffer status
  * @lock:
- * @pool: initial pool of iwl_rx_mem_buffer for the queue
- * @queue: actual rx queue
  *
  * NOTE:  rx_free and rx_used are used as a FIFO for iwl_rx_mem_buffers
  */
 struct iwl_rxq {
 	__le32 *bd;
 	dma_addr_t bd_dma;
+	struct iwl_rx_mem_buffer pool[RX_QUEUE_SIZE + RX_FREE_BUFFERS];
+	struct iwl_rx_mem_buffer *queue[RX_QUEUE_SIZE];
 	u32 read;
 	u32 write;
 	u32 free_count;
-	u32 used_count;
 	u32 write_actual;
 	struct list_head rx_free;
 	struct list_head rx_used;
@@ -116,32 +107,6 @@
 	struct iwl_rb_status *rb_stts;
 	dma_addr_t rb_stts_dma;
 	spinlock_t lock;
-	struct iwl_rx_mem_buffer pool[RX_QUEUE_SIZE];
-	struct iwl_rx_mem_buffer *queue[RX_QUEUE_SIZE];
-};
-
-/**
- * struct iwl_rb_allocator - Rx allocator
- * @pool: initial pool of allocator
- * @req_pending: number of requests the allcator had not processed yet
- * @req_ready: number of requests honored and ready for claiming
- * @rbd_allocated: RBDs with pages allocated and ready to be handled to
- *	the queue. This is a list of &struct iwl_rx_mem_buffer
- * @rbd_empty: RBDs with no page attached for allocator use. This is a list
- *	of &struct iwl_rx_mem_buffer
- * @lock: protects the rbd_allocated and rbd_empty lists
- * @alloc_wq: work queue for background calls
- * @rx_alloc: work struct for background calls
- */
-struct iwl_rb_allocator {
-	struct iwl_rx_mem_buffer pool[RX_POOL_SIZE];
-	atomic_t req_pending;
-	atomic_t req_ready;
-	struct list_head rbd_allocated;
-	struct list_head rbd_empty;
-	spinlock_t lock;
-	struct workqueue_struct *alloc_wq;
-	struct work_struct rx_alloc;
 };
 
 struct iwl_dma_ptr {
@@ -285,7 +250,7 @@
 /**
  * struct iwl_trans_pcie - PCIe transport specific data
  * @rxq: all the RX queue data
- * @rba: allocator for RX replenishing
+ * @rx_replenish: work that will be called when buffers need to be allocated
  * @drv - pointer to iwl_drv
  * @trans: pointer to the generic transport area
  * @scd_base_addr: scheduler sram base address in SRAM
@@ -308,7 +273,7 @@
  */
 struct iwl_trans_pcie {
 	struct iwl_rxq rxq;
-	struct iwl_rb_allocator rba;
+	struct work_struct rx_replenish;
 	struct iwl_trans *trans;
 	struct iwl_drv *drv;
 
diff --git a/drivers/net/wireless/iwlwifi/pcie/rx.c b/drivers/net/wireless/iwlwifi/pcie/rx.c
index a3fbaa0..adad8d0 100644
--- a/drivers/net/wireless/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/iwlwifi/pcie/rx.c
@@ -1,7 +1,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2013 - 2014 Intel Mobile Communications GmbH
  *
  * Portions of this file are derived from the ipw3945 project, as well
  * as portions of the ieee80211 subsystem header files.
@@ -74,29 +74,16 @@
  * resets the Rx queue buffers with new memory.
  *
  * The management in the driver is as follows:
- * + A list of pre-allocated RBDs is stored in iwl->rxq->rx_free.
- *   When the interrupt handler is called, the request is processed.
- *   The page is either stolen - transferred to the upper layer
- *   or reused - added immediately to the iwl->rxq->rx_free list.
- * + When the page is stolen - the driver updates the matching queue's used
- *   count, detaches the RBD and transfers it to the queue used list.
- *   When there are two used RBDs - they are transferred to the allocator empty
- *   list. Work is then scheduled for the allocator to start allocating
- *   eight buffers.
- *   When there are another 6 used RBDs - they are transferred to the allocator
- *   empty list and the driver tries to claim the pre-allocated buffers and
- *   add them to iwl->rxq->rx_free. If it fails - it continues to claim them
- *   until ready.
- *   When there are 8+ buffers in the free list - either from allocation or from
- *   8 reused unstolen pages - restock is called to update the FW and indexes.
- * + In order to make sure the allocator always has RBDs to use for allocation
- *   the allocator has initial pool in the size of num_queues*(8-2) - the
- *   maximum missing RBDs per allocation request (request posted with 2
- *    empty RBDs, there is no guarantee when the other 6 RBDs are supplied).
- *   The queues supplies the recycle of the rest of the RBDs.
+ * + A list of pre-allocated SKBs is stored in iwl->rxq->rx_free.  When
+ *   iwl->rxq->free_count drops to or below RX_LOW_WATERMARK, work is scheduled
+ *   to replenish the iwl->rxq->rx_free.
+ * + In iwl_pcie_rx_replenish (scheduled) if 'processed' != 'read' then the
+ *   iwl->rxq is replenished and the READ INDEX is updated (updating the
+ *   'processed' and 'read' driver indexes as well)
  * + A received packet is processed and handed to the kernel network stack,
  *   detached from the iwl->rxq.  The driver 'processed' index is updated.
- * + If there are no allocated buffers in iwl->rxq->rx_free,
+ * + The Host/Firmware iwl->rxq is replenished at irq thread time from the
+ *   rx_free list. If there are no allocated buffers in iwl->rxq->rx_free,
  *   the READ INDEX is not incremented and iwl->status(RX_STALLED) is set.
  *   If there were enough free buffers and RX_STALLED is set it is cleared.
  *
@@ -105,32 +92,18 @@
  *
  * iwl_rxq_alloc()            Allocates rx_free
  * iwl_pcie_rx_replenish()    Replenishes rx_free list from rx_used, and calls
- *                            iwl_pcie_rxq_restock.
- *                            Used only during initialization.
+ *                            iwl_pcie_rxq_restock
  * iwl_pcie_rxq_restock()     Moves available buffers from rx_free into Rx
  *                            queue, updates firmware pointers, and updates
- *                            the WRITE index.
- * iwl_pcie_rx_allocator()     Background work for allocating pages.
+ *                            the WRITE index.  If insufficient rx_free buffers
+ *                            are available, schedules iwl_pcie_rx_replenish
  *
  * -- enable interrupts --
  * ISR - iwl_rx()             Detach iwl_rx_mem_buffers from pool up to the
  *                            READ INDEX, detaching the SKB from the pool.
  *                            Moves the packet buffer from queue to rx_used.
- *                            Posts and claims requests to the allocator.
  *                            Calls iwl_pcie_rxq_restock to refill any empty
  *                            slots.
- *
- * RBD life-cycle:
- *
- * Init:
- * rxq.pool -> rxq.rx_used -> rxq.rx_free -> rxq.queue
- *
- * Regular Receive interrupt:
- * Page Stolen:
- * rxq.queue -> rxq.rx_used -> allocator.rbd_empty ->
- * allocator.rbd_allocated -> rxq.rx_free -> rxq.queue
- * Page not Stolen:
- * rxq.queue -> rxq.rx_free -> rxq.queue
  * ...
  *
  */
@@ -267,6 +240,10 @@
 		rxq->free_count--;
 	}
 	spin_unlock(&rxq->lock);
+	/* If the pre-allocated buffer pool is dropping low, schedule to
+	 * refill it */
+	if (rxq->free_count <= RX_LOW_WATERMARK)
+		schedule_work(&trans_pcie->rx_replenish);
 
 	/* If we've added more space for the firmware to place data, tell it.
 	 * Increment device's write pointer in multiples of 8. */
@@ -278,44 +255,6 @@
 }
 
 /*
- * iwl_pcie_rx_alloc_page - allocates and returns a page.
- *
- */
-static struct page *iwl_pcie_rx_alloc_page(struct iwl_trans *trans)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_rxq *rxq = &trans_pcie->rxq;
-	struct page *page;
-	gfp_t gfp_mask = GFP_KERNEL;
-
-	if (rxq->free_count > RX_LOW_WATERMARK)
-		gfp_mask |= __GFP_NOWARN;
-
-	if (trans_pcie->rx_page_order > 0)
-		gfp_mask |= __GFP_COMP;
-
-	/* Alloc a new receive buffer */
-	page = alloc_pages(gfp_mask, trans_pcie->rx_page_order);
-	if (!page) {
-		if (net_ratelimit())
-			IWL_DEBUG_INFO(trans, "alloc_pages failed, order: %d\n",
-				       trans_pcie->rx_page_order);
-		/* Issue an error if the hardware has consumed more than half
-		 * of its free buffer list and we don't have enough
-		 * pre-allocated buffers.
-`		 */
-		if (rxq->free_count <= RX_LOW_WATERMARK &&
-		    iwl_rxq_space(rxq) > (RX_QUEUE_SIZE / 2) &&
-		    net_ratelimit())
-			IWL_CRIT(trans,
-				 "Failed to alloc_pages with GFP_KERNEL. Only %u free buffers remaining.\n",
-				 rxq->free_count);
-		return NULL;
-	}
-	return page;
-}
-
-/*
  * iwl_pcie_rxq_alloc_rbs - allocate a page for each used RBD
  *
  * A used RBD is an Rx buffer that has been given to the stack. To use it again
@@ -324,12 +263,13 @@
  * iwl_pcie_rxq_restock. The latter function will update the HW to use the newly
  * allocated buffers.
  */
-static void iwl_pcie_rxq_alloc_rbs(struct iwl_trans *trans)
+static void iwl_pcie_rxq_alloc_rbs(struct iwl_trans *trans, gfp_t priority)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_rxq *rxq = &trans_pcie->rxq;
 	struct iwl_rx_mem_buffer *rxb;
 	struct page *page;
+	gfp_t gfp_mask = priority;
 
 	while (1) {
 		spin_lock(&rxq->lock);
@@ -339,10 +279,32 @@
 		}
 		spin_unlock(&rxq->lock);
 
+		if (rxq->free_count > RX_LOW_WATERMARK)
+			gfp_mask |= __GFP_NOWARN;
+
+		if (trans_pcie->rx_page_order > 0)
+			gfp_mask |= __GFP_COMP;
+
 		/* Alloc a new receive buffer */
-		page = iwl_pcie_rx_alloc_page(trans);
-		if (!page)
+		page = alloc_pages(gfp_mask, trans_pcie->rx_page_order);
+		if (!page) {
+			if (net_ratelimit())
+				IWL_DEBUG_INFO(trans, "alloc_pages failed, "
+					   "order: %d\n",
+					   trans_pcie->rx_page_order);
+
+			if ((rxq->free_count <= RX_LOW_WATERMARK) &&
+			    net_ratelimit())
+				IWL_CRIT(trans, "Failed to alloc_pages with %s."
+					 "Only %u free buffers remaining.\n",
+					 priority == GFP_ATOMIC ?
+					 "GFP_ATOMIC" : "GFP_KERNEL",
+					 rxq->free_count);
+			/* We don't reschedule replenish work here -- we will
+			 * call the restock method and if it still needs
+			 * more buffers it will schedule replenish */
 			return;
+		}
 
 		spin_lock(&rxq->lock);
 
@@ -393,7 +355,7 @@
 
 	lockdep_assert_held(&rxq->lock);
 
-	for (i = 0; i < RX_QUEUE_SIZE; i++) {
+	for (i = 0; i < RX_FREE_BUFFERS + RX_QUEUE_SIZE; i++) {
 		if (!rxq->pool[i].page)
 			continue;
 		dma_unmap_page(trans->dev, rxq->pool[i].page_dma,
@@ -410,144 +372,32 @@
  * When moving to rx_free an page is allocated for the slot.
  *
  * Also restock the Rx queue via iwl_pcie_rxq_restock.
- * This is called only during initialization
+ * This is called as a scheduled work item (except for during initialization)
  */
-static void iwl_pcie_rx_replenish(struct iwl_trans *trans)
+static void iwl_pcie_rx_replenish(struct iwl_trans *trans, gfp_t gfp)
 {
-	iwl_pcie_rxq_alloc_rbs(trans);
+	iwl_pcie_rxq_alloc_rbs(trans, gfp);
 
 	iwl_pcie_rxq_restock(trans);
 }
 
-/*
- * iwl_pcie_rx_allocator - Allocates pages in the background for RX queues
- *
- * Allocates for each received request 8 pages
- * Called as a scheduled work item.
- */
-static void iwl_pcie_rx_allocator(struct iwl_trans *trans)
+static void iwl_pcie_rx_replenish_work(struct work_struct *data)
 {
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_rb_allocator *rba = &trans_pcie->rba;
-
-	while (atomic_read(&rba->req_pending)) {
-		int i;
-		struct list_head local_empty;
-		struct list_head local_allocated;
-
-		INIT_LIST_HEAD(&local_allocated);
-		spin_lock(&rba->lock);
-		/* swap out the entire rba->rbd_empty to a local list */
-		list_replace_init(&rba->rbd_empty, &local_empty);
-		spin_unlock(&rba->lock);
-
-		for (i = 0; i < RX_CLAIM_REQ_ALLOC;) {
-			struct iwl_rx_mem_buffer *rxb;
-			struct page *page;
-
-			/* List should never be empty - each reused RBD is
-			 * returned to the list, and initial pool covers any
-			 * possible gap between the time the page is allocated
-			 * to the time the RBD is added.
-			 */
-			BUG_ON(list_empty(&local_empty));
-			/* Get the first rxb from the rbd list */
-			rxb = list_first_entry(&local_empty,
-					       struct iwl_rx_mem_buffer, list);
-			BUG_ON(rxb->page);
-
-			/* Alloc a new receive buffer */
-			page = iwl_pcie_rx_alloc_page(trans);
-			if (!page)
-				continue;
-			rxb->page = page;
-
-			/* Get physical address of the RB */
-			rxb->page_dma = dma_map_page(trans->dev, page, 0,
-					PAGE_SIZE << trans_pcie->rx_page_order,
-					DMA_FROM_DEVICE);
-			if (dma_mapping_error(trans->dev, rxb->page_dma)) {
-				rxb->page = NULL;
-				__free_pages(page, trans_pcie->rx_page_order);
-				continue;
-			}
-			/* dma address must be no more than 36 bits */
-			BUG_ON(rxb->page_dma & ~DMA_BIT_MASK(36));
-			/* and also 256 byte aligned! */
-			BUG_ON(rxb->page_dma & DMA_BIT_MASK(8));
-
-			/* move the allocated entry to the out list */
-			list_move(&rxb->list, &local_allocated);
-			i++;
-		}
-
-		spin_lock(&rba->lock);
-		/* add the allocated rbds to the allocator allocated list */
-		list_splice_tail(&local_allocated, &rba->rbd_allocated);
-		/* add the unused rbds back to the allocator empty list */
-		list_splice_tail(&local_empty, &rba->rbd_empty);
-		spin_unlock(&rba->lock);
-
-		atomic_dec(&rba->req_pending);
-		atomic_inc(&rba->req_ready);
-	}
-}
-
-/*
- * iwl_pcie_rx_allocator_get - Returns the pre-allocated pages
-.*
-.* Called by queue when the queue posted allocation request and
- * has freed 8 RBDs in order to restock itself.
- */
-static int iwl_pcie_rx_allocator_get(struct iwl_trans *trans,
-				     struct iwl_rx_mem_buffer
-				     *out[RX_CLAIM_REQ_ALLOC])
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_rb_allocator *rba = &trans_pcie->rba;
-	int i;
-
-	if (atomic_dec_return(&rba->req_ready) < 0) {
-		atomic_inc(&rba->req_ready);
-		IWL_DEBUG_RX(trans,
-			     "Allocation request not ready, pending requests = %d\n",
-			     atomic_read(&rba->req_pending));
-		return -ENOMEM;
-	}
-
-	spin_lock(&rba->lock);
-	for (i = 0; i < RX_CLAIM_REQ_ALLOC; i++) {
-		/* Get next free Rx buffer, remove it from free list */
-		out[i] = list_first_entry(&rba->rbd_allocated,
-			       struct iwl_rx_mem_buffer, list);
-		list_del(&out[i]->list);
-	}
-	spin_unlock(&rba->lock);
-
-	return 0;
-}
-
-static void iwl_pcie_rx_allocator_work(struct work_struct *data)
-{
-	struct iwl_rb_allocator *rba_p =
-		container_of(data, struct iwl_rb_allocator, rx_alloc);
 	struct iwl_trans_pcie *trans_pcie =
-		container_of(rba_p, struct iwl_trans_pcie, rba);
+	    container_of(data, struct iwl_trans_pcie, rx_replenish);
 
-	iwl_pcie_rx_allocator(trans_pcie->trans);
+	iwl_pcie_rx_replenish(trans_pcie->trans, GFP_KERNEL);
 }
 
 static int iwl_pcie_rx_alloc(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_rxq *rxq = &trans_pcie->rxq;
-	struct iwl_rb_allocator *rba = &trans_pcie->rba;
 	struct device *dev = trans->dev;
 
 	memset(&trans_pcie->rxq, 0, sizeof(trans_pcie->rxq));
 
 	spin_lock_init(&rxq->lock);
-	spin_lock_init(&rba->lock);
 
 	if (WARN_ON(rxq->bd || rxq->rb_stts))
 		return -EINVAL;
@@ -637,49 +487,15 @@
 	INIT_LIST_HEAD(&rxq->rx_free);
 	INIT_LIST_HEAD(&rxq->rx_used);
 	rxq->free_count = 0;
-	rxq->used_count = 0;
 
-	for (i = 0; i < RX_QUEUE_SIZE; i++)
+	for (i = 0; i < RX_FREE_BUFFERS + RX_QUEUE_SIZE; i++)
 		list_add(&rxq->pool[i].list, &rxq->rx_used);
 }
 
-static void iwl_pcie_rx_init_rba(struct iwl_rb_allocator *rba)
-{
-	int i;
-
-	lockdep_assert_held(&rba->lock);
-
-	INIT_LIST_HEAD(&rba->rbd_allocated);
-	INIT_LIST_HEAD(&rba->rbd_empty);
-
-	for (i = 0; i < RX_POOL_SIZE; i++)
-		list_add(&rba->pool[i].list, &rba->rbd_empty);
-}
-
-static void iwl_pcie_rx_free_rba(struct iwl_trans *trans)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_rb_allocator *rba = &trans_pcie->rba;
-	int i;
-
-	lockdep_assert_held(&rba->lock);
-
-	for (i = 0; i < RX_POOL_SIZE; i++) {
-		if (!rba->pool[i].page)
-			continue;
-		dma_unmap_page(trans->dev, rba->pool[i].page_dma,
-			       PAGE_SIZE << trans_pcie->rx_page_order,
-			       DMA_FROM_DEVICE);
-		__free_pages(rba->pool[i].page, trans_pcie->rx_page_order);
-		rba->pool[i].page = NULL;
-	}
-}
-
 int iwl_pcie_rx_init(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_rxq *rxq = &trans_pcie->rxq;
-	struct iwl_rb_allocator *rba = &trans_pcie->rba;
 	int i, err;
 
 	if (!rxq->bd) {
@@ -687,21 +503,11 @@
 		if (err)
 			return err;
 	}
-	if (!rba->alloc_wq)
-		rba->alloc_wq = alloc_workqueue("rb_allocator",
-						WQ_HIGHPRI | WQ_UNBOUND, 1);
-	INIT_WORK(&rba->rx_alloc, iwl_pcie_rx_allocator_work);
-
-	spin_lock(&rba->lock);
-	atomic_set(&rba->req_pending, 0);
-	atomic_set(&rba->req_ready, 0);
-	/* free all first - we might be reconfigured for a different size */
-	iwl_pcie_rx_free_rba(trans);
-	iwl_pcie_rx_init_rba(rba);
-	spin_unlock(&rba->lock);
 
 	spin_lock(&rxq->lock);
 
+	INIT_WORK(&trans_pcie->rx_replenish, iwl_pcie_rx_replenish_work);
+
 	/* free all first - we might be reconfigured for a different size */
 	iwl_pcie_rxq_free_rbs(trans);
 	iwl_pcie_rx_init_rxb_lists(rxq);
@@ -716,7 +522,7 @@
 	memset(rxq->rb_stts, 0, sizeof(*rxq->rb_stts));
 	spin_unlock(&rxq->lock);
 
-	iwl_pcie_rx_replenish(trans);
+	iwl_pcie_rx_replenish(trans, GFP_KERNEL);
 
 	iwl_pcie_rx_hw_init(trans, rxq);
 
@@ -731,7 +537,6 @@
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_rxq *rxq = &trans_pcie->rxq;
-	struct iwl_rb_allocator *rba = &trans_pcie->rba;
 
 	/*if rxq->bd is NULL, it means that nothing has been allocated,
 	 * exit now */
@@ -740,15 +545,7 @@
 		return;
 	}
 
-	cancel_work_sync(&rba->rx_alloc);
-	if (rba->alloc_wq) {
-		destroy_workqueue(rba->alloc_wq);
-		rba->alloc_wq = NULL;
-	}
-
-	spin_lock(&rba->lock);
-	iwl_pcie_rx_free_rba(trans);
-	spin_unlock(&rba->lock);
+	cancel_work_sync(&trans_pcie->rx_replenish);
 
 	spin_lock(&rxq->lock);
 	iwl_pcie_rxq_free_rbs(trans);
@@ -769,43 +566,6 @@
 	rxq->rb_stts = NULL;
 }
 
-/*
- * iwl_pcie_rx_reuse_rbd - Recycle used RBDs
- *
- * Called when a RBD can be reused. The RBD is transferred to the allocator.
- * When there are 2 empty RBDs - a request for allocation is posted
- */
-static void iwl_pcie_rx_reuse_rbd(struct iwl_trans *trans,
-				  struct iwl_rx_mem_buffer *rxb,
-				  struct iwl_rxq *rxq)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_rb_allocator *rba = &trans_pcie->rba;
-
-	/* Count the used RBDs */
-	rxq->used_count++;
-
-	/* Move the RBD to the used list, will be moved to allocator in batches
-	 * before claiming or posting a request*/
-	list_add_tail(&rxb->list, &rxq->rx_used);
-
-	/* If we have RX_POST_REQ_ALLOC new released rx buffers -
-	 * issue a request for allocator. Modulo RX_CLAIM_REQ_ALLOC is
-	 * used for the case we failed to claim RX_CLAIM_REQ_ALLOC,
-	 * after but we still need to post another request.
-	 */
-	if ((rxq->used_count % RX_CLAIM_REQ_ALLOC) == RX_POST_REQ_ALLOC) {
-		/* Move the 2 RBDs to the allocator ownership.
-		 Allocator has another 6 from pool for the request completion*/
-		spin_lock(&rba->lock);
-		list_splice_tail_init(&rxq->rx_used, &rba->rbd_empty);
-		spin_unlock(&rba->lock);
-
-		atomic_inc(&rba->req_pending);
-		queue_work(rba->alloc_wq, &rba->rx_alloc);
-	}
-}
-
 static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 				struct iwl_rx_mem_buffer *rxb)
 {
@@ -928,13 +688,13 @@
 			 */
 			__free_pages(rxb->page, trans_pcie->rx_page_order);
 			rxb->page = NULL;
-			iwl_pcie_rx_reuse_rbd(trans, rxb, rxq);
+			list_add_tail(&rxb->list, &rxq->rx_used);
 		} else {
 			list_add_tail(&rxb->list, &rxq->rx_free);
 			rxq->free_count++;
 		}
 	} else
-		iwl_pcie_rx_reuse_rbd(trans, rxb, rxq);
+		list_add_tail(&rxb->list, &rxq->rx_used);
 }
 
 /*
@@ -944,7 +704,10 @@
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_rxq *rxq = &trans_pcie->rxq;
-	u32 r, i, j;
+	u32 r, i;
+	u8 fill_rx = 0;
+	u32 count = 8;
+	int total_empty;
 
 restart:
 	spin_lock(&rxq->lock);
@@ -957,6 +720,14 @@
 	if (i == r)
 		IWL_DEBUG_RX(trans, "HW = SW = %d\n", r);
 
+	/* calculate total frames need to be restock after handling RX */
+	total_empty = r - rxq->write_actual;
+	if (total_empty < 0)
+		total_empty += RX_QUEUE_SIZE;
+
+	if (total_empty > (RX_QUEUE_SIZE / 2))
+		fill_rx = 1;
+
 	while (i != r) {
 		struct iwl_rx_mem_buffer *rxb;
 
@@ -968,48 +739,29 @@
 		iwl_pcie_rx_handle_rb(trans, rxb);
 
 		i = (i + 1) & RX_QUEUE_MASK;
-
-		/* If we have RX_CLAIM_REQ_ALLOC released rx buffers -
-		 * try to claim the pre-allocated buffers from the allocator */
-		if (rxq->used_count >= RX_CLAIM_REQ_ALLOC) {
-			struct iwl_rb_allocator *rba = &trans_pcie->rba;
-			struct iwl_rx_mem_buffer *out[RX_CLAIM_REQ_ALLOC];
-
-			/* Add the remaining 6 empty RBDs for allocator use */
-			spin_lock(&rba->lock);
-			list_splice_tail_init(&rxq->rx_used, &rba->rbd_empty);
-			spin_unlock(&rba->lock);
-
-			/* If not ready - continue, will try to reclaim later.
-			* No need to reschedule work - allocator exits only on
-			* success */
-			if (!iwl_pcie_rx_allocator_get(trans, out)) {
-				/* If success - then RX_CLAIM_REQ_ALLOC
-				 * buffers were retrieved and should be added
-				 * to free list */
-				rxq->used_count -= RX_CLAIM_REQ_ALLOC;
-				for (j = 0; j < RX_CLAIM_REQ_ALLOC; j++) {
-					list_add_tail(&out[j]->list,
-						      &rxq->rx_free);
-					rxq->free_count++;
-				}
+		/* If there are a lot of unused frames,
+		 * restock the Rx queue so ucode wont assert. */
+		if (fill_rx) {
+			count++;
+			if (count >= 8) {
+				rxq->read = i;
+				spin_unlock(&rxq->lock);
+				iwl_pcie_rx_replenish(trans, GFP_ATOMIC);
+				count = 0;
+				goto restart;
 			}
 		}
-		/* handle restock for two cases:
-		* - we just pulled buffers from the allocator
-		* - we have 8+ unstolen pages accumulated */
-		if (rxq->free_count >=  RX_CLAIM_REQ_ALLOC) {
-			rxq->read = i;
-			spin_unlock(&rxq->lock);
-			iwl_pcie_rxq_restock(trans);
-			goto restart;
-		}
 	}
 
 	/* Backtrack one entry */
 	rxq->read = i;
 	spin_unlock(&rxq->lock);
 
+	if (fill_rx)
+		iwl_pcie_rx_replenish(trans, GFP_ATOMIC);
+	else
+		iwl_pcie_rxq_restock(trans);
+
 	if (trans_pcie->napi.poll)
 		napi_gro_flush(&trans_pcie->napi, false);
 }
diff --git a/drivers/net/wireless/iwlwifi/pcie/trans.c b/drivers/net/wireless/iwlwifi/pcie/trans.c
index 43ae658..9e144e7 100644
--- a/drivers/net/wireless/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/iwlwifi/pcie/trans.c
@@ -182,7 +182,7 @@
 
 static void iwl_pcie_set_pwr(struct iwl_trans *trans, bool vaux)
 {
-	if (!trans->cfg->apmg_not_supported)
+	if (trans->cfg->apmg_not_supported)
 		return;
 
 	if (vaux && pci_pme_capable(to_pci_dev(trans->dev), PCI_D3cold))
@@ -478,10 +478,16 @@
 		if (trans->cfg->device_family == IWL_DEVICE_FAMILY_7000)
 			iwl_set_bits_prph(trans, APMG_PCIDEV_STT_REG,
 					  APMG_PCIDEV_STT_VAL_WAKE_ME);
-		else if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000)
+		else if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) {
+			iwl_set_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG,
+				    CSR_RESET_LINK_PWR_MGMT_DISABLED);
 			iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
 				    CSR_HW_IF_CONFIG_REG_PREPARE |
 				    CSR_HW_IF_CONFIG_REG_ENABLE_PME);
+			mdelay(1);
+			iwl_clear_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG,
+				      CSR_RESET_LINK_PWR_MGMT_DISABLED);
+		}
 		mdelay(5);
 	}
 
@@ -575,6 +581,10 @@
 	if (ret >= 0)
 		return 0;
 
+	iwl_set_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG,
+		    CSR_RESET_LINK_PWR_MGMT_DISABLED);
+	msleep(1);
+
 	for (iter = 0; iter < 10; iter++) {
 		/* If HW is not ready, prepare the conditions to check again */
 		iwl_set_bit(trans, CSR_HW_IF_CONFIG_REG,
@@ -582,8 +592,10 @@
 
 		do {
 			ret = iwl_pcie_set_hw_ready(trans);
-			if (ret >= 0)
-				return 0;
+			if (ret >= 0) {
+				ret = 0;
+				goto out;
+			}
 
 			usleep_range(200, 1000);
 			t += 200;
@@ -593,6 +605,10 @@
 
 	IWL_ERR(trans, "Couldn't prepare the card\n");
 
+out:
+	iwl_clear_bit(trans, CSR_DBG_LINK_PWR_MGMT_REG,
+		      CSR_RESET_LINK_PWR_MGMT_DISABLED);
+
 	return ret;
 }
 
@@ -2459,7 +2475,7 @@
 	struct iwl_trans_pcie *trans_pcie;
 	struct iwl_trans *trans;
 	u16 pci_cmd;
-	int err;
+	int ret;
 
 	trans = iwl_trans_alloc(sizeof(struct iwl_trans_pcie),
 				&pdev->dev, cfg, &trans_ops_pcie, 0);
@@ -2474,8 +2490,8 @@
 	spin_lock_init(&trans_pcie->ref_lock);
 	init_waitqueue_head(&trans_pcie->ucode_write_waitq);
 
-	err = pci_enable_device(pdev);
-	if (err)
+	ret = pci_enable_device(pdev);
+	if (ret)
 		goto out_no_pci;
 
 	if (!cfg->base_params->pcie_l1_allowed) {
@@ -2491,23 +2507,23 @@
 
 	pci_set_master(pdev);
 
-	err = pci_set_dma_mask(pdev, DMA_BIT_MASK(36));
-	if (!err)
-		err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(36));
-	if (err) {
-		err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
-		if (!err)
-			err = pci_set_consistent_dma_mask(pdev,
+	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(36));
+	if (!ret)
+		ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(36));
+	if (ret) {
+		ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(32));
+		if (!ret)
+			ret = pci_set_consistent_dma_mask(pdev,
 							  DMA_BIT_MASK(32));
 		/* both attempts failed: */
-		if (err) {
+		if (ret) {
 			dev_err(&pdev->dev, "No suitable DMA available\n");
 			goto out_pci_disable_device;
 		}
 	}
 
-	err = pci_request_regions(pdev, DRV_NAME);
-	if (err) {
+	ret = pci_request_regions(pdev, DRV_NAME);
+	if (ret) {
 		dev_err(&pdev->dev, "pci_request_regions failed\n");
 		goto out_pci_disable_device;
 	}
@@ -2515,7 +2531,7 @@
 	trans_pcie->hw_base = pci_ioremap_bar(pdev, 0);
 	if (!trans_pcie->hw_base) {
 		dev_err(&pdev->dev, "pci_ioremap_bar failed\n");
-		err = -ENODEV;
+		ret = -ENODEV;
 		goto out_pci_release_regions;
 	}
 
@@ -2527,9 +2543,9 @@
 	trans_pcie->pci_dev = pdev;
 	iwl_disable_interrupts(trans);
 
-	err = pci_enable_msi(pdev);
-	if (err) {
-		dev_err(&pdev->dev, "pci_enable_msi failed(0X%x)\n", err);
+	ret = pci_enable_msi(pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "pci_enable_msi failed(0X%x)\n", ret);
 		/* enable rfkill interrupt: hw bug w/a */
 		pci_read_config_word(pdev, PCI_COMMAND, &pci_cmd);
 		if (pci_cmd & PCI_COMMAND_INTX_DISABLE) {
@@ -2547,11 +2563,16 @@
 	 */
 	if (trans->cfg->device_family == IWL_DEVICE_FAMILY_8000) {
 		unsigned long flags;
-		int ret;
 
 		trans->hw_rev = (trans->hw_rev & 0xfff0) |
 				(CSR_HW_REV_STEP(trans->hw_rev << 2) << 2);
 
+		ret = iwl_pcie_prepare_card_hw(trans);
+		if (ret) {
+			IWL_WARN(trans, "Exit HW not ready\n");
+			goto out_pci_disable_msi;
+		}
+
 		/*
 		 * in-order to recognize C step driver should read chip version
 		 * id located at the AUX bus MISC address space.
@@ -2591,13 +2612,14 @@
 	/* Initialize the wait queue for commands */
 	init_waitqueue_head(&trans_pcie->wait_command_queue);
 
-	if (iwl_pcie_alloc_ict(trans))
+	ret = iwl_pcie_alloc_ict(trans);
+	if (ret)
 		goto out_pci_disable_msi;
 
-	err = request_threaded_irq(pdev->irq, iwl_pcie_isr,
+	ret = request_threaded_irq(pdev->irq, iwl_pcie_isr,
 				   iwl_pcie_irq_handler,
 				   IRQF_SHARED, DRV_NAME, trans);
-	if (err) {
+	if (ret) {
 		IWL_ERR(trans, "Error allocating IRQ %d\n", pdev->irq);
 		goto out_free_ict;
 	}
@@ -2617,5 +2639,5 @@
 	pci_disable_device(pdev);
 out_no_pci:
 	iwl_trans_free(trans);
-	return ERR_PTR(err);
+	return ERR_PTR(ret);
 }
diff --git a/drivers/net/wireless/iwlwifi/pcie/tx.c b/drivers/net/wireless/iwlwifi/pcie/tx.c
index 2b86c21..607acb5 100644
--- a/drivers/net/wireless/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/iwlwifi/pcie/tx.c
@@ -1875,8 +1875,19 @@
 
 	/* start timer if queue currently empty */
 	if (q->read_ptr == q->write_ptr) {
-		if (txq->wd_timeout)
-			mod_timer(&txq->stuck_timer, jiffies + txq->wd_timeout);
+		if (txq->wd_timeout) {
+			/*
+			 * If the TXQ is active, then set the timer, if not,
+			 * set the timer in remainder so that the timer will
+			 * be armed with the right value when the station will
+			 * wake up.
+			 */
+			if (!txq->frozen)
+				mod_timer(&txq->stuck_timer,
+					  jiffies + txq->wd_timeout);
+			else
+				txq->frozen_expiry_remainder = txq->wd_timeout;
+		}
 		IWL_DEBUG_RPM(trans, "Q: %d first tx - take ref\n", q->id);
 		iwl_trans_pcie_ref(trans);
 	}
diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c
index b6cc9ff..1c6788a 100644
--- a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c
+++ b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c
@@ -172,6 +172,7 @@
 		(struct rsi_91x_sdiodev *)adapter->rsi_dev;
 	u32 len;
 	u32 num_blocks;
+	const u8 *fw;
 	const struct firmware *fw_entry = NULL;
 	u32 block_size = dev->tx_blk_size;
 	int status = 0;
@@ -200,6 +201,10 @@
 		return status;
 	}
 
+	/* Copy firmware into DMA-accessible memory */
+	fw = kmemdup(fw_entry->data, fw_entry->size, GFP_KERNEL);
+	if (!fw)
+		return -ENOMEM;
 	len = fw_entry->size;
 
 	if (len % 4)
@@ -210,7 +215,8 @@
 	rsi_dbg(INIT_ZONE, "%s: Instruction size:%d\n", __func__, len);
 	rsi_dbg(INIT_ZONE, "%s: num blocks: %d\n", __func__, num_blocks);
 
-	status = rsi_copy_to_card(common, fw_entry->data, len, num_blocks);
+	status = rsi_copy_to_card(common, fw, len, num_blocks);
+	kfree(fw);
 	release_firmware(fw_entry);
 	return status;
 }
diff --git a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c
index 1106ce7..30c2cf7 100644
--- a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c
+++ b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c
@@ -146,7 +146,10 @@
 		return status;
 	}
 
+	/* Copy firmware into DMA-accessible memory */
 	fw = kmemdup(fw_entry->data, fw_entry->size, GFP_KERNEL);
+	if (!fw)
+		return -ENOMEM;
 	len = fw_entry->size;
 
 	if (len % 4)
@@ -158,6 +161,7 @@
 	rsi_dbg(INIT_ZONE, "%s: num blocks: %d\n", __func__, num_blocks);
 
 	status = rsi_copy_to_card(common, fw, len, num_blocks);
+	kfree(fw);
 	release_firmware(fw_entry);
 	return status;
 }
diff --git a/drivers/net/wireless/rtlwifi/core.c b/drivers/net/wireless/rtlwifi/core.c
index 3b3a88b..585d088 100644
--- a/drivers/net/wireless/rtlwifi/core.c
+++ b/drivers/net/wireless/rtlwifi/core.c
@@ -1015,9 +1015,12 @@
 {
 	struct rtl_priv *rtlpriv = rtl_priv(hw);
 	struct sk_buff *skb = ieee80211_beacon_get(hw, vif);
+	struct rtl_tcb_desc tcb_desc;
 
-	if (skb)
-		rtlpriv->intf_ops->adapter_tx(hw, NULL, skb, NULL);
+	if (skb) {
+		memset(&tcb_desc, 0, sizeof(struct rtl_tcb_desc));
+		rtlpriv->intf_ops->adapter_tx(hw, NULL, skb, &tcb_desc);
+	}
 }
 
 static void rtl_op_bss_info_changed(struct ieee80211_hw *hw,
diff --git a/drivers/net/wireless/rtlwifi/rtl8723be/sw.c b/drivers/net/wireless/rtlwifi/rtl8723be/sw.c
index 1017f02..7bf88d9 100644
--- a/drivers/net/wireless/rtlwifi/rtl8723be/sw.c
+++ b/drivers/net/wireless/rtlwifi/rtl8723be/sw.c
@@ -385,6 +385,7 @@
 module_param_named(ips, rtl8723be_mod_params.inactiveps, bool, 0444);
 module_param_named(swlps, rtl8723be_mod_params.swctrl_lps, bool, 0444);
 module_param_named(fwlps, rtl8723be_mod_params.fwctrl_lps, bool, 0444);
+module_param_named(msi, rtl8723be_mod_params.msi_support, bool, 0444);
 module_param_named(disable_watchdog, rtl8723be_mod_params.disable_watchdog,
 		   bool, 0444);
 MODULE_PARM_DESC(swenc, "Set to 1 for software crypto (default 0)\n");
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 1a83e19..28577a3 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -61,6 +61,12 @@
 void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue)
 {
 	atomic_dec(&queue->inflight_packets);
+
+	/* Wake the dealloc thread _after_ decrementing inflight_packets so
+	 * that if kthread_stop() has already been called, the dealloc thread
+	 * does not wait forever with nothing to wake it.
+	 */
+	wake_up(&queue->dealloc_wq);
 }
 
 int xenvif_schedulable(struct xenvif *vif)
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 880d0d6..3f44b52 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -810,23 +810,17 @@
 static struct gnttab_map_grant_ref *xenvif_get_requests(struct xenvif_queue *queue,
 							struct sk_buff *skb,
 							struct xen_netif_tx_request *txp,
-							struct gnttab_map_grant_ref *gop)
+							struct gnttab_map_grant_ref *gop,
+							unsigned int frag_overflow,
+							struct sk_buff *nskb)
 {
 	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	skb_frag_t *frags = shinfo->frags;
 	u16 pending_idx = XENVIF_TX_CB(skb)->pending_idx;
 	int start;
 	pending_ring_idx_t index;
-	unsigned int nr_slots, frag_overflow = 0;
+	unsigned int nr_slots;
 
-	/* At this point shinfo->nr_frags is in fact the number of
-	 * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX.
-	 */
-	if (shinfo->nr_frags > MAX_SKB_FRAGS) {
-		frag_overflow = shinfo->nr_frags - MAX_SKB_FRAGS;
-		BUG_ON(frag_overflow > MAX_SKB_FRAGS);
-		shinfo->nr_frags = MAX_SKB_FRAGS;
-	}
 	nr_slots = shinfo->nr_frags;
 
 	/* Skip first skb fragment if it is on same page as header fragment. */
@@ -841,13 +835,6 @@
 	}
 
 	if (frag_overflow) {
-		struct sk_buff *nskb = xenvif_alloc_skb(0);
-		if (unlikely(nskb == NULL)) {
-			if (net_ratelimit())
-				netdev_err(queue->vif->dev,
-					   "Can't allocate the frag_list skb.\n");
-			return NULL;
-		}
 
 		shinfo = skb_shinfo(nskb);
 		frags = shinfo->frags;
@@ -1175,9 +1162,10 @@
 				     unsigned *copy_ops,
 				     unsigned *map_ops)
 {
-	struct gnttab_map_grant_ref *gop = queue->tx_map_ops, *request_gop;
-	struct sk_buff *skb;
+	struct gnttab_map_grant_ref *gop = queue->tx_map_ops;
+	struct sk_buff *skb, *nskb;
 	int ret;
+	unsigned int frag_overflow;
 
 	while (skb_queue_len(&queue->tx_queue) < budget) {
 		struct xen_netif_tx_request txreq;
@@ -1265,6 +1253,29 @@
 			break;
 		}
 
+		skb_shinfo(skb)->nr_frags = ret;
+		if (data_len < txreq.size)
+			skb_shinfo(skb)->nr_frags++;
+		/* At this point shinfo->nr_frags is in fact the number of
+		 * slots, which can be as large as XEN_NETBK_LEGACY_SLOTS_MAX.
+		 */
+		frag_overflow = 0;
+		nskb = NULL;
+		if (skb_shinfo(skb)->nr_frags > MAX_SKB_FRAGS) {
+			frag_overflow = skb_shinfo(skb)->nr_frags - MAX_SKB_FRAGS;
+			BUG_ON(frag_overflow > MAX_SKB_FRAGS);
+			skb_shinfo(skb)->nr_frags = MAX_SKB_FRAGS;
+			nskb = xenvif_alloc_skb(0);
+			if (unlikely(nskb == NULL)) {
+				kfree_skb(skb);
+				xenvif_tx_err(queue, &txreq, idx);
+				if (net_ratelimit())
+					netdev_err(queue->vif->dev,
+						   "Can't allocate the frag_list skb.\n");
+				break;
+			}
+		}
+
 		if (extras[XEN_NETIF_EXTRA_TYPE_GSO - 1].type) {
 			struct xen_netif_extra_info *gso;
 			gso = &extras[XEN_NETIF_EXTRA_TYPE_GSO - 1];
@@ -1272,6 +1283,7 @@
 			if (xenvif_set_skb_gso(queue->vif, skb, gso)) {
 				/* Failure in xenvif_set_skb_gso is fatal. */
 				kfree_skb(skb);
+				kfree_skb(nskb);
 				break;
 			}
 		}
@@ -1294,9 +1306,7 @@
 
 		(*copy_ops)++;
 
-		skb_shinfo(skb)->nr_frags = ret;
 		if (data_len < txreq.size) {
-			skb_shinfo(skb)->nr_frags++;
 			frag_set_pending_idx(&skb_shinfo(skb)->frags[0],
 					     pending_idx);
 			xenvif_tx_create_map_op(queue, pending_idx, &txreq, gop);
@@ -1310,13 +1320,8 @@
 
 		queue->pending_cons++;
 
-		request_gop = xenvif_get_requests(queue, skb, txfrags, gop);
-		if (request_gop == NULL) {
-			kfree_skb(skb);
-			xenvif_tx_err(queue, &txreq, idx);
-			break;
-		}
-		gop = request_gop;
+		gop = xenvif_get_requests(queue, skb, txfrags, gop,
+				          frag_overflow, nskb);
 
 		__skb_queue_tail(&queue->tx_queue, skb);
 
@@ -1536,7 +1541,6 @@
 		smp_wmb();
 		queue->dealloc_prod++;
 	} while (ubuf);
-	wake_up(&queue->dealloc_wq);
 	spin_unlock_irqrestore(&queue->callback_lock, flags);
 
 	if (likely(zerocopy_success))
@@ -1566,13 +1570,13 @@
 		smp_rmb();
 
 		while (dc != dp) {
-			BUG_ON(gop - queue->tx_unmap_ops > MAX_PENDING_REQS);
+			BUG_ON(gop - queue->tx_unmap_ops >= MAX_PENDING_REQS);
 			pending_idx =
 				queue->dealloc_ring[pending_index(dc++)];
 
-			pending_idx_release[gop-queue->tx_unmap_ops] =
+			pending_idx_release[gop - queue->tx_unmap_ops] =
 				pending_idx;
-			queue->pages_to_unmap[gop-queue->tx_unmap_ops] =
+			queue->pages_to_unmap[gop - queue->tx_unmap_ops] =
 				queue->mmap_pages[pending_idx];
 			gnttab_set_unmap_op(gop,
 					    idx_to_kaddr(queue, pending_idx),
diff --git a/drivers/ntb/ntb.c b/drivers/ntb/ntb.c
index 23435f2..2e25307 100644
--- a/drivers/ntb/ntb.c
+++ b/drivers/ntb/ntb.c
@@ -114,7 +114,7 @@
 	ntb->dev.bus = &ntb_bus;
 	ntb->dev.parent = &ntb->pdev->dev;
 	ntb->dev.release = ntb_dev_release;
-	dev_set_name(&ntb->dev, pci_name(ntb->pdev));
+	dev_set_name(&ntb->dev, "%s", pci_name(ntb->pdev));
 
 	ntb->ctx = NULL;
 	ntb->ctx_ops = NULL;
diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
index efe3ad4..1c6386d 100644
--- a/drivers/ntb/ntb_transport.c
+++ b/drivers/ntb/ntb_transport.c
@@ -142,10 +142,11 @@
 
 	void (*rx_handler)(struct ntb_transport_qp *qp, void *qp_data,
 			   void *data, int len);
+	struct list_head rx_post_q;
 	struct list_head rx_pend_q;
 	struct list_head rx_free_q;
-	spinlock_t ntb_rx_pend_q_lock;
-	spinlock_t ntb_rx_free_q_lock;
+	/* ntb_rx_q_lock: synchronize access to rx_XXXX_q */
+	spinlock_t ntb_rx_q_lock;
 	void *rx_buff;
 	unsigned int rx_index;
 	unsigned int rx_max_entry;
@@ -211,6 +212,8 @@
 	bool link_is_up;
 	struct delayed_work link_work;
 	struct work_struct link_cleanup;
+
+	struct dentry *debugfs_node_dir;
 };
 
 enum {
@@ -436,13 +439,17 @@
 	char *buf;
 	ssize_t ret, out_offset, out_count;
 
+	qp = filp->private_data;
+
+	if (!qp || !qp->link_is_up)
+		return 0;
+
 	out_count = 1000;
 
 	buf = kmalloc(out_count, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
-	qp = filp->private_data;
 	out_offset = 0;
 	out_offset += snprintf(buf + out_offset, out_count - out_offset,
 			       "NTB QP stats\n");
@@ -534,6 +541,27 @@
 	return entry;
 }
 
+static struct ntb_queue_entry *ntb_list_mv(spinlock_t *lock,
+					   struct list_head *list,
+					   struct list_head *to_list)
+{
+	struct ntb_queue_entry *entry;
+	unsigned long flags;
+
+	spin_lock_irqsave(lock, flags);
+
+	if (list_empty(list)) {
+		entry = NULL;
+	} else {
+		entry = list_first_entry(list, struct ntb_queue_entry, entry);
+		list_move_tail(&entry->entry, to_list);
+	}
+
+	spin_unlock_irqrestore(lock, flags);
+
+	return entry;
+}
+
 static int ntb_transport_setup_qp_mw(struct ntb_transport_ctx *nt,
 				     unsigned int qp_num)
 {
@@ -601,13 +629,16 @@
 }
 
 static int ntb_set_mw(struct ntb_transport_ctx *nt, int num_mw,
-		      unsigned int size)
+		      resource_size_t size)
 {
 	struct ntb_transport_mw *mw = &nt->mw_vec[num_mw];
 	struct pci_dev *pdev = nt->ndev->pdev;
-	unsigned int xlat_size, buff_size;
+	size_t xlat_size, buff_size;
 	int rc;
 
+	if (!size)
+		return -EINVAL;
+
 	xlat_size = round_up(size, mw->xlat_align_size);
 	buff_size = round_up(size, mw->xlat_align);
 
@@ -627,7 +658,7 @@
 	if (!mw->virt_addr) {
 		mw->xlat_size = 0;
 		mw->buff_size = 0;
-		dev_err(&pdev->dev, "Unable to alloc MW buff of size %d\n",
+		dev_err(&pdev->dev, "Unable to alloc MW buff of size %zu\n",
 			buff_size);
 		return -ENOMEM;
 	}
@@ -867,6 +898,8 @@
 
 		if (qp->event_handler)
 			qp->event_handler(qp->cb_data, qp->link_is_up);
+
+		tasklet_schedule(&qp->rxc_db_work);
 	} else if (nt->link_is_up)
 		schedule_delayed_work(&qp->link_work,
 				      msecs_to_jiffies(NTB_LINK_DOWN_TIMEOUT));
@@ -923,12 +956,12 @@
 	qp->tx_max_frame = min(transport_mtu, tx_size / 2);
 	qp->tx_max_entry = tx_size / qp->tx_max_frame;
 
-	if (nt_debugfs_dir) {
+	if (nt->debugfs_node_dir) {
 		char debugfs_name[4];
 
 		snprintf(debugfs_name, 4, "qp%d", qp_num);
 		qp->debugfs_dir = debugfs_create_dir(debugfs_name,
-						     nt_debugfs_dir);
+						     nt->debugfs_node_dir);
 
 		qp->debugfs_stats = debugfs_create_file("stats", S_IRUSR,
 							qp->debugfs_dir, qp,
@@ -941,10 +974,10 @@
 	INIT_DELAYED_WORK(&qp->link_work, ntb_qp_link_work);
 	INIT_WORK(&qp->link_cleanup, ntb_qp_link_cleanup_work);
 
-	spin_lock_init(&qp->ntb_rx_pend_q_lock);
-	spin_lock_init(&qp->ntb_rx_free_q_lock);
+	spin_lock_init(&qp->ntb_rx_q_lock);
 	spin_lock_init(&qp->ntb_tx_free_q_lock);
 
+	INIT_LIST_HEAD(&qp->rx_post_q);
 	INIT_LIST_HEAD(&qp->rx_pend_q);
 	INIT_LIST_HEAD(&qp->rx_free_q);
 	INIT_LIST_HEAD(&qp->tx_free_q);
@@ -1031,6 +1064,12 @@
 		goto err2;
 	}
 
+	if (nt_debugfs_dir) {
+		nt->debugfs_node_dir =
+			debugfs_create_dir(pci_name(ndev->pdev),
+					   nt_debugfs_dir);
+	}
+
 	for (i = 0; i < qp_count; i++) {
 		rc = ntb_transport_init_queue(nt, i);
 		if (rc)
@@ -1107,22 +1146,47 @@
 	kfree(nt);
 }
 
+static void ntb_complete_rxc(struct ntb_transport_qp *qp)
+{
+	struct ntb_queue_entry *entry;
+	void *cb_data;
+	unsigned int len;
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&qp->ntb_rx_q_lock, irqflags);
+
+	while (!list_empty(&qp->rx_post_q)) {
+		entry = list_first_entry(&qp->rx_post_q,
+					 struct ntb_queue_entry, entry);
+		if (!(entry->flags & DESC_DONE_FLAG))
+			break;
+
+		entry->rx_hdr->flags = 0;
+		iowrite32(entry->index, &qp->rx_info->entry);
+
+		cb_data = entry->cb_data;
+		len = entry->len;
+
+		list_move_tail(&entry->entry, &qp->rx_free_q);
+
+		spin_unlock_irqrestore(&qp->ntb_rx_q_lock, irqflags);
+
+		if (qp->rx_handler && qp->client_ready)
+			qp->rx_handler(qp, qp->cb_data, cb_data, len);
+
+		spin_lock_irqsave(&qp->ntb_rx_q_lock, irqflags);
+	}
+
+	spin_unlock_irqrestore(&qp->ntb_rx_q_lock, irqflags);
+}
+
 static void ntb_rx_copy_callback(void *data)
 {
 	struct ntb_queue_entry *entry = data;
-	struct ntb_transport_qp *qp = entry->qp;
-	void *cb_data = entry->cb_data;
-	unsigned int len = entry->len;
-	struct ntb_payload_header *hdr = entry->rx_hdr;
 
-	hdr->flags = 0;
+	entry->flags |= DESC_DONE_FLAG;
 
-	iowrite32(entry->index, &qp->rx_info->entry);
-
-	ntb_list_add(&qp->ntb_rx_free_q_lock, &entry->entry, &qp->rx_free_q);
-
-	if (qp->rx_handler && qp->client_ready)
-		qp->rx_handler(qp, qp->cb_data, cb_data, len);
+	ntb_complete_rxc(entry->qp);
 }
 
 static void ntb_memcpy_rx(struct ntb_queue_entry *entry, void *offset)
@@ -1138,19 +1202,18 @@
 	ntb_rx_copy_callback(entry);
 }
 
-static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset,
-			 size_t len)
+static void ntb_async_rx(struct ntb_queue_entry *entry, void *offset)
 {
 	struct dma_async_tx_descriptor *txd;
 	struct ntb_transport_qp *qp = entry->qp;
 	struct dma_chan *chan = qp->dma_chan;
 	struct dma_device *device;
-	size_t pay_off, buff_off;
+	size_t pay_off, buff_off, len;
 	struct dmaengine_unmap_data *unmap;
 	dma_cookie_t cookie;
 	void *buf = entry->buf;
 
-	entry->len = len;
+	len = entry->len;
 
 	if (!chan)
 		goto err;
@@ -1226,7 +1289,6 @@
 	struct ntb_payload_header *hdr;
 	struct ntb_queue_entry *entry;
 	void *offset;
-	int rc;
 
 	offset = qp->rx_buff + qp->rx_max_frame * qp->rx_index;
 	hdr = offset + qp->rx_max_frame - sizeof(struct ntb_payload_header);
@@ -1255,65 +1317,43 @@
 		return -EIO;
 	}
 
-	entry = ntb_list_rm(&qp->ntb_rx_pend_q_lock, &qp->rx_pend_q);
+	entry = ntb_list_mv(&qp->ntb_rx_q_lock, &qp->rx_pend_q, &qp->rx_post_q);
 	if (!entry) {
 		dev_dbg(&qp->ndev->pdev->dev, "no receive buffer\n");
 		qp->rx_err_no_buf++;
-
-		rc = -ENOMEM;
-		goto err;
+		return -EAGAIN;
 	}
 
+	entry->rx_hdr = hdr;
+	entry->index = qp->rx_index;
+
 	if (hdr->len > entry->len) {
 		dev_dbg(&qp->ndev->pdev->dev,
 			"receive buffer overflow! Wanted %d got %d\n",
 			hdr->len, entry->len);
 		qp->rx_err_oflow++;
 
-		rc = -EIO;
-		goto err;
+		entry->len = -EIO;
+		entry->flags |= DESC_DONE_FLAG;
+
+		ntb_complete_rxc(qp);
+	} else {
+		dev_dbg(&qp->ndev->pdev->dev,
+			"RX OK index %u ver %u size %d into buf size %d\n",
+			qp->rx_index, hdr->ver, hdr->len, entry->len);
+
+		qp->rx_bytes += hdr->len;
+		qp->rx_pkts++;
+
+		entry->len = hdr->len;
+
+		ntb_async_rx(entry, offset);
 	}
 
-	dev_dbg(&qp->ndev->pdev->dev,
-		"RX OK index %u ver %u size %d into buf size %d\n",
-		qp->rx_index, hdr->ver, hdr->len, entry->len);
-
-	qp->rx_bytes += hdr->len;
-	qp->rx_pkts++;
-
-	entry->index = qp->rx_index;
-	entry->rx_hdr = hdr;
-
-	ntb_async_rx(entry, offset, hdr->len);
-
 	qp->rx_index++;
 	qp->rx_index %= qp->rx_max_entry;
 
 	return 0;
-
-err:
-	/* FIXME: if this syncrhonous update of the rx_index gets ahead of
-	 * asyncrhonous ntb_rx_copy_callback of previous entry, there are three
-	 * scenarios:
-	 *
-	 * 1) The peer might miss this update, but observe the update
-	 * from the memcpy completion callback.  In this case, the buffer will
-	 * not be freed on the peer to be reused for a different packet.  The
-	 * successful rx of a later packet would clear the condition, but the
-	 * condition could persist if several rx fail in a row.
-	 *
-	 * 2) The peer may observe this update before the asyncrhonous copy of
-	 * prior packets is completed.  The peer may overwrite the buffers of
-	 * the prior packets before they are copied.
-	 *
-	 * 3) Both: the peer may observe the update, and then observe the index
-	 * decrement by the asynchronous completion callback.  Who knows what
-	 * badness that will cause.
-	 */
-	hdr->flags = 0;
-	iowrite32(qp->rx_index, &qp->rx_info->entry);
-
-	return rc;
 }
 
 static void ntb_transport_rxc_db(unsigned long data)
@@ -1333,7 +1373,7 @@
 			break;
 	}
 
-	if (qp->dma_chan)
+	if (i && qp->dma_chan)
 		dma_async_issue_pending(qp->dma_chan);
 
 	if (i == qp->rx_max_entry) {
@@ -1609,7 +1649,7 @@
 			goto err1;
 
 		entry->qp = qp;
-		ntb_list_add(&qp->ntb_rx_free_q_lock, &entry->entry,
+		ntb_list_add(&qp->ntb_rx_q_lock, &entry->entry,
 			     &qp->rx_free_q);
 	}
 
@@ -1634,7 +1674,7 @@
 	while ((entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q)))
 		kfree(entry);
 err1:
-	while ((entry = ntb_list_rm(&qp->ntb_rx_free_q_lock, &qp->rx_free_q)))
+	while ((entry = ntb_list_rm(&qp->ntb_rx_q_lock, &qp->rx_free_q)))
 		kfree(entry);
 	if (qp->dma_chan)
 		dma_release_channel(qp->dma_chan);
@@ -1652,7 +1692,6 @@
  */
 void ntb_transport_free_queue(struct ntb_transport_qp *qp)
 {
-	struct ntb_transport_ctx *nt = qp->transport;
 	struct pci_dev *pdev;
 	struct ntb_queue_entry *entry;
 	u64 qp_bit;
@@ -1689,18 +1728,23 @@
 	qp->tx_handler = NULL;
 	qp->event_handler = NULL;
 
-	while ((entry = ntb_list_rm(&qp->ntb_rx_free_q_lock, &qp->rx_free_q)))
+	while ((entry = ntb_list_rm(&qp->ntb_rx_q_lock, &qp->rx_free_q)))
 		kfree(entry);
 
-	while ((entry = ntb_list_rm(&qp->ntb_rx_pend_q_lock, &qp->rx_pend_q))) {
-		dev_warn(&pdev->dev, "Freeing item from a non-empty queue\n");
+	while ((entry = ntb_list_rm(&qp->ntb_rx_q_lock, &qp->rx_pend_q))) {
+		dev_warn(&pdev->dev, "Freeing item from non-empty rx_pend_q\n");
+		kfree(entry);
+	}
+
+	while ((entry = ntb_list_rm(&qp->ntb_rx_q_lock, &qp->rx_post_q))) {
+		dev_warn(&pdev->dev, "Freeing item from non-empty rx_post_q\n");
 		kfree(entry);
 	}
 
 	while ((entry = ntb_list_rm(&qp->ntb_tx_free_q_lock, &qp->tx_free_q)))
 		kfree(entry);
 
-	nt->qp_bitmap_free |= qp_bit;
+	qp->transport->qp_bitmap_free |= qp_bit;
 
 	dev_info(&pdev->dev, "NTB Transport QP %d freed\n", qp->qp_num);
 }
@@ -1724,14 +1768,14 @@
 	if (!qp || qp->client_ready)
 		return NULL;
 
-	entry = ntb_list_rm(&qp->ntb_rx_pend_q_lock, &qp->rx_pend_q);
+	entry = ntb_list_rm(&qp->ntb_rx_q_lock, &qp->rx_pend_q);
 	if (!entry)
 		return NULL;
 
 	buf = entry->cb_data;
 	*len = entry->len;
 
-	ntb_list_add(&qp->ntb_rx_free_q_lock, &entry->entry, &qp->rx_free_q);
+	ntb_list_add(&qp->ntb_rx_q_lock, &entry->entry, &qp->rx_free_q);
 
 	return buf;
 }
@@ -1757,15 +1801,18 @@
 	if (!qp)
 		return -EINVAL;
 
-	entry = ntb_list_rm(&qp->ntb_rx_free_q_lock, &qp->rx_free_q);
+	entry = ntb_list_rm(&qp->ntb_rx_q_lock, &qp->rx_free_q);
 	if (!entry)
 		return -ENOMEM;
 
 	entry->cb_data = cb;
 	entry->buf = data;
 	entry->len = len;
+	entry->flags = 0;
 
-	ntb_list_add(&qp->ntb_rx_pend_q_lock, &entry->entry, &qp->rx_pend_q);
+	ntb_list_add(&qp->ntb_rx_q_lock, &entry->entry, &qp->rx_pend_q);
+
+	tasklet_schedule(&qp->rxc_db_work);
 
 	return 0;
 }
diff --git a/drivers/nvdimm/bus.c b/drivers/nvdimm/bus.c
index 8eb22c0..7e2c43f 100644
--- a/drivers/nvdimm/bus.c
+++ b/drivers/nvdimm/bus.c
@@ -535,8 +535,6 @@
 					__func__, dimm_name, cmd_name, i);
 			return -ENXIO;
 		}
-		if (!access_ok(VERIFY_READ, p + in_len, in_size))
-			return -EFAULT;
 		if (in_len < sizeof(in_env))
 			copy = min_t(u32, sizeof(in_env) - in_len, in_size);
 		else
@@ -557,8 +555,6 @@
 					__func__, dimm_name, cmd_name, i);
 			return -EFAULT;
 		}
-		if (!access_ok(VERIFY_WRITE, p + in_len + out_len, out_size))
-			return -EFAULT;
 		if (out_len < sizeof(out_env))
 			copy = min_t(u32, sizeof(out_env) - out_len, out_size);
 		else
@@ -570,9 +566,6 @@
 	}
 
 	buf_len = out_len + in_len;
-	if (!access_ok(VERIFY_WRITE, p, sizeof(buf_len)))
-		return -EFAULT;
-
 	if (buf_len > ND_IOCTL_MAX_BUFLEN) {
 		dev_dbg(dev, "%s:%s cmd: %s buf_len: %zu > %d\n", __func__,
 				dimm_name, cmd_name, buf_len,
@@ -706,8 +699,10 @@
 	nvdimm_major = rc;
 
 	nd_class = class_create(THIS_MODULE, "nd");
-	if (IS_ERR(nd_class))
+	if (IS_ERR(nd_class)) {
+		rc = PTR_ERR(nd_class);
 		goto err_class;
+	}
 
 	return 0;
 
diff --git a/drivers/nvdimm/region_devs.c b/drivers/nvdimm/region_devs.c
index a523342..7384455 100644
--- a/drivers/nvdimm/region_devs.c
+++ b/drivers/nvdimm/region_devs.c
@@ -458,10 +458,15 @@
 		nvdimm_bus_unlock(dev);
 	}
 	if (is_nd_btt(dev) && probe) {
+		struct nd_btt *nd_btt = to_nd_btt(dev);
+
 		nd_region = to_nd_region(dev->parent);
 		nvdimm_bus_lock(dev);
 		if (nd_region->btt_seed == dev)
 			nd_region_create_btt_seed(nd_region);
+		if (nd_region->ns_seed == &nd_btt->ndns->dev &&
+				is_nd_blk(dev->parent))
+			nd_region_create_blk_seed(nd_region);
 		nvdimm_bus_unlock(dev);
 	}
 }
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index 8df1b17..59bb855 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -47,7 +47,7 @@
 
 config OF_ADDRESS
 	def_bool y
-	depends on !SPARC
+	depends on !SPARC && HAS_IOMEM
 	select OF_ADDRESS_PCI if PCI
 
 config OF_ADDRESS_PCI
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 1801634..9f71770b6 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -979,7 +979,6 @@
 	.remove			= unittest_remove,
 	.driver = {
 		.name		= "unittest",
-		.owner		= THIS_MODULE,
 		.of_match_table	= of_match_ptr(unittest_match),
 	},
 };
@@ -1666,7 +1665,6 @@
 static struct i2c_driver unittest_i2c_dev_driver = {
 	.driver = {
 		.name = "unittest-i2c-dev",
-		.owner = THIS_MODULE,
 	},
 	.probe = unittest_i2c_dev_probe,
 	.remove = unittest_i2c_dev_remove,
@@ -1761,7 +1759,6 @@
 static struct i2c_driver unittest_i2c_mux_driver = {
 	.driver = {
 		.name = "unittest-i2c-mux",
-		.owner = THIS_MODULE,
 	},
 	.probe = unittest_i2c_mux_probe,
 	.remove = unittest_i2c_mux_remove,
diff --git a/drivers/parport/share.c b/drivers/parport/share.c
index 8067f54..5ce5ef21 100644
--- a/drivers/parport/share.c
+++ b/drivers/parport/share.c
@@ -891,8 +891,10 @@
 	par_dev->dev.release = free_pardevice;
 	par_dev->devmodel = true;
 	ret = device_register(&par_dev->dev);
-	if (ret)
-		goto err_put_dev;
+	if (ret) {
+		put_device(&par_dev->dev);
+		goto err_put_port;
+	}
 
 	/* Chain this onto the list */
 	par_dev->prev = NULL;
@@ -907,7 +909,8 @@
 			spin_unlock(&port->physport->pardevice_lock);
 			pr_debug("%s: cannot grant exclusive access for device %s\n",
 				 port->name, name);
-			goto err_put_dev;
+			device_unregister(&par_dev->dev);
+			goto err_put_port;
 		}
 		port->flags |= PARPORT_FLAG_EXCL;
 	}
@@ -938,8 +941,6 @@
 
 	return par_dev;
 
-err_put_dev:
-	put_device(&par_dev->dev);
 err_free_devname:
 	kfree(devname);
 err_free_par_dev:
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig
index 73de4ef..944f500 100644
--- a/drivers/pci/Kconfig
+++ b/drivers/pci/Kconfig
@@ -2,7 +2,7 @@
 # PCI configuration
 #
 config PCI_BUS_ADDR_T_64BIT
-	def_bool y if (ARCH_DMA_ADDR_T_64BIT || 64BIT)
+	def_bool y if (ARCH_DMA_ADDR_T_64BIT || (64BIT && !PARISC))
 	depends on PCI
 
 config PCI_MSI
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index cefd636..b978bbf 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -997,7 +997,12 @@
 	else if (type == PCI_EXP_TYPE_UPSTREAM ||
 		 type == PCI_EXP_TYPE_DOWNSTREAM) {
 		parent = pci_upstream_bridge(pdev);
-		if (!parent->has_secondary_link)
+
+		/*
+		 * Usually there's an upstream device (Root Port or Switch
+		 * Downstream Port), but we can't assume one exists.
+		 */
+		if (parent && !parent->has_secondary_link)
 			pdev->has_secondary_link = 1;
 	}
 }
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index c0e6ede..6b8dd16 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -56,6 +56,7 @@
 
 config PHY_PXA_28NM_HSIC
 	tristate "Marvell USB HSIC 28nm PHY Driver"
+	depends on HAS_IOMEM
 	select GENERIC_PHY
 	help
 	  Enable this to support Marvell USB HSIC PHY driver for Marvell
@@ -66,6 +67,7 @@
 
 config PHY_PXA_28NM_USB2
 	tristate "Marvell USB 2.0 28nm PHY Driver"
+	depends on HAS_IOMEM
 	select GENERIC_PHY
 	help
 	  Enable this to support Marvell USB 2.0 PHY driver for Marvell
diff --git a/drivers/phy/phy-berlin-usb.c b/drivers/phy/phy-berlin-usb.c
index c6fc95b..335e06d 100644
--- a/drivers/phy/phy-berlin-usb.c
+++ b/drivers/phy/phy-berlin-usb.c
@@ -105,9 +105,9 @@
 
 static const u32 phy_berlin_pll_dividers[] = {
 	/* Berlin 2 */
-	CLK_REF_DIV(0xc) | FEEDBACK_CLK_DIV(0x54),
-	/* Berlin 2CD */
 	CLK_REF_DIV(0x6) | FEEDBACK_CLK_DIV(0x55),
+	/* Berlin 2CD/Q */
+	CLK_REF_DIV(0xc) | FEEDBACK_CLK_DIV(0x54),
 };
 
 struct phy_berlin_usb_priv {
diff --git a/drivers/phy/phy-sun4i-usb.c b/drivers/phy/phy-sun4i-usb.c
index e17c539..2dad7e8 100644
--- a/drivers/phy/phy-sun4i-usb.c
+++ b/drivers/phy/phy-sun4i-usb.c
@@ -212,6 +212,7 @@
 
 	sun4i_usb_phy_write(phy, PHY_SQUELCH_DETECT, enabled ? 0 : 2, 2);
 }
+EXPORT_SYMBOL_GPL(sun4i_usb_phy_set_squelch_detect);
 
 static struct phy_ops sun4i_usb_phy_ops = {
 	.init		= sun4i_usb_phy_init,
diff --git a/drivers/phy/phy-ti-pipe3.c b/drivers/phy/phy-ti-pipe3.c
index 53f295c..08020dc 100644
--- a/drivers/phy/phy-ti-pipe3.c
+++ b/drivers/phy/phy-ti-pipe3.c
@@ -28,7 +28,8 @@
 #include <linux/delay.h>
 #include <linux/phy/omap_control_phy.h>
 #include <linux/of_platform.h>
-#include <linux/spinlock.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #define	PLL_STATUS		0x00000004
 #define	PLL_GO			0x00000008
@@ -53,6 +54,8 @@
 #define	PLL_LOCK		0x2
 #define	PLL_IDLE		0x1
 
+#define SATA_PLL_SOFT_RESET	BIT(18)
+
 /*
  * This is an Empirical value that works, need to confirm the actual
  * value required for the PIPE3PHY_PLL_CONFIGURATION2.PLL_IDLE status
@@ -83,10 +86,9 @@
 	struct clk		*refclk;
 	struct clk		*div_clk;
 	struct pipe3_dpll_map	*dpll_map;
-	bool			enabled;
-	spinlock_t		lock;	/* serialize clock enable/disable */
-	/* the below flag is needed specifically for SATA */
-	bool			refclk_enabled;
+	struct regmap		*dpll_reset_syscon; /* ctrl. reg. acces */
+	unsigned int		dpll_reset_reg; /* reg. index within syscon */
+	bool			sata_refclk_enabled;
 };
 
 static struct pipe3_dpll_map dpll_map_usb[] = {
@@ -137,6 +139,9 @@
 	return NULL;
 }
 
+static int ti_pipe3_enable_clocks(struct ti_pipe3 *phy);
+static void ti_pipe3_disable_clocks(struct ti_pipe3 *phy);
+
 static int ti_pipe3_power_off(struct phy *x)
 {
 	struct ti_pipe3 *phy = phy_get_drvdata(x);
@@ -217,6 +222,7 @@
 	u32 val;
 	int ret = 0;
 
+	ti_pipe3_enable_clocks(phy);
 	/*
 	 * Set pcie_pcs register to 0x96 for proper functioning of phy
 	 * as recommended in AM572x TRM SPRUHZ6, section 18.5.2.2, table
@@ -250,33 +256,46 @@
 	u32 val;
 	unsigned long timeout;
 
-	/* SATA DPLL can't be powered down due to Errata i783 and PCIe
-	 * does not have internal DPLL
+	/* If dpll_reset_syscon is not present we wont power down SATA DPLL
+	 * due to Errata i783
 	 */
-	if (of_device_is_compatible(phy->dev->of_node, "ti,phy-pipe3-sata") ||
-	    of_device_is_compatible(phy->dev->of_node, "ti,phy-pipe3-pcie"))
+	if (of_device_is_compatible(phy->dev->of_node, "ti,phy-pipe3-sata") &&
+	    !phy->dpll_reset_syscon)
 		return 0;
 
-	/* Put DPLL in IDLE mode */
-	val = ti_pipe3_readl(phy->pll_ctrl_base, PLL_CONFIGURATION2);
-	val |= PLL_IDLE;
-	ti_pipe3_writel(phy->pll_ctrl_base, PLL_CONFIGURATION2, val);
+	/* PCIe doesn't have internal DPLL */
+	if (!of_device_is_compatible(phy->dev->of_node, "ti,phy-pipe3-pcie")) {
+		/* Put DPLL in IDLE mode */
+		val = ti_pipe3_readl(phy->pll_ctrl_base, PLL_CONFIGURATION2);
+		val |= PLL_IDLE;
+		ti_pipe3_writel(phy->pll_ctrl_base, PLL_CONFIGURATION2, val);
 
-	/* wait for LDO and Oscillator to power down */
-	timeout = jiffies + msecs_to_jiffies(PLL_IDLE_TIME);
-	do {
-		cpu_relax();
-		val = ti_pipe3_readl(phy->pll_ctrl_base, PLL_STATUS);
-		if ((val & PLL_TICOPWDN) && (val & PLL_LDOPWDN))
-			break;
-	} while (!time_after(jiffies, timeout));
+		/* wait for LDO and Oscillator to power down */
+		timeout = jiffies + msecs_to_jiffies(PLL_IDLE_TIME);
+		do {
+			cpu_relax();
+			val = ti_pipe3_readl(phy->pll_ctrl_base, PLL_STATUS);
+			if ((val & PLL_TICOPWDN) && (val & PLL_LDOPWDN))
+				break;
+		} while (!time_after(jiffies, timeout));
 
-	if (!(val & PLL_TICOPWDN) || !(val & PLL_LDOPWDN)) {
-		dev_err(phy->dev, "Failed to power down: PLL_STATUS 0x%x\n",
-			val);
-		return -EBUSY;
+		if (!(val & PLL_TICOPWDN) || !(val & PLL_LDOPWDN)) {
+			dev_err(phy->dev, "Failed to power down: PLL_STATUS 0x%x\n",
+				val);
+			return -EBUSY;
+		}
 	}
 
+	/* i783: SATA needs control bit toggle after PLL unlock */
+	if (of_device_is_compatible(phy->dev->of_node, "ti,phy-pipe3-sata")) {
+		regmap_update_bits(phy->dpll_reset_syscon, phy->dpll_reset_reg,
+				   SATA_PLL_SOFT_RESET, SATA_PLL_SOFT_RESET);
+		regmap_update_bits(phy->dpll_reset_syscon, phy->dpll_reset_reg,
+				   SATA_PLL_SOFT_RESET, 0);
+	}
+
+	ti_pipe3_disable_clocks(phy);
+
 	return 0;
 }
 static struct phy_ops ops = {
@@ -306,7 +325,6 @@
 		return -ENOMEM;
 
 	phy->dev		= &pdev->dev;
-	spin_lock_init(&phy->lock);
 
 	if (!of_device_is_compatible(node, "ti,phy-pipe3-pcie")) {
 		match = of_match_device(ti_pipe3_id_table, &pdev->dev);
@@ -350,6 +368,21 @@
 		}
 	} else {
 		phy->wkupclk = ERR_PTR(-ENODEV);
+		phy->dpll_reset_syscon = syscon_regmap_lookup_by_phandle(node,
+							"syscon-pllreset");
+		if (IS_ERR(phy->dpll_reset_syscon)) {
+			dev_info(&pdev->dev,
+				 "can't get syscon-pllreset, sata dpll won't idle\n");
+			phy->dpll_reset_syscon = NULL;
+		} else {
+			if (of_property_read_u32_index(node,
+						       "syscon-pllreset", 1,
+						       &phy->dpll_reset_reg)) {
+				dev_err(&pdev->dev,
+					"couldn't get pllreset reg. offset\n");
+				return -EINVAL;
+			}
+		}
 	}
 
 	if (of_device_is_compatible(node, "ti,phy-pipe3-pcie")) {
@@ -403,6 +436,16 @@
 	platform_set_drvdata(pdev, phy);
 	pm_runtime_enable(phy->dev);
 
+	/*
+	 * Prevent auto-disable of refclk for SATA PHY due to Errata i783
+	 */
+	if (of_device_is_compatible(node, "ti,phy-pipe3-sata")) {
+		if (!IS_ERR(phy->refclk)) {
+			clk_prepare_enable(phy->refclk);
+			phy->sata_refclk_enabled = true;
+		}
+	}
+
 	generic_phy = devm_phy_create(phy->dev, NULL, &ops);
 	if (IS_ERR(generic_phy))
 		return PTR_ERR(generic_phy);
@@ -413,63 +456,33 @@
 	if (IS_ERR(phy_provider))
 		return PTR_ERR(phy_provider);
 
-	pm_runtime_get(&pdev->dev);
-
 	return 0;
 }
 
 static int ti_pipe3_remove(struct platform_device *pdev)
 {
-	if (!pm_runtime_suspended(&pdev->dev))
-		pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
 	return 0;
 }
 
-#ifdef CONFIG_PM
-static int ti_pipe3_enable_refclk(struct ti_pipe3 *phy)
+static int ti_pipe3_enable_clocks(struct ti_pipe3 *phy)
 {
-	if (!IS_ERR(phy->refclk) && !phy->refclk_enabled) {
-		int ret;
+	int ret = 0;
 
+	if (!IS_ERR(phy->refclk)) {
 		ret = clk_prepare_enable(phy->refclk);
 		if (ret) {
 			dev_err(phy->dev, "Failed to enable refclk %d\n", ret);
 			return ret;
 		}
-		phy->refclk_enabled = true;
 	}
 
-	return 0;
-}
-
-static void ti_pipe3_disable_refclk(struct ti_pipe3 *phy)
-{
-	if (!IS_ERR(phy->refclk))
-		clk_disable_unprepare(phy->refclk);
-
-	phy->refclk_enabled = false;
-}
-
-static int ti_pipe3_enable_clocks(struct ti_pipe3 *phy)
-{
-	int ret = 0;
-	unsigned long flags;
-
-	spin_lock_irqsave(&phy->lock, flags);
-	if (phy->enabled)
-		goto err1;
-
-	ret = ti_pipe3_enable_refclk(phy);
-	if (ret)
-		goto err1;
-
 	if (!IS_ERR(phy->wkupclk)) {
 		ret = clk_prepare_enable(phy->wkupclk);
 		if (ret) {
 			dev_err(phy->dev, "Failed to enable wkupclk %d\n", ret);
-			goto err2;
+			goto disable_refclk;
 		}
 	}
 
@@ -477,96 +490,43 @@
 		ret = clk_prepare_enable(phy->div_clk);
 		if (ret) {
 			dev_err(phy->dev, "Failed to enable div_clk %d\n", ret);
-			goto err3;
+			goto disable_wkupclk;
 		}
 	}
 
-	phy->enabled = true;
-	spin_unlock_irqrestore(&phy->lock, flags);
 	return 0;
 
-err3:
+disable_wkupclk:
 	if (!IS_ERR(phy->wkupclk))
 		clk_disable_unprepare(phy->wkupclk);
 
-err2:
+disable_refclk:
 	if (!IS_ERR(phy->refclk))
 		clk_disable_unprepare(phy->refclk);
 
-	ti_pipe3_disable_refclk(phy);
-err1:
-	spin_unlock_irqrestore(&phy->lock, flags);
 	return ret;
 }
 
 static void ti_pipe3_disable_clocks(struct ti_pipe3 *phy)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&phy->lock, flags);
-	if (!phy->enabled) {
-		spin_unlock_irqrestore(&phy->lock, flags);
-		return;
-	}
-
 	if (!IS_ERR(phy->wkupclk))
 		clk_disable_unprepare(phy->wkupclk);
-	/* Don't disable refclk for SATA PHY due to Errata i783 */
-	if (!of_device_is_compatible(phy->dev->of_node, "ti,phy-pipe3-sata"))
-		ti_pipe3_disable_refclk(phy);
+	if (!IS_ERR(phy->refclk)) {
+		clk_disable_unprepare(phy->refclk);
+		/*
+		 * SATA refclk needs an additional disable as we left it
+		 * on in probe to avoid Errata i783
+		 */
+		if (phy->sata_refclk_enabled) {
+			clk_disable_unprepare(phy->refclk);
+			phy->sata_refclk_enabled = false;
+		}
+	}
+
 	if (!IS_ERR(phy->div_clk))
 		clk_disable_unprepare(phy->div_clk);
-	phy->enabled = false;
-	spin_unlock_irqrestore(&phy->lock, flags);
 }
 
-static int ti_pipe3_runtime_suspend(struct device *dev)
-{
-	struct ti_pipe3	*phy = dev_get_drvdata(dev);
-
-	ti_pipe3_disable_clocks(phy);
-	return 0;
-}
-
-static int ti_pipe3_runtime_resume(struct device *dev)
-{
-	struct ti_pipe3	*phy = dev_get_drvdata(dev);
-	int ret = 0;
-
-	ret = ti_pipe3_enable_clocks(phy);
-	return ret;
-}
-
-static int ti_pipe3_suspend(struct device *dev)
-{
-	struct ti_pipe3	*phy = dev_get_drvdata(dev);
-
-	ti_pipe3_disable_clocks(phy);
-	return 0;
-}
-
-static int ti_pipe3_resume(struct device *dev)
-{
-	struct ti_pipe3	*phy = dev_get_drvdata(dev);
-	int ret;
-
-	ret = ti_pipe3_enable_clocks(phy);
-	if (ret)
-		return ret;
-
-	pm_runtime_disable(dev);
-	pm_runtime_set_active(dev);
-	pm_runtime_enable(dev);
-	return 0;
-}
-#endif
-
-static const struct dev_pm_ops ti_pipe3_pm_ops = {
-	SET_RUNTIME_PM_OPS(ti_pipe3_runtime_suspend,
-			   ti_pipe3_runtime_resume, NULL)
-	SET_SYSTEM_SLEEP_PM_OPS(ti_pipe3_suspend, ti_pipe3_resume)
-};
-
 static const struct of_device_id ti_pipe3_id_table[] = {
 	{
 		.compatible = "ti,phy-usb3",
@@ -592,7 +552,6 @@
 	.remove		= ti_pipe3_remove,
 	.driver		= {
 		.name	= "ti-pipe3",
-		.pm	= &ti_pipe3_pm_ops,
 		.of_match_table = ti_pipe3_id_table,
 	},
 };
diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c
index efcf2a2..6177315 100644
--- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c
+++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c
@@ -473,6 +473,8 @@
 
 	spin_lock_irqsave(&pc->irq_lock[bank], flags);
 	bcm2835_gpio_irq_config(pc, gpio, false);
+	/* Clear events that were latched prior to clearing event sources */
+	bcm2835_gpio_set_bit(pc, GPEDS0, gpio);
 	clear_bit(offset, &pc->enabled_irq_map[bank]);
 	spin_unlock_irqrestore(&pc->irq_lock[bank], flags);
 }
diff --git a/drivers/pinctrl/freescale/pinctrl-imx1-core.c b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
index 5fd4437..88a7fac 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx1-core.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
@@ -403,14 +403,13 @@
 			     unsigned num_configs)
 {
 	struct imx1_pinctrl *ipctl = pinctrl_dev_get_drvdata(pctldev);
-	const struct imx1_pinctrl_soc_info *info = ipctl->info;
 	int i;
 
 	for (i = 0; i != num_configs; ++i) {
 		imx1_write_bit(ipctl, pin_id, configs[i] & 0x01, MX1_PUEN);
 
 		dev_dbg(ipctl->dev, "pinconf set pullup pin %s\n",
-			info->pins[pin_id].name);
+			pin_desc_get(pctldev, pin_id)->name);
 	}
 
 	return 0;
diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c
index 557d0f2..97681fa 100644
--- a/drivers/pinctrl/nomadik/pinctrl-abx500.c
+++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c
@@ -787,7 +787,6 @@
 	.set_mux = abx500_pmx_set,
 	.gpio_request_enable = abx500_gpio_request_enable,
 	.gpio_disable_free = abx500_gpio_disable_free,
-	.strict = true,
 };
 
 static int abx500_get_groups_cnt(struct pinctrl_dev *pctldev)
diff --git a/drivers/pinctrl/pinctrl-lpc18xx.c b/drivers/pinctrl/pinctrl-lpc18xx.c
index ef0b697..347c763 100644
--- a/drivers/pinctrl/pinctrl-lpc18xx.c
+++ b/drivers/pinctrl/pinctrl-lpc18xx.c
@@ -823,7 +823,7 @@
 		break;
 
 	case PIN_CONFIG_INPUT_SCHMITT_ENABLE:
-		if (param)
+		if (param_val)
 			*reg &= ~(LPC18XX_SCU_I2C0_ZIF << shift);
 		else
 			*reg |= (LPC18XX_SCU_I2C0_ZIF << shift);
@@ -876,7 +876,7 @@
 		break;
 
 	case PIN_CONFIG_INPUT_SCHMITT_ENABLE:
-		if (param)
+		if (param_val)
 			*reg &= ~LPC18XX_SCU_PIN_ZIF;
 		else
 			*reg |= LPC18XX_SCU_PIN_ZIF;
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index b2de09d..0b8d480 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -1760,7 +1760,8 @@
 		int res;
 
 		res = request_irq(pcs_soc->irq, pcs_irq_handler,
-				  IRQF_SHARED | IRQF_NO_SUSPEND,
+				  IRQF_SHARED | IRQF_NO_SUSPEND |
+				  IRQF_NO_THREAD,
 				  name, pcs_soc);
 		if (res) {
 			pcs_soc->irq = -1;
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index 3dd5a3b..c760bf4 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -33,11 +33,6 @@
 #include "../core.h"
 #include "pinctrl-samsung.h"
 
-#define GROUP_SUFFIX		"-grp"
-#define GSUFFIX_LEN		sizeof(GROUP_SUFFIX)
-#define FUNCTION_SUFFIX		"-mux"
-#define FSUFFIX_LEN		sizeof(FUNCTION_SUFFIX)
-
 /* list of all possible config options supported */
 static struct pin_config {
 	const char *property;
diff --git a/drivers/pinctrl/sh-pfc/sh_pfc.h b/drivers/pinctrl/sh-pfc/sh_pfc.h
index c7508d5..0874cfe 100644
--- a/drivers/pinctrl/sh-pfc/sh_pfc.h
+++ b/drivers/pinctrl/sh-pfc/sh_pfc.h
@@ -224,7 +224,7 @@
 
 /* PINMUX_GPIO_GP_ALL - Expand to a list of sh_pfc_pin entries */
 #define _GP_GPIO(bank, _pin, _name, sfx)				\
-	[(bank * 32) + _pin] = {					\
+	{								\
 		.pin = (bank * 32) + _pin,				\
 		.name = __stringify(_name),				\
 		.enum_id = _name##_DATA,				\
diff --git a/drivers/pinctrl/spear/pinctrl-spear.c b/drivers/pinctrl/spear/pinctrl-spear.c
index f87a5ea..0afaf79 100644
--- a/drivers/pinctrl/spear/pinctrl-spear.c
+++ b/drivers/pinctrl/spear/pinctrl-spear.c
@@ -2,7 +2,7 @@
  * Driver for the ST Microelectronics SPEAr pinmux
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * Inspired from:
  * - U300 Pinctl drivers
diff --git a/drivers/pinctrl/spear/pinctrl-spear.h b/drivers/pinctrl/spear/pinctrl-spear.h
index dc8bf85..27c2cc8 100644
--- a/drivers/pinctrl/spear/pinctrl-spear.h
+++ b/drivers/pinctrl/spear/pinctrl-spear.h
@@ -2,7 +2,7 @@
  * Driver header file for the ST Microelectronics SPEAr pinmux
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/pinctrl/spear/pinctrl-spear1310.c b/drivers/pinctrl/spear/pinctrl-spear1310.c
index a7bdc537..92611bb 100644
--- a/drivers/pinctrl/spear/pinctrl-spear1310.c
+++ b/drivers/pinctrl/spear/pinctrl-spear1310.c
@@ -2,7 +2,7 @@
  * Driver for the ST Microelectronics SPEAr1310 pinmux
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
@@ -2730,7 +2730,7 @@
 }
 module_exit(spear1310_pinctrl_exit);
 
-MODULE_AUTHOR("Viresh Kumar <viresh.linux@gmail.com>");
+MODULE_AUTHOR("Viresh Kumar <vireshk@kernel.org>");
 MODULE_DESCRIPTION("ST Microelectronics SPEAr1310 pinctrl driver");
 MODULE_LICENSE("GPL v2");
 MODULE_DEVICE_TABLE(of, spear1310_pinctrl_of_match);
diff --git a/drivers/pinctrl/spear/pinctrl-spear1340.c b/drivers/pinctrl/spear/pinctrl-spear1340.c
index f43ec85..f842e9d 100644
--- a/drivers/pinctrl/spear/pinctrl-spear1340.c
+++ b/drivers/pinctrl/spear/pinctrl-spear1340.c
@@ -2,7 +2,7 @@
  * Driver for the ST Microelectronics SPEAr1340 pinmux
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
@@ -2046,7 +2046,7 @@
 }
 module_exit(spear1340_pinctrl_exit);
 
-MODULE_AUTHOR("Viresh Kumar <viresh.linux@gmail.com>");
+MODULE_AUTHOR("Viresh Kumar <vireshk@kernel.org>");
 MODULE_DESCRIPTION("ST Microelectronics SPEAr1340 pinctrl driver");
 MODULE_LICENSE("GPL v2");
 MODULE_DEVICE_TABLE(of, spear1340_pinctrl_of_match);
diff --git a/drivers/pinctrl/spear/pinctrl-spear300.c b/drivers/pinctrl/spear/pinctrl-spear300.c
index da8990a..d998a2c 100644
--- a/drivers/pinctrl/spear/pinctrl-spear300.c
+++ b/drivers/pinctrl/spear/pinctrl-spear300.c
@@ -2,7 +2,7 @@
  * Driver for the ST Microelectronics SPEAr300 pinmux
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
@@ -703,7 +703,7 @@
 }
 module_exit(spear300_pinctrl_exit);
 
-MODULE_AUTHOR("Viresh Kumar <viresh.linux@gmail.com>");
+MODULE_AUTHOR("Viresh Kumar <vireshk@kernel.org>");
 MODULE_DESCRIPTION("ST Microelectronics SPEAr300 pinctrl driver");
 MODULE_LICENSE("GPL v2");
 MODULE_DEVICE_TABLE(of, spear300_pinctrl_of_match);
diff --git a/drivers/pinctrl/spear/pinctrl-spear310.c b/drivers/pinctrl/spear/pinctrl-spear310.c
index 31ede51..609b18a 100644
--- a/drivers/pinctrl/spear/pinctrl-spear310.c
+++ b/drivers/pinctrl/spear/pinctrl-spear310.c
@@ -2,7 +2,7 @@
  * Driver for the ST Microelectronics SPEAr310 pinmux
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
@@ -426,7 +426,7 @@
 }
 module_exit(spear310_pinctrl_exit);
 
-MODULE_AUTHOR("Viresh Kumar <viresh.linux@gmail.com>");
+MODULE_AUTHOR("Viresh Kumar <vireshk@kernel.org>");
 MODULE_DESCRIPTION("ST Microelectronics SPEAr310 pinctrl driver");
 MODULE_LICENSE("GPL v2");
 MODULE_DEVICE_TABLE(of, spear310_pinctrl_of_match);
diff --git a/drivers/pinctrl/spear/pinctrl-spear320.c b/drivers/pinctrl/spear/pinctrl-spear320.c
index 506e40b..c071144 100644
--- a/drivers/pinctrl/spear/pinctrl-spear320.c
+++ b/drivers/pinctrl/spear/pinctrl-spear320.c
@@ -2,7 +2,7 @@
  * Driver for the ST Microelectronics SPEAr320 pinmux
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
@@ -3467,7 +3467,7 @@
 }
 module_exit(spear320_pinctrl_exit);
 
-MODULE_AUTHOR("Viresh Kumar <viresh.linux@gmail.com>");
+MODULE_AUTHOR("Viresh Kumar <vireshk@kernel.org>");
 MODULE_DESCRIPTION("ST Microelectronics SPEAr320 pinctrl driver");
 MODULE_LICENSE("GPL v2");
 MODULE_DEVICE_TABLE(of, spear320_pinctrl_of_match);
diff --git a/drivers/pinctrl/spear/pinctrl-spear3xx.c b/drivers/pinctrl/spear/pinctrl-spear3xx.c
index 12ee21a..d3119aa 100644
--- a/drivers/pinctrl/spear/pinctrl-spear3xx.c
+++ b/drivers/pinctrl/spear/pinctrl-spear3xx.c
@@ -2,7 +2,7 @@
  * Driver for the ST Microelectronics SPEAr3xx pinmux
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/pinctrl/spear/pinctrl-spear3xx.h b/drivers/pinctrl/spear/pinctrl-spear3xx.h
index 7860b36..ce19dcf 100644
--- a/drivers/pinctrl/spear/pinctrl-spear3xx.h
+++ b/drivers/pinctrl/spear/pinctrl-spear3xx.h
@@ -2,7 +2,7 @@
  * Header file for the ST Microelectronics SPEAr3xx pinmux
  *
  * Copyright (C) 2012 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/drivers/platform/chrome/Kconfig b/drivers/platform/chrome/Kconfig
index cb13299..3271cd1 100644
--- a/drivers/platform/chrome/Kconfig
+++ b/drivers/platform/chrome/Kconfig
@@ -4,7 +4,6 @@
 
 menuconfig CHROME_PLATFORMS
 	bool "Platform support for Chrome hardware"
-	depends on X86 || ARM
 	---help---
 	  Say Y here to get to see options for platform support for
 	  various Chromebooks and Chromeboxes. This option alone does
diff --git a/drivers/platform/x86/dell-laptop.c b/drivers/platform/x86/dell-laptop.c
index ed317cc..aaeeae8 100644
--- a/drivers/platform/x86/dell-laptop.c
+++ b/drivers/platform/x86/dell-laptop.c
@@ -309,12 +309,15 @@
 static struct calling_interface_buffer *buffer;
 static DEFINE_MUTEX(buffer_mutex);
 
-static int hwswitch_state;
+static void clear_buffer(void)
+{
+	memset(buffer, 0, sizeof(struct calling_interface_buffer));
+}
 
 static void get_buffer(void)
 {
 	mutex_lock(&buffer_mutex);
-	memset(buffer, 0, sizeof(struct calling_interface_buffer));
+	clear_buffer();
 }
 
 static void release_buffer(void)
@@ -548,21 +551,41 @@
 	int disable = blocked ? 1 : 0;
 	unsigned long radio = (unsigned long)data;
 	int hwswitch_bit = (unsigned long)data - 1;
+	int hwswitch;
+	int status;
+	int ret;
 
 	get_buffer();
+
 	dell_send_request(buffer, 17, 11);
+	ret = buffer->output[0];
+	status = buffer->output[1];
+
+	if (ret != 0)
+		goto out;
+
+	clear_buffer();
+
+	buffer->input[0] = 0x2;
+	dell_send_request(buffer, 17, 11);
+	ret = buffer->output[0];
+	hwswitch = buffer->output[1];
 
 	/* If the hardware switch controls this radio, and the hardware
 	   switch is disabled, always disable the radio */
-	if ((hwswitch_state & BIT(hwswitch_bit)) &&
-	    !(buffer->output[1] & BIT(16)))
+	if (ret == 0 && (hwswitch & BIT(hwswitch_bit)) &&
+	    (status & BIT(0)) && !(status & BIT(16)))
 		disable = 1;
 
+	clear_buffer();
+
 	buffer->input[0] = (1 | (radio<<8) | (disable << 16));
 	dell_send_request(buffer, 17, 11);
+	ret = buffer->output[0];
 
+ out:
 	release_buffer();
-	return 0;
+	return dell_smi_error(ret);
 }
 
 /* Must be called with the buffer held */
@@ -572,6 +595,7 @@
 	if (status & BIT(0)) {
 		/* Has hw-switch, sync sw_state to BIOS */
 		int block = rfkill_blocked(rfkill);
+		clear_buffer();
 		buffer->input[0] = (1 | (radio << 8) | (block << 16));
 		dell_send_request(buffer, 17, 11);
 	} else {
@@ -581,23 +605,43 @@
 }
 
 static void dell_rfkill_update_hw_state(struct rfkill *rfkill, int radio,
-					int status)
+					int status, int hwswitch)
 {
-	if (hwswitch_state & (BIT(radio - 1)))
+	if (hwswitch & (BIT(radio - 1)))
 		rfkill_set_hw_state(rfkill, !(status & BIT(16)));
 }
 
 static void dell_rfkill_query(struct rfkill *rfkill, void *data)
 {
+	int radio = ((unsigned long)data & 0xF);
+	int hwswitch;
 	int status;
+	int ret;
 
 	get_buffer();
+
 	dell_send_request(buffer, 17, 11);
+	ret = buffer->output[0];
 	status = buffer->output[1];
 
-	dell_rfkill_update_hw_state(rfkill, (unsigned long)data, status);
+	if (ret != 0 || !(status & BIT(0))) {
+		release_buffer();
+		return;
+	}
+
+	clear_buffer();
+
+	buffer->input[0] = 0x2;
+	dell_send_request(buffer, 17, 11);
+	ret = buffer->output[0];
+	hwswitch = buffer->output[1];
 
 	release_buffer();
+
+	if (ret != 0)
+		return;
+
+	dell_rfkill_update_hw_state(rfkill, radio, status, hwswitch);
 }
 
 static const struct rfkill_ops dell_rfkill_ops = {
@@ -609,13 +653,27 @@
 
 static int dell_debugfs_show(struct seq_file *s, void *data)
 {
+	int hwswitch_state;
+	int hwswitch_ret;
 	int status;
+	int ret;
 
 	get_buffer();
+
 	dell_send_request(buffer, 17, 11);
+	ret = buffer->output[0];
 	status = buffer->output[1];
+
+	clear_buffer();
+
+	buffer->input[0] = 0x2;
+	dell_send_request(buffer, 17, 11);
+	hwswitch_ret = buffer->output[0];
+	hwswitch_state = buffer->output[1];
+
 	release_buffer();
 
+	seq_printf(s, "return:\t%d\n", ret);
 	seq_printf(s, "status:\t0x%X\n", status);
 	seq_printf(s, "Bit 0 : Hardware switch supported:   %lu\n",
 		   status & BIT(0));
@@ -657,7 +715,8 @@
 	seq_printf(s, "Bit 21: WiGig is blocked:            %lu\n",
 		  (status & BIT(21)) >> 21);
 
-	seq_printf(s, "\nhwswitch_state:\t0x%X\n", hwswitch_state);
+	seq_printf(s, "\nhwswitch_return:\t%d\n", hwswitch_ret);
+	seq_printf(s, "hwswitch_state:\t0x%X\n", hwswitch_state);
 	seq_printf(s, "Bit 0 : Wifi controlled by switch:      %lu\n",
 		   hwswitch_state & BIT(0));
 	seq_printf(s, "Bit 1 : Bluetooth controlled by switch: %lu\n",
@@ -693,25 +752,43 @@
 
 static void dell_update_rfkill(struct work_struct *ignored)
 {
+	int hwswitch = 0;
 	int status;
+	int ret;
 
 	get_buffer();
+
 	dell_send_request(buffer, 17, 11);
+	ret = buffer->output[0];
 	status = buffer->output[1];
 
+	if (ret != 0)
+		goto out;
+
+	clear_buffer();
+
+	buffer->input[0] = 0x2;
+	dell_send_request(buffer, 17, 11);
+	ret = buffer->output[0];
+
+	if (ret == 0 && (status & BIT(0)))
+		hwswitch = buffer->output[1];
+
 	if (wifi_rfkill) {
-		dell_rfkill_update_hw_state(wifi_rfkill, 1, status);
+		dell_rfkill_update_hw_state(wifi_rfkill, 1, status, hwswitch);
 		dell_rfkill_update_sw_state(wifi_rfkill, 1, status);
 	}
 	if (bluetooth_rfkill) {
-		dell_rfkill_update_hw_state(bluetooth_rfkill, 2, status);
+		dell_rfkill_update_hw_state(bluetooth_rfkill, 2, status,
+					    hwswitch);
 		dell_rfkill_update_sw_state(bluetooth_rfkill, 2, status);
 	}
 	if (wwan_rfkill) {
-		dell_rfkill_update_hw_state(wwan_rfkill, 3, status);
+		dell_rfkill_update_hw_state(wwan_rfkill, 3, status, hwswitch);
 		dell_rfkill_update_sw_state(wwan_rfkill, 3, status);
 	}
 
+ out:
 	release_buffer();
 }
 static DECLARE_DELAYED_WORK(dell_rfkill_work, dell_update_rfkill);
@@ -773,21 +850,17 @@
 
 	get_buffer();
 	dell_send_request(buffer, 17, 11);
+	ret = buffer->output[0];
 	status = buffer->output[1];
-	buffer->input[0] = 0x2;
-	dell_send_request(buffer, 17, 11);
-	hwswitch_state = buffer->output[1];
 	release_buffer();
 
-	if (!(status & BIT(0))) {
-		if (force_rfkill) {
-			/* No hwsitch, clear all hw-controlled bits */
-			hwswitch_state &= ~7;
-		} else {
-			/* rfkill is only tested on laptops with a hwswitch */
-			return 0;
-		}
-	}
+	/* dell wireless info smbios call is not supported */
+	if (ret != 0)
+		return 0;
+
+	/* rfkill is only tested on laptops with a hwswitch */
+	if (!(status & BIT(0)) && !force_rfkill)
+		return 0;
 
 	if ((status & (1<<2|1<<8)) == (1<<2|1<<8)) {
 		wifi_rfkill = rfkill_alloc("dell-wifi", &platform_device->dev,
@@ -932,47 +1005,50 @@
 
 static int dell_send_intensity(struct backlight_device *bd)
 {
-	int ret = 0;
+	int token;
+	int ret;
+
+	token = find_token_location(BRIGHTNESS_TOKEN);
+	if (token == -1)
+		return -ENODEV;
 
 	get_buffer();
-	buffer->input[0] = find_token_location(BRIGHTNESS_TOKEN);
+	buffer->input[0] = token;
 	buffer->input[1] = bd->props.brightness;
 
-	if (buffer->input[0] == -1) {
-		ret = -ENODEV;
-		goto out;
-	}
-
 	if (power_supply_is_system_supplied() > 0)
 		dell_send_request(buffer, 1, 2);
 	else
 		dell_send_request(buffer, 1, 1);
 
- out:
+	ret = dell_smi_error(buffer->output[0]);
+
 	release_buffer();
 	return ret;
 }
 
 static int dell_get_intensity(struct backlight_device *bd)
 {
-	int ret = 0;
+	int token;
+	int ret;
+
+	token = find_token_location(BRIGHTNESS_TOKEN);
+	if (token == -1)
+		return -ENODEV;
 
 	get_buffer();
-	buffer->input[0] = find_token_location(BRIGHTNESS_TOKEN);
-
-	if (buffer->input[0] == -1) {
-		ret = -ENODEV;
-		goto out;
-	}
+	buffer->input[0] = token;
 
 	if (power_supply_is_system_supplied() > 0)
 		dell_send_request(buffer, 0, 2);
 	else
 		dell_send_request(buffer, 0, 1);
 
-	ret = buffer->output[1];
+	if (buffer->output[0])
+		ret = dell_smi_error(buffer->output[0]);
+	else
+		ret = buffer->output[1];
 
- out:
 	release_buffer();
 	return ret;
 }
@@ -2036,6 +2112,7 @@
 static int __init dell_init(void)
 {
 	int max_intensity = 0;
+	int token;
 	int ret;
 
 	if (!dmi_check_system(dell_device_table))
@@ -2094,13 +2171,15 @@
 	if (acpi_video_get_backlight_type() != acpi_backlight_vendor)
 		return 0;
 
-	get_buffer();
-	buffer->input[0] = find_token_location(BRIGHTNESS_TOKEN);
-	if (buffer->input[0] != -1) {
+	token = find_token_location(BRIGHTNESS_TOKEN);
+	if (token != -1) {
+		get_buffer();
+		buffer->input[0] = token;
 		dell_send_request(buffer, 0, 2);
-		max_intensity = buffer->output[3];
+		if (buffer->output[0] == 0)
+			max_intensity = buffer->output[3];
+		release_buffer();
 	}
-	release_buffer();
 
 	if (max_intensity) {
 		struct backlight_properties props;
diff --git a/drivers/platform/x86/intel_pmc_ipc.c b/drivers/platform/x86/intel_pmc_ipc.c
index d734763..105cfff 100644
--- a/drivers/platform/x86/intel_pmc_ipc.c
+++ b/drivers/platform/x86/intel_pmc_ipc.c
@@ -96,18 +96,18 @@
 	struct completion cmd_complete;
 
 	/* The following PMC BARs share the same ACPI device with the IPC */
-	void *acpi_io_base;
+	resource_size_t acpi_io_base;
 	int acpi_io_size;
 	struct platform_device *tco_dev;
 
 	/* gcr */
-	void *gcr_base;
+	resource_size_t gcr_base;
 	int gcr_size;
 
 	/* punit */
-	void *punit_base;
+	resource_size_t punit_base;
 	int punit_size;
-	void *punit_base2;
+	resource_size_t punit_base2;
 	int punit_size2;
 	struct platform_device *punit_dev;
 } ipcdev;
@@ -210,10 +210,15 @@
 	return ret;
 }
 
-/*
- * intel_pmc_ipc_simple_command
- * @cmd: command
- * @sub: sub type
+/**
+ * intel_pmc_ipc_simple_command() - Simple IPC command
+ * @cmd:	IPC command code.
+ * @sub:	IPC command sub type.
+ *
+ * Send a simple IPC command to PMC when don't need to specify
+ * input/output data and source/dest pointers.
+ *
+ * Return:	an IPC error code or 0 on success.
  */
 int intel_pmc_ipc_simple_command(int cmd, int sub)
 {
@@ -232,16 +237,20 @@
 }
 EXPORT_SYMBOL_GPL(intel_pmc_ipc_simple_command);
 
-/*
- * intel_pmc_ipc_raw_cmd
- * @cmd: command
- * @sub: sub type
- * @in: input data
- * @inlen: input length in bytes
- * @out: output data
- * @outlen: output length in dwords
- * @sptr: data writing to SPTR register
- * @dptr: data writing to DPTR register
+/**
+ * intel_pmc_ipc_raw_cmd() - IPC command with data and pointers
+ * @cmd:	IPC command code.
+ * @sub:	IPC command sub type.
+ * @in:		input data of this IPC command.
+ * @inlen:	input data length in bytes.
+ * @out:	output data of this IPC command.
+ * @outlen:	output data length in dwords.
+ * @sptr:	data writing to SPTR register.
+ * @dptr:	data writing to DPTR register.
+ *
+ * Send an IPC command to PMC with input/output data and source/dest pointers.
+ *
+ * Return:	an IPC error code or 0 on success.
  */
 int intel_pmc_ipc_raw_cmd(u32 cmd, u32 sub, u8 *in, u32 inlen, u32 *out,
 			  u32 outlen, u32 dptr, u32 sptr)
@@ -278,14 +287,18 @@
 }
 EXPORT_SYMBOL_GPL(intel_pmc_ipc_raw_cmd);
 
-/*
- * intel_pmc_ipc_command
- * @cmd: command
- * @sub: sub type
- * @in: input data
- * @inlen: input length in bytes
- * @out: output data
- * @outlen: output length in dwords
+/**
+ * intel_pmc_ipc_command() -  IPC command with input/output data
+ * @cmd:	IPC command code.
+ * @sub:	IPC command sub type.
+ * @in:		input data of this IPC command.
+ * @inlen:	input data length in bytes.
+ * @out:	output data of this IPC command.
+ * @outlen:	output data length in dwords.
+ *
+ * Send an IPC command to PMC with input/output data.
+ *
+ * Return:	an IPC error code or 0 on success.
  */
 int intel_pmc_ipc_command(u32 cmd, u32 sub, u8 *in, u32 inlen,
 			  u32 *out, u32 outlen)
@@ -480,11 +493,11 @@
 	pdev->dev.parent = ipcdev.dev;
 
 	res = punit_res;
-	res->start = (resource_size_t)ipcdev.punit_base;
+	res->start = ipcdev.punit_base;
 	res->end = res->start + ipcdev.punit_size - 1;
 
 	res = punit_res + PUNIT_RESOURCE_INTER;
-	res->start = (resource_size_t)ipcdev.punit_base2;
+	res->start = ipcdev.punit_base2;
 	res->end = res->start + ipcdev.punit_size2 - 1;
 
 	ret = platform_device_add_resources(pdev, punit_res,
@@ -522,15 +535,15 @@
 	pdev->dev.parent = ipcdev.dev;
 
 	res = tco_res + TCO_RESOURCE_ACPI_IO;
-	res->start = (resource_size_t)ipcdev.acpi_io_base + TCO_BASE_OFFSET;
+	res->start = ipcdev.acpi_io_base + TCO_BASE_OFFSET;
 	res->end = res->start + TCO_REGS_SIZE - 1;
 
 	res = tco_res + TCO_RESOURCE_SMI_EN_IO;
-	res->start = (resource_size_t)ipcdev.acpi_io_base + SMI_EN_OFFSET;
+	res->start = ipcdev.acpi_io_base + SMI_EN_OFFSET;
 	res->end = res->start + SMI_EN_SIZE - 1;
 
 	res = tco_res + TCO_RESOURCE_GCR_MEM;
-	res->start = (resource_size_t)ipcdev.gcr_base;
+	res->start = ipcdev.gcr_base;
 	res->end = res->start + ipcdev.gcr_size - 1;
 
 	ret = platform_device_add_resources(pdev, tco_res, ARRAY_SIZE(tco_res));
@@ -589,7 +602,7 @@
 		return -ENXIO;
 	}
 	size = resource_size(res);
-	ipcdev.acpi_io_base = (void *)res->start;
+	ipcdev.acpi_io_base = res->start;
 	ipcdev.acpi_io_size = size;
 	dev_info(&pdev->dev, "io res: %llx %x\n",
 		 (long long)res->start, (int)resource_size(res));
@@ -601,7 +614,7 @@
 		return -ENXIO;
 	}
 	size = resource_size(res);
-	ipcdev.punit_base = (void *)res->start;
+	ipcdev.punit_base = res->start;
 	ipcdev.punit_size = size;
 	dev_info(&pdev->dev, "punit data res: %llx %x\n",
 		 (long long)res->start, (int)resource_size(res));
@@ -613,7 +626,7 @@
 		return -ENXIO;
 	}
 	size = resource_size(res);
-	ipcdev.punit_base2 = (void *)res->start;
+	ipcdev.punit_base2 = res->start;
 	ipcdev.punit_size2 = size;
 	dev_info(&pdev->dev, "punit interface res: %llx %x\n",
 		 (long long)res->start, (int)resource_size(res));
@@ -637,7 +650,7 @@
 	}
 	ipcdev.ipc_base = addr;
 
-	ipcdev.gcr_base = (void *)(res->start + size);
+	ipcdev.gcr_base = res->start + size;
 	ipcdev.gcr_size = PLAT_RESOURCE_GCR_SIZE;
 	dev_info(&pdev->dev, "ipc res: %llx %x\n",
 		 (long long)res->start, (int)resource_size(res));
diff --git a/drivers/platform/x86/intel_scu_ipc.c b/drivers/platform/x86/intel_scu_ipc.c
index 001b199..187d108 100644
--- a/drivers/platform/x86/intel_scu_ipc.c
+++ b/drivers/platform/x86/intel_scu_ipc.c
@@ -216,13 +216,13 @@
 	int nc;
 	u32 offset = 0;
 	int err;
-	u8 cbuf[IPC_WWBUF_SIZE] = { };
+	u8 cbuf[IPC_WWBUF_SIZE];
 	u32 *wbuf = (u32 *)&cbuf;
 
-	mutex_lock(&ipclock);
-
 	memset(cbuf, 0, sizeof(cbuf));
 
+	mutex_lock(&ipclock);
+
 	if (ipcdev.pdev == NULL) {
 		mutex_unlock(&ipclock);
 		return -ENODEV;
diff --git a/drivers/pnp/system.c b/drivers/pnp/system.c
index 515f338..49c1720 100644
--- a/drivers/pnp/system.c
+++ b/drivers/pnp/system.c
@@ -7,7 +7,6 @@
  *	Bjorn Helgaas <bjorn.helgaas@hp.com>
  */
 
-#include <linux/acpi.h>
 #include <linux/pnp.h>
 #include <linux/device.h>
 #include <linux/init.h>
@@ -23,41 +22,25 @@
 	{"", 0}
 };
 
-#ifdef CONFIG_ACPI
-static bool __reserve_range(u64 start, unsigned int length, bool io, char *desc)
-{
-	u8 space_id = io ? ACPI_ADR_SPACE_SYSTEM_IO : ACPI_ADR_SPACE_SYSTEM_MEMORY;
-	return !acpi_reserve_region(start, length, space_id, IORESOURCE_BUSY, desc);
-}
-#else
-static bool __reserve_range(u64 start, unsigned int length, bool io, char *desc)
-{
-	struct resource *res;
-
-	res = io ? request_region(start, length, desc) :
-		request_mem_region(start, length, desc);
-	if (res) {
-		res->flags &= ~IORESOURCE_BUSY;
-		return true;
-	}
-	return false;
-}
-#endif
-
 static void reserve_range(struct pnp_dev *dev, struct resource *r, int port)
 {
 	char *regionid;
 	const char *pnpid = dev_name(&dev->dev);
 	resource_size_t start = r->start, end = r->end;
-	bool reserved;
+	struct resource *res;
 
 	regionid = kmalloc(16, GFP_KERNEL);
 	if (!regionid)
 		return;
 
 	snprintf(regionid, 16, "pnp %s", pnpid);
-	reserved = __reserve_range(start, end - start + 1, !!port, regionid);
-	if (!reserved)
+	if (port)
+		res = request_region(start, end - start + 1, regionid);
+	else
+		res = request_mem_region(start, end - start + 1, regionid);
+	if (res)
+		res->flags &= ~IORESOURCE_BUSY;
+	else
 		kfree(regionid);
 
 	/*
@@ -66,7 +49,7 @@
 	 * have double reservations.
 	 */
 	dev_info(&dev->dev, "%pR %s reserved\n", r,
-		 reserved ? "has been" : "could not be");
+		 res ? "has been" : "could not be");
 }
 
 static void reserve_resources_of_dev(struct pnp_dev *dev)
diff --git a/drivers/regulator/88pm800.c b/drivers/regulator/88pm800.c
index 832932b..7fd4f51 100644
--- a/drivers/regulator/88pm800.c
+++ b/drivers/regulator/88pm800.c
@@ -130,7 +130,7 @@
 		.owner	= THIS_MODULE,					\
 		.n_voltages = ARRAY_SIZE(ldo_volt_table),		\
 		.vsel_reg	= PM800_##vreg##_VOUT,			\
-		.vsel_mask	= 0x1f,					\
+		.vsel_mask	= 0xf,					\
 		.enable_reg	= PM800_##ereg,				\
 		.enable_mask	= 1 << (ebit),				\
 		.volt_table	= ldo_volt_table,			\
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index c9f7201..78387a6 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -109,6 +109,7 @@
 static struct regulator *create_regulator(struct regulator_dev *rdev,
 					  struct device *dev,
 					  const char *supply_name);
+static void _regulator_put(struct regulator *regulator);
 
 static const char *rdev_get_name(struct regulator_dev *rdev)
 {
@@ -1105,6 +1106,9 @@
 
 	rdev_info(rdev, "supplied by %s\n", rdev_get_name(supply_rdev));
 
+	if (!try_module_get(supply_rdev->owner))
+		return -ENODEV;
+
 	rdev->supply = create_regulator(supply_rdev, &rdev->dev, "SUPPLY");
 	if (rdev->supply == NULL) {
 		err = -ENOMEM;
@@ -1381,9 +1385,13 @@
 	}
 
 	if (!r) {
-		dev_err(dev, "Failed to resolve %s-supply for %s\n",
-			rdev->supply_name, rdev->desc->name);
-		return -EPROBE_DEFER;
+		if (have_full_constraints()) {
+			r = dummy_regulator_rdev;
+		} else {
+			dev_err(dev, "Failed to resolve %s-supply for %s\n",
+				rdev->supply_name, rdev->desc->name);
+			return -EPROBE_DEFER;
+		}
 	}
 
 	/* Recursively resolve the supply of the supply */
@@ -1398,8 +1406,11 @@
 	/* Cascade always-on state to supply */
 	if (_regulator_is_enabled(rdev)) {
 		ret = regulator_enable(rdev->supply);
-		if (ret < 0)
+		if (ret < 0) {
+			if (rdev->supply)
+				_regulator_put(rdev->supply);
 			return ret;
+		}
 	}
 
 	return 0;
diff --git a/drivers/regulator/max8973-regulator.c b/drivers/regulator/max8973-regulator.c
index 6f2bdad..e94ddcf 100644
--- a/drivers/regulator/max8973-regulator.c
+++ b/drivers/regulator/max8973-regulator.c
@@ -450,7 +450,7 @@
 		pdata->control_flags  |= MAX8973_CONTROL_FREQ_SHIFT_9PER_ENABLE;
 
 	if (of_property_read_bool(np, "maxim,enable-bias-control"))
-		pdata->control_flags  |= MAX8973_BIAS_ENABLE;
+		pdata->control_flags  |= MAX8973_CONTROL_BIAS_ENABLE;
 
 	return pdata;
 }
diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index 326ffb5..72fc3c3 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -34,6 +34,8 @@
 #include <linux/mfd/samsung/s2mps14.h>
 #include <linux/mfd/samsung/s2mpu02.h>
 
+/* The highest number of possible regulators for supported devices. */
+#define S2MPS_REGULATOR_MAX		S2MPS13_REGULATOR_MAX
 struct s2mps11_info {
 	unsigned int rdev_num;
 	int ramp_delay2;
@@ -49,7 +51,7 @@
 	 * One bit for each S2MPS13/S2MPS14/S2MPU02 regulator whether
 	 * the suspend mode was enabled.
 	 */
-	unsigned long long s2mps14_suspend_state:50;
+	DECLARE_BITMAP(suspend_state, S2MPS_REGULATOR_MAX);
 
 	/* Array of size rdev_num with GPIO-s for external sleep control */
 	int *ext_control_gpio;
@@ -500,7 +502,7 @@
 	switch (s2mps11->dev_type) {
 	case S2MPS13X:
 	case S2MPS14X:
-		if (s2mps11->s2mps14_suspend_state & (1 << rdev_get_id(rdev)))
+		if (test_bit(rdev_get_id(rdev), s2mps11->suspend_state))
 			val = S2MPS14_ENABLE_SUSPEND;
 		else if (gpio_is_valid(s2mps11->ext_control_gpio[rdev_get_id(rdev)]))
 			val = S2MPS14_ENABLE_EXT_CONTROL;
@@ -508,7 +510,7 @@
 			val = rdev->desc->enable_mask;
 		break;
 	case S2MPU02:
-		if (s2mps11->s2mps14_suspend_state & (1 << rdev_get_id(rdev)))
+		if (test_bit(rdev_get_id(rdev), s2mps11->suspend_state))
 			val = S2MPU02_ENABLE_SUSPEND;
 		else
 			val = rdev->desc->enable_mask;
@@ -562,7 +564,7 @@
 	if (ret < 0)
 		return ret;
 
-	s2mps11->s2mps14_suspend_state |= (1 << rdev_get_id(rdev));
+	set_bit(rdev_get_id(rdev), s2mps11->suspend_state);
 	/*
 	 * Don't enable suspend mode if regulator is already disabled because
 	 * this would effectively for a short time turn on the regulator after
@@ -960,18 +962,22 @@
 	case S2MPS11X:
 		s2mps11->rdev_num = ARRAY_SIZE(s2mps11_regulators);
 		regulators = s2mps11_regulators;
+		BUILD_BUG_ON(S2MPS_REGULATOR_MAX < s2mps11->rdev_num);
 		break;
 	case S2MPS13X:
 		s2mps11->rdev_num = ARRAY_SIZE(s2mps13_regulators);
 		regulators = s2mps13_regulators;
+		BUILD_BUG_ON(S2MPS_REGULATOR_MAX < s2mps11->rdev_num);
 		break;
 	case S2MPS14X:
 		s2mps11->rdev_num = ARRAY_SIZE(s2mps14_regulators);
 		regulators = s2mps14_regulators;
+		BUILD_BUG_ON(S2MPS_REGULATOR_MAX < s2mps11->rdev_num);
 		break;
 	case S2MPU02:
 		s2mps11->rdev_num = ARRAY_SIZE(s2mpu02_regulators);
 		regulators = s2mpu02_regulators;
+		BUILD_BUG_ON(S2MPS_REGULATOR_MAX < s2mps11->rdev_num);
 		break;
 	default:
 		dev_err(&pdev->dev, "Invalid device type: %u\n",
diff --git a/drivers/rtc/rtc-armada38x.c b/drivers/rtc/rtc-armada38x.c
index 4b62d1a..2b08cac 100644
--- a/drivers/rtc/rtc-armada38x.c
+++ b/drivers/rtc/rtc-armada38x.c
@@ -88,7 +88,7 @@
 {
 	struct armada38x_rtc *rtc = dev_get_drvdata(dev);
 	int ret = 0;
-	unsigned long time, flags;
+	unsigned long time;
 
 	ret = rtc_tm_to_time(tm, &time);
 
diff --git a/drivers/rtc/rtc-mt6397.c b/drivers/rtc/rtc-mt6397.c
index c0090b6..eab230b 100644
--- a/drivers/rtc/rtc-mt6397.c
+++ b/drivers/rtc/rtc-mt6397.c
@@ -343,6 +343,8 @@
 		goto out_dispose_irq;
 	}
 
+	device_init_wakeup(&pdev->dev, 1);
+
 	rtc->rtc_dev = rtc_device_register("mt6397-rtc", &pdev->dev,
 					   &mtk_rtc_ops, THIS_MODULE);
 	if (IS_ERR(rtc->rtc_dev)) {
@@ -351,8 +353,6 @@
 		goto out_free_irq;
 	}
 
-	device_init_wakeup(&pdev->dev, 1);
-
 	return 0;
 
 out_free_irq:
diff --git a/drivers/s390/Makefile b/drivers/s390/Makefile
index 95bccfd..e5225ad 100644
--- a/drivers/s390/Makefile
+++ b/drivers/s390/Makefile
@@ -2,7 +2,7 @@
 # Makefile for the S/390 specific device drivers
 #
 
-obj-y += cio/ block/ char/ crypto/ net/ scsi/ kvm/
+obj-y += cio/ block/ char/ crypto/ net/ scsi/ virtio/
 
 drivers-y += drivers/s390/built-in.o
 
diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 1aec8ff..f73d2f5 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -1863,6 +1863,33 @@
 }
 
 /*
+ * return 1 when device is not eligible for IO
+ */
+static int __dasd_device_is_unusable(struct dasd_device *device,
+				     struct dasd_ccw_req *cqr)
+{
+	int mask = ~(DASD_STOPPED_DC_WAIT | DASD_UNRESUMED_PM);
+
+	if (test_bit(DASD_FLAG_OFFLINE, &device->flags)) {
+		/* dasd is being set offline. */
+		return 1;
+	}
+	if (device->stopped) {
+		if (device->stopped & mask) {
+			/* stopped and CQR will not change that. */
+			return 1;
+		}
+		if (!test_bit(DASD_CQR_VERIFY_PATH, &cqr->flags)) {
+			/* CQR is not able to change device to
+			 * operational. */
+			return 1;
+		}
+		/* CQR required to get device operational. */
+	}
+	return 0;
+}
+
+/*
  * Take a look at the first request on the ccw queue and check
  * if it needs to be started.
  */
@@ -1876,13 +1903,8 @@
 	cqr = list_entry(device->ccw_queue.next, struct dasd_ccw_req, devlist);
 	if (cqr->status != DASD_CQR_QUEUED)
 		return;
-	/* when device is stopped, return request to previous layer
-	 * exception: only the disconnect or unresumed bits are set and the
-	 * cqr is a path verification request
-	 */
-	if (device->stopped &&
-	    !(!(device->stopped & ~(DASD_STOPPED_DC_WAIT | DASD_UNRESUMED_PM))
-	      && test_bit(DASD_CQR_VERIFY_PATH, &cqr->flags))) {
+	/* if device is not usable return request to upper layer */
+	if (__dasd_device_is_unusable(device, cqr)) {
 		cqr->intrc = -EAGAIN;
 		cqr->status = DASD_CQR_CLEARED;
 		dasd_schedule_device_bh(device);
diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index a2597e6..ee3a6fa 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -699,7 +699,8 @@
 					       struct dasd_device, alias_list);
 	spin_unlock_irqrestore(&lcu->lock, flags);
 	alias_priv = (struct dasd_eckd_private *) alias_device->private;
-	if ((alias_priv->count < private->count) && !alias_device->stopped)
+	if ((alias_priv->count < private->count) && !alias_device->stopped &&
+	    !test_bit(DASD_FLAG_OFFLINE, &alias_device->flags))
 		return alias_device;
 	else
 		return NULL;
diff --git a/drivers/s390/char/sclp_early.c b/drivers/s390/char/sclp_early.c
index aeed796..7bc6df3 100644
--- a/drivers/s390/char/sclp_early.c
+++ b/drivers/s390/char/sclp_early.c
@@ -7,6 +7,7 @@
 #define KMSG_COMPONENT "sclp_early"
 #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
 
+#include <linux/errno.h>
 #include <asm/ctl_reg.h>
 #include <asm/sclp.h>
 #include <asm/ipl.h>
diff --git a/drivers/s390/crypto/zcrypt_api.c b/drivers/s390/crypto/zcrypt_api.c
index 08f1830..01bf1f5 100644
--- a/drivers/s390/crypto/zcrypt_api.c
+++ b/drivers/s390/crypto/zcrypt_api.c
@@ -54,6 +54,10 @@
 		   "Copyright IBM Corp. 2001, 2012");
 MODULE_LICENSE("GPL");
 
+static int zcrypt_hwrng_seed = 1;
+module_param_named(hwrng_seed, zcrypt_hwrng_seed, int, S_IRUSR|S_IRGRP);
+MODULE_PARM_DESC(hwrng_seed, "Turn on/off hwrng auto seed, default is 1 (on).");
+
 static DEFINE_SPINLOCK(zcrypt_device_lock);
 static LIST_HEAD(zcrypt_device_list);
 static int zcrypt_device_count = 0;
@@ -1373,6 +1377,7 @@
 static struct hwrng zcrypt_rng_dev = {
 	.name		= "zcrypt",
 	.data_read	= zcrypt_rng_data_read,
+	.quality	= 990,
 };
 
 static int zcrypt_rng_device_add(void)
@@ -1387,6 +1392,8 @@
 			goto out;
 		}
 		zcrypt_rng_buffer_index = 0;
+		if (!zcrypt_hwrng_seed)
+			zcrypt_rng_dev.quality = 0;
 		rc = hwrng_register(&zcrypt_rng_dev);
 		if (rc)
 			goto out_free;
diff --git a/drivers/s390/kvm/Makefile b/drivers/s390/virtio/Makefile
similarity index 100%
rename from drivers/s390/kvm/Makefile
rename to drivers/s390/virtio/Makefile
diff --git a/drivers/s390/kvm/kvm_virtio.c b/drivers/s390/virtio/kvm_virtio.c
similarity index 100%
rename from drivers/s390/kvm/kvm_virtio.c
rename to drivers/s390/virtio/kvm_virtio.c
diff --git a/drivers/s390/kvm/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
similarity index 100%
rename from drivers/s390/kvm/virtio_ccw.c
rename to drivers/s390/virtio/virtio_ccw.c
diff --git a/drivers/scsi/fnic/fnic.h b/drivers/scsi/fnic/fnic.h
index 26270c3..ce129e5 100644
--- a/drivers/scsi/fnic/fnic.h
+++ b/drivers/scsi/fnic/fnic.h
@@ -39,7 +39,7 @@
 
