Merge tag 'v3.9' into efi-for-tip2

Resolve conflicts for Ingo.

Conflicts:
	drivers/firmware/Kconfig
	drivers/firmware/efivars.c

Signed-off-by: Matt Fleming <matt.fleming@intel.com>

24 files changed, 370 insertions, 77 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 70c0f3d..15b5cef 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1549,6 +1549,7 @@ config X86_SMAP
 config EFI
 	bool "EFI runtime service support"
 	depends on ACPI
+	select UCS2_STRING
 	---help---
 	  This enables the kernel to use EFI runtime services that are
 	  available (such as the EFI variable services).
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 8a84501..5ef205c 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -4,7 +4,7 @@
 # create a compressed vmlinux image from the original vmlinux
 #
 
-targets := vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo head_$(BITS).o misc.o string.o cmdline.o early_serial_console.o piggy.o
+targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma vmlinux.bin.xz vmlinux.bin.lzo
 
 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
@@ -29,7 +29,6 @@ VMLINUX_OBJS = $(obj)/vmlinux.lds $(obj)/head_$(BITS).o $(obj)/misc.o \
 	$(obj)/piggy.o
 
 $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
-$(obj)/efi_stub_$(BITS).o: KBUILD_CLFAGS += -fshort-wchar -mno-red-zone
 
 ifeq ($(CONFIG_EFI_STUB), y)
 	VMLINUX_OBJS += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o
@@ -43,7 +42,7 @@ OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
 $(obj)/vmlinux.bin: vmlinux FORCE
 	$(call if_changed,objcopy)
 
-targets += vmlinux.bin.all vmlinux.relocs
+targets += $(patsubst $(obj)/%,%,$(VMLINUX_OBJS)) vmlinux.bin.all vmlinux.relocs
 
 CMD_RELOCS = arch/x86/tools/relocs
 quiet_cmd_relocs = RELOCS  $@
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index c205035..35ee62f 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -251,6 +251,51 @@ static void find_bits(unsigned long mask, u8 *pos, u8 *size)
 	*size = len;
 }
 
+static efi_status_t setup_efi_vars(struct boot_params *params)
+{
+	struct setup_data *data;
+	struct efi_var_bootdata *efidata;
+	u64 store_size, remaining_size, var_size;
+	efi_status_t status;
+
+	if (sys_table->runtime->hdr.revision < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
+
+	while (data && data->next)
+		data = (struct setup_data *)(unsigned long)data->next;
+
+	status = efi_call_phys4((void *)sys_table->runtime->query_variable_info,
+				EFI_VARIABLE_NON_VOLATILE |
+				EFI_VARIABLE_BOOTSERVICE_ACCESS |
+				EFI_VARIABLE_RUNTIME_ACCESS, &store_size,
+				&remaining_size, &var_size);
+
+	if (status != EFI_SUCCESS)
+		return status;
+
+	status = efi_call_phys3(sys_table->boottime->allocate_pool,
+				EFI_LOADER_DATA, sizeof(*efidata), &efidata);
+
+	if (status != EFI_SUCCESS)
+		return status;
+
+	efidata->data.type = SETUP_EFI_VARS;
+	efidata->data.len = sizeof(struct efi_var_bootdata) -
+		sizeof(struct setup_data);
+	efidata->data.next = 0;
+	efidata->store_size = store_size;
+	efidata->remaining_size = remaining_size;
+	efidata->max_var_size = var_size;
+
+	if (data)
+		data->next = (unsigned long)efidata;
+	else
+		params->hdr.setup_data = (unsigned long)efidata;
+
+}
+
 static efi_status_t setup_efi_pci(struct boot_params *params)
 {
 	efi_pci_io_protocol *pci;
@@ -1157,6 +1202,8 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
 
 	setup_graphics(boot_params);
 
+	setup_efi_vars(boot_params);
+
 	setup_efi_pci(boot_params);
 
 	status = efi_call_phys3(sys_table->boottime->allocate_pool,
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 60c89f3..2fb5d58 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -102,6 +102,13 @@ extern void efi_call_phys_epilog(void);
 extern void efi_unmap_memmap(void);
 extern void efi_memory_uc(u64 addr, unsigned long size);
 
