Merge branch 'perf/core' into oprofile/master

Merge reason: Resolve conflicts with Don's NMI rework:

    commit 9c48f1c629ecfa114850c03f875c6691003214de
    Author: Don Zickus <dzickus@redhat.com>
    Date:   Fri Sep 30 15:06:21 2011 -0400
    x86, nmi: Wire up NMI handlers to new routines

Conflicts:
	arch/x86/oprofile/nmi_timer_int.c

Signed-off-by: Robert Richter <robert.richter@amd.com>

210 files changed, 2140 insertions, 1497 deletions

diff --git a/Documentation/hwmon/coretemp b/Documentation/hwmon/coretemp
index fa8776ab9b18..84d46c0c71a3 100644
--- a/Documentation/hwmon/coretemp
+++ b/Documentation/hwmon/coretemp
@@ -35,13 +35,6 @@ the Out-Of-Spec bit. Following table summarizes the exported sysfs files:
 All Sysfs entries are named with their core_id (represented here by 'X').
 tempX_input	 - Core temperature (in millidegrees Celsius).
 tempX_max	 - All cooling devices should be turned on (on Core2).
-		   Initialized with IA32_THERM_INTERRUPT. When the CPU
-		   temperature reaches this temperature, an interrupt is
-		   generated and tempX_max_alarm is set.
-tempX_max_hyst   - If the CPU temperature falls below than temperature,
-		   an interrupt is generated and tempX_max_alarm is reset.
-tempX_max_alarm  - Set if the temperature reaches or exceeds tempX_max.
-		   Reset if the temperature drops to or below tempX_max_hyst.
 tempX_crit	 - Maximum junction temperature (in millidegrees Celsius).
 tempX_crit_alarm - Set when Out-of-spec bit is set, never clears.
 		   Correct CPU operation is no longer guaranteed.
@@ -49,9 +42,10 @@ tempX_label	 - Contains string "Core X", where X is processor
 		   number. For Package temp, this will be "Physical id Y",
 		   where Y is the package number.
 
-The TjMax temperature is set to 85 degrees C if undocumented model specific
-register (UMSR) 0xee has bit 30 set. If not the TjMax is 100 degrees C as
-(sometimes) documented in processor datasheet.
+On CPU models which support it, TjMax is read from a model-specific register.
+On other models, it is set to an arbitrary value based on weak heuristics.
+If these heuristics don't work for you, you can pass the correct TjMax value
+as a module parameter (tjmax).
 
 Appendix A. Known TjMax lists (TBD):
 Some information comes from ark.intel.com
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 81546990f41c..ca5cdcd0f0e3 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1042,7 +1042,7 @@ conf/interface/*:
 	The functional behaviour for certain settings is different
 	depending on whether local forwarding is enabled or not.
 
-accept_ra - BOOLEAN
+accept_ra - INTEGER
 	Accept Router Advertisements; autoconfigure using them.
 
 	Possible values are:
@@ -1106,7 +1106,7 @@ dad_transmits - INTEGER
 	The amount of Duplicate Address Detection probes to send.
 	Default: 1
 
-forwarding - BOOLEAN
+forwarding - INTEGER
 	Configure interface-specific Host/Router behaviour.
 
 	Note: It is recommended to have the same setting on all
diff --git a/Documentation/networking/scaling.txt b/Documentation/networking/scaling.txt
index 58fd7414e6c0..8ce7c30e7230 100644
--- a/Documentation/networking/scaling.txt
+++ b/Documentation/networking/scaling.txt
@@ -243,7 +243,7 @@ configured. The number of entries in the global flow table is set through:
 
 The number of entries in the per-queue flow table are set through:
 
- /sys/class/net/<dev>/queues/tx-<n>/rps_flow_cnt
+ /sys/class/net/<dev>/queues/rx-<n>/rps_flow_cnt
 
 == Suggested Configuration
 
diff --git a/Documentation/vm/transhuge.txt b/Documentation/vm/transhuge.txt
index 0924aaca3302..29bdf62aac09 100644
--- a/Documentation/vm/transhuge.txt
+++ b/Documentation/vm/transhuge.txt
@@ -123,10 +123,11 @@ be automatically shutdown if it's set to "never".
 khugepaged runs usually at low frequency so while one may not want to
 invoke defrag algorithms synchronously during the page faults, it
 should be worth invoking defrag at least in khugepaged. However it's
-also possible to disable defrag in khugepaged:
+also possible to disable defrag in khugepaged by writing 0 or enable
+defrag in khugepaged by writing 1:
 
-echo yes >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
-echo no >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
+echo 0 >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
+echo 1 >/sys/kernel/mm/transparent_hugepage/khugepaged/defrag
 
 You can also control how many pages khugepaged should scan at each
 pass:
diff --git a/MAINTAINERS b/MAINTAINERS
index ae8820e173a2..ace8f9c81b96 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6374,7 +6374,6 @@ S:	Supported
 F:	arch/arm/mach-tegra
 
 TEHUTI ETHERNET DRIVER
-M:	Alexander Indenbaum <baum@tehutinetworks.net>
 M:	Andy Gospodarek <andy@greyhouse.net>
 L:	netdev@vger.kernel.org
 S:	Supported
diff --git a/Makefile b/Makefile
index 733dcba61f34..31f967c31e7f 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 1
 SUBLEVEL = 0
-EXTRAVERSION = -rc7
+EXTRAVERSION = -rc9
 NAME = "Divemaster Edition"
 
 # *DOCUMENTATION*
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 3269576dbfa8..3146ed3f6eca 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1283,6 +1283,20 @@ config ARM_ERRATA_364296
 	  processor into full low interrupt latency mode. ARM11MPCore
 	  is not affected.
 
+config ARM_ERRATA_764369
+	bool "ARM errata: Data cache line maintenance operation by MVA may not succeed"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for erratum 764369
+	  affecting Cortex-A9 MPCore with two or more processors (all
+	  current revisions). Under certain timing circumstances, a data
+	  cache line maintenance operation by MVA targeting an Inner
+	  Shareable memory region may fail to proceed up to either the
+	  Point of Coherency or to the Point of Unification of the
+	  system. This workaround adds a DSB instruction before the
+	  relevant cache maintenance functions and sets a specific bit
+	  in the diagnostic control register of the SCU.
+
 endmenu
 
 source "arch/arm/common/Kconfig"
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 8c73900da9ed..253cc86318bf 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -25,17 +25,17 @@
 
 #ifdef CONFIG_SMP
 
-#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
+#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
 	smp_mb();						\
 	__asm__ __volatile__(					\
-	"1:	ldrex	%1, [%2]\n"				\
+	"1:	ldrex	%1, [%3]\n"				\
 	"	" insn "\n"					\
-	"2:	strex	%1, %0, [%2]\n"				\
-	"	teq	%1, #0\n"				\
+	"2:	strex	%2, %0, [%3]\n"				\
+	"	teq	%2, #0\n"				\
 	"	bne	1b\n"					\
 	"	mov	%0, #0\n"				\
-	__futex_atomic_ex_table("%4")				\
-	: "=&r" (ret), "=&r" (oldval)				\
+	__futex_atomic_ex_table("%5")				\
+	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
 	: "cc", "memory")
 
@@ -73,14 +73,14 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 #include <linux/preempt.h>
 #include <asm/domain.h>
 
-#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
+#define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
 	__asm__ __volatile__(					\
-	"1:	" T(ldr) "	%1, [%2]\n"			\
+	"1:	" T(ldr) "	%1, [%3]\n"			\
 	"	" insn "\n"					\
-	"2:	" T(str) "	%0, [%2]\n"			\
+	"2:	" T(str) "	%0, [%3]\n"			\
 	"	mov	%0, #0\n"				\
-	__futex_atomic_ex_table("%4")				\
-	: "=&r" (ret), "=&r" (oldval)				\
+	__futex_atomic_ex_table("%5")				\
+	: "=&r" (ret), "=&r" (oldval), "=&r" (tmp)		\
 	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
 	: "cc", "memory")
 
@@ -117,7 +117,7 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	int cmp = (encoded_op >> 24) & 15;
 	int oparg = (encoded_op << 8) >> 20;
 	int cmparg = (encoded_op << 20) >> 20;
-	int oldval = 0, ret;
+	int oldval = 0, ret, tmp;
 
 	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
 		oparg = 1 << oparg;
@@ -129,19 +129,19 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 
 	switch (op) {
 	case FUTEX_OP_SET:
-		__futex_atomic_op("mov	%0, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("mov	%0, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	case FUTEX_OP_ADD:
-		__futex_atomic_op("add	%0, %1, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("add	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	case FUTEX_OP_OR:
-		__futex_atomic_op("orr	%0, %1, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("orr	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	case FUTEX_OP_ANDN:
-		__futex_atomic_op("and	%0, %1, %3", ret, oldval, uaddr, ~oparg);
+		__futex_atomic_op("and	%0, %1, %4", ret, oldval, tmp, uaddr, ~oparg);
 		break;
 	case FUTEX_OP_XOR:
-		__futex_atomic_op("eor	%0, %1, %3", ret, oldval, uaddr, oparg);
+		__futex_atomic_op("eor	%0, %1, %4", ret, oldval, tmp, uaddr, oparg);
 		break;
 	default:
 		ret = -ENOSYS;
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 2c04ed5efeb5..c60a2944f95b 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -478,8 +478,8 @@
 /*
  * Unimplemented (or alternatively implemented) syscalls
  */
-#define __IGNORE_fadvise64_64		1
-#define __IGNORE_migrate_pages		1
+#define __IGNORE_fadvise64_64
+#define __IGNORE_migrate_pages
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_ARM_UNISTD_H */
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
index 79ed5e7f204a..7fcddb75c877 100644
--- a/arch/arm/kernel/smp_scu.c
+++ b/arch/arm/kernel/smp_scu.c
@@ -13,6 +13,7 @@
 
 #include <asm/smp_scu.h>
 #include <asm/cacheflush.h>
+#include <asm/cputype.h>
 
 #define SCU_CTRL		0x00
 #define SCU_CONFIG		0x04
@@ -37,6 +38,15 @@ void __init scu_enable(void __iomem *scu_base)
 {
 	u32 scu_ctrl;
 
+#ifdef CONFIG_ARM_ERRATA_764369
+	/* Cortex-A9 only */
+	if ((read_cpuid(CPUID_ID) & 0xff0ffff0) == 0x410fc090) {
+		scu_ctrl = __raw_readl(scu_base + 0x30);
+		if (!(scu_ctrl & 1))
+			__raw_writel(scu_ctrl | 0x1, scu_base + 0x30);
+	}
+#endif
+
 	scu_ctrl = __raw_readl(scu_base + SCU_CTRL);
 	/* already enabled? */
 	if (scu_ctrl & 1)
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index bf977f8514f6..4e66f62b8d41 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -23,8 +23,10 @@
 
 #if defined(CONFIG_SMP_ON_UP) && !defined(CONFIG_DEBUG_SPINLOCK)
 #define ARM_EXIT_KEEP(x)	x
+#define ARM_EXIT_DISCARD(x)
 #else
 #define ARM_EXIT_KEEP(x)
+#define ARM_EXIT_DISCARD(x)	x
 #endif
 
 OUTPUT_ARCH(arm)
@@ -39,6 +41,11 @@ jiffies = jiffies_64 + 4;
 SECTIONS
 {
 	/*
+	 * XXX: The linker does not define how output sections are
+	 * assigned to input sections when there are multiple statements
+	 * matching the same input section name.  There is no documented
+	 * order of matching.
+	 *
 	 * unwind exit sections must be discarded before the rest of the
 	 * unwind sections get included.
 	 */
@@ -47,6 +54,9 @@ SECTIONS
 		*(.ARM.extab.exit.text)
 		ARM_CPU_DISCARD(*(.ARM.exidx.cpuexit.text))
 		ARM_CPU_DISCARD(*(.ARM.extab.cpuexit.text))
+		ARM_EXIT_DISCARD(EXIT_TEXT)
+		ARM_EXIT_DISCARD(EXIT_DATA)
+		EXIT_CALL
 #ifndef CONFIG_HOTPLUG
 		*(.ARM.exidx.devexit.text)
 		*(.ARM.extab.devexit.text)
@@ -58,6 +68,8 @@ SECTIONS
 #ifndef CONFIG_SMP_ON_UP
 		*(.alt.smp.init)
 #endif
+		*(.discard)
+		*(.discard.*)
 	}
 
 #ifdef CONFIG_XIP_KERNEL
@@ -279,9 +291,6 @@ SECTIONS
 
 	STABS_DEBUG
 	.comment 0 : { *(.comment) }
-
-	/* Default discards */
-	DISCARDS
 }
 
 /*
diff --git a/arch/arm/mach-exynos4/clock.c b/arch/arm/mach-exynos4/clock.c
index 79d6cd0c8e7b..86964d2e9e1b 100644
--- a/arch/arm/mach-exynos4/clock.c
+++ b/arch/arm/mach-exynos4/clock.c
@@ -899,8 +899,7 @@ static struct clksrc_clk clksrcs[] = {
 		.reg_div = { .reg = S5P_CLKDIV_CAM, .shift = 28, .size = 4 },
 	}, {
 		.clk		= {
-			.name		= "sclk_cam",
-			.devname	= "exynos4-fimc.0",
+			.name		= "sclk_cam0",
 			.enable		= exynos4_clksrc_mask_cam_ctrl,
 			.ctrlbit	= (1 << 16),
 		},
@@ -909,8 +908,7 @@ static struct clksrc_clk clksrcs[] = {
 		.reg_div = { .reg = S5P_CLKDIV_CAM, .shift = 16, .size = 4 },
 	}, {
 		.clk		= {
-			.name		= "sclk_cam",
-			.devname	= "exynos4-fimc.1",
+			.name		= "sclk_cam1",
 			.enable		= exynos4_clksrc_mask_cam_ctrl,
 			.ctrlbit	= (1 << 20),
 		},
diff --git a/arch/arm/mach-s3c2443/clock.c b/arch/arm/mach-s3c2443/clock.c
index a1a7176675b9..38058af48972 100644
--- a/arch/arm/mach-s3c2443/clock.c
+++ b/arch/arm/mach-s3c2443/clock.c
@@ -128,7 +128,7 @@ static int s3c2443_armclk_setrate(struct clk *clk, unsigned long rate)
 		unsigned long clkcon0;
 
 		clkcon0 = __raw_readl(S3C2443_CLKDIV0);
-		clkcon0 &= S3C2443_CLKDIV0_ARMDIV_MASK;
+		clkcon0 &= ~S3C2443_CLKDIV0_ARMDIV_MASK;
 		clkcon0 |= val << S3C2443_CLKDIV0_ARMDIV_SHIFT;
 		__raw_writel(clkcon0, S3C2443_CLKDIV0);
 	}
diff --git a/arch/arm/mach-s5pv210/clock.c b/arch/arm/mach-s5pv210/clock.c
index 52a8e607bcc2..f5f8fa89679c 100644
--- a/arch/arm/mach-s5pv210/clock.c
+++ b/arch/arm/mach-s5pv210/clock.c
@@ -815,8 +815,7 @@ static struct clksrc_clk clksrcs[] = {
 		.reg_div = { .reg = S5P_CLK_DIV3, .shift = 20, .size = 4 },
 	}, {
 		.clk		= {
-			.name		= "sclk_cam",
-			.devname	= "s5pv210-fimc.0",
+			.name		= "sclk_cam0",
 			.enable		= s5pv210_clk_mask0_ctrl,
 			.ctrlbit	= (1 << 3),
 		},
@@ -825,8 +824,7 @@ static struct clksrc_clk clksrcs[] = {
 		.reg_div = { .reg = S5P_CLK_DIV1, .shift = 12, .size = 4 },
 	}, {
 		.clk		= {
-			.name		= "sclk_cam",
-			.devname	= "s5pv210-fimc.1",
+			.name		= "sclk_cam1",
 			.enable		= s5pv210_clk_mask0_ctrl,
 			.ctrlbit	= (1 << 4),
 		},
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 3b24bfa3b828..07c4bc8ea0a4 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -174,6 +174,10 @@ ENTRY(v7_coherent_user_range)
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r12, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
  USER(	mcr	p15, 0, r12, c7, c11, 1	)	@ clean D line to the point of unification
 	add	r12, r12, r2
@@ -223,6 +227,10 @@ ENTRY(v7_flush_kern_dcache_area)
 	add	r1, r0, r1
 	sub	r3, r2, #1
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
 	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D line / unified line
 	add	r0, r0, r2
@@ -247,6 +255,10 @@ v7_dma_inv_range:
 	sub	r3, r2, #1
 	tst	r0, r3
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 	mcrne	p15, 0, r0, c7, c14, 1		@ clean & invalidate D / U line
 
 	tst	r1, r3
@@ -270,6 +282,10 @@ v7_dma_clean_range:
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
 	mcr	p15, 0, r0, c7, c10, 1		@ clean D / U line
 	add	r0, r0, r2
@@ -288,6 +304,10 @@ ENTRY(v7_dma_flush_range)
 	dcache_line_size r2, r3
 	sub	r3, r2, #1
 	bic	r0, r0, r3
+#ifdef CONFIG_ARM_ERRATA_764369
+	ALT_SMP(W(dsb))
+	ALT_UP(W(nop))
+#endif
 1:
 	mcr	p15, 0, r0, c7, c14, 1		@ clean & invalidate D / U line
 	add	r0, r0, r2
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 0a0a1e7c20d2..c3ff82f92d9c 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -324,6 +324,8 @@ __dma_alloc(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp,
 
 	if (addr)
 		*handle = pfn_to_dma(dev, page_to_pfn(page));
+	else
+		__dma_free_buffer(page, size);
 
 	return addr;
 }
diff --git a/arch/arm/plat-s5p/irq-gpioint.c b/arch/arm/plat-s5p/irq-gpioint.c
index f71078ef6bb5..f88216d23991 100644
--- a/arch/arm/plat-s5p/irq-gpioint.c
+++ b/arch/arm/plat-s5p/irq-gpioint.c
@@ -114,17 +114,18 @@ static __init int s5p_gpioint_add(struct s3c_gpio_chip *chip)
 {
 	static int used_gpioint_groups = 0;
 	int group = chip->group;
-	struct s5p_gpioint_bank *bank = NULL;
+	struct s5p_gpioint_bank *b, *bank = NULL;
 	struct irq_chip_generic *gc;
 	struct irq_chip_type *ct;
 
 	if (used_gpioint_groups >= S5P_GPIOINT_GROUP_COUNT)
 		return -ENOMEM;
 
-	list_for_each_entry(bank, &banks, list) {
-		if (group >= bank->start &&
-		    group < bank->start + bank->nr_groups)
+	list_for_each_entry(b, &banks, list) {
+		if (group >= b->start && group < b->start + b->nr_groups) {
+			bank = b;
 			break;
+		}
 	}
 	if (!bank)
 		return -EINVAL;
diff --git a/arch/powerpc/platforms/powermac/pci.c b/arch/powerpc/platforms/powermac/pci.c
index 5cc83851ad06..31a7d3a7ce25 100644
--- a/arch/powerpc/platforms/powermac/pci.c
+++ b/arch/powerpc/platforms/powermac/pci.c
@@ -561,6 +561,20 @@ static struct pci_ops u4_pcie_pci_ops =
 	.write = u4_pcie_write_config,
 };
 
+static void __devinit pmac_pci_fixup_u4_of_node(struct pci_dev *dev)
+{
+	/* Apple's device-tree "hides" the root complex virtual P2P bridge
+	 * on U4. However, Linux sees it, causing the PCI <-> OF matching
+	 * code to fail to properly match devices below it. This works around
+	 * it by setting the node of the bridge to point to the PHB node,
+	 * which is not entirely correct but fixes the matching code and
+	 * doesn't break anything else. It's also the simplest possible fix.
+	 */
+	if (dev->dev.of_node == NULL)
+		dev->dev.of_node = pcibios_get_phb_of_node(dev->bus);
+}
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_APPLE, 0x5b, pmac_pci_fixup_u4_of_node);
+
 #endif /* CONFIG_PPC64 */
 
 #ifdef CONFIG_PPC32
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 64b61bf72e93..547f1a6a35d4 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -188,7 +188,8 @@ extern char elf_platform[];
 #define SET_PERSONALITY(ex)					\
 do {								\
 	if (personality(current->personality) != PER_LINUX32)	\
-		set_personality(PER_LINUX);			\
+		set_personality(PER_LINUX |			\
+			(current->personality & ~PER_MASK));	\
 	if ((ex).e_ident[EI_CLASS] == ELFCLASS32)		\
 		set_thread_flag(TIF_31BIT);			\
 	else							\
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 519eb5f187ef..c0cb794bb365 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -658,12 +658,14 @@ static inline void pgste_set_pte(pte_t *ptep, pgste_t pgste)
  * struct gmap_struct - guest address space
  * @mm: pointer to the parent mm_struct
  * @table: pointer to the page directory
+ * @asce: address space control element for gmap page table
  * @crst_list: list of all crst tables used in the guest address space
  */
 struct gmap {
 	struct list_head list;
 	struct mm_struct *mm;
 	unsigned long *table;
+	unsigned long asce;
 	struct list_head crst_list;
 };
 
diff --git a/arch/s390/kernel/asm-offsets.c b/arch/s390/kernel/asm-offsets.c
index 532fd4322156..2b45591e1582 100644
--- a/arch/s390/kernel/asm-offsets.c
+++ b/arch/s390/kernel/asm-offsets.c
@@ -10,6 +10,7 @@
 #include <linux/sched.h>
 #include <asm/vdso.h>
 #include <asm/sigp.h>
+#include <asm/pgtable.h>
 
 /*
  * Make sure that the compiler is new enough. We want a compiler that
@@ -126,6 +127,7 @@ int main(void)
 	DEFINE(__LC_KERNEL_STACK, offsetof(struct _lowcore, kernel_stack));
 	DEFINE(__LC_ASYNC_STACK, offsetof(struct _lowcore, async_stack));
 	DEFINE(__LC_PANIC_STACK, offsetof(struct _lowcore, panic_stack));
+	DEFINE(__LC_USER_ASCE, offsetof(struct _lowcore, user_asce));
 	DEFINE(__LC_INT_CLOCK, offsetof(struct _lowcore, int_clock));
 	DEFINE(__LC_MCCK_CLOCK, offsetof(struct _lowcore, mcck_clock));
 	DEFINE(__LC_MACHINE_FLAGS, offsetof(struct _lowcore, machine_flags));
@@ -151,6 +153,7 @@ int main(void)
 	DEFINE(__LC_VDSO_PER_CPU, offsetof(struct _lowcore, vdso_per_cpu_data));
 	DEFINE(__LC_GMAP, offsetof(struct _lowcore, gmap));
 	DEFINE(__LC_CMF_HPP, offsetof(struct _lowcore, cmf_hpp));
+	DEFINE(__GMAP_ASCE, offsetof(struct gmap, asce));
 #endif /* CONFIG_32BIT */
 	return 0;
 }
diff --git a/arch/s390/kernel/entry64.S b/arch/s390/kernel/entry64.S
index 5f729d627cef..713da0760538 100644
--- a/arch/s390/kernel/entry64.S
+++ b/arch/s390/kernel/entry64.S
@@ -1076,6 +1076,11 @@ sie_loop:
 	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
 	tm	__TI_flags+7(%r14),_TIF_EXIT_SIE
 	jnz	sie_exit
+	lg	%r14,__LC_GMAP			# get gmap pointer
+	ltgr	%r14,%r14
+	jz	sie_gmap
+	lctlg	%c1,%c1,__GMAP_ASCE(%r14)	# load primary asce
+sie_gmap:
 	lg	%r14,__SF_EMPTY(%r15)		# get control block pointer
 	SPP	__SF_EMPTY(%r15)		# set guest id
 	sie	0(%r14)
@@ -1083,6 +1088,7 @@ sie_done:
 	SPP	__LC_CMF_HPP			# set host id
 	lg	%r14,__LC_THREAD_INFO		# pointer thread_info struct
 sie_exit:
+	lctlg	%c1,%c1,__LC_USER_ASCE		# load primary asce
 	ni	__TI_flags+6(%r14),255-(_TIF_SIE>>8)
 	lg	%r14,__SF_EMPTY+8(%r15)		# load guest register save area
 	stmg	%r0,%r13,0(%r14)		# save guest gprs 0-13
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index f17296e4fc89..dc2b580e27bc 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -123,6 +123,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 
 	switch (ext) {
 	case KVM_CAP_S390_PSW:
+	case KVM_CAP_S390_GMAP:
 		r = 1;
 		break;
 	default:
@@ -263,10 +264,12 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK;
 	restore_fp_regs(&vcpu->arch.guest_fpregs);
 	restore_access_regs(vcpu->arch.guest_acrs);
+	gmap_enable(vcpu->arch.gmap);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	gmap_disable(vcpu->arch.gmap);
 	save_fp_regs(&vcpu->arch.guest_fpregs);
 	save_access_regs(vcpu->arch.guest_acrs);
 	restore_fp_regs(&vcpu->arch.host_fpregs);
@@ -461,7 +464,6 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	local_irq_disable();
 	kvm_guest_enter();
 	local_irq_enable();
-	gmap_enable(vcpu->arch.gmap);
 	VCPU_EVENT(vcpu, 6, "entering sie flags %x",
 		   atomic_read(&vcpu->arch.sie_block->cpuflags));
 	if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) {
@@ -470,7 +472,6 @@ static void __vcpu_run(struct kvm_vcpu *vcpu)
 	}
 	VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
 		   vcpu->arch.sie_block->icptcode);
-	gmap_disable(vcpu->arch.gmap);
 	local_irq_disable();
 	kvm_guest_exit();
 	local_irq_enable();
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 4d1f2bce87b3..5d56c2b95b14 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -160,6 +160,8 @@ struct gmap *gmap_alloc(struct mm_struct *mm)
 	table = (unsigned long *) page_to_phys(page);
 	crst_table_init(table, _REGION1_ENTRY_EMPTY);
 	gmap->table = table;
+	gmap->asce = _ASCE_TYPE_REGION1 | _ASCE_TABLE_LENGTH |
+		     _ASCE_USER_BITS | __pa(table);
 	list_add(&gmap->list, &mm->context.gmap_list);
 	return gmap;
 
@@ -240,10 +242,6 @@ EXPORT_SYMBOL_GPL(gmap_free);
  */
 void gmap_enable(struct gmap *gmap)
 {
-	/* Load primary space page table origin. */
-	S390_lowcore.user_asce = _ASCE_TYPE_REGION1 | _ASCE_TABLE_LENGTH |
-				 _ASCE_USER_BITS | __pa(gmap->table);
-	asm volatile("lctlg 1,1,%0\n" : : "m" (S390_lowcore.user_asce) );
 	S390_lowcore.gmap = (unsigned long) gmap;
 }
 EXPORT_SYMBOL_GPL(gmap_enable);
@@ -254,10 +252,6 @@ EXPORT_SYMBOL_GPL(gmap_enable);
  */
 void gmap_disable(struct gmap *gmap)
 {
-	/* Load primary space page table origin. */
-	S390_lowcore.user_asce =
-		gmap->mm->context.asce_bits | __pa(gmap->mm->pgd);
-	asm volatile("lctlg 1,1,%0\n" : : "m" (S390_lowcore.user_asce) );
 	S390_lowcore.gmap = 0UL;
 }
 EXPORT_SYMBOL_GPL(gmap_disable);
@@ -309,15 +303,15 @@ int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len)
 		/* Walk the guest addr space page table */
 		table = gmap->table + (((to + off) >> 53) & 0x7ff);
 		if (*table & _REGION_ENTRY_INV)
-			return 0;
+			goto out;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		table = table + (((to + off) >> 42) & 0x7ff);
 		if (*table & _REGION_ENTRY_INV)
-			return 0;
+			goto out;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		table = table + (((to + off) >> 31) & 0x7ff);
 		if (*table & _REGION_ENTRY_INV)
-			return 0;
+			goto out;
 		table = (unsigned long *)(*table & _REGION_ENTRY_ORIGIN);
 		table = table + (((to + off) >> 20) & 0x7ff);
 
@@ -325,6 +319,7 @@ int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len)
 		flush |= gmap_unlink_segment(gmap, table);
 		*table = _SEGMENT_ENTRY_INV;
 	}
+out:
 	up_read(&gmap->mm->mmap_sem);
 	if (flush)
 		gmap_flush_tlb(gmap);
diff --git a/arch/sparc/include/asm/spitfire.h b/arch/sparc/include/asm/spitfire.h
index 55a17c6efeb8..d06a26601753 100644
--- a/arch/sparc/include/asm/spitfire.h
+++ b/arch/sparc/include/asm/spitfire.h
@@ -43,6 +43,8 @@
 #define SUN4V_CHIP_NIAGARA1	0x01
 #define SUN4V_CHIP_NIAGARA2	0x02
 #define SUN4V_CHIP_NIAGARA3	0x03
+#define SUN4V_CHIP_NIAGARA4	0x04
+#define SUN4V_CHIP_NIAGARA5	0x05
 #define SUN4V_CHIP_UNKNOWN	0xff
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/include/asm/xor_64.h b/arch/sparc/include/asm/xor_64.h
index 9ed6ff679ab7..ee8edc68423e 100644
--- a/arch/sparc/include/asm/xor_64.h
+++ b/arch/sparc/include/asm/xor_64.h
@@ -66,6 +66,8 @@ static struct xor_block_template xor_block_niagara = {
 	((tlb_type == hypervisor && \
 	  (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 || \
 	   sun4v_chip_type == SUN4V_CHIP_NIAGARA2 || \
-	   sun4v_chip_type == SUN4V_CHIP_NIAGARA3)) ? \
+	   sun4v_chip_type == SUN4V_CHIP_NIAGARA3 || \
+	   sun4v_chip_type == SUN4V_CHIP_NIAGARA4 || \
+	   sun4v_chip_type == SUN4V_CHIP_NIAGARA5)) ? \
 	 &xor_block_niagara : \
 	 &xor_block_VIS)
diff --git a/arch/sparc/kernel/cpu.c b/arch/sparc/kernel/cpu.c
index 9810fd881058..ba9b1cec4e6b 100644
--- a/arch/sparc/kernel/cpu.c
+++ b/arch/sparc/kernel/cpu.c
@@ -481,6 +481,18 @@ static void __init sun4v_cpu_probe(void)
 		sparc_pmu_type = "niagara3";
 		break;
 
+	case SUN4V_CHIP_NIAGARA4:
+		sparc_cpu_type = "UltraSparc T4 (Niagara4)";
+		sparc_fpu_type = "UltraSparc T4 integrated FPU";
+		sparc_pmu_type = "niagara4";
+		break;
+
+	case SUN4V_CHIP_NIAGARA5:
+		sparc_cpu_type = "UltraSparc T5 (Niagara5)";
+		sparc_fpu_type = "UltraSparc T5 integrated FPU";
+		sparc_pmu_type = "niagara5";
+		break;
+
 	default:
 		printk(KERN_WARNING "CPU: Unknown sun4v cpu type [%s]\n",
 		       prom_cpu_compatible);
diff --git a/arch/sparc/kernel/cpumap.c b/arch/sparc/kernel/cpumap.c
index 4197e8d62d4c..9323eafccb93 100644
--- a/arch/sparc/kernel/cpumap.c
+++ b/arch/sparc/kernel/cpumap.c
@@ -325,6 +325,8 @@ static int iterate_cpu(struct cpuinfo_tree *t, unsigned int root_index)
 	case SUN4V_CHIP_NIAGARA1:
 	case SUN4V_CHIP_NIAGARA2:
 	case SUN4V_CHIP_NIAGARA3:
+	case SUN4V_CHIP_NIAGARA4:
+	case SUN4V_CHIP_NIAGARA5:
 		rover_inc_table = niagara_iterate_method;
 		break;
 	default:
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index 0eac1b2fc53d..0d810c2f1d00 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -133,7 +133,7 @@ prom_sun4v_name:
 prom_niagara_prefix:
 	.asciz	"SUNW,UltraSPARC-T"
 prom_sparc_prefix:
-	.asciz	"SPARC-T"
+	.asciz	"SPARC-"
 	.align	4
 prom_root_compatible:
 	.skip	64
@@ -396,7 +396,7 @@ sun4v_chip_type:
 	or	%g1, %lo(prom_cpu_compatible), %g1
 	sethi	%hi(prom_sparc_prefix), %g7
 	or	%g7, %lo(prom_sparc_prefix), %g7
-	mov	7, %g3
+	mov	6, %g3
 90:	ldub	[%g7], %g2
 	ldub	[%g1], %g4
 	cmp	%g2, %g4
@@ -408,10 +408,23 @@ sun4v_chip_type:
 
 	sethi	%hi(prom_cpu_compatible), %g1
 	or	%g1, %lo(prom_cpu_compatible), %g1
-	ldub	[%g1 + 7], %g2
+	ldub	[%g1 + 6], %g2
+	cmp	%g2, 'T'
+	be,pt	%xcc, 70f
+	 cmp	%g2, 'M'
+	bne,pn	%xcc, 4f
+	 nop
+
+70:	ldub	[%g1 + 7], %g2
 	cmp	%g2, '3'
 	be,pt	%xcc, 5f
 	 mov	SUN4V_CHIP_NIAGARA3, %g4
+	cmp	%g2, '4'
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_NIAGARA4, %g4
+	cmp	%g2, '5'
+	be,pt	%xcc, 5f
+	 mov	SUN4V_CHIP_NIAGARA5, %g4
 	ba,pt	%xcc, 4f
 	 nop
 
@@ -545,6 +558,12 @@ niagara_tlb_fixup:
 	cmp	%g1, SUN4V_CHIP_NIAGARA3
 	be,pt	%xcc, niagara2_patch
 	 nop
+	cmp	%g1, SUN4V_CHIP_NIAGARA4
+	be,pt	%xcc, niagara2_patch
+	 nop
+	cmp	%g1, SUN4V_CHIP_NIAGARA5
+	be,pt	%xcc, niagara2_patch
+	 nop
 
 	call	generic_patch_copyops
 	 nop
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index c8cc461ff75f..f793742eec2b 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -380,8 +380,7 @@ void flush_thread(void)
 #endif
 	}
 
-	/* Now, this task is no longer a kernel thread. */
-	current->thread.current_ds = USER_DS;
+	/* This task is no longer a kernel thread. */
 	if (current->thread.flags & SPARC_FLAG_KTHREAD) {
 		current->thread.flags &= ~SPARC_FLAG_KTHREAD;
 
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index c158a95ec664..d959cd0a4aa4 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -368,9 +368,6 @@ void flush_thread(void)
 
 	/* Clear FPU register state. */
 	t->fpsaved[0] = 0;
-	
-	if (get_thread_current_ds() != ASI_AIUS)
-		set_fs(USER_DS);
 }
 
 /* It's a bit more tricky when 64-bit tasks are involved... */
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index d26e1f6c717a..3e3e2914c70b 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -137,7 +137,7 @@ static void __init process_switch(char c)
 		prom_halt();
 		break;
 	case 'p':
-		/* Just ignore, this behavior is now the default.  */
+		prom_early_console.flags &= ~CON_BOOT;
 		break;
 	default:
 		printk("Unknown boot switch (-%c)\n", c);
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 3c5bb784214f..c965595aa7e9 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -106,7 +106,7 @@ static void __init process_switch(char c)
 		prom_halt();
 		break;
 	case 'p':
-		/* Just ignore, this behavior is now the default.  */
+		prom_early_console.flags &= ~CON_BOOT;
 		break;
 	case 'P':
 		/* Force UltraSPARC-III P-Cache on. */
@@ -425,10 +425,14 @@ static void __init init_sparc64_elf_hwcap(void)
 	else if (tlb_type == hypervisor) {
 		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1 ||
 		    sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
-		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5)
 			cap |= HWCAP_SPARC_BLKINIT;
 		if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
-		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
+		    sun4v_chip_type == SUN4V_CHIP_NIAGARA5)
 			cap |= HWCAP_SPARC_N2;
 	}
 
@@ -452,11 +456,15 @@ static void __init init_sparc64_elf_hwcap(void)
 			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA1)
 				cap |= AV_SPARC_ASI_BLK_INIT;
 			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA2 ||
-			    sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+			    sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
+			    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
+			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5)
 				cap |= (AV_SPARC_VIS | AV_SPARC_VIS2 |
 					AV_SPARC_ASI_BLK_INIT |
 					AV_SPARC_POPC);
-			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3)
+			if (sun4v_chip_type == SUN4V_CHIP_NIAGARA3 ||
+			    sun4v_chip_type == SUN4V_CHIP_NIAGARA4 ||
+			    sun4v_chip_type == SUN4V_CHIP_NIAGARA5)
 				cap |= (AV_SPARC_VIS3 | AV_SPARC_HPC |
 					AV_SPARC_FMAF);
 		}
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 581531dbc8b5..8e073d802139 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -511,6 +511,11 @@ static void __init read_obp_translations(void)
 		for (i = 0; i < prom_trans_ents; i++)
 			prom_trans[i].data &= ~0x0003fe0000000000UL;
 	}
+
+	/* Force execute bit on.  */
+	for (i = 0; i < prom_trans_ents; i++)
+		prom_trans[i].data |= (tlb_type == hypervisor ?
+				       _PAGE_EXEC_4V : _PAGE_EXEC_4U);
 }
 
 static void __init hypervisor_tlb_lock(unsigned long vaddr,
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index 4886a68f267e..53610957feaf 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -22,25 +22,23 @@ void arch_trigger_all_cpu_backtrace(void);
 #define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
 #endif
 
-/*
- * Define some priorities for the nmi notifier call chain.
- *
- * Create a local nmi bit that has a higher priority than
- * external nmis, because the local ones are more frequent.
- *
- * Also setup some default high/normal/low settings for
- * subsystems to registers with.  Using 4 bits to separate
- * the priorities.  This can go a lot higher if needed be.
- */
-
-#define NMI_LOCAL_SHIFT		16	/* randomly picked */
-#define NMI_LOCAL_BIT		(1ULL << NMI_LOCAL_SHIFT)
-#define NMI_HIGH_PRIOR		(1ULL << 8)
-#define NMI_NORMAL_PRIOR	(1ULL << 4)
-#define NMI_LOW_PRIOR		(1ULL << 0)
-#define NMI_LOCAL_HIGH_PRIOR	(NMI_LOCAL_BIT | NMI_HIGH_PRIOR)
-#define NMI_LOCAL_NORMAL_PRIOR	(NMI_LOCAL_BIT | NMI_NORMAL_PRIOR)
-#define NMI_LOCAL_LOW_PRIOR	(NMI_LOCAL_BIT | NMI_LOW_PRIOR)
+#define NMI_FLAG_FIRST	1
+
+enum {
+	NMI_LOCAL=0,
+	NMI_UNKNOWN,
+	NMI_MAX
+};
+
+#define NMI_DONE	0
+#define NMI_HANDLED	1
+
+typedef int (*nmi_handler_t)(unsigned int, struct pt_regs *);
+
+int register_nmi_handler(unsigned int, nmi_handler_t, unsigned long,
+			 const char *);
+
+void unregister_nmi_handler(unsigned int, const char *);
 
 void stop_nmi(void);
 void restart_nmi(void);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 094fb30817ab..e47cb6167e8f 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -29,6 +29,9 @@
 #define ARCH_PERFMON_EVENTSEL_INV			(1ULL << 23)
 #define ARCH_PERFMON_EVENTSEL_CMASK			0xFF000000ULL
 
+#define AMD_PERFMON_EVENTSEL_GUESTONLY			(1ULL << 40)
+#define AMD_PERFMON_EVENTSEL_HOSTONLY			(1ULL << 41)
+
 #define AMD64_EVENTSEL_EVENT	\
 	(ARCH_PERFMON_EVENTSEL_EVENT | (0x0FULL << 32))
 #define INTEL_ARCH_EVENT_MASK	\
@@ -159,7 +162,19 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 	);							\
 }
 
+struct perf_guest_switch_msr {
+	unsigned msr;
+	u64 host, guest;
+};
+
+extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
 #else
+static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
+{
+	*nr = 0;
+	return NULL;
+}
+
 static inline void perf_events_lapic_init(void)	{ }
 #endif
 
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index 3250e3d605d9..92f297069e87 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -23,7 +23,7 @@ void machine_real_restart(unsigned int type);
 #define MRR_BIOS	0
 #define MRR_APM		1
 
-typedef void (*nmi_shootdown_cb)(int, struct die_args*);
+typedef void (*nmi_shootdown_cb)(int, struct pt_regs*);
 void nmi_shootdown_cpus(nmi_shootdown_cb callback);
 
 #endif /* _ASM_X86_REBOOT_H */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 82f2912155a5..8baca3c4871c 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -19,7 +19,7 @@ endif
 
 obj-y			:= process_$(BITS).o signal.o entry_$(BITS).o
 obj-y			+= traps.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
-obj-y			+= time.o ioport.o ldt.o dumpstack.o
+obj-y			+= time.o ioport.o ldt.o dumpstack.o nmi.o
 obj-y			+= setup.o x86_init.o i8259.o irqinit.o jump_label.o
 obj-$(CONFIG_IRQ_WORK)  += irq_work.o
 obj-y			+= probe_roms.o
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index d5e57db0f7be..31cb9ae992b7 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -60,22 +60,10 @@ void arch_trigger_all_cpu_backtrace(void)
 }
 
 static int __kprobes
-arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
-			 unsigned long cmd, void *__args)
+arch_trigger_all_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
 {
-	struct die_args *args = __args;
-	struct pt_regs *regs;
 	int cpu;
 
