Merge branch 'kvm-updates/2.6.40' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.40' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (131 commits)
  KVM: MMU: Use ptep_user for cmpxchg_gpte()
  KVM: Fix kvm mmu_notifier initialization order
  KVM: Add documentation for KVM_CAP_NR_VCPUS
  KVM: make guest mode entry to be rcu quiescent state
  KVM: x86 emulator: Make jmp far emulation into a separate function
  KVM: x86 emulator: Rename emulate_grpX() to em_grpX()
  KVM: x86 emulator: Remove unused arg from emulate_pop()
  KVM: x86 emulator: Remove unused arg from writeback()
  KVM: x86 emulator: Remove unused arg from read_descriptor()
  KVM: x86 emulator: Remove unused arg from seg_override()
  KVM: Validate userspace_addr of memslot when registered
  KVM: MMU: Clean up gpte reading with copy_from_user()
  KVM: PPC: booke: add sregs support
  KVM: PPC: booke: save/restore VRSAVE (a.k.a. USPRG0)
  KVM: PPC: use ticks, not usecs, for exit timing
  KVM: PPC: fix exit accounting for SPRs, tlbwe, tlbsx
  KVM: PPC: e500: emulate SVR
  KVM: VMX: Cache vmcs segment fields
  KVM: x86 emulator: consolidate segment accessors
  KVM: VMX: Avoid reading %rip unnecessarily when handling exceptions
  ...

Documentation/virtual/kvm/api.txt

@@ -175,7 +175,10 @@ Parameters: vcpu id (apic id on x86)
 Returns: vcpu fd on success, -1 on error
 
 This API adds a vcpu to a virtual machine.  The vcpu id is a small integer
-in the range [0, max_vcpus).
+in the range [0, max_vcpus).  You can use KVM_CAP_NR_VCPUS of the
+KVM_CHECK_EXTENSION ioctl() to determine the value for max_vcpus at run-time.
+If the KVM_CAP_NR_VCPUS does not exist, you should assume that max_vcpus is 4
+cpus max.
 
 4.8 KVM_GET_DIRTY_LOG (vm ioctl)
 
@@ -261,7 +264,7 @@ See KVM_GET_REGS for the data structure.
 4.13 KVM_GET_SREGS
 
 Capability: basic
-Architectures: x86
+Architectures: x86, ppc
 Type: vcpu ioctl
 Parameters: struct kvm_sregs (out)
 Returns: 0 on success, -1 on error
@@ -279,6 +282,8 @@ struct kvm_sregs {
 	__u64 interrupt_bitmap[(KVM_NR_INTERRUPTS + 63) / 64];
 };
 
+/* ppc -- see arch/powerpc/include/asm/kvm.h */
+
 interrupt_bitmap is a bitmap of pending external interrupts.  At most
 one bit may be set.  This interrupt has been acknowledged by the APIC
 but not yet injected into the cpu core.
@@ -286,7 +291,7 @@ but not yet injected into the cpu core.
 4.14 KVM_SET_SREGS
 
 Capability: basic
-Architectures: x86
+Architectures: x86, ppc
 Type: vcpu ioctl
 Parameters: struct kvm_sregs (in)
 Returns: 0 on success, -1 on error
@@ -1263,6 +1268,29 @@ struct kvm_assigned_msix_entry {
 	__u16 padding[3];
 };
 
+4.54 KVM_SET_TSC_KHZ
+
+Capability: KVM_CAP_TSC_CONTROL
+Architectures: x86
+Type: vcpu ioctl
+Parameters: virtual tsc_khz
+Returns: 0 on success, -1 on error
+
+Specifies the tsc frequency for the virtual machine. The unit of the
+frequency is KHz.
+
+4.55 KVM_GET_TSC_KHZ
+
+Capability: KVM_CAP_GET_TSC_KHZ
+Architectures: x86
+Type: vcpu ioctl
+Parameters: none
+Returns: virtual tsc-khz on success, negative value on error
+
+Returns the tsc frequency of the guest. The unit of the return value is
+KHz. If the host has unstable tsc this ioctl returns -EIO instead as an
+error.
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by

arch/ia64/kvm/vti.h

@@ -83,13 +83,13 @@
 union vac {
 	unsigned long value;
 	struct {
-		int a_int:1;
-		int a_from_int_cr:1;
-		int a_to_int_cr:1;
-		int a_from_psr:1;
-		int a_from_cpuid:1;
-		int a_cover:1;
-		int a_bsw:1;
+		unsigned int a_int:1;
+		unsigned int a_from_int_cr:1;
+		unsigned int a_to_int_cr:1;
+		unsigned int a_from_psr:1;
+		unsigned int a_from_cpuid:1;
+		unsigned int a_cover:1;
+		unsigned int a_bsw:1;
 		long reserved:57;
 	};
 };
@@ -97,12 +97,12 @@ union vac {
 union vdc {
 	unsigned long value;
 	struct {
-		int d_vmsw:1;
-		int d_extint:1;
-		int d_ibr_dbr:1;
-		int d_pmc:1;
-		int d_to_pmd:1;
-		int d_itm:1;
+		unsigned int d_vmsw:1;
+		unsigned int d_extint:1;
+		unsigned int d_ibr_dbr:1;
+		unsigned int d_pmc:1;
+		unsigned int d_to_pmd:1;
+		unsigned int d_itm:1;
 		long reserved:58;
 	};
 };

arch/powerpc/include/asm/kvm.h

@@ -45,6 +45,114 @@ struct kvm_regs {
 	__u64 gpr[32];
 };
 
+#define KVM_SREGS_E_IMPL_NONE	0
+#define KVM_SREGS_E_IMPL_FSL	1
+
+#define KVM_SREGS_E_FSL_PIDn	(1 << 0) /* PID1/PID2 */
+
+/*
+ * Feature bits indicate which sections of the sregs struct are valid,
+ * both in KVM_GET_SREGS and KVM_SET_SREGS.  On KVM_SET_SREGS, registers
+ * corresponding to unset feature bits will not be modified.  This allows
+ * restoring a checkpoint made without that feature, while keeping the
+ * default values of the new registers.
+ *
+ * KVM_SREGS_E_BASE contains:
+ * CSRR0/1 (refers to SRR2/3 on 40x)
+ * ESR
+ * DEAR
+ * MCSR
+ * TSR
+ * TCR
+ * DEC
+ * TB
+ * VRSAVE (USPRG0)
+ */
+#define KVM_SREGS_E_BASE		(1 << 0)
+
+/*
+ * KVM_SREGS_E_ARCH206 contains:
+ *
+ * PIR
+ * MCSRR0/1
+ * DECAR
+ * IVPR
+ */
+#define KVM_SREGS_E_ARCH206		(1 << 1)
+
+/*
+ * Contains EPCR, plus the upper half of 64-bit registers
+ * that are 32-bit on 32-bit implementations.
+ */
+#define KVM_SREGS_E_64			(1 << 2)
+
+#define KVM_SREGS_E_SPRG8		(1 << 3)
+#define KVM_SREGS_E_MCIVPR		(1 << 4)
+
+/*
+ * IVORs are used -- contains IVOR0-15, plus additional IVORs
+ * in combination with an appropriate feature bit.
+ */
+#define KVM_SREGS_E_IVOR		(1 << 5)
+
+/*
+ * Contains MAS0-4, MAS6-7, TLBnCFG, MMUCFG.
+ * Also TLBnPS if MMUCFG[MAVN] = 1.
+ */
+#define KVM_SREGS_E_ARCH206_MMU		(1 << 6)
+
+/* DBSR, DBCR, IAC, DAC, DVC */
+#define KVM_SREGS_E_DEBUG		(1 << 7)
+
+/* Enhanced debug -- DSRR0/1, SPRG9 */
+#define KVM_SREGS_E_ED			(1 << 8)
+
+/* Embedded Floating Point (SPE) -- IVOR32-34 if KVM_SREGS_E_IVOR */
+#define KVM_SREGS_E_SPE			(1 << 9)
+
+/* External Proxy (EXP) -- EPR */
+#define KVM_SREGS_EXP			(1 << 10)
+
+/* External PID (E.PD) -- EPSC/EPLC */
+#define KVM_SREGS_E_PD			(1 << 11)
+
+/* Processor Control (E.PC) -- IVOR36-37 if KVM_SREGS_E_IVOR */
+#define KVM_SREGS_E_PC			(1 << 12)
+
+/* Page table (E.PT) -- EPTCFG */
+#define KVM_SREGS_E_PT			(1 << 13)
+
+/* Embedded Performance Monitor (E.PM) -- IVOR35 if KVM_SREGS_E_IVOR */
+#define KVM_SREGS_E_PM			(1 << 14)
+
+/*
+ * Special updates:
+ *
+ * Some registers may change even while a vcpu is not running.
+ * To avoid losing these changes, by default these registers are
+ * not updated by KVM_SET_SREGS.  To force an update, set the bit
+ * in u.e.update_special corresponding to the register to be updated.
+ *
+ * The update_special field is zero on return from KVM_GET_SREGS.
+ *
+ * When restoring a checkpoint, the caller can set update_special
+ * to 0xffffffff to ensure that everything is restored, even new features
+ * that the caller doesn't know about.
+ */
+#define KVM_SREGS_E_UPDATE_MCSR		(1 << 0)
+#define KVM_SREGS_E_UPDATE_TSR		(1 << 1)
+#define KVM_SREGS_E_UPDATE_DEC		(1 << 2)
+#define KVM_SREGS_E_UPDATE_DBSR		(1 << 3)
+
+/*
+ * In KVM_SET_SREGS, reserved/pad fields must be left untouched from a
+ * previous KVM_GET_REGS.
+ *
+ * Unless otherwise indicated, setting any register with KVM_SET_SREGS
+ * directly sets its value.  It does not trigger any special semantics such
+ * as write-one-to-clear.  Calling KVM_SET_SREGS on an unmodified struct
+ * just received from KVM_GET_SREGS is always a no-op.
+ */
 struct kvm_sregs {
 	__u32 pvr;
 	union {
@@ -62,6 +170,82 @@ struct kvm_sregs {
 				__u64 dbat[8]; 
 			} ppc32;
 		} s;
+		struct {
+			union {
+				struct { /* KVM_SREGS_E_IMPL_FSL */
+					__u32 features; /* KVM_SREGS_E_FSL_ */
+					__u32 svr;
+					__u64 mcar;
+					__u32 hid0;
+
+					/* KVM_SREGS_E_FSL_PIDn */
+					__u32 pid1, pid2;
+				} fsl;
+				__u8 pad[256];
+			} impl;
+
+			__u32 features; /* KVM_SREGS_E_ */
+			__u32 impl_id;	/* KVM_SREGS_E_IMPL_ */
+			__u32 update_special; /* KVM_SREGS_E_UPDATE_ */
+			__u32 pir;	/* read-only */
+			__u64 sprg8;
+			__u64 sprg9;	/* E.ED */
+			__u64 csrr0;
+			__u64 dsrr0;	/* E.ED */
+			__u64 mcsrr0;
+			__u32 csrr1;
+			__u32 dsrr1;	/* E.ED */
+			__u32 mcsrr1;
+			__u32 esr;
+			__u64 dear;
+			__u64 ivpr;
+			__u64 mcivpr;
+			__u64 mcsr;	/* KVM_SREGS_E_UPDATE_MCSR */
+
+			__u32 tsr;	/* KVM_SREGS_E_UPDATE_TSR */
+			__u32 tcr;
+			__u32 decar;
+			__u32 dec;	/* KVM_SREGS_E_UPDATE_DEC */
+
+			/*
+			 * Userspace can read TB directly, but the
+			 * value reported here is consistent with "dec".
+			 *
+			 * Read-only.
+			 */
+			__u64 tb;
+
+			__u32 dbsr;	/* KVM_SREGS_E_UPDATE_DBSR */
+			__u32 dbcr[3];
+			__u32 iac[4];
+			__u32 dac[2];
+			__u32 dvc[2];
+			__u8 num_iac;	/* read-only */
+			__u8 num_dac;	/* read-only */
+			__u8 num_dvc;	/* read-only */
+			__u8 pad;
+
+			__u32 epr;	/* EXP */
+			__u32 vrsave;	/* a.k.a. USPRG0 */
+			__u32 epcr;	/* KVM_SREGS_E_64 */
+
+			__u32 mas0;
+			__u32 mas1;
+			__u64 mas2;
+			__u64 mas7_3;
+			__u32 mas4;
+			__u32 mas6;
+
+			__u32 ivor_low[16]; /* IVOR0-15 */
+			__u32 ivor_high[18]; /* IVOR32+, plus room to expand */
+
+			__u32 mmucfg;	/* read-only */
+			__u32 eptcfg;	/* E.PT, read-only */
+			__u32 tlbcfg[4];/* read-only */
+			__u32 tlbps[4]; /* read-only */
+
+			__u32 eplc, epsc; /* E.PD */
+		} e;
 		__u8 pad[1020];
 	} u;
 };

arch/powerpc/include/asm/kvm_44x.h

@@ -61,7 +61,6 @@ static inline struct kvmppc_vcpu_44x *to_44x(struct kvm_vcpu *vcpu)
 	return container_of(vcpu, struct kvmppc_vcpu_44x, vcpu);
 }
 
-void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 new_pid);
 void kvmppc_44x_tlb_put(struct kvm_vcpu *vcpu);
 void kvmppc_44x_tlb_load(struct kvm_vcpu *vcpu);
 

arch/powerpc/include/asm/kvm_e500.h

@@ -43,6 +43,7 @@ struct kvmppc_vcpu_e500 {
 
 	u32 host_pid[E500_PID_NUM];
 	u32 pid[E500_PID_NUM];
+	u32 svr;
 
 	u32 mas0;
 	u32 mas1;
@@ -58,6 +59,7 @@ struct kvmppc_vcpu_e500 {
 	u32 hid1;
 	u32 tlb0cfg;
 	u32 tlb1cfg;
+	u64 mcar;
 
 	struct kvm_vcpu vcpu;
 };

arch/powerpc/include/asm/kvm_host.h

@@ -223,6 +223,7 @@ struct kvm_vcpu_arch {
 	ulong hflags;
 	ulong guest_owned_ext;
 #endif
+	u32 vrsave; /* also USPRG0 */
 	u32 mmucr;
 	ulong sprg4;
 	ulong sprg5;
@@ -232,6 +233,9 @@ struct kvm_vcpu_arch {
 	ulong csrr1;
 	ulong dsrr0;
 	ulong dsrr1;
+	ulong mcsrr0;
+	ulong mcsrr1;
+	ulong mcsr;
 	ulong esr;
 	u32 dec;
 	u32 decar;
@@ -255,6 +259,7 @@ struct kvm_vcpu_arch {
 	u32 dbsr;
 
 #ifdef CONFIG_KVM_EXIT_TIMING
+	struct mutex exit_timing_lock;
 	struct kvmppc_exit_timing timing_exit;
 	struct kvmppc_exit_timing timing_last_enter;
 	u32 last_exit_type;

arch/powerpc/include/asm/kvm_ppc.h

@@ -61,6 +61,7 @@ extern int kvmppc_emulate_instruction(struct kvm_run *run,
                                       struct kvm_vcpu *vcpu);
 extern int kvmppc_emulate_mmio(struct kvm_run *run, struct kvm_vcpu *vcpu);
 extern void kvmppc_emulate_dec(struct kvm_vcpu *vcpu);
+extern u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb);
 
 /* Core-specific hooks */
 
@@ -142,4 +143,12 @@ static inline u32 kvmppc_set_field(u64 inst, int msb, int lsb, int value)
 	return r;
 }
 
+void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
+int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
+
+void kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
+int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs);
+
+void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid);
+
 #endif /* __POWERPC_KVM_PPC_H__ */

arch/powerpc/kernel/asm-offsets.c

@@ -396,6 +396,7 @@ int main(void)
 	DEFINE(VCPU_HOST_STACK, offsetof(struct kvm_vcpu, arch.host_stack));
 	DEFINE(VCPU_HOST_PID, offsetof(struct kvm_vcpu, arch.host_pid));
 	DEFINE(VCPU_GPRS, offsetof(struct kvm_vcpu, arch.gpr));
+	DEFINE(VCPU_VRSAVE, offsetof(struct kvm_vcpu, arch.vrsave));
 	DEFINE(VCPU_SPRG4, offsetof(struct kvm_vcpu, arch.sprg4));
 	DEFINE(VCPU_SPRG5, offsetof(struct kvm_vcpu, arch.sprg5));
 	DEFINE(VCPU_SPRG6, offsetof(struct kvm_vcpu, arch.sprg6));

arch/powerpc/kvm/44x.c

@@ -107,6 +107,16 @@ int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+	kvmppc_get_sregs_ivor(vcpu, sregs);
+}
+
+int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+	return kvmppc_set_sregs_ivor(vcpu, sregs);
+}
+
 struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 {
 	struct kvmppc_vcpu_44x *vcpu_44x;

arch/powerpc/kvm/44x_emulate.c

@@ -158,7 +158,6 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 		emulated = kvmppc_booke_emulate_mtspr(vcpu, sprn, rs);
 	}
 
