Merge branch 'kvm-updates/2.6.37' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.37' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (321 commits)
  KVM: Drop CONFIG_DMAR dependency around kvm_iommu_map_pages
  KVM: Fix signature of kvm_iommu_map_pages stub
  KVM: MCE: Send SRAR SIGBUS directly
  KVM: MCE: Add MCG_SER_P into KVM_MCE_CAP_SUPPORTED
  KVM: fix typo in copyright notice
  KVM: Disable interrupts around get_kernel_ns()
  KVM: MMU: Avoid sign extension in mmu_alloc_direct_roots() pae root address
  KVM: MMU: move access code parsing to FNAME(walk_addr) function
  KVM: MMU: audit: check whether have unsync sps after root sync
  KVM: MMU: audit: introduce audit_printk to cleanup audit code
  KVM: MMU: audit: unregister audit tracepoints before module unloaded
  KVM: MMU: audit: fix vcpu's spte walking
  KVM: MMU: set access bit for direct mapping
  KVM: MMU: cleanup for error mask set while walk guest page table
  KVM: MMU: update 'root_hpa' out of loop in PAE shadow path
  KVM: x86 emulator: Eliminate compilation warning in x86_decode_insn()
  KVM: x86: Fix constant type in kvm_get_time_scale
  KVM: VMX: Add AX to list of registers clobbered by guest switch
  KVM guest: Move a printk that's using the clock before it's ready
  KVM: x86: TSC catchup mode
  ...

5 files changed, 134 insertions, 22 deletions

diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 1f99ecf..b36c6b3 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -139,6 +139,7 @@ struct x86_emulate_ops {
 	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);
+	void (*get_idt)(struct desc_ptr *dt, struct kvm_vcpu *vcpu);
 	ulong (*get_cr)(int cr, struct kvm_vcpu *vcpu);
 	int (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu);
 	int (*cpl)(struct kvm_vcpu *vcpu);
@@ -156,7 +157,10 @@ struct operand {
 		unsigned long orig_val;
 		u64 orig_val64;
 	};
-	unsigned long *ptr;
+	union {
+		unsigned long *reg;
+		unsigned long mem;
+	} addr;
 	union {
 		unsigned long val;
 		u64 val64;
@@ -190,6 +194,7 @@ struct decode_cache {
 	bool has_seg_override;
 	u8 seg_override;
 	unsigned int d;
+	int (*execute)(struct x86_emulate_ctxt *ctxt);
 	unsigned long regs[NR_VCPU_REGS];
 	unsigned long eip;
 	/* modrm */
@@ -197,17 +202,16 @@ struct decode_cache {
 	u8 modrm_mod;
 	u8 modrm_reg;
 	u8 modrm_rm;
-	u8 use_modrm_ea;
+	u8 modrm_seg;
 	bool rip_relative;
-	unsigned long modrm_ea;
-	void *modrm_ptr;
-	unsigned long modrm_val;
 	struct fetch_cache fetch;
 	struct read_cache io_read;
 	struct read_cache mem_read;
 };
 
 struct x86_emulate_ctxt {
+	struct x86_emulate_ops *ops;
+
 	/* Register state before/after emulation. */
 	struct kvm_vcpu *vcpu;
 
@@ -220,12 +224,11 @@ struct x86_emulate_ctxt {
 	/* interruptibility state, as a result of execution of STI or MOV SS */
 	int interruptibility;
 
-	bool restart; /* restart string instruction after writeback */
+	bool perm_ok; /* do not check permissions if true */
 
 	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;
@@ -249,13 +252,14 @@ struct x86_emulate_ctxt {
 #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT64
 #endif
 