-	switch (cmd) {
-	case DIE_NMI:
-		break;
-
-	default:
-		return NOTIFY_DONE;
-	}
-
-	regs = args->regs;
 	cpu = smp_processor_id();
 
 	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
@@ -86,21 +74,16 @@ arch_trigger_all_cpu_backtrace_handler(struct notifier_block *self,
 		show_regs(regs);
 		arch_spin_unlock(&lock);
 		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
-		return NOTIFY_STOP;
+		return NMI_HANDLED;
 	}
 
-	return NOTIFY_DONE;
+	return NMI_DONE;
 }
 
-static __read_mostly struct notifier_block backtrace_notifier = {
-	.notifier_call          = arch_trigger_all_cpu_backtrace_handler,
-	.next                   = NULL,
-	.priority               = NMI_LOCAL_LOW_PRIOR,
-};
-
 static int __init register_trigger_all_cpu_backtrace(void)
 {
-	register_die_notifier(&backtrace_notifier);
+	register_nmi_handler(NMI_LOCAL, arch_trigger_all_cpu_backtrace_handler,
+				0, "arch_bt");
 	return 0;
 }
 early_initcall(register_trigger_all_cpu_backtrace);
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 34b18594e724..75be00ecfff2 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -672,18 +672,11 @@ void __cpuinit uv_cpu_init(void)
 /*
  * When NMI is received, print a stack trace.
  */
-int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
+int uv_handle_nmi(unsigned int reason, struct pt_regs *regs)
 {
 	unsigned long real_uv_nmi;
 	int bid;
 
-	if (reason != DIE_NMIUNKNOWN)
-		return NOTIFY_OK;
-
-	if (in_crash_kexec)
-		/* do nothing if entering the crash kernel */
-		return NOTIFY_OK;
-
 	/*
 	 * Each blade has an MMR that indicates when an NMI has been sent
 	 * to cpus on the blade. If an NMI is detected, atomically
@@ -704,7 +697,7 @@ int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
 	}
 
 	if (likely(__get_cpu_var(cpu_last_nmi_count) == uv_blade_info[bid].nmi_count))
-		return NOTIFY_DONE;
+		return NMI_DONE;
 
 	__get_cpu_var(cpu_last_nmi_count) = uv_blade_info[bid].nmi_count;
 
@@ -717,17 +710,12 @@ int uv_handle_nmi(struct notifier_block *self, unsigned long reason, void *data)
 	dump_stack();
 	spin_unlock(&uv_nmi_lock);
 
-	return NOTIFY_STOP;
+	return NMI_HANDLED;
 }
 
-static struct notifier_block uv_dump_stack_nmi_nb = {
-	.notifier_call	= uv_handle_nmi,
-	.priority = NMI_LOCAL_LOW_PRIOR - 1,
-};
-
 void uv_register_nmi_notifier(void)
 {
-	if (register_die_notifier(&uv_dump_stack_nmi_nb))
+	if (register_nmi_handler(NMI_UNKNOWN, uv_handle_nmi, 0, "uv"))
 		printk(KERN_WARNING "UV NMI handler failed to register\n");
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 0ed633c5048b..6199232161cf 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -78,27 +78,20 @@ static void raise_exception(struct mce *m, struct pt_regs *pregs)
 
 static cpumask_var_t mce_inject_cpumask;
 
-static int mce_raise_notify(struct notifier_block *self,
-			    unsigned long val, void *data)
+static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
 {
-	struct die_args *args = (struct die_args *)data;
 	int cpu = smp_processor_id();
 	struct mce *m = &__get_cpu_var(injectm);
-	if (val != DIE_NMI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
-		return NOTIFY_DONE;
+	if (!cpumask_test_cpu(cpu, mce_inject_cpumask))
+		return NMI_DONE;
 	cpumask_clear_cpu(cpu, mce_inject_cpumask);
 	if (m->inject_flags & MCJ_EXCEPTION)
-		raise_exception(m, args->regs);
+		raise_exception(m, regs);
 	else if (m->status)
 		raise_poll(m);
-	return NOTIFY_STOP;
+	return NMI_HANDLED;
 }
 
-static struct notifier_block mce_raise_nb = {
-	.notifier_call = mce_raise_notify,
-	.priority = NMI_LOCAL_NORMAL_PRIOR,
-};
-
 /* Inject mce on current CPU */
 static int raise_local(void)
 {
@@ -216,7 +209,8 @@ static int inject_init(void)
 		return -ENOMEM;
 	printk(KERN_INFO "Machine check injector initialized\n");
 	mce_chrdev_ops.write = mce_write;
-	register_die_notifier(&mce_raise_nb);
+	register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0,
+				"mce_notify");
 	return 0;
 }
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 08363b042122..fce51ad1f362 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -908,9 +908,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 
 	percpu_inc(mce_exception_count);
 
-	if (notify_die(DIE_NMI, "machine check", regs, error_code,
-			   18, SIGKILL) == NOTIFY_STOP)
-		goto out;
 	if (!banks)
 		goto out;
 
@@ -1140,6 +1137,15 @@ static void mce_start_timer(unsigned long data)
 	add_timer_on(t, smp_processor_id());
 }
 
+/* Must not be called in IRQ context where del_timer_sync() can deadlock */
+static void mce_timer_delete_all(void)
+{
+	int cpu;
+
+	for_each_online_cpu(cpu)
+		del_timer_sync(&per_cpu(mce_timer, cpu));
+}
+
 static void mce_do_trigger(struct work_struct *work)
 {
 	call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT);
@@ -1750,7 +1756,6 @@ static struct syscore_ops mce_syscore_ops = {
 
 static void mce_cpu_restart(void *data)
 {
-	del_timer_sync(&__get_cpu_var(mce_timer));
 	if (!mce_available(__this_cpu_ptr(&cpu_info)))
 		return;
 	__mcheck_cpu_init_generic();
@@ -1760,16 +1765,15 @@ static void mce_cpu_restart(void *data)
 /* Reinit MCEs after user configuration changes */
 static void mce_restart(void)
 {
+	mce_timer_delete_all();
 	on_each_cpu(mce_cpu_restart, NULL, 1);
 }
 
 /* Toggle features for corrected errors */
-static void mce_disable_ce(void *all)
+static void mce_disable_cmci(void *data)
 {
 	if (!mce_available(__this_cpu_ptr(&cpu_info)))
 		return;
-	if (all)
-		del_timer_sync(&__get_cpu_var(mce_timer));
 	cmci_clear();
 }
 
@@ -1852,7 +1856,8 @@ static ssize_t set_ignore_ce(struct sys_device *s,
 	if (mce_ignore_ce ^ !!new) {
 		if (new) {
 			/* disable ce features */
-			on_each_cpu(mce_disable_ce, (void *)1, 1);
+			mce_timer_delete_all();
+			on_each_cpu(mce_disable_cmci, NULL, 1);
 			mce_ignore_ce = 1;
 		} else {
 			/* enable ce features */
@@ -1875,7 +1880,7 @@ static ssize_t set_cmci_disabled(struct sys_device *s,
 	if (mce_cmci_disabled ^ !!new) {
 		if (new) {
 			/* disable cmci */
-			on_each_cpu(mce_disable_ce, NULL, 1);
+			on_each_cpu(mce_disable_cmci, NULL, 1);
 			mce_cmci_disabled = 1;
 		} else {
 			/* enable cmci */
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 8ab89112f93c..640891014b2a 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1058,76 +1058,15 @@ void perf_events_lapic_init(void)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 }
 
-struct pmu_nmi_state {
-	unsigned int	marked;
-	int		handled;
-};
-
-static DEFINE_PER_CPU(struct pmu_nmi_state, pmu_nmi);
-
 static int __kprobes
-perf_event_nmi_handler(struct notifier_block *self,
-			 unsigned long cmd, void *__args)
+perf_event_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 {
-	struct die_args *args = __args;
-	unsigned int this_nmi;
-	int handled;
-
 	if (!atomic_read(&active_events))
-		return NOTIFY_DONE;
-
-	switch (cmd) {
-	case DIE_NMI:
-		break;
-	case DIE_NMIUNKNOWN:
-		this_nmi = percpu_read(irq_stat.__nmi_count);
-		if (this_nmi != __this_cpu_read(pmu_nmi.marked))
-			/* let the kernel handle the unknown nmi */
-			return NOTIFY_DONE;
-		/*
-		 * This one is a PMU back-to-back nmi. Two events
-		 * trigger 'simultaneously' raising two back-to-back
-		 * NMIs. If the first NMI handles both, the latter
-		 * will be empty and daze the CPU. So, we drop it to
-		 * avoid false-positive 'unknown nmi' messages.
-		 */
-		return NOTIFY_STOP;
-	default:
-		return NOTIFY_DONE;
-	}
-
-	handled = x86_pmu.handle_irq(args->regs);
-	if (!handled)
-		return NOTIFY_DONE;
+		return NMI_DONE;
 
-	this_nmi = percpu_read(irq_stat.__nmi_count);
-	if ((handled > 1) ||
-		/* the next nmi could be a back-to-back nmi */
-	    ((__this_cpu_read(pmu_nmi.marked) == this_nmi) &&
-	     (__this_cpu_read(pmu_nmi.handled) > 1))) {
-		/*
-		 * We could have two subsequent back-to-back nmis: The
-		 * first handles more than one counter, the 2nd
-		 * handles only one counter and the 3rd handles no
-		 * counter.
-		 *
-		 * This is the 2nd nmi because the previous was
-		 * handling more than one counter. We will mark the
-		 * next (3rd) and then drop it if unhandled.
-		 */
-		__this_cpu_write(pmu_nmi.marked, this_nmi + 1);
-		__this_cpu_write(pmu_nmi.handled, handled);
-	}
-
-	return NOTIFY_STOP;
+	return x86_pmu.handle_irq(regs);
 }
 
-static __read_mostly struct notifier_block perf_event_nmi_notifier = {
-	.notifier_call		= perf_event_nmi_handler,
-	.next			= NULL,
-	.priority		= NMI_LOCAL_LOW_PRIOR,
-};
-
 struct event_constraint emptyconstraint;
 struct event_constraint unconstrained;
 
@@ -1232,7 +1171,7 @@ static int __init init_hw_perf_events(void)
 		((1LL << x86_pmu.num_counters_fixed)-1) << X86_PMC_IDX_FIXED;
 
 	perf_events_lapic_init();
-	register_die_notifier(&perf_event_nmi_notifier);
+	register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI");
 
 	unconstrained = (struct event_constraint)
 		__EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index fb330b0a816e..b9698d40ac4b 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -131,6 +131,13 @@ struct cpu_hw_events {
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 
 	/*
+	 * Intel host/guest exclude bits
+	 */
+	u64				intel_ctrl_guest_mask;
+	u64				intel_ctrl_host_mask;
+	struct perf_guest_switch_msr	guest_switch_msrs[X86_PMC_IDX_MAX];
+
+	/*
 	 * manage shared (per-core, per-cpu) registers
 	 * used on Intel NHM/WSM/SNB
 	 */
@@ -295,6 +302,11 @@ struct x86_pmu {
 	 */
 	struct extra_reg *extra_regs;
 	unsigned int er_flags;
+
+	/*
+	 * Intel host/guest support (KVM)
+	 */
+	struct perf_guest_switch_msr *(*guest_get_msrs)(int *nr);
 };
 
 #define ERF_NO_HT_SHARING	1
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 384450d67128..db8e603ff0c6 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -138,6 +138,19 @@ static int amd_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
+	if (event->attr.exclude_host && event->attr.exclude_guest)
+		/*
+		 * When HO == GO == 1 the hardware treats that as GO == HO == 0
+		 * and will count in both modes. We don't want to count in that
+		 * case so we emulate no-counting by setting US = OS = 0.
+		 */
+		event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR |
+				      ARCH_PERFMON_EVENTSEL_OS);
+	else if (event->attr.exclude_host)
+		event->hw.config |= AMD_PERFMON_EVENTSEL_GUESTONLY;
+	else if (event->attr.exclude_guest)
+		event->hw.config |= AMD_PERFMON_EVENTSEL_HOSTONLY;
+
 	if (event->attr.type != PERF_TYPE_RAW)
 		return 0;
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 61fa35750b98..e09ca20e86ee 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -749,7 +749,8 @@ static void intel_pmu_enable_all(int added)
 
 	intel_pmu_pebs_enable_all();
 	intel_pmu_lbr_enable_all();
-	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL,
+			x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask);
 
 	if (test_bit(X86_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
 		struct perf_event *event =
@@ -872,6 +873,7 @@ static void intel_pmu_disable_fixed(struct hw_perf_event *hwc)
 static void intel_pmu_disable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
 	if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
 		intel_pmu_disable_bts();
@@ -879,6 +881,9 @@ static void intel_pmu_disable_event(struct perf_event *event)
 		return;
 	}
 
+	cpuc->intel_ctrl_guest_mask &= ~(1ull << hwc->idx);
+	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
@@ -924,6 +929,7 @@ static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
 static void intel_pmu_enable_event(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
 	if (unlikely(hwc->idx == X86_PMC_IDX_FIXED_BTS)) {
 		if (!__this_cpu_read(cpu_hw_events.enabled))
@@ -933,6 +939,11 @@ static void intel_pmu_enable_event(struct perf_event *event)
 		return;
 	}
 
+	if (event->attr.exclude_host)
+		cpuc->intel_ctrl_guest_mask |= (1ull << hwc->idx);
+	if (event->attr.exclude_guest)
+		cpuc->intel_ctrl_host_mask |= (1ull << hwc->idx);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_enable_fixed(hwc);
 		return;
@@ -1302,12 +1313,84 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	return 0;
 }
 
+struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
+{
+	if (x86_pmu.guest_get_msrs)
+		return x86_pmu.guest_get_msrs(nr);
+	*nr = 0;
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(perf_guest_get_msrs);
+
+static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
+
+	arr[0].msr = MSR_CORE_PERF_GLOBAL_CTRL;
+	arr[0].host = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_guest_mask;
+	arr[0].guest = x86_pmu.intel_ctrl & ~cpuc->intel_ctrl_host_mask;
+
+	*nr = 1;
+	return arr;
+}
+
+static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
+	int idx;
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++)  {
+		struct perf_event *event = cpuc->events[idx];
+
+		arr[idx].msr = x86_pmu_config_addr(idx);
+		arr[idx].host = arr[idx].guest = 0;
+
+		if (!test_bit(idx, cpuc->active_mask))
+			continue;
+
+		arr[idx].host = arr[idx].guest =
+			event->hw.config | ARCH_PERFMON_EVENTSEL_ENABLE;
+
+		if (event->attr.exclude_host)
+			arr[idx].host &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
+		else if (event->attr.exclude_guest)
+			arr[idx].guest &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
+	}
+
+	*nr = x86_pmu.num_counters;
+	return arr;
+}
+
+static void core_pmu_enable_event(struct perf_event *event)
+{
+	if (!event->attr.exclude_host)
+		x86_pmu_enable_event(event);
+}
+
+static void core_pmu_enable_all(int added)
+{
+	struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+	int idx;
+
+	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+		struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
+
+		if (!test_bit(idx, cpuc->active_mask) ||
+				cpuc->events[idx]->attr.exclude_host)
+			continue;
+
+		__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+	}
+}
+
 static __initconst const struct x86_pmu core_pmu = {
 	.name			= "core",
 	.handle_irq		= x86_pmu_handle_irq,
 	.disable_all		= x86_pmu_disable_all,
-	.enable_all		= x86_pmu_enable_all,
-	.enable			= x86_pmu_enable_event,
+	.enable_all		= core_pmu_enable_all,
+	.enable			= core_pmu_enable_event,
 	.disable		= x86_pmu_disable_event,
 	.hw_config		= x86_pmu_hw_config,
 	.schedule_events	= x86_schedule_events,
@@ -1325,6 +1408,7 @@ static __initconst const struct x86_pmu core_pmu = {
 	.get_event_constraints	= intel_get_event_constraints,
 	.put_event_constraints	= intel_put_event_constraints,
 	.event_constraints	= intel_core_event_constraints,
+	.guest_get_msrs		= core_guest_get_msrs,
 };
 
 struct intel_shared_regs *allocate_shared_regs(int cpu)
@@ -1431,6 +1515,7 @@ static __initconst const struct x86_pmu intel_pmu = {
 	.cpu_prepare		= intel_pmu_cpu_prepare,
 	.cpu_starting		= intel_pmu_cpu_starting,
 	.cpu_dying		= intel_pmu_cpu_dying,
+	.guest_get_msrs		= intel_guest_get_msrs,
 };
 
 static void intel_clovertown_quirks(void)
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 764c7c2b1811..13ad89971d47 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -32,15 +32,12 @@ int in_crash_kexec;
 
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
 
-static void kdump_nmi_callback(int cpu, struct die_args *args)
+static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
 {
-	struct pt_regs *regs;
 #ifdef CONFIG_X86_32
 	struct pt_regs fixed_regs;
 #endif
 
-	regs = args->regs;
-
 #ifdef CONFIG_X86_32
 	if (!user_mode_vm(regs)) {
 		crash_fixup_ss_esp(&fixed_regs, regs);
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 00354d4919a9..faba5771acad 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -511,28 +511,37 @@ single_step_cont(struct pt_regs *regs, struct die_args *args)
 
 static int was_in_debug_nmi[NR_CPUS];
 
-static int __kgdb_notify(struct die_args *args, unsigned long cmd)
+static int kgdb_nmi_handler(unsigned int cmd, struct pt_regs *regs)
 {
-	struct pt_regs *regs = args->regs;
-
 	switch (cmd) {
-	case DIE_NMI:
+	case NMI_LOCAL:
 		if (atomic_read(&kgdb_active) != -1) {
 			/* KGDB CPU roundup */
 			kgdb_nmicallback(raw_smp_processor_id(), regs);
 			was_in_debug_nmi[raw_smp_processor_id()] = 1;
 			touch_nmi_watchdog();
-			return NOTIFY_STOP;
+			return NMI_HANDLED;
 		}
-		return NOTIFY_DONE;
+		break;
 
-	case DIE_NMIUNKNOWN:
+	case NMI_UNKNOWN:
 		if (was_in_debug_nmi[raw_smp_processor_id()]) {
 			was_in_debug_nmi[raw_smp_processor_id()] = 0;
-			return NOTIFY_STOP;
+			return NMI_HANDLED;
 		}
-		return NOTIFY_DONE;
+		break;
+	default:
+		/* do nothing */
+		break;
+	}
+	return NMI_DONE;
+}
+
+static int __kgdb_notify(struct die_args *args, unsigned long cmd)
+{
+	struct pt_regs *regs = args->regs;
 
+	switch (cmd) {
 	case DIE_DEBUG:
 		if (atomic_read(&kgdb_cpu_doing_single_step) != -1) {
 			if (user_mode(regs))
@@ -590,11 +599,6 @@ kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr)
 
 static struct notifier_block kgdb_notifier = {
 	.notifier_call	= kgdb_notify,
-
-	/*
-	 * Lowest-prio notifier priority, we want to be notified last:
-	 */
-	.priority	= NMI_LOCAL_LOW_PRIOR,
 };
 
 /**
@@ -605,7 +609,31 @@ static struct notifier_block kgdb_notifier = {
  */
 int kgdb_arch_init(void)
 {
-	return register_die_notifier(&kgdb_notifier);
+	int retval;
+
+	retval = register_die_notifier(&kgdb_notifier);
+	if (retval)
+		goto out;
+
+	retval = register_nmi_handler(NMI_LOCAL, kgdb_nmi_handler,
+					0, "kgdb");
+	if (retval)
+		goto out1;
+
+	retval = register_nmi_handler(NMI_UNKNOWN, kgdb_nmi_handler,
+					0, "kgdb");
+
+	if (retval)
+		goto out2;
+
+	return retval;
+
+out2:
+	unregister_nmi_handler(NMI_LOCAL, "kgdb");
+out1:
+	unregister_die_notifier(&kgdb_notifier);
+out:
+	return retval;
 }
 
 static void kgdb_hw_overflow_handler(struct perf_event *event,
@@ -673,6 +701,8 @@ void kgdb_arch_exit(void)
 			breakinfo[i].pev = NULL;
 		}
 	}
+	unregister_nmi_handler(NMI_UNKNOWN, "kgdb");
+	unregister_nmi_handler(NMI_LOCAL, "kgdb");
 	unregister_die_notifier(&kgdb_notifier);
 }
 
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
new file mode 100644
index 000000000000..e20f5e790599
--- /dev/null
+++ b/arch/x86/kernel/nmi.c
@@ -0,0 +1,336 @@
+/*
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ *  Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs
+ *  Copyright (C) 2011	Don Zickus Red Hat, Inc.
+ *
+ *  Pentium III FXSR, SSE support
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ */
+
+/*
+ * Handle hardware traps and faults.
+ */
+#include <linux/spinlock.h>
+#include <linux/kprobes.h>
+#include <linux/kdebug.h>
+#include <linux/nmi.h>
+#include <linux/delay.h>
+#include <linux/hardirq.h>
+#include <linux/slab.h>
+
+#if defined(CONFIG_EDAC)
+#include <linux/edac.h>
+#endif
+
+#include <linux/atomic.h>
+#include <asm/traps.h>
+#include <asm/mach_traps.h>
+#include <asm/nmi.h>
+
+#define NMI_MAX_NAMELEN	16
+struct nmiaction {
+	struct list_head list;
+	nmi_handler_t handler;
+	unsigned int flags;
+	char *name;
+};
+
+struct nmi_desc {
+	spinlock_t lock;
+	struct list_head head;
+};
+
+static struct nmi_desc nmi_desc[NMI_MAX] = 
+{
+	{
+		.lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[0].lock),
+		.head = LIST_HEAD_INIT(nmi_desc[0].head),
+	},
+	{
+		.lock = __SPIN_LOCK_UNLOCKED(&nmi_desc[1].lock),
+		.head = LIST_HEAD_INIT(nmi_desc[1].head),
+	},
+
+};
+
+static int ignore_nmis;
+
+int unknown_nmi_panic;
+/*
+ * Prevent NMI reason port (0x61) being accessed simultaneously, can
+ * only be used in NMI handler.
+ */
+static DEFINE_RAW_SPINLOCK(nmi_reason_lock);
+
+static int __init setup_unknown_nmi_panic(char *str)
+{
+	unknown_nmi_panic = 1;
+	return 1;
+}
+__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
+
+#define nmi_to_desc(type) (&nmi_desc[type])
+
+static int notrace __kprobes nmi_handle(unsigned int type, struct pt_regs *regs)
+{
+	struct nmi_desc *desc = nmi_to_desc(type);
+	struct nmiaction *a;
+	int handled=0;
+
+	rcu_read_lock();
+
+	/*
+	 * NMIs are edge-triggered, which means if you have enough
+	 * of them concurrently, you can lose some because only one
+	 * can be latched at any given time.  Walk the whole list
+	 * to handle those situations.
+	 */
+	list_for_each_entry_rcu(a, &desc->head, list) {
+
+		handled += a->handler(type, regs);
+
+	}
+
+	rcu_read_unlock();
+
+	/* return total number of NMI events handled */
+	return handled;
+}
+
+static int __setup_nmi(unsigned int type, struct nmiaction *action)
+{
+	struct nmi_desc *desc = nmi_to_desc(type);
+	unsigned long flags;
+
+	spin_lock_irqsave(&desc->lock, flags);
+
+	/*
+	 * some handlers need to be executed first otherwise a fake
+	 * event confuses some handlers (kdump uses this flag)
+	 */
+	if (action->flags & NMI_FLAG_FIRST)
+		list_add_rcu(&action->list, &desc->head);
+	else
+		list_add_tail_rcu(&action->list, &desc->head);
+	
+	spin_unlock_irqrestore(&desc->lock, flags);
+	return 0;
+}
+
+static struct nmiaction *__free_nmi(unsigned int type, const char *name)
+{
+	struct nmi_desc *desc = nmi_to_desc(type);
+	struct nmiaction *n;
+	unsigned long flags;
+
+	spin_lock_irqsave(&desc->lock, flags);
+
+	list_for_each_entry_rcu(n, &desc->head, list) {
+		/*
+		 * the name passed in to describe the nmi handler
+		 * is used as the lookup key
+		 */
+		if (!strcmp(n->name, name)) {
+			WARN(in_nmi(),
+				"Trying to free NMI (%s) from NMI context!\n", n->name);
+			list_del_rcu(&n->list);
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&desc->lock, flags);
+	synchronize_rcu();
+	return (n);
+}
+
+int register_nmi_handler(unsigned int type, nmi_handler_t handler,
+			unsigned long nmiflags, const char *devname)
+{
+	struct nmiaction *action;
+	int retval = -ENOMEM;
+
+	if (!handler)
+		return -EINVAL;
+
+	action = kzalloc(sizeof(struct nmiaction), GFP_KERNEL);
+	if (!action)
+		goto fail_action;
+
+	action->handler = handler;
+	action->flags = nmiflags;
+	action->name = kstrndup(devname, NMI_MAX_NAMELEN, GFP_KERNEL);
+	if (!action->name)
+		goto fail_action_name;
+
+	retval = __setup_nmi(type, action);
+
+	if (retval)
+		goto fail_setup_nmi;
+
+	return retval;
+
+fail_setup_nmi:
+	kfree(action->name);
+fail_action_name:
+	kfree(action);
+fail_action:	
+
+	return retval;
+}
+EXPORT_SYMBOL_GPL(register_nmi_handler);
+
+void unregister_nmi_handler(unsigned int type, const char *name)
+{
+	struct nmiaction *a;
+
+	a = __free_nmi(type, name);
+	if (a) {
+		kfree(a->name);
+		kfree(a);
+	}
+}
+
+EXPORT_SYMBOL_GPL(unregister_nmi_handler);
+
+static notrace __kprobes void
+pci_serr_error(unsigned char reason, struct pt_regs *regs)
+{
+	pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
+		 reason, smp_processor_id());
+
+	/*
+	 * On some machines, PCI SERR line is used to report memory
+	 * errors. EDAC makes use of it.
+	 */
+#if defined(CONFIG_EDAC)
+	if (edac_handler_set()) {
+		edac_atomic_assert_error();
+		return;
+	}
+#endif
+
+	if (panic_on_unrecovered_nmi)
+		panic("NMI: Not continuing");
+
+	pr_emerg("Dazed and confused, but trying to continue\n");
+
+	/* Clear and disable the PCI SERR error line. */
+	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR;
+	outb(reason, NMI_REASON_PORT);
+}
+
+static notrace __kprobes void
+io_check_error(unsigned char reason, struct pt_regs *regs)
+{
+	unsigned long i;
+
+	pr_emerg(
+	"NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n",
+		 reason, smp_processor_id());
+	show_registers(regs);
+
+	if (panic_on_io_nmi)
+		panic("NMI IOCK error: Not continuing");
+
+	/* Re-enable the IOCK line, wait for a few seconds */
+	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
+	outb(reason, NMI_REASON_PORT);
+
+	i = 20000;
+	while (--i) {
+		touch_nmi_watchdog();
+		udelay(100);
+	}
+
+	reason &= ~NMI_REASON_CLEAR_IOCHK;
+	outb(reason, NMI_REASON_PORT);
+}
+
+static notrace __kprobes void
+unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
+{
+	int handled;
+
+	handled = nmi_handle(NMI_UNKNOWN, regs);
+	if (handled)
+		return;
+#ifdef CONFIG_MCA
+	/*
+	 * Might actually be able to figure out what the guilty party
+	 * is:
+	 */
+	if (MCA_bus) {
+		mca_handle_nmi();
+		return;
+	}
+#endif
+	pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
+		 reason, smp_processor_id());
+
+	pr_emerg("Do you have a strange power saving mode enabled?\n");
+	if (unknown_nmi_panic || panic_on_unrecovered_nmi)
+		panic("NMI: Not continuing");
+
+	pr_emerg("Dazed and confused, but trying to continue\n");
+}
+
+static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
+{
+	unsigned char reason = 0;
+	int handled;
+
+	/*
+	 * CPU-specific NMI must be processed before non-CPU-specific
+	 * NMI, otherwise we may lose it, because the CPU-specific
+	 * NMI can not be detected/processed on other CPUs.
+	 */
+	handled = nmi_handle(NMI_LOCAL, regs);
+	if (handled)
+		return;
+
+	/* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
+	raw_spin_lock(&nmi_reason_lock);
+	reason = get_nmi_reason();
+
+	if (reason & NMI_REASON_MASK) {
+		if (reason & NMI_REASON_SERR)
+			pci_serr_error(reason, regs);
+		else if (reason & NMI_REASON_IOCHK)
+			io_check_error(reason, regs);
+#ifdef CONFIG_X86_32
+		/*
+		 * Reassert NMI in case it became active
+		 * meanwhile as it's edge-triggered:
+		 */
+		reassert_nmi();
+#endif
+		raw_spin_unlock(&nmi_reason_lock);
+		return;
+	}
+	raw_spin_unlock(&nmi_reason_lock);
+
+	unknown_nmi_error(reason, regs);
+}
+
+dotraplinkage notrace __kprobes void
+do_nmi(struct pt_regs *regs, long error_code)
+{
+	nmi_enter();
+
+	inc_irq_stat(__nmi_count);
+
+	if (!ignore_nmis)
+		default_do_nmi(regs);
+
+	nmi_exit();
+}
+
+void stop_nmi(void)
+{
+	ignore_nmis++;
+}
+
+void restart_nmi(void)
+{
+	ignore_nmis--;
+}
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 9242436e9937..e334be1182b9 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -464,7 +464,7 @@ static inline void kb_wait(void)
 	}
 }
 
-static void vmxoff_nmi(int cpu, struct die_args *args)
+static void vmxoff_nmi(int cpu, struct pt_regs *regs)
 {
 	cpu_emergency_vmxoff();
 }
@@ -736,14 +736,10 @@ static nmi_shootdown_cb shootdown_callback;
 
 static atomic_t waiting_for_crash_ipi;
 
-static int crash_nmi_callback(struct notifier_block *self,
-			unsigned long val, void *data)
+static int crash_nmi_callback(unsigned int val, struct pt_regs *regs)
 {
 	int cpu;
 
-	if (val != DIE_NMI)
-		return NOTIFY_OK;
-
 	cpu = raw_smp_processor_id();
 
 	/* Don't do anything if this handler is invoked on crashing cpu.
@@ -751,10 +747,10 @@ static int crash_nmi_callback(struct notifier_block *self,
 	 * an NMI if system was initially booted with nmi_watchdog parameter.
 	 */
 	if (cpu == crashing_cpu)
-		return NOTIFY_STOP;
+		return NMI_HANDLED;
 	local_irq_disable();
 
-	shootdown_callback(cpu, (struct die_args *)data);
+	shootdown_callback(cpu, regs);
 
 	atomic_dec(&waiting_for_crash_ipi);
 	/* Assume hlt works */
@@ -762,7 +758,7 @@ static int crash_nmi_callback(struct notifier_block *self,
 	for (;;)
 		cpu_relax();
 
-	return 1;
+	return NMI_HANDLED;
 }
 
 static void smp_send_nmi_allbutself(void)
@@ -770,12 +766,6 @@ static void smp_send_nmi_allbutself(void)
 	apic->send_IPI_allbutself(NMI_VECTOR);
 }
 
-static struct notifier_block crash_nmi_nb = {
-	.notifier_call = crash_nmi_callback,
-	/* we want to be the first one called */
-	.priority = NMI_LOCAL_HIGH_PRIOR+1,
-};
-
 /* Halt all other CPUs, calling the specified function on each of them
  *
  * This function can be used to halt all other CPUs on crash
@@ -794,7 +784,8 @@ void nmi_shootdown_cpus(nmi_shootdown_cb callback)
 
 	atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1);
 	/* Would it be better to replace the trap vector here? */
-	if (register_die_notifier(&crash_nmi_nb))
+	if (register_nmi_handler(NMI_LOCAL, crash_nmi_callback,
+				 NMI_FLAG_FIRST, "crash"))
 		return;		/* return what? */
 	/* Ensure the new callback function is set before sending
 	 * out the NMI
diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c
index 3f2ad2640d85..ccdbc16b8941 100644
--- a/arch/x86/kernel/rtc.c
+++ b/arch/x86/kernel/rtc.c
@@ -42,8 +42,11 @@ int mach_set_rtc_mmss(unsigned long nowtime)
 {
 	int real_seconds, real_minutes, cmos_minutes;
 	unsigned char save_control, save_freq_select;
+	unsigned long flags;
 	int retval = 0;
 
+	spin_lock_irqsave(&rtc_lock, flags);
+
 	 /* tell the clock it's being set */
 	save_control = CMOS_READ(RTC_CONTROL);
 	CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL);
@@ -93,12 +96,17 @@ int mach_set_rtc_mmss(unsigned long nowtime)
 	CMOS_WRITE(save_control, RTC_CONTROL);
 	CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
 
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
 	return retval;
 }
 
 unsigned long mach_get_cmos_time(void)
 {
 	unsigned int status, year, mon, day, hour, min, sec, century = 0;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rtc_lock, flags);
 
 	/*
 	 * If UIP is clear, then we have >= 244 microseconds before
@@ -125,6 +133,8 @@ unsigned long mach_get_cmos_time(void)
 	status = CMOS_READ(RTC_CONTROL);
 	WARN_ON_ONCE(RTC_ALWAYS_BCD && (status & RTC_DM_BINARY));
 
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
 	if (RTC_ALWAYS_BCD || !(status & RTC_DM_BINARY)) {
 		sec = bcd2bin(sec);
 		min = bcd2bin(min);
@@ -169,24 +179,15 @@ EXPORT_SYMBOL(rtc_cmos_write);
 
 int update_persistent_clock(struct timespec now)
 {
-	unsigned long flags;
-	int retval;
-
-	spin_lock_irqsave(&rtc_lock, flags);
-	retval = x86_platform.set_wallclock(now.tv_sec);
-	spin_unlock_irqrestore(&rtc_lock, flags);
-
-	return retval;
+	return x86_platform.set_wallclock(now.tv_sec);
 }
 
 /* not static: needed by APM */
 void read_persistent_clock(struct timespec *ts)
 {
-	unsigned long retval, flags;
+	unsigned long retval;
 
-	spin_lock_irqsave(&rtc_lock, flags);
 	retval = x86_platform.get_wallclock();
-	spin_unlock_irqrestore(&rtc_lock, flags);
 
 	ts->tv_sec = retval;
 	ts->tv_nsec = 0;
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 6913369c234c..a8e3eb83466c 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -81,15 +81,6 @@ gate_desc idt_table[NR_VECTORS] __page_aligned_data = { { { { 0, 0 } } }, };
 DECLARE_BITMAP(used_vectors, NR_VECTORS);
 EXPORT_SYMBOL_GPL(used_vectors);
 
-static int ignore_nmis;
-
-int unknown_nmi_panic;
-/*
- * Prevent NMI reason port (0x61) being accessed simultaneously, can
- * only be used in NMI handler.
- */
-static DEFINE_RAW_SPINLOCK(nmi_reason_lock);
-
 static inline void conditional_sti(struct pt_regs *regs)
 {
 	if (regs->flags & X86_EFLAGS_IF)
@@ -307,152 +298,6 @@ gp_in_kernel:
 	die("general protection fault", regs, error_code);
 }
 
-static int __init setup_unknown_nmi_panic(char *str)
-{
-	unknown_nmi_panic = 1;
-	return 1;
-}
-__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
-
-static notrace __kprobes void
-pci_serr_error(unsigned char reason, struct pt_regs *regs)
-{
-	pr_emerg("NMI: PCI system error (SERR) for reason %02x on CPU %d.\n",
-		 reason, smp_processor_id());
-
-	/*
-	 * On some machines, PCI SERR line is used to report memory
-	 * errors. EDAC makes use of it.
-	 */
-#if defined(CONFIG_EDAC)
-	if (edac_handler_set()) {
-		edac_atomic_assert_error();
-		return;
-	}
-#endif
-
-	if (panic_on_unrecovered_nmi)
-		panic("NMI: Not continuing");
-
-	pr_emerg("Dazed and confused, but trying to continue\n");
-
-	/* Clear and disable the PCI SERR error line. */
-	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_SERR;
-	outb(reason, NMI_REASON_PORT);
-}
-
-static notrace __kprobes void
-io_check_error(unsigned char reason, struct pt_regs *regs)
-{
-	unsigned long i;
-
-	pr_emerg(
-	"NMI: IOCK error (debug interrupt?) for reason %02x on CPU %d.\n",
-		 reason, smp_processor_id());
-	show_registers(regs);
-
-	if (panic_on_io_nmi)
-		panic("NMI IOCK error: Not continuing");
-
-	/* Re-enable the IOCK line, wait for a few seconds */
-	reason = (reason & NMI_REASON_CLEAR_MASK) | NMI_REASON_CLEAR_IOCHK;
-	outb(reason, NMI_REASON_PORT);
-
-	i = 20000;
-	while (--i) {
-		touch_nmi_watchdog();
-		udelay(100);
-	}
-
-	reason &= ~NMI_REASON_CLEAR_IOCHK;
-	outb(reason, NMI_REASON_PORT);
-}
-
-static notrace __kprobes void
-unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
-{
-	if (notify_die(DIE_NMIUNKNOWN, "nmi", regs, reason, 2, SIGINT) ==
-			NOTIFY_STOP)
-		return;
-#ifdef CONFIG_MCA
-	/*
-	 * Might actually be able to figure out what the guilty party
-	 * is:
-	 */
-	if (MCA_bus) {
-		mca_handle_nmi();
-		return;
-	}
-#endif
-	pr_emerg("Uhhuh. NMI received for unknown reason %02x on CPU %d.\n",
-		 reason, smp_processor_id());
-
-	pr_emerg("Do you have a strange power saving mode enabled?\n");
-	if (unknown_nmi_panic || panic_on_unrecovered_nmi)
-		panic("NMI: Not continuing");
-
-	pr_emerg("Dazed and confused, but trying to continue\n");
-}
-
-static notrace __kprobes void default_do_nmi(struct pt_regs *regs)
-{
-	unsigned char reason = 0;
-
-	/*
-	 * CPU-specific NMI must be processed before non-CPU-specific
-	 * NMI, otherwise we may lose it, because the CPU-specific
-	 * NMI can not be detected/processed on other CPUs.
-	 */
-	if (notify_die(DIE_NMI, "nmi", regs, 0, 2, SIGINT) == NOTIFY_STOP)
-		return;
-
-	/* Non-CPU-specific NMI: NMI sources can be processed on any CPU */
-	raw_spin_lock(&nmi_reason_lock);
-	reason = get_nmi_reason();
-
-	if (reason & NMI_REASON_MASK) {
-		if (reason & NMI_REASON_SERR)
-			pci_serr_error(reason, regs);
-		else if (reason & NMI_REASON_IOCHK)
-			io_check_error(reason, regs);
-#ifdef CONFIG_X86_32
-		/*
-		 * Reassert NMI in case it became active
-		 * meanwhile as it's edge-triggered:
-		 */
-		reassert_nmi();
-#endif
-		raw_spin_unlock(&nmi_reason_lock);
-		return;
-	}
-	raw_spin_unlock(&nmi_reason_lock);
-
-	unknown_nmi_error(reason, regs);
-}
-
-dotraplinkage notrace __kprobes void
-do_nmi(struct pt_regs *regs, long error_code)
-{
-	nmi_enter();
-
-	inc_irq_stat(__nmi_count);
-
-	if (!ignore_nmis)
-		default_do_nmi(regs);
-
-	nmi_exit();
-}
-
-void stop_nmi(void)
-{
-	ignore_nmis++;
-}
-
-void restart_nmi(void)
-{
-	ignore_nmis--;
-}
-
 /* May run on IST stack. */
 dotraplinkage void __kprobes do_int3(struct pt_regs *regs, long error_code)
 {
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 6f08bc940fa8..8b4cc5f067de 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3603,7 +3603,7 @@ done_prefixes:
 		break;
 	case Src2CL:
 		ctxt->src2.bytes = 1;
-		ctxt->src2.val = ctxt->regs[VCPU_REGS_RCX] & 0x8;
+		ctxt->src2.val = ctxt->regs[VCPU_REGS_RCX] & 0xff;
 		break;
 	case Src2ImmByte:
 		rc = decode_imm(ctxt, &ctxt->src2, 1, true);
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 1c5b69373a00..8e8da7960dbe 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -400,7 +400,8 @@ static u64 __update_clear_spte_slow(u64 *sptep, u64 spte)
 
 	/* xchg acts as a barrier before the setting of the high bits */
 	orig.spte_low = xchg(&ssptep->spte_low, sspte.spte_low);
-	orig.spte_high = ssptep->spte_high = sspte.spte_high;
+	orig.spte_high = ssptep->spte_high;
+	ssptep->spte_high = sspte.spte_high;
 	count_spte_clear(sptep, spte);
 
 	return orig.spte;
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 7ca4d43e8988..990c35bfa88f 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -61,26 +61,15 @@ u64 op_x86_get_ctrl(struct op_x86_model_spec const *model,
 }
 
