Merge remote-tracking branch 'wireless-next/master' into mac80211-next

45 files changed, 788 insertions, 338 deletions

diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index b1977bad5435..c8c1e700c26e 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -26,6 +26,7 @@
 #include <acpi/pdc_intel.h>
 
 #include <asm/numa.h>
+#include <asm/fixmap.h>
 #include <asm/processor.h>
 #include <asm/mmu.h>
 #include <asm/mpspec.h>
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 722aa3b04624..da31c8b8a92d 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -6,6 +6,7 @@
 #include <asm/processor.h>
 #include <asm/alternative.h>
 #include <asm/cmpxchg.h>
+#include <asm/rmwcc.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for
@@ -76,12 +77,7 @@ static inline void atomic_sub(int i, atomic_t *v)
  */
 static inline int atomic_sub_and_test(int i, atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "subl %2,%0; sete %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, i, "%0", "e");
 }
 
 /**
@@ -118,12 +114,7 @@ static inline void atomic_dec(atomic_t *v)
  */
 static inline int atomic_dec_and_test(atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "decl %0; sete %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
 }
 
 /**
@@ -136,12 +127,7 @@ static inline int atomic_dec_and_test(atomic_t *v)
  */
 static inline int atomic_inc_and_test(atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "incl %0; sete %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
 }
 
 /**
@@ -155,12 +141,7 @@ static inline int atomic_inc_and_test(atomic_t *v)
  */
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "addl %2,%0; sets %1"
-		     : "+m" (v->counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, i, "%0", "s");
 }
 
 /**
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 0e1cbfc8ee06..3f065c985aee 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -72,12 +72,7 @@ static inline void atomic64_sub(long i, atomic64_t *v)
  */
 static inline int atomic64_sub_and_test(long i, atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "subq %2,%0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "er" (i), "m" (v->counter) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, i, "%0", "e");
 }
 
 /**
@@ -116,12 +111,7 @@ static inline void atomic64_dec(atomic64_t *v)
  */
 static inline int atomic64_dec_and_test(atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "decq %0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "m" (v->counter) : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", "e");
 }
 
 /**
@@ -134,12 +124,7 @@ static inline int atomic64_dec_and_test(atomic64_t *v)
  */
 static inline int atomic64_inc_and_test(atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "incq %0; sete %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "m" (v->counter) : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", "e");
 }
 
 /**
@@ -153,12 +138,7 @@ static inline int atomic64_inc_and_test(atomic64_t *v)
  */
 static inline int atomic64_add_negative(long i, atomic64_t *v)
 {
-	unsigned char c;
-
-	asm volatile(LOCK_PREFIX "addq %2,%0; sets %1"
-		     : "=m" (v->counter), "=qm" (c)
-		     : "er" (i), "m" (v->counter) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, i, "%0", "s");
 }
 
 /**
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 41639ce8fd63..6d76d0935989 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -14,6 +14,7 @@
 
 #include <linux/compiler.h>
 #include <asm/alternative.h>
+#include <asm/rmwcc.h>
 
 #if BITS_PER_LONG == 32
 # define _BITOPS_LONG_SHIFT 5
@@ -204,12 +205,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr)
  */
 static inline int test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
-
-	asm volatile(LOCK_PREFIX "bts %2,%1\n\t"
-		     "sbb %0,%0" : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
-	return oldbit;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, nr, "%0", "c");
 }
 
 /**
@@ -255,13 +251,7 @@ static inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
-
-	asm volatile(LOCK_PREFIX "btr %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
-	return oldbit;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, nr, "%0", "c");
 }
 
 /**
@@ -314,13 +304,7 @@ static inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
  */
 static inline int test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
-
-	asm volatile(LOCK_PREFIX "btc %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR : "Ir" (nr) : "memory");
-
-	return oldbit;
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, nr, "%0", "c");
 }
 
 static __always_inline int constant_test_bit(long nr, const volatile unsigned long *addr)
diff --git a/arch/x86/include/asm/calling.h b/arch/x86/include/asm/calling.h
index 0fa675033912..cb4c73bfeb48 100644
--- a/arch/x86/include/asm/calling.h
+++ b/arch/x86/include/asm/calling.h
@@ -48,6 +48,8 @@ For 32-bit we have the following conventions - kernel is built with
 
 #include <asm/dwarf2.h>
 
+#ifdef CONFIG_X86_64
+
 /*
  * 64-bit system call stack frame layout defines and helpers,
  * for assembly code:
@@ -192,3 +194,51 @@ For 32-bit we have the following conventions - kernel is built with
 	.macro icebp
 	.byte 0xf1
 	.endm
+
+#else /* CONFIG_X86_64 */
+
+/*
+ * For 32bit only simplified versions of SAVE_ALL/RESTORE_ALL. These
+ * are different from the entry_32.S versions in not changing the segment
+ * registers. So only suitable for in kernel use, not when transitioning
+ * from or to user space. The resulting stack frame is not a standard
+ * pt_regs frame. The main use case is calling C code from assembler
+ * when all the registers need to be preserved.
+ */
+
+	.macro SAVE_ALL
+	pushl_cfi %eax
+	CFI_REL_OFFSET eax, 0
+	pushl_cfi %ebp
+	CFI_REL_OFFSET ebp, 0
+	pushl_cfi %edi
+	CFI_REL_OFFSET edi, 0
+	pushl_cfi %esi
+	CFI_REL_OFFSET esi, 0
+	pushl_cfi %edx
+	CFI_REL_OFFSET edx, 0
+	pushl_cfi %ecx
+	CFI_REL_OFFSET ecx, 0
+	pushl_cfi %ebx
+	CFI_REL_OFFSET ebx, 0
+	.endm
+
+	.macro RESTORE_ALL
+	popl_cfi %ebx
+	CFI_RESTORE ebx
+	popl_cfi %ecx
+	CFI_RESTORE ecx
+	popl_cfi %edx
+	CFI_RESTORE edx
+	popl_cfi %esi
+	CFI_RESTORE esi
+	popl_cfi %edi
+	CFI_RESTORE edi
+	popl_cfi %ebp
+	CFI_RESTORE ebp
+	popl_cfi %eax
+	CFI_RESTORE eax
+	.endm
+
+#endif /* CONFIG_X86_64 */
+
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index d3f5c63078d8..89270b4318db 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -374,7 +374,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 		 * Catch too early usage of this before alternatives
 		 * have run.
 		 */
-		asm goto("1: jmp %l[t_warn]\n"
+		asm_volatile_goto("1: jmp %l[t_warn]\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"
@@ -388,7 +388,7 @@ static __always_inline __pure bool __static_cpu_has(u16 bit)
 
 #endif
 
-		asm goto("1: jmp %l[t_no]\n"
+		asm_volatile_goto("1: jmp %l[t_no]\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"
@@ -453,7 +453,7 @@ static __always_inline __pure bool _static_cpu_has_safe(u16 bit)
  * have. Thus, we force the jump to the widest, 4-byte, signed relative
  * offset even though the last would often fit in less bytes.
  */
-		asm goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
+		asm_volatile_goto("1: .byte 0xe9\n .long %l[t_dynamic] - 2f\n"
 			 "2:\n"
 			 ".section .altinstructions,\"a\"\n"
 			 " .long 1b - .\n"		/* src offset */
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index b90e5dfeee46..50d033a8947d 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -327,10 +327,25 @@ static inline void write_trace_idt_entry(int entry, const gate_desc *gate)
 {
 	write_idt_entry(trace_idt_table, entry, gate);
 }
+
+static inline void _trace_set_gate(int gate, unsigned type, void *addr,
+				   unsigned dpl, unsigned ist, unsigned seg)
+{
+	gate_desc s;
+
+	pack_gate(&s, type, (unsigned long)addr, dpl, ist, seg);
+	/*
+	 * does not need to be atomic because it is only done once at
+	 * setup time
+	 */
+	write_trace_idt_entry(gate, &s);
+}
 #else
 static inline void write_trace_idt_entry(int entry, const gate_desc *gate)
 {
 }
+
+#define _trace_set_gate(gate, type, addr, dpl, ist, seg)
 #endif
 
 static inline void _set_gate(int gate, unsigned type, void *addr,
@@ -353,11 +368,14 @@ static inline void _set_gate(int gate, unsigned type, void *addr,
  * Pentium F0 0F bugfix can have resulted in the mapped
  * IDT being write-protected.
  */
-static inline void set_intr_gate(unsigned int n, void *addr)
-{
-	BUG_ON((unsigned)n > 0xFF);
-	_set_gate(n, GATE_INTERRUPT, addr, 0, 0, __KERNEL_CS);
-}
+#define set_intr_gate(n, addr)						\
+	do {								\
+		BUG_ON((unsigned)n > 0xFF);				\
+		_set_gate(n, GATE_INTERRUPT, (void *)addr, 0, 0,	\
+			  __KERNEL_CS);					\
+		_trace_set_gate(n, GATE_INTERRUPT, (void *)trace_##addr,\
+				0, 0, __KERNEL_CS);			\
+	} while (0)
 
 extern int first_system_vector;
 /* used_vectors is BITMAP for irq is not managed by percpu vector_irq */
@@ -374,37 +392,10 @@ static inline void alloc_system_vector(int vector)
 	}
 }
 
