KVM updates for 2.6.32 merge window (1/4)

index 29f9129..db0b8b6 100644
@@ -801,8 +801,9 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
 		vmx->rmode.irq.pending = true;
 		vmx->rmode.irq.vector = nr;
 		vmx->rmode.irq.rip = kvm_rip_read(vcpu);
-		if (nr == BP_VECTOR || nr == OF_VECTOR)
-			vmx->rmode.irq.rip++;
+		if (kvm_exception_is_soft(nr))
+			vmx->rmode.irq.rip +=
+				vmx->vcpu.arch.event_exit_inst_len;
 		intr_info |= INTR_TYPE_SOFT_INTR;
 		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
 		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1);

@@ -2468,6 +2469,9 @@ static void vmx_inject_irq(struct kvm_vcpu *vcpu)
 		vmx->rmode.irq.pending = true;
 		vmx->rmode.irq.vector = irq;
 		vmx->rmode.irq.rip = kvm_rip_read(vcpu);
+		if (vcpu->arch.interrupt.soft)
+			vmx->rmode.irq.rip +=
+				vmx->vcpu.arch.event_exit_inst_len;
 		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
 			     irq | INTR_TYPE_SOFT_INTR | INTR_INFO_VALID_MASK);
 		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1);

index eabdc1c..7956175 100644
@@ -752,8 +752,6 @@ static inline void kvm_inject_gp(struct kvm_vcpu *vcpu, u32 error_code)
 	kvm_queue_exception_e(vcpu, GP_VECTOR, error_code);
 }
 
-#define MSR_IA32_TIME_STAMP_COUNTER		0x010
-
 #define TSS_IOPB_BASE_OFFSET 0x66
 #define TSS_BASE_SIZE 0x68
 #define TSS_IOPB_SIZE (65536 / 8)

index b1f658a..48b22c9 100644
@@ -1953,7 +1953,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	switch (ecx) {
-	case MSR_IA32_TIME_STAMP_COUNTER: {
+	case MSR_IA32_TSC: {
 		u64 tsc;
 
 		rdtscll(tsc);

@@ -2043,7 +2043,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	switch (ecx) {
-	case MSR_IA32_TIME_STAMP_COUNTER: {
+	case MSR_IA32_TSC: {
 		u64 tsc;
 
 		rdtscll(tsc);

index db0b8b6..c87c93f 100644
@@ -941,7 +941,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata)
 	case MSR_EFER:
 		return kvm_get_msr_common(vcpu, msr_index, pdata);
 #endif
-	case MSR_IA32_TIME_STAMP_COUNTER:
+	case MSR_IA32_TSC:
 		data = guest_read_tsc();
 		break;
 	case MSR_IA32_SYSENTER_CS:

@@ -1001,7 +1001,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 	case MSR_IA32_SYSENTER_ESP:
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
-	case MSR_IA32_TIME_STAMP_COUNTER:
+	case MSR_IA32_TSC:
 		rdtscll(host_tsc);
 		guest_write_tsc(data, host_tsc);
 		break;

index 3d45290..6d46079 100644
@@ -466,7 +466,7 @@ static u32 msrs_to_save[] = {
 #ifdef CONFIG_X86_64
 	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
 #endif
-	MSR_IA32_TIME_STAMP_COUNTER, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
+	MSR_IA32_TSC, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
 };
 

@@ -644,8 +644,7 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
-	kvm_get_msr(v, MSR_IA32_TIME_STAMP_COUNTER,
-			  &vcpu->hv_clock.tsc_timestamp);
+	kvm_get_msr(v, MSR_IA32_TSC, &vcpu->hv_clock.tsc_timestamp);
 	ktime_get_ts(&ts);
 	local_irq_restore(flags);
 

index 125be8b..708b9c3 100644
@@ -17,6 +17,7 @@
 #define __KVM_HAVE_USER_NMI
 #define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_MSIX
+#define __KVM_HAVE_MCE
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256

index 7956175..81c68f6 100644
@@ -373,6 +373,11 @@ struct kvm_vcpu_arch {
 	unsigned long dr6;
 	unsigned long dr7;
 	unsigned long eff_db[KVM_NR_DB_REGS];
+
+	u64 mcg_cap;
+	u64 mcg_status;
+	u64 mcg_ctl;
+	u64 *mce_banks;
 };
 
 struct kvm_mem_alias {

299 lines not on this page · raw message

index 3db5d8d..7b17141 100644
@@ -415,6 +415,9 @@ struct kvm_trace_rec {
 #define KVM_CAP_ASSIGN_DEV_IRQ 29
 /* Another bug in KVM_SET_USER_MEMORY_REGION fixed: */
 #define KVM_CAP_JOIN_MEMORY_REGIONS_WORKS 30
+#ifdef __KVM_HAVE_MCE
+#define KVM_CAP_MCE 31
+#endif
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

@@ -454,6 +457,19 @@ struct kvm_irq_routing {
 
 #endif
 
+#ifdef KVM_CAP_MCE
+/* x86 MCE */
+struct kvm_x86_mce {
+	__u64 status;
+	__u64 addr;
+	__u64 misc;
+	__u64 mcg_status;
+	__u8 bank;
+	__u8 pad1[7];
+	__u64 pad2[3];
+};
+#endif
+
 /*
  * ioctls for VM fds
  */

@@ -541,6 +557,10 @@ struct kvm_irq_routing {
 #define KVM_NMI                   _IO(KVMIO,  0x9a)
 /* Available with KVM_CAP_SET_GUEST_DEBUG */
 #define KVM_SET_GUEST_DEBUG       _IOW(KVMIO,  0x9b, struct kvm_guest_debug)
+/* MCE for x86 */
+#define KVM_X86_SETUP_MCE         _IOW(KVMIO,  0x9c, __u64)
+#define KVM_X86_GET_MCE_CAP_SUPPORTED _IOR(KVMIO,  0x9d, __u64)
+#define KVM_X86_SET_MCE           _IOW(KVMIO,  0x9e, struct kvm_x86_mce)
 
 /*
  * Deprecated interfaces

index 55a9dd1..a93ba37 100644
@@ -973,8 +973,6 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	u64 data;
 
 	switch (msr) {
-	case 0xc0010010: /* SYSCFG */
-	case 0xc0010015: /* HWCR */
 	case MSR_IA32_PLATFORM_ID:
 	case MSR_IA32_UCODE_REV:
 	case MSR_IA32_EBL_CR_POWERON:

@@ -983,6 +981,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_IA32_LASTBRANCHTOIP:
 	case MSR_IA32_LASTINTFROMIP:
 	case MSR_IA32_LASTINTTOIP:
+	case MSR_K8_SYSCFG:
+	case MSR_K7_HWCR:
 	case MSR_VM_HSAVE_PA:
 	case MSR_P6_EVNTSEL0:
 	case MSR_P6_EVNTSEL1:

index a93ba37..25a1c57 100644
@@ -1506,6 +1506,10 @@ static int kvm_dev_ioctl_get_supported_cpuid(struct kvm_cpuid2 *cpuid,
 	for (func = 0x80000001; func <= limit && nent < cpuid->nent; ++func)
 		do_cpuid_ent(&cpuid_entries[nent], func, 0,
 			     &nent, cpuid->nent);
+	r = -E2BIG;
+	if (nent >= cpuid->nent)
+		goto out_free;
+
 	r = -EFAULT;
 	if (copy_to_user(entries, cpuid_entries,
 			 nent * sizeof(struct kvm_cpuid_entry2)))

index 616de46..a30d5fc 100644
@@ -60,6 +60,7 @@
 #define SrcImmByte  (6<<4)	/* 8-bit sign-extended immediate operand. */
 #define SrcOne      (7<<4)	/* Implied '1' */
 #define SrcImmUByte (8<<4)      /* 8-bit unsigned immediate operand. */
+#define SrcImmU     (9<<4)      /* Immediate operand, unsigned */
 #define SrcMask     (0xf<<4)
 /* Generic ModRM decode. */
 #define ModRM       (1<<8)