 
-static int profile_exceptions_notify(struct notifier_block *self,
-				     unsigned long val, void *data)
+static int profile_exceptions_notify(unsigned int val, struct pt_regs *regs)
 {
-	struct die_args *args = (struct die_args *)data;
-	int ret = NOTIFY_DONE;
-
-	switch (val) {
-	case DIE_NMI:
-		if (ctr_running)
-			model->check_ctrs(args->regs, &__get_cpu_var(cpu_msrs));
-		else if (!nmi_enabled)
-			break;
-		else
-			model->stop(&__get_cpu_var(cpu_msrs));
-		ret = NOTIFY_STOP;
-		break;
-	default:
-		break;
-	}
-	return ret;
+	if (ctr_running)
+		model->check_ctrs(regs, &__get_cpu_var(cpu_msrs));
+	else if (!nmi_enabled)
+		return NMI_DONE;
+	else
+		model->stop(&__get_cpu_var(cpu_msrs));
+	return NMI_HANDLED;
 }
 
 static void nmi_cpu_save_registers(struct op_msrs *msrs)
@@ -363,12 +352,6 @@ static void nmi_cpu_setup(void *dummy)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 }
 
-static struct notifier_block profile_exceptions_nb = {
-	.notifier_call = profile_exceptions_notify,
-	.next = NULL,
-	.priority = NMI_LOCAL_LOW_PRIOR,
-};
-
 static void nmi_cpu_restore_registers(struct op_msrs *msrs)
 {
 	struct op_msr *counters = msrs->counters;
@@ -508,7 +491,8 @@ static int nmi_setup(void)
 	ctr_running = 0;
 	/* make variables visible to the nmi handler: */
 	smp_mb();
-	err = register_die_notifier(&profile_exceptions_nb);
+	err = register_nmi_handler(NMI_LOCAL, profile_exceptions_notify,
+					0, "oprofile");
 	if (err)
 		goto fail;
 
@@ -538,7 +522,7 @@ static void nmi_shutdown(void)
 	put_online_cpus();
 	/* make variables visible to the nmi handler: */
 	smp_mb();
-	unregister_die_notifier(&profile_exceptions_nb);
+	unregister_nmi_handler(NMI_LOCAL, "oprofile");
 	msrs = &get_cpu_var(cpu_msrs);
 	model->shutdown(msrs);
 	free_msrs();
diff --git a/arch/x86/platform/mrst/vrtc.c b/arch/x86/platform/mrst/vrtc.c
index 73d70d65e76e..6d5dbcdd444a 100644
--- a/arch/x86/platform/mrst/vrtc.c
+++ b/arch/x86/platform/mrst/vrtc.c
@@ -58,8 +58,11 @@ EXPORT_SYMBOL_GPL(vrtc_cmos_write);
 unsigned long vrtc_get_time(void)
 {
 	u8 sec, min, hour, mday, mon;
+	unsigned long flags;
 	u32 year;
 
+	spin_lock_irqsave(&rtc_lock, flags);
+
 	while ((vrtc_cmos_read(RTC_FREQ_SELECT) & RTC_UIP))
 		cpu_relax();
 
@@ -70,6 +73,8 @@ unsigned long vrtc_get_time(void)
 	mon = vrtc_cmos_read(RTC_MONTH);
 	year = vrtc_cmos_read(RTC_YEAR);
 
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
 	/* vRTC YEAR reg contains the offset to 1960 */
 	year += 1960;
 
@@ -83,8 +88,10 @@ unsigned long vrtc_get_time(void)
 int vrtc_set_mmss(unsigned long nowtime)
 {
 	int real_sec, real_min;
+	unsigned long flags;
 	int vrtc_min;
 
+	spin_lock_irqsave(&rtc_lock, flags);
 	vrtc_min = vrtc_cmos_read(RTC_MINUTES);
 
 	real_sec = nowtime % 60;
@@ -95,6 +102,8 @@ int vrtc_set_mmss(unsigned long nowtime)
 
 	vrtc_cmos_write(real_sec, RTC_SECONDS);
 	vrtc_cmos_write(real_min, RTC_MINUTES);
+	spin_unlock_irqrestore(&rtc_lock, flags);
+
 	return 0;
 }
 
diff --git a/block/blk-core.c b/block/blk-core.c
index b2ed78afd9f0..d34433ae7917 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -348,9 +348,10 @@ void blk_put_queue(struct request_queue *q)
 EXPORT_SYMBOL(blk_put_queue);
 
 /*
- * Note: If a driver supplied the queue lock, it should not zap that lock
- * unexpectedly as some queue cleanup components like elevator_exit() and
- * blk_throtl_exit() need queue lock.
+ * Note: If a driver supplied the queue lock, it is disconnected
+ * by this function. The actual state of the lock doesn't matter
+ * here as the request_queue isn't accessible after this point
+ * (QUEUE_FLAG_DEAD is set) and no other requests will be queued.
  */
 void blk_cleanup_queue(struct request_queue *q)
 {
@@ -367,10 +368,8 @@ void blk_cleanup_queue(struct request_queue *q)
 	queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q);
 	mutex_unlock(&q->sysfs_lock);
 
-	if (q->elevator)
-		elevator_exit(q->elevator);
-
-	blk_throtl_exit(q);
+	if (q->queue_lock != &q->__queue_lock)
+		q->queue_lock = &q->__queue_lock;
 
 	blk_put_queue(q);
 }
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index e681805cdb47..60fda88c57f0 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -479,6 +479,11 @@ static void blk_release_queue(struct kobject *kobj)
 
 	blk_sync_queue(q);
 
+	if (q->elevator)
+		elevator_exit(q->elevator);
+
+	blk_throtl_exit(q);
+
 	if (rl->rq_pool)
 		mempool_destroy(rl->rq_pool);
 
diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index 0784f99a4665..b8e08cb67a18 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -50,6 +50,7 @@
 #include <acpi/hed.h>
 #include <asm/mce.h>
 #include <asm/tlbflush.h>
+#include <asm/nmi.h>
 
 #include "apei-internal.h"
 
@@ -749,15 +750,11 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 	}
 }
 
-static int ghes_notify_nmi(struct notifier_block *this,
-				  unsigned long cmd, void *data)
+static int ghes_notify_nmi(unsigned int cmd, struct pt_regs *regs)
 {
 	struct ghes *ghes, *ghes_global = NULL;
 	int sev, sev_global = -1;
-	int ret = NOTIFY_DONE;
-
-	if (cmd != DIE_NMI)
-		return ret;
+	int ret = NMI_DONE;
 
 	raw_spin_lock(&ghes_nmi_lock);
 	list_for_each_entry_rcu(ghes, &ghes_nmi, list) {
@@ -770,10 +767,10 @@ static int ghes_notify_nmi(struct notifier_block *this,
 			sev_global = sev;
 			ghes_global = ghes;
 		}
-		ret = NOTIFY_STOP;
+		ret = NMI_HANDLED;
 	}
 
-	if (ret == NOTIFY_DONE)
+	if (ret == NMI_DONE)
 		goto out;
 
 	if (sev_global >= GHES_SEV_PANIC) {
@@ -825,10 +822,6 @@ static struct notifier_block ghes_notifier_sci = {
 	.notifier_call = ghes_notify_sci,
 };
 
-static struct notifier_block ghes_notifier_nmi = {
-	.notifier_call = ghes_notify_nmi,
-};
-
 static unsigned long ghes_esource_prealloc_size(
 	const struct acpi_hest_generic *generic)
 {
@@ -918,7 +911,8 @@ static int __devinit ghes_probe(struct platform_device *ghes_dev)
 		ghes_estatus_pool_expand(len);
 		mutex_lock(&ghes_list_mutex);
 		if (list_empty(&ghes_nmi))
-			register_die_notifier(&ghes_notifier_nmi);
+			register_nmi_handler(NMI_LOCAL, ghes_notify_nmi, 0,
+						"ghes");
 		list_add_rcu(&ghes->list, &ghes_nmi);
 		mutex_unlock(&ghes_list_mutex);
 		break;
@@ -964,7 +958,7 @@ static int __devexit ghes_remove(struct platform_device *ghes_dev)
 		mutex_lock(&ghes_list_mutex);
 		list_del_rcu(&ghes->list);
 		if (list_empty(&ghes_nmi))
-			unregister_die_notifier(&ghes_notifier_nmi);
+			unregister_nmi_handler(NMI_LOCAL, "ghes");
 		mutex_unlock(&ghes_list_mutex);
 		/*
 		 * To synchronize with NMI handler, ghes can only be
diff --git a/drivers/base/power/clock_ops.c b/drivers/base/power/clock_ops.c
index 2c18d584066d..b97294e2d95b 100644
--- a/drivers/base/power/clock_ops.c
+++ b/drivers/base/power/clock_ops.c
@@ -42,6 +42,22 @@ static struct pm_clk_data *__to_pcd(struct device *dev)
 }
 
 /**
+ * pm_clk_acquire - Acquire a device clock.
+ * @dev: Device whose clock is to be acquired.
+ * @ce: PM clock entry corresponding to the clock.
+ */
+static void pm_clk_acquire(struct device *dev, struct pm_clock_entry *ce)
+{
+	ce->clk = clk_get(dev, ce->con_id);
+	if (IS_ERR(ce->clk)) {
+		ce->status = PCE_STATUS_ERROR;
+	} else {
+		ce->status = PCE_STATUS_ACQUIRED;
+		dev_dbg(dev, "Clock %s managed by runtime PM.\n", ce->con_id);
+	}
+}
+
+/**
  * pm_clk_add - Start using a device clock for power management.
  * @dev: Device whose clock is going to be used for power management.
  * @con_id: Connection ID of the clock.
@@ -73,6 +89,8 @@ int pm_clk_add(struct device *dev, const char *con_id)
 		}
 	}
 
+	pm_clk_acquire(dev, ce);
+
 	spin_lock_irq(&pcd->lock);
 	list_add_tail(&ce->node, &pcd->clock_list);
 	spin_unlock_irq(&pcd->lock);
@@ -82,17 +100,12 @@ int pm_clk_add(struct device *dev, const char *con_id)
 /**
  * __pm_clk_remove - Destroy PM clock entry.
  * @ce: PM clock entry to destroy.
- *
- * This routine must be called under the spinlock protecting the PM list of
- * clocks corresponding the the @ce's device.
  */
 static void __pm_clk_remove(struct pm_clock_entry *ce)
 {
 	if (!ce)
 		return;
 
-	list_del(&ce->node);
-
 	if (ce->status < PCE_STATUS_ERROR) {
 		if (ce->status == PCE_STATUS_ENABLED)
 			clk_disable(ce->clk);
@@ -126,18 +139,22 @@ void pm_clk_remove(struct device *dev, const char *con_id)
 	spin_lock_irq(&pcd->lock);
 
 	list_for_each_entry(ce, &pcd->clock_list, node) {
-		if (!con_id && !ce->con_id) {
-			__pm_clk_remove(ce);
-			break;
-		} else if (!con_id || !ce->con_id) {
+		if (!con_id && !ce->con_id)
+			goto remove;
+		else if (!con_id || !ce->con_id)
 			continue;
-		} else if (!strcmp(con_id, ce->con_id)) {
-			__pm_clk_remove(ce);
-			break;
-		}
+		else if (!strcmp(con_id, ce->con_id))
+			goto remove;
 	}
 
 	spin_unlock_irq(&pcd->lock);
+	return;
+
+ remove:
+	list_del(&ce->node);
+	spin_unlock_irq(&pcd->lock);
+
+	__pm_clk_remove(ce);
 }
 
 /**
@@ -175,20 +192,27 @@ void pm_clk_destroy(struct device *dev)
 {
 	struct pm_clk_data *pcd = __to_pcd(dev);
 	struct pm_clock_entry *ce, *c;
+	struct list_head list;
 
 	if (!pcd)
 		return;
 
 	dev->power.subsys_data = NULL;
+	INIT_LIST_HEAD(&list);
 
 	spin_lock_irq(&pcd->lock);
 
 	list_for_each_entry_safe_reverse(ce, c, &pcd->clock_list, node)
-		__pm_clk_remove(ce);
+		list_move(&ce->node, &list);
 
 	spin_unlock_irq(&pcd->lock);
 
 	kfree(pcd);
+
+	list_for_each_entry_safe_reverse(ce, c, &list, node) {
+		list_del(&ce->node);
+		__pm_clk_remove(ce);
+	}
 }
 
 #endif /* CONFIG_PM */
@@ -196,23 +220,6 @@ void pm_clk_destroy(struct device *dev)
 #ifdef CONFIG_PM_RUNTIME
 
 /**
- * pm_clk_acquire - Acquire a device clock.
- * @dev: Device whose clock is to be acquired.
- * @con_id: Connection ID of the clock.
- */
-static void pm_clk_acquire(struct device *dev,
-				    struct pm_clock_entry *ce)
-{
-	ce->clk = clk_get(dev, ce->con_id);
-	if (IS_ERR(ce->clk)) {
-		ce->status = PCE_STATUS_ERROR;
-	} else {
-		ce->status = PCE_STATUS_ACQUIRED;
-		dev_dbg(dev, "Clock %s managed by runtime PM.\n", ce->con_id);
-	}
-}
-
-/**
  * pm_clk_suspend - Disable clocks in a device's PM clock list.
  * @dev: Device to disable the clocks for.
  */
@@ -230,9 +237,6 @@ int pm_clk_suspend(struct device *dev)
 	spin_lock_irqsave(&pcd->lock, flags);
 
 	list_for_each_entry_reverse(ce, &pcd->clock_list, node) {
-		if (ce->status == PCE_STATUS_NONE)
-			pm_clk_acquire(dev, ce);
-
 		if (ce->status < PCE_STATUS_ERROR) {
 			clk_disable(ce->clk);
 			ce->status = PCE_STATUS_ACQUIRED;
@@ -262,9 +266,6 @@ int pm_clk_resume(struct device *dev)
 	spin_lock_irqsave(&pcd->lock, flags);
 
 	list_for_each_entry(ce, &pcd->clock_list, node) {
-		if (ce->status == PCE_STATUS_NONE)
-			pm_clk_acquire(dev, ce);
-
 		if (ce->status < PCE_STATUS_ERROR) {
 			clk_enable(ce->clk);
 			ce->status = PCE_STATUS_ENABLED;
diff --git a/drivers/char/ipmi/ipmi_watchdog.c b/drivers/char/ipmi/ipmi_watchdog.c
index 3302586655c4..c2917ffad2c2 100644
--- a/drivers/char/ipmi/ipmi_watchdog.c
+++ b/drivers/char/ipmi/ipmi_watchdog.c
@@ -65,6 +65,7 @@
  * mechanism for it at that time.
  */
 #include <asm/kdebug.h>
+#include <asm/nmi.h>
 #define HAVE_DIE_NMI
 #endif
 
@@ -1077,17 +1078,8 @@ static void ipmi_unregister_watchdog(int ipmi_intf)
 
 #ifdef HAVE_DIE_NMI
 static int
-ipmi_nmi(struct notifier_block *self, unsigned long val, void *data)
+ipmi_nmi(unsigned int val, struct pt_regs *regs)
 {
-	struct die_args *args = data;
-
-	if (val != DIE_NMIUNKNOWN)
-		return NOTIFY_OK;
-
-	/* Hack, if it's a memory or I/O error, ignore it. */
-	if (args->err & 0xc0)
-		return NOTIFY_OK;
-
 	/*
 	 * If we get here, it's an NMI that's not a memory or I/O
 	 * error.  We can't truly tell if it's from IPMI or not
@@ -1097,15 +1089,15 @@ ipmi_nmi(struct notifier_block *self, unsigned long val, void *data)
 
 	if (testing_nmi) {
 		testing_nmi = 2;
-		return NOTIFY_STOP;
+		return NMI_HANDLED;
 	}
 
 	/* If we are not expecting a timeout, ignore it. */
 	if (ipmi_watchdog_state == WDOG_TIMEOUT_NONE)
-		return NOTIFY_OK;
+		return NMI_DONE;
 
 	if (preaction_val != WDOG_PRETIMEOUT_NMI)
-		return NOTIFY_OK;
+		return NMI_DONE;
 
 	/*
 	 * If no one else handled the NMI, we assume it was the IPMI
@@ -1120,12 +1112,8 @@ ipmi_nmi(struct notifier_block *self, unsigned long val, void *data)
 			panic(PFX "pre-timeout");
 	}
 
-	return NOTIFY_STOP;
+	return NMI_HANDLED;
 }
-
-static struct notifier_block ipmi_nmi_handler = {
-	.notifier_call = ipmi_nmi
-};
 #endif
 
 static int wdog_reboot_handler(struct notifier_block *this,
@@ -1290,7 +1278,8 @@ static void check_parms(void)
 		}
 	}
 	if (do_nmi && !nmi_handler_registered) {
-		rv = register_die_notifier(&ipmi_nmi_handler);
+		rv = register_nmi_handler(NMI_UNKNOWN, ipmi_nmi, 0,
+						"ipmi");
 		if (rv) {
 			printk(KERN_WARNING PFX
 			       "Can't register nmi handler\n");
@@ -1298,7 +1287,7 @@ static void check_parms(void)
 		} else
 			nmi_handler_registered = 1;
 	} else if (!do_nmi && nmi_handler_registered) {
-		unregister_die_notifier(&ipmi_nmi_handler);
+		unregister_nmi_handler(NMI_UNKNOWN, "ipmi");
 		nmi_handler_registered = 0;
 	}
 #endif
@@ -1336,7 +1325,7 @@ static int __init ipmi_wdog_init(void)
 	if (rv) {
 #ifdef HAVE_DIE_NMI
 		if (nmi_handler_registered)
-			unregister_die_notifier(&ipmi_nmi_handler);
+			unregister_nmi_handler(NMI_UNKNOWN, "ipmi");
 #endif
 		atomic_notifier_chain_unregister(&panic_notifier_list,
 						 &wdog_panic_notifier);
@@ -1357,7 +1346,7 @@ static void __exit ipmi_wdog_exit(void)
 
 #ifdef HAVE_DIE_NMI
 	if (nmi_handler_registered)
-		unregister_die_notifier(&ipmi_nmi_handler);
+		unregister_nmi_handler(NMI_UNKNOWN, "ipmi");
 #endif
 
 	atomic_notifier_chain_unregister(&panic_notifier_list,
diff --git a/drivers/char/tpm/Kconfig b/drivers/char/tpm/Kconfig
index f6595aba4f0f..fa567f1158c2 100644
--- a/drivers/char/tpm/Kconfig
+++ b/drivers/char/tpm/Kconfig
@@ -43,6 +43,7 @@ config TCG_NSC
 
 config TCG_ATMEL
 	tristate "Atmel TPM Interface"
+	depends on PPC64 || HAS_IOPORT
 	---help---
 	  If you have a TPM security chip from Atmel say Yes and it 
 	  will be accessible from within Linux.  To compile this driver 
diff --git a/drivers/char/tpm/tpm.c b/drivers/char/tpm/tpm.c
index caf8012ef47c..9ca5c021d0b6 100644
--- a/drivers/char/tpm/tpm.c
+++ b/drivers/char/tpm/tpm.c
@@ -383,6 +383,9 @@ static ssize_t tpm_transmit(struct tpm_chip *chip, const char *buf,
 	u32 count, ordinal;
 	unsigned long stop;
 
+	if (bufsiz > TPM_BUFSIZE)
+		bufsiz = TPM_BUFSIZE;
+
 	count = be32_to_cpu(*((__be32 *) (buf + 2)));
 	ordinal = be32_to_cpu(*((__be32 *) (buf + 6)));
 	if (count == 0)
@@ -1102,6 +1105,7 @@ ssize_t tpm_read(struct file *file, char __user *buf,
 {
 	struct tpm_chip *chip = file->private_data;
 	ssize_t ret_size;
+	int rc;
 
 	del_singleshot_timer_sync(&chip->user_read_timer);
 	flush_work_sync(&chip->work);
@@ -1112,8 +1116,11 @@ ssize_t tpm_read(struct file *file, char __user *buf,
 			ret_size = size;
 
 		mutex_lock(&chip->buffer_mutex);
-		if (copy_to_user(buf, chip->data_buffer, ret_size))
+		rc = copy_to_user(buf, chip->data_buffer, ret_size);
+		memset(chip->data_buffer, 0, ret_size);
+		if (rc)
 			ret_size = -EFAULT;
+
 		mutex_unlock(&chip->buffer_mutex);
 	}
 
diff --git a/drivers/char/tpm/tpm_nsc.c b/drivers/char/tpm/tpm_nsc.c
index 82facc9104c7..4d2464871ada 100644
--- a/drivers/char/tpm/tpm_nsc.c
+++ b/drivers/char/tpm/tpm_nsc.c
@@ -396,8 +396,6 @@ static void __exit cleanup_nsc(void)
 	if (pdev) {
 		tpm_nsc_remove(&pdev->dev);
 		platform_device_unregister(pdev);
-		kfree(pdev);
-		pdev = NULL;
 	}
 
 	platform_driver_unregister(&nsc_drv);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index ce045a8cf82c..f07e4252b708 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -67,11 +67,11 @@ module_param_named(i915_enable_rc6, i915_enable_rc6, int, 0600);
 MODULE_PARM_DESC(i915_enable_rc6,
 		"Enable power-saving render C-state 6 (default: true)");
 
-unsigned int i915_enable_fbc __read_mostly = 1;
+unsigned int i915_enable_fbc __read_mostly = -1;
 module_param_named(i915_enable_fbc, i915_enable_fbc, int, 0600);
 MODULE_PARM_DESC(i915_enable_fbc,
 		"Enable frame buffer compression for power savings "
-		"(default: false)");
+		"(default: -1 (use per-chip default))");
 
 unsigned int i915_lvds_downclock __read_mostly = 0;
 module_param_named(lvds_downclock, i915_lvds_downclock, int, 0400);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 56a8554d9039..04411ad2e779 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1799,6 +1799,7 @@ static void intel_update_fbc(struct drm_device *dev)
 	struct drm_framebuffer *fb;
 	struct intel_framebuffer *intel_fb;
 	struct drm_i915_gem_object *obj;
+	int enable_fbc;
 
 	DRM_DEBUG_KMS("\n");
 
@@ -1839,8 +1840,15 @@ static void intel_update_fbc(struct drm_device *dev)
 	intel_fb = to_intel_framebuffer(fb);
 	obj = intel_fb->obj;
 
-	if (!i915_enable_fbc) {
-		DRM_DEBUG_KMS("fbc disabled per module param (default off)\n");
+	enable_fbc = i915_enable_fbc;
+	if (enable_fbc < 0) {
+		DRM_DEBUG_KMS("fbc set to per-chip default\n");
+		enable_fbc = 1;
+		if (INTEL_INFO(dev)->gen <= 5)
+			enable_fbc = 0;
+	}
+	if (!enable_fbc) {
+		DRM_DEBUG_KMS("fbc disabled per module param\n");
 		dev_priv->no_fbc_reason = FBC_MODULE_PARAM;
 		goto out_disable;
 	}
@@ -4687,13 +4695,13 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
 		bpc = 6; /* min is 18bpp */
 		break;
 	case 24:
-		bpc = min((unsigned int)8, display_bpc);
+		bpc = 8;
 		break;
 	case 30:
-		bpc = min((unsigned int)10, display_bpc);
+		bpc = 10;
 		break;
 	case 48:
-		bpc = min((unsigned int)12, display_bpc);
+		bpc = 12;
 		break;
 	default:
 		DRM_DEBUG("unsupported depth, assuming 24 bits\n");
@@ -4701,10 +4709,12 @@ static bool intel_choose_pipe_bpp_dither(struct drm_crtc *crtc,
 		break;
 	}
 
+	display_bpc = min(display_bpc, bpc);
+
 	DRM_DEBUG_DRIVER("setting pipe bpc to %d (max display bpc %d)\n",
 			 bpc, display_bpc);
 
-	*pipe_bpp = bpc * 3;
+	*pipe_bpp = display_bpc * 3;
 
 	return display_bpc != bpc;
 }
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 0b2ee9d39980..fe1099d8817e 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -337,9 +337,6 @@ extern void intel_release_load_detect_pipe(struct intel_encoder *intel_encoder,
 					   struct drm_connector *connector,
 					   struct intel_load_detect_pipe *old);
 
-extern struct drm_connector* intel_sdvo_find(struct drm_device *dev, int sdvoB);
-extern int intel_sdvo_supports_hotplug(struct drm_connector *connector);
-extern void intel_sdvo_set_hotplug(struct drm_connector *connector, int enable);
 extern void intelfb_restore(void);
 extern void intel_crtc_fb_gamma_set(struct drm_crtc *crtc, u16 red, u16 green,
 				    u16 blue, int regno);
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 30fe554d8936..6348c499616f 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -92,6 +92,11 @@ struct intel_sdvo {
 	*/
 	uint16_t attached_output;
 
+	/*
+	 * Hotplug activation bits for this device
+	 */
+	uint8_t hotplug_active[2];
+
 	/**
 	 * This is used to select the color range of RBG outputs in HDMI mode.
 	 * It is only valid when using TMDS encoding and 8 bit per color mode.
@@ -1208,74 +1213,20 @@ static bool intel_sdvo_get_capabilities(struct intel_sdvo *intel_sdvo, struct in
 	return true;
 }
 
-/* No use! */
-#if 0
-struct drm_connector* intel_sdvo_find(struct drm_device *dev, int sdvoB)
-{
-	struct drm_connector *connector = NULL;
-	struct intel_sdvo *iout = NULL;
-	struct intel_sdvo *sdvo;
-
-	/* find the sdvo connector */
-	list_for_each_entry(connector, &dev->mode_config.connector_list, head) {
-		iout = to_intel_sdvo(connector);
-
-		if (iout->type != INTEL_OUTPUT_SDVO)
-			continue;
-
-		sdvo = iout->dev_priv;
-
-		if (sdvo->sdvo_reg == SDVOB && sdvoB)
-			return connector;
-
-		if (sdvo->sdvo_reg == SDVOC && !sdvoB)
-			return connector;
-
-	}
-
-	return NULL;
-}
-
-int intel_sdvo_supports_hotplug(struct drm_connector *connector)
+static int intel_sdvo_supports_hotplug(struct intel_sdvo *intel_sdvo)
 {
 	u8 response[2];
-	u8 status;
-	struct intel_sdvo *intel_sdvo;
-	DRM_DEBUG_KMS("\n");
-
-	if (!connector)
-		return 0;
-
-	intel_sdvo = to_intel_sdvo(connector);
 
 	return intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_HOT_PLUG_SUPPORT,
 				    &response, 2) && response[0];
 }
 
-void intel_sdvo_set_hotplug(struct drm_connector *connector, int on)
+static void intel_sdvo_enable_hotplug(struct intel_encoder *encoder)
 {
-	u8 response[2];
-	u8 status;
-	struct intel_sdvo *intel_sdvo = to_intel_sdvo(connector);
-
-	intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_GET_ACTIVE_HOT_PLUG, NULL, 0);
-	intel_sdvo_read_response(intel_sdvo, &response, 2);
-
-	if (on) {
-		intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_GET_HOT_PLUG_SUPPORT, NULL, 0);
-		status = intel_sdvo_read_response(intel_sdvo, &response, 2);
-
-		intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_SET_ACTIVE_HOT_PLUG, &response, 2);
-	} else {
-		response[0] = 0;
-		response[1] = 0;
-		intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_SET_ACTIVE_HOT_PLUG, &response, 2);
-	}
+	struct intel_sdvo *intel_sdvo = to_intel_sdvo(&encoder->base);
 
-	intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_GET_ACTIVE_HOT_PLUG, NULL, 0);
-	intel_sdvo_read_response(intel_sdvo, &response, 2);
+	intel_sdvo_write_cmd(intel_sdvo, SDVO_CMD_SET_ACTIVE_HOT_PLUG, &intel_sdvo->hotplug_active, 2);
 }
-#endif
 
 static bool
 intel_sdvo_multifunc_encoder(struct intel_sdvo *intel_sdvo)
@@ -2045,6 +1996,7 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device)
 {
 	struct drm_encoder *encoder = &intel_sdvo->base.base;
 	struct drm_connector *connector;
+	struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
 	struct intel_connector *intel_connector;
 	struct intel_sdvo_connector *intel_sdvo_connector;
 
@@ -2062,7 +2014,17 @@ intel_sdvo_dvi_init(struct intel_sdvo *intel_sdvo, int device)
 
 	intel_connector = &intel_sdvo_connector->base;
 	connector = &intel_connector->base;
-	connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT;
+	if (intel_sdvo_supports_hotplug(intel_sdvo) & (1 << device)) {
+		connector->polled = DRM_CONNECTOR_POLL_HPD;
+		intel_sdvo->hotplug_active[0] |= 1 << device;
+		/* Some SDVO devices have one-shot hotplug interrupts.
+		 * Ensure that they get re-enabled when an interrupt happens.
+		 */
+		intel_encoder->hot_plug = intel_sdvo_enable_hotplug;
+		intel_sdvo_enable_hotplug(intel_encoder);
+	}
+	else
+		connector->polled = DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT;
 	encoder->encoder_type = DRM_MODE_ENCODER_TMDS;
 	connector->connector_type = DRM_MODE_CONNECTOR_DVID;
 
@@ -2569,6 +2531,14 @@ bool intel_sdvo_init(struct drm_device *dev, int sdvo_reg)
 	if (!intel_sdvo_get_capabilities(intel_sdvo, &intel_sdvo->caps))
 		goto err;
 
+	/* Set up hotplug command - note paranoia about contents of reply.
+	 * We assume that the hardware is in a sane state, and only touch
+	 * the bits we think we understand.
+	 */
+	intel_sdvo_get_value(intel_sdvo, SDVO_CMD_GET_ACTIVE_HOT_PLUG,
+			     &intel_sdvo->hotplug_active, 2);
+	intel_sdvo->hotplug_active[0] &= ~0x3;
+
 	if (intel_sdvo_output_setup(intel_sdvo,
 				    intel_sdvo->caps.output_flags) != true) {
 		DRM_DEBUG_KMS("SDVO output failed to setup on SDVO%c\n",
diff --git a/drivers/gpu/drm/radeon/atombios_dp.c b/drivers/gpu/drm/radeon/atombios_dp.c
index 7ad43c6b1db7..4da23889fea6 100644
--- a/drivers/gpu/drm/radeon/atombios_dp.c
+++ b/drivers/gpu/drm/radeon/atombios_dp.c
@@ -115,6 +115,7 @@ static int radeon_dp_aux_native_write(struct radeon_connector *radeon_connector,
 	u8 msg[20];
 	int msg_bytes = send_bytes + 4;
 	u8 ack;
+	unsigned retry;
 
 	if (send_bytes > 16)
 		return -1;
@@ -125,20 +126,20 @@ static int radeon_dp_aux_native_write(struct radeon_connector *radeon_connector,
 	msg[3] = (msg_bytes << 4) | (send_bytes - 1);
 	memcpy(&msg[4], send, send_bytes);
 
-	while (1) {
+	for (retry = 0; retry < 4; retry++) {
 		ret = radeon_process_aux_ch(dig_connector->dp_i2c_bus,
 					    msg, msg_bytes, NULL, 0, delay, &ack);
 		if (ret < 0)
 			return ret;
 		if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_ACK)
-			break;
+			return send_bytes;
 		else if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_DEFER)
 			udelay(400);
 		else
 			return -EIO;
 	}
 
-	return send_bytes;
+	return -EIO;
 }
 
 static int radeon_dp_aux_native_read(struct radeon_connector *radeon_connector,
@@ -149,26 +150,29 @@ static int radeon_dp_aux_native_read(struct radeon_connector *radeon_connector,
 	int msg_bytes = 4;
 	u8 ack;
 	int ret;
+	unsigned retry;
 
 	msg[0] = address;
 	msg[1] = address >> 8;
 	msg[2] = AUX_NATIVE_READ << 4;
 	msg[3] = (msg_bytes << 4) | (recv_bytes - 1);
 
-	while (1) {
+	for (retry = 0; retry < 4; retry++) {
 		ret = radeon_process_aux_ch(dig_connector->dp_i2c_bus,
 					    msg, msg_bytes, recv, recv_bytes, delay, &ack);
-		if (ret == 0)
-			return -EPROTO;
 		if (ret < 0)
 			return ret;
 		if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_ACK)
 			return ret;
 		else if ((ack & AUX_NATIVE_REPLY_MASK) == AUX_NATIVE_REPLY_DEFER)
 			udelay(400);
+		else if (ret == 0)
+			return -EPROTO;
 		else
 			return -EIO;
 	}
+
+	return -EIO;
 }
 
 static void radeon_write_dpcd_reg(struct radeon_connector *radeon_connector,
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index e8a746712b5b..c4ffa14fb2f4 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -1590,48 +1590,6 @@ static u32 evergreen_get_tile_pipe_to_backend_map(struct radeon_device *rdev,
 	return backend_map;
 }
 
-static void evergreen_program_channel_remap(struct radeon_device *rdev)
-{
-	u32 tcp_chan_steer_lo, tcp_chan_steer_hi, mc_shared_chremap, tmp;
-
-	tmp = RREG32(MC_SHARED_CHMAP);
-	switch ((tmp & NOOFCHAN_MASK) >> NOOFCHAN_SHIFT) {
-	case 0:
-	case 1:
-	case 2:
-	case 3:
-	default:
-		/* default mapping */
-		mc_shared_chremap = 0x00fac688;
-		break;
-	}
-
-	switch (rdev->family) {
-	case CHIP_HEMLOCK:
-	case CHIP_CYPRESS:
-	case CHIP_BARTS:
-		tcp_chan_steer_lo = 0x54763210;
-		tcp_chan_steer_hi = 0x0000ba98;
-		break;
-	case CHIP_JUNIPER:
-	case CHIP_REDWOOD:
-	case CHIP_CEDAR:
-	case CHIP_PALM:
-	case CHIP_SUMO:
-	case CHIP_SUMO2:
-	case CHIP_TURKS:
-	case CHIP_CAICOS:
-	default:
-		tcp_chan_steer_lo = 0x76543210;
-		tcp_chan_steer_hi = 0x0000ba98;
-		break;
-	}
-
-	WREG32(TCP_CHAN_STEER_LO, tcp_chan_steer_lo);
-	WREG32(TCP_CHAN_STEER_HI, tcp_chan_steer_hi);
-	WREG32(MC_SHARED_CHREMAP, mc_shared_chremap);
-}
-
 static void evergreen_gpu_init(struct radeon_device *rdev)
 {
 	u32 cc_rb_backend_disable = 0;
@@ -2078,8 +2036,6 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 	WREG32(DMIF_ADDR_CONFIG, gb_addr_config);
 	WREG32(HDP_ADDR_CONFIG, gb_addr_config);
 
-	evergreen_program_channel_remap(rdev);
-
 	num_shader_engines = ((RREG32(GB_ADDR_CONFIG) & NUM_SHADER_ENGINES(3)) >> 12) + 1;
 	grbm_gfx_index = INSTANCE_BROADCAST_WRITES;
 
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index 99fbd793c08c..8c79ca97753d 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -569,36 +569,6 @@ static u32 cayman_get_tile_pipe_to_backend_map(struct radeon_device *rdev,
 	return backend_map;
 }
 
-static void cayman_program_channel_remap(struct radeon_device *rdev)
-{
-	u32 tcp_chan_steer_lo, tcp_chan_steer_hi, mc_shared_chremap, tmp;
-
-	tmp = RREG32(MC_SHARED_CHMAP);
-	switch ((tmp & NOOFCHAN_MASK) >> NOOFCHAN_SHIFT) {
-	case 0:
-	case 1:
-	case 2:
-	case 3:
-	default:
-		/* default mapping */
-		mc_shared_chremap = 0x00fac688;
-		break;
-	}
-
-	switch (rdev->family) {
-	case CHIP_CAYMAN:
-	default:
-		//tcp_chan_steer_lo = 0x54763210
-		tcp_chan_steer_lo = 0x76543210;
-		tcp_chan_steer_hi = 0x0000ba98;
-		break;
-	}
-
-	WREG32(TCP_CHAN_STEER_LO, tcp_chan_steer_lo);
-	WREG32(TCP_CHAN_STEER_HI, tcp_chan_steer_hi);
-	WREG32(MC_SHARED_CHREMAP, mc_shared_chremap);
-}
-
 static u32 cayman_get_disable_mask_per_asic(struct radeon_device *rdev,
 					    u32 disable_mask_per_se,
 					    u32 max_disable_mask_per_se,
@@ -842,8 +812,6 @@ static void cayman_gpu_init(struct radeon_device *rdev)
 	WREG32(DMIF_ADDR_CONFIG, gb_addr_config);
 	WREG32(HDP_ADDR_CONFIG, gb_addr_config);
 
-	cayman_program_channel_remap(rdev);
-
 	/* primary versions */
 	WREG32(CC_RB_BACKEND_DISABLE, cc_rb_backend_disable);
 	WREG32(CC_SYS_RB_BACKEND_DISABLE, cc_rb_backend_disable);
diff --git a/drivers/gpu/drm/radeon/r100.c b/drivers/gpu/drm/radeon/r100.c
index 5b1837b4aacf..7fcdbbbf2979 100644
--- a/drivers/gpu/drm/radeon/r100.c
+++ b/drivers/gpu/drm/radeon/r100.c
@@ -773,8 +773,8 @@ int r100_copy_blit(struct radeon_device *rdev,
 		radeon_ring_write(rdev, (0x1fff) | (0x1fff << 16));
 		radeon_ring_write(rdev, 0);
 		radeon_ring_write(rdev, (0x1fff) | (0x1fff << 16));
-		radeon_ring_write(rdev, cur_pages);
-		radeon_ring_write(rdev, cur_pages);
+		radeon_ring_write(rdev, num_gpu_pages);
+		radeon_ring_write(rdev, num_gpu_pages);
 		radeon_ring_write(rdev, cur_pages | (stride_pixels << 16));
 	}
 	radeon_ring_write(rdev, PACKET0(RADEON_DSTCACHE_CTLSTAT, 0));
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index c4b8741dbf58..bce63fd329d4 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -68,11 +68,11 @@ void radeon_connector_hotplug(struct drm_connector *connector)
 	if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort) {
 		int saved_dpms = connector->dpms;
 
-		if (radeon_hpd_sense(rdev, radeon_connector->hpd.hpd) &&
-		    radeon_dp_needs_link_train(radeon_connector))
-			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
-		else
+		/* Only turn off the display it it's physically disconnected */
+		if (!radeon_hpd_sense(rdev, radeon_connector->hpd.hpd))
 			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
+		else if (radeon_dp_needs_link_train(radeon_connector))
+			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_ON);
 		connector->dpms = saved_dpms;
 	}
 }
diff --git a/drivers/gpu/drm/radeon/radeon_cursor.c b/drivers/gpu/drm/radeon/radeon_cursor.c
index 3189a7efb2e9..fde25c0d65a0 100644
--- a/drivers/gpu/drm/radeon/radeon_cursor.c
+++ b/drivers/gpu/drm/radeon/radeon_cursor.c
@@ -208,23 +208,25 @@ int radeon_crtc_cursor_move(struct drm_crtc *crtc,
 	int xorigin = 0, yorigin = 0;
 	int w = radeon_crtc->cursor_width;
 
-	if (x < 0)
-		xorigin = -x + 1;
-	if (y < 0)
-		yorigin = -y + 1;
-	if (xorigin >= CURSOR_WIDTH)
-		xorigin = CURSOR_WIDTH - 1;
-	if (yorigin >= CURSOR_HEIGHT)
-		yorigin = CURSOR_HEIGHT - 1;
-
 	if (ASIC_IS_AVIVO(rdev)) {
-		int i = 0;
-		struct drm_crtc *crtc_p;
-
 		/* avivo cursor are offset into the total surface */
 		x += crtc->x;
 		y += crtc->y;
-		DRM_DEBUG("x %d y %d c->x %d c->y %d\n", x, y, crtc->x, crtc->y);
+	}
+	DRM_DEBUG("x %d y %d c->x %d c->y %d\n", x, y, crtc->x, crtc->y);
+
+	if (x < 0) {
+		xorigin = min(-x, CURSOR_WIDTH - 1);
+		x = 0;
+	}
+	if (y < 0) {
+		yorigin = min(-y, CURSOR_HEIGHT - 1);
+		y = 0;
+	}
+
+	if (ASIC_IS_AVIVO(rdev)) {
+		int i = 0;
+		struct drm_crtc *crtc_p;
 
