Merge remote-tracking branch 'airlied/drm-next' into drm-intel-next-queued

Pull in Dave's drm-next pull request to have a clean base for 4.6.
Also, we need the various atomic state extensions Maarten recently
created.

Conflicts are just adjacent changes that all resolve to nothing in git
diff.

Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>

Documentation/devicetree/bindings/display/etnaviv/etnaviv-drm.txt

@@ -0,0 +1,54 @@
+Etnaviv DRM master device
+=========================
+
+The Etnaviv DRM master device is a virtual device needed to list all
+Vivante GPU cores that comprise the GPU subsystem.
+
+Required properties:
+- compatible: Should be one of
+    "fsl,imx-gpu-subsystem"
+    "marvell,dove-gpu-subsystem"
+- cores: Should contain a list of phandles pointing to Vivante GPU devices
+
+example:
+
+gpu-subsystem {
+	compatible = "fsl,imx-gpu-subsystem";
+	cores = <&gpu_2d>, <&gpu_3d>;
+};
+
+
+Vivante GPU core devices
+========================
+
+Required properties:
+- compatible: Should be "vivante,gc"
+  A more specific compatible is not needed, as the cores contain chip
+  identification registers at fixed locations, which provide all the
+  necessary information to the driver.
+- reg: should be register base and length as documented in the
+  datasheet
+- interrupts: Should contain the cores interrupt line
+- clocks: should contain one clock for entry in clock-names
+  see Documentation/devicetree/bindings/clock/clock-bindings.txt
+- clock-names:
+   - "bus":    AXI/register clock
+   - "core":   GPU core clock
+   - "shader": Shader clock (only required if GPU has feature PIPE_3D)
+
+Optional properties:
+- power-domains: a power domain consumer specifier according to
+  Documentation/devicetree/bindings/power/power_domain.txt
+
+example:
+
+gpu_3d: gpu@00130000 {
+	compatible = "vivante,gc";
+	reg = <0x00130000 0x4000>;
+	interrupts = <0 9 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&clks IMX6QDL_CLK_GPU3D_AXI>,
+	         <&clks IMX6QDL_CLK_GPU3D_CORE>,
+	         <&clks IMX6QDL_CLK_GPU3D_SHADER>;
+	clock-names = "bus", "core", "shader";
+	power-domains = <&gpc 1>;
+};

Documentation/devicetree/bindings/display/exynos/exynos_dp.txt

@@ -1,3 +1,20 @@
+Device-Tree bindings for Samsung Exynos Embedded DisplayPort Transmitter(eDP)
+
+DisplayPort is industry standard to accommodate the growing board adoption
+of digital display technology within the PC and CE industries.
+It consolidates the internal and external connection methods to reduce device
+complexity and cost. It also supports necessary features for important cross
+industry applications and provides performance scalability to enable the next
+generation of displays that feature higher color depths, refresh rates, and
+display resolutions.
+
+eDP (embedded display port) device is compliant with Embedded DisplayPort
+standard as follows,
+- DisplayPort standard 1.1a for Exynos5250 and Exynos5260.
+- DisplayPort standard 1.3 for Exynos5422s and Exynos5800.
+
+eDP resides between FIMD and panel or FIMD and bridge such as LVDS.
+
 The Exynos display port interface should be configured based on
 the type of panel connected to it.
 
@@ -66,8 +83,15 @@ Optional properties for dp-controller:
 		Hotplug detect GPIO.
 			Indicates which GPIO should be used for hotplug
 			detection
-	-video interfaces: Device node can contain video interface port
+Video interfaces:
-			    nodes according to [1].
+  Device node can contain video interface port nodes according to [1].
+  The following are properties specific to those nodes:
+
+  endpoint node connected to bridge or panel node:
+   - remote-endpoint: specifies the endpoint in panel or bridge node.
+		      This node is required in all kinds of exynos dp
+		      to represent the connection between dp and bridge
+		      or dp and panel.
 
 [1]: Documentation/devicetree/bindings/media/video-interfaces.txt
 
@@ -111,9 +135,18 @@ Board Specific portion:
 		};
 
 		ports {
-			port@0 {
+			port {
 				dp_out: endpoint {
-					remote-endpoint = <&bridge_in>;
+					remote-endpoint = <&dp_in>;
+				};
+			};
+		};
+
+		panel {
+			...
+			port {
+				dp_in: endpoint {
+					remote-endpoint = <&dp_out>;
 				};
 			};
 		};

Documentation/devicetree/bindings/display/msm/dsi.txt

@@ -14,17 +14,20 @@ Required properties:
 - clocks: device clocks
   See Documentation/devicetree/bindings/clocks/clock-bindings.txt for details.
 - clock-names: the following clocks are required:
-  * "bus_clk"
-  * "byte_clk"
-  * "core_clk"
-  * "core_mmss_clk"
-  * "iface_clk"
   * "mdp_core_clk"
+  * "iface_clk"
+  * "bus_clk"
+  * "core_mmss_clk"
+  * "byte_clk"
   * "pixel_clk"
+  * "core_clk"
+  For DSIv2, we need an additional clock:
+   * "src_clk"
 - vdd-supply: phandle to vdd regulator device node
 - vddio-supply: phandle to vdd-io regulator device node
 - vdda-supply: phandle to vdda regulator device node
 - qcom,dsi-phy: phandle to DSI PHY device node
+- syscon-sfpb: A phandle to mmss_sfpb syscon node (only for DSIv2)
 
 Optional properties:
 - panel@0: Node of panel connected to this DSI controller.
@@ -51,6 +54,7 @@ Required properties:
   * "qcom,dsi-phy-28nm-hpm"
   * "qcom,dsi-phy-28nm-lp"
   * "qcom,dsi-phy-20nm"
+  * "qcom,dsi-phy-28nm-8960"
 - reg: Physical base address and length of the registers of PLL, PHY and PHY
   regulator
 - reg-names: The names of register regions. The following regions are required:

Documentation/devicetree/bindings/display/msm/mdp.txt

@@ -2,18 +2,28 @@ Qualcomm adreno/snapdragon display controller
 
 Required properties:
 - compatible:
-  * "qcom,mdp" - mdp4
+  * "qcom,mdp4" - mdp4
+  * "qcom,mdp5" - mdp5
 - reg: Physical base address and length of the controller's registers.
 - interrupts: The interrupt signal from the display controller.
 - connectors: array of phandles for output device(s)
 - clocks: device clocks
   See ../clocks/clock-bindings.txt for details.
-- clock-names: the following clocks are required:
+- clock-names: the following clocks are required.
+  For MDP4:
    * "core_clk"
    * "iface_clk"
+   * "lut_clk"
    * "src_clk"
    * "hdmi_clk"
-  * "mpd_clk"
+   * "mdp_clk"
+  For MDP5:
+   * "bus_clk"
+   * "iface_clk"
+   * "core_clk_src"
+   * "core_clk"
+   * "lut_clk" (some MDP5 versions may not need this)
+   * "vsync_clk"
 
 Optional properties:
 - gpus: phandle for gpu device
@@ -26,7 +36,7 @@ Example:
 	...
 
 	mdp: qcom,mdp@5100000 {
-		compatible = "qcom,mdp";
+		compatible = "qcom,mdp4";
 		reg = <0x05100000 0xf0000>;
 		interrupts = <GIC_SPI 75 0>;
 		connectors = <&hdmi>;

Documentation/devicetree/bindings/display/panel/boe,tv080wum-nl0.txt

@@ -0,0 +1,7 @@
+Boe Corporation 8.0" WUXGA TFT LCD panel
+
+Required properties:
+- compatible: should be "boe,tv080wum-nl0"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.

Documentation/devicetree/bindings/display/panel/innolux,g121x1-l03.txt

@@ -0,0 +1,7 @@
+Innolux Corporation 12.1" G121X1-L03 XGA (1024x768) TFT LCD panel
+
+Required properties:
+- compatible: should be "innolux,g121x1-l03"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.

Documentation/devicetree/bindings/display/panel/kyo,tcg121xglp.txt

@@ -0,0 +1,7 @@
+Kyocera Corporation 12.1" XGA (1024x768) TFT LCD panel
+
+Required properties:
+- compatible: should be "kyo,tcg121xglp"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.

Documentation/devicetree/bindings/display/panel/panasonic,vvx10f034n00.txt

@@ -0,0 +1,20 @@
+Panasonic 10" WUXGA TFT LCD panel
+
+Required properties:
+- compatible: should be "panasonic,vvx10f034n00"
+- reg: DSI virtual channel of the peripheral
+- power-supply: phandle of the regulator that provides the supply voltage
+
+Optional properties:
+- backlight: phandle of the backlight device attached to the panel
+
+Example:
+
+	mdss_dsi@fd922800 {
+		panel@0 {
+			compatible = "panasonic,vvx10f034n00";
+			reg = <0>;
+			power-supply = <&vreg_vsp>;
+			backlight = <&lp8566_wled>;
+		};
+	};

Documentation/devicetree/bindings/display/panel/qiaodian,qd43003c0-40.txt

@@ -0,0 +1,7 @@
+QiaoDian XianShi Corporation 4"3 TFT LCD panel
+
+Required properties:
+- compatible: should be "qiaodian,qd43003c0-40"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.

Documentation/devicetree/bindings/display/panel/sharp,ls043t1le01.txt

@@ -0,0 +1,22 @@
+Sharp Microelectronics 4.3" qHD TFT LCD panel
+
+Required properties:
+- compatible: should be "sharp,ls043t1le01-qhd"
+- reg: DSI virtual channel of the peripheral
+- power-supply: phandle of the regulator that provides the supply voltage
+
+Optional properties:
+- backlight: phandle of the backlight device attached to the panel
+- reset-gpios: a GPIO spec for the reset pin
+
+Example:
+
+	mdss_dsi@fd922800 {
+		panel@0 {
+			compatible = "sharp,ls043t1le01-qhd";
+			reg = <0>;
+			avdd-supply = <&pm8941_l22>;
+			backlight = <&pm8941_wled>;
+			reset-gpios = <&pm8941_gpios 19 GPIO_ACTIVE_HIGH>;
+		};
+	};

Documentation/devicetree/bindings/display/rockchip/dw_mipi_dsi_rockchip.txt

@@ -0,0 +1,60 @@
+Rockchip specific extensions to the Synopsys Designware MIPI DSI
+================================
+
+Required properties:
+- #address-cells: Should be <1>.
+- #size-cells: Should be <0>.
+- compatible: "rockchip,rk3288-mipi-dsi", "snps,dw-mipi-dsi".
+- reg: Represent the physical address range of the controller.
+- interrupts: Represent the controller's interrupt to the CPU(s).
+- clocks, clock-names: Phandles to the controller's pll reference
+  clock(ref) and APB clock(pclk), as described in [1].
+- rockchip,grf: this soc should set GRF regs to mux vopl/vopb.
+- ports: contain a port node with endpoint definitions as defined in [2].
+  For vopb,set the reg = <0> and set the reg = <1> for vopl.
+
+[1] Documentation/devicetree/bindings/clock/clock-bindings.txt
+[2] Documentation/devicetree/bindings/media/video-interfaces.txt
+
+Example:
+	mipi_dsi: mipi@ff960000 {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		compatible = "rockchip,rk3288-mipi-dsi", "snps,dw-mipi-dsi";
+		reg = <0xff960000 0x4000>;
+		interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&cru SCLK_MIPI_24M>, <&cru PCLK_MIPI_DSI0>;
+		clock-names = "ref", "pclk";
+		rockchip,grf = <&grf>;
+		status = "okay";
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <1>;
+
+			mipi_in: port {
+				#address-cells = <1>;
+				#size-cells = <0>;
+				mipi_in_vopb: endpoint@0 {
+					reg = <0>;
+					remote-endpoint = <&vopb_out_mipi>;
+				};
+				mipi_in_vopl: endpoint@1 {
+					reg = <1>;
+					remote-endpoint = <&vopl_out_mipi>;
+				};
+			};
+		};
+
+		panel {
+			compatible ="boe,tv080wum-nl0";
+			reg = <0>;
+
+			enable-gpios = <&gpio7 3 GPIO_ACTIVE_HIGH>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&lcd_en>;
+			backlight = <&backlight>;
+			status = "okay";
+		};
+	};

