Merge tag 'please-pull-mce-bitmap-comment' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras into x86/ras

Pull MCE updates from Tony Luck:

 "Better comments so we understand our existing machine check
  bank bitmaps - prelude to adding another bitmap soon."

Signed-off-by: Ingo Molnar <mingo@kernel.org>

112 files changed, 1005 insertions, 531 deletions

diff --git a/Makefile b/Makefile
index c6863b55f7c7..0142c934adbd 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 10
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Unicycling Gorilla
 
 # *DOCUMENTATION*
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 49d993cee512..2651b1da1c56 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1189,6 +1189,16 @@ config PL310_ERRATA_588369
 	   is not correctly implemented in PL310 as clean lines are not
 	   invalidated as a result of these operations.
 
+config ARM_ERRATA_643719
+	bool "ARM errata: LoUIS bit field in CLIDR register is incorrect"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for the 643719 Cortex-A9 (prior to
+	  r1p0) erratum. On affected cores the LoUIS bit field of the CLIDR
+	  register returns zero when it should return one. The workaround
+	  corrects this value, ensuring cache maintenance operations which use
+	  it behave as intended and avoiding data corruption.
+
 config ARM_ERRATA_720789
 	bool "ARM errata: TLBIASIDIS and TLBIMVAIS operations can broadcast a faulty ASID"
 	depends on CPU_V7
@@ -2006,7 +2016,7 @@ config XIP_PHYS_ADDR
 
 config KEXEC
 	bool "Kexec system call (EXPERIMENTAL)"
-	depends on (!SMP || HOTPLUG_CPU)
+	depends on (!SMP || PM_SLEEP_SMP)
 	help
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 79e9bdbfc491..120b83bfde20 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -116,7 +116,8 @@ targets       := vmlinux vmlinux.lds \
 
 # Make sure files are removed during clean
 extra-y       += piggy.gzip piggy.lzo piggy.lzma piggy.xzkern \
-		 lib1funcs.S ashldi3.S $(libfdt) $(libfdt_hdrs)
+		 lib1funcs.S ashldi3.S $(libfdt) $(libfdt_hdrs) \
+		 hyp-stub.S
 
 ifeq ($(CONFIG_FUNCTION_TRACER),y)
 ORIG_CFLAGS := $(KBUILD_CFLAGS)
diff --git a/arch/arm/boot/dts/exynos5250-pinctrl.dtsi b/arch/arm/boot/dts/exynos5250-pinctrl.dtsi
index d1650fb34c0a..ded558bb0f3b 100644
--- a/arch/arm/boot/dts/exynos5250-pinctrl.dtsi
+++ b/arch/arm/boot/dts/exynos5250-pinctrl.dtsi
@@ -763,7 +763,7 @@
 		};
 	};
 
-	pinctrl@03680000 {
+	pinctrl@03860000 {
 		gpz: gpz {
 			gpio-controller;
 			#gpio-cells = <2>;
diff --git a/arch/arm/boot/dts/exynos5250.dtsi b/arch/arm/boot/dts/exynos5250.dtsi
index 0673524238a6..fc9fb3d526e2 100644
--- a/arch/arm/boot/dts/exynos5250.dtsi
+++ b/arch/arm/boot/dts/exynos5250.dtsi
@@ -161,9 +161,9 @@
 		interrupts = <0 50 0>;
 	};
 
-	pinctrl_3: pinctrl@03680000 {
+	pinctrl_3: pinctrl@03860000 {
 		compatible = "samsung,exynos5250-pinctrl";
-		reg = <0x0368000 0x1000>;
+		reg = <0x03860000 0x1000>;
 		interrupts = <0 47 0>;
 	};
 
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index bff71388e72a..17d0ae8672fa 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -320,9 +320,7 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
 }
 
 #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
-static inline void flush_kernel_dcache_page(struct page *page)
-{
-}
+extern void flush_kernel_dcache_page(struct page *);
 
 #define flush_dcache_mmap_lock(mapping) \
 	spin_lock_irq(&(mapping)->tree_lock)
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 8ef8c9337809..4fb074c446bf 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -134,6 +134,10 @@ void machine_kexec(struct kimage *image)
 	unsigned long reboot_code_buffer_phys;
 	void *reboot_code_buffer;
 
+	if (num_online_cpus() > 1) {
+		pr_err("kexec: error: multiple CPUs still online\n");
+		return;
+	}
 
 	page_list = image->head & PAGE_MASK;
 
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 282de4826abb..6e8931ccf13e 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -184,30 +184,61 @@ int __init reboot_setup(char *str)
 
 __setup("reboot=", reboot_setup);
 
+/*
+ * Called by kexec, immediately prior to machine_kexec().
+ *
+ * This must completely disable all secondary CPUs; simply causing those CPUs
+ * to execute e.g. a RAM-based pin loop is not sufficient. This allows the
+ * kexec'd kernel to use any and all RAM as it sees fit, without having to
+ * avoid any code or data used by any SW CPU pin loop. The CPU hotplug
+ * functionality embodied in disable_nonboot_cpus() to achieve this.
+ */
 void machine_shutdown(void)
 {
-#ifdef CONFIG_SMP
-	smp_send_stop();
-#endif
+	disable_nonboot_cpus();
 }
 
+/*
+ * Halting simply requires that the secondary CPUs stop performing any
+ * activity (executing tasks, handling interrupts). smp_send_stop()
+ * achieves this.
+ */
 void machine_halt(void)
 {
-	machine_shutdown();
+	smp_send_stop();
+
 	local_irq_disable();
 	while (1);
 }
 
+/*
+ * Power-off simply requires that the secondary CPUs stop performing any
+ * activity (executing tasks, handling interrupts). smp_send_stop()
+ * achieves this. When the system power is turned off, it will take all CPUs
+ * with it.
+ */
 void machine_power_off(void)
 {
-	machine_shutdown();
+	smp_send_stop();
+
 	if (pm_power_off)
 		pm_power_off();
 }
 
+/*
+ * Restart requires that the secondary CPUs stop performing any activity
+ * while the primary CPU resets the system. Systems with a single CPU can
+ * use soft_restart() as their machine descriptor's .restart hook, since that
+ * will cause the only available CPU to reset. Systems with multiple CPUs must
+ * provide a HW restart implementation, to ensure that all CPUs reset at once.
+ * This is required so that any code running after reset on the primary CPU
+ * doesn't have to co-ordinate with other CPUs to ensure they aren't still
+ * executing pre-reset code, and using RAM that the primary CPU's code wishes
+ * to use. Implementing such co-ordination would be essentially impossible.
+ */
 void machine_restart(char *cmd)
 {
-	machine_shutdown();
+	smp_send_stop();
 
 	arm_pm_restart(reboot_mode, cmd);
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 550d63cef68e..5919eb451bb9 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -651,17 +651,6 @@ void smp_send_reschedule(int cpu)
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-static void smp_kill_cpus(cpumask_t *mask)
-{
-	unsigned int cpu;
-	for_each_cpu(cpu, mask)
-		platform_cpu_kill(cpu);
-}
-#else
-static void smp_kill_cpus(cpumask_t *mask) { }
-#endif
-
 void smp_send_stop(void)
 {
 	unsigned long timeout;
@@ -679,8 +668,6 @@ void smp_send_stop(void)
 
 	if (num_online_cpus() > 1)
 		pr_warning("SMP: failed to stop secondary CPUs\n");
-
-	smp_kill_cpus(&mask);
 }
 
 /*
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 15451ee4acc8..515b00064da8 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -92,6 +92,14 @@ ENTRY(v7_flush_dcache_louis)
 	mrc	p15, 1, r0, c0, c0, 1		@ read clidr, r0 = clidr
 	ALT_SMP(ands	r3, r0, #(7 << 21))	@ extract LoUIS from clidr
 	ALT_UP(ands	r3, r0, #(7 << 27))	@ extract LoUU from clidr
+#ifdef CONFIG_ARM_ERRATA_643719
+	ALT_SMP(mrceq	p15, 0, r2, c0, c0, 0)	@ read main ID register
+	ALT_UP(moveq	pc, lr)			@ LoUU is zero, so nothing to do
+	ldreq	r1, =0x410fc090                 @ ID of ARM Cortex A9 r0p?
+	biceq	r2, r2, #0x0000000f             @ clear minor revision number
+	teqeq	r2, r1                          @ test for errata affected core and if so...
+	orreqs	r3, #(1 << 21)			@   fix LoUIS value (and set flags state to 'ne')
+#endif
 	ALT_SMP(mov	r3, r3, lsr #20)	@ r3 = LoUIS * 2
 	ALT_UP(mov	r3, r3, lsr #26)	@ r3 = LoUU * 2
 	moveq	pc, lr				@ return if level == 0
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 0d473cce501c..32aa5861119f 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -301,6 +301,39 @@ void flush_dcache_page(struct page *page)
 EXPORT_SYMBOL(flush_dcache_page);
 
 /*
+ * Ensure cache coherency for the kernel mapping of this page. We can
+ * assume that the page is pinned via kmap.
+ *
+ * If the page only exists in the page cache and there are no user
+ * space mappings, this is a no-op since the page was already marked
+ * dirty at creation.  Otherwise, we need to flush the dirty kernel
+ * cache lines directly.
+ */
+void flush_kernel_dcache_page(struct page *page)
+{
+	if (cache_is_vivt() || cache_is_vipt_aliasing()) {
+		struct address_space *mapping;
+
+		mapping = page_mapping(page);
+
+		if (!mapping || mapping_mapped(mapping)) {
+			void *addr;
+
+			addr = page_address(page);
+			/*
+			 * kmap_atomic() doesn't set the page virtual
+			 * address for highmem pages, and
+			 * kunmap_atomic() takes care of cache
+			 * flushing already.
+			 */
+			if (!IS_ENABLED(CONFIG_HIGHMEM) || addr)
+				__cpuc_flush_dcache_area(addr, PAGE_SIZE);
+		}
+	}
+}
+EXPORT_SYMBOL(flush_kernel_dcache_page);
+
+/*
  * Flush an anonymous page so that users of get_user_pages()
  * can safely access the data.  The expected sequence is:
  *
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index e0d8565671a6..4d409e6a552d 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -616,10 +616,12 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
-static void __init map_init_section(pmd_t *pmd, unsigned long addr,
+static void __init __map_init_section(pmd_t *pmd, unsigned long addr,
 			unsigned long end, phys_addr_t phys,
 			const struct mem_type *type)
 {
+	pmd_t *p = pmd;
+
 #ifndef CONFIG_ARM_LPAE
 	/*
 	 * In classic MMU format, puds and pmds are folded in to
@@ -638,7 +640,7 @@ static void __init map_init_section(pmd_t *pmd, unsigned long addr,
 		phys += SECTION_SIZE;
 	} while (pmd++, addr += SECTION_SIZE, addr != end);
 
-	flush_pmd_entry(pmd);
+	flush_pmd_entry(p);
 }
 
 static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
@@ -661,7 +663,7 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 		 */
 		if (type->prot_sect &&
 				((addr | next | phys) & ~SECTION_MASK) == 0) {
-			map_init_section(pmd, addr, next, phys, type);
+			__map_init_section(pmd, addr, next, phys, type);
 		} else {
 			alloc_init_pte(pmd, addr, next,
 						__phys_to_pfn(phys), type);
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 2c73a7301ff7..4c8c9c10a388 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -409,8 +409,8 @@ __v7_ca9mp_proc_info:
 	 */
 	.type   __v7_pj4b_proc_info, #object
 __v7_pj4b_proc_info:
-	.long	0x562f5840
-	.long	0xfffffff0
+	.long	0x560f5800
+	.long	0xff0fff00
 	__v7_proc __v7_pj4b_setup
 	.size	__v7_pj4b_proc_info, . - __v7_pj4b_proc_info
 
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 1e49e5eb81e9..9ba33c40cdf8 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1336,6 +1336,7 @@ void perf_callchain_user(struct perf_callchain_entry *entry,
 		return;
 	}
 
+	perf_callchain_store(entry, regs->pc);
 	tail = (struct frame_tail __user *)regs->regs[29];
 
 	while (entry->nr < PERF_MAX_STACK_DEPTH &&
diff --git a/arch/metag/include/asm/hugetlb.h b/arch/metag/include/asm/hugetlb.h
index f545477e61f3..471f481e67f3 100644
--- a/arch/metag/include/asm/hugetlb.h
+++ b/arch/metag/include/asm/hugetlb.h
@@ -2,6 +2,7 @@
 #define _ASM_METAG_HUGETLB_H
 
 #include <asm/page.h>
+#include <asm-generic/hugetlb.h>
 
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
diff --git a/arch/mn10300/include/asm/irqflags.h b/arch/mn10300/include/asm/irqflags.h
index 678f68d5f37b..8730c0a3c37d 100644
--- a/arch/mn10300/include/asm/irqflags.h
+++ b/arch/mn10300/include/asm/irqflags.h
@@ -13,9 +13,8 @@
 #define _ASM_IRQFLAGS_H
 
 #include <asm/cpu-regs.h>
-#ifndef __ASSEMBLY__
-#include <linux/smp.h>
-#endif
+/* linux/smp.h <- linux/irqflags.h needs asm/smp.h first */
+#include <asm/smp.h>
 
 /*
  * interrupt control
diff --git a/arch/mn10300/include/asm/smp.h b/arch/mn10300/include/asm/smp.h
index 6745dbe64944..56c42417d428 100644
--- a/arch/mn10300/include/asm/smp.h
+++ b/arch/mn10300/include/asm/smp.h
@@ -24,6 +24,7 @@
 #ifndef __ASSEMBLY__
 #include <linux/threads.h>
 #include <linux/cpumask.h>
+#include <linux/thread_info.h>
 #endif
 
 #ifdef CONFIG_SMP
@@ -85,7 +86,7 @@ extern cpumask_t cpu_boot_map;
 extern void smp_init_cpus(void);
 extern void smp_cache_interrupt(void);
 extern void send_IPI_allbutself(int irq);
-extern int smp_nmi_call_function(smp_call_func_t func, void *info, int wait);
+extern int smp_nmi_call_function(void (*func)(void *), void *info, int wait);
 
 extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
@@ -100,6 +101,7 @@ extern void __cpu_die(unsigned int cpu);
 #ifndef __ASSEMBLY__
 
 static inline void smp_init_cpus(void) {}
+#define raw_smp_processor_id() 0
 
 #endif /* __ASSEMBLY__ */
 #endif /* CONFIG_SMP */
diff --git a/arch/parisc/include/asm/mmzone.h b/arch/parisc/include/asm/mmzone.h
index cc50d33b7b88..b6b34a0987e7 100644
--- a/arch/parisc/include/asm/mmzone.h
+++ b/arch/parisc/include/asm/mmzone.h
@@ -27,7 +27,7 @@ extern struct node_map_data node_data[];
 
 #define PFNNID_SHIFT (30 - PAGE_SHIFT)
 #define PFNNID_MAP_MAX  512     /* support 512GB */
-extern unsigned char pfnnid_map[PFNNID_MAP_MAX];
+extern signed char pfnnid_map[PFNNID_MAP_MAX];
 
 #ifndef CONFIG_64BIT
 #define pfn_is_io(pfn) ((pfn & (0xf0000000UL >> PAGE_SHIFT)) == (0xf0000000UL >> PAGE_SHIFT))
@@ -46,7 +46,7 @@ static inline int pfn_to_nid(unsigned long pfn)
 	i = pfn >> PFNNID_SHIFT;
 	BUG_ON(i >= ARRAY_SIZE(pfnnid_map));
 
-	return (int)pfnnid_map[i];
+	return pfnnid_map[i];
 }
 
 static inline int pfn_valid(int pfn)
diff --git a/arch/parisc/include/asm/pci.h b/arch/parisc/include/asm/pci.h
index 3234f492d575..465154076d23 100644
--- a/arch/parisc/include/asm/pci.h
+++ b/arch/parisc/include/asm/pci.h
@@ -225,4 +225,9 @@ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel)
 	return channel ? 15 : 14;
 }
 
+#define HAVE_PCI_MMAP
+
+extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+	enum pci_mmap_state mmap_state, int write_combine);
+
 #endif /* __ASM_PARISC_PCI_H */
diff --git a/arch/parisc/kernel/hardware.c b/arch/parisc/kernel/hardware.c
index 9e2d2e408529..872275659d98 100644
--- a/arch/parisc/kernel/hardware.c
+++ b/arch/parisc/kernel/hardware.c
@@ -1205,6 +1205,7 @@ static struct hp_hardware hp_hardware_list[] = {
 	{HPHW_FIO, 0x004, 0x00320, 0x0, "Metheus Frame Buffer"}, 
 	{HPHW_FIO, 0x004, 0x00340, 0x0, "BARCO CX4500 VME Grphx Cnsl"}, 
 	{HPHW_FIO, 0x004, 0x00360, 0x0, "Hughes TOG VME FDDI"}, 
+	{HPHW_FIO, 0x076, 0x000AD, 0x00, "Crestone Peak RS-232"},
 	{HPHW_IOA, 0x185, 0x0000B, 0x00, "Java BC Summit Port"}, 
 	{HPHW_IOA, 0x1FF, 0x0000B, 0x00, "Hitachi Ghostview Summit Port"}, 
 	{HPHW_IOA, 0x580, 0x0000B, 0x10, "U2-IOA BC Runway Port"}, 
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 36d7f402e48e..b743a80eaba0 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -860,7 +860,7 @@ ENTRY(flush_dcache_page_asm)
 #endif
 
 	ldil		L%dcache_stride, %r1
-	ldw		R%dcache_stride(%r1), %r1
+	ldw		R%dcache_stride(%r1), r31
 
