Merge tag 'v3.15-rc4' into devel

Linux 3.15-rc4

154 files changed, 1223 insertions, 706 deletions

diff --git a/Documentation/devicetree/bindings/arm/arch_timer.txt b/Documentation/devicetree/bindings/arm/arch_timer.txt
index 06fc760..37b2caf 100644
--- a/Documentation/devicetree/bindings/arm/arch_timer.txt
+++ b/Documentation/devicetree/bindings/arm/arch_timer.txt
@@ -19,6 +19,9 @@ to deliver its interrupts via SPIs.
 
 - clock-frequency : The frequency of the main counter, in Hz. Optional.
 
+- always-on : a boolean property. If present, the timer is powered through an
+  always-on power domain, therefore it never loses context.
+
 Example:
 
 	timer {
diff --git a/Documentation/devicetree/bindings/ata/apm-xgene.txt b/Documentation/devicetree/bindings/ata/apm-xgene.txt
index 7bcfbf5..a668f0e 100644
--- a/Documentation/devicetree/bindings/ata/apm-xgene.txt
+++ b/Documentation/devicetree/bindings/ata/apm-xgene.txt
@@ -24,6 +24,7 @@ Required properties:
   * "sata-phy" for the SATA 6.0Gbps PHY
 
 Optional properties:
+- dma-coherent		: Present if dma operations are coherent
 - status		: Shall be "ok" if enabled or "disabled" if disabled.
 			  Default is "ok".
 
@@ -55,6 +56,7 @@ Example:
 			      <0x0 0x1f22e000 0x0 0x1000>,
 			      <0x0 0x1f227000 0x0 0x1000>;
 			interrupts = <0x0 0x87 0x4>;
+			dma-coherent;
 			status = "ok";
 			clocks = <&sataclk 0>;
 			phys = <&phy2 0>;
@@ -69,6 +71,7 @@ Example:
 			      <0x0 0x1f23e000 0x0 0x1000>,
 			      <0x0 0x1f237000 0x0 0x1000>;
 			interrupts = <0x0 0x88 0x4>;
+			dma-coherent;
 			status = "ok";
 			clocks = <&sataclk 0>;
 			phys = <&phy3 0>;
diff --git a/Documentation/devicetree/bindings/net/socfpga-dwmac.txt b/Documentation/devicetree/bindings/net/socfpga-dwmac.txt
index 636f0ac..2a60cd3 100644
--- a/Documentation/devicetree/bindings/net/socfpga-dwmac.txt
+++ b/Documentation/devicetree/bindings/net/socfpga-dwmac.txt
@@ -23,5 +23,5 @@ gmac0: ethernet@ff700000 {
 	interrupt-names = "macirq";
 	mac-address = [00 00 00 00 00 00];/* Filled in by U-Boot */
 	clocks = <&emac_0_clk>;
-	clocks-names = "stmmaceth";
+	clock-names = "stmmaceth";
 };
diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
index 80c1fb8..a2acd2b 100644
--- a/Documentation/devicetree/bindings/net/stmmac.txt
+++ b/Documentation/devicetree/bindings/net/stmmac.txt
@@ -33,7 +33,7 @@ Optional properties:
 - max-frame-size: See ethernet.txt file in the same directory
 - clocks: If present, the first clock should be the GMAC main clock,
   further clocks may be specified in derived bindings.
-- clocks-names: One name for each entry in the clocks property, the
+- clock-names: One name for each entry in the clocks property, the
   first one should be "stmmaceth".
 
 Examples:
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-st.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-st.txt
index 4bd5be0..26bcb18 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-st.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-st.txt
@@ -83,7 +83,7 @@ Example:
 		reg 		= <0xfe61f080 0x4>;
 		reg-names	= "irqmux";
 		interrupts 	= <GIC_SPI 180 IRQ_TYPE_LEVEL_HIGH>;
-		interrupts-names = "irqmux";
+		interrupt-names	= "irqmux";
 		ranges 		= <0 0xfe610000 0x5000>;
 
 		PIO0: gpio@fe610000 {
@@ -165,7 +165,7 @@ sdhci0:sdhci@fe810000{
 	interrupt-parent = <&PIO3>;
 	#interrupt-cells = <2>;
 	interrupts = <3 IRQ_TYPE_LEVEL_HIGH>; /* Interrupt line via PIO3-3 */
-	interrupts-names = "card-detect";
+	interrupt-names = "card-detect";
 	pinctrl-names = "default";
 	pinctrl-0	= <&pinctrl_mmc>;
 };
diff --git a/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.txt b/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.txt
index 569b26c4..60ca079 100644
--- a/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.txt
+++ b/Documentation/devicetree/bindings/sound/davinci-mcasp-audio.txt
@@ -47,7 +47,7 @@ mcasp0: mcasp0@1d00000 {
 	reg = <0x100000 0x3000>;
 	reg-names "mpu";
 	interrupts = <82>, <83>;
-	interrupts-names = "tx", "rx";
+	interrupt-names = "tx", "rx";
 	op-mode = <0>;		/* MCASP_IIS_MODE */
 	tdm-slots = <2>;
 	serial-dir = <
diff --git a/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt b/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt
index 74c66de..eff12be 100644
--- a/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt
+++ b/Documentation/devicetree/bindings/sound/tlv320aic31xx.txt
@@ -13,6 +13,9 @@ Required properties:
     "ti,tlv320aic3111" - TLV320AIC3111 (stereo speaker amp, MiniDSP)
 
 - reg - <int> -  I2C slave address
+- HPVDD-supply, SPRVDD-supply, SPLVDD-supply, AVDD-supply, IOVDD-supply,
+  DVDD-supply : power supplies for the device as covered in
+  Documentation/devicetree/bindings/regulator/regulator.txt
 
 
 Optional properties:
@@ -24,9 +27,6 @@ Optional properties:
         3 or MICBIAS_AVDD - MICBIAS output is connected to AVDD
 	If this node is not mentioned or if the value is unknown, then
 	micbias	is set to 2.0V.
-- HPVDD-supply, SPRVDD-supply, SPLVDD-supply, AVDD-supply, IOVDD-supply,
-  DVDD-supply : power supplies for the device as covered in
-  Documentation/devicetree/bindings/regulator/regulator.txt
 
 CODEC output pins:
   * HPL
diff --git a/MAINTAINERS b/MAINTAINERS
index 491a39d..d886239 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3485,6 +3485,12 @@ S:	Maintained
 F:	drivers/extcon/
 F:	Documentation/extcon/
 
+EXYNOS DP DRIVER
+M:	Jingoo Han <jg1.han@samsung.com>
+L:	dri-devel@lists.freedesktop.org
+S:	Maintained
+F:	drivers/gpu/drm/exynos/exynos_dp*
+
 EXYNOS MIPI DISPLAY DRIVERS
 M:	Inki Dae <inki.dae@samsung.com>
 M:	Donghwa Lee <dh09.lee@samsung.com>
@@ -3550,7 +3556,7 @@ F:	include/scsi/libfcoe.h
 F:	include/uapi/scsi/fc/
 
 FILE LOCKING (flock() and fcntl()/lockf())
-M:	Jeff Layton <jlayton@redhat.com>
+M:	Jeff Layton <jlayton@poochiereds.net>
 M:	J. Bruce Fields <bfields@fieldses.org>
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
@@ -5108,14 +5114,19 @@ F:	drivers/s390/kvm/
 
 KERNEL VIRTUAL MACHINE (KVM) FOR ARM
 M:	Christoffer Dall <christoffer.dall@linaro.org>
+M:	Marc Zyngier <marc.zyngier@arm.com>
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	kvmarm@lists.cs.columbia.edu
 W:	http://systems.cs.columbia.edu/projects/kvm-arm
 S:	Supported
 F:	arch/arm/include/uapi/asm/kvm*
 F:	arch/arm/include/asm/kvm*
 F:	arch/arm/kvm/
+F:	virt/kvm/arm/
+F:	include/kvm/arm_*
 
 KERNEL VIRTUAL MACHINE FOR ARM64 (KVM/arm64)
+M:	Christoffer Dall <christoffer.dall@linaro.org>
 M:	Marc Zyngier <marc.zyngier@arm.com>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	kvmarm@lists.cs.columbia.edu
diff --git a/Makefile b/Makefile
index 041c685..28a7259 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 15
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Shuffling Zombie Juror
 
 # *DOCUMENTATION*
diff --git a/arch/arc/kernel/entry.S b/arch/arc/kernel/entry.S
index 819dd5f..29b82ad 100644
--- a/arch/arc/kernel/entry.S
+++ b/arch/arc/kernel/entry.S
@@ -614,11 +614,13 @@ resume_user_mode_begin:
 
 resume_kernel_mode:
 
-#ifdef CONFIG_PREEMPT
-
-	; This is a must for preempt_schedule_irq()
+	; Disable Interrupts from this point on
+	; CONFIG_PREEMPT: This is a must for preempt_schedule_irq()
+	; !CONFIG_PREEMPT: To ensure restore_regs is intr safe
 	IRQ_DISABLE	r9
 
+#ifdef CONFIG_PREEMPT
+
 	; Can't preempt if preemption disabled
 	GET_CURR_THR_INFO_FROM_SP   r10
 	ld  r8, [r10, THREAD_INFO_PREEMPT_COUNT]
diff --git a/arch/arm/boot/dts/am33xx.dtsi b/arch/arm/boot/dts/am33xx.dtsi
index 07f283c..cb6811e 100644
--- a/arch/arm/boot/dts/am33xx.dtsi
+++ b/arch/arm/boot/dts/am33xx.dtsi
@@ -802,7 +802,7 @@
 			      <0x46000000 0x400000>;
 			reg-names = "mpu", "dat";
 			interrupts = <80>, <81>;
-			interrupts-names = "tx", "rx";
+			interrupt-names = "tx", "rx";
 			status = "disabled";
 			dmas = <&edma 8>,
 				<&edma 9>;
@@ -816,7 +816,7 @@
 			      <0x46400000 0x400000>;
 			reg-names = "mpu", "dat";
 			interrupts = <82>, <83>;
-			interrupts-names = "tx", "rx";
+			interrupt-names = "tx", "rx";
 			status = "disabled";
 			dmas = <&edma 10>,
 				<&edma 11>;
diff --git a/arch/arm/boot/dts/am4372.dtsi b/arch/arm/boot/dts/am4372.dtsi
index 36d523a..d1f8707 100644
--- a/arch/arm/boot/dts/am4372.dtsi
+++ b/arch/arm/boot/dts/am4372.dtsi
@@ -691,7 +691,7 @@
 			      <0x46000000 0x400000>;
 			reg-names = "mpu", "dat";
 			interrupts = <80>, <81>;
-			interrupts-names = "tx", "rx";
+			interrupt-names = "tx", "rx";
 			status = "disabled";
 			dmas = <&edma 8>,
 			       <&edma 9>;
@@ -705,7 +705,7 @@
 			      <0x46400000 0x400000>;
 			reg-names = "mpu", "dat";
 			interrupts = <82>, <83>;
-			interrupts-names = "tx", "rx";
+			interrupt-names = "tx", "rx";
 			status = "disabled";
 			dmas = <&edma 10>,
 			       <&edma 11>;
diff --git a/arch/arm/boot/dts/stih415-pinctrl.dtsi b/arch/arm/boot/dts/stih415-pinctrl.dtsi
index f09fb10..81df870 100644
--- a/arch/arm/boot/dts/stih415-pinctrl.dtsi
+++ b/arch/arm/boot/dts/stih415-pinctrl.dtsi
@@ -49,7 +49,7 @@
 			reg 		= <0xfe61f080 0x4>;
 			reg-names	= "irqmux";
 			interrupts 	= <GIC_SPI 180 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts-names = "irqmux";
+			interrupt-names	= "irqmux";
 			ranges 		= <0 0xfe610000 0x5000>;
 
 			PIO0: gpio@fe610000 {
@@ -187,7 +187,7 @@
 			reg 		= <0xfee0f080 0x4>;
 			reg-names	= "irqmux";
 			interrupts 	= <GIC_SPI 181 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts-names = "irqmux";
+			interrupt-names	= "irqmux";
 			ranges		= <0 0xfee00000 0x8000>;
 
 			PIO5: gpio@fee00000 {
@@ -282,7 +282,7 @@
 			reg 		= <0xfe82f080 0x4>;
 			reg-names	= "irqmux";
 			interrupts 	= <GIC_SPI 182 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts-names = "irqmux";
+			interrupt-names	= "irqmux";
 			ranges		= <0 0xfe820000 0x8000>;
 
 			PIO13: gpio@fe820000 {
@@ -423,7 +423,7 @@
 			reg 		= <0xfd6bf080 0x4>;
 			reg-names	= "irqmux";
 			interrupts 	= <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts-names = "irqmux";
+			interrupt-names	= "irqmux";
 			ranges		= <0 0xfd6b0000 0x3000>;
 
 			PIO100: gpio@fd6b0000 {
@@ -460,7 +460,7 @@
 			reg 		= <0xfd33f080 0x4>;
 			reg-names	= "irqmux";
 			interrupts 	= <GIC_SPI 114 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts-names = "irqmux";
+			interrupt-names	= "irqmux";
 			ranges		= <0 0xfd330000 0x5000>;
 
 			PIO103: gpio@fd330000 {
diff --git a/arch/arm/boot/dts/stih416-pinctrl.dtsi b/arch/arm/boot/dts/stih416-pinctrl.dtsi
index aeea304..250d5ec 100644
--- a/arch/arm/boot/dts/stih416-pinctrl.dtsi
+++ b/arch/arm/boot/dts/stih416-pinctrl.dtsi
@@ -53,7 +53,7 @@
 			reg 		= <0xfe61f080 0x4>;
 			reg-names	= "irqmux";
 			interrupts 	= <GIC_SPI 182 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts-names = "irqmux";
+			interrupt-names	= "irqmux";
 			ranges		= <0 0xfe610000 0x6000>;
 
 			PIO0: gpio@fe610000 {
@@ -201,7 +201,7 @@
 			reg 		= <0xfee0f080 0x4>;
 			reg-names	= "irqmux";
 			interrupts 	= <GIC_SPI 183 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts-names = "irqmux";
+			interrupt-names	= "irqmux";
 			ranges		= <0 0xfee00000 0x10000>;
 
 			PIO5: gpio@fee00000 {
@@ -333,7 +333,7 @@
 			reg 		= <0xfe82f080 0x4>;
 			reg-names	= "irqmux";
 			interrupts 	= <GIC_SPI 184 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts-names = "irqmux";
+			interrupt-names	= "irqmux";
 			ranges 		= <0 0xfe820000 0x6000>;
 
 			PIO13: gpio@fe820000 {
@@ -461,7 +461,7 @@
 			reg 		= <0xfd6bf080 0x4>;
 			reg-names	= "irqmux";
 			interrupts 	= <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts-names = "irqmux";
+			interrupt-names	= "irqmux";
 			ranges		= <0 0xfd6b0000 0x3000>;
 
 			PIO100: gpio@fd6b0000 {
@@ -498,7 +498,7 @@
 			reg 		= <0xfd33f080 0x4>;
 			reg-names	= "irqmux";
 			interrupts 	= <GIC_SPI 114 IRQ_TYPE_LEVEL_HIGH>;
-			interrupts-names = "irqmux";
+			interrupt-names	= "irqmux";
 			ranges			= <0 0xfd330000 0x5000>;
 
 			PIO103: gpio@fd330000 {
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index 466bd29..4be5bb1 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -23,7 +23,7 @@ config KVM
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_ARM_HOST
-	depends on ARM_VIRT_EXT && ARM_LPAE
+	depends on ARM_VIRT_EXT && ARM_LPAE && !CPU_BIG_ENDIAN
 	---help---
 	  Support hosting virtualized guest machines. You will also
 	  need to select one or more of the processor modules below.
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 80bb1e6..16f8049 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -42,6 +42,8 @@ static unsigned long hyp_idmap_start;
 static unsigned long hyp_idmap_end;
 static phys_addr_t hyp_idmap_vector;
 
+#define pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
+
 #define kvm_pmd_huge(_x)	(pmd_huge(_x) || pmd_trans_huge(_x))
 
 static void kvm_tlb_flush_vmid_ipa(struct kvm *kvm, phys_addr_t ipa)
@@ -293,14 +295,14 @@ void free_boot_hyp_pgd(void)
 	if (boot_hyp_pgd) {
 		unmap_range(NULL, boot_hyp_pgd, hyp_idmap_start, PAGE_SIZE);
 		unmap_range(NULL, boot_hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
-		kfree(boot_hyp_pgd);
+		free_pages((unsigned long)boot_hyp_pgd, pgd_order);
 		boot_hyp_pgd = NULL;
 	}
 
 	if (hyp_pgd)
 		unmap_range(NULL, hyp_pgd, TRAMPOLINE_VA, PAGE_SIZE);
 
-	kfree(init_bounce_page);
+	free_page((unsigned long)init_bounce_page);
 	init_bounce_page = NULL;
 
 	mutex_unlock(&kvm_hyp_pgd_mutex);
@@ -330,7 +332,7 @@ void free_hyp_pgds(void)
 		for (addr = VMALLOC_START; is_vmalloc_addr((void*)addr); addr += PGDIR_SIZE)
 			unmap_range(NULL, hyp_pgd, KERN_TO_HYP(addr), PGDIR_SIZE);
 
-		kfree(hyp_pgd);
+		free_pages((unsigned long)hyp_pgd, pgd_order);
 		hyp_pgd = NULL;
 	}
 
@@ -1024,7 +1026,7 @@ int kvm_mmu_init(void)
 		size_t len = __hyp_idmap_text_end - __hyp_idmap_text_start;
 		phys_addr_t phys_base;
 
-		init_bounce_page = kmalloc(PAGE_SIZE, GFP_KERNEL);
+		init_bounce_page = (void *)__get_free_page(GFP_KERNEL);
 		if (!init_bounce_page) {
 			kvm_err("Couldn't allocate HYP init bounce page\n");
 			err = -ENOMEM;
@@ -1050,8 +1052,9 @@ int kvm_mmu_init(void)
 			 (unsigned long)phys_base);
 	}
 
-	hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
-	boot_hyp_pgd = kzalloc(PTRS_PER_PGD * sizeof(pgd_t), GFP_KERNEL);
+	hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
+	boot_hyp_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, pgd_order);
+
 	if (!hyp_pgd || !boot_hyp_pgd) {
 		kvm_err("Hyp mode PGD not allocated\n");
 		err = -ENOMEM;
diff --git a/arch/arm64/boot/dts/apm-storm.dtsi b/arch/arm64/boot/dts/apm-storm.dtsi
index 93f4b2d..f8c40a6 100644
--- a/arch/arm64/boot/dts/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm-storm.dtsi
@@ -307,6 +307,7 @@
 			      <0x0 0x1f21e000 0x0 0x1000>,
 			      <0x0 0x1f217000 0x0 0x1000>;
 			interrupts = <0x0 0x86 0x4>;
+			dma-coherent;
 			status = "disabled";
 			clocks = <&sata01clk 0>;
 			phys = <&phy1 0>;
@@ -321,6 +322,7 @@
 			      <0x0 0x1f22e000 0x0 0x1000>,
 			      <0x0 0x1f227000 0x0 0x1000>;
 			interrupts = <0x0 0x87 0x4>;
+			dma-coherent;
 			status = "ok";
 			clocks = <&sata23clk 0>;
 			phys = <&phy2 0>;
@@ -334,6 +336,7 @@
 			      <0x0 0x1f23d000 0x0 0x1000>,
 			      <0x0 0x1f23e000 0x0 0x1000>;
 			interrupts = <0x0 0x88 0x4>;
+			dma-coherent;
 			status = "ok";
 			clocks = <&sata45clk 0>;
 			phys = <&phy3 0>;
diff --git a/arch/arm64/kernel/early_printk.c b/arch/arm64/kernel/early_printk.c
index ffbbdde..2dc36d0 100644
--- a/arch/arm64/kernel/early_printk.c
+++ b/arch/arm64/kernel/early_printk.c
@@ -143,10 +143,8 @@ static int __init setup_early_printk(char *buf)
 	}
 	/* no options parsing yet */
 
-	if (paddr) {
-		set_fixmap_io(FIX_EARLYCON_MEM_BASE, paddr);
-		early_base = (void __iomem *)fix_to_virt(FIX_EARLYCON_MEM_BASE);
-	}
+	if (paddr)
+		early_base = (void __iomem *)set_fixmap_offset_io(FIX_EARLYCON_MEM_BASE, paddr);
 
 	printch = match->printch;
 	early_console = &early_console_dev;
diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 93e7df89..7ec7846 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -396,7 +396,7 @@ static int __init arm64_device_init(void)
 	of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL);
 	return 0;
 }
-arch_initcall(arm64_device_init);
+arch_initcall_sync(arm64_device_init);
 
 static DEFINE_PER_CPU(struct cpu, cpu_data);
 
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 0ba347e..c851eb4 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -22,8 +22,11 @@
 #include <linux/slab.h>
 #include <linux/dma-mapping.h>
 #include <linux/dma-contiguous.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
 #include <linux/vmalloc.h>
 #include <linux/swiotlb.h>
+#include <linux/amba/bus.h>
 
 #include <asm/cacheflush.h>
 
@@ -305,17 +308,45 @@ struct dma_map_ops coherent_swiotlb_dma_ops = {
 };
 EXPORT_SYMBOL(coherent_swiotlb_dma_ops);
 
+static int dma_bus_notifier(struct notifier_block *nb,
+			    unsigned long event, void *_dev)
+{
+	struct device *dev = _dev;
+
+	if (event != BUS_NOTIFY_ADD_DEVICE)
+		return NOTIFY_DONE;
+
+	if (of_property_read_bool(dev->of_node, "dma-coherent"))
+		set_dma_ops(dev, &coherent_swiotlb_dma_ops);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block platform_bus_nb = {
+	.notifier_call = dma_bus_notifier,
+};
+
+static struct notifier_block amba_bus_nb = {
+	.notifier_call = dma_bus_notifier,
+};
+
 extern int swiotlb_late_init_with_default_size(size_t default_size);
 
 static int __init swiotlb_late_init(void)
 {
 	size_t swiotlb_size = min(SZ_64M, MAX_ORDER_NR_PAGES << PAGE_SHIFT);
 
-	dma_ops = &coherent_swiotlb_dma_ops;
+	/*
+	 * These must be registered before of_platform_populate().
+	 */
+	bus_register_notifier(&platform_bus_type, &platform_bus_nb);
+	bus_register_notifier(&amba_bustype, &amba_bus_nb);
+
+	dma_ops = &noncoherent_swiotlb_dma_ops;
 
 	return swiotlb_late_init_with_default_size(swiotlb_size);
 }
-subsys_initcall(swiotlb_late_init);
+arch_initcall(swiotlb_late_init);
 
 #define PREALLOC_DMA_DEBUG_ENTRIES	4096
 
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 6b7e895..0a472c4 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -374,6 +374,9 @@ int kern_addr_valid(unsigned long addr)
 	if (pmd_none(*pmd))
 		return 0;
 
+	if (pmd_sect(*pmd))
+		return pfn_valid(pmd_pfn(*pmd));
+
 	pte = pte_offset_kernel(pmd, addr);
 	if (pte_none(*pte))
 		return 0;
diff --git a/arch/hexagon/include/asm/barrier.h b/arch/hexagon/include/asm/barrier.h
deleted file mode 100644
index 4e863da..0000000
--- a/arch/hexagon/include/asm/barrier.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- * Memory barrier definitions for the Hexagon architecture
- *
- * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA.
- */
-
-#ifndef _ASM_BARRIER_H
-#define _ASM_BARRIER_H
-
-#define rmb()				barrier()
-#define read_barrier_depends()		barrier()
-#define wmb()				barrier()
-#define mb()				barrier()
-#define smp_rmb()			barrier()
-#define smp_read_barrier_depends()	barrier()
-#define smp_wmb()			barrier()
-#define smp_mb()			barrier()
-
-/*  Set a value and use a memory barrier.  Used by the scheduler somewhere.  */
-#define set_mb(var, value) \
-	do { var = value; mb(); } while (0)
-
-#endif /* _ASM_BARRIER_H */
diff --git a/arch/parisc/include/uapi/asm/Kbuild b/arch/parisc/include/uapi/asm/Kbuild
index a580642..348356c 100644
--- a/arch/parisc/include/uapi/asm/Kbuild
+++ b/arch/parisc/include/uapi/asm/Kbuild
@@ -1,6 +1,8 @@
 # UAPI Header export list
 include include/uapi/asm-generic/Kbuild.asm
 