Documentation/devicetree/bindings/display/rockchip/rockchip-vop.txt

@@ -7,6 +7,7 @@ buffer to an external LCD interface.
 Required properties:
 - compatible: value should be one of the following
 		"rockchip,rk3288-vop";
+		"rockchip,rk3036-vop";
 
 - interrupts: should contain a list of all VOP IP block interrupts in the
 		 order: VSYNC, LCD_SYSTEM. The interrupt specifier

Documentation/devicetree/bindings/dma/ti-edma.txt

@@ -22,8 +22,7 @@ Required properties:
 Optional properties:
 - ti,hwmods:	Name of the hwmods associated to the eDMA CC
 - ti,edma-memcpy-channels: List of channels allocated to be used for memcpy, iow
-		these channels will be SW triggered channels. The list must
+		these channels will be SW triggered channels. See example.
-		contain 16 bits numbers, see example.
 - ti,edma-reserved-slot-ranges: PaRAM slot ranges which should not be used by
 		the driver, they are allocated to be used by for example the
 		DSP. See example.
@@ -56,10 +55,9 @@ edma: edma@49000000 {
 	ti,tptcs = <&edma_tptc0 7>, <&edma_tptc1 7>, <&edma_tptc2 0>;
 
 	/* Channel 20 and 21 is allocated for memcpy */
-	ti,edma-memcpy-channels = /bits/ 16 <20 21>;
+	ti,edma-memcpy-channels = <20 21>;
-	/* The following PaRAM slots are reserved: 35-45 and 100-110 */
+	/* The following PaRAM slots are reserved: 35-44 and 100-109 */
-	ti,edma-reserved-slot-ranges = /bits/ 16 <35 10>,
+	ti,edma-reserved-slot-ranges = <35 10>, <100 10>;
-				       /bits/ 16 <100 10>;
 };
 
 edma_tptc0: tptc@49800000 {

Documentation/devicetree/bindings/gpio/gpio-mpc8xxx.txt

@@ -11,6 +11,10 @@ Required properties:
       0 = active high
       1 = active low
 
+Optional properties:
+- little-endian : GPIO registers are used as little endian. If not
+                  present registers are used as big endian by default.
+
 Example:
 
 gpio0: gpio@1100 {

Documentation/devicetree/bindings/input/sun4i-lradc-keys.txt

@@ -12,7 +12,7 @@ Each key is represented as a sub-node of "allwinner,sun4i-a10-lradc-keys":
 Required subnode-properties:
 	- label: Descriptive name of the key.
 	- linux,code: Keycode to emit.
-	- channel: Channel this key is attached to, mut be 0 or 1.
+	- channel: Channel this key is attached to, must be 0 or 1.
 	- voltage: Voltage in µV at lradc input when this key is pressed.
 
 Example:

Documentation/devicetree/bindings/media/exynos5-gsc.txt

@@ -7,6 +7,10 @@ Required properties:
 - reg: should contain G-Scaler physical address location and length.
 - interrupts: should contain G-Scaler interrupt number
 
+Optional properties:
+- samsung,sysreg: handle to syscon used to control the system registers to
+  set writeback input and destination
+
 Example:
 
 gsc_0:  gsc@0x13e00000 {

Documentation/devicetree/bindings/mtd/partition.txt

@@ -6,7 +6,9 @@ used for what purposes, but which don't use an on-flash partition table such
 as RedBoot.
 
 The partition table should be a subnode of the mtd node and should be named
-'partitions'. Partitions are defined in subnodes of the partitions node.
+'partitions'. This node should have the following property:
+- compatible : (required) must be "fixed-partitions"
+Partitions are then defined in subnodes of the partitions node.
 
 For backwards compatibility partitions as direct subnodes of the mtd device are
 supported. This use is discouraged.
@@ -36,6 +38,7 @@ Examples:
 
 flash@0 {
 	partitions {
+		compatible = "fixed-partitions";
 		#address-cells = <1>;
 		#size-cells = <1>;
 
@@ -53,6 +56,7 @@ flash@0 {
 
 flash@1 {
 	partitions {
+		compatible = "fixed-partitions";
 		#address-cells = <1>;
 		#size-cells = <2>;
 
@@ -66,6 +70,7 @@ flash@1 {
 
 flash@2 {
 	partitions {
+		compatible = "fixed-partitions";
 		#address-cells = <2>;
 		#size-cells = <2>;
 

Documentation/devicetree/bindings/vendor-prefixes.txt

@@ -33,6 +33,7 @@ auo	AU Optronics Corporation
 avago	Avago Technologies
 avic	Shanghai AVIC Optoelectronics Co., Ltd.
 axis	Axis Communications AB
+boe	BOE Technology Group Co., Ltd.
 bosch	Bosch Sensortec GmbH
 boundary	Boundary Devices Inc.
 brcm	Broadcom Corporation
@@ -123,6 +124,7 @@ jedec	JEDEC Solid State Technology Association
 karo	Ka-Ro electronics GmbH
 keymile	Keymile GmbH
 kinetic Kinetic Technologies
+kyo	Kyocera Corporation
 lacie	LaCie
 lantiq	Lantiq Semiconductor
 lenovo	Lenovo Group Ltd.
@@ -180,6 +182,7 @@ qca	Qualcomm Atheros, Inc.
 qcom	Qualcomm Technologies, Inc
 qemu	QEMU, a generic and open source machine emulator and virtualizer
 qi	Qi Hardware
+qiaodian	QiaoDian XianShi Corporation
 qnap	QNAP Systems, Inc.
 radxa	Radxa
 raidsonic	RaidSonic Technology GmbH
@@ -238,6 +241,7 @@ v3	V3 Semiconductor
 variscite	Variscite Ltd.
 via	VIA Technologies, Inc.
 virtio	Virtual I/O Device Specification, developed by the OASIS consortium
+vivante	Vivante Corporation
 voipac	Voipac Technologies s.r.o.
 wexler	Wexler
 winbond Winbond Electronics corp.

Documentation/networking/e100.txt

@@ -181,17 +181,3 @@ For general information, go to the Intel support website at:
 If an issue is identified with the released source code on the supported
 kernel with a supported adapter, email the specific information related to the
 issue to e1000-devel@lists.sourceforge.net.
-
-
-License
-=======
-
-This software program is released under the terms of a license agreement
-between you ('Licensee') and Intel. Do not use or load this software or any
-associated materials (collectively, the 'Software') until you have carefully
-read the full terms and conditions of the file COPYING located in this software
-package. By loading or using the Software, you agree to the terms of this
-Agreement. If you do not agree with the terms of this Agreement, do not install
-or use the Software.
-
-* Other names and brands may be claimed as the property of others.

MAINTAINERS

@@ -2975,6 +2975,7 @@ F:	kernel/cpuset.c
 CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
 M:	Johannes Weiner <hannes@cmpxchg.org>
 M:	Michal Hocko <mhocko@kernel.org>
+M:	Vladimir Davydov <vdavydov@virtuozzo.com>
 L:	cgroups@vger.kernel.org
 L:	linux-mm@kvack.org
 S:	Maintained
@@ -3743,6 +3744,15 @@ S:	Maintained
 F:	drivers/gpu/drm/sti
 F:	Documentation/devicetree/bindings/display/st,stih4xx.txt
 
+DRM DRIVERS FOR VIVANTE GPU IP
+M:	Lucas Stach <l.stach@pengutronix.de>
+R:	Russell King <linux+etnaviv@arm.linux.org.uk>
+R:	Christian Gmeiner <christian.gmeiner@gmail.com>
+L:	dri-devel@lists.freedesktop.org
+S:	Maintained
+F:	drivers/gpu/drm/etnaviv
+F:	Documentation/devicetree/bindings/display/etnaviv
+
 DSBR100 USB FM RADIO DRIVER
 M:	Alexey Klimov <klimov.linux@gmail.com>
 L:	linux-media@vger.kernel.org
@@ -5577,7 +5587,7 @@ R:	Jesse Brandeburg <jesse.brandeburg@intel.com>
 R:	Shannon Nelson <shannon.nelson@intel.com>
 R:	Carolyn Wyborny <carolyn.wyborny@intel.com>
 R:	Don Skidmore <donald.c.skidmore@intel.com>
-R:	Matthew Vick <matthew.vick@intel.com>
+R:	Bruce Allan <bruce.w.allan@intel.com>
 R:	John Ronciak <john.ronciak@intel.com>
 R:	Mitch Williams <mitch.a.williams@intel.com>
 L:	intel-wired-lan@lists.osuosl.org
@@ -8286,7 +8296,7 @@ F:	include/linux/delayacct.h
 F:	kernel/delayacct.c
 
 PERFORMANCE EVENTS SUBSYSTEM
-M:	Peter Zijlstra <a.p.zijlstra@chello.nl>
+M:	Peter Zijlstra <peterz@infradead.org>
 M:	Ingo Molnar <mingo@redhat.com>
 M:	Arnaldo Carvalho de Melo <acme@kernel.org>
 L:	linux-kernel@vger.kernel.org
@@ -8379,6 +8389,14 @@ L:	linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
 S:	Maintained
 F:	drivers/pinctrl/samsung/
 
+PIN CONTROLLER - SINGLE
+M:	Tony Lindgren <tony@atomide.com>
+M:	Haojian Zhuang <haojian.zhuang@linaro.org>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L:	linux-omap@vger.kernel.org
+S:	Maintained
+F:	drivers/pinctrl/pinctrl-single.c
+
 PIN CONTROLLER - ST SPEAR
 M:	Viresh Kumar <vireshk@kernel.org>
 L:	spear-devel@list.st.com
@@ -8945,6 +8963,13 @@ F:	drivers/rpmsg/
 F:	Documentation/rpmsg.txt
 F:	include/linux/rpmsg.h
 
+RENESAS ETHERNET DRIVERS
+R:	Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
+L:	netdev@vger.kernel.org
+L:	linux-sh@vger.kernel.org
+F:	drivers/net/ethernet/renesas/
+F:	include/linux/sh_eth.h
+
 RESET CONTROLLER FRAMEWORK
 M:	Philipp Zabel <p.zabel@pengutronix.de>
 S:	Maintained

Makefile

@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 4
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc6
 NAME = Blurry Fish Butt
 
 # *DOCUMENTATION*

arch/arc/Kconfig

@@ -445,6 +445,7 @@ config LINUX_LINK_BASE
 	  However some customers have peripherals mapped at this addr, so
 	  Linux needs to be scooted a bit.
 	  If you don't know what the above means, leave this setting alone.
+	  This needs to match memory start address specified in Device Tree
 
 config HIGHMEM
 	bool "High Memory Support"

arch/arc/boot/dts/axs10x_mb.dtsi

@@ -46,6 +46,7 @@
 			snps,pbl = < 32 >;
 			clocks = <&apbclk>;
 			clock-names = "stmmaceth";
+			max-speed = <100>;
 		};
 
 		ehci@0x40000 {

arch/arc/boot/dts/nsim_hs.dts

@@ -17,7 +17,8 @@
 
 	memory {
 		device_type = "memory";
-		reg = <0x0 0x80000000 0x0 0x40000000	/* 1 GB low mem */
+		/* CONFIG_LINUX_LINK_BASE needs to match low mem start */
+		reg = <0x0 0x80000000 0x0 0x20000000	/* 512 MB low mem */
 		       0x1 0x00000000 0x0 0x40000000>;	/* 1 GB highmem */
 	};
 

arch/arc/include/asm/mach_desc.h

@@ -23,7 +23,7 @@
  * @dt_compat:		Array of device tree 'compatible' strings
  * 			(XXX: although only 1st entry is looked at)
  * @init_early:		Very early callback [called from setup_arch()]
- * @init_cpu_smp:	for each CPU as it is coming up (SMP as well as UP)
+ * @init_per_cpu:	for each CPU as it is coming up (SMP as well as UP)
  * 			[(M):init_IRQ(), (o):start_kernel_secondary()]
  * @init_machine:	arch initcall level callback (e.g. populate static
  * 			platform devices or parse Devicetree)
@@ -35,7 +35,7 @@ struct machine_desc {
 	const char		**dt_compat;
 	void			(*init_early)(void);
 #ifdef CONFIG_SMP
-	void			(*init_cpu_smp)(unsigned int);
+	void			(*init_per_cpu)(unsigned int);
 #endif
 	void			(*init_machine)(void);
 	void			(*init_late)(void);

arch/arc/include/asm/smp.h

@@ -48,7 +48,7 @@ extern int smp_ipi_irq_setup(int cpu, int irq);
  * @init_early_smp:	A SMP specific h/w block can init itself
  * 			Could be common across platforms so not covered by
  * 			mach_desc->init_early()
- * @init_irq_cpu:	Called for each core so SMP h/w block driver can do
+ * @init_per_cpu:	Called for each core so SMP h/w block driver can do
  * 			any needed setup per cpu (e.g. IPI request)
  * @cpu_kick:		For Master to kickstart a cpu (optionally at a PC)
  * @ipi_send:		To send IPI to a @cpu
@@ -57,7 +57,7 @@ extern int smp_ipi_irq_setup(int cpu, int irq);
 struct plat_smp_ops {
 	const char 	*info;
 	void		(*init_early_smp)(void);
-	void		(*init_irq_cpu)(int cpu);
+	void		(*init_per_cpu)(int cpu);
 	void		(*cpu_kick)(int cpu, unsigned long pc);
 	void		(*ipi_send)(int cpu);
 	void		(*ipi_clear)(int irq);

arch/arc/include/asm/unwind.h

@@ -112,7 +112,6 @@ struct unwind_frame_info {
 
 extern int arc_unwind(struct unwind_frame_info *frame);
 extern void arc_unwind_init(void);
-extern void arc_unwind_setup(void);
 extern void *unwind_add_table(struct module *module, const void *table_start,
 			      unsigned long table_size);
 extern void unwind_remove_table(void *handle, int init_only);
@@ -152,9 +151,6 @@ static inline void arc_unwind_init(void)
 {
 }
 