 #ifdef CONFIG_64BIT
 	depdi,z		1, 63-PAGE_SHIFT,1, %r25
@@ -868,26 +868,26 @@ ENTRY(flush_dcache_page_asm)
 	depwi,z		1, 31-PAGE_SHIFT,1, %r25
 #endif
 	add		%r28, %r25, %r25
-	sub		%r25, %r1, %r25
-
-
-1:      fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
-	fdc,m		%r1(%r28)
+	sub		%r25, r31, %r25
+
+
+1:      fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
+	fdc,m		r31(%r28)
 	cmpb,COND(<<)		%r28, %r25,1b
-	fdc,m		%r1(%r28)
+	fdc,m		r31(%r28)
 
 	sync
 
@@ -936,7 +936,7 @@ ENTRY(flush_icache_page_asm)
 #endif
 
 	ldil		L%icache_stride, %r1
-	ldw		R%icache_stride(%r1), %r1
+	ldw		R%icache_stride(%r1), %r31
 
 #ifdef CONFIG_64BIT
 	depdi,z		1, 63-PAGE_SHIFT,1, %r25
@@ -944,28 +944,28 @@ ENTRY(flush_icache_page_asm)
 	depwi,z		1, 31-PAGE_SHIFT,1, %r25
 #endif
 	add		%r28, %r25, %r25
-	sub		%r25, %r1, %r25
+	sub		%r25, %r31, %r25
 
 
 	/* fic only has the type 26 form on PA1.1, requiring an
 	 * explicit space specification, so use %sr4 */
-1:      fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
-	fic,m		%r1(%sr4,%r28)
+1:      fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
 	cmpb,COND(<<)	%r28, %r25,1b
-	fic,m		%r1(%sr4,%r28)
+	fic,m		%r31(%sr4,%r28)
 
 	sync
 
diff --git a/arch/parisc/kernel/pci.c b/arch/parisc/kernel/pci.c
index 60309051875e..64f2764a8cef 100644
--- a/arch/parisc/kernel/pci.c
+++ b/arch/parisc/kernel/pci.c
@@ -220,6 +220,33 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
 }
 
 
+int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
+			enum pci_mmap_state mmap_state, int write_combine)
+{
+	unsigned long prot;
+
+	/*
+	 * I/O space can be accessed via normal processor loads and stores on
+	 * this platform but for now we elect not to do this and portable
+	 * drivers should not do this anyway.
+	 */
+	if (mmap_state == pci_mmap_io)
+		return -EINVAL;
+
+	if (write_combine)
+		return -EINVAL;
+
+	/*
+	 * Ignore write-combine; for now only return uncached mappings.
+	 */
+	prot = pgprot_val(vma->vm_page_prot);
+	prot |= _PAGE_NO_CACHE;
+	vma->vm_page_prot = __pgprot(prot);
+
+	return remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
+		vma->vm_end - vma->vm_start, vma->vm_page_prot);
+}
+
 /*
  * A driver is enabling the device.  We make sure that all the appropriate
  * bits are set to allow the device to operate as the driver is expecting.
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 1c965642068b..505b56c6b9b9 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -47,7 +47,7 @@ pte_t pg0[PT_INITIAL * PTRS_PER_PTE] __attribute__ ((__section__ (".data..vm0.pt
 
 #ifdef CONFIG_DISCONTIGMEM
 struct node_map_data node_data[MAX_NUMNODES] __read_mostly;
-unsigned char pfnnid_map[PFNNID_MAP_MAX] __read_mostly;
+signed char pfnnid_map[PFNNID_MAP_MAX] __read_mostly;
 #endif
 
 static struct resource data_resource = {
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 5cd7ad0c1176..1a1b51189773 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -673,7 +673,6 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		ret = s;
 		goto out;
 	}
-	kvmppc_lazy_ee_enable();
 
 	kvm_guest_enter();
 
@@ -699,6 +698,8 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	kvmppc_load_guest_fp(vcpu);
 #endif
 
+	kvmppc_lazy_ee_enable();
+
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
 
 	/* No need for kvm_guest_exit. It's done in handle_exit.
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 237c8e5f2640..77fdd2cef33b 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -592,8 +592,14 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 	do {
 		pmd = pmd_offset(pud, addr);
 		next = pmd_addr_end(addr, end);
-		if (pmd_none_or_clear_bad(pmd))
+		if (!is_hugepd(pmd)) {
+			/*
+			 * if it is not hugepd pointer, we should already find
+			 * it cleared.
+			 */
+			WARN_ON(!pmd_none_or_clear_bad(pmd));
 			continue;
+		}
 #ifdef CONFIG_PPC_FSL_BOOK3E
 		/*
 		 * Increment next by the size of the huge mapping since
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index ff18e3cfb6b1..7e4a97fbded4 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -6,6 +6,7 @@ generic-y += cputime.h
 generic-y += div64.h
 generic-y += emergency-restart.h
 generic-y += exec.h
+generic-y += linkage.h
 generic-y += local64.h
 generic-y += mutex.h
 generic-y += irq_regs.h
diff --git a/arch/sparc/include/asm/leon.h b/arch/sparc/include/asm/leon.h
index 15a716934e4d..b836e9297f2a 100644
--- a/arch/sparc/include/asm/leon.h
+++ b/arch/sparc/include/asm/leon.h
@@ -135,7 +135,7 @@ static inline int sparc_leon3_cpuid(void)
 
 #ifdef CONFIG_SMP
 # define LEON3_IRQ_IPI_DEFAULT		13
-# define LEON3_IRQ_TICKER		(leon3_ticker_irq)
+# define LEON3_IRQ_TICKER		(leon3_gptimer_irq)
 # define LEON3_IRQ_CROSS_CALL		15
 #endif
 
diff --git a/arch/sparc/include/asm/leon_amba.h b/arch/sparc/include/asm/leon_amba.h
index f3034eddf468..24ec48c3ff90 100644
--- a/arch/sparc/include/asm/leon_amba.h
+++ b/arch/sparc/include/asm/leon_amba.h
@@ -47,6 +47,7 @@ struct amba_prom_registers {
 #define LEON3_GPTIMER_LD 4
 #define LEON3_GPTIMER_IRQEN 8
 #define LEON3_GPTIMER_SEPIRQ 8
+#define LEON3_GPTIMER_TIMERS 0x7
 
 #define LEON23_REG_TIMER_CONTROL_EN    0x00000001 /* 1 = enable counting */
 /* 0 = hold scalar and counter */
diff --git a/arch/sparc/include/asm/linkage.h b/arch/sparc/include/asm/linkage.h
deleted file mode 100644
index 291c2d01c44f..000000000000
--- a/arch/sparc/include/asm/linkage.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_LINKAGE_H
-#define __ASM_LINKAGE_H
-
-/* Nothing to see here... */
-
-#endif
diff --git a/arch/sparc/kernel/ds.c b/arch/sparc/kernel/ds.c
index 75bb608c423e..5ef48dab5636 100644
--- a/arch/sparc/kernel/ds.c
+++ b/arch/sparc/kernel/ds.c
@@ -843,7 +843,8 @@ void ldom_reboot(const char *boot_command)
 		unsigned long len;
 
 		strcpy(full_boot_str, "boot ");
-		strcpy(full_boot_str + strlen("boot "), boot_command);
+		strlcpy(full_boot_str + strlen("boot "), boot_command,
+			sizeof(full_boot_str + strlen("boot ")));
 		len = strlen(full_boot_str);
 
 		if (reboot_data_supported) {
diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c
index 7c0231dabe44..b7c68976cbc7 100644
--- a/arch/sparc/kernel/leon_kernel.c
+++ b/arch/sparc/kernel/leon_kernel.c
@@ -38,7 +38,6 @@ static DEFINE_SPINLOCK(leon_irq_lock);
 
 unsigned long leon3_gptimer_irq; /* interrupt controller irq number */
 unsigned long leon3_gptimer_idx; /* Timer Index (0..6) within Timer Core */
-int leon3_ticker_irq; /* Timer ticker IRQ */
 unsigned int sparc_leon_eirq;
 #define LEON_IMASK(cpu) (&leon3_irqctrl_regs->mask[cpu])
 #define LEON_IACK (&leon3_irqctrl_regs->iclear)
@@ -278,6 +277,9 @@ irqreturn_t leon_percpu_timer_ce_interrupt(int irq, void *unused)
 
 	leon_clear_profile_irq(cpu);
 
+	if (cpu == boot_cpu_id)
+		timer_interrupt(irq, NULL);
+
 	ce = &per_cpu(sparc32_clockevent, cpu);
 
 	irq_enter();
@@ -299,6 +301,7 @@ void __init leon_init_timers(void)
 	int icsel;
 	int ampopts;
 	int err;
+	u32 config;
 
 	sparc_config.get_cycles_offset = leon_cycles_offset;
 	sparc_config.cs_period = 1000000 / HZ;
@@ -377,23 +380,6 @@ void __init leon_init_timers(void)
 	LEON3_BYPASS_STORE_PA(
 			&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl, 0);
 
-#ifdef CONFIG_SMP
-	leon3_ticker_irq = leon3_gptimer_irq + 1 + leon3_gptimer_idx;
-
-	if (!(LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->config) &
-	      (1<<LEON3_GPTIMER_SEPIRQ))) {
-		printk(KERN_ERR "timer not configured with separate irqs\n");
-		BUG();
-	}
-
-	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx+1].val,
-				0);
-	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx+1].rld,
-				(((1000000/HZ) - 1)));
-	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx+1].ctrl,
-				0);
-#endif
-
 	/*
 	 * The IRQ controller may (if implemented) consist of multiple
 	 * IRQ controllers, each mapped on a 4Kb boundary.
@@ -416,13 +402,6 @@ void __init leon_init_timers(void)
 	if (eirq != 0)
 		leon_eirq_setup(eirq);
 
-	irq = _leon_build_device_irq(NULL, leon3_gptimer_irq+leon3_gptimer_idx);
-	err = request_irq(irq, timer_interrupt, IRQF_TIMER, "timer", NULL);
-	if (err) {
-		printk(KERN_ERR "unable to attach timer IRQ%d\n", irq);
-		prom_halt();
-	}
-
 #ifdef CONFIG_SMP
 	{
 		unsigned long flags;
@@ -439,30 +418,31 @@ void __init leon_init_timers(void)
 	}
 #endif
 
-	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl,
-			      LEON3_GPTIMER_EN |
-			      LEON3_GPTIMER_RL |
-			      LEON3_GPTIMER_LD |
-			      LEON3_GPTIMER_IRQEN);
+	config = LEON3_BYPASS_LOAD_PA(&leon3_gptimer_regs->config);
+	if (config & (1 << LEON3_GPTIMER_SEPIRQ))
+		leon3_gptimer_irq += leon3_gptimer_idx;
+	else if ((config & LEON3_GPTIMER_TIMERS) > 1)
+		pr_warn("GPTIMER uses shared irqs, using other timers of the same core will fail.\n");
 
 #ifdef CONFIG_SMP
 	/* Install per-cpu IRQ handler for broadcasted ticker */
-	irq = leon_build_device_irq(leon3_ticker_irq, handle_percpu_irq,
+	irq = leon_build_device_irq(leon3_gptimer_irq, handle_percpu_irq,
 				    "per-cpu", 0);
 	err = request_irq(irq, leon_percpu_timer_ce_interrupt,
-			  IRQF_PERCPU | IRQF_TIMER, "ticker",
-			  NULL);
+			  IRQF_PERCPU | IRQF_TIMER, "timer", NULL);
+#else
+	irq = _leon_build_device_irq(NULL, leon3_gptimer_irq);
+	err = request_irq(irq, timer_interrupt, IRQF_TIMER, "timer", NULL);
+#endif
 	if (err) {
-		printk(KERN_ERR "unable to attach ticker IRQ%d\n", irq);
+		pr_err("Unable to attach timer IRQ%d\n", irq);
 		prom_halt();
 	}
-
-	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx+1].ctrl,
+	LEON3_BYPASS_STORE_PA(&leon3_gptimer_regs->e[leon3_gptimer_idx].ctrl,
 			      LEON3_GPTIMER_EN |
 			      LEON3_GPTIMER_RL |
 			      LEON3_GPTIMER_LD |
 			      LEON3_GPTIMER_IRQEN);
-#endif
 	return;
 bad:
 	printk(KERN_ERR "No Timer/irqctrl found\n");
diff --git a/arch/sparc/kernel/leon_pci_grpci1.c b/arch/sparc/kernel/leon_pci_grpci1.c
index 7739a54315e2..6df26e37f879 100644
--- a/arch/sparc/kernel/leon_pci_grpci1.c
+++ b/arch/sparc/kernel/leon_pci_grpci1.c
@@ -536,11 +536,9 @@ static int grpci1_of_probe(struct platform_device *ofdev)
 
 	/* find device register base address */
 	res = platform_get_resource(ofdev, IORESOURCE_MEM, 0);
-	regs = devm_request_and_ioremap(&ofdev->dev, res);
-	if (!regs) {
-		dev_err(&ofdev->dev, "io-regs mapping failed\n");
-		return -EADDRNOTAVAIL;
-	}
+	regs = devm_ioremap_resource(&ofdev->dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	/*
 	 * check that we're in Host Slot and that we can act as a Host Bridge
diff --git a/arch/sparc/kernel/leon_pmc.c b/arch/sparc/kernel/leon_pmc.c
index bdf53d9a8d46..b0b3967a2dd2 100644
--- a/arch/sparc/kernel/leon_pmc.c
+++ b/arch/sparc/kernel/leon_pmc.c
@@ -47,6 +47,10 @@ void pmc_leon_idle_fixup(void)
 	 * MMU does not get a TLB miss here by using the MMU BYPASS ASI.
 	 */
 	register unsigned int address = (unsigned int)leon3_irqctrl_regs;
+
+	/* Interrupts need to be enabled to not hang the CPU */
+	local_irq_enable();
+
 	__asm__ __volatile__ (
 		"wr	%%g0, %%asr19\n"
 		"lda	[%0] %1, %%g0\n"
@@ -60,6 +64,9 @@ void pmc_leon_idle_fixup(void)
  */
 void pmc_leon_idle(void)
 {
+	/* Interrupts need to be enabled to not hang the CPU */
+	local_irq_enable();
+
 	/* For systems without power-down, this will be no-op */
 	__asm__ __volatile__ ("wr	%g0, %asr19\n\t");
 }
diff --git a/arch/sparc/kernel/setup_32.c b/arch/sparc/kernel/setup_32.c
index 38bf80a22f02..1434526970a6 100644
--- a/arch/sparc/kernel/setup_32.c
+++ b/arch/sparc/kernel/setup_32.c
@@ -304,7 +304,7 @@ void __init setup_arch(char **cmdline_p)
 
 	/* Initialize PROM console and command line. */
 	*cmdline_p = prom_getbootargs();
-	strcpy(boot_command_line, *cmdline_p);
+	strlcpy(boot_command_line, *cmdline_p, COMMAND_LINE_SIZE);
 	parse_early_param();
 
 	boot_flags_init(*cmdline_p);
diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c
index 88a127b9c69e..13785547e435 100644
--- a/arch/sparc/kernel/setup_64.c
+++ b/arch/sparc/kernel/setup_64.c
@@ -555,7 +555,7 @@ void __init setup_arch(char **cmdline_p)
 {
 	/* Initialize PROM console and command line. */
 	*cmdline_p = prom_getbootargs();
-	strcpy(boot_command_line, *cmdline_p);
+	strlcpy(boot_command_line, *cmdline_p, COMMAND_LINE_SIZE);
 	parse_early_param();
 
 	boot_flags_init(*cmdline_p);
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index a7171997adfd..04fd55a6e461 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -1098,7 +1098,14 @@ static int __init grab_mblocks(struct mdesc_handle *md)
 		m->size = *val;
 		val = mdesc_get_property(md, node,
 					 "address-congruence-offset", NULL);
-		m->offset = *val;
+
+		/* The address-congruence-offset property is optional.
+		 * Explicity zero it be identifty this.
+		 */
+		if (val)
+			m->offset = *val;
+		else
+			m->offset = 0UL;
 
 		numadbg("MBLOCK[%d]: base[%llx] size[%llx] offset[%llx]\n",
 			count - 1, m->base, m->size, m->offset);
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index 83d89bcb44af..37e7bc4c95b3 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -85,8 +85,8 @@ static void tlb_batch_add_one(struct mm_struct *mm, unsigned long vaddr,
 	}
 
 	if (!tb->active) {
-		global_flush_tlb_page(mm, vaddr);
 		flush_tsb_user_page(mm, vaddr);
+		global_flush_tlb_page(mm, vaddr);
 		goto out;
 	}
 
diff --git a/arch/sparc/prom/bootstr_32.c b/arch/sparc/prom/bootstr_32.c
index f5ec32e0d419..d2b49d2365e7 100644
--- a/arch/sparc/prom/bootstr_32.c
+++ b/arch/sparc/prom/bootstr_32.c
@@ -23,23 +23,25 @@ prom_getbootargs(void)
 		return barg_buf;
 	}
 
