diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 15f79c2..0f5c3b4 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -866,6 +866,15 @@
 
 	dscc4.setup=	[NET]
 
+	dt_cpu_ftrs=	[PPC]
+			Format: {"off" | "known"}
+			Control how the dt_cpu_ftrs device-tree binding is
+			used for CPU feature discovery and setup (if it
+			exists).
+			off: Do not use it, fall back to legacy cpu table.
+			known: Do not pass through unknown features to guests
+			or userspace, only those that the kernel is aware of.
+
 	dump_apple_properties	[X86]
 			Dump name and content of EFI device properties on
 			x86 Macs.  Useful for driver authors to determine
diff --git a/Documentation/devicetree/bindings/usb/dwc2.txt b/Documentation/devicetree/bindings/usb/dwc2.txt
index 00bea03..fcf199b 100644
--- a/Documentation/devicetree/bindings/usb/dwc2.txt
+++ b/Documentation/devicetree/bindings/usb/dwc2.txt
@@ -10,6 +10,7 @@
   - "rockchip,rk3288-usb", "rockchip,rk3066-usb", "snps,dwc2": for rk3288 Soc;
   - "lantiq,arx100-usb": The DWC2 USB controller instance in Lantiq ARX SoCs;
   - "lantiq,xrx200-usb": The DWC2 USB controller instance in Lantiq XRX SoCs;
+  - "amlogic,meson8-usb": The DWC2 USB controller instance in Amlogic Meson8 SoCs;
   - "amlogic,meson8b-usb": The DWC2 USB controller instance in Amlogic Meson8b SoCs;
   - "amlogic,meson-gxbb-usb": The DWC2 USB controller instance in Amlogic S905 SoCs;
   - "amcc,dwc-otg": The DWC2 USB controller instance in AMCC Canyonlands 460EX SoCs;
diff --git a/MAINTAINERS b/MAINTAINERS
index 92139b6..09b5ab6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1172,7 +1172,7 @@
 
 ARM/CIRRUS LOGIC EP93XX ARM ARCHITECTURE
 M:	Hartley Sweeten <hsweeten@visionengravers.com>
-M:	Ryan Mallon <rmallon@gmail.com>
+M:	Alexander Sverdlin <alexander.sverdlin@gmail.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	arch/arm/mach-ep93xx/
@@ -1489,13 +1489,15 @@
 M:	Sebastian Hesselbarth <sebastian.hesselbarth@gmail.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-F:	arch/arm/mach-mvebu/
-F:	drivers/rtc/rtc-armada38x.c
 F:	arch/arm/boot/dts/armada*
 F:	arch/arm/boot/dts/kirkwood*
+F:	arch/arm/configs/mvebu_*_defconfig
+F:	arch/arm/mach-mvebu/
 F:	arch/arm64/boot/dts/marvell/armada*
 F:	drivers/cpufreq/mvebu-cpufreq.c
-F:	arch/arm/configs/mvebu_*_defconfig
+F:	drivers/irqchip/irq-armada-370-xp.c
+F:	drivers/irqchip/irq-mvebu-*
+F:	drivers/rtc/rtc-armada38x.c
 
 ARM/Marvell Berlin SoC support
 M:	Jisheng Zhang <jszhang@marvell.com>
@@ -1721,7 +1723,6 @@
 ARM/SAMSUNG EXYNOS ARM ARCHITECTURES
 M:	Kukjin Kim <kgene@kernel.org>
 M:	Krzysztof Kozlowski <krzk@kernel.org>
-R:	Javier Martinez Canillas <javier@osg.samsung.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
 Q:	https://patchwork.kernel.org/project/linux-samsung-soc/list/
@@ -1829,7 +1830,6 @@
 ARM/STI ARCHITECTURE
 M:	Patrice Chotard <patrice.chotard@st.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-L:	kernel@stlinux.com
 W:	http://www.stlinux.com
 S:	Maintained
 F:	arch/arm/mach-sti/
@@ -5622,7 +5622,7 @@
 
 GENWQE (IBM Generic Workqueue Card)
 M:	Frank Haverkamp <haver@linux.vnet.ibm.com>
-M:	Gabriel Krisman Bertazi <krisman@linux.vnet.ibm.com>
+M:	Guilherme G. Piccoli <gpiccoli@linux.vnet.ibm.com>
 S:	Supported
 F:	drivers/misc/genwqe/
 
@@ -5667,7 +5667,6 @@
 
 GPIO SUBSYSTEM
 M:	Linus Walleij <linus.walleij@linaro.org>
-M:	Alexandre Courbot <gnurou@gmail.com>
 L:	linux-gpio@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio.git
 S:	Maintained
@@ -11268,7 +11267,6 @@
 
 STI CEC DRIVER
 M:	Benjamin Gaignard <benjamin.gaignard@linaro.org>
-L:	kernel@stlinux.com
 S:	Maintained
 F:	drivers/staging/media/st-cec/
 F:	Documentation/devicetree/bindings/media/stih-cec.txt
@@ -11778,6 +11776,7 @@
 S:	Supported
 F:	arch/arm/mach-davinci/
 F:	drivers/i2c/busses/i2c-davinci.c
+F:	arch/arm/boot/dts/da850*
 
 TI DAVINCI SERIES MEDIA DRIVER
 M:	"Lad, Prabhakar" <prabhakar.csengg@gmail.com>
@@ -13861,7 +13860,7 @@
 F:	drivers/net/wireless/wl3501*
 
 WOLFSON MICROELECTRONICS DRIVERS
-L:	patches@opensource.wolfsonmicro.com
+L:	patches@opensource.cirrus.com
 T:	git https://github.com/CirrusLogic/linux-drivers.git
 W:	https://github.com/CirrusLogic/linux-drivers/wiki
 S:	Supported
diff --git a/arch/arm/boot/dts/bcm283x.dtsi b/arch/arm/boot/dts/bcm283x.dtsi
index 561f27d..9444a9a 100644
--- a/arch/arm/boot/dts/bcm283x.dtsi
+++ b/arch/arm/boot/dts/bcm283x.dtsi
@@ -3,6 +3,11 @@
 #include <dt-bindings/clock/bcm2835-aux.h>
 #include <dt-bindings/gpio/gpio.h>
 
+/* firmware-provided startup stubs live here, where the secondary CPUs are
+ * spinning.
+ */
+/memreserve/ 0x00000000 0x00001000;
+
 /* This include file covers the common peripherals and configuration between
  * bcm2835 and bcm2836 implementations, leaving the CPU configuration to
  * bcm2835.dtsi and bcm2836.dtsi.
diff --git a/arch/arm/boot/dts/keystone-k2l-netcp.dtsi b/arch/arm/boot/dts/keystone-k2l-netcp.dtsi
index b6f2682..66f615a 100644
--- a/arch/arm/boot/dts/keystone-k2l-netcp.dtsi
+++ b/arch/arm/boot/dts/keystone-k2l-netcp.dtsi
@@ -137,8 +137,8 @@
 	/* NetCP address range */
 	ranges = <0 0x26000000 0x1000000>;
 
-	clocks = <&clkpa>, <&clkcpgmac>, <&chipclk12>, <&clkosr>;
-	clock-names = "pa_clk", "ethss_clk", "cpts", "osr_clk";
+	clocks = <&clkpa>, <&clkcpgmac>, <&chipclk12>;
+	clock-names = "pa_clk", "ethss_clk", "cpts";
 	dma-coherent;
 
 	ti,navigator-dmas = <&dma_gbe 0>,
diff --git a/arch/arm/boot/dts/keystone-k2l.dtsi b/arch/arm/boot/dts/keystone-k2l.dtsi
index b58e7eb..1486504 100644
--- a/arch/arm/boot/dts/keystone-k2l.dtsi
+++ b/arch/arm/boot/dts/keystone-k2l.dtsi
@@ -232,6 +232,14 @@
 			};
 		};
 
+		osr: sram@70000000 {
+			compatible = "mmio-sram";
+			reg = <0x70000000 0x10000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			clocks = <&clkosr>;
+		};
+
 		dspgpio0: keystone_dsp_gpio@02620240 {
 			compatible = "ti,keystone-dsp-gpio";
 			gpio-controller;
diff --git a/arch/arm/boot/dts/versatile-pb.dts b/arch/arm/boot/dts/versatile-pb.dts
index 33a8eb2..06e2331 100644
--- a/arch/arm/boot/dts/versatile-pb.dts
+++ b/arch/arm/boot/dts/versatile-pb.dts
@@ -1,4 +1,4 @@
-#include <versatile-ab.dts>
+#include "versatile-ab.dts"
 
 / {
 	model = "ARM Versatile PB";
diff --git a/arch/arm/include/asm/device.h b/arch/arm/include/asm/device.h
index 36ec9c8..3234fe9 100644
--- a/arch/arm/include/asm/device.h
+++ b/arch/arm/include/asm/device.h
@@ -19,7 +19,8 @@
 #ifdef CONFIG_XEN
 	const struct dma_map_ops *dev_dma_ops;
 #endif
-	bool dma_coherent;
+	unsigned int dma_coherent:1;
+	unsigned int dma_ops_setup:1;
 };
 
 struct omap_device;
diff --git a/arch/arm/kvm/init.S b/arch/arm/kvm/init.S
index 570ed4a..5386528 100644
--- a/arch/arm/kvm/init.S
+++ b/arch/arm/kvm/init.S
@@ -104,7 +104,6 @@
 	@  - Write permission implies XN: disabled
 	@  - Instruction cache: enabled
 	@  - Data/Unified cache: enabled
-	@  - Memory alignment checks: enabled
 	@  - MMU: enabled (this code must be run from an identity mapping)
 	mrc	p15, 4, r0, c1, c0, 0	@ HSCR
 	ldr	r2, =HSCTLR_MASK
@@ -112,8 +111,8 @@
 	mrc	p15, 0, r1, c1, c0, 0	@ SCTLR
 	ldr	r2, =(HSCTLR_EE | HSCTLR_FI | HSCTLR_I | HSCTLR_C)
 	and	r1, r1, r2
- ARM(	ldr	r2, =(HSCTLR_M | HSCTLR_A)			)
- THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_A | HSCTLR_TE)		)
+ ARM(	ldr	r2, =(HSCTLR_M)					)
+ THUMB(	ldr	r2, =(HSCTLR_M | HSCTLR_TE)			)
 	orr	r1, r1, r2
 	orr	r0, r0, r1
 	mcr	p15, 4, r0, c1, c0, 0	@ HSCR
diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index 841e924..cbd959b 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -1,6 +1,7 @@
 menuconfig ARCH_AT91
 	bool "Atmel SoCs"
 	depends on ARCH_MULTI_V4T || ARCH_MULTI_V5 || ARCH_MULTI_V7
+	select ARM_CPU_SUSPEND if PM
 	select COMMON_CLK_AT91
 	select GPIOLIB
 	select PINCTRL
diff --git a/arch/arm/mach-davinci/pm.c b/arch/arm/mach-davinci/pm.c
index efb8035..b5cc05d 100644
--- a/arch/arm/mach-davinci/pm.c
+++ b/arch/arm/mach-davinci/pm.c
@@ -153,7 +153,8 @@
 	davinci_sram_suspend = sram_alloc(davinci_cpu_suspend_sz, NULL);
 	if (!davinci_sram_suspend) {
 		pr_err("PM: cannot allocate SRAM memory\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto no_sram_mem;
 	}
 
 	davinci_sram_push(davinci_sram_suspend, davinci_cpu_suspend,
@@ -161,6 +162,10 @@
 
 	suspend_set_ops(&davinci_pm_ops);
 
+	return 0;
+
+no_sram_mem:
+	iounmap(pm_config.ddrpsc_reg_base);
 no_ddrpsc_mem:
 	iounmap(pm_config.ddrpll_reg_base);
 no_ddrpll_mem:
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index c742dfd..bd83c53 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -2311,7 +2311,14 @@
 }
 EXPORT_SYMBOL_GPL(arm_iommu_attach_device);
 
-static void __arm_iommu_detach_device(struct device *dev)
+/**
+ * arm_iommu_detach_device
+ * @dev: valid struct device pointer
+ *
+ * Detaches the provided device from a previously attached map.
+ * This voids the dma operations (dma_map_ops pointer)
+ */
+void arm_iommu_detach_device(struct device *dev)
 {
 	struct dma_iommu_mapping *mapping;
 
@@ -2324,22 +2331,10 @@
 	iommu_detach_device(mapping->domain, dev);
 	kref_put(&mapping->kref, release_iommu_mapping);
 	to_dma_iommu_mapping(dev) = NULL;
+	set_dma_ops(dev, NULL);
 
 	pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev));
 }
-
-/**
- * arm_iommu_detach_device
- * @dev: valid struct device pointer
- *
- * Detaches the provided device from a previously attached map.
- * This voids the dma operations (dma_map_ops pointer)
- */
-void arm_iommu_detach_device(struct device *dev)
-{
-	__arm_iommu_detach_device(dev);
-	set_dma_ops(dev, NULL);
-}
 EXPORT_SYMBOL_GPL(arm_iommu_detach_device);
 
 static const struct dma_map_ops *arm_get_iommu_dma_map_ops(bool coherent)
@@ -2379,7 +2374,7 @@
 	if (!mapping)
 		return;
 
-	__arm_iommu_detach_device(dev);
+	arm_iommu_detach_device(dev);
 	arm_iommu_release_mapping(mapping);
 }
 
@@ -2430,9 +2425,13 @@
 		dev->dma_ops = xen_dma_ops;
 	}
 #endif
+	dev->archdata.dma_ops_setup = true;
 }
 
 void arch_teardown_dma_ops(struct device *dev)
 {
+	if (!dev->archdata.dma_ops_setup)
+		return;
+
 	arm_teardown_iommu_dma_ops(dev);
 }
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
index ac8df52..b4bc42e 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-master.dtsi
@@ -231,8 +231,7 @@
 			cpm_crypto: crypto@800000 {
 				compatible = "inside-secure,safexcel-eip197";
 				reg = <0x800000 0x200000>;
-				interrupts = <GIC_SPI 34 (IRQ_TYPE_EDGE_RISING
-				| IRQ_TYPE_LEVEL_HIGH)>,
+				interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 56 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
index 7740a75..6e20588 100644
--- a/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
+++ b/arch/arm64/boot/dts/marvell/armada-cp110-slave.dtsi
@@ -221,8 +221,7 @@
 			cps_crypto: crypto@800000 {
 				compatible = "inside-secure,safexcel-eip197";
 				reg = <0x800000 0x200000>;
-				interrupts = <GIC_SPI 34 (IRQ_TYPE_EDGE_RISING
-				| IRQ_TYPE_LEVEL_HIGH)>,
+				interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 278 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 279 IRQ_TYPE_LEVEL_HIGH>,
 					     <GIC_SPI 280 IRQ_TYPE_LEVEL_HIGH>,
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 65cdd87..97c123e 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -68,6 +68,7 @@
 CONFIG_PCIE_ARMADA_8K=y
 CONFIG_PCI_AARDVARK=y
 CONFIG_PCIE_RCAR=y
+CONFIG_PCIE_ROCKCHIP=m
 CONFIG_PCI_HOST_GENERIC=y
 CONFIG_PCI_XGENE=y
 CONFIG_ARM64_VA_BITS_48=y
@@ -208,6 +209,8 @@
 CONFIG_WL18XX=m
 CONFIG_WLCORE_SDIO=m
 CONFIG_INPUT_EVDEV=y
+CONFIG_KEYBOARD_ADC=m
+CONFIG_KEYBOARD_CROS_EC=y
 CONFIG_KEYBOARD_GPIO=y
 CONFIG_INPUT_MISC=y
 CONFIG_INPUT_PM8941_PWRKEY=y
@@ -263,6 +266,7 @@
 CONFIG_SPI_ORION=y
 CONFIG_SPI_PL022=y
 CONFIG_SPI_QUP=y
+CONFIG_SPI_ROCKCHIP=y
 CONFIG_SPI_S3C64XX=y
 CONFIG_SPI_SPIDEV=m
 CONFIG_SPMI=y
@@ -292,6 +296,7 @@
 CONFIG_CPU_THERMAL=y
 CONFIG_THERMAL_EMULATION=y
 CONFIG_EXYNOS_THERMAL=y
+CONFIG_ROCKCHIP_THERMAL=m
 CONFIG_WATCHDOG=y
 CONFIG_S3C2410_WATCHDOG=y
 CONFIG_MESON_GXBB_WATCHDOG=m
@@ -300,12 +305,14 @@
 CONFIG_BCM2835_WDT=y
 CONFIG_MFD_CROS_EC=y
 CONFIG_MFD_CROS_EC_I2C=y
+CONFIG_MFD_CROS_EC_SPI=y
 CONFIG_MFD_EXYNOS_LPASS=m
 CONFIG_MFD_HI655X_PMIC=y
 CONFIG_MFD_MAX77620=y
 CONFIG_MFD_SPMI_PMIC=y
 CONFIG_MFD_RK808=y
 CONFIG_MFD_SEC_CORE=y
+CONFIG_REGULATOR_FAN53555=y
 CONFIG_REGULATOR_FIXED_VOLTAGE=y
 CONFIG_REGULATOR_GPIO=y
 CONFIG_REGULATOR_HI655X=y
@@ -473,8 +480,10 @@
 CONFIG_EXTCON_USB_GPIO=y
 CONFIG_IIO=y
 CONFIG_EXYNOS_ADC=y
+CONFIG_ROCKCHIP_SARADC=m
 CONFIG_PWM=y
 CONFIG_PWM_BCM2835=m
+CONFIG_PWM_CROS_EC=m
 CONFIG_PWM_MESON=m
 CONFIG_PWM_ROCKCHIP=y
 CONFIG_PWM_SAMSUNG=y
@@ -484,6 +493,7 @@
 CONFIG_PHY_SUN4I_USB=y
 CONFIG_PHY_ROCKCHIP_INNO_USB2=y
 CONFIG_PHY_ROCKCHIP_EMMC=y
+CONFIG_PHY_ROCKCHIP_PCIE=m
 CONFIG_PHY_XGENE=y
 CONFIG_PHY_TEGRA_XUSB=y
 CONFIG_ARM_SCPI_PROTOCOL=y
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 15c142c..b4d13d9 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -286,6 +286,10 @@
 #define SCTLR_ELx_A	(1 << 1)
 #define SCTLR_ELx_M	1
 
+#define SCTLR_EL2_RES1	((1 << 4)  | (1 << 5)  | (1 << 11) | (1 << 16) | \
+			 (1 << 16) | (1 << 18) | (1 << 22) | (1 << 23) | \
+			 (1 << 28) | (1 << 29))
+
 #define SCTLR_ELx_FLAGS	(SCTLR_ELx_M | SCTLR_ELx_A | SCTLR_ELx_C | \
 			 SCTLR_ELx_SA | SCTLR_ELx_I)
 
diff --git a/arch/arm64/kvm/hyp-init.S b/arch/arm64/kvm/hyp-init.S
index 839425c..3f96155 100644
--- a/arch/arm64/kvm/hyp-init.S
+++ b/arch/arm64/kvm/hyp-init.S
@@ -106,10 +106,13 @@
 	tlbi	alle2
 	dsb	sy
 
-	mrs	x4, sctlr_el2
-	and	x4, x4, #SCTLR_ELx_EE	// preserve endianness of EL2
-	ldr	x5, =SCTLR_ELx_FLAGS
-	orr	x4, x4, x5
+	/*
+	 * Preserve all the RES1 bits while setting the default flags,
+	 * as well as the EE bit on BE. Drop the A flag since the compiler
+	 * is allowed to generate unaligned accesses.
+	 */
+	ldr	x4, =(SCTLR_EL2_RES1 | (SCTLR_ELx_FLAGS & ~SCTLR_ELx_A))
+CPU_BE(	orr	x4, x4, #SCTLR_ELx_EE)
 	msr	sctlr_el2, x4
 	isb
 
diff --git a/arch/arm64/kvm/vgic-sys-reg-v3.c b/arch/arm64/kvm/vgic-sys-reg-v3.c
index 79f37e3..6260b69 100644
--- a/arch/arm64/kvm/vgic-sys-reg-v3.c
+++ b/arch/arm64/kvm/vgic-sys-reg-v3.c
@@ -65,8 +65,8 @@
 		 * Here set VMCR.CTLR in ICC_CTLR_EL1 layout.
 		 * The vgic_set_vmcr() will convert to ICH_VMCR layout.
 		 */
-		vmcr.ctlr = val & ICC_CTLR_EL1_CBPR_MASK;
-		vmcr.ctlr |= val & ICC_CTLR_EL1_EOImode_MASK;
+		vmcr.cbpr = (val & ICC_CTLR_EL1_CBPR_MASK) >> ICC_CTLR_EL1_CBPR_SHIFT;
+		vmcr.eoim = (val & ICC_CTLR_EL1_EOImode_MASK) >> ICC_CTLR_EL1_EOImode_SHIFT;
 		vgic_set_vmcr(vcpu, &vmcr);
 	} else {
 		val = 0;
@@ -83,8 +83,8 @@
 		 * The VMCR.CTLR value is in ICC_CTLR_EL1 layout.
 		 * Extract it directly using ICC_CTLR_EL1 reg definitions.
 		 */
-		val |= vmcr.ctlr & ICC_CTLR_EL1_CBPR_MASK;
-		val |= vmcr.ctlr & ICC_CTLR_EL1_EOImode_MASK;
+		val |= (vmcr.cbpr << ICC_CTLR_EL1_CBPR_SHIFT) & ICC_CTLR_EL1_CBPR_MASK;
+		val |= (vmcr.eoim << ICC_CTLR_EL1_EOImode_SHIFT) & ICC_CTLR_EL1_EOImode_MASK;
 
 		p->regval = val;
 	}
@@ -135,7 +135,7 @@
 		p->regval = 0;
 
 	vgic_get_vmcr(vcpu, &vmcr);
-	if (!((vmcr.ctlr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT)) {
+	if (!vmcr.cbpr) {
 		if (p->is_write) {
 			vmcr.abpr = (p->regval & ICC_BPR1_EL1_MASK) >>
 				     ICC_BPR1_EL1_SHIFT;
diff --git a/arch/hexagon/mm/uaccess.c b/arch/hexagon/mm/uaccess.c
index ec90afd..c599eb1 100644
--- a/arch/hexagon/mm/uaccess.c
+++ b/arch/hexagon/mm/uaccess.c
@@ -37,15 +37,14 @@
 	long uncleared;
 
 	while (count > PAGE_SIZE) {
-		uncleared = __copy_to_user_hexagon(dest, &empty_zero_page,
-						PAGE_SIZE);
+		uncleared = raw_copy_to_user(dest, &empty_zero_page, PAGE_SIZE);
 		if (uncleared)
 			return count - (PAGE_SIZE - uncleared);
 		count -= PAGE_SIZE;
 		dest += PAGE_SIZE;
 	}
 	if (count)
-		count = __copy_to_user_hexagon(dest, &empty_zero_page, count);
+		count = raw_copy_to_user(dest, &empty_zero_page, count);
 
 	return count;
 }
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 83d2e0f..bf4391d 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -380,22 +380,6 @@
 
 menu "Kernel options"
 
-config PPC_DT_CPU_FTRS
-	bool "Device-tree based CPU feature discovery & setup"
-	depends on PPC_BOOK3S_64
-	default n
-	help
-	  This enables code to use a new device tree binding for describing CPU
-	  compatibility and features. Saying Y here will attempt to use the new
-	  binding if the firmware provides it. Currently only the skiboot
-	  firmware provides this binding.
-	  If you're not sure say Y.
-
-config PPC_CPUFEATURES_ENABLE_UNKNOWN
-	bool "cpufeatures pass through unknown features to guest/userspace"
-	depends on PPC_DT_CPU_FTRS
-	default y
-
 config HIGHMEM
 	bool "High memory support"
 	depends on PPC32
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index b4b5e6b..0c4e470 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -8,7 +8,7 @@
 #define H_PTE_INDEX_SIZE  9
 #define H_PMD_INDEX_SIZE  7
 #define H_PUD_INDEX_SIZE  9
-#define H_PGD_INDEX_SIZE  12
+#define H_PGD_INDEX_SIZE  9
 
 #ifndef __ASSEMBLY__
 #define H_PTE_TABLE_SIZE	(sizeof(pte_t) << H_PTE_INDEX_SIZE)
diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index c2d5095..d02ad93 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -214,7 +214,6 @@
 #define CPU_FTR_DAWR			LONG_ASM_CONST(0x0400000000000000)
 #define CPU_FTR_DABRX			LONG_ASM_CONST(0x0800000000000000)
 #define CPU_FTR_PMAO_BUG		LONG_ASM_CONST(0x1000000000000000)
-#define CPU_FTR_SUBCORE			LONG_ASM_CONST(0x2000000000000000)
 #define CPU_FTR_POWER9_DD1		LONG_ASM_CONST(0x4000000000000000)
 
 #ifndef __ASSEMBLY__
@@ -463,7 +462,7 @@
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | CPU_FTR_VMX_COPY | \
 	    CPU_FTR_DBELL | CPU_FTR_HAS_PPR | CPU_FTR_DAWR | \
-	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP | CPU_FTR_SUBCORE)
+	    CPU_FTR_ARCH_207S | CPU_FTR_TM_COMP)
 #define CPU_FTRS_POWER8E (CPU_FTRS_POWER8 | CPU_FTR_PMAO_BUG)
 #define CPU_FTRS_POWER8_DD1 (CPU_FTRS_POWER8 & ~CPU_FTR_DBELL)
 #define CPU_FTRS_POWER9 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index a2123f2..bb99b65 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -110,13 +110,18 @@
 #define TASK_SIZE_128TB (0x0000800000000000UL)
 #define TASK_SIZE_512TB (0x0002000000000000UL)
 
-#ifdef CONFIG_PPC_BOOK3S_64
+/*
+ * For now 512TB is only supported with book3s and 64K linux page size.
+ */
+#if defined(CONFIG_PPC_BOOK3S_64) && defined(CONFIG_PPC_64K_PAGES)
 /*
  * Max value currently used:
  */
-#define TASK_SIZE_USER64	TASK_SIZE_512TB
+#define TASK_SIZE_USER64		TASK_SIZE_512TB
+#define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_128TB
 #else
-#define TASK_SIZE_USER64	TASK_SIZE_64TB
+#define TASK_SIZE_USER64		TASK_SIZE_64TB
+#define DEFAULT_MAP_WINDOW_USER64	TASK_SIZE_64TB
 #endif
 
 /*
@@ -132,7 +137,7 @@
  * space during mmap's.
  */
 #define TASK_UNMAPPED_BASE_USER32 (PAGE_ALIGN(TASK_SIZE_USER32 / 4))
-#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(TASK_SIZE_128TB / 4))
+#define TASK_UNMAPPED_BASE_USER64 (PAGE_ALIGN(DEFAULT_MAP_WINDOW_USER64 / 4))
 
 #define TASK_UNMAPPED_BASE ((is_32bit_task()) ? \
 		TASK_UNMAPPED_BASE_USER32 : TASK_UNMAPPED_BASE_USER64 )
@@ -143,21 +148,15 @@
  * with 128TB and conditionally enable upto 512TB
  */
 #ifdef CONFIG_PPC_BOOK3S_64
-#define DEFAULT_MAP_WINDOW	((is_32bit_task()) ? \
-				 TASK_SIZE_USER32 : TASK_SIZE_128TB)
+#define DEFAULT_MAP_WINDOW	((is_32bit_task()) ?			\
+				 TASK_SIZE_USER32 : DEFAULT_MAP_WINDOW_USER64)
 #else
 #define DEFAULT_MAP_WINDOW	TASK_SIZE
 #endif
 
 #ifdef __powerpc64__
 
-#ifdef CONFIG_PPC_BOOK3S_64
-/* Limit stack to 128TB */
-#define STACK_TOP_USER64 TASK_SIZE_128TB
-#else
-#define STACK_TOP_USER64 TASK_SIZE_USER64
-#endif
-
+#define STACK_TOP_USER64 DEFAULT_MAP_WINDOW_USER64
 #define STACK_TOP_USER32 TASK_SIZE_USER32
 
 #define STACK_TOP (is_32bit_task() ? \
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 8b3b46b..3297715 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -44,8 +44,22 @@
 extern int sysfs_add_device_to_node(struct device *dev, int nid);
 extern void sysfs_remove_device_from_node(struct device *dev, int nid);
 
+static inline int early_cpu_to_node(int cpu)
+{
+	int nid;
+
+	nid = numa_cpu_lookup_table[cpu];
+
+	/*
+	 * Fall back to node 0 if nid is unset (it should be, except bugs).
+	 * This allows callers to safely do NODE_DATA(early_cpu_to_node(cpu)).
+	 */
+	return (nid < 0) ? 0 : nid;
+}
 #else
 
+static inline int early_cpu_to_node(int cpu) { return 0; }
+
 static inline void dump_numa_cpu_topology(void) {}
 
 static inline int sysfs_add_device_to_node(struct device *dev, int nid)
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index fcc7588..4c7656d 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -8,6 +8,7 @@
 #include <linux/export.h>
 #include <linux/init.h>
 #include <linux/jump_label.h>
+#include <linux/libfdt.h>
 #include <linux/memblock.h>
 #include <linux/printk.h>
 #include <linux/sched.h>
@@ -642,7 +643,6 @@
 	{"processor-control-facility", feat_enable_dbell, CPU_FTR_DBELL},
 	{"processor-control-facility-v3", feat_enable_dbell, CPU_FTR_DBELL},
 	{"processor-utilization-of-resources-register", feat_enable_purr, 0},
-	{"subcore", feat_enable, CPU_FTR_SUBCORE},
 	{"no-execute", feat_enable, 0},
 	{"strong-access-ordering", feat_enable, CPU_FTR_SAO},
 	{"cache-inhibited-large-page", feat_enable_large_ci, 0},
@@ -671,12 +671,24 @@
 	{"wait-v3", feat_enable, 0},
 };
 
-/* XXX: how to configure this? Default + boot time? */
-#ifdef CONFIG_PPC_CPUFEATURES_ENABLE_UNKNOWN
-#define CPU_FEATURE_ENABLE_UNKNOWN 1
-#else
-#define CPU_FEATURE_ENABLE_UNKNOWN 0
-#endif
+static bool __initdata using_dt_cpu_ftrs;
+static bool __initdata enable_unknown = true;
+
+static int __init dt_cpu_ftrs_parse(char *str)
+{
+	if (!str)
+		return 0;
+
+	if (!strcmp(str, "off"))
+		using_dt_cpu_ftrs = false;
+	else if (!strcmp(str, "known"))
+		enable_unknown = false;
+	else
+		return 1;
+
+	return 0;
+}
+early_param("dt_cpu_ftrs", dt_cpu_ftrs_parse);
 
 static void __init cpufeatures_setup_start(u32 isa)
 {
@@ -707,7 +719,7 @@
 		}
 	}
 
-	if (!known && CPU_FEATURE_ENABLE_UNKNOWN) {
+	if (!known && enable_unknown) {
 		if (!feat_try_enable_unknown(f)) {
 			pr_info("not enabling: %s (unknown and unsupported by kernel)\n",
 				f->name);
@@ -756,6 +768,26 @@
 		cur_cpu_spec->cpu_features, cur_cpu_spec->mmu_features);
 }
 
+static int __init disabled_on_cmdline(void)
+{
+	unsigned long root, chosen;
+	const char *p;
+
+	root = of_get_flat_dt_root();
+	chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
+	if (chosen == -FDT_ERR_NOTFOUND)
+		return false;
+
+	p = of_get_flat_dt_prop(chosen, "bootargs", NULL);
+	if (!p)
+		return false;
+
+	if (strstr(p, "dt_cpu_ftrs=off"))
+		return true;
+
+	return false;
+}
+
 static int __init fdt_find_cpu_features(unsigned long node, const char *uname,
 					int depth, void *data)
 {
@@ -766,8 +798,6 @@
 	return 0;
 }
 
-static bool __initdata using_dt_cpu_ftrs = false;
-
 bool __init dt_cpu_ftrs_in_use(void)
 {
 	return using_dt_cpu_ftrs;
@@ -775,6 +805,8 @@
 
 bool __init dt_cpu_ftrs_init(void *fdt)
 {
+	using_dt_cpu_ftrs = false;
+
 	/* Setup and verify the FDT, if it fails we just bail */
 	if (!early_init_dt_verify(fdt))
 		return false;
@@ -782,6 +814,9 @@
 	if (!of_scan_flat_dt(fdt_find_cpu_features, NULL))
 		return false;
 
+	if (disabled_on_cmdline())
+		return false;
+
 	cpufeatures_setup_cpu();
 
 	using_dt_cpu_ftrs = true;
@@ -1027,5 +1062,8 @@
 
 void __init dt_cpu_ftrs_scan(void)
 {
+	if (!using_dt_cpu_ftrs)
+		return;
+
 	of_scan_flat_dt(dt_cpu_ftrs_scan_callback, NULL);
 }
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index baae104..2ad725e 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1666,6 +1666,7 @@
 #ifdef CONFIG_VSX
 	current->thread.used_vsr = 0;
 #endif
+	current->thread.load_fp = 0;
 	memset(&current->thread.fp_state, 0, sizeof(current->thread.fp_state));
 	current->thread.fp_save_area = NULL;
 #ifdef CONFIG_ALTIVEC
@@ -1674,6 +1675,7 @@
 	current->thread.vr_save_area = NULL;
 	current->thread.vrsave = 0;
 	current->thread.used_vr = 0;
+	current->thread.load_vec = 0;
 #endif /* CONFIG_ALTIVEC */
 #ifdef CONFIG_SPE
 	memset(current->thread.evr, 0, sizeof(current->thread.evr));
@@ -1685,6 +1687,7 @@
 	current->thread.tm_tfhar = 0;
 	current->thread.tm_texasr = 0;
 	current->thread.tm_tfiar = 0;
+	current->thread.load_tm = 0;
 #endif /* CONFIG_PPC_TRANSACTIONAL_MEM */
 }
 EXPORT_SYMBOL(start_thread);
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 71dcda9..857129a 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -928,7 +928,7 @@
 
 #ifdef CONFIG_PPC_MM_SLICES
 #ifdef CONFIG_PPC64
-	init_mm.context.addr_limit = TASK_SIZE_128TB;
+	init_mm.context.addr_limit = DEFAULT_MAP_WINDOW_USER64;
 #else
 #error	"context.addr_limit not initialized."
 #endif
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index f35ff9d..a8c1f99 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -661,7 +661,7 @@
 
 static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align)
 {
-	return __alloc_bootmem_node(NODE_DATA(cpu_to_node(cpu)), size, align,
+	return __alloc_bootmem_node(NODE_DATA(early_cpu_to_node(cpu)), size, align,
 				    __pa(MAX_DMA_ADDRESS));
 }
 
@@ -672,7 +672,7 @@
 
 static int pcpu_cpu_distance(unsigned int from, unsigned int to)
 {
-	if (cpu_to_node(from) == cpu_to_node(to))
+	if (early_cpu_to_node(from) == early_cpu_to_node(to))
 		return LOCAL_DISTANCE;
 	else
 		return REMOTE_DISTANCE;
diff --git a/arch/powerpc/mm/mmu_context_book3s64.c b/arch/powerpc/mm/mmu_context_book3s64.c
index c6dca2a..a3edf81 100644
--- a/arch/powerpc/mm/mmu_context_book3s64.c
+++ b/arch/powerpc/mm/mmu_context_book3s64.c
@@ -99,7 +99,7 @@
 	 * mm->context.addr_limit. Default to max task size so that we copy the
 	 * default values to paca which will help us to handle slb miss early.
 	 */
-	mm->context.addr_limit = TASK_SIZE_128TB;
+	mm->context.addr_limit = DEFAULT_MAP_WINDOW_USER64;
 
 	/*
 	 * The old code would re-promote on fork, we don't do that when using
diff --git a/arch/powerpc/perf/power9-pmu.c b/arch/powerpc/perf/power9-pmu.c
index 018f8e9..bb28e1a 100644
--- a/arch/powerpc/perf/power9-pmu.c
+++ b/arch/powerpc/perf/power9-pmu.c
@@ -402,7 +402,7 @@
 	.name			= "POWER9",
 	.n_counter		= MAX_PMU_COUNTERS,
 	.add_fields		= ISA207_ADD_FIELDS,
-	.test_adder		= ISA207_TEST_ADDER,
+	.test_adder		= P9_DD1_TEST_ADDER,
 	.compute_mmcr		= isa207_compute_mmcr,
 	.config_bhrb		= power9_config_bhrb,
 	.bhrb_filter_map	= power9_bhrb_filter_map,
@@ -421,7 +421,7 @@
 	.name			= "POWER9",
 	.n_counter		= MAX_PMU_COUNTERS,
 	.add_fields		= ISA207_ADD_FIELDS,
-	.test_adder		= P9_DD1_TEST_ADDER,
+	.test_adder		= ISA207_TEST_ADDER,
 	.compute_mmcr		= isa207_compute_mmcr,
 	.config_bhrb		= power9_config_bhrb,
 	.bhrb_filter_map	= power9_bhrb_filter_map,
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index 33244e3..4fd64d3 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -59,6 +59,17 @@
 
 	  In case of doubt, say Y
 
+config PPC_DT_CPU_FTRS
+	bool "Device-tree based CPU feature discovery & setup"
+	depends on PPC_BOOK3S_64
+	default y
+	help
+	  This enables code to use a new device tree binding for describing CPU
+	  compatibility and features. Saying Y here will attempt to use the new
+	  binding if the firmware provides it. Currently only the skiboot
+	  firmware provides this binding.
+	  If you're not sure say Y.
+
 config UDBG_RTAS_CONSOLE
 	bool "RTAS based debug console"
 	depends on PPC_RTAS
diff --git a/arch/powerpc/platforms/cell/spufs/coredump.c b/arch/powerpc/platforms/cell/spufs/coredump.c
index e5a891a..84b7ac9 100644
--- a/arch/powerpc/platforms/cell/spufs/coredump.c
+++ b/arch/powerpc/platforms/cell/spufs/coredump.c
@@ -175,6 +175,8 @@
 	skip = roundup(cprm->pos - total + sz, 4) - cprm->pos;
 	if (!dump_skip(cprm, skip))
 		goto Eio;
+
+	rc = 0;
 out:
 	free_page((unsigned long)buf);
 	return rc;
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index 0babef1..8c61192 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -407,7 +407,13 @@
 
 static int subcore_init(void)
 {
-	if (!cpu_has_feature(CPU_FTR_SUBCORE))
+	unsigned pvr_ver;
+
+	pvr_ver = PVR_VER(mfspr(SPRN_PVR));
+
+	if (pvr_ver != PVR_POWER8 &&
+	    pvr_ver != PVR_POWER8E &&
+	    pvr_ver != PVR_POWER8NVL)
 		return 0;
 
 	/*
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index e104c71..1fb162b 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -124,6 +124,7 @@
 	for (i = 0; i < num_lmbs; i++) {
 		lmbs[i].base_addr = be64_to_cpu(lmbs[i].base_addr);
 		lmbs[i].drc_index = be32_to_cpu(lmbs[i].drc_index);
+		lmbs[i].aa_index = be32_to_cpu(lmbs[i].aa_index);
 		lmbs[i].flags = be32_to_cpu(lmbs[i].flags);
 	}
 
@@ -147,6 +148,7 @@
 	for (i = 0; i < num_lmbs; i++) {
 		lmbs[i].base_addr = cpu_to_be64(lmbs[i].base_addr);
 		lmbs[i].drc_index = cpu_to_be32(lmbs[i].drc_index);
+		lmbs[i].aa_index = cpu_to_be32(lmbs[i].aa_index);
 		lmbs[i].flags = cpu_to_be32(lmbs[i].flags);
 	}
 
diff --git a/arch/powerpc/sysdev/simple_gpio.c b/arch/powerpc/sysdev/simple_gpio.c
index ef470b47..6afddae2 100644
--- a/arch/powerpc/sysdev/simple_gpio.c
+++ b/arch/powerpc/sysdev/simple_gpio.c
@@ -75,7 +75,8 @@
 
 static void u8_gpio_save_regs(struct of_mm_gpio_chip *mm_gc)
 {
-	struct u8_gpio_chip *u8_gc = gpiochip_get_data(&mm_gc->gc);
+	struct u8_gpio_chip *u8_gc =
+		container_of(mm_gc, struct u8_gpio_chip, mm_gc);
 
 	u8_gc->data = in_8(mm_gc->regs);
 }
diff --git a/arch/s390/include/asm/kvm_host.h b/arch/s390/include/asm/kvm_host.h
index 426614a..65d07ac 100644
--- a/arch/s390/include/asm/kvm_host.h
+++ b/arch/s390/include/asm/kvm_host.h
@@ -541,7 +541,6 @@
 	struct mutex ais_lock;
 	u8 simm;
 	u8 nimm;
-	int ais_enabled;
 };
 
 struct kvm_hw_wp_info_arch {
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index caf15c8..2d120fe 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -2160,7 +2160,7 @@
 	struct kvm_s390_ais_req req;
 	int ret = 0;
 