+struct efi_var_bootdata {
+	struct setup_data data;
+	u64 store_size;
+	u64 remaining_size;
+	u64 max_var_size;
+};
+
 #ifdef CONFIG_EFI
 
 static inline bool efi_is_native(void)
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 5edd174..7361e47 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -703,7 +703,10 @@ static inline void arch_leave_lazy_mmu_mode(void)
 	PVOP_VCALL0(pv_mmu_ops.lazy_mode.leave);
 }
 
-void arch_flush_lazy_mmu_mode(void);
+static inline void arch_flush_lazy_mmu_mode(void)
+{
+	PVOP_VCALL0(pv_mmu_ops.lazy_mode.flush);
+}
 
 static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,
 				phys_addr_t phys, pgprot_t flags)
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 142236e..b3b0ec1 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -91,6 +91,7 @@ struct pv_lazy_ops {
 	/* Set deferred update mode, used for batching operations. */
 	void (*enter)(void);
 	void (*leave)(void);
+	void (*flush)(void);
 };
 
 struct pv_time_ops {
@@ -679,6 +680,7 @@ void paravirt_end_context_switch(struct task_struct *next);
 
 void paravirt_enter_lazy_mmu(void);
 void paravirt_leave_lazy_mmu(void);
+void paravirt_flush_lazy_mmu(void);
 
 void _paravirt_nop(void);
 u32 _paravirt_ident_32(u32);
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 1ace47b..2e188d6 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -29,13 +29,13 @@ extern const unsigned long sys_call_table[];
  */
 static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 {
-	return regs->orig_ax & __SYSCALL_MASK;
+	return regs->orig_ax;
 }
 
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
-	regs->ax = regs->orig_ax & __SYSCALL_MASK;
+	regs->ax = regs->orig_ax;
 }
 
 static inline long syscall_get_error(struct task_struct *task,
diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h
index 4fef207..c779730 100644
--- a/arch/x86/include/asm/tlb.h
+++ b/arch/x86/include/asm/tlb.h
@@ -7,7 +7,7 @@
 
 #define tlb_flush(tlb)							\
 {									\
-	if (tlb->fullmm == 0)						\
+	if (!tlb->fullmm && !tlb->need_flush_all) 			\
 		flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, 0UL);	\
 	else								\
 		flush_tlb_mm_range(tlb->mm, 0UL, TLB_FLUSH_ALL, 0UL);	\
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index c15ddaf..0874424 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -6,6 +6,7 @@
 #define SETUP_E820_EXT			1
 #define SETUP_DTB			2
 #define SETUP_PCI			3
+#define SETUP_EFI_VARS			4
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index a7d26d8..8f4be53 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -35,13 +35,6 @@ static bool __init ms_hyperv_platform(void)
 	if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
 		return false;
 
-	/*
-	 * Xen emulates Hyper-V to support enlightened Windows.
-	 * Check to see first if we are on a Xen Hypervisor.
-	 */
-	if (xen_cpuid_base())
-		return false;
-
 	cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS,
 	      &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]);
 
@@ -82,12 +75,6 @@ static void __init ms_hyperv_init_platform(void)
 
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
 		clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
-#if IS_ENABLED(CONFIG_HYPERV)
-	/*
-	 * Setup the IDT for hypervisor callback.
-	 */
-	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
-#endif
 }
 
 const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
@@ -103,6 +90,11 @@ static irq_handler_t vmbus_isr;
 
 void hv_register_vmbus_handler(int irq, irq_handler_t handler)
 {
+	/*
+	 * Setup the IDT for hypervisor callback.
+	 */
+	alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector);
+
 	vmbus_irq = irq;
 	vmbus_isr = handler;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index dab7580..cc45deb 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -153,8 +153,14 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly =
 };
 
 static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
-	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
-	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
+	INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
+	INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1),
+	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),
 	EVENT_EXTRA_END
 };
 
