Merge tag 'v3.10.13' into lsk/v3.10/topic/kvm

This is the 3.10.13 stable release

24 files changed, 188 insertions, 78 deletions

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index c205035a6b96..d606463aa6d6 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -992,18 +992,20 @@ static efi_status_t exit_boot(struct boot_params *boot_params,
 	efi_memory_desc_t *mem_map;
 	efi_status_t status;
 	__u32 desc_version;
+	bool called_exit = false;
 	u8 nr_entries;
 	int i;
 
 	size = sizeof(*mem_map) * 32;
 
 again:
-	size += sizeof(*mem_map);
+	size += sizeof(*mem_map) * 2;
 	_size = size;
 	status = low_alloc(size, 1, (unsigned long *)&mem_map);
 	if (status != EFI_SUCCESS)
 		return status;
 
+get_map:
 	status = efi_call_phys5(sys_table->boottime->get_memory_map, &size,
 				mem_map, &key, &desc_size, &desc_version);
 	if (status == EFI_BUFFER_TOO_SMALL) {
@@ -1029,8 +1031,20 @@ again:
 	/* Might as well exit boot services now */
 	status = efi_call_phys2(sys_table->boottime->exit_boot_services,
 				handle, key);
-	if (status != EFI_SUCCESS)
-		goto free_mem_map;
+	if (status != EFI_SUCCESS) {
+		/*
+		 * ExitBootServices() will fail if any of the event
+		 * handlers change the memory map. In which case, we
+		 * must be prepared to retry, but only once so that
+		 * we're guaranteed to exit on repeated failures instead
+		 * of spinning forever.
+		 */
+		if (called_exit)
+			goto free_mem_map;
+
+		called_exit = true;
+		goto get_map;
+	}
 
 	/* Historic? */
 	boot_params->alt_mem_k = 32 * 1024;
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index cf1a471a18a2..10adb41f162e 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -459,7 +459,7 @@ int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp);
+		compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
 		if (ksig->ka.sa.sa_flags & SA_RESTORER)
 			restorer = ksig->ka.sa.sa_restorer;
diff --git a/arch/x86/include/asm/bootparam_utils.h b/arch/x86/include/asm/bootparam_utils.h
index 653668d140f9..4a8cb8d7cbd5 100644
--- a/arch/x86/include/asm/bootparam_utils.h
+++ b/arch/x86/include/asm/bootparam_utils.h
@@ -35,9 +35,9 @@ static void sanitize_boot_params(struct boot_params *boot_params)
 	 */
 	if (boot_params->sentinel) {
 		/* fields in boot_params are left uninitialized, clear them */
-		memset(&boot_params->olpc_ofw_header, 0,
+		memset(&boot_params->ext_ramdisk_image, 0,
 		       (char *)&boot_params->efi_info -
-			(char *)&boot_params->olpc_ofw_header);
+			(char *)&boot_params->ext_ramdisk_image);
 		memset(&boot_params->kbd_status, 0,
 		       (char *)&boot_params->hdr -
 		       (char *)&boot_params->kbd_status);
diff --git a/arch/x86/include/asm/checksum_32.h b/arch/x86/include/asm/checksum_32.h
index 46fc474fd819..f50de6951738 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -49,9 +49,15 @@ static inline __wsum csum_partial_copy_from_user(const void __user *src,
 						 int len, __wsum sum,
 						 int *err_ptr)
 {
+	__wsum ret;
+
 	might_sleep();
-	return csum_partial_copy_generic((__force void *)src, dst,
-					 len, sum, err_ptr, NULL);
+	stac();
+	ret = csum_partial_copy_generic((__force void *)src, dst,
+					len, sum, err_ptr, NULL);
+	clac();
+
+	return ret;
 }
 
