Merge remote-tracking branch 'origin' into irqdomain/next

32 files changed, 277 insertions, 199 deletions

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 49331bedc15..70780689599 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -75,23 +75,54 @@ static inline int alternatives_text_reserved(void *start, void *end)
 }
 #endif	/* CONFIG_SMP */
 
+#define OLDINSTR(oldinstr)	"661:\n\t" oldinstr "\n662:\n"
+
+#define b_replacement(number)	"663"#number
+#define e_replacement(number)	"664"#number
+
+#define alt_slen "662b-661b"
+#define alt_rlen(number) e_replacement(number)"f-"b_replacement(number)"f"
+
+#define ALTINSTR_ENTRY(feature, number)					      \
+	" .long 661b - .\n"				/* label           */ \
+	" .long " b_replacement(number)"f - .\n"	/* new instruction */ \
+	" .word " __stringify(feature) "\n"		/* feature bit     */ \
+	" .byte " alt_slen "\n"				/* source len      */ \
+	" .byte " alt_rlen(number) "\n"			/* replacement len */
+
+#define DISCARD_ENTRY(number)				/* rlen <= slen */    \
+	" .byte 0xff + (" alt_rlen(number) ") - (" alt_slen ")\n"
+
+#define ALTINSTR_REPLACEMENT(newinstr, feature, number)	/* replacement */     \
+	b_replacement(number)":\n\t" newinstr "\n" e_replacement(number) ":\n\t"
+
 /* alternative assembly primitive: */
 #define ALTERNATIVE(oldinstr, newinstr, feature)			\
-									\
-      "661:\n\t" oldinstr "\n662:\n"					\
-      ".section .altinstructions,\"a\"\n"				\
-      "	 .long 661b - .\n"			/* label           */	\
-      "	 .long 663f - .\n"			/* new instruction */	\
-      "	 .word " __stringify(feature) "\n"	/* feature bit     */	\
-      "	 .byte 662b-661b\n"			/* sourcelen       */	\
-      "	 .byte 664f-663f\n"			/* replacementlen  */	\
-      ".previous\n"							\
-      ".section .discard,\"aw\",@progbits\n"				\
-      "	 .byte 0xff + (664f-663f) - (662b-661b)\n" /* rlen <= slen */	\
-      ".previous\n"							\
-      ".section .altinstr_replacement, \"ax\"\n"			\
-      "663:\n\t" newinstr "\n664:\n"		/* replacement     */	\
-      ".previous"
+	OLDINSTR(oldinstr)						\
+	".section .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY(feature, 1)					\
+	".previous\n"							\
+	".section .discard,\"aw\",@progbits\n"				\
+	DISCARD_ENTRY(1)						\
+	".previous\n"							\
+	".section .altinstr_replacement, \"ax\"\n"			\
+	ALTINSTR_REPLACEMENT(newinstr, feature, 1)			\
+	".previous"
+
+#define ALTERNATIVE_2(oldinstr, newinstr1, feature1, newinstr2, feature2)\
+	OLDINSTR(oldinstr)						\
+	".section .altinstructions,\"a\"\n"				\
+	ALTINSTR_ENTRY(feature1, 1)					\
+	ALTINSTR_ENTRY(feature2, 2)					\
+	".previous\n"							\
+	".section .discard,\"aw\",@progbits\n"				\
+	DISCARD_ENTRY(1)						\
+	DISCARD_ENTRY(2)						\
+	".previous\n"							\
+	".section .altinstr_replacement, \"ax\"\n"			\
+	ALTINSTR_REPLACEMENT(newinstr1, feature1, 1)			\
+	ALTINSTR_REPLACEMENT(newinstr2, feature2, 2)			\
+	".previous"
 
 /*
  * This must be included *after* the definition of ALTERNATIVE due to
@@ -140,6 +171,19 @@ static inline int alternatives_text_reserved(void *start, void *end)
 		: output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
 
 /*
+ * Like alternative_call, but there are two features and respective functions.
+ * If CPU has feature2, function2 is used.
+ * Otherwise, if CPU has feature1, function1 is used.
+ * Otherwise, old function is used.
+ */
+#define alternative_call_2(oldfunc, newfunc1, feature1, newfunc2, feature2,   \
+			   output, input...)				      \
+	asm volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", feature1,\
+		"call %P[new2]", feature2)				      \
+		: output : [old] "i" (oldfunc), [new1] "i" (newfunc1),	      \
+		[new2] "i" (newfunc2), ## input)
+
+/*
  * use this macro(s) if you need more than one output parameter
  * in alternative_io
  */
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h
index 49ad773f4b9..b3341e9cd8f 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd_nb.h
@@ -26,10 +26,31 @@ struct amd_l3_cache {
 	u8	 subcaches[4];
 };
 
+struct threshold_block {
+	unsigned int		block;
+	unsigned int		bank;
+	unsigned int		cpu;
+	u32			address;
+	u16			interrupt_enable;
+	bool			interrupt_capable;
+	u16			threshold_limit;
+	struct kobject		kobj;
+	struct list_head	miscj;
+};
+
+struct threshold_bank {
+	struct kobject		*kobj;
+	struct threshold_block	*blocks;
+
+	/* initialized to the number of CPUs on the node sharing this bank */
+	atomic_t		cpus;
+};
+
 struct amd_northbridge {
 	struct pci_dev *misc;
 	struct pci_dev *link;
 	struct amd_l3_cache l3_cache;
+	struct threshold_bank *bank4;
 };
 
 struct amd_northbridge_info {
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index eaff4790ed9..3ea51a84a0e 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -306,7 +306,8 @@ struct apic {
 	unsigned long (*check_apicid_used)(physid_mask_t *map, int apicid);
 	unsigned long (*check_apicid_present)(int apicid);
 