+generic-y += resource.h
+
 header-y += bitsperlong.h
 header-y += byteorder.h
 header-y += errno.h
@@ -13,7 +15,6 @@ header-y += msgbuf.h
 header-y += pdc.h
 header-y += posix_types.h
 header-y += ptrace.h
-header-y += resource.h
 header-y += sembuf.h
 header-y += setup.h
 header-y += shmbuf.h
diff --git a/arch/parisc/include/uapi/asm/resource.h b/arch/parisc/include/uapi/asm/resource.h
deleted file mode 100644
index 8b06343..0000000
--- a/arch/parisc/include/uapi/asm/resource.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef _ASM_PARISC_RESOURCE_H
-#define _ASM_PARISC_RESOURCE_H
-
-#define _STK_LIM_MAX	10 * _STK_LIM
-#include <asm-generic/resource.h>
-
-#endif
diff --git a/arch/powerpc/boot/main.c b/arch/powerpc/boot/main.c
index a28f021..d367a0a 100644
--- a/arch/powerpc/boot/main.c
+++ b/arch/powerpc/boot/main.c
@@ -139,18 +139,18 @@ static struct addr_range prep_initrd(struct addr_range vmlinux, void *chosen,
  * edit the command line passed to vmlinux (by setting /chosen/bootargs).
  * The buffer is put in it's own section so that tools may locate it easier.
  */
-static char cmdline[COMMAND_LINE_SIZE]
+static char cmdline[BOOT_COMMAND_LINE_SIZE]
 	__attribute__((__section__("__builtin_cmdline")));
 
 static void prep_cmdline(void *chosen)
 {
 	if (cmdline[0] == '\0')
-		getprop(chosen, "bootargs", cmdline, COMMAND_LINE_SIZE-1);
+		getprop(chosen, "bootargs", cmdline, BOOT_COMMAND_LINE_SIZE-1);
 
 	printf("\n\rLinux/PowerPC load: %s", cmdline);
 	/* If possible, edit the command line */
 	if (console_ops.edit_cmdline)
-		console_ops.edit_cmdline(cmdline, COMMAND_LINE_SIZE);
+		console_ops.edit_cmdline(cmdline, BOOT_COMMAND_LINE_SIZE);
 	printf("\n\r");
 
 	/* Put the command line back into the devtree for the kernel */
@@ -174,7 +174,7 @@ void start(void)
 	 * built-in command line wasn't set by an external tool */
 	if ((loader_info.cmdline_len > 0) && (cmdline[0] == '\0'))
 		memmove(cmdline, loader_info.cmdline,
-			min(loader_info.cmdline_len, COMMAND_LINE_SIZE-1));
+			min(loader_info.cmdline_len, BOOT_COMMAND_LINE_SIZE-1));
 
 	if (console_ops.open && (console_ops.open() < 0))
 		exit();
diff --git a/arch/powerpc/boot/ops.h b/arch/powerpc/boot/ops.h
index b3218ce..8aad3c5 100644
--- a/arch/powerpc/boot/ops.h
+++ b/arch/powerpc/boot/ops.h
@@ -15,7 +15,7 @@
 #include "types.h"
 #include "string.h"
 
-#define	COMMAND_LINE_SIZE	512
+#define	BOOT_COMMAND_LINE_SIZE	2048
 #define	MAX_PATH_LEN		256
 #define	MAX_PROP_LEN		256 /* What should this be? */
 
diff --git a/arch/powerpc/boot/ps3.c b/arch/powerpc/boot/ps3.c
index 9954d98..4ec2d86 100644
--- a/arch/powerpc/boot/ps3.c
+++ b/arch/powerpc/boot/ps3.c
@@ -47,13 +47,13 @@ BSS_STACK(4096);
  * The buffer is put in it's own section so that tools may locate it easier.
  */
 
-static char cmdline[COMMAND_LINE_SIZE]
+static char cmdline[BOOT_COMMAND_LINE_SIZE]
 	__attribute__((__section__("__builtin_cmdline")));
 
 static void prep_cmdline(void *chosen)
 {
 	if (cmdline[0] == '\0')
-		getprop(chosen, "bootargs", cmdline, COMMAND_LINE_SIZE-1);
+		getprop(chosen, "bootargs", cmdline, BOOT_COMMAND_LINE_SIZE-1);
 	else
 		setprop_str(chosen, "bootargs", cmdline);
 
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index a2efdaa..66ad7a7 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -41,14 +41,14 @@ struct opal_takeover_args {
  * size except the last one in the list to be as well.
  */
 struct opal_sg_entry {
-	void    *data;
-	long    length;
+	__be64 data;
+	__be64 length;
 };
 
-/* sg list */
+/* SG list */
 struct opal_sg_list {
-	unsigned long num_entries;
-	struct opal_sg_list *next;
+	__be64 length;
+	__be64 next;
 	struct opal_sg_entry entry[];
 };
 
@@ -858,8 +858,8 @@ int64_t opal_lpc_write(uint32_t chip_id, enum OpalLPCAddressType addr_type,
 int64_t opal_lpc_read(uint32_t chip_id, enum OpalLPCAddressType addr_type,
 		      uint32_t addr, __be32 *data, uint32_t sz);
 
-int64_t opal_read_elog(uint64_t buffer, size_t size, uint64_t log_id);
-int64_t opal_get_elog_size(uint64_t *log_id, size_t *size, uint64_t *elog_type);
+int64_t opal_read_elog(uint64_t buffer, uint64_t size, uint64_t log_id);
+int64_t opal_get_elog_size(__be64 *log_id, __be64 *size, __be64 *elog_type);
 int64_t opal_write_elog(uint64_t buffer, uint64_t size, uint64_t offset);
 int64_t opal_send_ack_elog(uint64_t log_id);
 void opal_resend_pending_logs(void);
@@ -868,23 +868,24 @@ int64_t opal_validate_flash(uint64_t buffer, uint32_t *size, uint32_t *result);
 int64_t opal_manage_flash(uint8_t op);
 int64_t opal_update_flash(uint64_t blk_list);
 int64_t opal_dump_init(uint8_t dump_type);
-int64_t opal_dump_info(uint32_t *dump_id, uint32_t *dump_size);
-int64_t opal_dump_info2(uint32_t *dump_id, uint32_t *dump_size, uint32_t *dump_type);
+int64_t opal_dump_info(__be32 *dump_id, __be32 *dump_size);
+int64_t opal_dump_info2(__be32 *dump_id, __be32 *dump_size, __be32 *dump_type);
 int64_t opal_dump_read(uint32_t dump_id, uint64_t buffer);
 int64_t opal_dump_ack(uint32_t dump_id);
 int64_t opal_dump_resend_notification(void);
 
-int64_t opal_get_msg(uint64_t buffer, size_t size);
-int64_t opal_check_completion(uint64_t buffer, size_t size, uint64_t token);
+int64_t opal_get_msg(uint64_t buffer, uint64_t size);
+int64_t opal_check_completion(uint64_t buffer, uint64_t size, uint64_t token);
 int64_t opal_sync_host_reboot(void);
 int64_t opal_get_param(uint64_t token, uint32_t param_id, uint64_t buffer,
-		size_t length);
+		uint64_t length);
 int64_t opal_set_param(uint64_t token, uint32_t param_id, uint64_t buffer,
-		size_t length);
+		uint64_t length);
 int64_t opal_sensor_read(uint32_t sensor_hndl, int token, __be32 *sensor_data);
 
 /* Internal functions */
-extern int early_init_dt_scan_opal(unsigned long node, const char *uname, int depth, void *data);
+extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
+				   int depth, void *data);
 extern int early_init_dt_scan_recoverable_ranges(unsigned long node,
 				 const char *uname, int depth, void *data);
 
@@ -893,10 +894,6 @@ extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);
 
 extern void hvc_opal_init_early(void);
 
-/* Internal functions */
-extern int early_init_dt_scan_opal(unsigned long node, const char *uname,
-				   int depth, void *data);
-
 extern int opal_notifier_register(struct notifier_block *nb);
 extern int opal_notifier_unregister(struct notifier_block *nb);
 
@@ -906,9 +903,6 @@ extern void opal_notifier_enable(void);
 extern void opal_notifier_disable(void);
 extern void opal_notifier_update_evt(uint64_t evt_mask, uint64_t evt_val);
 
-extern int opal_get_chars(uint32_t vtermno, char *buf, int count);
-extern int opal_put_chars(uint32_t vtermno, const char *buf, int total_len);
-
 extern int __opal_async_get_token(void);
 extern int opal_async_get_token_interruptible(void);
 extern int __opal_async_release_token(int token);
@@ -916,8 +910,6 @@ extern int opal_async_release_token(int token);
 extern int opal_async_wait_response(uint64_t token, struct opal_msg *msg);
 extern int opal_get_sensor_data(u32 sensor_hndl, u32 *sensor_data);
 
-extern void hvc_opal_init_early(void);
-
 struct rtc_time;
 extern int opal_set_rtc_time(struct rtc_time *tm);
 extern void opal_get_rtc_time(struct rtc_time *tm);
@@ -937,6 +929,10 @@ extern int opal_resync_timebase(void);
 
 extern void opal_lpc_init(void);
 
+struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr,
+					     unsigned long vmalloc_size);
+void opal_free_sg_list(struct opal_sg_list *sg);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __OPAL_H */
diff --git a/arch/powerpc/include/uapi/asm/setup.h b/arch/powerpc/include/uapi/asm/setup.h
index 552df83..ae3fb68 100644
--- a/arch/powerpc/include/uapi/asm/setup.h
+++ b/arch/powerpc/include/uapi/asm/setup.h
@@ -1 +1,6 @@
-#include <asm-generic/setup.h>
+#ifndef _UAPI_ASM_POWERPC_SETUP_H
+#define _UAPI_ASM_POWERPC_SETUP_H
+
+#define COMMAND_LINE_SIZE	2048
+
+#endif /* _UAPI_ASM_POWERPC_SETUP_H */
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 3bd77ed..450850a 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -120,6 +120,7 @@ EXPORT_SYMBOL(giveup_spe);
 EXPORT_SYMBOL(flush_instruction_cache);
 #endif
 EXPORT_SYMBOL(flush_dcache_range);
+EXPORT_SYMBOL(flush_icache_range);
 
 #ifdef CONFIG_SMP
 #ifdef CONFIG_PPC32
diff --git a/arch/powerpc/kernel/rtas_flash.c b/arch/powerpc/kernel/rtas_flash.c
index 2f3cdb0..658e89d 100644
--- a/arch/powerpc/kernel/rtas_flash.c
+++ b/arch/powerpc/kernel/rtas_flash.c
@@ -705,7 +705,7 @@ static int __init rtas_flash_init(void)
 	if (rtas_token("ibm,update-flash-64-and-reboot") ==
 		       RTAS_UNKNOWN_SERVICE) {
 		pr_info("rtas_flash: no firmware flash support\n");
-		return 1;
+		return -EINVAL;
 	}
 
 	rtas_validate_flash_data.buf = kzalloc(VALIDATE_BUF_SIZE, GFP_KERNEL);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index ffbb871..b031f93 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -242,6 +242,12 @@ kvm_novcpu_exit:
  */
 	.globl	kvm_start_guest
 kvm_start_guest:
+
+	/* Set runlatch bit the minute you wake up from nap */
+	mfspr	r1, SPRN_CTRLF
+	ori 	r1, r1, 1
+	mtspr	SPRN_CTRLT, r1
+
 	ld	r2,PACATOC(r13)
 
 	li	r0,KVM_HWTHREAD_IN_KVM
@@ -309,6 +315,11 @@ kvm_no_guest:
 	li	r0, KVM_HWTHREAD_IN_NAP
 	stb	r0, HSTATE_HWTHREAD_STATE(r13)
 kvm_do_nap:
+	/* Clear the runlatch bit before napping */
+	mfspr	r2, SPRN_CTRLF
+	clrrdi	r2, r2, 1
+	mtspr	SPRN_CTRLT, r2
+
 	li	r3, LPCR_PECE0
 	mfspr	r4, SPRN_LPCR
 	rlwimi	r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
@@ -1999,8 +2010,13 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
 
 	/*
 	 * Take a nap until a decrementer or external or doobell interrupt
-	 * occurs, with PECE1, PECE0 and PECEDP set in LPCR
+	 * occurs, with PECE1, PECE0 and PECEDP set in LPCR. Also clear the
+	 * runlatch bit before napping.
 	 */
+	mfspr	r2, SPRN_CTRLF
+	clrrdi	r2, r2, 1
+	mtspr	SPRN_CTRLT, r2
+
 	li	r0,1
 	stb	r0,HSTATE_HWTHREAD_REQ(r13)
 	mfspr	r5,SPRN_LPCR
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 3ea26c2..cf1d325 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -82,17 +82,14 @@ static inline void __tlbie(unsigned long vpn, int psize, int apsize, int ssize)
 		va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1);
 		va |= penc << 12;
 		va |= ssize << 8;
-		/* Add AVAL part */
-		if (psize != apsize) {
-			/*
-			 * MPSS, 64K base page size and 16MB parge page size
-			 * We don't need all the bits, but rest of the bits
-			 * must be ignored by the processor.
-			 * vpn cover upto 65 bits of va. (0...65) and we need
-			 * 58..64 bits of va.
-			 */
-			va |= (vpn & 0xfe);
-		}
+		/*
+		 * AVAL bits:
+		 * We don't need all the bits, but rest of the bits
+		 * must be ignored by the processor.
+		 * vpn cover upto 65 bits of va. (0...65) and we need
+		 * 58..64 bits of va.
+		 */
+		va |= (vpn & 0xfe); /* AVAL */
 		va |= 1; /* L */
 		asm volatile(ASM_FTR_IFCLR("tlbie %0,1", PPC_TLBIE(%1,%0), %2)
 			     : : "r" (va), "r"(0), "i" (CPU_FTR_ARCH_206)
@@ -133,17 +130,14 @@ static inline void __tlbiel(unsigned long vpn, int psize, int apsize, int ssize)
 		va &= ~((1ul << mmu_psize_defs[apsize].shift) - 1);
 		va |= penc << 12;
 		va |= ssize << 8;
-		/* Add AVAL part */
-		if (psize != apsize) {
-			/*
-			 * MPSS, 64K base page size and 16MB parge page size
-			 * We don't need all the bits, but rest of the bits
-			 * must be ignored by the processor.
-			 * vpn cover upto 65 bits of va. (0...65) and we need
-			 * 58..64 bits of va.
-			 */
-			va |= (vpn & 0xfe);
-		}
+		/*
+		 * AVAL bits:
+		 * We don't need all the bits, but rest of the bits
+		 * must be ignored by the processor.
+		 * vpn cover upto 65 bits of va. (0...65) and we need
+		 * 58..64 bits of va.
+		 */
+		va |= (vpn & 0xfe);
 		va |= 1; /* L */
 		asm volatile(".long 0x7c000224 | (%0 << 11) | (1 << 21)"
 			     : : "r"(va) : "memory");
diff --git a/arch/powerpc/perf/hv-24x7.c b/arch/powerpc/perf/hv-24x7.c
index 297c9105..e0766b8 100644
--- a/arch/powerpc/perf/hv-24x7.c
+++ b/arch/powerpc/perf/hv-24x7.c
@@ -155,16 +155,28 @@ static ssize_t read_offset_data(void *dest, size_t dest_len,
 	return copy_len;
 }
 
-static unsigned long h_get_24x7_catalog_page(char page[static 4096],
-					     u32 version, u32 index)
+static unsigned long h_get_24x7_catalog_page_(unsigned long phys_4096,
+					      unsigned long version,
+					      unsigned long index)
 {
-	WARN_ON(!IS_ALIGNED((unsigned long)page, 4096));
+	pr_devel("h_get_24x7_catalog_page(0x%lx, %lu, %lu)",
+			phys_4096,
+			version,
+			index);
+	WARN_ON(!IS_ALIGNED(phys_4096, 4096));
 	return plpar_hcall_norets(H_GET_24X7_CATALOG_PAGE,
-			virt_to_phys(page),
+			phys_4096,
 			version,
 			index);
 }
 
+static unsigned long h_get_24x7_catalog_page(char page[],
+					     u64 version, u32 index)
+{
+	return h_get_24x7_catalog_page_(virt_to_phys(page),
+					version, index);
+}
+
 static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
 			    struct bin_attribute *bin_attr, char *buf,
 			    loff_t offset, size_t count)
@@ -173,7 +185,7 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
 	ssize_t ret = 0;
 	size_t catalog_len = 0, catalog_page_len = 0, page_count = 0;
 	loff_t page_offset = 0;
-	uint32_t catalog_version_num = 0;
+	uint64_t catalog_version_num = 0;
 	void *page = kmem_cache_alloc(hv_page_cache, GFP_USER);
 	struct hv_24x7_catalog_page_0 *page_0 = page;
 	if (!page)
@@ -185,7 +197,7 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
 		goto e_free;
 	}
 
-	catalog_version_num = be32_to_cpu(page_0->version);
+	catalog_version_num = be64_to_cpu(page_0->version);
 	catalog_page_len = be32_to_cpu(page_0->length);
 	catalog_len = catalog_page_len * 4096;
 
@@ -208,8 +220,9 @@ static ssize_t catalog_read(struct file *filp, struct kobject *kobj,
 				page, 4096, page_offset * 4096);
 e_free:
 	if (hret)
-		pr_err("h_get_24x7_catalog_page(ver=%d, page=%lld) failed: rc=%ld\n",
-				catalog_version_num, page_offset, hret);
+		pr_err("h_get_24x7_catalog_page(ver=%lld, page=%lld) failed:"
+		       " rc=%ld\n",
+		       catalog_version_num, page_offset, hret);
 	kfree(page);
 
 	pr_devel("catalog_read: offset=%lld(%lld) count=%zu(%zu) catalog_len=%zu(%zu) => %zd\n",
@@ -243,7 +256,7 @@ e_free:								\
 static DEVICE_ATTR_RO(_name)
 
 PAGE_0_ATTR(catalog_version, "%lld\n",
-		(unsigned long long)be32_to_cpu(page_0->version));
+		(unsigned long long)be64_to_cpu(page_0->version));
 PAGE_0_ATTR(catalog_len, "%lld\n",
 		(unsigned long long)be32_to_cpu(page_0->length) * 4096);
 static BIN_ATTR_RO(catalog, 0/* real length varies */);
@@ -485,13 +498,13 @@ static int hv_24x7_init(void)
 	struct hv_perf_caps caps;
 
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
-		pr_info("not a virtualized system, not enabling\n");
+		pr_debug("not a virtualized system, not enabling\n");
 		return -ENODEV;
 	}
 
 	hret = hv_perf_caps_get(&caps);
 	if (hret) {
-		pr_info("could not obtain capabilities, error 0x%80lx, not enabling\n",
+		pr_debug("could not obtain capabilities, not enabling, rc=%ld\n",
 				hret);
 		return -ENODEV;
 	}
diff --git a/arch/powerpc/perf/hv-gpci.c b/arch/powerpc/perf/hv-gpci.c
index 278ba7b..c9d399a 100644
--- a/arch/powerpc/perf/hv-gpci.c
+++ b/arch/powerpc/perf/hv-gpci.c
@@ -78,7 +78,7 @@ static ssize_t kernel_version_show(struct device *dev,
 	return sprintf(page, "0x%x\n", COUNTER_INFO_VERSION_CURRENT);
 }
 
-DEVICE_ATTR_RO(kernel_version);
+static DEVICE_ATTR_RO(kernel_version);
 HV_CAPS_ATTR(version, "0x%x\n");
 HV_CAPS_ATTR(ga, "%d\n");
 HV_CAPS_ATTR(expanded, "%d\n");
@@ -273,13 +273,13 @@ static int hv_gpci_init(void)
 	struct hv_perf_caps caps;
 
 	if (!firmware_has_feature(FW_FEATURE_LPAR)) {
-		pr_info("not a virtualized system, not enabling\n");
+		pr_debug("not a virtualized system, not enabling\n");
 		return -ENODEV;
 	}
 
 	hret = hv_perf_caps_get(&caps);
 	if (hret) {
-		pr_info("could not obtain capabilities, error 0x%80lx, not enabling\n",
+		pr_debug("could not obtain capabilities, not enabling, rc=%ld\n",
 				hret);
 		return -ENODEV;
 	}
diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index b9827b0..788a197 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -209,89 +209,20 @@ static struct kobj_type dump_ktype = {
 	.default_attrs = dump_default_attrs,
 };
 
-static void free_dump_sg_list(struct opal_sg_list *list)
-{
-	struct opal_sg_list *sg1;
-	while (list) {
-		sg1 = list->next;
-		kfree(list);
-		list = sg1;
-	}
-	list = NULL;
-}
-
-static struct opal_sg_list *dump_data_to_sglist(struct dump_obj *dump)
-{
-	struct opal_sg_list *sg1, *list = NULL;
-	void *addr;
-	int64_t size;
-
-	addr = dump->buffer;
-	size = dump->size;
-
-	sg1 = kzalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!sg1)
-		goto nomem;
-
-	list = sg1;
-	sg1->num_entries = 0;
-	while (size > 0) {
-		/* Translate virtual address to physical address */
-		sg1->entry[sg1->num_entries].data =
-			(void *)(vmalloc_to_pfn(addr) << PAGE_SHIFT);
-
-		if (size > PAGE_SIZE)
-			sg1->entry[sg1->num_entries].length = PAGE_SIZE;
-		else
-			sg1->entry[sg1->num_entries].length = size;
-
-		sg1->num_entries++;
-		if (sg1->num_entries >= SG_ENTRIES_PER_NODE) {
-			sg1->next = kzalloc(PAGE_SIZE, GFP_KERNEL);
-			if (!sg1->next)
-				goto nomem;
-
-			sg1 = sg1->next;
-			sg1->num_entries = 0;
-		}
-		addr += PAGE_SIZE;
-		size -= PAGE_SIZE;
-	}
-	return list;
-
-nomem:
-	pr_err("%s : Failed to allocate memory\n", __func__);
-	free_dump_sg_list(list);
-	return NULL;
-}
-
-static void sglist_to_phy_addr(struct opal_sg_list *list)
-{
-	struct opal_sg_list *sg, *next;
-
-	for (sg = list; sg; sg = next) {
-		next = sg->next;
-		/* Don't translate NULL pointer for last entry */
-		if (sg->next)
-			sg->next = (struct opal_sg_list *)__pa(sg->next);
-		else
-			sg->next = NULL;
-
-		/* Convert num_entries to length */
-		sg->num_entries =
-			sg->num_entries * sizeof(struct opal_sg_entry) + 16;
-	}
-}
-
-static int64_t dump_read_info(uint32_t *id, uint32_t *size, uint32_t *type)
+static int64_t dump_read_info(uint32_t *dump_id, uint32_t *dump_size, uint32_t *dump_type)
 {
+	__be32 id, size, type;
 	int rc;
-	*type = 0xffffffff;
 
-	rc = opal_dump_info2(id, size, type);
+	type = cpu_to_be32(0xffffffff);
 
+	rc = opal_dump_info2(&id, &size, &type);
 	if (rc == OPAL_PARAMETER)
-		rc = opal_dump_info(id, size);
+		rc = opal_dump_info(&id, &size);
+
+	*dump_id = be32_to_cpu(id);
+	*dump_size = be32_to_cpu(size);
+	*dump_type = be32_to_cpu(type);
 
 	if (rc)
 		pr_warn("%s: Failed to get dump info (%d)\n",
@@ -314,15 +245,12 @@ static int64_t dump_read_data(struct dump_obj *dump)
 	}
 
 	/* Generate SG list */
-	list = dump_data_to_sglist(dump);
+	list = opal_vmalloc_to_sg_list(dump->buffer, dump->size);
 	if (!list) {
 		rc = -ENOMEM;
 		goto out;
 	}
 
-	/* Translate sg list addr to real address */
-	sglist_to_phy_addr(list);
-
 	/* First entry address */
 	addr = __pa(list);
 
@@ -341,7 +269,7 @@ static int64_t dump_read_data(struct dump_obj *dump)
 			__func__, dump->id);
 