-	switch(prom_vers) {
+	switch (prom_vers) {
 	case PROM_V0:
 		cp = barg_buf;
 		/* Start from 1 and go over fd(0,0,0)kernel */
-		for(iter = 1; iter < 8; iter++) {
+		for (iter = 1; iter < 8; iter++) {
 			arg = (*(romvec->pv_v0bootargs))->argv[iter];
 			if (arg == NULL)
 				break;
-			while(*arg != 0) {
+			while (*arg != 0) {
 				/* Leave place for space and null. */
-				if(cp >= barg_buf + BARG_LEN-2){
+				if (cp >= barg_buf + BARG_LEN - 2)
 					/* We might issue a warning here. */
 					break;
-				}
 				*cp++ = *arg++;
 			}
 			*cp++ = ' ';
+			if (cp >= barg_buf + BARG_LEN - 1)
+				/* We might issue a warning here. */
+				break;
 		}
 		*cp = 0;
 		break;
diff --git a/arch/sparc/prom/tree_64.c b/arch/sparc/prom/tree_64.c
index 92204c3800b5..bd1b2a3ac34e 100644
--- a/arch/sparc/prom/tree_64.c
+++ b/arch/sparc/prom/tree_64.c
@@ -39,7 +39,7 @@ inline phandle __prom_getchild(phandle node)
 	return prom_node_to_node("child", node);
 }
 
-inline phandle prom_getchild(phandle node)
+phandle prom_getchild(phandle node)
 {
 	phandle cnode;
 
@@ -72,7 +72,7 @@ inline phandle __prom_getsibling(phandle node)
 	return prom_node_to_node(prom_peer_name, node);
 }
 
-inline phandle prom_getsibling(phandle node)
+phandle prom_getsibling(phandle node)
 {
 	phandle sibnode;
 
@@ -89,7 +89,7 @@ EXPORT_SYMBOL(prom_getsibling);
 /* Return the length in bytes of property 'prop' at node 'node'.
  * Return -1 on error.
  */
-inline int prom_getproplen(phandle node, const char *prop)
+int prom_getproplen(phandle node, const char *prop)
 {
 	unsigned long args[6];
 
@@ -113,8 +113,8 @@ EXPORT_SYMBOL(prom_getproplen);
  * 'buffer' which has a size of 'bufsize'.  If the acquisition
  * was successful the length will be returned, else -1 is returned.
  */
-inline int prom_getproperty(phandle node, const char *prop,
-			    char *buffer, int bufsize)
+int prom_getproperty(phandle node, const char *prop,
+		     char *buffer, int bufsize)
 {
 	unsigned long args[8];
 	int plen;
@@ -141,7 +141,7 @@ EXPORT_SYMBOL(prom_getproperty);
 /* Acquire an integer property and return its value.  Returns -1
  * on failure.
  */
-inline int prom_getint(phandle node, const char *prop)
+int prom_getint(phandle node, const char *prop)
 {
 	int intprop;
 
@@ -235,7 +235,7 @@ static const char *prom_nextprop_name = "nextprop";
 /* Return the first property type for node 'node'.
  * buffer should be at least 32B in length
  */
-inline char *prom_firstprop(phandle node, char *buffer)
+char *prom_firstprop(phandle node, char *buffer)
 {
 	unsigned long args[7];
 
@@ -261,7 +261,7 @@ EXPORT_SYMBOL(prom_firstprop);
  * at node 'node' .  Returns NULL string if no more
  * property types for this node.
  */
-inline char *prom_nextprop(phandle node, const char *oprop, char *buffer)
+char *prom_nextprop(phandle node, const char *oprop, char *buffer)
 {
 	unsigned long args[7];
 	char buf[32];
diff --git a/arch/tile/lib/exports.c b/arch/tile/lib/exports.c
index 4385cb6fa00a..a93b02a25222 100644
--- a/arch/tile/lib/exports.c
+++ b/arch/tile/lib/exports.c
@@ -84,4 +84,6 @@ uint64_t __ashrdi3(uint64_t, unsigned int);
 EXPORT_SYMBOL(__ashrdi3);
 uint64_t __ashldi3(uint64_t, unsigned int);
 EXPORT_SYMBOL(__ashldi3);
+int __ffsdi2(uint64_t);
+EXPORT_SYMBOL(__ffsdi2);
 #endif
diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c
index d7d21851e60c..3df3bd544492 100644
--- a/arch/um/drivers/mconsole_kern.c
+++ b/arch/um/drivers/mconsole_kern.c
@@ -147,7 +147,7 @@ void mconsole_proc(struct mc_request *req)
 	}
 
 	do {
-		loff_t pos;
+		loff_t pos = file->f_pos;
 		mm_segment_t old_fs = get_fs();
 		set_fs(KERNEL_DS);
 		len = vfs_read(file, buf, PAGE_SIZE - 1, &pos);
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 685692c94f05..fe120da25625 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2265,6 +2265,7 @@ source "fs/Kconfig.binfmt"
 config IA32_EMULATION
 	bool "IA32 Emulation"
 	depends on X86_64
+	select BINFMT_ELF
 	select COMPAT_BINFMT_ELF
 	select HAVE_UID16
 	---help---
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index 62fe22cd4cba..477e9d75149b 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -2681,56 +2681,68 @@ ENTRY(aesni_xts_crypt8)
 	addq %rcx, KEYP
 
 	movdqa IV, STATE1
-	pxor 0x00(INP), STATE1
+	movdqu 0x00(INP), INC
+	pxor INC, STATE1
 	movdqu IV, 0x00(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE2
-	pxor 0x10(INP), STATE2
+	movdqu 0x10(INP), INC
+	pxor INC, STATE2
 	movdqu IV, 0x10(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE3
-	pxor 0x20(INP), STATE3
+	movdqu 0x20(INP), INC
+	pxor INC, STATE3
 	movdqu IV, 0x20(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE4
-	pxor 0x30(INP), STATE4
+	movdqu 0x30(INP), INC
+	pxor INC, STATE4
 	movdqu IV, 0x30(OUTP)
 
 	call *%r11
 
-	pxor 0x00(OUTP), STATE1
+	movdqu 0x00(OUTP), INC
+	pxor INC, STATE1
 	movdqu STATE1, 0x00(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE1
-	pxor 0x40(INP), STATE1
+	movdqu 0x40(INP), INC
+	pxor INC, STATE1
 	movdqu IV, 0x40(OUTP)
 
-	pxor 0x10(OUTP), STATE2
+	movdqu 0x10(OUTP), INC
+	pxor INC, STATE2
 	movdqu STATE2, 0x10(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE2
-	pxor 0x50(INP), STATE2
+	movdqu 0x50(INP), INC
+	pxor INC, STATE2
 	movdqu IV, 0x50(OUTP)
 
-	pxor 0x20(OUTP), STATE3
+	movdqu 0x20(OUTP), INC
+	pxor INC, STATE3
 	movdqu STATE3, 0x20(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE3
-	pxor 0x60(INP), STATE3
+	movdqu 0x60(INP), INC
+	pxor INC, STATE3
 	movdqu IV, 0x60(OUTP)
 
-	pxor 0x30(OUTP), STATE4
+	movdqu 0x30(OUTP), INC
+	pxor INC, STATE4
 	movdqu STATE4, 0x30(OUTP)
 
 	_aesni_gf128mul_x_ble()
 	movdqa IV, STATE4
-	pxor 0x70(INP), STATE4
+	movdqu 0x70(INP), INC
+	pxor INC, STATE4
 	movdqu IV, 0x70(OUTP)
 
 	_aesni_gf128mul_x_ble()
@@ -2738,16 +2750,20 @@ ENTRY(aesni_xts_crypt8)
 
 	call *%r11
 
-	pxor 0x40(OUTP), STATE1
+	movdqu 0x40(OUTP), INC
+	pxor INC, STATE1
 	movdqu STATE1, 0x40(OUTP)
 
-	pxor 0x50(OUTP), STATE2
+	movdqu 0x50(OUTP), INC
+	pxor INC, STATE2
 	movdqu STATE2, 0x50(OUTP)
 
-	pxor 0x60(OUTP), STATE3
+	movdqu 0x60(OUTP), INC
+	pxor INC, STATE3
 	movdqu STATE3, 0x60(OUTP)
 
-	pxor 0x70(OUTP), STATE4
+	movdqu 0x70(OUTP), INC
+	pxor INC, STATE4
 	movdqu STATE4, 0x70(OUTP)
 
 	ret
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index 805078e08013..52ff81cce008 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -192,7 +192,7 @@ static int aout_core_dump(long signr, struct pt_regs *regs, struct file *file,
 	/* struct user */
 	DUMP_WRITE(&dump, sizeof(dump));
 	/* Now dump all of the user data.  Include malloced stuff as well */
-	DUMP_SEEK(PAGE_SIZE);
+	DUMP_SEEK(PAGE_SIZE - sizeof(dump));
 	/* now we start writing out the user space info */
 	set_fs(USER_DS);
 	/* Dump the data area */
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index ba870bb6dd8e..57873beb3292 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -41,4 +41,9 @@ extern int vector_used_by_percpu_irq(unsigned int vector);
 
 extern void init_ISA_irqs(void);
 
+#ifdef CONFIG_X86_LOCAL_APIC
+void arch_trigger_all_cpu_backtrace(void);
+#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
+#endif
+
 #endif /* _ASM_X86_IRQ_H */
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 6825e2efd1b4..6bc3985ee473 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -60,11 +60,11 @@ static inline void __exit exit_amd_microcode(void) {}
 #ifdef CONFIG_MICROCODE_EARLY
 #define MAX_UCODE_COUNT 128
 extern void __init load_ucode_bsp(void);
-extern __init void load_ucode_ap(void);
+extern void __cpuinit load_ucode_ap(void);
 extern int __init save_microcode_in_initrd(void);
 #else
 static inline void __init load_ucode_bsp(void) {}
-static inline __init void load_ucode_ap(void) {}
+static inline void __cpuinit load_ucode_ap(void) {}
 static inline int __init save_microcode_in_initrd(void)
 {
 	return 0;
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index c0fa356e90de..86f9301903c8 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -18,9 +18,7 @@ extern int proc_nmi_enabled(struct ctl_table *, int ,
 			void __user *, size_t *, loff_t *);
 extern int unknown_nmi_panic;
 
-void arch_trigger_all_cpu_backtrace(void);
-#define arch_trigger_all_cpu_backtrace arch_trigger_all_cpu_backtrace
-#endif
+#endif /* CONFIG_X86_LOCAL_APIC */
 
 #define NMI_FLAG_FIRST	1
 
diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c
index 31cb9ae992b7..a698d7165c96 100644
--- a/arch/x86/kernel/apic/hw_nmi.c
+++ b/arch/x86/kernel/apic/hw_nmi.c
@@ -9,6 +9,7 @@
  *
  */
 #include <asm/apic.h>
+#include <asm/nmi.h>
 
 #include <linux/cpumask.h>
 #include <linux/kdebug.h>
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 9239504b41cb..bf49cdbb010f 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -89,7 +89,10 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
 static DEFINE_PER_CPU(struct mce, mces_seen);
 static int			cpu_missing;
 
-/* MCA banks polled by the period polling timer for corrected events */
+/*
+ * MCA banks polled by the period polling timer for corrected events.
+ * With Intel CMCI, this only has MCA banks which do not support CMCI (if any).
+ */
 DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = {
 	[0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL
 };
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index ae1697c2afe3..d56405309dc1 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -24,6 +24,18 @@
  * Also supports reliable discovery of shared banks.
  */
 
+/*
+ * CMCI can be delivered to multiple cpus that share a machine check bank
+ * so we need to designate a single cpu to process errors logged in each bank
+ * in the interrupt handler (otherwise we would have many races and potential
+ * double reporting of the same error).
+ * Note that this can change when a cpu is offlined or brought online since
+ * some MCA banks are shared across cpus. When a cpu is offlined, cmci_clear()
+ * disables CMCI on all banks owned by the cpu and clears this bitfield. At
+ * this point, cmci_rediscover() kicks in and a different cpu may end up
+ * taking ownership of some of the shared MCA banks that were previously
+ * owned by the offlined cpu.
+ */
 static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);
 
 /*
diff --git a/arch/x86/kernel/cpu/mtrr/cleanup.c b/arch/x86/kernel/cpu/mtrr/cleanup.c
index 35ffda5d0727..5f90b85ff22e 100644
--- a/arch/x86/kernel/cpu/mtrr/cleanup.c
+++ b/arch/x86/kernel/cpu/mtrr/cleanup.c
@@ -714,15 +714,15 @@ int __init mtrr_cleanup(unsigned address_bits)
 	if (mtrr_tom2)
 		x_remove_size = (mtrr_tom2 >> PAGE_SHIFT) - x_remove_base;
 
-	nr_range = x86_get_mtrr_mem_range(range, 0, x_remove_base, x_remove_size);
 	/*
 	 * [0, 1M) should always be covered by var mtrr with WB
 	 * and fixed mtrrs should take effect before var mtrr for it:
 	 */
-	nr_range = add_range_with_merge(range, RANGE_NUM, nr_range, 0,
+	nr_range = add_range_with_merge(range, RANGE_NUM, 0, 0,
 					1ULL<<(20 - PAGE_SHIFT));
-	/* Sort the ranges: */
-	sort_range(range, nr_range);
+	/* add from var mtrr at last */
+	nr_range = x86_get_mtrr_mem_range(range, nr_range,
+					  x_remove_base, x_remove_size);
 
 	range_sums = sum_ranges(range, nr_range);
 	printk(KERN_INFO "total RAM covered: %ldM\n",
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index f60d41ff9a97..a9e22073bd56 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -165,13 +165,13 @@ static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
 	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
-	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
 	EVENT_EXTRA_END
 };
 
 static struct extra_reg intel_snbep_extra_regs[] __read_mostly = {
 	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
 	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
+	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
 	EVENT_EXTRA_END
 };
 
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index d2c381280e3c..3dd37ebd591b 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -242,6 +242,7 @@ void __init kvmclock_init(void)
 	if (!mem)
 		return;
 	hv_clock = __va(mem);
+	memset(hv_clock, 0, size);
 
 	if (kvm_register_clock("boot clock")) {
 		hv_clock = NULL;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 4e7a37ff03ab..81a5f5e8f142 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -277,18 +277,6 @@ void exit_idle(void)
 }
 #endif
 
-void arch_cpu_idle_prepare(void)
-{
-	/*
-	 * If we're the non-boot CPU, nothing set the stack canary up
-	 * for us.  CPU0 already has it initialized but no harm in
-	 * doing it again.  This is a good place for updating it, as
-	 * we wont ever return from this function (so the invalid
-	 * canaries already on the stack wont ever trigger).
-	 */
-	boot_init_stack_canary();
-}
-
 void arch_cpu_idle_enter(void)
 {
 	local_touch_nmi();
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 9c73b51817e4..bfd348e99369 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -372,15 +372,15 @@ static bool __cpuinit match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 
 void __cpuinit set_cpu_sibling_map(int cpu)
 {
-	bool has_mc = boot_cpu_data.x86_max_cores > 1;
 	bool has_smt = smp_num_siblings > 1;
+	bool has_mp = has_smt || boot_cpu_data.x86_max_cores > 1;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct cpuinfo_x86 *o;
 	int i;
 
 	cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
 
-	if (!has_smt && !has_mc) {
+	if (!has_mp) {
 		cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
 		cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
 		cpumask_set_cpu(cpu, cpu_core_mask(cpu));
@@ -394,7 +394,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 		if ((i == cpu) || (has_smt && match_smt(c, o)))
 			link_mask(sibling, cpu, i);
 
-		if ((i == cpu) || (has_mc && match_llc(c, o)))
+		if ((i == cpu) || (has_mp && match_llc(c, o)))
 			link_mask(llc_shared, cpu, i);
 
 	}
@@ -406,7 +406,7 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		o = &cpu_data(i);
 
-		if ((i == cpu) || (has_mc && match_mc(c, o))) {
+		if ((i == cpu) || (has_mp && match_mc(c, o))) {
 			link_mask(core, cpu, i);
 
 			/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 094b5d96ab14..e8ba99c34180 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -582,8 +582,6 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 	if (index != XCR_XFEATURE_ENABLED_MASK)
 		return 1;
 	xcr0 = xcr;
-	if (kvm_x86_ops->get_cpl(vcpu) != 0)
-		return 1;
 	if (!(xcr0 & XSTATE_FP))
 		return 1;
 	if ((xcr0 & XSTATE_YMM) && !(xcr0 & XSTATE_SSE))
@@ -597,7 +595,8 @@ int __kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 
 int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr)
 {
-	if (__kvm_set_xcr(vcpu, index, xcr)) {
+	if (kvm_x86_ops->get_cpl(vcpu) != 0 ||
+	    __kvm_set_xcr(vcpu, index, xcr)) {
 		kvm_inject_gp(vcpu, 0);
 		return 1;
 	}
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index 5ae2eb09419e..d2fbcedcf6ea 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -1069,7 +1069,10 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
 		 * that by attempting to use more space than is available.
 		 */
 		unsigned long dummy_size = remaining_size + 1024;
-		void *dummy = kmalloc(dummy_size, GFP_ATOMIC);
+		void *dummy = kzalloc(dummy_size, GFP_ATOMIC);
+
+		if (!dummy)
+			return EFI_OUT_OF_RESOURCES;
 
 		status = efi.set_variable(efi_dummy_name, &EFI_DUMMY_GUID,
 					  EFI_VARIABLE_NON_VOLATILE |
@@ -1089,6 +1092,8 @@ efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
 					 0, dummy);
 		}
 