 #define DRV_NAME		"fnic"
 #define DRV_DESCRIPTION		"Cisco FCoE HBA Driver"
-#define DRV_VERSION		"1.6.0.17"
+#define DRV_VERSION		"1.6.0.17a"
 #define PFX			DRV_NAME ": "
 #define DFX                     DRV_NAME "%d: "
 
diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c
index 155b286..25436cd 100644
--- a/drivers/scsi/fnic/fnic_scsi.c
+++ b/drivers/scsi/fnic/fnic_scsi.c
@@ -425,6 +425,7 @@
 	unsigned long ptr;
 	struct fc_rport_priv *rdata;
 	spinlock_t *io_lock = NULL;
+	int io_lock_acquired = 0;
 
 	if (unlikely(fnic_chk_state_flags_locked(fnic, FNIC_FLAGS_IO_BLOCKED)))
 		return SCSI_MLQUEUE_HOST_BUSY;
@@ -518,6 +519,7 @@
 	spin_lock_irqsave(io_lock, flags);
 
 	/* initialize rest of io_req */
+	io_lock_acquired = 1;
 	io_req->port_id = rport->port_id;
 	io_req->start_time = jiffies;
 	CMD_STATE(sc) = FNIC_IOREQ_CMD_PENDING;
@@ -571,7 +573,7 @@
 		  (((u64)CMD_FLAGS(sc) >> 32) | CMD_STATE(sc)));
 
 	/* if only we issued IO, will we have the io lock */
-	if (CMD_FLAGS(sc) & FNIC_IO_INITIALIZED)
+	if (io_lock_acquired)
 		spin_unlock_irqrestore(io_lock, flags);
 
 	atomic_dec(&fnic->in_flight);
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 8827448..a9aa389 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -599,9 +599,10 @@
 {
 	struct ipr_trace_entry *trace_entry;
 	struct ipr_ioa_cfg *ioa_cfg = ipr_cmd->ioa_cfg;
+	unsigned int trace_index;
 
-	trace_entry = &ioa_cfg->trace[atomic_add_return
-			(1, &ioa_cfg->trace_index)%IPR_NUM_TRACE_ENTRIES];
+	trace_index = atomic_add_return(1, &ioa_cfg->trace_index) & IPR_TRACE_INDEX_MASK;
+	trace_entry = &ioa_cfg->trace[trace_index];
 	trace_entry->time = jiffies;
 	trace_entry->op_code = ipr_cmd->ioarcb.cmd_pkt.cdb[0];
 	trace_entry->type = type;
@@ -1051,10 +1052,15 @@
 
 static int ipr_get_hrrq_index(struct ipr_ioa_cfg *ioa_cfg)
 {
+	unsigned int hrrq;
+
 	if (ioa_cfg->hrrq_num == 1)
-		return 0;
-	else
-		return (atomic_add_return(1, &ioa_cfg->hrrq_index) % (ioa_cfg->hrrq_num - 1)) + 1;
+		hrrq = 0;
+	else {
+		hrrq = atomic_add_return(1, &ioa_cfg->hrrq_index);
+		hrrq = (hrrq % (ioa_cfg->hrrq_num - 1)) + 1;
+	}
+	return hrrq;
 }
 
 /**
@@ -6263,21 +6269,23 @@
 	struct ipr_ioa_cfg *ioa_cfg = ipr_cmd->ioa_cfg;
 	struct scsi_cmnd *scsi_cmd = ipr_cmd->scsi_cmd;
 	u32 ioasc = be32_to_cpu(ipr_cmd->s.ioasa.hdr.ioasc);
-	unsigned long hrrq_flags;
+	unsigned long lock_flags;
 
 	scsi_set_resid(scsi_cmd, be32_to_cpu(ipr_cmd->s.ioasa.hdr.residual_data_len));
 
 	if (likely(IPR_IOASC_SENSE_KEY(ioasc) == 0)) {
 		scsi_dma_unmap(scsi_cmd);
 
-		spin_lock_irqsave(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_lock_irqsave(ipr_cmd->hrrq->lock, lock_flags);
 		list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q);
 		scsi_cmd->scsi_done(scsi_cmd);
-		spin_unlock_irqrestore(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_unlock_irqrestore(ipr_cmd->hrrq->lock, lock_flags);
 	} else {
-		spin_lock_irqsave(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
+		spin_lock(&ipr_cmd->hrrq->_lock);
 		ipr_erp_start(ioa_cfg, ipr_cmd);
-		spin_unlock_irqrestore(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_unlock(&ipr_cmd->hrrq->_lock);
+		spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
 	}
 }
 
diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h
index 73790a1..6b97ee4 100644
--- a/drivers/scsi/ipr.h
+++ b/drivers/scsi/ipr.h
@@ -1486,6 +1486,7 @@
 
 #define IPR_NUM_TRACE_INDEX_BITS	8
 #define IPR_NUM_TRACE_ENTRIES		(1 << IPR_NUM_TRACE_INDEX_BITS)
+#define IPR_TRACE_INDEX_MASK		(IPR_NUM_TRACE_ENTRIES - 1)
 #define IPR_TRACE_SIZE	(sizeof(struct ipr_trace_entry) * IPR_NUM_TRACE_ENTRIES)
 	char trace_start[8];
 #define IPR_TRACE_START_LABEL			"trace"
diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index 1b3a094..30f9ef0 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -733,8 +733,6 @@
 	if (resp) {
 		resp(sp, fp, arg);
 		res = true;
-	} else if (!IS_ERR(fp)) {
-		fc_frame_free(fp);
 	}
 
 	spin_lock_bh(&ep->ex_lock);
@@ -1596,7 +1594,8 @@
 	 * If new exch resp handler is valid then call that
 	 * first.
 	 */
-	fc_invoke_resp(ep, sp, fp);
+	if (!fc_invoke_resp(ep, sp, fp))
+		fc_frame_free(fp);
 
 	fc_exch_release(ep);
 	return;
@@ -1695,7 +1694,8 @@
 	fc_exch_hold(ep);
 	if (!rc)
 		fc_exch_delete(ep);
-	fc_invoke_resp(ep, sp, fp);
+	if (!fc_invoke_resp(ep, sp, fp))
+		fc_frame_free(fp);
 	if (has_rec)
 		fc_exch_timer_set(ep, ep->r_a_tov);
 	fc_exch_release(ep);
diff --git a/drivers/scsi/libfc/fc_fcp.c b/drivers/scsi/libfc/fc_fcp.c
index c679594..2d5909c 100644
--- a/drivers/scsi/libfc/fc_fcp.c
+++ b/drivers/scsi/libfc/fc_fcp.c
@@ -1039,11 +1039,26 @@
 		fc_fcp_pkt_hold(fsp);
 		spin_unlock_irqrestore(&si->scsi_queue_lock, flags);
 
-		if (!fc_fcp_lock_pkt(fsp)) {
+		spin_lock_bh(&fsp->scsi_pkt_lock);
+		if (!(fsp->state & FC_SRB_COMPL)) {
+			fsp->state |= FC_SRB_COMPL;
+			/*
+			 * TODO: dropping scsi_pkt_lock and then reacquiring
+			 * again around fc_fcp_cleanup_cmd() is required,
+			 * since fc_fcp_cleanup_cmd() calls into
+			 * fc_seq_set_resp() and that func preempts cpu using
+			 * schedule. May be schedule and related code should be
+			 * removed instead of unlocking here to avoid scheduling
+			 * while atomic bug.
+			 */
+			spin_unlock_bh(&fsp->scsi_pkt_lock);
+
 			fc_fcp_cleanup_cmd(fsp, error);
+
+			spin_lock_bh(&fsp->scsi_pkt_lock);
 			fc_io_compl(fsp);
-			fc_fcp_unlock_pkt(fsp);
 		}
+		spin_unlock_bh(&fsp->scsi_pkt_lock);
 
 		fc_fcp_pkt_release(fsp);
 		spin_lock_irqsave(&si->scsi_queue_lock, flags);
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index 8053f24..98d9bb6 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -2941,10 +2941,10 @@
 {
 	struct iscsi_conn *conn = cls_conn->dd_data;
 	struct iscsi_session *session = conn->session;
-	unsigned long flags;
 
 	del_timer_sync(&conn->transport_timer);
 
+	mutex_lock(&session->eh_mutex);
 	spin_lock_bh(&session->frwd_lock);
 	conn->c_stage = ISCSI_CONN_CLEANUP_WAIT;
 	if (session->leadconn == conn) {
@@ -2956,28 +2956,6 @@
 	}
 	spin_unlock_bh(&session->frwd_lock);
 
-	/*
-	 * Block until all in-progress commands for this connection
-	 * time out or fail.
-	 */
-	for (;;) {
-		spin_lock_irqsave(session->host->host_lock, flags);
-		if (!atomic_read(&session->host->host_busy)) { /* OK for ERL == 0 */
-			spin_unlock_irqrestore(session->host->host_lock, flags);
-			break;
-		}
-		spin_unlock_irqrestore(session->host->host_lock, flags);
-		msleep_interruptible(500);
-		iscsi_conn_printk(KERN_INFO, conn, "iscsi conn_destroy(): "
-				  "host_busy %d host_failed %d\n",
-				  atomic_read(&session->host->host_busy),
-				  session->host->host_failed);
-		/*
-		 * force eh_abort() to unblock
-		 */
-		wake_up(&conn->ehwait);
-	}
-
 	/* flush queued up work because we free the connection below */
 	iscsi_suspend_tx(conn);
 
@@ -2994,6 +2972,7 @@
 	if (session->leadconn == conn)
 		session->leadconn = NULL;
 	spin_unlock_bh(&session->frwd_lock);
+	mutex_unlock(&session->eh_mutex);
 
 	iscsi_destroy_conn(cls_conn);
 }
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 82b92c4..437254e 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -738,7 +738,7 @@
 		ql_log(ql_log_info, vha, 0x706f,
 		    "Issuing MPI reset.\n");
 
-		if (IS_QLA83XX(ha)) {
+		if (IS_QLA83XX(ha) || IS_QLA27XX(ha)) {
 			uint32_t idc_control;
 
 			qla83xx_idc_lock(vha, 0);
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 0e6ee3c..8b011ae 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -67,10 +67,10 @@
  * |                              |                    | 0xd031-0xd0ff	|
  * |                              |                    | 0xd101-0xd1fe	|
  * |                              |                    | 0xd214-0xd2fe	|
- * | Target Mode		  |	  0xe079       |		|
- * | Target Mode Management	  |	  0xf072       | 0xf002		|
+ * | Target Mode		  |	  0xe080       |		|
+ * | Target Mode Management	  |	  0xf096       | 0xf002		|
  * |                              |                    | 0xf046-0xf049  |
- * | Target Mode Task Management  |	  0x1000b      |		|
+ * | Target Mode Task Management  |	  0x1000d      |		|
  * ----------------------------------------------------------------------
  */
 
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index e86201d..9ad819e 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -274,6 +274,7 @@
 #define RESPONSE_ENTRY_CNT_FX00		256     /* Number of response entries.*/
 
 struct req_que;
+struct qla_tgt_sess;
 
 /*
  * (sd.h is not exported, hence local inclusion)
@@ -2026,6 +2027,7 @@
 	uint16_t port_id;
 
 	unsigned long retry_delay_timestamp;
+	struct qla_tgt_sess *tgt_session;
 } fc_port_t;
 
 #include "qla_mr.h"
@@ -3154,13 +3156,13 @@
 /* Bit 21 of fw_attributes decides the MCTP capabilities */
 #define IS_MCTP_CAPABLE(ha)	(IS_QLA2031(ha) && \
 				((ha)->fw_attributes_ext[0] & BIT_0))
-#define IS_PI_UNINIT_CAPABLE(ha)	(IS_QLA83XX(ha))
-#define IS_PI_IPGUARD_CAPABLE(ha)	(IS_QLA83XX(ha))
+#define IS_PI_UNINIT_CAPABLE(ha)	(IS_QLA83XX(ha) || IS_QLA27XX(ha))
+#define IS_PI_IPGUARD_CAPABLE(ha)	(IS_QLA83XX(ha) || IS_QLA27XX(ha))
 #define IS_PI_DIFB_DIX0_CAPABLE(ha)	(0)
-#define IS_PI_SPLIT_DET_CAPABLE_HBA(ha)	(IS_QLA83XX(ha))
+#define IS_PI_SPLIT_DET_CAPABLE_HBA(ha)	(IS_QLA83XX(ha) || IS_QLA27XX(ha))
 #define IS_PI_SPLIT_DET_CAPABLE(ha)	(IS_PI_SPLIT_DET_CAPABLE_HBA(ha) && \
     (((ha)->fw_attributes_h << 16 | (ha)->fw_attributes) & BIT_22))
-#define IS_ATIO_MSIX_CAPABLE(ha) (IS_QLA83XX(ha))
+#define IS_ATIO_MSIX_CAPABLE(ha) (IS_QLA83XX(ha) || IS_QLA27XX(ha))
 #define IS_TGT_MODE_CAPABLE(ha)	(ha->tgt.atio_q_length)
 #define IS_SHADOW_REG_CAPABLE(ha)  (IS_QLA27XX(ha))
 #define IS_DPORT_CAPABLE(ha)  (IS_QLA83XX(ha) || IS_QLA27XX(ha))
@@ -3579,6 +3581,16 @@
 	uint16_t	fcoe_fcf_idx;
 	uint8_t		fcoe_vn_port_mac[6];
 
+	/* list of commands waiting on workqueue */
+	struct list_head	qla_cmd_list;
+	struct list_head	qla_sess_op_cmd_list;
+	spinlock_t		cmd_list_lock;
+
+	/* Counter to detect races between ELS and RSCN events */
+	atomic_t		generation_tick;
+	/* Time when global fcport update has been scheduled */
+	int			total_fcport_update_gen;
+
 	uint32_t	vp_abort_cnt;
 
 	struct fc_vport	*fc_vport;	/* holds fc_vport * for each vport */
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 6640131..11f2f32 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -115,6 +115,8 @@
 			QLA_LOGIO_LOGIN_RETRIED : 0;
 		qla2x00_post_async_login_done_work(fcport->vha, fcport,
 			lio->u.logio.data);
+	} else if (sp->type == SRB_LOGOUT_CMD) {
+		qlt_logo_completion_handler(fcport, QLA_FUNCTION_TIMEOUT);
 	}
 }
 
@@ -497,7 +499,10 @@
 qla2x00_async_logout_done(struct scsi_qla_host *vha, fc_port_t *fcport,
     uint16_t *data)
 {
-	qla2x00_mark_device_lost(vha, fcport, 1, 0);
+	/* Don't re-login in target mode */
+	if (!fcport->tgt_session)
+		qla2x00_mark_device_lost(vha, fcport, 1, 0);
+	qlt_logo_completion_handler(fcport, data[0]);
 	return;
 }
 
@@ -1538,7 +1543,7 @@
 		mem_size = (ha->fw_memory_size - 0x11000 + 1) *
 		    sizeof(uint16_t);
 	} else if (IS_FWI2_CAPABLE(ha)) {
-		if (IS_QLA83XX(ha))
+		if (IS_QLA83XX(ha) || IS_QLA27XX(ha))
 			fixed_size = offsetof(struct qla83xx_fw_dump, ext_mem);
 		else if (IS_QLA81XX(ha))
 			fixed_size = offsetof(struct qla81xx_fw_dump, ext_mem);
@@ -1550,7 +1555,7 @@
 		mem_size = (ha->fw_memory_size - 0x100000 + 1) *
 		    sizeof(uint32_t);
 		if (ha->mqenable) {
-			if (!IS_QLA83XX(ha))
+			if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha))
 				mq_size = sizeof(struct qla2xxx_mq_chain);
 			/*
 			 * Allocate maximum buffer size for all queues.
@@ -2922,21 +2927,14 @@
 {
 	fc_port_t *fcport = data;
 	struct fc_rport *rport;
-	scsi_qla_host_t *vha = fcport->vha;
 	unsigned long flags;
 
 	spin_lock_irqsave(fcport->vha->host->host_lock, flags);
 	rport = fcport->drport ? fcport->drport: fcport->rport;
 	fcport->drport = NULL;
 	spin_unlock_irqrestore(fcport->vha->host->host_lock, flags);
-	if (rport) {
+	if (rport)
 		fc_remote_port_delete(rport);
-		/*
-		 * Release the target mode FC NEXUS in qla_target.c code
-		 * if target mod is enabled.
-		 */
-		qlt_fc_port_deleted(vha, fcport);
-	}
 }
 
 /**
@@ -3303,6 +3301,7 @@
 	 * Create target mode FC NEXUS in qla_target.c if target mode is
 	 * enabled..
 	 */
+
 	qlt_fc_port_added(vha, fcport);
 
 	spin_lock_irqsave(fcport->vha->host->host_lock, flags);
@@ -3341,8 +3340,7 @@
 
 	if (IS_QLAFX00(vha->hw)) {
 		qla2x00_set_fcport_state(fcport, FCS_ONLINE);
-		qla2x00_reg_remote_port(vha, fcport);
-		return;
+		goto reg_port;
 	}
 	fcport->login_retry = 0;
 	fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT);
@@ -3350,7 +3348,16 @@
 	qla2x00_set_fcport_state(fcport, FCS_ONLINE);
 	qla2x00_iidma_fcport(vha, fcport);
 	qla24xx_update_fcport_fcp_prio(vha, fcport);
-	qla2x00_reg_remote_port(vha, fcport);
+
+reg_port:
+	if (qla_ini_mode_enabled(vha))
+		qla2x00_reg_remote_port(vha, fcport);
+	else {
+		/*
+		 * Create target mode FC NEXUS in qla_target.c
+		 */
+		qlt_fc_port_added(vha, fcport);
+	}
 }
 
 /*
@@ -3375,6 +3382,7 @@
 	LIST_HEAD(new_fcports);
 	struct qla_hw_data *ha = vha->hw;
 	struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev);
+	int		discovery_gen;
 
 	/* If FL port exists, then SNS is present */
 	if (IS_FWI2_CAPABLE(ha))
@@ -3445,6 +3453,14 @@
 			fcport->scan_state = QLA_FCPORT_SCAN;
 		}
 
+		/* Mark the time right before querying FW for connected ports.
+		 * This process is long, asynchronous and by the time it's done,
+		 * collected information might not be accurate anymore. E.g.
+		 * disconnected port might have re-connected and a brand new
+		 * session has been created. In this case session's generation
+		 * will be newer than discovery_gen. */
+		qlt_do_generation_tick(vha, &discovery_gen);
+
 		rval = qla2x00_find_all_fabric_devs(vha, &new_fcports);
 		if (rval != QLA_SUCCESS)
 			break;
@@ -3460,20 +3476,44 @@
 			if ((fcport->flags & FCF_FABRIC_DEVICE) == 0)
 				continue;
 
-			if (fcport->scan_state == QLA_FCPORT_SCAN &&
-			    atomic_read(&fcport->state) == FCS_ONLINE) {
-				qla2x00_mark_device_lost(vha, fcport,
-				    ql2xplogiabsentdevice, 0);
-				if (fcport->loop_id != FC_NO_LOOP_ID &&
-				    (fcport->flags & FCF_FCP2_DEVICE) == 0 &&
-				    fcport->port_type != FCT_INITIATOR &&
-				    fcport->port_type != FCT_BROADCAST) {
-					ha->isp_ops->fabric_logout(vha,
-					    fcport->loop_id,
-					    fcport->d_id.b.domain,
-					    fcport->d_id.b.area,
-					    fcport->d_id.b.al_pa);
-					qla2x00_clear_loop_id(fcport);
+			if (fcport->scan_state == QLA_FCPORT_SCAN) {
+				if (qla_ini_mode_enabled(base_vha) &&
+				    atomic_read(&fcport->state) == FCS_ONLINE) {
+					qla2x00_mark_device_lost(vha, fcport,
+					    ql2xplogiabsentdevice, 0);
+					if (fcport->loop_id != FC_NO_LOOP_ID &&
+					    (fcport->flags & FCF_FCP2_DEVICE) == 0 &&
+					    fcport->port_type != FCT_INITIATOR &&
+					    fcport->port_type != FCT_BROADCAST) {
+						ha->isp_ops->fabric_logout(vha,
+						    fcport->loop_id,
+						    fcport->d_id.b.domain,
+						    fcport->d_id.b.area,
+						    fcport->d_id.b.al_pa);
+						qla2x00_clear_loop_id(fcport);
+					}
+				} else if (!qla_ini_mode_enabled(base_vha)) {
+					/*
+					 * In target mode, explicitly kill
+					 * sessions and log out of devices
+					 * that are gone, so that we don't
+					 * end up with an initiator using the
+					 * wrong ACL (if the fabric recycles
+					 * an FC address and we have a stale
+					 * session around) and so that we don't
+					 * report initiators that are no longer
+					 * on the fabric.
+					 */
+					ql_dbg(ql_dbg_tgt_mgt, vha, 0xf077,
+					    "port gone, logging out/killing session: "
+					    "%8phC state 0x%x flags 0x%x fc4_type 0x%x "
+					    "scan_state %d\n",
+					    fcport->port_name,
+					    atomic_read(&fcport->state),
+					    fcport->flags, fcport->fc4_type,
+					    fcport->scan_state);
+					qlt_fc_port_deleted(vha, fcport,
+					    discovery_gen);
 				}
 			}
 		}
@@ -3494,6 +3534,28 @@
 			    (fcport->flags & FCF_LOGIN_NEEDED) == 0)
 				continue;
 
+			/*
+			 * If we're not an initiator, skip looking for devices
+			 * and logging in.  There's no reason for us to do it,
+			 * and it seems to actively cause problems in target
+			 * mode if we race with the initiator logging into us
+			 * (we might get the "port ID used" status back from
+			 * our login command and log out the initiator, which
+			 * seems to cause havoc).
+			 */
+			if (!qla_ini_mode_enabled(base_vha)) {
+				if (fcport->scan_state == QLA_FCPORT_FOUND) {
+					ql_dbg(ql_dbg_tgt_mgt, vha, 0xf078,
+					    "port %8phC state 0x%x flags 0x%x fc4_type 0x%x "
+					    "scan_state %d (initiator mode disabled; skipping "
+					    "login)\n", fcport->port_name,
+					    atomic_read(&fcport->state),
+					    fcport->flags, fcport->fc4_type,
+					    fcport->scan_state);
+				}
+				continue;
+			}
+
 			if (fcport->loop_id == FC_NO_LOOP_ID) {
 				fcport->loop_id = next_loopid;
 				rval = qla2x00_find_new_loop_id(
@@ -3520,16 +3582,38 @@
 			    test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags))
 				break;
 
-			/* Find a new loop ID to use. */
-			fcport->loop_id = next_loopid;
-			rval = qla2x00_find_new_loop_id(base_vha, fcport);
-			if (rval != QLA_SUCCESS) {
-				/* Ran out of IDs to use */
-				break;
-			}
+			/*
+			 * If we're not an initiator, skip looking for devices
+			 * and logging in.  There's no reason for us to do it,
+			 * and it seems to actively cause problems in target
+			 * mode if we race with the initiator logging into us
+			 * (we might get the "port ID used" status back from
+			 * our login command and log out the initiator, which
+			 * seems to cause havoc).
+			 */
+			if (qla_ini_mode_enabled(base_vha)) {
+				/* Find a new loop ID to use. */
+				fcport->loop_id = next_loopid;
+				rval = qla2x00_find_new_loop_id(base_vha,
+				    fcport);
+				if (rval != QLA_SUCCESS) {
+					/* Ran out of IDs to use */
+					break;
+				}
 
-			/* Login and update database */
-			qla2x00_fabric_dev_login(vha, fcport, &next_loopid);
+				/* Login and update database */
+				qla2x00_fabric_dev_login(vha, fcport,
+				    &next_loopid);
+			} else {
+				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf079,
+					"new port %8phC state 0x%x flags 0x%x fc4_type "
+					"0x%x scan_state %d (initiator mode disabled; "
+					"skipping login)\n",
+					fcport->port_name,
+					atomic_read(&fcport->state),
+					fcport->flags, fcport->fc4_type,
+					fcport->scan_state);
+			}
 
 			list_move_tail(&fcport->list, &vha->vp_fcports);
 		}
@@ -3725,11 +3809,12 @@
 			fcport->fp_speed = new_fcport->fp_speed;
 
 			/*
-			 * If address the same and state FCS_ONLINE, nothing
-			 * changed.
+			 * If address the same and state FCS_ONLINE
+			 * (or in target mode), nothing changed.
 			 */
 			if (fcport->d_id.b24 == new_fcport->d_id.b24 &&
-			    atomic_read(&fcport->state) == FCS_ONLINE) {
+			    (atomic_read(&fcport->state) == FCS_ONLINE ||
+			     !qla_ini_mode_enabled(base_vha))) {
 				break;
 			}
 
@@ -3749,6 +3834,22 @@
 			 * Log it out if still logged in and mark it for
 			 * relogin later.
 			 */
+			if (!qla_ini_mode_enabled(base_vha)) {
+				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf080,
+					 "port changed FC ID, %8phC"
+					 " old %x:%x:%x (loop_id 0x%04x)-> new %x:%x:%x\n",
+					 fcport->port_name,
+					 fcport->d_id.b.domain,
+					 fcport->d_id.b.area,
+					 fcport->d_id.b.al_pa,
+					 fcport->loop_id,
+					 new_fcport->d_id.b.domain,
+					 new_fcport->d_id.b.area,
+					 new_fcport->d_id.b.al_pa);
+				fcport->d_id.b24 = new_fcport->d_id.b24;
+				break;
+			}
+
 			fcport->d_id.b24 = new_fcport->d_id.b24;
 			fcport->flags |= FCF_LOGIN_NEEDED;
 			if (fcport->loop_id != FC_NO_LOOP_ID &&
@@ -3768,6 +3869,7 @@
 		if (found)
 			continue;
 		/* If device was not in our fcports list, then add it. */
+		new_fcport->scan_state = QLA_FCPORT_FOUND;
 		list_add_tail(&new_fcport->list, new_fcports);
 
 		/* Allocate a new replacement fcport. */
@@ -4188,6 +4290,14 @@
 			    atomic_read(&fcport->state) != FCS_UNCONFIGURED) {
 				spin_unlock_irqrestore(&ha->vport_slock, flags);
 				qla2x00_rport_del(fcport);
+
+				/*
+				 * Release the target mode FC NEXUS in
+				 * qla_target.c, if target mod is enabled.
+				 */
+				qlt_fc_port_deleted(vha, fcport,
+				    base_vha->total_fcport_update_gen);
+
 				spin_lock_irqsave(&ha->vport_slock, flags);
 			}
 		}
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 36fbd4c..6f02b26 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -1943,6 +1943,9 @@
 	logio->entry_type = LOGINOUT_PORT_IOCB_TYPE;
 	logio->control_flags =
 	    cpu_to_le16(LCF_COMMAND_LOGO|LCF_IMPL_LOGO);
+	if (!sp->fcport->tgt_session ||
+	    !sp->fcport->tgt_session->keep_nport_handle)
+		logio->control_flags |= cpu_to_le16(LCF_FREE_NPORT);
 	logio->nport_handle = cpu_to_le16(sp->fcport->loop_id);
 	logio->port_id[0] = sp->fcport->d_id.b.al_pa;
 	logio->port_id[1] = sp->fcport->d_id.b.area;
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 02b1c1c..b2f713a 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -2415,7 +2415,8 @@
 			*orig_iocb_cnt = mcp->mb[10];
 		if (vha->hw->flags.npiv_supported && max_npiv_vports)
 			*max_npiv_vports = mcp->mb[11];
-		if ((IS_QLA81XX(vha->hw) || IS_QLA83XX(vha->hw)) && max_fcfs)
+		if ((IS_QLA81XX(vha->hw) || IS_QLA83XX(vha->hw) ||
+		    IS_QLA27XX(vha->hw)) && max_fcfs)
 			*max_fcfs = mcp->mb[12];
 	}
 
@@ -3898,7 +3899,7 @@
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	if (!(rsp->options & BIT_0)) {
 		WRT_REG_DWORD(rsp->rsp_q_out, 0);
-		if (!IS_QLA83XX(ha))
+		if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha))
 			WRT_REG_DWORD(rsp->rsp_q_in, 0);
 	}
 
@@ -5345,7 +5346,7 @@
 	mbx_cmd_t *mcp = &mc;
 	struct qla_hw_data *ha = vha->hw;
 
-	if (!IS_QLA83XX(ha))
+	if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha))
 		return QLA_FUNCTION_FAILED;
 
 	ql_dbg(ql_dbg_mbx, vha, 0x1143, "Entered %s.\n", __func__);
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index a28815b..8a5cac8 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -2504,6 +2504,7 @@
 		ha->mbx_count = MAILBOX_REGISTER_COUNT;
 		req_length = REQUEST_ENTRY_CNT_24XX;
 		rsp_length = RESPONSE_ENTRY_CNT_2300;
+		ha->tgt.atio_q_length = ATIO_ENTRY_CNT_24XX;
 		ha->max_loop_id = SNS_LAST_LOOP_ID_2300;
 		ha->init_cb_size = sizeof(struct mid_init_cb_81xx);
 		ha->gid_list_info_size = 8;
@@ -3229,11 +3230,15 @@
 		spin_lock_irqsave(vha->host->host_lock, flags);
 		fcport->drport = rport;
 		spin_unlock_irqrestore(vha->host->host_lock, flags);
+		qlt_do_generation_tick(vha, &base_vha->total_fcport_update_gen);
 		set_bit(FCPORT_UPDATE_NEEDED, &base_vha->dpc_flags);
 		qla2xxx_wake_dpc(base_vha);
 	} else {
-		fc_remote_port_delete(rport);
-		qlt_fc_port_deleted(vha, fcport);
+		int now;
+		if (rport)
+			fc_remote_port_delete(rport);
+		qlt_do_generation_tick(vha, &now);
+		qlt_fc_port_deleted(vha, fcport, now);
 	}
 }
 
@@ -3763,8 +3768,11 @@
 	INIT_LIST_HEAD(&vha->vp_fcports);
 	INIT_LIST_HEAD(&vha->work_list);
 	INIT_LIST_HEAD(&vha->list);
+	INIT_LIST_HEAD(&vha->qla_cmd_list);
+	INIT_LIST_HEAD(&vha->qla_sess_op_cmd_list);
 
 	spin_lock_init(&vha->work_lock);
+	spin_lock_init(&vha->cmd_list_lock);
 
 	sprintf(vha->host_str, "%s_%ld", QLA2XXX_DRIVER_NAME, vha->host_no);
 	ql_dbg(ql_dbg_init, vha, 0x0041,
diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c
index 028e8c8..2feb5f3 100644
--- a/drivers/scsi/qla2xxx/qla_sup.c
+++ b/drivers/scsi/qla2xxx/qla_sup.c
@@ -1697,7 +1697,7 @@
 {
 	uint32_t led_select_value = 0;
 
-	if (!IS_QLA83XX(ha))
+	if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha))
 		goto out;
 
 	if (ha->port_no == 0)
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index b749026..58651ec 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -113,6 +113,11 @@
 static void qlt_alloc_qfull_cmd(struct scsi_qla_host *vha,
 	struct atio_from_isp *atio, uint16_t status, int qfull);
 static void qlt_disable_vha(struct scsi_qla_host *vha);
+static void qlt_clear_tgt_db(struct qla_tgt *tgt);
+static void qlt_send_notify_ack(struct scsi_qla_host *vha,
+	struct imm_ntfy_from_isp *ntfy,
+	uint32_t add_flags, uint16_t resp_code, int resp_code_valid,
+	uint16_t srr_flags, uint16_t srr_reject_code, uint8_t srr_explan);
 /*
  * Global Variables
  */
@@ -122,6 +127,16 @@
 static DEFINE_MUTEX(qla_tgt_mutex);
 static LIST_HEAD(qla_tgt_glist);
 
+/* This API intentionally takes dest as a parameter, rather than returning
+ * int value to avoid caller forgetting to issue wmb() after the store */
+void qlt_do_generation_tick(struct scsi_qla_host *vha, int *dest)
+{
+	scsi_qla_host_t *base_vha = pci_get_drvdata(vha->hw->pdev);
+	*dest = atomic_inc_return(&base_vha->generation_tick);
+	/* memory barrier */
+	wmb();
+}
+
 /* ha->hardware_lock supposed to be held on entry (to protect tgt->sess_list) */
 static struct qla_tgt_sess *qlt_find_sess_by_port_name(
 	struct qla_tgt *tgt,
@@ -381,14 +396,73 @@
 	struct qla_tgt *tgt = sess->tgt;
 	struct scsi_qla_host *vha = sess->vha;
 	struct qla_hw_data *ha = vha->hw;
+	unsigned long flags;
+	bool logout_started = false;
+	fc_port_t fcport;
+
+	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf084,
+		"%s: se_sess %p / sess %p from port %8phC loop_id %#04x"
+		" s_id %02x:%02x:%02x logout %d keep %d plogi %d\n",
+		__func__, sess->se_sess, sess, sess->port_name, sess->loop_id,
+		sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa,
+		sess->logout_on_delete, sess->keep_nport_handle,
+		sess->plogi_ack_needed);
 
 	BUG_ON(!tgt);
+
+	if (sess->logout_on_delete) {
+		int rc;
+
+		memset(&fcport, 0, sizeof(fcport));
+		fcport.loop_id = sess->loop_id;
+		fcport.d_id = sess->s_id;
+		memcpy(fcport.port_name, sess->port_name, WWN_SIZE);
+		fcport.vha = vha;
+		fcport.tgt_session = sess;
+
+		rc = qla2x00_post_async_logout_work(vha, &fcport, NULL);
+		if (rc != QLA_SUCCESS)
+			ql_log(ql_log_warn, vha, 0xf085,
+			       "Schedule logo failed sess %p rc %d\n",
+			       sess, rc);
+		else
+			logout_started = true;
+	}
+
 	/*
 	 * Release the target session for FC Nexus from fabric module code.
 	 */
 	if (sess->se_sess != NULL)
 		ha->tgt.tgt_ops->free_session(sess);
 
+	if (logout_started) {
+		bool traced = false;
+
+		while (!ACCESS_ONCE(sess->logout_completed)) {
+			if (!traced) {
+				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf086,
+					"%s: waiting for sess %p logout\n",
+					__func__, sess);
+				traced = true;
+			}
+			msleep(100);
+		}
+
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf087,
+			"%s: sess %p logout completed\n",
+			__func__, sess);
+	}
+
+	spin_lock_irqsave(&ha->hardware_lock, flags);
+
+	if (sess->plogi_ack_needed)
+		qlt_send_notify_ack(vha, &sess->tm_iocb,
+				    0, 0, 0, 0, 0, 0);
+
+	list_del(&sess->sess_list_entry);
+
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf001,
 	    "Unregistration of sess %p finished\n", sess);
 
@@ -409,9 +483,9 @@
 
 	vha->hw->tgt.tgt_ops->clear_nacl_from_fcport_map(sess);
 
-	list_del(&sess->sess_list_entry);
-	if (sess->deleted)
-		list_del(&sess->del_list_entry);
+	if (!list_empty(&sess->del_list_entry))
+		list_del_init(&sess->del_list_entry);
+	sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
 
 	INIT_WORK(&sess->free_work, qlt_free_session_done);
 	schedule_work(&sess->free_work);
@@ -431,10 +505,10 @@
 
 	loop_id = le16_to_cpu(n->u.isp24.nport_handle);
 	if (loop_id == 0xFFFF) {
-#if 0 /* FIXME: Re-enable Global event handling.. */
 		/* Global event */
-		atomic_inc(&ha->tgt.qla_tgt->tgt_global_resets_count);
-		qlt_clear_tgt_db(ha->tgt.qla_tgt);
+		atomic_inc(&vha->vha_tgt.qla_tgt->tgt_global_resets_count);
+		qlt_clear_tgt_db(vha->vha_tgt.qla_tgt);
+#if 0 /* FIXME: do we need to choose a session here? */
 		if (!list_empty(&ha->tgt.qla_tgt->sess_list)) {
 			sess = list_entry(ha->tgt.qla_tgt->sess_list.next,
 			    typeof(*sess), sess_list_entry);
@@ -489,27 +563,38 @@
 	struct qla_tgt *tgt = sess->tgt;
 	uint32_t dev_loss_tmo = tgt->ha->port_down_retry_count + 5;
 
-	if (sess->deleted)
-		return;
+	if (sess->deleted) {
+		/* Upgrade to unconditional deletion in case it was temporary */
+		if (immediate && sess->deleted == QLA_SESS_DELETION_PENDING)
+			list_del(&sess->del_list_entry);
+		else
+			return;
+	}
 
 	ql_dbg(ql_dbg_tgt, sess->vha, 0xe001,
 	    "Scheduling sess %p for deletion\n", sess);
-	list_add_tail(&sess->del_list_entry, &tgt->del_sess_list);
-	sess->deleted = 1;
 
-	if (immediate)
+	if (immediate) {
 		dev_loss_tmo = 0;
+		sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
+		list_add(&sess->del_list_entry, &tgt->del_sess_list);
+	} else {
+		sess->deleted = QLA_SESS_DELETION_PENDING;
+		list_add_tail(&sess->del_list_entry, &tgt->del_sess_list);
+	}
 
 	sess->expires = jiffies + dev_loss_tmo * HZ;
 
 	ql_dbg(ql_dbg_tgt, sess->vha, 0xe048,
-	    "qla_target(%d): session for port %8phC (loop ID %d) scheduled for "
-	    "deletion in %u secs (expires: %lu) immed: %d\n",
-	    sess->vha->vp_idx, sess->port_name, sess->loop_id, dev_loss_tmo,
-	    sess->expires, immediate);
+	    "qla_target(%d): session for port %8phC (loop ID %d s_id %02x:%02x:%02x)"
+	    " scheduled for deletion in %u secs (expires: %lu) immed: %d, logout: %d, gen: %#x\n",
+	    sess->vha->vp_idx, sess->port_name, sess->loop_id,
+	    sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa,
+	    dev_loss_tmo, sess->expires, immediate, sess->logout_on_delete,
+	    sess->generation);
 
 	if (immediate)
-		schedule_delayed_work(&tgt->sess_del_work, 0);
+		mod_delayed_work(system_wq, &tgt->sess_del_work, 0);
 	else
 		schedule_delayed_work(&tgt->sess_del_work,
 		    sess->expires - jiffies);
@@ -578,9 +663,9 @@
 /* ha->hardware_lock supposed to be held on entry */
 static void qlt_undelete_sess(struct qla_tgt_sess *sess)
 {
-	BUG_ON(!sess->deleted);
+	BUG_ON(sess->deleted != QLA_SESS_DELETION_PENDING);
 
-	list_del(&sess->del_list_entry);
+	list_del_init(&sess->del_list_entry);
 	sess->deleted = 0;
 }
 
@@ -599,7 +684,9 @@
 		    del_list_entry);
 		elapsed = jiffies;
 		if (time_after_eq(elapsed, sess->expires)) {
-			qlt_undelete_sess(sess);
+			/* No turning back */
+			list_del_init(&sess->del_list_entry);
+			sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
 
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf004,
 			    "Timeout: sess %p about to be deleted\n",
@@ -643,6 +730,13 @@
 			    fcport->d_id.b.al_pa, fcport->d_id.b.area,
 			    fcport->loop_id);
 
+			/* Cannot undelete at this point */
+			if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+				spin_unlock_irqrestore(&ha->hardware_lock,
+				    flags);
+				return NULL;
+			}
+
 			if (sess->deleted)
 				qlt_undelete_sess(sess);
 
@@ -652,6 +746,9 @@
 
 			if (sess->local && !local)
 				sess->local = 0;
+
+			qlt_do_generation_tick(vha, &sess->generation);
+
 			spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 			return sess;
@@ -673,6 +770,14 @@
 	sess->s_id = fcport->d_id;
 	sess->loop_id = fcport->loop_id;
 	sess->local = local;
+	INIT_LIST_HEAD(&sess->del_list_entry);
+
+	/* Under normal circumstances we want to logout from firmware when
+	 * session eventually ends and release corresponding nport handle.
+	 * In the exception cases (e.g. when new PLOGI is waiting) corresponding
+	 * code will adjust these flags as necessary. */
+	sess->logout_on_delete = 1;
+	sess->keep_nport_handle = 0;
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf006,
 	    "Adding sess %p to tgt %p via ->check_initiator_node_acl()\n",
@@ -705,6 +810,7 @@
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	list_add_tail(&sess->sess_list_entry, &vha->vha_tgt.qla_tgt->sess_list);
 	vha->vha_tgt.qla_tgt->sess_count++;
+	qlt_do_generation_tick(vha, &sess->generation);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04b,
@@ -718,7 +824,7 @@
 }
 
 /*
- * Called from drivers/scsi/qla2xxx/qla_init.c:qla2x00_reg_remote_port()
+ * Called from qla2x00_reg_remote_port()
  */
 void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport)
 {
@@ -750,6 +856,10 @@
 		mutex_unlock(&vha->vha_tgt.tgt_mutex);
 
 		spin_lock_irqsave(&ha->hardware_lock, flags);
+	} else if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+		/* Point of no return */
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+		return;
 	} else {
 		kref_get(&sess->se_sess->sess_kref);
 
@@ -780,27 +890,36 @@
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 }
 
-void qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport)
+/*
+ * max_gen - specifies maximum session generation
+ * at which this deletion requestion is still valid
+ */
+void
+qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport, int max_gen)
 {
-	struct qla_hw_data *ha = vha->hw;
 	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 	struct qla_tgt_sess *sess;
-	unsigned long flags;
 
 	if (!vha->hw->tgt.tgt_ops)
 		return;
 
-	if (!tgt || (fcport->port_type != FCT_INITIATOR))
+	if (!tgt)
 		return;
 
-	spin_lock_irqsave(&ha->hardware_lock, flags);
 	if (tgt->tgt_stop) {
-		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		return;
 	}
 	sess = qlt_find_sess_by_port_name(tgt, fcport->port_name);
 	if (!sess) {
-		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+		return;
+	}
+
+	if (max_gen - sess->generation < 0) {
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf092,
+		    "Ignoring stale deletion request for se_sess %p / sess %p"
+		    " for port %8phC, req_gen %d, sess_gen %d\n",
+		    sess->se_sess, sess, sess->port_name, max_gen,
+		    sess->generation);
 		return;
 	}
 
@@ -808,7 +927,6 @@
 
 	sess->local = 1;
 	qlt_schedule_sess_for_deletion(sess, false);
-	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 }
 
 static inline int test_tgt_sess_count(struct qla_tgt *tgt)
@@ -1175,6 +1293,70 @@
 	    FCP_TMF_CMPL, true);
 }
 
+static int abort_cmd_for_tag(struct scsi_qla_host *vha, uint32_t tag)
+{
+	struct qla_tgt_sess_op *op;
+	struct qla_tgt_cmd *cmd;
+
+	spin_lock(&vha->cmd_list_lock);
+
+	list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) {
+		if (tag == op->atio.u.isp24.exchange_addr) {
+			op->aborted = true;
+			spin_unlock(&vha->cmd_list_lock);
+			return 1;
+		}
+	}
+
+	list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) {
+		if (tag == cmd->atio.u.isp24.exchange_addr) {
+			cmd->state = QLA_TGT_STATE_ABORTED;
+			spin_unlock(&vha->cmd_list_lock);
+			return 1;
+		}
+	}
+
+	spin_unlock(&vha->cmd_list_lock);
+	return 0;
+}
+
+/* drop cmds for the given lun
+ * XXX only looks for cmds on the port through which lun reset was recieved
+ * XXX does not go through the list of other port (which may have cmds
+ *     for the same lun)
+ */
+static void abort_cmds_for_lun(struct scsi_qla_host *vha,
+				uint32_t lun, uint8_t *s_id)
+{
+	struct qla_tgt_sess_op *op;
+	struct qla_tgt_cmd *cmd;
+	uint32_t key;
+
+	key = sid_to_key(s_id);
+	spin_lock(&vha->cmd_list_lock);
+	list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) {
+		uint32_t op_key;
+		uint32_t op_lun;
+
+		op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id);
+		op_lun = scsilun_to_int(
+			(struct scsi_lun *)&op->atio.u.isp24.fcp_cmnd.lun);
+		if (op_key == key && op_lun == lun)
+			op->aborted = true;
+	}
+	list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) {
+		uint32_t cmd_key;
+		uint32_t cmd_lun;
+
+		cmd_key = sid_to_key(cmd->atio.u.isp24.fcp_hdr.s_id);
+		cmd_lun = scsilun_to_int(
+			(struct scsi_lun *)&cmd->atio.u.isp24.fcp_cmnd.lun);
+		if (cmd_key == key && cmd_lun == lun)
+			cmd->state = QLA_TGT_STATE_ABORTED;
+	}
+	spin_unlock(&vha->cmd_list_lock);
+}
+
 /* ha->hardware_lock supposed to be held on entry */
 static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha,
 	struct abts_recv_from_24xx *abts, struct qla_tgt_sess *sess)
@@ -1199,8 +1381,19 @@
 	}
 	spin_unlock(&se_sess->sess_cmd_lock);
 
-	if (!found_lun)
-		return -ENOENT;
+	/* cmd not in LIO lists, look in qla list */
+	if (!found_lun) {
+		if (abort_cmd_for_tag(vha, abts->exchange_addr_to_abort)) {
+			/* send TASK_ABORT response immediately */
+			qlt_24xx_send_abts_resp(vha, abts, FCP_TMF_CMPL, false);
+			return 0;
+		} else {
+			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf081,
+			    "unable to find cmd in driver or LIO for tag 0x%x\n",
+			    abts->exchange_addr_to_abort);
+			return -ENOENT;
+		}
+	}
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf00f,
 	    "qla_target(%d): task abort (tag=%d)\n",
@@ -1284,6 +1477,11 @@
 		return;
 	}
 
+	if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+		qlt_24xx_send_abts_resp(vha, abts, FCP_TMF_REJECTED, false);
+		return;
+	}
+
 	rc = __qlt_24xx_handle_abts(vha, abts, sess);
 	if (rc != 0) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf054,
@@ -1726,20 +1924,6 @@
 	struct qla_hw_data *ha = vha->hw;
 	struct se_cmd *se_cmd = &cmd->se_cmd;
 
-	if (unlikely(cmd->aborted)) {
-		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf014,
-		       "qla_target(%d): terminating exchange for aborted cmd=%p (se_cmd=%p, tag=%lld)",
-		       vha->vp_idx, cmd, se_cmd, se_cmd->tag);
-
-		cmd->state = QLA_TGT_STATE_ABORTED;
-		cmd->cmd_flags |= BIT_6;
-
-		qlt_send_term_exchange(vha, cmd, &cmd->atio, 0);
-
-		/* !! At this point cmd could be already freed !! */
-		return QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED;
-	}
-
 	prm->cmd = cmd;
 	prm->tgt = tgt;
 	prm->rq_result = scsi_status;
@@ -2301,6 +2485,19 @@
 	unsigned long flags = 0;
 	int res;
 
+	spin_lock_irqsave(&ha->hardware_lock, flags);
+	if (cmd->sess && cmd->sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+		cmd->state = QLA_TGT_STATE_PROCESSED;
+		if (cmd->sess->logout_completed)
+			/* no need to terminate. FW already freed exchange. */
+			qlt_abort_cmd_on_host_reset(cmd->vha, cmd);
+		else
+			qlt_send_term_exchange(vha, cmd, &cmd->atio, 1);
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+		return 0;
+	}
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
 	memset(&prm, 0, sizeof(prm));
 	qlt_check_srr_debug(cmd, &xmit_type);
 
@@ -2313,9 +2510,6 @@
 	res = qlt_pre_xmit_response(cmd, &prm, xmit_type, scsi_status,
 	    &full_req_cnt);
 	if (unlikely(res != 0)) {
-		if (res == QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED)
-			return 0;
-
 		return res;
 	}
 
@@ -2345,9 +2539,10 @@
 		res = qlt_build_ctio_crc2_pkt(&prm, vha);
 	else
 		res = qlt_24xx_build_ctio_pkt(&prm, vha);
-	if (unlikely(res != 0))
+	if (unlikely(res != 0)) {
+		vha->req->cnt += full_req_cnt;
 		goto out_unmap_unlock;
-
+	}
 
 	pkt = (struct ctio7_to_24xx *)prm.pkt;
 
@@ -2461,7 +2656,8 @@
 
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 
-	if (qla2x00_reset_active(vha) || cmd->reset_count != ha->chip_reset) {
+	if (qla2x00_reset_active(vha) || (cmd->reset_count != ha->chip_reset) ||
+	    (cmd->sess && cmd->sess->deleted == QLA_SESS_DELETION_IN_PROGRESS)) {
 		/*
 		 * Either a chip reset is active or this request was from
 		 * previous life, just abort the processing.
@@ -2485,8 +2681,11 @@
 	else
 		res = qlt_24xx_build_ctio_pkt(&prm, vha);
 
-	if (unlikely(res != 0))
+	if (unlikely(res != 0)) {
+		vha->req->cnt += prm.req_cnt;
 		goto out_unlock_free_unmap;
+	}
+
 	pkt = (struct ctio7_to_24xx *)prm.pkt;
 	pkt->u.status0.flags |= __constant_cpu_to_le16(CTIO7_FLAGS_DATA_OUT |
 	    CTIO7_FLAGS_STATUS_MODE_0);
@@ -2651,6 +2850,89 @@
 
 /* If hardware_lock held on entry, might drop it, then reaquire */
 /* This function sends the appropriate CTIO to ISP 2xxx or 24xx */
+static int __qlt_send_term_imm_notif(struct scsi_qla_host *vha,
+	struct imm_ntfy_from_isp *ntfy)
+{
+	struct nack_to_isp *nack;
+	struct qla_hw_data *ha = vha->hw;
+	request_t *pkt;
+	int ret = 0;
+
+	ql_dbg(ql_dbg_tgt_tmr, vha, 0xe01c,
+	    "Sending TERM ELS CTIO (ha=%p)\n", ha);
+
+	pkt = (request_t *)qla2x00_alloc_iocbs_ready(vha, NULL);
+	if (pkt == NULL) {
+		ql_dbg(ql_dbg_tgt, vha, 0xe080,
+		    "qla_target(%d): %s failed: unable to allocate "
+		    "request packet\n", vha->vp_idx, __func__);
+		return -ENOMEM;
+	}
+
+	pkt->entry_type = NOTIFY_ACK_TYPE;
+	pkt->entry_count = 1;
+	pkt->handle = QLA_TGT_SKIP_HANDLE | CTIO_COMPLETION_HANDLE_MARK;
+
+	nack = (struct nack_to_isp *)pkt;
+	nack->ox_id = ntfy->ox_id;
+
+	nack->u.isp24.nport_handle = ntfy->u.isp24.nport_handle;
+	if (le16_to_cpu(ntfy->u.isp24.status) == IMM_NTFY_ELS) {
+		nack->u.isp24.flags = ntfy->u.isp24.flags &
+			__constant_cpu_to_le32(NOTIFY24XX_FLAGS_PUREX_IOCB);
+	}
+
+	/* terminate */
+	nack->u.isp24.flags |=
+		__constant_cpu_to_le16(NOTIFY_ACK_FLAGS_TERMINATE);
+
+	nack->u.isp24.srr_rx_id = ntfy->u.isp24.srr_rx_id;
+	nack->u.isp24.status = ntfy->u.isp24.status;
+	nack->u.isp24.status_subcode = ntfy->u.isp24.status_subcode;
+	nack->u.isp24.fw_handle = ntfy->u.isp24.fw_handle;
+	nack->u.isp24.exchange_address = ntfy->u.isp24.exchange_address;
+	nack->u.isp24.srr_rel_offs = ntfy->u.isp24.srr_rel_offs;
+	nack->u.isp24.srr_ui = ntfy->u.isp24.srr_ui;
+	nack->u.isp24.vp_index = ntfy->u.isp24.vp_index;
+
+	qla2x00_start_iocbs(vha, vha->req);
+	return ret;
+}
+
+static void qlt_send_term_imm_notif(struct scsi_qla_host *vha,
+	struct imm_ntfy_from_isp *imm, int ha_locked)
+{
+	unsigned long flags = 0;
+	int rc;
+
+	if (qlt_issue_marker(vha, ha_locked) < 0)
+		return;
+
+	if (ha_locked) {
+		rc = __qlt_send_term_imm_notif(vha, imm);
+
+#if 0	/* Todo  */
+		if (rc == -ENOMEM)
+			qlt_alloc_qfull_cmd(vha, imm, 0, 0);
+#endif
+		goto done;
+	}
+
+	spin_lock_irqsave(&vha->hw->hardware_lock, flags);
+	rc = __qlt_send_term_imm_notif(vha, imm);
+
+#if 0	/* Todo */
+	if (rc == -ENOMEM)
+		qlt_alloc_qfull_cmd(vha, imm, 0, 0);
+#endif
+
+done:
+	if (!ha_locked)
+		spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
+}
+
+/* If hardware_lock held on entry, might drop it, then reaquire */
+/* This function sends the appropriate CTIO to ISP 2xxx or 24xx */
 static int __qlt_send_term_exchange(struct scsi_qla_host *vha,
 	struct qla_tgt_cmd *cmd,
 	struct atio_from_isp *atio)
@@ -2715,7 +2997,7 @@
 static void qlt_send_term_exchange(struct scsi_qla_host *vha,
 	struct qla_tgt_cmd *cmd, struct atio_from_isp *atio, int ha_locked)
 {
-	unsigned long flags;
+	unsigned long flags = 0;
 	int rc;
 
 	if (qlt_issue_marker(vha, ha_locked) < 0)
@@ -2731,17 +3013,18 @@
 	rc = __qlt_send_term_exchange(vha, cmd, atio);
 	if (rc == -ENOMEM)
 		qlt_alloc_qfull_cmd(vha, atio, 0, 0);
-	spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
 
 done:
 	if (cmd && ((cmd->state != QLA_TGT_STATE_ABORTED) ||
 	    !cmd->cmd_sent_to_fw)) {
-		if (!ha_locked && !in_interrupt())
-			msleep(250); /* just in case */
-
-		qlt_unmap_sg(vha, cmd);
+		if (cmd->sg_mapped)
+			qlt_unmap_sg(vha, cmd);
 		vha->hw->tgt.tgt_ops->free_cmd(cmd);
 	}
+
+	if (!ha_locked)
+		spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
+
 	return;
 }
 
@@ -2792,6 +3075,24 @@
 
 }
 
+void qlt_abort_cmd(struct qla_tgt_cmd *cmd)
+{
+	struct qla_tgt *tgt = cmd->tgt;
+	struct scsi_qla_host *vha = tgt->vha;
+	struct se_cmd *se_cmd = &cmd->se_cmd;
+
+	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf014,
+	    "qla_target(%d): terminating exchange for aborted cmd=%p "
+	    "(se_cmd=%p, tag=%llu)", vha->vp_idx, cmd, &cmd->se_cmd,
+	    se_cmd->tag);
+
+	cmd->state = QLA_TGT_STATE_ABORTED;
+	cmd->cmd_flags |= BIT_6;
+
+	qlt_send_term_exchange(vha, cmd, &cmd->atio, 0);
+}
+EXPORT_SYMBOL(qlt_abort_cmd);
+
 void qlt_free_cmd(struct qla_tgt_cmd *cmd)
 {
 	struct qla_tgt_sess *sess = cmd->sess;
@@ -3015,7 +3316,7 @@
 		dump_stack();
 	}
 
-	cmd->cmd_flags |= BIT_12;
+	cmd->cmd_flags |= BIT_17;
 	ha->tgt.tgt_ops->free_cmd(cmd);
 }
 
@@ -3177,7 +3478,7 @@
 skip_term:
 
 	if (cmd->state == QLA_TGT_STATE_PROCESSED) {
-		;
+		cmd->cmd_flags |= BIT_12;
 	} else if (cmd->state == QLA_TGT_STATE_NEED_DATA) {
 		int rx_status = 0;
 
@@ -3191,9 +3492,11 @@
 		ha->tgt.tgt_ops->handle_data(cmd);
 		return;
 	} else if (cmd->state == QLA_TGT_STATE_ABORTED) {
+		cmd->cmd_flags |= BIT_18;
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf01e,
 		  "Aborted command %p (tag %lld) finished\n", cmd, se_cmd->tag);
 	} else {
+		cmd->cmd_flags |= BIT_19;
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05c,
 		    "qla_target(%d): A command in state (%d) should "
 		    "not return a CTIO complete\n", vha->vp_idx, cmd->state);
@@ -3205,7 +3508,6 @@
 		dump_stack();
 	}
 
-
 	ha->tgt.tgt_ops->free_cmd(cmd);
 }
 
@@ -3263,6 +3565,13 @@
 	if (tgt->tgt_stop)
 		goto out_term;
 
+	if (cmd->state == QLA_TGT_STATE_ABORTED) {
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf082,
+		    "cmd with tag %u is aborted\n",
+		    cmd->atio.u.isp24.exchange_addr);
+		goto out_term;
+	}
+
 	cdb = &atio->u.isp24.fcp_cmnd.cdb[0];
 	cmd->se_cmd.tag = atio->u.isp24.exchange_addr;
 	cmd->unpacked_lun = scsilun_to_int(
@@ -3316,6 +3625,12 @@
 static void qlt_do_work(struct work_struct *work)
 {
 	struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work);
+	scsi_qla_host_t *vha = cmd->vha;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vha->cmd_list_lock, flags);
+	list_del(&cmd->cmd_list);
+	spin_unlock_irqrestore(&vha->cmd_list_lock, flags);
 
 	__qlt_do_work(cmd);
 }
@@ -3345,6 +3660,11 @@
 	cmd->loop_id = sess->loop_id;
 	cmd->conf_compl_supported = sess->conf_compl_supported;
 
+	cmd->cmd_flags = 0;
+	cmd->jiffies_at_alloc = get_jiffies_64();
+
+	cmd->reset_count = vha->hw->chip_reset;
+
 	return cmd;
 }
 
@@ -3362,14 +3682,25 @@
 	unsigned long flags;
 	uint8_t *s_id = op->atio.u.isp24.fcp_hdr.s_id;
 
+	spin_lock_irqsave(&vha->cmd_list_lock, flags);
+	list_del(&op->cmd_list);
+	spin_unlock_irqrestore(&vha->cmd_list_lock, flags);
+
+	if (op->aborted) {
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf083,
+		    "sess_op with tag %u is aborted\n",
+		    op->atio.u.isp24.exchange_addr);
+		goto out_term;
+	}
+
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf022,
-		"qla_target(%d): Unable to find wwn login"
-		" (s_id %x:%x:%x), trying to create it manually\n",
-		vha->vp_idx, s_id[0], s_id[1], s_id[2]);
+	    "qla_target(%d): Unable to find wwn login"
+	    " (s_id %x:%x:%x), trying to create it manually\n",
+	    vha->vp_idx, s_id[0], s_id[1], s_id[2]);
 
 	if (op->atio.u.raw.entry_count > 1) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf023,
-		        "Dropping multy entry atio %p\n", &op->atio);
+		    "Dropping multy entry atio %p\n", &op->atio);
 		goto out_term;
 	}
 
@@ -3434,10 +3765,25 @@
 
 		memcpy(&op->atio, atio, sizeof(*atio));
 		op->vha = vha;
+
+		spin_lock(&vha->cmd_list_lock);
+		list_add_tail(&op->cmd_list, &vha->qla_sess_op_cmd_list);
+		spin_unlock(&vha->cmd_list_lock);
+
 		INIT_WORK(&op->work, qlt_create_sess_from_atio);
 		queue_work(qla_tgt_wq, &op->work);
 		return 0;
 	}
+
+	/* Another WWN used to have our s_id. Our PLOGI scheduled its
+	 * session deletion, but it's still in sess_del_work wq */
+	if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+		ql_dbg(ql_dbg_io, vha, 0x3061,
+		    "New command while old session %p is being deleted\n",
+		    sess);
+		return -EFAULT;
+	}
+
 	/*
 	 * Do kref_get() before returning + dropping qla_hw_data->hardware_lock.
 	 */
@@ -3451,13 +3797,13 @@
 		return -ENOMEM;
 	}
 
-	cmd->cmd_flags = 0;
-	cmd->jiffies_at_alloc = get_jiffies_64();
-
-	cmd->reset_count = vha->hw->chip_reset;
-
 	cmd->cmd_in_wq = 1;
 	cmd->cmd_flags |= BIT_0;
+
+	spin_lock(&vha->cmd_list_lock);
+	list_add_tail(&cmd->cmd_list, &vha->qla_cmd_list);
+	spin_unlock(&vha->cmd_list_lock);
+
 	INIT_WORK(&cmd->work, qlt_do_work);
 	queue_work(qla_tgt_wq, &cmd->work);
 	return 0;
@@ -3471,6 +3817,7 @@
 	struct scsi_qla_host *vha = sess->vha;
 	struct qla_hw_data *ha = vha->hw;
 	struct qla_tgt_mgmt_cmd *mcmd;
+	struct atio_from_isp *a = (struct atio_from_isp *)iocb;
 	int res;
 	uint8_t tmr_func;
 
@@ -3511,6 +3858,7 @@
 		ql_dbg(ql_dbg_tgt_tmr, vha, 0x10002,
 		    "qla_target(%d): LUN_RESET received\n", sess->vha->vp_idx);
 		tmr_func = TMR_LUN_RESET;
+		abort_cmds_for_lun(vha, lun, a->u.isp24.fcp_hdr.s_id);
 		break;
 
 	case QLA_TGT_CLEAR_TS:
@@ -3599,6 +3947,9 @@
 		    sizeof(struct atio_from_isp));
 	}
 
+	if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS)
+		return -EFAULT;
+
 	return qlt_issue_task_mgmt(sess, unpacked_lun, fn, iocb, 0);
 }
 
@@ -3664,22 +4015,280 @@
 	return __qlt_abort_task(vha, iocb, sess);
 }
 
+void qlt_logo_completion_handler(fc_port_t *fcport, int rc)
+{
+	if (fcport->tgt_session) {
+		if (rc != MBS_COMMAND_COMPLETE) {
+			ql_dbg(ql_dbg_tgt_mgt, fcport->vha, 0xf093,
+				"%s: se_sess %p / sess %p from"
+				" port %8phC loop_id %#04x s_id %02x:%02x:%02x"
+				" LOGO failed: %#x\n",
+				__func__,
+				fcport->tgt_session->se_sess,
+				fcport->tgt_session,
+				fcport->port_name, fcport->loop_id,
+				fcport->d_id.b.domain, fcport->d_id.b.area,
+				fcport->d_id.b.al_pa, rc);
+		}
+
+		fcport->tgt_session->logout_completed = 1;
+	}
+}
+
+static void qlt_swap_imm_ntfy_iocb(struct imm_ntfy_from_isp *a,
+    struct imm_ntfy_from_isp *b)
+{
+	struct imm_ntfy_from_isp tmp;
+	memcpy(&tmp, a, sizeof(struct imm_ntfy_from_isp));
+	memcpy(a, b, sizeof(struct imm_ntfy_from_isp));
+	memcpy(b, &tmp, sizeof(struct imm_ntfy_from_isp));
+}
+
+/*
+* ha->hardware_lock supposed to be held on entry (to protect tgt->sess_list)
+*
+* Schedules sessions with matching port_id/loop_id but different wwn for
+* deletion. Returns existing session with matching wwn if present.
+* Null otherwise.
+*/
+static struct qla_tgt_sess *
+qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn,
+    port_id_t port_id, uint16_t loop_id)
+{
+	struct qla_tgt_sess *sess = NULL, *other_sess;
+	uint64_t other_wwn;
+
+	list_for_each_entry(other_sess, &tgt->sess_list, sess_list_entry) {
+
+		other_wwn = wwn_to_u64(other_sess->port_name);
+
+		if (wwn == other_wwn) {
+			WARN_ON(sess);
+			sess = other_sess;
+			continue;
+		}
+
+		/* find other sess with nport_id collision */
+		if (port_id.b24 == other_sess->s_id.b24) {
+			if (loop_id != other_sess->loop_id) {
+				ql_dbg(ql_dbg_tgt_tmr, tgt->vha, 0x1000c,
+				    "Invalidating sess %p loop_id %d wwn %llx.\n",
+				    other_sess, other_sess->loop_id, other_wwn);
+
+				/*
+				 * logout_on_delete is set by default, but another
+				 * session that has the same s_id/loop_id combo
+				 * might have cleared it when requested this session
+				 * deletion, so don't touch it
+				 */
+				qlt_schedule_sess_for_deletion(other_sess, true);
+			} else {
+				/*
+				 * Another wwn used to have our s_id/loop_id
+				 * combo - kill the session, but don't log out
+				 */
+				sess->logout_on_delete = 0;
+				qlt_schedule_sess_for_deletion(other_sess,
+				    true);
+			}
+			continue;
+		}
+
+		/* find other sess with nport handle collision */
+		if (loop_id == other_sess->loop_id) {
+			ql_dbg(ql_dbg_tgt_tmr, tgt->vha, 0x1000d,
+			       "Invalidating sess %p loop_id %d wwn %llx.\n",
+			       other_sess, other_sess->loop_id, other_wwn);
+
+			/* Same loop_id but different s_id
+			 * Ok to kill and logout */
+			qlt_schedule_sess_for_deletion(other_sess, true);
+		}
+	}
+
+	return sess;
+}
+
+/* Abort any commands for this s_id waiting on qla_tgt_wq workqueue */
+static int abort_cmds_for_s_id(struct scsi_qla_host *vha, port_id_t *s_id)
+{
+	struct qla_tgt_sess_op *op;
+	struct qla_tgt_cmd *cmd;
+	uint32_t key;
+	int count = 0;
+
+	key = (((u32)s_id->b.domain << 16) |
+	       ((u32)s_id->b.area   <<  8) |
+	       ((u32)s_id->b.al_pa));
+
+	spin_lock(&vha->cmd_list_lock);
+	list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) {
+		uint32_t op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id);
+		if (op_key == key) {
+			op->aborted = true;
+			count++;
+		}
+	}
+	list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) {
+		uint32_t cmd_key = sid_to_key(cmd->atio.u.isp24.fcp_hdr.s_id);
+		if (cmd_key == key) {
+			cmd->state = QLA_TGT_STATE_ABORTED;
+			count++;
+		}
+	}
+	spin_unlock(&vha->cmd_list_lock);
+
+	return count;
+}
+
 /*
  * ha->hardware_lock supposed to be held on entry. Might drop it, then reaquire
  */
 static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 	struct imm_ntfy_from_isp *iocb)
 {
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
+	struct qla_hw_data *ha = vha->hw;
+	struct qla_tgt_sess *sess = NULL;
+	uint64_t wwn;
+	port_id_t port_id;
+	uint16_t loop_id;
+	uint16_t wd3_lo;
 	int res = 0;
 
+	wwn = wwn_to_u64(iocb->u.isp24.port_name);
+
+	port_id.b.domain = iocb->u.isp24.port_id[2];
+	port_id.b.area   = iocb->u.isp24.port_id[1];
+	port_id.b.al_pa  = iocb->u.isp24.port_id[0];
+	port_id.b.rsvd_1 = 0;
+
+	loop_id = le16_to_cpu(iocb->u.isp24.nport_handle);
+
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf026,
 	    "qla_target(%d): Port ID: 0x%3phC ELS opcode: 0x%02x\n",
 	    vha->vp_idx, iocb->u.isp24.port_id, iocb->u.isp24.status_subcode);
 
+	/* res = 1 means ack at the end of thread
+	 * res = 0 means ack async/later.
+	 */
 	switch (iocb->u.isp24.status_subcode) {
 	case ELS_PLOGI:
-	case ELS_FLOGI:
+
+		/* Mark all stale commands in qla_tgt_wq for deletion */
+		abort_cmds_for_s_id(vha, &port_id);
+
+		if (wwn)
+			sess = qlt_find_sess_invalidate_other(tgt, wwn,
+			    port_id, loop_id);
+
+		if (!sess || IS_SW_RESV_ADDR(sess->s_id)) {
+			res = 1;
+			break;
+		}
+
+		if (sess->plogi_ack_needed) {
+			/*
+			 * Initiator sent another PLOGI before last PLOGI could
+			 * finish. Swap plogi iocbs and terminate old one
+			 * without acking, new one will get acked when session
+			 * deletion completes.
+			 */
+			ql_log(ql_log_warn, sess->vha, 0xf094,
+			    "sess %p received double plogi.\n", sess);
+
+			qlt_swap_imm_ntfy_iocb(iocb, &sess->tm_iocb);
+
+			qlt_send_term_imm_notif(vha, iocb, 1);
+
+			res = 0;
+			break;
+		}
+
+		res = 0;
+
+		/*
+		 * Save immediate Notif IOCB for Ack when sess is done
+		 * and being deleted.
+		 */
+		memcpy(&sess->tm_iocb, iocb, sizeof(sess->tm_iocb));
+		sess->plogi_ack_needed  = 1;
+
+		 /*
+		  * Under normal circumstances we want to release nport handle
+		  * during LOGO process to avoid nport handle leaks inside FW.
+		  * The exception is when LOGO is done while another PLOGI with
+		  * the same nport handle is waiting as might be the case here.
+		  * Note: there is always a possibily of a race where session
+		  * deletion has already started for other reasons (e.g. ACL
+		  * removal) and now PLOGI arrives:
+		  * 1. if PLOGI arrived in FW after nport handle has been freed,
+		  *    FW must have assigned this PLOGI a new/same handle and we
+		  *    can proceed ACK'ing it as usual when session deletion
+		  *    completes.
+		  * 2. if PLOGI arrived in FW before LOGO with LCF_FREE_NPORT
+		  *    bit reached it, the handle has now been released. We'll
+		  *    get an error when we ACK this PLOGI. Nothing will be sent
+		  *    back to initiator. Initiator should eventually retry
+		  *    PLOGI and situation will correct itself.
+		  */
+		sess->keep_nport_handle = ((sess->loop_id == loop_id) &&
+					   (sess->s_id.b24 == port_id.b24));
+		qlt_schedule_sess_for_deletion(sess, true);
+		break;
+
 	case ELS_PRLI:
+		wd3_lo = le16_to_cpu(iocb->u.isp24.u.prli.wd3_lo);
+
+		if (wwn)
+			sess = qlt_find_sess_invalidate_other(tgt, wwn, port_id,
+			    loop_id);
+
+		if (sess != NULL) {
+			if (sess->deleted) {
+				/*
+				 * Impatient initiator sent PRLI before last
+				 * PLOGI could finish. Will force him to re-try,
+				 * while last one finishes.
+				 */
+				ql_log(ql_log_warn, sess->vha, 0xf095,
+				    "sess %p PRLI received, before plogi ack.\n",
+				    sess);
+				qlt_send_term_imm_notif(vha, iocb, 1);
+				res = 0;
+				break;
+			}
+
+			/*
+			 * This shouldn't happen under normal circumstances,
+			 * since we have deleted the old session during PLOGI
+			 */
+			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf096,
+			    "PRLI (loop_id %#04x) for existing sess %p (loop_id %#04x)\n",
+			    sess->loop_id, sess, iocb->u.isp24.nport_handle);
+
+			sess->local = 0;
+			sess->loop_id = loop_id;
+			sess->s_id = port_id;
+
+			if (wd3_lo & BIT_7)
+				sess->conf_compl_supported = 1;
+
+		}
+		res = 1; /* send notify ack */
+
+		/* Make session global (not used in fabric mode) */
+		if (ha->current_topology != ISP_CFG_F) {
+			set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
+			set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
+			qla2xxx_wake_dpc(vha);
+		} else {
+			/* todo: else - create sess here. */
+			res = 1; /* send notify ack */
+		}
+
+		break;
+
 	case ELS_LOGO:
 	case ELS_PRLO:
 		res = qlt_reset(vha, iocb, QLA_TGT_NEXUS_LOSS_SESS);
@@ -3697,6 +4306,7 @@
 		break;
 	}
 
+	case ELS_FLOGI:	/* should never happen */
 	default:
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf061,
 		    "qla_target(%d): Unsupported ELS command %x "
@@ -5012,6 +5622,11 @@
 		if (!sess)
 			goto out_term;
 	} else {
+		if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+			sess = NULL;
+			goto out_term;
+		}
+
 		kref_get(&sess->se_sess->sess_kref);
 	}
 
@@ -5066,6 +5681,11 @@
 		if (!sess)
 			goto out_term;
 	} else {
+		if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+			sess = NULL;
+			goto out_term;
+		}
+
 		kref_get(&sess->se_sess->sess_kref);
 	}
 
@@ -5552,6 +6172,7 @@
 
 	/* Adjust ring index */
 	WRT_REG_DWORD(ISP_ATIO_Q_OUT(vha), ha->tgt.atio_ring_index);
+	RD_REG_DWORD_RELAXED(ISP_ATIO_Q_OUT(vha));
 }
 
 void
@@ -5793,7 +6414,7 @@
 	if (!QLA_TGT_MODE_ENABLED())
 		return;
 
-	if  (ha->mqenable || IS_QLA83XX(ha)) {
+	if  (ha->mqenable || IS_QLA83XX(ha) || IS_QLA27XX(ha)) {
 		ISP_ATIO_Q_IN(base_vha) = &ha->mqiobase->isp25mq.atio_q_in;
 		ISP_ATIO_Q_OUT(base_vha) = &ha->mqiobase->isp25mq.atio_q_out;
 	} else {
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 985d76d..bca584a 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -167,7 +167,24 @@
 			uint32_t srr_rel_offs;
 			uint16_t srr_ui;
 			uint16_t srr_ox_id;
-			uint8_t  reserved_4[19];
+			union {
+				struct {
+					uint8_t node_name[8];
+				} plogi; /* PLOGI/ADISC/PDISC */
+				struct {
+					/* PRLI word 3 bit 0-15 */
+					uint16_t wd3_lo;
+					uint8_t resv0[6];
+				} prli;
+				struct {
+					uint8_t port_id[3];
+					uint8_t resv1;
+					uint16_t nport_handle;
+					uint16_t resv2;
+				} req_els;
+			} u;
+			uint8_t port_name[8];
+			uint8_t resv3[3];
 			uint8_t  vp_index;
 			uint32_t reserved_5;
 			uint8_t  port_id[3];
@@ -234,6 +251,7 @@
 	uint8_t  reserved[2];
 	uint16_t ox_id;
 } __packed;
+#define NOTIFY_ACK_FLAGS_TERMINATE	BIT_3
 #define NOTIFY_ACK_SRR_FLAGS_ACCEPT	0
 #define NOTIFY_ACK_SRR_FLAGS_REJECT	1
 
@@ -790,13 +808,6 @@
 #define	FC_TM_REJECT                4
 #define FC_TM_FAILED                5
 
-/*
- * Error code of qlt_pre_xmit_response() meaning that cmd's exchange was
- * terminated, so no more actions is needed and success should be returned
- * to target.
- */
-#define QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED	0x1717
-
 #if (BITS_PER_LONG > 32) || defined(CONFIG_HIGHMEM64G)
 #define pci_dma_lo32(a) (a & 0xffffffff)
 #define pci_dma_hi32(a) ((((a) >> 16)>>16) & 0xffffffff)
@@ -874,6 +885,15 @@
 	struct scsi_qla_host *vha;
 	struct atio_from_isp atio;
 	struct work_struct work;
+	struct list_head cmd_list;
+	bool aborted;
+};
+
+enum qla_sess_deletion {
+	QLA_SESS_DELETION_NONE		= 0,
+	QLA_SESS_DELETION_PENDING	= 1, /* hopefully we can get rid of
+					      * this one */
+	QLA_SESS_DELETION_IN_PROGRESS	= 2,
 };
 
 /*
@@ -884,8 +904,15 @@
 	port_id_t s_id;
 
 	unsigned int conf_compl_supported:1;
-	unsigned int deleted:1;
+	unsigned int deleted:2;
 	unsigned int local:1;
+	unsigned int logout_on_delete:1;
+	unsigned int plogi_ack_needed:1;
+	unsigned int keep_nport_handle:1;
+
+	unsigned char logout_completed;
+
+	int generation;
 
 	struct se_session *se_sess;
 	struct scsi_qla_host *vha;
@@ -897,6 +924,10 @@
 
 	uint8_t port_name[WWN_SIZE];
 	struct work_struct free_work;
+
+	union {
+		struct imm_ntfy_from_isp tm_iocb;
+	};
 };
 
 struct qla_tgt_cmd {
@@ -912,7 +943,6 @@
 	unsigned int conf_compl_supported:1;
 	unsigned int sg_mapped:1;
 	unsigned int free_sg:1;
-	unsigned int aborted:1; /* Needed in case of SRR */
 	unsigned int write_data_transferred:1;
 	unsigned int ctx_dsd_alloced:1;
 	unsigned int q_full:1;
@@ -961,6 +991,9 @@
 	 * BIT_14 - Back end data received/sent.
 	 * BIT_15 - SRR prepare ctio
 	 * BIT_16 - complete free
+	 * BIT_17 - flush - qlt_abort_cmd_on_host_reset
+	 * BIT_18 - completion w/abort status
+	 * BIT_19 - completion w/unknown status
 	 */
 	uint32_t cmd_flags;
 };
@@ -1026,6 +1059,10 @@
 	struct qla_tgt_cmd *cmd;
 };
 
+/* Check for Switch reserved address */
+#define IS_SW_RESV_ADDR(_s_id) \
+	((_s_id.b.domain == 0xff) && (_s_id.b.area == 0xfc))
+
 #define QLA_TGT_XMIT_DATA		1
 #define QLA_TGT_XMIT_STATUS		2
 #define QLA_TGT_XMIT_ALL		(QLA_TGT_XMIT_STATUS|QLA_TGT_XMIT_DATA)
@@ -1043,7 +1080,7 @@
 extern void qlt_lport_deregister(struct scsi_qla_host *);
 extern void qlt_unreg_sess(struct qla_tgt_sess *);
 extern void qlt_fc_port_added(struct scsi_qla_host *, fc_port_t *);
-extern void qlt_fc_port_deleted(struct scsi_qla_host *, fc_port_t *);
+extern void qlt_fc_port_deleted(struct scsi_qla_host *, fc_port_t *, int);
 extern int __init qlt_init(void);
 extern void qlt_exit(void);
 extern void qlt_update_vp_map(struct scsi_qla_host *, int);
@@ -1073,12 +1110,23 @@
 		ha->host->active_mode |= MODE_INITIATOR;
 }
 
+static inline uint32_t sid_to_key(const uint8_t *s_id)
+{
+	uint32_t key;
+
+	key = (((unsigned long)s_id[0] << 16) |
+	       ((unsigned long)s_id[1] << 8) |
+	       (unsigned long)s_id[2]);
+	return key;
+}
+
 /*
  * Exported symbols from qla_target.c LLD logic used by qla2xxx code..
  */
 extern void qlt_response_pkt_all_vps(struct scsi_qla_host *, response_t *);
 extern int qlt_rdy_to_xfer(struct qla_tgt_cmd *);
 extern int qlt_xmit_response(struct qla_tgt_cmd *, int, uint8_t);
+extern void qlt_abort_cmd(struct qla_tgt_cmd *);
 extern void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_mcmd(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_cmd(struct qla_tgt_cmd *cmd);
@@ -1109,5 +1157,7 @@
 extern irqreturn_t qla83xx_msix_atio_q(int, void *);
 extern void qlt_83xx_iospace_config(struct qla_hw_data *);
 extern int qlt_free_qfull_cmds(struct scsi_qla_host *);
+extern void qlt_logo_completion_handler(fc_port_t *, int);
+extern void qlt_do_generation_tick(struct scsi_qla_host *, int *);
 
 #endif /* __QLA_TARGET_H */
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index d9a8c60..9224a06 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -374,7 +374,7 @@
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
-
+	cmd->cmd_flags |= BIT_3;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
 
@@ -405,7 +405,7 @@
 	    se_cmd->t_state == TRANSPORT_COMPLETE_QF_WP) {
 		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
 		wait_for_completion_timeout(&se_cmd->t_transport_stop_comp,
-						3000);
+					    3 * HZ);
 		return 0;
 	}
 	spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
@@ -541,12 +541,10 @@
 	cmd->cmd_flags |= BIT_4;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
-	cmd->aborted = (se_cmd->transport_state & CMD_T_ABORTED);
 
 	cmd->sg_cnt = se_cmd->t_data_nents;
 	cmd->sg = se_cmd->t_data_sg;
 	cmd->offset = 0;
-	cmd->cmd_flags |= BIT_3;
 
 	cmd->prot_sg_cnt = se_cmd->t_prot_nents;
 	cmd->prot_sg = se_cmd->t_prot_sg;
@@ -571,7 +569,6 @@
 	cmd->sg_cnt = 0;
 	cmd->offset = 0;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
-	cmd->aborted = (se_cmd->transport_state & CMD_T_ABORTED);
 	if (cmd->cmd_flags &  BIT_5) {
 		pr_crit("Bit_5 already set for cmd = %p.\n", cmd);
 		dump_stack();
@@ -636,14 +633,7 @@
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
-	struct scsi_qla_host *vha = cmd->vha;
-	struct qla_hw_data *ha = vha->hw;
-
-	if (!cmd->sg_mapped)
-		return;
-
-	pci_unmap_sg(ha->pdev, cmd->sg, cmd->sg_cnt, cmd->dma_data_direction);
-	cmd->sg_mapped = 0;
+	qlt_abort_cmd(cmd);
 }
 
 static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *,
@@ -1149,9 +1139,7 @@
 		return NULL;
 	}
 
-	key = (((unsigned long)s_id[0] << 16) |
-	       ((unsigned long)s_id[1] << 8) |
-	       (unsigned long)s_id[2]);
+	key = sid_to_key(s_id);
 	pr_debug("find_sess_by_s_id: 0x%06x\n", key);
 
 	se_nacl = btree_lookup32(&lport->lport_fcport_map, key);
@@ -1186,9 +1174,7 @@
 	void *slot;
 	int rc;
 
-	key = (((unsigned long)s_id[0] << 16) |
-	       ((unsigned long)s_id[1] << 8) |
-	       (unsigned long)s_id[2]);
+	key = sid_to_key(s_id);
 	pr_debug("set_sess_by_s_id: %06x\n", key);
 
 	slot = btree_lookup32(&lport->lport_fcport_map, key);
@@ -1544,6 +1530,10 @@
 	}
 
 	sess->conf_compl_supported = conf_compl_supported;
+
+	/* Reset logout parameters to default */
+	sess->logout_on_delete = 1;
+	sess->keep_nport_handle = 0;
 }
 
 /*
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 106884a..6457a8a 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -26,7 +26,6 @@
 #include <linux/blkdev.h>
 #include <linux/delay.h>
 #include <linux/jiffies.h>
-#include <asm/unaligned.h>
 
 #include <scsi/scsi.h>
 #include <scsi/scsi_cmnd.h>
@@ -944,7 +943,7 @@
 			    scmd->sdb.length);
 		scmd->sdb.table.sgl = &ses->sense_sgl;
 		scmd->sc_data_direction = DMA_FROM_DEVICE;
-		scmd->sdb.table.nents = 1;
+		scmd->sdb.table.nents = scmd->sdb.table.orig_nents = 1;
 		scmd->cmnd[0] = REQUEST_SENSE;
 		scmd->cmnd[4] = scmd->sdb.length;
 		scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]);
@@ -2523,33 +2522,3 @@
 	}
 }
 EXPORT_SYMBOL(scsi_build_sense_buffer);
-
-/**
- * scsi_set_sense_information - set the information field in a
- *		formatted sense data buffer
- * @buf:	Where to build sense data
- * @info:	64-bit information value to be set
- *
- **/
-void scsi_set_sense_information(u8 *buf, u64 info)
-{
-	if ((buf[0] & 0x7f) == 0x72) {
-		u8 *ucp, len;
-
-		len = buf[7];
-		ucp = (char *)scsi_sense_desc_find(buf, len + 8, 0);
-		if (!ucp) {
-			buf[7] = len + 0xa;
-			ucp = buf + 8 + len;
-		}
-		ucp[0] = 0;
-		ucp[1] = 0xa;
-		ucp[2] = 0x80; /* Valid bit */
-		ucp[3] = 0;
-		put_unaligned_be64(info, &ucp[4]);
-	} else if ((buf[0] & 0x7f) == 0x70) {
-		buf[0] |= 0x80;
-		put_unaligned_be64(info, &buf[3]);
-	}
-}
-EXPORT_SYMBOL(scsi_set_sense_information);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index b1a2631..448ebda 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -583,7 +583,7 @@
 
 static void scsi_free_sgtable(struct scsi_data_buffer *sdb, bool mq)
 {
-	if (mq && sdb->table.nents <= SCSI_MAX_SG_SEGMENTS)
+	if (mq && sdb->table.orig_nents <= SCSI_MAX_SG_SEGMENTS)
 		return;
 	__sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS, mq, scsi_sg_free);
 }
@@ -597,8 +597,8 @@
 
 	if (mq) {
 		if (nents <= SCSI_MAX_SG_SEGMENTS) {
-			sdb->table.nents = nents;
-			sg_init_table(sdb->table.sgl, sdb->table.nents);
+			sdb->table.nents = sdb->table.orig_nents = nents;
+			sg_init_table(sdb->table.sgl, nents);
 			return 0;
 		}
 		first_chunk = sdb->table.sgl;
diff --git a/drivers/scsi/scsi_pm.c b/drivers/scsi/scsi_pm.c
index 9e43ae1..e4b7998 100644
--- a/drivers/scsi/scsi_pm.c
+++ b/drivers/scsi/scsi_pm.c
@@ -217,15 +217,15 @@
 {
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
 	struct scsi_device *sdev = to_scsi_device(dev);
-	int err;
+	int err = 0;
 
-	err = blk_pre_runtime_suspend(sdev->request_queue);
-	if (err)
-		return err;
-	if (pm && pm->runtime_suspend)
+	if (pm && pm->runtime_suspend) {
+		err = blk_pre_runtime_suspend(sdev->request_queue);
+		if (err)
+			return err;
 		err = pm->runtime_suspend(dev);
-	blk_post_runtime_suspend(sdev->request_queue, err);
-
+		blk_post_runtime_suspend(sdev->request_queue, err);
+	}
 	return err;
 }
 
@@ -248,11 +248,11 @@
 	const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL;
 	int err = 0;
 
-	blk_pre_runtime_resume(sdev->request_queue);
-	if (pm && pm->runtime_resume)
+	if (pm && pm->runtime_resume) {
+		blk_pre_runtime_resume(sdev->request_queue);
 		err = pm->runtime_resume(dev);
-	blk_post_runtime_resume(sdev->request_queue, err);
-
+		blk_post_runtime_resume(sdev->request_queue, err);
+	}
 	return err;
 }
 
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 1ac38e7..9ad4116 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -859,7 +859,7 @@
 
 	depth = simple_strtoul(buf, NULL, 0);
 
-	if (depth < 1 || depth > sht->can_queue)
+	if (depth < 1 || depth > sdev->host->can_queue)
 		return -EINVAL;
 
 	retval = sht->change_queue_depth(sdev, depth);
diff --git a/drivers/scsi/scsi_transport_srp.c b/drivers/scsi/scsi_transport_srp.c
index a85292b..e3cd3ec 100644
--- a/drivers/scsi/scsi_transport_srp.c
+++ b/drivers/scsi/scsi_transport_srp.c
@@ -203,7 +203,7 @@
 	return tmo >= 0 ? sprintf(buf, "%d\n", tmo) : sprintf(buf, "off\n");
 }
 
-static int srp_parse_tmo(int *tmo, const char *buf)
+int srp_parse_tmo(int *tmo, const char *buf)
 {
 	int res = 0;
 
@@ -214,6 +214,7 @@
 
 	return res;
 }
+EXPORT_SYMBOL(srp_parse_tmo);
 
 static ssize_t show_reconnect_delay(struct device *dev,
 				    struct device_attribute *attr, char *buf)
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 3b2fcb4..a20da8c 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2770,9 +2770,9 @@
 	max_xfer = sdkp->max_xfer_blocks;
 	max_xfer <<= ilog2(sdp->sector_size) - 9;
 
-	max_xfer = min_not_zero(queue_max_hw_sectors(sdkp->disk->queue),
-				max_xfer);
-	blk_queue_max_hw_sectors(sdkp->disk->queue, max_xfer);
+	sdkp->disk->queue->limits.max_sectors =
+		min_not_zero(queue_max_hw_sectors(sdkp->disk->queue), max_xfer);
+
 	set_capacity(disk, sdkp->capacity);
 	sd_config_write_same(sdkp);
 	kfree(buffer);
diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 3f25b8f..871f355 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -1329,9 +1329,9 @@
 	spin_lock(&st_use_lock);
 	STp->in_use = 0;
 	spin_unlock(&st_use_lock);
-	scsi_tape_put(STp);
 	if (resumed)
 		scsi_autopm_put_device(STp->device);
+	scsi_tape_put(STp);
 	return retval;
 
 }
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 285f775..7dbbb29 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -949,7 +949,7 @@
 {
 	struct Scsi_Host *shost;
 	struct virtio_scsi *vscsi;
-	int err, host_prot;
+	int err;
 	u32 sg_elems, num_targets;
 	u32 cmd_per_lun;
 	u32 num_queues;
@@ -1009,6 +1009,8 @@
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 	if (virtio_has_feature(vdev, VIRTIO_SCSI_F_T10_PI)) {
+		int host_prot;
+
 		host_prot = SHOST_DIF_TYPE1_PROTECTION | SHOST_DIF_TYPE2_PROTECTION |
 			    SHOST_DIF_TYPE3_PROTECTION | SHOST_DIX_TYPE1_PROTECTION |
 			    SHOST_DIX_TYPE2_PROTECTION | SHOST_DIX_TYPE3_PROTECTION;
diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index 0cae169..43f6d3d 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -326,6 +326,15 @@
 	  This enables master mode support for the SPIFC (SPI flash
 	  controller) available in Amlogic Meson SoCs.
 
+config SPI_MT65XX
+	tristate "MediaTek SPI controller"
+	depends on ARCH_MEDIATEK || COMPILE_TEST
+	help
+	  This selects the MediaTek(R) SPI bus driver.
+	  If you want to use MediaTek(R) SPI interface,
+	  say Y or M here.If you are not sure, say N.
+	  SPI drivers for Mediatek MT65XX and MT81XX series ARM SoCs.
+
 config SPI_OC_TINY
 	tristate "OpenCores tiny SPI"
 	depends on GPIOLIB || COMPILE_TEST
@@ -612,7 +621,7 @@
 
 config SPI_ZYNQMP_GQSPI
 	tristate "Xilinx ZynqMP GQSPI controller"
-	depends on SPI_MASTER
+	depends on SPI_MASTER && HAS_DMA
 	help
 	  Enables Xilinx GQSPI controller driver for Zynq UltraScale+ MPSoC.
 
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index 1154dba..9746beb2 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -48,6 +48,7 @@
 obj-$(CONFIG_SPI_MPC512x_PSC)		+= spi-mpc512x-psc.o
 obj-$(CONFIG_SPI_MPC52xx_PSC)		+= spi-mpc52xx-psc.o
 obj-$(CONFIG_SPI_MPC52xx)		+= spi-mpc52xx.o
+obj-$(CONFIG_SPI_MT65XX)                += spi-mt65xx.o
 obj-$(CONFIG_SPI_MXS)			+= spi-mxs.o
 obj-$(CONFIG_SPI_NUC900)		+= spi-nuc900.o
 obj-$(CONFIG_SPI_OC_TINY)		+= spi-oc-tiny.o
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index c9eca34..bf9ed38 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -19,7 +19,6 @@
 #include <linux/interrupt.h>
 #include <linux/spi/spi.h>
 #include <linux/slab.h>
-#include <linux/platform_data/atmel.h>
 #include <linux/platform_data/dma-atmel.h>
 #include <linux/of.h>
 
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index 59705ab..e7874a6 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -480,7 +480,7 @@
 					 struct spi_device *spi,
 					 struct spi_transfer *tfr,
 					 u32 cs,
-					 unsigned long xfer_time_us)
+					 unsigned long long xfer_time_us)
 {
 	struct bcm2835_spi *bs = spi_master_get_devdata(master);
 	unsigned long timeout;
@@ -531,7 +531,8 @@
 {
 	struct bcm2835_spi *bs = spi_master_get_devdata(master);
 	unsigned long spi_hz, clk_hz, cdiv;
-	unsigned long spi_used_hz, xfer_time_us;
+	unsigned long spi_used_hz;
+	unsigned long long xfer_time_us;
 	u32 cs = bcm2835_rd(bs, BCM2835_SPI_CS);
 
 	/* set clock */
@@ -553,13 +554,11 @@
 	spi_used_hz = cdiv ? (clk_hz / cdiv) : (clk_hz / 65536);
 	bcm2835_wr(bs, BCM2835_SPI_CLK, cdiv);
 
-	/* handle all the modes */
+	/* handle all the 3-wire mode */
 	if ((spi->mode & SPI_3WIRE) && (tfr->rx_buf))
 		cs |= BCM2835_SPI_CS_REN;
-	if (spi->mode & SPI_CPOL)
-		cs |= BCM2835_SPI_CS_CPOL;
-	if (spi->mode & SPI_CPHA)
-		cs |= BCM2835_SPI_CS_CPHA;
+	else
+		cs &= ~BCM2835_SPI_CS_REN;
 
 	/* for gpio_cs set dummy CS so that no HW-CS get changed
 	 * we can not run this in bcm2835_spi_set_cs, as it does
@@ -575,9 +574,10 @@
 	bs->rx_len = tfr->len;
 
 	/* calculate the estimated time in us the transfer runs */
-	xfer_time_us = tfr->len
+	xfer_time_us = (unsigned long long)tfr->len
 		* 9 /* clocks/byte - SPI-HW waits 1 clock after each byte */
-		* 1000000 / spi_used_hz;
+		* 1000000;
+	do_div(xfer_time_us, spi_used_hz);
 
 	/* for short requests run polling*/
 	if (xfer_time_us <= BCM2835_SPI_POLLING_LIMIT_US)
@@ -592,6 +592,25 @@
 	return bcm2835_spi_transfer_one_irq(master, spi, tfr, cs);
 }
 
+static int bcm2835_spi_prepare_message(struct spi_master *master,
+				       struct spi_message *msg)
+{
+	struct spi_device *spi = msg->spi;
+	struct bcm2835_spi *bs = spi_master_get_devdata(master);
+	u32 cs = bcm2835_rd(bs, BCM2835_SPI_CS);
+
+	cs &= ~(BCM2835_SPI_CS_CPOL | BCM2835_SPI_CS_CPHA);
+
+	if (spi->mode & SPI_CPOL)
+		cs |= BCM2835_SPI_CS_CPOL;
+	if (spi->mode & SPI_CPHA)
+		cs |= BCM2835_SPI_CS_CPHA;
+
+	bcm2835_wr(bs, BCM2835_SPI_CS, cs);
+
+	return 0;
+}
+
 static void bcm2835_spi_handle_err(struct spi_master *master,
 				   struct spi_message *msg)
 {
@@ -739,6 +758,7 @@
 	master->set_cs = bcm2835_spi_set_cs;
 	master->transfer_one = bcm2835_spi_transfer_one;
 	master->handle_err = bcm2835_spi_handle_err;
+	master->prepare_message = bcm2835_spi_prepare_message;
 	master->dev.of_node = pdev->dev.of_node;
 
 	bs = spi_master_get_devdata(master);
diff --git a/drivers/spi/spi-bcm63xx-hsspi.c b/drivers/spi/spi-bcm63xx-hsspi.c
index f5ca6dc..55789f7 100644
--- a/drivers/spi/spi-bcm63xx-hsspi.c
+++ b/drivers/spi/spi-bcm63xx-hsspi.c
@@ -76,6 +76,7 @@
 #define HSSPI_FIFO_REG(x)			(0x200 + (x) * 0x200)
 
 
+#define HSSPI_OP_MULTIBIT			BIT(11)
 #define HSSPI_OP_CODE_SHIFT			13
 #define HSSPI_OP_SLEEP				(0 << HSSPI_OP_CODE_SHIFT)
 #define HSSPI_OP_READ_WRITE			(1 << HSSPI_OP_CODE_SHIFT)
@@ -171,9 +172,12 @@
 	if (opcode != HSSPI_OP_READ)
 		step_size -= HSSPI_OPCODE_LEN;
 
-	__raw_writel(0 << MODE_CTRL_PREPENDBYTE_CNT_SHIFT |
-		     2 << MODE_CTRL_MULTIDATA_WR_STRT_SHIFT |
-		     2 << MODE_CTRL_MULTIDATA_RD_STRT_SHIFT | 0xff,
+	if ((opcode == HSSPI_OP_READ && t->rx_nbits == SPI_NBITS_DUAL) ||
+	    (opcode == HSSPI_OP_WRITE && t->tx_nbits == SPI_NBITS_DUAL))
+		opcode |= HSSPI_OP_MULTIBIT;
+
+	__raw_writel(1 << MODE_CTRL_MULTIDATA_WR_SIZE_SHIFT |
+		     1 << MODE_CTRL_MULTIDATA_RD_SIZE_SHIFT | 0xff,
 		     bs->regs + HSSPI_PROFILE_MODE_CTRL_REG(chip_select));
 
 	while (pending > 0) {
@@ -374,7 +378,8 @@
 	master->num_chipselect = 8;
 	master->setup = bcm63xx_hsspi_setup;
 	master->transfer_one_message = bcm63xx_hsspi_transfer_one;
-	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH;
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH |
+			    SPI_RX_DUAL | SPI_TX_DUAL;
 	master->bits_per_word_mask = SPI_BPW_MASK(8);
 	master->auto_runtime_pm = true;
 
diff --git a/drivers/spi/spi-bitbang-txrx.h b/drivers/spi/spi-bitbang-txrx.h
index 06b34e5..47bb9b89 100644
--- a/drivers/spi/spi-bitbang-txrx.h
+++ b/drivers/spi/spi-bitbang-txrx.h
@@ -49,7 +49,7 @@
 {
 	/* if (cpol == 0) this is SPI_MODE_0; else this is SPI_MODE_2 */
 
-	bool oldbit = !(word & 1);
+	u32 oldbit = (!(word & (1<<(bits-1)))) << 31;
 	/* clock starts at inactive polarity */
 	for (word <<= (32 - bits); likely(bits); bits--) {
 
@@ -81,7 +81,7 @@
 {
 	/* if (cpol == 0) this is SPI_MODE_1; else this is SPI_MODE_3 */
 
-	bool oldbit = !(word & (1 << 31));
+	u32 oldbit = (!(word & (1<<(bits-1)))) << 31;
 	/* clock starts at inactive polarity */
 	for (word <<= (32 - bits); likely(bits); bits--) {
 
diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c
index 987afeb..3cf9faa 100644
--- a/drivers/spi/spi-davinci.c
+++ b/drivers/spi/spi-davinci.c
@@ -139,6 +139,8 @@
 	u32			(*get_tx)(struct davinci_spi *);
 
 	u8			*bytes_per_word;
+
+	u8			prescaler_limit;
 };
 
 static struct davinci_spi_config davinci_spi_default_cfg;
@@ -255,7 +257,7 @@
  * This function calculates the prescale value that generates a clock rate
  * less than or equal to the specified maximum.
  *
- * Returns: calculated prescale - 1 for easy programming into SPI registers
+ * Returns: calculated prescale value for easy programming into SPI registers
  * or negative error number if valid prescalar cannot be updated.
  */
 static inline int davinci_spi_get_prescale(struct davinci_spi *dspi,
@@ -263,12 +265,13 @@
 {
 	int ret;
 
-	ret = DIV_ROUND_UP(clk_get_rate(dspi->clk), max_speed_hz);
+	/* Subtract 1 to match what will be programmed into SPI register. */
+	ret = DIV_ROUND_UP(clk_get_rate(dspi->clk), max_speed_hz) - 1;
 
-	if (ret < 1 || ret > 256)
+	if (ret < dspi->prescaler_limit || ret > 255)
 		return -EINVAL;
 
-	return ret - 1;
+	return ret;
 }
 
 /**
@@ -832,13 +835,40 @@
 }
 
 #if defined(CONFIG_OF)
+
+/* OF SPI data structure */
+struct davinci_spi_of_data {
+	u8	version;
+	u8	prescaler_limit;
+};
+
+static const struct davinci_spi_of_data dm6441_spi_data = {
+	.version = SPI_VERSION_1,
+	.prescaler_limit = 2,
+};
+
+static const struct davinci_spi_of_data da830_spi_data = {
+	.version = SPI_VERSION_2,
+	.prescaler_limit = 2,
+};
+
+static const struct davinci_spi_of_data keystone_spi_data = {
+	.version = SPI_VERSION_1,
+	.prescaler_limit = 0,
+};
+
 static const struct of_device_id davinci_spi_of_match[] = {
 	{
 		.compatible = "ti,dm6441-spi",
+		.data = &dm6441_spi_data,
 	},
 	{
 		.compatible = "ti,da830-spi",
-		.data = (void *)SPI_VERSION_2,
+		.data = &da830_spi_data,
+	},
+	{
+		.compatible = "ti,keystone-spi",
+		.data = &keystone_spi_data,
 	},
 	{ },
 };
@@ -857,21 +887,21 @@
 			struct davinci_spi *dspi)
 {
 	struct device_node *node = pdev->dev.of_node;
+	struct davinci_spi_of_data *spi_data;
 	struct davinci_spi_platform_data *pdata;
 	unsigned int num_cs, intr_line = 0;
 	const struct of_device_id *match;
 
 	pdata = &dspi->pdata;
 
-	pdata->version = SPI_VERSION_1;
 	match = of_match_device(davinci_spi_of_match, &pdev->dev);
 	if (!match)
 		return -ENODEV;
 
-	/* match data has the SPI version number for SPI_VERSION_2 */
-	if (match->data == (void *)SPI_VERSION_2)
-		pdata->version = SPI_VERSION_2;
+	spi_data = (struct davinci_spi_of_data *)match->data;
 
+	pdata->version = spi_data->version;
+	pdata->prescaler_limit = spi_data->prescaler_limit;
 	/*
 	 * default num_cs is 1 and all chipsel are internal to the chip
 	 * indicated by chip_sel being NULL or cs_gpios being NULL or
@@ -991,7 +1021,7 @@
 
 	dspi->bitbang.chipselect = davinci_spi_chipselect;
 	dspi->bitbang.setup_transfer = davinci_spi_setup_transfer;
-
+	dspi->prescaler_limit = pdata->prescaler_limit;
 	dspi->version = pdata->version;
 
 	dspi->bitbang.flags = SPI_NO_CS | SPI_LSB_FIRST | SPI_LOOP;
diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c
index eb03e12..7edede6 100644
--- a/drivers/spi/spi-dw-mmio.c
+++ b/drivers/spi/spi-dw-mmio.c
@@ -74,6 +74,9 @@
 
 	dws->max_freq = clk_get_rate(dwsmmio->clk);
 
+	of_property_read_u32(pdev->dev.of_node, "reg-io-width",
+			     &dws->reg_io_width);
+
 	num_cs = 4;
 
 	if (pdev->dev.of_node)
diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index 8d67d03..4fbfcdc 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -194,7 +194,7 @@
 			else
 				txw = *(u16 *)(dws->tx);
 		}
-		dw_writel(dws, DW_SPI_DR, txw);
+		dw_write_io_reg(dws, DW_SPI_DR, txw);
 		dws->tx += dws->n_bytes;
 	}
 }
@@ -205,7 +205,7 @@
 	u16 rxw;
 
 	while (max--) {
-		rxw = dw_readl(dws, DW_SPI_DR);
+		rxw = dw_read_io_reg(dws, DW_SPI_DR);
 		/* Care rx only if the transfer's original "rx" is not null */
 		if (dws->rx_end - dws->len) {
 			if (dws->n_bytes == 1)
diff --git a/drivers/spi/spi-dw.h b/drivers/spi/spi-dw.h
index 6c91391..b75ed32 100644
--- a/drivers/spi/spi-dw.h
+++ b/drivers/spi/spi-dw.h
@@ -109,6 +109,7 @@
 	u32			fifo_len;	/* depth of the FIFO buffer */
 	u32			max_freq;	/* max bus freq supported */
 
+	u32			reg_io_width;	/* DR I/O width in bytes */
 	u16			bus_num;
 	u16			num_cs;		/* supported slave numbers */
 
@@ -145,11 +146,45 @@
 	return __raw_readl(dws->regs + offset);
 }
 
+static inline u16 dw_readw(struct dw_spi *dws, u32 offset)
+{
+	return __raw_readw(dws->regs + offset);
+}
+
 static inline void dw_writel(struct dw_spi *dws, u32 offset, u32 val)
 {
 	__raw_writel(val, dws->regs + offset);
 }
 
+static inline void dw_writew(struct dw_spi *dws, u32 offset, u16 val)
+{
+	__raw_writew(val, dws->regs + offset);
+}
+
+static inline u32 dw_read_io_reg(struct dw_spi *dws, u32 offset)
+{
+	switch (dws->reg_io_width) {
+	case 2:
+		return dw_readw(dws, offset);
+	case 4:
+	default:
+		return dw_readl(dws, offset);
+	}
+}
+
+static inline void dw_write_io_reg(struct dw_spi *dws, u32 offset, u32 val)
+{
+	switch (dws->reg_io_width) {
+	case 2:
+		dw_writew(dws, offset, val);
+		break;
+	case 4:
+	default:
+		dw_writel(dws, offset, val);
+		break;
+	}
+}
+
 static inline void spi_enable_chip(struct dw_spi *dws, int enable)
 {
 	dw_writel(dws, DW_SPI_SSIENR, (enable ? 1 : 0));
diff --git a/drivers/spi/spi-fsl-espi.c b/drivers/spi/spi-fsl-espi.c
index d3f05a0..c27124a 100644
--- a/drivers/spi/spi-fsl-espi.c
+++ b/drivers/spi/spi-fsl-espi.c
@@ -21,6 +21,7 @@
 #include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/spi/spi.h>
+#include <linux/pm_runtime.h>
 #include <sysdev/fsl_soc.h>
 
 #include "spi-fsl-lib.h"
@@ -85,6 +86,8 @@
 #define SPCOM_TRANLEN(x)	((x) << 0)
 #define	SPCOM_TRANLEN_MAX	0xFFFF	/* Max transaction length */
 
+#define AUTOSUSPEND_TIMEOUT 2000
+
 static void fsl_espi_change_mode(struct spi_device *spi)
 {
 	struct mpc8xxx_spi *mspi = spi_master_get_devdata(spi->master);
@@ -485,6 +488,8 @@
 	mpc8xxx_spi = spi_master_get_devdata(spi->master);
 	reg_base = mpc8xxx_spi->reg_base;
 
+	pm_runtime_get_sync(mpc8xxx_spi->dev);
+
 	hw_mode = cs->hw_mode; /* Save original settings */
 	cs->hw_mode = mpc8xxx_spi_read_reg(
 			&reg_base->csmode[spi->chip_select]);
@@ -507,6 +512,10 @@
 	mpc8xxx_spi_write_reg(&reg_base->mode, loop_mode);
 
 	retval = fsl_espi_setup_transfer(spi, NULL);
+
+	pm_runtime_mark_last_busy(mpc8xxx_spi->dev);
+	pm_runtime_put_autosuspend(mpc8xxx_spi->dev);
+
 	if (retval < 0) {
 		cs->hw_mode = hw_mode; /* Restore settings */
 		return retval;
@@ -604,20 +613,14 @@
 	return ret;
 }
 
-static void fsl_espi_remove(struct mpc8xxx_spi *mspi)
+#ifdef CONFIG_PM
+static int fsl_espi_runtime_suspend(struct device *dev)
 {
-	iounmap(mspi->reg_base);
-}
-
-static int fsl_espi_suspend(struct spi_master *master)
-{
-	struct mpc8xxx_spi *mpc8xxx_spi;
-	struct fsl_espi_reg *reg_base;
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(master);
+	struct fsl_espi_reg *reg_base = mpc8xxx_spi->reg_base;
 	u32 regval;
 
-	mpc8xxx_spi = spi_master_get_devdata(master);
-	reg_base = mpc8xxx_spi->reg_base;
-
 	regval = mpc8xxx_spi_read_reg(&reg_base->mode);
 	regval &= ~SPMODE_ENABLE;
 	mpc8xxx_spi_write_reg(&reg_base->mode, regval);
@@ -625,21 +628,20 @@
 	return 0;
 }
 
-static int fsl_espi_resume(struct spi_master *master)
+static int fsl_espi_runtime_resume(struct device *dev)
 {
-	struct mpc8xxx_spi *mpc8xxx_spi;
-	struct fsl_espi_reg *reg_base;
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(master);
+	struct fsl_espi_reg *reg_base = mpc8xxx_spi->reg_base;
 	u32 regval;
 
-	mpc8xxx_spi = spi_master_get_devdata(master);
-	reg_base = mpc8xxx_spi->reg_base;
-
 	regval = mpc8xxx_spi_read_reg(&reg_base->mode);
 	regval |= SPMODE_ENABLE;
 	mpc8xxx_spi_write_reg(&reg_base->mode, regval);
 
 	return 0;
 }
+#endif
 
 static struct spi_master * fsl_espi_probe(struct device *dev,
 		struct resource *mem, unsigned int irq)
@@ -667,25 +669,23 @@
 	master->setup = fsl_espi_setup;
 	master->cleanup = fsl_espi_cleanup;
 	master->transfer_one_message = fsl_espi_do_one_msg;
-	master->prepare_transfer_hardware = fsl_espi_resume;
-	master->unprepare_transfer_hardware = fsl_espi_suspend;
+	master->auto_runtime_pm = true;
 
 	mpc8xxx_spi = spi_master_get_devdata(master);
-	mpc8xxx_spi->spi_remove = fsl_espi_remove;
 
-	mpc8xxx_spi->reg_base = ioremap(mem->start, resource_size(mem));
-	if (!mpc8xxx_spi->reg_base) {
-		ret = -ENOMEM;
+	mpc8xxx_spi->reg_base = devm_ioremap_resource(dev, mem);
+	if (IS_ERR(mpc8xxx_spi->reg_base)) {
+		ret = PTR_ERR(mpc8xxx_spi->reg_base);
 		goto err_probe;
 	}
 
 	reg_base = mpc8xxx_spi->reg_base;
 
 	/* Register for SPI Interrupt */
-	ret = request_irq(mpc8xxx_spi->irq, fsl_espi_irq,
+	ret = devm_request_irq(dev, mpc8xxx_spi->irq, fsl_espi_irq,
 			  0, "fsl_espi", mpc8xxx_spi);
 	if (ret)
-		goto free_irq;
+		goto err_probe;
 
 	if (mpc8xxx_spi->flags & SPI_QE_CPU_MODE) {
 		mpc8xxx_spi->rx_shift = 16;
@@ -731,18 +731,27 @@
 
 	mpc8xxx_spi_write_reg(&reg_base->mode, regval);
 
-	ret = spi_register_master(master);
+	pm_runtime_set_autosuspend_delay(dev, AUTOSUSPEND_TIMEOUT);
+	pm_runtime_use_autosuspend(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+	pm_runtime_get_sync(dev);
+
+	ret = devm_spi_register_master(dev, master);
 	if (ret < 0)
-		goto unreg_master;
+		goto err_pm;
 
 	dev_info(dev, "at 0x%p (irq = %d)\n", reg_base, mpc8xxx_spi->irq);
 
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
 	return master;
 
-unreg_master:
-	free_irq(mpc8xxx_spi->irq, mpc8xxx_spi);
-free_irq:
-	iounmap(mpc8xxx_spi->reg_base);
+err_pm:
+	pm_runtime_put_noidle(dev);
+	pm_runtime_disable(dev);
+	pm_runtime_set_suspended(dev);
 err_probe:
 	spi_master_put(master);
 err:
@@ -809,7 +818,9 @@
 
 static int of_fsl_espi_remove(struct platform_device *dev)
 {
-	return mpc8xxx_spi_remove(&dev->dev);
+	pm_runtime_disable(&dev->dev);
+
+	return 0;
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -824,7 +835,11 @@
 		return ret;
 	}
 
-	return fsl_espi_suspend(master);
+	ret = pm_runtime_force_suspend(dev);
+	if (ret < 0)
+		return ret;
+
+	return 0;
 }
 
 static int of_fsl_espi_resume(struct device *dev)
@@ -834,7 +849,7 @@
 	struct mpc8xxx_spi *mpc8xxx_spi;
 	struct fsl_espi_reg *reg_base;
 	u32 regval;
-	int i;
+	int i, ret;
 
 	mpc8xxx_spi = spi_master_get_devdata(master);
 	reg_base = mpc8xxx_spi->reg_base;
@@ -854,11 +869,17 @@
 
 	mpc8xxx_spi_write_reg(&reg_base->mode, regval);
 
+	ret = pm_runtime_force_resume(dev);
+	if (ret < 0)
+		return ret;
+
 	return spi_master_resume(master);
 }
 #endif /* CONFIG_PM_SLEEP */
 
 static const struct dev_pm_ops espi_pm = {
+	SET_RUNTIME_PM_OPS(fsl_espi_runtime_suspend,
+			   fsl_espi_runtime_resume, NULL)
 	SET_SYSTEM_SLEEP_PM_OPS(of_fsl_espi_suspend, of_fsl_espi_resume)
 };
 
diff --git a/drivers/spi/spi-fsl-lib.c b/drivers/spi/spi-fsl-lib.c
index cb35d2f..1e43412 100644
--- a/drivers/spi/spi-fsl-lib.c
+++ b/drivers/spi/spi-fsl-lib.c
@@ -114,25 +114,6 @@
 }
 EXPORT_SYMBOL_GPL(mpc8xxx_spi_probe);
 
-int mpc8xxx_spi_remove(struct device *dev)
-{
-	struct mpc8xxx_spi *mpc8xxx_spi;
-	struct spi_master *master;
-
-	master = dev_get_drvdata(dev);
-	mpc8xxx_spi = spi_master_get_devdata(master);
-
-	spi_unregister_master(master);
-
-	free_irq(mpc8xxx_spi->irq, mpc8xxx_spi);
-
-	if (mpc8xxx_spi->spi_remove)
-		mpc8xxx_spi->spi_remove(mpc8xxx_spi);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(mpc8xxx_spi_remove);
-
 int of_mpc8xxx_spi_probe(struct platform_device *ofdev)
 {
 	struct device *dev = &ofdev->dev;
diff --git a/drivers/spi/spi-fsl-lib.h b/drivers/spi/spi-fsl-lib.h
index 1326a39..84f5dcb 100644
--- a/drivers/spi/spi-fsl-lib.h
+++ b/drivers/spi/spi-fsl-lib.h
@@ -54,9 +54,6 @@
 	void (*get_rx) (u32 rx_data, struct mpc8xxx_spi *);
 	u32(*get_tx) (struct mpc8xxx_spi *);
 
-	/* hooks for different controller driver */
-	void (*spi_remove) (struct mpc8xxx_spi *mspi);
-
 	unsigned int count;
 	unsigned int irq;
 
diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c
index 60c5907..8b290d9 100644
--- a/drivers/spi/spi-fsl-spi.c
+++ b/drivers/spi/spi-fsl-spi.c
@@ -559,12 +559,6 @@
 	return ret;
 }
 
-static void fsl_spi_remove(struct mpc8xxx_spi *mspi)
-{
-	iounmap(mspi->reg_base);
-	fsl_spi_cpm_free(mspi);
-}
-
 static void fsl_spi_grlib_cs_control(struct spi_device *spi, bool on)
 {
 	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(spi->master);
@@ -631,7 +625,6 @@
 	master->transfer_one_message = fsl_spi_do_one_msg;
 
 	mpc8xxx_spi = spi_master_get_devdata(master);
-	mpc8xxx_spi->spi_remove = fsl_spi_remove;
 	mpc8xxx_spi->max_bits_per_word = 32;
 	mpc8xxx_spi->type = fsl_spi_get_type(dev);
 
@@ -639,10 +632,10 @@
 	if (ret)
 		goto err_cpm_init;
 
-	mpc8xxx_spi->reg_base = ioremap(mem->start, resource_size(mem));
-	if (mpc8xxx_spi->reg_base == NULL) {
-		ret = -ENOMEM;
-		goto err_ioremap;
+	mpc8xxx_spi->reg_base = devm_ioremap_resource(dev, mem);
+	if (IS_ERR(mpc8xxx_spi->reg_base)) {
+		ret = PTR_ERR(mpc8xxx_spi->reg_base);
+		goto err_probe;
 	}
 
 	if (mpc8xxx_spi->type == TYPE_GRLIB)
@@ -661,11 +654,11 @@
 					&mpc8xxx_spi->tx_shift, 8, 1);
 
 	/* Register for SPI Interrupt */
-	ret = request_irq(mpc8xxx_spi->irq, fsl_spi_irq,
-			  0, "fsl_spi", mpc8xxx_spi);
+	ret = devm_request_irq(dev, mpc8xxx_spi->irq, fsl_spi_irq,
+			       0, "fsl_spi", mpc8xxx_spi);
 
 	if (ret != 0)
-		goto free_irq;
+		goto err_probe;
 
 	reg_base = mpc8xxx_spi->reg_base;
 
@@ -686,20 +679,16 @@
 
 	mpc8xxx_spi_write_reg(&reg_base->mode, regval);
 
-	ret = spi_register_master(master);
+	ret = devm_spi_register_master(dev, master);
 	if (ret < 0)
-		goto unreg_master;
+		goto err_probe;
 
 	dev_info(dev, "at 0x%p (irq = %d), %s mode\n", reg_base,
 		 mpc8xxx_spi->irq, mpc8xxx_spi_strmode(mpc8xxx_spi->flags));
 
 	return master;
 
-unreg_master:
-	free_irq(mpc8xxx_spi->irq, mpc8xxx_spi);
-free_irq:
-	iounmap(mpc8xxx_spi->reg_base);
-err_ioremap:
+err_probe:
 	fsl_spi_cpm_free(mpc8xxx_spi);
 err_cpm_init:
 	spi_master_put(master);
@@ -866,11 +855,8 @@
 {
 	struct spi_master *master = platform_get_drvdata(ofdev);
 	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(master);
-	int ret;
 
-	ret = mpc8xxx_spi_remove(&ofdev->dev);
-	if (ret)
-		return ret;
+	fsl_spi_cpm_free(mpc8xxx_spi);
 	if (mpc8xxx_spi->type == TYPE_FSL)
 		of_fsl_spi_free_chipselects(&ofdev->dev);
 	return 0;
@@ -916,7 +902,12 @@
 
 static int plat_mpc8xxx_spi_remove(struct platform_device *pdev)
 {
-	return mpc8xxx_spi_remove(&pdev->dev);
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct mpc8xxx_spi *mpc8xxx_spi = spi_master_get_devdata(master);
+
+	fsl_spi_cpm_free(mpc8xxx_spi);
+
+	return 0;
 }
 
 MODULE_ALIAS("platform:mpc8xxx_spi");
diff --git a/drivers/spi/spi-img-spfi.c b/drivers/spi/spi-img-spfi.c
index 788e2b1..823cbc9 100644
--- a/drivers/spi/spi-img-spfi.c
+++ b/drivers/spi/spi-img-spfi.c
@@ -40,6 +40,7 @@
 #define SPFI_CONTROL_SOFT_RESET			BIT(11)
 #define SPFI_CONTROL_SEND_DMA			BIT(10)
 #define SPFI_CONTROL_GET_DMA			BIT(9)
+#define SPFI_CONTROL_SE			BIT(8)
 #define SPFI_CONTROL_TMODE_SHIFT		5
 #define SPFI_CONTROL_TMODE_MASK			0x7
 #define SPFI_CONTROL_TMODE_SINGLE		0
@@ -104,6 +105,10 @@
 	bool rx_dma_busy;
 };
 
+struct img_spfi_device_data {
+	bool gpio_requested;
+};
+
 static inline u32 spfi_readl(struct img_spfi *spfi, u32 reg)
 {
 	return readl(spfi->regs + reg);
@@ -266,15 +271,15 @@
 		cpu_relax();
 	}
 
-	ret = spfi_wait_all_done(spfi);
-	if (ret < 0)
-		return ret;
-
 	if (rx_bytes > 0 || tx_bytes > 0) {
 		dev_err(spfi->dev, "PIO transfer timed out\n");
 		return -ETIMEDOUT;
 	}
 
+	ret = spfi_wait_all_done(spfi);
+	if (ret < 0)
+		return ret;
+
 	return 0;
 }
 
@@ -439,21 +444,50 @@
 
 static int img_spfi_setup(struct spi_device *spi)
 {
-	int ret;
+	int ret = -EINVAL;
+	struct img_spfi_device_data *spfi_data = spi_get_ctldata(spi);
 
-	ret = gpio_request_one(spi->cs_gpio, (spi->mode & SPI_CS_HIGH) ?
-			       GPIOF_OUT_INIT_LOW : GPIOF_OUT_INIT_HIGH,
-			       dev_name(&spi->dev));
-	if (ret)
-		dev_err(&spi->dev, "can't request chipselect gpio %d\n",
+	if (!spfi_data) {
+		spfi_data = kzalloc(sizeof(*spfi_data), GFP_KERNEL);
+		if (!spfi_data)
+			return -ENOMEM;
+		spfi_data->gpio_requested = false;
+		spi_set_ctldata(spi, spfi_data);
+	}
+	if (!spfi_data->gpio_requested) {
+		ret = gpio_request_one(spi->cs_gpio,
+				       (spi->mode & SPI_CS_HIGH) ?
+				       GPIOF_OUT_INIT_LOW : GPIOF_OUT_INIT_HIGH,
+				       dev_name(&spi->dev));
+		if (ret)
+			dev_err(&spi->dev, "can't request chipselect gpio %d\n",
 				spi->cs_gpio);
+		else
+			spfi_data->gpio_requested = true;
+	} else {
+		if (gpio_is_valid(spi->cs_gpio)) {
+			int mode = ((spi->mode & SPI_CS_HIGH) ?
+				    GPIOF_OUT_INIT_LOW : GPIOF_OUT_INIT_HIGH);
 
+			ret = gpio_direction_output(spi->cs_gpio, mode);
+			if (ret)
+				dev_err(&spi->dev, "chipselect gpio %d setup failed (%d)\n",
+					spi->cs_gpio, ret);
+		}
+	}
 	return ret;
 }
 
 static void img_spfi_cleanup(struct spi_device *spi)
 {
-	gpio_free(spi->cs_gpio);
+	struct img_spfi_device_data *spfi_data = spi_get_ctldata(spi);
+
+	if (spfi_data) {
+		if (spfi_data->gpio_requested)
+			gpio_free(spi->cs_gpio);
+		kfree(spfi_data);
+		spi_set_ctldata(spi, NULL);
+	}
 }
 
 static void img_spfi_config(struct spi_master *master, struct spi_device *spi,
@@ -491,6 +525,7 @@
 	else if (xfer->tx_nbits == SPI_NBITS_QUAD &&
 		 xfer->rx_nbits == SPI_NBITS_QUAD)
 		val |= SPFI_CONTROL_TMODE_QUAD << SPFI_CONTROL_TMODE_SHIFT;
+	val |= SPFI_CONTROL_SE;
 	spfi_writel(spfi, val, SPFI_CONTROL);
 }
 
@@ -546,6 +581,7 @@
 	struct img_spfi *spfi;
 	struct resource *res;
 	int ret;
+	u32 max_speed_hz;
 
 	master = spi_alloc_master(&pdev->dev, sizeof(*spfi));
 	if (!master)
@@ -610,6 +646,19 @@
 	master->max_speed_hz = clk_get_rate(spfi->spfi_clk) / 4;
 	master->min_speed_hz = clk_get_rate(spfi->spfi_clk) / 512;
 
+	/*
+	 * Maximum speed supported by spfi is limited to the lower value
+	 * between 1/4 of the SPFI clock or to "spfi-max-frequency"
+	 * defined in the device tree.
+	 * If no value is defined in the device tree assume the maximum
+	 * speed supported to be 1/4 of the SPFI clock.
+	 */
+	if (!of_property_read_u32(spfi->dev->of_node, "spfi-max-frequency",
+				  &max_speed_hz)) {
+		if (master->max_speed_hz > max_speed_hz)
+			master->max_speed_hz = max_speed_hz;
+	}
+
 	master->setup = img_spfi_setup;
 	master->cleanup = img_spfi_cleanup;
 	master->transfer_one = img_spfi_transfer_one;
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index eb7d3a6..f9deb84 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -201,8 +201,9 @@
 {
 	struct spi_imx_data *spi_imx = spi_master_get_devdata(master);
 
-	if (spi_imx->dma_is_inited && (transfer->len > spi_imx->rx_wml)
-	    && (transfer->len > spi_imx->tx_wml))
+	if (spi_imx->dma_is_inited
+	    && transfer->len > spi_imx->rx_wml * sizeof(u32)
+	    && transfer->len > spi_imx->tx_wml * sizeof(u32))
 		return true;
 	return false;
 }
diff --git a/drivers/spi/spi-mpc512x-psc.c b/drivers/spi/spi-mpc512x-psc.c
index 965d2bd..1e75341 100644
--- a/drivers/spi/spi-mpc512x-psc.c
+++ b/drivers/spi/spi-mpc512x-psc.c
@@ -30,11 +30,37 @@
 #include <linux/gpio.h>
 #include <asm/mpc52xx_psc.h>
 
+enum {
+	TYPE_MPC5121,
+	TYPE_MPC5125,
+};
+
+/*
+ * This macro abstracts the differences in the PSC register layout between
+ * MPC5121 (which uses a struct mpc52xx_psc) and MPC5125 (using mpc5125_psc).
+ */
+#define psc_addr(mps, regname) ({					\
+	void *__ret = NULL;						\
+	switch (mps->type) {						\
+	case TYPE_MPC5121: {						\
+			struct mpc52xx_psc __iomem *psc = mps->psc;	\
+			__ret = &psc->regname;				\
+		};							\
+		break;							\
+	case TYPE_MPC5125: {						\
+			struct mpc5125_psc __iomem *psc = mps->psc;	\
+			__ret = &psc->regname;				\
+		};							\
+		break;							\
+	}								\
+	__ret; })
+
 struct mpc512x_psc_spi {
 	void (*cs_control)(struct spi_device *spi, bool on);
 
 	/* driver internal data */
-	struct mpc52xx_psc __iomem *psc;
+	int type;
+	void __iomem *psc;
 	struct mpc512x_psc_fifo __iomem *fifo;
 	unsigned int irq;
 	u8 bits_per_word;
@@ -71,13 +97,12 @@
 {
 	struct mpc512x_psc_spi_cs *cs = spi->controller_state;
 	struct mpc512x_psc_spi *mps = spi_master_get_devdata(spi->master);
-	struct mpc52xx_psc __iomem *psc = mps->psc;
 	u32 sicr;
 	u32 ccr;
 	int speed;
 	u16 bclkdiv;
 
-	sicr = in_be32(&psc->sicr);
+	sicr = in_be32(psc_addr(mps, sicr));
 
 	/* Set clock phase and polarity */
 	if (spi->mode & SPI_CPHA)
@@ -94,9 +119,9 @@
 		sicr |= 0x10000000;
 	else
 		sicr &= ~0x10000000;
-	out_be32(&psc->sicr, sicr);
+	out_be32(psc_addr(mps, sicr), sicr);
 