 	/* Free SG list */
-	free_dump_sg_list(list);
+	opal_free_sg_list(list);
 
 out:
 	return rc;
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index ef7bc2a..10268c4 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -238,18 +238,25 @@ static struct elog_obj *create_elog_obj(uint64_t id, size_t size, uint64_t type)
 
 static void elog_work_fn(struct work_struct *work)
 {
-	size_t elog_size;
+	__be64 size;
+	__be64 id;
+	__be64 type;
+	uint64_t elog_size;
 	uint64_t log_id;
 	uint64_t elog_type;
 	int rc;
 	char name[2+16+1];
 
-	rc = opal_get_elog_size(&log_id, &elog_size, &elog_type);
+	rc = opal_get_elog_size(&id, &size, &type);
 	if (rc != OPAL_SUCCESS) {
 		pr_err("ELOG: Opal log read failed\n");
 		return;
 	}
 
+	elog_size = be64_to_cpu(size);
+	log_id = be64_to_cpu(id);
+	elog_type = be64_to_cpu(type);
+
 	BUG_ON(elog_size > OPAL_MAX_ERRLOG_SIZE);
 
 	if (elog_size >= OPAL_MAX_ERRLOG_SIZE)
diff --git a/arch/powerpc/platforms/powernv/opal-flash.c b/arch/powerpc/platforms/powernv/opal-flash.c
index 714ef97..dc487ff 100644
--- a/arch/powerpc/platforms/powernv/opal-flash.c
+++ b/arch/powerpc/platforms/powernv/opal-flash.c
@@ -79,9 +79,6 @@
 /* XXX: Assume candidate image size is <= 1GB */
 #define MAX_IMAGE_SIZE	0x40000000
 
-/* Flash sg list version */
-#define SG_LIST_VERSION (1UL)
-
 /* Image status */
 enum {
 	IMAGE_INVALID,
@@ -131,11 +128,15 @@ static DEFINE_MUTEX(image_data_mutex);
  */
 static inline void opal_flash_validate(void)
 {
-	struct validate_flash_t *args_buf = &validate_flash_data;
+	long ret;
+	void *buf = validate_flash_data.buf;
+	__be32 size, result;
 
-	args_buf->status = opal_validate_flash(__pa(args_buf->buf),
-					       &(args_buf->buf_size),
-					       &(args_buf->result));
+	ret = opal_validate_flash(__pa(buf), &size, &result);
+
+	validate_flash_data.status = ret;
+	validate_flash_data.buf_size = be32_to_cpu(size);
+	validate_flash_data.result = be32_to_cpu(result);
 }
 
 /*
@@ -268,93 +269,11 @@ static ssize_t manage_store(struct kobject *kobj,
 }
 
 /*
- * Free sg list
- */
-static void free_sg_list(struct opal_sg_list *list)
-{
-	struct opal_sg_list *sg1;
-	while (list) {
-		sg1 = list->next;
-		kfree(list);
-		list = sg1;
-	}
-	list = NULL;
-}
-
-/*
- * Build candidate image scatter gather list
- *
- * list format:
- *   -----------------------------------
- *  |  VER (8) | Entry length in bytes  |
- *   -----------------------------------
- *  |  Pointer to next entry            |
- *   -----------------------------------
- *  |  Address of memory area 1         |
- *   -----------------------------------
- *  |  Length of memory area 1          |
- *   -----------------------------------
- *  |   .........                       |
- *   -----------------------------------
- *  |   .........                       |
- *   -----------------------------------
- *  |  Address of memory area N         |
- *   -----------------------------------
- *  |  Length of memory area N          |
- *   -----------------------------------
- */
-static struct opal_sg_list *image_data_to_sglist(void)
-{
-	struct opal_sg_list *sg1, *list = NULL;
-	void *addr;
-	int size;
-
-	addr = image_data.data;
-	size = image_data.size;
-
-	sg1 = kzalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!sg1)
-		return NULL;
-
-	list = sg1;
-	sg1->num_entries = 0;
-	while (size > 0) {
-		/* Translate virtual address to physical address */
-		sg1->entry[sg1->num_entries].data =
-			(void *)(vmalloc_to_pfn(addr) << PAGE_SHIFT);
-
-		if (size > PAGE_SIZE)
-			sg1->entry[sg1->num_entries].length = PAGE_SIZE;
-		else
-			sg1->entry[sg1->num_entries].length = size;
-
-		sg1->num_entries++;
-		if (sg1->num_entries >= SG_ENTRIES_PER_NODE) {
-			sg1->next = kzalloc(PAGE_SIZE, GFP_KERNEL);
-			if (!sg1->next) {
-				pr_err("%s : Failed to allocate memory\n",
-				       __func__);
-				goto nomem;
-			}
-
-			sg1 = sg1->next;
-			sg1->num_entries = 0;
-		}
-		addr += PAGE_SIZE;
-		size -= PAGE_SIZE;
-	}
-	return list;
-nomem:
-	free_sg_list(list);
-	return NULL;
-}
-
-/*
  * OPAL update flash
  */
 static int opal_flash_update(int op)
 {
-	struct opal_sg_list *sg, *list, *next;
+	struct opal_sg_list *list;
 	unsigned long addr;
 	int64_t rc = OPAL_PARAMETER;
 
@@ -364,30 +283,13 @@ static int opal_flash_update(int op)
 		goto flash;
 	}
 
-	list = image_data_to_sglist();
+	list = opal_vmalloc_to_sg_list(image_data.data, image_data.size);
 	if (!list)
 		goto invalid_img;
 
 	/* First entry address */
 	addr = __pa(list);
 
-	/* Translate sg list address to absolute */
-	for (sg = list; sg; sg = next) {
-		next = sg->next;
-		/* Don't translate NULL pointer for last entry */
-		if (sg->next)
-			sg->next = (struct opal_sg_list *)__pa(sg->next);
-		else
-			sg->next = NULL;
-
-		/*
-		 * Convert num_entries to version/length format
-		 * to satisfy OPAL.
-		 */
-		sg->num_entries = (SG_LIST_VERSION << 56) |
-			(sg->num_entries * sizeof(struct opal_sg_entry) + 16);
-	}
-
 	pr_alert("FLASH: Image is %u bytes\n", image_data.size);
 	pr_alert("FLASH: Image update requested\n");
 	pr_alert("FLASH: Image will be updated during system reboot\n");
diff --git a/arch/powerpc/platforms/powernv/opal-sysparam.c b/arch/powerpc/platforms/powernv/opal-sysparam.c
index 6b61472..d202f9b 100644
--- a/arch/powerpc/platforms/powernv/opal-sysparam.c
+++ b/arch/powerpc/platforms/powernv/opal-sysparam.c
@@ -39,10 +39,11 @@ struct param_attr {
 	struct kobj_attribute kobj_attr;
 };
 
-static int opal_get_sys_param(u32 param_id, u32 length, void *buffer)
+static ssize_t opal_get_sys_param(u32 param_id, u32 length, void *buffer)
 {
 	struct opal_msg msg;
-	int ret, token;
+	ssize_t ret;
+	int token;
 
 	token = opal_async_get_token_interruptible();
 	if (token < 0) {
@@ -59,7 +60,7 @@ static int opal_get_sys_param(u32 param_id, u32 length, void *buffer)
 
 	ret = opal_async_wait_response(token, &msg);
 	if (ret) {
-		pr_err("%s: Failed to wait for the async response, %d\n",
+		pr_err("%s: Failed to wait for the async response, %zd\n",
 				__func__, ret);
 		goto out_token;
 	}
@@ -111,7 +112,7 @@ static ssize_t sys_param_show(struct kobject *kobj,
 {
 	struct param_attr *attr = container_of(kobj_attr, struct param_attr,
 			kobj_attr);
-	int ret;
+	ssize_t ret;
 
 	mutex_lock(&opal_sysparam_mutex);
 	ret = opal_get_sys_param(attr->param_id, attr->param_size,
@@ -121,9 +122,10 @@ static ssize_t sys_param_show(struct kobject *kobj,
 
 	memcpy(buf, param_data_buf, attr->param_size);
 
+	ret = attr->param_size;
 out:
 	mutex_unlock(&opal_sysparam_mutex);
-	return ret ? ret : attr->param_size;
+	return ret;
 }
 
 static ssize_t sys_param_store(struct kobject *kobj,
@@ -131,14 +133,20 @@ static ssize_t sys_param_store(struct kobject *kobj,
 {
 	struct param_attr *attr = container_of(kobj_attr, struct param_attr,
 			kobj_attr);
-	int ret;
+	ssize_t ret;
+
+        /* MAX_PARAM_DATA_LEN is sizeof(param_data_buf) */
+        if (count > MAX_PARAM_DATA_LEN)
+                count = MAX_PARAM_DATA_LEN;
 
 	mutex_lock(&opal_sysparam_mutex);
 	memcpy(param_data_buf, buf, count);
 	ret = opal_set_sys_param(attr->param_id, attr->param_size,
 			param_data_buf);
 	mutex_unlock(&opal_sysparam_mutex);
-	return ret ? ret : count;
+	if (!ret)
+		ret = count;
+	return ret;
 }
 
 void __init opal_sys_param_init(void)
@@ -214,13 +222,13 @@ void __init opal_sys_param_init(void)
 	}
 
 	if (of_property_read_u32_array(sysparam, "param-len", size, count)) {
-		pr_err("SYSPARAM: Missing propery param-len in the DT\n");
+		pr_err("SYSPARAM: Missing property param-len in the DT\n");
 		goto out_free_perm;
 	}
 
 
 	if (of_property_read_u8_array(sysparam, "param-perm", perm, count)) {
-		pr_err("SYSPARAM: Missing propery param-perm in the DT\n");
+		pr_err("SYSPARAM: Missing property param-perm in the DT\n");
 		goto out_free_perm;
 	}
 
@@ -233,6 +241,12 @@ void __init opal_sys_param_init(void)
 
 	/* For each of the parameters, populate the parameter attributes */
 	for (i = 0; i < count; i++) {
+		if (size[i] > MAX_PARAM_DATA_LEN) {
+			pr_warn("SYSPARAM: Not creating parameter %d as size "
+				"exceeds buffer length\n", i);
+			continue;
+		}
+
 		sysfs_attr_init(&attr[i].kobj_attr.attr);
 		attr[i].param_id = id[i];
 		attr[i].param_size = size[i];
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 49d2f00..360ad80c 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -242,14 +242,14 @@ void opal_notifier_update_evt(uint64_t evt_mask,
 void opal_notifier_enable(void)
 {
 	int64_t rc;
-	uint64_t evt = 0;
+	__be64 evt = 0;
 
 	atomic_set(&opal_notifier_hold, 0);
 
 	/* Process pending events */
 	rc = opal_poll_events(&evt);
 	if (rc == OPAL_SUCCESS && evt)
-		opal_do_notifier(evt);
+		opal_do_notifier(be64_to_cpu(evt));
 }
 
 void opal_notifier_disable(void)
@@ -529,7 +529,7 @@ static irqreturn_t opal_interrupt(int irq, void *data)
 
 	opal_handle_interrupt(virq_to_hw(irq), &events);
 
-	opal_do_notifier(events);
+	opal_do_notifier(be64_to_cpu(events));
 
 	return IRQ_HANDLED;
 }
@@ -638,3 +638,66 @@ void opal_shutdown(void)
 
 /* Export this so that test modules can use it */
 EXPORT_SYMBOL_GPL(opal_invalid_call);
+
+/* Convert a region of vmalloc memory to an opal sg list */
+struct opal_sg_list *opal_vmalloc_to_sg_list(void *vmalloc_addr,
+					     unsigned long vmalloc_size)
+{
+	struct opal_sg_list *sg, *first = NULL;
+	unsigned long i = 0;
+
+	sg = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!sg)
+		goto nomem;
+
+	first = sg;
+
+	while (vmalloc_size > 0) {
+		uint64_t data = vmalloc_to_pfn(vmalloc_addr) << PAGE_SHIFT;
+		uint64_t length = min(vmalloc_size, PAGE_SIZE);
+
+		sg->entry[i].data = cpu_to_be64(data);
+		sg->entry[i].length = cpu_to_be64(length);
+		i++;
+
+		if (i >= SG_ENTRIES_PER_NODE) {
+			struct opal_sg_list *next;
+
+			next = kzalloc(PAGE_SIZE, GFP_KERNEL);
+			if (!next)
+				goto nomem;
+
+			sg->length = cpu_to_be64(
+					i * sizeof(struct opal_sg_entry) + 16);
+			i = 0;
+			sg->next = cpu_to_be64(__pa(next));
+			sg = next;
+		}
+
+		vmalloc_addr += length;
+		vmalloc_size -= length;
+	}
+
+	sg->length = cpu_to_be64(i * sizeof(struct opal_sg_entry) + 16);
+
+	return first;
+
+nomem:
+	pr_err("%s : Failed to allocate memory\n", __func__);
+	opal_free_sg_list(first);
+	return NULL;
+}
+
+void opal_free_sg_list(struct opal_sg_list *sg)
+{
+	while (sg) {
+		uint64_t next = be64_to_cpu(sg->next);
+
+		kfree(sg);
+
+		if (next)
+			sg = __va(next);
+		else
+			sg = NULL;
+	}
+}
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 3b2b4fb..98824aa 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -343,7 +343,6 @@ static void pnv_ioda_setup_same_PE(struct pci_bus *bus, struct pnv_ioda_pe *pe)
 				pci_name(dev));
 			continue;
 		}
-		pci_dev_get(dev);
 		pdn->pcidev = dev;
 		pdn->pe_number = pe->pe_number;
 		pe->dma_weight += pnv_ioda_dma_weight(dev);
@@ -462,7 +461,7 @@ static void pnv_pci_ioda_dma_dev_setup(struct pnv_phb *phb, struct pci_dev *pdev
 
 	pe = &phb->ioda.pe_array[pdn->pe_number];
 	WARN_ON(get_dma_ops(&pdev->dev) != &dma_iommu_ops);
-	set_iommu_table_base_and_group(&pdev->dev, &pe->tce32_table);
+	set_iommu_table_base(&pdev->dev, &pe->tce32_table);
 }
 
 static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 61cf8fa..8723d32 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -162,18 +162,62 @@ static void pnv_shutdown(void)
 }
 
 #ifdef CONFIG_KEXEC
+static void pnv_kexec_wait_secondaries_down(void)
+{
+	int my_cpu, i, notified = -1;
+
+	my_cpu = get_cpu();
+
+	for_each_online_cpu(i) {
+		uint8_t status;
+		int64_t rc;
+
+		if (i == my_cpu)
+			continue;
+
+		for (;;) {
+			rc = opal_query_cpu_status(get_hard_smp_processor_id(i),
+						   &status);
+			if (rc != OPAL_SUCCESS || status != OPAL_THREAD_STARTED)
+				break;
+			barrier();
+			if (i != notified) {
+				printk(KERN_INFO "kexec: waiting for cpu %d "
+				       "(physical %d) to enter OPAL\n",
+				       i, paca[i].hw_cpu_id);
+				notified = i;
+			}
+		}
+	}
+}
+
 static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 {
 	xics_kexec_teardown_cpu(secondary);
 
-	/* Return secondary CPUs to firmware on OPAL v3 */
-	if (firmware_has_feature(FW_FEATURE_OPALv3) && secondary) {
+	/* On OPAL v3, we return all CPUs to firmware */
+
+	if (!firmware_has_feature(FW_FEATURE_OPALv3))
+		return;
+
+	if (secondary) {
+		/* Return secondary CPUs to firmware on OPAL v3 */
 		mb();
 		get_paca()->kexec_state = KEXEC_STATE_REAL_MODE;
 		mb();
 
 		/* Return the CPU to OPAL */
 		opal_return_cpu();
+	} else if (crash_shutdown) {
+		/*
+		 * On crash, we don't wait for secondaries to go
+		 * down as they might be unreachable or hung, so
+		 * instead we just wait a bit and move on.
+		 */
+		mdelay(1);
+	} else {
+		/* Primary waits for the secondaries to have reached OPAL */
+		pnv_kexec_wait_secondaries_down();
 	}
 }
 #endif /* CONFIG_KEXEC */
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 908672b..bf5fcd4 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -30,6 +30,7 @@
 #include <asm/cputhreads.h>
 #include <asm/xics.h>
 #include <asm/opal.h>
+#include <asm/runlatch.h>
 
 #include "powernv.h"
 
@@ -156,7 +157,9 @@ static void pnv_smp_cpu_kill_self(void)
 	 */
 	mtspr(SPRN_LPCR, mfspr(SPRN_LPCR) & ~(u64)LPCR_PECE1);
 	while (!generic_check_cpu_restart(cpu)) {
+		ppc64_runlatch_off();
 		power7_nap();
+		ppc64_runlatch_on();
 		if (!generic_check_cpu_restart(cpu)) {
 			DBG("CPU%d Unexpected exit while offline !\n", cpu);
 			/* We may be getting an IPI, so we re-enable
diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c
index 9b8e050..20d6297 100644
--- a/arch/powerpc/platforms/pseries/hotplug-cpu.c
+++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c
@@ -88,13 +88,14 @@ void set_default_offline_state(int cpu)
 
 static void rtas_stop_self(void)
 {
-	struct rtas_args args = {
-		.token = cpu_to_be32(rtas_stop_self_token),
+	static struct rtas_args args = {
 		.nargs = 0,
 		.nret = 1,
 		.rets = &args.args[0],
 	};
 
+	args.token = cpu_to_be32(rtas_stop_self_token);
+
 	local_irq_disable();
 
 	BUG_ON(rtas_stop_self_token == RTAS_UNKNOWN_SERVICE);
diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c
index 573b488..7f75c94 100644
--- a/arch/powerpc/platforms/pseries/hotplug-memory.c
+++ b/arch/powerpc/platforms/pseries/hotplug-memory.c
@@ -100,10 +100,10 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz
 
 	start_pfn = base >> PAGE_SHIFT;
 
-	if (!pfn_valid(start_pfn)) {
-		memblock_remove(base, memblock_size);
-		return 0;
-	}
+	lock_device_hotplug();
+
+	if (!pfn_valid(start_pfn))
+		goto out;
 
 	block_sz = memory_block_size_bytes();
 	sections_per_block = block_sz / MIN_MEMORY_BLOCK_SIZE;
@@ -114,8 +114,10 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz
 		base += MIN_MEMORY_BLOCK_SIZE;
 	}
 
+out:
 	/* Update memory regions for memory remove */
 	memblock_remove(base, memblock_size);
+	unlock_device_hotplug();
 	return 0;
 }
 
diff --git a/arch/powerpc/sysdev/ppc4xx_pci.c b/arch/powerpc/sysdev/ppc4xx_pci.c
index 64603a1..4914fd3 100644
--- a/arch/powerpc/sysdev/ppc4xx_pci.c
+++ b/arch/powerpc/sysdev/ppc4xx_pci.c
@@ -1058,7 +1058,7 @@ static int __init apm821xx_pciex_core_init(struct device_node *np)
 	return 1;
 }
 
-static int apm821xx_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
+static int __init apm821xx_pciex_init_port_hw(struct ppc4xx_pciex_port *port)
 {
 	u32 val;
 
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index 9c36dc3..452d3eb 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -276,7 +276,6 @@ static void bpf_jit_noleaks(struct bpf_jit *jit, struct sock_filter *filter)
 	case BPF_S_LD_W_IND:
 	case BPF_S_LD_H_IND:
 	case BPF_S_LD_B_IND:
-	case BPF_S_LDX_B_MSH:
 	case BPF_S_LD_IMM:
 	case BPF_S_LD_MEM:
 	case BPF_S_MISC_TXA:
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index d1b7c37..ce6ad7e 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -83,7 +83,9 @@ else
         KBUILD_CFLAGS += -m64
 
         # Don't autogenerate traditional x87, MMX or SSE instructions
-        KBUILD_CFLAGS += -mno-mmx -mno-sse -mno-80387 -mno-fp-ret-in-387
+        KBUILD_CFLAGS += -mno-mmx -mno-sse
+        KBUILD_CFLAGS += $(call cc-option,-mno-80387)
+        KBUILD_CFLAGS += $(call cc-option,-mno-fp-ret-in-387)
 
 	# Use -mpreferred-stack-boundary=3 if supported.
 	KBUILD_CFLAGS += $(call cc-option,-mpreferred-stack-boundary=3)
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 6ad4658..d23aa82 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -3425,6 +3425,11 @@ int get_nr_irqs_gsi(void)
 	return nr_irqs_gsi;
 }
 
+unsigned int arch_dynirq_lower_bound(unsigned int from)
+{
+	return from < nr_irqs_gsi ? nr_irqs_gsi : from;
+}
+
 int __init arch_probe_nr_irqs(void)
 {
 	int nr;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 7c87424..619f769 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -543,7 +543,8 @@ static int rapl_cpu_prepare(int cpu)
 	if (phys_id < 0)
 		return -1;
 
-	if (!rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits))
+	/* protect rdmsrl() to handle virtualization */
+	if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits))
 		return -1;
 
 	pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
diff --git a/arch/x86/kernel/vsmp_64.c b/arch/x86/kernel/vsmp_64.c
index f6584a9..5edc34b 100644
--- a/arch/x86/kernel/vsmp_64.c
+++ b/arch/x86/kernel/vsmp_64.c
@@ -26,6 +26,9 @@
 
 #define TOPOLOGY_REGISTER_OFFSET 0x10
 
+/* Flag below is initialized once during vSMP PCI initialization. */
+static int irq_routing_comply = 1;
+
 #if defined CONFIG_PCI && defined CONFIG_PARAVIRT
 /*
  * Interrupt control on vSMPowered systems:
@@ -101,6 +104,10 @@ static void __init set_vsmp_pv_ops(void)
 #ifdef CONFIG_SMP
 	if (cap & ctl & BIT(8)) {
 		ctl &= ~BIT(8);
+
+		/* Interrupt routing set to ignore */
+		irq_routing_comply = 0;
+
 #ifdef CONFIG_PROC_FS
 		/* Don't let users change irq affinity via procfs */
 		no_irq_affinity = 1;
@@ -218,7 +225,9 @@ static void vsmp_apic_post_init(void)
 {
 	/* need to update phys_pkg_id */
 	apic->phys_pkg_id = apicid_phys_pkg_id;
-	apic->vector_allocation_domain = fill_vector_allocation_domain;
+
+	if (!irq_routing_comply)
+		apic->vector_allocation_domain = fill_vector_allocation_domain;
 }
 
 void __init vsmp_init(void)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 1f68c58..33e8c02 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -503,7 +503,7 @@ static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
 				[number##_HIGH] = VMCS12_OFFSET(name)+4
 
 
-static const unsigned long shadow_read_only_fields[] = {
+static unsigned long shadow_read_only_fields[] = {
 	/*
 	 * We do NOT shadow fields that are modified when L0
 	 * traps and emulates any vmx instruction (e.g. VMPTRLD,
@@ -526,10 +526,10 @@ static const unsigned long shadow_read_only_fields[] = {
 	GUEST_LINEAR_ADDRESS,
 	GUEST_PHYSICAL_ADDRESS
 };
-static const int max_shadow_read_only_fields =
+static int max_shadow_read_only_fields =
 	ARRAY_SIZE(shadow_read_only_fields);
 
-static const unsigned long shadow_read_write_fields[] = {
+static unsigned long shadow_read_write_fields[] = {
 	GUEST_RIP,
 	GUEST_RSP,
 	GUEST_CR0,
@@ -558,7 +558,7 @@ static const unsigned long shadow_read_write_fields[] = {
 	HOST_FS_SELECTOR,
 	HOST_GS_SELECTOR
 };
-static const int max_shadow_read_write_fields =
+static int max_shadow_read_write_fields =
 	ARRAY_SIZE(shadow_read_write_fields);
 
 static const unsigned short vmcs_field_to_offset_table[] = {
@@ -3009,6 +3009,41 @@ static void free_kvm_area(void)
 	}
 }
 
