Merge branches 'acpi-pci' and 'pm-pci'

* acpi-pci:
  x86/PCI/ACPI: Fix regression caused by commit 4d6b4e69a245

* pm-pci:
  PCI / PM: Tune down retryable runtime suspend error messages

53 files changed, 911 insertions, 679 deletions

diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 3a45668f6dc3..94c18ebfd68c 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -32,6 +32,10 @@
 #include <asm/mpspec.h>
 #include <asm/realmode.h>
 
+#ifdef CONFIG_ACPI_APEI
+# include <asm/pgtable_types.h>
+#endif
+
 #ifdef CONFIG_ACPI
 extern int acpi_lapic;
 extern int acpi_ioapic;
@@ -147,4 +151,23 @@ extern int x86_acpi_numa_init(void);
 
 #define acpi_unlazy_tlb(x)	leave_mm(x)
 
+#ifdef CONFIG_ACPI_APEI
+static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
+{
+	/*
+	 * We currently have no way to look up the EFI memory map
+	 * attributes for a region in a consistent way, because the
+	 * memmap is discarded after efi_free_boot_services(). So if
+	 * you call efi_mem_attributes() during boot and at runtime,
+	 * you could theoretically see different attributes.
+	 *
+	 * Since we are yet to see any x86 platforms that require
+	 * anything other than PAGE_KERNEL (some arm64 platforms
+	 * require the equivalent of PAGE_KERNEL_NOCACHE), return that
+	 * until we know differently.
+	 */
+	 return PAGE_KERNEL;
+}
+#endif
+
 #endif /* _ASM_X86_ACPI_H */
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 1a5da2e63aee..3c56ef1ae068 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -81,7 +81,7 @@ static inline struct amd_northbridge *node_to_amd_nb(int node)
 	return (node < amd_northbridges.num) ? &amd_northbridges.nb[node] : NULL;
 }
 
-static inline u16 amd_get_node_id(struct pci_dev *pdev)
+static inline u16 amd_pci_dev_to_node_id(struct pci_dev *pdev)
 {
 	struct pci_dev *misc;
 	int i;
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index ebf6d5e5668c..a30316bf801a 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -115,6 +115,59 @@ static inline bool apic_is_x2apic_enabled(void)
 	return msr & X2APIC_ENABLE;
 }
 
+extern void enable_IR_x2apic(void);
+
+extern int get_physical_broadcast(void);
+
+extern int lapic_get_maxlvt(void);
+extern void clear_local_APIC(void);
+extern void disconnect_bsp_APIC(int virt_wire_setup);
+extern void disable_local_APIC(void);
+extern void lapic_shutdown(void);
+extern void sync_Arb_IDs(void);
+extern void init_bsp_APIC(void);
+extern void setup_local_APIC(void);
+extern void init_apic_mappings(void);
+void register_lapic_address(unsigned long address);
+extern void setup_boot_APIC_clock(void);
+extern void setup_secondary_APIC_clock(void);
+extern int APIC_init_uniprocessor(void);
+
+#ifdef CONFIG_X86_64
+static inline int apic_force_enable(unsigned long addr)
+{
+	return -1;
+}
+#else
+extern int apic_force_enable(unsigned long addr);
+#endif
+
+extern int apic_bsp_setup(bool upmode);
+extern void apic_ap_setup(void);
+
+/*
+ * On 32bit this is mach-xxx local
+ */
+#ifdef CONFIG_X86_64
+extern int apic_is_clustered_box(void);
+#else
+static inline int apic_is_clustered_box(void)
+{
+	return 0;
+}
+#endif
+
+extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask);
+
+#else /* !CONFIG_X86_LOCAL_APIC */
+static inline void lapic_shutdown(void) { }
+#define local_apic_timer_c2_ok		1
+static inline void init_apic_mappings(void) { }
+static inline void disable_local_APIC(void) { }
+# define setup_boot_APIC_clock x86_init_noop
+# define setup_secondary_APIC_clock x86_init_noop
+#endif /* !CONFIG_X86_LOCAL_APIC */
+
 #ifdef CONFIG_X86_X2APIC
 /*
  * Make previous memory operations globally visible before
@@ -186,67 +239,14 @@ static inline int x2apic_enabled(void)
 }
 
 #define x2apic_supported()	(cpu_has_x2apic)
-#else
+#else /* !CONFIG_X86_X2APIC */
 static inline void check_x2apic(void) { }
 static inline void x2apic_setup(void) { }
 static inline int x2apic_enabled(void) { return 0; }
 
 #define x2apic_mode		(0)
 #define	x2apic_supported()	(0)
-#endif
-
-extern void enable_IR_x2apic(void);
-
-extern int get_physical_broadcast(void);
-
-extern int lapic_get_maxlvt(void);
-extern void clear_local_APIC(void);
-extern void disconnect_bsp_APIC(int virt_wire_setup);
-extern void disable_local_APIC(void);
-extern void lapic_shutdown(void);
-extern void sync_Arb_IDs(void);
-extern void init_bsp_APIC(void);
-extern void setup_local_APIC(void);
-extern void init_apic_mappings(void);
-void register_lapic_address(unsigned long address);
-extern void setup_boot_APIC_clock(void);
-extern void setup_secondary_APIC_clock(void);
-extern int APIC_init_uniprocessor(void);
-
-#ifdef CONFIG_X86_64
-static inline int apic_force_enable(unsigned long addr)
-{
-	return -1;
-}
-#else
-extern int apic_force_enable(unsigned long addr);
-#endif
-
-extern int apic_bsp_setup(bool upmode);
-extern void apic_ap_setup(void);
-
-/*
- * On 32bit this is mach-xxx local
- */
-#ifdef CONFIG_X86_64
-extern int apic_is_clustered_box(void);
-#else
-static inline int apic_is_clustered_box(void)
-{
-	return 0;
-}
-#endif
-
-extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask);
-
-#else /* !CONFIG_X86_LOCAL_APIC */
-static inline void lapic_shutdown(void) { }
-#define local_apic_timer_c2_ok		1
-static inline void init_apic_mappings(void) { }
-static inline void disable_local_APIC(void) { }
-# define setup_boot_APIC_clock x86_init_noop
-# define setup_secondary_APIC_clock x86_init_noop
-#endif /* !CONFIG_X86_LOCAL_APIC */
+#endif /* !CONFIG_X86_X2APIC */
 
 #ifdef CONFIG_X86_64
 #define	SET_APIC_ID(x)		(apic->set_apic_id(x))
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index fb52aa644aab..ae5fb83e6d91 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -24,7 +24,7 @@
  */
 static __always_inline int atomic_read(const atomic_t *v)
 {
-	return ACCESS_ONCE((v)->counter);
+	return READ_ONCE((v)->counter);
 }
 
 /**
@@ -36,7 +36,7 @@ static __always_inline int atomic_read(const atomic_t *v)
  */
 static __always_inline void atomic_set(atomic_t *v, int i)
 {
-	v->counter = i;
+	WRITE_ONCE(v->counter, i);
 }
 
 /**
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 50e33eff58de..037351022f54 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -18,7 +18,7 @@
  */
 static inline long atomic64_read(const atomic64_t *v)
 {
-	return ACCESS_ONCE((v)->counter);
+	return READ_ONCE((v)->counter);
 }
 
 /**
@@ -30,7 +30,7 @@ static inline long atomic64_read(const atomic64_t *v)
  */
 static inline void atomic64_set(atomic64_t *v, long i)
 {
-	v->counter = i;
+	WRITE_ONCE(v->counter, i);
 }
 
 /**
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 9727b3b48bd1..e4f8010f22e0 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -12,7 +12,7 @@
 #include <asm/disabled-features.h>
 #endif
 
-#define NCAPINTS	13	/* N 32-bit words worth of info */
+#define NCAPINTS	14	/* N 32-bit words worth of info */
 #define NBUGINTS	1	/* N 32-bit bug flags */
 
 /*
@@ -255,6 +255,9 @@
 /* Intel-defined CPU QoS Sub-leaf, CPUID level 0x0000000F:1 (edx), word 12 */
 #define X86_FEATURE_CQM_OCCUP_LLC (12*32+ 0) /* LLC occupancy monitoring if 1 */
 
+/* AMD-defined CPU features, CPUID level 0x80000008 (ebx), word 13 */
+#define X86_FEATURE_CLZERO	(13*32+0) /* CLZERO instruction */
+
 /*
  * BUG word(s)
  */
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
new file mode 100644
index 000000000000..b7a1ab865d68
--- /dev/null
+++ b/arch/x86/include/asm/dwarf2.h
@@ -0,0 +1,84 @@
+#ifndef _ASM_X86_DWARF2_H
+#define _ASM_X86_DWARF2_H
+
+#ifndef __ASSEMBLY__
+#warning "asm/dwarf2.h should be only included in pure assembly files"
+#endif
+
+/*
+ * Macros for dwarf2 CFI unwind table entries.
+ * See "as.info" for details on these pseudo ops. Unfortunately
+ * they are only supported in very new binutils, so define them
+ * away for older version.
+ */
+
+#ifdef CONFIG_AS_CFI
+
+#define CFI_STARTPROC		.cfi_startproc
+#define CFI_ENDPROC		.cfi_endproc
+#define CFI_DEF_CFA		.cfi_def_cfa
+#define CFI_DEF_CFA_REGISTER	.cfi_def_cfa_register
+#define CFI_DEF_CFA_OFFSET	.cfi_def_cfa_offset
+#define CFI_ADJUST_CFA_OFFSET	.cfi_adjust_cfa_offset
+#define CFI_OFFSET		.cfi_offset
+#define CFI_REL_OFFSET		.cfi_rel_offset
+#define CFI_REGISTER		.cfi_register
+#define CFI_RESTORE		.cfi_restore
+#define CFI_REMEMBER_STATE	.cfi_remember_state
+#define CFI_RESTORE_STATE	.cfi_restore_state
+#define CFI_UNDEFINED		.cfi_undefined
+#define CFI_ESCAPE		.cfi_escape
+
+#ifdef CONFIG_AS_CFI_SIGNAL_FRAME
+#define CFI_SIGNAL_FRAME	.cfi_signal_frame
+#else
+#define CFI_SIGNAL_FRAME
+#endif
+
+#if defined(CONFIG_AS_CFI_SECTIONS) && defined(__ASSEMBLY__)
+#ifndef BUILD_VDSO
+	/*
+	 * Emit CFI data in .debug_frame sections, not .eh_frame sections.
+	 * The latter we currently just discard since we don't do DWARF
+	 * unwinding at runtime.  So only the offline DWARF information is
+	 * useful to anyone.  Note we should not use this directive if
+	 * vmlinux.lds.S gets changed so it doesn't discard .eh_frame.
+	 */
+	.cfi_sections .debug_frame
+#else
+	 /*
+	  * For the vDSO, emit both runtime unwind information and debug
+	  * symbols for the .dbg file.
+	  */
+	.cfi_sections .eh_frame, .debug_frame
+#endif
+#endif
+
+#else
+
+/*
+ * Due to the structure of pre-exisiting code, don't use assembler line
+ * comment character # to ignore the arguments. Instead, use a dummy macro.
+ */
+.macro cfi_ignore a=0, b=0, c=0, d=0
+.endm
+
+#define CFI_STARTPROC		cfi_ignore
+#define CFI_ENDPROC		cfi_ignore
+#define CFI_DEF_CFA		cfi_ignore
+#define CFI_DEF_CFA_REGISTER	cfi_ignore
+#define CFI_DEF_CFA_OFFSET	cfi_ignore
+#define CFI_ADJUST_CFA_OFFSET	cfi_ignore
+#define CFI_OFFSET		cfi_ignore
+#define CFI_REL_OFFSET		cfi_ignore
+#define CFI_REGISTER		cfi_ignore
+#define CFI_RESTORE		cfi_ignore
+#define CFI_REMEMBER_STATE	cfi_ignore
+#define CFI_RESTORE_STATE	cfi_ignore
+#define CFI_UNDEFINED		cfi_ignore
+#define CFI_ESCAPE		cfi_ignore
+#define CFI_SIGNAL_FRAME	cfi_ignore
+
+#endif
+
+#endif /* _ASM_X86_DWARF2_H */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index ae68be92f755..0010c78c4998 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -105,6 +105,7 @@ extern void __init efi_set_executable(efi_memory_desc_t *md, bool executable);
 extern int __init efi_memblock_x86_reserve_range(void);
 extern pgd_t * __init efi_call_phys_prolog(void);
 extern void __init efi_call_phys_epilog(pgd_t *save_pgd);
+extern void __init efi_print_memmap(void);
 extern void __init efi_unmap_memmap(void);
 extern void __init efi_memory_uc(u64 addr, unsigned long size);
 extern void __init efi_map_region(efi_memory_desc_t *md);
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 141c561f4664..1514753fd435 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -171,11 +171,11 @@ do {						\
 static inline void elf_common_init(struct thread_struct *t,
 				   struct pt_regs *regs, const u16 ds)
 {
-	/* Commented-out registers are cleared in stub_execve */
-	/*regs->ax = regs->bx =*/ regs->cx = regs->dx = 0;
-	regs->si = regs->di /*= regs->bp*/ = 0;
+	/* ax gets execve's return value. */
+	/*regs->ax = */ regs->bx = regs->cx = regs->dx = 0;
+	regs->si = regs->di = regs->bp = 0;
 	regs->r8 = regs->r9 = regs->r10 = regs->r11 = 0;
-	/*regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;*/
+	regs->r12 = regs->r13 = regs->r14 = regs->r15 = 0;
 	t->fs = t->gs = 0;
 	t->fsindex = t->gsindex = 0;
 	t->ds = t->es = ds;
@@ -328,7 +328,7 @@ else									\
 
