Merge branch 'kvm-updates/2.6.34' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.34' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (145 commits)
  KVM: x86: Add KVM_CAP_X86_ROBUST_SINGLESTEP
  KVM: VMX: Update instruction length on intercepted BP
  KVM: Fix emulate_sys[call, enter, exit]()'s fault handling
  KVM: Fix segment descriptor loading
  KVM: Fix load_guest_segment_descriptor() to inject page fault
  KVM: x86 emulator: Forbid modifying CS segment register by mov instruction
  KVM: Convert kvm->requests_lock to raw_spinlock_t
  KVM: Convert i8254/i8259 locks to raw_spinlocks
  KVM: x86 emulator: disallow opcode 82 in 64-bit mode
  KVM: x86 emulator: code style cleanup
  KVM: Plan obsolescence of kernel allocated slots, paravirt mmu
  KVM: x86 emulator: Add LOCK prefix validity checking
  KVM: x86 emulator: Check CPL level during privilege instruction emulation
  KVM: x86 emulator: Fix popf emulation
  KVM: x86 emulator: Check IOPL level during io instruction emulation
  KVM: x86 emulator: fix memory access during x86 emulation
  KVM: x86 emulator: Add Virtual-8086 mode of emulation
  KVM: x86 emulator: Add group9 instruction decoding
  KVM: x86 emulator: Add group8 instruction decoding
  KVM: do not store wqh in irqfd
  ...

Trivial conflicts in Documentation/feature-removal-schedule.txt

25 files changed, 2067 insertions, 798 deletions

diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index 9f828f87ca3..493092efaa3 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -11,6 +11,7 @@ header-y += sigcontext32.h
 header-y += ucontext.h
 header-y += processor-flags.h
 header-y += hw_breakpoint.h
+header-y += hyperv.h
 
