Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "Two oneliner 'perf bench' tooling fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf bench: Fix NULL pointer dereference in "perf bench all"
  perf bench numa: Make no args mean 'run all tests'
diff --git a/MAINTAINERS b/MAINTAINERS
index b3fdb0f..55a57ed 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -911,11 +911,11 @@
 F:	arch/arm/mach-footbridge/
 
 ARM/FREESCALE IMX / MXC ARM ARCHITECTURE
-M:	Shawn Guo <shawn.guo@linaro.org>
+M:	Shawn Guo <shawn.guo@freescale.com>
 M:	Sascha Hauer <kernel@pengutronix.de>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
-T:	git git://git.linaro.org/people/shawnguo/linux-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/shawnguo/linux.git
 F:	arch/arm/mach-imx/
 F:	arch/arm/boot/dts/imx*
 F:	arch/arm/configs/imx*_defconfig
diff --git a/arch/arm/boot/dts/sama5d36.dtsi b/arch/arm/boot/dts/sama5d36.dtsi
index 6c31c26..db58cad 100644
--- a/arch/arm/boot/dts/sama5d36.dtsi
+++ b/arch/arm/boot/dts/sama5d36.dtsi
@@ -8,8 +8,8 @@
  */
 #include "sama5d3.dtsi"
 #include "sama5d3_can.dtsi"
-#include "sama5d3_emac.dtsi"
 #include "sama5d3_gmac.dtsi"
+#include "sama5d3_emac.dtsi"
 #include "sama5d3_lcd.dtsi"
 #include "sama5d3_mci2.dtsi"
 #include "sama5d3_tcb1.dtsi"
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index dcae3a7..95fa1f1 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1776,12 +1776,12 @@
 
 config FORCE_MAX_ZONEORDER
 	int "Maximum zone order"
-	range 14 64 if HUGETLB_PAGE && PAGE_SIZE_64KB
-	default "14" if HUGETLB_PAGE && PAGE_SIZE_64KB
-	range 13 64 if HUGETLB_PAGE && PAGE_SIZE_32KB
-	default "13" if HUGETLB_PAGE && PAGE_SIZE_32KB
-	range 12 64 if HUGETLB_PAGE && PAGE_SIZE_16KB
-	default "12" if HUGETLB_PAGE && PAGE_SIZE_16KB
+	range 14 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
+	default "14" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_64KB
+	range 13 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB
+	default "13" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_32KB
+	range 12 64 if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB
+	default "12" if MIPS_HUGE_TLB_SUPPORT && PAGE_SIZE_16KB
 	range 11 64
 	default "11"
 	help
@@ -2353,9 +2353,8 @@
 	  If unsure, say Y. Only embedded should say N here.
 
 config MIPS_O32_FP64_SUPPORT
-	bool "Support for O32 binaries using 64-bit FP"
+	bool "Support for O32 binaries using 64-bit FP (EXPERIMENTAL)"
 	depends on 32BIT || MIPS32_O32
-	default y
 	help
 	  When this is enabled, the kernel will support use of 64-bit floating
 	  point registers with binaries using the O32 ABI along with the
@@ -2367,7 +2366,14 @@
 	  of your kernel & potentially improve FP emulation performance by
 	  saying N here.
 
-	  If unsure, say Y.
+	  Although binutils currently supports use of this flag the details
+	  concerning its effect upon the O32 ABI in userland are still being
+	  worked on. In order to avoid userland becoming dependant upon current
+	  behaviour before the details have been finalised, this option should
+	  be considered experimental and only enabled by those working upon
+	  said details.
+
+	  If unsure, say N.
 
 config USE_OF
 	bool
diff --git a/arch/mips/alchemy/board-gpr.c b/arch/mips/alchemy/board-gpr.c
index 9edc35f..acf9a2a 100644
--- a/arch/mips/alchemy/board-gpr.c
+++ b/arch/mips/alchemy/board-gpr.c
@@ -53,10 +53,8 @@
 	prom_init_cmdline();
 
 	memsize_str = prom_getenv("memsize");
-	if (!memsize_str)
+	if (!memsize_str || kstrtoul(memsize_str, 0, &memsize))
 		memsize = 0x04000000;
-	else
-		strict_strtoul(memsize_str, 0, &memsize);
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
diff --git a/arch/mips/alchemy/board-mtx1.c b/arch/mips/alchemy/board-mtx1.c
index 9969dba..25a59a2 100644
--- a/arch/mips/alchemy/board-mtx1.c
+++ b/arch/mips/alchemy/board-mtx1.c
@@ -52,10 +52,8 @@
 	prom_init_cmdline();
 
 	memsize_str = prom_getenv("memsize");
-	if (!memsize_str)
+	if (!memsize_str || kstrtoul(memsize_str, 0, &memsize))
 		memsize = 0x04000000;
-	else
-		strict_strtoul(memsize_str, 0, &memsize);
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
diff --git a/arch/mips/bcm47xx/board.c b/arch/mips/bcm47xx/board.c
index 6d612e2..cdd8246 100644
--- a/arch/mips/bcm47xx/board.c
+++ b/arch/mips/bcm47xx/board.c
@@ -1,3 +1,4 @@
+#include <linux/errno.h>
 #include <linux/export.h>
 #include <linux/string.h>
 #include <bcm47xx_board.h>
diff --git a/arch/mips/bcm47xx/nvram.c b/arch/mips/bcm47xx/nvram.c
index 6decb27..2bed73a 100644
--- a/arch/mips/bcm47xx/nvram.c
+++ b/arch/mips/bcm47xx/nvram.c
@@ -196,7 +196,7 @@
 	char nvram_var[10];
 	char buf[30];
 
-	for (i = 0; i < 16; i++) {
+	for (i = 0; i < 32; i++) {
 		err = snprintf(nvram_var, sizeof(nvram_var), "gpio%i", i);
 		if (err <= 0)
 			continue;
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index 25fbfae..c2bb4f8 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -975,10 +975,6 @@
 	if (ciu > 1 || bit > 63)
 		return -EINVAL;
 
-	/* These are the GPIO lines */
-	if (ciu == 0 && bit >= 16 && bit < 32)
-		return -EINVAL;
-
 	*out_hwirq = (ciu << 6) | bit;
 	*out_type = 0;
 
@@ -1007,6 +1003,10 @@
 	if (!octeon_irq_virq_in_range(virq))
 		return -EINVAL;
 
+	/* Don't map irq if it is reserved for GPIO. */
+	if (line == 0 && bit >= 16 && bit <32)
+		return 0;
+
 	if (line > 1 || octeon_irq_ciu_to_irq[line][bit] != 0)
 		return -EINVAL;
 
@@ -1525,10 +1525,6 @@
 	ciu = intspec[0];
 	bit = intspec[1];
 
-	/* Line 7  are the GPIO lines */
-	if (ciu > 6 || bit > 63)
-		return -EINVAL;
-
 	*out_hwirq = (ciu << 6) | bit;
 	*out_type = 0;
 
@@ -1570,8 +1566,14 @@
 	if (!octeon_irq_virq_in_range(virq))
 		return -EINVAL;
 
-	/* Line 7  are the GPIO lines */
-	if (line > 6 || octeon_irq_ciu_to_irq[line][bit] != 0)
+	/*
+	 * Don't map irq if it is reserved for GPIO.
+	 * (Line 7 are the GPIO lines.)
+	 */
+	if (line == 7)
+		return 0;
+
+	if (line > 7 || octeon_irq_ciu_to_irq[line][bit] != 0)
 		return -EINVAL;
 
 	if (octeon_irq_ciu2_is_edge(line, bit))
diff --git a/arch/mips/include/asm/asmmacro.h b/arch/mips/include/asm/asmmacro.h
index 3220c93..4225e99 100644
--- a/arch/mips/include/asm/asmmacro.h
+++ b/arch/mips/include/asm/asmmacro.h
@@ -9,6 +9,7 @@
 #define _ASM_ASMMACRO_H
 