 #define VDSO_ENTRY							\
 	((unsigned long)current->mm->context.vdso +			\
-	 selected_vdso32->sym___kernel_vsyscall)
+	 vdso_image_32.sym___kernel_vsyscall)
 
 struct linux_binprm;
 
diff --git a/arch/x86/include/asm/fpu/signal.h b/arch/x86/include/asm/fpu/signal.h
index 7358e9d61f1e..0e970d00dfcd 100644
--- a/arch/x86/include/asm/fpu/signal.h
+++ b/arch/x86/include/asm/fpu/signal.h
@@ -5,7 +5,7 @@
 #define _ASM_X86_FPU_SIGNAL_H
 
 #ifdef CONFIG_X86_64
-# include <asm/sigcontext32.h>
+# include <uapi/asm/sigcontext.h>
 # include <asm/user32.h>
 struct ksignal;
 int ia32_setup_rt_frame(int sig, struct ksignal *ksig,
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index c49c5173158e..1c6f6ac52ad0 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -95,63 +95,122 @@ struct swregs_state {
 /*
  * List of XSAVE features Linux knows about:
  */
-enum xfeature_bit {
-	XSTATE_BIT_FP,
-	XSTATE_BIT_SSE,
-	XSTATE_BIT_YMM,
-	XSTATE_BIT_BNDREGS,
-	XSTATE_BIT_BNDCSR,
-	XSTATE_BIT_OPMASK,
-	XSTATE_BIT_ZMM_Hi256,
-	XSTATE_BIT_Hi16_ZMM,
-
-	XFEATURES_NR_MAX,
+enum xfeature {
+	XFEATURE_FP,
+	XFEATURE_SSE,
+	/*
+	 * Values above here are "legacy states".
+	 * Those below are "extended states".
+	 */
+	XFEATURE_YMM,
+	XFEATURE_BNDREGS,
+	XFEATURE_BNDCSR,
+	XFEATURE_OPMASK,
+	XFEATURE_ZMM_Hi256,
+	XFEATURE_Hi16_ZMM,
+
+	XFEATURE_MAX,
 };
 
-#define XSTATE_FP		(1 << XSTATE_BIT_FP)
-#define XSTATE_SSE		(1 << XSTATE_BIT_SSE)
-#define XSTATE_YMM		(1 << XSTATE_BIT_YMM)
-#define XSTATE_BNDREGS		(1 << XSTATE_BIT_BNDREGS)
-#define XSTATE_BNDCSR		(1 << XSTATE_BIT_BNDCSR)
-#define XSTATE_OPMASK		(1 << XSTATE_BIT_OPMASK)
-#define XSTATE_ZMM_Hi256	(1 << XSTATE_BIT_ZMM_Hi256)
-#define XSTATE_Hi16_ZMM		(1 << XSTATE_BIT_Hi16_ZMM)
+#define XFEATURE_MASK_FP		(1 << XFEATURE_FP)
+#define XFEATURE_MASK_SSE		(1 << XFEATURE_SSE)
+#define XFEATURE_MASK_YMM		(1 << XFEATURE_YMM)
+#define XFEATURE_MASK_BNDREGS		(1 << XFEATURE_BNDREGS)
+#define XFEATURE_MASK_BNDCSR		(1 << XFEATURE_BNDCSR)
+#define XFEATURE_MASK_OPMASK		(1 << XFEATURE_OPMASK)
+#define XFEATURE_MASK_ZMM_Hi256		(1 << XFEATURE_ZMM_Hi256)
+#define XFEATURE_MASK_Hi16_ZMM		(1 << XFEATURE_Hi16_ZMM)
+
+#define XFEATURE_MASK_FPSSE		(XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
+#define XFEATURE_MASK_AVX512		(XFEATURE_MASK_OPMASK \
+					 | XFEATURE_MASK_ZMM_Hi256 \
+					 | XFEATURE_MASK_Hi16_ZMM)
+
+#define FIRST_EXTENDED_XFEATURE	XFEATURE_YMM
 
-#define XSTATE_FPSSE		(XSTATE_FP | XSTATE_SSE)
-#define XSTATE_AVX512		(XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
+struct reg_128_bit {
+	u8      regbytes[128/8];
+};
+struct reg_256_bit {
+	u8	regbytes[256/8];
+};
+struct reg_512_bit {
+	u8	regbytes[512/8];
+};
 
 /*
+ * State component 2:
+ *
  * There are 16x 256-bit AVX registers named YMM0-YMM15.
  * The low 128 bits are aliased to the 16 SSE registers (XMM0-XMM15)
- * and are stored in 'struct fxregs_state::xmm_space[]'.
+ * and are stored in 'struct fxregs_state::xmm_space[]' in the
+ * "legacy" area.
  *
- * The high 128 bits are stored here:
- *    16x 128 bits == 256 bytes.
+ * The high 128 bits are stored here.
  */
 struct ymmh_struct {
-	u8				ymmh_space[256];
-};
-
-/* We don't support LWP yet: */
-struct lwp_struct {
-	u8				reserved[128];
-};
+	struct reg_128_bit              hi_ymm[16];
+} __packed;
 
 /* Intel MPX support: */
-struct bndreg {
+
+struct mpx_bndreg {
 	u64				lower_bound;
 	u64				upper_bound;
 } __packed;
+/*
+ * State component 3 is used for the 4 128-bit bounds registers
+ */
+struct mpx_bndreg_state {
+	struct mpx_bndreg		bndreg[4];
+} __packed;
 
-struct bndcsr {
+/*
+ * State component 4 is used for the 64-bit user-mode MPX
+ * configuration register BNDCFGU and the 64-bit MPX status
+ * register BNDSTATUS.  We call the pair "BNDCSR".
+ */
+struct mpx_bndcsr {
 	u64				bndcfgu;
 	u64				bndstatus;
 } __packed;
 
-struct mpx_struct {
-	struct bndreg			bndreg[4];
-	struct bndcsr			bndcsr;
-};
+/*
+ * The BNDCSR state is padded out to be 64-bytes in size.
+ */
+struct mpx_bndcsr_state {
+	union {
+		struct mpx_bndcsr		bndcsr;
+		u8				pad_to_64_bytes[64];
+	};
+} __packed;
+
+/* AVX-512 Components: */
+
+/*
+ * State component 5 is used for the 8 64-bit opmask registers
+ * k0-k7 (opmask state).
+ */
+struct avx_512_opmask_state {
+	u64				opmask_reg[8];
+} __packed;
+
+/*
+ * State component 6 is used for the upper 256 bits of the
+ * registers ZMM0-ZMM15. These 16 256-bit values are denoted
+ * ZMM0_H-ZMM15_H (ZMM_Hi256 state).
+ */
+struct avx_512_zmm_uppers_state {
+	struct reg_256_bit		zmm_upper[16];
+} __packed;
+
+/*
+ * State component 7 is used for the 16 512-bit registers
+ * ZMM16-ZMM31 (Hi16_ZMM state).
+ */
+struct avx_512_hi16_state {
+	struct reg_512_bit		hi16_zmm[16];
+} __packed;
 
 struct xstate_header {
 	u64				xfeatures;
@@ -159,22 +218,19 @@ struct xstate_header {
 	u64				reserved[6];
 } __attribute__((packed));
 
-/* New processor state extensions should be added here: */
-#define XSTATE_RESERVE			(sizeof(struct ymmh_struct) + \
-					 sizeof(struct lwp_struct)  + \
-					 sizeof(struct mpx_struct)  )
 /*
  * This is our most modern FPU state format, as saved by the XSAVE
  * and restored by the XRSTOR instructions.
  *
  * It consists of a legacy fxregs portion, an xstate header and
- * subsequent fixed size areas as defined by the xstate header.
- * Not all CPUs support all the extensions.
+ * subsequent areas as defined by the xstate header.  Not all CPUs
+ * support all the extensions, so the size of the extended area
+ * can vary quite a bit between CPUs.
  */
 struct xregs_state {
 	struct fxregs_state		i387;
 	struct xstate_header		header;
-	u8				__reserved[XSTATE_RESERVE];
+	u8				extended_state_area[0];
 } __attribute__ ((packed, aligned (64)));
 
 /*
@@ -182,7 +238,9 @@ struct xregs_state {
  * put together, so that we can pick the right one runtime.
  *
  * The size of the structure is determined by the largest
- * member - which is the xsave area:
+ * member - which is the xsave area.  The padding is there
+ * to ensure that statically-allocated task_structs (just
+ * the init_task today) have enough space.
  */
 union fpregs_state {
 	struct fregs_state		fsave;
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 4656b25bb9a7..3a6c89b70307 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -6,7 +6,7 @@
 #include <linux/uaccess.h>
 
 /* Bit 63 of XCR0 is reserved for future expansion */
-#define XSTATE_EXTEND_MASK	(~(XSTATE_FPSSE | (1ULL << 63)))
+#define XFEATURE_MASK_EXTEND	(~(XFEATURE_MASK_FPSSE | (1ULL << 63)))
 
 #define XSTATE_CPUID		0x0000000d
 
@@ -19,14 +19,18 @@
 #define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
 
 /* Supported features which support lazy state saving */
-#define XSTATE_LAZY	(XSTATE_FP | XSTATE_SSE | XSTATE_YMM		      \
-			| XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM)
+#define XFEATURE_MASK_LAZY	(XFEATURE_MASK_FP | \
+				 XFEATURE_MASK_SSE | \
+				 XFEATURE_MASK_YMM | \
+				 XFEATURE_MASK_OPMASK |	\
+				 XFEATURE_MASK_ZMM_Hi256 | \
+				 XFEATURE_MASK_Hi16_ZMM)
 
 /* Supported features which require eager state saving */
-#define XSTATE_EAGER	(XSTATE_BNDREGS | XSTATE_BNDCSR)
+#define XFEATURE_MASK_EAGER	(XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)
 
 /* All currently supported features */
-#define XCNTXT_MASK	(XSTATE_LAZY | XSTATE_EAGER)
+#define XCNTXT_MASK	(XFEATURE_MASK_LAZY | XFEATURE_MASK_EAGER)
 
 #ifdef CONFIG_X86_64
 #define REX_PREFIX	"0x48, "
@@ -40,6 +44,7 @@ extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 
 extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
 
+void fpu__xstate_clear_all_cpu_caps(void);
 void *get_xsave_addr(struct xregs_state *xsave, int xstate);
 const void *get_xsave_field_ptr(int xstate_field);
 
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index 04e9d023168f..1c0b43724ce3 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -68,7 +68,6 @@ void *kmap_atomic(struct page *page);
 void __kunmap_atomic(void *kvaddr);
 void *kmap_atomic_pfn(unsigned long pfn);
 void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot);
-struct page *kmap_atomic_to_page(void *ptr);
 
 #define flush_cache_kmaps()	do { } while (0)
 
diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 5fa9fb0f8809..cc285ec4b2c1 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -63,10 +63,10 @@
 /* hpet memory map physical address */
 extern unsigned long hpet_address;
 extern unsigned long force_hpet_address;
-extern int boot_hpet_disable;
+extern bool boot_hpet_disable;
 extern u8 hpet_blockid;
-extern int hpet_force_user;
-extern u8 hpet_msi_disable;
+extern bool hpet_force_user;
+extern bool hpet_msi_disable;
 extern int is_hpet_enabled(void);
 extern int hpet_enable(void);
 extern void hpet_disable(void);
diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index ccffa53750a8..39bcefc20de7 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -60,6 +60,7 @@ struct legacy_pic {
 	void (*mask_all)(void);
 	void (*restore_mask)(void);
 	void (*init)(int auto_eoi);
+	int (*probe)(void);
 	int (*irq_pending)(unsigned int irq);
 	void (*make_irq)(unsigned int irq);
 };
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index 28019765442e..a9bdf5569ab3 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -10,7 +10,7 @@
  * 32 bit structures for IA32 support.
  */
 