@@ -1027,6 +1028,7 @@ done_prefixes:
 		c->src.type = OP_MEM;
 		break;
 	case SrcImm:
+	case SrcImmU:
 		c->src.type = OP_IMM;
 		c->src.ptr = (unsigned long *)c->eip;
 		c->src.bytes = (c->d & ByteOp) ? 1 : c->op_bytes;

@@ -1044,6 +1046,19 @@ done_prefixes:
 			c->src.val = insn_fetch(s32, 4, c->eip);
 			break;
 		}
+		if ((c->d & SrcMask) == SrcImmU) {
+			switch (c->src.bytes) {
+			case 1:
+				c->src.val &= 0xff;
+				break;
+			case 2:
+				c->src.val &= 0xffff;
+				break;
+			case 4:
+				c->src.val &= 0xffffffff;
+				break;
+			}
+		}
 		break;
 	case SrcImmByte:
 	case SrcImmUByte:

index a30d5fc..ef4dfca 100644
@@ -196,7 +196,7 @@ static u32 opcode_table[256] = {
 	ByteOp | SrcImmUByte, SrcImmUByte,
 	/* 0xE8 - 0xEF */
 	SrcImm | Stack, SrcImm | ImplicitOps,
-	SrcImm | Src2Imm16, SrcImmByte | ImplicitOps,
+	SrcImmU | Src2Imm16, SrcImmByte | ImplicitOps,
 	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
 	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
 	/* 0xF0 - 0xF7 */

index c87c93f..c14bffc 100644
@@ -3453,6 +3453,14 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	if (test_bit(VCPU_REGS_RIP, (unsigned long *)&vcpu->arch.regs_dirty))
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 
+	/* When single-stepping over STI and MOV SS, we must clear the
+	 * corresponding interruptibility bits in the guest state. Otherwise
+	 * vmentry fails as it then expects bit 14 (BS) in pending debug
+	 * exceptions being set, but that's not correct for the guest debugging
+	 * case. */
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		vmx_set_interrupt_shadow(vcpu, 0);
+
 	/*
 	 * Loading guest fpu may have cleared host cr0.ts
 	 */

index 25a1c57..f064239 100644
@@ -3361,9 +3361,6 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 
 static void inject_pending_irq(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
-	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
-		kvm_x86_ops->set_interrupt_shadow(vcpu, 0);
-
 	/* try to reinject previous events if any */
 	if (vcpu->arch.nmi_injected) {
 		kvm_x86_ops->set_nmi(vcpu);

index f064239..15f39fc 100644
@@ -1126,6 +1126,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_REINJECT_CONTROL:
 	case KVM_CAP_IRQ_INJECT_STATUS:
 	case KVM_CAP_ASSIGN_DEV_IRQ:
+	case KVM_CAP_IRQFD:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:

index 7b17141..8f53f24 100644
@@ -418,6 +418,7 @@ struct kvm_trace_rec {
 #ifdef __KVM_HAVE_MCE
 #define KVM_CAP_MCE 31
 #endif
+#define KVM_CAP_IRQFD 32
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

@@ -470,6 +471,15 @@ struct kvm_x86_mce {
 };
 #endif
 
+#define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
+
+struct kvm_irqfd {
+	__u32 fd;
+	__u32 gsi;
+	__u32 flags;
+	__u8  pad[20];
+};
+
 /*
  * ioctls for VM fds
  */

@@ -514,6 +524,7 @@ struct kvm_x86_mce {
 #define KVM_ASSIGN_SET_MSIX_ENTRY \
 			_IOW(KVMIO, 0x74, struct kvm_assigned_msix_entry)
 #define KVM_DEASSIGN_DEV_IRQ       _IOW(KVMIO, 0x75, struct kvm_assigned_irq)
+#define KVM_IRQFD                  _IOW(KVMIO, 0x76, struct kvm_irqfd)
 
 /*
  * ioctls for vcpu fds

index 3060bdc..7724dcb 100644
@@ -136,6 +136,12 @@ struct kvm {
 	struct list_head vm_list;
 	struct kvm_io_bus mmio_bus;
 	struct kvm_io_bus pio_bus;
+#ifdef CONFIG_HAVE_KVM_EVENTFD
+	struct {
+		spinlock_t        lock;
+		struct list_head  items;
+	} irqfds;
+#endif
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;
 	atomic_t users_count;

@@ -525,4 +531,22 @@ static inline void kvm_free_irq_routing(struct kvm *kvm) {}
 
 #endif
 
+#ifdef CONFIG_HAVE_KVM_EVENTFD
+
+void kvm_irqfd_init(struct kvm *kvm);
+int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags);
+void kvm_irqfd_release(struct kvm *kvm);
+
+#else
+
+static inline void kvm_irqfd_init(struct kvm *kvm) {}
+static inline int kvm_irqfd(struct kvm *kvm, int fd, int gsi, int flags)
+{
+	return -EINVAL;
+}
+
+static inline void kvm_irqfd_release(struct kvm *kvm) {}
+
+#endif /* CONFIG_HAVE_KVM_EVENTFD */
+
 #endif

329 lines not on this page · raw message

index 2884baf..dee321e 100644
@@ -986,6 +986,7 @@ static struct kvm *kvm_create_vm(void)
 	spin_lock_init(&kvm->mmu_lock);
 	spin_lock_init(&kvm->requests_lock);
 	kvm_io_bus_init(&kvm->pio_bus);
+	kvm_irqfd_init(kvm);
 	mutex_init(&kvm->lock);
 	kvm_io_bus_init(&kvm->mmio_bus);
 	init_rwsem(&kvm->slots_lock);

@@ -1071,6 +1072,8 @@ static int kvm_vm_release(struct inode *inode, struct file *filp)
 {
 	struct kvm *kvm = filp->private_data;
 
+	kvm_irqfd_release(kvm);
+
 	kvm_put_kvm(kvm);
 	return 0;
 }

@@ -2222,6 +2225,15 @@ static long kvm_vm_ioctl(struct file *filp,
 	}
 #endif
 #endif /* KVM_CAP_IRQ_ROUTING */
+	case KVM_IRQFD: {
+		struct kvm_irqfd data;
+
+		r = -EFAULT;
+		if (copy_from_user(&data, argp, sizeof data))
+			goto out;
+		r = kvm_irqfd(kvm, data.fd, data.gsi, data.flags);
+		break;
+	}
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 	}

index 21f68e0..0990bc9 100644
@@ -563,7 +563,7 @@ static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
 	}
 }
 
-struct kvm_pit *kvm_create_pit(struct kvm *kvm)
+struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 {
 	struct kvm_pit *pit;
 	struct kvm_kpit_state *pit_state;

@@ -589,11 +589,13 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm)
 	pit->dev.private = pit;
 	kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev);
 