-static inline void arc_unwind_setup(void)
-{
-}
 #define unwind_add_table(a, b, c)
 #define unwind_remove_table(a, b)
 

arch/arc/kernel/intc-arcv2.c

@@ -106,10 +106,21 @@ static struct irq_chip arcv2_irq_chip = {
 static int arcv2_irq_map(struct irq_domain *d, unsigned int irq,
 			 irq_hw_number_t hw)
 {
-	if (irq == TIMER0_IRQ || irq == IPI_IRQ)
+	/*
+	 * core intc IRQs [16, 23]:
+	 * Statically assigned always private-per-core (Timers, WDT, IPI, PCT)
+	 */
+	if (hw < 24) {
+		/*
+		 * A subsequent request_percpu_irq() fails if percpu_devid is
+		 * not set. That in turns sets NOAUTOEN, meaning each core needs
+		 * to call enable_percpu_irq()
+		 */
+		irq_set_percpu_devid(irq);
 		irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_percpu_irq);
-	else
+	} else {
 		irq_set_chip_and_handler(irq, &arcv2_irq_chip, handle_level_irq);
+	}
 
 	return 0;
 }

arch/arc/kernel/irq.c

@@ -29,11 +29,11 @@ void __init init_IRQ(void)
 
 #ifdef CONFIG_SMP
 	/* a SMP H/w block could do IPI IRQ request here */
-	if (plat_smp_ops.init_irq_cpu)
+	if (plat_smp_ops.init_per_cpu)
-		plat_smp_ops.init_irq_cpu(smp_processor_id());
+		plat_smp_ops.init_per_cpu(smp_processor_id());
 
-	if (machine_desc->init_cpu_smp)
+	if (machine_desc->init_per_cpu)
-		machine_desc->init_cpu_smp(smp_processor_id());
+		machine_desc->init_per_cpu(smp_processor_id());
 #endif
 }
 
@@ -51,6 +51,18 @@ void arch_do_IRQ(unsigned int irq, struct pt_regs *regs)
 	set_irq_regs(old_regs);
 }
 
+/*
+ * API called for requesting percpu interrupts - called by each CPU
+ *  - For boot CPU, actually request the IRQ with genirq core + enables
+ *  - For subsequent callers only enable called locally
+ *
+ * Relies on being called by boot cpu first (i.e. request called ahead) of
+ * any enable as expected by genirq. Hence Suitable only for TIMER, IPI
+ * which are guaranteed to be setup on boot core first.
+ * Late probed peripherals such as perf can't use this as there no guarantee
+ * of being called on boot CPU first.
+ */
+
 void arc_request_percpu_irq(int irq, int cpu,
                             irqreturn_t (*isr)(int irq, void *dev),
                             const char *irq_nm,
@@ -60,14 +72,17 @@ void arc_request_percpu_irq(int irq, int cpu,
 	if (!cpu) {
 		int rc;
 
+#ifdef CONFIG_ISA_ARCOMPACT
 		/*
-		 * These 2 calls are essential to making percpu IRQ APIs work
+		 * A subsequent request_percpu_irq() fails if percpu_devid is
-		 * Ideally these details could be hidden in irq chip map function
+		 * not set. That in turns sets NOAUTOEN, meaning each core needs
-		 * but the issue is IPIs IRQs being static (non-DT) and platform
+		 * to call enable_percpu_irq()
-		 * specific, so we can't identify them there.
+		 *
+		 * For ARCv2, this is done in irq map function since we know
+		 * which irqs are strictly per cpu
 		 */
 		irq_set_percpu_devid(irq);
-		irq_modify_status(irq, IRQ_NOAUTOEN, 0);  /* @irq, @clr, @set */
+#endif
 
 		rc = request_percpu_irq(irq, isr, irq_nm, percpu_dev);
 		if (rc)

arch/arc/kernel/mcip.c

@@ -132,7 +132,7 @@ static void mcip_probe_n_setup(void)
 struct plat_smp_ops plat_smp_ops = {
 	.info		= smp_cpuinfo_buf,
 	.init_early_smp	= mcip_probe_n_setup,
-	.init_irq_cpu	= mcip_setup_per_cpu,
+	.init_per_cpu	= mcip_setup_per_cpu,
 	.ipi_send	= mcip_ipi_send,
 	.ipi_clear	= mcip_ipi_clear,
 };

arch/arc/kernel/perf_event.c

@@ -428,12 +428,11 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev)
 
 #endif /* CONFIG_ISA_ARCV2 */
 
-void arc_cpu_pmu_irq_init(void)
+static void arc_cpu_pmu_irq_init(void *data)
 {
-	struct arc_pmu_cpu *pmu_cpu = this_cpu_ptr(&arc_pmu_cpu);
+	int irq = *(int *)data;
 
-	arc_request_percpu_irq(arc_pmu->irq, smp_processor_id(), arc_pmu_intr,
+	enable_percpu_irq(irq, IRQ_TYPE_NONE);
-			       "ARC perf counters", pmu_cpu);
 
 	/* Clear all pending interrupt flags */
 	write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff);
@@ -515,7 +514,6 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 
 	if (has_interrupts) {
 		int irq = platform_get_irq(pdev, 0);
-		unsigned long flags;
 
 		if (irq < 0) {
 			pr_err("Cannot get IRQ number for the platform\n");
@@ -524,24 +522,12 @@ static int arc_pmu_device_probe(struct platform_device *pdev)
 
 		arc_pmu->irq = irq;
 
-		/*
+		/* intc map function ensures irq_set_percpu_devid() called */
-		 * arc_cpu_pmu_irq_init() needs to be called on all cores for
+		request_percpu_irq(irq, arc_pmu_intr, "ARC perf counters",
-		 * their respective local PMU.
+				   this_cpu_ptr(&arc_pmu_cpu));
-		 * However we use opencoded on_each_cpu() to ensure it is called
+
-		 * on core0 first, so that arc_request_percpu_irq() sets up
+		on_each_cpu(arc_cpu_pmu_irq_init, &irq, 1);
-		 * AUTOEN etc. Otherwise enable_percpu_irq() fails to enable
-		 * perf IRQ on non master cores.
-		 * see arc_request_percpu_irq()
-		 */
-		preempt_disable();
-		local_irq_save(flags);
-		arc_cpu_pmu_irq_init();
-		local_irq_restore(flags);
-		smp_call_function((smp_call_func_t)arc_cpu_pmu_irq_init, 0, 1);
-		preempt_enable();
 
-		/* Clean all pending interrupt flags */
-		write_aux_reg(ARC_REG_PCT_INT_ACT, 0xffffffff);
 	} else
 		arc_pmu->pmu.capabilities |= PERF_PMU_CAP_NO_INTERRUPT;
 

arch/arc/kernel/setup.c

@@ -429,7 +429,6 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	arc_unwind_init();
-	arc_unwind_setup();
 }
 
 static int __init customize_machine(void)

arch/arc/kernel/smp.c

@@ -132,11 +132,11 @@ void start_kernel_secondary(void)
 	pr_info("## CPU%u LIVE ##: Executing Code...\n", cpu);
 
 	/* Some SMP H/w setup - for each cpu */
-	if (plat_smp_ops.init_irq_cpu)
+	if (plat_smp_ops.init_per_cpu)
-		plat_smp_ops.init_irq_cpu(cpu);
+		plat_smp_ops.init_per_cpu(cpu);
 
-	if (machine_desc->init_cpu_smp)
+	if (machine_desc->init_per_cpu)
-		machine_desc->init_cpu_smp(cpu);
+		machine_desc->init_per_cpu(cpu);
 
 	arc_local_timer_setup();
 

arch/arc/kernel/unwind.c

@@ -170,6 +170,23 @@ static struct unwind_table *find_table(unsigned long pc)
 
 static unsigned long read_pointer(const u8 **pLoc,
 				  const void *end, signed ptrType);
+static void init_unwind_hdr(struct unwind_table *table,
+			    void *(*alloc) (unsigned long));
+
+/*
+ * wrappers for header alloc (vs. calling one vs. other at call site)
+ * to elide section mismatches warnings
+ */
+static void *__init unw_hdr_alloc_early(unsigned long sz)
+{
+	return __alloc_bootmem_nopanic(sz, sizeof(unsigned int),
+				       MAX_DMA_ADDRESS);
+}
+
+static void *unw_hdr_alloc(unsigned long sz)
+{
+	return kmalloc(sz, GFP_KERNEL);
+}
 
 static void init_unwind_table(struct unwind_table *table, const char *name,
 			      const void *core_start, unsigned long core_size,
@@ -209,6 +226,8 @@ void __init arc_unwind_init(void)
 			  __start_unwind, __end_unwind - __start_unwind,
 			  NULL, 0);
 	  /*__start_unwind_hdr, __end_unwind_hdr - __start_unwind_hdr);*/
+
+	init_unwind_hdr(&root_table, unw_hdr_alloc_early);
 }
 
 static const u32 bad_cie, not_fde;
@@ -241,7 +260,7 @@ static void swap_eh_frame_hdr_table_entries(void *p1, void *p2, int size)
 	e2->fde = v;
 }
 
-static void __init setup_unwind_table(struct unwind_table *table,
+static void init_unwind_hdr(struct unwind_table *table,
 			    void *(*alloc) (unsigned long))
 {
 	const u8 *ptr;
@@ -274,13 +293,13 @@ static void __init setup_unwind_table(struct unwind_table *table,
 		const u32 *cie = cie_for_fde(fde, table);
 		signed ptrType;
 
-		if (cie == &not_fde)
+		if (cie == &not_fde)	/* only process FDE here */
 			continue;
 		if (cie == NULL || cie == &bad_cie)
-			return;
+			continue;	/* say FDE->CIE.version != 1 */
 		ptrType = fde_pointer_type(cie);
 		if (ptrType < 0)
-			return;
+			continue;
 
 		ptr = (const u8 *)(fde + 2);
 		if (!read_pointer(&ptr, (const u8 *)(fde + 1) + *fde,
@@ -300,9 +319,11 @@ static void __init setup_unwind_table(struct unwind_table *table,
 
 	hdrSize = 4 + sizeof(unsigned long) + sizeof(unsigned int)
 	    + 2 * n * sizeof(unsigned long);
+
 	header = alloc(hdrSize);
 	if (!header)
 		return;
+
 	header->version = 1;
 	header->eh_frame_ptr_enc = DW_EH_PE_abs | DW_EH_PE_native;
 	header->fde_count_enc = DW_EH_PE_abs | DW_EH_PE_data4;
@@ -322,6 +343,10 @@ static void __init setup_unwind_table(struct unwind_table *table,
 
 		if (fde[1] == 0xffffffff)
 			continue;	/* this is a CIE */
+
+		if (*(u8 *)(cie + 2) != 1)
+			continue;	/* FDE->CIE.version not supported */
+
 		ptr = (const u8 *)(fde + 2);
 		header->table[n].start = read_pointer(&ptr,
 						      (const u8 *)(fde + 1) +
@@ -342,18 +367,6 @@ static void __init setup_unwind_table(struct unwind_table *table,
 	table->header = (const void *)header;
 }
 