-#include <asm/sigcontext32.h>
+#include <uapi/asm/sigcontext.h>
 
 /* signal.h */
 
@@ -18,7 +18,7 @@ struct ucontext_ia32 {
 	unsigned int	  uc_flags;
 	unsigned int 	  uc_link;
 	compat_stack_t	  uc_stack;
-	struct sigcontext_ia32 uc_mcontext;
+	struct sigcontext_32 uc_mcontext;
 	compat_sigset_t	  uc_sigmask;	/* mask last for extensibility */
 };
 
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 046c7fb1ca43..a210eba2727c 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -33,6 +33,11 @@ enum irq_remap_cap {
 	IRQ_POSTING_CAP = 0,
 };
 
+struct vcpu_data {
+	u64 pi_desc_addr;	/* Physical address of PI Descriptor */
+	u32 vector;		/* Guest vector of the interrupt */
+};
+
 #ifdef CONFIG_IRQ_REMAP
 
 extern bool irq_remapping_cap(enum irq_remap_cap cap);
@@ -58,11 +63,6 @@ static inline struct irq_domain *arch_get_ir_parent_domain(void)
 	return x86_vector_domain;
 }
 
-struct vcpu_data {
-	u64 pi_desc_addr;	/* Physical address of PI Descriptor */
-	u32 vector;		/* Guest vector of the interrupt */
-};
-
 #else  /* CONFIG_IRQ_REMAP */
 
 static inline bool irq_remapping_cap(enum irq_remap_cap cap) { return 0; }
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index b130d59406fb..e5f5dc9787d5 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -29,11 +29,5 @@ extern void show_trace(struct task_struct *t, struct pt_regs *regs,
 extern void __show_regs(struct pt_regs *regs, int all);
 extern unsigned long oops_begin(void);
 extern void oops_end(unsigned long, struct pt_regs *, int signr);
-#ifdef CONFIG_KEXEC_CORE
-extern int in_crash_kexec;
-#else
-/* no crash dump is ever in progress if no crash kernel can be kexec'd */
-#define in_crash_kexec 0
-#endif
 
 #endif /* _ASM_X86_KDEBUG_H */
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index e16466ec473c..e9cd7befcb76 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -112,6 +112,16 @@ struct x86_emulate_ops {
 			struct x86_exception *fault);
 
 	/*
+	 * read_phys: Read bytes of standard (non-emulated/special) memory.
+	 *            Used for descriptor reading.
+	 *  @addr:  [IN ] Physical address from which to read.
+	 *  @val:   [OUT] Value read from memory.
+	 *  @bytes: [IN ] Number of bytes to read from memory.
+	 */
+	int (*read_phys)(struct x86_emulate_ctxt *ctxt, unsigned long addr,
+			void *val, unsigned int bytes);
+
+	/*
 	 * write_std: Write bytes of standard (non-emulated/special) memory.
 	 *            Used for descriptor writing.
 	 *  @addr:  [IN ] Linear address to which to write.
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 2beee0382088..30cfd64295a0 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -24,6 +24,7 @@
 #include <linux/perf_event.h>
 #include <linux/pvclock_gtod.h>
 #include <linux/clocksource.h>
+#include <linux/irqbypass.h>
 
 #include <asm/pvclock-abi.h>
 #include <asm/desc.h>
@@ -176,6 +177,8 @@ enum {
  */
 #define KVM_APIC_PV_EOI_PENDING	1
 
+struct kvm_kernel_irq_routing_entry;
+
 /*
  * We don't want allocation failures within the mmu code, so we preallocate
  * enough memory for a single page fault in a cache.
@@ -374,6 +377,7 @@ struct kvm_mtrr {
 /* Hyper-V per vcpu emulation context */
 struct kvm_vcpu_hv {
 	u64 hv_vapic;
+	s64 runtime_offset;
 };
 
 struct kvm_vcpu_arch {
@@ -396,6 +400,7 @@ struct kvm_vcpu_arch {
 	u64 efer;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
+	u64 eoi_exit_bitmap[4];
 	unsigned long apic_attention;
 	int32_t apic_arb_prio;
 	int mp_state;
@@ -500,6 +505,7 @@ struct kvm_vcpu_arch {
 	u32 virtual_tsc_mult;
 	u32 virtual_tsc_khz;
 	s64 ia32_tsc_adjust_msr;
+	u64 tsc_scaling_ratio;
 
 	atomic_t nmi_queued;  /* unprocessed asynchronous NMIs */
 	unsigned nmi_pending; /* NMI queued after currently running handler */
@@ -573,6 +579,9 @@ struct kvm_vcpu_arch {
 	struct {
 		bool pv_unhalted;
 	} pv;
+
+	int pending_ioapic_eoi;
+	int pending_external_vector;
 };
 
 struct kvm_lpage_info {
@@ -683,6 +692,9 @@ struct kvm_arch {
 	u32 bsp_vcpu_id;
 
 	u64 disabled_quirks;
+
+	bool irqchip_split;
+	u8 nr_reserved_ioapic_pins;
 };
 
 struct kvm_vm_stat {
@@ -766,7 +778,7 @@ struct kvm_x86_ops {
 	void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
 	void (*vcpu_put)(struct kvm_vcpu *vcpu);
 
-	void (*update_db_bp_intercept)(struct kvm_vcpu *vcpu);
+	void (*update_bp_intercept)(struct kvm_vcpu *vcpu);
 	int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
 	int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
 	u64 (*get_segment_base)(struct kvm_vcpu *vcpu, int seg);
@@ -819,10 +831,10 @@ struct kvm_x86_ops {
 	void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
 	void (*enable_irq_window)(struct kvm_vcpu *vcpu);
 	void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
-	int (*vm_has_apicv)(struct kvm *kvm);
+	int (*cpu_uses_apicv)(struct kvm_vcpu *vcpu);
 	void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
 	void (*hwapic_isr_update)(struct kvm *kvm, int isr);
-	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
+	void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu);
 	void (*set_virtual_x2apic_mode)(struct kvm_vcpu *vcpu, bool set);
 	void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu, hpa_t hpa);
 	void (*deliver_posted_interrupt)(struct kvm_vcpu *vcpu, int vector);
@@ -833,7 +845,7 @@ struct kvm_x86_ops {
 	int (*get_lpage_level)(void);
 	bool (*rdtscp_supported)(void);
 	bool (*invpcid_supported)(void);
-	void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment, bool host);
+	void (*adjust_tsc_offset_guest)(struct kvm_vcpu *vcpu, s64 adjustment);
 
 	void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
 
@@ -841,11 +853,9 @@ struct kvm_x86_ops {
 
 	bool (*has_wbinvd_exit)(void);
 
-	void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale);
 	u64 (*read_tsc_offset)(struct kvm_vcpu *vcpu);
 	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
 
-	u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc);
 	u64 (*read_l1_tsc)(struct kvm_vcpu *vcpu, u64 host_tsc);
 
 	void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
@@ -887,6 +897,20 @@ struct kvm_x86_ops {
 					   gfn_t offset, unsigned long mask);
 	/* pmu operations of sub-arch */
 	const struct kvm_pmu_ops *pmu_ops;
+
+	/*
+	 * Architecture specific hooks for vCPU blocking due to
+	 * HLT instruction.
+	 * Returns for .pre_block():
+	 *    - 0 means continue to block the vCPU.
+	 *    - 1 means we cannot block the vCPU since some event
+	 *        happens during this period, such as, 'ON' bit in
+	 *        posted-interrupts descriptor is set.
+	 */
+	int (*pre_block)(struct kvm_vcpu *vcpu);
+	void (*post_block)(struct kvm_vcpu *vcpu);
+	int (*update_pi_irte)(struct kvm *kvm, unsigned int host_irq,
+			      uint32_t guest_irq, bool set);
 };
 
 struct kvm_arch_async_pf {
@@ -898,17 +922,6 @@ struct kvm_arch_async_pf {
 
 extern struct kvm_x86_ops *kvm_x86_ops;
 
-static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
-					   s64 adjustment)
-{
-	kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, false);
-}
-
-static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)
-{
-	kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, true);
-}
-
 int kvm_mmu_module_init(void);
 void kvm_mmu_module_exit(void);
 
@@ -961,10 +974,12 @@ u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu);
 
 /* control of guest tsc rate supported? */
 extern bool kvm_has_tsc_control;
-/* minimum supported tsc_khz for guests */
-extern u32  kvm_min_guest_tsc_khz;
 /* maximum supported tsc_khz for guests */
 extern u32  kvm_max_guest_tsc_khz;
+/* number of bits of the fractional part of the TSC scaling ratio */
+extern u8   kvm_tsc_scaling_ratio_frac_bits;
+/* maximum allowed value of TSC scaling ratio */
+extern u64  kvm_max_tsc_scaling_ratio;
 
 enum emulation_result {
 	EMULATE_DONE,         /* no further processing */
@@ -1210,6 +1225,9 @@ void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
 void kvm_define_shared_msr(unsigned index, u32 msr);
 int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
 
+u64 kvm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc);
+u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc);
+
 unsigned long kvm_get_linear_rip(struct kvm_vcpu *vcpu);
 bool kvm_is_linear_rip(struct kvm_vcpu *vcpu, unsigned long linear_rip);
 
@@ -1226,11 +1244,18 @@ void kvm_complete_insn_gp(struct kvm_vcpu *vcpu, int err);
 
 int kvm_is_in_guest(void);
 
-int __x86_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem);
-int x86_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem);
+int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
+int x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
 bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
 bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
 
+bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq,
+			     struct kvm_vcpu **dest_vcpu);
+
+void kvm_set_msi_irq(struct kvm_kernel_irq_routing_entry *e,
+		     struct kvm_lapic_irq *irq);
+
+static inline void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu) {}
+static inline void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu) {}
+
 #endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 2dbc0bf2b9f3..2ea4527e462f 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -123,19 +123,27 @@ struct mca_config {
 };
 
 struct mce_vendor_flags {
-			/*
-			 * overflow recovery cpuid bit indicates that overflow
-			 * conditions are not fatal
-			 */
-	__u64		overflow_recov	: 1,
-
-			/*
-			 * SUCCOR stands for S/W UnCorrectable error COntainment
-			 * and Recovery. It indicates support for data poisoning
-			 * in HW and deferred error interrupts.
-			 */
-			succor		: 1,
-			__reserved_0	: 62;
+	/*
+	 * Indicates that overflow conditions are not fatal, when set.
+	 */
+	__u64 overflow_recov	: 1,
+
+	/*
+	 * (AMD) SUCCOR stands for S/W UnCorrectable error COntainment and
+	 * Recovery. It indicates support for data poisoning in HW and deferred
+	 * error interrupts.
+	 */
+	      succor		: 1,
+
+	/*
+	 * (AMD) SMCA: This bit indicates support for Scalable MCA which expands
+	 * the register space for each MCA bank and also increases number of
+	 * banks. Also, to accommodate the new banks and registers, the MCA
+	 * register space is moved to a new MSR range.
+	 */
+	      smca		: 1,
+
+	      __reserved_0	: 61;
 };
 extern struct mce_vendor_flags mce_flags;
 
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index 9e6278c7140e..34e62b1dcfce 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -27,7 +27,6 @@ struct cpu_signature {
 struct device;
 
 enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND };
-extern bool dis_ucode_ldr;
 
 struct microcode_ops {
 	enum ucode_state (*request_microcode_user) (int cpu,
@@ -55,6 +54,12 @@ struct ucode_cpu_info {
 };
 extern struct ucode_cpu_info ucode_cpu_info[];
 
+#ifdef CONFIG_MICROCODE
+int __init microcode_init(void);
+#else
+static inline int __init microcode_init(void)	{ return 0; };
+#endif
+
 #ifdef CONFIG_MICROCODE_INTEL
 extern struct microcode_ops * __init init_intel_microcode(void);
 #else
@@ -75,7 +80,6 @@ static inline struct microcode_ops * __init init_amd_microcode(void)
 static inline void __exit exit_amd_microcode(void) {}
 #endif
 
-#ifdef CONFIG_MICROCODE_EARLY
 #define MAX_UCODE_COUNT 128
 
 #define QCHAR(a, b, c, d) ((a) + ((b) << 8) + ((c) << 16) + ((d) << 24))
@@ -150,22 +154,18 @@ static inline unsigned int x86_model(unsigned int sig)
 	return model;
 }
 