-	void (*vector_allocation_domain)(int cpu, struct cpumask *retmask);
+	void (*vector_allocation_domain)(int cpu, struct cpumask *retmask,
+					 const struct cpumask *mask);
 	void (*init_apic_ldr)(void);
 
 	void (*ioapic_phys_id_map)(physid_mask_t *phys_map, physid_mask_t *retmap);
@@ -331,9 +332,9 @@ struct apic {
 	unsigned long (*set_apic_id)(unsigned int id);
 	unsigned long apic_id_mask;
 
-	unsigned int (*cpu_mask_to_apicid)(const struct cpumask *cpumask);
-	unsigned int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
-					       const struct cpumask *andmask);
+	int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
+				      const struct cpumask *andmask,
+				      unsigned int *apicid);
 
 	/* ipi */
 	void (*send_IPI_mask)(const struct cpumask *mask, int vector);
@@ -464,6 +465,8 @@ static inline u32 safe_apic_wait_icr_idle(void)
 	return apic->safe_wait_icr_idle();
 }
 
+extern void __init apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v));
+
 #else /* CONFIG_X86_LOCAL_APIC */
 
 static inline u32 apic_read(u32 reg) { return 0; }
@@ -473,6 +476,7 @@ static inline u64 apic_icr_read(void) { return 0; }
 static inline void apic_icr_write(u32 low, u32 high) { }
 static inline void apic_wait_icr_idle(void) { }
 static inline u32 safe_apic_wait_icr_idle(void) { return 0; }
+static inline void apic_set_eoi_write(void (*eoi_write)(u32 reg, u32 v)) {}
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
@@ -537,6 +541,11 @@ static inline const struct cpumask *default_target_cpus(void)
 #endif
 }
 
+static inline const struct cpumask *online_target_cpus(void)
+{
+	return cpu_online_mask;
+}
+
 DECLARE_EARLY_PER_CPU(u16, x86_bios_cpu_apicid);
 
 
@@ -586,21 +595,50 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb)
 
 #endif
 
-static inline unsigned int
-default_cpu_mask_to_apicid(const struct cpumask *cpumask)
+static inline int
+flat_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
+			    const struct cpumask *andmask,
+			    unsigned int *apicid)
 {
-	return cpumask_bits(cpumask)[0] & APIC_ALL_CPUS;
+	unsigned long cpu_mask = cpumask_bits(cpumask)[0] &
+				 cpumask_bits(andmask)[0] &
+				 cpumask_bits(cpu_online_mask)[0] &
+				 APIC_ALL_CPUS;
+
+	if (likely(cpu_mask)) {
+		*apicid = (unsigned int)cpu_mask;
+		return 0;
+	} else {
+		return -EINVAL;
+	}
 }
 
-static inline unsigned int
+extern int
 default_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
-			       const struct cpumask *andmask)
+			       const struct cpumask *andmask,
+			       unsigned int *apicid);
+
+static inline void
+flat_vector_allocation_domain(int cpu, struct cpumask *retmask,
+			      const struct cpumask *mask)
 {
-	unsigned long mask1 = cpumask_bits(cpumask)[0];
-	unsigned long mask2 = cpumask_bits(andmask)[0];
-	unsigned long mask3 = cpumask_bits(cpu_online_mask)[0];
+	/* Careful. Some cpus do not strictly honor the set of cpus
+	 * specified in the interrupt destination when using lowest
+	 * priority interrupt delivery mode.
+	 *
+	 * In particular there was a hyperthreading cpu observed to
+	 * deliver interrupts to the wrong hyperthread when only one
+	 * hyperthread was specified in the interrupt desitination.
+	 */
+	cpumask_clear(retmask);
+	cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
+}
 
-	return (unsigned int)(mask1 & mask2 & mask3);
+static inline void
+default_vector_allocation_domain(int cpu, struct cpumask *retmask,
+				 const struct cpumask *mask)
+{
+	cpumask_copy(retmask, cpumask_of(cpu));
 }
 
 static inline unsigned long default_check_apicid_used(physid_mask_t *map, int apicid)
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index a6983b27722..72f5009deb5 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -264,6 +264,13 @@ static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
  * This operation is non-atomic and can be reordered.
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
+ *
+ * Note: the operation is performed atomically with respect to
+ * the local CPU, but not other CPUs. Portable code should not
+ * rely on this behaviour.
+ * KVM relies on this behaviour on x86 for modifying memory that is also
+ * accessed from a hypervisor on the same CPU if running in a VM: don't change
+ * this without also updating arch/x86/kernel/kvm.c
  */
 static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr)
 {
diff --git a/arch/x86/include/asm/emergency-restart.h b/arch/x86/include/asm/emergency-restart.h
index cc70c1c78ca..75ce3f47d20 100644
--- a/arch/x86/include/asm/emergency-restart.h
+++ b/arch/x86/include/asm/emergency-restart.h
@@ -4,9 +4,7 @@
 enum reboot_type {
 	BOOT_TRIPLE = 't',
 	BOOT_KBD = 'k',
-#ifdef CONFIG_X86_32
 	BOOT_BIOS = 'b',
-#endif
 	BOOT_ACPI = 'a',
 	BOOT_EFI = 'e',
 	BOOT_CF9 = 'p',
diff --git a/arch/x86/include/asm/floppy.h b/arch/x86/include/asm/floppy.h
index dbe82a5c5ea..d3d74698dce 100644
--- a/arch/x86/include/asm/floppy.h
+++ b/arch/x86/include/asm/floppy.h
@@ -99,7 +99,7 @@ static irqreturn_t floppy_hardint(int irq, void *dev_id)
 		virtual_dma_residue += virtual_dma_count;
 		virtual_dma_count = 0;
 #ifdef TRACE_FLPY_INT
-		printk("count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n",
+		printk(KERN_DEBUG "count=%x, residue=%x calls=%d bytes=%d dma_wait=%d\n",
 		       virtual_dma_count, virtual_dma_residue, calls, bytes,
 		       dma_wait);
 		calls = 0;
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
index 7a15153c675..b518c750993 100644
--- a/arch/x86/include/asm/hypervisor.h
+++ b/arch/x86/include/asm/hypervisor.h
@@ -49,6 +49,7 @@ extern const struct hypervisor_x86 *x86_hyper;
 extern const struct hypervisor_x86 x86_hyper_vmware;
 extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
 extern const struct hypervisor_x86 x86_hyper_xen_hvm;
+extern const struct hypervisor_x86 x86_hyper_kvm;
 