@@ -2097,7 +2103,10 @@ __init int intel_pmu_init(void)
 		x86_pmu.event_constraints = intel_snb_event_constraints;
 		x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-		x86_pmu.extra_regs = intel_snb_extra_regs;
+		if (boot_cpu_data.x86_model == 45)
+			x86_pmu.extra_regs = intel_snbep_extra_regs;
+		else
+			x86_pmu.extra_regs = intel_snb_extra_regs;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
@@ -2123,7 +2132,10 @@ __init int intel_pmu_init(void)
 		x86_pmu.event_constraints = intel_ivb_event_constraints;
 		x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
 		x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
-		x86_pmu.extra_regs = intel_snb_extra_regs;
+		if (boot_cpu_data.x86_model == 62)
+			x86_pmu.extra_regs = intel_snbep_extra_regs;
+		else
+			x86_pmu.extra_regs = intel_snb_extra_regs;
 		/* all extra regs are per-cpu when HT is on */
 		x86_pmu.er_flags |= ERF_HAS_RSP_1;
 		x86_pmu.er_flags |= ERF_NO_HT_SHARING;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index b05a575..26830f3 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -314,10 +314,11 @@ int intel_pmu_drain_bts_buffer(void)
 	if (top <= at)
 		return 0;
 
+	memset(&regs, 0, sizeof(regs));
+
 	ds->bts_index = ds->bts_buffer_base;
 
 	perf_sample_data_init(&data, 0, event->hw.last_period);
-	regs.ip     = 0;
 
 	/*
 	 * Prepare a generic sample, i.e. fill in the invariant fields.
diff --git a/arch/x86/kernel/microcode_core_early.c b/arch/x86/kernel/microcode_core_early.c
index 577db84..833d51d 100644
--- a/arch/x86/kernel/microcode_core_early.c
+++ b/arch/x86/kernel/microcode_core_early.c
@@ -45,9 +45,6 @@ static int __cpuinit x86_vendor(void)
 	u32 eax = 0x00000000;
 	u32 ebx, ecx = 0, edx;
 
-	if (!have_cpuid_p())
-		return X86_VENDOR_UNKNOWN;
-
 	native_cpuid(&eax, &ebx, &ecx, &edx);
 
 	if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx))
@@ -59,18 +56,45 @@ static int __cpuinit x86_vendor(void)
 	return X86_VENDOR_UNKNOWN;
 }
 
+static int __cpuinit x86_family(void)
+{
+	u32 eax = 0x00000001;
+	u32 ebx, ecx = 0, edx;
+	int x86;
+
+	native_cpuid(&eax, &ebx, &ecx, &edx);
+
+	x86 = (eax >> 8) & 0xf;
+	if (x86 == 15)
+		x86 += (eax >> 20) & 0xff;
+
+	return x86;
+}
+
 void __init load_ucode_bsp(void)
 {
-	int vendor = x86_vendor();
+	int vendor, x86;
+
+	if (!have_cpuid_p())
+		return;
 
-	if (vendor == X86_VENDOR_INTEL)
+	vendor = x86_vendor();
+	x86 = x86_family();
+
+	if (vendor == X86_VENDOR_INTEL && x86 >= 6)
 		load_ucode_intel_bsp();
 }
 
 void __cpuinit load_ucode_ap(void)
 {
-	int vendor = x86_vendor();
+	int vendor, x86;
+
+	if (!have_cpuid_p())
+		return;
+
+	vendor = x86_vendor();
+	x86 = x86_family();
 
-	if (vendor == X86_VENDOR_INTEL)
+	if (vendor == X86_VENDOR_INTEL && x86 >= 6)
 		load_ucode_intel_ap();
 }
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 17fff18..8bfb335 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -263,6 +263,18 @@ void paravirt_leave_lazy_mmu(void)
 	leave_lazy(PARAVIRT_LAZY_MMU);
 }
 
