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>

56 files changed, 334 insertions, 195 deletions

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