 /*
@@ -176,10 +182,16 @@ static inline __wsum csum_and_copy_to_user(const void *src,
 					   int len, __wsum sum,
 					   int *err_ptr)
 {
+	__wsum ret;
+
 	might_sleep();
-	if (access_ok(VERIFY_WRITE, dst, len))
-		return csum_partial_copy_generic(src, (__force void *)dst,
-						 len, sum, NULL, err_ptr);
+	if (access_ok(VERIFY_WRITE, dst, len)) {
+		stac();
+		ret = csum_partial_copy_generic(src, (__force void *)dst,
+						len, sum, NULL, err_ptr);
+		clac();
+		return ret;
+	}
 
 	if (len)
 		*err_ptr = -EFAULT;
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index fa5f71e021d5..e6833c655e59 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -32,11 +32,20 @@
 #define MCI_STATUS_PCC   (1ULL<<57)  /* processor context corrupt */
 #define MCI_STATUS_S	 (1ULL<<56)  /* Signaled machine check */
 #define MCI_STATUS_AR	 (1ULL<<55)  /* Action required */
-#define MCACOD		  0xffff     /* MCA Error Code */
+
+/*
+ * Note that the full MCACOD field of IA32_MCi_STATUS MSR is
+ * bits 15:0.  But bit 12 is the 'F' bit, defined for corrected
+ * errors to indicate that errors are being filtered by hardware.
+ * We should mask out bit 12 when looking for specific signatures
+ * of uncorrected errors - so the F bit is deliberately skipped
+ * in this #define.
+ */
+#define MCACOD		  0xefff     /* MCA Error Code */
 
 /* Architecturally defined codes from SDM Vol. 3B Chapter 15 */
 #define MCACOD_SCRUB	0x00C0	/* 0xC0-0xCF Memory Scrubbing */
-#define MCACOD_SCRUBMSK	0xfff0
+#define MCACOD_SCRUBMSK	0xeff0	/* Skip bit 12 ('F' bit) */
 #define MCACOD_L3WB	0x017A	/* L3 Explicit Writeback */
 #define MCACOD_DATA	0x0134	/* Data Load */
 #define MCACOD_INSTR	0x0150	/* Instruction Fetch */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index cdbf36776106..be12c534fd59 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -45,22 +45,28 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 		/* Re-load page tables */
 		load_cr3(next->pgd);
 
-		/* stop flush ipis for the previous mm */
+		/* Stop flush ipis for the previous mm */
 		cpumask_clear_cpu(cpu, mm_cpumask(prev));
 
-		/*
-		 * load the LDT, if the LDT is different:
-		 */
+		/* Load the LDT, if the LDT is different: */
 		if (unlikely(prev->context.ldt != next->context.ldt))
 			load_LDT_nolock(&next->context);
 	}
 #ifdef CONFIG_SMP
-	else {
+	  else {
 		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
 		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
 
-		if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) {
-			/* We were in lazy tlb mode and leave_mm disabled
+		if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
+			/*
+			 * On established mms, the mm_cpumask is only changed
+			 * from irq context, from ptep_clear_flush() while in
+			 * lazy tlb mode, and here. Irqs are blocked during
+			 * schedule, protecting us from simultaneous changes.
+			 */
+			cpumask_set_cpu(cpu, mm_cpumask(next));
+			/*
+			 * We were in lazy tlb mode and leave_mm disabled
 			 * tlb flush IPI delivery. We must reload CR3
 			 * to make sure to use no freed page tables.
 			 */
diff --git a/arch/x86/include/asm/xor_avx.h b/arch/x86/include/asm/xor_avx.h
index 7ea79c5fa1f2..492b29802f57 100644
--- a/arch/x86/include/asm/xor_avx.h
+++ b/arch/x86/include/asm/xor_avx.h
@@ -167,12 +167,12 @@ static struct xor_block_template xor_block_avx = {
 
 #define AVX_XOR_SPEED \
 do { \
-	if (cpu_has_avx) \
+	if (cpu_has_avx && cpu_has_osxsave) \
 		xor_speed(&xor_block_avx); \
 } while (0)
 
 #define AVX_SELECT(FASTEST) \
-	(cpu_has_avx ? &xor_block_avx : FASTEST)
+	(cpu_has_avx && cpu_has_osxsave ? &xor_block_avx : FASTEST)
 
 #else
 
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index b44577bc9744..ec94e11807dc 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -48,9 +48,20 @@ int acpi_suspend_lowlevel(void)
 #ifndef CONFIG_64BIT
 	native_store_gdt((struct desc_ptr *)&header->pmode_gdt);
 