+#ifdef CONFIG_MICROCODE
 extern void __init load_ucode_bsp(void);
 extern void load_ucode_ap(void);
 extern int __init save_microcode_in_initrd(void);
 void reload_early_microcode(void);
 extern bool get_builtin_firmware(struct cpio_data *cd, const char *name);
 #else
-static inline void __init load_ucode_bsp(void) {}
-static inline void load_ucode_ap(void) {}
-static inline int __init save_microcode_in_initrd(void)
-{
-	return 0;
-}
-static inline void reload_early_microcode(void) {}
-static inline bool get_builtin_firmware(struct cpio_data *cd, const char *name)
-{
-	return false;
-}
+static inline void __init load_ucode_bsp(void)			{ }
+static inline void load_ucode_ap(void)				{ }
+static inline int __init save_microcode_in_initrd(void)		{ return 0; }
+static inline void reload_early_microcode(void)			{ }
+static inline bool
+get_builtin_firmware(struct cpio_data *cd, const char *name)	{ return false; }
 #endif
 #endif /* _ASM_X86_MICROCODE_H */
diff --git a/arch/x86/include/asm/microcode_amd.h b/arch/x86/include/asm/microcode_amd.h
index ac6d328977a6..adfc847a395e 100644
--- a/arch/x86/include/asm/microcode_amd.h
+++ b/arch/x86/include/asm/microcode_amd.h
@@ -64,7 +64,7 @@ extern enum ucode_state load_microcode_amd(int cpu, u8 family, const u8 *data, s
 #define PATCH_MAX_SIZE PAGE_SIZE
 extern u8 amd_ucode_patch[PATCH_MAX_SIZE];
 
-#ifdef CONFIG_MICROCODE_AMD_EARLY
+#ifdef CONFIG_MICROCODE_AMD
 extern void __init load_ucode_amd_bsp(unsigned int family);
 extern void load_ucode_amd_ap(void);
 extern int __init save_microcode_in_initrd_amd(void);
@@ -76,4 +76,5 @@ static inline int __init save_microcode_in_initrd_amd(void) { return -EINVAL; }
 void reload_ucode_amd(void) {}
 #endif
 
+extern bool check_current_patch_level(u32 *rev, bool early);
 #endif /* _ASM_X86_MICROCODE_AMD_H */
diff --git a/arch/x86/include/asm/microcode_intel.h b/arch/x86/include/asm/microcode_intel.h
index 7991c606125d..8559b0102ea1 100644
--- a/arch/x86/include/asm/microcode_intel.h
+++ b/arch/x86/include/asm/microcode_intel.h
@@ -57,7 +57,7 @@ extern int has_newer_microcode(void *mc, unsigned int csig, int cpf, int rev);
 extern int microcode_sanity_check(void *mc, int print_err);
 extern int find_matching_signature(void *mc, unsigned int csig, int cpf);
 
-#ifdef CONFIG_MICROCODE_INTEL_EARLY
+#ifdef CONFIG_MICROCODE_INTEL
 extern void __init load_ucode_intel_bsp(void);
 extern void load_ucode_intel_ap(void);
 extern void show_ucode_info_early(void);
@@ -71,13 +71,9 @@ static inline int __init save_microcode_in_initrd_intel(void) { return -EINVAL;
 static inline void reload_ucode_intel(void) {}
 #endif
 
-#if defined(CONFIG_MICROCODE_INTEL_EARLY) && defined(CONFIG_HOTPLUG_CPU)
+#ifdef CONFIG_HOTPLUG_CPU
 extern int save_mc_for_early(u8 *mc);
 #else
-static inline int save_mc_for_early(u8 *mc)
-{
-	return 0;
-}
+static inline int save_mc_for_early(u8 *mc) { return 0; }
 #endif
-
 #endif /* _ASM_X86_MICROCODE_INTEL_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index b8c14bb7fc8f..690b4027e17c 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -35,7 +35,7 @@
 #define MSR_IA32_PERFCTR0		0x000000c1
 #define MSR_IA32_PERFCTR1		0x000000c2
 #define MSR_FSB_FREQ			0x000000cd
-#define MSR_NHM_PLATFORM_INFO		0x000000ce
+#define MSR_PLATFORM_INFO		0x000000ce
 
 #define MSR_NHM_SNB_PKG_CST_CFG_CTL	0x000000e2
 #define NHM_C3_AUTO_DEMOTE		(1UL << 25)
@@ -44,7 +44,6 @@
 #define SNB_C1_AUTO_UNDEMOTE		(1UL << 27)
 #define SNB_C3_AUTO_UNDEMOTE		(1UL << 28)
 
-#define MSR_PLATFORM_INFO		0x000000ce
 #define MSR_MTRRcap			0x000000fe
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
@@ -206,6 +205,13 @@
 #define MSR_GFX_PERF_LIMIT_REASONS	0x000006B0
 #define MSR_RING_PERF_LIMIT_REASONS	0x000006B1
 
+/* Config TDP MSRs */
+#define MSR_CONFIG_TDP_NOMINAL		0x00000648
+#define MSR_CONFIG_TDP_LEVEL1		0x00000649
+#define MSR_CONFIG_TDP_LEVEL2		0x0000064A
+#define MSR_CONFIG_TDP_CONTROL		0x0000064B
+#define MSR_TURBO_ACTIVATION_RATIO	0x0000064C
+
 /* Hardware P state interface */
 #define MSR_PPERF			0x0000064e
 #define MSR_PERF_LIMIT_REASONS		0x0000064f
diff --git a/arch/x86/include/asm/numachip/numachip.h b/arch/x86/include/asm/numachip/numachip.h
index 1c6f7f6212c1..c64373a2d731 100644
--- a/arch/x86/include/asm/numachip/numachip.h
+++ b/arch/x86/include/asm/numachip/numachip.h
@@ -14,6 +14,7 @@
 #ifndef _ASM_X86_NUMACHIP_NUMACHIP_H
 #define _ASM_X86_NUMACHIP_NUMACHIP_H
 
+extern u8 numachip_system;
 extern int __init pci_numachip_init(void);
 
 #endif /* _ASM_X86_NUMACHIP_NUMACHIP_H */
diff --git a/arch/x86/include/asm/numachip/numachip_csr.h b/arch/x86/include/asm/numachip/numachip_csr.h
index 660f843df928..29719eecdc2e 100644
--- a/arch/x86/include/asm/numachip/numachip_csr.h
+++ b/arch/x86/include/asm/numachip/numachip_csr.h
@@ -14,12 +14,8 @@
 #ifndef _ASM_X86_NUMACHIP_NUMACHIP_CSR_H
 #define _ASM_X86_NUMACHIP_NUMACHIP_CSR_H
 
-#include <linux/numa.h>
-#include <linux/percpu.h>
+#include <linux/smp.h>
 #include <linux/io.h>
-#include <linux/swab.h>
-#include <asm/types.h>
-#include <asm/processor.h>
 
 #define CSR_NODE_SHIFT		16
 #define CSR_NODE_BITS(p)	(((unsigned long)(p)) << CSR_NODE_SHIFT)
@@ -27,11 +23,8 @@
 
 /* 32K CSR space, b15 indicates geo/non-geo */
 #define CSR_OFFSET_MASK	0x7fffUL
-
-/* Global CSR space covers all 4K possible nodes with 64K CSR space per node */
-#define NUMACHIP_GCSR_BASE	0x3fff00000000ULL
-#define NUMACHIP_GCSR_LIM	0x3fff0fffffffULL
-#define NUMACHIP_GCSR_SIZE	(NUMACHIP_GCSR_LIM - NUMACHIP_GCSR_BASE + 1)
+#define CSR_G0_NODE_IDS (0x008 + (0 << 12))
+#define CSR_G3_EXT_IRQ_GEN (0x030 + (3 << 12))
 
 /*
  * Local CSR space starts in global CSR space with "nodeid" = 0xfff0, however
@@ -41,12 +34,7 @@
 #define NUMACHIP_LCSR_BASE	0x3ffffe000000ULL
 #define NUMACHIP_LCSR_LIM	0x3fffffffffffULL
 #define NUMACHIP_LCSR_SIZE	(NUMACHIP_LCSR_LIM - NUMACHIP_LCSR_BASE + 1)
-
-static inline void *gcsr_address(int node, unsigned long offset)
-{
-	return __va(NUMACHIP_GCSR_BASE | (1UL << 15) |
-		CSR_NODE_BITS(node & CSR_NODE_MASK) | (offset & CSR_OFFSET_MASK));
-}
+#define NUMACHIP_LAPIC_BITS	8
 
 static inline void *lcsr_address(unsigned long offset)
 {
@@ -54,114 +42,57 @@ static inline void *lcsr_address(unsigned long offset)
 		CSR_NODE_BITS(0xfff0) | (offset & CSR_OFFSET_MASK));
 }
 
-static inline unsigned int read_gcsr(int node, unsigned long offset)
+static inline unsigned int read_lcsr(unsigned long offset)
 {
-	return swab32(readl(gcsr_address(node, offset)));
+	return swab32(readl(lcsr_address(offset)));
 }
 
-static inline void write_gcsr(int node, unsigned long offset, unsigned int val)
+static inline void write_lcsr(unsigned long offset, unsigned int val)
 {
-	writel(swab32(val), gcsr_address(node, offset));
+	writel(swab32(val), lcsr_address(offset));
 }
 
-static inline unsigned int read_lcsr(unsigned long offset)
+/*
+ * On NumaChip2, local CSR space is 16MB and starts at fixed offset below 4G
+ */
+
+#define NUMACHIP2_LCSR_BASE       0xf0000000UL
+#define NUMACHIP2_LCSR_SIZE       0x1000000UL
+#define NUMACHIP2_APIC_ICR        0x100000
+#define NUMACHIP2_TIMER_DEADLINE  0x200000
+#define NUMACHIP2_TIMER_INT       0x200008
+#define NUMACHIP2_TIMER_NOW       0x200018
+#define NUMACHIP2_TIMER_RESET     0x200020
+
+static inline void __iomem *numachip2_lcsr_address(unsigned long offset)
 {
-	return swab32(readl(lcsr_address(offset)));
+	return (void __iomem *)__va(NUMACHIP2_LCSR_BASE |
+		(offset & (NUMACHIP2_LCSR_SIZE - 1)));
 }
 
-static inline void write_lcsr(unsigned long offset, unsigned int val)
+static inline u32 numachip2_read32_lcsr(unsigned long offset)
 {
-	writel(swab32(val), lcsr_address(offset));
+	return readl(numachip2_lcsr_address(offset));
 }
 
-/* ========================================================================= */
-/*                   CSR_G0_STATE_CLEAR                                      */
-/* ========================================================================= */
-
-#define CSR_G0_STATE_CLEAR (0x000 + (0 << 12))
-union numachip_csr_g0_state_clear {
-	unsigned int v;
-	struct numachip_csr_g0_state_clear_s {
-		unsigned int _state:2;
-		unsigned int _rsvd_2_6:5;
-		unsigned int _lost:1;
-		unsigned int _rsvd_8_31:24;
-	} s;
-};
-
-/* ========================================================================= */
-/*                   CSR_G0_NODE_IDS                                         */
-/* ========================================================================= */
+static inline u64 numachip2_read64_lcsr(unsigned long offset)
+{
+	return readq(numachip2_lcsr_address(offset));
+}
 
-#define CSR_G0_NODE_IDS (0x008 + (0 << 12))
-union numachip_csr_g0_node_ids {
-	unsigned int v;
-	struct numachip_csr_g0_node_ids_s {
-		unsigned int _initialid:16;
-		unsigned int _nodeid:12;
-		unsigned int _rsvd_28_31:4;
-	} s;
-};
-
-/* ========================================================================= */
-/*                   CSR_G3_EXT_IRQ_GEN                                      */
-/* ========================================================================= */
+static inline void numachip2_write32_lcsr(unsigned long offset, u32 val)
+{
+	writel(val, numachip2_lcsr_address(offset));
+}
 
-#define CSR_G3_EXT_IRQ_GEN (0x030 + (3 << 12))
-union numachip_csr_g3_ext_irq_gen {
-	unsigned int v;
-	struct numachip_csr_g3_ext_irq_gen_s {
-		unsigned int _vector:8;
-		unsigned int _msgtype:3;
-		unsigned int _index:5;
-		unsigned int _destination_apic_id:16;
-	} s;
-};
-
-/* ========================================================================= */
-/*                   CSR_G3_EXT_IRQ_STATUS                                   */
-/* ========================================================================= */
-
-#define CSR_G3_EXT_IRQ_STATUS (0x034 + (3 << 12))
-union numachip_csr_g3_ext_irq_status {
-	unsigned int v;
-	struct numachip_csr_g3_ext_irq_status_s {
-		unsigned int _result:32;
-	} s;
-};
-
-/* ========================================================================= */
-/*                   CSR_G3_EXT_IRQ_DEST                                     */
-/* ========================================================================= */
-
-#define CSR_G3_EXT_IRQ_DEST (0x038 + (3 << 12))
-union numachip_csr_g3_ext_irq_dest {
-	unsigned int v;
-	struct numachip_csr_g3_ext_irq_dest_s {
-		unsigned int _irq:8;
-		unsigned int _rsvd_8_31:24;
-	} s;
-};
-
-/* ========================================================================= */
-/*                   CSR_G3_NC_ATT_MAP_SELECT                                */
-/* ========================================================================= */
-
-#define CSR_G3_NC_ATT_MAP_SELECT (0x7fc + (3 << 12))
-union numachip_csr_g3_nc_att_map_select {
-	unsigned int v;
-	struct numachip_csr_g3_nc_att_map_select_s {
-		unsigned int _upper_address_bits:4;
-		unsigned int _select_ram:4;
-		unsigned int _rsvd_8_31:24;
-	} s;
-};
-
-/* ========================================================================= */
-/*                   CSR_G3_NC_ATT_MAP_SELECT_0-255                          */
-/* ========================================================================= */
-
-#define CSR_G3_NC_ATT_MAP_SELECT_0 (0x800 + (3 << 12))
+static inline void numachip2_write64_lcsr(unsigned long offset, u64 val)
+{
+	writeq(val, numachip2_lcsr_address(offset));
+}
 