-#ifdef CONFIG_TRACING
-static inline void trace_set_intr_gate(unsigned int gate, void *addr)
-{
-	gate_desc s;
-
-	pack_gate(&s, GATE_INTERRUPT, (unsigned long)addr, 0, 0, __KERNEL_CS);
-	write_idt_entry(trace_idt_table, gate, &s);
-}
-
-static inline void __trace_alloc_intr_gate(unsigned int n, void *addr)
-{
-	trace_set_intr_gate(n, addr);
-}
-#else
-static inline void trace_set_intr_gate(unsigned int gate, void *addr)
-{
-}
-
-#define __trace_alloc_intr_gate(n, addr)
-#endif
-
-static inline void __alloc_intr_gate(unsigned int n, void *addr)
-{
-	set_intr_gate(n, addr);
-}
-
 #define alloc_intr_gate(n, addr)				\
 	do {							\
 		alloc_system_vector(n);				\
-		__alloc_intr_gate(n, addr);			\
-		__trace_alloc_intr_gate(n, trace_##addr);	\
+		set_intr_gate(n, addr);				\
 	} while (0)
 
 /*
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 0062a0125041..65c6e6e3a552 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -109,6 +109,8 @@ static inline bool efi_is_native(void)
 	return IS_ENABLED(CONFIG_X86_64) == efi_enabled(EFI_64BIT);
 }
 
+extern struct console early_efi_console;
+
 #else
 /*
  * IF EFI is not configured, have the EFI calls return -ENOSYS.
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 4d0bda7b11e3..c49a613c6452 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -365,7 +365,7 @@ static inline void drop_fpu(struct task_struct *tsk)
 	 * Forget coprocessor state..
 	 */
 	preempt_disable();
-	tsk->fpu_counter = 0;
+	tsk->thread.fpu_counter = 0;
 	__drop_fpu(tsk);
 	clear_used_math();
 	preempt_enable();
@@ -424,7 +424,7 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
 	 * or if the past 5 consecutive context-switches used math.
 	 */
 	fpu.preload = tsk_used_math(new) && (use_eager_fpu() ||
-					     new->fpu_counter > 5);
+					     new->thread.fpu_counter > 5);
 	if (__thread_has_fpu(old)) {
 		if (!__save_init_fpu(old))
 			cpu = ~0;
@@ -433,16 +433,16 @@ static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct ta
 
 		/* Don't change CR0.TS if we just switch! */
 		if (fpu.preload) {
-			new->fpu_counter++;
+			new->thread.fpu_counter++;
 			__thread_set_has_fpu(new);
 			prefetch(new->thread.fpu.state);
 		} else if (!use_eager_fpu())
 			stts();
 	} else {
-		old->fpu_counter = 0;
+		old->thread.fpu_counter = 0;
 		old->thread.fpu.last_cpu = ~0;
 		if (fpu.preload) {
-			new->fpu_counter++;
+			new->thread.fpu_counter++;
 			if (!use_eager_fpu() && fpu_lazy_restore(new, cpu))
 				fpu.preload = 0;
 			else
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 92b3bae08b74..cba45d99ac1a 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -187,6 +187,9 @@ extern __visible void smp_invalidate_interrupt(struct pt_regs *);
 #endif
 
 extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
+#ifdef CONFIG_TRACING
+#define trace_interrupt interrupt
+#endif
 
 typedef int vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
new file mode 100644
index 000000000000..459769d39263
--- /dev/null
+++ b/arch/x86/include/asm/intel-mid.h
@@ -0,0 +1,113 @@
+/*
+ * intel-mid.h: Intel MID specific setup code
+ *
+ * (C) Copyright 2009 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#ifndef _ASM_X86_INTEL_MID_H
+#define _ASM_X86_INTEL_MID_H
+
+#include <linux/sfi.h>
+#include <linux/platform_device.h>
+
+extern int intel_mid_pci_init(void);
+extern int get_gpio_by_name(const char *name);
+extern void intel_scu_device_register(struct platform_device *pdev);
+extern int __init sfi_parse_mrtc(struct sfi_table_header *table);
+extern int __init sfi_parse_mtmr(struct sfi_table_header *table);
+extern int sfi_mrtc_num;
+extern struct sfi_rtc_table_entry sfi_mrtc_array[];
+
+/*
+ * Here defines the array of devices platform data that IAFW would export
+ * through SFI "DEVS" table, we use name and type to match the device and
+ * its platform data.
+ */
+struct devs_id {
+	char name[SFI_NAME_LEN + 1];
+	u8 type;
+	u8 delay;
+	void *(*get_platform_data)(void *info);
+	/* Custom handler for devices */
+	void (*device_handler)(struct sfi_device_table_entry *pentry,
+				struct devs_id *dev);
+};
+
+#define sfi_device(i)   \
+	static const struct devs_id *const __intel_mid_sfi_##i##_dev __used \
+	__attribute__((__section__(".x86_intel_mid_dev.init"))) = &i
+
+/*
+ * Medfield is the follow-up of Moorestown, it combines two chip solution into
+ * one. Other than that it also added always-on and constant tsc and lapic
+ * timers. Medfield is the platform name, and the chip name is called Penwell
+ * we treat Medfield/Penwell as a variant of Moorestown. Penwell can be
+ * identified via MSRs.
+ */
+enum intel_mid_cpu_type {
+	/* 1 was Moorestown */
+	INTEL_MID_CPU_CHIP_PENWELL = 2,
+};
+
+extern enum intel_mid_cpu_type __intel_mid_cpu_chip;
+
+#ifdef CONFIG_X86_INTEL_MID
+
+static inline enum intel_mid_cpu_type intel_mid_identify_cpu(void)
+{
+	return __intel_mid_cpu_chip;
+}
+
+static inline bool intel_mid_has_msic(void)
+{
+	return (intel_mid_identify_cpu() == INTEL_MID_CPU_CHIP_PENWELL);
+}
+
+#else /* !CONFIG_X86_INTEL_MID */
+
+#define intel_mid_identify_cpu()    (0)
+#define intel_mid_has_msic()    (0)
+
+#endif /* !CONFIG_X86_INTEL_MID */
+
+enum intel_mid_timer_options {
+	INTEL_MID_TIMER_DEFAULT,
+	INTEL_MID_TIMER_APBT_ONLY,
+	INTEL_MID_TIMER_LAPIC_APBT,
+};
+
+extern enum intel_mid_timer_options intel_mid_timer_options;
+
+/*
+ * Penwell uses spread spectrum clock, so the freq number is not exactly
+ * the same as reported by MSR based on SDM.
+ */
+#define PENWELL_FSB_FREQ_83SKU         83200
+#define PENWELL_FSB_FREQ_100SKU        99840
+
+#define SFI_MTMR_MAX_NUM 8
+#define SFI_MRTC_MAX	8
+
+extern struct console early_mrst_console;
+extern void mrst_early_console_init(void);
+
+extern struct console early_hsu_console;
+extern void hsu_early_console_init(const char *);
+
+extern void intel_scu_devices_create(void);
+extern void intel_scu_devices_destroy(void);
+
+/* VRTC timer */
+#define MRST_VRTC_MAP_SZ	(1024)
+/*#define MRST_VRTC_PGOFFSET	(0xc00) */
+
+extern void intel_mid_rtc_init(void);
+
+/* the offset for the mapping of global gpio pin to irq */
+#define INTEL_MID_IRQ_OFFSET 0x100
+
+#endif /* _ASM_X86_INTEL_MID_H */
diff --git a/arch/x86/include/asm/mrst-vrtc.h b/arch/x86/include/asm/intel_mid_vrtc.h
index 1e69a75412a4..86ff4685c409 100644
--- a/arch/x86/include/asm/mrst-vrtc.h
+++ b/arch/x86/include/asm/intel_mid_vrtc.h
@@ -1,5 +1,5 @@
-#ifndef _MRST_VRTC_H
-#define _MRST_VRTC_H
+#ifndef _INTEL_MID_VRTC_H
+#define _INTEL_MID_VRTC_H
 