+	/*
+	 * We have to check that we can write back the value, and not
+	 * just read it.  At least on 90 nm Pentium M (Family 6, Model
+	 * 13), reading an invalid MSR is not guaranteed to trap, see
+	 * Erratum X4 in "Intel Pentium M Processor on 90 nm Process
+	 * with 2-MB L2 Cache and Intel® Processor A100 and A110 on 90
+	 * nm process with 512-KB L2 Cache Specification Update".
+	 */
 	if (!rdmsr_safe(MSR_EFER,
 			&header->pmode_efer_low,
-			&header->pmode_efer_high))
+			&header->pmode_efer_high) &&
+	    !wrmsr_safe(MSR_EFER,
+			header->pmode_efer_low,
+			header->pmode_efer_high))
 		header->pmode_behavior |= (1 << WAKEUP_BEHAVIOR_RESTORE_EFER);
 #endif /* !CONFIG_64BIT */
 
@@ -61,7 +72,10 @@ int acpi_suspend_lowlevel(void)
 	}
 	if (!rdmsr_safe(MSR_IA32_MISC_ENABLE,
 			&header->pmode_misc_en_low,
-			&header->pmode_misc_en_high))
+			&header->pmode_misc_en_high) &&
+	    !wrmsr_safe(MSR_IA32_MISC_ENABLE,
+			header->pmode_misc_en_low,
+			header->pmode_misc_en_high))
 		header->pmode_behavior |=
 			(1 << WAKEUP_BEHAVIOR_RESTORE_MISC_ENABLE);
 	header->realmode_flags = acpi_realmode_flags;
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 3048ded1b598..59554dca96ec 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -20,6 +20,7 @@ const struct pci_device_id amd_nb_misc_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F3) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) },
 	{}
 };
@@ -27,6 +28,7 @@ EXPORT_SYMBOL(amd_nb_misc_ids);
 
 static const struct pci_device_id amd_nb_link_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M30H_NB_F4) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) },
 	{}
 };
@@ -81,13 +83,20 @@ int amd_cache_northbridges(void)
 			next_northbridge(misc, amd_nb_misc_ids);
 		node_to_amd_nb(i)->link = link =
 			next_northbridge(link, amd_nb_link_ids);
-        }
+	}
 
+	/* GART present only on Fam15h upto model 0fh */
 	if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 ||
-	    boot_cpu_data.x86 == 0x15)
+	    (boot_cpu_data.x86 == 0x15 && boot_cpu_data.x86_model < 0x10))
 		amd_northbridges.flags |= AMD_NB_GART;
 
 	/*
+	 * Check for L3 cache presence.
+	 */
+	if (!cpuid_edx(0x80000006))
+		return 0;
+
+	/*
 	 * Some CPU families support L3 Cache Index Disable. There are some
 	 * limitations because of E382 and E388 on family 0x10.
 	 */
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index fa72a39e5d46..3982357de5b0 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -510,8 +510,9 @@ generic_get_free_region(unsigned long base, unsigned long size, int replace_reg)
 static void generic_get_mtrr(unsigned int reg, unsigned long *base,
 			     unsigned long *size, mtrr_type *type)
 {
-	unsigned int mask_lo, mask_hi, base_lo, base_hi;
-	unsigned int tmp, hi;
+	u32 mask_lo, mask_hi, base_lo, base_hi;
+	unsigned int hi;
+	u64 tmp, mask;
 
 	/*
 	 * get_mtrr doesn't need to update mtrr_state, also it could be called
@@ -532,18 +533,18 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
 	rdmsr(MTRRphysBase_MSR(reg), base_lo, base_hi);
 
 	/* Work out the shifted address mask: */
-	tmp = mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT;
-	mask_lo = size_or_mask | tmp;
+	tmp = (u64)mask_hi << (32 - PAGE_SHIFT) | mask_lo >> PAGE_SHIFT;
+	mask = size_or_mask | tmp;
 
 	/* Expand tmp with high bits to all 1s: */
-	hi = fls(tmp);
+	hi = fls64(tmp);
 	if (hi > 0) {
-		tmp |= ~((1<<(hi - 1)) - 1);
+		tmp |= ~((1ULL<<(hi - 1)) - 1);
 
-		if (tmp != mask_lo) {
+		if (tmp != mask) {
 			printk(KERN_WARNING "mtrr: your BIOS has configured an incorrect mask, fixing it.\n");
 			add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_STILL_OK);
-			mask_lo = tmp;
+			mask = tmp;
 		}
 	}
 
