Linux-libre 4.2.4-gnupck-4.2.4-gnu

271 files changed, 2716 insertions, 1316 deletions

diff --git a/Documentation/HOWTO b/Documentation/HOWTO
index 93aa86046..21152d397 100644
--- a/Documentation/HOWTO
+++ b/Documentation/HOWTO
@@ -218,16 +218,16 @@ The development process
 Linux kernel development process currently consists of a few different
 main kernel "branches" and lots of different subsystem-specific kernel
 branches.  These different branches are:
-  - main 3.x kernel tree
-  - 3.x.y -stable kernel tree
-  - 3.x -git kernel patches
+  - main 4.x kernel tree
+  - 4.x.y -stable kernel tree
+  - 4.x -git kernel patches
   - subsystem specific kernel trees and patches
-  - the 3.x -next kernel tree for integration tests
+  - the 4.x -next kernel tree for integration tests
 
-3.x kernel tree
+4.x kernel tree
 -----------------
-3.x kernels are maintained by Linus Torvalds, and can be found on
-kernel.org in the pub/linux/kernel/v3.x/ directory.  Its development
+4.x kernels are maintained by Linus Torvalds, and can be found on
+kernel.org in the pub/linux/kernel/v4.x/ directory.  Its development
 process is as follows:
   - As soon as a new kernel is released a two weeks window is open,
     during this period of time maintainers can submit big diffs to
@@ -262,20 +262,20 @@ mailing list about kernel releases:
 	released according to perceived bug status, not according to a
 	preconceived timeline."
 
-3.x.y -stable kernel tree
+4.x.y -stable kernel tree
 ---------------------------
 Kernels with 3-part versions are -stable kernels. They contain
 relatively small and critical fixes for security problems or significant
-regressions discovered in a given 3.x kernel.
+regressions discovered in a given 4.x kernel.
 
 This is the recommended branch for users who want the most recent stable
 kernel and are not interested in helping test development/experimental
 versions.
 
-If no 3.x.y kernel is available, then the highest numbered 3.x
+If no 4.x.y kernel is available, then the highest numbered 4.x
 kernel is the current stable kernel.
 
-3.x.y are maintained by the "stable" team <stable@vger.kernel.org>, and
+4.x.y are maintained by the "stable" team <stable@vger.kernel.org>, and
 are released as needs dictate.  The normal release period is approximately
 two weeks, but it can be longer if there are no pressing problems.  A
 security-related problem, instead, can cause a release to happen almost
@@ -285,7 +285,7 @@ The file Documentation/stable_kernel_rules.txt in the kernel tree
 documents what kinds of changes are acceptable for the -stable tree, and
 how the release process works.
 
-3.x -git patches
+4.x -git patches
 ------------------
 These are daily snapshots of Linus' kernel tree which are managed in a
 git repository (hence the name.) These patches are usually released
@@ -317,9 +317,9 @@ revisions to it, and maintainers can mark patches as under review,
 accepted, or rejected.  Most of these patchwork sites are listed at
 http://patchwork.kernel.org/.
 
-3.x -next kernel tree for integration tests
+4.x -next kernel tree for integration tests
 ---------------------------------------------
-Before updates from subsystem trees are merged into the mainline 3.x
+Before updates from subsystem trees are merged into the mainline 4.x
 tree, they need to be integration-tested.  For this purpose, a special
 testing repository exists into which virtually all subsystem trees are
 pulled on an almost daily basis:
diff --git a/Makefile b/Makefile
index d26a7d1e9..4546f3911 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 2
-SUBLEVEL = 3
+SUBLEVEL = 4
 EXTRAVERSION = -gnu
 NAME = Hurr durr I'ma sheep
 
diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c
index e7769c3ab..ac79491ee 100644
--- a/arch/arc/plat-axs10x/axs10x.c
+++ b/arch/arc/plat-axs10x/axs10x.c
@@ -402,6 +402,8 @@ static void __init axs103_early_init(void)
 	unsigned int num_cores = (read_aux_reg(ARC_REG_MCIP_BCR) >> 16) & 0x3F;
 	if (num_cores > 2)
 		arc_set_core_freq(50 * 1000000);
+	else if (num_cores == 2)
+		arc_set_core_freq(75 * 1000000);
 #endif
 
 	switch (arc_get_core_freq()/1000000) {
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 7451b447c..2c2b28ee4 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -54,6 +54,14 @@ AS		+= -EL
 LD		+= -EL
 endif
 
+#
+# The Scalar Replacement of Aggregates (SRA) optimization pass in GCC 4.9 and
+# later may result in code being generated that handles signed short and signed
+# char struct members incorrectly. So disable it.
+# (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65932)
+#
+KBUILD_CFLAGS	+= $(call cc-option,-fno-ipa-sra)
+
 # This selects which instruction set is used.
 # Note that GCC does not numerically define an architecture version
 # macro, but instead defines a whole series of macros which makes
diff --git a/arch/arm/boot/dts/exynos5420.dtsi b/arch/arm/boot/dts/exynos5420.dtsi
index 534f27ceb..fa8107dec 100644
--- a/arch/arm/boot/dts/exynos5420.dtsi
+++ b/arch/arm/boot/dts/exynos5420.dtsi
@@ -1118,7 +1118,7 @@
 		interrupt-parent = <&combiner>;
 		interrupts = <3 0>;
 		clock-names = "sysmmu", "master";
-		clocks = <&clock CLK_SMMU_FIMD1M0>, <&clock CLK_FIMD1>;
+		clocks = <&clock CLK_SMMU_FIMD1M1>, <&clock CLK_FIMD1>;
 		power-domains = <&disp_pd>;
 		#iommu-cells = <0>;
 	};
diff --git a/arch/arm/boot/dts/imx6qdl-rex.dtsi b/arch/arm/boot/dts/imx6qdl-rex.dtsi
index 3373fd958..a50356243 100644
--- a/arch/arm/boot/dts/imx6qdl-rex.dtsi
+++ b/arch/arm/boot/dts/imx6qdl-rex.dtsi
@@ -35,7 +35,6 @@
 			compatible = "regulator-fixed";
 			reg = <1>;
 			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_usbh1>;
 			regulator-name = "usbh1_vbus";
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
@@ -47,7 +46,6 @@
 			compatible = "regulator-fixed";
 			reg = <2>;
 			pinctrl-names = "default";
-			pinctrl-0 = <&pinctrl_usbotg>;
 			regulator-name = "usb_otg_vbus";
 			regulator-min-microvolt = <5000000>;
 			regulator-max-microvolt = <5000000>;
diff --git a/arch/arm/boot/dts/omap3-beagle.dts b/arch/arm/boot/dts/omap3-beagle.dts
index a5474113c..67659a0ed 100644
--- a/arch/arm/boot/dts/omap3-beagle.dts
+++ b/arch/arm/boot/dts/omap3-beagle.dts
@@ -202,7 +202,7 @@
 
 	tfp410_pins: pinmux_tfp410_pins {
 		pinctrl-single,pins = <
-			0x194 (PIN_OUTPUT | MUX_MODE4)	/* hdq_sio.gpio_170 */
+			0x196 (PIN_OUTPUT | MUX_MODE4)	/* hdq_sio.gpio_170 */
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts
index 275618f19..5771a149c 100644
--- a/arch/arm/boot/dts/omap5-uevm.dts
+++ b/arch/arm/boot/dts/omap5-uevm.dts
@@ -174,8 +174,8 @@
 
 	i2c5_pins: pinmux_i2c5_pins {
 		pinctrl-single,pins = <
-			0x184 (PIN_INPUT | MUX_MODE0)		/* i2c5_scl */
-			0x186 (PIN_INPUT | MUX_MODE0)		/* i2c5_sda */
+			0x186 (PIN_INPUT | MUX_MODE0)		/* i2c5_scl */
+			0x188 (PIN_INPUT | MUX_MODE0)		/* i2c5_sda */
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/sun7i-a20.dtsi b/arch/arm/boot/dts/sun7i-a20.dtsi
index 6a63f30c9..f5f384c04 100644
--- a/arch/arm/boot/dts/sun7i-a20.dtsi
+++ b/arch/arm/boot/dts/sun7i-a20.dtsi
@@ -107,7 +107,7 @@
 				720000	1200000
 				528000	1100000
 				312000	1000000
-				144000	900000
+				144000	1000000
 				>;
 			#cooling-cells = <2>;
 			cooling-min-level = <0>;
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
index a6ad93c9b..fd9eefce0 100644
--- a/arch/arm/kernel/kgdb.c
+++ b/arch/arm/kernel/kgdb.c
@@ -259,15 +259,17 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 	if (err)
 		return err;
 
-	patch_text((void *)bpt->bpt_addr,
-		   *(unsigned int *)arch_kgdb_ops.gdb_bpt_instr);
+	/* Machine is already stopped, so we can use __patch_text() directly */
+	__patch_text((void *)bpt->bpt_addr,
+		     *(unsigned int *)arch_kgdb_ops.gdb_bpt_instr);
 
 	return err;
 }
 
 int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
 {
-	patch_text((void *)bpt->bpt_addr, *(unsigned int *)bpt->saved_instr);
+	/* Machine is already stopped, so we can use __patch_text() directly */
+	__patch_text((void *)bpt->bpt_addr, *(unsigned int *)bpt->saved_instr);
 
 	return 0;
 }
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 54272e0be..7d5379c1c 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -795,8 +795,10 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu)
 
 	/* Don't bother with PPIs; they're already affine */
 	irq = platform_get_irq(pdev, 0);
-	if (irq >= 0 && irq_is_percpu(irq))
+	if (irq >= 0 && irq_is_percpu(irq)) {
+		cpumask_setall(&pmu->supported_cpus);
 		return 0;
+	}
 
 	irqs = kcalloc(pdev->num_resources, sizeof(*irqs), GFP_KERNEL);
 	if (!irqs)
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 423663e23..586eef262 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -343,12 +343,17 @@ setup_return(struct pt_regs *regs, struct ksignal *ksig,
 		 */
 		thumb = handler & 1;
 
-#if __LINUX_ARM_ARCH__ >= 7
+#if __LINUX_ARM_ARCH__ >= 6
 		/*
-		 * Clear the If-Then Thumb-2 execution state
-		 * ARM spec requires this to be all 000s in ARM mode
-		 * Snapdragon S4/Krait misbehaves on a Thumb=>ARM
-		 * signal transition without this.
+		 * Clear the If-Then Thumb-2 execution state.  ARM spec
+		 * requires this to be all 000s in ARM mode.  Snapdragon
+		 * S4/Krait misbehaves on a Thumb=>ARM signal transition
+		 * without this.
+		 *
+		 * We must do this whenever we are running on a Thumb-2
+		 * capable CPU, which includes ARMv6T2.  However, we elect
+		 * to do this whenever we're on an ARMv6 or later CPU for
+		 * simplicity.
 		 */
 		cpsr &= ~PSR_IT_MASK;
 #endif
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 702740d37..51a59504b 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -515,8 +515,7 @@ ARM_BE8(rev	r6, r6  )
 
 	mrc	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
 	str	r2, [vcpu, #VCPU_TIMER_CNTV_CTL]
-	bic	r2, #1			@ Clear ENABLE
-	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
+
 	isb
 
 	mrrc	p15, 3, rr_lo_hi(r2, r3), c14	@ CNTV_CVAL
@@ -529,6 +528,9 @@ ARM_BE8(rev	r6, r6  )
 	mcrr	p15, 4, r2, r2, c14	@ CNTVOFF
 
 1:
+	mov	r2, #0			@ Clear ENABLE
+	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
+
 	@ Allow physical timer/counter access for the host
 	mrc	p15, 4, r2, c14, c1, 0	@ CNTHCTL
 	orr	r2, r2, #(CNTHCTL_PL1PCEN | CNTHCTL_PL1PCTEN)
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 7b4201294..6984342da 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -1792,8 +1792,10 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		if (vma->vm_flags & VM_PFNMAP) {
 			gpa_t gpa = mem->guest_phys_addr +
 				    (vm_start - mem->userspace_addr);
-			phys_addr_t pa = (vma->vm_pgoff << PAGE_SHIFT) +
-					 vm_start - vma->vm_start;
+			phys_addr_t pa;
+
+			pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
+			pa += vm_start - vma->vm_start;
 
 			/* IO region dirty page logging not allowed */
 			if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES)
diff --git a/arch/arm/mach-exynos/mcpm-exynos.c b/arch/arm/mach-exynos/mcpm-exynos.c
index 9bdf54795..56978199c 100644
--- a/arch/arm/mach-exynos/mcpm-exynos.c
+++ b/arch/arm/mach-exynos/mcpm-exynos.c
@@ -20,6 +20,7 @@
 #include <asm/cputype.h>
 #include <asm/cp15.h>
 #include <asm/mcpm.h>
+#include <asm/smp_plat.h>
 
 #include "regs-pmu.h"
 #include "common.h"
@@ -70,7 +71,31 @@ static int exynos_cpu_powerup(unsigned int cpu, unsigned int cluster)
 		cluster >= EXYNOS5420_NR_CLUSTERS)
 		return -EINVAL;
 
-	exynos_cpu_power_up(cpunr);
+	if (!exynos_cpu_power_state(cpunr)) {
+		exynos_cpu_power_up(cpunr);
+
+		/*
+		 * This assumes the cluster number of the big cores(Cortex A15)
+		 * is 0 and the Little cores(Cortex A7) is 1.
+		 * When the system was booted from the Little core,
+		 * they should be reset during power up cpu.
+		 */
+		if (cluster &&
+		    cluster == MPIDR_AFFINITY_LEVEL(cpu_logical_map(0), 1)) {
+			/*
+			 * Before we reset the Little cores, we should wait
+			 * the SPARE2 register is set to 1 because the init
+			 * codes of the iROM will set the register after
+			 * initialization.
+			 */
+			while (!pmu_raw_readl(S5P_PMU_SPARE2))
+				udelay(10);
+
+			pmu_raw_writel(EXYNOS5420_KFC_CORE_RESET(cpu),
+					EXYNOS_SWRESET);
+		}
+	}
+
 	return 0;
 }
 
diff --git a/arch/arm/mach-exynos/regs-pmu.h b/arch/arm/mach-exynos/regs-pmu.h
index b7614333d..fba9068ed 100644
--- a/arch/arm/mach-exynos/regs-pmu.h
+++ b/arch/arm/mach-exynos/regs-pmu.h
@@ -513,6 +513,12 @@ static inline unsigned int exynos_pmu_cpunr(unsigned int mpidr)
 #define SPREAD_ENABLE						0xF
 #define SPREAD_USE_STANDWFI					0xF
 
+#define EXYNOS5420_KFC_CORE_RESET0				BIT(8)
+#define EXYNOS5420_KFC_ETM_RESET0				BIT(20)
+
+#define EXYNOS5420_KFC_CORE_RESET(_nr)				\
+	((EXYNOS5420_KFC_CORE_RESET0 | EXYNOS5420_KFC_ETM_RESET0) << (_nr))
+
 #define EXYNOS5420_BB_CON1					0x0784
 #define EXYNOS5420_BB_SEL_EN					BIT(31)
 #define EXYNOS5420_BB_PMOS_EN					BIT(7)
diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c
index ad9529cc4..daa1a65f2 100644
--- a/arch/arm/plat-pxa/ssp.c
+++ b/arch/arm/plat-pxa/ssp.c
@@ -107,7 +107,6 @@ static const struct of_device_id pxa_ssp_of_ids[] = {
 	{ .compatible = "mvrl,pxa168-ssp",	.data = (void *) PXA168_SSP },
 	{ .compatible = "mrvl,pxa910-ssp",	.data = (void *) PXA910_SSP },
 	{ .compatible = "mrvl,ce4100-ssp",	.data = (void *) CE4100_SSP },
-	{ .compatible = "mrvl,lpss-ssp",	.data = (void *) LPSS_SSP },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, pxa_ssp_of_ids);
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index e8ca6eaed..13671a9cf 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -258,7 +258,8 @@ static bool __init efi_virtmap_init(void)
 		 */
 		if (!is_normal_ram(md))
 			prot = __pgprot(PROT_DEVICE_nGnRE);
-		else if (md->type == EFI_RUNTIME_SERVICES_CODE)
+		else if (md->type == EFI_RUNTIME_SERVICES_CODE ||
+			 !PAGE_ALIGNED(md->phys_addr))
 			prot = PAGE_KERNEL_EXEC;
 		else
 			prot = PAGE_KERNEL;
diff --git a/arch/arm64/kernel/entry-ftrace.S b/arch/arm64/kernel/entry-ftrace.S
index 08cafc518..0f03a8fe2 100644
--- a/arch/arm64/kernel/entry-ftrace.S
+++ b/arch/arm64/kernel/entry-ftrace.S
@@ -178,6 +178,24 @@ ENTRY(ftrace_stub)
 ENDPROC(ftrace_stub)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	/* save return value regs*/
+	.macro save_return_regs
+	sub sp, sp, #64
+	stp x0, x1, [sp]
+	stp x2, x3, [sp, #16]
+	stp x4, x5, [sp, #32]
+	stp x6, x7, [sp, #48]
+	.endm
+
+	/* restore return value regs*/
+	.macro restore_return_regs
+	ldp x0, x1, [sp]
+	ldp x2, x3, [sp, #16]
+	ldp x4, x5, [sp, #32]
+	ldp x6, x7, [sp, #48]
+	add sp, sp, #64
+	.endm
+
 /*
  * void ftrace_graph_caller(void)
  *
@@ -204,11 +222,11 @@ ENDPROC(ftrace_graph_caller)
  * only when CONFIG_HAVE_FUNCTION_GRAPH_FP_TEST is enabled.
  */
 ENTRY(return_to_handler)
-	str	x0, [sp, #-16]!
+	save_return_regs
 	mov	x0, x29			//     parent's fp
 	bl	ftrace_return_to_handler// addr = ftrace_return_to_hander(fp);
 	mov	x30, x0			// restore the original return address
-	ldr	x0, [sp], #16
+	restore_return_regs
 	ret
 END(return_to_handler)
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 94d98cd1a..27c3e6fd2 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -278,6 +278,7 @@ retry:
 			 * starvation.
 			 */
 			mm_flags &= ~FAULT_FLAG_ALLOW_RETRY;
+			mm_flags |= FAULT_FLAG_TRIED;
 			goto retry;
 		}
 	}
diff --git a/arch/m68k/include/asm/linkage.h b/arch/m68k/include/asm/linkage.h
index 5a822bb79..066e74f66 100644
--- a/arch/m68k/include/asm/linkage.h
+++ b/arch/m68k/include/asm/linkage.h
@@ -4,4 +4,34 @@
 #define __ALIGN .align 4
 #define __ALIGN_STR ".align 4"
 
+/*
+ * Make sure the compiler doesn't do anything stupid with the
+ * arguments on the stack - they are owned by the *caller*, not
+ * the callee. This just fools gcc into not spilling into them,
+ * and keeps it from doing tailcall recursion and/or using the
+ * stack slots for temporaries, since they are live and "used"
+ * all the way to the end of the function.
+ */
+#define asmlinkage_protect(n, ret, args...) \
+	__asmlinkage_protect##n(ret, ##args)
+#define __asmlinkage_protect_n(ret, args...) \
+	__asm__ __volatile__ ("" : "=r" (ret) : "0" (ret), ##args)
+#define __asmlinkage_protect0(ret) \
+	__asmlinkage_protect_n(ret)
+#define __asmlinkage_protect1(ret, arg1) \
+	__asmlinkage_protect_n(ret, "m" (arg1))
+#define __asmlinkage_protect2(ret, arg1, arg2) \
+	__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2))
+#define __asmlinkage_protect3(ret, arg1, arg2, arg3) \
+	__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3))
+#define __asmlinkage_protect4(ret, arg1, arg2, arg3, arg4) \
+	__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \
+			      "m" (arg4))
+#define __asmlinkage_protect5(ret, arg1, arg2, arg3, arg4, arg5) \
+	__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \
+			      "m" (arg4), "m" (arg5))
+#define __asmlinkage_protect6(ret, arg1, arg2, arg3, arg4, arg5, arg6) \
+	__asmlinkage_protect_n(ret, "m" (arg1), "m" (arg2), "m" (arg3), \
+			      "m" (arg4), "m" (arg5), "m" (arg6))
+
 #endif
diff --git a/arch/mips/kernel/cps-vec.S b/arch/mips/kernel/cps-vec.S
index 9f71c06ae..209ded168 100644
--- a/arch/mips/kernel/cps-vec.S
+++ b/arch/mips/kernel/cps-vec.S
@@ -39,6 +39,7 @@
 	 mfc0	\dest, CP0_CONFIG, 3
 	andi	\dest, \dest, MIPS_CONF3_MT
 	beqz	\dest, \nomt
+	 nop
 	.endm
 
 .section .text.cps-vec
@@ -223,10 +224,9 @@ LEAF(excep_ejtag)
 	END(excep_ejtag)
 
 LEAF(mips_cps_core_init)
-#ifdef CONFIG_MIPS_MT
+#ifdef CONFIG_MIPS_MT_SMP
 	/* Check that the core implements the MT ASE */
 	has_mt	t0, 3f
-	 nop
 
 	.set	push
 	.set	mips64r2
@@ -310,8 +310,9 @@ LEAF(mips_cps_boot_vpes)
 	PTR_ADDU t0, t0, t1
 
 	/* Calculate this VPEs ID. If the core doesn't support MT use 0 */
+	li	t9, 0
+#ifdef CONFIG_MIPS_MT_SMP
 	has_mt	ta2, 1f
-	 li	t9, 0
 
 	/* Find the number of VPEs present in the core */
 	mfc0	t1, CP0_MVPCONF0
@@ -330,6 +331,7 @@ LEAF(mips_cps_boot_vpes)
 	/* Retrieve the VPE ID from EBase.CPUNum */
 	mfc0	t9, $15, 1
 	and	t9, t9, t1
+#endif
 
 1:	/* Calculate a pointer to this VPEs struct vpe_boot_config */
 	li	t1, VPEBOOTCFG_SIZE
@@ -337,7 +339,7 @@ LEAF(mips_cps_boot_vpes)
 	PTR_L	ta3, COREBOOTCFG_VPECONFIG(t0)
 	PTR_ADDU v0, v0, ta3
 
-#ifdef CONFIG_MIPS_MT
+#ifdef CONFIG_MIPS_MT_SMP
 
 	/* If the core doesn't support MT then return */
 	bnez	ta2, 1f
@@ -451,7 +453,7 @@ LEAF(mips_cps_boot_vpes)
 
 2:	.set	pop
 
-#endif /* CONFIG_MIPS_MT */
+#endif /* CONFIG_MIPS_MT_SMP */
 
 	/* Return */
 	jr	ra
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 008b33786..4ceac5cdd 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -338,7 +338,7 @@ static void __init bootmem_init(void)
 		if (end <= reserved_end)
 			continue;
 #ifdef CONFIG_BLK_DEV_INITRD
-		/* mapstart should be after initrd_end */
+		/* Skip zones before initrd and initrd itself */
 		if (initrd_end && end <= (unsigned long)PFN_UP(__pa(initrd_end)))
 			continue;
 #endif
@@ -371,6 +371,14 @@ static void __init bootmem_init(void)
 		max_low_pfn = PFN_DOWN(HIGHMEM_START);
 	}
 
+#ifdef CONFIG_BLK_DEV_INITRD
+	/*
+	 * mapstart should be after initrd_end
+	 */
+	if (initrd_end)
+		mapstart = max(mapstart, (unsigned long)PFN_UP(__pa(initrd_end)));
+#endif
+
 	/*
 	 * Initialize the boot-time allocator with low memory only.
 	 */
diff --git a/arch/mips/loongson64/common/env.c b/arch/mips/loongson64/common/env.c
index f6c44dd33..d6d07ad56 100644
--- a/arch/mips/loongson64/common/env.c
+++ b/arch/mips/loongson64/common/env.c
@@ -64,6 +64,9 @@ void __init prom_init_env(void)
 	}
 	if (memsize == 0)
 		memsize = 256;
+
+	loongson_sysconf.nr_uarts = 1;
+
 	pr_info("memsize=%u, highmemsize=%u\n", memsize, highmemsize);
 #else
 	struct boot_params *boot_p;
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index eeaf0245c..815892ed3 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -100,7 +100,7 @@ static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)
 	else
 #endif
 #if defined(CONFIG_ZONE_DMA) && !defined(CONFIG_ZONE_DMA32)
-	     if (dev->coherent_dma_mask < DMA_BIT_MASK(64))
+	     if (dev->coherent_dma_mask < DMA_BIT_MASK(sizeof(phys_addr_t) * 8))
 		dma_flag = __GFP_DMA;
 	else
 #endif
diff --git a/arch/mips/net/bpf_jit_asm.S b/arch/mips/net/bpf_jit_asm.S
index e92726099..dabf4179c 100644
--- a/arch/mips/net/bpf_jit_asm.S
+++ b/arch/mips/net/bpf_jit_asm.S
@@ -64,8 +64,20 @@ sk_load_word_positive:
 	PTR_ADDU t1, $r_skb_data, offset
 	lw	$r_A, 0(t1)
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
 	wsbh	t0, $r_A
 	rotr	$r_A, t0, 16
+# else
+	sll	t0, $r_A, 24
+	srl	t1, $r_A, 24
+	srl	t2, $r_A, 8
+	or	t0, t0, t1
+	andi	t2, t2, 0xff00
+	andi	t1, $r_A, 0xff00
+	or	t0, t0, t2
+	sll	t1, t1, 8
+	or	$r_A, t0, t1
+# endif
 #endif
 	jr	$r_ra
 	 move	$r_ret, zero
@@ -80,8 +92,16 @@ sk_load_half_positive:
 	PTR_ADDU t1, $r_skb_data, offset
 	lh	$r_A, 0(t1)
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
 	wsbh	t0, $r_A
 	seh	$r_A, t0
+# else
+	sll	t0, $r_A, 24
+	andi	t1, $r_A, 0xff00
+	sra	t0, t0, 16
+	srl	t1, t1, 8
+	or	$r_A, t0, t1
+# endif
 #endif
 	jr	$r_ra
 	 move	$r_ret, zero
@@ -148,23 +168,47 @@ sk_load_byte_positive:
 NESTED(bpf_slow_path_word, (6 * SZREG), $r_sp)
 	bpf_slow_path_common(4)
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
 	wsbh	t0, $r_s0
 	jr	$r_ra
 	 rotr	$r_A, t0, 16
-#endif
+# else
+	sll	t0, $r_s0, 24
+	srl	t1, $r_s0, 24
+	srl	t2, $r_s0, 8
+	or	t0, t0, t1
+	andi	t2, t2, 0xff00
+	andi	t1, $r_s0, 0xff00
+	or	t0, t0, t2
+	sll	t1, t1, 8
+	jr	$r_ra
+	 or	$r_A, t0, t1
+# endif
+#else
 	jr	$r_ra
-	move	$r_A, $r_s0
+	 move	$r_A, $r_s0
+#endif
 
 	END(bpf_slow_path_word)
 
 NESTED(bpf_slow_path_half, (6 * SZREG), $r_sp)
 	bpf_slow_path_common(2)
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
 	jr	$r_ra
 	 wsbh	$r_A, $r_s0
-#endif
+# else
+	sll	t0, $r_s0, 8
+	andi	t1, $r_s0, 0xff00
+	andi	t0, t0, 0xff00
+	srl	t1, t1, 8
+	jr	$r_ra
+	 or	$r_A, t0, t1
+# endif
+#else
 	jr	$r_ra
 	 move	$r_A, $r_s0
+#endif
 
 	END(bpf_slow_path_half)
 
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 05ea8fc7f..4816fe2fa 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -827,12 +827,15 @@ int kvmppc_h_logical_ci_load(struct kvm_vcpu *vcpu)
 	unsigned long size = kvmppc_get_gpr(vcpu, 4);
 	unsigned long addr = kvmppc_get_gpr(vcpu, 5);
 	u64 buf;
+	int srcu_idx;
 	int ret;
 
 	if (!is_power_of_2(size) || (size > sizeof(buf)))
 		return H_TOO_HARD;
 
+	srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	ret = kvm_io_bus_read(vcpu, KVM_MMIO_BUS, addr, size, &buf);
+	srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
 	if (ret != 0)
 		return H_TOO_HARD;
 
@@ -867,6 +870,7 @@ int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu)
 	unsigned long addr = kvmppc_get_gpr(vcpu, 5);
 	unsigned long val = kvmppc_get_gpr(vcpu, 6);
 	u64 buf;
+	int srcu_idx;
 	int ret;
 
 	switch (size) {
@@ -890,7 +894,9 @@ int kvmppc_h_logical_ci_store(struct kvm_vcpu *vcpu)
 		return H_TOO_HARD;
 	}
 
+	srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	ret = kvm_io_bus_write(vcpu, KVM_MMIO_BUS, addr, size, &buf);
+	srcu_read_unlock(&vcpu->kvm->srcu, srcu_idx);
 	if (ret != 0)
 		return H_TOO_HARD;
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 68d067ad4..a9f753fb7 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2178,7 +2178,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		vc->runner = vcpu;
 		if (n_ceded == vc->n_runnable) {
 			kvmppc_vcore_blocked(vc);
-		} else if (should_resched()) {
+		} else if (need_resched()) {
 			vc->vcore_state = VCORE_PREEMPT;
 			/* Let something else run */
 			cond_resched_lock(&vc->lock);
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 76408cf0a..437f64350 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1171,6 +1171,7 @@ mc_cont:
 	bl	kvmhv_accumulate_time
 #endif
 
+	mr 	r3, r12
 	/* Increment exit count, poke other threads to exit */
 	bl	kvmhv_commence_exit
 	nop
diff --git a/arch/powerpc/platforms/pasemi/msi.c b/arch/powerpc/platforms/pasemi/msi.c
index 27f2b187a..ff1bb4b69 100644
--- a/arch/powerpc/platforms/pasemi/msi.c
+++ b/arch/powerpc/platforms/pasemi/msi.c
@@ -63,6 +63,7 @@ static struct irq_chip mpic_pasemi_msi_chip = {
 static void pasemi_msi_teardown_msi_irqs(struct pci_dev *pdev)
 {
 	struct msi_desc *entry;
+	irq_hw_number_t hwirq;
 
 	pr_debug("pasemi_msi_teardown_msi_irqs, pdev %p\n", pdev);
 
@@ -70,10 +71,10 @@ static void pasemi_msi_teardown_msi_irqs(struct pci_dev *pdev)
 		if (entry->irq == NO_IRQ)
 			continue;
 
+		hwirq = virq_to_hw(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
-		msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap,
-				       virq_to_hw(entry->irq), ALLOC_CHUNK);
 		irq_dispose_mapping(entry->irq);
+		msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap, hwirq, ALLOC_CHUNK);
 	}
 
 	return;
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 765d8ed55..fd16f86e5 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -99,6 +99,7 @@ void pnv_teardown_msi_irqs(struct pci_dev *pdev)
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
 	struct msi_desc *entry;
+	irq_hw_number_t hwirq;
 
 	if (WARN_ON(!phb))
 		return;
@@ -106,10 +107,10 @@ void pnv_teardown_msi_irqs(struct pci_dev *pdev)
 	list_for_each_entry(entry, &pdev->msi_list, list) {
 		if (entry->irq == NO_IRQ)
 			continue;
+		hwirq = virq_to_hw(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
-		msi_bitmap_free_hwirqs(&phb->msi_bmp,
-			virq_to_hw(entry->irq) - phb->msi_base, 1);
 		irq_dispose_mapping(entry->irq);
+		msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq - phb->msi_base, 1);
 	}
 }
 #endif /* CONFIG_PCI_MSI */
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 5236e5427..691e8e517 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -128,15 +128,16 @@ static void fsl_teardown_msi_irqs(struct pci_dev *pdev)
 {
 	struct msi_desc *entry;
 	struct fsl_msi *msi_data;
+	irq_hw_number_t hwirq;
 
 	list_for_each_entry(entry, &pdev->msi_list, list) {
 		if (entry->irq == NO_IRQ)
 			continue;
+		hwirq = virq_to_hw(entry->irq);
 		msi_data = irq_get_chip_data(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
-		msi_bitmap_free_hwirqs(&msi_data->bitmap,
-				       virq_to_hw(entry->irq), 1);
 		irq_dispose_mapping(entry->irq);
+		msi_bitmap_free_hwirqs(&msi_data->bitmap, hwirq, 1);
 	}
 
 	return;
diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c
index fc46ef3b8..4c3165fa5 100644
--- a/arch/powerpc/sysdev/mpic_u3msi.c
+++ b/arch/powerpc/sysdev/mpic_u3msi.c
@@ -107,15 +107,16 @@ static u64 find_u4_magic_addr(struct pci_dev *pdev, unsigned int hwirq)
 static void u3msi_teardown_msi_irqs(struct pci_dev *pdev)
 {
 	struct msi_desc *entry;
+	irq_hw_number_t hwirq;
 
         list_for_each_entry(entry, &pdev->msi_list, list) {
 		if (entry->irq == NO_IRQ)
 			continue;
 
+		hwirq = virq_to_hw(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
-		msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap,
-				       virq_to_hw(entry->irq), 1);
 		irq_dispose_mapping(entry->irq);
+		msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap, hwirq, 1);
 	}
 
 	return;
diff --git a/arch/powerpc/sysdev/ppc4xx_msi.c b/arch/powerpc/sysdev/ppc4xx_msi.c
index 6eb21f2ea..060f23775 100644
--- a/arch/powerpc/sysdev/ppc4xx_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_msi.c
@@ -124,16 +124,17 @@ void ppc4xx_teardown_msi_irqs(struct pci_dev *dev)
 {
 	struct msi_desc *entry;
 	struct ppc4xx_msi *msi_data = &ppc4xx_msi;
+	irq_hw_number_t hwirq;
 
 	dev_dbg(&dev->dev, "PCIE-MSI: tearing down msi irqs\n");
 
 	list_for_each_entry(entry, &dev->msi_list, list) {
 		if (entry->irq == NO_IRQ)
 			continue;
+		hwirq = virq_to_hw(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
-		msi_bitmap_free_hwirqs(&msi_data->bitmap,
-				virq_to_hw(entry->irq), 1);
 		irq_dispose_mapping(entry->irq);
+		msi_bitmap_free_hwirqs(&msi_data->bitmap, hwirq, 1);
 	}
 }
 
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index d4788111c..fac6ac979 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -10,7 +10,7 @@ targets += misc.o piggy.o sizes.h head.o
 
 KBUILD_CFLAGS := -m64 -D__KERNEL__ $(LINUX_INCLUDE) -O2
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
-KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks
+KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks -msoft-float
 KBUILD_CFLAGS += $(call cc-option,-mpacked-stack)
 KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
 
diff --git a/arch/s390/kernel/compat_signal.c b/arch/s390/kernel/compat_signal.c
index fe8d6924e..c78ba51ae 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -48,6 +48,19 @@ typedef struct
 	struct ucontext32 uc;
 } rt_sigframe32;
 
+static inline void sigset_to_sigset32(unsigned long *set64,
+				      compat_sigset_word *set32)
+{
+	set32[0] = (compat_sigset_word) set64[0];
+	set32[1] = (compat_sigset_word)(set64[0] >> 32);
+}
+
+static inline void sigset32_to_sigset(compat_sigset_word *set32,
+				      unsigned long *set64)
+{
+	set64[0] = (unsigned long) set32[0] | ((unsigned long) set32[1] << 32);
+}
+
 int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 {
 	int err;
@@ -303,10 +316,12 @@ COMPAT_SYSCALL_DEFINE0(sigreturn)
 {
 	struct pt_regs *regs = task_pt_regs(current);
 	sigframe32 __user *frame = (sigframe32 __user *)regs->gprs[15];
+	compat_sigset_t cset;
 	sigset_t set;
 
-	if (__copy_from_user(&set.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE32))
+	if (__copy_from_user(&cset.sig, &frame->sc.oldmask, _SIGMASK_COPY_SIZE32))
 		goto badframe;
+	sigset32_to_sigset(cset.sig, set.sig);
 	set_current_blocked(&set);
 	if (restore_sigregs32(regs, &frame->sregs))
 		goto badframe;
@@ -323,10 +338,12 @@ COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
 {
 	struct pt_regs *regs = task_pt_regs(current);
 	rt_sigframe32 __user *frame = (rt_sigframe32 __user *)regs->gprs[15];
+	compat_sigset_t cset;
 	sigset_t set;
 
-	if (__copy_from_user(&set, &frame->uc.uc_sigmask, sizeof(set)))
+	if (__copy_from_user(&cset, &frame->uc.uc_sigmask, sizeof(cset)))
 		goto badframe;
+	sigset32_to_sigset(cset.sig, set.sig);
 	set_current_blocked(&set);
 	if (compat_restore_altstack(&frame->uc.uc_stack))
 		goto badframe;
@@ -397,7 +414,7 @@ static int setup_frame32(struct ksignal *ksig, sigset_t *set,
 		return -EFAULT;
 
 	/* Create struct sigcontext32 on the signal stack */
-	memcpy(&sc.oldmask, &set->sig, _SIGMASK_COPY_SIZE32);
+	sigset_to_sigset32(set->sig, sc.oldmask);
 	sc.sregs = (__u32)(unsigned long __force) &frame->sregs;
 	if (__copy_to_user(&frame->sc, &sc, sizeof(frame->sc)))
 		return -EFAULT;
@@ -458,6 +475,7 @@ static int setup_frame32(struct ksignal *ksig, sigset_t *set,
 static int setup_rt_frame32(struct ksignal *ksig, sigset_t *set,
 			    struct pt_regs *regs)
 {
+	compat_sigset_t cset;
 	rt_sigframe32 __user *frame;
 	unsigned long restorer;
 	size_t frame_size;
@@ -505,11 +523,12 @@ static int setup_rt_frame32(struct ksignal *ksig, sigset_t *set,
 	store_sigregs();
 
 	/* Create ucontext on the signal stack. */
+	sigset_to_sigset32(set->sig, cset.sig);
 	if (__put_user(uc_flags, &frame->uc.uc_flags) ||
 	    __put_user(0, &frame->uc.uc_link) ||
 	    __compat_save_altstack(&frame->uc.uc_stack, regs->gprs[15]) ||
 	    save_sigregs32(regs, &frame->uc.uc_mcontext) ||
-	    __copy_to_user(&frame->uc.uc_sigmask, set, sizeof(*set)) ||
+	    __copy_to_user(&frame->uc.uc_sigmask, &cset, sizeof(cset)) ||
 	    save_sigregs_ext32(regs, &frame->uc.uc_mcontext_ext))
 		return -EFAULT;
 
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 8cb3e438f..d330840a2 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1219,7 +1219,18 @@ END(error_exit)
 
 /* Runs on exception stack */
 ENTRY(nmi)
+	/*
+	 * Fix up the exception frame if we're on Xen.
+	 * PARAVIRT_ADJUST_EXCEPTION_FRAME is guaranteed to push at most
+	 * one value to the stack on native, so it may clobber the rdx
+	 * scratch slot, but it won't clobber any of the important
+	 * slots past it.
+	 *
+	 * Xen is a different story, because the Xen frame itself overlaps
+	 * the "NMI executing" variable.
+	 */
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
+
 	/*
 	 * We allow breakpoints in NMIs. If a breakpoint occurs, then
 	 * the iretq it performs will take us out of NMI context.
@@ -1270,9 +1281,12 @@ ENTRY(nmi)
 	 * we don't want to enable interrupts, because then we'll end
 	 * up in an awkward situation in which IRQs are on but NMIs
 	 * are off.
+	 *
+	 * We also must not push anything to the stack before switching
+	 * stacks lest we corrupt the "NMI executing" variable.
 	 */
 
-	SWAPGS
+	SWAPGS_UNSAFE_STACK
 	cld
 	movq	%rsp, %rdx
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 9ebc3d009..2350ab781 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -311,6 +311,7 @@
 /* C1E active bits in int pending message */
 #define K8_INTP_C1E_ACTIVE_MASK		0x18000000
 #define MSR_K8_TSEG_ADDR		0xc0010112
+#define MSR_K8_TSEG_MASK		0xc0010113
 #define K8_MTRRFIXRANGE_DRAM_ENABLE	0x00040000 /* MtrrFixDramEn bit    */
 #define K8_MTRRFIXRANGE_DRAM_MODIFY	0x00080000 /* MtrrFixDramModEn bit */
 #define K8_MTRR_RDMEM_WRMEM_MASK	0x18181818 /* Mask: RdMem|WrMem    */
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index dca71714f..b12f81022 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -90,9 +90,9 @@ static __always_inline bool __preempt_count_dec_and_test(void)
 /*
  * Returns true when we need to resched and can (barring IRQ state).
  */
-static __always_inline bool should_resched(void)
+static __always_inline bool should_resched(int preempt_offset)
 {
-	return unlikely(!raw_cpu_read_4(__preempt_count));
+	return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset);
 }
 
 #ifdef CONFIG_PREEMPT
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 9d51fae1c..eaba08076 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -39,18 +39,27 @@ static inline void queued_spin_unlock(struct qspinlock *lock)
 }
 #endif
 
-#define virt_queued_spin_lock virt_queued_spin_lock
-
-static inline bool virt_queued_spin_lock(struct qspinlock *lock)
+#ifdef CONFIG_PARAVIRT
+#define virt_spin_lock virt_spin_lock
+static inline bool virt_spin_lock(struct qspinlock *lock)
 {
 	if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
 		return false;
 
-	while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0)
-		cpu_relax();
+	/*
+	 * On hypervisors without PARAVIRT_SPINLOCKS support we fall
+	 * back to a Test-and-Set spinlock, because fair locks have
+	 * horrible lock 'holder' preemption issues.
+	 */
+
+	do {
+		while (atomic_read(&lock->val) != 0)
+			cpu_relax();
+	} while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0);
 
 	return true;
 }
+#endif /* CONFIG_PARAVIRT */
 
 #include <asm-generic/qspinlock.h>
 
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c42827eb8..25f909362 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -338,10 +338,15 @@ done:
 
 static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr)
 {
+	unsigned long flags;
+
 	if (instr[0] != 0x90)
 		return;
 
+	local_irq_save(flags);
 	add_nops(instr + (a->instrlen - a->padlen), a->padlen);
+	sync_core();
+	local_irq_restore(flags);
 
 	DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ",
 		   instr, a->instrlen - a->padlen, a->padlen);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index cde732c1b..307a49828 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -336,6 +336,13 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 	apic_write(APIC_LVTT, lvtt_value);
 
 	if (lvtt_value & APIC_LVT_TIMER_TSCDEADLINE) {
+		/*
+		 * See Intel SDM: TSC-Deadline Mode chapter. In xAPIC mode,
+		 * writing to the APIC LVTT and TSC_DEADLINE MSR isn't serialized.
+		 * According to Intel, MFENCE can do the serialization here.
+		 */
+		asm volatile("mfence" : : : "memory");
+
 		printk_once(KERN_DEBUG "TSC deadline timer enabled\n");
 		return;
 	}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 206052e55..5880b482d 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2522,6 +2522,7 @@ void __init setup_ioapic_dest(void)
 	int pin, ioapic, irq, irq_entry;
 	const struct cpumask *mask;
 	struct irq_data *idata;
+	struct irq_chip *chip;
 
 	if (skip_ioapic_setup == 1)
 		return;
@@ -2545,9 +2546,9 @@ void __init setup_ioapic_dest(void)
 		else
 			mask = apic->target_cpus();
 
-		irq_set_affinity(irq, mask);
+		chip = irq_data_get_irq_chip(idata);
+		chip->irq_set_affinity(idata, mask, false);
 	}
-
 }
 #endif
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 6326ae24e..1b09c420c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2102,9 +2102,12 @@ static struct event_constraint *
 intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			    struct perf_event *event)
 {
-	struct event_constraint *c1 = cpuc->event_constraint[idx];
+	struct event_constraint *c1 = NULL;
 	struct event_constraint *c2;
 
+	if (idx >= 0) /* fake does < 0 */
+		c1 = cpuc->event_constraint[idx];
+
 	/*
 	 * first time only
 	 * - static constraint: no change across incremental scheduling calls
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index e068d6683..74ca2fe7a 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -185,10 +185,9 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 }
 
 #ifdef CONFIG_KEXEC_FILE
-static int get_nr_ram_ranges_callback(unsigned long start_pfn,
-				unsigned long nr_pfn, void *arg)
+static int get_nr_ram_ranges_callback(u64 start, u64 end, void *arg)
 {
-	int *nr_ranges = arg;
+	unsigned int *nr_ranges = arg;
 
 	(*nr_ranges)++;
 	return 0;
@@ -214,7 +213,7 @@ static void fill_up_crash_elf_data(struct crash_elf_data *ced,
 
 	ced->image = image;
 
-	walk_system_ram_range(0, -1, &nr_ranges,
+	walk_system_ram_res(0, -1, &nr_ranges,
 				get_nr_ram_ranges_callback);
 
 	ced->max_nr_ranges = nr_ranges;
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 58bcfb67c..ebb5657ee 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -41,10 +41,18 @@
 #include <asm/timer.h>
 #include <asm/special_insns.h>
 
-/* nop stub */
-void _paravirt_nop(void)
-{
-}
+/*
+ * nop stub, which must not clobber anything *including the stack* to
+ * avoid confusing the entry prologues.
+ */
+extern void _paravirt_nop(void);
+asm (".pushsection .entry.text, \"ax\"\n"
+     ".global _paravirt_nop\n"
+     "_paravirt_nop:\n\t"
+     "ret\n\t"
+     ".size _paravirt_nop, . - _paravirt_nop\n\t"
+     ".type _paravirt_nop, @function\n\t"
+     ".popsection");
 
 /* identity function, which can be inlined */
 u32 _paravirt_ident_32(u32 x)
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index f6b916387..a90ac9556 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -497,27 +497,59 @@ void set_personality_ia32(bool x32)
 }
 EXPORT_SYMBOL_GPL(set_personality_ia32);
 
+/*
+ * Called from fs/proc with a reference on @p to find the function
+ * which called into schedule(). This needs to be done carefully
+ * because the task might wake up and we might look at a stack
+ * changing under us.
+ */
 unsigned long get_wchan(struct task_struct *p)
 {
-	unsigned long stack;
-	u64 fp, ip;
+	unsigned long start, bottom, top, sp, fp, ip;
 	int count = 0;
 
 	if (!p || p == current || p->state == TASK_RUNNING)
 		return 0;
-	stack = (unsigned long)task_stack_page(p);
-	if (p->thread.sp < stack || p->thread.sp >= stack+THREAD_SIZE)
+
+	start = (unsigned long)task_stack_page(p);
+	if (!start)
+		return 0;
+
+	/*
+	 * Layout of the stack page:
+	 *
+	 * ----------- topmax = start + THREAD_SIZE - sizeof(unsigned long)
+	 * PADDING
+	 * ----------- top = topmax - TOP_OF_KERNEL_STACK_PADDING
+	 * stack
+	 * ----------- bottom = start + sizeof(thread_info)
+	 * thread_info
+	 * ----------- start
+	 *
+	 * The tasks stack pointer points at the location where the
+	 * framepointer is stored. The data on the stack is:
+	 * ... IP FP ... IP FP
+	 *
+	 * We need to read FP and IP, so we need to adjust the upper
+	 * bound by another unsigned long.
+	 */
+	top = start + THREAD_SIZE - TOP_OF_KERNEL_STACK_PADDING;
+	top -= 2 * sizeof(unsigned long);
+	bottom = start + sizeof(struct thread_info);
+
+	sp = READ_ONCE(p->thread.sp);
+	if (sp < bottom || sp > top)
 		return 0;
-	fp = *(u64 *)(p->thread.sp);
+
+	fp = READ_ONCE(*(unsigned long *)sp);
 	do {
-		if (fp < (unsigned long)stack ||
-		    fp >= (unsigned long)stack+THREAD_SIZE)
+		if (fp < bottom || fp > top)
 			return 0;
-		ip = *(u64 *)(fp+8);
+		ip = READ_ONCE(*(unsigned long *)(fp + sizeof(unsigned long)));
 		if (!in_sched_functions(ip))
 			return ip;
-		fp = *(u64 *)fp;
-	} while (count++ < 16);
+		fp = READ_ONCE(*(unsigned long *)fp);
+	} while (count++ < 16 && p->state != TASK_RUNNING);
 	return 0;
 }
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 1b513e093..0e8151b4b 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -22,6 +22,7 @@
 #include <asm/hypervisor.h>
 #include <asm/nmi.h>
 #include <asm/x86_init.h>
+#include <asm/geode.h>
 
 unsigned int __read_mostly cpu_khz;	/* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
@@ -1018,15 +1019,17 @@ EXPORT_SYMBOL_GPL(mark_tsc_unstable);
 
 static void __init check_system_tsc_reliable(void)
 {
-#ifdef CONFIG_MGEODE_LX
-	/* RTSC counts during suspend */
+#if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC)
+	if (is_geode_lx()) {
+		/* RTSC counts during suspend */
 #define RTSC_SUSP 0x100
-	unsigned long res_low, res_high;
+		unsigned long res_low, res_high;
 