 extern unsigned char vrtc_cmos_read(unsigned char reg);
 extern void vrtc_cmos_write(unsigned char val, unsigned char reg);
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 64507f35800c..6a2cefb4395a 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -18,7 +18,7 @@
 
 static __always_inline bool arch_static_branch(struct static_key *key)
 {
-	asm goto("1:"
+	asm_volatile_goto("1:"
 		".byte " __stringify(STATIC_KEY_INIT_NOP) "\n\t"
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index 2c37aadcbc35..32ce71375b21 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -21,7 +21,7 @@ enum die_val {
 	DIE_NMIUNKNOWN,
 };
 
-extern void printk_address(unsigned long address, int reliable);
+extern void printk_address(unsigned long address);
 extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
 extern void show_trace(struct task_struct *t, struct pt_regs *regs,
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 15f960c06ff7..24ec1216596e 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -274,13 +274,17 @@ struct x86_emulate_ctxt {
 
 	bool guest_mode; /* guest running a nested guest */
 	bool perm_ok; /* do not check permissions if true */
-	bool only_vendor_specific_insn;
+	bool ud;	/* inject an #UD if host doesn't support insn */
 
 	bool have_exception;
 	struct x86_exception exception;
 
-	/* decode cache */
-	u8 twobyte;
+	/*
+	 * decode cache
+	 */
+
+	/* current opcode length in bytes */
+	u8 opcode_len;
 	u8 b;
 	u8 intercept;
 	u8 lock_prefix;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c76ff74a98f2..ae5d7830855c 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -79,6 +79,13 @@
 #define KVM_HPAGE_MASK(x)	(~(KVM_HPAGE_SIZE(x) - 1))
 #define KVM_PAGES_PER_HPAGE(x)	(KVM_HPAGE_SIZE(x) / PAGE_SIZE)
 
+static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
+{
+	/* KVM_HPAGE_GFN_SHIFT(PT_PAGE_TABLE_LEVEL) must be 0. */
+	return (gfn >> KVM_HPAGE_GFN_SHIFT(level)) -
+		(base_gfn >> KVM_HPAGE_GFN_SHIFT(level));
+}
+
 #define SELECTOR_TI_MASK (1 << 2)
 #define SELECTOR_RPL_MASK 0x03
 
@@ -253,7 +260,6 @@ struct kvm_pio_request {
  * mode.
  */
 struct kvm_mmu {
-	void (*new_cr3)(struct kvm_vcpu *vcpu);
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long root);
 	unsigned long (*get_cr3)(struct kvm_vcpu *vcpu);
 	u64 (*get_pdptr)(struct kvm_vcpu *vcpu, int index);
@@ -261,7 +267,6 @@ struct kvm_mmu {
 			  bool prefault);
 	void (*inject_page_fault)(struct kvm_vcpu *vcpu,
 				  struct x86_exception *fault);
-	void (*free)(struct kvm_vcpu *vcpu);
 	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
 			    struct x86_exception *exception);
 	gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access);
@@ -389,6 +394,8 @@ struct kvm_vcpu_arch {
 
 	struct fpu guest_fpu;
 	u64 xcr0;
+	u64 guest_supported_xcr0;
+	u32 guest_xstate_size;
 
 	struct kvm_pio_request pio;
 	void *pio_data;
@@ -557,7 +564,9 @@ struct kvm_arch {
 
 	struct list_head assigned_dev_head;
 	struct iommu_domain *iommu_domain;
-	int iommu_flags;
+	bool iommu_noncoherent;
+#define __KVM_HAVE_ARCH_NONCOHERENT_DMA
+	atomic_t noncoherent_dma_count;
 	struct kvm_pic *vpic;
 	struct kvm_ioapic *vioapic;
 	struct kvm_pit *vpit;
@@ -780,11 +789,11 @@ void kvm_mmu_module_exit(void);
 
 void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
 int kvm_mmu_create(struct kvm_vcpu *vcpu);
-int kvm_mmu_setup(struct kvm_vcpu *vcpu);
+void kvm_mmu_setup(struct kvm_vcpu *vcpu);
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
 		u64 dirty_mask, u64 nx_mask, u64 x_mask);
 
-int kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
+void kvm_mmu_reset_context(struct kvm_vcpu *vcpu);
 void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot);
 void kvm_mmu_write_protect_pt_masked(struct kvm *kvm,
 				     struct kvm_memory_slot *slot,
@@ -922,13 +931,11 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code,
 		       void *insn, int insn_len);
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);
+void kvm_mmu_new_cr3(struct kvm_vcpu *vcpu);
 
 void kvm_enable_tdp(void);
 void kvm_disable_tdp(void);
 
-int complete_pio(struct kvm_vcpu *vcpu);
-bool kvm_check_iopl(struct kvm_vcpu *vcpu);
-
 static inline gpa_t translate_gpa(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access)
 {
 	return gpa;
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 2d89e3980cbd..5b23e605e707 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -52,12 +52,7 @@ static inline void local_sub(long i, local_t *l)
  */
 static inline int local_sub_and_test(long i, local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_SUB "%2,%0; sete %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, i, "%0", "e");
 }
 
 /**
@@ -70,12 +65,7 @@ static inline int local_sub_and_test(long i, local_t *l)
  */
 static inline int local_dec_and_test(local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_DEC "%0; sete %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", "e");
 }
 
 /**
@@ -88,12 +78,7 @@ static inline int local_dec_and_test(local_t *l)
  */
 static inline int local_inc_and_test(local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_INC "%0; sete %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : : "memory");
-	return c != 0;
+	GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", "e");
 }
 
 /**
@@ -107,12 +92,7 @@ static inline int local_inc_and_test(local_t *l)
  */
 static inline int local_add_negative(long i, local_t *l)
 {
-	unsigned char c;
-
-	asm volatile(_ASM_ADD "%2,%0; sets %1"
-		     : "+m" (l->a.counter), "=qm" (c)
-		     : "ir" (i) : "memory");
-	return c;
+	GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, i, "%0", "s");
 }
 
 /**
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index cbe6b9e404ce..c696a8687567 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -16,6 +16,7 @@
 #define MCG_EXT_CNT_SHIFT	16
 #define MCG_EXT_CNT(c)		(((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
 #define MCG_SER_P		(1ULL<<24)   /* MCA recovery/new status bits */
+#define MCG_ELOG_P		(1ULL<<26)   /* Extended error log supported */
 
 /* MCG_STATUS register defines */
 #define MCG_STATUS_RIPV  (1ULL<<0)   /* restart ip valid */
diff --git a/arch/x86/include/asm/misc.h b/arch/x86/include/asm/misc.h
new file mode 100644
index 000000000000..475f5bbc7f53
--- /dev/null
+++ b/arch/x86/include/asm/misc.h
@@ -0,0 +1,6 @@
+#ifndef _ASM_X86_MISC_H
+#define _ASM_X86_MISC_H
+
+int num_digits(int val);
+
+#endif /* _ASM_X86_MISC_H */
diff --git a/arch/x86/include/asm/mpspec.h b/arch/x86/include/asm/mpspec.h
index 626cf70082d7..3142a94c7b4b 100644
--- a/arch/x86/include/asm/mpspec.h
+++ b/arch/x86/include/asm/mpspec.h
@@ -94,7 +94,7 @@ static inline void early_reserve_e820_mpc_new(void) { }
 #define default_get_smp_config x86_init_uint_noop
 #endif
 