 		/* avivo cursor image can't end on 128 pixel boundary or
 		 * go past the end of the frame if both crtcs are enabled
@@ -253,16 +255,12 @@ int radeon_crtc_cursor_move(struct drm_crtc *crtc,
 
 	radeon_lock_cursor(crtc, true);
 	if (ASIC_IS_DCE4(rdev)) {
-		WREG32(EVERGREEN_CUR_POSITION + radeon_crtc->crtc_offset,
-		       ((xorigin ? 0 : x) << 16) |
-		       (yorigin ? 0 : y));
+		WREG32(EVERGREEN_CUR_POSITION + radeon_crtc->crtc_offset, (x << 16) | y);
 		WREG32(EVERGREEN_CUR_HOT_SPOT + radeon_crtc->crtc_offset, (xorigin << 16) | yorigin);
 		WREG32(EVERGREEN_CUR_SIZE + radeon_crtc->crtc_offset,
 		       ((w - 1) << 16) | (radeon_crtc->cursor_height - 1));
 	} else if (ASIC_IS_AVIVO(rdev)) {
-		WREG32(AVIVO_D1CUR_POSITION + radeon_crtc->crtc_offset,
-			     ((xorigin ? 0 : x) << 16) |
-			     (yorigin ? 0 : y));
+		WREG32(AVIVO_D1CUR_POSITION + radeon_crtc->crtc_offset, (x << 16) | y);
 		WREG32(AVIVO_D1CUR_HOT_SPOT + radeon_crtc->crtc_offset, (xorigin << 16) | yorigin);
 		WREG32(AVIVO_D1CUR_SIZE + radeon_crtc->crtc_offset,
 		       ((w - 1) << 16) | (radeon_crtc->cursor_height - 1));
@@ -276,8 +274,8 @@ int radeon_crtc_cursor_move(struct drm_crtc *crtc,
 			| yorigin));
 		WREG32(RADEON_CUR_HORZ_VERT_POSN + radeon_crtc->crtc_offset,
 		       (RADEON_CUR_LOCK
-			| ((xorigin ? 0 : x) << 16)
-			| (yorigin ? 0 : y)));
+			| (x << 16)
+			| y));
 		/* offset is from DISP(2)_BASE_ADDRESS */
 		WREG32(RADEON_CUR_OFFSET + radeon_crtc->crtc_offset, (radeon_crtc->legacy_cursor_offset +
 								      (yorigin * 256)));
diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c
index 319d85d7e759..13690f3eb4a4 100644
--- a/drivers/gpu/drm/radeon/radeon_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -1507,7 +1507,14 @@ radeon_atom_encoder_dpms(struct drm_encoder *encoder, int mode)
 		switch (mode) {
 		case DRM_MODE_DPMS_ON:
 			args.ucAction = ATOM_ENABLE;
-			atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+			/* workaround for DVOOutputControl on some RS690 systems */
+			if (radeon_encoder->encoder_id == ENCODER_OBJECT_ID_INTERNAL_DDI) {
+				u32 reg = RREG32(RADEON_BIOS_3_SCRATCH);
+				WREG32(RADEON_BIOS_3_SCRATCH, reg & ~ATOM_S3_DFP2I_ACTIVE);
+				atom_execute_table(rdev->mode_info.atom_context, index, (uint32_t *)&args);
+				WREG32(RADEON_BIOS_3_SCRATCH, reg);
+			} 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);
diff --git a/drivers/gpu/drm/radeon/rv770.c b/drivers/gpu/drm/radeon/rv770.c
index 4720d000d440..b13c2eedc321 100644
--- a/drivers/gpu/drm/radeon/rv770.c
+++ b/drivers/gpu/drm/radeon/rv770.c
@@ -536,55 +536,6 @@ static u32 r700_get_tile_pipe_to_backend_map(struct radeon_device *rdev,
 	return backend_map;
 }
 
-static void rv770_program_channel_remap(struct radeon_device *rdev)
-{
-	u32 tcp_chan_steer, mc_shared_chremap, tmp;
-	bool force_no_swizzle;
-
-	switch (rdev->family) {
-	case CHIP_RV770:
-	case CHIP_RV730:
-		force_no_swizzle = false;
-		break;
-	case CHIP_RV710:
-	case CHIP_RV740:
-	default:
-		force_no_swizzle = true;
-		break;
-	}
-
-	tmp = RREG32(MC_SHARED_CHMAP);
-	switch ((tmp & NOOFCHAN_MASK) >> NOOFCHAN_SHIFT) {
-	case 0:
-	case 1:
-	default:
-		/* default mapping */
-		mc_shared_chremap = 0x00fac688;
-		break;
-	case 2:
-	case 3:
-		if (force_no_swizzle)
-			mc_shared_chremap = 0x00fac688;
-		else
-			mc_shared_chremap = 0x00bbc298;
-		break;
-	}
-
-	if (rdev->family == CHIP_RV740)
-		tcp_chan_steer = 0x00ef2a60;
-	else
-		tcp_chan_steer = 0x00fac688;
-
-	/* RV770 CE has special chremap setup */
-	if (rdev->pdev->device == 0x944e) {
-		tcp_chan_steer = 0x00b08b08;
-		mc_shared_chremap = 0x00b08b08;
-	}
-
-	WREG32(TCP_CHAN_STEER, tcp_chan_steer);
-	WREG32(MC_SHARED_CHREMAP, mc_shared_chremap);
-}
-
 static void rv770_gpu_init(struct radeon_device *rdev)
 {
 	int i, j, num_qd_pipes;
@@ -785,8 +736,6 @@ static void rv770_gpu_init(struct radeon_device *rdev)
 	WREG32(DCP_TILING_CONFIG, (gb_tiling_config & 0xffff));
 	WREG32(HDP_TILING_CONFIG, (gb_tiling_config & 0xffff));
 
-	rv770_program_channel_remap(rdev);
-
 	WREG32(CC_RB_BACKEND_DISABLE,      cc_rb_backend_disable);
 	WREG32(CC_GC_SHADER_PIPE_CONFIG,   cc_gc_shader_pipe_config);
 	WREG32(GC_USER_SHADER_PIPE_CONFIG, cc_gc_shader_pipe_config);
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index 411257676133..932383786642 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -36,17 +36,25 @@
 #include <linux/cpu.h>
 #include <linux/pci.h>
 #include <linux/smp.h>
+#include <linux/moduleparam.h>
 #include <asm/msr.h>
 #include <asm/processor.h>
 
 #define DRVNAME	"coretemp"
 
+/*
+ * force_tjmax only matters when TjMax can't be read from the CPU itself.
+ * When set, it replaces the driver's suboptimal heuristic.
+ */
+static int force_tjmax;
+module_param_named(tjmax, force_tjmax, int, 0444);
+MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
+
 #define BASE_SYSFS_ATTR_NO	2	/* Sysfs Base attr no for coretemp */
 #define NUM_REAL_CORES		16	/* Number of Real cores per cpu */
 #define CORETEMP_NAME_LENGTH	17	/* String Length of attrs */
 #define MAX_CORE_ATTRS		4	/* Maximum no of basic attrs */
-#define MAX_THRESH_ATTRS	3	/* Maximum no of Threshold attrs */
-#define TOTAL_ATTRS		(MAX_CORE_ATTRS + MAX_THRESH_ATTRS)
+#define TOTAL_ATTRS		(MAX_CORE_ATTRS + 1)
 #define MAX_CORE_DATA		(NUM_REAL_CORES + BASE_SYSFS_ATTR_NO)
 
 #ifdef CONFIG_SMP
@@ -69,8 +77,6 @@
  *		This value is passed as "id" field to rdmsr/wrmsr functions.
  * @status_reg: One of IA32_THERM_STATUS or IA32_PACKAGE_THERM_STATUS,
  *		from where the temperature values should be read.
- * @intrpt_reg: One of IA32_THERM_INTERRUPT or IA32_PACKAGE_THERM_INTERRUPT,
- *		from where the thresholds are read.
  * @attr_size:  Total number of pre-core attrs displayed in the sysfs.
  * @is_pkg_data: If this is 1, the temp_data holds pkgtemp data.
  *		Otherwise, temp_data holds coretemp data.
@@ -79,13 +85,11 @@
 struct temp_data {
 	int temp;
 	int ttarget;
-	int tmin;
 	int tjmax;
 	unsigned long last_updated;
 	unsigned int cpu;
 	u32 cpu_core_id;
 	u32 status_reg;
-	u32 intrpt_reg;
 	int attr_size;
 	bool is_pkg_data;
 	bool valid;
@@ -143,19 +147,6 @@ static ssize_t show_crit_alarm(struct device *dev,
 	return sprintf(buf, "%d\n", (eax >> 5) & 1);
 }
 
-static ssize_t show_max_alarm(struct device *dev,
-				struct device_attribute *devattr, char *buf)
-{
-	u32 eax, edx;
-	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
-	struct platform_data *pdata = dev_get_drvdata(dev);
-	struct temp_data *tdata = pdata->core_data[attr->index];
-
-	rdmsr_on_cpu(tdata->cpu, tdata->status_reg, &eax, &edx);
-
-	return sprintf(buf, "%d\n", !!(eax & THERM_STATUS_THRESHOLD1));
-}
-
 static ssize_t show_tjmax(struct device *dev,
 			struct device_attribute *devattr, char *buf)
 {
@@ -174,83 +165,6 @@ static ssize_t show_ttarget(struct device *dev,
 	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->ttarget);
 }
 
-static ssize_t store_ttarget(struct device *dev,
-				struct device_attribute *devattr,
-				const char *buf, size_t count)
-{
-	struct platform_data *pdata = dev_get_drvdata(dev);
-	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
-	struct temp_data *tdata = pdata->core_data[attr->index];
-	u32 eax, edx;
-	unsigned long val;
-	int diff;
-
-	if (strict_strtoul(buf, 10, &val))
-		return -EINVAL;
-
-	/*
-	 * THERM_MASK_THRESHOLD1 is 7 bits wide. Values are entered in terms
-	 * of milli degree celsius. Hence don't accept val > (127 * 1000)
-	 */
-	if (val > tdata->tjmax || val > 127000)
-		return -EINVAL;
-
-	diff = (tdata->tjmax - val) / 1000;
-
-	mutex_lock(&tdata->update_lock);
-	rdmsr_on_cpu(tdata->cpu, tdata->intrpt_reg, &eax, &edx);
-	eax = (eax & ~THERM_MASK_THRESHOLD1) |
-				(diff << THERM_SHIFT_THRESHOLD1);
-	wrmsr_on_cpu(tdata->cpu, tdata->intrpt_reg, eax, edx);
-	tdata->ttarget = val;
-	mutex_unlock(&tdata->update_lock);
-
-	return count;
-}
-
-static ssize_t show_tmin(struct device *dev,
-			struct device_attribute *devattr, char *buf)
-{
-	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
-	struct platform_data *pdata = dev_get_drvdata(dev);
-
-	return sprintf(buf, "%d\n", pdata->core_data[attr->index]->tmin);
-}
-
-static ssize_t store_tmin(struct device *dev,
-				struct device_attribute *devattr,
-				const char *buf, size_t count)
-{
-	struct platform_data *pdata = dev_get_drvdata(dev);
-	struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
-	struct temp_data *tdata = pdata->core_data[attr->index];
-	u32 eax, edx;
-	unsigned long val;
-	int diff;
-
-	if (strict_strtoul(buf, 10, &val))
-		return -EINVAL;
-
-	/*
-	 * THERM_MASK_THRESHOLD0 is 7 bits wide. Values are entered in terms
-	 * of milli degree celsius. Hence don't accept val > (127 * 1000)
-	 */
-	if (val > tdata->tjmax || val > 127000)
-		return -EINVAL;
-
-	diff = (tdata->tjmax - val) / 1000;
-
-	mutex_lock(&tdata->update_lock);
-	rdmsr_on_cpu(tdata->cpu, tdata->intrpt_reg, &eax, &edx);
-	eax = (eax & ~THERM_MASK_THRESHOLD0) |
-				(diff << THERM_SHIFT_THRESHOLD0);
-	wrmsr_on_cpu(tdata->cpu, tdata->intrpt_reg, eax, edx);
-	tdata->tmin = val;
-	mutex_unlock(&tdata->update_lock);
-
-	return count;
-}
-
 static ssize_t show_temp(struct device *dev,
 			struct device_attribute *devattr, char *buf)
 {
@@ -374,7 +288,6 @@ static int adjust_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 
 static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 {
-	/* The 100C is default for both mobile and non mobile CPUs */
 	int err;
 	u32 eax, edx;
 	u32 val;
@@ -385,7 +298,8 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 	 */
 	err = rdmsr_safe_on_cpu(id, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
 	if (err) {
-		dev_warn(dev, "Unable to read TjMax from CPU.\n");
+		if (c->x86_model > 0xe && c->x86_model != 0x1c)
+			dev_warn(dev, "Unable to read TjMax from CPU %u\n", id);
 	} else {
 		val = (eax >> 16) & 0xff;
 		/*
@@ -393,11 +307,17 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 		 * will be used
 		 */
 		if (val) {
-			dev_info(dev, "TjMax is %d C.\n", val);
+			dev_dbg(dev, "TjMax is %d degrees C\n", val);
 			return val * 1000;
 		}
 	}
 
+	if (force_tjmax) {
+		dev_notice(dev, "TjMax forced to %d degrees C by user\n",
+			   force_tjmax);
+		return force_tjmax * 1000;
+	}
+
 	/*
 	 * An assumption is made for early CPUs and unreadable MSR.
 	 * NOTE: the calculated value may not be correct.
@@ -414,21 +334,6 @@ static void __devinit get_ucode_rev_on_cpu(void *edx)
 	rdmsr(MSR_IA32_UCODE_REV, eax, *(u32 *)edx);
 }
 
-static int get_pkg_tjmax(unsigned int cpu, struct device *dev)
-{
-	int err;
-	u32 eax, edx, val;
-
-	err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
-	if (!err) {
-		val = (eax >> 16) & 0xff;
-		if (val)
-			return val * 1000;
-	}
-	dev_warn(dev, "Unable to read Pkg-TjMax from CPU:%u\n", cpu);
-	return 100000; /* Default TjMax: 100 degree celsius */
-}
-
 static int create_name_attr(struct platform_data *pdata, struct device *dev)
 {
 	sysfs_attr_init(&pdata->name_attr.attr);
@@ -442,19 +347,14 @@ static int create_core_attrs(struct temp_data *tdata, struct device *dev,
 				int attr_no)
 {
 	int err, i;
-	static ssize_t (*rd_ptr[TOTAL_ATTRS]) (struct device *dev,
+	static ssize_t (*const rd_ptr[TOTAL_ATTRS]) (struct device *dev,
 			struct device_attribute *devattr, char *buf) = {
 			show_label, show_crit_alarm, show_temp, show_tjmax,
-			show_max_alarm, show_ttarget, show_tmin };
-	static ssize_t (*rw_ptr[TOTAL_ATTRS]) (struct device *dev,
-			struct device_attribute *devattr, const char *buf,
-			size_t count) = { NULL, NULL, NULL, NULL, NULL,
-					store_ttarget, store_tmin };
-	static const char *names[TOTAL_ATTRS] = {
+			show_ttarget };
+	static const char *const names[TOTAL_ATTRS] = {
 					"temp%d_label", "temp%d_crit_alarm",
 					"temp%d_input", "temp%d_crit",
-					"temp%d_max_alarm", "temp%d_max",
-					"temp%d_max_hyst" };
+					"temp%d_max" };
 
 	for (i = 0; i < tdata->attr_size; i++) {
 		snprintf(tdata->attr_name[i], CORETEMP_NAME_LENGTH, names[i],
@@ -462,10 +362,6 @@ static int create_core_attrs(struct temp_data *tdata, struct device *dev,
 		sysfs_attr_init(&tdata->sd_attrs[i].dev_attr.attr);
 		tdata->sd_attrs[i].dev_attr.attr.name = tdata->attr_name[i];
 		tdata->sd_attrs[i].dev_attr.attr.mode = S_IRUGO;
-		if (rw_ptr[i]) {
-			tdata->sd_attrs[i].dev_attr.attr.mode |= S_IWUSR;
-			tdata->sd_attrs[i].dev_attr.store = rw_ptr[i];
-		}
 		tdata->sd_attrs[i].dev_attr.show = rd_ptr[i];
 		tdata->sd_attrs[i].index = attr_no;
 		err = device_create_file(dev, &tdata->sd_attrs[i].dev_attr);
@@ -481,9 +377,9 @@ exit_free:
 }
 
 
-static int __devinit chk_ucode_version(struct platform_device *pdev)
+static int __cpuinit chk_ucode_version(unsigned int cpu)
 {
-	struct cpuinfo_x86 *c = &cpu_data(pdev->id);
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	int err;
 	u32 edx;
 
@@ -494,17 +390,15 @@ static int __devinit chk_ucode_version(struct platform_device *pdev)
 	 */
 	if (c->x86_model == 0xe && c->x86_mask < 0xc) {
 		/* check for microcode update */
-		err = smp_call_function_single(pdev->id, get_ucode_rev_on_cpu,
+		err = smp_call_function_single(cpu, get_ucode_rev_on_cpu,
 					       &edx, 1);
 		if (err) {
-			dev_err(&pdev->dev,
-				"Cannot determine microcode revision of "
-				"CPU#%u (%d)!\n", pdev->id, err);
+			pr_err("Cannot determine microcode revision of "
+			       "CPU#%u (%d)!\n", cpu, err);
 			return -ENODEV;
 		} else if (edx < 0x39) {
-			dev_err(&pdev->dev,
-				"Errata AE18 not fixed, update BIOS or "
-				"microcode of the CPU!\n");
+			pr_err("Errata AE18 not fixed, update BIOS or "
+			       "microcode of the CPU!\n");
 			return -ENODEV;
 		}
 	}
@@ -538,8 +432,6 @@ static struct temp_data *init_temp_data(unsigned int cpu, int pkg_flag)
 
 	tdata->status_reg = pkg_flag ? MSR_IA32_PACKAGE_THERM_STATUS :
 							MSR_IA32_THERM_STATUS;
-	tdata->intrpt_reg = pkg_flag ? MSR_IA32_PACKAGE_THERM_INTERRUPT :
-						MSR_IA32_THERM_INTERRUPT;
 	tdata->is_pkg_data = pkg_flag;
 	tdata->cpu = cpu;
 	tdata->cpu_core_id = TO_CORE_ID(cpu);
@@ -548,11 +440,11 @@ static struct temp_data *init_temp_data(unsigned int cpu, int pkg_flag)
 	return tdata;
 }
 
-static int create_core_data(struct platform_data *pdata,
-				struct platform_device *pdev,
+static int create_core_data(struct platform_device *pdev,
 				unsigned int cpu, int pkg_flag)
 {
 	struct temp_data *tdata;
+	struct platform_data *pdata = platform_get_drvdata(pdev);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	u32 eax, edx;
 	int err, attr_no;
@@ -588,25 +480,21 @@ static int create_core_data(struct platform_data *pdata,
 		goto exit_free;
 
 	/* We can access status register. Get Critical Temperature */
-	if (pkg_flag)
-		tdata->tjmax = get_pkg_tjmax(pdev->id, &pdev->dev);
-	else
-		tdata->tjmax = get_tjmax(c, cpu, &pdev->dev);
+	tdata->tjmax = get_tjmax(c, cpu, &pdev->dev);
 
 	/*
-	 * Test if we can access the intrpt register. If so, increase the
-	 * 'size' enough to have ttarget/tmin/max_alarm interfaces.
-	 * Initialize ttarget with bits 16:22 of MSR_IA32_THERM_INTERRUPT
+	 * Read the still undocumented bits 8:15 of IA32_TEMPERATURE_TARGET.
+	 * The target temperature is available on older CPUs but not in this
+	 * register. Atoms don't have the register at all.
 	 */
-	err = rdmsr_safe_on_cpu(cpu, tdata->intrpt_reg, &eax, &edx);
-	if (!err) {
-		tdata->attr_size += MAX_THRESH_ATTRS;
-		tdata->tmin = tdata->tjmax -
-			      ((eax & THERM_MASK_THRESHOLD0) >>
-			       THERM_SHIFT_THRESHOLD0) * 1000;
-		tdata->ttarget = tdata->tjmax -
-				 ((eax & THERM_MASK_THRESHOLD1) >>
-				  THERM_SHIFT_THRESHOLD1) * 1000;
+	if (c->x86_model > 0xe && c->x86_model != 0x1c) {
+		err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET,
+					&eax, &edx);
+		if (!err) {
+			tdata->ttarget
+			  = tdata->tjmax - ((eax >> 8) & 0xff) * 1000;
+			tdata->attr_size++;
+		}
 	}
 
 	pdata->core_data[attr_no] = tdata;
@@ -618,22 +506,20 @@ static int create_core_data(struct platform_data *pdata,
 
 	return 0;
 exit_free:
+	pdata->core_data[attr_no] = NULL;
 	kfree(tdata);
 	return err;
 }
 
 static void coretemp_add_core(unsigned int cpu, int pkg_flag)
 {
-	struct platform_data *pdata;
 	struct platform_device *pdev = coretemp_get_pdev(cpu);
 	int err;
 
 	if (!pdev)
 		return;
 
-	pdata = platform_get_drvdata(pdev);
-
-	err = create_core_data(pdata, pdev, cpu, pkg_flag);
+	err = create_core_data(pdev, cpu, pkg_flag);
 	if (err)
 		dev_err(&pdev->dev, "Adding Core %u failed\n", cpu);
 }
@@ -657,11 +543,6 @@ static int __devinit coretemp_probe(struct platform_device *pdev)
 	struct platform_data *pdata;
 	int err;
 
-	/* Check the microcode version of the CPU */
-	err = chk_ucode_version(pdev);
-	if (err)
-		return err;
-
 	/* Initialize the per-package data structures */
 	pdata = kzalloc(sizeof(struct platform_data), GFP_KERNEL);
 	if (!pdata)
@@ -671,7 +552,7 @@ static int __devinit coretemp_probe(struct platform_device *pdev)
 	if (err)
 		goto exit_free;
 
-	pdata->phys_proc_id = TO_PHYS_ID(pdev->id);
+	pdata->phys_proc_id = pdev->id;
 	platform_set_drvdata(pdev, pdata);
 
 	pdata->hwmon_dev = hwmon_device_register(&pdev->dev);
@@ -723,7 +604,7 @@ static int __cpuinit coretemp_device_add(unsigned int cpu)
 
 	mutex_lock(&pdev_list_mutex);
 
-	pdev = platform_device_alloc(DRVNAME, cpu);
+	pdev = platform_device_alloc(DRVNAME, TO_PHYS_ID(cpu));
 	if (!pdev) {
 		err = -ENOMEM;
 		pr_err("Device allocation failed\n");
@@ -743,7 +624,7 @@ static int __cpuinit coretemp_device_add(unsigned int cpu)
 	}
 
 	pdev_entry->pdev = pdev;
-	pdev_entry->phys_proc_id = TO_PHYS_ID(cpu);
+	pdev_entry->phys_proc_id = pdev->id;
 
 	list_add_tail(&pdev_entry->list, &pdev_list);
 	mutex_unlock(&pdev_list_mutex);
@@ -804,6 +685,10 @@ static void __cpuinit get_core_online(unsigned int cpu)
 		return;
 
 	if (!pdev) {
+		/* Check the microcode version of the CPU */
+		if (chk_ucode_version(cpu))
+			return;
+
 		/*
 		 * Alright, we have DTS support.
 		 * We are bringing the _first_ core in this pkg
diff --git a/drivers/hwmon/ds620.c b/drivers/hwmon/ds620.c
index 257957c69d92..4f7c3fc40a89 100644
--- a/drivers/hwmon/ds620.c
+++ b/drivers/hwmon/ds620.c
@@ -72,7 +72,7 @@ struct ds620_data {
 	char valid;		/* !=0 if following fields are valid */
 	unsigned long last_updated;	/* In jiffies */
 
-	u16 temp[3];		/* Register values, word */
+	s16 temp[3];		/* Register values, word */
 };
 
 /*
diff --git a/drivers/hwmon/w83791d.c b/drivers/hwmon/w83791d.c
index 17cf1ab95521..8c2844e5691c 100644
--- a/drivers/hwmon/w83791d.c
+++ b/drivers/hwmon/w83791d.c
@@ -329,8 +329,8 @@ static int w83791d_detect(struct i2c_client *client,
 			  struct i2c_board_info *info);
 static int w83791d_remove(struct i2c_client *client);
 
-static int w83791d_read(struct i2c_client *client, u8 register);
-static int w83791d_write(struct i2c_client *client, u8 register, u8 value);
+static int w83791d_read(struct i2c_client *client, u8 reg);
+static int w83791d_write(struct i2c_client *client, u8 reg, u8 value);
 static struct w83791d_data *w83791d_update_device(struct device *dev);
 
 #ifdef DEBUG
diff --git a/drivers/ide/ide-disk.c b/drivers/ide/ide-disk.c
index 274798068a54..16f69be820c7 100644
--- a/drivers/ide/ide-disk.c
+++ b/drivers/ide/ide-disk.c
@@ -435,7 +435,12 @@ static int idedisk_prep_fn(struct request_queue *q, struct request *rq)
 	if (!(rq->cmd_flags & REQ_FLUSH))
 		return BLKPREP_OK;
 
-	cmd = kzalloc(sizeof(*cmd), GFP_ATOMIC);
+	if (rq->special) {
+		cmd = rq->special;
+		memset(cmd, 0, sizeof(*cmd));
+	} else {
+		cmd = kzalloc(sizeof(*cmd), GFP_ATOMIC);
+	}
 
 	/* FIXME: map struct ide_taskfile on rq->cmd[] */
 	BUG_ON(cmd == NULL);
diff --git a/drivers/infiniband/hw/cxgb3/iwch_cm.c b/drivers/infiniband/hw/cxgb3/iwch_cm.c
index 17bf9d95463c..6cd642aaa4de 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_cm.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_cm.c
@@ -287,7 +287,7 @@ void __free_ep(struct kref *kref)
 	if (test_bit(RELEASE_RESOURCES, &ep->com.flags)) {
 		cxgb3_remove_tid(ep->com.tdev, (void *)ep, ep->hwtid);
 		dst_release(ep->dst);
-		l2t_release(L2DATA(ep->com.tdev), ep->l2t);
+		l2t_release(ep->com.tdev, ep->l2t);
 	}
 	kfree(ep);
 }
@@ -1178,7 +1178,7 @@ static int act_open_rpl(struct t3cdev *tdev, struct sk_buff *skb, void *ctx)
 		release_tid(ep->com.tdev, GET_TID(rpl), NULL);
 	cxgb3_free_atid(ep->com.tdev, ep->atid);
 	dst_release(ep->dst);
-	l2t_release(L2DATA(ep->com.tdev), ep->l2t);
+	l2t_release(ep->com.tdev, ep->l2t);
 	put_ep(&ep->com);
 	return CPL_RET_BUF_DONE;
 }
@@ -1377,7 +1377,7 @@ static int pass_accept_req(struct t3cdev *tdev, struct sk_buff *skb, void *ctx)
 	if (!child_ep) {
 		printk(KERN_ERR MOD "%s - failed to allocate ep entry!\n",
 		       __func__);
-		l2t_release(L2DATA(tdev), l2t);
+		l2t_release(tdev, l2t);
 		dst_release(dst);
 		goto reject;
 	}
@@ -1956,7 +1956,7 @@ int iwch_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 	if (!err)
 		goto out;
 
-	l2t_release(L2DATA(h->rdev.t3cdev_p), ep->l2t);
+	l2t_release(h->rdev.t3cdev_p, ep->l2t);
 fail4:
 	dst_release(ep->dst);
 fail3:
@@ -2127,7 +2127,7 @@ int iwch_ep_redirect(void *ctx, struct dst_entry *old, struct dst_entry *new,
 	PDBG("%s ep %p redirect to dst %p l2t %p\n", __func__, ep, new,
 	     l2t);
 	dst_hold(new);
-	l2t_release(L2DATA(ep->com.tdev), ep->l2t);
+	l2t_release(ep->com.tdev, ep->l2t);
 	ep->l2t = l2t;
 	dst_release(old);
 	ep->dst = new;
diff --git a/drivers/media/video/omap/omap_vout.c b/drivers/media/video/omap/omap_vout.c
index b5ef36222440..b3a5ecdb33ac 100644
--- a/drivers/media/video/omap/omap_vout.c
+++ b/drivers/media/video/omap/omap_vout.c
@@ -2194,19 +2194,6 @@ static int __init omap_vout_probe(struct platform_device *pdev)
 					"'%s' Display already enabled\n",
 					def_display->name);
 			}
-			/* set the update mode */
-			if (def_display->caps &
-					OMAP_DSS_DISPLAY_CAP_MANUAL_UPDATE) {
-				if (dssdrv->enable_te)
-					dssdrv->enable_te(def_display, 0);
-				if (dssdrv->set_update_mode)
-					dssdrv->set_update_mode(def_display,
-							OMAP_DSS_UPDATE_MANUAL);
-			} else {
-				if (dssdrv->set_update_mode)
-					dssdrv->set_update_mode(def_display,
-							OMAP_DSS_UPDATE_AUTO);
-			}
 		}
 	}
 
diff --git a/drivers/media/video/omap3isp/ispccdc.c b/drivers/media/video/omap3isp/ispccdc.c
index 9d3459de04b2..80796eb0c53e 100644
--- a/drivers/media/video/omap3isp/ispccdc.c
+++ b/drivers/media/video/omap3isp/ispccdc.c
@@ -31,6 +31,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
 #include <media/v4l2-event.h>
 
 #include "isp.h"
diff --git a/drivers/media/video/uvc/uvc_driver.c b/drivers/media/video/uvc/uvc_driver.c
index d29f9c2d0854..e4100b1f68df 100644
--- a/drivers/media/video/uvc/uvc_driver.c
+++ b/drivers/media/video/uvc/uvc_driver.c
@@ -1961,7 +1961,7 @@ static int __uvc_resume(struct usb_interface *intf, int reset)
 
 	list_for_each_entry(stream, &dev->streams, list) {
 		if (stream->intf == intf)
-			return uvc_video_resume(stream);
+			return uvc_video_resume(stream, reset);
 	}
 
 	uvc_trace(UVC_TRACE_SUSPEND, "Resume: video streaming USB interface "
diff --git a/drivers/media/video/uvc/uvc_entity.c b/drivers/media/video/uvc/uvc_entity.c
index 48fea373c25a..29e239911d0e 100644
--- a/drivers/media/video/uvc/uvc_entity.c
+++ b/drivers/media/video/uvc/uvc_entity.c
@@ -49,7 +49,7 @@ static int uvc_mc_register_entity(struct uvc_video_chain *chain,
 		if (remote == NULL)
 			return -EINVAL;
 
-		source = (UVC_ENTITY_TYPE(remote) != UVC_TT_STREAMING)
+		source = (UVC_ENTITY_TYPE(remote) == UVC_TT_STREAMING)
 		       ? (remote->vdev ? &remote->vdev->entity : NULL)
 		       : &remote->subdev.entity;
 		if (source == NULL)
diff --git a/drivers/media/video/uvc/uvc_video.c b/drivers/media/video/uvc/uvc_video.c
index 8244167c8915..ffd1158628b6 100644
--- a/drivers/media/video/uvc/uvc_video.c
+++ b/drivers/media/video/uvc/uvc_video.c
@@ -1104,10 +1104,18 @@ int uvc_video_suspend(struct uvc_streaming *stream)
  * buffers, making sure userspace applications are notified of the problem
  * instead of waiting forever.
  */
-int uvc_video_resume(struct uvc_streaming *stream)
+int uvc_video_resume(struct uvc_streaming *stream, int reset)
 {
 	int ret;
 
+	/* If the bus has been reset on resume, set the alternate setting to 0.
+	 * This should be the default value, but some devices crash or otherwise
+	 * misbehave if they don't receive a SET_INTERFACE request before any
+	 * other video control request.
+	 */
+	if (reset)
+		usb_set_interface(stream->dev->udev, stream->intfnum, 0);
+
 	stream->frozen = 0;
 
 	ret = uvc_commit_video(stream, &stream->ctrl);
diff --git a/drivers/media/video/uvc/uvcvideo.h b/drivers/media/video/uvc/uvcvideo.h
index df32a43ca86a..cbdd49bf8b67 100644
--- a/drivers/media/video/uvc/uvcvideo.h
+++ b/drivers/media/video/uvc/uvcvideo.h
@@ -638,7 +638,7 @@ extern void uvc_mc_cleanup_entity(struct uvc_entity *entity);
 /* Video */
 extern int uvc_video_init(struct uvc_streaming *stream);
 extern int uvc_video_suspend(struct uvc_streaming *stream);
-extern int uvc_video_resume(struct uvc_streaming *stream);
+extern int uvc_video_resume(struct uvc_streaming *stream, int reset);
 extern int uvc_video_enable(struct uvc_streaming *stream, int enable);
 extern int uvc_probe_video(struct uvc_streaming *stream,
 		struct uvc_streaming_control *probe);
diff --git a/drivers/media/video/v4l2-dev.c b/drivers/media/video/v4l2-dev.c
index 06f14008b346..d72156517726 100644
--- a/drivers/media/video/v4l2-dev.c
+++ b/drivers/media/video/v4l2-dev.c
@@ -173,6 +173,17 @@ static void v4l2_device_release(struct device *cd)
 		media_device_unregister_entity(&vdev->entity);
 #endif
 
+	/* Do not call v4l2_device_put if there is no release callback set.
+	 * Drivers that have no v4l2_device release callback might free the
+	 * v4l2_dev instance in the video_device release callback below, so we
+	 * must perform this check here.
+	 *
+	 * TODO: In the long run all drivers that use v4l2_device should use the
+	 * v4l2_device release callback. This check will then be unnecessary.
+	 */
+	if (v4l2_dev->release == NULL)
+		v4l2_dev = NULL;
+
 	/* Release video_device and perform other
 	   cleanups as needed. */
 	vdev->release(vdev);
diff --git a/drivers/media/video/v4l2-device.c b/drivers/media/video/v4l2-device.c
index c72856c41434..e6a2c3b302d4 100644
--- a/drivers/media/video/v4l2-device.c
+++ b/drivers/media/video/v4l2-device.c
@@ -38,6 +38,7 @@ int v4l2_device_register(struct device *dev, struct v4l2_device *v4l2_dev)
 	mutex_init(&v4l2_dev->ioctl_lock);
 	v4l2_prio_init(&v4l2_dev->prio);
 	kref_init(&v4l2_dev->ref);
+	get_device(dev);
 	v4l2_dev->dev = dev;
 	if (dev == NULL) {
 		/* If dev == NULL, then name must be filled in by the caller */
@@ -93,6 +94,7 @@ void v4l2_device_disconnect(struct v4l2_device *v4l2_dev)
 
 	if (dev_get_drvdata(v4l2_dev->dev) == v4l2_dev)
 		dev_set_drvdata(v4l2_dev->dev, NULL);
+	put_device(v4l2_dev->dev);
 	v4l2_dev->dev = NULL;
 }
 EXPORT_SYMBOL_GPL(v4l2_device_disconnect);
diff --git a/drivers/mfd/jz4740-adc.c b/drivers/mfd/jz4740-adc.c
index 21131c7b0f1e..563654c9b19e 100644
--- a/drivers/mfd/jz4740-adc.c
+++ b/drivers/mfd/jz4740-adc.c
@@ -273,7 +273,7 @@ static int __devinit jz4740_adc_probe(struct platform_device *pdev)
 	ct->regs.ack = JZ_REG_ADC_STATUS;
 	ct->chip.irq_mask = irq_gc_mask_set_bit;
 	ct->chip.irq_unmask = irq_gc_mask_clr_bit;
-	ct->chip.irq_ack = irq_gc_ack;
+	ct->chip.irq_ack = irq_gc_ack_set_bit;
 
 	irq_setup_generic_chip(gc, IRQ_MSK(5), 0, 0, IRQ_NOPROBE | IRQ_LEVEL);
 
diff --git a/drivers/misc/lis3lv02d/lis3lv02d.c b/drivers/misc/lis3lv02d/lis3lv02d.c
index b928bc14e97b..8b51cd62d067 100644
--- a/drivers/misc/lis3lv02d/lis3lv02d.c
+++ b/drivers/misc/lis3lv02d/lis3lv02d.c
@@ -375,12 +375,14 @@ void lis3lv02d_poweron(struct lis3lv02d *lis3)
 	 *      both have been read. So the value read will always be correct.
 	 * Set BOOT bit to refresh factory tuning values.
 	 */
-	lis3->read(lis3, CTRL_REG2, &reg);
-	if (lis3->whoami ==  WAI_12B)
-		reg |= CTRL2_BDU | CTRL2_BOOT;
-	else
-		reg |= CTRL2_BOOT_8B;
-	lis3->write(lis3, CTRL_REG2, reg);
+	if (lis3->pdata) {
+		lis3->read(lis3, CTRL_REG2, &reg);
+		if (lis3->whoami ==  WAI_12B)
+			reg |= CTRL2_BDU | CTRL2_BOOT;
+		else
+			reg |= CTRL2_BOOT_8B;
+		lis3->write(lis3, CTRL_REG2, reg);
+	}
 
 	/* LIS3 power on delay is quite long */
 	msleep(lis3->pwron_delay / lis3lv02d_get_odr());
diff --git a/drivers/net/bnx2x/bnx2x_dcb.c b/drivers/net/bnx2x/bnx2x_dcb.c
index a1e004a82f7a..0b4acf67e0c6 100644
--- a/drivers/net/bnx2x/bnx2x_dcb.c
+++ b/drivers/net/bnx2x/bnx2x_dcb.c
@@ -2120,6 +2120,7 @@ static u8 bnx2x_dcbnl_get_cap(struct net_device *netdev, int capid, u8 *cap)
 			break;
 		case DCB_CAP_ATTR_DCBX:
 			*cap = BNX2X_DCBX_CAPS;
+			break;
 		default:
 			rval = -EINVAL;
 			break;
diff --git a/drivers/net/bnx2x/bnx2x_main.c b/drivers/net/bnx2x/bnx2x_main.c
index c027e9341a1a..15f800085bb2 100644
--- a/drivers/net/bnx2x/bnx2x_main.c
+++ b/drivers/net/bnx2x/bnx2x_main.c
@@ -4943,7 +4943,7 @@ static void bnx2x_init_def_sb(struct bnx2x *bp)
 	int igu_seg_id;
 	int port = BP_PORT(bp);
 	int func = BP_FUNC(bp);
-	int reg_offset;
+	int reg_offset, reg_offset_en5;
 	u64 section;
 	int index;
 	struct hc_sp_status_block_data sp_sb_data;
@@ -4966,6 +4966,8 @@ static void bnx2x_init_def_sb(struct bnx2x *bp)
 
 	reg_offset = (port ? MISC_REG_AEU_ENABLE1_FUNC_1_OUT_0 :
 			     MISC_REG_AEU_ENABLE1_FUNC_0_OUT_0);
+	reg_offset_en5 = (port ? MISC_REG_AEU_ENABLE5_FUNC_1_OUT_0 :
+				 MISC_REG_AEU_ENABLE5_FUNC_0_OUT_0);
 	for (index = 0; index < MAX_DYNAMIC_ATTN_GRPS; index++) {
 		int sindex;
 		/* take care of sig[0]..sig[4] */
@@ -4980,7 +4982,7 @@ static void bnx2x_init_def_sb(struct bnx2x *bp)
 			 * and not 16 between the different groups
 			 */
 			bp->attn_group[index].sig[4] = REG_RD(bp,
-					reg_offset + 0x10 + 0x4*index);
+					reg_offset_en5 + 0x4*index);
 		else
 			bp->attn_group[index].sig[4] = 0;
 	}
@@ -7625,8 +7627,11 @@ u32 bnx2x_send_unload_req(struct bnx2x *bp, int unload_mode)
 		u32 emac_base = port ? GRCBASE_EMAC1 : GRCBASE_EMAC0;
 		u8 *mac_addr = bp->dev->dev_addr;
 		u32 val;
+		u16 pmc;
+
 		/* The mac address is written to entries 1-4 to
-		   preserve entry 0 which is used by the PMF */
+		 * preserve entry 0 which is used by the PMF
+		 */
 		u8 entry = (BP_VN(bp) + 1)*8;
 
 		val = (mac_addr[0] << 8) | mac_addr[1];
@@ -7636,6 +7641,11 @@ u32 bnx2x_send_unload_req(struct bnx2x *bp, int unload_mode)
 		      (mac_addr[4] << 8) | mac_addr[5];
 		EMAC_WR(bp, EMAC_REG_EMAC_MAC_MATCH + entry + 4, val);
 
+		/* Enable the PME and clear the status */
+		pci_read_config_word(bp->pdev, bp->pm_cap + PCI_PM_CTRL, &pmc);
+		pmc |= PCI_PM_CTRL_PME_ENABLE | PCI_PM_CTRL_PME_STATUS;
+		pci_write_config_word(bp->pdev, bp->pm_cap + PCI_PM_CTRL, pmc);
+
 		reset_code = DRV_MSG_CODE_UNLOAD_REQ_WOL_EN;
 
 	} else
diff --git a/drivers/net/bnx2x/bnx2x_reg.h b/drivers/net/bnx2x/bnx2x_reg.h
index 750e8445dac4..fc7bd0f23c0b 100644
--- a/drivers/net/bnx2x/bnx2x_reg.h
+++ b/drivers/net/bnx2x/bnx2x_reg.h
@@ -1384,6 +1384,18 @@
    Latched ump_tx_parity; [31] MCP Latched scpad_parity; */
 #define MISC_REG_AEU_ENABLE4_PXP_0				 0xa108
 #define MISC_REG_AEU_ENABLE4_PXP_1				 0xa1a8
+/* [RW 32] fifth 32b for enabling the output for function 0 output0. Mapped
+ * as follows: [0] PGLUE config_space; [1] PGLUE misc_flr; [2] PGLUE B RBC
+ * attention [3] PGLUE B RBC parity; [4] ATC attention; [5] ATC parity; [6]
+ * mstat0 attention; [7] mstat0 parity; [8] mstat1 attention; [9] mstat1
+ * parity; [31-10] Reserved; */
+#define MISC_REG_AEU_ENABLE5_FUNC_0_OUT_0			 0xa688
+/* [RW 32] Fifth 32b for enabling the output for function 1 output0. Mapped
+ * as follows: [0] PGLUE config_space; [1] PGLUE misc_flr; [2] PGLUE B RBC
+ * attention [3] PGLUE B RBC parity; [4] ATC attention; [5] ATC parity; [6]
+ * mstat0 attention; [7] mstat0 parity; [8] mstat1 attention; [9] mstat1
+ * parity; [31-10] Reserved; */
+#define MISC_REG_AEU_ENABLE5_FUNC_1_OUT_0			 0xa6b0
 /* [RW 1] set/clr general attention 0; this will set/clr bit 94 in the aeu
    128 bit vector */
 #define MISC_REG_AEU_GENERAL_ATTN_0				 0xa000
diff --git a/drivers/net/bonding/bond_3ad.c b/drivers/net/bonding/bond_3ad.c
index a047eb973e3b..47b928ed08f8 100644
--- a/drivers/net/bonding/bond_3ad.c
+++ b/drivers/net/bonding/bond_3ad.c
@@ -2168,7 +2168,8 @@ void bond_3ad_state_machine_handler(struct work_struct *work)
 	}
 
 re_arm:
-	queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks);
+	if (!bond->kill_timers)
+		queue_delayed_work(bond->wq, &bond->ad_work, ad_delta_in_ticks);
 out:
 	read_unlock(&bond->lock);
 }
diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c
index 7f8b20a34ee3..d4fbd2e62616 100644
--- a/drivers/net/bonding/bond_alb.c
+++ b/drivers/net/bonding/bond_alb.c
@@ -1440,7 +1440,8 @@ void bond_alb_monitor(struct work_struct *work)
 	}
 
 re_arm:
-	queue_delayed_work(bond->wq, &bond->alb_work, alb_delta_in_ticks);
+	if (!bond->kill_timers)
+		queue_delayed_work(bond->wq, &bond->alb_work, alb_delta_in_ticks);
 out:
 	read_unlock(&bond->lock);
 }
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 43f2ea541088..6d79b78cfc75 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -777,6 +777,9 @@ static void bond_resend_igmp_join_requests(struct bonding *bond)
 
 	read_lock(&bond->lock);
 