-	pit->speaker_dev.read = speaker_ioport_read;
-	pit->speaker_dev.write = speaker_ioport_write;
-	pit->speaker_dev.in_range = speaker_in_range;
-	pit->speaker_dev.private = pit;
-	kvm_io_bus_register_dev(&kvm->pio_bus, &pit->speaker_dev);
+	if (flags & KVM_PIT_SPEAKER_DUMMY) {
+		pit->speaker_dev.read = speaker_ioport_read;
+		pit->speaker_dev.write = speaker_ioport_write;
+		pit->speaker_dev.in_range = speaker_in_range;
+		pit->speaker_dev.private = pit;
+		kvm_io_bus_register_dev(&kvm->pio_bus, &pit->speaker_dev);
+	}
 
 	kvm->arch.vpit = pit;
 	pit->kvm = kvm;

index bbd863f..b267018 100644
@@ -50,7 +50,7 @@ struct kvm_pit {
 
 void kvm_inject_pit_timer_irqs(struct kvm_vcpu *vcpu);
 void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val);
-struct kvm_pit *kvm_create_pit(struct kvm *kvm);
+struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags);
 void kvm_free_pit(struct kvm *kvm);
 void kvm_pit_reset(struct kvm_pit *pit);
 

index 15f39fc..5eb3b8d 100644
@@ -1127,6 +1127,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_IRQ_INJECT_STATUS:
 	case KVM_CAP_ASSIGN_DEV_IRQ:
 	case KVM_CAP_IRQFD:
+	case KVM_CAP_PIT2:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:

@@ -2038,6 +2039,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 	union {
 		struct kvm_pit_state ps;
 		struct kvm_memory_alias alias;
+		struct kvm_pit_config pit_config;
 	} u;
 
 	switch (ioctl) {

@@ -2098,12 +2100,20 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		}
 		break;
 	case KVM_CREATE_PIT:
+		u.pit_config.flags = KVM_PIT_SPEAKER_DUMMY;
+		goto create_pit;
+	case KVM_CREATE_PIT2:
+		r = -EFAULT;
+		if (copy_from_user(&u.pit_config, argp,
+				   sizeof(struct kvm_pit_config)))
+			goto out;
+	create_pit:
 		mutex_lock(&kvm->lock);
 		r = -EEXIST;
 		if (kvm->arch.vpit)
 			goto create_pit_unlock;
 		r = -ENOMEM;
-		kvm->arch.vpit = kvm_create_pit(kvm);
+		kvm->arch.vpit = kvm_create_pit(kvm, u.pit_config.flags);
 		if (kvm->arch.vpit)
 			r = 0;
 	create_pit_unlock:

index 8f53f24..65df6f5 100644
@@ -70,6 +70,14 @@ struct kvm_irqchip {
 	} chip;
 };
 
+/* for KVM_CREATE_PIT2 */
+struct kvm_pit_config {
+	__u32 flags;
+	__u32 pad[15];
+};
+
+#define KVM_PIT_SPEAKER_DUMMY     1
+
 #define KVM_EXIT_UNKNOWN          0
 #define KVM_EXIT_EXCEPTION        1
 #define KVM_EXIT_IO               2

@@ -419,6 +427,9 @@ struct kvm_trace_rec {
 #define KVM_CAP_MCE 31
 #endif
 #define KVM_CAP_IRQFD 32
+#ifdef __KVM_HAVE_PIT
+#define KVM_CAP_PIT2 33
+#endif
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

@@ -525,6 +536,7 @@ struct kvm_irqfd {
 			_IOW(KVMIO, 0x74, struct kvm_assigned_msix_entry)
 #define KVM_DEASSIGN_DEV_IRQ       _IOW(KVMIO, 0x75, struct kvm_assigned_irq)
 #define KVM_IRQFD                  _IOW(KVMIO, 0x76, struct kvm_irqfd)
+#define KVM_CREATE_PIT2		   _IOW(KVMIO, 0x77, struct kvm_pit_config)
 
 /*
  * ioctls for vcpu fds

index 80c57b0..3199221 100644
@@ -1224,7 +1224,7 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 		/*Initialize itc offset for vcpus*/
 		itc_offset = 0UL - kvm_get_itc(vcpu);
-		for (i = 0; i < kvm->arch.online_vcpus; i++) {
+		for (i = 0; i < KVM_MAX_VCPUS; i++) {
 			v = (struct kvm_vcpu *)((char *)vcpu +
 					sizeof(struct kvm_vcpu_data) * i);
 			v->arch.itc_offset = itc_offset;

index 1cd02f6..0a784f6 100644
@@ -182,8 +182,9 @@ struct kvm_s390_interrupt_info {
 };
 
 /* for local_interrupt.action_flags */
-#define ACTION_STORE_ON_STOP 1
-#define ACTION_STOP_ON_STOP  2
+#define ACTION_STORE_ON_STOP		(1<<0)
+#define ACTION_STOP_ON_STOP		(1<<1)
+#define ACTION_RELOADVCPU_ON_STOP	(1<<2)
 
 struct kvm_s390_local_interrupt {
 	spinlock_t lock;

index 98997cc..0732ab4 100644
@@ -128,7 +128,7 @@ static int handle_noop(struct kvm_vcpu *vcpu)
 
 static int handle_stop(struct kvm_vcpu *vcpu)
 {
-	int rc;
+	int rc = 0;
 
 	vcpu->stat.exit_stop_request++;
 	atomic_clear_mask(CPUSTAT_RUNNING, &vcpu->arch.sie_block->cpuflags);

@@ -141,12 +141,18 @@ static int handle_stop(struct kvm_vcpu *vcpu)
 			rc = -ENOTSUPP;
 	}
 
+	if (vcpu->arch.local_int.action_bits & ACTION_RELOADVCPU_ON_STOP) {
+		vcpu->arch.local_int.action_bits &= ~ACTION_RELOADVCPU_ON_STOP;
+		rc = SIE_INTERCEPT_RERUNVCPU;
+		vcpu->run->exit_reason = KVM_EXIT_INTR;
+	}
+
 	if (vcpu->arch.local_int.action_bits & ACTION_STOP_ON_STOP) {
 		vcpu->arch.local_int.action_bits &= ~ACTION_STOP_ON_STOP;
 		VCPU_EVENT(vcpu, 3, "%s", "cpu stopped");
 		rc = -ENOTSUPP;
-	} else
-		rc = 0;
+	}
+
 	spin_unlock_bh(&vcpu->arch.local_int.lock);
 	return rc;
 }

index 90d9d1b..1d65f62 100644
@@ -490,6 +490,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	vcpu_load(vcpu);
 
+rerun_vcpu:
 	/* verify, that memory has been registered */
 	if (!vcpu->kvm->arch.guest_memsize) {
 		vcpu_put(vcpu);

@@ -509,6 +510,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		vcpu->arch.sie_block->gpsw.addr = kvm_run->s390_sieic.addr;
 		break;
 	case KVM_EXIT_UNKNOWN:
+	case KVM_EXIT_INTR:
 	case KVM_EXIT_S390_RESET:
 		break;
 	default:

@@ -522,6 +524,9 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		rc = kvm_handle_sie_intercept(vcpu);
 	} while (!signal_pending(current) && !rc);
 
+	if (rc == SIE_INTERCEPT_RERUNVCPU)
+		goto rerun_vcpu;
+
 	if (signal_pending(current) && !rc)
 		rc = -EINTR;
 

index 748fee8..2072cd4 100644
@@ -20,6 +20,8 @@
 
 typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
 
+/* negativ values are error codes, positive values for internal conditions */
+#define SIE_INTERCEPT_RERUNVCPU		(1<<0)
 int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu);
 
 #define VM_EVENT(d_kvm, d_loglevel, d_string, d_args...)\

@@ -50,6 +52,7 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 		struct kvm_s390_interrupt *s390int);
 int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
+int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
 
 /* implemented in priv.c */
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);

104 lines not on this page · raw message

index 1d65f62..5c1c302 100644
@@ -527,8 +527,10 @@ rerun_vcpu:
 	if (rc == SIE_INTERCEPT_RERUNVCPU)
 		goto rerun_vcpu;
 
-	if (signal_pending(current) && !rc)
+	if (signal_pending(current) && !rc) {
+		kvm_run->exit_reason = KVM_EXIT_INTR;
 		rc = -EINTR;
+	}
 
 	if (rc == -ENOTSUPP) {
 		/* intercept cannot be handled in-kernel, prepare kvm-run */

index 0a784f6..75535d4 100644
@@ -1,7 +1,7 @@
 /*
  * asm-s390/kvm_host.h - definition for kernel virtual machines on s390
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)