+void paravirt_flush_lazy_mmu(void)
+{
+	preempt_disable();
+
+	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
+		arch_leave_lazy_mmu_mode();
+		arch_enter_lazy_mmu_mode();
+	}
+
+	preempt_enable();
+}
+
 void paravirt_start_context_switch(struct task_struct *prev)
 {
 	BUG_ON(preemptible());
@@ -292,18 +304,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 	return this_cpu_read(paravirt_lazy_mode);
 }
 
-void arch_flush_lazy_mmu_mode(void)
-{
-	preempt_disable();
-
-	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
-		arch_leave_lazy_mmu_mode();
-		arch_enter_lazy_mmu_mode();
-	}
-
-	preempt_enable();
-}
-
 struct pv_info pv_info = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
@@ -475,6 +475,7 @@ struct pv_mmu_ops pv_mmu_ops = {
 	.lazy_mode = {
 		.enter = paravirt_nop,
 		.leave = paravirt_nop,
+		.flush = paravirt_nop,
 	},
 
 	.set_fixmap = native_set_fixmap,
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 90d8cc9..fae9134 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -507,11 +507,14 @@ static void __init memblock_x86_reserve_range_setup_data(void)
 /*
  * Keep the crash kernel below this limit.  On 32 bits earlier kernels
  * would limit the kernel to the low 512 MiB due to mapping restrictions.
+ * On 64bit, old kexec-tools need to under 896MiB.
  */
 #ifdef CONFIG_X86_32
-# define CRASH_KERNEL_ADDR_MAX	(512 << 20)
+# define CRASH_KERNEL_ADDR_LOW_MAX	(512 << 20)
+# define CRASH_KERNEL_ADDR_HIGH_MAX	(512 << 20)
 #else
-# define CRASH_KERNEL_ADDR_MAX	MAXMEM
+# define CRASH_KERNEL_ADDR_LOW_MAX	(896UL<<20)
+# define CRASH_KERNEL_ADDR_HIGH_MAX	MAXMEM
 #endif
 
 static void __init reserve_crashkernel_low(void)
@@ -521,19 +524,35 @@ static void __init reserve_crashkernel_low(void)
 	unsigned long long low_base = 0, low_size = 0;
 	unsigned long total_low_mem;
 	unsigned long long base;
+	bool auto_set = false;
 	int ret;
 
 	total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT));
+	/* crashkernel=Y,low */
 	ret = parse_crashkernel_low(boot_command_line, total_low_mem,
 						&low_size, &base);
-	if (ret != 0 || low_size <= 0)
-		return;
+	if (ret != 0) {
+		/*
+		 * two parts from lib/swiotlb.c:
+		 *	swiotlb size: user specified with swiotlb= or default.
+		 *	swiotlb overflow buffer: now is hardcoded to 32k.
+		 *		We round it to 8M for other buffers that
+		 *		may need to stay low too.
+		 */
+		low_size = swiotlb_size_or_default() + (8UL<<20);
+		auto_set = true;
+	} else {
+		/* passed with crashkernel=0,low ? */
+		if (!low_size)
+			return;
+	}
 
 	low_base = memblock_find_in_range(low_size, (1ULL<<32),
 					low_size, alignment);
 
 	if (!low_base) {
-		pr_info("crashkernel low reservation failed - No suitable area found.\n");
+		if (!auto_set)
+			pr_info("crashkernel low reservation failed - No suitable area found.\n");
 
 		return;
 	}
@@ -554,14 +573,22 @@ static void __init reserve_crashkernel(void)
 	const unsigned long long alignment = 16<<20;	/* 16M */
 	unsigned long long total_mem;
 	unsigned long long crash_size, crash_base;
+	bool high = false;
 	int ret;
 
 	total_mem = memblock_phys_mem_size();
 
+	/* crashkernel=XM */
 	ret = parse_crashkernel(boot_command_line, total_mem,
 			&crash_size, &crash_base);
-	if (ret != 0 || crash_size <= 0)
-		return;
+	if (ret != 0 || crash_size <= 0) {
+		/* crashkernel=X,high */
+		ret = parse_crashkernel_high(boot_command_line, total_mem,
+				&crash_size, &crash_base);
+		if (ret != 0 || crash_size <= 0)
+			return;
+		high = true;
+	}
 