-	kvmppc_set_exit_type(vcpu, EMULATED_MTSPR_EXITS);
 	return emulated;
 }
 
@@ -179,7 +178,6 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		emulated = kvmppc_booke_emulate_mfspr(vcpu, sprn, rt);
 	}
 
-	kvmppc_set_exit_type(vcpu, EMULATED_MFSPR_EXITS);
 	return emulated;
 }
 

arch/powerpc/kvm/booke.c

@@ -569,6 +569,7 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	kvmppc_set_msr(vcpu, regs->msr);
 	vcpu->arch.shared->srr0 = regs->srr0;
 	vcpu->arch.shared->srr1 = regs->srr1;
+	kvmppc_set_pid(vcpu, regs->pid);
 	vcpu->arch.shared->sprg0 = regs->sprg0;
 	vcpu->arch.shared->sprg1 = regs->sprg1;
 	vcpu->arch.shared->sprg2 = regs->sprg2;
@@ -584,16 +585,165 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	return 0;
 }
 
+static void get_sregs_base(struct kvm_vcpu *vcpu,
+                           struct kvm_sregs *sregs)
+{
+	u64 tb = get_tb();
+
+	sregs->u.e.features |= KVM_SREGS_E_BASE;
+
+	sregs->u.e.csrr0 = vcpu->arch.csrr0;
+	sregs->u.e.csrr1 = vcpu->arch.csrr1;
+	sregs->u.e.mcsr = vcpu->arch.mcsr;
+	sregs->u.e.esr = vcpu->arch.esr;
+	sregs->u.e.dear = vcpu->arch.shared->dar;
+	sregs->u.e.tsr = vcpu->arch.tsr;
+	sregs->u.e.tcr = vcpu->arch.tcr;
+	sregs->u.e.dec = kvmppc_get_dec(vcpu, tb);
+	sregs->u.e.tb = tb;
+	sregs->u.e.vrsave = vcpu->arch.vrsave;
+}
+
+static int set_sregs_base(struct kvm_vcpu *vcpu,
+                          struct kvm_sregs *sregs)
+{
+	if (!(sregs->u.e.features & KVM_SREGS_E_BASE))
+		return 0;
+
+	vcpu->arch.csrr0 = sregs->u.e.csrr0;
+	vcpu->arch.csrr1 = sregs->u.e.csrr1;
+	vcpu->arch.mcsr = sregs->u.e.mcsr;
+	vcpu->arch.esr = sregs->u.e.esr;
+	vcpu->arch.shared->dar = sregs->u.e.dear;
+	vcpu->arch.vrsave = sregs->u.e.vrsave;
+	vcpu->arch.tcr = sregs->u.e.tcr;
+
+	if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_DEC)
+		vcpu->arch.dec = sregs->u.e.dec;
+
+	kvmppc_emulate_dec(vcpu);
+
+	if (sregs->u.e.update_special & KVM_SREGS_E_UPDATE_TSR) {
+		/*
+		 * FIXME: existing KVM timer handling is incomplete.
+		 * TSR cannot be read by the guest, and its value in
+		 * vcpu->arch is always zero.  For now, just handle
+		 * the case where the caller is trying to inject a
+		 * decrementer interrupt.
+		 */
+
+		if ((sregs->u.e.tsr & TSR_DIS) &&
+		    (vcpu->arch.tcr & TCR_DIE))
+			kvmppc_core_queue_dec(vcpu);
+	}
+
+	return 0;
+}
+
+static void get_sregs_arch206(struct kvm_vcpu *vcpu,
+                              struct kvm_sregs *sregs)
+{
+	sregs->u.e.features |= KVM_SREGS_E_ARCH206;
+
+	sregs->u.e.pir = 0;
+	sregs->u.e.mcsrr0 = vcpu->arch.mcsrr0;
+	sregs->u.e.mcsrr1 = vcpu->arch.mcsrr1;
+	sregs->u.e.decar = vcpu->arch.decar;
+	sregs->u.e.ivpr = vcpu->arch.ivpr;
+}
+
+static int set_sregs_arch206(struct kvm_vcpu *vcpu,
+                             struct kvm_sregs *sregs)
+{
+	if (!(sregs->u.e.features & KVM_SREGS_E_ARCH206))
+		return 0;
+
+	if (sregs->u.e.pir != 0)
+		return -EINVAL;
+
+	vcpu->arch.mcsrr0 = sregs->u.e.mcsrr0;
+	vcpu->arch.mcsrr1 = sregs->u.e.mcsrr1;
+	vcpu->arch.decar = sregs->u.e.decar;
+	vcpu->arch.ivpr = sregs->u.e.ivpr;
+
+	return 0;
+}
+
+void kvmppc_get_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+	sregs->u.e.features |= KVM_SREGS_E_IVOR;
+
+	sregs->u.e.ivor_low[0] = vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL];
+	sregs->u.e.ivor_low[1] = vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK];
+	sregs->u.e.ivor_low[2] = vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE];
+	sregs->u.e.ivor_low[3] = vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE];
+	sregs->u.e.ivor_low[4] = vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL];
+	sregs->u.e.ivor_low[5] = vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT];
+	sregs->u.e.ivor_low[6] = vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM];
+	sregs->u.e.ivor_low[7] = vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL];
+	sregs->u.e.ivor_low[8] = vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL];
+	sregs->u.e.ivor_low[9] = vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL];
+	sregs->u.e.ivor_low[10] = vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER];
+	sregs->u.e.ivor_low[11] = vcpu->arch.ivor[BOOKE_IRQPRIO_FIT];
+	sregs->u.e.ivor_low[12] = vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG];
+	sregs->u.e.ivor_low[13] = vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS];
+	sregs->u.e.ivor_low[14] = vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS];
+	sregs->u.e.ivor_low[15] = vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG];
+}
+
+int kvmppc_set_sregs_ivor(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+	if (!(sregs->u.e.features & KVM_SREGS_E_IVOR))
+		return 0;
+
+	vcpu->arch.ivor[BOOKE_IRQPRIO_CRITICAL] = sregs->u.e.ivor_low[0];
+	vcpu->arch.ivor[BOOKE_IRQPRIO_MACHINE_CHECK] = sregs->u.e.ivor_low[1];
+	vcpu->arch.ivor[BOOKE_IRQPRIO_DATA_STORAGE] = sregs->u.e.ivor_low[2];
+	vcpu->arch.ivor[BOOKE_IRQPRIO_INST_STORAGE] = sregs->u.e.ivor_low[3];
+	vcpu->arch.ivor[BOOKE_IRQPRIO_EXTERNAL] = sregs->u.e.ivor_low[4];
+	vcpu->arch.ivor[BOOKE_IRQPRIO_ALIGNMENT] = sregs->u.e.ivor_low[5];
+	vcpu->arch.ivor[BOOKE_IRQPRIO_PROGRAM] = sregs->u.e.ivor_low[6];
+	vcpu->arch.ivor[BOOKE_IRQPRIO_FP_UNAVAIL] = sregs->u.e.ivor_low[7];
+	vcpu->arch.ivor[BOOKE_IRQPRIO_SYSCALL] = sregs->u.e.ivor_low[8];
+	vcpu->arch.ivor[BOOKE_IRQPRIO_AP_UNAVAIL] = sregs->u.e.ivor_low[9];
+	vcpu->arch.ivor[BOOKE_IRQPRIO_DECREMENTER] = sregs->u.e.ivor_low[10];
+	vcpu->arch.ivor[BOOKE_IRQPRIO_FIT] = sregs->u.e.ivor_low[11];
+	vcpu->arch.ivor[BOOKE_IRQPRIO_WATCHDOG] = sregs->u.e.ivor_low[12];
+	vcpu->arch.ivor[BOOKE_IRQPRIO_DTLB_MISS] = sregs->u.e.ivor_low[13];
+	vcpu->arch.ivor[BOOKE_IRQPRIO_ITLB_MISS] = sregs->u.e.ivor_low[14];
+	vcpu->arch.ivor[BOOKE_IRQPRIO_DEBUG] = sregs->u.e.ivor_low[15];
+
+	return 0;
+}
+
 int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,
                                   struct kvm_sregs *sregs)
 {
-	return -ENOTSUPP;
+	sregs->pvr = vcpu->arch.pvr;
+
+	get_sregs_base(vcpu, sregs);
+	get_sregs_arch206(vcpu, sregs);
+	kvmppc_core_get_sregs(vcpu, sregs);
+	return 0;
 }
 
 int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
                                   struct kvm_sregs *sregs)
 {
-	return -ENOTSUPP;
+	int ret;
+
+	if (vcpu->arch.pvr != sregs->pvr)
+		return -EINVAL;
+
+	ret = set_sregs_base(vcpu, sregs);
+	if (ret < 0)
+		return ret;
+
+	ret = set_sregs_arch206(vcpu, sregs);
+	if (ret < 0)
+		return ret;
+
+	return kvmppc_core_set_sregs(vcpu, sregs);
 }
 
 int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)

arch/powerpc/kvm/booke_interrupts.S

@@ -380,7 +380,6 @@ lightweight_exit:
 	 * because host interrupt handlers would get confused. */
 	lwz	r1, VCPU_GPR(r1)(r4)
 
-	/* XXX handle USPRG0 */
 	/* Host interrupt handlers may have clobbered these guest-readable
 	 * SPRGs, so we need to reload them here with the guest's values. */
 	lwz	r3, VCPU_SPRG4(r4)

arch/powerpc/kvm/e500.c

@@ -63,6 +63,7 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	/* Registers init */
 	vcpu->arch.pvr = mfspr(SPRN_PVR);
+	vcpu_e500->svr = mfspr(SPRN_SVR);
 
 	/* Since booke kvm only support one core, update all vcpus' PIR to 0 */
 	vcpu->vcpu_id = 0;
@@ -96,6 +97,81 @@ int kvmppc_core_vcpu_translate(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+void kvmppc_core_get_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	sregs->u.e.features |= KVM_SREGS_E_ARCH206_MMU | KVM_SREGS_E_SPE |
+	                       KVM_SREGS_E_PM;
+	sregs->u.e.impl_id = KVM_SREGS_E_IMPL_FSL;
+
+	sregs->u.e.impl.fsl.features = 0;
+	sregs->u.e.impl.fsl.svr = vcpu_e500->svr;
+	sregs->u.e.impl.fsl.hid0 = vcpu_e500->hid0;
+	sregs->u.e.impl.fsl.mcar = vcpu_e500->mcar;
+
+	sregs->u.e.mas0 = vcpu_e500->mas0;
+	sregs->u.e.mas1 = vcpu_e500->mas1;
+	sregs->u.e.mas2 = vcpu_e500->mas2;
+	sregs->u.e.mas7_3 = ((u64)vcpu_e500->mas7 << 32) | vcpu_e500->mas3;
+	sregs->u.e.mas4 = vcpu_e500->mas4;
+	sregs->u.e.mas6 = vcpu_e500->mas6;
+
+	sregs->u.e.mmucfg = mfspr(SPRN_MMUCFG);
+	sregs->u.e.tlbcfg[0] = vcpu_e500->tlb0cfg;
+	sregs->u.e.tlbcfg[1] = vcpu_e500->tlb1cfg;
+	sregs->u.e.tlbcfg[2] = 0;
+	sregs->u.e.tlbcfg[3] = 0;
+
+	sregs->u.e.ivor_high[0] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];
+	sregs->u.e.ivor_high[1] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA];
+	sregs->u.e.ivor_high[2] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND];
+	sregs->u.e.ivor_high[3] =
+		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR];
+
+	kvmppc_get_sregs_ivor(vcpu, sregs);
+}
+
+int kvmppc_core_set_sregs(struct kvm_vcpu *vcpu, struct kvm_sregs *sregs)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	if (sregs->u.e.impl_id == KVM_SREGS_E_IMPL_FSL) {
+		vcpu_e500->svr = sregs->u.e.impl.fsl.svr;
+		vcpu_e500->hid0 = sregs->u.e.impl.fsl.hid0;
+		vcpu_e500->mcar = sregs->u.e.impl.fsl.mcar;
+	}
+
+	if (sregs->u.e.features & KVM_SREGS_E_ARCH206_MMU) {
+		vcpu_e500->mas0 = sregs->u.e.mas0;
+		vcpu_e500->mas1 = sregs->u.e.mas1;
+		vcpu_e500->mas2 = sregs->u.e.mas2;
+		vcpu_e500->mas7 = sregs->u.e.mas7_3 >> 32;
+		vcpu_e500->mas3 = (u32)sregs->u.e.mas7_3;
+		vcpu_e500->mas4 = sregs->u.e.mas4;
+		vcpu_e500->mas6 = sregs->u.e.mas6;
+	}
+
+	if (!(sregs->u.e.features & KVM_SREGS_E_IVOR))
+		return 0;
+
+	if (sregs->u.e.features & KVM_SREGS_E_SPE) {
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL] =
+			sregs->u.e.ivor_high[0];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_DATA] =
+			sregs->u.e.ivor_high[1];
+		vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_FP_ROUND] =
+			sregs->u.e.ivor_high[2];
+	}
+
+	if (sregs->u.e.features & KVM_SREGS_E_PM) {
+		vcpu->arch.ivor[BOOKE_IRQPRIO_PERFORMANCE_MONITOR] =
+			sregs->u.e.ivor_high[3];
+	}
+
+	return kvmppc_set_sregs_ivor(vcpu, sregs);
+}
+
 struct kvm_vcpu *kvmppc_core_vcpu_create(struct kvm *kvm, unsigned int id)
 {
 	struct kvmppc_vcpu_e500 *vcpu_e500;

arch/powerpc/kvm/e500_emulate.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
+ * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
  *
  * Author: Yu Liu, <yu.liu@freescale.com>
  *
@@ -78,8 +78,7 @@ int kvmppc_core_emulate_mtspr(struct kvm_vcpu *vcpu, int sprn, int rs)
 
 	switch (sprn) {
 	case SPRN_PID:
-		vcpu_e500->pid[0] = vcpu->arch.shadow_pid =
-			vcpu->arch.pid = spr_val;
+		kvmppc_set_pid(vcpu, spr_val);
 		break;
 	case SPRN_PID1:
 		vcpu_e500->pid[1] = spr_val; break;
@@ -175,6 +174,8 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 		kvmppc_set_gpr(vcpu, rt, vcpu_e500->hid0); break;
 	case SPRN_HID1:
 		kvmppc_set_gpr(vcpu, rt, vcpu_e500->hid1); break;
+	case SPRN_SVR:
+		kvmppc_set_gpr(vcpu, rt, vcpu_e500->svr); break;
 
 	case SPRN_MMUCSR0:
 		kvmppc_set_gpr(vcpu, rt, 0); break;

arch/powerpc/kvm/e500_tlb.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2008 Freescale Semiconductor, Inc. All rights reserved.
+ * Copyright (C) 2008-2011 Freescale Semiconductor, Inc. All rights reserved.
  *
  * Author: Yu Liu, yu.liu@freescale.com
  *
@@ -24,6 +24,7 @@
 #include "../mm/mmu_decl.h"
 #include "e500_tlb.h"
 #include "trace.h"
+#include "timing.h"
 
 #define to_htlb1_esel(esel) (tlb1_entry_num - (esel) - 1)
 
@@ -506,6 +507,7 @@ int kvmppc_e500_emul_tlbsx(struct kvm_vcpu *vcpu, int rb)
 		vcpu_e500->mas7 = 0;
 	}
 
+	kvmppc_set_exit_type(vcpu, EMULATED_TLBSX_EXITS);
 	return EMULATE_DONE;
 }
 
@@ -571,6 +573,7 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 		write_host_tlbe(vcpu_e500, stlbsel, sesel);
 	}
 
+	kvmppc_set_exit_type(vcpu, EMULATED_TLBWE_EXITS);
 	return EMULATE_DONE;
 }
 
@@ -672,6 +675,14 @@ int kvmppc_e500_tlb_search(struct kvm_vcpu *vcpu,
 	return -1;
 }
 