-static void *__init balloc(unsigned long sz)
-{
-	return __alloc_bootmem_nopanic(sz,
-				       sizeof(unsigned int),
-				       __pa(MAX_DMA_ADDRESS));
-}
-
-void __init arc_unwind_setup(void)
-{
-	setup_unwind_table(&root_table, balloc);
-}
-
 #ifdef CONFIG_MODULES
 
 static struct unwind_table *last_table;
@@ -377,6 +390,8 @@ void *unwind_add_table(struct module *module, const void *table_start,
 			  table_start, table_size,
 			  NULL, 0);
 
+	init_unwind_hdr(table, unw_hdr_alloc);
+
 #ifdef UNWIND_DEBUG
 	unw_debug("Table added for [%s] %lx %lx\n",
 		module->name, table->core.pc, table->core.range);
@@ -439,6 +454,7 @@ void unwind_remove_table(void *handle, int init_only)
 	info.init_only = init_only;
 
 	unlink_table(&info); /* XXX: SMP */
+	kfree(table->header);
 	kfree(table);
 }
 
@@ -507,7 +523,8 @@ static const u32 *cie_for_fde(const u32 *fde, const struct unwind_table *table)
 
 	if (*cie <= sizeof(*cie) + 4 || *cie >= fde[1] - sizeof(*fde)
 	    || (*cie & (sizeof(*cie) - 1))
-	    || (cie[1] != 0xffffffff))
+	    || (cie[1] != 0xffffffff)
+	    || ( *(u8 *)(cie + 2) != 1))   /* version 1 supported */
 		return NULL;	/* this is not a (valid) CIE */
 	return cie;
 }

arch/arc/mm/init.c

@@ -51,7 +51,9 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
 	int in_use = 0;
 
 	if (!low_mem_sz) {
-		BUG_ON(base != low_mem_start);
+		if (base != low_mem_start)
+			panic("CONFIG_LINUX_LINK_BASE != DT memory { }");
+
 		low_mem_sz = size;
 		in_use = 1;
 	} else {

arch/arm/boot/dts/am4372.dtsi

@@ -74,7 +74,7 @@
 		reg = <0x48240200 0x100>;
 		interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-parent = <&gic>;
-		clocks = <&dpll_mpu_m2_ck>;
+		clocks = <&mpu_periphclk>;
 	};
 
 	local_timer: timer@48240600 {
@@ -82,7 +82,7 @@
 		reg = <0x48240600 0x100>;
 		interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>;
 		interrupt-parent = <&gic>;
-		clocks = <&dpll_mpu_m2_ck>;
+		clocks = <&mpu_periphclk>;
 	};
 
 	l2-cache-controller@48242000 {

arch/arm/boot/dts/am43xx-clocks.dtsi

@@ -259,6 +259,14 @@
 		ti,invert-autoidle-bit;
 	};
 
+	mpu_periphclk: mpu_periphclk {
+		#clock-cells = <0>;
+		compatible = "fixed-factor-clock";
+		clocks = <&dpll_mpu_m2_ck>;
+		clock-mult = <1>;
+		clock-div = <2>;
+	};
+
 	dpll_ddr_ck: dpll_ddr_ck {
 		#clock-cells = <0>;
 		compatible = "ti,am3-dpll-clock";

arch/arm/boot/dts/at91-sama5d2_xplained.dts

@@ -184,6 +184,7 @@
 							regulator-name = "VDD_SDHC_1V8";
 							regulator-min-microvolt = <1800000>;
 							regulator-max-microvolt = <1800000>;
+							regulator-always-on;
 						};
 					};
 				};

arch/arm/boot/dts/berlin2q.dtsi

@@ -118,7 +118,8 @@
 		sdhci0: sdhci@ab0000 {
 			compatible = "mrvl,pxav3-mmc";
 			reg = <0xab0000 0x200>;
-			clocks = <&chip_clk CLKID_SDIO1XIN>;
+			clocks = <&chip_clk CLKID_SDIO1XIN>, <&chip_clk CLKID_SDIO>;
+			clock-names = "io", "core";
 			interrupts = <GIC_SPI 17 IRQ_TYPE_LEVEL_HIGH>;
 			status = "disabled";
 		};
@@ -126,7 +127,8 @@
 		sdhci1: sdhci@ab0800 {
 			compatible = "mrvl,pxav3-mmc";
 			reg = <0xab0800 0x200>;
-			clocks = <&chip_clk CLKID_SDIO1XIN>;
+			clocks = <&chip_clk CLKID_SDIO1XIN>, <&chip_clk CLKID_SDIO>;
+			clock-names = "io", "core";
 			interrupts = <GIC_SPI 20 IRQ_TYPE_LEVEL_HIGH>;
 			status = "disabled";
 		};
@@ -135,7 +137,7 @@
 			compatible = "mrvl,pxav3-mmc";
 			reg = <0xab1000 0x200>;
 			interrupts = <GIC_SPI 28 IRQ_TYPE_LEVEL_HIGH>;
-			clocks = <&chip_clk CLKID_NFC_ECC>, <&chip_clk CLKID_NFC>;
+			clocks = <&chip_clk CLKID_NFC_ECC>, <&chip_clk CLKID_SDIO>;
 			clock-names = "io", "core";
 			status = "disabled";
 		};

arch/arm/boot/dts/dm816x.dtsi

@@ -218,6 +218,7 @@
 			reg = <0x480c8000 0x2000>;
 			interrupts = <77>;
 			ti,hwmods = "mailbox";
+			#mbox-cells = <1>;
 			ti,mbox-num-users = <4>;
 			ti,mbox-num-fifos = <12>;
 			mbox_dsp: mbox_dsp {
@@ -279,8 +280,11 @@
 			ti,spi-num-cs = <4>;
 			ti,hwmods = "mcspi1";
 			dmas = <&edma 16 &edma 17
-				&edma 18 &edma 19>;
+				&edma 18 &edma 19
-			dma-names = "tx0", "rx0", "tx1", "rx1";
+				&edma 20 &edma 21
+				&edma 22 &edma 23>;
+			dma-names = "tx0", "rx0", "tx1", "rx1",
+				    "tx2", "rx2", "tx3", "rx3";
 		};
 
 		mmc1: mmc@48060000 {

arch/arm/boot/dts/exynos5800-peach-pi.dts

@@ -122,6 +122,12 @@
 		compatible = "auo,b133htn01";
 		power-supply = <&tps65090_fet6>;
 		backlight = <&backlight>;
+
+		port {
+			panel_in: endpoint {
+				remote-endpoint = <&dp_out>;
+			};
+		};
 	};
 
 	mmc1_pwrseq: mmc1_pwrseq {
@@ -148,7 +154,14 @@
 	samsung,link-rate = <0x0a>;
 	samsung,lane-count = <2>;
 	samsung,hpd-gpio = <&gpx2 6 GPIO_ACTIVE_HIGH>;
-	panel = <&panel>;
+
+	ports {
+		port {
+			dp_out: endpoint {
+				remote-endpoint = <&panel_in>;
+			};
+		};
+	};
 };
 
 &fimd {

arch/arm/boot/dts/vf610-colibri.dtsi

@@ -18,8 +18,3 @@
 		reg = <0x80000000 0x10000000>;
 	};
 };
-
-&L2 {
-	arm,data-latency = <2 1 2>;
-	arm,tag-latency = <3 2 3>;
-};

arch/arm/boot/dts/vf610.dtsi

@@ -19,7 +19,7 @@
 		reg = <0x40006000 0x1000>;
 		cache-unified;
 		cache-level = <2>;
-		arm,data-latency = <1 1 1>;
+		arm,data-latency = <3 3 3>;
 		arm,tag-latency = <2 2 2>;
 	};
 };

arch/arm/boot/dts/vfxxx.dtsi

@@ -178,8 +178,10 @@
 				compatible = "fsl,vf610-sai";
 				reg = <0x40031000 0x1000>;
 				interrupts = <86 IRQ_TYPE_LEVEL_HIGH>;
-				clocks = <&clks VF610_CLK_SAI2>;
+				clocks = <&clks VF610_CLK_SAI2>,
-				clock-names = "sai";
+					<&clks VF610_CLK_SAI2_DIV>,
+					<&clks 0>, <&clks 0>;
+				clock-names = "bus", "mclk1", "mclk2", "mclk3";
 				dma-names = "tx", "rx";
 				dmas = <&edma0 0 21>,
 					<&edma0 0 20>;

arch/arm/include/asm/arch_gicv3.h

@@ -21,6 +21,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/io.h>
+#include <asm/barrier.h>
 
 #define __ACCESS_CP15(CRn, Op1, CRm, Op2)	p15, Op1, %0, CRn, CRm, Op2
 #define __ACCESS_CP15_64(Op1, CRm)		p15, Op1, %Q0, %R0, CRm

arch/arm/include/asm/uaccess.h

@@ -510,10 +510,14 @@ __copy_to_user_std(void __user *to, const void *from, unsigned long n);
 static inline unsigned long __must_check
 __copy_to_user(void __user *to, const void *from, unsigned long n)
 {
+#ifndef CONFIG_UACCESS_WITH_MEMCPY
 	unsigned int __ua_flags = uaccess_save_and_enable();
 	n = arm_copy_to_user(to, from, n);
 	uaccess_restore(__ua_flags);
 	return n;
+#else
+	return arm_copy_to_user(to, from, n);
+#endif
 }
 
 extern unsigned long __must_check

arch/arm/kernel/process.c

@@ -95,6 +95,22 @@ void __show_regs(struct pt_regs *regs)
 {
 	unsigned long flags;
 	char buf[64];
+#ifndef CONFIG_CPU_V7M
+	unsigned int domain;
+#ifdef CONFIG_CPU_SW_DOMAIN_PAN
+	/*
+	 * Get the domain register for the parent context. In user
+	 * mode, we don't save the DACR, so lets use what it should
+	 * be. For other modes, we place it after the pt_regs struct.
+	 */
+	if (user_mode(regs))
+		domain = DACR_UACCESS_ENABLE;
+	else
+		domain = *(unsigned int *)(regs + 1);
+#else
+	domain = get_domain();
+#endif
+#endif
 
 	show_regs_print_info(KERN_DEFAULT);
 
@@ -123,21 +139,8 @@ void __show_regs(struct pt_regs *regs)
 
 #ifndef CONFIG_CPU_V7M
 	{
-		unsigned int domain = get_domain();
 		const char *segment;
 