-	rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high);
-	/* Geode_LX - the OLPC CPU has a very reliable TSC */
-	if (res_low & RTSC_SUSP)
-		tsc_clocksource_reliable = 1;
+		rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high);
+		/* Geode_LX - the OLPC CPU has a very reliable TSC */
+		if (res_low & RTSC_SUSP)
+			tsc_clocksource_reliable = 1;
+	}
 #endif
 	if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE))
 		tsc_clocksource_reliable = 1;
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 8e0c0844c..2d32b67a1 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -513,7 +513,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (svm->vmcb->control.next_rip != 0) {
-		WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS));
+		WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS));
 		svm->next_rip = svm->vmcb->control.next_rip;
 	}
 
@@ -865,64 +865,6 @@ static void svm_disable_lbrv(struct vcpu_svm *svm)
 	set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
 }
 
-#define MTRR_TYPE_UC_MINUS	7
-#define MTRR2PROTVAL_INVALID 0xff
-
-static u8 mtrr2protval[8];
-
-static u8 fallback_mtrr_type(int mtrr)
-{
-	/*
-	 * WT and WP aren't always available in the host PAT.  Treat
-	 * them as UC and UC- respectively.  Everything else should be
-	 * there.
-	 */
-	switch (mtrr)
-	{
-	case MTRR_TYPE_WRTHROUGH:
-		return MTRR_TYPE_UNCACHABLE;
-	case MTRR_TYPE_WRPROT:
-		return MTRR_TYPE_UC_MINUS;
-	default:
-		BUG();
-	}
-}
-
-static void build_mtrr2protval(void)
-{
-	int i;
-	u64 pat;
-
-	for (i = 0; i < 8; i++)
-		mtrr2protval[i] = MTRR2PROTVAL_INVALID;
-
-	/* Ignore the invalid MTRR types.  */
-	mtrr2protval[2] = 0;
-	mtrr2protval[3] = 0;
-
-	/*
-	 * Use host PAT value to figure out the mapping from guest MTRR
-	 * values to nested page table PAT/PCD/PWT values.  We do not
-	 * want to change the host PAT value every time we enter the
-	 * guest.
-	 */
-	rdmsrl(MSR_IA32_CR_PAT, pat);
-	for (i = 0; i < 8; i++) {
-		u8 mtrr = pat >> (8 * i);
-
-		if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID)
-			mtrr2protval[mtrr] = __cm_idx2pte(i);
-	}
-
-	for (i = 0; i < 8; i++) {
-		if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) {
-			u8 fallback = fallback_mtrr_type(i);
-			mtrr2protval[i] = mtrr2protval[fallback];
-			BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID);
-		}
-	}
-}
-
 static __init int svm_hardware_setup(void)
 {
 	int cpu;
@@ -989,7 +931,6 @@ static __init int svm_hardware_setup(void)
 	} else
 		kvm_disable_tdp();
 
-	build_mtrr2protval();
 	return 0;
 
 err:
@@ -1144,39 +1085,6 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 	return target_tsc - tsc;
 }
 
-static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat)
-{
-	struct kvm_vcpu *vcpu = &svm->vcpu;
-
-	/* Unlike Intel, AMD takes the guest's CR0.CD into account.
-	 *
-	 * AMD does not have IPAT.  To emulate it for the case of guests
-	 * with no assigned devices, just set everything to WB.  If guests
-	 * have assigned devices, however, we cannot force WB for RAM
-	 * pages only, so use the guest PAT directly.
-	 */
-	if (!kvm_arch_has_assigned_device(vcpu->kvm))
-		*g_pat = 0x0606060606060606;
-	else
-		*g_pat = vcpu->arch.pat;
-}
-
-static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
-{
-	u8 mtrr;
-
-	/*
-	 * 1. MMIO: trust guest MTRR, so same as item 3.
-	 * 2. No passthrough: always map as WB, and force guest PAT to WB as well
-	 * 3. Passthrough: can't guarantee the result, try to trust guest.
-	 */
-	if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm))
-		return 0;
-
-	mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
-	return mtrr2protval[mtrr];
-}
-
 static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -1260,6 +1168,7 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 	 * It also updates the guest-visible cr0 value.
 	 */
 	(void)kvm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
+	kvm_mmu_reset_context(&svm->vcpu);
 
 	save->cr4 = X86_CR4_PAE;
 	/* rdx = ?? */
@@ -1272,7 +1181,6 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 		clr_cr_intercept(svm, INTERCEPT_CR3_READ);
 		clr_cr_intercept(svm, INTERCEPT_CR3_WRITE);
 		save->g_pat = svm->vcpu.arch.pat;
-		svm_set_guest_pat(svm, &save->g_pat);
 		save->cr3 = 0;
 		save->cr4 = 0;
 	}
@@ -3347,16 +3255,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_VM_IGNNE:
 		vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
 		break;
-	case MSR_IA32_CR_PAT:
-		if (npt_enabled) {
-			if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
-				return 1;
-			vcpu->arch.pat = data;
-			svm_set_guest_pat(svm, &svm->vmcb->save.g_pat);
-			mark_dirty(svm->vmcb, VMCB_NPT);
-			break;
-		}
-		/* fall through */
 	default:
 		return kvm_set_msr_common(vcpu, msr);
 	}
@@ -4191,6 +4089,11 @@ static bool svm_has_high_real_mode_segbase(void)
 	return true;
 }
 
+static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
+{
+	return 0;
+}
+
 static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 {
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 83b7b5cd7..aa9e82295 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6134,6 +6134,8 @@ static __init int hardware_setup(void)
 	memcpy(vmx_msr_bitmap_longmode_x2apic,
 			vmx_msr_bitmap_longmode, PAGE_SIZE);
 
+	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
+
 	if (enable_apicv) {
 		for (msr = 0x800; msr <= 0x8ff; msr++)
 			vmx_disable_intercept_msr_read_x2apic(msr);
@@ -8632,17 +8634,22 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	u64 ipat = 0;
 
 	/* For VT-d and EPT combination
-	 * 1. MMIO: guest may want to apply WC, trust it.
+	 * 1. MMIO: always map as UC
 	 * 2. EPT with VT-d:
 	 *   a. VT-d without snooping control feature: can't guarantee the
-	 *	result, try to trust guest.  So the same as item 1.
+	 *	result, try to trust guest.
 	 *   b. VT-d with snooping control feature: snooping control feature of
 	 *	VT-d engine can guarantee the cache correctness. Just set it
 	 *	to WB to keep consistent with host. So the same as item 3.
 	 * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
 	 *    consistent with host MTRR
 	 */
-	if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+	if (is_mmio) {
+		cache = MTRR_TYPE_UNCACHABLE;
+		goto exit;
+	}
+
+	if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
 		ipat = VMX_EPT_IPAT_BIT;
 		cache = MTRR_TYPE_WRBACK;
 		goto exit;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8f0f6eca6..32c6e6ac5 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2388,6 +2388,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_LASTINTFROMIP:
 	case MSR_IA32_LASTINTTOIP:
 	case MSR_K8_SYSCFG:
+	case MSR_K8_TSEG_ADDR:
+	case MSR_K8_TSEG_MASK:
 	case MSR_K7_HWCR:
 	case MSR_VM_HSAVE_PA:
 	case MSR_K8_INT_PENDING_MSG:
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 3fba623e3..f9977a7a9 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1132,7 +1132,7 @@ void mark_rodata_ro(void)
 	 * has been zapped already via cleanup_highmem().
 	 */
 	all_end = roundup((unsigned long)_brk_end, PMD_SIZE);
-	set_memory_nx(rodata_start, (all_end - rodata_start) >> PAGE_SHIFT);
+	set_memory_nx(text_end, (all_end - text_end) >> PAGE_SHIFT);
 
 	rodata_test();
 
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
index 27062303c..7553921c1 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid_pci.c
@@ -35,6 +35,9 @@
 
 #define PCIE_CAP_OFFSET	0x100
 
+/* Quirks for the listed devices */
+#define PCI_DEVICE_ID_INTEL_MRFL_MMC	0x1190
+
 /* Fixed BAR fields */
 #define PCIE_VNDR_CAP_ID_FIXED_BAR 0x00	/* Fixed BAR (TBD) */
 #define PCI_FIXED_BAR_0_SIZE	0x04
@@ -214,10 +217,27 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
 	if (dev->irq_managed && dev->irq > 0)
 		return 0;
 
-	if (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_TANGIER)
+	switch (intel_mid_identify_cpu()) {
+	case INTEL_MID_CPU_CHIP_TANGIER:
 		polarity = 0; /* active high */
-	else
+
+		/* Special treatment for IRQ0 */
+		if (dev->irq == 0) {
+			/*
+			 * TNG has IRQ0 assigned to eMMC controller. But there
+			 * are also other devices with bogus PCI configuration
+			 * that have IRQ0 assigned. This check ensures that
+			 * eMMC gets it.
+			 */
+			if (dev->device != PCI_DEVICE_ID_INTEL_MRFL_MMC)
+				return -EBUSY;
+		}
+		break;
+	default:
 		polarity = 1; /* active low */
+		break;
+	}
+
 	ioapic_set_alloc_attr(&info, dev_to_node(&dev->dev), 1, polarity);
 
 	/*
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index e4308fe6a..c6835bfad 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -705,6 +705,70 @@ out:
 }
 
 /*
+ * Iterate the EFI memory map in reverse order because the regions
+ * will be mapped top-down. The end result is the same as if we had
+ * mapped things forward, but doesn't require us to change the
+ * existing implementation of efi_map_region().
+ */
+static inline void *efi_map_next_entry_reverse(void *entry)
+{
+	/* Initial call */
+	if (!entry)
+		return memmap.map_end - memmap.desc_size;
+
+	entry -= memmap.desc_size;
+	if (entry < memmap.map)
+		return NULL;
+
+	return entry;
+}
+
+/*
+ * efi_map_next_entry - Return the next EFI memory map descriptor
+ * @entry: Previous EFI memory map descriptor
+ *
+ * This is a helper function to iterate over the EFI memory map, which
+ * we do in different orders depending on the current configuration.
+ *
+ * To begin traversing the memory map @entry must be %NULL.
+ *
+ * Returns %NULL when we reach the end of the memory map.
+ */
+static void *efi_map_next_entry(void *entry)
+{
+	if (!efi_enabled(EFI_OLD_MEMMAP) && efi_enabled(EFI_64BIT)) {
+		/*
+		 * Starting in UEFI v2.5 the EFI_PROPERTIES_TABLE
+		 * config table feature requires us to map all entries
+		 * in the same order as they appear in the EFI memory
+		 * map. That is to say, entry N must have a lower
+		 * virtual address than entry N+1. This is because the
+		 * firmware toolchain leaves relative references in
+		 * the code/data sections, which are split and become
+		 * separate EFI memory regions. Mapping things
+		 * out-of-order leads to the firmware accessing
+		 * unmapped addresses.
+		 *
+		 * Since we need to map things this way whether or not
+		 * the kernel actually makes use of
+		 * EFI_PROPERTIES_TABLE, let's just switch to this
+		 * scheme by default for 64-bit.
+		 */
+		return efi_map_next_entry_reverse(entry);
+	}
+
+	/* Initial call */
+	if (!entry)
+		return memmap.map;
+
+	entry += memmap.desc_size;
+	if (entry >= memmap.map_end)
+		return NULL;
+
+	return entry;
+}
+
+/*
  * Map the efi memory ranges of the runtime services and update new_mmap with
  * virtual addresses.
  */
@@ -714,7 +778,8 @@ static void * __init efi_map_regions(int *count, int *pg_shift)
 	unsigned long left = 0;
 	efi_memory_desc_t *md;
 
-	for (p = memmap.map; p < memmap.map_end; p += memmap.desc_size) {
+	p = NULL;
+	while ((p = efi_map_next_entry(p))) {
 		md = p;
 		if (!(md->attribute & EFI_MEMORY_RUNTIME)) {
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 11d6fb4e8..777ad2f03 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -33,6 +33,10 @@
 #include <linux/memblock.h>
 #include <linux/edd.h>
 
+#ifdef CONFIG_KEXEC_CORE
+#include <linux/kexec.h>
+#endif
+
 #include <xen/xen.h>
 #include <xen/events.h>
 #include <xen/interface/xen.h>
@@ -1800,6 +1804,21 @@ static struct notifier_block xen_hvm_cpu_notifier = {
 	.notifier_call	= xen_hvm_cpu_notify,
 };
 
+#ifdef CONFIG_KEXEC_CORE
+static void xen_hvm_shutdown(void)
+{
+	native_machine_shutdown();
+	if (kexec_in_progress)
+		xen_reboot(SHUTDOWN_soft_reset);
+}
+
+static void xen_hvm_crash_shutdown(struct pt_regs *regs)
+{
+	native_machine_crash_shutdown(regs);
+	xen_reboot(SHUTDOWN_soft_reset);
+}
+#endif
+
 static void __init xen_hvm_guest_init(void)
 {
 	if (xen_pv_domain())
@@ -1819,6 +1838,10 @@ static void __init xen_hvm_guest_init(void)
 	x86_init.irqs.intr_init = xen_init_IRQ;
 	xen_hvm_init_time_ops();
 	xen_hvm_init_mmu_ops();
+#ifdef CONFIG_KEXEC_CORE
+	machine_ops.shutdown = xen_hvm_shutdown;
+	machine_ops.crash_shutdown = xen_hvm_crash_shutdown;
+#endif
 }
 #endif
 
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index d6283b3f5..9cc48d1d7 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -387,6 +387,9 @@ static void blkg_destroy_all(struct request_queue *q)
 		blkg_destroy(blkg);
 		spin_unlock(&blkcg->lock);
 	}
+
+	q->root_blkg = NULL;
+	q->root_rl.blkg = NULL;
 }
 
 /*
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 176262ec3..c69902695 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1807,7 +1807,6 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 
 		hctx = q->mq_ops->map_queue(q, i);
 		cpumask_set_cpu(i, hctx->cpumask);
-		cpumask_set_cpu(i, hctx->tags->cpumask);
 		ctx->index_hw = hctx->nr_ctx;
 		hctx->ctxs[hctx->nr_ctx++] = ctx;
 	}
@@ -1847,6 +1846,14 @@ static void blk_mq_map_swqueue(struct request_queue *q)
 		hctx->next_cpu = cpumask_first(hctx->cpumask);
 		hctx->next_cpu_batch = BLK_MQ_CPU_WORK_BATCH;
 	}
+
+	queue_for_each_ctx(q, ctx, i) {
+		if (!cpu_online(i))
+			continue;
+
+		hctx = q->mq_ops->map_queue(q, i);
+		cpumask_set_cpu(i, hctx->tags->cpumask);
+	}
 }
 
 static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set)
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
index 764280a91..e9fd32e91 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -148,7 +148,11 @@ static void cache_shared_cpu_map_remove(unsigned int cpu)
 
 			if (sibling == cpu) /* skip itself */
 				continue;
+
 			sib_cpu_ci = get_cpu_cacheinfo(sibling);
+			if (!sib_cpu_ci->info_list)
+				continue;
+
 			sib_leaf = sib_cpu_ci->info_list + index;
 			cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
 			cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
@@ -159,6 +163,9 @@ static void cache_shared_cpu_map_remove(unsigned int cpu)
 
 static void free_cache_attributes(unsigned int cpu)
 {
+	if (!per_cpu_cacheinfo(cpu))
+		return;
+
 	cache_shared_cpu_map_remove(cpu);
 
 	kfree(per_cpu_cacheinfo(cpu));
@@ -514,8 +521,7 @@ static int cacheinfo_cpu_callback(struct notifier_block *nfb,
 		break;
 	case CPU_DEAD:
 		cache_remove_dev(cpu);
-		if (per_cpu_cacheinfo(cpu))
-			free_cache_attributes(cpu);
+		free_cache_attributes(cpu);
 		break;
 	}
 	return notifier_from_errno(rc);
diff --git a/drivers/base/property.c b/drivers/base/property.c
index f3f6d167f..37a7bb7b2 100644
--- a/drivers/base/property.c
+++ b/drivers/base/property.c
@@ -27,9 +27,10 @@
  */
 void device_add_property_set(struct device *dev, struct property_set *pset)
 {
-	if (pset)
-		pset->fwnode.type = FWNODE_PDATA;
+	if (!pset)
+		return;
 
+	pset->fwnode.type = FWNODE_PDATA;
 	set_secondary_fwnode(dev, &pset->fwnode);
 }
 EXPORT_SYMBOL_GPL(device_add_property_set);
diff --git a/drivers/base/regmap/regmap-debugfs.c b/drivers/base/regmap/regmap-debugfs.c
index 5799a0b9e..c8941f39c 100644
--- a/drivers/base/regmap/regmap-debugfs.c
+++ b/drivers/base/regmap/regmap-debugfs.c
@@ -32,8 +32,7 @@ static DEFINE_MUTEX(regmap_debugfs_early_lock);
 /* Calculate the length of a fixed format  */
 static size_t regmap_calc_reg_len(int max_val, char *buf, size_t buf_size)
 {
-	snprintf(buf, buf_size, "%x", max_val);
-	return strlen(buf);
+	return snprintf(NULL, 0, "%x", max_val);
 }
 
 static ssize_t regmap_name_read_file(struct file *file,
@@ -432,7 +431,7 @@ static ssize_t regmap_access_read_file(struct file *file,
 		/* If we're in the region the user is trying to read */
 		if (p >= *ppos) {
 			/* ...but not beyond it */
-			if (buf_pos >= count - 1 - tot_len)
+			if (buf_pos + tot_len + 1 >= count)
 				break;
 
 			/* Format the register */
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index deb3f0017..767657565 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -212,6 +212,9 @@ static int xen_blkif_map(struct xen_blkif *blkif, grant_ref_t *gref,
 
 static int xen_blkif_disconnect(struct xen_blkif *blkif)
 {
+	struct pending_req *req, *n;
+	int i = 0, j;
+
 	if (blkif->xenblkd) {
 		kthread_stop(blkif->xenblkd);
 		wake_up(&blkif->shutdown_wq);
@@ -238,13 +241,28 @@ static int xen_blkif_disconnect(struct xen_blkif *blkif)
 	/* Remove all persistent grants and the cache of ballooned pages. */
 	xen_blkbk_free_caches(blkif);
 
+	/* Check that there is no request in use */
+	list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) {
+		list_del(&req->free_list);
+
+		for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++)
+			kfree(req->segments[j]);
+
+		for (j = 0; j < MAX_INDIRECT_PAGES; j++)
+			kfree(req->indirect_pages[j]);
+
+		kfree(req);
+		i++;
+	}
+
+	WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages));
+	blkif->nr_ring_pages = 0;
+
 	return 0;
 }
 
 static void xen_blkif_free(struct xen_blkif *blkif)
 {
-	struct pending_req *req, *n;
-	int i = 0, j;
 
 	xen_blkif_disconnect(blkif);
 	xen_vbd_free(&blkif->vbd);
@@ -257,22 +275,6 @@ static void xen_blkif_free(struct xen_blkif *blkif)
 	BUG_ON(!list_empty(&blkif->free_pages));
 	BUG_ON(!RB_EMPTY_ROOT(&blkif->persistent_gnts));
 
-	/* Check that there is no request in use */
-	list_for_each_entry_safe(req, n, &blkif->pending_free, free_list) {
-		list_del(&req->free_list);
-
-		for (j = 0; j < MAX_INDIRECT_SEGMENTS; j++)
-			kfree(req->segments[j]);
-
-		for (j = 0; j < MAX_INDIRECT_PAGES; j++)
-			kfree(req->indirect_pages[j]);
-
-		kfree(req);
-		i++;
-	}
-
-	WARN_ON(i != (XEN_BLKIF_REQS_PER_PAGE * blkif->nr_ring_pages));
-
 	kmem_cache_free(xen_blkif_cachep, blkif);
 }
 
diff --git a/drivers/clk/samsung/clk-cpu.c b/drivers/clk/samsung/clk-cpu.c
index 3a1fe07cf..dd02356e2 100644
--- a/drivers/clk/samsung/clk-cpu.c
+++ b/drivers/clk/samsung/clk-cpu.c
@@ -161,7 +161,7 @@ static int exynos_cpuclk_pre_rate_change(struct clk_notifier_data *ndata,
 	 * the values for DIV_COPY and DIV_HPM dividers need not be set.
 	 */
 	div0 = cfg_data->div0;
-	if (test_bit(CLK_CPU_HAS_DIV1, &cpuclk->flags)) {
+	if (cpuclk->flags & CLK_CPU_HAS_DIV1) {
 		div1 = cfg_data->div1;
 		if (readl(base + E4210_SRC_CPU) & E4210_MUX_HPM_MASK)
 			div1 = readl(base + E4210_DIV_CPU1) &
@@ -182,7 +182,7 @@ static int exynos_cpuclk_pre_rate_change(struct clk_notifier_data *ndata,
 		alt_div = DIV_ROUND_UP(alt_prate, tmp_rate) - 1;
 		WARN_ON(alt_div >= MAX_DIV);
 
-		if (test_bit(CLK_CPU_NEEDS_DEBUG_ALT_DIV, &cpuclk->flags)) {
+		if (cpuclk->flags & CLK_CPU_NEEDS_DEBUG_ALT_DIV) {
 			/*
 			 * In Exynos4210, ATB clock parent is also mout_core. So
 			 * ATB clock also needs to be mantained at safe speed.
@@ -203,7 +203,7 @@ static int exynos_cpuclk_pre_rate_change(struct clk_notifier_data *ndata,
 	writel(div0, base + E4210_DIV_CPU0);
 	wait_until_divider_stable(base + E4210_DIV_STAT_CPU0, DIV_MASK_ALL);
 
-	if (test_bit(CLK_CPU_HAS_DIV1, &cpuclk->flags)) {
+	if (cpuclk->flags & CLK_CPU_HAS_DIV1) {
 		writel(div1, base + E4210_DIV_CPU1);
 		wait_until_divider_stable(base + E4210_DIV_STAT_CPU1,
 				DIV_MASK_ALL);
@@ -222,7 +222,7 @@ static int exynos_cpuclk_post_rate_change(struct clk_notifier_data *ndata,
 	unsigned long mux_reg;
 
 	/* find out the divider values to use for clock data */
-	if (test_bit(CLK_CPU_NEEDS_DEBUG_ALT_DIV, &cpuclk->flags)) {
+	if (cpuclk->flags & CLK_CPU_NEEDS_DEBUG_ALT_DIV) {
 		while ((cfg_data->prate * 1000) != ndata->new_rate) {
 			if (cfg_data->prate == 0)
 				return -EINVAL;
@@ -237,7 +237,7 @@ static int exynos_cpuclk_post_rate_change(struct clk_notifier_data *ndata,
 	writel(mux_reg & ~(1 << 16), base + E4210_SRC_CPU);
 	wait_until_mux_stable(base + E4210_STAT_CPU, 16, 1);
 
-	if (test_bit(CLK_CPU_NEEDS_DEBUG_ALT_DIV, &cpuclk->flags)) {
+	if (cpuclk->flags & CLK_CPU_NEEDS_DEBUG_ALT_DIV) {
 		div |= (cfg_data->div0 & E4210_DIV0_ATB_MASK);
 		div_mask |= E4210_DIV0_ATB_MASK;
 	}
diff --git a/drivers/clk/ti/clk-3xxx.c b/drivers/clk/ti/clk-3xxx.c
index 757636d16..4ab28cfb8 100644
--- a/drivers/clk/ti/clk-3xxx.c
+++ b/drivers/clk/ti/clk-3xxx.c
@@ -163,7 +163,6 @@ static struct ti_dt_clk omap3xxx_clks[] = {
 	DT_CLK(NULL, "gpio2_ick", "gpio2_ick"),
 	DT_CLK(NULL, "wdt3_ick", "wdt3_ick"),
 	DT_CLK(NULL, "uart3_ick", "uart3_ick"),
-	DT_CLK(NULL, "uart4_ick", "uart4_ick"),
 	DT_CLK(NULL, "gpt9_ick", "gpt9_ick"),
 	DT_CLK(NULL, "gpt8_ick", "gpt8_ick"),
 	DT_CLK(NULL, "gpt7_ick", "gpt7_ick"),
@@ -308,6 +307,7 @@ static struct ti_dt_clk am35xx_clks[] = {
 static struct ti_dt_clk omap36xx_clks[] = {
 	DT_CLK(NULL, "omap_192m_alwon_fck", "omap_192m_alwon_fck"),
 	DT_CLK(NULL, "uart4_fck", "uart4_fck"),
+	DT_CLK(NULL, "uart4_ick", "uart4_ick"),
 	{ .node_name = NULL },
 };
 
diff --git a/drivers/clk/ti/clk-7xx.c b/drivers/clk/ti/clk-7xx.c
index 63b8323df..0eb82107c 100644
--- a/drivers/clk/ti/clk-7xx.c
+++ b/drivers/clk/ti/clk-7xx.c
@@ -16,7 +16,6 @@
 #include <linux/clkdev.h>
 #include <linux/clk/ti.h>
 
-#define DRA7_DPLL_ABE_DEFFREQ				180633600
 #define DRA7_DPLL_GMAC_DEFFREQ				1000000000
 #define DRA7_DPLL_USB_DEFFREQ				960000000
 
@@ -312,27 +311,12 @@ static struct ti_dt_clk dra7xx_clks[] = {
 int __init dra7xx_dt_clk_init(void)
 {
 	int rc;
-	struct clk *abe_dpll_mux, *sys_clkin2, *dpll_ck, *hdcp_ck;
+	struct clk *dpll_ck, *hdcp_ck;
 
 	ti_dt_clocks_register(dra7xx_clks);
 
 	omap2_clk_disable_autoidle_all();
 
-	abe_dpll_mux = clk_get_sys(NULL, "abe_dpll_sys_clk_mux");
-	sys_clkin2 = clk_get_sys(NULL, "sys_clkin2");
-	dpll_ck = clk_get_sys(NULL, "dpll_abe_ck");
-
-	rc = clk_set_parent(abe_dpll_mux, sys_clkin2);
-	if (!rc)
-		rc = clk_set_rate(dpll_ck, DRA7_DPLL_ABE_DEFFREQ);
-	if (rc)
-		pr_err("%s: failed to configure ABE DPLL!\n", __func__);
-
-	dpll_ck = clk_get_sys(NULL, "dpll_abe_m2x2_ck");
-	rc = clk_set_rate(dpll_ck, DRA7_DPLL_ABE_DEFFREQ * 2);
-	if (rc)
-		pr_err("%s: failed to configure ABE DPLL m2x2!\n", __func__);
-
 	dpll_ck = clk_get_sys(NULL, "dpll_gmac_ck");
 	rc = clk_set_rate(dpll_ck, DRA7_DPLL_GMAC_DEFFREQ);
 	if (rc)
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 0136dfcda..7c2a7385c 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -146,6 +146,9 @@ static ssize_t show_freqdomain_cpus(struct cpufreq_policy *policy, char *buf)
 {
 	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
 
+	if (unlikely(!data))
+		return -ENODEV;
+
 	return cpufreq_show_cpus(data->freqdomain_cpus, buf);
 }
 
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 528a82bf5..99a406501 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -255,7 +255,8 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 			rcu_read_unlock();
 
 			tol_uV = opp_uV * priv->voltage_tolerance / 100;
-			if (regulator_is_supported_voltage(cpu_reg, opp_uV,
+			if (regulator_is_supported_voltage(cpu_reg,
+							   opp_uV - tol_uV,
 							   opp_uV + tol_uV)) {
 				if (opp_uV < min_uV)
 					min_uV = opp_uV;
diff --git a/drivers/crypto/marvell/cesa.h b/drivers/crypto/marvell/cesa.h
index b60698b30..bc2a55bc3 100644
--- a/drivers/crypto/marvell/cesa.h
+++ b/drivers/crypto/marvell/cesa.h
@@ -687,6 +687,33 @@ static inline u32 mv_cesa_get_int_mask(struct mv_cesa_engine *engine)
 
 int mv_cesa_queue_req(struct crypto_async_request *req);
 
+/*
+ * Helper function that indicates whether a crypto request needs to be
+ * cleaned up or not after being enqueued using mv_cesa_queue_req().
+ */
+static inline int mv_cesa_req_needs_cleanup(struct crypto_async_request *req,
+					    int ret)
+{
+	/*
+	 * The queue still had some space, the request was queued
+	 * normally, so there's no need to clean it up.
+	 */
+	if (ret == -EINPROGRESS)
+		return false;
+
+	/*
+	 * The queue had not space left, but since the request is
+	 * flagged with CRYPTO_TFM_REQ_MAY_BACKLOG, it was added to
+	 * the backlog and will be processed later. There's no need to
+	 * clean it up.
+	 */
+	if (ret == -EBUSY && req->flags & CRYPTO_TFM_REQ_MAY_BACKLOG)
+		return false;
+
+	/* Request wasn't queued, we need to clean it up */
+	return true;
+}
+
 /* TDMA functions */
 
 static inline void mv_cesa_req_dma_iter_init(struct mv_cesa_dma_iter *iter,
diff --git a/drivers/crypto/marvell/cipher.c b/drivers/crypto/marvell/cipher.c
index 0745cf3b9..3df2f4e7a 100644
--- a/drivers/crypto/marvell/cipher.c
+++ b/drivers/crypto/marvell/cipher.c
@@ -189,7 +189,6 @@ static inline void mv_cesa_ablkcipher_prepare(struct crypto_async_request *req,
 {
 	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
-
 	creq->req.base.engine = engine;
 
 	if (creq->req.base.type == CESA_DMA_REQ)
@@ -431,7 +430,7 @@ static int mv_cesa_des_op(struct ablkcipher_request *req,
 		return ret;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ablkcipher_cleanup(req);
 
 	return ret;
@@ -551,7 +550,7 @@ static int mv_cesa_des3_op(struct ablkcipher_request *req,
 		return ret;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ablkcipher_cleanup(req);
 
 	return ret;
@@ -693,7 +692,7 @@ static int mv_cesa_aes_op(struct ablkcipher_request *req,
 		return ret;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ablkcipher_cleanup(req);
 
 	return ret;
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index ae9272eb9..e8d0d7128 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -739,10 +739,8 @@ static int mv_cesa_ahash_update(struct ahash_request *req)
 		return 0;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS) {
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ahash_cleanup(req);
-		return ret;
-	}
 
 	return ret;
 }
@@ -766,7 +764,7 @@ static int mv_cesa_ahash_final(struct ahash_request *req)
 		return 0;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ahash_cleanup(req);
 
 	return ret;
@@ -791,7 +789,7 @@ static int mv_cesa_ahash_finup(struct ahash_request *req)
 		return 0;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ahash_cleanup(req);
 
 	return ret;
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index 40afa2a16..da7917a2e 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -455,6 +455,15 @@ static struct at_xdmac_desc *at_xdmac_alloc_desc(struct dma_chan *chan,
 	return desc;
 }
 
+void at_xdmac_init_used_desc(struct at_xdmac_desc *desc)
+{
+	memset(&desc->lld, 0, sizeof(desc->lld));
+	INIT_LIST_HEAD(&desc->descs_list);
+	desc->direction = DMA_TRANS_NONE;
+	desc->xfer_size = 0;
+	desc->active_xfer = false;
+}
+
 /* Call must be protected by lock. */
 static struct at_xdmac_desc *at_xdmac_get_desc(struct at_xdmac_chan *atchan)
 {
@@ -466,7 +475,7 @@ static struct at_xdmac_desc *at_xdmac_get_desc(struct at_xdmac_chan *atchan)
 		desc = list_first_entry(&atchan->free_descs_list,
 					struct at_xdmac_desc, desc_node);
 		list_del(&desc->desc_node);
-		desc->active_xfer = false;
+		at_xdmac_init_used_desc(desc);
 	}
 
 	return desc;
@@ -797,10 +806,7 @@ at_xdmac_prep_dma_cyclic(struct dma_chan *chan, dma_addr_t buf_addr,
 		list_add_tail(&desc->desc_node, &first->descs_list);
 	}
 
-	prev->lld.mbr_nda = first->tx_dma_desc.phys;
-	dev_dbg(chan2dev(chan),
-		"%s: chain lld: prev=0x%p, mbr_nda=%pad\n",
-		__func__, prev, &prev->lld.mbr_nda);
+	at_xdmac_queue_desc(chan, prev, first);
 	first->tx_dma_desc.flags = flags;
 	first->xfer_size = buf_len;
 	first->direction = direction;
@@ -878,14 +884,14 @@ at_xdmac_interleaved_queue_desc(struct dma_chan *chan,
 
 	if (xt->src_inc) {
 		if (xt->src_sgl)
-			chan_cc |=  AT_XDMAC_CC_SAM_UBS_DS_AM;
+			chan_cc |=  AT_XDMAC_CC_SAM_UBS_AM;
 		else
 			chan_cc |=  AT_XDMAC_CC_SAM_INCREMENTED_AM;
 	}
 
 	if (xt->dst_inc) {
 		if (xt->dst_sgl)
-			chan_cc |=  AT_XDMAC_CC_DAM_UBS_DS_AM;
+			chan_cc |=  AT_XDMAC_CC_DAM_UBS_AM;
 		else
 			chan_cc |=  AT_XDMAC_CC_DAM_INCREMENTED_AM;
 	}
diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
index cf1c87fa1..bedce038c 100644
--- a/drivers/dma/dw/core.c
+++ b/drivers/dma/dw/core.c
@@ -1591,7 +1591,6 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 	INIT_LIST_HEAD(&dw->dma.channels);
 	for (i = 0; i < nr_channels; i++) {
 		struct dw_dma_chan	*dwc = &dw->chan[i];
-		int			r = nr_channels - i - 1;
 
 		dwc->chan.device = &dw->dma;
 		dma_cookie_init(&dwc->chan);
@@ -1603,7 +1602,7 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 
 		/* 7 is highest priority & 0 is lowest. */
 		if (pdata->chan_priority == CHAN_PRIORITY_ASCENDING)
-			dwc->priority = r;
+			dwc->priority = nr_channels - i - 1;
 		else
 			dwc->priority = i;
 
@@ -1622,6 +1621,7 @@ int dw_dma_probe(struct dw_dma_chip *chip, struct dw_dma_platform_data *pdata)
 		/* Hardware configuration */
 		if (autocfg) {
 			unsigned int dwc_params;
+			unsigned int r = DW_DMA_MAX_NR_CHANNELS - i - 1;
 			void __iomem *addr = chip->regs + r * sizeof(u32);
 
 			dwc_params = dma_read_byaddr(addr, DWC_PARAMS);
diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index ddcbbf5cd..95bdbbe2a 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -888,6 +888,7 @@ pxad_tx_prep(struct virt_dma_chan *vc, struct virt_dma_desc *vd,
 	struct dma_async_tx_descriptor *tx;
 	struct pxad_chan *chan = container_of(vc, struct pxad_chan, vc);
 
+	INIT_LIST_HEAD(&vd->node);
 	tx = vchan_tx_prep(vc, vd, tx_flags);
 	tx->tx_submit = pxad_tx_submit;
 	dev_dbg(&chan->vc.chan.dev->device,
diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c
index 43b57b02d..ca94f475f 100644
--- a/drivers/extcon/extcon.c
+++ b/drivers/extcon/extcon.c
@@ -126,7 +126,7 @@ static int find_cable_index_by_id(struct extcon_dev *edev, const unsigned int id
 
 static int find_cable_id_by_name(struct extcon_dev *edev, const char *name)
 {
-	unsigned int id = -EINVAL;
+	int id = -EINVAL;
 	int i = 0;
 
 	/* Find the id of extcon cable */
@@ -143,7 +143,7 @@ static int find_cable_id_by_name(struct extcon_dev *edev, const char *name)
 
 static int find_cable_index_by_name(struct extcon_dev *edev, const char *name)
 {
-	unsigned int id;
+	int id;
 
 	if (edev->max_supported == 0)
 		return -EINVAL;
@@ -159,7 +159,7 @@ static int find_cable_index_by_name(struct extcon_dev *edev, const char *name)
 static bool is_extcon_changed(u32 prev, u32 new, int idx, bool *attached)
 {
 	if (((prev >> idx) & 0x1) != ((new >> idx) & 0x1)) {
-		*attached = new ? true : false;
+		*attached = ((new >> idx) & 0x1) ? true : false;
 		return true;
 	}
 
@@ -378,7 +378,7 @@ EXPORT_SYMBOL_GPL(extcon_get_cable_state_);
  */
 int extcon_get_cable_state(struct extcon_dev *edev, const char *cable_name)
 {
-	unsigned int id;
+	int id;
 
 	id = find_cable_id_by_name(edev, cable_name);
 	if (id < 0)
@@ -426,7 +426,7 @@ EXPORT_SYMBOL_GPL(extcon_set_cable_state_);
 int extcon_set_cable_state(struct extcon_dev *edev,
 			const char *cable_name, bool cable_state)
 {
-	unsigned int id;
+	int id;
 
 	id = find_cable_id_by_name(edev, cable_name);
 	if (id < 0)
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index e29560e6b..950c87f5d 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/efi.h>
+#include <linux/sort.h>
 #include <asm/efi.h>
 
 #include "efistub.h"
@@ -305,6 +306,44 @@ fail:
  */
 #define EFI_RT_VIRTUAL_BASE	0x40000000
 
+static int cmp_mem_desc(const void *l, const void *r)
+{
+	const efi_memory_desc_t *left = l, *right = r;
+
+	return (left->phys_addr > right->phys_addr) ? 1 : -1;
+}
+
+/*
+ * Returns whether region @left ends exactly where region @right starts,
+ * or false if either argument is NULL.
+ */
+static bool regions_are_adjacent(efi_memory_desc_t *left,
+				 efi_memory_desc_t *right)
+{
+	u64 left_end;
+
+	if (left == NULL || right == NULL)
+		return false;
+
+	left_end = left->phys_addr + left->num_pages * EFI_PAGE_SIZE;
+
+	return left_end == right->phys_addr;
+}
+
+/*
+ * Returns whether region @left and region @right have compatible memory type
+ * mapping attributes, and are both EFI_MEMORY_RUNTIME regions.
+ */
+static bool regions_have_compatible_memory_type_attrs(efi_memory_desc_t *left,
+						      efi_memory_desc_t *right)
+{
+	static const u64 mem_type_mask = EFI_MEMORY_WB | EFI_MEMORY_WT |
+					 EFI_MEMORY_WC | EFI_MEMORY_UC |
+					 EFI_MEMORY_RUNTIME;
+
+	return ((left->attribute ^ right->attribute) & mem_type_mask) == 0;
+}
+
 /*
  * efi_get_virtmap() - create a virtual mapping for the EFI memory map
  *
@@ -317,33 +356,52 @@ void efi_get_virtmap(efi_memory_desc_t *memory_map, unsigned long map_size,
 		     int *count)
 {
 	u64 efi_virt_base = EFI_RT_VIRTUAL_BASE;
-	efi_memory_desc_t *out = runtime_map;
+	efi_memory_desc_t *in, *prev = NULL, *out = runtime_map;
 	int l;
 
-	for (l = 0; l < map_size; l += desc_size) {
-		efi_memory_desc_t *in = (void *)memory_map + l;
+	/*
+	 * To work around potential issues with the Properties Table feature
+	 * introduced in UEFI 2.5, which may split PE/COFF executable images
+	 * in memory into several RuntimeServicesCode and RuntimeServicesData
+	 * regions, we need to preserve the relative offsets between adjacent
+	 * EFI_MEMORY_RUNTIME regions with the same memory type attributes.
+	 * The easiest way to find adjacent regions is to sort the memory map
+	 * before traversing it.
+	 */
+	sort(memory_map, map_size / desc_size, desc_size, cmp_mem_desc, NULL);
+
+	for (l = 0; l < map_size; l += desc_size, prev = in) {
 		u64 paddr, size;
 
+		in = (void *)memory_map + l;
 		if (!(in->attribute & EFI_MEMORY_RUNTIME))
 			continue;
 
+		paddr = in->phys_addr;
+		size = in->num_pages * EFI_PAGE_SIZE;
+
 		/*
 		 * Make the mapping compatible with 64k pages: this allows
 		 * a 4k page size kernel to kexec a 64k page size kernel and
 		 * vice versa.
 		 */
-		paddr = round_down(in->phys_addr, SZ_64K);
-		size = round_up(in->num_pages * EFI_PAGE_SIZE +
-				in->phys_addr - paddr, SZ_64K);
-
-		/*
-		 * Avoid wasting memory on PTEs by choosing a virtual base that
-		 * is compatible with section mappings if this region has the
-		 * appropriate size and physical alignment. (Sections are 2 MB
-		 * on 4k granule kernels)
-		 */
-		if (IS_ALIGNED(in->phys_addr, SZ_2M) && size >= SZ_2M)
-			efi_virt_base = round_up(efi_virt_base, SZ_2M);
+		if (!regions_are_adjacent(prev, in) ||
+		    !regions_have_compatible_memory_type_attrs(prev, in)) {
+
+			paddr = round_down(in->phys_addr, SZ_64K);
+			size += in->phys_addr - paddr;
+
+			/*
+			 * Avoid wasting memory on PTEs by choosing a virtual
+			 * base that is compatible with section mappings if this
+			 * region has the appropriate size and physical
+			 * alignment. (Sections are 2 MB on 4k granule kernels)
+			 */
+			if (IS_ALIGNED(in->phys_addr, SZ_2M) && size >= SZ_2M)
+				efi_virt_base = round_up(efi_virt_base, SZ_2M);
+			else
+				efi_virt_base = round_up(efi_virt_base, SZ_64K);
+		}
 
 		in->virt_addr = efi_virt_base + in->phys_addr - paddr;
 		efi_virt_base += size;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index b4d36f0f2..c098d7620 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -140,7 +140,7 @@ void amdgpu_irq_preinstall(struct drm_device *dev)
  */
 int amdgpu_irq_postinstall(struct drm_device *dev)
 {
-	dev->max_vblank_count = 0x001fffff;
+	dev->max_vblank_count = 0x00ffffff;
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 6670ab7fa..5b7d80130 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -538,46 +538,60 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 		return -EINVAL;
 	}
 
-	if (msg_type == 1) {
+	switch (msg_type) {
+	case 0:
+		/* it's a create msg, calc image size (width * height) */
+		amdgpu_bo_kunmap(bo);
+
+		/* try to alloc a new handle */
+		for (i = 0; i < AMDGPU_MAX_UVD_HANDLES; ++i) {
+			if (atomic_read(&adev->uvd.handles[i]) == handle) {
+				DRM_ERROR("Handle 0x%x already in use!\n", handle);
+				return -EINVAL;
+			}
+
+			if (!atomic_cmpxchg(&adev->uvd.handles[i], 0, handle)) {
+				adev->uvd.filp[i] = ctx->parser->filp;
+				return 0;
+			}
+		}
+
+		DRM_ERROR("No more free UVD handles!\n");
+		return -EINVAL;
+
+	case 1:
 		/* it's a decode msg, calc buffer sizes */
 		r = amdgpu_uvd_cs_msg_decode(msg, ctx->buf_sizes);
 		amdgpu_bo_kunmap(bo);
 		if (r)
 			return r;
 
-	} else if (msg_type == 2) {
+		/* validate the handle */
+		for (i = 0; i < AMDGPU_MAX_UVD_HANDLES; ++i) {
+			if (atomic_read(&adev->uvd.handles[i]) == handle) {
+				if (adev->uvd.filp[i] != ctx->parser->filp) {
+					DRM_ERROR("UVD handle collision detected!\n");
+					return -EINVAL;
+				}
+				return 0;
+			}
+		}
+
+		DRM_ERROR("Invalid UVD handle 0x%x!\n", handle);
+		return -ENOENT;
+
+	case 2:
 		/* it's a destroy msg, free the handle */
 		for (i = 0; i < AMDGPU_MAX_UVD_HANDLES; ++i)
 			atomic_cmpxchg(&adev->uvd.handles[i], handle, 0);
 		amdgpu_bo_kunmap(bo);
 		return 0;
-	} else {
-		/* it's a create msg */
-		amdgpu_bo_kunmap(bo);
-
-		if (msg_type != 0) {
-			DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
-			return -EINVAL;
-		}
-
-		/* it's a create msg, no special handling needed */
-	}
-
-	/* create or decode, validate the handle */
-	for (i = 0; i < AMDGPU_MAX_UVD_HANDLES; ++i) {
-		if (atomic_read(&adev->uvd.handles[i]) == handle)
-			return 0;
-	}
 
-	/* handle not found try to alloc a new one */
-	for (i = 0; i < AMDGPU_MAX_UVD_HANDLES; ++i) {
-		if (!atomic_cmpxchg(&adev->uvd.handles[i], 0, handle)) {
-			adev->uvd.filp[i] = ctx->parser->filp;
-			return 0;
-		}
+	default:
+		DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
+		return -EINVAL;
 	}
-
-	DRM_ERROR("No more free UVD handles!\n");
+	BUG();
 	return -EINVAL;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 9a4e3b63f..b07402fc8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -787,7 +787,7 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 	int r;
 
 	if (mem) {
-		addr = mem->start << PAGE_SHIFT;
+		addr = (u64)mem->start << PAGE_SHIFT;
 		if (mem->mem_type != TTM_PL_TT)
 			addr += adev->vm_manager.vram_base_offset;
 	} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
index ae8caca61..e60557417 100644
--- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
+++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
@@ -1279,8 +1279,7 @@ amdgpu_atombios_encoder_setup_dig(struct drm_encoder *encoder, int action)
 			amdgpu_atombios_encoder_setup_dig_encoder(encoder, ATOM_ENCODER_CMD_DP_VIDEO_ON, 0);
 		}
 		if (amdgpu_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT))
-			amdgpu_atombios_encoder_setup_dig_transmitter(encoder,
-							       ATOM_TRANSMITTER_ACTION_LCD_BLON, 0, 0);
+			amdgpu_atombios_encoder_set_backlight_level(amdgpu_encoder, dig->backlight_level);
 		if (ext_encoder)
 			amdgpu_atombios_encoder_setup_external_encoder(encoder, ext_encoder, ATOM_ENABLE);
 	} else {
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
index 4efd671d7..9488ea6ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v4_2.c
@@ -224,11 +224,11 @@ static int uvd_v4_2_suspend(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = uvd_v4_2_hw_fini(adev);
+	r = amdgpu_uvd_suspend(adev);
 	if (r)
 		return r;
 
-	r = amdgpu_uvd_suspend(adev);
+	r = uvd_v4_2_hw_fini(adev);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index b756bd99c..d0ed99822 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -220,11 +220,11 @@ static int uvd_v5_0_suspend(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = uvd_v5_0_hw_fini(adev);
+	r = amdgpu_uvd_suspend(adev);
 	if (r)
 		return r;
 
-	r = amdgpu_uvd_suspend(adev);
+	r = uvd_v5_0_hw_fini(adev);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 49aa931b2..345eb760f 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -214,11 +214,11 @@ static int uvd_v6_0_suspend(void *handle)
 	int r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = uvd_v6_0_hw_fini(adev);
+	r = amdgpu_uvd_suspend(adev);
 	if (r)
 		return r;
 
-	r = amdgpu_uvd_suspend(adev);
+	r = uvd_v6_0_hw_fini(adev);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 68552da40..4f58a1e18 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1290,7 +1290,8 @@ static int vi_common_early_init(void *handle)
 	case CHIP_CARRIZO:
 		adev->has_uvd = true;
 		adev->cg_flags = 0;
-		adev->pg_flags = AMDGPU_PG_SUPPORT_UVD | AMDGPU_PG_SUPPORT_VCE;
+		/* Disable UVD pg */
+		adev->pg_flags = /* AMDGPU_PG_SUPPORT_UVD | */AMDGPU_PG_SUPPORT_VCE;
 		adev->external_rev_id = adev->rev_id + 0x1;
 		if (amdgpu_smc_load_fw && smc_enabled)
 			adev->firmware.smu_load = true;
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index eb603f1de..969e7898a 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -804,8 +804,6 @@ static void drm_dp_destroy_mst_branch_device(struct kref *kref)
 	struct drm_dp_mst_port *port, *tmp;
 	bool wake_tx = false;
 
-	cancel_work_sync(&mstb->mgr->work);
-
 	/*
 	 * destroy all ports - don't need lock
 	 * as there are no more references to the mst branch
@@ -863,29 +861,33 @@ static void drm_dp_destroy_port(struct kref *kref)
 {
 	struct drm_dp_mst_port *port = container_of(kref, struct drm_dp_mst_port, kref);
 	struct drm_dp_mst_topology_mgr *mgr = port->mgr;
+
 	if (!port->input) {
 		port->vcpi.num_slots = 0;
 
 		kfree(port->cached_edid);
 