-	ccr = in_be32(&psc->ccr);
+	ccr = in_be32(psc_addr(mps, ccr));
 	ccr &= 0xFF000000;
 	speed = cs->speed_hz;
 	if (!speed)
@@ -104,7 +129,7 @@
 	bclkdiv = (mps->mclk_rate / speed) - 1;
 
 	ccr |= (((bclkdiv & 0xff) << 16) | (((bclkdiv >> 8) & 0xff) << 8));
-	out_be32(&psc->ccr, ccr);
+	out_be32(psc_addr(mps, ccr), ccr);
 	mps->bits_per_word = cs->bits_per_word;
 
 	if (mps->cs_control && gpio_is_valid(spi->cs_gpio))
@@ -315,16 +340,15 @@
 static int mpc512x_psc_spi_prep_xfer_hw(struct spi_master *master)
 {
 	struct mpc512x_psc_spi *mps = spi_master_get_devdata(master);
-	struct mpc52xx_psc __iomem *psc = mps->psc;
 
 	dev_dbg(&master->dev, "%s()\n", __func__);
 
 	/* Zero MR2 */
-	in_8(&psc->mode);
-	out_8(&psc->mode, 0x0);
+	in_8(psc_addr(mps, mr2));
+	out_8(psc_addr(mps, mr2), 0x0);
 
 	/* enable transmitter/receiver */
-	out_8(&psc->command, MPC52xx_PSC_TX_ENABLE | MPC52xx_PSC_RX_ENABLE);
+	out_8(psc_addr(mps, command), MPC52xx_PSC_TX_ENABLE | MPC52xx_PSC_RX_ENABLE);
 
 	return 0;
 }
@@ -332,13 +356,12 @@
 static int mpc512x_psc_spi_unprep_xfer_hw(struct spi_master *master)
 {
 	struct mpc512x_psc_spi *mps = spi_master_get_devdata(master);
-	struct mpc52xx_psc __iomem *psc = mps->psc;
 	struct mpc512x_psc_fifo __iomem *fifo = mps->fifo;
 
 	dev_dbg(&master->dev, "%s()\n", __func__);
 
 	/* disable transmitter/receiver and fifo interrupt */
-	out_8(&psc->command, MPC52xx_PSC_TX_DISABLE | MPC52xx_PSC_RX_DISABLE);
+	out_8(psc_addr(mps, command), MPC52xx_PSC_TX_DISABLE | MPC52xx_PSC_RX_DISABLE);
 	out_be32(&fifo->tximr, 0);
 
 	return 0;
@@ -388,7 +411,6 @@
 static int mpc512x_psc_spi_port_config(struct spi_master *master,
 				       struct mpc512x_psc_spi *mps)
 {
-	struct mpc52xx_psc __iomem *psc = mps->psc;
 	struct mpc512x_psc_fifo __iomem *fifo = mps->fifo;
 	u32 sicr;
 	u32 ccr;
@@ -396,12 +418,12 @@
 	u16 bclkdiv;
 
 	/* Reset the PSC into a known state */
-	out_8(&psc->command, MPC52xx_PSC_RST_RX);
-	out_8(&psc->command, MPC52xx_PSC_RST_TX);
-	out_8(&psc->command, MPC52xx_PSC_TX_DISABLE | MPC52xx_PSC_RX_DISABLE);
+	out_8(psc_addr(mps, command), MPC52xx_PSC_RST_RX);
+	out_8(psc_addr(mps, command), MPC52xx_PSC_RST_TX);
+	out_8(psc_addr(mps, command), MPC52xx_PSC_TX_DISABLE | MPC52xx_PSC_RX_DISABLE);
 
 	/* Disable psc interrupts all useful interrupts are in fifo */
-	out_be16(&psc->isr_imr.imr, 0);
+	out_be16(psc_addr(mps, isr_imr.imr), 0);
 
 	/* Disable fifo interrupts, will be enabled later */
 	out_be32(&fifo->tximr, 0);
@@ -417,18 +439,18 @@
 		0x00004000 |	/* MSTR = 1   -- SPI master */
 		0x00000800;	/* UseEOF = 1 -- SS low until EOF */
 
-	out_be32(&psc->sicr, sicr);
+	out_be32(psc_addr(mps, sicr), sicr);
 
-	ccr = in_be32(&psc->ccr);
+	ccr = in_be32(psc_addr(mps, ccr));
 	ccr &= 0xFF000000;
 	speed = 1000000;	/* default 1MHz */
 	bclkdiv = (mps->mclk_rate / speed) - 1;
 	ccr |= (((bclkdiv & 0xff) << 16) | (((bclkdiv >> 8) & 0xff) << 8));
-	out_be32(&psc->ccr, ccr);
+	out_be32(psc_addr(mps, ccr), ccr);
 
 	/* Set 2ms DTL delay */
-	out_8(&psc->ctur, 0x00);
-	out_8(&psc->ctlr, 0x82);
+	out_8(psc_addr(mps, ctur), 0x00);
+	out_8(psc_addr(mps, ctlr), 0x82);
 
 	/* we don't use the alarms */
 	out_be32(&fifo->rxalarm, 0xfff);
@@ -482,6 +504,7 @@
 
 	dev_set_drvdata(dev, master);
 	mps = spi_master_get_devdata(master);
+	mps->type = (int)of_device_get_match_data(dev);
 	mps->irq = irq;
 
 	if (pdata == NULL) {
@@ -589,7 +612,8 @@
 }
 
 static const struct of_device_id mpc512x_psc_spi_of_match[] = {
-	{ .compatible = "fsl,mpc5121-psc-spi", },
+	{ .compatible = "fsl,mpc5121-psc-spi", .data = (void *)TYPE_MPC5121 },
+	{ .compatible = "fsl,mpc5125-psc-spi", .data = (void *)TYPE_MPC5125 },
 	{},
 };
 
diff --git a/drivers/spi/spi-mt65xx.c b/drivers/spi/spi-mt65xx.c
new file mode 100644
index 0000000..5f6315c
--- /dev/null
+++ b/drivers/spi/spi-mt65xx.c
@@ -0,0 +1,726 @@
+/*
+ * Copyright (c) 2015 MediaTek Inc.
+ * Author: Leilk Liu <leilk.liu@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/platform_data/spi-mt65xx.h>
+#include <linux/pm_runtime.h>
+#include <linux/spi/spi.h>
+
+#define SPI_CFG0_REG                      0x0000
+#define SPI_CFG1_REG                      0x0004
+#define SPI_TX_SRC_REG                    0x0008
+#define SPI_RX_DST_REG                    0x000c
+#define SPI_TX_DATA_REG                   0x0010
+#define SPI_RX_DATA_REG                   0x0014
+#define SPI_CMD_REG                       0x0018
+#define SPI_STATUS0_REG                   0x001c
+#define SPI_PAD_SEL_REG                   0x0024
+
+#define SPI_CFG0_SCK_HIGH_OFFSET          0
+#define SPI_CFG0_SCK_LOW_OFFSET           8
+#define SPI_CFG0_CS_HOLD_OFFSET           16
+#define SPI_CFG0_CS_SETUP_OFFSET          24
+
+#define SPI_CFG1_CS_IDLE_OFFSET           0
+#define SPI_CFG1_PACKET_LOOP_OFFSET       8
+#define SPI_CFG1_PACKET_LENGTH_OFFSET     16
+#define SPI_CFG1_GET_TICK_DLY_OFFSET      30
+
+#define SPI_CFG1_CS_IDLE_MASK             0xff
+#define SPI_CFG1_PACKET_LOOP_MASK         0xff00
+#define SPI_CFG1_PACKET_LENGTH_MASK       0x3ff0000
+
+#define SPI_CMD_ACT                  BIT(0)
+#define SPI_CMD_RESUME               BIT(1)
+#define SPI_CMD_RST                  BIT(2)
+#define SPI_CMD_PAUSE_EN             BIT(4)
+#define SPI_CMD_DEASSERT             BIT(5)
+#define SPI_CMD_CPHA                 BIT(8)
+#define SPI_CMD_CPOL                 BIT(9)
+#define SPI_CMD_RX_DMA               BIT(10)
+#define SPI_CMD_TX_DMA               BIT(11)
+#define SPI_CMD_TXMSBF               BIT(12)
+#define SPI_CMD_RXMSBF               BIT(13)
+#define SPI_CMD_RX_ENDIAN            BIT(14)
+#define SPI_CMD_TX_ENDIAN            BIT(15)
+#define SPI_CMD_FINISH_IE            BIT(16)
+#define SPI_CMD_PAUSE_IE             BIT(17)
+
+#define MT8173_SPI_MAX_PAD_SEL 3
+
+#define MTK_SPI_PAUSE_INT_STATUS 0x2
+
+#define MTK_SPI_IDLE 0
+#define MTK_SPI_PAUSED 1
+
+#define MTK_SPI_MAX_FIFO_SIZE 32
+#define MTK_SPI_PACKET_SIZE 1024
+
+struct mtk_spi_compatible {
+	bool need_pad_sel;
+	/* Must explicitly send dummy Tx bytes to do Rx only transfer */
+	bool must_tx;
+};
+
+struct mtk_spi {
+	void __iomem *base;
+	u32 state;
+	u32 pad_sel;
+	struct clk *spi_clk, *parent_clk;
+	struct spi_transfer *cur_transfer;
+	u32 xfer_len;
+	struct scatterlist *tx_sgl, *rx_sgl;
+	u32 tx_sgl_len, rx_sgl_len;
+	const struct mtk_spi_compatible *dev_comp;
+};
+
+static const struct mtk_spi_compatible mt6589_compat;
+static const struct mtk_spi_compatible mt8135_compat;
+static const struct mtk_spi_compatible mt8173_compat = {
+	.need_pad_sel = true,
+	.must_tx = true,
+};
+
+/*
+ * A piece of default chip info unless the platform
+ * supplies it.
+ */
+static const struct mtk_chip_config mtk_default_chip_info = {
+	.rx_mlsb = 1,
+	.tx_mlsb = 1,
+};
+
+static const struct of_device_id mtk_spi_of_match[] = {
+	{ .compatible = "mediatek,mt6589-spi", .data = (void *)&mt6589_compat },
+	{ .compatible = "mediatek,mt8135-spi", .data = (void *)&mt8135_compat },
+	{ .compatible = "mediatek,mt8173-spi", .data = (void *)&mt8173_compat },
+	{}
+};
+MODULE_DEVICE_TABLE(of, mtk_spi_of_match);
+
+static void mtk_spi_reset(struct mtk_spi *mdata)
+{
+	u32 reg_val;
+
+	/* set the software reset bit in SPI_CMD_REG. */
+	reg_val = readl(mdata->base + SPI_CMD_REG);
+	reg_val |= SPI_CMD_RST;
+	writel(reg_val, mdata->base + SPI_CMD_REG);
+
+	reg_val = readl(mdata->base + SPI_CMD_REG);
+	reg_val &= ~SPI_CMD_RST;
+	writel(reg_val, mdata->base + SPI_CMD_REG);
+}
+
+static void mtk_spi_config(struct mtk_spi *mdata,
+			   struct mtk_chip_config *chip_config)
+{
+	u32 reg_val;
+
+	reg_val = readl(mdata->base + SPI_CMD_REG);
+
+	/* set the mlsbx and mlsbtx */
+	if (chip_config->tx_mlsb)
+		reg_val |= SPI_CMD_TXMSBF;
+	else
+		reg_val &= ~SPI_CMD_TXMSBF;
+	if (chip_config->rx_mlsb)
+		reg_val |= SPI_CMD_RXMSBF;
+	else
+		reg_val &= ~SPI_CMD_RXMSBF;
+
+	/* set the tx/rx endian */
+#ifdef __LITTLE_ENDIAN
+	reg_val &= ~SPI_CMD_TX_ENDIAN;
+	reg_val &= ~SPI_CMD_RX_ENDIAN;
+#else
+	reg_val |= SPI_CMD_TX_ENDIAN;
+	reg_val |= SPI_CMD_RX_ENDIAN;
+#endif
+
+	/* set finish and pause interrupt always enable */
+	reg_val |= SPI_CMD_FINISH_IE | SPI_CMD_PAUSE_IE;
+
+	/* disable dma mode */
+	reg_val &= ~(SPI_CMD_TX_DMA | SPI_CMD_RX_DMA);
+
+	/* disable deassert mode */
+	reg_val &= ~SPI_CMD_DEASSERT;
+
+	writel(reg_val, mdata->base + SPI_CMD_REG);
+
+	/* pad select */
+	if (mdata->dev_comp->need_pad_sel)
+		writel(mdata->pad_sel, mdata->base + SPI_PAD_SEL_REG);
+}
+
+static int mtk_spi_prepare_hardware(struct spi_master *master)
+{
+	struct spi_transfer *trans;
+	struct mtk_spi *mdata = spi_master_get_devdata(master);
+	struct spi_message *msg = master->cur_msg;
+
+	trans = list_first_entry(&msg->transfers, struct spi_transfer,
+				 transfer_list);
+	if (!trans->cs_change) {
+		mdata->state = MTK_SPI_IDLE;
+		mtk_spi_reset(mdata);
+	}
+
+	return 0;
+}
+
+static int mtk_spi_prepare_message(struct spi_master *master,
+				   struct spi_message *msg)
+{
+	u32 reg_val;
+	u8 cpha, cpol;
+	struct mtk_chip_config *chip_config;
+	struct spi_device *spi = msg->spi;
+	struct mtk_spi *mdata = spi_master_get_devdata(master);
+
+	cpha = spi->mode & SPI_CPHA ? 1 : 0;
+	cpol = spi->mode & SPI_CPOL ? 1 : 0;
+
+	reg_val = readl(mdata->base + SPI_CMD_REG);
+	if (cpha)
+		reg_val |= SPI_CMD_CPHA;
+	else
+		reg_val &= ~SPI_CMD_CPHA;
+	if (cpol)
+		reg_val |= SPI_CMD_CPOL;
+	else
+		reg_val &= ~SPI_CMD_CPOL;
+	writel(reg_val, mdata->base + SPI_CMD_REG);
+
+	chip_config = spi->controller_data;
+	if (!chip_config) {
+		chip_config = (void *)&mtk_default_chip_info;
+		spi->controller_data = chip_config;
+	}
+	mtk_spi_config(mdata, chip_config);
+
+	return 0;
+}
+
+static void mtk_spi_set_cs(struct spi_device *spi, bool enable)
+{
+	u32 reg_val;
+	struct mtk_spi *mdata = spi_master_get_devdata(spi->master);
+
+	reg_val = readl(mdata->base + SPI_CMD_REG);
+	if (!enable)
+		reg_val |= SPI_CMD_PAUSE_EN;
+	else
+		reg_val &= ~SPI_CMD_PAUSE_EN;
+	writel(reg_val, mdata->base + SPI_CMD_REG);
+}
+
+static void mtk_spi_prepare_transfer(struct spi_master *master,
+				     struct spi_transfer *xfer)
+{
+	u32 spi_clk_hz, div, sck_time, cs_time, reg_val = 0;
+	struct mtk_spi *mdata = spi_master_get_devdata(master);
+
+	spi_clk_hz = clk_get_rate(mdata->spi_clk);
+	if (xfer->speed_hz < spi_clk_hz / 2)
+		div = DIV_ROUND_UP(spi_clk_hz, xfer->speed_hz);
+	else
+		div = 1;
+
+	sck_time = (div + 1) / 2;
+	cs_time = sck_time * 2;
+
+	reg_val |= (((sck_time - 1) & 0xff) << SPI_CFG0_SCK_HIGH_OFFSET);
+	reg_val |= (((sck_time - 1) & 0xff) << SPI_CFG0_SCK_LOW_OFFSET);
+	reg_val |= (((cs_time - 1) & 0xff) << SPI_CFG0_CS_HOLD_OFFSET);
+	reg_val |= (((cs_time - 1) & 0xff) << SPI_CFG0_CS_SETUP_OFFSET);
+	writel(reg_val, mdata->base + SPI_CFG0_REG);
+
+	reg_val = readl(mdata->base + SPI_CFG1_REG);
+	reg_val &= ~SPI_CFG1_CS_IDLE_MASK;
+	reg_val |= (((cs_time - 1) & 0xff) << SPI_CFG1_CS_IDLE_OFFSET);
+	writel(reg_val, mdata->base + SPI_CFG1_REG);
+}
+
+static void mtk_spi_setup_packet(struct spi_master *master)
+{
+	u32 packet_size, packet_loop, reg_val;
+	struct mtk_spi *mdata = spi_master_get_devdata(master);
+
+	packet_size = min_t(u32, mdata->xfer_len, MTK_SPI_PACKET_SIZE);
+	packet_loop = mdata->xfer_len / packet_size;
+
+	reg_val = readl(mdata->base + SPI_CFG1_REG);
+	reg_val &= ~(SPI_CFG1_PACKET_LENGTH_MASK | SPI_CFG1_PACKET_LOOP_MASK);
+	reg_val |= (packet_size - 1) << SPI_CFG1_PACKET_LENGTH_OFFSET;
+	reg_val |= (packet_loop - 1) << SPI_CFG1_PACKET_LOOP_OFFSET;
+	writel(reg_val, mdata->base + SPI_CFG1_REG);
+}
+
+static void mtk_spi_enable_transfer(struct spi_master *master)
+{
+	u32 cmd;
+	struct mtk_spi *mdata = spi_master_get_devdata(master);
+
+	cmd = readl(mdata->base + SPI_CMD_REG);
+	if (mdata->state == MTK_SPI_IDLE)
+		cmd |= SPI_CMD_ACT;
+	else
+		cmd |= SPI_CMD_RESUME;
+	writel(cmd, mdata->base + SPI_CMD_REG);
+}
+
+static int mtk_spi_get_mult_delta(u32 xfer_len)
+{
+	u32 mult_delta;
+
+	if (xfer_len > MTK_SPI_PACKET_SIZE)
+		mult_delta = xfer_len % MTK_SPI_PACKET_SIZE;
+	else
+		mult_delta = 0;
+
+	return mult_delta;
+}
+
+static void mtk_spi_update_mdata_len(struct spi_master *master)
+{
+	int mult_delta;
+	struct mtk_spi *mdata = spi_master_get_devdata(master);
+
+	if (mdata->tx_sgl_len && mdata->rx_sgl_len) {
+		if (mdata->tx_sgl_len > mdata->rx_sgl_len) {
+			mult_delta = mtk_spi_get_mult_delta(mdata->rx_sgl_len);
+			mdata->xfer_len = mdata->rx_sgl_len - mult_delta;
+			mdata->rx_sgl_len = mult_delta;
+			mdata->tx_sgl_len -= mdata->xfer_len;
+		} else {
+			mult_delta = mtk_spi_get_mult_delta(mdata->tx_sgl_len);
+			mdata->xfer_len = mdata->tx_sgl_len - mult_delta;
+			mdata->tx_sgl_len = mult_delta;
+			mdata->rx_sgl_len -= mdata->xfer_len;
+		}
+	} else if (mdata->tx_sgl_len) {
+		mult_delta = mtk_spi_get_mult_delta(mdata->tx_sgl_len);
+		mdata->xfer_len = mdata->tx_sgl_len - mult_delta;
+		mdata->tx_sgl_len = mult_delta;
+	} else if (mdata->rx_sgl_len) {
+		mult_delta = mtk_spi_get_mult_delta(mdata->rx_sgl_len);
+		mdata->xfer_len = mdata->rx_sgl_len - mult_delta;
+		mdata->rx_sgl_len = mult_delta;
+	}
+}
+
+static void mtk_spi_setup_dma_addr(struct spi_master *master,
+				   struct spi_transfer *xfer)
+{
+	struct mtk_spi *mdata = spi_master_get_devdata(master);
+
+	if (mdata->tx_sgl)
+		writel(xfer->tx_dma, mdata->base + SPI_TX_SRC_REG);
+	if (mdata->rx_sgl)
+		writel(xfer->rx_dma, mdata->base + SPI_RX_DST_REG);
+}
+
+static int mtk_spi_fifo_transfer(struct spi_master *master,
+				 struct spi_device *spi,
+				 struct spi_transfer *xfer)
+{
+	int cnt;
+	struct mtk_spi *mdata = spi_master_get_devdata(master);
+
+	mdata->cur_transfer = xfer;
+	mdata->xfer_len = xfer->len;
+	mtk_spi_prepare_transfer(master, xfer);
+	mtk_spi_setup_packet(master);
+
+	if (xfer->len % 4)
+		cnt = xfer->len / 4 + 1;
+	else
+		cnt = xfer->len / 4;
+	iowrite32_rep(mdata->base + SPI_TX_DATA_REG, xfer->tx_buf, cnt);
+
+	mtk_spi_enable_transfer(master);
+
+	return 1;
+}
+
+static int mtk_spi_dma_transfer(struct spi_master *master,
+				struct spi_device *spi,
+				struct spi_transfer *xfer)
+{
+	int cmd;
+	struct mtk_spi *mdata = spi_master_get_devdata(master);
+
+	mdata->tx_sgl = NULL;
+	mdata->rx_sgl = NULL;
+	mdata->tx_sgl_len = 0;
+	mdata->rx_sgl_len = 0;
+	mdata->cur_transfer = xfer;
+
+	mtk_spi_prepare_transfer(master, xfer);
+
+	cmd = readl(mdata->base + SPI_CMD_REG);
+	if (xfer->tx_buf)
+		cmd |= SPI_CMD_TX_DMA;
+	if (xfer->rx_buf)
+		cmd |= SPI_CMD_RX_DMA;
+	writel(cmd, mdata->base + SPI_CMD_REG);
+
+	if (xfer->tx_buf)
+		mdata->tx_sgl = xfer->tx_sg.sgl;
+	if (xfer->rx_buf)
+		mdata->rx_sgl = xfer->rx_sg.sgl;
+
+	if (mdata->tx_sgl) {
+		xfer->tx_dma = sg_dma_address(mdata->tx_sgl);
+		mdata->tx_sgl_len = sg_dma_len(mdata->tx_sgl);
+	}
+	if (mdata->rx_sgl) {
+		xfer->rx_dma = sg_dma_address(mdata->rx_sgl);
+		mdata->rx_sgl_len = sg_dma_len(mdata->rx_sgl);
+	}
+
+	mtk_spi_update_mdata_len(master);
+	mtk_spi_setup_packet(master);
+	mtk_spi_setup_dma_addr(master, xfer);
+	mtk_spi_enable_transfer(master);
+
+	return 1;
+}
+
+static int mtk_spi_transfer_one(struct spi_master *master,
+				struct spi_device *spi,
+				struct spi_transfer *xfer)
+{
+	if (master->can_dma(master, spi, xfer))
+		return mtk_spi_dma_transfer(master, spi, xfer);
+	else
+		return mtk_spi_fifo_transfer(master, spi, xfer);
+}
+
+static bool mtk_spi_can_dma(struct spi_master *master,
+			    struct spi_device *spi,
+			    struct spi_transfer *xfer)
+{
+	return xfer->len > MTK_SPI_MAX_FIFO_SIZE;
+}
+
+static irqreturn_t mtk_spi_interrupt(int irq, void *dev_id)
+{
+	u32 cmd, reg_val, cnt;
+	struct spi_master *master = dev_id;
+	struct mtk_spi *mdata = spi_master_get_devdata(master);
+	struct spi_transfer *trans = mdata->cur_transfer;
+
+	reg_val = readl(mdata->base + SPI_STATUS0_REG);
+	if (reg_val & MTK_SPI_PAUSE_INT_STATUS)
+		mdata->state = MTK_SPI_PAUSED;
+	else
+		mdata->state = MTK_SPI_IDLE;
+
+	if (!master->can_dma(master, master->cur_msg->spi, trans)) {
+		if (trans->rx_buf) {
+			if (mdata->xfer_len % 4)
+				cnt = mdata->xfer_len / 4 + 1;
+			else
+				cnt = mdata->xfer_len / 4;
+			ioread32_rep(mdata->base + SPI_RX_DATA_REG,
+				     trans->rx_buf, cnt);
+		}
+		spi_finalize_current_transfer(master);
+		return IRQ_HANDLED;
+	}
+
+	if (mdata->tx_sgl)
+		trans->tx_dma += mdata->xfer_len;
+	if (mdata->rx_sgl)
+		trans->rx_dma += mdata->xfer_len;
+
+	if (mdata->tx_sgl && (mdata->tx_sgl_len == 0)) {
+		mdata->tx_sgl = sg_next(mdata->tx_sgl);
+		if (mdata->tx_sgl) {
+			trans->tx_dma = sg_dma_address(mdata->tx_sgl);
+			mdata->tx_sgl_len = sg_dma_len(mdata->tx_sgl);
+		}
+	}
+	if (mdata->rx_sgl && (mdata->rx_sgl_len == 0)) {
+		mdata->rx_sgl = sg_next(mdata->rx_sgl);
+		if (mdata->rx_sgl) {
+			trans->rx_dma = sg_dma_address(mdata->rx_sgl);
+			mdata->rx_sgl_len = sg_dma_len(mdata->rx_sgl);
+		}
+	}
+
+	if (!mdata->tx_sgl && !mdata->rx_sgl) {
+		/* spi disable dma */
+		cmd = readl(mdata->base + SPI_CMD_REG);
+		cmd &= ~SPI_CMD_TX_DMA;
+		cmd &= ~SPI_CMD_RX_DMA;
+		writel(cmd, mdata->base + SPI_CMD_REG);
+
+		spi_finalize_current_transfer(master);
+		return IRQ_HANDLED;
+	}
+
+	mtk_spi_update_mdata_len(master);
+	mtk_spi_setup_packet(master);
+	mtk_spi_setup_dma_addr(master, trans);
+	mtk_spi_enable_transfer(master);
+
+	return IRQ_HANDLED;
+}
+
+static int mtk_spi_probe(struct platform_device *pdev)
+{
+	struct spi_master *master;
+	struct mtk_spi *mdata;
+	const struct of_device_id *of_id;
+	struct resource *res;
+	int irq, ret;
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*mdata));
+	if (!master) {
+		dev_err(&pdev->dev, "failed to alloc spi master\n");
+		return -ENOMEM;
+	}
+
+	master->auto_runtime_pm = true;
+	master->dev.of_node = pdev->dev.of_node;
+	master->mode_bits = SPI_CPOL | SPI_CPHA;
+
+	master->set_cs = mtk_spi_set_cs;
+	master->prepare_transfer_hardware = mtk_spi_prepare_hardware;
+	master->prepare_message = mtk_spi_prepare_message;
+	master->transfer_one = mtk_spi_transfer_one;
+	master->can_dma = mtk_spi_can_dma;
+
+	of_id = of_match_node(mtk_spi_of_match, pdev->dev.of_node);
+	if (!of_id) {
+		dev_err(&pdev->dev, "failed to probe of_node\n");
+		ret = -EINVAL;
+		goto err_put_master;
+	}
+
+	mdata = spi_master_get_devdata(master);
+	mdata->dev_comp = of_id->data;
+	if (mdata->dev_comp->must_tx)
+		master->flags = SPI_MASTER_MUST_TX;
+
+	if (mdata->dev_comp->need_pad_sel) {
+		ret = of_property_read_u32(pdev->dev.of_node,
+					   "mediatek,pad-select",
+					   &mdata->pad_sel);
+		if (ret) {
+			dev_err(&pdev->dev, "failed to read pad select: %d\n",
+				ret);
+			goto err_put_master;
+		}
+
+		if (mdata->pad_sel > MT8173_SPI_MAX_PAD_SEL) {
+			dev_err(&pdev->dev, "wrong pad-select: %u\n",
+				mdata->pad_sel);
+			ret = -EINVAL;
+			goto err_put_master;
+		}
+	}
+
+	platform_set_drvdata(pdev, master);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		ret = -ENODEV;
+		dev_err(&pdev->dev, "failed to determine base address\n");
+		goto err_put_master;
+	}
+
+	mdata->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(mdata->base)) {
+		ret = PTR_ERR(mdata->base);
+		goto err_put_master;
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "failed to get irq (%d)\n", irq);
+		ret = irq;
+		goto err_put_master;
+	}
+
+	if (!pdev->dev.dma_mask)
+		pdev->dev.dma_mask = &pdev->dev.coherent_dma_mask;
+
+	ret = devm_request_irq(&pdev->dev, irq, mtk_spi_interrupt,
+			       IRQF_TRIGGER_NONE, dev_name(&pdev->dev), master);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register irq (%d)\n", ret);
+		goto err_put_master;
+	}
+
+	mdata->spi_clk = devm_clk_get(&pdev->dev, "spi-clk");
+	if (IS_ERR(mdata->spi_clk)) {
+		ret = PTR_ERR(mdata->spi_clk);
+		dev_err(&pdev->dev, "failed to get spi-clk: %d\n", ret);
+		goto err_put_master;
+	}
+
+	mdata->parent_clk = devm_clk_get(&pdev->dev, "parent-clk");
+	if (IS_ERR(mdata->parent_clk)) {
+		ret = PTR_ERR(mdata->parent_clk);
+		dev_err(&pdev->dev, "failed to get parent-clk: %d\n", ret);
+		goto err_put_master;
+	}
+
+	ret = clk_prepare_enable(mdata->spi_clk);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to enable spi_clk (%d)\n", ret);
+		goto err_put_master;
+	}
+
+	ret = clk_set_parent(mdata->spi_clk, mdata->parent_clk);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to clk_set_parent (%d)\n", ret);
+		goto err_disable_clk;
+	}
+
+	clk_disable_unprepare(mdata->spi_clk);
+
+	pm_runtime_enable(&pdev->dev);
+
+	ret = devm_spi_register_master(&pdev->dev, master);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to register master (%d)\n", ret);
+		goto err_put_master;
+	}
+
+	return 0;
+
+err_disable_clk:
+	clk_disable_unprepare(mdata->spi_clk);
+err_put_master:
+	spi_master_put(master);
+
+	return ret;
+}
+
+static int mtk_spi_remove(struct platform_device *pdev)
+{
+	struct spi_master *master = platform_get_drvdata(pdev);
+	struct mtk_spi *mdata = spi_master_get_devdata(master);
+
+	pm_runtime_disable(&pdev->dev);
+
+	mtk_spi_reset(mdata);
+	clk_disable_unprepare(mdata->spi_clk);
+	spi_master_put(master);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM_SLEEP
+static int mtk_spi_suspend(struct device *dev)
+{
+	int ret;
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct mtk_spi *mdata = spi_master_get_devdata(master);
+
+	ret = spi_master_suspend(master);
+	if (ret)
+		return ret;
+
+	if (!pm_runtime_suspended(dev))
+		clk_disable_unprepare(mdata->spi_clk);
+
+	return ret;
+}
+
+static int mtk_spi_resume(struct device *dev)
+{
+	int ret;
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct mtk_spi *mdata = spi_master_get_devdata(master);
+
+	if (!pm_runtime_suspended(dev)) {
+		ret = clk_prepare_enable(mdata->spi_clk);
+		if (ret < 0) {
+			dev_err(dev, "failed to enable spi_clk (%d)\n", ret);
+			return ret;
+		}
+	}
+
+	ret = spi_master_resume(master);
+	if (ret < 0)
+		clk_disable_unprepare(mdata->spi_clk);
+
+	return ret;
+}
+#endif /* CONFIG_PM_SLEEP */
+
+#ifdef CONFIG_PM
+static int mtk_spi_runtime_suspend(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct mtk_spi *mdata = spi_master_get_devdata(master);
+
+	clk_disable_unprepare(mdata->spi_clk);
+
+	return 0;
+}
+
+static int mtk_spi_runtime_resume(struct device *dev)
+{
+	struct spi_master *master = dev_get_drvdata(dev);
+	struct mtk_spi *mdata = spi_master_get_devdata(master);
+	int ret;
+
+	ret = clk_prepare_enable(mdata->spi_clk);
+	if (ret < 0) {
+		dev_err(dev, "failed to enable spi_clk (%d)\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+#endif /* CONFIG_PM */
+
+static const struct dev_pm_ops mtk_spi_pm = {
+	SET_SYSTEM_SLEEP_PM_OPS(mtk_spi_suspend, mtk_spi_resume)
+	SET_RUNTIME_PM_OPS(mtk_spi_runtime_suspend,
+			   mtk_spi_runtime_resume, NULL)
+};
+
+static struct platform_driver mtk_spi_driver = {
+	.driver = {
+		.name = "mtk-spi",
+		.pm	= &mtk_spi_pm,
+		.of_match_table = mtk_spi_of_match,
+	},
+	.probe = mtk_spi_probe,
+	.remove = mtk_spi_remove,
+};
+
+module_platform_driver(mtk_spi_driver);
+
+MODULE_DESCRIPTION("MTK SPI Controller driver");
+MODULE_AUTHOR("Leilk Liu <leilk.liu@mediatek.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:mtk-spi");
diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 5867384..3d09e0b 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -245,6 +245,7 @@
 
 static void omap2_mcspi_set_cs(struct spi_device *spi, bool enable)
 {
+	struct omap2_mcspi *mcspi = spi_master_get_devdata(spi->master);
 	u32 l;
 
 	/* The controller handles the inverted chip selects
@@ -255,6 +256,12 @@
 		enable = !enable;
 
 	if (spi->controller_state) {
+		int err = pm_runtime_get_sync(mcspi->dev);
+		if (err < 0) {
+			dev_err(mcspi->dev, "failed to get sync: %d\n", err);
+			return;
+		}
+
 		l = mcspi_cached_chconf0(spi);
 
 		if (enable)
@@ -263,6 +270,9 @@
 			l |= OMAP2_MCSPI_CHCONF_FORCE;
 
 		mcspi_write_chconf0(spi, l);
+
+		pm_runtime_mark_last_busy(mcspi->dev);
+		pm_runtime_put_autosuspend(mcspi->dev);
 	}
 }
 
diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index 8cad107..a87cfd4 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -41,6 +41,11 @@
 #define ORION_SPI_DATA_OUT_REG		0x08
 #define ORION_SPI_DATA_IN_REG		0x0c
 #define ORION_SPI_INT_CAUSE_REG		0x10
+#define ORION_SPI_TIMING_PARAMS_REG	0x18
+
+#define ORION_SPI_TMISO_SAMPLE_MASK	(0x3 << 6)
+#define ORION_SPI_TMISO_SAMPLE_1	(1 << 6)
+#define ORION_SPI_TMISO_SAMPLE_2	(2 << 6)
 
 #define ORION_SPI_MODE_CPOL		(1 << 11)
 #define ORION_SPI_MODE_CPHA		(1 << 12)
@@ -70,6 +75,7 @@
 	unsigned int		min_divisor;
 	unsigned int		max_divisor;
 	u32			prescale_mask;
+	bool			is_errata_50mhz_ac;
 };
 
 struct orion_spi {
@@ -195,6 +201,41 @@
 	writel(reg, spi_reg(orion_spi, ORION_SPI_IF_CONFIG_REG));
 }
 
+static void
+orion_spi_50mhz_ac_timing_erratum(struct spi_device *spi, unsigned int speed)
+{
+	u32 reg;
+	struct orion_spi *orion_spi;
+
+	orion_spi = spi_master_get_devdata(spi->master);
+
+	/*
+	 * Erratum description: (Erratum NO. FE-9144572) The device
+	 * SPI interface supports frequencies of up to 50 MHz.
+	 * However, due to this erratum, when the device core clock is
+	 * 250 MHz and the SPI interfaces is configured for 50MHz SPI
+	 * clock and CPOL=CPHA=1 there might occur data corruption on
+	 * reads from the SPI device.
+	 * Erratum Workaround:
+	 * Work in one of the following configurations:
+	 * 1. Set CPOL=CPHA=0 in "SPI Interface Configuration
+	 * Register".
+	 * 2. Set TMISO_SAMPLE value to 0x2 in "SPI Timing Parameters 1
+	 * Register" before setting the interface.
+	 */
+	reg = readl(spi_reg(orion_spi, ORION_SPI_TIMING_PARAMS_REG));
+	reg &= ~ORION_SPI_TMISO_SAMPLE_MASK;
+
+	if (clk_get_rate(orion_spi->clk) == 250000000 &&
+			speed == 50000000 && spi->mode & SPI_CPOL &&
+			spi->mode & SPI_CPHA)
+		reg |= ORION_SPI_TMISO_SAMPLE_2;
+	else
+		reg |= ORION_SPI_TMISO_SAMPLE_1; /* This is the default value */
+
+	writel(reg, spi_reg(orion_spi, ORION_SPI_TIMING_PARAMS_REG));
+}
+
 /*
  * called only when no transfer is active on the bus
  */
@@ -216,6 +257,9 @@
 
 	orion_spi_mode_set(spi);
 
+	if (orion_spi->devdata->is_errata_50mhz_ac)
+		orion_spi_50mhz_ac_timing_erratum(spi, speed);
+
 	rc = orion_spi_baudrate_set(spi, speed);
 	if (rc)
 		return rc;
@@ -413,6 +457,14 @@
 	.prescale_mask = ARMADA_SPI_CLK_PRESCALE_MASK,
 };
 
+static const struct orion_spi_dev armada_380_spi_dev_data = {
+	.typ = ARMADA_SPI,
+	.max_hz = 50000000,
+	.max_divisor = 1920,
+	.prescale_mask = ARMADA_SPI_CLK_PRESCALE_MASK,
+	.is_errata_50mhz_ac = true,
+};
+
 static const struct of_device_id orion_spi_of_match_table[] = {
 	{
 		.compatible = "marvell,orion-spi",
@@ -428,7 +480,7 @@
 	},
 	{
 		.compatible = "marvell,armada-380-spi",
-		.data = &armada_xp_spi_dev_data,
+		.data = &armada_380_spi_dev_data,
 	},
 	{
 		.compatible = "marvell,armada-390-spi",
diff --git a/drivers/spi/spi-pxa2xx-pci.c b/drivers/spi/spi-pxa2xx-pci.c
index 3cfd435..d19d7f2 100644
--- a/drivers/spi/spi-pxa2xx-pci.c
+++ b/drivers/spi/spi-pxa2xx-pci.c
@@ -7,7 +7,6 @@
 #include <linux/of_device.h>
 #include <linux/module.h>
 #include <linux/spi/pxa2xx_spi.h>
-#include <linux/clk.h>
 #include <linux/clk-provider.h>
 
 #include <linux/dmaengine.h>
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 7293d6d..fdd79197 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -21,6 +21,7 @@
 #include <linux/err.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
+#include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/spi/pxa2xx_spi.h>
 #include <linux/spi/spi.h>
@@ -97,6 +98,15 @@
 		.tx_threshold_lo = 160,
 		.tx_threshold_hi = 224,
 	},
+	{	/* LPSS_SPT_SSP */
+		.offset = 0x200,
+		.reg_general = -1,
+		.reg_ssp = 0x20,
+		.reg_cs_ctrl = 0x24,
+		.rx_threshold = 1,
+		.tx_threshold_lo = 32,
+		.tx_threshold_hi = 56,
+	},
 };
 
 static inline const struct lpss_config
@@ -110,6 +120,7 @@
 	switch (drv_data->ssp_type) {
 	case LPSS_LPT_SSP:
 	case LPSS_BYT_SSP:
+	case LPSS_SPT_SSP:
 		return true;
 	default:
 		return false;
@@ -1107,6 +1118,7 @@
 		break;
 	case LPSS_LPT_SSP:
 	case LPSS_BYT_SSP:
+	case LPSS_SPT_SSP:
 		config = lpss_get_config(drv_data);
 		tx_thres = config->tx_threshold_lo;
 		tx_hi_thres = config->tx_threshold_hi;
@@ -1276,6 +1288,31 @@
 };
 MODULE_DEVICE_TABLE(acpi, pxa2xx_spi_acpi_match);
 
+/*
+ * PCI IDs of compound devices that integrate both host controller and private
+ * integrated DMA engine. Please note these are not used in module
+ * autoloading and probing in this module but matching the LPSS SSP type.
+ */
+static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = {
+	/* SPT-LP */
+	{ PCI_VDEVICE(INTEL, 0x9d29), LPSS_SPT_SSP },
+	{ PCI_VDEVICE(INTEL, 0x9d2a), LPSS_SPT_SSP },
+	/* SPT-H */
+	{ PCI_VDEVICE(INTEL, 0xa129), LPSS_SPT_SSP },
+	{ PCI_VDEVICE(INTEL, 0xa12a), LPSS_SPT_SSP },
+	{ },
+};
+
+static bool pxa2xx_spi_idma_filter(struct dma_chan *chan, void *param)
+{
+	struct device *dev = param;
+
+	if (dev != chan->device->dev->parent)
+		return false;
+
+	return true;
+}
+
 static struct pxa2xx_spi_master *
 pxa2xx_spi_acpi_get_pdata(struct platform_device *pdev)
 {
@@ -1283,16 +1320,25 @@
 	struct acpi_device *adev;
 	struct ssp_device *ssp;
 	struct resource *res;
-	const struct acpi_device_id *id;
+	const struct acpi_device_id *adev_id = NULL;
+	const struct pci_device_id *pcidev_id = NULL;
 	int devid, type;
 
 	if (!ACPI_HANDLE(&pdev->dev) ||
 	    acpi_bus_get_device(ACPI_HANDLE(&pdev->dev), &adev))
 		return NULL;
 
-	id = acpi_match_device(pdev->dev.driver->acpi_match_table, &pdev->dev);
-	if (id)
-		type = (int)id->driver_data;
+	if (dev_is_pci(pdev->dev.parent))
+		pcidev_id = pci_match_id(pxa2xx_spi_pci_compound_match,
+					 to_pci_dev(pdev->dev.parent));
+	else
+		adev_id = acpi_match_device(pdev->dev.driver->acpi_match_table,
+					    &pdev->dev);
+
+	if (adev_id)
+		type = (int)adev_id->driver_data;
+	else if (pcidev_id)
+		type = (int)pcidev_id->driver_data;
 	else
 		return NULL;
 
@@ -1311,6 +1357,12 @@
 	if (IS_ERR(ssp->mmio_base))
 		return NULL;
 
+	if (pcidev_id) {
+		pdata->tx_param = pdev->dev.parent;
+		pdata->rx_param = pdev->dev.parent;
+		pdata->dma_filter = pxa2xx_spi_idma_filter;
+	}
+
 	ssp->clk = devm_clk_get(&pdev->dev, NULL);
 	ssp->irq = platform_get_irq(pdev, 0);
 	ssp->type = type;
@@ -1362,8 +1414,7 @@
 		return -ENODEV;
 	}
 
-	/* Allocate master with space for drv_data and null dma buffer */
-	master = spi_alloc_master(dev, sizeof(struct driver_data) + 16);
+	master = spi_alloc_master(dev, sizeof(struct driver_data));
 	if (!master) {
 		dev_err(&pdev->dev, "cannot alloc spi_master\n");
 		pxa_ssp_free(ssp);
@@ -1390,7 +1441,6 @@
 	master->auto_runtime_pm = true;
 
 	drv_data->ssp_type = ssp->type;
-	drv_data->null_dma_buf = (u32 *)PTR_ALIGN(&drv_data[1], DMA_ALIGNMENT);
 
 	drv_data->ioaddr = ssp->mmio_base;
 	drv_data->ssdr_physical = ssp->phys_base + SSDR;
@@ -1424,8 +1474,6 @@
 	}
 
 	/* Setup DMA if requested */
-	drv_data->tx_channel = -1;
-	drv_data->rx_channel = -1;
 	if (platform_info->enable_dma) {
 		status = pxa2xx_spi_dma_setup(drv_data);
 		if (status) {
diff --git a/drivers/spi/spi-pxa2xx.h b/drivers/spi/spi-pxa2xx.h
index 9f01e9c..0a9b639 100644
--- a/drivers/spi/spi-pxa2xx.h
+++ b/drivers/spi/spi-pxa2xx.h
@@ -36,11 +36,6 @@
 	/* PXA hookup */
 	struct pxa2xx_spi_master *master_info;
 
-	/* PXA private DMA setup stuff */
-	int rx_channel;
-	int tx_channel;
-	u32 *null_dma_buf;
-
 	/* SSP register addresses */
 	void __iomem *ioaddr;
 	u32 ssdr_physical;
diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
index 68e7efe..79a8bc4 100644
--- a/drivers/spi/spi-rockchip.c
+++ b/drivers/spi/spi-rockchip.c
@@ -645,7 +645,6 @@
 	platform_set_drvdata(pdev, master);
 
 	rs = spi_master_get_devdata(master);
-	memset(rs, 0, sizeof(struct rockchip_spi));
 
 	/* Get basic io resource and map it */
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/spi/spi-rspi.c b/drivers/spi/spi-rspi.c
index f9189a0..8188433 100644
--- a/drivers/spi/spi-rspi.c
+++ b/drivers/spi/spi-rspi.c
@@ -383,7 +383,8 @@
 	rspi_write8(rspi, data, reg);
 }
 
-static int qspi_set_send_trigger(struct rspi_data *rspi, unsigned int len)
+static unsigned int qspi_set_send_trigger(struct rspi_data *rspi,
+					  unsigned int len)
 {
 	unsigned int n;
 
@@ -724,25 +725,25 @@
 static int qspi_trigger_transfer_out_in(struct rspi_data *rspi, const u8 *tx,
 					u8 *rx, unsigned int len)
 {
-	int i, n, ret;
-	int error;
+	unsigned int i, n;
+	int ret;
 
 	while (len > 0) {
 		n = qspi_set_send_trigger(rspi, len);
 		qspi_set_receive_trigger(rspi, len);
 		if (n == QSPI_BUFFER_SIZE) {
-			error = rspi_wait_for_tx_empty(rspi);
-			if (error < 0) {
+			ret = rspi_wait_for_tx_empty(rspi);
+			if (ret < 0) {
 				dev_err(&rspi->master->dev, "transmit timeout\n");
-				return error;
+				return ret;
 			}
 			for (i = 0; i < n; i++)
 				rspi_write_data(rspi, *tx++);
 
-			error = rspi_wait_for_rx_full(rspi);
-			if (error < 0) {
+			ret = rspi_wait_for_rx_full(rspi);
+			if (ret < 0) {
 				dev_err(&rspi->master->dev, "receive timeout\n");
-				return error;
+				return ret;
 			}
 			for (i = 0; i < n; i++)
 				*rx++ = rspi_read_data(rspi);
diff --git a/drivers/spi/spi-s3c24xx.c b/drivers/spi/spi-s3c24xx.c
index f747ca2..f36bc32 100644
--- a/drivers/spi/spi-s3c24xx.c
+++ b/drivers/spi/spi-s3c24xx.c
@@ -501,7 +501,6 @@
 	}
 
 	hw = spi_master_get_devdata(master);
-	memset(hw, 0, sizeof(struct s3c24xx_spi));
 
 	hw->master = master;
 	hw->pdata = pdata = dev_get_platdata(&pdev->dev);
diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c
index 2a8c513..cd1cfac 100644
--- a/drivers/spi/spi-s3c64xx.c
+++ b/drivers/spi/spi-s3c64xx.c
@@ -1191,8 +1191,8 @@
 
 	dev_dbg(&pdev->dev, "Samsung SoC SPI Driver loaded for Bus SPI-%d with %d Slaves attached\n",
 					sdd->port_id, master->num_chipselect);
-	dev_dbg(&pdev->dev, "\tIOmem=[%pR]\tDMA=[Rx-%d, Tx-%d]\n",
-					mem_res,
+	dev_dbg(&pdev->dev, "\tIOmem=[%pR]\tFIFO %dbytes\tDMA=[Rx-%d, Tx-%d]\n",
+					mem_res, (FIFO_LVL_MASK(sdd) >> 1) + 1,
 					sdd->rx_dma.dmach, sdd->tx_dma.dmach);
 
 	return 0;
diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index d3370a6..a7934ab 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -48,8 +48,8 @@
 	const struct sh_msiof_chipdata *chipdata;
 	struct sh_msiof_spi_info *info;
 	struct completion done;
-	int tx_fifo_size;
-	int rx_fifo_size;
+	unsigned int tx_fifo_size;
+	unsigned int rx_fifo_size;
 	void *tx_dma_page;
 	void *rx_dma_page;
 	dma_addr_t tx_dma_addr;
@@ -95,8 +95,6 @@
 #define MDR2_WDLEN1(i)	(((i) - 1) << 16) /* Word Count (1-64/256 (SH, A1))) */
 #define MDR2_GRPMASK1	0x00000001 /* Group Output Mask 1 (SH, A1) */
 
-#define MAX_WDLEN	256U
-
 /* TSCR and RSCR */
 #define SCR_BRPS_MASK	    0x1f00 /* Prescaler Setting (1-32) */
 #define SCR_BRPS(i)	(((i) - 1) << 8)
@@ -850,7 +848,12 @@
 		 *  DMA supports 32-bit words only, hence pack 8-bit and 16-bit
 		 *  words, with byte resp. word swapping.
 		 */
-		unsigned int l = min(len, MAX_WDLEN * 4);
+		unsigned int l = 0;
+
+		if (tx_buf)
+			l = min(len, p->tx_fifo_size * 4);
+		if (rx_buf)
+			l = min(len, p->rx_fifo_size * 4);
 
 		if (bits <= 8) {
 			if (l & 3)
@@ -963,7 +966,7 @@
 
 static const struct sh_msiof_chipdata r8a779x_data = {
 	.tx_fifo_size = 64,
-	.rx_fifo_size = 256,
+	.rx_fifo_size = 64,
 	.master_flags = SPI_MASTER_MUST_TX,
 };
 
@@ -1265,11 +1268,6 @@
 
 static const struct platform_device_id spi_driver_ids[] = {
 	{ "spi_sh_msiof",	(kernel_ulong_t)&sh_data },
-	{ "spi_r8a7790_msiof",	(kernel_ulong_t)&r8a779x_data },
-	{ "spi_r8a7791_msiof",	(kernel_ulong_t)&r8a779x_data },
-	{ "spi_r8a7792_msiof",	(kernel_ulong_t)&r8a779x_data },
-	{ "spi_r8a7793_msiof",	(kernel_ulong_t)&r8a779x_data },
-	{ "spi_r8a7794_msiof",	(kernel_ulong_t)&r8a779x_data },
 	{},
 };
 MODULE_DEVICE_TABLE(platform, spi_driver_ids);
diff --git a/drivers/spi/spi-xilinx.c b/drivers/spi/spi-xilinx.c
index 133f53a..a339c1e 100644
--- a/drivers/spi/spi-xilinx.c
+++ b/drivers/spi/spi-xilinx.c
@@ -249,19 +249,23 @@
 	xspi->tx_ptr = t->tx_buf;
 	xspi->rx_ptr = t->rx_buf;
 	remaining_words = t->len / xspi->bytes_per_word;
-	reinit_completion(&xspi->done);
 
 	if (xspi->irq >= 0 &&  remaining_words > xspi->buffer_size) {
+		u32 isr;
 		use_irq = true;
-		xspi->write_fn(XSPI_INTR_TX_EMPTY,
-				xspi->regs + XIPIF_V123B_IISR_OFFSET);
-		/* Enable the global IPIF interrupt */
-		xspi->write_fn(XIPIF_V123B_GINTR_ENABLE,
-				xspi->regs + XIPIF_V123B_DGIER_OFFSET);
 		/* Inhibit irq to avoid spurious irqs on tx_empty*/
 		cr = xspi->read_fn(xspi->regs + XSPI_CR_OFFSET);
 		xspi->write_fn(cr | XSPI_CR_TRANS_INHIBIT,
 			       xspi->regs + XSPI_CR_OFFSET);
+		/* ACK old irqs (if any) */
+		isr = xspi->read_fn(xspi->regs + XIPIF_V123B_IISR_OFFSET);
+		if (isr)
+			xspi->write_fn(isr,
+				       xspi->regs + XIPIF_V123B_IISR_OFFSET);
+		/* Enable the global IPIF interrupt */
+		xspi->write_fn(XIPIF_V123B_GINTR_ENABLE,
+				xspi->regs + XIPIF_V123B_DGIER_OFFSET);
+		reinit_completion(&xspi->done);
 	}
 
 	while (remaining_words) {
@@ -302,8 +306,10 @@
 		remaining_words -= n_words;
 	}
 
-	if (use_irq)
+	if (use_irq) {
 		xspi->write_fn(0, xspi->regs + XIPIF_V123B_DGIER_OFFSET);
+		xspi->write_fn(cr, xspi->regs + XSPI_CR_OFFSET);
+	}
 
 	return t->len;
 }
diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c
index 87b20a5..f23f36e 100644
--- a/drivers/spi/spi-zynqmp-gqspi.c
+++ b/drivers/spi/spi-zynqmp-gqspi.c
@@ -214,6 +214,7 @@
 	case GQSPI_SELECT_FLASH_CS_BOTH:
 		instanceptr->genfifocs = GQSPI_GENFIFO_CS_LOWER |
 			GQSPI_GENFIFO_CS_UPPER;
+		break;
 	case GQSPI_SELECT_FLASH_CS_UPPER:
 		instanceptr->genfifocs = GQSPI_GENFIFO_CS_UPPER;
 		break;
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 07476ca..3abb390 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -609,21 +609,30 @@
 		       enum dma_data_direction dir)
 {
 	const bool vmalloced_buf = is_vmalloc_addr(buf);
-	const int desc_len = vmalloced_buf ? PAGE_SIZE : master->max_dma_len;
-	const int sgs = DIV_ROUND_UP(len, desc_len);
+	int desc_len;
+	int sgs;
 	struct page *vm_page;
 	void *sg_buf;
 	size_t min;
 	int i, ret;
 
+	if (vmalloced_buf) {
+		desc_len = PAGE_SIZE;
+		sgs = DIV_ROUND_UP(len + offset_in_page(buf), desc_len);
+	} else {
+		desc_len = master->max_dma_len;
+		sgs = DIV_ROUND_UP(len, desc_len);
+	}
+
 	ret = sg_alloc_table(sgt, sgs, GFP_KERNEL);
 	if (ret != 0)
 		return ret;
 
 	for (i = 0; i < sgs; i++) {
-		min = min_t(size_t, len, desc_len);
 
 		if (vmalloced_buf) {
+			min = min_t(size_t,
+				    len, desc_len - offset_in_page(buf));
 			vm_page = vmalloc_to_page(buf);
 			if (!vm_page) {
 				sg_free_table(sgt);
@@ -632,6 +641,7 @@
 			sg_set_page(&sgt->sgl[i], vm_page,
 				    min, offset_in_page(buf));
 		} else {
+			min = min_t(size_t, len, desc_len);
 			sg_buf = buf;
 			sg_set_buf(&sgt->sgl[i], sg_buf, min);
 		}
@@ -672,8 +682,15 @@
 	if (!master->can_dma)
 		return 0;
 
-	tx_dev = master->dma_tx->device->dev;
-	rx_dev = master->dma_rx->device->dev;
+	if (master->dma_tx)
+		tx_dev = master->dma_tx->device->dev;
+	else
+		tx_dev = &master->dev;
+
+	if (master->dma_rx)
+		rx_dev = master->dma_rx->device->dev;
+	else
+		rx_dev = &master->dev;
 
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
 		if (!master->can_dma(master, msg->spi, xfer))
@@ -712,8 +729,15 @@
 	if (!master->cur_msg_mapped || !master->can_dma)
 		return 0;
 
-	tx_dev = master->dma_tx->device->dev;
-	rx_dev = master->dma_rx->device->dev;
+	if (master->dma_tx)
+		tx_dev = master->dma_tx->device->dev;
+	else
+		tx_dev = &master->dev;
+
+	if (master->dma_rx)
+		rx_dev = master->dma_rx->device->dev;
+	else
+		rx_dev = &master->dev;
 
 	list_for_each_entry(xfer, &msg->transfers, transfer_list) {
 		if (!master->can_dma(master, msg->spi, xfer))
@@ -1891,6 +1915,20 @@
  * other core methods are currently defined as inline functions.
  */
 
+static int __spi_validate_bits_per_word(struct spi_master *master, u8 bits_per_word)
+{
+	if (master->bits_per_word_mask) {
+		/* Only 32 bits fit in the mask */
+		if (bits_per_word > 32)
+			return -EINVAL;
+		if (!(master->bits_per_word_mask &
+				SPI_BPW_MASK(bits_per_word)))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 /**
  * spi_setup - setup SPI mode and clock rate
  * @spi: the device whose settings are being modified
@@ -1949,6 +1987,9 @@
 	if (!spi->bits_per_word)
 		spi->bits_per_word = 8;
 
+	if (__spi_validate_bits_per_word(spi->master, spi->bits_per_word))
+		return -EINVAL;
+
 	if (!spi->max_speed_hz)
 		spi->max_speed_hz = spi->master->max_speed_hz;
 
@@ -2011,19 +2052,15 @@
 
 		if (!xfer->speed_hz)
 			xfer->speed_hz = spi->max_speed_hz;
+		if (!xfer->speed_hz)
+			xfer->speed_hz = master->max_speed_hz;
 
 		if (master->max_speed_hz &&
 		    xfer->speed_hz > master->max_speed_hz)
 			xfer->speed_hz = master->max_speed_hz;
 
-		if (master->bits_per_word_mask) {
-			/* Only 32 bits fit in the mask */
-			if (xfer->bits_per_word > 32)
-				return -EINVAL;
-			if (!(master->bits_per_word_mask &
-					BIT(xfer->bits_per_word - 1)))
-				return -EINVAL;
-		}
+		if (__spi_validate_bits_per_word(master, xfer->bits_per_word))
+			return -EINVAL;
 
 		/*
 		 * SPI transfer length should be multiple of SPI word size
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index dd616ff..fba92a5 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -602,11 +602,11 @@
 	if (!spidev->tx_buffer) {
 		spidev->tx_buffer = kmalloc(bufsiz, GFP_KERNEL);
 		if (!spidev->tx_buffer) {
-				dev_dbg(&spidev->spi->dev, "open/ENOMEM\n");
-				status = -ENOMEM;
+			dev_dbg(&spidev->spi->dev, "open/ENOMEM\n");
+			status = -ENOMEM;
 			goto err_find_dev;
-			}
 		}
+	}
 
 	if (!spidev->rx_buffer) {
 		spidev->rx_buffer = kmalloc(bufsiz, GFP_KERNEL);
@@ -693,6 +693,7 @@
 #ifdef CONFIG_OF
 static const struct of_device_id spidev_dt_ids[] = {
 	{ .compatible = "rohm,dh2228fv" },
+	{ .compatible = "lineartechnology,ltc2488" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, spidev_dt_ids);
@@ -708,7 +709,7 @@
 
 	/*
 	 * spidev should never be referenced in DT without a specific
-	 * compatbile string, it is a Linux implementation thing
+	 * compatible string, it is a Linux implementation thing
 	 * rather than a description of the hardware.
 	 */
 	if (spi->dev.of_node && !of_match_device(spidev_dt_ids, &spi->dev)) {
diff --git a/drivers/staging/board/Kconfig b/drivers/staging/board/Kconfig
index b8ee818..3f287c4 100644
--- a/drivers/staging/board/Kconfig
+++ b/drivers/staging/board/Kconfig
@@ -1,6 +1,6 @@
 config STAGING_BOARD
 	bool "Staging Board Support"
-	depends on OF_ADDRESS
+	depends on OF_ADDRESS && OF_IRQ && CLKDEV_LOOKUP
 	help
 	  Select to enable per-board staging support code.
 
diff --git a/drivers/staging/comedi/drivers/das1800.c b/drivers/staging/comedi/drivers/das1800.c
index bfa4262..94078118 100644
--- a/drivers/staging/comedi/drivers/das1800.c
+++ b/drivers/staging/comedi/drivers/das1800.c
@@ -1266,6 +1266,7 @@
 		if (index == das1801hc || index == das1802hc)
 			return board;
 		index = das1801hc;
+		break;
 	default:
 		dev_err(dev->class_dev,
 			"Board model: probe returned 0x%x (unknown, please report)\n",
diff --git a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd.h b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd.h
index 7125eb9..8a9d4a0 100644
--- a/drivers/staging/lustre/lnet/klnds/socklnd/socklnd.h
+++ b/drivers/staging/lustre/lnet/klnds/socklnd/socklnd.h
@@ -31,7 +31,6 @@
 #define DEBUG_PORTAL_ALLOC
 #define DEBUG_SUBSYSTEM S_LND
 
-#include <asm/irq.h>
 #include <linux/crc32.h>
 #include <linux/errno.h>
 #include <linux/if.h>
diff --git a/drivers/staging/lustre/lustre/obdclass/debug.c b/drivers/staging/lustre/lustre/obdclass/debug.c
index 9c934e6..c61add4 100644
--- a/drivers/staging/lustre/lustre/obdclass/debug.c
+++ b/drivers/staging/lustre/lustre/obdclass/debug.c
@@ -40,7 +40,7 @@
 
 #define DEBUG_SUBSYSTEM D_OTHER
 
-#include <linux/unaligned/access_ok.h>
+#include <asm/unaligned.h>
 
 #include "../include/obd_support.h"
 #include "../include/lustre_debug.h"
diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c
index ed040fb..69bdc8f 100644
--- a/drivers/staging/vt6655/device_main.c
+++ b/drivers/staging/vt6655/device_main.c
@@ -1418,7 +1418,7 @@
 
 	priv->current_aid = conf->aid;
 
-	if (changed & BSS_CHANGED_BSSID) {
+	if (changed & BSS_CHANGED_BSSID && conf->bssid) {
 		unsigned long flags;
 
 		spin_lock_irqsave(&priv->lock, flags);
@@ -1483,8 +1483,9 @@
 		}
 	}
 
-	if (changed & BSS_CHANGED_ASSOC && priv->op_mode != NL80211_IFTYPE_AP) {
-		if (conf->assoc) {
+	if (changed & (BSS_CHANGED_ASSOC | BSS_CHANGED_BEACON_INFO) &&
+	    priv->op_mode != NL80211_IFTYPE_AP) {
+		if (conf->assoc && conf->beacon_rate) {
 			CARDbUpdateTSF(priv, conf->beacon_rate->hw_value,
 				       conf->sync_tsf);
 
diff --git a/drivers/staging/vt6656/main_usb.c b/drivers/staging/vt6656/main_usb.c
index f97323f..af572d7 100644
--- a/drivers/staging/vt6656/main_usb.c
+++ b/drivers/staging/vt6656/main_usb.c
@@ -701,7 +701,7 @@
 
 	priv->current_aid = conf->aid;
 
-	if (changed & BSS_CHANGED_BSSID)
+	if (changed & BSS_CHANGED_BSSID && conf->bssid)
 		vnt_mac_set_bssid_addr(priv, (u8 *)conf->bssid);
 
 
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 4e68b62..fd09290 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -968,9 +968,9 @@
 		cmd->cmd_flags |= ICF_NON_IMMEDIATE_UNSOLICITED_DATA;
 
 	conn->sess->init_task_tag = cmd->init_task_tag = hdr->itt;
-	if (hdr->flags & ISCSI_FLAG_CMD_READ) {
+	if (hdr->flags & ISCSI_FLAG_CMD_READ)
 		cmd->targ_xfer_tag = session_get_next_ttt(conn->sess);
-	} else if (hdr->flags & ISCSI_FLAG_CMD_WRITE)
+	else
 		cmd->targ_xfer_tag = 0xFFFFFFFF;
 	cmd->cmd_sn		= be32_to_cpu(hdr->cmdsn);
 	cmd->exp_stat_sn	= be32_to_cpu(hdr->exp_statsn);
@@ -3998,7 +3998,13 @@
 	}
 
 transport_err:
-	iscsit_take_action_for_connection_exit(conn);
+	/*
+	 * Avoid the normal connection failure code-path if this connection
+	 * is still within LOGIN mode, and iscsi_np process context is
+	 * responsible for cleaning up the early connection failure.
+	 */
+	if (conn->conn_state != TARG_CONN_STATE_IN_LOGIN)
+		iscsit_take_action_for_connection_exit(conn);
 out:
 	return 0;
 }
@@ -4082,7 +4088,7 @@
 
 int iscsi_target_rx_thread(void *arg)
 {
-	int ret;
+	int ret, rc;
 	u8 buffer[ISCSI_HDR_LEN], opcode;
 	u32 checksum = 0, digest = 0;
 	struct iscsi_conn *conn = arg;
@@ -4092,10 +4098,16 @@
 	 * connection recovery / failure event can be triggered externally.
 	 */
 	allow_signal(SIGINT);
+	/*
+	 * Wait for iscsi_post_login_handler() to complete before allowing
+	 * incoming iscsi/tcp socket I/O, and/or failing the connection.
+	 */
+	rc = wait_for_completion_interruptible(&conn->rx_login_comp);
+	if (rc < 0)
+		return 0;
 
 	if (conn->conn_transport->transport_type == ISCSI_INFINIBAND) {
 		struct completion comp;
-		int rc;
 
 		init_completion(&comp);
 		rc = wait_for_completion_interruptible(&comp);
@@ -4532,7 +4544,18 @@
 	struct iscsi_conn *conn)
 {
 	struct iscsi_session *sess = conn->sess;
-	int sleep = cmpxchg(&conn->tx_thread_active, true, false);
+	int sleep = 1;
+	/*
+	 * Traditional iscsi/tcp will invoke this logic from TX thread
+	 * context during session logout, so clear tx_thread_active and
+	 * sleep if iscsit_close_connection() has not already occured.
+	 *
+	 * Since iser-target invokes this logic from it's own workqueue,
+	 * always sleep waiting for RX/TX thread shutdown to complete
+	 * within iscsit_close_connection().
+	 */
+	if (conn->conn_transport->transport_type == ISCSI_TCP)
+		sleep = cmpxchg(&conn->tx_thread_active, true, false);
 
 	atomic_set(&conn->conn_logout_remove, 0);
 	complete(&conn->conn_logout_comp);
@@ -4546,7 +4569,10 @@
 static void iscsit_logout_post_handler_samecid(
 	struct iscsi_conn *conn)
 {
-	int sleep = cmpxchg(&conn->tx_thread_active, true, false);
+	int sleep = 1;
+
+	if (conn->conn_transport->transport_type == ISCSI_TCP)
+		sleep = cmpxchg(&conn->tx_thread_active, true, false);
 
 	atomic_set(&conn->conn_logout_remove, 0);
 	complete(&conn->conn_logout_comp);
@@ -4765,6 +4791,7 @@
 	struct iscsi_session *sess;
 	struct se_portal_group *se_tpg = &tpg->tpg_se_tpg;
 	struct se_session *se_sess, *se_sess_tmp;
+	LIST_HEAD(free_list);
 	int session_count = 0;
 
 	spin_lock_bh(&se_tpg->session_lock);
@@ -4786,15 +4813,18 @@
 		}
 		atomic_set(&sess->session_reinstatement, 1);
 		spin_unlock(&sess->conn_lock);
-		spin_unlock_bh(&se_tpg->session_lock);
 
-		iscsit_free_session(sess);
-		spin_lock_bh(&se_tpg->session_lock);
-
-		session_count++;
+		list_move_tail(&se_sess->sess_list, &free_list);
 	}
 	spin_unlock_bh(&se_tpg->session_lock);
 
+	list_for_each_entry_safe(se_sess, se_sess_tmp, &free_list, sess_list) {
+		sess = (struct iscsi_session *)se_sess->fabric_sess_ptr;
+
+		iscsit_free_session(sess);
+		session_count++;
+	}
+
 	pr_debug("Released %d iSCSI Session(s) from Target Portal"
 			" Group: %hu\n", session_count, tpg->tpgt);
 	return 0;
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 3d0fe4f..7e8f65e 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -82,6 +82,7 @@
 	init_completion(&conn->conn_logout_comp);
 	init_completion(&conn->rx_half_close_comp);
 	init_completion(&conn->tx_half_close_comp);
+	init_completion(&conn->rx_login_comp);
 	spin_lock_init(&conn->cmd_lock);
 	spin_lock_init(&conn->conn_usage_lock);
 	spin_lock_init(&conn->immed_queue_lock);
@@ -644,7 +645,7 @@
 		iscsit_start_nopin_timer(conn);
 }
 
-static int iscsit_start_kthreads(struct iscsi_conn *conn)
+int iscsit_start_kthreads(struct iscsi_conn *conn)
 {
 	int ret = 0;
 
@@ -679,6 +680,7 @@
 
 	return 0;
 out_tx:
+	send_sig(SIGINT, conn->tx_thread, 1);
 	kthread_stop(conn->tx_thread);
 	conn->tx_thread_active = false;
 out_bitmap:
@@ -689,7 +691,7 @@
 	return ret;
 }
 
-int iscsi_post_login_handler(
+void iscsi_post_login_handler(
 	struct iscsi_np *np,
 	struct iscsi_conn *conn,
 	u8 zero_tsih)
@@ -699,7 +701,6 @@
 	struct se_session *se_sess = sess->se_sess;
 	struct iscsi_portal_group *tpg = sess->tpg;
 	struct se_portal_group *se_tpg = &tpg->tpg_se_tpg;
-	int rc;
 
 	iscsit_inc_conn_usage_count(conn);
 
@@ -739,10 +740,6 @@
 			sess->sess_ops->InitiatorName);
 		spin_unlock_bh(&sess->conn_lock);
 
-		rc = iscsit_start_kthreads(conn);
-		if (rc)
-			return rc;
-
 		iscsi_post_login_start_timers(conn);
 		/*
 		 * Determine CPU mask to ensure connection's RX and TX kthreads
@@ -751,15 +748,20 @@
 		iscsit_thread_get_cpumask(conn);
 		conn->conn_rx_reset_cpumask = 1;
 		conn->conn_tx_reset_cpumask = 1;
-
+		/*
+		 * Wakeup the sleeping iscsi_target_rx_thread() now that
+		 * iscsi_conn is in TARG_CONN_STATE_LOGGED_IN state.
+		 */
+		complete(&conn->rx_login_comp);
 		iscsit_dec_conn_usage_count(conn);
+
 		if (stop_timer) {
 			spin_lock_bh(&se_tpg->session_lock);
 			iscsit_stop_time2retain_timer(sess);
 			spin_unlock_bh(&se_tpg->session_lock);
 		}
 		iscsit_dec_session_usage_count(sess);
-		return 0;
+		return;
 	}
 
 	iscsi_set_session_parameters(sess->sess_ops, conn->param_list, 1);
@@ -800,10 +802,6 @@
 		" iSCSI Target Portal Group: %hu\n", tpg->nsessions, tpg->tpgt);
 	spin_unlock_bh(&se_tpg->session_lock);
 
-	rc = iscsit_start_kthreads(conn);
-	if (rc)
-		return rc;
-
 	iscsi_post_login_start_timers(conn);
 	/*
 	 * Determine CPU mask to ensure connection's RX and TX kthreads
@@ -812,10 +810,12 @@
 	iscsit_thread_get_cpumask(conn);
 	conn->conn_rx_reset_cpumask = 1;
 	conn->conn_tx_reset_cpumask = 1;
-
+	/*
+	 * Wakeup the sleeping iscsi_target_rx_thread() now that
+	 * iscsi_conn is in TARG_CONN_STATE_LOGGED_IN state.
+	 */
+	complete(&conn->rx_login_comp);
 	iscsit_dec_conn_usage_count(conn);
-
-	return 0;
 }
 
 static void iscsi_handle_login_thread_timeout(unsigned long data)
@@ -1380,23 +1380,12 @@
 	if (ret < 0)
 		goto new_sess_out;
 
-	if (!conn->sess) {
-		pr_err("struct iscsi_conn session pointer is NULL!\n");
-		goto new_sess_out;
-	}
-
 	iscsi_stop_login_thread_timer(np);
 
-	if (signal_pending(current))
-		goto new_sess_out;
-
 	if (ret == 1) {
 		tpg_np = conn->tpg_np;
 
-		ret = iscsi_post_login_handler(np, conn, zero_tsih);
-		if (ret < 0)
-			goto new_sess_out;
-
+		iscsi_post_login_handler(np, conn, zero_tsih);
 		iscsit_deaccess_np(np, tpg, tpg_np);
 	}
 
diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h
index 1c73580..57aa0d0 100644
--- a/drivers/target/iscsi/iscsi_target_login.h
+++ b/drivers/target/iscsi/iscsi_target_login.h
@@ -12,7 +12,8 @@
 extern int iscsit_get_login_rx(struct iscsi_conn *, struct iscsi_login *);
 extern int iscsit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32);
 extern void iscsit_free_conn(struct iscsi_np *, struct iscsi_conn *);
-extern int iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8);
+extern int iscsit_start_kthreads(struct iscsi_conn *);
+extern void iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8);
 extern void iscsi_target_login_sess_out(struct iscsi_conn *, struct iscsi_np *,
 				bool, bool);
 extern int iscsi_target_login_thread(void *);
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 8c02fa3..f9cde91 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -17,6 +17,7 @@
  ******************************************************************************/
 
 #include <linux/ctype.h>
+#include <linux/kthread.h>
 #include <scsi/iscsi_proto.h>
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
@@ -361,10 +362,24 @@
 		ntohl(login_rsp->statsn), login->rsp_length);
 
 	padding = ((-login->rsp_length) & 3);
+	/*
+	 * Before sending the last login response containing the transition
+	 * bit for full-feature-phase, go ahead and start up TX/RX threads
+	 * now to avoid potential resource allocation failures after the
+	 * final login response has been sent.
+	 */
+	if (login->login_complete) {
+		int rc = iscsit_start_kthreads(conn);
+		if (rc) {
+			iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
+					    ISCSI_LOGIN_STATUS_NO_RESOURCES);
+			return -1;
+		}
+	}
 
 	if (conn->conn_transport->iscsit_put_login_tx(conn, login,
 					login->rsp_length + padding) < 0)
-		return -1;
+		goto err;
 
 	login->rsp_length		= 0;
 	mutex_lock(&sess->cmdsn_mutex);
@@ -373,6 +388,23 @@
 	mutex_unlock(&sess->cmdsn_mutex);
 
 	return 0;
+
+err:
+	if (login->login_complete) {
+		if (conn->rx_thread && conn->rx_thread_active) {
+			send_sig(SIGINT, conn->rx_thread, 1);
+			kthread_stop(conn->rx_thread);
+		}
+		if (conn->tx_thread && conn->tx_thread_active) {
+			send_sig(SIGINT, conn->tx_thread, 1);
+			kthread_stop(conn->tx_thread);
+		}
+		spin_lock(&iscsit_global->ts_bitmap_lock);
+		bitmap_release_region(iscsit_global->ts_bitmap, conn->bitmap_id,
+				      get_order(1));
+		spin_unlock(&iscsit_global->ts_bitmap_lock);
+	}
+	return -1;
 }
 
 static void iscsi_target_sk_data_ready(struct sock *sk)
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 0b0de36..860e840 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -457,8 +457,15 @@
 		if (!strcmp(t->tf_ops->name, fo->name)) {
 			BUG_ON(atomic_read(&t->tf_access_cnt));
 			list_del(&t->tf_list);
+			mutex_unlock(&g_tf_lock);
+			/*
+			 * Wait for any outstanding fabric se_deve_entry->rcu_head
+			 * callbacks to complete post kfree_rcu(), before allowing
+			 * fabric driver unload of TFO->module to proceed.
+			 */
+			rcu_barrier();
 			kfree(t);
-			break;
+			return;
 		}
 	}
 	mutex_unlock(&g_tf_lock);
@@ -747,7 +754,7 @@
 	if (!dev->transport->init_prot || !dev->transport->free_prot) {
 		/* 0 is only allowed value for non-supporting backends */
 		if (flag == 0)
-			return 0;
+			return count;
 
 		pr_err("DIF protection not supported by backend: %s\n",
 		       dev->transport->name);
@@ -1590,9 +1597,9 @@
 	u8 type = 0;
 
 	if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
-		return 0;
+		return count;
 	if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
-		return 0;
+		return count;
 
 	if (dev->export_count) {
 		pr_debug("Unable to process APTPL metadata while"
@@ -1658,22 +1665,32 @@
 		 * PR APTPL Metadata for Reservation
 		 */
 		case Opt_res_holder:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			res_holder = arg;
 			break;
 		case Opt_res_type:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			type = (u8)arg;
 			break;
 		case Opt_res_scope:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			break;
 		case Opt_res_all_tg_pt:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			all_tg_pt = (int)arg;
 			break;
 		case Opt_mapped_lun:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			mapped_lun = (u64)arg;
 			break;
 		/*
@@ -1701,14 +1718,20 @@
 			}
 			break;
 		case Opt_tpgt:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			tpgt = (u16)arg;
 			break;
 		case Opt_port_rtpi:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			break;
 		case Opt_target_lun:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			target_lun = (u64)arg;
 			break;
 		default:
@@ -1985,7 +2008,7 @@
 
 	lu_gp_mem = dev->dev_alua_lu_gp_mem;
 	if (!lu_gp_mem)
-		return 0;
+		return count;
 
 	if (count > LU_GROUP_NAME_BUF) {
 		pr_err("ALUA LU Group Alias too large!\n");
diff --git a/drivers/target/target_core_hba.c b/drivers/target/target_core_hba.c
index 62ea4e8..be9cefc 100644
--- a/drivers/target/target_core_hba.c
+++ b/drivers/target/target_core_hba.c
@@ -84,8 +84,16 @@
 	list_for_each_entry(tb, &backend_list, list) {
 		if (tb->ops == ops) {
 			list_del(&tb->list);
+			mutex_unlock(&backend_mutex);
+			/*
+			 * Wait for any outstanding backend driver ->rcu_head
+			 * callbacks to complete post TBO->free_device() ->
+			 * call_rcu(), before allowing backend driver module
+			 * unload of target_backend_ops->owner to proceed.
+			 */
+			rcu_barrier();
 			kfree(tb);
-			break;
+			return;
 		}
 	}
 	mutex_unlock(&backend_mutex);
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 0fdbe43..5ab7100 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -1474,7 +1474,7 @@
 	LIST_HEAD(tid_dest_list);
 	struct pr_transport_id_holder *tidh_new, *tidh, *tidh_tmp;
 	unsigned char *buf, *ptr, proto_ident;
-	const unsigned char *i_str;
+	const unsigned char *i_str = NULL;
 	char *iport_ptr = NULL, i_buf[PR_REG_ISID_ID_LEN];
 	sense_reason_t ret;
 	u32 tpdl, tid_len = 0;
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index 4703f40..384cf88 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -333,6 +333,7 @@
 	dev->dev_attrib.hw_block_size = RD_BLOCKSIZE;
 	dev->dev_attrib.hw_max_sectors = UINT_MAX;
 	dev->dev_attrib.hw_queue_depth = RD_MAX_DEVICE_QUEUE_DEPTH;
+	dev->dev_attrib.is_nonrot = 1;
 
 	rd_dev->rd_dev_id = rd_host->rd_host_dev_id_count++;
 
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index b074443..f87d4ce 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -454,10 +454,17 @@
 		    cmd->se_sess->sess_prot_type == TARGET_DIF_TYPE1_PROT)
 			buf[4] = 0x5;
 		else if (dev->dev_attrib.pi_prot_type == TARGET_DIF_TYPE3_PROT ||
-			cmd->se_sess->sess_prot_type == TARGET_DIF_TYPE3_PROT)
+			 cmd->se_sess->sess_prot_type == TARGET_DIF_TYPE3_PROT)
 			buf[4] = 0x4;
 	}
 
+	/* logical unit supports type 1 and type 3 protection */
+	if ((dev->transport->get_device_type(dev) == TYPE_DISK) &&
+	    (sess->sup_prot_ops & (TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS)) &&
+	    (dev->dev_attrib.pi_prot_type || cmd->se_sess->sess_prot_type)) {
+		buf[4] |= (0x3 << 3);
+	}
+
 	/* Set HEADSUP, ORDSUP, SIMPSUP */
 	buf[5] = 0x07;
 
@@ -1196,17 +1203,13 @@
 	struct se_dev_entry *deve;
 	struct se_session *sess = cmd->se_sess;
 	struct se_node_acl *nacl;
+	struct scsi_lun slun;
 	unsigned char *buf;
 	u32 lun_count = 0, offset = 8;
-
-	if (cmd->data_length < 16) {
-		pr_warn("REPORT LUNS allocation length %u too small\n",
-			cmd->data_length);
-		return TCM_INVALID_CDB_FIELD;
-	}
+	__be32 len;
 
 	buf = transport_kmap_data_sg(cmd);
-	if (!buf)
+	if (cmd->data_length && !buf)
 		return TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE;
 
 	/*
@@ -1214,11 +1217,9 @@
 	 * coming via a target_core_mod PASSTHROUGH op, and not through
 	 * a $FABRIC_MOD.  In that case, report LUN=0 only.
 	 */
-	if (!sess) {
-		int_to_scsilun(0, (struct scsi_lun *)&buf[offset]);
-		lun_count = 1;
+	if (!sess)
 		goto done;
-	}
+
 	nacl = sess->se_node_acl;
 
 	rcu_read_lock();
@@ -1229,10 +1230,12 @@
 		 * See SPC2-R20 7.19.
 		 */
 		lun_count++;
-		if ((offset + 8) > cmd->data_length)
+		if (offset >= cmd->data_length)
 			continue;
 
-		int_to_scsilun(deve->mapped_lun, (struct scsi_lun *)&buf[offset]);
+		int_to_scsilun(deve->mapped_lun, &slun);
+		memcpy(buf + offset, &slun,
+		       min(8u, cmd->data_length - offset));
 		offset += 8;
 	}
 	rcu_read_unlock();
@@ -1241,12 +1244,22 @@
 	 * See SPC3 r07, page 159.
 	 */
 done:
-	lun_count *= 8;
-	buf[0] = ((lun_count >> 24) & 0xff);
-	buf[1] = ((lun_count >> 16) & 0xff);
-	buf[2] = ((lun_count >> 8) & 0xff);
-	buf[3] = (lun_count & 0xff);
-	transport_kunmap_data_sg(cmd);
+	/*
+	 * If no LUNs are accessible, report virtual LUN 0.
+	 */
+	if (lun_count == 0) {
+		int_to_scsilun(0, &slun);
+		if (cmd->data_length > 8)
+			memcpy(buf + offset, &slun,
+			       min(8u, cmd->data_length - offset));
+		lun_count = 1;
+	}
+
+	if (buf) {
+		len = cpu_to_be32(lun_count * 8);
+		memcpy(buf, &len, min_t(int, sizeof len, cmd->data_length));
+		transport_kunmap_data_sg(cmd);
+	}
 
 	target_complete_cmd_with_length(cmd, GOOD, 8 + lun_count * 8);
 	return 0;
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 6509c61..620dcd4 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -68,7 +68,7 @@
  *	registered cooling device.
  * @cpufreq_state: integer value representing the current state of cpufreq
  *	cooling	devices.
- * @cpufreq_val: integer value representing the absolute value of the clipped
+ * @clipped_freq: integer value representing the absolute value of the clipped
  *	frequency.
  * @max_level: maximum cooling level. One less than total number of valid
  *	cpufreq frequencies.
@@ -91,7 +91,7 @@
 	int id;
 	struct thermal_cooling_device *cool_dev;
 	unsigned int cpufreq_state;
-	unsigned int cpufreq_val;
+	unsigned int clipped_freq;
 	unsigned int max_level;
 	unsigned int *freq_table;	/* In descending order */
 	struct cpumask allowed_cpus;
@@ -107,6 +107,9 @@
 static DEFINE_IDR(cpufreq_idr);
 static DEFINE_MUTEX(cooling_cpufreq_lock);
 
+static unsigned int cpufreq_dev_count;
+
+static DEFINE_MUTEX(cooling_list_lock);
 static LIST_HEAD(cpufreq_dev_list);
 
 /**
@@ -185,14 +188,14 @@
 {
 	struct cpufreq_cooling_device *cpufreq_dev;
 
-	mutex_lock(&cooling_cpufreq_lock);
+	mutex_lock(&cooling_list_lock);
 	list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
 		if (cpumask_test_cpu(cpu, &cpufreq_dev->allowed_cpus)) {
-			mutex_unlock(&cooling_cpufreq_lock);
+			mutex_unlock(&cooling_list_lock);
 			return get_level(cpufreq_dev, freq);
 		}
 	}
-	mutex_unlock(&cooling_cpufreq_lock);
+	mutex_unlock(&cooling_list_lock);
 
 	pr_err("%s: cpu:%d not part of any cooling device\n", __func__, cpu);
 	return THERMAL_CSTATE_INVALID;
@@ -215,29 +218,35 @@
 				    unsigned long event, void *data)
 {
 	struct cpufreq_policy *policy = data;
-	unsigned long max_freq = 0;
+	unsigned long clipped_freq;
 	struct cpufreq_cooling_device *cpufreq_dev;
 
-	switch (event) {
-
-	case CPUFREQ_ADJUST:
-		mutex_lock(&cooling_cpufreq_lock);
-		list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
-			if (!cpumask_test_cpu(policy->cpu,
-					      &cpufreq_dev->allowed_cpus))
-				continue;
-
-			max_freq = cpufreq_dev->cpufreq_val;
-
-			if (policy->max != max_freq)
-				cpufreq_verify_within_limits(policy, 0,
-							     max_freq);
-		}
-		mutex_unlock(&cooling_cpufreq_lock);
-		break;
-	default:
+	if (event != CPUFREQ_ADJUST)
 		return NOTIFY_DONE;
+
+	mutex_lock(&cooling_list_lock);
+	list_for_each_entry(cpufreq_dev, &cpufreq_dev_list, node) {
+		if (!cpumask_test_cpu(policy->cpu, &cpufreq_dev->allowed_cpus))
+			continue;
+
+		/*
+		 * policy->max is the maximum allowed frequency defined by user
+		 * and clipped_freq is the maximum that thermal constraints
+		 * allow.
+		 *
+		 * If clipped_freq is lower than policy->max, then we need to
+		 * readjust policy->max.
+		 *
+		 * But, if clipped_freq is greater than policy->max, we don't
+		 * need to do anything.
+		 */
+		clipped_freq = cpufreq_dev->clipped_freq;
+
+		if (policy->max > clipped_freq)
+			cpufreq_verify_within_limits(policy, 0, clipped_freq);
+		break;
 	}
+	mutex_unlock(&cooling_list_lock);
 
 	return NOTIFY_OK;
 }
@@ -519,7 +528,7 @@
 
 	clip_freq = cpufreq_device->freq_table[state];
 	cpufreq_device->cpufreq_state = state;
-	cpufreq_device->cpufreq_val = clip_freq;
+	cpufreq_device->clipped_freq = clip_freq;
 
 	cpufreq_update_policy(cpu);
 
@@ -861,17 +870,19 @@
 			pr_debug("%s: freq:%u KHz\n", __func__, freq);
 	}
 
-	cpufreq_dev->cpufreq_val = cpufreq_dev->freq_table[0];
+	cpufreq_dev->clipped_freq = cpufreq_dev->freq_table[0];
 	cpufreq_dev->cool_dev = cool_dev;
 
 	mutex_lock(&cooling_cpufreq_lock);
 
+	mutex_lock(&cooling_list_lock);
+	list_add(&cpufreq_dev->node, &cpufreq_dev_list);
+	mutex_unlock(&cooling_list_lock);
+
 	/* Register the notifier for first cpufreq cooling device */
-	if (list_empty(&cpufreq_dev_list))
+	if (!cpufreq_dev_count++)
 		cpufreq_register_notifier(&thermal_cpufreq_notifier_block,
 					  CPUFREQ_POLICY_NOTIFIER);
-	list_add(&cpufreq_dev->node, &cpufreq_dev_list);
-
 	mutex_unlock(&cooling_cpufreq_lock);
 
 	return cool_dev;
@@ -1013,13 +1024,17 @@
 		return;
 
 	cpufreq_dev = cdev->devdata;
-	mutex_lock(&cooling_cpufreq_lock);
-	list_del(&cpufreq_dev->node);
 
 	/* Unregister the notifier for the last cpufreq cooling device */
-	if (list_empty(&cpufreq_dev_list))
+	mutex_lock(&cooling_cpufreq_lock);
+	if (!--cpufreq_dev_count)
 		cpufreq_unregister_notifier(&thermal_cpufreq_notifier_block,
 					    CPUFREQ_POLICY_NOTIFIER);
+
+	mutex_lock(&cooling_list_lock);
+	list_del(&cpufreq_dev->node);
+	mutex_unlock(&cooling_list_lock);
+
 	mutex_unlock(&cooling_cpufreq_lock);
 
 	thermal_cooling_device_unregister(cpufreq_dev->cool_dev);
diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c
index d5dd357..b49f97c 100644
--- a/drivers/thermal/hisi_thermal.c
+++ b/drivers/thermal/hisi_thermal.c
@@ -405,7 +405,6 @@
 static struct platform_driver hisi_thermal_driver = {
 	.driver = {
 		.name		= "hisi_thermal",
-		.owner		= THIS_MODULE,
 		.pm		= &hisi_thermal_pm_ops,
 		.of_match_table = of_hisi_thermal_match,
 	},
diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c
index 4672250..7006860 100644
--- a/drivers/thermal/power_allocator.c
+++ b/drivers/thermal/power_allocator.c
@@ -229,7 +229,8 @@
 	struct thermal_instance *instance;
 	struct power_allocator_params *params = tz->governor_data;
 	u32 *req_power, *max_power, *granted_power, *extra_actor_power;
-	u32 total_req_power, max_allocatable_power;
+	u32 *weighted_req_power;
+	u32 total_req_power, max_allocatable_power, total_weighted_req_power;
 	u32 total_granted_power, power_range;
 	int i, num_actors, total_weight, ret = 0;
 	int trip_max_desired_temperature = params->trip_max_desired_temperature;
@@ -247,16 +248,17 @@
 	}
 
 	/*
-	 * We need to allocate three arrays of the same size:
-	 * req_power, max_power and granted_power.  They are going to
-	 * be needed until this function returns.  Allocate them all
-	 * in one go to simplify the allocation and deallocation
-	 * logic.
+	 * We need to allocate five arrays of the same size:
+	 * req_power, max_power, granted_power, extra_actor_power and
+	 * weighted_req_power.  They are going to be needed until this
+	 * function returns.  Allocate them all in one go to simplify
+	 * the allocation and deallocation logic.
 	 */
 	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*max_power));
 	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*granted_power));
 	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*extra_actor_power));
-	req_power = devm_kcalloc(&tz->device, num_actors * 4,
+	BUILD_BUG_ON(sizeof(*req_power) != sizeof(*weighted_req_power));
+	req_power = devm_kcalloc(&tz->device, num_actors * 5,
 				 sizeof(*req_power), GFP_KERNEL);
 	if (!req_power) {
 		ret = -ENOMEM;
@@ -266,8 +268,10 @@
 	max_power = &req_power[num_actors];
 	granted_power = &req_power[2 * num_actors];
 	extra_actor_power = &req_power[3 * num_actors];
+	weighted_req_power = &req_power[4 * num_actors];
 
 	i = 0;
+	total_weighted_req_power = 0;
 	total_req_power = 0;
 	max_allocatable_power = 0;
 
@@ -289,13 +293,14 @@
 		else
 			weight = instance->weight;
 
-		req_power[i] = frac_to_int(weight * req_power[i]);
+		weighted_req_power[i] = frac_to_int(weight * req_power[i]);
 
 		if (power_actor_get_max_power(cdev, tz, &max_power[i]))
 			continue;
 
 		total_req_power += req_power[i];
 		max_allocatable_power += max_power[i];
+		total_weighted_req_power += weighted_req_power[i];
 
 		i++;
 	}
@@ -303,8 +308,9 @@
 	power_range = pid_controller(tz, current_temp, control_temp,
 				     max_allocatable_power);
 
-	divvy_up_power(req_power, max_power, num_actors, total_req_power,
-		       power_range, granted_power, extra_actor_power);
+	divvy_up_power(weighted_req_power, max_power, num_actors,
+		       total_weighted_req_power, power_range, granted_power,
+		       extra_actor_power);
 
 	total_granted_power = 0;
 	i = 0;
@@ -328,7 +334,7 @@
 				      max_allocatable_power, current_temp,
 				      (s32)control_temp - (s32)current_temp);
 
-	devm_kfree(&tz->device, req_power);
+	kfree(req_power);
 unlock:
 	mutex_unlock(&tz->lock);
 
@@ -420,7 +426,7 @@
 		return -EINVAL;
 	}
 
-	params = devm_kzalloc(&tz->device, sizeof(*params), GFP_KERNEL);
+	params = kzalloc(sizeof(*params), GFP_KERNEL);
 	if (!params)
 		return -ENOMEM;
 
@@ -462,14 +468,14 @@
 	return 0;
 
 free:
-	devm_kfree(&tz->device, params);
+	kfree(params);
 	return ret;
 }
 
 static void power_allocator_unbind(struct thermal_zone_device *tz)
 {
 	dev_dbg(&tz->device, "Unbinding from thermal zone %d\n", tz->id);
-	devm_kfree(&tz->device, tz->governor_data);
+	kfree(tz->governor_data);
 	tz->governor_data = NULL;
 }
 
diff --git a/drivers/thermal/samsung/Kconfig b/drivers/thermal/samsung/Kconfig
index c8e35c1..e0da386 100644
--- a/drivers/thermal/samsung/Kconfig
+++ b/drivers/thermal/samsung/Kconfig
@@ -1,6 +1,6 @@
 config EXYNOS_THERMAL
 	tristate "Exynos thermal management unit driver"
-	depends on OF
+	depends on THERMAL_OF
 	help
 	  If you say yes here you get support for the TMU (Thermal Management
 	  Unit) driver for SAMSUNG EXYNOS series of SoCs. This driver initialises
diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c
index 531f4b17..c96ff10 100644
--- a/drivers/thermal/samsung/exynos_tmu.c
+++ b/drivers/thermal/samsung/exynos_tmu.c
@@ -1296,7 +1296,6 @@
 
 static int exynos_tmu_probe(struct platform_device *pdev)
 {
-	struct exynos_tmu_platform_data *pdata;
 	struct exynos_tmu_data *data;
 	int ret;
 
@@ -1318,8 +1317,6 @@
 	if (ret)
 		goto err_sensor;
 
-	pdata = data->pdata;
-
 	INIT_WORK(&data->irq_work, exynos_tmu_work);
 
 	data->clk = devm_clk_get(&pdev->dev, "tmu_apbif");
@@ -1392,6 +1389,8 @@
 	if (!IS_ERR(data->clk_sec))
 		clk_unprepare(data->clk_sec);
 err_sensor:
+	if (!IS_ERR_OR_NULL(data->regulator))
+		regulator_disable(data->regulator);
 	thermal_zone_of_sensor_unregister(&pdev->dev, data->tzd);
 
 	return ret;
diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
index 04659bf..4ca211b 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1333,6 +1333,7 @@
 	return -ENODEV;
 
 unbind:
+	device_remove_file(&tz->device, &pos->weight_attr);
 	device_remove_file(&tz->device, &pos->attr);
 	sysfs_remove_link(&tz->device.kobj, pos->name);
 	release_idr(&tz->idr, &tz->lock, pos->id);
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index c9c27f6..ee8bfac 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -1108,19 +1108,29 @@
  *	Locking: ctrl_lock
  */
 
-static void isig(int sig, struct tty_struct *tty)
+static void __isig(int sig, struct tty_struct *tty)
 {
-	struct n_tty_data *ldata = tty->disc_data;
 	struct pid *tty_pgrp = tty_get_pgrp(tty);
 	if (tty_pgrp) {
 		kill_pgrp(tty_pgrp, sig, 1);
 		put_pid(tty_pgrp);
 	}
+}
 
-	if (!L_NOFLSH(tty)) {
+static void isig(int sig, struct tty_struct *tty)
+{
+	struct n_tty_data *ldata = tty->disc_data;
+
+	if (L_NOFLSH(tty)) {
+		/* signal only */
+		__isig(sig, tty);
+
+	} else { /* signal and flush */
 		up_read(&tty->termios_rwsem);
 		down_write(&tty->termios_rwsem);
 
+		__isig(sig, tty);
+
 		/* clear echo buffer */
 		mutex_lock(&ldata->output_lock);
 		ldata->echo_head = ldata->echo_tail = 0;
diff --git a/drivers/tty/serial/Kconfig b/drivers/tty/serial/Kconfig
index 76e65b7..15b4079 100644
--- a/drivers/tty/serial/Kconfig
+++ b/drivers/tty/serial/Kconfig
@@ -1185,7 +1185,7 @@
 config SERIAL_SC16IS7XX
         tristate "SC16IS7xx serial support"
         select SERIAL_CORE
-        depends on I2C || SPI_MASTER
+        depends on (SPI_MASTER && !I2C) || I2C
         help
           This selects support for SC16IS7xx serial ports.
           Supported ICs are SC16IS740, SC16IS741, SC16IS750, SC16IS752,
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index 50cf5b1..fd27e98 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2310,8 +2310,8 @@
 	void __iomem *base;
 
 	base = devm_ioremap_resource(dev, mmiobase);
-	if (!base)
-		return -ENOMEM;
+	if (IS_ERR(base))
+		return PTR_ERR(base);
 
 	index = pl011_probe_dt_alias(index, dev);
 
diff --git a/drivers/tty/serial/etraxfs-uart.c b/drivers/tty/serial/etraxfs-uart.c
index a57301a..679709f 100644
--- a/drivers/tty/serial/etraxfs-uart.c
+++ b/drivers/tty/serial/etraxfs-uart.c
@@ -950,7 +950,7 @@
 
 	port = platform_get_drvdata(pdev);
 	uart_remove_one_port(&etraxfs_uart_driver, port);
-	etraxfs_uart_ports[pdev->id] = NULL;
+	etraxfs_uart_ports[port->line] = NULL;
 
 	return 0;
 }
diff --git a/drivers/tty/serial/imx.c b/drivers/tty/serial/imx.c
index 2c90dc3..54fdc78 100644
--- a/drivers/tty/serial/imx.c
+++ b/drivers/tty/serial/imx.c
@@ -1121,11 +1121,6 @@
 
 	writel(temp & ~UCR4_DREN, sport->port.membase + UCR4);
 
-	/* Can we enable the DMA support? */
-	if (is_imx6q_uart(sport) && !uart_console(port) &&
-	    !sport->dma_is_inited)
-		imx_uart_dma_init(sport);
-
 	spin_lock_irqsave(&sport->port.lock, flags);
 	/* Reset fifo's and state machines */
 	i = 100;
@@ -1143,9 +1138,6 @@
 	writel(USR1_RTSD, sport->port.membase + USR1);
 	writel(USR2_ORE, sport->port.membase + USR2);
 
-	if (sport->dma_is_inited && !sport->dma_is_enabled)
-		imx_enable_dma(sport);
-
 	temp = readl(sport->port.membase + UCR1);
 	temp |= UCR1_RRDYEN | UCR1_RTSDEN | UCR1_UARTEN;
 
@@ -1316,6 +1308,11 @@
 			} else {
 				ucr2 |= UCR2_CTSC;
 			}
+
+			/* Can we enable the DMA support? */
+			if (is_imx6q_uart(sport) && !uart_console(port)
+				&& !sport->dma_is_inited)
+				imx_uart_dma_init(sport);
 		} else {
 			termios->c_cflag &= ~CRTSCTS;
 		}
@@ -1432,6 +1429,8 @@
 	if (UART_ENABLE_MS(&sport->port, termios->c_cflag))
 		imx_enable_ms(&sport->port);
 
+	if (sport->dma_is_inited && !sport->dma_is_enabled)
+		imx_enable_dma(sport);
 	spin_unlock_irqrestore(&sport->port.lock, flags);
 }
 
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 9e65760..5ccc698c 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -354,6 +354,26 @@
 		     (reg << SC16IS7XX_REG_SHIFT) | port->line, val);
 }
 
+static void sc16is7xx_fifo_read(struct uart_port *port, unsigned int rxlen)
+{
+	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
+	u8 addr = (SC16IS7XX_RHR_REG << SC16IS7XX_REG_SHIFT) | port->line;
+
+	regcache_cache_bypass(s->regmap, true);
+	regmap_raw_read(s->regmap, addr, s->buf, rxlen);
+	regcache_cache_bypass(s->regmap, false);
+}
+
+static void sc16is7xx_fifo_write(struct uart_port *port, u8 to_send)
+{
+	struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
+	u8 addr = (SC16IS7XX_THR_REG << SC16IS7XX_REG_SHIFT) | port->line;
+
+	regcache_cache_bypass(s->regmap, true);
+	regmap_raw_write(s->regmap, addr, s->buf, to_send);
+	regcache_cache_bypass(s->regmap, false);
+}
+
 static void sc16is7xx_port_update(struct uart_port *port, u8 reg,
 				  u8 mask, u8 val)
 {
@@ -508,10 +528,7 @@
 			s->buf[0] = sc16is7xx_port_read(port, SC16IS7XX_RHR_REG);
 			bytes_read = 1;
 		} else {
-			regcache_cache_bypass(s->regmap, true);
-			regmap_raw_read(s->regmap, SC16IS7XX_RHR_REG,
-					s->buf, rxlen);
-			regcache_cache_bypass(s->regmap, false);
+			sc16is7xx_fifo_read(port, rxlen);
 			bytes_read = rxlen;
 		}
 
@@ -591,9 +608,8 @@
 			s->buf[i] = xmit->buf[xmit->tail];
 			xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1);
 		}
-		regcache_cache_bypass(s->regmap, true);
-		regmap_raw_write(s->regmap, SC16IS7XX_THR_REG, s->buf, to_send);
-		regcache_cache_bypass(s->regmap, false);
+
+		sc16is7xx_fifo_write(port, to_send);
 	}
 
 	if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 7ae1592..f368520 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -1418,7 +1418,7 @@
 	mutex_lock(&port->mutex);
 	uart_shutdown(tty, state);
 	tty_port_tty_set(port, NULL);
-	tty->closing = 0;
+
 	spin_lock_irqsave(&port->lock, flags);
 
 	if (port->blocked_open) {
@@ -1444,6 +1444,7 @@
 	mutex_unlock(&port->mutex);
 
 	tty_ldisc_flush(tty);
+	tty->closing = 0;
 }
 
 static void uart_wait_until_sent(struct tty_struct *tty, int timeout)
diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c
index ea27804..381a2b1 100644
--- a/drivers/tty/vt/selection.c
+++ b/drivers/tty/vt/selection.c
@@ -356,6 +356,7 @@
 			schedule();
 			continue;
 		}
+		__set_current_state(TASK_RUNNING);
 		count = sel_buffer_lth - pasted;
 		count = tty_ldisc_receive_buf(ld, sel_buffer + pasted, NULL,
 					      count);
diff --git a/drivers/tty/vt/vt.c b/drivers/tty/vt/vt.c
index 8fe5298..4462d16 100644
--- a/drivers/tty/vt/vt.c
+++ b/drivers/tty/vt/vt.c
@@ -742,6 +742,8 @@
 	__module_get(vc->vc_sw->owner);
 	vc->vc_num = num;
 	vc->vc_display_fg = &master_display_fg;
+	if (vc->vc_uni_pagedir_loc)
+		con_free_unimap(vc);
 	vc->vc_uni_pagedir_loc = &vc->vc_uni_pagedir;
 	vc->vc_uni_pagedir = NULL;
 	vc->vc_hi_font_mask = 0;
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 74fea4f..3ad48e1 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -1024,7 +1024,18 @@
 	},
 };
 
-module_platform_driver(ci_hdrc_driver);
+static int __init ci_hdrc_platform_register(void)
+{
+	ci_hdrc_host_driver_init();
+	return platform_driver_register(&ci_hdrc_driver);
+}
+module_init(ci_hdrc_platform_register);
+
+static void __exit ci_hdrc_platform_unregister(void)
+{
+	platform_driver_unregister(&ci_hdrc_driver);
+}
+module_exit(ci_hdrc_platform_unregister);
 
 MODULE_ALIAS("platform:ci_hdrc");
 MODULE_LICENSE("GPL v2");
diff --git a/drivers/usb/chipidea/host.c b/drivers/usb/chipidea/host.c
index 6cf87b8..7161439 100644
--- a/drivers/usb/chipidea/host.c
+++ b/drivers/usb/chipidea/host.c
@@ -249,9 +249,12 @@
 	rdrv->name	= "host";
 	ci->roles[CI_ROLE_HOST] = rdrv;
 
+	return 0;
+}
+
+void ci_hdrc_host_driver_init(void)
+{
 	ehci_init_driver(&ci_ehci_hc_driver, &ehci_ci_overrides);
 	orig_bus_suspend = ci_ehci_hc_driver.bus_suspend;
 	ci_ehci_hc_driver.bus_suspend = ci_ehci_bus_suspend;
-
-	return 0;
 }
diff --git a/drivers/usb/chipidea/host.h b/drivers/usb/chipidea/host.h
index 5707bf3..0f12f13 100644
--- a/drivers/usb/chipidea/host.h
+++ b/drivers/usb/chipidea/host.h
@@ -5,6 +5,7 @@
 
 int ci_hdrc_host_init(struct ci_hdrc *ci);
 void ci_hdrc_host_destroy(struct ci_hdrc *ci);
+void ci_hdrc_host_driver_init(void);
 
 #else
 
@@ -18,6 +19,11 @@
 
 }
 
+static void ci_hdrc_host_driver_init(void)
+{
+
+}
+
 #endif
 
 #endif /* __DRIVERS_USB_CHIPIDEA_HOST_H */
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index 519a77b..b30e742 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1944,6 +1944,7 @@
 	usb_deregister(&acm_driver);
 	tty_unregister_driver(acm_tty_driver);
 	put_tty_driver(acm_tty_driver);
+	idr_destroy(&acm_minors);
 }
 
 module_init(acm_init);
diff --git a/drivers/usb/common/ulpi.c b/drivers/usb/common/ulpi.c
index 0e6f968..01c0c04 100644
--- a/drivers/usb/common/ulpi.c
+++ b/drivers/usb/common/ulpi.c
@@ -242,7 +242,7 @@
 {
 	return bus_register(&ulpi_bus);
 }
-module_init(ulpi_init);
+subsys_initcall(ulpi_init);
 
 static void __exit ulpi_exit(void)
 {
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index be5b207..cbcd092 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1022,9 +1022,12 @@
 				dev_name(&usb_dev->dev), retval);
 		return (retval < 0) ? retval : -EMSGSIZE;
 	}
-	if (usb_dev->speed == USB_SPEED_SUPER) {
+
+	if (le16_to_cpu(usb_dev->descriptor.bcdUSB) >= 0x0201) {
 		retval = usb_get_bos_descriptor(usb_dev);
-		if (retval < 0) {
+		if (!retval) {
+			usb_dev->lpm_capable = usb_device_supports_lpm(usb_dev);
+		} else if (usb_dev->speed == USB_SPEED_SUPER) {
 			mutex_unlock(&usb_bus_list_lock);
 			dev_dbg(parent_dev, "can't read %s bos descriptor %d\n",
 					dev_name(&usb_dev->dev), retval);
diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 43cb2f2..73dfa19 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -122,7 +122,7 @@
 	return usb_get_intfdata(hdev->actconfig->interface[0]);
 }
 
-static int usb_device_supports_lpm(struct usb_device *udev)
+int usb_device_supports_lpm(struct usb_device *udev)
 {
 	/* USB 2.1 (and greater) devices indicate LPM support through
 	 * their USB 2.0 Extended Capabilities BOS descriptor.
diff --git a/drivers/usb/core/usb.h b/drivers/usb/core/usb.h
index 7eb1e26..457255a 100644
--- a/drivers/usb/core/usb.h
+++ b/drivers/usb/core/usb.h
@@ -65,6 +65,7 @@
 extern void usb_hub_cleanup(void);
 extern int usb_major_init(void);
 extern void usb_major_cleanup(void);
+extern int usb_device_supports_lpm(struct usb_device *udev);
 
 #ifdef	CONFIG_PM
 
diff --git a/drivers/usb/dwc2/core.c b/drivers/usb/dwc2/core.c
index e5b546f..c3cc1a7 100644
--- a/drivers/usb/dwc2/core.c
+++ b/drivers/usb/dwc2/core.c
@@ -72,17 +72,7 @@
 	dev_dbg(hsotg->dev, "%s\n", __func__);
 
 	/* Backup Host regs */
-	hr = hsotg->hr_backup;
-	if (!hr) {
-		hr = devm_kzalloc(hsotg->dev, sizeof(*hr), GFP_KERNEL);
-		if (!hr) {
-			dev_err(hsotg->dev, "%s: can't allocate host regs\n",
-					__func__);
-			return -ENOMEM;
-		}
-
-		hsotg->hr_backup = hr;
-	}
+	hr = &hsotg->hr_backup;
 	hr->hcfg = readl(hsotg->regs + HCFG);
 	hr->haintmsk = readl(hsotg->regs + HAINTMSK);
 	for (i = 0; i < hsotg->core_params->host_channels; ++i)
@@ -90,6 +80,7 @@
 
 	hr->hprt0 = readl(hsotg->regs + HPRT0);
 	hr->hfir = readl(hsotg->regs + HFIR);
+	hr->valid = true;
 
 	return 0;
 }
@@ -109,12 +100,13 @@
 	dev_dbg(hsotg->dev, "%s\n", __func__);
 
 	/* Restore host regs */
-	hr = hsotg->hr_backup;
-	if (!hr) {
+	hr = &hsotg->hr_backup;
+	if (!hr->valid) {
 		dev_err(hsotg->dev, "%s: no host registers to restore\n",
 				__func__);
 		return -EINVAL;
 	}
+	hr->valid = false;
 
 	writel(hr->hcfg, hsotg->regs + HCFG);
 	writel(hr->haintmsk, hsotg->regs + HAINTMSK);
@@ -152,17 +144,7 @@
 	dev_dbg(hsotg->dev, "%s\n", __func__);
 
 	/* Backup dev regs */
-	dr = hsotg->dr_backup;
-	if (!dr) {
-		dr = devm_kzalloc(hsotg->dev, sizeof(*dr), GFP_KERNEL);
-		if (!dr) {
-			dev_err(hsotg->dev, "%s: can't allocate device regs\n",
-					__func__);
-			return -ENOMEM;
-		}
-
-		hsotg->dr_backup = dr;
-	}
+	dr = &hsotg->dr_backup;
 
 	dr->dcfg = readl(hsotg->regs + DCFG);
 	dr->dctl = readl(hsotg->regs + DCTL);
@@ -195,7 +177,7 @@
 		dr->doeptsiz[i] = readl(hsotg->regs + DOEPTSIZ(i));
 		dr->doepdma[i] = readl(hsotg->regs + DOEPDMA(i));
 	}
-
+	dr->valid = true;
 	return 0;
 }
 
@@ -215,12 +197,13 @@
 	dev_dbg(hsotg->dev, "%s\n", __func__);
 
 	/* Restore dev regs */
-	dr = hsotg->dr_backup;
-	if (!dr) {
+	dr = &hsotg->dr_backup;
+	if (!dr->valid) {
 		dev_err(hsotg->dev, "%s: no device registers to restore\n",
 				__func__);
 		return -EINVAL;
 	}
+	dr->valid = false;
 
 	writel(dr->dcfg, hsotg->regs + DCFG);
 	writel(dr->dctl, hsotg->regs + DCTL);
@@ -268,17 +251,7 @@
 	int i;
 
 	/* Backup global regs */
-	gr = hsotg->gr_backup;
-	if (!gr) {
-		gr = devm_kzalloc(hsotg->dev, sizeof(*gr), GFP_KERNEL);
-		if (!gr) {
-			dev_err(hsotg->dev, "%s: can't allocate global regs\n",
-					__func__);
-			return -ENOMEM;
-		}
-
-		hsotg->gr_backup = gr;
-	}
+	gr = &hsotg->gr_backup;
 
 	gr->gotgctl = readl(hsotg->regs + GOTGCTL);
 	gr->gintmsk = readl(hsotg->regs + GINTMSK);
@@ -291,6 +264,7 @@
 	for (i = 0; i < MAX_EPS_CHANNELS; i++)
 		gr->dtxfsiz[i] = readl(hsotg->regs + DPTXFSIZN(i));
 
+	gr->valid = true;
 	return 0;
 }
 
@@ -309,12 +283,13 @@
 	dev_dbg(hsotg->dev, "%s\n", __func__);
 
 	/* Restore global regs */
-	gr = hsotg->gr_backup;
-	if (!gr) {
+	gr = &hsotg->gr_backup;
+	if (!gr->valid) {
 		dev_err(hsotg->dev, "%s: no global registers to restore\n",
 				__func__);
 		return -EINVAL;
 	}
+	gr->valid = false;
 
 	writel(0xffffffff, hsotg->regs + GINTSTS);
 	writel(gr->gotgctl, hsotg->regs + GOTGCTL);
diff --git a/drivers/usb/dwc2/core.h b/drivers/usb/dwc2/core.h
index 53b8de0..0ed87620 100644
--- a/drivers/usb/dwc2/core.h
+++ b/drivers/usb/dwc2/core.h
@@ -492,6 +492,7 @@
 	u32 gdfifocfg;
 	u32 dtxfsiz[MAX_EPS_CHANNELS];
 	u32 gpwrdn;
+	bool valid;
 };
 
 /**
@@ -521,6 +522,7 @@
 	u32 doepctl[MAX_EPS_CHANNELS];
 	u32 doeptsiz[MAX_EPS_CHANNELS];
 	u32 doepdma[MAX_EPS_CHANNELS];
+	bool valid;
 };
 
 /**
@@ -538,6 +540,7 @@
 	u32 hcintmsk[MAX_EPS_CHANNELS];
 	u32 hprt0;
 	u32 hfir;
+	bool valid;
 };
 
 /**
@@ -705,9 +708,9 @@
 	struct work_struct wf_otg;
 	struct timer_list wkp_timer;
 	enum dwc2_lx_state lx_state;
-	struct dwc2_gregs_backup *gr_backup;
-	struct dwc2_dregs_backup *dr_backup;
-	struct dwc2_hregs_backup *hr_backup;
+	struct dwc2_gregs_backup gr_backup;
+	struct dwc2_dregs_backup dr_backup;
+	struct dwc2_hregs_backup hr_backup;
 
 	struct dentry *debug_root;
 	struct debugfs_regset32 *regset;
diff --git a/drivers/usb/dwc2/hcd.c b/drivers/usb/dwc2/hcd.c
index b10377c..f845c41 100644
--- a/drivers/usb/dwc2/hcd.c
+++ b/drivers/usb/dwc2/hcd.c
@@ -359,10 +359,9 @@
 
 /* Caller must hold driver lock */
 static int dwc2_hcd_urb_enqueue(struct dwc2_hsotg *hsotg,
-				struct dwc2_hcd_urb *urb, void **ep_handle,
-				gfp_t mem_flags)
+				struct dwc2_hcd_urb *urb, struct dwc2_qh *qh,
+				struct dwc2_qtd *qtd)
 {
-	struct dwc2_qtd *qtd;
 	u32 intr_mask;
 	int retval;
 	int dev_speed;
@@ -386,18 +385,15 @@
 			return -ENODEV;
 	}
 
-	qtd = kzalloc(sizeof(*qtd), mem_flags);
 	if (!qtd)
-		return -ENOMEM;
+		return -EINVAL;
 
 	dwc2_hcd_qtd_init(qtd, urb);
-	retval = dwc2_hcd_qtd_add(hsotg, qtd, (struct dwc2_qh **)ep_handle,
-				  mem_flags);
+	retval = dwc2_hcd_qtd_add(hsotg, qtd, qh);
 	if (retval) {
 		dev_err(hsotg->dev,
 			"DWC OTG HCD URB Enqueue failed adding QTD. Error status %d\n",
 			retval);
-		kfree(qtd);
 		return retval;
 	}
 
@@ -2445,6 +2441,9 @@
 	u32 tflags = 0;
 	void *buf;
 	unsigned long flags;
+	struct dwc2_qh *qh;
+	bool qh_allocated = false;
+	struct dwc2_qtd *qtd;
 
 	if (dbg_urb(urb)) {
 		dev_vdbg(hsotg->dev, "DWC OTG HCD URB Enqueue\n");
@@ -2523,16 +2522,33 @@
 						 urb->iso_frame_desc[i].length);
 
 	urb->hcpriv = dwc2_urb;
+	qh = (struct dwc2_qh *) ep->hcpriv;
+	/* Create QH for the endpoint if it doesn't exist */
+	if (!qh) {
+		qh = dwc2_hcd_qh_create(hsotg, dwc2_urb, mem_flags);
+		if (!qh) {
+			retval = -ENOMEM;
+			goto fail0;
+		}
+		ep->hcpriv = qh;
+		qh_allocated = true;
+	}
+
+	qtd = kzalloc(sizeof(*qtd), mem_flags);
+	if (!qtd) {
+		retval = -ENOMEM;
+		goto fail1;
+	}
 
 	spin_lock_irqsave(&hsotg->lock, flags);
 	retval = usb_hcd_link_urb_to_ep(hcd, urb);
 	if (retval)
-		goto fail1;
-
-	retval = dwc2_hcd_urb_enqueue(hsotg, dwc2_urb, &ep->hcpriv, mem_flags);
-	if (retval)
 		goto fail2;
 
+	retval = dwc2_hcd_urb_enqueue(hsotg, dwc2_urb, qh, qtd);
+	if (retval)
+		goto fail3;
+
 	if (alloc_bandwidth) {
 		dwc2_allocate_bus_bandwidth(hcd,
 				dwc2_hcd_get_ep_bandwidth(hsotg, ep),
@@ -2543,12 +2559,25 @@
 
 	return 0;
 
-fail2:
+fail3:
 	dwc2_urb->priv = NULL;
 	usb_hcd_unlink_urb_from_ep(hcd, urb);
-fail1:
+fail2:
 	spin_unlock_irqrestore(&hsotg->lock, flags);
 	urb->hcpriv = NULL;
+	kfree(qtd);
+fail1:
+	if (qh_allocated) {
+		struct dwc2_qtd *qtd2, *qtd2_tmp;
+
+		ep->hcpriv = NULL;
+		dwc2_hcd_qh_unlink(hsotg, qh);
+		/* Free each QTD in the QH's QTD list */
+		list_for_each_entry_safe(qtd2, qtd2_tmp, &qh->qtd_list,
+							 qtd_list_entry)
+			dwc2_hcd_qtd_unlink_and_free(hsotg, qtd2, qh);
+		dwc2_hcd_qh_free(hsotg, qh);
+	}
 fail0:
 	kfree(dwc2_urb);
 
diff --git a/drivers/usb/dwc2/hcd.h b/drivers/usb/dwc2/hcd.h
index 7b5841c..fc10549 100644
--- a/drivers/usb/dwc2/hcd.h
+++ b/drivers/usb/dwc2/hcd.h
@@ -463,6 +463,9 @@
 /* Schedule Queue Functions */
 /* Implemented in hcd_queue.c */
 extern void dwc2_hcd_init_usecs(struct dwc2_hsotg *hsotg);
+extern struct dwc2_qh *dwc2_hcd_qh_create(struct dwc2_hsotg *hsotg,
+					  struct dwc2_hcd_urb *urb,
+					  gfp_t mem_flags);
 extern void dwc2_hcd_qh_free(struct dwc2_hsotg *hsotg, struct dwc2_qh *qh);
 extern int dwc2_hcd_qh_add(struct dwc2_hsotg *hsotg, struct dwc2_qh *qh);
 extern void dwc2_hcd_qh_unlink(struct dwc2_hsotg *hsotg, struct dwc2_qh *qh);
@@ -471,7 +474,7 @@
 
 extern void dwc2_hcd_qtd_init(struct dwc2_qtd *qtd, struct dwc2_hcd_urb *urb);
 extern int dwc2_hcd_qtd_add(struct dwc2_hsotg *hsotg, struct dwc2_qtd *qtd,
-			    struct dwc2_qh **qh, gfp_t mem_flags);
+			    struct dwc2_qh *qh);
 
 /* Unlinks and frees a QTD */
 static inline void dwc2_hcd_qtd_unlink_and_free(struct dwc2_hsotg *hsotg,
diff --git a/drivers/usb/dwc2/hcd_queue.c b/drivers/usb/dwc2/hcd_queue.c
index 9b5c362..3ad63d3 100644
--- a/drivers/usb/dwc2/hcd_queue.c
+++ b/drivers/usb/dwc2/hcd_queue.c
@@ -191,7 +191,7 @@
  *
  * Return: Pointer to the newly allocated QH, or NULL on error
  */
-static struct dwc2_qh *dwc2_hcd_qh_create(struct dwc2_hsotg *hsotg,
+struct dwc2_qh *dwc2_hcd_qh_create(struct dwc2_hsotg *hsotg,
 					  struct dwc2_hcd_urb *urb,
 					  gfp_t mem_flags)
 {
@@ -767,57 +767,32 @@
  *
  * @hsotg:        The DWC HCD structure
  * @qtd:          The QTD to add
- * @qh:           Out parameter to return queue head
- * @atomic_alloc: Flag to do atomic alloc if needed
+ * @qh:           Queue head to add qtd to
  *
  * Return: 0 if successful, negative error code otherwise
  *
- * Finds the correct QH to place the QTD into. If it does not find a QH, it
- * will create a new QH. If the QH to which the QTD is added is not currently
- * scheduled, it is placed into the proper schedule based on its EP type.
+ * If the QH to which the QTD is added is not currently scheduled, it is placed
+ * into the proper schedule based on its EP type.
  */
 int dwc2_hcd_qtd_add(struct dwc2_hsotg *hsotg, struct dwc2_qtd *qtd,
-		     struct dwc2_qh **qh, gfp_t mem_flags)
+		     struct dwc2_qh *qh)
 {
-	struct dwc2_hcd_urb *urb = qtd->urb;
-	int allocated = 0;
 	int retval;
 
-	/*
-	 * Get the QH which holds the QTD-list to insert to. Create QH if it
-	 * doesn't exist.
-	 */
-	if (*qh == NULL) {
-		*qh = dwc2_hcd_qh_create(hsotg, urb, mem_flags);
-		if (*qh == NULL)
-			return -ENOMEM;
-		allocated = 1;
+	if (unlikely(!qh)) {
+		dev_err(hsotg->dev, "%s: Invalid QH\n", __func__);
+		retval = -EINVAL;
+		goto fail;
 	}
 
-	retval = dwc2_hcd_qh_add(hsotg, *qh);
+	retval = dwc2_hcd_qh_add(hsotg, qh);
 	if (retval)
 		goto fail;
 
-	qtd->qh = *qh;
-	list_add_tail(&qtd->qtd_list_entry, &(*qh)->qtd_list);
+	qtd->qh = qh;
+	list_add_tail(&qtd->qtd_list_entry, &qh->qtd_list);
 
 	return 0;
-
 fail:
-	if (allocated) {
-		struct dwc2_qtd *qtd2, *qtd2_tmp;
-		struct dwc2_qh *qh_tmp = *qh;
-
-		*qh = NULL;
-		dwc2_hcd_qh_unlink(hsotg, qh_tmp);
-
-		/* Free each QTD in the QH's QTD list */
-		list_for_each_entry_safe(qtd2, qtd2_tmp, &qh_tmp->qtd_list,
-					 qtd_list_entry)
-			dwc2_hcd_qtd_unlink_and_free(hsotg, qtd2, qh_tmp);
-
-		dwc2_hcd_qh_free(hsotg, qh_tmp);
-	}
-
 	return retval;
 }
diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 5c110d8..ff5773c 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -446,10 +446,12 @@
 	/* Select the HS PHY interface */
 	switch (DWC3_GHWPARAMS3_HSPHY_IFC(dwc->hwparams.hwparams3)) {
 	case DWC3_GHWPARAMS3_HSPHY_IFC_UTMI_ULPI:
-		if (!strncmp(dwc->hsphy_interface, "utmi", 4)) {
+		if (dwc->hsphy_interface &&
+				!strncmp(dwc->hsphy_interface, "utmi", 4)) {
 			reg &= ~DWC3_GUSB2PHYCFG_ULPI_UTMI;
 			break;
-		} else if (!strncmp(dwc->hsphy_interface, "ulpi", 4)) {
+		} else if (dwc->hsphy_interface &&
+				!strncmp(dwc->hsphy_interface, "ulpi", 4)) {
 			reg |= DWC3_GUSB2PHYCFG_ULPI_UTMI;
 			dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg);
 		} else {
diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
index 2ef3c8d..69e769c 100644
--- a/drivers/usb/dwc3/ep0.c
+++ b/drivers/usb/dwc3/ep0.c
@@ -727,6 +727,10 @@
 		dwc3_trace(trace_dwc3_ep0, "USB_REQ_SET_ISOCH_DELAY");
 		ret = dwc3_ep0_set_isoch_delay(dwc, ctrl);
 		break;
+	case USB_REQ_SET_INTERFACE:
+		dwc3_trace(trace_dwc3_ep0, "USB_REQ_SET_INTERFACE");
+		dwc->start_config_issued = false;
+		/* Fall through */
 	default:
 		dwc3_trace(trace_dwc3_ep0, "Forwarding to gadget driver");
 		ret = dwc3_ep0_delegate_req(dwc, ctrl);
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 4e3447b..58b4657 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1758,10 +1758,13 @@
 		 * take such requests too, if that's ever needed:  to work
 		 * in config 0, etc.
 		 */
-		list_for_each_entry(f, &cdev->config->functions, list)
-			if (f->req_match && f->req_match(f, ctrl))
-				goto try_fun_setup;
-		f = NULL;
+		if (cdev->config) {
+			list_for_each_entry(f, &cdev->config->functions, list)
+				if (f->req_match && f->req_match(f, ctrl))
+					goto try_fun_setup;
+			f = NULL;
+		}
+
 		switch (ctrl->bRequestType & USB_RECIP_MASK) {
 		case USB_RECIP_INTERFACE:
 			if (!cdev->config || intf >= MAX_CONFIG_INTERFACES)
diff --git a/drivers/usb/gadget/configfs.c b/drivers/usb/gadget/configfs.c
index 0495c94..289e201 100644
--- a/drivers/usb/gadget/configfs.c
+++ b/drivers/usb/gadget/configfs.c
@@ -571,7 +571,7 @@
 	if (IS_ERR(fi))
 		return ERR_CAST(fi);
 
-	ret = config_item_set_name(&fi->group.cg_item, name);
+	ret = config_item_set_name(&fi->group.cg_item, "%s", name);
 	if (ret) {
 		usb_put_function_instance(fi);
 		return ERR_PTR(ret);
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 45b8c8b..6e7be91 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -924,7 +924,8 @@
 
 	kiocb->private = p;
 
-	kiocb_set_cancel_fn(kiocb, ffs_aio_cancel);
+	if (p->aio)
+		kiocb_set_cancel_fn(kiocb, ffs_aio_cancel);
 
 	res = ffs_epfile_io(kiocb->ki_filp, p);
 	if (res == -EIOCBQUEUED)
@@ -968,7 +969,8 @@
 
 	kiocb->private = p;
 
-	kiocb_set_cancel_fn(kiocb, ffs_aio_cancel);
+	if (p->aio)
+		kiocb_set_cancel_fn(kiocb, ffs_aio_cancel);
 
 	res = ffs_epfile_io(kiocb->ki_filp, p);
 	if (res == -EIOCBQUEUED)
diff --git a/drivers/usb/gadget/function/f_hid.c b/drivers/usb/gadget/function/f_hid.c
index f7f35a3..6df9715 100644
--- a/drivers/usb/gadget/function/f_hid.c
+++ b/drivers/usb/gadget/function/f_hid.c
@@ -699,6 +699,10 @@
 	int ret;
 
 	ret = ida_simple_get(&hidg_ida, 0, 0, GFP_KERNEL);
+	if (ret >= HIDG_MINORS) {
+		ida_simple_remove(&hidg_ida, ret);
+		ret = -ENODEV;
+	}
 
 	return ret;
 }
diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c
index d2259c6..f936268 100644
--- a/drivers/usb/gadget/function/f_mass_storage.c
+++ b/drivers/usb/gadget/function/f_mass_storage.c
@@ -2786,7 +2786,7 @@
 		return -EINVAL;
 	}
 
-	curlun = kcalloc(nluns, sizeof(*curlun), GFP_KERNEL);
+	curlun = kcalloc(FSG_MAX_LUNS, sizeof(*curlun), GFP_KERNEL);
 	if (unlikely(!curlun))
 		return -ENOMEM;
 