 static inline bool hypervisor_x2apic_available(void)
 {
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index dffc38ee625..345c99cef15 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -5,7 +5,6 @@ extern struct dma_map_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
 extern int iommu_pass_through;
-extern int iommu_group_mf;
 
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index e7d1c194d27..246617efd67 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -12,6 +12,7 @@
 /* Select x86 specific features in <linux/kvm.h> */
 #define __KVM_HAVE_PIT
 #define __KVM_HAVE_IOAPIC
+#define __KVM_HAVE_IRQ_LINE
 #define __KVM_HAVE_DEVICE_ASSIGNMENT
 #define __KVM_HAVE_MSI
 #define __KVM_HAVE_USER_NMI
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 1ac46c22dd5..c764f43b71c 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -192,8 +192,8 @@ struct x86_emulate_ops {
 			 struct x86_instruction_info *info,
 			 enum x86_intercept_stage stage);
 
-	bool (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
-			 u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
+	void (*get_cpuid)(struct x86_emulate_ctxt *ctxt,
+			  u32 *eax, u32 *ebx, u32 *ecx, u32 *edx);
 };
 
 typedef u32 __attribute__((vector_size(16))) sse128_t;
@@ -280,9 +280,9 @@ struct x86_emulate_ctxt {
 	u8 modrm_seg;
 	bool rip_relative;
 	unsigned long _eip;
+	struct operand memop;
 	/* Fields above regs are cleared together. */
 	unsigned long regs[NR_VCPU_REGS];
-	struct operand memop;
 	struct operand *memopp;
 	struct fetch_cache fetch;
 	struct read_cache io_read;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index db7c1f2709a..09155d64cf7 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -48,12 +48,13 @@
 
 #define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1)
 #define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD))
+#define CR3_PCID_ENABLED_RESERVED_BITS 0xFFFFFF0000000000ULL
 #define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS |	\
 				  0xFFFFFF0000000000ULL)
 #define CR4_RESERVED_BITS                                               \
 	(~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\
 			  | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE     \
-			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR  \
+			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
 			  | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_RDWRGSFS \
 			  | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
 
@@ -175,6 +176,13 @@ enum {
 
 /* apic attention bits */
 #define KVM_APIC_CHECK_VAPIC	0
+/*
+ * The following bit is set with PV-EOI, unset on EOI.
+ * We detect PV-EOI changes by guest by comparing
+ * this bit with PV-EOI in guest memory.
+ * See the implementation in apic_update_pv_eoi.
+ */
+#define KVM_APIC_PV_EOI_PENDING	1
 
 /*
  * We don't want allocation failures within the mmu code, so we preallocate
@@ -313,8 +321,8 @@ struct kvm_pmu {
 	u64 counter_bitmask[2];
 	u64 global_ctrl_mask;
 	u8 version;
-	struct kvm_pmc gp_counters[X86_PMC_MAX_GENERIC];
-	struct kvm_pmc fixed_counters[X86_PMC_MAX_FIXED];
+	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
+	struct kvm_pmc fixed_counters[INTEL_PMC_MAX_FIXED];
 	struct irq_work irq_work;
 	u64 reprogram_pmi;
 };
@@ -484,6 +492,11 @@ struct kvm_vcpu_arch {
 		u64 length;
 		u64 status;
 	} osvw;
+
+	struct {
+		u64 msr_val;
+		struct gfn_to_hva_cache data;
+	} pv_eoi;
 };
 
 struct kvm_lpage_info {
@@ -661,6 +674,7 @@ struct kvm_x86_ops {
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
 	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 (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
@@ -802,7 +816,20 @@ int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
 void kvm_propagate_fault(struct kvm_vcpu *vcpu, struct x86_exception *fault);
 bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
 
-int kvm_pic_set_irq(void *opaque, int irq, int level);
+static inline int __kvm_irq_line_state(unsigned long *irq_state,
+				       int irq_source_id, int level)
+{
+	/* Logical OR for level trig interrupt */
+	if (level)
+		__set_bit(irq_source_id, irq_state);
+	else
+		__clear_bit(irq_source_id, irq_state);
+
+	return !!(*irq_state);
+}
+
+int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level);
+void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
 
 void kvm_inject_nmi(struct kvm_vcpu *vcpu);
 
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 63ab1661d00..2f7712e08b1 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -22,6 +22,7 @@
 #define KVM_FEATURE_CLOCKSOURCE2        3
 #define KVM_FEATURE_ASYNC_PF		4
 #define KVM_FEATURE_STEAL_TIME		5
+#define KVM_FEATURE_PV_EOI		6
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
@@ -37,6 +38,7 @@
 #define MSR_KVM_SYSTEM_TIME_NEW 0x4b564d01
 #define MSR_KVM_ASYNC_PF_EN 0x4b564d02
 #define MSR_KVM_STEAL_TIME  0x4b564d03
+#define MSR_KVM_PV_EOI_EN      0x4b564d04
 
 struct kvm_steal_time {
 	__u64 steal;
@@ -89,6 +91,11 @@ struct kvm_vcpu_pv_apf_data {
 	__u32 enabled;
 };
 