@@ -228,8 +228,6 @@ struct kvm_vm_stat {
 };
 
 struct kvm_arch{
-	unsigned long guest_origin;
-	unsigned long guest_memsize;
 	struct sca_block *sca;
 	debug_info_t *dbf;
 	struct kvm_s390_float_interrupt float_int;

index ed60f3a..03c716a 100644
@@ -1,7 +1,7 @@
 /*
  * gaccess.h -  access guest memory
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)

@@ -16,13 +16,14 @@
 #include <linux/compiler.h>
 #include <linux/kvm_host.h>
 #include <asm/uaccess.h>
+#include "kvm-s390.h"
 
 static inline void __user *__guestaddr_to_user(struct kvm_vcpu *vcpu,
 					       unsigned long guestaddr)
 {
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	unsigned long origin  = vcpu->kvm->arch.guest_origin;
-	unsigned long memsize = vcpu->kvm->arch.guest_memsize;
+	unsigned long origin  = vcpu->arch.sie_block->gmsor;
+	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if (guestaddr < 2 * PAGE_SIZE)
 		guestaddr += prefix;

@@ -158,8 +159,8 @@ static inline int copy_to_guest(struct kvm_vcpu *vcpu, unsigned long guestdest,
 				const void *from, unsigned long n)
 {
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	unsigned long origin  = vcpu->kvm->arch.guest_origin;
-	unsigned long memsize = vcpu->kvm->arch.guest_memsize;
+	unsigned long origin  = vcpu->arch.sie_block->gmsor;
+	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if ((guestdest < 2 * PAGE_SIZE) && (guestdest + n > 2 * PAGE_SIZE))
 		goto slowpath;

@@ -209,8 +210,8 @@ static inline int copy_from_guest(struct kvm_vcpu *vcpu, void *to,
 				  unsigned long guestsrc, unsigned long n)
 {
 	unsigned long prefix  = vcpu->arch.sie_block->prefix;
-	unsigned long origin  = vcpu->kvm->arch.guest_origin;
-	unsigned long memsize = vcpu->kvm->arch.guest_memsize;
+	unsigned long origin  = vcpu->arch.sie_block->gmsor;
+	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if ((guestsrc < 2 * PAGE_SIZE) && (guestsrc + n > 2 * PAGE_SIZE))
 		goto slowpath;

@@ -244,8 +245,8 @@ static inline int copy_to_guest_absolute(struct kvm_vcpu *vcpu,
 					 unsigned long guestdest,
 					 const void *from, unsigned long n)
 {
-	unsigned long origin  = vcpu->kvm->arch.guest_origin;
-	unsigned long memsize = vcpu->kvm->arch.guest_memsize;
+	unsigned long origin  = vcpu->arch.sie_block->gmsor;
+	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if (guestdest + n > memsize)
 		return -EFAULT;

@@ -262,8 +263,8 @@ static inline int copy_from_guest_absolute(struct kvm_vcpu *vcpu, void *to,
 					   unsigned long guestsrc,
 					   unsigned long n)
 {
-	unsigned long origin  = vcpu->kvm->arch.guest_origin;
-	unsigned long memsize = vcpu->kvm->arch.guest_memsize;
+	unsigned long origin  = vcpu->arch.sie_block->gmsor;
+	unsigned long memsize = kvm_s390_vcpu_get_memsize(vcpu);
 
 	if (guestsrc + n > memsize)
 		return -EFAULT;

index 0732ab4..ba9d8a7 100644
@@ -1,7 +1,7 @@
 /*
  * intercept.c - in-kernel handling for sie intercepts
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)

@@ -164,9 +164,9 @@ static int handle_validity(struct kvm_vcpu *vcpu)
 
 	vcpu->stat.exit_validity++;
 	if ((viwhy == 0x37) && (vcpu->arch.sie_block->prefix
-		<= vcpu->kvm->arch.guest_memsize - 2*PAGE_SIZE)){
+		<= kvm_s390_vcpu_get_memsize(vcpu) - 2*PAGE_SIZE)) {
 		rc = fault_in_pages_writeable((char __user *)
-			 vcpu->kvm->arch.guest_origin +
+			 vcpu->arch.sie_block->gmsor +
 			 vcpu->arch.sie_block->prefix,
 			 2*PAGE_SIZE);
 		if (rc)

97 lines not on this page · raw message

index 2072cd4..ec5eee7 100644
@@ -1,7 +1,7 @@
 /*
  * kvm_s390.h -  definition for kvm on s390
  *
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)

@@ -9,6 +9,7 @@
  *
  *    Author(s): Carsten Otte <[email protected]>
  *               Christian Borntraeger <[email protected]>
+ *               Christian Ehrhardt <[email protected]>
  */
 
 #ifndef ARCH_S390_KVM_S390_H

@@ -18,6 +19,9 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 
+/* The current code can have up to 256 pages for virtio */
+#define VIRTIODESCSPACE (256ul * 4096ul)
+
 typedef int (*intercept_handler_t)(struct kvm_vcpu *vcpu);
 
 /* negativ values are error codes, positive values for internal conditions */

@@ -54,6 +58,29 @@ int kvm_s390_inject_vcpu(struct kvm_vcpu *vcpu,
 int kvm_s390_inject_program_int(struct kvm_vcpu *vcpu, u16 code);
 int kvm_s390_inject_sigp_stop(struct kvm_vcpu *vcpu, int action);
 
+static inline int kvm_s390_vcpu_get_memsize(struct kvm_vcpu *vcpu)
+{
+	return vcpu->arch.sie_block->gmslm
+		- vcpu->arch.sie_block->gmsor
+		- VIRTIODESCSPACE + 1ul;
+}
+
+static inline void kvm_s390_vcpu_set_mem(struct kvm_vcpu *vcpu)
+{
+	struct kvm_memory_slot *mem;
+
+	down_read(&vcpu->kvm->slots_lock);
+	mem = &vcpu->kvm->memslots[0];
+
+	vcpu->arch.sie_block->gmsor = mem->userspace_addr;
+	vcpu->arch.sie_block->gmslm =
+		mem->userspace_addr +
+		(mem->npages << PAGE_SHIFT) +
+		VIRTIODESCSPACE - 1ul;
+
+	up_read(&vcpu->kvm->slots_lock);
+}
+
 /* implemented in priv.c */
 int kvm_s390_handle_b2(struct kvm_vcpu *vcpu);
 

index 21897b0..40c8c67 100644
@@ -189,9 +189,9 @@ static int __sigp_set_prefix(struct kvm_vcpu *vcpu, u16 cpu_addr, u32 address,
 	/* make sure that the new value is valid memory */
 	address = address & 0x7fffe000u;
 	if ((copy_from_guest(vcpu, &tmp,
-		(u64) (address + vcpu->kvm->arch.guest_origin) , 1)) ||
+		(u64) (address + vcpu->arch.sie_block->gmsor) , 1)) ||
 	   (copy_from_guest(vcpu, &tmp, (u64) (address +
-			vcpu->kvm->arch.guest_origin + PAGE_SIZE), 1))) {
+			vcpu->arch.sie_block->gmsor + PAGE_SIZE), 1))) {
 		*reg |= SIGP_STAT_INVALID_PARAMETER;
 		return 1; /* invalid parameter */
 	}

index 65df6f5..632a856 100644
@@ -676,7 +676,7 @@ struct kvm_assigned_msix_nr {
 	__u16 padding;
 };
 