 #include <asm/hazards.h>
+#include <asm/asm-offsets.h>
 
 #ifdef CONFIG_32BIT
 #include <asm/asmmacro-32.h>
@@ -54,11 +55,21 @@
 	.endm
 
 	.macro	local_irq_disable reg=t0
+#ifdef CONFIG_PREEMPT
+	lw      \reg, TI_PRE_COUNT($28)
+	addi    \reg, \reg, 1
+	sw      \reg, TI_PRE_COUNT($28)
+#endif
 	mfc0	\reg, CP0_STATUS
 	ori	\reg, \reg, 1
 	xori	\reg, \reg, 1
 	mtc0	\reg, CP0_STATUS
 	irq_disable_hazard
+#ifdef CONFIG_PREEMPT
+	lw      \reg, TI_PRE_COUNT($28)
+	addi    \reg, \reg, -1
+	sw      \reg, TI_PRE_COUNT($28)
+#endif
 	.endm
 #endif /* CONFIG_MIPS_MT_SMTC */
 
@@ -106,7 +117,7 @@
 	.endm
 
 	.macro	fpu_save_double thread status tmp
-#if defined(CONFIG_MIPS64) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
 	sll	\tmp, \status, 5
 	bgez	\tmp, 10f
 	fpu_save_16odd \thread
@@ -159,7 +170,7 @@
 	.endm
 
 	.macro	fpu_restore_double thread status tmp
-#if defined(CONFIG_MIPS64) || defined(CONFIG_CPU_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
 	sll	\tmp, \status, 5
 	bgez	\tmp, 10f				# 16 register mode?
 
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 6b97495..58e50cb 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -57,7 +57,7 @@
 		return 0;
 
 	case FPU_64BIT:
-#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_MIPS64))
+#if !(defined(CONFIG_CPU_MIPS32_R2) || defined(CONFIG_64BIT))
 		/* we only have a 32-bit FPU */
 		return SIGFPE;
 #endif
diff --git a/arch/mips/include/asm/ftrace.h b/arch/mips/include/asm/ftrace.h
index ce35c9a..992aaba 100644
--- a/arch/mips/include/asm/ftrace.h
+++ b/arch/mips/include/asm/ftrace.h
@@ -22,12 +22,12 @@
 #define safe_load(load, src, dst, error)		\
 do {							\
 	asm volatile (					\
-		"1: " load " %[" STR(dst) "], 0(%[" STR(src) "])\n"\
-		"   li %[" STR(error) "], 0\n"		\
+		"1: " load " %[tmp_dst], 0(%[tmp_src])\n"	\
+		"   li %[tmp_err], 0\n"			\
 		"2:\n"					\
 							\
 		".section .fixup, \"ax\"\n"		\
-		"3: li %[" STR(error) "], 1\n"		\
+		"3: li %[tmp_err], 1\n"			\
 		"   j 2b\n"				\
 		".previous\n"				\
 							\
@@ -35,8 +35,8 @@
 		STR(PTR) "\t1b, 3b\n\t"			\
 		".previous\n"				\
 							\
-		: [dst] "=&r" (dst), [error] "=r" (error)\
-		: [src] "r" (src)			\
+		: [tmp_dst] "=&r" (dst), [tmp_err] "=r" (error)\
+		: [tmp_src] "r" (src)			\
 		: "memory"				\
 	);						\
 } while (0)
@@ -44,12 +44,12 @@
 #define safe_store(store, src, dst, error)	\
 do {						\
 	asm volatile (				\
-		"1: " store " %[" STR(src) "], 0(%[" STR(dst) "])\n"\
-		"   li %[" STR(error) "], 0\n"	\
+		"1: " store " %[tmp_src], 0(%[tmp_dst])\n"\
+		"   li %[tmp_err], 0\n"		\
 		"2:\n"				\
 						\
 		".section .fixup, \"ax\"\n"	\
-		"3: li %[" STR(error) "], 1\n"	\
+		"3: li %[tmp_err], 1\n"		\
 		"   j 2b\n"			\
 		".previous\n"			\
 						\
@@ -57,8 +57,8 @@
 		STR(PTR) "\t1b, 3b\n\t"		\
 		".previous\n"			\
 						\
-		: [error] "=r" (error)		\
-		: [dst] "r" (dst), [src] "r" (src)\
+		: [tmp_err] "=r" (error)	\
+		: [tmp_dst] "r" (dst), [tmp_src] "r" (src)\
 		: "memory"			\
 	);					\
 } while (0)
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index 33e8dbf..f35b131 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -13,6 +13,7 @@
 #ifndef __ASM_MIPS_SYSCALL_H
 #define __ASM_MIPS_SYSCALL_H
 
+#include <linux/compiler.h>
 #include <linux/audit.h>
 #include <linux/elf-em.h>
 #include <linux/kernel.h>
@@ -39,14 +40,14 @@
 
 #ifdef CONFIG_32BIT
 	case 4: case 5: case 6: case 7:
-		return get_user(*arg, (int *)usp + 4 * n);
+		return get_user(*arg, (int *)usp + n);
 #endif
 
 #ifdef CONFIG_64BIT
 	case 4: case 5: case 6: case 7:
 #ifdef CONFIG_MIPS32_O32
 		if (test_thread_flag(TIF_32BIT_REGS))
-			return get_user(*arg, (int *)usp + 4 * n);
+			return get_user(*arg, (int *)usp + n);
 		else
 #endif
 			*arg = regs->regs[4 + n];
@@ -57,6 +58,8 @@
 	default:
 		BUG();
 	}
+
+	unreachable();
 }
 
 static inline long syscall_get_return_value(struct task_struct *task,
@@ -83,11 +86,10 @@
 					 unsigned int i, unsigned int n,
 					 unsigned long *args)
 {
-	unsigned long arg;
 	int ret;
 
 	while (n--)
-		ret |= mips_get_syscall_arg(&arg, task, regs, i++);
+		ret |= mips_get_syscall_arg(args++, task, regs, i++);
 
 	/*
 	 * No way to communicate an error because this is a void function.
diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h
index b39ba25..f25181b 100644
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@@ -163,8 +163,8 @@
  */
 enum cop1x_func {
 	lwxc1_op     =	0x00, ldxc1_op	   =  0x01,
-	pfetch_op    =	0x07, swxc1_op	   =  0x08,
-	sdxc1_op     =	0x09, madd_s_op	   =  0x20,
+	swxc1_op     =  0x08, sdxc1_op	   =  0x09,
+	pfetch_op    =	0x0f, madd_s_op	   =  0x20,
 	madd_d_op    =	0x21, madd_e_op	   =  0x22,
 	msub_s_op    =	0x28, msub_d_op	   =  0x29,
 	msub_e_op    =	0x2a, nmadd_s_op   =  0x30,
diff --git a/arch/mips/kernel/ftrace.c b/arch/mips/kernel/ftrace.c
index 185ba25..374ed74 100644
--- a/arch/mips/kernel/ftrace.c
+++ b/arch/mips/kernel/ftrace.c
@@ -111,11 +111,10 @@
 	safe_store_code(new_code1, ip, faulted);
 	if (unlikely(faulted))
 		return -EFAULT;
-	ip += 4;
-	safe_store_code(new_code2, ip, faulted);
+	safe_store_code(new_code2, ip + 4, faulted);
 	if (unlikely(faulted))
 		return -EFAULT;
-	flush_icache_range(ip, ip + 8); /* original ip + 12 */
+	flush_icache_range(ip, ip + 8);
 	return 0;
 }
 #endif
diff --git a/arch/mips/kernel/r4k_fpu.S b/arch/mips/kernel/r4k_fpu.S
index 253b2fb..73b0ddf 100644
--- a/arch/mips/kernel/r4k_fpu.S
+++ b/arch/mips/kernel/r4k_fpu.S
@@ -35,9 +35,9 @@
 LEAF(_save_fp_context)
 	cfc1	t1, fcr31
 