-		/* we can't destroy the connector here, as
-		   we might be holding the mode_config.mutex
-		   from an EDID retrieval */
+		/*
+		 * The only time we don't have a connector
+		 * on an output port is if the connector init
+		 * fails.
+		 */
 		if (port->connector) {
+			/* we can't destroy the connector here, as
+			 * we might be holding the mode_config.mutex
+			 * from an EDID retrieval */
+
 			mutex_lock(&mgr->destroy_connector_lock);
 			list_add(&port->next, &mgr->destroy_connector_list);
 			mutex_unlock(&mgr->destroy_connector_lock);
 			schedule_work(&mgr->destroy_connector_work);
 			return;
 		}
+		/* no need to clean up vcpi
+		 * as if we have no connector we never setup a vcpi */
 		drm_dp_port_teardown_pdt(port, port->pdt);
-
-		if (!port->input && port->vcpi.vcpi > 0)
-			drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi);
 	}
 	kfree(port);
-
-	(*mgr->cbs->hotplug)(mgr);
 }
 
 static void drm_dp_put_port(struct drm_dp_mst_port *port)
@@ -1115,12 +1117,21 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb,
 		char proppath[255];
 		build_mst_prop_path(port, mstb, proppath, sizeof(proppath));
 		port->connector = (*mstb->mgr->cbs->add_connector)(mstb->mgr, port, proppath);
-
+		if (!port->connector) {
+			/* remove it from the port list */
+			mutex_lock(&mstb->mgr->lock);
+			list_del(&port->next);
+			mutex_unlock(&mstb->mgr->lock);
+			/* drop port list reference */
+			drm_dp_put_port(port);
+			goto out;
+		}
 		if (port->port_num >= 8) {
 			port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc);
 		}
 	}
 
+out:
 	/* put reference to this port */
 	drm_dp_put_port(port);
 }
@@ -1978,6 +1989,8 @@ void drm_dp_mst_topology_mgr_suspend(struct drm_dp_mst_topology_mgr *mgr)
 	drm_dp_dpcd_writeb(mgr->aux, DP_MSTM_CTRL,
 			   DP_MST_EN | DP_UPSTREAM_IS_SRC);
 	mutex_unlock(&mgr->lock);
+	flush_work(&mgr->work);
+	flush_work(&mgr->destroy_connector_work);
 }
 EXPORT_SYMBOL(drm_dp_mst_topology_mgr_suspend);
 
@@ -2661,7 +2674,7 @@ static void drm_dp_destroy_connector_work(struct work_struct *work)
 {
 	struct drm_dp_mst_topology_mgr *mgr = container_of(work, struct drm_dp_mst_topology_mgr, destroy_connector_work);
 	struct drm_dp_mst_port *port;
-
+	bool send_hotplug = false;
 	/*
 	 * Not a regular list traverse as we have to drop the destroy
 	 * connector lock before destroying the connector, to avoid AB->BA
@@ -2684,7 +2697,10 @@ static void drm_dp_destroy_connector_work(struct work_struct *work)
 		if (!port->input && port->vcpi.vcpi > 0)
 			drm_dp_mst_put_payload_id(mgr, port->vcpi.vcpi);
 		kfree(port);
+		send_hotplug = true;
 	}
+	if (send_hotplug)
+		(*mgr->cbs->hotplug)(mgr);
 }
 
 /**
@@ -2737,6 +2753,7 @@ EXPORT_SYMBOL(drm_dp_mst_topology_mgr_init);
  */
 void drm_dp_mst_topology_mgr_destroy(struct drm_dp_mst_topology_mgr *mgr)
 {
+	flush_work(&mgr->work);
 	flush_work(&mgr->destroy_connector_work);
 	mutex_lock(&mgr->payload_lock);
 	kfree(mgr->payloads);
diff --git a/drivers/gpu/drm/drm_lock.c b/drivers/gpu/drm/drm_lock.c
index f861361a6..4924d381b 100644
--- a/drivers/gpu/drm/drm_lock.c
+++ b/drivers/gpu/drm/drm_lock.c
@@ -61,6 +61,9 @@ int drm_legacy_lock(struct drm_device *dev, void *data,
 	struct drm_master *master = file_priv->master;
 	int ret = 0;
 
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
+
 	++file_priv->lock_count;
 
 	if (lock->context == DRM_KERNEL_CONTEXT) {
@@ -153,6 +156,9 @@ int drm_legacy_unlock(struct drm_device *dev, void *data, struct drm_file *file_
 	struct drm_lock *lock = data;
 	struct drm_master *master = file_priv->master;
 
+	if (drm_core_check_feature(dev, DRIVER_MODESET))
+		return -EINVAL;
+
 	if (lock->context == DRM_KERNEL_CONTEXT) {
 		DRM_ERROR("Process %d using kernel context %d\n",
 			  task_pid_nr(current), lock->context);
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 198fc3c32..17522f733 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -42,7 +42,7 @@ find_section(const void *_bdb, int section_id)
 	const struct bdb_header *bdb = _bdb;
 	const u8 *base = _bdb;
 	int index = 0;
-	u16 total, current_size;
+	u32 total, current_size;
 	u8 current_id;
 
 	/* skip to first section */
@@ -57,6 +57,10 @@ find_section(const void *_bdb, int section_id)
 		current_size = *((const u16 *)(base + index));
 		index += 2;
 
+		/* The MIPI Sequence Block v3+ has a separate size field. */
+		if (current_id == BDB_MIPI_SEQUENCE && *(base + index) >= 3)
+			current_size = *((const u32 *)(base + index + 1));
+
 		if (index + current_size > total)
 			return NULL;
 
@@ -859,6 +863,12 @@ parse_mipi(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
 		return;
 	}
 
+	/* Fail gracefully for forward incompatible sequence block. */
+	if (sequence->version >= 3) {
+		DRM_ERROR("Unable to parse MIPI Sequence Block v3+\n");
+		return;
+	}
+
 	DRM_DEBUG_DRIVER("Found MIPI sequence block\n");
 
 	block_size = get_blocksize(sequence);
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 7c6225c84..4649bd2ed 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -618,7 +618,7 @@ static int qxl_crtc_mode_set(struct drm_crtc *crtc,
 		  adjusted_mode->hdisplay,
 		  adjusted_mode->vdisplay);
 
-	if (qcrtc->index == 0)
+	if (bo->is_primary == false)
 		recreate_primary = true;
 
 	if (bo->surf.stride * bo->surf.height > qdev->vram_size) {
@@ -886,13 +886,15 @@ static enum drm_connector_status qxl_conn_detect(
 		drm_connector_to_qxl_output(connector);
 	struct drm_device *ddev = connector->dev;
 	struct qxl_device *qdev = ddev->dev_private;
-	int connected;
+	bool connected = false;
 
 	/* The first monitor is always connected */
-	connected = (output->index == 0) ||
-		    (qdev->client_monitors_config &&
-		     qdev->client_monitors_config->count > output->index &&
-		     qxl_head_enabled(&qdev->client_monitors_config->heads[output->index]));
+	if (!qdev->client_monitors_config) {
+		if (output->index == 0)
+			connected = true;
+	} else
+		connected = qdev->client_monitors_config->count > output->index &&
+		     qxl_head_enabled(&qdev->client_monitors_config->heads[output->index]);
 
 	DRM_DEBUG("#%d connected: %d\n", output->index, connected);
 	if (!connected)
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index c3872598b..65adb9c72 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -1624,8 +1624,9 @@ radeon_atom_encoder_dpms_avivo(struct drm_encoder *encoder, int mode)
 		} else
 			atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
 		if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
-			args.ucAction = ATOM_LCD_BLON;
-			atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+			struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+
+			atombios_set_backlight_level(radeon_encoder, dig->backlight_level);
 		}
 		break;
 	case DRM_MODE_DPMS_STANDBY:
@@ -1706,8 +1707,7 @@ radeon_atom_encoder_dpms_dig(struct drm_encoder *encoder, int mode)
 				atombios_dig_encoder_setup(encoder, ATOM_ENCODER_CMD_DP_VIDEO_ON, 0);
 		}
 		if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT))
-			atombios_dig_transmitter_setup(encoder,
-						       ATOM_TRANSMITTER_ACTION_LCD_BLON, 0, 0);
+			atombios_set_backlight_level(radeon_encoder, dig->backlight_level);
 		if (ext_encoder)
 			atombios_external_encoder_setup(encoder, ext_encoder, ATOM_ENABLE);
 		break;
diff --git a/drivers/hv/hv_utils_transport.c b/drivers/hv/hv_utils_transport.c
index ea7ba5ef1..6a9d80a53 100644
--- a/drivers/hv/hv_utils_transport.c
+++ b/drivers/hv/hv_utils_transport.c
@@ -186,7 +186,7 @@ int hvutil_transport_send(struct hvutil_transport *hvt, void *msg, int len)
 		return -EINVAL;
 	} else if (hvt->mode == HVUTIL_TRANSPORT_NETLINK) {
 		cn_msg = kzalloc(sizeof(*cn_msg) + len, GFP_ATOMIC);
-		if (!msg)
+		if (!cn_msg)
 			return -ENOMEM;
 		cn_msg->id.idx = hvt->cn_id.idx;
 		cn_msg->id.val = hvt->cn_id.val;
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index bd1c99dea..2aaedbe0b 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -354,6 +354,10 @@ static const u16 NCT6775_REG_TEMP_CRIT[ARRAY_SIZE(nct6775_temp_label) - 1]
 
 /* NCT6776 specific data */
 
+/* STEP_UP_TIME and STEP_DOWN_TIME regs are swapped for all chips but NCT6775 */
+#define NCT6776_REG_FAN_STEP_UP_TIME NCT6775_REG_FAN_STEP_DOWN_TIME
+#define NCT6776_REG_FAN_STEP_DOWN_TIME NCT6775_REG_FAN_STEP_UP_TIME
+
 static const s8 NCT6776_ALARM_BITS[] = {
 	0, 1, 2, 3, 8, 21, 20, 16,	/* in0.. in7 */
 	17, -1, -1, -1, -1, -1, -1,	/* in8..in14 */
@@ -3528,8 +3532,8 @@ static int nct6775_probe(struct platform_device *pdev)
 		data->REG_FAN_PULSES = NCT6776_REG_FAN_PULSES;
 		data->FAN_PULSE_SHIFT = NCT6775_FAN_PULSE_SHIFT;
 		data->REG_FAN_TIME[0] = NCT6775_REG_FAN_STOP_TIME;
-		data->REG_FAN_TIME[1] = NCT6775_REG_FAN_STEP_UP_TIME;
-		data->REG_FAN_TIME[2] = NCT6775_REG_FAN_STEP_DOWN_TIME;
+		data->REG_FAN_TIME[1] = NCT6776_REG_FAN_STEP_UP_TIME;
+		data->REG_FAN_TIME[2] = NCT6776_REG_FAN_STEP_DOWN_TIME;
 		data->REG_TOLERANCE_H = NCT6776_REG_TOLERANCE_H;
 		data->REG_PWM[0] = NCT6775_REG_PWM;
 		data->REG_PWM[1] = NCT6775_REG_FAN_START_OUTPUT;
@@ -3600,8 +3604,8 @@ static int nct6775_probe(struct platform_device *pdev)
 		data->REG_FAN_PULSES = NCT6779_REG_FAN_PULSES;
 		data->FAN_PULSE_SHIFT = NCT6775_FAN_PULSE_SHIFT;
 		data->REG_FAN_TIME[0] = NCT6775_REG_FAN_STOP_TIME;
-		data->REG_FAN_TIME[1] = NCT6775_REG_FAN_STEP_UP_TIME;
-		data->REG_FAN_TIME[2] = NCT6775_REG_FAN_STEP_DOWN_TIME;
+		data->REG_FAN_TIME[1] = NCT6776_REG_FAN_STEP_UP_TIME;
+		data->REG_FAN_TIME[2] = NCT6776_REG_FAN_STEP_DOWN_TIME;
 		data->REG_TOLERANCE_H = NCT6776_REG_TOLERANCE_H;
 		data->REG_PWM[0] = NCT6775_REG_PWM;
 		data->REG_PWM[1] = NCT6775_REG_FAN_START_OUTPUT;
@@ -3677,8 +3681,8 @@ static int nct6775_probe(struct platform_device *pdev)
 		data->REG_FAN_PULSES = NCT6779_REG_FAN_PULSES;
 		data->FAN_PULSE_SHIFT = NCT6775_FAN_PULSE_SHIFT;
 		data->REG_FAN_TIME[0] = NCT6775_REG_FAN_STOP_TIME;
-		data->REG_FAN_TIME[1] = NCT6775_REG_FAN_STEP_UP_TIME;
-		data->REG_FAN_TIME[2] = NCT6775_REG_FAN_STEP_DOWN_TIME;
+		data->REG_FAN_TIME[1] = NCT6776_REG_FAN_STEP_UP_TIME;
+		data->REG_FAN_TIME[2] = NCT6776_REG_FAN_STEP_DOWN_TIME;
 		data->REG_TOLERANCE_H = NCT6776_REG_TOLERANCE_H;
 		data->REG_PWM[0] = NCT6775_REG_PWM;
 		data->REG_PWM[1] = NCT6775_REG_FAN_START_OUTPUT;
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index d851e1828..85761b78b 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -3012,9 +3012,16 @@ isert_get_dataout(struct iscsi_conn *conn, struct iscsi_cmd *cmd, bool recovery)
 static int
 isert_immediate_queue(struct iscsi_conn *conn, struct iscsi_cmd *cmd, int state)
 {
-	int ret;
+	struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
+	int ret = 0;
 
 	switch (state) {
+	case ISTATE_REMOVE:
+		spin_lock_bh(&conn->cmd_lock);
+		list_del_init(&cmd->i_conn_node);
+		spin_unlock_bh(&conn->cmd_lock);
+		isert_put_cmd(isert_cmd, true);
+		break;
 	case ISTATE_SEND_NOPIN_WANT_RESPONSE:
 		ret = isert_put_nopin(cmd, conn, false);
 		break;
@@ -3379,6 +3386,41 @@ isert_wait4flush(struct isert_conn *isert_conn)
 	wait_for_completion(&isert_conn->wait_comp_err);
 }
 
+/**
+ * isert_put_unsol_pending_cmds() - Drop commands waiting for
+ *     unsolicitate dataout
+ * @conn:    iscsi connection
+ *
+ * We might still have commands that are waiting for unsolicited
+ * dataouts messages. We must put the extra reference on those
+ * before blocking on the target_wait_for_session_cmds
+ */
+static void
+isert_put_unsol_pending_cmds(struct iscsi_conn *conn)
+{
+	struct iscsi_cmd *cmd, *tmp;
+	static LIST_HEAD(drop_cmd_list);
+
+	spin_lock_bh(&conn->cmd_lock);
+	list_for_each_entry_safe(cmd, tmp, &conn->conn_cmd_list, i_conn_node) {
+		if ((cmd->cmd_flags & ICF_NON_IMMEDIATE_UNSOLICITED_DATA) &&
+		    (cmd->write_data_done < conn->sess->sess_ops->FirstBurstLength) &&
+		    (cmd->write_data_done < cmd->se_cmd.data_length))
+			list_move_tail(&cmd->i_conn_node, &drop_cmd_list);
+	}
+	spin_unlock_bh(&conn->cmd_lock);
+
+	list_for_each_entry_safe(cmd, tmp, &drop_cmd_list, i_conn_node) {
+		list_del_init(&cmd->i_conn_node);
+		if (cmd->i_state != ISTATE_REMOVE) {
+			struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
+
+			isert_info("conn %p dropping cmd %p\n", conn, cmd);
+			isert_put_cmd(isert_cmd, true);
+		}
+	}
+}
+
 static void isert_wait_conn(struct iscsi_conn *conn)
 {
 	struct isert_conn *isert_conn = conn->context;
@@ -3397,8 +3439,9 @@ static void isert_wait_conn(struct iscsi_conn *conn)
 	isert_conn_terminate(isert_conn);
 	mutex_unlock(&isert_conn->mutex);
 
-	isert_wait4cmds(conn);
 	isert_wait4flush(isert_conn);
+	isert_put_unsol_pending_cmds(conn);
+	isert_wait4cmds(conn);
 	isert_wait4logout(isert_conn);
 
 	queue_work(isert_release_wq, &isert_conn->release_work);
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index 459bf4429..7e077bf13 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -88,28 +88,36 @@ static void aic5_mask(struct irq_data *d)
 {
 	struct irq_domain *domain = d->domain;
 	struct irq_domain_chip_generic *dgc = domain->gc;
-	struct irq_chip_generic *gc = dgc->gc[0];
+	struct irq_chip_generic *bgc = dgc->gc[0];
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 
-	/* Disable interrupt on AIC5 */
-	irq_gc_lock(gc);
+	/*
+	 * Disable interrupt on AIC5. We always take the lock of the
+	 * first irq chip as all chips share the same registers.
+	 */
+	irq_gc_lock(bgc);
 	irq_reg_writel(gc, d->hwirq, AT91_AIC5_SSR);
 	irq_reg_writel(gc, 1, AT91_AIC5_IDCR);
 	gc->mask_cache &= ~d->mask;
-	irq_gc_unlock(gc);
+	irq_gc_unlock(bgc);
 }
 
 static void aic5_unmask(struct irq_data *d)
 {
 	struct irq_domain *domain = d->domain;
 	struct irq_domain_chip_generic *dgc = domain->gc;
-	struct irq_chip_generic *gc = dgc->gc[0];
+	struct irq_chip_generic *bgc = dgc->gc[0];
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 
-	/* Enable interrupt on AIC5 */
-	irq_gc_lock(gc);
+	/*
+	 * Enable interrupt on AIC5. We always take the lock of the
+	 * first irq chip as all chips share the same registers.
+	 */
+	irq_gc_lock(bgc);
 	irq_reg_writel(gc, d->hwirq, AT91_AIC5_SSR);
 	irq_reg_writel(gc, 1, AT91_AIC5_IECR);
 	gc->mask_cache |= d->mask;
-	irq_gc_unlock(gc);
+	irq_gc_unlock(bgc);
 }
 
 static int aic5_retrigger(struct irq_data *d)
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index c00e2db35..9a791dd52 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -921,8 +921,10 @@ retry_baser:
 			 * non-cacheable as well.
 			 */
 			shr = tmp & GITS_BASER_SHAREABILITY_MASK;
-			if (!shr)
+			if (!shr) {
 				cache = GITS_BASER_nC;
+				__flush_dcache_area(base, alloc_size);
+			}
 			goto retry_baser;
 		}
 
@@ -1163,6 +1165,8 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 		return NULL;
 	}
 
+	__flush_dcache_area(itt, sz);
+
 	dev->its = its;
 	dev->itt = itt;
 	dev->nr_ites = nr_ites;
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 9ad35f72a..433fb9df8 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -229,7 +229,7 @@ config LEDS_LP55XX_COMMON
 	tristate "Common Driver for TI/National LP5521/5523/55231/5562/8501"
 	depends on LEDS_LP5521 || LEDS_LP5523 || LEDS_LP5562 || LEDS_LP8501
 	select FW_LOADER
-	select FW_LOADER_USER_HELPER_FALLBACK
+	select FW_LOADER_USER_HELPER
 	help
 	  This option supports common operations for LP5521/5523/55231/5562/8501
 	  devices.
diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index beabfbc6f..ca51d58be 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -228,12 +228,15 @@ static int led_classdev_next_name(const char *init_name, char *name,
 {
 	unsigned int i = 0;
 	int ret = 0;
+	struct device *dev;
 
 	strlcpy(name, init_name, len);
 
-	while (class_find_device(leds_class, NULL, name, match_name) &&
-	       (ret < len))
+	while ((ret < len) &&
+	       (dev = class_find_device(leds_class, NULL, name, match_name))) {
+		put_device(dev);
 		ret = snprintf(name, len, "%s_%u", init_name, ++i);
+	}
 
 	if (ret >= len)
 		return -ENOMEM;
diff --git a/drivers/macintosh/windfarm_core.c b/drivers/macintosh/windfarm_core.c
index 3ee198b65..cc7ece171 100644
--- a/drivers/macintosh/windfarm_core.c
+++ b/drivers/macintosh/windfarm_core.c
@@ -435,7 +435,7 @@ int wf_unregister_client(struct notifier_block *nb)
 {
 	mutex_lock(&wf_lock);
 	blocking_notifier_chain_unregister(&wf_client_list, nb);
-	wf_client_count++;
+	wf_client_count--;
 	if (wf_client_count == 0)
 		wf_stop_thread();
 	mutex_unlock(&wf_lock);
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index e51de52ee..48b5890c2 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -1997,7 +1997,8 @@ int bitmap_resize(struct bitmap *bitmap, sector_t blocks,
 	if (bitmap->mddev->bitmap_info.offset || bitmap->mddev->bitmap_info.file)
 		ret = bitmap_storage_alloc(&store, chunks,
 					   !bitmap->mddev->bitmap_info.external,
-					   bitmap->cluster_slot);
+					   mddev_is_clustered(bitmap->mddev)
+					   ? bitmap->cluster_slot : 0);
 	if (ret)
 		goto err;
 
diff --git a/drivers/md/dm-cache-policy-cleaner.c b/drivers/md/dm-cache-policy-cleaner.c
index 240c9f0e8..8a0964565 100644
--- a/drivers/md/dm-cache-policy-cleaner.c
+++ b/drivers/md/dm-cache-policy-cleaner.c
@@ -436,7 +436,7 @@ static struct dm_cache_policy *wb_create(dm_cblock_t cache_size,
 static struct dm_cache_policy_type wb_policy_type = {
 	.name = "cleaner",
 	.version = {1, 0, 0},
-	.hint_size = 0,
+	.hint_size = 4,
 	.owner = THIS_MODULE,
 	.create = wb_create
 };
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 0f48fed44..0d28c5b9d 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -968,7 +968,8 @@ static void crypt_free_buffer_pages(struct crypt_config *cc, struct bio *clone);
 
 /*
  * Generate a new unfragmented bio with the given size
- * This should never violate the device limitations
+ * This should never violate the device limitations (but only because
+ * max_segment_size is being constrained to PAGE_SIZE).
  *
  * This function may be called concurrently. If we allocate from the mempool
  * concurrently, there is a possibility of deadlock. For example, if we have
@@ -2058,9 +2059,20 @@ static int crypt_iterate_devices(struct dm_target *ti,
 	return fn(ti, cc->dev, cc->start, ti->len, data);
 }
 
+static void crypt_io_hints(struct dm_target *ti, struct queue_limits *limits)
+{
+	/*
+	 * Unfortunate constraint that is required to avoid the potential
+	 * for exceeding underlying device's max_segments limits -- due to
+	 * crypt_alloc_buffer() possibly allocating pages for the encryption
+	 * bio that are not as physically contiguous as the original bio.
+	 */
+	limits->max_segment_size = PAGE_SIZE;
+}
+
 static struct target_type crypt_target = {
 	.name   = "crypt",
-	.version = {1, 14, 0},
+	.version = {1, 14, 1},
 	.module = THIS_MODULE,
 	.ctr    = crypt_ctr,
 	.dtr    = crypt_dtr,
@@ -2072,6 +2084,7 @@ static struct target_type crypt_target = {
 	.message = crypt_message,
 	.merge  = crypt_merge,
 	.iterate_devices = crypt_iterate_devices,
+	.io_hints = crypt_io_hints,
 };
 
 static int __init dm_crypt_init(void)
diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 2daa67793..1257d4843 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -329,8 +329,7 @@ static int validate_region_size(struct raid_set *rs, unsigned long region_size)
 		 */
 		if (min_region_size > (1 << 13)) {
 			/* If not a power of 2, make it the next power of 2 */
-			if (min_region_size & (min_region_size - 1))
-				region_size = 1 << fls(region_size);
+			region_size = roundup_pow_of_two(min_region_size);
 			DMINFO("Choosing default region size of %lu sectors",
 			       region_size);
 		} else {
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index d2bbe8cc1..75aef240c 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -4333,6 +4333,10 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits)
 {
 	struct thin_c *tc = ti->private;
 	struct pool *pool = tc->pool;
+	struct queue_limits *pool_limits = dm_get_queue_limits(pool->pool_md);
+
+	if (!pool_limits->discard_granularity)
+		return; /* pool's discard support is disabled */
 
 	limits->discard_granularity = pool->sectors_per_block << SECTOR_SHIFT;
 	limits->max_discard_sectors = 2048 * 1024 * 16; /* 16G */
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 0d7ab20c5..3e32f4e31 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2952,8 +2952,6 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
 
 	might_sleep();
 
-	map = dm_get_live_table(md, &srcu_idx);
-
 	spin_lock(&_minor_lock);
 	idr_replace(&_minor_idr, MINOR_ALLOCED, MINOR(disk_devt(dm_disk(md))));
 	set_bit(DMF_FREEING, &md->flags);
@@ -2967,14 +2965,14 @@ static void __dm_destroy(struct mapped_device *md, bool wait)
 	 * do not race with internal suspend.
 	 */
 	mutex_lock(&md->suspend_lock);
+	map = dm_get_live_table(md, &srcu_idx);
 	if (!dm_suspended_md(md)) {
 		dm_table_presuspend_targets(map);
 		dm_table_postsuspend_targets(map);
 	}
-	mutex_unlock(&md->suspend_lock);
-
 	/* dm_put_live_table must be before msleep, otherwise deadlock is possible */
 	dm_put_live_table(md, srcu_idx);
+	mutex_unlock(&md->suspend_lock);
 
 	/*
 	 * Rare, but there may be I/O requests still going to complete,
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index efb654eb5..0875e5e7e 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -83,7 +83,7 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	char b[BDEVNAME_SIZE];
 	char b2[BDEVNAME_SIZE];
 	struct r0conf *conf = kzalloc(sizeof(*conf), GFP_KERNEL);
-	bool discard_supported = false;
+	unsigned short blksize = 512;
 
 	if (!conf)
 		return -ENOMEM;
@@ -98,6 +98,9 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 		sector_div(sectors, mddev->chunk_sectors);
 		rdev1->sectors = sectors * mddev->chunk_sectors;
 
+		blksize = max(blksize, queue_logical_block_size(
+				      rdev1->bdev->bd_disk->queue));
+
 		rdev_for_each(rdev2, mddev) {
 			pr_debug("md/raid0:%s:   comparing %s(%llu)"
 				 " with %s(%llu)\n",
@@ -134,6 +137,18 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 	}
 	pr_debug("md/raid0:%s: FINAL %d zones\n",
 		 mdname(mddev), conf->nr_strip_zones);
+	/*
+	 * now since we have the hard sector sizes, we can make sure
+	 * chunk size is a multiple of that sector size
+	 */
+	if ((mddev->chunk_sectors << 9) % blksize) {
+		printk(KERN_ERR "md/raid0:%s: chunk_size of %d not multiple of block size %d\n",
+		       mdname(mddev),
+		       mddev->chunk_sectors << 9, blksize);
+		err = -EINVAL;
+		goto abort;
+	}
+
 	err = -ENOMEM;
 	conf->strip_zone = kzalloc(sizeof(struct strip_zone)*
 				conf->nr_strip_zones, GFP_KERNEL);
@@ -188,19 +203,12 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 		}
 		dev[j] = rdev1;
 
-		if (mddev->queue)
-			disk_stack_limits(mddev->gendisk, rdev1->bdev,
-					  rdev1->data_offset << 9);
-
 		if (rdev1->bdev->bd_disk->queue->merge_bvec_fn)
 			conf->has_merge_bvec = 1;
 
 		if (!smallest || (rdev1->sectors < smallest->sectors))
 			smallest = rdev1;
 		cnt++;
-
-		if (blk_queue_discard(bdev_get_queue(rdev1->bdev)))
-			discard_supported = true;
 	}
 	if (cnt != mddev->raid_disks) {
 		printk(KERN_ERR "md/raid0:%s: too few disks (%d of %d) - "
@@ -261,28 +269,6 @@ static int create_strip_zones(struct mddev *mddev, struct r0conf **private_conf)
 			 (unsigned long long)smallest->sectors);
 	}
 
-	/*
-	 * now since we have the hard sector sizes, we can make sure
-	 * chunk size is a multiple of that sector size
-	 */
-	if ((mddev->chunk_sectors << 9) % queue_logical_block_size(mddev->queue)) {
-		printk(KERN_ERR "md/raid0:%s: chunk_size of %d not valid\n",
-		       mdname(mddev),
-		       mddev->chunk_sectors << 9);
-		goto abort;
-	}
-
-	if (mddev->queue) {
-		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
-		blk_queue_io_opt(mddev->queue,
-				 (mddev->chunk_sectors << 9) * mddev->raid_disks);
-
-		if (!discard_supported)
-			queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
-		else
-			queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
-	}
-
 	pr_debug("md/raid0:%s: done.\n", mdname(mddev));
 	*private_conf = conf;
 
@@ -433,12 +419,6 @@ static int raid0_run(struct mddev *mddev)
 	if (md_check_no_bitmap(mddev))
 		return -EINVAL;
 
-	if (mddev->queue) {
-		blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
-		blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
-		blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
-	}
-
 	/* if private is not null, we are here after takeover */
 	if (mddev->private == NULL) {
 		ret = create_strip_zones(mddev, &conf);
@@ -447,6 +427,29 @@ static int raid0_run(struct mddev *mddev)
 		mddev->private = conf;
 	}
 	conf = mddev->private;
+	if (mddev->queue) {
+		struct md_rdev *rdev;
+		bool discard_supported = false;
+
+		blk_queue_max_hw_sectors(mddev->queue, mddev->chunk_sectors);
+		blk_queue_max_write_same_sectors(mddev->queue, mddev->chunk_sectors);
+		blk_queue_max_discard_sectors(mddev->queue, mddev->chunk_sectors);
+
+		blk_queue_io_min(mddev->queue, mddev->chunk_sectors << 9);
+		blk_queue_io_opt(mddev->queue,
+				 (mddev->chunk_sectors << 9) * mddev->raid_disks);
+
+		rdev_for_each(rdev, mddev) {
+			disk_stack_limits(mddev->gendisk, rdev->bdev,
+					  rdev->data_offset << 9);
+			if (blk_queue_discard(bdev_get_queue(rdev->bdev)))
+				discard_supported = true;
+		}
+		if (!discard_supported)
+			queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+		else
+			queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, mddev->queue);
+	}
 
 	/* calculate array device size */
 	md_set_array_sectors(mddev, raid0_size(mddev, 0, 0));
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 9e3fdbdc4..2f4503a7f 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -134,9 +134,11 @@ void mmc_request_done(struct mmc_host *host, struct mmc_request *mrq)
 	int err = cmd->error;
 
 	/* Flag re-tuning needed on CRC errors */
-	if (err == -EILSEQ || (mrq->sbc && mrq->sbc->error == -EILSEQ) ||
+	if ((cmd->opcode != MMC_SEND_TUNING_BLOCK &&
+	    cmd->opcode != MMC_SEND_TUNING_BLOCK_HS200) &&
+	    (err == -EILSEQ || (mrq->sbc && mrq->sbc->error == -EILSEQ) ||
 	    (mrq->data && mrq->data->error == -EILSEQ) ||
-	    (mrq->stop && mrq->stop->error == -EILSEQ))
+	    (mrq->stop && mrq->stop->error == -EILSEQ)))
 		mmc_retune_needed(host);
 
 	if (err && cmd->retries && mmc_host_is_spi(host)) {
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index 99a9c9011..79979e9d5 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -457,7 +457,7 @@ int mmc_of_parse(struct mmc_host *host)
 					   0, &cd_gpio_invert);
 		if (!ret)
 			dev_info(host->parent, "Got CD GPIO\n");
-		else if (ret != -ENOENT)
+		else if (ret != -ENOENT && ret != -ENOSYS)
 			return ret;
 
 		/*
@@ -481,7 +481,7 @@ int mmc_of_parse(struct mmc_host *host)
 	ret = mmc_gpiod_request_ro(host, "wp", 0, false, 0, &ro_gpio_invert);
 	if (!ret)
 		dev_info(host->parent, "Got WP GPIO\n");
-	else if (ret != -ENOENT)
+	else if (ret != -ENOENT && ret != -ENOSYS)
 		return ret;
 
 	if (of_property_read_bool(np, "disable-wp"))
diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
index 40e9d8e45..e41fb7405 100644
--- a/drivers/mmc/host/dw_mmc.c
+++ b/drivers/mmc/host/dw_mmc.c
@@ -99,6 +99,9 @@ struct idmac_desc {
 
 	__le32		des3;	/* buffer 2 physical address */
 };
+
+/* Each descriptor can transfer up to 4KB of data in chained mode */
+#define DW_MCI_DESC_DATA_LENGTH	0x1000
 #endif /* CONFIG_MMC_DW_IDMAC */
 
 static bool dw_mci_reset(struct dw_mci *host);
@@ -462,66 +465,96 @@ static void dw_mci_idmac_complete_dma(struct dw_mci *host)
 static void dw_mci_translate_sglist(struct dw_mci *host, struct mmc_data *data,
 				    unsigned int sg_len)
 {
+	unsigned int desc_len;
 	int i;
 	if (host->dma_64bit_address == 1) {
-		struct idmac_desc_64addr *desc = host->sg_cpu;
+		struct idmac_desc_64addr *desc_first, *desc_last, *desc;
+
+		desc_first = desc_last = desc = host->sg_cpu;
 
-		for (i = 0; i < sg_len; i++, desc++) {
+		for (i = 0; i < sg_len; i++) {
 			unsigned int length = sg_dma_len(&data->sg[i]);
 			u64 mem_addr = sg_dma_address(&data->sg[i]);
 
-			/*
-			 * Set the OWN bit and disable interrupts for this
-			 * descriptor
-			 */
-			desc->des0 = IDMAC_DES0_OWN | IDMAC_DES0_DIC |
-						IDMAC_DES0_CH;
-			/* Buffer length */
-			IDMAC_64ADDR_SET_BUFFER1_SIZE(desc, length);
-
-			/* Physical address to DMA to/from */
-			desc->des4 = mem_addr & 0xffffffff;
-			desc->des5 = mem_addr >> 32;
+			for ( ; length ; desc++) {
+				desc_len = (length <= DW_MCI_DESC_DATA_LENGTH) ?
+					   length : DW_MCI_DESC_DATA_LENGTH;
+
+				length -= desc_len;
+
+				/*
+				 * Set the OWN bit and disable interrupts
+				 * for this descriptor
+				 */
+				desc->des0 = IDMAC_DES0_OWN | IDMAC_DES0_DIC |
+							IDMAC_DES0_CH;
+
+				/* Buffer length */
+				IDMAC_64ADDR_SET_BUFFER1_SIZE(desc, desc_len);
+
+				/* Physical address to DMA to/from */
+				desc->des4 = mem_addr & 0xffffffff;
+				desc->des5 = mem_addr >> 32;
+
+				/* Update physical address for the next desc */
+				mem_addr += desc_len;
+
+				/* Save pointer to the last descriptor */
+				desc_last = desc;
+			}
 		}
 
 		/* Set first descriptor */
-		desc = host->sg_cpu;
-		desc->des0 |= IDMAC_DES0_FD;
+		desc_first->des0 |= IDMAC_DES0_FD;
 
 		/* Set last descriptor */
-		desc = host->sg_cpu + (i - 1) *
-				sizeof(struct idmac_desc_64addr);
-		desc->des0 &= ~(IDMAC_DES0_CH | IDMAC_DES0_DIC);
-		desc->des0 |= IDMAC_DES0_LD;
+		desc_last->des0 &= ~(IDMAC_DES0_CH | IDMAC_DES0_DIC);
+		desc_last->des0 |= IDMAC_DES0_LD;
 
 	} else {
-		struct idmac_desc *desc = host->sg_cpu;
+		struct idmac_desc *desc_first, *desc_last, *desc;
+
+		desc_first = desc_last = desc = host->sg_cpu;
 
-		for (i = 0; i < sg_len; i++, desc++) {
+		for (i = 0; i < sg_len; i++) {
 			unsigned int length = sg_dma_len(&data->sg[i]);
 			u32 mem_addr = sg_dma_address(&data->sg[i]);
 
-			/*
-			 * Set the OWN bit and disable interrupts for this
-			 * descriptor
-			 */
-			desc->des0 = cpu_to_le32(IDMAC_DES0_OWN |
-					IDMAC_DES0_DIC | IDMAC_DES0_CH);
-			/* Buffer length */
-			IDMAC_SET_BUFFER1_SIZE(desc, length);
+			for ( ; length ; desc++) {
+				desc_len = (length <= DW_MCI_DESC_DATA_LENGTH) ?
+					   length : DW_MCI_DESC_DATA_LENGTH;
+
+				length -= desc_len;
+
+				/*
+				 * Set the OWN bit and disable interrupts
+				 * for this descriptor
+				 */
+				desc->des0 = cpu_to_le32(IDMAC_DES0_OWN |
+							 IDMAC_DES0_DIC |
+							 IDMAC_DES0_CH);
+
+				/* Buffer length */
+				IDMAC_SET_BUFFER1_SIZE(desc, desc_len);
 
-			/* Physical address to DMA to/from */
-			desc->des2 = cpu_to_le32(mem_addr);
+				/* Physical address to DMA to/from */
+				desc->des2 = cpu_to_le32(mem_addr);
+
+				/* Update physical address for the next desc */
+				mem_addr += desc_len;
+
+				/* Save pointer to the last descriptor */
+				desc_last = desc;
+			}
 		}
 
 		/* Set first descriptor */
-		desc = host->sg_cpu;
-		desc->des0 |= cpu_to_le32(IDMAC_DES0_FD);
+		desc_first->des0 |= cpu_to_le32(IDMAC_DES0_FD);
 
 		/* Set last descriptor */
-		desc = host->sg_cpu + (i - 1) * sizeof(struct idmac_desc);
-		desc->des0 &= cpu_to_le32(~(IDMAC_DES0_CH | IDMAC_DES0_DIC));
-		desc->des0 |= cpu_to_le32(IDMAC_DES0_LD);
+		desc_last->des0 &= cpu_to_le32(~(IDMAC_DES0_CH |
+					       IDMAC_DES0_DIC));
+		desc_last->des0 |= cpu_to_le32(IDMAC_DES0_LD);
 	}
 
 	wmb();
@@ -2394,7 +2427,7 @@ static int dw_mci_init_slot(struct dw_mci *host, unsigned int id)
 #ifdef CONFIG_MMC_DW_IDMAC
 		mmc->max_segs = host->ring_size;
 		mmc->max_blk_size = 65536;
-		mmc->max_seg_size = 0x1000;
+		mmc->max_seg_size = DW_MCI_DESC_DATA_LENGTH;
 		mmc->max_req_size = mmc->max_seg_size * host->ring_size;
 		mmc->max_blk_count = mmc->max_req_size / 512;
 #else
diff --git a/drivers/mmc/host/sdhci-pxav3.c b/drivers/mmc/host/sdhci-pxav3.c
index 946d37f94..f5edf9d3a 100644
--- a/drivers/mmc/host/sdhci-pxav3.c
+++ b/drivers/mmc/host/sdhci-pxav3.c
@@ -135,6 +135,7 @@ static int armada_38x_quirks(struct platform_device *pdev,
 	struct sdhci_pxa *pxa = pltfm_host->priv;
 	struct resource *res;
 
+	host->quirks &= ~SDHCI_QUIRK_CAP_CLOCK_BASE_BROKEN;
 	host->quirks |= SDHCI_QUIRK_MISSING_CAPS;
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
 					   "conf-sdio3");
@@ -290,6 +291,9 @@ static void pxav3_set_uhs_signaling(struct sdhci_host *host, unsigned int uhs)
 		    uhs == MMC_TIMING_UHS_DDR50) {
 			reg_val &= ~SDIO3_CONF_CLK_INV;
 			reg_val |= SDIO3_CONF_SD_FB_CLK;
+		} else if (uhs == MMC_TIMING_MMC_HS) {
+			reg_val &= ~SDIO3_CONF_CLK_INV;
+			reg_val &= ~SDIO3_CONF_SD_FB_CLK;
 		} else {
 			reg_val |= SDIO3_CONF_CLK_INV;
 			reg_val &= ~SDIO3_CONF_SD_FB_CLK;
@@ -398,7 +402,7 @@ static int sdhci_pxav3_probe(struct platform_device *pdev)
 	if (of_device_is_compatible(np, "marvell,armada-380-sdhci")) {
 		ret = armada_38x_quirks(pdev, host);
 		if (ret < 0)
-			goto err_clk_get;
+			goto err_mbus_win;
 		ret = mv_conf_mbus_windows(pdev, mv_mbus_dram_info());
 		if (ret < 0)
 			goto err_mbus_win;
diff --git a/drivers/mtd/nand/pxa3xx_nand.c b/drivers/mtd/nand/pxa3xx_nand.c
index 1259cc558..5465fa439 100644
--- a/drivers/mtd/nand/pxa3xx_nand.c
+++ b/drivers/mtd/nand/pxa3xx_nand.c
@@ -1473,6 +1473,9 @@ static int pxa3xx_nand_scan(struct mtd_info *mtd)
 	if (pdata->keep_config && !pxa3xx_nand_detect_config(info))
 		goto KEEP_CONFIG;
 
+	/* Set a default chunk size */
+	info->chunk_size = 512;
+
 	ret = pxa3xx_nand_sensing(info);
 	if (ret) {
 		dev_info(&info->pdev->dev, "There is no chip on cs %d!\n",
diff --git a/drivers/mtd/nand/sunxi_nand.c b/drivers/mtd/nand/sunxi_nand.c
index 6f93b2990..499b8e433 100644
--- a/drivers/mtd/nand/sunxi_nand.c
+++ b/drivers/mtd/nand/sunxi_nand.c
@@ -138,6 +138,10 @@
 #define NFC_ECC_MODE		GENMASK(15, 12)
 #define NFC_RANDOM_SEED		GENMASK(30, 16)
 
+/* NFC_USER_DATA helper macros */
+#define NFC_BUF_TO_USER_DATA(buf)	((buf)[0] | ((buf)[1] << 8) | \
+					((buf)[2] << 16) | ((buf)[3] << 24))
+
 #define NFC_DEFAULT_TIMEOUT_MS	1000
 
 #define NFC_SRAM_SIZE		1024
@@ -632,15 +636,9 @@ static int sunxi_nfc_hw_ecc_write_page(struct mtd_info *mtd,
 		offset = layout->eccpos[i * ecc->bytes] - 4 + mtd->writesize;
 
 		/* Fill OOB data in */
-		if (oob_required) {
-			tmp = 0xffffffff;
-			memcpy_toio(nfc->regs + NFC_REG_USER_DATA_BASE, &tmp,
-				    4);
-		} else {
-			memcpy_toio(nfc->regs + NFC_REG_USER_DATA_BASE,
-				    chip->oob_poi + offset - mtd->writesize,
-				    4);
-		}
+		writel(NFC_BUF_TO_USER_DATA(chip->oob_poi +
+					    layout->oobfree[i].offset),
+		       nfc->regs + NFC_REG_USER_DATA_BASE);
 
 		chip->cmdfunc(mtd, NAND_CMD_RNDIN, offset, -1);
 
@@ -770,14 +768,8 @@ static int sunxi_nfc_hw_syndrome_ecc_write_page(struct mtd_info *mtd,
 		offset += ecc->size;
 
 		/* Fill OOB data in */
-		if (oob_required) {
-			tmp = 0xffffffff;
-			memcpy_toio(nfc->regs + NFC_REG_USER_DATA_BASE, &tmp,
-				    4);
-		} else {
-			memcpy_toio(nfc->regs + NFC_REG_USER_DATA_BASE, oob,
-				    4);
-		}
+		writel(NFC_BUF_TO_USER_DATA(oob),
+		       nfc->regs + NFC_REG_USER_DATA_BASE);
 
 		tmp = NFC_DATA_TRANS | NFC_DATA_SWAP_METHOD | NFC_ACCESS_DIR |
 		      (1 << 30);
@@ -1312,6 +1304,7 @@ static void sunxi_nand_chips_cleanup(struct sunxi_nfc *nfc)
 					node);
 		nand_release(&chip->mtd);
 		sunxi_nand_ecc_cleanup(&chip->nand.ecc);
+		list_del(&chip->node);
 	}
 }
 
diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c
index 5bbd1f094..1fc23e48f 100644
--- a/drivers/mtd/ubi/io.c
+++ b/drivers/mtd/ubi/io.c
@@ -926,6 +926,11 @@ static int validate_vid_hdr(const struct ubi_device *ubi,
 		goto bad;
 	}
 
+	if (data_size > ubi->leb_size) {
+		ubi_err(ubi, "bad data_size");
+		goto bad;
+	}
+
 	if (vol_type == UBI_VID_STATIC) {
 		/*
 		 * Although from high-level point of view static volumes may
diff --git a/drivers/mtd/ubi/vtbl.c b/drivers/mtd/ubi/vtbl.c
index 80bdd5b88..d85c19762 100644
--- a/drivers/mtd/ubi/vtbl.c
+++ b/drivers/mtd/ubi/vtbl.c
@@ -649,6 +649,7 @@ static int init_volumes(struct ubi_device *ubi,
 		if (ubi->corr_peb_count)
 			ubi_err(ubi, "%d PEBs are corrupted and not used",
 				ubi->corr_peb_count);
+		return -ENOSPC;
 	}
 	ubi->rsvd_pebs += reserved_pebs;
 	ubi->avail_pebs -= reserved_pebs;
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 275d9fb6f..eb4489f90 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -1601,6 +1601,7 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai)
 		if (ubi->corr_peb_count)
 			ubi_err(ubi, "%d PEBs are corrupted and not used",
 				ubi->corr_peb_count);
+		err = -ENOSPC;
 		goto out_free;
 	}
 	ubi->avail_pebs -= reserved_pebs;
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 8d7b59689..5bc9fca67 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2851,7 +2851,7 @@ static void igb_probe_vfs(struct igb_adapter *adapter)
 		return;
 
 	pci_sriov_set_totalvfs(pdev, 7);
-	igb_pci_enable_sriov(pdev, max_vfs);
+	igb_enable_sriov(pdev, max_vfs);
 
 #endif /* CONFIG_PCI_IOV */
 }
diff --git a/drivers/net/ethernet/via/Kconfig b/drivers/net/ethernet/via/Kconfig
index 2f1264b88..d3d094742 100644
--- a/drivers/net/ethernet/via/Kconfig
+++ b/drivers/net/ethernet/via/Kconfig
@@ -17,7 +17,7 @@ if NET_VENDOR_VIA
 
 config VIA_RHINE
 	tristate "VIA Rhine support"
-	depends on (PCI || OF_IRQ)
+	depends on PCI || (OF_IRQ && GENERIC_PCI_IOMAP)
 	depends on HAS_DMA
 	select CRC32
 	select MII
diff --git a/drivers/net/wireless/ath/ath10k/htc.c b/drivers/net/wireless/ath/ath10k/htc.c
index 85bfa2acb..32d9ff1b1 100644
--- a/drivers/net/wireless/ath/ath10k/htc.c
+++ b/drivers/net/wireless/ath/ath10k/htc.c
@@ -145,8 +145,10 @@ int ath10k_htc_send(struct ath10k_htc *htc,
 	skb_cb->eid = eid;
 	skb_cb->paddr = dma_map_single(dev, skb->data, skb->len, DMA_TO_DEVICE);
 	ret = dma_mapping_error(dev, skb_cb->paddr);
-	if (ret)
+	if (ret) {
+		ret = -EIO;
 		goto err_credits;
+	}
 
 	sg_item.transfer_id = ep->eid;
 	sg_item.transfer_context = skb;
diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c
index a60ef7d1d..7be3ce6e0 100644
--- a/drivers/net/wireless/ath/ath10k/htt_tx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_tx.c
@@ -371,8 +371,10 @@ int ath10k_htt_mgmt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
 	skb_cb->paddr = dma_map_single(dev, msdu->data, msdu->len,
 				       DMA_TO_DEVICE);
 	res = dma_mapping_error(dev, skb_cb->paddr);
-	if (res)
+	if (res) {
+		res = -EIO;
 		goto err_free_txdesc;
+	}
 
 	skb_put(txdesc, len);
 	cmd = (struct htt_cmd *)txdesc->data;
@@ -456,8 +458,10 @@ int ath10k_htt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
 	skb_cb->paddr = dma_map_single(dev, msdu->data, msdu->len,
 				       DMA_TO_DEVICE);
 	res = dma_mapping_error(dev, skb_cb->paddr);
-	if (res)
+	if (res) {
+		res = -EIO;
 		goto err_free_txbuf;
+	}
 
 	switch (skb_cb->txmode) {
 	case ATH10K_HW_TXRX_RAW:
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 218b6af63..0d3c474ff 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -591,11 +591,19 @@ ath10k_mac_get_any_chandef_iter(struct ieee80211_hw *hw,
 static int ath10k_peer_create(struct ath10k *ar, u32 vdev_id, const u8 *addr,
 			      enum wmi_peer_type peer_type)
 {
+	struct ath10k_vif *arvif;
+	int num_peers = 0;
 	int ret;
 
 	lockdep_assert_held(&ar->conf_mutex);
 