+#define KVM_PV_EOI_BIT 0
+#define KVM_PV_EOI_MASK (0x1 << KVM_PV_EOI_BIT)
+#define KVM_PV_EOI_ENABLED KVM_PV_EOI_MASK
+#define KVM_PV_EOI_DISABLED 0x0
+
 #ifdef __KERNEL__
 #include <asm/processor.h>
 
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 084ef95274c..813ed103f45 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -115,8 +115,8 @@ notrace static inline int native_write_msr_safe(unsigned int msr,
 
 extern unsigned long long native_read_tsc(void);
 
-extern int native_rdmsr_safe_regs(u32 regs[8]);
-extern int native_wrmsr_safe_regs(u32 regs[8]);
+extern int rdmsr_safe_regs(u32 regs[8]);
+extern int wrmsr_safe_regs(u32 regs[8]);
 
 static __always_inline unsigned long long __native_read_tsc(void)
 {
@@ -187,43 +187,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
 	return err;
 }
 
-static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
-{
-	u32 gprs[8] = { 0 };
-	int err;
-
-	gprs[1] = msr;
-	gprs[7] = 0x9c5a203a;
-
-	err = native_rdmsr_safe_regs(gprs);
-
-	*p = gprs[0] | ((u64)gprs[2] << 32);
-
-	return err;
-}
-
-static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
-{
-	u32 gprs[8] = { 0 };
-
-	gprs[0] = (u32)val;
-	gprs[1] = msr;
-	gprs[2] = val >> 32;
-	gprs[7] = 0x9c5a203a;
-
-	return native_wrmsr_safe_regs(gprs);
-}
-
-static inline int rdmsr_safe_regs(u32 regs[8])
-{
-	return native_rdmsr_safe_regs(regs);
-}
-
-static inline int wrmsr_safe_regs(u32 regs[8])
-{
-	return native_wrmsr_safe_regs(regs);
-}
-
 #define rdtscl(low)						\
 	((low) = (u32)__native_read_tsc())
 
@@ -237,6 +200,8 @@ do {							\
 	(high) = (u32)(_l >> 32);			\
 } while (0)
 
+#define rdpmcl(counter, val) ((val) = native_read_pmc(counter))
+
 #define rdtscp(low, high, aux)					\
 do {                                                            \
 	unsigned long long _val = native_read_tscp(&(aux));     \
@@ -248,8 +213,7 @@ do {                                                            \
 
 #endif	/* !CONFIG_PARAVIRT */
 
-
-#define checking_wrmsrl(msr, val) wrmsr_safe((msr), (u32)(val),		\
+#define wrmsrl_safe(msr, val) wrmsr_safe((msr), (u32)(val),		\
 					     (u32)((val) >> 32))
 
 #define write_tsc(val1, val2) wrmsr(MSR_IA32_TSC, (val1), (val2))
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index dc580c42851..c0fa356e90d 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -44,28 +44,14 @@ struct nmiaction {
 	const char		*name;
 };
 
-#define register_nmi_handler(t, fn, fg, n)		\
+#define register_nmi_handler(t, fn, fg, n, init...)	\
 ({							\
-	static struct nmiaction fn##_na = {		\
+	static struct nmiaction init fn##_na = {	\
 		.handler = (fn),			\
 		.name = (n),				\
 		.flags = (fg),				\
 	};						\
-	__register_nmi_handler((t), &fn##_na);	\
-})
-
-/*
- * For special handlers that register/unregister in the
- * init section only.  This should be considered rare.
- */
-#define register_nmi_handler_initonly(t, fn, fg, n)		\
-({							\
-	static struct nmiaction fn##_na __initdata = {		\
-		.handler = (fn),			\
-		.name = (n),				\
-		.flags = (fg),				\
-	};						\
-	__register_nmi_handler((t), &fn##_na);	\
+	__register_nmi_handler((t), &fn##_na);		\
 })
 
 int __register_nmi_handler(unsigned int, struct nmiaction *);
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 6cbbabf5270..0b47ddb6f00 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -128,21 +128,11 @@ static inline u64 paravirt_read_msr(unsigned msr, int *err)
 	return PVOP_CALL2(u64, pv_cpu_ops.read_msr, msr, err);
 }
 
-static inline int paravirt_rdmsr_regs(u32 *regs)
-{
-	return PVOP_CALL1(int, pv_cpu_ops.rdmsr_regs, regs);
-}
-
 static inline int paravirt_write_msr(unsigned msr, unsigned low, unsigned high)
 {
 	return PVOP_CALL3(int, pv_cpu_ops.write_msr, msr, low, high);
 }
 
-static inline int paravirt_wrmsr_regs(u32 *regs)
-{
-	return PVOP_CALL1(int, pv_cpu_ops.wrmsr_regs, regs);
-}
-
 /* These should all do BUG_ON(_err), but our headers are too tangled. */
 #define rdmsr(msr, val1, val2)			\
 do {						\
@@ -176,9 +166,6 @@ do {						\
 	_err;					\
 })
 
-#define rdmsr_safe_regs(regs)	paravirt_rdmsr_regs(regs)
-#define wrmsr_safe_regs(regs)	paravirt_wrmsr_regs(regs)
-
 static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
 {
 	int err;
@@ -186,32 +173,6 @@ static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
 	*p = paravirt_read_msr(msr, &err);
 	return err;
 }
-static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
-{
-	u32 gprs[8] = { 0 };
-	int err;
-
-	gprs[1] = msr;
-	gprs[7] = 0x9c5a203a;
-
-	err = paravirt_rdmsr_regs(gprs);
-
-	*p = gprs[0] | ((u64)gprs[2] << 32);
-
-	return err;
-}
-
-static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
-{
-	u32 gprs[8] = { 0 };
-
-	gprs[0] = (u32)val;
-	gprs[1] = msr;
-	gprs[2] = val >> 32;
-	gprs[7] = 0x9c5a203a;
-
-	return paravirt_wrmsr_regs(gprs);
-}
 
 static inline u64 paravirt_read_tsc(void)
 {
@@ -252,6 +213,8 @@ do {						\
 	high = _l >> 32;			\
 } while (0)
 