-#if defined(CONFIG_64BIT) || defined(CONFIG_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
 	.set	push
-#ifdef CONFIG_MIPS32_R2
+#ifdef CONFIG_CPU_MIPS32_R2
 	.set	mips64r2
 	mfc0	t0, CP0_STATUS
 	sll	t0, t0, 5
@@ -146,11 +146,11 @@
  *  - cp1 status/control register
  */
 LEAF(_restore_fp_context)
-	EX	lw t0, SC_FPC_CSR(a0)
+	EX	lw t1, SC_FPC_CSR(a0)
 
-#if defined(CONFIG_64BIT) || defined(CONFIG_MIPS32_R2)
+#if defined(CONFIG_64BIT) || defined(CONFIG_CPU_MIPS32_R2)
 	.set	push
-#ifdef CONFIG_MIPS32_R2
+#ifdef CONFIG_CPU_MIPS32_R2
 	.set	mips64r2
 	mfc0	t0, CP0_STATUS
 	sll	t0, t0, 5
@@ -191,7 +191,7 @@
 	EX	ldc1 $f26, SC_FPREGS+208(a0)
 	EX	ldc1 $f28, SC_FPREGS+224(a0)
 	EX	ldc1 $f30, SC_FPREGS+240(a0)
-	ctc1	t0, fcr31
+	ctc1	t1, fcr31
 	jr	ra
 	 li	v0, 0					# success
 	END(_restore_fp_context)
@@ -199,7 +199,7 @@
 #ifdef CONFIG_MIPS32_COMPAT
 LEAF(_restore_fp_context32)
 	/* Restore an o32 sigcontext.  */
-	EX	lw t0, SC32_FPC_CSR(a0)
+	EX	lw t1, SC32_FPC_CSR(a0)
 
 	mfc0	t0, CP0_STATUS
 	sll	t0, t0, 5
@@ -239,7 +239,7 @@
 	EX	ldc1 $f26, SC32_FPREGS+208(a0)
 	EX	ldc1 $f28, SC32_FPREGS+224(a0)
 	EX	ldc1 $f30, SC32_FPREGS+240(a0)
-	ctc1	t0, fcr31
+	ctc1	t1, fcr31
 	jr	ra
 	 li	v0, 0					# success
 	END(_restore_fp_context32)
diff --git a/arch/mips/kernel/rtlx-cmp.c b/arch/mips/kernel/rtlx-cmp.c
index 56dc696..758fb3c 100644
--- a/arch/mips/kernel/rtlx-cmp.c
+++ b/arch/mips/kernel/rtlx-cmp.c
@@ -112,5 +112,8 @@
 
 	for (i = 0; i < RTLX_CHANNELS; i++)
 		device_destroy(mt_class, MKDEV(major, i));
+
 	unregister_chrdev(major, RTLX_MODULE_NAME);
+
+	aprp_hook = NULL;
 }
diff --git a/arch/mips/kernel/rtlx-mt.c b/arch/mips/kernel/rtlx-mt.c
index 91d61ba..9c1aca0 100644
--- a/arch/mips/kernel/rtlx-mt.c
+++ b/arch/mips/kernel/rtlx-mt.c
@@ -144,5 +144,8 @@
 
 	for (i = 0; i < RTLX_CHANNELS; i++)
 		device_destroy(mt_class, MKDEV(major, i));
+
 	unregister_chrdev(major, RTLX_MODULE_NAME);
+
+	aprp_hook = NULL;
 }
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index 506925b..0b4e2e3 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -1538,10 +1538,10 @@
 		break;
 	}
 
-	case 0x7:		/* 7 */
-		if (MIPSInst_FUNC(ir) != pfetch_op) {
+	case 0x3:
+		if (MIPSInst_FUNC(ir) != pfetch_op)
 			return SIGILL;
-		}
+
 		/* ignore prefx operation */
 		break;
 
diff --git a/arch/mips/mti-malta/malta-amon.c b/arch/mips/mti-malta/malta-amon.c
index 592ac04..84ac523 100644
--- a/arch/mips/mti-malta/malta-amon.c
+++ b/arch/mips/mti-malta/malta-amon.c
@@ -72,7 +72,7 @@
 	return 0;
 }
 
-#ifdef CONFIG_MIPS_VPE_LOADER
+#ifdef CONFIG_MIPS_VPE_LOADER_CMP
 int vpe_run(struct vpe *v)
 {
 	struct vpe_notifications *n;
diff --git a/arch/mips/mti-malta/malta-int.c b/arch/mips/mti-malta/malta-int.c
index ca3e3a4..2242181 100644
--- a/arch/mips/mti-malta/malta-int.c
+++ b/arch/mips/mti-malta/malta-int.c
@@ -119,7 +119,7 @@
 
 	do_IRQ(MALTA_INT_BASE + irq);
 
-#ifdef MIPS_VPE_APSP_API
+#ifdef CONFIG_MIPS_VPE_APSP_API_MT
 	if (aprp_hook)
 		aprp_hook();
 #endif
@@ -310,7 +310,7 @@
 
 static irqreturn_t ipi_resched_interrupt(int irq, void *dev_id)
 {
-#ifdef MIPS_VPE_APSP_API
+#ifdef CONFIG_MIPS_VPE_APSP_API_CMP
 	if (aprp_hook)
 		aprp_hook();
 #endif
diff --git a/arch/mips/pci/msi-octeon.c b/arch/mips/pci/msi-octeon.c
index d37be36..2b91b0e 100644
--- a/arch/mips/pci/msi-octeon.c
+++ b/arch/mips/pci/msi-octeon.c
@@ -150,6 +150,7 @@
 		msg.address_lo =
 			((128ul << 20) + CVMX_PCI_MSI_RCV) & 0xffffffff;
 		msg.address_hi = ((128ul << 20) + CVMX_PCI_MSI_RCV) >> 32;
+		break;
 	case OCTEON_DMA_BAR_TYPE_BIG:
 		/* When using big bar, Bar 0 is based at 0 */
 		msg.address_lo = (0 + CVMX_PCI_MSI_RCV) & 0xffffffff;
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index e66d4ec..818dce3 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1504,73 +1504,6 @@
 1:	addi	r8,r8,16
 	.endr
 