-	if (ar->num_peers >= ar->max_num_peers)
+	num_peers = ar->num_peers;
+
+	/* Each vdev consumes a peer entry as well */
+	list_for_each_entry(arvif, &ar->arvifs, list)
+		num_peers++;
+
+	if (num_peers >= ar->max_num_peers)
 		return -ENOBUFS;
 
 	ret = ath10k_wmi_peer_create(ar, vdev_id, addr, peer_type);
@@ -2995,6 +3003,8 @@ void ath10k_mac_tx_unlock(struct ath10k *ar, int reason)
 						   IEEE80211_IFACE_ITER_RESUME_ALL,
 						   ath10k_mac_tx_unlock_iter,
 						   ar);
+
+	ieee80211_wake_queue(ar->hw, ar->hw->offchannel_tx_hw_queue);
 }
 
 void ath10k_mac_vif_tx_lock(struct ath10k_vif *arvif, int reason)
@@ -3034,38 +3044,16 @@ static void ath10k_mac_vif_handle_tx_pause(struct ath10k_vif *arvif,
 
 	lockdep_assert_held(&ar->htt.tx_lock);
 
-	switch (pause_id) {
-	case WMI_TLV_TX_PAUSE_ID_MCC:
-	case WMI_TLV_TX_PAUSE_ID_P2P_CLI_NOA:
-	case WMI_TLV_TX_PAUSE_ID_P2P_GO_PS:
-	case WMI_TLV_TX_PAUSE_ID_AP_PS:
-	case WMI_TLV_TX_PAUSE_ID_IBSS_PS:
-		switch (action) {
-		case WMI_TLV_TX_PAUSE_ACTION_STOP:
-			ath10k_mac_vif_tx_lock(arvif, pause_id);
-			break;
-		case WMI_TLV_TX_PAUSE_ACTION_WAKE:
-			ath10k_mac_vif_tx_unlock(arvif, pause_id);
-			break;
-		default:
-			ath10k_warn(ar, "received unknown tx pause action %d on vdev %i, ignoring\n",
-				    action, arvif->vdev_id);
-			break;
-		}
+	switch (action) {
+	case WMI_TLV_TX_PAUSE_ACTION_STOP:
+		ath10k_mac_vif_tx_lock(arvif, pause_id);
+		break;
+	case WMI_TLV_TX_PAUSE_ACTION_WAKE:
+		ath10k_mac_vif_tx_unlock(arvif, pause_id);
 		break;
-	case WMI_TLV_TX_PAUSE_ID_AP_PEER_PS:
-	case WMI_TLV_TX_PAUSE_ID_AP_PEER_UAPSD:
-	case WMI_TLV_TX_PAUSE_ID_STA_ADD_BA:
-	case WMI_TLV_TX_PAUSE_ID_HOST:
 	default:
-		/* FIXME: Some pause_ids aren't vdev specific. Instead they
-		 * target peer_id and tid. Implementing these could improve
-		 * traffic scheduling fairness across multiple connected
-		 * stations in AP/IBSS modes.
-		 */
-		ath10k_dbg(ar, ATH10K_DBG_MAC,
-			   "mac ignoring unsupported tx pause vdev %i id %d\n",
-			   arvif->vdev_id, pause_id);
+		ath10k_warn(ar, "received unknown tx pause action %d on vdev %i, ignoring\n",
+			    action, arvif->vdev_id);
 		break;
 	}
 }
@@ -3082,12 +3070,15 @@ static void ath10k_mac_handle_tx_pause_iter(void *data, u8 *mac,
 	struct ath10k_vif *arvif = ath10k_vif_to_arvif(vif);
 	struct ath10k_mac_tx_pause *arg = data;
 
+	if (arvif->vdev_id != arg->vdev_id)
+		return;
+
 	ath10k_mac_vif_handle_tx_pause(arvif, arg->pause_id, arg->action);
 }
 
-void ath10k_mac_handle_tx_pause(struct ath10k *ar, u32 vdev_id,
-				enum wmi_tlv_tx_pause_id pause_id,
-				enum wmi_tlv_tx_pause_action action)
+void ath10k_mac_handle_tx_pause_vdev(struct ath10k *ar, u32 vdev_id,
+				     enum wmi_tlv_tx_pause_id pause_id,
+				     enum wmi_tlv_tx_pause_action action)
 {
 	struct ath10k_mac_tx_pause arg = {
 		.vdev_id = vdev_id,
@@ -4080,6 +4071,11 @@ static int ath10k_add_interface(struct ieee80211_hw *hw,
 		       sizeof(arvif->bitrate_mask.control[i].vht_mcs));
 	}
 
+	if (ar->num_peers >= ar->max_num_peers) {
+		ath10k_warn(ar, "refusing vdev creation due to insufficient peer entry resources in firmware\n");
+		return -ENOBUFS;
+	}
+
 	if (ar->free_vdev_map == 0) {
 		ath10k_warn(ar, "Free vdev map is empty, no more interfaces allowed.\n");
 		ret = -EBUSY;
@@ -4287,6 +4283,11 @@ static int ath10k_add_interface(struct ieee80211_hw *hw,
 		}
 	}
 
+	spin_lock_bh(&ar->htt.tx_lock);
+	if (!ar->tx_paused)
+		ieee80211_wake_queue(ar->hw, arvif->vdev_id);
+	spin_unlock_bh(&ar->htt.tx_lock);
+
 	mutex_unlock(&ar->conf_mutex);
 	return 0;
 
@@ -5561,6 +5562,21 @@ static int ath10k_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
 	return ret;
 }
 
+static int ath10k_mac_op_set_frag_threshold(struct ieee80211_hw *hw, u32 value)
+{
+	/* Even though there's a WMI enum for fragmentation threshold no known
+	 * firmware actually implements it. Moreover it is not possible to rely
+	 * frame fragmentation to mac80211 because firmware clears the "more
+	 * fragments" bit in frame control making it impossible for remote
+	 * devices to reassemble frames.
+	 *
+	 * Hence implement a dummy callback just to say fragmentation isn't
+	 * supported. This effectively prevents mac80211 from doing frame
+	 * fragmentation in software.
+	 */
+	return -EOPNOTSUPP;
+}
+
 static void ath10k_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			 u32 queues, bool drop)
 {
@@ -6395,6 +6411,7 @@ static const struct ieee80211_ops ath10k_ops = {
 	.remain_on_channel		= ath10k_remain_on_channel,
 	.cancel_remain_on_channel	= ath10k_cancel_remain_on_channel,
 	.set_rts_threshold		= ath10k_set_rts_threshold,
+	.set_frag_threshold		= ath10k_mac_op_set_frag_threshold,
 	.flush				= ath10k_flush,
 	.tx_last_beacon			= ath10k_tx_last_beacon,
 	.set_antenna			= ath10k_set_antenna,
diff --git a/drivers/net/wireless/ath/ath10k/mac.h b/drivers/net/wireless/ath/ath10k/mac.h
index b291f0637..e3cefe4c7 100644
--- a/drivers/net/wireless/ath/ath10k/mac.h
+++ b/drivers/net/wireless/ath/ath10k/mac.h
@@ -61,9 +61,9 @@ int ath10k_mac_vif_chan(struct ieee80211_vif *vif,
 
 void ath10k_mac_handle_beacon(struct ath10k *ar, struct sk_buff *skb);
 void ath10k_mac_handle_beacon_miss(struct ath10k *ar, u32 vdev_id);
-void ath10k_mac_handle_tx_pause(struct ath10k *ar, u32 vdev_id,
-				enum wmi_tlv_tx_pause_id pause_id,
-				enum wmi_tlv_tx_pause_action action);
+void ath10k_mac_handle_tx_pause_vdev(struct ath10k *ar, u32 vdev_id,
+				     enum wmi_tlv_tx_pause_id pause_id,
+				     enum wmi_tlv_tx_pause_action action);
 
 u8 ath10k_mac_hw_rate_to_idx(const struct ieee80211_supported_band *sband,
 			     u8 hw_rate);
diff --git a/drivers/net/wireless/ath/ath10k/pci.c b/drivers/net/wireless/ath/ath10k/pci.c
index ecc9ab57b..79b707138 100644
--- a/drivers/net/wireless/ath/ath10k/pci.c
+++ b/drivers/net/wireless/ath/ath10k/pci.c
@@ -1546,8 +1546,10 @@ static int ath10k_pci_hif_exchange_bmi_msg(struct ath10k *ar,
 
 	req_paddr = dma_map_single(ar->dev, treq, req_len, DMA_TO_DEVICE);
 	ret = dma_mapping_error(ar->dev, req_paddr);
-	if (ret)
+	if (ret) {
+		ret = -EIO;
 		goto err_dma;
+	}
 
 	if (resp && resp_len) {
 		tresp = kzalloc(*resp_len, GFP_KERNEL);
@@ -1559,8 +1561,10 @@ static int ath10k_pci_hif_exchange_bmi_msg(struct ath10k *ar,
 		resp_paddr = dma_map_single(ar->dev, tresp, *resp_len,
 					    DMA_FROM_DEVICE);
 		ret = dma_mapping_error(ar->dev, resp_paddr);
-		if (ret)
+		if (ret) {
+			ret = EIO;
 			goto err_req;
+		}
 
 		xfer.wait_for_resp = true;
 		xfer.resp_len = 0;
diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
index 8fdba3865..6f477e830 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
@@ -377,12 +377,34 @@ static int ath10k_wmi_tlv_event_tx_pause(struct ath10k *ar,
 		   "wmi tlv tx pause pause_id %u action %u vdev_map 0x%08x peer_id %u tid_map 0x%08x\n",
 		   pause_id, action, vdev_map, peer_id, tid_map);
 
-	for (vdev_id = 0; vdev_map; vdev_id++) {
-		if (!(vdev_map & BIT(vdev_id)))
-			continue;
-
-		vdev_map &= ~BIT(vdev_id);
-		ath10k_mac_handle_tx_pause(ar, vdev_id, pause_id, action);
+	switch (pause_id) {
+	case WMI_TLV_TX_PAUSE_ID_MCC:
+	case WMI_TLV_TX_PAUSE_ID_P2P_CLI_NOA:
+	case WMI_TLV_TX_PAUSE_ID_P2P_GO_PS:
+	case WMI_TLV_TX_PAUSE_ID_AP_PS:
+	case WMI_TLV_TX_PAUSE_ID_IBSS_PS:
+		for (vdev_id = 0; vdev_map; vdev_id++) {
+			if (!(vdev_map & BIT(vdev_id)))
+				continue;
+
+			vdev_map &= ~BIT(vdev_id);
+			ath10k_mac_handle_tx_pause_vdev(ar, vdev_id, pause_id,
+							action);
+		}
+		break;
+	case WMI_TLV_TX_PAUSE_ID_AP_PEER_PS:
+	case WMI_TLV_TX_PAUSE_ID_AP_PEER_UAPSD:
+	case WMI_TLV_TX_PAUSE_ID_STA_ADD_BA:
+	case WMI_TLV_TX_PAUSE_ID_HOST:
+		ath10k_dbg(ar, ATH10K_DBG_MAC,
+			   "mac ignoring unsupported tx pause id %d\n",
+			   pause_id);
+		break;
+	default:
+		ath10k_dbg(ar, ATH10K_DBG_MAC,
+			   "mac ignoring unknown tx pause vdev %d\n",
+			   pause_id);
+		break;
 	}
 
 	kfree(tb);
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 6c046c244..8dd84c160 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -2391,6 +2391,7 @@ void ath10k_wmi_event_host_swba(struct ath10k *ar, struct sk_buff *skb)
 				ath10k_warn(ar, "failed to map beacon: %d\n",
 					    ret);
 				dev_kfree_skb_any(bcn);
+				ret = -EIO;
 				goto skip;
 			}
 
diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c
index afd382417..6eb4d21e3 100644
--- a/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c
+++ b/drivers/net/wireless/rsi/rsi_91x_sdio_ops.c
@@ -203,8 +203,10 @@ static int rsi_load_ta_instructions(struct rsi_common *common)
 
 	/* Copy firmware into DMA-accessible memory */
 	fw = kmemdup(fw_entry->data, fw_entry->size, GFP_KERNEL);
-	if (!fw)
-		return -ENOMEM;
+	if (!fw) {
+		status = -ENOMEM;
+		goto out;
+	}
 	len = fw_entry->size;
 
 	if (len % 4)
@@ -217,6 +219,8 @@ static int rsi_load_ta_instructions(struct rsi_common *common)
 
 	status = rsi_copy_to_card(common, fw, len, num_blocks);
 	kfree(fw);
+
+out:
 	release_firmware(fw_entry);
 	return status;
 }
diff --git a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c
index c8cfb4a1c..3bd8fba4f 100644
--- a/drivers/net/wireless/rsi/rsi_91x_usb_ops.c
+++ b/drivers/net/wireless/rsi/rsi_91x_usb_ops.c
@@ -148,8 +148,10 @@ static int rsi_load_ta_instructions(struct rsi_common *common)
 
 	/* Copy firmware into DMA-accessible memory */
 	fw = kmemdup(fw_entry->data, fw_entry->size, GFP_KERNEL);
-	if (!fw)
-		return -ENOMEM;
+	if (!fw) {
+		status = -ENOMEM;
+		goto out;
+	}
 	len = fw_entry->size;
 
 	if (len % 4)
@@ -162,6 +164,8 @@ static int rsi_load_ta_instructions(struct rsi_common *common)
 
 	status = rsi_copy_to_card(common, fw, len, num_blocks);
 	kfree(fw);
+
+out:
 	release_firmware(fw_entry);
 	return status;
 }
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index f948c46d5..5ff0cfd14 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1348,7 +1348,8 @@ static void xennet_disconnect_backend(struct netfront_info *info)
 		queue->tx_evtchn = queue->rx_evtchn = 0;
 		queue->tx_irq = queue->rx_irq = 0;
 
-		napi_synchronize(&queue->napi);
+		if (netif_running(info->netdev))
+			napi_synchronize(&queue->napi);
 
 		xennet_release_tx_bufs(queue);
 		xennet_release_rx_bufs(queue);
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index ade9eb917..b796d1bd8 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -86,6 +86,8 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 	struct pmem_device *pmem = bdev->bd_disk->private_data;
 
 	pmem_do_bvec(pmem, page, PAGE_CACHE_SIZE, 0, rw, sector);
+	if (rw & WRITE)
+		wmb_pmem();
 	page_endio(page, rw & WRITE, 0);
 
 	return 0;
diff --git a/drivers/pci/access.c b/drivers/pci/access.c
index b965c1216..502a82ca1 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -442,7 +442,8 @@ static const struct pci_vpd_ops pci_vpd_pci22_ops = {
 static ssize_t pci_vpd_f0_read(struct pci_dev *dev, loff_t pos, size_t count,
 			       void *arg)
 {
-	struct pci_dev *tdev = pci_get_slot(dev->bus, PCI_SLOT(dev->devfn));
+	struct pci_dev *tdev = pci_get_slot(dev->bus,
+					    PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
 	ssize_t ret;
 
 	if (!tdev)
@@ -456,7 +457,8 @@ static ssize_t pci_vpd_f0_read(struct pci_dev *dev, loff_t pos, size_t count,
 static ssize_t pci_vpd_f0_write(struct pci_dev *dev, loff_t pos, size_t count,
 				const void *arg)
 {
-	struct pci_dev *tdev = pci_get_slot(dev->bus, PCI_SLOT(dev->devfn));
+	struct pci_dev *tdev = pci_get_slot(dev->bus,
+					    PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
 	ssize_t ret;
 
 	if (!tdev)
@@ -473,22 +475,6 @@ static const struct pci_vpd_ops pci_vpd_f0_ops = {
 	.release = pci_vpd_pci22_release,
 };
 
-static int pci_vpd_f0_dev_check(struct pci_dev *dev)
-{
-	struct pci_dev *tdev = pci_get_slot(dev->bus, PCI_SLOT(dev->devfn));
-	int ret = 0;
-
-	if (!tdev)
-		return -ENODEV;
-	if (!tdev->vpd || !tdev->multifunction ||
-	    dev->class != tdev->class || dev->vendor != tdev->vendor ||
-	    dev->device != tdev->device)
-		ret = -ENODEV;
-
-	pci_dev_put(tdev);
-	return ret;
-}
-
 int pci_vpd_pci22_init(struct pci_dev *dev)
 {
 	struct pci_vpd_pci22 *vpd;
@@ -497,12 +483,7 @@ int pci_vpd_pci22_init(struct pci_dev *dev)
 	cap = pci_find_capability(dev, PCI_CAP_ID_VPD);
 	if (!cap)
 		return -ENODEV;
-	if (dev->dev_flags & PCI_DEV_FLAGS_VPD_REF_F0) {
-		int ret = pci_vpd_f0_dev_check(dev);
 
-		if (ret)
-			return ret;
-	}
 	vpd = kzalloc(sizeof(*vpd), GFP_ATOMIC);
 	if (!vpd)
 		return -ENOMEM;
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 6fbd3f2b5..d3346d239 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -256,6 +256,8 @@ bool pci_bus_clip_resource(struct pci_dev *dev, int idx)
 
 		res->start = start;
 		res->end = end;
+		res->flags &= ~IORESOURCE_UNSET;
+		orig_res.flags &= ~IORESOURCE_UNSET;
 		dev_printk(KERN_DEBUG, &dev->dev, "%pR clipped to %pR\n",
 				 &orig_res, res);
 
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index dbd13854f..6b1c6a915 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -1906,11 +1906,27 @@ static void quirk_netmos(struct pci_dev *dev)
 DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_NETMOS, PCI_ANY_ID,
 			 PCI_CLASS_COMMUNICATION_SERIAL, 8, quirk_netmos);
 
+/*
+ * Quirk non-zero PCI functions to route VPD access through function 0 for
+ * devices that share VPD resources between functions.  The functions are
+ * expected to be identical devices.
+ */
 static void quirk_f0_vpd_link(struct pci_dev *dev)
 {
-	if (!dev->multifunction || !PCI_FUNC(dev->devfn))
+	struct pci_dev *f0;
+
+	if (!PCI_FUNC(dev->devfn))
 		return;
-	dev->dev_flags |= PCI_DEV_FLAGS_VPD_REF_F0;
+
+	f0 = pci_get_slot(dev->bus, PCI_DEVFN(PCI_SLOT(dev->devfn), 0));
+	if (!f0)
+		return;
+
+	if (f0->vpd && dev->class == f0->class &&
+	    dev->vendor == f0->vendor && dev->device == f0->device)
+		dev->dev_flags |= PCI_DEV_FLAGS_VPD_REF_F0;
+
+	pci_dev_put(f0);
 }
 DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
 			      PCI_CLASS_NETWORK_ETHERNET, 8, quirk_f0_vpd_link);
diff --git a/drivers/pcmcia/sa1100_generic.c b/drivers/pcmcia/sa1100_generic.c
index 803945259..42861cc70 100644
--- a/drivers/pcmcia/sa1100_generic.c
+++ b/drivers/pcmcia/sa1100_generic.c
@@ -93,7 +93,6 @@ static int sa11x0_drv_pcmcia_remove(struct platform_device *dev)
 	for (i = 0; i < sinfo->nskt; i++)
 		soc_pcmcia_remove_one(&sinfo->skt[i]);
 
-	clk_put(sinfo->clk);
 	kfree(sinfo);
 	return 0;
 }
diff --git a/drivers/pcmcia/sa11xx_base.c b/drivers/pcmcia/sa11xx_base.c
index cf6de2c2b..553d70a67 100644
--- a/drivers/pcmcia/sa11xx_base.c
+++ b/drivers/pcmcia/sa11xx_base.c
@@ -222,7 +222,7 @@ int sa11xx_drv_pcmcia_probe(struct device *dev, struct pcmcia_low_level *ops,
 	int i, ret = 0;
 	struct clk *clk;
 
-	clk = clk_get(dev, NULL);
+	clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(clk))
 		return PTR_ERR(clk);
 
@@ -251,7 +251,6 @@ int sa11xx_drv_pcmcia_probe(struct device *dev, struct pcmcia_low_level *ops,
 	if (ret) {
 		while (--i >= 0)
 			soc_pcmcia_remove_one(&sinfo->skt[i]);
-		clk_put(clk);
 		kfree(sinfo);
 	} else {
 		dev_set_drvdata(dev, sinfo);
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index 3ad7b1fa2..6f4f310de 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -2408,11 +2408,9 @@ static int toshiba_acpi_setup_keyboard(struct toshiba_acpi_dev *dev)
 	if (error)
 		return error;
 
-	error = toshiba_hotkey_event_type_get(dev, &events_type);
-	if (error) {
-		pr_err("Unable to query Hotkey Event Type\n");
-		return error;
-	}
+	if (toshiba_hotkey_event_type_get(dev, &events_type))
+		pr_notice("Unable to query Hotkey Event Type\n");
+
 	dev->hotkey_event_type = events_type;
 
 	dev->hotkey_dev = input_allocate_device();
diff --git a/drivers/power/avs/Kconfig b/drivers/power/avs/Kconfig
index 7f3d389bd..a67eeace6 100644
--- a/drivers/power/avs/Kconfig
+++ b/drivers/power/avs/Kconfig
@@ -13,7 +13,7 @@ menuconfig POWER_AVS
 
 config ROCKCHIP_IODOMAIN
         tristate "Rockchip IO domain support"
-        depends on ARCH_ROCKCHIP && OF
+        depends on POWER_AVS && ARCH_ROCKCHIP && OF
         help
           Say y here to enable support io domains on Rockchip SoCs. It is
           necessary for the io domain setting of the SoC to match the
diff --git a/drivers/regulator/axp20x-regulator.c b/drivers/regulator/axp20x-regulator.c
index 646829132..1dea0e835 100644
--- a/drivers/regulator/axp20x-regulator.c
+++ b/drivers/regulator/axp20x-regulator.c
@@ -192,9 +192,9 @@ static const struct regulator_desc axp22x_regulators[] = {
 	AXP_DESC(AXP22X, DCDC3, "dcdc3", "vin3", 600, 1860, 20,
 		 AXP22X_DCDC3_V_OUT, 0x3f, AXP22X_PWR_OUT_CTRL1, BIT(3)),
 	AXP_DESC(AXP22X, DCDC4, "dcdc4", "vin4", 600, 1540, 20,
-		 AXP22X_DCDC4_V_OUT, 0x3f, AXP22X_PWR_OUT_CTRL1, BIT(3)),
+		 AXP22X_DCDC4_V_OUT, 0x3f, AXP22X_PWR_OUT_CTRL1, BIT(4)),
 	AXP_DESC(AXP22X, DCDC5, "dcdc5", "vin5", 1000, 2550, 50,
-		 AXP22X_DCDC5_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL1, BIT(4)),
+		 AXP22X_DCDC5_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL1, BIT(5)),
 	/* secondary switchable output of DCDC1 */
 	AXP_DESC_SW(AXP22X, DC1SW, "dc1sw", "dcdc1", 1600, 3400, 100,
 		    AXP22X_DCDC1_V_OUT, 0x1f, AXP22X_PWR_OUT_CTRL2, BIT(7)),
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 78387a6cb..508153385 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1376,15 +1376,19 @@ static int regulator_resolve_supply(struct regulator_dev *rdev)
 		return 0;
 
 	r = regulator_dev_lookup(dev, rdev->supply_name, &ret);
-	if (ret == -ENODEV) {
-		/*
-		 * No supply was specified for this regulator and
-		 * there will never be one.
-		 */
-		return 0;
-	}
-
 	if (!r) {
+		if (ret == -ENODEV) {
+			/*
+			 * No supply was specified for this regulator and
+			 * there will never be one.
+			 */
+			return 0;
+		}
+
+		/* Did the lookup explicitly defer for us? */
+		if (ret == -EPROBE_DEFER)
+			return ret;
+
 		if (have_full_constraints()) {
 			r = dummy_regulator_rdev;
 		} else {
diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index add419d6f..a56a7b243 100644
--- a/drivers/scsi/3w-9xxx.c
+++ b/drivers/scsi/3w-9xxx.c
@@ -212,6 +212,17 @@ static const struct file_operations twa_fops = {
 	.llseek		= noop_llseek,
 };
 
+/*
+ * The controllers use an inline buffer instead of a mapped SGL for small,
+ * single entry buffers.  Note that we treat a zero-length transfer like
+ * a mapped SGL.
+ */
+static bool twa_command_mapped(struct scsi_cmnd *cmd)
+{
+	return scsi_sg_count(cmd) != 1 ||
+		scsi_bufflen(cmd) >= TW_MIN_SGL_LENGTH;
+}
+
 /* This function will complete an aen request from the isr */
 static int twa_aen_complete(TW_Device_Extension *tw_dev, int request_id)
 {
@@ -1339,7 +1350,8 @@ static irqreturn_t twa_interrupt(int irq, void *dev_instance)
 				}
 
 				/* Now complete the io */
-				scsi_dma_unmap(cmd);
+				if (twa_command_mapped(cmd))
+					scsi_dma_unmap(cmd);
 				cmd->scsi_done(cmd);
 				tw_dev->state[request_id] = TW_S_COMPLETED;
 				twa_free_request_id(tw_dev, request_id);
@@ -1582,7 +1594,8 @@ static int twa_reset_device_extension(TW_Device_Extension *tw_dev)
 				struct scsi_cmnd *cmd = tw_dev->srb[i];
 
 				cmd->result = (DID_RESET << 16);
-				scsi_dma_unmap(cmd);
+				if (twa_command_mapped(cmd))
+					scsi_dma_unmap(cmd);
 				cmd->scsi_done(cmd);
 			}
 		}
@@ -1765,12 +1778,14 @@ static int twa_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_
 	retval = twa_scsiop_execute_scsi(tw_dev, request_id, NULL, 0, NULL);
 	switch (retval) {
 	case SCSI_MLQUEUE_HOST_BUSY:
-		scsi_dma_unmap(SCpnt);
+		if (twa_command_mapped(SCpnt))
+			scsi_dma_unmap(SCpnt);
 		twa_free_request_id(tw_dev, request_id);
 		break;
 	case 1:
 		SCpnt->result = (DID_ERROR << 16);
-		scsi_dma_unmap(SCpnt);
+		if (twa_command_mapped(SCpnt))
+			scsi_dma_unmap(SCpnt);
 		done(SCpnt);
 		tw_dev->state[request_id] = TW_S_COMPLETED;
 		twa_free_request_id(tw_dev, request_id);
@@ -1831,8 +1846,7 @@ static int twa_scsiop_execute_scsi(TW_Device_Extension *tw_dev, int request_id,
 		/* Map sglist from scsi layer to cmd packet */
 
 		if (scsi_sg_count(srb)) {
-			if ((scsi_sg_count(srb) == 1) &&
-			    (scsi_bufflen(srb) < TW_MIN_SGL_LENGTH)) {
+			if (!twa_command_mapped(srb)) {
 				if (srb->sc_data_direction == DMA_TO_DEVICE ||
 				    srb->sc_data_direction == DMA_BIDIRECTIONAL)
 					scsi_sg_copy_to_buffer(srb,
@@ -1905,7 +1919,7 @@ static void twa_scsiop_execute_scsi_complete(TW_Device_Extension *tw_dev, int re
 {
 	struct scsi_cmnd *cmd = tw_dev->srb[request_id];
 
-	if (scsi_bufflen(cmd) < TW_MIN_SGL_LENGTH &&
+	if (!twa_command_mapped(cmd) &&
 	    (cmd->sc_data_direction == DMA_FROM_DEVICE ||
 	     cmd->sc_data_direction == DMA_BIDIRECTIONAL)) {
 		if (scsi_sg_count(cmd) == 1) {
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 1dafeb433..cab4e98b2 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -5104,7 +5104,7 @@ static int hpsa_eh_device_reset_handler(struct scsi_cmnd *scsicmd)
 	int rc;
 	struct ctlr_info *h;
 	struct hpsa_scsi_dev_t *dev;
-	char msg[40];
+	char msg[48];
 
 	/* find the controller to which the command to be aborted was sent */
 	h = sdev_to_hba(scsicmd->device);
@@ -5122,16 +5122,18 @@ static int hpsa_eh_device_reset_handler(struct scsi_cmnd *scsicmd)
 
 	/* if controller locked up, we can guarantee command won't complete */
 	if (lockup_detected(h)) {
-		sprintf(msg, "cmd %d RESET FAILED, lockup detected",
-				hpsa_get_cmd_index(scsicmd));
+		snprintf(msg, sizeof(msg),
+			 "cmd %d RESET FAILED, lockup detected",
+			 hpsa_get_cmd_index(scsicmd));
 		hpsa_show_dev_msg(KERN_WARNING, h, dev, msg);
 		return FAILED;
 	}
 
 	/* this reset request might be the result of a lockup; check */
 	if (detect_controller_lockup(h)) {
-		sprintf(msg, "cmd %d RESET FAILED, new lockup detected",
-				hpsa_get_cmd_index(scsicmd));
+		snprintf(msg, sizeof(msg),
+			 "cmd %d RESET FAILED, new lockup detected",
+			 hpsa_get_cmd_index(scsicmd));
 		hpsa_show_dev_msg(KERN_WARNING, h, dev, msg);
 		return FAILED;
 	}
@@ -5145,7 +5147,8 @@ static int hpsa_eh_device_reset_handler(struct scsi_cmnd *scsicmd)
 	/* send a reset to the SCSI LUN which the command was sent to */
 	rc = hpsa_do_reset(h, dev, dev->scsi3addr, HPSA_RESET_TYPE_LUN,
 			   DEFAULT_REPLY_QUEUE);
-	sprintf(msg, "reset %s", rc == 0 ? "completed successfully" : "failed");
+	snprintf(msg, sizeof(msg), "reset %s",
+		 rc == 0 ? "completed successfully" : "failed");
 	hpsa_show_dev_msg(KERN_WARNING, h, dev, msg);
 	return rc == 0 ? SUCCESS : FAILED;
 }
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index a9aa38903..cccab6188 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -4554,7 +4554,7 @@ static ssize_t ipr_store_raw_mode(struct device *dev,
 	spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
 	res = (struct ipr_resource_entry *)sdev->hostdata;
 	if (res) {
-		if (ioa_cfg->sis64 && ipr_is_af_dasd_device(res)) {
+		if (ipr_is_af_dasd_device(res)) {
 			res->raw_mode = simple_strtoul(buf, NULL, 10);
 			len = strlen(buf);
 			if (res->sdev)
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 6457a8a0d..bf3d801ac 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -2169,8 +2169,17 @@ int scsi_error_handler(void *data)
 	 * We never actually get interrupted because kthread_run
 	 * disables signal delivery for the created thread.
 	 */
-	while (!kthread_should_stop()) {
+	while (true) {
+		/*
+		 * The sequence in kthread_stop() sets the stop flag first
+		 * then wakes the process.  To avoid missed wakeups, the task
+		 * should always be in a non running state before the stop
+		 * flag is checked
+		 */
 		set_current_state(TASK_INTERRUPTIBLE);
+		if (kthread_should_stop())
+			break;
+
 		if ((shost->host_failed == 0 && shost->host_eh_scheduled == 0) ||
 		    shost->host_failed != atomic_read(&shost->host_busy)) {
 			SCSI_LOG_ERROR_RECOVERY(1,
diff --git a/drivers/spi/spi-bcm2835.c b/drivers/spi/spi-bcm2835.c
index c9357bb39..744596464 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -386,14 +386,14 @@ static bool bcm2835_spi_can_dma(struct spi_master *master,
 	/* otherwise we only allow transfers within the same page
 	 * to avoid wasting time on dma_mapping when it is not practical
 	 */
-	if (((size_t)tfr->tx_buf & PAGE_MASK) + tfr->len > PAGE_SIZE) {
+	if (((size_t)tfr->tx_buf & (PAGE_SIZE - 1)) + tfr->len > PAGE_SIZE) {
 		dev_warn_once(&spi->dev,
 			      "Unaligned spi tx-transfer bridging page\n");
 		return false;
 	}
-	if (((size_t)tfr->rx_buf & PAGE_MASK) + tfr->len > PAGE_SIZE) {
+	if (((size_t)tfr->rx_buf & (PAGE_SIZE - 1)) + tfr->len > PAGE_SIZE) {
 		dev_warn_once(&spi->dev,
-			      "Unaligned spi tx-transfer bridging page\n");
+			      "Unaligned spi rx-transfer bridging page\n");
 		return false;
 	}
 
diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 7293d6d87..8e4b1a7c3 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -643,6 +643,10 @@ static irqreturn_t ssp_int(int irq, void *dev_id)
 	if (!(sccr1_reg & SSCR1_TIE))
 		mask &= ~SSSR_TFS;
 
+	/* Ignore RX timeout interrupt if it is disabled */
+	if (!(sccr1_reg & SSCR1_TINTE))
+		mask &= ~SSSR_TINT;
+
 	if (!(status & mask))
 		return IRQ_NONE;
 
diff --git a/drivers/spi/spi-xtensa-xtfpga.c b/drivers/spi/spi-xtensa-xtfpga.c
index 2e32ea2f1..be6155cba 100644
--- a/drivers/spi/spi-xtensa-xtfpga.c
+++ b/drivers/spi/spi-xtensa-xtfpga.c
@@ -34,13 +34,13 @@ struct xtfpga_spi {
 static inline void xtfpga_spi_write32(const struct xtfpga_spi *spi,
 				      unsigned addr, u32 val)
 {
-	iowrite32(val, spi->regs + addr);
+	__raw_writel(val, spi->regs + addr);
 }
 
 static inline unsigned int xtfpga_spi_read32(const struct xtfpga_spi *spi,
 					     unsigned addr)
 {
-	return ioread32(spi->regs + addr);
+	return __raw_readl(spi->regs + addr);
 }
 
 static inline void xtfpga_spi_wait_busy(struct xtfpga_spi *xspi)
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index cf8b91b23..9ce2f156d 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1437,8 +1437,7 @@ static struct class spi_master_class = {
  *
  * The caller is responsible for assigning the bus number and initializing
  * the master's methods before calling spi_register_master(); and (after errors
- * adding the device) calling spi_master_put() and kfree() to prevent a memory
- * leak.
+ * adding the device) calling spi_master_put() to prevent a memory leak.
  */
 struct spi_master *spi_alloc_master(struct device *dev, unsigned size)
 {
diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
index c7de64171..97aad8f91 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -651,7 +651,8 @@ static int spidev_release(struct inode *inode, struct file *filp)
 		kfree(spidev->rx_buffer);
 		spidev->rx_buffer = NULL;
 
-		spidev->speed_hz = spidev->spi->max_speed_hz;
+		if (spidev->spi)
+			spidev->speed_hz = spidev->spi->max_speed_hz;
 
 		/* ... after we unbound from the underlying device? */
 		spin_lock_irq(&spidev->spi_lock);
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index 6f4811263..b71b1f2d9 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -1179,13 +1179,13 @@ struct ion_handle *ion_import_dma_buf(struct ion_client *client, int fd)
 		mutex_unlock(&client->lock);
 		goto end;
 	}
-	mutex_unlock(&client->lock);
 
 	handle = ion_handle_create(client, buffer);
-	if (IS_ERR(handle))
+	if (IS_ERR(handle)) {
+		mutex_unlock(&client->lock);
 		goto end;
+	}
 
-	mutex_lock(&client->lock);
 	ret = ion_handle_add(client, handle);
 	mutex_unlock(&client->lock);
 	if (ret) {
diff --git a/drivers/staging/speakup/fakekey.c b/drivers/staging/speakup/fakekey.c
index 4299cf45f..5e1f16c36 100644
--- a/drivers/staging/speakup/fakekey.c
+++ b/drivers/staging/speakup/fakekey.c
@@ -81,6 +81,7 @@ void speakup_fake_down_arrow(void)
 	__this_cpu_write(reporting_keystroke, true);
 	input_report_key(virt_keyboard, KEY_DOWN, PRESSED);
 	input_report_key(virt_keyboard, KEY_DOWN, RELEASED);
+	input_sync(virt_keyboard);
 	__this_cpu_write(reporting_keystroke, false);
 
 	/* reenable preemption */
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index fd092909a..56cf1996f 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -341,7 +341,6 @@ static struct iscsi_np *iscsit_get_np(
 
 struct iscsi_np *iscsit_add_np(
 	struct __kernel_sockaddr_storage *sockaddr,
-	char *ip_str,
 	int network_transport)
 {
 	struct sockaddr_in *sock_in;
@@ -370,11 +369,9 @@ struct iscsi_np *iscsit_add_np(
 	np->np_flags |= NPF_IP_NETWORK;
 	if (sockaddr->ss_family == AF_INET6) {
 		sock_in6 = (struct sockaddr_in6 *)sockaddr;
-		snprintf(np->np_ip, IPV6_ADDRESS_SPACE, "%s", ip_str);
 		np->np_port = ntohs(sock_in6->sin6_port);
 	} else {
 		sock_in = (struct sockaddr_in *)sockaddr;
-		sprintf(np->np_ip, "%s", ip_str);
 		np->np_port = ntohs(sock_in->sin_port);
 	}
 
@@ -411,8 +408,8 @@ struct iscsi_np *iscsit_add_np(
 	list_add_tail(&np->np_list, &g_np_list);
 	mutex_unlock(&np_lock);
 
-	pr_debug("CORE[0] - Added Network Portal: %s:%hu on %s\n",
-		np->np_ip, np->np_port, np->np_transport->name);
+	pr_debug("CORE[0] - Added Network Portal: %pISc:%hu on %s\n",
+		&np->np_sockaddr, np->np_port, np->np_transport->name);
 
 	return np;
 }
@@ -481,8 +478,8 @@ int iscsit_del_np(struct iscsi_np *np)
 	list_del(&np->np_list);
 	mutex_unlock(&np_lock);
 
-	pr_debug("CORE[0] - Removed Network Portal: %s:%hu on %s\n",
-		np->np_ip, np->np_port, np->np_transport->name);
+	pr_debug("CORE[0] - Removed Network Portal: %pISc:%hu on %s\n",
+		&np->np_sockaddr, np->np_port, np->np_transport->name);
 
 	iscsit_put_transport(np->np_transport);
 	kfree(np);
@@ -3464,7 +3461,6 @@ iscsit_build_sendtargets_response(struct iscsi_cmd *cmd,
 						tpg_np_list) {
 				struct iscsi_np *np = tpg_np->tpg_np;
 				bool inaddr_any = iscsit_check_inaddr_any(np);
-				char *fmt_str;
 
 				if (np->np_network_transport != network_transport)
 					continue;
@@ -3492,15 +3488,18 @@ iscsit_build_sendtargets_response(struct iscsi_cmd *cmd,
 					}
 				}
 
-				if (np->np_sockaddr.ss_family == AF_INET6)
-					fmt_str = "TargetAddress=[%s]:%hu,%hu";
-				else
-					fmt_str = "TargetAddress=%s:%hu,%hu";
-
-				len = sprintf(buf, fmt_str,
-					inaddr_any ? conn->local_ip : np->np_ip,
-					np->np_port,
-					tpg->tpgt);
+				if (inaddr_any) {
+					len = sprintf(buf, "TargetAddress="
+						      "%s:%hu,%hu",
+						      conn->local_ip,
+						      np->np_port,
+						      tpg->tpgt);
+				} else {
+					len = sprintf(buf, "TargetAddress="
+						      "%pISpc,%hu",
+						      &np->np_sockaddr,
+						      tpg->tpgt);
+				}
 				len += 1;
 
 				if ((len + payload_len) > buffer_len) {
diff --git a/drivers/target/iscsi/iscsi_target.h b/drivers/target/iscsi/iscsi_target.h
index 7d0f9c00d..d294f030a 100644
--- a/drivers/target/iscsi/iscsi_target.h
+++ b/drivers/target/iscsi/iscsi_target.h
@@ -13,7 +13,7 @@ extern int iscsit_deaccess_np(struct iscsi_np *, struct iscsi_portal_group *,
 extern bool iscsit_check_np_match(struct __kernel_sockaddr_storage *,
 				struct iscsi_np *, int);
 extern struct iscsi_np *iscsit_add_np(struct __kernel_sockaddr_storage *,
-				char *, int);
+				int);
 extern int iscsit_reset_np_thread(struct iscsi_np *, struct iscsi_tpg_np *,
 				struct iscsi_portal_group *, bool);
 extern int iscsit_del_np(struct iscsi_np *);
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index c1898c84b..db3b9b986 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -99,7 +99,7 @@ static ssize_t lio_target_np_store_sctp(
 		 * Use existing np->np_sockaddr for SCTP network portal reference
 		 */
 		tpg_np_sctp = iscsit_tpg_add_network_portal(tpg, &np->np_sockaddr,
-					np->np_ip, tpg_np, ISCSI_SCTP_TCP);
+					tpg_np, ISCSI_SCTP_TCP);
 		if (!tpg_np_sctp || IS_ERR(tpg_np_sctp))
 			goto out;
 	} else {
@@ -177,7 +177,7 @@ static ssize_t lio_target_np_store_iser(
 		}
 
 		tpg_np_iser = iscsit_tpg_add_network_portal(tpg, &np->np_sockaddr,
-				np->np_ip, tpg_np, ISCSI_INFINIBAND);
+				tpg_np, ISCSI_INFINIBAND);
 		if (IS_ERR(tpg_np_iser)) {
 			rc = PTR_ERR(tpg_np_iser);
 			goto out;
@@ -248,8 +248,8 @@ static struct se_tpg_np *lio_target_call_addnptotpg(
 			return ERR_PTR(-EINVAL);
 		}
 		str++; /* Skip over leading "[" */
-		*str2 = '\0'; /* Terminate the IPv6 address */
-		str2++; /* Skip over the "]" */
+		*str2 = '\0'; /* Terminate the unbracketed IPv6 address */
+		str2++; /* Skip over the \0 */
 		port_str = strstr(str2, ":");
 		if (!port_str) {
 			pr_err("Unable to locate \":port\""
@@ -316,7 +316,7 @@ static struct se_tpg_np *lio_target_call_addnptotpg(
 	 * sys/kernel/config/iscsi/$IQN/$TPG/np/$IP:$PORT/
 	 *
 	 */
-	tpg_np = iscsit_tpg_add_network_portal(tpg, &sockaddr, str, NULL,
+	tpg_np = iscsit_tpg_add_network_portal(tpg, &sockaddr, NULL,
 				ISCSI_TCP);
 	if (IS_ERR(tpg_np)) {
 		iscsit_put_tpg(tpg);
@@ -344,8 +344,8 @@ static void lio_target_call_delnpfromtpg(
 
 	se_tpg = &tpg->tpg_se_tpg;
 	pr_debug("LIO_Target_ConfigFS: DEREGISTER -> %s TPGT: %hu"
-		" PORTAL: %s:%hu\n", config_item_name(&se_tpg->se_tpg_wwn->wwn_group.cg_item),
-		tpg->tpgt, tpg_np->tpg_np->np_ip, tpg_np->tpg_np->np_port);
+		" PORTAL: %pISc:%hu\n", config_item_name(&se_tpg->se_tpg_wwn->wwn_group.cg_item),
+		tpg->tpgt, &tpg_np->tpg_np->np_sockaddr, tpg_np->tpg_np->np_port);
 
 	ret = iscsit_tpg_del_network_portal(tpg, tpg_np);
 	if (ret < 0)
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 7e8f65e54..666c0739b 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -823,8 +823,8 @@ static void iscsi_handle_login_thread_timeout(unsigned long data)
 	struct iscsi_np *np = (struct iscsi_np *) data;
 
 	spin_lock_bh(&np->np_thread_lock);
-	pr_err("iSCSI Login timeout on Network Portal %s:%hu\n",
-			np->np_ip, np->np_port);
+	pr_err("iSCSI Login timeout on Network Portal %pISc:%hu\n",
+			&np->np_sockaddr, np->np_port);
 
 	if (np->np_login_timer_flags & ISCSI_TF_STOP) {
 		spin_unlock_bh(&np->np_thread_lock);
@@ -1302,8 +1302,8 @@ static int __iscsi_target_login_thread(struct iscsi_np *np)
 	spin_lock_bh(&np->np_thread_lock);
 	if (np->np_thread_state != ISCSI_NP_THREAD_ACTIVE) {
 		spin_unlock_bh(&np->np_thread_lock);
-		pr_err("iSCSI Network Portal on %s:%hu currently not"
-			" active.\n", np->np_ip, np->np_port);
+		pr_err("iSCSI Network Portal on %pISc:%hu currently not"
+			" active.\n", &np->np_sockaddr, np->np_port);
 		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
 				ISCSI_LOGIN_STATUS_SVC_UNAVAILABLE);
 		goto new_sess_out;
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index e8a52f7d6..51d1734d5 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -407,6 +407,7 @@ int iscsi_create_default_params(struct iscsi_param_list **param_list_ptr)
 			TYPERANGE_UTF8, USE_INITIAL_ONLY);
 	if (!param)
 		goto out;
+
 	/*
 	 * Extra parameters for ISER from RFC-5046
 	 */
@@ -496,9 +497,9 @@ int iscsi_set_keys_to_negotiate(
 		} else if (!strcmp(param->name, SESSIONTYPE)) {
 			SET_PSTATE_NEGOTIATE(param);
 		} else if (!strcmp(param->name, IFMARKER)) {
-			SET_PSTATE_NEGOTIATE(param);
+			SET_PSTATE_REJECT(param);
 		} else if (!strcmp(param->name, OFMARKER)) {
-			SET_PSTATE_NEGOTIATE(param);
+			SET_PSTATE_REJECT(param);
 		} else if (!strcmp(param->name, IFMARKINT)) {
 			SET_PSTATE_REJECT(param);
 		} else if (!strcmp(param->name, OFMARKINT)) {
diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index 968068ffc..de26bee4b 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -460,7 +460,6 @@ static bool iscsit_tpg_check_network_portal(
 struct iscsi_tpg_np *iscsit_tpg_add_network_portal(
 	struct iscsi_portal_group *tpg,
 	struct __kernel_sockaddr_storage *sockaddr,
-	char *ip_str,
 	struct iscsi_tpg_np *tpg_np_parent,
 	int network_transport)
 {
@@ -470,8 +469,8 @@ struct iscsi_tpg_np *iscsit_tpg_add_network_portal(
 	if (!tpg_np_parent) {
 		if (iscsit_tpg_check_network_portal(tpg->tpg_tiqn, sockaddr,
 				network_transport)) {
-			pr_err("Network Portal: %s already exists on a"
-				" different TPG on %s\n", ip_str,
+			pr_err("Network Portal: %pISc already exists on a"
+				" different TPG on %s\n", sockaddr,
 				tpg->tpg_tiqn->tiqn);
 			return ERR_PTR(-EEXIST);
 		}
@@ -484,7 +483,7 @@ struct iscsi_tpg_np *iscsit_tpg_add_network_portal(
 		return ERR_PTR(-ENOMEM);
 	}
 
-	np = iscsit_add_np(sockaddr, ip_str, network_transport);
+	np = iscsit_add_np(sockaddr, network_transport);
 	if (IS_ERR(np)) {
 		kfree(tpg_np);
 		return ERR_CAST(np);
@@ -514,8 +513,8 @@ struct iscsi_tpg_np *iscsit_tpg_add_network_portal(
 		spin_unlock(&tpg_np_parent->tpg_np_parent_lock);
 	}
 
-	pr_debug("CORE[%s] - Added Network Portal: %s:%hu,%hu on %s\n",
-		tpg->tpg_tiqn->tiqn, np->np_ip, np->np_port, tpg->tpgt,
+	pr_debug("CORE[%s] - Added Network Portal: %pISc:%hu,%hu on %s\n",
+		tpg->tpg_tiqn->tiqn, &np->np_sockaddr, np->np_port, tpg->tpgt,
 		np->np_transport->name);
 
 	return tpg_np;
@@ -528,8 +527,8 @@ static int iscsit_tpg_release_np(
 {
 	iscsit_clear_tpg_np_login_thread(tpg_np, tpg, true);
 