@@ -551,8 +552,8 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
 	 * This works correctly if size is a power of two, i.e. a
 	 * contiguous range:
 	 */
-	*size = -mask_lo;
-	*base = base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT;
+	*size = -mask;
+	*base = (u64)base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT;
 	*type = base_lo & 0xff;
 
 out_put_cpu:
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 726bf963c227..ca22b73aaa25 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -305,7 +305,8 @@ int mtrr_add_page(unsigned long base, unsigned long size,
 		return -EINVAL;
 	}
 
-	if (base & size_or_mask || size & size_or_mask) {
+	if ((base | (base + size - 1)) >>
+	    (boot_cpu_data.x86_phys_bits - PAGE_SHIFT)) {
 		pr_warning("mtrr: base or size exceeds the MTRR width\n");
 		return -EINVAL;
 	}
@@ -583,6 +584,7 @@ static struct syscore_ops mtrr_syscore_ops = {
 
 int __initdata changed_by_mtrr_cleanup;
 
+#define SIZE_OR_MASK_BITS(n)  (~((1ULL << ((n) - PAGE_SHIFT)) - 1))
 /**
  * mtrr_bp_init - initialize mtrrs on the boot CPU
  *
@@ -600,7 +602,7 @@ void __init mtrr_bp_init(void)
 
 	if (cpu_has_mtrr) {
 		mtrr_if = &generic_mtrr_ops;
-		size_or_mask = 0xff000000;			/* 36 bits */
+		size_or_mask = SIZE_OR_MASK_BITS(36);
 		size_and_mask = 0x00f00000;
 		phys_addr = 36;
 
@@ -619,7 +621,7 @@ void __init mtrr_bp_init(void)
 			     boot_cpu_data.x86_mask == 0x4))
 				phys_addr = 36;
 
-			size_or_mask = ~((1ULL << (phys_addr - PAGE_SHIFT)) - 1);
+			size_or_mask = SIZE_OR_MASK_BITS(phys_addr);
 			size_and_mask = ~size_or_mask & 0xfffff00000ULL;
 		} else if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR &&
 			   boot_cpu_data.x86 == 6) {
@@ -627,7 +629,7 @@ void __init mtrr_bp_init(void)
 			 * VIA C* family have Intel style MTRRs,
 			 * but don't support PAE
 			 */
-			size_or_mask = 0xfff00000;		/* 32 bits */
+			size_or_mask = SIZE_OR_MASK_BITS(32);
 			size_and_mask = 0;
 			phys_addr = 32;
 		}
@@ -637,21 +639,21 @@ void __init mtrr_bp_init(void)
 			if (cpu_has_k6_mtrr) {
 				/* Pre-Athlon (K6) AMD CPU MTRRs */
 				mtrr_if = mtrr_ops[X86_VENDOR_AMD];
-				size_or_mask = 0xfff00000;	/* 32 bits */
+				size_or_mask = SIZE_OR_MASK_BITS(32);
 				size_and_mask = 0;
 			}
 			break;
 		case X86_VENDOR_CENTAUR:
 			if (cpu_has_centaur_mcr) {
 				mtrr_if = mtrr_ops[X86_VENDOR_CENTAUR];
-				size_or_mask = 0xfff00000;	/* 32 bits */
+				size_or_mask = SIZE_OR_MASK_BITS(32);
 				size_and_mask = 0;
 			}
 			break;
 		case X86_VENDOR_CYRIX:
 			if (cpu_has_cyrix_arr) {
 				mtrr_if = mtrr_ops[X86_VENDOR_CYRIX];
-				size_or_mask = 0xfff00000;	/* 32 bits */
+				size_or_mask = SIZE_OR_MASK_BITS(32);
 				size_and_mask = 0;
 			}
 			break;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index 52441a2af538..8aac56bda7dc 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -314,8 +314,8 @@ static struct uncore_event_desc snbep_uncore_imc_events[] = {
 static struct uncore_event_desc snbep_uncore_qpi_events[] = {
 	INTEL_UNCORE_EVENT_DESC(clockticks,       "event=0x14"),
 	INTEL_UNCORE_EVENT_DESC(txl_flits_active, "event=0x00,umask=0x06"),
-	INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x02,umask=0x08"),
-	INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x03,umask=0x04"),
+	INTEL_UNCORE_EVENT_DESC(drs_data,         "event=0x102,umask=0x08"),
+	INTEL_UNCORE_EVENT_DESC(ncb_data,         "event=0x103,umask=0x04"),
 	{ /* end: all zeroes */ },
 };
 