+#define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter))
+
 static inline unsigned long long paravirt_rdtscp(unsigned int *aux)
 {
 	return PVOP_CALL1(u64, pv_cpu_ops.read_tscp, aux);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 8e8b9a4987e..8613cbb7ba4 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -153,9 +153,7 @@ struct pv_cpu_ops {
 	/* MSR, PMC and TSR operations.
 	   err = 0/-EFAULT.  wrmsr returns 0/-EFAULT. */
 	u64 (*read_msr)(unsigned int msr, int *err);
-	int (*rdmsr_regs)(u32 *regs);
 	int (*write_msr)(unsigned int msr, unsigned low, unsigned high);
-	int (*wrmsr_regs)(u32 *regs);
 
 	u64 (*read_tsc)(void);
 	u64 (*read_pmc)(int counter);
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index b3a53174602..73e8eeff22e 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -7,9 +7,13 @@
 #undef DEBUG
 
 #ifdef DEBUG
-#define DBG(x...) printk(x)
+#define DBG(fmt, ...) printk(fmt, ##__VA_ARGS__)
 #else
-#define DBG(x...)
+#define DBG(fmt, ...)				\
+do {						\
+	if (0)					\
+		printk(fmt, ##__VA_ARGS__);	\
+} while (0)
 #endif
 
 #define PCI_PROBE_BIOS		0x0001
@@ -100,6 +104,7 @@ struct pci_raw_ops {
 extern const struct pci_raw_ops *raw_pci_ops;
 extern const struct pci_raw_ops *raw_pci_ext_ops;
 
+extern const struct pci_raw_ops pci_mmcfg;
 extern const struct pci_raw_ops pci_direct_conf1;
 extern bool port_cf9_safe;
 
@@ -135,6 +140,12 @@ struct pci_mmcfg_region {
 
 extern int __init pci_mmcfg_arch_init(void);
 extern void __init pci_mmcfg_arch_free(void);
+extern int __devinit pci_mmcfg_arch_map(struct pci_mmcfg_region *cfg);
+extern void pci_mmcfg_arch_unmap(struct pci_mmcfg_region *cfg);
+extern int __devinit pci_mmconfig_insert(struct device *dev,
+					 u16 seg, u8 start,
+					 u8 end, phys_addr_t addr);
+extern int pci_mmconfig_delete(u16 seg, u8 start, u8 end);
 extern struct pci_mmcfg_region *pci_mmconfig_lookup(int segment, int bus);
 
 extern struct list_head pci_mmcfg_list;
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 588f52ea810..c78f14a0df0 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -5,11 +5,10 @@
  * Performance event hw details:
  */
 
-#define X86_PMC_MAX_GENERIC				       32
-#define X86_PMC_MAX_FIXED					3
+#define INTEL_PMC_MAX_GENERIC				       32
+#define INTEL_PMC_MAX_FIXED					3
+#define INTEL_PMC_IDX_FIXED				       32
 
-#define X86_PMC_IDX_GENERIC				        0
-#define X86_PMC_IDX_FIXED				       32
 #define X86_PMC_IDX_MAX					       64
 
 #define MSR_ARCH_PERFMON_PERFCTR0			      0xc1
@@ -48,8 +47,7 @@
 	(X86_RAW_EVENT_MASK          |  \
 	 AMD64_EVENTSEL_EVENT)
 #define AMD64_NUM_COUNTERS				4
-#define AMD64_NUM_COUNTERS_F15H				6
-#define AMD64_NUM_COUNTERS_MAX				AMD64_NUM_COUNTERS_F15H
+#define AMD64_NUM_COUNTERS_CORE				6
 
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_SEL		0x3c
 #define ARCH_PERFMON_UNHALTED_CORE_CYCLES_UMASK		(0x00 << 8)
@@ -121,16 +119,16 @@ struct x86_pmu_capability {
 
 /* Instr_Retired.Any: */
 #define MSR_ARCH_PERFMON_FIXED_CTR0	0x309
-#define X86_PMC_IDX_FIXED_INSTRUCTIONS	(X86_PMC_IDX_FIXED + 0)
+#define INTEL_PMC_IDX_FIXED_INSTRUCTIONS	(INTEL_PMC_IDX_FIXED + 0)
 
 /* CPU_CLK_Unhalted.Core: */
 #define MSR_ARCH_PERFMON_FIXED_CTR1	0x30a
-#define X86_PMC_IDX_FIXED_CPU_CYCLES	(X86_PMC_IDX_FIXED + 1)
+#define INTEL_PMC_IDX_FIXED_CPU_CYCLES	(INTEL_PMC_IDX_FIXED + 1)
 
 /* CPU_CLK_Unhalted.Ref: */
 #define MSR_ARCH_PERFMON_FIXED_CTR2	0x30b
-#define X86_PMC_IDX_FIXED_REF_CYCLES	(X86_PMC_IDX_FIXED + 2)
-#define X86_PMC_MSK_FIXED_REF_CYCLES	(1ULL << X86_PMC_IDX_FIXED_REF_CYCLES)
+#define INTEL_PMC_IDX_FIXED_REF_CYCLES	(INTEL_PMC_IDX_FIXED + 2)
+#define INTEL_PMC_MSK_FIXED_REF_CYCLES	(1ULL << INTEL_PMC_IDX_FIXED_REF_CYCLES)
 