+	if (bond->kill_timers)
+		goto out;
+
 	/* rejoin all groups on bond device */
 	__bond_resend_igmp_join_requests(bond->dev);
 
@@ -790,9 +793,9 @@ static void bond_resend_igmp_join_requests(struct bonding *bond)
 			__bond_resend_igmp_join_requests(vlan_dev);
 	}
 
-	if (--bond->igmp_retrans > 0)
+	if ((--bond->igmp_retrans > 0) && !bond->kill_timers)
 		queue_delayed_work(bond->wq, &bond->mcast_work, HZ/5);
-
+out:
 	read_unlock(&bond->lock);
 }
 
@@ -2538,7 +2541,7 @@ void bond_mii_monitor(struct work_struct *work)
 	}
 
 re_arm:
-	if (bond->params.miimon)
+	if (bond->params.miimon && !bond->kill_timers)
 		queue_delayed_work(bond->wq, &bond->mii_work,
 				   msecs_to_jiffies(bond->params.miimon));
 out:
@@ -2886,7 +2889,7 @@ void bond_loadbalance_arp_mon(struct work_struct *work)
 	}
 
 re_arm:
-	if (bond->params.arp_interval)
+	if (bond->params.arp_interval && !bond->kill_timers)
 		queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
 out:
 	read_unlock(&bond->lock);
@@ -3154,7 +3157,7 @@ void bond_activebackup_arp_mon(struct work_struct *work)
 	bond_ab_arp_probe(bond);
 
 re_arm:
-	if (bond->params.arp_interval)
+	if (bond->params.arp_interval && !bond->kill_timers)
 		queue_delayed_work(bond->wq, &bond->arp_work, delta_in_ticks);
 out:
 	read_unlock(&bond->lock);
diff --git a/drivers/net/cxgb3/cxgb3_offload.c b/drivers/net/cxgb3/cxgb3_offload.c
index 805076c54f1b..da5a5d9b8aff 100644
--- a/drivers/net/cxgb3/cxgb3_offload.c
+++ b/drivers/net/cxgb3/cxgb3_offload.c
@@ -1146,12 +1146,14 @@ static void cxgb_redirect(struct dst_entry *old, struct dst_entry *new)
 		if (te && te->ctx && te->client && te->client->redirect) {
 			update_tcb = te->client->redirect(te->ctx, old, new, e);
 			if (update_tcb) {
+				rcu_read_lock();
 				l2t_hold(L2DATA(tdev), e);
+				rcu_read_unlock();
 				set_l2t_ix(tdev, tid, e);
 			}
 		}
 	}
-	l2t_release(L2DATA(tdev), e);
+	l2t_release(tdev, e);
 }
 
 /*
@@ -1264,7 +1266,7 @@ int cxgb3_offload_activate(struct adapter *adapter)
 		goto out_free;
 
 	err = -ENOMEM;
-	L2DATA(dev) = t3_init_l2t(l2t_capacity);
+	RCU_INIT_POINTER(dev->l2opt, t3_init_l2t(l2t_capacity));
 	if (!L2DATA(dev))
 		goto out_free;
 
@@ -1298,16 +1300,24 @@ int cxgb3_offload_activate(struct adapter *adapter)
 
 out_free_l2t:
 	t3_free_l2t(L2DATA(dev));
-	L2DATA(dev) = NULL;
+	rcu_assign_pointer(dev->l2opt, NULL);
 out_free:
 	kfree(t);
 	return err;
 }
 
+static void clean_l2_data(struct rcu_head *head)
+{
+	struct l2t_data *d = container_of(head, struct l2t_data, rcu_head);
+	t3_free_l2t(d);
+}
+
+
 void cxgb3_offload_deactivate(struct adapter *adapter)
 {
 	struct t3cdev *tdev = &adapter->tdev;
 	struct t3c_data *t = T3C_DATA(tdev);
+	struct l2t_data *d;
 
 	remove_adapter(adapter);
 	if (list_empty(&adapter_list))
@@ -1315,8 +1325,11 @@ void cxgb3_offload_deactivate(struct adapter *adapter)
 
 	free_tid_maps(&t->tid_maps);
 	T3C_DATA(tdev) = NULL;
-	t3_free_l2t(L2DATA(tdev));
-	L2DATA(tdev) = NULL;
+	rcu_read_lock();
+	d = L2DATA(tdev);
+	rcu_read_unlock();
+	rcu_assign_pointer(tdev->l2opt, NULL);
+	call_rcu(&d->rcu_head, clean_l2_data);
 	if (t->nofail_skb)
 		kfree_skb(t->nofail_skb);
 	kfree(t);
diff --git a/drivers/net/cxgb3/l2t.c b/drivers/net/cxgb3/l2t.c
index f452c4003253..41540978a173 100644
--- a/drivers/net/cxgb3/l2t.c
+++ b/drivers/net/cxgb3/l2t.c
@@ -300,14 +300,21 @@ static inline void reuse_entry(struct l2t_entry *e, struct neighbour *neigh)
 struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct neighbour *neigh,
 			     struct net_device *dev)
 {
-	struct l2t_entry *e;
-	struct l2t_data *d = L2DATA(cdev);
+	struct l2t_entry *e = NULL;
+	struct l2t_data *d;
+	int hash;
 	u32 addr = *(u32 *) neigh->primary_key;
 	int ifidx = neigh->dev->ifindex;
-	int hash = arp_hash(addr, ifidx, d);
 	struct port_info *p = netdev_priv(dev);
 	int smt_idx = p->port_id;
 
+	rcu_read_lock();
+	d = L2DATA(cdev);
+	if (!d)
+		goto done_rcu;
+
+	hash = arp_hash(addr, ifidx, d);
+
 	write_lock_bh(&d->lock);
 	for (e = d->l2tab[hash].first; e; e = e->next)
 		if (e->addr == addr && e->ifindex == ifidx &&
@@ -338,6 +345,8 @@ struct l2t_entry *t3_l2t_get(struct t3cdev *cdev, struct neighbour *neigh,
 	}
 done:
 	write_unlock_bh(&d->lock);
+done_rcu:
+	rcu_read_unlock();
 	return e;
 }
 
diff --git a/drivers/net/cxgb3/l2t.h b/drivers/net/cxgb3/l2t.h
index 7a12d52ed4fc..c5f54796e2cb 100644
--- a/drivers/net/cxgb3/l2t.h
+++ b/drivers/net/cxgb3/l2t.h
@@ -76,6 +76,7 @@ struct l2t_data {
 	atomic_t nfree;		/* number of free entries */
 	rwlock_t lock;
 	struct l2t_entry l2tab[0];
+	struct rcu_head rcu_head;	/* to handle rcu cleanup */
 };
 
 typedef void (*arp_failure_handler_func)(struct t3cdev * dev,
@@ -99,7 +100,7 @@ static inline void set_arp_failure_handler(struct sk_buff *skb,
 /*
  * Getting to the L2 data from an offload device.
  */
-#define L2DATA(dev) ((dev)->l2opt)
+#define L2DATA(cdev) (rcu_dereference((cdev)->l2opt))
 
 #define W_TCB_L2T_IX    0
 #define S_TCB_L2T_IX    7
@@ -126,15 +127,22 @@ static inline int l2t_send(struct t3cdev *dev, struct sk_buff *skb,
 	return t3_l2t_send_slow(dev, skb, e);
 }
 
-static inline void l2t_release(struct l2t_data *d, struct l2t_entry *e)
+static inline void l2t_release(struct t3cdev *t, struct l2t_entry *e)
 {
-	if (atomic_dec_and_test(&e->refcnt))
+	struct l2t_data *d;
+
+	rcu_read_lock();
+	d = L2DATA(t);
+
+	if (atomic_dec_and_test(&e->refcnt) && d)
 		t3_l2e_free(d, e);
+
+	rcu_read_unlock();
 }
 
 static inline void l2t_hold(struct l2t_data *d, struct l2t_entry *e)
 {
-	if (atomic_add_return(1, &e->refcnt) == 1)	/* 0 -> 1 transition */
+	if (d && atomic_add_return(1, &e->refcnt) == 1)	/* 0 -> 1 transition */
 		atomic_dec(&d->nfree);
 }
 
diff --git a/drivers/net/cxgb4/cxgb4_main.c b/drivers/net/cxgb4/cxgb4_main.c
index c9957b7f17b5..b4efa292fd6f 100644
--- a/drivers/net/cxgb4/cxgb4_main.c
+++ b/drivers/net/cxgb4/cxgb4_main.c
@@ -3712,6 +3712,9 @@ static int __devinit init_one(struct pci_dev *pdev,
 		setup_debugfs(adapter);
 	}
 
+	/* PCIe EEH recovery on powerpc platforms needs fundamental reset */
+	pdev->needs_freset = 1;
+
 	if (is_offload(adapter))
 		attach_ulds(adapter);
 
diff --git a/drivers/net/ibmveth.c b/drivers/net/ibmveth.c
index 8dd5fccef725..d393f1e764ed 100644
--- a/drivers/net/ibmveth.c
+++ b/drivers/net/ibmveth.c
@@ -636,8 +636,8 @@ static int ibmveth_open(struct net_device *netdev)
 		netdev_err(netdev, "unable to request irq 0x%x, rc %d\n",
 			   netdev->irq, rc);
 		do {
-			rc = h_free_logical_lan(adapter->vdev->unit_address);
-		} while (H_IS_LONG_BUSY(rc) || (rc == H_BUSY));
+			lpar_rc = h_free_logical_lan(adapter->vdev->unit_address);
+		} while (H_IS_LONG_BUSY(lpar_rc) || (lpar_rc == H_BUSY));
 
 		goto err_out;
 	}
diff --git a/drivers/net/pch_gbe/pch_gbe_main.c b/drivers/net/pch_gbe/pch_gbe_main.c
index 567ff10889be..b8b4ba27b0e7 100644
--- a/drivers/net/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/pch_gbe/pch_gbe_main.c
@@ -1199,6 +1199,8 @@ static irqreturn_t pch_gbe_intr(int irq, void *data)
 			iowrite32((int_en & ~PCH_GBE_INT_RX_FIFO_ERR),
 				  &hw->reg->INT_EN);
 			pch_gbe_stop_receive(adapter);
+			int_st |= ioread32(&hw->reg->INT_ST);
+			int_st = int_st & ioread32(&hw->reg->INT_EN);
 		}
 	if (int_st & PCH_GBE_INT_RX_DMA_ERR)
 		adapter->stats.intr_rx_dma_err_count++;
@@ -1218,14 +1220,11 @@ static irqreturn_t pch_gbe_intr(int irq, void *data)
 			/* Set Pause packet */
 			pch_gbe_mac_set_pause_packet(hw);
 		}
-		if ((int_en & (PCH_GBE_INT_RX_DMA_CMPLT | PCH_GBE_INT_TX_CMPLT))
-		    == 0) {
-			return IRQ_HANDLED;
-		}
 	}
 
 	/* When request status is Receive interruption */
-	if ((int_st & (PCH_GBE_INT_RX_DMA_CMPLT | PCH_GBE_INT_TX_CMPLT))) {
+	if ((int_st & (PCH_GBE_INT_RX_DMA_CMPLT | PCH_GBE_INT_TX_CMPLT)) ||
+	    (adapter->rx_stop_flag == true)) {
 		if (likely(napi_schedule_prep(&adapter->napi))) {
 			/* Enable only Rx Descriptor empty */
 			atomic_inc(&adapter->irq_sem);
@@ -1385,7 +1384,7 @@ pch_gbe_clean_tx(struct pch_gbe_adapter *adapter,
 	struct sk_buff *skb;
 	unsigned int i;
 	unsigned int cleaned_count = 0;
-	bool cleaned = false;
+	bool cleaned = true;
 
 	pr_debug("next_to_clean : %d\n", tx_ring->next_to_clean);
 
@@ -1396,7 +1395,6 @@ pch_gbe_clean_tx(struct pch_gbe_adapter *adapter,
 
 	while ((tx_desc->gbec_status & DSC_INIT16) == 0x0000) {
 		pr_debug("gbec_status:0x%04x\n", tx_desc->gbec_status);
-		cleaned = true;
 		buffer_info = &tx_ring->buffer_info[i];
 		skb = buffer_info->skb;
 
@@ -1439,8 +1437,10 @@ pch_gbe_clean_tx(struct pch_gbe_adapter *adapter,
 		tx_desc = PCH_GBE_TX_DESC(*tx_ring, i);
 
 		/* weight of a sort for tx, to avoid endless transmit cleanup */
-		if (cleaned_count++ == PCH_GBE_TX_WEIGHT)
+		if (cleaned_count++ == PCH_GBE_TX_WEIGHT) {
+			cleaned = false;
 			break;
+		}
 	}
 	pr_debug("called pch_gbe_unmap_and_free_tx_resource() %d count\n",
 		 cleaned_count);
@@ -2168,7 +2168,6 @@ static int pch_gbe_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct pch_gbe_adapter *adapter =
 	    container_of(napi, struct pch_gbe_adapter, napi);
-	struct net_device *netdev = adapter->netdev;
 	int work_done = 0;
 	bool poll_end_flag = false;
 	bool cleaned = false;
@@ -2176,33 +2175,32 @@ static int pch_gbe_napi_poll(struct napi_struct *napi, int budget)
 
 	pr_debug("budget : %d\n", budget);
 
-	/* Keep link state information with original netdev */
-	if (!netif_carrier_ok(netdev)) {
+	pch_gbe_clean_rx(adapter, adapter->rx_ring, &work_done, budget);
+	cleaned = pch_gbe_clean_tx(adapter, adapter->tx_ring);
+
+	if (!cleaned)
+		work_done = budget;
+	/* If no Tx and not enough Rx work done,
+	 * exit the polling mode
+	 */
+	if (work_done < budget)
 		poll_end_flag = true;
-	} else {
-		pch_gbe_clean_rx(adapter, adapter->rx_ring, &work_done, budget);
+
+	if (poll_end_flag) {
+		napi_complete(napi);
+		if (adapter->rx_stop_flag) {
+			adapter->rx_stop_flag = false;
+			pch_gbe_start_receive(&adapter->hw);
+		}
+		pch_gbe_irq_enable(adapter);
+	} else
 		if (adapter->rx_stop_flag) {
 			adapter->rx_stop_flag = false;
 			pch_gbe_start_receive(&adapter->hw);
 			int_en = ioread32(&adapter->hw.reg->INT_EN);
 			iowrite32((int_en | PCH_GBE_INT_RX_FIFO_ERR),
-					&adapter->hw.reg->INT_EN);
+				&adapter->hw.reg->INT_EN);
 		}
-		cleaned = pch_gbe_clean_tx(adapter, adapter->tx_ring);
-
-		if (cleaned)
-			work_done = budget;
-		/* If no Tx and not enough Rx work done,
-		 * exit the polling mode
-		 */
-		if ((work_done < budget) || !netif_running(netdev))
-			poll_end_flag = true;
-	}
-
-	if (poll_end_flag) {
-		napi_complete(napi);
-		pch_gbe_irq_enable(adapter);
-	}
 
 	pr_debug("poll_end_flag : %d  work_done : %d  budget : %d\n",
 		 poll_end_flag, work_done, budget);
diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index cb6e0b486b1e..edd7304773eb 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -589,7 +589,7 @@ static void decode_rxts(struct dp83640_private *dp83640,
 	prune_rx_ts(dp83640);
 
 	if (list_empty(&dp83640->rxpool)) {
-		pr_warning("dp83640: rx timestamp pool is empty\n");
+		pr_debug("dp83640: rx timestamp pool is empty\n");
 		goto out;
 	}
 	rxts = list_first_entry(&dp83640->rxpool, struct rxts, list);
@@ -612,7 +612,7 @@ static void decode_txts(struct dp83640_private *dp83640,
 	skb = skb_dequeue(&dp83640->tx_queue);
 
 	if (!skb) {
-		pr_warning("dp83640: have timestamp but tx_queue empty\n");
+		pr_debug("dp83640: have timestamp but tx_queue empty\n");
 		return;
 	}
 	ns = phy2txts(phy_txts);
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_2p2_initvals.h b/drivers/net/wireless/ath/ath9k/ar9003_2p2_initvals.h
index 2339728a7306..3e69c631ebb4 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_2p2_initvals.h
+++ b/drivers/net/wireless/ath/ath9k/ar9003_2p2_initvals.h
@@ -1514,7 +1514,7 @@ static const u32 ar9300_2p2_mac_core[][2] = {
 	{0x00008258, 0x00000000},
 	{0x0000825c, 0x40000000},
 	{0x00008260, 0x00080922},
-	{0x00008264, 0x9bc00010},
+	{0x00008264, 0x9d400010},
 	{0x00008268, 0xffffffff},
 	{0x0000826c, 0x0000ffff},
 	{0x00008270, 0x00000000},
diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c
index 9a4850154fb2..4c21f8cbdeb5 100644
--- a/drivers/net/wireless/ath/ath9k/recv.c
+++ b/drivers/net/wireless/ath/ath9k/recv.c
@@ -205,14 +205,22 @@ static void ath_rx_remove_buffer(struct ath_softc *sc,
 
 static void ath_rx_edma_cleanup(struct ath_softc *sc)
 {
+	struct ath_hw *ah = sc->sc_ah;
+	struct ath_common *common = ath9k_hw_common(ah);
 	struct ath_buf *bf;
 
 	ath_rx_remove_buffer(sc, ATH9K_RX_QUEUE_LP);
 	ath_rx_remove_buffer(sc, ATH9K_RX_QUEUE_HP);
 
 	list_for_each_entry(bf, &sc->rx.rxbuf, list) {
-		if (bf->bf_mpdu)
+		if (bf->bf_mpdu) {
+			dma_unmap_single(sc->dev, bf->bf_buf_addr,
+					common->rx_bufsize,
+					DMA_BIDIRECTIONAL);
 			dev_kfree_skb_any(bf->bf_mpdu);
+			bf->bf_buf_addr = 0;
+			bf->bf_mpdu = NULL;
+		}
 	}
 
 	INIT_LIST_HEAD(&sc->rx.rxbuf);
diff --git a/drivers/net/wireless/iwlegacy/iwl-core.c b/drivers/net/wireless/iwlegacy/iwl-core.c
index 35cd2537e7fd..e5971fe9d169 100644
--- a/drivers/net/wireless/iwlegacy/iwl-core.c
+++ b/drivers/net/wireless/iwlegacy/iwl-core.c
@@ -937,7 +937,7 @@ void iwl_legacy_irq_handle_error(struct iwl_priv *priv)
 					&priv->contexts[IWL_RXON_CTX_BSS]);
 #endif
 
-	wake_up_interruptible(&priv->wait_command_queue);
+	wake_up(&priv->wait_command_queue);
 
 	/* Keep the restart process from trying to send host
 	 * commands by clearing the INIT status bit */
@@ -1746,7 +1746,7 @@ int iwl_legacy_force_reset(struct iwl_priv *priv, bool external)
 
 	/* Set the FW error flag -- cleared on iwl_down */
 	set_bit(STATUS_FW_ERROR, &priv->status);
-	wake_up_interruptible(&priv->wait_command_queue);
+	wake_up(&priv->wait_command_queue);
 	/*
 	 * Keep the restart process from trying to send host
 	 * commands by clearing the INIT status bit
diff --git a/drivers/net/wireless/iwlegacy/iwl-hcmd.c b/drivers/net/wireless/iwlegacy/iwl-hcmd.c
index 62b4b09122cb..ce1fc9feb61f 100644
--- a/drivers/net/wireless/iwlegacy/iwl-hcmd.c
+++ b/drivers/net/wireless/iwlegacy/iwl-hcmd.c
@@ -167,7 +167,7 @@ int iwl_legacy_send_cmd_sync(struct iwl_priv *priv, struct iwl_host_cmd *cmd)
 		goto out;
 	}
 
-	ret = wait_event_interruptible_timeout(priv->wait_command_queue,
+	ret = wait_event_timeout(priv->wait_command_queue,
 			!test_bit(STATUS_HCMD_ACTIVE, &priv->status),
 			HOST_COMPLETE_TIMEOUT);
 	if (!ret) {
diff --git a/drivers/net/wireless/iwlegacy/iwl-tx.c b/drivers/net/wireless/iwlegacy/iwl-tx.c
index 4fff995c6f3e..ef9e268bf8a0 100644
--- a/drivers/net/wireless/iwlegacy/iwl-tx.c
+++ b/drivers/net/wireless/iwlegacy/iwl-tx.c
@@ -625,6 +625,8 @@ iwl_legacy_tx_cmd_complete(struct iwl_priv *priv, struct iwl_rx_mem_buffer *rxb)
 	cmd = txq->cmd[cmd_index];
 	meta = &txq->meta[cmd_index];
 
+	txq->time_stamp = jiffies;
+
 	pci_unmap_single(priv->pci_dev,
 			 dma_unmap_addr(meta, mapping),
 			 dma_unmap_len(meta, len),
@@ -645,7 +647,7 @@ iwl_legacy_tx_cmd_complete(struct iwl_priv *priv, struct iwl_rx_mem_buffer *rxb)
 		clear_bit(STATUS_HCMD_ACTIVE, &priv->status);
 		IWL_DEBUG_INFO(priv, "Clearing HCMD_ACTIVE for command %s\n",
 			       iwl_legacy_get_cmd_string(cmd->hdr.cmd));
-		wake_up_interruptible(&priv->wait_command_queue);
+		wake_up(&priv->wait_command_queue);
 	}
 
 	/* Mark as unmapped */
diff --git a/drivers/net/wireless/iwlegacy/iwl3945-base.c b/drivers/net/wireless/iwlegacy/iwl3945-base.c
index 795826a014ed..66ee15629a76 100644
--- a/drivers/net/wireless/iwlegacy/iwl3945-base.c
+++ b/drivers/net/wireless/iwlegacy/iwl3945-base.c
@@ -841,7 +841,7 @@ static void iwl3945_rx_card_state_notif(struct iwl_priv *priv,
 		wiphy_rfkill_set_hw_state(priv->hw->wiphy,
 				test_bit(STATUS_RF_KILL_HW, &priv->status));
 	else
-		wake_up_interruptible(&priv->wait_command_queue);
+		wake_up(&priv->wait_command_queue);
 }
 
 /**
@@ -2269,7 +2269,7 @@ static void iwl3945_alive_start(struct iwl_priv *priv)
 	iwl3945_reg_txpower_periodic(priv);
 
 	IWL_DEBUG_INFO(priv, "ALIVE processing complete.\n");
-	wake_up_interruptible(&priv->wait_command_queue);
+	wake_up(&priv->wait_command_queue);
 
 	return;
 
@@ -2300,7 +2300,7 @@ static void __iwl3945_down(struct iwl_priv *priv)
 	iwl_legacy_clear_driver_stations(priv);
 
 	/* Unblock any waiting calls */
-	wake_up_interruptible_all(&priv->wait_command_queue);
+	wake_up_all(&priv->wait_command_queue);
 
 	/* Wipe out the EXIT_PENDING status bit if we are not actually
 	 * exiting the module */
@@ -2853,7 +2853,7 @@ static int iwl3945_mac_start(struct ieee80211_hw *hw)
 
 	/* Wait for START_ALIVE from ucode. Otherwise callbacks from
 	 * mac80211 will not be run successfully. */
-	ret = wait_event_interruptible_timeout(priv->wait_command_queue,
+	ret = wait_event_timeout(priv->wait_command_queue,
 			test_bit(STATUS_READY, &priv->status),
 			UCODE_READY_TIMEOUT);
 	if (!ret) {
diff --git a/drivers/net/wireless/iwlegacy/iwl4965-base.c b/drivers/net/wireless/iwlegacy/iwl4965-base.c
index 14334668034e..aa0c2539761e 100644
--- a/drivers/net/wireless/iwlegacy/iwl4965-base.c
+++ b/drivers/net/wireless/iwlegacy/iwl4965-base.c
@@ -576,7 +576,7 @@ static void iwl4965_rx_card_state_notif(struct iwl_priv *priv,
 		wiphy_rfkill_set_hw_state(priv->hw->wiphy,
 			test_bit(STATUS_RF_KILL_HW, &priv->status));
 	else
-		wake_up_interruptible(&priv->wait_command_queue);
+		wake_up(&priv->wait_command_queue);
 }
 
 /**
@@ -926,7 +926,7 @@ static void iwl4965_irq_tasklet(struct iwl_priv *priv)
 		handled |= CSR_INT_BIT_FH_TX;
 		/* Wake up uCode load routine, now that load is complete */
 		priv->ucode_write_complete = 1;
-		wake_up_interruptible(&priv->wait_command_queue);
+		wake_up(&priv->wait_command_queue);
 	}
 
 	if (inta & ~handled) {
@@ -1795,7 +1795,7 @@ static void iwl4965_alive_start(struct iwl_priv *priv)
 	iwl4965_rf_kill_ct_config(priv);
 
 	IWL_DEBUG_INFO(priv, "ALIVE processing complete.\n");
-	wake_up_interruptible(&priv->wait_command_queue);
+	wake_up(&priv->wait_command_queue);
 
 	iwl_legacy_power_update_mode(priv, true);
 	IWL_DEBUG_INFO(priv, "Updated power mode\n");
@@ -1828,7 +1828,7 @@ static void __iwl4965_down(struct iwl_priv *priv)
 	iwl_legacy_clear_driver_stations(priv);
 
 	/* Unblock any waiting calls */
-	wake_up_interruptible_all(&priv->wait_command_queue);
+	wake_up_all(&priv->wait_command_queue);
 
 	/* Wipe out the EXIT_PENDING status bit if we are not actually
 	 * exiting the module */
@@ -2266,7 +2266,7 @@ int iwl4965_mac_start(struct ieee80211_hw *hw)
 
 	/* Wait for START_ALIVE from Run Time ucode. Otherwise callbacks from
 	 * mac80211 will not be run successfully. */
-	ret = wait_event_interruptible_timeout(priv->wait_command_queue,
+	ret = wait_event_timeout(priv->wait_command_queue,
 			test_bit(STATUS_READY, &priv->status),
 			UCODE_READY_TIMEOUT);
 	if (!ret) {
diff --git a/drivers/net/wireless/iwlwifi/iwl-scan.c b/drivers/net/wireless/iwlwifi/iwl-scan.c
index dd6937e97055..77e528f5db88 100644
--- a/drivers/net/wireless/iwlwifi/iwl-scan.c
+++ b/drivers/net/wireless/iwlwifi/iwl-scan.c
@@ -405,31 +405,33 @@ int iwl_mac_hw_scan(struct ieee80211_hw *hw,
 
 	mutex_lock(&priv->mutex);
 
-	if (test_bit(STATUS_SCANNING, &priv->status) &&
-	    priv->scan_type != IWL_SCAN_NORMAL) {
-		IWL_DEBUG_SCAN(priv, "Scan already in progress.\n");
-		ret = -EAGAIN;
-		goto out_unlock;
-	}
-
-	/* mac80211 will only ask for one band at a time */
-	priv->scan_request = req;
-	priv->scan_vif = vif;
-
 	/*
 	 * If an internal scan is in progress, just set
 	 * up the scan_request as per above.
 	 */
 	if (priv->scan_type != IWL_SCAN_NORMAL) {
-		IWL_DEBUG_SCAN(priv, "SCAN request during internal scan\n");
+		IWL_DEBUG_SCAN(priv,
+			       "SCAN request during internal scan - defer\n");
+		priv->scan_request = req;
+		priv->scan_vif = vif;
 		ret = 0;
-	} else
+	} else {
+		priv->scan_request = req;
+		priv->scan_vif = vif;
+		/*
+		 * mac80211 will only ask for one band at a time
+		 * so using channels[0] here is ok
+		 */
 		ret = iwl_scan_initiate(priv, vif, IWL_SCAN_NORMAL,
 					req->channels[0]->band);
+		if (ret) {
+			priv->scan_request = NULL;
+			priv->scan_vif = NULL;
+		}
+	}
 
 	IWL_DEBUG_MAC80211(priv, "leave\n");
 
-out_unlock:
 	mutex_unlock(&priv->mutex);
 
 	return ret;
diff --git a/drivers/net/wireless/rtlwifi/usb.c b/drivers/net/wireless/rtlwifi/usb.c
index 8b1cef0ffde6..4bf3cf457ef0 100644
--- a/drivers/net/wireless/rtlwifi/usb.c
+++ b/drivers/net/wireless/rtlwifi/usb.c
@@ -863,6 +863,7 @@ static void _rtl_usb_tx_preprocess(struct ieee80211_hw *hw, struct sk_buff *skb,
 	u8 tid = 0;
 	u16 seq_number = 0;
 
+	memset(&tcb_desc, 0, sizeof(struct rtl_tcb_desc));
 	if (ieee80211_is_auth(fc)) {
 		RT_TRACE(rtlpriv, COMP_SEND, DBG_DMESG, ("MAC80211_LINKING\n"));
 		rtl_ips_nic_on(hw);
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 0ca86f9ec4ed..182562952c79 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -327,12 +327,12 @@ int xenvif_connect(struct xenvif *vif, unsigned long tx_ring_ref,
 	xenvif_get(vif);
 
 	rtnl_lock();
-	if (netif_running(vif->dev))
-		xenvif_up(vif);
 	if (!vif->can_sg && vif->dev->mtu > ETH_DATA_LEN)
 		dev_set_mtu(vif->dev, ETH_DATA_LEN);
 	netdev_update_features(vif->dev);
 	netif_carrier_on(vif->dev);
+	if (netif_running(vif->dev))
+		xenvif_up(vif);
 	rtnl_unlock();
 
 	return 0;
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 4e84fd4a4312..e9651f0a8817 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -77,7 +77,7 @@ unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE;
 unsigned long pci_hotplug_io_size  = DEFAULT_HOTPLUG_IO_SIZE;
 unsigned long pci_hotplug_mem_size = DEFAULT_HOTPLUG_MEM_SIZE;
 
-enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_SAFE;
+enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_TUNE_OFF;
 
 /*
  * The default CLS is used if arch didn't set CLS explicitly and not
@@ -3568,10 +3568,14 @@ static int __init pci_setup(char *str)
 				pci_hotplug_io_size = memparse(str + 9, &str);
 			} else if (!strncmp(str, "hpmemsize=", 10)) {
 				pci_hotplug_mem_size = memparse(str + 10, &str);
+			} else if (!strncmp(str, "pcie_bus_tune_off", 17)) {
+				pcie_bus_config = PCIE_BUS_TUNE_OFF;
 			} else if (!strncmp(str, "pcie_bus_safe", 13)) {
 				pcie_bus_config = PCIE_BUS_SAFE;
 			} else if (!strncmp(str, "pcie_bus_perf", 13)) {
 				pcie_bus_config = PCIE_BUS_PERFORMANCE;
+			} else if (!strncmp(str, "pcie_bus_peer2peer", 18)) {
+				pcie_bus_config = PCIE_BUS_PEER2PEER;
 			} else {
 				printk(KERN_ERR "PCI: Unknown option `%s'\n",
 						str);
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index f3f94a5c068f..6ab6bd3df4b2 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1458,12 +1458,24 @@ static int pcie_bus_configure_set(struct pci_dev *dev, void *data)
  */
 void pcie_bus_configure_settings(struct pci_bus *bus, u8 mpss)
 {
-	u8 smpss = mpss;
+	u8 smpss;
 
 	if (!pci_is_pcie(bus->self))
 		return;
 
+	if (pcie_bus_config == PCIE_BUS_TUNE_OFF)
+		return;
+
+	/* FIXME - Peer to peer DMA is possible, though the endpoint would need
+	 * to be aware to the MPS of the destination.  To work around this,
+	 * simply force the MPS of the entire system to the smallest possible.
+	 */
+	if (pcie_bus_config == PCIE_BUS_PEER2PEER)
+		smpss = 0;
+
 	if (pcie_bus_config == PCIE_BUS_SAFE) {
+		smpss = mpss;
+
 		pcie_find_smpss(bus->self, &smpss);
 		pci_walk_bus(bus, pcie_find_smpss, &smpss);
 	}
diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index cbde448f9947..eb3140ee821e 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -654,8 +654,8 @@ static struct io_subchannel_private console_priv;
 static int console_subchannel_in_use;
 
 /*
- * Use tpi to get a pending interrupt, call the interrupt handler and
- * return a pointer to the subchannel structure.
+ * Use cio_tpi to get a pending interrupt and call the interrupt handler.
+ * Return non-zero if an interrupt was processed, zero otherwise.
  */
 static int cio_tpi(void)
 {
@@ -667,6 +667,10 @@ static int cio_tpi(void)
 	tpi_info = (struct tpi_info *)&S390_lowcore.subchannel_id;
 	if (tpi(NULL) != 1)
 		return 0;
+	if (tpi_info->adapter_IO) {
+		do_adapter_IO(tpi_info->isc);
+		return 1;
+	}
 	irb = (struct irb *)&S390_lowcore.irb;
 	/* Store interrupt response block to lowcore. */
 	if (tsch(tpi_info->schid, irb) != 0)
diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index b7bd5b0cc7aa..3868ab2397c6 100644
--- a/drivers/scsi/3w-9xxx.c
+++ b/drivers/scsi/3w-9xxx.c
@@ -1800,10 +1800,12 @@ static int twa_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_
 	switch (retval) {
 	case SCSI_MLQUEUE_HOST_BUSY:
 		twa_free_request_id(tw_dev, request_id);
+		twa_unmap_scsi_data(tw_dev, request_id);
 		break;
 	case 1:
 		tw_dev->state[request_id] = TW_S_COMPLETED;
 		twa_free_request_id(tw_dev, request_id);
+		twa_unmap_scsi_data(tw_dev, request_id);
 		SCpnt->result = (DID_ERROR << 16);
 		done(SCpnt);
 		retval = 0;
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 8d9dae89f065..3878b7395081 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -837,6 +837,7 @@ config SCSI_ISCI
 	# (temporary): known alpha quality driver
 	depends on EXPERIMENTAL
 	select SCSI_SAS_LIBSAS
+	select SCSI_SAS_HOST_SMP
 	---help---
 	  This driver supports the 6Gb/s SAS capabilities of the storage
 	  control unit found in the Intel(R) C600 series chipset.
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index 3c08f5352b2d..6153a66a8a31 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -88,7 +88,7 @@ obj-$(CONFIG_SCSI_QLOGIC_FAS)	+= qlogicfas408.o	qlogicfas.o
 obj-$(CONFIG_PCMCIA_QLOGIC)	+= qlogicfas408.o
 obj-$(CONFIG_SCSI_QLOGIC_1280)	+= qla1280.o 
 obj-$(CONFIG_SCSI_QLA_FC)	+= qla2xxx/
-obj-$(CONFIG_SCSI_QLA_ISCSI)	+= qla4xxx/
+obj-$(CONFIG_SCSI_QLA_ISCSI)	+= libiscsi.o qla4xxx/
 obj-$(CONFIG_SCSI_LPFC)		+= lpfc/
 obj-$(CONFIG_SCSI_BFA_FC)	+= bfa/
 obj-$(CONFIG_SCSI_PAS16)	+= pas16.o
diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index e7d0d47b9185..e5f2d7d9002e 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -1283,6 +1283,8 @@ static int _aac_reset_adapter(struct aac_dev *aac, int forced)
 	kfree(aac->queues);
 	aac->queues = NULL;
 	free_irq(aac->pdev->irq, aac);
+	if (aac->msi)
+		pci_disable_msi(aac->pdev);
 	kfree(aac->fsa_dev);
 	aac->fsa_dev = NULL;
 	quirks = aac_get_driver_ident(index)->quirks;
diff --git a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
index bd22041e2789..f58644850333 100644
--- a/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
+++ b/drivers/scsi/cxgbi/cxgb3i/cxgb3i.c
@@ -913,7 +913,7 @@ static void l2t_put(struct cxgbi_sock *csk)
 	struct t3cdev *t3dev = (struct t3cdev *)csk->cdev->lldev;
 
 	if (csk->l2t) {
-		l2t_release(L2DATA(t3dev), csk->l2t);
+		l2t_release(t3dev, csk->l2t);
 		csk->l2t = NULL;
 		cxgbi_sock_put(csk);
 	}
diff --git a/drivers/scsi/libsas/sas_expander.c b/drivers/scsi/libsas/sas_expander.c
index f84084bba2f0..c9e3dc024bc3 100644
--- a/drivers/scsi/libsas/sas_expander.c
+++ b/drivers/scsi/libsas/sas_expander.c
@@ -1721,7 +1721,7 @@ static int sas_find_bcast_dev(struct domain_device *dev,
 	list_for_each_entry(ch, &ex->children, siblings) {
 		if (ch->dev_type == EDGE_DEV || ch->dev_type == FANOUT_DEV) {
 			res = sas_find_bcast_dev(ch, src_dev);
-			if (src_dev)
+			if (*src_dev)
 				return res;
 		}
 	}
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 646fc5263d50..8a7591f035e6 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -1507,8 +1507,8 @@ qla2x00_handle_dif_error(srb_t *sp, struct sts_entry_24xx *sts24)
 
 			if (k != blocks_done) {
 				qla_printk(KERN_WARNING, sp->fcport->vha->hw,
-				    "unexpected tag values tag:lba=%x:%lx)\n",
-				    e_ref_tag, lba_s);
+				    "unexpected tag values tag:lba=%x:%llx)\n",
+				    e_ref_tag, (unsigned long long)lba_s);
 				return 1;
 			}
 
diff --git a/drivers/spi/spi-fsl-spi.c b/drivers/spi/spi-fsl-spi.c
index d2407558773f..24cacff57786 100644
--- a/drivers/spi/spi-fsl-spi.c
+++ b/drivers/spi/spi-fsl-spi.c
@@ -825,6 +825,9 @@ static void fsl_spi_cpm_free(struct mpc8xxx_spi *mspi)
 {
 	struct device *dev = mspi->dev;
 
+	if (!(mspi->flags & SPI_CPM_MODE))
+		return;
+
 	dma_unmap_single(dev, mspi->dma_dummy_rx, SPI_MRBLR, DMA_FROM_DEVICE);
 	dma_unmap_single(dev, mspi->dma_dummy_tx, PAGE_SIZE, DMA_TO_DEVICE);
 	cpm_muram_free(cpm_muram_offset(mspi->tx_bd));
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 8ac6542aedcd..fa594d604aca 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -786,9 +786,11 @@ static int __devinit spi_imx_probe(struct platform_device *pdev)
 		int cs_gpio = of_get_named_gpio(np, "cs-gpios", i);
 		if (cs_gpio < 0)
 			cs_gpio = mxc_platform_info->chipselect[i];
+
+		spi_imx->chipselect[i] = cs_gpio;
 		if (cs_gpio < 0)
 			continue;
-		spi_imx->chipselect[i] = cs_gpio;
+
 		ret = gpio_request(spi_imx->chipselect[i], DRIVER_NAME);
 		if (ret) {
 			while (i > 0) {
diff --git a/drivers/spi/spi-topcliff-pch.c b/drivers/spi/spi-topcliff-pch.c
index 1d23f3831866..6a80749391db 100644
--- a/drivers/spi/spi-topcliff-pch.c
+++ b/drivers/spi/spi-topcliff-pch.c
@@ -50,6 +50,8 @@
 #define PCH_RX_THOLD		7
 #define PCH_RX_THOLD_MAX	15
 
+#define PCH_TX_THOLD		2
+
 #define PCH_MAX_BAUDRATE	5000000
 #define PCH_MAX_FIFO_DEPTH	16
 
@@ -58,6 +60,7 @@
 #define PCH_SLEEP_TIME		10
 
 #define SSN_LOW			0x02U
+#define SSN_HIGH		0x03U
 #define SSN_NO_CONTROL		0x00U
 #define PCH_MAX_CS		0xFF
 #define PCI_DEVICE_ID_GE_SPI	0x8816
@@ -316,16 +319,19 @@ static void pch_spi_handler_sub(struct pch_spi_data *data, u32 reg_spsr_val,
 