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 94ab6b90dd3f..63bdb29b2549 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -196,15 +196,23 @@ static void __init ati_bugs_contd(int num, int slot, int func)
 static void __init intel_remapping_check(int num, int slot, int func)
 {
 	u8 revision;
+	u16 device;
 
+	device = read_pci_config_16(num, slot, func, PCI_DEVICE_ID);
 	revision = read_pci_config_byte(num, slot, func, PCI_REVISION_ID);
 
 	/*
-	 * Revision 0x13 of this chipset supports irq remapping
-	 * but has an erratum that breaks its behavior, flag it as such
+ 	 * Revision 13 of all triggering devices id in this quirk have
+	 * a problem draining interrupts when irq remapping is enabled,
+	 * and should be flagged as broken.  Additionally revisions 0x12
+	 * and 0x22 of device id 0x3405 has this problem.
 	 */
 	if (revision == 0x13)
 		set_irq_remapping_broken();
+	else if ((device == 0x3405) &&
+	    ((revision == 0x12) ||
+	     (revision == 0x22)))
+		set_irq_remapping_broken();
 
 }
 
@@ -239,6 +247,8 @@ static struct chipset early_qrk[] __initdata = {
 	  PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd },
 	{ PCI_VENDOR_ID_INTEL, 0x3403, PCI_CLASS_BRIDGE_HOST,
 	  PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
+	{ PCI_VENDOR_ID_INTEL, 0x3405, PCI_CLASS_BRIDGE_HOST,
+	  PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
 	{ PCI_VENDOR_ID_INTEL, 0x3406, PCI_CLASS_BRIDGE_HOST,
 	  PCI_BASE_CLASS_BRIDGE, 0, intel_remapping_check },
 	{}
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 321d65ebaffe..a8368608ab41 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -513,7 +513,7 @@ ENTRY(phys_base)
 #include "../../x86/xen/xen-head.S"
 	
 	.section .bss, "aw", @nobits
-	.align L1_CACHE_BYTES
+	.align PAGE_SIZE
 ENTRY(idt_table)
 	.skip IDT_ENTRIES * 16
 
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index cb339097b9ea..f7ea30dce238 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -116,7 +116,7 @@ static void __cpuinit mxcsr_feature_mask_init(void)
 
 	if (cpu_has_fxsr) {
 		memset(&fx_scratch, 0, sizeof(struct i387_fxsave_struct));
-		asm volatile("fxsave %0" : : "m" (fx_scratch));
+		asm volatile("fxsave %0" : "+m" (fx_scratch));
 		mask = fx_scratch.mxcsr_mask;
 		if (mask == 0)
 			mask = 0x0000ffbf;
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 69562992e457..087ab2af381a 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -364,7 +364,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
+		save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
 		/* Set up to return from userspace.  */
 		restorer = VDSO32_SYMBOL(current->mm->context.vdso, rt_sigreturn);
@@ -429,7 +429,7 @@ static int __setup_rt_frame(int sig, struct ksignal *ksig,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		err |= __save_altstack(&frame->uc.uc_stack, regs->sp);
+		save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 
 		/* Set up to return from userspace.  If provided, use a stub
 		   already in userspace.  */
@@ -496,7 +496,7 @@ static int x32_setup_rt_frame(struct ksignal *ksig,
 		else
 			put_user_ex(0, &frame->uc.uc_flags);
 		put_user_ex(0, &frame->uc.uc_link);
-		err |= __compat_save_altstack(&frame->uc.uc_stack, regs->sp);
+		compat_save_altstack_ex(&frame->uc.uc_stack, regs->sp);
 		put_user_ex(0, &frame->uc.uc__pad0);
 