 unifdef-y += e820.h
 unifdef-y += ist.h
diff --git a/arch/x86/include/asm/hyperv.h b/arch/x86/include/asm/hyperv.h
new file mode 100644
index 00000000000..e153a2b3889
--- /dev/null
+++ b/arch/x86/include/asm/hyperv.h
@@ -0,0 +1,186 @@
+#ifndef _ASM_X86_KVM_HYPERV_H
+#define _ASM_X86_KVM_HYPERV_H
+
+#include <linux/types.h>
+
+/*
+ * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
+ * is set by CPUID(HvCpuIdFunctionVersionAndFeatures).
+ */
+#define HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS	0x40000000
+#define HYPERV_CPUID_INTERFACE			0x40000001
+#define HYPERV_CPUID_VERSION			0x40000002
+#define HYPERV_CPUID_FEATURES			0x40000003
+#define HYPERV_CPUID_ENLIGHTMENT_INFO		0x40000004
+#define HYPERV_CPUID_IMPLEMENT_LIMITS		0x40000005
+
+/*
+ * Feature identification. EAX indicates which features are available
+ * to the partition based upon the current partition privileges.
+ */
+
+/* VP Runtime (HV_X64_MSR_VP_RUNTIME) available */
+#define HV_X64_MSR_VP_RUNTIME_AVAILABLE		(1 << 0)
+/* Partition Reference Counter (HV_X64_MSR_TIME_REF_COUNT) available*/
+#define HV_X64_MSR_TIME_REF_COUNT_AVAILABLE	(1 << 1)
+/*
+ * Basic SynIC MSRs (HV_X64_MSR_SCONTROL through HV_X64_MSR_EOM
+ * and HV_X64_MSR_SINT0 through HV_X64_MSR_SINT15) available
+ */
+#define HV_X64_MSR_SYNIC_AVAILABLE		(1 << 2)
+/*
+ * Synthetic Timer MSRs (HV_X64_MSR_STIMER0_CONFIG through
+ * HV_X64_MSR_STIMER3_COUNT) available
+ */
+#define HV_X64_MSR_SYNTIMER_AVAILABLE		(1 << 3)
+/*
+ * APIC access MSRs (HV_X64_MSR_EOI, HV_X64_MSR_ICR and HV_X64_MSR_TPR)
+ * are available
+ */
+#define HV_X64_MSR_APIC_ACCESS_AVAILABLE	(1 << 4)
+/* Hypercall MSRs (HV_X64_MSR_GUEST_OS_ID and HV_X64_MSR_HYPERCALL) available*/
+#define HV_X64_MSR_HYPERCALL_AVAILABLE		(1 << 5)
+/* Access virtual processor index MSR (HV_X64_MSR_VP_INDEX) available*/
+#define HV_X64_MSR_VP_INDEX_AVAILABLE		(1 << 6)
+/* Virtual system reset MSR (HV_X64_MSR_RESET) is available*/
+#define HV_X64_MSR_RESET_AVAILABLE		(1 << 7)
+ /*
+  * Access statistics pages MSRs (HV_X64_MSR_STATS_PARTITION_RETAIL_PAGE,
+  * HV_X64_MSR_STATS_PARTITION_INTERNAL_PAGE, HV_X64_MSR_STATS_VP_RETAIL_PAGE,
+  * HV_X64_MSR_STATS_VP_INTERNAL_PAGE) available
+  */
+#define HV_X64_MSR_STAT_PAGES_AVAILABLE		(1 << 8)
+
+/*
+ * Feature identification: EBX indicates which flags were specified at
+ * partition creation. The format is the same as the partition creation
+ * flag structure defined in section Partition Creation Flags.
+ */
+#define HV_X64_CREATE_PARTITIONS		(1 << 0)
+#define HV_X64_ACCESS_PARTITION_ID		(1 << 1)
+#define HV_X64_ACCESS_MEMORY_POOL		(1 << 2)
+#define HV_X64_ADJUST_MESSAGE_BUFFERS		(1 << 3)
+#define HV_X64_POST_MESSAGES			(1 << 4)
+#define HV_X64_SIGNAL_EVENTS			(1 << 5)
+#define HV_X64_CREATE_PORT			(1 << 6)
+#define HV_X64_CONNECT_PORT			(1 << 7)
+#define HV_X64_ACCESS_STATS			(1 << 8)
+#define HV_X64_DEBUGGING			(1 << 11)
+#define HV_X64_CPU_POWER_MANAGEMENT		(1 << 12)
+#define HV_X64_CONFIGURE_PROFILER		(1 << 13)
+
+/*
+ * Feature identification. EDX indicates which miscellaneous features
+ * are available to the partition.
+ */
+/* The MWAIT instruction is available (per section MONITOR / MWAIT) */
+#define HV_X64_MWAIT_AVAILABLE				(1 << 0)
+/* Guest debugging support is available */
+#define HV_X64_GUEST_DEBUGGING_AVAILABLE		(1 << 1)
+/* Performance Monitor support is available*/
+#define HV_X64_PERF_MONITOR_AVAILABLE			(1 << 2)
+/* Support for physical CPU dynamic partitioning events is available*/
+#define HV_X64_CPU_DYNAMIC_PARTITIONING_AVAILABLE	(1 << 3)
+/*
+ * Support for passing hypercall input parameter block via XMM
+ * registers is available
+ */
+#define HV_X64_HYPERCALL_PARAMS_XMM_AVAILABLE		(1 << 4)
+/* Support for a virtual guest idle state is available */
+#define HV_X64_GUEST_IDLE_STATE_AVAILABLE		(1 << 5)
+
+/*
+ * Implementation recommendations. Indicates which behaviors the hypervisor
+ * recommends the OS implement for optimal performance.
+ */
+ /*
+  * Recommend using hypercall for address space switches rather
+  * than MOV to CR3 instruction
+  */
+#define HV_X64_MWAIT_RECOMMENDED		(1 << 0)
+/* Recommend using hypercall for local TLB flushes rather
+ * than INVLPG or MOV to CR3 instructions */
+#define HV_X64_LOCAL_TLB_FLUSH_RECOMMENDED	(1 << 1)