+static void init_vmcs_shadow_fields(void)
+{
+	int i, j;
+
+	/* No checks for read only fields yet */
+
+	for (i = j = 0; i < max_shadow_read_write_fields; i++) {
+		switch (shadow_read_write_fields[i]) {
+		case GUEST_BNDCFGS:
+			if (!vmx_mpx_supported())
+				continue;
+			break;
+		default:
+			break;
+		}
+
+		if (j < i)
+			shadow_read_write_fields[j] =
+				shadow_read_write_fields[i];
+		j++;
+	}
+	max_shadow_read_write_fields = j;
+
+	/* shadowed fields guest access without vmexit */
+	for (i = 0; i < max_shadow_read_write_fields; i++) {
+		clear_bit(shadow_read_write_fields[i],
+			  vmx_vmwrite_bitmap);
+		clear_bit(shadow_read_write_fields[i],
+			  vmx_vmread_bitmap);
+	}
+	for (i = 0; i < max_shadow_read_only_fields; i++)
+		clear_bit(shadow_read_only_fields[i],
+			  vmx_vmread_bitmap);
+}
+
 static __init int alloc_kvm_area(void)
 {
 	int cpu;
@@ -3039,6 +3074,8 @@ static __init int hardware_setup(void)
 		enable_vpid = 0;
 	if (!cpu_has_vmx_shadow_vmcs())
 		enable_shadow_vmcs = 0;
+	if (enable_shadow_vmcs)
+		init_vmcs_shadow_fields();
 
 	if (!cpu_has_vmx_ept() ||
 	    !cpu_has_vmx_ept_4levels()) {
@@ -8803,14 +8840,6 @@ static int __init vmx_init(void)
 
 	memset(vmx_vmread_bitmap, 0xff, PAGE_SIZE);
 	memset(vmx_vmwrite_bitmap, 0xff, PAGE_SIZE);
-	/* shadowed read/write fields */
-	for (i = 0; i < max_shadow_read_write_fields; i++) {
-		clear_bit(shadow_read_write_fields[i], vmx_vmwrite_bitmap);
-		clear_bit(shadow_read_write_fields[i], vmx_vmread_bitmap);
-	}
-	/* shadowed read only fields */
-	for (i = 0; i < max_shadow_read_only_fields; i++)
-		clear_bit(shadow_read_only_fields[i], vmx_vmread_bitmap);
 
 	/*
 	 * Allow direct access to the PC debug port (it is often used for I/O
diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
index c29c2c3..b06f5f5 100644
--- a/drivers/acpi/acpi_processor.c
+++ b/drivers/acpi/acpi_processor.c
@@ -170,6 +170,9 @@ static int acpi_processor_hotadd_init(struct acpi_processor *pr)
 	acpi_status status;
 	int ret;
 
+	if (pr->apic_id == -1)
+		return -ENODEV;
+
 	status = acpi_evaluate_integer(pr->handle, "_STA", NULL, &sta);
 	if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_PRESENT))
 		return -ENODEV;
@@ -260,10 +263,8 @@ static int acpi_processor_get_info(struct acpi_device *device)
 	}
 
 	apic_id = acpi_get_apicid(pr->handle, device_declaration, pr->acpi_id);
-	if (apic_id < 0) {
+	if (apic_id < 0)
 		acpi_handle_debug(pr->handle, "failed to get CPU APIC ID.\n");
-		return -ENODEV;
-	}
 	pr->apic_id = apic_id;
 
 	cpu_index = acpi_map_cpuid(pr->apic_id, pr->acpi_id);
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index d7d32c2..ad11ba4 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -206,13 +206,13 @@ unlock:
 	spin_unlock_irqrestore(&ec->lock, flags);
 }
 
-static int acpi_ec_sync_query(struct acpi_ec *ec);
+static int acpi_ec_sync_query(struct acpi_ec *ec, u8 *data);
 
 static int ec_check_sci_sync(struct acpi_ec *ec, u8 state)
 {
 	if (state & ACPI_EC_FLAG_SCI) {
 		if (!test_and_set_bit(EC_FLAGS_QUERY_PENDING, &ec->flags))
-			return acpi_ec_sync_query(ec);
+			return acpi_ec_sync_query(ec, NULL);
 	}
 	return 0;
 }
@@ -443,10 +443,8 @@ acpi_handle ec_get_handle(void)
 
 EXPORT_SYMBOL(ec_get_handle);
 
-static int acpi_ec_query_unlocked(struct acpi_ec *ec, u8 *data);
-
 /*
- * Clears stale _Q events that might have accumulated in the EC.
+ * Process _Q events that might have accumulated in the EC.
  * Run with locked ec mutex.
  */
 static void acpi_ec_clear(struct acpi_ec *ec)
@@ -455,7 +453,7 @@ static void acpi_ec_clear(struct acpi_ec *ec)
 	u8 value = 0;
 
 	for (i = 0; i < ACPI_EC_CLEAR_MAX; i++) {
-		status = acpi_ec_query_unlocked(ec, &value);
+		status = acpi_ec_sync_query(ec, &value);
 		if (status || !value)
 			break;
 	}
@@ -582,13 +580,18 @@ static void acpi_ec_run(void *cxt)
 	kfree(handler);
 }
 
-static int acpi_ec_sync_query(struct acpi_ec *ec)
+static int acpi_ec_sync_query(struct acpi_ec *ec, u8 *data)
 {
 	u8 value = 0;
 	int status;
 	struct acpi_ec_query_handler *handler, *copy;
-	if ((status = acpi_ec_query_unlocked(ec, &value)))
+
+	status = acpi_ec_query_unlocked(ec, &value);
+	if (data)
+		*data = value;
+	if (status)
 		return status;
+
 	list_for_each_entry(handler, &ec->list, node) {
 		if (value == handler->query_bit) {
 			/* have custom handler for this bit */
@@ -612,7 +615,7 @@ static void acpi_ec_gpe_query(void *ec_cxt)
 	if (!ec)
 		return;
 	mutex_lock(&ec->mutex);
-	acpi_ec_sync_query(ec);
+	acpi_ec_sync_query(ec, NULL);
 	mutex_unlock(&ec->mutex);
 }
 
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index 8986b9f..62ec61e 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -52,6 +52,7 @@ static DEFINE_MUTEX(deferred_probe_mutex);
 static LIST_HEAD(deferred_probe_pending_list);
 static LIST_HEAD(deferred_probe_active_list);
 static struct workqueue_struct *deferred_wq;
+static atomic_t deferred_trigger_count = ATOMIC_INIT(0);
 
 /**
  * deferred_probe_work_func() - Retry probing devices in the active list.
@@ -135,6 +136,17 @@ static bool driver_deferred_probe_enable = false;
  * This functions moves all devices from the pending list to the active
  * list and schedules the deferred probe workqueue to process them.  It
  * should be called anytime a driver is successfully bound to a device.
+ *
+ * Note, there is a race condition in multi-threaded probe. In the case where
+ * more than one device is probing at the same time, it is possible for one
+ * probe to complete successfully while another is about to defer. If the second
+ * depends on the first, then it will get put on the pending list after the
+ * trigger event has already occured and will be stuck there.
+ *
+ * The atomic 'deferred_trigger_count' is used to determine if a successful
+ * trigger has occurred in the midst of probing a driver. If the trigger count
+ * changes in the midst of a probe, then deferred processing should be triggered
+ * again.
  */
 static void driver_deferred_probe_trigger(void)
 {
@@ -147,6 +159,7 @@ static void driver_deferred_probe_trigger(void)
 	 * into the active list so they can be retried by the workqueue
 	 */
 	mutex_lock(&deferred_probe_mutex);
+	atomic_inc(&deferred_trigger_count);
 	list_splice_tail_init(&deferred_probe_pending_list,
 			      &deferred_probe_active_list);
 	mutex_unlock(&deferred_probe_mutex);
@@ -265,6 +278,7 @@ static DECLARE_WAIT_QUEUE_HEAD(probe_waitqueue);
 static int really_probe(struct device *dev, struct device_driver *drv)
 {
 	int ret = 0;
+	int local_trigger_count = atomic_read(&deferred_trigger_count);
 
 	atomic_inc(&probe_count);
 	pr_debug("bus: '%s': %s: probing driver %s with device %s\n",
@@ -310,6 +324,9 @@ probe_failed:
 		/* Driver requested deferred probing */
 		dev_info(dev, "Driver %s requests probe deferral\n", drv->name);
 		driver_deferred_probe_add(dev);
+		/* Did a trigger occur while probing? Need to re-trigger if yes */
+		if (local_trigger_count != atomic_read(&deferred_trigger_count))
+			driver_deferred_probe_trigger();
 	} else if (ret != -ENODEV && ret != -ENXIO) {
 		/* driver matched but the probe failed */
 		printk(KERN_WARNING
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index e714709..5b47210 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -13,6 +13,7 @@
 #include <linux/string.h>
 #include <linux/platform_device.h>
 #include <linux/of_device.h>
+#include <linux/of_irq.h>
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/dma-mapping.h>
@@ -87,7 +88,11 @@ int platform_get_irq(struct platform_device *dev, unsigned int num)
 		return -ENXIO;
 	return dev->archdata.irqs[num];
 #else
-	struct resource *r = platform_get_resource(dev, IORESOURCE_IRQ, num);
+	struct resource *r;
+	if (IS_ENABLED(CONFIG_OF_IRQ) && dev->dev.of_node)
+		return of_irq_get(dev->dev.of_node, num);
+
+	r = platform_get_resource(dev, IORESOURCE_IRQ, num);
 
 	return r ? r->start : -ENXIO;
 #endif
diff --git a/drivers/clk/versatile/clk-vexpress-osc.c b/drivers/clk/versatile/clk-vexpress-osc.c
index a535c7b..4223912 100644
--- a/drivers/clk/versatile/clk-vexpress-osc.c
+++ b/drivers/clk/versatile/clk-vexpress-osc.c
@@ -100,6 +100,8 @@ void __init vexpress_osc_of_setup(struct device_node *node)
 	struct clk *clk;
 	u32 range[2];
 
+	vexpress_sysreg_of_early_init();
+
 	osc = kzalloc(sizeof(*osc), GFP_KERNEL);
 	if (!osc)
 		return;
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 57e823c..5163ec1 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -66,6 +66,7 @@ static int arch_timer_ppi[MAX_TIMER_PPI];
 static struct clock_event_device __percpu *arch_timer_evt;
 
 static bool arch_timer_use_virtual = true;
+static bool arch_timer_c3stop;
 static bool arch_timer_mem_use_virtual;
 
 /*
@@ -263,7 +264,8 @@ static void __arch_timer_setup(unsigned type,
 	clk->features = CLOCK_EVT_FEAT_ONESHOT;
 
 	if (type == ARCH_CP15_TIMER) {
-		clk->features |= CLOCK_EVT_FEAT_C3STOP;
+		if (arch_timer_c3stop)
+			clk->features |= CLOCK_EVT_FEAT_C3STOP;
 		clk->name = "arch_sys_timer";
 		clk->rating = 450;
 		clk->cpumask = cpumask_of(smp_processor_id());
@@ -665,6 +667,8 @@ static void __init arch_timer_init(struct device_node *np)
 		}
 	}
 
+	arch_timer_c3stop = !of_property_read_bool(np, "always-on");
+
 	arch_timer_register();
 	arch_timer_common_init();
 }
diff --git a/drivers/clocksource/zevio-timer.c b/drivers/clocksource/zevio-timer.c
index ca81809..7ce4421 100644
--- a/drivers/clocksource/zevio-timer.c
+++ b/drivers/clocksource/zevio-timer.c
@@ -212,4 +212,9 @@ error_free:
 	return ret;
 }
 
-CLOCKSOURCE_OF_DECLARE(zevio_timer, "lsi,zevio-timer", zevio_timer_add);
+static void __init zevio_timer_init(struct device_node *node)
+{
+	BUG_ON(zevio_timer_add(node));
+}
+
+CLOCKSOURCE_OF_DECLARE(zevio_timer, "lsi,zevio-timer", zevio_timer_init);
diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c
index d00e5d1..5c4369b 100644
--- a/drivers/cpufreq/longhaul.c
+++ b/drivers/cpufreq/longhaul.c
@@ -242,7 +242,7 @@ static void do_powersaver(int cx_address, unsigned int mults_index,
  * Sets a new clock ratio.
  */
 
-static void longhaul_setstate(struct cpufreq_policy *policy,
+static int longhaul_setstate(struct cpufreq_policy *policy,
 		unsigned int table_index)
 {
 	unsigned int mults_index;
@@ -258,10 +258,12 @@ static void longhaul_setstate(struct cpufreq_policy *policy,
 	/* Safety precautions */
 	mult = mults[mults_index & 0x1f];
 	if (mult == -1)
-		return;
+		return -EINVAL;
+
 	speed = calc_speed(mult);
 	if ((speed > highest_speed) || (speed < lowest_speed))
-		return;
+		return -EINVAL;
+
 	/* Voltage transition before frequency transition? */
 	if (can_scale_voltage && longhaul_index < table_index)
 		dir = 1;
@@ -269,8 +271,6 @@ static void longhaul_setstate(struct cpufreq_policy *policy,
 	freqs.old = calc_speed(longhaul_get_cpu_mult());
 	freqs.new = speed;
 
-	cpufreq_freq_transition_begin(policy, &freqs);
-
 	pr_debug("Setting to FSB:%dMHz Mult:%d.%dx (%s)\n",
 			fsb, mult/10, mult%10, print_speed(speed/1000));
 retry_loop:
@@ -385,12 +385,14 @@ retry_loop:
 			goto retry_loop;
 		}
 	}
-	/* Report true CPU frequency */
-	cpufreq_freq_transition_end(policy, &freqs, 0);
 
-	if (!bm_timeout)
+	if (!bm_timeout) {
 		printk(KERN_INFO PFX "Warning: Timeout while waiting for "
 				"idle PCI bus.\n");
+		return -EBUSY;
+	}
+
+	return 0;
 }
 
 /*
@@ -631,9 +633,10 @@ static int longhaul_target(struct cpufreq_policy *policy,
 	unsigned int i;
 	unsigned int dir = 0;
 	u8 vid, current_vid;
+	int retval = 0;
 
 	if (!can_scale_voltage)
-		longhaul_setstate(policy, table_index);
+		retval = longhaul_setstate(policy, table_index);
 	else {
 		/* On test system voltage transitions exceeding single
 		 * step up or down were turning motherboard off. Both
@@ -648,7 +651,7 @@ static int longhaul_target(struct cpufreq_policy *policy,
 		while (i != table_index) {
 			vid = (longhaul_table[i].driver_data >> 8) & 0x1f;
 			if (vid != current_vid) {
-				longhaul_setstate(policy, i);
+				retval = longhaul_setstate(policy, i);
 				current_vid = vid;
 				msleep(200);
 			}
@@ -657,10 +660,11 @@ static int longhaul_target(struct cpufreq_policy *policy,
 			else
 				i--;
 		}
-		longhaul_setstate(policy, table_index);
+		retval = longhaul_setstate(policy, table_index);
 	}
+
 	longhaul_index = table_index;
-	return 0;
+	return retval;
 }
 
 
@@ -968,7 +972,15 @@ static void __exit longhaul_exit(void)
 
 	for (i = 0; i < numscales; i++) {
 		if (mults[i] == maxmult) {
+			struct cpufreq_freqs freqs;
+
+			freqs.old = policy->cur;
+			freqs.new = longhaul_table[i].frequency;
+			freqs.flags = 0;
+
+			cpufreq_freq_transition_begin(policy, &freqs);
 			longhaul_setstate(policy, i);
+			cpufreq_freq_transition_end(policy, &freqs, 0);
 			break;
 		}
 	}
diff --git a/drivers/cpufreq/powernow-k6.c b/drivers/cpufreq/powernow-k6.c
index 49f120e..78904e6 100644
--- a/drivers/cpufreq/powernow-k6.c
+++ b/drivers/cpufreq/powernow-k6.c
@@ -138,22 +138,14 @@ static void powernow_k6_set_cpu_multiplier(unsigned int best_i)
 static int powernow_k6_target(struct cpufreq_policy *policy,
 		unsigned int best_i)
 {
-	struct cpufreq_freqs freqs;
 
 	if (clock_ratio[best_i].driver_data > max_multiplier) {
 		printk(KERN_ERR PFX "invalid target frequency\n");
 		return -EINVAL;
 	}
 
-	freqs.old = busfreq * powernow_k6_get_cpu_multiplier();
-	freqs.new = busfreq * clock_ratio[best_i].driver_data;
-
-	cpufreq_freq_transition_begin(policy, &freqs);
-
 	powernow_k6_set_cpu_multiplier(best_i);
 
-	cpufreq_freq_transition_end(policy, &freqs, 0);
-
 	return 0;
 }
 
@@ -227,9 +219,20 @@ have_busfreq:
 static int powernow_k6_cpu_exit(struct cpufreq_policy *policy)
 {
 	unsigned int i;
-	for (i = 0; i < 8; i++) {
-		if (i == max_multiplier)
+
+	for (i = 0; (clock_ratio[i].frequency != CPUFREQ_TABLE_END); i++) {
+		if (clock_ratio[i].driver_data == max_multiplier) {
+			struct cpufreq_freqs freqs;
+
+			freqs.old = policy->cur;
+			freqs.new = clock_ratio[i].frequency;
+			freqs.flags = 0;
+
+			cpufreq_freq_transition_begin(policy, &freqs);
 			powernow_k6_target(policy, i);
+			cpufreq_freq_transition_end(policy, &freqs, 0);
+			break;
+		}
 	}
 	return 0;
 }
diff --git a/drivers/cpufreq/powernow-k7.c b/drivers/cpufreq/powernow-k7.c
index f911645..e61e224 100644
--- a/drivers/cpufreq/powernow-k7.c
+++ b/drivers/cpufreq/powernow-k7.c
@@ -269,8 +269,6 @@ static int powernow_target(struct cpufreq_policy *policy, unsigned int index)
 
 	freqs.new = powernow_table[index].frequency;
 
-	cpufreq_freq_transition_begin(policy, &freqs);
-
 	/* Now do the magic poking into the MSRs.  */
 
 	if (have_a0 == 1)	/* A0 errata 5 */
@@ -290,8 +288,6 @@ static int powernow_target(struct cpufreq_policy *policy, unsigned int index)
 	if (have_a0 == 1)
 		local_irq_enable();
 
-	cpufreq_freq_transition_end(policy, &freqs, 0);
-
 	return 0;
 }
 
diff --git a/drivers/cpufreq/ppc-corenet-cpufreq.c b/drivers/cpufreq/ppc-corenet-cpufreq.c
index a1ca3dd..0af618a 100644
--- a/drivers/cpufreq/ppc-corenet-cpufreq.c
+++ b/drivers/cpufreq/ppc-corenet-cpufreq.c
@@ -138,6 +138,7 @@ static int corenet_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	struct cpufreq_frequency_table *table;
 	struct cpu_data *data;
 	unsigned int cpu = policy->cpu;
+	u64 transition_latency_hz;
 
 	np = of_get_cpu_node(cpu, NULL);
 	if (!np)
@@ -205,8 +206,10 @@ static int corenet_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	for_each_cpu(i, per_cpu(cpu_mask, cpu))
 		per_cpu(cpu_data, i) = data;
 
+	transition_latency_hz = 12ULL * NSEC_PER_SEC;
 	policy->cpuinfo.transition_latency =
-				(12ULL * NSEC_PER_SEC) / fsl_get_sys_freq();
+		do_div(transition_latency_hz, fsl_get_sys_freq());
+
 	of_node_put(np);
 
 	return 0;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_crtc.c b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
index e930d4f..1ef5ab9 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_crtc.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_crtc.c
@@ -145,6 +145,7 @@ exynos_drm_crtc_mode_set(struct drm_crtc *crtc, struct drm_display_mode *mode,
 
 	plane->crtc = crtc;
 	plane->fb = crtc->primary->fb;
+	drm_framebuffer_reference(plane->fb);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
index c786cd4..2a3ad24 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dmabuf.c
@@ -263,7 +263,7 @@ struct drm_gem_object *exynos_dmabuf_prime_import(struct drm_device *drm_dev,
 	buffer->sgt = sgt;
 	exynos_gem_obj->base.import_attach = attach;
 
-	DRM_DEBUG_PRIME("dma_addr = 0x%x, size = 0x%lx\n", buffer->dma_addr,
+	DRM_DEBUG_PRIME("dma_addr = %pad, size = 0x%lx\n", &buffer->dma_addr,
 								buffer->size);
 
 	return &exynos_gem_obj->base;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index eb73e3b..4ac4381 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -1426,9 +1426,9 @@ static int exynos_dsi_probe(struct platform_device *pdev)
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	dsi->reg_base = devm_ioremap_resource(&pdev->dev, res);
-	if (!dsi->reg_base) {
+	if (IS_ERR(dsi->reg_base)) {
 		dev_err(&pdev->dev, "failed to remap io region\n");
-		return -EADDRNOTAVAIL;
+		return PTR_ERR(dsi->reg_base);
 	}
 
 	dsi->phy = devm_phy_get(&pdev->dev, "dsim");
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index 7afead9..852f2da 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -220,7 +220,7 @@ static void vidi_win_commit(struct exynos_drm_manager *mgr, int zpos)
 
 	win_data->enabled = true;
 
-	DRM_DEBUG_KMS("dma_addr = 0x%x\n", win_data->dma_addr);
+	DRM_DEBUG_KMS("dma_addr = %pad\n", &win_data->dma_addr);
 
 	if (ctx->vblank_on)
 		schedule_work(&ctx->work);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index ab5e93c..62a5c36 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -50,7 +50,7 @@ bool intel_enable_ppgtt(struct drm_device *dev, bool full)
 
 	/* Full ppgtt disabled by default for now due to issues. */
 	if (full)
-		return false; /* HAS_PPGTT(dev) */
+		return HAS_PPGTT(dev) && (i915.enable_ppgtt == 2);
 	else
 		return HAS_ALIASING_PPGTT(dev);
 }
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 7753249..f98ba4e 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1362,10 +1362,20 @@ static inline void intel_hpd_irq_handler(struct drm_device *dev,
 	spin_lock(&dev_priv->irq_lock);
 	for (i = 1; i < HPD_NUM_PINS; i++) {
 
-		WARN_ONCE(hpd[i] & hotplug_trigger &&
-			  dev_priv->hpd_stats[i].hpd_mark == HPD_DISABLED,
-			  "Received HPD interrupt (0x%08x) on pin %d (0x%08x) although disabled\n",
-			  hotplug_trigger, i, hpd[i]);
+		if (hpd[i] & hotplug_trigger &&
+		    dev_priv->hpd_stats[i].hpd_mark == HPD_DISABLED) {
+			/*
+			 * On GMCH platforms the interrupt mask bits only
+			 * prevent irq generation, not the setting of the
+			 * hotplug bits itself. So only WARN about unexpected
+			 * interrupts on saner platforms.
+			 */
+			WARN_ONCE(INTEL_INFO(dev)->gen >= 5 && !IS_VALLEYVIEW(dev),
+				  "Received HPD interrupt (0x%08x) on pin %d (0x%08x) although disabled\n",
+				  hotplug_trigger, i, hpd[i]);
+
+			continue;
+		}
 
 		if (!(hpd[i] & hotplug_trigger) ||
 		    dev_priv->hpd_stats[i].hpd_mark != HPD_ENABLED)
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 9f5b18d..c77af69 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -827,6 +827,7 @@ enum punit_power_well {
 # define MI_FLUSH_ENABLE				(1 << 12)
 # define ASYNC_FLIP_PERF_DISABLE			(1 << 14)
 # define MODE_IDLE					(1 << 9)
+# define STOP_RING					(1 << 8)
 
 #define GEN6_GT_MODE	0x20d0
 #define GEN7_GT_MODE	0x7008
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index dae976f..69bcc42 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9654,11 +9654,22 @@ intel_pipe_config_compare(struct drm_device *dev,
 	PIPE_CONF_CHECK_I(pipe_src_w);
 	PIPE_CONF_CHECK_I(pipe_src_h);
 