-#endif /* _ASM_X86_NUMACHIP_NUMACHIP_CSR_H */
+static inline unsigned int numachip2_timer(void)
+{
+	return (smp_processor_id() % 48) << 6;
+}
 
+#endif /* _ASM_X86_NUMACHIP_NUMACHIP_CSR_H */
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 4edd53b79a81..4928cf0d5af0 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -26,9 +26,6 @@
 #define MCE_STACK 4
 #define N_EXCEPTION_STACKS 4  /* hw limit: 7 */
 
-#define PUD_PAGE_SIZE		(_AC(1, UL) << PUD_SHIFT)
-#define PUD_PAGE_MASK		(~(PUD_PAGE_SIZE-1))
-
 /*
  * Set __PAGE_OFFSET to the most negative possible address +
  * PGDIR_SIZE*16 (pgd slot 272).  The gap is to allow a space for a
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index c7c712f2648b..c5b7fb2774d0 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -20,6 +20,9 @@
 #define PMD_PAGE_SIZE		(_AC(1, UL) << PMD_SHIFT)
 #define PMD_PAGE_MASK		(~(PMD_PAGE_SIZE-1))
 
+#define PUD_PAGE_SIZE		(_AC(1, UL) << PUD_SHIFT)
+#define PUD_PAGE_MASK		(~(PUD_PAGE_SIZE-1))
+
 #define HPAGE_SHIFT		PMD_SHIFT
 #define HPAGE_SIZE		(_AC(1,UL) << HPAGE_SHIFT)
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1))
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 867da5bbb4a3..6ec0c8b2e9df 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -19,6 +19,13 @@
 #include <asm/x86_init.h>
 
 void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
+void ptdump_walk_pgd_level_checkwx(void);
+
+#ifdef CONFIG_DEBUG_WX
+#define debug_checkwx() ptdump_walk_pgd_level_checkwx()
+#else
+#define debug_checkwx() do { } while (0)
+#endif
 
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
@@ -142,12 +149,12 @@ static inline unsigned long pte_pfn(pte_t pte)
 
 static inline unsigned long pmd_pfn(pmd_t pmd)
 {
-	return (pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT;
+	return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
 }
 
 static inline unsigned long pud_pfn(pud_t pud)
 {
-	return (pud_val(pud) & PTE_PFN_MASK) >> PAGE_SHIFT;
+	return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT;
 }
 
 #define pte_page(pte)	pfn_to_page(pte_pfn(pte))
@@ -318,6 +325,16 @@ static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
 	return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY);
 }
 
+static inline pte_t pte_clear_soft_dirty(pte_t pte)
+{
+	return pte_clear_flags(pte, _PAGE_SOFT_DIRTY);
+}
+
+static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd)
+{
+	return pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY);
+}
+
 #endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
 
 /*
@@ -379,7 +396,9 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 	return __pgprot(preservebits | addbits);
 }
 
-#define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK)
+#define pte_pgprot(x) __pgprot(pte_flags(x))
+#define pmd_pgprot(x) __pgprot(pmd_flags(x))
+#define pud_pgprot(x) __pgprot(pud_flags(x))
 
 #define canon_pgprot(p) __pgprot(massage_pgprot(p))
 
@@ -502,14 +521,15 @@ static inline int pmd_none(pmd_t pmd)
 
 static inline unsigned long pmd_page_vaddr(pmd_t pmd)
 {
-	return (unsigned long)__va(pmd_val(pmd) & PTE_PFN_MASK);
+	return (unsigned long)__va(pmd_val(pmd) & pmd_pfn_mask(pmd));
 }
 
 /*
  * Currently stuck as a macro due to indirect forward reference to
  * linux/mmzone.h's __section_mem_map_addr() definition:
  */
-#define pmd_page(pmd)	pfn_to_page((pmd_val(pmd) & PTE_PFN_MASK) >> PAGE_SHIFT)
+#define pmd_page(pmd)		\
+	pfn_to_page((pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT)
 
 /*
  * the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
@@ -570,14 +590,15 @@ static inline int pud_present(pud_t pud)
 
 static inline unsigned long pud_page_vaddr(pud_t pud)
 {
-	return (unsigned long)__va((unsigned long)pud_val(pud) & PTE_PFN_MASK);
+	return (unsigned long)__va(pud_val(pud) & pud_pfn_mask(pud));
 }
 
 /*
  * Currently stuck as a macro due to indirect forward reference to
  * linux/mmzone.h's __section_mem_map_addr() definition:
  */
-#define pud_page(pud)		pfn_to_page(pud_val(pud) >> PAGE_SHIFT)
+#define pud_page(pud)		\
+	pfn_to_page((pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT)
 
 /* Find an entry in the second-level page table.. */
 static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 13f310bfc09a..dd5b0aa9dd2f 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -209,10 +209,10 @@ enum page_cache_mode {
 
 #include <linux/types.h>
 
-/* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */
+/* Extracts the PFN from a (pte|pmd|pud|pgd)val_t of a 4KB page */
 #define PTE_PFN_MASK		((pteval_t)PHYSICAL_PAGE_MASK)
 
-/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */
+/* Extracts the flags from a (pte|pmd|pud|pgd)val_t of a 4KB page */
 #define PTE_FLAGS_MASK		(~PTE_PFN_MASK)
 
 typedef struct pgprot { pgprotval_t pgprot; } pgprot_t;
@@ -276,14 +276,46 @@ static inline pmdval_t native_pmd_val(pmd_t pmd)
 }
 #endif
 
+static inline pudval_t pud_pfn_mask(pud_t pud)
+{
+	if (native_pud_val(pud) & _PAGE_PSE)
+		return PUD_PAGE_MASK & PHYSICAL_PAGE_MASK;
+	else
+		return PTE_PFN_MASK;
+}
+
+static inline pudval_t pud_flags_mask(pud_t pud)
+{
+	if (native_pud_val(pud) & _PAGE_PSE)
+		return ~(PUD_PAGE_MASK & (pudval_t)PHYSICAL_PAGE_MASK);
+	else
+		return ~PTE_PFN_MASK;
+}
+
 static inline pudval_t pud_flags(pud_t pud)
 {
-	return native_pud_val(pud) & PTE_FLAGS_MASK;
+	return native_pud_val(pud) & pud_flags_mask(pud);
+}
+
+static inline pmdval_t pmd_pfn_mask(pmd_t pmd)
+{
+	if (native_pmd_val(pmd) & _PAGE_PSE)
+		return PMD_PAGE_MASK & PHYSICAL_PAGE_MASK;
+	else
+		return PTE_PFN_MASK;
+}
+
+static inline pmdval_t pmd_flags_mask(pmd_t pmd)
+{
+	if (native_pmd_val(pmd) & _PAGE_PSE)
+		return ~(PMD_PAGE_MASK & (pmdval_t)PHYSICAL_PAGE_MASK);
+	else
+		return ~PTE_PFN_MASK;
 }
 
 static inline pmdval_t pmd_flags(pmd_t pmd)
 {
-	return native_pmd_val(pmd) & PTE_FLAGS_MASK;
+	return native_pmd_val(pmd) & pmd_flags_mask(pmd);
 }
 
 static inline pte_t native_make_pte(pteval_t val)
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index b12f81022a6b..01bcde84d3e4 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -30,12 +30,9 @@ static __always_inline void preempt_count_set(int pc)
 /*
  * must be macros to avoid header recursion hell
  */
-#define init_task_preempt_count(p) do { \
-	task_thread_info(p)->saved_preempt_count = PREEMPT_DISABLED; \
-} while (0)
+#define init_task_preempt_count(p) do { } while (0)
 
 #define init_idle_preempt_count(p, cpu) do { \
-	task_thread_info(p)->saved_preempt_count = PREEMPT_ENABLED; \
 	per_cpu(__preempt_count, (cpu)) = PREEMPT_ENABLED; \
 } while (0)
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 19577dd325fa..67522256c7ff 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -11,7 +11,7 @@ struct vm86;
 #include <asm/math_emu.h>
 #include <asm/segment.h>
 #include <asm/types.h>
-#include <asm/sigcontext.h>
+#include <uapi/asm/sigcontext.h>
 #include <asm/current.h>
 #include <asm/cpufeature.h>
 #include <asm/page.h>
@@ -556,12 +556,12 @@ static inline unsigned int cpuid_edx(unsigned int op)
 }
 
 /* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
-static inline void rep_nop(void)
+static __always_inline void rep_nop(void)
 {
 	asm volatile("rep; nop" ::: "memory");
 }
 
-static inline void cpu_relax(void)
+static __always_inline void cpu_relax(void)
 {
 	rep_nop();
 }
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index 9dfce4e0417d..e6cd2c489dbb 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -1,79 +1,8 @@
 #ifndef _ASM_X86_SIGCONTEXT_H
 #define _ASM_X86_SIGCONTEXT_H
 
-#include <uapi/asm/sigcontext.h>
-
-#ifdef __i386__
-struct sigcontext {
-	unsigned short gs, __gsh;
-	unsigned short fs, __fsh;
-	unsigned short es, __esh;
-	unsigned short ds, __dsh;
-	unsigned long di;
-	unsigned long si;
-	unsigned long bp;
-	unsigned long sp;
-	unsigned long bx;
-	unsigned long dx;
-	unsigned long cx;
-	unsigned long ax;
-	unsigned long trapno;
-	unsigned long err;
-	unsigned long ip;
-	unsigned short cs, __csh;
-	unsigned long flags;
-	unsigned long sp_at_signal;
-	unsigned short ss, __ssh;
+/* This is a legacy header - all kernel code includes <uapi/asm/sigcontext.h> directly. */
 
-	/*
-	 * fpstate is really (struct _fpstate *) or (struct _xstate *)
-	 * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved
-	 * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end
-	 * of extended memory layout. See comments at the definition of
-	 * (struct _fpx_sw_bytes)
-	 */
-	void __user *fpstate;		/* zero when no FPU/extended context */
-	unsigned long oldmask;
-	unsigned long cr2;
-};
-#else /* __i386__ */
-struct sigcontext {
-	unsigned long r8;
-	unsigned long r9;
-	unsigned long r10;
-	unsigned long r11;
-	unsigned long r12;
-	unsigned long r13;
-	unsigned long r14;
-	unsigned long r15;
-	unsigned long di;
-	unsigned long si;
-	unsigned long bp;
-	unsigned long bx;
-	unsigned long dx;
-	unsigned long ax;
-	unsigned long cx;
-	unsigned long sp;
-	unsigned long ip;
-	unsigned long flags;
-	unsigned short cs;
-	unsigned short gs;
-	unsigned short fs;
-	unsigned short __pad0;
-	unsigned long err;
-	unsigned long trapno;
-	unsigned long oldmask;
-	unsigned long cr2;
+#include <uapi/asm/sigcontext.h>
 
-	/*
-	 * fpstate is really (struct _fpstate *) or (struct _xstate *)
-	 * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved
-	 * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end
-	 * of extended memory layout. See comments at the definition of
-	 * (struct _fpx_sw_bytes)
-	 */
-	void __user *fpstate;		/* zero when no FPU/extended context */
-	unsigned long reserved1[8];
-};
-#endif /* !__i386__ */
 #endif /* _ASM_X86_SIGCONTEXT_H */
diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h
index 1f3175bb994e..34edd1650bae 100644
--- a/arch/x86/include/asm/sigframe.h
+++ b/arch/x86/include/asm/sigframe.h
@@ -1,7 +1,7 @@
 #ifndef _ASM_X86_SIGFRAME_H
 #define _ASM_X86_SIGFRAME_H
 