+/*
+ * Recommend using hypercall for remote TLB flushes rather
+ * than inter-processor interrupts
+ */
+#define HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED	(1 << 2)
+/*
+ * Recommend using MSRs for accessing APIC registers
+ * EOI, ICR and TPR rather than their memory-mapped counterparts
+ */
+#define HV_X64_APIC_ACCESS_RECOMMENDED		(1 << 3)
+/* Recommend using the hypervisor-provided MSR to initiate a system RESET */
+#define HV_X64_SYSTEM_RESET_RECOMMENDED		(1 << 4)
+/*
+ * Recommend using relaxed timing for this partition. If used,
+ * the VM should disable any watchdog timeouts that rely on the
+ * timely delivery of external interrupts
+ */
+#define HV_X64_RELAXED_TIMING_RECOMMENDED	(1 << 5)
+
+/* MSR used to identify the guest OS. */
+#define HV_X64_MSR_GUEST_OS_ID			0x40000000
+
+/* MSR used to setup pages used to communicate with the hypervisor. */
+#define HV_X64_MSR_HYPERCALL			0x40000001
+
+/* MSR used to provide vcpu index */
+#define HV_X64_MSR_VP_INDEX			0x40000002
+
+/* Define the virtual APIC registers */
+#define HV_X64_MSR_EOI				0x40000070
+#define HV_X64_MSR_ICR				0x40000071
+#define HV_X64_MSR_TPR				0x40000072
+#define HV_X64_MSR_APIC_ASSIST_PAGE		0x40000073
+
+/* Define synthetic interrupt controller model specific registers. */
+#define HV_X64_MSR_SCONTROL			0x40000080
+#define HV_X64_MSR_SVERSION			0x40000081
+#define HV_X64_MSR_SIEFP			0x40000082
+#define HV_X64_MSR_SIMP				0x40000083
+#define HV_X64_MSR_EOM				0x40000084
+#define HV_X64_MSR_SINT0			0x40000090
+#define HV_X64_MSR_SINT1			0x40000091
+#define HV_X64_MSR_SINT2			0x40000092
+#define HV_X64_MSR_SINT3			0x40000093
+#define HV_X64_MSR_SINT4			0x40000094
+#define HV_X64_MSR_SINT5			0x40000095
+#define HV_X64_MSR_SINT6			0x40000096
+#define HV_X64_MSR_SINT7			0x40000097
+#define HV_X64_MSR_SINT8			0x40000098
+#define HV_X64_MSR_SINT9			0x40000099
+#define HV_X64_MSR_SINT10			0x4000009A
+#define HV_X64_MSR_SINT11			0x4000009B
+#define HV_X64_MSR_SINT12			0x4000009C
+#define HV_X64_MSR_SINT13			0x4000009D
+#define HV_X64_MSR_SINT14			0x4000009E
+#define HV_X64_MSR_SINT15			0x4000009F
+
+
+#define HV_X64_MSR_HYPERCALL_ENABLE		0x00000001
+#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT	12
+#define HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_MASK	\
+		(~((1ull << HV_X64_MSR_HYPERCALL_PAGE_ADDRESS_SHIFT) - 1))
+
+/* Declare the various hypercall operations. */
+#define HV_X64_HV_NOTIFY_LONG_SPIN_WAIT		0x0008
+
+#define HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE		0x00000001
+#define HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT	12
+#define HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_MASK	\
+		(~((1ull << HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT) - 1))
+
+#define HV_PROCESSOR_POWER_STATE_C0		0
+#define HV_PROCESSOR_POWER_STATE_C1		1
+#define HV_PROCESSOR_POWER_STATE_C2		2
+#define HV_PROCESSOR_POWER_STATE_C3		3
+
+/* hypercall status code */
+#define HV_STATUS_SUCCESS			0
+#define HV_STATUS_INVALID_HYPERCALL_CODE	2
+#define HV_STATUS_INVALID_HYPERCALL_INPUT	3
+#define HV_STATUS_INVALID_ALIGNMENT		4
+
+#endif
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 7c18e1230f5..7a6f54fa13b 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -54,13 +54,23 @@ struct x86_emulate_ctxt;
 struct x86_emulate_ops {
 	/*
 	 * read_std: Read bytes of standard (non-emulated/special) memory.
-	 *           Used for instruction fetch, stack operations, and others.
+	 *           Used for descriptor reading.
 	 *  @addr:  [IN ] Linear address from which to read.
 	 *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
 	 *  @bytes: [IN ] Number of bytes to read from memory.
 	 */
 	int (*read_std)(unsigned long addr, void *val,
-			unsigned int bytes, struct kvm_vcpu *vcpu);
+			unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
+
+	/*
+	 * fetch: Read bytes of standard (non-emulated/special) memory.
+	 *        Used for instruction fetch.
+	 *  @addr:  [IN ] Linear address from which to read.
+	 *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
+	 *  @bytes: [IN ] Number of bytes to read from memory.
+	 */
+	int (*fetch)(unsigned long addr, void *val,
+			unsigned int bytes, struct kvm_vcpu *vcpu, u32 *error);
 