 /*
  * We model BTS tracing as another fixed-mode PMC.
@@ -139,7 +137,7 @@ struct x86_pmu_capability {
  * values are used by actual fixed events and higher values are used
  * to indicate other overflow conditions in the PERF_GLOBAL_STATUS msr.
  */
-#define X86_PMC_IDX_FIXED_BTS				(X86_PMC_IDX_FIXED + 16)
+#define INTEL_PMC_IDX_FIXED_BTS				(INTEL_PMC_IDX_FIXED + 16)
 
 /*
  * IBS cpuid feature detection
@@ -234,6 +232,7 @@ struct perf_guest_switch_msr {
 
 extern struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr);
 extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap);
+extern void perf_check_microcode(void);
 #else
 static inline perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
 {
@@ -247,6 +246,7 @@ static inline void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
 }
 
 static inline void perf_events_lapic_init(void)	{ }
+static inline void perf_check_microcode(void) { }
 #endif
 
 #if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD)
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index 98391db840c..f2b489cf160 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -2,9 +2,9 @@
 #define _ASM_X86_PGTABLE_2LEVEL_H
 
 #define pte_ERROR(e) \
-	printk("%s:%d: bad pte %08lx.\n", __FILE__, __LINE__, (e).pte_low)
+	pr_err("%s:%d: bad pte %08lx\n", __FILE__, __LINE__, (e).pte_low)
 #define pgd_ERROR(e) \
-	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, pgd_val(e))
+	pr_err("%s:%d: bad pgd %08lx\n", __FILE__, __LINE__, pgd_val(e))
 
 /*
  * Certain architectures need to do special things when PTEs
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index cb00ccc7d57..4cc9f2b7cdc 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -9,13 +9,13 @@
  */
 
 #define pte_ERROR(e)							\
-	printk("%s:%d: bad pte %p(%08lx%08lx).\n",			\
+	pr_err("%s:%d: bad pte %p(%08lx%08lx)\n",			\
 	       __FILE__, __LINE__, &(e), (e).pte_high, (e).pte_low)
 #define pmd_ERROR(e)							\
-	printk("%s:%d: bad pmd %p(%016Lx).\n",				\
+	pr_err("%s:%d: bad pmd %p(%016Lx)\n",				\
 	       __FILE__, __LINE__, &(e), pmd_val(e))
 #define pgd_ERROR(e)							\
-	printk("%s:%d: bad pgd %p(%016Lx).\n",				\
+	pr_err("%s:%d: bad pgd %p(%016Lx)\n",				\
 	       __FILE__, __LINE__, &(e), pgd_val(e))
 
 /* Rules for using set_pte: the pte being assigned *must* be
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 975f709e09a..8251be02301 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -26,16 +26,16 @@ extern pgd_t init_level4_pgt[];
 extern void paging_init(void);
 
 #define pte_ERROR(e)					\
-	printk("%s:%d: bad pte %p(%016lx).\n",		\
+	pr_err("%s:%d: bad pte %p(%016lx)\n",		\
 	       __FILE__, __LINE__, &(e), pte_val(e))
 #define pmd_ERROR(e)					\
-	printk("%s:%d: bad pmd %p(%016lx).\n",		\
+	pr_err("%s:%d: bad pmd %p(%016lx)\n",		\
 	       __FILE__, __LINE__, &(e), pmd_val(e))
 #define pud_ERROR(e)					\
-	printk("%s:%d: bad pud %p(%016lx).\n",		\
+	pr_err("%s:%d: bad pud %p(%016lx)\n",		\
 	       __FILE__, __LINE__, &(e), pud_val(e))
 #define pgd_ERROR(e)					\
-	printk("%s:%d: bad pgd %p(%016lx).\n",		\
+	pr_err("%s:%d: bad pgd %p(%016lx)\n",		\
 	       __FILE__, __LINE__, &(e), pgd_val(e))
 
 struct mm_struct;
diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index f8ab3eaad12..aea1d1d848c 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -44,6 +44,7 @@
  */
 #define X86_CR3_PWT	0x00000008 /* Page Write Through */
 #define X86_CR3_PCD	0x00000010 /* Page Cache Disable */
+#define X86_CR3_PCID_MASK 0x00000fff /* PCID Mask */
 
 /*
  * Intel CPU features in CR4
@@ -61,6 +62,7 @@
 #define X86_CR4_OSXMMEXCPT 0x00000400 /* enable unmasked SSE exceptions */
 #define X86_CR4_VMXE	0x00002000 /* enable VMX virtualization */
 #define X86_CR4_RDWRGSFS 0x00010000 /* enable RDWRGSFS support */
+#define X86_CR4_PCIDE	0x00020000 /* enable PCID support */
 #define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */
 #define X86_CR4_SMEP	0x00100000 /* enable SMEP support */
 
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index fce3f4ae5bd..fe1ec5bcd84 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -21,8 +21,9 @@ struct real_mode_header {
 	u32	wakeup_header;
 #endif
 	/* APM/BIOS reboot */
-#ifdef CONFIG_X86_32
 	u32	machine_real_restart_asm;
+#ifdef CONFIG_X86_64
+	u32	machine_real_restart_seg;
 #endif
 };
 
diff --git a/arch/x86/include/asm/reboot.h b/arch/x86/include/asm/reboot.h
index 92f297069e8..a82c4f1b4d8 100644
--- a/arch/x86/include/asm/reboot.h
+++ b/arch/x86/include/asm/reboot.h
@@ -18,8 +18,8 @@ extern struct machine_ops machine_ops;
 
 void native_machine_crash_shutdown(struct pt_regs *regs);
 void native_machine_shutdown(void);
-void machine_real_restart(unsigned int type);
-/* These must match dispatch_table in reboot_32.S */
+void __noreturn machine_real_restart(unsigned int type);
+/* These must match dispatch in arch/x86/realmore/rm/reboot.S */
 #define MRR_BIOS	0
 #define MRR_APM		1
 