-#define KVM_MAX_MSIX_PER_DEV		512
+#define KVM_MAX_MSIX_PER_DEV		256
 struct kvm_assigned_msix_entry {
 	__u32 assigned_dev_id;
 	__u32 gsi;

index ed66e4c..39fddc0 100644
@@ -27,6 +27,9 @@ struct vcpu_svm {
 	unsigned long vmcb_pa;
 	struct svm_cpu_data *svm_data;
 	uint64_t asid_generation;
+	uint64_t sysenter_cs;
+	uint64_t sysenter_esp;
+	uint64_t sysenter_eip;
 
 	u64 next_rip;
 

index 48b22c9..df6e7fb 100644
@@ -1978,13 +1978,13 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
 		break;
 #endif
 	case MSR_IA32_SYSENTER_CS:
-		*data = svm->vmcb->save.sysenter_cs;
+		*data = svm->sysenter_cs;
 		break;
 	case MSR_IA32_SYSENTER_EIP:
-		*data = svm->vmcb->save.sysenter_eip;
+		*data = svm->sysenter_eip;
 		break;
 	case MSR_IA32_SYSENTER_ESP:
-		*data = svm->vmcb->save.sysenter_esp;
+		*data = svm->sysenter_esp;
 		break;
 	/* Nobody will change the following 5 values in the VMCB so
 	   we can safely return them on rdmsr. They will always be 0

@@ -2068,13 +2068,13 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 		break;
 #endif
 	case MSR_IA32_SYSENTER_CS:
-		svm->vmcb->save.sysenter_cs = data;
+		svm->sysenter_cs = data;
 		break;
 	case MSR_IA32_SYSENTER_EIP:
-		svm->vmcb->save.sysenter_eip = data;
+		svm->sysenter_eip = data;
 		break;
 	case MSR_IA32_SYSENTER_ESP:
-		svm->vmcb->save.sysenter_esp = data;
+		svm->sysenter_esp = data;
 		break;
 	case MSR_IA32_DEBUGCTLMSR:
 		if (!svm_has(SVM_FEATURE_LBRV)) {

index dee321e..2d9bc43 100644
@@ -120,7 +120,7 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
 {
 	struct kvm_assigned_dev_kernel *assigned_dev;
 	struct kvm *kvm;
-	int irq, i;
+	int i;
 
 	assigned_dev = container_of(work, struct kvm_assigned_dev_kernel,
 				    interrupt_work);

@@ -143,20 +143,10 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
 			kvm_set_irq(assigned_dev->kvm,
 				    assigned_dev->irq_source_id,
 				    guest_entries[i].vector, 1);
-			irq = assigned_dev->host_msix_entries[i].vector;
-			if (irq != 0)
-				enable_irq(irq);
-			assigned_dev->host_irq_disabled = false;
 		}
-	} else {
+	} else
 		kvm_set_irq(assigned_dev->kvm, assigned_dev->irq_source_id,
 			    assigned_dev->guest_irq, 1);
-		if (assigned_dev->irq_requested_type &
-				KVM_DEV_IRQ_GUEST_MSI) {
-			enable_irq(assigned_dev->host_irq);
-			assigned_dev->host_irq_disabled = false;
-		}
-	}
 
 	spin_unlock_irq(&assigned_dev->assigned_dev_lock);
 	mutex_unlock(&assigned_dev->kvm->lock);

@@ -179,8 +169,10 @@ static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)
 
 	schedule_work(&assigned_dev->interrupt_work);
 
-	disable_irq_nosync(irq);
-	assigned_dev->host_irq_disabled = true;
+	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_GUEST_INTX) {
+		disable_irq_nosync(irq);
+		assigned_dev->host_irq_disabled = true;
+	}
 
 out:
 	spin_unlock_irqrestore(&assigned_dev->assigned_dev_lock, flags);

@@ -417,6 +409,7 @@ static int assigned_device_enable_guest_msi(struct kvm *kvm,
 {
 	dev->guest_irq = irq->guest_irq;
 	dev->ack_notifier.gsi = -1;
+	dev->host_irq_disabled = false;
 	return 0;
 }
 #endif

@@ -427,6 +420,7 @@ static int assigned_device_enable_guest_msix(struct kvm *kvm,
 {
 	dev->guest_irq = irq->guest_irq;
 	dev->ack_notifier.gsi = -1;
+	dev->host_irq_disabled = false;
 	return 0;
 }
 #endif

index 7724dcb..19240fe 100644
@@ -249,8 +249,6 @@ long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg);
-void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
-void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
 
 int kvm_dev_ioctl_check_extension(long ext);
 

deleted file mode 100644
index 39fddc0..0000000
@@ -1,54 +0,0 @@
-#ifndef __KVM_SVM_H
-#define __KVM_SVM_H
-
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/kvm_host.h>
-#include <asm/msr.h>
-
-#include <asm/svm.h>
-
-static const u32 host_save_user_msrs[] = {
-#ifdef CONFIG_X86_64
-	MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE,
-	MSR_FS_BASE,
-#endif
-	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
-};
-
-#define NR_HOST_SAVE_USER_MSRS ARRAY_SIZE(host_save_user_msrs)
-
-struct kvm_vcpu;
-
-struct vcpu_svm {
-	struct kvm_vcpu vcpu;
-	struct vmcb *vmcb;
-	unsigned long vmcb_pa;
-	struct svm_cpu_data *svm_data;
-	uint64_t asid_generation;
-	uint64_t sysenter_cs;
-	uint64_t sysenter_esp;
-	uint64_t sysenter_eip;
-
-	u64 next_rip;
-
-	u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS];
-	u64 host_gs_base;
-	unsigned long host_cr2;
-
-	u32 *msrpm;
-	struct vmcb *hsave;
-	u64 hsave_msr;
-
-	u64 nested_vmcb;
-
-	/* These are the merged vectors */
-	u32 *nested_msrpm;
-
-	/* gpa pointers to the real vectors */
-	u64 nested_vmcb_msrpm;
-};
-
-#endif
-

54 lines not on this page · raw message

index 0cef809..f4d1b55 100644
@@ -138,7 +138,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu_44x);
 }
 
-static int kvmppc_44x_init(void)
+static int __init kvmppc_44x_init(void)
 {
 	int r;
 

@@ -149,7 +149,7 @@ static int kvmppc_44x_init(void)
 	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_44x), THIS_MODULE);
 }
 
-static void kvmppc_44x_exit(void)
+static void __exit kvmppc_44x_exit(void)
 {
 	kvmppc_booke_exit();
 }

index 642e420..e7bf4d0 100644
@@ -520,7 +520,7 @@ int kvm_arch_vcpu_ioctl_translate(struct kvm_vcpu *vcpu,
 	return kvmppc_core_vcpu_translate(vcpu, tr);
 }
 
-int kvmppc_booke_init(void)
+int __init kvmppc_booke_init(void)
 {
 	unsigned long ivor[16];
 	unsigned long max_ivor = 0;

index d8067fd..674e796 100644
@@ -132,7 +132,7 @@ void kvmppc_core_vcpu_free(struct kvm_vcpu *vcpu)
 	kmem_cache_free(kvm_vcpu_cache, vcpu_e500);
 }
 
-static int kvmppc_e500_init(void)
+static int __init kvmppc_e500_init(void)
 {
 	int r, i;
 	unsigned long ivor[3];

@@ -160,7 +160,7 @@ static int kvmppc_e500_init(void)
 	return kvm_init(NULL, sizeof(struct kvmppc_vcpu_e500), THIS_MODULE);
 }
 