+		kfree(dummy);
+
 		/*
 		 * The runtime code may now have triggered a garbage collection
 		 * run, so check the variable info again
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 652fd5ce303c..cab13f2fc28e 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -164,15 +164,24 @@ static int acpi_lpss_create_device(struct acpi_device *adev,
 	if (dev_desc->clk_required) {
 		ret = register_device_clock(adev, pdata);
 		if (ret) {
-			/*
-			 * Skip the device, but don't terminate the namespace
-			 * scan.
-			 */
-			kfree(pdata);
-			return 0;
+			/* Skip the device, but continue the namespace scan. */
+			ret = 0;
+			goto err_out;
 		}
 	}
 
+	/*
+	 * This works around a known issue in ACPI tables where LPSS devices
+	 * have _PS0 and _PS3 without _PSC (and no power resources), so
+	 * acpi_bus_init_power() will assume that the BIOS has put them into D0.
+	 */
+	ret = acpi_device_fix_up_power(adev);
+	if (ret) {
+		/* Skip the device, but continue the namespace scan. */
+		ret = 0;
+		goto err_out;
+	}
+
 	adev->driver_data = pdata;
 	ret = acpi_create_platform_device(adev, id);
 	if (ret > 0)
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 318fa32a141e..31c217a42839 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -290,6 +290,26 @@ int acpi_bus_init_power(struct acpi_device *device)
 	return 0;
 }
 
+/**
+ * acpi_device_fix_up_power - Force device with missing _PSC into D0.
+ * @device: Device object whose power state is to be fixed up.
+ *
+ * Devices without power resources and _PSC, but having _PS0 and _PS3 defined,
+ * are assumed to be put into D0 by the BIOS.  However, in some cases that may
+ * not be the case and this function should be used then.
+ */
+int acpi_device_fix_up_power(struct acpi_device *device)
+{
+	int ret = 0;
+
+	if (!device->power.flags.power_resources
+	    && !device->power.flags.explicit_get
+	    && device->power.state == ACPI_STATE_D0)
+		ret = acpi_dev_pm_explicit_set(device, ACPI_STATE_D0);
+
+	return ret;
+}
+
 int acpi_bus_update_power(acpi_handle handle, int *state_p)
 {
 	struct acpi_device *device;
diff --git a/drivers/acpi/dock.c b/drivers/acpi/dock.c
index 4fdea381ef21..ec117c6c996c 100644
--- a/drivers/acpi/dock.c
+++ b/drivers/acpi/dock.c
@@ -868,8 +868,10 @@ static ssize_t write_undock(struct device *dev, struct device_attribute *attr,
 	if (!count)
 		return -EINVAL;
 
+	acpi_scan_lock_acquire();
 	begin_undock(dock_station);
 	ret = handle_eject_request(dock_station, ACPI_NOTIFY_EJECT_REQUEST);
+	acpi_scan_lock_release();
 	return ret ? ret: count;
 }
 static DEVICE_ATTR(undock, S_IWUSR, NULL, write_undock);
diff --git a/drivers/acpi/power.c b/drivers/acpi/power.c
index f962047c6c85..288bb270f8ed 100644
--- a/drivers/acpi/power.c
+++ b/drivers/acpi/power.c
@@ -885,6 +885,7 @@ int acpi_add_power_resource(acpi_handle handle)
 				ACPI_STA_DEFAULT);
 	mutex_init(&resource->resource_lock);
 	INIT_LIST_HEAD(&resource->dependent);
+	INIT_LIST_HEAD(&resource->list_node);
 	resource->name = device->pnp.bus_id;
 	strcpy(acpi_device_name(device), ACPI_POWER_DEVICE_NAME);
 	strcpy(acpi_device_class(device), ACPI_POWER_CLASS);
diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
index a3868f6c222a..3322b47ab7ca 100644
--- a/drivers/acpi/resource.c
+++ b/drivers/acpi/resource.c
@@ -304,7 +304,8 @@ static void acpi_dev_irqresource_disabled(struct resource *res, u32 gsi)
 }
 
 static void acpi_dev_get_irqresource(struct resource *res, u32 gsi,
-				     u8 triggering, u8 polarity, u8 shareable)
+				     u8 triggering, u8 polarity, u8 shareable,
+				     bool legacy)
 {
 	int irq, p, t;
 
@@ -317,14 +318,19 @@ static void acpi_dev_get_irqresource(struct resource *res, u32 gsi,
 	 * In IO-APIC mode, use overrided attribute. Two reasons:
 	 * 1. BIOS bug in DSDT
 	 * 2. BIOS uses IO-APIC mode Interrupt Source Override
+	 *
+	 * We do this only if we are dealing with IRQ() or IRQNoFlags()
+	 * resource (the legacy ISA resources). With modern ACPI 5 devices
+	 * using extended IRQ descriptors we take the IRQ configuration
+	 * from _CRS directly.
 	 */
-	if (!acpi_get_override_irq(gsi, &t, &p)) {
+	if (legacy && !acpi_get_override_irq(gsi, &t, &p)) {
 		u8 trig = t ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
 		u8 pol = p ? ACPI_ACTIVE_LOW : ACPI_ACTIVE_HIGH;
 
 		if (triggering != trig || polarity != pol) {
 			pr_warning("ACPI: IRQ %d override to %s, %s\n", gsi,
-				   t ? "edge" : "level", p ? "low" : "high");
+				   t ? "level" : "edge", p ? "low" : "high");
 			triggering = trig;
 			polarity = pol;
 		}
@@ -373,7 +379,7 @@ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index,
 		}
 		acpi_dev_get_irqresource(res, irq->interrupts[index],
 					 irq->triggering, irq->polarity,
-					 irq->sharable);
+					 irq->sharable, true);
 		break;
 	case ACPI_RESOURCE_TYPE_EXTENDED_IRQ:
 		ext_irq = &ares->data.extended_irq;
@@ -383,7 +389,7 @@ bool acpi_dev_resource_interrupt(struct acpi_resource *ares, int index,
 		}
 		acpi_dev_get_irqresource(res, ext_irq->interrupts[index],
 					 ext_irq->triggering, ext_irq->polarity,
-					 ext_irq->sharable);
+					 ext_irq->sharable, false);
 		break;
 	default:
 		return false;
diff --git a/drivers/base/firmware_class.c b/drivers/base/firmware_class.c
index 4b1f9265887f..01e21037d8fe 100644
--- a/drivers/base/firmware_class.c
+++ b/drivers/base/firmware_class.c
@@ -450,8 +450,18 @@ static void fw_load_abort(struct firmware_priv *fw_priv)
 {
 	struct firmware_buf *buf = fw_priv->buf;
 
+	/*
+	 * There is a small window in which user can write to 'loading'
+	 * between loading done and disappearance of 'loading'
+	 */
+	if (test_bit(FW_STATUS_DONE, &buf->status))
+		return;
+
 	set_bit(FW_STATUS_ABORT, &buf->status);
 	complete_all(&buf->completion);
+
+	/* avoid user action after loading abort */
+	fw_priv->buf = NULL;
 }
 
 #define is_fw_load_aborted(buf)	\
@@ -528,7 +538,12 @@ static ssize_t firmware_loading_show(struct device *dev,
 				     struct device_attribute *attr, char *buf)
 {
 	struct firmware_priv *fw_priv = to_firmware_priv(dev);
-	int loading = test_bit(FW_STATUS_LOADING, &fw_priv->buf->status);
+	int loading = 0;
+
+	mutex_lock(&fw_lock);
+	if (fw_priv->buf)
+		loading = test_bit(FW_STATUS_LOADING, &fw_priv->buf->status);
+	mutex_unlock(&fw_lock);
 
 	return sprintf(buf, "%d\n", loading);
 }
@@ -570,12 +585,12 @@ static ssize_t firmware_loading_store(struct device *dev,
 				      const char *buf, size_t count)
 {
 	struct firmware_priv *fw_priv = to_firmware_priv(dev);
-	struct firmware_buf *fw_buf = fw_priv->buf;
+	struct firmware_buf *fw_buf;
 	int loading = simple_strtol(buf, NULL, 10);
 	int i;
 
 	mutex_lock(&fw_lock);
-
+	fw_buf = fw_priv->buf;
 	if (!fw_buf)
 		goto out;
 
@@ -777,10 +792,6 @@ static void firmware_class_timeout_work(struct work_struct *work)
 			struct firmware_priv, timeout_work.work);
 
 	mutex_lock(&fw_lock);
-	if (test_bit(FW_STATUS_DONE, &(fw_priv->buf->status))) {
-		mutex_unlock(&fw_lock);
-		return;
-	}
 	fw_load_abort(fw_priv);
 	mutex_unlock(&fw_lock);
 }
@@ -861,8 +872,6 @@ static int _request_firmware_load(struct firmware_priv *fw_priv, bool uevent,
 
 	cancel_delayed_work_sync(&fw_priv->timeout_work);
 
-	fw_priv->buf = NULL;
-
 	device_remove_file(f_dev, &dev_attr_loading);
 err_del_bin_attr:
 	device_remove_bin_file(f_dev, &firmware_attr_data);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 3063452e55da..49394e3f31bc 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -1036,12 +1036,16 @@ static const char *rbd_segment_name(struct rbd_device *rbd_dev, u64 offset)
 	char *name;
 	u64 segment;
 	int ret;
+	char *name_format;
 
 	name = kmem_cache_alloc(rbd_segment_name_cache, GFP_NOIO);
 	if (!name)
 		return NULL;
 	segment = offset >> rbd_dev->header.obj_order;
-	ret = snprintf(name, MAX_OBJ_NAME_SIZE + 1, "%s.%012llx",
+	name_format = "%s.%012llx";
+	if (rbd_dev->image_format == 2)
+		name_format = "%s.%016llx";
+	ret = snprintf(name, MAX_OBJ_NAME_SIZE + 1, name_format,
 			rbd_dev->header.object_prefix, segment);
 	if (ret < 0 || ret > MAX_OBJ_NAME_SIZE) {
 		pr_err("error formatting segment name for #%llu (%d)\n",
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index dcde35231e25..5b7b9110254b 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -190,8 +190,7 @@ struct dma_buf *drm_gem_prime_export(struct drm_device *dev,
 		if (ret)
 			return ERR_PTR(ret);
 	}
-	return dma_buf_export(obj, &drm_gem_prime_dmabuf_ops, obj->size,
-			      0600);
+	return dma_buf_export(obj, &drm_gem_prime_dmabuf_ops, obj->size, flags);
 }
 EXPORT_SYMBOL(drm_gem_prime_export);
 
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 0e5341695922..6948eb88c2b7 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -2687,6 +2687,9 @@ void r600_uvd_rbc_stop(struct radeon_device *rdev)
 int r600_uvd_init(struct radeon_device *rdev)
 {
 	int i, j, r;
+	/* disable byte swapping */
+	u32 lmi_swap_cntl = 0;
+	u32 mp_swap_cntl = 0;
 
 	/* raise clocks while booting up the VCPU */
 	radeon_set_uvd_clocks(rdev, 53300, 40000);
@@ -2711,9 +2714,13 @@ int r600_uvd_init(struct radeon_device *rdev)
 	WREG32(UVD_LMI_CTRL, 0x40 | (1 << 8) | (1 << 13) |
 			     (1 << 21) | (1 << 9) | (1 << 20));
 
-	/* disable byte swapping */
-	WREG32(UVD_LMI_SWAP_CNTL, 0);
-	WREG32(UVD_MP_SWAP_CNTL, 0);
+#ifdef __BIG_ENDIAN
+	/* swap (8 in 32) RB and IB */
+	lmi_swap_cntl = 0xa;
+	mp_swap_cntl = 0;
+#endif
+	WREG32(UVD_LMI_SWAP_CNTL, lmi_swap_cntl);
+	WREG32(UVD_MP_SWAP_CNTL, mp_swap_cntl);
 
 	WREG32(UVD_MPC_SET_MUXA0, 0x40c2040);
 	WREG32(UVD_MPC_SET_MUXA1, 0x0);
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 189973836cff..b0dc0b6cb4e0 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -244,16 +244,6 @@ void radeon_scratch_free(struct radeon_device *rdev, uint32_t reg)
  */
 void radeon_wb_disable(struct radeon_device *rdev)
 {
-	int r;
-
-	if (rdev->wb.wb_obj) {
-		r = radeon_bo_reserve(rdev->wb.wb_obj, false);
-		if (unlikely(r != 0))
-			return;
-		radeon_bo_kunmap(rdev->wb.wb_obj);
-		radeon_bo_unpin(rdev->wb.wb_obj);
-		radeon_bo_unreserve(rdev->wb.wb_obj);
-	}
 	rdev->wb.enabled = false;
 }
 
@@ -269,6 +259,11 @@ void radeon_wb_fini(struct radeon_device *rdev)
 {
 	radeon_wb_disable(rdev);
 	if (rdev->wb.wb_obj) {
+		if (!radeon_bo_reserve(rdev->wb.wb_obj, false)) {
+			radeon_bo_kunmap(rdev->wb.wb_obj);
+			radeon_bo_unpin(rdev->wb.wb_obj);
+			radeon_bo_unreserve(rdev->wb.wb_obj);
+		}
 		radeon_bo_unref(&rdev->wb.wb_obj);
 		rdev->wb.wb = NULL;
 		rdev->wb.wb_obj = NULL;
@@ -295,26 +290,26 @@ int radeon_wb_init(struct radeon_device *rdev)
 			dev_warn(rdev->dev, "(%d) create WB bo failed\n", r);
 			return r;
 		}
-	}
-	r = radeon_bo_reserve(rdev->wb.wb_obj, false);
-	if (unlikely(r != 0)) {
-		radeon_wb_fini(rdev);
-		return r;
-	}
-	r = radeon_bo_pin(rdev->wb.wb_obj, RADEON_GEM_DOMAIN_GTT,
-			  &rdev->wb.gpu_addr);
-	if (r) {
+		r = radeon_bo_reserve(rdev->wb.wb_obj, false);
+		if (unlikely(r != 0)) {
+			radeon_wb_fini(rdev);
+			return r;
+		}
+		r = radeon_bo_pin(rdev->wb.wb_obj, RADEON_GEM_DOMAIN_GTT,
+				&rdev->wb.gpu_addr);
+		if (r) {
+			radeon_bo_unreserve(rdev->wb.wb_obj);
+			dev_warn(rdev->dev, "(%d) pin WB bo failed\n", r);
+			radeon_wb_fini(rdev);
+			return r;
+		}
+		r = radeon_bo_kmap(rdev->wb.wb_obj, (void **)&rdev->wb.wb);
 		radeon_bo_unreserve(rdev->wb.wb_obj);
-		dev_warn(rdev->dev, "(%d) pin WB bo failed\n", r);
-		radeon_wb_fini(rdev);
-		return r;
-	}
-	r = radeon_bo_kmap(rdev->wb.wb_obj, (void **)&rdev->wb.wb);
-	radeon_bo_unreserve(rdev->wb.wb_obj);
-	if (r) {
-		dev_warn(rdev->dev, "(%d) map WB bo failed\n", r);
-		radeon_wb_fini(rdev);
-		return r;
+		if (r) {
+			dev_warn(rdev->dev, "(%d) map WB bo failed\n", r);
+			radeon_wb_fini(rdev);
+			return r;
+		}
 	}
 