-	/* Save DEC */
-	mfspr	r5,SPRN_DEC
-	mftb	r6
-	extsw	r5,r5
-	add	r5,r5,r6
-	std	r5,VCPU_DEC_EXPIRES(r9)
-
-BEGIN_FTR_SECTION
-	b	8f
-END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
-	/* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
-	mfmsr	r8
-	li	r0, 1
-	rldimi	r8, r0, MSR_TM_LG, 63-MSR_TM_LG
-	mtmsrd	r8
-
-	/* Save POWER8-specific registers */
-	mfspr	r5, SPRN_IAMR
-	mfspr	r6, SPRN_PSPB
-	mfspr	r7, SPRN_FSCR
-	std	r5, VCPU_IAMR(r9)
-	stw	r6, VCPU_PSPB(r9)
-	std	r7, VCPU_FSCR(r9)
-	mfspr	r5, SPRN_IC
-	mfspr	r6, SPRN_VTB
-	mfspr	r7, SPRN_TAR
-	std	r5, VCPU_IC(r9)
-	std	r6, VCPU_VTB(r9)
-	std	r7, VCPU_TAR(r9)
-#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
-	mfspr	r5, SPRN_TFHAR
-	mfspr	r6, SPRN_TFIAR
-	mfspr	r7, SPRN_TEXASR
-	std	r5, VCPU_TFHAR(r9)
-	std	r6, VCPU_TFIAR(r9)
-	std	r7, VCPU_TEXASR(r9)
-#endif
-	mfspr	r8, SPRN_EBBHR
-	std	r8, VCPU_EBBHR(r9)
-	mfspr	r5, SPRN_EBBRR
-	mfspr	r6, SPRN_BESCR
-	mfspr	r7, SPRN_CSIGR
-	mfspr	r8, SPRN_TACR
-	std	r5, VCPU_EBBRR(r9)
-	std	r6, VCPU_BESCR(r9)
-	std	r7, VCPU_CSIGR(r9)
-	std	r8, VCPU_TACR(r9)
-	mfspr	r5, SPRN_TCSCR
-	mfspr	r6, SPRN_ACOP
-	mfspr	r7, SPRN_PID
-	mfspr	r8, SPRN_WORT
-	std	r5, VCPU_TCSCR(r9)
-	std	r6, VCPU_ACOP(r9)
-	stw	r7, VCPU_GUEST_PID(r9)
-	std	r8, VCPU_WORT(r9)
-8:
-
-	/* Save and reset AMR and UAMOR before turning on the MMU */
-BEGIN_FTR_SECTION
-	mfspr	r5,SPRN_AMR
-	mfspr	r6,SPRN_UAMOR
-	std	r5,VCPU_AMR(r9)
-	std	r6,VCPU_UAMOR(r9)
-	li	r6,0
-	mtspr	SPRN_AMR,r6
-END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
-
 	/* Unset guest mode */
 	li	r0, KVM_GUEST_MODE_NONE
 	stb	r0, HSTATE_IN_GUEST(r13)
@@ -2203,7 +2136,7 @@
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
 	mfspr	r6,SPRN_VRSAVE
-	stw	r6,VCPU_VRSAVE(r3)
+	stw	r6,VCPU_VRSAVE(r31)
 	mtlr	r30
 	mtmsrd	r5
 	isync
@@ -2240,7 +2173,7 @@
 	bl	.load_vr_state
 END_FTR_SECTION_IFSET(CPU_FTR_ALTIVEC)
 #endif
-	lwz	r7,VCPU_VRSAVE(r4)
+	lwz	r7,VCPU_VRSAVE(r31)
 	mtspr	SPRN_VRSAVE,r7
 	mtlr	r30
 	mr	r4,r31
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index fd972a3..9fa8aa0 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -18,7 +18,6 @@
 #include <linux/pci_ids.h>
 #include <linux/pci.h>
 #include <linux/bitops.h>
-#include <linux/ioport.h>
 #include <linux/suspend.h>
 #include <asm/e820.h>
 #include <asm/io.h>
@@ -54,18 +53,6 @@
 
 int fix_aperture __initdata = 1;
 
-static struct resource gart_resource = {
-	.name	= "GART",
-	.flags	= IORESOURCE_MEM,
-};
-
-static void __init insert_aperture_resource(u32 aper_base, u32 aper_size)
-{
-	gart_resource.start = aper_base;
-	gart_resource.end = aper_base + aper_size - 1;
-	insert_resource(&iomem_resource, &gart_resource);
-}
-
 /* This code runs before the PCI subsystem is initialized, so just
    access the northbridge directly. */
 
@@ -96,7 +83,6 @@
 	memblock_reserve(addr, aper_size);
 	printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n",
 			aper_size >> 10, addr);
-	insert_aperture_resource((u32)addr, aper_size);
 	register_nosave_region(addr >> PAGE_SHIFT,
 			       (addr+aper_size) >> PAGE_SHIFT);
 
@@ -444,12 +430,8 @@
 
 out:
 	if (!fix && !fallback_aper_force) {
-		if (last_aper_base) {
-			unsigned long n = (32 * 1024 * 1024) << last_aper_order;
-
-			insert_aperture_resource((u32)last_aper_base, n);
+		if (last_aper_base)
 			return 1;
-		}
 		return 0;
 	}
 
diff --git a/block/blk-core.c b/block/blk-core.c
index 853f927..bfe16d5 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -693,20 +693,11 @@
 	if (!uninit_q)
 		return NULL;
 
-	uninit_q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
-	if (!uninit_q->flush_rq)
-		goto out_cleanup_queue;
-
 	q = blk_init_allocated_queue(uninit_q, rfn, lock);
 	if (!q)
-		goto out_free_flush_rq;
-	return q;
+		blk_cleanup_queue(uninit_q);
 
-out_free_flush_rq:
-	kfree(uninit_q->flush_rq);
-out_cleanup_queue:
-	blk_cleanup_queue(uninit_q);
-	return NULL;
+	return q;
 }
 EXPORT_SYMBOL(blk_init_queue_node);
 
@@ -717,9 +708,13 @@
 	if (!q)
 		return NULL;
 
-	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+	q->flush_rq = kzalloc(sizeof(struct request), GFP_KERNEL);
+	if (!q->flush_rq)
 		return NULL;
 
+	if (blk_init_rl(&q->root_rl, q, GFP_KERNEL))
+		goto fail;
+
 	q->request_fn		= rfn;
 	q->prep_rq_fn		= NULL;
 	q->unprep_rq_fn		= NULL;
@@ -742,12 +737,16 @@
 	/* init elevator */
 	if (elevator_init(q, NULL)) {
 		mutex_unlock(&q->sysfs_lock);
-		return NULL;
+		goto fail;
 	}
 
 	mutex_unlock(&q->sysfs_lock);
 
 	return q;
+
+fail:
+	kfree(q->flush_rq);
+	return NULL;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
 
diff --git a/block/blk-flush.c b/block/blk-flush.c
index f598f79..43e6b47 100644
--- a/block/blk-flush.c
+++ b/block/blk-flush.c
@@ -140,14 +140,17 @@
 	blk_mq_insert_request(rq, false, true, false);
 }
 
-static bool blk_flush_queue_rq(struct request *rq)
+static bool blk_flush_queue_rq(struct request *rq, bool add_front)
 {
 	if (rq->q->mq_ops) {
 		INIT_WORK(&rq->mq_flush_work, mq_flush_run);
 		kblockd_schedule_work(rq->q, &rq->mq_flush_work);
 		return false;
 	} else {
-		list_add_tail(&rq->queuelist, &rq->q->queue_head);
+		if (add_front)
+			list_add(&rq->queuelist, &rq->q->queue_head);
+		else
+			list_add_tail(&rq->queuelist, &rq->q->queue_head);
 		return true;
 	}
 }
@@ -193,7 +196,7 @@
 
 	case REQ_FSEQ_DATA:
 		list_move_tail(&rq->flush.list, &q->flush_data_in_flight);
-		queued = blk_flush_queue_rq(rq);
+		queued = blk_flush_queue_rq(rq, true);
 		break;
 
 	case REQ_FSEQ_DONE:
@@ -326,7 +329,7 @@
 	q->flush_rq->rq_disk = first_rq->rq_disk;
 	q->flush_rq->end_io = flush_end_io;
 