-#include <asm/sigcontext.h>
+#include <uapi/asm/sigcontext.h>
 #include <asm/siginfo.h>
 #include <asm/ucontext.h>
 #include <linux/compat.h>
@@ -9,8 +9,6 @@
 #ifdef CONFIG_X86_32
 #define sigframe_ia32		sigframe
 #define rt_sigframe_ia32	rt_sigframe
-#define sigcontext_ia32		sigcontext
-#define _fpstate_ia32		_fpstate
 #define ucontext_ia32		ucontext
 #else /* !CONFIG_X86_32 */
 
@@ -24,7 +22,7 @@
 struct sigframe_ia32 {
 	u32 pretcode;
 	int sig;
-	struct sigcontext_ia32 sc;
+	struct sigcontext_32 sc;
 	/*
 	 * fpstate is unused. fpstate is moved/allocated after
 	 * retcode[] below. This movement allows to have the FP state and the
@@ -33,7 +31,7 @@ struct sigframe_ia32 {
 	 * the offset of extramask[] in the sigframe and thus prevent any
 	 * legacy application accessing/modifying it.
 	 */
-	struct _fpstate_ia32 fpstate_unused;
+	struct _fpstate_32 fpstate_unused;
 #ifdef CONFIG_IA32_EMULATION
 	unsigned int extramask[_COMPAT_NSIG_WORDS-1];
 #else /* !CONFIG_IA32_EMULATION */
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index c481be78fcf1..2138c9ae19ee 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -34,7 +34,7 @@ extern void do_signal(struct pt_regs *regs);
 
 #define __ARCH_HAS_SA_RESTORER
 
-#include <asm/sigcontext.h>
+#include <uapi/asm/sigcontext.h>
 
 #ifdef __i386__
 
diff --git a/arch/x86/include/asm/string_64.h b/arch/x86/include/asm/string_64.h
index e4661196994e..ff8b9a17dc4b 100644
--- a/arch/x86/include/asm/string_64.h
+++ b/arch/x86/include/asm/string_64.h
@@ -27,12 +27,11 @@ static __always_inline void *__inline_memcpy(void *to, const void *from, size_t
    function. */
 
 #define __HAVE_ARCH_MEMCPY 1
+extern void *memcpy(void *to, const void *from, size_t len);
 extern void *__memcpy(void *to, const void *from, size_t len);
 
 #ifndef CONFIG_KMEMCHECK
-#if (__GNUC__ == 4 && __GNUC_MINOR__ >= 3) || __GNUC__ > 4
-extern void *memcpy(void *to, const void *from, size_t len);
-#else
+#if (__GNUC__ == 4 && __GNUC_MINOR__ < 3) || __GNUC__ < 4
 #define memcpy(dst, src, len)					\
 ({								\
 	size_t __len = (len);					\
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index d7f3b3b78ac3..751bf4b7bf11 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -79,12 +79,12 @@ do {									\
 #else /* CONFIG_X86_32 */
 
 /* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
+#define SAVE_CONTEXT    "pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp\t"
 
 #define __EXTRA_CLOBBER  \
 	, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
-	  "r12", "r13", "r14", "r15"
+	  "r12", "r13", "r14", "r15", "flags"
 
 #ifdef CONFIG_CC_STACKPROTECTOR
 #define __switch_canary							  \
@@ -100,7 +100,11 @@ do {									\
 #define __switch_canary_iparam
 #endif	/* CC_STACKPROTECTOR */
 
-/* Save restore flags to clear handle leaking NT */
+/*
+ * There is no need to save or restore flags, because flags are always
+ * clean in kernel mode, with the possible exception of IOPL.  Kernel IOPL
+ * has no effect.
+ */
 #define switch_to(prev, next, last) \
 	asm volatile(SAVE_CONTEXT					  \
 	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index d6a756ae04c8..999b7cd2e78c 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -20,9 +20,21 @@
 #include <asm/thread_info.h>	/* for TS_COMPAT */
 #include <asm/unistd.h>
 
-typedef void (*sys_call_ptr_t)(void);
+typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long,
+					  unsigned long, unsigned long,
+					  unsigned long, unsigned long);
 extern const sys_call_ptr_t sys_call_table[];
 
+#if defined(CONFIG_X86_32)
+#define ia32_sys_call_table sys_call_table
+#define __NR_syscall_compat_max __NR_syscall_max
+#define IA32_NR_syscalls NR_syscalls
+#endif
+
+#if defined(CONFIG_IA32_EMULATION)
+extern const sys_call_ptr_t ia32_sys_call_table[];
+#endif
+
 /*
  * Only the low 32 bits of orig_ax are meaningful, so we return int.
  * This importantly ignores the high bits on 64-bit, so comparisons
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 8afdc3e44247..c7b551028740 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -57,9 +57,7 @@ struct thread_info {
 	__u32			flags;		/* low level flags */
 	__u32			status;		/* thread synchronous flags */
 	__u32			cpu;		/* current CPU */
-	int			saved_preempt_count;
 	mm_segment_t		addr_limit;
-	void __user		*sysenter_return;
 	unsigned int		sig_on_uaccess_error:1;
 	unsigned int		uaccess_err:1;	/* uaccess failed */
 };
@@ -69,7 +67,6 @@ struct thread_info {
 	.task		= &tsk,			\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.saved_preempt_count = INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
 }
 
diff --git a/arch/x86/include/asm/trace/mpx.h b/arch/x86/include/asm/trace/mpx.h
index 173dd3ba108c..0f492fc50bce 100644
--- a/arch/x86/include/asm/trace/mpx.h
+++ b/arch/x86/include/asm/trace/mpx.h
@@ -11,7 +11,7 @@
 TRACE_EVENT(mpx_bounds_register_exception,
 
 	TP_PROTO(void *addr_referenced,
-		 const struct bndreg *bndreg),
+		 const struct mpx_bndreg *bndreg),
 	TP_ARGS(addr_referenced, bndreg),
 
 	TP_STRUCT__entry(
@@ -44,7 +44,7 @@ TRACE_EVENT(mpx_bounds_register_exception,
 
 TRACE_EVENT(bounds_exception_mpx,
 
-	TP_PROTO(const struct bndcsr *bndcsr),
+	TP_PROTO(const struct mpx_bndcsr *bndcsr),
 	TP_ARGS(bndcsr),
 
 	TP_STRUCT__entry(
@@ -116,7 +116,8 @@ TRACE_EVENT(mpx_new_bounds_table,
 /*
  * This gets used outside of MPX-specific code, so we need a stub.
  */
-static inline void trace_bounds_exception_mpx(const struct bndcsr *bndcsr)
+static inline
+void trace_bounds_exception_mpx(const struct mpx_bndcsr *bndcsr)
 {
 }
 
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index a8df874f3e88..09b1b0ab94b7 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -51,13 +51,13 @@ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, un
 	 * limit, not add it to the address).
 	 */
 	if (__builtin_constant_p(size))
-		return addr > limit - size;
+		return unlikely(addr > limit - size);
 
 	/* Arbitrary sizes? Be careful about overflow */
 	addr += size;
-	if (addr < size)
+	if (unlikely(addr < size))
 		return true;
-	return addr > limit;
+	return unlikely(addr > limit);
 }
 
 #define __range_not_ok(addr, size, limit)				\
@@ -182,7 +182,7 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
 		     : "=a" (__ret_gu), "=r" (__val_gu)			\
 		     : "0" (ptr), "i" (sizeof(*(ptr))));		\
 	(x) = (__force __typeof__(*(ptr))) __val_gu;			\
-	__ret_gu;							\
+	__builtin_expect(__ret_gu, 0);					\
 })
 
 #define __put_user_x(size, x, ptr, __ret_pu)			\
@@ -278,7 +278,7 @@ extern void __put_user_8(void);
 		__put_user_x(X, __pu_val, ptr, __ret_pu);	\
 		break;						\
 	}							\
-	__ret_pu;						\
+	__builtin_expect(__ret_pu, 0);				\
 })
 
 #define __put_user_size(x, ptr, size, retval, errret)			\
@@ -401,7 +401,7 @@ do {									\
 ({								\
 	int __pu_err;						\
 	__put_user_size((x), (ptr), (size), __pu_err, -EFAULT);	\
-	__pu_err;						\
+	__builtin_expect(__pu_err, 0);				\
 })
 
 #define __get_user_nocheck(x, ptr, size)				\
@@ -410,7 +410,7 @@ do {									\
 	unsigned long __gu_val;						\
 	__get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);	\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
-	__gu_err;							\
+	__builtin_expect(__gu_err, 0);					\
 })
 
 /* FIXME: this hack is definitely wrong -AK */
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index a00ad8f2a657..ea7074784cc4 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -609,7 +609,7 @@ struct uv_cpu_nmi_s {
 
 DECLARE_PER_CPU(struct uv_cpu_nmi_s, uv_cpu_nmi);
 
-#define uv_hub_nmi			(uv_cpu_nmi.hub)
+#define uv_hub_nmi			this_cpu_read(uv_cpu_nmi.hub)
 #define uv_cpu_nmi_per(cpu)		(per_cpu(uv_cpu_nmi, cpu))
 #define uv_hub_nmi_per(cpu)		(uv_cpu_nmi_per(cpu).hub)
 
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 8021bd28c0f1..756de9190aec 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -26,7 +26,7 @@ struct vdso_image {
 	long sym___kernel_sigreturn;
 	long sym___kernel_rt_sigreturn;
 	long sym___kernel_vsyscall;
-	long sym_VDSO32_SYSENTER_RETURN;
+	long sym_int80_landing_pad;
 };
 
 #ifdef CONFIG_X86_64
@@ -38,13 +38,7 @@ extern const struct vdso_image vdso_image_x32;
 #endif
 
 #if defined CONFIG_X86_32 || defined CONFIG_COMPAT
-extern const struct vdso_image vdso_image_32_int80;
-#ifdef CONFIG_COMPAT
-extern const struct vdso_image vdso_image_32_syscall;
-#endif
-extern const struct vdso_image vdso_image_32_sysenter;
-
-extern const struct vdso_image *selected_vdso32;
+extern const struct vdso_image vdso_image_32;
 #endif
 
 extern void __init init_vdso_image(const struct vdso_image *image);
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 448b7ca61aee..14c63c7e8337 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -72,7 +72,8 @@
 #define SECONDARY_EXEC_SHADOW_VMCS              0x00004000
 #define SECONDARY_EXEC_ENABLE_PML               0x00020000
 #define SECONDARY_EXEC_XSAVES			0x00100000
-
+#define SECONDARY_EXEC_PCOMMIT			0x00200000
+#define SECONDARY_EXEC_TSC_SCALING              0x02000000
 
 #define PIN_BASED_EXT_INTR_MASK                 0x00000001
 #define PIN_BASED_NMI_EXITING                   0x00000008
@@ -167,6 +168,8 @@ enum vmcs_field {
 	VMWRITE_BITMAP                  = 0x00002028,
 	XSS_EXIT_BITMAP                 = 0x0000202C,
 	XSS_EXIT_BITMAP_HIGH            = 0x0000202D,
+	TSC_MULTIPLIER                  = 0x00002032,
+	TSC_MULTIPLIER_HIGH             = 0x00002033,
 	GUEST_PHYSICAL_ADDRESS          = 0x00002400,
 	GUEST_PHYSICAL_ADDRESS_HIGH     = 0x00002401,
 	VMCS_LINK_POINTER               = 0x00002800,
@@ -416,6 +419,7 @@ enum vmcs_field {
 #define VMX_EPT_EXTENT_CONTEXT_BIT		(1ull << 25)
 #define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
 
+#define VMX_VPID_INVVPID_BIT                    (1ull << 0) /* (32 - 32) */
 #define VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT      (1ull << 9) /* (41 - 32) */
 #define VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT      (1ull << 10) /* (42 - 32) */
 
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index d866959e5685..8b2d4bea9962 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -57,4 +57,9 @@ static inline bool xen_x2apic_para_available(void)
 }
 #endif
 
+#ifdef CONFIG_HOTPLUG_CPU
+void xen_arch_register_cpu(int num);
+void xen_arch_unregister_cpu(int num);
+#endif
+
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 0679e11d2cf7..f5fb840b43e8 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -12,7 +12,7 @@
 #include <asm/pgtable.h>
 
 #include <xen/interface/xen.h>
-#include <xen/grant_table.h>
+#include <xen/interface/grant_table.h>
 #include <xen/features.h>
 
 /* Xen machine address */
@@ -43,6 +43,8 @@ extern unsigned long *xen_p2m_addr;
 extern unsigned long  xen_p2m_size;
 extern unsigned long  xen_max_p2m_pfn;
 