 	/* clear wb memory */
diff --git a/drivers/gpu/drm/radeon/radeon_fence.c b/drivers/gpu/drm/radeon/radeon_fence.c
index 5b937dfe6f65..ddb8f8e04eb5 100644
--- a/drivers/gpu/drm/radeon/radeon_fence.c
+++ b/drivers/gpu/drm/radeon/radeon_fence.c
@@ -63,7 +63,9 @@ static void radeon_fence_write(struct radeon_device *rdev, u32 seq, int ring)
 {
 	struct radeon_fence_driver *drv = &rdev->fence_drv[ring];
 	if (likely(rdev->wb.enabled || !drv->scratch_reg)) {
-		*drv->cpu_addr = cpu_to_le32(seq);
+		if (drv->cpu_addr) {
+			*drv->cpu_addr = cpu_to_le32(seq);
+		}
 	} else {
 		WREG32(drv->scratch_reg, seq);
 	}
@@ -84,7 +86,11 @@ static u32 radeon_fence_read(struct radeon_device *rdev, int ring)
 	u32 seq = 0;
 
 	if (likely(rdev->wb.enabled || !drv->scratch_reg)) {
-		seq = le32_to_cpu(*drv->cpu_addr);
+		if (drv->cpu_addr) {
+			seq = le32_to_cpu(*drv->cpu_addr);
+		} else {
+			seq = lower_32_bits(atomic64_read(&drv->last_seq));
+		}
 	} else {
 		seq = RREG32(drv->scratch_reg);
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_gart.c b/drivers/gpu/drm/radeon/radeon_gart.c
index 2c1341f63dc5..43ec4a401f07 100644
--- a/drivers/gpu/drm/radeon/radeon_gart.c
+++ b/drivers/gpu/drm/radeon/radeon_gart.c
@@ -1197,11 +1197,13 @@ int radeon_vm_bo_update_pte(struct radeon_device *rdev,
 int radeon_vm_bo_rmv(struct radeon_device *rdev,
 		     struct radeon_bo_va *bo_va)
 {
-	int r;
+	int r = 0;
 
 	mutex_lock(&rdev->vm_manager.lock);
 	mutex_lock(&bo_va->vm->mutex);
-	r = radeon_vm_bo_update_pte(rdev, bo_va->vm, bo_va->bo, NULL);
+	if (bo_va->soffset) {
+		r = radeon_vm_bo_update_pte(rdev, bo_va->vm, bo_va->bo, NULL);
+	}
 	mutex_unlock(&rdev->vm_manager.lock);
 	list_del(&bo_va->vm_list);
 	mutex_unlock(&bo_va->vm->mutex);
diff --git a/drivers/gpu/drm/radeon/radeon_ring.c b/drivers/gpu/drm/radeon/radeon_ring.c
index e17faa7cf732..82434018cbe8 100644
--- a/drivers/gpu/drm/radeon/radeon_ring.c
+++ b/drivers/gpu/drm/radeon/radeon_ring.c
@@ -402,6 +402,13 @@ int radeon_ring_alloc(struct radeon_device *rdev, struct radeon_ring *ring, unsi
 		return -ENOMEM;
 	/* Align requested size with padding so unlock_commit can
 	 * pad safely */
+	radeon_ring_free_size(rdev, ring);
+	if (ring->ring_free_dw == (ring->ring_size / 4)) {
+		/* This is an empty ring update lockup info to avoid
+		 * false positive.
+		 */
+		radeon_ring_lockup_update(ring);
+	}
 	ndw = (ndw + ring->align_mask) & ~ring->align_mask;
 	while (ndw > (ring->ring_free_dw - 1)) {
 		radeon_ring_free_size(rdev, ring);
diff --git a/drivers/gpu/drm/radeon/radeon_uvd.c b/drivers/gpu/drm/radeon/radeon_uvd.c
index 906e5c0ca3b9..cad735dd02c6 100644
--- a/drivers/gpu/drm/radeon/radeon_uvd.c
+++ b/drivers/gpu/drm/radeon/radeon_uvd.c
@@ -159,7 +159,17 @@ int radeon_uvd_suspend(struct radeon_device *rdev)
 	if (!r) {
 		radeon_bo_kunmap(rdev->uvd.vcpu_bo);
 		radeon_bo_unpin(rdev->uvd.vcpu_bo);
+		rdev->uvd.cpu_addr = NULL;
+		if (!radeon_bo_pin(rdev->uvd.vcpu_bo, RADEON_GEM_DOMAIN_CPU, NULL)) {
+			radeon_bo_kmap(rdev->uvd.vcpu_bo, &rdev->uvd.cpu_addr);
+		}
 		radeon_bo_unreserve(rdev->uvd.vcpu_bo);
+
+		if (rdev->uvd.cpu_addr) {
+			radeon_fence_driver_start_ring(rdev, R600_RING_TYPE_UVD_INDEX);
+		} else {
+			rdev->fence_drv[R600_RING_TYPE_UVD_INDEX].cpu_addr = NULL;
+		}
 	}
 	return r;
 }
@@ -178,6 +188,10 @@ int radeon_uvd_resume(struct radeon_device *rdev)
 		return r;
 	}
 
+	/* Have been pin in cpu unmap unpin */
+	radeon_bo_kunmap(rdev->uvd.vcpu_bo);
+	radeon_bo_unpin(rdev->uvd.vcpu_bo);
+
 	r = radeon_bo_pin(rdev->uvd.vcpu_bo, RADEON_GEM_DOMAIN_VRAM,
 			  &rdev->uvd.gpu_addr);
 	if (r) {
@@ -613,19 +627,19 @@ int radeon_uvd_get_create_msg(struct radeon_device *rdev, int ring,
 	}
 
 	/* stitch together an UVD create msg */
-	msg[0] = 0x00000de4;
-	msg[1] = 0x00000000;
-	msg[2] = handle;
-	msg[3] = 0x00000000;
-	msg[4] = 0x00000000;
-	msg[5] = 0x00000000;
-	msg[6] = 0x00000000;
-	msg[7] = 0x00000780;
-	msg[8] = 0x00000440;
-	msg[9] = 0x00000000;
-	msg[10] = 0x01b37000;
+	msg[0] = cpu_to_le32(0x00000de4);
+	msg[1] = cpu_to_le32(0x00000000);
+	msg[2] = cpu_to_le32(handle);
+	msg[3] = cpu_to_le32(0x00000000);
+	msg[4] = cpu_to_le32(0x00000000);
+	msg[5] = cpu_to_le32(0x00000000);
+	msg[6] = cpu_to_le32(0x00000000);
+	msg[7] = cpu_to_le32(0x00000780);
+	msg[8] = cpu_to_le32(0x00000440);
+	msg[9] = cpu_to_le32(0x00000000);
+	msg[10] = cpu_to_le32(0x01b37000);
 	for (i = 11; i < 1024; ++i)
-		msg[i] = 0x0;
+		msg[i] = cpu_to_le32(0x0);
 
 	radeon_bo_kunmap(bo);
 	radeon_bo_unreserve(bo);
@@ -659,12 +673,12 @@ int radeon_uvd_get_destroy_msg(struct radeon_device *rdev, int ring,
 	}
 
 	/* stitch together an UVD destroy msg */
-	msg[0] = 0x00000de4;
-	msg[1] = 0x00000002;
-	msg[2] = handle;
-	msg[3] = 0x00000000;
+	msg[0] = cpu_to_le32(0x00000de4);
+	msg[1] = cpu_to_le32(0x00000002);
+	msg[2] = cpu_to_le32(handle);
+	msg[3] = cpu_to_le32(0x00000000);
 	for (i = 4; i < 1024; ++i)
-		msg[i] = 0x0;
+		msg[i] = cpu_to_le32(0x0);
 
 	radeon_bo_kunmap(bo);
 	radeon_bo_unreserve(bo);
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index 1760ceb68b7b..19ceaa60e0f4 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -705,7 +705,7 @@ static int gic_irq_domain_xlate(struct irq_domain *d,
 static int __cpuinit gic_secondary_init(struct notifier_block *nfb,
 					unsigned long action, void *hcpu)
 {
-	if (action == CPU_STARTING)
+	if (action == CPU_STARTING || action == CPU_STARTING_FROZEN)
 		gic_cpu_init(&gic_data[0]);
 	return NOTIFY_OK;
 }
diff --git a/drivers/media/Kconfig b/drivers/media/Kconfig
index 7f5a7cac6dc7..8270388e2a0d 100644
--- a/drivers/media/Kconfig
+++ b/drivers/media/Kconfig
@@ -136,9 +136,9 @@ config DVB_NET
 
 # This Kconfig option is used by both PCI and USB drivers
 config TTPCI_EEPROM
-        tristate
-        depends on I2C
-        default n
+	tristate
+	depends on I2C
+	default n
 
 source "drivers/media/dvb-core/Kconfig"
 
@@ -189,6 +189,12 @@ config MEDIA_SUBDRV_AUTOSELECT
 
 	  If unsure say Y.
 
+config MEDIA_ATTACH
+	bool
+	depends on MEDIA_ANALOG_TV_SUPPORT || MEDIA_DIGITAL_TV_SUPPORT || MEDIA_RADIO_SUPPORT
+	depends on MODULES
+	default MODULES
+
 source "drivers/media/i2c/Kconfig"
 source "drivers/media/tuners/Kconfig"
 source "drivers/media/dvb-frontends/Kconfig"
diff --git a/drivers/media/platform/exynos4-is/fimc-is.c b/drivers/media/platform/exynos4-is/fimc-is.c
index 520e4398b69c..0741945b79ed 100644
--- a/drivers/media/platform/exynos4-is/fimc-is.c
+++ b/drivers/media/platform/exynos4-is/fimc-is.c
@@ -834,23 +834,11 @@ static int fimc_is_probe(struct platform_device *pdev)
 		goto err_clk;
 	}
 	pm_runtime_enable(dev);
-	/*
-	 * Enable only the ISP power domain, keep FIMC-IS clocks off until
-	 * the whole clock tree is configured. The ISP power domain needs
-	 * be active in order to acces any CMU_ISP clock registers.
-	 */
-	ret = pm_runtime_get_sync(dev);
-	if (ret < 0)
-		goto err_irq;
-
-	ret = fimc_is_setup_clocks(is);
-	pm_runtime_put_sync(dev);
 
+	ret = pm_runtime_get_sync(dev);
 	if (ret < 0)
 		goto err_irq;
 
-	is->clk_init = true;
-
 	is->alloc_ctx = vb2_dma_contig_init_ctx(dev);
 	if (IS_ERR(is->alloc_ctx)) {
 		ret = PTR_ERR(is->alloc_ctx);
@@ -872,6 +860,8 @@ static int fimc_is_probe(struct platform_device *pdev)
 	if (ret < 0)
 		goto err_dfs;
 
+	pm_runtime_put_sync(dev);
+
 	dev_dbg(dev, "FIMC-IS registered successfully\n");
 	return 0;
 
@@ -891,9 +881,11 @@ err_clk:
 static int fimc_is_runtime_resume(struct device *dev)
 {
 	struct fimc_is *is = dev_get_drvdata(dev);
+	int ret;
 
-	if (!is->clk_init)
-		return 0;
+	ret = fimc_is_setup_clocks(is);
+	if (ret)
+		return ret;
 
 	return fimc_is_enable_clocks(is);
 }
@@ -902,9 +894,7 @@ static int fimc_is_runtime_suspend(struct device *dev)
 {
 	struct fimc_is *is = dev_get_drvdata(dev);
 
-	if (is->clk_init)
-		fimc_is_disable_clocks(is);
-
+	fimc_is_disable_clocks(is);
 	return 0;
 }
 
diff --git a/drivers/media/platform/exynos4-is/fimc-is.h b/drivers/media/platform/exynos4-is/fimc-is.h
index 606a7c9fe526..d7db133b493f 100644
--- a/drivers/media/platform/exynos4-is/fimc-is.h
+++ b/drivers/media/platform/exynos4-is/fimc-is.h
@@ -264,7 +264,6 @@ struct fimc_is {
 	spinlock_t			slock;
 
 	struct clk			*clocks[ISS_CLKS_MAX];
-	bool				clk_init;
 	void __iomem			*regs;
 	void __iomem			*pmu_regs;
 	int				irq;
diff --git a/drivers/media/platform/s5p-jpeg/Makefile b/drivers/media/platform/s5p-jpeg/Makefile
index ddc2900d88a2..d18cb5edd2d5 100644
--- a/drivers/media/platform/s5p-jpeg/Makefile
+++ b/drivers/media/platform/s5p-jpeg/Makefile
@@ -1,2 +1,2 @@
 s5p-jpeg-objs := jpeg-core.o
-obj-$(CONFIG_VIDEO_SAMSUNG_S5P_JPEG) := s5p-jpeg.o
+obj-$(CONFIG_VIDEO_SAMSUNG_S5P_JPEG) += s5p-jpeg.o
diff --git a/drivers/media/platform/s5p-mfc/Makefile b/drivers/media/platform/s5p-mfc/Makefile
index 379008c6d09a..15f59b324fef 100644
--- a/drivers/media/platform/s5p-mfc/Makefile
+++ b/drivers/media/platform/s5p-mfc/Makefile
@@ -1,4 +1,4 @@
-obj-$(CONFIG_VIDEO_SAMSUNG_S5P_MFC) := s5p-mfc.o
+obj-$(CONFIG_VIDEO_SAMSUNG_S5P_MFC) += s5p-mfc.o
 s5p-mfc-y += s5p_mfc.o s5p_mfc_intr.o
 s5p-mfc-y += s5p_mfc_dec.o s5p_mfc_enc.o
 s5p-mfc-y += s5p_mfc_ctrl.o s5p_mfc_pm.o
diff --git a/drivers/media/tuners/Kconfig b/drivers/media/tuners/Kconfig
index f6768cad001a..15665debc572 100644
--- a/drivers/media/tuners/Kconfig
+++ b/drivers/media/tuners/Kconfig
@@ -1,23 +1,3 @@
-config MEDIA_ATTACH
-	bool "Load and attach frontend and tuner driver modules as needed"
-	depends on MEDIA_ANALOG_TV_SUPPORT || MEDIA_DIGITAL_TV_SUPPORT || MEDIA_RADIO_SUPPORT
-	depends on MODULES
-	default y if !EXPERT
-	help
-	  Remove the static dependency of DVB card drivers on all
-	  frontend modules for all possible card variants. Instead,
-	  allow the card drivers to only load the frontend modules
-	  they require.
-
-	  Also, tuner module will automatically load a tuner driver
-	  when needed, for analog mode.
-
-	  This saves several KBytes of memory.
-
-	  Note: You will need module-init-tools v3.2 or later for this feature.
-
-	  If unsure say Y.
-
 # Analog TV tuners, auto-loaded via tuner.ko
 config MEDIA_TUNER
 	tristate
diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index 22015fe1a0f3..2cc8ec70e3b6 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -376,7 +376,7 @@ static int rtl2832u_read_config(struct dvb_usb_device *d)
 	struct rtl28xxu_req req_mxl5007t = {0xd9c0, CMD_I2C_RD, 1, buf};
 	struct rtl28xxu_req req_e4000 = {0x02c8, CMD_I2C_RD, 1, buf};
 	struct rtl28xxu_req req_tda18272 = {0x00c0, CMD_I2C_RD, 2, buf};
-	struct rtl28xxu_req req_r820t = {0x0034, CMD_I2C_RD, 5, buf};
+	struct rtl28xxu_req req_r820t = {0x0034, CMD_I2C_RD, 1, buf};
 
 	dev_dbg(&d->udev->dev, "%s:\n", __func__);
 
@@ -481,9 +481,9 @@ static int rtl2832u_read_config(struct dvb_usb_device *d)
 		goto found;
 	}
 
-	/* check R820T by reading tuner stats at I2C addr 0x1a */
+	/* check R820T ID register; reg=00 val=69 */
 	ret = rtl28xxu_ctrl_msg(d, &req_r820t);
-	if (ret == 0) {
+	if (ret == 0 && buf[0] == 0x69) {
 		priv->tuner = TUNER_RTL2832_R820T;
 		priv->tuner_name = "R820T";
 		goto found;
diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c
index 9544cdc0d1af..e79e006eb9ab 100644
--- a/drivers/parisc/iosapic.c
+++ b/drivers/parisc/iosapic.c
@@ -811,6 +811,70 @@ int iosapic_fixup_irq(void *isi_obj, struct pci_dev *pcidev)
 	return pcidev->irq;
 }
 
+static struct iosapic_info *first_isi = NULL;
+
+#ifdef CONFIG_64BIT
+int iosapic_serial_irq(int num)
+{
+	struct iosapic_info *isi = first_isi;
+	struct irt_entry *irte = NULL;  /* only used if PAT PDC */
+	struct vector_info *vi;
+	int isi_line;	/* line used by device */
+
+	/* lookup IRT entry for isi/slot/pin set */
+	irte = &irt_cell[num];
+
+	DBG_IRT("iosapic_serial_irq(): irte %p %x %x %x %x %x %x %x %x\n",
+		irte,
+		irte->entry_type,
+		irte->entry_length,
+		irte->polarity_trigger,
+		irte->src_bus_irq_devno,
+		irte->src_bus_id,
+		irte->src_seg_id,
+		irte->dest_iosapic_intin,
+		(u32) irte->dest_iosapic_addr);
+	isi_line = irte->dest_iosapic_intin;
+
+	/* get vector info for this input line */
+	vi = isi->isi_vector + isi_line;
+	DBG_IRT("iosapic_serial_irq:  line %d vi 0x%p\n", isi_line, vi);
+
+	/* If this IRQ line has already been setup, skip it */
+	if (vi->irte)
+		goto out;
+
+	vi->irte = irte;
+
+	/*
+	 * Allocate processor IRQ
+	 *
+	 * XXX/FIXME The txn_alloc_irq() code and related code should be
+	 * moved to enable_irq(). That way we only allocate processor IRQ
+	 * bits for devices that actually have drivers claiming them.
+	 * Right now we assign an IRQ to every PCI device present,
+	 * regardless of whether it's used or not.
+	 */
+	vi->txn_irq = txn_alloc_irq(8);
+
+	if (vi->txn_irq < 0)
+		panic("I/O sapic: couldn't get TXN IRQ\n");
+
+	/* enable_irq() will use txn_* to program IRdT */
+	vi->txn_addr = txn_alloc_addr(vi->txn_irq);
+	vi->txn_data = txn_alloc_data(vi->txn_irq);
+
+	vi->eoi_addr = isi->addr + IOSAPIC_REG_EOI;
+	vi->eoi_data = cpu_to_le32(vi->txn_data);
+
+	cpu_claim_irq(vi->txn_irq, &iosapic_interrupt_type, vi);
+
+ out:
+
+	return vi->txn_irq;
+}
+#endif
+
 