 	/* if transfer complete interrupt */
 	if (reg_spsr_val & SPSR_FI_BIT) {
-		if (tx_index < bpw_len)
+		if ((tx_index == bpw_len) && (rx_index == tx_index)) {
+			/* disable interrupts */
+			pch_spi_setclr_reg(data->master, PCH_SPCR, 0, PCH_ALL);
+
+			/* transfer is completed;
+			   inform pch_spi_process_messages */
+			data->transfer_complete = true;
+			data->transfer_active = false;
+			wake_up(&data->wait);
+		} else {
 			dev_err(&data->master->dev,
 				"%s : Transfer is not completed", __func__);
-		/* disable interrupts */
-		pch_spi_setclr_reg(data->master, PCH_SPCR, 0, PCH_ALL);
-
-		/* transfer is completed;inform pch_spi_process_messages */
-		data->transfer_complete = true;
-		data->transfer_active = false;
-		wake_up(&data->wait);
+		}
 	}
 }
 
@@ -348,16 +354,26 @@ static irqreturn_t pch_spi_handler(int irq, void *dev_id)
 			"%s returning due to suspend\n", __func__);
 		return IRQ_NONE;
 	}
-	if (data->use_dma)
-		return IRQ_NONE;
 
 	io_remap_addr = data->io_remap_addr;
 	spsr = io_remap_addr + PCH_SPSR;
 
 	reg_spsr_val = ioread32(spsr);
 
-	if (reg_spsr_val & SPSR_ORF_BIT)
-		dev_err(&board_dat->pdev->dev, "%s Over run error", __func__);
+	if (reg_spsr_val & SPSR_ORF_BIT) {
+		dev_err(&board_dat->pdev->dev, "%s Over run error\n", __func__);
+		if (data->current_msg->complete != 0) {
+			data->transfer_complete = true;
+			data->current_msg->status = -EIO;
+			data->current_msg->complete(data->current_msg->context);
+			data->bcurrent_msg_processing = false;
+			data->current_msg = NULL;
+			data->cur_trans = NULL;
+		}
+	}
+
+	if (data->use_dma)
+		return IRQ_NONE;
 
 	/* Check if the interrupt is for SPI device */
 	if (reg_spsr_val & (SPSR_FI_BIT | SPSR_RFI_BIT)) {
@@ -756,10 +772,6 @@ static void pch_spi_set_ir(struct pch_spi_data *data)
 
 	wait_event_interruptible(data->wait, data->transfer_complete);
 
-	pch_spi_writereg(data->master, PCH_SSNXCR, SSN_NO_CONTROL);
-	dev_dbg(&data->master->dev,
-		"%s:no more control over SSN-writing 0 to SSNXCR.", __func__);
-
 	/* clear all interrupts */
 	pch_spi_writereg(data->master, PCH_SPSR,
 			 pch_spi_readreg(data->master, PCH_SPSR));
@@ -815,10 +827,11 @@ static void pch_spi_copy_rx_data_for_dma(struct pch_spi_data *data, int bpw)
 	}
 }
 
-static void pch_spi_start_transfer(struct pch_spi_data *data)
+static int pch_spi_start_transfer(struct pch_spi_data *data)
 {
 	struct pch_spi_dma_ctrl *dma;
 	unsigned long flags;
+	int rtn;
 
 	dma = &data->dma;
 
@@ -833,19 +846,23 @@ static void pch_spi_start_transfer(struct pch_spi_data *data)
 				 initiating the transfer. */
 	dev_dbg(&data->master->dev,
 		"%s:waiting for transfer to get over\n", __func__);
-	wait_event_interruptible(data->wait, data->transfer_complete);
+	rtn = wait_event_interruptible_timeout(data->wait,
+					       data->transfer_complete,
+					       msecs_to_jiffies(2 * HZ));
 
 	dma_sync_sg_for_cpu(&data->master->dev, dma->sg_rx_p, dma->nent,
 			    DMA_FROM_DEVICE);
+
+	dma_sync_sg_for_cpu(&data->master->dev, dma->sg_tx_p, dma->nent,
+			    DMA_FROM_DEVICE);
+	memset(data->dma.tx_buf_virt, 0, PAGE_SIZE);
+
 	async_tx_ack(dma->desc_rx);
 	async_tx_ack(dma->desc_tx);
 	kfree(dma->sg_tx_p);
 	kfree(dma->sg_rx_p);
 
 	spin_lock_irqsave(&data->lock, flags);
-	pch_spi_writereg(data->master, PCH_SSNXCR, SSN_NO_CONTROL);
-	dev_dbg(&data->master->dev,
-		"%s:no more control over SSN-writing 0 to SSNXCR.", __func__);
 
 	/* clear fifo threshold, disable interrupts, disable SPI transfer */
 	pch_spi_setclr_reg(data->master, PCH_SPCR, 0,
@@ -858,6 +875,8 @@ static void pch_spi_start_transfer(struct pch_spi_data *data)
 	pch_spi_clear_fifo(data->master);
 
 	spin_unlock_irqrestore(&data->lock, flags);
+
+	return rtn;
 }
 
 static void pch_dma_rx_complete(void *arg)
@@ -1023,8 +1042,7 @@ static void pch_spi_handle_dma(struct pch_spi_data *data, int *bpw)
 	/* set receive fifo threshold and transmit fifo threshold */
 	pch_spi_setclr_reg(data->master, PCH_SPCR,
 			   ((size - 1) << SPCR_RFIC_FIELD) |
-			   ((PCH_MAX_FIFO_DEPTH - PCH_DMA_TRANS_SIZE) <<
-			    SPCR_TFIC_FIELD),
+			   (PCH_TX_THOLD << SPCR_TFIC_FIELD),
 			   MASK_RFIC_SPCR_BITS | MASK_TFIC_SPCR_BITS);
 
 	spin_unlock_irqrestore(&data->lock, flags);
@@ -1035,13 +1053,20 @@ static void pch_spi_handle_dma(struct pch_spi_data *data, int *bpw)
 	/* offset, length setting */
 	sg = dma->sg_rx_p;
 	for (i = 0; i < num; i++, sg++) {
-		if (i == 0) {
-			sg->offset = 0;
+		if (i == (num - 2)) {
+			sg->offset = size * i;
+			sg->offset = sg->offset * (*bpw / 8);
 			sg_set_page(sg, virt_to_page(dma->rx_buf_virt), rem,
 				    sg->offset);
 			sg_dma_len(sg) = rem;
+		} else if (i == (num - 1)) {
+			sg->offset = size * (i - 1) + rem;
+			sg->offset = sg->offset * (*bpw / 8);
+			sg_set_page(sg, virt_to_page(dma->rx_buf_virt), size,
+				    sg->offset);
+			sg_dma_len(sg) = size;
 		} else {
-			sg->offset = rem + size * (i - 1);
+			sg->offset = size * i;
 			sg->offset = sg->offset * (*bpw / 8);
 			sg_set_page(sg, virt_to_page(dma->rx_buf_virt), size,
 				    sg->offset);
@@ -1065,6 +1090,16 @@ static void pch_spi_handle_dma(struct pch_spi_data *data, int *bpw)
 	dma->desc_rx = desc_rx;
 
 	/* TX */
+	if (data->bpw_len > PCH_DMA_TRANS_SIZE) {
+		num = data->bpw_len / PCH_DMA_TRANS_SIZE;
+		size = PCH_DMA_TRANS_SIZE;
+		rem = 16;
+	} else {
+		num = 1;
+		size = data->bpw_len;
+		rem = data->bpw_len;
+	}
+
 	dma->sg_tx_p = kzalloc(sizeof(struct scatterlist)*num, GFP_ATOMIC);
 	sg_init_table(dma->sg_tx_p, num); /* Initialize SG table */
 	/* offset, length setting */
@@ -1162,6 +1197,7 @@ static void pch_spi_process_messages(struct work_struct *pwork)
 	if (data->use_dma)
 		pch_spi_request_dma(data,
 				    data->current_msg->spi->bits_per_word);
+	pch_spi_writereg(data->master, PCH_SSNXCR, SSN_NO_CONTROL);
 	do {
 		/* If we are already processing a message get the next
 		transfer structure from the message otherwise retrieve
@@ -1184,7 +1220,8 @@ static void pch_spi_process_messages(struct work_struct *pwork)
 
 		if (data->use_dma) {
 			pch_spi_handle_dma(data, &bpw);
-			pch_spi_start_transfer(data);
+			if (!pch_spi_start_transfer(data))
+				goto out;
 			pch_spi_copy_rx_data_for_dma(data, bpw);
 		} else {
 			pch_spi_set_tx(data, &bpw);
@@ -1222,6 +1259,8 @@ static void pch_spi_process_messages(struct work_struct *pwork)
 
 	} while (data->cur_trans != NULL);
 
+out:
+	pch_spi_writereg(data->master, PCH_SSNXCR, SSN_HIGH);
 	if (data->use_dma)
 		pch_spi_release_dma(data);
 }
diff --git a/drivers/watchdog/hpwdt.c b/drivers/watchdog/hpwdt.c
index 809cbda03d7a..7e7feac05221 100644
--- a/drivers/watchdog/hpwdt.c
+++ b/drivers/watchdog/hpwdt.c
@@ -477,15 +477,11 @@ static int hpwdt_time_left(void)
 /*
  *	NMI Handler
  */
-static int hpwdt_pretimeout(struct notifier_block *nb, unsigned long ulReason,
-				void *data)
+static int hpwdt_pretimeout(unsigned int ulReason, struct pt_regs *regs)
 {
 	unsigned long rom_pl;
 	static int die_nmi_called;
 
-	if (ulReason != DIE_NMIUNKNOWN)
-		goto out;
-
 	if (!hpwdt_nmi_decoding)
 		goto out;
 
@@ -508,7 +504,7 @@ static int hpwdt_pretimeout(struct notifier_block *nb, unsigned long ulReason,
 		"Management Log for details.\n");
 
 out:
-	return NOTIFY_OK;
+	return NMI_DONE;
 }
 #endif /* CONFIG_HPWDT_NMI_DECODING */
 
@@ -648,13 +644,6 @@ static struct miscdevice hpwdt_miscdev = {
 	.fops = &hpwdt_fops,
 };
 
-#ifdef CONFIG_HPWDT_NMI_DECODING
-static struct notifier_block die_notifier = {
-	.notifier_call = hpwdt_pretimeout,
-	.priority = 0,
-};
-#endif /* CONFIG_HPWDT_NMI_DECODING */
-
 /*
  *	Init & Exit
  */
@@ -740,10 +729,9 @@ static int __devinit hpwdt_init_nmi_decoding(struct pci_dev *dev)
 	 * die notify list to handle a critical NMI. The default is to
 	 * be last so other users of the NMI signal can function.
 	 */
-	if (priority)
-		die_notifier.priority = 0x7FFFFFFF;
-
-	retval = register_die_notifier(&die_notifier);
+	retval = register_nmi_handler(NMI_UNKNOWN, hpwdt_pretimeout,
+					(priority) ? NMI_FLAG_FIRST : 0,
+					"hpwdt");
 	if (retval != 0) {
 		dev_warn(&dev->dev,
 			"Unable to register a die notifier (err=%d).\n",
@@ -763,7 +751,7 @@ static int __devinit hpwdt_init_nmi_decoding(struct pci_dev *dev)
 
 static void hpwdt_exit_nmi_decoding(void)
 {
-	unregister_die_notifier(&die_notifier);
+	unregister_nmi_handler(NMI_UNKNOWN, "hpwdt");
 	if (cru_rom_addr)
 		iounmap(cru_rom_addr);
 }
diff --git a/drivers/zorro/zorro.c b/drivers/zorro/zorro.c
index e0c2807b0970..181fa8158a8b 100644
--- a/drivers/zorro/zorro.c
+++ b/drivers/zorro/zorro.c
@@ -148,10 +148,10 @@ static int __init amiga_zorro_probe(struct platform_device *pdev)
 	}
 	platform_set_drvdata(pdev, bus);
 
-	/* Register all devices */
 	pr_info("Zorro: Probing AutoConfig expansion devices: %u device%s\n",
 		 zorro_num_autocon, zorro_num_autocon == 1 ? "" : "s");
 
+	/* First identify all devices ... */
 	for (i = 0; i < zorro_num_autocon; i++) {
 		z = &zorro_autocon[i];
 		z->id = (z->rom.er_Manufacturer<<16) | (z->rom.er_Product<<8);
@@ -172,6 +172,11 @@ static int __init amiga_zorro_probe(struct platform_device *pdev)
 		dev_set_name(&z->dev, "%02x", i);
 		z->dev.parent = &bus->dev;
 		z->dev.bus = &zorro_bus_type;
+	}
+
+	/* ... then register them */
+	for (i = 0; i < zorro_num_autocon; i++) {
+		z = &zorro_autocon[i];
 		error = device_register(&z->dev);
 		if (error) {
 			dev_err(&bus->dev, "Error registering device %s\n",
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index a381cd22f518..e4e57d59edb7 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1036,11 +1036,13 @@ out:
  * on error we return an unlocked page and the error value
  * on success we return a locked page and 0
  */
-static int prepare_uptodate_page(struct page *page, u64 pos)
+static int prepare_uptodate_page(struct page *page, u64 pos,
+				 bool force_uptodate)
 {
 	int ret = 0;
 
-	if ((pos & (PAGE_CACHE_SIZE - 1)) && !PageUptodate(page)) {
+	if (((pos & (PAGE_CACHE_SIZE - 1)) || force_uptodate) &&
+	    !PageUptodate(page)) {
 		ret = btrfs_readpage(NULL, page);
 		if (ret)
 			return ret;
@@ -1061,7 +1063,7 @@ static int prepare_uptodate_page(struct page *page, u64 pos)
 static noinline int prepare_pages(struct btrfs_root *root, struct file *file,
 			 struct page **pages, size_t num_pages,
 			 loff_t pos, unsigned long first_index,
-			 size_t write_bytes)
+			 size_t write_bytes, bool force_uptodate)
 {
 	struct extent_state *cached_state = NULL;
 	int i;
@@ -1086,10 +1088,11 @@ again:
 		}
 
 		if (i == 0)
-			err = prepare_uptodate_page(pages[i], pos);
+			err = prepare_uptodate_page(pages[i], pos,
+						    force_uptodate);
 		if (i == num_pages - 1)
 			err = prepare_uptodate_page(pages[i],
-						    pos + write_bytes);
+						    pos + write_bytes, false);
 		if (err) {
 			page_cache_release(pages[i]);
 			faili = i - 1;
@@ -1158,6 +1161,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 	size_t num_written = 0;
 	int nrptrs;
 	int ret = 0;
+	bool force_page_uptodate = false;
 
 	nrptrs = min((iov_iter_count(i) + PAGE_CACHE_SIZE - 1) /
 		     PAGE_CACHE_SIZE, PAGE_CACHE_SIZE /
@@ -1200,7 +1204,8 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		 * contents of pages from loop to loop
 		 */
 		ret = prepare_pages(root, file, pages, num_pages,
-				    pos, first_index, write_bytes);
+				    pos, first_index, write_bytes,
+				    force_page_uptodate);
 		if (ret) {
 			btrfs_delalloc_release_space(inode,
 					num_pages << PAGE_CACHE_SHIFT);
@@ -1217,12 +1222,15 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		if (copied < write_bytes)
 			nrptrs = 1;
 
-		if (copied == 0)
+		if (copied == 0) {
+			force_page_uptodate = true;
 			dirty_pages = 0;
-		else
+		} else {
+			force_page_uptodate = false;
 			dirty_pages = (copied + offset +
 				       PAGE_CACHE_SIZE - 1) >>
 				       PAGE_CACHE_SHIFT;
+		}
 
 		/*
 		 * If we had a short copy we need to release the excess delaloc
diff --git a/fs/namei.c b/fs/namei.c
index f4788365ea22..0b3138de2a3b 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -721,12 +721,6 @@ static int follow_automount(struct path *path, unsigned flags,
 	if (!path->dentry->d_op || !path->dentry->d_op->d_automount)
 		return -EREMOTE;
 
-	/* We don't want to mount if someone supplied AT_NO_AUTOMOUNT
-	 * and this is the terminal part of the path.
-	 */
-	if ((flags & LOOKUP_NO_AUTOMOUNT) && !(flags & LOOKUP_PARENT))
-		return -EISDIR; /* we actually want to stop here */
-
 	/* We don't want to mount if someone's just doing a stat -
 	 * unless they're stat'ing a directory and appended a '/' to
 	 * the name.
@@ -739,7 +733,7 @@ static int follow_automount(struct path *path, unsigned flags,
 	 * of the daemon to instantiate them before they can be used.
 	 */
 	if (!(flags & (LOOKUP_PARENT | LOOKUP_DIRECTORY |
-		     LOOKUP_OPEN | LOOKUP_CREATE)) &&
+		     LOOKUP_OPEN | LOOKUP_CREATE | LOOKUP_AUTOMOUNT)) &&
 	    path->dentry->d_inode)
 		return -EISDIR;
 
diff --git a/fs/namespace.c b/fs/namespace.c
index 22bfe8273c68..b4febb29d3bb 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1757,7 +1757,7 @@ static int do_loopback(struct path *path, char *old_name,
 		return err;
 	if (!old_name || !*old_name)
 		return -EINVAL;
-	err = kern_path(old_name, LOOKUP_FOLLOW, &old_path);
+	err = kern_path(old_name, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &old_path);
 	if (err)
 		return err;
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 9b7dd7013b15..5b19b6aabe18 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2798,7 +2798,7 @@ static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt,
 		goto out_put_mnt_ns;
 
 	ret = vfs_path_lookup(root_mnt->mnt_root, root_mnt,
-			export_path, LOOKUP_FOLLOW, &path);
+			export_path, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
 
 	nfs_referral_loop_unprotect();
 	put_mnt_ns(ns_private);
diff --git a/fs/quota/quota.c b/fs/quota/quota.c
index b34bdb25490c..10b6be3ca280 100644
--- a/fs/quota/quota.c
+++ b/fs/quota/quota.c
@@ -355,7 +355,7 @@ SYSCALL_DEFINE4(quotactl, unsigned int, cmd, const char __user *, special,
 	 * resolution (think about autofs) and thus deadlocks could arise.
 	 */
 	if (cmds == Q_QUOTAON) {
-		ret = user_path_at(AT_FDCWD, addr, LOOKUP_FOLLOW, &path);
+		ret = user_path_at(AT_FDCWD, addr, LOOKUP_FOLLOW|LOOKUP_AUTOMOUNT, &path);
 		if (ret)
 			pathp = ERR_PTR(ret);
 		else
diff --git a/fs/stat.c b/fs/stat.c
index ba5316ffac61..78a3aa83c7ea 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -81,8 +81,6 @@ int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
 
 	if (!(flag & AT_SYMLINK_NOFOLLOW))
 		lookup_flags |= LOOKUP_FOLLOW;
-	if (flag & AT_NO_AUTOMOUNT)
-		lookup_flags |= LOOKUP_NO_AUTOMOUNT;
 	if (flag & AT_EMPTY_PATH)
 		lookup_flags |= LOOKUP_EMPTY;
 
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index e807ad687a07..3ad553e8eae2 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -80,6 +80,7 @@ extern void irq_domain_del(struct irq_domain *domain);
 #endif /* CONFIG_IRQ_DOMAIN */
 
 #if defined(CONFIG_IRQ_DOMAIN) && defined(CONFIG_OF_IRQ)
+extern struct irq_domain_ops irq_domain_simple_ops;
 extern void irq_domain_add_simple(struct device_node *controller, int irq_base);
 extern void irq_domain_generate_simple(const struct of_device_id *match,
 					u64 phys_base, unsigned int irq_start);
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 2c366b52f505..aace6b8691a2 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -553,6 +553,7 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_SPAPR_TCE 63
 #define KVM_CAP_PPC_SMT 64
 #define KVM_CAP_PPC_RMA	65
+#define KVM_CAP_S390_GMAP 71
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 76fe2c62ae71..409328d1cbbb 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -48,11 +48,12 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND};
  */
 #define LOOKUP_FOLLOW		0x0001
 #define LOOKUP_DIRECTORY	0x0002
+#define LOOKUP_AUTOMOUNT	0x0004
 
 #define LOOKUP_PARENT		0x0010
 #define LOOKUP_REVAL		0x0020
 #define LOOKUP_RCU		0x0040
-#define LOOKUP_NO_AUTOMOUNT	0x0080
+
 /*
  * Intent data
  */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 8c230cbcbb48..9fc01226055b 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -621,8 +621,9 @@ struct pci_driver {
 extern void pcie_bus_configure_settings(struct pci_bus *bus, u8 smpss);
 
 enum pcie_bus_config_types {
-	PCIE_BUS_PERFORMANCE,
+	PCIE_BUS_TUNE_OFF,
 	PCIE_BUS_SAFE,
+	PCIE_BUS_PERFORMANCE,
 	PCIE_BUS_PEER2PEER,
 };
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c816075c01ce..1e9ebe5e0091 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -220,7 +220,10 @@ struct perf_event_attr {
 				mmap_data      :  1, /* non-exec mmap data    */
 				sample_id_all  :  1, /* sample_type all events */
 
-				__reserved_1   : 45;
+				exclude_host   :  1, /* don't count in host   */
+				exclude_guest  :  1, /* don't count in guest  */
+
+				__reserved_1   : 43;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
diff --git a/include/linux/ptp_classify.h b/include/linux/ptp_classify.h
index e07e2742a865..1dc420ba213a 100644
--- a/include/linux/ptp_classify.h
+++ b/include/linux/ptp_classify.h
@@ -51,6 +51,7 @@
 #define PTP_CLASS_V2_VLAN (PTP_CLASS_V2 | PTP_CLASS_VLAN)
 
 #define PTP_EV_PORT 319
+#define PTP_GEN_BIT 0x08 /* indicates general message, if set in message type */
 
 #define OFF_ETYPE	12
 #define OFF_IHL		14
@@ -116,14 +117,20 @@ static inline int ptp_filter_init(struct sock_filter *f, int len)
 	{OP_OR,		0,   0, PTP_CLASS_IPV6		}, /*              */ \
 	{OP_RETA,	0,   0, 0			}, /*              */ \
 /*L3x*/	{OP_RETK,	0,   0, PTP_CLASS_NONE		}, /*              */ \
-/*L40*/	{OP_JEQ,	0,   6, ETH_P_8021Q		}, /* f goto L50   */ \
+/*L40*/	{OP_JEQ,	0,   9, ETH_P_8021Q		}, /* f goto L50   */ \
 	{OP_LDH,	0,   0, OFF_ETYPE + 4		}, /*              */ \
-	{OP_JEQ,	0,   9, ETH_P_1588		}, /* f goto L60   */ \
+	{OP_JEQ,	0,  15, ETH_P_1588		}, /* f goto L60   */ \
+	{OP_LDB,	0,   0, ETH_HLEN + VLAN_HLEN	}, /*              */ \
+	{OP_AND,	0,   0, PTP_GEN_BIT		}, /*              */ \
+	{OP_JEQ,	0,  12, 0			}, /* f goto L6x   */ \
 	{OP_LDH,	0,   0, ETH_HLEN + VLAN_HLEN	}, /*              */ \
 	{OP_AND,	0,   0, PTP_CLASS_VMASK		}, /*              */ \
 	{OP_OR,		0,   0, PTP_CLASS_VLAN		}, /*              */ \
 	{OP_RETA,	0,   0, 0			}, /*              */ \
-/*L50*/	{OP_JEQ,	0,   4, ETH_P_1588		}, /* f goto L61   */ \
+/*L50*/	{OP_JEQ,	0,   7, ETH_P_1588		}, /* f goto L61   */ \
+	{OP_LDB,	0,   0, ETH_HLEN		}, /*              */ \
+	{OP_AND,	0,   0, PTP_GEN_BIT		}, /*              */ \
+	{OP_JEQ,	0,   4, 0			}, /* f goto L6x   */ \
 	{OP_LDH,	0,   0, ETH_HLEN		}, /*              */ \
 	{OP_AND,	0,   0, PTP_CLASS_VMASK		}, /*              */ \
 	{OP_OR,		0,   0, PTP_CLASS_L2		}, /*              */ \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4ac2c0578e0f..41d0237fd449 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1956,7 +1956,6 @@ static inline void disable_sched_clock_irqtime(void) {}
 
 extern unsigned long long
 task_sched_runtime(struct task_struct *task);
-extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
 
 /* sched_exec is called by processes performing an exec */
 #ifdef CONFIG_SMP
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 6bca4cc0063c..5f172703eb4f 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -298,7 +298,7 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template,
 		__array(char, name, 32)
 		__field(unsigned long, ino)
 		__field(unsigned long, state)
-		__field(unsigned long, age)
+		__field(unsigned long, dirtied_when)
 		__field(unsigned long, writeback_index)
 		__field(long, nr_to_write)
 		__field(unsigned long, wrote)
@@ -309,19 +309,19 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template,
 			dev_name(inode->i_mapping->backing_dev_info->dev), 32);
 		__entry->ino		= inode->i_ino;
 		__entry->state		= inode->i_state;
-		__entry->age		= (jiffies - inode->dirtied_when) *
-								1000 / HZ;
+		__entry->dirtied_when	= inode->dirtied_when;
 		__entry->writeback_index = inode->i_mapping->writeback_index;
 		__entry->nr_to_write	= nr_to_write;
 		__entry->wrote		= nr_to_write - wbc->nr_to_write;
 	),
 
-	TP_printk("bdi %s: ino=%lu state=%s age=%lu "
+	TP_printk("bdi %s: ino=%lu state=%s dirtied_when=%lu age=%lu "
 		  "index=%lu to_write=%ld wrote=%lu",
 		  __entry->name,
 		  __entry->ino,
 		  show_inode_state(__entry->state),
-		  __entry->age,
+		  __entry->dirtied_when,
+		  (jiffies - __entry->dirtied_when) / HZ,
 		  __entry->writeback_index,
 		  __entry->nr_to_write,
 		  __entry->wrote
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 533c49f48047..769724944fc6 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -711,6 +711,9 @@ __attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
 #undef __perf_count
 #define __perf_count(c) __count = (c)
 
+#undef TP_perf_assign
+#define TP_perf_assign(args...) args
+
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 static notrace void							\
diff --git a/init/main.c b/init/main.c
index 2a9b88aa5e76..03b408dff825 100644
--- a/init/main.c
+++ b/init/main.c
@@ -381,9 +381,6 @@ static noinline void __init_refok rest_init(void)
 	preempt_enable_no_resched();
 	schedule();
 
-	/* At this point, we can enable user mode helper functionality */
-	usermodehelper_enable();
-
 	/* Call into cpu_idle with preempt disabled */
 	preempt_disable();
 	cpu_idle();
@@ -733,6 +730,7 @@ static void __init do_basic_setup(void)
 	driver_init();
 	init_irq_proc();
 	do_ctors();
+	usermodehelper_enable();
 	do_initcalls();
 }
 
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index d5828da3fd38..b57a3776de44 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -29,7 +29,11 @@ void irq_domain_add(struct irq_domain *domain)
 	 */
 	for (hwirq = 0; hwirq < domain->nr_irq; hwirq++) {
 		d = irq_get_irq_data(irq_domain_to_irq(domain, hwirq));
-		if (d || d->domain) {
+		if (!d) {
+			WARN(1, "error: assigning domain to non existant irq_desc");
+			return;
+		}
+		if (d->domain) {
 			/* things are broken; just report, don't clean up */
 			WARN(1, "error: irq_desc already assigned to a domain");
 			return;
diff --git a/kernel/posix-cpu-timers.c b/kernel/posix-cpu-timers.c
index 58f405b581e7..c8008dd58ef2 100644
--- a/kernel/posix-cpu-timers.c
+++ b/kernel/posix-cpu-timers.c
@@ -250,7 +250,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 	do {
 		times->utime = cputime_add(times->utime, t->utime);
 		times->stime = cputime_add(times->stime, t->stime);
-		times->sum_exec_runtime += t->se.sum_exec_runtime;
+		times->sum_exec_runtime += task_sched_runtime(t);
 	} while_each_thread(tsk, t);
 out:
 	rcu_read_unlock();
@@ -312,7 +312,8 @@ static int cpu_clock_sample_group(const clockid_t which_clock,
 		cpu->cpu = cputime.utime;
 		break;
 	case CPUCLOCK_SCHED:
-		cpu->sched = thread_group_sched_runtime(p);
+		thread_group_cputime(p, &cputime);
+		cpu->sched = cputime.sum_exec_runtime;
 		break;
 	}
 	return 0;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 9de3ecfd20f9..a70d2a5d8c7b 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -744,20 +744,17 @@ int ptrace_request(struct task_struct *child, long request,
 			break;
 
 		si = child->last_siginfo;
-		if (unlikely(!si || si->si_code >> 8 != PTRACE_EVENT_STOP))
-			break;
-
-		child->jobctl |= JOBCTL_LISTENING;
-
-		/*
-		 * If NOTIFY is set, it means event happened between start
-		 * of this trap and now.  Trigger re-trap immediately.
-		 */
-		if (child->jobctl & JOBCTL_TRAP_NOTIFY)
-			signal_wake_up(child, true);
-
+		if (likely(si && (si->si_code >> 8) == PTRACE_EVENT_STOP)) {
+			child->jobctl |= JOBCTL_LISTENING;
+			/*
+			 * If NOTIFY is set, it means event happened between
+			 * start of this trap and now.  Trigger re-trap.
+			 */
+			if (child->jobctl & JOBCTL_TRAP_NOTIFY)
+				signal_wake_up(child, true);
+			ret = 0;
+		}
 		unlock_task_sighand(child, &flags);
-		ret = 0;
 		break;
 
 	case PTRACE_DETACH:	 /* detach a process that was attached. */
diff --git a/kernel/resource.c b/kernel/resource.c
index 3b3cedc52592..c8dc249da5ce 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -419,6 +419,9 @@ static int __find_resource(struct resource *root, struct resource *old,
 		else
 			tmp.end = root->end;
 
+		if (tmp.end < tmp.start)
+			goto next;
+
 		resource_clip(&tmp, constraint->min, constraint->max);
 		arch_remove_reservations(&tmp);
 
@@ -436,8 +439,10 @@ static int __find_resource(struct resource *root, struct resource *old,
 				return 0;
 			}
 		}
-		if (!this)
+
+next:		if (!this || this->end == root->end)
 			break;
+
 		if (this != old)
 			tmp.start = this->end + 1;
 		this = this->sibling;
diff --git a/kernel/sched.c b/kernel/sched.c
index ec5f472bc5b9..b50b0f0c9aa9 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -3725,30 +3725,6 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 }
 
 /*
- * Return sum_exec_runtime for the thread group.
- * In case the task is currently running, return the sum plus current's
- * pending runtime that have not been accounted yet.
- *
- * Note that the thread group might have other running tasks as well,
- * so the return value not includes other pending runtime that other
- * running tasks might have.
- */
-unsigned long long thread_group_sched_runtime(struct task_struct *p)
-{
-	struct task_cputime totals;
-	unsigned long flags;
-	struct rq *rq;
-	u64 ns;
-
-	rq = task_rq_lock(p, &flags);
-	thread_group_cputime(p, &totals);
-	ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq);
-	task_rq_unlock(rq, p, &flags);
-
-	return ns;
-}
-
-/*
  * Account user cpu time to a process.
  * @p: the process that the cpu time gets accounted to
  * @cputime: the cpu time spent in user space since the last update
@@ -4372,7 +4348,7 @@ static inline void sched_submit_work(struct task_struct *tsk)
 		blk_schedule_flush_plug(tsk);
 }
 
-asmlinkage void schedule(void)
+asmlinkage void __sched schedule(void)
 {
 	struct task_struct *tsk = current;
 
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 97540f0c9e47..af1177858be3 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1050,7 +1050,7 @@ select_task_rq_rt(struct task_struct *p, int sd_flag, int flags)
 	 */
 	if (curr && unlikely(rt_task(curr)) &&
 	    (curr->rt.nr_cpus_allowed < 2 ||
-	     curr->prio < p->prio) &&
+	     curr->prio <= p->prio) &&
 	    (p->rt.nr_cpus_allowed > 1)) {
 		int target = find_lowest_rq(p);
 
@@ -1581,7 +1581,7 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p)
 	    p->rt.nr_cpus_allowed > 1 &&
 	    rt_task(rq->curr) &&
 	    (rq->curr->rt.nr_cpus_allowed < 2 ||
-	     rq->curr->prio < p->prio))
+	     rq->curr->prio <= p->prio))
 		push_rt_tasks(rq);
 }
 
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 3e2f91ffa4e2..05dd35114a27 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -565,7 +565,7 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface)
 	struct orig_node *orig_node = NULL;
 	int data_len = skb->len, ret;
 	short vid = -1;
-	bool do_bcast = false;
+	bool do_bcast;
 
 	if (atomic_read(&bat_priv->mesh_state) != MESH_ACTIVE)
 		goto dropped;
@@ -598,15 +598,15 @@ static int interface_tx(struct sk_buff *skb, struct net_device *soft_iface)
 	tt_local_add(soft_iface, ethhdr->h_source);
 
 	orig_node = transtable_search(bat_priv, ethhdr->h_dest);
-	if (is_multicast_ether_addr(ethhdr->h_dest) ||
-				(orig_node && orig_node->gw_flags)) {
+	do_bcast = is_multicast_ether_addr(ethhdr->h_dest);
+	if (do_bcast ||	(orig_node && orig_node->gw_flags)) {
 		ret = gw_is_target(bat_priv, skb, orig_node);
 
 		if (ret < 0)
 			goto dropped;
 
-		if (ret == 0)
-			do_bcast = true;
+		if (ret)
+			do_bcast = false;
 	}
 
 	/* ethernet packet should be broadcasted */
diff --git a/net/can/bcm.c b/net/can/bcm.c
index d6c8ae5b2e6a..c84963d2dee6 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -344,6 +344,18 @@ static void bcm_send_to_user(struct bcm_op *op, struct bcm_msg_head *head,
 	}
 }
 
+static void bcm_tx_start_timer(struct bcm_op *op)
+{
+	if (op->kt_ival1.tv64 && op->count)
+		hrtimer_start(&op->timer,
+			      ktime_add(ktime_get(), op->kt_ival1),
+			      HRTIMER_MODE_ABS);
+	else if (op->kt_ival2.tv64)
+		hrtimer_start(&op->timer,
+			      ktime_add(ktime_get(), op->kt_ival2),
+			      HRTIMER_MODE_ABS);
+}
+
 static void bcm_tx_timeout_tsklet(unsigned long data)
 {
 	struct bcm_op *op = (struct bcm_op *)data;
@@ -365,26 +377,12 @@ static void bcm_tx_timeout_tsklet(unsigned long data)
 
 			bcm_send_to_user(op, &msg_head, NULL, 0);
 		}
-	}
-
-	if (op->kt_ival1.tv64 && (op->count > 0)) {
-
-		/* send (next) frame */
 		bcm_can_tx(op);
-		hrtimer_start(&op->timer,
-			      ktime_add(ktime_get(), op->kt_ival1),
-			      HRTIMER_MODE_ABS);
 
-	} else {
-		if (op->kt_ival2.tv64) {
+	} else if (op->kt_ival2.tv64)
+		bcm_can_tx(op);
 
-			/* send (next) frame */
-			bcm_can_tx(op);
-			hrtimer_start(&op->timer,
-				      ktime_add(ktime_get(), op->kt_ival2),
-				      HRTIMER_MODE_ABS);
-		}
-	}
+	bcm_tx_start_timer(op);
 }
 
 /*
@@ -964,23 +962,20 @@ static int bcm_tx_setup(struct bcm_msg_head *msg_head, struct msghdr *msg,
 			hrtimer_cancel(&op->timer);
 	}
 
-	if ((op->flags & STARTTIMER) &&
-	    ((op->kt_ival1.tv64 && op->count) || op->kt_ival2.tv64)) {
-
+	if (op->flags & STARTTIMER) {
+		hrtimer_cancel(&op->timer);
 		/* spec: send can_frame when starting timer */
 		op->flags |= TX_ANNOUNCE;
-
-		if (op->kt_ival1.tv64 && (op->count > 0)) {
-			/* op->count-- is done in bcm_tx_timeout_handler */
-			hrtimer_start(&op->timer, op->kt_ival1,
-				      HRTIMER_MODE_REL);
-		} else
-			hrtimer_start(&op->timer, op->kt_ival2,
-				      HRTIMER_MODE_REL);
 	}
 
-	if (op->flags & TX_ANNOUNCE)
+	if (op->flags & TX_ANNOUNCE) {
 		bcm_can_tx(op);
+		if (op->count)
+			op->count--;
+	}
+
+	if (op->flags & STARTTIMER)
+		bcm_tx_start_timer(op);
 
 	return msg_head->nframes * CFSIZ + MHSIZ;
 }
diff --git a/net/ceph/ceph_common.c b/net/ceph/ceph_common.c
index 132963abc266..2883ea01e680 100644
--- a/net/ceph/ceph_common.c
+++ b/net/ceph/ceph_common.c
@@ -232,6 +232,7 @@ void ceph_destroy_options(struct ceph_options *opt)
 		ceph_crypto_key_destroy(opt->key);
 		kfree(opt->key);
 	}
+	kfree(opt->mon_addr);
 	kfree(opt);
 }
 EXPORT_SYMBOL(ceph_destroy_options);
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index c340e2e0765b..9918e9eb276e 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -2307,6 +2307,7 @@ struct ceph_msg *ceph_msg_new(int type, int front_len, gfp_t flags)
 	m->front_max = front_len;
 	m->front_is_vmalloc = false;
 	m->more_to_follow = false;
+	m->ack_stamp = 0;
 	m->pool = NULL;
 
 	/* middle */
diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c
index 16836a7df7a6..88ad8a2501b5 100644
--- a/net/ceph/osd_client.c
+++ b/net/ceph/osd_client.c
@@ -217,6 +217,7 @@ struct ceph_osd_request *ceph_osdc_alloc_request(struct ceph_osd_client *osdc,
 	INIT_LIST_HEAD(&req->r_unsafe_item);
 	INIT_LIST_HEAD(&req->r_linger_item);
 	INIT_LIST_HEAD(&req->r_linger_osd);
+	INIT_LIST_HEAD(&req->r_req_lru_item);
 	req->r_flags = flags;
 
 	WARN_ON((flags & (CEPH_OSD_FLAG_READ|CEPH_OSD_FLAG_WRITE)) == 0);
@@ -816,13 +817,10 @@ static void __register_request(struct ceph_osd_client *osdc,
 {
 	req->r_tid = ++osdc->last_tid;
 	req->r_request->hdr.tid = cpu_to_le64(req->r_tid);
-	INIT_LIST_HEAD(&req->r_req_lru_item);
-
 	dout("__register_request %p tid %lld\n", req, req->r_tid);
 	__insert_request(osdc, req);
 	ceph_osdc_get_request(req);
 	osdc->num_requests++;
-
 	if (osdc->num_requests == 1) {
 		dout(" first request, scheduling timeout\n");
 		__schedule_osd_timeout(osdc);
diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c
index e97c3588c3ec..fd863fe76934 100644
--- a/net/ceph/osdmap.c
+++ b/net/ceph/osdmap.c
@@ -339,6 +339,7 @@ static int __insert_pg_mapping(struct ceph_pg_mapping *new,
 	struct ceph_pg_mapping *pg = NULL;
 	int c;
 
+	dout("__insert_pg_mapping %llx %p\n", *(u64 *)&new->pgid, new);
 	while (*p) {
 		parent = *p;
 		pg = rb_entry(parent, struct ceph_pg_mapping, node);
@@ -366,16 +367,33 @@ static struct ceph_pg_mapping *__lookup_pg_mapping(struct rb_root *root,
 	while (n) {
 		pg = rb_entry(n, struct ceph_pg_mapping, node);
 		c = pgid_cmp(pgid, pg->pgid);
-		if (c < 0)
+		if (c < 0) {
 			n = n->rb_left;
-		else if (c > 0)
+		} else if (c > 0) {
 			n = n->rb_right;
-		else
+		} else {
+			dout("__lookup_pg_mapping %llx got %p\n",
+			     *(u64 *)&pgid, pg);
 			return pg;
+		}
 	}
 	return NULL;
 }
 
+static int __remove_pg_mapping(struct rb_root *root, struct ceph_pg pgid)
+{
+	struct ceph_pg_mapping *pg = __lookup_pg_mapping(root, pgid);
+
+	if (pg) {
+		dout("__remove_pg_mapping %llx %p\n", *(u64 *)&pgid, pg);
+		rb_erase(&pg->node, root);
+		kfree(pg);
+		return 0;
+	}
+	dout("__remove_pg_mapping %llx dne\n", *(u64 *)&pgid);
+	return -ENOENT;
+}
+
 /*
  * rbtree of pg pool info
  */
@@ -711,7 +729,6 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 	void *start = *p;
 	int err = -EINVAL;
 	u16 version;
-	struct rb_node *rbp;
 
 	ceph_decode_16_safe(p, end, version, bad);
 	if (version > CEPH_OSDMAP_INC_VERSION) {
@@ -861,7 +878,6 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 	}
 
 	/* new_pg_temp */
-	rbp = rb_first(&map->pg_temp);
 	ceph_decode_32_safe(p, end, len, bad);
 	while (len--) {
 		struct ceph_pg_mapping *pg;
@@ -872,18 +888,6 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 		ceph_decode_copy(p, &pgid, sizeof(pgid));
 		pglen = ceph_decode_32(p);
 