+extern int xen_alloc_p2m_entry(unsigned long pfn);
+
 extern unsigned long get_phys_to_machine(unsigned long pfn);
 extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn);
 extern bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn);
@@ -296,8 +298,8 @@ void make_lowmem_page_readwrite(void *vaddr);
 #define xen_unmap(cookie) iounmap((cookie))
 
 static inline bool xen_arch_need_swiotlb(struct device *dev,
-					 unsigned long pfn,
-					 unsigned long bfn)
+					 phys_addr_t phys,
+					 dma_addr_t dev_addr)
 {
 	return false;
 }
diff --git a/arch/x86/include/uapi/asm/hyperv.h b/arch/x86/include/uapi/asm/hyperv.h
index f0412c50c47b..040d4083c24f 100644
--- a/arch/x86/include/uapi/asm/hyperv.h
+++ b/arch/x86/include/uapi/asm/hyperv.h
@@ -153,6 +153,12 @@
 /* MSR used to provide vcpu index */
 #define HV_X64_MSR_VP_INDEX			0x40000002
 
+/* MSR used to reset the guest OS. */
+#define HV_X64_MSR_RESET			0x40000003
+
+/* MSR used to provide vcpu runtime in 100ns units */
+#define HV_X64_MSR_VP_RUNTIME			0x40000010
+
 /* MSR used to read the per-partition time reference counter */
 #define HV_X64_MSR_TIME_REF_COUNT		0x40000020
 
@@ -251,4 +257,16 @@ typedef struct _HV_REFERENCE_TSC_PAGE {
 	__s64 tsc_offset;
 } HV_REFERENCE_TSC_PAGE, *PHV_REFERENCE_TSC_PAGE;
 
+/* Define the number of synthetic interrupt sources. */
+#define HV_SYNIC_SINT_COUNT		(16)
+/* Define the expected SynIC version. */
+#define HV_SYNIC_VERSION_1		(0x1)
+
+#define HV_SYNIC_CONTROL_ENABLE		(1ULL << 0)
+#define HV_SYNIC_SIMP_ENABLE		(1ULL << 0)
+#define HV_SYNIC_SIEFP_ENABLE		(1ULL << 0)
+#define HV_SYNIC_SINT_MASKED		(1ULL << 16)
+#define HV_SYNIC_SINT_AUTO_EOI		(1ULL << 17)
+#define HV_SYNIC_SINT_VECTOR_MASK	(0xFF)
+
 #endif
diff --git a/arch/x86/include/uapi/asm/mce.h b/arch/x86/include/uapi/asm/mce.h
index 76880ede9a35..03429da2fa80 100644
--- a/arch/x86/include/uapi/asm/mce.h
+++ b/arch/x86/include/uapi/asm/mce.h
@@ -2,7 +2,7 @@
 #define _UAPI_ASM_X86_MCE_H
 
 #include <linux/types.h>
-#include <asm/ioctls.h>
+#include <linux/ioctl.h>
 
 /* Fields are zero when not available */
 struct mce {
diff --git a/arch/x86/include/uapi/asm/sigcontext.h b/arch/x86/include/uapi/asm/sigcontext.h
index 40836a9a7250..d485232f1e9f 100644
--- a/arch/x86/include/uapi/asm/sigcontext.h
+++ b/arch/x86/include/uapi/asm/sigcontext.h
@@ -1,221 +1,360 @@
 #ifndef _UAPI_ASM_X86_SIGCONTEXT_H
 #define _UAPI_ASM_X86_SIGCONTEXT_H
 
+/*
+ * Linux signal context definitions. The sigcontext includes a complex
+ * hierarchy of CPU and FPU state, available to user-space (on the stack) when
+ * a signal handler is executed.
+ *
+ * As over the years this ABI grew from its very simple roots towards
+ * supporting more and more CPU state organically, some of the details (which
+ * were rather clever hacks back in the days) became a bit quirky by today.
+ *
+ * The current ABI includes flexible provisions for future extensions, so we
+ * won't have to grow new quirks for quite some time. Promise!
+ */
+
 #include <linux/compiler.h>
 #include <linux/types.h>
 
-#define FP_XSTATE_MAGIC1	0x46505853U
-#define FP_XSTATE_MAGIC2	0x46505845U
-#define FP_XSTATE_MAGIC2_SIZE	sizeof(FP_XSTATE_MAGIC2)
+#define FP_XSTATE_MAGIC1		0x46505853U
+#define FP_XSTATE_MAGIC2		0x46505845U
+#define FP_XSTATE_MAGIC2_SIZE		sizeof(FP_XSTATE_MAGIC2)
 
 /*
- * bytes 464..511 in the current 512byte layout of fxsave/fxrstor frame
- * are reserved for SW usage. On cpu's supporting xsave/xrstor, these bytes
- * are used to extended the fpstate pointer in the sigcontext, which now
- * includes the extended state information along with fpstate information.
+ * Bytes 464..511 in the current 512-byte layout of the FXSAVE/FXRSTOR frame
+ * are reserved for SW usage. On CPUs supporting XSAVE/XRSTOR, these bytes are
+ * used to extend the fpstate pointer in the sigcontext, which now includes the
+ * extended state information along with fpstate information.
+ *
+ * If sw_reserved.magic1 == FP_XSTATE_MAGIC1 then there's a
+ * sw_reserved.extended_size bytes large extended context area present. (The
+ * last 32-bit word of this extended area (at the
+ * fpstate+extended_size-FP_XSTATE_MAGIC2_SIZE address) is set to
+ * FP_XSTATE_MAGIC2 so that you can sanity check your size calculations.)
  *
- * Presence of FP_XSTATE_MAGIC1 at the beginning of this SW reserved
- * area and FP_XSTATE_MAGIC2 at the end of memory layout
- * (extended_size - FP_XSTATE_MAGIC2_SIZE) indicates the presence of the
- * extended state information in the memory layout pointed by the fpstate
- * pointer in sigcontext.
+ * This extended area typically grows with newer CPUs that have larger and
+ * larger XSAVE areas.
  */
 struct _fpx_sw_bytes {
-	__u32 magic1;		/* FP_XSTATE_MAGIC1 */
-	__u32 extended_size;	/* total size of the layout referred by
-				 * fpstate pointer in the sigcontext.
-				 */
-	__u64 xfeatures;
-				/* feature bit mask (including fp/sse/extended
-				 * state) that is present in the memory
-				 * layout.
-				 */
-	__u32 xstate_size;	/* actual xsave state size, based on the
-				 * features saved in the layout.
-				 * 'extended_size' will be greater than
-				 * 'xstate_size'.
-				 */
-	__u32 padding[7];	/*  for future use. */
+	/*
+	 * If set to FP_XSTATE_MAGIC1 then this is an xstate context.
+	 * 0 if a legacy frame.
+	 */
+	__u32				magic1;
+
+	/*
+	 * Total size of the fpstate area:
+	 *
+	 *  - if magic1 == 0 then it's sizeof(struct _fpstate)
+	 *  - if magic1 == FP_XSTATE_MAGIC1 then it's sizeof(struct _xstate)
+	 *    plus extensions (if any)
+	 */
+	__u32				extended_size;
+
+	/*
+	 * Feature bit mask (including FP/SSE/extended state) that is present
+	 * in the memory layout:
+	 */
+	__u64				xfeatures;
+
+	/*
+	 * Actual XSAVE state size, based on the xfeatures saved in the layout.
+	 * 'extended_size' is greater than 'xstate_size':
+	 */
+	__u32				xstate_size;
+
+	/* For future use: */
+	__u32				padding[7];
 };
 
-#ifdef __i386__
 /*
- * As documented in the iBCS2 standard..
- *
- * The first part of "struct _fpstate" is just the normal i387
- * hardware setup, the extra "status" word is used to save the
- * coprocessor status word before entering the handler.
+ * As documented in the iBCS2 standard:
  *
- * Pentium III FXSR, SSE support
- *	Gareth Hughes <gareth@valinux.com>, May 2000
+ * The first part of "struct _fpstate" is just the normal i387 hardware setup,
+ * the extra "status" word is used to save the coprocessor status word before
+ * entering the handler.
  *
- * The FPU state data structure has had to grow to accommodate the
- * extended FPU state required by the Streaming SIMD Extensions.
- * There is no documented standard to accomplish this at the moment.
+ * The FPU state data structure has had to grow to accommodate the extended FPU
+ * state required by the Streaming SIMD Extensions.  There is no documented
+ * standard to accomplish this at the moment.
  */
+
+/* 10-byte legacy floating point register: */
 struct _fpreg {
-	unsigned short significand[4];
-	unsigned short exponent;
+	__u16				significand[4];
+	__u16				exponent;
 };
 
+/* 16-byte floating point register: */
 struct _fpxreg {
-	unsigned short significand[4];
-	unsigned short exponent;
-	unsigned short padding[3];
+	__u16				significand[4];
+	__u16				exponent;
+	__u16				padding[3];
 };
 
+/* 16-byte XMM register: */
 struct _xmmreg {
-	unsigned long element[4];
+	__u32				element[4];
 };
 
-struct _fpstate {
-	/* Regular FPU environment */
-	unsigned long	cw;
-	unsigned long	sw;
-	unsigned long	tag;
-	unsigned long	ipoff;
-	unsigned long	cssel;
-	unsigned long	dataoff;
-	unsigned long	datasel;
-	struct _fpreg	_st[8];
-	unsigned short	status;
-	unsigned short	magic;		/* 0xffff = regular FPU data only */
+#define X86_FXSR_MAGIC			0x0000
+
+/*
+ * The 32-bit FPU frame:
+ */
+struct _fpstate_32 {
+	/* Legacy FPU environment: */
+	__u32				cw;
+	__u32				sw;
+	__u32				tag;
+	__u32				ipoff;
+	__u32				cssel;
+	__u32				dataoff;
+	__u32				datasel;
+	struct _fpreg			_st[8];
+	__u16				status;
+	__u16				magic;		/* 0xffff: regular FPU data only */
+							/* 0x0000: FXSR FPU data */
 
 	/* FXSR FPU environment */
-	unsigned long	_fxsr_env[6];	/* FXSR FPU env is ignored */
-	unsigned long	mxcsr;
-	unsigned long	reserved;
-	struct _fpxreg	_fxsr_st[8];	/* FXSR FPU reg data is ignored */
-	struct _xmmreg	_xmm[8];
-	unsigned long	padding1[44];
+	__u32				_fxsr_env[6];	/* FXSR FPU env is ignored */
+	__u32				mxcsr;
+	__u32				reserved;
+	struct _fpxreg			_fxsr_st[8];	/* FXSR FPU reg data is ignored */
+	struct _xmmreg			_xmm[8];	/* First 8 XMM registers */
+	union {
+		__u32			padding1[44];	/* Second 8 XMM registers plus padding */
+		__u32			padding[44];	/* Alias name for old user-space */
+	};
 
 	union {
-		unsigned long	padding2[12];
-		struct _fpx_sw_bytes sw_reserved; /* represents the extended
-						   * state info */
+		__u32			padding2[12];
+		struct _fpx_sw_bytes	sw_reserved;	/* Potential extended state is encoded here */
 	};
 };
 
-#define X86_FXSR_MAGIC		0x0000
-
-#ifndef __KERNEL__
 /*
- * User-space might still rely on the old definition:
+ * The 64-bit FPU frame. (FXSAVE format and later)
+ *
+ * Note1: If sw_reserved.magic1 == FP_XSTATE_MAGIC1 then the structure is
+ *        larger: 'struct _xstate'. Note that 'struct _xstate' embedds
+ *        'struct _fpstate' so that you can always assume the _fpstate portion
+ *        exists so that you can check the magic value.
+ *
+ * Note2: Reserved fields may someday contain valuable data. Always
+ *	  save/restore them when you change signal frames.
  */
-struct sigcontext {
-	unsigned short gs, __gsh;
-	unsigned short fs, __fsh;
-	unsigned short es, __esh;
-	unsigned short ds, __dsh;
-	unsigned long edi;
-	unsigned long esi;
-	unsigned long ebp;
-	unsigned long esp;
-	unsigned long ebx;
-	unsigned long edx;
-	unsigned long ecx;
-	unsigned long eax;
-	unsigned long trapno;
-	unsigned long err;
-	unsigned long eip;
-	unsigned short cs, __csh;
-	unsigned long eflags;
-	unsigned long esp_at_signal;
-	unsigned short ss, __ssh;
-	struct _fpstate __user *fpstate;
-	unsigned long oldmask;
-	unsigned long cr2;
-};
-#endif /* !__KERNEL__ */
-
-#else /* __i386__ */
-
-/* FXSAVE frame */
-/* Note: reserved1/2 may someday contain valuable data. Always save/restore
-   them when you change signal frames. */
-struct _fpstate {
-	__u16	cwd;
-	__u16	swd;
-	__u16	twd;		/* Note this is not the same as the
-				   32bit/x87/FSAVE twd */
-	__u16	fop;
-	__u64	rip;
-	__u64	rdp;
-	__u32	mxcsr;
-	__u32	mxcsr_mask;
-	__u32	st_space[32];	/* 8*16 bytes for each FP-reg */
-	__u32	xmm_space[64];	/* 16*16 bytes for each XMM-reg  */
-	__u32	reserved2[12];
+struct _fpstate_64 {
+	__u16				cwd;
+	__u16				swd;
+	/* Note this is not the same as the 32-bit/x87/FSAVE twd: */
+	__u16				twd;
+	__u16				fop;
+	__u64				rip;
+	__u64				rdp;
+	__u32				mxcsr;
+	__u32				mxcsr_mask;
+	__u32				st_space[32];	/*  8x  FP registers, 16 bytes each */
+	__u32				xmm_space[64];	/* 16x XMM registers, 16 bytes each */
+	__u32				reserved2[12];
 	union {
-		__u32	reserved3[12];
-		struct _fpx_sw_bytes sw_reserved; /* represents the extended
-						   * state information */
+		__u32			reserved3[12];
+		struct _fpx_sw_bytes	sw_reserved;	/* Potential extended state is encoded here */
 	};
 };
 