-	pr_debug("CORE[%s] - Removed Network Portal: %s:%hu,%hu on %s\n",
-		tpg->tpg_tiqn->tiqn, np->np_ip, np->np_port, tpg->tpgt,
+	pr_debug("CORE[%s] - Removed Network Portal: %pISc:%hu,%hu on %s\n",
+		tpg->tpg_tiqn->tiqn, &np->np_sockaddr, np->np_port, tpg->tpgt,
 		np->np_transport->name);
 
 	tpg_np->tpg_np = NULL;
diff --git a/drivers/target/iscsi/iscsi_target_tpg.h b/drivers/target/iscsi/iscsi_target_tpg.h
index 95ff5bdec..28abda89e 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.h
+++ b/drivers/target/iscsi/iscsi_target_tpg.h
@@ -22,7 +22,7 @@ extern struct iscsi_node_attrib *iscsit_tpg_get_node_attrib(struct iscsi_session
 extern void iscsit_tpg_del_external_nps(struct iscsi_tpg_np *);
 extern struct iscsi_tpg_np *iscsit_tpg_locate_child_np(struct iscsi_tpg_np *, int);
 extern struct iscsi_tpg_np *iscsit_tpg_add_network_portal(struct iscsi_portal_group *,
-			struct __kernel_sockaddr_storage *, char *, struct iscsi_tpg_np *,
+			struct __kernel_sockaddr_storage *, struct iscsi_tpg_np *,
 			int);
 extern int iscsit_tpg_del_network_portal(struct iscsi_portal_group *,
 			struct iscsi_tpg_np *);
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 09e682b1c..8f1cd194f 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -427,8 +427,6 @@ void core_disable_device_list_for_node(
 
 	hlist_del_rcu(&orig->link);
 	clear_bit(DEF_PR_REG_ACTIVE, &orig->deve_flags);
-	rcu_assign_pointer(orig->se_lun, NULL);
-	rcu_assign_pointer(orig->se_lun_acl, NULL);
 	orig->lun_flags = 0;
 	orig->creation_time = 0;
 	orig->attach_count--;
@@ -439,6 +437,9 @@ void core_disable_device_list_for_node(
 	kref_put(&orig->pr_kref, target_pr_kref_release);
 	wait_for_completion(&orig->pr_comp);
 
+	rcu_assign_pointer(orig->se_lun, NULL);
+	rcu_assign_pointer(orig->se_lun_acl, NULL);
+
 	kfree_rcu(orig, rcu_head);
 
 	core_scsi3_free_pr_reg_from_nacl(dev, nacl);
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 5ab7100de..e79331150 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -618,7 +618,7 @@ static struct t10_pr_registration *__core_scsi3_do_alloc_registration(
 	struct se_device *dev,
 	struct se_node_acl *nacl,
 	struct se_lun *lun,
-	struct se_dev_entry *deve,
+	struct se_dev_entry *dest_deve,
 	u64 mapped_lun,
 	unsigned char *isid,
 	u64 sa_res_key,
@@ -640,7 +640,29 @@ static struct t10_pr_registration *__core_scsi3_do_alloc_registration(
 	INIT_LIST_HEAD(&pr_reg->pr_reg_atp_mem_list);
 	atomic_set(&pr_reg->pr_res_holders, 0);
 	pr_reg->pr_reg_nacl = nacl;
-	pr_reg->pr_reg_deve = deve;
+	/*
+	 * For destination registrations for ALL_TG_PT=1 and SPEC_I_PT=1,
+	 * the se_dev_entry->pr_ref will have been already obtained by
+	 * core_get_se_deve_from_rtpi() or __core_scsi3_alloc_registration().
+	 *
+	 * Otherwise, locate se_dev_entry now and obtain a reference until
+	 * registration completes in __core_scsi3_add_registration().
+	 */
+	if (dest_deve) {
+		pr_reg->pr_reg_deve = dest_deve;
+	} else {
+		rcu_read_lock();
+		pr_reg->pr_reg_deve = target_nacl_find_deve(nacl, mapped_lun);
+		if (!pr_reg->pr_reg_deve) {
+			rcu_read_unlock();
+			pr_err("Unable to locate PR deve %s mapped_lun: %llu\n",
+				nacl->initiatorname, mapped_lun);
+			kmem_cache_free(t10_pr_reg_cache, pr_reg);
+			return NULL;
+		}
+		kref_get(&pr_reg->pr_reg_deve->pr_kref);
+		rcu_read_unlock();
+	}
 	pr_reg->pr_res_mapped_lun = mapped_lun;
 	pr_reg->pr_aptpl_target_lun = lun->unpacked_lun;
 	pr_reg->tg_pt_sep_rtpi = lun->lun_rtpi;
@@ -936,17 +958,29 @@ static int __core_scsi3_check_aptpl_registration(
 		    !(strcmp(pr_reg->pr_tport, t_port)) &&
 		     (pr_reg->pr_reg_tpgt == tpgt) &&
 		     (pr_reg->pr_aptpl_target_lun == target_lun)) {
+			/*
+			 * Obtain the ->pr_reg_deve pointer + reference, that
+			 * is released by __core_scsi3_add_registration() below.
+			 */
+			rcu_read_lock();
+			pr_reg->pr_reg_deve = target_nacl_find_deve(nacl, mapped_lun);
+			if (!pr_reg->pr_reg_deve) {
+				pr_err("Unable to locate PR APTPL %s mapped_lun:"
+					" %llu\n", nacl->initiatorname, mapped_lun);
+				rcu_read_unlock();
+				continue;
+			}
+			kref_get(&pr_reg->pr_reg_deve->pr_kref);
+			rcu_read_unlock();
 
 			pr_reg->pr_reg_nacl = nacl;
 			pr_reg->tg_pt_sep_rtpi = lun->lun_rtpi;
-
 			list_del(&pr_reg->pr_reg_aptpl_list);
 			spin_unlock(&pr_tmpl->aptpl_reg_lock);
 			/*
 			 * At this point all of the pointers in *pr_reg will
 			 * be setup, so go ahead and add the registration.
 			 */
-
 			__core_scsi3_add_registration(dev, nacl, pr_reg, 0, 0);
 			/*
 			 * If this registration is the reservation holder,
@@ -1044,18 +1078,11 @@ static void __core_scsi3_add_registration(
 
 	__core_scsi3_dump_registration(tfo, dev, nacl, pr_reg, register_type);
 	spin_unlock(&pr_tmpl->registration_lock);
-
-	rcu_read_lock();
-	deve = pr_reg->pr_reg_deve;
-	if (deve)
-		set_bit(DEF_PR_REG_ACTIVE, &deve->deve_flags);
-	rcu_read_unlock();
-
 	/*
 	 * Skip extra processing for ALL_TG_PT=0 or REGISTER_AND_MOVE.
 	 */
 	if (!pr_reg->pr_reg_all_tg_pt || register_move)
-		return;
+		goto out;
 	/*
 	 * Walk pr_reg->pr_reg_atp_list and add registrations for ALL_TG_PT=1
 	 * allocated in __core_scsi3_alloc_registration()
@@ -1075,19 +1102,31 @@ static void __core_scsi3_add_registration(
 		__core_scsi3_dump_registration(tfo, dev, nacl_tmp, pr_reg_tmp,
 					       register_type);
 		spin_unlock(&pr_tmpl->registration_lock);
-
+		/*
+		 * Drop configfs group dependency reference and deve->pr_kref
+		 * obtained from  __core_scsi3_alloc_registration() code.
+		 */
 		rcu_read_lock();
 		deve = pr_reg_tmp->pr_reg_deve;
-		if (deve)
+		if (deve) {
 			set_bit(DEF_PR_REG_ACTIVE, &deve->deve_flags);
+			core_scsi3_lunacl_undepend_item(deve);
+			pr_reg_tmp->pr_reg_deve = NULL;
+		}
 		rcu_read_unlock();
-
-		/*
-		 * Drop configfs group dependency reference from
-		 * __core_scsi3_alloc_registration()
-		 */
-		core_scsi3_lunacl_undepend_item(pr_reg_tmp->pr_reg_deve);
 	}
+out:
+	/*
+	 * Drop deve->pr_kref obtained in __core_scsi3_do_alloc_registration()
+	 */
+	rcu_read_lock();
+	deve = pr_reg->pr_reg_deve;
+	if (deve) {
+		set_bit(DEF_PR_REG_ACTIVE, &deve->deve_flags);
+		kref_put(&deve->pr_kref, target_pr_kref_release);
+		pr_reg->pr_reg_deve = NULL;
+	}
+	rcu_read_unlock();
 }
 
 static int core_scsi3_alloc_registration(
@@ -1785,9 +1824,11 @@ core_scsi3_decode_spec_i_port(
 			dest_node_acl->initiatorname, i_buf, (dest_se_deve) ?
 			dest_se_deve->mapped_lun : 0);
 
-		if (!dest_se_deve)
+		if (!dest_se_deve) {
+			kref_put(&local_pr_reg->pr_reg_deve->pr_kref,
+				 target_pr_kref_release);
 			continue;
-
+		}
 		core_scsi3_lunacl_undepend_item(dest_se_deve);
 		core_scsi3_nodeacl_undepend_item(dest_node_acl);
 		core_scsi3_tpg_undepend_item(dest_tpg);
@@ -1823,9 +1864,11 @@ out:
 
 		kmem_cache_free(t10_pr_reg_cache, dest_pr_reg);
 
-		if (!dest_se_deve)
+		if (!dest_se_deve) {
+			kref_put(&local_pr_reg->pr_reg_deve->pr_kref,
+				 target_pr_kref_release);
 			continue;
-
+		}
 		core_scsi3_lunacl_undepend_item(dest_se_deve);
 		core_scsi3_nodeacl_undepend_item(dest_node_acl);
 		core_scsi3_tpg_undepend_item(dest_tpg);
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 4515f5254..47fe94ee1 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -450,6 +450,8 @@ int target_xcopy_setup_pt(void)
 	memset(&xcopy_pt_sess, 0, sizeof(struct se_session));
 	INIT_LIST_HEAD(&xcopy_pt_sess.sess_list);
 	INIT_LIST_HEAD(&xcopy_pt_sess.sess_acl_list);
+	INIT_LIST_HEAD(&xcopy_pt_sess.sess_cmd_list);
+	spin_lock_init(&xcopy_pt_sess.sess_cmd_lock);
 
 	xcopy_pt_nacl.se_tpg = &xcopy_pt_tpg;
 	xcopy_pt_nacl.nacl_sess = &xcopy_pt_sess;
@@ -644,7 +646,7 @@ static int target_xcopy_read_source(
 	pr_debug("XCOPY: Built READ_16: LBA: %llu Sectors: %u Length: %u\n",
 		(unsigned long long)src_lba, src_sectors, length);
 
-	transport_init_se_cmd(se_cmd, &xcopy_pt_tfo, NULL, length,
+	transport_init_se_cmd(se_cmd, &xcopy_pt_tfo, &xcopy_pt_sess, length,
 			      DMA_FROM_DEVICE, 0, &xpt_cmd->sense_buffer[0]);
 	xop->src_pt_cmd = xpt_cmd;
 
@@ -704,7 +706,7 @@ static int target_xcopy_write_destination(
 	pr_debug("XCOPY: Built WRITE_16: LBA: %llu Sectors: %u Length: %u\n",
 		(unsigned long long)dst_lba, dst_sectors, length);
 
-	transport_init_se_cmd(se_cmd, &xcopy_pt_tfo, NULL, length,
+	transport_init_se_cmd(se_cmd, &xcopy_pt_tfo, &xcopy_pt_sess, length,
 			      DMA_TO_DEVICE, 0, &xpt_cmd->sense_buffer[0]);
 	xop->dst_pt_cmd = xpt_cmd;
 
diff --git a/drivers/thermal/cpu_cooling.c b/drivers/thermal/cpu_cooling.c
index 620dcd405..42c6f71bd 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -262,7 +262,9 @@ static int cpufreq_thermal_notifier(struct notifier_block *nb,
  * efficiently.  Power is stored in mW, frequency in KHz.  The
  * resulting table is in ascending order.
  *
- * Return: 0 on success, -E* on error.
+ * Return: 0 on success, -EINVAL if there are no OPPs for any CPUs,
+ * -ENOMEM if we run out of memory or -EAGAIN if an OPP was
+ * added/enabled while the function was executing.
  */
 static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 				 u32 capacitance)
@@ -273,8 +275,6 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 	int num_opps = 0, cpu, i, ret = 0;
 	unsigned long freq;
 
-	rcu_read_lock();
-
 	for_each_cpu(cpu, &cpufreq_device->allowed_cpus) {
 		dev = get_cpu_device(cpu);
 		if (!dev) {
@@ -284,24 +284,20 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		}
 
 		num_opps = dev_pm_opp_get_opp_count(dev);
-		if (num_opps > 0) {
+		if (num_opps > 0)
 			break;
-		} else if (num_opps < 0) {
-			ret = num_opps;
-			goto unlock;
-		}
+		else if (num_opps < 0)
+			return num_opps;
 	}
 
-	if (num_opps == 0) {
-		ret = -EINVAL;
-		goto unlock;
-	}
+	if (num_opps == 0)
+		return -EINVAL;
 
 	power_table = kcalloc(num_opps, sizeof(*power_table), GFP_KERNEL);
-	if (!power_table) {
-		ret = -ENOMEM;
-		goto unlock;
-	}
+	if (!power_table)
+		return -ENOMEM;
+
+	rcu_read_lock();
 
 	for (freq = 0, i = 0;
 	     opp = dev_pm_opp_find_freq_ceil(dev, &freq), !IS_ERR(opp);
@@ -309,6 +305,12 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		u32 freq_mhz, voltage_mv;
 		u64 power;
 
+		if (i >= num_opps) {
+			rcu_read_unlock();
+			ret = -EAGAIN;
+			goto free_power_table;
+		}
+
 		freq_mhz = freq / 1000000;
 		voltage_mv = dev_pm_opp_get_voltage(opp) / 1000;
 
@@ -326,17 +328,22 @@ static int build_dyn_power_table(struct cpufreq_cooling_device *cpufreq_device,
 		power_table[i].power = power;
 	}
 
-	if (i == 0) {
+	rcu_read_unlock();
+
+	if (i != num_opps) {
 		ret = PTR_ERR(opp);
-		goto unlock;
+		goto free_power_table;
 	}
 
 	cpufreq_device->cpu_dev = dev;
 	cpufreq_device->dyn_power_table = power_table;
 	cpufreq_device->dyn_power_table_entries = i;
 
-unlock:
-	rcu_read_unlock();
+	return 0;
+
+free_power_table:
+	kfree(power_table);
+
 	return ret;
 }
 
@@ -847,7 +854,7 @@ __cpufreq_cooling_register(struct device_node *np,
 	ret = get_idr(&cpufreq_idr, &cpufreq_dev->id);
 	if (ret) {
 		cool_dev = ERR_PTR(ret);
-		goto free_table;
+		goto free_power_table;
 	}
 
 	snprintf(dev_name, sizeof(dev_name), "thermal-cpufreq-%d",
@@ -889,6 +896,8 @@ __cpufreq_cooling_register(struct device_node *np,
 
 remove_idr:
 	release_idr(&cpufreq_idr, cpufreq_dev->id);
+free_power_table:
+	kfree(cpufreq_dev->dyn_power_table);
 free_table:
 	kfree(cpufreq_dev->freq_table);
 free_time_in_idle_timestamp:
@@ -1039,6 +1048,7 @@ void cpufreq_cooling_unregister(struct thermal_cooling_device *cdev)
 
 	thermal_cooling_device_unregister(cpufreq_dev->cool_dev);
 	release_idr(&cpufreq_idr, cpufreq_dev->id);
+	kfree(cpufreq_dev->dyn_power_table);
 	kfree(cpufreq_dev->time_in_idle_timestamp);
 	kfree(cpufreq_dev->time_in_idle);
 	kfree(cpufreq_dev->freq_table);
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index ee8bfacf2..afc1879f6 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -343,8 +343,7 @@ static void n_tty_packet_mode_flush(struct tty_struct *tty)
 		spin_lock_irqsave(&tty->ctrl_lock, flags);
 		tty->ctrl_status |= TIOCPKT_FLUSHREAD;
 		spin_unlock_irqrestore(&tty->ctrl_lock, flags);
-		if (waitqueue_active(&tty->link->read_wait))
-			wake_up_interruptible(&tty->link->read_wait);
+		wake_up_interruptible(&tty->link->read_wait);
 	}
 }
 
@@ -1382,8 +1381,7 @@ handle_newline:
 			put_tty_queue(c, ldata);
 			smp_store_release(&ldata->canon_head, ldata->read_head);
 			kill_fasync(&tty->fasync, SIGIO, POLL_IN);
-			if (waitqueue_active(&tty->read_wait))
-				wake_up_interruptible_poll(&tty->read_wait, POLLIN);
+			wake_up_interruptible_poll(&tty->read_wait, POLLIN);
 			return 0;
 		}
 	}
@@ -1667,8 +1665,7 @@ static void __receive_buf(struct tty_struct *tty, const unsigned char *cp,
 
 	if ((read_cnt(ldata) >= ldata->minimum_to_wake) || L_EXTPROC(tty)) {
 		kill_fasync(&tty->fasync, SIGIO, POLL_IN);
-		if (waitqueue_active(&tty->read_wait))
-			wake_up_interruptible_poll(&tty->read_wait, POLLIN);
+		wake_up_interruptible_poll(&tty->read_wait, POLLIN);
 	}
 }
 
@@ -1887,10 +1884,8 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
 	}
 
 	/* The termios change make the tty ready for I/O */
-	if (waitqueue_active(&tty->write_wait))
-		wake_up_interruptible(&tty->write_wait);
-	if (waitqueue_active(&tty->read_wait))
-		wake_up_interruptible(&tty->read_wait);
+	wake_up_interruptible(&tty->write_wait);
+	wake_up_interruptible(&tty->read_wait);
 }
 
 /**
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index 2736eb262..a3a83164b 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -326,6 +326,14 @@ configured less than Maximum supported fifo bytes */
 				  UART_FCR7_64BYTE,
 		.flags		= UART_CAP_FIFO,
 	},
+	[PORT_RT2880] = {
+		.name		= "Palmchip BK-3103",
+		.fifo_size	= 16,
+		.tx_loadsz	= 16,
+		.fcr		= UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10,
+		.rxtrig_bytes	= {1, 4, 8, 14},
+		.flags		= UART_CAP_FIFO,
+	},
 };
 
 /* Uart divisor latch read */
diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
index 2a8f52815..40326b342 100644
--- a/drivers/tty/serial/atmel_serial.c
+++ b/drivers/tty/serial/atmel_serial.c
@@ -2641,7 +2641,7 @@ static int atmel_serial_probe(struct platform_device *pdev)
 	ret = atmel_init_gpios(port, &pdev->dev);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Failed to initialize GPIOs.");
-		goto err;
+		goto err_clear_bit;
 	}
 
 	ret = atmel_init_port(port, pdev);
diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c
index 57fc6ee12..774df354a 100644
--- a/drivers/tty/tty_io.c
+++ b/drivers/tty/tty_io.c
@@ -2136,8 +2136,24 @@ retry_open:
 	if (!noctty &&
 	    current->signal->leader &&
 	    !current->signal->tty &&
-	    tty->session == NULL)
-		__proc_set_tty(tty);
+	    tty->session == NULL) {
+		/*
+		 * Don't let a process that only has write access to the tty
+		 * obtain the privileges associated with having a tty as
+		 * controlling terminal (being able to reopen it with full
+		 * access through /dev/tty, being able to perform pushback).
+		 * Many distributions set the group of all ttys to "tty" and
+		 * grant write-only access to all terminals for setgid tty
+		 * binaries, which should not imply full privileges on all ttys.
+		 *
+		 * This could theoretically break old code that performs open()
+		 * on a write-only file descriptor. In that case, it might be
+		 * necessary to also permit this if
+		 * inode_permission(inode, MAY_READ) == 0.
+		 */
+		if (filp->f_mode & FMODE_READ)
+			__proc_set_tty(tty);
+	}
 	spin_unlock_irq(&current->sighand->siglock);
 	read_unlock(&tasklist_lock);
 	tty_unlock(tty);
@@ -2426,7 +2442,7 @@ static int fionbio(struct file *file, int __user *p)
  *		Takes ->siglock() when updating signal->tty
  */
 
-static int tiocsctty(struct tty_struct *tty, int arg)
+static int tiocsctty(struct tty_struct *tty, struct file *file, int arg)
 {
 	int ret = 0;
 
@@ -2460,6 +2476,13 @@ static int tiocsctty(struct tty_struct *tty, int arg)
 			goto unlock;
 		}
 	}
+
+	/* See the comment in tty_open(). */
+	if ((file->f_mode & FMODE_READ) == 0 && !capable(CAP_SYS_ADMIN)) {
+		ret = -EPERM;
+		goto unlock;
+	}
+
 	proc_set_tty(tty);
 unlock:
 	read_unlock(&tasklist_lock);
@@ -2852,7 +2875,7 @@ long tty_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 		no_tty();
 		return 0;
 	case TIOCSCTTY:
-		return tiocsctty(tty, arg);
+		return tiocsctty(tty, file, arg);
 	case TIOCGPGRP:
 		return tiocgpgrp(tty, real_tty, p);
 	case TIOCSPGRP:
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index 389f0e034..fa774323e 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -56,7 +56,7 @@ static const struct of_device_id ci_hdrc_imx_dt_ids[] = {
 	{ .compatible = "fsl,imx27-usb", .data = &imx27_usb_data},
 	{ .compatible = "fsl,imx6q-usb", .data = &imx6q_usb_data},
 	{ .compatible = "fsl,imx6sl-usb", .data = &imx6sl_usb_data},
-	{ .compatible = "fsl,imx6sx-usb", .data = &imx6sl_usb_data},
+	{ .compatible = "fsl,imx6sx-usb", .data = &imx6sx_usb_data},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, ci_hdrc_imx_dt_ids);
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 764f668d4..6e53c24fa 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -656,6 +656,44 @@ __acquires(hwep->lock)
 	return 0;
 }
 
+static int _ep_set_halt(struct usb_ep *ep, int value, bool check_transfer)
+{
+	struct ci_hw_ep *hwep = container_of(ep, struct ci_hw_ep, ep);
+	int direction, retval = 0;
+	unsigned long flags;
+
+	if (ep == NULL || hwep->ep.desc == NULL)
+		return -EINVAL;
+
+	if (usb_endpoint_xfer_isoc(hwep->ep.desc))
+		return -EOPNOTSUPP;
+
+	spin_lock_irqsave(hwep->lock, flags);
+
+	if (value && hwep->dir == TX && check_transfer &&
+		!list_empty(&hwep->qh.queue) &&
+			!usb_endpoint_xfer_control(hwep->ep.desc)) {
+		spin_unlock_irqrestore(hwep->lock, flags);
+		return -EAGAIN;
+	}
+
+	direction = hwep->dir;
+	do {
+		retval |= hw_ep_set_halt(hwep->ci, hwep->num, hwep->dir, value);
+
+		if (!value)
+			hwep->wedge = 0;
+
+		if (hwep->type == USB_ENDPOINT_XFER_CONTROL)
+			hwep->dir = (hwep->dir == TX) ? RX : TX;
+
+	} while (hwep->dir != direction);
+
+	spin_unlock_irqrestore(hwep->lock, flags);
+	return retval;
+}
+
+
 /**
  * _gadget_stop_activity: stops all USB activity, flushes & disables all endpts
  * @gadget: gadget
@@ -1051,7 +1089,7 @@ __acquires(ci->lock)
 				num += ci->hw_ep_max / 2;
 
 			spin_unlock(&ci->lock);
-			err = usb_ep_set_halt(&ci->ci_hw_ep[num].ep);
+			err = _ep_set_halt(&ci->ci_hw_ep[num].ep, 1, false);
 			spin_lock(&ci->lock);
 			if (!err)
 				isr_setup_status_phase(ci);
@@ -1110,8 +1148,8 @@ delegate:
 
 	if (err < 0) {
 		spin_unlock(&ci->lock);
-		if (usb_ep_set_halt(&hwep->ep))
-			dev_err(ci->dev, "error: ep_set_halt\n");
+		if (_ep_set_halt(&hwep->ep, 1, false))
+			dev_err(ci->dev, "error: _ep_set_halt\n");
 		spin_lock(&ci->lock);
 	}
 }
@@ -1142,9 +1180,9 @@ __acquires(ci->lock)
 					err = isr_setup_status_phase(ci);
 				if (err < 0) {
 					spin_unlock(&ci->lock);
-					if (usb_ep_set_halt(&hwep->ep))
+					if (_ep_set_halt(&hwep->ep, 1, false))
 						dev_err(ci->dev,
-							"error: ep_set_halt\n");
+						"error: _ep_set_halt\n");
 					spin_lock(&ci->lock);
 				}
 			}
@@ -1390,41 +1428,7 @@ static int ep_dequeue(struct usb_ep *ep, struct usb_request *req)
  */
 static int ep_set_halt(struct usb_ep *ep, int value)
 {
-	struct ci_hw_ep *hwep = container_of(ep, struct ci_hw_ep, ep);
-	int direction, retval = 0;
-	unsigned long flags;
-
-	if (ep == NULL || hwep->ep.desc == NULL)
-		return -EINVAL;
-
-	if (usb_endpoint_xfer_isoc(hwep->ep.desc))
-		return -EOPNOTSUPP;
-
-	spin_lock_irqsave(hwep->lock, flags);
-
-#ifndef STALL_IN
-	/* g_file_storage MS compliant but g_zero fails chapter 9 compliance */
-	if (value && hwep->type == USB_ENDPOINT_XFER_BULK && hwep->dir == TX &&
-	    !list_empty(&hwep->qh.queue)) {
-		spin_unlock_irqrestore(hwep->lock, flags);
-		return -EAGAIN;
-	}
-#endif
-
-	direction = hwep->dir;
-	do {
-		retval |= hw_ep_set_halt(hwep->ci, hwep->num, hwep->dir, value);
-
-		if (!value)
-			hwep->wedge = 0;
-
-		if (hwep->type == USB_ENDPOINT_XFER_CONTROL)
-			hwep->dir = (hwep->dir == TX) ? RX : TX;
-
-	} while (hwep->dir != direction);
-
-	spin_unlock_irqrestore(hwep->lock, flags);
-	return retval;
+	return _ep_set_halt(ep, value, true);
 }
 
 /**
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index b2a540b43..b9ddf0c1f 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -112,7 +112,7 @@ static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno,
 				cfgno, inum, asnum, ep->desc.bEndpointAddress);
 		ep->ss_ep_comp.bmAttributes = 16;
 	} else if (usb_endpoint_xfer_isoc(&ep->desc) &&
-			desc->bmAttributes > 2) {
+		   USB_SS_MULT(desc->bmAttributes) > 3) {
 		dev_warn(ddev, "Isoc endpoint has Mult of %d in "
 				"config %d interface %d altsetting %d ep %d: "
 				"setting to 3\n", desc->bmAttributes + 1,
@@ -121,7 +121,8 @@ static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno,
 	}
 
 	if (usb_endpoint_xfer_isoc(&ep->desc))
-		max_tx = (desc->bMaxBurst + 1) * (desc->bmAttributes + 1) *
+		max_tx = (desc->bMaxBurst + 1) *
+			(USB_SS_MULT(desc->bmAttributes)) *
 			usb_endpoint_maxp(&ep->desc);
 	else if (usb_endpoint_xfer_int(&ep->desc))
 		max_tx = usb_endpoint_maxp(&ep->desc) *
diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index d85abfed8..f5a381945 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -54,6 +54,13 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x046d, 0x082d), .driver_info = USB_QUIRK_DELAY_INIT },
 	{ USB_DEVICE(0x046d, 0x0843), .driver_info = USB_QUIRK_DELAY_INIT },
 
+	/* Logitech ConferenceCam CC3000e */
+	{ USB_DEVICE(0x046d, 0x0847), .driver_info = USB_QUIRK_DELAY_INIT },
+	{ USB_DEVICE(0x046d, 0x0848), .driver_info = USB_QUIRK_DELAY_INIT },
+
+	/* Logitech PTZ Pro Camera */
+	{ USB_DEVICE(0x046d, 0x0853), .driver_info = USB_QUIRK_DELAY_INIT },
+
 	/* Logitech Quickcam Fusion */
 	{ USB_DEVICE(0x046d, 0x08c1), .driver_info = USB_QUIRK_RESET_RESUME },
 
@@ -78,6 +85,12 @@ static const struct usb_device_id usb_quirk_list[] = {
 	/* Philips PSC805 audio device */
 	{ USB_DEVICE(0x0471, 0x0155), .driver_info = USB_QUIRK_RESET_RESUME },
 
+	/* Plantronic Audio 655 DSP */
+	{ USB_DEVICE(0x047f, 0xc008), .driver_info = USB_QUIRK_RESET_RESUME },
+
+	/* Plantronic Audio 648 USB */
+	{ USB_DEVICE(0x047f, 0xc013), .driver_info = USB_QUIRK_RESET_RESUME },
+
 	/* Artisman Watchdog Dongle */
 	{ USB_DEVICE(0x04b4, 0x0526), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 9a8c936cd..41f841fa6 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1498,10 +1498,10 @@ int xhci_endpoint_init(struct xhci_hcd *xhci,
 	 * use Event Data TRBs, and we don't chain in a link TRB on short
 	 * transfers, we're basically dividing by 1.
 	 *
-	 * xHCI 1.0 specification indicates that the Average TRB Length should
-	 * be set to 8 for control endpoints.
+	 * xHCI 1.0 and 1.1 specification indicates that the Average TRB Length
+	 * should be set to 8 for control endpoints.
 	 */
-	if (usb_endpoint_xfer_control(&ep->desc) && xhci->hci_version == 0x100)
+	if (usb_endpoint_xfer_control(&ep->desc) && xhci->hci_version >= 0x100)
 		ep_ctx->tx_info |= cpu_to_le32(AVG_TRB_LENGTH_FOR_EP(8));
 	else
 		ep_ctx->tx_info |=
@@ -1792,8 +1792,7 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 	int size;
 	int i, j, num_ports;
 
-	if (timer_pending(&xhci->cmd_timer))
-		del_timer_sync(&xhci->cmd_timer);
+	del_timer_sync(&xhci->cmd_timer);
 
 	/* Free the Event Ring Segment Table and the actual Event Ring */
 	size = sizeof(struct xhci_erst_entry)*(xhci->erst.num_entries);
@@ -2321,6 +2320,10 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 
 	INIT_LIST_HEAD(&xhci->cmd_list);
 
+	/* init command timeout timer */
+	setup_timer(&xhci->cmd_timer, xhci_handle_command_timeout,
+		    (unsigned long)xhci);
+
 	page_size = readl(&xhci->op_regs->page_size);
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 			"Supported page size register = 0x%x", page_size);
@@ -2505,10 +2508,6 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 			"Wrote ERST address to ir_set 0.");
 	xhci_print_ir_set(xhci, 0);
 
-	/* init command timeout timer */
-	setup_timer(&xhci->cmd_timer, xhci_handle_command_timeout,
-		    (unsigned long)xhci);
-
 	/*
 	 * XXX: Might need to set the Interrupter Moderation Register to
 	 * something other than the default (~1ms minimum between interrupts).
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 5590eac2b..c79d33676 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -180,51 +180,6 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 				"QUIRK: Resetting on resume");
 }
 
-/*
- * In some Intel xHCI controllers, in order to get D3 working,
- * through a vendor specific SSIC CONFIG register at offset 0x883c,
- * SSIC PORT need to be marked as "unused" before putting xHCI
- * into D3. After D3 exit, the SSIC port need to be marked as "used".
- * Without this change, xHCI might not enter D3 state.
- * Make sure PME works on some Intel xHCI controllers by writing 1 to clear
- * the Internal PME flag bit in vendor specific PMCTRL register at offset 0x80a4
- */
-static void xhci_pme_quirk(struct usb_hcd *hcd, bool suspend)
-{
-	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
-	struct pci_dev		*pdev = to_pci_dev(hcd->self.controller);
-	u32 val;
-	void __iomem *reg;
-
-	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
-		 pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI) {
-
-		reg = (void __iomem *) xhci->cap_regs + PORT2_SSIC_CONFIG_REG2;
-
-		/* Notify SSIC that SSIC profile programming is not done */
-		val = readl(reg) & ~PROG_DONE;
-		writel(val, reg);
-
-		/* Mark SSIC port as unused(suspend) or used(resume) */
-		val = readl(reg);
-		if (suspend)
-			val |= SSIC_PORT_UNUSED;
-		else
-			val &= ~SSIC_PORT_UNUSED;
-		writel(val, reg);
-
-		/* Notify SSIC that SSIC profile programming is done */
-		val = readl(reg) | PROG_DONE;
-		writel(val, reg);
-		readl(reg);
-	}
-
-	reg = (void __iomem *) xhci->cap_regs + 0x80a4;
-	val = readl(reg);
-	writel(val | BIT(28), reg);
-	readl(reg);
-}
-
 #ifdef CONFIG_ACPI
 static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev)
 {
@@ -345,6 +300,51 @@ static void xhci_pci_remove(struct pci_dev *dev)
 }
 
 #ifdef CONFIG_PM
+/*
+ * In some Intel xHCI controllers, in order to get D3 working,
+ * through a vendor specific SSIC CONFIG register at offset 0x883c,
+ * SSIC PORT need to be marked as "unused" before putting xHCI
+ * into D3. After D3 exit, the SSIC port need to be marked as "used".
+ * Without this change, xHCI might not enter D3 state.
+ * Make sure PME works on some Intel xHCI controllers by writing 1 to clear
+ * the Internal PME flag bit in vendor specific PMCTRL register at offset 0x80a4
+ */
+static void xhci_pme_quirk(struct usb_hcd *hcd, bool suspend)
+{
+	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
+	struct pci_dev		*pdev = to_pci_dev(hcd->self.controller);
+	u32 val;
+	void __iomem *reg;
+
+	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+		 pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI) {
+
+		reg = (void __iomem *) xhci->cap_regs + PORT2_SSIC_CONFIG_REG2;
+
+		/* Notify SSIC that SSIC profile programming is not done */
+		val = readl(reg) & ~PROG_DONE;
+		writel(val, reg);
+
+		/* Mark SSIC port as unused(suspend) or used(resume) */
+		val = readl(reg);
+		if (suspend)
+			val |= SSIC_PORT_UNUSED;
+		else
+			val &= ~SSIC_PORT_UNUSED;
+		writel(val, reg);
+
+		/* Notify SSIC that SSIC profile programming is done */
+		val = readl(reg) | PROG_DONE;
+		writel(val, reg);
+		readl(reg);
+	}
+
+	reg = (void __iomem *) xhci->cap_regs + 0x80a4;
+	val = readl(reg);
+	writel(val | BIT(28), reg);
+	readl(reg);
+}
+
 static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup)
 {
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index 32f4d5644..8aadf3def 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -302,6 +302,15 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci)
 	ret = xhci_handshake(&xhci->op_regs->cmd_ring,
 			CMD_RING_RUNNING, 0, 5 * 1000 * 1000);
 	if (ret < 0) {
+		/* we are about to kill xhci, give it one more chance */
+		xhci_write_64(xhci, temp_64 | CMD_RING_ABORT,
+			      &xhci->op_regs->cmd_ring);
+		udelay(1000);
+		ret = xhci_handshake(&xhci->op_regs->cmd_ring,
+				     CMD_RING_RUNNING, 0, 3 * 1000 * 1000);
+		if (ret == 0)
+			return 0;
+
 		xhci_err(xhci, "Stopped the command ring failed, "
 				"maybe the host is dead\n");
 		xhci->xhc_state |= XHCI_STATE_DYING;
@@ -3041,9 +3050,11 @@ static int queue_bulk_sg_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 	struct xhci_td *td;
 	struct scatterlist *sg;
 	int num_sgs;
-	int trb_buff_len, this_sg_len, running_total;
+	int trb_buff_len, this_sg_len, running_total, ret;
 	unsigned int total_packet_count;
+	bool zero_length_needed;
 	bool first_trb;
+	int last_trb_num;
 	u64 addr;
 	bool more_trbs_coming;
 
@@ -3059,13 +3070,27 @@ static int queue_bulk_sg_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 	total_packet_count = DIV_ROUND_UP(urb->transfer_buffer_length,
 			usb_endpoint_maxp(&urb->ep->desc));
 
-	trb_buff_len = prepare_transfer(xhci, xhci->devs[slot_id],
+	ret = prepare_transfer(xhci, xhci->devs[slot_id],
 			ep_index, urb->stream_id,
 			num_trbs, urb, 0, mem_flags);
-	if (trb_buff_len < 0)
-		return trb_buff_len;
+	if (ret < 0)
+		return ret;
 
 	urb_priv = urb->hcpriv;
+
+	/* Deal with URB_ZERO_PACKET - need one more td/trb */
+	zero_length_needed = urb->transfer_flags & URB_ZERO_PACKET &&
+		urb_priv->length == 2;
+	if (zero_length_needed) {
+		num_trbs++;
+		xhci_dbg(xhci, "Creating zero length td.\n");
+		ret = prepare_transfer(xhci, xhci->devs[slot_id],
+				ep_index, urb->stream_id,
+				1, urb, 1, mem_flags);
+		if (ret < 0)
+			return ret;
+	}
+
 	td = urb_priv->td[0];
 
 	/*
@@ -3095,6 +3120,7 @@ static int queue_bulk_sg_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		trb_buff_len = urb->transfer_buffer_length;
 
 	first_trb = true;
+	last_trb_num = zero_length_needed ? 2 : 1;
 	/* Queue the first TRB, even if it's zero-length */
 	do {
 		u32 field = 0;
@@ -3112,12 +3138,15 @@ static int queue_bulk_sg_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		/* Chain all the TRBs together; clear the chain bit in the last
 		 * TRB to indicate it's the last TRB in the chain.
 		 */
-		if (num_trbs > 1) {
+		if (num_trbs > last_trb_num) {
 			field |= TRB_CHAIN;
-		} else {
-			/* FIXME - add check for ZERO_PACKET flag before this */
+		} else if (num_trbs == last_trb_num) {
 			td->last_trb = ep_ring->enqueue;
 			field |= TRB_IOC;
+		} else if (zero_length_needed && num_trbs == 1) {
+			trb_buff_len = 0;
+			urb_priv->td[1]->last_trb = ep_ring->enqueue;
+			field |= TRB_IOC;
 		}
 
 		/* Only set interrupt on short packet for IN endpoints */
@@ -3179,7 +3208,7 @@ static int queue_bulk_sg_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		if (running_total + trb_buff_len > urb->transfer_buffer_length)
 			trb_buff_len =
 				urb->transfer_buffer_length - running_total;
-	} while (running_total < urb->transfer_buffer_length);
+	} while (num_trbs > 0);
 
 	check_trb_math(urb, num_trbs, running_total);
 	giveback_first_trb(xhci, slot_id, ep_index, urb->stream_id,
@@ -3197,7 +3226,9 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 	int num_trbs;
 	struct xhci_generic_trb *start_trb;
 	bool first_trb;
+	int last_trb_num;
 	bool more_trbs_coming;
+	bool zero_length_needed;
 	int start_cycle;
 	u32 field, length_field;
 
@@ -3228,7 +3259,6 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		num_trbs++;
 		running_total += TRB_MAX_BUFF_SIZE;
 	}
-	/* FIXME: this doesn't deal with URB_ZERO_PACKET - need one more */
 
 	ret = prepare_transfer(xhci, xhci->devs[slot_id],
 			ep_index, urb->stream_id,
@@ -3237,6 +3267,20 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		return ret;
 
 	urb_priv = urb->hcpriv;
+
+	/* Deal with URB_ZERO_PACKET - need one more td/trb */
+	zero_length_needed = urb->transfer_flags & URB_ZERO_PACKET &&
+		urb_priv->length == 2;
+	if (zero_length_needed) {
+		num_trbs++;
+		xhci_dbg(xhci, "Creating zero length td.\n");
+		ret = prepare_transfer(xhci, xhci->devs[slot_id],
+				ep_index, urb->stream_id,
+				1, urb, 1, mem_flags);
+		if (ret < 0)
+			return ret;
+	}
+
 	td = urb_priv->td[0];
 
 	/*
@@ -3258,7 +3302,7 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		trb_buff_len = urb->transfer_buffer_length;
 
 	first_trb = true;
-
+	last_trb_num = zero_length_needed ? 2 : 1;
 	/* Queue the first TRB, even if it's zero-length */
 	do {
 		u32 remainder = 0;
@@ -3275,12 +3319,15 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		/* Chain all the TRBs together; clear the chain bit in the last
 		 * TRB to indicate it's the last TRB in the chain.
 		 */
-		if (num_trbs > 1) {
+		if (num_trbs > last_trb_num) {
 			field |= TRB_CHAIN;
-		} else {
-			/* FIXME - add check for ZERO_PACKET flag before this */
+		} else if (num_trbs == last_trb_num) {
 			td->last_trb = ep_ring->enqueue;
 			field |= TRB_IOC;
+		} else if (zero_length_needed && num_trbs == 1) {
+			trb_buff_len = 0;
+			urb_priv->td[1]->last_trb = ep_ring->enqueue;
+			field |= TRB_IOC;
 		}
 
 		/* Only set interrupt on short packet for IN endpoints */
@@ -3318,7 +3365,7 @@ int xhci_queue_bulk_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 		trb_buff_len = urb->transfer_buffer_length - running_total;
 		if (trb_buff_len > TRB_MAX_BUFF_SIZE)
 			trb_buff_len = TRB_MAX_BUFF_SIZE;
-	} while (running_total < urb->transfer_buffer_length);
+	} while (num_trbs > 0);
 
 	check_trb_math(urb, num_trbs, running_total);
 	giveback_first_trb(xhci, slot_id, ep_index, urb->stream_id,
@@ -3385,8 +3432,8 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 	if (start_cycle == 0)
 		field |= 0x1;
 
-	/* xHCI 1.0 6.4.1.2.1: Transfer Type field */
-	if (xhci->hci_version == 0x100) {
+	/* xHCI 1.0/1.1 6.4.1.2.1: Transfer Type field */
+	if (xhci->hci_version >= 0x100) {
 		if (urb->transfer_buffer_length > 0) {
 			if (setup->bRequestType & USB_DIR_IN)
 				field |= TRB_TX_TYPE(TRB_DATA_IN);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 526ebc0c7..d7b9f484d 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -146,7 +146,8 @@ static int xhci_start(struct xhci_hcd *xhci)
 				"waited %u microseconds.\n",
 				XHCI_MAX_HALT_USEC);
 	if (!ret)
-		xhci->xhc_state &= ~XHCI_STATE_HALTED;
+		xhci->xhc_state &= ~(XHCI_STATE_HALTED | XHCI_STATE_DYING);
+
 	return ret;
 }
 
@@ -654,15 +655,6 @@ int xhci_run(struct usb_hcd *hcd)
 }
 EXPORT_SYMBOL_GPL(xhci_run);
 
-static void xhci_only_stop_hcd(struct usb_hcd *hcd)
-{
-	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
-
-	spin_lock_irq(&xhci->lock);
-	xhci_halt(xhci);
-	spin_unlock_irq(&xhci->lock);
-}
-
 /*
  * Stop xHCI driver.
  *
@@ -677,12 +669,14 @@ void xhci_stop(struct usb_hcd *hcd)
 	u32 temp;
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
 
-	if (!usb_hcd_is_primary_hcd(hcd)) {
-		xhci_only_stop_hcd(xhci->shared_hcd);
+	if (xhci->xhc_state & XHCI_STATE_HALTED)
 		return;
-	}
 
+	mutex_lock(&xhci->mutex);
 	spin_lock_irq(&xhci->lock);
+	xhci->xhc_state |= XHCI_STATE_HALTED;
+	xhci->cmd_ring_state = CMD_RING_STATE_STOPPED;
+
 	/* Make sure the xHC is halted for a USB3 roothub
 	 * (xhci_stop() could be called as part of failed init).
 	 */
@@ -717,6 +711,7 @@ void xhci_stop(struct usb_hcd *hcd)
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 			"xhci_stop completed - status = %x",
 			readl(&xhci->op_regs->status));
+	mutex_unlock(&xhci->mutex);
 }
 
 /*
@@ -1340,6 +1335,11 @@ int xhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flags)
 
 	if (usb_endpoint_xfer_isoc(&urb->ep->desc))
 		size = urb->number_of_packets;
+	else if (usb_endpoint_is_bulk_out(&urb->ep->desc) &&
+	    urb->transfer_buffer_length > 0 &&
+	    urb->transfer_flags & URB_ZERO_PACKET &&
+	    !(urb->transfer_buffer_length % usb_endpoint_maxp(&urb->ep->desc)))
+		size = 2;
 	else
 		size = 1;
 
@@ -3788,6 +3788,9 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
 
 	mutex_lock(&xhci->mutex);
 
+	if (xhci->xhc_state)	/* dying or halted */
+		goto out;
+
 	if (!udev->slot_id) {
 		xhci_dbg_trace(xhci, trace_xhci_dbg_address,
 				"Bad Slot ID %d", udev->slot_id);
diff --git a/drivers/usb/misc/chaoskey.c b/drivers/usb/misc/chaoskey.c
index 3ad5d19e4..23c794813 100644
--- a/drivers/usb/misc/chaoskey.c
+++ b/drivers/usb/misc/chaoskey.c
@@ -472,7 +472,7 @@ static int chaoskey_rng_read(struct hwrng *rng, void *data,
 	if (this_time > max)
 		this_time = max;
 
-	memcpy(data, dev->buf, this_time);
+	memcpy(data, dev->buf + dev->used, this_time);
 
 	dev->used += this_time;
 
diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c
index 4d1b44c23..d07cafb7d 100644
--- a/drivers/usb/musb/musb_cppi41.c
+++ b/drivers/usb/musb/musb_cppi41.c
@@ -614,7 +614,7 @@ static int cppi41_dma_controller_start(struct cppi41_dma_controller *controller)
 {
 	struct musb *musb = controller->musb;
 	struct device *dev = musb->controller;
-	struct device_node *np = dev->of_node;
+	struct device_node *np = dev->parent->of_node;
 	struct cppi41_dma_channel *cppi41_channel;
 	int count;
 	int i;
@@ -664,7 +664,7 @@ static int cppi41_dma_controller_start(struct cppi41_dma_controller *controller)
 		musb_dma->status = MUSB_DMA_STATUS_FREE;
 		musb_dma->max_len = SZ_4M;
 
-		dc = dma_request_slave_channel(dev, str);
+		dc = dma_request_slave_channel(dev->parent, str);
 		if (!dc) {
 			dev_err(dev, "Failed to request %s.\n", str);
 			ret = -EPROBE_DEFER;
@@ -695,7 +695,7 @@ cppi41_dma_controller_create(struct musb *musb, void __iomem *base)
 	struct cppi41_dma_controller *controller;
 	int ret = 0;
 
-	if (!musb->controller->of_node) {
+	if (!musb->controller->parent->of_node) {
 		dev_err(musb->controller, "Need DT for the DMA engine.\n");
 		return NULL;
 	}
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index 1334a3de3..67325ec94 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -225,8 +225,11 @@ static void dsps_musb_enable(struct musb *musb)
 
 	dsps_writel(reg_base, wrp->epintr_set, epmask);
 	dsps_writel(reg_base, wrp->coreintr_set, coremask);
-	/* start polling for ID change. */
-	mod_timer(&glue->timer, jiffies + msecs_to_jiffies(wrp->poll_timeout));
+	/* start polling for ID change in dual-role idle mode */
+	if (musb->xceiv->otg->state == OTG_STATE_B_IDLE &&
+			musb->port_mode == MUSB_PORT_MODE_DUAL_ROLE)
+		mod_timer(&glue->timer, jiffies +
+				msecs_to_jiffies(wrp->poll_timeout));
 	dsps_musb_try_idle(musb, 0);
 }
 
diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c
index deee68eaf..0cd85f2cc 100644
--- a/drivers/usb/phy/phy-generic.c
+++ b/drivers/usb/phy/phy-generic.c
@@ -230,7 +230,8 @@ int usb_phy_gen_create_phy(struct device *dev, struct usb_phy_generic *nop,
 		clk_rate = pdata->clk_rate;
 		needs_vcc = pdata->needs_vcc;
 		if (gpio_is_valid(pdata->gpio_reset)) {
-			err = devm_gpio_request_one(dev, pdata->gpio_reset, 0,
+			err = devm_gpio_request_one(dev, pdata->gpio_reset,
+						    GPIOF_ACTIVE_LOW,
 						    dev_name(dev));
 			if (!err)
 				nop->gpiod_reset =
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 876423b88..7c8eb4c4c 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -278,6 +278,10 @@ static void option_instat_callback(struct urb *urb);
 #define ZTE_PRODUCT_MF622			0x0001
 #define ZTE_PRODUCT_MF628			0x0015
 #define ZTE_PRODUCT_MF626			0x0031
+#define ZTE_PRODUCT_ZM8620_X			0x0396
+#define ZTE_PRODUCT_ME3620_MBIM			0x0426
+#define ZTE_PRODUCT_ME3620_X			0x1432
+#define ZTE_PRODUCT_ME3620_L			0x1433
 #define ZTE_PRODUCT_AC2726			0xfff1
 #define ZTE_PRODUCT_MG880			0xfffd
 #define ZTE_PRODUCT_CDMA_TECH			0xfffe
@@ -544,6 +548,18 @@ static const struct option_blacklist_info zte_mc2716_z_blacklist = {
 	.sendsetup = BIT(1) | BIT(2) | BIT(3),
 };
 