-void generic_processor_info(int apicid, int version);
+int generic_processor_info(int apicid, int version);
 #ifdef CONFIG_ACPI
 extern void mp_register_ioapic(int id, u32 address, u32 gsi_base);
 extern void mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h
deleted file mode 100644
index fc18bf3ce7c8..000000000000
--- a/arch/x86/include/asm/mrst.h
+++ /dev/null
@@ -1,81 +0,0 @@
-/*
- * mrst.h: Intel Moorestown platform specific setup code
- *
- * (C) Copyright 2009 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-#ifndef _ASM_X86_MRST_H
-#define _ASM_X86_MRST_H
-
-#include <linux/sfi.h>
-
-extern int pci_mrst_init(void);
-extern int __init sfi_parse_mrtc(struct sfi_table_header *table);
-extern int sfi_mrtc_num;
-extern struct sfi_rtc_table_entry sfi_mrtc_array[];
-
-/*
- * Medfield is the follow-up of Moorestown, it combines two chip solution into
- * one. Other than that it also added always-on and constant tsc and lapic
- * timers. Medfield is the platform name, and the chip name is called Penwell
- * we treat Medfield/Penwell as a variant of Moorestown. Penwell can be
- * identified via MSRs.
- */
-enum mrst_cpu_type {
-	/* 1 was Moorestown */
-	MRST_CPU_CHIP_PENWELL = 2,
-};
-
-extern enum mrst_cpu_type __mrst_cpu_chip;
-
-#ifdef CONFIG_X86_INTEL_MID
-
-static inline enum mrst_cpu_type mrst_identify_cpu(void)
-{
-	return __mrst_cpu_chip;
-}
-
-#else /* !CONFIG_X86_INTEL_MID */
-
-#define mrst_identify_cpu()    (0)
-
-#endif /* !CONFIG_X86_INTEL_MID */
-
-enum mrst_timer_options {
-	MRST_TIMER_DEFAULT,
-	MRST_TIMER_APBT_ONLY,
-	MRST_TIMER_LAPIC_APBT,
-};
-
-extern enum mrst_timer_options mrst_timer_options;
-
-/*
- * Penwell uses spread spectrum clock, so the freq number is not exactly
- * the same as reported by MSR based on SDM.
- */
-#define PENWELL_FSB_FREQ_83SKU         83200
-#define PENWELL_FSB_FREQ_100SKU        99840
-
-#define SFI_MTMR_MAX_NUM 8
-#define SFI_MRTC_MAX	8
-
-extern struct console early_mrst_console;
-extern void mrst_early_console_init(void);
-
-extern struct console early_hsu_console;
-extern void hsu_early_console_init(const char *);
-
-extern void intel_scu_devices_create(void);
-extern void intel_scu_devices_destroy(void);
-
-/* VRTC timer */
-#define MRST_VRTC_MAP_SZ	(1024)
-/*#define MRST_VRTC_PGOFFSET	(0xc00) */
-
-extern void mrst_rtc_init(void);
-
-#endif /* _ASM_X86_MRST_H */
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index cb7502852acb..e139b13f2a33 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -218,10 +218,14 @@ void msrs_free(struct msr *msrs);
 #ifdef CONFIG_SMP
 int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
+int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
+int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
 void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs);
 void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr *msrs);
 int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
 int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
+int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
+int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
 int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]);
 int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]);
 #else  /*  CONFIG_SMP  */
@@ -235,6 +239,16 @@ static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 	wrmsr(msr_no, l, h);
 	return 0;
 }
+static inline int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+{
+	rdmsrl(msr_no, *q);
+	return 0;
+}
+static inline int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+{
+	wrmsrl(msr_no, q);
+	return 0;
+}
 static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no,
 				struct msr *msrs)
 {
@@ -254,6 +268,14 @@ static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 {
 	return wrmsr_safe(msr_no, l, h);
 }
+static inline int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+{
+	return rdmsrl_safe(msr_no, q);
+}
+static inline int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+{
+	return wrmsrl_safe(msr_no, q);
+}
 static inline int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
 {
 	return rdmsr_safe_regs(regs);
diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h
index e7e6751648ed..07537a44216e 100644
--- a/arch/x86/include/asm/mutex_64.h
+++ b/arch/x86/include/asm/mutex_64.h
@@ -20,7 +20,7 @@
 static inline void __mutex_fastpath_lock(atomic_t *v,
 					 void (*fail_fn)(atomic_t *))
 {
-	asm volatile goto(LOCK_PREFIX "   decl %0\n"
+	asm_volatile_goto(LOCK_PREFIX "   decl %0\n"
 			  "   jns %l[exit]\n"
 			  : : "m" (v->counter)
 			  : "memory", "cc"
@@ -75,7 +75,7 @@ static inline int __mutex_fastpath_lock_retval(atomic_t *count)
 static inline void __mutex_fastpath_unlock(atomic_t *v,
 					   void (*fail_fn)(atomic_t *))
 {
-	asm volatile goto(LOCK_PREFIX "   incl %0\n"
+	asm_volatile_goto(LOCK_PREFIX "   incl %0\n"
 			  "   jg %l[exit]\n"
 			  : : "m" (v->counter)
 			  : "memory", "cc"
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 0da5200ee79d..94220d14d5cc 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -128,7 +128,8 @@ do {							\
 do {									\
 	typedef typeof(var) pao_T__;					\
 	const int pao_ID__ = (__builtin_constant_p(val) &&		\
-			      ((val) == 1 || (val) == -1)) ? (val) : 0;	\
+			      ((val) == 1 || (val) == -1)) ?		\
+				(int)(val) : 0;				\
 	if (0) {							\
 		pao_T__ pao_tmp__;					\
 		pao_tmp__ = (val);					\
@@ -377,9 +378,6 @@ do {									\
 #define __this_cpu_or_1(pcp, val)	percpu_to_op("or", (pcp), val)
 #define __this_cpu_or_2(pcp, val)	percpu_to_op("or", (pcp), val)
 #define __this_cpu_or_4(pcp, val)	percpu_to_op("or", (pcp), val)
-#define __this_cpu_xor_1(pcp, val)	percpu_to_op("xor", (pcp), val)
-#define __this_cpu_xor_2(pcp, val)	percpu_to_op("xor", (pcp), val)
-#define __this_cpu_xor_4(pcp, val)	percpu_to_op("xor", (pcp), val)
 #define __this_cpu_xchg_1(pcp, val)	percpu_xchg_op(pcp, val)
 #define __this_cpu_xchg_2(pcp, val)	percpu_xchg_op(pcp, val)
 #define __this_cpu_xchg_4(pcp, val)	percpu_xchg_op(pcp, val)
@@ -399,9 +397,6 @@ do {									\
 #define this_cpu_or_1(pcp, val)		percpu_to_op("or", (pcp), val)
 #define this_cpu_or_2(pcp, val)		percpu_to_op("or", (pcp), val)
 #define this_cpu_or_4(pcp, val)		percpu_to_op("or", (pcp), val)
-#define this_cpu_xor_1(pcp, val)	percpu_to_op("xor", (pcp), val)
-#define this_cpu_xor_2(pcp, val)	percpu_to_op("xor", (pcp), val)
-#define this_cpu_xor_4(pcp, val)	percpu_to_op("xor", (pcp), val)
 #define this_cpu_xchg_1(pcp, nval)	percpu_xchg_op(pcp, nval)
 #define this_cpu_xchg_2(pcp, nval)	percpu_xchg_op(pcp, nval)
 #define this_cpu_xchg_4(pcp, nval)	percpu_xchg_op(pcp, nval)
@@ -446,7 +441,6 @@ do {									\
 #define __this_cpu_add_8(pcp, val)	percpu_add_op((pcp), val)
 #define __this_cpu_and_8(pcp, val)	percpu_to_op("and", (pcp), val)
 #define __this_cpu_or_8(pcp, val)	percpu_to_op("or", (pcp), val)
-#define __this_cpu_xor_8(pcp, val)	percpu_to_op("xor", (pcp), val)
 #define __this_cpu_add_return_8(pcp, val) percpu_add_return_op(pcp, val)
 #define __this_cpu_xchg_8(pcp, nval)	percpu_xchg_op(pcp, nval)
 #define __this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
@@ -456,7 +450,6 @@ do {									\
 #define this_cpu_add_8(pcp, val)	percpu_add_op((pcp), val)
 #define this_cpu_and_8(pcp, val)	percpu_to_op("and", (pcp), val)
 #define this_cpu_or_8(pcp, val)		percpu_to_op("or", (pcp), val)
-#define this_cpu_xor_8(pcp, val)	percpu_to_op("xor", (pcp), val)
 #define this_cpu_add_return_8(pcp, val)	percpu_add_return_op(pcp, val)
 #define this_cpu_xchg_8(pcp, nval)	percpu_xchg_op(pcp, nval)
 #define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index b4389a468fb6..c4412e972bbd 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -80,12 +80,21 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 #if PAGETABLE_LEVELS > 2
 static inline pmd_t *pmd_alloc_one(struct mm_struct *mm, unsigned long addr)
 {
-	return (pmd_t *)get_zeroed_page(GFP_KERNEL|__GFP_REPEAT);
+	struct page *page;
+	page = alloc_pages(GFP_KERNEL | __GFP_REPEAT | __GFP_ZERO, 0);
+	if (!page)
+		return NULL;
+	if (!pgtable_pmd_page_ctor(page)) {
+		__free_pages(page, 0);
+		return NULL;
+	}
+	return (pmd_t *)page_address(page);
 }
 