 	/* 0 means: find the address automatically */
 	if (crash_base <= 0) {
@@ -569,7 +596,9 @@ static void __init reserve_crashkernel(void)
 		 *  kexec want bzImage is below CRASH_KERNEL_ADDR_MAX
 		 */
 		crash_base = memblock_find_in_range(alignment,
-			       CRASH_KERNEL_ADDR_MAX, crash_size, alignment);
+					high ? CRASH_KERNEL_ADDR_HIGH_MAX :
+					       CRASH_KERNEL_ADDR_LOW_MAX,
+					crash_size, alignment);
 
 		if (!crash_base) {
 			pr_info("crashkernel reservation failed - No suitable area found.\n");
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 02b51dd..f77df1c 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1857,7 +1857,7 @@ int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data)
 	if (!pv_eoi_enabled(vcpu))
 		return 0;
 	return kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.pv_eoi.data,
-					 addr);
+					 addr, sizeof(u8));
 }
 
 void kvm_lapic_init(void)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f19ac0a..e172132 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1823,7 +1823,8 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 		return 0;
 	}
 
-	if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa))
+	if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.apf.data, gpa,
+					sizeof(u32)))
 		return 1;
 
 	vcpu->arch.apf.send_user_only = !(data & KVM_ASYNC_PF_SEND_ALWAYS);
@@ -1952,12 +1953,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 
 		gpa_offset = data & ~(PAGE_MASK | 1);
 
-		/* Check that the address is 32-byte aligned. */
-		if (gpa_offset & (sizeof(struct pvclock_vcpu_time_info) - 1))
-			break;
-
 		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
-		     &vcpu->arch.pv_time, data & ~1ULL))
+		     &vcpu->arch.pv_time, data & ~1ULL,
+		     sizeof(struct pvclock_vcpu_time_info)))
 			vcpu->arch.pv_time_enabled = false;
 		else
 			vcpu->arch.pv_time_enabled = true;
@@ -1977,7 +1975,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 
 		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, &vcpu->arch.st.stime,
-							data & KVM_STEAL_VALID_BITS))
+						data & KVM_STEAL_VALID_BITS,
+						sizeof(struct kvm_steal_time)))
 			return 1;
 
 		vcpu->arch.st.msr_val = data;
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 1cbd89c..7114c63 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1334,6 +1334,7 @@ __init void lguest_init(void)
 	pv_mmu_ops.read_cr3 = lguest_read_cr3;
 	pv_mmu_ops.lazy_mode.enter = paravirt_enter_lazy_mmu;
 	pv_mmu_ops.lazy_mode.leave = lguest_leave_lazy_mmu_mode;
+	pv_mmu_ops.lazy_mode.flush = paravirt_flush_lazy_mmu;
 	pv_mmu_ops.pte_update = lguest_pte_update;
 	pv_mmu_ops.pte_update_defer = lguest_pte_update;
 
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 2b97525..0e88336 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -378,10 +378,12 @@ static noinline __kprobes int vmalloc_fault(unsigned long address)
 	if (pgd_none(*pgd_ref))
 		return -1;
 
-	if (pgd_none(*pgd))
+	if (pgd_none(*pgd)) {
 		set_pgd(pgd, *pgd_ref);
-	else
+		arch_flush_lazy_mmu_mode();
+	} else {
 		BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+	}
 
 	/*
 	 * Below here mismatches are bugs because these lower tables
diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c
index b008656..0e38951 100644
--- a/arch/x86/mm/pageattr-test.c
+++ b/arch/x86/mm/pageattr-test.c
@@ -68,7 +68,7 @@ static int print_split(struct split_state *s)
 			s->gpg++;
 			i += GPS/PAGE_SIZE;
 		} else if (level == PG_LEVEL_2M) {
-			if (!(pte_val(*pte) & _PAGE_PSE)) {
+			if ((pte_val(*pte) & _PAGE_PRESENT) && !(pte_val(*pte) & _PAGE_PSE)) {
 				printk(KERN_ERR
 					"%lx level %d but not PSE %Lx\n",
 					addr, level, (u64)pte_val(*pte));
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 091934e..fb4e73e 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -467,7 +467,7 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	 * We are safe now. Check whether the new pgprot is the same:
 	 */
 	old_pte = *kpte;
-	old_prot = new_prot = req_prot = pte_pgprot(old_pte);
+	old_prot = req_prot = pte_pgprot(old_pte);
 