 		if (ksig->ka.sa.sa_flags & SA_RESTORER) {
diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c
index dbded5aedb81..30277e27431a 100644
--- a/arch/x86/kernel/sys_x86_64.c
+++ b/arch/x86/kernel/sys_x86_64.c
@@ -101,7 +101,7 @@ static void find_start_end(unsigned long flags, unsigned long *begin,
 				*begin = new_begin;
 		}
 	} else {
-		*begin = TASK_UNMAPPED_BASE;
+		*begin = current->mm->mmap_legacy_base;
 		*end = TASK_SIZE;
 	}
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 260a91939555..5402c94ab768 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3399,15 +3399,22 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
 	var->limit = vmx_read_guest_seg_limit(vmx, seg);
 	var->selector = vmx_read_guest_seg_selector(vmx, seg);
 	ar = vmx_read_guest_seg_ar(vmx, seg);
+	var->unusable = (ar >> 16) & 1;
 	var->type = ar & 15;
 	var->s = (ar >> 4) & 1;
 	var->dpl = (ar >> 5) & 3;
-	var->present = (ar >> 7) & 1;
+	/*
+	 * Some userspaces do not preserve unusable property. Since usable
+	 * segment has to be present according to VMX spec we can use present
+	 * property to amend userspace bug by making unusable segment always
+	 * nonpresent. vmx_segment_access_rights() already marks nonpresent
+	 * segment as unusable.
+	 */
+	var->present = !var->unusable;
 	var->avl = (ar >> 12) & 1;
 	var->l = (ar >> 13) & 1;
 	var->db = (ar >> 14) & 1;
 	var->g = (ar >> 15) & 1;
-	var->unusable = (ar >> 16) & 1;
 }
 
 static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
diff --git a/arch/x86/lib/csum-wrappers_64.c b/arch/x86/lib/csum-wrappers_64.c
index 25b7ae8d058a..7609e0e421ec 100644
--- a/arch/x86/lib/csum-wrappers_64.c
+++ b/arch/x86/lib/csum-wrappers_64.c
@@ -6,6 +6,7 @@
  */
 #include <asm/checksum.h>
 #include <linux/module.h>
+#include <asm/smap.h>
 
 /**
  * csum_partial_copy_from_user - Copy and checksum from user space.
@@ -52,8 +53,10 @@ csum_partial_copy_from_user(const void __user *src, void *dst,
 			len -= 2;
 		}
 	}
+	stac();
 	isum = csum_partial_copy_generic((__force const void *)src,
 				dst, len, isum, errp, NULL);
+	clac();
 	if (unlikely(*errp))
 		goto out_err;
 
@@ -82,6 +85,8 @@ __wsum
 csum_partial_copy_to_user(const void *src, void __user *dst,
 			  int len, __wsum isum, int *errp)
 {
+	__wsum ret;
+
 	might_sleep();
 
 	if (unlikely(!access_ok(VERIFY_WRITE, dst, len))) {
@@ -105,8 +110,11 @@ csum_partial_copy_to_user(const void *src, void __user *dst,
 	}
 
 	*errp = 0;
-	return csum_partial_copy_generic(src, (void __force *)dst,
-					 len, isum, NULL, errp);
+	stac();
+	ret = csum_partial_copy_generic(src, (void __force *)dst,
+					len, isum, NULL, errp);
+	clac();
+	return ret;
 }
 EXPORT_SYMBOL(csum_partial_copy_to_user);
 
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 1f34e9219775..7a5bf1b76e2f 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -78,8 +78,8 @@ __ref void *alloc_low_pages(unsigned int num)
 	return __va(pfn << PAGE_SHIFT);
 }
 
-/* need 4 4k for initial PMD_SIZE, 4k for 0-ISA_END_ADDRESS */
-#define INIT_PGT_BUF_SIZE	(5 * PAGE_SIZE)
+/* need 3 4k for initial PMD_SIZE,  3 4k for 0-ISA_END_ADDRESS */
+#define INIT_PGT_BUF_SIZE	(6 * PAGE_SIZE)
 RESERVE_BRK(early_pgt_alloc, INIT_PGT_BUF_SIZE);
 void  __init early_alloc_pgt_buf(void)
 {
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 845df6835f9f..5c1ae28825cd 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -112,12 +112,14 @@ static unsigned long mmap_legacy_base(void)
  */
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
+	mm->mmap_legacy_base = mmap_legacy_base();
+	mm->mmap_base = mmap_base();
+
 	if (mmap_is_legacy()) {
-		mm->mmap_base = mmap_legacy_base();
+		mm->mmap_base = mm->mmap_legacy_base;
 		mm->get_unmapped_area = arch_get_unmapped_area;
 		mm->unmap_area = arch_unmap_area;
 	} else {
-		mm->mmap_base = mmap_base();
 		mm->get_unmapped_area = arch_get_unmapped_area_topdown;
 		mm->unmap_area = arch_unmap_area_topdown;
 	}
diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
index 94eac5c85cdc..0a9fb7a0b452 100644
--- a/arch/x86/xen/setup.c
+++ b/arch/x86/xen/setup.c
@@ -313,6 +313,17 @@ static void xen_align_and_add_e820_region(u64 start, u64 size, int type)
 	e820_add_region(start, end - start, type);
 }
 