-	if (!fi->ais_enabled)
+	if (!test_kvm_facility(kvm, 72))
 		return -ENOTSUPP;
 
 	if (copy_from_user(&req, (void __user *)attr->addr, sizeof(req)))
@@ -2204,7 +2204,7 @@
 	};
 	int ret = 0;
 
-	if (!fi->ais_enabled || !adapter->suppressible)
+	if (!test_kvm_facility(kvm, 72) || !adapter->suppressible)
 		return kvm_s390_inject_vm(kvm, &s390int);
 
 	mutex_lock(&fi->ais_lock);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 689ac48..f28e2e7 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -558,7 +558,6 @@
 		} else {
 			set_kvm_facility(kvm->arch.model.fac_mask, 72);
 			set_kvm_facility(kvm->arch.model.fac_list, 72);
-			kvm->arch.float_int.ais_enabled = 1;
 			r = 0;
 		}
 		mutex_unlock(&kvm->lock);
@@ -1533,7 +1532,6 @@
 	mutex_init(&kvm->arch.float_int.ais_lock);
 	kvm->arch.float_int.simm = 0;
 	kvm->arch.float_int.nimm = 0;
-	kvm->arch.float_int.ais_enabled = 0;
 	spin_lock_init(&kvm->arch.float_int.lock);
 	for (i = 0; i < FIRQ_LIST_COUNT; i++)
 		INIT_LIST_HEAD(&kvm->arch.float_int.lists[i]);
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index a70fd61..6f07744 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -255,6 +255,7 @@
 		break;
 
 	case 4: /* MediaGX/GXm or Geode GXM/GXLV/GX1 */
+	case 11: /* GX1 with inverted Device ID */
 #ifdef CONFIG_PCI
 	{
 		u32 vendor, device;
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index afdfd23..f522415 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -619,6 +619,9 @@
 
 	show_saved_mc();
 
+	/* initrd is going away, clear patch ptr. */
+	intel_ucode_patch = NULL;
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index da5c097..43e10d6 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -161,8 +161,8 @@
 			 */
 			rcu_irq_exit();
 			native_safe_halt();
-			rcu_irq_enter();
 			local_irq_disable();
+			rcu_irq_enter();
 		}
 	}
 	if (!n.halted)
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index a181ae7..59ca2ee 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -780,18 +780,20 @@
 static int move_to_next_stateful_cpuid_entry(struct kvm_vcpu *vcpu, int i)
 {
 	struct kvm_cpuid_entry2 *e = &vcpu->arch.cpuid_entries[i];
-	int j, nent = vcpu->arch.cpuid_nent;
+	struct kvm_cpuid_entry2 *ej;
+	int j = i;
+	int nent = vcpu->arch.cpuid_nent;
 
 	e->flags &= ~KVM_CPUID_FLAG_STATE_READ_NEXT;
 	/* when no next entry is found, the current entry[i] is reselected */
-	for (j = i + 1; ; j = (j + 1) % nent) {
-		struct kvm_cpuid_entry2 *ej = &vcpu->arch.cpuid_entries[j];
-		if (ej->function == e->function) {
-			ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
-			return j;
-		}
-	}
-	return 0; /* silence gcc, even though control never reaches here */
+	do {
+		j = (j + 1) % nent;
+		ej = &vcpu->arch.cpuid_entries[j];
+	} while (ej->function != e->function);
+
+	ej->flags |= KVM_CPUID_FLAG_STATE_READ_NEXT;
+
+	return j;
 }
 
 /* find an entry with matching function, matching index (if needed), and that
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 5d3376f..cb82259 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3698,12 +3698,15 @@
 	return kvm_setup_async_pf(vcpu, gva, kvm_vcpu_gfn_to_hva(vcpu, gfn), &arch);
 }
 
-static bool can_do_async_pf(struct kvm_vcpu *vcpu)
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu)
 {
 	if (unlikely(!lapic_in_kernel(vcpu) ||
 		     kvm_event_needs_reinjection(vcpu)))
 		return false;
 
+	if (is_guest_mode(vcpu))
+		return false;
+
 	return kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
@@ -3719,7 +3722,7 @@
 	if (!async)
 		return false; /* *pfn has correct page already */
 
-	if (!prefault && can_do_async_pf(vcpu)) {
+	if (!prefault && kvm_can_do_async_pf(vcpu)) {
 		trace_kvm_try_async_get_page(gva, gfn);
 		if (kvm_find_async_pf_gfn(vcpu, gfn)) {
 			trace_kvm_async_pf_doublefault(gva, gfn);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 2797580..330bf3a 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -76,6 +76,7 @@
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly,
 			     bool accessed_dirty);
+bool kvm_can_do_async_pf(struct kvm_vcpu *vcpu);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 9b4b5d6..ca5d2b9 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2425,7 +2425,7 @@
 	if (!(vmcs12->exception_bitmap & (1u << nr)))
 		return 0;
 
-	nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason,
+	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 			  vmcs_read32(VM_EXIT_INTR_INFO),
 			  vmcs_readl(EXIT_QUALIFICATION));
 	return 1;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a2cd099..87d3cb9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -8607,8 +8607,7 @@
 	if (!(vcpu->arch.apf.msr_val & KVM_ASYNC_PF_ENABLED))
 		return true;
 	else
-		return !kvm_event_needs_reinjection(vcpu) &&
-			kvm_x86_ops->interrupt_allowed(vcpu);
+		return kvm_can_do_async_pf(vcpu);
 }
 
 void kvm_arch_start_assignment(struct kvm *kvm)
diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c
index c8a32fb..78b2e0d 100644
--- a/block/bfq-cgroup.c
+++ b/block/bfq-cgroup.c
@@ -52,7 +52,7 @@
 BFQG_FLAG_FNS(empty)
 #undef BFQG_FLAG_FNS
 
-/* This should be called with the queue_lock held. */
+/* This should be called with the scheduler lock held. */
 static void bfqg_stats_update_group_wait_time(struct bfqg_stats *stats)
 {
 	unsigned long long now;
@@ -67,7 +67,7 @@
 	bfqg_stats_clear_waiting(stats);
 }
 
-/* This should be called with the queue_lock held. */
+/* This should be called with the scheduler lock held. */
 static void bfqg_stats_set_start_group_wait_time(struct bfq_group *bfqg,
 						 struct bfq_group *curr_bfqg)
 {
@@ -81,7 +81,7 @@
 	bfqg_stats_mark_waiting(stats);
 }
 
-/* This should be called with the queue_lock held. */
+/* This should be called with the scheduler lock held. */
 static void bfqg_stats_end_empty_time(struct bfqg_stats *stats)
 {
 	unsigned long long now;
@@ -203,12 +203,30 @@
 
 static void bfqg_get(struct bfq_group *bfqg)
 {
-	return blkg_get(bfqg_to_blkg(bfqg));
+	bfqg->ref++;
 }
 
 void bfqg_put(struct bfq_group *bfqg)
 {
-	return blkg_put(bfqg_to_blkg(bfqg));
+	bfqg->ref--;
+
+	if (bfqg->ref == 0)
+		kfree(bfqg);
+}
+
+static void bfqg_and_blkg_get(struct bfq_group *bfqg)
+{
+	/* see comments in bfq_bic_update_cgroup for why refcounting bfqg */
+	bfqg_get(bfqg);
+
+	blkg_get(bfqg_to_blkg(bfqg));
+}
+
+void bfqg_and_blkg_put(struct bfq_group *bfqg)
+{
+	bfqg_put(bfqg);
+
+	blkg_put(bfqg_to_blkg(bfqg));
 }
 
 void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
@@ -312,7 +330,11 @@
 	if (bfqq) {
 		bfqq->ioprio = bfqq->new_ioprio;
 		bfqq->ioprio_class = bfqq->new_ioprio_class;
-		bfqg_get(bfqg);
+		/*
+		 * Make sure that bfqg and its associated blkg do not
+		 * disappear before entity.
+		 */
+		bfqg_and_blkg_get(bfqg);
 	}
 	entity->parent = bfqg->my_entity; /* NULL for root group */
 	entity->sched_data = &bfqg->sched_data;
@@ -399,6 +421,8 @@
 		return NULL;
 	}
 
+	/* see comments in bfq_bic_update_cgroup for why refcounting */
+	bfqg_get(bfqg);
 	return &bfqg->pd;
 }
 
@@ -426,7 +450,7 @@
 	struct bfq_group *bfqg = pd_to_bfqg(pd);
 
 	bfqg_stats_exit(&bfqg->stats);
-	return kfree(bfqg);
+	bfqg_put(bfqg);
 }
 
 void bfq_pd_reset_stats(struct blkg_policy_data *pd)
@@ -496,9 +520,10 @@
  * Move @bfqq to @bfqg, deactivating it from its old group and reactivating
  * it on the new one.  Avoid putting the entity on the old group idle tree.
  *
- * Must be called under the queue lock; the cgroup owning @bfqg must
- * not disappear (by now this just means that we are called under
- * rcu_read_lock()).
+ * Must be called under the scheduler lock, to make sure that the blkg
+ * owning @bfqg does not disappear (see comments in
+ * bfq_bic_update_cgroup on guaranteeing the consistency of blkg
+ * objects).
  */
 void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		   struct bfq_group *bfqg)
@@ -519,16 +544,12 @@
 		bfq_deactivate_bfqq(bfqd, bfqq, false, false);
 	else if (entity->on_st)
 		bfq_put_idle_entity(bfq_entity_service_tree(entity), entity);
-	bfqg_put(bfqq_group(bfqq));
+	bfqg_and_blkg_put(bfqq_group(bfqq));
 
-	/*
-	 * Here we use a reference to bfqg.  We don't need a refcounter
-	 * as the cgroup reference will not be dropped, so that its
-	 * destroy() callback will not be invoked.
-	 */
 	entity->parent = bfqg->my_entity;
 	entity->sched_data = &bfqg->sched_data;
-	bfqg_get(bfqg);
+	/* pin down bfqg and its associated blkg  */
+	bfqg_and_blkg_get(bfqg);
 
 	if (bfq_bfqq_busy(bfqq)) {
 		bfq_pos_tree_add_move(bfqd, bfqq);
@@ -545,8 +566,9 @@
  * @bic: the bic to move.
  * @blkcg: the blk-cgroup to move to.
  *
- * Move bic to blkcg, assuming that bfqd->queue is locked; the caller
- * has to make sure that the reference to cgroup is valid across the call.
+ * Move bic to blkcg, assuming that bfqd->lock is held; which makes
+ * sure that the reference to cgroup is valid across the call (see
+ * comments in bfq_bic_update_cgroup on this issue)
  *
  * NOTE: an alternative approach might have been to store the current
  * cgroup in bfqq and getting a reference to it, reducing the lookup
@@ -604,6 +626,57 @@
 		goto out;
 
 	bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio));
+	/*
+	 * Update blkg_path for bfq_log_* functions. We cache this
+	 * path, and update it here, for the following
+	 * reasons. Operations on blkg objects in blk-cgroup are
+	 * protected with the request_queue lock, and not with the
+	 * lock that protects the instances of this scheduler
+	 * (bfqd->lock). This exposes BFQ to the following sort of
+	 * race.
+	 *
+	 * The blkg_lookup performed in bfq_get_queue, protected
+	 * through rcu, may happen to return the address of a copy of
+	 * the original blkg. If this is the case, then the
+	 * bfqg_and_blkg_get performed in bfq_get_queue, to pin down
+	 * the blkg, is useless: it does not prevent blk-cgroup code
+	 * from destroying both the original blkg and all objects
+	 * directly or indirectly referred by the copy of the
+	 * blkg.
+	 *
+	 * On the bright side, destroy operations on a blkg invoke, as
+	 * a first step, hooks of the scheduler associated with the
+	 * blkg. And these hooks are executed with bfqd->lock held for
+	 * BFQ. As a consequence, for any blkg associated with the
+	 * request queue this instance of the scheduler is attached
+	 * to, we are guaranteed that such a blkg is not destroyed, and
+	 * that all the pointers it contains are consistent, while we
+	 * are holding bfqd->lock. A blkg_lookup performed with
+	 * bfqd->lock held then returns a fully consistent blkg, which
+	 * remains consistent until this lock is held.
+	 *
+	 * Thanks to the last fact, and to the fact that: (1) bfqg has
+	 * been obtained through a blkg_lookup in the above
+	 * assignment, and (2) bfqd->lock is being held, here we can
+	 * safely use the policy data for the involved blkg (i.e., the
+	 * field bfqg->pd) to get to the blkg associated with bfqg,
+	 * and then we can safely use any field of blkg. After we
+	 * release bfqd->lock, even just getting blkg through this
+	 * bfqg may cause dangling references to be traversed, as
+	 * bfqg->pd may not exist any more.
+	 *
+	 * In view of the above facts, here we cache, in the bfqg, any
+	 * blkg data we may need for this bic, and for its associated
+	 * bfq_queue. As of now, we need to cache only the path of the
+	 * blkg, which is used in the bfq_log_* functions.
+	 *
+	 * Finally, note that bfqg itself needs to be protected from
+	 * destruction on the blkg_free of the original blkg (which
+	 * invokes bfq_pd_free). We use an additional private
+	 * refcounter for bfqg, to let it disappear only after no
+	 * bfq_queue refers to it any longer.
+	 */
+	blkg_path(bfqg_to_blkg(bfqg), bfqg->blkg_path, sizeof(bfqg->blkg_path));
 	bic->blkcg_serial_nr = serial_nr;
 out:
 	rcu_read_unlock();
@@ -640,8 +713,6 @@
  * @bfqd: the device data structure with the root group.
  * @bfqg: the group to move from.
  * @st: the service tree with the entities.
- *
- * Needs queue_lock to be taken and reference to be valid over the call.
  */
 static void bfq_reparent_active_entities(struct bfq_data *bfqd,
 					 struct bfq_group *bfqg,
@@ -692,8 +763,7 @@
 		/*
 		 * The idle tree may still contain bfq_queues belonging
 		 * to exited task because they never migrated to a different
-		 * cgroup from the one being destroyed now.  No one else
-		 * can access them so it's safe to act without any lock.
+		 * cgroup from the one being destroyed now.
 		 */
 		bfq_flush_idle_tree(st);
 
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 08ce450..ed93da2 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -3665,7 +3665,7 @@
 
 	kmem_cache_free(bfq_pool, bfqq);
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
-	bfqg_put(bfqg);
+	bfqg_and_blkg_put(bfqg);
 #endif
 }
 
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index ae783c0..5c3bf98 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -759,6 +759,12 @@
 	/* must be the first member */
 	struct blkg_policy_data pd;
 
+	/* cached path for this blkg (see comments in bfq_bic_update_cgroup) */
+	char blkg_path[128];
+
+	/* reference counter (see comments in bfq_bic_update_cgroup) */
+	int ref;
+
 	struct bfq_entity entity;
 	struct bfq_sched_data sched_data;
 
@@ -838,7 +844,7 @@
 struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
 struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
-void bfqg_put(struct bfq_group *bfqg);
+void bfqg_and_blkg_put(struct bfq_group *bfqg);
 
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
 extern struct cftype bfq_blkcg_legacy_files[];
@@ -910,20 +916,13 @@
 struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
 
 #define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	do {			\
-	char __pbuf[128];						\
-									\
-	blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \
-	blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid, \
+	blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid,\
 			bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
-			  __pbuf, ##args);				\
+			bfqq_group(bfqq)->blkg_path, ##args);		\
 } while (0)
 
-#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)	do {			\
-	char __pbuf[128];						\
-									\
-	blkg_path(bfqg_to_blkg(bfqg), __pbuf, sizeof(__pbuf));		\
-	blk_add_trace_msg((bfqd)->queue, "%s " fmt, __pbuf, ##args);	\
-} while (0)
+#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)	\
+	blk_add_trace_msg((bfqd)->queue, "%s " fmt, (bfqg)->blkg_path, ##args)
 
 #else /* CONFIG_BFQ_GROUP_IOSCHED */
 
diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 5384713..b5009a8 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -175,6 +175,9 @@
 	if (bio_op(bio) != REQ_OP_READ && bio_op(bio) != REQ_OP_WRITE)
 		return false;
 
+	if (!bio_sectors(bio))
+		return false;
+
 	/* Already protected? */
 	if (bio_integrity(bio))
 		return false;
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 1bccced..bb66c96 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1461,22 +1461,28 @@
 	return blk_tag_to_qc_t(rq->internal_tag, hctx->queue_num, true);
 }
 
-static void __blk_mq_try_issue_directly(struct request *rq, blk_qc_t *cookie,
-				      bool may_sleep)
+static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
+					struct request *rq,
+					blk_qc_t *cookie, bool may_sleep)
 {
 	struct request_queue *q = rq->q;
 	struct blk_mq_queue_data bd = {
 		.rq = rq,
 		.last = true,
 	};
-	struct blk_mq_hw_ctx *hctx;
 	blk_qc_t new_cookie;
 	int ret;
+	bool run_queue = true;
+
+	if (blk_mq_hctx_stopped(hctx)) {
+		run_queue = false;
+		goto insert;
+	}
 
 	if (q->elevator)
 		goto insert;
 
-	if (!blk_mq_get_driver_tag(rq, &hctx, false))
+	if (!blk_mq_get_driver_tag(rq, NULL, false))
 		goto insert;
 
 	new_cookie = request_to_qc_t(hctx, rq);
@@ -1500,7 +1506,7 @@
 
 	__blk_mq_requeue_request(rq);
 insert:
-	blk_mq_sched_insert_request(rq, false, true, false, may_sleep);
+	blk_mq_sched_insert_request(rq, false, run_queue, false, may_sleep);
 }
 
 static void blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
@@ -1508,7 +1514,7 @@
 {
 	if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
 		rcu_read_lock();
-		__blk_mq_try_issue_directly(rq, cookie, false);
+		__blk_mq_try_issue_directly(hctx, rq, cookie, false);
 		rcu_read_unlock();
 	} else {
 		unsigned int srcu_idx;
@@ -1516,7 +1522,7 @@
 		might_sleep();
 
 		srcu_idx = srcu_read_lock(&hctx->queue_rq_srcu);
-		__blk_mq_try_issue_directly(rq, cookie, true);
+		__blk_mq_try_issue_directly(hctx, rq, cookie, true);
 		srcu_read_unlock(&hctx->queue_rq_srcu, srcu_idx);
 	}
 }
@@ -1619,9 +1625,12 @@
 
 		blk_mq_put_ctx(data.ctx);
 
-		if (same_queue_rq)
+		if (same_queue_rq) {
+			data.hctx = blk_mq_map_queue(q,
+					same_queue_rq->mq_ctx->cpu);
 			blk_mq_try_issue_directly(data.hctx, same_queue_rq,
 					&cookie);
+		}
 	} else if (q->nr_hw_queues > 1 && is_sync) {
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index fc13dd0..a7285bf 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -27,6 +27,13 @@
 #define MIN_THROTL_IOPS (10)
 #define DFL_LATENCY_TARGET (-1L)
 #define DFL_IDLE_THRESHOLD (0)
+#define DFL_HD_BASELINE_LATENCY (4000L) /* 4ms */
+#define LATENCY_FILTERED_SSD (0)
+/*
+ * For HD, very small latency comes from sequential IO. Such IO is helpless to
+ * help determine if its IO is impacted by others, hence we ignore the IO
+ */
+#define LATENCY_FILTERED_HD (1000L) /* 1ms */
 
 #define SKIP_LATENCY (((u64)1) << BLK_STAT_RES_SHIFT)
 
@@ -212,6 +219,7 @@
 	struct avg_latency_bucket avg_buckets[LATENCY_BUCKET_SIZE];
 	struct latency_bucket __percpu *latency_buckets;
 	unsigned long last_calculate_time;
+	unsigned long filtered_latency;
 
 	bool track_bio_latency;
 };
@@ -698,7 +706,7 @@
 static void throtl_schedule_pending_timer(struct throtl_service_queue *sq,
 					  unsigned long expires)
 {
-	unsigned long max_expire = jiffies + 8 * sq_to_tg(sq)->td->throtl_slice;
+	unsigned long max_expire = jiffies + 8 * sq_to_td(sq)->throtl_slice;
 
 	/*
 	 * Since we are adjusting the throttle limit dynamically, the sleep
@@ -2281,7 +2289,7 @@
 		throtl_track_latency(tg->td, blk_stat_size(&bio->bi_issue_stat),
 			bio_op(bio), lat);
 
-	if (tg->latency_target) {
+	if (tg->latency_target && lat >= tg->td->filtered_latency) {
 		int bucket;
 		unsigned int threshold;
 
@@ -2417,14 +2425,20 @@
 void blk_throtl_register_queue(struct request_queue *q)
 {
 	struct throtl_data *td;
+	int i;
 
 	td = q->td;
 	BUG_ON(!td);
 
-	if (blk_queue_nonrot(q))
+	if (blk_queue_nonrot(q)) {
 		td->throtl_slice = DFL_THROTL_SLICE_SSD;
-	else
+		td->filtered_latency = LATENCY_FILTERED_SSD;
+	} else {
 		td->throtl_slice = DFL_THROTL_SLICE_HD;
+		td->filtered_latency = LATENCY_FILTERED_HD;
+		for (i = 0; i < LATENCY_BUCKET_SIZE; i++)
+			td->avg_buckets[i].latency = DFL_HD_BASELINE_LATENCY;
+	}
 #ifndef CONFIG_BLK_DEV_THROTTLING_LOW
 	/* if no low limit, use previous default */
 	td->throtl_slice = DFL_THROTL_SLICE_HD;
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index c5fecf9..797b28d 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -666,14 +666,6 @@
 	int ret = -ENODEV;
 	struct fwnode_handle *iort_fwnode;
 
-	/*
-	 * If we already translated the fwspec there
-	 * is nothing left to do, return the iommu_ops.
-	 */
-	ops = iort_fwspec_iommu_ops(dev->iommu_fwspec);
-	if (ops)
-		return ops;
-
 	if (node) {
 		iort_fwnode = iort_get_fwnode(node);
 		if (!iort_fwnode)
@@ -735,6 +727,14 @@
 	u32 streamid = 0;
 	int err;
 
+	/*
+	 * If we already translated the fwspec there
+	 * is nothing left to do, return the iommu_ops.
+	 */
+	ops = iort_fwspec_iommu_ops(dev->iommu_fwspec);
+	if (ops)
+		return ops;
+
 	if (dev_is_pci(dev)) {
 		struct pci_bus *bus = to_pci_dev(dev)->bus;
 		u32 rid;
@@ -782,6 +782,12 @@
 	if (err)
 		ops = ERR_PTR(err);
 
+	/* Ignore all other errors apart from EPROBE_DEFER */
+	if (IS_ERR(ops) && (PTR_ERR(ops) != -EPROBE_DEFER)) {
+		dev_dbg(dev, "Adding to IOMMU failed: %ld\n", PTR_ERR(ops));
+		ops = NULL;
+	}
+
 	return ops;
 }
 
diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index a9a9ab3..d42eeef 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -782,7 +782,7 @@
 	if ((battery->state & ACPI_BATTERY_STATE_CRITICAL) ||
 	    (test_bit(ACPI_BATTERY_ALARM_PRESENT, &battery->flags) &&
             (battery->capacity_now <= battery->alarm)))
-		pm_wakeup_hard_event(&battery->device->dev);
+		pm_wakeup_event(&battery->device->dev, 0);
 
 	return result;
 }
diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 9ad8cdb..e19f530 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -217,7 +217,7 @@
 	}
 
 	if (state)
-		pm_wakeup_hard_event(&device->dev);
+		pm_wakeup_event(&device->dev, 0);
 
 	ret = blocking_notifier_call_chain(&acpi_lid_notifier, state, device);
 	if (ret == NOTIFY_DONE)
@@ -402,7 +402,7 @@
 		} else {
 			int keycode;
 
-			pm_wakeup_hard_event(&device->dev);
+			pm_wakeup_event(&device->dev, 0);
 			if (button->suspended)
 				break;
 
@@ -534,7 +534,6 @@
 		lid_device = device;
 	}
 
-	device_init_wakeup(&device->dev, true);
 	printk(KERN_INFO PREFIX "%s [%s]\n", name, acpi_device_bid(device));
 	return 0;
 
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 798d500..993fd31 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -24,7 +24,6 @@
 #include <linux/pm_qos.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_runtime.h>
-#include <linux/suspend.h>
 
 #include "internal.h"
 
@@ -400,7 +399,7 @@
 	mutex_lock(&acpi_pm_notifier_lock);
 
 	if (adev->wakeup.flags.notifier_present) {
-		pm_wakeup_ws_event(adev->wakeup.ws, 0, true);
+		__pm_wakeup_event(adev->wakeup.ws, 0);
 		if (adev->wakeup.context.work.func)
 			queue_pm_work(&adev->wakeup.context.work);
 	}
diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index e39ec7b..3a10d757 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1371,8 +1371,8 @@
 	iort_set_dma_mask(dev);
 
 	iommu = iort_iommu_configure(dev);
-	if (IS_ERR(iommu))
-		return PTR_ERR(iommu);
+	if (IS_ERR(iommu) && PTR_ERR(iommu) == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
 
 	size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
 	/*
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index a6574d6..097d630 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -663,40 +663,14 @@
 	acpi_os_wait_events_complete();
 	if (acpi_sci_irq_valid())
 		enable_irq_wake(acpi_sci_irq);
-
 	return 0;
 }
 
-static void acpi_freeze_wake(void)
-{
-	/*
-	 * If IRQD_WAKEUP_ARMED is not set for the SCI at this point, it means
-	 * that the SCI has triggered while suspended, so cancel the wakeup in
-	 * case it has not been a wakeup event (the GPEs will be checked later).
-	 */
-	if (acpi_sci_irq_valid() &&
-	    !irqd_is_wakeup_armed(irq_get_irq_data(acpi_sci_irq)))
-		pm_system_cancel_wakeup();
-}
-
-static void acpi_freeze_sync(void)
-{
-	/*
-	 * Process all pending events in case there are any wakeup ones.
-	 *
-	 * The EC driver uses the system workqueue, so that one needs to be
-	 * flushed too.
-	 */
-	acpi_os_wait_events_complete();
-	flush_scheduled_work();
-}
-
 static void acpi_freeze_restore(void)
 {
 	acpi_disable_wakeup_devices(ACPI_STATE_S0);
 	if (acpi_sci_irq_valid())
 		disable_irq_wake(acpi_sci_irq);
-
 	acpi_enable_all_runtime_gpes();
 }
 
@@ -708,8 +682,6 @@
 static const struct platform_freeze_ops acpi_freeze_ops = {
 	.begin = acpi_freeze_begin,
 	.prepare = acpi_freeze_prepare,
-	.wake = acpi_freeze_wake,
-	.sync = acpi_freeze_sync,
 	.restore = acpi_freeze_restore,
 	.end = acpi_freeze_end,
 };
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index e987a6f..9faee1c 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1091,6 +1091,11 @@
 	if (async_error)
 		goto Complete;
 
+	if (pm_wakeup_pending()) {
+		async_error = -EBUSY;
+		goto Complete;
+	}
+
 	if (dev->power.syscore || dev->power.direct_complete)
 		goto Complete;
 
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index 9c36b27..c313b60 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -28,8 +28,8 @@
 /* First wakeup IRQ seen by the kernel in the last cycle. */
 unsigned int pm_wakeup_irq __read_mostly;
 
-/* If greater than 0 and the system is suspending, terminate the suspend. */
-static atomic_t pm_abort_suspend __read_mostly;
+/* If set and the system is suspending, terminate the suspend. */
+static bool pm_abort_suspend __read_mostly;
 
 /*
  * Combined counters of registered wakeup events and wakeup events in progress.
@@ -855,26 +855,20 @@
 		pm_print_active_wakeup_sources();
 	}
 
-	return ret || atomic_read(&pm_abort_suspend) > 0;
+	return ret || pm_abort_suspend;
 }
 
 void pm_system_wakeup(void)
 {
-	atomic_inc(&pm_abort_suspend);
+	pm_abort_suspend = true;
 	freeze_wake();
 }
 EXPORT_SYMBOL_GPL(pm_system_wakeup);
 
-void pm_system_cancel_wakeup(void)
+void pm_wakeup_clear(void)
 {
-	atomic_dec(&pm_abort_suspend);
-}
-
-void pm_wakeup_clear(bool reset)
-{
+	pm_abort_suspend = false;
 	pm_wakeup_irq = 0;
-	if (reset)
-		atomic_set(&pm_abort_suspend, 0);
 }
 
 void pm_system_irq_wakeup(unsigned int irq_number)
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 28d9329..ebbd0c3 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -608,6 +608,9 @@
  */
 static int loop_flush(struct loop_device *lo)
 {
+	/* loop not yet configured, no running thread, nothing to flush */
+	if (lo->lo_state != Lo_bound)
+		return 0;
 	return loop_switch(lo, NULL);
 }
 
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 6e0cbe0..593a881 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -343,7 +343,7 @@
 	phys_addr_t offset = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
 
 	/* It's illegal to wrap around the end of the physical address space. */
-	if (offset + (phys_addr_t)size < offset)
+	if (offset + (phys_addr_t)size - 1 < offset)
 		return -EINVAL;
 
 	if (!valid_mmap_phys_addr_range(vma->vm_pgoff, size))
diff --git a/drivers/char/random.c b/drivers/char/random.c
index a561f0c..e870f32 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1,6 +1,9 @@
 /*
  * random.c -- A strong random number generator
  *
+ * Copyright (C) 2017 Jason A. Donenfeld <Jason@zx2c4.com>. All
+ * Rights Reserved.
+ *
  * Copyright Matt Mackall <mpm@selenic.com>, 2003, 2004, 2005
  *
  * Copyright Theodore Ts'o, 1994, 1995, 1996, 1997, 1998, 1999.  All
@@ -762,6 +765,8 @@
 static struct crng_state **crng_node_pool __read_mostly;
 #endif
 
+static void invalidate_batched_entropy(void);
+
 static void crng_initialize(struct crng_state *crng)
 {
 	int		i;
@@ -799,6 +804,7 @@
 		cp++; crng_init_cnt++; len--;
 	}
 	if (crng_init_cnt >= CRNG_INIT_CNT_THRESH) {
+		invalidate_batched_entropy();
 		crng_init = 1;
 		wake_up_interruptible(&crng_init_wait);
 		pr_notice("random: fast init done\n");
@@ -836,6 +842,7 @@
 	memzero_explicit(&buf, sizeof(buf));
 	crng->init_time = jiffies;
 	if (crng == &primary_crng && crng_init < 2) {
+		invalidate_batched_entropy();
 		crng_init = 2;
 		process_random_ready_list();
 		wake_up_interruptible(&crng_init_wait);
@@ -1097,15 +1104,15 @@
 static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs)
 {
 	__u32 *ptr = (__u32 *) regs;
-	unsigned long flags;
+	unsigned int idx;
 
 	if (regs == NULL)
 		return 0;
-	local_irq_save(flags);
-	if (f->reg_idx >= sizeof(struct pt_regs) / sizeof(__u32))
-		f->reg_idx = 0;
-	ptr += f->reg_idx++;
-	local_irq_restore(flags);
+	idx = READ_ONCE(f->reg_idx);
+	if (idx >= sizeof(struct pt_regs) / sizeof(__u32))
+		idx = 0;
+	ptr += idx++;
+	WRITE_ONCE(f->reg_idx, idx);
 	return *ptr;
 }
 
@@ -2023,6 +2030,7 @@
 	};
 	unsigned int position;
 };
+static rwlock_t batched_entropy_reset_lock = __RW_LOCK_UNLOCKED(batched_entropy_reset_lock);
 
 /*
  * Get a random word for internal kernel use only. The quality of the random
@@ -2033,6 +2041,8 @@
 u64 get_random_u64(void)
 {
 	u64 ret;
+	bool use_lock = crng_init < 2;
+	unsigned long flags;
 	struct batched_entropy *batch;
 
 #if BITS_PER_LONG == 64
@@ -2045,11 +2055,15 @@
 #endif
 
 	batch = &get_cpu_var(batched_entropy_u64);
+	if (use_lock)
+		read_lock_irqsave(&batched_entropy_reset_lock, flags);
 	if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) {
 		extract_crng((u8 *)batch->entropy_u64);
 		batch->position = 0;
 	}
 	ret = batch->entropy_u64[batch->position++];
+	if (use_lock)
+		read_unlock_irqrestore(&batched_entropy_reset_lock, flags);
 	put_cpu_var(batched_entropy_u64);
 	return ret;
 }
@@ -2059,22 +2073,45 @@
 u32 get_random_u32(void)
 {
 	u32 ret;
+	bool use_lock = crng_init < 2;
+	unsigned long flags;
 	struct batched_entropy *batch;
 
 	if (arch_get_random_int(&ret))
 		return ret;
 
 	batch = &get_cpu_var(batched_entropy_u32);
+	if (use_lock)
+		read_lock_irqsave(&batched_entropy_reset_lock, flags);
 	if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) {
 		extract_crng((u8 *)batch->entropy_u32);
 		batch->position = 0;
 	}
 	ret = batch->entropy_u32[batch->position++];
+	if (use_lock)
+		read_unlock_irqrestore(&batched_entropy_reset_lock, flags);
 	put_cpu_var(batched_entropy_u32);
 	return ret;
 }
 EXPORT_SYMBOL(get_random_u32);
 
+/* It's important to invalidate all potential batched entropy that might
+ * be stored before the crng is initialized, which we can do lazily by
+ * simply resetting the counter to zero so that it's re-extracted on the
+ * next usage. */
+static void invalidate_batched_entropy(void)
+{
+	int cpu;
+	unsigned long flags;
+
+	write_lock_irqsave(&batched_entropy_reset_lock, flags);
+	for_each_possible_cpu (cpu) {
+		per_cpu_ptr(&batched_entropy_u32, cpu)->position = 0;
+		per_cpu_ptr(&batched_entropy_u64, cpu)->position = 0;
+	}
+	write_unlock_irqrestore(&batched_entropy_reset_lock, flags);
+}
+
 /**
  * randomize_page - Generate a random, page aligned address
  * @start:	The smallest acceptable address the caller will take.
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index b7de5bd..eb11585 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -571,9 +571,10 @@
 static int min_perf_pct_min(void)
 {
 	struct cpudata *cpu = all_cpu_data[0];
+	int turbo_pstate = cpu->pstate.turbo_pstate;
 
-	return DIV_ROUND_UP(cpu->pstate.min_pstate * 100,
-			    cpu->pstate.turbo_pstate);
+	return turbo_pstate ?
+		DIV_ROUND_UP(cpu->pstate.min_pstate * 100, turbo_pstate) : 0;
 }
 
 static s16 intel_pstate_get_epb(struct cpudata *cpu_data)
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index 6ed32aa..922d082 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -210,9 +210,12 @@
 static struct inode *dax_alloc_inode(struct super_block *sb)
 {
 	struct dax_device *dax_dev;
+	struct inode *inode;
 
 	dax_dev = kmem_cache_alloc(dax_cache, GFP_KERNEL);
-	return &dax_dev->inode;
+	inode = &dax_dev->inode;
+	inode->i_rdev = 0;
+	return inode;
 }
 
 static struct dax_device *to_dax_dev(struct inode *inode)
@@ -227,7 +230,8 @@
 
 	kfree(dax_dev->host);
 	dax_dev->host = NULL;
-	ida_simple_remove(&dax_minor_ida, MINOR(inode->i_rdev));
+	if (inode->i_rdev)
+		ida_simple_remove(&dax_minor_ida, MINOR(inode->i_rdev));
 	kmem_cache_free(dax_cache, dax_dev);
 }
 
@@ -423,6 +427,7 @@
 	struct dax_device *dax_dev = _dax_dev;
 	struct inode *inode = &dax_dev->inode;
 
+	memset(dax_dev, 0, sizeof(*dax_dev));
 	inode_init_once(inode);
 }
 
diff --git a/drivers/firmware/efi/efi-bgrt.c b/drivers/firmware/efi/efi-bgrt.c
index 8bf2732..b58233e 100644
--- a/drivers/firmware/efi/efi-bgrt.c
+++ b/drivers/firmware/efi/efi-bgrt.c
@@ -27,6 +27,26 @@
 	u32 size;
 } __packed;
 
+static bool efi_bgrt_addr_valid(u64 addr)
+{
+	efi_memory_desc_t *md;
+
+	for_each_efi_memory_desc(md) {
+		u64 size;
+		u64 end;
+
+		if (md->type != EFI_BOOT_SERVICES_DATA)
+			continue;
+
+		size = md->num_pages << EFI_PAGE_SHIFT;
+		end = md->phys_addr + size;
+		if (addr >= md->phys_addr && addr < end)
+			return true;
+	}
+
+	return false;
+}
+
 void __init efi_bgrt_init(struct acpi_table_header *table)
 {
 	void *image;
@@ -36,7 +56,7 @@
 	if (acpi_disabled)
 		return;
 
-	if (!efi_enabled(EFI_BOOT))
+	if (!efi_enabled(EFI_MEMMAP))
 		return;
 
 	if (table->length < sizeof(bgrt_tab)) {
@@ -65,6 +85,10 @@
 		goto out;
 	}
 
+	if (!efi_bgrt_addr_valid(bgrt->image_address)) {
+		pr_notice("Ignoring BGRT: invalid image address\n");
+		goto out;
+	}
 	image = early_memremap(bgrt->image_address, sizeof(bmp_header));
 	if (!image) {
 		pr_notice("Ignoring BGRT: failed to map image header memory\n");
diff --git a/drivers/firmware/google/vpd.c b/drivers/firmware/google/vpd.c
index 1e7860f..31058d40 100644
--- a/drivers/firmware/google/vpd.c
+++ b/drivers/firmware/google/vpd.c
@@ -136,12 +136,12 @@
 	info->value = value;
 
 	INIT_LIST_HEAD(&info->list);
-	list_add_tail(&info->list, &sec->attribs);
 
 	ret = sysfs_create_bin_file(sec->kobj, &info->bin_attr);
 	if (ret)
 		goto free_info_key;
 
+	list_add_tail(&info->list, &sec->attribs);
 	return 0;
 
 free_info_key:
@@ -158,8 +158,8 @@
 	struct vpd_attrib_info *temp;
 
 	list_for_each_entry_safe(info, temp, &sec->attribs, list) {
-		kfree(info->key);
 		sysfs_remove_bin_file(sec->kobj, &info->bin_attr);
+		kfree(info->key);
 		kfree(info);
 	}
 }
@@ -244,7 +244,7 @@
 {
 	if (sec->enabled) {
 		vpd_section_attrib_destroy(sec);
-		kobject_del(sec->kobj);
+		kobject_put(sec->kobj);
 		sysfs_remove_bin_file(vpd_kobj, &sec->bin_attr);
 		kfree(sec->raw_name);
 		iounmap(sec->baseaddr);
@@ -331,7 +331,7 @@
 {
 	vpd_section_destroy(&ro_vpd);
 	vpd_section_destroy(&rw_vpd);
-	kobject_del(vpd_kobj);
+	kobject_put(vpd_kobj);
 }
 
 module_init(vpd_platform_init);
diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index ccea609..4ca436e 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -646,6 +646,9 @@
 	int rc;
 	int i;
 
+	if (!gpio->clk)
+		return -EINVAL;
+
 	rc = usecs_to_cycles(gpio, usecs, &requested_cycles);
 	if (rc < 0) {
 		dev_warn(chip->parent, "Failed to convert %luus to cycles at %luHz: %d\n",
diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c
index 2197368..e60156e 100644
--- a/drivers/gpio/gpio-crystalcove.c
+++ b/drivers/gpio/gpio-crystalcove.c
@@ -90,8 +90,18 @@
 {
 	int reg;
 