-#ifdef CONFIG_CPU_SW_DOMAIN_PAN
-		/*
-		 * Get the domain register for the parent context. In user
-		 * mode, we don't save the DACR, so lets use what it should
-		 * be. For other modes, we place it after the pt_regs struct.
-		 */
-		if (user_mode(regs))
-			domain = DACR_UACCESS_ENABLE;
-		else
-			domain = *(unsigned int *)(regs + 1);
-#endif
-
 		if ((domain & domain_mask(DOMAIN_USER)) ==
 		    domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
 			segment = "none";
@@ -163,11 +166,11 @@ void __show_regs(struct pt_regs *regs)
 		buf[0] = '\0';
 #ifdef CONFIG_CPU_CP15_MMU
 		{
-			unsigned int transbase, dac = get_domain();
+			unsigned int transbase;
 			asm("mrc p15, 0, %0, c2, c0\n\t"
 			    : "=r" (transbase));
 			snprintf(buf, sizeof(buf), "  Table: %08x  DAC: %08x",
-			  	transbase, dac);
+				transbase, domain);
 		}
 #endif
 		asm("mrc p15, 0, %0, c1, c0\n" : "=r" (ctrl));

arch/arm/kernel/swp_emulate.c

@@ -36,10 +36,10 @@
  */
 #define __user_swpX_asm(data, addr, res, temp, B)		\
 	__asm__ __volatile__(					\
-	"	mov		%2, %1\n"			\
+	"0:	ldrex"B"	%2, [%3]\n"			\
-	"0:	ldrex"B"	%1, [%3]\n"			\
+	"1:	strex"B"	%0, %1, [%3]\n"			\
-	"1:	strex"B"	%0, %2, [%3]\n"			\
 	"	cmp		%0, #0\n"			\
+	"	moveq		%1, %2\n"			\
 	"	movne		%0, %4\n"			\
 	"2:\n"							\
 	"	.section	 .text.fixup,\"ax\"\n"		\

arch/arm/lib/uaccess_with_memcpy.c

@@ -88,6 +88,7 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp)
 static unsigned long noinline
 __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
 {
+	unsigned long ua_flags;
 	int atomic;
 
 	if (unlikely(segment_eq(get_fs(), KERNEL_DS))) {
@@ -118,7 +119,9 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
 		if (tocopy > n)
 			tocopy = n;
 
+		ua_flags = uaccess_save_and_enable();
 		memcpy((void *)to, from, tocopy);
+		uaccess_restore(ua_flags);
 		to += tocopy;
 		from += tocopy;
 		n -= tocopy;
@@ -145,14 +148,21 @@ arm_copy_to_user(void __user *to, const void *from, unsigned long n)
 	 * With frame pointer disabled, tail call optimization kicks in
 	 * as well making this test almost invisible.
 	 */
-	if (n < 64)
+	if (n < 64) {
-		return __copy_to_user_std(to, from, n);
+		unsigned long ua_flags = uaccess_save_and_enable();
-	return __copy_to_user_memcpy(to, from, n);
+		n = __copy_to_user_std(to, from, n);
+		uaccess_restore(ua_flags);
+	} else {
+		n = __copy_to_user_memcpy(to, from, n);
+	}
+	return n;
 }
 	
 static unsigned long noinline
 __clear_user_memset(void __user *addr, unsigned long n)
 {
+	unsigned long ua_flags;
+
 	if (unlikely(segment_eq(get_fs(), KERNEL_DS))) {
 		memset((void *)addr, 0, n);
 		return 0;
@@ -175,7 +185,9 @@ __clear_user_memset(void __user *addr, unsigned long n)
 		if (tocopy > n)
 			tocopy = n;
 
+		ua_flags = uaccess_save_and_enable();
 		memset((void *)addr, 0, tocopy);
+		uaccess_restore(ua_flags);
 		addr += tocopy;
 		n -= tocopy;
 
@@ -193,9 +205,14 @@ out:
 unsigned long arm_clear_user(void __user *addr, unsigned long n)
 {
 	/* See rational for this in __copy_to_user() above. */
-	if (n < 64)
+	if (n < 64) {
-		return __clear_user_std(addr, n);
+		unsigned long ua_flags = uaccess_save_and_enable();
-	return __clear_user_memset(addr, n);
+		n = __clear_user_std(addr, n);
+		uaccess_restore(ua_flags);
+	} else {
+		n = __clear_user_memset(addr, n);
+	}
+	return n;
 }
 
 #if 0

arch/arm/mach-at91/Kconfig

@@ -4,7 +4,6 @@ menuconfig ARCH_AT91
 	select ARCH_REQUIRE_GPIOLIB
 	select COMMON_CLK_AT91
 	select PINCTRL
-	select PINCTRL_AT91
 	select SOC_BUS
 
 if ARCH_AT91
@@ -17,6 +16,7 @@ config SOC_SAMA5D2
 	select HAVE_AT91_USB_CLK
 	select HAVE_AT91_H32MX
 	select HAVE_AT91_GENERATED_CLK
+	select PINCTRL_AT91PIO4
 	help
 	  Select this if ou are using one of Atmel's SAMA5D2 family SoC.
 
@@ -27,6 +27,7 @@ config SOC_SAMA5D3
 	select HAVE_AT91_UTMI
 	select HAVE_AT91_SMD
 	select HAVE_AT91_USB_CLK
+	select PINCTRL_AT91
 	help
 	  Select this if you are using one of Atmel's SAMA5D3 family SoC.
 	  This support covers SAMA5D31, SAMA5D33, SAMA5D34, SAMA5D35, SAMA5D36.
@@ -40,6 +41,7 @@ config SOC_SAMA5D4
 	select HAVE_AT91_SMD
 	select HAVE_AT91_USB_CLK
 	select HAVE_AT91_H32MX
+	select PINCTRL_AT91
 	help
 	  Select this if you are using one of Atmel's SAMA5D4 family SoC.
 
@@ -50,6 +52,7 @@ config SOC_AT91RM9200
 	select CPU_ARM920T
 	select HAVE_AT91_USB_CLK
 	select MIGHT_HAVE_PCI
+	select PINCTRL_AT91
 	select SOC_SAM_V4_V5
 	select SRAM if PM
 	help
@@ -65,6 +68,7 @@ config SOC_AT91SAM9
 	select HAVE_AT91_UTMI
 	select HAVE_FB_ATMEL
 	select MEMORY
+	select PINCTRL_AT91
 	select SOC_SAM_V4_V5
 	select SRAM if PM
 	help

arch/arm/mach-at91/pm.c

@@ -41,8 +41,10 @@
  * implementation should be moved down into the pinctrl driver and get
  * called as part of the generic suspend/resume path.
  */
+#ifdef CONFIG_PINCTRL_AT91
 extern void at91_pinctrl_gpio_suspend(void);
 extern void at91_pinctrl_gpio_resume(void);
+#endif
 
 static struct {
 	unsigned long uhp_udp_mask;
@@ -151,8 +153,9 @@ static void at91_pm_suspend(suspend_state_t state)
 
 static int at91_pm_enter(suspend_state_t state)
 {
+#ifdef CONFIG_PINCTRL_AT91
 	at91_pinctrl_gpio_suspend();
-
+#endif
 	switch (state) {
 	/*
 	 * Suspend-to-RAM is like STANDBY plus slow clock mode, so
@@ -192,7 +195,9 @@ static int at91_pm_enter(suspend_state_t state)
 error:
 	target_state = PM_SUSPEND_ON;
 
+#ifdef CONFIG_PINCTRL_AT91
 	at91_pinctrl_gpio_resume();
+#endif
 	return 0;
 }
 

arch/arm/mach-exynos/pmu.c

@@ -748,8 +748,12 @@ static void exynos5_powerdown_conf(enum sys_powerdown mode)
 void exynos_sys_powerdown_conf(enum sys_powerdown mode)
 {
 	unsigned int i;
+	const struct exynos_pmu_data *pmu_data;
 
-	const struct exynos_pmu_data *pmu_data = pmu_context->pmu_data;
+	if (!pmu_context)
+		return;
+
+	pmu_data = pmu_context->pmu_data;
 
 	if (pmu_data->powerdown_conf)
 		pmu_data->powerdown_conf(mode);

arch/arm/mach-ixp4xx/include/mach/io.h

@@ -143,7 +143,7 @@ static inline void __indirect_writesl(volatile void __iomem *bus_addr,
 		writel(*vaddr++, bus_addr);
 }
 
-static inline unsigned char __indirect_readb(const volatile void __iomem *p)
+static inline u8 __indirect_readb(const volatile void __iomem *p)
 {
 	u32 addr = (u32)p;
 	u32 n, byte_enables, data;
@@ -166,7 +166,7 @@ static inline void __indirect_readsb(const volatile void __iomem *bus_addr,
 		*vaddr++ = readb(bus_addr);
 }
 
-static inline unsigned short __indirect_readw(const volatile void __iomem *p)
+static inline u16 __indirect_readw(const volatile void __iomem *p)
 {
 	u32 addr = (u32)p;
 	u32 n, byte_enables, data;
@@ -189,7 +189,7 @@ static inline void __indirect_readsw(const volatile void __iomem *bus_addr,
 		*vaddr++ = readw(bus_addr);
 }
 
-static inline unsigned long __indirect_readl(const volatile void __iomem *p)
+static inline u32 __indirect_readl(const volatile void __iomem *p)
 {
 	u32 addr = (__force u32)p;
 	u32 data;
@@ -350,7 +350,7 @@ static inline void insl(u32 io_addr, void *p, u32 count)
 					((unsigned long)p <= (PIO_MASK + PIO_OFFSET)))
 
 #define	ioread8(p)			ioread8(p)
-static inline unsigned int ioread8(const void __iomem *addr)
+static inline u8 ioread8(const void __iomem *addr)
 {
 	unsigned long port = (unsigned long __force)addr;
 	if (__is_io_address(port))
@@ -378,7 +378,7 @@ static inline void ioread8_rep(const void __iomem *addr, void *vaddr, u32 count)
 }
 
 #define	ioread16(p)			ioread16(p)
-static inline unsigned int ioread16(const void __iomem *addr)
+static inline u16 ioread16(const void __iomem *addr)
 {
 	unsigned long port = (unsigned long __force)addr;
 	if (__is_io_address(port))
@@ -407,7 +407,7 @@ static inline void ioread16_rep(const void __iomem *addr, void *vaddr,
 }
 
 #define	ioread32(p)			ioread32(p)
-static inline unsigned int ioread32(const void __iomem *addr)
+static inline u32 ioread32(const void __iomem *addr)
 {
 	unsigned long port = (unsigned long __force)addr;
 	if (__is_io_address(port))

arch/arm/mach-omap2/Kconfig

@@ -121,6 +121,7 @@ config ARCH_OMAP2PLUS_TYPICAL
 	select NEON if CPU_V7
 	select PM
 	select REGULATOR
+	select REGULATOR_FIXED_VOLTAGE
 	select TWL4030_CORE if ARCH_OMAP3 || ARCH_OMAP4
 	select TWL4030_POWER if ARCH_OMAP3 || ARCH_OMAP4
 	select VFP
@@ -201,7 +202,6 @@ config MACH_OMAP3_PANDORA
 	depends on ARCH_OMAP3
 	default y
 	select OMAP_PACKAGE_CBB
-	select REGULATOR_FIXED_VOLTAGE if REGULATOR
 
 config MACH_NOKIA_N810
        bool

arch/arm/mach-pxa/ezx.c

@@ -889,6 +889,7 @@ static void __init e680_init(void)
 
 	pxa_set_keypad_info(&e680_keypad_platform_data);
 
+	pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
 	platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
 	platform_add_devices(ARRAY_AND_SIZE(e680_devices));
 }
@@ -956,6 +957,7 @@ static void __init a1200_init(void)
 
 	pxa_set_keypad_info(&a1200_keypad_platform_data);
 
+	pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
 	platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
 	platform_add_devices(ARRAY_AND_SIZE(a1200_devices));
 }
@@ -1148,6 +1150,7 @@ static void __init a910_init(void)
 		platform_device_register(&a910_camera);
 	}
 
+	pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
 	platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
 	platform_add_devices(ARRAY_AND_SIZE(a910_devices));
 }
@@ -1215,6 +1218,7 @@ static void __init e6_init(void)
 
 	pxa_set_keypad_info(&e6_keypad_platform_data);
 
+	pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
 	platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
 	platform_add_devices(ARRAY_AND_SIZE(e6_devices));
 }
@@ -1256,6 +1260,7 @@ static void __init e2_init(void)
 
 	pxa_set_keypad_info(&e2_keypad_platform_data);
 