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index f48394513c3..2ffa95dc233 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -169,11 +169,6 @@ void x86_idle_thread_init(unsigned int cpu, struct task_struct *idle);
 void smp_store_cpu_info(int id);
 #define cpu_physical_id(cpu)	per_cpu(x86_cpu_to_apicid, cpu)
 
-/* We don't mark CPUs online until __cpu_up(), so we need another measure */
-static inline int num_booting_cpus(void)
-{
-	return cpumask_weight(cpu_callout_mask);
-}
 #else /* !CONFIG_SMP */
 #define wbinvd_on_cpu(cpu)     wbinvd()
 static inline int wbinvd_on_all_cpus(void)
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 8e796fbbf9c..d8def8b3dba 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -17,6 +17,8 @@
 
 /* Handles exceptions in both to and from, but doesn't do access_ok */
 __must_check unsigned long
+copy_user_enhanced_fast_string(void *to, const void *from, unsigned len);
+__must_check unsigned long
 copy_user_generic_string(void *to, const void *from, unsigned len);
 __must_check unsigned long
 copy_user_generic_unrolled(void *to, const void *from, unsigned len);
@@ -26,9 +28,16 @@ copy_user_generic(void *to, const void *from, unsigned len)
 {
 	unsigned ret;
 
-	alternative_call(copy_user_generic_unrolled,
+	/*
+	 * If CPU has ERMS feature, use copy_user_enhanced_fast_string.
+	 * Otherwise, if CPU has rep_good feature, use copy_user_generic_string.
+	 * Otherwise, use copy_user_generic_unrolled.
+	 */
+	alternative_call_2(copy_user_generic_unrolled,
 			 copy_user_generic_string,
 			 X86_FEATURE_REP_GOOD,
+			 copy_user_enhanced_fast_string,
+			 X86_FEATURE_ERMS,
 			 ASM_OUTPUT2("=a" (ret), "=D" (to), "=S" (from),
 				     "=d" (len)),
 			 "1" (to), "2" (from), "3" (len)
diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
index 1e9bed14f7a..f3971bbcd1d 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -48,7 +48,7 @@ struct arch_uprobe_task {
 #endif
 };
 
-extern int  arch_uprobe_analyze_insn(struct arch_uprobe *aup, struct mm_struct *mm);
+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);
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 6149b476d9d..a06983cdc12 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -140,6 +140,9 @@
 #define IPI_RESET_LIMIT			1
 /* after this # consecutive successes, bump up the throttle if it was lowered */
 #define COMPLETE_THRESHOLD		5
+/* after this # of giveups (fall back to kernel IPI's) disable the use of
+   the BAU for a period of time */
+#define GIVEUP_LIMIT			100
 
 #define UV_LB_SUBNODEID			0x10
 
@@ -166,7 +169,6 @@
 #define FLUSH_RETRY_TIMEOUT		2
 #define FLUSH_GIVEUP			3
 #define FLUSH_COMPLETE			4
-#define FLUSH_RETRY_BUSYBUG		5
 
 /*
  * tuning the action when the numalink network is extremely delayed
@@ -175,7 +177,7 @@
 						   microseconds */
 #define CONGESTED_REPS			10	/* long delays averaged over
 						   this many broadcasts */
-#define CONGESTED_PERIOD		30	/* time for the bau to be
+#define DISABLED_PERIOD			10	/* time for the bau to be
 						   disabled, in seconds */
 /* see msg_type: */
 #define MSG_NOOP			0
@@ -520,6 +522,12 @@ struct ptc_stats {
 	unsigned long	s_uv2_wars;		/* uv2 workaround, perm. busy */
 	unsigned long	s_uv2_wars_hw;		/* uv2 workaround, hiwater */
 	unsigned long	s_uv2_war_waits;	/* uv2 workaround, long waits */
+	unsigned long	s_overipilimit;		/* over the ipi reset limit */
+	unsigned long	s_giveuplimit;		/* disables, over giveup limit*/
+	unsigned long	s_enters;		/* entries to the driver */
+	unsigned long	s_ipifordisabled;	/* fall back to IPI; disabled */
+	unsigned long	s_plugged;		/* plugged by h/w bug*/
+	unsigned long	s_congested;		/* giveup on long wait */
 	/* destination statistics */
 	unsigned long	d_alltlb;		/* times all tlb's on this
 						   cpu were flushed */
@@ -586,8 +594,8 @@ struct bau_control {
 	int			timeout_tries;
 	int			ipi_attempts;
 	int			conseccompletes;
-	int			baudisabled;
-	int			set_bau_off;
+	short			nobau;
+	short			baudisabled;
 	short			cpu;
 	short			osnode;
 	short			uvhub_cpu;
@@ -596,14 +604,16 @@ struct bau_control {
 	short			cpus_in_socket;
 	short			cpus_in_uvhub;
 	short			partition_base_pnode;
-	short			using_desc; /* an index, like uvhub_cpu */
-	unsigned int		inuse_map;
+	short			busy;       /* all were busy (war) */
 	unsigned short		message_number;
 	unsigned short		uvhub_quiesce;
 	short			socket_acknowledge_count[DEST_Q_SIZE];
 	cycles_t		send_message;
+	cycles_t		period_end;
+	cycles_t		period_time;
 	spinlock_t		uvhub_lock;
 	spinlock_t		queue_lock;
+	spinlock_t		disable_lock;
 	/* tunables */
 	int			max_concurr;
 	int			max_concurr_const;
@@ -614,9 +624,9 @@ struct bau_control {
 	int			complete_threshold;
 	int			cong_response_us;
 	int			cong_reps;
-	int			cong_period;
-	unsigned long		clocks_per_100_usec;
-	cycles_t		period_time;
+	cycles_t		disabled_period;
+	int			period_giveups;
+	int			giveup_limit;
 	long			period_requests;
 	struct hub_and_pnode	*thp;
 };
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 31f180c21ce..74fcb963595 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -60,6 +60,7 @@
 #define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
 #define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
 #define SECONDARY_EXEC_PAUSE_LOOP_EXITING	0x00000400
+#define SECONDARY_EXEC_ENABLE_INVPCID		0x00001000
 
