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

 /*
- * 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

 /*
- * 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_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,
+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 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 	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 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 		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))
+		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 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 		--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 @@ static bool FNAME(prefetch_invalid_gpte)(struct kvm_vcpu *vcpu,
 }
 
 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/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);