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
 	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+	pgtable_pmd_page_dtor(virt_to_page(pmd));
 	free_page((unsigned long)pmd);
 }
 
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
new file mode 100644
index 000000000000..8729723636fd
--- /dev/null
+++ b/arch/x86/include/asm/preempt.h
@@ -0,0 +1,100 @@
+#ifndef __ASM_PREEMPT_H
+#define __ASM_PREEMPT_H
+
+#include <asm/rmwcc.h>
+#include <asm/percpu.h>
+#include <linux/thread_info.h>
+
+DECLARE_PER_CPU(int, __preempt_count);
+
+/*
+ * We mask the PREEMPT_NEED_RESCHED bit so as not to confuse all current users
+ * that think a non-zero value indicates we cannot preempt.
+ */
+static __always_inline int preempt_count(void)
+{
+	return __this_cpu_read_4(__preempt_count) & ~PREEMPT_NEED_RESCHED;
+}
+
+static __always_inline void preempt_count_set(int pc)
+{
+	__this_cpu_write_4(__preempt_count, pc);
+}
+
+/*
+ * must be macros to avoid header recursion hell
+ */
+#define task_preempt_count(p) \
+	(task_thread_info(p)->saved_preempt_count & ~PREEMPT_NEED_RESCHED)
+
+#define init_task_preempt_count(p) do { \
+	task_thread_info(p)->saved_preempt_count = PREEMPT_DISABLED; \
+} 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)
+
+/*
+ * We fold the NEED_RESCHED bit into the preempt count such that
+ * preempt_enable() can decrement and test for needing to reschedule with a
+ * single instruction.
+ *
+ * We invert the actual bit, so that when the decrement hits 0 we know we both
+ * need to resched (the bit is cleared) and can resched (no preempt count).
+ */
+
+static __always_inline void set_preempt_need_resched(void)
+{
+	__this_cpu_and_4(__preempt_count, ~PREEMPT_NEED_RESCHED);
+}
+
+static __always_inline void clear_preempt_need_resched(void)
+{
+	__this_cpu_or_4(__preempt_count, PREEMPT_NEED_RESCHED);
+}
+
+static __always_inline bool test_preempt_need_resched(void)
+{
+	return !(__this_cpu_read_4(__preempt_count) & PREEMPT_NEED_RESCHED);
+}
+
+/*
+ * The various preempt_count add/sub methods
+ */
+
+static __always_inline void __preempt_count_add(int val)
+{
+	__this_cpu_add_4(__preempt_count, val);
+}
+
+static __always_inline void __preempt_count_sub(int val)
+{
+	__this_cpu_add_4(__preempt_count, -val);
+}
+
+static __always_inline bool __preempt_count_dec_and_test(void)
+{
+	GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");
+}
+
+/*
+ * Returns true when we need to resched and can (barring IRQ state).
+ */
+static __always_inline bool should_resched(void)
+{
+	return unlikely(!__this_cpu_read_4(__preempt_count));
+}
+
+#ifdef CONFIG_PREEMPT
+  extern asmlinkage void ___preempt_schedule(void);
+# define __preempt_schedule() asm ("call ___preempt_schedule")
+  extern asmlinkage void preempt_schedule(void);
+# ifdef CONFIG_CONTEXT_TRACKING
+    extern asmlinkage void ___preempt_schedule_context(void);
+#   define __preempt_schedule_context() asm ("call ___preempt_schedule_context")
+# endif
+#endif
+
+#endif /* __ASM_PREEMPT_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 987c75ecc334..7b034a4057f9 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -488,6 +488,15 @@ struct thread_struct {
 	unsigned long		iopl;
 	/* Max allowed port in the bitmap, in bytes: */
 	unsigned		io_bitmap_max;
+	/*
+	 * fpu_counter contains the number of consecutive context switches
+	 * that the FPU is used. If this is over a threshold, the lazy fpu
+	 * saving becomes unlazy to save the trap. This is an unsigned char
+	 * so that after 256 times the counter wraps and the behavior turns
+	 * lazy again; this to deal with bursty apps that only use FPU for
+	 * a short time
+	 */
+	unsigned char fpu_counter;
 };
 
 /*
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
index bade6ac3b14f..fbeb06ed0eaa 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -39,10 +39,5 @@ static inline void x86_dtb_init(void) { }
 
 extern char cmd_line[COMMAND_LINE_SIZE];
 
-#define pci_address_to_pio pci_address_to_pio
-unsigned long pci_address_to_pio(phys_addr_t addr);
-
-#define HAVE_ARCH_DEVTREE_FIXUPS
-
 #endif /* __ASSEMBLY__ */
 #endif
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index be8269b00e2a..d6b078e9fa28 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -14,6 +14,8 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
 			    struct timespec *ts);
 void pvclock_resume(void);
 
+void pvclock_touch_watchdogs(void);
+
 /*
  * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
  * yielding a 64-bit result.
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
new file mode 100644
index 000000000000..1ff990f1de8e
--- /dev/null
+++ b/arch/x86/include/asm/rmwcc.h
@@ -0,0 +1,41 @@
+#ifndef _ASM_X86_RMWcc
+#define _ASM_X86_RMWcc
+
+#ifdef CC_HAVE_ASM_GOTO
+
+#define __GEN_RMWcc(fullop, var, cc, ...)				\
+do {									\
+	asm_volatile_goto (fullop "; j" cc " %l[cc_label]"		\
+			: : "m" (var), ## __VA_ARGS__ 			\
+			: "memory" : cc_label);				\
+	return 0;							\
+cc_label:								\
+	return 1;							\
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc) 				\
+	__GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, val, arg0, cc)			\
+	__GEN_RMWcc(op " %1, " arg0, var, cc, "er" (val))
+
+#else /* !CC_HAVE_ASM_GOTO */
+
+#define __GEN_RMWcc(fullop, var, cc, ...)				\
+do {									\
+	char c;								\
+	asm volatile (fullop "; set" cc " %1"				\
+			: "+m" (var), "=qm" (c)				\
+			: __VA_ARGS__ : "memory");			\
+	return c != 0;							\
+} while (0)
+
+#define GEN_UNARY_RMWcc(op, var, arg0, cc)				\
+	__GEN_RMWcc(op " " arg0, var, cc)
+
+#define GEN_BINARY_RMWcc(op, var, val, arg0, cc)			\
+	__GEN_RMWcc(op " %2, " arg0, var, cc, "er" (val))
+
+#endif /* CC_HAVE_ASM_GOTO */
+
+#endif /* _ASM_X86_RMWcc */
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index c48a95035a77..6f1c3a8a33ab 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -214,6 +214,9 @@
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__
 extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][2+2+5];
+#ifdef CONFIG_TRACING
+#define trace_early_idt_handlers early_idt_handlers
+#endif
 
 /*
  * Load a segment. Fall back on loading the zero
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 347555492dad..59bcf4e22418 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -51,9 +51,9 @@ extern void i386_reserve_resources(void);
 extern void setup_default_timer_irq(void);
 
 #ifdef CONFIG_X86_INTEL_MID
-extern void x86_mrst_early_setup(void);
+extern void x86_intel_mid_early_setup(void);
 #else
-static inline void x86_mrst_early_setup(void) { }
+static inline void x86_intel_mid_early_setup(void) { }
 #endif
 