-	if (gpio == 94)
-		return GPIOPANELCTL;
+	if (gpio >= CRYSTALCOVE_GPIO_NUM) {
+		/*
+		 * Virtual GPIO called from ACPI, for now we only support
+		 * the panel ctl.
+		 */
+		switch (gpio) {
+		case 0x5e:
+			return GPIOPANELCTL;
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
 
 	if (reg_type == CTRL_IN) {
 		if (gpio < 8)
@@ -130,36 +140,36 @@
 static int crystalcove_gpio_dir_in(struct gpio_chip *chip, unsigned gpio)
 {
 	struct crystalcove_gpio *cg = gpiochip_get_data(chip);
+	int reg = to_reg(gpio, CTRL_OUT);
 
-	if (gpio > CRYSTALCOVE_VGPIO_NUM)
+	if (reg < 0)
 		return 0;
 
-	return regmap_write(cg->regmap, to_reg(gpio, CTRL_OUT),
-			    CTLO_INPUT_SET);
+	return regmap_write(cg->regmap, reg, CTLO_INPUT_SET);
 }
 
 static int crystalcove_gpio_dir_out(struct gpio_chip *chip, unsigned gpio,
 				    int value)
 {
 	struct crystalcove_gpio *cg = gpiochip_get_data(chip);
+	int reg = to_reg(gpio, CTRL_OUT);
 
-	if (gpio > CRYSTALCOVE_VGPIO_NUM)
+	if (reg < 0)
 		return 0;
 
-	return regmap_write(cg->regmap, to_reg(gpio, CTRL_OUT),
-			    CTLO_OUTPUT_SET | value);
+	return regmap_write(cg->regmap, reg, CTLO_OUTPUT_SET | value);
 }
 
 static int crystalcove_gpio_get(struct gpio_chip *chip, unsigned gpio)
 {
 	struct crystalcove_gpio *cg = gpiochip_get_data(chip);
-	int ret;
 	unsigned int val;
+	int ret, reg = to_reg(gpio, CTRL_IN);
 
-	if (gpio > CRYSTALCOVE_VGPIO_NUM)
+	if (reg < 0)
 		return 0;
 
-	ret = regmap_read(cg->regmap, to_reg(gpio, CTRL_IN), &val);
+	ret = regmap_read(cg->regmap, reg, &val);
 	if (ret)
 		return ret;
 
@@ -170,14 +180,15 @@
 				 unsigned gpio, int value)
 {
 	struct crystalcove_gpio *cg = gpiochip_get_data(chip);
+	int reg = to_reg(gpio, CTRL_OUT);
 
-	if (gpio > CRYSTALCOVE_VGPIO_NUM)
+	if (reg < 0)
 		return;
 
 	if (value)
-		regmap_update_bits(cg->regmap, to_reg(gpio, CTRL_OUT), 1, 1);
+		regmap_update_bits(cg->regmap, reg, 1, 1);
 	else
-		regmap_update_bits(cg->regmap, to_reg(gpio, CTRL_OUT), 1, 0);
+		regmap_update_bits(cg->regmap, reg, 1, 0);
 }
 
 static int crystalcove_irq_type(struct irq_data *data, unsigned type)
@@ -185,6 +196,9 @@
 	struct crystalcove_gpio *cg =
 		gpiochip_get_data(irq_data_get_irq_chip_data(data));
 
+	if (data->hwirq >= CRYSTALCOVE_GPIO_NUM)
+		return 0;
+
 	switch (type) {
 	case IRQ_TYPE_NONE:
 		cg->intcnt_value = CTLI_INTCNT_DIS;
@@ -235,8 +249,10 @@
 	struct crystalcove_gpio *cg =
 		gpiochip_get_data(irq_data_get_irq_chip_data(data));
 
-	cg->set_irq_mask = false;
-	cg->update |= UPDATE_IRQ_MASK;
+	if (data->hwirq < CRYSTALCOVE_GPIO_NUM) {
+		cg->set_irq_mask = false;
+		cg->update |= UPDATE_IRQ_MASK;
+	}
 }
 
 static void crystalcove_irq_mask(struct irq_data *data)
@@ -244,8 +260,10 @@
 	struct crystalcove_gpio *cg =
 		gpiochip_get_data(irq_data_get_irq_chip_data(data));
 
-	cg->set_irq_mask = true;
-	cg->update |= UPDATE_IRQ_MASK;
+	if (data->hwirq < CRYSTALCOVE_GPIO_NUM) {
+		cg->set_irq_mask = true;
+		cg->update |= UPDATE_IRQ_MASK;
+	}
 }
 
 static struct irq_chip crystalcove_irqchip = {
diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c
index 19a92ef..5104b63 100644
--- a/drivers/gpio/gpio-mvebu.c
+++ b/drivers/gpio/gpio-mvebu.c
@@ -747,7 +747,7 @@
 		set = U32_MAX;
 	else
 		return -EINVAL;
-	writel_relaxed(0, mvebu_gpioreg_blink_counter_select(mvchip));
+	writel_relaxed(set, mvebu_gpioreg_blink_counter_select(mvchip));
 
 	mvpwm = devm_kzalloc(dev, sizeof(struct mvebu_pwm), GFP_KERNEL);
 	if (!mvpwm)
@@ -768,6 +768,13 @@
 	mvpwm->chip.dev = dev;
 	mvpwm->chip.ops = &mvebu_pwm_ops;
 	mvpwm->chip.npwm = mvchip->chip.ngpio;
+	/*
+	 * There may already be some PWM allocated, so we can't force
+	 * mvpwm->chip.base to a fixed point like mvchip->chip.base.
+	 * So, we let pwmchip_add() do the numbering and take the next free
+	 * region.
+	 */
+	mvpwm->chip.base = -1;
 
 	spin_lock_init(&mvpwm->lock);
 
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 8be9719..aa885a6 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -508,6 +508,8 @@
 		bool has_connectors =
 			!!new_crtc_state->connector_mask;
 
+		WARN_ON(!drm_modeset_is_locked(&crtc->mutex));
+
 		if (!drm_mode_equal(&old_crtc_state->mode, &new_crtc_state->mode)) {
 			DRM_DEBUG_ATOMIC("[CRTC:%d:%s] mode changed\n",
 					 crtc->base.id, crtc->name);
@@ -551,6 +553,8 @@
 	for_each_oldnew_connector_in_state(state, connector, old_connector_state, new_connector_state, i) {
 		const struct drm_connector_helper_funcs *funcs = connector->helper_private;
 
+		WARN_ON(!drm_modeset_is_locked(&dev->mode_config.connection_mutex));
+
 		/*
 		 * This only sets crtc->connectors_changed for routing changes,
 		 * drivers must set crtc->connectors_changed themselves when
@@ -650,6 +654,8 @@
 	for_each_oldnew_plane_in_state(state, plane, old_plane_state, new_plane_state, i) {
 		const struct drm_plane_helper_funcs *funcs;
 
+		WARN_ON(!drm_modeset_is_locked(&plane->mutex));
+
 		funcs = plane->helper_private;
 
 		drm_atomic_helper_plane_changed(state, old_plane_state, new_plane_state, plane);
@@ -2663,7 +2669,12 @@
 
 	drm_modeset_acquire_init(&ctx, 0);
 	while (1) {
+		err = drm_modeset_lock_all_ctx(dev, &ctx);
+		if (err)
+			goto out;
+
 		err = drm_atomic_helper_commit_duplicated_state(state, &ctx);
+out:
 		if (err != -EDEADLK)
 			break;
 
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index b5c6bb4..37b8ad3 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -358,7 +358,12 @@
 void drm_unplug_dev(struct drm_device *dev)
 {
 	/* for a USB device */
-	drm_dev_unregister(dev);
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		drm_modeset_unregister_all(dev);
+
+	drm_minor_unregister(dev, DRM_MINOR_PRIMARY);
+	drm_minor_unregister(dev, DRM_MINOR_RENDER);
+	drm_minor_unregister(dev, DRM_MINOR_CONTROL);
 
 	mutex_lock(&drm_global_mutex);
 
diff --git a/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c b/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c
index 5abc69c..f77dcfa 100644
--- a/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c
+++ b/drivers/gpu/drm/hisilicon/kirin/dw_drm_dsi.c
@@ -760,7 +760,7 @@
 	 * Get the endpoint node. In our case, dsi has one output port1
 	 * to which the external HDMI bridge is connected.
 	 */
-	ret = drm_of_find_panel_or_bridge(np, 0, 0, NULL, &dsi->bridge);
+	ret = drm_of_find_panel_or_bridge(np, 1, 0, NULL, &dsi->bridge);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index c994fe6..4842867 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1235,6 +1235,15 @@
 		goto out_fini;
 
 	pci_set_drvdata(pdev, &dev_priv->drm);
+	/*
+	 * Disable the system suspend direct complete optimization, which can
+	 * leave the device suspended skipping the driver's suspend handlers
+	 * if the device was already runtime suspended. This is needed due to
+	 * the difference in our runtime and system suspend sequence and
+	 * becaue the HDA driver may require us to enable the audio power
+	 * domain during system suspend.
+	 */
+	pdev->dev_flags |= PCI_DEV_FLAGS_NEEDS_RESUME;
 
 	ret = i915_driver_init_early(dev_priv, ent);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 963f6d4..2c453a4 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2991,6 +2991,16 @@
 	return false;
 }
 
+static inline bool
+intel_ggtt_update_needs_vtd_wa(struct drm_i915_private *dev_priv)
+{
+#ifdef CONFIG_INTEL_IOMMU
+	if (IS_BROXTON(dev_priv) && intel_iommu_gfx_mapped)
+		return true;
+#endif
+	return false;
+}
+
 int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv,
 				int enable_ppgtt);
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b6ac3df..462031c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3298,6 +3298,10 @@
 {
 	int ret;
 
+	/* If the device is asleep, we have no requests outstanding */
+	if (!READ_ONCE(i915->gt.awake))
+		return 0;
+
 	if (flags & I915_WAIT_LOCKED) {
 		struct i915_gem_timeline *tl;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 50b8f11..f1989b8 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2191,6 +2191,101 @@
 		gen8_set_pte(&gtt_base[i], scratch_pte);
 }
 
+static void bxt_vtd_ggtt_wa(struct i915_address_space *vm)
+{
+	struct drm_i915_private *dev_priv = vm->i915;
+
+	/*
+	 * Make sure the internal GAM fifo has been cleared of all GTT
+	 * writes before exiting stop_machine(). This guarantees that
+	 * any aperture accesses waiting to start in another process
+	 * cannot back up behind the GTT writes causing a hang.
+	 * The register can be any arbitrary GAM register.
+	 */
+	POSTING_READ(GFX_FLSH_CNTL_GEN6);
+}
+
+struct insert_page {
+	struct i915_address_space *vm;
+	dma_addr_t addr;
+	u64 offset;
+	enum i915_cache_level level;
+};
+
+static int bxt_vtd_ggtt_insert_page__cb(void *_arg)
+{
+	struct insert_page *arg = _arg;
+
+	gen8_ggtt_insert_page(arg->vm, arg->addr, arg->offset, arg->level, 0);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_insert_page__BKL(struct i915_address_space *vm,
+					  dma_addr_t addr,
+					  u64 offset,
+					  enum i915_cache_level level,
+					  u32 unused)
+{
+	struct insert_page arg = { vm, addr, offset, level };
+
+	stop_machine(bxt_vtd_ggtt_insert_page__cb, &arg, NULL);
+}
+
+struct insert_entries {
+	struct i915_address_space *vm;
+	struct sg_table *st;
+	u64 start;
+	enum i915_cache_level level;
+};
+
+static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
+{
+	struct insert_entries *arg = _arg;
+
+	gen8_ggtt_insert_entries(arg->vm, arg->st, arg->start, arg->level, 0);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
+					     struct sg_table *st,
+					     u64 start,
+					     enum i915_cache_level level,
+					     u32 unused)
+{
+	struct insert_entries arg = { vm, st, start, level };
+
+	stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
+}
+
+struct clear_range {
+	struct i915_address_space *vm;
+	u64 start;
+	u64 length;
+};
+
+static int bxt_vtd_ggtt_clear_range__cb(void *_arg)
+{
+	struct clear_range *arg = _arg;
+
+	gen8_ggtt_clear_range(arg->vm, arg->start, arg->length);
+	bxt_vtd_ggtt_wa(arg->vm);
+
+	return 0;
+}
+
+static void bxt_vtd_ggtt_clear_range__BKL(struct i915_address_space *vm,
+					  u64 start,
+					  u64 length)
+{
+	struct clear_range arg = { vm, start, length };
+
+	stop_machine(bxt_vtd_ggtt_clear_range__cb, &arg, NULL);
+}
+
 static void gen6_ggtt_clear_range(struct i915_address_space *vm,
 				  u64 start, u64 length)
 {
@@ -2785,6 +2880,14 @@
 
 	ggtt->base.insert_entries = gen8_ggtt_insert_entries;
 
+	/* Serialize GTT updates with aperture access on BXT if VT-d is on. */
+	if (intel_ggtt_update_needs_vtd_wa(dev_priv)) {
+		ggtt->base.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
+		ggtt->base.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
+		if (ggtt->base.clear_range != nop_clear_range)
+			ggtt->base.clear_range = bxt_vtd_ggtt_clear_range__BKL;
+	}
+
 	ggtt->invalidate = gen6_ggtt_invalidate;
 
 	return ggtt_probe_common(ggtt, size);
@@ -2997,7 +3100,8 @@
 
 void i915_ggtt_disable_guc(struct drm_i915_private *i915)
 {
-	i915->ggtt.invalidate = gen6_ggtt_invalidate;
+	if (i915->ggtt.invalidate == guc_ggtt_invalidate)
+		i915->ggtt.invalidate = gen6_ggtt_invalidate;
 }
 
 void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index a0d6d43..fb5231f 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -278,7 +278,7 @@
 			obj->mm.quirked = false;
 		}
 		if (!i915_gem_object_is_tiled(obj)) {
-			GEM_BUG_ON(!obj->mm.quirked);
+			GEM_BUG_ON(obj->mm.quirked);
 			__i915_gem_object_pin_pages(obj);
 			obj->mm.quirked = true;
 		}
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index f87b0c4..1a78363 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -208,7 +208,7 @@
 static const struct intel_device_info intel_ironlake_m_info = {
 	GEN5_FEATURES,
 	.platform = INTEL_IRONLAKE,
-	.is_mobile = 1,
+	.is_mobile = 1, .has_fbc = 1,
 };
 
 #define GEN6_FEATURES \
@@ -390,7 +390,6 @@
 	.has_hw_contexts = 1, \
 	.has_logical_ring_contexts = 1, \
 	.has_guc = 1, \
-	.has_decoupled_mmio = 1, \
 	.has_aliasing_ppgtt = 1, \
 	.has_full_ppgtt = 1, \
 	.has_full_48bit_ppgtt = 1, \
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3cabe52..569717a 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -12203,6 +12203,15 @@
 	 * type. For DP ports it behaves like most other platforms, but on HDMI
 	 * there's an extra 1 line difference. So we need to add two instead of
 	 * one to the value.
+	 *
+	 * On VLV/CHV DSI the scanline counter would appear to increment
+	 * approx. 1/3 of a scanline before start of vblank. Unfortunately
+	 * that means we can't tell whether we're in vblank or not while
+	 * we're on that particular line. We must still set scanline_offset
+	 * to 1 so that the vblank timestamps come out correct when we query
+	 * the scanline counter from within the vblank interrupt handler.
+	 * However if queried just before the start of vblank we'll get an
+	 * answer that's slightly in the future.
 	 */
 	if (IS_GEN2(dev_priv)) {
 		const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 854e8e0..f94eacf 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1075,6 +1075,22 @@
 	return 0;
 }
 
+static bool ring_is_idle(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+	bool idle = true;
+
+	intel_runtime_pm_get(dev_priv);
+
+	/* No bit for gen2, so assume the CS parser is idle */
+	if (INTEL_GEN(dev_priv) > 2 && !(I915_READ_MODE(engine) & MODE_IDLE))
+		idle = false;
+
+	intel_runtime_pm_put(dev_priv);
+
+	return idle;
+}
+
 /**
  * intel_engine_is_idle() - Report if the engine has finished process all work
  * @engine: the intel_engine_cs
@@ -1084,8 +1100,6 @@
  */
 bool intel_engine_is_idle(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
-
 	/* Any inflight/incomplete requests? */
 	if (!i915_seqno_passed(intel_engine_get_seqno(engine),
 			       intel_engine_last_submit(engine)))
@@ -1100,7 +1114,7 @@
 		return false;
 
 	/* Ring stopped? */
-	if (INTEL_GEN(dev_priv) > 2 && !(I915_READ_MODE(engine) & MODE_IDLE))
+	if (!ring_is_idle(engine))
 		return false;
 
 	return true;
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index ded2add..d93c584 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -82,20 +82,10 @@
 static void intel_fbc_get_plane_source_size(struct intel_fbc_state_cache *cache,
 					    int *width, int *height)
 {
-	int w, h;
-
-	if (drm_rotation_90_or_270(cache->plane.rotation)) {
-		w = cache->plane.src_h;
-		h = cache->plane.src_w;
-	} else {
-		w = cache->plane.src_w;
-		h = cache->plane.src_h;
-	}
-
 	if (width)
-		*width = w;
+		*width = cache->plane.src_w;
 	if (height)
-		*height = h;
+		*height = cache->plane.src_h;
 }
 
 static int intel_fbc_calculate_cfb_size(struct drm_i915_private *dev_priv,
@@ -746,6 +736,11 @@
 		cache->crtc.hsw_bdw_pixel_rate = crtc_state->pixel_rate;
 
 	cache->plane.rotation = plane_state->base.rotation;
+	/*
+	 * Src coordinates are already rotated by 270 degrees for
+	 * the 90/270 degree plane rotation cases (to match the
+	 * GTT mapping), hence no need to account for rotation here.
+	 */
 	cache->plane.src_w = drm_rect_width(&plane_state->base.src) >> 16;
 	cache->plane.src_h = drm_rect_height(&plane_state->base.src) >> 16;
 	cache->plane.visible = plane_state->base.visible;
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 570bd60..2ca481b 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -4335,11 +4335,19 @@
 	struct drm_crtc_state *cstate;
 	struct intel_atomic_state *intel_state = to_intel_atomic_state(state);
 	struct skl_wm_values *results = &intel_state->wm_results;
+	struct drm_device *dev = state->dev;
 	struct skl_pipe_wm *pipe_wm;
 	bool changed = false;
 	int ret, i;
 
 	/*
+	 * When we distrust bios wm we always need to recompute to set the
+	 * expected DDB allocations for each CRTC.
+	 */
+	if (to_i915(dev)->wm.distrust_bios_wm)
+		changed = true;
+
+	/*
 	 * If this transaction isn't actually touching any CRTC's, don't
 	 * bother with watermark calculation.  Note that if we pass this
 	 * test, we're guaranteed to hold at least one CRTC state mutex,
@@ -4349,6 +4357,7 @@
 	 */
 	for_each_new_crtc_in_state(state, crtc, cstate, i)
 		changed = true;
+
 	if (!changed)
 		return 0;
 
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index c3780d0..559f1ab 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -435,8 +435,9 @@
 	}
 
 	/* PSR2 is restricted to work with panel resolutions upto 3200x2000 */
-	if (intel_crtc->config->pipe_src_w > 3200 ||
-				intel_crtc->config->pipe_src_h > 2000) {
+	if (dev_priv->psr.psr2_support &&
+	    (intel_crtc->config->pipe_src_w > 3200 ||
+	     intel_crtc->config->pipe_src_h > 2000)) {
 		dev_priv->psr.psr2_support = false;
 		return false;
 	}
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 8c87c71..e6517edc 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -83,10 +83,13 @@
  */
 void intel_pipe_update_start(struct intel_crtc *crtc)
 {
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	const struct drm_display_mode *adjusted_mode = &crtc->config->base.adjusted_mode;
 	long timeout = msecs_to_jiffies_timeout(1);
 	int scanline, min, max, vblank_start;
 	wait_queue_head_t *wq = drm_crtc_vblank_waitqueue(&crtc->base);
+	bool need_vlv_dsi_wa = (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+		intel_crtc_has_type(crtc->config, INTEL_OUTPUT_DSI);
 	DEFINE_WAIT(wait);
 
 	vblank_start = adjusted_mode->crtc_vblank_start;
@@ -139,6 +142,24 @@
 
 	drm_crtc_vblank_put(&crtc->base);
 
+	/*
+	 * On VLV/CHV DSI the scanline counter would appear to
+	 * increment approx. 1/3 of a scanline before start of vblank.
+	 * The registers still get latched at start of vblank however.
+	 * This means we must not write any registers on the first
+	 * line of vblank (since not the whole line is actually in
+	 * vblank). And unfortunately we can't use the interrupt to
+	 * wait here since it will fire too soon. We could use the
+	 * frame start interrupt instead since it will fire after the
+	 * critical scanline, but that would require more changes
+	 * in the interrupt code. So for now we'll just do the nasty
+	 * thing and poll for the bad scanline to pass us by.
+	 *
+	 * FIXME figure out if BXT+ DSI suffers from this as well
+	 */
+	while (need_vlv_dsi_wa && scanline == vblank_start)
+		scanline = intel_get_crtc_scanline(crtc);
+
 	crtc->debug.scanline_start = scanline;
 	crtc->debug.start_vbl_time = ktime_get();
 	crtc->debug.start_vbl_count = intel_crtc_get_vblank_counter(crtc);
diff --git a/drivers/gpu/drm/i915/intel_uc.h b/drivers/gpu/drm/i915/intel_uc.h
index 4b7f73a..f841152 100644
--- a/drivers/gpu/drm/i915/intel_uc.h
+++ b/drivers/gpu/drm/i915/intel_uc.h
@@ -59,8 +59,6 @@
  *                available in the work queue (note, the queue is shared,
  *                not per-engine). It is OK for this to be nonzero, but
  *                it should not be huge!
- *   q_fail: failed to enqueue a work item. This should never happen,
- *           because we check for space beforehand.
  *   b_fail: failed to ring the doorbell. This should never happen, unless
  *           somehow the hardware misbehaves, or maybe if the GuC firmware
  *           crashes? We probably need to reset the GPU to recover.
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index 8fb801f..8b05ecb 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -673,7 +673,7 @@
 		ret = drm_of_find_panel_or_bridge(child,
 						  imx_ldb->lvds_mux ? 4 : 2, 0,
 						  &channel->panel, &channel->bridge);
-		if (ret)
+		if (ret && ret != -ENODEV)
 			return ret;
 
 		/* panel ddc only if there is no bridge */
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index 808b995..b5cc6e1 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -19,6 +19,7 @@
 #include <drm/drm_of.h>
 #include <linux/clk.h>
 #include <linux/component.h>
+#include <linux/iopoll.h>
 #include <linux/irq.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
@@ -900,16 +901,12 @@
 
 static void mtk_dsi_wait_for_idle(struct mtk_dsi *dsi)
 {
-	u32 timeout_ms = 500000; /* total 1s ~ 2s timeout */
+	int ret;
+	u32 val;
 
-	while (timeout_ms--) {
-		if (!(readl(dsi->regs + DSI_INTSTA) & DSI_BUSY))
-			break;
-
-		usleep_range(2, 4);
-	}
-
-	if (timeout_ms == 0) {
+	ret = readl_poll_timeout(dsi->regs + DSI_INTSTA, val, !(val & DSI_BUSY),
+				 4, 2000000);
+	if (ret) {
 		DRM_WARN("polling dsi wait not busy timeout!\n");
 
 		mtk_dsi_enable(dsi);
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index 41a1c03..0a4ffd7 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1062,7 +1062,7 @@
 	}
 
 	err = hdmi_vendor_infoframe_pack(&frame, buffer, sizeof(buffer));
-	if (err) {
+	if (err < 0) {
 		dev_err(hdmi->dev, "Failed to pack vendor infoframe: %zd\n",
 			err);
 		return err;
diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
index 75382f5..10b227d 100644
--- a/drivers/gpu/drm/meson/meson_drv.c
+++ b/drivers/gpu/drm/meson/meson_drv.c
@@ -152,7 +152,7 @@
 	.max_register   = 0x1000,
 };
 
-static int meson_drv_bind(struct device *dev)
+static int meson_drv_bind_master(struct device *dev, bool has_components)
 {
 	struct platform_device *pdev = to_platform_device(dev);
 	struct meson_drm *priv;
@@ -233,10 +233,12 @@
 	if (ret)
 		goto free_drm;
 
-	ret = component_bind_all(drm->dev, drm);
-	if (ret) {
-		dev_err(drm->dev, "Couldn't bind all components\n");
-		goto free_drm;
+	if (has_components) {
+		ret = component_bind_all(drm->dev, drm);
+		if (ret) {
+			dev_err(drm->dev, "Couldn't bind all components\n");
+			goto free_drm;
+		}
 	}
 
 	ret = meson_plane_create(priv);
@@ -276,6 +278,11 @@
 	return ret;
 }
 
+static int meson_drv_bind(struct device *dev)
+{
+	return meson_drv_bind_master(dev, true);
+}
+
 static void meson_drv_unbind(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
@@ -357,6 +364,9 @@
 		count += meson_probe_remote(pdev, &match, np, remote);
 	}
 
+	if (count && !match)
+		return meson_drv_bind_master(&pdev->dev, false);
+
 	/* If some endpoints were found, initialize the nodes */
 	if (count) {
 		dev_info(&pdev->dev, "Queued %d outputs on vpu\n", count);
diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h
index 6a567fe..820a480 100644
--- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h
+++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/timer.h
@@ -4,6 +4,7 @@
 
 struct nvkm_alarm {
 	struct list_head head;
+	struct list_head exec;
 	u64 timestamp;
 	void (*func)(struct nvkm_alarm *);
 };
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 36268e1..15a13d0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -80,7 +80,7 @@
 module_param_named(modeset, nouveau_modeset, int, 0400);
 
 MODULE_PARM_DESC(runpm, "disable (0), force enable (1), optimus only default (-1)");
-int nouveau_runtime_pm = -1;
+static int nouveau_runtime_pm = -1;
 module_param_named(runpm, nouveau_runtime_pm, int, 0400);
 
 static struct drm_driver driver_stub;
@@ -495,7 +495,7 @@
 	nouveau_fbcon_init(dev);
 	nouveau_led_init(dev);
 
-	if (nouveau_runtime_pm != 0) {
+	if (nouveau_pmops_runtime()) {
 		pm_runtime_use_autosuspend(dev->dev);
 		pm_runtime_set_autosuspend_delay(dev->dev, 5000);
 		pm_runtime_set_active(dev->dev);
@@ -527,7 +527,7 @@
 {
 	struct nouveau_drm *drm = nouveau_drm(dev);
 
-	if (nouveau_runtime_pm != 0) {
+	if (nouveau_pmops_runtime()) {
 		pm_runtime_get_sync(dev->dev);
 		pm_runtime_forbid(dev->dev);
 	}
@@ -726,6 +726,14 @@
 	return nouveau_do_resume(drm_dev, false);
 }
 
+bool
+nouveau_pmops_runtime()
+{
+	if (nouveau_runtime_pm == -1)
+		return nouveau_is_optimus() || nouveau_is_v1_dsm();
+	return nouveau_runtime_pm == 1;
+}
+
 static int
 nouveau_pmops_runtime_suspend(struct device *dev)
 {
@@ -733,14 +741,7 @@
 	struct drm_device *drm_dev = pci_get_drvdata(pdev);
 	int ret;
 
-	if (nouveau_runtime_pm == 0) {
-		pm_runtime_forbid(dev);
-		return -EBUSY;
-	}
-
-	/* are we optimus enabled? */
-	if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) {
-		DRM_DEBUG_DRIVER("failing to power off - not optimus\n");
+	if (!nouveau_pmops_runtime()) {
 		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
@@ -765,8 +766,10 @@
 	struct nvif_device *device = &nouveau_drm(drm_dev)->client.device;
 	int ret;
 
-	if (nouveau_runtime_pm == 0)
-		return -EINVAL;
+	if (!nouveau_pmops_runtime()) {
+		pm_runtime_forbid(dev);
+		return -EBUSY;
+	}
 
 	pci_set_power_state(pdev, PCI_D0);
 	pci_restore_state(pdev);
@@ -796,14 +799,7 @@
 	struct nouveau_drm *drm = nouveau_drm(drm_dev);
 	struct drm_crtc *crtc;
 
-	if (nouveau_runtime_pm == 0) {
-		pm_runtime_forbid(dev);
-		return -EBUSY;
-	}
-
-	/* are we optimus enabled? */
-	if (nouveau_runtime_pm == -1 && !nouveau_is_optimus() && !nouveau_is_v1_dsm()) {
-		DRM_DEBUG_DRIVER("failing to power off - not optimus\n");
+	if (!nouveau_pmops_runtime()) {
 		pm_runtime_forbid(dev);
 		return -EBUSY;
 	}
diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h
index eadec2f..a11b6aa 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drv.h
+++ b/drivers/gpu/drm/nouveau/nouveau_drv.h
@@ -108,8 +108,6 @@
 #include <nvif/object.h>
 #include <nvif/device.h>
 
-extern int nouveau_runtime_pm;
-
 struct nouveau_drm {
 	struct nouveau_cli client;
 	struct drm_device *dev;
@@ -195,6 +193,7 @@
 
 int nouveau_pmops_suspend(struct device *);
 int nouveau_pmops_resume(struct device *);
+bool nouveau_pmops_runtime(void);
 
 #include <nvkm/core/tegra.h>
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_vga.c b/drivers/gpu/drm/nouveau/nouveau_vga.c
index a4aacbc..02fe0ef 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vga.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vga.c
@@ -87,7 +87,7 @@
 nouveau_vga_init(struct nouveau_drm *drm)
 {
 	struct drm_device *dev = drm->dev;
-	bool runtime = false;
+	bool runtime = nouveau_pmops_runtime();
 
 	/* only relevant for PCI devices */
 	if (!dev->pdev)
@@ -99,10 +99,6 @@
 	if (pci_is_thunderbolt_attached(dev->pdev))
 		return;
 
-	if (nouveau_runtime_pm == 1)
-		runtime = true;
-	if ((nouveau_runtime_pm == -1) && (nouveau_is_optimus() || nouveau_is_v1_dsm()))
-		runtime = true;
 	vga_switcheroo_register_client(dev->pdev, &nouveau_switcheroo_ops, runtime);
 
 	if (runtime && nouveau_is_v1_dsm() && !nouveau_is_optimus())
@@ -113,18 +109,13 @@
 nouveau_vga_fini(struct nouveau_drm *drm)
 {
 	struct drm_device *dev = drm->dev;
-	bool runtime = false;
+	bool runtime = nouveau_pmops_runtime();
 
 	vga_client_register(dev->pdev, NULL, NULL, NULL);
 
 	if (pci_is_thunderbolt_attached(dev->pdev))
 		return;
 
-	if (nouveau_runtime_pm == 1)
-		runtime = true;
-	if ((nouveau_runtime_pm == -1) && (nouveau_is_optimus() || nouveau_is_v1_dsm()))
-		runtime = true;
-
 	vga_switcheroo_unregister_client(dev->pdev);
 	if (runtime && nouveau_is_v1_dsm() && !nouveau_is_optimus())
 		vga_switcheroo_fini_domain_pm_ops(drm->dev->dev);
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index a7663249..06e564a 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -2107,7 +2107,8 @@
 					asyc->set.dither = true;
 			}
 		} else {
-			asyc->set.mask = ~0;
+			if (asyc)
+				asyc->set.mask = ~0;
 			asyh->set.mask = ~0;
 		}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c
index f2a86ea..2437f7d 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/timer/base.c
@@ -50,7 +50,8 @@
 		/* Move to completed list.  We'll drop the lock before
 		 * executing the callback so it can reschedule itself.
 		 */
-		list_move_tail(&alarm->head, &exec);
+		list_del_init(&alarm->head);
+		list_add(&alarm->exec, &exec);
 	}
 
 	/* Shut down interrupt if no more pending alarms. */
@@ -59,8 +60,8 @@
 	spin_unlock_irqrestore(&tmr->lock, flags);
 
 	/* Execute completed callbacks. */
-	list_for_each_entry_safe(alarm, atemp, &exec, head) {
-		list_del_init(&alarm->head);
+	list_for_each_entry_safe(alarm, atemp, &exec, exec) {
+		list_del(&alarm->exec);
 		alarm->func(alarm);
 	}
 }
diff --git a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
index d8fa7a9..ce5f2d1 100644
--- a/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
+++ b/drivers/gpu/drm/rockchip/analogix_dp-rockchip.c
@@ -245,8 +245,6 @@
 				      struct drm_connector_state *conn_state)
 {
 	struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc_state);
-	struct rockchip_dp_device *dp = to_dp(encoder);
-	int ret;
 
 	/*
 	 * The hardware IC designed that VOP must output the RGB10 video
@@ -258,16 +256,6 @@
 
 	s->output_mode = ROCKCHIP_OUT_MODE_AAAA;
 	s->output_type = DRM_MODE_CONNECTOR_eDP;
-	if (dp->data->chip_type == RK3399_EDP) {
-		/*
-		 * For RK3399, VOP Lit must code the out mode to RGB888,
-		 * VOP Big must code the out mode to RGB10.
-		 */
-		ret = drm_of_encoder_active_endpoint_id(dp->dev->of_node,
-							encoder);
-		if (ret > 0)
-			s->output_mode = ROCKCHIP_OUT_MODE_P888;
-	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c
index a2169dd..14fa1f8 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c
@@ -615,7 +615,6 @@
 {
 	struct cdn_dp_device *dp = encoder_to_dp(encoder);
 	int ret, val;
-	struct rockchip_crtc_state *state;
 
 	ret = drm_of_encoder_active_endpoint_id(dp->dev->of_node, encoder);
 	if (ret < 0) {
@@ -625,14 +624,10 @@
 
 	DRM_DEV_DEBUG_KMS(dp->dev, "vop %s output to cdn-dp\n",
 			  (ret) ? "LIT" : "BIG");
-	state = to_rockchip_crtc_state(encoder->crtc->state);
-	if (ret) {
+	if (ret)
 		val = DP_SEL_VOP_LIT | (DP_SEL_VOP_LIT << 16);
-		state->output_mode = ROCKCHIP_OUT_MODE_P888;
-	} else {
+	else
 		val = DP_SEL_VOP_LIT << 16;
-		state->output_mode = ROCKCHIP_OUT_MODE_AAAA;
-	}
 
 	ret = cdn_dp_grf_write(dp, GRF_SOC_CON9, val);
 	if (ret)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 3f7a82d..45589d6 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -875,6 +875,7 @@
 static void vop_crtc_enable(struct drm_crtc *crtc)
 {
 	struct vop *vop = to_vop(crtc);
+	const struct vop_data *vop_data = vop->data;
 	struct rockchip_crtc_state *s = to_rockchip_crtc_state(crtc->state);
 	struct drm_display_mode *adjusted_mode = &crtc->state->adjusted_mode;
 	u16 hsync_len = adjusted_mode->hsync_end - adjusted_mode->hsync_start;
@@ -967,6 +968,13 @@
 		DRM_DEV_ERROR(vop->dev, "unsupported connector_type [%d]\n",
 			      s->output_type);
 	}
+
+	/*
+	 * if vop is not support RGB10 output, need force RGB10 to RGB888.
+	 */
+	if (s->output_mode == ROCKCHIP_OUT_MODE_AAAA &&
+	    !(vop_data->feature & VOP_FEATURE_OUTPUT_RGB10))
+		s->output_mode = ROCKCHIP_OUT_MODE_P888;
 	VOP_CTRL_SET(vop, out_mode, s->output_mode);
 
 	VOP_CTRL_SET(vop, htotal_pw, (htotal << 16) | hsync_len);
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
index 5a4faa85..9979fd0 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
@@ -142,6 +142,9 @@
 	const struct vop_intr *intr;
 	const struct vop_win_data *win;
 	unsigned int win_size;
+
+#define VOP_FEATURE_OUTPUT_RGB10	BIT(0)
+	u64 feature;
 };
 
 /* interrupt define */
diff --git a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
index 0da4444..bafd698 100644
--- a/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
+++ b/drivers/gpu/drm/rockchip/rockchip_vop_reg.c
@@ -275,6 +275,7 @@
 static const struct vop_data rk3288_vop = {
 	.init_table = rk3288_init_reg_table,
 	.table_size = ARRAY_SIZE(rk3288_init_reg_table),
+	.feature = VOP_FEATURE_OUTPUT_RGB10,
 	.intr = &rk3288_vop_intr,
 	.ctrl = &rk3288_ctrl_data,
 	.win = rk3288_vop_win_data,
@@ -343,6 +344,7 @@
 static const struct vop_data rk3399_vop_big = {
 	.init_table = rk3399_init_reg_table,
 	.table_size = ARRAY_SIZE(rk3399_init_reg_table),
+	.feature = VOP_FEATURE_OUTPUT_RGB10,
 	.intr = &rk3399_vop_intr,
 	.ctrl = &rk3399_ctrl_data,
 	/*
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 130d51c..4b948fba 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -41,9 +41,9 @@
 #include <drm/ttm/ttm_module.h>
 #include "vmwgfx_fence.h"
 
-#define VMWGFX_DRIVER_DATE "20170221"
+#define VMWGFX_DRIVER_DATE "20170607"
 #define VMWGFX_DRIVER_MAJOR 2
-#define VMWGFX_DRIVER_MINOR 12
+#define VMWGFX_DRIVER_MINOR 13
 #define VMWGFX_DRIVER_PATCHLEVEL 0
 #define VMWGFX_FILE_PAGE_OFFSET 0x00100000
 #define VMWGFX_FIFO_STATIC_SIZE (1024*1024)
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
index b6a0806..a1c68e6 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
@@ -368,6 +368,8 @@
 				return fifo_state->static_buffer;
 			else {
 				fifo_state->dynamic_buffer = vmalloc(bytes);
+				if (!fifo_state->dynamic_buffer)
+					goto out_err;
 				return fifo_state->dynamic_buffer;
 			}
 		}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index ef9f3a2..1d2db5d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -274,108 +274,6 @@
 }
 