@@ -2796,8 +2796,6 @@
 	common->luns = curlun;
 	common->nluns = nluns;
 
-	pr_info("Number of LUNs=%d\n", common->nluns);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(fsg_common_set_nluns);
@@ -3563,14 +3561,26 @@
 	struct fsg_opts *opts = fsg_opts_from_func_inst(fi);
 	struct fsg_common *common = opts->common;
 	struct fsg_dev *fsg;
+	unsigned nluns, i;
 
 	fsg = kzalloc(sizeof(*fsg), GFP_KERNEL);
 	if (unlikely(!fsg))
 		return ERR_PTR(-ENOMEM);
 
 	mutex_lock(&opts->lock);
+	if (!opts->refcnt) {
+		for (nluns = i = 0; i < FSG_MAX_LUNS; ++i)
+			if (common->luns[i])
+				nluns = i + 1;
+		if (!nluns)
+			pr_warn("No LUNS defined, continuing anyway\n");
+		else
+			common->nluns = nluns;
+		pr_info("Number of LUNs=%u\n", common->nluns);
+	}
 	opts->refcnt++;
 	mutex_unlock(&opts->lock);
+
 	fsg->function.name	= FSG_DRIVER_DESC;
 	fsg->function.bind	= fsg_bind;
 	fsg->function.unbind	= fsg_unbind;
diff --git a/drivers/usb/gadget/function/f_midi.c b/drivers/usb/gadget/function/f_midi.c
index 6316aa5..ad50a67 100644
--- a/drivers/usb/gadget/function/f_midi.c
+++ b/drivers/usb/gadget/function/f_midi.c
@@ -1145,7 +1145,7 @@
 	if (opts->id && !midi->id) {
 		status = -ENOMEM;
 		mutex_unlock(&opts->lock);
-		goto kstrdup_fail;
+		goto setup_fail;
 	}
 	midi->in_ports = opts->in_ports;
 	midi->out_ports = opts->out_ports;
@@ -1164,8 +1164,6 @@
 
 	return &midi->func;
 
-kstrdup_fail:
-	f_midi_unregister_card(midi);
 setup_fail:
 	for (--i; i >= 0; i--)
 		kfree(midi->in_port[i]);
diff --git a/drivers/usb/gadget/function/f_printer.c b/drivers/usb/gadget/function/f_printer.c
index 44173df..357f63f 100644
--- a/drivers/usb/gadget/function/f_printer.c
+++ b/drivers/usb/gadget/function/f_printer.c
@@ -1248,7 +1248,15 @@
 
 static inline int gprinter_get_minor(void)
 {
-	return ida_simple_get(&printer_ida, 0, 0, GFP_KERNEL);
+	int ret;
+
+	ret = ida_simple_get(&printer_ida, 0, 0, GFP_KERNEL);
+	if (ret >= PRINTER_MINORS) {
+		ida_simple_remove(&printer_ida, ret);
+		ret = -ENODEV;
+	}
+
+	return ret;
 }
 
 static inline void gprinter_put_minor(int minor)
diff --git a/drivers/usb/gadget/function/f_uac2.c b/drivers/usb/gadget/function/f_uac2.c
index 6d3eb8b..5318615 100644
--- a/drivers/usb/gadget/function/f_uac2.c
+++ b/drivers/usb/gadget/function/f_uac2.c
@@ -1162,14 +1162,14 @@
 			factor = 1000;
 		} else {
 			ep_desc = &hs_epin_desc;
-			factor = 125;
+			factor = 8000;
 		}
 
 		/* pre-compute some values for iso_complete() */
 		uac2->p_framesize = opts->p_ssize *
 				    num_channels(opts->p_chmask);
 		rate = opts->p_srate * uac2->p_framesize;
-		uac2->p_interval = (1 << (ep_desc->bInterval - 1)) * factor;
+		uac2->p_interval = factor / (1 << (ep_desc->bInterval - 1));
 		uac2->p_pktsize = min_t(unsigned int, rate / uac2->p_interval,
 					prm->max_psize);
 
diff --git a/drivers/usb/gadget/udc/bdc/bdc_ep.c b/drivers/usb/gadget/udc/bdc/bdc_ep.c
index b04980c..1efa612 100644
--- a/drivers/usb/gadget/udc/bdc/bdc_ep.c
+++ b/drivers/usb/gadget/udc/bdc/bdc_ep.c
@@ -779,7 +779,7 @@
 	/* The current hw dequeue pointer */
 	tmp_32 = bdc_readl(bdc->regs, BDC_EPSTS0(0));
 	deq_ptr_64 = tmp_32;
-	tmp_32 = bdc_readl(bdc->regs, BDC_EPSTS0(1));
+	tmp_32 = bdc_readl(bdc->regs, BDC_EPSTS1(0));
 	deq_ptr_64 |= ((u64)tmp_32 << 32);
 
 	/* we have the dma addr of next bd that will be fetched by hardware */
diff --git a/drivers/usb/gadget/udc/fotg210-udc.c b/drivers/usb/gadget/udc/fotg210-udc.c
index e547ea7..1137e33 100644
--- a/drivers/usb/gadget/udc/fotg210-udc.c
+++ b/drivers/usb/gadget/udc/fotg210-udc.c
@@ -1171,7 +1171,7 @@
 			  udc_name, fotg210);
 	if (ret < 0) {
 		pr_err("request_irq error (%d)\n", ret);
-		goto err_irq;
+		goto err_req;
 	}
 
 	ret = usb_add_gadget_udc(&pdev->dev, &fotg210->gadget);
@@ -1183,7 +1183,6 @@
 	return 0;
 
 err_add_udc:
-err_irq:
 	free_irq(ires->start, fotg210);
 
 err_req:
diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c
index d32160d..5da37c9 100644
--- a/drivers/usb/gadget/udc/mv_udc_core.c
+++ b/drivers/usb/gadget/udc/mv_udc_core.c
@@ -2167,7 +2167,7 @@
 		return -ENODEV;
 	}
 
-	udc->phy_regs = ioremap(r->start, resource_size(r));
+	udc->phy_regs = devm_ioremap(&pdev->dev, r->start, resource_size(r));
 	if (udc->phy_regs == NULL) {
 		dev_err(&pdev->dev, "failed to map phy I/O memory\n");
 		return -EBUSY;
diff --git a/drivers/usb/gadget/udc/udc-core.c b/drivers/usb/gadget/udc/udc-core.c
index d69c355..89ed5e7 100644
--- a/drivers/usb/gadget/udc/udc-core.c
+++ b/drivers/usb/gadget/udc/udc-core.c
@@ -60,13 +60,15 @@
 int usb_gadget_map_request(struct usb_gadget *gadget,
 		struct usb_request *req, int is_in)
 {
+	struct device *dev = gadget->dev.parent;
+
 	if (req->length == 0)
 		return 0;
 
 	if (req->num_sgs) {
 		int     mapped;
 
-		mapped = dma_map_sg(&gadget->dev, req->sg, req->num_sgs,
+		mapped = dma_map_sg(dev, req->sg, req->num_sgs,
 				is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 		if (mapped == 0) {
 			dev_err(&gadget->dev, "failed to map SGs\n");
@@ -75,11 +77,11 @@
 
 		req->num_mapped_sgs = mapped;
 	} else {
-		req->dma = dma_map_single(&gadget->dev, req->buf, req->length,
+		req->dma = dma_map_single(dev, req->buf, req->length,
 				is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 
-		if (dma_mapping_error(&gadget->dev, req->dma)) {
-			dev_err(&gadget->dev, "failed to map buffer\n");
+		if (dma_mapping_error(dev, req->dma)) {
+			dev_err(dev, "failed to map buffer\n");
 			return -EFAULT;
 		}
 	}
@@ -95,12 +97,12 @@
 		return;
 
 	if (req->num_mapped_sgs) {
-		dma_unmap_sg(&gadget->dev, req->sg, req->num_mapped_sgs,
+		dma_unmap_sg(gadget->dev.parent, req->sg, req->num_mapped_sgs,
 				is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 
 		req->num_mapped_sgs = 0;
 	} else {
-		dma_unmap_single(&gadget->dev, req->dma, req->length,
+		dma_unmap_single(gadget->dev.parent, req->dma, req->length,
 				is_in ? DMA_TO_DEVICE : DMA_FROM_DEVICE);
 	}
 }
@@ -321,6 +323,7 @@
 
 err3:
 	put_device(&udc->dev);
+	device_del(&gadget->dev);
 
 err2:
 	put_device(&gadget->dev);
diff --git a/drivers/usb/host/ohci-q.c b/drivers/usb/host/ohci-q.c
index f7d561e..d029bbe 100644
--- a/drivers/usb/host/ohci-q.c
+++ b/drivers/usb/host/ohci-q.c
@@ -981,10 +981,6 @@
 		int			completed, modified;
 		__hc32			*prev;
 
-		/* Is this ED already invisible to the hardware? */
-		if (ed->state == ED_IDLE)
-			goto ed_idle;
-
 		/* only take off EDs that the HC isn't using, accounting for
 		 * frame counter wraps and EDs with partially retired TDs
 		 */
@@ -1012,12 +1008,10 @@
 		}
 
 		/* ED's now officially unlinked, hc doesn't see */
-		ed->state = ED_IDLE;
 		ed->hwHeadP &= ~cpu_to_hc32(ohci, ED_H);
 		ed->hwNextED = 0;
 		wmb();
 		ed->hwINFO &= ~cpu_to_hc32(ohci, ED_SKIP | ED_DEQUEUE);
-ed_idle:
 
 		/* reentrancy:  if we drop the schedule lock, someone might
 		 * have modified this list.  normally it's just prepending
@@ -1088,6 +1082,7 @@
 		if (list_empty(&ed->td_list)) {
 			*last = ed->ed_next;
 			ed->ed_next = NULL;
+			ed->state = ED_IDLE;
 			list_del(&ed->in_use_list);
 		} else if (ohci->rh_state == OHCI_RH_RUNNING) {
 			*last = ed->ed_next;
diff --git a/drivers/usb/host/ohci-tmio.c b/drivers/usb/host/ohci-tmio.c
index e9a6eec..cfcfadf 100644
--- a/drivers/usb/host/ohci-tmio.c
+++ b/drivers/usb/host/ohci-tmio.c
@@ -58,7 +58,7 @@
 #define CCR_PM_CKRNEN    0x0002
 #define CCR_PM_USBPW1    0x0004
 #define CCR_PM_USBPW2    0x0008
-#define CCR_PM_USBPW3    0x0008
+#define CCR_PM_USBPW3    0x0010
 #define CCR_PM_PMEE      0x0100
 #define CCR_PM_PMES      0x8000
 
diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index e75c565..78241b5 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -484,10 +484,13 @@
 	u32 pls = status_reg & PORT_PLS_MASK;
 
 	/* resume state is a xHCI internal state.
-	 * Do not report it to usb core.
+	 * Do not report it to usb core, instead, pretend to be U3,
+	 * thus usb core knows it's not ready for transfer
 	 */
-	if (pls == XDEV_RESUME)
+	if (pls == XDEV_RESUME) {
+		*status |= USB_SS_PORT_LS_U3;
 		return;
+	}
 
 	/* When the CAS bit is set then warm reset
 	 * should be performed on port
@@ -588,7 +591,14 @@
 		status |= USB_PORT_STAT_C_RESET << 16;
 	/* USB3.0 only */
 	if (hcd->speed == HCD_USB3) {
-		if ((raw_port_status & PORT_PLC))
+		/* Port link change with port in resume state should not be
+		 * reported to usbcore, as this is an internal state to be
+		 * handled by xhci driver. Reporting PLC to usbcore may
+		 * cause usbcore clearing PLC first and port change event
+		 * irq won't be generated.
+		 */
+		if ((raw_port_status & PORT_PLC) &&
+			(raw_port_status & PORT_PLS_MASK) != XDEV_RESUME)
 			status |= USB_PORT_STAT_C_LINK_STATE << 16;
 		if ((raw_port_status & PORT_WRC))
 			status |= USB_PORT_STAT_C_BH_RESET << 16;
@@ -1120,10 +1130,10 @@
 	spin_lock_irqsave(&xhci->lock, flags);
 
 	if (hcd->self.root_hub->do_remote_wakeup) {
-		if (bus_state->resuming_ports) {
+		if (bus_state->resuming_ports ||	/* USB2 */
+		    bus_state->port_remote_wakeup) {	/* USB3 */
 			spin_unlock_irqrestore(&xhci->lock, flags);
-			xhci_dbg(xhci, "suspend failed because "
-						"a port is resuming\n");
+			xhci_dbg(xhci, "suspend failed because a port is resuming\n");
 			return -EBUSY;
 		}
 	}
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index f833640..9a8c936 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1427,10 +1427,10 @@
 		/* Attempt to use the ring cache */
 		if (virt_dev->num_rings_cached == 0)
 			return -ENOMEM;
+		virt_dev->num_rings_cached--;
 		virt_dev->eps[ep_index].new_ring =
 			virt_dev->ring_cache[virt_dev->num_rings_cached];
 		virt_dev->ring_cache[virt_dev->num_rings_cached] = NULL;
-		virt_dev->num_rings_cached--;
 		xhci_reinit_cached_ring(xhci, virt_dev->eps[ep_index].new_ring,
 					1, type);
 	}
@@ -1792,7 +1792,8 @@
 	int size;
 	int i, j, num_ports;
 
-	del_timer_sync(&xhci->cmd_timer);
+	if (timer_pending(&xhci->cmd_timer))
+		del_timer_sync(&xhci->cmd_timer);
 
 	/* Free the Event Ring Segment Table and the actual Event Ring */
 	size = sizeof(struct xhci_erst_entry)*(xhci->erst.num_entries);
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 4a4cb1d..5590eac 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -23,10 +23,15 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/acpi.h>
 
 #include "xhci.h"
 #include "xhci-trace.h"
 
+#define PORT2_SSIC_CONFIG_REG2	0x883c
+#define PROG_DONE		(1 << 30)
+#define SSIC_PORT_UNUSED	(1 << 31)
+
 /* Device for a quirk */
 #define PCI_VENDOR_ID_FRESCO_LOGIC	0x1b73
 #define PCI_DEVICE_ID_FRESCO_LOGIC_PDK	0x1000
@@ -176,20 +181,63 @@
 }
 
 /*
+ * In some Intel xHCI controllers, in order to get D3 working,
+ * through a vendor specific SSIC CONFIG register at offset 0x883c,
+ * SSIC PORT need to be marked as "unused" before putting xHCI
+ * into D3. After D3 exit, the SSIC port need to be marked as "used".
+ * Without this change, xHCI might not enter D3 state.
  * Make sure PME works on some Intel xHCI controllers by writing 1 to clear
  * the Internal PME flag bit in vendor specific PMCTRL register at offset 0x80a4
  */
-static void xhci_pme_quirk(struct xhci_hcd *xhci)
+static void xhci_pme_quirk(struct usb_hcd *hcd, bool suspend)
 {
+	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
+	struct pci_dev		*pdev = to_pci_dev(hcd->self.controller);
 	u32 val;
 	void __iomem *reg;
 
+	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+		 pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI) {
+
+		reg = (void __iomem *) xhci->cap_regs + PORT2_SSIC_CONFIG_REG2;
+
+		/* Notify SSIC that SSIC profile programming is not done */
+		val = readl(reg) & ~PROG_DONE;
+		writel(val, reg);
+
+		/* Mark SSIC port as unused(suspend) or used(resume) */
+		val = readl(reg);
+		if (suspend)
+			val |= SSIC_PORT_UNUSED;
+		else
+			val &= ~SSIC_PORT_UNUSED;
+		writel(val, reg);
+
+		/* Notify SSIC that SSIC profile programming is done */
+		val = readl(reg) | PROG_DONE;
+		writel(val, reg);
+		readl(reg);
+	}
+
 	reg = (void __iomem *) xhci->cap_regs + 0x80a4;
 	val = readl(reg);
 	writel(val | BIT(28), reg);
 	readl(reg);
 }
 
+#ifdef CONFIG_ACPI
+static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev)
+{
+	static const u8 intel_dsm_uuid[] = {
+		0xb7, 0x0c, 0x34, 0xac,	0x01, 0xe9, 0xbf, 0x45,
+		0xb7, 0xe6, 0x2b, 0x34, 0xec, 0x93, 0x1e, 0x23,
+	};
+	acpi_evaluate_dsm(ACPI_HANDLE(&dev->dev), intel_dsm_uuid, 3, 1, NULL);
+}
+#else
+	static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev) { }
+#endif /* CONFIG_ACPI */
+
 /* called during probe() after chip reset completes */
 static int xhci_pci_setup(struct usb_hcd *hcd)
 {
@@ -263,6 +311,9 @@
 			HCC_MAX_PSA(xhci->hcc_params) >= 4)
 		xhci->shared_hcd->can_do_streams = 1;
 
+	if (xhci->quirks & XHCI_PME_STUCK_QUIRK)
+		xhci_pme_acpi_rtd3_enable(dev);
+
 	/* USB-2 and USB-3 roothubs initialized, allow runtime pm suspend */
 	pm_runtime_put_noidle(&dev->dev);
 
@@ -307,7 +358,7 @@
 		pdev->no_d3cold = true;
 
 	if (xhci->quirks & XHCI_PME_STUCK_QUIRK)
-		xhci_pme_quirk(xhci);
+		xhci_pme_quirk(hcd, true);
 
 	return xhci_suspend(xhci, do_wakeup);
 }
@@ -340,7 +391,7 @@
 		usb_enable_intel_xhci_ports(pdev);
 
 	if (xhci->quirks & XHCI_PME_STUCK_QUIRK)
-		xhci_pme_quirk(xhci);
+		xhci_pme_quirk(hcd, false);
 
 	retval = xhci_resume(xhci, hibernated);
 	return retval;
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 94416ff..32f4d56 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -82,7 +82,7 @@
 		return 0;
 	/* offset in TRBs */
 	segment_offset = trb - seg->trbs;
-	if (segment_offset > TRBS_PER_SEGMENT)
+	if (segment_offset >= TRBS_PER_SEGMENT)
 		return 0;
 	return seg->dma + (segment_offset * sizeof(*trb));
 }
@@ -1546,6 +1546,9 @@
 		usb_hcd_resume_root_hub(hcd);
 	}
 
+	if (hcd->speed == HCD_USB3 && (temp & PORT_PLS_MASK) == XDEV_INACTIVE)
+		bus_state->port_remote_wakeup &= ~(1 << faked_port_index);
+
 	if ((temp & PORT_PLC) && (temp & PORT_PLS_MASK) == XDEV_RESUME) {
 		xhci_dbg(xhci, "port resume event for port %d\n", port_id);
 
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 7da0d60..526ebc0 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -3453,6 +3453,9 @@
 			return -EINVAL;
 	}
 
+	if (virt_dev->tt_info)
+		old_active_eps = virt_dev->tt_info->active_eps;
+
 	if (virt_dev->udev != udev) {
 		/* If the virt_dev and the udev does not match, this virt_dev
 		 * may belong to another udev.
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 31e46cc..ed2ebf6 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -285,6 +285,7 @@
 #define XDEV_U0		(0x0 << 5)
 #define XDEV_U2		(0x2 << 5)
 #define XDEV_U3		(0x3 << 5)
+#define XDEV_INACTIVE	(0x6 << 5)
 #define XDEV_RESUME	(0xf << 5)
 /* true: port has power (see HCC_PPC) */
 #define PORT_POWER	(1 << 9)
diff --git a/drivers/usb/musb/musb_virthub.c b/drivers/usb/musb/musb_virthub.c
index 30842bc..92d5f71 100644
--- a/drivers/usb/musb/musb_virthub.c
+++ b/drivers/usb/musb/musb_virthub.c
@@ -275,9 +275,7 @@
 #ifdef CONFIG_USB_MUSB_HOST
 	return 1;
 #else
-	if (musb->port_mode == MUSB_PORT_MODE_HOST)
-		return 1;
-	return musb->g.dev.driver != NULL;
+	return musb->port_mode == MUSB_PORT_MODE_HOST;
 #endif
 }
 
diff --git a/drivers/usb/phy/phy-mxs-usb.c b/drivers/usb/phy/phy-mxs-usb.c
index 8f7cb06..3fcc048 100644
--- a/drivers/usb/phy/phy-mxs-usb.c
+++ b/drivers/usb/phy/phy-mxs-usb.c
@@ -217,6 +217,9 @@
 {
 	unsigned int vbus_value;
 
+	if (!mxs_phy->regmap_anatop)
+		return false;
+
 	if (mxs_phy->port_id == 0)
 		regmap_read(mxs_phy->regmap_anatop,
 			ANADIG_USB1_VBUS_DET_STAT,
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index ffd739e..eac7cca 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -187,6 +187,7 @@
 	{ USB_DEVICE(0x1FB9, 0x0602) }, /* Lake Shore Model 648 Magnet Power Supply */
 	{ USB_DEVICE(0x1FB9, 0x0700) }, /* Lake Shore Model 737 VSM Controller */
 	{ USB_DEVICE(0x1FB9, 0x0701) }, /* Lake Shore Model 776 Hall Matrix */
+	{ USB_DEVICE(0x2626, 0xEA60) }, /* Aruba Networks 7xxx USB Serial Console */
 	{ USB_DEVICE(0x3195, 0xF190) }, /* Link Instruments MSO-19 */
 	{ USB_DEVICE(0x3195, 0xF280) }, /* Link Instruments MSO-28 */
 	{ USB_DEVICE(0x3195, 0xF281) }, /* Link Instruments MSO-28 */
diff --git a/drivers/usb/serial/mos7720.c b/drivers/usb/serial/mos7720.c
index 4f70df3..78b4f64 100644
--- a/drivers/usb/serial/mos7720.c
+++ b/drivers/usb/serial/mos7720.c
@@ -121,26 +121,26 @@
 static const unsigned int dummy; /* for clarity in register access fns */
 
 enum mos_regs {
-	THR,	          /* serial port regs */
-	RHR,
-	IER,
-	FCR,
-	ISR,
-	LCR,
-	MCR,
-	LSR,
-	MSR,
-	SPR,
-	DLL,
-	DLM,
-	DPR,              /* parallel port regs */
-	DSR,
-	DCR,
-	ECR,
-	SP1_REG,          /* device control regs */
-	SP2_REG,          /* serial port 2 (7720 only) */
-	PP_REG,
-	SP_CONTROL_REG,
+	MOS7720_THR,		  /* serial port regs */
+	MOS7720_RHR,
+	MOS7720_IER,
+	MOS7720_FCR,
+	MOS7720_ISR,
+	MOS7720_LCR,
+	MOS7720_MCR,
+	MOS7720_LSR,
+	MOS7720_MSR,
+	MOS7720_SPR,
+	MOS7720_DLL,
+	MOS7720_DLM,
+	MOS7720_DPR,		  /* parallel port regs */
+	MOS7720_DSR,
+	MOS7720_DCR,
+	MOS7720_ECR,
+	MOS7720_SP1_REG,	  /* device control regs */
+	MOS7720_SP2_REG,	  /* serial port 2 (7720 only) */
+	MOS7720_PP_REG,
+	MOS7720_SP_CONTROL_REG,
 };
 
 /*
@@ -150,26 +150,26 @@
 static inline __u16 get_reg_index(enum mos_regs reg)
 {
 	static const __u16 mos7715_index_lookup_table[] = {
-		0x00,		/* THR */
-		0x00,		/* RHR */
-		0x01,		/* IER */
-		0x02,		/* FCR */
-		0x02,		/* ISR */
-		0x03,		/* LCR */
-		0x04,		/* MCR */
-		0x05,		/* LSR */
-		0x06,		/* MSR */
-		0x07,		/* SPR */
-		0x00,		/* DLL */
-		0x01,		/* DLM */
-		0x00,		/* DPR */
-		0x01,		/* DSR */
-		0x02,		/* DCR */
-		0x0a,		/* ECR */
-		0x01,		/* SP1_REG */
-		0x02,		/* SP2_REG (7720 only) */
-		0x04,		/* PP_REG (7715 only) */
-		0x08,		/* SP_CONTROL_REG */
+		0x00,		/* MOS7720_THR */
+		0x00,		/* MOS7720_RHR */
+		0x01,		/* MOS7720_IER */
+		0x02,		/* MOS7720_FCR */
+		0x02,		/* MOS7720_ISR */
+		0x03,		/* MOS7720_LCR */
+		0x04,		/* MOS7720_MCR */
+		0x05,		/* MOS7720_LSR */
+		0x06,		/* MOS7720_MSR */
+		0x07,		/* MOS7720_SPR */
+		0x00,		/* MOS7720_DLL */
+		0x01,		/* MOS7720_DLM */
+		0x00,		/* MOS7720_DPR */
+		0x01,		/* MOS7720_DSR */
+		0x02,		/* MOS7720_DCR */
+		0x0a,		/* MOS7720_ECR */
+		0x01,		/* MOS7720_SP1_REG */
+		0x02,		/* MOS7720_SP2_REG (7720 only) */
+		0x04,		/* MOS7720_PP_REG (7715 only) */
+		0x08,		/* MOS7720_SP_CONTROL_REG */
 	};
 	return mos7715_index_lookup_table[reg];
 }
@@ -181,10 +181,10 @@
 static inline __u16 get_reg_value(enum mos_regs reg,
 				  unsigned int serial_portnum)
 {
-	if (reg >= SP1_REG)	      /* control reg */
+	if (reg >= MOS7720_SP1_REG)	/* control reg */
 		return 0x0000;
 
-	else if (reg >= DPR)	      /* parallel port reg (7715 only) */
+	else if (reg >= MOS7720_DPR)	/* parallel port reg (7715 only) */
 		return 0x0100;
 
 	else			      /* serial port reg */
@@ -252,7 +252,8 @@
 				      enum mos7715_pp_modes mode)
 {
 	mos_parport->shadowECR = mode;
-	write_mos_reg(mos_parport->serial, dummy, ECR, mos_parport->shadowECR);
+	write_mos_reg(mos_parport->serial, dummy, MOS7720_ECR,
+		      mos_parport->shadowECR);
 	return 0;
 }
 
@@ -486,7 +487,7 @@
 	if (parport_prologue(pp) < 0)
 		return;
 	mos7715_change_mode(mos_parport, SPP);
-	write_mos_reg(mos_parport->serial, dummy, DPR, (__u8)d);
+	write_mos_reg(mos_parport->serial, dummy, MOS7720_DPR, (__u8)d);
 	parport_epilogue(pp);
 }
 
@@ -497,7 +498,7 @@
 
 	if (parport_prologue(pp) < 0)
 		return 0;
-	read_mos_reg(mos_parport->serial, dummy, DPR, &d);
+	read_mos_reg(mos_parport->serial, dummy, MOS7720_DPR, &d);
 	parport_epilogue(pp);
 	return d;
 }
@@ -510,7 +511,7 @@
 	if (parport_prologue(pp) < 0)
 		return;
 	data = ((__u8)d & 0x0f) | (mos_parport->shadowDCR & 0xf0);
-	write_mos_reg(mos_parport->serial, dummy, DCR, data);
+	write_mos_reg(mos_parport->serial, dummy, MOS7720_DCR, data);
 	mos_parport->shadowDCR = data;
 	parport_epilogue(pp);
 }
@@ -543,7 +544,8 @@
 	if (parport_prologue(pp) < 0)
 		return 0;
 	mos_parport->shadowDCR = (mos_parport->shadowDCR & (~mask)) ^ val;
-	write_mos_reg(mos_parport->serial, dummy, DCR, mos_parport->shadowDCR);
+	write_mos_reg(mos_parport->serial, dummy, MOS7720_DCR,
+		      mos_parport->shadowDCR);
 	dcr = mos_parport->shadowDCR & 0x0f;
 	parport_epilogue(pp);
 	return dcr;
@@ -581,7 +583,8 @@
 		return;
 	mos7715_change_mode(mos_parport, PS2);
 	mos_parport->shadowDCR &=  ~0x20;
-	write_mos_reg(mos_parport->serial, dummy, DCR, mos_parport->shadowDCR);
+	write_mos_reg(mos_parport->serial, dummy, MOS7720_DCR,
+		      mos_parport->shadowDCR);
 	parport_epilogue(pp);
 }
 
@@ -593,7 +596,8 @@
 		return;
 	mos7715_change_mode(mos_parport, PS2);
 	mos_parport->shadowDCR |= 0x20;
-	write_mos_reg(mos_parport->serial, dummy, DCR, mos_parport->shadowDCR);
+	write_mos_reg(mos_parport->serial, dummy, MOS7720_DCR,
+		      mos_parport->shadowDCR);
 	parport_epilogue(pp);
 }
 
@@ -633,8 +637,10 @@
 		spin_unlock(&release_lock);
 		return;
 	}
-	write_parport_reg_nonblock(mos_parport, DCR, mos_parport->shadowDCR);
-	write_parport_reg_nonblock(mos_parport, ECR, mos_parport->shadowECR);
+	write_parport_reg_nonblock(mos_parport, MOS7720_DCR,
+				   mos_parport->shadowDCR);
+	write_parport_reg_nonblock(mos_parport, MOS7720_ECR,
+				   mos_parport->shadowECR);
 	spin_unlock(&release_lock);
 }
 
@@ -714,14 +720,16 @@
 	init_completion(&mos_parport->syncmsg_compl);
 
 	/* cycle parallel port reset bit */
-	write_mos_reg(mos_parport->serial, dummy, PP_REG, (__u8)0x80);
-	write_mos_reg(mos_parport->serial, dummy, PP_REG, (__u8)0x00);
+	write_mos_reg(mos_parport->serial, dummy, MOS7720_PP_REG, (__u8)0x80);
+	write_mos_reg(mos_parport->serial, dummy, MOS7720_PP_REG, (__u8)0x00);
 
 	/* initialize device registers */
 	mos_parport->shadowDCR = DCR_INIT_VAL;
-	write_mos_reg(mos_parport->serial, dummy, DCR, mos_parport->shadowDCR);
+	write_mos_reg(mos_parport->serial, dummy, MOS7720_DCR,
+		      mos_parport->shadowDCR);
 	mos_parport->shadowECR = ECR_INIT_VAL;
-	write_mos_reg(mos_parport->serial, dummy, ECR, mos_parport->shadowECR);
+	write_mos_reg(mos_parport->serial, dummy, MOS7720_ECR,
+		      mos_parport->shadowECR);
 
 	/* register with parport core */
 	mos_parport->pp = parport_register_port(0, PARPORT_IRQ_NONE,
@@ -1033,45 +1041,49 @@
 	 /* Initialize MCS7720 -- Write Init values to corresponding Registers
 	  *
 	  * Register Index
-	  * 0 : THR/RHR
-	  * 1 : IER
-	  * 2 : FCR
-	  * 3 : LCR
-	  * 4 : MCR
-	  * 5 : LSR
-	  * 6 : MSR
-	  * 7 : SPR
+	  * 0 : MOS7720_THR/MOS7720_RHR
+	  * 1 : MOS7720_IER
+	  * 2 : MOS7720_FCR
+	  * 3 : MOS7720_LCR
+	  * 4 : MOS7720_MCR
+	  * 5 : MOS7720_LSR
+	  * 6 : MOS7720_MSR
+	  * 7 : MOS7720_SPR
 	  *
 	  * 0x08 : SP1/2 Control Reg
 	  */
 	port_number = port->port_number;
-	read_mos_reg(serial, port_number, LSR, &data);
+	read_mos_reg(serial, port_number, MOS7720_LSR, &data);
 
 	dev_dbg(&port->dev, "SS::%p LSR:%x\n", mos7720_port, data);
 
-	write_mos_reg(serial, dummy, SP1_REG, 0x02);
-	write_mos_reg(serial, dummy, SP2_REG, 0x02);
+	write_mos_reg(serial, dummy, MOS7720_SP1_REG, 0x02);
+	write_mos_reg(serial, dummy, MOS7720_SP2_REG, 0x02);
 
-	write_mos_reg(serial, port_number, IER, 0x00);
-	write_mos_reg(serial, port_number, FCR, 0x00);
+	write_mos_reg(serial, port_number, MOS7720_IER, 0x00);
+	write_mos_reg(serial, port_number, MOS7720_FCR, 0x00);
 
-	write_mos_reg(serial, port_number, FCR, 0xcf);
+	write_mos_reg(serial, port_number, MOS7720_FCR, 0xcf);
 	mos7720_port->shadowLCR = 0x03;
-	write_mos_reg(serial, port_number, LCR, mos7720_port->shadowLCR);
+	write_mos_reg(serial, port_number, MOS7720_LCR,
+		      mos7720_port->shadowLCR);
 	mos7720_port->shadowMCR = 0x0b;
-	write_mos_reg(serial, port_number, MCR, mos7720_port->shadowMCR);
+	write_mos_reg(serial, port_number, MOS7720_MCR,
+		      mos7720_port->shadowMCR);
 
-	write_mos_reg(serial, port_number, SP_CONTROL_REG, 0x00);
-	read_mos_reg(serial, dummy, SP_CONTROL_REG, &data);
+	write_mos_reg(serial, port_number, MOS7720_SP_CONTROL_REG, 0x00);
+	read_mos_reg(serial, dummy, MOS7720_SP_CONTROL_REG, &data);
 	data = data | (port->port_number + 1);
-	write_mos_reg(serial, dummy, SP_CONTROL_REG, data);
+	write_mos_reg(serial, dummy, MOS7720_SP_CONTROL_REG, data);
 	mos7720_port->shadowLCR = 0x83;
-	write_mos_reg(serial, port_number, LCR, mos7720_port->shadowLCR);
-	write_mos_reg(serial, port_number, THR, 0x0c);
-	write_mos_reg(serial, port_number, IER, 0x00);
+	write_mos_reg(serial, port_number, MOS7720_LCR,
+		      mos7720_port->shadowLCR);
+	write_mos_reg(serial, port_number, MOS7720_THR, 0x0c);
+	write_mos_reg(serial, port_number, MOS7720_IER, 0x00);
 	mos7720_port->shadowLCR = 0x03;
-	write_mos_reg(serial, port_number, LCR, mos7720_port->shadowLCR);
-	write_mos_reg(serial, port_number, IER, 0x0c);
+	write_mos_reg(serial, port_number, MOS7720_LCR,
+		      mos7720_port->shadowLCR);
+	write_mos_reg(serial, port_number, MOS7720_IER, 0x0c);
 
 	response = usb_submit_urb(port->read_urb, GFP_KERNEL);
 	if (response)
@@ -1144,8 +1156,8 @@
 	usb_kill_urb(port->write_urb);
 	usb_kill_urb(port->read_urb);
 
-	write_mos_reg(serial, port->port_number, MCR, 0x00);
-	write_mos_reg(serial, port->port_number, IER, 0x00);
+	write_mos_reg(serial, port->port_number, MOS7720_MCR, 0x00);
+	write_mos_reg(serial, port->port_number, MOS7720_IER, 0x00);
 
 	mos7720_port->open = 0;
 }
@@ -1169,7 +1181,8 @@
 		data = mos7720_port->shadowLCR & ~UART_LCR_SBC;
 
 	mos7720_port->shadowLCR  = data;
-	write_mos_reg(serial, port->port_number, LCR, mos7720_port->shadowLCR);
+	write_mos_reg(serial, port->port_number, MOS7720_LCR,
+		      mos7720_port->shadowLCR);
 }
 
 /*
@@ -1297,7 +1310,7 @@
 	/* if we are implementing RTS/CTS, toggle that line */
 	if (tty->termios.c_cflag & CRTSCTS) {
 		mos7720_port->shadowMCR &= ~UART_MCR_RTS;
-		write_mos_reg(port->serial, port->port_number, MCR,
+		write_mos_reg(port->serial, port->port_number, MOS7720_MCR,
 			      mos7720_port->shadowMCR);
 	}
 }
@@ -1327,7 +1340,7 @@
 	/* if we are implementing RTS/CTS, toggle that line */
 	if (tty->termios.c_cflag & CRTSCTS) {
 		mos7720_port->shadowMCR |= UART_MCR_RTS;
-		write_mos_reg(port->serial, port->port_number, MCR,
+		write_mos_reg(port->serial, port->port_number, MOS7720_MCR,
 			      mos7720_port->shadowMCR);
 	}
 }
@@ -1352,35 +1365,39 @@
 	dev_dbg(&port->dev, "Sending Setting Commands ..........\n");
 	port_number = port->port_number;
 
-	write_mos_reg(serial, port_number, IER, 0x00);
-	write_mos_reg(serial, port_number, FCR, 0x00);
-	write_mos_reg(serial, port_number, FCR, 0xcf);
+	write_mos_reg(serial, port_number, MOS7720_IER, 0x00);
+	write_mos_reg(serial, port_number, MOS7720_FCR, 0x00);
+	write_mos_reg(serial, port_number, MOS7720_FCR, 0xcf);
 	mos7720_port->shadowMCR = 0x0b;
-	write_mos_reg(serial, port_number, MCR, mos7720_port->shadowMCR);
-	write_mos_reg(serial, dummy, SP_CONTROL_REG, 0x00);
+	write_mos_reg(serial, port_number, MOS7720_MCR,
+		      mos7720_port->shadowMCR);
+	write_mos_reg(serial, dummy, MOS7720_SP_CONTROL_REG, 0x00);
 
 	/***********************************************
 	 *              Set for higher rates           *
 	 ***********************************************/
 	/* writing baud rate verbatum into uart clock field clearly not right */
 	if (port_number == 0)
-		sp_reg = SP1_REG;
+		sp_reg = MOS7720_SP1_REG;
 	else
-		sp_reg = SP2_REG;
+		sp_reg = MOS7720_SP2_REG;
 	write_mos_reg(serial, dummy, sp_reg, baud * 0x10);
-	write_mos_reg(serial, dummy, SP_CONTROL_REG, 0x03);
+	write_mos_reg(serial, dummy, MOS7720_SP_CONTROL_REG, 0x03);
 	mos7720_port->shadowMCR = 0x2b;
-	write_mos_reg(serial, port_number, MCR, mos7720_port->shadowMCR);
+	write_mos_reg(serial, port_number, MOS7720_MCR,
+		      mos7720_port->shadowMCR);
 
 	/***********************************************
 	 *              Set DLL/DLM
 	 ***********************************************/
 	mos7720_port->shadowLCR = mos7720_port->shadowLCR | UART_LCR_DLAB;
-	write_mos_reg(serial, port_number, LCR, mos7720_port->shadowLCR);
-	write_mos_reg(serial, port_number, DLL, 0x01);
-	write_mos_reg(serial, port_number, DLM, 0x00);
+	write_mos_reg(serial, port_number, MOS7720_LCR,
+		      mos7720_port->shadowLCR);
+	write_mos_reg(serial, port_number, MOS7720_DLL, 0x01);
+	write_mos_reg(serial, port_number, MOS7720_DLM, 0x00);
 	mos7720_port->shadowLCR = mos7720_port->shadowLCR & ~UART_LCR_DLAB;
-	write_mos_reg(serial, port_number, LCR, mos7720_port->shadowLCR);
+	write_mos_reg(serial, port_number, MOS7720_LCR,
+		      mos7720_port->shadowLCR);
 
 	return 0;
 }
@@ -1488,15 +1505,16 @@
 
 	/* Enable access to divisor latch */
 	mos7720_port->shadowLCR = mos7720_port->shadowLCR | UART_LCR_DLAB;
-	write_mos_reg(serial, number, LCR, mos7720_port->shadowLCR);
+	write_mos_reg(serial, number, MOS7720_LCR, mos7720_port->shadowLCR);
 
 	/* Write the divisor */
-	write_mos_reg(serial, number, DLL, (__u8)(divisor & 0xff));
-	write_mos_reg(serial, number, DLM, (__u8)((divisor & 0xff00) >> 8));
+	write_mos_reg(serial, number, MOS7720_DLL, (__u8)(divisor & 0xff));
+	write_mos_reg(serial, number, MOS7720_DLM,
+		      (__u8)((divisor & 0xff00) >> 8));
 
 	/* Disable access to divisor latch */
 	mos7720_port->shadowLCR = mos7720_port->shadowLCR & ~UART_LCR_DLAB;
-	write_mos_reg(serial, number, LCR, mos7720_port->shadowLCR);
+	write_mos_reg(serial, number, MOS7720_LCR, mos7720_port->shadowLCR);
 
 	return status;
 }
@@ -1600,14 +1618,16 @@
 
 
 	/* Disable Interrupts */
-	write_mos_reg(serial, port_number, IER, 0x00);
-	write_mos_reg(serial, port_number, FCR, 0x00);
-	write_mos_reg(serial, port_number, FCR, 0xcf);
+	write_mos_reg(serial, port_number, MOS7720_IER, 0x00);
+	write_mos_reg(serial, port_number, MOS7720_FCR, 0x00);
+	write_mos_reg(serial, port_number, MOS7720_FCR, 0xcf);
 
 	/* Send the updated LCR value to the mos7720 */
-	write_mos_reg(serial, port_number, LCR, mos7720_port->shadowLCR);
+	write_mos_reg(serial, port_number, MOS7720_LCR,
+		      mos7720_port->shadowLCR);
 	mos7720_port->shadowMCR = 0x0b;
-	write_mos_reg(serial, port_number, MCR, mos7720_port->shadowMCR);
+	write_mos_reg(serial, port_number, MOS7720_MCR,
+		      mos7720_port->shadowMCR);
 
 	/* set up the MCR register and send it to the mos7720 */
 	mos7720_port->shadowMCR = UART_MCR_OUT2;
@@ -1619,14 +1639,17 @@
 		/* To set hardware flow control to the specified *
 		 * serial port, in SP1/2_CONTROL_REG             */
 		if (port_number)
-			write_mos_reg(serial, dummy, SP_CONTROL_REG, 0x01);
+			write_mos_reg(serial, dummy, MOS7720_SP_CONTROL_REG,
+				      0x01);
 		else
-			write_mos_reg(serial, dummy, SP_CONTROL_REG, 0x02);
+			write_mos_reg(serial, dummy, MOS7720_SP_CONTROL_REG,
+				      0x02);
 
 	} else
 		mos7720_port->shadowMCR &= ~(UART_MCR_XONANY);
 
-	write_mos_reg(serial, port_number, MCR, mos7720_port->shadowMCR);
+	write_mos_reg(serial, port_number, MOS7720_MCR,
+		      mos7720_port->shadowMCR);
 
 	/* Determine divisor based on baud rate */
 	baud = tty_get_baud_rate(tty);
@@ -1639,7 +1662,7 @@
 	if (baud >= 230400) {
 		set_higher_rates(mos7720_port, baud);
 		/* Enable Interrupts */
-		write_mos_reg(serial, port_number, IER, 0x0c);
+		write_mos_reg(serial, port_number, MOS7720_IER, 0x0c);
 		return;
 	}
 
@@ -1650,7 +1673,7 @@
 	if (cflag & CBAUD)
 		tty_encode_baud_rate(tty, baud, baud);
 	/* Enable Interrupts */
-	write_mos_reg(serial, port_number, IER, 0x0c);
+	write_mos_reg(serial, port_number, MOS7720_IER, 0x0c);
 
 	if (port->read_urb->status != -EINPROGRESS) {
 		status = usb_submit_urb(port->read_urb, GFP_KERNEL);
@@ -1725,7 +1748,7 @@
 
 	count = mos7720_chars_in_buffer(tty);
 	if (count == 0) {
-		read_mos_reg(port->serial, port_number, LSR, &data);
+		read_mos_reg(port->serial, port_number, MOS7720_LSR, &data);
 		if ((data & (UART_LSR_TEMT | UART_LSR_THRE))
 					== (UART_LSR_TEMT | UART_LSR_THRE)) {
 			dev_dbg(&port->dev, "%s -- Empty\n", __func__);
@@ -1782,7 +1805,7 @@
 		mcr &= ~UART_MCR_LOOP;
 
 	mos7720_port->shadowMCR = mcr;
-	write_mos_reg(port->serial, port->port_number, MCR,
+	write_mos_reg(port->serial, port->port_number, MOS7720_MCR,
 		      mos7720_port->shadowMCR);
 
 	return 0;
@@ -1827,7 +1850,7 @@
 	}
 
 	mos7720_port->shadowMCR = mcr;
-	write_mos_reg(port->serial, port->port_number, MCR,
+	write_mos_reg(port->serial, port->port_number, MOS7720_MCR,
 		      mos7720_port->shadowMCR);
 
 	return 0;
@@ -1942,7 +1965,7 @@
 	}
 #endif
 	/* LSR For Port 1 */
-	read_mos_reg(serial, 0, LSR, &data);
+	read_mos_reg(serial, 0, MOS7720_LSR, &data);
 	dev_dbg(&dev->dev, "LSR:%x\n", data);
 
 	return 0;
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index f0c0c53..876423b 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1099,6 +1099,8 @@
 	{ USB_DEVICE(QUALCOMM_VENDOR_ID, 0x9000)}, /* SIMCom SIM5218 */
 	{ USB_DEVICE_INTERFACE_CLASS(SIERRA_VENDOR_ID, 0x68c0, 0xff),
 	  .driver_info = (kernel_ulong_t)&sierra_mc73xx_blacklist }, /* MC73xx */
+	{ USB_DEVICE_INTERFACE_CLASS(SIERRA_VENDOR_ID, 0x9041, 0xff),
+	  .driver_info = (kernel_ulong_t)&sierra_mc73xx_blacklist }, /* MC7305/MC7355 */
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6001) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_CMU_300) },
 	{ USB_DEVICE(CMOTECH_VENDOR_ID, CMOTECH_PRODUCT_6003),
@@ -1765,6 +1767,7 @@
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x7d03, 0xff, 0x00, 0x00) },
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e01, 0xff, 0xff, 0xff) }, /* D-Link DWM-152/C1 */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x07d1, 0x3e02, 0xff, 0xff, 0xff) }, /* D-Link DWM-156/C1 */
+	{ USB_DEVICE_INTERFACE_CLASS(0x2020, 0x4000, 0xff) },                /* OLICARD300 - MT6225 */
 	{ USB_DEVICE(INOVIA_VENDOR_ID, INOVIA_SEW858) },
 	{ USB_DEVICE(VIATELECOM_VENDOR_ID, VIATELECOM_PRODUCT_CDS7) },
 	{ } /* Terminating entry */
diff --git a/drivers/usb/serial/qcserial.c b/drivers/usb/serial/qcserial.c
index 9c63897..d156545 100644
--- a/drivers/usb/serial/qcserial.c
+++ b/drivers/usb/serial/qcserial.c
@@ -145,7 +145,6 @@
 	{DEVICE_SWI(0x1199, 0x901c)},	/* Sierra Wireless EM7700 */
 	{DEVICE_SWI(0x1199, 0x901f)},	/* Sierra Wireless EM7355 */
 	{DEVICE_SWI(0x1199, 0x9040)},	/* Sierra Wireless Modem */
-	{DEVICE_SWI(0x1199, 0x9041)},	/* Sierra Wireless MC7305/MC7355 */
 	{DEVICE_SWI(0x1199, 0x9051)},	/* Netgear AirCard 340U */
 	{DEVICE_SWI(0x1199, 0x9053)},	/* Sierra Wireless Modem */
 	{DEVICE_SWI(0x1199, 0x9054)},	/* Sierra Wireless Modem */
@@ -158,6 +157,7 @@
 	{DEVICE_SWI(0x413c, 0x81a4)},	/* Dell Wireless 5570e HSPA+ (42Mbps) Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81a8)},	/* Dell Wireless 5808 Gobi(TM) 4G LTE Mobile Broadband Card */
 	{DEVICE_SWI(0x413c, 0x81a9)},	/* Dell Wireless 5808e Gobi(TM) 4G LTE Mobile Broadband Card */
+	{DEVICE_SWI(0x413c, 0x81b1)},	/* Dell Wireless 5809e Gobi(TM) 4G LTE Mobile Broadband Card */
 
 	/* Huawei devices */
 	{DEVICE_HWI(0x03f0, 0x581d)},	/* HP lt4112 LTE/HSPA+ Gobi 4G Modem (Huawei me906e) */
diff --git a/drivers/usb/serial/sierra.c b/drivers/usb/serial/sierra.c
index 46179a0..07d1ecd 100644
--- a/drivers/usb/serial/sierra.c
+++ b/drivers/usb/serial/sierra.c
@@ -289,6 +289,7 @@
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x1199, 0x68AA, 0xFF, 0xFF, 0xFF),
 	  .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
 	},
+	{ USB_DEVICE(0x1199, 0x68AB) }, /* Sierra Wireless AR8550 */
 	/* AT&T Direct IP LTE modems */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x0F3D, 0x68AA, 0xFF, 0xFF, 0xFF),
 	  .driver_info = (kernel_ulong_t)&direct_ip_interface_blacklist
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 529066b..46f1f13 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -1306,6 +1306,7 @@
 	tty_unregister_driver(usb_serial_tty_driver);
 	put_tty_driver(usb_serial_tty_driver);
 	bus_unregister(&usb_serial_bus_type);
+	idr_destroy(&serial_minors);
 }
 
 
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index caf1888..6b24791 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -2065,6 +2065,18 @@
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_NO_READ_DISC_INFO ),
 
+/* Reported by Oliver Neukum <oneukum@suse.com>
+ * This device morphes spontaneously into another device if the access
+ * pattern of Windows isn't followed. Thus writable media would be dirty
+ * if the initial instance is used. So the device is limited to its
+ * virtual CD.
+ * And yes, the concept that BCD goes up to 9 is not heeded */
+UNUSUAL_DEV( 0x19d2, 0x1225, 0x0000, 0xffff,
+		"ZTE,Incorporated",
+		"ZTE WCDMA Technologies MSM",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_SINGLE_LUN ),
+
 /* Reported by Sven Geggus <sven-usbst@geggus.net>
  * This encrypted pen drive returns bogus data for the initial READ(10).
  */
@@ -2074,6 +2086,17 @@
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_INITIAL_READ10 ),
 
+/* Reported by Hans de Goede <hdegoede@redhat.com>
+ * These are mini projectors using USB for both power and video data transport
+ * The usb-storage interface is a virtual windows driver CD, which the gm12u320
+ * driver automatically converts into framebuffer & kms dri device nodes.
+ */
+UNUSUAL_DEV( 0x1de1, 0xc102, 0x0000, 0xffff,
+		"Grain-media Technology Corp.",
+		"USB3.0 Device GM12U320",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_IGNORE_DEVICE ),
+
 /* Patch by Richard Schütz <r.schtz@t-online.de>
  * This external hard drive enclosure uses a JMicron chip which
  * needs the US_FL_IGNORE_RESIDUE flag to work properly. */
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 2fb29df..563c510 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -689,6 +689,23 @@
 }
 EXPORT_SYMBOL_GPL(vfio_device_get_from_dev);
 
+static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group,
+						     char *buf)
+{
+	struct vfio_device *device;
+
+	mutex_lock(&group->device_lock);
+	list_for_each_entry(device, &group->device_list, group_next) {
+		if (!strcmp(dev_name(device->dev), buf)) {
+			vfio_device_get(device);
+			break;
+		}
+	}
+	mutex_unlock(&group->device_lock);
+
+	return device;
+}
+
 /*
  * Caller must hold a reference to the vfio_device
  */
@@ -1198,53 +1215,53 @@
 {
 	struct vfio_device *device;
 	struct file *filep;
-	int ret = -ENODEV;
+	int ret;
 
 	if (0 == atomic_read(&group->container_users) ||
 	    !group->container->iommu_driver || !vfio_group_viable(group))
 		return -EINVAL;
 
-	mutex_lock(&group->device_lock);
-	list_for_each_entry(device, &group->device_list, group_next) {
-		if (strcmp(dev_name(device->dev), buf))
-			continue;
+	device = vfio_device_get_from_name(group, buf);
+	if (!device)
+		return -ENODEV;
 
-		ret = device->ops->open(device->device_data);
-		if (ret)
-			break;
-		/*
-		 * We can't use anon_inode_getfd() because we need to modify
-		 * the f_mode flags directly to allow more than just ioctls
-		 */
-		ret = get_unused_fd_flags(O_CLOEXEC);
-		if (ret < 0) {
-			device->ops->release(device->device_data);
-			break;
-		}
-
-		filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops,
-					   device, O_RDWR);
-		if (IS_ERR(filep)) {
-			put_unused_fd(ret);
-			ret = PTR_ERR(filep);
-			device->ops->release(device->device_data);
-			break;
-		}
-
-		/*
-		 * TODO: add an anon_inode interface to do this.
-		 * Appears to be missing by lack of need rather than
-		 * explicitly prevented.  Now there's need.
-		 */
-		filep->f_mode |= (FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
-
-		vfio_device_get(device);
-		atomic_inc(&group->container_users);
-
-		fd_install(ret, filep);
-		break;
+	ret = device->ops->open(device->device_data);
+	if (ret) {
+		vfio_device_put(device);
+		return ret;
 	}
-	mutex_unlock(&group->device_lock);
+
+	/*
+	 * We can't use anon_inode_getfd() because we need to modify
+	 * the f_mode flags directly to allow more than just ioctls
+	 */
+	ret = get_unused_fd_flags(O_CLOEXEC);
+	if (ret < 0) {
+		device->ops->release(device->device_data);
+		vfio_device_put(device);
+		return ret;
+	}
+
+	filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops,
+				   device, O_RDWR);
+	if (IS_ERR(filep)) {
+		put_unused_fd(ret);
+		ret = PTR_ERR(filep);
+		device->ops->release(device->device_data);
+		vfio_device_put(device);
+		return ret;
+	}
+
+	/*
+	 * TODO: add an anon_inode interface to do this.
+	 * Appears to be missing by lack of need rather than
+	 * explicitly prevented.  Now there's need.
+	 */
+	filep->f_mode |= (FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
+
+	atomic_inc(&group->container_users);
+
+	fd_install(ret, filep);
 
 	return ret;
 }
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 9e8e004..eec2f11 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -22,14 +22,20 @@
 #include <linux/file.h>
 #include <linux/highmem.h>
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 #include <linux/kthread.h>
 #include <linux/cgroup.h>
 #include <linux/module.h>
+#include <linux/sort.h>
 
 #include "vhost.h"
 
+static ushort max_mem_regions = 64;
+module_param(max_mem_regions, ushort, 0444);
+MODULE_PARM_DESC(max_mem_regions,
+	"Maximum number of memory regions in memory map. (default: 64)");
+
 enum {
-	VHOST_MEMORY_MAX_NREGIONS = 64,
 	VHOST_MEMORY_F_LOG = 0x1,
 };
 
@@ -543,7 +549,7 @@
 		fput(dev->log_file);
 	dev->log_file = NULL;
 	/* No one will access memory at this point */
-	kfree(dev->memory);
+	kvfree(dev->memory);
 	dev->memory = NULL;
 	WARN_ON(!list_empty(&dev->work_list));
 	if (dev->worker) {
@@ -663,6 +669,25 @@
 }
 EXPORT_SYMBOL_GPL(vhost_vq_access_ok);
 
+static int vhost_memory_reg_sort_cmp(const void *p1, const void *p2)
+{
+	const struct vhost_memory_region *r1 = p1, *r2 = p2;
+	if (r1->guest_phys_addr < r2->guest_phys_addr)
+		return 1;
+	if (r1->guest_phys_addr > r2->guest_phys_addr)
+		return -1;
+	return 0;
+}
+
+static void *vhost_kvzalloc(unsigned long size)
+{
+	void *n = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+
+	if (!n)
+		n = vzalloc(size);
+	return n;
+}
+
 static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 {
 	struct vhost_memory mem, *newmem, *oldmem;
@@ -673,21 +698,23 @@
 		return -EFAULT;
 	if (mem.padding)
 		return -EOPNOTSUPP;
-	if (mem.nregions > VHOST_MEMORY_MAX_NREGIONS)
+	if (mem.nregions > max_mem_regions)
 		return -E2BIG;
-	newmem = kmalloc(size + mem.nregions * sizeof *m->regions, GFP_KERNEL);
+	newmem = vhost_kvzalloc(size + mem.nregions * sizeof(*m->regions));
 	if (!newmem)
 		return -ENOMEM;
 
 	memcpy(newmem, &mem, size);
 	if (copy_from_user(newmem->regions, m->regions,
 			   mem.nregions * sizeof *m->regions)) {
-		kfree(newmem);
+		kvfree(newmem);
 		return -EFAULT;
 	}
+	sort(newmem->regions, newmem->nregions, sizeof(*newmem->regions),
+		vhost_memory_reg_sort_cmp, NULL);
 
 	if (!memory_access_ok(d, newmem, 0)) {
-		kfree(newmem);
+		kvfree(newmem);
 		return -EFAULT;
 	}
 	oldmem = d->memory;
@@ -699,7 +726,7 @@
 		d->vqs[i]->memory = newmem;
 		mutex_unlock(&d->vqs[i]->mutex);
 	}
-	kfree(oldmem);
+	kvfree(oldmem);
 	return 0;
 }
 
@@ -965,6 +992,7 @@
 		}
 		if (eventfp != d->log_file) {
 			filep = d->log_file;
+			d->log_file = eventfp;
 			ctx = d->log_ctx;
 			d->log_ctx = eventfp ?
 				eventfd_ctx_fileget(eventfp) : NULL;
@@ -992,17 +1020,22 @@
 static const struct vhost_memory_region *find_region(struct vhost_memory *mem,
 						     __u64 addr, __u32 len)
 {
-	struct vhost_memory_region *reg;
-	int i;
+	const struct vhost_memory_region *reg;
+	int start = 0, end = mem->nregions;
 
-	/* linear search is not brilliant, but we really have on the order of 6
-	 * regions in practice */
-	for (i = 0; i < mem->nregions; ++i) {
-		reg = mem->regions + i;
-		if (reg->guest_phys_addr <= addr &&
-		    reg->guest_phys_addr + reg->memory_size - 1 >= addr)
-			return reg;
+	while (start < end) {
+		int slot = start + (end - start) / 2;
+		reg = mem->regions + slot;
+		if (addr >= reg->guest_phys_addr)
+			end = slot;
+		else
+			start = slot + 1;
 	}
+
+	reg = mem->regions + start;
+	if (addr >= reg->guest_phys_addr &&
+		reg->guest_phys_addr + reg->memory_size > addr)
+		return reg;
 	return NULL;
 }
 
diff --git a/drivers/video/console/fbcon.c b/drivers/video/console/fbcon.c
index 658c34b..1aaf893 100644
--- a/drivers/video/console/fbcon.c
+++ b/drivers/video/console/fbcon.c
@@ -1306,10 +1306,11 @@
 	int y;
  	int c = scr_readw((u16 *) vc->vc_pos);
 
+	ops->cur_blink_jiffies = msecs_to_jiffies(vc->vc_cur_blink_ms);
+
 	if (fbcon_is_inactive(vc, info) || vc->vc_deccm != 1)
 		return;
 
-	ops->cur_blink_jiffies = msecs_to_jiffies(vc->vc_cur_blink_ms);
 	if (vc->vc_cursor_type & 0x10)
 		fbcon_del_cursor_timer(info);
 	else
diff --git a/drivers/video/fbdev/Kconfig b/drivers/video/fbdev/Kconfig
index 2d98de5..f888561 100644
--- a/drivers/video/fbdev/Kconfig
+++ b/drivers/video/fbdev/Kconfig
@@ -298,7 +298,7 @@
 
 # Helper logic selected only by the ARM Versatile platform family.
 config PLAT_VERSATILE_CLCD
-	def_bool ARCH_VERSATILE || ARCH_REALVIEW || ARCH_VEXPRESS
+	def_bool ARCH_VERSATILE || ARCH_REALVIEW || ARCH_VEXPRESS || ARCH_INTEGRATOR
 	depends on ARM
 	depends on FB_ARMCLCD && FB=y
 
diff --git a/drivers/video/fbdev/omap2/dss/dss-of.c b/drivers/video/fbdev/omap2/dss/dss-of.c
index 928ee63..bf407b6 100644
--- a/drivers/video/fbdev/omap2/dss/dss-of.c
+++ b/drivers/video/fbdev/omap2/dss/dss-of.c
@@ -60,6 +60,8 @@
 			}
 			prev = port;
 		} while (of_node_cmp(port->name, "port") != 0);
+
+		of_node_put(ports);
 	}
 
 	return port;
@@ -94,7 +96,7 @@
 	if (!port)
 		return NULL;
 
-	np = of_get_next_parent(port);
+	np = of_get_parent(port);
 
 	for (i = 0; i < 2 && np; ++i) {
 		struct property *prop;
diff --git a/drivers/video/fbdev/pxa3xx-gcu.c b/drivers/video/fbdev/pxa3xx-gcu.c
index 86bd457..50bce45 100644
--- a/drivers/video/fbdev/pxa3xx-gcu.c
+++ b/drivers/video/fbdev/pxa3xx-gcu.c
@@ -653,7 +653,7 @@
 		goto err_free_dma;
 	}
 
-	ret = clk_enable(priv->clk);
+	ret = clk_prepare_enable(priv->clk);
 	if (ret < 0) {
 		dev_err(dev, "failed to enable clock\n");
 		goto err_misc_deregister;
@@ -685,7 +685,7 @@
 	misc_deregister(&priv->misc_dev);
 
 err_disable_clk:
-	clk_disable(priv->clk);
+	clk_disable_unprepare(priv->clk);
 
 	return ret;
 }
diff --git a/drivers/video/fbdev/stifb.c b/drivers/video/fbdev/stifb.c
index 86621fa..735355b 100644
--- a/drivers/video/fbdev/stifb.c
+++ b/drivers/video/fbdev/stifb.c
@@ -121,6 +121,7 @@
 #define REG_3		0x0004a0
 #define REG_4		0x000600
 #define REG_6		0x000800
+#define REG_7		0x000804
 #define REG_8		0x000820
 #define REG_9		0x000a04
 #define REG_10		0x018000
@@ -135,6 +136,8 @@
 #define REG_21		0x200218
 #define REG_22		0x0005a0
 #define REG_23		0x0005c0
+#define REG_24		0x000808
+#define REG_25		0x000b00
 #define REG_26		0x200118
 #define REG_27		0x200308
 #define REG_32		0x21003c
@@ -429,6 +432,9 @@
 #define SET_LENXY_START_RECFILL(fb, lenxy) \
 	WRITE_WORD(lenxy, fb, REG_9)
 
+#define SETUP_COPYAREA(fb) \
+	WRITE_BYTE(0, fb, REG_16b1)
+
 static void
 HYPER_ENABLE_DISABLE_DISPLAY(struct stifb_info *fb, int enable)
 {
@@ -1004,6 +1010,36 @@
 	return 0;
 }
 
+static void
+stifb_copyarea(struct fb_info *info, const struct fb_copyarea *area)
+{
+	struct stifb_info *fb = container_of(info, struct stifb_info, info);
+
+	SETUP_COPYAREA(fb);
+
+	SETUP_HW(fb);
+	if (fb->info.var.bits_per_pixel == 32) {
+		WRITE_WORD(0xBBA0A000, fb, REG_10);
+
+		NGLE_REALLY_SET_IMAGE_PLANEMASK(fb, 0xffffffff);
+	} else {
+		WRITE_WORD(fb->id == S9000_ID_HCRX ? 0x13a02000 : 0x13a01000, fb, REG_10);
+
+		NGLE_REALLY_SET_IMAGE_PLANEMASK(fb, 0xff);
+	}
+
+	NGLE_QUICK_SET_IMAGE_BITMAP_OP(fb,
+		IBOvals(RopSrc, MaskAddrOffset(0),
+		BitmapExtent08, StaticReg(1),
+		DataDynamic, MaskOtc, BGx(0), FGx(0)));
+
+	WRITE_WORD(((area->sx << 16) | area->sy), fb, REG_24);
+	WRITE_WORD(((area->width << 16) | area->height), fb, REG_7);
+	WRITE_WORD(((area->dx << 16) | area->dy), fb, REG_25);
+
+	SETUP_FB(fb);
+}
+
 static void __init
 stifb_init_display(struct stifb_info *fb)
 {
@@ -1069,7 +1105,7 @@
 	.fb_setcolreg	= stifb_setcolreg,
 	.fb_blank	= stifb_blank,
 	.fb_fillrect	= cfb_fillrect,
-	.fb_copyarea	= cfb_copyarea,
+	.fb_copyarea	= stifb_copyarea,
 	.fb_imageblit	= cfb_imageblit,
 };
 
@@ -1258,7 +1294,7 @@
 	info->fbops = &stifb_ops;
 	info->screen_base = ioremap_nocache(REGION_BASE(fb,1), fix->smem_len);
 	info->screen_size = fix->smem_len;
-	info->flags = FBINFO_DEFAULT;
+	info->flags = FBINFO_DEFAULT | FBINFO_HWACCEL_COPYAREA;
 	info->pseudo_palette = &fb->pseudo_palette;
 
 	/* This has to be done !!! */
diff --git a/drivers/video/of_videomode.c b/drivers/video/of_videomode.c
index 111c2d1..b5102aa 100644
--- a/drivers/video/of_videomode.c
+++ b/drivers/video/of_videomode.c
@@ -44,11 +44,9 @@
 		index = disp->native_mode;
 
 	ret = videomode_from_timings(disp, vm, index);
-	if (ret)
-		return ret;
 
 	display_timings_release(disp);
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(of_get_videomode);
diff --git a/drivers/virtio/virtio_input.c b/drivers/virtio/virtio_input.c
index 60e2a16..c96944b 100644
--- a/drivers/virtio/virtio_input.c
+++ b/drivers/virtio/virtio_input.c
@@ -313,6 +313,7 @@
 static void virtinput_remove(struct virtio_device *vdev)
 {
 	struct virtio_input *vi = vdev->priv;
+	void *buf;
 	unsigned long flags;
 
 	spin_lock_irqsave(&vi->lock, flags);
@@ -320,6 +321,9 @@
 	spin_unlock_irqrestore(&vi->lock, flags);
 
 	input_unregister_device(vi->idev);
+	vdev->config->reset(vdev);
+	while ((buf = virtqueue_detach_unused_buf(vi->sts)) != NULL)
+		kfree(buf);
 	vdev->config->del_vqs(vdev);
 	kfree(vi);
 }
diff --git a/drivers/watchdog/sp805_wdt.c b/drivers/watchdog/sp805_wdt.c
index c1b03f4..4e7fec3 100644
--- a/drivers/watchdog/sp805_wdt.c
+++ b/drivers/watchdog/sp805_wdt.c
@@ -4,7 +4,7 @@
  * Watchdog driver for ARM SP805 watchdog module
  *
  * Copyright (C) 2010 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2 or later. This program is licensed "as is" without any
@@ -303,6 +303,6 @@
 
 module_amba_driver(sp805_wdt_driver);
 
-MODULE_AUTHOR("Viresh Kumar <viresh.linux@gmail.com>");
+MODULE_AUTHOR("Viresh Kumar <vireshk@kernel.org>");
 MODULE_DESCRIPTION("ARM SP805 Watchdog Driver");
 MODULE_LICENSE("GPL");
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index fd93369..bf4a23c 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -472,7 +472,7 @@
 }
 
 /*
- * We avoid multiple worker processes conflicting via the balloon mutex.
+ * As this is a work item it is guaranteed to run as a single instance only.
  * We may of course race updates of the target counts (which are protected
  * by the balloon lock), or with changes to the Xen hard limit, but we will
  * recover from these in time.
@@ -482,9 +482,10 @@
 	enum bp_state state = BP_DONE;
 	long credit;
 
-	mutex_lock(&balloon_mutex);
 
 	do {
+		mutex_lock(&balloon_mutex);
+
 		credit = current_credit();
 
 		if (credit > 0) {
@@ -499,17 +500,15 @@
 
 		state = update_schedule(state);
 
-#ifndef CONFIG_PREEMPT
-		if (need_resched())
-			schedule();
-#endif
+		mutex_unlock(&balloon_mutex);
+
+		cond_resched();
+
 	} while (credit && state == BP_DONE);
 
 	/* Schedule more work if there is some still to be done. */
 	if (state == BP_EAGAIN)
 		schedule_delayed_work(&balloon_worker, balloon_stats.schedule_delay * HZ);
-
-	mutex_unlock(&balloon_mutex);
 }
 
 /* Resets the Xen limit, sets new target, and kicks off processing. */
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 67b9163..0dbb222 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -568,12 +568,14 @@
 
 	pr_debug("priv %p\n", priv);
 
+	mutex_lock(&priv->lock);
 	while (!list_empty(&priv->maps)) {
 		map = list_entry(priv->maps.next, struct grant_map, next);
 		list_del(&map->next);
 		gntdev_put_map(NULL /* already removed */, map);
 	}
 	WARN_ON(!list_empty(&priv->freeable_maps));
+	mutex_unlock(&priv->lock);
 
 	if (use_ptemod)
 		mmu_notifier_unregister(&priv->mn, priv->mm);
diff --git a/drivers/xen/xenbus/xenbus_client.c b/drivers/xen/xenbus/xenbus_client.c
index 9ad3272..e303535 100644
--- a/drivers/xen/xenbus/xenbus_client.c
+++ b/drivers/xen/xenbus/xenbus_client.c
@@ -814,8 +814,10 @@
 
 	rv = xenbus_unmap_ring(dev, node->handles, node->nr_handles,
 			       addrs);
-	if (!rv)
+	if (!rv) {
 		vunmap(vaddr);
+		free_xenballooned_pages(node->nr_handles, node->hvm.pages);
+	}
 	else
 		WARN(1, "Leaking %p, size %u page(s)\n", vaddr,
 		     node->nr_handles);
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 510040b..b1dc518 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -540,8 +540,7 @@
 	unlock_new_inode(inode);
 	return inode;
 error:
-	unlock_new_inode(inode);
-	iput(inode);
+	iget_failed(inode);
 	return ERR_PTR(retval);
 
 }
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 09e44337..e8aa57d 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -149,8 +149,7 @@
 	unlock_new_inode(inode);
 	return inode;
 error:
-	unlock_new_inode(inode);
-	iput(inode);
+	iget_failed(inode);
 	return ERR_PTR(retval);
 
 }
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 0ef5cc1..81220b2 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -44,6 +44,8 @@
 #define BTRFS_INODE_IN_DELALLOC_LIST		9
 #define BTRFS_INODE_READDIO_NEED_LOCK		10
 #define BTRFS_INODE_HAS_PROPS		        11
+/* DIO is ready to submit */
+#define BTRFS_INODE_DIO_READY		        12
 /*
  * The following 3 bits are meant only for the btree inode.
  * When any of them is set, it means an error happened while writing an
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 80a9aef..aac314e 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1778,6 +1778,7 @@
 	spinlock_t unused_bgs_lock;
 	struct list_head unused_bgs;
 	struct mutex unused_bg_unpin_mutex;
+	struct mutex delete_unused_bgs_mutex;
 
 	/* For btrfs to record security options */
 	struct security_mnt_opts security_opts;
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 862fbc2..564a7de 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -378,7 +378,7 @@
 
 	ret = btrfs_kobj_add_device(tgt_device->fs_devices, tgt_device);
 	if (ret)
-		btrfs_error(root->fs_info, ret, "kobj add dev failed");
+		btrfs_err(root->fs_info, "kobj add dev failed %d\n", ret);
 
 	printk_in_rcu(KERN_INFO
 		      "BTRFS: dev_replace from %s (devid %llu) to %s started\n",
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 3f43bfea..f556c37 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1751,6 +1751,7 @@
 {
 	struct btrfs_root *root = arg;
 	int again;
+	struct btrfs_trans_handle *trans;
 
 	do {
 		again = 0;
@@ -1772,7 +1773,6 @@
 		}
 
 		btrfs_run_delayed_iputs(root);
-		btrfs_delete_unused_bgs(root->fs_info);
 		again = btrfs_clean_one_deleted_snapshot(root);
 		mutex_unlock(&root->fs_info->cleaner_mutex);
 
@@ -1781,6 +1781,16 @@
 		 * needn't do anything special here.
 		 */
 		btrfs_run_defrag_inodes(root->fs_info);
+
+		/*
+		 * Acquires fs_info->delete_unused_bgs_mutex to avoid racing
+		 * with relocation (btrfs_relocate_chunk) and relocation
+		 * acquires fs_info->cleaner_mutex (btrfs_relocate_block_group)
+		 * after acquiring fs_info->delete_unused_bgs_mutex. So we
+		 * can't hold, nor need to, fs_info->cleaner_mutex when deleting
+		 * unused block groups.
+		 */
+		btrfs_delete_unused_bgs(root->fs_info);
 sleep:
 		if (!try_to_freeze() && !again) {
 			set_current_state(TASK_INTERRUPTIBLE);
@@ -1789,6 +1799,34 @@
 			__set_current_state(TASK_RUNNING);
 		}
 	} while (!kthread_should_stop());
+
+	/*
+	 * Transaction kthread is stopped before us and wakes us up.
+	 * However we might have started a new transaction and COWed some
+	 * tree blocks when deleting unused block groups for example. So
+	 * make sure we commit the transaction we started to have a clean
+	 * shutdown when evicting the btree inode - if it has dirty pages
+	 * when we do the final iput() on it, eviction will trigger a
+	 * writeback for it which will fail with null pointer dereferences
+	 * since work queues and other resources were already released and
+	 * destroyed by the time the iput/eviction/writeback is made.
+	 */
+	trans = btrfs_attach_transaction(root);
+	if (IS_ERR(trans)) {
+		if (PTR_ERR(trans) != -ENOENT)
+			btrfs_err(root->fs_info,
+				  "cleaner transaction attach returned %ld",
+				  PTR_ERR(trans));
+	} else {
+		int ret;
+
+		ret = btrfs_commit_transaction(trans, root);
+		if (ret)
+			btrfs_err(root->fs_info,
+				  "cleaner open transaction commit returned %d",
+				  ret);
+	}
+
 	return 0;
 }
 
@@ -2492,6 +2530,7 @@
 	spin_lock_init(&fs_info->unused_bgs_lock);
 	rwlock_init(&fs_info->tree_mod_log_lock);
 	mutex_init(&fs_info->unused_bg_unpin_mutex);
+	mutex_init(&fs_info->delete_unused_bgs_mutex);
 	mutex_init(&fs_info->reloc_mutex);
 	mutex_init(&fs_info->delalloc_root_mutex);
 	seqlock_init(&fs_info->profiles_lock);
@@ -2803,6 +2842,7 @@
 	    !extent_buffer_uptodate(chunk_root->node)) {
 		printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n",
 		       sb->s_id);
+		chunk_root->node = NULL;
 		goto fail_tree_roots;
 	}
 	btrfs_set_root_node(&chunk_root->root_item, chunk_root->node);
@@ -2840,7 +2880,7 @@
 	    !extent_buffer_uptodate(tree_root->node)) {
 		printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n",
 		       sb->s_id);
-
+		tree_root->node = NULL;
 		goto recovery_tree_root;
 	}
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 38b76cc..07204bf 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2296,9 +2296,22 @@
 static inline struct btrfs_delayed_ref_node *
 select_delayed_ref(struct btrfs_delayed_ref_head *head)
 {
+	struct btrfs_delayed_ref_node *ref;
+
 	if (list_empty(&head->ref_list))
 		return NULL;
 
+	/*
+	 * Select a delayed ref of type BTRFS_ADD_DELAYED_REF first.
+	 * This is to prevent a ref count from going down to zero, which deletes
+	 * the extent item from the extent tree, when there still are references
+	 * to add, which would fail because they would not find the extent item.
+	 */
+	list_for_each_entry(ref, &head->ref_list, list) {
+		if (ref->action == BTRFS_ADD_DELAYED_REF)
+			return ref;
+	}
+
 	return list_entry(head->ref_list.next, struct btrfs_delayed_ref_node,
 			  list);
 }
@@ -4214,6 +4227,24 @@
 	space_info->chunk_alloc = 0;
 	spin_unlock(&space_info->lock);
 	mutex_unlock(&fs_info->chunk_mutex);
+	/*
+	 * When we allocate a new chunk we reserve space in the chunk block
+	 * reserve to make sure we can COW nodes/leafs in the chunk tree or
+	 * add new nodes/leafs to it if we end up needing to do it when
+	 * inserting the chunk item and updating device items as part of the
+	 * second phase of chunk allocation, performed by
+	 * btrfs_finish_chunk_alloc(). So make sure we don't accumulate a
+	 * large number of new block groups to create in our transaction
+	 * handle's new_bgs list to avoid exhausting the chunk block reserve
+	 * in extreme cases - like having a single transaction create many new
+	 * block groups when starting to write out the free space caches of all
+	 * the block groups that were made dirty during the lifetime of the
+	 * transaction.
+	 */
+	if (trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) {
+		btrfs_create_pending_block_groups(trans, trans->root);
+		btrfs_trans_release_chunk_metadata(trans);
+	}
 	return ret;
 }
 
@@ -9889,6 +9920,8 @@
 		}
 		spin_unlock(&fs_info->unused_bgs_lock);
 
+		mutex_lock(&root->fs_info->delete_unused_bgs_mutex);
+
 		/* Don't want to race with allocators so take the groups_sem */
 		down_write(&space_info->groups_sem);
 		spin_lock(&block_group->lock);
@@ -9983,6 +10016,7 @@
 end_trans:
 		btrfs_end_transaction(trans, root);
 next:
+		mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 		btrfs_put_block_group(block_group);
 		spin_lock(&fs_info->unused_bgs_lock);
 	}
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index f6a596d..d4a582a 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -246,6 +246,7 @@
 {
 	struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
 	struct rb_root *rbroot = &root->free_ino_pinned->free_space_offset;
+	spinlock_t *rbroot_lock = &root->free_ino_pinned->tree_lock;
 	struct btrfs_free_space *info;
 	struct rb_node *n;
 	u64 count;
@@ -254,24 +255,30 @@
 		return;
 
 	while (1) {
+		bool add_to_ctl = true;
+
+		spin_lock(rbroot_lock);
 		n = rb_first(rbroot);
-		if (!n)
+		if (!n) {
+			spin_unlock(rbroot_lock);
 			break;
+		}
 
 		info = rb_entry(n, struct btrfs_free_space, offset_index);
 		BUG_ON(info->bitmap); /* Logic error */
 
 		if (info->offset > root->ino_cache_progress)
-			goto free;
+			add_to_ctl = false;
 		else if (info->offset + info->bytes > root->ino_cache_progress)
 			count = root->ino_cache_progress - info->offset + 1;
 		else
 			count = info->bytes;
 
-		__btrfs_add_free_space(ctl, info->offset, count);
-free:
 		rb_erase(&info->offset_index, rbroot);
-		kfree(info);
+		spin_unlock(rbroot_lock);
+		if (add_to_ctl)
+			__btrfs_add_free_space(ctl, info->offset, count);
+		kmem_cache_free(btrfs_free_space_cachep, info);
 	}
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 855935f..e33dff3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4209,7 +4209,7 @@
 	u64 extent_num_bytes = 0;
 	u64 extent_offset = 0;
 	u64 item_end = 0;
-	u64 last_size = (u64)-1;
+	u64 last_size = new_size;
 	u32 found_type = (u8)-1;
 	int found_extent;
 	int del_item;
@@ -4493,8 +4493,7 @@
 			btrfs_abort_transaction(trans, root, ret);
 	}
 error:
-	if (last_size != (u64)-1 &&
-	    root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
+	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
 		btrfs_ordered_update_i_size(inode, last_size, NULL);
 
 	btrfs_free_path(path);
@@ -4989,8 +4988,9 @@
 	/*
 	 * Keep looping until we have no more ranges in the io tree.
 	 * We can have ongoing bios started by readpages (called from readahead)
-	 * that didn't get their end io callbacks called yet or they are still
-	 * in progress ((extent_io.c:end_bio_extent_readpage()). This means some
+	 * that have their endio callback (extent_io.c:end_bio_extent_readpage)
+	 * still in progress (unlocked the pages in the bio but did not yet
+	 * unlocked the ranges in the io tree). Therefore this means some
 	 * ranges can still be locked and eviction started because before
 	 * submitting those bios, which are executed by a separate task (work
 	 * queue kthread), inode references (inode->i_count) were not taken
@@ -7546,6 +7546,7 @@
 
 		current->journal_info = outstanding_extents;
 		btrfs_free_reserved_data_space(inode, len);
+		set_bit(BTRFS_INODE_DIO_READY, &BTRFS_I(inode)->runtime_flags);
 	}
 
 	/*
@@ -7871,8 +7872,6 @@
 	struct bio *dio_bio;
 	int ret;
 
-	if (err)
-		goto out_done;
 again:
 	ret = btrfs_dec_test_first_ordered_pending(inode, &ordered,
 						   &ordered_offset,
@@ -7895,7 +7894,6 @@
 		ordered = NULL;
 		goto again;
 	}
-out_done:
 	dio_bio = dip->dio_bio;
 
 	kfree(dip);
@@ -8163,9 +8161,8 @@
 static void btrfs_submit_direct(int rw, struct bio *dio_bio,
 				struct inode *inode, loff_t file_offset)
 {
-	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct btrfs_dio_private *dip;
-	struct bio *io_bio;
+	struct btrfs_dio_private *dip = NULL;
+	struct bio *io_bio = NULL;
 	struct btrfs_io_bio *btrfs_bio;
 	int skip_sum;
 	int write = rw & REQ_WRITE;
@@ -8182,7 +8179,7 @@
 	dip = kzalloc(sizeof(*dip), GFP_NOFS);
 	if (!dip) {
 		ret = -ENOMEM;
-		goto free_io_bio;
+		goto free_ordered;
 	}
 
 	dip->private = dio_bio->bi_private;
@@ -8210,25 +8207,55 @@
 
 	if (btrfs_bio->end_io)
 		btrfs_bio->end_io(btrfs_bio, ret);
-free_io_bio:
-	bio_put(io_bio);
 
 free_ordered:
 	/*
-	 * If this is a write, we need to clean up the reserved space and kill
-	 * the ordered extent.
+	 * If we arrived here it means either we failed to submit the dip
+	 * or we either failed to clone the dio_bio or failed to allocate the
+	 * dip. If we cloned the dio_bio and allocated the dip, we can just
+	 * call bio_endio against our io_bio so that we get proper resource
+	 * cleanup if we fail to submit the dip, otherwise, we must do the
+	 * same as btrfs_endio_direct_[write|read] because we can't call these
+	 * callbacks - they require an allocated dip and a clone of dio_bio.
 	 */
-	if (write) {
-		struct btrfs_ordered_extent *ordered;
-		ordered = btrfs_lookup_ordered_extent(inode, file_offset);
-		if (!test_bit(BTRFS_ORDERED_PREALLOC, &ordered->flags) &&
-		    !test_bit(BTRFS_ORDERED_NOCOW, &ordered->flags))
-			btrfs_free_reserved_extent(root, ordered->start,
-						   ordered->disk_len, 1);
-		btrfs_put_ordered_extent(ordered);
-		btrfs_put_ordered_extent(ordered);
+	if (io_bio && dip) {
+		bio_endio(io_bio, ret);
+		/*
+		 * The end io callbacks free our dip, do the final put on io_bio
+		 * and all the cleanup and final put for dio_bio (through
+		 * dio_end_io()).
+		 */
+		dip = NULL;
+		io_bio = NULL;
+	} else {
+		if (write) {
+			struct btrfs_ordered_extent *ordered;
+
+			ordered = btrfs_lookup_ordered_extent(inode,
+							      file_offset);
+			set_bit(BTRFS_ORDERED_IOERR, &ordered->flags);
+			/*
+			 * Decrements our ref on the ordered extent and removes
+			 * the ordered extent from the inode's ordered tree,
+			 * doing all the proper resource cleanup such as for the
+			 * reserved space and waking up any waiters for this
+			 * ordered extent (through btrfs_remove_ordered_extent).
+			 */
+			btrfs_finish_ordered_io(ordered);
+		} else {
+			unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
+			      file_offset + dio_bio->bi_iter.bi_size - 1);
+		}
+		clear_bit(BIO_UPTODATE, &dio_bio->bi_flags);
+		/*
+		 * Releases and cleans up our dio_bio, no need to bio_put()
+		 * nor bio_endio()/bio_io_error() against dio_bio.
+		 */
+		dio_end_io(dio_bio, ret);
 	}
-	bio_endio(dio_bio, ret);
+	if (io_bio)
+		bio_put(io_bio);
+	kfree(dip);
 }
 
 static ssize_t check_direct_IO(struct btrfs_root *root, struct kiocb *iocb,
@@ -8330,9 +8357,18 @@
 				   btrfs_submit_direct, flags);
 	if (iov_iter_rw(iter) == WRITE) {
 		current->journal_info = NULL;
-		if (ret < 0 && ret != -EIOCBQUEUED)
-			btrfs_delalloc_release_space(inode, count);
-		else if (ret >= 0 && (size_t)ret < count)
+		if (ret < 0 && ret != -EIOCBQUEUED) {
+			/*
+			 * If the error comes from submitting stage,
+			 * btrfs_get_blocsk_direct() has free'd data space,
+			 * and metadata space will be handled by
+			 * finish_ordered_fn, don't do that again to make
+			 * sure bytes_may_use is correct.
+			 */
+			if (!test_and_clear_bit(BTRFS_INODE_DIO_READY,
+				     &BTRFS_I(inode)->runtime_flags))
+				btrfs_delalloc_release_space(inode, count);
+		} else if (ret >= 0 && (size_t)ret < count)
 			btrfs_delalloc_release_space(inode,
 						     count - (size_t)ret);
 	}
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index c86b835..0770c91 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -87,7 +87,8 @@
 
 
 static int btrfs_clone(struct inode *src, struct inode *inode,
-		       u64 off, u64 olen, u64 olen_aligned, u64 destoff);
+		       u64 off, u64 olen, u64 olen_aligned, u64 destoff,
+		       int no_time_update);
 
 /* Mask out flags that are inappropriate for the given type of inode. */
 static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags)
@@ -2765,14 +2766,11 @@
 	return ret;
 }
 
-static struct page *extent_same_get_page(struct inode *inode, u64 off)
+static struct page *extent_same_get_page(struct inode *inode, pgoff_t index)
 {
 	struct page *page;
-	pgoff_t index;
 	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 
-	index = off >> PAGE_CACHE_SHIFT;
-
 	page = grab_cache_page(inode->i_mapping, index);
 	if (!page)
 		return NULL;
@@ -2793,6 +2791,20 @@
 	return page;
 }
 
+static int gather_extent_pages(struct inode *inode, struct page **pages,
+			       int num_pages, u64 off)
+{
+	int i;
+	pgoff_t index = off >> PAGE_CACHE_SHIFT;
+
+	for (i = 0; i < num_pages; i++) {
+		pages[i] = extent_same_get_page(inode, index + i);
+		if (!pages[i])
+			return -ENOMEM;
+	}
+	return 0;
+}
+
 static inline void lock_extent_range(struct inode *inode, u64 off, u64 len)
 {
 	/* do any pending delalloc/csum calc on src, one way or
@@ -2818,52 +2830,120 @@
 	}
 }
 
-static void btrfs_double_unlock(struct inode *inode1, u64 loff1,
-				struct inode *inode2, u64 loff2, u64 len)
+static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2)
 {
-	unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
-	unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
-
 	mutex_unlock(&inode1->i_mutex);
 	mutex_unlock(&inode2->i_mutex);
 }
 
-static void btrfs_double_lock(struct inode *inode1, u64 loff1,
-			      struct inode *inode2, u64 loff2, u64 len)
+static void btrfs_double_inode_lock(struct inode *inode1, struct inode *inode2)
+{
+	if (inode1 < inode2)
+		swap(inode1, inode2);
+
+	mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
+	if (inode1 != inode2)
+		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
+}
+
+static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
+				      struct inode *inode2, u64 loff2, u64 len)
+{
+	unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
+	unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
+}
+
+static void btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
+				     struct inode *inode2, u64 loff2, u64 len)
 {
 	if (inode1 < inode2) {
 		swap(inode1, inode2);
 		swap(loff1, loff2);
 	}
-
-	mutex_lock_nested(&inode1->i_mutex, I_MUTEX_PARENT);
 	lock_extent_range(inode1, loff1, len);
-	if (inode1 != inode2) {
-		mutex_lock_nested(&inode2->i_mutex, I_MUTEX_CHILD);
+	if (inode1 != inode2)
 		lock_extent_range(inode2, loff2, len);
+}
+
+struct cmp_pages {
+	int		num_pages;
+	struct page	**src_pages;
+	struct page	**dst_pages;
+};
+
+static void btrfs_cmp_data_free(struct cmp_pages *cmp)
+{
+	int i;
+	struct page *pg;
+
+	for (i = 0; i < cmp->num_pages; i++) {
+		pg = cmp->src_pages[i];
+		if (pg)
+			page_cache_release(pg);
+		pg = cmp->dst_pages[i];
+		if (pg)
+			page_cache_release(pg);
 	}
+	kfree(cmp->src_pages);
+	kfree(cmp->dst_pages);
+}
+
+static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
+				  struct inode *dst, u64 dst_loff,
+				  u64 len, struct cmp_pages *cmp)
+{
+	int ret;
+	int num_pages = PAGE_CACHE_ALIGN(len) >> PAGE_CACHE_SHIFT;
+	struct page **src_pgarr, **dst_pgarr;
+
+	/*
+	 * We must gather up all the pages before we initiate our
+	 * extent locking. We use an array for the page pointers. Size
+	 * of the array is bounded by len, which is in turn bounded by
+	 * BTRFS_MAX_DEDUPE_LEN.
+	 */
+	src_pgarr = kzalloc(num_pages * sizeof(struct page *), GFP_NOFS);
+	dst_pgarr = kzalloc(num_pages * sizeof(struct page *), GFP_NOFS);
+	if (!src_pgarr || !dst_pgarr) {
+		kfree(src_pgarr);
+		kfree(dst_pgarr);
+		return -ENOMEM;
+	}
+	cmp->num_pages = num_pages;
+	cmp->src_pages = src_pgarr;
+	cmp->dst_pages = dst_pgarr;
+
+	ret = gather_extent_pages(src, cmp->src_pages, cmp->num_pages, loff);
+	if (ret)
+		goto out;
+
+	ret = gather_extent_pages(dst, cmp->dst_pages, cmp->num_pages, dst_loff);
+
+out:
+	if (ret)
+		btrfs_cmp_data_free(cmp);
+	return 0;
 }
 
 static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
-			  u64 dst_loff, u64 len)
+			  u64 dst_loff, u64 len, struct cmp_pages *cmp)
 {
 	int ret = 0;
+	int i;
 	struct page *src_page, *dst_page;
 	unsigned int cmp_len = PAGE_CACHE_SIZE;
 	void *addr, *dst_addr;
 
+	i = 0;
 	while (len) {
 		if (len < PAGE_CACHE_SIZE)
 			cmp_len = len;
 
-		src_page = extent_same_get_page(src, loff);
-		if (!src_page)
-			return -EINVAL;
-		dst_page = extent_same_get_page(dst, dst_loff);
-		if (!dst_page) {
-			page_cache_release(src_page);
-			return -EINVAL;
-		}
+		BUG_ON(i >= cmp->num_pages);
+
+		src_page = cmp->src_pages[i];
+		dst_page = cmp->dst_pages[i];
+
 		addr = kmap_atomic(src_page);
 		dst_addr = kmap_atomic(dst_page);
 
@@ -2875,15 +2955,12 @@
 
 		kunmap_atomic(addr);
 		kunmap_atomic(dst_addr);
-		page_cache_release(src_page);
-		page_cache_release(dst_page);
 
 		if (ret)
 			break;
 
-		loff += cmp_len;
-		dst_loff += cmp_len;
 		len -= cmp_len;
+		i++;
 	}
 
 	return ret;
@@ -2914,27 +2991,62 @@
 {
 	int ret;
 	u64 len = olen;
+	struct cmp_pages cmp;
+	int same_inode = 0;
+	u64 same_lock_start = 0;
+	u64 same_lock_len = 0;
 
-	/*
-	 * btrfs_clone() can't handle extents in the same file
-	 * yet. Once that works, we can drop this check and replace it
-	 * with a check for the same inode, but overlapping extents.
-	 */
 	if (src == dst)
-		return -EINVAL;
+		same_inode = 1;
 
 	if (len == 0)
 		return 0;
 
-	btrfs_double_lock(src, loff, dst, dst_loff, len);
+	if (same_inode) {
+		mutex_lock(&src->i_mutex);
 
-	ret = extent_same_check_offsets(src, loff, &len, olen);
-	if (ret)
-		goto out_unlock;
+		ret = extent_same_check_offsets(src, loff, &len, olen);
+		if (ret)
+			goto out_unlock;
 
-	ret = extent_same_check_offsets(dst, dst_loff, &len, olen);
-	if (ret)
-		goto out_unlock;
+		/*
+		 * Single inode case wants the same checks, except we
+		 * don't want our length pushed out past i_size as
+		 * comparing that data range makes no sense.
+		 *
+		 * extent_same_check_offsets() will do this for an
+		 * unaligned length at i_size, so catch it here and
+		 * reject the request.
+		 *
+		 * This effectively means we require aligned extents
+		 * for the single-inode case, whereas the other cases
+		 * allow an unaligned length so long as it ends at
+		 * i_size.
+		 */
+		if (len != olen) {
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+
+		/* Check for overlapping ranges */
+		if (dst_loff + len > loff && dst_loff < loff + len) {
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+
+		same_lock_start = min_t(u64, loff, dst_loff);
+		same_lock_len = max_t(u64, loff, dst_loff) + len - same_lock_start;
+	} else {
+		btrfs_double_inode_lock(src, dst);
+
+		ret = extent_same_check_offsets(src, loff, &len, olen);
+		if (ret)
+			goto out_unlock;
+
+		ret = extent_same_check_offsets(dst, dst_loff, &len, olen);
+		if (ret)
+			goto out_unlock;
+	}
 
 	/* don't make the dst file partly checksummed */
 	if ((BTRFS_I(src)->flags & BTRFS_INODE_NODATASUM) !=
@@ -2943,12 +3055,32 @@
 		goto out_unlock;
 	}
 
-	ret = btrfs_cmp_data(src, loff, dst, dst_loff, len);
-	if (ret == 0)
-		ret = btrfs_clone(src, dst, loff, olen, len, dst_loff);
+	ret = btrfs_cmp_data_prepare(src, loff, dst, dst_loff, olen, &cmp);
+	if (ret)
+		goto out_unlock;
 
+	if (same_inode)
+		lock_extent_range(src, same_lock_start, same_lock_len);
+	else
+		btrfs_double_extent_lock(src, loff, dst, dst_loff, len);
+
+	/* pass original length for comparison so we stay within i_size */
+	ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp);
+	if (ret == 0)
+		ret = btrfs_clone(src, dst, loff, olen, len, dst_loff, 1);
+
+	if (same_inode)
+		unlock_extent(&BTRFS_I(src)->io_tree, same_lock_start,
+			      same_lock_start + same_lock_len - 1);
+	else
+		btrfs_double_extent_unlock(src, loff, dst, dst_loff, len);
+
+	btrfs_cmp_data_free(&cmp);
 out_unlock:
-	btrfs_double_unlock(src, loff, dst, dst_loff, len);
+	if (same_inode)
+		mutex_unlock(&src->i_mutex);
+	else
+		btrfs_double_inode_unlock(src, dst);
 
 	return ret;
 }
@@ -2958,7 +3090,7 @@
 static long btrfs_ioctl_file_extent_same(struct file *file,
 			struct btrfs_ioctl_same_args __user *argp)
 {
-	struct btrfs_ioctl_same_args *same;
+	struct btrfs_ioctl_same_args *same = NULL;
 	struct btrfs_ioctl_same_extent_info *info;
 	struct inode *src = file_inode(file);
 	u64 off;
@@ -2988,6 +3120,7 @@
 
 	if (IS_ERR(same)) {
 		ret = PTR_ERR(same);
+		same = NULL;
 		goto out;
 	}
 
@@ -3058,6 +3191,7 @@
 
 out:
 	mnt_drop_write_file(file);
+	kfree(same);
 	return ret;
 }
 
@@ -3100,13 +3234,15 @@
 				     struct inode *inode,
 				     u64 endoff,
 				     const u64 destoff,
-				     const u64 olen)
+				     const u64 olen,
+				     int no_time_update)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret;
 
 	inode_inc_iversion(inode);
-	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+	if (!no_time_update)
+		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
 	/*
 	 * We round up to the block size at eof when determining which
 	 * extents to clone above, but shouldn't round up the file size.
@@ -3191,13 +3327,13 @@
  * @inode: Inode to clone to
  * @off: Offset within source to start clone from
  * @olen: Original length, passed by user, of range to clone
- * @olen_aligned: Block-aligned value of olen, extent_same uses
- *               identical values here
+ * @olen_aligned: Block-aligned value of olen
  * @destoff: Offset within @inode to start clone
+ * @no_time_update: Whether to update mtime/ctime on the target inode
  */
 static int btrfs_clone(struct inode *src, struct inode *inode,
 		       const u64 off, const u64 olen, const u64 olen_aligned,
-		       const u64 destoff)
+		       const u64 destoff, int no_time_update)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_path *path = NULL;
@@ -3452,6 +3588,20 @@
 				u64 trim = 0;
 				u64 aligned_end = 0;
 
+				/*
+				 * Don't copy an inline extent into an offset
+				 * greater than zero. Having an inline extent
+				 * at such an offset results in chaos as btrfs
+				 * isn't prepared for such cases. Just skip
+				 * this case for the same reasons as commented
+				 * at btrfs_ioctl_clone().
+				 */
+				if (last_dest_end > 0) {
+					ret = -EOPNOTSUPP;
+					btrfs_end_transaction(trans, root);
+					goto out;
+				}
+
 				if (off > key.offset) {
 					skip = off - key.offset;
 					new_key.offset += skip;
@@ -3521,7 +3671,8 @@
 					      root->sectorsize);
 			ret = clone_finish_inode_update(trans, inode,
 							last_dest_end,
-							destoff, olen);
+							destoff, olen,
+							no_time_update);
 			if (ret)
 				goto out;
 			if (new_key.offset + datal >= destoff + len)
@@ -3559,7 +3710,7 @@
 		clone_update_extent_map(inode, trans, NULL, last_dest_end,
 					destoff + len - last_dest_end);
 		ret = clone_finish_inode_update(trans, inode, destoff + len,
-						destoff, olen);
+						destoff, olen, no_time_update);
 	}
 
 out:
@@ -3696,7 +3847,7 @@
 		lock_extent_range(inode, destoff, len);
 	}
 
-	ret = btrfs_clone(src, inode, off, olen, len, destoff);
+	ret = btrfs_clone(src, inode, off, olen, len, destoff, 0);
 
 	if (same_inode) {
 		u64 lock_start = min_t(u64, off, destoff);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 89656d7..52170cf 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -552,6 +552,10 @@
 	trace_btrfs_ordered_extent_put(entry->inode, entry);
 
 	if (atomic_dec_and_test(&entry->refs)) {
+		ASSERT(list_empty(&entry->log_list));
+		ASSERT(list_empty(&entry->trans_list));
+		ASSERT(list_empty(&entry->root_extent_list));
+		ASSERT(RB_EMPTY_NODE(&entry->rb_node));
 		if (entry->inode)
 			btrfs_add_delayed_iput(entry->inode);
 		while (!list_empty(&entry->list)) {
@@ -579,6 +583,7 @@
 	spin_lock_irq(&tree->lock);
 	node = &entry->rb_node;
 	rb_erase(node, &tree->tree);
+	RB_CLEAR_NODE(node);
 	if (tree->last == node)
 		tree->last = NULL;
 	set_bit(BTRFS_ORDERED_COMPLETE, &entry->flags);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index d5f1f03..8a82029 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1349,6 +1349,11 @@
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	int ret = 0;
+	/* Sometimes we would want to clear the limit on this qgroup.
+	 * To meet this requirement, we treat the -1 as a special value
+	 * which tell kernel to clear the limit on this qgroup.
+	 */
+	const u64 CLEAR_VALUE = -1;
 
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
 	quota_root = fs_info->quota_root;
@@ -1364,14 +1369,42 @@
 	}
 
 	spin_lock(&fs_info->qgroup_lock);
-	if (limit->flags & BTRFS_QGROUP_LIMIT_MAX_RFER)
-		qgroup->max_rfer = limit->max_rfer;
-	if (limit->flags & BTRFS_QGROUP_LIMIT_MAX_EXCL)
-		qgroup->max_excl = limit->max_excl;
-	if (limit->flags & BTRFS_QGROUP_LIMIT_RSV_RFER)
-		qgroup->rsv_rfer = limit->rsv_rfer;
-	if (limit->flags & BTRFS_QGROUP_LIMIT_RSV_EXCL)
-		qgroup->rsv_excl = limit->rsv_excl;
+	if (limit->flags & BTRFS_QGROUP_LIMIT_MAX_RFER) {
+		if (limit->max_rfer == CLEAR_VALUE) {
+			qgroup->lim_flags &= ~BTRFS_QGROUP_LIMIT_MAX_RFER;
+			limit->flags &= ~BTRFS_QGROUP_LIMIT_MAX_RFER;
+			qgroup->max_rfer = 0;
+		} else {
+			qgroup->max_rfer = limit->max_rfer;
+		}
+	}
+	if (limit->flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) {
+		if (limit->max_excl == CLEAR_VALUE) {
+			qgroup->lim_flags &= ~BTRFS_QGROUP_LIMIT_MAX_EXCL;
+			limit->flags &= ~BTRFS_QGROUP_LIMIT_MAX_EXCL;
+			qgroup->max_excl = 0;
+		} else {
+			qgroup->max_excl = limit->max_excl;
+		}
+	}
+	if (limit->flags & BTRFS_QGROUP_LIMIT_RSV_RFER) {
+		if (limit->rsv_rfer == CLEAR_VALUE) {
+			qgroup->lim_flags &= ~BTRFS_QGROUP_LIMIT_RSV_RFER;
+			limit->flags &= ~BTRFS_QGROUP_LIMIT_RSV_RFER;
+			qgroup->rsv_rfer = 0;
+		} else {
+			qgroup->rsv_rfer = limit->rsv_rfer;
+		}
+	}
+	if (limit->flags & BTRFS_QGROUP_LIMIT_RSV_EXCL) {
+		if (limit->rsv_excl == CLEAR_VALUE) {
+			qgroup->lim_flags &= ~BTRFS_QGROUP_LIMIT_RSV_EXCL;
+			limit->flags &= ~BTRFS_QGROUP_LIMIT_RSV_EXCL;
+			qgroup->rsv_excl = 0;
+		} else {
+			qgroup->rsv_excl = limit->rsv_excl;
+		}
+	}
 	qgroup->lim_flags |= limit->flags;
 
 	spin_unlock(&fs_info->qgroup_lock);
@@ -1618,6 +1651,11 @@
 				/* Exclusive -> exclusive, nothing changed */
 			}
 		}
+
+		/* For exclusive extent, free its reserved bytes too */
+		if (nr_old_roots == 0 && nr_new_roots == 1 &&
+		    cur_new_count == nr_new_roots)
+			qg->reserved -= num_bytes;
 		if (dirty)
 			qgroup_dirty(fs_info, qg);
 	}
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 827951f..88cbb59 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4049,7 +4049,7 @@
 	if (trans && progress && err == -ENOSPC) {
 		ret = btrfs_force_chunk_alloc(trans, rc->extent_root,
 					      rc->block_group->flags);
-		if (ret == 0) {
+		if (ret == 1) {
 			err = 0;
 			progress = 0;
 			goto restart;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 9f2feab..94db0fa 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3571,7 +3571,6 @@
 static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info,
 						int is_dev_replace)
 {
-	int ret = 0;
 	unsigned int flags = WQ_FREEZABLE | WQ_UNBOUND;
 	int max_active = fs_info->thread_pool_size;
 
@@ -3584,34 +3583,36 @@
 			fs_info->scrub_workers =
 				btrfs_alloc_workqueue("btrfs-scrub", flags,
 						      max_active, 4);
-		if (!fs_info->scrub_workers) {
-			ret = -ENOMEM;
-			goto out;
-		}
+		if (!fs_info->scrub_workers)
+			goto fail_scrub_workers;
+
 		fs_info->scrub_wr_completion_workers =
 			btrfs_alloc_workqueue("btrfs-scrubwrc", flags,
 					      max_active, 2);
-		if (!fs_info->scrub_wr_completion_workers) {
-			ret = -ENOMEM;
-			goto out;
-		}
+		if (!fs_info->scrub_wr_completion_workers)
+			goto fail_scrub_wr_completion_workers;
+
 		fs_info->scrub_nocow_workers =
 			btrfs_alloc_workqueue("btrfs-scrubnc", flags, 1, 0);
-		if (!fs_info->scrub_nocow_workers) {
-			ret = -ENOMEM;
-			goto out;
-		}
+		if (!fs_info->scrub_nocow_workers)
+			goto fail_scrub_nocow_workers;
 		fs_info->scrub_parity_workers =
 			btrfs_alloc_workqueue("btrfs-scrubparity", flags,
 					      max_active, 2);
-		if (!fs_info->scrub_parity_workers) {
-			ret = -ENOMEM;
-			goto out;
-		}
+		if (!fs_info->scrub_parity_workers)
+			goto fail_scrub_parity_workers;
 	}
 	++fs_info->scrub_workers_refcnt;
-out:
-	return ret;
+	return 0;
+
+fail_scrub_parity_workers:
+	btrfs_destroy_workqueue(fs_info->scrub_nocow_workers);
+fail_scrub_nocow_workers:
+	btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers);
+fail_scrub_wr_completion_workers:
+	btrfs_destroy_workqueue(fs_info->scrub_workers);
+fail_scrub_workers:
+	return -ENOMEM;
 }
 
 static noinline_for_stack void scrub_workers_put(struct btrfs_fs_info *fs_info)
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index c0f18e7..f5021fc 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -761,7 +761,7 @@
 
 	if (!list_empty(&trans->ordered)) {
 		spin_lock(&info->trans_lock);
-		list_splice(&trans->ordered, &cur_trans->pending_ordered);
+		list_splice_init(&trans->ordered, &cur_trans->pending_ordered);
 		spin_unlock(&info->trans_lock);
 	}
 
@@ -1866,7 +1866,7 @@
 	}
 
 	spin_lock(&root->fs_info->trans_lock);
-	list_splice(&trans->ordered, &cur_trans->pending_ordered);
+	list_splice_init(&trans->ordered, &cur_trans->pending_ordered);
 	if (cur_trans->state >= TRANS_STATE_COMMIT_START) {
 		spin_unlock(&root->fs_info->trans_lock);
 		atomic_inc(&cur_trans->use_count);
@@ -2152,7 +2152,8 @@
 
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
 
-	if (current != root->fs_info->transaction_kthread)
+	if (current != root->fs_info->transaction_kthread &&
+	    current != root->fs_info->cleaner_kthread)
 		btrfs_run_delayed_iputs(root);
 
 	return ret;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 1ce80c1..9c45431 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4117,6 +4117,187 @@
 	return 0;
 }
 
+/*
+ * At the moment we always log all xattrs. This is to figure out at log replay
+ * time which xattrs must have their deletion replayed. If a xattr is missing
+ * in the log tree and exists in the fs/subvol tree, we delete it. This is
+ * because if a xattr is deleted, the inode is fsynced and a power failure
+ * happens, causing the log to be replayed the next time the fs is mounted,
+ * we want the xattr to not exist anymore (same behaviour as other filesystems
+ * with a journal, ext3/4, xfs, f2fs, etc).
+ */
+static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
+				struct btrfs_root *root,
+				struct inode *inode,
+				struct btrfs_path *path,
+				struct btrfs_path *dst_path)
+{
+	int ret;
+	struct btrfs_key key;
+	const u64 ino = btrfs_ino(inode);
+	int ins_nr = 0;
+	int start_slot = 0;
+
+	key.objectid = ino;
+	key.type = BTRFS_XATTR_ITEM_KEY;
+	key.offset = 0;
+
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		return ret;
+
+	while (true) {
+		int slot = path->slots[0];
+		struct extent_buffer *leaf = path->nodes[0];
+		int nritems = btrfs_header_nritems(leaf);
+
+		if (slot >= nritems) {
+			if (ins_nr > 0) {
+				u64 last_extent = 0;
+
+				ret = copy_items(trans, inode, dst_path, path,
+						 &last_extent, start_slot,
+						 ins_nr, 1, 0);
+				/* can't be 1, extent items aren't processed */
+				ASSERT(ret <= 0);
+				if (ret < 0)
+					return ret;
+				ins_nr = 0;
+			}
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				return ret;
+			else if (ret > 0)
+				break;
+			continue;
+		}
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+		if (key.objectid != ino || key.type != BTRFS_XATTR_ITEM_KEY)
+			break;
+
+		if (ins_nr == 0)
+			start_slot = slot;
+		ins_nr++;
+		path->slots[0]++;
+		cond_resched();
+	}
+	if (ins_nr > 0) {
+		u64 last_extent = 0;
+
+		ret = copy_items(trans, inode, dst_path, path,
+				 &last_extent, start_slot,
+				 ins_nr, 1, 0);
+		/* can't be 1, extent items aren't processed */
+		ASSERT(ret <= 0);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * If the no holes feature is enabled we need to make sure any hole between the
+ * last extent and the i_size of our inode is explicitly marked in the log. This
+ * is to make sure that doing something like:
+ *
+ *      1) create file with 128Kb of data
+ *      2) truncate file to 64Kb
+ *      3) truncate file to 256Kb
+ *      4) fsync file
+ *      5) <crash/power failure>
+ *      6) mount fs and trigger log replay
+ *
+ * Will give us a file with a size of 256Kb, the first 64Kb of data match what
+ * the file had in its first 64Kb of data at step 1 and the last 192Kb of the
+ * file correspond to a hole. The presence of explicit holes in a log tree is
+ * what guarantees that log replay will remove/adjust file extent items in the
+ * fs/subvol tree.
+ *
+ * Here we do not need to care about holes between extents, that is already done
+ * by copy_items(). We also only need to do this in the full sync path, where we
+ * lookup for extents from the fs/subvol tree only. In the fast path case, we
+ * lookup the list of modified extent maps and if any represents a hole, we
+ * insert a corresponding extent representing a hole in the log tree.
+ */
+static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
+				   struct btrfs_root *root,
+				   struct inode *inode,
+				   struct btrfs_path *path)
+{
+	int ret;
+	struct btrfs_key key;
+	u64 hole_start;
+	u64 hole_size;
+	struct extent_buffer *leaf;
+	struct btrfs_root *log = root->log_root;
+	const u64 ino = btrfs_ino(inode);
+	const u64 i_size = i_size_read(inode);
+
+	if (!btrfs_fs_incompat(root->fs_info, NO_HOLES))
+		return 0;
+
+	key.objectid = ino;
+	key.type = BTRFS_EXTENT_DATA_KEY;
+	key.offset = (u64)-1;
+
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	ASSERT(ret != 0);
+	if (ret < 0)
+		return ret;
+
+	ASSERT(path->slots[0] > 0);
+	path->slots[0]--;
+	leaf = path->nodes[0];
+	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+
+	if (key.objectid != ino || key.type != BTRFS_EXTENT_DATA_KEY) {
+		/* inode does not have any extents */
+		hole_start = 0;
+		hole_size = i_size;
+	} else {
+		struct btrfs_file_extent_item *extent;
+		u64 len;
+
+		/*
+		 * If there's an extent beyond i_size, an explicit hole was
+		 * already inserted by copy_items().
+		 */
+		if (key.offset >= i_size)
+			return 0;
+
+		extent = btrfs_item_ptr(leaf, path->slots[0],
+					struct btrfs_file_extent_item);
+
+		if (btrfs_file_extent_type(leaf, extent) ==
+		    BTRFS_FILE_EXTENT_INLINE) {
+			len = btrfs_file_extent_inline_len(leaf,
+							   path->slots[0],
+							   extent);
+			ASSERT(len == i_size);
+			return 0;
+		}
+
+		len = btrfs_file_extent_num_bytes(leaf, extent);
+		/* Last extent goes beyond i_size, no need to log a hole. */
+		if (key.offset + len > i_size)
+			return 0;
+		hole_start = key.offset + len;
+		hole_size = i_size - hole_start;
+	}
+	btrfs_release_path(path);
+
+	/* Last extent ends at i_size. */
+	if (hole_size == 0)
+		return 0;
+
+	hole_size = ALIGN(hole_size, root->sectorsize);
+	ret = btrfs_insert_file_extent(trans, log, ino, hole_start, 0, 0,
+				       hole_size, 0, hole_size, 0, 0, 0);
+	return ret;
+}
+
 /* log a single inode in the tree log.
  * At least one parent directory for this inode must exist in the tree
  * or be logged already.
@@ -4155,6 +4336,7 @@
 	u64 ino = btrfs_ino(inode);
 	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
 	u64 logged_isize = 0;
+	bool need_log_inode_item = true;
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -4263,11 +4445,6 @@
 		} else {
 			if (inode_only == LOG_INODE_ALL)
 				fast_search = true;
-			ret = log_inode_item(trans, log, dst_path, inode);
-			if (ret) {
-				err = ret;
-				goto out_unlock;
-			}
 			goto log_extents;
 		}
 
@@ -4290,6 +4467,28 @@
 		if (min_key.type > max_key.type)
 			break;
 
+		if (min_key.type == BTRFS_INODE_ITEM_KEY)
+			need_log_inode_item = false;
+
+		/* Skip xattrs, we log them later with btrfs_log_all_xattrs() */
+		if (min_key.type == BTRFS_XATTR_ITEM_KEY) {
+			if (ins_nr == 0)
+				goto next_slot;
+			ret = copy_items(trans, inode, dst_path, path,
+					 &last_extent, ins_start_slot,
+					 ins_nr, inode_only, logged_isize);
+			if (ret < 0) {
+				err = ret;
+				goto out_unlock;
+			}
+			ins_nr = 0;
+			if (ret) {
+				btrfs_release_path(path);
+				continue;
+			}
+			goto next_slot;
+		}
+
 		src = path->nodes[0];
 		if (ins_nr && ins_start_slot + ins_nr == path->slots[0]) {
 			ins_nr++;
@@ -4357,9 +4556,26 @@
 		ins_nr = 0;
 	}
 
+	btrfs_release_path(path);
+	btrfs_release_path(dst_path);
+	err = btrfs_log_all_xattrs(trans, root, inode, path, dst_path);
+	if (err)
+		goto out_unlock;
+	if (max_key.type >= BTRFS_EXTENT_DATA_KEY && !fast_search) {
+		btrfs_release_path(path);
+		btrfs_release_path(dst_path);
+		err = btrfs_log_trailing_hole(trans, root, inode, path);
+		if (err)
+			goto out_unlock;
+	}
 log_extents:
 	btrfs_release_path(path);
 	btrfs_release_path(dst_path);
+	if (need_log_inode_item) {
+		err = log_inode_item(trans, log, dst_path, inode);
+		if (err)
+			goto out_unlock;
+	}
 	if (fast_search) {
 		/*
 		 * Some ordered extents started by fsync might have completed
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 4b438b4..fbe7c10 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2766,6 +2766,20 @@
 	root = root->fs_info->chunk_root;
 	extent_root = root->fs_info->extent_root;
 
+	/*
+	 * Prevent races with automatic removal of unused block groups.
+	 * After we relocate and before we remove the chunk with offset
+	 * chunk_offset, automatic removal of the block group can kick in,
+	 * resulting in a failure when calling btrfs_remove_chunk() below.
+	 *
+	 * Make sure to acquire this mutex before doing a tree search (dev
+	 * or chunk trees) to find chunks. Otherwise the cleaner kthread might
+	 * call btrfs_remove_chunk() (through btrfs_delete_unused_bgs()) after
+	 * we release the path used to search the chunk/dev tree and before
+	 * the current task acquires this mutex and calls us.
+	 */
+	ASSERT(mutex_is_locked(&root->fs_info->delete_unused_bgs_mutex));
+
 	ret = btrfs_can_relocate(extent_root, chunk_offset);
 	if (ret)
 		return -ENOSPC;
@@ -2814,13 +2828,18 @@
 	key.type = BTRFS_CHUNK_ITEM_KEY;
 
 	while (1) {
+		mutex_lock(&root->fs_info->delete_unused_bgs_mutex);
 		ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
-		if (ret < 0)
+		if (ret < 0) {
+			mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 			goto error;
+		}
 		BUG_ON(ret == 0); /* Corruption */
 
 		ret = btrfs_previous_item(chunk_root, path, key.objectid,
 					  key.type);
+		if (ret)
+			mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 		if (ret < 0)
 			goto error;
 		if (ret > 0)
@@ -2843,6 +2862,7 @@
 			else
 				BUG_ON(ret);
 		}
+		mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 
 		if (found_key.offset == 0)
 			break;
@@ -3299,9 +3319,12 @@
 			goto error;
 		}
 
+		mutex_lock(&fs_info->delete_unused_bgs_mutex);
 		ret = btrfs_search_slot(NULL, chunk_root, &key, path, 0, 0);
-		if (ret < 0)
+		if (ret < 0) {
+			mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 			goto error;
+		}
 
 		/*
 		 * this shouldn't happen, it means the last relocate
@@ -3313,6 +3336,7 @@
 		ret = btrfs_previous_item(chunk_root, path, 0,
 					  BTRFS_CHUNK_ITEM_KEY);
 		if (ret) {
+			mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 			ret = 0;
 			break;
 		}
@@ -3321,8 +3345,10 @@
 		slot = path->slots[0];
 		btrfs_item_key_to_cpu(leaf, &found_key, slot);
 
-		if (found_key.objectid != key.objectid)
+		if (found_key.objectid != key.objectid) {
+			mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 			break;
+		}
 
 		chunk = btrfs_item_ptr(leaf, slot, struct btrfs_chunk);
 
@@ -3335,10 +3361,13 @@
 		ret = should_balance_chunk(chunk_root, leaf, chunk,
 					   found_key.offset);
 		btrfs_release_path(path);
-		if (!ret)
+		if (!ret) {
+			mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 			goto loop;
+		}
 
 		if (counting) {
+			mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 			spin_lock(&fs_info->balance_lock);
 			bctl->stat.expected++;
 			spin_unlock(&fs_info->balance_lock);
@@ -3348,6 +3377,7 @@
 		ret = btrfs_relocate_chunk(chunk_root,
 					   found_key.objectid,
 					   found_key.offset);
+		mutex_unlock(&fs_info->delete_unused_bgs_mutex);
 		if (ret && ret != -ENOSPC)
 			goto error;
 		if (ret == -ENOSPC) {
@@ -4087,11 +4117,16 @@
 	key.type = BTRFS_DEV_EXTENT_KEY;
 
 	do {
+		mutex_lock(&root->fs_info->delete_unused_bgs_mutex);
 		ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-		if (ret < 0)
+		if (ret < 0) {
+			mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 			goto done;
+		}
 
 		ret = btrfs_previous_item(root, path, 0, key.type);
+		if (ret)
+			mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 		if (ret < 0)
 			goto done;
 		if (ret) {
@@ -4105,6 +4140,7 @@
 		btrfs_item_key_to_cpu(l, &key, path->slots[0]);
 
 		if (key.objectid != device->devid) {
+			mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 			btrfs_release_path(path);
 			break;
 		}
@@ -4113,6 +4149,7 @@
 		length = btrfs_dev_extent_length(l, dev_extent);
 
 		if (key.offset + length <= new_size) {
+			mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 			btrfs_release_path(path);
 			break;
 		}
@@ -4122,6 +4159,7 @@
 		btrfs_release_path(path);
 
 		ret = btrfs_relocate_chunk(root, chunk_objectid, chunk_offset);
+		mutex_unlock(&root->fs_info->delete_unused_bgs_mutex);
 		if (ret && ret != -ENOSPC)
 			goto done;
 		if (ret == -ENOSPC)
@@ -5715,7 +5753,6 @@
 static void btrfs_end_bio(struct bio *bio, int err)
 {
 	struct btrfs_bio *bbio = bio->bi_private;
-	struct btrfs_device *dev = bbio->stripes[0].dev;
 	int is_orig_bio = 0;
 
 	if (err) {
@@ -5723,6 +5760,7 @@
 		if (err == -EIO || err == -EREMOTEIO) {
 			unsigned int stripe_index =
 				btrfs_io_bio(bio)->stripe_index;
+			struct btrfs_device *dev;
 
 			BUG_ON(stripe_index >= bbio->num_stripes);
 			dev = bbio->stripes[stripe_index].dev;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index dc10c9d..ddd5e94 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1506,7 +1506,6 @@
 
 	swap(cf, ci->i_prealloc_cap_flush);
 	cf->caps = flushing;
-	cf->kick = false;
 
 	spin_lock(&mdsc->cap_dirty_lock);
 	list_del_init(&ci->i_dirty_item);
@@ -2123,8 +2122,7 @@
 
 static int __kick_flushing_caps(struct ceph_mds_client *mdsc,
 				struct ceph_mds_session *session,
-				struct ceph_inode_info *ci,
-				bool kick_all)
+				struct ceph_inode_info *ci)
 {
 	struct inode *inode = &ci->vfs_inode;
 	struct ceph_cap *cap;
@@ -2150,9 +2148,7 @@
 
 		for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) {
 			cf = rb_entry(n, struct ceph_cap_flush, i_node);
-			if (cf->tid < first_tid)
-				continue;
-			if (kick_all || cf->kick)
+			if (cf->tid >= first_tid)
 				break;
 		}
 		if (!n) {
@@ -2161,7 +2157,6 @@
 		}
 
 		cf = rb_entry(n, struct ceph_cap_flush, i_node);
-		cf->kick = false;
 
 		first_tid = cf->tid + 1;
 
@@ -2181,8 +2176,6 @@
 {
 	struct ceph_inode_info *ci;
 	struct ceph_cap *cap;
-	struct ceph_cap_flush *cf;
-	struct rb_node *n;
 
 	dout("early_kick_flushing_caps mds%d\n", session->s_mds);
 	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
@@ -2205,16 +2198,11 @@
 		if ((cap->issued & ci->i_flushing_caps) !=
 		    ci->i_flushing_caps) {
 			spin_unlock(&ci->i_ceph_lock);
-			if (!__kick_flushing_caps(mdsc, session, ci, true))
+			if (!__kick_flushing_caps(mdsc, session, ci))
 				continue;
 			spin_lock(&ci->i_ceph_lock);
 		}
 
-		for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) {
-			cf = rb_entry(n, struct ceph_cap_flush, i_node);
-			cf->kick = true;
-		}
-
 		spin_unlock(&ci->i_ceph_lock);
 	}
 }
@@ -2228,7 +2216,7 @@
 
 	dout("kick_flushing_caps mds%d\n", session->s_mds);
 	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
-		int delayed = __kick_flushing_caps(mdsc, session, ci, false);
+		int delayed = __kick_flushing_caps(mdsc, session, ci);
 		if (delayed) {
 			spin_lock(&ci->i_ceph_lock);
 			__cap_delay_requeue(mdsc, ci);
@@ -2261,7 +2249,7 @@
 
 		spin_unlock(&ci->i_ceph_lock);
 
-		delayed = __kick_flushing_caps(mdsc, session, ci, true);
+		delayed = __kick_flushing_caps(mdsc, session, ci);
 		if (delayed) {
 			spin_lock(&ci->i_ceph_lock);
 			__cap_delay_requeue(mdsc, ci);
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 4347039..6706bde 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -287,7 +287,7 @@
 		return 0;
 
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
+	list_for_each_entry(lock, &ctx->flc_posix, fl_list) {
 		++seen_fcntl;
 		if (seen_fcntl > num_fcntl_locks) {
 			err = -ENOSPC;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 860cc016..2f2460d 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -189,7 +189,6 @@
 struct ceph_cap_flush {
 	u64 tid;
 	int caps;
-	bool kick;
 	struct rb_node g_node; // global
 	union {
 		struct rb_node i_node; // inode
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 6b8e2f0..48851f6 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -896,6 +896,7 @@
 /* 'X' - originally XFS but some now in the VFS */
 COMPATIBLE_IOCTL(FIFREEZE)
 COMPATIBLE_IOCTL(FITHAW)
+COMPATIBLE_IOCTL(FITRIM)
 COMPATIBLE_IOCTL(KDGETKEYCODE)
 COMPATIBLE_IOCTL(KDSETKEYCODE)
 COMPATIBLE_IOCTL(KDGKBTYPE)
diff --git a/fs/configfs/item.c b/fs/configfs/item.c
index 4d6a30e..b863a09 100644
--- a/fs/configfs/item.c
+++ b/fs/configfs/item.c
@@ -115,7 +115,7 @@
 				const char *name,
 				struct config_item_type *type)
 {
-	config_item_set_name(item, name);
+	config_item_set_name(item, "%s", name);
 	item->ci_type = type;
 	config_item_init(item);
 }
@@ -124,7 +124,7 @@
 void config_group_init_type_name(struct config_group *group, const char *name,
 			 struct config_item_type *type)
 {
-	config_item_set_name(&group->cg_item, name);
+	config_item_set_name(&group->cg_item, "%s", name);
 	group->cg_item.ci_type = type;
 	config_group_init(group);
 }
diff --git a/fs/dax.c b/fs/dax.c
index c3e21cc..a7f77e1 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -319,6 +319,12 @@
  * @vma: The virtual memory area where the fault occurred
  * @vmf: The description of the fault
  * @get_block: The filesystem method used to translate file offsets to blocks
+ * @complete_unwritten: The filesystem method used to convert unwritten blocks
+ *	to written so the data written to them is exposed. This is required for
+ *	required by write faults for filesystems that will return unwritten
+ *	extent mappings from @get_block, but it is optional for reads as
+ *	dax_insert_mapping() will always zero unwritten blocks. If the fs does
+ *	not support unwritten extents, the it should pass NULL.
  *
  * When a page fault occurs, filesystems may call this helper in their
  * fault handler for DAX files. __dax_fault() assumes the caller has done all
@@ -437,8 +443,12 @@
 	 * as for normal BH based IO completions.
 	 */
 	error = dax_insert_mapping(inode, &bh, vma, vmf);
-	if (buffer_unwritten(&bh))
-		complete_unwritten(&bh, !error);
+	if (buffer_unwritten(&bh)) {
+		if (complete_unwritten)
+			complete_unwritten(&bh, !error);
+		else
+			WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE));
+	}
 
  out:
 	if (error == -ENOMEM)
diff --git a/fs/dcache.c b/fs/dcache.c
index 7a3f3e5..9b5fe50 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -642,7 +642,7 @@
 
 	/*
 	 * If we have a d_op->d_delete() operation, we sould not
-	 * let the dentry count go to zero, so use "put__or_lock".
+	 * let the dentry count go to zero, so use "put_or_lock".
 	 */
 	if (unlikely(dentry->d_flags & DCACHE_OP_DELETE))
 		return lockref_put_or_lock(&dentry->d_lockref);
@@ -697,7 +697,7 @@
 	 */
 	smp_rmb();
 	d_flags = ACCESS_ONCE(dentry->d_flags);
-	d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST;
+	d_flags &= DCACHE_REFERENCED | DCACHE_LRU_LIST | DCACHE_DISCONNECTED;
 
 	/* Nothing to do? Dropping the reference was all we needed? */
 	if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry))
@@ -776,6 +776,9 @@
 	if (unlikely(d_unhashed(dentry)))
 		goto kill_it;
 
+	if (unlikely(dentry->d_flags & DCACHE_DISCONNECTED))
+		goto kill_it;
+
 	if (unlikely(dentry->d_flags & DCACHE_OP_DELETE)) {
 		if (dentry->d_op->d_delete(dentry))
 			goto kill_it;
@@ -3439,22 +3442,15 @@
 	inode_init_early();
 }
 