-	PIPE_CONF_CHECK_I(gmch_pfit.control);
-	/* pfit ratios are autocomputed by the hw on gen4+ */
-	if (INTEL_INFO(dev)->gen < 4)
-		PIPE_CONF_CHECK_I(gmch_pfit.pgm_ratios);
-	PIPE_CONF_CHECK_I(gmch_pfit.lvds_border_bits);
+	/*
+	 * FIXME: BIOS likes to set up a cloned config with lvds+external
+	 * screen. Since we don't yet re-compute the pipe config when moving
+	 * just the lvds port away to another pipe the sw tracking won't match.
+	 *
+	 * Proper atomic modesets with recomputed global state will fix this.
+	 * Until then just don't check gmch state for inherited modes.
+	 */
+	if (!PIPE_CONF_QUIRK(PIPE_CONFIG_QUIRK_INHERITED_MODE)) {
+		PIPE_CONF_CHECK_I(gmch_pfit.control);
+		/* pfit ratios are autocomputed by the hw on gen4+ */
+		if (INTEL_INFO(dev)->gen < 4)
+			PIPE_CONF_CHECK_I(gmch_pfit.pgm_ratios);
+		PIPE_CONF_CHECK_I(gmch_pfit.lvds_border_bits);
+	}
+
 	PIPE_CONF_CHECK_I(pch_pfit.enabled);
 	if (current_config->pch_pfit.enabled) {
 		PIPE_CONF_CHECK_I(pch_pfit.pos);
@@ -11616,6 +11627,8 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 			    base.head) {
 		memset(&crtc->config, 0, sizeof(crtc->config));
 
+		crtc->config.quirks |= PIPE_CONFIG_QUIRK_INHERITED_MODE;
+
 		crtc->active = dev_priv->display.get_pipe_config(crtc,
 								 &crtc->config);
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index d2a5588..dfa8528 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -3619,7 +3619,8 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 {
 	struct drm_connector *connector = &intel_connector->base;
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct intel_encoder *intel_encoder = &intel_dig_port->base;
+	struct drm_device *dev = intel_encoder->base.dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_display_mode *fixed_mode = NULL;
 	bool has_dpcd;
@@ -3629,6 +3630,14 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	if (!is_edp(intel_dp))
 		return true;
 
+	/* The VDD bit needs a power domain reference, so if the bit is already
+	 * enabled when we boot, grab this reference. */
+	if (edp_have_panel_vdd(intel_dp)) {
+		enum intel_display_power_domain power_domain;
+		power_domain = intel_display_port_power_domain(intel_encoder);
+		intel_display_power_get(dev_priv, power_domain);
+	}
+
 	/* Cache DPCD and EDID for edp. */
 	intel_edp_panel_vdd_on(intel_dp);
 	has_dpcd = intel_dp_get_dpcd(intel_dp);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 0542de9..328b1a7 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -236,7 +236,8 @@ struct intel_crtc_config {
 	 * tracked with quirk flags so that fastboot and state checker can act
 	 * accordingly.
 	 */
-#define PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS (1<<0) /* unreliable sync mode.flags */
+#define PIPE_CONFIG_QUIRK_MODE_SYNC_FLAGS	(1<<0) /* unreliable sync mode.flags */
+#define PIPE_CONFIG_QUIRK_INHERITED_MODE	(1<<1) /* mode inherited from firmware */
 	unsigned long quirks;
 
 	/* User requested mode, only valid as a starting point to
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index b4d44e6..fce4a0d 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -132,6 +132,16 @@ static int intelfb_create(struct drm_fb_helper *helper,
 
 	mutex_lock(&dev->struct_mutex);
 
+	if (intel_fb &&
+	    (sizes->fb_width > intel_fb->base.width ||
+	     sizes->fb_height > intel_fb->base.height)) {
+		DRM_DEBUG_KMS("BIOS fb too small (%dx%d), we require (%dx%d),"
+			      " releasing it\n",
+			      intel_fb->base.width, intel_fb->base.height,
+			      sizes->fb_width, sizes->fb_height);
+		drm_framebuffer_unreference(&intel_fb->base);
+		intel_fb = ifbdev->fb = NULL;
+	}
 	if (!intel_fb || WARN_ON(!intel_fb->obj)) {
 		DRM_DEBUG_KMS("no BIOS fb, allocating a new one\n");
 		ret = intelfb_alloc(helper, sizes);
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index b0413e1..157267a 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -821,11 +821,11 @@ static void intel_disable_hdmi(struct intel_encoder *encoder)
 	}
 }
 
-static int hdmi_portclock_limit(struct intel_hdmi *hdmi)
+static int hdmi_portclock_limit(struct intel_hdmi *hdmi, bool respect_dvi_limit)
 {
 	struct drm_device *dev = intel_hdmi_to_dev(hdmi);
 
-	if (!hdmi->has_hdmi_sink || IS_G4X(dev))
+	if ((respect_dvi_limit && !hdmi->has_hdmi_sink) || IS_G4X(dev))
 		return 165000;
 	else if (IS_HASWELL(dev) || INTEL_INFO(dev)->gen >= 8)
 		return 300000;
@@ -837,7 +837,8 @@ static enum drm_mode_status
 intel_hdmi_mode_valid(struct drm_connector *connector,
 		      struct drm_display_mode *mode)
 {
-	if (mode->clock > hdmi_portclock_limit(intel_attached_hdmi(connector)))
+	if (mode->clock > hdmi_portclock_limit(intel_attached_hdmi(connector),
+					       true))
 		return MODE_CLOCK_HIGH;
 	if (mode->clock < 20000)
 		return MODE_CLOCK_LOW;
@@ -879,7 +880,7 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	struct drm_device *dev = encoder->base.dev;
 	struct drm_display_mode *adjusted_mode = &pipe_config->adjusted_mode;
 	int clock_12bpc = pipe_config->adjusted_mode.crtc_clock * 3 / 2;
-	int portclock_limit = hdmi_portclock_limit(intel_hdmi);
+	int portclock_limit = hdmi_portclock_limit(intel_hdmi, false);
 	int desired_bpp;
 
 	if (intel_hdmi->color_range_auto) {
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 6bc68bd..79fb4cc 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -437,32 +437,41 @@ static void ring_setup_phys_status_page(struct intel_ring_buffer *ring)
 	I915_WRITE(HWS_PGA, addr);
 }
 
-static int init_ring_common(struct intel_ring_buffer *ring)
+static bool stop_ring(struct intel_ring_buffer *ring)
 {
-	struct drm_device *dev = ring->dev;
-	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct drm_i915_gem_object *obj = ring->obj;
-	int ret = 0;
-	u32 head;
+	struct drm_i915_private *dev_priv = to_i915(ring->dev);
 
-	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
+	if (!IS_GEN2(ring->dev)) {
+		I915_WRITE_MODE(ring, _MASKED_BIT_ENABLE(STOP_RING));
+		if (wait_for_atomic((I915_READ_MODE(ring) & MODE_IDLE) != 0, 1000)) {
+			DRM_ERROR("%s :timed out trying to stop ring\n", ring->name);
+			return false;
+		}
+	}
 
-	/* Stop the ring if it's running. */
 	I915_WRITE_CTL(ring, 0);
 	I915_WRITE_HEAD(ring, 0);
 	ring->write_tail(ring, 0);
-	if (wait_for_atomic((I915_READ_MODE(ring) & MODE_IDLE) != 0, 1000))
-		DRM_ERROR("%s :timed out trying to stop ring\n", ring->name);
 
-	if (I915_NEED_GFX_HWS(dev))
-		intel_ring_setup_status_page(ring);
-	else
-		ring_setup_phys_status_page(ring);
+	if (!IS_GEN2(ring->dev)) {
+		(void)I915_READ_CTL(ring);
+		I915_WRITE_MODE(ring, _MASKED_BIT_DISABLE(STOP_RING));
+	}
 
-	head = I915_READ_HEAD(ring) & HEAD_ADDR;
+	return (I915_READ_HEAD(ring) & HEAD_ADDR) == 0;
+}
 
-	/* G45 ring initialization fails to reset head to zero */
-	if (head != 0) {
+static int init_ring_common(struct intel_ring_buffer *ring)
+{
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_i915_gem_object *obj = ring->obj;
+	int ret = 0;
+
+	gen6_gt_force_wake_get(dev_priv, FORCEWAKE_ALL);
+
+	if (!stop_ring(ring)) {
+		/* G45 ring initialization often fails to reset head to zero */
 		DRM_DEBUG_KMS("%s head not reset to zero "
 			      "ctl %08x head %08x tail %08x start %08x\n",
 			      ring->name,
@@ -471,9 +480,7 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 			      I915_READ_TAIL(ring),
 			      I915_READ_START(ring));
 
-		I915_WRITE_HEAD(ring, 0);
-
-		if (I915_READ_HEAD(ring) & HEAD_ADDR) {
+		if (!stop_ring(ring)) {
 			DRM_ERROR("failed to set %s head to zero "
 				  "ctl %08x head %08x tail %08x start %08x\n",
 				  ring->name,
@@ -481,9 +488,16 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 				  I915_READ_HEAD(ring),
 				  I915_READ_TAIL(ring),
 				  I915_READ_START(ring));
+			ret = -EIO;
+			goto out;
 		}
 	}
 
+	if (I915_NEED_GFX_HWS(dev))
+		intel_ring_setup_status_page(ring);
+	else
+		ring_setup_phys_status_page(ring);
+
 	/* Initialize the ring. This must happen _after_ we've cleared the ring
 	 * registers with the above sequence (the readback of the HEAD registers
 	 * also enforces ordering), otherwise the hw might lose the new ring
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 270a6a9..2b91c4b 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -34,6 +34,7 @@ struct  intel_hw_status_page {
 #define I915_WRITE_IMR(ring, val) I915_WRITE(RING_IMR((ring)->mmio_base), val)
 
 #define I915_READ_MODE(ring) I915_READ(RING_MI_MODE((ring)->mmio_base))
+#define I915_WRITE_MODE(ring, val) I915_WRITE(RING_MI_MODE((ring)->mmio_base), val)
 
 enum intel_ring_hangcheck_action {
 	HANGCHECK_IDLE = 0,
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
index 3e6c0f3..ef9957d 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_crtc.c
@@ -510,9 +510,8 @@ static void update_cursor(struct drm_crtc *crtc)
 					MDP4_DMA_CURSOR_BLEND_CONFIG_CURSOR_EN);
 		} else {
 			/* disable cursor: */
-			mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_BASE(dma), 0);
-			mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_BLEND_CONFIG(dma),
-					MDP4_DMA_CURSOR_BLEND_CONFIG_FORMAT(CURSOR_ARGB));
+			mdp4_write(mdp4_kms, REG_MDP4_DMA_CURSOR_BASE(dma),
+					mdp4_kms->blank_cursor_iova);
 		}
 
 		/* and drop the iova ref + obj rev when done scanning out: */
@@ -574,11 +573,9 @@ static int mdp4_crtc_cursor_set(struct drm_crtc *crtc,
 
 	if (old_bo) {
 		/* drop our previous reference: */
-		msm_gem_put_iova(old_bo, mdp4_kms->id);
-		drm_gem_object_unreference_unlocked(old_bo);
+		drm_flip_work_queue(&mdp4_crtc->unref_cursor_work, old_bo);
 	}
 
-	crtc_flush(crtc);
 	request_pending(crtc, PENDING_CURSOR);
 
 	return 0;
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c
index c740ccd..8edd531c 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_irq.c
@@ -70,12 +70,12 @@ irqreturn_t mdp4_irq(struct msm_kms *kms)
 
 	VERB("status=%08x", status);
 
+	mdp_dispatch_irqs(mdp_kms, status);
+
 	for (id = 0; id < priv->num_crtcs; id++)
 		if (status & mdp4_crtc_vblank(priv->crtcs[id]))
 			drm_handle_vblank(dev, id);
 
-	mdp_dispatch_irqs(mdp_kms, status);
-
 	return IRQ_HANDLED;
 }
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c
index 272e707..0bb4faa 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.c
@@ -144,6 +144,10 @@ static void mdp4_preclose(struct msm_kms *kms, struct drm_file *file)
 static void mdp4_destroy(struct msm_kms *kms)
 {
 	struct mdp4_kms *mdp4_kms = to_mdp4_kms(to_mdp_kms(kms));
+	if (mdp4_kms->blank_cursor_iova)
+		msm_gem_put_iova(mdp4_kms->blank_cursor_bo, mdp4_kms->id);
+	if (mdp4_kms->blank_cursor_bo)
+		drm_gem_object_unreference(mdp4_kms->blank_cursor_bo);
 	kfree(mdp4_kms);
 }
 
@@ -372,6 +376,23 @@ struct msm_kms *mdp4_kms_init(struct drm_device *dev)
 		goto fail;
 	}
 
+	mutex_lock(&dev->struct_mutex);
+	mdp4_kms->blank_cursor_bo = msm_gem_new(dev, SZ_16K, MSM_BO_WC);
+	mutex_unlock(&dev->struct_mutex);
+	if (IS_ERR(mdp4_kms->blank_cursor_bo)) {
+		ret = PTR_ERR(mdp4_kms->blank_cursor_bo);
+		dev_err(dev->dev, "could not allocate blank-cursor bo: %d\n", ret);
+		mdp4_kms->blank_cursor_bo = NULL;
+		goto fail;
+	}
+
+	ret = msm_gem_get_iova(mdp4_kms->blank_cursor_bo, mdp4_kms->id,
+			&mdp4_kms->blank_cursor_iova);
+	if (ret) {
+		dev_err(dev->dev, "could not pin blank-cursor bo: %d\n", ret);
+		goto fail;
+	}
+
 	return kms;
 
 fail:
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h
index 66a4d31..715520c5 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_kms.h
@@ -44,6 +44,10 @@ struct mdp4_kms {
 	struct clk *lut_clk;
 
 	struct mdp_irq error_handler;
+
+	/* empty/blank cursor bo to use when cursor is "disabled" */
+	struct drm_gem_object *blank_cursor_bo;
+	uint32_t blank_cursor_iova;
 };
 #define to_mdp4_kms(x) container_of(x, struct mdp4_kms, base)
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c
index 353d494..f2b985b 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c
@@ -71,11 +71,11 @@ static void mdp5_irq_mdp(struct mdp_kms *mdp_kms)
 
 	VERB("status=%08x", status);
 
+	mdp_dispatch_irqs(mdp_kms, status);
+
 	for (id = 0; id < priv->num_crtcs; id++)
 		if (status & mdp5_crtc_vblank(priv->crtcs[id]))
 			drm_handle_vblank(dev, id);
-
-	mdp_dispatch_irqs(mdp_kms, status);
 }
 
 irqreturn_t mdp5_irq(struct msm_kms *kms)
diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c
index 6c6d7d4..a752ab8 100644
--- a/drivers/gpu/drm/msm/msm_fbdev.c
+++ b/drivers/gpu/drm/msm/msm_fbdev.c
@@ -62,11 +62,8 @@ static int msm_fbdev_create(struct drm_fb_helper *helper,
 	dma_addr_t paddr;
 	int ret, size;
 
-	/* only doing ARGB32 since this is what is needed to alpha-blend
-	 * with video overlays:
-	 */
 	sizes->surface_bpp = 32;
-	sizes->surface_depth = 32;
+	sizes->surface_depth = 24;
 
 	DBG("create fbdev: %dx%d@%d (%dx%d)", sizes->surface_width,
 			sizes->surface_height, sizes->surface_bpp,
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 3da8264..bb8026d 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -118,8 +118,10 @@ static void put_pages(struct drm_gem_object *obj)
 
 		if (iommu_present(&platform_bus_type))
 			drm_gem_put_pages(obj, msm_obj->pages, true, false);
-		else
+		else {
 			drm_mm_remove_node(msm_obj->vram_node);
+			drm_free_large(msm_obj->pages);
+		}
 
 		msm_obj->pages = NULL;
 	}
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index 36c717a..edb871d 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -312,7 +312,7 @@ static void tegra_crtc_disable(struct drm_crtc *crtc)
 	struct drm_device *drm = crtc->dev;
 	struct drm_plane *plane;
 
-	list_for_each_entry(plane, &drm->mode_config.plane_list, head) {
+	drm_for_each_legacy_plane(plane, &drm->mode_config.plane_list) {
 		if (plane->crtc == crtc) {
 			tegra_plane_disable(plane);
 			plane->crtc = NULL;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 931490b..87df0b3 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -1214,14 +1214,36 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 		SVGA3dCmdSurfaceDMA dma;
 	} *cmd;
 	int ret;
+	SVGA3dCmdSurfaceDMASuffix *suffix;
+	uint32_t bo_size;
 
 	cmd = container_of(header, struct vmw_dma_cmd, header);
+	suffix = (SVGA3dCmdSurfaceDMASuffix *)((unsigned long) &cmd->dma +
+					       header->size - sizeof(*suffix));
+
+	/* Make sure device and verifier stays in sync. */
+	if (unlikely(suffix->suffixSize != sizeof(*suffix))) {
+		DRM_ERROR("Invalid DMA suffix size.\n");
+		return -EINVAL;
+	}
+
 	ret = vmw_translate_guest_ptr(dev_priv, sw_context,
 				      &cmd->dma.guest.ptr,
 				      &vmw_bo);
 	if (unlikely(ret != 0))
 		return ret;
 
+	/* Make sure DMA doesn't cross BO boundaries. */
+	bo_size = vmw_bo->base.num_pages * PAGE_SIZE;
+	if (unlikely(cmd->dma.guest.ptr.offset > bo_size)) {
+		DRM_ERROR("Invalid DMA offset.\n");
+		return -EINVAL;
+	}
+
+	bo_size -= cmd->dma.guest.ptr.offset;
+	if (unlikely(suffix->maximumOffset > bo_size))
+		suffix->maximumOffset = bo_size;
+
 	ret = vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
 				user_surface_converter, &cmd->dma.host.sid,
 				NULL);
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index 6d02e3b..d76f0b7 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -365,12 +365,12 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 		if (cpu_has_tjmax(c))
 			dev_warn(dev, "Unable to read TjMax from CPU %u\n", id);
 	} else {
-		val = (eax >> 16) & 0x7f;
+		val = (eax >> 16) & 0xff;
 		/*
 		 * If the TjMax is not plausible, an assumption
 		 * will be used
 		 */
-		if (val >= 85) {
+		if (val) {
 			dev_dbg(dev, "TjMax is %d degrees C\n", val);
 			return val * 1000;
 		}
diff --git a/drivers/infiniband/hw/cxgb4/Kconfig b/drivers/infiniband/hw/cxgb4/Kconfig
index d4e8983..23f38cf 100644
--- a/drivers/infiniband/hw/cxgb4/Kconfig
+++ b/drivers/infiniband/hw/cxgb4/Kconfig
@@ -1,10 +1,10 @@
 config INFINIBAND_CXGB4
-	tristate "Chelsio T4 RDMA Driver"
+	tristate "Chelsio T4/T5 RDMA Driver"
 	depends on CHELSIO_T4 && INET && (IPV6 || IPV6=n)
 	select GENERIC_ALLOCATOR
 	---help---
-	  This is an iWARP/RDMA driver for the Chelsio T4 1GbE and
-	  10GbE adapters.
+	  This is an iWARP/RDMA driver for the Chelsio T4 and T5
+	  1GbE, 10GbE adapters and T5 40GbE adapter.
 
 	  For general information about Chelsio and our products, visit
 	  our website at <http://www.chelsio.com>.
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 185452a..1f863a9 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -587,6 +587,10 @@ static int send_connect(struct c4iw_ep *ep)
 		opt2 |= SACK_EN(1);
 	if (wscale && enable_tcp_window_scaling)
 		opt2 |= WND_SCALE_EN(1);
+	if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
+		opt2 |= T5_OPT_2_VALID;
+		opt2 |= V_CONG_CNTRL(CONG_ALG_TAHOE);
+	}
 	t4_set_arp_err_handler(skb, NULL, act_open_req_arp_failure);
 
 	if (is_t4(ep->com.dev->rdev.lldi.adapter_type)) {
@@ -996,7 +1000,7 @@ static void close_complete_upcall(struct c4iw_ep *ep, int status)
 static int abort_connection(struct c4iw_ep *ep, struct sk_buff *skb, gfp_t gfp)
 {
 	PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
-	state_set(&ep->com, ABORTING);
+	__state_set(&ep->com, ABORTING);
 	set_bit(ABORT_CONN, &ep->com.history);
 	return send_abort(ep, skb, gfp);
 }
@@ -1154,7 +1158,7 @@ static int update_rx_credits(struct c4iw_ep *ep, u32 credits)
 	return credits;
 }
 
-static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
+static int process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
 {
 	struct mpa_message *mpa;
 	struct mpa_v2_conn_params *mpa_v2_params;
@@ -1164,6 +1168,7 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
 	struct c4iw_qp_attributes attrs;
 	enum c4iw_qp_attr_mask mask;
 	int err;
+	int disconnect = 0;
 
 	PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
 
@@ -1173,7 +1178,7 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
 	 * will abort the connection.
 	 */
 	if (stop_ep_timer(ep))
-		return;
+		return 0;
 
 	/*
 	 * If we get more than the supported amount of private data
@@ -1195,7 +1200,7 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
 	 * if we don't even have the mpa message, then bail.
 	 */
 	if (ep->mpa_pkt_len < sizeof(*mpa))
-		return;
+		return 0;
 	mpa = (struct mpa_message *) ep->mpa_pkt;
 
 	/* Validate MPA header. */
@@ -1235,7 +1240,7 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
 	 * We'll continue process when more data arrives.
 	 */
 	if (ep->mpa_pkt_len < (sizeof(*mpa) + plen))
-		return;
+		return 0;
 
 	if (mpa->flags & MPA_REJECT) {
 		err = -ECONNREFUSED;
@@ -1337,9 +1342,11 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
 		attrs.layer_etype = LAYER_MPA | DDP_LLP;
 		attrs.ecode = MPA_NOMATCH_RTR;
 		attrs.next_state = C4IW_QP_STATE_TERMINATE;
+		attrs.send_term = 1;
 		err = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
-				C4IW_QP_ATTR_NEXT_STATE, &attrs, 0);
+				C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
 		err = -ENOMEM;
+		disconnect = 1;
 		goto out;
 	}
 
@@ -1355,9 +1362,11 @@ static void process_mpa_reply(struct c4iw_ep *ep, struct sk_buff *skb)
 		attrs.layer_etype = LAYER_MPA | DDP_LLP;
 		attrs.ecode = MPA_INSUFF_IRD;
 		attrs.next_state = C4IW_QP_STATE_TERMINATE;
+		attrs.send_term = 1;
 		err = c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
-				C4IW_QP_ATTR_NEXT_STATE, &attrs, 0);
+				C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
 		err = -ENOMEM;
+		disconnect = 1;
 		goto out;
 	}
 	goto out;
@@ -1366,7 +1375,7 @@ err:
 	send_abort(ep, skb, GFP_KERNEL);
 out:
 	connect_reply_upcall(ep, err);
-	return;
+	return disconnect;
 }
 
 static void process_mpa_request(struct c4iw_ep *ep, struct sk_buff *skb)
@@ -1524,6 +1533,7 @@ static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb)
 	unsigned int tid = GET_TID(hdr);
 	struct tid_info *t = dev->rdev.lldi.tids;
 	__u8 status = hdr->status;
+	int disconnect = 0;
 
 	ep = lookup_tid(t, tid);
 	if (!ep)
@@ -1539,7 +1549,7 @@ static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb)
 	switch (ep->com.state) {
 	case MPA_REQ_SENT:
 		ep->rcv_seq += dlen;
-		process_mpa_reply(ep, skb);
+		disconnect = process_mpa_reply(ep, skb);
 		break;
 	case MPA_REQ_WAIT:
 		ep->rcv_seq += dlen;
@@ -1555,13 +1565,16 @@ static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb)
 			       ep->com.state, ep->hwtid, status);
 		attrs.next_state = C4IW_QP_STATE_TERMINATE;
 		c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
-			       C4IW_QP_ATTR_NEXT_STATE, &attrs, 0);
+			       C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
+		disconnect = 1;
 		break;
 	}
 	default:
 		break;
 	}
 	mutex_unlock(&ep->com.mutex);
+	if (disconnect)
+		c4iw_ep_disconnect(ep, 0, GFP_KERNEL);
 	return 0;
 }
 
@@ -2009,6 +2022,10 @@ static void accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
 		if (tcph->ece && tcph->cwr)
 			opt2 |= CCTRL_ECN(1);
 	}
+	if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
+		opt2 |= T5_OPT_2_VALID;
+		opt2 |= V_CONG_CNTRL(CONG_ALG_TAHOE);
+	}
 
 	rpl = cplhdr(skb);
 	INIT_TP_WR(rpl, ep->hwtid);
@@ -3482,9 +3499,9 @@ static void process_timeout(struct c4iw_ep *ep)
 			__func__, ep, ep->hwtid, ep->com.state);
 		abort = 0;
 	}
-	mutex_unlock(&ep->com.mutex);
 	if (abort)
 		abort_connection(ep, NULL, GFP_KERNEL);
+	mutex_unlock(&ep->com.mutex);
 	c4iw_put_ep(&ep->com);
 }
 