 
-
-/**
- * vmw_du_cursor_plane_update() - Update cursor image and location
- *
- * @plane: plane object to update
- * @crtc: owning CRTC of @plane
- * @fb: framebuffer to flip onto plane
- * @crtc_x: x offset of plane on crtc
- * @crtc_y: y offset of plane on crtc
- * @crtc_w: width of plane rectangle on crtc
- * @crtc_h: height of plane rectangle on crtc
- * @src_x: Not used
- * @src_y: Not used
- * @src_w: Not used
- * @src_h: Not used
- *
- *
- * RETURNS:
- * Zero on success, error code on failure
- */
-int vmw_du_cursor_plane_update(struct drm_plane *plane,
-			       struct drm_crtc *crtc,
-			       struct drm_framebuffer *fb,
-			       int crtc_x, int crtc_y,
-			       unsigned int crtc_w,
-			       unsigned int crtc_h,
-			       uint32_t src_x, uint32_t src_y,
-			       uint32_t src_w, uint32_t src_h)
-{
-	struct vmw_private *dev_priv = vmw_priv(crtc->dev);
-	struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
-	struct vmw_surface *surface = NULL;
-	struct vmw_dma_buffer *dmabuf = NULL;
-	s32 hotspot_x, hotspot_y;
-	int ret;
-
-	hotspot_x = du->hotspot_x + fb->hot_x;
-	hotspot_y = du->hotspot_y + fb->hot_y;
-
-	/* A lot of the code assumes this */
-	if (crtc_w != 64 || crtc_h != 64) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (vmw_framebuffer_to_vfb(fb)->dmabuf)
-		dmabuf = vmw_framebuffer_to_vfbd(fb)->buffer;
-	else
-		surface = vmw_framebuffer_to_vfbs(fb)->surface;
-
-	if (surface && !surface->snooper.image) {
-		DRM_ERROR("surface not suitable for cursor\n");
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* setup new image */
-	ret = 0;
-	if (surface) {
-		/* vmw_user_surface_lookup takes one reference */
-		du->cursor_surface = surface;
-
-		du->cursor_age = du->cursor_surface->snooper.age;
-
-		ret = vmw_cursor_update_image(dev_priv, surface->snooper.image,
-					      64, 64, hotspot_x, hotspot_y);
-	} else if (dmabuf) {
-		/* vmw_user_surface_lookup takes one reference */
-		du->cursor_dmabuf = dmabuf;
-
-		ret = vmw_cursor_update_dmabuf(dev_priv, dmabuf, crtc_w, crtc_h,
-					       hotspot_x, hotspot_y);
-	} else {
-		vmw_cursor_update_position(dev_priv, false, 0, 0);
-		goto out;
-	}
-
-	if (!ret) {
-		du->cursor_x = crtc_x + du->set_gui_x;
-		du->cursor_y = crtc_y + du->set_gui_y;
-
-		vmw_cursor_update_position(dev_priv, true,
-					   du->cursor_x + hotspot_x,
-					   du->cursor_y + hotspot_y);
-	}
-
-out:
-	return ret;
-}
-
-
-int vmw_du_cursor_plane_disable(struct drm_plane *plane)
-{
-	if (plane->fb) {
-		drm_framebuffer_unreference(plane->fb);
-		plane->fb = NULL;
-	}
-
-	return -EINVAL;
-}
-
-
 void vmw_du_cursor_plane_destroy(struct drm_plane *plane)
 {
 	vmw_cursor_update_position(plane->dev->dev_private, false, 0, 0);
@@ -473,18 +371,6 @@
 
 
 void
-vmw_du_cursor_plane_atomic_disable(struct drm_plane *plane,
-				   struct drm_plane_state *old_state)
-{
-	struct drm_crtc *crtc = plane->state->crtc ?: old_state->crtc;
-	struct vmw_private *dev_priv = vmw_priv(crtc->dev);
-
-	drm_atomic_set_fb_for_plane(plane->state, NULL);
-	vmw_cursor_update_position(dev_priv, false, 0, 0);
-}
-
-
-void
 vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 				  struct drm_plane_state *old_state)
 {
@@ -1498,6 +1384,7 @@
 	 */
 	if (vmw_kms_srf_ok(dev_priv, mode_cmd->width, mode_cmd->height)  &&
 	    dmabuf && only_2d &&
+	    mode_cmd->width > 64 &&  /* Don't create a proxy for cursor */
 	    dev_priv->active_display_unit == vmw_du_screen_target) {
 		ret = vmw_create_dmabuf_proxy(dev_priv->dev, mode_cmd,
 					      dmabuf, &surface);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
index 13f2f1d2..5f8d678 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
@@ -256,10 +256,6 @@
 			   u16 *r, u16 *g, u16 *b,
 			   uint32_t size,
 			   struct drm_modeset_acquire_ctx *ctx);
-int vmw_du_crtc_cursor_set2(struct drm_crtc *crtc, struct drm_file *file_priv,
-			    uint32_t handle, uint32_t width, uint32_t height,
-			    int32_t hot_x, int32_t hot_y);
-int vmw_du_crtc_cursor_move(struct drm_crtc *crtc, int x, int y);
 int vmw_du_connector_set_property(struct drm_connector *connector,
 				  struct drm_property *property,
 				  uint64_t val);
@@ -339,15 +335,6 @@
 /* Universal Plane Helpers */
 void vmw_du_primary_plane_destroy(struct drm_plane *plane);
 void vmw_du_cursor_plane_destroy(struct drm_plane *plane);
-int vmw_du_cursor_plane_disable(struct drm_plane *plane);
-int vmw_du_cursor_plane_update(struct drm_plane *plane,
-			       struct drm_crtc *crtc,
-			       struct drm_framebuffer *fb,
-			       int crtc_x, int crtc_y,
-			       unsigned int crtc_w,
-			       unsigned int crtc_h,
-			       uint32_t src_x, uint32_t src_y,
-			       uint32_t src_w, uint32_t src_h);
 
 /* Atomic Helpers */
 int vmw_du_primary_plane_atomic_check(struct drm_plane *plane,
@@ -356,8 +343,6 @@
 				     struct drm_plane_state *state);
 void vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 				       struct drm_plane_state *old_state);
-void vmw_du_cursor_plane_atomic_disable(struct drm_plane *plane,
-					struct drm_plane_state *old_state);
 int vmw_du_cursor_plane_prepare_fb(struct drm_plane *plane,
 				   struct drm_plane_state *new_state);
 void vmw_du_plane_cleanup_fb(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index bad31bd..50be1f0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -56,6 +56,8 @@
  * @right: Right side of bounding box.
  * @top: Top side of bounding box.
  * @bottom: Bottom side of bounding box.
+ * @fb_left: Left side of the framebuffer/content bounding box
+ * @fb_top: Top of the framebuffer/content bounding box
  * @buf: DMA buffer when DMA-ing between buffer and screen targets.
  * @sid: Surface ID when copying between surface and screen targets.
  */
@@ -63,6 +65,7 @@
 	struct vmw_kms_dirty base;
 	SVGA3dTransferType  transfer;
 	s32 left, right, top, bottom;
+	s32 fb_left, fb_top;
 	u32 pitch;
 	union {
 		struct vmw_dma_buffer *buf;
@@ -647,7 +650,7 @@
  *
  * @dirty: The closure structure.
  *
- * This function calculates the bounding box for all the incoming clips
+ * This function calculates the bounding box for all the incoming clips.
  */
 static void vmw_stdu_dmabuf_cpu_clip(struct vmw_kms_dirty *dirty)
 {
@@ -656,11 +659,19 @@
 
 	dirty->num_hits = 1;
 
-	/* Calculate bounding box */
+	/* Calculate destination bounding box */
 	ddirty->left = min_t(s32, ddirty->left, dirty->unit_x1);
 	ddirty->top = min_t(s32, ddirty->top, dirty->unit_y1);
 	ddirty->right = max_t(s32, ddirty->right, dirty->unit_x2);
 	ddirty->bottom = max_t(s32, ddirty->bottom, dirty->unit_y2);
+
+	/*
+	 * Calculate content bounding box.  We only need the top-left
+	 * coordinate because width and height will be the same as the
+	 * destination bounding box above
+	 */
+	ddirty->fb_left = min_t(s32, ddirty->fb_left, dirty->fb_x);
+	ddirty->fb_top  = min_t(s32, ddirty->fb_top, dirty->fb_y);
 }
 
 
@@ -697,11 +708,11 @@
 	/* Assume we are blitting from Host (display_srf) to Guest (dmabuf) */
 	src_pitch = stdu->display_srf->base_size.width * stdu->cpp;
 	src = ttm_kmap_obj_virtual(&stdu->host_map, &not_used);
-	src += dirty->unit_y1 * src_pitch + dirty->unit_x1 * stdu->cpp;
+	src += ddirty->top * src_pitch + ddirty->left * stdu->cpp;
 
 	dst_pitch = ddirty->pitch;
 	dst = ttm_kmap_obj_virtual(&stdu->guest_map, &not_used);
-	dst += dirty->fb_y * dst_pitch + dirty->fb_x * stdu->cpp;
+	dst += ddirty->fb_top * dst_pitch + ddirty->fb_left * stdu->cpp;
 
 
 	/* Figure out the real direction */
@@ -760,7 +771,7 @@
 	}
 
 out_cleanup:
-	ddirty->left = ddirty->top = S32_MAX;
+	ddirty->left = ddirty->top = ddirty->fb_left = ddirty->fb_top = S32_MAX;
 	ddirty->right = ddirty->bottom = S32_MIN;
 }
 
@@ -812,6 +823,7 @@
 		SVGA3D_READ_HOST_VRAM;
 	ddirty.left = ddirty.top = S32_MAX;
 	ddirty.right = ddirty.bottom = S32_MIN;
+	ddirty.fb_left = ddirty.fb_top = S32_MAX;
 	ddirty.pitch = vfb->base.pitches[0];
 	ddirty.buf = buf;
 	ddirty.base.fifo_commit = vmw_stdu_dmabuf_fifo_commit;
@@ -1355,6 +1367,11 @@
 		DRM_ERROR("Failed to bind surface to STDU.\n");
 	else
 		crtc->primary->fb = plane->state->fb;
+
+	ret = vmw_stdu_update_st(dev_priv, stdu);
+
+	if (ret)
+		DRM_ERROR("Failed to update STDU.\n");
 }
 
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 7681341..6b70bd2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -1274,11 +1274,14 @@
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
 	int ret;
 	uint32_t size;
-	uint32_t backup_handle;
+	uint32_t backup_handle = 0;
 
 	if (req->multisample_count != 0)
 		return -EINVAL;
 
+	if (req->mip_levels > DRM_VMW_MAX_MIP_LEVELS)
+		return -EINVAL;
+
 	if (unlikely(vmw_user_surface_size == 0))
 		vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) +
 			128;
@@ -1314,12 +1317,16 @@
 		ret = vmw_user_dmabuf_lookup(tfile, req->buffer_handle,
 					     &res->backup,
 					     &user_srf->backup_base);
-		if (ret == 0 && res->backup->base.num_pages * PAGE_SIZE <
-		    res->backup_size) {
-			DRM_ERROR("Surface backup buffer is too small.\n");
-			vmw_dmabuf_unreference(&res->backup);
-			ret = -EINVAL;
-			goto out_unlock;
+		if (ret == 0) {
+			if (res->backup->base.num_pages * PAGE_SIZE <
+			    res->backup_size) {
+				DRM_ERROR("Surface backup buffer is too small.\n");
+				vmw_dmabuf_unreference(&res->backup);
+				ret = -EINVAL;
+				goto out_unlock;
+			} else {
+				backup_handle = req->buffer_handle;
+			}
 		}
 	} else if (req->drm_surface_flags & drm_vmw_surface_flag_create_buffer)
 		ret = vmw_user_dmabuf_alloc(dev_priv, tfile,
@@ -1491,7 +1498,7 @@
 				 dev_priv->stdu_max_height);
 
 		if (size.width > max_width || size.height > max_height) {
-			DRM_ERROR("%ux%u\n, exeeds max surface size %ux%u",
+			DRM_ERROR("%ux%u\n, exceeds max surface size %ux%u",
 				  size.width, size.height,
 				  max_width, max_height);
 			return -EINVAL;
diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 16d5568..2fb5f43 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -725,15 +725,16 @@
 	spin_lock_irqsave(&ipu->lock, flags);
 
 	val = ipu_cm_read(ipu, IPU_CONF);
-	if (vdi) {
+	if (vdi)
 		val |= IPU_CONF_IC_INPUT;
-	} else {
+	else
 		val &= ~IPU_CONF_IC_INPUT;
-		if (csi_id == 1)
-			val |= IPU_CONF_CSI_SEL;
-		else
-			val &= ~IPU_CONF_CSI_SEL;
-	}
+
+	if (csi_id == 1)
+		val |= IPU_CONF_CSI_SEL;
+	else
+		val &= ~IPU_CONF_CSI_SEL;
+
 	ipu_cm_write(ipu, val, IPU_CONF);
 
 	spin_unlock_irqrestore(&ipu->lock, flags);
diff --git a/drivers/gpu/ipu-v3/ipu-pre.c b/drivers/gpu/ipu-v3/ipu-pre.c
index c555633..c35f74c 100644
--- a/drivers/gpu/ipu-v3/ipu-pre.c
+++ b/drivers/gpu/ipu-v3/ipu-pre.c
@@ -131,8 +131,6 @@
 	if (pre->in_use)
 		return -EBUSY;
 
-	clk_prepare_enable(pre->clk_axi);
-
 	/* first get the engine out of reset and remove clock gating */
 	writel(0, pre->regs + IPU_PRE_CTRL);
 
@@ -149,12 +147,7 @@
 
 void ipu_pre_put(struct ipu_pre *pre)
 {
-	u32 val;
-
-	val = IPU_PRE_CTRL_SFTRST | IPU_PRE_CTRL_CLKGATE;
-	writel(val, pre->regs + IPU_PRE_CTRL);
-
-	clk_disable_unprepare(pre->clk_axi);
+	writel(IPU_PRE_CTRL_SFTRST, pre->regs + IPU_PRE_CTRL);
 
 	pre->in_use = false;
 }
@@ -249,6 +242,8 @@
 	if (!pre->buffer_virt)
 		return -ENOMEM;
 
+	clk_prepare_enable(pre->clk_axi);
+
 	pre->dev = dev;
 	platform_set_drvdata(pdev, pre);
 	mutex_lock(&ipu_pre_list_mutex);
@@ -268,6 +263,8 @@
 	available_pres--;
 	mutex_unlock(&ipu_pre_list_mutex);
 
+	clk_disable_unprepare(pre->clk_axi);
+
 	if (pre->buffer_virt)
 		gen_pool_free(pre->iram, (unsigned long)pre->buffer_virt,
 			      IPU_PRE_MAX_WIDTH * IPU_PRE_NUM_SCANLINES * 4);
diff --git a/drivers/iio/adc/bcm_iproc_adc.c b/drivers/iio/adc/bcm_iproc_adc.c
index 21d38c8..7f4f9c4 100644
--- a/drivers/iio/adc/bcm_iproc_adc.c
+++ b/drivers/iio/adc/bcm_iproc_adc.c
@@ -143,7 +143,7 @@
 	iproc_adc_dbg_reg(dev, adc_priv, IPROC_SOFT_BYPASS_DATA);
 }
 
-static irqreturn_t iproc_adc_interrupt_handler(int irq, void *data)
+static irqreturn_t iproc_adc_interrupt_thread(int irq, void *data)
 {
 	u32 channel_intr_status;
 	u32 intr_status;
@@ -167,7 +167,7 @@
 	return IRQ_NONE;
 }
 
-static irqreturn_t iproc_adc_interrupt_thread(int irq, void *data)
+static irqreturn_t iproc_adc_interrupt_handler(int irq, void *data)
 {
 	irqreturn_t retval = IRQ_NONE;
 	struct iproc_adc_priv *adc_priv;
@@ -181,7 +181,7 @@
 	adc_priv = iio_priv(indio_dev);
 
 	regmap_read(adc_priv->regmap, IPROC_INTERRUPT_STATUS, &intr_status);
-	dev_dbg(&indio_dev->dev, "iproc_adc_interrupt_thread(),INTRPT_STS:%x\n",
+	dev_dbg(&indio_dev->dev, "iproc_adc_interrupt_handler(),INTRPT_STS:%x\n",
 			intr_status);
 
 	intr_channels = (intr_status & IPROC_ADC_INTR_MASK) >> IPROC_ADC_INTR;
@@ -566,8 +566,8 @@
 	}
 
 	ret = devm_request_threaded_irq(&pdev->dev, adc_priv->irqno,
-				iproc_adc_interrupt_thread,
 				iproc_adc_interrupt_handler,
+				iproc_adc_interrupt_thread,
 				IRQF_SHARED, "iproc-adc", indio_dev);
 	if (ret) {
 		dev_err(&pdev->dev, "request_irq error %d\n", ret);
diff --git a/drivers/iio/adc/max9611.c b/drivers/iio/adc/max9611.c
index ec82106..b0526e4 100644
--- a/drivers/iio/adc/max9611.c
+++ b/drivers/iio/adc/max9611.c
@@ -438,10 +438,10 @@
 	struct max9611_dev *max9611 = iio_priv(dev_to_iio_dev(dev));
 	unsigned int i, r;
 
-	i = max9611->shunt_resistor_uohm / 1000;
-	r = max9611->shunt_resistor_uohm % 1000;
+	i = max9611->shunt_resistor_uohm / 1000000;
+	r = max9611->shunt_resistor_uohm % 1000000;
 
-	return sprintf(buf, "%u.%03u\n", i, r);
+	return sprintf(buf, "%u.%06u\n", i, r);
 }
 
 static IIO_DEVICE_ATTR(in_power_shunt_resistor, 0444,
@@ -536,8 +536,8 @@
 	int ret;
 
 	indio_dev = devm_iio_device_alloc(&client->dev, sizeof(*max9611));
-	if (IS_ERR(indio_dev))
-		return PTR_ERR(indio_dev);
+	if (!indio_dev)
+		return -ENOMEM;
 
 	i2c_set_clientdata(client, indio_dev);
 
diff --git a/drivers/iio/adc/sun4i-gpadc-iio.c b/drivers/iio/adc/sun4i-gpadc-iio.c
index b235273..81d4c39 100644
--- a/drivers/iio/adc/sun4i-gpadc-iio.c
+++ b/drivers/iio/adc/sun4i-gpadc-iio.c
@@ -105,6 +105,8 @@
 	bool				no_irq;
 	/* prevents concurrent reads of temperature and ADC */
 	struct mutex			mutex;
+	struct thermal_zone_device	*tzd;
+	struct device			*sensor_device;
 };
 
 #define SUN4I_GPADC_ADC_CHANNEL(_channel, _name) {		\
@@ -502,7 +504,6 @@
 {
 	struct sun4i_gpadc_iio *info = iio_priv(indio_dev);
 	const struct of_device_id *of_dev;
-	struct thermal_zone_device *tzd;
 	struct resource *mem;
 	void __iomem *base;
 	int ret;
@@ -532,13 +533,14 @@
 	if (!IS_ENABLED(CONFIG_THERMAL_OF))
 		return 0;
 
-	tzd = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, info,
-						   &sun4i_ts_tz_ops);
-	if (IS_ERR(tzd))
+	info->sensor_device = &pdev->dev;
+	info->tzd = thermal_zone_of_sensor_register(info->sensor_device, 0,
+						    info, &sun4i_ts_tz_ops);
+	if (IS_ERR(info->tzd))
 		dev_err(&pdev->dev, "could not register thermal sensor: %ld\n",
-			PTR_ERR(tzd));
+			PTR_ERR(info->tzd));
 
-	return PTR_ERR_OR_ZERO(tzd);
+	return PTR_ERR_OR_ZERO(info->tzd);
 }
 
 static int sun4i_gpadc_probe_mfd(struct platform_device *pdev,
@@ -584,15 +586,15 @@
 		 * of_node, and the device from this driver as third argument to
 		 * return the temperature.
 		 */
-		struct thermal_zone_device *tzd;
-		tzd = devm_thermal_zone_of_sensor_register(pdev->dev.parent, 0,
-							   info,
-							   &sun4i_ts_tz_ops);
-		if (IS_ERR(tzd)) {
+		info->sensor_device = pdev->dev.parent;
+		info->tzd = thermal_zone_of_sensor_register(info->sensor_device,
+							    0, info,
+							    &sun4i_ts_tz_ops);
+		if (IS_ERR(info->tzd)) {
 			dev_err(&pdev->dev,
 				"could not register thermal sensor: %ld\n",
-				PTR_ERR(tzd));
-			return PTR_ERR(tzd);
+				PTR_ERR(info->tzd));
+			return PTR_ERR(info->tzd);
 		}
 	} else {
 		indio_dev->num_channels =
@@ -688,7 +690,13 @@
 
 	pm_runtime_put(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
-	if (!info->no_irq && IS_ENABLED(CONFIG_THERMAL_OF))
+
+	if (!IS_ENABLED(CONFIG_THERMAL_OF))
+		return 0;
+
+	thermal_zone_of_sensor_unregister(info->sensor_device, info->tzd);
+
+	if (!info->no_irq)
 		iio_map_array_unregister(indio_dev);
 
 	return 0;
@@ -700,6 +708,7 @@
 	{ "sun6i-a31-gpadc-iio", (kernel_ulong_t)&sun6i_gpadc_data },
 	{ /* sentinel */ },
 };
+MODULE_DEVICE_TABLE(platform, sun4i_gpadc_id);
 
 static struct platform_driver sun4i_gpadc_driver = {
 	.driver = {
@@ -711,6 +720,7 @@
 	.probe = sun4i_gpadc_probe,
 	.remove = sun4i_gpadc_remove,
 };
+MODULE_DEVICE_TABLE(of, sun4i_gpadc_of_id);
 
 module_platform_driver(sun4i_gpadc_driver);
 
diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c
index 4282cec..6cbed7e 100644
--- a/drivers/iio/adc/ti_am335x_adc.c
+++ b/drivers/iio/adc/ti_am335x_adc.c
@@ -614,7 +614,7 @@
 		return -EINVAL;
 	}
 
-	indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*indio_dev));
+	indio_dev = devm_iio_device_alloc(&pdev->dev, sizeof(*adc_dev));
 	if (indio_dev == NULL) {
 		dev_err(&pdev->dev, "failed to allocate iio device\n");
 		return -ENOMEM;
diff --git a/drivers/iio/industrialio-trigger.c b/drivers/iio/industrialio-trigger.c
index 978e1592..4061fed 100644
--- a/drivers/iio/industrialio-trigger.c
+++ b/drivers/iio/industrialio-trigger.c
@@ -451,7 +451,8 @@
 	return len;
 
 out_trigger_put:
-	iio_trigger_put(trig);
+	if (trig)
+		iio_trigger_put(trig);
 	return ret;
 }
 
diff --git a/drivers/iio/light/ltr501.c b/drivers/iio/light/ltr501.c
index b30e0c1..67838ed 100644
--- a/drivers/iio/light/ltr501.c
+++ b/drivers/iio/light/ltr501.c
@@ -74,9 +74,9 @@
 static const struct reg_field reg_field_it =
 				REG_FIELD(LTR501_ALS_MEAS_RATE, 3, 4);
 static const struct reg_field reg_field_als_intr =
-				REG_FIELD(LTR501_INTR, 0, 0);
-static const struct reg_field reg_field_ps_intr =
 				REG_FIELD(LTR501_INTR, 1, 1);
+static const struct reg_field reg_field_ps_intr =
+				REG_FIELD(LTR501_INTR, 0, 0);
 static const struct reg_field reg_field_als_rate =
 				REG_FIELD(LTR501_ALS_MEAS_RATE, 0, 2);
 static const struct reg_field reg_field_ps_rate =
diff --git a/drivers/iio/proximity/as3935.c b/drivers/iio/proximity/as3935.c
index ddf9bee..aa4df0d 100644
--- a/drivers/iio/proximity/as3935.c
+++ b/drivers/iio/proximity/as3935.c
@@ -40,9 +40,9 @@
 #define AS3935_AFE_PWR_BIT	BIT(0)
 
 #define AS3935_INT		0x03
-#define AS3935_INT_MASK		0x07
+#define AS3935_INT_MASK		0x0f
 #define AS3935_EVENT_INT	BIT(3)
-#define AS3935_NOISE_INT	BIT(1)
+#define AS3935_NOISE_INT	BIT(0)
 
 #define AS3935_DATA		0x07
 #define AS3935_DATA_MASK	0x3F
@@ -215,7 +215,7 @@
 
 	st->buffer[0] = val & AS3935_DATA_MASK;
 	iio_push_to_buffers_with_timestamp(indio_dev, &st->buffer,
-					   pf->timestamp);
+					   iio_get_time_ns(indio_dev));
 err_read:
 	iio_trigger_notify_done(indio_dev->trig);
 
@@ -244,7 +244,7 @@
 
 	switch (val) {
 	case AS3935_EVENT_INT:
-		iio_trigger_poll(st->trig);
+		iio_trigger_poll_chained(st->trig);
 		break;
 	case AS3935_NOISE_INT:
 		dev_warn(&st->spi->dev, "noise level is too high\n");
@@ -269,8 +269,6 @@
 
 static void calibrate_as3935(struct as3935_state *st)
 {
-	mutex_lock(&st->lock);
-
 	/* mask disturber interrupt bit */
 	as3935_write(st, AS3935_INT, BIT(5));
 
@@ -280,8 +278,6 @@
 
 	mdelay(2);
 	as3935_write(st, AS3935_TUNE_CAP, (st->tune_cap / TUNE_CAP_DIV));
-
-	mutex_unlock(&st->lock);
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -318,6 +314,8 @@
 	val &= ~AS3935_AFE_PWR_BIT;
 	ret = as3935_write(st, AS3935_AFE_GAIN, val);
 
+	calibrate_as3935(st);
+
 err_resume:
 	mutex_unlock(&st->lock);
 
diff --git a/drivers/input/mouse/elantech.c b/drivers/input/mouse/elantech.c
index e73d968..f1fa1f1 100644
--- a/drivers/input/mouse/elantech.c
+++ b/drivers/input/mouse/elantech.c
@@ -1118,8 +1118,10 @@
  * Asus UX32VD             0x361f02        00, 15, 0e      clickpad
  * Avatar AVIU-145A2       0x361f00        ?               clickpad
  * Fujitsu LIFEBOOK E544   0x470f00        d0, 12, 09      2 hw buttons
+ * Fujitsu LIFEBOOK E546   0x470f00        50, 12, 09      2 hw buttons
  * Fujitsu LIFEBOOK E547   0x470f00        50, 12, 09      2 hw buttons
  * Fujitsu LIFEBOOK E554   0x570f01        40, 14, 0c      2 hw buttons
+ * Fujitsu LIFEBOOK E557   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
@@ -1525,6 +1527,13 @@
 		},
 	},
 	{
+		/* Fujitsu LIFEBOOK E546  does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E546"),
+		},
+	},
+	{
 		/* Fujitsu LIFEBOOK E547 does not work with crc_enabled == 0 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
@@ -1546,6 +1555,13 @@
 		},
 	},
 	{
+		/* Fujitsu LIFEBOOK E557 does not work with crc_enabled == 0 */
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E557"),
+		},
+	},
+	{
 		/* Fujitsu LIFEBOOK U745 does not work with crc_enabled == 0 */
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
diff --git a/drivers/input/rmi4/rmi_f03.c b/drivers/input/rmi4/rmi_f03.c
index 77dad04..ad71a5e 100644
--- a/drivers/input/rmi4/rmi_f03.c
+++ b/drivers/input/rmi4/rmi_f03.c
@@ -146,7 +146,7 @@
 	if (!serio)
 		return -ENOMEM;
 
-	serio->id.type = SERIO_8042;
+	serio->id.type = SERIO_PS_PSTHRU;
 	serio->write = rmi_f03_pt_write;
 	serio->port_data = f03;
 
diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c
index 9f44ee8..19779b8 100644
--- a/drivers/iommu/of_iommu.c
+++ b/drivers/iommu/of_iommu.c
@@ -118,6 +118,7 @@
 
 	ops = iommu_ops_from_fwnode(fwnode);
 	if ((ops && !ops->of_xlate) ||
+	    !of_device_is_available(iommu_spec->np) ||
 	    (!ops && !of_iommu_driver_present(iommu_spec->np)))
 		return NULL;
 
@@ -236,6 +237,12 @@
 			ops = ERR_PTR(err);
 	}
 
+	/* Ignore all other errors apart from EPROBE_DEFER */
+	if (IS_ERR(ops) && (PTR_ERR(ops) != -EPROBE_DEFER)) {
+		dev_dbg(dev, "Adding to IOMMU failed: %ld\n", PTR_ERR(ops));
+		ops = NULL;
+	}
+
 	return ops;
 }
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 212a677..87edc34 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5174,6 +5174,18 @@
 
 static void no_op(struct percpu_ref *r) {}
 
+int mddev_init_writes_pending(struct mddev *mddev)
+{
+	if (mddev->writes_pending.percpu_count_ptr)
+		return 0;
+	if (percpu_ref_init(&mddev->writes_pending, no_op, 0, GFP_KERNEL) < 0)
+		return -ENOMEM;
+	/* We want to start with the refcount at zero */
+	percpu_ref_put(&mddev->writes_pending);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mddev_init_writes_pending);
+
 static int md_alloc(dev_t dev, char *name)
 {
 	/*
@@ -5239,10 +5251,6 @@
 	blk_queue_make_request(mddev->queue, md_make_request);
 	blk_set_stacking_limits(&mddev->queue->limits);
 
-	if (percpu_ref_init(&mddev->writes_pending, no_op, 0, GFP_KERNEL) < 0)
-		goto abort;
-	/* We want to start with the refcount at zero */
-	percpu_ref_put(&mddev->writes_pending);
 	disk = alloc_disk(1 << shift);
 	if (!disk) {
 		blk_cleanup_queue(mddev->queue);
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 11f1514..0fa1de4 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -648,6 +648,7 @@
 extern void md_wakeup_thread(struct md_thread *thread);
 extern void md_check_recovery(struct mddev *mddev);
 extern void md_reap_sync_thread(struct mddev *mddev);
+extern int mddev_init_writes_pending(struct mddev *mddev);
 extern void md_write_start(struct mddev *mddev, struct bio *bi);
 extern void md_write_inc(struct mddev *mddev, struct bio *bi);
 extern void md_write_end(struct mddev *mddev);
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index af5056d..e1a7e3d 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -3063,6 +3063,8 @@
 			mdname(mddev));
 		return -EIO;
 	}
+	if (mddev_init_writes_pending(mddev) < 0)
+		return -ENOMEM;
 	/*
 	 * copy the already verified devices into our private RAID1
 	 * bookkeeping area. [whatever we allocate in run(),
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 4343d7f..797ed60 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -3611,6 +3611,9 @@
 	int first = 1;
 	bool discard_supported = false;
 
+	if (mddev_init_writes_pending(mddev) < 0)
+		return -ENOMEM;
+
 	if (mddev->private == NULL) {
 		conf = setup_conf(mddev);
 		if (IS_ERR(conf))
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 7220646..ec0f951 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7118,6 +7118,9 @@
 	long long min_offset_diff = 0;
 	int first = 1;
 
+	if (mddev_init_writes_pending(mddev) < 0)
+		return -ENOMEM;
+
 	if (mddev->recovery_cp != MaxSector)
 		pr_notice("md/raid:%s: not clean -- starting background reconstruction\n",
 			  mdname(mddev));
diff --git a/drivers/memory/atmel-ebi.c b/drivers/memory/atmel-ebi.c
index 35910f9..99e644c 100644
--- a/drivers/memory/atmel-ebi.c
+++ b/drivers/memory/atmel-ebi.c
@@ -581,7 +581,7 @@
 	return of_platform_populate(np, NULL, NULL, dev);
 }
 
-static int atmel_ebi_resume(struct device *dev)
+static __maybe_unused int atmel_ebi_resume(struct device *dev)
 {
 	struct atmel_ebi *ebi = dev_get_drvdata(dev);
 	struct atmel_ebi_dev *ebid;
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index 17b433f..0761271 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -159,11 +159,8 @@
 
 	/* Do this outside the status_mutex to avoid a circular dependency with
 	 * the locking in cxl_mmap_fault() */
-	if (copy_from_user(&work, uwork,
-			   sizeof(struct cxl_ioctl_start_work))) {
-		rc = -EFAULT;
-		goto out;
-	}
+	if (copy_from_user(&work, uwork, sizeof(work)))
+		return -EFAULT;
 
 	mutex_lock(&ctx->status_mutex);
 	if (ctx->status != OPENED) {
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index 871a2f0..8d6ea97 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -1302,13 +1302,16 @@
 
 void cxl_native_release_psl_err_irq(struct cxl *adapter)
 {
-	if (adapter->native->err_virq != irq_find_mapping(NULL, adapter->native->err_hwirq))
+	if (adapter->native->err_virq == 0 ||
+	    adapter->native->err_virq !=
+	    irq_find_mapping(NULL, adapter->native->err_hwirq))
 		return;
 
 	cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000);
 	cxl_unmap_irq(adapter->native->err_virq, adapter);
 	cxl_ops->release_one_irq(adapter, adapter->native->err_hwirq);
 	kfree(adapter->irq_name);
+	adapter->native->err_virq = 0;
 }
 
 int cxl_native_register_serr_irq(struct cxl_afu *afu)
@@ -1346,13 +1349,15 @@
 
 void cxl_native_release_serr_irq(struct cxl_afu *afu)
 {
-	if (afu->serr_virq != irq_find_mapping(NULL, afu->serr_hwirq))
+	if (afu->serr_virq == 0 ||
+	    afu->serr_virq != irq_find_mapping(NULL, afu->serr_hwirq))
 		return;
 
 	cxl_p1n_write(afu, CXL_PSL_SERR_An, 0x0000000000000000);
 	cxl_unmap_irq(afu->serr_virq, afu);
 	cxl_ops->release_one_irq(afu->adapter, afu->serr_hwirq);
 	kfree(afu->err_irq_name);
+	afu->serr_virq = 0;
 }
 
 int cxl_native_register_psl_irq(struct cxl_afu *afu)
@@ -1375,12 +1380,15 @@
 
 void cxl_native_release_psl_irq(struct cxl_afu *afu)
 {
-	if (afu->native->psl_virq != irq_find_mapping(NULL, afu->native->psl_hwirq))
+	if (afu->native->psl_virq == 0 ||
+	    afu->native->psl_virq !=
+	    irq_find_mapping(NULL, afu->native->psl_hwirq))
 		return;
 
 	cxl_unmap_irq(afu->native->psl_virq, afu);
 	cxl_ops->release_one_irq(afu->adapter, afu->native->psl_hwirq);
 	kfree(afu->psl_irq_name);
+	afu->native->psl_virq = 0;
 }
 
 static void recover_psl_err(struct cxl_afu *afu, u64 errstat)
diff --git a/drivers/misc/mei/bus.c b/drivers/misc/mei/bus.c
index d1928fd..07aad857 100644
--- a/drivers/misc/mei/bus.c
+++ b/drivers/misc/mei/bus.c
@@ -763,8 +763,10 @@
 {
 	struct mei_cl_device *cldev = to_mei_cl_device(dev);
 	const uuid_le *uuid = mei_me_cl_uuid(cldev->me_cl);
+	u8 version = mei_me_cl_ver(cldev->me_cl);
 
-	return scnprintf(buf, PAGE_SIZE, "mei:%s:%pUl:", cldev->name, uuid);
+	return scnprintf(buf, PAGE_SIZE, "mei:%s:%pUl:%02X:",
+			 cldev->name, uuid, version);
 }
 static DEVICE_ATTR_RO(modalias);
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index a609264..903d581 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -56,7 +56,7 @@
 static int nvme_char_major;
 module_param(nvme_char_major, int, 0);
 
-static unsigned long default_ps_max_latency_us = 25000;
+static unsigned long default_ps_max_latency_us = 100000;
 module_param(default_ps_max_latency_us, ulong, 0644);
 MODULE_PARM_DESC(default_ps_max_latency_us,
 		 "max power saving latency for new devices; use PM QOS to change per device");
@@ -1342,7 +1342,7 @@
 	 * transitioning between power states.  Therefore, when running
 	 * in any given state, we will enter the next lower-power
 	 * non-operational state after waiting 50 * (enlat + exlat)
-	 * microseconds, as long as that state's total latency is under
+	 * microseconds, as long as that state's exit latency is under
 	 * the requested maximum latency.
 	 *
 	 * We will not autonomously enter any non-operational state for
@@ -1387,7 +1387,7 @@
 		 * lowest-power state, not the number of states.
 		 */
 		for (state = (int)ctrl->npss; state >= 0; state--) {
-			u64 total_latency_us, transition_ms;
+			u64 total_latency_us, exit_latency_us, transition_ms;
 
 			if (target)
 				table->entries[state] = target;
@@ -1408,12 +1408,15 @@
 			      NVME_PS_FLAGS_NON_OP_STATE))
 				continue;
 
-			total_latency_us =
-				(u64)le32_to_cpu(ctrl->psd[state].entry_lat) +
-				+ le32_to_cpu(ctrl->psd[state].exit_lat);
-			if (total_latency_us > ctrl->ps_max_latency_us)
+			exit_latency_us =
+				(u64)le32_to_cpu(ctrl->psd[state].exit_lat);
+			if (exit_latency_us > ctrl->ps_max_latency_us)
 				continue;
 
+			total_latency_us =
+				exit_latency_us +
+				le32_to_cpu(ctrl->psd[state].entry_lat);
+
 			/*
 			 * This state is good.  Use it as the APST idle
 			 * target for higher power states.
@@ -2438,6 +2441,10 @@
 	struct nvme_ns *ns;
 
 	mutex_lock(&ctrl->namespaces_mutex);
+
+	/* Forcibly start all queues to avoid having stuck requests */
+	blk_mq_start_hw_queues(ctrl->admin_q);
+
 	list_for_each_entry(ns, &ctrl->namespaces, list) {
 		/*
 		 * Revalidating a dead namespace sets capacity to 0. This will
diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 5b14cbe..92964ce 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1139,6 +1139,7 @@
 /* *********************** NVME Ctrl Routines **************************** */
 
 static void __nvme_fc_final_op_cleanup(struct request *rq);
+static void nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg);
 
 static int
 nvme_fc_reinit_request(void *data, struct request *rq)
@@ -1265,7 +1266,7 @@
 	struct nvme_command *sqe = &op->cmd_iu.sqe;
 	__le16 status = cpu_to_le16(NVME_SC_SUCCESS << 1);
 	union nvme_result result;
-	bool complete_rq;
+	bool complete_rq, terminate_assoc = true;
 
 	/*
 	 * WARNING:
@@ -1294,6 +1295,14 @@
 	 * fabricate a CQE, the following fields will not be set as they
 	 * are not referenced:
 	 *      cqe.sqid,  cqe.sqhd,  cqe.command_id
+	 *
+	 * Failure or error of an individual i/o, in a transport
+	 * detected fashion unrelated to the nvme completion status,
+	 * potentially cause the initiator and target sides to get out
+	 * of sync on SQ head/tail (aka outstanding io count allowed).
+	 * Per FC-NVME spec, failure of an individual command requires
+	 * the connection to be terminated, which in turn requires the
+	 * association to be terminated.
 	 */
 
 	fc_dma_sync_single_for_cpu(ctrl->lport->dev, op->fcp_req.rspdma,
@@ -1359,6 +1368,8 @@
 		goto done;
 	}
 
+	terminate_assoc = false;
+
 done:
 	if (op->flags & FCOP_FLAGS_AEN) {
 		nvme_complete_async_event(&queue->ctrl->ctrl, status, &result);
@@ -1366,7 +1377,7 @@
 		atomic_set(&op->state, FCPOP_STATE_IDLE);
 		op->flags = FCOP_FLAGS_AEN;	/* clear other flags */
 		nvme_fc_ctrl_put(ctrl);
-		return;
+		goto check_error;
 	}
 
 	complete_rq = __nvme_fc_fcpop_chk_teardowns(ctrl, op);
@@ -1379,6 +1390,10 @@
 		nvme_end_request(rq, status, result);
 	} else
 		__nvme_fc_final_op_cleanup(rq);
+
+check_error:
+	if (terminate_assoc)
+		nvme_fc_error_recovery(ctrl, "transport detected io error");
 }
 
 static int
@@ -2791,6 +2806,7 @@
 		ctrl->ctrl.opts = NULL;
 		/* initiate nvme ctrl ref counting teardown */
 		nvme_uninit_ctrl(&ctrl->ctrl);
+		nvme_put_ctrl(&ctrl->ctrl);
 
 		/* as we're past the point where we transition to the ref
 		 * counting teardown path, if we return a bad pointer here,
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index d52701df..951042a 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1367,7 +1367,7 @@
 	bool nssro = dev->subsystem && (csts & NVME_CSTS_NSSRO);
 
 	/* If there is a reset ongoing, we shouldn't reset again. */
-	if (work_busy(&dev->reset_work))
+	if (dev->ctrl.state == NVME_CTRL_RESETTING)
 		return false;
 
 	/* We shouldn't reset unless the controller is on fatal error state
@@ -1903,7 +1903,7 @@
 	bool was_suspend = !!(dev->ctrl.ctrl_config & NVME_CC_SHN_NORMAL);
 	int result = -ENODEV;
 
-	if (WARN_ON(dev->ctrl.state == NVME_CTRL_RESETTING))
+	if (WARN_ON(dev->ctrl.state != NVME_CTRL_RESETTING))
 		goto out;
 
 	/*
@@ -1913,9 +1913,6 @@
 	if (dev->ctrl.ctrl_config & NVME_CC_ENABLE)
 		nvme_dev_disable(dev, false);
 
-	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING))
-		goto out;
-
 	result = nvme_pci_enable(dev);
 	if (result)
 		goto out;
@@ -2009,8 +2006,8 @@
 {
 	if (!dev->ctrl.admin_q || blk_queue_dying(dev->ctrl.admin_q))
 		return -ENODEV;
-	if (work_busy(&dev->reset_work))
-		return -ENODEV;
+	if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING))
+		return -EBUSY;
 	if (!queue_work(nvme_workq, &dev->reset_work))
 		return -EBUSY;
 	return 0;
@@ -2136,6 +2133,7 @@
 	if (result)
 		goto release_pools;
 