 /*
 ** squirrel away the I/O Sapic Version
@@ -877,6 +941,8 @@ void *iosapic_register(unsigned long hpa)
 		vip->irqline = (unsigned char) cnt;
 		vip->iosapic = isi;
 	}
+	if (!first_isi)
+		first_isi = isi;
 	return isi;
 }
 
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 7a3870f385f6..66b0b26a1381 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -688,8 +688,12 @@ static int tcm_qla2xxx_queue_status(struct se_cmd *se_cmd)
 		 * For FCP_READ with CHECK_CONDITION status, clear cmd->bufflen
 		 * for qla_tgt_xmit_response LLD code
 		 */
+		if (se_cmd->se_cmd_flags & SCF_OVERFLOW_BIT) {
+			se_cmd->se_cmd_flags &= ~SCF_OVERFLOW_BIT;
+			se_cmd->residual_count = 0;
+		}
 		se_cmd->se_cmd_flags |= SCF_UNDERFLOW_BIT;
-		se_cmd->residual_count = se_cmd->data_length;
+		se_cmd->residual_count += se_cmd->data_length;
 
 		cmd->bufflen = 0;
 	}
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index 13e9e715ad2e..8d8b3ff68490 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -155,7 +155,7 @@ static ssize_t lio_target_np_store_iser(
 	struct iscsi_tpg_np *tpg_np_iser = NULL;
 	char *endptr;
 	u32 op;
-	int rc;
+	int rc = 0;
 
 	op = simple_strtoul(page, &endptr, 0);
 	if ((op != 1) && (op != 0)) {
@@ -174,31 +174,32 @@ static ssize_t lio_target_np_store_iser(
 		return -EINVAL;
 
 	if (op) {
-		int rc = request_module("ib_isert");
-		if (rc != 0)
+		rc = request_module("ib_isert");
+		if (rc != 0) {
 			pr_warn("Unable to request_module for ib_isert\n");
+			rc = 0;
+		}
 
 		tpg_np_iser = iscsit_tpg_add_network_portal(tpg, &np->np_sockaddr,
 				np->np_ip, tpg_np, ISCSI_INFINIBAND);
-		if (!tpg_np_iser || IS_ERR(tpg_np_iser))
+		if (IS_ERR(tpg_np_iser)) {
+			rc = PTR_ERR(tpg_np_iser);
 			goto out;
+		}
 	} else {
 		tpg_np_iser = iscsit_tpg_locate_child_np(tpg_np, ISCSI_INFINIBAND);
-		if (!tpg_np_iser)
-			goto out;
-
-		rc = iscsit_tpg_del_network_portal(tpg, tpg_np_iser);
-		if (rc < 0)
-			goto out;
+		if (tpg_np_iser) {
+			rc = iscsit_tpg_del_network_portal(tpg, tpg_np_iser);
+			if (rc < 0)
+				goto out;
+		}
 	}
 
-	printk("lio_target_np_store_iser() done, op: %d\n", op);
-
 	iscsit_put_tpg(tpg);
 	return count;
 out:
 	iscsit_put_tpg(tpg);
-	return -EINVAL;
+	return rc;
 }
 
 TF_NP_BASE_ATTR(lio_target, iser, S_IRUGO | S_IWUSR);
diff --git a/drivers/target/iscsi/iscsi_target_erl0.c b/drivers/target/iscsi/iscsi_target_erl0.c
index 8e6298cc8839..dcb199da06b9 100644
--- a/drivers/target/iscsi/iscsi_target_erl0.c
+++ b/drivers/target/iscsi/iscsi_target_erl0.c
@@ -842,11 +842,11 @@ int iscsit_stop_time2retain_timer(struct iscsi_session *sess)
 		return 0;
 
 	sess->time2retain_timer_flags |= ISCSI_TF_STOP;
-	spin_unlock_bh(&se_tpg->session_lock);
+	spin_unlock(&se_tpg->session_lock);
 
 	del_timer_sync(&sess->time2retain_timer);
 
-	spin_lock_bh(&se_tpg->session_lock);
+	spin_lock(&se_tpg->session_lock);
 	sess->time2retain_timer_flags &= ~ISCSI_TF_RUNNING;
 	pr_debug("Stopped Time2Retain Timer for SID: %u\n",
 			sess->sid);
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index bb5d5c5bce65..3402241be87c 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -984,8 +984,6 @@ int iscsi_target_setup_login_socket(
 	}
 
 	np->np_transport = t;
-	printk("Set np->np_transport to %p -> %s\n", np->np_transport,
-				np->np_transport->name);
 	return 0;
 }
 
@@ -1002,7 +1000,6 @@ int iscsit_accept_np(struct iscsi_np *np, struct iscsi_conn *conn)
 
 	conn->sock = new_sock;
 	conn->login_family = np->np_sockaddr.ss_family;
-	printk("iSCSI/TCP: Setup conn->sock from new_sock: %p\n", new_sock);
 
 	if (np->np_sockaddr.ss_family == AF_INET6) {
 		memset(&sock_in6, 0, sizeof(struct sockaddr_in6));
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 7ad912060e21..cd5018ff9cd7 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -721,9 +721,6 @@ int iscsi_target_locate_portal(
 
 		start += strlen(key) + strlen(value) + 2;
 	}
-
-	printk("i_buf: %s, s_buf: %s, t_buf: %s\n", i_buf, s_buf, t_buf);
-
 	/*
 	 * See 5.3.  Login Phase.
 	 */
diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c
index 59bfaecc4e14..abfd99089781 100644
--- a/drivers/tty/pty.c
+++ b/drivers/tty/pty.c
@@ -244,14 +244,9 @@ static void pty_flush_buffer(struct tty_struct *tty)
 
 static int pty_open(struct tty_struct *tty, struct file *filp)
 {
-	int	retval = -ENODEV;
-
 	if (!tty || !tty->link)
-		goto out;
-
-	set_bit(TTY_IO_ERROR, &tty->flags);
+		return -ENODEV;
 
-	retval = -EIO;
 	if (test_bit(TTY_OTHER_CLOSED, &tty->flags))
 		goto out;
 	if (test_bit(TTY_PTY_LOCK, &tty->link->flags))
@@ -262,9 +257,11 @@ static int pty_open(struct tty_struct *tty, struct file *filp)
 	clear_bit(TTY_IO_ERROR, &tty->flags);
 	clear_bit(TTY_OTHER_CLOSED, &tty->link->flags);
 	set_bit(TTY_THROTTLED, &tty->flags);
-	retval = 0;
+	return 0;
+
 out:
-	return retval;
+	set_bit(TTY_IO_ERROR, &tty->flags);
+	return -EIO;
 }
 
 static void pty_set_termios(struct tty_struct *tty,
diff --git a/drivers/tty/serial/8250/8250_gsc.c b/drivers/tty/serial/8250/8250_gsc.c
index 097dff9c08ad..bb91b4713ebd 100644
--- a/drivers/tty/serial/8250/8250_gsc.c
+++ b/drivers/tty/serial/8250/8250_gsc.c
@@ -30,6 +30,12 @@ static int __init serial_init_chip(struct parisc_device *dev)
 	unsigned long address;
 	int err;
 
+#ifdef CONFIG_64BIT
+	extern int iosapic_serial_irq(int cellnum);
+	if (!dev->irq && (dev->id.sversion == 0xad))
+		dev->irq = iosapic_serial_irq(dev->mod_index-1);
+#endif
+
 	if (!dev->irq) {
 		/* We find some unattached serial ports by walking native
 		 * busses.  These should be silently ignored.  Otherwise,
@@ -51,7 +57,8 @@ static int __init serial_init_chip(struct parisc_device *dev)
 	memset(&uart, 0, sizeof(uart));
 	uart.port.iotype	= UPIO_MEM;
 	/* 7.272727MHz on Lasi.  Assumed the same for Dino, Wax and Timi. */
-	uart.port.uartclk	= 7272727;
+	uart.port.uartclk	= (dev->id.sversion != 0xad) ?
+					7272727 : 1843200;
 	uart.port.mapbase	= address;
 	uart.port.membase	= ioremap_nocache(address, 16);
 	uart.port.irq	= dev->irq;
@@ -73,6 +80,7 @@ static struct parisc_device_id serial_tbl[] = {
 	{ HPHW_FIO, HVERSION_REV_ANY_ID, HVERSION_ANY_ID, 0x00075 },
 	{ HPHW_FIO, HVERSION_REV_ANY_ID, HVERSION_ANY_ID, 0x0008c },
 	{ HPHW_FIO, HVERSION_REV_ANY_ID, HVERSION_ANY_ID, 0x0008d },
+	{ HPHW_FIO, HVERSION_REV_ANY_ID, HVERSION_ANY_ID, 0x000ad },
 	{ 0 }
 };
 
diff --git a/drivers/tty/vt/vt_ioctl.c b/drivers/tty/vt/vt_ioctl.c
index fc2c06c66e89..2bd78e2ac8ec 100644
--- a/drivers/tty/vt/vt_ioctl.c
+++ b/drivers/tty/vt/vt_ioctl.c
@@ -289,13 +289,10 @@ static int vt_disallocate(unsigned int vc_num)
 	struct vc_data *vc = NULL;
 	int ret = 0;
 
-	if (!vc_num)
-		return 0;
-
 	console_lock();
 	if (VT_BUSY(vc_num))
 		ret = -EBUSY;
-	else
+	else if (vc_num)
 		vc = vc_deallocate(vc_num);
 	console_unlock();
 
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index 7ef3eb8617a6..2311b1e4e43c 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -4,11 +4,17 @@
 menuconfig USB_PHY
 	bool "USB Physical Layer drivers"
 	help
-	  USB controllers (those which are host, device or DRD) need a
-	  device to handle the physical layer signalling, commonly called
-	  a PHY.
+	  Most USB controllers have the physical layer signalling part
+	  (commonly called a PHY) built in.  However, dual-role devices
+	  (a.k.a. USB on-the-go) which support being USB master or slave
+	  with the same connector often use an external PHY.
 
-	  The following drivers add support for such PHY devices.
+	  The drivers in this submenu add support for such PHY devices.
+	  They are not needed for standard master-only (or the vast
+	  majority of slave-only) USB interfaces.
+
+	  If you're not sure if this applies to you, it probably doesn't;
+	  say N here.
 
 if USB_PHY
 
diff --git a/drivers/usb/serial/ti_usb_3410_5052.c b/drivers/usb/serial/ti_usb_3410_5052.c
index c92c5ed4e580..e581c2549a57 100644
--- a/drivers/usb/serial/ti_usb_3410_5052.c
+++ b/drivers/usb/serial/ti_usb_3410_5052.c
@@ -172,7 +172,8 @@ static struct usb_device_id ti_id_table_3410[15+TI_EXTRA_VID_PID_COUNT+1] = {
 	{ USB_DEVICE(IBM_VENDOR_ID, IBM_4543_PRODUCT_ID) },
 	{ USB_DEVICE(IBM_VENDOR_ID, IBM_454B_PRODUCT_ID) },
 	{ USB_DEVICE(IBM_VENDOR_ID, IBM_454C_PRODUCT_ID) },
-	{ USB_DEVICE(ABBOTT_VENDOR_ID, ABBOTT_PRODUCT_ID) },
+	{ USB_DEVICE(ABBOTT_VENDOR_ID, ABBOTT_STEREO_PLUG_ID) },
+	{ USB_DEVICE(ABBOTT_VENDOR_ID, ABBOTT_STRIP_PORT_ID) },
 	{ USB_DEVICE(TI_VENDOR_ID, FRI2_PRODUCT_ID) },
 };
 
diff --git a/drivers/usb/serial/ti_usb_3410_5052.h b/drivers/usb/serial/ti_usb_3410_5052.h
index b353e7e3d480..4a2423e84d55 100644
--- a/drivers/usb/serial/ti_usb_3410_5052.h
+++ b/drivers/usb/serial/ti_usb_3410_5052.h
@@ -52,7 +52,9 @@
 
 /* Abbott Diabetics vendor and product ids */
 #define ABBOTT_VENDOR_ID		0x1a61
-#define ABBOTT_PRODUCT_ID		0x3410
+#define ABBOTT_STEREO_PLUG_ID		0x3410
+#define ABBOTT_PRODUCT_ID		ABBOTT_STEREO_PLUG_ID
+#define ABBOTT_STRIP_PORT_ID		0x3420
 
 /* Commands */
 #define TI_GET_VERSION			0x01
diff --git a/fs/internal.h b/fs/internal.h
index eaa75f75b625..68121584ae37 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -132,6 +132,12 @@ extern struct dentry *__d_alloc(struct super_block *, const struct qstr *);
 extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *);
 
 /*
+ * splice.c
+ */
+extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
+		loff_t *opos, size_t len, unsigned int flags);
+
+/*
  * pipe.c
  */
 extern const struct file_operations pipefifo_fops;
diff --git a/fs/read_write.c b/fs/read_write.c
index 03430008704e..2cefa417be34 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1064,6 +1064,7 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 	struct fd in, out;
 	struct inode *in_inode, *out_inode;
 	loff_t pos;
+	loff_t out_pos;
 	ssize_t retval;
 	int fl;
 
@@ -1077,12 +1078,14 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 	if (!(in.file->f_mode & FMODE_READ))
 		goto fput_in;
 	retval = -ESPIPE;
-	if (!ppos)
-		ppos = &in.file->f_pos;
-	else
+	if (!ppos) {
+		pos = in.file->f_pos;
+	} else {
+		pos = *ppos;
 		if (!(in.file->f_mode & FMODE_PREAD))
 			goto fput_in;
-	retval = rw_verify_area(READ, in.file, ppos, count);
+	}
+	retval = rw_verify_area(READ, in.file, &pos, count);
 	if (retval < 0)
 		goto fput_in;
 	count = retval;
@@ -1099,7 +1102,8 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 	retval = -EINVAL;
 	in_inode = file_inode(in.file);
 	out_inode = file_inode(out.file);
-	retval = rw_verify_area(WRITE, out.file, &out.file->f_pos, count);
+	out_pos = out.file->f_pos;
+	retval = rw_verify_area(WRITE, out.file, &out_pos, count);
 	if (retval < 0)
 		goto fput_out;
 	count = retval;
@@ -1107,7 +1111,6 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 	if (!max)
 		max = min(in_inode->i_sb->s_maxbytes, out_inode->i_sb->s_maxbytes);
 
-	pos = *ppos;
 	if (unlikely(pos + count > max)) {
 		retval = -EOVERFLOW;
 		if (pos >= max)
@@ -1126,18 +1129,23 @@ static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 	if (in.file->f_flags & O_NONBLOCK)
 		fl = SPLICE_F_NONBLOCK;
 #endif
-	retval = do_splice_direct(in.file, ppos, out.file, count, fl);
+	retval = do_splice_direct(in.file, &pos, out.file, &out_pos, count, fl);
 
 	if (retval > 0) {
 		add_rchar(current, retval);
 		add_wchar(current, retval);
 		fsnotify_access(in.file);
 		fsnotify_modify(out.file);
+		out.file->f_pos = out_pos;
+		if (ppos)
+			*ppos = pos;
+		else
+			in.file->f_pos = pos;
 	}
 
 	inc_syscr(current);
 	inc_syscw(current);
-	if (*ppos > max)
+	if (pos > max)
 		retval = -EOVERFLOW;
 
 fput_out:
diff --git a/fs/splice.c b/fs/splice.c
index e6b25598c8c4..9eca476227d5 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -1274,7 +1274,7 @@ static int direct_splice_actor(struct pipe_inode_info *pipe,
 {
 	struct file *file = sd->u.file;
 
-	return do_splice_from(pipe, file, &file->f_pos, sd->total_len,
+	return do_splice_from(pipe, file, sd->opos, sd->total_len,
 			      sd->flags);
 }
 
@@ -1294,7 +1294,7 @@ static int direct_splice_actor(struct pipe_inode_info *pipe,
  *
  */
 long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
-		      size_t len, unsigned int flags)
+		      loff_t *opos, size_t len, unsigned int flags)
 {
 	struct splice_desc sd = {
 		.len		= len,
@@ -1302,6 +1302,7 @@ long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
 		.flags		= flags,
 		.pos		= *ppos,
 		.u.file		= out,
+		.opos		= opos,
 	};
 	long ret;
 
@@ -1325,7 +1326,7 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 {
 	struct pipe_inode_info *ipipe;
 	struct pipe_inode_info *opipe;
-	loff_t offset, *off;
+	loff_t offset;
 	long ret;
 
 	ipipe = get_pipe_info(in);
@@ -1356,13 +1357,15 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 				return -EINVAL;
 			if (copy_from_user(&offset, off_out, sizeof(loff_t)))
 				return -EFAULT;
-			off = &offset;
-		} else
-			off = &out->f_pos;
+		} else {
+			offset = out->f_pos;
+		}
 