-#ifndef __KERNEL__
-/*
- * User-space might still rely on the old definition:
- */
-struct sigcontext {
-	__u64 r8;
-	__u64 r9;
-	__u64 r10;
-	__u64 r11;
-	__u64 r12;
-	__u64 r13;
-	__u64 r14;
-	__u64 r15;
-	__u64 rdi;
-	__u64 rsi;
-	__u64 rbp;
-	__u64 rbx;
-	__u64 rdx;
-	__u64 rax;
-	__u64 rcx;
-	__u64 rsp;
-	__u64 rip;
-	__u64 eflags;		/* RFLAGS */
-	__u16 cs;
-	__u16 gs;
-	__u16 fs;
-	__u16 __pad0;
-	__u64 err;
-	__u64 trapno;
-	__u64 oldmask;
-	__u64 cr2;
-	struct _fpstate __user *fpstate;	/* zero when no FPU context */
-#ifdef __ILP32__
-	__u32 __fpstate_pad;
+#ifdef __i386__
+# define _fpstate _fpstate_32
+#else
+# define _fpstate _fpstate_64
 #endif
-	__u64 reserved1[8];
-};
-#endif /* !__KERNEL__ */
-
-#endif /* !__i386__ */
 
 struct _header {
-	__u64 xfeatures;
-	__u64 reserved1[2];
-	__u64 reserved2[5];
+	__u64				xfeatures;
+	__u64				reserved1[2];
+	__u64				reserved2[5];
 };
 
 struct _ymmh_state {
-	/* 16 * 16 bytes for each YMMH-reg */
-	__u32 ymmh_space[64];
+	/* 16x YMM registers, 16 bytes each: */
+	__u32				ymmh_space[64];
 };
 
 /*
- * Extended state pointed by the fpstate pointer in the sigcontext.
- * In addition to the fpstate, information encoded in the xstate_hdr
- * indicates the presence of other extended state information
- * supported by the processor and OS.
+ * Extended state pointed to by sigcontext::fpstate.
+ *
+ * In addition to the fpstate, information encoded in _xstate::xstate_hdr
+ * indicates the presence of other extended state information supported
+ * by the CPU and kernel:
  */
 struct _xstate {
-	struct _fpstate fpstate;
-	struct _header xstate_hdr;
-	struct _ymmh_state ymmh;
-	/* new processor state extensions go here */
+	struct _fpstate			fpstate;
+	struct _header			xstate_hdr;
+	struct _ymmh_state		ymmh;
+	/* New processor state extensions go here: */
+};
+
+/*
+ * The 32-bit signal frame:
+ */
+struct sigcontext_32 {
+	__u16				gs, __gsh;
+	__u16				fs, __fsh;
+	__u16				es, __esh;
+	__u16				ds, __dsh;
+	__u32				di;
+	__u32				si;
+	__u32				bp;
+	__u32				sp;
+	__u32				bx;
+	__u32				dx;
+	__u32				cx;
+	__u32				ax;
+	__u32				trapno;
+	__u32				err;
+	__u32				ip;
+	__u16				cs, __csh;
+	__u32				flags;
+	__u32				sp_at_signal;
+	__u16				ss, __ssh;
+
+	/*
+	 * fpstate is really (struct _fpstate *) or (struct _xstate *)
+	 * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved
+	 * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end
+	 * of extended memory layout. See comments at the definition of
+	 * (struct _fpx_sw_bytes)
+	 */
+	__u32				fpstate; /* Zero when no FPU/extended context */
+	__u32				oldmask;
+	__u32				cr2;
+};
+
+/*
+ * The 64-bit signal frame:
+ */
+struct sigcontext_64 {
+	__u64				r8;
+	__u64				r9;
+	__u64				r10;
+	__u64				r11;
+	__u64				r12;
+	__u64				r13;
+	__u64				r14;
+	__u64				r15;
+	__u64				di;
+	__u64				si;
+	__u64				bp;
+	__u64				bx;
+	__u64				dx;
+	__u64				ax;
+	__u64				cx;
+	__u64				sp;
+	__u64				ip;
+	__u64				flags;
+	__u16				cs;
+	__u16				gs;
+	__u16				fs;
+	__u16				__pad0;
+	__u64				err;
+	__u64				trapno;
+	__u64				oldmask;
+	__u64				cr2;
+
+	/*
+	 * fpstate is really (struct _fpstate *) or (struct _xstate *)
+	 * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved
+	 * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end
+	 * of extended memory layout. See comments at the definition of
+	 * (struct _fpx_sw_bytes)
+	 */
+	__u64				fpstate; /* Zero when no FPU/extended context */
+	__u64				reserved1[8];
+};
+
+/*
+ * Create the real 'struct sigcontext' type:
+ */
+#ifdef __KERNEL__
+# ifdef __i386__
+#  define sigcontext sigcontext_32
+# else
+#  define sigcontext sigcontext_64
+# endif
+#endif
+
+/*
+ * The old user-space sigcontext definition, just in case user-space still
+ * relies on it. The kernel definition (in asm/sigcontext.h) has unified
+ * field names but otherwise the same layout.
+ */
+#ifndef __KERNEL__
+
+#define _fpstate_ia32			_fpstate_32
+#define sigcontext_ia32			sigcontext_32
+
+
+# ifdef __i386__
+struct sigcontext {
+	__u16				gs, __gsh;
+	__u16				fs, __fsh;
+	__u16				es, __esh;
+	__u16				ds, __dsh;
+	__u32				edi;
+	__u32				esi;
+	__u32				ebp;
+	__u32				esp;
+	__u32				ebx;
+	__u32				edx;
+	__u32				ecx;
+	__u32				eax;
+	__u32				trapno;
+	__u32				err;
+	__u32				eip;
+	__u16				cs, __csh;
+	__u32				eflags;
+	__u32				esp_at_signal;
+	__u16				ss, __ssh;
+	struct _fpstate __user		*fpstate;
+	__u32				oldmask;
+	__u32				cr2;
 };
+# else /* __x86_64__: */
+struct sigcontext {
+	__u64				r8;
+	__u64				r9;
+	__u64				r10;
+	__u64				r11;
+	__u64				r12;
+	__u64				r13;
+	__u64				r14;
+	__u64				r15;
+	__u64				rdi;
+	__u64				rsi;
+	__u64				rbp;
+	__u64				rbx;
+	__u64				rdx;
+	__u64				rax;
+	__u64				rcx;
+	__u64				rsp;
+	__u64				rip;
+	__u64				eflags;		/* RFLAGS */
+	__u16				cs;
+	__u16				gs;
+	__u16				fs;
+	__u16				__pad0;
+	__u64				err;
+	__u64				trapno;
+	__u64				oldmask;
+	__u64				cr2;
+	struct _fpstate __user		*fpstate;	/* Zero when no FPU context */
+#  ifdef __ILP32__
+	__u32				__fpstate_pad;
+#  endif
+	__u64				reserved1[8];
+};
+# endif /* __x86_64__ */
+#endif /* !__KERNEL__ */
 
 #endif /* _UAPI_ASM_X86_SIGCONTEXT_H */
diff --git a/arch/x86/include/uapi/asm/sigcontext32.h b/arch/x86/include/uapi/asm/sigcontext32.h
index ad1478c4ae12..a92b0f0dc09e 100644
--- a/arch/x86/include/uapi/asm/sigcontext32.h
+++ b/arch/x86/include/uapi/asm/sigcontext32.h
@@ -1,77 +1,8 @@
 #ifndef _ASM_X86_SIGCONTEXT32_H
 #define _ASM_X86_SIGCONTEXT32_H
 
-#include <linux/types.h>
+/* This is a legacy file - all the type definitions are in sigcontext.h: */
 
-/* signal context for 32bit programs. */
-
-#define X86_FXSR_MAGIC		0x0000
-
-struct _fpreg {
-	unsigned short significand[4];
-	unsigned short exponent;
-};
-
-struct _fpxreg {
-	unsigned short significand[4];
-	unsigned short exponent;
-	unsigned short padding[3];
-};
-
-struct _xmmreg {
-	__u32	element[4];
-};
-
-/* FSAVE frame with extensions */
-struct _fpstate_ia32 {
-	/* Regular FPU environment */
-	__u32 	cw;
-	__u32	sw;
-	__u32	tag;	/* not compatible to 64bit twd */
-	__u32	ipoff;
-	__u32	cssel;
-	__u32	dataoff;
-	__u32	datasel;
-	struct _fpreg	_st[8];
-	unsigned short	status;
-	unsigned short	magic;		/* 0xffff = regular FPU data only */
-
-	/* FXSR FPU environment */
-	__u32	_fxsr_env[6];
-	__u32	mxcsr;
-	__u32	reserved;
-	struct _fpxreg	_fxsr_st[8];
-	struct _xmmreg	_xmm[8];	/* It's actually 16 */
-	__u32	padding[44];
-	union {
-		__u32 padding2[12];
-		struct _fpx_sw_bytes sw_reserved;
-	};
-};
-
-struct sigcontext_ia32 {
-       unsigned short gs, __gsh;
-       unsigned short fs, __fsh;
-       unsigned short es, __esh;
-       unsigned short ds, __dsh;
-       unsigned int di;
-       unsigned int si;
-       unsigned int bp;
-       unsigned int sp;
-       unsigned int bx;
-       unsigned int dx;
-       unsigned int cx;
-       unsigned int ax;
-       unsigned int trapno;
-       unsigned int err;
-       unsigned int ip;
-       unsigned short cs, __csh;
-       unsigned int flags;
-       unsigned int sp_at_signal;
-       unsigned short ss, __ssh;
-       unsigned int fpstate;		/* really (struct _fpstate_ia32 *) */
-       unsigned int oldmask;
-       unsigned int cr2;
-};
+#include <asm/sigcontext.h>
 
 #endif /* _ASM_X86_SIGCONTEXT32_H */
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index b5d7640abc5d..8a4add8e4639 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -100,6 +100,7 @@
 	{ SVM_EXIT_EXCP_BASE + UD_VECTOR,       "UD excp" }, \
 	{ SVM_EXIT_EXCP_BASE + PF_VECTOR,       "PF excp" }, \
 	{ SVM_EXIT_EXCP_BASE + NM_VECTOR,       "NM excp" }, \
+	{ SVM_EXIT_EXCP_BASE + AC_VECTOR,       "AC excp" }, \
 	{ SVM_EXIT_EXCP_BASE + MC_VECTOR,       "MC excp" }, \
 	{ SVM_EXIT_INTR,        "interrupt" }, \
 	{ SVM_EXIT_NMI,         "nmi" }, \
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 37fee272618f..5b15d94a33f8 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -78,6 +78,7 @@
 #define EXIT_REASON_PML_FULL            62
 #define EXIT_REASON_XSAVES              63
 #define EXIT_REASON_XRSTORS             64
+#define EXIT_REASON_PCOMMIT             65
 
 #define VMX_EXIT_REASONS \
 	{ EXIT_REASON_EXCEPTION_NMI,         "EXCEPTION_NMI" }, \
@@ -126,7 +127,8 @@
 	{ EXIT_REASON_INVVPID,               "INVVPID" }, \
 	{ EXIT_REASON_INVPCID,               "INVPCID" }, \
 	{ EXIT_REASON_XSAVES,                "XSAVES" }, \
-	{ EXIT_REASON_XRSTORS,               "XRSTORS" }
+	{ EXIT_REASON_XRSTORS,               "XRSTORS" }, \
+	{ EXIT_REASON_PCOMMIT,               "PCOMMIT" }
 
 #define VMX_ABORT_SAVE_GUEST_MSR_FAIL        1
 #define VMX_ABORT_LOAD_HOST_MSR_FAIL         4