+	nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING);
 	dev_info(dev->ctrl.device, "pci function %s\n", dev_name(&pdev->dev));
 
 	queue_work(nvme_workq, &dev->reset_work);
@@ -2179,6 +2177,7 @@
 
 	nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
 
+	cancel_work_sync(&dev->reset_work);
 	pci_set_drvdata(pdev, NULL);
 
 	if (!pci_device_is_present(pdev)) {
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 28bd255..24397d3 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -753,28 +753,26 @@
 	if (ret)
 		goto requeue;
 
-	blk_mq_start_stopped_hw_queues(ctrl->ctrl.admin_q, true);
-
 	ret = nvmf_connect_admin_queue(&ctrl->ctrl);
 	if (ret)
-		goto stop_admin_q;
+		goto requeue;
 
 	set_bit(NVME_RDMA_Q_LIVE, &ctrl->queues[0].flags);
 
 	ret = nvme_enable_ctrl(&ctrl->ctrl, ctrl->cap);
 	if (ret)
-		goto stop_admin_q;
+		goto requeue;
 
 	nvme_start_keep_alive(&ctrl->ctrl);
 
 	if (ctrl->queue_count > 1) {
 		ret = nvme_rdma_init_io_queues(ctrl);
 		if (ret)
-			goto stop_admin_q;
+			goto requeue;
 
 		ret = nvme_rdma_connect_io_queues(ctrl);
 		if (ret)
-			goto stop_admin_q;
+			goto requeue;
 	}
 
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
@@ -782,7 +780,6 @@
 	ctrl->ctrl.opts->nr_reconnects = 0;
 
 	if (ctrl->queue_count > 1) {
-		nvme_start_queues(&ctrl->ctrl);
 		nvme_queue_scan(&ctrl->ctrl);
 		nvme_queue_async_events(&ctrl->ctrl);
 	}
@@ -791,8 +788,6 @@
 
 	return;
 
-stop_admin_q:
-	blk_mq_stop_hw_queues(ctrl->ctrl.admin_q);
 requeue:
 	dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
 			ctrl->ctrl.opts->nr_reconnects);
@@ -823,6 +818,13 @@
 	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
 				nvme_cancel_request, &ctrl->ctrl);
 
+	/*
+	 * queues are not a live anymore, so restart the queues to fail fast
+	 * new IO
+	 */
+	blk_mq_start_stopped_hw_queues(ctrl->ctrl.admin_q, true);
+	nvme_start_queues(&ctrl->ctrl);
+
 	nvme_rdma_reconnect_or_remove(ctrl);
 }
 
@@ -1433,7 +1435,7 @@
 /*
  * We cannot accept any other command until the Connect command has completed.
  */
-static inline bool nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue,
+static inline int nvme_rdma_queue_is_ready(struct nvme_rdma_queue *queue,
 		struct request *rq)
 {
 	if (unlikely(!test_bit(NVME_RDMA_Q_LIVE, &queue->flags))) {
@@ -1441,11 +1443,22 @@
 
 		if (!blk_rq_is_passthrough(rq) ||
 		    cmd->common.opcode != nvme_fabrics_command ||
-		    cmd->fabrics.fctype != nvme_fabrics_type_connect)
-			return false;
+		    cmd->fabrics.fctype != nvme_fabrics_type_connect) {
+			/*
+			 * reconnecting state means transport disruption, which
+			 * can take a long time and even might fail permanently,
+			 * so we can't let incoming I/O be requeued forever.
+			 * fail it fast to allow upper layers a chance to
+			 * failover.
+			 */
+			if (queue->ctrl->ctrl.state == NVME_CTRL_RECONNECTING)
+				return -EIO;
+			else
+				return -EAGAIN;
+		}
 	}
 
-	return true;
+	return 0;
 }
 
 static int nvme_rdma_queue_rq(struct blk_mq_hw_ctx *hctx,
@@ -1463,8 +1476,9 @@
 
 	WARN_ON_ONCE(rq->tag < 0);
 
-	if (!nvme_rdma_queue_is_ready(queue, rq))
-		return BLK_MQ_RQ_QUEUE_BUSY;
+	ret = nvme_rdma_queue_is_ready(queue, rq);
+	if (unlikely(ret))
+		goto err;
 
 	dev = queue->device->dev;
 	ib_dma_sync_single_for_cpu(dev, sqe->dma,
diff --git a/drivers/of/device.c b/drivers/of/device.c
index 9416d05..28c38c7 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -144,8 +144,8 @@
 		coherent ? " " : " not ");
 
 	iommu = of_iommu_configure(dev, np);
-	if (IS_ERR(iommu))
-		return PTR_ERR(iommu);
+	if (IS_ERR(iommu) && PTR_ERR(iommu) == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
 
 	dev_dbg(dev, "device is%sbehind an iommu\n",
 		iommu ? " " : " not ");
diff --git a/drivers/phy/phy-qcom-qmp.c b/drivers/phy/phy-qcom-qmp.c
index 727e23b..78ca628 100644
--- a/drivers/phy/phy-qcom-qmp.c
+++ b/drivers/phy/phy-qcom-qmp.c
@@ -844,7 +844,7 @@
 	int num = qmp->cfg->num_vregs;
 	int i;
 
-	qmp->vregs = devm_kcalloc(dev, num, sizeof(qmp->vregs), GFP_KERNEL);
+	qmp->vregs = devm_kcalloc(dev, num, sizeof(*qmp->vregs), GFP_KERNEL);
 	if (!qmp->vregs)
 		return -ENOMEM;
 
@@ -983,16 +983,16 @@
 	 * Resources are indexed as: tx -> 0; rx -> 1; pcs -> 2.
 	 */
 	qphy->tx = of_iomap(np, 0);
-	if (IS_ERR(qphy->tx))
-		return PTR_ERR(qphy->tx);
+	if (!qphy->tx)
+		return -ENOMEM;
 
 	qphy->rx = of_iomap(np, 1);
-	if (IS_ERR(qphy->rx))
-		return PTR_ERR(qphy->rx);
+	if (!qphy->rx)
+		return -ENOMEM;
 
 	qphy->pcs = of_iomap(np, 2);
-	if (IS_ERR(qphy->pcs))
-		return PTR_ERR(qphy->pcs);
+	if (!qphy->pcs)
+		return -ENOMEM;
 
 	/*
 	 * Get PHY's Pipe clock, if any. USB3 and PCIe are PIPE3
diff --git a/drivers/platform/goldfish/goldfish_pipe.c b/drivers/platform/goldfish/goldfish_pipe.c
index 2de1e60..5f36721 100644
--- a/drivers/platform/goldfish/goldfish_pipe.c
+++ b/drivers/platform/goldfish/goldfish_pipe.c
@@ -704,7 +704,7 @@
 		/* Reallocate the array */
 		u32 new_capacity = 2 * dev->pipes_capacity;
 		struct goldfish_pipe **pipes =
-			kcalloc(new_capacity, sizeof(*pipes), GFP_KERNEL);
+			kcalloc(new_capacity, sizeof(*pipes), GFP_ATOMIC);
 		if (!pipes)
 			return -ENOMEM;
 		memcpy(pipes, dev->pipes, sizeof(*pipes) * dev->pipes_capacity);
diff --git a/drivers/reset/hisilicon/hi6220_reset.c b/drivers/reset/hisilicon/hi6220_reset.c
index 35ce53e..d5e5229 100644
--- a/drivers/reset/hisilicon/hi6220_reset.c
+++ b/drivers/reset/hisilicon/hi6220_reset.c
@@ -155,3 +155,5 @@
 }
 
 postcore_initcall(hi6220_reset_init);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/scsi/bnx2fc/bnx2fc.h b/drivers/scsi/bnx2fc/bnx2fc.h
index 4fc8ed5..1f424e4 100644
--- a/drivers/scsi/bnx2fc/bnx2fc.h
+++ b/drivers/scsi/bnx2fc/bnx2fc.h
@@ -191,6 +191,7 @@
 	struct bnx2fc_cmd_mgr *cmd_mgr;
 	spinlock_t hba_lock;
 	struct mutex hba_mutex;
+	struct mutex hba_stats_mutex;
 	unsigned long adapter_state;
 		#define ADAPTER_STATE_UP		0
 		#define ADAPTER_STATE_GOING_DOWN	1
diff --git a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
index 93b5a00..902722d 100644
--- a/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
+++ b/drivers/scsi/bnx2fc/bnx2fc_fcoe.c
@@ -663,15 +663,17 @@
 	if (!fw_stats)
 		return NULL;
 
+	mutex_lock(&hba->hba_stats_mutex);
+
 	bnx2fc_stats = fc_get_host_stats(shost);
 
 	init_completion(&hba->stat_req_done);
 	if (bnx2fc_send_stat_req(hba))
-		return bnx2fc_stats;
+		goto unlock_stats_mutex;
 	rc = wait_for_completion_timeout(&hba->stat_req_done, (2 * HZ));
 	if (!rc) {
 		BNX2FC_HBA_DBG(lport, "FW stat req timed out\n");
-		return bnx2fc_stats;
+		goto unlock_stats_mutex;
 	}
 	BNX2FC_STATS(hba, rx_stat2, fc_crc_cnt);
 	bnx2fc_stats->invalid_crc_count += hba->bfw_stats.fc_crc_cnt;
@@ -693,6 +695,9 @@
 
 	memcpy(&hba->prev_stats, hba->stats_buffer,
 	       sizeof(struct fcoe_statistics_params));
+
+unlock_stats_mutex:
+	mutex_unlock(&hba->hba_stats_mutex);
 	return bnx2fc_stats;
 }
 
@@ -1340,6 +1345,7 @@
 	}
 	spin_lock_init(&hba->hba_lock);
 	mutex_init(&hba->hba_mutex);
+	mutex_init(&hba->hba_stats_mutex);
 
 	hba->cnic = cnic;
 
diff --git a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
index 1076c15..0aae094 100644
--- a/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
+++ b/drivers/scsi/cxgbi/cxgb4i/cxgb4i.c
@@ -1595,7 +1595,6 @@
 		cxgbi_sock_put(csk);
 	}
 	csk->dst = NULL;
-	csk->cdev = NULL;
 }
 
 static int init_act_open(struct cxgbi_sock *csk)
diff --git a/drivers/scsi/cxgbi/libcxgbi.c b/drivers/scsi/cxgbi/libcxgbi.c
index fb06974..e4c83b7 100644
--- a/drivers/scsi/cxgbi/libcxgbi.c
+++ b/drivers/scsi/cxgbi/libcxgbi.c
@@ -867,7 +867,8 @@
 	log_debug(1 << CXGBI_DBG_SOCK, "csk 0x%p,%u,0x%lx,%u.\n",
 		csk, (csk)->state, (csk)->flags, (csk)->tid);
 	spin_lock_bh(&csk->lock);
-	dst_confirm(csk->dst);
+	if (csk->dst)
+		dst_confirm(csk->dst);
 	data_lost = skb_queue_len(&csk->receive_queue);
 	__skb_queue_purge(&csk->receive_queue);
 
@@ -882,7 +883,8 @@
 	}
 
 	if (close_req) {
-		if (data_lost)
+		if (!cxgbi_sock_flag(csk, CTPF_LOGOUT_RSP_RCVD) ||
+		    data_lost)
 			csk->cdev->csk_send_abort_req(csk);
 		else
 			csk->cdev->csk_send_close_req(csk);
@@ -1186,9 +1188,10 @@
 				cxgbi_ulp_extra_len(cxgbi_skcb_ulp_mode(skb));
 		skb = next;
 	}
-done:
+
 	if (likely(skb_queue_len(&csk->write_queue)))
 		cdev->csk_push_tx_frames(csk, 1);
+done:
 	spin_unlock_bh(&csk->lock);
 	return copied;
 
@@ -1568,9 +1571,12 @@
 	}
 }
 
-static int skb_read_pdu_bhs(struct iscsi_conn *conn, struct sk_buff *skb)
+static int
+skb_read_pdu_bhs(struct cxgbi_sock *csk, struct iscsi_conn *conn,
+		 struct sk_buff *skb)
 {
 	struct iscsi_tcp_conn *tcp_conn = conn->dd_data;
+	int err;
 
 	log_debug(1 << CXGBI_DBG_PDU_RX,
 		"conn 0x%p, skb 0x%p, len %u, flag 0x%lx.\n",
@@ -1608,7 +1614,16 @@
 		}
 	}
 
-	return read_pdu_skb(conn, skb, 0, 0);
+	err = read_pdu_skb(conn, skb, 0, 0);
+	if (likely(err >= 0)) {
+		struct iscsi_hdr *hdr = (struct iscsi_hdr *)skb->data;
+		u8 opcode = hdr->opcode & ISCSI_OPCODE_MASK;
+
+		if (unlikely(opcode == ISCSI_OP_LOGOUT_RSP))
+			cxgbi_sock_set_flag(csk, CTPF_LOGOUT_RSP_RCVD);
+	}
+
+	return err;
 }
 
 static int skb_read_pdu_data(struct iscsi_conn *conn, struct sk_buff *lskb,
@@ -1713,7 +1728,7 @@
 			cxgbi_skcb_rx_pdulen(skb));
 
 		if (cxgbi_skcb_test_flag(skb, SKCBF_RX_COALESCED)) {
-			err = skb_read_pdu_bhs(conn, skb);
+			err = skb_read_pdu_bhs(csk, conn, skb);
 			if (err < 0) {
 				pr_err("coalesced bhs, csk 0x%p, skb 0x%p,%u, "
 					"f 0x%lx, plen %u.\n",
@@ -1731,7 +1746,7 @@
 					cxgbi_skcb_flags(skb),
 					cxgbi_skcb_rx_pdulen(skb));
 		} else {
-			err = skb_read_pdu_bhs(conn, skb);
+			err = skb_read_pdu_bhs(csk, conn, skb);
 			if (err < 0) {
 				pr_err("bhs, csk 0x%p, skb 0x%p,%u, "
 					"f 0x%lx, plen %u.\n",
diff --git a/drivers/scsi/cxgbi/libcxgbi.h b/drivers/scsi/cxgbi/libcxgbi.h
index 239462a..37f07aa 100644
--- a/drivers/scsi/cxgbi/libcxgbi.h
+++ b/drivers/scsi/cxgbi/libcxgbi.h
@@ -187,6 +187,7 @@
 	CTPF_HAS_ATID,		/* reserved atid */
 	CTPF_HAS_TID,		/* reserved hw tid */
 	CTPF_OFFLOAD_DOWN,	/* offload function off */
+	CTPF_LOGOUT_RSP_RCVD,   /* received logout response */
 };
 
 struct cxgbi_skb_rx_cb {
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index 8912767..da669dc 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -127,7 +127,7 @@
 void lpfc_do_scr_ns_plogi(struct lpfc_hba *, struct lpfc_vport *);
 int lpfc_check_sparm(struct lpfc_vport *, struct lpfc_nodelist *,
 		     struct serv_parm *, uint32_t, int);
-int lpfc_els_abort(struct lpfc_hba *, struct lpfc_nodelist *);
+void lpfc_els_abort(struct lpfc_hba *, struct lpfc_nodelist *);
 void lpfc_more_plogi(struct lpfc_vport *);
 void lpfc_more_adisc(struct lpfc_vport *);
 void lpfc_end_rscn(struct lpfc_vport *);
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index f2cd19c..24ce96d 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -978,9 +978,10 @@
 					 ndlp, did, ndlp->nlp_fc4_type,
 					 FC_TYPE_FCP, FC_TYPE_NVME);
 			ndlp->nlp_prev_state = NLP_STE_REG_LOGIN_ISSUE;
+
+			lpfc_nlp_set_state(vport, ndlp, NLP_STE_PRLI_ISSUE);
+			lpfc_issue_els_prli(vport, ndlp, 0);
 		}
-		lpfc_nlp_set_state(vport, ndlp, NLP_STE_PRLI_ISSUE);
-		lpfc_issue_els_prli(vport, ndlp, 0);
 	} else
 		lpfc_printf_vlog(vport, KERN_ERR, LOG_DISCOVERY,
 				 "3065 GFT_ID failed x%08x\n", irsp->ulpStatus);
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index bff3de0..f74cb01 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -206,7 +206,7 @@
  * associated with a LPFC_NODELIST entry. This
  * routine effectively results in a "software abort".
  */
-int
+void
 lpfc_els_abort(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 {
 	LIST_HEAD(abort_list);
@@ -215,6 +215,10 @@
 
 	pring = lpfc_phba_elsring(phba);
 
+	/* In case of error recovery path, we might have a NULL pring here */
+	if (!pring)
+		return;
+
 	/* Abort outstanding I/O on NPort <nlp_DID> */
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_DISCOVERY,
 			 "2819 Abort outstanding I/O on NPort x%x "
@@ -273,7 +277,6 @@
 			      IOSTAT_LOCAL_REJECT, IOERR_SLI_ABORTED);
 
 	lpfc_cancel_retry_delay_tmo(phba->pport, ndlp);
-	return 0;
 }
 
 static int
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 074a6b5..518b15e 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -799,8 +799,8 @@
 	}
 	spin_unlock_irqrestore(&ctxp->ctxlock, flags);
 
-	lpfc_nvmeio_data(phba, "NVMET FCP FREE: xri x%x ste %d\n", ctxp->oxid,
-			 ctxp->state, 0);
+	lpfc_nvmeio_data(phba, "NVMET FCP FREE: xri x%x ste %d abt %d\n", ctxp->oxid,
+			 ctxp->state, aborting);
 
 	atomic_inc(&lpfc_nvmep->xmt_fcp_release);
 
diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
index 16d1cd5..ca3420d 100644
--- a/drivers/scsi/qla2xxx/qla_bsg.c
+++ b/drivers/scsi/qla2xxx/qla_bsg.c
@@ -730,6 +730,8 @@
 		return -EIO;
 	}
 
+	memset(&elreq, 0, sizeof(elreq));
+
 	elreq.req_sg_cnt = dma_map_sg(&ha->pdev->dev,
 		bsg_job->request_payload.sg_list, bsg_job->request_payload.sg_cnt,
 		DMA_TO_DEVICE);
@@ -795,10 +797,9 @@
 
 	if (atomic_read(&vha->loop_state) == LOOP_READY &&
 	    (ha->current_topology == ISP_CFG_F ||
-	    ((IS_QLA81XX(ha) || IS_QLA8031(ha) || IS_QLA8044(ha)) &&
-	    le32_to_cpu(*(uint32_t *)req_data) == ELS_OPCODE_BYTE
-	    && req_data_len == MAX_ELS_FRAME_PAYLOAD)) &&
-		elreq.options == EXTERNAL_LOOPBACK) {
+	    (le32_to_cpu(*(uint32_t *)req_data) == ELS_OPCODE_BYTE &&
+	     req_data_len == MAX_ELS_FRAME_PAYLOAD)) &&
+	    elreq.options == EXTERNAL_LOOPBACK) {
 		type = "FC_BSG_HST_VENDOR_ECHO_DIAG";
 		ql_dbg(ql_dbg_user, vha, 0x701e,
 		    "BSG request type: %s.\n", type);
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 51b4179..88748a6 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -1131,7 +1131,7 @@
 
 	/* Mailbox registers. */
 	mbx_reg = &reg->mailbox0;
-	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, dmp_reg++)
+	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, mbx_reg++)
 		fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg));
 
 	/* Transfer sequence registers. */
@@ -2090,7 +2090,7 @@
 
 	/* Mailbox registers. */
 	mbx_reg = &reg->mailbox0;
-	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, dmp_reg++)
+	for (cnt = 0; cnt < sizeof(fw->mailbox_reg) / 2; cnt++, mbx_reg++)
 		fw->mailbox_reg[cnt] = htons(RD_REG_WORD(mbx_reg));
 
 	/* Transfer sequence registers. */
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index ae11901..eddbc12 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -3425,6 +3425,7 @@
 	uint8_t 	max_req_queues;
 	uint8_t 	max_rsp_queues;
 	uint8_t		max_qpairs;
+	uint8_t		num_qpairs;
 	struct qla_qpair *base_qpair;
 	struct qla_npiv_entry *npiv_info;
 	uint16_t	nvram_npiv_size;
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 0347433..0391fc3 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -7543,12 +7543,13 @@
 		/* Assign available que pair id */
 		mutex_lock(&ha->mq_lock);
 		qpair_id = find_first_zero_bit(ha->qpair_qid_map, ha->max_qpairs);
-		if (qpair_id >= ha->max_qpairs) {
+		if (ha->num_qpairs >= ha->max_qpairs) {
 			mutex_unlock(&ha->mq_lock);
 			ql_log(ql_log_warn, vha, 0x0183,
 			    "No resources to create additional q pair.\n");
 			goto fail_qid_map;
 		}
+		ha->num_qpairs++;
 		set_bit(qpair_id, ha->qpair_qid_map);
 		ha->queue_pair_map[qpair_id] = qpair;
 		qpair->id = qpair_id;
@@ -7635,6 +7636,7 @@
 fail_msix:
 	ha->queue_pair_map[qpair_id] = NULL;
 	clear_bit(qpair_id, ha->qpair_qid_map);
+	ha->num_qpairs--;
 	mutex_unlock(&ha->mq_lock);
 fail_qid_map:
 	kfree(qpair);
@@ -7660,6 +7662,7 @@
 	mutex_lock(&ha->mq_lock);
 	ha->queue_pair_map[qpair->id] = NULL;
 	clear_bit(qpair->id, ha->qpair_qid_map);
+	ha->num_qpairs--;
 	list_del(&qpair->qp_list_elem);
 	if (list_empty(&vha->qp_list))
 		vha->flags.qpairs_available = 0;
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index 66df6cec..c61a6a8 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -129,28 +129,16 @@
 }
 
 static inline void
-qla2x00_clean_dsd_pool(struct qla_hw_data *ha, srb_t *sp,
-	struct qla_tgt_cmd *tc)
+qla2x00_clean_dsd_pool(struct qla_hw_data *ha, struct crc_context *ctx)
 {
-	struct dsd_dma *dsd_ptr, *tdsd_ptr;
-	struct crc_context *ctx;
-
-	if (sp)
-		ctx = (struct crc_context *)GET_CMD_CTX_SP(sp);
-	else if (tc)
-		ctx = (struct crc_context *)tc->ctx;
-	else {
-		BUG();
-		return;
-	}
+	struct dsd_dma *dsd, *tdsd;
 
 	/* clean up allocated prev pool */
-	list_for_each_entry_safe(dsd_ptr, tdsd_ptr,
-	    &ctx->dsd_list, list) {
-		dma_pool_free(ha->dl_dma_pool, dsd_ptr->dsd_addr,
-		    dsd_ptr->dsd_list_dma);
-		list_del(&dsd_ptr->list);
-		kfree(dsd_ptr);
+	list_for_each_entry_safe(dsd, tdsd, &ctx->dsd_list, list) {
+		dma_pool_free(ha->dl_dma_pool, dsd->dsd_addr,
+		    dsd->dsd_list_dma);
+		list_del(&dsd->list);
+		kfree(dsd);
 	}
 	INIT_LIST_HEAD(&ctx->dsd_list);
 }
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index aac0350..2572121 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -3282,7 +3282,7 @@
 	}
 
 	/* Enable MSI-X vector for response queue update for queue 0 */
-	if (IS_QLA83XX(ha) || IS_QLA27XX(ha)) {
+	if (IS_QLA25XX(ha) || IS_QLA83XX(ha) || IS_QLA27XX(ha)) {
 		if (ha->msixbase && ha->mqiobase &&
 		    (ha->max_rsp_queues > 1 || ha->max_req_queues > 1 ||
 		     ql2xmqsupport))
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index a113ab3..cba1fc5 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -3676,15 +3676,6 @@
 				qlt_update_host_map(vha, id);
 			}
 
-			fc_host_port_name(vha->host) =
-			    wwn_to_u64(vha->port_name);
-
-			if (qla_ini_mode_enabled(vha))
-				ql_dbg(ql_dbg_mbx, vha, 0x1018,
-				    "FA-WWN portname %016llx (%x)\n",
-				    fc_host_port_name(vha->host),
-				    rptid_entry->vp_status);
-
 			set_bit(REGISTER_FC4_NEEDED, &vha->dpc_flags);
 			set_bit(REGISTER_FDMI_NEEDED, &vha->dpc_flags);
 		} else {
@@ -4821,9 +4812,9 @@
 
 	memset(mcp->mb, 0 , sizeof(mcp->mb));
 	mcp->mb[0] = MBC_DIAGNOSTIC_ECHO;
-	mcp->mb[1] = mreq->options | BIT_6;	/* BIT_6 specifies 64bit address */
+	/* BIT_6 specifies 64bit address */
+	mcp->mb[1] = mreq->options | BIT_15 | BIT_6;
 	if (IS_CNA_CAPABLE(ha)) {
-		mcp->mb[1] |= BIT_15;
 		mcp->mb[2] = vha->fcoe_fcf_idx;
 	}
 	mcp->mb[16] = LSW(mreq->rcv_dma);
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 1c79579..79f0502 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -630,29 +630,34 @@
 		sp->flags &= ~SRB_CRC_PROT_DMA_VALID;
 	}
 
+	if (!ctx)
+		goto end;
+
 	if (sp->flags & SRB_CRC_CTX_DSD_VALID) {
 		/* List assured to be having elements */
-		qla2x00_clean_dsd_pool(ha, sp, NULL);
+		qla2x00_clean_dsd_pool(ha, ctx);
 		sp->flags &= ~SRB_CRC_CTX_DSD_VALID;
 	}
 
 	if (sp->flags & SRB_CRC_CTX_DMA_VALID) {
-		dma_pool_free(ha->dl_dma_pool, ctx,
-		    ((struct crc_context *)ctx)->crc_ctx_dma);
+		struct crc_context *ctx0 = ctx;
+
+		dma_pool_free(ha->dl_dma_pool, ctx0, ctx0->crc_ctx_dma);
 		sp->flags &= ~SRB_CRC_CTX_DMA_VALID;
 	}
 
 	if (sp->flags & SRB_FCP_CMND_DMA_VALID) {
-		struct ct6_dsd *ctx1 = (struct ct6_dsd *)ctx;
+		struct ct6_dsd *ctx1 = ctx;
 
 		dma_pool_free(ha->fcp_cmnd_dma_pool, ctx1->fcp_cmnd,
-			ctx1->fcp_cmnd_dma);
+		    ctx1->fcp_cmnd_dma);
 		list_splice(&ctx1->dsd_list, &ha->gbl_dsd_list);
 		ha->gbl_dsd_inuse -= ctx1->dsd_use_cnt;
 		ha->gbl_dsd_avail += ctx1->dsd_use_cnt;
 		mempool_free(ctx1, ha->ctx_mempool);
 	}
 
+end:
 	CMD_SP(cmd) = NULL;
 	qla2x00_rel_sp(sp);
 }
@@ -699,21 +704,24 @@
 		sp->flags &= ~SRB_CRC_PROT_DMA_VALID;
 	}
 
+	if (!ctx)
+		goto end;
+
 	if (sp->flags & SRB_CRC_CTX_DSD_VALID) {
 		/* List assured to be having elements */
-		qla2x00_clean_dsd_pool(ha, sp, NULL);
+		qla2x00_clean_dsd_pool(ha, ctx);
 		sp->flags &= ~SRB_CRC_CTX_DSD_VALID;
 	}
 
 	if (sp->flags & SRB_CRC_CTX_DMA_VALID) {
-		dma_pool_free(ha->dl_dma_pool, ctx,
-		    ((struct crc_context *)ctx)->crc_ctx_dma);
+		struct crc_context *ctx0 = ctx;
+
+		dma_pool_free(ha->dl_dma_pool, ctx, ctx0->crc_ctx_dma);
 		sp->flags &= ~SRB_CRC_CTX_DMA_VALID;
 	}
 
 	if (sp->flags & SRB_FCP_CMND_DMA_VALID) {
-		struct ct6_dsd *ctx1 = (struct ct6_dsd *)ctx;
-
+		struct ct6_dsd *ctx1 = ctx;
 		dma_pool_free(ha->fcp_cmnd_dma_pool, ctx1->fcp_cmnd,
 		    ctx1->fcp_cmnd_dma);
 		list_splice(&ctx1->dsd_list, &ha->gbl_dsd_list);
@@ -721,7 +729,7 @@
 		ha->gbl_dsd_avail += ctx1->dsd_use_cnt;
 		mempool_free(ctx1, ha->ctx_mempool);
 	}
-
+end:
 	CMD_SP(cmd) = NULL;
 	qla2xxx_rel_qpair_sp(sp->qpair, sp);
 }
@@ -1632,7 +1640,7 @@
 void
 qla2x00_abort_all_cmds(scsi_qla_host_t *vha, int res)
 {
-	int que, cnt;
+	int que, cnt, status;
 	unsigned long flags;
 	srb_t *sp;
 	struct qla_hw_data *ha = vha->hw;
@@ -1662,8 +1670,12 @@
 					 */
 					sp_get(sp);
 					spin_unlock_irqrestore(&ha->hardware_lock, flags);
-					qla2xxx_eh_abort(GET_CMD_SP(sp));
+					status = qla2xxx_eh_abort(GET_CMD_SP(sp));
 					spin_lock_irqsave(&ha->hardware_lock, flags);
+					/* Get rid of extra reference if immediate exit
+					 * from ql2xxx_eh_abort */
+					if (status == FAILED && (qla2x00_isp_reg_stat(ha)))
+						atomic_dec(&sp->ref_count);
 				}
 				req->outstanding_cmds[cnt] = NULL;
 				sp->done(sp, res);
@@ -2623,10 +2635,10 @@
 
 	if (mem_only) {
 		if (pci_enable_device_mem(pdev))
-			goto probe_out;
+			return ret;
 	} else {
 		if (pci_enable_device(pdev))
-			goto probe_out;
+			return ret;
 	}
 
 	/* This may fail but that's ok */
@@ -2636,7 +2648,7 @@
 	if (!ha) {
 		ql_log_pci(ql_log_fatal, pdev, 0x0009,
 		    "Unable to allocate memory for ha.\n");
-		goto probe_out;
+		goto disable_device;
 	}
 	ql_dbg_pci(ql_dbg_init, pdev, 0x000a,
 	    "Memory allocated for ha=%p.\n", ha);
@@ -3254,7 +3266,7 @@
 	pci_release_selected_regions(ha->pdev, ha->bars);
 	kfree(ha);
 
-probe_out:
+disable_device:
 	pci_disable_device(pdev);
 	return ret;
 }
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 0e03ca2..e766d84 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -2245,11 +2245,13 @@
 		pci_unmap_sg(ha->pdev, cmd->prot_sg, cmd->prot_sg_cnt,
 			cmd->dma_data_direction);
 
-	if (cmd->ctx_dsd_alloced)
-		qla2x00_clean_dsd_pool(ha, NULL, cmd);
+	if (!cmd->ctx)
+		return;
 
-	if (cmd->ctx)
-		dma_pool_free(ha->dl_dma_pool, cmd->ctx, cmd->ctx->crc_ctx_dma);
+	if (cmd->ctx_dsd_alloced)
+		qla2x00_clean_dsd_pool(ha, cmd->ctx);
+
+	dma_pool_free(ha->dl_dma_pool, cmd->ctx, cmd->ctx->crc_ctx_dma);
 }
 
 static int qlt_check_reserve_free_req(struct scsi_qla_host *vha,
diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c
index 8a58ef3..c197972 100644
--- a/drivers/scsi/qla2xxx/qla_tmpl.c
+++ b/drivers/scsi/qla2xxx/qla_tmpl.c
@@ -371,7 +371,7 @@
 		goto done;
 	}
 
-	if (end <= start || start == 0 || end == 0) {
+	if (end < start || start == 0 || end == 0) {
 		ql_dbg(ql_dbg_misc, vha, 0xd023,
 		    "%s: unusable range (start=%x end=%x)\n", __func__,
 		    ent->t262.end_addr, ent->t262.start_addr);
diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 17249c3..dc095a2 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -1404,7 +1404,7 @@
 	arr[4] = SDEBUG_LONG_INQ_SZ - 5;
 	arr[5] = (int)have_dif_prot;	/* PROTECT bit */
 	if (sdebug_vpd_use_hostno == 0)
-		arr[5] = 0x10; /* claim: implicit TGPS */
+		arr[5] |= 0x10; /* claim: implicit TPGS */
 	arr[6] = 0x10; /* claim: MultiP */
 	/* arr[6] |= 0x40; ... claim: EncServ (enclosure services) */
 	arr[7] = 0xa; /* claim: LINKED + CMDQUE */
diff --git a/drivers/staging/ccree/Kconfig b/drivers/staging/ccree/Kconfig
index ae62704..4be87f5 100644
--- a/drivers/staging/ccree/Kconfig
+++ b/drivers/staging/ccree/Kconfig
@@ -1,6 +1,6 @@
 config CRYPTO_DEV_CCREE
 	tristate "Support for ARM TrustZone CryptoCell C7XX family of Crypto accelerators"
-	depends on CRYPTO_HW && OF && HAS_DMA
+	depends on CRYPTO && CRYPTO_HW && OF && HAS_DMA
 	default n
 	select CRYPTO_HASH
 	select CRYPTO_BLKCIPHER
diff --git a/drivers/staging/ccree/ssi_buffer_mgr.c b/drivers/staging/ccree/ssi_buffer_mgr.c
index 038e2ff..6471d3d2 100644
--- a/drivers/staging/ccree/ssi_buffer_mgr.c
+++ b/drivers/staging/ccree/ssi_buffer_mgr.c
@@ -216,7 +216,8 @@
 	uint32_t nents, lbytes;
 
 	nents = ssi_buffer_mgr_get_sgl_nents(sg, end, &lbytes, NULL);
-	sg_copy_buffer(sg, nents, (void *)dest, (end - to_skip), 0, (direct == SSI_SG_TO_BUF));
+	sg_copy_buffer(sg, nents, (void *)dest, (end - to_skip + 1), to_skip,
+		       (direct == SSI_SG_TO_BUF));
 }
 
 static inline int ssi_buffer_mgr_render_buff_to_mlli(
diff --git a/drivers/staging/lustre/lustre/lov/lov_pack.c b/drivers/staging/lustre/lustre/lov/lov_pack.c
index 2e1bd47..e6727ce 100644
--- a/drivers/staging/lustre/lustre/lov/lov_pack.c
+++ b/drivers/staging/lustre/lustre/lov/lov_pack.c
@@ -293,18 +293,10 @@
 	size_t lmmk_size;
 	size_t lum_size;
 	int rc;
-	mm_segment_t seg;
 
 	if (!lsm)
 		return -ENODATA;
 
-	/*
-	 * "Switch to kernel segment" to allow copying from kernel space by
-	 * copy_{to,from}_user().
-	 */
-	seg = get_fs();
-	set_fs(KERNEL_DS);
-
 	if (lsm->lsm_magic != LOV_MAGIC_V1 && lsm->lsm_magic != LOV_MAGIC_V3) {
 		CERROR("bad LSM MAGIC: 0x%08X != 0x%08X nor 0x%08X\n",
 		       lsm->lsm_magic, LOV_MAGIC_V1, LOV_MAGIC_V3);
@@ -406,6 +398,5 @@
 out_free:
 	kvfree(lmmk);
 out:
-	set_fs(seg);
 	return rc;
 }
diff --git a/drivers/usb/chipidea/core.c b/drivers/usb/chipidea/core.c
index 9e217b1..fe4fe24 100644
--- a/drivers/usb/chipidea/core.c
+++ b/drivers/usb/chipidea/core.c
@@ -843,7 +843,10 @@
 {
 	struct ci_hdrc *ci = dev_get_drvdata(dev);
 
-	return sprintf(buf, "%s\n", ci_role(ci)->name);
+	if (ci->role != CI_ROLE_END)
+		return sprintf(buf, "%s\n", ci_role(ci)->name);
+
+	return 0;
 }
 
 static ssize_t ci_role_store(struct device *dev,
diff --git a/drivers/usb/chipidea/debug.c b/drivers/usb/chipidea/debug.c
index 6d23eed..1c31e8a 100644
--- a/drivers/usb/chipidea/debug.c
+++ b/drivers/usb/chipidea/debug.c
@@ -294,7 +294,8 @@
 {
 	struct ci_hdrc *ci = s->private;
 
-	seq_printf(s, "%s\n", ci_role(ci)->name);
+	if (ci->role != CI_ROLE_END)
+		seq_printf(s, "%s\n", ci_role(ci)->name);
 
 	return 0;
 }
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 56d2d32..d68b125 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -1993,6 +1993,7 @@
 int ci_hdrc_gadget_init(struct ci_hdrc *ci)
 {
 	struct ci_role_driver *rdrv;
+	int ret;
 
 	if (!hw_read(ci, CAP_DCCPARAMS, DCCPARAMS_DC))
 		return -ENXIO;
@@ -2005,7 +2006,10 @@
 	rdrv->stop	= udc_id_switch_for_host;
 	rdrv->irq	= udc_irq;
 	rdrv->name	= "gadget";
-	ci->roles[CI_ROLE_GADGET] = rdrv;
 
-	return udc_start(ci);
+	ret = udc_start(ci);
+	if (!ret)
+		ci->roles[CI_ROLE_GADGET] = rdrv;
+
+	return ret;
 }
diff --git a/drivers/usb/chipidea/usbmisc_imx.c b/drivers/usb/chipidea/usbmisc_imx.c
index e77a4ed..9f4a018 100644
--- a/drivers/usb/chipidea/usbmisc_imx.c
+++ b/drivers/usb/chipidea/usbmisc_imx.c
@@ -108,6 +108,8 @@
 	const struct usbmisc_ops *ops;
 };
 
+static inline bool is_imx53_usbmisc(struct imx_usbmisc_data *data);
+
 static int usbmisc_imx25_init(struct imx_usbmisc_data *data)
 {
 	struct imx_usbmisc *usbmisc = dev_get_drvdata(data->dev);
@@ -242,10 +244,15 @@
 			val = readl(reg) | MX53_USB_UHx_CTRL_WAKE_UP_EN
 				| MX53_USB_UHx_CTRL_ULPI_INT_EN;
 			writel(val, reg);
-			/* Disable internal 60Mhz clock */
-			reg = usbmisc->base + MX53_USB_CLKONOFF_CTRL_OFFSET;
-			val = readl(reg) | MX53_USB_CLKONOFF_CTRL_H2_INT60CKOFF;
-			writel(val, reg);
+			if (is_imx53_usbmisc(data)) {
+				/* Disable internal 60Mhz clock */
+				reg = usbmisc->base +
+					MX53_USB_CLKONOFF_CTRL_OFFSET;
+				val = readl(reg) |
+					MX53_USB_CLKONOFF_CTRL_H2_INT60CKOFF;
+				writel(val, reg);
+			}
+
 		}
 		if (data->disable_oc) {
 			reg = usbmisc->base + MX53_USB_UH2_CTRL_OFFSET;
@@ -267,10 +274,15 @@
 			val = readl(reg) | MX53_USB_UHx_CTRL_WAKE_UP_EN
 				| MX53_USB_UHx_CTRL_ULPI_INT_EN;
 			writel(val, reg);
-			/* Disable internal 60Mhz clock */
-			reg = usbmisc->base + MX53_USB_CLKONOFF_CTRL_OFFSET;
-			val = readl(reg) | MX53_USB_CLKONOFF_CTRL_H3_INT60CKOFF;
-			writel(val, reg);
+
+			if (is_imx53_usbmisc(data)) {
+				/* Disable internal 60Mhz clock */
+				reg = usbmisc->base +
+					MX53_USB_CLKONOFF_CTRL_OFFSET;
+				val = readl(reg) |
+					MX53_USB_CLKONOFF_CTRL_H3_INT60CKOFF;
+				writel(val, reg);
+			}
 		}
 		if (data->disable_oc) {
 			reg = usbmisc->base + MX53_USB_UH3_CTRL_OFFSET;
@@ -456,6 +468,10 @@
 	.init = usbmisc_imx27_init,
 };
 
+static const struct usbmisc_ops imx51_usbmisc_ops = {
+	.init = usbmisc_imx53_init,
+};
+
 static const struct usbmisc_ops imx53_usbmisc_ops = {
 	.init = usbmisc_imx53_init,
 };
@@ -479,6 +495,13 @@
 	.set_wakeup = usbmisc_imx7d_set_wakeup,
 };
 