+void kvmppc_set_pid(struct kvm_vcpu *vcpu, u32 pid)
+{
+	struct kvmppc_vcpu_e500 *vcpu_e500 = to_e500(vcpu);
+
+	vcpu_e500->pid[0] = vcpu->arch.shadow_pid =
+		vcpu->arch.pid = pid;
+}
+
 void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
 {
 	struct tlbe *tlbe;

arch/powerpc/kvm/emulate.c

@@ -114,6 +114,12 @@ void kvmppc_emulate_dec(struct kvm_vcpu *vcpu)
 	}
 }
 
+u32 kvmppc_get_dec(struct kvm_vcpu *vcpu, u64 tb)
+{
+	u64 jd = tb - vcpu->arch.dec_jiffies;
+	return vcpu->arch.dec - jd;
+}
+
 /* XXX to do:
  * lhax
  * lhaux
@@ -279,11 +285,8 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 			case SPRN_DEC:
 			{
-				u64 jd = get_tb() - vcpu->arch.dec_jiffies;
-				kvmppc_set_gpr(vcpu, rt, vcpu->arch.dec - jd);
-				pr_debug("mfDEC: %x - %llx = %lx\n",
-					 vcpu->arch.dec, jd,
-					 kvmppc_get_gpr(vcpu, rt));
+				kvmppc_set_gpr(vcpu, rt,
+					       kvmppc_get_dec(vcpu, get_tb()));
 				break;
 			}
 			default:
@@ -294,6 +297,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 				}
 				break;
 			}
+			kvmppc_set_exit_type(vcpu, EMULATED_MFSPR_EXITS);
 			break;
 
 		case OP_31_XOP_STHX:
@@ -363,6 +367,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 					printk("mtspr: unknown spr %x\n", sprn);
 				break;
 			}
+			kvmppc_set_exit_type(vcpu, EMULATED_MTSPR_EXITS);
 			break;
 
 		case OP_31_XOP_DCBI:

arch/powerpc/kvm/powerpc.c

@@ -175,7 +175,11 @@ int kvm_dev_ioctl_check_extension(long ext)
 	int r;
 
 	switch (ext) {
+#ifdef CONFIG_BOOKE
+	case KVM_CAP_PPC_BOOKE_SREGS:
+#else
 	case KVM_CAP_PPC_SEGSTATE:
+#endif
 	case KVM_CAP_PPC_PAIRED_SINGLES:
 	case KVM_CAP_PPC_UNSET_IRQ:
 	case KVM_CAP_PPC_IRQ_LEVEL:
@@ -284,6 +288,10 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 	tasklet_init(&vcpu->arch.tasklet, kvmppc_decrementer_func, (ulong)vcpu);
 	vcpu->arch.dec_timer.function = kvmppc_decrementer_wakeup;
 
+#ifdef CONFIG_KVM_EXIT_TIMING
+	mutex_init(&vcpu->arch.exit_timing_lock);
+#endif
+
 	return 0;
 }
 
@@ -294,12 +302,25 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
+#ifdef CONFIG_BOOKE
+	/*
+	 * vrsave (formerly usprg0) isn't used by Linux, but may
+	 * be used by the guest.
+	 *
+	 * On non-booke this is associated with Altivec and
+	 * is handled by code in book3s.c.
+	 */
+	mtspr(SPRN_VRSAVE, vcpu->arch.vrsave);
+#endif
 	kvmppc_core_vcpu_load(vcpu, cpu);
 }
 
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
 	kvmppc_core_vcpu_put(vcpu);
+#ifdef CONFIG_BOOKE
+	vcpu->arch.vrsave = mfspr(SPRN_VRSAVE);
+#endif
 }
 
 int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,

arch/powerpc/kvm/timing.c

@@ -34,8 +34,8 @@ void kvmppc_init_timing_stats(struct kvm_vcpu *vcpu)
 {
 	int i;
 
-	/* pause guest execution to avoid concurrent updates */
-	mutex_lock(&vcpu->mutex);
+	/* Take a lock to avoid concurrent updates */
+	mutex_lock(&vcpu->arch.exit_timing_lock);
 
 	vcpu->arch.last_exit_type = 0xDEAD;
 	for (i = 0; i < __NUMBER_OF_KVM_EXIT_TYPES; i++) {
@@ -49,7 +49,7 @@ void kvmppc_init_timing_stats(struct kvm_vcpu *vcpu)
 	vcpu->arch.timing_exit.tv64 = 0;
 	vcpu->arch.timing_last_enter.tv64 = 0;
 
-	mutex_unlock(&vcpu->mutex);
+	mutex_unlock(&vcpu->arch.exit_timing_lock);
 }
 
 static void add_exit_timing(struct kvm_vcpu *vcpu, u64 duration, int type)
@@ -65,6 +65,8 @@ static void add_exit_timing(struct kvm_vcpu *vcpu, u64 duration, int type)
 		return;
 	}
 
+	mutex_lock(&vcpu->arch.exit_timing_lock);
+
 	vcpu->arch.timing_count_type[type]++;
 
 	/* sum */
@@ -93,6 +95,8 @@ static void add_exit_timing(struct kvm_vcpu *vcpu, u64 duration, int type)
 		vcpu->arch.timing_min_duration[type] = duration;
 	if (unlikely(duration > vcpu->arch.timing_max_duration[type]))
 		vcpu->arch.timing_max_duration[type] = duration;
+
+	mutex_unlock(&vcpu->arch.exit_timing_lock);
 }
 
 void kvmppc_update_timing_stats(struct kvm_vcpu *vcpu)
@@ -147,17 +151,30 @@ static int kvmppc_exit_timing_show(struct seq_file *m, void *private)
 {
 	struct kvm_vcpu *vcpu = m->private;
 	int i;
+	u64 min, max, sum, sum_quad;
 
 	seq_printf(m, "%s", "type	count	min	max	sum	sum_squared\n");
 
+
 	for (i = 0; i < __NUMBER_OF_KVM_EXIT_TYPES; i++) {
+
+		min = vcpu->arch.timing_min_duration[i];
+		do_div(min, tb_ticks_per_usec);
+		max = vcpu->arch.timing_max_duration[i];
+		do_div(max, tb_ticks_per_usec);
+		sum = vcpu->arch.timing_sum_duration[i];
+		do_div(sum, tb_ticks_per_usec);
+		sum_quad = vcpu->arch.timing_sum_quad_duration[i];
+		do_div(sum_quad, tb_ticks_per_usec);
+
 		seq_printf(m, "%12s	%10d	%10lld	%10lld	%20lld	%20lld\n",
 			kvm_exit_names[i],
 			vcpu->arch.timing_count_type[i],
-			vcpu->arch.timing_min_duration[i],
-			vcpu->arch.timing_max_duration[i],
-			vcpu->arch.timing_sum_duration[i],
-			vcpu->arch.timing_sum_quad_duration[i]);
+			min,
+			max,
+			sum,
+			sum_quad);
+
 	}
 	return 0;
 }

arch/x86/include/asm/kvm_emulate.h

@@ -14,6 +14,8 @@
 #include <asm/desc_defs.h>
 
 struct x86_emulate_ctxt;
+enum x86_intercept;
+enum x86_intercept_stage;
 
 struct x86_exception {
 	u8 vector;
@@ -23,6 +25,24 @@ struct x86_exception {
 	u64 address; /* cr2 or nested page fault gpa */
 };
 
+/*
+ * This struct is used to carry enough information from the instruction
+ * decoder to main KVM so that a decision can be made whether the
+ * instruction needs to be intercepted or not.
+ */
+struct x86_instruction_info {
+	u8  intercept;          /* which intercept                      */
+	u8  rep_prefix;         /* rep prefix?                          */
+	u8  modrm_mod;		/* mod part of modrm			*/
+	u8  modrm_reg;          /* index of register used               */
+	u8  modrm_rm;		/* rm part of modrm			*/
+	u64 src_val;            /* value of source operand              */
+	u8  src_bytes;          /* size of source operand               */
+	u8  dst_bytes;          /* size of destination operand          */
+	u8  ad_bytes;           /* size of src/dst address              */
+	u64 next_rip;           /* rip following the instruction        */
+};
+
 /*
  * x86_emulate_ops:
  *
@@ -62,6 +82,7 @@ struct x86_exception {
 #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 */
+#define X86EMUL_INTERCEPTED     6 /* Intercepted by nested VMCB/VMCS */
 
 struct x86_emulate_ops {
 	/*
@@ -71,8 +92,9 @@ struct x86_emulate_ops {
 	 *  @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,
+	int (*read_std)(struct x86_emulate_ctxt *ctxt,
+			unsigned long addr, void *val,
+			unsigned int bytes,
 			struct x86_exception *fault);
 
 	/*
@@ -82,8 +104,8 @@ struct x86_emulate_ops {
 	 *  @val:   [OUT] Value write to memory, zero-extended to 'u_long'.
 	 *  @bytes: [IN ] Number of bytes to write to memory.
 	 */
-	int (*write_std)(unsigned long addr, void *val,
-			 unsigned int bytes, struct kvm_vcpu *vcpu,
+	int (*write_std)(struct x86_emulate_ctxt *ctxt,
+			 unsigned long addr, void *val, unsigned int bytes,
 			 struct x86_exception *fault);
 	/*
 	 * fetch: Read bytes of standard (non-emulated/special) memory.
@@ -92,8 +114,8 @@ struct x86_emulate_ops {
 	 *  @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,
+	int (*fetch)(struct x86_emulate_ctxt *ctxt,
+		     unsigned long addr, void *val, unsigned int bytes,
 		     struct x86_exception *fault);
 
 	/*
@@ -102,11 +124,9 @@ struct x86_emulate_ops {
 	 *  @val:   [OUT] Value read from memory, zero-extended to 'u_long'.
 	 *  @bytes: [IN ] Number of bytes to read from memory.
 	 */
-	int (*read_emulated)(unsigned long addr,
-			     void *val,
-			     unsigned int bytes,
-			     struct x86_exception *fault,
-			     struct kvm_vcpu *vcpu);
+	int (*read_emulated)(struct x86_emulate_ctxt *ctxt,
+			     unsigned long addr, void *val, unsigned int bytes,
+			     struct x86_exception *fault);
 
 	/*
 	 * write_emulated: Write bytes to emulated/special memory area.
@@ -115,11 +135,10 @@ struct x86_emulate_ops {
 	 *                required).
 	 *  @bytes: [IN ] Number of bytes to write to memory.
 	 */
-	int (*write_emulated)(unsigned long addr,
-			      const void *val,
+	int (*write_emulated)(struct x86_emulate_ctxt *ctxt,
+			      unsigned long addr, const void *val,
 			      unsigned int bytes,
-			      struct x86_exception *fault,
-			      struct kvm_vcpu *vcpu);
+			      struct x86_exception *fault);
 
 	/*
 	 * cmpxchg_emulated: Emulate an atomic (LOCKed) CMPXCHG operation on an
@@ -129,40 +148,54 @@ struct x86_emulate_ops {
 	 *  @new:   [IN ] Value to write to @addr.
 	 *  @bytes: [IN ] Number of bytes to access using CMPXCHG.
 	 */
-	int (*cmpxchg_emulated)(unsigned long addr,
+	int (*cmpxchg_emulated)(struct x86_emulate_ctxt *ctxt,
+				unsigned long addr,
 				const void *old,
 				const void *new,
 				unsigned int bytes,
-				struct x86_exception *fault,
-				struct kvm_vcpu *vcpu);
-
-	int (*pio_in_emulated)(int size, unsigned short port, void *val,
-			       unsigned int count, struct kvm_vcpu *vcpu);
-
-	int (*pio_out_emulated)(int size, unsigned short port, const void *val,
-				unsigned int count, struct kvm_vcpu *vcpu);
-
-	bool (*get_cached_descriptor)(struct desc_struct *desc, u32 *base3,
-				      int seg, struct kvm_vcpu *vcpu);
-	void (*set_cached_descriptor)(struct desc_struct *desc, u32 base3,
-				      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);
-	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);
-	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);
+				struct x86_exception *fault);
+	void (*invlpg)(struct x86_emulate_ctxt *ctxt, ulong addr);
+
+	int (*pio_in_emulated)(struct x86_emulate_ctxt *ctxt,
+			       int size, unsigned short port, void *val,
+			       unsigned int count);
+
+	int (*pio_out_emulated)(struct x86_emulate_ctxt *ctxt,
+				int size, unsigned short port, const void *val,
+				unsigned int count);
+
+	bool (*get_segment)(struct x86_emulate_ctxt *ctxt, u16 *selector,
+			    struct desc_struct *desc, u32 *base3, int seg);
+	void (*set_segment)(struct x86_emulate_ctxt *ctxt, u16 selector,
+			    struct desc_struct *desc, u32 base3, int seg);
+	unsigned long (*get_cached_segment_base)(struct x86_emulate_ctxt *ctxt,
+						 int seg);
+	void (*get_gdt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt);
+	void (*get_idt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt);
+	void (*set_gdt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt);
+	void (*set_idt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt);
+	ulong (*get_cr)(struct x86_emulate_ctxt *ctxt, int cr);
+	int (*set_cr)(struct x86_emulate_ctxt *ctxt, int cr, ulong val);
+	int (*cpl)(struct x86_emulate_ctxt *ctxt);
+	int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest);
+	int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value);
+	int (*set_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 data);
+	int (*get_msr)(struct x86_emulate_ctxt *ctxt, u32 msr_index, u64 *pdata);
+	void (*halt)(struct x86_emulate_ctxt *ctxt);
+	void (*wbinvd)(struct x86_emulate_ctxt *ctxt);
+	int (*fix_hypercall)(struct x86_emulate_ctxt *ctxt);
+	void (*get_fpu)(struct x86_emulate_ctxt *ctxt); /* disables preempt */
+	void (*put_fpu)(struct x86_emulate_ctxt *ctxt); /* reenables preempt */
+	int (*intercept)(struct x86_emulate_ctxt *ctxt,
+			 struct x86_instruction_info *info,
+			 enum x86_intercept_stage stage);
 };
 
+typedef u32 __attribute__((vector_size(16))) sse128_t;
+
 /* Type, address-of, and value of an instruction's operand. */
 struct operand {
-	enum { OP_REG, OP_MEM, OP_IMM, OP_NONE } type;
+	enum { OP_REG, OP_MEM, OP_IMM, OP_XMM, OP_NONE } type;
 	unsigned int bytes;
 	union {
 		unsigned long orig_val;
@@ -174,11 +207,13 @@ struct operand {
 			ulong ea;
 			unsigned seg;
 		} mem;
+		unsigned xmm;
 	} addr;
 	union {
 		unsigned long val;
 		u64 val64;
 		char valptr[sizeof(unsigned long) + 2];
+		sse128_t vec_val;
 	};
 };
 
@@ -197,6 +232,7 @@ struct read_cache {
 struct decode_cache {
 	u8 twobyte;
 	u8 b;
+	u8 intercept;
 	u8 lock_prefix;
 	u8 rep_prefix;
 	u8 op_bytes;
@@ -209,6 +245,7 @@ struct decode_cache {
 	u8 seg_override;
 	unsigned int d;
 	int (*execute)(struct x86_emulate_ctxt *ctxt);
+	int (*check_perm)(struct x86_emulate_ctxt *ctxt);
 	unsigned long regs[NR_VCPU_REGS];
 	unsigned long eip;
 	/* modrm */
@@ -227,17 +264,15 @@ struct x86_emulate_ctxt {
 	struct x86_emulate_ops *ops;
 
 	/* Register state before/after emulation. */
-	struct kvm_vcpu *vcpu;
-
 	unsigned long eflags;
 	unsigned long eip; /* eip before instruction emulation */
 	/* Emulated execution mode, represented by an X86EMUL_MODE value. */
 	int mode;
-	u32 cs_base;
 
 	/* interruptibility state, as a result of execution of STI or MOV SS */
 	int interruptibility;
 
+	bool guest_mode; /* guest running a nested guest */
 	bool perm_ok; /* do not check permissions if true */
 	bool only_vendor_specific_insn;
 
@@ -249,8 +284,8 @@ struct x86_emulate_ctxt {
 };
 
 /* Repeat String Operation Prefix */
-#define REPE_PREFIX	1
-#define REPNE_PREFIX	2
+#define REPE_PREFIX	0xf3
+#define REPNE_PREFIX	0xf2
 
 /* Execution mode, passed to the emulator. */
 #define X86EMUL_MODE_REAL     0	/* Real mode.             */
@@ -259,6 +294,69 @@ struct x86_emulate_ctxt {
 #define X86EMUL_MODE_PROT32   4	/* 32-bit protected mode. */
 #define X86EMUL_MODE_PROT64   8	/* 64-bit (long) mode.    */
 