 	pgprot_val(req_prot) &= ~pgprot_val(cpa->mask_clr);
 	pgprot_val(req_prot) |= pgprot_val(cpa->mask_set);
@@ -478,12 +478,12 @@ try_preserve_large_page(pte_t *kpte, unsigned long address,
 	 * a non present pmd. The canon_pgprot will clear _PAGE_GLOBAL
 	 * for the ancient hardware that doesn't support it.
 	 */
-	if (pgprot_val(new_prot) & _PAGE_PRESENT)
-		pgprot_val(new_prot) |= _PAGE_PSE | _PAGE_GLOBAL;
+	if (pgprot_val(req_prot) & _PAGE_PRESENT)
+		pgprot_val(req_prot) |= _PAGE_PSE | _PAGE_GLOBAL;
 	else
-		pgprot_val(new_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL);
+		pgprot_val(req_prot) &= ~(_PAGE_PSE | _PAGE_GLOBAL);
 
-	new_prot = canon_pgprot(new_prot);
+	req_prot = canon_pgprot(req_prot);
 
 	/*
 	 * old_pte points to the large page base address. So we need
@@ -1413,6 +1413,8 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
 	 * but that can deadlock->flush only current cpu:
 	 */
 	__flush_tlb_all();
+
+	arch_flush_lazy_mmu_mode();
 }
 
 #ifdef CONFIG_HIBERNATION
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 193350b..17fda6a 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -58,6 +58,13 @@ void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte)
 void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd)
 {
 	paravirt_release_pmd(__pa(pmd) >> PAGE_SHIFT);
+	/*
+	 * NOTE! For PAE, any changes to the top page-directory-pointer-table
+	 * entries need a full cr3 reload to flush.
+	 */
+#ifdef CONFIG_X86_PAE
+	tlb->need_flush_all = 1;
+#endif
 	tlb_remove_page(tlb, virt_to_page(pmd));
 }
 
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index fff986d..012b3f6 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -41,6 +41,7 @@
 #include <linux/io.h>
 #include <linux/reboot.h>
 #include <linux/bcd.h>
+#include <linux/ucs2_string.h>
 
 #include <asm/setup.h>
 #include <asm/efi.h>
@@ -51,6 +52,13 @@
 
 #define EFI_DEBUG	1
 
+/*
+ * There's some additional metadata associated with each
+ * variable. Intel's reference implementation is 60 bytes - bump that
+ * to account for potential alignment constraints
+ */
+#define VAR_METADATA_SIZE 64
+
 struct efi __read_mostly efi = {
 	.mps        = EFI_INVALID_TABLE_ADDR,
 	.acpi       = EFI_INVALID_TABLE_ADDR,
@@ -69,6 +77,13 @@ struct efi_memory_map memmap;
 static struct efi efi_phys __initdata;
 static efi_system_table_t efi_systab __initdata;
 
+static u64 efi_var_store_size;
+static u64 efi_var_remaining_size;
+static u64 efi_var_max_var_size;
+static u64 boot_used_size;
+static u64 boot_var_size;
+static u64 active_size;
+
 unsigned long x86_efi_facility;
 
 /*
@@ -98,6 +113,15 @@ static int __init setup_add_efi_memmap(char *arg)
 }
 early_param("add_efi_memmap", setup_add_efi_memmap);
 