+void xen_ignore_unusable(struct e820entry *list, size_t map_size)
+{
+	struct e820entry *entry;
+	unsigned int i;
+
+	for (i = 0, entry = list; i < map_size; i++, entry++) {
+		if (entry->type == E820_UNUSABLE)
+			entry->type = E820_RAM;
+	}
+}
+
 /**
  * machine_specific_memory_setup - Hook for machine specific memory setup.
  **/
@@ -353,6 +364,17 @@ char * __init xen_memory_setup(void)
 	}
 	BUG_ON(rc);
 
+	/*
+	 * Xen won't allow a 1:1 mapping to be created to UNUSABLE
+	 * regions, so if we're using the machine memory map leave the
+	 * region as RAM as it is in the pseudo-physical map.
+	 *
+	 * UNUSABLE regions in domUs are not handled and will need
+	 * a patch in the future.
+	 */
+	if (xen_initial_domain())
+		xen_ignore_unusable(map, memmap.nr_entries);
+
 	/* Make sure the Xen-supplied memory map is well-ordered. */
 	sanitize_e820_map(map, memmap.nr_entries, &memmap.nr_entries);
 
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index d99cae8147d1..a1e58e19d0cc 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -667,8 +667,15 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus)
 static int __cpuinit xen_hvm_cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int rc;
-	rc = native_cpu_up(cpu, tidle);
-	WARN_ON (xen_smp_intr_init(cpu));
+	/*
+	 * xen_smp_intr_init() needs to run before native_cpu_up()
+	 * so that IPI vectors are set up on the booting CPU before
+	 * it is marked online in native_cpu_up().
+	*/
+	rc = xen_smp_intr_init(cpu);
+	WARN_ON(rc);
+	if (!rc)
+		rc =  native_cpu_up(cpu, tidle);
 	return rc;
 }
 
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 3d88bfdf9e1c..13e8935e2eab 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -36,9 +36,8 @@ static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate);
 /* snapshots of runstate info */
 static DEFINE_PER_CPU(struct vcpu_runstate_info, xen_runstate_snapshot);
 
-/* unused ns of stolen and blocked time */
+/* unused ns of stolen time */
 static DEFINE_PER_CPU(u64, xen_residual_stolen);
-static DEFINE_PER_CPU(u64, xen_residual_blocked);
 
 /* return an consistent snapshot of 64-bit time/counter value */
 static u64 get64(const u64 *p)
@@ -115,7 +114,7 @@ static void do_stolen_accounting(void)
 {
 	struct vcpu_runstate_info state;
 	struct vcpu_runstate_info *snap;
-	s64 blocked, runnable, offline, stolen;
+	s64 runnable, offline, stolen;
 	cputime_t ticks;
 
 	get_runstate_snapshot(&state);
@@ -125,7 +124,6 @@ static void do_stolen_accounting(void)
 	snap = &__get_cpu_var(xen_runstate_snapshot);
 
 	/* work out how much time the VCPU has not been runn*ing*  */
-	blocked = state.time[RUNSTATE_blocked] - snap->time[RUNSTATE_blocked];
 	runnable = state.time[RUNSTATE_runnable] - snap->time[RUNSTATE_runnable];
 	offline = state.time[RUNSTATE_offline] - snap->time[RUNSTATE_offline];
 
@@ -141,17 +139,6 @@ static void do_stolen_accounting(void)
 	ticks = iter_div_u64_rem(stolen, NS_PER_TICK, &stolen);
 	__this_cpu_write(xen_residual_stolen, stolen);
 	account_steal_ticks(ticks);
-
-	/* Add the appropriate number of ticks of blocked time,
-	   including any left-overs from last time. */
-	blocked += __this_cpu_read(xen_residual_blocked);
-
-	if (blocked < 0)
-		blocked = 0;
-
-	ticks = iter_div_u64_rem(blocked, NS_PER_TICK, &blocked);
-	__this_cpu_write(xen_residual_blocked, blocked);
-	account_idle_ticks(ticks);
 }
 
 /* Get the TSC speed from Xen */