+/* any protected mode   */
+#define X86EMUL_MODE_PROT     (X86EMUL_MODE_PROT16|X86EMUL_MODE_PROT32| \
+			       X86EMUL_MODE_PROT64)
+
+enum x86_intercept_stage {
+	X86_ICTP_NONE = 0,   /* Allow zero-init to not match anything */
+	X86_ICPT_PRE_EXCEPT,
+	X86_ICPT_POST_EXCEPT,
+	X86_ICPT_POST_MEMACCESS,
+};
+
+enum x86_intercept {
+	x86_intercept_none,
+	x86_intercept_cr_read,
+	x86_intercept_cr_write,
+	x86_intercept_clts,
+	x86_intercept_lmsw,
+	x86_intercept_smsw,
+	x86_intercept_dr_read,
+	x86_intercept_dr_write,
+	x86_intercept_lidt,
+	x86_intercept_sidt,
+	x86_intercept_lgdt,
+	x86_intercept_sgdt,
+	x86_intercept_lldt,
+	x86_intercept_sldt,
+	x86_intercept_ltr,
+	x86_intercept_str,
+	x86_intercept_rdtsc,
+	x86_intercept_rdpmc,
+	x86_intercept_pushf,
+	x86_intercept_popf,
+	x86_intercept_cpuid,
+	x86_intercept_rsm,
+	x86_intercept_iret,
+	x86_intercept_intn,
+	x86_intercept_invd,
+	x86_intercept_pause,
+	x86_intercept_hlt,
+	x86_intercept_invlpg,
+	x86_intercept_invlpga,
+	x86_intercept_vmrun,
+	x86_intercept_vmload,
+	x86_intercept_vmsave,
+	x86_intercept_vmmcall,
+	x86_intercept_stgi,
+	x86_intercept_clgi,
+	x86_intercept_skinit,
+	x86_intercept_rdtscp,
+	x86_intercept_icebp,
+	x86_intercept_wbinvd,
+	x86_intercept_monitor,
+	x86_intercept_mwait,
+	x86_intercept_rdmsr,
+	x86_intercept_wrmsr,
+	x86_intercept_in,
+	x86_intercept_ins,
+	x86_intercept_out,
+	x86_intercept_outs,
+
+	nr_x86_intercepts
+};
+
 /* Host execution mode. */
 #if defined(CONFIG_X86_32)
 #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT32
@@ -270,6 +368,7 @@ int x86_decode_insn(struct x86_emulate_ctxt *ctxt, void *insn, int insn_len);
 #define EMULATION_FAILED -1
 #define EMULATION_OK 0
 #define EMULATION_RESTART 1
+#define EMULATION_INTERCEPTED 2
 int x86_emulate_insn(struct x86_emulate_ctxt *ctxt);
 int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
 			 u16 tss_selector, int reason,

arch/x86/include/asm/kvm_host.h

@@ -30,14 +30,30 @@
 #define KVM_MEMORY_SLOTS 32
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
+#define KVM_MMIO_SIZE 16
 
 #define KVM_PIO_PAGE_OFFSET 1
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 2
 
+#define CR0_RESERVED_BITS                                               \
+	(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
+			  | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \
+			  | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG))
+
 #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_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_OSXSAVE \
+			  | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
+
+#define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
+
+
 
 #define INVALID_PAGE (~(hpa_t)0)
 #define VALID_PAGE(x) ((x) != INVALID_PAGE)
@@ -118,6 +134,9 @@ enum kvm_reg {
 enum kvm_reg_ex {
 	VCPU_EXREG_PDPTR = NR_VCPU_REGS,
 	VCPU_EXREG_CR3,
+	VCPU_EXREG_RFLAGS,
+	VCPU_EXREG_CPL,
+	VCPU_EXREG_SEGMENTS,
 };
 
 enum {
@@ -256,7 +275,7 @@ struct kvm_mmu {
 			 struct kvm_mmu_page *sp);
 	void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva);
 	void (*update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
-			u64 *spte, const void *pte, unsigned long mmu_seq);
+			   u64 *spte, const void *pte);
 	hpa_t root_hpa;
 	int root_level;
 	int shadow_root_level;
@@ -340,7 +359,6 @@ struct kvm_vcpu_arch {
 	struct fpu guest_fpu;
 	u64 xcr0;
 
-	gva_t mmio_fault_cr2;
 	struct kvm_pio_request pio;
 	void *pio_data;
 
@@ -367,18 +385,22 @@ struct kvm_vcpu_arch {
 	/* emulate context */
 
 	struct x86_emulate_ctxt emulate_ctxt;
+	bool emulate_regs_need_sync_to_vcpu;
+	bool emulate_regs_need_sync_from_vcpu;
 
 	gpa_t time;
 	struct pvclock_vcpu_time_info hv_clock;
 	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;
+	u32 virtual_tsc_khz;
 	bool tsc_catchup;
+	u32  tsc_catchup_mult;
+	s8   tsc_catchup_shift;
 
 	bool nmi_pending;
 	bool nmi_injected;
@@ -448,9 +470,6 @@ struct kvm_arch {
 	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;
 
@@ -502,6 +521,8 @@ struct kvm_vcpu_stat {
 	u32 nmi_injections;
 };
 
+struct x86_instruction_info;
+
 struct kvm_x86_ops {
 	int (*cpu_has_kvm_support)(void);          /* __init */
 	int (*disabled_by_bios)(void);             /* __init */
@@ -586,9 +607,17 @@ struct kvm_x86_ops {
 
 	bool (*has_wbinvd_exit)(void);
 
+	void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz);
 	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
 
+	u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc);
+
 	void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);
+
+	int (*check_intercept)(struct kvm_vcpu *vcpu,
+			       struct x86_instruction_info *info,
+			       enum x86_intercept_stage stage);
+
 	const struct trace_print_flags *exit_reasons_str;
 };
 
@@ -627,6 +656,13 @@ u8 kvm_get_guest_memory_type(struct kvm_vcpu *vcpu, gfn_t gfn);
 
 extern bool tdp_enabled;
 
+/* control of guest tsc rate supported? */
+extern bool kvm_has_tsc_control;
+/* minimum supported tsc_khz for guests */
+extern u32  kvm_min_guest_tsc_khz;
+/* maximum supported tsc_khz for guests */
+extern u32  kvm_max_guest_tsc_khz;
+
 enum emulation_result {
 	EMULATE_DONE,       /* no further processing */
 	EMULATE_DO_MMIO,      /* kvm_run filled with mmio request */
@@ -645,9 +681,6 @@ static inline int emulate_instruction(struct kvm_vcpu *vcpu,
 	return x86_emulate_instruction(vcpu, 0, emulation_type, NULL, 0);
 }
 
-void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
-void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address);
-
 void kvm_enable_efer_bits(u64);
 int kvm_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *data);
 int kvm_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data);
@@ -657,8 +690,6 @@ struct x86_emulate_ctxt;
 int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port);
 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 kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);
 
 void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
@@ -721,8 +752,6 @@ gpa_t kvm_mmu_gva_to_gpa_system(struct kvm_vcpu *vcpu, gva_t gva,
 
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
 
-int kvm_fix_hypercall(struct kvm_vcpu *vcpu);
-
 int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t gva, u32 error_code,
 		       void *insn, int insn_len);
 void kvm_mmu_invlpg(struct kvm_vcpu *vcpu, gva_t gva);

arch/x86/include/asm/msr-index.h

@@ -118,6 +118,7 @@
    complete list. */
 
 #define MSR_AMD64_PATCH_LEVEL		0x0000008b
+#define MSR_AMD64_TSC_RATIO		0xc0000104
 #define MSR_AMD64_NB_CFG		0xc001001f
 #define MSR_AMD64_PATCH_LOADER		0xc0010020
 #define MSR_AMD64_OSVW_ID_LENGTH	0xc0010140

arch/x86/kvm/i8254.h

@@ -33,7 +33,6 @@ struct kvm_kpit_state {
 };
 
 struct kvm_pit {
-	unsigned long base_addresss;
 	struct kvm_io_device dev;
 	struct kvm_io_device speaker_dev;
 	struct kvm *kvm;
@@ -51,7 +50,6 @@ struct kvm_pit {
 #define KVM_MAX_PIT_INTR_INTERVAL   HZ / 100
 #define KVM_PIT_CHANNEL_MASK	    0x3
 
-void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val, int hpet_legacy_start);
 struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags);
 void kvm_free_pit(struct kvm *kvm);

arch/x86/kvm/irq.h

@@ -75,7 +75,6 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm);
 void kvm_destroy_pic(struct kvm *kvm);
 int kvm_pic_read_irq(struct kvm *kvm);
 void kvm_pic_update_irq(struct kvm_pic *s);
-void kvm_pic_clear_isr_ack(struct kvm *kvm);
 
 static inline struct kvm_pic *pic_irqchip(struct kvm *kvm)
 {
@@ -100,7 +99,6 @@ void __kvm_migrate_apic_timer(struct kvm_vcpu *vcpu);
 void __kvm_migrate_pit_timer(struct kvm_vcpu *vcpu);
 void __kvm_migrate_timers(struct kvm_vcpu *vcpu);
 
-int pit_has_pending_timer(struct kvm_vcpu *vcpu);
 int apic_has_pending_timer(struct kvm_vcpu *vcpu);
 
 #endif

arch/x86/kvm/mmu.c

@@ -1206,7 +1206,7 @@ static void nonpaging_invlpg(struct kvm_vcpu *vcpu, gva_t gva)
 
 static void nonpaging_update_pte(struct kvm_vcpu *vcpu,
 				 struct kvm_mmu_page *sp, u64 *spte,
-				 const void *pte, unsigned long mmu_seq)
+				 const void *pte)
 {
 	WARN_ON(1);
 }
@@ -3163,9 +3163,8 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu,
 }
 
 static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
-				  struct kvm_mmu_page *sp,
-				  u64 *spte,
-				  const void *new, unsigned long mmu_seq)
+				  struct kvm_mmu_page *sp, u64 *spte,
+				  const void *new)
 {
 	if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
 		++vcpu->kvm->stat.mmu_pde_zapped;
@@ -3173,7 +3172,7 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
         }
 
 	++vcpu->kvm->stat.mmu_pte_updated;
-	vcpu->arch.mmu.update_pte(vcpu, sp, spte, new, mmu_seq);
+	vcpu->arch.mmu.update_pte(vcpu, sp, spte, new);
 }
 
 static bool need_remote_flush(u64 old, u64 new)
@@ -3229,7 +3228,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	struct kvm_mmu_page *sp;
 	struct hlist_node *node;
 	LIST_HEAD(invalid_list);
-	unsigned long mmu_seq;
 	u64 entry, gentry, *spte;
 	unsigned pte_size, page_offset, misaligned, quadrant, offset;
 	int level, npte, invlpg_counter, r, flooded = 0;
@@ -3271,9 +3269,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		break;
 	}
 
-	mmu_seq = vcpu->kvm->mmu_notifier_seq;
-	smp_rmb();
-
 	spin_lock(&vcpu->kvm->mmu_lock);
 	if (atomic_read(&vcpu->kvm->arch.invlpg_counter) != invlpg_counter)
 		gentry = 0;
@@ -3345,8 +3340,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 			if (gentry &&
 			      !((sp->role.word ^ vcpu->arch.mmu.base_role.word)
 			      & mask.word))
-				mmu_pte_write_new_pte(vcpu, sp, spte, &gentry,
-						      mmu_seq);
+				mmu_pte_write_new_pte(vcpu, sp, spte, &gentry);
 			if (!remote_flush && need_remote_flush(entry, *spte))
 				remote_flush = true;
 			++spte;

arch/x86/kvm/paging_tmpl.h

@@ -78,15 +78,19 @@ static gfn_t gpte_to_gfn_lvl(pt_element_t gpte, int lvl)
 	return (gpte & PT_LVL_ADDR_MASK(lvl)) >> PAGE_SHIFT;
 }
 
-static bool FNAME(cmpxchg_gpte)(struct kvm *kvm,
-			 gfn_t table_gfn, unsigned index,
-			 pt_element_t orig_pte, pt_element_t new_pte)
+static int FNAME(cmpxchg_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+			       pt_element_t __user *ptep_user, unsigned index,
+			       pt_element_t orig_pte, pt_element_t new_pte)
 {
+	int npages;
 	pt_element_t ret;
 	pt_element_t *table;
 	struct page *page;
 
-	page = gfn_to_page(kvm, table_gfn);
+	npages = get_user_pages_fast((unsigned long)ptep_user, 1, 1, &page);
+	/* Check if the user is doing something meaningless. */
+	if (unlikely(npages != 1))
+		return -EFAULT;
 
 	table = kmap_atomic(page, KM_USER0);
 	ret = CMPXCHG(&table[index], orig_pte, new_pte);
@@ -117,6 +121,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 				    gva_t addr, u32 access)
 {
 	pt_element_t pte;
+	pt_element_t __user *ptep_user;
 	gfn_t table_gfn;
 	unsigned index, pt_access, uninitialized_var(pte_access);
 	gpa_t pte_gpa;
@@ -152,6 +157,9 @@ walk:
 	pt_access = ACC_ALL;
 
 	for (;;) {
+		gfn_t real_gfn;
+		unsigned long host_addr;
+
 		index = PT_INDEX(addr, walker->level);
 
 		table_gfn = gpte_to_gfn(pte);
@@ -160,43 +168,64 @@ walk:
 		walker->table_gfn[walker->level - 1] = table_gfn;
 		walker->pte_gpa[walker->level - 1] = pte_gpa;
 
-		if (kvm_read_guest_page_mmu(vcpu, mmu, table_gfn, &pte,
-					    offset, sizeof(pte),
-					    PFERR_USER_MASK|PFERR_WRITE_MASK)) {
+		real_gfn = mmu->translate_gpa(vcpu, gfn_to_gpa(table_gfn),
+					      PFERR_USER_MASK|PFERR_WRITE_MASK);
+		if (unlikely(real_gfn == UNMAPPED_GVA)) {
+			present = false;
+			break;
+		}
+		real_gfn = gpa_to_gfn(real_gfn);
+
+		host_addr = gfn_to_hva(vcpu->kvm, real_gfn);
+		if (unlikely(kvm_is_error_hva(host_addr))) {
+			present = false;
+			break;
+		}
+
+		ptep_user = (pt_element_t __user *)((void *)host_addr + offset);
+		if (unlikely(__copy_from_user(&pte, ptep_user, sizeof(pte)))) {
 			present = false;
 			break;
 		}
 
 		trace_kvm_mmu_paging_element(pte, walker->level);
 
-		if (!is_present_gpte(pte)) {
+		if (unlikely(!is_present_gpte(pte))) {
 			present = false;
 			break;
 		}
 
-		if (is_rsvd_bits_set(&vcpu->arch.mmu, pte, walker->level)) {
+		if (unlikely(is_rsvd_bits_set(&vcpu->arch.mmu, pte,
+					      walker->level))) {
 			rsvd_fault = true;
 			break;
 		}
 
-		if (write_fault && !is_writable_pte(pte))
-			if (user_fault || is_write_protection(vcpu))
-				eperm = true;
+		if (unlikely(write_fault && !is_writable_pte(pte)
+			     && (user_fault || is_write_protection(vcpu))))
+			eperm = true;
 
-		if (user_fault && !(pte & PT_USER_MASK))
+		if (unlikely(user_fault && !(pte & PT_USER_MASK)))
 			eperm = true;
 
 #if PTTYPE == 64
-		if (fetch_fault && (pte & PT64_NX_MASK))
+		if (unlikely(fetch_fault && (pte & PT64_NX_MASK)))
 			eperm = true;
 #endif
 
-		if (!eperm && !rsvd_fault && !(pte & PT_ACCESSED_MASK)) {
+		if (!eperm && !rsvd_fault
+		    && unlikely(!(pte & PT_ACCESSED_MASK))) {
+			int ret;
 			trace_kvm_mmu_set_accessed_bit(table_gfn, index,
 						       sizeof(pte));
-			if (FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn,
-			    index, pte, pte|PT_ACCESSED_MASK))
+			ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index,
+						  pte, pte|PT_ACCESSED_MASK);
+			if (unlikely(ret < 0)) {
+				present = false;
+				break;
+			} else if (ret)
 				goto walk;
+
 			mark_page_dirty(vcpu->kvm, table_gfn);
 			pte |= PT_ACCESSED_MASK;
 		}
@@ -241,17 +270,21 @@ walk:
 		--walker->level;
 	}
 
-	if (!present || eperm || rsvd_fault)
+	if (unlikely(!present || eperm || rsvd_fault))
 		goto error;
 
-	if (write_fault && !is_dirty_gpte(pte)) {
-		bool ret;
+	if (write_fault && unlikely(!is_dirty_gpte(pte))) {
+		int ret;
 
 		trace_kvm_mmu_set_dirty_bit(table_gfn, index, sizeof(pte));
-		ret = FNAME(cmpxchg_gpte)(vcpu->kvm, table_gfn, index, pte,
-			    pte|PT_DIRTY_MASK);
-		if (ret)
+		ret = FNAME(cmpxchg_gpte)(vcpu, mmu, ptep_user, index,
+					  pte, pte|PT_DIRTY_MASK);
+		if (unlikely(ret < 0)) {
+			present = false;
+			goto error;
+		} else if (ret)
 			goto walk;
+
 		mark_page_dirty(vcpu->kvm, table_gfn);
 		pte |= PT_DIRTY_MASK;
 		walker->ptes[walker->level - 1] = pte;
@@ -325,7 +358,7 @@ no_present:
 }
 
 static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
-			      u64 *spte, const void *pte, unsigned long mmu_seq)
+			      u64 *spte, const void *pte)
 {
 	pt_element_t gpte;
 	unsigned pte_access;
@@ -342,8 +375,6 @@ static void FNAME(update_pte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 		kvm_release_pfn_clean(pfn);
 		return;
 	}
-	if (mmu_notifier_retry(vcpu, mmu_seq))
-		return;
 