 #ifdef CONFIG_X86_INTEL_CE
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 27811190cbd7..3ba3de457d05 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -28,8 +28,7 @@ struct thread_info {
 	__u32			flags;		/* low level flags */
 	__u32			status;		/* thread synchronous flags */
 	__u32			cpu;		/* current CPU */
-	int			preempt_count;	/* 0 => preemptable,
-						   <0 => BUG */
+	int			saved_preempt_count;
 	mm_segment_t		addr_limit;
 	struct restart_block    restart_block;
 	void __user		*sysenter_return;
@@ -49,7 +48,7 @@ struct thread_info {
 	.exec_domain	= &default_exec_domain,	\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.preempt_count	= INIT_PREEMPT_COUNT,	\
+	.saved_preempt_count = INIT_PREEMPT_COUNT,	\
 	.addr_limit	= KERNEL_DS,		\
 	.restart_block = {			\
 		.fn = do_no_restart_syscall,	\
@@ -154,8 +153,6 @@ struct thread_info {
 #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY)
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW)
 
-#define PREEMPT_ACTIVE		0x10000000
-
 #ifdef CONFIG_X86_32
 
 #define STACK_WARN	(THREAD_SIZE/8)
diff --git a/arch/x86/include/asm/trace/exceptions.h b/arch/x86/include/asm/trace/exceptions.h
new file mode 100644
index 000000000000..2fbc66c7885b
--- /dev/null
+++ b/arch/x86/include/asm/trace/exceptions.h
@@ -0,0 +1,52 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM exceptions
+
+#if !defined(_TRACE_PAGE_FAULT_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PAGE_FAULT_H
+
+#include <linux/tracepoint.h>
+
+extern void trace_irq_vector_regfunc(void);
+extern void trace_irq_vector_unregfunc(void);
+
+DECLARE_EVENT_CLASS(x86_exceptions,
+
+	TP_PROTO(unsigned long address, struct pt_regs *regs,
+		 unsigned long error_code),
+
+	TP_ARGS(address, regs, error_code),
+
+	TP_STRUCT__entry(
+		__field(		unsigned long, address	)
+		__field(		unsigned long, ip	)
+		__field(		unsigned long, error_code )
+	),
+
+	TP_fast_assign(
+		__entry->address = address;
+		__entry->ip = regs->ip;
+		__entry->error_code = error_code;
+	),
+
+	TP_printk("address=%pf ip=%pf error_code=0x%lx",
+		  (void *)__entry->address, (void *)__entry->ip,
+		  __entry->error_code) );
+
+#define DEFINE_PAGE_FAULT_EVENT(name)				\
+DEFINE_EVENT_FN(x86_exceptions, name,				\
+	TP_PROTO(unsigned long address,	struct pt_regs *regs,	\
+		 unsigned long error_code),			\
+	TP_ARGS(address, regs, error_code),			\
+	trace_irq_vector_regfunc,				\
+	trace_irq_vector_unregfunc);
+
+DEFINE_PAGE_FAULT_EVENT(page_fault_user);
+DEFINE_PAGE_FAULT_EVENT(page_fault_kernel);
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE exceptions
+#endif /*  _TRACE_PAGE_FAULT_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 7036cb60cd87..58d66fe06b61 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -37,6 +37,23 @@ asmlinkage void machine_check(void);
 #endif /* CONFIG_X86_MCE */
 asmlinkage void simd_coprocessor_error(void);
 
+#ifdef CONFIG_TRACING
+asmlinkage void trace_page_fault(void);
+#define trace_divide_error divide_error
+#define trace_bounds bounds
+#define trace_invalid_op invalid_op
+#define trace_device_not_available device_not_available
+#define trace_coprocessor_segment_overrun coprocessor_segment_overrun
+#define trace_invalid_TSS invalid_TSS
+#define trace_segment_not_present segment_not_present
+#define trace_general_protection general_protection
+#define trace_spurious_interrupt_bug spurious_interrupt_bug
+#define trace_coprocessor_error coprocessor_error
+#define trace_alignment_check alignment_check
+#define trace_simd_coprocessor_error simd_coprocessor_error
+#define trace_async_page_fault async_page_fault
+#endif
+
 dotraplinkage void do_divide_error(struct pt_regs *, long);
 dotraplinkage void do_debug(struct pt_regs *, long);
 dotraplinkage void do_nmi(struct pt_regs *, long);
@@ -55,6 +72,9 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *);
 #endif
 dotraplinkage void do_general_protection(struct pt_regs *, long);
 dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);
+#ifdef CONFIG_TRACING
+dotraplinkage void trace_do_page_fault(struct pt_regs *, unsigned long);
+#endif
 dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long);
 dotraplinkage void do_coprocessor_error(struct pt_regs *, long);
 dotraplinkage void do_alignment_check(struct pt_regs *, long);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 5838fa911aa0..8ec57c07b125 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -542,5 +542,103 @@ extern struct movsl_mask {
 # include <asm/uaccess_64.h>
 #endif
 
+unsigned long __must_check _copy_from_user(void *to, const void __user *from,
+					   unsigned n);
+unsigned long __must_check _copy_to_user(void __user *to, const void *from,
+					 unsigned n);
+
+#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
+# define copy_user_diag __compiletime_error
+#else
+# define copy_user_diag __compiletime_warning
+#endif
+
+extern void copy_user_diag("copy_from_user() buffer size is too small")
+copy_from_user_overflow(void);
+extern void copy_user_diag("copy_to_user() buffer size is too small")
+copy_to_user_overflow(void) __asm__("copy_from_user_overflow");
+
+#undef copy_user_diag
+
+#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
+
+extern void
+__compiletime_warning("copy_from_user() buffer size is not provably correct")
+__copy_from_user_overflow(void) __asm__("copy_from_user_overflow");
+#define __copy_from_user_overflow(size, count) __copy_from_user_overflow()
+
+extern void
+__compiletime_warning("copy_to_user() buffer size is not provably correct")
+__copy_to_user_overflow(void) __asm__("copy_from_user_overflow");
+#define __copy_to_user_overflow(size, count) __copy_to_user_overflow()
+
+#else
+
+static inline void
+__copy_from_user_overflow(int size, unsigned long count)
+{
+	WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count);
+}
+
+#define __copy_to_user_overflow __copy_from_user_overflow
+
+#endif
+
+static inline unsigned long __must_check
+copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	int sz = __compiletime_object_size(to);
+
+	might_fault();
+
+	/*
+	 * While we would like to have the compiler do the checking for us
+	 * even in the non-constant size case, any false positives there are
+	 * a problem (especially when DEBUG_STRICT_USER_COPY_CHECKS, but even
+	 * without - the [hopefully] dangerous looking nature of the warning
+	 * would make people go look at the respecitive call sites over and
+	 * over again just to find that there's no problem).
+	 *
+	 * And there are cases where it's just not realistic for the compiler
+	 * to prove the count to be in range. For example when multiple call
+	 * sites of a helper function - perhaps in different source files -
+	 * all doing proper range checking, yet the helper function not doing
+	 * so again.
+	 *
+	 * Therefore limit the compile time checking to the constant size
+	 * case, and do only runtime checking for non-constant sizes.
+	 */
+
+	if (likely(sz < 0 || sz >= n))
+		n = _copy_from_user(to, from, n);
+	else if(__builtin_constant_p(n))
+		copy_from_user_overflow();
+	else
+		__copy_from_user_overflow(sz, n);
+
+	return n;
+}
+
+static inline unsigned long __must_check
+copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	int sz = __compiletime_object_size(from);
+
+	might_fault();
+
+	/* See the comment in copy_from_user() above. */
+	if (likely(sz < 0 || sz >= n))
+		n = _copy_to_user(to, from, n);
+	else if(__builtin_constant_p(n))
+		copy_to_user_overflow();
+	else
+		__copy_to_user_overflow(sz, n);
+
+	return n;
+}
+
+#undef __copy_from_user_overflow
+#undef __copy_to_user_overflow
+
 #endif /* _ASM_X86_UACCESS_H */
 
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 7f760a9f1f61..3c03a5de64d3 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -184,33 +184,4 @@ __copy_from_user_inatomic_nocache(void *to, const void __user *from,
        return __copy_from_user_ll_nocache_nozero(to, from, n);
 }
 