-static void kvmppc_e500_exit(void)
+static void __init kvmppc_e500_exit(void)
 {
 	kvmppc_booke_exit();
 }

index 5ae620d..03ea280 100644
@@ -80,7 +80,10 @@ static void coalesced_mmio_write(struct kvm_io_device *this,
 
 static void coalesced_mmio_destructor(struct kvm_io_device *this)
 {
-	kfree(this);
+	struct kvm_coalesced_mmio_dev *dev =
+		(struct kvm_coalesced_mmio_dev *)this->private;
+
+	kfree(dev);
 }
 
 int kvm_coalesced_mmio_init(struct kvm *kvm)

index 0990bc9..e800d2d 100644
@@ -350,10 +350,20 @@ void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val)
 	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 }
 
+static inline struct kvm_pit *dev_to_pit(struct kvm_io_device *dev)
+{
+	return container_of(dev, struct kvm_pit, dev);
+}
+
+static inline struct kvm_pit *speaker_to_pit(struct kvm_io_device *dev)
+{
+	return container_of(dev, struct kvm_pit, speaker_dev);
+}
+
 static void pit_ioport_write(struct kvm_io_device *this,
 			     gpa_t addr, int len, const void *data)
 {
-	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	struct kvm_pit *pit = dev_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	int channel, access;

@@ -426,7 +436,7 @@ static void pit_ioport_write(struct kvm_io_device *this,
 static void pit_ioport_read(struct kvm_io_device *this,
 			    gpa_t addr, int len, void *data)
 {
-	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	struct kvm_pit *pit = dev_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	int ret, count;

@@ -497,7 +507,7 @@ static int pit_in_range(struct kvm_io_device *this, gpa_t addr,
 static void speaker_ioport_write(struct kvm_io_device *this,
 				 gpa_t addr, int len, const void *data)
 {
-	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	struct kvm_pit *pit = speaker_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	u32 val = *(u32 *) data;

@@ -511,7 +521,7 @@ static void speaker_ioport_write(struct kvm_io_device *this,
 static void speaker_ioport_read(struct kvm_io_device *this,
 				gpa_t addr, int len, void *data)
 {
-	struct kvm_pit *pit = (struct kvm_pit *)this->private;
+	struct kvm_pit *pit = speaker_to_pit(this);
 	struct kvm_kpit_state *pit_state = &pit->pit_state;
 	struct kvm *kvm = pit->kvm;
 	unsigned int refresh_clock;

@@ -563,6 +573,18 @@ static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
 	}
 }
 
+static const struct kvm_io_device_ops pit_dev_ops = {
+	.read     = pit_ioport_read,
+	.write    = pit_ioport_write,
+	.in_range = pit_in_range,
+};
+
+static const struct kvm_io_device_ops speaker_dev_ops = {
+	.read     = speaker_ioport_read,
+	.write    = speaker_ioport_write,
+	.in_range = speaker_in_range,
+};
+
 struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 {
 	struct kvm_pit *pit;

@@ -583,17 +605,11 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 	spin_lock_init(&pit->pit_state.inject_lock);
 
 	/* Initialize PIO device */
-	pit->dev.read = pit_ioport_read;
-	pit->dev.write = pit_ioport_write;
-	pit->dev.in_range = pit_in_range;
-	pit->dev.private = pit;
+	kvm_iodevice_init(&pit->dev, &pit_dev_ops);
 	kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev);
 
 	if (flags & KVM_PIT_SPEAKER_DUMMY) {
-		pit->speaker_dev.read = speaker_ioport_read;
-		pit->speaker_dev.write = speaker_ioport_write;
-		pit->speaker_dev.in_range = speaker_in_range;
-		pit->speaker_dev.private = pit;
+		kvm_iodevice_init(&pit->speaker_dev, &speaker_dev_ops);
 		kvm_io_bus_register_dev(&kvm->pio_bus, &pit->speaker_dev);
 	}
 

index 1ccb50c..2520922 100644
@@ -444,10 +444,15 @@ static int picdev_in_range(struct kvm_io_device *this, gpa_t addr,
 	}
 }
 
+static inline struct kvm_pic *to_pic(struct kvm_io_device *dev)
+{
+	return container_of(dev, struct kvm_pic, dev);
+}
+
 static void picdev_write(struct kvm_io_device *this,
 			 gpa_t addr, int len, const void *val)
 {
-	struct kvm_pic *s = this->private;
+	struct kvm_pic *s = to_pic(this);
 	unsigned char data = *(unsigned char *)val;
 
 	if (len != 1) {

@@ -474,7 +479,7 @@ static void picdev_write(struct kvm_io_device *this,
 static void picdev_read(struct kvm_io_device *this,
 			gpa_t addr, int len, void *val)
 {
-	struct kvm_pic *s = this->private;
+	struct kvm_pic *s = to_pic(this);
 	unsigned char data = 0;
 
 	if (len != 1) {

@@ -516,6 +521,12 @@ static void pic_irq_request(void *opaque, int level)
 	}
 }
 
+static const struct kvm_io_device_ops picdev_ops = {
+	.read     = picdev_read,
+	.write    = picdev_write,
+	.in_range = picdev_in_range,
+};
+
 struct kvm_pic *kvm_create_pic(struct kvm *kvm)
 {
 	struct kvm_pic *s;

@@ -534,10 +545,7 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm)
 	/*
 	 * Initialize PIO device
 	 */
-	s->dev.read = picdev_read;
-	s->dev.write = picdev_write;
-	s->dev.in_range = picdev_in_range;
-	s->dev.private = s;
+	kvm_iodevice_init(&s->dev, &picdev_ops);
 	kvm_io_bus_register_dev(&kvm->pio_bus, &s->dev);
 	return s;
 }

index ae99d83..4bfd458 100644
@@ -522,10 +522,15 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset)
 	return val;
 }
 
+static inline struct kvm_lapic *to_lapic(struct kvm_io_device *dev)
+{
+	return container_of(dev, struct kvm_lapic, dev);
+}
+
 static void apic_mmio_read(struct kvm_io_device *this,
 			   gpa_t address, int len, void *data)
 {
-	struct kvm_lapic *apic = (struct kvm_lapic *)this->private;
+	struct kvm_lapic *apic = to_lapic(this);
 	unsigned int offset = address - apic->base_address;
 	unsigned char alignment = offset & 0xf;
 	u32 result;

@@ -606,7 +611,7 @@ static void apic_manage_nmi_watchdog(struct kvm_lapic *apic, u32 lvt0_val)
 static void apic_mmio_write(struct kvm_io_device *this,
 			    gpa_t address, int len, const void *data)
 {
-	struct kvm_lapic *apic = (struct kvm_lapic *)this->private;
+	struct kvm_lapic *apic = to_lapic(this);
 	unsigned int offset = address - apic->base_address;
 	unsigned char alignment = offset & 0xf;
 	u32 val;

@@ -723,7 +728,7 @@ static void apic_mmio_write(struct kvm_io_device *this,
 static int apic_mmio_range(struct kvm_io_device *this, gpa_t addr,
 			   int len, int size)
 {
-	struct kvm_lapic *apic = (struct kvm_lapic *)this->private;
+	struct kvm_lapic *apic = to_lapic(this);
 	int ret = 0;
 
 

@@ -917,6 +922,12 @@ static struct kvm_timer_ops lapic_timer_ops = {
 	.is_periodic = lapic_is_periodic,
 };
 
+static const struct kvm_io_device_ops apic_mmio_ops = {
+	.read     = apic_mmio_read,
+	.write    = apic_mmio_write,
+	.in_range = apic_mmio_range,
+};
+
 int kvm_create_lapic(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic;