 	/*
 	 * read_emulated: Read bytes from emulated/special memory area.
@@ -74,7 +84,7 @@ struct x86_emulate_ops {
 			     struct kvm_vcpu *vcpu);
 
 	/*
-	 * write_emulated: Read bytes from emulated/special memory area.
+	 * write_emulated: Write bytes to emulated/special memory area.
 	 *  @addr:  [IN ] Linear address to which to write.
 	 *  @val:   [IN ] Value to write to memory (low-order bytes used as
 	 *                required).
@@ -168,6 +178,7 @@ struct x86_emulate_ctxt {
 
 /* Execution mode, passed to the emulator. */
 #define X86EMUL_MODE_REAL     0	/* Real mode.             */
+#define X86EMUL_MODE_VM86     1	/* Virtual 8086 mode.     */
 #define X86EMUL_MODE_PROT16   2	/* 16-bit protected mode. */
 #define X86EMUL_MODE_PROT32   4	/* 32-bit protected mode. */
 #define X86EMUL_MODE_PROT64   8	/* 64-bit (long) mode.    */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 4f865e8b854..06d9e79ca37 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -25,7 +25,7 @@
 #include <asm/mtrr.h>
 #include <asm/msr-index.h>
 
-#define KVM_MAX_VCPUS 16
+#define KVM_MAX_VCPUS 64
 #define KVM_MEMORY_SLOTS 32
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
@@ -38,19 +38,6 @@
 #define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS |	\
 				  0xFFFFFF0000000000ULL)
 
-#define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST				\
-	(X86_CR0_WP | X86_CR0_NE | X86_CR0_NW | X86_CR0_CD)
-#define KVM_GUEST_CR0_MASK						\
-	(KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
-#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST				\
-	(X86_CR0_WP | X86_CR0_NE | X86_CR0_TS | X86_CR0_MP)
-#define KVM_VM_CR0_ALWAYS_ON						\
-	(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
-#define KVM_GUEST_CR4_MASK						\
-	(X86_CR4_VME | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_PGE | X86_CR4_VMXE)
-#define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)
-#define KVM_RMODE_VM_CR4_ALWAYS_ON (X86_CR4_VME | X86_CR4_PAE | X86_CR4_VMXE)
-
 #define INVALID_PAGE (~(hpa_t)0)
 #define UNMAPPED_GVA (~(gpa_t)0)
 
@@ -256,7 +243,8 @@ struct kvm_mmu {
 	void (*new_cr3)(struct kvm_vcpu *vcpu);
 	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
 	void (*free)(struct kvm_vcpu *vcpu);
-	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva);
+	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
+			    u32 *error);
 	void (*prefetch_page)(struct kvm_vcpu *vcpu,
 			      struct kvm_mmu_page *page);
 	int (*sync_page)(struct kvm_vcpu *vcpu,
@@ -282,13 +270,15 @@ struct kvm_vcpu_arch {
 	u32 regs_dirty;
 
 	unsigned long cr0;
+	unsigned long cr0_guest_owned_bits;
 	unsigned long cr2;
 	unsigned long cr3;
 	unsigned long cr4;
+	unsigned long cr4_guest_owned_bits;
 	unsigned long cr8;
 	u32 hflags;
 	u64 pdptrs[4]; /* pae */
-	u64 shadow_efer;
+	u64 efer;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
 	int32_t apic_arb_prio;
@@ -374,17 +364,27 @@ struct kvm_vcpu_arch {
 	/* used for guest single stepping over the given code position */
 	u16 singlestep_cs;
 	unsigned long singlestep_rip;
+	/* fields used by HYPER-V emulation */
+	u64 hv_vapic;
 };
 
 struct kvm_mem_alias {
 	gfn_t base_gfn;
 	unsigned long npages;
 	gfn_t target_gfn;
+#define KVM_ALIAS_INVALID     1UL
+	unsigned long flags;
 };
 
-struct kvm_arch{
-	int naliases;
+#define KVM_ARCH_HAS_UNALIAS_INSTANTIATION
+
+struct kvm_mem_aliases {
 	struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS];
+	int naliases;
+};
+
+struct kvm_arch {
+	struct kvm_mem_aliases *aliases;
 
 	unsigned int n_free_mmu_pages;
 	unsigned int n_requested_mmu_pages;
@@ -416,6 +416,10 @@ struct kvm_arch{
 	s64 kvmclock_offset;
 
 	struct kvm_xen_hvm_config xen_hvm_config;
+
+	/* fields used by HYPER-V emulation */
+	u64 hv_guest_os_id;
+	u64 hv_hypercall;
 };
 
 struct kvm_vm_stat {
@@ -471,6 +475,7 @@ struct kvm_x86_ops {
 	int (*hardware_setup)(void);               /* __init */
 	void (*hardware_unsetup)(void);            /* __exit */
 	bool (*cpu_has_accelerated_tpr)(void);
+	void (*cpuid_update)(struct kvm_vcpu *vcpu);
 
 	/* Create, but do not attach this VCPU */
 	struct kvm_vcpu *(*vcpu_create)(struct kvm *kvm, unsigned id);
@@ -492,6 +497,7 @@ struct kvm_x86_ops {
 	void (*set_segment)(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg);
 	void (*get_cs_db_l_bits)(struct kvm_vcpu *vcpu, int *db, int *l);
+	void (*decache_cr0_guest_bits)(struct kvm_vcpu *vcpu);
 	void (*decache_cr4_guest_bits)(struct kvm_vcpu *vcpu);
 	void (*set_cr0)(struct kvm_vcpu *vcpu, unsigned long cr0);
 	void (*set_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
@@ -501,12 +507,13 @@ struct kvm_x86_ops {
 	void (*set_idt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
 	void (*get_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
 	void (*set_gdt)(struct kvm_vcpu *vcpu, struct descriptor_table *dt);
-	unsigned long (*get_dr)(struct kvm_vcpu *vcpu, int dr);
-	void (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value,
-		       int *exception);
+	int (*get_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long *dest);
+	int (*set_dr)(struct kvm_vcpu *vcpu, int dr, unsigned long value);
 	void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
 	unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
 	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
+	void (*fpu_activate)(struct kvm_vcpu *vcpu);
+	void (*fpu_deactivate)(struct kvm_vcpu *vcpu);
 
 	void (*tlb_flush)(struct kvm_vcpu *vcpu);
 
@@ -531,7 +538,8 @@ struct kvm_x86_ops {
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*get_tdp_level)(void);
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
-	bool (*gb_page_enable)(void);
+	int (*get_lpage_level)(void);
+	bool (*rdtscp_supported)(void);
 
 	const struct trace_print_flags *exit_reasons_str;
 };
@@ -606,8 +614,7 @@ int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
 		    unsigned long value);
 
 void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
-int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
-				int type_bits, int seg);
+int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg);
 
 int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason);
 
@@ -653,6 +660,10 @@ void __kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu);
 int kvm_mmu_load(struct kvm_vcpu *vcpu);
 void kvm_mmu_unload(struct kvm_vcpu *vcpu);
 void kvm_mmu_sync_roots(struct kvm_vcpu *vcpu);
+gpa_t kvm_mmu_gva_to_gpa_read(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
+gpa_t kvm_mmu_gva_to_gpa_fetch(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
+gpa_t kvm_mmu_gva_to_gpa_write(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
+gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva, u32 *error);
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
@@ -666,6 +677,7 @@ void kvm_disable_tdp(void);
 
 int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
 int complete_pio(struct kvm_vcpu *vcpu);
+bool kvm_check_iopl(struct kvm_vcpu *vcpu);
 
 struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn);
 
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index c584076a47f..ffae1420e7d 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_KVM_PARA_H
 
 #include <linux/types.h>
+#include <asm/hyperv.h>
 
 /* This CPUID returns the signature 'KVMKVMKVM' in ebx, ecx, and edx.  It
  * should be used to determine that a VM is running under KVM.
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 1fecb7e6113..38638cd2fa4 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -313,7 +313,7 @@ struct __attribute__ ((__packed__)) vmcb {
 
 #define SVM_EXIT_ERR		-1
 
-#define SVM_CR0_SELECTIVE_MASK (1 << 3 | 1) /* TS and MP */
+#define SVM_CR0_SELECTIVE_MASK (X86_CR0_TS | X86_CR0_MP)
 
 #define SVM_VMLOAD ".byte 0x0f, 0x01, 0xda"
 #define SVM_VMRUN  ".byte 0x0f, 0x01, 0xd8"
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 2b4945419a8..fb9a080740e 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -53,6 +53,7 @@
  */
 #define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
 #define SECONDARY_EXEC_ENABLE_EPT               0x00000002
+#define SECONDARY_EXEC_RDTSCP			0x00000008
 #define SECONDARY_EXEC_ENABLE_VPID              0x00000020
 #define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
 #define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
@@ -251,6 +252,7 @@ enum vmcs_field {
 #define EXIT_REASON_MSR_READ            31
 #define EXIT_REASON_MSR_WRITE           32
 #define EXIT_REASON_MWAIT_INSTRUCTION   36
+#define EXIT_REASON_MONITOR_INSTRUCTION 39
 #define EXIT_REASON_PAUSE_INSTRUCTION   40
 #define EXIT_REASON_MCE_DURING_VMENTRY	 41
 #define EXIT_REASON_TPR_BELOW_THRESHOLD 43
@@ -362,6 +364,7 @@ enum vmcs_field {
 #define VMX_EPTP_UC_BIT				(1ull << 8)
 #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_EXTENT_INDIVIDUAL_BIT		(1ull << 24)
 #define VMX_EPT_EXTENT_CONTEXT_BIT		(1ull << 25)
 #define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
@@ -374,7 +377,7 @@ enum vmcs_field {
 #define VMX_EPT_READABLE_MASK			0x1ull
 #define VMX_EPT_WRITABLE_MASK			0x2ull
 #define VMX_EPT_EXECUTABLE_MASK			0x4ull
-#define VMX_EPT_IGMT_BIT    			(1ull << 6)
+#define VMX_EPT_IPAT_BIT    			(1ull << 6)
 
 #define VMX_EPT_IDENTITY_PAGETABLE_ADDR		0xfffbc000ul
 
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 9055e5872ff..1c0c6ab9c60 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -301,7 +301,8 @@ static int __init vsyscall_init(void)
 	register_sysctl_table(kernel_root_table2);
 #endif
 	on_each_cpu(cpu_vsyscall_init, NULL, 1);
-	hotcpu_notifier(cpu_vsyscall_notifier, 0);
+	/* notifier priority > KVM */
+	hotcpu_notifier(cpu_vsyscall_notifier, 30);
 	return 0;
 }
 
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 3c4d0109ad2..970bbd47951 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -29,6 +29,7 @@ config KVM
 	select HAVE_KVM_EVENTFD
 	select KVM_APIC_ARCHITECTURE
 	select USER_RETURN_NOTIFIER
+	select KVM_MMIO
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 7e8faea4651..4dade6ac082 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -32,7 +32,7 @@
 #include <linux/module.h>
 #include <asm/kvm_emulate.h>
 
-#include "mmu.h"		/* for is_long_mode() */
+#include "x86.h"
 
 /*
  * Opcode effective-address decode tables.
@@ -76,6 +76,8 @@
 #define GroupDual   (1<<15)     /* Alternate decoding of mod == 3 */
 #define GroupMask   0xff        /* Group number stored in bits 0:7 */
 /* Misc flags */
+#define Lock        (1<<26) /* lock prefix is allowed for the instruction */
+#define Priv        (1<<27) /* instruction generates #GP if current CPL != 0 */
 #define No64	    (1<<28)
 /* Source 2 operand type */
 #define Src2None    (0<<29)
@@ -88,39 +90,40 @@
 enum {
 	Group1_80, Group1_81, Group1_82, Group1_83,
 	Group1A, Group3_Byte, Group3, Group4, Group5, Group7,
+	Group8, Group9,
 };
 
 static u32 opcode_table[256] = {
 	/* 0x00 - 0x07 */
-	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
+	ByteOp | DstMem | SrcReg | ModRM | Lock, DstMem | SrcReg | ModRM | Lock,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
 	ByteOp | DstAcc | SrcImm, DstAcc | SrcImm,
 	ImplicitOps | Stack | No64, ImplicitOps | Stack | No64,
 	/* 0x08 - 0x0F */
-	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
+	ByteOp | DstMem | SrcReg | ModRM | Lock, DstMem | SrcReg | ModRM | Lock,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
 	ByteOp | DstAcc | SrcImm, DstAcc | SrcImm,
 	ImplicitOps | Stack | No64, 0,
 	/* 0x10 - 0x17 */
-	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
+	ByteOp | DstMem | SrcReg | ModRM | Lock, DstMem | SrcReg | ModRM | Lock,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
 	ByteOp | DstAcc | SrcImm, DstAcc | SrcImm,
 	ImplicitOps | Stack | No64, ImplicitOps | Stack | No64,
 	/* 0x18 - 0x1F */
-	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
+	ByteOp | DstMem | SrcReg | ModRM | Lock, DstMem | SrcReg | ModRM | Lock,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
 	ByteOp | DstAcc | SrcImm, DstAcc | SrcImm,
 	ImplicitOps | Stack | No64, ImplicitOps | Stack | No64,
 	/* 0x20 - 0x27 */
-	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
+	ByteOp | DstMem | SrcReg | ModRM | Lock, DstMem | SrcReg | ModRM | Lock,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
 	DstAcc | SrcImmByte, DstAcc | SrcImm, 0, 0,
 	/* 0x28 - 0x2F */
-	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
+	ByteOp | DstMem | SrcReg | ModRM | Lock, DstMem | SrcReg | ModRM | Lock,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
 	0, 0, 0, 0,
 	/* 0x30 - 0x37 */
-	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
+	ByteOp | DstMem | SrcReg | ModRM | Lock, DstMem | SrcReg | ModRM | Lock,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
 	0, 0, 0, 0,
 	/* 0x38 - 0x3F */
@@ -156,7 +159,7 @@ static u32 opcode_table[256] = {
 	Group | Group1_80, Group | Group1_81,
 	Group | Group1_82, Group | Group1_83,
 	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
-	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
+	ByteOp | DstMem | SrcReg | ModRM | Lock, DstMem | SrcReg | ModRM | Lock,
 	/* 0x88 - 0x8F */
 	ByteOp | DstMem | SrcReg | ModRM | Mov, DstMem | SrcReg | ModRM | Mov,
 	ByteOp | DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov,
@@ -210,7 +213,7 @@ static u32 opcode_table[256] = {
 	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
 	/* 0xF0 - 0xF7 */
 	0, 0, 0, 0,
-	ImplicitOps, ImplicitOps, Group | Group3_Byte, Group | Group3,
+	ImplicitOps | Priv, ImplicitOps, Group | Group3_Byte, Group | Group3,
 	/* 0xF8 - 0xFF */
 	ImplicitOps, 0, ImplicitOps, ImplicitOps,
 	ImplicitOps, ImplicitOps, Group | Group4, Group | Group5,
@@ -218,16 +221,20 @@ static u32 opcode_table[256] = {
 
 static u32 twobyte_table[256] = {
 	/* 0x00 - 0x0F */
-	0, Group | GroupDual | Group7, 0, 0, 0, ImplicitOps, ImplicitOps, 0,
-	ImplicitOps, ImplicitOps, 0, 0, 0, ImplicitOps | ModRM, 0, 0,
+	0, Group | GroupDual | Group7, 0, 0,
+	0, ImplicitOps, ImplicitOps | Priv, 0,
+	ImplicitOps | Priv, ImplicitOps | Priv, 0, 0,
+	0, ImplicitOps | ModRM, 0, 0,
 	/* 0x10 - 0x1F */
 	0, 0, 0, 0, 0, 0, 0, 0, ImplicitOps | ModRM, 0, 0, 0, 0, 0, 0, 0,
 	/* 0x20 - 0x2F */
-	ModRM | ImplicitOps, ModRM, ModRM | ImplicitOps, ModRM, 0, 0, 0, 0,
+	ModRM | ImplicitOps | Priv, ModRM | Priv,
+	ModRM | ImplicitOps | Priv, ModRM | Priv,
+	0, 0, 0, 0,
 	0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0x30 - 0x3F */
-	ImplicitOps, 0, ImplicitOps, 0,
-	ImplicitOps, ImplicitOps, 0, 0,
+	ImplicitOps | Priv, 0, ImplicitOps | Priv, 0,
+	ImplicitOps, ImplicitOps | Priv, 0, 0,
 	0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0x40 - 0x47 */
 	DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov,
@@ -257,21 +264,23 @@ static u32 twobyte_table[256] = {
 	DstMem | SrcReg | Src2CL | ModRM, 0, 0,
 	/* 0xA8 - 0xAF */
 	ImplicitOps | Stack, ImplicitOps | Stack,
-	0, DstMem | SrcReg | ModRM | BitOp,
+	0, DstMem | SrcReg | ModRM | BitOp | Lock,
 	DstMem | SrcReg | Src2ImmByte | ModRM,
 	DstMem | SrcReg | Src2CL | ModRM,
 	ModRM, 0,
 	/* 0xB0 - 0xB7 */
-	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM, 0,
-	    DstMem | SrcReg | ModRM | BitOp,
+	ByteOp | DstMem | SrcReg | ModRM | Lock, DstMem | SrcReg | ModRM | Lock,
+	0, DstMem | SrcReg | ModRM | BitOp | Lock,
 	0, 0, ByteOp | DstReg | SrcMem | ModRM | Mov,
 	    DstReg | SrcMem16 | ModRM | Mov,
 	/* 0xB8 - 0xBF */
-	0, 0, DstMem | SrcImmByte | ModRM, DstMem | SrcReg | ModRM | BitOp,
+	0, 0,
+	Group | Group8, DstMem | SrcReg | ModRM | BitOp | Lock,
 	0, 0, ByteOp | DstReg | SrcMem | ModRM | Mov,
 	    DstReg | SrcMem16 | ModRM | Mov,
 	/* 0xC0 - 0xCF */
-	0, 0, 0, DstMem | SrcReg | ModRM | Mov, 0, 0, 0, ImplicitOps | ModRM,
+	0, 0, 0, DstMem | SrcReg | ModRM | Mov,
+	0, 0, 0, Group | GroupDual | Group9,
 	0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0xD0 - 0xDF */
 	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -283,25 +292,41 @@ static u32 twobyte_table[256] = {
 
 static u32 group_table[] = {
 	[Group1_80*8] =
-	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
-	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
-	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
-	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+	ByteOp | DstMem | SrcImm | ModRM | Lock,
+	ByteOp | DstMem | SrcImm | ModRM | Lock,
+	ByteOp | DstMem | SrcImm | ModRM | Lock,
+	ByteOp | DstMem | SrcImm | ModRM | Lock,
+	ByteOp | DstMem | SrcImm | ModRM | Lock,
+	ByteOp | DstMem | SrcImm | ModRM | Lock,
+	ByteOp | DstMem | SrcImm | ModRM | Lock,
+	ByteOp | DstMem | SrcImm | ModRM,
 	[Group1_81*8] =
-	DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM,
-	DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM,
-	DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM,
-	DstMem | SrcImm | ModRM, DstMem | SrcImm | ModRM,
+	DstMem | SrcImm | ModRM | Lock,
+	DstMem | SrcImm | ModRM | Lock,
+	DstMem | SrcImm | ModRM | Lock,
+	DstMem | SrcImm | ModRM | Lock,
+	DstMem | SrcImm | ModRM | Lock,
+	DstMem | SrcImm | ModRM | Lock,
+	DstMem | SrcImm | ModRM | Lock,
+	DstMem | SrcImm | ModRM,
 	[Group1_82*8] =
-	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
-	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
-	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
-	ByteOp | DstMem | SrcImm | ModRM, ByteOp | DstMem | SrcImm | ModRM,
+	ByteOp | DstMem | SrcImm | ModRM | No64 | Lock,
+	ByteOp | DstMem | SrcImm | ModRM | No64 | Lock,
+	ByteOp | DstMem | SrcImm | ModRM | No64 | Lock,
+	ByteOp | DstMem | SrcImm | ModRM | No64 | Lock,
+	ByteOp | DstMem | SrcImm | ModRM | No64 | Lock,
+	ByteOp | DstMem | SrcImm | ModRM | No64 | Lock,
+	ByteOp | DstMem | SrcImm | ModRM | No64 | Lock,
+	ByteOp | DstMem | SrcImm | ModRM | No64,
 	[Group1_83*8] =
-	DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM,
-	DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM,
-	DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM,
-	DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM,
+	DstMem | SrcImmByte | ModRM | Lock,
+	DstMem | SrcImmByte | ModRM | Lock,
+	DstMem | SrcImmByte | ModRM | Lock,
+	DstMem | SrcImmByte | ModRM | Lock,
+	DstMem | SrcImmByte | ModRM | Lock,
+	DstMem | SrcImmByte | ModRM | Lock,
+	DstMem | SrcImmByte | ModRM | Lock,
+	DstMem | SrcImmByte | ModRM,
 	[Group1A*8] =
 	DstMem | SrcNone | ModRM | Mov | Stack, 0, 0, 0, 0, 0, 0, 0,
 	[Group3_Byte*8] =
@@ -320,24 +345,39 @@ static u32 group_table[] = {
 	SrcMem | ModRM | Stack, 0,
 	SrcMem | ModRM | Stack, 0, SrcMem | ModRM | Stack, 0,
 	[Group7*8] =
-	0, 0, ModRM | SrcMem, ModRM | SrcMem,
+	0, 0, ModRM | SrcMem | Priv, ModRM | SrcMem | Priv,
 	SrcNone | ModRM | DstMem | Mov, 0,
-	SrcMem16 | ModRM | Mov, SrcMem | ModRM | ByteOp,
+	SrcMem16 | ModRM | Mov | Priv, SrcMem | ModRM | ByteOp | Priv,
+	[Group8*8] =
+	0, 0, 0, 0,
+	DstMem | SrcImmByte | ModRM, DstMem | SrcImmByte | ModRM | Lock,
+	DstMem | SrcImmByte | ModRM | Lock, DstMem | SrcImmByte | ModRM | Lock,
+	[Group9*8] =
+	0, ImplicitOps | ModRM | Lock, 0, 0, 0, 0, 0, 0,
 };
 
 static u32 group2_table[] = {
 	[Group7*8] =
-	SrcNone | ModRM, 0, 0, SrcNone | ModRM,
+	SrcNone | ModRM | Priv, 0, 0, SrcNone | ModRM,
 	SrcNone | ModRM | DstMem | Mov, 0,
 	SrcMem16 | ModRM | Mov, 0,
+	[Group9*8] =
+	0, 0, 0, 0, 0, 0, 0, 0,
 };
 
 /* EFLAGS bit definitions. */
+#define EFLG_ID (1<<21)
+#define EFLG_VIP (1<<20)
+#define EFLG_VIF (1<<19)
+#define EFLG_AC (1<<18)
 #define EFLG_VM (1<<17)
 #define EFLG_RF (1<<16)