-int x86_decode_insn(struct x86_emulate_ctxt *ctxt,
-		    struct x86_emulate_ops *ops);
-int x86_emulate_insn(struct x86_emulate_ctxt *ctxt,
-		     struct x86_emulate_ops *ops);
+int x86_decode_insn(struct x86_emulate_ctxt *ctxt);
+#define EMULATION_FAILED -1
+#define EMULATION_OK 0
+#define EMULATION_RESTART 1
+int x86_emulate_insn(struct x86_emulate_ctxt *ctxt);
 int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
-			 struct x86_emulate_ops *ops,
 			 u16 tss_selector, int reason,
 			 bool has_error_code, u32 error_code);
-
+int emulate_int_real(struct x86_emulate_ctxt *ctxt,
+		     struct x86_emulate_ops *ops, int irq);
 #endif /* _ASM_X86_KVM_X86_EMULATE_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c52e2eb..9e6fe39 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -236,10 +236,14 @@ struct kvm_pio_request {
  */
 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);
 	int (*page_fault)(struct kvm_vcpu *vcpu, gva_t gva, u32 err);
+	void (*inject_page_fault)(struct kvm_vcpu *vcpu);
 	void (*free)(struct kvm_vcpu *vcpu);
 	gpa_t (*gva_to_gpa)(struct kvm_vcpu *vcpu, gva_t gva, u32 access,
 			    u32 *error);
+	gpa_t (*translate_gpa)(struct kvm_vcpu *vcpu, gpa_t gpa, u32 access);
 	void (*prefetch_page)(struct kvm_vcpu *vcpu,
 			      struct kvm_mmu_page *page);
 	int (*sync_page)(struct kvm_vcpu *vcpu,
@@ -249,13 +253,18 @@ struct kvm_mmu {
 	int root_level;
 	int shadow_root_level;
 	union kvm_mmu_page_role base_role;
+	bool direct_map;
 
 	u64 *pae_root;
+	u64 *lm_root;
 	u64 rsvd_bits_mask[2][4];
+
+	bool nx;
+
+	u64 pdptrs[4]; /* pae */
 };
 
 struct kvm_vcpu_arch {
-	u64 host_tsc;
 	/*
 	 * rip and regs accesses must go through
 	 * kvm_{register,rip}_{read,write} functions.
@@ -272,7 +281,6 @@ struct kvm_vcpu_arch {
 	unsigned long cr4_guest_owned_bits;
 	unsigned long cr8;
 	u32 hflags;
-	u64 pdptrs[4]; /* pae */
 	u64 efer;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
@@ -282,7 +290,41 @@ struct kvm_vcpu_arch {
 	u64 ia32_misc_enable_msr;
 	bool tpr_access_reporting;
 
+	/*
+	 * Paging state of the vcpu
+	 *
+	 * If the vcpu runs in guest mode with two level paging this still saves
+	 * the paging mode of the l1 guest. This context is always used to
+	 * handle faults.
+	 */
 	struct kvm_mmu mmu;
+
+	/*
+	 * Paging state of an L2 guest (used for nested npt)
+	 *
+	 * This context will save all necessary information to walk page tables
+	 * of the an L2 guest. This context is only initialized for page table
+	 * walking and not for faulting since we never handle l2 page faults on
+	 * the host.
+	 */
+	struct kvm_mmu nested_mmu;
+
+	/*
+	 * Pointer to the mmu context currently used for
+	 * gva_to_gpa translations.
+	 */
+	struct kvm_mmu *walk_mmu;
+
+	/*
+	 * This struct is filled with the necessary information to propagate a
+	 * page fault into the guest
+	 */
+	struct {
+		u64      address;
+		unsigned error_code;
+		bool     nested;
+	} fault;
+
 	/* only needed in kvm_pv_mmu_op() path, but it's hot so
 	 * put it here to avoid allocation */
 	struct kvm_pv_mmu_op_buffer mmu_op_buffer;
@@ -336,9 +378,15 @@ struct kvm_vcpu_arch {
 
 	gpa_t time;
 	struct pvclock_vcpu_time_info hv_clock;
-	unsigned int hv_clock_tsc_khz;
+	unsigned int hw_tsc_khz;
 	unsigned int time_offset;
 	struct page *time_page;
+	u64 last_host_tsc;
+	u64 last_guest_tsc;
+	u64 last_kernel_ns;
+	u64 last_tsc_nsec;
+	u64 last_tsc_write;
+	bool tsc_catchup;
 
 	bool nmi_pending;
 	bool nmi_injected;
@@ -367,9 +415,9 @@ struct kvm_vcpu_arch {
 };
 
 struct kvm_arch {
-	unsigned int n_free_mmu_pages;
+	unsigned int n_used_mmu_pages;
 	unsigned int n_requested_mmu_pages;
-	unsigned int n_alloc_mmu_pages;
+	unsigned int n_max_mmu_pages;
 	atomic_t invlpg_counter;
 	struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
 	/*
@@ -394,8 +442,14 @@ struct kvm_arch {
 	gpa_t ept_identity_map_addr;
 
 	unsigned long irq_sources_bitmap;
-	u64 vm_init_tsc;
 	s64 kvmclock_offset;
+	spinlock_t tsc_write_lock;
+	u64 last_tsc_nsec;
+	u64 last_tsc_offset;
+	u64 last_tsc_write;
+	u32 virtual_tsc_khz;
+	u32 virtual_tsc_mult;
+	s8 virtual_tsc_shift;
 
 	struct kvm_xen_hvm_config xen_hvm_config;
 