-	return blk_flush_queue_rq(q->flush_rq);
+	return blk_flush_queue_rq(q->flush_rq, false);
 }
 
 static void flush_data_end_io(struct request *rq, int error)
diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index 51602695..d777bb7 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -4498,7 +4498,7 @@
 	}
 	dev_info(&pdev->dev, "NUMA node %d (closest: %d,%d, probe on %d:%d)\n",
 		my_node, pcibus_to_node(pdev->bus), dev_to_node(&pdev->dev),
-		cpu_to_node(smp_processor_id()), smp_processor_id());
+		cpu_to_node(raw_smp_processor_id()), raw_smp_processor_id());
 
 	dd = kzalloc_node(sizeof(struct driver_data), GFP_KERNEL, my_node);
 	if (dd == NULL) {
diff --git a/drivers/clocksource/vf_pit_timer.c b/drivers/clocksource/vf_pit_timer.c
index 02821b0..a918bc4 100644
--- a/drivers/clocksource/vf_pit_timer.c
+++ b/drivers/clocksource/vf_pit_timer.c
@@ -54,7 +54,7 @@
 
 static u64 pit_read_sched_clock(void)
 {
-	return __raw_readl(clksrc_base + PITCVAL);
+	return ~__raw_readl(clksrc_base + PITCVAL);
 }
 
 static int __init pit_clocksource_init(unsigned long rate)
diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 5736aaa..f7af69b 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -468,8 +468,8 @@
 	} else {
 		list_for_each_entry_safe(dev, tmp, &driver->legacy_dev_list,
 					 legacy_dev_list) {
-			drm_put_dev(dev);
 			list_del(&dev->legacy_dev_list);
+			drm_put_dev(dev);
 		}
 	}
 	DRM_INFO("Module unloaded\n");
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 215131a..c204b4e 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -172,20 +172,24 @@
 
 	ret = exynos_drm_subdrv_open(dev, file);
 	if (ret)
-		goto out;
+		goto err_file_priv_free;
 
 	anon_filp = anon_inode_getfile("exynos_gem", &exynos_drm_gem_fops,
 					NULL, 0);
 	if (IS_ERR(anon_filp)) {
 		ret = PTR_ERR(anon_filp);
-		goto out;
+		goto err_subdrv_close;
 	}
 
 	anon_filp->f_mode = FMODE_READ | FMODE_WRITE;
 	file_priv->anon_filp = anon_filp;
 
 	return ret;
-out:
+
+err_subdrv_close:
+	exynos_drm_subdrv_close(dev, file);
+
+err_file_priv_free:
 	kfree(file_priv);
 	file->driver_priv = NULL;
 	return ret;
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index d58b4e2..28d24ca 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -214,6 +214,13 @@
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	int bios_reserved = 0;
 
+#ifdef CONFIG_INTEL_IOMMU
+	if (intel_iommu_gfx_mapped) {
+		DRM_INFO("DMAR active, disabling use of stolen memory\n");
+		return 0;
+	}
+#endif
+
 	if (dev_priv->gtt.stolen_size == 0)
 		return 0;
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 9fec711..d554169 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -618,33 +618,25 @@
 
 /* raw reads, only for fast reads of display block, no need for forcewake etc. */
 #define __raw_i915_read32(dev_priv__, reg__) readl((dev_priv__)->regs + (reg__))
-#define __raw_i915_read16(dev_priv__, reg__) readw((dev_priv__)->regs + (reg__))
 
 static bool ilk_pipe_in_vblank_locked(struct drm_device *dev, enum pipe pipe)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	uint32_t status;
+	int reg;
 
-	if (INTEL_INFO(dev)->gen < 7) {
-		status = pipe == PIPE_A ?
-			DE_PIPEA_VBLANK :
-			DE_PIPEB_VBLANK;
+	if (INTEL_INFO(dev)->gen >= 8) {
+		status = GEN8_PIPE_VBLANK;
+		reg = GEN8_DE_PIPE_ISR(pipe);
+	} else if (INTEL_INFO(dev)->gen >= 7) {
+		status = DE_PIPE_VBLANK_IVB(pipe);
+		reg = DEISR;
 	} else {
-		switch (pipe) {
-		default:
-		case PIPE_A:
-			status = DE_PIPEA_VBLANK_IVB;
-			break;
-		case PIPE_B:
-			status = DE_PIPEB_VBLANK_IVB;
-			break;
-		case PIPE_C:
-			status = DE_PIPEC_VBLANK_IVB;
-			break;
-		}
+		status = DE_PIPE_VBLANK(pipe);
+		reg = DEISR;
 	}
 
-	return __raw_i915_read32(dev_priv, DEISR) & status;
+	return __raw_i915_read32(dev_priv, reg) & status;
 }
 
 static int i915_get_crtc_scanoutpos(struct drm_device *dev, int pipe,
@@ -702,7 +694,28 @@
 		else
 			position = __raw_i915_read32(dev_priv, PIPEDSL(pipe)) & DSL_LINEMASK_GEN3;
 
-		if (HAS_PCH_SPLIT(dev)) {
+		if (HAS_DDI(dev)) {
+			/*
+			 * On HSW HDMI outputs there seems to be a 2 line
+			 * difference, whereas eDP has the normal 1 line
+			 * difference that earlier platforms have. External
+			 * DP is unknown. For now just check for the 2 line
+			 * difference case on all output types on HSW+.
+			 *
+			 * This might misinterpret the scanline counter being
+			 * one line too far along on eDP, but that's less
+			 * dangerous than the alternative since that would lead
+			 * the vblank timestamp code astray when it sees a
+			 * scanline count before vblank_start during a vblank
+			 * interrupt.
+			 */
+			in_vbl = ilk_pipe_in_vblank_locked(dev, pipe);
+			if ((in_vbl && (position == vbl_start - 2 ||
+					position == vbl_start - 1)) ||
+			    (!in_vbl && (position == vbl_end - 2 ||
+					 position == vbl_end - 1)))
+				position = (position + 2) % vtotal;
+		} else if (HAS_PCH_SPLIT(dev)) {
 			/*
 			 * The scanline counter increments at the leading edge
 			 * of hsync, ie. it completely misses the active portion
@@ -2769,10 +2782,9 @@
 		return;
 
 	if (HAS_PCH_IBX(dev)) {
-		mask = SDE_GMBUS | SDE_AUX_MASK | SDE_TRANSB_FIFO_UNDER |
-		       SDE_TRANSA_FIFO_UNDER | SDE_POISON;
+		mask = SDE_GMBUS | SDE_AUX_MASK | SDE_POISON;
 	} else {
-		mask = SDE_GMBUS_CPT | SDE_AUX_MASK_CPT | SDE_ERROR_CPT;
+		mask = SDE_GMBUS_CPT | SDE_AUX_MASK_CPT;
 
 		I915_WRITE(SERR_INT, I915_READ(SERR_INT));
 	}
@@ -2832,20 +2844,19 @@
 		display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE_IVB |
 				DE_PCH_EVENT_IVB | DE_PLANEC_FLIP_DONE_IVB |
 				DE_PLANEB_FLIP_DONE_IVB |
-				DE_PLANEA_FLIP_DONE_IVB | DE_AUX_CHANNEL_A_IVB |
-				DE_ERR_INT_IVB);
+				DE_PLANEA_FLIP_DONE_IVB | DE_AUX_CHANNEL_A_IVB);
 		extra_mask = (DE_PIPEC_VBLANK_IVB | DE_PIPEB_VBLANK_IVB |
-			      DE_PIPEA_VBLANK_IVB);
+			      DE_PIPEA_VBLANK_IVB | DE_ERR_INT_IVB);
 