+static bool efi_no_storage_paranoia;
+
+static int __init setup_storage_paranoia(char *arg)
+{
+	efi_no_storage_paranoia = true;
+	return 0;
+}
+early_param("efi_no_storage_paranoia", setup_storage_paranoia);
+
 
 static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
@@ -162,8 +186,53 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
 					       efi_char16_t *name,
 					       efi_guid_t *vendor)
 {
-	return efi_call_virt3(get_next_variable,
-			      name_size, name, vendor);
+	efi_status_t status;
+	static bool finished = false;
+	static u64 var_size;
+
+	status = efi_call_virt3(get_next_variable,
+				name_size, name, vendor);
+
+	if (status == EFI_NOT_FOUND) {
+		finished = true;
+		if (var_size < boot_used_size) {
+			boot_var_size = boot_used_size - var_size;
+			active_size += boot_var_size;
+		} else {
+			printk(KERN_WARNING FW_BUG  "efi: Inconsistent initial sizes\n");
+		}
+	}
+
+	if (boot_used_size && !finished) {
+		unsigned long size;
+		u32 attr;
+		efi_status_t s;
+		void *tmp;
+
+		s = virt_efi_get_variable(name, vendor, &attr, &size, NULL);
+
+		if (s != EFI_BUFFER_TOO_SMALL || !size)
+			return status;
+
+		tmp = kmalloc(size, GFP_ATOMIC);
+
+		if (!tmp)
+			return status;
+
+		s = virt_efi_get_variable(name, vendor, &attr, &size, tmp);
+
+		if (s == EFI_SUCCESS && (attr & EFI_VARIABLE_NON_VOLATILE)) {
+			var_size += size;
+			var_size += ucs2_strsize(name, 1024);
+			active_size += size;
+			active_size += VAR_METADATA_SIZE;
+			active_size += ucs2_strsize(name, 1024);
+		}
+
+		kfree(tmp);
+	}
+
+	return status;
 }
 
 static efi_status_t virt_efi_set_variable(efi_char16_t *name,
@@ -172,9 +241,34 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name,
 					  unsigned long data_size,
 					  void *data)
 {
-	return efi_call_virt5(set_variable,
-			      name, vendor, attr,
-			      data_size, data);
+	efi_status_t status;
+	u32 orig_attr = 0;
+	unsigned long orig_size = 0;
+
+	status = virt_efi_get_variable(name, vendor, &orig_attr, &orig_size,
+				       NULL);
+
+	if (status != EFI_BUFFER_TOO_SMALL)
+		orig_size = 0;
+
+	status = efi_call_virt5(set_variable,
+				name, vendor, attr,
+				data_size, data);
+
+	if (status == EFI_SUCCESS) {
+		if (orig_size) {
+			active_size -= orig_size;
+			active_size -= ucs2_strsize(name, 1024);
+			active_size -= VAR_METADATA_SIZE;
+		}
+		if (data_size) {
+			active_size += data_size;
+			active_size += ucs2_strsize(name, 1024);
+			active_size += VAR_METADATA_SIZE;
+		}
+	}
+
+	return status;
 }
 
 static efi_status_t virt_efi_query_variable_info(u32 attr,
@@ -683,6 +777,9 @@ void __init efi_init(void)
 	char vendor[100] = "unknown";
 	int i = 0;
 	void *tmp;
+	struct setup_data *data;
+	struct efi_var_bootdata *efi_var_data;
+	u64 pa_data;
 
 #ifdef CONFIG_X86_32
 	if (boot_params.efi_info.efi_systab_hi ||
@@ -700,6 +797,22 @@ void __init efi_init(void)
 	if (efi_systab_init(efi_phys.systab))
 		return;
 
+	pa_data = boot_params.hdr.setup_data;
+	while (pa_data) {
+		data = early_ioremap(pa_data, sizeof(*efi_var_data));
+		if (data->type == SETUP_EFI_VARS) {
+			efi_var_data = (struct efi_var_bootdata *)data;
+
+			efi_var_store_size = efi_var_data->store_size;
+			efi_var_remaining_size = efi_var_data->remaining_size;
+			efi_var_max_var_size = efi_var_data->max_var_size;
+		}
+		pa_data = data->next;
+		early_iounmap(data, sizeof(*efi_var_data));
+	}
+
+	boot_used_size = efi_var_store_size - efi_var_remaining_size;
+
 	set_bit(EFI_SYSTEM_TABLES, &x86_efi_facility);
 