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index 7b8c580..7474b49 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -435,6 +435,7 @@ struct c4iw_qp_attributes {
 	u8 ecode;
 	u16 sq_db_inc;
 	u16 rq_db_inc;
+	u8 send_term;
 };
 
 struct c4iw_qp {
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 7b5114c..086f62f 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -1388,11 +1388,12 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 			qhp->attr.layer_etype = attrs->layer_etype;
 			qhp->attr.ecode = attrs->ecode;
 			ep = qhp->ep;
-			disconnect = 1;
-			c4iw_get_ep(&qhp->ep->com);
-			if (!internal)
+			if (!internal) {
+				c4iw_get_ep(&qhp->ep->com);
 				terminate = 1;
-			else {
+				disconnect = 1;
+			} else {
+				terminate = qhp->attr.send_term;
 				ret = rdma_fini(rhp, qhp, ep);
 				if (ret)
 					goto err;
@@ -1776,11 +1777,15 @@ int c4iw_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	/*
 	 * Use SQ_PSN and RQ_PSN to pass in IDX_INC values for
 	 * ringing the queue db when we're in DB_FULL mode.
+	 * Only allow this on T4 devices.
 	 */
 	attrs.sq_db_inc = attr->sq_psn;
 	attrs.rq_db_inc = attr->rq_psn;
 	mask |= (attr_mask & IB_QP_SQ_PSN) ? C4IW_QP_ATTR_SQ_DB : 0;
 	mask |= (attr_mask & IB_QP_RQ_PSN) ? C4IW_QP_ATTR_RQ_DB : 0;
+	if (is_t5(to_c4iw_qp(ibqp)->rhp->rdev.lldi.adapter_type) &&
+	    (mask & (C4IW_QP_ATTR_SQ_DB|C4IW_QP_ATTR_RQ_DB)))
+		return -EINVAL;
 
 	return c4iw_modify_qp(rhp, qhp, mask, &attrs, 0);
 }
diff --git a/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h b/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
index dc193c2..6121ca0 100644
--- a/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
+++ b/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
@@ -836,4 +836,18 @@ struct ulptx_idata {
 #define V_RX_DACK_CHANGE(x) ((x) << S_RX_DACK_CHANGE)
 #define F_RX_DACK_CHANGE    V_RX_DACK_CHANGE(1U)
 
+enum {                     /* TCP congestion control algorithms */
+	CONG_ALG_RENO,
+	CONG_ALG_TAHOE,
+	CONG_ALG_NEWRENO,
+	CONG_ALG_HIGHSPEED
+};
+
+#define S_CONG_CNTRL    14
+#define M_CONG_CNTRL    0x3
+#define V_CONG_CNTRL(x) ((x) << S_CONG_CNTRL)
+#define G_CONG_CNTRL(x) (((x) >> S_CONG_CNTRL) & M_CONG_CNTRL)
+
+#define T5_OPT_2_VALID       (1 << 31)
+
 #endif /* _T4FW_RI_API_H_ */
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 41be897..3899ba7 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -41,6 +41,7 @@
 #define ARMADA_370_XP_INT_SET_ENABLE_OFFS	(0x30)
 #define ARMADA_370_XP_INT_CLEAR_ENABLE_OFFS	(0x34)
 #define ARMADA_370_XP_INT_SOURCE_CTL(irq)	(0x100 + irq*4)
+#define ARMADA_370_XP_INT_SOURCE_CPU_MASK	0xF
 
 #define ARMADA_370_XP_CPU_INTACK_OFFS		(0x44)
 #define ARMADA_375_PPI_CAUSE			(0x10)
@@ -132,8 +133,7 @@ static int armada_370_xp_setup_msi_irq(struct msi_chip *chip,
 				       struct msi_desc *desc)
 {
 	struct msi_msg msg;
-	irq_hw_number_t hwirq;
-	int virq;
+	int virq, hwirq;
 
 	hwirq = armada_370_xp_alloc_msi();
 	if (hwirq < 0)
@@ -159,8 +159,19 @@ static void armada_370_xp_teardown_msi_irq(struct msi_chip *chip,
 					   unsigned int irq)
 {
 	struct irq_data *d = irq_get_irq_data(irq);
+	unsigned long hwirq = d->hwirq;
+
 	irq_dispose_mapping(irq);
-	armada_370_xp_free_msi(d->hwirq);
+	armada_370_xp_free_msi(hwirq);
+}
+
+static int armada_370_xp_check_msi_device(struct msi_chip *chip, struct pci_dev *dev,
+					  int nvec, int type)
+{
+	/* We support MSI, but not MSI-X */
+	if (type == PCI_CAP_ID_MSI)
+		return 0;
+	return -EINVAL;
 }
 
 static struct irq_chip armada_370_xp_msi_irq_chip = {
@@ -201,6 +212,7 @@ static int armada_370_xp_msi_init(struct device_node *node,
 
 	msi_chip->setup_irq = armada_370_xp_setup_msi_irq;
 	msi_chip->teardown_irq = armada_370_xp_teardown_msi_irq;
+	msi_chip->check_device = armada_370_xp_check_msi_device;
 	msi_chip->of_node = node;
 
 	armada_370_xp_msi_domain =
@@ -244,35 +256,18 @@ static DEFINE_RAW_SPINLOCK(irq_controller_lock);
 static int armada_xp_set_affinity(struct irq_data *d,
 				  const struct cpumask *mask_val, bool force)
 {
-	unsigned long reg;
-	unsigned long new_mask = 0;
-	unsigned long online_mask = 0;
-	unsigned long count = 0;
 	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	unsigned long reg, mask;
 	int cpu;
 
-	for_each_cpu(cpu, mask_val) {
-		new_mask |= 1 << cpu_logical_map(cpu);
-		count++;
-	}
-
-	/*
-	 * Forbid mutlicore interrupt affinity
-	 * This is required since the MPIC HW doesn't limit
-	 * several CPUs from acknowledging the same interrupt.
-	 */
-	if (count > 1)
-		return -EINVAL;
-
-	for_each_cpu(cpu, cpu_online_mask)
-		online_mask |= 1 << cpu_logical_map(cpu);
+	/* Select a single core from the affinity mask which is online */
+	cpu = cpumask_any_and(mask_val, cpu_online_mask);
+	mask = 1UL << cpu_logical_map(cpu);
 
 	raw_spin_lock(&irq_controller_lock);
-
 	reg = readl(main_int_base + ARMADA_370_XP_INT_SOURCE_CTL(hwirq));
-	reg = (reg & (~online_mask)) | new_mask;
+	reg = (reg & (~ARMADA_370_XP_INT_SOURCE_CPU_MASK)) | mask;
 	writel(reg, main_int_base + ARMADA_370_XP_INT_SOURCE_CTL(hwirq));
-
 	raw_spin_unlock(&irq_controller_lock);
 
 	return 0;
@@ -494,15 +489,6 @@ static int __init armada_370_xp_mpic_of_init(struct device_node *node,
 
 #ifdef CONFIG_SMP
 	armada_xp_mpic_smp_cpu_init();
-
-	/*
-	 * Set the default affinity from all CPUs to the boot cpu.
-	 * This is required since the MPIC doesn't limit several CPUs
-	 * from acknowledging the same interrupt.
-	 */
-	cpumask_clear(irq_default_affinity);
-	cpumask_set_cpu(smp_processor_id(), irq_default_affinity);
-
 #endif
 
 	armada_370_xp_msi_init(node, main_int_res.start);
diff --git a/drivers/irqchip/irq-crossbar.c b/drivers/irqchip/irq-crossbar.c
index fc817d2..3d15d16 100644
--- a/drivers/irqchip/irq-crossbar.c
+++ b/drivers/irqchip/irq-crossbar.c
@@ -107,7 +107,7 @@ static int __init crossbar_of_init(struct device_node *node)
 	int i, size, max, reserved = 0, entry;
 	const __be32 *irqsr;
 
-	cb = kzalloc(sizeof(struct cb_device *), GFP_KERNEL);
+	cb = kzalloc(sizeof(*cb), GFP_KERNEL);
 
 	if (!cb)
 		return -ENOMEM;
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index 1bf4a71..9380be7 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -2488,6 +2488,7 @@ static int cache_map(struct dm_target *ti, struct bio *bio)
 
 		} else {
 			inc_hit_counter(cache, bio);
+			pb->all_io_entry = dm_deferred_entry_inc(cache->all_io_ds);
 
 			if (bio_data_dir(bio) == WRITE && writethrough_mode(&cache->features) &&
 			    !is_dirty(cache, lookup_result.cblock))
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 53728be..13abade 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -232,6 +232,13 @@ struct thin_c {
 	struct bio_list deferred_bio_list;
 	struct bio_list retry_on_resume_list;
 	struct rb_root sort_bio_list; /* sorted list of deferred bios */
+
+	/*
+	 * Ensures the thin is not destroyed until the worker has finished
+	 * iterating the active_thins list.
+	 */
+	atomic_t refcount;
+	struct completion can_destroy;
 };
 
 /*----------------------------------------------------------------*/
@@ -1486,6 +1493,45 @@ static void process_thin_deferred_bios(struct thin_c *tc)
 	blk_finish_plug(&plug);
 }
 
+static void thin_get(struct thin_c *tc);
+static void thin_put(struct thin_c *tc);
+
+/*
+ * We can't hold rcu_read_lock() around code that can block.  So we
+ * find a thin with the rcu lock held; bump a refcount; then drop
+ * the lock.
+ */
+static struct thin_c *get_first_thin(struct pool *pool)
+{
+	struct thin_c *tc = NULL;
+
+	rcu_read_lock();
+	if (!list_empty(&pool->active_thins)) {
+		tc = list_entry_rcu(pool->active_thins.next, struct thin_c, list);
+		thin_get(tc);
+	}
+	rcu_read_unlock();
+
+	return tc;
+}
+
+static struct thin_c *get_next_thin(struct pool *pool, struct thin_c *tc)
+{
+	struct thin_c *old_tc = tc;
+
+	rcu_read_lock();
+	list_for_each_entry_continue_rcu(tc, &pool->active_thins, list) {
+		thin_get(tc);
+		thin_put(old_tc);
+		rcu_read_unlock();
+		return tc;
+	}
+	thin_put(old_tc);
+	rcu_read_unlock();
+
+	return NULL;
+}
+
 static void process_deferred_bios(struct pool *pool)
 {
 	unsigned long flags;
@@ -1493,10 +1539,11 @@ static void process_deferred_bios(struct pool *pool)
 	struct bio_list bios;
 	struct thin_c *tc;
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(tc, &pool->active_thins, list)
+	tc = get_first_thin(pool);
+	while (tc) {
 		process_thin_deferred_bios(tc);
-	rcu_read_unlock();
+		tc = get_next_thin(pool, tc);
+	}
 
 	/*
 	 * If there are any deferred flush bios, we must commit
@@ -1578,7 +1625,7 @@ static void noflush_work(struct thin_c *tc, void (*fn)(struct work_struct *))
 {
 	struct noflush_work w;
 
-	INIT_WORK(&w.worker, fn);
+	INIT_WORK_ONSTACK(&w.worker, fn);
 	w.tc = tc;
 	atomic_set(&w.complete, 0);
 	init_waitqueue_head(&w.wait);
@@ -3061,11 +3108,25 @@ static struct target_type pool_target = {
 /*----------------------------------------------------------------
  * Thin target methods
  *--------------------------------------------------------------*/
+static void thin_get(struct thin_c *tc)
+{
+	atomic_inc(&tc->refcount);
+}
+
+static void thin_put(struct thin_c *tc)
+{
+	if (atomic_dec_and_test(&tc->refcount))
+		complete(&tc->can_destroy);
+}
+
 static void thin_dtr(struct dm_target *ti)
 {
 	struct thin_c *tc = ti->private;
 	unsigned long flags;
 
+	thin_put(tc);
+	wait_for_completion(&tc->can_destroy);
+
 	spin_lock_irqsave(&tc->pool->lock, flags);
 	list_del_rcu(&tc->list);
 	spin_unlock_irqrestore(&tc->pool->lock, flags);
@@ -3101,6 +3162,7 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 	struct thin_c *tc;
 	struct dm_dev *pool_dev, *origin_dev;
 	struct mapped_device *pool_md;
+	unsigned long flags;
 
 	mutex_lock(&dm_thin_pool_table.mutex);
 
@@ -3191,9 +3253,12 @@ static int thin_ctr(struct dm_target *ti, unsigned argc, char **argv)
 
 	mutex_unlock(&dm_thin_pool_table.mutex);
 
-	spin_lock(&tc->pool->lock);
+	atomic_set(&tc->refcount, 1);
+	init_completion(&tc->can_destroy);
+
+	spin_lock_irqsave(&tc->pool->lock, flags);
 	list_add_tail_rcu(&tc->list, &tc->pool->active_thins);
-	spin_unlock(&tc->pool->lock);
+	spin_unlock_irqrestore(&tc->pool->lock, flags);
 	/*
 	 * This synchronize_rcu() call is needed here otherwise we risk a
 	 * wake_worker() call finding no bios to process (because the newly
diff --git a/drivers/md/dm-verity.c b/drivers/md/dm-verity.c
index 796007a..7a7bab8 100644
--- a/drivers/md/dm-verity.c
+++ b/drivers/md/dm-verity.c
@@ -330,15 +330,17 @@ test_block_hash:
 				return r;
 			}
 		}
-
 		todo = 1 << v->data_dev_block_bits;
-		while (io->iter.bi_size) {
+		do {
 			u8 *page;
+			unsigned len;
 			struct bio_vec bv = bio_iter_iovec(bio, io->iter);
 
 			page = kmap_atomic(bv.bv_page);
-			r = crypto_shash_update(desc, page + bv.bv_offset,
-						bv.bv_len);
+			len = bv.bv_len;
+			if (likely(len >= todo))
+				len = todo;
+			r = crypto_shash_update(desc, page + bv.bv_offset, len);
 			kunmap_atomic(page);
 
 			if (r < 0) {
@@ -346,8 +348,9 @@ test_block_hash:
 				return r;
 			}
 
-			bio_advance_iter(bio, &io->iter, bv.bv_len);
-		}
+			bio_advance_iter(bio, &io->iter, len);
+			todo -= len;
+		} while (todo);
 
 		if (!v->version) {
 			r = crypto_shash_update(desc, v->salt, v->salt_size);
diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index 9bcf2cf..5aeb894 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -364,7 +364,7 @@ int of_irq_to_resource(struct device_node *dev, int index, struct resource *r)
 
 		memset(r, 0, sizeof(*r));
 		/*
-		 * Get optional "interrupts-names" property to add a name
+		 * Get optional "interrupt-names" property to add a name
 		 * to the resource.
 		 */
 		of_property_read_string_index(dev, "interrupt-names", index,
@@ -380,6 +380,32 @@ int of_irq_to_resource(struct device_node *dev, int index, struct resource *r)
 EXPORT_SYMBOL_GPL(of_irq_to_resource);
 
 /**
+ * of_irq_get - Decode a node's IRQ and return it as a Linux irq number
+ * @dev: pointer to device tree node
+ * @index: zero-based index of the irq
+ *
+ * Returns Linux irq number on success, or -EPROBE_DEFER if the irq domain
+ * is not yet created.
+ *
+ */
+int of_irq_get(struct device_node *dev, int index)
+{
+	int rc;
+	struct of_phandle_args oirq;
+	struct irq_domain *domain;
+
+	rc = of_irq_parse_one(dev, index, &oirq);
+	if (rc)
+		return rc;
+
+	domain = irq_find_host(oirq.np);
+	if (!domain)
+		return -EPROBE_DEFER;
+
+	return irq_create_of_mapping(&oirq);
+}
+
+/**
  * of_irq_count - Count the number of IRQs a node uses
  * @dev: pointer to device tree node
  */
diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 404d1da..bd47fbc 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -168,7 +168,9 @@ struct platform_device *of_device_alloc(struct device_node *np,
 			rc = of_address_to_resource(np, i, res);
 			WARN_ON(rc);
 		}
-		WARN_ON(of_irq_to_resource_table(np, res, num_irq) != num_irq);
+		if (of_irq_to_resource_table(np, res, num_irq) != num_irq)
+			pr_debug("not all legacy IRQ resources mapped for %s\n",
+				 np->name);
 	}
 
 	dev->dev.of_node = of_node_get(np);
diff --git a/drivers/of/selftest.c b/drivers/of/selftest.c
index ae44500..fe70b86 100644
--- a/drivers/of/selftest.c
+++ b/drivers/of/selftest.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_irq.h>
+#include <linux/of_platform.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
@@ -427,6 +428,36 @@ static void __init of_selftest_match_node(void)
 	}
 }
 
+static void __init of_selftest_platform_populate(void)
+{
+	int irq;
+	struct device_node *np;
+	struct platform_device *pdev;
+
+	np = of_find_node_by_path("/testcase-data");
+	of_platform_populate(np, of_default_bus_match_table, NULL, NULL);
+
+	/* Test that a missing irq domain returns -EPROBE_DEFER */
+	np = of_find_node_by_path("/testcase-data/testcase-device1");
+	pdev = of_find_device_by_node(np);
+	if (!pdev)
+		selftest(0, "device 1 creation failed\n");
+	irq = platform_get_irq(pdev, 0);
+	if (irq != -EPROBE_DEFER)
+		selftest(0, "device deferred probe failed - %d\n", irq);
+
+	/* Test that a parsing failure does not return -EPROBE_DEFER */
+	np = of_find_node_by_path("/testcase-data/testcase-device2");
+	pdev = of_find_device_by_node(np);
+	if (!pdev)
+		selftest(0, "device 2 creation failed\n");
+	irq = platform_get_irq(pdev, 0);
+	if (irq >= 0 || irq == -EPROBE_DEFER)
+		selftest(0, "device parsing error failed - %d\n", irq);
+
+	selftest(1, "passed");
+}
+
 static int __init of_selftest(void)
 {
 	struct device_node *np;
@@ -445,6 +476,7 @@ static int __init of_selftest(void)
 	of_selftest_parse_interrupts();
 	of_selftest_parse_interrupts_extended();
 	of_selftest_match_node();
+	of_selftest_platform_populate();
 	pr_info("end of selftest - %i passed, %i failed\n",
 		selftest_results.passed, selftest_results.failed);
 	return 0;
diff --git a/drivers/of/testcase-data/tests-interrupts.dtsi b/drivers/of/testcase-data/tests-interrupts.dtsi
index c843720..da4695f 100644
--- a/drivers/of/testcase-data/tests-interrupts.dtsi
+++ b/drivers/of/testcase-data/tests-interrupts.dtsi
@@ -54,5 +54,18 @@
 						      <&test_intmap1 1 2>;
 			};
 		};
+
+		testcase-device1 {
+			compatible = "testcase-device";
+			interrupt-parent = <&test_intc0>;
+			interrupts = <1>;
+		};
+
+		testcase-device2 {
+			compatible = "testcase-device";
+			interrupt-parent = <&test_intc2>;
+			interrupts = <1>; /* invalid specifier - too short */
+		};
 	};
+
 };
diff --git a/drivers/pinctrl/pinctrl-as3722.c b/drivers/pinctrl/pinctrl-as3722.c
index 92ed4b2..c862f9c0 100644
--- a/drivers/pinctrl/pinctrl-as3722.c
+++ b/drivers/pinctrl/pinctrl-as3722.c
@@ -64,7 +64,6 @@ struct as3722_pin_function {
 };
 
 struct as3722_gpio_pin_control {
-	bool enable_gpio_invert;
 	unsigned mode_prop;
 	int io_function;
 };
@@ -320,10 +319,8 @@ static int as3722_pinctrl_gpio_set_direction(struct pinctrl_dev *pctldev,
 		return mode;
 	}
 
-	if (as_pci->gpio_control[offset].enable_gpio_invert)
-		mode |= AS3722_GPIO_INV;
-
-	return as3722_write(as3722, AS3722_GPIOn_CONTROL_REG(offset), mode);
+	return as3722_update_bits(as3722, AS3722_GPIOn_CONTROL_REG(offset),
+				AS3722_GPIO_MODE_MASK, mode);
 }
 
 static const struct pinmux_ops as3722_pinmux_ops = {
@@ -496,10 +493,18 @@ static void as3722_gpio_set(struct gpio_chip *chip, unsigned offset,
 {
 	struct as3722_pctrl_info *as_pci = to_as_pci(chip);
 	struct as3722 *as3722 = as_pci->as3722;
-	int en_invert = as_pci->gpio_control[offset].enable_gpio_invert;
+	int en_invert;
 	u32 val;
 	int ret;
 
+	ret = as3722_read(as3722, AS3722_GPIOn_CONTROL_REG(offset), &val);
+	if (ret < 0) {
+		dev_err(as_pci->dev,
+			"GPIO_CONTROL%d_REG read failed: %d\n", offset, ret);
+		return;
+	}
+	en_invert = !!(val & AS3722_GPIO_INV);
+
 	if (value)
 		val = (en_invert) ? 0 : AS3722_GPIOn_SIGNAL(offset);
 	else
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index 81075f2..2960557 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -810,6 +810,7 @@ static const struct pinconf_ops pcs_pinconf_ops = {
 static int pcs_add_pin(struct pcs_device *pcs, unsigned offset,
 		unsigned pin_pos)
 {
+	struct pcs_soc_data *pcs_soc = &pcs->socdata;
 	struct pinctrl_pin_desc *pin;
 	struct pcs_name *pn;
 	int i;
@@ -821,6 +822,18 @@ static int pcs_add_pin(struct pcs_device *pcs, unsigned offset,
 		return -ENOMEM;
 	}
 
+	if (pcs_soc->irq_enable_mask) {
+		unsigned val;
+
+		val = pcs->read(pcs->base + offset);
+		if (val & pcs_soc->irq_enable_mask) {
+			dev_dbg(pcs->dev, "irq enabled at boot for pin at %lx (%x), clearing\n",
+				(unsigned long)pcs->res->start + offset, val);
+			val &= ~pcs_soc->irq_enable_mask;
+			pcs->write(val, pcs->base + offset);
+		}
+	}
+
 	pin = &pcs->pins.pa[i];
 	pn = &pcs->names[i];
 	sprintf(pn->name, "%lx.%d",
diff --git a/drivers/pinctrl/pinctrl-tb10x.c b/drivers/pinctrl/pinctrl-tb10x.c
index c5e0f69..26ca685 100644
--- a/drivers/pinctrl/pinctrl-tb10x.c
+++ b/drivers/pinctrl/pinctrl-tb10x.c
@@ -629,9 +629,8 @@ static int tb10x_gpio_request_enable(struct pinctrl_dev *pctl,
 	 */
 	for (i = 0; i < state->pinfuncgrpcnt; i++) {
 		const struct tb10x_pinfuncgrp *pfg = &state->pingroups[i];
-		unsigned int port = pfg->port;
 		unsigned int mode = pfg->mode;
-		int j;
+		int j, port = pfg->port;
 
 		/*
 		 * Skip pin groups which are always mapped and don't need
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7790.c b/drivers/pinctrl/sh-pfc/pfc-r8a7790.c
index 4809371..f5cd3f9 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7790.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7790.c
@@ -4794,8 +4794,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = {
 		FN_MSIOF0_SCK_B, 0,
 		/* IP5_23_21 [3] */
 		FN_WE1_N, FN_IERX, FN_CAN1_RX, FN_VI1_G4,
-		FN_VI1_G4_B, FN_VI2_R6, FN_SCIFA0_CTS_N_B,
-		FN_IERX_C, 0,
+		FN_VI1_G4_B, FN_VI2_R6, FN_SCIFA0_CTS_N_B, FN_IERX_C,
 		/* IP5_20_18 [3] */
 		FN_WE0_N, FN_IECLK, FN_CAN_CLK,
 		FN_VI2_VSYNC_N, FN_SCIFA0_TXD_B, FN_VI2_VSYNC_N_B, 0, 0,
diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
index 5186d70..7868bf3 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a7791.c
@@ -5288,7 +5288,7 @@ static const struct pinmux_cfg_reg pinmux_config_regs[] = {
 		/* SEL_SCIF3 [2] */
 		FN_SEL_SCIF3_0, FN_SEL_SCIF3_1, FN_SEL_SCIF3_2, FN_SEL_SCIF3_3,
 		/* SEL_IEB [2] */
-		FN_SEL_IEB_0, FN_SEL_IEB_1, FN_SEL_IEB_2,
+		FN_SEL_IEB_0, FN_SEL_IEB_1, FN_SEL_IEB_2, 0,
 		/* SEL_MMC [1] */
 		FN_SEL_MMC_0, FN_SEL_MMC_1,
 		/* SEL_SCIF5 [1] */
diff --git a/drivers/pnp/pnpacpi/core.c b/drivers/pnp/pnpacpi/core.c
index 9f611cb..c31aa07 100644
--- a/drivers/pnp/pnpacpi/core.c
+++ b/drivers/pnp/pnpacpi/core.c
@@ -83,8 +83,7 @@ static int pnpacpi_set_resources(struct pnp_dev *dev)
 {
 	struct acpi_device *acpi_dev;
 	acpi_handle handle;
-	struct acpi_buffer buffer;
-	int ret;
+	int ret = 0;
 
 	pnp_dbg(&dev->dev, "set resources\n");
 