+	pwm_add_table(ezx_pwm_lookup, ARRAY_SIZE(ezx_pwm_lookup));
 	platform_add_devices(ARRAY_AND_SIZE(ezx_devices));
 	platform_add_devices(ARRAY_AND_SIZE(e2_devices));
 }

arch/arm/mach-s3c24xx/pll-s3c2440-12000000.c

@@ -20,7 +20,7 @@
 #include <plat/cpu.h>
 #include <plat/cpu-freq-core.h>
 
-static struct cpufreq_frequency_table s3c2440_plls_12[] __initdata = {
+static struct cpufreq_frequency_table s3c2440_plls_12[] = {
 	{ .frequency = 75000000,	.driver_data = PLLVAL(0x75, 3, 3),  }, 	/* FVco 600.000000 */
 	{ .frequency = 80000000,	.driver_data = PLLVAL(0x98, 4, 3),  }, 	/* FVco 640.000000 */
 	{ .frequency = 90000000,	.driver_data = PLLVAL(0x70, 2, 3),  }, 	/* FVco 720.000000 */

arch/arm/mach-s3c24xx/pll-s3c2440-16934400.c

@@ -20,7 +20,7 @@
 #include <plat/cpu.h>
 #include <plat/cpu-freq-core.h>
 
-static struct cpufreq_frequency_table s3c2440_plls_169344[] __initdata = {
+static struct cpufreq_frequency_table s3c2440_plls_169344[] = {
 	{ .frequency = 78019200,	.driver_data = PLLVAL(121, 5, 3), 	}, 	/* FVco 624.153600 */
 	{ .frequency = 84067200,	.driver_data = PLLVAL(131, 5, 3), 	}, 	/* FVco 672.537600 */
 	{ .frequency = 90115200,	.driver_data = PLLVAL(141, 5, 3), 	}, 	/* FVco 720.921600 */

arch/arm/mm/context.c

@@ -165,13 +165,28 @@ static void flush_context(unsigned int cpu)
 		__flush_icache_all();
 }
 
-static int is_reserved_asid(u64 asid)
+static bool check_update_reserved_asid(u64 asid, u64 newasid)
 {
 	int cpu;
-	for_each_possible_cpu(cpu)
+	bool hit = false;
-		if (per_cpu(reserved_asids, cpu) == asid)
+
-			return 1;
+	/*
-	return 0;
+	 * Iterate over the set of reserved ASIDs looking for a match.
+	 * If we find one, then we can update our mm to use newasid
+	 * (i.e. the same ASID in the current generation) but we can't
+	 * exit the loop early, since we need to ensure that all copies
+	 * of the old ASID are updated to reflect the mm. Failure to do
+	 * so could result in us missing the reserved ASID in a future
+	 * generation.
+	 */
+	for_each_possible_cpu(cpu) {
+		if (per_cpu(reserved_asids, cpu) == asid) {
+			hit = true;
+			per_cpu(reserved_asids, cpu) = newasid;
+		}
+	}
+
+	return hit;
 }
 
 static u64 new_context(struct mm_struct *mm, unsigned int cpu)
@@ -181,12 +196,14 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 	u64 generation = atomic64_read(&asid_generation);
 
 	if (asid != 0) {
+		u64 newasid = generation | (asid & ~ASID_MASK);
+
 		/*
 		 * If our current ASID was active during a rollover, we
 		 * can continue to use it and this was just a false alarm.
 		 */
-		if (is_reserved_asid(asid))
+		if (check_update_reserved_asid(asid, newasid))
-			return generation | (asid & ~ASID_MASK);
+			return newasid;
 
 		/*
 		 * We had a valid ASID in a previous life, so try to re-use
@@ -194,7 +211,7 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 		 */
 		asid &= ~ASID_MASK;
 		if (!__test_and_set_bit(asid, asid_map))
-			goto bump_gen;
+			return newasid;
 	}
 
 	/*
@@ -216,11 +233,8 @@ static u64 new_context(struct mm_struct *mm, unsigned int cpu)
 
 	__set_bit(asid, asid_map);
 	cur_idx = asid;
-
-bump_gen:
-	asid |= generation;
 	cpumask_clear(mm_cpumask(mm));
-	return asid;
+	return asid | generation;
 }
 
 void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk)

arch/arm/mm/dma-mapping.c

@@ -1521,7 +1521,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 		return -ENOMEM;
 
 	for (count = 0, s = sg; count < (size >> PAGE_SHIFT); s = sg_next(s)) {
-		phys_addr_t phys = sg_phys(s) & PAGE_MASK;
+		phys_addr_t phys = page_to_phys(sg_page(s));
 		unsigned int len = PAGE_ALIGN(s->offset + s->length);
 
 		if (!is_coherent &&

arch/arm/mm/init.c

@@ -22,6 +22,7 @@
 #include <linux/memblock.h>
 #include <linux/dma-contiguous.h>
 #include <linux/sizes.h>
+#include <linux/stop_machine.h>
 
 #include <asm/cp15.h>
 #include <asm/mach-types.h>
@@ -627,12 +628,10 @@ static struct section_perm ro_perms[] = {
  * safe to be called with preemption disabled, as under stop_machine().
  */
 static inline void section_update(unsigned long addr, pmdval_t mask,
-				  pmdval_t prot)
+				  pmdval_t prot, struct mm_struct *mm)
 {
-	struct mm_struct *mm;
 	pmd_t *pmd;
 
-	mm = current->active_mm;
 	pmd = pmd_offset(pud_offset(pgd_offset(mm, addr), addr), addr);
 
 #ifdef CONFIG_ARM_LPAE
@@ -656,49 +655,82 @@ static inline bool arch_has_strict_perms(void)
 	return !!(get_cr() & CR_XP);
 }
 
-#define set_section_perms(perms, field)	{				\
+void set_section_perms(struct section_perm *perms, int n, bool set,
-	size_t i;							\
+			struct mm_struct *mm)
-	unsigned long addr;						\
+{
-									\
+	size_t i;
-	if (!arch_has_strict_perms())					\
+	unsigned long addr;
-		return;							\
+
-									\
+	if (!arch_has_strict_perms())
-	for (i = 0; i < ARRAY_SIZE(perms); i++) {			\
+		return;
-		if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) ||	\
+
-		    !IS_ALIGNED(perms[i].end, SECTION_SIZE)) {		\
+	for (i = 0; i < n; i++) {
-			pr_err("BUG: section %lx-%lx not aligned to %lx\n", \
+		if (!IS_ALIGNED(perms[i].start, SECTION_SIZE) ||
-				perms[i].start, perms[i].end,		\
+		    !IS_ALIGNED(perms[i].end, SECTION_SIZE)) {
-				SECTION_SIZE);				\
+			pr_err("BUG: section %lx-%lx not aligned to %lx\n",
-			continue;					\
+				perms[i].start, perms[i].end,
-		}							\
+				SECTION_SIZE);
-									\
+			continue;
-		for (addr = perms[i].start;				\
+		}
-		     addr < perms[i].end;				\
+
-		     addr += SECTION_SIZE)				\
+		for (addr = perms[i].start;
-			section_update(addr, perms[i].mask,		\
+		     addr < perms[i].end;
-				       perms[i].field);			\
+		     addr += SECTION_SIZE)
-	}								\
+			section_update(addr, perms[i].mask,
+				set ? perms[i].prot : perms[i].clear, mm);
+	}
+
 }
 
-static inline void fix_kernmem_perms(void)
+static void update_sections_early(struct section_perm perms[], int n)
 {
-	set_section_perms(nx_perms, prot);
+	struct task_struct *t, *s;
+
+	read_lock(&tasklist_lock);
+	for_each_process(t) {
+		if (t->flags & PF_KTHREAD)
+			continue;
+		for_each_thread(t, s)
+			set_section_perms(perms, n, true, s->mm);
+	}
+	read_unlock(&tasklist_lock);
+	set_section_perms(perms, n, true, current->active_mm);
+	set_section_perms(perms, n, true, &init_mm);
+}
+
+int __fix_kernmem_perms(void *unused)
+{
+	update_sections_early(nx_perms, ARRAY_SIZE(nx_perms));
+	return 0;
+}
+
+void fix_kernmem_perms(void)
+{
+	stop_machine(__fix_kernmem_perms, NULL, NULL);
 }
 
 #ifdef CONFIG_DEBUG_RODATA
+int __mark_rodata_ro(void *unused)
+{
+	update_sections_early(ro_perms, ARRAY_SIZE(ro_perms));
+	return 0;
+}
+
 void mark_rodata_ro(void)
 {
-	set_section_perms(ro_perms, prot);
+	stop_machine(__mark_rodata_ro, NULL, NULL);
 }
 
 void set_kernel_text_rw(void)
 {
-	set_section_perms(ro_perms, clear);
+	set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), false,
+				current->active_mm);
 }
 
 void set_kernel_text_ro(void)
 {
-	set_section_perms(ro_perms, prot);
+	set_section_perms(ro_perms, ARRAY_SIZE(ro_perms), true,
+				current->active_mm);
 }
 #endif /* CONFIG_DEBUG_RODATA */
 

arch/arm/mm/proc-v7.S

@@ -95,7 +95,7 @@ ENDPROC(cpu_v7_dcache_clean_area)
 .equ	cpu_v7_suspend_size, 4 * 9
 #ifdef CONFIG_ARM_CPU_SUSPEND
 ENTRY(cpu_v7_do_suspend)
-	stmfd	sp!, {r4 - r10, lr}
+	stmfd	sp!, {r4 - r11, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
 	mrc	p15, 0, r5, c13, c0, 3	@ User r/o thread ID
 	stmia	r0!, {r4 - r5}
@@ -112,7 +112,7 @@ ENTRY(cpu_v7_do_suspend)
 	mrc	p15, 0, r9, c1, c0, 1	@ Auxiliary control register
 	mrc	p15, 0, r10, c1, c0, 2	@ Co-processor access control
 	stmia	r0, {r5 - r11}
-	ldmfd	sp!, {r4 - r10, pc}
+	ldmfd	sp!, {r4 - r11, pc}
 ENDPROC(cpu_v7_do_suspend)
 
 ENTRY(cpu_v7_do_resume)

arch/arm64/boot/dts/freescale/fsl-ls2080a.dtsi

@@ -269,6 +269,7 @@
 			clock-frequency = <0>;	/* Updated by bootloader */
 			voltage-ranges = <1800 1800 3300 3300>;
 			sdhci,auto-cmd12;
+			little-endian;
 			bus-width = <4>;
 		};
 
@@ -277,6 +278,7 @@
 			reg = <0x0 0x2300000 0x0 0x10000>;
 			interrupts = <0 36 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -287,6 +289,7 @@
 			reg = <0x0 0x2310000 0x0 0x10000>;
 			interrupts = <0 36 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -297,6 +300,7 @@
 			reg = <0x0 0x2320000 0x0 0x10000>;
 			interrupts = <0 37 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;
@@ -307,6 +311,7 @@
 			reg = <0x0 0x2330000 0x0 0x10000>;
 			interrupts = <0 37 0x4>; /* Level high type */
 			gpio-controller;
+			little-endian;
 			#gpio-cells = <2>;
 			interrupt-controller;
 			#interrupt-cells = <2>;

arch/arm64/include/asm/arch_gicv3.h

@@ -77,6 +77,7 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/stringify.h>
+#include <asm/barrier.h>
 
 /*
  * Low-level accessors

arch/arm64/include/asm/pgtable.h

@@ -276,10 +276,14 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 	 * hardware updates of the pte (ptep_set_access_flags safely changes
 	 * valid ptes without going through an invalid entry).
 	 */
-	if (IS_ENABLED(CONFIG_DEBUG_VM) && IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
+	if (IS_ENABLED(CONFIG_ARM64_HW_AFDBM) &&
-	    pte_valid(*ptep)) {
+	    pte_valid(*ptep) && pte_valid(pte)) {
-		BUG_ON(!pte_young(pte));
+		VM_WARN_ONCE(!pte_young(pte),
-		BUG_ON(pte_write(*ptep) && !pte_dirty(pte));
+			     "%s: racy access flag clearing: 0x%016llx -> 0x%016llx",
+			     __func__, pte_val(*ptep), pte_val(pte));
+		VM_WARN_ONCE(pte_write(*ptep) && !pte_dirty(pte),
+			     "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx",
+			     __func__, pte_val(*ptep), pte_val(pte));
 	}
 
 	set_pte(ptep, pte);

arch/arm64/kernel/vmlinux.lds.S

@@ -5,6 +5,7 @@
  */
 
 #include <asm-generic/vmlinux.lds.h>
+#include <asm/cache.h>
 #include <asm/kernel-pgtable.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
@@ -140,7 +141,7 @@ SECTIONS
 		ARM_EXIT_KEEP(EXIT_DATA)
 	}
 
-	PERCPU_SECTION(64)
+	PERCPU_SECTION(L1_CACHE_BYTES)
 