 	/*
@@ -1000,3 +1113,48 @@ u64 efi_mem_attributes(unsigned long phys_addr)
 	}
 	return 0;
 }
+
+/*
+ * Some firmware has serious problems when using more than 50% of the EFI
+ * variable store, i.e. it triggers bugs that can brick machines. Ensure that
+ * we never use more than this safe limit.
+ *
+ * Return EFI_SUCCESS if it is safe to write 'size' bytes to the variable
+ * store.
+ */
+efi_status_t efi_query_variable_store(u32 attributes, unsigned long size)
+{
+	efi_status_t status;
+	u64 storage_size, remaining_size, max_size;
+
+	status = efi.query_variable_info(attributes, &storage_size,
+					 &remaining_size, &max_size);
+	if (status != EFI_SUCCESS)
+		return status;
+
+	if (!max_size && remaining_size > size)
+		printk_once(KERN_ERR FW_BUG "Broken EFI implementation"
+			    " is returning MaxVariableSize=0\n");
+	/*
+	 * Some firmware implementations refuse to boot if there's insufficient
+	 * space in the variable store. We account for that by refusing the
+	 * write if permitting it would reduce the available space to under
+	 * 50%. However, some firmware won't reclaim variable space until
+	 * after the used (not merely the actively used) space drops below
+	 * a threshold. We can approximate that case with the value calculated
+	 * above. If both the firmware and our calculations indicate that the
+	 * available space would drop below 50%, refuse the write.
+	 */
+
+	if (!storage_size || size > remaining_size ||
+	    (max_size && size > max_size))
+		return EFI_OUT_OF_RESOURCES;
+
+	if (!efi_no_storage_paranoia &&
+	    ((active_size + size + VAR_METADATA_SIZE > storage_size / 2) &&
+	     (remaining_size - size < storage_size / 2)))
+		return EFI_OUT_OF_RESOURCES;
+
+	return EFI_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(efi_query_variable_store);
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 6afbb2c..e006c18 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1748,14 +1748,18 @@ static void *m2v(phys_addr_t maddr)
 }
 
 /* Set the page permissions on an identity-mapped pages */
-static void set_page_prot(void *addr, pgprot_t prot)
+static void set_page_prot_flags(void *addr, pgprot_t prot, unsigned long flags)
 {
 	unsigned long pfn = __pa(addr) >> PAGE_SHIFT;
 	pte_t pte = pfn_pte(pfn, prot);
 
-	if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, 0))
+	if (HYPERVISOR_update_va_mapping((unsigned long)addr, pte, flags))
 		BUG();
 }
+static void set_page_prot(void *addr, pgprot_t prot)
+{
+	return set_page_prot_flags(addr, prot, UVMF_NONE);
+}
 #ifdef CONFIG_X86_32
 static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn)
 {
@@ -1839,12 +1843,12 @@ static void __init check_pt_base(unsigned long *pt_base, unsigned long *pt_end,
 				 unsigned long addr)
 {
 	if (*pt_base == PFN_DOWN(__pa(addr))) {
-		set_page_prot((void *)addr, PAGE_KERNEL);
+		set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG);
 		clear_page((void *)addr);
 		(*pt_base)++;
 	}
 	if (*pt_end == PFN_DOWN(__pa(addr))) {
-		set_page_prot((void *)addr, PAGE_KERNEL);
+		set_page_prot_flags((void *)addr, PAGE_KERNEL, UVMF_INVLPG);
 		clear_page((void *)addr);
 		(*pt_end)--;
 	}
@@ -2196,6 +2200,7 @@ static const struct pv_mmu_ops xen_mmu_ops __initconst = {
 	.lazy_mode = {
 		.enter = paravirt_enter_lazy_mmu,
 		.leave = xen_leave_lazy_mmu,
+		.flush = paravirt_flush_lazy_mmu,
 	},
 
 	.set_fixmap = xen_set_fixmap,