+static const struct option_blacklist_info zte_me3620_mbim_blacklist = {
+	.reserved = BIT(2) | BIT(3) | BIT(4),
+};
+
+static const struct option_blacklist_info zte_me3620_xl_blacklist = {
+	.reserved = BIT(3) | BIT(4) | BIT(5),
+};
+
+static const struct option_blacklist_info zte_zm8620_x_blacklist = {
+	.reserved = BIT(3) | BIT(4) | BIT(5),
+};
+
 static const struct option_blacklist_info huawei_cdc12_blacklist = {
 	.reserved = BIT(1) | BIT(2),
 };
@@ -1591,6 +1607,14 @@ static const struct usb_device_id option_ids[] = {
 	 .driver_info = (kernel_ulong_t)&zte_ad3812_z_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2716, 0xff, 0xff, 0xff),
 	 .driver_info = (kernel_ulong_t)&zte_mc2716_z_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ME3620_L),
+	 .driver_info = (kernel_ulong_t)&zte_me3620_xl_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ME3620_MBIM),
+	 .driver_info = (kernel_ulong_t)&zte_me3620_mbim_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ME3620_X),
+	 .driver_info = (kernel_ulong_t)&zte_me3620_xl_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ZM8620_X),
+	 .driver_info = (kernel_ulong_t)&zte_zm8620_x_blacklist },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x01) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x05) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x86, 0x10) },
diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c
index b93131d8c..59cb91b2e 100644
--- a/drivers/usb/serial/whiteheat.c
+++ b/drivers/usb/serial/whiteheat.c
@@ -80,6 +80,8 @@ static int  whiteheat_firmware_download(struct usb_serial *serial,
 static int  whiteheat_firmware_attach(struct usb_serial *serial);
 
 /* function prototypes for the Connect Tech WhiteHEAT serial converter */
+static int whiteheat_probe(struct usb_serial *serial,
+				const struct usb_device_id *id);
 static int  whiteheat_attach(struct usb_serial *serial);
 static void whiteheat_release(struct usb_serial *serial);
 static int  whiteheat_port_probe(struct usb_serial_port *port);
@@ -116,6 +118,7 @@ static struct usb_serial_driver whiteheat_device = {
 	.description =		"Connect Tech - WhiteHEAT",
 	.id_table =		id_table_std,
 	.num_ports =		4,
+	.probe =		whiteheat_probe,
 	.attach =		whiteheat_attach,
 	.release =		whiteheat_release,
 	.port_probe =		whiteheat_port_probe,
@@ -217,6 +220,34 @@ static int whiteheat_firmware_attach(struct usb_serial *serial)
 /*****************************************************************************
  * Connect Tech's White Heat serial driver functions
  *****************************************************************************/
+
+static int whiteheat_probe(struct usb_serial *serial,
+				const struct usb_device_id *id)
+{
+	struct usb_host_interface *iface_desc;
+	struct usb_endpoint_descriptor *endpoint;
+	size_t num_bulk_in = 0;
+	size_t num_bulk_out = 0;
+	size_t min_num_bulk;
+	unsigned int i;
+
+	iface_desc = serial->interface->cur_altsetting;
+
+	for (i = 0; i < iface_desc->desc.bNumEndpoints; i++) {
+		endpoint = &iface_desc->endpoint[i].desc;
+		if (usb_endpoint_is_bulk_in(endpoint))
+			++num_bulk_in;
+		if (usb_endpoint_is_bulk_out(endpoint))
+			++num_bulk_out;
+	}
+
+	min_num_bulk = COMMAND_PORT + 1;
+	if (num_bulk_in < min_num_bulk || num_bulk_out < min_num_bulk)
+		return -ENODEV;
+
+	return 0;
+}
+
 static int whiteheat_attach(struct usb_serial *serial)
 {
 	struct usb_serial_port *command_port;
diff --git a/drivers/watchdog/imgpdc_wdt.c b/drivers/watchdog/imgpdc_wdt.c
index 0f7362182..15ab07230 100644
--- a/drivers/watchdog/imgpdc_wdt.c
+++ b/drivers/watchdog/imgpdc_wdt.c
@@ -316,6 +316,7 @@ static int pdc_wdt_remove(struct platform_device *pdev)
 {
 	struct pdc_wdt_dev *pdc_wdt = platform_get_drvdata(pdev);
 
+	unregister_restart_handler(&pdc_wdt->restart_handler);
 	pdc_wdt_stop(&pdc_wdt->wdt_dev);
 	watchdog_unregister_device(&pdc_wdt->wdt_dev);
 	clk_disable_unprepare(pdc_wdt->wdt_clk);
diff --git a/drivers/watchdog/sunxi_wdt.c b/drivers/watchdog/sunxi_wdt.c
index a29afb37c..47bd8a14d 100644
--- a/drivers/watchdog/sunxi_wdt.c
+++ b/drivers/watchdog/sunxi_wdt.c
@@ -184,7 +184,7 @@ static int sunxi_wdt_start(struct watchdog_device *wdt_dev)
 	/* Set system reset function */
 	reg = readl(wdt_base + regs->wdt_cfg);
 	reg &= ~(regs->wdt_reset_mask);
-	reg |= ~(regs->wdt_reset_val);
+	reg |= regs->wdt_reset_val;
 	writel(reg, wdt_base + regs->wdt_cfg);
 
 	/* Enable watchdog */
diff --git a/drivers/xen/preempt.c b/drivers/xen/preempt.c
index a1800c150..08cb419eb 100644
--- a/drivers/xen/preempt.c
+++ b/drivers/xen/preempt.c
@@ -31,7 +31,7 @@ EXPORT_SYMBOL_GPL(xen_in_preemptible_hcall);
 asmlinkage __visible void xen_maybe_preempt_hcall(void)
 {
 	if (unlikely(__this_cpu_read(xen_in_preemptible_hcall)
-		     && should_resched())) {
+		     && need_resched())) {
 		/*
 		 * Clear flag as we may be rescheduled on a different
 		 * cpu.
diff --git a/fs/aufs/dentry.c b/fs/aufs/dentry.c
index 993c95e14..d03087c84 100644
--- a/fs/aufs/dentry.c
+++ b/fs/aufs/dentry.c
@@ -179,7 +179,7 @@ int au_lkup_dentry(struct dentry *dentry, aufs_bindex_t bstart, mode_t type)
 		if (dirperm1)
 			au_fset_lkup(args.flags, IGNORE_PERM);
 
-		if (au_dbwh(dentry) >= 0)
+		if (au_dbwh(dentry) == bindex)
 			break;
 		if (!h_dentry)
 			continue;
diff --git a/fs/aufs/i_op.c b/fs/aufs/i_op.c
index a50cd4c59..9c60a9eed 100644
--- a/fs/aufs/i_op.c
+++ b/fs/aufs/i_op.c
@@ -8,7 +8,6 @@
 
 #include <linux/device_cgroup.h>
 #include <linux/fs_stack.h>
-#include <linux/mm.h>
 #include <linux/namei.h>
 #include <linux/security.h>
 #include "aufs.h"
diff --git a/fs/aufs/i_op_ren.c b/fs/aufs/i_op_ren.c
index 132301251..652e973ce 100644
--- a/fs/aufs/i_op_ren.c
+++ b/fs/aufs/i_op_ren.c
@@ -77,7 +77,7 @@ struct au_ren_args {
 /*
  * functions for reverting.
  * when an error happened in a single rename systemcall, we should revert
- * everything as if nothing happend.
+ * everything as if nothing happened.
  * we don't need to revert the copied-up/down the parent dir since they are
  * harmless.
  */
@@ -859,7 +859,7 @@ int aufs_rename(struct inode *_src_dir, struct dentry *_src_dentry,
 
 	/*
 	 * is it possible?
-	 * yes, it happend (in linux-3.3-rcN) but I don't know why.
+	 * yes, it happened (in linux-3.3-rcN) but I don't know why.
 	 * there may exist a problem somewhere else.
 	 */
 	err = -EINVAL;
diff --git a/fs/aufs/vdir.c b/fs/aufs/vdir.c
index c3f6a74a1..db81f49dd 100644
--- a/fs/aufs/vdir.c
+++ b/fs/aufs/vdir.c
@@ -40,7 +40,7 @@ static unsigned char *last_deblk(struct au_vdir *vdir)
 
 /* ---------------------------------------------------------------------- */
 
-/* estimate the apropriate size for name hash table */
+/* estimate the appropriate size for name hash table */
 unsigned int au_rdhash_est(loff_t sz)
 {
 	unsigned int n;
@@ -366,7 +366,7 @@ static struct au_vdir *alloc_vdir(struct file *file)
 
 	vdir->vd_deblk_sz = au_sbi(sb)->si_rdblk;
 	if (!vdir->vd_deblk_sz) {
-		/* estimate the apropriate size for deblk */
+		/* estimate the appropriate size for deblk */
 		vdir->vd_deblk_sz = au_dir_size(file, /*dentry*/NULL);
 		/* pr_info("vd_deblk_sz %u\n", vdir->vd_deblk_sz); */
 	}
diff --git a/fs/aufs/vfsub.h b/fs/aufs/vfsub.h
index 778ea2053..541b7b160 100644
--- a/fs/aufs/vfsub.h
+++ b/fs/aufs/vfsub.h
@@ -183,6 +183,7 @@ static inline void vfsub_file_accessed(struct file *h_file)
 }
 #endif
 
+#if 0 /* reserved */
 static inline void vfsub_touch_atime(struct vfsmount *h_mnt,
 				     struct dentry *h_dentry)
 {
@@ -193,6 +194,7 @@ static inline void vfsub_touch_atime(struct vfsmount *h_mnt,
 	touch_atime(&h_path);
 	vfsub_update_h_iattr(&h_path, /*did*/NULL); /*ignore*/
 }
+#endif
 
 static inline int vfsub_update_time(struct inode *h_inode, struct timespec *ts,
 				    int flags)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 198243717..1170f8ce5 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1241,6 +1241,13 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 				goto out_clear;
 			}
 			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
+			/*
+			 * If the partition is not aligned on a page
+			 * boundary, we can't do dax I/O to it.
+			 */
+			if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) ||
+			    (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
+				bdev->bd_inode->i_flags &= ~S_DAX;
 		}
 	} else {
 		if (bdev->bd_contains == bdev) {
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 02d05817c..3fc4fec9b 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2798,7 +2798,8 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 			      bio_end_io_t end_io_func,
 			      int mirror_num,
 			      unsigned long prev_bio_flags,
-			      unsigned long bio_flags)
+			      unsigned long bio_flags,
+			      bool force_bio_submit)
 {
 	int ret = 0;
 	struct bio *bio;
@@ -2816,6 +2817,7 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree,
 			contig = bio_end_sector(bio) == sector;
 
 		if (prev_bio_flags != bio_flags || !contig ||
+		    force_bio_submit ||
 		    merge_bio(rw, tree, page, offset, page_size, bio, bio_flags) ||
 		    bio_add_page(bio, page, page_size, offset) < page_size) {
 			ret = submit_one_bio(rw, bio, mirror_num,
@@ -2909,7 +2911,8 @@ static int __do_readpage(struct extent_io_tree *tree,
 			 get_extent_t *get_extent,
 			 struct extent_map **em_cached,
 			 struct bio **bio, int mirror_num,
-			 unsigned long *bio_flags, int rw)
+			 unsigned long *bio_flags, int rw,
+			 u64 *prev_em_start)
 {
 	struct inode *inode = page->mapping->host;
 	u64 start = page_offset(page);
@@ -2957,6 +2960,7 @@ static int __do_readpage(struct extent_io_tree *tree,
 	}
 	while (cur <= end) {
 		unsigned long pnr = (last_byte >> PAGE_CACHE_SHIFT) + 1;
+		bool force_bio_submit = false;
 
 		if (cur >= last_byte) {
 			char *userpage;
@@ -3007,6 +3011,49 @@ static int __do_readpage(struct extent_io_tree *tree,
 		block_start = em->block_start;
 		if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
 			block_start = EXTENT_MAP_HOLE;
+
+		/*
+		 * If we have a file range that points to a compressed extent
+		 * and it's followed by a consecutive file range that points to
+		 * to the same compressed extent (possibly with a different
+		 * offset and/or length, so it either points to the whole extent
+		 * or only part of it), we must make sure we do not submit a
+		 * single bio to populate the pages for the 2 ranges because
+		 * this makes the compressed extent read zero out the pages
+		 * belonging to the 2nd range. Imagine the following scenario:
+		 *
+		 *  File layout
+		 *  [0 - 8K]                     [8K - 24K]
+		 *    |                               |
+		 *    |                               |
+		 * points to extent X,         points to extent X,
+		 * offset 4K, length of 8K     offset 0, length 16K
+		 *
+		 * [extent X, compressed length = 4K uncompressed length = 16K]
+		 *
+		 * If the bio to read the compressed extent covers both ranges,
+		 * it will decompress extent X into the pages belonging to the
+		 * first range and then it will stop, zeroing out the remaining
+		 * pages that belong to the other range that points to extent X.
+		 * So here we make sure we submit 2 bios, one for the first
+		 * range and another one for the third range. Both will target
+		 * the same physical extent from disk, but we can't currently
+		 * make the compressed bio endio callback populate the pages
+		 * for both ranges because each compressed bio is tightly
+		 * coupled with a single extent map, and each range can have
+		 * an extent map with a different offset value relative to the
+		 * uncompressed data of our extent and different lengths. This
+		 * is a corner case so we prioritize correctness over
+		 * non-optimal behavior (submitting 2 bios for the same extent).
+		 */
+		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) &&
+		    prev_em_start && *prev_em_start != (u64)-1 &&
+		    *prev_em_start != em->orig_start)
+			force_bio_submit = true;
+
+		if (prev_em_start)
+			*prev_em_start = em->orig_start;
+
 		free_extent_map(em);
 		em = NULL;
 
@@ -3056,7 +3103,8 @@ static int __do_readpage(struct extent_io_tree *tree,
 					 bdev, bio, pnr,
 					 end_bio_extent_readpage, mirror_num,
 					 *bio_flags,
-					 this_bio_flag);
+					 this_bio_flag,
+					 force_bio_submit);
 		if (!ret) {
 			nr++;
 			*bio_flags = this_bio_flag;
@@ -3083,7 +3131,8 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 					     get_extent_t *get_extent,
 					     struct extent_map **em_cached,
 					     struct bio **bio, int mirror_num,
-					     unsigned long *bio_flags, int rw)
+					     unsigned long *bio_flags, int rw,
+					     u64 *prev_em_start)
 {
 	struct inode *inode;
 	struct btrfs_ordered_extent *ordered;
@@ -3103,7 +3152,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 
 	for (index = 0; index < nr_pages; index++) {
 		__do_readpage(tree, pages[index], get_extent, em_cached, bio,
-			      mirror_num, bio_flags, rw);
+			      mirror_num, bio_flags, rw, prev_em_start);
 		page_cache_release(pages[index]);
 	}
 }
@@ -3113,7 +3162,8 @@ static void __extent_readpages(struct extent_io_tree *tree,
 			       int nr_pages, get_extent_t *get_extent,
 			       struct extent_map **em_cached,
 			       struct bio **bio, int mirror_num,
-			       unsigned long *bio_flags, int rw)
+			       unsigned long *bio_flags, int rw,
+			       u64 *prev_em_start)
 {
 	u64 start = 0;
 	u64 end = 0;
@@ -3134,7 +3184,7 @@ static void __extent_readpages(struct extent_io_tree *tree,
 						  index - first_index, start,
 						  end, get_extent, em_cached,
 						  bio, mirror_num, bio_flags,
-						  rw);
+						  rw, prev_em_start);
 			start = page_start;
 			end = start + PAGE_CACHE_SIZE - 1;
 			first_index = index;
@@ -3145,7 +3195,8 @@ static void __extent_readpages(struct extent_io_tree *tree,
 		__do_contiguous_readpages(tree, &pages[first_index],
 					  index - first_index, start,
 					  end, get_extent, em_cached, bio,
-					  mirror_num, bio_flags, rw);
+					  mirror_num, bio_flags, rw,
+					  prev_em_start);
 }
 
 static int __extent_read_full_page(struct extent_io_tree *tree,
@@ -3171,7 +3222,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 	}
 
 	ret = __do_readpage(tree, page, get_extent, NULL, bio, mirror_num,
-			    bio_flags, rw);
+			    bio_flags, rw, NULL);
 	return ret;
 }
 
@@ -3197,7 +3248,7 @@ int extent_read_full_page_nolock(struct extent_io_tree *tree, struct page *page,
 	int ret;
 
 	ret = __do_readpage(tree, page, get_extent, NULL, &bio, mirror_num,
-				      &bio_flags, READ);
+			    &bio_flags, READ, NULL);
 	if (bio)
 		ret = submit_one_bio(READ, bio, mirror_num, bio_flags);
 	return ret;
@@ -3450,7 +3501,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 						 sector, iosize, pg_offset,
 						 bdev, &epd->bio, max_nr,
 						 end_bio_extent_writepage,
-						 0, 0, 0);
+						 0, 0, 0, false);
 			if (ret)
 				SetPageError(page);
 		}
@@ -3752,7 +3803,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 		ret = submit_extent_page(rw, tree, p, offset >> 9,
 					 PAGE_CACHE_SIZE, 0, bdev, &epd->bio,
 					 -1, end_bio_extent_buffer_writepage,
-					 0, epd->bio_flags, bio_flags);
+					 0, epd->bio_flags, bio_flags, false);
 		epd->bio_flags = bio_flags;
 		if (ret) {
 			set_btree_ioerr(p);
@@ -4156,6 +4207,7 @@ int extent_readpages(struct extent_io_tree *tree,
 	struct page *page;
 	struct extent_map *em_cached = NULL;
 	int nr = 0;
+	u64 prev_em_start = (u64)-1;
 
 	for (page_idx = 0; page_idx < nr_pages; page_idx++) {
 		page = list_entry(pages->prev, struct page, lru);
@@ -4172,12 +4224,12 @@ int extent_readpages(struct extent_io_tree *tree,
 		if (nr < ARRAY_SIZE(pagepool))
 			continue;
 		__extent_readpages(tree, pagepool, nr, get_extent, &em_cached,
-				   &bio, 0, &bio_flags, READ);
+				   &bio, 0, &bio_flags, READ, &prev_em_start);
 		nr = 0;
 	}
 	if (nr)
 		__extent_readpages(tree, pagepool, nr, get_extent, &em_cached,
-				   &bio, 0, &bio_flags, READ);
+				   &bio, 0, &bio_flags, READ, &prev_em_start);
 
 	if (em_cached)
 		free_extent_map(em_cached);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e33dff356..b54e63038 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5051,7 +5051,8 @@ void btrfs_evict_inode(struct inode *inode)
 		goto no_delete;
 	}
 	/* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */
-	btrfs_wait_ordered_range(inode, 0, (u64)-1);
+	if (!special_file(inode->i_mode))
+		btrfs_wait_ordered_range(inode, 0, (u64)-1);
 
 	btrfs_free_io_failure_record(inode, 0, (u64)-1);
 
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index aa0dc2573..afa09fce8 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -444,6 +444,48 @@ find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp)
 	return 0;
 }
 
+/* Server has provided av pairs/target info in the type 2 challenge
+ * packet and we have plucked it and stored within smb session.
+ * We parse that blob here to find the server given timestamp
+ * as part of ntlmv2 authentication (or local current time as
+ * default in case of failure)
+ */
+static __le64
+find_timestamp(struct cifs_ses *ses)
+{
+	unsigned int attrsize;
+	unsigned int type;
+	unsigned int onesize = sizeof(struct ntlmssp2_name);
+	unsigned char *blobptr;
+	unsigned char *blobend;
+	struct ntlmssp2_name *attrptr;
+
+	if (!ses->auth_key.len || !ses->auth_key.response)
+		return 0;
+
+	blobptr = ses->auth_key.response;
+	blobend = blobptr + ses->auth_key.len;
+
+	while (blobptr + onesize < blobend) {
+		attrptr = (struct ntlmssp2_name *) blobptr;
+		type = le16_to_cpu(attrptr->type);
+		if (type == NTLMSSP_AV_EOL)
+			break;
+		blobptr += 2; /* advance attr type */
+		attrsize = le16_to_cpu(attrptr->length);
+		blobptr += 2; /* advance attr size */
+		if (blobptr + attrsize > blobend)
+			break;
+		if (type == NTLMSSP_AV_TIMESTAMP) {
+			if (attrsize == sizeof(u64))
+				return *((__le64 *)blobptr);
+		}
+		blobptr += attrsize; /* advance attr value */
+	}
+
+	return cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME));
+}
+
 static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
 			    const struct nls_table *nls_cp)
 {
@@ -641,6 +683,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 	struct ntlmv2_resp *ntlmv2;
 	char ntlmv2_hash[16];
 	unsigned char *tiblob = NULL; /* target info blob */
+	__le64 rsp_timestamp;
 
 	if (ses->server->negflavor == CIFS_NEGFLAVOR_EXTENDED) {
 		if (!ses->domainName) {
@@ -659,6 +702,12 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 		}
 	}
 
+	/* Must be within 5 minutes of the server (or in range +/-2h
+	 * in case of Mac OS X), so simply carry over server timestamp
+	 * (as Windows 7 does)
+	 */
+	rsp_timestamp = find_timestamp(ses);
+
 	baselen = CIFS_SESS_KEY_SIZE + sizeof(struct ntlmv2_resp);
 	tilen = ses->auth_key.len;
 	tiblob = ses->auth_key.response;
@@ -675,8 +724,8 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 			(ses->auth_key.response + CIFS_SESS_KEY_SIZE);
 	ntlmv2->blob_signature = cpu_to_le32(0x00000101);
 	ntlmv2->reserved = 0;
-	/* Must be within 5 minutes of the server */
-	ntlmv2->time = cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME));
+	ntlmv2->time = rsp_timestamp;
+
 	get_random_bytes(&ntlmv2->client_chal, sizeof(ntlmv2->client_chal));
 	ntlmv2->reserved2 = 0;
 
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index f621b44cb..6b66dd5d1 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -2034,7 +2034,6 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs,
 	struct tcon_link *tlink = NULL;
 	struct cifs_tcon *tcon = NULL;
 	struct TCP_Server_Info *server;
-	struct cifs_io_parms io_parms;
 
 	/*
 	 * To avoid spurious oplock breaks from server, in the case of
@@ -2056,18 +2055,6 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs,
 			rc = -ENOSYS;
 		cifsFileInfo_put(open_file);
 		cifs_dbg(FYI, "SetFSize for attrs rc = %d\n", rc);
-		if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) {
-			unsigned int bytes_written;
-
-			io_parms.netfid = open_file->fid.netfid;
-			io_parms.pid = open_file->pid;
-			io_parms.tcon = tcon;
-			io_parms.offset = 0;
-			io_parms.length = attrs->ia_size;
-			rc = CIFSSMBWrite(xid, &io_parms, &bytes_written,
-					  NULL, NULL, 1);
-			cifs_dbg(FYI, "Wrt seteof rc %d\n", rc);
-		}
 	} else
 		rc = -EINVAL;
 
@@ -2093,28 +2080,7 @@ cifs_set_file_size(struct inode *inode, struct iattr *attrs,
 	else
 		rc = -ENOSYS;
 	cifs_dbg(FYI, "SetEOF by path (setattrs) rc = %d\n", rc);
-	if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) {
-		__u16 netfid;
-		int oplock = 0;
 
-		rc = SMBLegacyOpen(xid, tcon, full_path, FILE_OPEN,
-				   GENERIC_WRITE, CREATE_NOT_DIR, &netfid,
-				   &oplock, NULL, cifs_sb->local_nls,
-				   cifs_remap(cifs_sb));
-		if (rc == 0) {
-			unsigned int bytes_written;
-
-			io_parms.netfid = netfid;
-			io_parms.pid = current->tgid;
-			io_parms.tcon = tcon;
-			io_parms.offset = 0;
-			io_parms.length = attrs->ia_size;
-			rc = CIFSSMBWrite(xid, &io_parms, &bytes_written, NULL,
-					  NULL,  1);
-			cifs_dbg(FYI, "wrt seteof rc %d\n", rc);
-			CIFSSMBClose(xid, tcon, netfid);
-		}
-	}
 	if (tlink)
 		cifs_put_tlink(tlink);
 
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index df91bcf56..18da19f4f 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -50,9 +50,13 @@ change_conf(struct TCP_Server_Info *server)
 		break;
 	default:
 		server->echoes = true;
-		server->oplocks = true;
+		if (enable_oplocks) {
+			server->oplocks = true;
+			server->oplock_credits = 1;
+		} else
+			server->oplocks = false;
+
 		server->echo_credits = 1;
-		server->oplock_credits = 1;
 	}
 	server->credits -= server->echo_credits + server->oplock_credits;
 	return 0;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index b8b4f08ee..60dd83164 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -46,6 +46,7 @@
 #include "smb2status.h"
 #include "smb2glob.h"
 #include "cifspdu.h"
+#include "cifs_spnego.h"
 
 /*
  *  The following table defines the expected "StructureSize" of SMB2 requests
@@ -486,19 +487,15 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		cifs_dbg(FYI, "missing security blob on negprot\n");
 
 	rc = cifs_enable_signing(server, ses->sign);
-#ifdef CONFIG_SMB2_ASN1  /* BB REMOVEME when updated asn1.c ready */
 	if (rc)
 		goto neg_exit;
-	if (blob_length)
+	if (blob_length) {
 		rc = decode_negTokenInit(security_blob, blob_length, server);
-	if (rc == 1)
-		rc = 0;
-	else if (rc == 0) {
-		rc = -EIO;
-		goto neg_exit;
+		if (rc == 1)
+			rc = 0;
+		else if (rc == 0)
+			rc = -EIO;
 	}
-#endif
-
 neg_exit:
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
@@ -592,7 +589,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 	__le32 phase = NtLmNegotiate; /* NTLMSSP, if needed, is multistage */
 	struct TCP_Server_Info *server = ses->server;
 	u16 blob_length = 0;
-	char *security_blob;
+	struct key *spnego_key = NULL;
+	char *security_blob = NULL;
 	char *ntlmssp_blob = NULL;
 	bool use_spnego = false; /* else use raw ntlmssp */
 
@@ -620,7 +618,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 	ses->ntlmssp->sesskey_per_smbsess = true;
 
 	/* FIXME: allow for other auth types besides NTLMSSP (e.g. krb5) */
-	ses->sectype = RawNTLMSSP;
+	if (ses->sectype != Kerberos && ses->sectype != RawNTLMSSP)
+		ses->sectype = RawNTLMSSP;
 
 ssetup_ntlmssp_authenticate:
 	if (phase == NtLmChallenge)
@@ -649,7 +648,48 @@ ssetup_ntlmssp_authenticate:
 	iov[0].iov_base = (char *)req;
 	/* 4 for rfc1002 length field and 1 for pad */
 	iov[0].iov_len = get_rfc1002_length(req) + 4 - 1;
-	if (phase == NtLmNegotiate) {
+
+	if (ses->sectype == Kerberos) {
+#ifdef CONFIG_CIFS_UPCALL
+		struct cifs_spnego_msg *msg;
+
+		spnego_key = cifs_get_spnego_key(ses);
+		if (IS_ERR(spnego_key)) {
+			rc = PTR_ERR(spnego_key);
+			spnego_key = NULL;
+			goto ssetup_exit;
+		}
+
+		msg = spnego_key->payload.data;
+		/*
+		 * check version field to make sure that cifs.upcall is
+		 * sending us a response in an expected form
+		 */
+		if (msg->version != CIFS_SPNEGO_UPCALL_VERSION) {
+			cifs_dbg(VFS,
+				  "bad cifs.upcall version. Expected %d got %d",
+				  CIFS_SPNEGO_UPCALL_VERSION, msg->version);
+			rc = -EKEYREJECTED;
+			goto ssetup_exit;
+		}
+		ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
+						 GFP_KERNEL);
+		if (!ses->auth_key.response) {
+			cifs_dbg(VFS,
+				"Kerberos can't allocate (%u bytes) memory",
+				msg->sesskey_len);
+			rc = -ENOMEM;
+			goto ssetup_exit;
+		}
+		ses->auth_key.len = msg->sesskey_len;
+		blob_length = msg->secblob_len;
+		iov[1].iov_base = msg->data + msg->sesskey_len;
+		iov[1].iov_len = blob_length;
+#else
+		rc = -EOPNOTSUPP;
+		goto ssetup_exit;
+#endif /* CONFIG_CIFS_UPCALL */
+	} else if (phase == NtLmNegotiate) { /* if not krb5 must be ntlmssp */
 		ntlmssp_blob = kmalloc(sizeof(struct _NEGOTIATE_MESSAGE),
 				       GFP_KERNEL);
 		if (ntlmssp_blob == NULL) {
@@ -672,6 +712,8 @@ ssetup_ntlmssp_authenticate:
 			/* with raw NTLMSSP we don't encapsulate in SPNEGO */
 			security_blob = ntlmssp_blob;
 		}
+		iov[1].iov_base = security_blob;
+		iov[1].iov_len = blob_length;
 	} else if (phase == NtLmAuthenticate) {
 		req->hdr.SessionId = ses->Suid;
 		ntlmssp_blob = kzalloc(sizeof(struct _NEGOTIATE_MESSAGE) + 500,
@@ -699,6 +741,8 @@ ssetup_ntlmssp_authenticate:
 		} else {
 			security_blob = ntlmssp_blob;
 		}
+		iov[1].iov_base = security_blob;
+		iov[1].iov_len = blob_length;
 	} else {
 		cifs_dbg(VFS, "illegal ntlmssp phase\n");
 		rc = -EIO;
@@ -710,8 +754,6 @@ ssetup_ntlmssp_authenticate:
 				cpu_to_le16(sizeof(struct smb2_sess_setup_req) -
 					    1 /* pad */ - 4 /* rfc1001 len */);
 	req->SecurityBufferLength = cpu_to_le16(blob_length);
-	iov[1].iov_base = security_blob;
-	iov[1].iov_len = blob_length;
 
 	inc_rfc1001_len(req, blob_length - 1 /* pad */);
 
@@ -722,6 +764,7 @@ ssetup_ntlmssp_authenticate:
 
 	kfree(security_blob);
 	rsp = (struct smb2_sess_setup_rsp *)iov[0].iov_base;
+	ses->Suid = rsp->hdr.SessionId;
 	if (resp_buftype != CIFS_NO_BUFFER &&
 	    rsp->hdr.Status == STATUS_MORE_PROCESSING_REQUIRED) {
 		if (phase != NtLmNegotiate) {
@@ -739,7 +782,6 @@ ssetup_ntlmssp_authenticate:
 		/* NTLMSSP Negotiate sent now processing challenge (response) */
 		phase = NtLmChallenge; /* process ntlmssp challenge */
 		rc = 0; /* MORE_PROCESSING is not an error here but expected */
-		ses->Suid = rsp->hdr.SessionId;
 		rc = decode_ntlmssp_challenge(rsp->Buffer,
 				le16_to_cpu(rsp->SecurityBufferLength), ses);
 	}
@@ -796,6 +838,10 @@ keygen_exit:
 		kfree(ses->auth_key.response);
 		ses->auth_key.response = NULL;
 	}
+	if (spnego_key) {
+		key_invalidate(spnego_key);
+		key_put(spnego_key);
+	}
 	kfree(ses->ntlmssp);
 
 	return rc;
diff --git a/fs/dax.c b/fs/dax.c
index a7f77e1fa..ef35a2014 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -116,7 +116,8 @@ static ssize_t dax_io(struct inode *inode, struct iov_iter *iter,
 		unsigned len;
 		if (pos == max) {
 			unsigned blkbits = inode->i_blkbits;
-			sector_t block = pos >> blkbits;
+			long page = pos >> PAGE_SHIFT;
+			sector_t block = page << (PAGE_SHIFT - blkbits);
 			unsigned first = pos - (block << blkbits);
 			long size;
 
diff --git a/fs/dcache.c b/fs/dcache.c
index 1bced3f3f..f07398460 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2927,6 +2927,13 @@ restart:
 
 		if (dentry == vfsmnt->mnt_root || IS_ROOT(dentry)) {
 			struct mount *parent = ACCESS_ONCE(mnt->mnt_parent);
+			/* Escaped? */
+			if (dentry != vfsmnt->mnt_root) {
+				bptr = *buffer;
+				blen = *buflen;
+				error = 3;
+				break;
+			}
 			/* Global root? */
 			if (mnt != parent) {
 				dentry = ACCESS_ONCE(mnt->mnt_mountpoint);
diff --git a/fs/namei.c b/fs/namei.c
index 1c2105ed2..36df4818a 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -560,6 +560,24 @@ static int __nd_alloc_stack(struct nameidata *nd)
 	return 0;
 }
 
+/**
+ * path_connected - Verify that a path->dentry is below path->mnt.mnt_root
+ * @path: nameidate to verify
+ *
+ * Rename can sometimes move a file or directory outside of a bind
+ * mount, path_connected allows those cases to be detected.
+ */
+static bool path_connected(const struct path *path)
+{
+	struct vfsmount *mnt = path->mnt;
+
+	/* Only bind mounts can have disconnected paths */
+	if (mnt->mnt_root == mnt->mnt_sb->s_root)
+		return true;
+
+	return is_subdir(path->dentry, mnt->mnt_root);
+}
+
 static inline int nd_alloc_stack(struct nameidata *nd)
 {
 	if (likely(nd->depth != EMBEDDED_LEVELS))
@@ -1296,6 +1314,8 @@ static int follow_dotdot_rcu(struct nameidata *nd)
 				return -ECHILD;
 			nd->path.dentry = parent;
 			nd->seq = seq;
+			if (unlikely(!path_connected(&nd->path)))
+				return -ENOENT;
 			break;
 		} else {
 			struct mount *mnt = real_mount(nd->path.mnt);
@@ -1396,7 +1416,7 @@ static void follow_mount(struct path *path)
 	}
 }
 
-static void follow_dotdot(struct nameidata *nd)
+static int follow_dotdot(struct nameidata *nd)
 {
 	if (!nd->root.mnt)
 		set_root(nd);
@@ -1412,6 +1432,8 @@ static void follow_dotdot(struct nameidata *nd)
 			/* rare case of legitimate dget_parent()... */
 			nd->path.dentry = dget_parent(nd->path.dentry);
 			dput(old);
+			if (unlikely(!path_connected(&nd->path)))
+				return -ENOENT;
 			break;
 		}
 		if (!follow_up(&nd->path))
@@ -1419,6 +1441,7 @@ static void follow_dotdot(struct nameidata *nd)
 	}
 	follow_mount(&nd->path);
 	nd->inode = nd->path.dentry->d_inode;
+	return 0;
 }
 
 /*
@@ -1535,8 +1558,6 @@ static int lookup_fast(struct nameidata *nd,
 		negative = d_is_negative(dentry);
 		if (read_seqcount_retry(&dentry->d_seq, seq))
 			return -ECHILD;
-		if (negative)
-			return -ENOENT;
 
 		/*
 		 * This sequence count validates that the parent had no
@@ -1557,6 +1578,12 @@ static int lookup_fast(struct nameidata *nd,
 				goto unlazy;
 			}
 		}
+		/*
+		 * Note: do negative dentry check after revalidation in
+		 * case that drops it.
+		 */
+		if (negative)
+			return -ENOENT;
 		path->mnt = mnt;
 		path->dentry = dentry;
 		if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
@@ -1634,7 +1661,7 @@ static inline int handle_dots(struct nameidata *nd, int type)
 		if (nd->flags & LOOKUP_RCU) {
 			return follow_dotdot_rcu(nd);
 		} else
-			follow_dotdot(nd);
+			return follow_dotdot(nd);
 	}
 	return 0;
 }
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 029d688a9..c56886829 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -113,7 +113,8 @@ out:
 	return status;
 }
 
-static int nfs_delegation_claim_opens(struct inode *inode, const nfs4_stateid *stateid)
+static int nfs_delegation_claim_opens(struct inode *inode,
+		const nfs4_stateid *stateid, fmode_t type)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_open_context *ctx;
@@ -140,7 +141,7 @@ again:
 		/* Block nfs4_proc_unlck */
 		mutex_lock(&sp->so_delegreturn_mutex);
 		seq = raw_seqcount_begin(&sp->so_reclaim_seqcount);
-		err = nfs4_open_delegation_recall(ctx, state, stateid);
+		err = nfs4_open_delegation_recall(ctx, state, stateid, type);
 		if (!err)
 			err = nfs_delegation_claim_locks(ctx, state, stateid);
 		if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
@@ -411,7 +412,8 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation
 	do {
 		if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
 			break;
-		err = nfs_delegation_claim_opens(inode, &delegation->stateid);
+		err = nfs_delegation_claim_opens(inode, &delegation->stateid,
+				delegation->type);
 		if (!issync || err != -EAGAIN)
 			break;
 		/*
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index e3c20a3cc..785c8525b 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -54,7 +54,7 @@ void nfs_delegation_reap_unclaimed(struct nfs_client *clp);
 
 /* NFSv4 delegation-related procedures */
 int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4_stateid *stateid, int issync);
-int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid);
+int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid, fmode_t type);
 int nfs4_lock_delegation_recall(struct file_lock *fl, struct nfs4_state *state, const nfs4_stateid *stateid);
 bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags);
 
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index b34f2e228..02ec07973 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -629,23 +629,18 @@ out_put:
 	goto out;
 }
 
-static void filelayout_free_fh_array(struct nfs4_filelayout_segment *fl)
+static void _filelayout_free_lseg(struct nfs4_filelayout_segment *fl)
 {
 	int i;
 
-	for (i = 0; i < fl->num_fh; i++) {
-		if (!fl->fh_array[i])
-			break;
-		kfree(fl->fh_array[i]);
+	if (fl->fh_array) {
+		for (i = 0; i < fl->num_fh; i++) {
+			if (!fl->fh_array[i])
+				break;
+			kfree(fl->fh_array[i]);
+		}
+		kfree(fl->fh_array);
 	}
-	kfree(fl->fh_array);
-	fl->fh_array = NULL;
-}
-
-static void
-_filelayout_free_lseg(struct nfs4_filelayout_segment *fl)
-{
-	filelayout_free_fh_array(fl);
 	kfree(fl);
 }
 
@@ -716,21 +711,21 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 		/* Do we want to use a mempool here? */
 		fl->fh_array[i] = kmalloc(sizeof(struct nfs_fh), gfp_flags);
 		if (!fl->fh_array[i])
-			goto out_err_free;
+			goto out_err;
 
 		p = xdr_inline_decode(&stream, 4);
 		if (unlikely(!p))
-			goto out_err_free;
+			goto out_err;
 		fl->fh_array[i]->size = be32_to_cpup(p++);
 		if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) {
 			printk(KERN_ERR "NFS: Too big fh %d received %d\n",
 			       i, fl->fh_array[i]->size);
-			goto out_err_free;
+			goto out_err;
 		}
 
 		p = xdr_inline_decode(&stream, fl->fh_array[i]->size);
 		if (unlikely(!p))
-			goto out_err_free;
+			goto out_err;
 		memcpy(fl->fh_array[i]->data, p, fl->fh_array[i]->size);
 		dprintk("DEBUG: %s: fh len %d\n", __func__,
 			fl->fh_array[i]->size);
@@ -739,8 +734,6 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 	__free_page(scratch);
 	return 0;
 
-out_err_free:
-	filelayout_free_fh_array(fl);
 out_err:
 	__free_page(scratch);
 	return -EIO;
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index d731bbf97..0f020e4d8 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -175,10 +175,12 @@ loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 {
 	struct nfs_server *server = NFS_SERVER(file_inode(filep));
 	struct nfs4_exception exception = { };
-	int err;
+	loff_t err;
 
 	do {
 		err = _nfs42_proc_llseek(filep, offset, whence);
+		if (err >= 0)
+			break;
 		if (err == -ENOTSUPP)
 			return -EOPNOTSUPP;
 		err = nfs4_handle_exception(server, err, &exception);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 73c8204ad..d2daacad3 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1127,6 +1127,21 @@ static int nfs4_wait_for_completion_rpc_task(struct rpc_task *task)
 	return ret;
 }
 
+static bool nfs4_mode_match_open_stateid(struct nfs4_state *state,
+		fmode_t fmode)
+{
+	switch(fmode & (FMODE_READ|FMODE_WRITE)) {
+	case FMODE_READ|FMODE_WRITE:
+		return state->n_rdwr != 0;
+	case FMODE_WRITE:
+		return state->n_wronly != 0;
+	case FMODE_READ:
+		return state->n_rdonly != 0;
+	}
+	WARN_ON_ONCE(1);
+	return false;
+}
+
 static int can_open_cached(struct nfs4_state *state, fmode_t mode, int open_mode)
 {
 	int ret = 0;
@@ -1561,17 +1576,13 @@ static struct nfs4_opendata *nfs4_open_recoverdata_alloc(struct nfs_open_context
 	return opendata;
 }
 
-static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmode, struct nfs4_state **res)
+static int nfs4_open_recover_helper(struct nfs4_opendata *opendata,
+		fmode_t fmode)
 {
 	struct nfs4_state *newstate;
 	int ret;
 
-	if ((opendata->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR ||
-	     opendata->o_arg.claim == NFS4_OPEN_CLAIM_DELEG_CUR_FH) &&
-	    (opendata->o_arg.u.delegation_type & fmode) != fmode)
-		/* This mode can't have been delegated, so we must have
-		 * a valid open_stateid to cover it - not need to reclaim.
-		 */
+	if (!nfs4_mode_match_open_stateid(opendata->state, fmode))
 		return 0;
 	opendata->o_arg.open_flags = 0;
 	opendata->o_arg.fmode = fmode;
@@ -1587,14 +1598,14 @@ static int nfs4_open_recover_helper(struct nfs4_opendata *opendata, fmode_t fmod
 	newstate = nfs4_opendata_to_nfs4_state(opendata);
 	if (IS_ERR(newstate))
 		return PTR_ERR(newstate);
+	if (newstate != opendata->state)
+		ret = -ESTALE;
 	nfs4_close_state(newstate, fmode);
-	*res = newstate;
-	return 0;
+	return ret;
 }
 
 static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *state)
 {
-	struct nfs4_state *newstate;
 	int ret;
 
 	/* Don't trigger recovery in nfs_test_and_clear_all_open_stateid */
@@ -1605,27 +1616,15 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state *
 	clear_bit(NFS_DELEGATED_STATE, &state->flags);
 	clear_bit(NFS_OPEN_STATE, &state->flags);
 	smp_rmb();
-	if (state->n_rdwr != 0) {
-		ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE, &newstate);
-		if (ret != 0)
-			return ret;
-		if (newstate != state)
-			return -ESTALE;
-	}
-	if (state->n_wronly != 0) {
-		ret = nfs4_open_recover_helper(opendata, FMODE_WRITE, &newstate);
-		if (ret != 0)
-			return ret;
-		if (newstate != state)
-			return -ESTALE;
-	}
-	if (state->n_rdonly != 0) {
-		ret = nfs4_open_recover_helper(opendata, FMODE_READ, &newstate);
-		if (ret != 0)
-			return ret;
-		if (newstate != state)
-			return -ESTALE;
-	}
+	ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE);
+	if (ret != 0)
+		return ret;
+	ret = nfs4_open_recover_helper(opendata, FMODE_WRITE);
+	if (ret != 0)
+		return ret;
+	ret = nfs4_open_recover_helper(opendata, FMODE_READ);
+	if (ret != 0)
+		return ret;
 	/*
 	 * We may have performed cached opens for all three recoveries.
 	 * Check if we need to update the current stateid.
@@ -1749,18 +1748,32 @@ static int nfs4_handle_delegation_recall_error(struct nfs_server *server, struct
 	return err;
 }
 
-int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state *state, const nfs4_stateid *stateid)
+int nfs4_open_delegation_recall(struct nfs_open_context *ctx,
+		struct nfs4_state *state, const nfs4_stateid *stateid,
+		fmode_t type)
 {
 	struct nfs_server *server = NFS_SERVER(state->inode);
 	struct nfs4_opendata *opendata;
-	int err;
+	int err = 0;
 
 	opendata = nfs4_open_recoverdata_alloc(ctx, state,
 			NFS4_OPEN_CLAIM_DELEG_CUR_FH);
 	if (IS_ERR(opendata))
 		return PTR_ERR(opendata);
 	nfs4_stateid_copy(&opendata->o_arg.u.delegation, stateid);
-	err = nfs4_open_recover(opendata, state);
+	clear_bit(NFS_DELEGATED_STATE, &state->flags);
+	switch (type & (FMODE_READ|FMODE_WRITE)) {
+	case FMODE_READ|FMODE_WRITE:
+	case FMODE_WRITE:
+		err = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE);
+		if (err)
+			break;
+		err = nfs4_open_recover_helper(opendata, FMODE_WRITE);
+		if (err)
+			break;
+	case FMODE_READ:
+		err = nfs4_open_recover_helper(opendata, FMODE_READ);
+	}
 	nfs4_opendata_put(opendata);
 	return nfs4_handle_delegation_recall_error(server, state, stateid, err);
 }
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 7c5718ba6..fe3ddd20f 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -508,7 +508,7 @@ size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
 	 * for it without upsetting the slab allocator.
 	 */
 	if (((mirror->pg_count + req->wb_bytes) >> PAGE_SHIFT) *
-			sizeof(struct page) > PAGE_SIZE)
+			sizeof(struct page *) > PAGE_SIZE)
 		return 0;
 
 	return min(mirror->pg_bsize - mirror->pg_count, (size_t)req->wb_bytes);
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index ae0ff7a11..01b8cc8e8 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -72,6 +72,9 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio)
 {
 	struct nfs_pgio_mirror *mirror;
 
+	if (pgio->pg_ops && pgio->pg_ops->pg_cleanup)
+		pgio->pg_ops->pg_cleanup(pgio);
+
 	pgio->pg_ops = &nfs_pgio_rw_ops;
 
 	/* read path should never have more than one mirror */
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index fdee9270c..b45b465bc 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1223,7 +1223,7 @@ static int nfs_can_extend_write(struct file *file, struct page *page, struct ino
 		return 1;
 	if (!flctx || (list_empty_careful(&flctx->flc_flock) &&
 		       list_empty_careful(&flctx->flc_posix)))
-		return 0;
+		return 1;
 
 	/* Check to see if there are whole file write locks */
 	ret = 0;
@@ -1351,6 +1351,9 @@ void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio)
 {
 	struct nfs_pgio_mirror *mirror;
 
+	if (pgio->pg_ops && pgio->pg_ops->pg_cleanup)
+		pgio->pg_ops->pg_cleanup(pgio);
+
 	pgio->pg_ops = &nfs_pgio_rw_ops;
 
 	nfs_pageio_stop_mirroring(pgio);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index fdf4b41d0..482cfd344 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -1439,6 +1439,7 @@ int dlm_master_request_handler(struct o2net_msg *msg, u32 len, void *data,
 	int found, ret;
 	int set_maybe;
 	int dispatch_assert = 0;
+	int dispatched = 0;
 
 	if (!dlm_grab(dlm))
 		return DLM_MASTER_RESP_NO;
@@ -1658,15 +1659,18 @@ send_response:
 			mlog(ML_ERROR, "failed to dispatch assert master work\n");
 			response = DLM_MASTER_RESP_ERROR;
 			dlm_lockres_put(res);
-		} else
+		} else {
+			dispatched = 1;
 			__dlm_lockres_grab_inflight_worker(dlm, res);
+		}
 		spin_unlock(&res->spinlock);
 	} else {
 		if (res)
 			dlm_lockres_put(res);
 	}
 