 	. = ALIGN(PAGE_SIZE);
 	__init_end = .;
@@ -158,7 +159,7 @@ SECTIONS
 	. = ALIGN(PAGE_SIZE);
 	_data = .;
 	_sdata = .;
-	RW_DATA_SECTION(64, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
 	PECOFF_EDATA_PADDING
 	_edata = .;
 

arch/blackfin/kernel/perf_event.c

@@ -14,7 +14,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *
  * ppc:

arch/ia64/include/asm/unistd.h

@@ -11,7 +11,7 @@
 
 
 
-#define NR_syscalls			322 /* length of syscall table */
+#define NR_syscalls			323 /* length of syscall table */
 
 /*
  * The following defines stop scripts/checksyscalls.sh from complaining about

arch/ia64/include/uapi/asm/unistd.h

@@ -335,5 +335,6 @@
 #define __NR_userfaultfd		1343
 #define __NR_membarrier			1344
 #define __NR_kcmp			1345
+#define __NR_mlock2			1346
 
 #endif /* _UAPI_ASM_IA64_UNISTD_H */

arch/ia64/kernel/entry.S

@@ -1771,5 +1771,6 @@ sys_call_table:
 	data8 sys_userfaultfd
 	data8 sys_membarrier
 	data8 sys_kcmp				// 1345
+	data8 sys_mlock2
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls

arch/microblaze/kernel/dma.c

@@ -61,7 +61,8 @@ static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
 	/* FIXME this part of code is untested */
 	for_each_sg(sgl, sg, nents, i) {
 		sg->dma_address = sg_phys(sg);
-		__dma_sync(sg_phys(sg), sg->length, direction);
+		__dma_sync(page_to_phys(sg_page(sg)) + sg->offset,
+							sg->length, direction);
 	}
 
 	return nents;

arch/mips/mm/dma-default.c

@@ -145,7 +145,7 @@ static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
 
 	gfp = massage_gfp_flags(dev, gfp);
 
-	if (IS_ENABLED(CONFIG_DMA_CMA) && !(gfp & GFP_ATOMIC))
+	if (IS_ENABLED(CONFIG_DMA_CMA) && gfpflags_allow_blocking(gfp))
 		page = dma_alloc_from_contiguous(dev,
 					count, get_order(size));
 	if (!page)

arch/parisc/include/asm/pgtable.h

@@ -372,7 +372,8 @@ static inline pte_t pte_mkspecial(pte_t pte)	{ return pte; }
  */
 #ifdef CONFIG_HUGETLB_PAGE
 #define pte_huge(pte)           (pte_val(pte) & _PAGE_HUGE)
-#define pte_mkhuge(pte)         (__pte(pte_val(pte) | _PAGE_HUGE))
+#define pte_mkhuge(pte)         (__pte(pte_val(pte) | \
+				 (parisc_requires_coherency() ? 0 : _PAGE_HUGE)))
 #else
 #define pte_huge(pte)           (0)
 #define pte_mkhuge(pte)         (pte)

arch/parisc/include/uapi/asm/unistd.h

@@ -360,8 +360,9 @@
 #define __NR_execveat		(__NR_Linux + 342)
 #define __NR_membarrier		(__NR_Linux + 343)
 #define __NR_userfaultfd	(__NR_Linux + 344)
+#define __NR_mlock2		(__NR_Linux + 345)
 
-#define __NR_Linux_syscalls	(__NR_userfaultfd + 1)
+#define __NR_Linux_syscalls	(__NR_mlock2 + 1)
 
 
 #define __IGNORE_select		/* newselect */

arch/parisc/kernel/pci.c

@@ -171,24 +171,6 @@ void pcibios_set_master(struct pci_dev *dev)
 }
 
 
-void __init pcibios_init_bus(struct pci_bus *bus)
-{
-	struct pci_dev *dev = bus->self;
-	unsigned short bridge_ctl;
-
-	/* We deal only with pci controllers and pci-pci bridges. */
-	if (!dev || (dev->class >> 8) != PCI_CLASS_BRIDGE_PCI)
-		return;
-
-	/* PCI-PCI bridge - set the cache line and default latency
-	   (32) for primary and secondary buses. */
-	pci_write_config_byte(dev, PCI_SEC_LATENCY_TIMER, 32);
-
-	pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &bridge_ctl);
-	bridge_ctl |= PCI_BRIDGE_CTL_PARITY | PCI_BRIDGE_CTL_SERR;
-	pci_write_config_word(dev, PCI_BRIDGE_CONTROL, bridge_ctl);
-}
-
 /*
  * pcibios align resources() is called every time generic PCI code
  * wants to generate a new address. The process of looking for

arch/parisc/kernel/syscall_table.S

@@ -440,6 +440,7 @@
 	ENTRY_COMP(execveat)
 	ENTRY_SAME(membarrier)
 	ENTRY_SAME(userfaultfd)
+	ENTRY_SAME(mlock2)		/* 345 */
 
 
 .ifne (. - 90b) - (__NR_Linux_syscalls * (91b - 90b))

arch/powerpc/boot/dts/sbc8641d.dts

@@ -227,23 +227,15 @@
 				reg = <0x520 0x20>;
 
 				phy0: ethernet-phy@1f {
-					interrupt-parent = <&mpic>;
-					interrupts = <10 1>;
 					reg = <0x1f>;
 				};
 				phy1: ethernet-phy@0 {
-					interrupt-parent = <&mpic>;
-					interrupts = <10 1>;
 					reg = <0>;
 				};
 				phy2: ethernet-phy@1 {
-					interrupt-parent = <&mpic>;
-					interrupts = <10 1>;
 					reg = <1>;
 				};
 				phy3: ethernet-phy@2 {
-					interrupt-parent = <&mpic>;
-					interrupts = <10 1>;
 					reg = <2>;
 				};
 				tbi0: tbi-phy@11 {

arch/powerpc/include/asm/systbl.h

@@ -370,16 +370,16 @@ COMPAT_SYS(execveat)
 PPC64ONLY(switch_endian)
 SYSCALL_SPU(userfaultfd)
 SYSCALL_SPU(membarrier)
-SYSCALL(semop)
+SYSCALL(ni_syscall)
-SYSCALL(semget)
+SYSCALL(ni_syscall)
-COMPAT_SYS(semctl)
+SYSCALL(ni_syscall)
-COMPAT_SYS(semtimedop)
+SYSCALL(ni_syscall)
-COMPAT_SYS(msgsnd)
+SYSCALL(ni_syscall)
-COMPAT_SYS(msgrcv)
+SYSCALL(ni_syscall)
-SYSCALL(msgget)
+SYSCALL(ni_syscall)
-COMPAT_SYS(msgctl)
+SYSCALL(ni_syscall)
-COMPAT_SYS(shmat)
+SYSCALL(ni_syscall)
-SYSCALL(shmdt)
+SYSCALL(ni_syscall)
-SYSCALL(shmget)
+SYSCALL(ni_syscall)
-COMPAT_SYS(shmctl)
+SYSCALL(ni_syscall)
 SYSCALL(mlock2)

arch/powerpc/include/uapi/asm/unistd.h

@@ -388,18 +388,6 @@
 #define __NR_switch_endian	363
 #define __NR_userfaultfd	364
 #define __NR_membarrier		365
-#define __NR_semop		366
-#define __NR_semget		367
-#define __NR_semctl		368
-#define __NR_semtimedop		369
-#define __NR_msgsnd		370
-#define __NR_msgrcv		371
-#define __NR_msgget		372
-#define __NR_msgctl		373
-#define __NR_shmat		374
-#define __NR_shmdt		375
-#define __NR_shmget		376
-#define __NR_shmctl		377
 #define __NR_mlock2		378
 
 #endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */

arch/powerpc/kernel/eeh_driver.c

@@ -590,16 +590,10 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	eeh_ops->configure_bridge(pe);
 	eeh_pe_restore_bars(pe);
 
-	/*
+	/* Clear frozen state */
-	 * If it's PHB PE, the frozen state on all available PEs should have
-	 * been cleared by the PHB reset. Otherwise, we unfreeze the PE and its
-	 * child PEs because they might be in frozen state.
-	 */
-	if (!(pe->type & EEH_PE_PHB)) {
 	rc = eeh_clear_pe_frozen_state(pe, false);
 	if (rc)
 		return rc;
-	}
 
 	/* Give the system 5 seconds to finish running the user-space
 	 * hotplug shutdown scripts, e.g. ifdown for ethernet.  Yes,

arch/powerpc/kvm/book3s_hv.c

@@ -224,6 +224,12 @@ static void kvmppc_core_vcpu_put_hv(struct kvm_vcpu *vcpu)
 
 static void kvmppc_set_msr_hv(struct kvm_vcpu *vcpu, u64 msr)
 {
+	/*
+	 * Check for illegal transactional state bit combination
+	 * and if we find it, force the TS field to a safe state.
+	 */
+	if ((msr & MSR_TS_MASK) == MSR_TS_MASK)
+		msr &= ~MSR_TS_MASK;
 	vcpu->arch.shregs.msr = msr;
 	kvmppc_end_cede(vcpu);
 }

arch/powerpc/platforms/powernv/opal-irqchip.c

@@ -43,11 +43,34 @@ static unsigned int opal_irq_count;
 static unsigned int *opal_irqs;
 
 static void opal_handle_irq_work(struct irq_work *work);
-static __be64 last_outstanding_events;
+static u64 last_outstanding_events;
 static struct irq_work opal_event_irq_work = {
 	.func = opal_handle_irq_work,
 };
 
+void opal_handle_events(uint64_t events)
+{
+	int virq, hwirq = 0;
+	u64 mask = opal_event_irqchip.mask;
+
+	if (!in_irq() && (events & mask)) {
+		last_outstanding_events = events;
+		irq_work_queue(&opal_event_irq_work);
+		return;
+	}
+
+	while (events & mask) {
+		hwirq = fls64(events) - 1;
+		if (BIT_ULL(hwirq) & mask) {
+			virq = irq_find_mapping(opal_event_irqchip.domain,
+						hwirq);
+			if (virq)
+				generic_handle_irq(virq);
+		}
+		events &= ~BIT_ULL(hwirq);
+	}
+}
+
 static void opal_event_mask(struct irq_data *d)
 {
 	clear_bit(d->hwirq, &opal_event_irqchip.mask);
@@ -55,9 +78,21 @@ static void opal_event_mask(struct irq_data *d)
 
 static void opal_event_unmask(struct irq_data *d)
 {
+	__be64 events;
+
 	set_bit(d->hwirq, &opal_event_irqchip.mask);
 
-	opal_poll_events(&last_outstanding_events);
+	opal_poll_events(&events);
+	last_outstanding_events = be64_to_cpu(events);
+
+	/*
+	 * We can't just handle the events now with opal_handle_events().
+	 * If we did we would deadlock when opal_event_unmask() is called from
+	 * handle_level_irq() with the irq descriptor lock held, because
+	 * calling opal_handle_events() would call generic_handle_irq() and
+	 * then handle_level_irq() which would try to take the descriptor lock
+	 * again. Instead queue the events for later.
+	 */
 	if (last_outstanding_events & opal_event_irqchip.mask)
 		/* Need to retrigger the interrupt */
 		irq_work_queue(&opal_event_irq_work);
@@ -96,29 +131,6 @@ static int opal_event_map(struct irq_domain *d, unsigned int irq,
 	return 0;
 }
 
-void opal_handle_events(uint64_t events)
-{
-	int virq, hwirq = 0;
-	u64 mask = opal_event_irqchip.mask;
-
-	if (!in_irq() && (events & mask)) {
-		last_outstanding_events = events;
-		irq_work_queue(&opal_event_irq_work);
-		return;
-	}
-
-	while (events & mask) {
-		hwirq = fls64(events) - 1;
-		if (BIT_ULL(hwirq) & mask) {
-			virq = irq_find_mapping(opal_event_irqchip.domain,
-						hwirq);
-			if (virq)
-				generic_handle_irq(virq);
-		}
-		events &= ~BIT_ULL(hwirq);
-	}
-}
-
 static irqreturn_t opal_interrupt(int irq, void *data)
 {
 	__be64 events;
@@ -131,7 +143,7 @@ static irqreturn_t opal_interrupt(int irq, void *data)
 
 static void opal_handle_irq_work(struct irq_work *work)
 {
-	opal_handle_events(be64_to_cpu(last_outstanding_events));
+	opal_handle_events(last_outstanding_events);
 }
 
 static int opal_event_match(struct irq_domain *h, struct device_node *node,

arch/powerpc/platforms/powernv/opal.c

@@ -278,7 +278,7 @@ static void opal_handle_message(void)
 