 	/*
 	 * we call mmu_set_spte() with host_writable = true because that

arch/x86/kvm/svm.c

@@ -63,6 +63,10 @@ MODULE_LICENSE("GPL");
 
 #define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
 
+#define TSC_RATIO_RSVD          0xffffff0000000000ULL
+#define TSC_RATIO_MIN		0x0000000000000001ULL
+#define TSC_RATIO_MAX		0x000000ffffffffffULL
+
 static bool erratum_383_found __read_mostly;
 
 static const u32 host_save_user_msrs[] = {
@@ -93,14 +97,6 @@ struct nested_state {
 	/* A VMEXIT is required but not yet emulated */
 	bool exit_required;
 
-	/*
-	 * If we vmexit during an instruction emulation we need this to restore
-	 * the l1 guest rip after the emulation
-	 */
-	unsigned long vmexit_rip;
-	unsigned long vmexit_rsp;
-	unsigned long vmexit_rax;
-
 	/* cache for intercepts of the guest */
 	u32 intercept_cr;
 	u32 intercept_dr;
@@ -144,8 +140,13 @@ struct vcpu_svm {
 	unsigned int3_injected;
 	unsigned long int3_rip;
 	u32 apf_reason;
+
+	u64  tsc_ratio;
 };
 
+static DEFINE_PER_CPU(u64, current_tsc_ratio);
+#define TSC_RATIO_DEFAULT	0x0100000000ULL
+
 #define MSR_INVALID			0xffffffffU
 
 static struct svm_direct_access_msrs {
@@ -190,6 +191,7 @@ static int nested_svm_intercept(struct vcpu_svm *svm);
 static int nested_svm_vmexit(struct vcpu_svm *svm);
 static int nested_svm_check_exception(struct vcpu_svm *svm, unsigned nr,
 				      bool has_error_code, u32 error_code);
+static u64 __scale_tsc(u64 ratio, u64 tsc);
 
 enum {
 	VMCB_INTERCEPTS, /* Intercept vectors, TSC offset,
@@ -376,7 +378,6 @@ struct svm_cpu_data {
 };
 
 static DEFINE_PER_CPU(struct svm_cpu_data *, svm_data);
-static uint32_t svm_features;
 
 struct svm_init_data {
 	int cpu;
@@ -569,6 +570,10 @@ static int has_svm(void)
 
 static void svm_hardware_disable(void *garbage)
 {
+	/* Make sure we clean up behind us */
+	if (static_cpu_has(X86_FEATURE_TSCRATEMSR))
+		wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT);
+
 	cpu_svm_disable();
 }
 
@@ -610,6 +615,11 @@ static int svm_hardware_enable(void *garbage)
 
 	wrmsrl(MSR_VM_HSAVE_PA, page_to_pfn(sd->save_area) << PAGE_SHIFT);
 
+	if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) {
+		wrmsrl(MSR_AMD64_TSC_RATIO, TSC_RATIO_DEFAULT);
+		__get_cpu_var(current_tsc_ratio) = TSC_RATIO_DEFAULT;
+	}
+
 	svm_init_erratum_383();
 
 	return 0;
@@ -791,6 +801,23 @@ static __init int svm_hardware_setup(void)
 	if (boot_cpu_has(X86_FEATURE_FXSR_OPT))
 		kvm_enable_efer_bits(EFER_FFXSR);
 
+	if (boot_cpu_has(X86_FEATURE_TSCRATEMSR)) {
+		u64 max;
+
+		kvm_has_tsc_control = true;
+
+		/*
+		 * Make sure the user can only configure tsc_khz values that
+		 * fit into a signed integer.
+		 * A min value is not calculated needed because it will always
+		 * be 1 on all machines and a value of 0 is used to disable
+		 * tsc-scaling for the vcpu.
+		 */
+		max = min(0x7fffffffULL, __scale_tsc(tsc_khz, TSC_RATIO_MAX));
+
+		kvm_max_guest_tsc_khz = max;
+	}
+
 	if (nested) {
 		printk(KERN_INFO "kvm: Nested Virtualization enabled\n");
 		kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE);
@@ -802,8 +829,6 @@ static __init int svm_hardware_setup(void)
 			goto err;
 	}
 
-	svm_features = cpuid_edx(SVM_CPUID_FUNC);
-
 	if (!boot_cpu_has(X86_FEATURE_NPT))
 		npt_enabled = false;
 
@@ -854,6 +879,64 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type)
 	seg->base = 0;
 }
 
+static u64 __scale_tsc(u64 ratio, u64 tsc)
+{
+	u64 mult, frac, _tsc;
+
+	mult  = ratio >> 32;
+	frac  = ratio & ((1ULL << 32) - 1);
+
+	_tsc  = tsc;
+	_tsc *= mult;
+	_tsc += (tsc >> 32) * frac;
+	_tsc += ((tsc & ((1ULL << 32) - 1)) * frac) >> 32;
+
+	return _tsc;
+}
+
+static u64 svm_scale_tsc(struct kvm_vcpu *vcpu, u64 tsc)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	u64 _tsc = tsc;
+
+	if (svm->tsc_ratio != TSC_RATIO_DEFAULT)
+		_tsc = __scale_tsc(svm->tsc_ratio, tsc);
+
+	return _tsc;
+}
+
+static void svm_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	u64 ratio;
+	u64 khz;
+
+	/* TSC scaling supported? */
+	if (!boot_cpu_has(X86_FEATURE_TSCRATEMSR))
+		return;
+
+	/* TSC-Scaling disabled or guest TSC same frequency as host TSC? */
+	if (user_tsc_khz == 0) {
+		vcpu->arch.virtual_tsc_khz = 0;
+		svm->tsc_ratio = TSC_RATIO_DEFAULT;
+		return;
+	}
+
+	khz = user_tsc_khz;
+
+	/* TSC scaling required  - calculate ratio */
+	ratio = khz << 32;
+	do_div(ratio, tsc_khz);
+
+	if (ratio == 0 || ratio & TSC_RATIO_RSVD) {
+		WARN_ONCE(1, "Invalid TSC ratio - virtual-tsc-khz=%u\n",
+				user_tsc_khz);
+		return;
+	}
+	vcpu->arch.virtual_tsc_khz = user_tsc_khz;
+	svm->tsc_ratio             = ratio;
+}
+
 static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -880,6 +963,15 @@ static void svm_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment)
 	mark_dirty(svm->vmcb, VMCB_INTERCEPTS);
 }
 
+static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
+{
+	u64 tsc;
+
+	tsc = svm_scale_tsc(vcpu, native_read_tsc());
+
+	return target_tsc - tsc;
+}
+
 static void init_vmcb(struct vcpu_svm *svm)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -975,7 +1067,7 @@ static void init_vmcb(struct vcpu_svm *svm)
 	svm_set_efer(&svm->vcpu, 0);
 	save->dr6 = 0xffff0ff0;
 	save->dr7 = 0x400;
-	save->rflags = 2;
+	kvm_set_rflags(&svm->vcpu, 2);
 	save->rip = 0x0000fff0;
 	svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
 
@@ -1048,6 +1140,8 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
 		goto out;
 	}
 
+	svm->tsc_ratio = TSC_RATIO_DEFAULT;
+
 	err = kvm_vcpu_init(&svm->vcpu, kvm, id);
 	if (err)
 		goto free_svm;
@@ -1141,6 +1235,12 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
 		rdmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
+
+	if (static_cpu_has(X86_FEATURE_TSCRATEMSR) &&
+	    svm->tsc_ratio != __get_cpu_var(current_tsc_ratio)) {
+		__get_cpu_var(current_tsc_ratio) = svm->tsc_ratio;
+		wrmsrl(MSR_AMD64_TSC_RATIO, svm->tsc_ratio);
+	}
 }
 
 static void svm_vcpu_put(struct kvm_vcpu *vcpu)
@@ -1365,31 +1465,6 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (is_guest_mode(vcpu)) {
-		/*
-		 * We are here because we run in nested mode, the host kvm
-		 * intercepts cr0 writes but the l1 hypervisor does not.
-		 * But the L1 hypervisor may intercept selective cr0 writes.
-		 * This needs to be checked here.
-		 */
-		unsigned long old, new;
-
-		/* Remove bits that would trigger a real cr0 write intercept */
-		old = vcpu->arch.cr0 & SVM_CR0_SELECTIVE_MASK;
-		new = cr0 & SVM_CR0_SELECTIVE_MASK;
-
-		if (old == new) {
-			/* cr0 write with ts and mp unchanged */
-			svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE;
-			if (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE) {
-				svm->nested.vmexit_rip = kvm_rip_read(vcpu);
-				svm->nested.vmexit_rsp = kvm_register_read(vcpu, VCPU_REGS_RSP);
-				svm->nested.vmexit_rax = kvm_register_read(vcpu, VCPU_REGS_RAX);
-				return;
-			}
-		}
-	}
-
 #ifdef CONFIG_X86_64
 	if (vcpu->arch.efer & EFER_LME) {
 		if (!is_paging(vcpu) && (cr0 & X86_CR0_PG)) {
@@ -2127,7 +2202,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	nested_vmcb->save.cr3    = kvm_read_cr3(&svm->vcpu);
 	nested_vmcb->save.cr2    = vmcb->save.cr2;
 	nested_vmcb->save.cr4    = svm->vcpu.arch.cr4;
-	nested_vmcb->save.rflags = vmcb->save.rflags;
+	nested_vmcb->save.rflags = kvm_get_rflags(&svm->vcpu);
 	nested_vmcb->save.rip    = vmcb->save.rip;
 	nested_vmcb->save.rsp    = vmcb->save.rsp;
 	nested_vmcb->save.rax    = vmcb->save.rax;
@@ -2184,7 +2259,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	svm->vmcb->save.ds = hsave->save.ds;
 	svm->vmcb->save.gdtr = hsave->save.gdtr;
 	svm->vmcb->save.idtr = hsave->save.idtr;
-	svm->vmcb->save.rflags = hsave->save.rflags;
+	kvm_set_rflags(&svm->vcpu, hsave->save.rflags);
 	svm_set_efer(&svm->vcpu, hsave->save.efer);
 	svm_set_cr0(&svm->vcpu, hsave->save.cr0 | X86_CR0_PE);
 	svm_set_cr4(&svm->vcpu, hsave->save.cr4);
@@ -2312,7 +2387,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
 	hsave->save.efer   = svm->vcpu.arch.efer;
 	hsave->save.cr0    = kvm_read_cr0(&svm->vcpu);
 	hsave->save.cr4    = svm->vcpu.arch.cr4;
-	hsave->save.rflags = vmcb->save.rflags;
+	hsave->save.rflags = kvm_get_rflags(&svm->vcpu);
 	hsave->save.rip    = kvm_rip_read(&svm->vcpu);
 	hsave->save.rsp    = vmcb->save.rsp;
 	hsave->save.rax    = vmcb->save.rax;
@@ -2323,7 +2398,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
 
 	copy_vmcb_control_area(hsave, vmcb);
 
-	if (svm->vmcb->save.rflags & X86_EFLAGS_IF)
+	if (kvm_get_rflags(&svm->vcpu) & X86_EFLAGS_IF)
 		svm->vcpu.arch.hflags |= HF_HIF_MASK;
 	else
 		svm->vcpu.arch.hflags &= ~HF_HIF_MASK;
@@ -2341,7 +2416,7 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
 	svm->vmcb->save.ds = nested_vmcb->save.ds;
 	svm->vmcb->save.gdtr = nested_vmcb->save.gdtr;
 	svm->vmcb->save.idtr = nested_vmcb->save.idtr;
-	svm->vmcb->save.rflags = nested_vmcb->save.rflags;
+	kvm_set_rflags(&svm->vcpu, nested_vmcb->save.rflags);
 	svm_set_efer(&svm->vcpu, nested_vmcb->save.efer);
 	svm_set_cr0(&svm->vcpu, nested_vmcb->save.cr0);
 	svm_set_cr4(&svm->vcpu, nested_vmcb->save.cr4);
@@ -2443,13 +2518,13 @@ static int vmload_interception(struct vcpu_svm *svm)
 	if (nested_svm_check_permissions(svm))
 		return 1;
 
-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
-	skip_emulated_instruction(&svm->vcpu);
-
 	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
 	if (!nested_vmcb)
 		return 1;
 
+	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+	skip_emulated_instruction(&svm->vcpu);
+
 	nested_svm_vmloadsave(nested_vmcb, svm->vmcb);
 	nested_svm_unmap(page);
 
@@ -2464,13 +2539,13 @@ static int vmsave_interception(struct vcpu_svm *svm)
 	if (nested_svm_check_permissions(svm))
 		return 1;
 
-	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
-	skip_emulated_instruction(&svm->vcpu);
-
 	nested_vmcb = nested_svm_map(svm, svm->vmcb->save.rax, &page);
 	if (!nested_vmcb)
 		return 1;
 
+	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+	skip_emulated_instruction(&svm->vcpu);
+
 	nested_svm_vmloadsave(svm->vmcb, nested_vmcb);
 	nested_svm_unmap(page);
 
@@ -2676,6 +2751,29 @@ static int emulate_on_interception(struct vcpu_svm *svm)
 	return emulate_instruction(&svm->vcpu, 0) == EMULATE_DONE;
 }
 
+bool check_selective_cr0_intercepted(struct vcpu_svm *svm, unsigned long val)
+{
+	unsigned long cr0 = svm->vcpu.arch.cr0;
+	bool ret = false;
+	u64 intercept;
+
+	intercept = svm->nested.intercept;
+
+	if (!is_guest_mode(&svm->vcpu) ||
+	    (!(intercept & (1ULL << INTERCEPT_SELECTIVE_CR0))))
+		return false;
+
+	cr0 &= ~SVM_CR0_SELECTIVE_MASK;
+	val &= ~SVM_CR0_SELECTIVE_MASK;
+
+	if (cr0 ^ val) {
+		svm->vmcb->control.exit_code = SVM_EXIT_CR0_SEL_WRITE;
+		ret = (nested_svm_exit_handled(svm) == NESTED_EXIT_DONE);
+	}
+
+	return ret;
+}
+
 #define CR_VALID (1ULL << 63)
 
 static int cr_interception(struct vcpu_svm *svm)
@@ -2699,7 +2797,11 @@ static int cr_interception(struct vcpu_svm *svm)
 		val = kvm_register_read(&svm->vcpu, reg);
 		switch (cr) {
 		case 0:
-			err = kvm_set_cr0(&svm->vcpu, val);
+			if (!check_selective_cr0_intercepted(svm, val))
+				err = kvm_set_cr0(&svm->vcpu, val);
+			else
+				return 1;
+
 			break;
 		case 3:
 			err = kvm_set_cr3(&svm->vcpu, val);
@@ -2744,23 +2846,6 @@ static int cr_interception(struct vcpu_svm *svm)
 	return 1;
 }
 
-static int cr0_write_interception(struct vcpu_svm *svm)
-{
-	struct kvm_vcpu *vcpu = &svm->vcpu;
-	int r;
-
-	r = cr_interception(svm);
-
-	if (svm->nested.vmexit_rip) {
-		kvm_register_write(vcpu, VCPU_REGS_RIP, svm->nested.vmexit_rip);
-		kvm_register_write(vcpu, VCPU_REGS_RSP, svm->nested.vmexit_rsp);
-		kvm_register_write(vcpu, VCPU_REGS_RAX, svm->nested.vmexit_rax);
-		svm->nested.vmexit_rip = 0;
-	}
-
-	return r;
-}
-
 static int dr_interception(struct vcpu_svm *svm)
 {
 	int reg, dr;
@@ -2813,7 +2898,9 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
 	case MSR_IA32_TSC: {
 		struct vmcb *vmcb = get_host_vmcb(svm);
 
-		*data = vmcb->control.tsc_offset + native_read_tsc();
+		*data = vmcb->control.tsc_offset +
+			svm_scale_tsc(vcpu, native_read_tsc());
+
 		break;
 	}
 	case MSR_STAR:
@@ -3048,7 +3135,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_READ_CR4]			= cr_interception,
 	[SVM_EXIT_READ_CR8]			= cr_interception,
 	[SVM_EXIT_CR0_SEL_WRITE]		= emulate_on_interception,
-	[SVM_EXIT_WRITE_CR0]			= cr0_write_interception,
+	[SVM_EXIT_WRITE_CR0]			= cr_interception,
 	[SVM_EXIT_WRITE_CR3]			= cr_interception,
 	[SVM_EXIT_WRITE_CR4]			= cr_interception,
 	[SVM_EXIT_WRITE_CR8]			= cr8_write_interception,
@@ -3104,97 +3191,109 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_NPF]				= pf_interception,
 };
 