-		/* remove any? */
-		while (rbp && pgid_cmp(rb_entry(rbp, struct ceph_pg_mapping,
-						node)->pgid, pgid) <= 0) {
-			struct ceph_pg_mapping *cur =
-				rb_entry(rbp, struct ceph_pg_mapping, node);
-
-			rbp = rb_next(rbp);
-			dout(" removed pg_temp %llx\n", *(u64 *)&cur->pgid);
-			rb_erase(&cur->node, &map->pg_temp);
-			kfree(cur);
-		}
-
 		if (pglen) {
 			/* insert */
 			ceph_decode_need(p, end, pglen*sizeof(u32), bad);
@@ -903,17 +907,11 @@ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
 			}
 			dout(" added pg_temp %llx len %d\n", *(u64 *)&pgid,
 			     pglen);
+		} else {
+			/* remove */
+			__remove_pg_mapping(&map->pg_temp, pgid);
 		}
 	}
-	while (rbp) {
-		struct ceph_pg_mapping *cur =
-			rb_entry(rbp, struct ceph_pg_mapping, node);
-
-		rbp = rb_next(rbp);
-		dout(" removed pg_temp %llx\n", *(u64 *)&cur->pgid);
-		rb_erase(&cur->node, &map->pg_temp);
-		kfree(cur);
-	}
 
 	/* ignore the rest */
 	*p = end;
@@ -1046,10 +1044,25 @@ static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
 	struct ceph_pg_mapping *pg;
 	struct ceph_pg_pool_info *pool;
 	int ruleno;
-	unsigned poolid, ps, pps;
+	unsigned poolid, ps, pps, t;
 	int preferred;
 
+	poolid = le32_to_cpu(pgid.pool);
+	ps = le16_to_cpu(pgid.ps);
+	preferred = (s16)le16_to_cpu(pgid.preferred);
+
+	pool = __lookup_pg_pool(&osdmap->pg_pools, poolid);
+	if (!pool)
+		return NULL;
+
 	/* pg_temp? */
+	if (preferred >= 0)
+		t = ceph_stable_mod(ps, le32_to_cpu(pool->v.lpg_num),
+				    pool->lpgp_num_mask);
+	else
+		t = ceph_stable_mod(ps, le32_to_cpu(pool->v.pg_num),
+				    pool->pgp_num_mask);
+	pgid.ps = cpu_to_le16(t);
 	pg = __lookup_pg_mapping(&osdmap->pg_temp, pgid);
 	if (pg) {
 		*num = pg->len;
@@ -1057,18 +1070,6 @@ static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
 	}
 
 	/* crush */
-	poolid = le32_to_cpu(pgid.pool);
-	ps = le16_to_cpu(pgid.ps);
-	preferred = (s16)le16_to_cpu(pgid.preferred);
-
-	/* don't forcefeed bad device ids to crush */
-	if (preferred >= osdmap->max_osd ||
-	    preferred >= osdmap->crush->max_devices)
-		preferred = -1;
-
-	pool = __lookup_pg_pool(&osdmap->pg_pools, poolid);
-	if (!pool)
-		return NULL;
 	ruleno = crush_find_rule(osdmap->crush, pool->v.crush_ruleset,
 				 pool->v.type, pool->v.size);
 	if (ruleno < 0) {
@@ -1078,6 +1079,11 @@ static int *calc_pg_raw(struct ceph_osdmap *osdmap, struct ceph_pg pgid,
 		return NULL;
 	}
 
+	/* don't forcefeed bad device ids to crush */
+	if (preferred >= osdmap->max_osd ||
+	    preferred >= osdmap->crush->max_devices)
+		preferred = -1;
+
 	if (preferred >= 0)
 		pps = ceph_stable_mod(ps,
 				      le32_to_cpu(pool->v.lpgp_num),
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 705c82886281..def0538e2413 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -696,8 +696,10 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb,
 	int err;
 
 	err = ip6mr_fib_lookup(net, &fl6, &mrt);
-	if (err < 0)
+	if (err < 0) {
+		kfree_skb(skb);
 		return err;
+	}
 
 	read_lock(&mrt_lock);
 	dev->stats.tx_bytes += skb->len;
@@ -2052,8 +2054,10 @@ int ip6_mr_input(struct sk_buff *skb)
 	int err;
 
 	err = ip6mr_fib_lookup(net, &fl6, &mrt);
-	if (err < 0)
+	if (err < 0) {
+		kfree_skb(skb);
 		return err;
+	}
 
 	read_lock(&mrt_lock);
 	cache = ip6mr_cache_find(mrt,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1250f9020670..fb545edef6ea 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -244,7 +244,9 @@ static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops,
 {
 	struct rt6_info *rt = dst_alloc(ops, dev, 0, 0, flags);
 
-	memset(&rt->rt6i_table, 0, sizeof(*rt) - sizeof(struct dst_entry));
+	if (rt != NULL)
+		memset(&rt->rt6i_table, 0,
+			sizeof(*rt) - sizeof(struct dst_entry));
 
 	return rt;
 }
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3c9fa618b69d..79cc6469508d 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1383,6 +1383,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 		newtp->af_specific = &tcp_sock_ipv6_mapped_specific;
 #endif
 
+		newnp->ipv6_ac_list = NULL;
+		newnp->ipv6_fl_list = NULL;
 		newnp->pktoptions  = NULL;
 		newnp->opt	   = NULL;
 		newnp->mcast_oif   = inet6_iif(skb);
@@ -1447,6 +1449,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	   First: no IPv4 options.
 	 */
 	newinet->inet_opt = NULL;
+	newnp->ipv6_ac_list = NULL;
 	newnp->ipv6_fl_list = NULL;
 
 	/* Clone RX bits */
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c698cec0a445..fabb4fafa281 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -961,7 +961,10 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev,
 	return 0;
 
 drop_n_acct:
-	po->stats.tp_drops = atomic_inc_return(&sk->sk_drops);
+	spin_lock(&sk->sk_receive_queue.lock);
+	po->stats.tp_drops++;
+	atomic_inc(&sk->sk_drops);
+	spin_unlock(&sk->sk_receive_queue.lock);
 
 drop_n_restore:
 	if (skb_head != skb->data && skb_shared(skb)) {
diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c
index 8b77edbab272..4e1de171866c 100644
--- a/net/rds/iw_rdma.c
+++ b/net/rds/iw_rdma.c
@@ -84,7 +84,8 @@ static int rds_iw_map_fastreg(struct rds_iw_mr_pool *pool,
 static void rds_iw_free_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr);
 static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool,
 			struct list_head *unmap_list,
-			struct list_head *kill_list);
+			struct list_head *kill_list,
+			int *unpinned);
 static void rds_iw_destroy_fastreg(struct rds_iw_mr_pool *pool, struct rds_iw_mr *ibmr);
 
 static int rds_iw_get_device(struct rds_sock *rs, struct rds_iw_device **rds_iwdev, struct rdma_cm_id **cm_id)
@@ -499,7 +500,7 @@ static int rds_iw_flush_mr_pool(struct rds_iw_mr_pool *pool, int free_all)
 	LIST_HEAD(unmap_list);
 	LIST_HEAD(kill_list);
 	unsigned long flags;
-	unsigned int nfreed = 0, ncleaned = 0, free_goal;
+	unsigned int nfreed = 0, ncleaned = 0, unpinned = 0, free_goal;
 	int ret = 0;
 
 	rds_iw_stats_inc(s_iw_rdma_mr_pool_flush);
@@ -524,7 +525,8 @@ static int rds_iw_flush_mr_pool(struct rds_iw_mr_pool *pool, int free_all)
 	 * will be destroyed by the unmap function.
 	 */
 	if (!list_empty(&unmap_list)) {
-		ncleaned = rds_iw_unmap_fastreg_list(pool, &unmap_list, &kill_list);
+		ncleaned = rds_iw_unmap_fastreg_list(pool, &unmap_list,
+						     &kill_list, &unpinned);
 		/* If we've been asked to destroy all MRs, move those
 		 * that were simply cleaned to the kill list */
 		if (free_all)
@@ -548,6 +550,7 @@ static int rds_iw_flush_mr_pool(struct rds_iw_mr_pool *pool, int free_all)
 		spin_unlock_irqrestore(&pool->list_lock, flags);
 	}
 
+	atomic_sub(unpinned, &pool->free_pinned);
 	atomic_sub(ncleaned, &pool->dirty_count);
 	atomic_sub(nfreed, &pool->item_count);
 
@@ -828,7 +831,8 @@ static void rds_iw_free_fastreg(struct rds_iw_mr_pool *pool,
 
 static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool,
 				struct list_head *unmap_list,
-				struct list_head *kill_list)
+				struct list_head *kill_list,
+				int *unpinned)
 {
 	struct rds_iw_mapping *mapping, *next;
 	unsigned int ncleaned = 0;
@@ -855,6 +859,7 @@ static unsigned int rds_iw_unmap_fastreg_list(struct rds_iw_mr_pool *pool,
 
 		spin_lock_irqsave(&pool->list_lock, flags);
 		list_for_each_entry_safe(mapping, next, unmap_list, m_list) {
+			*unpinned += mapping->m_sg.len;
 			list_move(&mapping->m_list, &laundered);
 			ncleaned++;
 		}
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index e83e7fee3bc0..ea40d540a990 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4113,9 +4113,12 @@ static int nl80211_crypto_settings(struct cfg80211_registered_device *rdev,
 		if (len % sizeof(u32))
 			return -EINVAL;
 
+		if (settings->n_akm_suites > NL80211_MAX_NR_AKM_SUITES)
+			return -EINVAL;
+
 		memcpy(settings->akm_suites, data, len);
 
-		for (i = 0; i < settings->n_ciphers_pairwise; i++)
+		for (i = 0; i < settings->n_akm_suites; i++)
 			if (!nl80211_valid_akm_suite(settings->akm_suites[i]))
 				return -EINVAL;
 	}
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 94fdcc7f1030..552df27dcf53 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1349,14 +1349,16 @@ static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family)
 		BUG();
 	}
 	xdst = dst_alloc(dst_ops, NULL, 0, 0, 0);
-	memset(&xdst->u.rt6.rt6i_table, 0, sizeof(*xdst) - sizeof(struct dst_entry));
-	xfrm_policy_put_afinfo(afinfo);
 
-	if (likely(xdst))
+	if (likely(xdst)) {
+		memset(&xdst->u.rt6.rt6i_table, 0,
+			sizeof(*xdst) - sizeof(struct dst_entry));
 		xdst->flo.ops = &xfrm_bundle_fc_ops;
-	else
+	} else
 		xdst = ERR_PTR(-ENOBUFS);
 
+	xfrm_policy_put_afinfo(afinfo);
+
 	return xdst;
 }
 
diff --git a/sound/pci/fm801.c b/sound/pci/fm801.c
index f9123f09e83e..32b02d906703 100644
--- a/sound/pci/fm801.c
+++ b/sound/pci/fm801.c
@@ -68,6 +68,7 @@ MODULE_PARM_DESC(enable, "Enable FM801 soundcard.");
 module_param_array(tea575x_tuner, int, NULL, 0444);
 MODULE_PARM_DESC(tea575x_tuner, "TEA575x tuner access method (0 = auto, 1 = SF256-PCS, 2=SF256-PCP, 3=SF64-PCR, 8=disable, +16=tuner-only).");
 
+#define TUNER_DISABLED		(1<<3)
 #define TUNER_ONLY		(1<<4)
 #define TUNER_TYPE_MASK		(~TUNER_ONLY & 0xFFFF)
 
@@ -1150,7 +1151,8 @@ static int snd_fm801_free(struct fm801 *chip)
 
       __end_hw:
 #ifdef CONFIG_SND_FM801_TEA575X_BOOL
-	snd_tea575x_exit(&chip->tea);
+	if (!(chip->tea575x_tuner & TUNER_DISABLED))
+		snd_tea575x_exit(&chip->tea);
 #endif
 	if (chip->irq >= 0)
 		free_irq(chip->irq, chip);
@@ -1236,7 +1238,6 @@ static int __devinit snd_fm801_create(struct snd_card *card,
 	    (tea575x_tuner & TUNER_TYPE_MASK) < 4) {
 		if (snd_tea575x_init(&chip->tea)) {
 			snd_printk(KERN_ERR "TEA575x radio not found\n");
-			snd_fm801_free(chip);
 			return -ENODEV;
 		}
 	} else if ((tea575x_tuner & TUNER_TYPE_MASK) == 0) {
@@ -1251,11 +1252,15 @@ static int __devinit snd_fm801_create(struct snd_card *card,
 		}
 		if (tea575x_tuner == 4) {
 			snd_printk(KERN_ERR "TEA575x radio not found\n");
-			snd_fm801_free(chip);
-			return -ENODEV;
+			chip->tea575x_tuner = TUNER_DISABLED;
 		}
 	}
-	strlcpy(chip->tea.card, snd_fm801_tea575x_gpios[(tea575x_tuner & TUNER_TYPE_MASK) - 1].name, sizeof(chip->tea.card));
+	if (!(chip->tea575x_tuner & TUNER_DISABLED)) {
+		strlcpy(chip->tea.card,
+			snd_fm801_tea575x_gpios[(tea575x_tuner &
+						 TUNER_TYPE_MASK) - 1].name,
+			sizeof(chip->tea.card));
+	}
 #endif
 
 	*rchip = chip;
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index be6982289c0d..e9a2a8795d1b 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1924,7 +1924,8 @@ static unsigned int azx_via_get_position(struct azx *chip,
 }
 
 static unsigned int azx_get_position(struct azx *chip,
-				     struct azx_dev *azx_dev)
+				     struct azx_dev *azx_dev,
+				     bool with_check)
 {
 	unsigned int pos;
 	int stream = azx_dev->substream->stream;
@@ -1940,7 +1941,7 @@ static unsigned int azx_get_position(struct azx *chip,
 	default:
 		/* use the position buffer */
 		pos = le32_to_cpu(*azx_dev->posbuf);
-		if (chip->position_fix[stream] == POS_FIX_AUTO) {
+		if (with_check && chip->position_fix[stream] == POS_FIX_AUTO) {
 			if (!pos || pos == (u32)-1) {
 				printk(KERN_WARNING
 				       "hda-intel: Invalid position buffer, "
@@ -1964,7 +1965,7 @@ static snd_pcm_uframes_t azx_pcm_pointer(struct snd_pcm_substream *substream)
 	struct azx *chip = apcm->chip;
 	struct azx_dev *azx_dev = get_azx_dev(substream);
 	return bytes_to_frames(substream->runtime,
-			       azx_get_position(chip, azx_dev));
+			       azx_get_position(chip, azx_dev, false));
 }
 
 /*
@@ -1987,7 +1988,7 @@ static int azx_position_ok(struct azx *chip, struct azx_dev *azx_dev)
 		return -1;	/* bogus (too early) interrupt */
 
 	stream = azx_dev->substream->stream;
-	pos = azx_get_position(chip, azx_dev);
+	pos = azx_get_position(chip, azx_dev, true);
 
 	if (WARN_ONCE(!azx_dev->period_bytes,
 		      "hda-intel: zero azx_dev->period_bytes"))
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 0503c999e7d3..7a73621a8909 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -578,6 +578,10 @@ static void alc_line_automute(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
 
+	/* check LO jack only when it's different from HP */
+	if (spec->autocfg.line_out_pins[0] == spec->autocfg.hp_pins[0])
+		return;
+
 	spec->line_jack_present =
 		detect_jacks(codec, ARRAY_SIZE(spec->autocfg.line_out_pins),
 			     spec->autocfg.line_out_pins);
@@ -1321,7 +1325,9 @@ do_sku:
 	 * 15   : 1 --> enable the function "Mute internal speaker
 	 *	        when the external headphone out jack is plugged"
 	 */
-	if (!spec->autocfg.hp_pins[0]) {
+	if (!spec->autocfg.hp_pins[0] &&
+	    !(spec->autocfg.line_out_pins[0] &&
+	      spec->autocfg.line_out_type == AUTO_PIN_HP_OUT)) {
 		hda_nid_t nid;
 		tmp = (ass >> 11) & 0x3;	/* HP to chassis */
 		if (tmp == 0)
diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 1b7c11432aa7..987e3cf71a0b 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -5630,6 +5630,7 @@ again:
 	switch (codec->vendor_id) {
 	case 0x111d76d1:
 	case 0x111d76d9:
+	case 0x111d76df:
 	case 0x111d76e5:
 	case 0x111d7666:
 	case 0x111d7667:
diff --git a/sound/soc/blackfin/bf5xx-ad73311.c b/sound/soc/blackfin/bf5xx-ad73311.c
index 732a247f2527..b94eb7ef7d16 100644
--- a/sound/soc/blackfin/bf5xx-ad73311.c
+++ b/sound/soc/blackfin/bf5xx-ad73311.c
@@ -128,7 +128,7 @@ static int snd_ad73311_configure(void)
 	return 0;
 }
 
-static int bf5xx_probe(struct platform_device *pdev)
+static int bf5xx_probe(struct snd_soc_card *card)
 {
 	int err;
 	if (gpio_request(GPIO_SE, "AD73311_SE")) {
diff --git a/sound/soc/codecs/ssm2602.c b/sound/soc/codecs/ssm2602.c
index 84f4ad568556..9801cd7cfcb5 100644
--- a/sound/soc/codecs/ssm2602.c
+++ b/sound/soc/codecs/ssm2602.c
@@ -431,7 +431,8 @@ static int ssm2602_set_dai_fmt(struct snd_soc_dai *codec_dai,
 static int ssm2602_set_bias_level(struct snd_soc_codec *codec,
 				 enum snd_soc_bias_level level)
 {
-	u16 reg = snd_soc_read(codec, SSM2602_PWR) & 0xff7f;
+	u16 reg = snd_soc_read(codec, SSM2602_PWR);
+	reg &= ~(PWR_POWER_OFF | PWR_OSC_PDN);
 
 	switch (level) {
 	case SND_SOC_BIAS_ON:
diff --git a/sound/soc/codecs/wm8753.c b/sound/soc/codecs/wm8753.c
index ffa2ffe5ec11..aa091a0d8187 100644
--- a/sound/soc/codecs/wm8753.c
+++ b/sound/soc/codecs/wm8753.c
@@ -1454,8 +1454,8 @@ static int wm8753_probe(struct snd_soc_codec *codec)
 	/* set the update bits */
 	snd_soc_update_bits(codec, WM8753_LDAC, 0x0100, 0x0100);
 	snd_soc_update_bits(codec, WM8753_RDAC, 0x0100, 0x0100);
-	snd_soc_update_bits(codec, WM8753_LDAC, 0x0100, 0x0100);
-	snd_soc_update_bits(codec, WM8753_RDAC, 0x0100, 0x0100);
+	snd_soc_update_bits(codec, WM8753_LADC, 0x0100, 0x0100);
+	snd_soc_update_bits(codec, WM8753_RADC, 0x0100, 0x0100);
 	snd_soc_update_bits(codec, WM8753_LOUT1V, 0x0100, 0x0100);
 	snd_soc_update_bits(codec, WM8753_ROUT1V, 0x0100, 0x0100);
 	snd_soc_update_bits(codec, WM8753_LOUT2V, 0x0100, 0x0100);
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index 1725550c293e..d2c315fa1b9b 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -3479,31 +3479,6 @@ int wm8962_mic_detect(struct snd_soc_codec *codec, struct snd_soc_jack *jack)
 }
 EXPORT_SYMBOL_GPL(wm8962_mic_detect);
 
-#ifdef CONFIG_PM
-static int wm8962_resume(struct snd_soc_codec *codec)
-{
-	u16 *reg_cache = codec->reg_cache;
-	int i;
-
-	/* Restore the registers */
-	for (i = 1; i < codec->driver->reg_cache_size; i++) {
-		switch (i) {
-		case WM8962_SOFTWARE_RESET:
-			continue;
-		default:
-			break;
-		}
-
-		if (reg_cache[i] != wm8962_reg[i])
-			snd_soc_write(codec, i, reg_cache[i]);
-	}
-
-	return 0;
-}
-#else
-#define wm8962_resume NULL
-#endif
-
 #if defined(CONFIG_INPUT) || defined(CONFIG_INPUT_MODULE)
 static int beep_rates[] = {
 	500, 1000, 2000, 4000,
@@ -4015,7 +3990,6 @@ static int wm8962_remove(struct snd_soc_codec *codec)
 static struct snd_soc_codec_driver soc_codec_dev_wm8962 = {
 	.probe =	wm8962_probe,
 	.remove =	wm8962_remove,
-	.resume =	wm8962_resume,
 	.set_bias_level = wm8962_set_bias_level,
 	.reg_cache_size = WM8962_MAX_REGISTER + 1,
 	.reg_word_size = sizeof(u16),
diff --git a/sound/soc/omap/mcpdm.c b/sound/soc/omap/mcpdm.c
index 928f03707451..50e59194ad81 100644
--- a/sound/soc/omap/mcpdm.c
+++ b/sound/soc/omap/mcpdm.c
@@ -449,7 +449,7 @@ exit:
 	return ret;
 }
 
-int __devexit omap_mcpdm_remove(struct platform_device *pdev)
+int omap_mcpdm_remove(struct platform_device *pdev)
 {
 	struct omap_mcpdm *mcpdm_ptr = platform_get_drvdata(pdev);
 
diff --git a/sound/soc/omap/mcpdm.h b/sound/soc/omap/mcpdm.h
index df3e16fb51f3..20c20a8649fe 100644
--- a/sound/soc/omap/mcpdm.h
+++ b/sound/soc/omap/mcpdm.h
@@ -150,4 +150,4 @@ extern int omap_mcpdm_request(void);
 extern void omap_mcpdm_free(void);
 extern int omap_mcpdm_set_offset(int offset1, int offset2);
 int __devinit omap_mcpdm_probe(struct platform_device *pdev);
-int __devexit omap_mcpdm_remove(struct platform_device *pdev);
+int omap_mcpdm_remove(struct platform_device *pdev);
diff --git a/sound/soc/omap/omap-mcbsp.c b/sound/soc/omap/omap-mcbsp.c
index ebcc2d4d2b18..478d60778453 100644
--- a/sound/soc/omap/omap-mcbsp.c
+++ b/sound/soc/omap/omap-mcbsp.c
@@ -516,6 +516,12 @@ static int omap_mcbsp_dai_set_dai_sysclk(struct snd_soc_dai *cpu_dai,
 	struct omap_mcbsp_reg_cfg *regs = &mcbsp_data->regs;
 	int err = 0;
 
+	if (mcbsp_data->active)
+		if (freq == mcbsp_data->in_freq)
+			return 0;
+		else
+			return -EBUSY;
+
 	/* The McBSP signal muxing functions are only available on McBSP1 */
 	if (clk_id == OMAP_MCBSP_CLKR_SRC_CLKR ||
 	    clk_id == OMAP_MCBSP_CLKR_SRC_CLKX ||
diff --git a/sound/soc/pxa/zylonite.c b/sound/soc/pxa/zylonite.c
index b6445757fc54..2b8350b52232 100644
--- a/sound/soc/pxa/zylonite.c
+++ b/sound/soc/pxa/zylonite.c
@@ -196,20 +196,20 @@ static int zylonite_probe(struct snd_soc_card *card)
 	if (clk_pout) {
 		pout = clk_get(NULL, "CLK_POUT");
 		if (IS_ERR(pout)) {
-			dev_err(&pdev->dev, "Unable to obtain CLK_POUT: %ld\n",
+			dev_err(card->dev, "Unable to obtain CLK_POUT: %ld\n",
 				PTR_ERR(pout));
 			return PTR_ERR(pout);
 		}
 
 		ret = clk_enable(pout);
 		if (ret != 0) {
-			dev_err(&pdev->dev, "Unable to enable CLK_POUT: %d\n",
+			dev_err(card->dev, "Unable to enable CLK_POUT: %d\n",
 				ret);
 			clk_put(pout);
 			return ret;
 		}
 
-		dev_dbg(&pdev->dev, "MCLK enabled at %luHz\n",
+		dev_dbg(card->dev, "MCLK enabled at %luHz\n",
 			clk_get_rate(pout));
 	}
 
@@ -241,7 +241,7 @@ static int zylonite_resume_pre(struct snd_soc_card *card)
 	if (clk_pout) {
 		ret = clk_enable(pout);
 		if (ret != 0)
-			dev_err(&pdev->dev, "Unable to enable CLK_POUT: %d\n",
+			dev_err(card->dev, "Unable to enable CLK_POUT: %d\n",
 				ret);
 	}
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index d2ef014af215..ef69f5a02709 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -30,6 +30,7 @@
 #include <linux/bitops.h>
 #include <linux/debugfs.h>
 #include <linux/platform_device.h>
+#include <linux/ctype.h>
 #include <linux/slab.h>
 #include <sound/ac97_codec.h>
 #include <sound/core.h>
@@ -1434,9 +1435,20 @@ static void snd_soc_instantiate_card(struct snd_soc_card *card)
 		 "%s", card->name);
 	snprintf(card->snd_card->longname, sizeof(card->snd_card->longname),
 		 "%s", card->long_name ? card->long_name : card->name);
-	if (card->driver_name)
-		strlcpy(card->snd_card->driver, card->driver_name,
-			sizeof(card->snd_card->driver));
+	snprintf(card->snd_card->driver, sizeof(card->snd_card->driver),
+		 "%s", card->driver_name ? card->driver_name : card->name);
+	for (i = 0; i < ARRAY_SIZE(card->snd_card->driver); i++) {
+		switch (card->snd_card->driver[i]) {
+		case '_':
+		case '-':
+		case '\0':
+			break;
+		default:
+			if (!isalnum(card->snd_card->driver[i]))
+				card->snd_card->driver[i] = '_';
+			break;
+		}
+	}
 
 	if (card->late_probe) {
 		ret = card->late_probe(card);
diff --git a/sound/usb/card.c b/sound/usb/card.c
index 781d9e61adfb..d8f2bf401458 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -530,8 +530,11 @@ snd_usb_audio_probe(struct usb_device *dev,
 	return chip;
 
  __error:
-	if (chip && !chip->num_interfaces)
-		snd_card_free(chip->card);
+	if (chip) {
+		if (!chip->num_interfaces)
+			snd_card_free(chip->card);
+		chip->probing = 0;
+	}
 	mutex_unlock(&register_mutex);
  __err_val:
 	return NULL;
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index 98a31e3181a5..0102d83600db 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -83,6 +83,9 @@ OPTIONS
 --symfs=<directory>::
         Look for files with symbols relative to this directory.
 
+-M::
+--disassembler-style=:: Set disassembler style for objdump.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1]
diff --git a/tools/perf/Documentation/perf-buildid-list.txt b/tools/perf/Documentation/perf-buildid-list.txt
index 5eaac6f26d51..cc22325ffd1b 100644
--- a/tools/perf/Documentation/perf-buildid-list.txt
+++ b/tools/perf/Documentation/perf-buildid-list.txt
@@ -16,6 +16,9 @@ This command displays the buildids found in a perf.data file, so that other
 tools can be used to fetch packages with matching symbol tables for use by
 perf report.
 
+It can also be used to show the build id of the running kernel or in an ELF
+file using -i/--input.
+
 OPTIONS
 -------
 -H::
@@ -27,6 +30,9 @@ OPTIONS
 -f::
 --force::
 	Don't do ownership validation.
+-k::
+--kernel::
+	Show running kernel build id.
 -v::
 --verbose::
 	Be more verbose.
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 04253c07d19a..6349b6c0e3ec 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -134,6 +134,9 @@ OPTIONS
 	CPUs are specified with -: 0-2. Default is to report samples on all
 	CPUs.
 
+-M::
+--disassembler-style=:: Set disassembler style for objdump.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1]
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index 46822d5fde1c..5b212b57f70b 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -8,7 +8,7 @@ perf-sched - Tool to trace/measure scheduler properties (latencies)
 SYNOPSIS
 --------
 [verse]
-'perf sched' {record|latency|map|replay|trace}
+'perf sched' {record|latency|map|replay|script}
 
 DESCRIPTION
 -----------
@@ -20,8 +20,8 @@ There are five variants of perf sched:
   'perf sched latency' to report the per task scheduling latencies
   and other scheduling properties of the workload.
 
-  'perf sched trace' to see a detailed trace of the workload that
-  was recorded.
+  'perf sched script' to see a detailed trace of the workload that
+   was recorded (aliased to 'perf script' for now).
 
   'perf sched replay' to simulate the workload that was recorded
   via perf sched record. (this is done by starting up mockup threads
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 08394c4879a8..8966b9ab2014 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -95,12 +95,21 @@ corresponding events, i.e., they always refer to events defined earlier on the c
 line.
 
 -o file::
--output file::
+--output file::
 Print the output into the designated file.
 
 --append::
 Append to the output file designated with the -o option. Ignored if -o is not specified.
 
+--log-fd::
+
+Log output to fd, instead of stderr.  Complementary to --output, and mutually exclusive
+with it.  --append may be used here.  Examples:
+     3>results  perf stat --log-fd 3          -- $cmd
+     3>>results perf stat --log-fd 3 --append -- $cmd
+
+
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 3b8f7b80376b..e9d5c271db69 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -30,6 +30,8 @@ endif
 # Define EXTRA_CFLAGS=-m64 or EXTRA_CFLAGS=-m32 as appropriate for cross-builds.
 #
 # Define NO_DWARF if you do not want debug-info analysis feature at all.
+#
+# Define WERROR=0 to disable treating any warnings as errors.
 
 $(OUTPUT)PERF-VERSION-FILE: .FORCE-PERF-VERSION-FILE
 	@$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
@@ -63,6 +65,11 @@ ifeq ($(ARCH),x86_64)
 	endif
 endif
 
+# Treat warnings as errors unless directed not to
+ifneq ($(WERROR),0)
+	CFLAGS_WERROR := -Werror
+endif
+
 #
 # Include saner warnings here, which can catch bugs:
 #
@@ -95,7 +102,7 @@ ifndef PERF_DEBUG
   CFLAGS_OPTIMIZE = -O6
 endif
 
-CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 -Werror $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
+CFLAGS = -fno-omit-frame-pointer -ggdb3 -Wall -Wextra -std=gnu99 $(CFLAGS_WERROR) $(CFLAGS_OPTIMIZE) -D_FORTIFY_SOURCE=2 $(EXTRA_WARNINGS) $(EXTRA_CFLAGS)
 EXTLIBS = -lpthread -lrt -lelf -lm
 ALL_CFLAGS = $(CFLAGS) -D_LARGEFILE64_SOURCE -D_FILE_OFFSET_BITS=64
 ALL_LDFLAGS = $(LDFLAGS)
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index c5be28851f01..cf68819f7453 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -273,6 +273,8 @@ static const struct option options[] = {
 		    "Interleave source code with assembly code (default)"),
 	OPT_BOOLEAN('0', "asm-raw", &symbol_conf.annotate_asm_raw,
 		    "Display raw encoding of assembly instructions (default)"),
+	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
+		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-buildid-list.c b/tools/perf/builtin-buildid-list.c
index 5af32ae9031e..cb690a65bf02 100644
--- a/tools/perf/builtin-buildid-list.c
+++ b/tools/perf/builtin-buildid-list.c
@@ -1,7 +1,8 @@
 /*
  * builtin-buildid-list.c
  *
- * Builtin buildid-list command: list buildids in perf.data
+ * Builtin buildid-list command: list buildids in perf.data, in the running
+ * kernel and in ELF files.
  *
  * Copyright (C) 2009, Red Hat Inc.
  * Copyright (C) 2009, Arnaldo Carvalho de Melo <acme@redhat.com>
@@ -15,8 +16,11 @@
 #include "util/session.h"
 #include "util/symbol.h"
 
+#include <libelf.h>
+
 static char const *input_name = "perf.data";
 static bool force;
+static bool show_kernel;
 static bool with_hits;
 
 static const char * const buildid_list_usage[] = {
@@ -29,12 +33,13 @@ static const struct option options[] = {
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
 	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
+	OPT_BOOLEAN('k', "kernel", &show_kernel, "Show current kernel build id"),
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose"),
 	OPT_END()
 };
 
-static int __cmd_buildid_list(void)
+static int perf_session__list_build_ids(void)
 {
 	struct perf_session *session;
 
@@ -52,6 +57,49 @@ static int __cmd_buildid_list(void)
 	return 0;
 }
 
+static int sysfs__fprintf_build_id(FILE *fp)
+{
+	u8 kallsyms_build_id[BUILD_ID_SIZE];
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+	if (sysfs__read_build_id("/sys/kernel/notes", kallsyms_build_id,
+				 sizeof(kallsyms_build_id)) != 0)
+		return -1;
+
+	build_id__sprintf(kallsyms_build_id, sizeof(kallsyms_build_id),
+			  sbuild_id);
+	fprintf(fp, "%s\n", sbuild_id);
+	return 0;
+}
+
+static int filename__fprintf_build_id(const char *name, FILE *fp)
+{
+	u8 build_id[BUILD_ID_SIZE];
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+	if (filename__read_build_id(name, build_id,
+				    sizeof(build_id)) != sizeof(build_id))
+		return 0;
+
+	build_id__sprintf(build_id, sizeof(build_id), sbuild_id);
+	return fprintf(fp, "%s\n", sbuild_id);
+}
+
+static int __cmd_buildid_list(void)
+{
+	if (show_kernel)
+		return sysfs__fprintf_build_id(stdout);
+
+	elf_version(EV_CURRENT);
+	/*
+ 	 * See if this is an ELF file first:
+ 	 */
+	if (filename__fprintf_build_id(input_name, stdout))
+		return 0;
+
+	return perf_session__list_build_ids();
+}
+
 int cmd_buildid_list(int argc, const char **argv, const char *prefix __used)
 {
 	argc = parse_options(argc, argv, options, buildid_list_usage, 0);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 6b0519f885e4..dd6467872f60 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -73,6 +73,7 @@ static off_t			post_processing_offset;
 
 static struct perf_session	*session;
 static const char		*cpu_list;
+static const char               *progname;
 
 static void advance_output(size_t size)
 {
@@ -137,17 +138,29 @@ static void mmap_read(struct perf_mmap *md)
 
 static volatile int done = 0;
 static volatile int signr = -1;
+static volatile int child_finished = 0;
 
 static void sig_handler(int sig)
 {
+	if (sig == SIGCHLD)
+		child_finished = 1;
+
 	done = 1;
 	signr = sig;
 }
 
 static void sig_atexit(void)
 {
-	if (child_pid > 0)
-		kill(child_pid, SIGTERM);
+	int status;
+
+	if (child_pid > 0) {
+		if (!child_finished)
+			kill(child_pid, SIGTERM);
+
+		wait(&status);
+		if (WIFSIGNALED(status))
+			psignal(WTERMSIG(status), progname);
+	}
 
 	if (signr == -1 || signr == SIGUSR1)
 		return;
@@ -161,6 +174,7 @@ static void config_attr(struct perf_evsel *evsel, struct perf_evlist *evlist)
 	struct perf_event_attr *attr = &evsel->attr;
 	int track = !evsel->idx; /* only the first counter needs these */
 
+	attr->disabled		= 1;
 	attr->inherit		= !no_inherit;
 	attr->read_format	= PERF_FORMAT_TOTAL_TIME_ENABLED |
 				  PERF_FORMAT_TOTAL_TIME_RUNNING |
@@ -445,6 +459,8 @@ static int __cmd_record(int argc, const char **argv)
 	char buf;
 	struct machine *machine;
 
+	progname = argv[0];
+
 	page_size = sysconf(_SC_PAGE_SIZE);
 
 	atexit(sig_atexit);
@@ -671,6 +687,8 @@ static int __cmd_record(int argc, const char **argv)
 		}
 	}
 
+	perf_evlist__enable(evsel_list);
+
 	/*
 	 * Let the child rip
 	 */
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index d7ff277bdb78..3d58334909a5 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -229,10 +229,7 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 
 	list_for_each_entry(pos, &evlist->entries, node) {
 		struct hists *hists = &pos->hists;
-		const char *evname = NULL;
-
-		if (rb_first(&hists->entries) != rb_last(&hists->entries))
-			evname = event_name(pos);
+		const char *evname = event_name(pos);
 
 		hists__fprintf_nr_sample_events(hists, evname, stdout);
 		hists__fprintf(hists, NULL, false, stdout);
@@ -487,6 +484,8 @@ static const struct option options[] = {
 	OPT_STRING(0, "symfs", &symbol_conf.symfs, "directory",
 		    "Look for files with symbols relative to this directory"),
 	OPT_STRING('c', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
+	OPT_STRING('M', "disassembler-style", &disassembler_style, "disassembler style",
+		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_END()
 };
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index bec64a9e741c..7ce65f52415e 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -196,6 +196,7 @@ static bool			csv_output			= false;
 static bool			group				= false;
 static const char		*output_name			= NULL;
 static FILE			*output				= NULL;
+static int			output_fd;
 
 static volatile int done = 0;
 
@@ -253,8 +254,13 @@ static double avg_stats(struct stats *stats)
  */
 static double stddev_stats(struct stats *stats)
 {
-	double variance = stats->M2 / (stats->n - 1);
-	double variance_mean = variance / stats->n;
+	double variance, variance_mean;
+
+	if (!stats->n)
+		return 0.0;
+
+	variance = stats->M2 / (stats->n - 1);
+	variance_mean = variance / stats->n;
 
 	return sqrt(variance_mean);
 }
@@ -489,6 +495,8 @@ static int run_perf_stat(int argc __used, const char **argv)
 	if (forks) {
 		close(go_pipe[1]);
 		wait(&status);
+		if (WIFSIGNALED(status))
+			psignal(WTERMSIG(status), argv[0]);
 	} else {
 		while(!done) sleep(1);
 	}
@@ -522,7 +530,7 @@ static void print_noise_pct(double total, double avg)
 
 	if (csv_output)
 		fprintf(output, "%s%.2f%%", csv_sep, pct);
-	else
+	else if (pct)
 		fprintf(output, "  ( +-%6.2f%% )", pct);
 }
 
@@ -1080,6 +1088,8 @@ static const struct option options[] = {
 	OPT_STRING('o', "output", &output_name, "file",
 		    "output file name"),
 	OPT_BOOLEAN(0, "append", &append_file, "append to the output file"),
+	OPT_INTEGER(0, "log-fd", &output_fd,
+		    "log output to fd, instead of stderr"),
 	OPT_END()
 };
 
@@ -1166,6 +1176,10 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 	if (output_name && strcmp(output_name, "-"))
 		output = NULL;
 
+	if (output_name && output_fd) {
+		fprintf(stderr, "cannot use both --output and --log-fd\n");
+		usage_with_options(stat_usage, options);
+	}
 	if (!output) {
 		struct timespec tm;
 		mode = append_file ? "a" : "w";
@@ -1177,18 +1191,27 @@ int cmd_stat(int argc, const char **argv, const char *prefix __used)
 		}
 		clock_gettime(CLOCK_REALTIME, &tm);
 		fprintf(output, "# started on %s\n", ctime(&tm.tv_sec));
+	} else if (output_fd != 2) {
+		mode = append_file ? "a" : "w";
+		output = fdopen(output_fd, mode);
+		if (!output) {
+			perror("Failed opening logfd");
+			return -errno;
+		}
 	}
 
-	if (csv_sep)
+	if (csv_sep) {
 		csv_output = true;
-	else
+		if (!strcmp(csv_sep, "\\t"))
+			csv_sep = "\t";
+	} else
 		csv_sep = DEFAULT_SEPARATOR;
 
 	/*
 	 * let the spreadsheet do the pretty-printing
 	 */
 	if (csv_output) {
-		/* User explicitely passed -B? */
+		/* User explicitly passed -B? */
 		if (big_num_opt == 1) {
 			fprintf(stderr, "-B option not supported with -x\n");
 			usage_with_options(stat_usage, options);
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index 55f4c76f2821..efe696f936e2 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -561,7 +561,7 @@ static int test__basic_mmap(void)
 		}
 
 		err = perf_event__parse_sample(event, attr.sample_type, sample_size,
-					       false, &sample);
+					       false, &sample, false);
 		if (err) {
 			pr_err("Can't parse sample, err = %d\n", err);
 			goto out_munmap;
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index a43433f08300..5ede7d7c9239 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -191,7 +191,8 @@ static void __zero_source_counters(struct sym_entry *syme)
 	symbol__annotate_zero_histograms(sym);
 }
 
-static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip)
+static void record_precise_ip(struct sym_entry *syme, struct map *map,
+			      int counter, u64 ip)
 {
 	struct annotation *notes;
 	struct symbol *sym;
@@ -205,8 +206,8 @@ static void record_precise_ip(struct sym_entry *syme, int counter, u64 ip)
 	if (pthread_mutex_trylock(&notes->lock))
 		return;
 
-	ip = syme->map->map_ip(syme->map, ip);
-	symbol__inc_addr_samples(sym, syme->map, counter, ip);
+	ip = map->map_ip(map, ip);
+	symbol__inc_addr_samples(sym, map, counter, ip);
 
 	pthread_mutex_unlock(&notes->lock);
 }
@@ -250,7 +251,7 @@ static void __list_insert_active_sym(struct sym_entry *syme)
 	list_add(&syme->node, &top.active_symbols);
 }
 