-void __init vfs_caches_init(unsigned long mempages)
+void __init vfs_caches_init(void)
 {
-	unsigned long reserve;
-
-	/* Base hash sizes on available memory, with a reserve equal to
-           150% of current kernel size */
-
-	reserve = min((mempages - nr_free_pages()) * 3/2, mempages - 1);
-	mempages -= reserve;
-
 	names_cachep = kmem_cache_create("names_cache", PATH_MAX, 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
 
 	dcache_init();
 	inode_init();
-	files_init(mempages);
+	files_init();
+	files_maxfiles_init();
 	mnt_init();
 	bdev_cache_init();
 	chrdev_init();
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index 72afcc6..feef8a9 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -325,7 +325,6 @@
 		return rc;
 
 	switch (cmd) {
-	case FITRIM:
 	case FS_IOC32_GETFLAGS:
 	case FS_IOC32_SETFLAGS:
 	case FS_IOC32_GETVERSION:
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index aadb728..2553aa8 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -504,7 +504,7 @@
 	struct buffer_head		*bh;
 	int				err;
 
-	bh = sb_getblk(inode->i_sb, pblk);
+	bh = sb_getblk_gfp(inode->i_sb, pblk, __GFP_MOVABLE | GFP_NOFS);
 	if (unlikely(!bh))
 		return ERR_PTR(-ENOMEM);
 
@@ -1089,7 +1089,7 @@
 		err = -EIO;
 		goto cleanup;
 	}
-	bh = sb_getblk(inode->i_sb, newblock);
+	bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS);
 	if (unlikely(!bh)) {
 		err = -ENOMEM;
 		goto cleanup;
@@ -1283,7 +1283,7 @@
 	if (newblock == 0)
 		return err;
 
-	bh = sb_getblk(inode->i_sb, newblock);
+	bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS);
 	if (unlikely(!bh))
 		return -ENOMEM;
 	lock_buffer(bh);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 41f8e55..cecf9aa 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1323,7 +1323,7 @@
 					     unsigned int offset,
 					     unsigned int length)
 {
-	int to_release = 0;
+	int to_release = 0, contiguous_blks = 0;
 	struct buffer_head *head, *bh;
 	unsigned int curr_off = 0;
 	struct inode *inode = page->mapping->host;
@@ -1344,14 +1344,23 @@
 
 		if ((offset <= curr_off) && (buffer_delay(bh))) {
 			to_release++;
+			contiguous_blks++;
 			clear_buffer_delay(bh);
+		} else if (contiguous_blks) {
+			lblk = page->index <<
+			       (PAGE_CACHE_SHIFT - inode->i_blkbits);
+			lblk += (curr_off >> inode->i_blkbits) -
+				contiguous_blks;
+			ext4_es_remove_extent(inode, lblk, contiguous_blks);
+			contiguous_blks = 0;
 		}
 		curr_off = next_off;
 	} while ((bh = bh->b_this_page) != head);
 
-	if (to_release) {
+	if (contiguous_blks) {
 		lblk = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
-		ext4_es_remove_extent(inode, lblk, to_release);
+		lblk += (curr_off >> inode->i_blkbits) - contiguous_blks;
+		ext4_es_remove_extent(inode, lblk, contiguous_blks);
 	}
 
 	/* If we have released all the blocks belonging to a cluster, then we
@@ -4344,7 +4353,12 @@
 	int inode_size = EXT4_INODE_SIZE(sb);
 
 	oi.orig_ino = orig_ino;
-	ino = (orig_ino & ~(inodes_per_block - 1)) + 1;
+	/*
+	 * Calculate the first inode in the inode table block.  Inode
+	 * numbers are one-based.  That is, the first inode in a block
+	 * (assuming 4k blocks and 256 byte inodes) is (n*16 + 1).
+	 */
+	ino = ((orig_ino - 1) & ~(inodes_per_block - 1)) + 1;
 	for (i = 0; i < inodes_per_block; i++, ino++, buf += inode_size) {
 		if (ino == orig_ino)
 			continue;
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index cb84512..1346cfa 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -755,7 +755,6 @@
 		return err;
 	}
 	case EXT4_IOC_MOVE_EXT:
-	case FITRIM:
 	case EXT4_IOC_RESIZE_FS:
 	case EXT4_IOC_PRECACHE_EXTENTS:
 	case EXT4_IOC_SET_ENCRYPTION_POLICY:
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index f6aedf8..34b610e 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -4816,18 +4816,12 @@
 		/*
 		 * blocks being freed are metadata. these blocks shouldn't
 		 * be used until this transaction is committed
+		 *
+		 * We use __GFP_NOFAIL because ext4_free_blocks() is not allowed
+		 * to fail.
 		 */
-	retry:
-		new_entry = kmem_cache_alloc(ext4_free_data_cachep, GFP_NOFS);
-		if (!new_entry) {
-			/*
-			 * We use a retry loop because
-			 * ext4_free_blocks() is not allowed to fail.
-			 */
-			cond_resched();
-			congestion_wait(BLK_RW_ASYNC, HZ/50);
-			goto retry;
-		}
+		new_entry = kmem_cache_alloc(ext4_free_data_cachep,
+				GFP_NOFS|__GFP_NOFAIL);
 		new_entry->efd_start_cluster = bit;
 		new_entry->efd_group = block_group;
 		new_entry->efd_count = count_clusters;
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index b52374e..6163ad2 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -620,6 +620,7 @@
 	struct ext4_inode_info		*ei = EXT4_I(inode);
 	struct ext4_extent		*ex;
 	unsigned int			i, len;
+	ext4_lblk_t			start, end;
 	ext4_fsblk_t			blk;
 	handle_t			*handle;
 	int				ret;
@@ -633,6 +634,14 @@
 				       EXT4_FEATURE_RO_COMPAT_BIGALLOC))
 		return -EOPNOTSUPP;
 
+	/*
+	 * In order to get correct extent info, force all delayed allocation
+	 * blocks to be allocated, otherwise delayed allocation blocks may not
+	 * be reflected and bypass the checks on extent header.
+	 */
+	if (test_opt(inode->i_sb, DELALLOC))
+		ext4_alloc_da_blocks(inode);
+
 	handle = ext4_journal_start(inode, EXT4_HT_MIGRATE, 1);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
@@ -650,11 +659,13 @@
 		goto errout;
 	}
 	if (eh->eh_entries == 0)
-		blk = len = 0;
+		blk = len = start = end = 0;
 	else {
 		len = le16_to_cpu(ex->ee_len);
 		blk = ext4_ext_pblock(ex);
-		if (len > EXT4_NDIR_BLOCKS) {
+		start = le32_to_cpu(ex->ee_block);
+		end = start + len - 1;
+		if (end >= EXT4_NDIR_BLOCKS) {
 			ret = -EOPNOTSUPP;
 			goto errout;
 		}
@@ -662,7 +673,7 @@
 
 	ext4_clear_inode_flag(inode, EXT4_INODE_EXTENTS);
 	memset(ei->i_data, 0, sizeof(ei->i_data));
-	for (i=0; i < len; i++)
+	for (i = start; i <= end; i++)
 		ei->i_data[i] = cpu_to_le32(blk++);
 	ext4_mark_inode_dirty(handle, inode);
 errout:
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 9bedfa8..f71e19a 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2072,8 +2072,6 @@
 		return 1;
 	}
 
-	mark_inode_dirty(inode);
-
 	if (!PageDirty(page)) {
 		__set_page_dirty_nobuffers(page);
 		update_dirty_page(inode, page);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index ada2a3d..b0f38c3 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1331,12 +1331,13 @@
 	if (ret)
 		return ret;
 
-	if (f2fs_is_atomic_file(inode))
+	if (f2fs_is_atomic_file(inode)) {
+		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 		commit_inmem_pages(inode, false);
+	}
 
 	ret = f2fs_sync_file(filp, 0, LONG_MAX, 0);
 	mnt_drop_write_file(filp);
-	clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 	return ret;
 }
 
@@ -1387,8 +1388,8 @@
 	f2fs_balance_fs(F2FS_I_SB(inode));
 
 	if (f2fs_is_atomic_file(inode)) {
-		commit_inmem_pages(inode, false);
 		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+		commit_inmem_pages(inode, false);
 	}
 
 	if (f2fs_is_volatile_file(inode))
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index e1e7361..22fb5ef 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -556,27 +556,39 @@
 	if (!fio.encrypted_page)
 		goto put_out;
 
-	f2fs_submit_page_bio(&fio);
-
-	/* allocate block address */
-	f2fs_wait_on_page_writeback(dn.node_page, NODE);
-
-	allocate_data_block(fio.sbi, NULL, fio.blk_addr,
-					&fio.blk_addr, &sum, CURSEG_COLD_DATA);
-	dn.data_blkaddr = fio.blk_addr;
+	err = f2fs_submit_page_bio(&fio);
+	if (err)
+		goto put_page_out;
 
 	/* write page */
 	lock_page(fio.encrypted_page);
+
+	if (unlikely(!PageUptodate(fio.encrypted_page)))
+		goto put_page_out;
+	if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi)))
+		goto put_page_out;
+
+	set_page_dirty(fio.encrypted_page);
+	f2fs_wait_on_page_writeback(fio.encrypted_page, META);
+	if (clear_page_dirty_for_io(fio.encrypted_page))
+		dec_page_count(fio.sbi, F2FS_DIRTY_META);
+
 	set_page_writeback(fio.encrypted_page);
+
+	/* allocate block address */
+	f2fs_wait_on_page_writeback(dn.node_page, NODE);
+	allocate_data_block(fio.sbi, NULL, fio.blk_addr,
+					&fio.blk_addr, &sum, CURSEG_COLD_DATA);
 	fio.rw = WRITE_SYNC;
 	f2fs_submit_page_mbio(&fio);
 
+	dn.data_blkaddr = fio.blk_addr;
 	set_data_blkaddr(&dn);
 	f2fs_update_extent_cache(&dn);
 	set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
 	if (page->index == 0)
 		set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
-
+put_page_out:
 	f2fs_put_page(fio.encrypted_page, 1);
 put_out:
 	f2fs_put_dnode(&dn);
@@ -605,8 +617,8 @@
 			.page = page,
 			.encrypted_page = NULL,
 		};
+		set_page_dirty(page);
 		f2fs_wait_on_page_writeback(page, DATA);
-
 		if (clear_page_dirty_for_io(page))
 			inode_dec_dirty_pages(inode);
 		set_cold_data(page);
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 38e75fb..a13ffcc 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -141,6 +141,8 @@
 	kunmap_atomic(dst_addr);
 	SetPageUptodate(page);
 no_update:
+	set_page_dirty(page);
+
 	/* clear dirty state */
 	dirty = clear_page_dirty_for_io(page);
 
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 1eb3437..61b97f9 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -257,6 +257,7 @@
 		if (!abort) {
 			lock_page(cur->page);
 			if (cur->page->mapping == inode->i_mapping) {
+				set_page_dirty(cur->page);
 				f2fs_wait_on_page_writeback(cur->page, DATA);
 				if (clear_page_dirty_for_io(cur->page))
 					inode_dec_dirty_pages(inode);
diff --git a/fs/file_table.c b/fs/file_table.c
index 7f9d407..ad17e05 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -25,6 +25,7 @@
 #include <linux/hardirq.h>
 #include <linux/task_work.h>
 #include <linux/ima.h>
+#include <linux/swap.h>
 
 #include <linux/atomic.h>
 
@@ -308,19 +309,24 @@
 	}
 }
 
-void __init files_init(unsigned long mempages)
+void __init files_init(void)
 { 
-	unsigned long n;
-
 	filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
 			SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
-
-	/*
-	 * One file with associated inode and dcache is very roughly 1K.
-	 * Per default don't use more than 10% of our memory for files. 
-	 */ 
-
-	n = (mempages * (PAGE_SIZE / 1024)) / 10;
-	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
 	percpu_counter_init(&nr_files, 0, GFP_KERNEL);
+}
+
+/*
+ * One file with associated inode and dcache is very roughly 1K. Per default
+ * do not use more than 10% of our memory for files.
+ */
+void __init files_maxfiles_init(void)
+{
+	unsigned long n;
+	unsigned long memreserve = (totalram_pages - nr_free_pages()) * 3/2;
+
+	memreserve = min(memreserve, totalram_pages - 1);
+	n = ((totalram_pages - memreserve) * (PAGE_SIZE / 1024)) / 10;
+
+	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
 } 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index f0520bc..518c629 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -702,6 +702,7 @@
 	else
 		wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes);
 }
+EXPORT_SYMBOL_GPL(wbc_account_io);
 
 /**
  * inode_congested - test whether an inode is congested
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 80cc1b3..ebb5e37 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -2246,7 +2246,15 @@
 
 			err = -EINVAL;
 			if (old) {
-				struct fuse_dev *fud = fuse_get_dev(old);
+				struct fuse_dev *fud = NULL;
+
+				/*
+				 * Check against file->f_op because CUSE
+				 * uses the same ioctl handler.
+				 */
+				if (old->f_op == file->f_op &&
+				    old->f_cred->user_ns == file->f_cred->user_ns)
+					fud = fuse_get_dev(old);
 
 				if (fud) {
 					mutex_lock(&fuse_mutex);
diff --git a/fs/hpfs/alloc.c b/fs/hpfs/alloc.c
index f005046..d6a4b55 100644
--- a/fs/hpfs/alloc.c
+++ b/fs/hpfs/alloc.c
@@ -484,3 +484,98 @@
 	a->btree.first_free = cpu_to_le16(8);
 	return a;
 }
+
+static unsigned find_run(__le32 *bmp, unsigned *idx)
+{
+	unsigned len;
+	while (tstbits(bmp, *idx, 1)) {
+		(*idx)++;
+		if (unlikely(*idx >= 0x4000))
+			return 0;
+	}
+	len = 1;
+	while (!tstbits(bmp, *idx + len, 1))
+		len++;
+	return len;
+}
+
+static int do_trim(struct super_block *s, secno start, unsigned len, secno limit_start, secno limit_end, unsigned minlen, unsigned *result)
+{
+	int err;
+	secno end;
+	if (fatal_signal_pending(current))
+		return -EINTR;
+	end = start + len;
+	if (start < limit_start)
+		start = limit_start;
+	if (end > limit_end)
+		end = limit_end;
+	if (start >= end)
+		return 0;
+	if (end - start < minlen)
+		return 0;
+	err = sb_issue_discard(s, start, end - start, GFP_NOFS, 0);
+	if (err)
+		return err;
+	*result += end - start;
+	return 0;
+}
+
+int hpfs_trim_fs(struct super_block *s, u64 start, u64 end, u64 minlen, unsigned *result)
+{
+	int err = 0;
+	struct hpfs_sb_info *sbi = hpfs_sb(s);
+	unsigned idx, len, start_bmp, end_bmp;
+	__le32 *bmp;
+	struct quad_buffer_head qbh;
+
+	*result = 0;
+	if (!end || end > sbi->sb_fs_size)
+		end = sbi->sb_fs_size;
+	if (start >= sbi->sb_fs_size)
+		return 0;
+	if (minlen > 0x4000)
+		return 0;
+	if (start < sbi->sb_dirband_start + sbi->sb_dirband_size && end > sbi->sb_dirband_start) {
+		hpfs_lock(s);
+		if (s->s_flags & MS_RDONLY) {
+			err = -EROFS;
+			goto unlock_1;
+		}
+		if (!(bmp = hpfs_map_dnode_bitmap(s, &qbh))) {
+			err = -EIO;
+			goto unlock_1;
+		}
+		idx = 0;
+		while ((len = find_run(bmp, &idx)) && !err) {
+			err = do_trim(s, sbi->sb_dirband_start + idx * 4, len * 4, start, end, minlen, result);
+			idx += len;
+		}
+		hpfs_brelse4(&qbh);
+unlock_1:
+		hpfs_unlock(s);
+	}
+	start_bmp = start >> 14;
+	end_bmp = (end + 0x3fff) >> 14;
+	while (start_bmp < end_bmp && !err) {
+		hpfs_lock(s);
+		if (s->s_flags & MS_RDONLY) {
+			err = -EROFS;
+			goto unlock_2;
+		}
+		if (!(bmp = hpfs_map_bitmap(s, start_bmp, &qbh, "trim"))) {
+			err = -EIO;
+			goto unlock_2;
+		}
+		idx = 0;
+		while ((len = find_run(bmp, &idx)) && !err) {
+			err = do_trim(s, (start_bmp << 14) + idx, len, start, end, minlen, result);
+			idx += len;
+		}
+		hpfs_brelse4(&qbh);
+unlock_2:
+		hpfs_unlock(s);
+		start_bmp++;
+	}
+	return err;
+}
diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index 2a8e074..dc540bf 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -327,4 +327,5 @@
 	.iterate	= hpfs_readdir,
 	.release	= hpfs_dir_release,
 	.fsync		= hpfs_file_fsync,
+	.unlocked_ioctl	= hpfs_ioctl,
 };
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index 6d8cfe9..7ca28d6 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -203,6 +203,7 @@
 	.release	= hpfs_file_release,
 	.fsync		= hpfs_file_fsync,
 	.splice_read	= generic_file_splice_read,
+	.unlocked_ioctl	= hpfs_ioctl,
 };
 
 const struct inode_operations hpfs_file_iops =
diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h
index bb04b58..c4867b5 100644
--- a/fs/hpfs/hpfs_fn.h
+++ b/fs/hpfs/hpfs_fn.h
@@ -18,6 +18,8 @@
 #include <linux/pagemap.h>
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/blkdev.h>
 #include <asm/unaligned.h>
 
 #include "hpfs.h"
@@ -200,6 +202,7 @@
 struct dnode *hpfs_alloc_dnode(struct super_block *, secno, dnode_secno *, struct quad_buffer_head *);
 struct fnode *hpfs_alloc_fnode(struct super_block *, secno, fnode_secno *, struct buffer_head **);
 struct anode *hpfs_alloc_anode(struct super_block *, secno, anode_secno *, struct buffer_head **);
+int hpfs_trim_fs(struct super_block *, u64, u64, u64, unsigned *);
 
 /* anode.c */
 
@@ -318,6 +321,7 @@
 void hpfs_error(struct super_block *, const char *, ...);
 int hpfs_stop_cycles(struct super_block *, int, int *, int *, char *);
 unsigned hpfs_get_free_dnodes(struct super_block *);
+long hpfs_ioctl(struct file *file, unsigned cmd, unsigned long arg);
 
 /*
  * local time (HPFS) to GMT (Unix)
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 7cd00d3..68a9bed0 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -52,17 +52,20 @@
 }
 
 /* Filesystem error... */
-static char err_buf[1024];
-
 void hpfs_error(struct super_block *s, const char *fmt, ...)
 {
+	struct va_format vaf;
 	va_list args;
 
 	va_start(args, fmt);
-	vsnprintf(err_buf, sizeof(err_buf), fmt, args);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	pr_err("filesystem error: %pV", &vaf);
+
 	va_end(args);
 
-	pr_err("filesystem error: %s", err_buf);
 	if (!hpfs_sb(s)->sb_was_error) {
 		if (hpfs_sb(s)->sb_err == 2) {
 			pr_cont("; crashing the system because you wanted it\n");
@@ -196,12 +199,39 @@
 	return 0;
 }
 
+
+long hpfs_ioctl(struct file *file, unsigned cmd, unsigned long arg)
+{
+	switch (cmd) {
+		case FITRIM: {
+			struct fstrim_range range;
+			secno n_trimmed;
+			int r;
+			if (!capable(CAP_SYS_ADMIN))
+				return -EPERM;
+			if (copy_from_user(&range, (struct fstrim_range __user *)arg, sizeof(range)))
+				return -EFAULT;
+			r = hpfs_trim_fs(file_inode(file)->i_sb, range.start >> 9, (range.start + range.len) >> 9, (range.minlen + 511) >> 9, &n_trimmed);
+			if (r)
+				return r;
+			range.len = (u64)n_trimmed << 9;
+			if (copy_to_user((struct fstrim_range __user *)arg, &range, sizeof(range)))
+				return -EFAULT;
+			return 0;
+		}
+		default: {
+			return -ENOIOCTLCMD;
+		}
+	}
+}
+
+
 static struct kmem_cache * hpfs_inode_cachep;
 
 static struct inode *hpfs_alloc_inode(struct super_block *sb)
 {
 	struct hpfs_inode_info *ei;
-	ei = (struct hpfs_inode_info *)kmem_cache_alloc(hpfs_inode_cachep, GFP_NOFS);
+	ei = kmem_cache_alloc(hpfs_inode_cachep, GFP_NOFS);
 	if (!ei)
 		return NULL;
 	ei->vfs_inode.i_version = 1;
@@ -424,11 +454,14 @@
 	int o;
 	struct hpfs_sb_info *sbi = hpfs_sb(s);
 	char *new_opts = kstrdup(data, GFP_KERNEL);
-	
+
+	if (!new_opts)
+		return -ENOMEM;
+
 	sync_filesystem(s);
 
 	*flags |= MS_NOATIME;
-	
+
 	hpfs_lock(s);
 	uid = sbi->sb_uid; gid = sbi->sb_gid;
 	umask = 0777 & ~sbi->sb_mode;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 0cf74df..973c24c 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1010,6 +1010,8 @@
 	inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
 		goto out_dentry;
+	if (creat_flags == HUGETLB_SHMFS_INODE)
+		inode->i_flags |= S_PRIVATE;
 
 	file = ERR_PTR(-ENOMEM);
 	if (hugetlb_reserve_pages(inode, 0,
diff --git a/fs/jfs/file.c b/fs/jfs/file.c
index e98d39d..b9dc23c 100644
--- a/fs/jfs/file.c
+++ b/fs/jfs/file.c
@@ -76,7 +76,7 @@
 		if (ji->active_ag == -1) {
 			struct jfs_sb_info *jfs_sb = JFS_SBI(inode->i_sb);
 			ji->active_ag = BLKTOAG(addressPXD(&ji->ixpxd), jfs_sb);
-			atomic_inc( &jfs_sb->bmap->db_active[ji->active_ag]);
+			atomic_inc(&jfs_sb->bmap->db_active[ji->active_ag]);
 		}
 		spin_unlock_irq(&ji->ag_lock);
 	}
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 6f1cb2b..41aa3ca 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -134,11 +134,11 @@
 	 * It has been committed since the last change, but was still
 	 * on the dirty inode list.
 	 */
-	 if (!test_cflag(COMMIT_Dirty, inode)) {
+	if (!test_cflag(COMMIT_Dirty, inode)) {
 		/* Make sure committed changes hit the disk */
 		jfs_flush_journal(JFS_SBI(inode->i_sb)->log, wait);
 		return 0;
-	 }
+	}
 
 	if (jfs_commit_inode(inode, wait)) {
 		jfs_err("jfs_write_inode: jfs_commit_inode failed!");
diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c
index 93a1232..8db8b7d 100644
--- a/fs/jfs/ioctl.c
+++ b/fs/jfs/ioctl.c
@@ -180,9 +180,6 @@
 	case JFS_IOC_SETFLAGS32:
 		cmd = JFS_IOC_SETFLAGS;
 		break;
-	case FITRIM:
-		cmd = FITRIM;
-		break;
 	}
 	return jfs_ioctl(filp, cmd, arg);
 }
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index e33be92..a5ac97b 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -1160,7 +1160,7 @@
 		rc = dtModify(tid, new_dir, &new_dname, &ino,
 			      old_ip->i_ino, JFS_RENAME);
 		if (rc)
-			goto out4;
+			goto out_tx;
 		drop_nlink(new_ip);
 		if (S_ISDIR(new_ip->i_mode)) {
 			drop_nlink(new_ip);
@@ -1185,7 +1185,7 @@
 			if ((new_size = commitZeroLink(tid, new_ip)) < 0) {
 				txAbort(tid, 1);	/* Marks FS Dirty */
 				rc = new_size;
-				goto out4;
+				goto out_tx;
 			}
 			tblk = tid_to_tblock(tid);
 			tblk->xflag |= COMMIT_DELETE;
@@ -1203,7 +1203,7 @@
 		if (rc) {
 			jfs_err("jfs_rename didn't expect dtSearch to fail "
 				"w/rc = %d", rc);
-			goto out4;
+			goto out_tx;
 		}
 
 		ino = old_ip->i_ino;
@@ -1211,7 +1211,7 @@
 		if (rc) {
 			if (rc == -EIO)
 				jfs_err("jfs_rename: dtInsert returned -EIO");
-			goto out4;
+			goto out_tx;
 		}
 		if (S_ISDIR(old_ip->i_mode))
 			inc_nlink(new_dir);
@@ -1226,7 +1226,7 @@
 		jfs_err("jfs_rename did not expect dtDelete to return rc = %d",
 			rc);
 		txAbort(tid, 1);	/* Marks Filesystem dirty */
-		goto out4;
+		goto out_tx;
 	}
 	if (S_ISDIR(old_ip->i_mode)) {
 		drop_nlink(old_dir);
@@ -1285,7 +1285,7 @@
 
 	rc = txCommit(tid, ipcount, iplist, commit_flag);
 
-      out4:
+      out_tx:
 	txEnd(tid);
 	if (new_ip)
 		mutex_unlock(&JFS_IP(new_ip)->commit_mutex);
@@ -1308,13 +1308,6 @@
 	}
 	if (new_ip && (new_ip->i_nlink == 0))
 		set_cflag(COMMIT_Nolink, new_ip);
-      out3:
-	free_UCSname(&new_dname);
-      out2:
-	free_UCSname(&old_dname);
-      out1:
-	if (new_ip && !S_ISDIR(new_ip->i_mode))
-		IWRITE_UNLOCK(new_ip);
 	/*
 	 * Truncating the directory index table is not guaranteed.  It
 	 * may need to be done iteratively
@@ -1325,7 +1318,13 @@
 
 		clear_cflag(COMMIT_Stale, old_dir);
 	}
-
+	if (new_ip && !S_ISDIR(new_ip->i_mode))
+		IWRITE_UNLOCK(new_ip);
+      out3:
+	free_UCSname(&new_dname);
+      out2:
+	free_UCSname(&old_dname);
+      out1:
 	jfs_info("jfs_rename: returning %d", rc);
 	return rc;
 }
diff --git a/fs/locks.c b/fs/locks.c
index 653faab..d3d558b 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -862,12 +862,11 @@
  * whether or not a lock was successfully freed by testing the return
  * value for -ENOENT.
  */
-static int flock_lock_file(struct file *filp, struct file_lock *request)
+static int flock_lock_inode(struct inode *inode, struct file_lock *request)
 {
 	struct file_lock *new_fl = NULL;
 	struct file_lock *fl;
 	struct file_lock_context *ctx;
-	struct inode *inode = file_inode(filp);
 	int error = 0;
 	bool found = false;
 	LIST_HEAD(dispose);
@@ -890,7 +889,7 @@
 		goto find_conflict;
 
 	list_for_each_entry(fl, &ctx->flc_flock, fl_list) {
-		if (filp != fl->fl_file)
+		if (request->fl_file != fl->fl_file)
 			continue;
 		if (request->fl_type == fl->fl_type)
 			goto out;
@@ -1164,20 +1163,19 @@
 EXPORT_SYMBOL(posix_lock_file);
 
 /**
- * posix_lock_file_wait - Apply a POSIX-style lock to a file
- * @filp: The file to apply the lock to
+ * posix_lock_inode_wait - Apply a POSIX-style lock to a file
+ * @inode: inode of file to which lock request should be applied
  * @fl: The lock to be applied
  *
- * Add a POSIX style lock to a file.
- * We merge adjacent & overlapping locks whenever possible.
- * POSIX locks are sorted by owner task, then by starting address
+ * Variant of posix_lock_file_wait that does not take a filp, and so can be
+ * used after the filp has already been torn down.
  */
-int posix_lock_file_wait(struct file *filp, struct file_lock *fl)
+int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 {
 	int error;
 	might_sleep ();
 	for (;;) {
-		error = posix_lock_file(filp, fl, NULL);
+		error = __posix_lock_file(inode, fl, NULL);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
 		error = wait_event_interruptible(fl->fl_wait, !fl->fl_next);
@@ -1189,7 +1187,7 @@
 	}
 	return error;
 }
-EXPORT_SYMBOL(posix_lock_file_wait);
+EXPORT_SYMBOL(posix_lock_inode_wait);
 
 /**
  * locks_mandatory_locked - Check for an active lock
@@ -1851,18 +1849,18 @@
 }
 
 /**
- * flock_lock_file_wait - Apply a FLOCK-style lock to a file
- * @filp: The file to apply the lock to
+ * flock_lock_inode_wait - Apply a FLOCK-style lock to a file
+ * @inode: inode of the file to apply to
  * @fl: The lock to be applied
  *
- * Add a FLOCK style lock to a file.
+ * Apply a FLOCK style lock request to an inode.
  */
-int flock_lock_file_wait(struct file *filp, struct file_lock *fl)
+int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl)
 {
 	int error;
 	might_sleep();
 	for (;;) {
-		error = flock_lock_file(filp, fl);
+		error = flock_lock_inode(inode, fl);
 		if (error != FILE_LOCK_DEFERRED)
 			break;
 		error = wait_event_interruptible(fl->fl_wait, !fl->fl_next);
@@ -1874,8 +1872,7 @@
 	}
 	return error;
 }
-
-EXPORT_SYMBOL(flock_lock_file_wait);
+EXPORT_SYMBOL(flock_lock_inode_wait);
 
 /**
  *	sys_flock: - flock() system call.
@@ -2401,7 +2398,8 @@
 		.fl_type = F_UNLCK,
 		.fl_end = OFFSET_MAX,
 	};
-	struct file_lock_context *flctx = file_inode(filp)->i_flctx;
+	struct inode *inode = file_inode(filp);
+	struct file_lock_context *flctx = inode->i_flctx;
 
 	if (list_empty(&flctx->flc_flock))
 		return;
@@ -2409,7 +2407,7 @@
 	if (filp->f_op->flock)
 		filp->f_op->flock(filp, F_SETLKW, &fl);
 	else
-		flock_lock_file(filp, &fl);
+		flock_lock_inode(inode, &fl);
 
 	if (fl.fl_ops && fl.fl_ops->fl_release_private)
 		fl.fl_ops->fl_release_private(&fl);
diff --git a/fs/namei.c b/fs/namei.c
index ae4e4c1..1c2105e 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -879,7 +879,7 @@
 		return 0;
 
 	/* Allowed if parent directory not sticky and world-writable. */
-	parent = nd->path.dentry->d_inode;
+	parent = nd->inode;
 	if ((parent->i_mode & (S_ISVTX|S_IWOTH)) != (S_ISVTX|S_IWOTH))
 		return 0;
 
@@ -1954,8 +1954,13 @@
 				continue;
 			}
 		}
-		if (unlikely(!d_can_lookup(nd->path.dentry)))
+		if (unlikely(!d_can_lookup(nd->path.dentry))) {
+			if (nd->flags & LOOKUP_RCU) {
+				if (unlazy_walk(nd, NULL, 0))
+					return -ECHILD;
+			}
 			return -ENOTDIR;
+		}
 	}
 }
 
diff --git a/fs/namespace.c b/fs/namespace.c
index c7cb8a5..2b8aa15 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1361,6 +1361,36 @@
 	UMOUNT_PROPAGATE = 2,
 	UMOUNT_CONNECTED = 4,
 };
+
+static bool disconnect_mount(struct mount *mnt, enum umount_tree_flags how)
+{
+	/* Leaving mounts connected is only valid for lazy umounts */
+	if (how & UMOUNT_SYNC)
+		return true;
+
+	/* A mount without a parent has nothing to be connected to */
+	if (!mnt_has_parent(mnt))
+		return true;
+
+	/* Because the reference counting rules change when mounts are
+	 * unmounted and connected, umounted mounts may not be
+	 * connected to mounted mounts.
+	 */
+	if (!(mnt->mnt_parent->mnt.mnt_flags & MNT_UMOUNT))
+		return true;
+
+	/* Has it been requested that the mount remain connected? */
+	if (how & UMOUNT_CONNECTED)
+		return false;
+
+	/* Is the mount locked such that it needs to remain connected? */
+	if (IS_MNT_LOCKED(mnt))
+		return false;
+
+	/* By default disconnect the mount */
+	return true;
+}
+
 /*
  * mount_lock must be held
  * namespace_sem must be held for write
@@ -1398,10 +1428,7 @@
 		if (how & UMOUNT_SYNC)
 			p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
 
-		disconnect = !(((how & UMOUNT_CONNECTED) &&
-				mnt_has_parent(p) &&
-				(p->mnt_parent->mnt.mnt_flags & MNT_UMOUNT)) ||
-			       IS_MNT_LOCKED_AND_LAZY(p));
+		disconnect = disconnect_mount(p, how);
 
 		pin_insert_group(&p->mnt_umount, &p->mnt_parent->mnt,
 				 disconnect ? &unmounted : NULL);
@@ -1538,11 +1565,8 @@
 	while (!hlist_empty(&mp->m_list)) {
 		mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
 		if (mnt->mnt.mnt_flags & MNT_UMOUNT) {
-			struct mount *p, *tmp;
-			list_for_each_entry_safe(p, tmp, &mnt->mnt_mounts,  mnt_child) {
-				hlist_add_head(&p->mnt_umount.s_list, &unmounted);
-				umount_mnt(p);
-			}
+			hlist_add_head(&mnt->mnt_umount.s_list, &unmounted);
+			umount_mnt(mnt);
 		}
 		else umount_tree(mnt, UMOUNT_CONNECTED);
 	}
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index ecebb40..4a90c9b 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -775,7 +775,7 @@
 	server->options = data->options;
 	server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID|
 		NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP|
-		NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME|NFS_CAP_CHANGE_ATTR;
+		NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME;
 
 	if (data->rsize)
 		server->rsize = nfs_block_size(data->rsize, NULL);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index c12951b..b3289d7 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1852,7 +1852,7 @@
 	struct nfs42_layoutstat_devinfo *devinfo;
 	int i;
 
-	for (i = 0; i <= FF_LAYOUT_MIRROR_COUNT(pls); i++) {
+	for (i = 0; i < FF_LAYOUT_MIRROR_COUNT(pls); i++) {
 		if (*dev_count >= dev_limit)
 			break;
 		mirror = FF_LAYOUT_COMP(pls, i);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index b77b328..0adc7d2 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -442,8 +442,9 @@
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
 		if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
 			inode->i_version = fattr->change_attr;
-		else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR))
-			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
+		else
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR
+				| NFS_INO_REVAL_PAGECACHE);
 		if (fattr->valid & NFS_ATTR_FATTR_SIZE)
 			inode->i_size = nfs_size_to_loff_t(fattr->size);
 		else
@@ -1244,9 +1245,11 @@
 	if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
 		cur_size = i_size_read(inode);
 		new_isize = nfs_size_to_loff_t(fattr->size);
-		if (cur_size != new_isize && nfsi->nrequests == 0)
+		if (cur_size != new_isize)
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
 	}
+	if (nfsi->nrequests != 0)
+		invalid &= ~NFS_INO_REVAL_PAGECACHE;
 
 	/* Have any file permissions changed? */
 	if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO))
@@ -1684,13 +1687,12 @@
 			invalid |= NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_DATA
 				| NFS_INO_INVALID_ACCESS
-				| NFS_INO_INVALID_ACL
-				| NFS_INO_REVAL_PAGECACHE;
+				| NFS_INO_INVALID_ACL;
 			if (S_ISDIR(inode->i_mode))
 				nfs_force_lookup_revalidate(inode);
 			inode->i_version = fattr->change_attr;
 		}
-	} else if (server->caps & NFS_CAP_CHANGE_ATTR)
+	} else
 		nfsi->cache_validity |= save_cache_validity;
 
 	if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
@@ -1717,7 +1719,6 @@
 			if ((nfsi->nrequests == 0) || new_isize > cur_isize) {
 				i_size_write(inode, new_isize);
 				invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
-				invalid &= ~NFS_INO_REVAL_PAGECACHE;
 			}
 			dprintk("NFS: isize change on server for file %s/%ld "
 					"(%Ld to %Ld)\n",
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 7e3c460..9b372b8 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -296,6 +296,22 @@
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
 extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags);
+static inline struct nfs4_label *
+nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src)
+{
+	if (!dst || !src)
+		return NULL;
+
+	if (src->len > NFS4_MAXLABELLEN)
+		return NULL;
+
+	dst->lfs = src->lfs;
+	dst->pi = src->pi;
+	dst->len = src->len;
+	memcpy(dst->label, src->label, src->len);
+
+	return dst;
+}
 static inline void nfs4_label_free(struct nfs4_label *label)
 {
 	if (label) {
@@ -316,6 +332,11 @@
 static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
 {
 }
+static inline struct nfs4_label *
+nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src)
+{
+	return NULL;
+}
 #endif /* CONFIG_NFS_V4_SECURITY_LABEL */
 
 /* proc.c */
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index f486b80..d731bbf 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -135,7 +135,7 @@
 	return err;
 }
 
-loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
+static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 {
 	struct inode *inode = file_inode(filep);
 	struct nfs42_seek_args args = {
@@ -171,6 +171,23 @@
 	return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes);
 }
 
+loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
+{
+	struct nfs_server *server = NFS_SERVER(file_inode(filep));
+	struct nfs4_exception exception = { };
+	int err;
+
+	do {
+		err = _nfs42_proc_llseek(filep, offset, whence);
+		if (err == -ENOTSUPP)
+			return -EOPNOTSUPP;
+		err = nfs4_handle_exception(server, err, &exception);
+	} while (exception.retry);
+
+	return err;
+}
+
+
 static void
 nfs42_layoutstat_prepare(struct rpc_task *task, void *calldata)
 {
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6f228b5..3acb1eb 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -467,7 +467,10 @@
 
 static void renew_lease(const struct nfs_server *server, unsigned long timestamp)
 {
-	do_renew_lease(server->nfs_client, timestamp);
+	struct nfs_client *clp = server->nfs_client;
+
+	if (!nfs4_has_session(clp))
+		do_renew_lease(clp, timestamp);
 }
 
 struct nfs4_call_sync_data {
@@ -616,8 +619,7 @@
 		clp = session->clp;
 		do_renew_lease(clp, res->sr_timestamp);
 		/* Check sequence flags */
-		if (res->sr_status_flags != 0)
-			nfs4_schedule_lease_recovery(clp);
+		nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags);
 		nfs41_update_target_slotid(slot->table, slot, res);
 		break;
 	case 1:
@@ -910,6 +912,7 @@
 	struct nfs_open_confirmres c_res;
 	struct nfs4_string owner_name;
 	struct nfs4_string group_name;
+	struct nfs4_label *a_label;
 	struct nfs_fattr f_attr;
 	struct nfs4_label *f_label;
 	struct dentry *dir;
@@ -1013,6 +1016,10 @@
 	if (IS_ERR(p->f_label))
 		goto err_free_p;
 
+	p->a_label = nfs4_label_alloc(server, gfp_mask);
+	if (IS_ERR(p->a_label))
+		goto err_free_f;
+
 	alloc_seqid = server->nfs_client->cl_mvops->alloc_seqid;
 	p->o_arg.seqid = alloc_seqid(&sp->so_seqid, gfp_mask);
 	if (IS_ERR(p->o_arg.seqid))
@@ -1041,7 +1048,7 @@
 	p->o_arg.server = server;
 	p->o_arg.bitmask = nfs4_bitmask(server, label);
 	p->o_arg.open_bitmap = &nfs4_fattr_bitmap[0];
-	p->o_arg.label = label;
+	p->o_arg.label = nfs4_label_copy(p->a_label, label);
 	p->o_arg.claim = nfs4_map_atomic_open_claim(server, claim);
 	switch (p->o_arg.claim) {
 	case NFS4_OPEN_CLAIM_NULL:
@@ -1074,6 +1081,8 @@
 	return p;
 
 err_free_label:
+	nfs4_label_free(p->a_label);
+err_free_f:
 	nfs4_label_free(p->f_label);
 err_free_p:
 	kfree(p);
@@ -1093,6 +1102,7 @@
 		nfs4_put_open_state(p->state);
 	nfs4_put_state_owner(p->owner);
 
+	nfs4_label_free(p->a_label);
 	nfs4_label_free(p->f_label);
 
 	dput(p->dir);
@@ -1198,12 +1208,15 @@
 
 static void nfs_resync_open_stateid_locked(struct nfs4_state *state)
 {
+	if (!(state->n_wronly || state->n_rdonly || state->n_rdwr))
+		return;
 	if (state->n_wronly)
 		set_bit(NFS_O_WRONLY_STATE, &state->flags);
 	if (state->n_rdonly)
 		set_bit(NFS_O_RDONLY_STATE, &state->flags);
 	if (state->n_rdwr)
 		set_bit(NFS_O_RDWR_STATE, &state->flags);
+	set_bit(NFS_OPEN_STATE, &state->flags);
 }
 
 static void nfs_clear_open_stateid_locked(struct nfs4_state *state,
@@ -5439,15 +5452,15 @@
 	return err;
 }
 
-static int do_vfs_lock(struct file *file, struct file_lock *fl)
+static int do_vfs_lock(struct inode *inode, struct file_lock *fl)
 {
 	int res = 0;
 	switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) {
 		case FL_POSIX:
-			res = posix_lock_file_wait(file, fl);
+			res = posix_lock_inode_wait(inode, fl);
 			break;
 		case FL_FLOCK:
-			res = flock_lock_file_wait(file, fl);
+			res = flock_lock_inode_wait(inode, fl);
 			break;
 		default:
 			BUG();
@@ -5484,7 +5497,6 @@
 	atomic_inc(&lsp->ls_count);
 	/* Ensure we don't close file until we're done freeing locks! */
 	p->ctx = get_nfs_open_context(ctx);
-	get_file(fl->fl_file);
 	memcpy(&p->fl, fl, sizeof(p->fl));
 	p->server = NFS_SERVER(inode);
 	return p;
@@ -5496,7 +5508,6 @@
 	nfs_free_seqid(calldata->arg.seqid);
 	nfs4_put_lock_state(calldata->lsp);
 	put_nfs_open_context(calldata->ctx);
-	fput(calldata->fl.fl_file);
 	kfree(calldata);
 }
 
@@ -5509,7 +5520,7 @@
 	switch (task->tk_status) {
 		case 0:
 			renew_lease(calldata->server, calldata->timestamp);
-			do_vfs_lock(calldata->fl.fl_file, &calldata->fl);
+			do_vfs_lock(calldata->lsp->ls_state->inode, &calldata->fl);
 			if (nfs4_update_lock_stateid(calldata->lsp,
 					&calldata->res.stateid))
 				break;
@@ -5617,7 +5628,7 @@
 	mutex_lock(&sp->so_delegreturn_mutex);
 	/* Exclude nfs4_reclaim_open_stateid() - note nesting! */
 	down_read(&nfsi->rwsem);
-	if (do_vfs_lock(request->fl_file, request) == -ENOENT) {
+	if (do_vfs_lock(inode, request) == -ENOENT) {
 		up_read(&nfsi->rwsem);
 		mutex_unlock(&sp->so_delegreturn_mutex);
 		goto out;
@@ -5758,7 +5769,7 @@
 				data->timestamp);
 		if (data->arg.new_lock) {
 			data->fl.fl_flags &= ~(FL_SLEEP | FL_ACCESS);
-			if (do_vfs_lock(data->fl.fl_file, &data->fl) < 0) {
+			if (do_vfs_lock(lsp->ls_state->inode, &data->fl) < 0) {
 				rpc_restart_call_prepare(task);
 				break;
 			}
@@ -6000,7 +6011,7 @@
 	if (status != 0)
 		goto out;
 	request->fl_flags |= FL_ACCESS;
-	status = do_vfs_lock(request->fl_file, request);
+	status = do_vfs_lock(state->inode, request);
 	if (status < 0)
 		goto out;
 	down_read(&nfsi->rwsem);
@@ -6008,7 +6019,7 @@
 		/* Yes: cache locks! */
 		/* ...but avoid races with delegation recall... */
 		request->fl_flags = fl_flags & ~FL_SLEEP;
-		status = do_vfs_lock(request->fl_file, request);
+		status = do_vfs_lock(state->inode, request);
 		up_read(&nfsi->rwsem);
 		goto out;
 	}
@@ -7573,13 +7584,8 @@
 		goto out;
 	}
 	ret = rpc_wait_for_completion_task(task);
-	if (!ret) {
-		struct nfs4_sequence_res *res = task->tk_msg.rpc_resp;
-
-		if (task->tk_status == 0)
-			nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags);
+	if (!ret)
 		ret = task->tk_status;
-	}
 	rpc_put_task(task);
 out:
 	dprintk("<-- %s status=%d\n", __func__, ret);
@@ -7967,16 +7973,17 @@
 {
 	struct nfs4_layoutreturn *lrp = calldata;
 	struct pnfs_layout_hdr *lo = lrp->args.layout;
+	LIST_HEAD(freeme);
 
 	dprintk("--> %s\n", __func__);
 	spin_lock(&lo->plh_inode->i_lock);
 	if (lrp->res.lrs_present)
 		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+	pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range);
 	pnfs_clear_layoutreturn_waitbit(lo);
-	clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags);
-	rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
 	lo->plh_block_lgets--;
 	spin_unlock(&lo->plh_inode->i_lock);
+	pnfs_free_lseg_list(&freeme);
 	pnfs_put_layout_hdr(lrp->args.layout);
 	nfs_iput_and_deactive(lrp->inode);
 	kfree(calldata);
@@ -8590,7 +8597,6 @@
 	.minor_version = 0,
 	.init_caps = NFS_CAP_READDIRPLUS
 		| NFS_CAP_ATOMIC_OPEN
-		| NFS_CAP_CHANGE_ATTR
 		| NFS_CAP_POSIX_LOCK,
 	.init_client = nfs40_init_client,
 	.shutdown_client = nfs40_shutdown_client,
@@ -8616,7 +8622,6 @@
 	.minor_version = 1,
 	.init_caps = NFS_CAP_READDIRPLUS
 		| NFS_CAP_ATOMIC_OPEN
-		| NFS_CAP_CHANGE_ATTR
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
 		| NFS_CAP_ATOMIC_OPEN_V1,
@@ -8639,7 +8644,6 @@
 	.minor_version = 2,
 	.init_caps = NFS_CAP_READDIRPLUS
 		| NFS_CAP_ATOMIC_OPEN
-		| NFS_CAP_CHANGE_ATTR
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
 		| NFS_CAP_ATOMIC_OPEN_V1
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 605840d..f2e2ad8 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -2191,25 +2191,35 @@
 	}
 }
 
-static void nfs41_handle_state_revoked(struct nfs_client *clp)
+static void nfs41_handle_all_state_revoked(struct nfs_client *clp)
 {
 	nfs4_reset_all_state(clp);
 	dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname);
 }
 
+static void nfs41_handle_some_state_revoked(struct nfs_client *clp)
+{
+	nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_nograce);
+	nfs4_schedule_state_manager(clp);
+
+	dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname);
+}
+
 static void nfs41_handle_recallable_state_revoked(struct nfs_client *clp)
 {
-	/* This will need to handle layouts too */
-	nfs_expire_all_delegations(clp);
+	/* FIXME: For now, we destroy all layouts. */
+	pnfs_destroy_all_layouts(clp);
+	/* FIXME: For now, we test all delegations+open state+locks. */
+	nfs41_handle_some_state_revoked(clp);
 	dprintk("%s: Recallable state revoked on server %s!\n", __func__,
 			clp->cl_hostname);
 }
 
 static void nfs41_handle_backchannel_fault(struct nfs_client *clp)
 {
-	nfs_expire_all_delegations(clp);
-	if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0)
-		nfs4_schedule_state_manager(clp);
+	set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+	nfs4_schedule_state_manager(clp);
+
 	dprintk("%s: server %s declared a backchannel fault\n", __func__,
 			clp->cl_hostname);
 }
@@ -2231,10 +2241,11 @@
 
 	if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED)
 		nfs41_handle_server_reboot(clp);
-	if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED |
-			    SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED |
+	if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED))
+		nfs41_handle_all_state_revoked(clp);
+	if (flags & (SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED |
 			    SEQ4_STATUS_ADMIN_STATE_REVOKED))
-		nfs41_handle_state_revoked(clp);
+		nfs41_handle_some_state_revoked(clp);
 	if (flags & SEQ4_STATUS_LEASE_MOVED)
 		nfs4_schedule_lease_moved_recovery(clp);
 	if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED)
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 1da68d3..4984bbe 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -1100,8 +1100,6 @@
 		mirror->pg_base = 0;
 		mirror->pg_recoalesce = 0;
 
-		desc->pg_moreio = 0;
-
 		while (!list_empty(&head)) {
 			struct nfs_page *req;
 
@@ -1109,8 +1107,11 @@
 			nfs_list_remove_request(req);
 			if (__nfs_pageio_add_request(desc, req))
 				continue;
-			if (desc->pg_error < 0)
+			if (desc->pg_error < 0) {
+				list_splice_tail(&head, &mirror->pg_list);
+				mirror->pg_recoalesce = 1;
 				return 0;
+			}
 			break;
 		}
 	} while (mirror->pg_recoalesce);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 0ba9a02..70bf706 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -352,7 +352,7 @@
 {
 	struct pnfs_layout_segment *s;
 
-	if (!test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
+	if (!test_and_clear_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
 		return false;
 
 	list_for_each_entry(s, &lo->plh_segs, pls_list)
@@ -362,6 +362,18 @@
 	return true;
 }
 
+static bool
+pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo)
+{
+	if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+		return false;
+	lo->plh_return_iomode = 0;
+	lo->plh_block_lgets++;
+	pnfs_get_layout_hdr(lo);
+	clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags);
+	return true;
+}
+
 static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg,
 		struct pnfs_layout_hdr *lo, struct inode *inode)
 {
@@ -372,17 +384,16 @@
 	if (pnfs_layout_need_return(lo, lseg)) {
 		nfs4_stateid stateid;
 		enum pnfs_iomode iomode;
+		bool send;
 
 		stateid = lo->plh_stateid;
 		iomode = lo->plh_return_iomode;
-		/* decreased in pnfs_send_layoutreturn() */
-		lo->plh_block_lgets++;
-		lo->plh_return_iomode = 0;
+		send = pnfs_prepare_layoutreturn(lo);
 		spin_unlock(&inode->i_lock);
-		pnfs_get_layout_hdr(lo);
-
-		/* Send an async layoutreturn so we dont deadlock */
-		pnfs_send_layoutreturn(lo, stateid, iomode, false);
+		if (send) {
+			/* Send an async layoutreturn so we dont deadlock */
+			pnfs_send_layoutreturn(lo, stateid, iomode, false);
+		}
 	} else
 		spin_unlock(&inode->i_lock);
 }
@@ -411,6 +422,10 @@
 		pnfs_layoutreturn_before_put_lseg(lseg, lo, inode);
 
 	if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) {
+		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) {
+			spin_unlock(&inode->i_lock);
+			return;
+		}
 		pnfs_get_layout_hdr(lo);
 		pnfs_layout_remove_lseg(lo, lseg);
 		spin_unlock(&inode->i_lock);
@@ -451,6 +466,8 @@
 		test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
 	if (atomic_dec_and_test(&lseg->pls_refcount)) {
 		struct pnfs_layout_hdr *lo = lseg->pls_layout;
+		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags))
+			return;
 		pnfs_get_layout_hdr(lo);
 		pnfs_layout_remove_lseg(lo, lseg);
 		pnfs_free_lseg_async(lseg);
@@ -924,6 +941,7 @@
 	clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags);
 	smp_mb__after_atomic();
 	wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN);
+	rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
 }
 
 static int
@@ -978,6 +996,7 @@
 	LIST_HEAD(tmp_list);
 	nfs4_stateid stateid;
 	int status = 0, empty;
+	bool send;
 
 	dprintk("NFS: %s for inode %lu\n", __func__, ino->i_ino);
 
@@ -1007,17 +1026,18 @@
 	/* Don't send a LAYOUTRETURN if list was initially empty */
 	if (empty) {
 		spin_unlock(&ino->i_lock);
-		pnfs_put_layout_hdr(lo);
 		dprintk("NFS: %s no layout segments to return\n", __func__);
-		goto out;
+		goto out_put_layout_hdr;
 	}
 
 	set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
-	lo->plh_block_lgets++;
+	send = pnfs_prepare_layoutreturn(lo);
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
-
-	status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true);
+	if (send)
+		status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true);
+out_put_layout_hdr:
+	pnfs_put_layout_hdr(lo);
 out:
 	dprintk("<-- %s status: %d\n", __func__, status);
 	return status;
@@ -1097,13 +1117,9 @@
 out_noroc:
 	if (lo) {
 		stateid = lo->plh_stateid;
-		layoutreturn =
-			test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
-					   &lo->plh_flags);
-		if (layoutreturn) {
-			lo->plh_block_lgets++;
-			pnfs_get_layout_hdr(lo);
-		}
+		if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+					   &lo->plh_flags))
+			layoutreturn = pnfs_prepare_layoutreturn(lo);
 	}
 	spin_unlock(&ino->i_lock);
 	if (layoutreturn) {
@@ -1146,15 +1162,18 @@
 	struct pnfs_layout_segment *lseg;
 	nfs4_stateid stateid;
 	u32 current_seqid;
-	bool found = false, layoutreturn = false;
+	bool layoutreturn = false;
 
 	spin_lock(&ino->i_lock);
-	list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list)
-		if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) {
-			rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
-			found = true;
-			goto out;
-		}
+	list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list) {
+		if (!test_bit(NFS_LSEG_ROC, &lseg->pls_flags))
+			continue;
+		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags))
+			continue;
+		rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
+		spin_unlock(&ino->i_lock);
+		return true;
+	}
 	lo = nfsi->layout;
 	current_seqid = be32_to_cpu(lo->plh_stateid.seqid);
 
@@ -1162,23 +1181,19 @@
 	 * a barrier, we choose the worst-case barrier.
 	 */
 	*barrier = current_seqid + atomic_read(&lo->plh_outstanding);
-out:
-	if (!found) {
-		stateid = lo->plh_stateid;
-		layoutreturn =
-			test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
-					   &lo->plh_flags);
-		if (layoutreturn) {
-			lo->plh_block_lgets++;
-			pnfs_get_layout_hdr(lo);
-		}
-	}
+	stateid = lo->plh_stateid;
+	if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+					   &lo->plh_flags))
+		layoutreturn = pnfs_prepare_layoutreturn(lo);
+	if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+		rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
+
 	spin_unlock(&ino->i_lock);
 	if (layoutreturn) {
-		rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
 		pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, false);
+		return true;
 	}
-	return found;
+	return false;
 }
 
 /*
@@ -1695,7 +1710,6 @@
 	spin_lock(&inode->i_lock);
 	/* set failure bit so that pnfs path will be retried later */
 	pnfs_layout_set_fail_bit(lo, iomode);
-	set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
 	if (lo->plh_return_iomode == 0)
 		lo->plh_return_iomode = range.iomode;
 	else if (lo->plh_return_iomode != range.iomode)
@@ -2207,13 +2221,12 @@
 	if (ld->prepare_layoutcommit) {
 		status = ld->prepare_layoutcommit(&data->args);
 		if (status) {
+			put_rpccred(data->cred);
 			spin_lock(&inode->i_lock);
 			set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags);
 			if (end_pos > nfsi->layout->plh_lwb)
 				nfsi->layout->plh_lwb = end_pos;
-			spin_unlock(&inode->i_lock);
-			put_rpccred(data->cred);
-			goto clear_layoutcommitting;
+			goto out_unlock;
 		}
 	}
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 65869ca..75a35a1 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1379,24 +1379,27 @@
 {
 	struct nfs_pgio_args *argp = &hdr->args;
 	struct nfs_pgio_res *resp = &hdr->res;
+	u64 size = argp->offset + resp->count;
 
 	if (!(fattr->valid & NFS_ATTR_FATTR_SIZE))
+		fattr->size = size;
+	if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode)) {
+		fattr->valid &= ~NFS_ATTR_FATTR_SIZE;
 		return;
-	if (argp->offset + resp->count != fattr->size)
-		return;
-	if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode))
+	}
+	if (size != fattr->size)
 		return;
 	/* Set attribute barrier */
 	nfs_fattr_set_barrier(fattr);
+	/* ...and update size */
+	fattr->valid |= NFS_ATTR_FATTR_SIZE;
 }
 
 void nfs_writeback_update_inode(struct nfs_pgio_header *hdr)
 {
-	struct nfs_fattr *fattr = hdr->res.fattr;
+	struct nfs_fattr *fattr = &hdr->fattr;
 	struct inode *inode = hdr->inode;
 
-	if (fattr == NULL)
-		return;
 	spin_lock(&inode->i_lock);
 	nfs_writeback_check_extend(hdr, fattr);
 	nfs_post_op_update_inode_force_wcc_locked(inode, fattr);
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 6904213..ebf90e4 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -212,6 +212,7 @@
 	BUG_ON(!ls->ls_file);
 
 	if (nfsd4_layout_setlease(ls)) {
+		fput(ls->ls_file);
 		put_nfs4_file(fp);
 		kmem_cache_free(nfs4_layout_stateid_cache, ls);
 		return NULL;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 61dfb33..9520271 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4396,9 +4396,9 @@
 	queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ);
 }
 
-static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_ol_stateid *stp)
+static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp)
 {
-	if (!fh_match(&fhp->fh_handle, &stp->st_stid.sc_file->fi_fhandle))
+	if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle))
 		return nfserr_bad_stateid;
 	return nfs_ok;
 }
@@ -4601,9 +4601,6 @@
 {
 	__be32 status;
 
-	status = nfs4_check_fh(fhp, ols);
-	if (status)
-		return status;
 	status = nfsd4_check_openowner_confirmed(ols);
 	if (status)
 		return status;
@@ -4690,6 +4687,9 @@
 		status = nfserr_bad_stateid;
 		break;
 	}
+	if (status)
+		goto out;
+	status = nfs4_check_fh(fhp, s);
 
 done:
 	if (!status && filpp)
@@ -4798,7 +4798,7 @@
 	status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
 	if (status)
 		return status;
-	return nfs4_check_fh(current_fh, stp);
+	return nfs4_check_fh(current_fh, &stp->st_stid);
 }
 
 /* 
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 5463385..75e0563 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2143,6 +2143,7 @@
 #define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \
 			      FATTR4_WORD0_RDATTR_ERROR)
 #define WORD1_ABSENT_FS_ATTRS FATTR4_WORD1_MOUNTED_ON_FILEID
+#define WORD2_ABSENT_FS_ATTRS 0
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 static inline __be32
@@ -2171,7 +2172,7 @@
 { return 0; }
 #endif
 
-static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err)
+static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *bmval2, u32 *rdattr_err)
 {
 	/* As per referral draft:  */
 	if (*bmval0 & ~WORD0_ABSENT_FS_ATTRS ||
@@ -2184,6 +2185,7 @@
 	}
 	*bmval0 &= WORD0_ABSENT_FS_ATTRS;
 	*bmval1 &= WORD1_ABSENT_FS_ATTRS;
+	*bmval2 &= WORD2_ABSENT_FS_ATTRS;
 	return 0;
 }
 
@@ -2246,8 +2248,7 @@
 	BUG_ON(bmval2 & ~nfsd_suppattrs2(minorversion));
 
 	if (exp->ex_fslocs.migrated) {
-		BUG_ON(bmval[2]);
-		status = fattr_handle_absent_fs(&bmval0, &bmval1, &rdattr_err);
+		status = fattr_handle_absent_fs(&bmval0, &bmval1, &bmval2, &rdattr_err);
 		if (status)
 			goto out;
 	}
@@ -2286,8 +2287,8 @@
 	}
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
-	if ((bmval[2] & FATTR4_WORD2_SECURITY_LABEL) ||
-			bmval[0] & FATTR4_WORD0_SUPPORTED_ATTRS) {
+	if ((bmval2 & FATTR4_WORD2_SECURITY_LABEL) ||
+	     bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) {
 		err = security_inode_getsecctx(d_inode(dentry),
 						&context, &contextlen);
 		contextsupport = (err == 0);
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 9a20e51..aba4381 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -1369,7 +1369,6 @@
 	case NILFS_IOCTL_SYNC:
 	case NILFS_IOCTL_RESIZE:
 	case NILFS_IOCTL_SET_ALLOC_RANGE:
-	case FITRIM:
 		break;
 	default:
 		return -ENOIOCTLCMD;
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 92e48c7..39ddcaf 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -412,16 +412,36 @@
 					 unsigned int flags)
 {
 	struct fsnotify_mark *lmark, *mark;
+	LIST_HEAD(to_free);
 
+	/*
+	 * We have to be really careful here. Anytime we drop mark_mutex, e.g.
+	 * fsnotify_clear_marks_by_inode() can come and free marks. Even in our
+	 * to_free list so we have to use mark_mutex even when accessing that
+	 * list. And freeing mark requires us to drop mark_mutex. So we can
+	 * reliably free only the first mark in the list. That's why we first
+	 * move marks to free to to_free list in one go and then free marks in
+	 * to_free list one by one.
+	 */
 	mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
 	list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
-		if (mark->flags & flags) {
-			fsnotify_get_mark(mark);
-			fsnotify_destroy_mark_locked(mark, group);
-			fsnotify_put_mark(mark);
-		}
+		if (mark->flags & flags)
+			list_move(&mark->g_list, &to_free);
 	}
 	mutex_unlock(&group->mark_mutex);
+
+	while (1) {
+		mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
+		if (list_empty(&to_free)) {
+			mutex_unlock(&group->mark_mutex);
+			break;
+		}
+		mark = list_first_entry(&to_free, struct fsnotify_mark, g_list);
+		fsnotify_get_mark(mark);
+		fsnotify_destroy_mark_locked(mark, group);
+		mutex_unlock(&group->mark_mutex);
+		fsnotify_put_mark(mark);
+	}
 }
 
 /*
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 1a35c61..0f5fd9d 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -685,7 +685,7 @@
 
 	if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
 		u64 s = i_size_read(inode);
-		sector_t sector = (p_cpos << (osb->s_clustersize_bits - 9)) +
+		sector_t sector = ((u64)p_cpos << (osb->s_clustersize_bits - 9)) +
 			(do_div(s, osb->s_clustersize) >> 9);
 
 		ret = blkdev_issue_zeroout(osb->sb->s_bdev, sector,
@@ -910,7 +910,7 @@
 		BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN));
 
 		ret = blkdev_issue_zeroout(osb->sb->s_bdev,
-				p_cpos << (osb->s_clustersize_bits - 9),
+				(u64)p_cpos << (osb->s_clustersize_bits - 9),
 				zero_len_head >> 9, GFP_NOFS, false);
 		if (ret < 0)
 			mlog_errno(ret);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 8b23aa2..23157e4 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -4025,9 +4025,13 @@
 	osb->dc_work_sequence = osb->dc_wake_sequence;
 
 	processed = osb->blocked_lock_count;
-	while (processed) {
-		BUG_ON(list_empty(&osb->blocked_lock_list));
-
+	/*
+	 * blocked lock processing in this loop might call iput which can
+	 * remove items off osb->blocked_lock_list. Downconvert up to
+	 * 'processed' number of locks, but stop short if we had some
+	 * removed in ocfs2_mark_lockres_freeing when downconverting.
+	 */
+	while (processed && !list_empty(&osb->blocked_lock_list)) {
 		lockres = list_entry(osb->blocked_lock_list.next,
 				     struct ocfs2_lock_res, l_blocked_list);
 		list_del_init(&lockres->l_blocked_list);
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 53e6c40..3cb097c 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -980,7 +980,6 @@
 	case OCFS2_IOC_GROUP_EXTEND:
 	case OCFS2_IOC_GROUP_ADD:
 	case OCFS2_IOC_GROUP_ADD64:
-	case FITRIM:
 		break;
 	case OCFS2_IOC_REFLINK:
 		if (copy_from_user(&args, argp, sizeof(args)))
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index f140e3db..d9da5a4 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -343,6 +343,9 @@
 	struct path realpath;
 	enum ovl_path_type type;
 
+	if (d_is_dir(dentry))
+		return d_backing_inode(dentry);
+
 	type = ovl_path_real(dentry, &realpath);
 	if (ovl_open_need_copy_up(file_flags, type, realpath.dentry)) {
 		err = ovl_want_write(dentry);
diff --git a/fs/pnode.h b/fs/pnode.h
index 7114ce6..0fcdbe7 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -20,8 +20,6 @@
 #define SET_MNT_MARK(m) ((m)->mnt.mnt_flags |= MNT_MARKED)
 #define CLEAR_MNT_MARK(m) ((m)->mnt.mnt_flags &= ~MNT_MARKED)
 #define IS_MNT_LOCKED(m) ((m)->mnt.mnt_flags & MNT_LOCKED)
-#define IS_MNT_LOCKED_AND_LAZY(m) \
-	(((m)->mnt.mnt_flags & (MNT_LOCKED|MNT_SYNC_UMOUNT)) == MNT_LOCKED)
 
 #define CL_EXPIRE    		0x01
 #define CL_SLAVE     		0x02
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
index d751fcb..1ade120 100644
--- a/fs/proc/Kconfig
+++ b/fs/proc/Kconfig
@@ -75,3 +75,9 @@
 config PROC_CHILDREN
 	bool "Include /proc/<pid>/task/<tid>/children file"
 	default n
+	help
+	  Provides a fast way to retrieve first level children pids of a task. See
+	  <file:Documentation/filesystems/proc.txt> for more information.
+
+	  Say Y if you are running any user-space software which takes benefit from
+	  this interface. For example, rkt is such a piece of software.
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 87782e8..aa50d1a 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -243,6 +243,11 @@
 	len1 = arg_end - arg_start;
 	len2 = env_end - env_start;
 
+	/* Empty ARGV. */
+	if (len1 == 0) {
+		rv = 0;
+		goto out_free_page;
+	}
 	/*
 	 * Inherently racy -- command line shares address space
 	 * with code and data.
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 91a4e64..92e6726 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -92,7 +92,7 @@
 			     roundup(sizeof(CORE_STR), 4)) +
 			roundup(sizeof(struct elf_prstatus), 4) +
 			roundup(sizeof(struct elf_prpsinfo), 4) +
-			roundup(sizeof(struct task_struct), 4);
+			roundup(arch_task_struct_size, 4);
 	*elf_buflen = PAGE_ALIGN(*elf_buflen);
 	return size + *elf_buflen;
 }
@@ -415,7 +415,7 @@
 	/* set up the task structure */
 	notes[2].name	= CORE_STR;
 	notes[2].type	= NT_TASKSTRUCT;
-	notes[2].datasz	= sizeof(struct task_struct);
+	notes[2].datasz	= arch_task_struct_size;
 	notes[2].data	= current;
 
 	nhdr->p_filesz	+= notesize(&notes[2]);
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 7e412ad..270221f 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -121,8 +121,9 @@
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitly for the right codes here.
 		 */
-		if (kinfo->si_code == BUS_MCEERR_AR ||
-		    kinfo->si_code == BUS_MCEERR_AO)
+		if (kinfo->si_signo == SIGBUS &&
+		    (kinfo->si_code == BUS_MCEERR_AR ||
+		     kinfo->si_code == BUS_MCEERR_AO))
 			err |= __put_user((short) kinfo->si_addr_lsb,
 					  &uinfo->ssi_addr_lsb);
 #endif
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 6afac3d..8d0b3ad 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -1652,17 +1652,9 @@
 		       iinfo->i_ext.i_data, inode->i_sb->s_blocksize -
 					sizeof(struct unallocSpaceEntry));
 		use->descTag.tagIdent = cpu_to_le16(TAG_IDENT_USE);
-		use->descTag.tagLocation =
-				cpu_to_le32(iinfo->i_location.logicalBlockNum);
-		crclen = sizeof(struct unallocSpaceEntry) +
-				iinfo->i_lenAlloc - sizeof(struct tag);
-		use->descTag.descCRCLength = cpu_to_le16(crclen);
-		use->descTag.descCRC = cpu_to_le16(crc_itu_t(0, (char *)use +
-							   sizeof(struct tag),
-							   crclen));
-		use->descTag.tagChecksum = udf_tag_checksum(&use->descTag);
+		crclen = sizeof(struct unallocSpaceEntry);
 
-		goto out;
+		goto finish;
 	}
 
 	if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_UID_FORGET))
@@ -1782,6 +1774,8 @@
 		efe->descTag.tagIdent = cpu_to_le16(TAG_IDENT_EFE);
 		crclen = sizeof(struct extendedFileEntry);
 	}
+
+finish:
 	if (iinfo->i_strat4096) {
 		fe->icbTag.strategyType = cpu_to_le16(4096);
 		fe->icbTag.strategyParameter = cpu_to_le16(1);
@@ -1791,7 +1785,9 @@
 		fe->icbTag.numEntries = cpu_to_le16(1);
 	}
 
-	if (S_ISDIR(inode->i_mode))
+	if (iinfo->i_use)
+		fe->icbTag.fileType = ICBTAG_FILE_TYPE_USE;
+	else if (S_ISDIR(inode->i_mode))
 		fe->icbTag.fileType = ICBTAG_FILE_TYPE_DIRECTORY;
 	else if (S_ISREG(inode->i_mode))
 		fe->icbTag.fileType = ICBTAG_FILE_TYPE_REGULAR;
@@ -1828,7 +1824,6 @@
 						  crclen));
 	fe->descTag.tagChecksum = udf_tag_checksum(&fe->descTag);
 
-out:
 	set_buffer_uptodate(bh);
 	unlock_buffer(bh);
 
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 20de88d..dd71403 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -159,11 +159,10 @@
 	struct xfs_buf	*bp)
 {
 	struct xfs_mount *mp = bp->b_target->bt_mount;
-	struct xfs_buf_log_item	*bip = bp->b_fspriv;
+	int		blksize = mp->m_attr_geo->blksize;
 	char		*ptr;
 	int		len;
 	xfs_daddr_t	bno;
-	int		blksize = mp->m_attr_geo->blksize;
 
 	/* no verification of non-crc buffers */
 	if (!xfs_sb_version_hascrc(&mp->m_sb))
@@ -175,16 +174,22 @@
 	ASSERT(len >= blksize);
 
 	while (len > 0) {
+		struct xfs_attr3_rmt_hdr *rmt = (struct xfs_attr3_rmt_hdr *)ptr;
+
 		if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) {
 			xfs_buf_ioerror(bp, -EFSCORRUPTED);
 			xfs_verifier_error(bp);
 			return;
 		}
-		if (bip) {
-			struct xfs_attr3_rmt_hdr *rmt;
 
-			rmt = (struct xfs_attr3_rmt_hdr *)ptr;
-			rmt->rm_lsn = cpu_to_be64(bip->bli_item.li_lsn);
+		/*
+		 * Ensure we aren't writing bogus LSNs to disk. See
+		 * xfs_attr3_rmt_hdr_set() for the explanation.
+		 */
+		if (rmt->rm_lsn != cpu_to_be64(NULLCOMMITLSN)) {
+			xfs_buf_ioerror(bp, -EFSCORRUPTED);
+			xfs_verifier_error(bp);
+			return;
 		}
 		xfs_update_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF);
 
@@ -221,6 +226,18 @@
 	rmt->rm_owner = cpu_to_be64(ino);
 	rmt->rm_blkno = cpu_to_be64(bno);
 
+	/*
+	 * Remote attribute blocks are written synchronously, so we don't
+	 * have an LSN that we can stamp in them that makes any sense to log
+	 * recovery. To ensure that log recovery handles overwrites of these
+	 * blocks sanely (i.e. once they've been freed and reallocated as some
+	 * other type of metadata) we need to ensure that the LSN has a value
+	 * that tells log recovery to ignore the LSN and overwrite the buffer
+	 * with whatever is in it's log. To do this, we use the magic
+	 * NULLCOMMITLSN to indicate that the LSN is invalid.
+	 */
+	rmt->rm_lsn = cpu_to_be64(NULLCOMMITLSN);
+
 	return sizeof(struct xfs_attr3_rmt_hdr);
 }
 
@@ -434,14 +451,21 @@
 
 		/*
 		 * Allocate a single extent, up to the size of the value.
+		 *
+		 * Note that we have to consider this a data allocation as we
+		 * write the remote attribute without logging the contents.
+		 * Hence we must ensure that we aren't using blocks that are on
+		 * the busy list so that we don't overwrite blocks which have
+		 * recently been freed but their transactions are not yet
+		 * committed to disk. If we overwrite the contents of a busy
+		 * extent and then crash then the block may not contain the
+		 * correct metadata after log recovery occurs.
 		 */
 		xfs_bmap_init(args->flist, args->firstblock);
 		nmap = 1;
 		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
-				  blkcnt,
-				  XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA,
-				  args->firstblock, args->total, &map, &nmap,
-				  args->flist);
+				  blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock,
+				  args->total, &map, &nmap, args->flist);
 		if (!error) {
 			error = xfs_bmap_finish(&args->trans, args->flist,
 						&committed);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f0e8249..db4acc1 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1514,18 +1514,27 @@
 	struct vm_area_struct	*vma,
 	struct vm_fault		*vmf)
 {
-	struct xfs_inode	*ip = XFS_I(file_inode(vma->vm_file));
+	struct inode		*inode = file_inode(vma->vm_file);
 	int			ret;
 
-	trace_xfs_filemap_fault(ip);
+	trace_xfs_filemap_fault(XFS_I(inode));
 
 	/* DAX can shortcut the normal fault path on write faults! */
-	if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(VFS_I(ip)))
+	if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(inode))
 		return xfs_filemap_page_mkwrite(vma, vmf);
 
-	xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
-	ret = filemap_fault(vma, vmf);
-	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
+	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+	if (IS_DAX(inode)) {
+		/*
+		 * we do not want to trigger unwritten extent conversion on read
+		 * faults - that is unnecessary overhead and would also require
+		 * changes to xfs_get_blocks_direct() to map unwritten extent
+		 * ioend for conversion on read-only mappings.
+		 */
+		ret = __dax_fault(vma, vmf, xfs_get_blocks_direct, NULL);
+	} else
+		ret = filemap_fault(vma, vmf);
+	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	return ret;
 }
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 01dd228..480ebba 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1886,9 +1886,14 @@
 		uuid = &((struct xfs_dir3_blk_hdr *)blk)->uuid;
 		break;
 	case XFS_ATTR3_RMT_MAGIC:
-		lsn = be64_to_cpu(((struct xfs_attr3_rmt_hdr *)blk)->rm_lsn);
-		uuid = &((struct xfs_attr3_rmt_hdr *)blk)->rm_uuid;
-		break;
+		/*
+		 * Remote attr blocks are written synchronously, rather than
+		 * being logged. That means they do not contain a valid LSN
+		 * (i.e. transactionally ordered) in them, and hence any time we
+		 * see a buffer to replay over the top of a remote attribute
+		 * block we should simply do so.
+		 */
+		goto recover_immediately;
 	case XFS_SB_MAGIC:
 		lsn = be64_to_cpu(((struct xfs_dsb *)blk)->sb_lsn);
 		uuid = &((struct xfs_dsb *)blk)->sb_uuid;
diff --git a/include/asm-generic/mm-arch-hooks.h b/include/asm-generic/mm-arch-hooks.h
new file mode 100644
index 0000000..5ff0e51
--- /dev/null
+++ b/include/asm-generic/mm-arch-hooks.h
@@ -0,0 +1,16 @@
+/*
+ * Architecture specific mm hooks
+ */
+
+#ifndef _ASM_GENERIC_MM_ARCH_HOOKS_H
+#define _ASM_GENERIC_MM_ARCH_HOOKS_H
+
+/*
+ * This file should be included through arch/../include/asm/Kbuild for
+ * the architecture which doesn't need specific mm hooks.
+ *
+ * In that case, the generic hooks defined in include/linux/mm-arch-hooks.h
+ * are used.
+ */
+
+#endif /* _ASM_GENERIC_MM_ARCH_HOOKS_H */
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 48db6a5..5aa5197 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -691,7 +691,7 @@
 	struct timer_list disable_timer;		/* delayed disable timer */
 
 	/* vblank counter, protected by dev->vblank_time_lock for writes */
-	unsigned long count;
+	u32 count;
 	/* vblank timestamps, protected by dev->vblank_time_lock for writes */
 	struct timeval time[DRM_VBLANKTIME_RBSIZE];
 
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 57ca8cc..3b4d8a4 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -743,8 +743,6 @@
 	uint8_t num_h_tile, num_v_tile;
 	uint8_t tile_h_loc, tile_v_loc;
 	uint16_t tile_h_size, tile_v_size;
-
-	struct list_head destroy_list;
 };
 
 /**
diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h
index c8fc187..918aa68 100644
--- a/include/drm/drm_crtc_helper.h
+++ b/include/drm/drm_crtc_helper.h
@@ -168,6 +168,7 @@
  * @get_modes: get mode list for this connector
  * @mode_valid: is this mode valid on the given connector? (optional)
  * @best_encoder: return the preferred encoder for this connector
+ * @atomic_best_encoder: atomic version of @best_encoder
  *
  * The helper operations are called by the mid-layer CRTC helper.
  */
@@ -176,6 +177,8 @@
 	enum drm_mode_status (*mode_valid)(struct drm_connector *connector,
 					   struct drm_display_mode *mode);
 	struct drm_encoder *(*best_encoder)(struct drm_connector *connector);
+	struct drm_encoder *(*atomic_best_encoder)(struct drm_connector *connector,
+						   struct drm_connector_state *connector_state);
 };
 
 extern void drm_helper_disable_unused_functions(struct drm_device *dev);
diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h
index 7990501..53c53c4 100644
--- a/include/drm/drm_edid.h
+++ b/include/drm/drm_edid.h
@@ -348,6 +348,25 @@
 }
 
 /**
+ * drm_eld_sad - Get ELD SAD structures.
+ * @eld: pointer to an eld memory structure with sad_count set
+ */
+static inline const uint8_t *drm_eld_sad(const uint8_t *eld)
+{
+	unsigned int ver, mnl;
+
+	ver = (eld[DRM_ELD_VER] & DRM_ELD_VER_MASK) >> DRM_ELD_VER_SHIFT;
+	if (ver != 2 && ver != 31)
+		return NULL;
+
+	mnl = drm_eld_mnl(eld);
+	if (mnl > 16)
+		return NULL;
+
+	return eld + DRM_ELD_CEA_SAD(mnl, 0);
+}
+
+/**
  * drm_eld_sad_count - Get ELD SAD count.
  * @eld: pointer to an eld memory structure with sad_count set
  */
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 45c39a3..8bc073d 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -172,6 +172,7 @@
 	{0x1002, 0x6610, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6611, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6613, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_NEW_MEMMAP}, \
+	{0x1002, 0x6617, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6620, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6621, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
 	{0x1002, 0x6623, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_OLAND|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index c471dfc..d2445fa 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -58,6 +58,19 @@
 	acpi_fwnode_handle(adev) : NULL)
 #define ACPI_HANDLE(dev)		acpi_device_handle(ACPI_COMPANION(dev))
 
+/**
+ * ACPI_DEVICE_CLASS - macro used to describe an ACPI device with
+ * the PCI-defined class-code information
+ *
+ * @_cls : the class, subclass, prog-if triple for this device
+ * @_msk : the class mask for this device
+ *
+ * This macro is used to create a struct acpi_device_id that matches a
+ * specific PCI class. The .id and .driver_data fields will be left
+ * initialized with the default value.
+ */
+#define ACPI_DEVICE_CLASS(_cls, _msk)	.cls = (_cls), .cls_msk = (_msk),
+
 static inline bool has_acpi_companion(struct device *dev)
 {
 	return is_acpi_node(dev->fwnode);
@@ -309,9 +322,6 @@
 
 int acpi_resources_are_enforced(void);
 
-int acpi_reserve_region(u64 start, unsigned int length, u8 space_id,
-			unsigned long flags, char *desc);
-
 #ifdef CONFIG_HIBERNATION
 void __init acpi_no_s4_hw_signature(void);
 #endif
@@ -446,6 +456,7 @@
 #define ACPI_COMPANION(dev)		(NULL)
 #define ACPI_COMPANION_SET(dev, adev)	do { } while (0)
 #define ACPI_HANDLE(dev)		(NULL)
+#define ACPI_DEVICE_CLASS(_cls, _msk)	.cls = (0), .cls_msk = (0),
 
 struct fwnode_handle;
 
@@ -507,13 +518,6 @@
 	return 0;
 }
 
-static inline int acpi_reserve_region(u64 start, unsigned int length,
-				      u8 space_id, unsigned long flags,
-				      char *desc)
-{
-	return -ENXIO;
-}
-
 struct acpi_table_header;
 static inline int acpi_table_parse(char *id,
 				int (*handler)(struct acpi_table_header *))
diff --git a/include/linux/amba/sp810.h b/include/linux/amba/sp810.h
index c7df89f..58fe9e8 100644
--- a/include/linux/amba/sp810.h
+++ b/include/linux/amba/sp810.h
@@ -2,7 +2,7 @@
  * ARM PrimeXsys System Controller SP810 header file
  *
  * Copyright (C) 2009 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/include/linux/ata.h b/include/linux/ata.h
index fed3641..d2992bf 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -45,6 +45,7 @@
 	ATA_SECT_SIZE		= 512,
 	ATA_MAX_SECTORS_128	= 128,
 	ATA_MAX_SECTORS		= 256,
+	ATA_MAX_SECTORS_1024    = 1024,
 	ATA_MAX_SECTORS_LBA48	= 65535,/* TODO: 65536? */
 	ATA_MAX_SECTORS_TAPE	= 65535,
 
@@ -384,8 +385,6 @@
 	SATA_SSP		= 0x06,	/* Software Settings Preservation */
 	SATA_DEVSLP		= 0x09,	/* Device Sleep */
 
-	SETFEATURE_SENSE_DATA = 0xC3, /* Sense Data Reporting feature */
-
 	/* feature values for SET_MAX */
 	ATA_SET_MAX_ADDR	= 0x00,
 	ATA_SET_MAX_PASSWD	= 0x01,
@@ -529,8 +528,6 @@
 #define ata_id_cdb_intr(id)	(((id)[ATA_ID_CONFIG] & 0x60) == 0x20)
 #define ata_id_has_da(id)	((id)[ATA_ID_SATA_CAPABILITY_2] & (1 << 4))
 #define ata_id_has_devslp(id)	((id)[ATA_ID_FEATURE_SUPP] & (1 << 8))
-#define ata_id_has_ncq_autosense(id) \
-				((id)[ATA_ID_FEATURE_SUPP] & (1 << 7))
 
 static inline bool ata_id_has_hipm(const u16 *id)
 {
@@ -719,20 +716,6 @@
 	return false;
 }
 
-static inline bool ata_id_has_sense_reporting(const u16 *id)
-{
-	if (!(id[ATA_ID_CFS_ENABLE_2] & (1 << 15)))
-		return false;
-	return id[ATA_ID_COMMAND_SET_3] & (1 << 6);
-}
-
-static inline bool ata_id_sense_reporting_enabled(const u16 *id)
-{
-	if (!(id[ATA_ID_CFS_ENABLE_2] & (1 << 15)))
-		return false;
-	return id[ATA_ID_COMMAND_SET_4] & (1 << 6);
-}
-
 /**
  *	ata_id_major_version	-	get ATA level of drive
  *	@id: Identify data
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 58cfab8..1b62d76 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -47,6 +47,7 @@
 
 	struct blkcg_policy_data	*pd[BLKCG_MAX_POLS];
 
+	struct list_head		all_blkcgs_node;
 #ifdef CONFIG_CGROUP_WRITEBACK
 	struct list_head		cgwb_list;
 #endif
@@ -88,18 +89,12 @@
  * Policies that need to keep per-blkcg data which is independent
  * from any request_queue associated to it must specify its size
  * with the cpd_size field of the blkcg_policy structure and
- * embed a blkcg_policy_data in it. blkcg core allocates
- * policy-specific per-blkcg structures lazily the first time
- * they are actually needed, so it handles them together with
- * blkgs. cpd_init() is invoked to let each policy handle
- * per-blkcg data.
+ * embed a blkcg_policy_data in it.  cpd_init() is invoked to let
+ * each policy handle per-blkcg data.
  */
 struct blkcg_policy_data {
 	/* the policy id this per-policy data belongs to */
 	int				plid;
-
-	/* used during policy activation */
-	struct list_head		alloc_node;
 };
 
 /* association between a blk cgroup and a request queue */
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 73b4522..e6797de 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -317,6 +317,13 @@
 	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
 }
 
+
+static inline struct buffer_head *
+sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp)
+{
+	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp);
+}
+
 static inline struct buffer_head *
 sb_find_get_block(struct super_block *sb, sector_t block)
 {
diff --git a/include/linux/can/skb.h b/include/linux/can/skb.h
index b6a52a4..51bb653 100644
--- a/include/linux/can/skb.h
+++ b/include/linux/can/skb.h
@@ -27,10 +27,12 @@
 /**
  * struct can_skb_priv - private additional data inside CAN sk_buffs
  * @ifindex:	ifindex of the first interface the CAN frame appeared on
+ * @skbcnt:	atomic counter to have an unique id together with skb pointer
  * @cf:		align to the following CAN frame at skb->data
  */
 struct can_skb_priv {
 	int ifindex;
+	int skbcnt;
 	struct can_frame cf[0];
 };
 
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index e154994..3775327 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -8,6 +8,7 @@
 #include <linux/radix-tree.h>
 #include <linux/uio.h>
 #include <linux/workqueue.h>
+#include <net/net_namespace.h>
 
 #include <linux/ceph/types.h>
 #include <linux/ceph/buffer.h>
@@ -56,6 +57,7 @@
 	struct ceph_entity_addr my_enc_addr;
 
 	atomic_t stopping;
+	possible_net_t net;
 	bool nocrc;
 	bool tcp_nodelay;
 
@@ -267,6 +269,7 @@
 			u64 required_features,
 			bool nocrc,
 			bool tcp_nodelay);
+extern void ceph_messenger_fini(struct ceph_messenger *msgr);
 
 extern void ceph_con_init(struct ceph_connection *con, void *private,
 			const struct ceph_connection_operations *ops,
diff --git a/include/linux/clkdev.h b/include/linux/clkdev.h
index a240b18..08bffcc 100644
--- a/include/linux/clkdev.h
+++ b/include/linux/clkdev.h
@@ -33,18 +33,19 @@
 	}
 
 struct clk_lookup *clkdev_alloc(struct clk *clk, const char *con_id,
-	const char *dev_fmt, ...);
+	const char *dev_fmt, ...) __printf(3, 4);
 
 void clkdev_add(struct clk_lookup *cl);
 void clkdev_drop(struct clk_lookup *cl);
 
 struct clk_lookup *clkdev_create(struct clk *clk, const char *con_id,
-	const char *dev_fmt, ...);
+	const char *dev_fmt, ...) __printf(3, 4);
 
 void clkdev_add_table(struct clk_lookup *, size_t);
 int clk_add_alias(const char *, const char *, const char *, struct device *);
 
-int clk_register_clkdev(struct clk *, const char *, const char *, ...);
+int clk_register_clkdev(struct clk *, const char *, const char *, ...)
+	__printf(3, 4);
 int clk_register_clkdevs(struct clk *, struct clk_lookup *, size_t);
 
 #ifdef CONFIG_COMMON_CLK
diff --git a/include/linux/compat.h b/include/linux/compat.h
index ab25814..a76c917 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -424,7 +424,7 @@
 
 asmlinkage long compat_sys_adjtimex(struct compat_timex __user *utp);
 
-extern int compat_printk(const char *fmt, ...);
+extern __printf(1, 2) int compat_printk(const char *fmt, ...);
 extern void sigset_from_compat(sigset_t *set, const compat_sigset_t *compat);
 extern void sigset_to_compat(compat_sigset_t *compat, const sigset_t *set);
 
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 7f8ad95..e08a6ae 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -17,11 +17,11 @@
 # define __release(x)	__context__(x,-1)
 # define __cond_lock(x,c)	((c) ? ({ __acquire(x); 1; }) : 0)
 # define __percpu	__attribute__((noderef, address_space(3)))
+# define __pmem		__attribute__((noderef, address_space(5)))
 #ifdef CONFIG_SPARSE_RCU_POINTER
 # define __rcu		__attribute__((noderef, address_space(4)))
 #else
 # define __rcu
-# define __pmem		__attribute__((noderef, address_space(5)))
 #endif
 extern void __chk_user_ptr(const volatile void __user *);
 extern void __chk_io_ptr(const volatile void __iomem *);
diff --git a/include/linux/configfs.h b/include/linux/configfs.h
index c9e5c57..63a36e8 100644
--- a/include/linux/configfs.h
+++ b/include/linux/configfs.h
@@ -64,7 +64,8 @@
 	struct dentry		*ci_dentry;
 };
 
-extern int config_item_set_name(struct config_item *, const char *, ...);
+extern __printf(2, 3)
+int config_item_set_name(struct config_item *, const char *, ...);
 
 static inline char *config_item_name(struct config_item * item)
 {
diff --git a/include/linux/cper.h b/include/linux/cper.h
index 76abba4..dcacb1a 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -340,7 +340,27 @@
 	__u64	mm_reg_addr;
 };
 
-/* Memory Error Section */
+/* Old Memory Error Section UEFI 2.1, 2.2 */
+struct cper_sec_mem_err_old {
+	__u64	validation_bits;
+	__u64	error_status;
+	__u64	physical_addr;
+	__u64	physical_addr_mask;
+	__u16	node;
+	__u16	card;
+	__u16	module;
+	__u16	bank;
+	__u16	device;
+	__u16	row;
+	__u16	column;
+	__u16	bit_pos;
+	__u64	requestor_id;
+	__u64	responder_id;
+	__u64	target_id;
+	__u8	error_type;
+};
+
+/* Memory Error Section UEFI >= 2.3 */
 struct cper_sec_mem_err {
 	__u64	validation_bits;
 	__u64	error_status;
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index c0fb6b1..23c30bd 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -40,9 +40,10 @@
 extern int cpu_add_dev_attr_group(struct attribute_group *attrs);
 extern void cpu_remove_dev_attr_group(struct attribute_group *attrs);
 
-extern struct device *cpu_device_create(struct device *parent, void *drvdata,
-					const struct attribute_group **groups,
-					const char *fmt, ...);
+extern __printf(4, 5)
+struct device *cpu_device_create(struct device *parent, void *drvdata,
+				 const struct attribute_group **groups,
+				 const char *fmt, ...);
 #ifdef CONFIG_HOTPLUG_CPU
 extern void unregister_cpu(struct cpu *cpu);
 extern ssize_t arch_cpu_probe(const char *, size_t);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 29ad97c..bde1e56 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -62,6 +62,7 @@
 	/* CPUs sharing clock, require sw coordination */
 	cpumask_var_t		cpus;	/* Online CPUs only */
 	cpumask_var_t		related_cpus; /* Online + Offline CPUs */
+	cpumask_var_t		real_cpus; /* Related and present */
 
 	unsigned int		shared_type; /* ACPI: ANY or ALL affected CPUs
 						should set cpufreq */
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index d2d5024..d67ae11 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -327,7 +327,8 @@
 /*
  * helper function for dentry_operations.d_dname() members
  */
-extern char *dynamic_dname(struct dentry *, char *, int, const char *, ...);
+extern __printf(4, 5)
+char *dynamic_dname(struct dentry *, char *, int, const char *, ...);
 extern char *simple_dname(struct dentry *, char *, int);
 
 extern char *__d_path(const struct path *, const struct path *, char *, int);
diff --git a/include/linux/device.h b/include/linux/device.h
index 5a31bf3..a2b4ea7 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -637,8 +637,9 @@
 
 /* managed devm_k.alloc/kfree for device drivers */
 extern void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp);
-extern char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt,
-			     va_list ap);
+extern __printf(3, 0)
+char *devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt,
+		      va_list ap);
 extern __printf(3, 4)
 char *devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...);
 static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp)
@@ -1011,12 +1012,10 @@
 /*
  * Easy functions for dynamically creating devices on the fly
  */
-extern struct device *device_create_vargs(struct class *cls,
-					  struct device *parent,
-					  dev_t devt,
-					  void *drvdata,
-					  const char *fmt,
-					  va_list vargs);
+extern __printf(5, 0)
+struct device *device_create_vargs(struct class *cls, struct device *parent,
+				   dev_t devt, void *drvdata,
+				   const char *fmt, va_list vargs);
 extern __printf(5, 6)
 struct device *device_create(struct class *cls, struct device *parent,
 			     dev_t devt, void *drvdata,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a0653e5..84b783f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -55,7 +55,8 @@
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
-extern void __init files_init(unsigned long);
+extern void __init files_init(void);
+extern void __init files_maxfiles_init(void);
 
 extern struct files_stat_struct files_stat;
 extern unsigned long get_max_files(void);
@@ -1046,12 +1047,12 @@
 extern void locks_release_private(struct file_lock *);
 extern void posix_test_lock(struct file *, struct file_lock *);
 extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *);
-extern int posix_lock_file_wait(struct file *, struct file_lock *);
+extern int posix_lock_inode_wait(struct inode *, struct file_lock *);
 extern int posix_unblock_lock(struct file_lock *);
 extern int vfs_test_lock(struct file *, struct file_lock *);
 extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *);
 extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
-extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl);
+extern int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl);
 extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
 extern void lease_get_mtime(struct inode *, struct timespec *time);
 extern int generic_setlease(struct file *, long, struct file_lock **, void **priv);
@@ -1137,7 +1138,8 @@
 	return -ENOLCK;
 }
 
-static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl)
+static inline int posix_lock_inode_wait(struct inode *inode,
+					struct file_lock *fl)
 {
 	return -ENOLCK;
 }
@@ -1163,8 +1165,8 @@
 	return 0;
 }
 
-static inline int flock_lock_file_wait(struct file *filp,
-				       struct file_lock *request)
+static inline int flock_lock_inode_wait(struct inode *inode,
+					struct file_lock *request)
 {
 	return -ENOLCK;
 }
@@ -1202,6 +1204,20 @@
 			struct file *filp, struct files_struct *files) {}
 #endif /* !CONFIG_FILE_LOCKING */
 
+static inline struct inode *file_inode(const struct file *f)
+{
+	return f->f_inode;
+}
+
+static inline int posix_lock_file_wait(struct file *filp, struct file_lock *fl)
+{
+	return posix_lock_inode_wait(file_inode(filp), fl);
+}
+
+static inline int flock_lock_file_wait(struct file *filp, struct file_lock *fl)
+{
+	return flock_lock_inode_wait(file_inode(filp), fl);
+}
 
 struct fasync_struct {
 	spinlock_t		fa_lock;
@@ -2011,11 +2027,6 @@
 extern void iput(struct inode *);
 extern int generic_update_time(struct inode *, struct timespec *, int);
 
-static inline struct inode *file_inode(const struct file *f)
-{
-	return f->f_inode;
-}
-
 /* /sys/fs */
 extern struct kobject *fs_kobj;
 
@@ -2235,7 +2246,7 @@
 
 /* fs/dcache.c */
 extern void __init vfs_caches_init_early(void);
-extern void __init vfs_caches_init(unsigned long);
+extern void __init vfs_caches_init(void);
 
 extern struct kmem_cache *names_cachep;
 
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 1da6029..6cd8c0e 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -116,6 +116,7 @@
  *            SAVE_REGS. If another ops with this flag set is already registered
  *            for any of the functions that this ops will be registered for, then
  *            this ops will fail to register or set_filter_ip.
+ * PID     - Is affected by set_ftrace_pid (allows filtering on those pids)
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= 1 << 0,
@@ -132,6 +133,7 @@
 	FTRACE_OPS_FL_MODIFYING			= 1 << 11,
 	FTRACE_OPS_FL_ALLOC_TRAMP		= 1 << 12,
 	FTRACE_OPS_FL_IPMODIFY			= 1 << 13,
+	FTRACE_OPS_FL_PID			= 1 << 14,
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -159,6 +161,7 @@
 	struct ftrace_ops		*next;
 	unsigned long			flags;
 	void				*private;
+	ftrace_func_t			saved_func;
 	int __percpu			*disabled;
 #ifdef CONFIG_DYNAMIC_FTRACE
 	int				nr_trampolines;
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index cc7ec12..c8393cd 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -45,7 +45,7 @@
  * @base: identifies the first GPIO number handled by this chip;
  *	or, if negative during registration, requests dynamic ID allocation.
  *	DEPRECATION: providing anything non-negative and nailing the base
- *	base offset of GPIO chips is deprecated. Please pass -1 as base to
+ *	offset of GPIO chips is deprecated. Please pass -1 as base to
  *	let gpiolib select the chip base in all possible cases. We want to
  *	get rid of the static GPIO number space in the long run.
  * @ngpio: the number of GPIOs handled by this controller; the last GPIO
diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h
index 0042bf3..c02b5ce 100644
--- a/include/linux/hid-sensor-hub.h
+++ b/include/linux/hid-sensor-hub.h
@@ -230,6 +230,7 @@
 	struct platform_device *pdev;
 	unsigned usage_id;
 	atomic_t data_ready;
+	atomic_t user_requested_state;
 	struct iio_trigger *trigger;
 	struct hid_sensor_hub_attribute_info poll;
 	struct hid_sensor_hub_attribute_info report_state;
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 2050261..d891f94 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -460,15 +460,14 @@
 	return &mm->page_table_lock;
 }
 
-static inline bool hugepages_supported(void)
-{
-	/*
-	 * Some platform decide whether they support huge pages at boot
-	 * time. On these, such as powerpc, HPAGE_SHIFT is set to 0 when
-	 * there is no such support
-	 */
-	return HPAGE_SHIFT != 0;
-}
+#ifndef hugepages_supported
+/*
+ * Some platform decide whether they support huge pages at boot
+ * time. Some of them, such as powerpc, set HPAGE_SHIFT to 0
+ * when there is no such support
+ */
+#define hugepages_supported() (HPAGE_SHIFT != 0)
+#endif
 
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
diff --git a/include/linux/init.h b/include/linux/init.h
index 7c68c36..b449f37 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -282,68 +282,8 @@
 void __init parse_early_options(char *cmdline);
 #endif /* __ASSEMBLY__ */
 
-/**
- * module_init() - driver initialization entry point
- * @x: function to be run at kernel boot time or module insertion
- * 
- * module_init() will either be called during do_initcalls() (if
- * builtin) or at module insertion time (if a module).  There can only
- * be one per module.
- */
-#define module_init(x)	__initcall(x);
-
-/**
- * module_exit() - driver exit entry point
- * @x: function to be run when driver is removed
- * 
- * module_exit() will wrap the driver clean-up code
- * with cleanup_module() when used with rmmod when
- * the driver is a module.  If the driver is statically
- * compiled into the kernel, module_exit() has no effect.
- * There can only be one per module.
- */
-#define module_exit(x)	__exitcall(x);
-
 #else /* MODULE */
 
-/*
- * In most cases loadable modules do not need custom
- * initcall levels. There are still some valid cases where
- * a driver may be needed early if built in, and does not
- * matter when built as a loadable module. Like bus
- * snooping debug drivers.
- */
-#define early_initcall(fn)		module_init(fn)
-#define core_initcall(fn)		module_init(fn)
-#define core_initcall_sync(fn)		module_init(fn)
-#define postcore_initcall(fn)		module_init(fn)
-#define postcore_initcall_sync(fn)	module_init(fn)
-#define arch_initcall(fn)		module_init(fn)
-#define subsys_initcall(fn)		module_init(fn)
-#define subsys_initcall_sync(fn)	module_init(fn)
-#define fs_initcall(fn)			module_init(fn)
-#define fs_initcall_sync(fn)		module_init(fn)
-#define rootfs_initcall(fn)		module_init(fn)
-#define device_initcall(fn)		module_init(fn)
-#define device_initcall_sync(fn)	module_init(fn)
-#define late_initcall(fn)		module_init(fn)
-#define late_initcall_sync(fn)		module_init(fn)
-
-#define console_initcall(fn)		module_init(fn)
-#define security_initcall(fn)		module_init(fn)
-
-/* Each module must use one module_init(). */
-#define module_init(initfn)					\
-	static inline initcall_t __inittest(void)		\
-	{ return initfn; }					\
-	int init_module(void) __attribute__((alias(#initfn)));
-
-/* This is only required if you want to be unloadable. */
-#define module_exit(exitfn)					\
-	static inline exitcall_t __exittest(void)		\
-	{ return exitfn; }					\
-	void cleanup_module(void) __attribute__((alias(#exitfn)));
-
 #define __setup_param(str, unique_id, fn)	/* nothing */
 #define __setup(str, func) 			/* nothing */
 #endif
@@ -351,24 +291,6 @@
 /* Data marked not to be saved by software suspend */
 #define __nosavedata __section(.data..nosave)
 
-/* This means "can be init if no module support, otherwise module load
-   may call it." */
-#ifdef CONFIG_MODULES
-#define __init_or_module
-#define __initdata_or_module
-#define __initconst_or_module
-#define __INIT_OR_MODULE	.text
-#define __INITDATA_OR_MODULE	.data
-#define __INITRODATA_OR_MODULE	.section ".rodata","a",%progbits
-#else
-#define __init_or_module __init
-#define __initdata_or_module __initdata
-#define __initconst_or_module __initconst
-#define __INIT_OR_MODULE __INIT
-#define __INITDATA_OR_MODULE __INITDATA
-#define __INITRODATA_OR_MODULE __INITRODATA
-#endif /*CONFIG_MODULES*/
-
 #ifdef MODULE
 #define __exit_p(x) x
 #else
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index dc767f7..f9c1b6d 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -258,7 +258,7 @@
 				 void *data);
 struct device *iommu_device_create(struct device *parent, void *drvdata,
 				   const struct attribute_group **groups,
-				   const char *fmt, ...);
+				   const char *fmt, ...) __printf(4, 5);
 void iommu_device_destroy(struct device *dev);
 int iommu_device_link(struct device *dev, struct device *link);
 void iommu_device_unlink(struct device *dev, struct device *link);
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 92188b0..51744bc 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -484,6 +484,7 @@
 extern int irq_chip_set_wake_parent(struct irq_data *data, unsigned int on);
 extern int irq_chip_set_vcpu_affinity_parent(struct irq_data *data,
 					     void *vcpu_info);
+extern int irq_chip_set_type_parent(struct irq_data *data, unsigned int type);
 #endif
 
 /* Handling of unhandled and spurious interrupts: */
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 624a668..fcea4e4 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -87,7 +87,12 @@
 	const char		*name;
 } ____cacheline_internodealigned_in_smp;
 
-#ifndef CONFIG_SPARSE_IRQ
+#ifdef CONFIG_SPARSE_IRQ
+extern void irq_lock_sparse(void);
+extern void irq_unlock_sparse(void);
+#else
+static inline void irq_lock_sparse(void) { }
+static inline void irq_unlock_sparse(void) { }
 extern struct irq_desc irq_desc[NR_IRQS];
 #endif
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 5f0be58..5582410 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -411,7 +411,8 @@
 int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
 extern __printf(2, 3)
 char *kasprintf(gfp_t gfp, const char *fmt, ...);
-extern char *kvasprintf(gfp_t gfp, const char *fmt, va_list args);
+extern __printf(2, 0)
+char *kvasprintf(gfp_t gfp, const char *fmt, va_list args);
 
 extern __scanf(2, 3)
 int sscanf(const char *, const char *, ...);
@@ -679,10 +680,10 @@
 		__ftrace_vprintk(_THIS_IP_, fmt, vargs);		\
 } while (0)
 
-extern int
+extern __printf(2, 0) int
 __ftrace_vbprintk(unsigned long ip, const char *fmt, va_list ap);
 
-extern int
+extern __printf(2, 0) int
 __ftrace_vprintk(unsigned long ip, const char *fmt, va_list ap);
 
 extern void ftrace_dump(enum ftrace_dump_mode oops_dump_mode);
@@ -702,7 +703,7 @@
 {
 	return 0;
 }
-static inline int
+static __printf(1, 0) inline int
 ftrace_vprintk(const char *fmt, va_list ap)
 {
 	return 0;
diff --git a/include/linux/kobject.h b/include/linux/kobject.h
index 2d61b90..637f670 100644
--- a/include/linux/kobject.h
+++ b/include/linux/kobject.h
@@ -80,8 +80,9 @@
 
 extern __printf(2, 3)
 int kobject_set_name(struct kobject *kobj, const char *name, ...);
-extern int kobject_set_name_vargs(struct kobject *kobj, const char *fmt,
-				  va_list vargs);
+extern __printf(2, 0)
+int kobject_set_name_vargs(struct kobject *kobj, const char *fmt,
+			   va_list vargs);
 
 static inline const char *kobject_name(const struct kobject *kobj)
 {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9564fd7..05e99b8 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -734,6 +734,24 @@
 	return false;
 }
 #endif
+#ifdef __KVM_HAVE_ARCH_ASSIGNED_DEVICE
+void kvm_arch_start_assignment(struct kvm *kvm);
+void kvm_arch_end_assignment(struct kvm *kvm);
+bool kvm_arch_has_assigned_device(struct kvm *kvm);
+#else
+static inline void kvm_arch_start_assignment(struct kvm *kvm)
+{
+}
+
+static inline void kvm_arch_end_assignment(struct kvm *kvm)
+{
+}
+
+static inline bool kvm_arch_has_assigned_device(struct kvm *kvm)
+{
+	return false;
+}
+#endif
 
 static inline wait_queue_head_t *kvm_arch_vcpu_wq(struct kvm_vcpu *vcpu)
 {
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 36ce37b..c9cfbcd 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -431,6 +431,8 @@
 	ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21),	/* some WDs have broken LPM */
 	ATA_HORKAGE_ZERO_AFTER_TRIM = (1 << 22),/* guarantees zero after trim */
 	ATA_HORKAGE_NO_NCQ_LOG	= (1 << 23),	/* don't use NCQ for log read */
+	ATA_HORKAGE_NOTRIM	= (1 << 24),	/* don't use TRIM */
+	ATA_HORKAGE_MAX_SEC_1024 = (1 << 25),	/* Limit max sects to 1024 */
 
 	 /* DMA mask for user DMA control: User visible values; DO NOT
 	    renumber */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 2e872f9..bf6f117 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1003,6 +1003,34 @@
 }
 
 /*
+ * Return true only if the page has been allocated with
+ * ALLOC_NO_WATERMARKS and the low watermark was not
+ * met implying that the system is under some pressure.
+ */
+static inline bool page_is_pfmemalloc(struct page *page)
+{
+	/*
+	 * Page index cannot be this large so this must be
+	 * a pfmemalloc page.
+	 */
+	return page->index == -1UL;
+}
+
+/*
+ * Only to be called by the page allocator on a freshly allocated
+ * page.
+ */
+static inline void set_page_pfmemalloc(struct page *page)
+{
+	page->index = -1UL;
+}
+
+static inline void clear_page_pfmemalloc(struct page *page)
+{
+	page->index = 0;
+}
+
+/*
  * Different kinds of faults, as returned by handle_mm_fault().
  * Used to decide whether a process gets delivered SIGBUS or
  * just gets major/minor fault counters bumped up.
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0038ac7..1554957 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -63,15 +63,6 @@
 		union {
 			pgoff_t index;		/* Our offset within mapping. */
 			void *freelist;		/* sl[aou]b first free object */
-			bool pfmemalloc;	/* If set by the page allocator,
-						 * ALLOC_NO_WATERMARKS was set
-						 * and the low watermark was not
-						 * met implying that the system
-						 * is under some pressure. The
-						 * caller should try ensure
-						 * this page is only used to
-						 * free other pages.
-						 */
 		};
 
 		union {
diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h
index c5d5278..3ba327a 100644
--- a/include/linux/mmiotrace.h
+++ b/include/linux/mmiotrace.h
@@ -106,6 +106,6 @@
 extern void disable_mmiotrace(void);
 extern void mmio_trace_rw(struct mmiotrace_rw *rw);
 extern void mmio_trace_mapping(struct mmiotrace_map *map);
-extern int mmio_trace_printk(const char *fmt, va_list args);
+extern __printf(1, 0) int mmio_trace_printk(const char *fmt, va_list args);
 
 #endif /* _LINUX_MMIOTRACE_H */
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index 8183d66..34f25b7 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -189,6 +189,8 @@
 struct acpi_device_id {
 	__u8 id[ACPI_ID_LEN];
 	kernel_ulong_t driver_data;
+	__u32 cls;
+	__u32 cls_msk;
 };
 
 #define PNP_ID_LEN	8
diff --git a/include/linux/module.h b/include/linux/module.h
index d67b193..3a19c79 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -11,6 +11,7 @@
 #include <linux/compiler.h>
 #include <linux/cache.h>
 #include <linux/kmod.h>
+#include <linux/init.h>
 #include <linux/elf.h>
 #include <linux/stringify.h>
 #include <linux/kobject.h>
@@ -71,6 +72,89 @@
 extern int init_module(void);
 extern void cleanup_module(void);
 
+#ifndef MODULE
+/**
+ * module_init() - driver initialization entry point
+ * @x: function to be run at kernel boot time or module insertion
+ *
+ * module_init() will either be called during do_initcalls() (if
+ * builtin) or at module insertion time (if a module).  There can only
+ * be one per module.
+ */
+#define module_init(x)	__initcall(x);
+
+/**
+ * module_exit() - driver exit entry point
+ * @x: function to be run when driver is removed
+ *
+ * module_exit() will wrap the driver clean-up code
+ * with cleanup_module() when used with rmmod when
+ * the driver is a module.  If the driver is statically
+ * compiled into the kernel, module_exit() has no effect.
+ * There can only be one per module.
+ */
+#define module_exit(x)	__exitcall(x);
+
+#else /* MODULE */
+
+/*
+ * In most cases loadable modules do not need custom
+ * initcall levels. There are still some valid cases where
+ * a driver may be needed early if built in, and does not
+ * matter when built as a loadable module. Like bus
+ * snooping debug drivers.
+ */
+#define early_initcall(fn)		module_init(fn)
+#define core_initcall(fn)		module_init(fn)
+#define core_initcall_sync(fn)		module_init(fn)
+#define postcore_initcall(fn)		module_init(fn)
+#define postcore_initcall_sync(fn)	module_init(fn)
+#define arch_initcall(fn)		module_init(fn)
+#define subsys_initcall(fn)		module_init(fn)
+#define subsys_initcall_sync(fn)	module_init(fn)
+#define fs_initcall(fn)			module_init(fn)
+#define fs_initcall_sync(fn)		module_init(fn)
+#define rootfs_initcall(fn)		module_init(fn)
+#define device_initcall(fn)		module_init(fn)
+#define device_initcall_sync(fn)	module_init(fn)
+#define late_initcall(fn)		module_init(fn)
+#define late_initcall_sync(fn)		module_init(fn)
+
+#define console_initcall(fn)		module_init(fn)
+#define security_initcall(fn)		module_init(fn)
+
+/* Each module must use one module_init(). */
+#define module_init(initfn)					\
+	static inline initcall_t __inittest(void)		\
+	{ return initfn; }					\
+	int init_module(void) __attribute__((alias(#initfn)));
+
+/* This is only required if you want to be unloadable. */
+#define module_exit(exitfn)					\
+	static inline exitcall_t __exittest(void)		\
+	{ return exitfn; }					\
+	void cleanup_module(void) __attribute__((alias(#exitfn)));
+
+#endif
+
+/* This means "can be init if no module support, otherwise module load
+   may call it." */
+#ifdef CONFIG_MODULES
+#define __init_or_module
+#define __initdata_or_module
+#define __initconst_or_module
+#define __INIT_OR_MODULE	.text
+#define __INITDATA_OR_MODULE	.data
+#define __INITRODATA_OR_MODULE	.section ".rodata","a",%progbits
+#else
+#define __init_or_module __init
+#define __initdata_or_module __initdata
+#define __initconst_or_module __initconst
+#define __INIT_OR_MODULE __INIT
+#define __INITDATA_OR_MODULE __INITDATA
+#define __INITRODATA_OR_MODULE __INITRODATA
+#endif /*CONFIG_MODULES*/
+
 /* Archs provide a method of finding the correct exception table. */
 struct exception_table_entry;
 
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index f25e2bd..272f429 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -178,17 +178,17 @@
 /* Chip may not exist, so silence any errors in scan */
 #define NAND_SCAN_SILENT_NODEV	0x00040000
 /*
- * This option could be defined by controller drivers to protect against
- * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers
- */
-#define NAND_USE_BOUNCE_BUFFER	0x00080000
-/*
  * Autodetect nand buswidth with readid/onfi.
  * This suppose the driver will configure the hardware in 8 bits mode
  * when calling nand_scan_ident, and update its configuration
  * before calling nand_scan_tail.
  */
 #define NAND_BUSWIDTH_AUTO      0x00080000
+/*
+ * This option could be defined by controller drivers to protect against
+ * kmap'ed, vmalloc'ed highmem buffers being passed from upper layers
+ */
+#define NAND_USE_BOUNCE_BUFFER	0x00100000
 
 /* Options set by nand scan */
 /* Nand scan has allocated controller struct */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index f91b5ad..874b772 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -292,9 +292,12 @@
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	spin_lock(&inode->i_lock);
-	nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS;
+	nfsi->cache_validity |= NFS_INO_INVALID_ATTR |
+				NFS_INO_REVAL_PAGECACHE |
+				NFS_INO_INVALID_ACCESS |
+				NFS_INO_INVALID_ACL;
 	if (S_ISDIR(inode->i_mode))
-		nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_DATA;
+		nfsi->cache_validity |= NFS_INO_INVALID_DATA;
 	spin_unlock(&inode->i_lock);
 }
 
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index a2ea149..20bc8e5 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -220,7 +220,7 @@
 #define NFS_CAP_SYMLINKS	(1U << 2)
 #define NFS_CAP_ACLS		(1U << 3)
 #define NFS_CAP_ATOMIC_OPEN	(1U << 4)
-#define NFS_CAP_CHANGE_ATTR	(1U << 5)
+/* #define NFS_CAP_CHANGE_ATTR	(1U << 5) */
 #define NFS_CAP_FILEID		(1U << 6)
 #define NFS_CAP_MODE		(1U << 7)
 #define NFS_CAP_NLINK		(1U << 8)
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 4c50854..cc7dd687 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -59,7 +59,7 @@
 #else /* CONFIG_OF */
 
 static inline int of_driver_match_device(struct device *dev,
-					 struct device_driver *drv)
+					 const struct device_driver *drv)
 {
 	return 0;
 }
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index f34e040..41c9384 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -631,15 +631,19 @@
 	 1 << PG_private | 1 << PG_private_2 | \
 	 1 << PG_writeback | 1 << PG_reserved | \
 	 1 << PG_slab	 | 1 << PG_swapcache | 1 << PG_active | \
-	 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \
+	 1 << PG_unevictable | __PG_MLOCKED | \
 	 __PG_COMPOUND_LOCK)
 
 /*
  * Flags checked when a page is prepped for return by the page allocator.
- * Pages being prepped should not have any flags set.  It they are set,
+ * Pages being prepped should not have these flags set.  It they are set,
  * there has been a kernel bug or struct page corruption.
+ *
+ * __PG_HWPOISON is exceptional because it needs to be kept beyond page's
+ * alloc-free cycle to prevent from reusing the page.
  */
-#define PAGE_FLAGS_CHECK_AT_PREP	((1 << NR_PAGEFLAGS) - 1)
+#define PAGE_FLAGS_CHECK_AT_PREP	\
+	(((1 << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON)
 
 #define PAGE_FLAGS_PRIVATE				\
 	(1 << PG_private | 1 << PG_private_2)
diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h
index b48c347..cacaabe 100644
--- a/include/linux/page_owner.h
+++ b/include/linux/page_owner.h
@@ -8,6 +8,7 @@
 extern void __reset_page_owner(struct page *page, unsigned int order);
 extern void __set_page_owner(struct page *page,
 			unsigned int order, gfp_t gfp_mask);
+extern gfp_t __get_page_owner_gfp(struct page *page);
 
 static inline void reset_page_owner(struct page *page, unsigned int order)
 {
@@ -25,6 +26,14 @@
 
 	__set_page_owner(page, order, gfp_mask);
 }
+
+static inline gfp_t get_page_owner_gfp(struct page *page)
+{
+	if (likely(!page_owner_inited))
+		return 0;
+
+	return __get_page_owner_gfp(page);
+}
 #else
 static inline void reset_page_owner(struct page *page, unsigned int order)
 {
@@ -33,6 +42,10 @@
 			unsigned int order, gfp_t gfp_mask)
 {
 }
+static inline gfp_t get_page_owner_gfp(struct page *page)
+{
+	return 0;
+}
 
 #endif /* CONFIG_PAGE_OWNER */
 #endif /* __LINUX_PAGE_OWNER_H */
diff --git a/include/linux/pata_arasan_cf_data.h b/include/linux/pata_arasan_cf_data.h
index 3cc21c9..9fade5d 100644
--- a/include/linux/pata_arasan_cf_data.h
+++ b/include/linux/pata_arasan_cf_data.h
@@ -4,7 +4,7 @@
  * Arasan Compact Flash host controller platform data header file
  *
  * Copyright (C) 2011 ST Microelectronics
- * Viresh Kumar <viresh.linux@gmail.com>
+ * Viresh Kumar <vireshk@kernel.org>
  *
  * This file is licensed under the terms of the GNU General Public
  * License version 2. This program is licensed "as is" without any
diff --git a/include/linux/platform_data/macb.h b/include/linux/platform_data/macb.h
index 044a124..21b15f6 100644
--- a/include/linux/platform_data/macb.h
+++ b/include/linux/platform_data/macb.h
@@ -8,11 +8,19 @@
 #ifndef __MACB_PDATA_H__
 #define __MACB_PDATA_H__
 
+/**
+ * struct macb_platform_data - platform data for MACB Ethernet
+ * @phy_mask:		phy mask passed when register the MDIO bus
+ *			within the driver
+ * @phy_irq_pin:	PHY IRQ
+ * @is_rmii:		using RMII interface?
+ * @rev_eth_addr:	reverse Ethernet address byte order
+ */
 struct macb_platform_data {
 	u32		phy_mask;
-	int		phy_irq_pin;	/* PHY IRQ */
-	u8		is_rmii;	/* using RMII interface? */
-	u8		rev_eth_addr;	/* reverse Ethernet address byte order */
+	int		phy_irq_pin;
+	u8		is_rmii;
+	u8		rev_eth_addr;
 };
 
 #endif /* __MACB_PDATA_H__ */
diff --git a/include/linux/platform_data/mmc-esdhc-imx.h b/include/linux/platform_data/mmc-esdhc-imx.h
index 75f70f6..e1571ef 100644
--- a/include/linux/platform_data/mmc-esdhc-imx.h
+++ b/include/linux/platform_data/mmc-esdhc-imx.h
@@ -43,7 +43,6 @@
 	enum wp_types wp_type;
 	enum cd_types cd_type;
 	int max_bus_width;
-	unsigned int f_max;
 	bool support_vsel;
 	unsigned int delay_line;
 };
diff --git a/include/linux/platform_data/spi-davinci.h b/include/linux/platform_data/spi-davinci.h
index 8dc2fa47..f4edcb0 100644
--- a/include/linux/platform_data/spi-davinci.h
+++ b/include/linux/platform_data/spi-davinci.h
@@ -49,6 +49,7 @@
 	u8			num_chipselect;
 	u8			intr_line;
 	u8			*chip_sel;
+	u8			prescaler_limit;
 	bool			cshold_bug;
 	enum dma_event_q	dma_event_q;
 };
diff --git a/include/linux/platform_data/spi-mt65xx.h b/include/linux/platform_data/spi-mt65xx.h
new file mode 100644
index 0000000..54b0448
--- /dev/null
+++ b/include/linux/platform_data/spi-mt65xx.h
@@ -0,0 +1,20 @@
+/*
+ *  MTK SPI bus driver definitions
+ *
+ * Copyright (c) 2015 MediaTek Inc.
+ * Author: Leilk Liu <leilk.liu@mediatek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ____LINUX_PLATFORM_DATA_SPI_MTK_H
+#define ____LINUX_PLATFORM_DATA_SPI_MTK_H
+
+/* Board specific platform_data */
+struct mtk_chip_config {
+	u32 tx_mlsb;
+	u32 rx_mlsb;
+};
+#endif
diff --git a/include/linux/printk.h b/include/linux/printk.h
index 58b1fec..a6298b2 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -122,7 +122,7 @@
 void early_printk(const char *s, ...) { }
 #endif
 
-typedef int(*printk_func_t)(const char *fmt, va_list args);
+typedef __printf(1, 0) int (*printk_func_t)(const char *fmt, va_list args);
 
 #ifdef CONFIG_PRINTK
 asmlinkage __printf(5, 0)
@@ -166,7 +166,7 @@
 u32 log_buf_len_get(void);
 void log_buf_kexec_setup(void);
 void __init setup_log_buf(int early);
-void dump_stack_set_arch_desc(const char *fmt, ...);
+__printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...);
 void dump_stack_print_info(const char *log_lvl);
 void show_regs_print_info(const char *log_lvl);
 #else
@@ -217,7 +217,7 @@
 {
 }
 
-static inline void dump_stack_set_arch_desc(const char *fmt, ...)
+static inline __printf(1, 2) void dump_stack_set_arch_desc(const char *fmt, ...)
 {
 }
 
diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index 0485bab..9227377 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -197,6 +197,7 @@
 	QUARK_X1000_SSP,
 	LPSS_LPT_SSP, /* Keep LPSS types sorted with lpss_platforms[] */
 	LPSS_BYT_SSP,
+	LPSS_SPT_SSP,
 };
 
 struct ssp_device {
diff --git a/include/linux/rtc/sirfsoc_rtciobrg.h b/include/linux/rtc/sirfsoc_rtciobrg.h
index 2c92e1c..aefd997 100644
--- a/include/linux/rtc/sirfsoc_rtciobrg.h
+++ b/include/linux/rtc/sirfsoc_rtciobrg.h
@@ -9,10 +9,14 @@
 #ifndef _SIRFSOC_RTC_IOBRG_H_
 #define _SIRFSOC_RTC_IOBRG_H_
 
+struct regmap_config;
+
 extern void sirfsoc_rtc_iobrg_besyncing(void);
 
 extern u32 sirfsoc_rtc_iobrg_readl(u32 addr);
 
 extern void sirfsoc_rtc_iobrg_writel(u32 val, u32 addr);
+struct regmap *devm_regmap_init_iobg(struct device *dev,
+				    const struct regmap_config *config);
 
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ae21f15..04b5ada 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1522,8 +1522,6 @@
 /* hung task detection */
 	unsigned long last_switch_count;
 #endif
-/* CPU-specific state of this task */
-	struct thread_struct thread;
 /* filesystem information */
 	struct fs_struct *fs;
 /* open file information */
@@ -1778,8 +1776,22 @@
 	unsigned long	task_state_change;
 #endif
 	int pagefault_disabled;
+/* CPU-specific state of this task */
+	struct thread_struct thread;
+/*
+ * WARNING: on x86, 'thread_struct' contains a variable-sized
+ * structure.  It *MUST* be at the end of 'task_struct'.
+ *
+ * Do not put anything below here!
+ */
 };
 
+#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
+extern int arch_task_struct_size __read_mostly;
+#else
+# define arch_task_struct_size (sizeof(struct task_struct))
+#endif
+
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
 #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
 
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index d6cdd6e..9b88536 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1602,20 +1602,16 @@
 	skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
 	/*
-	 * Propagate page->pfmemalloc to the skb if we can. The problem is
-	 * that not all callers have unique ownership of the page. If
-	 * pfmemalloc is set, we check the mapping as a mapping implies
-	 * page->index is set (index and pfmemalloc share space).
-	 * If it's a valid mapping, we cannot use page->pfmemalloc but we
-	 * do not lose pfmemalloc information as the pages would not be
-	 * allocated using __GFP_MEMALLOC.
+	 * Propagate page pfmemalloc to the skb if we can. The problem is
+	 * that not all callers have unique ownership of the page but rely
+	 * on page_is_pfmemalloc doing the right thing(tm).
 	 */
 	frag->page.p		  = page;
 	frag->page_offset	  = off;
 	skb_frag_size_set(frag, size);
 
 	page = compound_head(page);
-	if (page->pfmemalloc && !page->mapping)
+	if (page_is_pfmemalloc(page))
 		skb->pfmemalloc	= true;
 }
 
@@ -2263,7 +2259,7 @@
 static inline void skb_propagate_pfmemalloc(struct page *page,
 					     struct sk_buff *skb)
 {
-	if (page && page->pfmemalloc)
+	if (page_is_pfmemalloc(page))
 		skb->pfmemalloc = true;
 }
 
@@ -2884,11 +2880,11 @@
  *
  * PHY drivers may accept clones of transmitted packets for
  * timestamping via their phy_driver.txtstamp method. These drivers
- * must call this function to return the skb back to the stack, with
- * or without a timestamp.
+ * must call this function to return the skb back to the stack with a
+ * timestamp.
  *
  * @skb: clone of the the original outgoing packet
- * @hwtstamps: hardware time stamps, may be NULL if not available
+ * @hwtstamps: hardware time stamps
  *
  */
 void skb_complete_tx_timestamp(struct sk_buff *skb,
diff --git a/include/linux/tick.h b/include/linux/tick.h
index 3741ba1..edbfc9a 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -67,10 +67,13 @@
 static inline void tick_broadcast_control(enum tick_broadcast_mode mode) { }
 #endif /* BROADCAST */
 
-#if defined(CONFIG_GENERIC_CLOCKEVENTS_BROADCAST) && defined(CONFIG_TICK_ONESHOT)
+#ifdef CONFIG_GENERIC_CLOCKEVENTS
 extern int tick_broadcast_oneshot_control(enum tick_broadcast_state state);
 #else
-static inline int tick_broadcast_oneshot_control(enum tick_broadcast_state state) { return 0; }
+static inline int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+{
+	return 0;
+}
 #endif
 
 static inline void tick_broadcast_enable(void)
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 3aa72e6..6e191e4 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -145,7 +145,6 @@
 }
 #endif
 
-#define do_posix_clock_monotonic_gettime(ts) ktime_get_ts(ts)
 #define ktime_get_real_ts64(ts)	getnstimeofday64(ts)
 
 /*
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index 7c9b484..1f6526c 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -80,6 +80,9 @@
 #define CDC_NCM_TIMER_INTERVAL_MIN		5UL
 #define CDC_NCM_TIMER_INTERVAL_MAX		(U32_MAX / NSEC_PER_USEC)
 