-void dump_vmcb(struct kvm_vcpu *vcpu)
+static void dump_vmcb(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb_control_area *control = &svm->vmcb->control;
 	struct vmcb_save_area *save = &svm->vmcb->save;
 
 	pr_err("VMCB Control Area:\n");
-	pr_err("cr_read:            %04x\n", control->intercept_cr & 0xffff);
-	pr_err("cr_write:           %04x\n", control->intercept_cr >> 16);
-	pr_err("dr_read:            %04x\n", control->intercept_dr & 0xffff);
-	pr_err("dr_write:           %04x\n", control->intercept_dr >> 16);
-	pr_err("exceptions:         %08x\n", control->intercept_exceptions);
-	pr_err("intercepts:         %016llx\n", control->intercept);
-	pr_err("pause filter count: %d\n", control->pause_filter_count);
-	pr_err("iopm_base_pa:       %016llx\n", control->iopm_base_pa);
-	pr_err("msrpm_base_pa:      %016llx\n", control->msrpm_base_pa);
-	pr_err("tsc_offset:         %016llx\n", control->tsc_offset);
-	pr_err("asid:               %d\n", control->asid);
-	pr_err("tlb_ctl:            %d\n", control->tlb_ctl);
-	pr_err("int_ctl:            %08x\n", control->int_ctl);
-	pr_err("int_vector:         %08x\n", control->int_vector);
-	pr_err("int_state:          %08x\n", control->int_state);
-	pr_err("exit_code:          %08x\n", control->exit_code);
-	pr_err("exit_info1:         %016llx\n", control->exit_info_1);
-	pr_err("exit_info2:         %016llx\n", control->exit_info_2);
-	pr_err("exit_int_info:      %08x\n", control->exit_int_info);
-	pr_err("exit_int_info_err:  %08x\n", control->exit_int_info_err);
-	pr_err("nested_ctl:         %lld\n", control->nested_ctl);
-	pr_err("nested_cr3:         %016llx\n", control->nested_cr3);
-	pr_err("event_inj:          %08x\n", control->event_inj);
-	pr_err("event_inj_err:      %08x\n", control->event_inj_err);
-	pr_err("lbr_ctl:            %lld\n", control->lbr_ctl);
-	pr_err("next_rip:           %016llx\n", control->next_rip);
+	pr_err("%-20s%04x\n", "cr_read:", control->intercept_cr & 0xffff);
+	pr_err("%-20s%04x\n", "cr_write:", control->intercept_cr >> 16);
+	pr_err("%-20s%04x\n", "dr_read:", control->intercept_dr & 0xffff);
+	pr_err("%-20s%04x\n", "dr_write:", control->intercept_dr >> 16);
+	pr_err("%-20s%08x\n", "exceptions:", control->intercept_exceptions);
+	pr_err("%-20s%016llx\n", "intercepts:", control->intercept);
+	pr_err("%-20s%d\n", "pause filter count:", control->pause_filter_count);
+	pr_err("%-20s%016llx\n", "iopm_base_pa:", control->iopm_base_pa);
+	pr_err("%-20s%016llx\n", "msrpm_base_pa:", control->msrpm_base_pa);
+	pr_err("%-20s%016llx\n", "tsc_offset:", control->tsc_offset);
+	pr_err("%-20s%d\n", "asid:", control->asid);
+	pr_err("%-20s%d\n", "tlb_ctl:", control->tlb_ctl);
+	pr_err("%-20s%08x\n", "int_ctl:", control->int_ctl);
+	pr_err("%-20s%08x\n", "int_vector:", control->int_vector);
+	pr_err("%-20s%08x\n", "int_state:", control->int_state);
+	pr_err("%-20s%08x\n", "exit_code:", control->exit_code);
+	pr_err("%-20s%016llx\n", "exit_info1:", control->exit_info_1);
+	pr_err("%-20s%016llx\n", "exit_info2:", control->exit_info_2);
+	pr_err("%-20s%08x\n", "exit_int_info:", control->exit_int_info);
+	pr_err("%-20s%08x\n", "exit_int_info_err:", control->exit_int_info_err);
+	pr_err("%-20s%lld\n", "nested_ctl:", control->nested_ctl);
+	pr_err("%-20s%016llx\n", "nested_cr3:", control->nested_cr3);
+	pr_err("%-20s%08x\n", "event_inj:", control->event_inj);
+	pr_err("%-20s%08x\n", "event_inj_err:", control->event_inj_err);
+	pr_err("%-20s%lld\n", "lbr_ctl:", control->lbr_ctl);
+	pr_err("%-20s%016llx\n", "next_rip:", control->next_rip);
 	pr_err("VMCB State Save Area:\n");
-	pr_err("es:   s: %04x a: %04x l: %08x b: %016llx\n",
-		save->es.selector, save->es.attrib,
-		save->es.limit, save->es.base);
-	pr_err("cs:   s: %04x a: %04x l: %08x b: %016llx\n",
-		save->cs.selector, save->cs.attrib,
-		save->cs.limit, save->cs.base);
-	pr_err("ss:   s: %04x a: %04x l: %08x b: %016llx\n",
-		save->ss.selector, save->ss.attrib,
-		save->ss.limit, save->ss.base);
-	pr_err("ds:   s: %04x a: %04x l: %08x b: %016llx\n",
-		save->ds.selector, save->ds.attrib,
-		save->ds.limit, save->ds.base);
-	pr_err("fs:   s: %04x a: %04x l: %08x b: %016llx\n",
-		save->fs.selector, save->fs.attrib,
-		save->fs.limit, save->fs.base);
-	pr_err("gs:   s: %04x a: %04x l: %08x b: %016llx\n",
-		save->gs.selector, save->gs.attrib,
-		save->gs.limit, save->gs.base);
-	pr_err("gdtr: s: %04x a: %04x l: %08x b: %016llx\n",
-		save->gdtr.selector, save->gdtr.attrib,
-		save->gdtr.limit, save->gdtr.base);
-	pr_err("ldtr: s: %04x a: %04x l: %08x b: %016llx\n",
-		save->ldtr.selector, save->ldtr.attrib,
-		save->ldtr.limit, save->ldtr.base);
-	pr_err("idtr: s: %04x a: %04x l: %08x b: %016llx\n",
-		save->idtr.selector, save->idtr.attrib,
-		save->idtr.limit, save->idtr.base);
-	pr_err("tr:   s: %04x a: %04x l: %08x b: %016llx\n",
-		save->tr.selector, save->tr.attrib,
-		save->tr.limit, save->tr.base);
+	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
+	       "es:",
+	       save->es.selector, save->es.attrib,
+	       save->es.limit, save->es.base);
+	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
+	       "cs:",
+	       save->cs.selector, save->cs.attrib,
+	       save->cs.limit, save->cs.base);
+	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
+	       "ss:",
+	       save->ss.selector, save->ss.attrib,
+	       save->ss.limit, save->ss.base);
+	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
+	       "ds:",
+	       save->ds.selector, save->ds.attrib,
+	       save->ds.limit, save->ds.base);
+	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
+	       "fs:",
+	       save->fs.selector, save->fs.attrib,
+	       save->fs.limit, save->fs.base);
+	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
+	       "gs:",
+	       save->gs.selector, save->gs.attrib,
+	       save->gs.limit, save->gs.base);
+	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
+	       "gdtr:",
+	       save->gdtr.selector, save->gdtr.attrib,
+	       save->gdtr.limit, save->gdtr.base);
+	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
+	       "ldtr:",
+	       save->ldtr.selector, save->ldtr.attrib,
+	       save->ldtr.limit, save->ldtr.base);
+	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
+	       "idtr:",
+	       save->idtr.selector, save->idtr.attrib,
+	       save->idtr.limit, save->idtr.base);
+	pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
+	       "tr:",
+	       save->tr.selector, save->tr.attrib,
+	       save->tr.limit, save->tr.base);
 	pr_err("cpl:            %d                efer:         %016llx\n",
 		save->cpl, save->efer);
-	pr_err("cr0:            %016llx cr2:          %016llx\n",
-		save->cr0, save->cr2);
-	pr_err("cr3:            %016llx cr4:          %016llx\n",
-		save->cr3, save->cr4);
-	pr_err("dr6:            %016llx dr7:          %016llx\n",
-		save->dr6, save->dr7);
-	pr_err("rip:            %016llx rflags:       %016llx\n",
-		save->rip, save->rflags);
-	pr_err("rsp:            %016llx rax:          %016llx\n",
-		save->rsp, save->rax);
-	pr_err("star:           %016llx lstar:        %016llx\n",
-		save->star, save->lstar);
-	pr_err("cstar:          %016llx sfmask:       %016llx\n",
-		save->cstar, save->sfmask);
-	pr_err("kernel_gs_base: %016llx sysenter_cs:  %016llx\n",
-		save->kernel_gs_base, save->sysenter_cs);
-	pr_err("sysenter_esp:   %016llx sysenter_eip: %016llx\n",
-		save->sysenter_esp, save->sysenter_eip);
-	pr_err("gpat:           %016llx dbgctl:       %016llx\n",
-		save->g_pat, save->dbgctl);
-	pr_err("br_from:        %016llx br_to:        %016llx\n",
-		save->br_from, save->br_to);
-	pr_err("excp_from:      %016llx excp_to:      %016llx\n",
-		save->last_excp_from, save->last_excp_to);
-
+	pr_err("%-15s %016llx %-13s %016llx\n",
+	       "cr0:", save->cr0, "cr2:", save->cr2);
+	pr_err("%-15s %016llx %-13s %016llx\n",
+	       "cr3:", save->cr3, "cr4:", save->cr4);
+	pr_err("%-15s %016llx %-13s %016llx\n",
+	       "dr6:", save->dr6, "dr7:", save->dr7);
+	pr_err("%-15s %016llx %-13s %016llx\n",
+	       "rip:", save->rip, "rflags:", save->rflags);
+	pr_err("%-15s %016llx %-13s %016llx\n",
+	       "rsp:", save->rsp, "rax:", save->rax);
+	pr_err("%-15s %016llx %-13s %016llx\n",
+	       "star:", save->star, "lstar:", save->lstar);
+	pr_err("%-15s %016llx %-13s %016llx\n",
+	       "cstar:", save->cstar, "sfmask:", save->sfmask);
+	pr_err("%-15s %016llx %-13s %016llx\n",
+	       "kernel_gs_base:", save->kernel_gs_base,
+	       "sysenter_cs:", save->sysenter_cs);
+	pr_err("%-15s %016llx %-13s %016llx\n",
+	       "sysenter_esp:", save->sysenter_esp,
+	       "sysenter_eip:", save->sysenter_eip);
+	pr_err("%-15s %016llx %-13s %016llx\n",
+	       "gpat:", save->g_pat, "dbgctl:", save->dbgctl);
+	pr_err("%-15s %016llx %-13s %016llx\n",
+	       "br_from:", save->br_from, "br_to:", save->br_to);
+	pr_err("%-15s %016llx %-13s %016llx\n",
+	       "excp_from:", save->last_excp_from,
+	       "excp_to:", save->last_excp_to);
 }
 
 static void svm_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2)
@@ -3384,7 +3483,7 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu)
 	     (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK))
 		return 0;
 
-	ret = !!(vmcb->save.rflags & X86_EFLAGS_IF);
+	ret = !!(kvm_get_rflags(vcpu) & X86_EFLAGS_IF);
 
 	if (is_guest_mode(vcpu))
 		return ret && !(svm->vcpu.arch.hflags & HF_VINTR_MASK);
@@ -3871,6 +3970,186 @@ static void svm_fpu_deactivate(struct kvm_vcpu *vcpu)
 	update_cr0_intercept(svm);
 }
 
+#define PRE_EX(exit)  { .exit_code = (exit), \
+			.stage = X86_ICPT_PRE_EXCEPT, }
+#define POST_EX(exit) { .exit_code = (exit), \
+			.stage = X86_ICPT_POST_EXCEPT, }
+#define POST_MEM(exit) { .exit_code = (exit), \
+			.stage = X86_ICPT_POST_MEMACCESS, }
+
+static struct __x86_intercept {
+	u32 exit_code;
+	enum x86_intercept_stage stage;
+} x86_intercept_map[] = {
+	[x86_intercept_cr_read]		= POST_EX(SVM_EXIT_READ_CR0),
+	[x86_intercept_cr_write]	= POST_EX(SVM_EXIT_WRITE_CR0),
+	[x86_intercept_clts]		= POST_EX(SVM_EXIT_WRITE_CR0),
+	[x86_intercept_lmsw]		= POST_EX(SVM_EXIT_WRITE_CR0),
+	[x86_intercept_smsw]		= POST_EX(SVM_EXIT_READ_CR0),
+	[x86_intercept_dr_read]		= POST_EX(SVM_EXIT_READ_DR0),
+	[x86_intercept_dr_write]	= POST_EX(SVM_EXIT_WRITE_DR0),
+	[x86_intercept_sldt]		= POST_EX(SVM_EXIT_LDTR_READ),
+	[x86_intercept_str]		= POST_EX(SVM_EXIT_TR_READ),
+	[x86_intercept_lldt]		= POST_EX(SVM_EXIT_LDTR_WRITE),
+	[x86_intercept_ltr]		= POST_EX(SVM_EXIT_TR_WRITE),
+	[x86_intercept_sgdt]		= POST_EX(SVM_EXIT_GDTR_READ),
+	[x86_intercept_sidt]		= POST_EX(SVM_EXIT_IDTR_READ),
+	[x86_intercept_lgdt]		= POST_EX(SVM_EXIT_GDTR_WRITE),
+	[x86_intercept_lidt]		= POST_EX(SVM_EXIT_IDTR_WRITE),
+	[x86_intercept_vmrun]		= POST_EX(SVM_EXIT_VMRUN),
+	[x86_intercept_vmmcall]		= POST_EX(SVM_EXIT_VMMCALL),
+	[x86_intercept_vmload]		= POST_EX(SVM_EXIT_VMLOAD),
+	[x86_intercept_vmsave]		= POST_EX(SVM_EXIT_VMSAVE),
+	[x86_intercept_stgi]		= POST_EX(SVM_EXIT_STGI),
+	[x86_intercept_clgi]		= POST_EX(SVM_EXIT_CLGI),
+	[x86_intercept_skinit]		= POST_EX(SVM_EXIT_SKINIT),
+	[x86_intercept_invlpga]		= POST_EX(SVM_EXIT_INVLPGA),
+	[x86_intercept_rdtscp]		= POST_EX(SVM_EXIT_RDTSCP),
+	[x86_intercept_monitor]		= POST_MEM(SVM_EXIT_MONITOR),
+	[x86_intercept_mwait]		= POST_EX(SVM_EXIT_MWAIT),
+	[x86_intercept_invlpg]		= POST_EX(SVM_EXIT_INVLPG),
+	[x86_intercept_invd]		= POST_EX(SVM_EXIT_INVD),
+	[x86_intercept_wbinvd]		= POST_EX(SVM_EXIT_WBINVD),
+	[x86_intercept_wrmsr]		= POST_EX(SVM_EXIT_MSR),
+	[x86_intercept_rdtsc]		= POST_EX(SVM_EXIT_RDTSC),
+	[x86_intercept_rdmsr]		= POST_EX(SVM_EXIT_MSR),
+	[x86_intercept_rdpmc]		= POST_EX(SVM_EXIT_RDPMC),
+	[x86_intercept_cpuid]		= PRE_EX(SVM_EXIT_CPUID),
+	[x86_intercept_rsm]		= PRE_EX(SVM_EXIT_RSM),
+	[x86_intercept_pause]		= PRE_EX(SVM_EXIT_PAUSE),
+	[x86_intercept_pushf]		= PRE_EX(SVM_EXIT_PUSHF),
+	[x86_intercept_popf]		= PRE_EX(SVM_EXIT_POPF),
+	[x86_intercept_intn]		= PRE_EX(SVM_EXIT_SWINT),
+	[x86_intercept_iret]		= PRE_EX(SVM_EXIT_IRET),
+	[x86_intercept_icebp]		= PRE_EX(SVM_EXIT_ICEBP),
+	[x86_intercept_hlt]		= POST_EX(SVM_EXIT_HLT),
+	[x86_intercept_in]		= POST_EX(SVM_EXIT_IOIO),
+	[x86_intercept_ins]		= POST_EX(SVM_EXIT_IOIO),
+	[x86_intercept_out]		= POST_EX(SVM_EXIT_IOIO),
+	[x86_intercept_outs]		= POST_EX(SVM_EXIT_IOIO),
+};
+
+#undef PRE_EX
+#undef POST_EX
+#undef POST_MEM
+
+static int svm_check_intercept(struct kvm_vcpu *vcpu,
+			       struct x86_instruction_info *info,
+			       enum x86_intercept_stage stage)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	int vmexit, ret = X86EMUL_CONTINUE;
+	struct __x86_intercept icpt_info;
+	struct vmcb *vmcb = svm->vmcb;
+
+	if (info->intercept >= ARRAY_SIZE(x86_intercept_map))
+		goto out;
+
+	icpt_info = x86_intercept_map[info->intercept];
+
+	if (stage != icpt_info.stage)
+		goto out;
+
+	switch (icpt_info.exit_code) {
+	case SVM_EXIT_READ_CR0:
+		if (info->intercept == x86_intercept_cr_read)
+			icpt_info.exit_code += info->modrm_reg;
+		break;
+	case SVM_EXIT_WRITE_CR0: {
+		unsigned long cr0, val;
+		u64 intercept;
+
+		if (info->intercept == x86_intercept_cr_write)
+			icpt_info.exit_code += info->modrm_reg;
+
+		if (icpt_info.exit_code != SVM_EXIT_WRITE_CR0)
+			break;
+
+		intercept = svm->nested.intercept;
+
+		if (!(intercept & (1ULL << INTERCEPT_SELECTIVE_CR0)))
+			break;
+
+		cr0 = vcpu->arch.cr0 & ~SVM_CR0_SELECTIVE_MASK;
+		val = info->src_val  & ~SVM_CR0_SELECTIVE_MASK;
+
+		if (info->intercept == x86_intercept_lmsw) {
+			cr0 &= 0xfUL;
+			val &= 0xfUL;
+			/* lmsw can't clear PE - catch this here */
+			if (cr0 & X86_CR0_PE)
+				val |= X86_CR0_PE;
+		}
+
+		if (cr0 ^ val)
+			icpt_info.exit_code = SVM_EXIT_CR0_SEL_WRITE;
+
+		break;
+	}
+	case SVM_EXIT_READ_DR0:
+	case SVM_EXIT_WRITE_DR0:
+		icpt_info.exit_code += info->modrm_reg;
+		break;
+	case SVM_EXIT_MSR:
+		if (info->intercept == x86_intercept_wrmsr)
+			vmcb->control.exit_info_1 = 1;
+		else
+			vmcb->control.exit_info_1 = 0;
+		break;
+	case SVM_EXIT_PAUSE:
+		/*
+		 * We get this for NOP only, but pause
+		 * is rep not, check this here
+		 */
+		if (info->rep_prefix != REPE_PREFIX)
+			goto out;
+	case SVM_EXIT_IOIO: {
+		u64 exit_info;
+		u32 bytes;
+
+		exit_info = (vcpu->arch.regs[VCPU_REGS_RDX] & 0xffff) << 16;
+
+		if (info->intercept == x86_intercept_in ||
+		    info->intercept == x86_intercept_ins) {
+			exit_info |= SVM_IOIO_TYPE_MASK;
+			bytes = info->src_bytes;
+		} else {
+			bytes = info->dst_bytes;
+		}
+
+		if (info->intercept == x86_intercept_outs ||
+		    info->intercept == x86_intercept_ins)
+			exit_info |= SVM_IOIO_STR_MASK;
+
+		if (info->rep_prefix)
+			exit_info |= SVM_IOIO_REP_MASK;
+
+		bytes = min(bytes, 4u);
+
+		exit_info |= bytes << SVM_IOIO_SIZE_SHIFT;
+
+		exit_info |= (u32)info->ad_bytes << (SVM_IOIO_ASIZE_SHIFT - 1);
+
+		vmcb->control.exit_info_1 = exit_info;
+		vmcb->control.exit_info_2 = info->next_rip;
+
+		break;
+	}
+	default:
+		break;
+	}
+
+	vmcb->control.next_rip  = info->next_rip;
+	vmcb->control.exit_code = icpt_info.exit_code;
+	vmexit = nested_svm_exit_handled(svm);
+
+	ret = (vmexit == NESTED_EXIT_DONE) ? X86EMUL_INTERCEPTED
+					   : X86EMUL_CONTINUE;
+
+out:
+	return ret;
+}
+
 static struct kvm_x86_ops svm_x86_ops = {
 	.cpu_has_kvm_support = has_svm,
 	.disabled_by_bios = is_disabled,
@@ -3952,10 +4231,14 @@ static struct kvm_x86_ops svm_x86_ops = {
 