-unsigned long __must_check copy_to_user(void __user *to,
-					const void *from, unsigned long n);
-unsigned long __must_check _copy_from_user(void *to,
-					  const void __user *from,
-					  unsigned long n);
-
-
-extern void copy_from_user_overflow(void)
-#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS
-	__compiletime_error("copy_from_user() buffer size is not provably correct")
-#else
-	__compiletime_warning("copy_from_user() buffer size is not provably correct")
-#endif
-;
-
-static inline unsigned long __must_check copy_from_user(void *to,
-					  const void __user *from,
-					  unsigned long n)
-{
-	int sz = __compiletime_object_size(to);
-
-	if (likely(sz == -1 || sz >= n))
-		n = _copy_from_user(to, from, n);
-	else
-		copy_from_user_overflow();
-
-	return n;
-}
-
 #endif /* _ASM_X86_UACCESS_32_H */
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 4f7923dd0007..190413d0de57 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -46,42 +46,13 @@ copy_user_generic(void *to, const void *from, unsigned len)
 }
 
 __must_check unsigned long
-_copy_to_user(void __user *to, const void *from, unsigned len);
-__must_check unsigned long
-_copy_from_user(void *to, const void __user *from, unsigned len);
-__must_check unsigned long
 copy_in_user(void __user *to, const void __user *from, unsigned len);
 
-static inline unsigned long __must_check copy_from_user(void *to,
-					  const void __user *from,
-					  unsigned long n)
-{
-	int sz = __compiletime_object_size(to);
-
-	might_fault();
-	if (likely(sz == -1 || sz >= n))
-		n = _copy_from_user(to, from, n);
-#ifdef CONFIG_DEBUG_VM
-	else
-		WARN(1, "Buffer overflow detected!\n");
-#endif
-	return n;
-}
-
 static __always_inline __must_check
-int copy_to_user(void __user *dst, const void *src, unsigned size)
-{
-	might_fault();
-
-	return _copy_to_user(dst, src, size);
-}
-
-static __always_inline __must_check
-int __copy_from_user(void *dst, const void __user *src, unsigned size)
+int __copy_from_user_nocheck(void *dst, const void __user *src, unsigned size)
 {
 	int ret = 0;
 
-	might_fault();
 	if (!__builtin_constant_p(size))
 		return copy_user_generic(dst, (__force void *)src, size);
 	switch (size) {
@@ -121,11 +92,17 @@ int __copy_from_user(void *dst, const void __user *src, unsigned size)
 }
 
 static __always_inline __must_check
-int __copy_to_user(void __user *dst, const void *src, unsigned size)
+int __copy_from_user(void *dst, const void __user *src, unsigned size)
+{
+	might_fault();
+	return __copy_from_user_nocheck(dst, src, size);
+}
+
+static __always_inline __must_check
+int __copy_to_user_nocheck(void __user *dst, const void *src, unsigned size)
 {
 	int ret = 0;
 
-	might_fault();
 	if (!__builtin_constant_p(size))
 		return copy_user_generic((__force void *)dst, src, size);
 	switch (size) {
@@ -165,6 +142,13 @@ int __copy_to_user(void __user *dst, const void *src, unsigned size)
 }
 
 static __always_inline __must_check
+int __copy_to_user(void __user *dst, const void *src, unsigned size)
+{
+	might_fault();
+	return __copy_to_user_nocheck(dst, src, size);
+}
+
+static __always_inline __must_check
 int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 {
 	int ret = 0;
@@ -220,13 +204,13 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 static __must_check __always_inline int
 __copy_from_user_inatomic(void *dst, const void __user *src, unsigned size)
 {
-	return copy_user_generic(dst, (__force const void *)src, size);
+	return __copy_from_user_nocheck(dst, (__force const void *)src, size);
 }
 
 static __must_check __always_inline int
 __copy_to_user_inatomic(void __user *dst, const void *src, unsigned size)
 {
-	return copy_user_generic((__force void *)dst, src, size);
+	return __copy_to_user_nocheck((__force void *)dst, src, size);
 }
 
 extern long __copy_user_nocache(void *dst, const void __user *src,
diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
index 6e5197910fd8..3087ea9c5f2e 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -35,7 +35,10 @@ typedef u8 uprobe_opcode_t;
 
 struct arch_uprobe {
 	u16				fixups;
-	u8				insn[MAX_UINSN_BYTES];
+	union {
+		u8			insn[MAX_UINSN_BYTES];
+		u8			ixol[MAX_UINSN_BYTES];
+	};
 #ifdef CONFIG_X86_64
 	unsigned long			rip_rela_target_address;
 #endif
@@ -49,11 +52,4 @@ struct arch_uprobe_task {
 	unsigned int			saved_tf;
 };
 
-extern int  arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm, unsigned long addr);
-extern int  arch_uprobe_pre_xol(struct arch_uprobe *aup, struct pt_regs *regs);
-extern int  arch_uprobe_post_xol(struct arch_uprobe *aup, struct pt_regs *regs);
-extern bool arch_uprobe_xol_was_trapped(struct task_struct *tsk);
-extern int  arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, void *data);
-extern void arch_uprobe_abort_xol(struct arch_uprobe *aup, struct pt_regs *regs);
-extern unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs);
 #endif	/* _ASM_UPROBES_H */
diff --git a/arch/x86/include/asm/uv/uv.h b/arch/x86/include/asm/uv/uv.h
index 062921ef34e9..6b964a0b86d1 100644
--- a/arch/x86/include/asm/uv/uv.h
+++ b/arch/x86/include/asm/uv/uv.h
@@ -12,6 +12,7 @@ extern enum uv_system_type get_uv_system_type(void);
 extern int is_uv_system(void);
 extern void uv_cpu_init(void);
 extern void uv_nmi_init(void);
+extern void uv_register_nmi_notifier(void);
 extern void uv_system_init(void);
 extern const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 						 struct mm_struct *mm,
@@ -25,6 +26,7 @@ static inline enum uv_system_type get_uv_system_type(void) { return UV_NONE; }
 static inline int is_uv_system(void)	{ return 0; }
 static inline void uv_cpu_init(void)	{ }
 static inline void uv_system_init(void)	{ }
+static inline void uv_register_nmi_notifier(void) { }
 static inline const struct cpumask *
 uv_flush_tlb_others(const struct cpumask *cpumask, struct mm_struct *mm,
 		    unsigned long start, unsigned long end, unsigned int cpu)
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 2c32df95bb78..a30836c8ac4d 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -502,8 +502,8 @@ struct uv_blade_info {
 	unsigned short	nr_online_cpus;
 	unsigned short	pnode;
 	short		memory_nid;
-	spinlock_t	nmi_lock;
-	unsigned long	nmi_count;
+	spinlock_t	nmi_lock;	/* obsolete, see uv_hub_nmi */
+	unsigned long	nmi_count;	/* obsolete, see uv_hub_nmi */
 };
 extern struct uv_blade_info *uv_blade_info;
 extern short *uv_node_to_blade;
@@ -576,6 +576,59 @@ static inline int uv_num_possible_blades(void)
 	return uv_possible_blades;
 }
 