+/* Driver flags */
+#define CDC_NCM_FLAG_NDP_TO_END	0x02		/* NDP is placed at end of frame */
+
 #define cdc_ncm_comm_intf_is_mbim(x)  ((x)->desc.bInterfaceSubClass == USB_CDC_SUBCLASS_MBIM && \
 				       (x)->desc.bInterfaceProtocol == USB_CDC_PROTO_NONE)
 #define cdc_ncm_data_intf_is_mbim(x)  ((x)->desc.bInterfaceProtocol == USB_CDC_MBIM_PROTO_NTB)
@@ -103,9 +106,11 @@
 
 	spinlock_t mtx;
 	atomic_t stop;
+	int drvflags;
 
 	u32 timer_interval;
 	u32 max_ndp_size;
+	struct usb_cdc_ncm_ndp16 *delayed_ndp16;
 
 	u32 tx_timer_pending;
 	u32 tx_curr_frame_num;
@@ -133,7 +138,7 @@
 };
 
 u8 cdc_ncm_select_altsetting(struct usb_interface *intf);
-int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting);
+int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_altsetting, int drvflags);
 void cdc_ncm_unbind(struct usbnet *dev, struct usb_interface *intf);
 struct sk_buff *cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign);
 int cdc_ncm_rx_verify_nth16(struct cdc_ncm_ctx *ctx, struct sk_buff *skb_in);
diff --git a/include/media/rc-core.h b/include/media/rc-core.h
index 45534da5..644bdc6 100644
--- a/include/media/rc-core.h
+++ b/include/media/rc-core.h
@@ -74,8 +74,6 @@
  * @input_dev: the input child device used to communicate events to userspace
  * @driver_type: specifies if protocol decoding is done in hardware or software
  * @idle: used to keep track of RX state
- * @encode_wakeup: wakeup filtering uses IR encode API, therefore the allowed
- *	wakeup protocols is the set of all raw encoders
  * @allowed_protocols: bitmask with the supported RC_BIT_* protocols
  * @enabled_protocols: bitmask with the enabled RC_BIT_* protocols
  * @allowed_wakeup_protocols: bitmask with the supported RC_BIT_* wakeup protocols
@@ -136,7 +134,6 @@
 	struct input_dev		*input_dev;
 	enum rc_driver_type		driver_type;
 	bool				idle;
-	bool				encode_wakeup;
 	u64				allowed_protocols;
 	u64				enabled_protocols;
 	u64				allowed_wakeup_protocols;
@@ -246,7 +243,6 @@
 #define US_TO_NS(usec)		((usec) * 1000)
 #define MS_TO_US(msec)		((msec) * 1000)
 #define MS_TO_NS(msec)		((msec) * 1000 * 1000)
-#define NS_TO_US(nsec)		DIV_ROUND_UP(nsec, 1000L)
 
 void ir_raw_event_handle(struct rc_dev *dev);
 int ir_raw_event_store(struct rc_dev *dev, struct ir_raw_event *ev);
@@ -254,9 +250,6 @@
 int ir_raw_event_store_with_filter(struct rc_dev *dev,
 				struct ir_raw_event *ev);
 void ir_raw_event_set_idle(struct rc_dev *dev, bool idle);
-int ir_raw_encode_scancode(u64 protocols,
-			   const struct rc_scancode_filter *scancode,
-			   struct ir_raw_event *events, unsigned int max);
 
 static inline void ir_raw_event_reset(struct rc_dev *dev)
 {
diff --git a/include/media/videobuf2-core.h b/include/media/videobuf2-core.h
index 22a44c2..c192e1b 100644
--- a/include/media/videobuf2-core.h
+++ b/include/media/videobuf2-core.h
@@ -139,6 +139,7 @@
  * @VB2_BUF_STATE_PREPARING:	buffer is being prepared in videobuf
  * @VB2_BUF_STATE_PREPARED:	buffer prepared in videobuf and by the driver
  * @VB2_BUF_STATE_QUEUED:	buffer queued in videobuf, but not in driver
+ * @VB2_BUF_STATE_REQUEUEING:	re-queue a buffer to the driver
  * @VB2_BUF_STATE_ACTIVE:	buffer queued in driver and possibly used
  *				in a hardware operation
  * @VB2_BUF_STATE_DONE:		buffer returned from driver to videobuf, but
@@ -152,6 +153,7 @@
 	VB2_BUF_STATE_PREPARING,
 	VB2_BUF_STATE_PREPARED,
 	VB2_BUF_STATE_QUEUED,
+	VB2_BUF_STATE_REQUEUEING,
 	VB2_BUF_STATE_ACTIVE,
 	VB2_BUF_STATE_DONE,
 	VB2_BUF_STATE_ERROR,
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 3ee4c92..931738b 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -99,7 +99,6 @@
 
 int tcf_hash_search(struct tc_action *a, u32 index);
 void tcf_hash_destroy(struct tc_action *a);
-int tcf_hash_release(struct tc_action *a, int bind);
 u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo);
 int tcf_hash_check(u32 index, struct tc_action *a, int bind);
 int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
@@ -107,6 +106,13 @@
 void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est);
 void tcf_hash_insert(struct tc_action *a);
 
+int __tcf_hash_release(struct tc_action *a, bool bind, bool strict);
+
+static inline int tcf_hash_release(struct tc_action *a, bool bind)
+{
+	return __tcf_hash_release(a, bind, false);
+}
+
 int tcf_register_action(struct tc_action_ops *a, unsigned int mask);
 int tcf_unregister_action(struct tc_action_ops *a);
 int tcf_action_destroy(struct list_head *actions, int bind);
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index a741678..883fe1e 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -4868,6 +4868,23 @@
 			     struct cfg80211_chan_def *chandef,
 			     enum nl80211_iftype iftype);
 
+/**
+ * cfg80211_reg_can_beacon_relax - check if beaconing is allowed with relaxation
+ * @wiphy: the wiphy
+ * @chandef: the channel definition
+ * @iftype: interface type
+ *
+ * Return: %true if there is no secondary channel or the secondary channel(s)
+ * can be used for beaconing (i.e. is not a radar channel etc.). This version
+ * also checks if IR-relaxation conditions apply, to allow beaconing under
+ * more permissive conditions.
+ *
+ * Requires the RTNL to be held.
+ */
+bool cfg80211_reg_can_beacon_relax(struct wiphy *wiphy,
+				   struct cfg80211_chan_def *chandef,
+				   enum nl80211_iftype iftype);
+
 /*
  * cfg80211_ch_switch_notify - update wdev channel and notify userspace
  * @dev: the device which switched channels
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index e1300b3..53eead2 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -21,13 +21,11 @@
  * @INET_FRAG_FIRST_IN: first fragment has arrived
  * @INET_FRAG_LAST_IN: final fragment has arrived
  * @INET_FRAG_COMPLETE: frag queue has been processed and is due for destruction
- * @INET_FRAG_EVICTED: frag queue is being evicted
  */
 enum {
 	INET_FRAG_FIRST_IN	= BIT(0),
 	INET_FRAG_LAST_IN	= BIT(1),
 	INET_FRAG_COMPLETE	= BIT(2),
-	INET_FRAG_EVICTED	= BIT(3)
 };
 
 /**
@@ -45,6 +43,7 @@
  * @flags: fragment queue flags
  * @max_size: maximum received fragment size
  * @net: namespace that this frag belongs to
+ * @list_evictor: list of queues to forcefully evict (e.g. due to low memory)
  */
 struct inet_frag_queue {
 	spinlock_t		lock;
@@ -59,6 +58,7 @@
 	__u8			flags;
 	u16			max_size;
 	struct netns_frags	*net;
+	struct hlist_node	list_evictor;
 };
 
 #define INETFRAGS_HASHSZ	1024
@@ -125,6 +125,11 @@
 		inet_frag_destroy(q, f);
 }
 
+static inline bool inet_frag_evicting(struct inet_frag_queue *q)
+{
+	return !hlist_unhashed(&q->list_evictor);
+}
+
 /* Memory Tracking Functions. */
 
 /* The default percpu_counter batch size is not big enough to scale to
@@ -139,14 +144,14 @@
 	return percpu_counter_read(&nf->mem);
 }
 
-static inline void sub_frag_mem_limit(struct inet_frag_queue *q, int i)
+static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	__percpu_counter_add(&q->net->mem, -i, frag_percpu_counter_batch);
+	__percpu_counter_add(&nf->mem, -i, frag_percpu_counter_batch);
 }
 
-static inline void add_frag_mem_limit(struct inet_frag_queue *q, int i)
+static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	__percpu_counter_add(&q->net->mem, i, frag_percpu_counter_batch);
+	__percpu_counter_add(&nf->mem, i, frag_percpu_counter_batch);
 }
 
 static inline void init_frag_mem_limit(struct netns_frags *nf)
diff --git a/include/net/ip.h b/include/net/ip.h
index 0750a18..d5fe9f2 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -161,6 +161,7 @@
 }
 
 /* datagram.c */
+int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 
 void ip4_datagram_release_cb(struct sock *sk);
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 49c142b..5fa643b 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -183,7 +183,6 @@
 struct fib_table {
 	struct hlist_node	tb_hlist;
 	u32			tb_id;
-	int			tb_default;
 	int			tb_num_default;
 	struct rcu_head		rcu;
 	unsigned long 		*tb_data;
@@ -290,7 +289,7 @@
 int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 			u8 tos, int oif, struct net_device *dev,
 			struct in_device *idev, u32 *itag);
-void fib_select_default(struct fib_result *res);
+void fib_select_default(const struct flowi4 *flp, struct fib_result *res);
 #ifdef CONFIG_IP_ROUTE_CLASSID
 static inline int fib_num_tclassid_users(struct net *net)
 {
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 095433b..37cd391 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -291,7 +291,7 @@
 extern unsigned int nf_conntrack_hash_rnd;
 void init_nf_conntrack_hash_rnd(void);
 
-void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl);
+struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags);
 
 #define NF_CT_STAT_INC(net, count)	  __this_cpu_inc((net)->ct.stat->count)
 #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count)
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 29d6a94..723b61c 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -68,7 +68,6 @@
 	spinlock_t		lock;
 	struct hlist_nulls_head unconfirmed;
 	struct hlist_nulls_head dying;
-	struct hlist_nulls_head tmpl;
 };
 
 struct netns_ct {
diff --git a/include/net/sock.h b/include/net/sock.h
index 05a8c1a..f21f070 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -902,7 +902,7 @@
 void sk_set_memalloc(struct sock *sk);
 void sk_clear_memalloc(struct sock *sk);
 
-int sk_wait_data(struct sock *sk, long *timeo);
+int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb);
 
 struct request_sock_ops;
 struct timewait_sock_ops;
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 986fddb..b0f898e 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1745,6 +1745,7 @@
 	char			     node_desc[64];
 	__be64			     node_guid;
 	u32			     local_dma_lkey;
+	u16                          is_switch:1;
 	u8                           node_type;
 	u8                           phys_port_cnt;
 
@@ -1824,6 +1825,20 @@
 					       u8 port_num);
 
 /**
+ * rdma_cap_ib_switch - Check if the device is IB switch
+ * @device: Device to check
+ *
+ * Device driver is responsible for setting is_switch bit on
+ * in ib_device structure at init time.
+ *
+ * Return: true if the device is IB switch.
+ */
+static inline bool rdma_cap_ib_switch(const struct ib_device *device)
+{
+	return device->is_switch;
+}
+
+/**
  * rdma_start_port - Return the first valid port number for the device
  * specified
  *
@@ -1833,7 +1848,7 @@
  */
 static inline u8 rdma_start_port(const struct ib_device *device)
 {
-	return (device->node_type == RDMA_NODE_IB_SWITCH) ? 0 : 1;
+	return rdma_cap_ib_switch(device) ? 0 : 1;
 }
 
 /**
@@ -1846,8 +1861,7 @@
  */
 static inline u8 rdma_end_port(const struct ib_device *device)
 {
-	return (device->node_type == RDMA_NODE_IB_SWITCH) ?
-		0 : device->phys_port_cnt;
+	return rdma_cap_ib_switch(device) ? 0 : device->phys_port_cnt;
 }
 
 static inline bool rdma_protocol_ib(const struct ib_device *device, u8 port_num)
diff --git a/include/scsi/scsi_eh.h b/include/scsi/scsi_eh.h
index 4942710..8d1d7fa 100644
--- a/include/scsi/scsi_eh.h
+++ b/include/scsi/scsi_eh.h
@@ -28,7 +28,6 @@
 				   u64 * info_out);
 
 extern void scsi_build_sense_buffer(int desc, u8 *buf, u8 key, u8 asc, u8 ascq);
-extern void scsi_set_sense_information(u8 *buf, u64 info);
 
 extern int scsi_ioctl_reset(struct scsi_device *, int __user *);
 
diff --git a/include/scsi/scsi_transport_srp.h b/include/scsi/scsi_transport_srp.h
index cdb05dd1..d40d3ef 100644
--- a/include/scsi/scsi_transport_srp.h
+++ b/include/scsi/scsi_transport_srp.h
@@ -119,6 +119,7 @@
 extern void srp_rport_del(struct srp_rport *);
 extern int srp_tmo_valid(int reconnect_delay, int fast_io_fail_tmo,
 			 int dev_loss_tmo);
+int srp_parse_tmo(int *tmo, const char *buf);
 extern int srp_reconnect_rport(struct srp_rport *rport);
 extern void srp_start_tl_fail_timers(struct srp_rport *rport);
 extern void srp_remove_host(struct Scsi_Host *);
diff --git a/include/sound/soc-topology.h b/include/sound/soc-topology.h
index 865a141..427bc41 100644
--- a/include/sound/soc-topology.h
+++ b/include/sound/soc-topology.h
@@ -141,6 +141,8 @@
 	int io_ops_count;
 };
 
+#ifdef CONFIG_SND_SOC_TOPOLOGY
+
 /* gets a pointer to data from the firmware block header */
 static inline const void *snd_soc_tplg_get_data(struct snd_soc_tplg_hdr *hdr)
 {
@@ -165,4 +167,14 @@
 	const struct snd_soc_tplg_widget_events *events, int num_events,
 	u16 event_type);
 
+#else
+
+static inline int snd_soc_tplg_component_remove(struct snd_soc_component *comp,
+						u32 index)
+{
+	return 0;
+}
+
+#endif
+
 #endif
diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h
index 34117b8..0aedbb2 100644
--- a/include/target/iscsi/iscsi_target_core.h
+++ b/include/target/iscsi/iscsi_target_core.h
@@ -595,6 +595,7 @@
 	int			bitmap_id;
 	int			rx_thread_active;
 	struct task_struct	*rx_thread;
+	struct completion	rx_login_comp;
 	int			tx_thread_active;
 	struct task_struct	*tx_thread;
 	/* list_head for session connection list */
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index b6fce90..fbdd118 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -32,7 +32,7 @@
 #ifndef __AMDGPU_DRM_H__
 #define __AMDGPU_DRM_H__
 
-#include <drm/drm.h>
+#include "drm.h"
 
 #define DRM_AMDGPU_GEM_CREATE		0x00
 #define DRM_AMDGPU_GEM_MMAP		0x01
@@ -614,6 +614,8 @@
 	uint32_t vram_type;
 	/** video memory bit width*/
 	uint32_t vram_bit_width;
+	/* vce harvesting instance */
+	uint32_t vce_harvest_config;
 };
 
 struct drm_amdgpu_info_hw_ip {
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 6e1a2ed..db809b7 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1070,6 +1070,14 @@
 	__u64 offset;
 	__u64 val; /* Return value */
 };
+/* Known registers:
+ *
+ * Render engine timestamp - 0x2358 + 64bit - gen7+
+ * - Note this register returns an invalid value if using the default
+ *   single instruction 8byte read, in order to workaround that use
+ *   offset (0x2538 | 1) instead.
+ *
+ */
 
 struct drm_i915_reset_stats {
 	__u32 ctx_id;
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 1ef7666..01aa2a8 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -33,7 +33,7 @@
 #ifndef __RADEON_DRM_H__
 #define __RADEON_DRM_H__
 
-#include <drm/drm.h>
+#include "drm.h"
 
 /* WARNING: If you change any of these defines, make sure to change the
  * defines in the X server file (radeon_sarea.h)
diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h
index 669a1f0..23cbd34 100644
--- a/include/uapi/linux/netconf.h
+++ b/include/uapi/linux/netconf.h
@@ -15,6 +15,7 @@
 	NETCONFA_RP_FILTER,
 	NETCONFA_MC_FORWARDING,
 	NETCONFA_PROXY_NEIGH,
+	NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 	__NETCONFA_MAX
 };
 #define NETCONFA_MAX	(__NETCONFA_MAX - 1)
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index efe3443..413417f 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -319,6 +319,7 @@
 #define PCI_MSIX_PBA		8	/* Pending Bit Array offset */
 #define  PCI_MSIX_PBA_BIR	0x00000007 /* BAR index */
 #define  PCI_MSIX_PBA_OFFSET	0xfffffff8 /* Offset into specified BAR */
+#define PCI_MSIX_FLAGS_BIRMASK	PCI_MSIX_PBA_BIR /* deprecated */
 #define PCI_CAP_MSIX_SIZEOF	12	/* size of MSIX registers */
 
 /* MSI-X Table entry format */
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 7bbee79..ec32293 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -34,6 +34,7 @@
 /* The feature bitmap for virtio net */
 #define VIRTIO_NET_F_CSUM	0	/* Host handles pkts w/ partial csum */
 #define VIRTIO_NET_F_GUEST_CSUM	1	/* Guest handles pkts w/ partial csum */
+#define VIRTIO_NET_F_CTRL_GUEST_OFFLOADS 2 /* Dynamic offload configuration. */
 #define VIRTIO_NET_F_MAC	5	/* Host has given MAC address. */
 #define VIRTIO_NET_F_GUEST_TSO4	7	/* Guest can handle TSOv4 in. */
 #define VIRTIO_NET_F_GUEST_TSO6	8	/* Guest can handle TSOv6 in. */
@@ -226,4 +227,19 @@
  #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN        1
  #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX        0x8000
 
+/*
+ * Control network offloads
+ *
+ * Reconfigures the network offloads that Guest can handle.
+ *
+ * Available with the VIRTIO_NET_F_CTRL_GUEST_OFFLOADS feature bit.
+ *
+ * Command data format matches the feature bit mask exactly.
+ *
+ * See VIRTIO_NET_F_GUEST_* for the list of offloads
+ * that can be enabled/disabled.
+ */
+#define VIRTIO_NET_CTRL_GUEST_OFFLOADS   5
+#define VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET        0
+
 #endif /* _LINUX_VIRTIO_NET_H */
diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h
index 7530146..90007a1 100644
--- a/include/uapi/linux/virtio_pci.h
+++ b/include/uapi/linux/virtio_pci.h
@@ -157,6 +157,12 @@
 	__le32 queue_used_hi;		/* read-write */
 };
 
+/* Fields in VIRTIO_PCI_CAP_PCI_CFG: */
+struct virtio_pci_cfg_cap {
+	struct virtio_pci_cap cap;
+	__u8 pci_cfg_data[4]; /* Data for BAR access. */
+};
+
 /* Macro versions of offsets for the Old Timers! */
 #define VIRTIO_PCI_CAP_VNDR		0
 #define VIRTIO_PCI_CAP_NEXT		1
diff --git a/include/uapi/linux/virtio_ring.h b/include/uapi/linux/virtio_ring.h
index 915980a..c072959 100644
--- a/include/uapi/linux/virtio_ring.h
+++ b/include/uapi/linux/virtio_ring.h
@@ -31,6 +31,9 @@
  * SUCH DAMAGE.
  *
  * Copyright Rusty Russell IBM Corporation 2007. */
+#ifndef __KERNEL__
+#include <stdint.h>
+#endif
 #include <linux/types.h>
 #include <linux/virtio_types.h>
 
@@ -143,7 +146,7 @@
 	vr->num = num;
 	vr->desc = p;
 	vr->avail = p + num*sizeof(struct vring_desc);
-	vr->used = (void *)(((unsigned long)&vr->avail->ring[num] + sizeof(__virtio16)
+	vr->used = (void *)(((uintptr_t)&vr->avail->ring[num] + sizeof(__virtio16)
 		+ align-1) & ~(align - 1));
 }
 
diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h
index 1221520..247c50b 100644
--- a/include/uapi/sound/asoc.h
+++ b/include/uapi/sound/asoc.h
@@ -18,6 +18,12 @@
 #include <linux/types.h>
 #include <sound/asound.h>
 
+#ifndef __KERNEL__
+#error This API is an early revision and not enabled in the current
+#error kernel release, it will be enabled in a future kernel version
+#error with incompatible changes to what is here.
+#endif
+
 /*
  * Maximum number of channels topology kcontrol can represent.
  */
@@ -77,7 +83,7 @@
 #define SND_SOC_TPLG_NUM_TEXTS		16
 
 /* ABI version */
-#define SND_SOC_TPLG_ABI_VERSION	0x2
+#define SND_SOC_TPLG_ABI_VERSION	0x3
 
 /* Max size of TLV data */
 #define SND_SOC_TPLG_TLV_SIZE		32
@@ -97,7 +103,8 @@
 #define SND_SOC_TPLG_TYPE_PCM		7
 #define SND_SOC_TPLG_TYPE_MANIFEST	8
 #define SND_SOC_TPLG_TYPE_CODEC_LINK	9
-#define SND_SOC_TPLG_TYPE_MAX	SND_SOC_TPLG_TYPE_CODEC_LINK
+#define SND_SOC_TPLG_TYPE_PDATA		10
+#define SND_SOC_TPLG_TYPE_MAX	SND_SOC_TPLG_TYPE_PDATA
 
 /* vendor block IDs - please add new vendor types to end */
 #define SND_SOC_TPLG_TYPE_VENDOR_FW	1000
@@ -110,7 +117,7 @@
 
 /*
  * Block Header.
- * This header preceeds all object and object arrays below.
+ * This header precedes all object and object arrays below.
  */
 struct snd_soc_tplg_hdr {
 	__le32 magic;		/* magic number */
@@ -137,11 +144,19 @@
 /*
  * Kcontrol TLV data.
  */
+struct snd_soc_tplg_tlv_dbscale {
+	__le32 min;
+	__le32 step;
+	__le32 mute;
+} __attribute__((packed));
+
 struct snd_soc_tplg_ctl_tlv {
-	__le32 size;	/* in bytes aligned to 4 */
-	__le32 numid;	/* control element numeric identification */
-	__le32 count;	/* number of elem in data array */
-	__le32 data[SND_SOC_TPLG_TLV_SIZE];
+	__le32 size;	/* in bytes of this structure */
+	__le32 type;	/* SNDRV_CTL_TLVT_*, type of TLV */
+	union {
+		__le32 data[SND_SOC_TPLG_TLV_SIZE];
+		struct snd_soc_tplg_tlv_dbscale scale;
+	};
 } __attribute__((packed));
 
 /*
@@ -155,9 +170,11 @@
 } __attribute__((packed));
 
 /*
- * Kcontrol Operations IDs
+ * Genericl Operations IDs, for binding Kcontrol or Bytes ext ops
+ * Kcontrol ops need get/put/info.
+ * Bytes ext ops need get/put.
  */
-struct snd_soc_tplg_kcontrol_ops_id {
+struct snd_soc_tplg_io_ops {
 	__le32 get;
 	__le32 put;
 	__le32 info;
@@ -171,8 +188,8 @@
 	__le32 type;
 	char name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
 	__le32 access;
-	struct snd_soc_tplg_kcontrol_ops_id ops;
-	__le32 tlv_size;	/* non zero means control has TLV data */
+	struct snd_soc_tplg_io_ops ops;
+	struct snd_soc_tplg_ctl_tlv tlv;
 } __attribute__((packed));
 
 /*
@@ -222,7 +239,7 @@
 /*
  * Manifest. List totals for each payload type. Not used in parsing, but will
  * be passed to the component driver before any other objects in order for any
- * global componnent resource allocations.
+ * global component resource allocations.
  *
  * File block representation for manifest :-
  * +-----------------------------------+----+
@@ -238,6 +255,7 @@
 	__le32 graph_elems;	/* number of graph elements */
 	__le32 dai_elems;	/* number of DAI elements */
 	__le32 dai_link_elems;	/* number of DAI link elements */
+	struct snd_soc_tplg_private priv;
 } __attribute__((packed));
 
 /*
@@ -259,7 +277,6 @@
 	__le32 invert;
 	__le32 num_channels;
 	struct snd_soc_tplg_channel channel[SND_SOC_TPLG_MAX_CHAN];
-	struct snd_soc_tplg_ctl_tlv tlv;
 	struct snd_soc_tplg_private priv;
 } __attribute__((packed));
 
@@ -303,6 +320,7 @@
 	__le32 mask;
 	__le32 base;
 	__le32 num_regs;
+	struct snd_soc_tplg_io_ops ext_ops;
 	struct snd_soc_tplg_private priv;
 } __attribute__((packed));
 
@@ -347,6 +365,7 @@
 	__le32 reg;		/* negative reg = no direct dapm */
 	__le32 shift;		/* bits to shift */
 	__le32 mask;		/* non-shifted mask */
+	__le32 subseq;		/* sort within widget type */
 	__u32 invert;		/* invert the power bit */
 	__u32 ignore_suspend;	/* kept enabled over suspend */
 	__u16 event_flags;
diff --git a/init/main.c b/init/main.c
index c5d5626..5650655 100644
--- a/init/main.c
+++ b/init/main.c
@@ -656,7 +656,7 @@
 	key_init();
 	security_init();
 	dbg_late_init();
-	vfs_caches_init(totalram_pages);
+	vfs_caches_init();
 	signals_init();
 	/* rootfs populating might need page-writeback */
 	page_writeback_init();
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index a24ba9f..161a180 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -142,7 +142,6 @@
 		if (!leaf)
 			return -ENOMEM;
 		INIT_LIST_HEAD(&leaf->msg_list);
-		info->qsize += sizeof(*leaf);
 	}
 	leaf->priority = msg->m_type;
 	rb_link_node(&leaf->rb_node, parent, p);
@@ -187,7 +186,6 @@
 			     "lazy leaf delete!\n");
 		rb_erase(&leaf->rb_node, &info->msg_tree);
 		if (info->node_cache) {
-			info->qsize -= sizeof(*leaf);
 			kfree(leaf);
 		} else {
 			info->node_cache = leaf;
@@ -200,7 +198,6 @@
 		if (list_empty(&leaf->msg_list)) {
 			rb_erase(&leaf->rb_node, &info->msg_tree);
 			if (info->node_cache) {
-				info->qsize -= sizeof(*leaf);
 				kfree(leaf);
 			} else {
 				info->node_cache = leaf;
@@ -1034,7 +1031,6 @@
 		/* Save our speculative allocation into the cache */
 		INIT_LIST_HEAD(&new_leaf->msg_list);
 		info->node_cache = new_leaf;
-		info->qsize += sizeof(*new_leaf);
 		new_leaf = NULL;
 	} else {
 		kfree(new_leaf);
@@ -1142,7 +1138,6 @@
 		/* Save our speculative allocation into the cache */
 		INIT_LIST_HEAD(&new_leaf->msg_list);
 		info->node_cache = new_leaf;
-		info->qsize += sizeof(*new_leaf);
 	} else {
 		kfree(new_leaf);
 	}
diff --git a/ipc/sem.c b/ipc/sem.c
index bc3d530..b471e5a 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -253,6 +253,16 @@
 }
 
 /*
+ * spin_unlock_wait() and !spin_is_locked() are not memory barriers, they
+ * are only control barriers.
+ * The code must pair with spin_unlock(&sem->lock) or
+ * spin_unlock(&sem_perm.lock), thus just the control barrier is insufficient.
+ *
+ * smp_rmb() is sufficient, as writes cannot pass the control barrier.
+ */
+#define ipc_smp_acquire__after_spin_is_unlocked()	smp_rmb()
+
+/*
  * Wait until all currently ongoing simple ops have completed.
  * Caller must own sem_perm.lock.
  * New simple ops cannot start, because simple ops first check
@@ -275,6 +285,7 @@
 		sem = sma->sem_base + i;
 		spin_unlock_wait(&sem->lock);
 	}
+	ipc_smp_acquire__after_spin_is_unlocked();
 }
 
 /*
@@ -327,13 +338,12 @@
 		/* Then check that the global lock is free */
 		if (!spin_is_locked(&sma->sem_perm.lock)) {
 			/*
-			 * The ipc object lock check must be visible on all
-			 * cores before rechecking the complex count.  Otherwise
-			 * we can race with  another thread that does:
+			 * We need a memory barrier with acquire semantics,
+			 * otherwise we can race with another thread that does:
 			 *	complex_count++;
 			 *	spin_unlock(sem_perm.lock);
 			 */
-			smp_rmb();
+			ipc_smp_acquire__after_spin_is_unlocked();
 
 			/*
 			 * Now repeat the test of complex_count:
@@ -2074,17 +2084,28 @@
 		rcu_read_lock();
 		un = list_entry_rcu(ulp->list_proc.next,
 				    struct sem_undo, list_proc);
-		if (&un->list_proc == &ulp->list_proc)
-			semid = -1;
-		 else
-			semid = un->semid;
-
-		if (semid == -1) {
+		if (&un->list_proc == &ulp->list_proc) {
+			/*
+			 * We must wait for freeary() before freeing this ulp,
+			 * in case we raced with last sem_undo. There is a small
+			 * possibility where we exit while freeary() didn't
+			 * finish unlocking sem_undo_list.
+			 */
+			spin_unlock_wait(&ulp->lock);
 			rcu_read_unlock();
 			break;
 		}
+		spin_lock(&ulp->lock);
+		semid = un->semid;
+		spin_unlock(&ulp->lock);
 
-		sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, un->semid);
+		/* exit_sem raced with IPC_RMID, nothing to do */
+		if (semid == -1) {
+			rcu_read_unlock();
+			continue;
+		}
+
+		sma = sem_obtain_object_check(tsk->nsproxy->ipc_ns, semid);
 		/* exit_sem raced with IPC_RMID, nothing to do */
 		if (IS_ERR(sma)) {
 			rcu_read_unlock();
@@ -2112,9 +2133,11 @@
 		ipc_assert_locked_object(&sma->sem_perm);
 		list_del(&un->list_id);
 
-		spin_lock(&ulp->lock);
+		/* we are the last process using this ulp, acquiring ulp->lock
+		 * isn't required. Besides that, we are also protected against
+		 * IPC_RMID as we hold sma->sem_perm lock now
+		 */
 		list_del_rcu(&un->list_proc);
-		spin_unlock(&ulp->lock);
 
 		/* perform adjustments registered in un */
 		for (i = 0; i < sma->sem_nsems; i++) {
diff --git a/ipc/shm.c b/ipc/shm.c
index 06e5cf2..4aef24d 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -545,7 +545,7 @@
 		if  ((shmflg & SHM_NORESERVE) &&
 				sysctl_overcommit_memory != OVERCOMMIT_NEVER)
 			acctflag = VM_NORESERVE;
-		file = shmem_file_setup(name, size, acctflag);
+		file = shmem_kernel_file_setup(name, size, acctflag);
 	}
 	error = PTR_ERR(file);
 	if (IS_ERR(file))
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 09c6564..e85bdfd 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1021,8 +1021,7 @@
 	 * for strings that are too long, we should not have created
 	 * any.
 	 */
-	if (unlikely((len == 0) || len > MAX_ARG_STRLEN - 1)) {
-		WARN_ON(1);
+	if (WARN_ON_ONCE(len < 0 || len > MAX_ARG_STRLEN - 1)) {
 		send_sig(SIGKILL, current, 0);
 		return -1;
 	}
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9c9c9fa..5644ec5 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -21,6 +21,7 @@
 #include <linux/suspend.h>
 #include <linux/lockdep.h>
 #include <linux/tick.h>
+#include <linux/irq.h>
 #include <trace/events/power.h>
 
 #include "smpboot.h"
@@ -392,13 +393,19 @@
 	smpboot_park_threads(cpu);
 
 	/*
+	 * Prevent irq alloc/free while the dying cpu reorganizes the
+	 * interrupt affinities.
+	 */
+	irq_lock_sparse();
+
+	/*
 	 * So now all preempt/rcu users must observe !cpu_active().
 	 */
-
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
 		cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
+		irq_unlock_sparse();
 		goto out_release;
 	}
 	BUG_ON(cpu_online(cpu));
@@ -415,6 +422,9 @@
 	smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */
 	per_cpu(cpu_dead_idle, cpu) = false;
 
+	/* Interrupts are moved away from the dying cpu, reenable alloc/free */
+	irq_unlock_sparse();
+
 	hotplug_cpu__broadcast_tick_pull(cpu);
 	/* This actually kills the CPU. */
 	__cpu_die(cpu);
@@ -519,6 +529,7 @@
 
 	/* Arch-specific enabling code. */
 	ret = __cpu_up(cpu, idle);
+
 	if (ret != 0)
 		goto out_notify;
 	BUG_ON(!cpu_online(cpu));
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index ee14e3a..f0acff0 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1223,7 +1223,7 @@
 	spin_unlock_irq(&callback_lock);
 
 	/* use trialcs->mems_allowed as a temp variable */
-	update_nodemasks_hier(cs, &cs->mems_allowed);
+	update_nodemasks_hier(cs, &trialcs->mems_allowed);
 done:
 	return retval;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e965cfa..e6feb51 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1868,8 +1868,6 @@
 
 	perf_pmu_disable(event->pmu);
 
-	event->tstamp_running += tstamp - event->tstamp_stopped;
-
 	perf_set_shadow_time(event, ctx, tstamp);
 
 	perf_log_itrace_start(event);
@@ -1881,6 +1879,8 @@
 		goto out;
 	}
 
+	event->tstamp_running += tstamp - event->tstamp_stopped;
+
 	if (!is_software_event(event))
 		cpuctx->active_oncpu++;
 	if (!ctx->nr_active++)
@@ -3958,28 +3958,21 @@
 		perf_event_for_each_child(sibling, func);
 }
 
-static int perf_event_period(struct perf_event *event, u64 __user *arg)
-{
-	struct perf_event_context *ctx = event->ctx;
-	int ret = 0, active;
+struct period_event {
+	struct perf_event *event;
 	u64 value;
+};
 
-	if (!is_sampling_event(event))
-		return -EINVAL;
+static int __perf_event_period(void *info)
+{
+	struct period_event *pe = info;
+	struct perf_event *event = pe->event;
+	struct perf_event_context *ctx = event->ctx;
+	u64 value = pe->value;
+	bool active;
 
-	if (copy_from_user(&value, arg, sizeof(value)))
-		return -EFAULT;
-
-	if (!value)
-		return -EINVAL;
-
-	raw_spin_lock_irq(&ctx->lock);
+	raw_spin_lock(&ctx->lock);
 	if (event->attr.freq) {
-		if (value > sysctl_perf_event_sample_rate) {
-			ret = -EINVAL;
-			goto unlock;
-		}
-
 		event->attr.sample_freq = value;
 	} else {
 		event->attr.sample_period = value;
@@ -3998,11 +3991,53 @@
 		event->pmu->start(event, PERF_EF_RELOAD);
 		perf_pmu_enable(ctx->pmu);
 	}
+	raw_spin_unlock(&ctx->lock);
 
-unlock:
+	return 0;
+}
+
+static int perf_event_period(struct perf_event *event, u64 __user *arg)
+{
+	struct period_event pe = { .event = event, };
+	struct perf_event_context *ctx = event->ctx;
+	struct task_struct *task;
+	u64 value;
+
+	if (!is_sampling_event(event))
+		return -EINVAL;
+
+	if (copy_from_user(&value, arg, sizeof(value)))
+		return -EFAULT;
+
+	if (!value)
+		return -EINVAL;
+
+	if (event->attr.freq && value > sysctl_perf_event_sample_rate)
+		return -EINVAL;
+
+	task = ctx->task;
+	pe.value = value;
+
+	if (!task) {
+		cpu_function_call(event->cpu, __perf_event_period, &pe);
+		return 0;
+	}
+
+retry:
+	if (!task_function_call(task, __perf_event_period, &pe))
+		return 0;
+
+	raw_spin_lock_irq(&ctx->lock);
+	if (ctx->is_active) {
+		raw_spin_unlock_irq(&ctx->lock);
+		task = ctx->task;
+		goto retry;
+	}
+
+	__perf_event_period(&pe);
 	raw_spin_unlock_irq(&ctx->lock);
 
-	return ret;
+	return 0;
 }
 
 static const struct file_operations perf_fops;
@@ -4358,14 +4393,6 @@
 	rcu_read_unlock();
 }
 
-static void rb_free_rcu(struct rcu_head *rcu_head)
-{
-	struct ring_buffer *rb;
-
-	rb = container_of(rcu_head, struct ring_buffer, rcu_head);
-	rb_free(rb);
-}
-
 struct ring_buffer *ring_buffer_get(struct perf_event *event)
 {
 	struct ring_buffer *rb;
@@ -4748,12 +4775,20 @@
  * to user-space before waking everybody up.
  */
 
+static inline struct fasync_struct **perf_event_fasync(struct perf_event *event)
+{
+	/* only the parent has fasync state */
+	if (event->parent)
+		event = event->parent;
+	return &event->fasync;
+}
+
 void perf_event_wakeup(struct perf_event *event)
 {
 	ring_buffer_wakeup(event);
 
 	if (event->pending_kill) {
-		kill_fasync(&event->fasync, SIGIO, event->pending_kill);
+		kill_fasync(perf_event_fasync(event), SIGIO, event->pending_kill);
 		event->pending_kill = 0;
 	}
 }
@@ -6132,7 +6167,7 @@
 	else
 		perf_event_output(event, data, regs);
 
-	if (event->fasync && event->pending_kill) {
+	if (*perf_event_fasync(event) && event->pending_kill) {
 		event->pending_wakeup = 1;
 		irq_work_queue(&event->pending);
 	}
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index 2deb24c..2bbad9c 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -11,6 +11,7 @@
 struct ring_buffer {
 	atomic_t			refcount;
 	struct rcu_head			rcu_head;
+	struct irq_work			irq_work;
 #ifdef CONFIG_PERF_USE_VMALLOC
 	struct work_struct		work;
 	int				page_order;	/* allocation order  */
@@ -55,6 +56,15 @@
 };
 
 extern void rb_free(struct ring_buffer *rb);
+
+static inline void rb_free_rcu(struct rcu_head *rcu_head)
+{
+	struct ring_buffer *rb;
+
+	rb = container_of(rcu_head, struct ring_buffer, rcu_head);
+	rb_free(rb);
+}
+
 extern struct ring_buffer *
 rb_alloc(int nr_pages, long watermark, int cpu, int flags);
 extern void perf_event_wakeup(struct perf_event *event);
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 9647282..c8aa3f7 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -221,6 +221,8 @@
 	rcu_read_unlock();
 }
 
+static void rb_irq_work(struct irq_work *work);
+
 static void
 ring_buffer_init(struct ring_buffer *rb, long watermark, int flags)
 {
@@ -241,6 +243,16 @@
 
 	INIT_LIST_HEAD(&rb->event_list);
 	spin_lock_init(&rb->event_lock);
+	init_irq_work(&rb->irq_work, rb_irq_work);
+}
+
+static void ring_buffer_put_async(struct ring_buffer *rb)
+{
+	if (!atomic_dec_and_test(&rb->refcount))
+		return;
+
+	rb->rcu_head.next = (void *)rb;
+	irq_work_queue(&rb->irq_work);
 }
 
 /*
@@ -319,7 +331,7 @@
 	rb_free_aux(rb);
 
 err:
-	ring_buffer_put(rb);
+	ring_buffer_put_async(rb);
 	handle->event = NULL;
 
 	return NULL;
@@ -370,7 +382,7 @@
 
 	local_set(&rb->aux_nest, 0);
 	rb_free_aux(rb);
-	ring_buffer_put(rb);
+	ring_buffer_put_async(rb);
 }
 
 /*
@@ -547,17 +559,30 @@
 		rb->aux_priv = NULL;
 	}
 
-	for (pg = 0; pg < rb->aux_nr_pages; pg++)
-		rb_free_aux_page(rb, pg);
+	if (rb->aux_nr_pages) {
+		for (pg = 0; pg < rb->aux_nr_pages; pg++)
+			rb_free_aux_page(rb, pg);
 
-	kfree(rb->aux_pages);
-	rb->aux_nr_pages = 0;
+		kfree(rb->aux_pages);
+		rb->aux_nr_pages = 0;
+	}
 }
 
 void rb_free_aux(struct ring_buffer *rb)
 {
 	if (atomic_dec_and_test(&rb->aux_refcount))
+		irq_work_queue(&rb->irq_work);
+}
+
+static void rb_irq_work(struct irq_work *work)
+{
+	struct ring_buffer *rb = container_of(work, struct ring_buffer, irq_work);
+
+	if (!atomic_read(&rb->aux_refcount))
 		__rb_free_aux(rb);
+
+	if (rb->rcu_head.next == (void *)rb)
+		call_rcu(&rb->rcu_head, rb_free_rcu);
 }
 
 #ifndef CONFIG_PERF_USE_VMALLOC
diff --git a/kernel/fork.c b/kernel/fork.c
index 1bfefc6..dbd9b8d 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -287,6 +287,11 @@
 	max_threads = clamp_t(u64, threads, MIN_THREADS, MAX_THREADS);
 }
 
+#ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT
+/* Initialized by the architecture: */
+int arch_task_struct_size __read_mostly;
+#endif
+
 void __init fork_init(void)
 {
 #ifndef CONFIG_ARCH_TASK_STRUCT_ALLOCATOR
@@ -295,7 +300,7 @@
 #endif
 	/* create a slab on which task_structs can be allocated */
 	task_struct_cachep =
-		kmem_cache_create("task_struct", sizeof(struct task_struct),
+		kmem_cache_create("task_struct", arch_task_struct_size,
 			ARCH_MIN_TASKALIGN, SLAB_PANIC | SLAB_NOTRACK, NULL);
 #endif
 
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 27f4332..ae21682 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -985,6 +985,23 @@
 }
 
 /**
+ * irq_chip_set_type_parent - Set IRQ type on the parent interrupt
+ * @data:	Pointer to interrupt specific data
+ * @type:	IRQ_TYPE_{LEVEL,EDGE}_* value - see include/linux/irq.h
+ *
+ * Conditional, as the underlying parent chip might not implement it.
+ */
+int irq_chip_set_type_parent(struct irq_data *data, unsigned int type)
+{
+	data = data->parent_data;
+
+	if (data->chip->irq_set_type)
+		return data->chip->irq_set_type(data, type);
+
+	return -ENOSYS;
+}
+
+/**
  * irq_chip_retrigger_hierarchy - Retrigger an interrupt in hardware
  * @data:	Pointer to interrupt specific data
  *
@@ -997,7 +1014,7 @@
 		if (data->chip && data->chip->irq_retrigger)
 			return data->chip->irq_retrigger(data);
 
-	return -ENOSYS;
+	return 0;
 }
 
 /**
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 4834ee8..61008b8 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -76,12 +76,8 @@
 
 #ifdef CONFIG_SPARSE_IRQ
 static inline void irq_mark_irq(unsigned int irq) { }
-extern void irq_lock_sparse(void);
-extern void irq_unlock_sparse(void);
 #else
 extern void irq_mark_irq(unsigned int irq);
-static inline void irq_lock_sparse(void) { }
-static inline void irq_unlock_sparse(void) { }
 #endif
 
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 9065107..7a5237a 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -75,13 +75,21 @@
 		    !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) {
 #ifdef CONFIG_HARDIRQS_SW_RESEND
 			/*
-			 * If the interrupt has a parent irq and runs
-			 * in the thread context of the parent irq,
-			 * retrigger the parent.
+			 * If the interrupt is running in the thread
+			 * context of the parent irq we need to be
+			 * careful, because we cannot trigger it
+			 * directly.
 			 */
-			if (desc->parent_irq &&
-			    irq_settings_is_nested_thread(desc))
+			if (irq_settings_is_nested_thread(desc)) {
+				/*
+				 * If the parent_irq is valid, we
+				 * retrigger the parent, otherwise we
+				 * do nothing.
+				 */
+				if (!desc->parent_irq)
+					return;
 				irq = desc->parent_irq;
+			}
 			/* Set it pending and activate the softirq: */
 			set_bit(irq, irqs_resend);
 			tasklet_schedule(&resend_tasklet);
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 10e489c..fdea0be 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -97,6 +97,7 @@
 {
 	return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags);
 }
+EXPORT_SYMBOL_GPL(kthread_should_park);
 
 /**
  * kthread_freezable_should_stop - should this freezable kthread return now?
@@ -171,6 +172,7 @@
 {
 	__kthread_parkme(to_kthread(current));
 }
+EXPORT_SYMBOL_GPL(kthread_parkme);
 
 static int kthread(void *_create)
 {
@@ -411,6 +413,7 @@
 	if (kthread)
 		__kthread_unpark(k, kthread);
 }
+EXPORT_SYMBOL_GPL(kthread_unpark);
 
 /**
  * kthread_park - park a thread created by kthread_create().
@@ -441,6 +444,7 @@
 	}
 	return ret;
 }
+EXPORT_SYMBOL_GPL(kthread_park);
 
 /**
  * kthread_stop - stop a thread created by kthread_create().
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 04ab181..df19ae4 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -4,6 +4,7 @@
 
 #include <linux/hash.h>
 #include <linux/bootmem.h>
+#include <linux/debug_locks.h>
 
 /*
  * Implement paravirt qspinlocks; the general idea is to halt the vcpus instead
@@ -286,15 +287,23 @@
 {
 	struct __qspinlock *l = (void *)lock;
 	struct pv_node *node;
+	u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
 
 	/*
 	 * We must not unlock if SLOW, because in that case we must first
 	 * unhash. Otherwise it would be possible to have multiple @lock
 	 * entries, which would be BAD.
 	 */
-	if (likely(cmpxchg(&l->locked, _Q_LOCKED_VAL, 0) == _Q_LOCKED_VAL))
+	if (likely(lockval == _Q_LOCKED_VAL))
 		return;
 
+	if (unlikely(lockval != _Q_SLOW_VAL)) {
+		if (debug_locks_silent)
+			return;
+		WARN(1, "pvqspinlock: lock %p has corrupted value 0x%x!\n", lock, atomic_read(&lock->val));
+		return;
+	}
+
 	/*
 	 * Since the above failed to release, this must be the SLOW path.
 	 * Therefore start by looking up the blocked node and unhashing it.
diff --git a/kernel/module.c b/kernel/module.c
index 3e0e197..b86b7bf 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -602,13 +602,16 @@
 }
 EXPORT_SYMBOL_GPL(find_symbol);
 
-/* Search for module by name: must hold module_mutex. */
+/*
+ * Search for module by name: must hold module_mutex (or preempt disabled
+ * for read-only access).
+ */
 static struct module *find_module_all(const char *name, size_t len,
 				      bool even_unformed)
 {
 	struct module *mod;
 
-	module_assert_mutex();
+	module_assert_mutex_or_preempt();
 
 	list_for_each_entry(mod, &modules, list) {
 		if (!even_unformed && mod->state == MODULE_STATE_UNFORMED)
@@ -621,6 +624,7 @@
 
 struct module *find_module(const char *name)
 {
+	module_assert_mutex();
 	return find_module_all(name, strlen(name), false);
 }
 EXPORT_SYMBOL_GPL(find_module);
@@ -3557,6 +3561,7 @@
 	mutex_lock(&module_mutex);
 	/* Unlink carefully: kallsyms could be walking list. */
 	list_del_rcu(&mod->list);
+	mod_tree_remove(mod);
 	wake_up_all(&module_wq);
 	/* Wait for RCU-sched synchronizing before releasing mod->list. */
 	synchronize_sched();
diff --git a/kernel/resource.c b/kernel/resource.c
index 90552aa..fed052a 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -504,13 +504,13 @@
 {
 	struct resource *p;
 	resource_size_t end = start + size - 1;
-	int flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+	unsigned long flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 	const char *name = "System RAM";
 	int ret = -1;
 
 	read_lock(&resource_lock);
 	for (p = iomem_resource.child; p ; p = p->sibling) {
-		if (end < p->start)
+		if (p->end < start)
 			continue;
 
 		if (p->start <= start && end <= p->end) {
@@ -521,7 +521,7 @@
 				ret = 1;
 			break;
 		}
-		if (p->end < start)
+		if (end < p->start)
 			break;	/* not found */
 	}
 	read_unlock(&resource_lock);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 65c8f3e..d113c3b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3683,7 +3683,7 @@
 	cfs_rq->throttled = 1;
 	cfs_rq->throttled_clock = rq_clock(rq);
 	raw_spin_lock(&cfs_b->lock);
-	empty = list_empty(&cfs_rq->throttled_list);
+	empty = list_empty(&cfs_b->throttled_cfs_rq);
 
 	/*
 	 * Add to the _head_ of the list, so that an already-started
diff --git a/kernel/signal.c b/kernel/signal.c
index 836df8d..0f6bbbe 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2748,12 +2748,15 @@
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitly for the right codes here.
 		 */
-		if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
+		if (from->si_signo == SIGBUS &&
+		    (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO))
 			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
 #endif
 #ifdef SEGV_BNDERR
-		err |= __put_user(from->si_lower, &to->si_lower);
-		err |= __put_user(from->si_upper, &to->si_upper);
+		if (from->si_signo == SIGSEGV && from->si_code == SEGV_BNDERR) {
+			err |= __put_user(from->si_lower, &to->si_lower);
+			err |= __put_user(from->si_upper, &to->si_upper);
+		}
 #endif
 		break;
 	case __SI_CHLD:
@@ -3017,7 +3020,7 @@
 			int, sig,
 			struct compat_siginfo __user *, uinfo)
 {
-	siginfo_t info;
+	siginfo_t info = {};
 	int ret = copy_siginfo_from_user32(&info, uinfo);
 	if (unlikely(ret))
 		return ret;
@@ -3061,7 +3064,7 @@
 			int, sig,
 			struct compat_siginfo __user *, uinfo)
 {
-	siginfo_t info;
+	siginfo_t info = {};
 
 	if (copy_siginfo_from_user32(&info, uinfo))
 		return -EFAULT;
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 08ccc3d..50eb107 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -120,19 +120,25 @@
 		/* The clockevent device is getting replaced. Shut it down. */
 
 	case CLOCK_EVT_STATE_SHUTDOWN:
-		return dev->set_state_shutdown(dev);
+		if (dev->set_state_shutdown)
+			return dev->set_state_shutdown(dev);
+		return 0;
 
 	case CLOCK_EVT_STATE_PERIODIC:
 		/* Core internal bug */
 		if (!(dev->features & CLOCK_EVT_FEAT_PERIODIC))
 			return -ENOSYS;
-		return dev->set_state_periodic(dev);
+		if (dev->set_state_periodic)
+			return dev->set_state_periodic(dev);
+		return 0;
 
 	case CLOCK_EVT_STATE_ONESHOT:
 		/* Core internal bug */
 		if (!(dev->features & CLOCK_EVT_FEAT_ONESHOT))
 			return -ENOSYS;
-		return dev->set_state_oneshot(dev);
+		if (dev->set_state_oneshot)
+			return dev->set_state_oneshot(dev);
+		return 0;
 
 	case CLOCK_EVT_STATE_ONESHOT_STOPPED:
 		/* Core internal bug */
@@ -471,18 +477,6 @@
 	if (dev->features & CLOCK_EVT_FEAT_DUMMY)
 		return 0;
 
-	/* New state-specific callbacks */
-	if (!dev->set_state_shutdown)
-		return -EINVAL;
-
-	if ((dev->features & CLOCK_EVT_FEAT_PERIODIC) &&
-	    !dev->set_state_periodic)
-		return -EINVAL;
-
-	if ((dev->features & CLOCK_EVT_FEAT_ONESHOT) &&
-	    !dev->set_state_oneshot)
-		return -EINVAL;
-
 	return 0;
 }
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index d39f32c..f6aae79 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -159,7 +159,7 @@
 {
 	struct clock_event_device *bc = tick_broadcast_device.evtdev;
 	unsigned long flags;
-	int ret;
+	int ret = 0;
 
 	raw_spin_lock_irqsave(&tick_broadcast_lock, flags);
 
@@ -221,13 +221,14 @@
 			 * If we kept the cpu in the broadcast mask,
 			 * tell the caller to leave the per cpu device
 			 * in shutdown state. The periodic interrupt
-			 * is delivered by the broadcast device.
+			 * is delivered by the broadcast device, if
+			 * the broadcast device exists and is not
+			 * hrtimer based.
 			 */
-			ret = cpumask_test_cpu(cpu, tick_broadcast_mask);
+			if (bc && !(bc->features & CLOCK_EVT_FEAT_HRTIMER))
+				ret = cpumask_test_cpu(cpu, tick_broadcast_mask);
 			break;
 		default:
-			/* Nothing to do */
-			ret = 0;
 			break;
 		}
 	}
@@ -265,8 +266,22 @@
 	 * Check, if the current cpu is in the mask
 	 */
 	if (cpumask_test_cpu(cpu, mask)) {
+		struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
 		cpumask_clear_cpu(cpu, mask);
-		local = true;
+		/*
+		 * We only run the local handler, if the broadcast
+		 * device is not hrtimer based. Otherwise we run into
+		 * a hrtimer recursion.
+		 *
+		 * local timer_interrupt()
+		 *   local_handler()
+		 *     expire_hrtimers()
+		 *       bc_handler()
+		 *         local_handler()
+		 *	     expire_hrtimers()
+		 */
+		local = !(bc->features & CLOCK_EVT_FEAT_HRTIMER);
 	}
 
 	if (!cpumask_empty(mask)) {
@@ -301,6 +316,13 @@
 	bool bc_local;
 
 	raw_spin_lock(&tick_broadcast_lock);
+
+	/* Handle spurious interrupts gracefully */
+	if (clockevent_state_shutdown(tick_broadcast_device.evtdev)) {
+		raw_spin_unlock(&tick_broadcast_lock);
+		return;
+	}
+
 	bc_local = tick_do_periodic_broadcast();
 
 	if (clockevent_state_oneshot(dev)) {
@@ -359,8 +381,16 @@
 	case TICK_BROADCAST_ON:
 		cpumask_set_cpu(cpu, tick_broadcast_on);
 		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_mask)) {
-			if (tick_broadcast_device.mode ==
-			    TICKDEV_MODE_PERIODIC)
+			/*
+			 * Only shutdown the cpu local device, if:
+			 *
+			 * - the broadcast device exists
+			 * - the broadcast device is not a hrtimer based one
+			 * - the broadcast device is in periodic mode to
+			 *   avoid a hickup during switch to oneshot mode
+			 */
+			if (bc && !(bc->features & CLOCK_EVT_FEAT_HRTIMER) &&
+			    tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
 				clockevents_shutdown(dev);
 		}
 		break;
@@ -379,14 +409,16 @@
 		break;
 	}
 
-	if (cpumask_empty(tick_broadcast_mask)) {
-		if (!bc_stopped)
-			clockevents_shutdown(bc);
-	} else if (bc_stopped) {
-		if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
-			tick_broadcast_start_periodic(bc);
-		else
-			tick_broadcast_setup_oneshot(bc);
+	if (bc) {
+		if (cpumask_empty(tick_broadcast_mask)) {
+			if (!bc_stopped)
+				clockevents_shutdown(bc);
+		} else if (bc_stopped) {
+			if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
+				tick_broadcast_start_periodic(bc);
+			else
+				tick_broadcast_setup_oneshot(bc);
+		}
 	}
 	raw_spin_unlock(&tick_broadcast_lock);
 }
@@ -662,71 +694,82 @@
 	clockevents_switch_state(dev, CLOCK_EVT_STATE_SHUTDOWN);
 }
 
-/**
- * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode
- * @state:	The target state (enter/exit)
- *
- * The system enters/leaves a state, where affected devices might stop
- * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
- *
- * Called with interrupts disabled, so clockevents_lock is not
- * required here because the local clock event device cannot go away
- * under us.
- */
-int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+int __tick_broadcast_oneshot_control(enum tick_broadcast_state state)
 {
 	struct clock_event_device *bc, *dev;
-	struct tick_device *td;
 	int cpu, ret = 0;
 	ktime_t now;
 
 	/*
-	 * Periodic mode does not care about the enter/exit of power
-	 * states
+	 * If there is no broadcast device, tell the caller not to go
+	 * into deep idle.
 	 */
-	if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC)
-		return 0;
+	if (!tick_broadcast_device.evtdev)
+		return -EBUSY;
 
-	/*
-	 * We are called with preemtion disabled from the depth of the
-	 * idle code, so we can't be moved away.
-	 */
-	td = this_cpu_ptr(&tick_cpu_device);
-	dev = td->evtdev;
-
-	if (!(dev->features & CLOCK_EVT_FEAT_C3STOP))
-		return 0;
+	dev = this_cpu_ptr(&tick_cpu_device)->evtdev;
 
 	raw_spin_lock(&tick_broadcast_lock);
 	bc = tick_broadcast_device.evtdev;
 	cpu = smp_processor_id();
 
 	if (state == TICK_BROADCAST_ENTER) {
+		/*
+		 * If the current CPU owns the hrtimer broadcast
+		 * mechanism, it cannot go deep idle and we do not add
+		 * the CPU to the broadcast mask. We don't have to go
+		 * through the EXIT path as the local timer is not
+		 * shutdown.
+		 */
+		ret = broadcast_needs_cpu(bc, cpu);
+		if (ret)
+			goto out;
+
+		/*
+		 * If the broadcast device is in periodic mode, we
+		 * return.
+		 */
+		if (tick_broadcast_device.mode == TICKDEV_MODE_PERIODIC) {
+			/* If it is a hrtimer based broadcast, return busy */
+			if (bc->features & CLOCK_EVT_FEAT_HRTIMER)
+				ret = -EBUSY;
+			goto out;
+		}
+
 		if (!cpumask_test_and_set_cpu(cpu, tick_broadcast_oneshot_mask)) {
 			WARN_ON_ONCE(cpumask_test_cpu(cpu, tick_broadcast_pending_mask));
+
+			/* Conditionally shut down the local timer. */
 			broadcast_shutdown_local(bc, dev);
+
 			/*
 			 * We only reprogram the broadcast timer if we
 			 * did not mark ourself in the force mask and
 			 * if the cpu local event is earlier than the
 			 * broadcast event. If the current CPU is in
 			 * the force mask, then we are going to be
-			 * woken by the IPI right away.
+			 * woken by the IPI right away; we return
+			 * busy, so the CPU does not try to go deep
+			 * idle.
 			 */
-			if (!cpumask_test_cpu(cpu, tick_broadcast_force_mask) &&
-			    dev->next_event.tv64 < bc->next_event.tv64)
+			if (cpumask_test_cpu(cpu, tick_broadcast_force_mask)) {
+				ret = -EBUSY;
+			} else if (dev->next_event.tv64 < bc->next_event.tv64) {
 				tick_broadcast_set_event(bc, cpu, dev->next_event);
+				/*
+				 * In case of hrtimer broadcasts the
+				 * programming might have moved the
+				 * timer to this cpu. If yes, remove
+				 * us from the broadcast mask and
+				 * return busy.
+				 */
+				ret = broadcast_needs_cpu(bc, cpu);
+				if (ret) {
+					cpumask_clear_cpu(cpu,
+						tick_broadcast_oneshot_mask);
+				}
+			}
 		}
-		/*
-		 * If the current CPU owns the hrtimer broadcast
-		 * mechanism, it cannot go deep idle and we remove the
-		 * CPU from the broadcast mask. We don't have to go
-		 * through the EXIT path as the local timer is not
-		 * shutdown.
-		 */
-		ret = broadcast_needs_cpu(bc, cpu);
-		if (ret)
-			cpumask_clear_cpu(cpu, tick_broadcast_oneshot_mask);
 	} else {
 		if (cpumask_test_and_clear_cpu(cpu, tick_broadcast_oneshot_mask)) {
 			clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT);
@@ -796,7 +839,6 @@
 	raw_spin_unlock(&tick_broadcast_lock);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control);
 
 /*
  * Reset the one shot broadcast for a cpu
@@ -938,6 +980,16 @@
 	return bc ? bc->features & CLOCK_EVT_FEAT_ONESHOT : false;
 }
 
+#else
+int __tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+{
+	struct clock_event_device *bc = tick_broadcast_device.evtdev;
+
+	if (!bc || (bc->features & CLOCK_EVT_FEAT_HRTIMER))
+		return -EBUSY;
+
+	return 0;
+}
 #endif
 
 void __init tick_broadcast_init(void)
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 76446cb..f8bf475 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -343,6 +343,28 @@
 	tick_install_broadcast_device(newdev);
 }
 
+/**
+ * tick_broadcast_oneshot_control - Enter/exit broadcast oneshot mode
+ * @state:	The target state (enter/exit)
+ *
+ * The system enters/leaves a state, where affected devices might stop
+ * Returns 0 on success, -EBUSY if the cpu is used to broadcast wakeups.
+ *
+ * Called with interrupts disabled, so clockevents_lock is not
+ * required here because the local clock event device cannot go away
+ * under us.
+ */
+int tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+{
+	struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+
+	if (!(td->evtdev->features & CLOCK_EVT_FEAT_C3STOP))
+		return 0;
+
+	return __tick_broadcast_oneshot_control(state);
+}
+EXPORT_SYMBOL_GPL(tick_broadcast_oneshot_control);
+
 #ifdef CONFIG_HOTPLUG_CPU
 /*
  * Transfer the do_timer job away from a dying cpu.
diff --git a/kernel/time/tick-sched.h b/kernel/time/tick-sched.h
index 42fdf49..a4a8d4e 100644
--- a/kernel/time/tick-sched.h
+++ b/kernel/time/tick-sched.h
@@ -71,4 +71,14 @@
 static inline void tick_cancel_sched_timer(int cpu) { }
 #endif
 
+#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST
+extern int __tick_broadcast_oneshot_control(enum tick_broadcast_state state);
+#else
+static inline int
+__tick_broadcast_oneshot_control(enum tick_broadcast_state state)
+{
+	return -EBUSY;
+}
+#endif
+
 #endif
diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index 5e097fa..84190f0 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -807,8 +807,8 @@
 			spin_unlock(&base->lock);
 			base = new_base;
 			spin_lock(&base->lock);
-			timer->flags &= ~TIMER_BASEMASK;
-			timer->flags |= base->cpu;
+			WRITE_ONCE(timer->flags,
+				   (timer->flags & ~TIMER_BASEMASK) | base->cpu);
 		}
 	}
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 02bece4..eb11011 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -98,6 +98,13 @@
 	struct pid *pid;
 };
 
+static bool ftrace_pids_enabled(void)
+{
+	return !list_empty(&ftrace_pids);
+}
+
+static void ftrace_update_trampoline(struct ftrace_ops *ops);
+
 /*
  * ftrace_disabled is set when an anomaly is discovered.
  * ftrace_disabled is much stronger than ftrace_enabled.
@@ -109,7 +116,6 @@
 static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end;
 static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
 ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
-ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
 static struct ftrace_ops global_ops;
 static struct ftrace_ops control_ops;
 
@@ -183,14 +189,7 @@
 	if (!test_tsk_trace_trace(current))
 		return;
 
-	ftrace_pid_function(ip, parent_ip, op, regs);
-}
-
-static void set_ftrace_pid_function(ftrace_func_t func)
-{
-	/* do not set ftrace_pid_function to itself! */
-	if (func != ftrace_pid_func)
-		ftrace_pid_function = func;
+	op->saved_func(ip, parent_ip, op, regs);
 }
 
 /**
@@ -202,7 +201,6 @@
 void clear_ftrace_function(void)
 {
 	ftrace_trace_function = ftrace_stub;
-	ftrace_pid_function = ftrace_stub;
 }
 
 static void control_ops_disable_all(struct ftrace_ops *ops)
@@ -436,6 +434,12 @@
 	} else
 		add_ftrace_ops(&ftrace_ops_list, ops);
 
+	/* Always save the function, and reset at unregistering */
+	ops->saved_func = ops->func;
+
+	if (ops->flags & FTRACE_OPS_FL_PID && ftrace_pids_enabled())
+		ops->func = ftrace_pid_func;
+
 	ftrace_update_trampoline(ops);
 
 	if (ftrace_enabled)
@@ -463,15 +467,28 @@
 	if (ftrace_enabled)
 		update_ftrace_function();
 
+	ops->func = ops->saved_func;
+
 	return 0;
 }
 
 static void ftrace_update_pid_func(void)
 {
+	bool enabled = ftrace_pids_enabled();
+	struct ftrace_ops *op;
+
 	/* Only do something if we are tracing something */
 	if (ftrace_trace_function == ftrace_stub)
 		return;
 
+	do_for_each_ftrace_op(op, ftrace_ops_list) {
+		if (op->flags & FTRACE_OPS_FL_PID) {
+			op->func = enabled ? ftrace_pid_func :
+				op->saved_func;
+			ftrace_update_trampoline(op);
+		}
+	} while_for_each_ftrace_op(op);
+
 	update_ftrace_function();
 }
 
@@ -1133,7 +1150,8 @@
 	.local_hash.filter_hash		= EMPTY_HASH,
 	INIT_OPS_HASH(global_ops)
 	.flags				= FTRACE_OPS_FL_RECURSION_SAFE |
-					  FTRACE_OPS_FL_INITIALIZED,
+					  FTRACE_OPS_FL_INITIALIZED |
+					  FTRACE_OPS_FL_PID,
 };
 
 /*
@@ -5023,7 +5041,9 @@
 
 static struct ftrace_ops global_ops = {
 	.func			= ftrace_stub,
-	.flags			= FTRACE_OPS_FL_RECURSION_SAFE | FTRACE_OPS_FL_INITIALIZED,
+	.flags			= FTRACE_OPS_FL_RECURSION_SAFE |
+				  FTRACE_OPS_FL_INITIALIZED |
+				  FTRACE_OPS_FL_PID,
 };
 
 static int __init ftrace_nodyn_init(void)
@@ -5080,11 +5100,6 @@
 		if (WARN_ON(tr->ops->func != ftrace_stub))
 			printk("ftrace ops had %pS for function\n",
 			       tr->ops->func);
-		/* Only the top level instance does pid tracing */
-		if (!list_empty(&ftrace_pids)) {
-			set_ftrace_pid_function(func);
-			func = ftrace_pid_func;
-		}
 	}
 	tr->ops->func = func;
 	tr->ops->private = tr;
@@ -5371,7 +5386,7 @@
 {
 	mutex_lock(&ftrace_lock);
 
-	if (list_empty(&ftrace_pids) && (!*pos))
+	if (!ftrace_pids_enabled() && (!*pos))
 		return (void *) 1;
 
 	return seq_list_start(&ftrace_pids, *pos);
@@ -5610,6 +5625,7 @@
 	.func			= ftrace_stub,
 	.flags			= FTRACE_OPS_FL_RECURSION_SAFE |
 				   FTRACE_OPS_FL_INITIALIZED |
+				   FTRACE_OPS_FL_PID |
 				   FTRACE_OPS_FL_STUB,
 #ifdef FTRACE_GRAPH_TRAMP_ADDR
 	.trampoline		= FTRACE_GRAPH_TRAMP_ADDR,
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index f060716..74bde81 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -444,6 +444,7 @@
 
 	TRACE_CONTROL_BIT,
 
+	TRACE_BRANCH_BIT,
 /*
  * Abuse of the trace_recursion.
  * As we need a way to maintain state if we are tracing the function
diff --git a/kernel/trace/trace_branch.c b/kernel/trace/trace_branch.c
index a87b43f..e2e12ad 100644
--- a/kernel/trace/trace_branch.c
+++ b/kernel/trace/trace_branch.c
@@ -36,9 +36,12 @@
 	struct trace_branch *entry;
 	struct ring_buffer *buffer;
 	unsigned long flags;
-	int cpu, pc;
+	int pc;
 	const char *p;
 
+	if (current->trace_recursion & TRACE_BRANCH_BIT)
+		return;
+
 	/*
 	 * I would love to save just the ftrace_likely_data pointer, but
 	 * this code can also be used by modules. Ugly things can happen
@@ -49,10 +52,10 @@
 	if (unlikely(!tr))
 		return;
 
-	local_irq_save(flags);
-	cpu = raw_smp_processor_id();
-	data = per_cpu_ptr(tr->trace_buffer.data, cpu);
-	if (atomic_inc_return(&data->disabled) != 1)
+	raw_local_irq_save(flags);
+	current->trace_recursion |= TRACE_BRANCH_BIT;
+	data = this_cpu_ptr(tr->trace_buffer.data);
+	if (atomic_read(&data->disabled))
 		goto out;
 
 	pc = preempt_count();
@@ -81,8 +84,8 @@
 		__buffer_unlock_commit(buffer, event);
 
  out:
-	atomic_dec(&data->disabled);
-	local_irq_restore(flags);
+	current->trace_recursion &= ~TRACE_BRANCH_BIT;
+	raw_local_irq_restore(flags);
 }
 
 static inline
diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
index 777eda7..39f24d6 100644
--- a/lib/Kconfig.kasan
+++ b/lib/Kconfig.kasan
@@ -18,10 +18,6 @@
 	  For better error detection enable CONFIG_STACKTRACE,
 	  and add slub_debug=U to boot cmdline.
 
-config KASAN_SHADOW_OFFSET
-	hex
-	default 0xdffffc0000000000 if X86_64
-
 choice
 	prompt "Instrumentation type"
 	depends on KASAN
diff --git a/lib/decompress.c b/lib/decompress.c
index 528ff93..62696df 100644
--- a/lib/decompress.c
+++ b/lib/decompress.c
@@ -59,8 +59,11 @@
 {
 	const struct compress_format *cf;
 
-	if (len < 2)
+	if (len < 2) {
+		if (name)
+			*name = NULL;
 		return NULL;	/* Need at least this much... */
+	}
 
 	pr_debug("Compressed data magic: %#.2x %#.2x\n", inbuf[0], inbuf[1]);
 
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index ae4b65e..dace71f 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -574,6 +574,9 @@
 	unsigned long flags;
 	phys_addr_t cln;
 
+	if (dma_debug_disabled())
+		return;
+
 	if (!page)
 		return;
 
diff --git a/lib/hexdump.c b/lib/hexdump.c
index 7ea0969..8d74c20 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -11,6 +11,7 @@
 #include <linux/ctype.h>
 #include <linux/kernel.h>
 #include <linux/export.h>
+#include <asm/unaligned.h>
 
 const char hex_asc[] = "0123456789abcdef";
 EXPORT_SYMBOL(hex_asc);
@@ -139,7 +140,7 @@
 		for (j = 0; j < ngroups; j++) {
 			ret = snprintf(linebuf + lx, linebuflen - lx,
 				       "%s%16.16llx", j ? " " : "",
-				       (unsigned long long)*(ptr8 + j));
+				       get_unaligned(ptr8 + j));
 			if (ret >= linebuflen - lx)
 				goto overflow1;
 			lx += ret;
@@ -150,7 +151,7 @@
 		for (j = 0; j < ngroups; j++) {
 			ret = snprintf(linebuf + lx, linebuflen - lx,
 				       "%s%8.8x", j ? " " : "",
-				       *(ptr4 + j));
+				       get_unaligned(ptr4 + j));
 			if (ret >= linebuflen - lx)
 				goto overflow1;
 			lx += ret;
@@ -161,7 +162,7 @@
 		for (j = 0; j < ngroups; j++) {
 			ret = snprintf(linebuf + lx, linebuflen - lx,
 				       "%s%4.4x", j ? " " : "",
-				       *(ptr2 + j));
+				       get_unaligned(ptr2 + j));
 			if (ret >= linebuflen - lx)
 				goto overflow1;
 			lx += ret;
diff --git a/lib/iommu-common.c b/lib/iommu-common.c
index df30632..ff19f66 100644
--- a/lib/iommu-common.c
+++ b/lib/iommu-common.c
@@ -119,7 +119,7 @@
 	unsigned long align_mask = 0;
 
 	if (align_order > 0)
-		align_mask = 0xffffffffffffffffl >> (64 - align_order);
+		align_mask = ~0ul >> (BITS_PER_LONG - align_order);
 
 	/* Sanity check */
 	if (unlikely(npages == 0)) {
diff --git a/lib/kobject.c b/lib/kobject.c
index 2e3bd01..3e3a5c3 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -337,8 +337,9 @@
 }
 EXPORT_SYMBOL(kobject_init);
 
-static int kobject_add_varg(struct kobject *kobj, struct kobject *parent,
-			    const char *fmt, va_list vargs)
+static __printf(3, 0) int kobject_add_varg(struct kobject *kobj,
+					   struct kobject *parent,
+					   const char *fmt, va_list vargs)
 {
 	int retval;
 
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index a60a6d3..cc0c697 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -610,6 +610,8 @@
 		iter->skip = 0;
 	}
 
+	iter->p = NULL;
+
 	/* Ensure we see any new tables. */
 	smp_rmb();
 
@@ -620,8 +622,6 @@
 		return ERR_PTR(-EAGAIN);
 	}
 
-	iter->p = NULL;
-
 	return NULL;
 }
 EXPORT_SYMBOL_GPL(rhashtable_walk_next);
diff --git a/mm/cma.h b/mm/cma.h
index 1132d73..17c75a4 100644
--- a/mm/cma.h
+++ b/mm/cma.h
@@ -16,7 +16,7 @@
 extern struct cma cma_areas[MAX_CMA_AREAS];
 extern unsigned cma_area_count;
 
-static unsigned long cma_bitmap_maxno(struct cma *cma)
+static inline unsigned long cma_bitmap_maxno(struct cma *cma)
 {
 	return cma->count >> cma->order_per_bit;
 }
diff --git a/mm/cma_debug.c b/mm/cma_debug.c
index 7621ee3..f8e4b60 100644
--- a/mm/cma_debug.c
+++ b/mm/cma_debug.c
@@ -39,7 +39,7 @@
 
 	mutex_lock(&cma->lock);
 	/* pages counter is smaller than sizeof(int) */
-	used = bitmap_weight(cma->bitmap, (int)cma->count);
+	used = bitmap_weight(cma->bitmap, (int)cma_bitmap_maxno(cma));
 	mutex_unlock(&cma->lock);
 	*val = (u64)used << cma->order_per_bit;
 
@@ -52,13 +52,14 @@
 	struct cma *cma = data;
 	unsigned long maxchunk = 0;
 	unsigned long start, end = 0;
+	unsigned long bitmap_maxno = cma_bitmap_maxno(cma);
 
 	mutex_lock(&cma->lock);
 	for (;;) {
-		start = find_next_zero_bit(cma->bitmap, cma->count, end);
+		start = find_next_zero_bit(cma->bitmap, bitmap_maxno, end);
 		if (start >= cma->count)
 			break;
-		end = find_next_bit(cma->bitmap, cma->count, start);
+		end = find_next_bit(cma->bitmap, bitmap_maxno, start);
 		maxchunk = max(end - start, maxchunk);
 	}
 	mutex_unlock(&cma->lock);
@@ -170,10 +171,10 @@
 
 	tmp = debugfs_create_dir(name, cma_debugfs_root);
 
-	debugfs_create_file("alloc", S_IWUSR, cma_debugfs_root, cma,
+	debugfs_create_file("alloc", S_IWUSR, tmp, cma,
 				&cma_alloc_fops);
 
-	debugfs_create_file("free", S_IWUSR, cma_debugfs_root, cma,
+	debugfs_create_file("free", S_IWUSR, tmp, cma,
 				&cma_free_fops);
 
 	debugfs_create_file("base_pfn", S_IRUGO, tmp,
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c107094..097c7a4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1676,12 +1676,7 @@
 		/* after clearing PageTail the gup refcount can be released */
 		smp_mb__after_atomic();
 
-		/*
-		 * retain hwpoison flag of the poisoned tail page:
-		 *   fix for the unsuitable process killed on Guest Machine(KVM)
-		 *   by the memory-failure.
-		 */
-		page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON;
+		page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 		page_tail->flags |= (page->flags &
 				     ((1L << PG_referenced) |
 				      (1L << PG_swapbacked) |
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 6c513a6..7b28e9c 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -2,7 +2,7 @@
  * This file contains shadow memory manipulation code.
  *
  * Copyright (c) 2014 Samsung Electronics Co., Ltd.
- * Author: Andrey Ryabinin <a.ryabinin@samsung.com>
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
  *
  * Some of code borrowed from https://github.com/xairy/linux by
  *        Andrey Konovalov <adech.fo@gmail.com>
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 680ceed..e07c94f 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -2,7 +2,7 @@
  * This file contains error reporting code.
  *
  * Copyright (c) 2014 Samsung Electronics Co., Ltd.
- * Author: Andrey Ryabinin <a.ryabinin@samsung.com>
+ * Author: Andrey Ryabinin <ryabinin.a.a@gmail.com>
  *
  * Some of code borrowed from https://github.com/xairy/linux by
  *        Andrey Konovalov <adech.fo@gmail.com>
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index c53543d..1f4446a9 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -909,6 +909,18 @@
 	 * directly for tail pages.
 	 */
 	if (PageTransHuge(head)) {
+		/*
+		 * Non anonymous thp exists only in allocation/free time. We
+		 * can't handle such a case correctly, so let's give it up.
+		 * This should be better than triggering BUG_ON when kernel
+		 * tries to touch the "partially handled" page.
+		 */
+		if (!PageAnon(head)) {
+			pr_err("MCE: %#lx: non anonymous thp\n",
+				page_to_pfn(page));
+			return 0;
+		}
+
 		if (get_page_unless_zero(head)) {
 			if (PageTail(page))
 				get_page(page);
@@ -1134,17 +1146,11 @@
 	}
 
 	if (!PageHuge(p) && PageTransHuge(hpage)) {
-		if (!PageAnon(hpage)) {
-			pr_err("MCE: %#lx: non anonymous thp\n", pfn);
-			if (TestClearPageHWPoison(p))
-				atomic_long_sub(nr_pages, &num_poisoned_pages);
-			put_page(p);
-			if (p != hpage)
-				put_page(hpage);
-			return -EBUSY;
-		}
-		if (unlikely(split_huge_page(hpage))) {
-			pr_err("MCE: %#lx: thp split failed\n", pfn);
+		if (!PageAnon(hpage) || unlikely(split_huge_page(hpage))) {
+			if (!PageAnon(hpage))
+				pr_err("MCE: %#lx: non anonymous thp\n", pfn);
+			else
+				pr_err("MCE: %#lx: thp split failed\n", pfn);
 			if (TestClearPageHWPoison(p))
 				atomic_long_sub(nr_pages, &num_poisoned_pages);
 			put_page(p);
@@ -1209,9 +1215,9 @@
 	if (!PageHWPoison(p)) {
 		printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn);
 		atomic_long_sub(nr_pages, &num_poisoned_pages);
+		unlock_page(hpage);
 		put_page(hpage);
-		res = 0;
-		goto out;
+		return 0;
 	}
 	if (hwpoison_filter(p)) {
 		if (TestClearPageHWPoison(p))
@@ -1535,6 +1541,8 @@
 		 */
 		ret = __get_any_page(page, pfn, 0);
 		if (!PageLRU(page)) {
+			/* Drop page reference which is from __get_any_page() */
+			put_page(page);
 			pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n",
 				pfn, page->flags);
 			return -EIO;
@@ -1564,13 +1572,12 @@
 	unlock_page(hpage);
 
 	ret = isolate_huge_page(hpage, &pagelist);
-	if (ret) {
-		/*
-		 * get_any_page() and isolate_huge_page() takes a refcount each,
-		 * so need to drop one here.
-		 */
-		put_page(hpage);
-	} else {
+	/*
+	 * get_any_page() and isolate_huge_page() takes a refcount each,
+	 * so need to drop one here.
+	 */
+	put_page(hpage);
+	if (!ret) {
 		pr_info("soft offline: %#lx hugepage failed to isolate\n", pfn);
 		return -EBUSY;
 	}
@@ -1656,6 +1663,8 @@
 		inc_zone_page_state(page, NR_ISOLATED_ANON +
 					page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
+		if (!TestSetPageHWPoison(page))
+			atomic_long_inc(&num_poisoned_pages);
 		ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
 					MIGRATE_SYNC, MR_MEMORY_FAILURE);
 		if (ret) {
@@ -1670,9 +1679,8 @@
 				pfn, ret, page->flags);
 			if (ret > 0)
 				ret = -EIO;
-		} else {
-			SetPageHWPoison(page);
-			atomic_long_inc(&num_poisoned_pages);
+			if (TestClearPageHWPoison(page))
+				atomic_long_dec(&num_poisoned_pages);
 		}
 	} else {
 		pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n",
diff --git a/mm/memory.c b/mm/memory.c
index a84fbb7..388dcf9 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2670,6 +2670,10 @@
 
 	pte_unmap(page_table);
 
+	/* File mapping without ->vm_ops ? */
+	if (vma->vm_flags & VM_SHARED)
+		return VM_FAULT_SIGBUS;
+
 	/* Check if we need to add a guard page to the stack */
 	if (check_stack_guard_page(vma, address) < 0)
 		return VM_FAULT_SIGSEGV;
@@ -3099,6 +3103,9 @@
 			- vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
 
 	pte_unmap(page_table);
+	/* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */
+	if (!vma->vm_ops->fault)
+		return VM_FAULT_SIGBUS;
 	if (!(flags & FAULT_FLAG_WRITE))
 		return do_read_fault(mm, vma, address, pmd, pgoff, flags,
 				orig_pte);
@@ -3244,13 +3251,12 @@
 	barrier();
 	if (!pte_present(entry)) {
 		if (pte_none(entry)) {
-			if (vma->vm_ops) {
-				if (likely(vma->vm_ops->fault))
-					return do_fault(mm, vma, address, pte,
-							pmd, flags, entry);
-			}
-			return do_anonymous_page(mm, vma, address,
-						 pte, pmd, flags);
+			if (vma->vm_ops)
+				return do_fault(mm, vma, address, pte, pmd,
+						flags, entry);
+
+			return do_anonymous_page(mm, vma, address, pte, pmd,
+					flags);
 		}
 		return do_swap_page(mm, vma, address,
 					pte, pmd, flags, entry);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 26fbba7..6da82bc 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -446,7 +446,7 @@
 	int nr_pages = PAGES_PER_SECTION;
 	int nid = pgdat->node_id;
 	int zone_type;
-	unsigned long flags;
+	unsigned long flags, pfn;
 	int ret;
 
 	zone_type = zone - pgdat->node_zones;
@@ -461,6 +461,14 @@
 	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 	memmap_init_zone(nr_pages, nid, zone_type,
 			 phys_start_pfn, MEMMAP_HOTPLUG);
+
+	/* online_page_range is called later and expects pages reserved */
+	for (pfn = phys_start_pfn; pfn < phys_start_pfn + nr_pages; pfn++) {
+		if (!pfn_valid(pfn))
+			continue;
+
+		SetPageReserved(pfn_to_page(pfn));
+	}
 	return 0;
 }
 
@@ -1269,6 +1277,7 @@
 
 	/* create new memmap entry */
 	firmware_map_add_hotplug(start, start + size, "System RAM");
+	memblock_add_node(start, size, nid);
 
 	goto out;
 
@@ -2005,6 +2014,8 @@
 
 	/* remove memmap entry */
 	firmware_map_remove(start, start + size, "System RAM");
+	memblock_free(start, size);
+	memblock_remove(start, size);
 
 	arch_remove_memory(start, size);
 
diff --git a/mm/migrate.c b/mm/migrate.c
index ee401e4..eb426710 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -880,7 +880,8 @@
 	/* Establish migration ptes or remove ptes */
 	if (page_mapped(page)) {
 		try_to_unmap(page,
-			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
+			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS|
+			TTU_IGNORE_HWPOISON);
 		page_was_mapped = 1;
 	}
 
@@ -950,7 +951,10 @@
 		list_del(&page->lru);
 		dec_zone_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
-		if (reason != MR_MEMORY_FAILURE)
+		/* Soft-offlined page shouldn't go through lru cache list */
+		if (reason == MR_MEMORY_FAILURE)
+			put_page(page);
+		else
 			putback_lru_page(page);
 	}
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 22cddd3..5cccc12 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2063,10 +2063,10 @@
  */
 void __init page_writeback_init(void)
 {
+	BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL));
+
 	writeback_set_ratelimit();
 	register_cpu_notifier(&ratelimit_nb);
-
-	BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL));
 }
 
 /**
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 506eac8..5b5240b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -18,7 +18,6 @@
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/interrupt.h>
-#include <linux/rwsem.h>
 #include <linux/pagemap.h>
 #include <linux/jiffies.h>
 #include <linux/bootmem.h>
@@ -246,9 +245,7 @@
 /* Returns true if the struct page for the pfn is uninitialised */
 static inline bool __meminit early_page_uninitialised(unsigned long pfn)
 {
-	int nid = early_pfn_to_nid(pfn);
-
-	if (pfn >= NODE_DATA(nid)->first_deferred_pfn)
+	if (pfn >= NODE_DATA(early_pfn_to_nid(pfn))->first_deferred_pfn)
 		return true;
 
 	return false;
@@ -983,21 +980,21 @@
 
 #if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \
 	defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
-/* Only safe to use early in boot when initialisation is single-threaded */
+
 static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;
 
 int __meminit early_pfn_to_nid(unsigned long pfn)
 {
+	static DEFINE_SPINLOCK(early_pfn_lock);
 	int nid;
 
-	/* The system will behave unpredictably otherwise */
-	BUG_ON(system_state != SYSTEM_BOOTING);
-
+	spin_lock(&early_pfn_lock);
 	nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
-	if (nid >= 0)
-		return nid;
-	/* just returns 0 */
-	return 0;
+	if (nid < 0)
+		nid = 0;
+	spin_unlock(&early_pfn_lock);
+
+	return nid;
 }
 #endif
 
@@ -1062,7 +1059,15 @@
 		__free_pages_boot_core(page, pfn, 0);
 }
 
-static __initdata DECLARE_RWSEM(pgdat_init_rwsem);
+/* Completion tracking for deferred_init_memmap() threads */
+static atomic_t pgdat_init_n_undone __initdata;
+static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp);
+
+static inline void __init pgdat_init_report_one_done(void)
+{
+	if (atomic_dec_and_test(&pgdat_init_n_undone))
+		complete(&pgdat_init_all_done_comp);
+}
 
 /* Initialise remaining memory on a node */
 static int __init deferred_init_memmap(void *data)
@@ -1079,7 +1084,7 @@
 	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
 	if (first_init_pfn == ULONG_MAX) {
-		up_read(&pgdat_init_rwsem);
+		pgdat_init_report_one_done();
 		return 0;
 	}
 
@@ -1179,7 +1184,8 @@
 
 	pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages,
 					jiffies_to_msecs(jiffies - start));
-	up_read(&pgdat_init_rwsem);
+
+	pgdat_init_report_one_done();
 	return 0;
 }
 
@@ -1187,14 +1193,17 @@
 {
 	int nid;
 
+	/* There will be num_node_state(N_MEMORY) threads */
+	atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY));
 	for_each_node_state(nid, N_MEMORY) {
-		down_read(&pgdat_init_rwsem);
 		kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid);
 	}
 
 	/* Block until all are initialised */
-	down_write(&pgdat_init_rwsem);
-	up_write(&pgdat_init_rwsem);
+	wait_for_completion(&pgdat_init_all_done_comp);
+
+	/* Reinit limits that are based on free pages after the kernel is up */
+	files_maxfiles_init();
 }
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
@@ -1287,6 +1296,10 @@
 		bad_reason = "non-NULL mapping";
 	if (unlikely(atomic_read(&page->_count) != 0))
 		bad_reason = "nonzero _count";
+	if (unlikely(page->flags & __PG_HWPOISON)) {
+		bad_reason = "HWPoisoned (hardware-corrupted)";
+		bad_flags = __PG_HWPOISON;
+	}
 	if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) {
 		bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set";
 		bad_flags = PAGE_FLAGS_CHECK_AT_PREP;
@@ -1330,12 +1343,15 @@
 	set_page_owner(page, order, gfp_flags);
 
 	/*
-	 * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was necessary to
+	 * page is set pfmemalloc when ALLOC_NO_WATERMARKS was necessary to
 	 * allocate the page. The expectation is that the caller is taking
 	 * steps that will free more memory. The caller should avoid the page
 	 * being used for !PFMEMALLOC purposes.
 	 */
-	page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS);
+	if (alloc_flags & ALLOC_NO_WATERMARKS)
+		set_page_pfmemalloc(page);
+	else
+		clear_page_pfmemalloc(page);
 
 	return 0;
 }
@@ -1950,6 +1966,7 @@
 void split_page(struct page *page, unsigned int order)
 {
 	int i;
+	gfp_t gfp_mask;
 
 	VM_BUG_ON_PAGE(PageCompound(page), page);
 	VM_BUG_ON_PAGE(!page_count(page), page);
@@ -1963,10 +1980,11 @@
 		split_page(virt_to_page(page[0].shadow), order);
 #endif
 
-	set_page_owner(page, 0, 0);
+	gfp_mask = get_page_owner_gfp(page);
+	set_page_owner(page, 0, gfp_mask);
 	for (i = 1; i < (1 << order); i++) {
 		set_page_refcounted(page + i);
-		set_page_owner(page + i, 0, 0);
+		set_page_owner(page + i, 0, gfp_mask);
 	}
 }
 EXPORT_SYMBOL_GPL(split_page);
@@ -1996,6 +2014,8 @@
 	zone->free_area[order].nr_free--;
 	rmv_page_order(page);
 
+	set_page_owner(page, order, __GFP_MOVABLE);
+
 	/* Set the pageblock if the isolated page is at least a pageblock */
 	if (order >= pageblock_order - 1) {
 		struct page *endpage = page + (1 << order) - 1;
@@ -2007,7 +2027,7 @@
 		}
 	}
 
-	set_page_owner(page, order, 0);
+
 	return 1UL << order;
 }
 
@@ -3328,7 +3348,7 @@
 		atomic_add(size - 1, &page->_count);
 
 		/* reset page count bias and offset to start of new frag */
-		nc->pfmemalloc = page->pfmemalloc;
+		nc->pfmemalloc = page_is_pfmemalloc(page);
 		nc->pagecnt_bias = size;
 		nc->offset = size;
 	}
@@ -5043,6 +5063,10 @@
 {
 	unsigned long zone_start_pfn, zone_end_pfn;
 
+	/* When hotadd a new node, the node should be empty */
+	if (!node_start_pfn && !node_end_pfn)
+		return 0;
+
 	/* Get the start and end of the zone */
 	zone_start_pfn = arch_zone_lowest_possible_pfn[zone_type];
 	zone_end_pfn = arch_zone_highest_possible_pfn[zone_type];
@@ -5106,6 +5130,10 @@
 	unsigned long zone_high = arch_zone_highest_possible_pfn[zone_type];
 	unsigned long zone_start_pfn, zone_end_pfn;
 
+	/* When hotadd a new node, the node should be empty */
+	if (!node_start_pfn && !node_end_pfn)
+		return 0;
+
 	zone_start_pfn = clamp(node_start_pfn, zone_low, zone_high);
 	zone_end_pfn = clamp(node_end_pfn, zone_low, zone_high);
 
diff --git a/mm/page_owner.c b/mm/page_owner.c
index bd5f842..983c3a1 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -76,6 +76,13 @@
 	__set_bit(PAGE_EXT_OWNER, &page_ext->flags);
 }
 
+gfp_t __get_page_owner_gfp(struct page *page)
+{
+	struct page_ext *page_ext = lookup_page_ext(page);
+
+	return page_ext->gfp_mask;
+}
+
 static ssize_t
 print_page_owner(char __user *buf, size_t count, unsigned long pfn,
 		struct page *page, struct page_ext *page_ext)
diff --git a/mm/shmem.c b/mm/shmem.c
index 4caf8ed..dbe0c1e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3363,8 +3363,8 @@
  * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be
  * 	kernel internal.  There will be NO LSM permission checks against the
  * 	underlying inode.  So users of this interface must do LSM checks at a
- * 	higher layer.  The one user is the big_key implementation.  LSM checks
- * 	are provided at the key level rather than the inode level.
+ *	higher layer.  The users are the big_key and shm implementations.  LSM
+ *	checks are provided at the key or shm level rather than the inode.
  * @name: name for dentry (to be seen in /proc/<pid>/maps
  * @size: size to be set for the file
  * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
diff --git a/mm/slab.c b/mm/slab.c
index 200e224..bbd0b47 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1603,7 +1603,7 @@
 	}
 
 	/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
-	if (unlikely(page->pfmemalloc))
+	if (page_is_pfmemalloc(page))
 		pfmemalloc_active = true;
 
 	nr_pages = (1 << cachep->gfporder);
@@ -1614,7 +1614,7 @@
 		add_zone_page_state(page_zone(page),
 			NR_SLAB_UNRECLAIMABLE, nr_pages);
 	__SetPageSlab(page);
-	if (page->pfmemalloc)
+	if (page_is_pfmemalloc(page))
 		SetPageSlabPfmemalloc(page);
 
 	if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) {
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 3e5f8f2..8683110 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -37,8 +37,7 @@
 		SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \
 		SLAB_FAILSLAB)
 
-#define SLAB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \
-		SLAB_CACHE_DMA | SLAB_NOTRACK)
+#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | SLAB_NOTRACK)
 
 /*
  * Merge control. If this is set then no merging of slab caches will occur.
diff --git a/mm/slub.c b/mm/slub.c
index 816df00..f68c0e5 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1427,7 +1427,7 @@
 	inc_slabs_node(s, page_to_nid(page), page->objects);
 	page->slab_cache = s;
 	__SetPageSlab(page);
-	if (page->pfmemalloc)
+	if (page_is_pfmemalloc(page))
 		SetPageSlabPfmemalloc(page);
 
 	start = page_address(page);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e61445d..8286938 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -973,22 +973,18 @@
 		 *    caller can stall after page list has been processed.
 		 *
 		 * 2) Global or new memcg reclaim encounters a page that is
-		 *    not marked for immediate reclaim or the caller does not
-		 *    have __GFP_IO. In this case mark the page for immediate
+		 *    not marked for immediate reclaim, or the caller does not
+		 *    have __GFP_FS (or __GFP_IO if it's simply going to swap,
+		 *    not to fs). In this case mark the page for immediate
 		 *    reclaim and continue scanning.
 		 *
-		 *    __GFP_IO is checked  because a loop driver thread might
+		 *    Require may_enter_fs because we would wait on fs, which
+		 *    may not have submitted IO yet. And the loop driver might
 		 *    enter reclaim, and deadlock if it waits on a page for
 		 *    which it is needed to do the write (loop masks off
 		 *    __GFP_IO|__GFP_FS for this reason); but more thought
 		 *    would probably show more reasons.
 		 *
-		 *    Don't require __GFP_FS, since we're not going into the
-		 *    FS, just waiting on its writeback completion. Worryingly,
-		 *    ext4 gfs2 and xfs allocate pages with
-		 *    grab_cache_page_write_begin(,,AOP_FLAG_NOFS), so testing
-		 *    may_enter_fs here is liable to OOM on them.
-		 *
 		 * 3) Legacy memcg encounters a page that is not already marked
 		 *    PageReclaim. memcg does not have any dirty pages
 		 *    throttling so we could easily OOM just because too many
@@ -1005,7 +1001,7 @@
 
 			/* Case 2 above */
 			} else if (sane_reclaim(sc) ||
-			    !PageReclaim(page) || !(sc->gfp_mask & __GFP_IO)) {
+			    !PageReclaim(page) || !may_enter_fs) {
 				/*
 				 * This is slightly racy - end_page_writeback()
 				 * might have just cleared PageReclaim, then
diff --git a/net/9p/client.c b/net/9p/client.c
index 498454b..ea79ee9 100644
--- a/net/9p/client.c
+++ b/net/9p/client.c
@@ -1541,6 +1541,7 @@
 	struct p9_client *clnt = fid->clnt;
 	struct p9_req_t *req;
 	int total = 0;
+	*err = 0;
 
 	p9_debug(P9_DEBUG_9P, ">>> TREAD fid %d offset %llu %d\n",
 		   fid->fid, (unsigned long long) offset, (int)iov_iter_count(to));
@@ -1620,6 +1621,7 @@
 	struct p9_client *clnt = fid->clnt;
 	struct p9_req_t *req;
 	int total = 0;
+	*err = 0;
 
 	p9_debug(P9_DEBUG_9P, ">>> TWRITE fid %d offset %llu count %zd\n",
 				fid->fid, (unsigned long long) offset,
diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c
index 9dd49ca..6e70ddb 100644
--- a/net/9p/trans_virtio.c
+++ b/net/9p/trans_virtio.c
@@ -704,6 +704,7 @@
 
 	mutex_unlock(&virtio_9p_lock);
 
+	vdev->config->reset(vdev);
 	vdev->config->del_vqs(vdev);
 
 	sysfs_remove_file(&(vdev->dev.kobj), &dev_attr_mount_tag.attr);
diff --git a/net/ax25/ax25_subr.c b/net/ax25/ax25_subr.c
index 1997538..3b78e84 100644
--- a/net/ax25/ax25_subr.c
+++ b/net/ax25/ax25_subr.c
@@ -264,6 +264,7 @@
 {
 	ax25_clear_queues(ax25);
 
+	ax25_stop_heartbeat(ax25);
 	ax25_stop_t1timer(ax25);
 	ax25_stop_t2timer(ax25);
 	ax25_stop_t3timer(ax25);
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index fb54e6a..6d0b471 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -1138,6 +1138,9 @@
  * @bat_priv: the bat priv with all the soft interface information
  * @skb: packet to check
  * @hdr_size: size of the encapsulation header
+ *
+ * Returns true if the packet was snooped and consumed by DAT. False if the
+ * packet has to be delivered to the interface
  */
 bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv,
 					 struct sk_buff *skb, int hdr_size)
@@ -1145,7 +1148,7 @@
 	uint16_t type;
 	__be32 ip_src, ip_dst;
 	uint8_t *hw_src, *hw_dst;
-	bool ret = false;
+	bool dropped = false;
 	unsigned short vid;
 
 	if (!atomic_read(&bat_priv->distributed_arp_table))
@@ -1174,12 +1177,17 @@
 	/* if this REPLY is directed to a client of mine, let's deliver the
 	 * packet to the interface
 	 */
-	ret = !batadv_is_my_client(bat_priv, hw_dst, vid);
+	dropped = !batadv_is_my_client(bat_priv, hw_dst, vid);
+
+	/* if this REPLY is sent on behalf of a client of mine, let's drop the
+	 * packet because the client will reply by itself
+	 */
+	dropped |= batadv_is_my_client(bat_priv, hw_src, vid);
 out:
-	if (ret)
+	if (dropped)
 		kfree_skb(skb);
-	/* if ret == false -> packet has to be delivered to the interface */
-	return ret;
+	/* if dropped == false -> deliver to the interface */
+	return dropped;
 }
 
 /**
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index bb015862..cffa92d 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -439,6 +439,8 @@
 
 	INIT_HLIST_NODE(&gw_node->list);
 	gw_node->orig_node = orig_node;
+	gw_node->bandwidth_down = ntohl(gateway->bandwidth_down);
+	gw_node->bandwidth_up = ntohl(gateway->bandwidth_up);
 	atomic_set(&gw_node->refcount, 1);
 
 	spin_lock_bh(&bat_priv->gw.list_lock);
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index c002961..a2fc843 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -479,6 +479,9 @@
  */
 void batadv_softif_vlan_free_ref(struct batadv_softif_vlan *vlan)
 {
+	if (!vlan)
+		return;
+
 	if (atomic_dec_and_test(&vlan->refcount)) {
 		spin_lock_bh(&vlan->bat_priv->softif_vlan_list_lock);
 		hlist_del_rcu(&vlan->list);
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index b482495..5809b39 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -594,6 +594,12 @@
 
 	/* increase the refcounter of the related vlan */
 	vlan = batadv_softif_vlan_get(bat_priv, vid);
+	if (WARN(!vlan, "adding TT local entry %pM to non-existent VLAN %d",
+		 addr, BATADV_PRINT_VID(vid))) {
+		kfree(tt_local);
+		tt_local = NULL;
+		goto out;
+	}
 
 	batadv_dbg(BATADV_DBG_TT, bat_priv,
 		   "Creating new local tt entry: %pM (vid: %d, ttvn: %d)\n",
@@ -1034,6 +1040,7 @@
 	struct batadv_tt_local_entry *tt_local_entry;
 	uint16_t flags, curr_flags = BATADV_NO_FLAGS;
 	struct batadv_softif_vlan *vlan;
+	void *tt_entry_exists;
 
 	tt_local_entry = batadv_tt_local_hash_find(bat_priv, addr, vid);
 	if (!tt_local_entry)
@@ -1061,11 +1068,22 @@
 	 * immediately purge it
 	 */
 	batadv_tt_local_event(bat_priv, tt_local_entry, BATADV_TT_CLIENT_DEL);
-	hlist_del_rcu(&tt_local_entry->common.hash_entry);
+
+	tt_entry_exists = batadv_hash_remove(bat_priv->tt.local_hash,
+					     batadv_compare_tt,
+					     batadv_choose_tt,
+					     &tt_local_entry->common);
+	if (!tt_entry_exists)
+		goto out;
+
+	/* extra call to free the local tt entry */
 	batadv_tt_local_entry_free_ref(tt_local_entry);
 
 	/* decrease the reference held for this vlan */
 	vlan = batadv_softif_vlan_get(bat_priv, vid);
+	if (!vlan)
+		goto out;
+
 	batadv_softif_vlan_free_ref(vlan);
 	batadv_softif_vlan_free_ref(vlan);
 
@@ -1166,8 +1184,10 @@
 			/* decrease the reference held for this vlan */
 			vlan = batadv_softif_vlan_get(bat_priv,
 						      tt_common_entry->vid);
-			batadv_softif_vlan_free_ref(vlan);
-			batadv_softif_vlan_free_ref(vlan);
+			if (vlan) {
+				batadv_softif_vlan_free_ref(vlan);
+				batadv_softif_vlan_free_ref(vlan);
+			}
 
 			batadv_tt_local_entry_free_ref(tt_local);
 		}
@@ -3207,8 +3227,10 @@
 
 			/* decrease the reference held for this vlan */
 			vlan = batadv_softif_vlan_get(bat_priv, tt_common->vid);
-			batadv_softif_vlan_free_ref(vlan);
-			batadv_softif_vlan_free_ref(vlan);
+			if (vlan) {
+				batadv_softif_vlan_free_ref(vlan);
+				batadv_softif_vlan_free_ref(vlan);
+			}
 
 			batadv_tt_local_entry_free_ref(tt_local);
 		}
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 7998fb2..92720f3 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -7820,7 +7820,7 @@
 	/* Make sure we copy only the significant bytes based on the
 	 * encryption key size, and set the rest of the value to zeroes.
 	 */
-	memcpy(ev.key.val, key->val, sizeof(key->enc_size));
+	memcpy(ev.key.val, key->val, key->enc_size);
 	memset(ev.key.val + key->enc_size, 0,
 	       sizeof(ev.key.val) - key->enc_size);
 
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 3d0f7d2..ad82324 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -2312,6 +2312,10 @@
 		return 1;
 
 	chan = conn->smp;
+	if (!chan) {
+		BT_ERR("SMP security requested but not available");
+		return 1;
+	}
 
 	if (!hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED))
 		return 1;
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index e97572b..fa7bfce 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -37,14 +37,30 @@
 
 int br_dev_queue_push_xmit(struct sock *sk, struct sk_buff *skb)
 {
-	if (!is_skb_forwardable(skb->dev, skb)) {
-		kfree_skb(skb);
-	} else {
-		skb_push(skb, ETH_HLEN);
-		br_drop_fake_rtable(skb);
-		dev_queue_xmit(skb);
+	if (!is_skb_forwardable(skb->dev, skb))
+		goto drop;
+
+	skb_push(skb, ETH_HLEN);
+	br_drop_fake_rtable(skb);
+	skb_sender_cpu_clear(skb);
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL &&
+	    (skb->protocol == htons(ETH_P_8021Q) ||
+	     skb->protocol == htons(ETH_P_8021AD))) {
+		int depth;
+
+		if (!__vlan_get_protocol(skb, skb->protocol, &depth))
+			goto drop;
+
+		skb_set_network_header(skb, depth);
 	}
 
+	dev_queue_xmit(skb);
+
+	return 0;
+
+drop:
+	kfree_skb(skb);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(br_dev_queue_push_xmit);
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index e29ad70..c943219 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -323,6 +323,7 @@
 	struct net_bridge_port_group *p;
 	struct net_bridge_port_group __rcu **pp;
 	struct net_bridge_mdb_htable *mdb;
+	unsigned long now = jiffies;
 	int err;
 
 	mdb = mlock_dereference(br->mdb, br);
@@ -347,8 +348,9 @@
 	if (unlikely(!p))
 		return -ENOMEM;
 	rcu_assign_pointer(*pp, p);
+	if (state == MDB_TEMPORARY)
+		mod_timer(&p->timer, now + br->multicast_membership_interval);
 
-	br_mdb_notify(br->dev, port, group, RTM_NEWMDB);
 	return 0;
 }
 
@@ -371,6 +373,7 @@
 	if (!p || p->br != br || p->state == BR_STATE_DISABLED)
 		return -EINVAL;
 
+	memset(&ip, 0, sizeof(ip));
 	ip.proto = entry->addr.proto;
 	if (ip.proto == htons(ETH_P_IP))
 		ip.u.ip4 = entry->addr.u.ip4;
@@ -417,20 +420,14 @@
 	if (!netif_running(br->dev) || br->multicast_disabled)
 		return -EINVAL;
 
+	memset(&ip, 0, sizeof(ip));
 	ip.proto = entry->addr.proto;
-	if (ip.proto == htons(ETH_P_IP)) {
-		if (timer_pending(&br->ip4_other_query.timer))
-			return -EBUSY;
-
+	if (ip.proto == htons(ETH_P_IP))
 		ip.u.ip4 = entry->addr.u.ip4;
 #if IS_ENABLED(CONFIG_IPV6)
-	} else {
-		if (timer_pending(&br->ip6_other_query.timer))
-			return -EBUSY;
-
+	else
 		ip.u.ip6 = entry->addr.u.ip6;
 #endif
-	}
 
 	spin_lock_bh(&br->multicast_lock);
 	mdb = mlock_dereference(br->mdb, br);
@@ -448,6 +445,7 @@
 		if (p->port->state == BR_STATE_DISABLED)
 			goto unlock;
 
+		entry->state = p->state;
 		rcu_assign_pointer(*pp, p->next);
 		hlist_del_init(&p->mglist);
 		del_timer(&p->timer);
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 742a6c2..1285eaf 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -39,6 +39,16 @@
 				       struct bridge_mcast_own_query *query);
 static void br_multicast_add_router(struct net_bridge *br,
 				    struct net_bridge_port *port);
+static void br_ip4_multicast_leave_group(struct net_bridge *br,
+					 struct net_bridge_port *port,
+					 __be32 group,
+					 __u16 vid);
+#if IS_ENABLED(CONFIG_IPV6)
+static void br_ip6_multicast_leave_group(struct net_bridge *br,
+					 struct net_bridge_port *port,
+					 const struct in6_addr *group,
+					 __u16 vid);
+#endif
 unsigned int br_mdb_rehash_seq;
 
 static inline int br_ip_equal(const struct br_ip *a, const struct br_ip *b)
@@ -1010,9 +1020,15 @@
 			continue;
 		}
 
-		err = br_ip4_multicast_add_group(br, port, group, vid);
-		if (err)
-			break;
+		if ((type == IGMPV3_CHANGE_TO_INCLUDE ||
+		     type == IGMPV3_MODE_IS_INCLUDE) &&
+		    ntohs(grec->grec_nsrcs) == 0) {
+			br_ip4_multicast_leave_group(br, port, group, vid);
+		} else {
+			err = br_ip4_multicast_add_group(br, port, group, vid);
+			if (err)
+				break;
+		}
 	}
 
 	return err;
@@ -1071,10 +1087,17 @@
 			continue;
 		}
 
-		err = br_ip6_multicast_add_group(br, port, &grec->grec_mca,
-						 vid);
-		if (err)
-			break;
+		if ((grec->grec_type == MLD2_CHANGE_TO_INCLUDE ||
+		     grec->grec_type == MLD2_MODE_IS_INCLUDE) &&
+		    ntohs(*nsrcs) == 0) {
+			br_ip6_multicast_leave_group(br, port, &grec->grec_mca,
+						     vid);
+		} else {
+			err = br_ip6_multicast_add_group(br, port,
+							 &grec->grec_mca, vid);
+			if (!err)
+				break;
+		}
 	}
 
 	return err;
@@ -1393,8 +1416,7 @@
 
 	spin_lock(&br->multicast_lock);
 	if (!netif_running(br->dev) ||
-	    (port && port->state == BR_STATE_DISABLED) ||
-	    timer_pending(&other_query->timer))
+	    (port && port->state == BR_STATE_DISABLED))
 		goto out;
 
 	mdb = mlock_dereference(br->mdb, br);
@@ -1402,6 +1424,31 @@
 	if (!mp)
 		goto out;
 
+	if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) {
+		struct net_bridge_port_group __rcu **pp;
+
+		for (pp = &mp->ports;
+		     (p = mlock_dereference(*pp, br)) != NULL;
+		     pp = &p->next) {
+			if (p->port != port)
+				continue;
+
+			rcu_assign_pointer(*pp, p->next);
+			hlist_del_init(&p->mglist);
+			del_timer(&p->timer);
+			call_rcu_bh(&p->rcu, br_multicast_free_pg);
+			br_mdb_notify(br->dev, port, group, RTM_DELMDB);
+
+			if (!mp->ports && !mp->mglist &&
+			    netif_running(br->dev))
+				mod_timer(&mp->timer, jiffies);
+		}
+		goto out;
+	}
+
+	if (timer_pending(&other_query->timer))
+		goto out;
+
 	if (br->multicast_querier) {
 		__br_multicast_send_query(br, port, &mp->addr);
 
@@ -1427,28 +1474,6 @@
 		}
 	}
 
-	if (port && (port->flags & BR_MULTICAST_FAST_LEAVE)) {
-		struct net_bridge_port_group __rcu **pp;
-
-		for (pp = &mp->ports;
-		     (p = mlock_dereference(*pp, br)) != NULL;
-		     pp = &p->next) {
-			if (p->port != port)
-				continue;
-
-			rcu_assign_pointer(*pp, p->next);
-			hlist_del_init(&p->mglist);
-			del_timer(&p->timer);
-			call_rcu_bh(&p->rcu, br_multicast_free_pg);
-			br_mdb_notify(br->dev, port, group, RTM_DELMDB);
-
-			if (!mp->ports && !mp->mglist &&
-			    netif_running(br->dev))
-				mod_timer(&mp->timer, jiffies);
-		}
-		goto out;
-	}
-
 	now = jiffies;
 	time = now + br->multicast_last_member_count *
 		     br->multicast_last_member_interval;
@@ -1566,7 +1591,7 @@
 		break;
 	}
 
-	if (skb_trimmed)
+	if (skb_trimmed && skb_trimmed != skb)
 		kfree_skb(skb_trimmed);
 
 	return err;
@@ -1611,7 +1636,7 @@
 		break;
 	}
 
-	if (skb_trimmed)
+	if (skb_trimmed && skb_trimmed != skb)
 		kfree_skb(skb_trimmed);
 
 	return err;
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index d89f4fa..c8b9bcf 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -111,7 +111,7 @@
 /* largest possible L2 header, see br_nf_dev_queue_xmit() */
 #define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN)
 
-#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4) || IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)
 struct brnf_frag_data {
 	char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH];
 	u8 encap_size;
@@ -694,6 +694,7 @@
 }
 #endif
 
+#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV4)
 static int br_nf_ip_fragment(struct sock *sk, struct sk_buff *skb,
 			     int (*output)(struct sock *, struct sk_buff *))
 {
@@ -712,6 +713,7 @@
 
 	return ip_do_fragment(sk, skb, output);
 }
+#endif
 
 static unsigned int nf_bridge_mtu_reduction(const struct sk_buff *skb)
 {
@@ -742,7 +744,7 @@
 		struct brnf_frag_data *data;
 
 		if (br_validate_ipv4(skb))
-			return NF_DROP;
+			goto drop;
 
 		IPCB(skb)->frag_max_size = nf_bridge->frag_max_size;
 
@@ -767,7 +769,7 @@
 		struct brnf_frag_data *data;
 
 		if (br_validate_ipv6(skb))
-			return NF_DROP;
+			goto drop;
 
 		IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size;
 
@@ -782,12 +784,16 @@
 
 		if (v6ops)
 			return v6ops->fragment(sk, skb, br_nf_push_frag_xmit);
-		else
-			return -EMSGSIZE;
+
+		kfree_skb(skb);
+		return -EMSGSIZE;
 	}
 #endif
 	nf_bridge_info_free(skb);
 	return br_dev_queue_push_xmit(sk, skb);
+ drop:
+	kfree_skb(skb);
+	return 0;
 }
 
 /* PF_BRIDGE/POST_ROUTING ********************************************/
diff --git a/net/bridge/br_netfilter_ipv6.c b/net/bridge/br_netfilter_ipv6.c
index 6d12d26..13b7d1e 100644
--- a/net/bridge/br_netfilter_ipv6.c
+++ b/net/bridge/br_netfilter_ipv6.c
@@ -104,7 +104,7 @@
 {
 	const struct ipv6hdr *hdr;
 	struct net_device *dev = skb->dev;
-	struct inet6_dev *idev = in6_dev_get(skb->dev);
+	struct inet6_dev *idev = __in6_dev_get(skb->dev);
 	u32 pkt_len;
 	u8 ip6h_len = sizeof(struct ipv6hdr);
 
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 6b67ed3..4d74a06 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -112,6 +112,8 @@
 		+ nla_total_size(1)	/* IFLA_BRPORT_FAST_LEAVE */
 		+ nla_total_size(1)	/* IFLA_BRPORT_LEARNING */
 		+ nla_total_size(1)	/* IFLA_BRPORT_UNICAST_FLOOD */
+		+ nla_total_size(1)	/* IFLA_BRPORT_PROXYARP */
+		+ nla_total_size(1)	/* IFLA_BRPORT_PROXYARP_WIFI */
 		+ 0;
 }
 
@@ -457,6 +459,8 @@
 		if (nla_len(attr) != sizeof(struct bridge_vlan_info))
 			return -EINVAL;
 		vinfo = nla_data(attr);
+		if (!vinfo->vid || vinfo->vid >= VLAN_VID_MASK)
+			return -EINVAL;
 		if (vinfo->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) {
 			if (vinfo_start)
 				return -EINVAL;
@@ -504,6 +508,8 @@
 	[IFLA_BRPORT_FAST_LEAVE]= { .type = NLA_U8 },
 	[IFLA_BRPORT_LEARNING]	= { .type = NLA_U8 },
 	[IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 },
+	[IFLA_BRPORT_PROXYARP]	= { .type = NLA_U8 },
+	[IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 },
 };
 
 /* Change the state of the port and notify spanning tree */
@@ -691,9 +697,17 @@
 				    struct nlattr *tb[],
 				    struct nlattr *data[])
 {
+	struct net_bridge *br = netdev_priv(brdev);
+	int ret;
+
 	if (!data)
 		return 0;
-	return br_setport(br_port_get_rtnl(dev), data);
+
+	spin_lock_bh(&br->lock);
+	ret = br_setport(br_port_get_rtnl(dev), data);
+	spin_unlock_bh(&br->lock);
+
+	return ret;
 }
 
 static int br_port_fill_slave_info(struct sk_buff *skb,
diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c
index b4b6dab..ed74ffa 100644
--- a/net/bridge/br_stp.c
+++ b/net/bridge/br_stp.c
@@ -209,8 +209,9 @@
 		br_send_config_bpdu(p, &bpdu);
 		p->topology_change_ack = 0;
 		p->config_pending = 0;
-		mod_timer(&p->hold_timer,
-			  round_jiffies(jiffies + BR_HOLD_TIME));
+		if (p->br->stp_enabled == BR_KERNEL_STP)
+			mod_timer(&p->hold_timer,
+				  round_jiffies(jiffies + BR_HOLD_TIME));
 	}
 }
 
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index a2730e7..4ca449a 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -48,7 +48,8 @@
 	struct net_bridge_port *p;
 
 	spin_lock_bh(&br->lock);
-	mod_timer(&br->hello_timer, jiffies + br->hello_time);
+	if (br->stp_enabled == BR_KERNEL_STP)
+		mod_timer(&br->hello_timer, jiffies + br->hello_time);
 	mod_timer(&br->gc_timer, jiffies + HZ/10);
 
 	br_config_bpdu_generation(br);
@@ -127,6 +128,7 @@
 	int r;
 	char *argv[] = { BR_STP_PROG, br->dev->name, "start", NULL };
 	char *envp[] = { NULL };
+	struct net_bridge_port *p;
 
 	r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
 
@@ -140,6 +142,10 @@
 	if (r == 0) {
 		br->stp_enabled = BR_USER_STP;
 		br_debug(br, "userspace STP started\n");
+		/* Stop hello and hold timers */
+		del_timer(&br->hello_timer);
+		list_for_each_entry(p, &br->port_list, list)
+			del_timer(&p->hold_timer);
 	} else {
 		br->stp_enabled = BR_KERNEL_STP;
 		br_debug(br, "using kernel STP\n");
@@ -156,12 +162,17 @@
 	int r;
 	char *argv[] = { BR_STP_PROG, br->dev->name, "stop", NULL };
 	char *envp[] = { NULL };
+	struct net_bridge_port *p;
 
 	if (br->stp_enabled == BR_USER_STP) {
 		r = call_usermodehelper(BR_STP_PROG, argv, envp, UMH_WAIT_PROC);
 		br_info(br, "userspace STP stopped, return code %d\n", r);
 
 		/* To start timers on any ports left in blocking */
+		mod_timer(&br->hello_timer, jiffies + br->hello_time);
+		list_for_each_entry(p, &br->port_list, list)
+			mod_timer(&p->hold_timer,
+				  round_jiffies(jiffies + BR_HOLD_TIME));
 		spin_lock_bh(&br->lock);
 		br_port_state_selection(br);
 		spin_unlock_bh(&br->lock);
diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c
index 7caf7fa..5f0f5af 100644
--- a/net/bridge/br_stp_timer.c
+++ b/net/bridge/br_stp_timer.c
@@ -40,7 +40,9 @@
 	if (br->dev->flags & IFF_UP) {
 		br_config_bpdu_generation(br);
 
-		mod_timer(&br->hello_timer, round_jiffies(jiffies + br->hello_time));
+		if (br->stp_enabled != BR_USER_STP)
+			mod_timer(&br->hello_timer,
+				  round_jiffies(jiffies + br->hello_time));
 	}
 	spin_unlock(&br->lock);
 }
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index 3cc71b9..cc85891 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -121,12 +121,13 @@
  * Copied from sock.c:sock_queue_rcv_skb(), but changed so packets are
  * not dropped, but CAIF is sending flow off instead.
  */
-static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+static void caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	int err;
 	unsigned long flags;
 	struct sk_buff_head *list = &sk->sk_receive_queue;
 	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
+	bool queued = false;
 
 	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
 		(unsigned int)sk->sk_rcvbuf && rx_flow_is_on(cf_sk)) {
@@ -139,7 +140,8 @@
 
 	err = sk_filter(sk, skb);
 	if (err)
-		return err;
+		goto out;
+
 	if (!sk_rmem_schedule(sk, skb, skb->truesize) && rx_flow_is_on(cf_sk)) {
 		set_rx_flow_off(cf_sk);
 		net_dbg_ratelimited("sending flow OFF due to rmem_schedule\n");
@@ -147,21 +149,16 @@
 	}
 	skb->dev = NULL;
 	skb_set_owner_r(skb, sk);
-	/* Cache the SKB length before we tack it onto the receive
-	 * queue. Once it is added it no longer belongs to us and
-	 * may be freed by other threads of control pulling packets
-	 * from the queue.
-	 */
 	spin_lock_irqsave(&list->lock, flags);
-	if (!sock_flag(sk, SOCK_DEAD))
+	queued = !sock_flag(sk, SOCK_DEAD);
+	if (queued)
 		__skb_queue_tail(list, skb);
 	spin_unlock_irqrestore(&list->lock, flags);
-
-	if (!sock_flag(sk, SOCK_DEAD))
+out:
+	if (queued)
 		sk->sk_data_ready(sk);
 	else
 		kfree_skb(skb);
-	return 0;
 }
 
 /* Packet Receive Callback function called from CAIF Stack */
diff --git a/net/can/af_can.c b/net/can/af_can.c
index 7933e62..166d436 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -89,6 +89,8 @@
 struct s_stats    can_stats;       /* packet statistics */
 struct s_pstats   can_pstats;      /* receive list statistics */
 
+static atomic_t skbcounter = ATOMIC_INIT(0);
+
 /*
  * af_can socket functions
  */
@@ -310,12 +312,8 @@
 		return err;
 	}
 
-	if (newskb) {
-		if (!(newskb->tstamp.tv64))
-			__net_timestamp(newskb);
-
+	if (newskb)
 		netif_rx_ni(newskb);
-	}
 
 	/* update statistics */
 	can_stats.tx_frames++;
@@ -683,6 +681,10 @@
 	can_stats.rx_frames++;
 	can_stats.rx_frames_delta++;
 
+	/* create non-zero unique skb identifier together with *skb */
+	while (!(can_skb_prv(skb)->skbcnt))
+		can_skb_prv(skb)->skbcnt = atomic_inc_return(&skbcounter);
+
 	rcu_read_lock();
 
 	/* deliver the packet to sockets listening on all devices */
diff --git a/net/can/bcm.c b/net/can/bcm.c
index b523453..a1ba687 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -261,6 +261,7 @@
 
 	can_skb_reserve(skb);
 	can_skb_prv(skb)->ifindex = dev->ifindex;
+	can_skb_prv(skb)->skbcnt = 0;
 
 	memcpy(skb_put(skb, CFSIZ), cf, CFSIZ);
 
@@ -1217,6 +1218,7 @@
 	}
 
 	can_skb_prv(skb)->ifindex = dev->ifindex;
+	can_skb_prv(skb)->skbcnt = 0;
 	skb->dev = dev;
 	can_skb_set_owner(skb, sk);
 	err = can_send(skb, 1); /* send with loopback */
diff --git a/net/can/raw.c b/net/can/raw.c
index 31b9748..2e67b14 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -75,7 +75,7 @@
  */
 
 struct uniqframe {
-	ktime_t tstamp;
+	int skbcnt;
 	const struct sk_buff *skb;
 	unsigned int join_rx_count;
 };
@@ -133,7 +133,7 @@
 
 	/* eliminate multiple filter matches for the same skb */
 	if (this_cpu_ptr(ro->uniq)->skb == oskb &&
-	    ktime_equal(this_cpu_ptr(ro->uniq)->tstamp, oskb->tstamp)) {
+	    this_cpu_ptr(ro->uniq)->skbcnt == can_skb_prv(oskb)->skbcnt) {
 		if (ro->join_filters) {
 			this_cpu_inc(ro->uniq->join_rx_count);
 			/* drop frame until all enabled filters matched */
@@ -144,7 +144,7 @@
 		}
 	} else {
 		this_cpu_ptr(ro->uniq)->skb = oskb;
-		this_cpu_ptr(ro->uniq)->tstamp = oskb->tstamp;
+		this_cpu_ptr(ro->uniq)->skbcnt = can_skb_prv(oskb)->skbcnt;
 		this_cpu_ptr(ro->uniq)->join_rx_count = 1;
 		/* drop first frame to check all enabled filters? */
 		if (ro->join_filters && ro->count > 1)
@@ -749,6 +749,7 @@
 
 	can_skb_reserve(skb);
 	can_skb_prv(skb)->ifindex = dev->ifindex;
+	can_skb_prv(skb)->skbcnt = 0;
 
 	err = memcpy_from_msg(skb_put(skb, size), msg, size);
 	if (err < 0)
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index cb7db32..f30329f 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -9,6 +9,7 @@
 #include <keys/ceph-type.h>
 #include <linux/module.h>
 #include <linux/mount.h>
+#include <linux/nsproxy.h>
 #include <linux/parser.h>
 #include <linux/sched.h>
 #include <linux/seq_file.h>
@@ -16,8 +17,6 @@
 #include <linux/statfs.h>
 #include <linux/string.h>
 #include <linux/vmalloc.h>
-#include <linux/nsproxy.h>
-#include <net/net_namespace.h>
 
 
 #include <linux/ceph/ceph_features.h>
@@ -131,6 +130,13 @@
 	int i;
 	int ret;
 
+	/*
+	 * Don't bother comparing options if network namespaces don't
+	 * match.
+	 */
+	if (!net_eq(current->nsproxy->net_ns, read_pnet(&client->msgr.net)))
+		return -1;
+
 	ret = memcmp(opt1, opt2, ofs);
 	if (ret)
 		return ret;
@@ -335,9 +341,6 @@
 	int err = -ENOMEM;
 	substring_t argstr[MAX_OPT_ARGS];
 
-	if (current->nsproxy->net_ns != &init_net)
-		return ERR_PTR(-EINVAL);
-
 	opt = kzalloc(sizeof(*opt), GFP_KERNEL);
 	if (!opt)
 		return ERR_PTR(-ENOMEM);
@@ -608,6 +611,7 @@
 fail_monc:
 	ceph_monc_stop(&client->monc);
 fail:
+	ceph_messenger_fini(&client->msgr);
 	kfree(client);
 	return ERR_PTR(err);
 }
@@ -621,8 +625,8 @@
 
 	/* unmount */
 	ceph_osdc_stop(&client->osdc);
-
 	ceph_monc_stop(&client->monc);
+	ceph_messenger_fini(&client->msgr);
 
 	ceph_debugfs_client_cleanup(client);
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 1679f47..e3be1d22 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -6,6 +6,7 @@
 #include <linux/inet.h>
 #include <linux/kthread.h>
 #include <linux/net.h>
+#include <linux/nsproxy.h>
 #include <linux/slab.h>
 #include <linux/socket.h>
 #include <linux/string.h>
@@ -479,7 +480,7 @@
 	int ret;
 
 	BUG_ON(con->sock);
-	ret = sock_create_kern(&init_net, con->peer_addr.in_addr.ss_family,
+	ret = sock_create_kern(read_pnet(&con->msgr->net), paddr->ss_family,
 			       SOCK_STREAM, IPPROTO_TCP, &sock);
 	if (ret)
 		return ret;
@@ -1731,17 +1732,17 @@
 
 static bool addr_is_blank(struct sockaddr_storage *ss)
 {
+	struct in_addr *addr = &((struct sockaddr_in *)ss)->sin_addr;
+	struct in6_addr *addr6 = &((struct sockaddr_in6 *)ss)->sin6_addr;
+
 	switch (ss->ss_family) {
 	case AF_INET:
-		return ((struct sockaddr_in *)ss)->sin_addr.s_addr == 0;
+		return addr->s_addr == htonl(INADDR_ANY);
 	case AF_INET6:
-		return
-		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[0] == 0 &&
-		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[1] == 0 &&
-		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[2] == 0 &&
-		     ((struct sockaddr_in6 *)ss)->sin6_addr.s6_addr32[3] == 0;
+		return ipv6_addr_any(addr6);
+	default:
+		return true;
 	}
-	return false;
 }
 
 static int addr_port(struct sockaddr_storage *ss)
@@ -2944,11 +2945,18 @@
 	msgr->tcp_nodelay = tcp_nodelay;
 
 	atomic_set(&msgr->stopping, 0);
+	write_pnet(&msgr->net, get_net(current->nsproxy->net_ns));
 
 	dout("%s %p\n", __func__, msgr);
 }
 EXPORT_SYMBOL(ceph_messenger_init);
 
+void ceph_messenger_fini(struct ceph_messenger *msgr)
+{
+	put_net(read_pnet(&msgr->net));
+}
+EXPORT_SYMBOL(ceph_messenger_fini);
+
 static void clear_standby(struct ceph_connection *con)
 {
 	/* come back from STANDBY? */
diff --git a/net/core/datagram.c b/net/core/datagram.c
index b80fb91..617088a 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -131,6 +131,35 @@
 	goto out;
 }
 
+static struct sk_buff *skb_set_peeked(struct sk_buff *skb)
+{
+	struct sk_buff *nskb;
+
+	if (skb->peeked)
+		return skb;
+
+	/* We have to unshare an skb before modifying it. */
+	if (!skb_shared(skb))
+		goto done;
+
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (!nskb)
+		return ERR_PTR(-ENOMEM);
+
+	skb->prev->next = nskb;
+	skb->next->prev = nskb;
+	nskb->prev = skb->prev;
+	nskb->next = skb->next;
+
+	consume_skb(skb);
+	skb = nskb;
+
+done:
+	skb->peeked = 1;
+
+	return skb;
+}
+
 /**
  *	__skb_recv_datagram - Receive a datagram skbuff
  *	@sk: socket
@@ -165,7 +194,9 @@
 struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 				    int *peeked, int *off, int *err)
 {
+	struct sk_buff_head *queue = &sk->sk_receive_queue;
 	struct sk_buff *skb, *last;
+	unsigned long cpu_flags;
 	long timeo;
 	/*
 	 * Caller is allowed not to check sk->sk_err before skb_recv_datagram()
@@ -184,8 +215,6 @@
 		 * Look at current nfs client by the way...
 		 * However, this function was correct in any case. 8)
 		 */
-		unsigned long cpu_flags;
-		struct sk_buff_head *queue = &sk->sk_receive_queue;
 		int _off = *off;
 
 		last = (struct sk_buff *)queue;
@@ -199,7 +228,12 @@
 					_off -= skb->len;
 					continue;
 				}
-				skb->peeked = 1;
+
+				skb = skb_set_peeked(skb);
+				error = PTR_ERR(skb);
+				if (IS_ERR(skb))
+					goto unlock_err;
+
 				atomic_inc(&skb->users);
 			} else
 				__skb_unlink(skb, queue);
@@ -223,6 +257,8 @@
 
 	return NULL;
 
+unlock_err:
+	spin_unlock_irqrestore(&queue->lock, cpu_flags);
 no_packet:
 	*err = error;
 	return NULL;
@@ -622,7 +658,8 @@
 		    !skb->csum_complete_sw)
 			netdev_rx_csum_fault(skb->dev);
 	}
-	skb->csum_valid = !sum;
+	if (!skb_shared(skb))
+		skb->csum_valid = !sum;
 	return sum;
 }
 EXPORT_SYMBOL(__skb_checksum_complete_head);
@@ -642,11 +679,13 @@
 			netdev_rx_csum_fault(skb->dev);
 	}
 
-	/* Save full packet checksum */
-	skb->csum = csum;
-	skb->ip_summed = CHECKSUM_COMPLETE;
-	skb->csum_complete_sw = 1;
-	skb->csum_valid = !sum;
+	if (!skb_shared(skb)) {
+		/* Save full packet checksum */
+		skb->csum = csum;
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		skb->csum_complete_sw = 1;
+		skb->csum_valid = !sum;
+	}
 
 	return sum;
 }
diff --git a/net/core/dev.c b/net/core/dev.c
index 6778a99..a8e4dd4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -677,10 +677,6 @@
 	if (dev->netdev_ops && dev->netdev_ops->ndo_get_iflink)
 		return dev->netdev_ops->ndo_get_iflink(dev);
 
-	/* If dev->rtnl_link_ops is set, it's a virtual interface. */
-	if (dev->rtnl_link_ops)
-		return 0;
-
 	return dev->ifindex;
 }
 EXPORT_SYMBOL(dev_get_iflink);
@@ -3452,6 +3448,8 @@
 	local_irq_save(flags);
 
 	rps_lock(sd);
+	if (!netif_running(skb->dev))
+		goto drop;
 	qlen = skb_queue_len(&sd->input_pkt_queue);
 	if (qlen <= netdev_max_backlog && !skb_flow_limit(skb, qlen)) {
 		if (qlen) {
@@ -3473,6 +3471,7 @@
 		goto enqueue;
 	}
 
+drop:
 	sd->dropped++;
 	rps_unlock(sd);
 
@@ -3775,8 +3774,6 @@
 
 	pt_prev = NULL;
 
-	rcu_read_lock();
-
 another_round:
 	skb->skb_iif = skb->dev->ifindex;
 
@@ -3786,7 +3783,7 @@
 	    skb->protocol == cpu_to_be16(ETH_P_8021AD)) {
 		skb = skb_vlan_untag(skb);
 		if (unlikely(!skb))
-			goto unlock;
+			goto out;
 	}
 
 #ifdef CONFIG_NET_CLS_ACT
@@ -3816,10 +3813,10 @@
 	if (static_key_false(&ingress_needed)) {
 		skb = handle_ing(skb, &pt_prev, &ret, orig_dev);
 		if (!skb)
-			goto unlock;
+			goto out;
 
 		if (nf_ingress(skb, &pt_prev, &ret, orig_dev) < 0)
-			goto unlock;
+			goto out;
 	}
 #endif
 #ifdef CONFIG_NET_CLS_ACT
@@ -3837,7 +3834,7 @@
 		if (vlan_do_receive(&skb))
 			goto another_round;
 		else if (unlikely(!skb))
-			goto unlock;
+			goto out;
 	}
 
 	rx_handler = rcu_dereference(skb->dev->rx_handler);
@@ -3849,7 +3846,7 @@
 		switch (rx_handler(&skb)) {
 		case RX_HANDLER_CONSUMED:
 			ret = NET_RX_SUCCESS;
-			goto unlock;
+			goto out;
 		case RX_HANDLER_ANOTHER:
 			goto another_round;
 		case RX_HANDLER_EXACT:
@@ -3903,8 +3900,7 @@
 		ret = NET_RX_DROP;
 	}
 
-unlock:
-	rcu_read_unlock();
+out:
 	return ret;
 }
 
@@ -3935,29 +3931,30 @@
 
 static int netif_receive_skb_internal(struct sk_buff *skb)
 {
+	int ret;
+
 	net_timestamp_check(netdev_tstamp_prequeue, skb);
 
 	if (skb_defer_rx_timestamp(skb))
 		return NET_RX_SUCCESS;
 
+	rcu_read_lock();
+
 #ifdef CONFIG_RPS
 	if (static_key_false(&rps_needed)) {
 		struct rps_dev_flow voidflow, *rflow = &voidflow;
-		int cpu, ret;
-
-		rcu_read_lock();
-
-		cpu = get_rps_cpu(skb->dev, skb, &rflow);
+		int cpu = get_rps_cpu(skb->dev, skb, &rflow);
 
 		if (cpu >= 0) {
 			ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
 			rcu_read_unlock();
 			return ret;
 		}
-		rcu_read_unlock();
 	}
 #endif
-	return __netif_receive_skb(skb);
+	ret = __netif_receive_skb(skb);
+	rcu_read_unlock();
+	return ret;
 }
 
 /**
@@ -4502,8 +4499,10 @@
 		struct sk_buff *skb;
 
 		while ((skb = __skb_dequeue(&sd->process_queue))) {
+			rcu_read_lock();
 			local_irq_enable();
 			__netif_receive_skb(skb);
+			rcu_read_unlock();
 			local_irq_disable();
 			input_queue_head_incr(sd);
 			if (++work >= quota) {
@@ -6139,6 +6138,7 @@
 		unlist_netdevice(dev);
 
 		dev->reg_state = NETREG_UNREGISTERING;
+		on_each_cpu(flush_backlog, dev, 1);
 	}
 
 	synchronize_net();
@@ -6409,7 +6409,8 @@
 	struct netdev_queue *tx;
 	size_t sz = count * sizeof(*tx);
 
-	BUG_ON(count < 1 || count > 0xffff);
+	if (count < 1 || count > 0xffff)
+		return -EINVAL;
 
 	tx = kzalloc(sz, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
 	if (!tx) {
@@ -6773,8 +6774,6 @@
 
 		dev->reg_state = NETREG_UNREGISTERED;
 
-		on_each_cpu(flush_backlog, dev, 1);
-
 		netdev_wait_allrefs(dev);
 
 		/* paranoia */
diff --git a/net/core/dst.c b/net/core/dst.c
index e956ce6..002144be 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -284,7 +284,9 @@
 		int newrefcnt;
 
 		newrefcnt = atomic_dec_return(&dst->__refcnt);
-		WARN_ON(newrefcnt < 0);
+		if (unlikely(newrefcnt < 0))
+			net_warn_ratelimited("%s: dst:%p refcnt:%d\n",
+					     __func__, dst, newrefcnt);
 		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt)
 			call_rcu(&dst->rcu_head, dst_destroy_rcu);
 	}
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 9dfb88a..92d886f 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -66,7 +66,7 @@
 
    NOTES.
 