+static inline bool is_imx53_usbmisc(struct imx_usbmisc_data *data)
+{
+	struct imx_usbmisc *usbmisc = dev_get_drvdata(data->dev);
+
+	return usbmisc->ops == &imx53_usbmisc_ops;
+}
+
 int imx_usbmisc_init(struct imx_usbmisc_data *data)
 {
 	struct imx_usbmisc *usbmisc;
@@ -536,7 +559,7 @@
 	},
 	{
 		.compatible = "fsl,imx51-usbmisc",
-		.data = &imx53_usbmisc_ops,
+		.data = &imx51_usbmisc_ops,
 	},
 	{
 		.compatible = "fsl,imx53-usbmisc",
diff --git a/drivers/usb/dwc2/params.c b/drivers/usb/dwc2/params.c
index 9cd8722..a3ffe97 100644
--- a/drivers/usb/dwc2/params.c
+++ b/drivers/usb/dwc2/params.c
@@ -144,6 +144,8 @@
 	{ .compatible = "lantiq,xrx200-usb", .data = dwc2_set_ltq_params },
 	{ .compatible = "snps,dwc2" },
 	{ .compatible = "samsung,s3c6400-hsotg" },
+	{ .compatible = "amlogic,meson8-usb",
+	  .data = dwc2_set_amlogic_params },
 	{ .compatible = "amlogic,meson8b-usb",
 	  .data = dwc2_set_amlogic_params },
 	{ .compatible = "amlogic,meson-gxbb-usb",
diff --git a/drivers/usb/gadget/function/f_mass_storage.c b/drivers/usb/gadget/function/f_mass_storage.c
index 4c8aacc..74d57d6 100644
--- a/drivers/usb/gadget/function/f_mass_storage.c
+++ b/drivers/usb/gadget/function/f_mass_storage.c
@@ -396,7 +396,11 @@
 /* Caller must hold fsg->lock */
 static void wakeup_thread(struct fsg_common *common)
 {
-	smp_wmb();	/* ensure the write of bh->state is complete */
+	/*
+	 * Ensure the reading of thread_wakeup_needed
+	 * and the writing of bh->state are completed
+	 */
+	smp_mb();
 	/* Tell the main thread that something has happened */
 	common->thread_wakeup_needed = 1;
 	if (common->thread_task)
@@ -627,7 +631,12 @@
 	}
 	__set_current_state(TASK_RUNNING);
 	common->thread_wakeup_needed = 0;
-	smp_rmb();	/* ensure the latest bh->state is visible */
+
+	/*
+	 * Ensure the writing of thread_wakeup_needed
+	 * and the reading of bh->state are completed
+	 */
+	smp_mb();
 	return rc;
 }
 
diff --git a/drivers/usb/gadget/udc/renesas_usb3.c b/drivers/usb/gadget/udc/renesas_usb3.c
index 5a2d845..cd4c885 100644
--- a/drivers/usb/gadget/udc/renesas_usb3.c
+++ b/drivers/usb/gadget/udc/renesas_usb3.c
@@ -623,7 +623,6 @@
 {
 	usb3_disconnect(usb3);
 	usb3_write(usb3, 0, USB3_P0_INT_ENA);
-	usb3_write(usb3, 0, USB3_PN_INT_ENA);
 	usb3_write(usb3, 0, USB3_USB_OTG_INT_ENA);
 	usb3_write(usb3, 0, USB3_USB_INT_ENA_1);
 	usb3_write(usb3, 0, USB3_USB_INT_ENA_2);
@@ -1475,7 +1474,13 @@
 				    struct renesas_usb3_request *usb3_req,
 				    int status)
 {
-	usb3_pn_stop(usb3);
+	unsigned long flags;
+
+	spin_lock_irqsave(&usb3->lock, flags);
+	if (usb3_pn_change(usb3, usb3_ep->num))
+		usb3_pn_stop(usb3);
+	spin_unlock_irqrestore(&usb3->lock, flags);
+
 	usb3_disable_pipe_irq(usb3, usb3_ep->num);
 	usb3_request_done(usb3_ep, usb3_req, status);
 
@@ -1504,30 +1509,46 @@
 {
 	struct renesas_usb3_ep *usb3_ep = usb3_get_ep(usb3, num);
 	struct renesas_usb3_request *usb3_req = usb3_get_request(usb3_ep);
+	bool done = false;
 
 	if (!usb3_req)
 		return;
 
+	spin_lock(&usb3->lock);
+	if (usb3_pn_change(usb3, num))
+		goto out;
+
 	if (usb3_ep->dir_in) {
 		/* Do not stop the IN pipe here to detect LSTTR interrupt */
 		if (!usb3_write_pipe(usb3_ep, usb3_req, USB3_PN_WRITE))
 			usb3_clear_bit(usb3, PN_INT_BFRDY, USB3_PN_INT_ENA);
 	} else {
 		if (!usb3_read_pipe(usb3_ep, usb3_req, USB3_PN_READ))
-			usb3_request_done_pipen(usb3, usb3_ep, usb3_req, 0);
+			done = true;
 	}
+
+out:
+	/* need to unlock because usb3_request_done_pipen() locks it */
+	spin_unlock(&usb3->lock);
+
+	if (done)
+		usb3_request_done_pipen(usb3, usb3_ep, usb3_req, 0);
 }
 
 static void usb3_irq_epc_pipen(struct renesas_usb3 *usb3, int num)
 {
 	u32 pn_int_sta;
 
-	if (usb3_pn_change(usb3, num) < 0)
+	spin_lock(&usb3->lock);
+	if (usb3_pn_change(usb3, num) < 0) {
+		spin_unlock(&usb3->lock);
 		return;
+	}
 
 	pn_int_sta = usb3_read(usb3, USB3_PN_INT_STA);
 	pn_int_sta &= usb3_read(usb3, USB3_PN_INT_ENA);
 	usb3_write(usb3, pn_int_sta, USB3_PN_INT_STA);
+	spin_unlock(&usb3->lock);
 	if (pn_int_sta & PN_INT_LSTTR)
 		usb3_irq_epc_pipen_lsttr(usb3, num);
 	if (pn_int_sta & PN_INT_BFRDY)
@@ -1660,6 +1681,7 @@
 
 	spin_lock_irqsave(&usb3->lock, flags);
 	if (!usb3_pn_change(usb3, usb3_ep->num)) {
+		usb3_write(usb3, 0, USB3_PN_INT_ENA);
 		usb3_write(usb3, 0, USB3_PN_RAMMAP);
 		usb3_clear_bit(usb3, PN_CON_EN, USB3_PN_CON);
 	}
@@ -1799,6 +1821,9 @@
 	/* hook up the driver */
 	usb3->driver = driver;
 
+	pm_runtime_enable(usb3_to_dev(usb3));
+	pm_runtime_get_sync(usb3_to_dev(usb3));
+
 	renesas_usb3_init_controller(usb3);
 
 	return 0;
@@ -1807,14 +1832,14 @@
 static int renesas_usb3_stop(struct usb_gadget *gadget)
 {
 	struct renesas_usb3 *usb3 = gadget_to_renesas_usb3(gadget);
-	unsigned long flags;
 
-	spin_lock_irqsave(&usb3->lock, flags);
 	usb3->softconnect = false;
 	usb3->gadget.speed = USB_SPEED_UNKNOWN;
 	usb3->driver = NULL;
 	renesas_usb3_stop_controller(usb3);
-	spin_unlock_irqrestore(&usb3->lock, flags);
+
+	pm_runtime_put(usb3_to_dev(usb3));
+	pm_runtime_disable(usb3_to_dev(usb3));
 
 	return 0;
 }
@@ -1891,9 +1916,6 @@
 
 	device_remove_file(&pdev->dev, &dev_attr_role);
 
-	pm_runtime_put(&pdev->dev);
-	pm_runtime_disable(&pdev->dev);
-
 	usb_del_gadget_udc(&usb3->gadget);
 
 	__renesas_usb3_ep_free_request(usb3->ep0_req);
@@ -2099,9 +2121,6 @@
 
 	usb3->workaround_for_vbus = priv->workaround_for_vbus;
 
-	pm_runtime_enable(&pdev->dev);
-	pm_runtime_get_sync(&pdev->dev);
-
 	dev_info(&pdev->dev, "probed\n");
 
 	return 0;
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index 9c7ee26..bc6a9be 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -245,6 +245,11 @@
 		dsps_mod_timer_optional(glue);
 		break;
 	case OTG_STATE_A_WAIT_BCON:
+		/* keep VBUS on for host-only mode */
+		if (musb->port_mode == MUSB_PORT_MODE_HOST) {
+			dsps_mod_timer_optional(glue);
+			break;
+		}
 		musb_writeb(musb->mregs, MUSB_DEVCTL, 0);
 		skip_session = 1;
 		/* fall */
diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
index 7a92a5e..feca75b07 100644
--- a/drivers/xen/privcmd.c
+++ b/drivers/xen/privcmd.c
@@ -362,8 +362,8 @@
 				st->global_error = 1;
 		}
 	}
-	st->va += PAGE_SIZE * nr;
-	st->index += nr;
+	st->va += XEN_PAGE_SIZE * nr;
+	st->index += nr / XEN_PFN_PER_PAGE;
 
 	return 0;
 }
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 643c70d..4f8f75d 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2563,7 +2563,7 @@
 static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_fs_info *fs_info,
 						 unsigned num_items)
 {
-	return fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items;
+	return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items;
 }
 
 /*
@@ -2573,7 +2573,7 @@
 static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_fs_info *fs_info,
 						 unsigned num_items)
 {
-	return fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
+	return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
 }
 
 int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index 60a7506..c24d615 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -468,7 +468,7 @@
 
 	if (btrfs_dir_name_len(leaf, dir_item) > namelen) {
 		btrfs_crit(fs_info, "invalid dir item name len: %u",
-		       (unsigned)btrfs_dir_data_len(leaf, dir_item));
+		       (unsigned)btrfs_dir_name_len(leaf, dir_item));
 		return 1;
 	}
 
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8685d67..5f678dc 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3467,10 +3467,12 @@
 		 * we fua the first super.  The others we allow
 		 * to go down lazy.
 		 */
-		if (i == 0)
-			ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_FUA, bh);
-		else
+		if (i == 0) {
+			ret = btrfsic_submit_bh(REQ_OP_WRITE,
+						REQ_SYNC | REQ_FUA, bh);
+		} else {
 			ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
+		}
 		if (ret)
 			errors++;
 	}
@@ -3535,7 +3537,7 @@
 
 	bio->bi_end_io = btrfs_end_empty_barrier;
 	bio->bi_bdev = device->bdev;
-	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH;
 	init_completion(&device->flush_wait);
 	bio->bi_private = &device->flush_wait;
 	device->flush_bio = bio;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index e390451..33d979e 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3993,6 +3993,7 @@
 				    info->space_info_kobj, "%s",
 				    alloc_name(found->flags));
 	if (ret) {
+		percpu_counter_destroy(&found->total_bytes_pinned);
 		kfree(found);
 		return ret;
 	}
@@ -4844,7 +4845,7 @@
 	spin_unlock(&delayed_rsv->lock);
 
 commit:
-	trans = btrfs_join_transaction(fs_info->fs_root);
+	trans = btrfs_join_transaction(fs_info->extent_root);
 	if (IS_ERR(trans))
 		return -ENOSPC;
 
@@ -4862,7 +4863,7 @@
 		       struct btrfs_space_info *space_info, u64 num_bytes,
 		       u64 orig_bytes, int state)
 {
-	struct btrfs_root *root = fs_info->fs_root;
+	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_trans_handle *trans;
 	int nr;
 	int ret = 0;
@@ -5062,7 +5063,7 @@
 	int flush_state = FLUSH_DELAYED_ITEMS_NR;
 
 	spin_lock(&space_info->lock);
-	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root,
+	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->extent_root,
 						      space_info);
 	if (!to_reclaim) {
 		spin_unlock(&space_info->lock);
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index d8da3ed..d3619e0 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2458,7 +2458,7 @@
 	if (!uptodate) {
 		ClearPageUptodate(page);
 		SetPageError(page);
-		ret = ret < 0 ? ret : -EIO;
+		ret = err < 0 ? err : -EIO;
 		mapping_set_error(page->mapping, ret);
 	}
 }
@@ -4377,6 +4377,123 @@
 	return NULL;
 }
 
+/*
+ * To cache previous fiemap extent
+ *
+ * Will be used for merging fiemap extent
+ */
+struct fiemap_cache {
+	u64 offset;
+	u64 phys;
+	u64 len;
+	u32 flags;
+	bool cached;
+};
+
+/*
+ * Helper to submit fiemap extent.
+ *
+ * Will try to merge current fiemap extent specified by @offset, @phys,
+ * @len and @flags with cached one.
+ * And only when we fails to merge, cached one will be submitted as
+ * fiemap extent.
+ *
+ * Return value is the same as fiemap_fill_next_extent().
+ */
+static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo,
+				struct fiemap_cache *cache,
+				u64 offset, u64 phys, u64 len, u32 flags)
+{
+	int ret = 0;
+
+	if (!cache->cached)
+		goto assign;
+
+	/*
+	 * Sanity check, extent_fiemap() should have ensured that new
+	 * fiemap extent won't overlap with cahced one.
+	 * Not recoverable.
+	 *
+	 * NOTE: Physical address can overlap, due to compression
+	 */
+	if (cache->offset + cache->len > offset) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	/*
+	 * Only merges fiemap extents if
+	 * 1) Their logical addresses are continuous
+	 *
+	 * 2) Their physical addresses are continuous
+	 *    So truly compressed (physical size smaller than logical size)
+	 *    extents won't get merged with each other
+	 *
+	 * 3) Share same flags except FIEMAP_EXTENT_LAST
+	 *    So regular extent won't get merged with prealloc extent
+	 */
+	if (cache->offset + cache->len  == offset &&
+	    cache->phys + cache->len == phys  &&
+	    (cache->flags & ~FIEMAP_EXTENT_LAST) ==
+			(flags & ~FIEMAP_EXTENT_LAST)) {
+		cache->len += len;
+		cache->flags |= flags;
+		goto try_submit_last;
+	}
+
+	/* Not mergeable, need to submit cached one */
+	ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys,
+				      cache->len, cache->flags);
+	cache->cached = false;
+	if (ret)
+		return ret;
+assign:
+	cache->cached = true;
+	cache->offset = offset;
+	cache->phys = phys;
+	cache->len = len;
+	cache->flags = flags;
+try_submit_last:
+	if (cache->flags & FIEMAP_EXTENT_LAST) {
+		ret = fiemap_fill_next_extent(fieinfo, cache->offset,
+				cache->phys, cache->len, cache->flags);
+		cache->cached = false;
+	}
+	return ret;
+}
+
+/*
+ * Sanity check for fiemap cache
+ *
+ * All fiemap cache should be submitted by emit_fiemap_extent()
+ * Iteration should be terminated either by last fiemap extent or
+ * fieinfo->fi_extents_max.
+ * So no cached fiemap should exist.
+ */
+static int check_fiemap_cache(struct btrfs_fs_info *fs_info,
+			       struct fiemap_extent_info *fieinfo,
+			       struct fiemap_cache *cache)
+{
+	int ret;
+
+	if (!cache->cached)
+		return 0;
+
+	/* Small and recoverbale problem, only to info developer */
+#ifdef CONFIG_BTRFS_DEBUG
+	WARN_ON(1);
+#endif
+	btrfs_warn(fs_info,
+		   "unhandled fiemap cache detected: offset=%llu phys=%llu len=%llu flags=0x%x",
+		   cache->offset, cache->phys, cache->len, cache->flags);
+	ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys,
+				      cache->len, cache->flags);
+	cache->cached = false;
+	if (ret > 0)
+		ret = 0;
+	return ret;
+}
+
 int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		__u64 start, __u64 len, get_extent_t *get_extent)
 {
@@ -4394,6 +4511,7 @@
 	struct extent_state *cached_state = NULL;
 	struct btrfs_path *path;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct fiemap_cache cache = { 0 };
 	int end = 0;
 	u64 em_start = 0;
 	u64 em_len = 0;
@@ -4573,8 +4691,8 @@
 			flags |= FIEMAP_EXTENT_LAST;
 			end = 1;
 		}
-		ret = fiemap_fill_next_extent(fieinfo, em_start, disko,
-					      em_len, flags);
+		ret = emit_fiemap_extent(fieinfo, &cache, em_start, disko,
+					   em_len, flags);
 		if (ret) {
 			if (ret == 1)
 				ret = 0;
@@ -4582,6 +4700,8 @@
 		}
 	}
 out_free:
+	if (!ret)
+		ret = check_fiemap_cache(root->fs_info, fieinfo, &cache);
 	free_extent_map(em);
 out:
 	btrfs_free_path(path);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 17cbe93..ef3c98c 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -2952,7 +2952,7 @@
 
 	ret = test_range_bit(io_tree, ordered_extent->file_offset,
 			ordered_extent->file_offset + ordered_extent->len - 1,
-			EXTENT_DEFRAG, 1, cached_state);
+			EXTENT_DEFRAG, 0, cached_state);
 	if (ret) {
 		u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item);
 		if (0 && last_snapshot >= BTRFS_I(inode)->generation)
@@ -7483,8 +7483,8 @@
 	int found = false;
 	void **pagep = NULL;
 	struct page *page = NULL;
-	int start_idx;
-	int end_idx;
+	unsigned long start_idx;
+	unsigned long end_idx;
 
 	start_idx = start >> PAGE_SHIFT;
 
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index fd38993..3ec0e46d 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
  */
 
+#include <linux/quotaops.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
 #include "xattr.h"
@@ -232,6 +233,9 @@
 	handle_t *handle;
 	int error, retries = 0;
 
+	error = dquot_initialize(inode);
+	if (error)
+		return error;
 retry:
 	handle = ext4_journal_start(inode, EXT4_HT_XATTR,
 				    ext4_jbd2_credits_xattr(inode));
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 8e80461..3219154 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2523,7 +2523,6 @@
 			   int buf_size,
 			   struct inode *dir,
 			   struct ext4_filename *fname,
-			   const struct qstr *d_name,
 			   unsigned int offset,
 			   struct ext4_dir_entry_2 **res_dir);
 extern int ext4_generic_delete_entry(handle_t *handle,
@@ -3007,7 +3006,6 @@
 				   int *has_inline_data);
 extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
 					struct ext4_filename *fname,
-					const struct qstr *d_name,
 					struct ext4_dir_entry_2 **res_dir,
 					int *has_inline_data);
 extern int ext4_delete_inline_entry(handle_t *handle,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 2a97dff..3e36508 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3413,13 +3413,13 @@
 	struct ext4_sb_info *sbi;
 	struct ext4_extent_header *eh;
 	struct ext4_map_blocks split_map;
-	struct ext4_extent zero_ex;
+	struct ext4_extent zero_ex1, zero_ex2;
 	struct ext4_extent *ex, *abut_ex;
 	ext4_lblk_t ee_block, eof_block;
 	unsigned int ee_len, depth, map_len = map->m_len;
 	int allocated = 0, max_zeroout = 0;
 	int err = 0;
-	int split_flag = 0;
+	int split_flag = EXT4_EXT_DATA_VALID2;
 
 	ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical"
 		"block %llu, max_blocks %u\n", inode->i_ino,
@@ -3436,7 +3436,8 @@
 	ex = path[depth].p_ext;
 	ee_block = le32_to_cpu(ex->ee_block);
 	ee_len = ext4_ext_get_actual_len(ex);
-	zero_ex.ee_len = 0;
+	zero_ex1.ee_len = 0;
+	zero_ex2.ee_len = 0;
 
 	trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
 
@@ -3576,62 +3577,52 @@
 	if (ext4_encrypted_inode(inode))
 		max_zeroout = 0;
 
-	/* If extent is less than s_max_zeroout_kb, zeroout directly */
-	if (max_zeroout && (ee_len <= max_zeroout)) {
-		err = ext4_ext_zeroout(inode, ex);
-		if (err)
-			goto out;
-		zero_ex.ee_block = ex->ee_block;
-		zero_ex.ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex));
-		ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex));
-
-		err = ext4_ext_get_access(handle, inode, path + depth);
-		if (err)
-			goto out;
-		ext4_ext_mark_initialized(ex);
-		ext4_ext_try_to_merge(handle, inode, path, ex);
-		err = ext4_ext_dirty(handle, inode, path + path->p_depth);
-		goto out;
-	}
-
 	/*
-	 * four cases:
+	 * five cases:
 	 * 1. split the extent into three extents.
-	 * 2. split the extent into two extents, zeroout the first half.
-	 * 3. split the extent into two extents, zeroout the second half.
+	 * 2. split the extent into two extents, zeroout the head of the first
+	 *    extent.
+	 * 3. split the extent into two extents, zeroout the tail of the second
+	 *    extent.
 	 * 4. split the extent into two extents with out zeroout.
+	 * 5. no splitting needed, just possibly zeroout the head and / or the
+	 *    tail of the extent.
 	 */
 	split_map.m_lblk = map->m_lblk;
 	split_map.m_len = map->m_len;
 
-	if (max_zeroout && (allocated > map->m_len)) {
+	if (max_zeroout && (allocated > split_map.m_len)) {
 		if (allocated <= max_zeroout) {
-			/* case 3 */
-			zero_ex.ee_block =
-					 cpu_to_le32(map->m_lblk);
-			zero_ex.ee_len = cpu_to_le16(allocated);
-			ext4_ext_store_pblock(&zero_ex,
-				ext4_ext_pblock(ex) + map->m_lblk - ee_block);
-			err = ext4_ext_zeroout(inode, &zero_ex);
+			/* case 3 or 5 */
+			zero_ex1.ee_block =
+				 cpu_to_le32(split_map.m_lblk +
+					     split_map.m_len);
+			zero_ex1.ee_len =
+				cpu_to_le16(allocated - split_map.m_len);
+			ext4_ext_store_pblock(&zero_ex1,
+				ext4_ext_pblock(ex) + split_map.m_lblk +
+				split_map.m_len - ee_block);
+			err = ext4_ext_zeroout(inode, &zero_ex1);
 			if (err)
 				goto out;
-			split_map.m_lblk = map->m_lblk;
 			split_map.m_len = allocated;
-		} else if (map->m_lblk - ee_block + map->m_len < max_zeroout) {
-			/* case 2 */
-			if (map->m_lblk != ee_block) {
-				zero_ex.ee_block = ex->ee_block;
-				zero_ex.ee_len = cpu_to_le16(map->m_lblk -
+		}
+		if (split_map.m_lblk - ee_block + split_map.m_len <
+								max_zeroout) {
+			/* case 2 or 5 */
+			if (split_map.m_lblk != ee_block) {
+				zero_ex2.ee_block = ex->ee_block;
+				zero_ex2.ee_len = cpu_to_le16(split_map.m_lblk -
 							ee_block);
-				ext4_ext_store_pblock(&zero_ex,
+				ext4_ext_store_pblock(&zero_ex2,
 						      ext4_ext_pblock(ex));
-				err = ext4_ext_zeroout(inode, &zero_ex);
+				err = ext4_ext_zeroout(inode, &zero_ex2);
 				if (err)
 					goto out;
 			}
 
+			split_map.m_len += split_map.m_lblk - ee_block;
 			split_map.m_lblk = ee_block;
-			split_map.m_len = map->m_lblk - ee_block + map->m_len;
 			allocated = map->m_len;
 		}
 	}
@@ -3642,8 +3633,11 @@
 		err = 0;
 out:
 	/* If we have gotten a failure, don't zero out status tree */
-	if (!err)
-		err = ext4_zeroout_es(inode, &zero_ex);
+	if (!err) {
+		err = ext4_zeroout_es(inode, &zero_ex1);
+		if (!err)
+			err = ext4_zeroout_es(inode, &zero_ex2);
+	}
 	return err ? err : allocated;
 }
 
@@ -4883,6 +4877,8 @@
 
 	/* Zero out partial block at the edges of the range */
 	ret = ext4_zero_partial_blocks(handle, inode, offset, len);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 
 	if (file->f_flags & O_SYNC)
 		ext4_handle_sync(handle);
@@ -5569,6 +5565,7 @@
 		ext4_handle_sync(handle);
 	inode->i_mtime = inode->i_ctime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
+	ext4_update_inode_fsync_trans(handle, inode, 1);
 
 out_stop:
 	ext4_journal_stop(handle);
@@ -5742,6 +5739,8 @@
 	up_write(&EXT4_I(inode)->i_data_sem);
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 
 out_stop:
 	ext4_journal_stop(handle);
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 831fd6be..02ce7e7 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -474,57 +474,37 @@
 	endoff = (loff_t)end_blk << blkbits;
 
 	index = startoff >> PAGE_SHIFT;
-	end = endoff >> PAGE_SHIFT;
+	end = (endoff - 1) >> PAGE_SHIFT;
 
 	pagevec_init(&pvec, 0);
 	do {
 		int i, num;
 		unsigned long nr_pages;
 
-		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
+		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1;
 		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
 					  (pgoff_t)num);
-		if (nr_pages == 0) {
-			if (whence == SEEK_DATA)
-				break;
-
-			BUG_ON(whence != SEEK_HOLE);
-			/*
-			 * If this is the first time to go into the loop and
-			 * offset is not beyond the end offset, it will be a
-			 * hole at this offset
-			 */
-			if (lastoff == startoff || lastoff < endoff)
-				found = 1;
+		if (nr_pages == 0)
 			break;
-		}
-
-		/*
-		 * If this is the first time to go into the loop and
-		 * offset is smaller than the first page offset, it will be a
-		 * hole at this offset.
-		 */
-		if (lastoff == startoff && whence == SEEK_HOLE &&
-		    lastoff < page_offset(pvec.pages[0])) {
-			found = 1;
-			break;
-		}
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 			struct buffer_head *bh, *head;
 
 			/*
-			 * If the current offset is not beyond the end of given
-			 * range, it will be a hole.
+			 * If current offset is smaller than the page offset,
+			 * there is a hole at this offset.
 			 */
-			if (lastoff < endoff && whence == SEEK_HOLE &&
-			    page->index > end) {
+			if (whence == SEEK_HOLE && lastoff < endoff &&
+			    lastoff < page_offset(pvec.pages[i])) {
 				found = 1;
 				*offset = lastoff;
 				goto out;
 			}
 
+			if (page->index > end)
+				goto out;
+
 			lock_page(page);
 
 			if (unlikely(page->mapping != inode->i_mapping)) {
@@ -564,20 +544,18 @@
 			unlock_page(page);
 		}
 
-		/*
-		 * The no. of pages is less than our desired, that would be a
-		 * hole in there.
-		 */
-		if (nr_pages < num && whence == SEEK_HOLE) {
-			found = 1;
-			*offset = lastoff;
+		/* The no. of pages is less than our desired, we are done. */
+		if (nr_pages < num)
 			break;
-		}
 
 		index = pvec.pages[i - 1]->index + 1;
 		pagevec_release(&pvec);
 	} while (index <= end);
 
+	if (whence == SEEK_HOLE && lastoff < endoff) {
+		found = 1;
+		*offset = lastoff;
+	}
 out:
 	pagevec_release(&pvec);
 	return found;
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index d5dea4c..8d141c0 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1627,7 +1627,6 @@
 
 struct buffer_head *ext4_find_inline_entry(struct inode *dir,
 					struct ext4_filename *fname,
-					const struct qstr *d_name,
 					struct ext4_dir_entry_2 **res_dir,
 					int *has_inline_data)
 {
@@ -1649,7 +1648,7 @@
 						EXT4_INLINE_DOTDOT_SIZE;
 	inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE;
 	ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
-			      dir, fname, d_name, 0, res_dir);
+			      dir, fname, 0, res_dir);
 	if (ret == 1)
 		goto out_find;
 	if (ret < 0)
@@ -1662,7 +1661,7 @@
 	inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE;
 
 	ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
-			      dir, fname, d_name, 0, res_dir);
+			      dir, fname, 0, res_dir);
 	if (ret == 1)
 		goto out_find;
 
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 1bd0bfa..5cf82d0 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2124,15 +2124,29 @@
 static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
 {
 	int len;
-	loff_t size = i_size_read(mpd->inode);
+	loff_t size;
 	int err;
 
 	BUG_ON(page->index != mpd->first_page);
+	clear_page_dirty_for_io(page);
+	/*
+	 * We have to be very careful here!  Nothing protects writeback path
+	 * against i_size changes and the page can be writeably mapped into
+	 * page tables. So an application can be growing i_size and writing
+	 * data through mmap while writeback runs. clear_page_dirty_for_io()
+	 * write-protects our page in page tables and the page cannot get
+	 * written to again until we release page lock. So only after
+	 * clear_page_dirty_for_io() we are safe to sample i_size for
+	 * ext4_bio_write_page() to zero-out tail of the written page. We rely
+	 * on the barrier provided by TestClearPageDirty in
+	 * clear_page_dirty_for_io() to make sure i_size is really sampled only
+	 * after page tables are updated.
+	 */
+	size = i_size_read(mpd->inode);
 	if (page->index == size >> PAGE_SHIFT)
 		len = size & ~PAGE_MASK;
 	else
 		len = PAGE_SIZE;
-	clear_page_dirty_for_io(page);
 	err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
 	if (!err)
 		mpd->wbc->nr_to_write--;
@@ -3629,9 +3643,6 @@
 		get_block_func = ext4_dio_get_block_unwritten_async;
 		dio_flags = DIO_LOCKING;
 	}
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-	BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode));
-#endif
 	ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
 				   get_block_func, ext4_end_io_dio, NULL,
 				   dio_flags);
@@ -3713,7 +3724,7 @@
 	 */
 	inode_lock_shared(inode);
 	ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
-					   iocb->ki_pos + count);
+					   iocb->ki_pos + count - 1);
 	if (ret)
 		goto out_unlock;
 	ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
@@ -4207,6 +4218,8 @@
 
 	inode->i_mtime = inode->i_ctime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 out_stop:
 	ext4_journal_stop(handle);
 out_dio:
@@ -5637,8 +5650,9 @@
 	/* No extended attributes present */
 	if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
 	    header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
-		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
-			new_extra_isize);
+		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
+		       EXT4_I(inode)->i_extra_isize, 0,
+		       new_extra_isize - EXT4_I(inode)->i_extra_isize);
 		EXT4_I(inode)->i_extra_isize = new_extra_isize;
 		return 0;
 	}
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 5083bce2..b7928cd 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3887,7 +3887,8 @@
 
 	err = ext4_mb_load_buddy(sb, group, &e4b);
 	if (err) {
-		ext4_error(sb, "Error loading buddy information for %u", group);
+		ext4_warning(sb, "Error %d loading buddy information for %u",
+			     err, group);
 		put_bh(bitmap_bh);
 		return 0;
 	}
@@ -4044,10 +4045,11 @@
 		BUG_ON(pa->pa_type != MB_INODE_PA);
 		group = ext4_get_group_number(sb, pa->pa_pstart);
 
-		err = ext4_mb_load_buddy(sb, group, &e4b);
+		err = ext4_mb_load_buddy_gfp(sb, group, &e4b,
+					     GFP_NOFS|__GFP_NOFAIL);
 		if (err) {
-			ext4_error(sb, "Error loading buddy information for %u",
-					group);
+			ext4_error(sb, "Error %d loading buddy information for %u",
+				   err, group);
 			continue;
 		}
 
@@ -4303,11 +4305,14 @@
 	spin_unlock(&lg->lg_prealloc_lock);
 
 	list_for_each_entry_safe(pa, tmp, &discard_list, u.pa_tmp_list) {
+		int err;
 
 		group = ext4_get_group_number(sb, pa->pa_pstart);
-		if (ext4_mb_load_buddy(sb, group, &e4b)) {
-			ext4_error(sb, "Error loading buddy information for %u",
-					group);
+		err = ext4_mb_load_buddy_gfp(sb, group, &e4b,
+					     GFP_NOFS|__GFP_NOFAIL);
+		if (err) {
+			ext4_error(sb, "Error %d loading buddy information for %u",
+				   err, group);
 			continue;
 		}
 		ext4_lock_group(sb, group);
@@ -5127,8 +5132,8 @@
 
 	ret = ext4_mb_load_buddy(sb, group, &e4b);
 	if (ret) {
-		ext4_error(sb, "Error in loading buddy "
-				"information for %u", group);
+		ext4_warning(sb, "Error %d loading buddy information for %u",
+			     ret, group);
 		return ret;
 	}
 	bitmap = e4b.bd_bitmap;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index b81f7d4..404256c 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1155,12 +1155,11 @@
 static inline int search_dirblock(struct buffer_head *bh,
 				  struct inode *dir,
 				  struct ext4_filename *fname,
-				  const struct qstr *d_name,
 				  unsigned int offset,
 				  struct ext4_dir_entry_2 **res_dir)
 {
 	return ext4_search_dir(bh, bh->b_data, dir->i_sb->s_blocksize, dir,
-			       fname, d_name, offset, res_dir);
+			       fname, offset, res_dir);
 }
 
 /*
@@ -1262,7 +1261,6 @@
  */
 int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
 		    struct inode *dir, struct ext4_filename *fname,
-		    const struct qstr *d_name,
 		    unsigned int offset, struct ext4_dir_entry_2 **res_dir)
 {
 	struct ext4_dir_entry_2 * de;
@@ -1355,7 +1353,7 @@
 
 	if (ext4_has_inline_data(dir)) {
 		int has_inline_data = 1;
-		ret = ext4_find_inline_entry(dir, &fname, d_name, res_dir,
+		ret = ext4_find_inline_entry(dir, &fname, res_dir,
 					     &has_inline_data);
 		if (has_inline_data) {
 			if (inlined)
@@ -1447,7 +1445,7 @@
 			goto next;
 		}
 		set_buffer_verified(bh);
-		i = search_dirblock(bh, dir, &fname, d_name,
+		i = search_dirblock(bh, dir, &fname,
 			    block << EXT4_BLOCK_SIZE_BITS(sb), res_dir);
 		if (i == 1) {
 			EXT4_I(dir)->i_dir_start_lookup = block;
@@ -1488,7 +1486,6 @@
 {
 	struct super_block * sb = dir->i_sb;
 	struct dx_frame frames[2], *frame;
-	const struct qstr *d_name = fname->usr_fname;
 	struct buffer_head *bh;
 	ext4_lblk_t block;
 	int retval;
@@ -1505,7 +1502,7 @@
 		if (IS_ERR(bh))
 			goto errout;
 
-		retval = search_dirblock(bh, dir, fname, d_name,
+		retval = search_dirblock(bh, dir, fname,
 					 block << EXT4_BLOCK_SIZE_BITS(sb),
 					 res_dir);
 		if (retval == 1)
@@ -1530,7 +1527,7 @@
 
 	bh = NULL;
 errout:
-	dxtrace(printk(KERN_DEBUG "%s not found\n", d_name->name));
+	dxtrace(printk(KERN_DEBUG "%s not found\n", fname->usr_fname->name));
 success:
 	dx_release(frames);
 	return bh;
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 0b177da..d37c81f 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -848,14 +848,9 @@
 {
 	int type;
 
-	if (ext4_has_feature_quota(sb)) {
-		dquot_disable(sb, -1,
-			      DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
-	} else {
-		/* Use our quota_off function to clear inode flags etc. */
-		for (type = 0; type < EXT4_MAXQUOTAS; type++)
-			ext4_quota_off(sb, type);
-	}
+	/* Use our quota_off function to clear inode flags etc. */
+	for (type = 0; type < EXT4_MAXQUOTAS; type++)
+		ext4_quota_off(sb, type);
 }
 #else
 static inline void ext4_quota_off_umount(struct super_block *sb)
@@ -1179,6 +1174,9 @@
 		return res;
 	}
 
+	res = dquot_initialize(inode);
+	if (res)
+		return res;
 retry:
 	handle = ext4_journal_start(inode, EXT4_HT_MISC,
 			ext4_jbd2_credits_xattr(inode));
@@ -5485,7 +5483,7 @@
 		goto out;
 
 	err = dquot_quota_off(sb, type);
-	if (err)
+	if (err || ext4_has_feature_quota(sb))
 		goto out_put;
 
 	inode_lock(inode);
@@ -5505,6 +5503,7 @@
 out_unlock:
 	inode_unlock(inode);
 out_put:
+	lockdep_set_quota_inode(inode, I_DATA_SEM_NORMAL);
 	iput(inode);
 	return err;
 out:
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 8fb7ce1..5d3c253 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -888,6 +888,8 @@
 			else {
 				u32 ref;
 
+				WARN_ON_ONCE(dquot_initialize_needed(inode));
+
 				/* The old block is released after updating
 				   the inode. */
 				error = dquot_alloc_block(inode,
@@ -954,6 +956,8 @@
 			/* We need to allocate a new block */
 			ext4_fsblk_t goal, block;
 
+			WARN_ON_ONCE(dquot_initialize_needed(inode));
+
 			goal = ext4_group_first_block_no(sb,
 						EXT4_I(inode)->i_block_group);
 
@@ -1166,6 +1170,7 @@
 		return -EINVAL;
 	if (strlen(name) > 255)
 		return -ERANGE;
+
 	ext4_write_lock_xattr(inode, &no_expand);
 
 	error = ext4_reserve_inode_write(handle, inode, &is.iloc);
@@ -1267,6 +1272,9 @@
 	int error, retries = 0;
 	int credits = ext4_jbd2_credits_xattr(inode);
 
+	error = dquot_initialize(inode);
+	if (error)
+		return error;
 retry:
 	handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits);
 	if (IS_ERR(handle)) {
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 9ee4832..2d30a6d 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -680,6 +680,12 @@
 
 	rwsem_release(&journal->j_trans_commit_map, 1, _THIS_IP_);
 	handle->h_buffer_credits = nblocks;
+	/*
+	 * Restore the original nofs context because the journal restart
+	 * is basically the same thing as journal stop and start.
+	 * start_this_handle will start a new nofs context.
+	 */
+	memalloc_nofs_restore(handle->saved_alloc_context);
 	ret = start_this_handle(journal, handle, gfp_mask);
 	return ret;
 }
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index ebf80c7..48813ae 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -1512,6 +1512,22 @@
 }
 EXPORT_SYMBOL(dquot_initialize);
 
+bool dquot_initialize_needed(struct inode *inode)
+{
+	struct dquot **dquots;
+	int i;
+
+	if (!dquot_active(inode))
+		return false;
+
+	dquots = i_dquot(inode);
+	for (i = 0; i < MAXQUOTAS; i++)
+		if (!dquots[i] && sb_has_quota_active(inode->i_sb, i))
+			return true;
+	return false;
+}
+EXPORT_SYMBOL(dquot_initialize_needed);
+
 /*
  * Release all quotas referenced by inode.
  *
diff --git a/fs/stat.c b/fs/stat.c
index f494b18..c356108 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -672,6 +672,7 @@
 		inode->i_bytes -= 512;
 	}
 }
+EXPORT_SYMBOL(__inode_add_bytes);
 
 void inode_add_bytes(struct inode *inode, loff_t bytes)
 {
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index a0376a2..d642cc0 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -82,7 +82,8 @@
 			ufs_error (sb, "ufs_free_fragments",
 				   "bit already cleared for fragment %u", i);
 	}
-	
+
+	inode_sub_bytes(inode, count << uspi->s_fshift);
 	fs32_add(sb, &ucg->cg_cs.cs_nffree, count);
 	uspi->cs_total.cs_nffree += count;
 	fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, count);
@@ -184,6 +185,7 @@
 			ufs_error(sb, "ufs_free_blocks", "freeing free fragment");
 		}
 		ubh_setblock(UCPI_UBH(ucpi), ucpi->c_freeoff, blkno);
+		inode_sub_bytes(inode, uspi->s_fpb << uspi->s_fshift);
 		if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
 			ufs_clusteracct (sb, ucpi, blkno, 1);
 
@@ -494,6 +496,20 @@
 	return 0;
 }		
 
+static bool try_add_frags(struct inode *inode, unsigned frags)
+{
+	unsigned size = frags * i_blocksize(inode);
+	spin_lock(&inode->i_lock);
+	__inode_add_bytes(inode, size);
+	if (unlikely((u32)inode->i_blocks != inode->i_blocks)) {
+		__inode_sub_bytes(inode, size);
+		spin_unlock(&inode->i_lock);
+		return false;
+	}
+	spin_unlock(&inode->i_lock);
+	return true;
+}
+
 static u64 ufs_add_fragments(struct inode *inode, u64 fragment,
 			     unsigned oldcount, unsigned newcount)
 {
@@ -530,6 +546,9 @@
 	for (i = oldcount; i < newcount; i++)
 		if (ubh_isclr (UCPI_UBH(ucpi), ucpi->c_freeoff, fragno + i))
 			return 0;
+
+	if (!try_add_frags(inode, count))
+		return 0;
 	/*
 	 * Block can be extended
 	 */
@@ -647,6 +666,7 @@
 			ubh_setbit (UCPI_UBH(ucpi), ucpi->c_freeoff, goal + i);
 		i = uspi->s_fpb - count;
 