-	dlm_put(dlm);
+	if (!dispatched)
+		dlm_put(dlm);
 	return response;
 }
 
@@ -2090,7 +2094,6 @@ int dlm_dispatch_assert_master(struct dlm_ctxt *dlm,
 
 
 	/* queue up work for dlm_assert_master_worker */
-	dlm_grab(dlm);  /* get an extra ref for the work item */
 	dlm_init_work_item(dlm, item, dlm_assert_master_worker, NULL);
 	item->u.am.lockres = res; /* already have a ref */
 	/* can optionally ignore node numbers higher than this node */
diff --git a/fs/ocfs2/dlm/dlmrecovery.c b/fs/ocfs2/dlm/dlmrecovery.c
index ce12e0b1a..3d90ad7ff 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1694,6 +1694,7 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 	unsigned int hash;
 	int master = DLM_LOCK_RES_OWNER_UNKNOWN;
 	u32 flags = DLM_ASSERT_MASTER_REQUERY;
+	int dispatched = 0;
 
 	if (!dlm_grab(dlm)) {
 		/* since the domain has gone away on this
@@ -1719,8 +1720,10 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 				dlm_put(dlm);
 				/* sender will take care of this and retry */
 				return ret;
-			} else
+			} else {
+				dispatched = 1;
 				__dlm_lockres_grab_inflight_worker(dlm, res);
+			}
 			spin_unlock(&res->spinlock);
 		} else {
 			/* put.. incase we are not the master */
@@ -1730,7 +1733,8 @@ int dlm_master_requery_handler(struct o2net_msg *msg, u32 len, void *data,
 	}
 	spin_unlock(&dlm->spinlock);
 
-	dlm_put(dlm);
+	if (!dispatched)
+		dlm_put(dlm);
 	return master;
 }
 
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index 96f3448b6..fd65b3f19 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -652,11 +652,8 @@ int ubifs_init_security(struct inode *dentry, struct inode *inode,
 {
 	int err;
 
-	mutex_lock(&inode->i_mutex);
 	err = security_inode_init_security(inode, dentry, qstr,
 					   &init_xattrs, 0);
-	mutex_unlock(&inode->i_mutex);
-
 	if (err) {
 		struct ubifs_info *c = dentry->i_sb->s_fs_info;
 		ubifs_err(c, "cannot initialize security for inode %lu, error %d",
diff --git a/include/asm-generic/preempt.h b/include/asm-generic/preempt.h
index d0a7a4753..0bec580a4 100644
--- a/include/asm-generic/preempt.h
+++ b/include/asm-generic/preempt.h
@@ -71,9 +71,10 @@ static __always_inline bool __preempt_count_dec_and_test(void)
 /*
  * Returns true when we need to resched and can (barring IRQ state).
  */
-static __always_inline bool should_resched(void)
+static __always_inline bool should_resched(int preempt_offset)
 {
-	return unlikely(!preempt_count() && tif_need_resched());
+	return unlikely(preempt_count() == preempt_offset &&
+			tif_need_resched());
 }
 
 #ifdef CONFIG_PREEMPT
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 83bfb87f5..e2aadbc71 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -111,8 +111,8 @@ static inline void queued_spin_unlock_wait(struct qspinlock *lock)
 		cpu_relax();
 }
 
-#ifndef virt_queued_spin_lock
-static __always_inline bool virt_queued_spin_lock(struct qspinlock *lock)
+#ifndef virt_spin_lock
+static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 {
 	return false;
 }
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 93755a629..430c876ad 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -463,31 +463,8 @@ struct cgroup_subsys {
 	unsigned int depends_on;
 };
 
-extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
-
-/**
- * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups
- * @tsk: target task
- *
- * Called from threadgroup_change_begin() and allows cgroup operations to
- * synchronize against threadgroup changes using a percpu_rw_semaphore.
- */
-static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk)
-{
-	percpu_down_read(&cgroup_threadgroup_rwsem);
-}
-
-/**
- * cgroup_threadgroup_change_end - threadgroup exclusion for cgroups
- * @tsk: target task
- *
- * Called from threadgroup_change_end().  Counterpart of
- * cgroup_threadcgroup_change_begin().
- */
-static inline void cgroup_threadgroup_change_end(struct task_struct *tsk)
-{
-	percpu_up_read(&cgroup_threadgroup_rwsem);
-}
+void cgroup_threadgroup_change_begin(struct task_struct *tsk);
+void cgroup_threadgroup_change_end(struct task_struct *tsk);
 
 #else	/* CONFIG_CGROUPS */
 
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index e8493fee8..bb9b075f0 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -25,6 +25,13 @@
 extern struct files_struct init_files;
 extern struct fs_struct init_fs;
 
+#ifdef CONFIG_CGROUPS
+#define INIT_GROUP_RWSEM(sig)						\
+	.group_rwsem = __RWSEM_INITIALIZER(sig.group_rwsem),
+#else
+#define INIT_GROUP_RWSEM(sig)
+#endif
+
 #ifdef CONFIG_CPUSETS
 #define INIT_CPUSET_SEQ(tsk)							\
 	.mems_allowed_seq = SEQCNT_ZERO(tsk.mems_allowed_seq),
@@ -48,6 +55,7 @@ extern struct fs_struct init_fs;
 	},								\
 	.cred_guard_mutex =						\
 		 __MUTEX_INITIALIZER(sig.cred_guard_mutex),		\
+	INIT_GROUP_RWSEM(sig)						\
 }
 
 extern struct nsproxy init_nsproxy;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8a6e1fc37..6293566d7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -916,6 +916,27 @@ static inline void set_page_links(struct page *page, enum zone_type zone,
 #endif
 }
 
+#ifdef CONFIG_MEMCG
+static inline struct mem_cgroup *page_memcg(struct page *page)
+{
+	return page->mem_cgroup;
+}
+
+static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg)
+{
+	page->mem_cgroup = memcg;
+}
+#else
+static inline struct mem_cgroup *page_memcg(struct page *page)
+{
+	return NULL;
+}
+
+static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg)
+{
+}
+#endif
+
 /*
  * Some inline functions in vmstat.h depend on page_zone()
  */
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 84991f185..bea8dd8ff 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -84,13 +84,21 @@
  */
 #define in_nmi()	(preempt_count() & NMI_MASK)
 
+/*
+ * The preempt_count offset after preempt_disable();
+ */
 #if defined(CONFIG_PREEMPT_COUNT)
-# define PREEMPT_DISABLE_OFFSET 1
+# define PREEMPT_DISABLE_OFFSET	PREEMPT_OFFSET
 #else
-# define PREEMPT_DISABLE_OFFSET 0
+# define PREEMPT_DISABLE_OFFSET	0
 #endif
 
 /*
+ * The preempt_count offset after spin_lock()
+ */
+#define PREEMPT_LOCK_OFFSET	PREEMPT_DISABLE_OFFSET
+
+/*
  * The preempt_count offset needed for things like:
  *
  *  spin_lock_bh()
@@ -103,7 +111,7 @@
  *
  * Work as expected.
  */
-#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_DISABLE_OFFSET)
+#define SOFTIRQ_LOCK_OFFSET (SOFTIRQ_DISABLE_OFFSET + PREEMPT_LOCK_OFFSET)
 
 /*
  * Are we running in atomic context?  WARNING: this macro cannot
@@ -124,7 +132,8 @@
 #if defined(CONFIG_DEBUG_PREEMPT) || defined(CONFIG_PREEMPT_TRACER)
 extern void preempt_count_add(int val);
 extern void preempt_count_sub(int val);
-#define preempt_count_dec_and_test() ({ preempt_count_sub(1); should_resched(); })
+#define preempt_count_dec_and_test() \
+	({ preempt_count_sub(1); should_resched(0); })
 #else
 #define preempt_count_add(val)	__preempt_count_add(val)
 #define preempt_count_sub(val)	__preempt_count_sub(val)
@@ -184,7 +193,7 @@ do { \
 
 #define preempt_check_resched() \
 do { \
-	if (should_resched()) \
+	if (should_resched(0)) \
 		__preempt_schedule(); \
 } while (0)
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 04b5ada46..bfca8aa21 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -754,6 +754,18 @@ struct signal_struct {
 	unsigned audit_tty_log_passwd;
 	struct tty_audit_buf *tty_audit_buf;
 #endif
+#ifdef CONFIG_CGROUPS
+	/*
+	 * group_rwsem prevents new tasks from entering the threadgroup and
+	 * member tasks from exiting,a more specifically, setting of
+	 * PF_EXITING.  fork and exit paths are protected with this rwsem
+	 * using threadgroup_change_begin/end().  Users which require
+	 * threadgroup to remain stable should use threadgroup_[un]lock()
+	 * which also takes care of exec path.  Currently, cgroup is the
+	 * only user.
+	 */
+	struct rw_semaphore group_rwsem;
+#endif
 
 	oom_flags_t oom_flags;
 	short oom_score_adj;		/* OOM kill score adjustment */
@@ -2897,12 +2909,6 @@ extern int _cond_resched(void);
 
 extern int __cond_resched_lock(spinlock_t *lock);
 
-#ifdef CONFIG_PREEMPT_COUNT
-#define PREEMPT_LOCK_OFFSET	PREEMPT_OFFSET
-#else
-#define PREEMPT_LOCK_OFFSET	0
-#endif
-
 #define cond_resched_lock(lock) ({				\
 	___might_sleep(__FILE__, __LINE__, PREEMPT_LOCK_OFFSET);\
 	__cond_resched_lock(lock);				\
diff --git a/include/linux/security.h b/include/linux/security.h
index 79d85ddf8..2f4c1f7aa 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -946,7 +946,7 @@ static inline int security_task_prctl(int option, unsigned long arg2,
 				      unsigned long arg4,
 				      unsigned long arg5)
 {
-	return cap_task_prctl(option, arg2, arg3, arg3, arg5);
+	return cap_task_prctl(option, arg2, arg3, arg4, arg5);
 }
 
 static inline void security_task_to_inode(struct task_struct *p, struct inode *inode)
diff --git a/include/net/netfilter/br_netfilter.h b/include/net/netfilter/br_netfilter.h
index bab824bde..d4c6b5f30 100644
--- a/include/net/netfilter/br_netfilter.h
+++ b/include/net/netfilter/br_netfilter.h
@@ -59,7 +59,7 @@ static inline unsigned int
 br_nf_pre_routing_ipv6(const struct nf_hook_ops *ops, struct sk_buff *skb,
 		       const struct nf_hook_state *state)
 {
-	return NF_DROP;
+	return NF_ACCEPT;
 }
 #endif
 
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 2a246680a..aa8bee72c 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -125,7 +125,7 @@ static inline enum nft_data_types nft_dreg_to_type(enum nft_registers reg)
 
 static inline enum nft_registers nft_type_to_reg(enum nft_data_types type)
 {
-	return type == NFT_DATA_VERDICT ? NFT_REG_VERDICT : NFT_REG_1;
+	return type == NFT_DATA_VERDICT ? NFT_REG_VERDICT : NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE;
 }
 
 unsigned int nft_parse_register(const struct nlattr *attr);
diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h
index 0aedbb2c1..7e7f8875a 100644
--- a/include/target/iscsi/iscsi_target_core.h
+++ b/include/target/iscsi/iscsi_target_core.h
@@ -776,7 +776,6 @@ struct iscsi_np {
 	enum iscsi_timer_flags_table np_login_timer_flags;
 	u32			np_exports;
 	enum np_flags_table	np_flags;
-	unsigned char		np_ip[IPV6_ADDRESS_SPACE];
 	u16			np_port;
 	spinlock_t		np_thread_lock;
 	struct completion	np_restart_comp;
diff --git a/include/xen/interface/sched.h b/include/xen/interface/sched.h
index 9ce083960..f18490985 100644
--- a/include/xen/interface/sched.h
+++ b/include/xen/interface/sched.h
@@ -107,5 +107,13 @@ struct sched_watchdog {
 #define SHUTDOWN_suspend    2  /* Clean up, save suspend info, kill.         */
 #define SHUTDOWN_crash      3  /* Tell controller we've crashed.             */
 #define SHUTDOWN_watchdog   4  /* Restart because watchdog time expired.     */
+/*
+ * Domain asked to perform 'soft reset' for it. The expected behavior is to
+ * reset internal Xen state for the domain returning it to the point where it
+ * was created but leaving the domain's memory contents and vCPU contexts
+ * intact. This will allow the domain to start over and set up all Xen specific
+ * interfaces again.
+ */
+#define SHUTDOWN_soft_reset 5
 
 #endif /* __XEN_PUBLIC_SCHED_H__ */
diff --git a/ipc/msg.c b/ipc/msg.c
index 66c4f567e..1471db9a7 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -137,13 +137,6 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
 		return retval;
 	}
 
-	/* ipc_addid() locks msq upon success. */
-	id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
-	if (id < 0) {
-		ipc_rcu_putref(msq, msg_rcu_free);
-		return id;
-	}
-
 	msq->q_stime = msq->q_rtime = 0;
 	msq->q_ctime = get_seconds();
 	msq->q_cbytes = msq->q_qnum = 0;
@@ -153,6 +146,13 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
 	INIT_LIST_HEAD(&msq->q_receivers);
 	INIT_LIST_HEAD(&msq->q_senders);
 
+	/* ipc_addid() locks msq upon success. */
+	id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
+	if (id < 0) {
+		ipc_rcu_putref(msq, msg_rcu_free);
+		return id;
+	}
+
 	ipc_unlock_object(&msq->q_perm);
 	rcu_read_unlock();
 
diff --git a/ipc/shm.c b/ipc/shm.c
index ca158fd90..80037b240 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -551,12 +551,6 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	if (IS_ERR(file))
 		goto no_file;
 
-	id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
-	if (id < 0) {
-		error = id;
-		goto no_id;
-	}
-
 	shp->shm_cprid = task_tgid_vnr(current);
 	shp->shm_lprid = 0;
 	shp->shm_atim = shp->shm_dtim = 0;
@@ -565,6 +559,13 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	shp->shm_nattch = 0;
 	shp->shm_file = file;
 	shp->shm_creator = current;
+
+	id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
+	if (id < 0) {
+		error = id;
+		goto no_id;
+	}
+
 	list_add(&shp->shm_clist, &current->sysvshm.shm_clist);
 
 	/*
diff --git a/ipc/util.c b/ipc/util.c
index be4230020..0f401d94b 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -237,6 +237,10 @@ int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int size)
 	rcu_read_lock();
 	spin_lock(&new->lock);
 
+	current_euid_egid(&euid, &egid);
+	new->cuid = new->uid = euid;
+	new->gid = new->cgid = egid;
+
 	id = idr_alloc(&ids->ipcs_idr, new,
 		       (next_id < 0) ? 0 : ipcid_to_idx(next_id), 0,
 		       GFP_NOWAIT);
@@ -249,10 +253,6 @@ int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int size)
 
 	ids->in_use++;
 
-	current_euid_egid(&euid, &egid);
-	new->cuid = new->uid = euid;
-	new->gid = new->cgid = egid;
-
 	if (next_id < 0) {
 		new->seq = ids->seq++;
 		if (ids->seq > IPCID_SEQ_MAX)
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c6c4240e7..fe6f855de 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -46,7 +46,6 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/rwsem.h>
-#include <linux/percpu-rwsem.h>
 #include <linux/string.h>
 #include <linux/sort.h>
 #include <linux/kmod.h>
@@ -104,8 +103,6 @@ static DEFINE_SPINLOCK(cgroup_idr_lock);
  */
 static DEFINE_SPINLOCK(release_agent_path_lock);
 
-struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
-
 #define cgroup_assert_mutex_or_rcu_locked()				\
 	rcu_lockdep_assert(rcu_read_lock_held() ||			\
 			   lockdep_is_held(&cgroup_mutex),		\
@@ -870,6 +867,48 @@ static struct css_set *find_css_set(struct css_set *old_cset,
 	return cset;
 }
 
+void cgroup_threadgroup_change_begin(struct task_struct *tsk)
+{
+	down_read(&tsk->signal->group_rwsem);
+}
+
+void cgroup_threadgroup_change_end(struct task_struct *tsk)
+{
+	up_read(&tsk->signal->group_rwsem);
+}
+
+/**
+ * threadgroup_lock - lock threadgroup
+ * @tsk: member task of the threadgroup to lock
+ *
+ * Lock the threadgroup @tsk belongs to.  No new task is allowed to enter
+ * and member tasks aren't allowed to exit (as indicated by PF_EXITING) or
+ * change ->group_leader/pid.  This is useful for cases where the threadgroup
+ * needs to stay stable across blockable operations.
+ *
+ * fork and exit explicitly call threadgroup_change_{begin|end}() for
+ * synchronization.  While held, no new task will be added to threadgroup
+ * and no existing live task will have its PF_EXITING set.
+ *
+ * de_thread() does threadgroup_change_{begin|end}() when a non-leader
+ * sub-thread becomes a new leader.
+ */
+static void threadgroup_lock(struct task_struct *tsk)
+{
+	down_write(&tsk->signal->group_rwsem);
+}
+
+/**
+ * threadgroup_unlock - unlock threadgroup
+ * @tsk: member task of the threadgroup to unlock
+ *
+ * Reverse threadgroup_lock().
+ */
+static inline void threadgroup_unlock(struct task_struct *tsk)
+{
+	up_write(&tsk->signal->group_rwsem);
+}
+
 static struct cgroup_root *cgroup_root_from_kf(struct kernfs_root *kf_root)
 {
 	struct cgroup *root_cgrp = kf_root->kn->priv;
@@ -2066,9 +2105,9 @@ static void cgroup_task_migrate(struct cgroup *old_cgrp,
 	lockdep_assert_held(&css_set_rwsem);
 
 	/*
-	 * We are synchronized through cgroup_threadgroup_rwsem against
-	 * PF_EXITING setting such that we can't race against cgroup_exit()
-	 * changing the css_set to init_css_set and dropping the old one.
+	 * We are synchronized through threadgroup_lock() against PF_EXITING
+	 * setting such that we can't race against cgroup_exit() changing the
+	 * css_set to init_css_set and dropping the old one.
 	 */
 	WARN_ON_ONCE(tsk->flags & PF_EXITING);
 	old_cset = task_css_set(tsk);
@@ -2125,11 +2164,10 @@ static void cgroup_migrate_finish(struct list_head *preloaded_csets)
  * @src_cset and add it to @preloaded_csets, which should later be cleaned
  * up by cgroup_migrate_finish().
  *
- * This function may be called without holding cgroup_threadgroup_rwsem
- * even if the target is a process.  Threads may be created and destroyed
- * but as long as cgroup_mutex is not dropped, no new css_set can be put
- * into play and the preloaded css_sets are guaranteed to cover all
- * migrations.
+ * This function may be called without holding threadgroup_lock even if the
+ * target is a process.  Threads may be created and destroyed but as long
+ * as cgroup_mutex is not dropped, no new css_set can be put into play and
+ * the preloaded css_sets are guaranteed to cover all migrations.
  */
 static void cgroup_migrate_add_src(struct css_set *src_cset,
 				   struct cgroup *dst_cgrp,
@@ -2232,7 +2270,7 @@ err:
  * @threadgroup: whether @leader points to the whole process or a single task
  *
  * Migrate a process or task denoted by @leader to @cgrp.  If migrating a
- * process, the caller must be holding cgroup_threadgroup_rwsem.  The
+ * process, the caller must be holding threadgroup_lock of @leader.  The
  * caller is also responsible for invoking cgroup_migrate_add_src() and
  * cgroup_migrate_prepare_dst() on the targets before invoking this
  * function and following up with cgroup_migrate_finish().
@@ -2360,7 +2398,7 @@ out_release_tset:
  * @leader: the task or the leader of the threadgroup to be attached
  * @threadgroup: attach the whole threadgroup?
  *
- * Call holding cgroup_mutex and cgroup_threadgroup_rwsem.
+ * Call holding cgroup_mutex and threadgroup_lock of @leader.
  */
 static int cgroup_attach_task(struct cgroup *dst_cgrp,
 			      struct task_struct *leader, bool threadgroup)
@@ -2452,13 +2490,14 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	if (!cgrp)
 		return -ENODEV;
 
-	percpu_down_write(&cgroup_threadgroup_rwsem);
+retry_find_task:
 	rcu_read_lock();
 	if (pid) {
 		tsk = find_task_by_vpid(pid);
 		if (!tsk) {
+			rcu_read_unlock();
 			ret = -ESRCH;
-			goto out_unlock_rcu;
+			goto out_unlock_cgroup;
 		}
 	} else {
 		tsk = current;
@@ -2474,23 +2513,37 @@ static ssize_t __cgroup_procs_write(struct kernfs_open_file *of, char *buf,
 	 */
 	if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
 		ret = -EINVAL;
-		goto out_unlock_rcu;
+		rcu_read_unlock();
+		goto out_unlock_cgroup;
 	}
 
 	get_task_struct(tsk);
 	rcu_read_unlock();
 
+	threadgroup_lock(tsk);
+	if (threadgroup) {
+		if (!thread_group_leader(tsk)) {
+			/*
+			 * a race with de_thread from another thread's exec()
+			 * may strip us of our leadership, if this happens,
+			 * there is no choice but to throw this task away and
+			 * try again; this is
+			 * "double-double-toil-and-trouble-check locking".
+			 */
+			threadgroup_unlock(tsk);
+			put_task_struct(tsk);
+			goto retry_find_task;
+		}
+	}
+
 	ret = cgroup_procs_write_permission(tsk, cgrp, of);
 	if (!ret)
 		ret = cgroup_attach_task(cgrp, tsk, threadgroup);
 
-	put_task_struct(tsk);
-	goto out_unlock_threadgroup;
+	threadgroup_unlock(tsk);
 
-out_unlock_rcu:
-	rcu_read_unlock();
-out_unlock_threadgroup:
-	percpu_up_write(&cgroup_threadgroup_rwsem);
+	put_task_struct(tsk);
+out_unlock_cgroup:
 	cgroup_kn_unlock(of->kn);
 	return ret ?: nbytes;
 }
@@ -2635,8 +2688,6 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 
 	lockdep_assert_held(&cgroup_mutex);
 
-	percpu_down_write(&cgroup_threadgroup_rwsem);
-
 	/* look up all csses currently attached to @cgrp's subtree */
 	down_read(&css_set_rwsem);
 	css_for_each_descendant_pre(css, cgroup_css(cgrp, NULL)) {
@@ -2692,8 +2743,17 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 				goto out_finish;
 			last_task = task;
 
+			threadgroup_lock(task);
+			/* raced against de_thread() from another thread? */
+			if (!thread_group_leader(task)) {
+				threadgroup_unlock(task);
+				put_task_struct(task);
+				continue;
+			}
+
 			ret = cgroup_migrate(src_cset->dfl_cgrp, task, true);
 
+			threadgroup_unlock(task);
 			put_task_struct(task);
 
 			if (WARN(ret, "cgroup: failed to update controllers for the default hierarchy (%d), further operations may crash or hang\n", ret))
@@ -2703,7 +2763,6 @@ static int cgroup_update_dfl_csses(struct cgroup *cgrp)
 
 out_finish:
 	cgroup_migrate_finish(&preloaded_csets);
-	percpu_up_write(&cgroup_threadgroup_rwsem);
 	return ret;
 }
 
@@ -5013,7 +5072,6 @@ int __init cgroup_init(void)
 	unsigned long key;
 	int ssid, err;
 
-	BUG_ON(percpu_init_rwsem(&cgroup_threadgroup_rwsem));
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup_dfl_base_files));
 	BUG_ON(cgroup_init_cftypes(NULL, cgroup_legacy_base_files));
 
diff --git a/kernel/fork.c b/kernel/fork.c
index aef3961c4..45927e013 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1146,6 +1146,10 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	tty_audit_fork(sig);
 	sched_autogroup_fork(sig);
 
+#ifdef CONFIG_CGROUPS
+	init_rwsem(&sig->group_rwsem);
+#endif
+
 	sig->oom_score_adj = current->signal->oom_score_adj;
 	sig->oom_score_adj_min = current->signal->oom_score_adj_min;
 
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 0e97c142c..4e6267a34 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -12,6 +12,7 @@
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
+#include <linux/mutex.h>
 
 #include "internals.h"
 
@@ -323,18 +324,29 @@ void register_handler_proc(unsigned int irq, struct irqaction *action)
 
 void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 {
+	static DEFINE_MUTEX(register_lock);
 	char name [MAX_NAMELEN];
 
-	if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip) || desc->dir)
+	if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip))
 		return;
 
+	/*
+	 * irq directories are registered only when a handler is
+	 * added, not when the descriptor is created, so multiple
+	 * tasks might try to register at the same time.
+	 */
+	mutex_lock(&register_lock);
+
+	if (desc->dir)
+		goto out_unlock;
+
 	memset(name, 0, MAX_NAMELEN);
 	sprintf(name, "%d", irq);
 
 	/* create /proc/irq/1234 */
 	desc->dir = proc_mkdir(name, root_irq_dir);
 	if (!desc->dir)
-		return;
+		goto out_unlock;
 
 #ifdef CONFIG_SMP
 	/* create /proc/irq/<irq>/smp_affinity */
@@ -355,6 +367,9 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 
 	proc_create_data("spurious", 0444, desc->dir,
 			 &irq_spurious_proc_fops, (void *)(long)irq);
+
+out_unlock:
+	mutex_unlock(&register_lock);
 }
 
 void unregister_irq_proc(unsigned int irq, struct irq_desc *desc)
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 38c49202d..8ed01611a 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -289,7 +289,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	if (pv_enabled())
 		goto queue;
 
-	if (virt_queued_spin_lock(lock))
+	if (virt_spin_lock(lock))
 		return;
 
 	/*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e9673433c..677663167 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2461,11 +2461,11 @@ static struct rq *finish_task_switch(struct task_struct *prev)
 	 * If a task dies, then it sets TASK_DEAD in tsk->state and calls
 	 * schedule one last time. The schedule call will never return, and
 	 * the scheduled task must drop that reference.
-	 * The test for TASK_DEAD must occur while the runqueue locks are
-	 * still held, otherwise prev could be scheduled on another cpu, die
-	 * there before we look at prev->state, and then the reference would
-	 * be dropped twice.
-	 *		Manfred Spraul <manfred@colorfullife.com>
+	 *
+	 * We must observe prev->state before clearing prev->on_cpu (in
+	 * finish_lock_switch), otherwise a concurrent wakeup can get prev
+	 * running on another CPU and we could rave with its RUNNING -> DEAD
+	 * transition, resulting in a double drop.
 	 */
 	prev_state = prev->state;
 	vtime_task_switch(prev);
@@ -2614,13 +2614,20 @@ unsigned long nr_running(void)
 
 /*
  * Check if only the current task is running on the cpu.
+ *
+ * Caution: this function does not check that the caller has disabled
+ * preemption, thus the result might have a time-of-check-to-time-of-use
+ * race.  The caller is responsible to use it correctly, for example:
+ *
+ * - from a non-preemptable section (of course)
+ *
+ * - from a thread that is bound to a single CPU
+ *
+ * - in a loop with very short iterations (e.g. a polling loop)
  */
 bool single_task_running(void)
 {
-	if (cpu_rq(smp_processor_id())->nr_running == 1)
-		return true;
-	else
-		return false;
+	return raw_rq()->nr_running == 1;
 }
 EXPORT_SYMBOL(single_task_running);
 
@@ -4492,7 +4499,7 @@ SYSCALL_DEFINE0(sched_yield)
 
 int __sched _cond_resched(void)
 {
-	if (should_resched()) {
+	if (should_resched(0)) {
 		preempt_schedule_common();
 		return 1;
 	}
@@ -4510,7 +4517,7 @@ EXPORT_SYMBOL(_cond_resched);
  */
 int __cond_resched_lock(spinlock_t *lock)
 {
-	int resched = should_resched();
+	int resched = should_resched(PREEMPT_LOCK_OFFSET);
 	int ret = 0;
 
 	lockdep_assert_held(lock);
@@ -4532,7 +4539,7 @@ int __sched __cond_resched_softirq(void)
 {
 	BUG_ON(!in_softirq());
 
-	if (should_resched()) {
+	if (should_resched(SOFTIRQ_DISABLE_OFFSET)) {
 		local_bh_enable();
 		preempt_schedule_common();
 		local_bh_disable();
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 84d48790b..08ab96b36 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1091,9 +1091,10 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev)
 	 * After ->on_cpu is cleared, the task can be moved to a different CPU.
 	 * We must ensure this doesn't happen until the switch is completely
 	 * finished.
+	 *
+	 * Pairs with the control dependency and rmb in try_to_wake_up().
 	 */
-	smp_wmb();
-	prev->on_cpu = 0;
+	smp_store_release(&prev->on_cpu, 0);
 #endif
 #ifdef CONFIG_DEBUG_SPINLOCK
 	/* this is a valid case when another task releases the spinlock */
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index 841b72f72..3a38775b5 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -217,7 +217,7 @@ static void clocksource_watchdog(unsigned long data)
 			continue;
 
 		/* Check the deviation from the watchdog clocksource. */
-		if ((abs(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD)) {
+		if (abs64(cs_nsec - wd_nsec) > WATCHDOG_THRESHOLD) {
 			pr_warn("timekeeping watchdog: Marking clocksource '%s' as unstable because the skew is too large:\n",
 				cs->name);
 			pr_warn("                      '%s' wd_now: %llx wd_last: %llx mask: %llx\n",
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index bca3667a2..a20d4110e 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1607,7 +1607,7 @@ static __always_inline void timekeeping_freqadjust(struct timekeeper *tk,
 	negative = (tick_error < 0);
 
 	/* Sort out the magnitude of the correction */
-	tick_error = abs(tick_error);
+	tick_error = abs64(tick_error);
 	for (adj = 0; tick_error > interval; adj++)
 		tick_error >>= 1;
 
diff --git a/lib/iommu-common.c b/lib/iommu-common.c
index ff19f66d3..b1c93e94c 100644
--- a/lib/iommu-common.c
+++ b/lib/iommu-common.c
@@ -21,8 +21,7 @@ static	DEFINE_PER_CPU(unsigned int, iommu_hash_common);
 
 static inline bool need_flush(struct iommu_map_table *iommu)
 {
-	return (iommu->lazy_flush != NULL &&
-		(iommu->flags & IOMMU_NEED_FLUSH) != 0);
+	return ((iommu->flags & IOMMU_NEED_FLUSH) != 0);
 }
 
 static inline void set_flush(struct iommu_map_table *iommu)
@@ -211,7 +210,8 @@ unsigned long iommu_tbl_range_alloc(struct device *dev,
 			goto bail;
 		}
 	}
-	if (n < pool->hint || need_flush(iommu)) {
+	if (iommu->lazy_flush &&
+	    (n < pool->hint || need_flush(iommu))) {
 		clear_flush(iommu);
 		iommu->lazy_flush(iommu);
 	}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a8c308708..62c1ec5a9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2974,6 +2974,14 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 			continue;
 
 		/*
+		 * Shared VMAs have their own reserves and do not affect
+		 * MAP_PRIVATE accounting but it is possible that a shared
+		 * VMA is using the same page so check and skip such VMAs.
+		 */
+		if (iter_vma->vm_flags & VM_MAYSHARE)
+			continue;
+
+		/*
 		 * Unmap the page from other VMAs without their own reserves.
 		 * They get marked to be SIGKILLed if they fault in these
 		 * areas. This is because a future no-page fault on this VMA
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index acb93c554..237d46864 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -806,12 +806,14 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
 }
 
 /*
+ * Return page count for single (non recursive) @memcg.
+ *
  * Implementation Note: reading percpu statistics for memcg.
  *
  * Both of vmstat[] and percpu_counter has threshold and do periodic
  * synchronization to implement "quick" read. There are trade-off between
  * reading cost and precision of value. Then, we may have a chance to implement
- * a periodic synchronizion of counter in memcg's counter.
+ * a periodic synchronization of counter in memcg's counter.
  *
  * But this _read() function is used for user interface now. The user accounts
  * memory usage by memory cgroup and he _always_ requires exact value because
@@ -821,17 +823,24 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
  *
  * If there are kernel internal actions which can make use of some not-exact
  * value, and reading all cpu value can be performance bottleneck in some
- * common workload, threashold and synchonization as vmstat[] should be
+ * common workload, threshold and synchronization as vmstat[] should be
  * implemented.
  */
-static long mem_cgroup_read_stat(struct mem_cgroup *memcg,
-				 enum mem_cgroup_stat_index idx)
+static unsigned long
+mem_cgroup_read_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx)
 {
 	long val = 0;
 	int cpu;
 
+	/* Per-cpu values can be negative, use a signed accumulator */
 	for_each_possible_cpu(cpu)
 		val += per_cpu(memcg->stat->count[idx], cpu);
+	/*
+	 * Summing races with updates, so val may be negative.  Avoid exposing
+	 * transient negative values.
+	 */
+	if (val < 0)
+		val = 0;
 	return val;
 }
 
@@ -1498,7 +1507,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 		for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
 			if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 				continue;
-			pr_cont(" %s:%ldKB", mem_cgroup_stat_names[i],
+			pr_cont(" %s:%luKB", mem_cgroup_stat_names[i],
 				K(mem_cgroup_read_stat(iter, i)));
 		}
 
@@ -3119,14 +3128,11 @@ static unsigned long tree_stat(struct mem_cgroup *memcg,
 			       enum mem_cgroup_stat_index idx)
 {
 	struct mem_cgroup *iter;
-	long val = 0;
+	unsigned long val = 0;
 
-	/* Per-cpu values can be negative, use a signed accumulator */
 	for_each_mem_cgroup_tree(iter, memcg)
 		val += mem_cgroup_read_stat(iter, idx);
 
-	if (val < 0) /* race ? */
-		val = 0;
 	return val;
 }
 
@@ -3469,7 +3475,7 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
 		if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 			continue;
-		seq_printf(m, "%s %ld\n", mem_cgroup_stat_names[i],
+		seq_printf(m, "%s %lu\n", mem_cgroup_stat_names[i],
 			   mem_cgroup_read_stat(memcg, i) * PAGE_SIZE);
 	}
 
@@ -3494,13 +3500,13 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 			   (u64)memsw * PAGE_SIZE);
 
 	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
-		long long val = 0;
+		unsigned long long val = 0;
 
 		if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 			continue;
 		for_each_mem_cgroup_tree(mi, memcg)
 			val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE;
-		seq_printf(m, "total_%s %lld\n", mem_cgroup_stat_names[i], val);
+		seq_printf(m, "total_%s %llu\n", mem_cgroup_stat_names[i], val);
 	}
 
 	for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) {
diff --git a/mm/migrate.c b/mm/migrate.c
index eb4267107..fcb6204de 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -734,6 +734,15 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 	if (PageSwapBacked(page))
 		SetPageSwapBacked(newpage);
 
+	/*
+	 * Indirectly called below, migrate_page_copy() copies PG_dirty and thus
+	 * needs newpage's memcg set to transfer memcg dirty page accounting.
+	 * So perform memcg migration in two steps:
+	 * 1. set newpage->mem_cgroup (here)
+	 * 2. clear page->mem_cgroup (below)
+	 */
+	set_page_memcg(newpage, page_memcg(page));
+
 	mapping = page_mapping(page);
 	if (!mapping)
 		rc = migrate_page(mapping, newpage, page, mode);
@@ -750,9 +759,10 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 		rc = fallback_migrate_page(mapping, newpage, page, mode);
 
 	if (rc != MIGRATEPAGE_SUCCESS) {
+		set_page_memcg(newpage, NULL);
 		newpage->mapping = NULL;
 	} else {
-		mem_cgroup_migrate(page, newpage, false);
+		set_page_memcg(page, NULL);
 		if (page_was_mapped)
 			remove_migration_ptes(page, newpage);
 		page->mapping = NULL;
@@ -1068,7 +1078,7 @@ out:
 	if (rc != MIGRATEPAGE_SUCCESS && put_new_page)
 		put_new_page(new_hpage, private);
 	else
-		put_page(new_hpage);
+		putback_active_hugepage(new_hpage);
 
 	if (result) {
 		if (rc)
diff --git a/mm/slab.c b/mm/slab.c
index bbd0b47dc..ae3602830 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2190,9 +2190,16 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 			size += BYTES_PER_WORD;
 	}
 #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
-	if (size >= kmalloc_size(INDEX_NODE + 1)
-	    && cachep->object_size > cache_line_size()
-	    && ALIGN(size, cachep->align) < PAGE_SIZE) {
+	/*
+	 * To activate debug pagealloc, off-slab management is necessary
+	 * requirement. In early phase of initialization, small sized slab
+	 * doesn't get initialized so it would not be possible. So, we need
+	 * to check size >= 256. It guarantees that all necessary small
+	 * sized slab is initialized in current slab initialization sequence.
+	 */
+	if (!slab_early_init && size >= kmalloc_size(INDEX_NODE) &&
+		size >= 256 && cachep->object_size > cache_line_size() &&
+		ALIGN(size, cachep->align) < PAGE_SIZE) {
 		cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align);
 		size = PAGE_SIZE;
 	}
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index 6d0b471ee..cc7d87d64 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -19,6 +19,7 @@
 #include "main.h"
 
 #include <linux/atomic.h>
+#include <linux/bitops.h>
 #include <linux/byteorder/generic.h>
 #include <linux/errno.h>
 #include <linux/etherdevice.h>
@@ -453,7 +454,7 @@ static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res,
 	int j;
 
 	/* check if orig node candidate is running DAT */
-	if (!(candidate->capabilities & BATADV_ORIG_CAPA_HAS_DAT))
+	if (!test_bit(BATADV_ORIG_CAPA_HAS_DAT, &candidate->capabilities))
 		goto out;
 
 	/* Check if this node has already been selected... */
@@ -713,9 +714,9 @@ static void batadv_dat_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
 					   uint16_t tvlv_value_len)
 {
 	if (flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND)
-		orig->capabilities &= ~BATADV_ORIG_CAPA_HAS_DAT;
+		clear_bit(BATADV_ORIG_CAPA_HAS_DAT, &orig->capabilities);
 	else
-		orig->capabilities |= BATADV_ORIG_CAPA_HAS_DAT;
+		set_bit(BATADV_ORIG_CAPA_HAS_DAT, &orig->capabilities);
 }
 
 /**
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index 7aa480b7e..68a955496 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -19,6 +19,8 @@
 #include "main.h"
 
 #include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/bug.h>
 #include <linux/byteorder/generic.h>
 #include <linux/errno.h>
 #include <linux/etherdevice.h>
@@ -588,19 +590,26 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
  *
  * If the BATADV_MCAST_WANT_ALL_UNSNOOPABLES flag of this originator,
  * orig, has toggled then this method updates counter and list accordingly.
+ *
+ * Caller needs to hold orig->mcast_handler_lock.
  */
 static void batadv_mcast_want_unsnoop_update(struct batadv_priv *bat_priv,
 					     struct batadv_orig_node *orig,
 					     uint8_t mcast_flags)
 {
+	struct hlist_node *node = &orig->mcast_want_all_unsnoopables_node;
+	struct hlist_head *head = &bat_priv->mcast.want_all_unsnoopables_list;
+
 	/* switched from flag unset to set */
 	if (mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES &&
 	    !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES)) {
 		atomic_inc(&bat_priv->mcast.num_want_all_unsnoopables);
 
 		spin_lock_bh(&bat_priv->mcast.want_lists_lock);
-		hlist_add_head_rcu(&orig->mcast_want_all_unsnoopables_node,
-				   &bat_priv->mcast.want_all_unsnoopables_list);
+		/* flag checks above + mcast_handler_lock prevents this */
+		WARN_ON(!hlist_unhashed(node));
+
+		hlist_add_head_rcu(node, head);
 		spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
 	/* switched from flag set to unset */
 	} else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_UNSNOOPABLES) &&
@@ -608,7 +617,10 @@ static void batadv_mcast_want_unsnoop_update(struct batadv_priv *bat_priv,
 		atomic_dec(&bat_priv->mcast.num_want_all_unsnoopables);
 
 		spin_lock_bh(&bat_priv->mcast.want_lists_lock);
-		hlist_del_rcu(&orig->mcast_want_all_unsnoopables_node);
+		/* flag checks above + mcast_handler_lock prevents this */
+		WARN_ON(hlist_unhashed(node));
+
+		hlist_del_init_rcu(node);
 		spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
 	}
 }
@@ -621,19 +633,26 @@ static void batadv_mcast_want_unsnoop_update(struct batadv_priv *bat_priv,
  *
  * If the BATADV_MCAST_WANT_ALL_IPV4 flag of this originator, orig, has
  * toggled then this method updates counter and list accordingly.
+ *
+ * Caller needs to hold orig->mcast_handler_lock.
  */
 static void batadv_mcast_want_ipv4_update(struct batadv_priv *bat_priv,
 					  struct batadv_orig_node *orig,
 					  uint8_t mcast_flags)
 {
+	struct hlist_node *node = &orig->mcast_want_all_ipv4_node;
+	struct hlist_head *head = &bat_priv->mcast.want_all_ipv4_list;
+
 	/* switched from flag unset to set */
 	if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV4 &&
 	    !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV4)) {
 		atomic_inc(&bat_priv->mcast.num_want_all_ipv4);
 
 		spin_lock_bh(&bat_priv->mcast.want_lists_lock);
-		hlist_add_head_rcu(&orig->mcast_want_all_ipv4_node,
-				   &bat_priv->mcast.want_all_ipv4_list);
+		/* flag checks above + mcast_handler_lock prevents this */
+		WARN_ON(!hlist_unhashed(node));
+
+		hlist_add_head_rcu(node, head);
 		spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
 	/* switched from flag set to unset */
 	} else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_IPV4) &&
@@ -641,7 +660,10 @@ static void batadv_mcast_want_ipv4_update(struct batadv_priv *bat_priv,
 		atomic_dec(&bat_priv->mcast.num_want_all_ipv4);
 
 		spin_lock_bh(&bat_priv->mcast.want_lists_lock);
-		hlist_del_rcu(&orig->mcast_want_all_ipv4_node);
+		/* flag checks above + mcast_handler_lock prevents this */
+		WARN_ON(hlist_unhashed(node));
+
+		hlist_del_init_rcu(node);
 		spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
 	}
 }
@@ -654,19 +676,26 @@ static void batadv_mcast_want_ipv4_update(struct batadv_priv *bat_priv,
  *
  * If the BATADV_MCAST_WANT_ALL_IPV6 flag of this originator, orig, has
  * toggled then this method updates counter and list accordingly.
+ *
+ * Caller needs to hold orig->mcast_handler_lock.
  */
 static void batadv_mcast_want_ipv6_update(struct batadv_priv *bat_priv,
 					  struct batadv_orig_node *orig,
 					  uint8_t mcast_flags)
 {
+	struct hlist_node *node = &orig->mcast_want_all_ipv6_node;
+	struct hlist_head *head = &bat_priv->mcast.want_all_ipv6_list;
+
 	/* switched from flag unset to set */
 	if (mcast_flags & BATADV_MCAST_WANT_ALL_IPV6 &&
 	    !(orig->mcast_flags & BATADV_MCAST_WANT_ALL_IPV6)) {
 		atomic_inc(&bat_priv->mcast.num_want_all_ipv6);
 
 		spin_lock_bh(&bat_priv->mcast.want_lists_lock);
-		hlist_add_head_rcu(&orig->mcast_want_all_ipv6_node,
-				   &bat_priv->mcast.want_all_ipv6_list);
+		/* flag checks above + mcast_handler_lock prevents this */
+		WARN_ON(!hlist_unhashed(node));
+
+		hlist_add_head_rcu(node, head);
 		spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
 	/* switched from flag set to unset */
 	} else if (!(mcast_flags & BATADV_MCAST_WANT_ALL_IPV6) &&
@@ -674,7 +703,10 @@ static void batadv_mcast_want_ipv6_update(struct batadv_priv *bat_priv,
 		atomic_dec(&bat_priv->mcast.num_want_all_ipv6);
 
 		spin_lock_bh(&bat_priv->mcast.want_lists_lock);
-		hlist_del_rcu(&orig->mcast_want_all_ipv6_node);
+		/* flag checks above + mcast_handler_lock prevents this */
+		WARN_ON(hlist_unhashed(node));
+
+		hlist_del_init_rcu(node);
 		spin_unlock_bh(&bat_priv->mcast.want_lists_lock);
 	}
 }
@@ -697,39 +729,42 @@ static void batadv_mcast_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
 	uint8_t mcast_flags = BATADV_NO_FLAGS;
 	bool orig_initialized;
 
-	orig_initialized = orig->capa_initialized & BATADV_ORIG_CAPA_HAS_MCAST;
+	if (orig_mcast_enabled && tvlv_value &&
+	    (tvlv_value_len >= sizeof(mcast_flags)))
+		mcast_flags = *(uint8_t *)tvlv_value;
+
+	spin_lock_bh(&orig->mcast_handler_lock);
+	orig_initialized = test_bit(BATADV_ORIG_CAPA_HAS_MCAST,
+				    &orig->capa_initialized);
 
 	/* If mcast support is turned on decrease the disabled mcast node
 	 * counter only if we had increased it for this node before. If this
 	 * is a completely new orig_node no need to decrease the counter.
 	 */
 	if (orig_mcast_enabled &&
-	    !(orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST)) {
+	    !test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities)) {
 		if (orig_initialized)
 			atomic_dec(&bat_priv->mcast.num_disabled);
-		orig->capabilities |= BATADV_ORIG_CAPA_HAS_MCAST;
+		set_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities);
 	/* If mcast support is being switched off or if this is an initial
 	 * OGM without mcast support then increase the disabled mcast
 	 * node counter.
 	 */
 	} else if (!orig_mcast_enabled &&
-		   (orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST ||
+		   (test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities) ||
 		    !orig_initialized)) {
 		atomic_inc(&bat_priv->mcast.num_disabled);
-		orig->capabilities &= ~BATADV_ORIG_CAPA_HAS_MCAST;
+		clear_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities);
 	}
 
-	orig->capa_initialized |= BATADV_ORIG_CAPA_HAS_MCAST;
-
-	if (orig_mcast_enabled && tvlv_value &&
-	    (tvlv_value_len >= sizeof(mcast_flags)))
-		mcast_flags = *(uint8_t *)tvlv_value;
+	set_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capa_initialized);
 
 	batadv_mcast_want_unsnoop_update(bat_priv, orig, mcast_flags);
 	batadv_mcast_want_ipv4_update(bat_priv, orig, mcast_flags);
 	batadv_mcast_want_ipv6_update(bat_priv, orig, mcast_flags);
 
 	orig->mcast_flags = mcast_flags;
+	spin_unlock_bh(&orig->mcast_handler_lock);
 }
 
 /**
@@ -763,11 +798,15 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig)
 {
 	struct batadv_priv *bat_priv = orig->bat_priv;
 
-	if (!(orig->capabilities & BATADV_ORIG_CAPA_HAS_MCAST) &&
-	    orig->capa_initialized & BATADV_ORIG_CAPA_HAS_MCAST)
+	spin_lock_bh(&orig->mcast_handler_lock);
+
+	if (!test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capabilities) &&
+	    test_bit(BATADV_ORIG_CAPA_HAS_MCAST, &orig->capa_initialized))
 		atomic_dec(&bat_priv->mcast.num_disabled);
 
 	batadv_mcast_want_unsnoop_update(bat_priv, orig, BATADV_NO_FLAGS);
 	batadv_mcast_want_ipv4_update(bat_priv, orig, BATADV_NO_FLAGS);
 	batadv_mcast_want_ipv6_update(bat_priv, orig, BATADV_NO_FLAGS);
+
+	spin_unlock_bh(&orig->mcast_handler_lock);
 }
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index f0a50f31d..46604010d 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -19,6 +19,7 @@
 #include "main.h"
 
 #include <linux/atomic.h>
+#include <linux/bitops.h>
 #include <linux/byteorder/generic.h>
 #include <linux/compiler.h>
 #include <linux/debugfs.h>
@@ -134,9 +135,9 @@ static void batadv_nc_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
 					  uint16_t tvlv_value_len)
 {
 	if (flags & BATADV_TVLV_HANDLER_OGM_CIFNOTFND)
-		orig->capabilities &= ~BATADV_ORIG_CAPA_HAS_NC;
+		clear_bit(BATADV_ORIG_CAPA_HAS_NC, &orig->capabilities);
 	else
-		orig->capabilities |= BATADV_ORIG_CAPA_HAS_NC;
+		set_bit(BATADV_ORIG_CAPA_HAS_NC, &orig->capabilities);
 }
 
 /**
@@ -894,7 +895,7 @@ void batadv_nc_update_nc_node(struct batadv_priv *bat_priv,
 		goto out;
 
 	/* check if orig node is network coding enabled */
-	if (!(orig_node->capabilities & BATADV_ORIG_CAPA_HAS_NC))
+	if (!test_bit(BATADV_ORIG_CAPA_HAS_NC, &orig_node->capabilities))
 		goto out;
 