-   * avbps is scaled by 2^5, avpps is scaled by 2^10.
+   * avbps and avpps are scaled by 2^5.
    * both values are reported as 32 bit unsigned values. bps can
      overflow for fast links : max speed being 34360Mbit/sec
    * Minimal interval is HZ/4=250msec (it is the greatest common divisor
@@ -85,10 +85,10 @@
 	struct gnet_stats_rate_est64	*rate_est;
 	spinlock_t		*stats_lock;
 	int			ewma_log;
+	u32			last_packets;
+	unsigned long		avpps;
 	u64			last_bytes;
 	u64			avbps;
-	u32			last_packets;
-	u32			avpps;
 	struct rcu_head		e_rcu;
 	struct rb_node		node;
 	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
@@ -118,8 +118,8 @@
 	rcu_read_lock();
 	list_for_each_entry_rcu(e, &elist[idx].list, list) {
 		struct gnet_stats_basic_packed b = {0};
+		unsigned long rate;
 		u64 brate;
-		u32 rate;
 
 		spin_lock(e->stats_lock);
 		read_lock(&est_lock);
@@ -133,10 +133,11 @@
 		e->avbps += (brate >> e->ewma_log) - (e->avbps >> e->ewma_log);
 		e->rate_est->bps = (e->avbps+0xF)>>5;
 
-		rate = (b.packets - e->last_packets)<<(12 - idx);
+		rate = b.packets - e->last_packets;
+		rate <<= (7 - idx);
 		e->last_packets = b.packets;
 		e->avpps += (rate >> e->ewma_log) - (e->avpps >> e->ewma_log);
-		e->rate_est->pps = (e->avpps+0x1FF)>>10;
+		e->rate_est->pps = (e->avpps + 0xF) >> 5;
 skip:
 		read_unlock(&est_lock);
 		spin_unlock(e->stats_lock);
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 1f2a126..6441f47 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -23,7 +23,8 @@
 
 struct cgroup_cls_state *task_cls_state(struct task_struct *p)
 {
-	return css_cls_state(task_css(p, net_cls_cgrp_id));
+	return css_cls_state(task_css_check(p, net_cls_cgrp_id,
+					    rcu_read_lock_bh_held()));
 }
 EXPORT_SYMBOL_GPL(task_cls_state);
 
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 05badbb..1cbd209 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3514,8 +3514,6 @@
 
 	set_freezable();
 
-	__set_current_state(TASK_RUNNING);
-
 	while (!kthread_should_stop()) {
 		pkt_dev = next_to_run(t);
 
@@ -3560,7 +3558,6 @@
 
 		try_to_freeze();
 	}
-	set_current_state(TASK_INTERRUPTIBLE);
 
 	pr_debug("%s stopping all device\n", t->tsk->comm);
 	pktgen_stop(t);
@@ -3571,13 +3568,6 @@
 	pr_debug("%s removing thread\n", t->tsk->comm);
 	pktgen_rem_thread(t);
 
-	/* Wait for kthread_stop */
-	while (!kthread_should_stop()) {
-		set_current_state(TASK_INTERRUPTIBLE);
-		schedule();
-	}
-	__set_current_state(TASK_RUNNING);
-
 	return 0;
 }
 
@@ -3769,6 +3759,7 @@
 	}
 
 	t->net = pn;
+	get_task_struct(p);
 	wake_up_process(p);
 	wait_for_completion(&t->start_done);
 
@@ -3891,6 +3882,7 @@
 		t = list_entry(q, struct pktgen_thread, th_list);
 		list_del(&t->th_list);
 		kthread_stop(t->tsk);
+		put_task_struct(t->tsk);
 		kfree(t);
 	}
 
diff --git a/net/core/request_sock.c b/net/core/request_sock.c
index 87b22c0..b42f0e2 100644
--- a/net/core/request_sock.c
+++ b/net/core/request_sock.c
@@ -103,10 +103,16 @@
 			spin_lock_bh(&queue->syn_wait_lock);
 			while ((req = lopt->syn_table[i]) != NULL) {
 				lopt->syn_table[i] = req->dl_next;
+				/* Because of following del_timer_sync(),
+				 * we must release the spinlock here
+				 * or risk a dead lock.
+				 */
+				spin_unlock_bh(&queue->syn_wait_lock);
 				atomic_inc(&lopt->qlen_dec);
-				if (del_timer(&req->rsk_timer))
+				if (del_timer_sync(&req->rsk_timer))
 					reqsk_put(req);
 				reqsk_put(req);
+				spin_lock_bh(&queue->syn_wait_lock);
 			}
 			spin_unlock_bh(&queue->syn_wait_lock);
 		}
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 01ced4a..dc004b1 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1328,10 +1328,6 @@
 	[IFLA_INFO_SLAVE_DATA]	= { .type = NLA_NESTED },
 };
 
-static const struct nla_policy ifla_vfinfo_policy[IFLA_VF_INFO_MAX+1] = {
-	[IFLA_VF_INFO]		= { .type = NLA_NESTED },
-};
-
 static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = {
 	[IFLA_VF_MAC]		= { .len = sizeof(struct ifla_vf_mac) },
 	[IFLA_VF_VLAN]		= { .len = sizeof(struct ifla_vf_vlan) },
@@ -1488,96 +1484,98 @@
 	return 0;
 }
 
-static int do_setvfinfo(struct net_device *dev, struct nlattr *attr)
+static int do_setvfinfo(struct net_device *dev, struct nlattr **tb)
 {
-	int rem, err = -EINVAL;
-	struct nlattr *vf;
 	const struct net_device_ops *ops = dev->netdev_ops;
+	int err = -EINVAL;
 
-	nla_for_each_nested(vf, attr, rem) {
-		switch (nla_type(vf)) {
-		case IFLA_VF_MAC: {
-			struct ifla_vf_mac *ivm;
-			ivm = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_mac)
-				err = ops->ndo_set_vf_mac(dev, ivm->vf,
-							  ivm->mac);
-			break;
-		}
-		case IFLA_VF_VLAN: {
-			struct ifla_vf_vlan *ivv;
-			ivv = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_vlan)
-				err = ops->ndo_set_vf_vlan(dev, ivv->vf,
-							   ivv->vlan,
-							   ivv->qos);
-			break;
-		}
-		case IFLA_VF_TX_RATE: {
-			struct ifla_vf_tx_rate *ivt;
-			struct ifla_vf_info ivf;
-			ivt = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_get_vf_config)
-				err = ops->ndo_get_vf_config(dev, ivt->vf,
-							     &ivf);
-			if (err)
-				break;
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_rate)
-				err = ops->ndo_set_vf_rate(dev, ivt->vf,
-							   ivf.min_tx_rate,
-							   ivt->rate);
-			break;
-		}
-		case IFLA_VF_RATE: {
-			struct ifla_vf_rate *ivt;
-			ivt = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_rate)
-				err = ops->ndo_set_vf_rate(dev, ivt->vf,
-							   ivt->min_tx_rate,
-							   ivt->max_tx_rate);
-			break;
-		}
-		case IFLA_VF_SPOOFCHK: {
-			struct ifla_vf_spoofchk *ivs;
-			ivs = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_spoofchk)
-				err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
-							       ivs->setting);
-			break;
-		}
-		case IFLA_VF_LINK_STATE: {
-			struct ifla_vf_link_state *ivl;
-			ivl = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_link_state)
-				err = ops->ndo_set_vf_link_state(dev, ivl->vf,
-								 ivl->link_state);
-			break;
-		}
-		case IFLA_VF_RSS_QUERY_EN: {
-			struct ifla_vf_rss_query_en *ivrssq_en;
+	if (tb[IFLA_VF_MAC]) {
+		struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]);
 
-			ivrssq_en = nla_data(vf);
-			err = -EOPNOTSUPP;
-			if (ops->ndo_set_vf_rss_query_en)
-				err = ops->ndo_set_vf_rss_query_en(dev,
-							    ivrssq_en->vf,
-							    ivrssq_en->setting);
-			break;
-		}
-		default:
-			err = -EINVAL;
-			break;
-		}
-		if (err)
-			break;
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_mac)
+			err = ops->ndo_set_vf_mac(dev, ivm->vf,
+						  ivm->mac);
+		if (err < 0)
+			return err;
 	}
+
+	if (tb[IFLA_VF_VLAN]) {
+		struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_vlan)
+			err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan,
+						   ivv->qos);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_TX_RATE]) {
+		struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]);
+		struct ifla_vf_info ivf;
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_get_vf_config)
+			err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf);
+		if (err < 0)
+			return err;
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_rate)
+			err = ops->ndo_set_vf_rate(dev, ivt->vf,
+						   ivf.min_tx_rate,
+						   ivt->rate);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_RATE]) {
+		struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_rate)
+			err = ops->ndo_set_vf_rate(dev, ivt->vf,
+						   ivt->min_tx_rate,
+						   ivt->max_tx_rate);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_SPOOFCHK]) {
+		struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_spoofchk)
+			err = ops->ndo_set_vf_spoofchk(dev, ivs->vf,
+						       ivs->setting);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_LINK_STATE]) {
+		struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]);
+
+		err = -EOPNOTSUPP;
+		if (ops->ndo_set_vf_link_state)
+			err = ops->ndo_set_vf_link_state(dev, ivl->vf,
+							 ivl->link_state);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[IFLA_VF_RSS_QUERY_EN]) {
+		struct ifla_vf_rss_query_en *ivrssq_en;
+
+		err = -EOPNOTSUPP;
+		ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]);
+		if (ops->ndo_set_vf_rss_query_en)
+			err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf,
+							   ivrssq_en->setting);
+		if (err < 0)
+			return err;
+	}
+
 	return err;
 }
 
@@ -1773,14 +1771,21 @@
 	}
 
 	if (tb[IFLA_VFINFO_LIST]) {
+		struct nlattr *vfinfo[IFLA_VF_MAX + 1];
 		struct nlattr *attr;
 		int rem;
+
 		nla_for_each_nested(attr, tb[IFLA_VFINFO_LIST], rem) {
-			if (nla_type(attr) != IFLA_VF_INFO) {
+			if (nla_type(attr) != IFLA_VF_INFO ||
+			    nla_len(attr) < NLA_HDRLEN) {
 				err = -EINVAL;
 				goto errout;
 			}
-			err = do_setvfinfo(dev, attr);
+			err = nla_parse_nested(vfinfo, IFLA_VF_MAX, attr,
+					       ifla_vf_policy);
+			if (err < 0)
+				goto errout;
+			err = do_setvfinfo(dev, vfinfo);
 			if (err < 0)
 				goto errout;
 			status |= DO_SETLINK_NOTIFY;
@@ -1799,10 +1804,13 @@
 			goto errout;
 
 		nla_for_each_nested(attr, tb[IFLA_VF_PORTS], rem) {
-			if (nla_type(attr) != IFLA_VF_PORT)
-				continue;
-			err = nla_parse_nested(port, IFLA_PORT_MAX,
-				attr, ifla_port_policy);
+			if (nla_type(attr) != IFLA_VF_PORT ||
+			    nla_len(attr) < NLA_HDRLEN) {
+				err = -EINVAL;
+				goto errout;
+			}
+			err = nla_parse_nested(port, IFLA_PORT_MAX, attr,
+					       ifla_port_policy);
 			if (err < 0)
 				goto errout;
 			if (!port[IFLA_PORT_VF]) {
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b6a19ca..7b84330 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -340,7 +340,7 @@
 
 	if (skb && frag_size) {
 		skb->head_frag = 1;
-		if (virt_to_head_page(data)->pfmemalloc)
+		if (page_is_pfmemalloc(virt_to_head_page(data)))
 			skb->pfmemalloc = 1;
 	}
 	return skb;
@@ -4022,8 +4022,8 @@
  * Otherwise returns the provided skb. Returns NULL in error cases
  * (e.g. transport_len exceeds skb length or out-of-memory).
  *
- * Caller needs to set the skb transport header and release the returned skb.
- * Provided skb is consumed.
+ * Caller needs to set the skb transport header and free any returned skb if it
+ * differs from the provided skb.
  */
 static struct sk_buff *skb_checksum_maybe_trim(struct sk_buff *skb,
 					       unsigned int transport_len)
@@ -4032,16 +4032,12 @@
 	unsigned int len = skb_transport_offset(skb) + transport_len;
 	int ret;
 
-	if (skb->len < len) {
-		kfree_skb(skb);
+	if (skb->len < len)
 		return NULL;
-	} else if (skb->len == len) {
+	else if (skb->len == len)
 		return skb;
-	}
 
 	skb_chk = skb_clone(skb, GFP_ATOMIC);
-	kfree_skb(skb);
-
 	if (!skb_chk)
 		return NULL;
 
@@ -4066,8 +4062,8 @@
  * If the skb has data beyond the given transport length, then a
  * trimmed & cloned skb is checked and returned.
  *
- * Caller needs to set the skb transport header and release the returned skb.
- * Provided skb is consumed.
+ * Caller needs to set the skb transport header and free any returned skb if it
+ * differs from the provided skb.
  */
 struct sk_buff *skb_checksum_trimmed(struct sk_buff *skb,
 				     unsigned int transport_len,
@@ -4079,23 +4075,26 @@
 
 	skb_chk = skb_checksum_maybe_trim(skb, transport_len);
 	if (!skb_chk)
-		return NULL;
+		goto err;
 
-	if (!pskb_may_pull(skb_chk, offset)) {
-		kfree_skb(skb_chk);
-		return NULL;
-	}
+	if (!pskb_may_pull(skb_chk, offset))
+		goto err;
 
 	__skb_pull(skb_chk, offset);
 	ret = skb_chkf(skb_chk);
 	__skb_push(skb_chk, offset);
 
-	if (ret) {
-		kfree_skb(skb_chk);
-		return NULL;
-	}
+	if (ret)
+		goto err;
 
 	return skb_chk;
+
+err:
+	if (skb_chk && skb_chk != skb)
+		kfree_skb(skb_chk);
+
+	return NULL;
+
 }
 EXPORT_SYMBOL(skb_checksum_trimmed);
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 08f16db..193901d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1497,7 +1497,8 @@
 		sock_copy(newsk, sk);
 
 		/* SANITY */
-		get_net(sock_net(newsk));
+		if (likely(newsk->sk_net_refcnt))
+			get_net(sock_net(newsk));
 		sk_node_init(&newsk->sk_node);
 		sock_lock_init(newsk);
 		bh_lock_sock(newsk);
@@ -1967,20 +1968,21 @@
  * sk_wait_data - wait for data to arrive at sk_receive_queue
  * @sk:    sock to wait on
  * @timeo: for how long
+ * @skb:   last skb seen on sk_receive_queue
  *
  * Now socket state including sk->sk_err is changed only under lock,
  * hence we may omit checks after joining wait queue.
  * We check receive queue before schedule() only as optimization;
  * it is very likely that release_sock() added new data.
  */
-int sk_wait_data(struct sock *sk, long *timeo)
+int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
 {
 	int rc;
 	DEFINE_WAIT(wait);
 
 	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 	set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
-	rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue));
+	rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb);
 	clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	finish_wait(sk_sleep(sk), &wait);
 	return rc;
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 52a9401..b5cf13a 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -886,7 +886,7 @@
 			break;
 		}
 
-		sk_wait_data(sk, &timeo);
+		sk_wait_data(sk, &timeo, NULL);
 		continue;
 	found_ok_skb:
 		if (len > skb->len)
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 392e29a..b445d49 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -630,7 +630,7 @@
 			continue;
 
 		cd->sw_addr = be32_to_cpup(sw_addr);
-		if (cd->sw_addr > PHY_MAX_ADDR)
+		if (cd->sw_addr >= PHY_MAX_ADDR)
 			continue;
 
 		if (!of_property_read_u32(child, "eeprom-length", &eeprom_len))
@@ -642,6 +642,8 @@
 				continue;
 
 			port_index = be32_to_cpup(port_reg);
+			if (port_index >= DSA_MAX_PORTS)
+				break;
 
 			port_name = of_get_property(port, "label", NULL);
 			if (!port_name)
@@ -666,8 +668,6 @@
 					goto out_free_chip;
 			}
 
-			if (port_index == DSA_MAX_PORTS)
-				break;
 		}
 	}
 
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 0917123..35c47dd 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -756,7 +756,8 @@
 		return -ENODEV;
 
 	/* Use already configured phy mode */
-	p->phy_interface = p->phy->interface;
+	if (p->phy_interface == PHY_INTERFACE_MODE_NA)
+		p->phy_interface = p->phy->interface;
 	phy_connect_direct(slave_dev, p->phy, dsa_slave_adjust_link,
 			   p->phy_interface);
 
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index f46e4d1..214d44a 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -207,7 +207,7 @@
 	} else {
 		fq->q.meat += skb->len;
 	}
-	add_frag_mem_limit(&fq->q, skb->truesize);
+	add_frag_mem_limit(fq->q.net, skb->truesize);
 
 	if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
 	    fq->q.meat == fq->q.len) {
@@ -287,7 +287,7 @@
 		clone->data_len = clone->len;
 		head->data_len -= clone->len;
 		head->len -= clone->len;
-		add_frag_mem_limit(&fq->q, clone->truesize);
+		add_frag_mem_limit(fq->q.net, clone->truesize);
 	}
 
 	WARN_ON(head == NULL);
@@ -310,7 +310,7 @@
 		}
 		fp = next;
 	}
-	sub_frag_mem_limit(&fq->q, sum_truesize);
+	sub_frag_mem_limit(fq->q.net, sum_truesize);
 
 	head->next = NULL;
 	head->dev = dev;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 933a928..6c8b1fb 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1017,14 +1017,16 @@
 
 	neigh = neigh_lookup(&arp_tbl, &ip, dev);
 	if (neigh) {
-		read_lock_bh(&neigh->lock);
-		memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len);
-		r->arp_flags = arp_state_to_flags(neigh);
-		read_unlock_bh(&neigh->lock);
-		r->arp_ha.sa_family = dev->type;
-		strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev));
+		if (!(neigh->nud_state & NUD_NOARP)) {
+			read_lock_bh(&neigh->lock);
+			memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len);
+			r->arp_flags = arp_state_to_flags(neigh);
+			read_unlock_bh(&neigh->lock);
+			r->arp_ha.sa_family = dev->type;
+			strlcpy(r->arp_dev, dev->name, sizeof(r->arp_dev));
+			err = 0;
+		}
 		neigh_release(neigh);
-		err = 0;
 	}
 	return err;
 }
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 90c0e83..574fad9 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -20,7 +20,7 @@
 #include <net/route.h>
 #include <net/tcp_states.h>
 
-int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct sockaddr_in *usin = (struct sockaddr_in *) uaddr;
@@ -39,8 +39,6 @@
 
 	sk_dst_reset(sk);
 
-	lock_sock(sk);
-
 	oif = sk->sk_bound_dev_if;
 	saddr = inet->inet_saddr;
 	if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
@@ -82,9 +80,19 @@
 	sk_dst_set(sk, &rt->dst);
 	err = 0;
 out:
-	release_sock(sk);
 	return err;
 }
+EXPORT_SYMBOL(__ip4_datagram_connect);
+
+int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+	int res;
+
+	lock_sock(sk);
+	res = __ip4_datagram_connect(sk, uaddr, addr_len);
+	release_sock(sk);
+	return res;
+}
 EXPORT_SYMBOL(ip4_datagram_connect);
 
 /* Because UDP xmit path can manipulate sk_dst_cache without holding
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 7498716..2d9cb17 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -882,7 +882,6 @@
 		queue_delayed_work(system_power_efficient_wq,
 				&check_lifetime_work, 0);
 		rtmsg_ifa(RTM_NEWADDR, ifa, nlh, NETLINK_CB(skb).portid);
-		blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, ifa);
 	}
 	return 0;
 }
@@ -1740,6 +1739,8 @@
 		size += nla_total_size(4);
 	if (type == -1 || type == NETCONFA_PROXY_NEIGH)
 		size += nla_total_size(4);
+	if (type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN)
+		size += nla_total_size(4);
 
 	return size;
 }
@@ -1780,6 +1781,10 @@
 	    nla_put_s32(skb, NETCONFA_PROXY_NEIGH,
 			IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0)
 		goto nla_put_failure;
+	if ((type == -1 || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN) &&
+	    nla_put_s32(skb, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+			IPV4_DEVCONF(*devconf, IGNORE_ROUTES_WITH_LINKDOWN)) < 0)
+		goto nla_put_failure;
 
 	nlmsg_end(skb, nlh);
 	return 0;
@@ -1819,6 +1824,7 @@
 	[NETCONFA_FORWARDING]	= { .len = sizeof(int) },
 	[NETCONFA_RP_FILTER]	= { .len = sizeof(int) },
 	[NETCONFA_PROXY_NEIGH]	= { .len = sizeof(int) },
+	[NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN]	= { .len = sizeof(int) },
 };
 
 static int inet_netconf_get_devconf(struct sk_buff *in_skb,
@@ -2048,6 +2054,12 @@
 			inet_netconf_notify_devconf(net, NETCONFA_PROXY_NEIGH,
 						    ifindex, cnf);
 		}
+		if (i == IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN - 1 &&
+		    new_value != old_value) {
+			ifindex = devinet_conf_ifindex(net, cnf);
+			inet_netconf_notify_devconf(net, NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
+						    ifindex, cnf);
+		}
 	}
 
 	return ret;
diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h
index c6211ed..9c02920 100644
--- a/net/ipv4/fib_lookup.h
+++ b/net/ipv4/fib_lookup.h
@@ -13,6 +13,7 @@
 	u8			fa_state;
 	u8			fa_slen;
 	u32			tb_id;
+	s16			fa_default;
 	struct rcu_head		rcu;
 };
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index c7358ea..3a06586 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1202,23 +1202,40 @@
 }
 
 /* Must be invoked inside of an RCU protected region.  */
-void fib_select_default(struct fib_result *res)
+void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
 {
 	struct fib_info *fi = NULL, *last_resort = NULL;
 	struct hlist_head *fa_head = res->fa_head;
 	struct fib_table *tb = res->table;
+	u8 slen = 32 - res->prefixlen;
 	int order = -1, last_idx = -1;
-	struct fib_alias *fa;
+	struct fib_alias *fa, *fa1 = NULL;
+	u32 last_prio = res->fi->fib_priority;
+	u8 last_tos = 0;
 
 	hlist_for_each_entry_rcu(fa, fa_head, fa_list) {
 		struct fib_info *next_fi = fa->fa_info;
 
+		if (fa->fa_slen != slen)
+			continue;
+		if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
+			continue;
+		if (fa->tb_id != tb->tb_id)
+			continue;
+		if (next_fi->fib_priority > last_prio &&
+		    fa->fa_tos == last_tos) {
+			if (last_tos)
+				continue;
+			break;
+		}
+		if (next_fi->fib_flags & RTNH_F_DEAD)
+			continue;
+		last_tos = fa->fa_tos;
+		last_prio = next_fi->fib_priority;
+
 		if (next_fi->fib_scope != res->scope ||
 		    fa->fa_type != RTN_UNICAST)
 			continue;
-
-		if (next_fi->fib_priority > res->fi->fib_priority)
-			break;
 		if (!next_fi->fib_nh[0].nh_gw ||
 		    next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
 			continue;
@@ -1228,10 +1245,11 @@
 		if (!fi) {
 			if (next_fi != res->fi)
 				break;
+			fa1 = fa;
 		} else if (!fib_detect_death(fi, order, &last_resort,
-					     &last_idx, tb->tb_default)) {
+					     &last_idx, fa1->fa_default)) {
 			fib_result_assign(res, fi);
-			tb->tb_default = order;
+			fa1->fa_default = order;
 			goto out;
 		}
 		fi = next_fi;
@@ -1239,20 +1257,21 @@
 	}
 
 	if (order <= 0 || !fi) {
-		tb->tb_default = -1;
+		if (fa1)
+			fa1->fa_default = -1;
 		goto out;
 	}
 
 	if (!fib_detect_death(fi, order, &last_resort, &last_idx,
-				tb->tb_default)) {
+			      fa1->fa_default)) {
 		fib_result_assign(res, fi);
-		tb->tb_default = order;
+		fa1->fa_default = order;
 		goto out;
 	}
 
 	if (last_idx >= 0)
 		fib_result_assign(res, last_resort);
-	tb->tb_default = last_idx;
+	fa1->fa_default = last_idx;
 out:
 	return;
 }
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 15d3261..b0c6258 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1171,6 +1171,7 @@
 			new_fa->fa_state = state & ~FA_S_ACCESSED;
 			new_fa->fa_slen = fa->fa_slen;
 			new_fa->tb_id = tb->tb_id;
+			new_fa->fa_default = -1;
 
 			err = switchdev_fib_ipv4_add(key, plen, fi,
 						     new_fa->fa_tos,
@@ -1222,6 +1223,7 @@
 	new_fa->fa_state = 0;
 	new_fa->fa_slen = slen;
 	new_fa->tb_id = tb->tb_id;
+	new_fa->fa_default = -1;
 
 	/* (Optionally) offload fib entry to switch hardware. */
 	err = switchdev_fib_ipv4_add(key, plen, fi, tos, cfg->fc_type,
@@ -1791,8 +1793,6 @@
 		if (hlist_empty(&n->leaf)) {
 			put_child_root(pn, n->key, NULL);
 			node_free(n);
-		} else {
-			leaf_pull_suffix(pn, n);
 		}
 	}
 }
@@ -1862,8 +1862,6 @@
 		if (hlist_empty(&n->leaf)) {
 			put_child_root(pn, n->key, NULL);
 			node_free(n);
-		} else {
-			leaf_pull_suffix(pn, n);
 		}
 	}
 
@@ -1990,7 +1988,6 @@
 		return NULL;
 
 	tb->tb_id = id;
-	tb->tb_default = -1;
 	tb->tb_num_default = 0;
 	tb->tb_data = (alias ? alias->__data : tb->__data);
 
@@ -2468,7 +2465,7 @@
 		key = l->key + 1;
 		iter->pos++;
 
-		if (pos-- <= 0)
+		if (--pos <= 0)
 			break;
 
 		l = NULL;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 651cdf6..9fdfd9d 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1435,33 +1435,35 @@
 	struct sk_buff *skb_chk;
 	unsigned int transport_len;
 	unsigned int len = skb_transport_offset(skb) + sizeof(struct igmphdr);
-	int ret;
+	int ret = -EINVAL;
 
 	transport_len = ntohs(ip_hdr(skb)->tot_len) - ip_hdrlen(skb);
 
-	skb_get(skb);
 	skb_chk = skb_checksum_trimmed(skb, transport_len,
 				       ip_mc_validate_checksum);
 	if (!skb_chk)
-		return -EINVAL;
+		goto err;
 
-	if (!pskb_may_pull(skb_chk, len)) {
-		kfree_skb(skb_chk);
-		return -EINVAL;
-	}
+	if (!pskb_may_pull(skb_chk, len))
+		goto err;
 
 	ret = ip_mc_check_igmp_msg(skb_chk);
-	if (ret) {
-		kfree_skb(skb_chk);
-		return ret;
-	}
+	if (ret)
+		goto err;
 
 	if (skb_trimmed)
 		*skb_trimmed = skb_chk;
-	else
+	/* free now unneeded clone */
+	else if (skb_chk != skb)
 		kfree_skb(skb_chk);
 
-	return 0;
+	ret = 0;
+
+err:
+	if (ret && skb_chk && skb_chk != skb)
+		kfree_skb(skb_chk);
+
+	return ret;
 }
 
 /**
@@ -1470,7 +1472,7 @@
  * @skb_trimmed: to store an skb pointer trimmed to IPv4 packet tail (optional)
  *
  * Checks whether an IPv4 packet is a valid IGMP packet. If so sets
- * skb network and transport headers accordingly and returns zero.
+ * skb transport header accordingly and returns zero.
  *
  * -EINVAL: A broken packet was detected, i.e. it violates some internet
  *  standard
@@ -1485,7 +1487,8 @@
  * to leave the original skb and its full frame unchanged (which might be
  * desirable for layer 2 frame jugglers).
  *
- * The caller needs to release a reference count from any returned skb_trimmed.
+ * Caller needs to set the skb network header and free any returned skb if it
+ * differs from the provided skb.
  */
 int ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed)
 {
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 60021d0..1349571 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -593,7 +593,7 @@
 	}
 
 	spin_unlock(&queue->syn_wait_lock);
-	if (del_timer(&req->rsk_timer))
+	if (timer_pending(&req->rsk_timer) && del_timer_sync(&req->rsk_timer))
 		reqsk_put(req);
 	return found;
 }
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 9bc2667..c3b1f3a 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -152,8 +152,8 @@
 				       inet6_sk(sk)->tclass) < 0)
 				goto errout;
 
-		if (ipv6_only_sock(sk) &&
-		    nla_put_u8(skb, INET_DIAG_SKV6ONLY, 1))
+		if (((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) &&
+		    nla_put_u8(skb, INET_DIAG_SKV6ONLY, ipv6_only_sock(sk)))
 			goto errout;
 	}
 #endif
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 5e346a0..d0a7c03 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -131,34 +131,22 @@
 	unsigned int evicted = 0;
 	HLIST_HEAD(expired);
 
-evict_again:
 	spin_lock(&hb->chain_lock);
 
 	hlist_for_each_entry_safe(fq, n, &hb->chain, list) {
 		if (!inet_fragq_should_evict(fq))
 			continue;
 
-		if (!del_timer(&fq->timer)) {
-			/* q expiring right now thus increment its refcount so
-			 * it won't be freed under us and wait until the timer
-			 * has finished executing then destroy it
-			 */
-			atomic_inc(&fq->refcnt);
-			spin_unlock(&hb->chain_lock);
-			del_timer_sync(&fq->timer);
-			inet_frag_put(fq, f);
-			goto evict_again;
-		}
+		if (!del_timer(&fq->timer))
+			continue;
 
-		fq->flags |= INET_FRAG_EVICTED;
-		hlist_del(&fq->list);
-		hlist_add_head(&fq->list, &expired);
+		hlist_add_head(&fq->list_evictor, &expired);
 		++evicted;
 	}
 
 	spin_unlock(&hb->chain_lock);
 
-	hlist_for_each_entry_safe(fq, n, &expired, list)
+	hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
 		f->frag_expire((unsigned long) fq);
 
 	return evicted;
@@ -240,18 +228,20 @@
 	int i;
 
 	nf->low_thresh = 0;
-	local_bh_disable();
 
 evict_again:
+	local_bh_disable();
 	seq = read_seqbegin(&f->rnd_seqlock);
 
 	for (i = 0; i < INETFRAGS_HASHSZ ; i++)
 		inet_evict_bucket(f, &f->hash[i]);
 
-	if (read_seqretry(&f->rnd_seqlock, seq))
-		goto evict_again;
-
 	local_bh_enable();
+	cond_resched();
+
+	if (read_seqretry(&f->rnd_seqlock, seq) ||
+	    percpu_counter_sum(&nf->mem))
+		goto evict_again;
 
 	percpu_counter_destroy(&nf->mem);
 }
@@ -284,8 +274,8 @@
 	struct inet_frag_bucket *hb;
 
 	hb = get_frag_bucket_locked(fq, f);
-	if (!(fq->flags & INET_FRAG_EVICTED))
-		hlist_del(&fq->list);
+	hlist_del(&fq->list);
+	fq->flags |= INET_FRAG_COMPLETE;
 	spin_unlock(&hb->chain_lock);
 }
 
@@ -297,7 +287,6 @@
 	if (!(fq->flags & INET_FRAG_COMPLETE)) {
 		fq_unlink(fq, f);
 		atomic_dec(&fq->refcnt);
-		fq->flags |= INET_FRAG_COMPLETE;
 	}
 }
 EXPORT_SYMBOL(inet_frag_kill);
@@ -330,11 +319,12 @@
 		fp = xp;
 	}
 	sum = sum_truesize + f->qsize;
-	sub_frag_mem_limit(q, sum);
 
 	if (f->destructor)
 		f->destructor(q);
 	kmem_cache_free(f->frags_cachep, q);
+
+	sub_frag_mem_limit(nf, sum);
 }
 EXPORT_SYMBOL(inet_frag_destroy);
 
@@ -390,7 +380,7 @@
 
 	q->net = nf;
 	f->constructor(q, arg);
-	add_frag_mem_limit(q, f->qsize);
+	add_frag_mem_limit(nf, f->qsize);
 
 	setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
 	spin_lock_init(&q->lock);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 5f9b063..0cb9165 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -624,22 +624,21 @@
 
 int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
 {
+	unsigned int locksz = sizeof(spinlock_t);
 	unsigned int i, nblocks = 1;
 
-	if (sizeof(spinlock_t) != 0) {
+	if (locksz != 0) {
 		/* allocate 2 cache lines or at least one spinlock per cpu */
-		nblocks = max_t(unsigned int,
-				2 * L1_CACHE_BYTES / sizeof(spinlock_t),
-				1);
+		nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U);
 		nblocks = roundup_pow_of_two(nblocks * num_possible_cpus());
 
 		/* no more locks than number of hash buckets */
 		nblocks = min(nblocks, hashinfo->ehash_mask + 1);
 
-		hashinfo->ehash_locks =	kmalloc_array(nblocks, sizeof(spinlock_t),
+		hashinfo->ehash_locks =	kmalloc_array(nblocks, locksz,
 						      GFP_KERNEL | __GFP_NOWARN);
 		if (!hashinfo->ehash_locks)
-			hashinfo->ehash_locks = vmalloc(nblocks * sizeof(spinlock_t));
+			hashinfo->ehash_locks = vmalloc(nblocks * locksz);
 
 		if (!hashinfo->ehash_locks)
 			return -ENOMEM;
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index a50dc6d..921138f 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -202,7 +202,7 @@
 	ipq_kill(qp);
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
 
-	if (!(qp->q.flags & INET_FRAG_EVICTED)) {
+	if (!inet_frag_evicting(&qp->q)) {
 		struct sk_buff *head = qp->q.fragments;
 		const struct iphdr *iph;
 		int err;
@@ -309,7 +309,7 @@
 		kfree_skb(fp);
 		fp = xp;
 	} while (fp);
-	sub_frag_mem_limit(&qp->q, sum_truesize);
+	sub_frag_mem_limit(qp->q.net, sum_truesize);
 
 	qp->q.flags = 0;
 	qp->q.len = 0;
@@ -351,7 +351,7 @@
 	ihl = ip_hdrlen(skb);
 
 	/* Determine the position of this fragment. */
-	end = offset + skb->len - ihl;
+	end = offset + skb->len - skb_network_offset(skb) - ihl;
 	err = -EINVAL;
 
 	/* Is this the final fragment? */
@@ -381,7 +381,7 @@
 		goto err;
 
 	err = -ENOMEM;
-	if (!pskb_pull(skb, ihl))
+	if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
 		goto err;
 
 	err = pskb_trim_rcsum(skb, end - offset);
@@ -455,7 +455,7 @@
 				qp->q.fragments = next;
 
 			qp->q.meat -= free_it->len;
-			sub_frag_mem_limit(&qp->q, free_it->truesize);
+			sub_frag_mem_limit(qp->q.net, free_it->truesize);
 			kfree_skb(free_it);
 		}
 	}
@@ -479,7 +479,7 @@
 	qp->q.stamp = skb->tstamp;
 	qp->q.meat += skb->len;
 	qp->ecn |= ecn;
-	add_frag_mem_limit(&qp->q, skb->truesize);
+	add_frag_mem_limit(qp->q.net, skb->truesize);
 	if (offset == 0)
 		qp->q.flags |= INET_FRAG_FIRST_IN;
 
@@ -587,7 +587,7 @@
 		head->len -= clone->len;
 		clone->csum = 0;
 		clone->ip_summed = head->ip_summed;
-		add_frag_mem_limit(&qp->q, clone->truesize);
+		add_frag_mem_limit(qp->q.net, clone->truesize);
 	}
 
 	skb_push(head, head->data - skb_network_header(head));
@@ -615,7 +615,7 @@
 		}
 		fp = next;
 	}
-	sub_frag_mem_limit(&qp->q, sum_truesize);
+	sub_frag_mem_limit(qp->q.net, sum_truesize);
 
 	head->next = NULL;
 	head->dev = dev;
@@ -641,6 +641,8 @@
 		iph->frag_off = 0;
 	}
 
+	ip_send_check(iph);
+
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
 	qp->q.fragments = NULL;
 	qp->q.fragments_tail = NULL;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 4c2c3ba..626d9e5 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -586,7 +586,8 @@
 EXPORT_SYMBOL(ip_tunnel_encap);
 
 static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
-			    struct rtable *rt, __be16 df)
+			    struct rtable *rt, __be16 df,
+			    const struct iphdr *inner_iph)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len;
@@ -603,7 +604,8 @@
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		if (!skb_is_gso(skb) &&
-		    (df & htons(IP_DF)) && mtu < pkt_size) {
+		    (inner_iph->frag_off & htons(IP_DF)) &&
+		    mtu < pkt_size) {
 			memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
 			return -E2BIG;
@@ -737,7 +739,7 @@
 		goto tx_error;
 	}
 
-	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) {
+	if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) {
 		ip_rt_put(rt);
 		goto tx_error;
 	}
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 95c9b6e..92305a1 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -254,9 +254,10 @@
 	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
 	unsigned int verdict = NF_DROP;
 	const struct arphdr *arp;
-	struct arpt_entry *e, *back;
+	struct arpt_entry *e, **jumpstack;
 	const char *indev, *outdev;
 	const void *table_base;
+	unsigned int cpu, stackidx = 0;
 	const struct xt_table_info *private;
 	struct xt_action_param acpar;
 	unsigned int addend;
@@ -270,15 +271,16 @@
 	local_bh_disable();
 	addend = xt_write_recseq_begin();
 	private = table->private;
+	cpu     = smp_processor_id();
 	/*
 	 * Ensure we load private-> members after we've fetched the base
 	 * pointer.
 	 */
 	smp_read_barrier_depends();
 	table_base = private->entries;
+	jumpstack  = (struct arpt_entry **)private->jumpstack[cpu];
 
 	e = get_entry(table_base, private->hook_entry[hook]);
-	back = get_entry(table_base, private->underflow[hook]);
 
 	acpar.in      = state->in;
 	acpar.out     = state->out;
@@ -312,18 +314,23 @@
 					verdict = (unsigned int)(-v) - 1;
 					break;
 				}
-				e = back;
-				back = get_entry(table_base, back->comefrom);
+				if (stackidx == 0) {
+					e = get_entry(table_base,
+						      private->underflow[hook]);
+				} else {
+					e = jumpstack[--stackidx];
+					e = arpt_next_entry(e);
+				}
 				continue;
 			}
 			if (table_base + v
 			    != arpt_next_entry(e)) {
-				/* Save old back ptr in next entry */
-				struct arpt_entry *next = arpt_next_entry(e);
-				next->comefrom = (void *)back - table_base;
 
-				/* set back pointer to next entry */
-				back = next;
+				if (stackidx >= private->stacksize) {
+					verdict = NF_DROP;
+					break;
+				}
+				jumpstack[stackidx++] = e;
 			}
 
 			e = get_entry(table_base, v);
diff --git a/net/ipv4/netfilter/ipt_SYNPROXY.c b/net/ipv4/netfilter/ipt_SYNPROXY.c
index fe8cc18..95ea633e 100644
--- a/net/ipv4/netfilter/ipt_SYNPROXY.c
+++ b/net/ipv4/netfilter/ipt_SYNPROXY.c
@@ -226,7 +226,8 @@
 
 	synproxy_build_options(nth, opts);
 
-	synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size);
+	synproxy_send_tcp(skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY,
+	                  niph, nth, tcp_hdr_size);
 }
 
 static bool
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d0362a2..e681b85 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2176,7 +2176,7 @@
 	if (!res.prefixlen &&
 	    res.table->tb_num_default > 1 &&
 	    res.type == RTN_UNICAST && !fl4->flowi4_oif)
-		fib_select_default(&res);
+		fib_select_default(fl4, &res);
 
 	if (!fl4->saddr)
 		fl4->saddr = FIB_RES_PREFSRC(net, res);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 433231c..0330ab2 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -41,8 +41,6 @@
 static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
 static int ip_ping_group_range_min[] = { 0, 0 };
 static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
-static int min_sndbuf = SOCK_MIN_SNDBUF;
-static int min_rcvbuf = SOCK_MIN_RCVBUF;
 
 /* Update system visible IP port range */
 static void set_local_port_range(struct net *net, int range[2])
@@ -530,7 +528,7 @@
 		.maxlen		= sizeof(sysctl_tcp_wmem),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &min_sndbuf,
+		.extra1		= &one,
 	},
 	{
 		.procname	= "tcp_notsent_lowat",
@@ -545,7 +543,7 @@
 		.maxlen		= sizeof(sysctl_tcp_rmem),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &min_rcvbuf,
+		.extra1		= &one,
 	},
 	{
 		.procname	= "tcp_app_win",
@@ -758,7 +756,7 @@
 		.maxlen		= sizeof(sysctl_udp_rmem_min),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &min_rcvbuf,
+		.extra1		= &one
 	},
 	{
 		.procname	= "udp_wmem_min",
@@ -766,7 +764,7 @@
 		.maxlen		= sizeof(sysctl_udp_wmem_min),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &min_sndbuf,
+		.extra1		= &one
 	},
 	{ }
 };
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7f40567..45534a5 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -780,7 +780,7 @@
 				ret = -EAGAIN;
 				break;
 			}
-			sk_wait_data(sk, &timeo);
+			sk_wait_data(sk, &timeo, NULL);
 			if (signal_pending(current)) {
 				ret = sock_intr_errno(timeo);
 				break;
@@ -1575,7 +1575,7 @@
 	int target;		/* Read at least this many bytes */
 	long timeo;
 	struct task_struct *user_recv = NULL;
-	struct sk_buff *skb;
+	struct sk_buff *skb, *last;
 	u32 urg_hole = 0;
 
 	if (unlikely(flags & MSG_ERRQUEUE))
@@ -1635,7 +1635,9 @@
 
 		/* Next get a buffer. */
 
+		last = skb_peek_tail(&sk->sk_receive_queue);
 		skb_queue_walk(&sk->sk_receive_queue, skb) {
+			last = skb;
 			/* Now that we have two receive queues this
 			 * shouldn't happen.
 			 */
@@ -1754,8 +1756,9 @@
 			/* Do not sleep, just process backlog. */
 			release_sock(sk);
 			lock_sock(sk);
-		} else
-			sk_wait_data(sk, &timeo);
+		} else {
+			sk_wait_data(sk, &timeo, last);
+		}
 
 		if (user_recv) {
 			int chunk;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 684f095..728f5b3 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1917,14 +1917,13 @@
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
-	bool new_recovery = false;
+	bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
 	bool is_reneg;			/* is receiver reneging on SACKs? */
 
 	/* Reduce ssthresh if it has not yet been made inside this window. */
 	if (icsk->icsk_ca_state <= TCP_CA_Disorder ||
 	    !after(tp->high_seq, tp->snd_una) ||
 	    (icsk->icsk_ca_state == TCP_CA_Loss && !icsk->icsk_retransmits)) {
-		new_recovery = true;
 		tp->prior_ssthresh = tcp_current_ssthresh(sk);
 		tp->snd_ssthresh = icsk->icsk_ca_ops->ssthresh(sk);
 		tcp_ca_event(sk, CA_EVENT_LOSS);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d7d4c2b..0ea2e1c 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1348,7 +1348,7 @@
 	req = inet_csk_search_req(sk, th->source, iph->saddr, iph->daddr);
 	if (req) {
 		nsk = tcp_check_req(sk, skb, req, false);
-		if (!nsk)
+		if (!nsk || nsk == sk)
 			reqsk_put(req);
 		return nsk;
 	}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 83aa604..1b8c5ba 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1995,12 +1995,19 @@
 
 	skb->sk = sk;
 	skb->destructor = sock_efree;
-	dst = sk->sk_rx_dst;
+	dst = READ_ONCE(sk->sk_rx_dst);
 
 	if (dst)
 		dst = dst_check(dst, 0);
-	if (dst)
-		skb_dst_set_noref(skb, dst);
+	if (dst) {
+		/* DST_NOCACHE can not be used without taking a reference */
+		if (dst->flags & DST_NOCACHE) {
+			if (likely(atomic_inc_not_zero(&dst->__refcnt)))
+				skb_dst_set(skb, dst);
+		} else {
+			skb_dst_set_noref(skb, dst);
+		}
+	}
 }
 
 int udp_rcv(struct sk_buff *skb)
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 62d908e..b10a889 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -40,7 +40,7 @@
 	return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0);
 }
 
-int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
 	struct sockaddr_in6	*usin = (struct sockaddr_in6 *) uaddr;
 	struct inet_sock	*inet = inet_sk(sk);
@@ -56,7 +56,7 @@
 	if (usin->sin6_family == AF_INET) {
 		if (__ipv6_only_sock(sk))
 			return -EAFNOSUPPORT;
-		err = ip4_datagram_connect(sk, uaddr, addr_len);
+		err = __ip4_datagram_connect(sk, uaddr, addr_len);
 		goto ipv4_connected;
 	}
 
@@ -98,9 +98,9 @@
 		sin.sin_addr.s_addr = daddr->s6_addr32[3];
 		sin.sin_port = usin->sin6_port;
 
-		err = ip4_datagram_connect(sk,
-					   (struct sockaddr *) &sin,
-					   sizeof(sin));
+		err = __ip4_datagram_connect(sk,
+					     (struct sockaddr *) &sin,
+					     sizeof(sin));
 
 ipv4_connected:
 		if (err)
@@ -204,6 +204,16 @@
 	fl6_sock_release(flowlabel);
 	return err;
 }
+
+int ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+	int res;
+
+	lock_sock(sk);
+	res = __ip6_datagram_connect(sk, uaddr, addr_len);
+	release_sock(sk);
+	return res;
+}
 EXPORT_SYMBOL_GPL(ip6_datagram_connect);
 
 int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *uaddr,
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 55d1986..548c623 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -172,6 +172,8 @@
 			*ppcpu_rt = NULL;
 		}
 	}
+
+	non_pcpu_rt->rt6i_pcpu = NULL;
 }
 
 static void rt6_release(struct rt6_info *rt)
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index f2e464e..57990c9 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -331,10 +331,10 @@
 				if (offset < 0)
 					goto out;
 
-				if (!ipv6_is_mld(skb, nexthdr, offset))
-					goto out;
+				if (ipv6_is_mld(skb, nexthdr, offset))
+					deliver = true;
 
-				deliver = true;
+				goto out;
 			}
 			/* unknown RA - process it normally */
 		}
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index e893cd1..08b6204 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -292,8 +292,6 @@
 static const struct net_offload sit_offload = {
 	.callbacks = {
 		.gso_segment	= ipv6_gso_segment,
-		.gro_receive	= ipv6_gro_receive,
-		.gro_complete	= ipv6_gro_complete,
 	},
 };
 
diff --git a/net/ipv6/mcast_snoop.c b/net/ipv6/mcast_snoop.c
index df8afe5..9405b04 100644
--- a/net/ipv6/mcast_snoop.c
+++ b/net/ipv6/mcast_snoop.c
@@ -143,34 +143,36 @@
 	struct sk_buff *skb_chk = NULL;
 	unsigned int transport_len;
 	unsigned int len = skb_transport_offset(skb) + sizeof(struct mld_msg);
-	int ret;
+	int ret = -EINVAL;
 
 	transport_len = ntohs(ipv6_hdr(skb)->payload_len);
 	transport_len -= skb_transport_offset(skb) - sizeof(struct ipv6hdr);
 
-	skb_get(skb);
 	skb_chk = skb_checksum_trimmed(skb, transport_len,
 				       ipv6_mc_validate_checksum);
 	if (!skb_chk)
-		return -EINVAL;
+		goto err;
 
-	if (!pskb_may_pull(skb_chk, len)) {
-		kfree_skb(skb_chk);
-		return -EINVAL;
-	}
+	if (!pskb_may_pull(skb_chk, len))
+		goto err;
 
 	ret = ipv6_mc_check_mld_msg(skb_chk);
-	if (ret) {
-		kfree_skb(skb_chk);
-		return ret;
-	}
+	if (ret)
+		goto err;
 
 	if (skb_trimmed)
 		*skb_trimmed = skb_chk;
-	else
+	/* free now unneeded clone */
+	else if (skb_chk != skb)
 		kfree_skb(skb_chk);
 
-	return 0;
+	ret = 0;
+
+err:
+	if (ret && skb_chk && skb_chk != skb)
+		kfree_skb(skb_chk);
+
+	return ret;
 }
 
 /**
@@ -179,7 +181,7 @@
  * @skb_trimmed: to store an skb pointer trimmed to IPv6 packet tail (optional)
  *
  * Checks whether an IPv6 packet is a valid MLD packet. If so sets
- * skb network and transport headers accordingly and returns zero.
+ * skb transport header accordingly and returns zero.
  *
  * -EINVAL: A broken packet was detected, i.e. it violates some internet
  *  standard
@@ -194,7 +196,8 @@
  * to leave the original skb and its full frame unchanged (which might be
  * desirable for layer 2 frame jugglers).
  *
- * The caller needs to release a reference count from any returned skb_trimmed.
+ * Caller needs to set the skb network header and free any returned skb if it
+ * differs from the provided skb.
  */
 int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed)
 {
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 0a05b35..c53331c 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1650,6 +1650,7 @@
 static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct netdev_notifier_change_info *change_info;
 	struct net *net = dev_net(dev);
 	struct inet6_dev *idev;
 
@@ -1664,6 +1665,11 @@
 			ndisc_send_unsol_na(dev);
 		in6_dev_put(idev);
 		break;
+	case NETDEV_CHANGE:
+		change_info = ptr;
+		if (change_info->flags_changed & IFF_NOARP)
+			neigh_changeaddr(&nd_tbl, dev);
+		break;
 	case NETDEV_DOWN:
 		neigh_ifdown(&nd_tbl, dev);
 		fib6_run_gc(0, net, false);
diff --git a/net/ipv6/netfilter/ip6t_SYNPROXY.c b/net/ipv6/netfilter/ip6t_SYNPROXY.c
index 6edb7b1..ebbb754 100644
--- a/net/ipv6/netfilter/ip6t_SYNPROXY.c
+++ b/net/ipv6/netfilter/ip6t_SYNPROXY.c
@@ -37,12 +37,13 @@
 }
 
 static void
-synproxy_send_tcp(const struct sk_buff *skb, struct sk_buff *nskb,
+synproxy_send_tcp(const struct synproxy_net *snet,
+		  const struct sk_buff *skb, struct sk_buff *nskb,
 		  struct nf_conntrack *nfct, enum ip_conntrack_info ctinfo,
 		  struct ipv6hdr *niph, struct tcphdr *nth,
 		  unsigned int tcp_hdr_size)
 {
-	struct net *net = nf_ct_net((struct nf_conn *)nfct);
+	struct net *net = nf_ct_net(snet->tmpl);
 	struct dst_entry *dst;
 	struct flowi6 fl6;
 
@@ -83,7 +84,8 @@
 }
 
 static void
-synproxy_send_client_synack(const struct sk_buff *skb, const struct tcphdr *th,
+synproxy_send_client_synack(const struct synproxy_net *snet,
+			    const struct sk_buff *skb, const struct tcphdr *th,
 			    const struct synproxy_options *opts)
 {
 	struct sk_buff *nskb;
@@ -119,7 +121,7 @@
 
 	synproxy_build_options(nth, opts);
 
-	synproxy_send_tcp(skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY,
+	synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY,
 			  niph, nth, tcp_hdr_size);
 }
 
@@ -163,7 +165,7 @@
 
 	synproxy_build_options(nth, opts);
 
-	synproxy_send_tcp(skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW,
+	synproxy_send_tcp(snet, skb, nskb, &snet->tmpl->ct_general, IP_CT_NEW,
 			  niph, nth, tcp_hdr_size);
 }
 
@@ -203,7 +205,7 @@
 
 	synproxy_build_options(nth, opts);
 
-	synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size);
+	synproxy_send_tcp(snet, skb, nskb, NULL, 0, niph, nth, tcp_hdr_size);
 }
 
 static void
@@ -241,7 +243,8 @@
 
 	synproxy_build_options(nth, opts);
 
-	synproxy_send_tcp(skb, nskb, NULL, 0, niph, nth, tcp_hdr_size);
+	synproxy_send_tcp(snet, skb, nskb, skb->nfct, IP_CT_ESTABLISHED_REPLY,
+	                  niph, nth, tcp_hdr_size);
 }
 
 static bool
@@ -301,7 +304,7 @@
 					  XT_SYNPROXY_OPT_SACK_PERM |
 					  XT_SYNPROXY_OPT_ECN);
 
-		synproxy_send_client_synack(skb, th, &opts);
+		synproxy_send_client_synack(snet, skb, th, &opts);
 		return NF_DROP;
 
 	} else if (th->ack && !(th->fin || th->rst || th->syn)) {
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 6f187c8..6d02498 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -348,7 +348,7 @@
 	fq->ecn |= ecn;
 	if (payload_len > fq->q.max_size)
 		fq->q.max_size = payload_len;
-	add_frag_mem_limit(&fq->q, skb->truesize);
+	add_frag_mem_limit(fq->q.net, skb->truesize);
 
 	/* The first fragment.
 	 * nhoffset is obtained from the first fragment, of course.
@@ -430,7 +430,7 @@
 		clone->ip_summed = head->ip_summed;
 
 		NFCT_FRAG6_CB(clone)->orig = NULL;
-		add_frag_mem_limit(&fq->q, clone->truesize);
+		add_frag_mem_limit(fq->q.net, clone->truesize);
 	}
 
 	/* We have to remove fragment header from datagram and to relocate
@@ -454,7 +454,7 @@
 			head->csum = csum_add(head->csum, fp->csum);
 		head->truesize += fp->truesize;
 	}
-	sub_frag_mem_limit(&fq->q, head->truesize);
+	sub_frag_mem_limit(fq->q.net, head->truesize);
 
 	head->ignore_df = 1;
 	head->next = NULL;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 8ffa2c8..f1159bb 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -144,7 +144,7 @@
 
 	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
 
-	if (fq->q.flags & INET_FRAG_EVICTED)
+	if (inet_frag_evicting(&fq->q))
 		goto out_rcu_unlock;
 
 	IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
@@ -330,7 +330,7 @@
 	fq->q.stamp = skb->tstamp;
 	fq->q.meat += skb->len;
 	fq->ecn |= ecn;
-	add_frag_mem_limit(&fq->q, skb->truesize);
+	add_frag_mem_limit(fq->q.net, skb->truesize);
 
 	/* The first fragment.
 	 * nhoffset is obtained from the first fragment, of course.
@@ -443,7 +443,7 @@
 		head->len -= clone->len;
 		clone->csum = 0;
 		clone->ip_summed = head->ip_summed;
-		add_frag_mem_limit(&fq->q, clone->truesize);
+		add_frag_mem_limit(fq->q.net, clone->truesize);
 	}
 
 	/* We have to remove fragment header from datagram and to relocate
@@ -481,7 +481,7 @@
 		}
 		fp = next;
 	}
-	sub_frag_mem_limit(&fq->q, sum_truesize);
+	sub_frag_mem_limit(fq->q.net, sum_truesize);
 
 	head->next = NULL;
 	head->dev = dev;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1a1122a..d155864 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -318,8 +318,7 @@
 /* allocate dst with ip6_dst_ops */
 static struct rt6_info *__ip6_dst_alloc(struct net *net,
 					struct net_device *dev,
-					int flags,
-					struct fib6_table *table)
+					int flags)
 {
 	struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
 					0, DST_OBSOLETE_FORCE_CHK, flags);
@@ -336,10 +335,9 @@
 
 static struct rt6_info *ip6_dst_alloc(struct net *net,
 				      struct net_device *dev,
-				      int flags,
-				      struct fib6_table *table)
+				      int flags)
 {
-	struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags, table);
+	struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags);
 
 	if (rt) {
 		rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC);
@@ -369,10 +367,7 @@
 	struct inet6_dev *idev;
 
 	dst_destroy_metrics_generic(dst);
-
-	if (rt->rt6i_pcpu)
-		free_percpu(rt->rt6i_pcpu);
-
+	free_percpu(rt->rt6i_pcpu);
 	rt6_uncached_list_del(rt);
 
 	idev = rt->rt6i_idev;
@@ -953,8 +948,7 @@
 	if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
 		ort = (struct rt6_info *)ort->dst.from;
 
-	rt = __ip6_dst_alloc(dev_net(ort->dst.dev), ort->dst.dev,
-			     0, ort->rt6i_table);
+	rt = __ip6_dst_alloc(dev_net(ort->dst.dev), ort->dst.dev, 0);
 
 	if (!rt)
 		return NULL;
@@ -986,8 +980,7 @@
 	struct rt6_info *pcpu_rt;
 
 	pcpu_rt = __ip6_dst_alloc(dev_net(rt->dst.dev),
-				  rt->dst.dev, rt->dst.flags,
-				  rt->rt6i_table);
+				  rt->dst.dev, rt->dst.flags);
 
 	if (!pcpu_rt)
 		return NULL;
@@ -1000,32 +993,53 @@
 /* It should be called with read_lock_bh(&tb6_lock) acquired */
 static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt)
 {
-	struct rt6_info *pcpu_rt, *prev, **p;
+	struct rt6_info *pcpu_rt, **p;
 
 	p = this_cpu_ptr(rt->rt6i_pcpu);
 	pcpu_rt = *p;
 
-	if (pcpu_rt)
-		goto done;
+	if (pcpu_rt) {
+		dst_hold(&pcpu_rt->dst);
+		rt6_dst_from_metrics_check(pcpu_rt);
+	}
+	return pcpu_rt;
+}
+
+static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt)
+{
+	struct fib6_table *table = rt->rt6i_table;
+	struct rt6_info *pcpu_rt, *prev, **p;
 
 	pcpu_rt = ip6_rt_pcpu_alloc(rt);
 	if (!pcpu_rt) {
 		struct net *net = dev_net(rt->dst.dev);
 
-		pcpu_rt = net->ipv6.ip6_null_entry;
-		goto done;
+		dst_hold(&net->ipv6.ip6_null_entry->dst);
+		return net->ipv6.ip6_null_entry;
 	}
 
-	prev = cmpxchg(p, NULL, pcpu_rt);
-	if (prev) {
-		/* If someone did it before us, return prev instead */
+	read_lock_bh(&table->tb6_lock);
+	if (rt->rt6i_pcpu) {
+		p = this_cpu_ptr(rt->rt6i_pcpu);
+		prev = cmpxchg(p, NULL, pcpu_rt);
+		if (prev) {
+			/* If someone did it before us, return prev instead */
+			dst_destroy(&pcpu_rt->dst);
+			pcpu_rt = prev;
+		}
+	} else {
+		/* rt has been removed from the fib6 tree
+		 * before we have a chance to acquire the read_lock.
+		 * In this case, don't brother to create a pcpu rt
+		 * since rt is going away anyway.  The next
+		 * dst_check() will trigger a re-lookup.
+		 */
 		dst_destroy(&pcpu_rt->dst);
-		pcpu_rt = prev;
+		pcpu_rt = rt;
 	}
-
-done:
 	dst_hold(&pcpu_rt->dst);
 	rt6_dst_from_metrics_check(pcpu_rt);
+	read_unlock_bh(&table->tb6_lock);
 	return pcpu_rt;
 }
 
@@ -1100,9 +1114,22 @@
 		rt->dst.lastuse = jiffies;
 		rt->dst.__use++;
 		pcpu_rt = rt6_get_pcpu_route(rt);
-		read_unlock_bh(&table->tb6_lock);
+
+		if (pcpu_rt) {
+			read_unlock_bh(&table->tb6_lock);
+		} else {
+			/* We have to do the read_unlock first
+			 * because rt6_make_pcpu_route() may trigger
+			 * ip6_dst_gc() which will take the write_lock.
+			 */
+			dst_hold(&rt->dst);
+			read_unlock_bh(&table->tb6_lock);
+			pcpu_rt = rt6_make_pcpu_route(rt);
+			dst_release(&rt->dst);
+		}
 
 		return pcpu_rt;
+
 	}
 }
 
@@ -1558,7 +1585,7 @@
 	if (unlikely(!idev))
 		return ERR_PTR(-ENODEV);
 
-	rt = ip6_dst_alloc(net, dev, 0, NULL);
+	rt = ip6_dst_alloc(net, dev, 0);
 	if (unlikely(!rt)) {
 		in6_dev_put(idev);
 		dst = ERR_PTR(-ENOMEM);
@@ -1745,7 +1772,8 @@
 	if (!table)
 		goto out;
 
-	rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table);
+	rt = ip6_dst_alloc(net, NULL,
+			   (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT);
 
 	if (!rt) {
 		err = -ENOMEM;
@@ -1834,6 +1862,7 @@
 		int gwa_type;
 
 		gw_addr = &cfg->fc_gateway;
+		gwa_type = ipv6_addr_type(gw_addr);
 
 		/* if gw_addr is local we will fail to detect this in case
 		 * address is still TENTATIVE (DAD in progress). rt6_lookup()
@@ -1841,11 +1870,12 @@
 		 * prefix route was assigned to, which might be non-loopback.
 		 */
 		err = -EINVAL;
-		if (ipv6_chk_addr_and_flags(net, gw_addr, NULL, 0, 0))
+		if (ipv6_chk_addr_and_flags(net, gw_addr,
+					    gwa_type & IPV6_ADDR_LINKLOCAL ?
+					    dev : NULL, 0, 0))
 			goto out;
 
 		rt->rt6i_gateway = *gw_addr;
-		gwa_type = ipv6_addr_type(gw_addr);
 
 		if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) {
 			struct rt6_info *grt;
@@ -2400,7 +2430,7 @@
 {
 	struct net *net = dev_net(idev->dev);
 	struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev,
-					    DST_NOCOUNT, NULL);
+					    DST_NOCOUNT);
 	if (!rt)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 6748c42..7a6cea5 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -943,7 +943,7 @@
 				   &ipv6_hdr(skb)->daddr, tcp_v6_iif(skb));
 	if (req) {
 		nsk = tcp_check_req(sk, skb, req, false);
-		if (!nsk)
+		if (!nsk || nsk == sk)
 			reqsk_put(req);
 		return nsk;
 	}
diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c
index 8fd9feb..8dab4e5 100644
--- a/net/llc/af_llc.c
+++ b/net/llc/af_llc.c
@@ -613,7 +613,7 @@
 		if (signal_pending(current))
 			break;
 		rc = 0;
-		if (sk_wait_data(sk, &timeo))
+		if (sk_wait_data(sk, &timeo, NULL))
 			break;
 	}
 	return rc;
@@ -802,7 +802,7 @@
 			release_sock(sk);
 			lock_sock(sk);
 		} else
-			sk_wait_data(sk, &timeo);
+			sk_wait_data(sk, &timeo, NULL);
 
 		if ((flags & MSG_PEEK) && peek_seq != llc->copied_seq) {
 			net_dbg_ratelimited("LLC(%s:%d): Application bug, race in MSG_PEEK\n",
diff --git a/net/mac80211/debugfs_netdev.c b/net/mac80211/debugfs_netdev.c
index 29236e8..c09c013 100644
--- a/net/mac80211/debugfs_netdev.c
+++ b/net/mac80211/debugfs_netdev.c
@@ -723,6 +723,7 @@
 
 	debugfs_remove_recursive(sdata->vif.debugfs_dir);
 	sdata->vif.debugfs_dir = NULL;
+	sdata->debugfs.subdir_stations = NULL;
 }
 
 void ieee80211_debugfs_rename_netdev(struct ieee80211_sub_if_data *sdata)
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index ed1edac..553ac6d 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1863,10 +1863,6 @@
 	ieee80211_teardown_sdata(sdata);
 }
 
-/*
- * Remove all interfaces, may only be called at hardware unregistration
- * time because it doesn't do RCU-safe list removals.
- */
 void ieee80211_remove_interfaces(struct ieee80211_local *local)
 {
 	struct ieee80211_sub_if_data *sdata, *tmp;
@@ -1875,14 +1871,21 @@
 
 	ASSERT_RTNL();
 
-	/*
-	 * Close all AP_VLAN interfaces first, as otherwise they
-	 * might be closed while the AP interface they belong to
-	 * is closed, causing unregister_netdevice_many() to crash.
+	/* Before destroying the interfaces, make sure they're all stopped so
+	 * that the hardware is stopped. Otherwise, the driver might still be
+	 * iterating the interfaces during the shutdown, e.g. from a worker
+	 * or from RX processing or similar, and if it does so (using atomic
+	 * iteration) while we're manipulating the list, the iteration will
+	 * crash.
+	 *
+	 * After this, the hardware should be stopped and the driver should
+	 * have stopped all of its activities, so that we can do RCU-unaware
+	 * manipulations of the interface list below.
 	 */
-	list_for_each_entry(sdata, &local->interfaces, list)
-		if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
-			dev_close(sdata->dev);
+	cfg80211_shutdown_all_interfaces(local->hw.wiphy);
+
+	WARN(local->open_count, "%s: open count remains %d\n",
+	     wiphy_name(local->hw.wiphy), local->open_count);
 
 	mutex_lock(&local->iflist_mtx);
 	list_for_each_entry_safe(sdata, tmp, &local->interfaces, list) {
diff --git a/net/mac80211/mesh_plink.c b/net/mac80211/mesh_plink.c
index 5438d13..3b59099 100644
--- a/net/mac80211/mesh_plink.c
+++ b/net/mac80211/mesh_plink.c
@@ -306,7 +306,7 @@
 		if (action == WLAN_SP_MESH_PEERING_CONFIRM) {
 			/* AID */
 			pos = skb_put(skb, 2);
-			put_unaligned_le16(plid, pos + 2);
+			put_unaligned_le16(plid, pos);
 		}
 		if (ieee80211_add_srates_ie(sdata, skb, true, band) ||
 		    ieee80211_add_ext_srates_ie(sdata, skb, true, band) ||
@@ -1122,6 +1122,9 @@
 						WLAN_SP_MESH_PEERING_CONFIRM) {
 		baseaddr += 4;
 		baselen += 4;
+
+		if (baselen > len)
+			return;
 	}
 	ieee802_11_parse_elems(baseaddr, len - baselen, true, &elems);
 	mesh_process_plink_frame(sdata, mgmt, &elems);
diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
index 06b60980..b676b9f 100644
--- a/net/mac80211/pm.c
+++ b/net/mac80211/pm.c
@@ -76,6 +76,22 @@
 			if (sdata->vif.type != NL80211_IFTYPE_STATION)
 				continue;
 			ieee80211_mgd_quiesce(sdata);
+			/* If suspended during TX in progress, and wowlan
+			 * is enabled (connection will be active) there
+			 * can be a race where the driver is put out
+			 * of power-save due to TX and during suspend
+			 * dynamic_ps_timer is cancelled and TX packet
+			 * is flushed, leaving the driver in ACTIVE even
+			 * after resuming until dynamic_ps_timer puts
+			 * driver back in DOZE.
+			 */
+			if (sdata->u.mgd.associated &&
+			    sdata->u.mgd.powersave &&
+			     !(local->hw.conf.flags & IEEE80211_CONF_PS)) {
+				local->hw.conf.flags |= IEEE80211_CONF_PS;
+				ieee80211_hw_config(local,
+						    IEEE80211_CONF_CHANGE_PS);
+			}
 		}
 
 		err = drv_suspend(local, wowlan);
diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c
index 247552a..3ece7d1 100644
--- a/net/mac80211/rc80211_minstrel.c
+++ b/net/mac80211/rc80211_minstrel.c
@@ -92,14 +92,15 @@
 static inline void
 minstrel_sort_best_tp_rates(struct minstrel_sta_info *mi, int i, u8 *tp_list)
 {
-	int j = MAX_THR_RATES;
-	struct minstrel_rate_stats *tmp_mrs = &mi->r[j - 1].stats;
+	int j;
+	struct minstrel_rate_stats *tmp_mrs;
 	struct minstrel_rate_stats *cur_mrs = &mi->r[i].stats;
 
-	while (j > 0 && (minstrel_get_tp_avg(&mi->r[i], cur_mrs->prob_ewma) >
-	       minstrel_get_tp_avg(&mi->r[tp_list[j - 1]], tmp_mrs->prob_ewma))) {
-		j--;
+	for (j = MAX_THR_RATES; j > 0; --j) {
 		tmp_mrs = &mi->r[tp_list[j - 1]].stats;
+		if (minstrel_get_tp_avg(&mi->r[i], cur_mrs->prob_ewma) <=
+		    minstrel_get_tp_avg(&mi->r[tp_list[j - 1]], tmp_mrs->prob_ewma))
+			break;
 	}
 
 	if (j < MAX_THR_RATES - 1)
diff --git a/net/mac80211/tdls.c b/net/mac80211/tdls.c
index ad31b2d..8db6e29 100644
--- a/net/mac80211/tdls.c
+++ b/net/mac80211/tdls.c
@@ -60,6 +60,7 @@
 	struct ieee80211_channel *ch;
 	struct cfg80211_chan_def chandef;
 	int i, subband_start;
+	struct wiphy *wiphy = sdata->local->hw.wiphy;
 
 	for (i = start; i <= end; i += spacing) {
 		if (!ch_cnt)
@@ -70,9 +71,8 @@
 			/* we will be active on the channel */
 			cfg80211_chandef_create(&chandef, ch,
 						NL80211_CHAN_NO_HT);
-			if (cfg80211_reg_can_beacon(sdata->local->hw.wiphy,
-						    &chandef,
-						    sdata->wdev.iftype)) {
+			if (cfg80211_reg_can_beacon_relax(wiphy, &chandef,
+							  sdata->wdev.iftype)) {
 				ch_cnt++;
 				/*
 				 * check if the next channel is also part of
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 8410bb3..b823350 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1117,7 +1117,9 @@
 			queued = true;
 			info->control.vif = &tx->sdata->vif;
 			info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
-			info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
+			info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS |
+					IEEE80211_TX_CTL_NO_PS_BUFFER |
+					IEEE80211_TX_STATUS_EOSP;
 			__skb_queue_tail(&tid_tx->pending, skb);
 			if (skb_queue_len(&tid_tx->pending) > STA_MAX_TX_BUFFER)
 				purge_skb = __skb_dequeue(&tid_tx->pending);
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 5d2b806..38fbc19 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -319,7 +319,13 @@
 		 * return *ignored=0 i.e. ICMP and NF_DROP
 		 */
 		sched = rcu_dereference(svc->scheduler);
-		dest = sched->schedule(svc, skb, iph);
+		if (sched) {
+			/* read svc->sched_data after svc->scheduler */
+			smp_rmb();
+			dest = sched->schedule(svc, skb, iph);
+		} else {
+			dest = NULL;
+		}
 		if (!dest) {
 			IP_VS_DBG(1, "p-schedule: no dest found.\n");
 			kfree(param.pe_data);
@@ -467,7 +473,13 @@
 	}
 
 	sched = rcu_dereference(svc->scheduler);
-	dest = sched->schedule(svc, skb, iph);
+	if (sched) {
+		/* read svc->sched_data after svc->scheduler */
+		smp_rmb();
+		dest = sched->schedule(svc, skb, iph);
+	} else {
+		dest = NULL;
+	}
 	if (dest == NULL) {
 		IP_VS_DBG(1, "Schedule: no dest found.\n");
 		return NULL;
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 285eae3..24c5542 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -842,15 +842,16 @@
 	__ip_vs_dst_cache_reset(dest);
 	spin_unlock_bh(&dest->dst_lock);
 
-	sched = rcu_dereference_protected(svc->scheduler, 1);
 	if (add) {
 		ip_vs_start_estimator(svc->net, &dest->stats);
 		list_add_rcu(&dest->n_list, &svc->destinations);
 		svc->num_dests++;
-		if (sched->add_dest)
+		sched = rcu_dereference_protected(svc->scheduler, 1);
+		if (sched && sched->add_dest)
 			sched->add_dest(svc, dest);
 	} else {
-		if (sched->upd_dest)
+		sched = rcu_dereference_protected(svc->scheduler, 1);
+		if (sched && sched->upd_dest)
 			sched->upd_dest(svc, dest);
 	}
 }
@@ -1084,7 +1085,7 @@
 		struct ip_vs_scheduler *sched;
 
 		sched = rcu_dereference_protected(svc->scheduler, 1);
-		if (sched->del_dest)
+		if (sched && sched->del_dest)
 			sched->del_dest(svc, dest);
 	}
 }
@@ -1175,11 +1176,14 @@
 	ip_vs_use_count_inc();
 
 	/* Lookup the scheduler by 'u->sched_name' */
-	sched = ip_vs_scheduler_get(u->sched_name);
-	if (sched == NULL) {
-		pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name);
-		ret = -ENOENT;
-		goto out_err;
+	if (strcmp(u->sched_name, "none")) {
+		sched = ip_vs_scheduler_get(u->sched_name);
+		if (!sched) {
+			pr_info("Scheduler module ip_vs_%s not found\n",
+				u->sched_name);
+			ret = -ENOENT;
+			goto out_err;
+		}
 	}
 
 	if (u->pe_name && *u->pe_name) {
@@ -1240,10 +1244,12 @@
 	spin_lock_init(&svc->stats.lock);
 
 	/* Bind the scheduler */
-	ret = ip_vs_bind_scheduler(svc, sched);
-	if (ret)
-		goto out_err;
-	sched = NULL;
+	if (sched) {
+		ret = ip_vs_bind_scheduler(svc, sched);
+		if (ret)
+			goto out_err;
+		sched = NULL;
+	}
 
 	/* Bind the ct retriever */
 	RCU_INIT_POINTER(svc->pe, pe);
@@ -1291,17 +1297,20 @@
 static int
 ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u)
 {
-	struct ip_vs_scheduler *sched, *old_sched;
+	struct ip_vs_scheduler *sched = NULL, *old_sched;
 	struct ip_vs_pe *pe = NULL, *old_pe = NULL;
 	int ret = 0;
 
 	/*
 	 * Lookup the scheduler, by 'u->sched_name'
 	 */
-	sched = ip_vs_scheduler_get(u->sched_name);
-	if (sched == NULL) {
-		pr_info("Scheduler module ip_vs_%s not found\n", u->sched_name);
-		return -ENOENT;
+	if (strcmp(u->sched_name, "none")) {
+		sched = ip_vs_scheduler_get(u->sched_name);
+		if (!sched) {
+			pr_info("Scheduler module ip_vs_%s not found\n",
+				u->sched_name);
+			return -ENOENT;
+		}
 	}
 	old_sched = sched;
 
@@ -1329,14 +1338,20 @@
 
 	old_sched = rcu_dereference_protected(svc->scheduler, 1);
 	if (sched != old_sched) {
-		/* Bind the new scheduler */
-		ret = ip_vs_bind_scheduler(svc, sched);
-		if (ret) {
-			old_sched = sched;
-			goto out;
+		if (old_sched) {
+			ip_vs_unbind_scheduler(svc, old_sched);
+			RCU_INIT_POINTER(svc->scheduler, NULL);
+			/* Wait all svc->sched_data users */
+			synchronize_rcu();
 		}
-		/* Unbind the old scheduler on success */
-		ip_vs_unbind_scheduler(svc, old_sched);
+		/* Bind the new scheduler */
+		if (sched) {
+			ret = ip_vs_bind_scheduler(svc, sched);
+			if (ret) {
+				ip_vs_scheduler_put(sched);
+				goto out;
+			}
+		}
 	}
 
 	/*
@@ -1982,6 +1997,7 @@
 		const struct ip_vs_iter *iter = seq->private;
 		const struct ip_vs_dest *dest;
 		struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler);
+		char *sched_name = sched ? sched->name : "none";
 
 		if (iter->table == ip_vs_svc_table) {
 #ifdef CONFIG_IP_VS_IPV6
@@ -1990,18 +2006,18 @@
 					   ip_vs_proto_name(svc->protocol),
 					   &svc->addr.in6,
 					   ntohs(svc->port),
-					   sched->name);
+					   sched_name);
 			else
 #endif
 				seq_printf(seq, "%s  %08X:%04X %s %s ",
 					   ip_vs_proto_name(svc->protocol),
 					   ntohl(svc->addr.ip),
 					   ntohs(svc->port),
-					   sched->name,
+					   sched_name,
 					   (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
 		} else {
 			seq_printf(seq, "FWM  %08X %s %s",
-				   svc->fwmark, sched->name,
+				   svc->fwmark, sched_name,
 				   (svc->flags & IP_VS_SVC_F_ONEPACKET)?"ops ":"");
 		}
 
@@ -2427,13 +2443,15 @@
 {
 	struct ip_vs_scheduler *sched;
 	struct ip_vs_kstats kstats;
+	char *sched_name;
 
 	sched = rcu_dereference_protected(src->scheduler, 1);
+	sched_name = sched ? sched->name : "none";
 	dst->protocol = src->protocol;
 	dst->addr = src->addr.ip;
 	dst->port = src->port;
 	dst->fwmark = src->fwmark;
-	strlcpy(dst->sched_name, sched->name, sizeof(dst->sched_name));
+	strlcpy(dst->sched_name, sched_name, sizeof(dst->sched_name));
 	dst->flags = src->flags;
 	dst->timeout = src->timeout / HZ;
 	dst->netmask = src->netmask;
@@ -2892,6 +2910,7 @@
 	struct ip_vs_flags flags = { .flags = svc->flags,
 				     .mask = ~0 };
 	struct ip_vs_kstats kstats;
+	char *sched_name;
 
 	nl_service = nla_nest_start(skb, IPVS_CMD_ATTR_SERVICE);
 	if (!nl_service)
@@ -2910,8 +2929,9 @@
 	}
 
 	sched = rcu_dereference_protected(svc->scheduler, 1);
+	sched_name = sched ? sched->name : "none";
 	pe = rcu_dereference_protected(svc->pe, 1);
-	if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched->name) ||
+	if (nla_put_string(skb, IPVS_SVC_ATTR_SCHED_NAME, sched_name) ||
 	    (pe && nla_put_string(skb, IPVS_SVC_ATTR_PE_NAME, pe->name)) ||
 	    nla_put(skb, IPVS_SVC_ATTR_FLAGS, sizeof(flags), &flags) ||
 	    nla_put_u32(skb, IPVS_SVC_ATTR_TIMEOUT, svc->timeout / HZ) ||
diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c
index 199760c..7e81416 100644
--- a/net/netfilter/ipvs/ip_vs_sched.c
+++ b/net/netfilter/ipvs/ip_vs_sched.c
@@ -74,7 +74,7 @@
 
 	if (sched->done_service)
 		sched->done_service(svc);
-	/* svc->scheduler can not be set to NULL */
+	/* svc->scheduler can be set to NULL only by caller */
 }
 
 
@@ -147,21 +147,21 @@
 
 void ip_vs_scheduler_err(struct ip_vs_service *svc, const char *msg)
 {
-	struct ip_vs_scheduler *sched;
+	struct ip_vs_scheduler *sched = rcu_dereference(svc->scheduler);
+	char *sched_name = sched ? sched->name : "none";
 
-	sched = rcu_dereference(svc->scheduler);
 	if (svc->fwmark) {
 		IP_VS_ERR_RL("%s: FWM %u 0x%08X - %s\n",
-			     sched->name, svc->fwmark, svc->fwmark, msg);
+			     sched_name, svc->fwmark, svc->fwmark, msg);
 #ifdef CONFIG_IP_VS_IPV6
 	} else if (svc->af == AF_INET6) {
 		IP_VS_ERR_RL("%s: %s [%pI6c]:%d - %s\n",
-			     sched->name, ip_vs_proto_name(svc->protocol),
+			     sched_name, ip_vs_proto_name(svc->protocol),
 			     &svc->addr.in6, ntohs(svc->port), msg);
 #endif
 	} else {
 		IP_VS_ERR_RL("%s: %s %pI4:%d - %s\n",
-			     sched->name, ip_vs_proto_name(svc->protocol),
+			     sched_name, ip_vs_proto_name(svc->protocol),
 			     &svc->addr.ip, ntohs(svc->port), msg);
 	}
 }
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index b08ba95..d99ad93 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -612,7 +612,7 @@
 			pkts = atomic_add_return(1, &cp->in_pkts);
 		else
 			pkts = sysctl_sync_threshold(ipvs);
-		ip_vs_sync_conn(net, cp->control, pkts);
+		ip_vs_sync_conn(net, cp, pkts);
 	}
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index bf66a86..258a0b0 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -130,7 +130,6 @@
 
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = daddr;
-	fl4.saddr = (rt_mode & IP_VS_RT_MODE_CONNECT) ? *saddr : 0;
 	fl4.flowi4_flags = (rt_mode & IP_VS_RT_MODE_KNOWN_NH) ?
 			   FLOWI_FLAG_KNOWN_NH : 0;
 
@@ -505,6 +504,13 @@
 	return -1;
 
 err_unreach:
+	/* The ip6_link_failure function requires the dev field to be set
+	 * in order to get the net (further for the sake of fwmark
+	 * reflection).
+	 */
+	if (!skb->dev)
+		skb->dev = skb_dst(skb)->dev;
+
 	dst_link_failure(skb);
 	return -1;
 }
@@ -523,10 +529,27 @@
 	if (ret == NF_ACCEPT) {
 		nf_reset(skb);
 		skb_forward_csum(skb);
+		if (!skb->sk)
+			skb_sender_cpu_clear(skb);
 	}
 	return ret;
 }
 
+/* In the event of a remote destination, it's possible that we would have
+ * matches against an old socket (particularly a TIME-WAIT socket). This
+ * causes havoc down the line (ip_local_out et. al. expect regular sockets
+ * and invalid memory accesses will happen) so simply drop the association
+ * in this case.
+*/
+static inline void ip_vs_drop_early_demux_sk(struct sk_buff *skb)
+{
+	/* If dev is set, the packet came from the LOCAL_IN callback and
+	 * not from a local TCP socket.
+	 */
+	if (skb->dev)
+		skb_orphan(skb);
+}
+
 /* return NF_STOLEN (sent) or NF_ACCEPT if local=1 (not sent) */
 static inline int ip_vs_nat_send_or_cont(int pf, struct sk_buff *skb,
 					 struct ip_vs_conn *cp, int local)
@@ -538,12 +561,23 @@
 		ip_vs_notrack(skb);
 	else
 		ip_vs_update_conntrack(skb, cp, 1);
+
+	/* Remove the early_demux association unless it's bound for the
+	 * exact same port and address on this host after translation.
+	 */
+	if (!local || cp->vport != cp->dport ||
+	    !ip_vs_addr_equal(cp->af, &cp->vaddr, &cp->daddr))
+		ip_vs_drop_early_demux_sk(skb);
+
 	if (!local) {
 		skb_forward_csum(skb);
+		if (!skb->sk)
+			skb_sender_cpu_clear(skb);
 		NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb,
 			NULL, skb_dst(skb)->dev, dst_output_sk);
 	} else
 		ret = NF_ACCEPT;
+
 	return ret;
 }
 
@@ -557,7 +591,10 @@
 	if (likely(!(cp->flags & IP_VS_CONN_F_NFCT)))
 		ip_vs_notrack(skb);
 	if (!local) {
+		ip_vs_drop_early_demux_sk(skb);
 		skb_forward_csum(skb);
+		if (!skb->sk)
+			skb_sender_cpu_clear(skb);
 		NF_HOOK(pf, NF_INET_LOCAL_OUT, NULL, skb,
 			NULL, skb_dst(skb)->dev, dst_output_sk);
 	} else
@@ -845,6 +882,8 @@
 	struct ipv6hdr *old_ipv6h = NULL;
 #endif
 
+	ip_vs_drop_early_demux_sk(skb);
+
 	if (skb_headroom(skb) < max_headroom || skb_cloned(skb)) {
 		new_skb = skb_realloc_headroom(skb, max_headroom);
 		if (!new_skb)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 13fad86..3c20d02 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -287,6 +287,46 @@
 	spin_unlock(&pcpu->lock);
 }
 
+/* Released via destroy_conntrack() */
+struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags)
+{
+	struct nf_conn *tmpl;
+
+	tmpl = kzalloc(sizeof(*tmpl), flags);
+	if (tmpl == NULL)
+		return NULL;
+
+	tmpl->status = IPS_TEMPLATE;
+	write_pnet(&tmpl->ct_net, net);
+
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	if (zone) {
+		struct nf_conntrack_zone *nf_ct_zone;
+
+		nf_ct_zone = nf_ct_ext_add(tmpl, NF_CT_EXT_ZONE, flags);
+		if (!nf_ct_zone)
+			goto out_free;
+		nf_ct_zone->id = zone;
+	}
+#endif
+	atomic_set(&tmpl->ct_general.use, 0);
+
+	return tmpl;
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+out_free:
+	kfree(tmpl);
+	return NULL;
+#endif
+}
+EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc);
+
+static void nf_ct_tmpl_free(struct nf_conn *tmpl)
+{
+	nf_ct_ext_destroy(tmpl);
+	nf_ct_ext_free(tmpl);
+	kfree(tmpl);
+}
+
 static void
 destroy_conntrack(struct nf_conntrack *nfct)
 {
@@ -298,6 +338,10 @@
 	NF_CT_ASSERT(atomic_read(&nfct->use) == 0);
 	NF_CT_ASSERT(!timer_pending(&ct->timeout));
 
+	if (unlikely(nf_ct_is_template(ct))) {
+		nf_ct_tmpl_free(ct);
+		return;
+	}
 	rcu_read_lock();
 	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
 	if (l4proto && l4proto->destroy)
@@ -540,28 +584,6 @@
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
 
-/* deletion from this larval template list happens via nf_ct_put() */
-void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl)
-{
-	struct ct_pcpu *pcpu;
-
-	__set_bit(IPS_TEMPLATE_BIT, &tmpl->status);
-	__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
-	nf_conntrack_get(&tmpl->ct_general);
-
-	/* add this conntrack to the (per cpu) tmpl list */
-	local_bh_disable();
-	tmpl->cpu = smp_processor_id();
-	pcpu = per_cpu_ptr(nf_ct_net(tmpl)->ct.pcpu_lists, tmpl->cpu);
-
-	spin_lock(&pcpu->lock);
-	/* Overload tuple linked list to put us in template list. */
-	hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
-				 &pcpu->tmpl);
-	spin_unlock_bh(&pcpu->lock);
-}
-EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert);
-
 /* Confirm a connection given skb; places it in hash table */
 int
 __nf_conntrack_confirm(struct sk_buff *skb)
@@ -1522,10 +1544,8 @@
 	sz = nr_slots * sizeof(struct hlist_nulls_head);
 	hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO,
 					get_order(sz));
-	if (!hash) {
-		printk(KERN_WARNING "nf_conntrack: falling back to vmalloc.\n");
+	if (!hash)
 		hash = vzalloc(sz);
-	}
 
 	if (hash && nulls)
 		for (i = 0; i < nr_slots; i++)
@@ -1751,7 +1771,6 @@
 		spin_lock_init(&pcpu->lock);
 		INIT_HLIST_NULLS_HEAD(&pcpu->unconfirmed, UNCONFIRMED_NULLS_VAL);
 		INIT_HLIST_NULLS_HEAD(&pcpu->dying, DYING_NULLS_VAL);
-		INIT_HLIST_NULLS_HEAD(&pcpu->tmpl, TEMPLATE_NULLS_VAL);
 	}
 
 	net->ct.stat = alloc_percpu(struct ip_conntrack_stat);
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 7a17070..b45a422 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -219,7 +219,8 @@
 			a->mask.src.u3.all[count] & b->mask.src.u3.all[count];
 	}
 
-	return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask);
+	return nf_ct_tuple_mask_cmp(&a->tuple, &b->tuple, &intersect_mask) &&
+	       nf_ct_zone(a->master) == nf_ct_zone(b->master);
 }
 
 static inline int expect_matches(const struct nf_conntrack_expect *a,
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index d1c2394..6b8b0ab 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2995,11 +2995,6 @@
 	}
 
 	err = nf_ct_expect_related_report(exp, portid, report);
-	if (err < 0)
-		goto err_exp;
-
-	return 0;
-err_exp:
 	nf_ct_expect_put(exp);
 err_ct:
 	nf_ct_put(ct);
diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c
index cd60d39..8a8b2ab 100644
--- a/net/netfilter/nf_queue.c
+++ b/net/netfilter/nf_queue.c
@@ -213,7 +213,7 @@
 
 	if (verdict == NF_ACCEPT) {
 	next_hook:
-		verdict = nf_iterate(&nf_hooks[entry->state.pf][entry->state.hook],
+		verdict = nf_iterate(entry->state.hook_list,
 				     skb, &entry->state, &elem);
 	}
 
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index 789feea..d7f1685 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -349,23 +349,20 @@
 static int __net_init synproxy_net_init(struct net *net)
 {
 	struct synproxy_net *snet = synproxy_pernet(net);
-	struct nf_conntrack_tuple t;
 	struct nf_conn *ct;
 	int err = -ENOMEM;
 
-	memset(&t, 0, sizeof(t));
-	ct = nf_conntrack_alloc(net, 0, &t, &t, GFP_KERNEL);
-	if (IS_ERR(ct)) {
-		err = PTR_ERR(ct);
+	ct = nf_ct_tmpl_alloc(net, 0, GFP_KERNEL);
+	if (!ct)
 		goto err1;
-	}
 
 	if (!nfct_seqadj_ext_add(ct))
 		goto err2;
 	if (!nfct_synproxy_ext_add(ct))
 		goto err2;
 
-	nf_conntrack_tmpl_insert(net, ct);
+	__set_bit(IPS_CONFIRMED_BIT, &ct->status);
+	nf_conntrack_get(&ct->ct_general);
 	snet->tmpl = ct;
 
 	snet->stats = alloc_percpu(struct synproxy_stats);
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 8b117c9..0c0e8ec 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -269,6 +269,12 @@
 	}
 }
 
+enum {
+	NFNL_BATCH_FAILURE	= (1 << 0),
+	NFNL_BATCH_DONE		= (1 << 1),
+	NFNL_BATCH_REPLAY	= (1 << 2),
+};
+
 static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
 				u_int16_t subsys_id)
 {
@@ -276,13 +282,15 @@
 	struct net *net = sock_net(skb->sk);
 	const struct nfnetlink_subsystem *ss;
 	const struct nfnl_callback *nc;
-	bool success = true, done = false;
 	static LIST_HEAD(err_list);
+	u32 status;
 	int err;
 
 	if (subsys_id >= NFNL_SUBSYS_COUNT)
 		return netlink_ack(skb, nlh, -EINVAL);
 replay:
+	status = 0;
+
 	skb = netlink_skb_clone(oskb, GFP_KERNEL);
 	if (!skb)
 		return netlink_ack(oskb, nlh, -ENOMEM);
@@ -336,10 +344,10 @@
 		if (type == NFNL_MSG_BATCH_BEGIN) {
 			/* Malformed: Batch begin twice */
 			nfnl_err_reset(&err_list);
-			success = false;
+			status |= NFNL_BATCH_FAILURE;
 			goto done;
 		} else if (type == NFNL_MSG_BATCH_END) {
-			done = true;
+			status |= NFNL_BATCH_DONE;
 			goto done;
 		} else if (type < NLMSG_MIN_TYPE) {
 			err = -EINVAL;
@@ -382,11 +390,8 @@
 			 * original skb.
 			 */
 			if (err == -EAGAIN) {
-				nfnl_err_reset(&err_list);
-				ss->abort(oskb);
-				nfnl_unlock(subsys_id);
-				kfree_skb(skb);
-				goto replay;
+				status |= NFNL_BATCH_REPLAY;
+				goto next;
 			}
 		}
 ack:
@@ -402,7 +407,7 @@
 				 */
 				nfnl_err_reset(&err_list);
 				netlink_ack(skb, nlmsg_hdr(oskb), -ENOMEM);
-				success = false;
+				status |= NFNL_BATCH_FAILURE;
 				goto done;
 			}
 			/* We don't stop processing the batch on errors, thus,
@@ -410,19 +415,26 @@
 			 * triggers.
 			 */
 			if (err)
-				success = false;
+				status |= NFNL_BATCH_FAILURE;
 		}
-
+next:
 		msglen = NLMSG_ALIGN(nlh->nlmsg_len);
 		if (msglen > skb->len)
 			msglen = skb->len;
 		skb_pull(skb, msglen);
 	}
 done:
-	if (success && done)
-		ss->commit(oskb);
-	else
+	if (status & NFNL_BATCH_REPLAY) {
 		ss->abort(oskb);
+		nfnl_err_reset(&err_list);
+		nfnl_unlock(subsys_id);
+		kfree_skb(skb);
+		goto replay;
+	} else if (status == NFNL_BATCH_DONE) {
+		ss->commit(oskb);
+	} else {
+		ss->abort(oskb);
+	}
 
 	nfnl_err_deliver(&err_list, oskb);
 	nfnl_unlock(subsys_id);
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 75747ae..43ddeee 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -184,7 +184,6 @@
 static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 			  struct xt_ct_target_info_v1 *info)
 {
-	struct nf_conntrack_tuple t;
 	struct nf_conn *ct;
 	int ret = -EOPNOTSUPP;
 
@@ -202,11 +201,11 @@
 	if (ret < 0)
 		goto err1;
 
-	memset(&t, 0, sizeof(t));
-	ct = nf_conntrack_alloc(par->net, info->zone, &t, &t, GFP_KERNEL);
-	ret = PTR_ERR(ct);
-	if (IS_ERR(ct))
+	ct = nf_ct_tmpl_alloc(par->net, info->zone, GFP_KERNEL);
+	if (!ct) {
+		ret = -ENOMEM;
 		goto err2;
+	}
 
 	ret = 0;
 	if ((info->ct_events || info->exp_events) &&
@@ -227,8 +226,8 @@
 		if (ret < 0)
 			goto err3;
 	}
-
-	nf_conntrack_tmpl_insert(par->net, ct);
+	__set_bit(IPS_CONFIRMED_BIT, &ct->status);
+	nf_conntrack_get(&ct->ct_general);
 out:
 	info->ct = ct;
 	return 0;
diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index f407ebc1..29d2c31 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -126,6 +126,7 @@
 		goto out;
 	}
 
+	sysfs_attr_init(&info->timer->attr.attr);
 	info->timer->attr.attr.name = kstrdup(info->label, GFP_KERNEL);
 	if (!info->timer->attr.attr.name) {
 		ret = -ENOMEM;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index dea9253..67d2104 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -158,7 +158,7 @@
 out:
 	spin_unlock(&netlink_tap_lock);
 
-	if (found && nt->module)
+	if (found)
 		module_put(nt->module);
 
 	return found ? 0 : -ENODEV;
@@ -357,25 +357,52 @@
 	return NULL;
 }
 
+
+static void
+__netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, bool tx_ring, void **pg_vec,
+		   unsigned int order)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+	struct sk_buff_head *queue;
+	struct netlink_ring *ring;
+
+	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
+	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
+
+	spin_lock_bh(&queue->lock);
+
+	ring->frame_max		= req->nm_frame_nr - 1;
+	ring->head		= 0;
+	ring->frame_size	= req->nm_frame_size;
+	ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
+
+	swap(ring->pg_vec_len, req->nm_block_nr);
+	swap(ring->pg_vec_order, order);
+	swap(ring->pg_vec, pg_vec);
+
+	__skb_queue_purge(queue);
+	spin_unlock_bh(&queue->lock);
+
+	WARN_ON(atomic_read(&nlk->mapped));
+
+	if (pg_vec)
+		free_pg_vec(pg_vec, order, req->nm_block_nr);
+}
+
 static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
-			    bool closing, bool tx_ring)
+			    bool tx_ring)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 	struct netlink_ring *ring;
-	struct sk_buff_head *queue;
 	void **pg_vec = NULL;
 	unsigned int order = 0;
-	int err;
 
 	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
-	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
 
-	if (!closing) {
-		if (atomic_read(&nlk->mapped))
-			return -EBUSY;
-		if (atomic_read(&ring->pending))
-			return -EBUSY;
-	}
+	if (atomic_read(&nlk->mapped))
+		return -EBUSY;
+	if (atomic_read(&ring->pending))
+		return -EBUSY;
 
 	if (req->nm_block_nr) {
 		if (ring->pg_vec != NULL)
@@ -407,31 +434,19 @@
 			return -EINVAL;
 	}
 
-	err = -EBUSY;
 	mutex_lock(&nlk->pg_vec_lock);
-	if (closing || atomic_read(&nlk->mapped) == 0) {
-		err = 0;
-		spin_lock_bh(&queue->lock);
-
-		ring->frame_max		= req->nm_frame_nr - 1;
-		ring->head		= 0;
-		ring->frame_size	= req->nm_frame_size;
-		ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
-
-		swap(ring->pg_vec_len, req->nm_block_nr);
-		swap(ring->pg_vec_order, order);
-		swap(ring->pg_vec, pg_vec);
-
-		__skb_queue_purge(queue);
-		spin_unlock_bh(&queue->lock);
-
-		WARN_ON(atomic_read(&nlk->mapped));
+	if (atomic_read(&nlk->mapped) == 0) {
+		__netlink_set_ring(sk, req, tx_ring, pg_vec, order);
+		mutex_unlock(&nlk->pg_vec_lock);
+		return 0;
 	}
+
 	mutex_unlock(&nlk->pg_vec_lock);
 
 	if (pg_vec)
 		free_pg_vec(pg_vec, order, req->nm_block_nr);
-	return err;
+
+	return -EBUSY;
 }
 
 static void netlink_mm_open(struct vm_area_struct *vma)
@@ -900,10 +915,10 @@
 
 		memset(&req, 0, sizeof(req));
 		if (nlk->rx_ring.pg_vec)
-			netlink_set_ring(sk, &req, true, false);
+			__netlink_set_ring(sk, &req, false, NULL, 0);
 		memset(&req, 0, sizeof(req));
 		if (nlk->tx_ring.pg_vec)
-			netlink_set_ring(sk, &req, true, true);
+			__netlink_set_ring(sk, &req, true, NULL, 0);
 	}
 #endif /* CONFIG_NETLINK_MMAP */
 
@@ -1081,6 +1096,11 @@
 
 	err = __netlink_insert(table, sk);
 	if (err) {
+		/* In case the hashtable backend returns with -EBUSY
+		 * from here, it must not escape to the caller.
+		 */
+		if (unlikely(err == -EBUSY))
+			err = -EOVERFLOW;
 		if (err == -EEXIST)
 			err = -EADDRINUSE;
 		nlk_sk(sk)->portid = 0;
@@ -2223,7 +2243,7 @@
 			return -EINVAL;
 		if (copy_from_user(&req, optval, sizeof(req)))
 			return -EFAULT;
-		err = netlink_set_ring(sk, &req, false,
+		err = netlink_set_ring(sk, &req,
 				       optname == NETLINK_TX_RING);
 		break;
 	}
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 8a8c0b8..ee34f47 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -273,28 +273,36 @@
 	return 0;
 }
 
-static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
-			__be32 *addr, __be32 new_addr)
+static void update_ip_l4_checksum(struct sk_buff *skb, struct iphdr *nh,
+				  __be32 addr, __be32 new_addr)
 {
 	int transport_len = skb->len - skb_transport_offset(skb);
 
+	if (nh->frag_off & htons(IP_OFFSET))
+		return;
+
 	if (nh->protocol == IPPROTO_TCP) {
 		if (likely(transport_len >= sizeof(struct tcphdr)))
 			inet_proto_csum_replace4(&tcp_hdr(skb)->check, skb,
-						 *addr, new_addr, 1);
+						 addr, new_addr, 1);
 	} else if (nh->protocol == IPPROTO_UDP) {
 		if (likely(transport_len >= sizeof(struct udphdr))) {
 			struct udphdr *uh = udp_hdr(skb);
 
 			if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) {
 				inet_proto_csum_replace4(&uh->check, skb,
-							 *addr, new_addr, 1);
+							 addr, new_addr, 1);
 				if (!uh->check)
 					uh->check = CSUM_MANGLED_0;
 			}
 		}
 	}
+}
 
+static void set_ip_addr(struct sk_buff *skb, struct iphdr *nh,
+			__be32 *addr, __be32 new_addr)
+{
+	update_ip_l4_checksum(skb, nh, *addr, new_addr);
 	csum_replace4(&nh->check, *addr, new_addr);
 	skb_clear_hash(skb);
 	*addr = new_addr;
diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c
index 4613df8..6552394 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -752,7 +752,7 @@
 	BUILD_BUG_ON(sizeof(struct sw_flow_key) % sizeof(long));
 
 	flow_cache = kmem_cache_create("sw_flow", sizeof(struct sw_flow)
-				       + (num_possible_nodes()
+				       + (nr_node_ids
 					  * sizeof(struct flow_stats *)),
 				       0, 0, NULL);
 	if (flow_cache == NULL)
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c9e8741..ed458b3 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2403,7 +2403,8 @@
 		}
 		tp_len = tpacket_fill_skb(po, skb, ph, dev, size_max, proto,
 					  addr, hlen);
-		if (tp_len > dev->mtu + dev->hard_header_len) {
+		if (likely(tp_len >= 0) &&
+		    tp_len > dev->mtu + dev->hard_header_len) {
 			struct ethhdr *ehdr;
 			/* Earlier code assumed this would be a VLAN pkt,
 			 * double-check this now that we have the actual
@@ -2784,7 +2785,7 @@
 static int packet_do_bind(struct sock *sk, struct net_device *dev, __be16 proto)
 {
 	struct packet_sock *po = pkt_sk(sk);
-	const struct net_device *dev_curr;
+	struct net_device *dev_curr;
 	__be16 proto_curr;
 	bool need_rehook;
 
@@ -2808,15 +2809,13 @@
 
 		po->num = proto;
 		po->prot_hook.type = proto;
-
-		if (po->prot_hook.dev)
-			dev_put(po->prot_hook.dev);
-
 		po->prot_hook.dev = dev;
 
 		po->ifindex = dev ? dev->ifindex : 0;
 		packet_cached_dev_assign(po, dev);
 	}
+	if (dev_curr)
+		dev_put(dev_curr);
 
 	if (proto == 0 || !need_rehook)
 		goto out_unlock;
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 273b8bf..657ba9f 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -759,8 +759,10 @@
 	}
 
 	ibmr = rds_ib_alloc_fmr(rds_ibdev);
-	if (IS_ERR(ibmr))
+	if (IS_ERR(ibmr)) {
+		rds_ib_dev_put(rds_ibdev);
 		return ibmr;
+	}
 
 	ret = rds_ib_map_fmr(rds_ibdev, ibmr, sg, nents);
 	if (ret == 0)
diff --git a/net/rds/info.c b/net/rds/info.c
index 9a6b4f6..140a44a5f 100644
--- a/net/rds/info.c
+++ b/net/rds/info.c
@@ -176,7 +176,7 @@
 
 	/* check for all kinds of wrapping and the like */
 	start = (unsigned long)optval;
-	if (len < 0 || len + PAGE_SIZE - 1 < len || start + len < start) {
+	if (len < 0 || len > INT_MAX - PAGE_SIZE + 1 || start + len < start) {
 		ret = -EINVAL;
 		goto out;
 	}
diff --git a/net/rds/transport.c b/net/rds/transport.c
index 8b4a6cd..83498e1 100644
--- a/net/rds/transport.c
+++ b/net/rds/transport.c
@@ -73,7 +73,7 @@
 
 void rds_trans_put(struct rds_transport *trans)
 {
-	if (trans && trans->t_owner)
+	if (trans)
 		module_put(trans->t_owner);
 }
 
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index af427a3..43ec926 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -45,7 +45,7 @@
 }
 EXPORT_SYMBOL(tcf_hash_destroy);
 
-int tcf_hash_release(struct tc_action *a, int bind)
+int __tcf_hash_release(struct tc_action *a, bool bind, bool strict)
 {
 	struct tcf_common *p = a->priv;
 	int ret = 0;
@@ -53,7 +53,7 @@
 	if (p) {
 		if (bind)
 			p->tcfc_bindcnt--;
-		else if (p->tcfc_bindcnt > 0)
+		else if (strict && p->tcfc_bindcnt > 0)
 			return -EPERM;
 
 		p->tcfc_refcnt--;
@@ -64,9 +64,10 @@
 			ret = 1;
 		}
 	}
+
 	return ret;
 }
-EXPORT_SYMBOL(tcf_hash_release);
+EXPORT_SYMBOL(__tcf_hash_release);
 
 static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb,
 			   struct tc_action *a)
@@ -136,7 +137,7 @@
 		head = &hinfo->htab[tcf_hash(i, hinfo->hmask)];
 		hlist_for_each_entry_safe(p, n, head, tcfc_head) {
 			a->priv = p;
-			ret = tcf_hash_release(a, 0);
+			ret = __tcf_hash_release(a, false, true);
 			if (ret == ACT_P_DELETED) {
 				module_put(a->ops->owner);
 				n_i++;
@@ -408,7 +409,7 @@
 	int ret = 0;
 
 	list_for_each_entry_safe(a, tmp, actions, list) {
-		ret = tcf_hash_release(a, bind);
+		ret = __tcf_hash_release(a, bind, true);
 		if (ret == ACT_P_DELETED)
 			module_put(a->ops->owner);
 		else if (ret < 0)
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 1d56903..d0edeb7 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -27,9 +27,10 @@
 struct tcf_bpf_cfg {
 	struct bpf_prog *filter;
 	struct sock_filter *bpf_ops;
-	char *bpf_name;
+	const char *bpf_name;
 	u32 bpf_fd;
 	u16 bpf_num_ops;
+	bool is_ebpf;
 };
 
 static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act,
@@ -207,6 +208,7 @@
 	cfg->bpf_ops = bpf_ops;
 	cfg->bpf_num_ops = bpf_num_ops;
 	cfg->filter = fp;
+	cfg->is_ebpf = false;
 
 	return 0;
 }
@@ -241,18 +243,40 @@
 	cfg->bpf_fd = bpf_fd;
 	cfg->bpf_name = name;
 	cfg->filter = fp;
+	cfg->is_ebpf = true;
 
 	return 0;
 }
 
+static void tcf_bpf_cfg_cleanup(const struct tcf_bpf_cfg *cfg)
+{
+	if (cfg->is_ebpf)
+		bpf_prog_put(cfg->filter);
+	else
+		bpf_prog_destroy(cfg->filter);
+
+	kfree(cfg->bpf_ops);
+	kfree(cfg->bpf_name);
+}
+
+static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog,
+				  struct tcf_bpf_cfg *cfg)
+{
+	cfg->is_ebpf = tcf_bpf_is_ebpf(prog);
+	cfg->filter = prog->filter;
+
+	cfg->bpf_ops = prog->bpf_ops;
+	cfg->bpf_name = prog->bpf_name;
+}
+
 static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action *act,
 			int replace, int bind)
 {
 	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
+	struct tcf_bpf_cfg cfg, old;
 	struct tc_act_bpf *parm;
 	struct tcf_bpf *prog;
-	struct tcf_bpf_cfg cfg;
 	bool is_bpf, is_ebpf;
 	int ret;
 
@@ -301,6 +325,9 @@
 	prog = to_bpf(act);
 	spin_lock_bh(&prog->tcf_lock);
 
+	if (ret != ACT_P_CREATED)
+		tcf_bpf_prog_fill_cfg(prog, &old);
+
 	prog->bpf_ops = cfg.bpf_ops;
 	prog->bpf_name = cfg.bpf_name;
 
@@ -316,29 +343,22 @@
 
 	if (ret == ACT_P_CREATED)
 		tcf_hash_insert(act);
+	else
+		tcf_bpf_cfg_cleanup(&old);
 
 	return ret;
 
 destroy_fp:
-	if (is_ebpf)
-		bpf_prog_put(cfg.filter);
-	else
-		bpf_prog_destroy(cfg.filter);
-
-	kfree(cfg.bpf_ops);
-	kfree(cfg.bpf_name);
-
+	tcf_bpf_cfg_cleanup(&cfg);
 	return ret;
 }
 
 static void tcf_bpf_cleanup(struct tc_action *act, int bind)
 {
-	const struct tcf_bpf *prog = act->priv;
+	struct tcf_bpf_cfg tmp;
 
-	if (tcf_bpf_is_ebpf(prog))
-		bpf_prog_put(prog->filter);
-	else
-		bpf_prog_destroy(prog->filter);
+	tcf_bpf_prog_fill_cfg(act->priv, &tmp);
+	tcf_bpf_cfg_cleanup(&tmp);
 }
 
 static struct tc_action_ops act_bpf_ops __read_mostly = {
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index a42a3b2..2685450 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -98,6 +98,8 @@
 			return ret;
 		ret = ACT_P_CREATED;
 	} else {
+		if (bind)
+			return 0;
 		if (!ovr) {
 			tcf_hash_release(a, bind);
 			return -EEXIST;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 17e6d66..ff8b466 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -68,13 +68,12 @@
 		}
 		ret = ACT_P_CREATED;
 	} else {
-		p = to_pedit(a);
-		tcf_hash_release(a, bind);
 		if (bind)
 			return 0;
+		tcf_hash_release(a, bind);
 		if (!ovr)
 			return -EEXIST;
-
+		p = to_pedit(a);
 		if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) {
 			keys = kmalloc(ksize, GFP_KERNEL);
 			if (keys == NULL)
diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index c79ecfd..e5168f8 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -378,7 +378,7 @@
 		goto errout;
 
 	if (oldprog) {
-		list_replace_rcu(&prog->link, &oldprog->link);
+		list_replace_rcu(&oldprog->link, &prog->link);
 		tcf_unbind_filter(tp, &oldprog->res);
 		call_rcu(&oldprog->rcu, __cls_bpf_delete_prog);
 	} else {
diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 76bc3a2..bb2a0f5 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -425,6 +425,8 @@
 	if (!fnew)
 		goto err2;
 
+	tcf_exts_init(&fnew->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE);
+
 	fold = (struct flow_filter *)*arg;
 	if (fold) {
 		err = -EINVAL;
@@ -486,7 +488,6 @@
 		fnew->mask  = ~0U;
 		fnew->tp = tp;
 		get_random_bytes(&fnew->hashrnd, 4);
-		tcf_exts_init(&fnew->exts, TCA_FLOW_ACT, TCA_FLOW_POLICE);
 	}
 
 	fnew->perturb_timer.function = flow_perturbation;
@@ -526,7 +527,7 @@
 	if (*arg == 0)
 		list_add_tail_rcu(&fnew->list, &head->filters);
 	else
-		list_replace_rcu(&fnew->list, &fold->list);
+		list_replace_rcu(&fold->list, &fnew->list);
 
 	*arg = (unsigned long)fnew;
 
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 9d37ccd..2f3d03f 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -499,7 +499,7 @@
 	*arg = (unsigned long) fnew;
 
 	if (fold) {
-		list_replace_rcu(&fnew->list, &fold->list);
+		list_replace_rcu(&fold->list, &fnew->list);
 		tcf_unbind_filter(tp, &fold->res);
 		call_rcu(&fold->rcu, fl_destroy_filter);
 	} else {
diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c
index 93d5742..6a783af 100644
--- a/net/sched/sch_choke.c
+++ b/net/sched/sch_choke.c
@@ -385,6 +385,19 @@
 {
 	struct choke_sched_data *q = qdisc_priv(sch);
 
+	while (q->head != q->tail) {
+		struct sk_buff *skb = q->tab[q->head];
+
+		q->head = (q->head + 1) & q->tab_mask;
+		if (!skb)
+			continue;
+		qdisc_qstats_backlog_dec(sch, skb);
+		--sch->q.qlen;
+		qdisc_drop(skb, sch);
+	}
+
+	memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *));
+	q->head = q->tail = 0;
 	red_restart(&q->vars);
 }
 
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index d75993f..a9ba030 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -155,14 +155,23 @@
 	skb = dequeue_head(flow);
 	len = qdisc_pkt_len(skb);
 	q->backlogs[idx] -= len;
-	kfree_skb(skb);
 	sch->q.qlen--;
 	qdisc_qstats_drop(sch);
 	qdisc_qstats_backlog_dec(sch, skb);
+	kfree_skb(skb);
 	flow->dropped++;
 	return idx;
 }
 
+static unsigned int fq_codel_qdisc_drop(struct Qdisc *sch)
+{
+	unsigned int prev_backlog;
+
+	prev_backlog = sch->qstats.backlog;
+	fq_codel_drop(sch);
+	return prev_backlog - sch->qstats.backlog;
+}
+
 static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct fq_codel_sched_data *q = qdisc_priv(sch);
@@ -279,10 +288,26 @@
 
 static void fq_codel_reset(struct Qdisc *sch)
 {
-	struct sk_buff *skb;
+	struct fq_codel_sched_data *q = qdisc_priv(sch);
+	int i;
 
-	while ((skb = fq_codel_dequeue(sch)) != NULL)
-		kfree_skb(skb);
+	INIT_LIST_HEAD(&q->new_flows);
+	INIT_LIST_HEAD(&q->old_flows);
+	for (i = 0; i < q->flows_cnt; i++) {
+		struct fq_codel_flow *flow = q->flows + i;
+
+		while (flow->head) {
+			struct sk_buff *skb = dequeue_head(flow);
+
+			qdisc_qstats_backlog_dec(sch, skb);
+			kfree_skb(skb);
+		}
+
+		INIT_LIST_HEAD(&flow->flowchain);
+		codel_vars_init(&flow->cvars);
+	}
+	memset(q->backlogs, 0, q->flows_cnt * sizeof(u32));
+	sch->q.qlen = 0;
 }
 
 static const struct nla_policy fq_codel_policy[TCA_FQ_CODEL_MAX + 1] = {
@@ -604,7 +629,7 @@
 	.enqueue	=	fq_codel_enqueue,
 	.dequeue	=	fq_codel_dequeue,
 	.peek		=	qdisc_peek_dequeued,
-	.drop		=	fq_codel_drop,
+	.drop		=	fq_codel_qdisc_drop,
 	.init		=	fq_codel_init,
 	.reset		=	fq_codel_reset,
 	.destroy	=	fq_codel_destroy,
diff --git a/net/sched/sch_plug.c b/net/sched/sch_plug.c
index 89f8fcf..ade9445 100644
--- a/net/sched/sch_plug.c
+++ b/net/sched/sch_plug.c
@@ -216,6 +216,7 @@
 	.peek        =       qdisc_peek_head,
 	.init        =       plug_init,
 	.change      =       plug_change,
+	.reset       =	     qdisc_reset_queue,
 	.owner       =       THIS_MODULE,
 };
 
diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c
index 7d14926..52f75a5 100644
--- a/net/sched/sch_sfq.c
+++ b/net/sched/sch_sfq.c
@@ -306,10 +306,10 @@
 		len = qdisc_pkt_len(skb);
 		slot->backlog -= len;
 		sfq_dec(q, x);
-		kfree_skb(skb);
 		sch->q.qlen--;
 		qdisc_qstats_drop(sch);
 		qdisc_qstats_backlog_dec(sch, skb);
+		kfree_skb(skb);
 		return len;
 	}
 
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 1425ec2..17bef01 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2200,12 +2200,6 @@
 	if (copy_from_user(&sctp_sk(sk)->subscribe, optval, optlen))
 		return -EFAULT;
 
-	if (sctp_sk(sk)->subscribe.sctp_data_io_event)
-		pr_warn_ratelimited(DEPRECATED "%s (pid %d) "
-				    "Requested SCTP_SNDRCVINFO event.\n"
-				    "Use SCTP_RCVINFO through SCTP_RECVRCVINFO option instead.\n",
-				    current->comm, task_pid_nr(current));
-
 	/* At the time when a user app subscribes to SCTP_SENDER_DRY_EVENT,
 	 * if there is no data to be sent or retransmit, the stack will
 	 * immediately send up this notification.
diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c
index 9825ff0..6255d14 100644
--- a/net/sunrpc/backchannel_rqst.c
+++ b/net/sunrpc/backchannel_rqst.c
@@ -240,8 +240,8 @@
 		req = xprt_alloc_bc_req(xprt, GFP_ATOMIC);
 		if (!req)
 			goto not_found;
-		/* Note: this 'free' request adds it to xprt->bc_pa_list */
-		xprt_free_bc_request(req);
+		list_add_tail(&req->rq_bc_pa_list, &xprt->bc_pa_list);
+		xprt->bc_alloc_count++;
 	}
 	req = list_first_entry(&xprt->bc_pa_list, struct rpc_rqst,
 				rq_bc_pa_list);
@@ -336,7 +336,7 @@
 
 	spin_lock(&xprt->bc_pa_lock);
 	list_del(&req->rq_bc_pa_list);
-	xprt->bc_alloc_count--;
+	xprt_dec_alloc_count(xprt, 1);
 	spin_unlock(&xprt->bc_pa_lock);
 
 	req->rq_private_buf.len = copied;
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index cbc6af9..23608eb 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -1902,6 +1902,7 @@
 
 	switch (task->tk_status) {
 	case -EAGAIN:
+	case -ENOBUFS:
 		break;
 	default:
 		dprint_status(task);
@@ -1928,7 +1929,6 @@
 	case -ECONNABORTED:
 	case -EADDRINUSE:
 	case -ENOTCONN:
-	case -ENOBUFS:
 	case -EPIPE:
 		rpc_task_force_reencode(task);
 	}
@@ -2057,12 +2057,13 @@
 	case -ECONNABORTED:
 		rpc_force_rebind(clnt);
 	case -EADDRINUSE:
-	case -ENOBUFS:
 		rpc_delay(task, 3*HZ);
 	case -EPIPE:
 	case -ENOTCONN:
 		task->tk_action = call_bind;
 		break;
+	case -ENOBUFS:
+		rpc_delay(task, HZ>>2);
 	case -EAGAIN:
 		task->tk_action = call_transmit;
 		break;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index e193c2b..0030376 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -527,6 +527,10 @@
 			      true, &sent);
 	dprintk("RPC:       %s(%u) = %d\n",
 			__func__, xdr->len - req->rq_bytes_sent, status);
+
+	if (status == -EAGAIN && sock_writeable(transport->inet))
+		status = -ENOBUFS;
+
 	if (likely(sent > 0) || status == 0) {
 		req->rq_bytes_sent += sent;
 		req->rq_xmit_bytes_sent += sent;
@@ -539,6 +543,7 @@
 
 	switch (status) {
 	case -ENOBUFS:
+		break;
 	case -EAGAIN:
 		status = xs_nospace(task);
 		break;
@@ -589,6 +594,9 @@
 	if (status == -EPERM)
 		goto process_status;
 
+	if (status == -EAGAIN && sock_writeable(transport->inet))
+		status = -ENOBUFS;
+
 	if (sent > 0 || status == 0) {
 		req->rq_xmit_bytes_sent += sent;
 		if (sent >= req->rq_slen)
@@ -669,9 +677,6 @@
 		dprintk("RPC:       xs_tcp_send_request(%u) = %d\n",
 				xdr->len - req->rq_bytes_sent, status);
 
-		if (unlikely(sent == 0 && status < 0))
-			break;
-
 		/* If we've sent the entire packet, immediately
 		 * reset the count of bytes sent. */
 		req->rq_bytes_sent += sent;
@@ -681,18 +686,21 @@
 			return 0;
 		}
 
-		if (sent != 0)
-			continue;
-		status = -EAGAIN;
-		break;
+		if (status < 0)
+			break;
+		if (sent == 0) {
+			status = -EAGAIN;
+			break;
+		}
 	}
+	if (status == -EAGAIN && sk_stream_is_writeable(transport->inet))
+		status = -ENOBUFS;
 
 	switch (status) {
 	case -ENOTSOCK:
 		status = -ENOTCONN;
 		/* Should we call xs_close() here? */
 		break;
-	case -ENOBUFS:
 	case -EAGAIN:
 		status = xs_nospace(task);
 		break;
@@ -703,6 +711,7 @@
 	case -ECONNREFUSED:
 	case -ENOTCONN:
 	case -EADDRINUSE:
+	case -ENOBUFS:
 	case -EPIPE:
 		clear_bit(SOCK_ASYNC_NOSPACE, &transport->sock->flags);
 	}
diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 84f77a0..9f2add3 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -171,8 +171,10 @@
 		 * released.
 		 */
 
-		attr->trans = SWITCHDEV_TRANS_ABORT;
-		__switchdev_port_attr_set(dev, attr);
+		if (err != -EOPNOTSUPP) {
+			attr->trans = SWITCHDEV_TRANS_ABORT;
+			__switchdev_port_attr_set(dev, attr);
+		}
 
 		return err;
 	}
@@ -249,8 +251,10 @@
 		 * released.
 		 */
 
-		obj->trans = SWITCHDEV_TRANS_ABORT;
-		__switchdev_port_obj_add(dev, obj);
+		if (err != -EOPNOTSUPP) {
+			obj->trans = SWITCHDEV_TRANS_ABORT;
+			__switchdev_port_obj_add(dev, obj);
+		}
 
 		return err;
 	}
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 46b6ed5..3a7567f 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -2007,6 +2007,7 @@
 	res = tipc_sk_create(sock_net(sock->sk), new_sock, 0, 1);
 	if (res)
 		goto exit;
+	security_sk_clone(sock->sk, new_sock->sk);
 
 	new_sk = new_sock->sk;
 	new_tsock = tipc_sk(new_sk);
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 915b328..59cabc9 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -797,23 +797,18 @@
 	return false;
 }
 