+		inode_sub_bytes(inode, i << uspi->s_fshift);
 		fs32_add(sb, &ucg->cg_cs.cs_nffree, i);
 		uspi->cs_total.cs_nffree += i;
 		fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, i);
@@ -657,6 +677,8 @@
 	result = ufs_bitmap_search (sb, ucpi, goal, allocsize);
 	if (result == INVBLOCK)
 		return 0;
+	if (!try_add_frags(inode, count))
+		return 0;
 	for (i = 0; i < count; i++)
 		ubh_clrbit (UCPI_UBH(ucpi), ucpi->c_freeoff, result + i);
 	
@@ -716,6 +738,8 @@
 		return INVBLOCK;
 	ucpi->c_rotor = result;
 gotit:
+	if (!try_add_frags(inode, uspi->s_fpb))
+		return 0;
 	blkno = ufs_fragstoblks(result);
 	ubh_clrblock (UCPI_UBH(ucpi), ucpi->c_freeoff, blkno);
 	if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index 7e41aee..da553ff 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -235,7 +235,8 @@
 
 	p = ufs_get_direct_data_ptr(uspi, ufsi, block);
 	tmp = ufs_new_fragments(inode, p, lastfrag, ufs_data_ptr_to_cpu(sb, p),
-				new_size, err, locked_page);
+				new_size - (lastfrag & uspi->s_fpbmask), err,
+				locked_page);
 	return tmp != 0;
 }
 
@@ -284,7 +285,7 @@
 			goal += uspi->s_fpb;
 	}
 	tmp = ufs_new_fragments(inode, p, ufs_blknum(new_fragment),
-				goal, uspi->s_fpb, err, locked_page);
+				goal, nfrags, err, locked_page);
 
 	if (!tmp) {
 		*err = -ENOSPC;
@@ -402,7 +403,9 @@
 
 	if (!create) {
 		phys64 = ufs_frag_map(inode, offsets, depth);
-		goto out;
+		if (phys64)
+			map_bh(bh_result, sb, phys64 + frag);
+		return 0;
 	}
 
         /* This code entered only while writing ....? */
@@ -841,8 +844,11 @@
 	truncate_inode_pages_final(&inode->i_data);
 	if (want_delete) {
 		inode->i_size = 0;
-		if (inode->i_blocks)
+		if (inode->i_blocks &&
+		    (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+		     S_ISLNK(inode->i_mode)))
 			ufs_truncate_blocks(inode);
+		ufs_update_inode(inode, inode_needs_sync(inode));
 	}
 
 	invalidate_inode_buffers(inode);
@@ -1100,7 +1106,7 @@
        return err;
 }
 
-static void __ufs_truncate_blocks(struct inode *inode)
+static void ufs_truncate_blocks(struct inode *inode)
 {
 	struct ufs_inode_info *ufsi = UFS_I(inode);
 	struct super_block *sb = inode->i_sb;
@@ -1183,7 +1189,7 @@
 
 	truncate_setsize(inode, size);
 
-	__ufs_truncate_blocks(inode);
+	ufs_truncate_blocks(inode);
 	inode->i_mtime = inode->i_ctime = current_time(inode);
 	mark_inode_dirty(inode);
 out:
@@ -1191,16 +1197,6 @@
 	return err;
 }
 
-static void ufs_truncate_blocks(struct inode *inode)
-{
-	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-	      S_ISLNK(inode->i_mode)))
-		return;
-	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
-		return;
-	__ufs_truncate_blocks(inode);
-}
-
 int ufs_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 29ecaf7..878cc62 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -746,6 +746,23 @@
 	return;
 }
 
+static u64 ufs_max_bytes(struct super_block *sb)
+{
+	struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
+	int bits = uspi->s_apbshift;
+	u64 res;
+
+	if (bits > 21)
+		res = ~0ULL;
+	else
+		res = UFS_NDADDR + (1LL << bits) + (1LL << (2*bits)) +
+			(1LL << (3*bits));
+
+	if (res >= (MAX_LFS_FILESIZE >> uspi->s_bshift))
+		return MAX_LFS_FILESIZE;
+	return res << uspi->s_bshift;
+}
+
 static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct ufs_sb_info * sbi;
@@ -1211,6 +1228,7 @@
 			    "fast symlink size (%u)\n", uspi->s_maxsymlinklen);
 		uspi->s_maxsymlinklen = maxsymlen;
 	}
+	sb->s_maxbytes = ufs_max_bytes(sb);
 	sb->s_max_links = UFS_LINK_MAX;
 
 	inode = ufs_iget(sb, UFS_ROOTINO);
diff --git a/fs/ufs/util.h b/fs/ufs/util.h
index b7fbf53..398019f 100644
--- a/fs/ufs/util.h
+++ b/fs/ufs/util.h
@@ -473,15 +473,19 @@
 static inline int _ubh_isblockset_(struct ufs_sb_private_info * uspi,
 	struct ufs_buffer_head * ubh, unsigned begin, unsigned block)
 {
+	u8 mask;
 	switch (uspi->s_fpb) {
 	case 8:
 	    	return (*ubh_get_addr (ubh, begin + block) == 0xff);
 	case 4:
-		return (*ubh_get_addr (ubh, begin + (block >> 1)) == (0x0f << ((block & 0x01) << 2)));
+		mask = 0x0f << ((block & 0x01) << 2);
+		return (*ubh_get_addr (ubh, begin + (block >> 1)) & mask) == mask;
 	case 2:
-		return (*ubh_get_addr (ubh, begin + (block >> 2)) == (0x03 << ((block & 0x03) << 1)));
+		mask = 0x03 << ((block & 0x03) << 1);
+		return (*ubh_get_addr (ubh, begin + (block >> 2)) & mask) == mask;
 	case 1:
-		return (*ubh_get_addr (ubh, begin + (block >> 3)) == (0x01 << (block & 0x07)));
+		mask = 0x01 << (block & 0x07);
+		return (*ubh_get_addr (ubh, begin + (block >> 3)) & mask) == mask;
 	}
 	return 0;	
 }
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index ea91260..d614c5e 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -21,4 +21,5 @@
  * -Wunused-function.  This turns out to avoid the need for complex #ifdef
  * directives.  Suppress the warning in clang as well.
  */
-#define inline inline __attribute__((unused))
+#undef inline
+#define inline inline __attribute__((unused)) notrace
diff --git a/include/linux/dma-iommu.h b/include/linux/dma-iommu.h
index 4eac267..92f2083 100644
--- a/include/linux/dma-iommu.h
+++ b/include/linux/dma-iommu.h
@@ -78,6 +78,7 @@
 
 struct iommu_domain;
 struct msi_msg;
+struct device;
 
 static inline int iommu_dma_init(void)
 {
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 9ec5e22..0e306c5 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -153,7 +153,7 @@
 #endif
 
 	/* managed by elevator core */
-	char icq_cache_name[ELV_NAME_MAX + 5];	/* elvname + "_io_cq" */
+	char icq_cache_name[ELV_NAME_MAX + 6];	/* elvname + "_io_cq" */
 	struct list_head list;
 };
 
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index fffb912..1fa293a 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -417,6 +417,10 @@
 #define ICH_HCR_EN			(1 << 0)
 #define ICH_HCR_UIE			(1 << 1)
 
+#define ICH_VMCR_ACK_CTL_SHIFT		2
+#define ICH_VMCR_ACK_CTL_MASK		(1 << ICH_VMCR_ACK_CTL_SHIFT)
+#define ICH_VMCR_FIQ_EN_SHIFT		3
+#define ICH_VMCR_FIQ_EN_MASK		(1 << ICH_VMCR_FIQ_EN_SHIFT)
 #define ICH_VMCR_CBPR_SHIFT		4
 #define ICH_VMCR_CBPR_MASK		(1 << ICH_VMCR_CBPR_SHIFT)
 #define ICH_VMCR_EOIM_SHIFT		9
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index dc30f3d..d3453ee 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -25,7 +25,18 @@
 #define GICC_ENABLE			0x1
 #define GICC_INT_PRI_THRESHOLD		0xf0
 
-#define GIC_CPU_CTRL_EOImodeNS		(1 << 9)
+#define GIC_CPU_CTRL_EnableGrp0_SHIFT	0
+#define GIC_CPU_CTRL_EnableGrp0		(1 << GIC_CPU_CTRL_EnableGrp0_SHIFT)
+#define GIC_CPU_CTRL_EnableGrp1_SHIFT	1
+#define GIC_CPU_CTRL_EnableGrp1		(1 << GIC_CPU_CTRL_EnableGrp1_SHIFT)
+#define GIC_CPU_CTRL_AckCtl_SHIFT	2
+#define GIC_CPU_CTRL_AckCtl		(1 << GIC_CPU_CTRL_AckCtl_SHIFT)
+#define GIC_CPU_CTRL_FIQEn_SHIFT	3
+#define GIC_CPU_CTRL_FIQEn		(1 << GIC_CPU_CTRL_FIQEn_SHIFT)
+#define GIC_CPU_CTRL_CBPR_SHIFT		4
+#define GIC_CPU_CTRL_CBPR		(1 << GIC_CPU_CTRL_CBPR_SHIFT)
+#define GIC_CPU_CTRL_EOImodeNS_SHIFT	9
+#define GIC_CPU_CTRL_EOImodeNS		(1 << GIC_CPU_CTRL_EOImodeNS_SHIFT)
 
 #define GICC_IAR_INT_ID_MASK		0x3ff
 #define GICC_INT_SPURIOUS		1023
@@ -84,8 +95,19 @@
 #define GICH_LR_EOI			(1 << 19)
 #define GICH_LR_HW			(1 << 31)
 
-#define GICH_VMCR_CTRL_SHIFT		0
-#define GICH_VMCR_CTRL_MASK		(0x21f << GICH_VMCR_CTRL_SHIFT)
+#define GICH_VMCR_ENABLE_GRP0_SHIFT	0
+#define GICH_VMCR_ENABLE_GRP0_MASK	(1 << GICH_VMCR_ENABLE_GRP0_SHIFT)
+#define GICH_VMCR_ENABLE_GRP1_SHIFT	1
+#define GICH_VMCR_ENABLE_GRP1_MASK	(1 << GICH_VMCR_ENABLE_GRP1_SHIFT)
+#define GICH_VMCR_ACK_CTL_SHIFT		2
+#define GICH_VMCR_ACK_CTL_MASK		(1 << GICH_VMCR_ACK_CTL_SHIFT)
+#define GICH_VMCR_FIQ_EN_SHIFT		3
+#define GICH_VMCR_FIQ_EN_MASK		(1 << GICH_VMCR_FIQ_EN_SHIFT)
+#define GICH_VMCR_CBPR_SHIFT		4
+#define GICH_VMCR_CBPR_MASK		(1 << GICH_VMCR_CBPR_SHIFT)
+#define GICH_VMCR_EOI_MODE_SHIFT	9
+#define GICH_VMCR_EOI_MODE_MASK		(1 << GICH_VMCR_EOI_MODE_SHIFT)
+
 #define GICH_VMCR_PRIMASK_SHIFT		27
 #define GICH_VMCR_PRIMASK_MASK		(0x1f << GICH_VMCR_PRIMASK_SHIFT)
 #define GICH_VMCR_BINPOINT_SHIFT	21
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 9c6f768..dda22f4 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -44,6 +44,7 @@
 void inode_reclaim_rsv_space(struct inode *inode, qsize_t number);
 
 int dquot_initialize(struct inode *inode);
+bool dquot_initialize_needed(struct inode *inode);
 void dquot_drop(struct inode *inode);
 struct dquot *dqget(struct super_block *sb, struct kqid qid);
 static inline struct dquot *dqgrab(struct dquot *dquot)
@@ -207,6 +208,11 @@
 	return 0;
 }
 
+static inline bool dquot_initialize_needed(struct inode *inode)
+{
+	return false;
+}
+
 static inline void dquot_drop(struct inode *inode)
 {
 }
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 167ad88..4c1d5f7e 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -172,9 +172,7 @@
 {
 	int retval;
 
-	preempt_disable();
 	retval = __srcu_read_lock(sp);
-	preempt_enable();
 	rcu_lock_acquire(&(sp)->dep_map);
 	return retval;
 }
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 0b1cf32..d971837 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -189,8 +189,6 @@
 struct platform_freeze_ops {
 	int (*begin)(void);
 	int (*prepare)(void);
-	void (*wake)(void);
-	void (*sync)(void);
 	void (*restore)(void);
 	void (*end)(void);
 };
@@ -430,8 +428,7 @@
 
 extern bool pm_wakeup_pending(void);
 extern void pm_system_wakeup(void);
-extern void pm_system_cancel_wakeup(void);
-extern void pm_wakeup_clear(bool reset);
+extern void pm_wakeup_clear(void);
 extern void pm_system_irq_wakeup(unsigned int irq_number);
 extern bool pm_get_wakeup_count(unsigned int *count, bool block);
 extern bool pm_save_wakeup_count(unsigned int count);
@@ -481,7 +478,7 @@
 
 static inline bool pm_wakeup_pending(void) { return false; }
 static inline void pm_system_wakeup(void) {}
-static inline void pm_wakeup_clear(bool reset) {}
+static inline void pm_wakeup_clear(void) {}
 static inline void pm_system_irq_wakeup(unsigned int irq_number) {}
 
 static inline void lock_system_sleep(void) {}
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 9ae6fbe..cb51034 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1658,13 +1658,13 @@
 	ret = !sp->name || sp->cant_stop ? -EINVAL : 0;
 	mutex_unlock(&cpuhp_state_mutex);
 	if (ret)
-		return ret;
+		goto out;
 
 	if (st->state < target)
 		ret = do_cpu_up(dev->id, target);
 	else
 		ret = do_cpu_down(dev->id, target);
-
+out:
 	unlock_device_hotplug();
 	return ret ? ret : count;
 }
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6e75a5c..6c4e523 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7316,6 +7316,21 @@
 	return __perf_event_account_interrupt(event, 1);
 }
 
+static bool sample_is_allowed(struct perf_event *event, struct pt_regs *regs)
+{
+	/*
+	 * Due to interrupt latency (AKA "skid"), we may enter the
+	 * kernel before taking an overflow, even if the PMU is only
+	 * counting user events.
+	 * To avoid leaking information to userspace, we must always
+	 * reject kernel samples when exclude_kernel is set.
+	 */
+	if (event->attr.exclude_kernel && !user_mode(regs))
+		return false;
+
+	return true;
+}
+
 /*
  * Generic event overflow handling, sampling.
  */
@@ -7337,6 +7352,12 @@
 	ret = __perf_event_account_interrupt(event, throttle);
 
 	/*
+	 * For security, drop the skid kernel samples if necessary.
+	 */
+	if (!sample_is_allowed(event, regs))
+		return ret;
+
+	/*
 	 * XXX event_limit might not quite work as expected on inherited
 	 * events
 	 */
diff --git a/kernel/power/process.c b/kernel/power/process.c
index 78672d3..c7209f0 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -132,7 +132,7 @@
 	if (!pm_freezing)
 		atomic_inc(&system_freezing_cnt);
 
-	pm_wakeup_clear(true);
+	pm_wakeup_clear();
 	pr_info("Freezing user space processes ... ");
 	pm_freezing = true;
 	error = try_to_freeze_tasks(true);
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index c0248c7..15e6bae 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -72,8 +72,6 @@
 
 static void freeze_enter(void)
 {
-	trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_FREEZE, true);
-
 	spin_lock_irq(&suspend_freeze_lock);
 	if (pm_wakeup_pending())
 		goto out;
@@ -100,27 +98,6 @@
  out:
 	suspend_freeze_state = FREEZE_STATE_NONE;
 	spin_unlock_irq(&suspend_freeze_lock);
-
-	trace_suspend_resume(TPS("machine_suspend"), PM_SUSPEND_FREEZE, false);
-}
-
-static void s2idle_loop(void)
-{
-	do {
-		freeze_enter();
-
-		if (freeze_ops && freeze_ops->wake)
-			freeze_ops->wake();
-
-		dpm_resume_noirq(PMSG_RESUME);
-		if (freeze_ops && freeze_ops->sync)
-			freeze_ops->sync();
-
-		if (pm_wakeup_pending())
-			break;
-
-		pm_wakeup_clear(false);
-	} while (!dpm_suspend_noirq(PMSG_SUSPEND));
 }
 
 void freeze_wake(void)
@@ -394,8 +371,10 @@
 	 * all the devices are suspended.
 	 */
 	if (state == PM_SUSPEND_FREEZE) {
-		s2idle_loop();
-		goto Platform_early_resume;
+		trace_suspend_resume(TPS("machine_suspend"), state, true);
+		freeze_enter();
+		trace_suspend_resume(TPS("machine_suspend"), state, false);
+		goto Platform_wake;
 	}
 
 	error = disable_nonboot_cpus();
diff --git a/kernel/rcu/srcu.c b/kernel/rcu/srcu.c
index 584d8a9..dea0361 100644
--- a/kernel/rcu/srcu.c
+++ b/kernel/rcu/srcu.c
@@ -263,7 +263,7 @@
 
 /*
  * Counts the new reader in the appropriate per-CPU element of the
- * srcu_struct.  Must be called from process context.
+ * srcu_struct.
  * Returns an index that must be passed to the matching srcu_read_unlock().
  */
 int __srcu_read_lock(struct srcu_struct *sp)
@@ -271,7 +271,7 @@
 	int idx;
 
 	idx = READ_ONCE(sp->completed) & 0x1;
-	__this_cpu_inc(sp->per_cpu_ref->lock_count[idx]);
+	this_cpu_inc(sp->per_cpu_ref->lock_count[idx]);
 	smp_mb(); /* B */  /* Avoid leaking the critical section. */
 	return idx;
 }
@@ -281,7 +281,6 @@
  * Removes the count for the old reader from the appropriate per-CPU
  * element of the srcu_struct.  Note that this may well be a different
  * CPU than that which was incremented by the corresponding srcu_read_lock().
- * Must be called from process context.
  */
 void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 {
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 36e1f82..32798eb 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -97,8 +97,9 @@
 
 /*
  * Counts the new reader in the appropriate per-CPU element of the
- * srcu_struct.  Must be called from process context.
- * Returns an index that must be passed to the matching srcu_read_unlock().
+ * srcu_struct.  Can be invoked from irq/bh handlers, but the matching
+ * __srcu_read_unlock() must be in the same handler instance.  Returns an
+ * index that must be passed to the matching srcu_read_unlock().
  */
 int __srcu_read_lock(struct srcu_struct *sp)
 {
@@ -112,7 +113,7 @@
 
 /*
  * Removes the count for the old reader from the appropriate element of
- * the srcu_struct.  Must be called from process context.
+ * the srcu_struct.
  */
 void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 {
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 3ae8474..157654f 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -357,7 +357,7 @@
 
 /*
  * Counts the new reader in the appropriate per-CPU element of the
- * srcu_struct.  Must be called from process context.
+ * srcu_struct.
  * Returns an index that must be passed to the matching srcu_read_unlock().
  */
 int __srcu_read_lock(struct srcu_struct *sp)
@@ -365,7 +365,7 @@
 	int idx;
 
 	idx = READ_ONCE(sp->srcu_idx) & 0x1;
-	__this_cpu_inc(sp->sda->srcu_lock_count[idx]);
+	this_cpu_inc(sp->sda->srcu_lock_count[idx]);
 	smp_mb(); /* B */  /* Avoid leaking the critical section. */
 	return idx;
 }
@@ -375,7 +375,6 @@
  * Removes the count for the old reader from the appropriate per-CPU
  * element of the srcu_struct.  Note that this may well be a different
  * CPU than that which was incremented by the corresponding srcu_read_lock().
- * Must be called from process context.
  */
 void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 {
diff --git a/sound/core/timer.c b/sound/core/timer.c
index 2f836ca..cd67d1c 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -1618,6 +1618,7 @@
 	if (err < 0)
 		goto __err;
 
+	tu->qhead = tu->qtail = tu->qused = 0;
 	kfree(tu->queue);
 	tu->queue = NULL;
 	kfree(tu->tqueue);
@@ -1959,6 +1960,7 @@
 
 	tu = file->private_data;
 	unit = tu->tread ? sizeof(struct snd_timer_tread) : sizeof(struct snd_timer_read);
+	mutex_lock(&tu->ioctl_lock);
 	spin_lock_irq(&tu->qlock);
 	while ((long)count - result >= unit) {
 		while (!tu->qused) {
@@ -1974,7 +1976,9 @@
 			add_wait_queue(&tu->qchange_sleep, &wait);
 
 			spin_unlock_irq(&tu->qlock);
+			mutex_unlock(&tu->ioctl_lock);
 			schedule();
+			mutex_lock(&tu->ioctl_lock);
 			spin_lock_irq(&tu->qlock);
 
 			remove_wait_queue(&tu->qchange_sleep, &wait);
@@ -1994,7 +1998,6 @@
 		tu->qused--;
 		spin_unlock_irq(&tu->qlock);
 
-		mutex_lock(&tu->ioctl_lock);
 		if (tu->tread) {
 			if (copy_to_user(buffer, &tu->tqueue[qhead],
 					 sizeof(struct snd_timer_tread)))
@@ -2004,7 +2007,6 @@
 					 sizeof(struct snd_timer_read)))
 				err = -EFAULT;
 		}
-		mutex_unlock(&tu->ioctl_lock);
 
 		spin_lock_irq(&tu->qlock);
 		if (err < 0)
@@ -2014,6 +2016,7 @@
 	}
  _error:
 	spin_unlock_irq(&tu->qlock);
+	mutex_unlock(&tu->ioctl_lock);
 	return result > 0 ? result : err;
 }
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index a57988d..cbeebc0 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5854,7 +5854,11 @@
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x10c0, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
+	SND_PCI_QUIRK(0x1043, 0x10d0, "ASUS X540LA/X540LJ", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x1043, 0x11c0, "ASUS X556UR", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1043, 0x1290, "ASUS X441SA", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1043, 0x12a0, "ASUS X441UV", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC),
@@ -5862,13 +5866,10 @@
 	SND_PCI_QUIRK(0x1043, 0x1517, "Asus Zenbook UX31A", ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A),
 	SND_PCI_QUIRK(0x1043, 0x16e3, "ASUS UX50", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
+	SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1b13, "Asus U41SV", ALC269_FIXUP_INV_DMIC),
-	SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x1bbd, "ASUS Z550MA", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1043, 0x10d0, "ASUS X540LA/X540LJ", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1043, 0x11c0, "ASUS X556UR", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1043, 0x1290, "ASUS X441SA", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
-	SND_PCI_QUIRK(0x1043, 0x12a0, "ASUS X441UV", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1043, 0x1c23, "Asus X55U", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
 	SND_PCI_QUIRK(0x1043, 0x1ccd, "ASUS X555UB", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
 	SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC),
diff --git a/sound/soc/atmel/atmel-classd.c b/sound/soc/atmel/atmel-classd.c
index 7ae46c2..b7ef8c5 100644
--- a/sound/soc/atmel/atmel-classd.c
+++ b/sound/soc/atmel/atmel-classd.c
@@ -301,6 +301,14 @@
 	return 0;
 }
 
+static int atmel_classd_codec_resume(struct snd_soc_codec *codec)
+{
+	struct snd_soc_card *card = snd_soc_codec_get_drvdata(codec);
+	struct atmel_classd *dd = snd_soc_card_get_drvdata(card);
+
+	return regcache_sync(dd->regmap);
+}
+
 static struct regmap *atmel_classd_codec_get_remap(struct device *dev)
 {
 	return dev_get_regmap(dev, NULL);
@@ -308,6 +316,7 @@
 
 static struct snd_soc_codec_driver soc_codec_dev_classd = {
 	.probe		= atmel_classd_codec_probe,
+	.resume		= atmel_classd_codec_resume,
 	.get_regmap	= atmel_classd_codec_get_remap,
 	.component_driver = {
 		.controls		= atmel_classd_snd_controls,
diff --git a/sound/soc/codecs/da7213.c b/sound/soc/codecs/da7213.c
index 6dd7578..024d83f 100644
--- a/sound/soc/codecs/da7213.c
+++ b/sound/soc/codecs/da7213.c
@@ -772,7 +772,7 @@
 				++i;
 				msleep(50);
 			}
-		} while ((i < DA7213_SRM_CHECK_RETRIES) & (!srm_lock));
+		} while ((i < DA7213_SRM_CHECK_RETRIES) && (!srm_lock));
 
 		if (!srm_lock)
 			dev_warn(codec->dev, "SRM failed to lock\n");
diff --git a/sound/soc/codecs/rt286.c b/sound/soc/codecs/rt286.c
index 9c365a7..7899a2c 100644
--- a/sound/soc/codecs/rt286.c
+++ b/sound/soc/codecs/rt286.c
@@ -1108,6 +1108,13 @@
 			DMI_MATCH(DMI_PRODUCT_NAME, "Kabylake Client platform")
 		}
 	},
+	{
+		.ident = "Thinkpad Helix 2nd",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad Helix 2nd")
+		}
+	},
 
 	{ }
 };
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index 2c9deda..bc136d2 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -202,7 +202,7 @@
 	if (ret < 0)
 		return ret;
 
-	ret = asoc_simple_card_init_mic(rtd->card, &priv->hp_jack, PREFIX);
+	ret = asoc_simple_card_init_mic(rtd->card, &priv->mic_jack, PREFIX);
 	if (ret < 0)
 		return ret;
 
diff --git a/sound/soc/intel/skylake/skl-sst-ipc.c b/sound/soc/intel/skylake/skl-sst-ipc.c
index 58c5250..498b153 100644
--- a/sound/soc/intel/skylake/skl-sst-ipc.c
+++ b/sound/soc/intel/skylake/skl-sst-ipc.c
@@ -413,8 +413,11 @@
 	u32 reply = header.primary & IPC_GLB_REPLY_STATUS_MASK;
 	u64 *ipc_header = (u64 *)(&header);
 	struct skl_sst *skl = container_of(ipc, struct skl_sst, ipc);
+	unsigned long flags;
 
+	spin_lock_irqsave(&ipc->dsp->spinlock, flags);
 	msg = skl_ipc_reply_get_msg(ipc, *ipc_header);
+	spin_unlock_irqrestore(&ipc->dsp->spinlock, flags);
 	if (msg == NULL) {
 		dev_dbg(ipc->dev, "ipc: rx list is empty\n");
 		return;
@@ -456,8 +459,10 @@
 		}
 	}
 
+	spin_lock_irqsave(&ipc->dsp->spinlock, flags);
 	list_del(&msg->list);
 	sst_ipc_tx_msg_reply_complete(ipc, msg);
+	spin_unlock_irqrestore(&ipc->dsp->spinlock, flags);
 }
 
 irqreturn_t skl_dsp_irq_thread_handler(int irq, void *context)
diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index 3a99712..64a0f8e 100644
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -2502,7 +2502,7 @@
 
 			if (ret < 0)
 				return ret;
-			tkn_count += ret;
+			tkn_count = ret;
 
 			tuple_size += tkn_count *
 				sizeof(struct snd_soc_tplg_vendor_string_elem);
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index 6df3b31..4c9b578 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -410,7 +410,7 @@
 	struct skl *skl  = ebus_to_skl(ebus);
 	struct hdac_bus *bus = ebus_to_hbus(ebus);
 
-	skl->init_failed = 1; /* to be sure */
+	skl->init_done = 0; /* to be sure */
 
 	snd_hdac_ext_stop_streams(ebus);
 
@@ -428,8 +428,10 @@
 
 	snd_hdac_ext_bus_exit(ebus);
 
+	cancel_work_sync(&skl->probe_work);
 	if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI))
 		snd_hdac_i915_exit(&ebus->bus);
+
 	return 0;
 }
 
@@ -566,6 +568,84 @@
 	.get_response = snd_hdac_bus_get_response,
 };
 
+static int skl_i915_init(struct hdac_bus *bus)
+{
+	int err;
+
+	/*
+	 * The HDMI codec is in GPU so we need to ensure that it is powered
+	 * up and ready for probe
+	 */
+	err = snd_hdac_i915_init(bus);
+	if (err < 0)
+		return err;
+
+	err = snd_hdac_display_power(bus, true);
+	if (err < 0)
+		dev_err(bus->dev, "Cannot turn on display power on i915\n");
+
+	return err;
+}
+
+static void skl_probe_work(struct work_struct *work)
+{
+	struct skl *skl = container_of(work, struct skl, probe_work);
+	struct hdac_ext_bus *ebus = &skl->ebus;
+	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_ext_link *hlink = NULL;
+	int err;
+
+	if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) {
+		err = skl_i915_init(bus);
+		if (err < 0)
+			return;
+	}
+
+	err = skl_init_chip(bus, true);
+	if (err < 0) {
+		dev_err(bus->dev, "Init chip failed with err: %d\n", err);
+		goto out_err;
+	}
+
+	/* codec detection */
+	if (!bus->codec_mask)
+		dev_info(bus->dev, "no hda codecs found!\n");
+
+	/* create codec instances */
+	err = skl_codec_create(ebus);
+	if (err < 0)
+		goto out_err;
+
+	if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) {
+		err = snd_hdac_display_power(bus, false);
+		if (err < 0) {
+			dev_err(bus->dev, "Cannot turn off display power on i915\n");
+			return;
+		}
+	}
+
+	/* register platform dai and controls */
+	err = skl_platform_register(bus->dev);
+	if (err < 0)
+		return;
+	/*
+	 * we are done probing so decrement link counts
+	 */
+	list_for_each_entry(hlink, &ebus->hlink_list, list)
+		snd_hdac_ext_bus_link_put(ebus, hlink);
+
+	/* configure PM */
+	pm_runtime_put_noidle(bus->dev);
+	pm_runtime_allow(bus->dev);
+	skl->init_done = 1;
+
+	return;
+
+out_err:
+	if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI))
+		err = snd_hdac_display_power(bus, false);
+}
+
 /*
  * constructor
  */
@@ -593,6 +673,7 @@
 	snd_hdac_ext_bus_init(ebus, &pci->dev, &bus_core_ops, io_ops);
 	ebus->bus.use_posbuf = 1;
 	skl->pci = pci;
+	INIT_WORK(&skl->probe_work, skl_probe_work);
 
 	ebus->bus.bdl_pos_adj = 0;
 
@@ -601,27 +682,6 @@
 	return 0;
 }
 
-static int skl_i915_init(struct hdac_bus *bus)
-{
-	int err;
-
-	/*
-	 * The HDMI codec is in GPU so we need to ensure that it is powered
-	 * up and ready for probe
-	 */
-	err = snd_hdac_i915_init(bus);
-	if (err < 0)
-		return err;
-
-	err = snd_hdac_display_power(bus, true);
-	if (err < 0) {
-		dev_err(bus->dev, "Cannot turn on display power on i915\n");
-		return err;
-	}
-
-	return err;
-}
-
 static int skl_first_init(struct hdac_ext_bus *ebus)
 {
 	struct skl *skl = ebus_to_skl(ebus);
@@ -684,20 +744,7 @@
 	/* initialize chip */
 	skl_init_pci(skl);
 
-	if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) {
-		err = skl_i915_init(bus);
-		if (err < 0)
-			return err;
-	}
-
-	skl_init_chip(bus, true);
-
-	/* codec detection */
-	if (!bus->codec_mask) {
-		dev_info(bus->dev, "no hda codecs found!\n");
-	}
-
-	return 0;
+	return skl_init_chip(bus, true);
 }
 
 static int skl_probe(struct pci_dev *pci,
@@ -706,7 +753,6 @@
 	struct skl *skl;
 	struct hdac_ext_bus *ebus = NULL;
 	struct hdac_bus *bus = NULL;
-	struct hdac_ext_link *hlink = NULL;
 	int err;
 
 	/* we use ext core ops, so provide NULL for ops here */
@@ -729,7 +775,7 @@
 
 	if (skl->nhlt == NULL) {
 		err = -ENODEV;
-		goto out_display_power_off;
+		goto out_free;
 	}
 
 	err = skl_nhlt_create_sysfs(skl);
@@ -760,56 +806,24 @@
 	if (bus->mlcap)
 		snd_hdac_ext_bus_get_ml_capabilities(ebus);
 
+	snd_hdac_bus_stop_chip(bus);
+
 	/* create device for soc dmic */
 	err = skl_dmic_device_register(skl);
 	if (err < 0)
 		goto out_dsp_free;
 
-	/* register platform dai and controls */
-	err = skl_platform_register(bus->dev);
-	if (err < 0)
-		goto out_dmic_free;
-
-	/* create codec instances */
-	err = skl_codec_create(ebus);
-	if (err < 0)
-		goto out_unregister;
-
-	if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI)) {
-		err = snd_hdac_display_power(bus, false);
-		if (err < 0) {
-			dev_err(bus->dev, "Cannot turn off display power on i915\n");
-			return err;
-		}
-	}
-
-	/*
-	 * we are done probling so decrement link counts
-	 */
-	list_for_each_entry(hlink, &ebus->hlink_list, list)
-		snd_hdac_ext_bus_link_put(ebus, hlink);
-
-	/* configure PM */
-	pm_runtime_put_noidle(bus->dev);
-	pm_runtime_allow(bus->dev);
+	schedule_work(&skl->probe_work);
 
 	return 0;
 
-out_unregister:
-	skl_platform_unregister(bus->dev);
-out_dmic_free:
-	skl_dmic_device_unregister(skl);
 out_dsp_free:
 	skl_free_dsp(skl);
 out_mach_free:
 	skl_machine_device_unregister(skl);
 out_nhlt_free:
 	skl_nhlt_free(skl->nhlt);
-out_display_power_off:
-	if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI))
-		snd_hdac_display_power(bus, false);
 out_free:
-	skl->init_failed = 1;
 	skl_free(ebus);
 
 	return err;
@@ -828,7 +842,7 @@
 
 	skl = ebus_to_skl(ebus);
 
-	if (skl->init_failed)
+	if (!skl->init_done)
 		return;
 
 	snd_hdac_ext_stop_streams(ebus);
diff --git a/sound/soc/intel/skylake/skl.h b/sound/soc/intel/skylake/skl.h
index a454f60..2a630fc 100644
--- a/sound/soc/intel/skylake/skl.h
+++ b/sound/soc/intel/skylake/skl.h
@@ -46,7 +46,7 @@
 	struct hdac_ext_bus ebus;
 	struct pci_dev *pci;
 
-	unsigned int init_failed:1; /* delayed init failed */
+	unsigned int init_done:1; /* delayed init status */
 	struct platform_device *dmic_dev;
 	struct platform_device *i2s_dev;
 	struct snd_soc_platform *platform;
@@ -64,6 +64,8 @@
 	const struct firmware *tplg;
 
 	int supend_active;
+
+	struct work_struct probe_work;
 };
 
 #define skl_to_ebus(s)	(&(s)->ebus)
diff --git a/sound/soc/sh/rcar/adg.c b/sound/soc/sh/rcar/adg.c
index 66203d1..d3b0dc1 100644
--- a/sound/soc/sh/rcar/adg.c
+++ b/sound/soc/sh/rcar/adg.c
@@ -507,7 +507,8 @@
 				rbga = rbgx;
 				adg->rbga_rate_for_441khz = rate / div;
 				ckr |= brg_table[i] << 20;
-				if (req_441kHz_rate)
+				if (req_441kHz_rate &&
+				    !(adg_mode_flags(adg) & AUDIO_OUT_48))
 					parent_clk_name = __clk_get_name(clk);
 			}
 		}
@@ -522,7 +523,8 @@
 				rbgb = rbgx;
 				adg->rbgb_rate_for_48khz = rate / div;
 				ckr |= brg_table[i] << 16;
-				if (req_48kHz_rate)
+				if (req_48kHz_rate &&
+				    (adg_mode_flags(adg) & AUDIO_OUT_48))
 					parent_clk_name = __clk_get_name(clk);
 			}
 		}
diff --git a/sound/soc/sh/rcar/cmd.c b/sound/soc/sh/rcar/cmd.c
index 7d92a24..d879c01 100644
--- a/sound/soc/sh/rcar/cmd.c
+++ b/sound/soc/sh/rcar/cmd.c
@@ -89,6 +89,7 @@
 	dev_dbg(dev, "ctu/mix path = 0x%08x", data);
 
 	rsnd_mod_write(mod, CMD_ROUTE_SLCT, data);
+	rsnd_mod_write(mod, CMD_BUSIF_MODE, rsnd_get_busif_shift(io, mod) | 1);
 	rsnd_mod_write(mod, CMD_BUSIF_DALIGN, rsnd_get_dalign(mod, io));
 
 	rsnd_adg_set_cmd_timsel_gen2(mod, io);
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index 1744015..8c1f4e2 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -343,6 +343,57 @@
 		return 0x76543210;
 }
 
+u32 rsnd_get_busif_shift(struct rsnd_dai_stream *io, struct rsnd_mod *mod)
+{
+	enum rsnd_mod_type playback_mods[] = {
+		RSND_MOD_SRC,
+		RSND_MOD_CMD,
+		RSND_MOD_SSIU,
+	};
+	enum rsnd_mod_type capture_mods[] = {
+		RSND_MOD_CMD,
+		RSND_MOD_SRC,
+		RSND_MOD_SSIU,
+	};
+	struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
+	struct rsnd_mod *tmod = NULL;
+	enum rsnd_mod_type *mods =
+		rsnd_io_is_play(io) ?
+		playback_mods : capture_mods;
+	int i;
+
+	/*
+	 * This is needed for 24bit data
+	 * We need to shift 8bit
+	 *
+	 * Linux 24bit data is located as 0x00******
+	 * HW    24bit data is located as 0x******00
+	 *
+	 */
+	switch (runtime->sample_bits) {
+	case 16:
+		return 0;
+	case 32:
+		break;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(playback_mods); i++) {
+		tmod = rsnd_io_to_mod(io, mods[i]);
+		if (tmod)
+			break;
+	}
+
+	if (tmod != mod)
+		return 0;
+
+	if (rsnd_io_is_play(io))
+		return  (0 << 20) | /* shift to Left */
+			(8 << 16);  /* 8bit */
+	else
+		return  (1 << 20) | /* shift to Right */
+			(8 << 16);  /* 8bit */
+}
+
 /*
  *	rsnd_dai functions
  */
diff --git a/sound/soc/sh/rcar/gen.c b/sound/soc/sh/rcar/gen.c
index 63b6d3c..4b09807 100644
--- a/sound/soc/sh/rcar/gen.c
+++ b/sound/soc/sh/rcar/gen.c
@@ -236,6 +236,7 @@
 		RSND_GEN_M_REG(SRC_ROUTE_MODE0,	0xc,	0x20),
 		RSND_GEN_M_REG(SRC_CTRL,	0x10,	0x20),
 		RSND_GEN_M_REG(SRC_INT_ENABLE0,	0x18,	0x20),
+		RSND_GEN_M_REG(CMD_BUSIF_MODE,	0x184,	0x20),
 		RSND_GEN_M_REG(CMD_BUSIF_DALIGN,0x188,	0x20),
 		RSND_GEN_M_REG(CMD_ROUTE_SLCT,	0x18c,	0x20),
 		RSND_GEN_M_REG(CMD_CTRL,	0x190,	0x20),
diff --git a/sound/soc/sh/rcar/rsnd.h b/sound/soc/sh/rcar/rsnd.h
index dbf4163..323af41 100644
--- a/sound/soc/sh/rcar/rsnd.h
+++ b/sound/soc/sh/rcar/rsnd.h
@@ -73,6 +73,7 @@
 	RSND_REG_SCU_SYS_INT_EN0,
 	RSND_REG_SCU_SYS_INT_EN1,
 	RSND_REG_CMD_CTRL,
+	RSND_REG_CMD_BUSIF_MODE,
 	RSND_REG_CMD_BUSIF_DALIGN,
 	RSND_REG_CMD_ROUTE_SLCT,
 	RSND_REG_CMDOUT_TIMSEL,
@@ -204,6 +205,7 @@
 		    u32 mask, u32 data);
 u32 rsnd_get_adinr_bit(struct rsnd_mod *mod, struct rsnd_dai_stream *io);
 u32 rsnd_get_dalign(struct rsnd_mod *mod, struct rsnd_dai_stream *io);
+u32 rsnd_get_busif_shift(struct rsnd_dai_stream *io, struct rsnd_mod *mod);
 
 /*
  *	R-Car DMA
diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c
index 20b5b2ec..76a477a 100644
--- a/sound/soc/sh/rcar/src.c
+++ b/sound/soc/sh/rcar/src.c
@@ -190,11 +190,13 @@
 	struct rsnd_priv *priv = rsnd_mod_to_priv(mod);
 	struct device *dev = rsnd_priv_to_dev(priv);
 	struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
+	int is_play = rsnd_io_is_play(io);
 	int use_src = 0;
 	u32 fin, fout;
 	u32 ifscr, fsrate, adinr;
 	u32 cr, route;
 	u32 bsdsr, bsisr;
+	u32 i_busif, o_busif, tmp;
 	uint ratio;
 
 	if (!runtime)
@@ -270,6 +272,11 @@
 		break;
 	}
 
+	/* BUSIF_MODE */
+	tmp = rsnd_get_busif_shift(io, mod);
+	i_busif = ( is_play ? tmp : 0) | 1;
+	o_busif = (!is_play ? tmp : 0) | 1;
+
 	rsnd_mod_write(mod, SRC_ROUTE_MODE0, route);
 
 	rsnd_mod_write(mod, SRC_SRCIR, 1);	/* initialize */
@@ -281,8 +288,9 @@
 	rsnd_mod_write(mod, SRC_BSISR, bsisr);
 	rsnd_mod_write(mod, SRC_SRCIR, 0);	/* cancel initialize */
 
-	rsnd_mod_write(mod, SRC_I_BUSIF_MODE, 1);
-	rsnd_mod_write(mod, SRC_O_BUSIF_MODE, 1);
+	rsnd_mod_write(mod, SRC_I_BUSIF_MODE, i_busif);
+	rsnd_mod_write(mod, SRC_O_BUSIF_MODE, o_busif);
+
 	rsnd_mod_write(mod, SRC_BUSIF_DALIGN, rsnd_get_dalign(mod, io));
 
 	rsnd_adg_set_src_timesel_gen2(mod, io, fin, fout);
diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c
index 135c566..91e5c07 100644
--- a/sound/soc/sh/rcar/ssi.c
+++ b/sound/soc/sh/rcar/ssi.c
@@ -302,7 +302,7 @@
 	 * always use 32bit system word.
 	 * see also rsnd_ssi_master_clk_enable()
 	 */
-	cr_own = FORCE | SWL_32 | PDTA;
+	cr_own = FORCE | SWL_32;
 
 	if (rdai->bit_clk_inv)
 		cr_own |= SCKP;
@@ -550,6 +550,13 @@
 		struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
 		u32 *buf = (u32 *)(runtime->dma_area +
 				   rsnd_dai_pointer_offset(io, 0));
+		int shift = 0;
+
+		switch (runtime->sample_bits) {
+		case 32:
+			shift = 8;
+			break;
+		}
 
 		/*
 		 * 8/16/32 data can be assesse to TDR/RDR register
@@ -557,9 +564,9 @@
 		 * see rsnd_ssi_init()
 		 */
 		if (rsnd_io_is_play(io))
-			rsnd_mod_write(mod, SSITDR, *buf);
+			rsnd_mod_write(mod, SSITDR, (*buf) << shift);
 		else
-			*buf = rsnd_mod_read(mod, SSIRDR);
+			*buf = (rsnd_mod_read(mod, SSIRDR) >> shift);
 
 		elapsed = rsnd_dai_pointer_update(io, sizeof(*buf));
 	}
@@ -709,6 +716,11 @@
 			       struct rsnd_priv *priv)
 {
 	struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod);
+	struct rsnd_mod *ssi_parent_mod = rsnd_io_to_mod_ssip(io);
+
+	/* Do nothing for SSI parent mod */
+	if (ssi_parent_mod == mod)
+		return 0;
 
 	/* PIO will request IRQ again */
 	free_irq(ssi->irq, mod);
diff --git a/sound/soc/sh/rcar/ssiu.c b/sound/soc/sh/rcar/ssiu.c
index 14fafda..512d238 100644
--- a/sound/soc/sh/rcar/ssiu.c
+++ b/sound/soc/sh/rcar/ssiu.c
@@ -144,7 +144,8 @@
 			       (rsnd_io_is_play(io) ?
 				rsnd_runtime_channel_after_ctu(io) :
 				rsnd_runtime_channel_original(io)));
-		rsnd_mod_write(mod, SSI_BUSIF_MODE,  1);
+		rsnd_mod_write(mod, SSI_BUSIF_MODE,
+			       rsnd_get_busif_shift(io, mod) | 1);
 		rsnd_mod_write(mod, SSI_BUSIF_DALIGN,
 			       rsnd_get_dalign(mod, io));
 	}
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index aae099c..754e3ef 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -2286,6 +2286,9 @@
 	list_for_each_entry(rtd, &card->rtd_list, list)
 		flush_delayed_work(&rtd->delayed_work);
 
+	/* free the ALSA card at first; this syncs with pending operations */
+	snd_card_free(card->snd_card);
+
 	/* remove and free each DAI */
 	soc_remove_dai_links(card);
 	soc_remove_pcm_runtimes(card);
@@ -2300,9 +2303,7 @@
 	if (card->remove)
 		card->remove(card);
 
-	snd_card_free(card->snd_card);
 	return 0;
-
 }
 
 /* removes a socdev */
diff --git a/tools/perf/Documentation/perf-probe.txt b/tools/perf/Documentation/perf-probe.txt
index e6c9902..165c2b1 100644
--- a/tools/perf/Documentation/perf-probe.txt
+++ b/tools/perf/Documentation/perf-probe.txt
@@ -240,9 +240,13 @@
  or
  ./perf probe --add='schedule:12 cpu'
 
- this will add one or more probes which has the name start with "schedule".
+Add one or more probes which has the name start with "schedule".
 