@@ -951,10 +962,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
 	vcpu->arch.apic_base = APIC_DEFAULT_PHYS_BASE;
 
 	kvm_lapic_reset(vcpu);
-	apic->dev.read = apic_mmio_read;
-	apic->dev.write = apic_mmio_write;
-	apic->dev.in_range = apic_mmio_range;
-	apic->dev.private = apic;
+	kvm_iodevice_init(&apic->dev, &apic_mmio_ops);
 
 	return 0;
 nomem_free_apic:

index 5eb3b8d..75e9df0 100644
@@ -2264,7 +2264,7 @@ static struct kvm_io_device *vcpu_find_pervcpu_dev(struct kvm_vcpu *vcpu,
 
 	if (vcpu->arch.apic) {
 		dev = &vcpu->arch.apic->dev;
-		if (dev->in_range(dev, addr, len, is_write))
+		if (kvm_iodevice_in_range(dev, addr, len, is_write))
 			return dev;
 	}
 	return NULL;

index 03ea280..c4c7ec2 100644
@@ -14,11 +14,15 @@
 
 #include "coalesced_mmio.h"
 
+static inline struct kvm_coalesced_mmio_dev *to_mmio(struct kvm_io_device *dev)
+{
+	return container_of(dev, struct kvm_coalesced_mmio_dev, dev);
+}
+
 static int coalesced_mmio_in_range(struct kvm_io_device *this,
 				   gpa_t addr, int len, int is_write)
 {
-	struct kvm_coalesced_mmio_dev *dev =
-				(struct kvm_coalesced_mmio_dev*)this->private;
+	struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
 	struct kvm_coalesced_mmio_zone *zone;
 	int next;
 	int i;

@@ -63,8 +67,7 @@ static int coalesced_mmio_in_range(struct kvm_io_device *this,
 static void coalesced_mmio_write(struct kvm_io_device *this,
 				 gpa_t addr, int len, const void *val)
 {
-	struct kvm_coalesced_mmio_dev *dev =
-				(struct kvm_coalesced_mmio_dev*)this->private;
+	struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
 	struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring;
 
 	/* kvm->lock must be taken by caller before call to in_range()*/

@@ -80,12 +83,17 @@ static void coalesced_mmio_write(struct kvm_io_device *this,
 
 static void coalesced_mmio_destructor(struct kvm_io_device *this)
 {
-	struct kvm_coalesced_mmio_dev *dev =
-		(struct kvm_coalesced_mmio_dev *)this->private;
+	struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
 
 	kfree(dev);
 }
 
+static const struct kvm_io_device_ops coalesced_mmio_ops = {
+	.write      = coalesced_mmio_write,
+	.in_range   = coalesced_mmio_in_range,
+	.destructor = coalesced_mmio_destructor,
+};
+
 int kvm_coalesced_mmio_init(struct kvm *kvm)
 {
 	struct kvm_coalesced_mmio_dev *dev;

@@ -93,10 +101,7 @@ int kvm_coalesced_mmio_init(struct kvm *kvm)
 	dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;
-	dev->dev.write  = coalesced_mmio_write;
-	dev->dev.in_range  = coalesced_mmio_in_range;
-	dev->dev.destructor  = coalesced_mmio_destructor;
-	dev->dev.private  = dev;
+	kvm_iodevice_init(&dev->dev, &coalesced_mmio_ops);
 	dev->kvm = kvm;
 	kvm->coalesced_mmio_dev = dev;
 	kvm_io_bus_register_dev(&kvm->mmio_bus, &dev->dev);

index 1150c6d..469b9fa 100644
@@ -220,10 +220,15 @@ void kvm_ioapic_update_eoi(struct kvm *kvm, int vector, int trigger_mode)
 			__kvm_ioapic_update_eoi(ioapic, i, trigger_mode);
 }
 
+static inline struct kvm_ioapic *to_ioapic(struct kvm_io_device *dev)
+{
+	return container_of(dev, struct kvm_ioapic, dev);
+}
+
 static int ioapic_in_range(struct kvm_io_device *this, gpa_t addr,
 			   int len, int is_write)
 {
-	struct kvm_ioapic *ioapic = (struct kvm_ioapic *)this->private;
+	struct kvm_ioapic *ioapic = to_ioapic(this);
 
 	return ((addr >= ioapic->base_address &&
 		 (addr < ioapic->base_address + IOAPIC_MEM_LENGTH)));

@@ -232,7 +237,7 @@ static int ioapic_in_range(struct kvm_io_device *this, gpa_t addr,
 static void ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
 			     void *val)
 {
-	struct kvm_ioapic *ioapic = (struct kvm_ioapic *)this->private;
+	struct kvm_ioapic *ioapic = to_ioapic(this);
 	u32 result;
 
 	ioapic_debug("addr %lx\n", (unsigned long)addr);

@@ -269,7 +274,7 @@ static void ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
 static void ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
 			      const void *val)
 {
-	struct kvm_ioapic *ioapic = (struct kvm_ioapic *)this->private;
+	struct kvm_ioapic *ioapic = to_ioapic(this);
 	u32 data;
 
 	ioapic_debug("ioapic_mmio_write addr=%p len=%d val=%p\n",

@@ -314,6 +319,12 @@ void kvm_ioapic_reset(struct kvm_ioapic *ioapic)
 	ioapic->id = 0;
 }
 
+static const struct kvm_io_device_ops ioapic_mmio_ops = {
+	.read     = ioapic_mmio_read,
+	.write    = ioapic_mmio_write,
+	.in_range = ioapic_in_range,
+};
+
 int kvm_ioapic_init(struct kvm *kvm)
 {
 	struct kvm_ioapic *ioapic;

@@ -323,10 +334,7 @@ int kvm_ioapic_init(struct kvm *kvm)
 		return -ENOMEM;
 	kvm->arch.vioapic = ioapic;
 	kvm_ioapic_reset(ioapic);
-	ioapic->dev.read = ioapic_mmio_read;
-	ioapic->dev.write = ioapic_mmio_write;
-	ioapic->dev.in_range = ioapic_in_range;
-	ioapic->dev.private = ioapic;
+	kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
 	ioapic->kvm = kvm;
 	kvm_io_bus_register_dev(&kvm->mmio_bus, &ioapic->dev);
 	return 0;

index 55e8846..2c67f5a 100644
@@ -18,7 +18,9 @@
 
 #include <linux/kvm_types.h>
 
-struct kvm_io_device {
+struct kvm_io_device;
+
+struct kvm_io_device_ops {
 	void (*read)(struct kvm_io_device *this,
 		     gpa_t addr,
 		     int len,

@@ -30,16 +32,25 @@ struct kvm_io_device {
 	int (*in_range)(struct kvm_io_device *this, gpa_t addr, int len,
 			int is_write);
 	void (*destructor)(struct kvm_io_device *this);
+};
+
 
-	void             *private;
+struct kvm_io_device {
+	const struct kvm_io_device_ops *ops;
 };
 
+static inline void kvm_iodevice_init(struct kvm_io_device *dev,
+				     const struct kvm_io_device_ops *ops)
+{
+	dev->ops = ops;
+}
+
 static inline void kvm_iodevice_read(struct kvm_io_device *dev,
 				     gpa_t addr,
 				     int len,
 				     void *val)
 {
-	dev->read(dev, addr, len, val);
+	dev->ops->read(dev, addr, len, val);
 }
 
 static inline void kvm_iodevice_write(struct kvm_io_device *dev,

@@ -47,19 +58,19 @@ static inline void kvm_iodevice_write(struct kvm_io_device *dev,
 				      int len,
 				      const void *val)
 {
-	dev->write(dev, addr, len, val);
+	dev->ops->write(dev, addr, len, val);
 }
 
-static inline int kvm_iodevice_inrange(struct kvm_io_device *dev,
-				       gpa_t addr, int len, int is_write)
+static inline int kvm_iodevice_in_range(struct kvm_io_device *dev,
+					gpa_t addr, int len, int is_write)
 {
-	return dev->in_range(dev, addr, len, is_write);
+	return dev->ops->in_range(dev, addr, len, is_write);
 }
 
 static inline void kvm_iodevice_destructor(struct kvm_io_device *dev)
 {
-	if (dev->destructor)
-		dev->destructor(dev);
+	if (dev->ops->destructor)
+		dev->ops->destructor(dev);
 }
 