-		ret = do_splice_from(ipipe, out, off, len, flags);
+		ret = do_splice_from(ipipe, out, &offset, len, flags);
 
-		if (off_out && copy_to_user(off_out, off, sizeof(loff_t)))
+		if (!off_out)
+			out->f_pos = offset;
+		else if (copy_to_user(off_out, &offset, sizeof(loff_t)))
 			ret = -EFAULT;
 
 		return ret;
@@ -1376,13 +1379,15 @@ static long do_splice(struct file *in, loff_t __user *off_in,
 				return -EINVAL;
 			if (copy_from_user(&offset, off_in, sizeof(loff_t)))
 				return -EFAULT;
-			off = &offset;
-		} else
-			off = &in->f_pos;
+		} else {
+			offset = in->f_pos;
+		}
 
-		ret = do_splice_to(in, off, opipe, len, flags);
+		ret = do_splice_to(in, &offset, opipe, len, flags);
 
-		if (off_in && copy_to_user(off_in, off, sizeof(loff_t)))
+		if (!off_in)
+			in->f_pos = offset;
+		else if (copy_to_user(off_in, &offset, sizeof(loff_t)))
 			ret = -EFAULT;
 
 		return ret;
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 636c59f2003a..c13c919ab99e 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -382,6 +382,7 @@ const char *acpi_power_state_string(int state);
 int acpi_device_get_power(struct acpi_device *device, int *state);
 int acpi_device_set_power(struct acpi_device *device, int state);
 int acpi_bus_init_power(struct acpi_device *device);
+int acpi_device_fix_up_power(struct acpi_device *device);
 int acpi_bus_update_power(acpi_handle handle, int *state_p);
 bool acpi_bus_power_manageable(acpi_handle handle);
 
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index 365f4a61bf04..fc09d7b0dacf 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -3,6 +3,7 @@
 
 #include <linux/sched.h>
 #include <linux/percpu.h>
+#include <linux/vtime.h>
 #include <asm/ptrace.h>
 
 struct context_tracking {
@@ -19,6 +20,26 @@ struct context_tracking {
 	} state;
 };
 
+static inline void __guest_enter(void)
+{
+	/*
+	 * This is running in ioctl context so we can avoid
+	 * the call to vtime_account() with its unnecessary idle check.
+	 */
+	vtime_account_system(current);
+	current->flags |= PF_VCPU;
+}
+
+static inline void __guest_exit(void)
+{
+	/*
+	 * This is running in ioctl context so we can avoid
+	 * the call to vtime_account() with its unnecessary idle check.
+	 */
+	vtime_account_system(current);
+	current->flags &= ~PF_VCPU;
+}
+
 #ifdef CONFIG_CONTEXT_TRACKING
 DECLARE_PER_CPU(struct context_tracking, context_tracking);
 
@@ -35,6 +56,9 @@ static inline bool context_tracking_active(void)
 extern void user_enter(void);
 extern void user_exit(void);
 
+extern void guest_enter(void);
+extern void guest_exit(void);
+
 static inline enum ctx_state exception_enter(void)
 {
 	enum ctx_state prev_ctx;
@@ -57,6 +81,17 @@ extern void context_tracking_task_switch(struct task_struct *prev,
 static inline bool context_tracking_in_user(void) { return false; }
 static inline void user_enter(void) { }
 static inline void user_exit(void) { }
+
+static inline void guest_enter(void)
+{
+	__guest_enter();
+}
+
+static inline void guest_exit(void)
+{
+	__guest_exit();
+}
+
 static inline enum ctx_state exception_enter(void) { return 0; }
 static inline void exception_exit(enum ctx_state prev_ctx) { }
 static inline void context_tracking_task_switch(struct task_struct *prev,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 43db02e9c9fa..65c2be22b601 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2414,8 +2414,6 @@ extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
 		struct file *, loff_t *, size_t, unsigned int);
 extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
 		struct file *out, loff_t *, size_t len, unsigned int flags);
-extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
-		size_t len, unsigned int flags);
 
 extern void
 file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index f0eea07d2c2b..8db53cfaccdb 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -23,6 +23,7 @@
 #include <linux/ratelimit.h>
 #include <linux/err.h>
 #include <linux/irqflags.h>
+#include <linux/context_tracking.h>
 #include <asm/signal.h>
 
 #include <linux/kvm.h>
@@ -760,42 +761,6 @@ static inline int kvm_iommu_unmap_guest(struct kvm *kvm)
 }
 #endif
 
-static inline void __guest_enter(void)
-{
-	/*
-	 * This is running in ioctl context so we can avoid
-	 * the call to vtime_account() with its unnecessary idle check.
-	 */
-	vtime_account_system(current);
-	current->flags |= PF_VCPU;
-}
-
-static inline void __guest_exit(void)
-{
-	/*
-	 * This is running in ioctl context so we can avoid
-	 * the call to vtime_account() with its unnecessary idle check.
-	 */
-	vtime_account_system(current);
-	current->flags &= ~PF_VCPU;
-}
-
-#ifdef CONFIG_CONTEXT_TRACKING
-extern void guest_enter(void);
-extern void guest_exit(void);
-
-#else /* !CONFIG_CONTEXT_TRACKING */
-static inline void guest_enter(void)
-{
-	__guest_enter();
-}
-
-static inline void guest_exit(void)
-{
-	__guest_exit();
-}
-#endif /* !CONFIG_CONTEXT_TRACKING */
-
 static inline void kvm_guest_enter(void)
 {
 	unsigned long flags;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index f463a46424e2..c5b6dbf9c2fc 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -389,8 +389,7 @@ struct perf_event {
 	/* mmap bits */
 	struct mutex			mmap_mutex;
 	atomic_t			mmap_count;
-	int				mmap_locked;
-	struct user_struct		*mmap_user;
+
 	struct ring_buffer		*rb;
 	struct list_head		rb_entry;
 
diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index 87a03c746f17..f5d4723cdb3d 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -33,9 +33,25 @@ do { \
 		preempt_schedule(); \
 } while (0)
 
+#ifdef CONFIG_CONTEXT_TRACKING
+
+void preempt_schedule_context(void);
+
+#define preempt_check_resched_context() \
+do { \
+	if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) \
+		preempt_schedule_context(); \
+} while (0)
+#else
+
+#define preempt_check_resched_context() preempt_check_resched()
+
+#endif /* CONFIG_CONTEXT_TRACKING */
+
 #else /* !CONFIG_PREEMPT */
 
 #define preempt_check_resched()		do { } while (0)
+#define preempt_check_resched_context()	do { } while (0)
 
 #endif /* CONFIG_PREEMPT */
 
@@ -88,7 +104,7 @@ do { \
 do { \
 	preempt_enable_no_resched_notrace(); \
 	barrier(); \
-	preempt_check_resched(); \
+	preempt_check_resched_context(); \
 } while (0)
 
 #else /* !CONFIG_PREEMPT_COUNT */
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 09a545a7dfa3..74575cbf2d6f 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -35,6 +35,7 @@ struct splice_desc {
 		void *data;		/* cookie */
 	} u;
 	loff_t pos;			/* file position */
+	loff_t *opos;			/* sendfile: output position */
 	size_t num_spliced;		/* number of bytes already spliced */
 	bool need_wakeup;		/* need to wake up writer */
 };
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index 71a5782d8c59..b1dd2db80076 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -34,7 +34,7 @@ static inline void vtime_user_exit(struct task_struct *tsk)
 }
 extern void vtime_guest_enter(struct task_struct *tsk);
 extern void vtime_guest_exit(struct task_struct *tsk);
-extern void vtime_init_idle(struct task_struct *tsk);
+extern void vtime_init_idle(struct task_struct *tsk, int cpu);
 #else
 static inline void vtime_account_irq_exit(struct task_struct *tsk)
 {
@@ -45,7 +45,7 @@ static inline void vtime_user_enter(struct task_struct *tsk) { }
 static inline void vtime_user_exit(struct task_struct *tsk) { }
 static inline void vtime_guest_enter(struct task_struct *tsk) { }
 static inline void vtime_guest_exit(struct task_struct *tsk) { }
-static inline void vtime_init_idle(struct task_struct *tsk) { }
+static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { }
 #endif
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 65349f07b878..383f8231e436 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -15,7 +15,6 @@
  */
 
 #include <linux/context_tracking.h>
-#include <linux/kvm_host.h>
 #include <linux/rcupdate.h>
 #include <linux/sched.h>
 #include <linux/hardirq.h>
@@ -71,6 +70,46 @@ void user_enter(void)
 	local_irq_restore(flags);
 }
 
+#ifdef CONFIG_PREEMPT
+/**
+ * preempt_schedule_context - preempt_schedule called by tracing
+ *
+ * The tracing infrastructure uses preempt_enable_notrace to prevent
+ * recursion and tracing preempt enabling caused by the tracing
+ * infrastructure itself. But as tracing can happen in areas coming
+ * from userspace or just about to enter userspace, a preempt enable
+ * can occur before user_exit() is called. This will cause the scheduler
+ * to be called when the system is still in usermode.
+ *
+ * To prevent this, the preempt_enable_notrace will use this function
+ * instead of preempt_schedule() to exit user context if needed before
+ * calling the scheduler.
+ */
+void __sched notrace preempt_schedule_context(void)
+{
+	struct thread_info *ti = current_thread_info();
+	enum ctx_state prev_ctx;
+
+	if (likely(ti->preempt_count || irqs_disabled()))
+		return;
+
+	/*
+	 * Need to disable preemption in case user_exit() is traced
+	 * and the tracer calls preempt_enable_notrace() causing
+	 * an infinite recursion.
+	 */
+	preempt_disable_notrace();
+	prev_ctx = exception_enter();
+	preempt_enable_no_resched_notrace();
+
+	preempt_schedule();
+
+	preempt_disable_notrace();
+	exception_exit(prev_ctx);
+	preempt_enable_notrace();
+}
+EXPORT_SYMBOL_GPL(preempt_schedule_context);
+#endif /* CONFIG_PREEMPT */
 
 /**
  * user_exit - Inform the context tracking that the CPU is
diff --git a/kernel/cpu/idle.c b/kernel/cpu/idle.c
index d5585f5e038e..e695c0a0bcb5 100644
--- a/kernel/cpu/idle.c
+++ b/kernel/cpu/idle.c
@@ -5,6 +5,7 @@
 #include <linux/cpu.h>
 #include <linux/tick.h>
 #include <linux/mm.h>
+#include <linux/stackprotector.h>
 
 #include <asm/tlb.h>
 
@@ -58,6 +59,7 @@ void __weak arch_cpu_idle_dead(void) { }
 void __weak arch_cpu_idle(void)
 {
 	cpu_idle_force_poll = 1;
+	local_irq_enable();
 }
 
 /*
@@ -112,6 +114,21 @@ static void cpu_idle_loop(void)
 
 void cpu_startup_entry(enum cpuhp_state state)
 {
+	/*
+	 * This #ifdef needs to die, but it's too late in the cycle to
+	 * make this generic (arm and sh have never invoked the canary
+	 * init for the non boot cpus!). Will be fixed in 3.11
+	 */
+#ifdef CONFIG_X86
+	/*
+	 * If we're the non-boot CPU, nothing set the stack canary up
+	 * for us. The boot CPU already has it initialized but no harm
+	 * in doing it again. This is a good place for updating it, as
+	 * we wont ever return from this function (so the invalid
+	 * canaries already on the stack wont ever trigger).
+	 */
+	boot_init_stack_canary();
+#endif
 	current_set_polling();
 	arch_cpu_idle_prepare();
 	cpu_idle_loop();
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9dc297faf7c0..b391907d5352 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -196,9 +196,6 @@ static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
 static void update_context_time(struct perf_event_context *ctx);
 static u64 perf_event_time(struct perf_event *event);
 
-static void ring_buffer_attach(struct perf_event *event,
-			       struct ring_buffer *rb);
-
 void __weak perf_event_print_debug(void)	{ }
 
 extern __weak const char *perf_pmu_name(void)
@@ -2918,6 +2915,7 @@ static void free_event_rcu(struct rcu_head *head)
 }
 
 static void ring_buffer_put(struct ring_buffer *rb);
+static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb);
 
 static void free_event(struct perf_event *event)
 {
@@ -2942,15 +2940,30 @@ static void free_event(struct perf_event *event)
 		if (has_branch_stack(event)) {
 			static_key_slow_dec_deferred(&perf_sched_events);
 			/* is system-wide event */
-			if (!(event->attach_state & PERF_ATTACH_TASK))
+			if (!(event->attach_state & PERF_ATTACH_TASK)) {
 				atomic_dec(&per_cpu(perf_branch_stack_events,
 						    event->cpu));
+			}
 		}
 	}
 
 	if (event->rb) {
-		ring_buffer_put(event->rb);
-		event->rb = NULL;
+		struct ring_buffer *rb;
+
+		/*
+		 * Can happen when we close an event with re-directed output.
+		 *
+		 * Since we have a 0 refcount, perf_mmap_close() will skip
+		 * over us; possibly making our ring_buffer_put() the last.
+		 */
+		mutex_lock(&event->mmap_mutex);
+		rb = event->rb;
+		if (rb) {
+			rcu_assign_pointer(event->rb, NULL);
+			ring_buffer_detach(event, rb);
+			ring_buffer_put(rb); /* could be last */
+		}
+		mutex_unlock(&event->mmap_mutex);
 	}
 
 	if (is_cgroup_event(event))
@@ -3188,30 +3201,13 @@ static unsigned int perf_poll(struct file *file, poll_table *wait)
 	unsigned int events = POLL_HUP;
 
 	/*
-	 * Race between perf_event_set_output() and perf_poll(): perf_poll()
-	 * grabs the rb reference but perf_event_set_output() overrides it.
-	 * Here is the timeline for two threads T1, T2:
-	 * t0: T1, rb = rcu_dereference(event->rb)
-	 * t1: T2, old_rb = event->rb
-	 * t2: T2, event->rb = new rb
-	 * t3: T2, ring_buffer_detach(old_rb)
-	 * t4: T1, ring_buffer_attach(rb1)
-	 * t5: T1, poll_wait(event->waitq)
-	 *
-	 * To avoid this problem, we grab mmap_mutex in perf_poll()
-	 * thereby ensuring that the assignment of the new ring buffer
-	 * and the detachment of the old buffer appear atomic to perf_poll()
+	 * Pin the event->rb by taking event->mmap_mutex; otherwise
+	 * perf_event_set_output() can swizzle our rb and make us miss wakeups.
 	 */
 	mutex_lock(&event->mmap_mutex);
-
-	rcu_read_lock();
-	rb = rcu_dereference(event->rb);
-	if (rb) {
-		ring_buffer_attach(event, rb);
+	rb = event->rb;
+	if (rb)
 		events = atomic_xchg(&rb->poll, 0);
-	}
-	rcu_read_unlock();
-
 	mutex_unlock(&event->mmap_mutex);
 
 	poll_wait(file, &event->waitq, wait);
@@ -3521,16 +3517,12 @@ static void ring_buffer_attach(struct perf_event *event,
 		return;
 
 	spin_lock_irqsave(&rb->event_lock, flags);
-	if (!list_empty(&event->rb_entry))
-		goto unlock;
-
-	list_add(&event->rb_entry, &rb->event_list);
-unlock:
+	if (list_empty(&event->rb_entry))
+		list_add(&event->rb_entry, &rb->event_list);
 	spin_unlock_irqrestore(&rb->event_lock, flags);
 }
 
-static void ring_buffer_detach(struct perf_event *event,
-			       struct ring_buffer *rb)
+static void ring_buffer_detach(struct perf_event *event, struct ring_buffer *rb)
 {
 	unsigned long flags;
 
@@ -3549,13 +3541,10 @@ static void ring_buffer_wakeup(struct perf_event *event)
 
 	rcu_read_lock();
 	rb = rcu_dereference(event->rb);
-	if (!rb)
-		goto unlock;
-
-	list_for_each_entry_rcu(event, &rb->event_list, rb_entry)
-		wake_up_all(&event->waitq);
-
-unlock:
+	if (rb) {
+		list_for_each_entry_rcu(event, &rb->event_list, rb_entry)
+			wake_up_all(&event->waitq);
+	}
 	rcu_read_unlock();
 }
 
@@ -3584,18 +3573,10 @@ static struct ring_buffer *ring_buffer_get(struct perf_event *event)
 
 static void ring_buffer_put(struct ring_buffer *rb)
 {
-	struct perf_event *event, *n;
-	unsigned long flags;
-
 	if (!atomic_dec_and_test(&rb->refcount))
 		return;
 
-	spin_lock_irqsave(&rb->event_lock, flags);
-	list_for_each_entry_safe(event, n, &rb->event_list, rb_entry) {
-		list_del_init(&event->rb_entry);
-		wake_up_all(&event->waitq);
-	}
-	spin_unlock_irqrestore(&rb->event_lock, flags);
+	WARN_ON_ONCE(!list_empty(&rb->event_list));
 
 	call_rcu(&rb->rcu_head, rb_free_rcu);
 }
@@ -3605,26 +3586,100 @@ static void perf_mmap_open(struct vm_area_struct *vma)
 	struct perf_event *event = vma->vm_file->private_data;
 
 	atomic_inc(&event->mmap_count);
+	atomic_inc(&event->rb->mmap_count);
 }
 
+/*
+ * A buffer can be mmap()ed multiple times; either directly through the same
+ * event, or through other events by use of perf_event_set_output().
+ *
+ * In order to undo the VM accounting done by perf_mmap() we need to destroy
+ * the buffer here, where we still have a VM context. This means we need
+ * to detach all events redirecting to us.
+ */
 static void perf_mmap_close(struct vm_area_struct *vma)
 {
 	struct perf_event *event = vma->vm_file->private_data;
 