 	/* Sanity check */
 	if (type >= OPAL_MSG_TYPE_MAX) {
-		pr_warning("%s: Unknown message type: %u\n", __func__, type);
+		pr_warn_once("%s: Unknown message type: %u\n", __func__, type);
 		return;
 	}
 	opal_message_do_notify(type, (void *)&msg);

arch/s390/kernel/dis.c

@@ -1920,16 +1920,23 @@ static int print_insn(char *buffer, unsigned char *code, unsigned long addr)
 			}
 			if (separator)
 				ptr += sprintf(ptr, "%c", separator);
+			/*
+			 * Use four '%' characters below because of the
+			 * following two conversions:
+			 *
+			 *  1) sprintf: %%%%r -> %%r
+			 *  2) printk : %%r   -> %r
+			 */
 			if (operand->flags & OPERAND_GPR)
-				ptr += sprintf(ptr, "%%r%i", value);
+				ptr += sprintf(ptr, "%%%%r%i", value);
 			else if (operand->flags & OPERAND_FPR)
-				ptr += sprintf(ptr, "%%f%i", value);
+				ptr += sprintf(ptr, "%%%%f%i", value);
 			else if (operand->flags & OPERAND_AR)
-				ptr += sprintf(ptr, "%%a%i", value);
+				ptr += sprintf(ptr, "%%%%a%i", value);
 			else if (operand->flags & OPERAND_CR)
-				ptr += sprintf(ptr, "%%c%i", value);
+				ptr += sprintf(ptr, "%%%%c%i", value);
 			else if (operand->flags & OPERAND_VR)
-				ptr += sprintf(ptr, "%%v%i", value);
+				ptr += sprintf(ptr, "%%%%v%i", value);
 			else if (operand->flags & OPERAND_PCREL)
 				ptr += sprintf(ptr, "%lx", (signed int) value
 								      + addr);

arch/sh/include/uapi/asm/unistd_64.h

@@ -278,7 +278,7 @@
 #define __NR_fsetxattr		256
 #define __NR_getxattr		257
 #define __NR_lgetxattr		258
-#define __NR_fgetxattr		269
+#define __NR_fgetxattr		259
 #define __NR_listxattr		260
 #define __NR_llistxattr		261
 #define __NR_flistxattr		262

arch/sh/kernel/perf_event.c

@@ -10,7 +10,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *
  * ppc:

arch/sparc/kernel/perf_event.c

@@ -9,7 +9,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/perf_event.h>

arch/tile/kernel/perf_event.c

@@ -21,7 +21,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  */

arch/um/Makefile

@@ -131,7 +131,7 @@ export LDS_ELF_FORMAT := $(ELF_FORMAT)
 # The wrappers will select whether using "malloc" or the kernel allocator.
 LINK_WRAPS = -Wl,--wrap,malloc -Wl,--wrap,free -Wl,--wrap,calloc
 
-LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt)) -lrt
+LD_FLAGS_CMDLINE = $(foreach opt,$(LDFLAGS),-Wl,$(opt))
 
 # Used by link-vmlinux.sh which has special support for um link
 export CFLAGS_vmlinux := $(LINK-y) $(LINK_WRAPS) $(LD_FLAGS_CMDLINE)

arch/um/drivers/net_user.c

@@ -249,21 +249,23 @@ void close_addr(unsigned char *addr, unsigned char *netmask, void *arg)
 
 char *split_if_spec(char *str, ...)
 {
-	char **arg, *end;
+	char **arg, *end, *ret = NULL;
 	va_list ap;
 
 	va_start(ap, str);
 	while ((arg = va_arg(ap, char **)) != NULL) {
 		if (*str == '\0')
-			return NULL;
+			goto out;
 		end = strchr(str, ',');
 		if (end != str)
 			*arg = str;
 		if (end == NULL)
-			return NULL;
+			goto out;
 		*end++ = '\0';
 		str = end;
 	}
+	ret = str;
+out:
 	va_end(ap);
-	return str;
+	return ret;
 }

arch/um/kernel/signal.c

@@ -69,7 +69,7 @@ void do_signal(struct pt_regs *regs)
 	struct ksignal ksig;
 	int handled_sig = 0;
 
-	while (get_signal(&ksig)) {
+	if (get_signal(&ksig)) {
 		handled_sig = 1;
 		/* Whee!  Actually deliver the signal.  */
 		handle_signal(&ksig, regs);

arch/x86/kernel/cpu/perf_event.c

@@ -5,7 +5,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  *

arch/x86/kernel/cpu/perf_event.h

@@ -5,7 +5,7 @@
  *  Copyright (C) 2008-2009 Red Hat, Inc., Ingo Molnar
  *  Copyright (C) 2009 Jaswinder Singh Rajput
  *  Copyright (C) 2009 Advanced Micro Devices, Inc., Robert Richter
- *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ *  Copyright (C) 2008-2009 Red Hat, Inc., Peter Zijlstra
  *  Copyright (C) 2009 Intel Corporation, <markus.t.metzger@intel.com>
  *  Copyright (C) 2009 Google, Inc., Stephane Eranian
  *
@@ -387,7 +387,7 @@ struct cpu_hw_events {
 /* Check flags and event code/umask, and set the HSW N/A flag */
 #define INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_NA(code, n) \
 	__EVENT_CONSTRAINT(code, n, 			\
-			  INTEL_ARCH_EVENT_MASK|INTEL_ARCH_EVENT_MASK, \
+			  INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_NA_HSW)
 
 
@@ -627,6 +627,7 @@ struct x86_perf_task_context {
 	u64 lbr_from[MAX_LBR_ENTRIES];
 	u64 lbr_to[MAX_LBR_ENTRIES];
 	u64 lbr_info[MAX_LBR_ENTRIES];
+	int tos;
 	int lbr_callstack_users;
 	int lbr_stack_state;
 };

arch/x86/kernel/cpu/perf_event_intel.c

@@ -232,7 +232,7 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */
-	INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.* */
+	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 	INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */
 	/* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */

arch/x86/kernel/cpu/perf_event_intel_cqm.c

@@ -298,7 +298,7 @@ static bool __match_event(struct perf_event *a, struct perf_event *b)
 static inline struct perf_cgroup *event_to_cgroup(struct perf_event *event)
 {
 	if (event->attach_state & PERF_ATTACH_TASK)
-		return perf_cgroup_from_task(event->hw.target);
+		return perf_cgroup_from_task(event->hw.target, event->ctx);
 
 	return event->cgrp;
 }

arch/x86/kernel/cpu/perf_event_intel_lbr.c

@@ -239,7 +239,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 	}
 
 	mask = x86_pmu.lbr_nr - 1;
-	tos = intel_pmu_lbr_tos();
+	tos = task_ctx->tos;
 	for (i = 0; i < tos; i++) {
 		lbr_idx = (tos - i) & mask;
 		wrmsrl(x86_pmu.lbr_from + lbr_idx, task_ctx->lbr_from[i]);
@@ -247,6 +247,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+	wrmsrl(x86_pmu.lbr_tos, tos);
 	task_ctx->lbr_stack_state = LBR_NONE;
 }
 
@@ -270,6 +271,7 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+	task_ctx->tos = tos;
 	task_ctx->lbr_stack_state = LBR_VALID;
 }
 

arch/x86/kernel/irq_work.c

@@ -1,7 +1,7 @@
 /*
  * x86 specific code for irq_work
  *
- * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
+ * Copyright (C) 2010 Red Hat, Inc., Peter Zijlstra
  */
 
 #include <linux/kernel.h>

arch/x86/kvm/cpuid.h

@@ -38,6 +38,14 @@ static inline bool guest_cpuid_has_xsave(struct kvm_vcpu *vcpu)
 	return best && (best->ecx & bit(X86_FEATURE_XSAVE));
 }
 
+static inline bool guest_cpuid_has_mtrr(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 1, 0);
+	return best && (best->edx & bit(X86_FEATURE_MTRR));
+}
+
 static inline bool guest_cpuid_has_tsc_adjust(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;

arch/x86/kvm/mtrr.c

@@ -120,14 +120,22 @@ static u8 mtrr_default_type(struct kvm_mtrr *mtrr_state)
 	return mtrr_state->deftype & IA32_MTRR_DEF_TYPE_TYPE_MASK;
 }
 
-static u8 mtrr_disabled_type(void)
+static u8 mtrr_disabled_type(struct kvm_vcpu *vcpu)
 {
 	/*
 	 * 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.
+	 *
+	 * However, virtual machines can be run with CPUID such that
+	 * there are no MTRRs.  In that case, the firmware will never
+	 * enable MTRRs and it is obviously undesirable to run the
+	 * guest entirely with UC memory and we use WB.
 	 */
+	if (guest_cpuid_has_mtrr(vcpu))
 		return MTRR_TYPE_UNCACHABLE;
+	else
+		return MTRR_TYPE_WRBACK;
 }
 
 /*
@@ -267,7 +275,7 @@ static int fixed_mtrr_addr_to_seg(u64 addr)
 
 	for (seg = 0; seg < seg_num; seg++) {
 		mtrr_seg = &fixed_seg_table[seg];
-		if (mtrr_seg->start >= addr && addr < mtrr_seg->end)
+		if (mtrr_seg->start <= addr && addr < mtrr_seg->end)
 			return seg;
 	}
 
@@ -300,7 +308,6 @@ static void var_mtrr_range(struct kvm_mtrr_range *range, u64 *start, u64 *end)
 	*start = range->base & PAGE_MASK;
 
 	mask = range->mask & PAGE_MASK;
-	mask |= ~0ULL << boot_cpu_data.x86_phys_bits;
 
 	/* This cannot overflow because writing to the reserved bits of
 	 * variable MTRRs causes a #GP.
@@ -356,10 +363,14 @@ static void set_var_mtrr_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	if (var_mtrr_range_is_valid(cur))
 		list_del(&mtrr_state->var_ranges[index].node);
 
+	/* Extend the mask with all 1 bits to the left, since those
+	 * bits must implicitly be 0.  The bits are then cleared
+	 * when reading them.
+	 */
 	if (!is_mtrr_mask)
 		cur->base = data;
 	else
-		cur->mask = data;
+		cur->mask = data | (-1LL << cpuid_maxphyaddr(vcpu));
 
 	/* add it to the list if it's enabled. */
 	if (var_mtrr_range_is_valid(cur)) {
@@ -426,6 +437,8 @@ int kvm_mtrr_get_msr(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 			*pdata = vcpu->arch.mtrr_state.var_ranges[index].base;
 		else
 			*pdata = vcpu->arch.mtrr_state.var_ranges[index].mask;
+
+		*pdata &= (1ULL << cpuid_maxphyaddr(vcpu)) - 1;
 	}
 
 	return 0;
@@ -670,7 +683,7 @@ u8 kvm_mtrr_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn)
 	}
 
 	if (iter.mtrr_disabled)
-		return mtrr_disabled_type();
+		return mtrr_disabled_type(vcpu);
 
 	/* not contained in any MTRRs. */
 	if (type == -1)

arch/x86/kvm/svm.c

@@ -3422,6 +3422,8 @@ static int handle_exit(struct kvm_vcpu *vcpu)
 	struct kvm_run *kvm_run = vcpu->run;
 	u32 exit_code = svm->vmcb->control.exit_code;
 
+	trace_kvm_exit(exit_code, vcpu, KVM_ISA_SVM);
+
 	if (!is_cr_intercept(svm, INTERCEPT_CR0_WRITE))
 		vcpu->arch.cr0 = svm->vmcb->save.cr0;
 	if (npt_enabled)
@@ -3892,8 +3894,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 	vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp;
 	vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip;
 
-	trace_kvm_exit(svm->vmcb->control.exit_code, vcpu, KVM_ISA_SVM);
-
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_before_handle_nmi(&svm->vcpu);