 	.has_wbinvd_exit = svm_has_wbinvd_exit,
 
+	.set_tsc_khz = svm_set_tsc_khz,
 	.write_tsc_offset = svm_write_tsc_offset,
 	.adjust_tsc_offset = svm_adjust_tsc_offset,
+	.compute_tsc_offset = svm_compute_tsc_offset,
 
 	.set_tdp_cr3 = set_tdp_cr3,
+
+	.check_intercept = svm_check_intercept,
 };
 
 static int __init svm_init(void)

arch/x86/kvm/vmx.c

@@ -128,8 +128,11 @@ struct vcpu_vmx {
 	unsigned long         host_rsp;
 	int                   launched;
 	u8                    fail;
+	u8                    cpl;
+	bool                  nmi_known_unmasked;
 	u32                   exit_intr_info;
 	u32                   idt_vectoring_info;
+	ulong                 rflags;
 	struct shared_msr_entry *guest_msrs;
 	int                   nmsrs;
 	int                   save_nmsrs;
@@ -159,6 +162,10 @@ struct vcpu_vmx {
 			u32 ar;
 		} tr, es, ds, fs, gs;
 	} rmode;
+	struct {
+		u32 bitmask; /* 4 bits per segment (1 bit per field) */
+		struct kvm_save_segment seg[8];
+	} segment_cache;
 	int vpid;
 	bool emulation_required;
 
@@ -171,6 +178,15 @@ struct vcpu_vmx {
 	bool rdtscp_enabled;
 };
 
+enum segment_cache_field {
+	SEG_FIELD_SEL = 0,
+	SEG_FIELD_BASE = 1,
+	SEG_FIELD_LIMIT = 2,
+	SEG_FIELD_AR = 3,
+
+	SEG_FIELD_NR = 4
+};
+
 static inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
 {
 	return container_of(vcpu, struct vcpu_vmx, vcpu);
@@ -643,6 +659,62 @@ static void vmcs_set_bits(unsigned long field, u32 mask)
 	vmcs_writel(field, vmcs_readl(field) | mask);
 }
 
+static void vmx_segment_cache_clear(struct vcpu_vmx *vmx)
+{
+	vmx->segment_cache.bitmask = 0;
+}
+
+static bool vmx_segment_cache_test_set(struct vcpu_vmx *vmx, unsigned seg,
+				       unsigned field)
+{
+	bool ret;
+	u32 mask = 1 << (seg * SEG_FIELD_NR + field);
+
+	if (!(vmx->vcpu.arch.regs_avail & (1 << VCPU_EXREG_SEGMENTS))) {
+		vmx->vcpu.arch.regs_avail |= (1 << VCPU_EXREG_SEGMENTS);
+		vmx->segment_cache.bitmask = 0;
+	}
+	ret = vmx->segment_cache.bitmask & mask;
+	vmx->segment_cache.bitmask |= mask;
+	return ret;
+}
+
+static u16 vmx_read_guest_seg_selector(struct vcpu_vmx *vmx, unsigned seg)
+{
+	u16 *p = &vmx->segment_cache.seg[seg].selector;
+
+	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_SEL))
+		*p = vmcs_read16(kvm_vmx_segment_fields[seg].selector);
+	return *p;
+}
+
+static ulong vmx_read_guest_seg_base(struct vcpu_vmx *vmx, unsigned seg)
+{
+	ulong *p = &vmx->segment_cache.seg[seg].base;
+
+	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_BASE))
+		*p = vmcs_readl(kvm_vmx_segment_fields[seg].base);
+	return *p;
+}
+
+static u32 vmx_read_guest_seg_limit(struct vcpu_vmx *vmx, unsigned seg)
+{
+	u32 *p = &vmx->segment_cache.seg[seg].limit;
+
+	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_LIMIT))
+		*p = vmcs_read32(kvm_vmx_segment_fields[seg].limit);
+	return *p;
+}
+
+static u32 vmx_read_guest_seg_ar(struct vcpu_vmx *vmx, unsigned seg)
+{
+	u32 *p = &vmx->segment_cache.seg[seg].ar;
+
+	if (!vmx_segment_cache_test_set(vmx, seg, SEG_FIELD_AR))
+		*p = vmcs_read32(kvm_vmx_segment_fields[seg].ar_bytes);
+	return *p;
+}
+
 static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 {
 	u32 eb;
@@ -970,17 +1042,24 @@ static unsigned long vmx_get_rflags(struct kvm_vcpu *vcpu)
 {
 	unsigned long rflags, save_rflags;
 
-	rflags = vmcs_readl(GUEST_RFLAGS);
-	if (to_vmx(vcpu)->rmode.vm86_active) {
-		rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
-		save_rflags = to_vmx(vcpu)->rmode.save_rflags;
-		rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
+	if (!test_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail)) {
+		__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
+		rflags = vmcs_readl(GUEST_RFLAGS);
+		if (to_vmx(vcpu)->rmode.vm86_active) {
+			rflags &= RMODE_GUEST_OWNED_EFLAGS_BITS;
+			save_rflags = to_vmx(vcpu)->rmode.save_rflags;
+			rflags |= save_rflags & ~RMODE_GUEST_OWNED_EFLAGS_BITS;
+		}
+		to_vmx(vcpu)->rflags = rflags;
 	}
-	return rflags;
+	return to_vmx(vcpu)->rflags;
 }
 
 static void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
+	__set_bit(VCPU_EXREG_RFLAGS, (ulong *)&vcpu->arch.regs_avail);
+	__clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
+	to_vmx(vcpu)->rflags = rflags;
 	if (to_vmx(vcpu)->rmode.vm86_active) {
 		to_vmx(vcpu)->rmode.save_rflags = rflags;
 		rflags |= X86_EFLAGS_IOPL | X86_EFLAGS_VM;
@@ -1053,7 +1132,10 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
 	}
 
 	if (vmx->rmode.vm86_active) {
-		if (kvm_inject_realmode_interrupt(vcpu, nr) != EMULATE_DONE)
+		int inc_eip = 0;
+		if (kvm_exception_is_soft(nr))
+			inc_eip = vcpu->arch.event_exit_inst_len;
+		if (kvm_inject_realmode_interrupt(vcpu, nr, inc_eip) != EMULATE_DONE)
 			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 		return;
 	}
@@ -1150,6 +1232,16 @@ static u64 guest_read_tsc(void)
 	return host_tsc + tsc_offset;
 }
 
+/*
+ * Empty call-back. Needs to be implemented when VMX enables the SET_TSC_KHZ
+ * ioctl. In this case the call-back should update internal vmx state to make
+ * the changes effective.
+ */
+static void vmx_set_tsc_khz(struct kvm_vcpu *vcpu, u32 user_tsc_khz)
+{
+	/* Nothing to do here */
+}
+
 /*
  * writes 'offset' into guest's timestamp counter offset register
  */
@@ -1164,6 +1256,11 @@ static void vmx_adjust_tsc_offset(struct kvm_vcpu *vcpu, s64 adjustment)
 	vmcs_write64(TSC_OFFSET, offset + adjustment);
 }
 
+static u64 vmx_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
+{
+	return target_tsc - native_read_tsc();
+}
+
 /*
  * Reads an msr value (of 'msr_index') into 'pdata'.
  * Returns 0 on success, non-0 otherwise.
@@ -1243,9 +1340,11 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 		break;
 #ifdef CONFIG_X86_64
 	case MSR_FS_BASE:
+		vmx_segment_cache_clear(vmx);
 		vmcs_writel(GUEST_FS_BASE, data);
 		break;
 	case MSR_GS_BASE:
+		vmx_segment_cache_clear(vmx);
 		vmcs_writel(GUEST_GS_BASE, data);
 		break;
 	case MSR_KERNEL_GS_BASE:
@@ -1689,6 +1788,8 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
 	vmx->emulation_required = 1;
 	vmx->rmode.vm86_active = 0;
 
+	vmx_segment_cache_clear(vmx);
+
 	vmcs_write16(GUEST_TR_SELECTOR, vmx->rmode.tr.selector);
 	vmcs_writel(GUEST_TR_BASE, vmx->rmode.tr.base);
 	vmcs_write32(GUEST_TR_LIMIT, vmx->rmode.tr.limit);
@@ -1712,6 +1813,8 @@ static void enter_pmode(struct kvm_vcpu *vcpu)
 	fix_pmode_dataseg(VCPU_SREG_GS, &vmx->rmode.gs);
 	fix_pmode_dataseg(VCPU_SREG_FS, &vmx->rmode.fs);
 
+	vmx_segment_cache_clear(vmx);
+
 	vmcs_write16(GUEST_SS_SELECTOR, 0);
 	vmcs_write32(GUEST_SS_AR_BYTES, 0x93);
 
@@ -1775,6 +1878,8 @@ static void enter_rmode(struct kvm_vcpu *vcpu)
 		vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	}
 
+	vmx_segment_cache_clear(vmx);
+
 	vmx->rmode.tr.selector = vmcs_read16(GUEST_TR_SELECTOR);
 	vmx->rmode.tr.base = vmcs_readl(GUEST_TR_BASE);
 	vmcs_writel(GUEST_TR_BASE, rmode_tss_base(vcpu->kvm));
@@ -1851,6 +1956,8 @@ static void enter_lmode(struct kvm_vcpu *vcpu)
 {
 	u32 guest_tr_ar;
 
+	vmx_segment_cache_clear(to_vmx(vcpu));
+
 	guest_tr_ar = vmcs_read32(GUEST_TR_AR_BYTES);
 	if ((guest_tr_ar & AR_TYPE_MASK) != AR_TYPE_BUSY_64_TSS) {
 		printk(KERN_DEBUG "%s: tss fixup for long mode. \n",
@@ -1998,6 +2105,7 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	vmcs_writel(CR0_READ_SHADOW, cr0);
 	vmcs_writel(GUEST_CR0, hw_cr0);
 	vcpu->arch.cr0 = cr0;
+	__clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
 }
 
 static u64 construct_eptp(unsigned long root_hpa)
@@ -2053,7 +2161,6 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
 			    struct kvm_segment *var, int seg)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
 	struct kvm_save_segment *save;
 	u32 ar;
 
@@ -2075,13 +2182,13 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
 		var->limit = save->limit;
 		ar = save->ar;
 		if (seg == VCPU_SREG_TR
-		    || var->selector == vmcs_read16(sf->selector))
+		    || var->selector == vmx_read_guest_seg_selector(vmx, seg))
 			goto use_saved_rmode_seg;
 	}
-	var->base = vmcs_readl(sf->base);
-	var->limit = vmcs_read32(sf->limit);
-	var->selector = vmcs_read16(sf->selector);
-	ar = vmcs_read32(sf->ar_bytes);
+	var->base = vmx_read_guest_seg_base(vmx, seg);
+	var->limit = vmx_read_guest_seg_limit(vmx, seg);
+	var->selector = vmx_read_guest_seg_selector(vmx, seg);
+	ar = vmx_read_guest_seg_ar(vmx, seg);
 use_saved_rmode_seg:
 	if ((ar & AR_UNUSABLE_MASK) && !emulate_invalid_guest_state)
 		ar = 0;
@@ -2098,27 +2205,37 @@ use_saved_rmode_seg:
 
 static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
 {
-	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
 	struct kvm_segment s;
 
 	if (to_vmx(vcpu)->rmode.vm86_active) {
 		vmx_get_segment(vcpu, &s, seg);
 		return s.base;
 	}
-	return vmcs_readl(sf->base);
+	return vmx_read_guest_seg_base(to_vmx(vcpu), seg);
 }
 
-static int vmx_get_cpl(struct kvm_vcpu *vcpu)
+static int __vmx_get_cpl(struct kvm_vcpu *vcpu)
 {
 	if (!is_protmode(vcpu))
 		return 0;
 
-	if (vmx_get_rflags(vcpu) & X86_EFLAGS_VM) /* if virtual 8086 */
+	if (!is_long_mode(vcpu)
+	    && (kvm_get_rflags(vcpu) & X86_EFLAGS_VM)) /* if virtual 8086 */
 		return 3;
 
-	return vmcs_read16(GUEST_CS_SELECTOR) & 3;
+	return vmx_read_guest_seg_selector(to_vmx(vcpu), VCPU_SREG_CS) & 3;
 }
 