 		I915_WRITE(GEN7_ERR_INT, I915_READ(GEN7_ERR_INT));
 	} else {
 		display_mask = (DE_MASTER_IRQ_CONTROL | DE_GSE | DE_PCH_EVENT |
 				DE_PLANEA_FLIP_DONE | DE_PLANEB_FLIP_DONE |
 				DE_AUX_CHANNEL_A |
-				DE_PIPEB_FIFO_UNDERRUN | DE_PIPEA_FIFO_UNDERRUN |
 				DE_PIPEB_CRC_DONE | DE_PIPEA_CRC_DONE |
 				DE_POISON);
-		extra_mask = DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT;
+		extra_mask = DE_PIPEA_VBLANK | DE_PIPEB_VBLANK | DE_PCU_EVENT |
+				DE_PIPEB_FIFO_UNDERRUN | DE_PIPEA_FIFO_UNDERRUN;
 	}
 
 	dev_priv->irq_mask = ~display_mask;
@@ -2961,9 +2972,9 @@
 	struct drm_device *dev = dev_priv->dev;
 	uint32_t de_pipe_masked = GEN8_PIPE_FLIP_DONE |
 		GEN8_PIPE_CDCLK_CRC_DONE |
-		GEN8_PIPE_FIFO_UNDERRUN |
 		GEN8_DE_PIPE_IRQ_FAULT_ERRORS;
-	uint32_t de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK;
+	uint32_t de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK |
+		GEN8_PIPE_FIFO_UNDERRUN;
 	int pipe;
 	dev_priv->de_irq_mask[PIPE_A] = ~de_pipe_masked;
 	dev_priv->de_irq_mask[PIPE_B] = ~de_pipe_masked;
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index e06b9e0..234ac5f 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1244,6 +1244,7 @@
 	if (type == INTEL_OUTPUT_DISPLAYPORT || type == INTEL_OUTPUT_EDP) {
 		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
 		intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
+		ironlake_edp_panel_vdd_on(intel_dp);
 		ironlake_edp_panel_off(intel_dp);
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 57552eb..2688f6d 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1249,17 +1249,24 @@
 
 	DRM_DEBUG_KMS("Turn eDP power off\n");
 
+	WARN(!intel_dp->want_panel_vdd, "Need VDD to turn off panel\n");
+
 	pp = ironlake_get_pp_control(intel_dp);
 	/* We need to switch off panel power _and_ force vdd, for otherwise some
 	 * panels get very unhappy and cease to work. */
-	pp &= ~(POWER_TARGET_ON | PANEL_POWER_RESET | EDP_BLC_ENABLE);
+	pp &= ~(POWER_TARGET_ON | EDP_FORCE_VDD | PANEL_POWER_RESET | EDP_BLC_ENABLE);
 
 	pp_ctrl_reg = _pp_ctrl_reg(intel_dp);
 
 	I915_WRITE(pp_ctrl_reg, pp);
 	POSTING_READ(pp_ctrl_reg);
 
+	intel_dp->want_panel_vdd = false;
+
 	ironlake_wait_panel_off(intel_dp);
+
+	/* We got a reference when we enabled the VDD. */
+	intel_runtime_pm_put(dev_priv);
 }
 
 void ironlake_edp_backlight_on(struct intel_dp *intel_dp)
@@ -1639,7 +1646,7 @@
 		val |= EDP_PSR_LINK_DISABLE;
 
 	I915_WRITE(EDP_PSR_CTL(dev), val |
-		   IS_BROADWELL(dev) ? 0 : link_entry_time |
+		   (IS_BROADWELL(dev) ? 0 : link_entry_time) |
 		   max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT |
 		   idle_frames << EDP_PSR_IDLE_FRAME_SHIFT |
 		   EDP_PSR_ENABLE);
@@ -1784,6 +1791,7 @@
 
 	/* Make sure the panel is off before trying to change the mode. But also
 	 * ensure that we have vdd while we switch off the panel. */
+	ironlake_edp_panel_vdd_on(intel_dp);
 	ironlake_edp_backlight_off(intel_dp);
 	intel_dp_sink_dpms(intel_dp, DRM_MODE_DPMS_OFF);
 	ironlake_edp_panel_off(intel_dp);
diff --git a/drivers/hid/hid-lg4ff.c b/drivers/hid/hid-lg4ff.c
index befe0e3..24883b4 100644
--- a/drivers/hid/hid-lg4ff.c
+++ b/drivers/hid/hid-lg4ff.c
@@ -43,6 +43,7 @@
 #define G25_REV_MIN 0x22
 #define G27_REV_MAJ 0x12
 #define G27_REV_MIN 0x38
+#define G27_2_REV_MIN 0x39
 
 #define to_hid_device(pdev) container_of(pdev, struct hid_device, dev)
 
@@ -130,6 +131,7 @@
 	{DFP_REV_MAJ,  DFP_REV_MIN,  &native_dfp},	/* Driving Force Pro */
 	{G25_REV_MAJ,  G25_REV_MIN,  &native_g25},	/* G25 */
 	{G27_REV_MAJ,  G27_REV_MIN,  &native_g27},	/* G27 */
+	{G27_REV_MAJ,  G27_2_REV_MIN,  &native_g27},	/* G27 v2 */
 };
 
 /* Recalculates X axis value accordingly to currently selected range */
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index 1235405..2f19b15 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -42,6 +42,7 @@
 #define DUALSHOCK4_CONTROLLER_BT  BIT(6)
 
 #define SONY_LED_SUPPORT (SIXAXIS_CONTROLLER_USB | BUZZ_CONTROLLER | DUALSHOCK4_CONTROLLER_USB)
+#define SONY_FF_SUPPORT (SIXAXIS_CONTROLLER_USB | DUALSHOCK4_CONTROLLER_USB)
 
 #define MAX_LEDS 4
 
@@ -499,6 +500,7 @@
 	__u8 right;
 #endif
 
+	__u8 worker_initialized;
 	__u8 led_state[MAX_LEDS];
 	__u8 led_count;
 };
@@ -993,22 +995,11 @@
 	return input_ff_create_memless(input_dev, NULL, sony_play_effect);
 }
 
-static void sony_destroy_ff(struct hid_device *hdev)
-{
-	struct sony_sc *sc = hid_get_drvdata(hdev);
-
-	cancel_work_sync(&sc->state_worker);
-}
-
 #else
 static int sony_init_ff(struct hid_device *hdev)
 {
 	return 0;
 }
-
-static void sony_destroy_ff(struct hid_device *hdev)
-{
-}
 #endif
 
 static int sony_set_output_report(struct sony_sc *sc, int req_id, int req_size)
@@ -1077,6 +1068,8 @@
 	if (sc->quirks & SIXAXIS_CONTROLLER_USB) {
 		hdev->hid_output_raw_report = sixaxis_usb_output_raw_report;
 		ret = sixaxis_set_operational_usb(hdev);
+
+		sc->worker_initialized = 1;
 		INIT_WORK(&sc->state_worker, sixaxis_state_worker);
 	}
 	else if (sc->quirks & SIXAXIS_CONTROLLER_BT)
@@ -1087,6 +1080,7 @@
 		if (ret < 0)
 			goto err_stop;
 
+		sc->worker_initialized = 1;
 		INIT_WORK(&sc->state_worker, dualshock4_state_worker);
 	} else {
 		ret = 0;
@@ -1101,9 +1095,11 @@
 			goto err_stop;
 	}
 
-	ret = sony_init_ff(hdev);
-	if (ret < 0)
-		goto err_stop;
+	if (sc->quirks & SONY_FF_SUPPORT) {
+		ret = sony_init_ff(hdev);
+		if (ret < 0)
+			goto err_stop;
+	}
 
 	return 0;
 err_stop:
@@ -1120,7 +1116,8 @@
 	if (sc->quirks & SONY_LED_SUPPORT)
 		sony_leds_remove(hdev);
 
-	sony_destroy_ff(hdev);
+	if (sc->worker_initialized)
+		cancel_work_sync(&sc->state_worker);
 
 	hid_hw_stop(hdev);
 }
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index cb0137b..ab24ce2 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -320,13 +320,13 @@
 			hid_hw_close(hidraw->hid);
 			wake_up_interruptible(&hidraw->wait);
 		}
+		device_destroy(hidraw_class,
+			       MKDEV(hidraw_major, hidraw->minor));
 	} else {
 		--hidraw->open;
 	}
 	if (!hidraw->open) {
 		if (!hidraw->exist) {
-			device_destroy(hidraw_class,
-					MKDEV(hidraw_major, hidraw->minor));
 			hidraw_table[hidraw->minor] = NULL;
 			kfree(hidraw);
 		} else {
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 4e4cc28..4cdb3a1 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -495,10 +495,6 @@
 	FILTER_TRACE_FN,
 };
 