 	/* accept ogms from 'good' neighbors and single hop neighbors */
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 018b7495a..32a0fcfab 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -696,8 +696,13 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
 	orig_node->last_seen = jiffies;
 	reset_time = jiffies - 1 - msecs_to_jiffies(BATADV_RESET_PROTECTION_MS);
 	orig_node->bcast_seqno_reset = reset_time;
+
 #ifdef CONFIG_BATMAN_ADV_MCAST
 	orig_node->mcast_flags = BATADV_NO_FLAGS;
+	INIT_HLIST_NODE(&orig_node->mcast_want_all_unsnoopables_node);
+	INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv4_node);
+	INIT_HLIST_NODE(&orig_node->mcast_want_all_ipv6_node);
+	spin_lock_init(&orig_node->mcast_handler_lock);
 #endif
 
 	/* create a vlan object for the "untagged" LAN */
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index a2fc843c2..51cda3a7c 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -202,6 +202,7 @@ static int batadv_interface_tx(struct sk_buff *skb,
 	int gw_mode;
 	enum batadv_forw_mode forw_mode;
 	struct batadv_orig_node *mcast_single_orig = NULL;
+	int network_offset = ETH_HLEN;
 
 	if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE)
 		goto dropped;
@@ -214,14 +215,18 @@ static int batadv_interface_tx(struct sk_buff *skb,
 	case ETH_P_8021Q:
 		vhdr = vlan_eth_hdr(skb);
 
-		if (vhdr->h_vlan_encapsulated_proto != ethertype)
+		if (vhdr->h_vlan_encapsulated_proto != ethertype) {
+			network_offset += VLAN_HLEN;
 			break;
+		}
 
 		/* fall through */
 	case ETH_P_BATMAN:
 		goto dropped;
 	}
 
+	skb_set_network_header(skb, network_offset);
+
 	if (batadv_bla_tx(bat_priv, skb, vid))
 		goto dropped;
 
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index 5809b39c1..c9b26291a 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -19,6 +19,7 @@
 #include "main.h"
 
 #include <linux/atomic.h>
+#include <linux/bitops.h>
 #include <linux/bug.h>
 #include <linux/byteorder/generic.h>
 #include <linux/compiler.h>
@@ -1882,7 +1883,7 @@ void batadv_tt_global_del_orig(struct batadv_priv *bat_priv,
 		}
 		spin_unlock_bh(list_lock);
 	}
-	orig_node->capa_initialized &= ~BATADV_ORIG_CAPA_HAS_TT;
+	clear_bit(BATADV_ORIG_CAPA_HAS_TT, &orig_node->capa_initialized);
 }
 
 static bool batadv_tt_global_to_purge(struct batadv_tt_global_entry *tt_global,
@@ -2841,7 +2842,7 @@ static void _batadv_tt_update_changes(struct batadv_priv *bat_priv,
 				return;
 		}
 	}
-	orig_node->capa_initialized |= BATADV_ORIG_CAPA_HAS_TT;
+	set_bit(BATADV_ORIG_CAPA_HAS_TT, &orig_node->capa_initialized);
 }
 
 static void batadv_tt_fill_gtable(struct batadv_priv *bat_priv,
@@ -3343,7 +3344,8 @@ static void batadv_tt_update_orig(struct batadv_priv *bat_priv,
 	bool has_tt_init;
 
 	tt_vlan = (struct batadv_tvlv_tt_vlan_data *)tt_buff;
-	has_tt_init = orig_node->capa_initialized & BATADV_ORIG_CAPA_HAS_TT;
+	has_tt_init = test_bit(BATADV_ORIG_CAPA_HAS_TT,
+			       &orig_node->capa_initialized);
 
 	/* orig table not initialised AND first diff is in the OGM OR the ttvn
 	 * increased by one -> we can apply the attached changes
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 67d634836..55610a805 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -221,6 +221,7 @@ struct batadv_orig_bat_iv {
  * @batadv_dat_addr_t:  address of the orig node in the distributed hash
  * @last_seen: time when last packet from this node was received
  * @bcast_seqno_reset: time when the broadcast seqno window was reset
+ * @mcast_handler_lock: synchronizes mcast-capability and -flag changes
  * @mcast_flags: multicast flags announced by the orig node
  * @mcast_want_all_unsnoop_node: a list node for the
  *  mcast.want_all_unsnoopables list
@@ -268,13 +269,15 @@ struct batadv_orig_node {
 	unsigned long last_seen;
 	unsigned long bcast_seqno_reset;
 #ifdef CONFIG_BATMAN_ADV_MCAST
+	/* synchronizes mcast tvlv specific orig changes */
+	spinlock_t mcast_handler_lock;
 	uint8_t mcast_flags;
 	struct hlist_node mcast_want_all_unsnoopables_node;
 	struct hlist_node mcast_want_all_ipv4_node;
 	struct hlist_node mcast_want_all_ipv6_node;
 #endif
-	uint8_t capabilities;
-	uint8_t capa_initialized;
+	unsigned long capabilities;
+	unsigned long capa_initialized;
 	atomic_t last_ttvn;
 	unsigned char *tt_buff;
 	int16_t tt_buff_len;
@@ -313,10 +316,10 @@ struct batadv_orig_node {
  *  (= orig node announces a tvlv of type BATADV_TVLV_MCAST)
  */
 enum batadv_orig_capabilities {
-	BATADV_ORIG_CAPA_HAS_DAT = BIT(0),
-	BATADV_ORIG_CAPA_HAS_NC = BIT(1),
-	BATADV_ORIG_CAPA_HAS_TT = BIT(2),
-	BATADV_ORIG_CAPA_HAS_MCAST = BIT(3),
+	BATADV_ORIG_CAPA_HAS_DAT,
+	BATADV_ORIG_CAPA_HAS_NC,
+	BATADV_ORIG_CAPA_HAS_TT,
+	BATADV_ORIG_CAPA_HAS_MCAST,
 };
 
 /**
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index ad82324f7..0510a577a 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -2311,12 +2311,6 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 	if (!conn)
 		return 1;
 
-	chan = conn->smp;
-	if (!chan) {
-		BT_ERR("SMP security requested but not available");
-		return 1;
-	}
-
 	if (!hci_dev_test_flag(hcon->hdev, HCI_LE_ENABLED))
 		return 1;
 
@@ -2330,6 +2324,12 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 		if (smp_ltk_encrypt(conn, hcon->pending_sec_level))
 			return 0;
 
+	chan = conn->smp;
+	if (!chan) {
+		BT_ERR("SMP security requested but not available");
+		return 1;
+	}
+
 	l2cap_chan_lock(chan);
 
 	/* If SMP is already in progress ignore this request */
diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h
index afe905c20..691b54fca 100644
--- a/net/netfilter/ipset/ip_set_hash_gen.h
+++ b/net/netfilter/ipset/ip_set_hash_gen.h
@@ -152,9 +152,13 @@ htable_bits(u32 hashsize)
 #define SET_HOST_MASK(family)	(family == AF_INET ? 32 : 128)
 
 #ifdef IP_SET_HASH_WITH_NET0
+/* cidr from 0 to SET_HOST_MASK() value and c = cidr + 1 */
 #define NLEN(family)		(SET_HOST_MASK(family) + 1)
+#define CIDR_POS(c)		((c) - 1)
 #else
+/* cidr from 1 to SET_HOST_MASK() value and c = cidr + 1 */
 #define NLEN(family)		SET_HOST_MASK(family)
+#define CIDR_POS(c)		((c) - 2)
 #endif
 
 #else
@@ -305,7 +309,7 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
 		} else if (h->nets[i].cidr[n] < cidr) {
 			j = i;
 		} else if (h->nets[i].cidr[n] == cidr) {
-			h->nets[cidr - 1].nets[n]++;
+			h->nets[CIDR_POS(cidr)].nets[n]++;
 			return;
 		}
 	}
@@ -314,7 +318,7 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
 			h->nets[i].cidr[n] = h->nets[i - 1].cidr[n];
 	}
 	h->nets[i].cidr[n] = cidr;
-	h->nets[cidr - 1].nets[n] = 1;
+	h->nets[CIDR_POS(cidr)].nets[n] = 1;
 }
 
 static void
@@ -325,8 +329,8 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 nets_length, u8 n)
 	for (i = 0; i < nets_length; i++) {
 		if (h->nets[i].cidr[n] != cidr)
 			continue;
-		h->nets[cidr - 1].nets[n]--;
-		if (h->nets[cidr - 1].nets[n] > 0)
+		h->nets[CIDR_POS(cidr)].nets[n]--;
+		if (h->nets[CIDR_POS(cidr)].nets[n] > 0)
 			return;
 		for (j = i; j < net_end && h->nets[j].cidr[n]; j++)
 			h->nets[j].cidr[n] = h->nets[j + 1].cidr[n];
diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c
index 3c862c0a7..a93dfebff 100644
--- a/net/netfilter/ipset/ip_set_hash_netnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netnet.c
@@ -131,6 +131,13 @@ hash_netnet4_data_next(struct hash_netnet4_elem *next,
 #define HOST_MASK	32
 #include "ip_set_hash_gen.h"
 
+static void
+hash_netnet4_init(struct hash_netnet4_elem *e)
+{
+	e->cidr[0] = HOST_MASK;
+	e->cidr[1] = HOST_MASK;
+}
+
 static int
 hash_netnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
 		  const struct xt_action_param *par,
@@ -160,7 +167,7 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 {
 	const struct hash_netnet *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_netnet4_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, };
+	struct hash_netnet4_elem e = { };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 ip = 0, ip_to = 0, last;
 	u32 ip2 = 0, ip2_from = 0, ip2_to = 0, last2;
@@ -169,6 +176,7 @@ hash_netnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 	if (tb[IPSET_ATTR_LINENO])
 		*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
 
+	hash_netnet4_init(&e);
 	if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
 		     !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
 		return -IPSET_ERR_PROTOCOL;
@@ -357,6 +365,13 @@ hash_netnet6_data_next(struct hash_netnet4_elem *next,
 #define IP_SET_EMIT_CREATE
 #include "ip_set_hash_gen.h"
 
+static void
+hash_netnet6_init(struct hash_netnet6_elem *e)
+{
+	e->cidr[0] = HOST_MASK;
+	e->cidr[1] = HOST_MASK;
+}
+
 static int
 hash_netnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
 		  const struct xt_action_param *par,
@@ -385,13 +400,14 @@ hash_netnet6_uadt(struct ip_set *set, struct nlattr *tb[],
 		  enum ipset_adt adt, u32 *lineno, u32 flags, bool retried)
 {
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_netnet6_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, };
+	struct hash_netnet6_elem e = { };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	int ret;
 
 	if (tb[IPSET_ATTR_LINENO])
 		*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
 
+	hash_netnet6_init(&e);
 	if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
 		     !ip_set_optattr_netorder(tb, IPSET_ATTR_CADT_FLAGS)))
 		return -IPSET_ERR_PROTOCOL;
diff --git a/net/netfilter/ipset/ip_set_hash_netportnet.c b/net/netfilter/ipset/ip_set_hash_netportnet.c
index 0c68734f5..9a14c2378 100644
--- a/net/netfilter/ipset/ip_set_hash_netportnet.c
+++ b/net/netfilter/ipset/ip_set_hash_netportnet.c
@@ -142,6 +142,13 @@ hash_netportnet4_data_next(struct hash_netportnet4_elem *next,
 #define HOST_MASK	32
 #include "ip_set_hash_gen.h"
 
+static void
+hash_netportnet4_init(struct hash_netportnet4_elem *e)
+{
+	e->cidr[0] = HOST_MASK;
+	e->cidr[1] = HOST_MASK;
+}
+
 static int
 hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb,
 		      const struct xt_action_param *par,
@@ -175,7 +182,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 {
 	const struct hash_netportnet *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_netportnet4_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, };
+	struct hash_netportnet4_elem e = { };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 ip = 0, ip_to = 0, ip_last, p = 0, port, port_to;
 	u32 ip2_from = 0, ip2_to = 0, ip2_last, ip2;
@@ -185,6 +192,7 @@ hash_netportnet4_uadt(struct ip_set *set, struct nlattr *tb[],
 	if (tb[IPSET_ATTR_LINENO])
 		*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
 
+	hash_netportnet4_init(&e);
 	if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
 		     !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
 		     !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
@@ -412,6 +420,13 @@ hash_netportnet6_data_next(struct hash_netportnet4_elem *next,
 #define IP_SET_EMIT_CREATE
 #include "ip_set_hash_gen.h"
 
+static void
+hash_netportnet6_init(struct hash_netportnet6_elem *e)
+{
+	e->cidr[0] = HOST_MASK;
+	e->cidr[1] = HOST_MASK;
+}
+
 static int
 hash_netportnet6_kadt(struct ip_set *set, const struct sk_buff *skb,
 		      const struct xt_action_param *par,
@@ -445,7 +460,7 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
 {
 	const struct hash_netportnet *h = set->data;
 	ipset_adtfn adtfn = set->variant->adt[adt];
-	struct hash_netportnet6_elem e = { .cidr = { HOST_MASK, HOST_MASK, }, };
+	struct hash_netportnet6_elem e = { };
 	struct ip_set_ext ext = IP_SET_INIT_UEXT(set);
 	u32 port, port_to;
 	bool with_ports = false;
@@ -454,6 +469,7 @@ hash_netportnet6_uadt(struct ip_set *set, struct nlattr *tb[],
 	if (tb[IPSET_ATTR_LINENO])
 		*lineno = nla_get_u32(tb[IPSET_ATTR_LINENO]);
 
+	hash_netportnet6_init(&e);
 	if (unlikely(!tb[IPSET_ATTR_IP] || !tb[IPSET_ATTR_IP2] ||
 		     !ip_set_attr_netorder(tb, IPSET_ATTR_PORT) ||
 		     !ip_set_optattr_netorder(tb, IPSET_ATTR_PORT_TO) ||
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 675d12c69..a5d41dfa9 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -107,12 +107,17 @@ EXPORT_SYMBOL(nf_log_register);
 
 void nf_log_unregister(struct nf_logger *logger)
 {
+	const struct nf_logger *log;
 	int i;
 
 	mutex_lock(&nf_log_mutex);
-	for (i = 0; i < NFPROTO_NUMPROTO; i++)
-		RCU_INIT_POINTER(loggers[i][logger->type], NULL);
+	for (i = 0; i < NFPROTO_NUMPROTO; i++) {
+		log = nft_log_dereference(loggers[i][logger->type]);
+		if (log == logger)
+			RCU_INIT_POINTER(loggers[i][logger->type], NULL);
+	}
 	mutex_unlock(&nf_log_mutex);
+	synchronize_rcu();
 }
 EXPORT_SYMBOL(nf_log_unregister);
 
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 0c0e8ecf0..70277b11f 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -444,6 +444,7 @@ done:
 static void nfnetlink_rcv(struct sk_buff *skb)
 {
 	struct nlmsghdr *nlh = nlmsg_hdr(skb);
+	u_int16_t res_id;
 	int msglen;
 
 	if (nlh->nlmsg_len < NLMSG_HDRLEN ||
@@ -468,7 +469,12 @@ static void nfnetlink_rcv(struct sk_buff *skb)
 
 		nfgenmsg = nlmsg_data(nlh);
 		skb_pull(skb, msglen);
-		nfnetlink_rcv_batch(skb, nlh, nfgenmsg->res_id);
+		/* Work around old nft using host byte order */
+		if (nfgenmsg->res_id == NFNL_SUBSYS_NFTABLES)
+			res_id = NFNL_SUBSYS_NFTABLES;
+		else
+			res_id = ntohs(nfgenmsg->res_id);
+		nfnetlink_rcv_batch(skb, nlh, res_id);
 	} else {
 		netlink_rcv_skb(skb, &nfnetlink_rcv_msg);
 	}
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 66def315e..9c8fab001 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -619,6 +619,13 @@ struct nft_xt {
 
 static struct nft_expr_type nft_match_type;
 
+static bool nft_match_cmp(const struct xt_match *match,
+			  const char *name, u32 rev, u32 family)
+{
+	return strcmp(match->name, name) == 0 && match->revision == rev &&
+	       (match->family == NFPROTO_UNSPEC || match->family == family);
+}
+
 static const struct nft_expr_ops *
 nft_match_select_ops(const struct nft_ctx *ctx,
 		     const struct nlattr * const tb[])
@@ -626,7 +633,7 @@ nft_match_select_ops(const struct nft_ctx *ctx,
 	struct nft_xt *nft_match;
 	struct xt_match *match;
 	char *mt_name;
-	__u32 rev, family;
+	u32 rev, family;
 
 	if (tb[NFTA_MATCH_NAME] == NULL ||
 	    tb[NFTA_MATCH_REV] == NULL ||
@@ -641,8 +648,7 @@ nft_match_select_ops(const struct nft_ctx *ctx,
 	list_for_each_entry(nft_match, &nft_match_list, head) {
 		struct xt_match *match = nft_match->ops.data;
 
-		if (strcmp(match->name, mt_name) == 0 &&
-		    match->revision == rev && match->family == family) {
+		if (nft_match_cmp(match, mt_name, rev, family)) {
 			if (!try_module_get(match->me))
 				return ERR_PTR(-ENOENT);
 
@@ -693,6 +699,13 @@ static LIST_HEAD(nft_target_list);
 
 static struct nft_expr_type nft_target_type;
 
+static bool nft_target_cmp(const struct xt_target *tg,
+			   const char *name, u32 rev, u32 family)
+{
+	return strcmp(tg->name, name) == 0 && tg->revision == rev &&
+	       (tg->family == NFPROTO_UNSPEC || tg->family == family);
+}
+
 static const struct nft_expr_ops *
 nft_target_select_ops(const struct nft_ctx *ctx,
 		      const struct nlattr * const tb[])
@@ -700,7 +713,7 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 	struct nft_xt *nft_target;
 	struct xt_target *target;
 	char *tg_name;
-	__u32 rev, family;
+	u32 rev, family;
 
 	if (tb[NFTA_TARGET_NAME] == NULL ||
 	    tb[NFTA_TARGET_REV] == NULL ||
@@ -715,8 +728,7 @@ nft_target_select_ops(const struct nft_ctx *ctx,
 	list_for_each_entry(nft_target, &nft_target_list, head) {
 		struct xt_target *target = nft_target->ops.data;
 
-		if (strcmp(target->name, tg_name) == 0 &&
-		    target->revision == rev && target->family == family) {
+		if (nft_target_cmp(target, tg_name, rev, family)) {
 			if (!try_module_get(target->me))
 				return ERR_PTR(-ENOENT);
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index d25cd430f..95412abc9 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -384,6 +384,7 @@ static int send_reply(struct svcxprt_rdma *rdma,
 		      int byte_count)
 {
 	struct ib_send_wr send_wr;
+	u32 xdr_off;
 	int sge_no;
 	int sge_bytes;
 	int page_no;
@@ -418,8 +419,8 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	ctxt->direction = DMA_TO_DEVICE;
 
 	/* Map the payload indicated by 'byte_count' */
+	xdr_off = 0;
 	for (sge_no = 1; byte_count && sge_no < vec->count; sge_no++) {
-		int xdr_off = 0;
 		sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count);
 		byte_count -= sge_bytes;
 		ctxt->sge[sge_no].addr =
@@ -457,6 +458,13 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	}
 	rqstp->rq_next_page = rqstp->rq_respages + 1;
 
+	/* The loop above bumps sc_dma_used for each sge. The
+	 * xdr_buf.tail gets a separate sge, but resides in the
+	 * same page as xdr_buf.head. Don't count it twice.
+	 */
+	if (sge_no > ctxt->count)
+		atomic_dec(&rdma->sc_dma_used);
+
 	if (sge_no > rdma->sc_max_sge) {
 		pr_err("svcrdma: Too many sges (%d)\n", sge_no);
 		goto err;
diff --git a/sound/arm/Kconfig b/sound/arm/Kconfig
index 885683a3b..e04062117 100644
--- a/sound/arm/Kconfig
+++ b/sound/arm/Kconfig
@@ -9,6 +9,14 @@ menuconfig SND_ARM
 	  Drivers that are implemented on ASoC can be found in
 	  "ALSA for SoC audio support" section.
 
+config SND_PXA2XX_LIB
+	tristate
+	select SND_AC97_CODEC if SND_PXA2XX_LIB_AC97
+	select SND_DMAENGINE_PCM
+
+config SND_PXA2XX_LIB_AC97
+	bool
+
 if SND_ARM
 
 config SND_ARMAACI
@@ -21,13 +29,6 @@ config SND_PXA2XX_PCM
 	tristate
 	select SND_PCM
 
-config SND_PXA2XX_LIB
-	tristate
-	select SND_AC97_CODEC if SND_PXA2XX_LIB_AC97
-
-config SND_PXA2XX_LIB_AC97
-	bool
-
 config SND_PXA2XX_AC97
 	tristate "AC97 driver for the Intel PXA2xx chip"
 	depends on ARCH_PXA
diff --git a/sound/pci/hda/hda_tegra.c b/sound/pci/hda/hda_tegra.c
index 477742cb7..58c0aad37 100644
--- a/sound/pci/hda/hda_tegra.c
+++ b/sound/pci/hda/hda_tegra.c
@@ -73,6 +73,7 @@ struct hda_tegra {
 	struct clk *hda2codec_2x_clk;
 	struct clk *hda2hdmi_clk;
 	void __iomem *regs;
+	struct work_struct probe_work;
 };
 
 #ifdef CONFIG_PM
@@ -294,7 +295,9 @@ static int hda_tegra_dev_disconnect(struct snd_device *device)
 static int hda_tegra_dev_free(struct snd_device *device)
 {
 	struct azx *chip = device->device_data;
+	struct hda_tegra *hda = container_of(chip, struct hda_tegra, chip);
 
+	cancel_work_sync(&hda->probe_work);
 	if (azx_bus(chip)->chip_init) {
 		azx_stop_all_streams(chip);
 		azx_stop_chip(chip);
@@ -426,6 +429,9 @@ static int hda_tegra_first_init(struct azx *chip, struct platform_device *pdev)
 /*
  * constructor
  */
+
+static void hda_tegra_probe_work(struct work_struct *work);
+
 static int hda_tegra_create(struct snd_card *card,
 			    unsigned int driver_caps,
 			    struct hda_tegra *hda)
@@ -452,6 +458,8 @@ static int hda_tegra_create(struct snd_card *card,
 	chip->single_cmd = false;
 	chip->snoop = true;
 
+	INIT_WORK(&hda->probe_work, hda_tegra_probe_work);
+
 	err = azx_bus_init(chip, NULL, &hda_tegra_io_ops);
 	if (err < 0)
 		return err;
@@ -499,6 +507,21 @@ static int hda_tegra_probe(struct platform_device *pdev)
 	card->private_data = chip;
 
 	dev_set_drvdata(&pdev->dev, card);
+	schedule_work(&hda->probe_work);
+
+	return 0;
+
+out_free:
+	snd_card_free(card);
+	return err;
+}
+
+static void hda_tegra_probe_work(struct work_struct *work)
+{
+	struct hda_tegra *hda = container_of(work, struct hda_tegra, probe_work);
+	struct azx *chip = &hda->chip;
+	struct platform_device *pdev = to_platform_device(hda->dev);
+	int err;
 
 	err = hda_tegra_first_init(chip, pdev);
 	if (err < 0)
@@ -520,11 +543,8 @@ static int hda_tegra_probe(struct platform_device *pdev)
 	chip->running = 1;
 	snd_hda_set_power_save(&chip->bus, power_save * 1000);
 
-	return 0;
-
-out_free:
-	snd_card_free(card);
-	return err;
+ out_free:
+	return; /* no error return from async probe */
 }
 
 static int hda_tegra_remove(struct platform_device *pdev)
diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index 584a0343a..85813de26 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -633,6 +633,7 @@ static const struct snd_pci_quirk cs4208_mac_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x106b, 0x5e00, "MacBookPro 11,2", CS4208_MBP11),
 	SND_PCI_QUIRK(0x106b, 0x7100, "MacBookAir 6,1", CS4208_MBA6),
 	SND_PCI_QUIRK(0x106b, 0x7200, "MacBookAir 6,2", CS4208_MBA6),
+	SND_PCI_QUIRK(0x106b, 0x7b00, "MacBookPro 12,1", CS4208_MBP11),
 	{} /* terminator */
 };
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c8f01ccc2..6a6613987 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4188,6 +4188,24 @@ static void alc_fixup_disable_aamix(struct hda_codec *codec,
 	}
 }
 
+/* fixup for Thinkpad docks: add dock pins, avoid HP parser fixup */
+static void alc_fixup_tpt440_dock(struct hda_codec *codec,
+				  const struct hda_fixup *fix, int action)
+{
+	static const struct hda_pintbl pincfgs[] = {
+		{ 0x16, 0x21211010 }, /* dock headphone */
+		{ 0x19, 0x21a11010 }, /* dock mic */
+		{ }
+	};
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->parse_flags = HDA_PINCFG_NO_HP_FIXUP;
+		codec->power_save_node = 0; /* avoid click noises */
+		snd_hda_apply_pincfgs(codec, pincfgs);
+	}
+}
+
 static void alc_shutup_dell_xps13(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
@@ -4562,7 +4580,6 @@ enum {
 	ALC255_FIXUP_HEADSET_MODE_NO_HP_MIC,
 	ALC293_FIXUP_DELL1_MIC_NO_PRESENCE,
 	ALC292_FIXUP_TPT440_DOCK,
-	ALC292_FIXUP_TPT440_DOCK2,
 	ALC283_FIXUP_BXBT2807_MIC,
 	ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED,
 	ALC282_FIXUP_ASPIRE_V5_PINS,
@@ -5029,17 +5046,7 @@ static const struct hda_fixup alc269_fixups[] = {
 	},
 	[ALC292_FIXUP_TPT440_DOCK] = {
 		.type = HDA_FIXUP_FUNC,
-		.v.func = alc269_fixup_pincfg_no_hp_to_lineout,
-		.chained = true,
-		.chain_id = ALC292_FIXUP_TPT440_DOCK2
-	},
-	[ALC292_FIXUP_TPT440_DOCK2] = {
-		.type = HDA_FIXUP_PINS,
-		.v.pins = (const struct hda_pintbl[]) {
-			{ 0x16, 0x21211010 }, /* dock headphone */
-			{ 0x19, 0x21a11010 }, /* dock mic */
-			{ }
-		},
+		.v.func = alc_fixup_tpt440_dock,
 		.chained = true,
 		.chain_id = ALC269_FIXUP_LIMIT_INT_MIC_BOOST
 	},
@@ -5299,6 +5306,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x2212, "Thinkpad T440", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2214, "Thinkpad X240", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2215, "Thinkpad", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x17aa, 0x2223, "ThinkPad T550", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x2226, "ThinkPad X250", ALC292_FIXUP_TPT440_DOCK),
 	SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x3978, "IdeaPad Y410P", ALC269_FIXUP_NO_SHUTUP),
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 9d947aef2..def5cc8df 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -4520,7 +4520,11 @@ static int patch_stac92hd73xx(struct hda_codec *codec)
 		return err;
 
 	spec = codec->spec;
-	codec->power_save_node = 1;
+	/* enable power_save_node only for new 92HD89xx chips, as it causes
+	 * click noises on old 92HD73xx chips.
+	 */
+	if ((codec->core.vendor_id & 0xfffffff0) != 0x111d7670)
+		codec->power_save_node = 1;
 	spec->linear_tone_beep = 0;
 	spec->gen.mixer_nid = 0x1d;
 	spec->have_spdif_mux = 1;
diff --git a/sound/soc/au1x/db1200.c b/sound/soc/au1x/db1200.c
index 58c316480..8c907ebea 100644
--- a/sound/soc/au1x/db1200.c
+++ b/sound/soc/au1x/db1200.c
@@ -129,6 +129,8 @@ static struct snd_soc_dai_link db1300_i2s_dai = {
 	.cpu_dai_name	= "au1xpsc_i2s.2",
 	.platform_name	= "au1xpsc-pcm.2",
 	.codec_name	= "wm8731.0-001b",
+	.dai_fmt	= SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_NB_NF |
+			  SND_SOC_DAIFMT_CBM_CFM,
 	.ops		= &db1200_i2s_wm8731_ops,
 };
 
@@ -146,6 +148,8 @@ static struct snd_soc_dai_link db1550_i2s_dai = {
 	.cpu_dai_name	= "au1xpsc_i2s.3",
 	.platform_name	= "au1xpsc-pcm.3",
 	.codec_name	= "wm8731.0-001b",
+	.dai_fmt	= SND_SOC_DAIFMT_LEFT_J | SND_SOC_DAIFMT_NB_NF |
+			  SND_SOC_DAIFMT_CBM_CFM,
 	.ops		= &db1200_i2s_wm8731_ops,
 };
 
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index e673f6ceb..7c411297b 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -1377,8 +1377,8 @@ static int sgtl5000_probe(struct snd_soc_codec *codec)
 			sgtl5000->micbias_resistor << SGTL5000_BIAS_R_SHIFT);
 
 	snd_soc_update_bits(codec, SGTL5000_CHIP_MIC_CTRL,
-			SGTL5000_BIAS_R_MASK,
-			sgtl5000->micbias_voltage << SGTL5000_BIAS_R_SHIFT);
+			SGTL5000_BIAS_VOLT_MASK,
+			sgtl5000->micbias_voltage << SGTL5000_BIAS_VOLT_SHIFT);
 	/*
 	 * disable DAP
 	 * TODO:
diff --git a/sound/soc/codecs/tas2552.c b/sound/soc/codecs/tas2552.c
index 4f25a7d0e..b3e5685ac 100644
--- a/sound/soc/codecs/tas2552.c
+++ b/sound/soc/codecs/tas2552.c
@@ -551,7 +551,7 @@ static struct snd_soc_dai_driver tas2552_dai[] = {
 /*
  * DAC digital volumes. From -7 to 24 dB in 1 dB steps
  */
-static DECLARE_TLV_DB_SCALE(dac_tlv, -7, 100, 0);
+static DECLARE_TLV_DB_SCALE(dac_tlv, -700, 100, 0);
 
 static const char * const tas2552_din_source_select[] = {
 	"Muted",
diff --git a/sound/soc/dwc/designware_i2s.c b/sound/soc/dwc/designware_i2s.c
index a3e97b46b..0d28e3b35 100644
--- a/sound/soc/dwc/designware_i2s.c
+++ b/sound/soc/dwc/designware_i2s.c
@@ -131,10 +131,10 @@ static inline void i2s_clear_irqs(struct dw_i2s_dev *dev, u32 stream)
 
 	if (stream == SNDRV_PCM_STREAM_PLAYBACK) {
 		for (i = 0; i < 4; i++)
-			i2s_write_reg(dev->i2s_base, TOR(i), 0);
+			i2s_read_reg(dev->i2s_base, TOR(i));
 	} else {
 		for (i = 0; i < 4; i++)
-			i2s_write_reg(dev->i2s_base, ROR(i), 0);
+			i2s_read_reg(dev->i2s_base, ROR(i));
 	}
 }
 
diff --git a/sound/soc/pxa/Kconfig b/sound/soc/pxa/Kconfig
index 39cea8084..f2bf8661d 100644
--- a/sound/soc/pxa/Kconfig
+++ b/sound/soc/pxa/Kconfig
@@ -1,7 +1,6 @@
 config SND_PXA2XX_SOC
 	tristate "SoC Audio for the Intel PXA2xx chip"
 	depends on ARCH_PXA
-	select SND_ARM
 	select SND_PXA2XX_LIB
 	help
 	  Say Y or M if you want to add support for codecs attached to
@@ -25,7 +24,6 @@ config SND_PXA2XX_AC97
 config SND_PXA2XX_SOC_AC97
 	tristate
 	select AC97_BUS
-	select SND_ARM
 	select SND_PXA2XX_LIB_AC97
 	select SND_SOC_AC97_BUS
 
diff --git a/sound/soc/pxa/pxa2xx-ac97.c b/sound/soc/pxa/pxa2xx-ac97.c
index 1f6054650..9e4b04e0f 100644
--- a/sound/soc/pxa/pxa2xx-ac97.c
+++ b/sound/soc/pxa/pxa2xx-ac97.c
@@ -49,7 +49,7 @@ static struct snd_ac97_bus_ops pxa2xx_ac97_ops = {
 	.reset	= pxa2xx_ac97_cold_reset,
 };
 
-static unsigned long pxa2xx_ac97_pcm_stereo_in_req = 12;
+static unsigned long pxa2xx_ac97_pcm_stereo_in_req = 11;
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_stereo_in = {
 	.addr		= __PREG(PCDR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
@@ -57,7 +57,7 @@ static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_stereo_in = {
 	.filter_data	= &pxa2xx_ac97_pcm_stereo_in_req,
 };
 
-static unsigned long pxa2xx_ac97_pcm_stereo_out_req = 11;
+static unsigned long pxa2xx_ac97_pcm_stereo_out_req = 12;
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_stereo_out = {
 	.addr		= __PREG(PCDR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
diff --git a/sound/synth/emux/emux_oss.c b/sound/synth/emux/emux_oss.c
index 82e350e95..ac75816ad 100644
--- a/sound/synth/emux/emux_oss.c
+++ b/sound/synth/emux/emux_oss.c
@@ -69,7 +69,8 @@ snd_emux_init_seq_oss(struct snd_emux *emu)
 	struct snd_seq_oss_reg *arg;
 	struct snd_seq_device *dev;
 
-	if (snd_seq_device_new(emu->card, 0, SNDRV_SEQ_DEV_ID_OSS,
+	/* using device#1 here for avoiding conflicts with OPL3 */
+	if (snd_seq_device_new(emu->card, 1, SNDRV_SEQ_DEV_ID_OSS,
 			       sizeof(struct snd_seq_oss_reg), &dev) < 0)
 		return;
 
diff --git a/tools/lguest/lguest.c b/tools/lguest/lguest.c
index e44052483..80159e681 100644
--- a/tools/lguest/lguest.c
+++ b/tools/lguest/lguest.c
@@ -125,7 +125,11 @@ struct device_list {
 /* The list of Guest devices, based on command line arguments. */
 static struct device_list devices;
 
-struct virtio_pci_cfg_cap {
+/*
+ * Just like struct virtio_pci_cfg_cap in uapi/linux/virtio_pci.h,
+ * but uses a u32 explicitly for the data.
+ */
+struct virtio_pci_cfg_cap_u32 {
 	struct virtio_pci_cap cap;
 	u32 pci_cfg_data; /* Data for BAR access. */
 };
@@ -157,7 +161,7 @@ struct pci_config {
 	struct virtio_pci_notify_cap notify;
 	struct virtio_pci_cap isr;
 	struct virtio_pci_cap device;
-	struct virtio_pci_cfg_cap cfg_access;
+	struct virtio_pci_cfg_cap_u32 cfg_access;
 };
 
 /* The device structure describes a single device. */
@@ -1291,7 +1295,7 @@ static struct device *dev_and_reg(u32 *reg)
  * only fault if they try to write with some invalid bar/offset/length.
  */
 static bool valid_bar_access(struct device *d,
-			     struct virtio_pci_cfg_cap *cfg_access)
+			     struct virtio_pci_cfg_cap_u32 *cfg_access)
 {
 	/* We only have 1 bar (BAR0) */
 	if (cfg_access->cap.bar != 0)
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index cc25f059a..a843bee66 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -3721,7 +3721,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 	struct format_field *field;
 	struct printk_map *printk;
 	long long val, fval;
-	unsigned long addr;
+	unsigned long long addr;
 	char *str;
 	unsigned char *hex;
 	int print;
@@ -3754,13 +3754,30 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		 */
 		if (!(field->flags & FIELD_IS_ARRAY) &&
 		    field->size == pevent->long_size) {
-			addr = *(unsigned long *)(data + field->offset);
+
+			/* Handle heterogeneous recording and processing
+			 * architectures
+			 *
+			 * CASE I:
+			 * Traces recorded on 32-bit devices (32-bit
+			 * addressing) and processed on 64-bit devices:
+			 * In this case, only 32 bits should be read.
+			 *
+			 * CASE II:
+			 * Traces recorded on 64 bit devices and processed
+			 * on 32-bit devices:
+			 * In this case, 64 bits must be read.
+			 */
+			addr = (pevent->long_size == 8) ?
+				*(unsigned long long *)(data + field->offset) :
+				(unsigned long long)*(unsigned int *)(data + field->offset);
+
 			/* Check if it matches a print format */
 			printk = find_printk(pevent, addr);
 			if (printk)
 				trace_seq_puts(s, printk->printk);
 			else
-				trace_seq_printf(s, "%lx", addr);
+				trace_seq_printf(s, "%llx", addr);
 			break;
 		}
 		str = malloc(len + 1);
diff --git a/tools/perf/arch/alpha/Build b/tools/perf/arch/alpha/Build
new file mode 100644
index 000000000..1bb8bf6d7
--- /dev/null
+++ b/tools/perf/arch/alpha/Build
@@ -0,0 +1 @@
+# empty
diff --git a/tools/perf/arch/mips/Build b/tools/perf/arch/mips/Build
new file mode 100644
index 000000000..1bb8bf6d7
--- /dev/null
+++ b/tools/perf/arch/mips/Build
@@ -0,0 +1 @@
+# empty
diff --git a/tools/perf/arch/parisc/Build b/tools/perf/arch/parisc/Build
new file mode 100644
index 000000000..1bb8bf6d7
--- /dev/null
+++ b/tools/perf/arch/parisc/Build
@@ -0,0 +1 @@
+# empty
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index d99d850e1..ef355fc0e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -694,7 +694,7 @@ static void abs_printout(int id, int nr, struct perf_evsel *evsel, double avg)
 static void print_aggr(char *prefix)
 {
 	struct perf_evsel *counter;
-	int cpu, cpu2, s, s2, id, nr;
+	int cpu, s, s2, id, nr;
 	double uval;
 	u64 ena, run, val;
 
@@ -707,8 +707,7 @@ static void print_aggr(char *prefix)
 			val = ena = run = 0;
 			nr = 0;
 			for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-				cpu2 = perf_evsel__cpus(counter)->map[cpu];
-				s2 = aggr_get_id(evsel_list->cpus, cpu2);
+				s2 = aggr_get_id(perf_evsel__cpus(counter), cpu);
 				if (s2 != id)
 					continue;
 				val += perf_counts(counter->counts, cpu, 0)->val;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 03ace57a8..4215cc155 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1442,7 +1442,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused,
 	if (ph->needs_swap)
 		nr = bswap_32(nr);
 
-	ph->env.nr_cpus_online = nr;
+	ph->env.nr_cpus_avail = nr;
 
 	ret = readn(fd, &nr, sizeof(nr));
 	if (ret != sizeof(nr))
@@ -1451,7 +1451,7 @@ static int process_nrcpus(struct perf_file_section *section __maybe_unused,
 	if (ph->needs_swap)
 		nr = bswap_32(nr);
 
-	ph->env.nr_cpus_avail = nr;
+	ph->env.nr_cpus_online = nr;
 	return 0;
 }
 
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index 6f28d53d4..f298c696e 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -151,6 +151,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	hists__new_col_len(hists, HISTC_LOCAL_WEIGHT, 12);
 	hists__new_col_len(hists, HISTC_GLOBAL_WEIGHT, 12);
 
+	if (h->srcline)
+		hists__new_col_len(hists, HISTC_SRCLINE, strlen(h->srcline));
+
 	if (h->transaction)
 		hists__new_col_len(hists, HISTC_TRANSACTION,
 				   hist_entry__transaction_len());
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 591905a02..9cd70819c 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -255,7 +255,7 @@ PE_PMU_EVENT_PRE '-' PE_PMU_EVENT_SUF sep_dc
 	list_add_tail(&term->list, head);
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+	ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
 	parse_events__free_terms(head);
 	$$ = list;
 }
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 381f23a44..ae6351db6 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -274,12 +274,13 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso)
 	int ret = 0;
 
 	if (module) {
-		list_for_each_entry(dso, &host_machine->dsos.head, node) {
-			if (!dso->kernel)
-				continue;
-			if (strncmp(dso->short_name + 1, module,
-				    dso->short_name_len - 2) == 0)
-				goto found;
+		char module_name[128];
+
+		snprintf(module_name, sizeof(module_name), "[%s]", module);
+		map = map_groups__find_by_name(&host_machine->kmaps, MAP__FUNCTION, module_name);
+		if (map) {
+			dso = map->dso;
+			goto found;
 		}
 		pr_debug("Failed to find module %s.\n", module);
 		return -ENOENT;
diff --git a/tools/perf/util/probe-event.h b/tools/perf/util/probe-event.h
index 31db6ee7d..cd55c6db4 100644
--- a/tools/perf/util/probe-event.h
+++ b/tools/perf/util/probe-event.h
@@ -106,6 +106,8 @@ struct variable_list {
 	struct strlist			*vars;	/* Available variables */
 };
 
+struct map;
+
 /* Command string to events */
 extern int parse_perf_probe_command(const char *cmd,
 				    struct perf_probe_event *pev);
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 65f7e389a..333858821 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -1260,8 +1260,6 @@ out_close:
 static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
 		       bool temp)
 {
-	GElf_Ehdr *ehdr;
-
 	kcore->elfclass = elfclass;
 
 	if (temp)
@@ -1278,9 +1276,7 @@ static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
 	if (!gelf_newehdr(kcore->elf, elfclass))
 		goto out_end;
 
-	ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr);
-	if (!ehdr)
-		goto out_end;
+	memset(&kcore->ehdr, 0, sizeof(GElf_Ehdr));
 
 	return 0;
 
@@ -1337,23 +1333,18 @@ static int kcore__copy_hdr(struct kcore *from, struct kcore *to, size_t count)
 static int kcore__add_phdr(struct kcore *kcore, int idx, off_t offset,
 			   u64 addr, u64 len)
 {
-	GElf_Phdr gphdr;
-	GElf_Phdr *phdr;
-
-	phdr = gelf_getphdr(kcore->elf, idx, &gphdr);
-	if (!phdr)
-		return -1;
-
-	phdr->p_type	= PT_LOAD;
-	phdr->p_flags	= PF_R | PF_W | PF_X;
-	phdr->p_offset	= offset;
-	phdr->p_vaddr	= addr;
-	phdr->p_paddr	= 0;
-	phdr->p_filesz	= len;
-	phdr->p_memsz	= len;
-	phdr->p_align	= page_size;
-
-	if (!gelf_update_phdr(kcore->elf, idx, phdr))
+	GElf_Phdr phdr = {
+		.p_type		= PT_LOAD,
+		.p_flags	= PF_R | PF_W | PF_X,
+		.p_offset	= offset,
+		.p_vaddr	= addr,
+		.p_paddr	= 0,
+		.p_filesz	= len,
+		.p_memsz	= len,
+		.p_align	= page_size,
+	};
+
+	if (!gelf_update_phdr(kcore->elf, idx, &phdr))
 		return -1;
 
 	return 0;
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 9ff4193df..79db45336 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -771,40 +771,14 @@ static enum kvm_bus ioeventfd_bus_from_flags(__u32 flags)
 	return KVM_MMIO_BUS;
 }
 
-static int
-kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
+static int kvm_assign_ioeventfd_idx(struct kvm *kvm,
+				enum kvm_bus bus_idx,
+				struct kvm_ioeventfd *args)
 {
-	enum kvm_bus              bus_idx;
-	struct _ioeventfd        *p;
-	struct eventfd_ctx       *eventfd;
-	int                       ret;
-
-	bus_idx = ioeventfd_bus_from_flags(args->flags);
-	/* must be natural-word sized, or 0 to ignore length */
-	switch (args->len) {
-	case 0:
-	case 1:
-	case 2:
-	case 4:
-	case 8:
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	/* check for range overflow */
-	if (args->addr + args->len < args->addr)
-		return -EINVAL;
 
-	/* check for extra flags that we don't understand */
-	if (args->flags & ~KVM_IOEVENTFD_VALID_FLAG_MASK)
-		return -EINVAL;
-
-	/* ioeventfd with no length can't be combined with DATAMATCH */
-	if (!args->len &&
-	    args->flags & (KVM_IOEVENTFD_FLAG_PIO |
-			   KVM_IOEVENTFD_FLAG_DATAMATCH))
-		return -EINVAL;
+	struct eventfd_ctx *eventfd;
+	struct _ioeventfd *p;
+	int ret;
 
 	eventfd = eventfd_ctx_fdget(args->fd);
 	if (IS_ERR(eventfd))
@@ -843,16 +817,6 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 	if (ret < 0)
 		goto unlock_fail;
 
-	/* When length is ignored, MMIO is also put on a separate bus, for
-	 * faster lookups.
-	 */
-	if (!args->len && !(args->flags & KVM_IOEVENTFD_FLAG_PIO)) {
-		ret = kvm_io_bus_register_dev(kvm, KVM_FAST_MMIO_BUS,
-					      p->addr, 0, &p->dev);
-		if (ret < 0)
-			goto register_fail;
-	}
-
 	kvm->buses[bus_idx]->ioeventfd_count++;
 	list_add_tail(&p->list, &kvm->ioeventfds);
 
@@ -860,8 +824,6 @@ kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 
 	return 0;
 
-register_fail:
-	kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
 unlock_fail:
 	mutex_unlock(&kvm->slots_lock);
 
@@ -873,14 +835,13 @@ fail:
 }
 
 static int
-kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
+kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
+			   struct kvm_ioeventfd *args)
 {
-	enum kvm_bus              bus_idx;
 	struct _ioeventfd        *p, *tmp;
 	struct eventfd_ctx       *eventfd;
 	int                       ret = -ENOENT;
 
-	bus_idx = ioeventfd_bus_from_flags(args->flags);
 	eventfd = eventfd_ctx_fdget(args->fd);
 	if (IS_ERR(eventfd))
 		return PTR_ERR(eventfd);
@@ -901,10 +862,6 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 			continue;
 
 		kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
-		if (!p->length) {
-			kvm_io_bus_unregister_dev(kvm, KVM_FAST_MMIO_BUS,
-						  &p->dev);
-		}
 		kvm->buses[bus_idx]->ioeventfd_count--;
 		ioeventfd_release(p);
 		ret = 0;
@@ -918,6 +875,71 @@ kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 	return ret;
 }
 
+static int kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
+{
+	enum kvm_bus bus_idx = ioeventfd_bus_from_flags(args->flags);
+	int ret = kvm_deassign_ioeventfd_idx(kvm, bus_idx, args);
+
+	if (!args->len && bus_idx == KVM_MMIO_BUS)
+		kvm_deassign_ioeventfd_idx(kvm, KVM_FAST_MMIO_BUS, args);
+
+	return ret;
+}
+
+static int
+kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
+{
+	enum kvm_bus              bus_idx;
+	int ret;
+
+	bus_idx = ioeventfd_bus_from_flags(args->flags);
+	/* must be natural-word sized, or 0 to ignore length */
+	switch (args->len) {
+	case 0:
+	case 1:
+	case 2:
+	case 4:
+	case 8:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* check for range overflow */
+	if (args->addr + args->len < args->addr)
+		return -EINVAL;
+
+	/* check for extra flags that we don't understand */
+	if (args->flags & ~KVM_IOEVENTFD_VALID_FLAG_MASK)
+		return -EINVAL;
+
+	/* ioeventfd with no length can't be combined with DATAMATCH */
+	if (!args->len &&
+	    args->flags & (KVM_IOEVENTFD_FLAG_PIO |
+			   KVM_IOEVENTFD_FLAG_DATAMATCH))
+		return -EINVAL;
+
+	ret = kvm_assign_ioeventfd_idx(kvm, bus_idx, args);
+	if (ret)
+		goto fail;
+
+	/* When length is ignored, MMIO is also put on a separate bus, for
+	 * faster lookups.
+	 */
+	if (!args->len && bus_idx == KVM_MMIO_BUS) {
+		ret = kvm_assign_ioeventfd_idx(kvm, KVM_FAST_MMIO_BUS, args);
+		if (ret < 0)
+			goto fast_fail;
+	}
+
+	return 0;
+
+fast_fail:
+	kvm_deassign_ioeventfd_idx(kvm, bus_idx, args);
+fail:
+	return ret;
+}
+
 int
 kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 8b8a44453..5a2a78a91 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -3080,10 +3080,25 @@ static void kvm_io_bus_destroy(struct kvm_io_bus *bus)
 static inline int kvm_io_bus_cmp(const struct kvm_io_range *r1,
 				 const struct kvm_io_range *r2)
 {
-	if (r1->addr < r2->addr)
+	gpa_t addr1 = r1->addr;
+	gpa_t addr2 = r2->addr;
+
+	if (addr1 < addr2)
 		return -1;
-	if (r1->addr + r1->len > r2->addr + r2->len)
+
+	/* If r2->len == 0, match the exact address.  If r2->len != 0,
+	 * accept any overlapping write.  Any order is acceptable for
+	 * overlapping ranges, because kvm_io_bus_get_first_dev ensures
+	 * we process all of them.
+	 */
+	if (r2->len) {
+		addr1 += r1->len;
+		addr2 += r2->len;
+	}
+
+	if (addr1 > addr2)
 		return 1;
+
 	return 0;
 }