+static int vmx_get_cpl(struct kvm_vcpu *vcpu)
+{
+	if (!test_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail)) {
+		__set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
+		to_vmx(vcpu)->cpl = __vmx_get_cpl(vcpu);
+	}
+	return to_vmx(vcpu)->cpl;
+}
+
+
 static u32 vmx_segment_access_rights(struct kvm_segment *var)
 {
 	u32 ar;
@@ -2148,6 +2265,8 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
 	u32 ar;
 
+	vmx_segment_cache_clear(vmx);
+
 	if (vmx->rmode.vm86_active && seg == VCPU_SREG_TR) {
 		vmcs_write16(sf->selector, var->selector);
 		vmx->rmode.tr.selector = var->selector;
@@ -2184,11 +2303,12 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu,
 		ar |= 0x1; /* Accessed */
 
 	vmcs_write32(sf->ar_bytes, ar);
+	__clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
 }
 
 static void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
 {
-	u32 ar = vmcs_read32(GUEST_CS_AR_BYTES);
+	u32 ar = vmx_read_guest_seg_ar(to_vmx(vcpu), VCPU_SREG_CS);
 
 	*db = (ar >> 14) & 1;
 	*l = (ar >> 13) & 1;
@@ -2775,6 +2895,8 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 	if (ret != 0)
 		goto out;
 
+	vmx_segment_cache_clear(vmx);
+
 	seg_setup(VCPU_SREG_CS);
 	/*
 	 * GUEST_CS_BASE should really be 0xffff0000, but VT vm86 mode
@@ -2904,7 +3026,10 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu)
 
 	++vcpu->stat.irq_injections;
 	if (vmx->rmode.vm86_active) {
-		if (kvm_inject_realmode_interrupt(vcpu, irq) != EMULATE_DONE)
+		int inc_eip = 0;
+		if (vcpu->arch.interrupt.soft)
+			inc_eip = vcpu->arch.event_exit_inst_len;
+		if (kvm_inject_realmode_interrupt(vcpu, irq, inc_eip) != EMULATE_DONE)
 			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 		return;
 	}
@@ -2937,8 +3062,9 @@ static void vmx_inject_nmi(struct kvm_vcpu *vcpu)
 	}
 
 	++vcpu->stat.nmi_injections;
+	vmx->nmi_known_unmasked = false;
 	if (vmx->rmode.vm86_active) {
-		if (kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR) != EMULATE_DONE)
+		if (kvm_inject_realmode_interrupt(vcpu, NMI_VECTOR, 0) != EMULATE_DONE)
 			kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
 		return;
 	}
@@ -2961,6 +3087,8 @@ static bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu)
 {
 	if (!cpu_has_virtual_nmis())
 		return to_vmx(vcpu)->soft_vnmi_blocked;
+	if (to_vmx(vcpu)->nmi_known_unmasked)
+		return false;
 	return vmcs_read32(GUEST_INTERRUPTIBILITY_INFO)	& GUEST_INTR_STATE_NMI;
 }
 
@@ -2974,6 +3102,7 @@ static void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
 			vmx->vnmi_blocked_time = 0;
 		}
 	} else {
+		vmx->nmi_known_unmasked = !masked;
 		if (masked)
 			vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
 				      GUEST_INTR_STATE_NMI);
@@ -3091,7 +3220,7 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 	enum emulation_result er;
 
 	vect_info = vmx->idt_vectoring_info;
-	intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+	intr_info = vmx->exit_intr_info;
 
 	if (is_machine_check(intr_info))
 		return handle_machine_check(vcpu);
@@ -3122,7 +3251,6 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 	}
 
 	error_code = 0;
-	rip = kvm_rip_read(vcpu);
 	if (intr_info & INTR_INFO_DELIVER_CODE_MASK)
 		error_code = vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
 	if (is_page_fault(intr_info)) {
@@ -3169,6 +3297,7 @@ static int handle_exception(struct kvm_vcpu *vcpu)
 		vmx->vcpu.arch.event_exit_inst_len =
 			vmcs_read32(VM_EXIT_INSTRUCTION_LEN);
 		kvm_run->exit_reason = KVM_EXIT_DEBUG;
+		rip = kvm_rip_read(vcpu);
 		kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip;
 		kvm_run->debug.arch.exception = ex_no;
 		break;
@@ -3505,9 +3634,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
 		switch (type) {
 		case INTR_TYPE_NMI_INTR:
 			vcpu->arch.nmi_injected = false;
-			if (cpu_has_virtual_nmis())
-				vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
-					      GUEST_INTR_STATE_NMI);
+			vmx_set_nmi_mask(vcpu, true);
 			break;
 		case INTR_TYPE_EXT_INTR:
 		case INTR_TYPE_SOFT_INTR:
@@ -3867,12 +3994,17 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 
 static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
 {
-	u32 exit_intr_info = vmx->exit_intr_info;
+	u32 exit_intr_info;
+
+	if (!(vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY
+	      || vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI))
+		return;
+
+	vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+	exit_intr_info = vmx->exit_intr_info;
 
 	/* Handle machine checks before interrupts are enabled */
-	if ((vmx->exit_reason == EXIT_REASON_MCE_DURING_VMENTRY)
-	    || (vmx->exit_reason == EXIT_REASON_EXCEPTION_NMI
-		&& is_machine_check(exit_intr_info)))
+	if (is_machine_check(exit_intr_info))
 		kvm_machine_check();
 
 	/* We need to handle NMIs before interrupts are enabled */
@@ -3886,7 +4018,7 @@ static void vmx_complete_atomic_exit(struct vcpu_vmx *vmx)
 
 static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
 {
-	u32 exit_intr_info = vmx->exit_intr_info;
+	u32 exit_intr_info;
 	bool unblock_nmi;
 	u8 vector;
 	bool idtv_info_valid;
@@ -3894,6 +4026,13 @@ static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
 	idtv_info_valid = vmx->idt_vectoring_info & VECTORING_INFO_VALID_MASK;
 
 	if (cpu_has_virtual_nmis()) {
+		if (vmx->nmi_known_unmasked)
+			return;
+		/*
+		 * Can't use vmx->exit_intr_info since we're not sure what
+		 * the exit reason is.
+		 */
+		exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
 		unblock_nmi = (exit_intr_info & INTR_INFO_UNBLOCK_NMI) != 0;
 		vector = exit_intr_info & INTR_INFO_VECTOR_MASK;
 		/*
@@ -3910,6 +4049,10 @@ static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
 		    vector != DF_VECTOR && !idtv_info_valid)
 			vmcs_set_bits(GUEST_INTERRUPTIBILITY_INFO,
 				      GUEST_INTR_STATE_NMI);
+		else
+			vmx->nmi_known_unmasked =
+				!(vmcs_read32(GUEST_INTERRUPTIBILITY_INFO)
+				  & GUEST_INTR_STATE_NMI);
 	} else if (unlikely(vmx->soft_vnmi_blocked))
 		vmx->vnmi_blocked_time +=
 			ktime_to_ns(ktime_sub(ktime_get(), vmx->entry_time));
@@ -3946,8 +4089,7 @@ static void __vmx_complete_interrupts(struct vcpu_vmx *vmx,
 		 * Clear bit "block by NMI" before VM entry if a NMI
 		 * delivery faulted.
 		 */
-		vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
-				GUEST_INTR_STATE_NMI);
+		vmx_set_nmi_mask(&vmx->vcpu, false);
 		break;
 	case INTR_TYPE_SOFT_EXCEPTION:
 		vmx->vcpu.arch.event_exit_inst_len =
@@ -4124,7 +4266,10 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	      );
 
 	vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
+				  | (1 << VCPU_EXREG_RFLAGS)
+				  | (1 << VCPU_EXREG_CPL)
 				  | (1 << VCPU_EXREG_PDPTR)
+				  | (1 << VCPU_EXREG_SEGMENTS)
 				  | (1 << VCPU_EXREG_CR3));
 	vcpu->arch.regs_dirty = 0;
 
@@ -4134,7 +4279,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	vmx->launched = 1;
 
 	vmx->exit_reason = vmcs_read32(VM_EXIT_REASON);
-	vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
 
 	vmx_complete_atomic_exit(vmx);
 	vmx_recover_nmi_blocking(vmx);
@@ -4195,8 +4339,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 		goto free_vcpu;
 
 	vmx->guest_msrs = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	err = -ENOMEM;
 	if (!vmx->guest_msrs) {
-		err = -ENOMEM;
 		goto uninit_vcpu;
 	}
 
@@ -4215,7 +4359,8 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
 	if (err)
 		goto free_vmcs;
 	if (vm_need_virtualize_apic_accesses(kvm))
-		if (alloc_apic_access_page(kvm) != 0)
+		err = alloc_apic_access_page(kvm);
+		if (err)
 			goto free_vmcs;
 
 	if (enable_ept) {
@@ -4368,6 +4513,13 @@ static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 {
 }
 
+static int vmx_check_intercept(struct kvm_vcpu *vcpu,
+			       struct x86_instruction_info *info,
+			       enum x86_intercept_stage stage)
+{
+	return X86EMUL_CONTINUE;
+}
+
 static struct kvm_x86_ops vmx_x86_ops = {
 	.cpu_has_kvm_support = cpu_has_kvm_support,
 	.disabled_by_bios = vmx_disabled_by_bios,
@@ -4449,10 +4601,14 @@ static struct kvm_x86_ops vmx_x86_ops = {
 
 	.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
 
+	.set_tsc_khz = vmx_set_tsc_khz,
 	.write_tsc_offset = vmx_write_tsc_offset,
 	.adjust_tsc_offset = vmx_adjust_tsc_offset,
+	.compute_tsc_offset = vmx_compute_tsc_offset,
 
 	.set_tdp_cr3 = vmx_set_cr3,
+
+	.check_intercept = vmx_check_intercept,
 };
 
 static int __init vmx_init(void)

arch/x86/kvm/x86.h

@@ -77,7 +77,7 @@ static inline u32 bit(int bitno)
 
 void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
-int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq);
+int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq, int inc_eip);
 
 void kvm_write_tsc(struct kvm_vcpu *vcpu, u64 data);
 

include/linux/kvm.h

@@ -541,6 +541,9 @@ struct kvm_ppc_pvinfo {
 #define KVM_CAP_PPC_GET_PVINFO 57
 #define KVM_CAP_PPC_IRQ_LEVEL 58
 #define KVM_CAP_ASYNC_PF 59
+#define KVM_CAP_TSC_CONTROL 60
+#define KVM_CAP_GET_TSC_KHZ 61
+#define KVM_CAP_PPC_BOOKE_SREGS 62
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -677,6 +680,9 @@ struct kvm_clock_data {
 #define KVM_SET_PIT2              _IOW(KVMIO,  0xa0, struct kvm_pit_state2)
 /* Available with KVM_CAP_PPC_GET_PVINFO */
 #define KVM_PPC_GET_PVINFO	  _IOW(KVMIO,  0xa1, struct kvm_ppc_pvinfo)
+/* Available with KVM_CAP_TSC_CONTROL */
+#define KVM_SET_TSC_KHZ           _IO(KVMIO,  0xa2)
+#define KVM_GET_TSC_KHZ           _IO(KVMIO,  0xa3)
 
 /*
  * ioctls for vcpu fds

include/linux/kvm_host.h

@@ -27,6 +27,10 @@
 
 #include <asm/kvm_host.h>
 
+#ifndef KVM_MMIO_SIZE
+#define KVM_MMIO_SIZE 8
+#endif
+
 /*
  * vcpu->requests bit members
  */
@@ -43,7 +47,6 @@
 #define KVM_REQ_DEACTIVATE_FPU    10
 #define KVM_REQ_EVENT             11
 #define KVM_REQ_APF_HALT          12
-#define KVM_REQ_NMI               13
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID	0
 
@@ -133,7 +136,8 @@ struct kvm_vcpu {
 	int mmio_read_completed;
 	int mmio_is_write;
 	int mmio_size;
-	unsigned char mmio_data[8];
+	int mmio_index;
+	unsigned char mmio_data[KVM_MMIO_SIZE];
 	gpa_t mmio_phys_addr;
 #endif
 
@@ -292,9 +296,10 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
 }
 
 #define kvm_for_each_vcpu(idx, vcpup, kvm) \
-	for (idx = 0, vcpup = kvm_get_vcpu(kvm, idx); \
-	     idx < atomic_read(&kvm->online_vcpus) && vcpup; \
-	     vcpup = kvm_get_vcpu(kvm, ++idx))
+	for (idx = 0; \
+	     idx < atomic_read(&kvm->online_vcpus) && \
+	     (vcpup = kvm_get_vcpu(kvm, idx)) != NULL; \
+	     idx++)
 
 int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id);
 void kvm_vcpu_uninit(struct kvm_vcpu *vcpu);
@@ -365,7 +370,6 @@ pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
 		      bool *writable);
 pfn_t gfn_to_pfn_memslot(struct kvm *kvm,
 			 struct kvm_memory_slot *slot, gfn_t gfn);
-int memslot_id(struct kvm *kvm, gfn_t gfn);
 void kvm_release_pfn_dirty(pfn_t);
 void kvm_release_pfn_clean(pfn_t pfn);
 void kvm_set_pfn_dirty(pfn_t pfn);
@@ -587,8 +591,17 @@ static inline int kvm_deassign_device(struct kvm *kvm,
 
 static inline void kvm_guest_enter(void)
 {
+	BUG_ON(preemptible());
 	account_system_vtime(current);
 	current->flags |= PF_VCPU;
+	/* KVM does not hold any references to rcu protected data when it
+	 * switches CPU into a guest mode. In fact switching to a guest mode
+	 * is very similar to exiting to userspase from rcu point of view. In
+	 * addition CPU may stay in a guest mode for quite a long time (up to
+	 * one time slice). Lets treat guest mode as quiescent state, just like
+	 * we do with user-mode execution.
+	 */
+	rcu_virt_note_context_switch(smp_processor_id());
 }
 
 static inline void kvm_guest_exit(void)
@@ -597,6 +610,11 @@ static inline void kvm_guest_exit(void)
 	current->flags &= ~PF_VCPU;
 }
 
+static inline int memslot_id(struct kvm *kvm, gfn_t gfn)
+{
+	return gfn_to_memslot(kvm, gfn)->id;
+}
+
 static inline unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
 					       gfn_t gfn)
 {

virt/kvm/ioapic.c

@@ -167,7 +167,7 @@ static int ioapic_deliver(struct kvm_ioapic *ioapic, int irq)
 
 	ioapic_debug("dest=%x dest_mode=%x delivery_mode=%x "
 		     "vector=%x trig_mode=%x\n",
-		     entry->fields.dest, entry->fields.dest_mode,
+		     entry->fields.dest_id, entry->fields.dest_mode,
 		     entry->fields.delivery_mode, entry->fields.vector,
 		     entry->fields.trig_mode);
 

virt/kvm/kvm_main.c

@@ -467,6 +467,7 @@ static struct kvm *kvm_create_vm(void)
 		if (!kvm->buses[i])
 			goto out_err;
 	}
+	spin_lock_init(&kvm->mmu_lock);
 
 	r = kvm_init_mmu_notifier(kvm);
 	if (r)
@@ -474,7 +475,6 @@ static struct kvm *kvm_create_vm(void)
 
 	kvm->mm = current->mm;
 	atomic_inc(&kvm->mm->mm_count);
-	spin_lock_init(&kvm->mmu_lock);
 	kvm_eventfd_init(kvm);
 	mutex_init(&kvm->lock);
 	mutex_init(&kvm->irq_lock);
@@ -648,7 +648,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		goto out;
 	if (mem->guest_phys_addr & (PAGE_SIZE - 1))
 		goto out;
-	if (user_alloc && (mem->userspace_addr & (PAGE_SIZE - 1)))
+	/* We can read the guest memory with __xxx_user() later on. */
+	if (user_alloc &&
+	    ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
+	     !access_ok(VERIFY_WRITE, mem->userspace_addr, mem->memory_size)))
 		goto out;
 	if (mem->slot >= KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
 		goto out;
@@ -996,23 +999,6 @@ out:
 	return size;
 }
 
-int memslot_id(struct kvm *kvm, gfn_t gfn)
-{
-	int i;
-	struct kvm_memslots *slots = kvm_memslots(kvm);
-	struct kvm_memory_slot *memslot = NULL;
-
-	for (i = 0; i < slots->nmemslots; ++i) {
-		memslot = &slots->memslots[i];
-
-		if (gfn >= memslot->base_gfn
-		    && gfn < memslot->base_gfn + memslot->npages)
-			break;
-	}
-
-	return memslot - slots->memslots;
-}
-
 static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
 				     gfn_t *nr_pages)
 {
@@ -1300,7 +1286,7 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 	addr = gfn_to_hva(kvm, gfn);
 	if (kvm_is_error_hva(addr))
 		return -EFAULT;
-	r = copy_from_user(data, (void __user *)addr + offset, len);
+	r = __copy_from_user(data, (void __user *)addr + offset, len);
 	if (r)
 		return -EFAULT;
 	return 0;