-static void print_sym_table(struct perf_session *session)
+static void print_sym_table(void)
 {
 	char bf[160];
 	int printed = 0;
@@ -270,10 +271,11 @@ static void print_sym_table(struct perf_session *session)
 
 	printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
 
-	if (session->hists.stats.total_lost != 0) {
+	if (top.total_lost_warned != top.session->hists.stats.total_lost) {
+		top.total_lost_warned = top.session->hists.stats.total_lost;
 		color_fprintf(stdout, PERF_COLOR_RED, "WARNING:");
 		printf(" LOST %" PRIu64 " events, Check IO/CPU overload\n",
-		       session->hists.stats.total_lost);
+		       top.total_lost_warned);
 	}
 
 	if (top.sym_filter_entry) {
@@ -474,7 +476,7 @@ static int key_mapped(int c)
 	return 0;
 }
 
-static void handle_keypress(struct perf_session *session, int c)
+static void handle_keypress(int c)
 {
 	if (!key_mapped(c)) {
 		struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
@@ -550,7 +552,7 @@ static void handle_keypress(struct perf_session *session, int c)
 		case 'Q':
 			printf("exiting.\n");
 			if (dump_symtab)
-				perf_session__fprintf_dsos(session, stderr);
+				perf_session__fprintf_dsos(top.session, stderr);
 			exit(0);
 		case 's':
 			prompt_symbol(&top.sym_filter_entry, "Enter details symbol");
@@ -602,7 +604,6 @@ static void *display_thread(void *arg __used)
 	struct pollfd stdin_poll = { .fd = 0, .events = POLLIN };
 	struct termios tc, save;
 	int delay_msecs, c;
-	struct perf_session *session = (struct perf_session *) arg;
 
 	tcgetattr(0, &save);
 	tc = save;
@@ -617,13 +618,13 @@ repeat:
 	getc(stdin);
 
 	do {
-		print_sym_table(session);
+		print_sym_table();
 	} while (!poll(&stdin_poll, 1, delay_msecs) == 1);
 
 	c = getc(stdin);
 	tcsetattr(0, TCSAFLUSH, &save);
 
-	handle_keypress(session, c);
+	handle_keypress(c);
 	goto repeat;
 
 	return NULL;
@@ -810,7 +811,7 @@ static void perf_event__process_sample(const union perf_event *event,
 		evsel = perf_evlist__id2evsel(top.evlist, sample->id);
 		assert(evsel != NULL);
 		syme->count[evsel->idx]++;
-		record_precise_ip(syme, evsel->idx, ip);
+		record_precise_ip(syme, al.map, evsel->idx, ip);
 		pthread_mutex_lock(&top.active_symbols_lock);
 		if (list_empty(&syme->node) || !syme->node.next) {
 			static bool first = true;
@@ -935,27 +936,27 @@ static int __cmd_top(void)
 	 * FIXME: perf_session__new should allow passing a O_MMAP, so that all this
 	 * mmap reading, etc is encapsulated in it. Use O_WRONLY for now.
 	 */
-	struct perf_session *session = perf_session__new(NULL, O_WRONLY, false, false, NULL);
-	if (session == NULL)
+	top.session = perf_session__new(NULL, O_WRONLY, false, false, NULL);
+	if (top.session == NULL)
 		return -ENOMEM;
 
 	if (top.target_tid != -1)
 		perf_event__synthesize_thread_map(top.evlist->threads,
-						  perf_event__process, session);
+						  perf_event__process, top.session);
 	else
-		perf_event__synthesize_threads(perf_event__process, session);
+		perf_event__synthesize_threads(perf_event__process, top.session);
 
 	start_counters(top.evlist);
-	session->evlist = top.evlist;
-	perf_session__update_sample_type(session);
+	top.session->evlist = top.evlist;
+	perf_session__update_sample_type(top.session);
 
 	/* Wait for a minimal set of events before starting the snapshot */
 	poll(top.evlist->pollfd, top.evlist->nr_fds, 100);
 
-	perf_session__mmap_read(session);
+	perf_session__mmap_read(top.session);
 
 	if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
-							     display_thread), session)) {
+							     display_thread), NULL)) {
 		printf("Could not create display thread.\n");
 		exit(-1);
 	}
@@ -973,7 +974,7 @@ static int __cmd_top(void)
 	while (1) {
 		u64 hits = top.samples;
 
-		perf_session__mmap_read(session);
+		perf_session__mmap_read(top.session);
 
 		if (hits == top.samples)
 			ret = poll(top.evlist->pollfd, top.evlist->nr_fds, 100);
diff --git a/tools/perf/scripts/python/bin/net_dropmonitor-record b/tools/perf/scripts/python/bin/net_dropmonitor-record
new file mode 100755
index 000000000000..423fb81dadae
--- /dev/null
+++ b/tools/perf/scripts/python/bin/net_dropmonitor-record
@@ -0,0 +1,2 @@
+#!/bin/bash
+perf record -e skb:kfree_skb $@
diff --git a/tools/perf/scripts/python/bin/net_dropmonitor-report b/tools/perf/scripts/python/bin/net_dropmonitor-report
new file mode 100755
index 000000000000..8d698f5a06aa
--- /dev/null
+++ b/tools/perf/scripts/python/bin/net_dropmonitor-report
@@ -0,0 +1,4 @@
+#!/bin/bash
+# description: display a table of dropped frames
+
+perf script -s "$PERF_EXEC_PATH"/scripts/python/net_dropmonitor.py $@
diff --git a/tools/perf/scripts/python/net_dropmonitor.py b/tools/perf/scripts/python/net_dropmonitor.py
new file mode 100755
index 000000000000..a4ffc9500023
--- /dev/null
+++ b/tools/perf/scripts/python/net_dropmonitor.py
@@ -0,0 +1,72 @@
+# Monitor the system for dropped packets and proudce a report of drop locations and counts
+
+import os
+import sys
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+		'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+from perf_trace_context import *
+from Core import *
+from Util import *
+
+drop_log = {}
+kallsyms = []
+
+def get_kallsyms_table():
+	global kallsyms
+	try:
+		f = open("/proc/kallsyms", "r")
+		linecount = 0
+		for line in f:
+			linecount = linecount+1
+		f.seek(0)
+	except:
+		return
+
+
+	j = 0
+	for line in f:
+		loc = int(line.split()[0], 16)
+		name = line.split()[2]
+		j = j +1
+		if ((j % 100) == 0):
+			print "\r" + str(j) + "/" + str(linecount),
+		kallsyms.append({ 'loc': loc, 'name' : name})
+
+	print "\r" + str(j) + "/" + str(linecount)
+	kallsyms.sort()
+	return
+
+def get_sym(sloc):
+	loc = int(sloc)
+	for i in kallsyms:
+		if (i['loc'] >= loc):
+			return (i['name'], i['loc']-loc)
+	return (None, 0)
+
+def print_drop_table():
+	print "%25s %25s %25s" % ("LOCATION", "OFFSET", "COUNT")
+	for i in drop_log.keys():
+		(sym, off) = get_sym(i)
+		if sym == None:
+			sym = i
+		print "%25s %25s %25s" % (sym, off, drop_log[i])
+
+
+def trace_begin():
+	print "Starting trace (Ctrl-C to dump results)"
+
+def trace_end():
+	print "Gathering kallsyms data"
+	get_kallsyms_table()
+	print_drop_table()
+
+# called from perf, when it finds a correspoinding event
+def skb__kfree_skb(name, context, cpu, sec, nsec, pid, comm,
+			skbaddr, protocol, location):
+	slocation = str(location)
+	try:
+		drop_log[slocation] = drop_log[slocation] + 1
+	except:
+		drop_log[slocation] = 1
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 01d36ba54053..bc8f4773d4d8 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -16,6 +16,8 @@
 #include "annotate.h"
 #include <pthread.h>
 
+const char 	*disassembler_style;
+
 int symbol__annotate_init(struct map *map __used, struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
@@ -323,9 +325,11 @@ fallback:
 		 dso, dso->long_name, sym, sym->name);
 
 	snprintf(command, sizeof(command),
-		 "objdump --start-address=0x%016" PRIx64
+		 "objdump %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
 		 " -d %s %s -C %s|grep -v %s|expand",
+		 disassembler_style ? "-M " : "",
+		 disassembler_style ? disassembler_style : "",
 		 map__rip_2objdump(map, sym->start),
 		 map__rip_2objdump(map, sym->end),
 		 symbol_conf.annotate_asm_raw ? "" : "--no-show-raw",
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index c2c286896801..6ede1286ee71 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -100,4 +100,6 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map, int evidx,
 			 int refresh);
 #endif
 
+extern const char	*disassembler_style;
+
 #endif	/* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 3c1b8a632101..437f8ca679a0 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -169,12 +169,17 @@ static int perf_event__synthesize_mmap_events(union perf_event *event,
 			continue;
 		pbf += n + 3;
 		if (*pbf == 'x') { /* vm_exec */
+			char anonstr[] = "//anon\n";
 			char *execname = strchr(bf, '/');
 
 			/* Catch VDSO */
 			if (execname == NULL)
 				execname = strstr(bf, "[vdso]");
 
+			/* Catch anonymous mmaps */
+			if ((execname == NULL) && !strstr(bf, "["))
+				execname = anonstr;
+
 			if (execname == NULL)
 				continue;
 
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 1d7f66488a88..357a85b85248 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -186,6 +186,6 @@ const char *perf_event__name(unsigned int id);
 
 int perf_event__parse_sample(const union perf_event *event, u64 type,
 			     int sample_size, bool sample_id_all,
-			     struct perf_sample *sample);
+			     struct perf_sample *sample, bool swapped);
 
 #endif /* __PERF_RECORD_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index c12bd476c6f7..72e9f4886b6d 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -113,6 +113,19 @@ void perf_evlist__disable(struct perf_evlist *evlist)
 	}
 }
 
+void perf_evlist__enable(struct perf_evlist *evlist)
+{
+	int cpu, thread;
+	struct perf_evsel *pos;
+
+	for (cpu = 0; cpu < evlist->cpus->nr; cpu++) {
+		list_for_each_entry(pos, &evlist->entries, node) {
+			for (thread = 0; thread < evlist->threads->nr; thread++)
+				ioctl(FD(pos, cpu, thread), PERF_EVENT_IOC_ENABLE);
+		}
+	}
+}
+
 int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 {
 	int nfds = evlist->cpus->nr * evlist->threads->nr * evlist->nr_entries;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index ce85ae9ae57a..f34915002745 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -54,6 +54,7 @@ int perf_evlist__mmap(struct perf_evlist *evlist, int pages, bool overwrite);
 void perf_evlist__munmap(struct perf_evlist *evlist);
 
 void perf_evlist__disable(struct perf_evlist *evlist);
+void perf_evlist__enable(struct perf_evlist *evlist);
 
 static inline void perf_evlist__set_maps(struct perf_evlist *evlist,
 					 struct cpu_map *cpus,
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index a03a36b7908a..e389815078d3 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -7,6 +7,8 @@
  * Released under the GPL v2. (and only v2, not any later version)
  */
 
+#include <byteswap.h>
+#include "asm/bug.h"
 #include "evsel.h"
 #include "evlist.h"
 #include "util.h"
@@ -342,10 +344,20 @@ static bool sample_overlap(const union perf_event *event,
 
 int perf_event__parse_sample(const union perf_event *event, u64 type,
 			     int sample_size, bool sample_id_all,
-			     struct perf_sample *data)
+			     struct perf_sample *data, bool swapped)
 {
 	const u64 *array;
 
+	/*
+	 * used for cross-endian analysis. See git commit 65014ab3
+	 * for why this goofiness is needed.
+	 */
+	union {
+		u64 val64;
+		u32 val32[2];
+	} u;
+
+
 	data->cpu = data->pid = data->tid = -1;
 	data->stream_id = data->id = data->time = -1ULL;
 
@@ -366,9 +378,16 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_TID) {
-		u32 *p = (u32 *)array;
-		data->pid = p[0];
-		data->tid = p[1];
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+		}
+
+		data->pid = u.val32[0];
+		data->tid = u.val32[1];
 		array++;
 	}
 
@@ -395,8 +414,15 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_CPU) {
-		u32 *p = (u32 *)array;
-		data->cpu = *p;
+
+		u.val64 = *array;
+		if (swapped) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+		}
+
+		data->cpu = u.val32[0];
 		array++;
 	}
 
@@ -423,18 +449,27 @@ int perf_event__parse_sample(const union perf_event *event, u64 type,
 	}
 
 	if (type & PERF_SAMPLE_RAW) {
-		u32 *p = (u32 *)array;
+		const u64 *pdata;
+
+		u.val64 = *array;
+		if (WARN_ONCE(swapped,
+			      "Endianness of raw data not corrected!\n")) {
+			/* undo swap of u64, then swap on individual u32s */
+			u.val64 = bswap_64(u.val64);
+			u.val32[0] = bswap_32(u.val32[0]);
+			u.val32[1] = bswap_32(u.val32[1]);
+		}
 
 		if (sample_overlap(event, array, sizeof(u32)))
 			return -EFAULT;
 
-		data->raw_size = *p;
-		p++;
+		data->raw_size = u.val32[0];
+		pdata = (void *) array + sizeof(u32);
 
-		if (sample_overlap(event, p, data->raw_size))
+		if (sample_overlap(event, pdata, data->raw_size))
 			return -EFAULT;
 
-		data->raw_data = p;
+		data->raw_data = (void *) pdata;
 	}
 
 	return 0;
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index a16ecab5229d..9cf0d4393c8d 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -18,6 +18,13 @@ static inline int is_anon_memory(const char *filename)
 	return strcmp(filename, "//anon") == 0;
 }
 
+static inline int is_no_dso_memory(const char *filename)
+{
+	return !strcmp(filename, "[stack]") ||
+	       !strcmp(filename, "[vdso]")  ||
+	       !strcmp(filename, "[heap]");
+}
+
 void map__init(struct map *self, enum map_type type,
 	       u64 start, u64 end, u64 pgoff, struct dso *dso)
 {
@@ -42,9 +49,10 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 	if (self != NULL) {
 		char newfilename[PATH_MAX];
 		struct dso *dso;
-		int anon;
+		int anon, no_dso;
 
 		anon = is_anon_memory(filename);
+		no_dso = is_no_dso_memory(filename);
 
 		if (anon) {
 			snprintf(newfilename, sizeof(newfilename), "/tmp/perf-%d.map", pid);
@@ -57,12 +65,16 @@ struct map *map__new(struct list_head *dsos__list, u64 start, u64 len,
 
 		map__init(self, type, start, start + len, pgoff, dso);
 
-		if (anon) {
-set_identity:
+		if (anon || no_dso) {
 			self->map_ip = self->unmap_ip = identity__map_ip;
-		} else if (strcmp(filename, "[vdso]") == 0) {
-			dso__set_loaded(dso, self->type);
-			goto set_identity;
+
+			/*
+			 * Set memory without DSO as loaded. All map__find_*
+			 * functions still return NULL, and we avoid the
+			 * unnecessary map__load warning.
+			 */
+			if (no_dso)
+				dso__set_loaded(dso, self->type);
 		}
 	}
 	return self;
@@ -220,55 +232,55 @@ u64 map__objdump_2ip(struct map *map, u64 addr)
 	return ip;
 }
 
-void map_groups__init(struct map_groups *self)
+void map_groups__init(struct map_groups *mg)
 {
 	int i;
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		self->maps[i] = RB_ROOT;
-		INIT_LIST_HEAD(&self->removed_maps[i]);
+		mg->maps[i] = RB_ROOT;
+		INIT_LIST_HEAD(&mg->removed_maps[i]);
 	}
-	self->machine = NULL;
+	mg->machine = NULL;
 }
 
-static void maps__delete(struct rb_root *self)
+static void maps__delete(struct rb_root *maps)
 {
-	struct rb_node *next = rb_first(self);
+	struct rb_node *next = rb_first(maps);
 
 	while (next) {
 		struct map *pos = rb_entry(next, struct map, rb_node);
 
 		next = rb_next(&pos->rb_node);
-		rb_erase(&pos->rb_node, self);
+		rb_erase(&pos->rb_node, maps);
 		map__delete(pos);
 	}
 }
 
-static void maps__delete_removed(struct list_head *self)
+static void maps__delete_removed(struct list_head *maps)
 {
 	struct map *pos, *n;
 
-	list_for_each_entry_safe(pos, n, self, node) {
+	list_for_each_entry_safe(pos, n, maps, node) {
 		list_del(&pos->node);
 		map__delete(pos);
 	}
 }
 
-void map_groups__exit(struct map_groups *self)
+void map_groups__exit(struct map_groups *mg)
 {
 	int i;
 
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
-		maps__delete(&self->maps[i]);
-		maps__delete_removed(&self->removed_maps[i]);
+		maps__delete(&mg->maps[i]);
+		maps__delete_removed(&mg->removed_maps[i]);
 	}
 }
 
-void map_groups__flush(struct map_groups *self)
+void map_groups__flush(struct map_groups *mg)
 {
 	int type;
 
 	for (type = 0; type < MAP__NR_TYPES; type++) {
-		struct rb_root *root = &self->maps[type];
+		struct rb_root *root = &mg->maps[type];
 		struct rb_node *next = rb_first(root);
 
 		while (next) {
@@ -280,17 +292,17 @@ void map_groups__flush(struct map_groups *self)
 			 * instance in some hist_entry instances, so
 			 * just move them to a separate list.
 			 */
-			list_add_tail(&pos->node, &self->removed_maps[pos->type]);
+			list_add_tail(&pos->node, &mg->removed_maps[pos->type]);
 		}
 	}
 }
 
-struct symbol *map_groups__find_symbol(struct map_groups *self,
+struct symbol *map_groups__find_symbol(struct map_groups *mg,
 				       enum map_type type, u64 addr,
 				       struct map **mapp,
 				       symbol_filter_t filter)
 {
-	struct map *map = map_groups__find(self, type, addr);
+	struct map *map = map_groups__find(mg, type, addr);
 
 	if (map != NULL) {
 		if (mapp != NULL)
@@ -301,7 +313,7 @@ struct symbol *map_groups__find_symbol(struct map_groups *self,
 	return NULL;
 }
 
-struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
+struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 					       enum map_type type,
 					       const char *name,
 					       struct map **mapp,
@@ -309,7 +321,7 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
 {
 	struct rb_node *nd;
 
-	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
 		struct symbol *sym = map__find_symbol_by_name(pos, name, filter);
 
@@ -323,13 +335,13 @@ struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
 	return NULL;
 }
 
-size_t __map_groups__fprintf_maps(struct map_groups *self,
+size_t __map_groups__fprintf_maps(struct map_groups *mg,
 				  enum map_type type, int verbose, FILE *fp)
 {
 	size_t printed = fprintf(fp, "%s:\n", map_type__name[type]);
 	struct rb_node *nd;
 
-	for (nd = rb_first(&self->maps[type]); nd; nd = rb_next(nd)) {
+	for (nd = rb_first(&mg->maps[type]); nd; nd = rb_next(nd)) {
 		struct map *pos = rb_entry(nd, struct map, rb_node);
 		printed += fprintf(fp, "Map:");
 		printed += map__fprintf(pos, fp);
@@ -342,22 +354,22 @@ size_t __map_groups__fprintf_maps(struct map_groups *self,
 	return printed;
 }
 
-size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp)
+size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp)
 {
 	size_t printed = 0, i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_maps(self, i, verbose, fp);
+		printed += __map_groups__fprintf_maps(mg, i, verbose, fp);
 	return printed;
 }
 
-static size_t __map_groups__fprintf_removed_maps(struct map_groups *self,
+static size_t __map_groups__fprintf_removed_maps(struct map_groups *mg,
 						 enum map_type type,
 						 int verbose, FILE *fp)
 {
 	struct map *pos;
 	size_t printed = 0;
 
-	list_for_each_entry(pos, &self->removed_maps[type], node) {
+	list_for_each_entry(pos, &mg->removed_maps[type], node) {
 		printed += fprintf(fp, "Map:");
 		printed += map__fprintf(pos, fp);
 		if (verbose > 1) {
@@ -368,26 +380,26 @@ static size_t __map_groups__fprintf_removed_maps(struct map_groups *self,
 	return printed;
 }
 
-static size_t map_groups__fprintf_removed_maps(struct map_groups *self,
+static size_t map_groups__fprintf_removed_maps(struct map_groups *mg,
 					       int verbose, FILE *fp)
 {
 	size_t printed = 0, i;
 	for (i = 0; i < MAP__NR_TYPES; ++i)
-		printed += __map_groups__fprintf_removed_maps(self, i, verbose, fp);
+		printed += __map_groups__fprintf_removed_maps(mg, i, verbose, fp);
 	return printed;
 }
 
-size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp)
+size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp)
 {
-	size_t printed = map_groups__fprintf_maps(self, verbose, fp);
+	size_t printed = map_groups__fprintf_maps(mg, verbose, fp);
 	printed += fprintf(fp, "Removed maps:\n");
-	return printed + map_groups__fprintf_removed_maps(self, verbose, fp);
+	return printed + map_groups__fprintf_removed_maps(mg, verbose, fp);
 }
 
-int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
+int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 				   int verbose, FILE *fp)
 {
-	struct rb_root *root = &self->maps[map->type];
+	struct rb_root *root = &mg->maps[map->type];
 	struct rb_node *next = rb_first(root);
 	int err = 0;
 
@@ -418,7 +430,7 @@ int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
 			}
 
 			before->end = map->start - 1;
-			map_groups__insert(self, before);
+			map_groups__insert(mg, before);
 			if (verbose >= 2)
 				map__fprintf(before, fp);
 		}
@@ -432,7 +444,7 @@ int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
 			}
 
 			after->start = map->end + 1;
-			map_groups__insert(self, after);
+			map_groups__insert(mg, after);
 			if (verbose >= 2)
 				map__fprintf(after, fp);
 		}
@@ -441,7 +453,7 @@ move_map:
 		 * If we have references, just move them to a separate list.
 		 */
 		if (pos->referenced)
-			list_add_tail(&pos->node, &self->removed_maps[map->type]);
+			list_add_tail(&pos->node, &mg->removed_maps[map->type]);
 		else
 			map__delete(pos);
 
@@ -455,7 +467,7 @@ move_map:
 /*
  * XXX This should not really _copy_ te maps, but refcount them.
  */
-int map_groups__clone(struct map_groups *self,
+int map_groups__clone(struct map_groups *mg,
 		      struct map_groups *parent, enum map_type type)
 {
 	struct rb_node *nd;
@@ -464,7 +476,7 @@ int map_groups__clone(struct map_groups *self,
 		struct map *new = map__clone(map);
 		if (new == NULL)
 			return -ENOMEM;
-		map_groups__insert(self, new);
+		map_groups__insert(mg, new);
 	}
 	return 0;
 }
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index b397c0383728..890d85545d0f 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -123,17 +123,17 @@ void map__fixup_end(struct map *self);
 
 void map__reloc_vmlinux(struct map *self);
 
-size_t __map_groups__fprintf_maps(struct map_groups *self,
+size_t __map_groups__fprintf_maps(struct map_groups *mg,
 				  enum map_type type, int verbose, FILE *fp);
 void maps__insert(struct rb_root *maps, struct map *map);
-void maps__remove(struct rb_root *self, struct map *map);
+void maps__remove(struct rb_root *maps, struct map *map);
 struct map *maps__find(struct rb_root *maps, u64 addr);
-void map_groups__init(struct map_groups *self);
-void map_groups__exit(struct map_groups *self);
-int map_groups__clone(struct map_groups *self,
+void map_groups__init(struct map_groups *mg);
+void map_groups__exit(struct map_groups *mg);
+int map_groups__clone(struct map_groups *mg,
 		      struct map_groups *parent, enum map_type type);
-size_t map_groups__fprintf(struct map_groups *self, int verbose, FILE *fp);
-size_t map_groups__fprintf_maps(struct map_groups *self, int verbose, FILE *fp);
+size_t map_groups__fprintf(struct map_groups *mg, int verbose, FILE *fp);
+size_t map_groups__fprintf_maps(struct map_groups *mg, int verbose, FILE *fp);
 
 typedef void (*machine__process_t)(struct machine *self, void *data);
 
@@ -162,29 +162,29 @@ static inline bool machine__is_host(struct machine *self)
 	return self ? self->pid == HOST_KERNEL_ID : false;
 }
 
-static inline void map_groups__insert(struct map_groups *self, struct map *map)
+static inline void map_groups__insert(struct map_groups *mg, struct map *map)
 {
-	maps__insert(&self->maps[map->type], map);
-	map->groups = self;
+	maps__insert(&mg->maps[map->type], map);
+	map->groups = mg;
 }
 
-static inline void map_groups__remove(struct map_groups *self, struct map *map)
+static inline void map_groups__remove(struct map_groups *mg, struct map *map)
 {
-	maps__remove(&self->maps[map->type], map);
+	maps__remove(&mg->maps[map->type], map);
 }
 
-static inline struct map *map_groups__find(struct map_groups *self,
+static inline struct map *map_groups__find(struct map_groups *mg,
 					   enum map_type type, u64 addr)
 {
-	return maps__find(&self->maps[type], addr);
+	return maps__find(&mg->maps[type], addr);
 }
 
-struct symbol *map_groups__find_symbol(struct map_groups *self,
+struct symbol *map_groups__find_symbol(struct map_groups *mg,
 				       enum map_type type, u64 addr,
 				       struct map **mapp,
 				       symbol_filter_t filter);
 
-struct symbol *map_groups__find_symbol_by_name(struct map_groups *self,
+struct symbol *map_groups__find_symbol_by_name(struct map_groups *mg,
 					       enum map_type type,
 					       const char *name,
 					       struct map **mapp,
@@ -208,11 +208,11 @@ struct symbol *machine__find_kernel_function(struct machine *self, u64 addr,
 }
 
 static inline
-struct symbol *map_groups__find_function_by_name(struct map_groups *self,
+struct symbol *map_groups__find_function_by_name(struct map_groups *mg,
 						 const char *name, struct map **mapp,
 						 symbol_filter_t filter)
 {
-	return map_groups__find_symbol_by_name(self, MAP__FUNCTION, name, mapp, filter);
+	return map_groups__find_symbol_by_name(mg, MAP__FUNCTION, name, mapp, filter);
 }
 
 static inline
@@ -225,13 +225,13 @@ struct symbol *machine__find_kernel_function_by_name(struct machine *self,
 						 filter);
 }
 
-int map_groups__fixup_overlappings(struct map_groups *self, struct map *map,
+int map_groups__fixup_overlappings(struct map_groups *mg, struct map *map,
 				   int verbose, FILE *fp);
 
-struct map *map_groups__find_by_name(struct map_groups *self,
+struct map *map_groups__find_by_name(struct map_groups *mg,
 				     enum map_type type, const char *name);
 struct map *machine__new_module(struct machine *self, u64 start, const char *filename);
 
-void map_groups__flush(struct map_groups *self);
+void map_groups__flush(struct map_groups *mg);
 
 #endif /* __PERF_MAP_H */
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 555fc3864b90..5d732621a462 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -659,7 +659,7 @@ static int find_variable(Dwarf_Die *sc_die, struct probe_finder *pf)
 		if (!die_find_variable_at(&pf->cu_die, pf->pvar->var, 0, &vr_die))
 			ret = -ENOENT;
 	}
-	if (ret == 0)
+	if (ret >= 0)
 		ret = convert_variable(&vr_die, pf);
 
 	if (ret < 0)
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index cbc8f215d4b7..7624324efad4 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -803,7 +803,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 		first = list_entry(evlist->entries.next, struct perf_evsel, node);
 		err = perf_event__parse_sample(event, first->attr.sample_type,
 					       perf_evsel__sample_size(first),
-					       sample_id_all, &pevent->sample);
+					       sample_id_all, &pevent->sample, false);
 		if (err)
 			return PyErr_Format(PyExc_OSError,
 					    "perf: can't parse sample, err=%d", err);
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 170601e67d6b..974d0cbee5e9 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -162,7 +162,8 @@ static inline int perf_session__parse_sample(struct perf_session *session,
 {
 	return perf_event__parse_sample(event, session->sample_type,
 					session->sample_size,
-					session->sample_id_all, sample);
+					session->sample_id_all, sample,
+					session->header.needs_swap);
 }
 
 struct perf_evsel *perf_session__find_first_evtype(struct perf_session *session,
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 401e220566fd..1ee8f1e40f18 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -151,11 +151,17 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	u64 ip_l, ip_r;
 
+	if (!left->ms.sym && !right->ms.sym)
+		return right->level - left->level;
+
+	if (!left->ms.sym || !right->ms.sym)
+		return cmp_null(left->ms.sym, right->ms.sym);
+
 	if (left->ms.sym == right->ms.sym)
 		return 0;
 
-	ip_l = left->ms.sym ? left->ms.sym->start : left->ip;
-	ip_r = right->ms.sym ? right->ms.sym->start : right->ip;
+	ip_l = left->ms.sym->start;
+	ip_r = right->ms.sym->start;
 
 	return (int64_t)(ip_r - ip_l);
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 245e60d6b4e7..077df15ee705 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -76,16 +76,104 @@ static void dso__set_sorted_by_name(struct dso *dso, enum map_type type)
 
 bool symbol_type__is_a(char symbol_type, enum map_type map_type)
 {
+	symbol_type = toupper(symbol_type);
+
 	switch (map_type) {
 	case MAP__FUNCTION:
 		return symbol_type == 'T' || symbol_type == 'W';
 	case MAP__VARIABLE:
-		return symbol_type == 'D' || symbol_type == 'd';
+		return symbol_type == 'D';
 	default:
 		return false;
 	}
 }
 
+static int prefix_underscores_count(const char *str)
+{
+	const char *tail = str;
+
+	while (*tail == '_')
+		tail++;
+
+	return tail - str;
+}
+
+#define SYMBOL_A 0
+#define SYMBOL_B 1
+
+static int choose_best_symbol(struct symbol *syma, struct symbol *symb)
+{
+	s64 a;
+	s64 b;
+
+	/* Prefer a symbol with non zero length */
+	a = syma->end - syma->start;
+	b = symb->end - symb->start;
+	if ((b == 0) && (a > 0))
+		return SYMBOL_A;
+	else if ((a == 0) && (b > 0))
+		return SYMBOL_B;
+
+	/* Prefer a non weak symbol over a weak one */
+	a = syma->binding == STB_WEAK;
+	b = symb->binding == STB_WEAK;
+	if (b && !a)
+		return SYMBOL_A;
+	if (a && !b)
+		return SYMBOL_B;
+
+	/* Prefer a global symbol over a non global one */
+	a = syma->binding == STB_GLOBAL;
+	b = symb->binding == STB_GLOBAL;
+	if (a && !b)
+		return SYMBOL_A;
+	if (b && !a)
+		return SYMBOL_B;
+
+	/* Prefer a symbol with less underscores */
+	a = prefix_underscores_count(syma->name);
+	b = prefix_underscores_count(symb->name);
+	if (b > a)
+		return SYMBOL_A;
+	else if (a > b)
+		return SYMBOL_B;
+
+	/* If all else fails, choose the symbol with the longest name */
+	if (strlen(syma->name) >= strlen(symb->name))
+		return SYMBOL_A;
+	else
+		return SYMBOL_B;
+}
+
+static void symbols__fixup_duplicate(struct rb_root *symbols)
+{
+	struct rb_node *nd;
+	struct symbol *curr, *next;
+
+	nd = rb_first(symbols);
+
+	while (nd) {
+		curr = rb_entry(nd, struct symbol, rb_node);
+again:
+		nd = rb_next(&curr->rb_node);
+		next = rb_entry(nd, struct symbol, rb_node);
+
+		if (!nd)
+			break;
+
+		if (curr->start != next->start)
+			continue;
+
+		if (choose_best_symbol(curr, next) == SYMBOL_A) {
+			rb_erase(&next->rb_node, symbols);
+			goto again;
+		} else {
+			nd = rb_next(&curr->rb_node);
+			rb_erase(&curr->rb_node, symbols);
+		}
+	}
+}
+
 static void symbols__fixup_end(struct rb_root *symbols)
 {
 	struct rb_node *nd, *prevnd = rb_first(symbols);
@@ -440,18 +528,11 @@ int kallsyms__parse(const char *filename, void *arg,
 	char *line = NULL;
 	size_t n;
 	int err = -1;
-	u64 prev_start = 0;
-	char prev_symbol_type = 0;
-	char *prev_symbol_name;
 	FILE *file = fopen(filename, "r");
 
 	if (file == NULL)
 		goto out_failure;
 
-	prev_symbol_name = malloc(KSYM_NAME_LEN);
-	if (prev_symbol_name == NULL)
-		goto out_close;
-
 	err = 0;
 
 	while (!feof(file)) {
@@ -472,7 +553,7 @@ int kallsyms__parse(const char *filename, void *arg,
 		if (len + 2 >= line_len)
 			continue;
 
-		symbol_type = toupper(line[len]);
+		symbol_type = line[len];
 		len += 2;
 		symbol_name = line + len;
 		len = line_len - len;
@@ -482,24 +563,18 @@ int kallsyms__parse(const char *filename, void *arg,
 			break;
 		}
 
-		if (prev_symbol_type) {
-			u64 end = start;
-			if (end != prev_start)
-				--end;
-			err = process_symbol(arg, prev_symbol_name,
-					     prev_symbol_type, prev_start, end);
-			if (err)
-				break;
-		}
-
-		memcpy(prev_symbol_name, symbol_name, len + 1);
-		prev_symbol_type = symbol_type;
-		prev_start = start;
+		/*
+		 * module symbols are not sorted so we add all
+		 * symbols with zero length and rely on
+		 * symbols__fixup_end() to fix it up.
+		 */
+		err = process_symbol(arg, symbol_name,
+				     symbol_type, start, start);
+		if (err)
+			break;
 	}
 
-	free(prev_symbol_name);
 	free(line);
-out_close:
 	fclose(file);
 	return err;
 
@@ -705,6 +780,9 @@ int dso__load_kallsyms(struct dso *dso, const char *filename,
 	if (dso__load_all_kallsyms(dso, filename, map) < 0)
 		return -1;
 
+	symbols__fixup_duplicate(&dso->symbols[map->type]);
+	symbols__fixup_end(&dso->symbols[map->type]);
+
 	if (dso->kernel == DSO_TYPE_GUEST_KERNEL)
 		dso->symtab_type = SYMTAB__GUEST_KALLSYMS;
 	else
@@ -1094,8 +1172,7 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 	if (dso->has_build_id) {
 		u8 build_id[BUILD_ID_SIZE];
 
-		if (elf_read_build_id(elf, build_id,
-				      BUILD_ID_SIZE) != BUILD_ID_SIZE)
+		if (elf_read_build_id(elf, build_id, BUILD_ID_SIZE) < 0)
 			goto out_elf_end;
 
 		if (!dso__build_id_equal(dso, build_id))
@@ -1113,6 +1190,8 @@ static int dso__load_sym(struct dso *dso, struct map *map, const char *name,
 	}
 
 	opdsec = elf_section_by_name(elf, &ehdr, &opdshdr, ".opd", &opdidx);
+	if (opdshdr.sh_type != SHT_PROGBITS)
+		opdsec = NULL;
 	if (opdsec)
 		opddata = elf_rawdata(opdsec, NULL);
 
@@ -1278,6 +1357,7 @@ new_symbol:
 	 * For misannotated, zeroed, ASM function sizes.
 	 */
 	if (nr > 0) {
+		symbols__fixup_duplicate(&dso->symbols[map->type]);
 		symbols__fixup_end(&dso->symbols[map->type]);
 		if (kmap) {
 			/*
@@ -1364,8 +1444,8 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size)
 	ptr = data->d_buf;
 	while (ptr < (data->d_buf + data->d_size)) {
 		GElf_Nhdr *nhdr = ptr;
-		int namesz = NOTE_ALIGN(nhdr->n_namesz),
-		    descsz = NOTE_ALIGN(nhdr->n_descsz);
+		size_t namesz = NOTE_ALIGN(nhdr->n_namesz),
+		       descsz = NOTE_ALIGN(nhdr->n_descsz);
 		const char *name;
 
 		ptr += sizeof(*nhdr);
@@ -1374,8 +1454,10 @@ static int elf_read_build_id(Elf *elf, void *bf, size_t size)
 		if (nhdr->n_type == NT_GNU_BUILD_ID &&
 		    nhdr->n_namesz == sizeof("GNU")) {
 			if (memcmp(name, "GNU", sizeof("GNU")) == 0) {
-				memcpy(bf, ptr, BUILD_ID_SIZE);
-				err = BUILD_ID_SIZE;
+				size_t sz = min(size, descsz);
+				memcpy(bf, ptr, sz);
+				memset(bf + sz, 0, size - sz);
+				err = descsz;
 				break;
 			}
 		}
@@ -1427,7 +1509,7 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
 	while (1) {
 		char bf[BUFSIZ];
 		GElf_Nhdr nhdr;
-		int namesz, descsz;
+		size_t namesz, descsz;
 
 		if (read(fd, &nhdr, sizeof(nhdr)) != sizeof(nhdr))
 			break;
@@ -1436,15 +1518,16 @@ int sysfs__read_build_id(const char *filename, void *build_id, size_t size)
 		descsz = NOTE_ALIGN(nhdr.n_descsz);
 		if (nhdr.n_type == NT_GNU_BUILD_ID &&
 		    nhdr.n_namesz == sizeof("GNU")) {
-			if (read(fd, bf, namesz) != namesz)
+			if (read(fd, bf, namesz) != (ssize_t)namesz)
 				break;
 			if (memcmp(bf, "GNU", sizeof("GNU")) == 0) {
-				if (read(fd, build_id,
-				    BUILD_ID_SIZE) == BUILD_ID_SIZE) {
+				size_t sz = min(descsz, size);
+				if (read(fd, build_id, sz) == (ssize_t)sz) {
+					memset(build_id + sz, 0, size - sz);
 					err = 0;
 					break;
 				}
-			} else if (read(fd, bf, descsz) != descsz)
+			} else if (read(fd, bf, descsz) != (ssize_t)descsz)
 				break;
 		} else {
 			int n = namesz + descsz;
diff --git a/tools/perf/util/top.h b/tools/perf/util/top.h
index bfbf95bcc603..b07b0410463c 100644
--- a/tools/perf/util/top.h
+++ b/tools/perf/util/top.h
@@ -10,6 +10,7 @@
 
 struct perf_evlist;
 struct perf_evsel;
+struct perf_session;
 
 struct sym_entry {
 	struct rb_node		rb_node;
@@ -38,6 +39,7 @@ struct perf_top {
 	u64		   kernel_samples, us_samples;
 	u64		   exact_samples;
 	u64		   guest_us_samples, guest_kernel_samples;
+	u64		   total_lost_warned;
 	int		   print_entries, count_filter, delay_secs;
 	int		   display_weighted, freq, rb_entries;
 	pid_t		   target_pid, target_tid;
@@ -45,6 +47,7 @@ struct perf_top {
 	const char	   *cpu_list;
 	struct sym_entry   *sym_filter_entry;
 	struct perf_evsel  *sym_evsel;
+	struct perf_session *session;
 };
 
 size_t perf_top__header_snprintf(struct perf_top *top, char *bf, size_t size);
diff --git a/tools/perf/util/ui/browsers/top.c b/tools/perf/util/ui/browsers/top.c
index 88403cf8396a..9b6b43b32ac8 100644
--- a/tools/perf/util/ui/browsers/top.c
+++ b/tools/perf/util/ui/browsers/top.c
@@ -11,10 +11,12 @@
 #include "../helpline.h"
 #include "../libslang.h"
 #include "../util.h"
+#include "../ui.h"
 #include "../../evlist.h"
 #include "../../hist.h"
 #include "../../sort.h"
 #include "../../symbol.h"
+#include "../../session.h"
 #include "../../top.h"
 
 struct perf_top_browser {
@@ -43,10 +45,10 @@ static void perf_top_browser__write(struct ui_browser *browser, void *entry, int
 
 	if (top->evlist->nr_entries == 1 || !top->display_weighted) {
 		slsmg_printf("%20.2f ", syme->weight);
-		width -= 24;
+		width -= 21;
 	} else {
 		slsmg_printf("%9.1f %10ld ", syme->weight, syme->snap_count);
-		width -= 23;
+		width -= 20;
 	}
 
 	slsmg_printf("%4.1f%%", pcnt);
@@ -143,6 +145,25 @@ do_annotation:
 	symbol__tui_annotate(sym, syme->map, 0, top->delay_secs * 1000);
 }
 
+static void perf_top_browser__warn_lost(struct perf_top_browser *browser)
+{
+	struct perf_top *top = browser->b.priv;
+	char msg[128];
+	int len;
+
+	top->total_lost_warned = top->session->hists.stats.total_lost;
+	pthread_mutex_lock(&ui__lock);
+	ui_browser__set_color(&browser->b, HE_COLORSET_TOP);
+	len = snprintf(msg, sizeof(msg),
+		      " WARNING: LOST %" PRIu64 " events, Check IO/CPU overload",
+		      top->total_lost_warned);
+	if (len > browser->b.width)
+		len = browser->b.width;
+	SLsmg_gotorc(0, browser->b.width - len);
+	slsmg_write_nstring(msg, len);
+	pthread_mutex_unlock(&ui__lock);
+}
+
 static int perf_top_browser__run(struct perf_top_browser *browser)
 {
 	int key;
@@ -174,6 +195,9 @@ static int perf_top_browser__run(struct perf_top_browser *browser)
 			ui_browser__set_color(&browser->b, NEWT_COLORSET_ROOT);
 			SLsmg_gotorc(0, 0);
 			slsmg_write_nstring(title, browser->b.width);
+
+			if (top->total_lost_warned != top->session->hists.stats.total_lost)
+				perf_top_browser__warn_lost(browser);
 			break;
 		case 'a':
 		case NEWT_KEY_RIGHT: