Merge branch 'kvm-updates/2.6.36' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.36' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (198 commits)
  KVM: VMX: Fix host GDT.LIMIT corruption
  KVM: MMU: using __xchg_spte more smarter
  KVM: MMU: cleanup spte set and accssed/dirty tracking
  KVM: MMU: don't atomicly set spte if it's not present
  KVM: MMU: fix page dirty tracking lost while sync page
  KVM: MMU: fix broken page accessed tracking with ept enabled
  KVM: MMU: add missing reserved bits check in speculative path
  KVM: MMU: fix mmu notifier invalidate handler for huge spte
  KVM: x86 emulator: fix xchg instruction emulation
  KVM: x86: Call mask notifiers from pic
  KVM: x86: never re-execute instruction with enabled tdp
  KVM: Document KVM_GET_SUPPORTED_CPUID2 ioctl
  KVM: x86: emulator: inc/dec can have lock prefix
  KVM: MMU: Eliminate redundant temporaries in FNAME(fetch)
  KVM: MMU: Validate all gptes during fetch, not just those used for new pages
  KVM: MMU: Simplify spte fetch() function
  KVM: MMU: Add gpte_valid() helper
  KVM: MMU: Add validate_direct_spte() helper
  KVM: MMU: Add drop_large_spte() helper
  KVM: MMU: Use __set_spte to link shadow pages
  ...

7 files changed, 79 insertions, 58 deletions

diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index c991b3a7b904..815c5b2b9f57 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -482,6 +482,8 @@ static inline void fpu_copy(struct fpu *dst, struct fpu *src)
 	memcpy(dst->state, src->state, xstate_size);
 }
 
+extern void fpu_finit(struct fpu *fpu);
+
 #endif /* __ASSEMBLY__ */
 
 #define PSHUFB_XMM5_XMM0 .byte 0x66, 0x0f, 0x38, 0x00, 0xc5
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index ff90055c7f0b..4d8dcbdfc120 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -22,6 +22,8 @@
 #define __KVM_HAVE_XEN_HVM
 #define __KVM_HAVE_VCPU_EVENTS
 #define __KVM_HAVE_DEBUGREGS
+#define __KVM_HAVE_XSAVE
+#define __KVM_HAVE_XCRS
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256
@@ -299,4 +301,24 @@ struct kvm_debugregs {
 	__u64 reserved[9];
 };
 
+/* for KVM_CAP_XSAVE */
+struct kvm_xsave {
+	__u32 region[1024];
+};
+
+#define KVM_MAX_XCRS	16
+
+struct kvm_xcr {
+	__u32 xcr;
+	__u32 reserved;
+	__u64 value;
+};
+
+struct kvm_xcrs {
+	__u32 nr_xcrs;
+	__u32 flags;
+	struct kvm_xcr xcrs[KVM_MAX_XCRS];
+	__u64 padding[16];
+};
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 0b2729bf2070..51cfd730ac5d 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -51,8 +51,10 @@ struct x86_emulate_ctxt;
 #define X86EMUL_UNHANDLEABLE    1
 /* Terminate emulation but return success to the caller. */
 #define X86EMUL_PROPAGATE_FAULT 2 /* propagate a generated fault to guest */
-#define X86EMUL_RETRY_INSTR     2 /* retry the instruction for some reason */
-#define X86EMUL_CMPXCHG_FAILED  2 /* cmpxchg did not see expected value */
+#define X86EMUL_RETRY_INSTR     3 /* retry the instruction for some reason */
+#define X86EMUL_CMPXCHG_FAILED  4 /* cmpxchg did not see expected value */
+#define X86EMUL_IO_NEEDED       5 /* IO is needed to complete emulation */
+
 struct x86_emulate_ops {
 	/*
 	 * read_std: Read bytes of standard (non-emulated/special) memory.
@@ -92,6 +94,7 @@ struct x86_emulate_ops {
 	int (*read_emulated)(unsigned long addr,
 			     void *val,
 			     unsigned int bytes,
+			     unsigned int *error,
 			     struct kvm_vcpu *vcpu);
 
 	/*
@@ -104,6 +107,7 @@ struct x86_emulate_ops {
 	int (*write_emulated)(unsigned long addr,
 			      const void *val,
 			      unsigned int bytes,
+			      unsigned int *error,
 			      struct kvm_vcpu *vcpu);
 
 	/*
@@ -118,6 +122,7 @@ struct x86_emulate_ops {
 				const void *old,
 				const void *new,
 				unsigned int bytes,
+				unsigned int *error,
 				struct kvm_vcpu *vcpu);
 
 	int (*pio_in_emulated)(int size, unsigned short port, void *val,
@@ -132,18 +137,26 @@ struct x86_emulate_ops {
 				      int seg, struct kvm_vcpu *vcpu);
 	u16 (*get_segment_selector)(int seg, struct kvm_vcpu *vcpu);
 	void (*set_segment_selector)(u16 sel, int seg, struct kvm_vcpu *vcpu);
+	unsigned long (*get_cached_segment_base)(int seg, struct kvm_vcpu *vcpu);
 	void (*get_gdt)(struct desc_ptr *dt, struct kvm_vcpu *vcpu);
 	ulong (*get_cr)(int cr, struct kvm_vcpu *vcpu);
-	void (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu);
+	int (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu);
 	int (*cpl)(struct kvm_vcpu *vcpu);
-	void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags);
+	int (*get_dr)(int dr, unsigned long *dest, struct kvm_vcpu *vcpu);
+	int (*set_dr)(int dr, unsigned long value, struct kvm_vcpu *vcpu);
+	int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
+	int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata);
 };
 
 /* Type, address-of, and value of an instruction's operand. */
 struct operand {
 	enum { OP_REG, OP_MEM, OP_IMM, OP_NONE } type;
 	unsigned int bytes;
-	unsigned long val, orig_val, *ptr;
+	unsigned long orig_val, *ptr;
+	union {
+		unsigned long val;
+		char valptr[sizeof(unsigned long) + 2];
+	};
 };
 
 struct fetch_cache {
@@ -186,6 +199,7 @@ struct decode_cache {
 	unsigned long modrm_val;
 	struct fetch_cache fetch;
 	struct read_cache io_read;
+	struct read_cache mem_read;
 };
 
 struct x86_emulate_ctxt {
@@ -202,6 +216,12 @@ struct x86_emulate_ctxt {
 	int interruptibility;
 
 	bool restart; /* restart string instruction after writeback */
+
+	int exception; /* exception that happens during emulation or -1 */
+	u32 error_code; /* error code for exception */
+	bool error_code_valid;
+	unsigned long cr2; /* faulted address in case of #PF */
+
 	/* decode cache */
 	struct decode_cache decode;
 };
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 76f5483cffec..502e53f999cf 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -15,6 +15,7 @@
 #include <linux/mm.h>
 #include <linux/mmu_notifier.h>
 #include <linux/tracepoint.h>
+#include <linux/cpumask.h>
 
 #include <linux/kvm.h>
 #include <linux/kvm_para.h>
@@ -39,11 +40,14 @@
 				  0xFFFFFF0000000000ULL)
 
 #define INVALID_PAGE (~(hpa_t)0)
+#define VALID_PAGE(x) ((x) != INVALID_PAGE)
+
 #define UNMAPPED_GVA (~(gpa_t)0)
 
 /* KVM Hugepage definitions for x86 */
 #define KVM_NR_PAGE_SIZES	3
-#define KVM_HPAGE_SHIFT(x)	(PAGE_SHIFT + (((x) - 1) * 9))
+#define KVM_HPAGE_GFN_SHIFT(x)	(((x) - 1) * 9)
+#define KVM_HPAGE_SHIFT(x)	(PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x))
 #define KVM_HPAGE_SIZE(x)	(1UL << KVM_HPAGE_SHIFT(x))
 #define KVM_HPAGE_MASK(x)	(~(KVM_HPAGE_SIZE(x) - 1))
 #define KVM_PAGES_PER_HPAGE(x)	(KVM_HPAGE_SIZE(x) / PAGE_SIZE)
@@ -69,8 +73,6 @@
 
 #define IOPL_SHIFT 12
 
-#define KVM_ALIAS_SLOTS 4
-
 #define KVM_PERMILLE_MMU_PAGES 20
 #define KVM_MIN_ALLOC_MMU_PAGES 64
 #define KVM_MMU_HASH_SHIFT 10
@@ -241,7 +243,7 @@ struct kvm_mmu {
 	void (*prefetch_page)(struct kvm_vcpu *vcpu,
 			      struct kvm_mmu_page *page);
 	int (*sync_page)(struct kvm_vcpu *vcpu,
-			 struct kvm_mmu_page *sp);
+			 struct kvm_mmu_page *sp, bool clear_unsync);
 	void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva);
 	hpa_t root_hpa;
 	int root_level;
@@ -301,8 +303,8 @@ struct kvm_vcpu_arch {
 		unsigned long mmu_seq;
 	} update_pte;
 
-	struct i387_fxsave_struct host_fx_image;
-	struct i387_fxsave_struct guest_fx_image;
+	struct fpu guest_fpu;
+	u64 xcr0;
 
 	gva_t mmio_fault_cr2;
 	struct kvm_pio_request pio;
@@ -360,26 +362,11 @@ struct kvm_vcpu_arch {
 
 	/* 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;
-};
 
-#define KVM_ARCH_HAS_UNALIAS_INSTANTIATION
-
-struct kvm_mem_aliases {
-	struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS];
-	int naliases;
+	cpumask_var_t wbinvd_dirty_mask;
 };
 
 struct kvm_arch {
-	struct kvm_mem_aliases *aliases;
-
 	unsigned int n_free_mmu_pages;
 	unsigned int n_requested_mmu_pages;
 	unsigned int n_alloc_mmu_pages;
@@ -533,6 +520,8 @@ struct kvm_x86_ops {
 
 	void (*set_supported_cpuid)(u32 func, struct kvm_cpuid_entry2 *entry);
 
+	bool (*has_wbinvd_exit)(void);
+
 	const struct trace_print_flags *exit_reasons_str;
 };
 
@@ -576,7 +565,6 @@ enum emulation_result {
 #define EMULTYPE_SKIP		    (1 << 2)
 int emulate_instruction(struct kvm_vcpu *vcpu,
 			unsigned long cr2, u16 error_code, int emulation_type);
-void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context);
 void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
 void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
 
@@ -591,10 +579,7 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu);
 int kvm_emulate_halt(struct kvm_vcpu *vcpu);
 int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address);
 int emulate_clts(struct kvm_vcpu *vcpu);
-int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr,
-		    unsigned long *dest);
-int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr,
-		    unsigned long value);
+int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);
 
 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 seg);
@@ -602,15 +587,16 @@ 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,
 		    bool has_error_code, u32 error_code);
 
-void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
-void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
-void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
+int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
+int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
+int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
 void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8);
 int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val);
 int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val);
 unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu);
 void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw);
 void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l);
+int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr);
 
 int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata);
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data);
@@ -630,12 +616,7 @@ int kvm_pic_set_irq(void *opaque, int irq, int level);
 
 void kvm_inject_nmi(struct kvm_vcpu *vcpu);
 
-void fx_init(struct kvm_vcpu *vcpu);
-
-int emulator_write_emulated(unsigned long addr,
-			    const void *val,
-			    unsigned int bytes,
-			    struct kvm_vcpu *vcpu);
+int fx_init(struct kvm_vcpu *vcpu);
 
 void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu);
 void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
@@ -664,8 +645,6 @@ void kvm_disable_tdp(void);
 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);
-
 static inline struct kvm_mmu_page *page_header(hpa_t shadow_page)
 {
 	struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT);
@@ -719,21 +698,6 @@ static inline unsigned long read_msr(unsigned long msr)
 }
 #endif
 
-static inline void kvm_fx_save(struct i387_fxsave_struct *image)
-{
-	asm("fxsave (%0)":: "r" (image));
-}
-
-static inline void kvm_fx_restore(struct i387_fxsave_struct *image)
-{
-	asm("fxrstor (%0)":: "r" (image));
-}
-
-static inline void kvm_fx_finit(void)
-{
-	asm("finit");
-}
-
 static inline u32 get_rdx_init_val(void)
 {
 	return 0x600; /* P6 family */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 8c7ae4318629..509a42187dc2 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -20,6 +20,7 @@
 #define _EFER_LMA		10 /* Long mode active (read-only) */
 #define _EFER_NX		11 /* No execute enable */
 #define _EFER_SVME		12 /* Enable virtualization */
+#define _EFER_LMSLE		13 /* Long Mode Segment Limit Enable */
 #define _EFER_FFXSR		14 /* Enable Fast FXSAVE/FXRSTOR */
 
 #define EFER_SCE		(1<<_EFER_SCE)
@@ -27,6 +28,7 @@
 #define EFER_LMA		(1<<_EFER_LMA)
 #define EFER_NX			(1<<_EFER_NX)
 #define EFER_SVME		(1<<_EFER_SVME)
+#define EFER_LMSLE		(1<<_EFER_LMSLE)
 #define EFER_FFXSR		(1<<_EFER_FFXSR)
 
 /* Intel MSRs. Some also available on other CPUs */
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 9e6779f7cf2d..9f0cbd987d50 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -257,6 +257,7 @@ enum vmcs_field {
 #define EXIT_REASON_IO_INSTRUCTION      30
 #define EXIT_REASON_MSR_READ            31
 #define EXIT_REASON_MSR_WRITE           32
+#define EXIT_REASON_INVALID_STATE	33
 #define EXIT_REASON_MWAIT_INSTRUCTION   36
 #define EXIT_REASON_MONITOR_INSTRUCTION 39
 #define EXIT_REASON_PAUSE_INSTRUCTION   40
@@ -266,6 +267,7 @@ enum vmcs_field {
 #define EXIT_REASON_EPT_VIOLATION       48
 #define EXIT_REASON_EPT_MISCONFIG       49
 #define EXIT_REASON_WBINVD		54
+#define EXIT_REASON_XSETBV		55
 
 /*
  * Interruption-information format
@@ -375,6 +377,9 @@ enum vmcs_field {
 #define VMX_EPT_EXTENT_CONTEXT_BIT		(1ull << 25)
 #define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
 
+#define VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT      (1ull << 9) /* (41 - 32) */
+#define VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT      (1ull << 10) /* (42 - 32) */
+
 #define VMX_EPT_DEFAULT_GAW			3
 #define VMX_EPT_MAX_GAW				0x4
 #define VMX_EPT_MT_EPTE_SHIFT			3
diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h
index 2c4390cae228..32c36668fa7b 100644
--- a/arch/x86/include/asm/xsave.h
+++ b/arch/x86/include/asm/xsave.h
@@ -13,6 +13,12 @@
 
 #define FXSAVE_SIZE	512
 
+#define XSAVE_HDR_SIZE	    64
+#define XSAVE_HDR_OFFSET    FXSAVE_SIZE
+
+#define XSAVE_YMM_SIZE	    256
+#define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
+
 /*
  * These are the features that the OS can handle currently.
  */