+/* Per Hub NMI support */
+extern void uv_nmi_setup(void);
+
+/* BMC sets a bit this MMR non-zero before sending an NMI */
+#define UVH_NMI_MMR		UVH_SCRATCH5
+#define UVH_NMI_MMR_CLEAR	UVH_SCRATCH5_ALIAS
+#define UVH_NMI_MMR_SHIFT	63
+#define	UVH_NMI_MMR_TYPE	"SCRATCH5"
+
+/* Newer SMM NMI handler, not present in all systems */
+#define UVH_NMI_MMRX		UVH_EVENT_OCCURRED0
+#define UVH_NMI_MMRX_CLEAR	UVH_EVENT_OCCURRED0_ALIAS
+#define UVH_NMI_MMRX_SHIFT	(is_uv1_hub() ? \
+					UV1H_EVENT_OCCURRED0_EXTIO_INT0_SHFT :\
+					UVXH_EVENT_OCCURRED0_EXTIO_INT0_SHFT)
+#define	UVH_NMI_MMRX_TYPE	"EXTIO_INT0"
+
+/* Non-zero indicates newer SMM NMI handler present */
+#define UVH_NMI_MMRX_SUPPORTED	UVH_EXTIO_INT0_BROADCAST
+
+/* Indicates to BIOS that we want to use the newer SMM NMI handler */
+#define UVH_NMI_MMRX_REQ	UVH_SCRATCH5_ALIAS_2
+#define UVH_NMI_MMRX_REQ_SHIFT	62
+
+struct uv_hub_nmi_s {
+	raw_spinlock_t	nmi_lock;
+	atomic_t	in_nmi;		/* flag this node in UV NMI IRQ */
+	atomic_t	cpu_owner;	/* last locker of this struct */
+	atomic_t	read_mmr_count;	/* count of MMR reads */
+	atomic_t	nmi_count;	/* count of true UV NMIs */
+	unsigned long	nmi_value;	/* last value read from NMI MMR */
+};
+
+struct uv_cpu_nmi_s {
+	struct uv_hub_nmi_s	*hub;
+	atomic_t		state;
+	atomic_t		pinging;
+	int			queries;
+	int			pings;
+};
+
+DECLARE_PER_CPU(struct uv_cpu_nmi_s, __uv_cpu_nmi);
+#define uv_cpu_nmi			(__get_cpu_var(__uv_cpu_nmi))
+#define uv_hub_nmi			(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)
+
+/* uv_cpu_nmi_states */
+#define	UV_NMI_STATE_OUT		0
+#define	UV_NMI_STATE_IN			1
+#define	UV_NMI_STATE_DUMP		2
+#define	UV_NMI_STATE_DUMP_DONE		3
+
 /* Update SCIR state */
 static inline void uv_set_scir_bits(unsigned char value)
 {
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index bd5f80e58a23..e42249bcf7e1 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -461,6 +461,23 @@ union uvh_event_occurred0_u {
 
 
 /* ========================================================================= */
+/*                         UVH_EXTIO_INT0_BROADCAST                          */
+/* ========================================================================= */
+#define UVH_EXTIO_INT0_BROADCAST 0x61448UL
+#define UVH_EXTIO_INT0_BROADCAST_32 0x3f0
+
+#define UVH_EXTIO_INT0_BROADCAST_ENABLE_SHFT		0
+#define UVH_EXTIO_INT0_BROADCAST_ENABLE_MASK		0x0000000000000001UL
+
+union uvh_extio_int0_broadcast_u {
+	unsigned long	v;
+	struct uvh_extio_int0_broadcast_s {
+		unsigned long	enable:1;			/* RW */
+		unsigned long	rsvd_1_63:63;
+	} s;
+};
+
+/* ========================================================================= */
 /*                         UVH_GR0_TLB_INT0_CONFIG                           */
 /* ========================================================================= */
 #define UVH_GR0_TLB_INT0_CONFIG 0x61b00UL
@@ -2606,6 +2623,20 @@ union uvh_scratch5_u {
 };
 
 /* ========================================================================= */
+/*                            UVH_SCRATCH5_ALIAS                             */
+/* ========================================================================= */
+#define UVH_SCRATCH5_ALIAS 0x2d0208UL
+#define UVH_SCRATCH5_ALIAS_32 0x780
+
+
+/* ========================================================================= */
+/*                           UVH_SCRATCH5_ALIAS_2                            */
+/* ========================================================================= */
+#define UVH_SCRATCH5_ALIAS_2 0x2d0210UL
+#define UVH_SCRATCH5_ALIAS_2_32 0x788
+
+
+/* ========================================================================= */
 /*                          UVXH_EVENT_OCCURRED2                             */
 /* ========================================================================= */
 #define UVXH_EVENT_OCCURRED2 0x70100UL
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 828a1565ba57..0f1be11e43d2 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -172,6 +172,7 @@ struct x86_platform_ops {
 
 struct pci_dev;
 struct msi_msg;
+struct msi_desc;
 
 struct x86_msi_ops {
 	int (*setup_msi_irqs)(struct pci_dev *dev, int nvec, int type);
@@ -182,6 +183,8 @@ struct x86_msi_ops {
 	void (*teardown_msi_irqs)(struct pci_dev *dev);
 	void (*restore_msi_irqs)(struct pci_dev *dev, int irq);
 	int  (*setup_hpet_msi)(unsigned int irq, unsigned int id);
+	u32 (*msi_mask_irq)(struct msi_desc *desc, u32 mask, u32 flag);
+	u32 (*msix_mask_irq)(struct msi_desc *desc, u32 flag);
 };
 
 struct IO_APIC_route_entry;
diff --git a/arch/x86/include/asm/xen/page-coherent.h b/arch/x86/include/asm/xen/page-coherent.h
new file mode 100644
index 000000000000..7f02fe4e2c7b
--- /dev/null
+++ b/arch/x86/include/asm/xen/page-coherent.h
@@ -0,0 +1,38 @@
+#ifndef _ASM_X86_XEN_PAGE_COHERENT_H
+#define _ASM_X86_XEN_PAGE_COHERENT_H
+
+#include <asm/page.h>
+#include <linux/dma-attrs.h>
+#include <linux/dma-mapping.h>
+
+static inline void *xen_alloc_coherent_pages(struct device *hwdev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flags,
+		struct dma_attrs *attrs)
+{
+	void *vstart = (void*)__get_free_pages(flags, get_order(size));
+	*dma_handle = virt_to_phys(vstart);
+	return vstart;
+}
+
+static inline void xen_free_coherent_pages(struct device *hwdev, size_t size,
+		void *cpu_addr, dma_addr_t dma_handle,
+		struct dma_attrs *attrs)
+{
+	free_pages((unsigned long) cpu_addr, get_order(size));
+}
+
+static inline void xen_dma_map_page(struct device *hwdev, struct page *page,
+	     unsigned long offset, size_t size, enum dma_data_direction dir,
+	     struct dma_attrs *attrs) { }
+
+static inline void xen_dma_unmap_page(struct device *hwdev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir,
+		struct dma_attrs *attrs) { }
+
+static inline void xen_dma_sync_single_for_cpu(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir) { }
+
+static inline void xen_dma_sync_single_for_device(struct device *hwdev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir) { }
+
+#endif /* _ASM_X86_XEN_PAGE_COHERENT_H */
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index 6aef9fbc09b7..b913915e8e63 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -79,30 +79,38 @@ static inline int phys_to_machine_mapping_valid(unsigned long pfn)
 	return get_phys_to_machine(pfn) != INVALID_P2M_ENTRY;
 }
 
-static inline unsigned long mfn_to_pfn(unsigned long mfn)
+static inline unsigned long mfn_to_pfn_no_overrides(unsigned long mfn)
 {
 	unsigned long pfn;
-	int ret = 0;
+	int ret;
 
 	if (xen_feature(XENFEAT_auto_translated_physmap))
 		return mfn;
 
-	if (unlikely(mfn >= machine_to_phys_nr)) {
-		pfn = ~0;
-		goto try_override;
-	}
-	pfn = 0;
+	if (unlikely(mfn >= machine_to_phys_nr))
+		return ~0;
+
 	/*
 	 * The array access can fail (e.g., device space beyond end of RAM).
 	 * In such cases it doesn't matter what we return (we return garbage),
 	 * but we must handle the fault without crashing!
 	 */
 	ret = __get_user(pfn, &machine_to_phys_mapping[mfn]);
-try_override:
-	/* ret might be < 0 if there are no entries in the m2p for mfn */
 	if (ret < 0)
-		pfn = ~0;
-	else if (get_phys_to_machine(pfn) != mfn)
+		return ~0;
+
+	return pfn;
+}
+
+static inline unsigned long mfn_to_pfn(unsigned long mfn)
+{
+	unsigned long pfn;
+
+	if (xen_feature(XENFEAT_auto_translated_physmap))
+		return mfn;
+
+	pfn = mfn_to_pfn_no_overrides(mfn);
+	if (get_phys_to_machine(pfn) != mfn) {
 		/*
 		 * If this appears to be a foreign mfn (because the pfn
 		 * doesn't map back to the mfn), then check the local override
@@ -111,6 +119,7 @@ try_override:
 		 * m2p_find_override_pfn returns ~0 if it doesn't find anything.
 		 */
 		pfn = m2p_find_override_pfn(mfn, ~0);
+	}
 
 	/* 
 	 * pfn is ~0 if there are no entries in the m2p for mfn or if the