@@ -505,6 +559,7 @@ struct kvm_x86_ops {
 	void (*queue_exception)(struct kvm_vcpu *vcpu, unsigned nr,
 				bool has_error_code, u32 error_code,
 				bool reinject);
+	void (*cancel_injection)(struct kvm_vcpu *vcpu);
 	int (*interrupt_allowed)(struct kvm_vcpu *vcpu);
 	int (*nmi_allowed)(struct kvm_vcpu *vcpu);
 	bool (*get_nmi_mask)(struct kvm_vcpu *vcpu);
@@ -517,11 +572,16 @@ 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);
+	void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment);
+
+	void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
 
 	void (*set_supported_cpuid)(u32 func, struct kvm_cpuid_entry2 *entry);
 
 	bool (*has_wbinvd_exit)(void);
 
+	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
+
 	const struct trace_print_flags *exit_reasons_str;
 };
 
@@ -544,7 +604,7 @@ void kvm_mmu_zap_all(struct kvm *kvm);
 unsigned int kvm_mmu_calculate_mmu_pages(struct kvm *kvm);
 void kvm_mmu_change_mmu_pages(struct kvm *kvm, unsigned int kvm_nr_mmu_pages);
 
-int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
+int load_pdptrs(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu, unsigned long cr3);
 
 int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
 			  const void *val, int bytes);
@@ -608,8 +668,11 @@ void kvm_queue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_queue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
 void kvm_requeue_exception(struct kvm_vcpu *vcpu, unsigned nr);
 void kvm_requeue_exception_e(struct kvm_vcpu *vcpu, unsigned nr, u32 error_code);
-void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long cr2,
-			   u32 error_code);
+void kvm_inject_page_fault(struct kvm_vcpu *vcpu);
+int kvm_read_guest_page_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+			    gfn_t gfn, void *data, int offset, int len,
+			    u32 access);
+void kvm_propagate_fault(struct kvm_vcpu *vcpu);
 bool kvm_require_cpl(struct kvm_vcpu *vcpu, int required_cpl);
 
 int kvm_pic_set_irq(void *opaque, int irq, int level);
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 05eba5e..7b562b6 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -158,6 +158,12 @@ static inline unsigned int kvm_arch_para_features(void)
 	return cpuid_eax(KVM_CPUID_FEATURES);
 }
 
+#ifdef CONFIG_KVM_GUEST
+void __init kvm_guest_init(void);
+#else
+#define kvm_guest_init() do { } while (0)
 #endif
 
+#endif /* __KERNEL__ */
+
 #endif /* _ASM_X86_KVM_PARA_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 986f779..83c4bb1 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -198,6 +198,7 @@
 #define MSR_IA32_TSC			0x00000010
 #define MSR_IA32_PLATFORM_ID		0x00000017
 #define MSR_IA32_EBL_CR_POWERON		0x0000002a
+#define MSR_EBC_FREQUENCY_ID		0x0000002c
 #define MSR_IA32_FEATURE_CONTROL        0x0000003a
 
 #define FEATURE_CONTROL_LOCKED				(1<<0)
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index cd02f32..7f7e577 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -12,4 +12,42 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall,
 			    struct pvclock_vcpu_time_info *vcpu,
 			    struct timespec *ts);
 
+/*
+ * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
+ * yielding a 64-bit result.
+ */
+static inline u64 pvclock_scale_delta(u64 delta, u32 mul_frac, int shift)
+{
+	u64 product;
+#ifdef __i386__
+	u32 tmp1, tmp2;
+#endif
+
+	if (shift < 0)
+		delta >>= -shift;
+	else
+		delta <<= shift;
+
+#ifdef __i386__
+	__asm__ (
+		"mul  %5       ; "
+		"mov  %4,%%eax ; "
+		"mov  %%edx,%4 ; "
+		"mul  %5       ; "
+		"xor  %5,%5    ; "
+		"add  %4,%%eax ; "
+		"adc  %5,%%edx ; "
+		: "=A" (product), "=r" (tmp1), "=r" (tmp2)
+		: "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
+#elif defined(__x86_64__)
+	__asm__ (
+		"mul %%rdx ; shrd $32,%%rdx,%%rax"
+		: "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
+#else
+#error implement me!
+#endif
+
+	return product;
+}
+
 #endif /* _ASM_X86_PVCLOCK_H */