 
 #define PIN_BASED_EXT_INTR_MASK                 0x00000001
@@ -281,6 +282,7 @@ enum vmcs_field {
 #define EXIT_REASON_EPT_MISCONFIG       49
 #define EXIT_REASON_WBINVD		54
 #define EXIT_REASON_XSETBV		55
+#define EXIT_REASON_INVPCID		58
 
 /*
  * Interruption-information format
@@ -404,6 +406,7 @@ enum vmcs_field {
 #define VMX_EPTP_WB_BIT				(1ull << 14)
 #define VMX_EPT_2MB_PAGE_BIT			(1ull << 16)
 #define VMX_EPT_1GB_PAGE_BIT			(1ull << 17)
+#define VMX_EPT_AD_BIT					(1ull << 21)
 #define VMX_EPT_EXTENT_INDIVIDUAL_BIT		(1ull << 24)
 #define VMX_EPT_EXTENT_CONTEXT_BIT		(1ull << 25)
 #define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
@@ -415,11 +418,14 @@ enum vmcs_field {
 #define VMX_EPT_MAX_GAW				0x4
 #define VMX_EPT_MT_EPTE_SHIFT			3
 #define VMX_EPT_GAW_EPTP_SHIFT			3
+#define VMX_EPT_AD_ENABLE_BIT			(1ull << 6)
 #define VMX_EPT_DEFAULT_MT			0x6ull
 #define VMX_EPT_READABLE_MASK			0x1ull
 #define VMX_EPT_WRITABLE_MASK			0x2ull
 #define VMX_EPT_EXECUTABLE_MASK			0x4ull
 #define VMX_EPT_IPAT_BIT    			(1ull << 6)
+#define VMX_EPT_ACCESS_BIT				(1ull << 8)
+#define VMX_EPT_DIRTY_BIT				(1ull << 9)
 
 #define VMX_EPT_IDENTITY_PAGETABLE_ADDR		0xfffbc000ul
 
diff --git a/arch/x86/include/asm/x2apic.h b/arch/x86/include/asm/x2apic.h
index 92e54abf89e..f90f0a587c6 100644
--- a/arch/x86/include/asm/x2apic.h
+++ b/arch/x86/include/asm/x2apic.h
@@ -9,15 +9,6 @@
 #include <asm/ipi.h>
 #include <linux/cpumask.h>
 
-/*
- * Need to use more than cpu 0, because we need more vectors
- * when MSI-X are used.
- */
-static const struct cpumask *x2apic_target_cpus(void)
-{
-	return cpu_online_mask;
-}
-
 static int x2apic_apic_id_valid(int apicid)
 {
 	return 1;
@@ -28,15 +19,6 @@ static int x2apic_apic_id_registered(void)
 	return 1;
 }
 
-/*
- * For now each logical cpu is in its own vector allocation domain.
- */
-static void x2apic_vector_allocation_domain(int cpu, struct cpumask *retmask)
-{
-	cpumask_clear(retmask);
-	cpumask_set_cpu(cpu, retmask);
-}
-
 static void
 __x2apic_send_IPI_dest(unsigned int apicid, int vector, unsigned int dest)
 {
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index c090af10ac7..38155f66714 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -156,7 +156,6 @@ struct x86_cpuinit_ops {
 /**
  * struct x86_platform_ops - platform specific runtime functions
  * @calibrate_tsc:		calibrate TSC
- * @wallclock_init:		init the wallclock device
  * @get_wallclock:		get time from HW clock like RTC etc.
  * @set_wallclock:		set time back to HW clock
  * @is_untracked_pat_range	exclude from PAT logic
@@ -164,10 +163,10 @@ struct x86_cpuinit_ops {
  * @i8042_detect		pre-detect if i8042 controller exists
  * @save_sched_clock_state:	save state for sched_clock() on suspend
  * @restore_sched_clock_state:	restore state for sched_clock() on resume
+ * @apic_post_init:		adjust apic if neeeded
  */
 struct x86_platform_ops {
 	unsigned long (*calibrate_tsc)(void);
-	void (*wallclock_init)(void);
 	unsigned long (*get_wallclock)(void);
 	int (*set_wallclock)(unsigned long nowtime);
 	void (*iommu_shutdown)(void);
@@ -177,6 +176,7 @@ struct x86_platform_ops {
 	int (*i8042_detect)(void);
 	void (*save_sched_clock_state)(void);
 	void (*restore_sched_clock_state)(void);
+	void (*apic_post_init)(void);
 };
 
 struct pci_dev;
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 5728852fb90..59c226d120c 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -48,6 +48,7 @@
 #include <xen/interface/sched.h>
 #include <xen/interface/physdev.h>
 #include <xen/interface/platform.h>
+#include <xen/interface/xen-mca.h>
 
 /*
  * The hypercall asms have to meet several constraints:
@@ -302,6 +303,13 @@ HYPERVISOR_set_timer_op(u64 timeout)
 }
 
 static inline int
+HYPERVISOR_mca(struct xen_mc *mc_op)
+{
+	mc_op->interface_version = XEN_MCA_INTERFACE_VERSION;
+	return _hypercall1(int, mca, mc_op);
+}
+
+static inline int
 HYPERVISOR_dom0_op(struct xen_platform_op *platform_op)
 {
 	platform_op->interface_version = XENPF_INTERFACE_VERSION;