-#define EVENT_STORAGE_SIZE 128
-extern struct mutex event_storage_mutex;
-extern char event_storage[EVENT_STORAGE_SIZE];
-
 extern int trace_event_raw_init(struct ftrace_event_call *call);
 extern int trace_define_field(struct ftrace_event_call *call, const char *type,
 			      const char *name, int offset, int size,
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 1da693d..b66c211 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -250,8 +250,7 @@
 	int (*rmap_one)(struct page *page, struct vm_area_struct *vma,
 					unsigned long addr, void *arg);
 	int (*done)(struct page *page);
-	int (*file_nonlinear)(struct page *, struct address_space *,
-					struct vm_area_struct *vma);
+	int (*file_nonlinear)(struct page *, struct address_space *, void *arg);
 	struct anon_vma *(*anon_lock)(struct page *page);
 	bool (*invalid_vma)(struct vm_area_struct *vma, void *arg);
 };
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 1a8b28d..1ee19a2 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -310,15 +310,12 @@
 #undef __array
 #define __array(type, item, len)					\
 	do {								\
-		mutex_lock(&event_storage_mutex);			\
+		char *type_str = #type"["__stringify(len)"]";		\
 		BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);			\
-		snprintf(event_storage, sizeof(event_storage),		\
-			 "%s[%d]", #type, len);				\
-		ret = trace_define_field(event_call, event_storage, #item, \
+		ret = trace_define_field(event_call, type_str, #item,	\
 				 offsetof(typeof(field), item),		\
 				 sizeof(field.item),			\
 				 is_signed_type(type), FILTER_OTHER);	\
-		mutex_unlock(&event_storage_mutex);			\
 		if (ret)						\
 			return ret;					\
 	} while (0);
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 105f273..0c753dd 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4112,17 +4112,17 @@
 
 	err = percpu_ref_init(&css->refcnt, css_release);
 	if (err)
-		goto err_free;
+		goto err_free_css;
 
 	init_css(css, ss, cgrp);
 
 	err = cgroup_populate_dir(cgrp, 1 << ss->subsys_id);
 	if (err)
-		goto err_free;
+		goto err_free_percpu_ref;
 
 	err = online_css(css);
 	if (err)
-		goto err_free;
+		goto err_clear_dir;
 
 	dget(cgrp->dentry);
 	css_get(css->parent);
@@ -4138,8 +4138,11 @@
 
 	return 0;
 
-err_free:
+err_clear_dir:
+	cgroup_clear_dir(css->cgroup, 1 << css->ss->subsys_id);
+err_free_percpu_ref:
 	percpu_ref_cancel_init(&css->refcnt);
+err_free_css:
 	ss->css_free(css);
 	return err;
 }
diff --git a/kernel/futex.c b/kernel/futex.c
index 44a1261..08ec814 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -234,6 +234,7 @@
  * waiting on a futex.
  */
 struct futex_hash_bucket {
+	atomic_t waiters;
 	spinlock_t lock;
 	struct plist_head chain;
 } ____cacheline_aligned_in_smp;
@@ -253,22 +254,37 @@
 	smp_mb__after_atomic_inc();
 }
 
-static inline bool hb_waiters_pending(struct futex_hash_bucket *hb)
+/*
+ * Reflects a new waiter being added to the waitqueue.
+ */
+static inline void hb_waiters_inc(struct futex_hash_bucket *hb)
 {
 #ifdef CONFIG_SMP
+	atomic_inc(&hb->waiters);
 	/*
-	 * Tasks trying to enter the critical region are most likely
-	 * potential waiters that will be added to the plist. Ensure
-	 * that wakers won't miss to-be-slept tasks in the window between
-	 * the wait call and the actual plist_add.
+	 * Full barrier (A), see the ordering comment above.
 	 */
-	if (spin_is_locked(&hb->lock))
-		return true;
-	smp_rmb(); /* Make sure we check the lock state first */
+	smp_mb__after_atomic_inc();
+#endif
+}
 
-	return !plist_head_empty(&hb->chain);
+/*
+ * Reflects a waiter being removed from the waitqueue by wakeup
+ * paths.
+ */
+static inline void hb_waiters_dec(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+	atomic_dec(&hb->waiters);
+#endif
+}
+
+static inline int hb_waiters_pending(struct futex_hash_bucket *hb)
+{
+#ifdef CONFIG_SMP
+	return atomic_read(&hb->waiters);
 #else
-	return true;
+	return 1;
 #endif
 }
 
@@ -954,6 +970,7 @@
 
 	hb = container_of(q->lock_ptr, struct futex_hash_bucket, lock);
 	plist_del(&q->list, &hb->chain);
+	hb_waiters_dec(hb);
 }
 
 /*
@@ -1257,7 +1274,9 @@
 	 */
 	if (likely(&hb1->chain != &hb2->chain)) {
 		plist_del(&q->list, &hb1->chain);
+		hb_waiters_dec(hb1);
 		plist_add(&q->list, &hb2->chain);
+		hb_waiters_inc(hb2);
 		q->lock_ptr = &hb2->lock;
 	}
 	get_futex_key_refs(key2);
@@ -1600,6 +1619,17 @@
 	struct futex_hash_bucket *hb;
 
 	hb = hash_futex(&q->key);
+
+	/*
+	 * Increment the counter before taking the lock so that
+	 * a potential waker won't miss a to-be-slept task that is
+	 * waiting for the spinlock. This is safe as all queue_lock()
+	 * users end up calling queue_me(). Similarly, for housekeeping,
+	 * decrement the counter at queue_unlock() when some error has
+	 * occurred and we don't end up adding the task to the list.
+	 */
+	hb_waiters_inc(hb);
+
 	q->lock_ptr = &hb->lock;
 
 	spin_lock(&hb->lock); /* implies MB (A) */
@@ -1611,6 +1641,7 @@
 	__releases(&hb->lock)
 {
 	spin_unlock(&hb->lock);
+	hb_waiters_dec(hb);
 }
 
 /**
@@ -2342,6 +2373,7 @@
 		 * Unqueue the futex_q and determine which it was.
 		 */
 		plist_del(&q->list, &hb->chain);
+		hb_waiters_dec(hb);
 
 		/* Handle spurious wakeups gracefully */
 		ret = -EWOULDBLOCK;
@@ -2875,6 +2907,7 @@
 		futex_cmpxchg_enabled = 1;
 
 	for (i = 0; i < futex_hashsize; i++) {
+		atomic_set(&futex_queues[i].waiters, 0);
 		plist_head_init(&futex_queues[i].chain);
 		spin_lock_init(&futex_queues[i].lock);
 	}
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f3989ce..7b16d40 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -27,12 +27,6 @@
 
 DEFINE_MUTEX(event_mutex);
 
-DEFINE_MUTEX(event_storage_mutex);
-EXPORT_SYMBOL_GPL(event_storage_mutex);
-
-char event_storage[EVENT_STORAGE_SIZE];
-EXPORT_SYMBOL_GPL(event_storage);
-
 LIST_HEAD(ftrace_events);
 static LIST_HEAD(ftrace_common_fields);
 
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 7c3e3e7..ee0a509 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -95,15 +95,12 @@
 #undef __array
 #define __array(type, item, len)					\
 	do {								\
+		char *type_str = #type"["__stringify(len)"]";		\
 		BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);			\
-		mutex_lock(&event_storage_mutex);			\
-		snprintf(event_storage, sizeof(event_storage),		\
-			 "%s[%d]", #type, len);				\
-		ret = trace_define_field(event_call, event_storage, #item, \
+		ret = trace_define_field(event_call, type_str, #item,	\
 				 offsetof(typeof(field), item),		\
 				 sizeof(field.item),			\
 				 is_signed_type(type), filter_type);	\
-		mutex_unlock(&event_storage_mutex);			\
 		if (ret)						\
 			return ret;					\
 	} while (0);
diff --git a/mm/fremap.c b/mm/fremap.c
index bbc4d66..34feba6 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -23,28 +23,44 @@
 