- Add probes on lines in schedule() function which calls update_rq_clock().
+ ./perf probe schedule*
+ or
+ ./perf probe --add='schedule*'
+
+Add probes on lines in schedule() function which calls update_rq_clock().
 
  ./perf probe 'schedule;update_rq_clock*'
  or
diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index dfbb506..142606c 100644
--- a/tools/perf/Documentation/perf-script-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -39,7 +39,7 @@
 When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
-ignored (or passed to a 'trace_handled' function, see below) and the
+ignored (or passed to a 'trace_unhandled' function, see below) and the
 next event is processed.
 
 Most of the event's field values are passed as arguments to the
diff --git a/tools/perf/Documentation/perf-script-python.txt b/tools/perf/Documentation/perf-script-python.txt
index 54acba2..51ec2d2 100644
--- a/tools/perf/Documentation/perf-script-python.txt
+++ b/tools/perf/Documentation/perf-script-python.txt
@@ -149,10 +149,8 @@
 		print "id=%d, args=%s\n" % \
 		(id, args),
 
-def trace_unhandled(event_name, context, common_cpu, common_secs, common_nsecs,
-		common_pid, common_comm):
-		print_header(event_name, common_cpu, common_secs, common_nsecs,
-		common_pid, common_comm)
+def trace_unhandled(event_name, context, event_fields_dict):
+		print ' '.join(['%s=%s'%(k,str(v))for k,v in sorted(event_fields_dict.items())])
 
 def print_header(event_name, cpu, secs, nsecs, pid, comm):
 	print "%-20s %5u %05u.%09u %8u %-20s " % \
@@ -321,7 +319,7 @@
 process can be generalized to any tracepoint or set of tracepoints
 you're interested in - basically find the tracepoint(s) you're
 interested in by looking at the list of available events shown by
-'perf list' and/or look in /sys/kernel/debug/tracing events for
+'perf list' and/or look in /sys/kernel/debug/tracing/events/ for
 detailed event and field info, record the corresponding trace data
 using 'perf record', passing it the list of interesting events,
 generate a skeleton script using 'perf script -g python' and modify the
@@ -334,7 +332,7 @@
 scripts listed by the 'perf script -l' command e.g.:
 
 ----
-root@tropicana:~# perf script -l
+# perf script -l
 List of available trace scripts:
   wakeup-latency                       system-wide min/max/avg wakeup latency
   rw-by-file <comm>                    r/w activity for a program, by file
@@ -383,8 +381,6 @@
 
 ----
 # ls -al kernel-source/tools/perf/scripts/python
-
-root@tropicana:/home/trz/src/tip# ls -al tools/perf/scripts/python
 total 32
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:30 .
 drwxr-xr-x 4 trz trz 4096 2010-01-26 22:29 ..
@@ -399,7 +395,7 @@
 should show a new entry for your script:
 
 ----
-root@tropicana:~# perf script -l
+# perf script -l
 List of available trace scripts:
   wakeup-latency                       system-wide min/max/avg wakeup latency
   rw-by-file <comm>                    r/w activity for a program, by file
@@ -437,7 +433,7 @@
 When perf script is invoked using a trace script, a user-defined
 'handler function' is called for each event in the trace.  If there's
 no handler function defined for a given event type, the event is
-ignored (or passed to a 'trace_handled' function, see below) and the
+ignored (or passed to a 'trace_unhandled' function, see below) and the
 next event is processed.
 
 Most of the event's field values are passed as arguments to the
@@ -532,7 +528,7 @@
 gives scripts a chance to do setup tasks:
 
 ----
-def trace_begin:
+def trace_begin():
     pass
 ----
 
@@ -541,7 +537,7 @@
  as display results:
 
 ----
-def trace_end:
+def trace_end():
     pass
 ----
 
@@ -550,8 +546,7 @@
  of common arguments are passed into it:
 
 ----
-def trace_unhandled(event_name, context, common_cpu, common_secs,
-        common_nsecs, common_pid, common_comm):
+def trace_unhandled(event_name, context, event_fields_dict):
     pass
 ----
 
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index 837067f..6b40e9f 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -26,6 +26,7 @@
 
 const char *const powerpc_triplets[] = {
 	"powerpc-unknown-linux-gnu-",
+	"powerpc-linux-gnu-",
 	"powerpc64-unknown-linux-gnu-",
 	"powerpc64-linux-gnu-",
 	"powerpc64le-linux-gnu-",
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index a935b50..ad9324d1 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -1578,6 +1578,7 @@
 static void print_footer(void)
 {
 	FILE *output = stat_config.output;
+	int n;
 
 	if (!null_run)
 		fprintf(output, "\n");
@@ -1590,7 +1591,9 @@
 	}
 	fprintf(output, "\n\n");
 
-	if (print_free_counters_hint)
+	if (print_free_counters_hint &&
+	    sysctl__read_int("kernel/nmi_watchdog", &n) >= 0 &&
+	    n > 0)
 		fprintf(output,
 "Some events weren't counted. Try disabling the NMI watchdog:\n"
 "	echo 0 > /proc/sys/kernel/nmi_watchdog\n"
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index d014350..4b2a5d2 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -681,6 +681,10 @@
 	{ .name	    = "mlockall",   .errmsg = true,
 	  .arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
 	{ .name	    = "mmap",	    .hexret = true,
+/* The standard mmap maps to old_mmap on s390x */
+#if defined(__s390x__)
+	.alias = "old_mmap",
+#endif
 	  .arg_scnprintf = { [0] = SCA_HEX,	  /* addr */
 			     [2] = SCA_MMAP_PROT, /* prot */
 			     [3] = SCA_MMAP_FLAGS, /* flags */ }, },
diff --git a/tools/perf/tests/bp_signal.c b/tools/perf/tests/bp_signal.c
index e7664fe..8ba2c46 100644
--- a/tools/perf/tests/bp_signal.c
+++ b/tools/perf/tests/bp_signal.c
@@ -288,3 +288,17 @@
 	return count1 == 1 && overflows == 3 && count2 == 3 && overflows_2 == 3 && count3 == 2 ?
 		TEST_OK : TEST_FAIL;
 }
+
+bool test__bp_signal_is_supported(void)
+{
+/*
+ * The powerpc so far does not have support to even create
+ * instruction breakpoint using the perf event interface.
+ * Once it's there we can release this.
+ */
+#ifdef __powerpc__
+	return false;
+#else
+	return true;
+#endif
+}
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 9e08d29..3ccfd58 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -97,10 +97,12 @@
 	{
 		.desc = "Breakpoint overflow signal handler",
 		.func = test__bp_signal,
+		.is_supported = test__bp_signal_is_supported,
 	},
 	{
 		.desc = "Breakpoint overflow sampling",
 		.func = test__bp_signal_overflow,
+		.is_supported = test__bp_signal_is_supported,
 	},
 	{
 		.desc = "Number of exit events of a simple workload",
@@ -401,6 +403,11 @@
 		if (!perf_test__matches(t, curr, argc, argv))
 			continue;
 
+		if (t->is_supported && !t->is_supported()) {
+			pr_debug("%2d: %-*s: Disabled\n", i, width, t->desc);
+			continue;
+		}
+
 		pr_info("%2d: %-*s:", i, width, t->desc);
 
 		if (intlist__find(skiplist, i)) {
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 1f14e76..94b7c7b 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -229,6 +229,8 @@
 	unsigned char buf2[BUFSZ];
 	size_t ret_len;
 	u64 objdump_addr;
+	const char *objdump_name;
+	char decomp_name[KMOD_DECOMP_LEN];
 	int ret;
 
 	pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
@@ -289,9 +291,25 @@
 		state->done[state->done_cnt++] = al.map->start;
 	}
 
+	objdump_name = al.map->dso->long_name;
+	if (dso__needs_decompress(al.map->dso)) {
+		if (dso__decompress_kmodule_path(al.map->dso, objdump_name,
+						 decomp_name,
+						 sizeof(decomp_name)) < 0) {
+			pr_debug("decompression failed\n");
+			return -1;
+		}
+
+		objdump_name = decomp_name;
+	}
+
 	/* Read the object code using objdump */
 	objdump_addr = map__rip_2objdump(al.map, al.addr);
-	ret = read_via_objdump(al.map->dso->long_name, objdump_addr, buf2, len);
+	ret = read_via_objdump(objdump_name, objdump_addr, buf2, len);
+
+	if (dso__needs_decompress(al.map->dso))
+		unlink(objdump_name);
+
 	if (ret > 0) {
 		/*
 		 * The kernel maps are inaccurate - assume objdump is right in
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 6318596..5773638 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -34,6 +34,7 @@
 		int (*get_nr)(void);
 		const char *(*get_desc)(int subtest);
 	} subtest;
+	bool (*is_supported)(void);
 };
 
 /* Tests */
@@ -99,6 +100,8 @@
 int test__clang_subtest_get_nr(void);
 int test__unit_number__scnprint(int subtest);
 
+bool test__bp_signal_is_supported(void);
+
 #if defined(__arm__) || defined(__aarch64__)
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 struct thread;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 683f834..ddbd56d 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -239,10 +239,20 @@
 	const char *s = strchr(ops->raw, '+');
 	const char *c = strchr(ops->raw, ',');
 
-	if (c++ != NULL)
+	/*
+	 * skip over possible up to 2 operands to get to address, e.g.:
+	 * tbnz	 w0, #26, ffff0000083cd190 <security_file_permission+0xd0>
+	 */
+	if (c++ != NULL) {
 		ops->target.addr = strtoull(c, NULL, 16);
-	else
+		if (!ops->target.addr) {
+			c = strchr(c, ',');
+			if (c++ != NULL)
+				ops->target.addr = strtoull(c, NULL, 16);
+		}
+	} else {
 		ops->target.addr = strtoull(ops->raw, NULL, 16);
+	}
 
 	if (s++ != NULL) {
 		ops->target.offset = strtoull(s, NULL, 16);
@@ -257,10 +267,27 @@
 static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
+	const char *c = strchr(ops->raw, ',');
+
 	if (!ops->target.addr || ops->target.offset < 0)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
-	return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset);
+	if (c != NULL) {
+		const char *c2 = strchr(c + 1, ',');
+
+		/* check for 3-op insn */
+		if (c2 != NULL)
+			c = c2;
+		c++;
+
+		/* mirror arch objdump's space-after-comma style */
+		if (*c == ' ')
+			c++;
+	}
+
+	return scnprintf(bf, size, "%-6.6s %.*s%" PRIx64,
+			 ins->name, c ? c - ops->raw : 0, ops->raw,
+			 ops->target.offset);
 }
 
 static struct ins_ops jump_ops = {
@@ -1294,6 +1321,7 @@
 	char linkname[PATH_MAX];
 	char *build_id_filename;
 	char *build_id_path = NULL;
+	char *pos;
 
 	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
 	    !dso__is_kcore(dso))
@@ -1313,7 +1341,14 @@
 	if (!build_id_path)
 		return -1;
 
-	dirname(build_id_path);
+	/*
+	 * old style build-id cache has name of XX/XXXXXXX.. while
+	 * new style has XX/XXXXXXX../{elf,kallsyms,vdso}.
+	 * extract the build-id part of dirname in the new style only.
+	 */
+	pos = strrchr(build_id_path, '/');
+	if (pos && strlen(pos) < SBUILD_ID_SIZE - 2)
+		dirname(build_id_path);
 
 	if (dso__is_kcore(dso) ||
 	    readlink(build_id_path, linkname, sizeof(linkname)) < 0 ||
@@ -1396,31 +1431,10 @@
 				sizeof(symfs_filename));
 		}
 	} else if (dso__needs_decompress(dso)) {
-		char tmp[PATH_MAX];
-		struct kmod_path m;
-		int fd;
-		bool ret;
+		char tmp[KMOD_DECOMP_LEN];
 
-		if (kmod_path__parse_ext(&m, symfs_filename))
-			goto out;
-
-		snprintf(tmp, PATH_MAX, "/tmp/perf-kmod-XXXXXX");
-
-		fd = mkstemp(tmp);
-		if (fd < 0) {
-			free(m.ext);
-			goto out;
-		}
-
-		ret = decompress_to_file(m.ext, symfs_filename, fd);
-
-		if (ret)
-			pr_err("Cannot decompress %s %s\n", m.ext, symfs_filename);
-
-		free(m.ext);
-		close(fd);
-
-		if (!ret)
+		if (dso__decompress_kmodule_path(dso, symfs_filename,
+						 tmp, sizeof(tmp)) < 0)
 			goto out;
 
 		strcpy(symfs_filename, tmp);
@@ -1429,7 +1443,7 @@
 	snprintf(command, sizeof(command),
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -l -d %s %s -C %s 2>/dev/null|grep -v %s:|expand",
+		 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
 		 objdump_path ? objdump_path : "objdump",
 		 disassembler_style ? "-M " : "",
 		 disassembler_style ? disassembler_style : "",
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 168cc49..e0148b0 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -278,51 +278,6 @@
 	return bf;
 }
 
-bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size)
-{
-	char *id_name = NULL, *ch;
-	struct stat sb;
-	char sbuild_id[SBUILD_ID_SIZE];
-
-	if (!dso->has_build_id)
-		goto err;
-
-	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
-	id_name = build_id_cache__linkname(sbuild_id, NULL, 0);
-	if (!id_name)
-		goto err;
-	if (access(id_name, F_OK))
-		goto err;
-	if (lstat(id_name, &sb) == -1)
-		goto err;
-	if ((size_t)sb.st_size > size - 1)
-		goto err;
-	if (readlink(id_name, bf, size - 1) < 0)
-		goto err;
-
-	bf[sb.st_size] = '\0';
-
-	/*
-	 * link should be:
-	 * ../../lib/modules/4.4.0-rc4/kernel/net/ipv4/netfilter/nf_nat_ipv4.ko/a09fe3eb3147dafa4e3b31dbd6257e4d696bdc92
-	 */
-	ch = strrchr(bf, '/');
-	if (!ch)
-		goto err;
-	if (ch - 3 < bf)
-		goto err;
-
-	free(id_name);
-	return strncmp(".ko", ch - 3, 3) == 0;
-err:
-	pr_err("Invalid build id: %s\n", id_name ? :
-					 dso->long_name ? :
-					 dso->short_name ? :
-					 "[unknown]");
-	free(id_name);
-	return false;
-}
-
 #define dsos__for_each_with_build_id(pos, head)	\
 	list_for_each_entry(pos, head, node)	\
 		if (!pos->has_build_id)		\
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 8a89b19..96690a5 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -17,7 +17,6 @@
 				    size_t size);
 
 char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
-bool dso__build_id_is_kmod(const struct dso *dso, char *bf, size_t size);
 
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct perf_evsel *evsel,
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index a96a99d..4e7ab61 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -248,6 +248,64 @@
 		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
 }
 
+static int decompress_kmodule(struct dso *dso, const char *name, char *tmpbuf)
+{
+	int fd = -1;
+	struct kmod_path m;
+
+	if (!dso__needs_decompress(dso))
+		return -1;
+
+	if (kmod_path__parse_ext(&m, dso->long_name))
+		return -1;
+
+	if (!m.comp)
+		goto out;
+
+	fd = mkstemp(tmpbuf);
+	if (fd < 0) {
+		dso->load_errno = errno;
+		goto out;
+	}
+
+	if (!decompress_to_file(m.ext, name, fd)) {
+		dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
+		close(fd);
+		fd = -1;
+	}
+
+out:
+	free(m.ext);
+	return fd;
+}
+
+int dso__decompress_kmodule_fd(struct dso *dso, const char *name)
+{
+	char tmpbuf[] = KMOD_DECOMP_NAME;
+	int fd;
+
+	fd = decompress_kmodule(dso, name, tmpbuf);
+	unlink(tmpbuf);
+	return fd;
+}
+
+int dso__decompress_kmodule_path(struct dso *dso, const char *name,
+				 char *pathname, size_t len)
+{
+	char tmpbuf[] = KMOD_DECOMP_NAME;
+	int fd;
+
+	fd = decompress_kmodule(dso, name, tmpbuf);
+	if (fd < 0) {
+		unlink(tmpbuf);
+		return -1;
+	}
+
+	strncpy(pathname, tmpbuf, len);
+	close(fd);
+	return 0;
+}
+
 /*
  * Parses kernel module specified in @path and updates
  * @m argument like:
@@ -335,6 +393,21 @@
 	return 0;
 }
 
+void dso__set_module_info(struct dso *dso, struct kmod_path *m,
+			  struct machine *machine)
+{
+	if (machine__is_host(machine))
+		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
+	else
+		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
+
+	/* _KMODULE_COMP should be next to _KMODULE */
+	if (m->kmod && m->comp)
+		dso->symtab_type++;
+
+	dso__set_short_name(dso, strdup(m->name), true);
+}
+
 /*
  * Global list of open DSOs and the counter.
  */
@@ -381,7 +454,7 @@
 
 static int __open_dso(struct dso *dso, struct machine *machine)
 {
-	int fd;
+	int fd = -EINVAL;
 	char *root_dir = (char *)"";
 	char *name = malloc(PATH_MAX);
 
@@ -392,15 +465,30 @@
 		root_dir = machine->root_dir;
 
 	if (dso__read_binary_type_filename(dso, dso->binary_type,
-					    root_dir, name, PATH_MAX)) {
-		free(name);
-		return -EINVAL;
-	}
+					    root_dir, name, PATH_MAX))
+		goto out;
 
 	if (!is_regular_file(name))
-		return -EINVAL;
+		goto out;
+
+	if (dso__needs_decompress(dso)) {
+		char newpath[KMOD_DECOMP_LEN];
+		size_t len = sizeof(newpath);
+
+		if (dso__decompress_kmodule_path(dso, name, newpath, len) < 0) {
+			fd = -dso->load_errno;
+			goto out;
+		}
+
+		strcpy(name, newpath);
+	}
 
 	fd = do_open(name);
+
+	if (dso__needs_decompress(dso))
+		unlink(name);
+
+out:
 	free(name);
 	return fd;
 }
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index 12350b1..bd061ba 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -244,6 +244,12 @@
 bool is_kernel_module(const char *pathname, int cpumode);
 bool decompress_to_file(const char *ext, const char *filename, int output_fd);
 bool dso__needs_decompress(struct dso *dso);
+int dso__decompress_kmodule_fd(struct dso *dso, const char *name);
+int dso__decompress_kmodule_path(struct dso *dso, const char *name,
+				 char *pathname, size_t len);
+
+#define KMOD_DECOMP_NAME  "/tmp/perf-kmod-XXXXXX"
+#define KMOD_DECOMP_LEN   sizeof(KMOD_DECOMP_NAME)
 
 struct kmod_path {
 	char *name;
@@ -259,6 +265,9 @@
 #define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false)
 #define kmod_path__parse_ext(__m, __p)  __kmod_path__parse(__m, __p, false, true)
 
+void dso__set_module_info(struct dso *dso, struct kmod_path *m,
+			  struct machine *machine);
+
 /*
  * The dso__data_* external interface provides following functions:
  *   dso__data_get_fd
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 314a071..5cac8d5 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1469,8 +1469,16 @@
 
 		dso__set_build_id(dso, &bev->build_id);
 
-		if (!is_kernel_module(filename, cpumode))
-			dso->kernel = dso_type;
+		if (dso_type != DSO_TYPE_USER) {
+			struct kmod_path m = { .name = NULL, };
+
+			if (!kmod_path__parse_name(&m, filename) && m.kmod)
+				dso__set_module_info(dso, &m, machine);
+			else
+				dso->kernel = dso_type;
+
+			free(m.name);
+		}
 
 		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
 				  sbuild_id);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index d97e014..d7f31cb 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -572,16 +572,7 @@
 		if (dso == NULL)
 			goto out_unlock;
 
-		if (machine__is_host(machine))
-			dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
-		else
-			dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
-
-		/* _KMODULE_COMP should be next to _KMODULE */
-		if (m->kmod && m->comp)
-			dso->symtab_type++;
-
-		dso__set_short_name(dso, strdup(m->name), true);
+		dso__set_module_info(dso, m, machine);
 		dso__set_long_name(dso, strdup(filename), true);
 	}
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 9d92af7..40de3cb 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1219,7 +1219,7 @@
 	fprintf(ofp, "# be retrieved using Python functions of the form "
 		"common_*(context).\n");
 
-	fprintf(ofp, "# See the perf-trace-python Documentation for the list "
+	fprintf(ofp, "# See the perf-script-python Documentation for the list "
 		"of available functions.\n\n");
 
 	fprintf(ofp, "import os\n");
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index e7ee47f..502505c 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -637,43 +637,6 @@
 	return 0;
 }
 
-static int decompress_kmodule(struct dso *dso, const char *name,
-			      enum dso_binary_type type)
-{
-	int fd = -1;
-	char tmpbuf[] = "/tmp/perf-kmod-XXXXXX";
-	struct kmod_path m;
-
-	if (type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP &&
-	    type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP &&
-	    type != DSO_BINARY_TYPE__BUILD_ID_CACHE)
-		return -1;
-
-	if (type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
-		name = dso->long_name;
-
-	if (kmod_path__parse_ext(&m, name) || !m.comp)
-		return -1;
-
-	fd = mkstemp(tmpbuf);
-	if (fd < 0) {
-		dso->load_errno = errno;
-		goto out;
-	}
-
-	if (!decompress_to_file(m.ext, name, fd)) {
-		dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
-		close(fd);
-		fd = -1;
-	}
-
-	unlink(tmpbuf);
-
-out:
-	free(m.ext);
-	return fd;
-}
-
 bool symsrc__possibly_runtime(struct symsrc *ss)
 {
 	return ss->dynsym || ss->opdsec;
@@ -705,9 +668,11 @@
 	int fd;
 
 	if (dso__needs_decompress(dso)) {
-		fd = decompress_kmodule(dso, name, type);
+		fd = dso__decompress_kmodule_fd(dso, name);
 		if (fd < 0)
 			return -1;
+
+		type = dso->symtab_type;
 	} else {
 		fd = open(name, O_RDONLY);
 		if (fd < 0) {
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 8f2b068..e7a98db 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1562,10 +1562,6 @@
 	if (!runtime_ss && syms_ss)
 		runtime_ss = syms_ss;
 
-	if (syms_ss && syms_ss->type == DSO_BINARY_TYPE__BUILD_ID_CACHE)
-		if (dso__build_id_is_kmod(dso, name, PATH_MAX))
-			kmod = true;
-
 	if (syms_ss)
 		ret = dso__load_sym(dso, map, syms_ss, runtime_ss, kmod);
 	else
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 943a062..da45c4b 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -39,6 +39,14 @@
 		return 0;
 
 	mod = dwfl_addrmodule(ui->dwfl, ip);
+	if (mod) {
+		Dwarf_Addr s;
+
+		dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
+		if (s != al->map->start)
+			mod = 0;
+	}
+
 	if (!mod)
 		mod = dwfl_report_elf(ui->dwfl, dso->short_name,
 				      dso->long_name, -1, al->map->start,
@@ -224,7 +232,7 @@
 
 	err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui);
 
-	if (err && !ui->max_stack)
+	if (err && ui->max_stack != max_stack)
 		err = 0;
 
 	/*
diff --git a/virt/kvm/arm/hyp/vgic-v3-sr.c b/virt/kvm/arm/hyp/vgic-v3-sr.c
index 32c3295..8794036 100644
--- a/virt/kvm/arm/hyp/vgic-v3-sr.c
+++ b/virt/kvm/arm/hyp/vgic-v3-sr.c
@@ -22,7 +22,7 @@
 #include <asm/kvm_hyp.h>
 
 #define vtr_to_max_lr_idx(v)		((v) & 0xf)
-#define vtr_to_nr_pre_bits(v)		(((u32)(v) >> 26) + 1)
+#define vtr_to_nr_pre_bits(v)		((((u32)(v) >> 26) & 7) + 1)
 
 static u64 __hyp_text __gic_v3_get_lr(unsigned int lr)
 {
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index a2d6324..e2e5eff 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -879,6 +879,9 @@
 	pmd_t *pmd;
 
 	pud = stage2_get_pud(kvm, cache, addr);
+	if (!pud)
+		return NULL;
+
 	if (stage2_pud_none(*pud)) {
 		if (!cache)
 			return NULL;
diff --git a/virt/kvm/arm/vgic/vgic-mmio-v2.c b/virt/kvm/arm/vgic/vgic-mmio-v2.c
index 0a4283e..63e0bbd 100644
--- a/virt/kvm/arm/vgic/vgic-mmio-v2.c
+++ b/virt/kvm/arm/vgic/vgic-mmio-v2.c
@@ -226,7 +226,13 @@
 
 	switch (addr & 0xff) {
 	case GIC_CPU_CTRL:
-		val = vmcr.ctlr;
+		val = vmcr.grpen0 << GIC_CPU_CTRL_EnableGrp0_SHIFT;
+		val |= vmcr.grpen1 << GIC_CPU_CTRL_EnableGrp1_SHIFT;
+		val |= vmcr.ackctl << GIC_CPU_CTRL_AckCtl_SHIFT;
+		val |= vmcr.fiqen << GIC_CPU_CTRL_FIQEn_SHIFT;
+		val |= vmcr.cbpr << GIC_CPU_CTRL_CBPR_SHIFT;
+		val |= vmcr.eoim << GIC_CPU_CTRL_EOImodeNS_SHIFT;
+
 		break;
 	case GIC_CPU_PRIMASK:
 		/*
@@ -267,7 +273,13 @@
 
 	switch (addr & 0xff) {
 	case GIC_CPU_CTRL:
-		vmcr.ctlr = val;
+		vmcr.grpen0 = !!(val & GIC_CPU_CTRL_EnableGrp0);
+		vmcr.grpen1 = !!(val & GIC_CPU_CTRL_EnableGrp1);
+		vmcr.ackctl = !!(val & GIC_CPU_CTRL_AckCtl);
+		vmcr.fiqen = !!(val & GIC_CPU_CTRL_FIQEn);
+		vmcr.cbpr = !!(val & GIC_CPU_CTRL_CBPR);
+		vmcr.eoim = !!(val & GIC_CPU_CTRL_EOImodeNS);
+
 		break;
 	case GIC_CPU_PRIMASK:
 		/*
diff --git a/virt/kvm/arm/vgic/vgic-v2.c b/virt/kvm/arm/vgic/vgic-v2.c
index 504b4bd..e4187e5 100644
--- a/virt/kvm/arm/vgic/vgic-v2.c
+++ b/virt/kvm/arm/vgic/vgic-v2.c
@@ -177,7 +177,18 @@
 	struct vgic_v2_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v2;
 	u32 vmcr;
 
-	vmcr  = (vmcrp->ctlr << GICH_VMCR_CTRL_SHIFT) & GICH_VMCR_CTRL_MASK;
+	vmcr = (vmcrp->grpen0 << GICH_VMCR_ENABLE_GRP0_SHIFT) &
+		GICH_VMCR_ENABLE_GRP0_MASK;
+	vmcr |= (vmcrp->grpen1 << GICH_VMCR_ENABLE_GRP1_SHIFT) &
+		GICH_VMCR_ENABLE_GRP1_MASK;
+	vmcr |= (vmcrp->ackctl << GICH_VMCR_ACK_CTL_SHIFT) &
+		GICH_VMCR_ACK_CTL_MASK;
+	vmcr |= (vmcrp->fiqen << GICH_VMCR_FIQ_EN_SHIFT) &
+		GICH_VMCR_FIQ_EN_MASK;
+	vmcr |= (vmcrp->cbpr << GICH_VMCR_CBPR_SHIFT) &
+		GICH_VMCR_CBPR_MASK;
+	vmcr |= (vmcrp->eoim << GICH_VMCR_EOI_MODE_SHIFT) &
+		GICH_VMCR_EOI_MODE_MASK;
 	vmcr |= (vmcrp->abpr << GICH_VMCR_ALIAS_BINPOINT_SHIFT) &
 		GICH_VMCR_ALIAS_BINPOINT_MASK;
 	vmcr |= (vmcrp->bpr << GICH_VMCR_BINPOINT_SHIFT) &
@@ -195,8 +206,19 @@
 
 	vmcr = cpu_if->vgic_vmcr;
 
-	vmcrp->ctlr = (vmcr & GICH_VMCR_CTRL_MASK) >>
-			GICH_VMCR_CTRL_SHIFT;
+	vmcrp->grpen0 = (vmcr & GICH_VMCR_ENABLE_GRP0_MASK) >>
+		GICH_VMCR_ENABLE_GRP0_SHIFT;
+	vmcrp->grpen1 = (vmcr & GICH_VMCR_ENABLE_GRP1_MASK) >>
+		GICH_VMCR_ENABLE_GRP1_SHIFT;
+	vmcrp->ackctl = (vmcr & GICH_VMCR_ACK_CTL_MASK) >>
+		GICH_VMCR_ACK_CTL_SHIFT;
+	vmcrp->fiqen = (vmcr & GICH_VMCR_FIQ_EN_MASK) >>
+		GICH_VMCR_FIQ_EN_SHIFT;
+	vmcrp->cbpr = (vmcr & GICH_VMCR_CBPR_MASK) >>
+		GICH_VMCR_CBPR_SHIFT;
+	vmcrp->eoim = (vmcr & GICH_VMCR_EOI_MODE_MASK) >>
+		GICH_VMCR_EOI_MODE_SHIFT;
+
 	vmcrp->abpr = (vmcr & GICH_VMCR_ALIAS_BINPOINT_MASK) >>
 			GICH_VMCR_ALIAS_BINPOINT_SHIFT;
 	vmcrp->bpr  = (vmcr & GICH_VMCR_BINPOINT_MASK) >>
diff --git a/virt/kvm/arm/vgic/vgic-v3.c b/virt/kvm/arm/vgic/vgic-v3.c
index 6fe3f00..030248e 100644
--- a/virt/kvm/arm/vgic/vgic-v3.c
+++ b/virt/kvm/arm/vgic/vgic-v3.c
@@ -159,15 +159,24 @@
 void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	u32 model = vcpu->kvm->arch.vgic.vgic_model;
 	u32 vmcr;
 
-	/*
-	 * Ignore the FIQen bit, because GIC emulation always implies
-	 * SRE=1 which means the vFIQEn bit is also RES1.
-	 */
-	vmcr = ((vmcrp->ctlr >> ICC_CTLR_EL1_EOImode_SHIFT) <<
-		 ICH_VMCR_EOIM_SHIFT) & ICH_VMCR_EOIM_MASK;
-	vmcr |= (vmcrp->ctlr << ICH_VMCR_CBPR_SHIFT) & ICH_VMCR_CBPR_MASK;
+	if (model == KVM_DEV_TYPE_ARM_VGIC_V2) {
+		vmcr = (vmcrp->ackctl << ICH_VMCR_ACK_CTL_SHIFT) &
+			ICH_VMCR_ACK_CTL_MASK;
+		vmcr |= (vmcrp->fiqen << ICH_VMCR_FIQ_EN_SHIFT) &
+			ICH_VMCR_FIQ_EN_MASK;
+	} else {
+		/*
+		 * When emulating GICv3 on GICv3 with SRE=1 on the
+		 * VFIQEn bit is RES1 and the VAckCtl bit is RES0.
+		 */
+		vmcr = ICH_VMCR_FIQ_EN_MASK;
+	}
+
+	vmcr |= (vmcrp->cbpr << ICH_VMCR_CBPR_SHIFT) & ICH_VMCR_CBPR_MASK;
+	vmcr |= (vmcrp->eoim << ICH_VMCR_EOIM_SHIFT) & ICH_VMCR_EOIM_MASK;
 	vmcr |= (vmcrp->abpr << ICH_VMCR_BPR1_SHIFT) & ICH_VMCR_BPR1_MASK;
 	vmcr |= (vmcrp->bpr << ICH_VMCR_BPR0_SHIFT) & ICH_VMCR_BPR0_MASK;
 	vmcr |= (vmcrp->pmr << ICH_VMCR_PMR_SHIFT) & ICH_VMCR_PMR_MASK;
@@ -180,17 +189,27 @@
 void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp)
 {
 	struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3;
+	u32 model = vcpu->kvm->arch.vgic.vgic_model;
 	u32 vmcr;
 
 	vmcr = cpu_if->vgic_vmcr;
 
-	/*
-	 * Ignore the FIQen bit, because GIC emulation always implies
-	 * SRE=1 which means the vFIQEn bit is also RES1.
-	 */
-	vmcrp->ctlr = ((vmcr >> ICH_VMCR_EOIM_SHIFT) <<
-			ICC_CTLR_EL1_EOImode_SHIFT) & ICC_CTLR_EL1_EOImode_MASK;
-	vmcrp->ctlr |= (vmcr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT;
+	if (model == KVM_DEV_TYPE_ARM_VGIC_V2) {
+		vmcrp->ackctl = (vmcr & ICH_VMCR_ACK_CTL_MASK) >>
+			ICH_VMCR_ACK_CTL_SHIFT;
+		vmcrp->fiqen = (vmcr & ICH_VMCR_FIQ_EN_MASK) >>
+			ICH_VMCR_FIQ_EN_SHIFT;
+	} else {
+		/*
+		 * When emulating GICv3 on GICv3 with SRE=1 on the
+		 * VFIQEn bit is RES1 and the VAckCtl bit is RES0.
+		 */
+		vmcrp->fiqen = 1;
+		vmcrp->ackctl = 0;
+	}
+
+	vmcrp->cbpr = (vmcr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT;
+	vmcrp->eoim = (vmcr & ICH_VMCR_EOIM_MASK) >> ICH_VMCR_EOIM_SHIFT;
 	vmcrp->abpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT;
 	vmcrp->bpr  = (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT;
 	vmcrp->pmr  = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT;
diff --git a/virt/kvm/arm/vgic/vgic.h b/virt/kvm/arm/vgic/vgic.h
index da83e4ca..bba7fa2 100644
--- a/virt/kvm/arm/vgic/vgic.h
+++ b/virt/kvm/arm/vgic/vgic.h
@@ -111,14 +111,18 @@
  * registers regardless of the hardware backed GIC used.
  */
 struct vgic_vmcr {
-	u32	ctlr;
+	u32	grpen0;
+	u32	grpen1;
+
+	u32	ackctl;
+	u32	fiqen;
+	u32	cbpr;
+	u32	eoim;
+
 	u32	abpr;
 	u32	bpr;
 	u32	pmr;  /* Priority mask field in the GICC_PMR and
 		       * ICC_PMR_EL1 priority field format */
-	/* Below member variable are valid only for GICv3 */
-	u32	grpen0;
-	u32	grpen1;
 };
 
 struct vgic_reg_attr {