-	if (atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex)) {
-		unsigned long size = perf_data_size(event->rb);
-		struct user_struct *user = event->mmap_user;
-		struct ring_buffer *rb = event->rb;
+	struct ring_buffer *rb = event->rb;
+	struct user_struct *mmap_user = rb->mmap_user;
+	int mmap_locked = rb->mmap_locked;
+	unsigned long size = perf_data_size(rb);
+
+	atomic_dec(&rb->mmap_count);
+
+	if (!atomic_dec_and_mutex_lock(&event->mmap_count, &event->mmap_mutex))
+		return;
 
-		atomic_long_sub((size >> PAGE_SHIFT) + 1, &user->locked_vm);
-		vma->vm_mm->pinned_vm -= event->mmap_locked;
-		rcu_assign_pointer(event->rb, NULL);
-		ring_buffer_detach(event, rb);
+	/* Detach current event from the buffer. */
+	rcu_assign_pointer(event->rb, NULL);
+	ring_buffer_detach(event, rb);
+	mutex_unlock(&event->mmap_mutex);
+
+	/* If there's still other mmap()s of this buffer, we're done. */
+	if (atomic_read(&rb->mmap_count)) {
+		ring_buffer_put(rb); /* can't be last */
+		return;
+	}
+
+	/*
+	 * No other mmap()s, detach from all other events that might redirect
+	 * into the now unreachable buffer. Somewhat complicated by the
+	 * fact that rb::event_lock otherwise nests inside mmap_mutex.
+	 */
+again:
+	rcu_read_lock();
+	list_for_each_entry_rcu(event, &rb->event_list, rb_entry) {
+		if (!atomic_long_inc_not_zero(&event->refcount)) {
+			/*
+			 * This event is en-route to free_event() which will
+			 * detach it and remove it from the list.
+			 */
+			continue;
+		}
+		rcu_read_unlock();
+
+		mutex_lock(&event->mmap_mutex);
+		/*
+		 * Check we didn't race with perf_event_set_output() which can
+		 * swizzle the rb from under us while we were waiting to
+		 * acquire mmap_mutex.
+		 *
+		 * If we find a different rb; ignore this event, a next
+		 * iteration will no longer find it on the list. We have to
+		 * still restart the iteration to make sure we're not now
+		 * iterating the wrong list.
+		 */
+		if (event->rb == rb) {
+			rcu_assign_pointer(event->rb, NULL);
+			ring_buffer_detach(event, rb);
+			ring_buffer_put(rb); /* can't be last, we still have one */
+		}
 		mutex_unlock(&event->mmap_mutex);
+		put_event(event);
 
-		ring_buffer_put(rb);
-		free_uid(user);
+		/*
+		 * Restart the iteration; either we're on the wrong list or
+		 * destroyed its integrity by doing a deletion.
+		 */
+		goto again;
 	}
+	rcu_read_unlock();
+
+	/*
+	 * It could be there's still a few 0-ref events on the list; they'll
+	 * get cleaned up by free_event() -- they'll also still have their
+	 * ref on the rb and will free it whenever they are done with it.
+	 *
+	 * Aside from that, this buffer is 'fully' detached and unmapped,
+	 * undo the VM accounting.
+	 */
+
+	atomic_long_sub((size >> PAGE_SHIFT) + 1, &mmap_user->locked_vm);
+	vma->vm_mm->pinned_vm -= mmap_locked;
+	free_uid(mmap_user);
+
+	ring_buffer_put(rb); /* could be last */
 }
 
 static const struct vm_operations_struct perf_mmap_vmops = {
@@ -3674,12 +3729,24 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		return -EINVAL;
 
 	WARN_ON_ONCE(event->ctx->parent_ctx);
+again:
 	mutex_lock(&event->mmap_mutex);
 	if (event->rb) {
-		if (event->rb->nr_pages == nr_pages)
-			atomic_inc(&event->rb->refcount);
-		else
+		if (event->rb->nr_pages != nr_pages) {
 			ret = -EINVAL;
+			goto unlock;
+		}
+
+		if (!atomic_inc_not_zero(&event->rb->mmap_count)) {
+			/*
+			 * Raced against perf_mmap_close() through
+			 * perf_event_set_output(). Try again, hope for better
+			 * luck.
+			 */
+			mutex_unlock(&event->mmap_mutex);
+			goto again;
+		}
+
 		goto unlock;
 	}
 
@@ -3720,12 +3787,16 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 		ret = -ENOMEM;
 		goto unlock;
 	}
-	rcu_assign_pointer(event->rb, rb);
+
+	atomic_set(&rb->mmap_count, 1);
+	rb->mmap_locked = extra;
+	rb->mmap_user = get_current_user();
 
 	atomic_long_add(user_extra, &user->locked_vm);
-	event->mmap_locked = extra;
-	event->mmap_user = get_current_user();
-	vma->vm_mm->pinned_vm += event->mmap_locked;
+	vma->vm_mm->pinned_vm += extra;
+
+	ring_buffer_attach(event, rb);
+	rcu_assign_pointer(event->rb, rb);
 
 	perf_event_update_userpage(event);
 
@@ -3734,7 +3805,11 @@ unlock:
 		atomic_inc(&event->mmap_count);
 	mutex_unlock(&event->mmap_mutex);
 
-	vma->vm_flags |= VM_DONTEXPAND | VM_DONTDUMP;
+	/*
+	 * Since pinned accounting is per vm we cannot allow fork() to copy our
+	 * vma.
+	 */
+	vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND | VM_DONTDUMP;
 	vma->vm_ops = &perf_mmap_vmops;
 
 	return ret;
@@ -6412,6 +6487,8 @@ set:
 	if (atomic_read(&event->mmap_count))
 		goto unlock;
 
+	old_rb = event->rb;
+
 	if (output_event) {
 		/* get the rb we want to redirect to */
 		rb = ring_buffer_get(output_event);
@@ -6419,16 +6496,28 @@ set:
 			goto unlock;
 	}
 
-	old_rb = event->rb;
-	rcu_assign_pointer(event->rb, rb);
 	if (old_rb)
 		ring_buffer_detach(event, old_rb);
+
+	if (rb)
+		ring_buffer_attach(event, rb);
+
+	rcu_assign_pointer(event->rb, rb);
+
+	if (old_rb) {
+		ring_buffer_put(old_rb);
+		/*
+		 * Since we detached before setting the new rb, so that we
+		 * could attach the new rb, we could have missed a wakeup.
+		 * Provide it now.
+		 */
+		wake_up_all(&event->waitq);
+	}
+
 	ret = 0;
 unlock:
 	mutex_unlock(&event->mmap_mutex);
 
-	if (old_rb)
-		ring_buffer_put(old_rb);
 out:
 	return ret;
 }
diff --git a/kernel/events/internal.h b/kernel/events/internal.h
index eb675c4d59df..ca6599723be5 100644
--- a/kernel/events/internal.h
+++ b/kernel/events/internal.h
@@ -31,6 +31,10 @@ struct ring_buffer {
 	spinlock_t			event_lock;
 	struct list_head		event_list;
 
+	atomic_t			mmap_count;
+	unsigned long			mmap_locked;
+	struct user_struct		*mmap_user;
+
 	struct perf_event_mmap_page	*user_page;
 	void				*data_pages[0];
 };
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 3fed7f0cbcdf..bddf3b201a48 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -467,6 +467,7 @@ static struct kprobe *__kprobes get_optimized_kprobe(unsigned long addr)
 /* Optimization staging list, protected by kprobe_mutex */
 static LIST_HEAD(optimizing_list);
 static LIST_HEAD(unoptimizing_list);
+static LIST_HEAD(freeing_list);
 
 static void kprobe_optimizer(struct work_struct *work);
 static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
@@ -504,7 +505,7 @@ static __kprobes void do_optimize_kprobes(void)
  * Unoptimize (replace a jump with a breakpoint and remove the breakpoint
  * if need) kprobes listed on unoptimizing_list.
  */
-static __kprobes void do_unoptimize_kprobes(struct list_head *free_list)
+static __kprobes void do_unoptimize_kprobes(void)
 {
 	struct optimized_kprobe *op, *tmp;
 
@@ -515,9 +516,9 @@ static __kprobes void do_unoptimize_kprobes(struct list_head *free_list)
 	/* Ditto to do_optimize_kprobes */
 	get_online_cpus();
 	mutex_lock(&text_mutex);
-	arch_unoptimize_kprobes(&unoptimizing_list, free_list);
+	arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list);
 	/* Loop free_list for disarming */
-	list_for_each_entry_safe(op, tmp, free_list, list) {
+	list_for_each_entry_safe(op, tmp, &freeing_list, list) {
 		/* Disarm probes if marked disabled */
 		if (kprobe_disabled(&op->kp))
 			arch_disarm_kprobe(&op->kp);
@@ -536,11 +537,11 @@ static __kprobes void do_unoptimize_kprobes(struct list_head *free_list)
 }
 
 /* Reclaim all kprobes on the free_list */
-static __kprobes void do_free_cleaned_kprobes(struct list_head *free_list)
+static __kprobes void do_free_cleaned_kprobes(void)
 {
 	struct optimized_kprobe *op, *tmp;
 
-	list_for_each_entry_safe(op, tmp, free_list, list) {
+	list_for_each_entry_safe(op, tmp, &freeing_list, list) {
 		BUG_ON(!kprobe_unused(&op->kp));
 		list_del_init(&op->list);
 		free_aggr_kprobe(&op->kp);
@@ -556,8 +557,6 @@ static __kprobes void kick_kprobe_optimizer(void)
 /* Kprobe jump optimizer */
 static __kprobes void kprobe_optimizer(struct work_struct *work)
 {
-	LIST_HEAD(free_list);
-
 	mutex_lock(&kprobe_mutex);
 	/* Lock modules while optimizing kprobes */
 	mutex_lock(&module_mutex);
@@ -566,7 +565,7 @@ static __kprobes void kprobe_optimizer(struct work_struct *work)
 	 * Step 1: Unoptimize kprobes and collect cleaned (unused and disarmed)
 	 * kprobes before waiting for quiesence period.
 	 */
-	do_unoptimize_kprobes(&free_list);
+	do_unoptimize_kprobes();
 
 	/*
 	 * Step 2: Wait for quiesence period to ensure all running interrupts
@@ -581,7 +580,7 @@ static __kprobes void kprobe_optimizer(struct work_struct *work)
 	do_optimize_kprobes();
 
 	/* Step 4: Free cleaned kprobes after quiesence period */
-	do_free_cleaned_kprobes(&free_list);
+	do_free_cleaned_kprobes();
 
 	mutex_unlock(&module_mutex);
 	mutex_unlock(&kprobe_mutex);
@@ -723,8 +722,19 @@ static void __kprobes kill_optimized_kprobe(struct kprobe *p)
 	if (!list_empty(&op->list))
 		/* Dequeue from the (un)optimization queue */
 		list_del_init(&op->list);
-
 	op->kp.flags &= ~KPROBE_FLAG_OPTIMIZED;
+
+	if (kprobe_unused(p)) {
+		/* Enqueue if it is unused */
+		list_add(&op->list, &freeing_list);
+		/*
+		 * Remove unused probes from the hash list. After waiting
+		 * for synchronization, this probe is reclaimed.
+		 * (reclaiming is done by do_free_cleaned_kprobes().)
+		 */
+		hlist_del_rcu(&op->kp.hlist);
+	}
+
 	/* Don't touch the code, because it is already freed. */
 	arch_remove_optimized_kprobe(op);
 }
diff --git a/kernel/range.c b/kernel/range.c
index eb911dbce267..322ea8e93e4b 100644
--- a/kernel/range.c
+++ b/kernel/range.c
@@ -4,7 +4,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/sort.h>
-
+#include <linux/string.h>
 #include <linux/range.h>
 
 int add_range(struct range *range, int az, int nr_range, u64 start, u64 end)
@@ -32,9 +32,8 @@ int add_range_with_merge(struct range *range, int az, int nr_range,
 	if (start >= end)
 		return nr_range;
 
-	/* Try to merge it with old one: */
+	/* get new start/end: */
 	for (i = 0; i < nr_range; i++) {
-		u64 final_start, final_end;
 		u64 common_start, common_end;
 
 		if (!range[i].end)
@@ -45,14 +44,16 @@ int add_range_with_merge(struct range *range, int az, int nr_range,
 		if (common_start > common_end)
 			continue;
 
-		final_start = min(range[i].start, start);
-		final_end = max(range[i].end, end);
+		/* new start/end, will add it back at last */
+		start = min(range[i].start, start);
+		end = max(range[i].end, end);
 
-		/* clear it and add it back for further merge */
-		range[i].start = 0;
-		range[i].end =  0;
-		return add_range_with_merge(range, az, nr_range,
-			final_start, final_end);
+		memmove(&range[i], &range[i + 1],
+			(nr_range - (i + 1)) * sizeof(range[i]));
+		range[nr_range - 1].start = 0;
+		range[nr_range - 1].end   = 0;
+		nr_range--;
+		i--;
 	}
 
 	/* Need to add it: */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 58453b8272fd..e8b335016c52 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -633,7 +633,19 @@ void wake_up_nohz_cpu(int cpu)
 static inline bool got_nohz_idle_kick(void)
 {
 	int cpu = smp_processor_id();
-	return idle_cpu(cpu) && test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu));
+
+	if (!test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)))
+		return false;
+
+	if (idle_cpu(cpu) && !need_resched())
+		return true;
+
+	/*
+	 * We can't run Idle Load Balance on this CPU for this time so we
+	 * cancel it and clear NOHZ_BALANCE_KICK
+	 */
+	clear_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu));
+	return false;
 }
 
 #else /* CONFIG_NO_HZ_COMMON */
@@ -1393,8 +1405,9 @@ static void sched_ttwu_pending(void)
 
 void scheduler_ipi(void)
 {
-	if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick()
-	    && !tick_nohz_full_cpu(smp_processor_id()))
+	if (llist_empty(&this_rq()->wake_list)
+			&& !tick_nohz_full_cpu(smp_processor_id())
+			&& !got_nohz_idle_kick())
 		return;
 
 	/*
@@ -1417,7 +1430,7 @@ void scheduler_ipi(void)
 	/*
 	 * Check if someone kicked us for doing the nohz idle load balance.
 	 */
-	if (unlikely(got_nohz_idle_kick() && !need_resched())) {
+	if (unlikely(got_nohz_idle_kick())) {
 		this_rq()->idle_balance = 1;
 		raise_softirq_irqoff(SCHED_SOFTIRQ);
 	}
@@ -4745,7 +4758,7 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu)
 	 */
 	idle->sched_class = &idle_sched_class;
 	ftrace_graph_init_idle_task(idle, cpu);
-	vtime_init_idle(idle);
+	vtime_init_idle(idle, cpu);
 #if defined(CONFIG_SMP)
 	sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
 #endif
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index cc2dc3eea8a3..b5ccba22603b 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -747,17 +747,17 @@ void arch_vtime_task_switch(struct task_struct *prev)
 
 	write_seqlock(&current->vtime_seqlock);
 	current->vtime_snap_whence = VTIME_SYS;
-	current->vtime_snap = sched_clock();
+	current->vtime_snap = sched_clock_cpu(smp_processor_id());
 	write_sequnlock(&current->vtime_seqlock);
 }
 
-void vtime_init_idle(struct task_struct *t)
+void vtime_init_idle(struct task_struct *t, int cpu)
 {
 	unsigned long flags;
 
 	write_seqlock_irqsave(&t->vtime_seqlock, flags);
 	t->vtime_snap_whence = VTIME_SYS;
-	t->vtime_snap = sched_clock();
+	t->vtime_snap = sched_clock_cpu(cpu);
 	write_sequnlock_irqrestore(&t->vtime_seqlock, flags);
 }
 
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index 0c739423b0f9..b4c245580b79 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -698,10 +698,6 @@ void tick_broadcast_setup_oneshot(struct clock_event_device *bc)
 
 		bc->event_handler = tick_handle_oneshot_broadcast;
 
-		/* Take the do_timer update */
-		if (!tick_nohz_full_cpu(cpu))
-			tick_do_timer_cpu = cpu;
-
 		/*
 		 * We must be careful here. There might be other CPUs
 		 * waiting for periodic broadcast. We need to set the
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index f4208138fbf4..0cf1c1453181 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -306,7 +306,7 @@ static int __cpuinit tick_nohz_cpu_down_callback(struct notifier_block *nfb,
 		 * we can't safely shutdown that CPU.
 		 */
 		if (have_nohz_full_mask && tick_do_timer_cpu == cpu)
-			return -EINVAL;
+			return NOTIFY_BAD;
 		break;
 	}
 	return NOTIFY_OK;