-bool cfg80211_reg_can_beacon(struct wiphy *wiphy,
-			     struct cfg80211_chan_def *chandef,
-			     enum nl80211_iftype iftype)
+static bool _cfg80211_reg_can_beacon(struct wiphy *wiphy,
+				     struct cfg80211_chan_def *chandef,
+				     enum nl80211_iftype iftype,
+				     bool check_no_ir)
 {
 	bool res;
 	u32 prohibited_flags = IEEE80211_CHAN_DISABLED |
 			       IEEE80211_CHAN_RADAR;
 
-	trace_cfg80211_reg_can_beacon(wiphy, chandef, iftype);
+	trace_cfg80211_reg_can_beacon(wiphy, chandef, iftype, check_no_ir);
 
-	/*
-	 * Under certain conditions suggested by some regulatory bodies a
-	 * GO/STA can IR on channels marked with IEEE80211_NO_IR. Set this flag
-	 * only if such relaxations are not enabled and the conditions are not
-	 * met.
-	 */
-	if (!cfg80211_ir_permissive_chan(wiphy, iftype, chandef->chan))
+	if (check_no_ir)
 		prohibited_flags |= IEEE80211_CHAN_NO_IR;
 
 	if (cfg80211_chandef_dfs_required(wiphy, chandef, iftype) > 0 &&
@@ -827,8 +822,36 @@
 	trace_cfg80211_return_bool(res);
 	return res;
 }
+
+bool cfg80211_reg_can_beacon(struct wiphy *wiphy,
+			     struct cfg80211_chan_def *chandef,
+			     enum nl80211_iftype iftype)
+{
+	return _cfg80211_reg_can_beacon(wiphy, chandef, iftype, true);
+}
 EXPORT_SYMBOL(cfg80211_reg_can_beacon);
 
+bool cfg80211_reg_can_beacon_relax(struct wiphy *wiphy,
+				   struct cfg80211_chan_def *chandef,
+				   enum nl80211_iftype iftype)
+{
+	bool check_no_ir;
+
+	ASSERT_RTNL();
+
+	/*
+	 * Under certain conditions suggested by some regulatory bodies a
+	 * GO/STA can IR on channels marked with IEEE80211_NO_IR. Set this flag
+	 * only if such relaxations are not enabled and the conditions are not
+	 * met.
+	 */
+	check_no_ir = !cfg80211_ir_permissive_chan(wiphy, iftype,
+						   chandef->chan);
+
+	return _cfg80211_reg_can_beacon(wiphy, chandef, iftype, check_no_ir);
+}
+EXPORT_SYMBOL(cfg80211_reg_can_beacon_relax);
+
 int cfg80211_set_monitor_channel(struct cfg80211_registered_device *rdev,
 				 struct cfg80211_chan_def *chandef)
 {
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index c264eff..76b4157 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -2003,7 +2003,8 @@
 	switch (iftype) {
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_P2P_GO:
-		if (!cfg80211_reg_can_beacon(&rdev->wiphy, &chandef, iftype)) {
+		if (!cfg80211_reg_can_beacon_relax(&rdev->wiphy, &chandef,
+						   iftype)) {
 			result = -EINVAL;
 			break;
 		}
@@ -3403,8 +3404,8 @@
 	} else if (!nl80211_get_ap_channel(rdev, &params))
 		return -EINVAL;
 
-	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &params.chandef,
-				     wdev->iftype))
+	if (!cfg80211_reg_can_beacon_relax(&rdev->wiphy, &params.chandef,
+					   wdev->iftype))
 		return -EINVAL;
 
 	if (info->attrs[NL80211_ATTR_ACL_POLICY]) {
@@ -6492,8 +6493,8 @@
 	if (err)
 		return err;
 
-	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &params.chandef,
-				     wdev->iftype))
+	if (!cfg80211_reg_can_beacon_relax(&rdev->wiphy, &params.chandef,
+					   wdev->iftype))
 		return -EINVAL;
 
 	err = cfg80211_chandef_dfs_required(wdev->wiphy,
@@ -10170,7 +10171,8 @@
 		return -EINVAL;
 
 	/* we will be active on the TDLS link */
-	if (!cfg80211_reg_can_beacon(&rdev->wiphy, &chandef, wdev->iftype))
+	if (!cfg80211_reg_can_beacon_relax(&rdev->wiphy, &chandef,
+					   wdev->iftype))
 		return -EINVAL;
 
 	/* don't allow switching to DFS channels */
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index d359e06..aa2d754 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -544,15 +544,15 @@
 	reg_regdb_query(alpha2);
 
 	if (reg_crda_timeouts > REG_MAX_CRDA_TIMEOUTS) {
-		pr_info("Exceeded CRDA call max attempts. Not calling CRDA\n");
+		pr_debug("Exceeded CRDA call max attempts. Not calling CRDA\n");
 		return -EINVAL;
 	}
 
 	if (!is_world_regdom((char *) alpha2))
-		pr_info("Calling CRDA for country: %c%c\n",
+		pr_debug("Calling CRDA for country: %c%c\n",
 			alpha2[0], alpha2[1]);
 	else
-		pr_info("Calling CRDA to update world regulatory domain\n");
+		pr_debug("Calling CRDA to update world regulatory domain\n");
 
 	return kobject_uevent_env(&reg_pdev->dev.kobj, KOBJ_CHANGE, env);
 }
@@ -1589,7 +1589,7 @@
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_P2P_GO:
 	case NL80211_IFTYPE_ADHOC:
-		return cfg80211_reg_can_beacon(wiphy, &chandef, iftype);
+		return cfg80211_reg_can_beacon_relax(wiphy, &chandef, iftype);
 	case NL80211_IFTYPE_STATION:
 	case NL80211_IFTYPE_P2P_CLIENT:
 		return cfg80211_chandef_usable(wiphy, &chandef,
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index af3617c..a808279 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -2358,20 +2358,23 @@
 
 TRACE_EVENT(cfg80211_reg_can_beacon,
 	TP_PROTO(struct wiphy *wiphy, struct cfg80211_chan_def *chandef,
-		 enum nl80211_iftype iftype),
-	TP_ARGS(wiphy, chandef, iftype),
+		 enum nl80211_iftype iftype, bool check_no_ir),
+	TP_ARGS(wiphy, chandef, iftype, check_no_ir),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		CHAN_DEF_ENTRY
 		__field(enum nl80211_iftype, iftype)
+		__field(bool, check_no_ir)
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
 		CHAN_DEF_ASSIGN(chandef);
 		__entry->iftype = iftype;
+		__entry->check_no_ir = check_no_ir;
 	),
-	TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT ", iftype=%d",
-		  WIPHY_PR_ARG, CHAN_DEF_PR_ARG, __entry->iftype)
+	TP_printk(WIPHY_PR_FMT ", " CHAN_DEF_PR_FMT ", iftype=%d check_no_ir=%s",
+		  WIPHY_PR_ARG, CHAN_DEF_PR_ARG, __entry->iftype,
+		  BOOL_TO_STR(__entry->check_no_ir))
 );
 
 TRACE_EVENT(cfg80211_chandef_dfs_required,
diff --git a/samples/trace_events/trace-events-sample.h b/samples/trace_events/trace-events-sample.h
index 8965d1b..125d640 100644
--- a/samples/trace_events/trace-events-sample.h
+++ b/samples/trace_events/trace-events-sample.h
@@ -168,7 +168,10 @@
  *
  *      For __dynamic_array(int, foo, bar) use __get_dynamic_array(foo)
  *            Use __get_dynamic_array_len(foo) to get the length of the array
- *            saved.
+ *            saved. Note, __get_dynamic_array_len() returns the total allocated
+ *            length of the dynamic array; __print_array() expects the second
+ *            parameter to be the number of elements. To get that, the array length
+ *            needs to be divided by the element size.
  *
  *      For __string(foo, bar) use __get_str(foo)
  *
@@ -288,7 +291,7 @@
  *    This prints out the array that is defined by __array in a nice format.
  */
 		  __print_array(__get_dynamic_array(list),
-				__get_dynamic_array_len(list),
+				__get_dynamic_array_len(list) / sizeof(int),
 				sizeof(int)),
 		  __get_str(str), __get_bitmask(cpus))
 );
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index 90e1edc..d5c8e9a 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -2599,7 +2599,7 @@
 # if LONG_LINE is ignored, the other 2 types are also ignored
 #
 
-		if ($length > $max_line_length) {
+		if ($line =~ /^\+/ && $length > $max_line_length) {
 			my $msg_type = "LONG_LINE";
 
 			# Check the allowed long line types first
diff --git a/scripts/kconfig/streamline_config.pl b/scripts/kconfig/streamline_config.pl
index 9cb8522..f3d3fb4 100755
--- a/scripts/kconfig/streamline_config.pl
+++ b/scripts/kconfig/streamline_config.pl
@@ -137,7 +137,7 @@
 my $kconfig = $ARGV[1];
 my $lsmod_file = $ENV{'LSMOD'};
 
-my @makefiles = `find $ksource -name Makefile 2>/dev/null`;
+my @makefiles = `find $ksource -name Makefile -or -name Kbuild 2>/dev/null`;
 chomp @makefiles;
 
 my %depends;
diff --git a/scripts/mod/devicetable-offsets.c b/scripts/mod/devicetable-offsets.c
index eff7de1..e70fcd1 100644
--- a/scripts/mod/devicetable-offsets.c
+++ b/scripts/mod/devicetable-offsets.c
@@ -63,6 +63,8 @@
 
 	DEVID(acpi_device_id);
 	DEVID_FIELD(acpi_device_id, id);
+	DEVID_FIELD(acpi_device_id, cls);
+	DEVID_FIELD(acpi_device_id, cls_msk);
 
 	DEVID(pnp_device_id);
 	DEVID_FIELD(pnp_device_id, id);
diff --git a/scripts/mod/file2alias.c b/scripts/mod/file2alias.c
index 84c86f3..5f20882 100644
--- a/scripts/mod/file2alias.c
+++ b/scripts/mod/file2alias.c
@@ -523,12 +523,40 @@
 }
 ADD_TO_DEVTABLE("serio", serio_device_id, do_serio_entry);
 
-/* looks like: "acpi:ACPI0003 or acpi:PNP0C0B" or "acpi:LNXVIDEO" */
+/* looks like: "acpi:ACPI0003" or "acpi:PNP0C0B" or "acpi:LNXVIDEO" or
+ *             "acpi:bbsspp" (bb=base-class, ss=sub-class, pp=prog-if)
+ *
+ * NOTE: Each driver should use one of the following : _HID, _CIDs
+ *       or _CLS. Also, bb, ss, and pp can be substituted with ??
+ *       as don't care byte.
+ */
 static int do_acpi_entry(const char *filename,
 			void *symval, char *alias)
 {
 	DEF_FIELD_ADDR(symval, acpi_device_id, id);
-	sprintf(alias, "acpi*:%s:*", *id);
+	DEF_FIELD_ADDR(symval, acpi_device_id, cls);
+	DEF_FIELD_ADDR(symval, acpi_device_id, cls_msk);
+
+	if (id && strlen((const char *)*id))
+		sprintf(alias, "acpi*:%s:*", *id);
+	else if (cls) {
+		int i, byte_shift, cnt = 0;
+		unsigned int msk;
+
+		sprintf(&alias[cnt], "acpi*:");
+		cnt = 6;
+		for (i = 1; i <= 3; i++) {
+			byte_shift = 8 * (3-i);
+			msk = (*cls_msk >> byte_shift) & 0xFF;
+			if (msk)
+				sprintf(&alias[cnt], "%02x",
+					(*cls >> byte_shift) & 0xFF);
+			else
+				sprintf(&alias[cnt], "??");
+			cnt += 2;
+		}
+		sprintf(&alias[cnt], ":*");
+	}
 	return 1;
 }
 ADD_TO_DEVTABLE("acpi", acpi_device_id, do_acpi_entry);
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 91ee1b2..12d3db3 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -886,7 +886,8 @@
 #define TEXT_SECTIONS ".text", ".text.unlikely", ".sched.text", \
 		".kprobes.text"
 #define OTHER_TEXT_SECTIONS ".ref.text", ".head.text", ".spinlock.text", \
-		".fixup", ".entry.text", ".exception.text", ".text.*"
+		".fixup", ".entry.text", ".exception.text", ".text.*", \
+		".coldtext"
 
 #define INIT_SECTIONS      ".init.*"
 #define MEM_INIT_SECTIONS  ".meminit.*"
diff --git a/security/keys/keyring.c b/security/keys/keyring.c
index e72548b..d334370 100644
--- a/security/keys/keyring.c
+++ b/security/keys/keyring.c
@@ -1181,9 +1181,11 @@
 	if (index_key->type == &key_type_keyring)
 		up_write(&keyring_serialise_link_sem);
 
-	if (edit && !edit->dead_leaf) {
-		key_payload_reserve(keyring,
-				    keyring->datalen - KEYQUOTA_LINK_BYTES);
+	if (edit) {
+		if (!edit->dead_leaf) {
+			key_payload_reserve(keyring,
+				keyring->datalen - KEYQUOTA_LINK_BYTES);
+		}
 		assoc_array_cancel_edit(edit);
 	}
 	up_write(&keyring->sem);
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 6231081..564079c 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3283,7 +3283,8 @@
 	int rc = 0;
 
 	if (default_noexec &&
-	    (prot & PROT_EXEC) && (!file || (!shared && (prot & PROT_WRITE)))) {
+	    (prot & PROT_EXEC) && (!file || IS_PRIVATE(file_inode(file)) ||
+				   (!shared && (prot & PROT_WRITE)))) {
 		/*
 		 * We are making executable an anonymous mapping or a
 		 * private file mapping that will also be writable.
diff --git a/security/selinux/ss/ebitmap.c b/security/selinux/ss/ebitmap.c
index afe6a26..57644b1 100644
--- a/security/selinux/ss/ebitmap.c
+++ b/security/selinux/ss/ebitmap.c
@@ -153,6 +153,12 @@
 		if (offset == (u32)-1)
 			return 0;
 
+		/* don't waste ebitmap space if the netlabel bitmap is empty */
+		if (bitmap == 0) {
+			offset += EBITMAP_UNIT_SIZE;
+			continue;
+		}
+
 		if (e_iter == NULL ||
 		    offset >= e_iter->startbit + EBITMAP_SIZE) {
 			e_prev = e_iter;
diff --git a/security/yama/yama_lsm.c b/security/yama/yama_lsm.c
index 9ed3250..5ebb896 100644
--- a/security/yama/yama_lsm.c
+++ b/security/yama/yama_lsm.c
@@ -406,6 +406,7 @@
 	 */
 	if (!security_module_enable("yama"))
 		return 0;
+	yama_add_hooks();
 #endif
 	pr_info("Yama: becoming mindful.\n");
 
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index d126c03..75888dd 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -85,7 +85,7 @@
 void snd_pcm_stream_lock(struct snd_pcm_substream *substream)
 {
 	if (substream->pcm->nonatomic) {
-		down_read(&snd_pcm_link_rwsem);
+		down_read_nested(&snd_pcm_link_rwsem, SINGLE_DEPTH_NESTING);
 		mutex_lock(&substream->self_group.mutex);
 	} else {
 		read_lock(&snd_pcm_link_rwlock);
diff --git a/sound/firewire/amdtp.c b/sound/firewire/amdtp.c
index 7bb988f..2a153d2 100644
--- a/sound/firewire/amdtp.c
+++ b/sound/firewire/amdtp.c
@@ -740,8 +740,9 @@
 	    s->data_block_counter != UINT_MAX)
 		data_block_counter = s->data_block_counter;
 
-	if (((s->flags & CIP_SKIP_DBC_ZERO_CHECK) && data_block_counter == 0) ||
-	    (s->data_block_counter == UINT_MAX)) {
+	if (((s->flags & CIP_SKIP_DBC_ZERO_CHECK) &&
+	     data_block_counter == s->tx_first_dbc) ||
+	    s->data_block_counter == UINT_MAX) {
 		lost = false;
 	} else if (!(s->flags & CIP_DBC_IS_END_EVENT)) {
 		lost = data_block_counter != s->data_block_counter;
diff --git a/sound/firewire/amdtp.h b/sound/firewire/amdtp.h
index 26b9093..b2cf9e7 100644
--- a/sound/firewire/amdtp.h
+++ b/sound/firewire/amdtp.h
@@ -157,6 +157,8 @@
 
 	/* quirk: fixed interval of dbc between previos/current packets. */
 	unsigned int tx_dbc_interval;
+	/* quirk: indicate the value of dbc field in a first packet. */
+	unsigned int tx_first_dbc;
 
 	bool callbacked;
 	wait_queue_head_t callback_wait;
diff --git a/sound/firewire/fireworks/fireworks.c b/sound/firewire/fireworks/fireworks.c
index 2682e7e..c94a432 100644
--- a/sound/firewire/fireworks/fireworks.c
+++ b/sound/firewire/fireworks/fireworks.c
@@ -248,8 +248,16 @@
 	err = get_hardware_info(efw);
 	if (err < 0)
 		goto error;
+	/* AudioFire8 (since 2009) and AudioFirePre8 */
 	if (entry->model_id == MODEL_ECHO_AUDIOFIRE_9)
 		efw->is_af9 = true;
+	/* These models uses the same firmware. */
+	if (entry->model_id == MODEL_ECHO_AUDIOFIRE_2 ||
+	    entry->model_id == MODEL_ECHO_AUDIOFIRE_4 ||
+	    entry->model_id == MODEL_ECHO_AUDIOFIRE_9 ||
+	    entry->model_id == MODEL_GIBSON_RIP ||
+	    entry->model_id == MODEL_GIBSON_GOLDTOP)
+		efw->is_fireworks3 = true;
 
 	snd_efw_proc_init(efw);
 
diff --git a/sound/firewire/fireworks/fireworks.h b/sound/firewire/fireworks/fireworks.h
index 4f0201a..084d414 100644
--- a/sound/firewire/fireworks/fireworks.h
+++ b/sound/firewire/fireworks/fireworks.h
@@ -71,6 +71,7 @@
 
 	/* for quirks */
 	bool is_af9;
+	bool is_fireworks3;
 	u32 firmware_version;
 
 	unsigned int midi_in_ports;
diff --git a/sound/firewire/fireworks/fireworks_stream.c b/sound/firewire/fireworks/fireworks_stream.c
index c55db1b..7e353f1 100644
--- a/sound/firewire/fireworks/fireworks_stream.c
+++ b/sound/firewire/fireworks/fireworks_stream.c
@@ -172,6 +172,15 @@
 	efw->tx_stream.flags |= CIP_DBC_IS_END_EVENT;
 	/* Fireworks reset dbc at bus reset. */
 	efw->tx_stream.flags |= CIP_SKIP_DBC_ZERO_CHECK;
+	/*
+	 * But Recent firmwares starts packets with non-zero dbc.
+	 * Driver version 5.7.6 installs firmware version 5.7.3.
+	 */
+	if (efw->is_fireworks3 &&
+	    (efw->firmware_version == 0x5070000 ||
+	     efw->firmware_version == 0x5070300 ||
+	     efw->firmware_version == 0x5080000))
+		efw->tx_stream.tx_first_dbc = 0x02;
 	/* AudioFire9 always reports wrong dbs. */
 	if (efw->is_af9)
 		efw->tx_stream.flags |= CIP_WRONG_DBS;
diff --git a/sound/hda/ext/hdac_ext_controller.c b/sound/hda/ext/hdac_ext_controller.c
index b2da19b..358f161 100644
--- a/sound/hda/ext/hdac_ext_controller.c
+++ b/sound/hda/ext/hdac_ext_controller.c
@@ -44,16 +44,10 @@
 
 	offset = snd_hdac_chip_readl(bus, LLCH);
 
-	if (offset < 0)
-		return -EIO;
-
 	/* Lets walk the linked capabilities list */
 	do {
 		cur_cap = _snd_hdac_chip_read(l, bus, offset);
 
-		if (cur_cap < 0)
-			return -EIO;
-
 		dev_dbg(bus->dev, "Capability version: 0x%x\n",
 				((cur_cap & AZX_CAP_HDR_VER_MASK) >> AZX_CAP_HDR_VER_OFF));
 
diff --git a/sound/hda/ext/hdac_ext_stream.c b/sound/hda/ext/hdac_ext_stream.c
index f8ffbdb..3de47dd 100644
--- a/sound/hda/ext/hdac_ext_stream.c
+++ b/sound/hda/ext/hdac_ext_stream.c
@@ -299,7 +299,7 @@
 		if (stream->direction != substream->stream)
 			continue;
 
-		if (stream->opened) {
+		if (!stream->opened) {
 			if (!hstream->decoupled)
 				snd_hdac_ext_stream_decouple(ebus, hstream, true);
 			res = hstream;
diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c
index 442500e..5676b84 100644
--- a/sound/hda/hdac_i915.c
+++ b/sound/hda/hdac_i915.c
@@ -56,8 +56,11 @@
 		enable ? "enable" : "disable");
 
 	if (enable) {
-		if (!bus->i915_power_refcount++)
+		if (!bus->i915_power_refcount++) {
 			acomp->ops->get_power(acomp->dev);
+			snd_hdac_set_codec_wakeup(bus, true);
+			snd_hdac_set_codec_wakeup(bus, false);
+		}
 	} else {
 		WARN_ON(!bus->i915_power_refcount);
 		if (!--bus->i915_power_refcount)
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index ac0db16..b077bb6 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -5175,7 +5175,7 @@
 	int err = 0;
 
 	mutex_lock(&spec->pcm_mutex);
-	if (!spec->indep_hp_enabled)
+	if (spec->indep_hp && !spec->indep_hp_enabled)
 		err = -EBUSY;
 	else
 		spec->active_streams |= 1 << STREAM_INDEP_HP;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 745535d..c38c68f5 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -867,7 +867,7 @@
 
 	chip = card->private_data;
 	hda = container_of(chip, struct hda_intel, chip);
-	if (chip->disabled || hda->init_failed)
+	if (chip->disabled || hda->init_failed || !chip->running)
 		return 0;
 
 	bus = azx_bus(chip);
@@ -902,7 +902,7 @@
 
 	chip = card->private_data;
 	hda = container_of(chip, struct hda_intel, chip);
-	if (chip->disabled || hda->init_failed)
+	if (chip->disabled || hda->init_failed || !chip->running)
 		return 0;
 
 	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL
@@ -979,14 +979,16 @@
 	if (!azx_has_pm_runtime(chip))
 		return 0;
 
-	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL
-		&& hda->need_i915_power) {
-		bus =  azx_bus(chip);
-		snd_hdac_display_power(bus, true);
-		haswell_set_bclk(hda);
-		/* toggle codec wakeup bit for STATESTS read */
-		snd_hdac_set_codec_wakeup(bus, true);
-		snd_hdac_set_codec_wakeup(bus, false);
+	if (chip->driver_caps & AZX_DCAPS_I915_POWERWELL) {
+		bus = azx_bus(chip);
+		if (hda->need_i915_power) {
+			snd_hdac_display_power(bus, true);
+			haswell_set_bclk(hda);
+		} else {
+			/* toggle codec wakeup bit for STATESTS read */
+			snd_hdac_set_codec_wakeup(bus, true);
+			snd_hdac_set_codec_wakeup(bus, false);
+		}
 	}
 
 	/* Read STATESTS before controller reset */
@@ -1025,7 +1027,7 @@
 		return 0;
 
 	if (!power_save_controller || !azx_has_pm_runtime(chip) ||
-	    azx_bus(chip)->codec_powered)
+	    azx_bus(chip)->codec_powered || !chip->running)
 		return -EBUSY;
 
 	return 0;
@@ -2182,6 +2184,8 @@
 	/* ATI HDMI */
 	{ PCI_DEVICE(0x1002, 0x1308),
 	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+	{ PCI_DEVICE(0x1002, 0x157a),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0x793b),
 	  .driver_data = AZX_DRIVER_ATIHDMI | AZX_DCAPS_PRESET_ATI_HDMI },
 	{ PCI_DEVICE(0x1002, 0x7919),
@@ -2236,8 +2240,14 @@
 	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0xaab0),
 	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+	{ PCI_DEVICE(0x1002, 0xaac0),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	{ PCI_DEVICE(0x1002, 0xaac8),
 	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+	{ PCI_DEVICE(0x1002, 0xaad8),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
+	{ PCI_DEVICE(0x1002, 0xaae8),
+	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
 	/* VIA VT8251/VT8237A */
 	{ PCI_DEVICE(0x1106, 0x3288),
 	  .driver_data = AZX_DRIVER_VIA | AZX_DCAPS_POSFIX_VIA },
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index 25ccf78..584a034 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -999,9 +999,7 @@
 
 	spec->spdif_present = spdif_present;
 	/* SPDIF TX on/off */
-	if (spdif_present)
-		snd_hda_set_pin_ctl(codec, spdif_pin,
-				    spdif_present ? PIN_OUT : 0);
+	snd_hda_set_pin_ctl(codec, spdif_pin, spdif_present ? PIN_OUT : 0);
 
 	cs_automute(codec);
 }
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 2f24338..a97db5f 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -3512,6 +3512,7 @@
 { .id = 0x10de0070, .name = "GPU 70 HDMI/DP",	.patch = patch_nvhdmi },
 { .id = 0x10de0071, .name = "GPU 71 HDMI/DP",	.patch = patch_nvhdmi },
 { .id = 0x10de0072, .name = "GPU 72 HDMI/DP",	.patch = patch_nvhdmi },
+{ .id = 0x10de007d, .name = "GPU 7d HDMI/DP",	.patch = patch_nvhdmi },
 { .id = 0x10de8001, .name = "MCP73 HDMI",	.patch = patch_nvhdmi_2ch },
 { .id = 0x11069f80, .name = "VX900 HDMI/DP",	.patch = patch_via_hdmi },
 { .id = 0x11069f81, .name = "VX900 HDMI/DP",	.patch = patch_via_hdmi },
@@ -3527,6 +3528,7 @@
 { .id = 0x80862807, .name = "Haswell HDMI",	.patch = patch_generic_hdmi },
 { .id = 0x80862808, .name = "Broadwell HDMI",	.patch = patch_generic_hdmi },
 { .id = 0x80862809, .name = "Skylake HDMI",	.patch = patch_generic_hdmi },
+{ .id = 0x8086280a, .name = "Broxton HDMI",	.patch = patch_generic_hdmi },
 { .id = 0x80862880, .name = "CedarTrail HDMI",	.patch = patch_generic_hdmi },
 { .id = 0x80862882, .name = "Valleyview2 HDMI",	.patch = patch_generic_hdmi },
 { .id = 0x80862883, .name = "Braswell HDMI",	.patch = patch_generic_hdmi },
@@ -3575,6 +3577,7 @@
 MODULE_ALIAS("snd-hda-codec-id:10de0070");
 MODULE_ALIAS("snd-hda-codec-id:10de0071");
 MODULE_ALIAS("snd-hda-codec-id:10de0072");
+MODULE_ALIAS("snd-hda-codec-id:10de007d");
 MODULE_ALIAS("snd-hda-codec-id:10de8001");
 MODULE_ALIAS("snd-hda-codec-id:11069f80");
 MODULE_ALIAS("snd-hda-codec-id:11069f81");
@@ -3591,6 +3594,7 @@
 MODULE_ALIAS("snd-hda-codec-id:80862807");
 MODULE_ALIAS("snd-hda-codec-id:80862808");
 MODULE_ALIAS("snd-hda-codec-id:80862809");
+MODULE_ALIAS("snd-hda-codec-id:8086280a");
 MODULE_ALIAS("snd-hda-codec-id:80862880");
 MODULE_ALIAS("snd-hda-codec-id:80862882");
 MODULE_ALIAS("snd-hda-codec-id:80862883");
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index b3b4468..374ea53 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2222,7 +2222,7 @@
 	SND_PCI_QUIRK(0x106b, 0x4300, "iMac 9,1", ALC889_FIXUP_IMAC91_VREF),
 	SND_PCI_QUIRK(0x106b, 0x4600, "MacbookPro 5,2", ALC889_FIXUP_IMAC91_VREF),
 	SND_PCI_QUIRK(0x106b, 0x4900, "iMac 9,1 Aluminum", ALC889_FIXUP_IMAC91_VREF),
-	SND_PCI_QUIRK(0x106b, 0x4a00, "Macbook 5,2", ALC889_FIXUP_IMAC91_VREF),
+	SND_PCI_QUIRK(0x106b, 0x4a00, "Macbook 5,2", ALC889_FIXUP_MBA11_VREF),
 
 	SND_PCI_QUIRK(0x1071, 0x8258, "Evesham Voyaeger", ALC882_FIXUP_EAPD),
 	SND_PCI_QUIRK(0x1462, 0x7350, "MSI-7350", ALC889_FIXUP_CD),
@@ -4441,6 +4441,55 @@
 	}
 }
 
+/* Hook to update amp GPIO4 for automute */
+static void alc280_hp_gpio4_automute_hook(struct hda_codec *codec,
+					  struct hda_jack_callback *jack)
+{
+	struct alc_spec *spec = codec->spec;
+
+	snd_hda_gen_hp_automute(codec, jack);
+	/* mute_led_polarity is set to 0, so we pass inverted value here */
+	alc_update_gpio_led(codec, 0x10, !spec->gen.hp_jack_present);
+}
+
+/* Manage GPIOs for HP EliteBook Folio 9480m.
+ *
+ * GPIO4 is the headphone amplifier power control
+ * GPIO3 is the audio output mute indicator LED
+ */
+
+static void alc280_fixup_hp_9480m(struct hda_codec *codec,
+				  const struct hda_fixup *fix,
+				  int action)
+{
+	struct alc_spec *spec = codec->spec;
+	static const struct hda_verb gpio_init[] = {
+		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x18 },
+		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x18 },
+		{}
+	};
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		/* Set the hooks to turn the headphone amp on/off
+		 * as needed
+		 */
+		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
+		spec->gen.hp_automute_hook = alc280_hp_gpio4_automute_hook;
+
+		/* The GPIOs are currently off */
+		spec->gpio_led = 0;
+
+		/* GPIO3 is connected to the output mute LED,
+		 * high is on, low is off
+		 */
+		spec->mute_led_polarity = 0;
+		spec->gpio_mute_led_mask = 0x08;
+
+		/* Initialize GPIO configuration */
+		snd_hda_add_verbs(codec, gpio_init);
+	}
+}
+
 /* for hda_fixup_thinkpad_acpi() */
 #include "thinkpad_helper.c"
 
@@ -4521,6 +4570,7 @@
 	ALC286_FIXUP_HP_GPIO_LED,
 	ALC280_FIXUP_HP_GPIO2_MIC_HOTKEY,
 	ALC280_FIXUP_HP_DOCK_PINS,
+	ALC280_FIXUP_HP_9480M,
 	ALC288_FIXUP_DELL_HEADSET_MODE,
 	ALC288_FIXUP_DELL1_MIC_NO_PRESENCE,
 	ALC288_FIXUP_DELL_XPS_13_GPIO6,
@@ -5011,7 +5061,7 @@
 			{ 0x14, 0x90170110 },
 			{ 0x17, 0x40000008 },
 			{ 0x18, 0x411111f0 },
-			{ 0x19, 0x411111f0 },
+			{ 0x19, 0x01a1913c },
 			{ 0x1a, 0x411111f0 },
 			{ 0x1b, 0x411111f0 },
 			{ 0x1d, 0x40f89b2d },
@@ -5043,6 +5093,10 @@
 		.chained = true,
 		.chain_id = ALC280_FIXUP_HP_GPIO4
 	},
+	[ALC280_FIXUP_HP_9480M] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc280_fixup_hp_9480m,
+	},
 	[ALC288_FIXUP_DELL_HEADSET_MODE] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_headset_mode_dell_alc288,
@@ -5131,9 +5185,12 @@
 	SND_PCI_QUIRK(0x1028, 0x064a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x064b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0665, "Dell XPS 13", ALC288_FIXUP_DELL_XPS_13),
+	SND_PCI_QUIRK(0x1028, 0x069a, "Dell Vostro 5480", ALC290_FIXUP_SUBWOOFER_HSJACK),
 	SND_PCI_QUIRK(0x1028, 0x06c7, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x06d9, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x06da, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x06de, "Dell", ALC292_FIXUP_DISABLE_AAMIX),
+	SND_PCI_QUIRK(0x1028, 0x06db, "Dell", ALC292_FIXUP_DISABLE_AAMIX),
 	SND_PCI_QUIRK(0x1028, 0x164a, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x164b, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x1586, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC2),
@@ -5161,6 +5218,7 @@
 	SND_PCI_QUIRK(0x103c, 0x22b7, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22bf, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
 	SND_PCI_QUIRK(0x103c, 0x22cf, "HP", ALC269_FIXUP_HP_MUTE_LED_MIC1),
+	SND_PCI_QUIRK(0x103c, 0x22db, "HP", ALC280_FIXUP_HP_9480M),
 	SND_PCI_QUIRK(0x103c, 0x22dc, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	SND_PCI_QUIRK(0x103c, 0x22fb, "HP", ALC269_FIXUP_HP_GPIO_MIC1_LED),
 	/* ALC290 */
@@ -5234,6 +5292,7 @@
 	SND_PCI_QUIRK(0x17aa, 0x220c, "Thinkpad T440s", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x220e, "Thinkpad T440p", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2210, "Thinkpad T540p", ALC292_FIXUP_TPT440_DOCK),
+	SND_PCI_QUIRK(0x17aa, 0x2211, "Thinkpad W541", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad T440", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad X240", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
@@ -5343,8 +5402,6 @@
 	{0x19, 0x411111f0}, \
 	{0x1a, 0x411111f0}, \
 	{0x1b, 0x411111f0}, \
-	{0x1d, 0x40700001}, \
-	{0x1e, 0x411111f0}, \
 	{0x21, 0x02211020}
 
 #define ALC282_STANDARD_PINS \
@@ -5375,8 +5432,7 @@
 	{0x15, 0x0221401f}, \
 	{0x1a, 0x411111f0}, \
 	{0x1b, 0x411111f0}, \
-	{0x1d, 0x40700001}, \
-	{0x1e, 0x411111f0}
+	{0x1d, 0x40700001}
 
 #define ALC298_STANDARD_PINS \
 	{0x18, 0x411111f0}, \
@@ -5408,6 +5464,39 @@
 		{0x1d, 0x40700001},
 		{0x21, 0x02211030}),
 	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x40000000},
+		{0x14, 0x90170130},
+		{0x17, 0x411111f0},
+		{0x18, 0x411111f0},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x01014020},
+		{0x1d, 0x4054c029},
+		{0x1e, 0x411111f0},
+		{0x21, 0x0221103f}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x40000000},
+		{0x14, 0x90170150},
+		{0x17, 0x411111f0},
+		{0x18, 0x411111f0},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x02011020},
+		{0x1d, 0x4054c029},
+		{0x1e, 0x411111f0},
+		{0x21, 0x0221105f}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		{0x12, 0x40000000},
+		{0x14, 0x90170110},
+		{0x17, 0x411111f0},
+		{0x18, 0x411111f0},
+		{0x19, 0x411111f0},
+		{0x1a, 0x411111f0},
+		{0x1b, 0x01014020},
+		{0x1d, 0x4054c029},
+		{0x1e, 0x411111f0},
+		{0x21, 0x0221101f}),
+	SND_HDA_PIN_QUIRK(0x10ec0255, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x12, 0x90a60160},
 		{0x14, 0x90170120},
 		{0x17, 0x90170140},
@@ -5469,10 +5558,19 @@
 		{0x21, 0x02211030}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC256_STANDARD_PINS,
-		{0x13, 0x40000000}),
+		{0x13, 0x40000000},
+		{0x1d, 0x40700001},
+		{0x1e, 0x411111f0}),
 	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC256_STANDARD_PINS,
-		{0x13, 0x411111f0}),
+		{0x13, 0x411111f0},
+		{0x1d, 0x40700001},
+		{0x1e, 0x411111f0}),
+	SND_HDA_PIN_QUIRK(0x10ec0256, 0x1028, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC256_STANDARD_PINS,
+		{0x13, 0x411111f0},
+		{0x1d, 0x4077992d},
+		{0x1e, 0x411111ff}),
 	SND_HDA_PIN_QUIRK(0x10ec0280, 0x103c, "HP", ALC280_FIXUP_HP_GPIO4,
 		{0x12, 0x90a60130},
 		{0x13, 0x40000000},
@@ -5635,35 +5733,48 @@
 		{0x13, 0x411111f0},
 		{0x16, 0x01014020},
 		{0x18, 0x411111f0},
-		{0x19, 0x01a19030}),
+		{0x19, 0x01a19030},
+		{0x1e, 0x411111f0}),
 	SND_HDA_PIN_QUIRK(0x10ec0292, 0x1028, "Dell", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE,
 		ALC292_STANDARD_PINS,
 		{0x12, 0x90a60140},
 		{0x13, 0x411111f0},
 		{0x16, 0x01014020},
 		{0x18, 0x02a19031},
-		{0x19, 0x01a1903e}),
+		{0x19, 0x01a1903e},
+		{0x1e, 0x411111f0}),
 	SND_HDA_PIN_QUIRK(0x10ec0292, 0x1028, "Dell", ALC269_FIXUP_DELL3_MIC_NO_PRESENCE,
 		ALC292_STANDARD_PINS,
 		{0x12, 0x90a60140},
 		{0x13, 0x411111f0},
 		{0x16, 0x411111f0},
 		{0x18, 0x411111f0},
-		{0x19, 0x411111f0}),
+		{0x19, 0x411111f0},
+		{0x1e, 0x411111f0}),
 	SND_HDA_PIN_QUIRK(0x10ec0293, 0x1028, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC292_STANDARD_PINS,
 		{0x12, 0x40000000},
 		{0x13, 0x90a60140},
 		{0x16, 0x21014020},
 		{0x18, 0x411111f0},
-		{0x19, 0x21a19030}),
+		{0x19, 0x21a19030},
+		{0x1e, 0x411111f0}),
 	SND_HDA_PIN_QUIRK(0x10ec0293, 0x1028, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC292_STANDARD_PINS,
 		{0x12, 0x40000000},
 		{0x13, 0x90a60140},
 		{0x16, 0x411111f0},
 		{0x18, 0x411111f0},
-		{0x19, 0x411111f0}),
+		{0x19, 0x411111f0},
+		{0x1e, 0x411111f0}),
+	SND_HDA_PIN_QUIRK(0x10ec0293, 0x1028, "Dell", ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
+		ALC292_STANDARD_PINS,
+		{0x12, 0x40000000},
+		{0x13, 0x90a60140},
+		{0x16, 0x21014020},
+		{0x18, 0x411111f0},
+		{0x19, 0x21a19030},
+		{0x1e, 0x411111ff}),
 	SND_HDA_PIN_QUIRK(0x10ec0298, 0x1028, "Dell", ALC298_FIXUP_DELL1_MIC_NO_PRESENCE,
 		ALC298_STANDARD_PINS,
 		{0x12, 0x90a60130},
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index dcc7fe9..9d947ae 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -2920,7 +2920,8 @@
 	SND_PCI_QUIRK(PCI_VENDOR_ID_HP, 0x148a,
 		      "HP Mini", STAC_92HD83XXX_HP_LED),
 	SND_PCI_QUIRK_VENDOR(PCI_VENDOR_ID_HP, "HP", STAC_92HD83XXX_HP),
-	SND_PCI_QUIRK(PCI_VENDOR_ID_TOSHIBA, 0xfa91,
+	/* match both for 0xfa91 and 0xfa93 */
+	SND_PCI_QUIRK_MASK(PCI_VENDOR_ID_TOSHIBA, 0xfffd, 0xfa91,
 		      "Toshiba Satellite S50D", STAC_92HD83XXX_GPIO10_EAPD),
 	{} /* terminator */
 };
diff --git a/sound/pci/oxygen/oxygen_mixer.c b/sound/pci/oxygen/oxygen_mixer.c
index 6492bca..4ca1266 100644
--- a/sound/pci/oxygen/oxygen_mixer.c
+++ b/sound/pci/oxygen/oxygen_mixer.c
@@ -88,7 +88,7 @@
 	int changed;
 
 	mutex_lock(&chip->mutex);
-	changed = !value->value.integer.value[0] != chip->dac_mute;
+	changed = (!value->value.integer.value[0]) != chip->dac_mute;
 	if (changed) {
 		chip->dac_mute = !value->value.integer.value[0];
 		chip->model.update_dac_mute(chip);
diff --git a/sound/soc/Kconfig b/sound/soc/Kconfig
index 2ae9619..1d651b8 100644
--- a/sound/soc/Kconfig
+++ b/sound/soc/Kconfig
@@ -30,6 +30,9 @@
 	bool
 	select SND_DMAENGINE_PCM
 
+config SND_SOC_TOPOLOGY
+	bool
+
 # All the supported SoCs
 source "sound/soc/adi/Kconfig"
 source "sound/soc/atmel/Kconfig"
diff --git a/sound/soc/Makefile b/sound/soc/Makefile
index e189903..669648b 100644
--- a/sound/soc/Makefile
+++ b/sound/soc/Makefile
@@ -1,6 +1,9 @@
 snd-soc-core-objs := soc-core.o soc-dapm.o soc-jack.o soc-cache.o soc-utils.o
 snd-soc-core-objs += soc-pcm.o soc-compress.o soc-io.o soc-devres.o soc-ops.o
+
+ifneq ($(CONFIG_SND_SOC_TOPOLOGY),)
 snd-soc-core-objs += soc-topology.o
+endif
 
 ifneq ($(CONFIG_SND_SOC_GENERIC_DMAENGINE_PCM),)
 snd-soc-core-objs += soc-generic-dmaengine-pcm.o
diff --git a/sound/soc/codecs/cs4265.c b/sound/soc/codecs/cs4265.c
index d7ec4756..8e36198 100644
--- a/sound/soc/codecs/cs4265.c
+++ b/sound/soc/codecs/cs4265.c
@@ -457,14 +457,14 @@
 	case SND_SOC_DAIFMT_RIGHT_J:
 		if (params_width(params) == 16) {
 			snd_soc_update_bits(codec, CS4265_DAC_CTL,
-				CS4265_DAC_CTL_DIF, (1 << 5));
+				CS4265_DAC_CTL_DIF, (2 << 4));
 			snd_soc_update_bits(codec, CS4265_SPDIF_CTL2,
-				CS4265_SPDIF_CTL2_DIF, (1 << 7));
+				CS4265_SPDIF_CTL2_DIF, (2 << 6));
 		} else {
 			snd_soc_update_bits(codec, CS4265_DAC_CTL,
-				CS4265_DAC_CTL_DIF, (3 << 5));
+				CS4265_DAC_CTL_DIF, (3 << 4));
 			snd_soc_update_bits(codec, CS4265_SPDIF_CTL2,
-				CS4265_SPDIF_CTL2_DIF, (1 << 7));
+				CS4265_SPDIF_CTL2_DIF, (3 << 6));
 		}
 		break;
 	case SND_SOC_DAIFMT_LEFT_J:
@@ -473,7 +473,7 @@
 		snd_soc_update_bits(codec, CS4265_ADC_CTL,
 			CS4265_ADC_DIF, 0);
 		snd_soc_update_bits(codec, CS4265_SPDIF_CTL2,
-			CS4265_SPDIF_CTL2_DIF, (1 << 6));
+			CS4265_SPDIF_CTL2_DIF, 0);
 
 		break;
 	default:
diff --git a/sound/soc/codecs/pcm1681.c b/sound/soc/codecs/pcm1681.c
index 477e13d..e7ba557 100644
--- a/sound/soc/codecs/pcm1681.c
+++ b/sound/soc/codecs/pcm1681.c
@@ -102,7 +102,7 @@
 
 	if (val != -1) {
 		regmap_update_bits(priv->regmap, PCM1681_DEEMPH_CONTROL,
-					PCM1681_DEEMPH_RATE_MASK, val);
+				   PCM1681_DEEMPH_RATE_MASK, val << 3);
 		enable = 1;
 	} else
 		enable = 0;
diff --git a/sound/soc/codecs/rt5645.c b/sound/soc/codecs/rt5645.c
index 9ce311e..961bd7e 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -2943,6 +2943,9 @@
 {
 	int val, btn_type, gpio_state = 0, report = 0;
 
+	if (!rt5645->codec)
+		return -EINVAL;
+
 	switch (rt5645->pdata.jd_mode) {
 	case 0: /* Not using rt5645 JD */
 		if (rt5645->gpiod_hp_det) {
@@ -3338,6 +3341,8 @@
 		break;
 
 	case RT5645_DMIC_DATA_GPIO5:
+		regmap_update_bits(rt5645->regmap, RT5645_GPIO_CTRL1,
+			RT5645_I2S2_DAC_PIN_MASK, RT5645_I2S2_DAC_PIN_GPIO);
 		regmap_update_bits(rt5645->regmap, RT5645_DMIC_CTRL1,
 			RT5645_DMIC_1_DP_MASK, RT5645_DMIC_1_DP_GPIO5);
 		regmap_update_bits(rt5645->regmap, RT5645_GPIO_CTRL1,
diff --git a/sound/soc/codecs/rt5645.h b/sound/soc/codecs/rt5645.h
index 0353a6a..278bb9f 100644
--- a/sound/soc/codecs/rt5645.h
+++ b/sound/soc/codecs/rt5645.h
@@ -1693,6 +1693,10 @@
 #define RT5645_GP6_PIN_SFT			6
 #define RT5645_GP6_PIN_GPIO6			(0x0 << 6)
 #define RT5645_GP6_PIN_DMIC2_SDA		(0x1 << 6)
+#define RT5645_I2S2_DAC_PIN_MASK		(0x1 << 4)
+#define RT5645_I2S2_DAC_PIN_SFT			4
+#define RT5645_I2S2_DAC_PIN_I2S			(0x0 << 4)
+#define RT5645_I2S2_DAC_PIN_GPIO		(0x1 << 4)
 #define RT5645_GP8_PIN_MASK			(0x1 << 3)
 #define RT5645_GP8_PIN_SFT			3
 #define RT5645_GP8_PIN_GPIO8			(0x0 << 3)
diff --git a/sound/soc/codecs/sgtl5000.h b/sound/soc/codecs/sgtl5000.h
index bd7a344..1c317de 100644
--- a/sound/soc/codecs/sgtl5000.h
+++ b/sound/soc/codecs/sgtl5000.h
@@ -275,7 +275,7 @@
 #define SGTL5000_BIAS_CTRL_MASK			0x000e
 #define SGTL5000_BIAS_CTRL_SHIFT		1
 #define SGTL5000_BIAS_CTRL_WIDTH		3
-#define SGTL5000_SMALL_POP			0
+#define SGTL5000_SMALL_POP			1
 
 /*
  * SGTL5000_CHIP_MIC_CTRL
diff --git a/sound/soc/codecs/ssm4567.c b/sound/soc/codecs/ssm4567.c
index 938d2cb..84a4f5a 100644
--- a/sound/soc/codecs/ssm4567.c
+++ b/sound/soc/codecs/ssm4567.c
@@ -315,7 +315,13 @@
 	if (invert_fclk)
 		ctrl1 |= SSM4567_SAI_CTRL_1_FSYNC;
 
-	return regmap_write(ssm4567->regmap, SSM4567_REG_SAI_CTRL_1, ctrl1);
+	return regmap_update_bits(ssm4567->regmap, SSM4567_REG_SAI_CTRL_1,
+			SSM4567_SAI_CTRL_1_BCLK |
+			SSM4567_SAI_CTRL_1_FSYNC |
+			SSM4567_SAI_CTRL_1_LJ |
+			SSM4567_SAI_CTRL_1_TDM |
+			SSM4567_SAI_CTRL_1_PDM,
+			ctrl1);
 }
 
 static int ssm4567_set_power(struct ssm4567 *ssm4567, bool enable)
diff --git a/sound/soc/fsl/fsl_ssi.c b/sound/soc/fsl/fsl_ssi.c
index c7647e0..c0b940e 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -633,7 +633,7 @@
 		sub *= 100000;
 		do_div(sub, freq);
 
-		if (sub < savesub) {
+		if (sub < savesub && !(i == 0 && psr == 0 && div2 == 0)) {
 			baudrate = tmprate;
 			savesub = sub;
 			pm = i;
diff --git a/sound/soc/intel/Makefile b/sound/soc/intel/Makefile
index 3853ec2..6de5d5c 100644
--- a/sound/soc/intel/Makefile
+++ b/sound/soc/intel/Makefile
@@ -7,4 +7,4 @@
 obj-$(CONFIG_SND_SST_MFLD_PLATFORM) += atom/
 
 # Machine support
-obj-$(CONFIG_SND_SOC_INTEL_SST) += boards/
+obj-$(CONFIG_SND_SOC) += boards/
diff --git a/sound/soc/intel/atom/sst/sst_drv_interface.c b/sound/soc/intel/atom/sst/sst_drv_interface.c
index 620da1d..0e0e4d9 100644
--- a/sound/soc/intel/atom/sst/sst_drv_interface.c
+++ b/sound/soc/intel/atom/sst/sst_drv_interface.c
@@ -42,6 +42,11 @@
 #define MIN_FRAGMENT_SIZE (50 * 1024)
 #define MAX_FRAGMENT_SIZE (1024 * 1024)
 #define SST_GET_BYTES_PER_SAMPLE(pcm_wd_sz)  (((pcm_wd_sz + 15) >> 4) << 1)
+#ifdef CONFIG_PM
+#define GET_USAGE_COUNT(dev) (atomic_read(&dev->power.usage_count))
+#else
+#define GET_USAGE_COUNT(dev) 1
+#endif
 
 int free_stream_context(struct intel_sst_drv *ctx, unsigned int str_id)
 {
@@ -141,15 +146,9 @@
 	int ret = 0;
 	int usage_count = 0;
 
-#ifdef CONFIG_PM
-	usage_count = atomic_read(&dev->power.usage_count);
-#else
-	usage_count = 1;
-#endif
-
 	if (state == true) {
 		ret = pm_runtime_get_sync(dev);
-
+		usage_count = GET_USAGE_COUNT(dev);
 		dev_dbg(ctx->dev, "Enable: pm usage count: %d\n", usage_count);
 		if (ret < 0) {
 			dev_err(ctx->dev, "Runtime get failed with err: %d\n", ret);
@@ -164,6 +163,7 @@
 			}
 		}
 	} else {
+		usage_count = GET_USAGE_COUNT(dev);
 		dev_dbg(ctx->dev, "Disable: pm usage count: %d\n", usage_count);
 		return sst_pm_runtime_put(ctx);
 	}
diff --git a/sound/soc/intel/baytrail/sst-baytrail-ipc.c b/sound/soc/intel/baytrail/sst-baytrail-ipc.c
index 4c01bb4..5bbaa66 100644
--- a/sound/soc/intel/baytrail/sst-baytrail-ipc.c
+++ b/sound/soc/intel/baytrail/sst-baytrail-ipc.c
@@ -701,6 +701,8 @@
 	if (byt == NULL)
 		return -ENOMEM;
 
+	byt->dev = dev;
+
 	ipc = &byt->ipc;
 	ipc->dev = dev;
 	ipc->ops.tx_msg = byt_tx_msg;
diff --git a/sound/soc/intel/boards/cht_bsw_max98090_ti.c b/sound/soc/intel/boards/cht_bsw_max98090_ti.c
index d604ee8..70f8321 100644
--- a/sound/soc/intel/boards/cht_bsw_max98090_ti.c
+++ b/sound/soc/intel/boards/cht_bsw_max98090_ti.c
@@ -69,12 +69,12 @@
 	{"Headphone", NULL, "HPR"},
 	{"Ext Spk", NULL, "SPKL"},
 	{"Ext Spk", NULL, "SPKR"},
-	{"AIF1 Playback", NULL, "ssp2 Tx"},
+	{"HiFi Playback", NULL, "ssp2 Tx"},
 	{"ssp2 Tx", NULL, "codec_out0"},
 	{"ssp2 Tx", NULL, "codec_out1"},
 	{"codec_in0", NULL, "ssp2 Rx" },
 	{"codec_in1", NULL, "ssp2 Rx" },
-	{"ssp2 Rx", NULL, "AIF1 Capture"},
+	{"ssp2 Rx", NULL, "HiFi Capture"},
 };
 
 static const struct snd_kcontrol_new cht_mc_controls[] = {
diff --git a/sound/soc/intel/haswell/sst-haswell-ipc.c b/sound/soc/intel/haswell/sst-haswell-ipc.c
index f95f271..f6efa9d 100644
--- a/sound/soc/intel/haswell/sst-haswell-ipc.c
+++ b/sound/soc/intel/haswell/sst-haswell-ipc.c
@@ -2119,6 +2119,8 @@
 	if (hsw == NULL)
 		return -ENOMEM;
 
+	hsw->dev = dev;
+
 	ipc = &hsw->ipc;
 	ipc->dev = dev;
 	ipc->ops.tx_msg = hsw_tx_msg;
diff --git a/sound/soc/mediatek/mt8173-max98090.c b/sound/soc/mediatek/mt8173-max98090.c
index 4d44b58..2d2536a 100644
--- a/sound/soc/mediatek/mt8173-max98090.c
+++ b/sound/soc/mediatek/mt8173-max98090.c
@@ -103,7 +103,6 @@
 		.name = "MAX98090 Playback",
 		.stream_name = "MAX98090 Playback",
 		.cpu_dai_name = "DL1",
-		.platform_name = "11220000.mt8173-afe-pcm",
 		.codec_name = "snd-soc-dummy",
 		.codec_dai_name = "snd-soc-dummy-dai",
 		.trigger = {SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
@@ -114,7 +113,6 @@
 		.name = "MAX98090 Capture",
 		.stream_name = "MAX98090 Capture",
 		.cpu_dai_name = "VUL",
-		.platform_name = "11220000.mt8173-afe-pcm",
 		.codec_name = "snd-soc-dummy",
 		.codec_dai_name = "snd-soc-dummy-dai",
 		.trigger = {SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
@@ -125,7 +123,6 @@
 	{
 		.name = "Codec",
 		.cpu_dai_name = "I2S",
-		.platform_name = "11220000.mt8173-afe-pcm",
 		.no_pcm = 1,
 		.codec_dai_name = "HiFi",
 		.init = mt8173_max98090_init,
@@ -152,9 +149,21 @@
 static int mt8173_max98090_dev_probe(struct platform_device *pdev)
 {
 	struct snd_soc_card *card = &mt8173_max98090_card;
-	struct device_node *codec_node;
+	struct device_node *codec_node, *platform_node;
 	int ret, i;
 
+	platform_node = of_parse_phandle(pdev->dev.of_node,
+					 "mediatek,platform", 0);
+	if (!platform_node) {
+		dev_err(&pdev->dev, "Property 'platform' missing or invalid\n");
+		return -EINVAL;
+	}
+	for (i = 0; i < card->num_links; i++) {
+		if (mt8173_max98090_dais[i].platform_name)
+			continue;
+		mt8173_max98090_dais[i].platform_of_node = platform_node;
+	}
+
 	codec_node = of_parse_phandle(pdev->dev.of_node,
 				      "mediatek,audio-codec", 0);
 	if (!codec_node) {
diff --git a/sound/soc/mediatek/mt8173-rt5650-rt5676.c b/sound/soc/mediatek/mt8173-rt5650-rt5676.c
index 0940553..6f52eca 100644
--- a/sound/soc/mediatek/mt8173-rt5650-rt5676.c
+++ b/sound/soc/mediatek/mt8173-rt5650-rt5676.c
@@ -138,7 +138,6 @@
 		.name = "rt5650_rt5676 Playback",
 		.stream_name = "rt5650_rt5676 Playback",
 		.cpu_dai_name = "DL1",
-		.platform_name = "11220000.mt8173-afe-pcm",
 		.codec_name = "snd-soc-dummy",
 		.codec_dai_name = "snd-soc-dummy-dai",
 		.trigger = {SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
@@ -149,7 +148,6 @@
 		.name = "rt5650_rt5676 Capture",
 		.stream_name = "rt5650_rt5676 Capture",
 		.cpu_dai_name = "VUL",
-		.platform_name = "11220000.mt8173-afe-pcm",
 		.codec_name = "snd-soc-dummy",
 		.codec_dai_name = "snd-soc-dummy-dai",
 		.trigger = {SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
@@ -161,7 +159,6 @@
 	{
 		.name = "Codec",
 		.cpu_dai_name = "I2S",
-		.platform_name = "11220000.mt8173-afe-pcm",
 		.no_pcm = 1,
 		.codecs = mt8173_rt5650_rt5676_codecs,
 		.num_codecs = 2,
@@ -209,7 +206,21 @@
 static int mt8173_rt5650_rt5676_dev_probe(struct platform_device *pdev)
 {
 	struct snd_soc_card *card = &mt8173_rt5650_rt5676_card;
-	int ret;
+	struct device_node *platform_node;
+	int i, ret;
+
+	platform_node = of_parse_phandle(pdev->dev.of_node,
+					 "mediatek,platform", 0);
+	if (!platform_node) {
+		dev_err(&pdev->dev, "Property 'platform' missing or invalid\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < card->num_links; i++) {
+		if (mt8173_rt5650_rt5676_dais[i].platform_name)
+			continue;
+		mt8173_rt5650_rt5676_dais[i].platform_of_node = platform_node;
+	}
 
 	mt8173_rt5650_rt5676_codecs[0].of_node =
 		of_parse_phandle(pdev->dev.of_node, "mediatek,audio-codec", 0);
diff --git a/sound/soc/mediatek/mtk-afe-pcm.c b/sound/soc/mediatek/mtk-afe-pcm.c
index cc228db..9863da7 100644
--- a/sound/soc/mediatek/mtk-afe-pcm.c
+++ b/sound/soc/mediatek/mtk-afe-pcm.c
@@ -1199,6 +1199,8 @@
 static int mtk_afe_pcm_dev_remove(struct platform_device *pdev)
 {
 	pm_runtime_disable(&pdev->dev);
+	if (!pm_runtime_status_suspended(&pdev->dev))
+		mtk_afe_runtime_suspend(&pdev->dev);
 	snd_soc_unregister_component(&pdev->dev);
 	snd_soc_unregister_platform(&pdev->dev);
 	return 0;
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 3a4a5c0..0e1e69c 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1716,6 +1716,7 @@
 	if (card->remove)
 		card->remove(card);
 
+	snd_soc_dapm_free(&card->dapm);
 	soc_cleanup_card_debugfs(card);
 	snd_card_free(card->snd_card);
 
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index aa327c9..e0de807 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -358,9 +358,10 @@
 			data->widget =
 				snd_soc_dapm_new_control_unlocked(widget->dapm,
 				&template);
+			kfree(name);
 			if (!data->widget) {
 				ret = -ENOMEM;
-				goto err_name;
+				goto err_data;
 			}
 		}
 		break;
@@ -389,11 +390,12 @@
 
 			data->value = template.on_val;
 
-			data->widget = snd_soc_dapm_new_control(widget->dapm,
-					&template);
+			data->widget = snd_soc_dapm_new_control_unlocked(
+						widget->dapm, &template);
+			kfree(name);
 			if (!data->widget) {
 				ret = -ENOMEM;
-				goto err_name;
+				goto err_data;
 			}
 
 			snd_soc_dapm_add_path(widget->dapm, data->widget,
@@ -408,8 +410,6 @@
 
 	return 0;
 
-err_name:
-	kfree(name);
 err_data:
 	kfree(data);
 	return ret;
@@ -418,8 +418,6 @@
 static void dapm_kcontrol_free(struct snd_kcontrol *kctl)
 {
 	struct dapm_kcontrol_data *data = snd_kcontrol_chip(kctl);
-	if (data->widget)
-		kfree(data->widget->name);
 	kfree(data->wlist);
 	kfree(data);
 }
@@ -1952,6 +1950,7 @@
 					   size_t count, loff_t *ppos)
 {
 	struct snd_soc_dapm_widget *w = file->private_data;
+	struct snd_soc_card *card = w->dapm->card;
 	char *buf;
 	int in, out;
 	ssize_t ret;
@@ -1961,6 +1960,8 @@
 	if (!buf)
 		return -ENOMEM;
 
+	mutex_lock(&card->dapm_mutex);
+
 	/* Supply widgets are not handled by is_connected_{input,output}_ep() */
 	if (w->is_supply) {
 		in = 0;
@@ -2007,6 +2008,8 @@
 					p->sink->name);
 	}
 
+	mutex_unlock(&card->dapm_mutex);
+
 	ret = simple_read_from_buffer(user_buf, count, ppos, buf, ret);
 
 	kfree(buf);
@@ -2281,11 +2284,15 @@
 	struct snd_soc_pcm_runtime *rtd = dev_get_drvdata(dev);
 	int i, count = 0;
 
+	mutex_lock(&rtd->card->dapm_mutex);
+
 	for (i = 0; i < rtd->num_codecs; i++) {
 		struct snd_soc_codec *codec = rtd->codec_dais[i]->codec;
 		count += dapm_widget_show_codec(codec, buf + count);
 	}
 
+	mutex_unlock(&rtd->card->dapm_mutex);
+
 	return count;
 }
 
@@ -3334,16 +3341,10 @@
 	}
 
 	prefix = soc_dapm_prefix(dapm);
-	if (prefix) {
+	if (prefix)
 		w->name = kasprintf(GFP_KERNEL, "%s %s", prefix, widget->name);
-		if (widget->sname)
-			w->sname = kasprintf(GFP_KERNEL, "%s %s", prefix,
-					     widget->sname);
-	} else {
+	else
 		w->name = kasprintf(GFP_KERNEL, "%s", widget->name);
-		if (widget->sname)
-			w->sname = kasprintf(GFP_KERNEL, "%s", widget->sname);
-	}
 	if (w->name == NULL) {
 		kfree(w);
 		return NULL;
@@ -3792,7 +3793,7 @@
 				break;
 			}
 
-			if (!w->sname || !strstr(w->sname, dai_w->name))
+			if (!w->sname || !strstr(w->sname, dai_w->sname))
 				continue;
 
 			if (dai_w->id == snd_soc_dapm_dai_in) {
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index d096068..31068b8 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -33,6 +33,7 @@
 #include <sound/soc.h>
 #include <sound/soc-dapm.h>
 #include <sound/soc-topology.h>
+#include <sound/tlv.h>
 
 /*
  * We make several passes over the data (since it wont necessarily be ordered)
@@ -144,7 +145,7 @@
 	{SND_SOC_TPLG_CTL_STROBE, snd_soc_get_strobe,
 		snd_soc_put_strobe, NULL},
 	{SND_SOC_TPLG_DAPM_CTL_VOLSW, snd_soc_dapm_get_volsw,
-		snd_soc_dapm_put_volsw, NULL},
+		snd_soc_dapm_put_volsw, snd_soc_info_volsw},
 	{SND_SOC_TPLG_DAPM_CTL_ENUM_DOUBLE, snd_soc_dapm_get_enum_double,
 		snd_soc_dapm_put_enum_double, snd_soc_info_enum_double},
 	{SND_SOC_TPLG_DAPM_CTL_ENUM_VIRT, snd_soc_dapm_get_enum_double,
@@ -534,7 +535,7 @@
 			k->put = bops[i].put;
 		if (k->get == NULL && bops[i].id == hdr->ops.get)
 			k->get = bops[i].get;
-		if (k->info == NULL && ops[i].id == hdr->ops.info)
+		if (k->info == NULL && bops[i].id == hdr->ops.info)
 			k->info = bops[i].info;
 	}
 
@@ -579,29 +580,51 @@
 	return 0;
 }
 
-static int soc_tplg_create_tlv(struct soc_tplg *tplg,
-	struct snd_kcontrol_new *kc, u32 tlv_size)
+
+static int soc_tplg_create_tlv_db_scale(struct soc_tplg *tplg,
+	struct snd_kcontrol_new *kc, struct snd_soc_tplg_tlv_dbscale *scale)
 {
-	struct snd_soc_tplg_ctl_tlv *tplg_tlv;
-	struct snd_ctl_tlv *tlv;
+	unsigned int item_len = 2 * sizeof(unsigned int);
+	unsigned int *p;
 
-	if (tlv_size == 0)
-		return 0;
-
-	tplg_tlv = (struct snd_soc_tplg_ctl_tlv *) tplg->pos;
-	tplg->pos += tlv_size;
-
-	tlv = kzalloc(sizeof(*tlv) + tlv_size, GFP_KERNEL);
-	if (tlv == NULL)
+	p = kzalloc(item_len + 2 * sizeof(unsigned int), GFP_KERNEL);
+	if (!p)
 		return -ENOMEM;
 
-	dev_dbg(tplg->dev, " created TLV type %d size %d bytes\n",
-		tplg_tlv->numid, tplg_tlv->size);
+	p[0] = SNDRV_CTL_TLVT_DB_SCALE;
+	p[1] = item_len;
+	p[2] = scale->min;
+	p[3] = (scale->step & TLV_DB_SCALE_MASK)
+			| (scale->mute ? TLV_DB_SCALE_MUTE : 0);
 
-	tlv->numid = tplg_tlv->numid;
-	tlv->length = tplg_tlv->size;
-	memcpy(tlv->tlv, tplg_tlv + 1, tplg_tlv->size);
-	kc->tlv.p = (void *)tlv;
+	kc->tlv.p = (void *)p;
+	return 0;
+}
+
+static int soc_tplg_create_tlv(struct soc_tplg *tplg,
+	struct snd_kcontrol_new *kc, struct snd_soc_tplg_ctl_hdr *tc)
+{
+	struct snd_soc_tplg_ctl_tlv *tplg_tlv;
+
+	if (!(tc->access & SNDRV_CTL_ELEM_ACCESS_TLV_READWRITE))
+		return 0;
+
+	if (tc->access & SNDRV_CTL_ELEM_ACCESS_TLV_CALLBACK) {
+		kc->tlv.c = snd_soc_bytes_tlv_callback;
+	} else {
+		tplg_tlv = &tc->tlv;
+		switch (tplg_tlv->type) {
+		case SNDRV_CTL_TLVT_DB_SCALE:
+			return soc_tplg_create_tlv_db_scale(tplg, kc,
+					&tplg_tlv->scale);
+
+		/* TODO: add support for other TLV types */
+		default:
+			dev_dbg(tplg->dev, "Unsupported TLV type %d\n",
+					tplg_tlv->type);
+			return -EINVAL;
+		}
+	}
 
 	return 0;
 }
@@ -773,7 +796,7 @@
 		}
 
 		/* create any TLV data */
-		soc_tplg_create_tlv(tplg, &kc, mc->hdr.tlv_size);
+		soc_tplg_create_tlv(tplg, &kc, &mc->hdr);
 
 		/* register control here */
 		err = soc_tplg_add_kcontrol(tplg, &kc,
@@ -1351,6 +1374,7 @@
 	template.reg = w->reg;
 	template.shift = w->shift;
 	template.mask = w->mask;
+	template.subseq = w->subseq;
 	template.on_val = w->invert ? 0 : 1;
 	template.off_val = w->invert ? 1 : 0;
 	template.ignore_suspend = w->ignore_suspend;
diff --git a/sound/soc/zte/zx296702-i2s.c b/sound/soc/zte/zx296702-i2s.c
index 98d96e1..1930c42 100644
--- a/sound/soc/zte/zx296702-i2s.c
+++ b/sound/soc/zte/zx296702-i2s.c
@@ -393,9 +393,9 @@
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	zx_i2s->mapbase = res->start;
 	zx_i2s->reg_base = devm_ioremap_resource(&pdev->dev, res);
-	if (!zx_i2s->reg_base) {
+	if (IS_ERR(zx_i2s->reg_base)) {
 		dev_err(&pdev->dev, "ioremap failed!\n");
-		return -EIO;
+		return PTR_ERR(zx_i2s->reg_base);
 	}
 
 	writel_relaxed(0, zx_i2s->reg_base + ZX_I2S_FIFO_CTRL);
diff --git a/sound/soc/zte/zx296702-spdif.c b/sound/soc/zte/zx296702-spdif.c
index 11a0e46..26265ce 100644
--- a/sound/soc/zte/zx296702-spdif.c
+++ b/sound/soc/zte/zx296702-spdif.c
@@ -322,9 +322,9 @@
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	zx_spdif->mapbase = res->start;
 	zx_spdif->reg_base = devm_ioremap_resource(&pdev->dev, res);
-	if (!zx_spdif->reg_base) {
+	if (IS_ERR(zx_spdif->reg_base)) {
 		dev_err(&pdev->dev, "ioremap failed!\n");
-		return -EIO;
+		return PTR_ERR(zx_spdif->reg_base);
 	}
 
 	zx_spdif_dev_init(zx_spdif->reg_base);
diff --git a/sound/sparc/amd7930.c b/sound/sparc/amd7930.c
index 1b1a89e..784ceb8 100644
--- a/sound/sparc/amd7930.c
+++ b/sound/sparc/amd7930.c
@@ -956,6 +956,7 @@
 	if (!amd->regs) {
 		snd_printk(KERN_ERR
 			   "amd7930-%d: Unable to map chip registers.\n", dev);
+		kfree(amd);
 		return -EIO;
 	}
 
diff --git a/sound/usb/card.c b/sound/usb/card.c
index 1fab977..0450593 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -638,7 +638,7 @@
 	int err = -ENODEV;
 
 	down_read(&chip->shutdown_rwsem);
-	if (chip->probing && chip->in_pm)
+	if (chip->probing || chip->in_pm)
 		err = 0;
 	else if (!chip->shutdown)
 		err = usb_autopm_get_interface(chip->pm_intf);
diff --git a/sound/usb/line6/pcm.c b/sound/usb/line6/pcm.c
index 8461d6b..204cc07 100644
--- a/sound/usb/line6/pcm.c
+++ b/sound/usb/line6/pcm.c
@@ -186,12 +186,8 @@
 	int ret = 0;
 
 	spin_lock_irqsave(&pstr->lock, flags);
-	if (!test_and_set_bit(type, &pstr->running)) {
-		if (pstr->active_urbs || pstr->unlink_urbs) {
-			ret = -EBUSY;
-			goto error;
-		}
-
+	if (!test_and_set_bit(type, &pstr->running) &&
+	    !(pstr->active_urbs || pstr->unlink_urbs)) {
 		pstr->count = 0;
 		/* Submit all currently available URBs */
 		if (direction == SNDRV_PCM_STREAM_PLAYBACK)
@@ -199,7 +195,6 @@
 		else
 			ret = line6_submit_audio_in_all_urbs(line6pcm);
 	}
- error:
 	if (ret < 0)
 		clear_bit(type, &pstr->running);
 	spin_unlock_irqrestore(&pstr->lock, flags);
diff --git a/sound/usb/mixer_maps.c b/sound/usb/mixer_maps.c
index e5000da..6a803ef 100644
--- a/sound/usb/mixer_maps.c
+++ b/sound/usb/mixer_maps.c
@@ -341,6 +341,20 @@
 	{ 0 }
 };
 
+/* Bose companion 5, the dB conversion factor is 16 instead of 256 */
+static struct usbmix_dB_map bose_companion5_dB = {-5006, -6};
+static struct usbmix_name_map bose_companion5_map[] = {
+	{ 3, NULL, .dB = &bose_companion5_dB },
+	{ 0 }	/* terminator */
+};
+
+/* Dragonfly DAC 1.2, the dB conversion factor is 1 instead of 256 */
+static struct usbmix_dB_map dragonfly_1_2_dB = {0, 5000};
+static struct usbmix_name_map dragonfly_1_2_map[] = {
+	{ 7, NULL, .dB = &dragonfly_1_2_dB },
+	{ 0 }	/* terminator */
+};
+
 /*
  * Control map entries
  */
@@ -451,6 +465,16 @@
 		.id = USB_ID(0x25c4, 0x0003),
 		.map = scms_usb3318_map,
 	},
+	{
+		/* Bose Companion 5 */
+		.id = USB_ID(0x05a7, 0x1020),
+		.map = bose_companion5_map,
+	},
+	{
+		/* Dragonfly DAC 1.2 */
+		.id = USB_ID(0x21b4, 0x0081),
+		.map = dragonfly_1_2_map,
+	},
 	{ 0 } /* terminator */
 };
 
diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 2f6d3e9..e475665 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -2512,6 +2512,74 @@
 	}
 },
 
+/* Steinberg devices */
+{
+	/* Steinberg MI2 */
+	USB_DEVICE_VENDOR_SPEC(0x0a4e, 0x2040),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = & (const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 1,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 3,
+				.type = QUIRK_MIDI_FIXED_ENDPOINT,
+				.data = &(const struct snd_usb_midi_endpoint_info) {
+					.out_cables = 0x0001,
+					.in_cables  = 0x0001
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+{
+	/* Steinberg MI4 */
+	USB_DEVICE_VENDOR_SPEC(0x0a4e, 0x4040),
+	.driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+		.ifnum = QUIRK_ANY_INTERFACE,
+		.type = QUIRK_COMPOSITE,
+		.data = & (const struct snd_usb_audio_quirk[]) {
+			{
+				.ifnum = 0,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 1,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 2,
+				.type = QUIRK_AUDIO_STANDARD_INTERFACE
+			},
+			{
+				.ifnum = 3,
+				.type = QUIRK_MIDI_FIXED_ENDPOINT,
+				.data = &(const struct snd_usb_midi_endpoint_info) {
+					.out_cables = 0x0001,
+					.in_cables  = 0x0001
+				}
+			},
+			{
+				.ifnum = -1
+			}
+		}
+	}
+},
+
 /* TerraTec devices */
 {
 	USB_DEVICE_VENDOR_SPEC(0x0ccd, 0x0012),
diff --git a/tools/include/linux/compiler.h b/tools/include/linux/compiler.h
index f0e7267..9098083 100644
--- a/tools/include/linux/compiler.h
+++ b/tools/include/linux/compiler.h
@@ -41,4 +41,62 @@
 
 #define ACCESS_ONCE(x) (*(volatile typeof(x) *)&(x))
 
+#include <linux/types.h>
+
+static __always_inline void __read_once_size(const volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(__u8 *)res = *(volatile __u8 *)p; break;
+	case 2: *(__u16 *)res = *(volatile __u16 *)p; break;
+	case 4: *(__u32 *)res = *(volatile __u32 *)p; break;
+	case 8: *(__u64 *)res = *(volatile __u64 *)p; break;
+	default:
+		barrier();
+		__builtin_memcpy((void *)res, (const void *)p, size);
+		barrier();
+	}
+}
+
+static __always_inline void __write_once_size(volatile void *p, void *res, int size)
+{
+	switch (size) {
+	case 1: *(volatile __u8 *)p = *(__u8 *)res; break;
+	case 2: *(volatile __u16 *)p = *(__u16 *)res; break;
+	case 4: *(volatile __u32 *)p = *(__u32 *)res; break;
+	case 8: *(volatile __u64 *)p = *(__u64 *)res; break;
+	default:
+		barrier();
+		__builtin_memcpy((void *)p, (const void *)res, size);
+		barrier();
+	}
+}
+
+/*
+ * Prevent the compiler from merging or refetching reads or writes. The
+ * compiler is also forbidden from reordering successive instances of
+ * READ_ONCE, WRITE_ONCE and ACCESS_ONCE (see below), but only when the
+ * compiler is aware of some particular ordering.  One way to make the
+ * compiler aware of ordering is to put the two invocations of READ_ONCE,
+ * WRITE_ONCE or ACCESS_ONCE() in different C statements.
+ *
+ * In contrast to ACCESS_ONCE these two macros will also work on aggregate
+ * data types like structs or unions. If the size of the accessed data
+ * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
+ * READ_ONCE() and WRITE_ONCE()  will fall back to memcpy and print a
+ * compile-time warning.
+ *
+ * Their two major use cases are: (1) Mediating communication between
+ * process-level code and irq/NMI handlers, all running on the same CPU,
+ * and (2) Ensuring that the compiler does not  fold, spindle, or otherwise
+ * mutilate accesses that either do not require ordering or that interact
+ * with an explicit memory barrier or atomic instruction that provides the
+ * required ordering.
+ */
+
+#define READ_ONCE(x) \
+	({ union { typeof(x) __val; char __c[1]; } __u; __read_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+
+#define WRITE_ONCE(x, val) \
+	({ union { typeof(x) __val; char __c[1]; } __u = { .__val = (val) }; __write_once_size(&(x), __u.__c, sizeof(x)); __u.__val; })
+
 #endif /* _TOOLS_LINUX_COMPILER_H */
diff --git a/tools/include/linux/export.h b/tools/include/linux/export.h
deleted file mode 100644
index d07e586..0000000
--- a/tools/include/linux/export.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef _TOOLS_LINUX_EXPORT_H_
-#define _TOOLS_LINUX_EXPORT_H_
-
-#define EXPORT_SYMBOL(sym)
-#define EXPORT_SYMBOL_GPL(sym)
-#define EXPORT_SYMBOL_GPL_FUTURE(sym)
-#define EXPORT_UNUSED_SYMBOL(sym)
-#define EXPORT_UNUSED_SYMBOL_GPL(sym)
-
-#endif
diff --git a/tools/include/linux/rbtree.h b/tools/include/linux/rbtree.h
new file mode 100644
index 0000000..1125822
--- /dev/null
+++ b/tools/include/linux/rbtree.h
@@ -0,0 +1,104 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  linux/include/linux/rbtree.h
+
+  To use rbtrees you'll have to implement your own insert and search cores.
+  This will avoid us to use callbacks and to drop drammatically performances.
+  I know it's not the cleaner way,  but in C (not in C++) to get
+  performances and genericity...
+
+  See Documentation/rbtree.txt for documentation and samples.
+*/
+
+#ifndef __TOOLS_LINUX_PERF_RBTREE_H
+#define __TOOLS_LINUX_PERF_RBTREE_H
+
+#include <linux/kernel.h>
+#include <linux/stddef.h>
+
+struct rb_node {
+	unsigned long  __rb_parent_color;
+	struct rb_node *rb_right;
+	struct rb_node *rb_left;
+} __attribute__((aligned(sizeof(long))));
+    /* The alignment might seem pointless, but allegedly CRIS needs it */
+
+struct rb_root {
+	struct rb_node *rb_node;
+};
+
+
+#define rb_parent(r)   ((struct rb_node *)((r)->__rb_parent_color & ~3))
+
+#define RB_ROOT	(struct rb_root) { NULL, }
+#define	rb_entry(ptr, type, member) container_of(ptr, type, member)
+
+#define RB_EMPTY_ROOT(root)  ((root)->rb_node == NULL)
+
+/* 'empty' nodes are nodes that are known not to be inserted in an rbtree */
+#define RB_EMPTY_NODE(node)  \
+	((node)->__rb_parent_color == (unsigned long)(node))
+#define RB_CLEAR_NODE(node)  \
+	((node)->__rb_parent_color = (unsigned long)(node))
+
+
+extern void rb_insert_color(struct rb_node *, struct rb_root *);
+extern void rb_erase(struct rb_node *, struct rb_root *);
+
+
+/* Find logical next and previous nodes in a tree */
+extern struct rb_node *rb_next(const struct rb_node *);
+extern struct rb_node *rb_prev(const struct rb_node *);
+extern struct rb_node *rb_first(const struct rb_root *);
+extern struct rb_node *rb_last(const struct rb_root *);
+
+/* Postorder iteration - always visit the parent after its children */
+extern struct rb_node *rb_first_postorder(const struct rb_root *);
+extern struct rb_node *rb_next_postorder(const struct rb_node *);
+
+/* Fast replacement of a single node without remove/rebalance/add/rebalance */
+extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
+			    struct rb_root *root);
+
+static inline void rb_link_node(struct rb_node *node, struct rb_node *parent,
+				struct rb_node **rb_link)
+{
+	node->__rb_parent_color = (unsigned long)parent;
+	node->rb_left = node->rb_right = NULL;
+
+	*rb_link = node;
+}
+
+#define rb_entry_safe(ptr, type, member) \
+	({ typeof(ptr) ____ptr = (ptr); \
+	   ____ptr ? rb_entry(____ptr, type, member) : NULL; \
+	})
+
+
+/*
+ * Handy for checking that we are not deleting an entry that is
+ * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
+ * probably should be moved to lib/rbtree.c...
+ */
+static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
+{
+	rb_erase(n, root);
+	RB_CLEAR_NODE(n);
+}
+#endif /* __TOOLS_LINUX_PERF_RBTREE_H */
diff --git a/tools/include/linux/rbtree_augmented.h b/tools/include/linux/rbtree_augmented.h
new file mode 100644
index 0000000..43be941
--- /dev/null
+++ b/tools/include/linux/rbtree_augmented.h
@@ -0,0 +1,245 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+  (C) 2002  David Woodhouse <dwmw2@infradead.org>
+  (C) 2012  Michel Lespinasse <walken@google.com>
+
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  tools/linux/include/linux/rbtree_augmented.h
+
+  Copied from:
+  linux/include/linux/rbtree_augmented.h
+*/
+
+#ifndef _TOOLS_LINUX_RBTREE_AUGMENTED_H
+#define _TOOLS_LINUX_RBTREE_AUGMENTED_H
+
+#include <linux/compiler.h>
+#include <linux/rbtree.h>
+
+/*
+ * Please note - only struct rb_augment_callbacks and the prototypes for
+ * rb_insert_augmented() and rb_erase_augmented() are intended to be public.
+ * The rest are implementation details you are not expected to depend on.
+ *
+ * See Documentation/rbtree.txt for documentation and samples.
+ */
+
+struct rb_augment_callbacks {
+	void (*propagate)(struct rb_node *node, struct rb_node *stop);
+	void (*copy)(struct rb_node *old, struct rb_node *new);
+	void (*rotate)(struct rb_node *old, struct rb_node *new);
+};
+
+extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+/*
+ * Fixup the rbtree and update the augmented information when rebalancing.
+ *
+ * On insertion, the user must update the augmented information on the path
+ * leading to the inserted node, then call rb_link_node() as usual and
+ * rb_augment_inserted() instead of the usual rb_insert_color() call.
+ * If rb_augment_inserted() rebalances the rbtree, it will callback into
+ * a user provided function to update the augmented information on the
+ * affected subtrees.
+ */
+static inline void
+rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+		    const struct rb_augment_callbacks *augment)
+{
+	__rb_insert_augmented(node, root, augment->rotate);
+}
+
+#define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield,	\
+			     rbtype, rbaugmented, rbcompute)		\
+static inline void							\
+rbname ## _propagate(struct rb_node *rb, struct rb_node *stop)		\
+{									\
+	while (rb != stop) {						\
+		rbstruct *node = rb_entry(rb, rbstruct, rbfield);	\
+		rbtype augmented = rbcompute(node);			\
+		if (node->rbaugmented == augmented)			\
+			break;						\
+		node->rbaugmented = augmented;				\
+		rb = rb_parent(&node->rbfield);				\
+	}								\
+}									\
+static inline void							\
+rbname ## _copy(struct rb_node *rb_old, struct rb_node *rb_new)		\
+{									\
+	rbstruct *old = rb_entry(rb_old, rbstruct, rbfield);		\
+	rbstruct *new = rb_entry(rb_new, rbstruct, rbfield);		\
+	new->rbaugmented = old->rbaugmented;				\
+}									\
+static void								\
+rbname ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new)	\
+{									\
+	rbstruct *old = rb_entry(rb_old, rbstruct, rbfield);		\
+	rbstruct *new = rb_entry(rb_new, rbstruct, rbfield);		\
+	new->rbaugmented = old->rbaugmented;				\
+	old->rbaugmented = rbcompute(old);				\
+}									\
+rbstatic const struct rb_augment_callbacks rbname = {			\
+	rbname ## _propagate, rbname ## _copy, rbname ## _rotate	\
+};
+
+
+#define	RB_RED		0
+#define	RB_BLACK	1
+
+#define __rb_parent(pc)    ((struct rb_node *)(pc & ~3))
+
+#define __rb_color(pc)     ((pc) & 1)
+#define __rb_is_black(pc)  __rb_color(pc)
+#define __rb_is_red(pc)    (!__rb_color(pc))
+#define rb_color(rb)       __rb_color((rb)->__rb_parent_color)
+#define rb_is_red(rb)      __rb_is_red((rb)->__rb_parent_color)
+#define rb_is_black(rb)    __rb_is_black((rb)->__rb_parent_color)
+
+static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p)
+{
+	rb->__rb_parent_color = rb_color(rb) | (unsigned long)p;
+}
+
+static inline void rb_set_parent_color(struct rb_node *rb,
+				       struct rb_node *p, int color)
+{
+	rb->__rb_parent_color = (unsigned long)p | color;
+}
+
+static inline void
+__rb_change_child(struct rb_node *old, struct rb_node *new,
+		  struct rb_node *parent, struct rb_root *root)
+{
+	if (parent) {
+		if (parent->rb_left == old)
+			parent->rb_left = new;
+		else
+			parent->rb_right = new;
+	} else
+		root->rb_node = new;
+}
+
+extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+
+static __always_inline struct rb_node *
+__rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+		     const struct rb_augment_callbacks *augment)
+{
+	struct rb_node *child = node->rb_right, *tmp = node->rb_left;
+	struct rb_node *parent, *rebalance;
+	unsigned long pc;
+
+	if (!tmp) {
+		/*
+		 * Case 1: node to erase has no more than 1 child (easy!)
+		 *
+		 * Note that if there is one child it must be red due to 5)
+		 * and node must be black due to 4). We adjust colors locally
+		 * so as to bypass __rb_erase_color() later on.
+		 */
+		pc = node->__rb_parent_color;
+		parent = __rb_parent(pc);
+		__rb_change_child(node, child, parent, root);
+		if (child) {
+			child->__rb_parent_color = pc;
+			rebalance = NULL;
+		} else
+			rebalance = __rb_is_black(pc) ? parent : NULL;
+		tmp = parent;
+	} else if (!child) {
+		/* Still case 1, but this time the child is node->rb_left */
+		tmp->__rb_parent_color = pc = node->__rb_parent_color;
+		parent = __rb_parent(pc);
+		__rb_change_child(node, tmp, parent, root);
+		rebalance = NULL;
+		tmp = parent;
+	} else {
+		struct rb_node *successor = child, *child2;
+		tmp = child->rb_left;
+		if (!tmp) {
+			/*
+			 * Case 2: node's successor is its right child
+			 *
+			 *    (n)          (s)
+			 *    / \          / \
+			 *  (x) (s)  ->  (x) (c)
+			 *        \
+			 *        (c)
+			 */
+			parent = successor;
+			child2 = successor->rb_right;
+			augment->copy(node, successor);
+		} else {
+			/*
+			 * Case 3: node's successor is leftmost under
+			 * node's right child subtree
+			 *
+			 *    (n)          (s)
+			 *    / \          / \
+			 *  (x) (y)  ->  (x) (y)
+			 *      /            /
+			 *    (p)          (p)
+			 *    /            /
+			 *  (s)          (c)
+			 *    \
+			 *    (c)
+			 */
+			do {
+				parent = successor;
+				successor = tmp;
+				tmp = tmp->rb_left;
+			} while (tmp);
+			parent->rb_left = child2 = successor->rb_right;
+			successor->rb_right = child;
+			rb_set_parent(child, successor);
+			augment->copy(node, successor);
+			augment->propagate(parent, successor);
+		}
+
+		successor->rb_left = tmp = node->rb_left;
+		rb_set_parent(tmp, successor);
+
+		pc = node->__rb_parent_color;
+		tmp = __rb_parent(pc);
+		__rb_change_child(node, successor, tmp, root);
+		if (child2) {
+			successor->__rb_parent_color = pc;
+			rb_set_parent_color(child2, parent, RB_BLACK);
+			rebalance = NULL;
+		} else {
+			unsigned long pc2 = successor->__rb_parent_color;
+			successor->__rb_parent_color = pc;
+			rebalance = __rb_is_black(pc2) ? parent : NULL;
+		}
+		tmp = successor;
+	}
+
+	augment->propagate(tmp, NULL);
+	return rebalance;
+}
+
+static __always_inline void
+rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+		   const struct rb_augment_callbacks *augment)
+{
+	struct rb_node *rebalance = __rb_erase_augmented(node, root, augment);
+	if (rebalance)
+		__rb_erase_color(rebalance, root, augment->rotate);
+}
+
+#endif	/* _TOOLS_LINUX_RBTREE_AUGMENTED_H */
diff --git a/tools/lib/api/Makefile b/tools/lib/api/Makefile
index 8bd9606..fe1b02c 100644
--- a/tools/lib/api/Makefile
+++ b/tools/lib/api/Makefile
@@ -36,7 +36,7 @@
 
 clean:
 	$(call QUIET_CLEAN, libapi) $(RM) $(LIBFILE); \
-	find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o | xargs $(RM)
+	find $(if $(OUTPUT),$(OUTPUT),.) -name \*.o -or -name \*.o.cmd -or -name \*.o.d | xargs $(RM)
 
 FORCE:
 
diff --git a/tools/lib/hweight.c b/tools/lib/hweight.c
new file mode 100644
index 0000000..0b859b8
--- /dev/null
+++ b/tools/lib/hweight.c
@@ -0,0 +1,62 @@
+#include <linux/bitops.h>
+#include <asm/types.h>
+
+/**
+ * hweightN - returns the hamming weight of a N-bit word
+ * @x: the word to weigh
+ *
+ * The Hamming Weight of a number is the total number of bits set in it.
+ */
+
+unsigned int __sw_hweight32(unsigned int w)
+{
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
+	w -= (w >> 1) & 0x55555555;
+	w =  (w & 0x33333333) + ((w >> 2) & 0x33333333);
+	w =  (w + (w >> 4)) & 0x0f0f0f0f;
+	return (w * 0x01010101) >> 24;
+#else
+	unsigned int res = w - ((w >> 1) & 0x55555555);
+	res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
+	res = (res + (res >> 4)) & 0x0F0F0F0F;
+	res = res + (res >> 8);
+	return (res + (res >> 16)) & 0x000000FF;
+#endif
+}
+
+unsigned int __sw_hweight16(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x5555);
+	res = (res & 0x3333) + ((res >> 2) & 0x3333);
+	res = (res + (res >> 4)) & 0x0F0F;
+	return (res + (res >> 8)) & 0x00FF;
+}
+
+unsigned int __sw_hweight8(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x55);
+	res = (res & 0x33) + ((res >> 2) & 0x33);
+	return (res + (res >> 4)) & 0x0F;
+}
+
+unsigned long __sw_hweight64(__u64 w)
+{
+#if BITS_PER_LONG == 32
+	return __sw_hweight32((unsigned int)(w >> 32)) +
+	       __sw_hweight32((unsigned int)w);
+#elif BITS_PER_LONG == 64
+#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
+	w -= (w >> 1) & 0x5555555555555555ul;
+	w =  (w & 0x3333333333333333ul) + ((w >> 2) & 0x3333333333333333ul);
+	w =  (w + (w >> 4)) & 0x0f0f0f0f0f0f0f0ful;
+	return (w * 0x0101010101010101ul) >> 56;
+#else
+	__u64 res = w - ((w >> 1) & 0x5555555555555555ul);
+	res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
+	res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
+	res = res + (res >> 8);
+	res = res + (res >> 16);
+	return (res + (res >> 32)) & 0x00000000000000FFul;
+#endif
+#endif
+}
diff --git a/tools/lib/rbtree.c b/tools/lib/rbtree.c
new file mode 100644
index 0000000..17c2b59
--- /dev/null
+++ b/tools/lib/rbtree.c
@@ -0,0 +1,548 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+  (C) 2002  David Woodhouse <dwmw2@infradead.org>
+  (C) 2012  Michel Lespinasse <walken@google.com>
+
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  linux/lib/rbtree.c
+*/
+
+#include <linux/rbtree_augmented.h>
+
+/*
+ * red-black trees properties:  http://en.wikipedia.org/wiki/Rbtree
+ *
+ *  1) A node is either red or black
+ *  2) The root is black
+ *  3) All leaves (NULL) are black
+ *  4) Both children of every red node are black
+ *  5) Every simple path from root to leaves contains the same number
+ *     of black nodes.
+ *
+ *  4 and 5 give the O(log n) guarantee, since 4 implies you cannot have two
+ *  consecutive red nodes in a path and every red node is therefore followed by
+ *  a black. So if B is the number of black nodes on every simple path (as per
+ *  5), then the longest possible path due to 4 is 2B.
+ *
+ *  We shall indicate color with case, where black nodes are uppercase and red
+ *  nodes will be lowercase. Unknown color nodes shall be drawn as red within
+ *  parentheses and have some accompanying text comment.
+ */
+
+static inline void rb_set_black(struct rb_node *rb)
+{
+	rb->__rb_parent_color |= RB_BLACK;
+}
+
+static inline struct rb_node *rb_red_parent(struct rb_node *red)
+{
+	return (struct rb_node *)red->__rb_parent_color;
+}
+
+/*
+ * Helper function for rotations:
+ * - old's parent and color get assigned to new
+ * - old gets assigned new as a parent and 'color' as a color.
+ */
+static inline void
+__rb_rotate_set_parents(struct rb_node *old, struct rb_node *new,
+			struct rb_root *root, int color)
+{
+	struct rb_node *parent = rb_parent(old);
+	new->__rb_parent_color = old->__rb_parent_color;
+	rb_set_parent_color(old, new, color);
+	__rb_change_child(old, new, parent, root);
+}
+
+static __always_inline void
+__rb_insert(struct rb_node *node, struct rb_root *root,
+	    void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	struct rb_node *parent = rb_red_parent(node), *gparent, *tmp;
+
+	while (true) {
+		/*
+		 * Loop invariant: node is red
+		 *
+		 * If there is a black parent, we are done.
+		 * Otherwise, take some corrective action as we don't
+		 * want a red root or two consecutive red nodes.
+		 */
+		if (!parent) {
+			rb_set_parent_color(node, NULL, RB_BLACK);
+			break;
+		} else if (rb_is_black(parent))
+			break;
+
+		gparent = rb_red_parent(parent);
+
+		tmp = gparent->rb_right;
+		if (parent != tmp) {	/* parent == gparent->rb_left */
+			if (tmp && rb_is_red(tmp)) {
+				/*
+				 * Case 1 - color flips
+				 *
+				 *       G            g
+				 *      / \          / \
+				 *     p   u  -->   P   U
+				 *    /            /
+				 *   n            n
+				 *
+				 * However, since g's parent might be red, and
+				 * 4) does not allow this, we need to recurse
+				 * at g.
+				 */
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+				rb_set_parent_color(parent, gparent, RB_BLACK);
+				node = gparent;
+				parent = rb_parent(node);
+				rb_set_parent_color(node, parent, RB_RED);
+				continue;
+			}
+
+			tmp = parent->rb_right;
+			if (node == tmp) {
+				/*
+				 * Case 2 - left rotate at parent
+				 *
+				 *      G             G
+				 *     / \           / \
+				 *    p   U  -->    n   U
+				 *     \           /
+				 *      n         p
+				 *
+				 * This still leaves us in violation of 4), the
+				 * continuation into Case 3 will fix that.
+				 */
+				parent->rb_right = tmp = node->rb_left;
+				node->rb_left = parent;
+				if (tmp)
+					rb_set_parent_color(tmp, parent,
+							    RB_BLACK);
+				rb_set_parent_color(parent, node, RB_RED);
+				augment_rotate(parent, node);
+				parent = node;
+				tmp = node->rb_right;
+			}
+
+			/*
+			 * Case 3 - right rotate at gparent
+			 *
+			 *        G           P
+			 *       / \         / \
+			 *      p   U  -->  n   g
+			 *     /                 \
+			 *    n                   U
+			 */
+			gparent->rb_left = tmp;  /* == parent->rb_right */
+			parent->rb_right = gparent;
+			if (tmp)
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
+			augment_rotate(gparent, parent);
+			break;
+		} else {
+			tmp = gparent->rb_left;
+			if (tmp && rb_is_red(tmp)) {
+				/* Case 1 - color flips */
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+				rb_set_parent_color(parent, gparent, RB_BLACK);
+				node = gparent;
+				parent = rb_parent(node);
+				rb_set_parent_color(node, parent, RB_RED);
+				continue;
+			}
+
+			tmp = parent->rb_left;
+			if (node == tmp) {
+				/* Case 2 - right rotate at parent */
+				parent->rb_left = tmp = node->rb_right;
+				node->rb_right = parent;
+				if (tmp)
+					rb_set_parent_color(tmp, parent,
+							    RB_BLACK);
+				rb_set_parent_color(parent, node, RB_RED);
+				augment_rotate(parent, node);
+				parent = node;
+				tmp = node->rb_left;
+			}
+
+			/* Case 3 - left rotate at gparent */
+			gparent->rb_right = tmp;  /* == parent->rb_left */
+			parent->rb_left = gparent;
+			if (tmp)
+				rb_set_parent_color(tmp, gparent, RB_BLACK);
+			__rb_rotate_set_parents(gparent, parent, root, RB_RED);
+			augment_rotate(gparent, parent);
+			break;
+		}
+	}
+}
+
+/*
+ * Inline version for rb_erase() use - we want to be able to inline
+ * and eliminate the dummy_rotate callback there
+ */
+static __always_inline void
+____rb_erase_color(struct rb_node *parent, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	struct rb_node *node = NULL, *sibling, *tmp1, *tmp2;
+
+	while (true) {
+		/*
+		 * Loop invariants:
+		 * - node is black (or NULL on first iteration)
+		 * - node is not the root (parent is not NULL)
+		 * - All leaf paths going through parent and node have a
+		 *   black node count that is 1 lower than other leaf paths.
+		 */
+		sibling = parent->rb_right;
+		if (node != sibling) {	/* node == parent->rb_left */
+			if (rb_is_red(sibling)) {
+				/*
+				 * Case 1 - left rotate at parent
+				 *
+				 *     P               S
+				 *    / \             / \
+				 *   N   s    -->    p   Sr
+				 *      / \         / \
+				 *     Sl  Sr      N   Sl
+				 */
+				parent->rb_right = tmp1 = sibling->rb_left;
+				sibling->rb_left = parent;
+				rb_set_parent_color(tmp1, parent, RB_BLACK);
+				__rb_rotate_set_parents(parent, sibling, root,
+							RB_RED);
+				augment_rotate(parent, sibling);
+				sibling = tmp1;
+			}
+			tmp1 = sibling->rb_right;
+			if (!tmp1 || rb_is_black(tmp1)) {
+				tmp2 = sibling->rb_left;
+				if (!tmp2 || rb_is_black(tmp2)) {
+					/*
+					 * Case 2 - sibling color flip
+					 * (p could be either color here)
+					 *
+					 *    (p)           (p)
+					 *    / \           / \
+					 *   N   S    -->  N   s
+					 *      / \           / \
+					 *     Sl  Sr        Sl  Sr
+					 *
+					 * This leaves us violating 5) which
+					 * can be fixed by flipping p to black
+					 * if it was red, or by recursing at p.
+					 * p is red when coming from Case 1.
+					 */
+					rb_set_parent_color(sibling, parent,
+							    RB_RED);
+					if (rb_is_red(parent))
+						rb_set_black(parent);
+					else {
+						node = parent;
+						parent = rb_parent(node);
+						if (parent)
+							continue;
+					}
+					break;
+				}
+				/*
+				 * Case 3 - right rotate at sibling
+				 * (p could be either color here)
+				 *
+				 *   (p)           (p)
+				 *   / \           / \
+				 *  N   S    -->  N   Sl
+				 *     / \             \
+				 *    sl  Sr            s
+				 *                       \
+				 *                        Sr
+				 */
+				sibling->rb_left = tmp1 = tmp2->rb_right;
+				tmp2->rb_right = sibling;
+				parent->rb_right = tmp2;
+				if (tmp1)
+					rb_set_parent_color(tmp1, sibling,
+							    RB_BLACK);
+				augment_rotate(sibling, tmp2);
+				tmp1 = sibling;
+				sibling = tmp2;
+			}
+			/*
+			 * Case 4 - left rotate at parent + color flips
+			 * (p and sl could be either color here.
+			 *  After rotation, p becomes black, s acquires
+			 *  p's color, and sl keeps its color)
+			 *
+			 *      (p)             (s)
+			 *      / \             / \
+			 *     N   S     -->   P   Sr
+			 *        / \         / \
+			 *      (sl) sr      N  (sl)
+			 */
+			parent->rb_right = tmp2 = sibling->rb_left;
+			sibling->rb_left = parent;
+			rb_set_parent_color(tmp1, sibling, RB_BLACK);
+			if (tmp2)
+				rb_set_parent(tmp2, parent);
+			__rb_rotate_set_parents(parent, sibling, root,
+						RB_BLACK);
+			augment_rotate(parent, sibling);
+			break;
+		} else {
+			sibling = parent->rb_left;
+			if (rb_is_red(sibling)) {
+				/* Case 1 - right rotate at parent */
+				parent->rb_left = tmp1 = sibling->rb_right;
+				sibling->rb_right = parent;
+				rb_set_parent_color(tmp1, parent, RB_BLACK);
+				__rb_rotate_set_parents(parent, sibling, root,
+							RB_RED);
+				augment_rotate(parent, sibling);
+				sibling = tmp1;
+			}
+			tmp1 = sibling->rb_left;
+			if (!tmp1 || rb_is_black(tmp1)) {
+				tmp2 = sibling->rb_right;
+				if (!tmp2 || rb_is_black(tmp2)) {
+					/* Case 2 - sibling color flip */
+					rb_set_parent_color(sibling, parent,
+							    RB_RED);
+					if (rb_is_red(parent))
+						rb_set_black(parent);
+					else {
+						node = parent;
+						parent = rb_parent(node);
+						if (parent)
+							continue;
+					}
+					break;
+				}
+				/* Case 3 - right rotate at sibling */
+				sibling->rb_right = tmp1 = tmp2->rb_left;
+				tmp2->rb_left = sibling;
+				parent->rb_left = tmp2;
+				if (tmp1)
+					rb_set_parent_color(tmp1, sibling,
+							    RB_BLACK);
+				augment_rotate(sibling, tmp2);
+				tmp1 = sibling;
+				sibling = tmp2;
+			}
+			/* Case 4 - left rotate at parent + color flips */
+			parent->rb_left = tmp2 = sibling->rb_right;
+			sibling->rb_right = parent;
+			rb_set_parent_color(tmp1, sibling, RB_BLACK);
+			if (tmp2)
+				rb_set_parent(tmp2, parent);
+			__rb_rotate_set_parents(parent, sibling, root,
+						RB_BLACK);
+			augment_rotate(parent, sibling);
+			break;
+		}
+	}
+}
+
+/* Non-inline version for rb_erase_augmented() use */
+void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	____rb_erase_color(parent, root, augment_rotate);
+}
+
+/*
+ * Non-augmented rbtree manipulation functions.
+ *
+ * We use dummy augmented callbacks here, and have the compiler optimize them
+ * out of the rb_insert_color() and rb_erase() function definitions.
+ */
+
+static inline void dummy_propagate(struct rb_node *node, struct rb_node *stop) {}
+static inline void dummy_copy(struct rb_node *old, struct rb_node *new) {}
+static inline void dummy_rotate(struct rb_node *old, struct rb_node *new) {}
+
+static const struct rb_augment_callbacks dummy_callbacks = {
+	dummy_propagate, dummy_copy, dummy_rotate
+};
+
+void rb_insert_color(struct rb_node *node, struct rb_root *root)
+{
+	__rb_insert(node, root, dummy_rotate);
+}
+
+void rb_erase(struct rb_node *node, struct rb_root *root)
+{
+	struct rb_node *rebalance;
+	rebalance = __rb_erase_augmented(node, root, &dummy_callbacks);
+	if (rebalance)
+		____rb_erase_color(rebalance, root, dummy_rotate);
+}
+
+/*
+ * Augmented rbtree manipulation functions.
+ *
+ * This instantiates the same __always_inline functions as in the non-augmented
+ * case, but this time with user-defined callbacks.
+ */
+
+void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
+{
+	__rb_insert(node, root, augment_rotate);
+}
+
+/*
+ * This function returns the first node (in sort order) of the tree.
+ */
+struct rb_node *rb_first(const struct rb_root *root)
+{
+	struct rb_node	*n;
+
+	n = root->rb_node;
+	if (!n)
+		return NULL;
+	while (n->rb_left)
+		n = n->rb_left;
+	return n;
+}
+
+struct rb_node *rb_last(const struct rb_root *root)
+{
+	struct rb_node	*n;
+
+	n = root->rb_node;
+	if (!n)
+		return NULL;
+	while (n->rb_right)
+		n = n->rb_right;
+	return n;
+}
+
+struct rb_node *rb_next(const struct rb_node *node)
+{
+	struct rb_node *parent;
+
+	if (RB_EMPTY_NODE(node))
+		return NULL;
+
+	/*
+	 * If we have a right-hand child, go down and then left as far
+	 * as we can.
+	 */
+	if (node->rb_right) {
+		node = node->rb_right;
+		while (node->rb_left)
+			node=node->rb_left;
+		return (struct rb_node *)node;
+	}
+
+	/*
+	 * No right-hand children. Everything down and left is smaller than us,
+	 * so any 'next' node must be in the general direction of our parent.
+	 * Go up the tree; any time the ancestor is a right-hand child of its
+	 * parent, keep going up. First time it's a left-hand child of its
+	 * parent, said parent is our 'next' node.
+	 */
+	while ((parent = rb_parent(node)) && node == parent->rb_right)
+		node = parent;
+
+	return parent;
+}
+
+struct rb_node *rb_prev(const struct rb_node *node)
+{
+	struct rb_node *parent;
+
+	if (RB_EMPTY_NODE(node))
+		return NULL;
+
+	/*
+	 * If we have a left-hand child, go down and then right as far
+	 * as we can.
+	 */
+	if (node->rb_left) {
+		node = node->rb_left;
+		while (node->rb_right)
+			node=node->rb_right;
+		return (struct rb_node *)node;
+	}
+
+	/*
+	 * No left-hand children. Go up till we find an ancestor which
+	 * is a right-hand child of its parent.
+	 */
+	while ((parent = rb_parent(node)) && node == parent->rb_left)
+		node = parent;
+
+	return parent;
+}
+
+void rb_replace_node(struct rb_node *victim, struct rb_node *new,
+		     struct rb_root *root)
+{
+	struct rb_node *parent = rb_parent(victim);
+
+	/* Set the surrounding nodes to point to the replacement */
+	__rb_change_child(victim, new, parent, root);
+	if (victim->rb_left)
+		rb_set_parent(victim->rb_left, new);
+	if (victim->rb_right)
+		rb_set_parent(victim->rb_right, new);
+
+	/* Copy the pointers/colour from the victim to the replacement */
+	*new = *victim;
+}
+
+static struct rb_node *rb_left_deepest_node(const struct rb_node *node)
+{
+	for (;;) {
+		if (node->rb_left)
+			node = node->rb_left;
+		else if (node->rb_right)
+			node = node->rb_right;
+		else
+			return (struct rb_node *)node;
+	}
+}
+
+struct rb_node *rb_next_postorder(const struct rb_node *node)
+{
+	const struct rb_node *parent;
+	if (!node)
+		return NULL;
+	parent = rb_parent(node);
+
+	/* If we're sitting on node, we've already seen our children */
+	if (parent && node == parent->rb_left && parent->rb_right) {
+		/* If we are the parent's left node, go to the parent's right
+		 * node then all the way down to the left */
+		return rb_left_deepest_node(parent->rb_right);
+	} else
+		/* Otherwise we are the parent's right node, and the parent
+		 * should be next */
+		return (struct rb_node *)parent;
+}
+
+struct rb_node *rb_first_postorder(const struct rb_root *root)
+{
+	if (!root->rb_node)
+		return NULL;
+
+	return rb_left_deepest_node(root->rb_node);
+}
diff --git a/tools/lib/traceevent/Makefile b/tools/lib/traceevent/Makefile
index 6daaff6..7851df1 100644
--- a/tools/lib/traceevent/Makefile
+++ b/tools/lib/traceevent/Makefile
@@ -268,7 +268,7 @@
 
 clean:
 	$(call QUIET_CLEAN, libtraceevent) \
-		$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d \
+		$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d .*.cmd \
 		$(RM) TRACEEVENT-CFLAGS tags TAGS
 
 PHONY += force plugins
diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index fe50a1b..d01a0aa 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -18,6 +18,8 @@
 tools/arch/x86/include/asm/rmwcc.h
 tools/lib/traceevent
 tools/lib/api
+tools/lib/hweight.c
+tools/lib/rbtree.c
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
 tools/lib/util/find_next_bit.c
@@ -44,6 +46,8 @@
 tools/include/linux/list.h
 tools/include/linux/log2.h
 tools/include/linux/poison.h
+tools/include/linux/rbtree.h
+tools/include/linux/rbtree_augmented.h
 tools/include/linux/types.h
 include/asm-generic/bitops/arch_hweight.h
 include/asm-generic/bitops/const_hweight.h
@@ -51,12 +55,9 @@
 include/asm-generic/bitops/__fls.h
 include/asm-generic/bitops/fls.h
 include/linux/perf_event.h
-include/linux/rbtree.h
 include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
-lib/hweight.c
-lib/rbtree.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
 arch/*/include/uapi/asm/unistd*.h
@@ -65,7 +66,6 @@
 arch/*/lib/memset*.S
 include/linux/poison.h
 include/linux/hw_breakpoint.h
-include/linux/rbtree_augmented.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/const.h
 include/uapi/linux/swab.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 7a4b549..bba3463 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -109,9 +109,22 @@
 	$(Q)$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
 	$(Q)touch $(OUTPUT)PERF-VERSION-FILE
 
-CC = $(CROSS_COMPILE)gcc
-LD ?= $(CROSS_COMPILE)ld
-AR = $(CROSS_COMPILE)ar
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+# Allow setting CC and AR and LD, or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
+$(call allow-override,LD,$(CROSS_COMPILE)ld)
+
 PKG_CONFIG = $(CROSS_COMPILE)pkg-config
 
 RM      = rm -f
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index de165a1..20b56eb 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -521,6 +521,15 @@
 		goto out_child;
 	}
 
+	/*
+	 * Normally perf_session__new would do this, but it doesn't have the
+	 * evlist.
+	 */
+	if (rec->tool.ordered_events && !perf_evlist__sample_id_all(rec->evlist)) {
+		pr_warning("WARNING: No sample_id_all support, falling back to unordered processing\n");
+		rec->tool.ordered_events = false;
+	}
+
 	if (!rec->evlist->nr_groups)
 		perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
 
@@ -965,9 +974,11 @@
 	.tool = {
 		.sample		= process_sample_event,
 		.fork		= perf_event__process_fork,
+		.exit		= perf_event__process_exit,
 		.comm		= perf_event__process_comm,
 		.mmap		= perf_event__process_mmap,
 		.mmap2		= perf_event__process_mmap2,
+		.ordered_events	= true,
 	},
 };
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 37e301a..d99d850 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -343,7 +343,7 @@
 	return 0;
 }
 
-static void read_counters(bool close)
+static void read_counters(bool close_counters)
 {
 	struct perf_evsel *counter;
 
@@ -354,7 +354,7 @@
 		if (process_counter(counter))
 			pr_warning("failed to process counter %s\n", counter->name);
 
-		if (close) {
+		if (close_counters) {
 			perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
 					     thread_map__nr(evsel_list->threads));
 		}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ecf3197..6135cc0 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -601,8 +601,8 @@
 
 static void display_setup_sig(void)
 {
-	signal(SIGSEGV, display_sig);
-	signal(SIGFPE,  display_sig);
+	signal(SIGSEGV, sighandler_dump_stack);
+	signal(SIGFPE, sighandler_dump_stack);
 	signal(SIGINT,  display_sig);
 	signal(SIGQUIT, display_sig);
 	signal(SIGTERM, display_sig);
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 094ddae..d31fac1 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -638,7 +638,7 @@
 prefix ?= $(HOME)
 endif
 bindir_relative = bin
-bindir = $(prefix)/$(bindir_relative)
+bindir = $(abspath $(prefix)/$(bindir_relative))
 mandir = share/man
 infodir = share/info
 perfexecdir = libexec/perf-core
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 7629bef..fa67613 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -48,7 +48,7 @@
 
 static bool hist_browser__has_filter(struct hist_browser *hb)
 {
-	return hists__has_filter(hb->hists) || hb->min_pcnt;
+	return hists__has_filter(hb->hists) || hb->min_pcnt || symbol_conf.has_filter;
 }
 
 static int hist_browser__get_folding(struct hist_browser *browser)
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 586a59d..d2d318c 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -139,10 +139,10 @@
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
-$(OUTPUT)util/rbtree.o: ../../lib/rbtree.c FORCE
+$(OUTPUT)util/rbtree.o: ../lib/rbtree.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
 
-$(OUTPUT)util/hweight.o: ../../lib/hweight.c FORCE
+$(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 7e7405c..83d9dd9 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -53,11 +53,6 @@
 {
 	struct perf_event_mmap_page *pc = userpg;
 
-#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
-	pr_err("Cannot use AUX area tracing mmaps\n");
-	return -1;
-#endif
-
 	WARN_ONCE(mm->base, "Uninitialized auxtrace_mmap\n");
 
 	mm->userpg = userpg;
@@ -73,6 +68,11 @@
 		return 0;
 	}
 
+#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+	pr_err("Cannot use AUX area tracing mmaps\n");
+	return -1;
+#endif
+
 	pc->aux_offset = mp->offset;
 	pc->aux_size = mp->len;
 
diff --git a/tools/perf/util/include/linux/rbtree.h b/tools/perf/util/include/linux/rbtree.h
deleted file mode 100644
index f06d89f..0000000
--- a/tools/perf/util/include/linux/rbtree.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef __TOOLS_LINUX_PERF_RBTREE_H
-#define __TOOLS_LINUX_PERF_RBTREE_H
-#include <stdbool.h>
-#include "../../../../include/linux/rbtree.h"
-
-/*
- * Handy for checking that we are not deleting an entry that is
- * already in a list, found in block/{blk-throttle,cfq-iosched}.c,
- * probably should be moved to lib/rbtree.c...
- */
-static inline void rb_erase_init(struct rb_node *n, struct rb_root *root)
-{
-	rb_erase(n, root);
-	RB_CLEAR_NODE(n);
-}
-#endif /* __TOOLS_LINUX_PERF_RBTREE_H */
diff --git a/tools/perf/util/include/linux/rbtree_augmented.h b/tools/perf/util/include/linux/rbtree_augmented.h
deleted file mode 100644
index 9d6fcdf..0000000
--- a/tools/perf/util/include/linux/rbtree_augmented.h
+++ /dev/null
@@ -1,2 +0,0 @@
-#include <stdbool.h>
-#include "../../../../include/linux/rbtree_augmented.h"
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 7ff6827..f1a4c83 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1387,6 +1387,24 @@
 							event->fork.ptid);
 	int err = 0;
 
+	if (dump_trace)
+		perf_event__fprintf_task(event, stdout);
+
+	/*
+	 * There may be an existing thread that is not actually the parent,
+	 * either because we are processing events out of order, or because the
+	 * (fork) event that would have removed the thread was lost. Assume the
+	 * latter case and continue on as best we can.
+	 */
+	if (parent->pid_ != (pid_t)event->fork.ppid) {
+		dump_printf("removing erroneous parent thread %d/%d\n",
+			    parent->pid_, parent->tid);
+		machine__remove_thread(machine, parent);
+		thread__put(parent);
+		parent = machine__findnew_thread(machine, event->fork.ppid,
+						 event->fork.ptid);
+	}
+
 	/* if a thread currently exists for the thread id remove it */
 	if (thread != NULL) {
 		machine__remove_thread(machine, thread);
@@ -1395,8 +1413,6 @@
 
 	thread = machine__findnew_thread(machine, event->fork.pid,
 					 event->fork.tid);
-	if (dump_trace)
-		perf_event__fprintf_task(event, stdout);
 
 	if (thread == NULL || parent == NULL ||
 	    thread__fork(thread, parent, sample->time) < 0) {
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index e23ded4..0766d98 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,7 +10,7 @@
 util/evlist.c
 util/evsel.c
 util/cpumap.c
-../../lib/hweight.c
+../lib/hweight.c
 util/thread_map.c
 util/util.c
 util/xyarray.c
@@ -19,5 +19,5 @@
 util/stat.c
 util/strlist.c
 util/trace-event.c
-../../lib/rbtree.c
+../lib/rbtree.c
 util/string.c
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 53e8bb7..2a5d8d7 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -85,7 +85,7 @@
 	else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
 		update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
 	else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
-		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+		update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count[0]);
 	else if (perf_stat_evsel__is(counter, TRANSACTION_START))
 		update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
 	else if (perf_stat_evsel__is(counter, ELISION_START))
@@ -398,20 +398,18 @@
 				" #   %5.2f%% aborted cycles         ",
 				100.0 * ((total2-avg) / total));
 	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
-		   avg > 0 &&
 		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
-		if (total)
+		if (avg)
 			ratio = total / avg;
 
 		fprintf(out, " # %8.0f cycles / transaction   ", ratio);
 	} else if (perf_stat_evsel__is(evsel, ELISION_START) &&
-		   avg > 0 &&
 		   runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
 		total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
-		if (total)
+		if (avg)
 			ratio = total / avg;
 
 		fprintf(out, " # %8.0f cycles / elision       ", ratio);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 48b588c..60f1141 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1911,6 +1911,8 @@
 		pr_err("problems parsing %s list\n", list_name);
 		return -1;
 	}
+
+	symbol_conf.has_filter = true;
 	return 0;
 }
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index bef47ead..b98ce51 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -105,7 +105,8 @@
 			demangle_kernel,
 			filter_relative,
 			show_hist_headers,
-			branch_callstack;
+			branch_callstack,
+			has_filter;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 28c4b74..0a9ae80 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -191,6 +191,12 @@
 	if (thread->pid_ == parent->pid_)
 		return 0;
 
+	if (thread->mg == parent->mg) {
+		pr_debug("broken map groups on thread %d/%d parent %d/%d\n",
+			 thread->pid_, thread->tid, parent->pid_, parent->tid);
+		return 0;
+	}
+
 	/* But this one is new process, copy maps. */
 	for (i = 0; i < MAP__NR_TYPES; ++i)
 		if (map_groups__clone(thread->mg, parent->mg, i) < 0)
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index da7646d..292ae2c 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -136,8 +136,7 @@
 		if (grow) {
 			struct thread_map *tmp;
 
-			tmp = realloc(threads, (sizeof(*threads) +
-						max_threads * sizeof(pid_t)));
+			tmp = thread_map__realloc(threads, max_threads);
 			if (tmp == NULL)
 				goto out_free_namelist;
 
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 4b89118..44d440d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -236,18 +236,16 @@
 	const char *file_name;
 	struct dso *dso;
 
-	pthread_rwlock_wrlock(&machine->dsos.lock);
 	dso = __dsos__find(&machine->dsos, vdso_file->dso_name, true);
 	if (dso)
-		goto out_unlock;
+		goto out;
 
 	file_name = vdso__get_compat_file(vdso_file);
 	if (!file_name)
-		goto out_unlock;
+		goto out;
 
 	dso = __machine__addnew_vdso(machine, vdso_file->dso_name, file_name);
-out_unlock:
-	pthread_rwlock_unlock(&machine->dsos.lock);
+out:
 	return dso;
 }
 
diff --git a/tools/testing/nvdimm/Kbuild b/tools/testing/nvdimm/Kbuild
index 8e9b645..f56914c 100644
--- a/tools/testing/nvdimm/Kbuild
+++ b/tools/testing/nvdimm/Kbuild
@@ -1,3 +1,6 @@
+ldflags-y += --wrap=ioremap_wt
+ldflags-y += --wrap=ioremap_wc
+ldflags-y += --wrap=devm_ioremap_nocache
 ldflags-y += --wrap=ioremap_cache
 ldflags-y += --wrap=ioremap_nocache
 ldflags-y += --wrap=iounmap
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index c85a6f6..64bfaa5 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -65,6 +65,21 @@
 	return fallback_fn(offset, size);
 }
 
+void __iomem *__wrap_devm_ioremap_nocache(struct device *dev,
+		resource_size_t offset, unsigned long size)
+{
+	struct nfit_test_resource *nfit_res;
+
+	rcu_read_lock();
+	nfit_res = get_nfit_res(offset);
+	rcu_read_unlock();
+	if (nfit_res)
+		return (void __iomem *) nfit_res->buf + offset
+			- nfit_res->res->start;
+	return devm_ioremap_nocache(dev, offset, size);
+}
+EXPORT_SYMBOL(__wrap_devm_ioremap_nocache);
+
 void __iomem *__wrap_ioremap_cache(resource_size_t offset, unsigned long size)
 {
 	return __nfit_test_ioremap(offset, size, ioremap_cache);
@@ -77,6 +92,18 @@
 }
 EXPORT_SYMBOL(__wrap_ioremap_nocache);
 
+void __iomem *__wrap_ioremap_wt(resource_size_t offset, unsigned long size)
+{
+	return __nfit_test_ioremap(offset, size, ioremap_wt);
+}
+EXPORT_SYMBOL(__wrap_ioremap_wt);
+
+void __iomem *__wrap_ioremap_wc(resource_size_t offset, unsigned long size)
+{
+	return __nfit_test_ioremap(offset, size, ioremap_wc);
+}
+EXPORT_SYMBOL(__wrap_ioremap_wc);
+
 void __wrap_iounmap(volatile void __iomem *addr)
 {
 	struct nfit_test_resource *nfit_res;
diff --git a/tools/testing/nvdimm/test/nfit.c b/tools/testing/nvdimm/test/nfit.c
index 4b69b83..d0bdae4 100644
--- a/tools/testing/nvdimm/test/nfit.c
+++ b/tools/testing/nvdimm/test/nfit.c
@@ -128,6 +128,8 @@
 	int num_pm;
 	void **dimm;
 	dma_addr_t *dimm_dma;
+	void **flush;
+	dma_addr_t *flush_dma;
 	void **label;
 	dma_addr_t *label_dma;
 	void **spa_set;
@@ -155,7 +157,7 @@
 	int i, rc;
 
 	if (!nfit_mem || !test_bit(cmd, &nfit_mem->dsm_mask))
-		return -ENXIO;
+		return -ENOTTY;
 
 	/* lookup label space for the given dimm */
 	for (i = 0; i < ARRAY_SIZE(handle); i++)
@@ -331,7 +333,8 @@
 			+ sizeof(struct acpi_nfit_system_address) * NUM_SPA
 			+ sizeof(struct acpi_nfit_memory_map) * NUM_MEM
 			+ sizeof(struct acpi_nfit_control_region) * NUM_DCR
-			+ sizeof(struct acpi_nfit_data_region) * NUM_BDW;
+			+ sizeof(struct acpi_nfit_data_region) * NUM_BDW
+			+ sizeof(struct acpi_nfit_flush_address) * NUM_DCR;
 	int i;
 
 	t->nfit_buf = test_alloc(t, nfit_size, &t->nfit_dma);
@@ -356,6 +359,10 @@
 		if (!t->label[i])
 			return -ENOMEM;
 		sprintf(t->label[i], "label%d", i);
+
+		t->flush[i] = test_alloc(t, 8, &t->flush_dma[i]);
+		if (!t->flush[i])
+			return -ENOMEM;
 	}
 
 	for (i = 0; i < NUM_DCR; i++) {
@@ -408,6 +415,7 @@
 	struct acpi_nfit_system_address *spa;
 	struct acpi_nfit_control_region *dcr;
 	struct acpi_nfit_data_region *bdw;
+	struct acpi_nfit_flush_address *flush;
 	unsigned int offset;
 
 	nfit_test_init_header(nfit_buf, size);
@@ -831,6 +839,39 @@
 	bdw->capacity = DIMM_SIZE;
 	bdw->start_address = 0;
 
+	offset = offset + sizeof(struct acpi_nfit_data_region) * 4;
+	/* flush0 (dimm0) */
+	flush = nfit_buf + offset;
+	flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS;
+	flush->header.length = sizeof(struct acpi_nfit_flush_address);
+	flush->device_handle = handle[0];
+	flush->hint_count = 1;
+	flush->hint_address[0] = t->flush_dma[0];
+
+	/* flush1 (dimm1) */
+	flush = nfit_buf + offset + sizeof(struct acpi_nfit_flush_address) * 1;
+	flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS;
+	flush->header.length = sizeof(struct acpi_nfit_flush_address);
+	flush->device_handle = handle[1];
+	flush->hint_count = 1;
+	flush->hint_address[0] = t->flush_dma[1];
+
+	/* flush2 (dimm2) */
+	flush = nfit_buf + offset + sizeof(struct acpi_nfit_flush_address) * 2;
+	flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS;
+	flush->header.length = sizeof(struct acpi_nfit_flush_address);
+	flush->device_handle = handle[2];
+	flush->hint_count = 1;
+	flush->hint_address[0] = t->flush_dma[2];
+
+	/* flush3 (dimm3) */
+	flush = nfit_buf + offset + sizeof(struct acpi_nfit_flush_address) * 3;
+	flush->header.type = ACPI_NFIT_TYPE_FLUSH_ADDRESS;
+	flush->header.length = sizeof(struct acpi_nfit_flush_address);
+	flush->device_handle = handle[3];
+	flush->hint_count = 1;
+	flush->hint_address[0] = t->flush_dma[3];
+
 	acpi_desc = &t->acpi_desc;
 	set_bit(ND_CMD_GET_CONFIG_SIZE, &acpi_desc->dimm_dsm_force_en);
 	set_bit(ND_CMD_GET_CONFIG_DATA, &acpi_desc->dimm_dsm_force_en);
@@ -933,6 +974,10 @@
 				GFP_KERNEL);
 		nfit_test->dimm_dma = devm_kcalloc(dev, num, sizeof(dma_addr_t),
 				GFP_KERNEL);
+		nfit_test->flush = devm_kcalloc(dev, num, sizeof(void *),
+				GFP_KERNEL);
+		nfit_test->flush_dma = devm_kcalloc(dev, num, sizeof(dma_addr_t),
+				GFP_KERNEL);
 		nfit_test->label = devm_kcalloc(dev, num, sizeof(void *),
 				GFP_KERNEL);
 		nfit_test->label_dma = devm_kcalloc(dev, num,
@@ -943,7 +988,8 @@
 				sizeof(dma_addr_t), GFP_KERNEL);
 		if (nfit_test->dimm && nfit_test->dimm_dma && nfit_test->label
 				&& nfit_test->label_dma && nfit_test->dcr
-				&& nfit_test->dcr_dma)
+				&& nfit_test->dcr_dma && nfit_test->flush
+				&& nfit_test->flush_dma)
 			/* pass */;
 		else
 			return -ENOMEM;
diff --git a/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c b/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c
index 7f0c756..3d7dc6a 100644
--- a/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c
+++ b/tools/testing/selftests/futex/functional/futex_requeue_pi_signal_restart.c
@@ -191,7 +191,7 @@
 		if (res > 0) {
 			atomic_set(&requeued, 1);
 			break;
-		} else if (res > 0) {
+		} else if (res < 0) {
 			error("FUTEX_CMP_REQUEUE_PI failed\n", errno);
 			ret = RET_ERROR;
 			break;
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index 620e37f..1dd087d 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -155,6 +155,8 @@
 		list_add_tail(&kvg->node, &kv->group_list);
 		kvg->vfio_group = vfio_group;
 
+		kvm_arch_start_assignment(dev->kvm);
+
 		mutex_unlock(&kv->lock);
 
 		kvm_vfio_update_coherency(dev);
@@ -190,6 +192,8 @@
 			break;
 		}
 
+		kvm_arch_end_assignment(dev->kvm);
+
 		mutex_unlock(&kv->lock);
 
 		kvm_vfio_group_put_external_user(vfio_group);
@@ -239,6 +243,7 @@
 		kvm_vfio_group_put_external_user(kvg->vfio_group);
 		list_del(&kvg->node);
 		kfree(kvg);
+		kvm_arch_end_assignment(dev->kvm);
 	}
 
 	kvm_vfio_update_coherency(dev);