 #include "internal.h"
 
+static int mm_counter(struct page *page)
+{
+	return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES;
+}
+
 static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long addr, pte_t *ptep)
 {
 	pte_t pte = *ptep;
+	struct page *page;
+	swp_entry_t entry;
 
 	if (pte_present(pte)) {
-		struct page *page;
-
 		flush_cache_page(vma, addr, pte_pfn(pte));
 		pte = ptep_clear_flush(vma, addr, ptep);
 		page = vm_normal_page(vma, addr, pte);
 		if (page) {
 			if (pte_dirty(pte))
 				set_page_dirty(page);
+			update_hiwater_rss(mm);
+			dec_mm_counter(mm, mm_counter(page));
 			page_remove_rmap(page);
 			page_cache_release(page);
-			update_hiwater_rss(mm);
-			dec_mm_counter(mm, MM_FILEPAGES);
 		}
-	} else {
-		if (!pte_file(pte))
-			free_swap_and_cache(pte_to_swp_entry(pte));
+	} else {	/* zap_pte() is not called when pte_none() */
+		if (!pte_file(pte)) {
+			update_hiwater_rss(mm);
+			entry = pte_to_swp_entry(pte);
+			if (non_swap_entry(entry)) {
+				if (is_migration_entry(entry)) {
+					page = migration_entry_to_page(entry);
+					dec_mm_counter(mm, mm_counter(page));
+				}
+			} else {
+				free_swap_and_cache(entry);
+				dec_mm_counter(mm, MM_SWAPENTS);
+			}
+		}
 		pte_clear_not_present_full(mm, addr, ptep, 0);
 	}
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index b494fdb..bed4880 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -178,6 +178,37 @@
 }
 
 /*
+ * Congratulations to trinity for discovering this bug.
+ * mm/fremap.c's remap_file_pages() accepts any range within a single vma to
+ * convert that vma to VM_NONLINEAR; and generic_file_remap_pages() will then
+ * replace the specified range by file ptes throughout (maybe populated after).
+ * If page migration finds a page within that range, while it's still located
+ * by vma_interval_tree rather than lost to i_mmap_nonlinear list, no problem:
+ * zap_pte() clears the temporary migration entry before mmap_sem is dropped.
+ * But if the migrating page is in a part of the vma outside the range to be
+ * remapped, then it will not be cleared, and remove_migration_ptes() needs to
+ * deal with it.  Fortunately, this part of the vma is of course still linear,
+ * so we just need to use linear location on the nonlinear list.
+ */
+static int remove_linear_migration_ptes_from_nonlinear(struct page *page,
+		struct address_space *mapping, void *arg)
+{
+	struct vm_area_struct *vma;
+	/* hugetlbfs does not support remap_pages, so no huge pgoff worries */
+	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
+	unsigned long addr;
+
+	list_for_each_entry(vma,
+		&mapping->i_mmap_nonlinear, shared.nonlinear) {
+
+		addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+		if (addr >= vma->vm_start && addr < vma->vm_end)
+			remove_migration_pte(page, vma, addr, arg);
+	}
+	return SWAP_AGAIN;
+}
+
+/*
  * Get rid of all migration entries and replace them by
  * references to the indicated page.
  */
@@ -186,6 +217,7 @@
 	struct rmap_walk_control rwc = {
 		.rmap_one = remove_migration_pte,
 		.arg = old,
+		.file_nonlinear = remove_linear_migration_ptes_from_nonlinear,
 	};
 
 	rmap_walk(new, &rwc);
diff --git a/mm/rmap.c b/mm/rmap.c
index d9d4231..8fc049f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1360,8 +1360,9 @@
 }
 
 static int try_to_unmap_nonlinear(struct page *page,
-		struct address_space *mapping, struct vm_area_struct *vma)
+		struct address_space *mapping, void *arg)
 {
+	struct vm_area_struct *vma;
 	int ret = SWAP_AGAIN;
 	unsigned long cursor;
 	unsigned long max_nl_cursor = 0;
@@ -1663,7 +1664,7 @@
 	if (list_empty(&mapping->i_mmap_nonlinear))
 		goto done;
 
-	ret = rwc->file_nonlinear(page, mapping, vma);
+	ret = rwc->file_nonlinear(page, mapping, rwc->arg);
 
 done:
 	mutex_unlock(&mapping->i_mmap_mutex);
diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 7a20897..7403f34 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -133,7 +133,7 @@
 		kfree(data);
 	}
 	snd_card_unref(compr->card);
-	return 0;
+	return ret;
 }
 
 static int snd_compr_free(struct inode *inode, struct file *f)
diff --git a/sound/pci/oxygen/xonar_dg.c b/sound/pci/oxygen/xonar_dg.c
index ed6f199..4cf3200 100644
--- a/sound/pci/oxygen/xonar_dg.c
+++ b/sound/pci/oxygen/xonar_dg.c
@@ -238,11 +238,21 @@
 	cs4245_write_spi(chip, CS4245_MCLK_FREQ);
 }
 
+static inline unsigned int shift_bits(unsigned int value,
+				      unsigned int shift_from,
+				      unsigned int shift_to,
+				      unsigned int mask)
+{
+	if (shift_from < shift_to)
+		return (value << (shift_to - shift_from)) & mask;
+	else
+		return (value >> (shift_from - shift_to)) & mask;
+}
+
 unsigned int adjust_dg_dac_routing(struct oxygen *chip,
 					  unsigned int play_routing)
 {
 	struct dg *data = chip->model_data;
-	unsigned int routing = 0;
 
 	switch (data->output_sel) {
 	case PLAYBACK_DST_HP:
@@ -252,15 +262,23 @@
 			OXYGEN_PLAY_MUTE67, OXYGEN_PLAY_MUTE_MASK);
 		break;
 	case PLAYBACK_DST_MULTICH:
-		routing = (0 << OXYGEN_PLAY_DAC0_SOURCE_SHIFT) |
-			  (2 << OXYGEN_PLAY_DAC1_SOURCE_SHIFT) |
-			  (1 << OXYGEN_PLAY_DAC2_SOURCE_SHIFT) |
-			  (0 << OXYGEN_PLAY_DAC3_SOURCE_SHIFT);
 		oxygen_write8_masked(chip, OXYGEN_PLAY_ROUTING,
 			OXYGEN_PLAY_MUTE01, OXYGEN_PLAY_MUTE_MASK);
 		break;
 	}
-	return routing;
+	return (play_routing & OXYGEN_PLAY_DAC0_SOURCE_MASK) |
+	       shift_bits(play_routing,
+			  OXYGEN_PLAY_DAC2_SOURCE_SHIFT,
+			  OXYGEN_PLAY_DAC1_SOURCE_SHIFT,
+			  OXYGEN_PLAY_DAC1_SOURCE_MASK) |
+	       shift_bits(play_routing,
+			  OXYGEN_PLAY_DAC1_SOURCE_SHIFT,
+			  OXYGEN_PLAY_DAC2_SOURCE_SHIFT,
+			  OXYGEN_PLAY_DAC2_SOURCE_MASK) |
+	       shift_bits(play_routing,
+			  OXYGEN_PLAY_DAC0_SOURCE_SHIFT,
+			  OXYGEN_PLAY_DAC3_SOURCE_SHIFT,
+			  OXYGEN_PLAY_DAC3_SOURCE_MASK);
 }
 
 void dump_cs4245_registers(struct oxygen *chip,