@@ -97,19 +96,26 @@ static int pnpacpi_set_resources(struct pnp_dev *dev)
 	if (WARN_ON_ONCE(acpi_dev != dev->data))
 		dev->data = acpi_dev;
 
-	ret = pnpacpi_build_resource_template(dev, &buffer);
-	if (ret)
-		return ret;
-	ret = pnpacpi_encode_resources(dev, &buffer);
-	if (ret) {
+	if (acpi_has_method(handle, METHOD_NAME__SRS)) {
+		struct acpi_buffer buffer;
+
+		ret = pnpacpi_build_resource_template(dev, &buffer);
+		if (ret)
+			return ret;
+
+		ret = pnpacpi_encode_resources(dev, &buffer);
+		if (!ret) {
+			acpi_status status;
+
+			status = acpi_set_current_resources(handle, &buffer);
+			if (ACPI_FAILURE(status))
+				ret = -EIO;
+		}
 		kfree(buffer.pointer);
-		return ret;
 	}
-	if (ACPI_FAILURE(acpi_set_current_resources(handle, &buffer)))
-		ret = -EINVAL;
-	else if (acpi_bus_power_manageable(handle))
+	if (!ret && acpi_bus_power_manageable(handle))
 		ret = acpi_bus_set_power(handle, ACPI_STATE_D0);
-	kfree(buffer.pointer);
+
 	return ret;
 }
 
@@ -117,7 +123,7 @@ static int pnpacpi_disable_resources(struct pnp_dev *dev)
 {
 	struct acpi_device *acpi_dev;
 	acpi_handle handle;
-	int ret;
+	acpi_status status;
 
 	dev_dbg(&dev->dev, "disable resources\n");
 
@@ -128,13 +134,15 @@ static int pnpacpi_disable_resources(struct pnp_dev *dev)
 	}
 
 	/* acpi_unregister_gsi(pnp_irq(dev, 0)); */
-	ret = 0;
 	if (acpi_bus_power_manageable(handle))
 		acpi_bus_set_power(handle, ACPI_STATE_D3_COLD);
-		/* continue even if acpi_bus_set_power() fails */
-	if (ACPI_FAILURE(acpi_evaluate_object(handle, "_DIS", NULL, NULL)))
-		ret = -ENODEV;
-	return ret;
+
+	/* continue even if acpi_bus_set_power() fails */
+	status = acpi_evaluate_object(handle, "_DIS", NULL, NULL);
+	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND)
+		return -ENODEV;
+
+	return 0;
 }
 
 #ifdef CONFIG_ACPI_SLEEP
diff --git a/drivers/pnp/quirks.c b/drivers/pnp/quirks.c
index 3736bc4..ebf0d67 100644
--- a/drivers/pnp/quirks.c
+++ b/drivers/pnp/quirks.c
@@ -335,7 +335,7 @@ static void quirk_amd_mmconfig_area(struct pnp_dev *dev)
 }
 #endif
 
-#ifdef CONFIG_X86
+#ifdef CONFIG_PCI
 /* Device IDs of parts that have 32KB MCH space */
 static const unsigned int mch_quirk_devices[] = {
 	0x0154,	/* Ivy Bridge */
@@ -440,7 +440,7 @@ static struct pnp_fixup pnp_fixups[] = {
 #ifdef CONFIG_AMD_NB
 	{"PNP0c01", quirk_amd_mmconfig_area},
 #endif
-#ifdef CONFIG_X86
+#ifdef CONFIG_PCI
 	{"PNP0c02", quirk_intel_mch},
 #endif
 	{""}
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 9f0ea6c..e3bf885 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -541,18 +541,27 @@ static void chsc_process_sei_nt0(struct chsc_sei_nt0_area *sei_area)
 
 static void chsc_process_event_information(struct chsc_sei *sei, u64 ntsm)
 {
-	do {
+	static int ntsm_unsupported;
+
+	while (true) {
 		memset(sei, 0, sizeof(*sei));
 		sei->request.length = 0x0010;
 		sei->request.code = 0x000e;
-		sei->ntsm = ntsm;
+		if (!ntsm_unsupported)
+			sei->ntsm = ntsm;
 
 		if (chsc(sei))
 			break;
 
 		if (sei->response.code != 0x0001) {
-			CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x)\n",
-				      sei->response.code);
+			CIO_CRW_EVENT(2, "chsc: sei failed (rc=%04x, ntsm=%llx)\n",
+				      sei->response.code, sei->ntsm);
+
+			if (sei->response.code == 3 && sei->ntsm) {
+				/* Fallback for old firmware. */
+				ntsm_unsupported = 1;
+				continue;
+			}
 			break;
 		}
 
@@ -568,7 +577,10 @@ static void chsc_process_event_information(struct chsc_sei *sei, u64 ntsm)
 			CIO_CRW_EVENT(2, "chsc: unhandled nt: %d\n", sei->nt);
 			break;
 		}
-	} while (sei->u.nt0_area.flags & 0x80);
+
+		if (!(sei->u.nt0_area.flags & 0x80))
+			break;
+	}
 }
 
 /*
diff --git a/drivers/scsi/mpt2sas/mpt2sas_scsih.c b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
index 7f0af4f..6fd7d40 100644
--- a/drivers/scsi/mpt2sas/mpt2sas_scsih.c
+++ b/drivers/scsi/mpt2sas/mpt2sas_scsih.c
@@ -8293,7 +8293,6 @@ _scsih_suspend(struct pci_dev *pdev, pm_message_t state)
 
 	mpt2sas_base_free_resources(ioc);
 	pci_save_state(pdev);
-	pci_disable_device(pdev);
 	pci_set_power_state(pdev, device_state);
 	return 0;
 }
diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 16bfd50..db3b494 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -750,8 +750,12 @@ static void __virtscsi_set_affinity(struct virtio_scsi *vscsi, bool affinity)
 
 		vscsi->affinity_hint_set = true;
 	} else {
-		for (i = 0; i < vscsi->num_queues; i++)
+		for (i = 0; i < vscsi->num_queues; i++) {
+			if (!vscsi->req_vqs[i].vq)
+				continue;
+
 			virtqueue_set_affinity(vscsi->req_vqs[i].vq, -1);
+		}
 
 		vscsi->affinity_hint_set = false;
 	}
diff --git a/fs/aio.c b/fs/aio.c
index 12a3de0e..a0ed6c7 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -112,6 +112,11 @@ struct kioctx {
 
 	struct work_struct	free_work;
 
+	/*
+	 * signals when all in-flight requests are done
+	 */
+	struct completion *requests_done;
+
 	struct {
 		/*
 		 * This counts the number of available slots in the ringbuffer,
@@ -508,6 +513,10 @@ static void free_ioctx_reqs(struct percpu_ref *ref)
 {
 	struct kioctx *ctx = container_of(ref, struct kioctx, reqs);
 
+	/* At this point we know that there are no any in-flight requests */
+	if (ctx->requests_done)
+		complete(ctx->requests_done);
+
 	INIT_WORK(&ctx->free_work, free_ioctx);
 	schedule_work(&ctx->free_work);
 }
@@ -718,7 +727,8 @@ err:
  *	when the processes owning a context have all exited to encourage
  *	the rapid destruction of the kioctx.
  */
-static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx)
+static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx,
+		struct completion *requests_done)
 {
 	if (!atomic_xchg(&ctx->dead, 1)) {
 		struct kioctx_table *table;
@@ -747,7 +757,11 @@ static void kill_ioctx(struct mm_struct *mm, struct kioctx *ctx)
 		if (ctx->mmap_size)
 			vm_munmap(ctx->mmap_base, ctx->mmap_size);
 
+		ctx->requests_done = requests_done;
 		percpu_ref_kill(&ctx->users);
+	} else {
+		if (requests_done)
+			complete(requests_done);
 	}
 }
 
@@ -809,7 +823,7 @@ void exit_aio(struct mm_struct *mm)
 		 */
 		ctx->mmap_size = 0;
 
-		kill_ioctx(mm, ctx);
+		kill_ioctx(mm, ctx, NULL);
 	}
 }
 
@@ -1185,7 +1199,7 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp)
 	if (!IS_ERR(ioctx)) {
 		ret = put_user(ioctx->user_id, ctxp);
 		if (ret)
-			kill_ioctx(current->mm, ioctx);
+			kill_ioctx(current->mm, ioctx, NULL);
 		percpu_ref_put(&ioctx->users);
 	}
 
@@ -1203,8 +1217,22 @@ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx)
 {
 	struct kioctx *ioctx = lookup_ioctx(ctx);
 	if (likely(NULL != ioctx)) {
-		kill_ioctx(current->mm, ioctx);
+		struct completion requests_done =
+			COMPLETION_INITIALIZER_ONSTACK(requests_done);
+
+		/* Pass requests_done to kill_ioctx() where it can be set
+		 * in a thread-safe way. If we try to set it here then we have
+		 * a race condition if two io_destroy() called simultaneously.
+		 */
+		kill_ioctx(current->mm, ioctx, &requests_done);
 		percpu_ref_put(&ioctx->users);
+
+		/* Wait until all IO for the context are done. Otherwise kernel
+		 * keep using user-space buffers even if user thinks the context
+		 * is destroyed.
+		 */
+		wait_for_completion(&requests_done);
+
 		return 0;
 	}
 	pr_debug("EINVAL: io_destroy: invalid context id\n");
@@ -1299,10 +1327,8 @@ rw_common:
 						&iovec, compat)
 			: aio_setup_single_vector(req, rw, buf, &nr_segs,
 						  iovec);
-		if (ret)
-			return ret;
-
-		ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes);
+		if (!ret)
+			ret = rw_verify_area(rw, file, &req->ki_pos, req->ki_nbytes);
 		if (ret < 0) {
 			if (iovec != &inline_vec)
 				kfree(iovec);
diff --git a/include/asm-generic/fixmap.h b/include/asm-generic/fixmap.h
index 5a64ca4..f23174f 100644
--- a/include/asm-generic/fixmap.h
+++ b/include/asm-generic/fixmap.h
@@ -93,5 +93,8 @@ static inline unsigned long virt_to_fix(const unsigned long vaddr)
 #define set_fixmap_io(idx, phys) \
 	__set_fixmap(idx, phys, FIXMAP_PAGE_IO)
 
+#define set_fixmap_offset_io(idx, phys) \
+	__set_fixmap_offset(idx, phys, FIXMAP_PAGE_IO)
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ASM_GENERIC_FIXMAP_H */
diff --git a/include/asm-generic/word-at-a-time.h b/include/asm-generic/word-at-a-time.h
index d96deb4..94f9ea8 100644
--- a/include/asm-generic/word-at-a-time.h
+++ b/include/asm-generic/word-at-a-time.h
@@ -50,7 +50,7 @@ static inline bool has_zero(unsigned long val, unsigned long *data, const struct
 }
 
 #ifndef zero_bytemask
-#define zero_bytemask(mask) (~0ul << __fls(mask) << 1)
+#define zero_bytemask(mask) (~1ul << __fls(mask))
 #endif
 
 #endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 9212b01..ae9504b 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -535,6 +535,7 @@ static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_a
 extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
 extern int skip_trace(unsigned long ip);
+extern void ftrace_module_init(struct module *mod);
 
 extern void ftrace_disable_daemon(void);
 extern void ftrace_enable_daemon(void);
@@ -544,6 +545,7 @@ static inline int ftrace_force_update(void) { return 0; }
 static inline void ftrace_disable_daemon(void) { }
 static inline void ftrace_enable_daemon(void) { }
 static inline void ftrace_release_mod(struct module *mod) {}
+static inline void ftrace_module_init(struct module *mod) {}
 static inline __init int register_ftrace_command(struct ftrace_func_command *cmd)
 {
 	return -EINVAL;
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 8834a7e..97ac926 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -210,7 +210,7 @@ extern int __irq_set_affinity(unsigned int irq, const struct cpumask *cpumask,
 /**
  * irq_set_affinity - Set the irq affinity of a given irq
  * @irq:	Interrupt to set affinity
- * @mask:	cpumask
+ * @cpumask:	cpumask
  *
  * Fails if cpumask does not contain an online CPU
  */
@@ -223,7 +223,7 @@ irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 /**
  * irq_force_affinity - Force the irq affinity of a given irq
  * @irq:	Interrupt to set affinity
- * @mask:	cpumask
+ * @cpumask:	cpumask
  *
  * Same as irq_set_affinity, but without checking the mask against
  * online cpus.
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 10a0b1a..5c57efb 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -603,6 +603,8 @@ static inline u32 irq_get_trigger_type(unsigned int irq)
 	return d ? irqd_get_trigger_type(d) : 0;
 }
 
+unsigned int arch_dynirq_lower_bound(unsigned int from);
+
 int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
 		struct module *owner);
 
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index 3f23b44..6404253 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -44,11 +44,16 @@ extern void of_irq_init(const struct of_device_id *matches);
 
 #ifdef CONFIG_OF_IRQ
 extern int of_irq_count(struct device_node *dev);
+extern int of_irq_get(struct device_node *dev, int index);
 #else
 static inline int of_irq_count(struct device_node *dev)
 {
 	return 0;
 }
+static inline int of_irq_get(struct device_node *dev, int index)
+{
+	return 0;
+}
 #endif
 
 #if defined(CONFIG_OF)
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index 11fd51b..ed0b2c5 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -25,7 +25,7 @@ struct module;
 	{ (1UL << TAINT_OOT_MODULE),		"O" },		\
 	{ (1UL << TAINT_FORCED_MODULE),		"F" },		\
 	{ (1UL << TAINT_CRAP),			"C" },		\
-	{ (1UL << TAINT_UNSIGNED_MODULE),	"X" })
+	{ (1UL << TAINT_UNSIGNED_MODULE),	"E" })
 
 TRACE_EVENT(module_load,
 
diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c
index d55092c..6b715c0 100644
--- a/kernel/hrtimer.c
+++ b/kernel/hrtimer.c
@@ -234,6 +234,11 @@ again:
 			goto again;
 		}
 		timer->base = new_base;
+	} else {
+		if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) {
+			cpu = this_cpu;
+			goto again;
+		}
 	}
 	return new_base;
 }
@@ -569,6 +574,23 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal)
 
 	cpu_base->expires_next.tv64 = expires_next.tv64;
 
+	/*
+	 * If a hang was detected in the last timer interrupt then we
+	 * leave the hang delay active in the hardware. We want the
+	 * system to make progress. That also prevents the following
+	 * scenario:
+	 * T1 expires 50ms from now
+	 * T2 expires 5s from now
+	 *
+	 * T1 is removed, so this code is called and would reprogram
+	 * the hardware to 5s from now. Any hrtimer_start after that
+	 * will not reprogram the hardware due to hang_detected being
+	 * set. So we'd effectivly block all timers until the T2 event
+	 * fires.
+	 */
+	if (cpu_base->hang_detected)
+		return;
+
 	if (cpu_base->expires_next.tv64 != KTIME_MAX)
 		tick_program_event(cpu_base->expires_next, 1);
 }
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index a7174617..bb07f29 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -363,6 +363,13 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
 		if (from > irq)
 			return -EINVAL;
 		from = irq;
+	} else {
+		/*
+		 * For interrupts which are freely allocated the
+		 * architecture can force a lower bound to the @from
+		 * argument. x86 uses this to exclude the GSI space.
+		 */
+		from = arch_dynirq_lower_bound(from);
 	}
 
 	mutex_lock(&sparse_irq_lock);
diff --git a/kernel/module.c b/kernel/module.c
index 1186940..079c461 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -815,9 +815,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user,
 		return -EFAULT;
 	name[MODULE_NAME_LEN-1] = '\0';
 
-	if (!(flags & O_NONBLOCK))
-		pr_warn("waiting module removal not supported: please upgrade\n");
-
 	if (mutex_lock_interruptible(&module_mutex) != 0)
 		return -EINTR;
 
@@ -3271,6 +3268,9 @@ static int load_module(struct load_info *info, const char __user *uargs,
 
 	dynamic_debug_setup(info->debug, info->num_debug);
 
+	/* Ftrace init must be called in the MODULE_STATE_UNFORMED state */
+	ftrace_module_init(mod);
+
 	/* Finally it's fully formed, ready to start executing. */
 	err = complete_formation(mod, info);
 	if (err)
diff --git a/kernel/softirq.c b/kernel/softirq.c
index b50990a..33e4648 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -779,3 +779,8 @@ int __init __weak arch_early_irq_init(void)
 {
 	return 0;
 }
+
+unsigned int __weak arch_dynirq_lower_bound(unsigned int from)
+{
+	return from;
+}
diff --git a/kernel/timer.c b/kernel/timer.c
index 87bd529..3bb01a3 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -838,7 +838,7 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
 
 	bit = find_last_bit(&mask, BITS_PER_LONG);
 
-	mask = (1 << bit) - 1;
+	mask = (1UL << bit) - 1;
 
 	expires_limit = expires_limit & ~(mask);
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 1fd4b94..4a54a25 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4330,16 +4330,11 @@ static void ftrace_init_module(struct module *mod,
 	ftrace_process_locs(mod, start, end);
 }
 
-static int ftrace_module_notify_enter(struct notifier_block *self,
-				      unsigned long val, void *data)
+void ftrace_module_init(struct module *mod)
 {
-	struct module *mod = data;
-
-	if (val == MODULE_STATE_COMING)
-		ftrace_init_module(mod, mod->ftrace_callsites,
-				   mod->ftrace_callsites +
-				   mod->num_ftrace_callsites);
-	return 0;
+	ftrace_init_module(mod, mod->ftrace_callsites,
+			   mod->ftrace_callsites +
+			   mod->num_ftrace_callsites);
 }
 
 static int ftrace_module_notify_exit(struct notifier_block *self,
@@ -4353,11 +4348,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self,
 	return 0;
 }
 #else
-static int ftrace_module_notify_enter(struct notifier_block *self,
-				      unsigned long val, void *data)
-{
-	return 0;
-}
 static int ftrace_module_notify_exit(struct notifier_block *self,
 				     unsigned long val, void *data)
 {
@@ -4365,11 +4355,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self,
 }
 #endif /* CONFIG_MODULES */
 
-struct notifier_block ftrace_module_enter_nb = {
-	.notifier_call = ftrace_module_notify_enter,
-	.priority = INT_MAX,	/* Run before anything that can use kprobes */
-};
-
 struct notifier_block ftrace_module_exit_nb = {
 	.notifier_call = ftrace_module_notify_exit,
 	.priority = INT_MIN,	/* Run after anything that can remove kprobes */
@@ -4403,10 +4388,6 @@ void __init ftrace_init(void)
 				  __start_mcount_loc,
 				  __stop_mcount_loc);
 
-	ret = register_module_notifier(&ftrace_module_enter_nb);
-	if (ret)
-		pr_warning("Failed to register trace ftrace module enter notifier\n");
-
 	ret = register_module_notifier(&ftrace_module_exit_nb);
 	if (ret)
 		pr_warning("Failed to register trace ftrace module exit notifier\n");
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index 925f537..4747b47 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -77,7 +77,7 @@ event_triggers_call(struct ftrace_event_file *file, void *rec)
 			data->ops->func(data);
 			continue;
 		}
-		filter = rcu_dereference(data->filter);
+		filter = rcu_dereference_sched(data->filter);
 		if (filter && !filter_match_preds(filter, rec))
 			continue;
 		if (data->cmd_ops->post_trigger) {
diff --git a/mm/vmacache.c b/mm/vmacache.c
index d4224b3..1037a3ba 100644
--- a/mm/vmacache.c
+++ b/mm/vmacache.c
@@ -81,10 +81,12 @@ struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr)
 	for (i = 0; i < VMACACHE_SIZE; i++) {
 		struct vm_area_struct *vma = current->vmacache[i];
 
-		if (vma && vma->vm_start <= addr && vma->vm_end > addr) {
-			BUG_ON(vma->vm_mm != mm);
+		if (!vma)
+			continue;
+		if (WARN_ON_ONCE(vma->vm_mm != mm))
+			break;
+		if (vma->vm_start <= addr && vma->vm_end > addr)
 			return vma;
-		}
 	}
 
 	return NULL;
diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c
index 248b90a..480bbdd 100644
--- a/sound/pci/hda/hda_controller.c
+++ b/sound/pci/hda/hda_controller.c
@@ -1059,24 +1059,26 @@ static void azx_init_cmd_io(struct azx *chip)
 
 	/* reset the corb hw read pointer */
 	azx_writew(chip, CORBRP, ICH6_CORBRP_RST);
-	for (timeout = 1000; timeout > 0; timeout--) {
-		if ((azx_readw(chip, CORBRP) & ICH6_CORBRP_RST) == ICH6_CORBRP_RST)
-			break;
-		udelay(1);
-	}
-	if (timeout <= 0)
-		dev_err(chip->card->dev, "CORB reset timeout#1, CORBRP = %d\n",
-			azx_readw(chip, CORBRP));
+	if (!(chip->driver_caps & AZX_DCAPS_CORBRP_SELF_CLEAR)) {
+		for (timeout = 1000; timeout > 0; timeout--) {
+			if ((azx_readw(chip, CORBRP) & ICH6_CORBRP_RST) == ICH6_CORBRP_RST)
+				break;
+			udelay(1);
+		}
+		if (timeout <= 0)
+			dev_err(chip->card->dev, "CORB reset timeout#1, CORBRP = %d\n",
+				azx_readw(chip, CORBRP));
 
-	azx_writew(chip, CORBRP, 0);
-	for (timeout = 1000; timeout > 0; timeout--) {
-		if (azx_readw(chip, CORBRP) == 0)
-			break;
-		udelay(1);
+		azx_writew(chip, CORBRP, 0);
+		for (timeout = 1000; timeout > 0; timeout--) {
+			if (azx_readw(chip, CORBRP) == 0)
+				break;
+			udelay(1);
+		}
+		if (timeout <= 0)
+			dev_err(chip->card->dev, "CORB reset timeout#2, CORBRP = %d\n",
+				azx_readw(chip, CORBRP));
 	}
-	if (timeout <= 0)
-		dev_err(chip->card->dev, "CORB reset timeout#2, CORBRP = %d\n",
-			azx_readw(chip, CORBRP));
 
 	/* enable corb dma */
 	azx_writeb(chip, CORBCTL, ICH6_CORBCTL_RUN);
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index d6bca62..b540ad7 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -249,7 +249,8 @@ enum {
 /* quirks for Nvidia */
 #define AZX_DCAPS_PRESET_NVIDIA \
 	(AZX_DCAPS_NVIDIA_SNOOP | AZX_DCAPS_RIRB_DELAY | AZX_DCAPS_NO_MSI |\
-	 AZX_DCAPS_ALIGN_BUFSIZE | AZX_DCAPS_NO_64BIT)
+	 AZX_DCAPS_ALIGN_BUFSIZE | AZX_DCAPS_NO_64BIT |\
+	 AZX_DCAPS_CORBRP_SELF_CLEAR)
 
 #define AZX_DCAPS_PRESET_CTHDA \
 	(AZX_DCAPS_NO_MSI | AZX_DCAPS_POSFIX_LPIB | AZX_DCAPS_4K_BDLE_BOUNDARY)
diff --git a/sound/pci/hda/hda_priv.h b/sound/pci/hda/hda_priv.h
index ba38b81..4a7cb01 100644
--- a/sound/pci/hda/hda_priv.h
+++ b/sound/pci/hda/hda_priv.h
@@ -189,6 +189,7 @@ enum { SDI0, SDI1, SDI2, SDI3, SDO0, SDO1, SDO2, SDO3 };
 #define AZX_DCAPS_COUNT_LPIB_DELAY  (1 << 25)	/* Take LPIB as delay */
 #define AZX_DCAPS_PM_RUNTIME	(1 << 26)	/* runtime PM support */
 #define AZX_DCAPS_I915_POWERWELL (1 << 27)	/* HSW i915 powerwell support */
+#define AZX_DCAPS_CORBRP_SELF_CLEAR (1 << 28)	/* CORBRP clears itself after reset */
 
 /* position fix mode */
 enum {
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c643dfc..c1952c9 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4621,6 +4621,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1028, 0x0667, "Dell", ALC269_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0668, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x0669, "Dell", ALC255_FIXUP_DELL2_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1028, 0x0674, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x067f, "Dell", ALC255_FIXUP_DELL1_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x15cc, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1028, 0x15cd, "Dell X5 Precision", ALC269_FIXUP_DELL2_MIC_NO_PRESENCE),
diff --git a/sound/soc/codecs/alc5623.c b/sound/soc/codecs/alc5623.c
index f500905..2acf82f 100644
--- a/sound/soc/codecs/alc5623.c
+++ b/sound/soc/codecs/alc5623.c
@@ -1018,13 +1018,13 @@ static int alc5623_i2c_probe(struct i2c_client *client,
 		dev_err(&client->dev, "failed to read vendor ID1: %d\n", ret);
 		return ret;
 	}
-	vid1 = ((vid1 & 0xff) << 8) | (vid1 >> 8);
 
 	ret = regmap_read(alc5623->regmap, ALC5623_VENDOR_ID2, &vid2);
 	if (ret < 0) {
 		dev_err(&client->dev, "failed to read vendor ID2: %d\n", ret);
 		return ret;
 	}
+	vid2 >>= 8;
 
 	if ((vid1 != 0x10ec) || (vid2 != id->driver_data)) {
 		dev_err(&client->dev, "unknown or wrong codec\n");
diff --git a/sound/soc/codecs/cs42l52.c b/sound/soc/codecs/cs42l52.c
index 460d355..2213a03 100644
--- a/sound/soc/codecs/cs42l52.c
+++ b/sound/soc/codecs/cs42l52.c
@@ -1229,8 +1229,10 @@ static int cs42l52_i2c_probe(struct i2c_client *i2c_client,
 	}
 
 	if (cs42l52->pdata.reset_gpio) {
-		ret = gpio_request_one(cs42l52->pdata.reset_gpio,
-				       GPIOF_OUT_INIT_HIGH, "CS42L52 /RST");
+		ret = devm_gpio_request_one(&i2c_client->dev,
+					    cs42l52->pdata.reset_gpio,
+					    GPIOF_OUT_INIT_HIGH,
+					    "CS42L52 /RST");
 		if (ret < 0) {
 			dev_err(&i2c_client->dev, "Failed to request /RST %d: %d\n",
 				cs42l52->pdata.reset_gpio, ret);
diff --git a/sound/soc/codecs/cs42l73.c b/sound/soc/codecs/cs42l73.c
index 0ee60a1..ae37179 100644
--- a/sound/soc/codecs/cs42l73.c
+++ b/sound/soc/codecs/cs42l73.c
@@ -1443,8 +1443,10 @@ static int cs42l73_i2c_probe(struct i2c_client *i2c_client,
 	i2c_set_clientdata(i2c_client, cs42l73);
 
 	if (cs42l73->pdata.reset_gpio) {
-		ret = gpio_request_one(cs42l73->pdata.reset_gpio,
-				       GPIOF_OUT_INIT_HIGH, "CS42L73 /RST");
+		ret = devm_gpio_request_one(&i2c_client->dev,
+					    cs42l73->pdata.reset_gpio,
+					    GPIOF_OUT_INIT_HIGH,
+					    "CS42L73 /RST");
 		if (ret < 0) {
 			dev_err(&i2c_client->dev, "Failed to request /RST %d: %d\n",
 				cs42l73->pdata.reset_gpio, ret);
diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c
index b183510..d7349bc 100644
--- a/sound/soc/codecs/tlv320aic3x.c
+++ b/sound/soc/codecs/tlv320aic3x.c
@@ -1399,7 +1399,6 @@ static int aic3x_probe(struct snd_soc_codec *codec)
 	}
 
 	aic3x_add_widgets(codec);
-	list_add(&aic3x->list, &reset_list);
 
 	return 0;
 
@@ -1569,7 +1568,13 @@ static int aic3x_i2c_probe(struct i2c_client *i2c,
 
 	ret = snd_soc_register_codec(&i2c->dev,
 			&soc_codec_dev_aic3x, &aic3x_dai, 1);
-	return ret;
+
+	if (ret != 0)
+		goto err_gpio;
+
+	list_add(&aic3x->list, &reset_list);
+
+	return 0;
 
 err_gpio:
 	if (gpio_is_valid(aic3x->gpio_reset) &&
diff --git a/sound/soc/fsl/fsl_spdif.h b/sound/soc/fsl/fsl_spdif.h
index b126679..605a10b 100644
--- a/sound/soc/fsl/fsl_spdif.h
+++ b/sound/soc/fsl/fsl_spdif.h
@@ -144,8 +144,8 @@ enum spdif_gainsel {
 
 /* SPDIF Clock register */
 #define STC_SYSCLK_DIV_OFFSET		11
-#define STC_SYSCLK_DIV_MASK		(0x1ff << STC_TXCLK_SRC_OFFSET)
-#define STC_SYSCLK_DIV(x)		((((x) - 1) << STC_TXCLK_DIV_OFFSET) & STC_SYSCLK_DIV_MASK)
+#define STC_SYSCLK_DIV_MASK		(0x1ff << STC_SYSCLK_DIV_OFFSET)
+#define STC_SYSCLK_DIV(x)		((((x) - 1) << STC_SYSCLK_DIV_OFFSET) & STC_SYSCLK_DIV_MASK)
 #define STC_TXCLK_SRC_OFFSET		8
 #define STC_TXCLK_SRC_MASK		(0x7 << STC_TXCLK_SRC_OFFSET)
 #define STC_TXCLK_SRC_SET(x)		((x << STC_TXCLK_SRC_OFFSET) & STC_TXCLK_SRC_MASK)
diff --git a/sound/soc/intel/sst-dsp-priv.h b/sound/soc/intel/sst-dsp-priv.h
index fe8e81aa..30ca14a 100644
--- a/sound/soc/intel/sst-dsp-priv.h
+++ b/sound/soc/intel/sst-dsp-priv.h
@@ -136,7 +136,7 @@ struct sst_module_data {
 	enum sst_data_type data_type;	/* type of module data */
 
 	u32 size;		/* size in bytes */
-	u32 offset;		/* offset in FW file */
+	int32_t offset;		/* offset in FW file */
 	u32 data_offset;	/* offset in ADSP memory space */
 	void *data;		/* module data */
 };
diff --git a/sound/soc/intel/sst-haswell-ipc.c b/sound/soc/intel/sst-haswell-ipc.c
index f46bb4d..50e4246 100644
--- a/sound/soc/intel/sst-haswell-ipc.c
+++ b/sound/soc/intel/sst-haswell-ipc.c
@@ -617,7 +617,7 @@ static void hsw_notification_work(struct work_struct *work)
 	case IPC_POSITION_CHANGED:
 		trace_ipc_notification("DSP stream position changed for",
 			stream->reply.stream_hw_id);
-		sst_dsp_inbox_read(hsw->dsp, pos, sizeof(pos));
+		sst_dsp_inbox_read(hsw->dsp, pos, sizeof(*pos));
 
 		if (stream->notify_position)
 			stream->notify_position(stream, stream->pdata);
@@ -991,7 +991,8 @@ int sst_hsw_stream_get_volume(struct sst_hsw *hsw, struct sst_hsw_stream *stream
 		return -EINVAL;
 
 	sst_dsp_read(hsw->dsp, volume,
-		stream->reply.volume_register_address[channel], sizeof(volume));
+		stream->reply.volume_register_address[channel],
+		sizeof(*volume));
 
 	return 0;
 }
@@ -1609,7 +1610,7 @@ int sst_hsw_dx_set_state(struct sst_hsw *hsw,
 	trace_ipc_request("PM enter Dx state", state);
 
 	ret = ipc_tx_message_wait(hsw, header, &state_, sizeof(state_),
-		dx, sizeof(dx));
+		dx, sizeof(*dx));
 	if (ret < 0) {
 		dev_err(hsw->dev, "ipc: error set dx state %d failed\n", state);
 		return ret;
diff --git a/sound/soc/jz4740/Makefile b/sound/soc/jz4740/Makefile
index be873c1..d32c540 100644
--- a/sound/soc/jz4740/Makefile
+++ b/sound/soc/jz4740/Makefile
@@ -1,10 +1,8 @@
 #
 # Jz4740 Platform Support
 #
-snd-soc-jz4740-objs := jz4740-pcm.o
 snd-soc-jz4740-i2s-objs := jz4740-i2s.o
 
-obj-$(CONFIG_SND_JZ4740_SOC) += snd-soc-jz4740.o
 obj-$(CONFIG_SND_JZ4740_SOC_I2S) += snd-soc-jz4740-i2s.o
 
 # Jz4740 Machine Support
diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c
index 6232b7d..4d0720e 100644
--- a/sound/soc/sh/rcar/src.c
+++ b/sound/soc/sh/rcar/src.c
@@ -258,7 +258,7 @@ static int rsnd_src_init(struct rsnd_mod *mod,
 {
 	struct rsnd_src *src = rsnd_mod_to_src(mod);
 
-	clk_enable(src->clk);
+	clk_prepare_enable(src->clk);
 
 	return 0;
 }
@@ -269,7 +269,7 @@ static int rsnd_src_quit(struct rsnd_mod *mod,
 {
 	struct rsnd_src *src = rsnd_mod_to_src(mod);
 
-	clk_disable(src->clk);
+	clk_disable_unprepare(src->clk);
 
 	return 0;
 }
diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c
index 4b7e206..1d8387c 100644
--- a/sound/soc/sh/rcar/ssi.c
+++ b/sound/soc/sh/rcar/ssi.c
@@ -171,7 +171,7 @@ static void rsnd_ssi_hw_start(struct rsnd_ssi *ssi,
 	u32 cr;
 
 	if (0 == ssi->usrcnt) {
-		clk_enable(ssi->clk);
+		clk_prepare_enable(ssi->clk);
 
 		if (rsnd_dai_is_clk_master(rdai)) {
 			if (rsnd_ssi_clk_from_parent(ssi))
@@ -230,7 +230,7 @@ static void rsnd_ssi_hw_stop(struct rsnd_ssi *ssi,
 				rsnd_ssi_master_clk_stop(ssi);
 		}
 
-		clk_disable(ssi->clk);
+		clk_disable_unprepare(ssi->clk);
 	}
 
 	dev_dbg(dev, "ssi%d hw stopped\n", rsnd_mod_id(&ssi->mod));
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index c8a780d..7769b0a 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -254,7 +254,6 @@ static int dapm_kcontrol_data_alloc(struct snd_soc_dapm_widget *widget,
 static void dapm_kcontrol_free(struct snd_kcontrol *kctl)
 {
 	struct dapm_kcontrol_data *data = snd_kcontrol_chip(kctl);
-	kfree(data->widget);
 	kfree(data->wlist);
 	kfree(data);
 }
diff --git a/tools/lib/api/fs/debugfs.c b/tools/lib/api/fs/debugfs.c
index 7c43479..a74fba6 100644
--- a/tools/lib/api/fs/debugfs.c
+++ b/tools/lib/api/fs/debugfs.c
@@ -12,8 +12,8 @@
 char debugfs_mountpoint[PATH_MAX + 1] = "/sys/kernel/debug";
 
 static const char * const debugfs_known_mountpoints[] = {
-	"/sys/kernel/debug/",
-	"/debug/",
+	"/sys/kernel/debug",
+	"/debug",
 	0,
 };
 
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index baec7d8..b83184f 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -4344,6 +4344,7 @@ static void pretty_print(struct trace_seq *s, void *data, int size, struct event
 					      format, len_arg, arg);
 				trace_seq_terminate(&p);
 				trace_seq_puts(s, p.buffer);
+				trace_seq_destroy(&p);
 				arg = arg->next;
 				break;
 			default:
diff --git a/tools/lib/traceevent/event-parse.h b/tools/lib/traceevent/event-parse.h
index 791c539..feab942 100644
--- a/tools/lib/traceevent/event-parse.h
+++ b/tools/lib/traceevent/event-parse.h
@@ -876,8 +876,8 @@ struct event_filter {
 struct event_filter *pevent_filter_alloc(struct pevent *pevent);
 
 /* for backward compatibility */
-#define FILTER_NONE		PEVENT_ERRNO__FILTER_NOT_FOUND
-#define FILTER_NOEXIST		PEVENT_ERRNO__NO_FILTER
+#define FILTER_NONE		PEVENT_ERRNO__NO_FILTER
+#define FILTER_NOEXIST		PEVENT_ERRNO__FILTER_NOT_FOUND
 #define FILTER_MISS		PEVENT_ERRNO__FILTER_MISS
 #define FILTER_MATCH		PEVENT_ERRNO__FILTER_MATCH
 
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index e969233..895edd3 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -589,7 +589,7 @@ $(GTK_OBJS): $(OUTPUT)%.o: %.c $(LIB_H)
 	$(QUIET_CC)$(CC) -o $@ -c -fPIC $(CFLAGS) $(GTK_CFLAGS) $<
 
 $(OUTPUT)libperf-gtk.so: $(GTK_OBJS) $(PERFLIBS)
-	$(QUIET_LINK)$(CC) -o $@ -shared $(ALL_LDFLAGS) $(filter %.o,$^) $(GTK_LIBS)
+	$(QUIET_LINK)$(CC) -o $@ -shared $(LDFLAGS) $(filter %.o,$^) $(GTK_LIBS)
 
 $(OUTPUT)builtin-help.o: builtin-help.c $(OUTPUT)common-cmds.h $(OUTPUT)PERF-CFLAGS
 	$(QUIET_CC)$(CC) -o $@ -c $(CFLAGS) \
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index b602ad9..83bc238 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -23,9 +23,10 @@ static int sample_ustack(struct perf_sample *sample,
 
 	sp = (unsigned long) regs[PERF_REG_X86_SP];
 
-	map = map_groups__find(&thread->mg, MAP__FUNCTION, (u64) sp);
+	map = map_groups__find(&thread->mg, MAP__VARIABLE, (u64) sp);
 	if (!map) {
 		pr_debug("failed to get stack map\n");
+		free(buf);
 		return -1;
 	}
 
diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S
index 99167bf..60875d5 100644
--- a/tools/perf/arch/x86/tests/regs_load.S
+++ b/tools/perf/arch/x86/tests/regs_load.S
@@ -1,4 +1,3 @@
-
 #include <linux/linkage.h>
 
 #define AX	 0
@@ -90,3 +89,10 @@ ENTRY(perf_regs_load)
 	ret
 ENDPROC(perf_regs_load)
 #endif
+
+/*
+ * We need to provide note.GNU-stack section, saying that we want
+ * NOT executable stack. Otherwise the final linking will assume that
+ * the ELF stack should not be restricted at all and set it RWX.
+ */
+.section .note.GNU-stack,"",@progbits
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index ee21fa9..802cf544 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -34,6 +34,14 @@ ifeq ($(ARCH),arm)
   LIBUNWIND_LIBS = -lunwind -lunwind-arm
 endif
 
+# So far there's only x86 libdw unwind support merged in perf.
+# Disable it on all other architectures in case libdw unwind
+# support is detected in system. Add supported architectures
+# to the check.
+ifneq ($(ARCH),x86)
+  NO_LIBDW_DWARF_UNWIND := 1
+endif
+
 ifeq ($(LIBUNWIND_LIBS),)
   NO_LIBUNWIND := 1
 else
@@ -109,6 +117,10 @@ CFLAGS += -Wall
 CFLAGS += -Wextra
 CFLAGS += -std=gnu99
 
+# Enforce a non-executable stack, as we may regress (again) in the future by
+# adding assembler files missing the .GNU-stack linker note.
+LDFLAGS += -Wl,-z,noexecstack
+
 EXTLIBS = -lelf -lpthread -lrt -lm -ldl
 
 ifneq ($(OUTPUT),)
@@ -186,7 +198,10 @@ VF_FEATURE_TESTS =			\
 	stackprotector-all		\
 	timerfd				\
 	libunwind-debug-frame		\
-	bionic
+	bionic				\
+	liberty				\
+	liberty-z			\
+	cplus-demangle
 
 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all CORE_FEATURE_TESTS features.
 # If in the future we need per-feature checks/flags for features not
@@ -504,7 +519,21 @@ else
 endif
 
 ifeq ($(feature-libbfd), 1)
-  EXTLIBS += -lbfd -lz -liberty
+  EXTLIBS += -lbfd
+
+  # call all detections now so we get correct
+  # status in VF output
+  $(call feature_check,liberty)
+  $(call feature_check,liberty-z)
+  $(call feature_check,cplus-demangle)
+
+  ifeq ($(feature-liberty), 1)
+    EXTLIBS += -liberty
+  else
+    ifeq ($(feature-liberty-z), 1)
+      EXTLIBS += -liberty -lz
+    endif
+  endif
 endif
 
 ifdef NO_DEMANGLE
@@ -515,15 +544,10 @@ else
     CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT
   else
     ifneq ($(feature-libbfd), 1)
-      $(call feature_check,liberty)
-      ifeq ($(feature-liberty), 1)
-        EXTLIBS += -lbfd -liberty
-      else
-        $(call feature_check,liberty-z)
-        ifeq ($(feature-liberty-z), 1)
-          EXTLIBS += -lbfd -liberty -lz
-        else
-          $(call feature_check,cplus-demangle)
+      ifneq ($(feature-liberty), 1)
+        ifneq ($(feature-liberty-z), 1)
+          # we dont have neither HAVE_CPLUS_DEMANGLE_SUPPORT
+          # or any of 'bfd iberty z' trinity
           ifeq ($(feature-cplus-demangle), 1)
             EXTLIBS += -liberty
             CFLAGS += -DHAVE_CPLUS_DEMANGLE_SUPPORT
diff --git a/tools/perf/tests/make b/tools/perf/tests/make
index 5daeae1..2f92d6e 100644
--- a/tools/perf/tests/make
+++ b/tools/perf/tests/make
@@ -46,6 +46,7 @@ make_install_man    := install-man
 make_install_html   := install-html
 make_install_info   := install-info
 make_install_pdf    := install-pdf
+make_static         := LDFLAGS=-static
 
 # all the NO_* variable combined
 make_minimal        := NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1
@@ -87,6 +88,7 @@ run += make_install_bin
 # run += make_install_info
 # run += make_install_pdf
 run += make_minimal
+run += make_static
 
 ifneq ($(call has,ctags),)
 run += make_tags
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index a53cd0b..27c2a5e 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -717,7 +717,7 @@ static char *get_kernel_version(const char *root_dir)
 }
 
 static int map_groups__set_modules_path_dir(struct map_groups *mg,
-				const char *dir_name)
+				const char *dir_name, int depth)
 {
 	struct dirent *dent;
 	DIR *dir = opendir(dir_name);
@@ -742,7 +742,15 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg,
 			    !strcmp(dent->d_name, ".."))
 				continue;
 
-			ret = map_groups__set_modules_path_dir(mg, path);
+			/* Do not follow top-level source and build symlinks */
+			if (depth == 0) {
+				if (!strcmp(dent->d_name, "source") ||
+				    !strcmp(dent->d_name, "build"))
+					continue;
+			}
+
+			ret = map_groups__set_modules_path_dir(mg, path,
+							       depth + 1);
 			if (ret < 0)
 				goto out;
 		} else {
@@ -786,11 +794,11 @@ static int machine__set_modules_path(struct machine *machine)
 	if (!version)
 		return -1;
 
-	snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s/kernel",
+	snprintf(modules_path, sizeof(modules_path), "%s/lib/modules/%s",
 		 machine->root_dir, version);
 	free(version);
 
-	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path);
+	return map_groups__set_modules_path_dir(&machine->kmaps, modules_path, 0);
 }
 
 static int machine__create_module(void *arg, const char *name, u64 start)
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 47b2983..56ff9be 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -548,11 +548,10 @@ static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
 	u32 val;
 	u32 *reg;
 
-	offset >>= 1;
 	reg = vgic_bitmap_get_reg(&vcpu->kvm->arch.vgic.irq_cfg,
-				  vcpu->vcpu_id, offset);
+				  vcpu->vcpu_id, offset >> 1);
 
-	if (offset & 2)
+	if (offset & 4)
 		val = *reg >> 16;
 	else
 		val = *reg & 0xffff;
@@ -561,13 +560,13 @@ static bool handle_mmio_cfg_reg(struct kvm_vcpu *vcpu,
 	vgic_reg_access(mmio, &val, offset,
 			ACCESS_READ_VALUE | ACCESS_WRITE_VALUE);
 	if (mmio->is_write) {
-		if (offset < 4) {
+		if (offset < 8) {
 			*reg = ~0U; /* Force PPIs/SGIs to 1 */
 			return false;
 		}
 
 		val = vgic_cfg_compress(val);
-		if (offset & 2) {
+		if (offset & 4) {
 			*reg &= 0xffff;
 			*reg |= val << 16;
 		} else {
@@ -916,6 +915,7 @@ static void vgic_dispatch_sgi(struct kvm_vcpu *vcpu, u32 reg)
 	case 0:
 		if (!target_cpus)
 			return;
+		break;
 
 	case 1:
 		target_cpus = ((1 << nrcpus) - 1) & ~(1 << vcpu_id) & 0xff;
@@ -1667,10 +1667,11 @@ static int vgic_ioaddr_assign(struct kvm *kvm, phys_addr_t *ioaddr,
 	if (addr + size < addr)
 		return -EINVAL;
 
+	*ioaddr = addr;
 	ret = vgic_ioaddr_overlap(kvm);
 	if (ret)
-		return ret;
-	*ioaddr = addr;
+		*ioaddr = VGIC_ADDR_UNDEF;
+
 	return ret;
 }
 
diff --git a/virt/kvm/assigned-dev.c b/virt/kvm/assigned-dev.c
index 8db4370..bf06577 100644
--- a/virt/kvm/assigned-dev.c
+++ b/virt/kvm/assigned-dev.c
@@ -395,7 +395,8 @@ static int assigned_device_enable_host_msix(struct kvm *kvm,
 	if (dev->entries_nr == 0)
 		return r;
 
-	r = pci_enable_msix(dev->dev, dev->host_msix_entries, dev->entries_nr);
+	r = pci_enable_msix_exact(dev->dev,
+				  dev->host_msix_entries, dev->entries_nr);
 	if (r)
 		return r;
 
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 10df100..06e6401 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -101,7 +101,7 @@ static void async_pf_execute(struct work_struct *work)
 	if (waitqueue_active(&vcpu->wq))
 		wake_up_interruptible(&vcpu->wq);
 
-	mmdrop(mm);
+	mmput(mm);
 	kvm_put_kvm(vcpu->kvm);
 }
 
@@ -118,7 +118,7 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 		flush_work(&work->work);
 #else
 		if (cancel_work_sync(&work->work)) {
-			mmdrop(work->mm);
+			mmput(work->mm);
 			kvm_put_kvm(vcpu->kvm); /* == work->vcpu->kvm */
 			kmem_cache_free(async_pf_cache, work);
 		}
@@ -183,7 +183,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 	work->addr = hva;
 	work->arch = *arch;
 	work->mm = current->mm;
-	atomic_inc(&work->mm->mm_count);
+	atomic_inc(&work->mm->mm_users);
 	kvm_get_kvm(work->vcpu->kvm);
 
 	/* this can't really happen otherwise gfn_to_pfn_async
@@ -201,7 +201,7 @@ int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, unsigned long hva,
 	return 1;
 retry_sync:
 	kvm_put_kvm(work->vcpu->kvm);
-	mmdrop(work->mm);
+	mmput(work->mm);
 	kmem_cache_free(async_pf_cache, work);
 	return 0;
 }