 #endif /* __KVM_IODEV_H__ */

index 2d9bc43..d1f9c87 100644
@@ -2463,7 +2463,7 @@ struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus,
 	for (i = 0; i < bus->dev_count; i++) {
 		struct kvm_io_device *pos = bus->devs[i];
 
-		if (pos->in_range(pos, addr, len, is_write))
+		if (kvm_iodevice_in_range(pos, addr, len, is_write))
 			return pos;
 	}
 

index e800d2d..977af7a 100644
@@ -604,15 +604,6 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 	mutex_lock(&pit->pit_state.lock);
 	spin_lock_init(&pit->pit_state.inject_lock);
 
-	/* Initialize PIO device */
-	kvm_iodevice_init(&pit->dev, &pit_dev_ops);
-	kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev);
-
-	if (flags & KVM_PIT_SPEAKER_DUMMY) {
-		kvm_iodevice_init(&pit->speaker_dev, &speaker_dev_ops);
-		kvm_io_bus_register_dev(&kvm->pio_bus, &pit->speaker_dev);
-	}
-
 	kvm->arch.vpit = pit;
 	pit->kvm = kvm;
 

@@ -631,6 +622,14 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 	pit->mask_notifier.func = pit_mask_notifer;
 	kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
 
+	kvm_iodevice_init(&pit->dev, &pit_dev_ops);
+	kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev);
+
+	if (flags & KVM_PIT_SPEAKER_DUMMY) {
+		kvm_iodevice_init(&pit->speaker_dev, &speaker_dev_ops);
+		kvm_io_bus_register_dev(&kvm->pio_bus, &pit->speaker_dev);
+	}
+
 	return pit;
 }
 

index c14bffc..ea0e1d5 100644
@@ -1651,7 +1651,6 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	if (enable_ept) {
 		eptp = construct_eptp(cr3);
 		vmcs_write64(EPT_POINTER, eptp);
-		ept_sync_context(eptp);
 		ept_load_pdptrs(vcpu);
 		guest_cr3 = is_paging(vcpu) ? vcpu->arch.cr3 :
 			VMX_EPT_IDENTITY_PAGETABLE_ADDR;

index ea0e1d5..752465f 100644
@@ -1547,10 +1547,6 @@ static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
 {
 	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-		if (!load_pdptrs(vcpu, vcpu->arch.cr3)) {
-			printk(KERN_ERR "EPT: Fail to load pdptrs!\n");
-			return;
-		}
 		vmcs_write64(GUEST_PDPTR0, vcpu->arch.pdptrs[0]);
 		vmcs_write64(GUEST_PDPTR1, vcpu->arch.pdptrs[1]);
 		vmcs_write64(GUEST_PDPTR2, vcpu->arch.pdptrs[2]);

@@ -1558,6 +1554,16 @@ static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
 	}
 }
 
+static void ept_save_pdptrs(struct kvm_vcpu *vcpu)
+{
+	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
+		vcpu->arch.pdptrs[0] = vmcs_read64(GUEST_PDPTR0);
+		vcpu->arch.pdptrs[1] = vmcs_read64(GUEST_PDPTR1);
+		vcpu->arch.pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
+		vcpu->arch.pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
+	}
+}
+
 static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);
 
 static void ept_update_paging_mode_cr0(unsigned long *hw_cr0,

@@ -1651,7 +1657,6 @@ static void vmx_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	if (enable_ept) {
 		eptp = construct_eptp(cr3);
 		vmcs_write64(EPT_POINTER, eptp);
-		ept_load_pdptrs(vcpu);
 		guest_cr3 = is_paging(vcpu) ? vcpu->arch.cr3 :
 			VMX_EPT_IDENTITY_PAGETABLE_ADDR;
 	}

@@ -3252,7 +3257,7 @@ static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	 * to sync with guest real CR3. */
 	if (enable_ept && is_paging(vcpu)) {
 		vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
-		ept_load_pdptrs(vcpu);
+		ept_save_pdptrs(vcpu);
 	}
 
 	if (unlikely(vmx->fail)) {

@@ -3437,6 +3442,10 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	if (enable_ept && is_paging(vcpu)) {
+		vmcs_writel(GUEST_CR3, vcpu->arch.cr3);
+		ept_load_pdptrs(vcpu);
+	}
 	/* Record the guest's net vcpu time for enforced NMI injections. */
 	if (unlikely(!cpu_has_virtual_nmis() && vmx->soft_vnmi_blocked))
 		vmx->entry_time = ktime_get();

index 81c68f6..1cc901e 100644
@@ -120,6 +120,10 @@ enum kvm_reg {
 	NR_VCPU_REGS
 };
 
+enum kvm_reg_ex {
+	VCPU_EXREG_PDPTR = NR_VCPU_REGS,
+};
+
 enum {
 	VCPU_SREG_ES,
 	VCPU_SREG_CS,

index 1ff819d..7bcc5b6 100644
@@ -29,4 +29,13 @@ static inline void kvm_rip_write(struct kvm_vcpu *vcpu, unsigned long val)
 	kvm_register_write(vcpu, VCPU_REGS_RIP, val);
 }
 
+static inline u64 kvm_pdptr_read(struct kvm_vcpu *vcpu, int index)
+{
+	if (!test_bit(VCPU_EXREG_PDPTR,
+		      (unsigned long *)&vcpu->arch.regs_avail))
+		kvm_x86_ops->cache_reg(vcpu, VCPU_EXREG_PDPTR);
+
+	return vcpu->arch.pdptrs[index];
+}
+
 #endif

index 0ef5bb2..8ee67e3 100644
@@ -18,6 +18,7 @@
  */
 
 #include "mmu.h"
+#include "kvm_cache_regs.h"
 
 #include <linux/kvm_host.h>
 #include <linux/types.h>

@@ -1954,6 +1955,7 @@ static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
 	gfn_t root_gfn;
 	struct kvm_mmu_page *sp;
 	int direct = 0;
+	u64 pdptr;
 
 	root_gfn = vcpu->arch.cr3 >> PAGE_SHIFT;
 

@@ -1981,11 +1983,12 @@ static int mmu_alloc_roots(struct kvm_vcpu *vcpu)
 
 		ASSERT(!VALID_PAGE(root));
 		if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) {
-			if (!is_present_pte(vcpu->arch.pdptrs[i])) {
+			pdptr = kvm_pdptr_read(vcpu, i);
+			if (!is_present_pte(pdptr)) {
 				vcpu->arch.mmu.pae_root[i] = 0;
 				continue;
 			}
-			root_gfn = vcpu->arch.pdptrs[i] >> PAGE_SHIFT;
+			root_gfn = pdptr >> PAGE_SHIFT;
 		} else if (vcpu->arch.mmu.root_level == 0)
 			root_gfn = 0;
 		if (mmu_check_root(vcpu, root_gfn))

index 67785f6..4cb1dbf 100644
@@ -131,7 +131,7 @@ walk:
 	pte = vcpu->arch.cr3;
 #if PTTYPE == 64
 	if (!is_long_mode(vcpu)) {
-		pte = vcpu->arch.pdptrs[(addr >> 30) & 3];
+		pte = kvm_pdptr_read(vcpu, (addr >> 30) & 3);
 		if (!is_present_pte(pte))
 			goto not_present;
 		--walker->level;

index 14a98ab..0710e45 100644
@@ -780,6 +780,18 @@ static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 	to_svm(vcpu)->vmcb->save.rflags = rflags;
 }
 
+static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
+{
+	switch (reg) {
+	case VCPU_EXREG_PDPTR:
+		BUG_ON(!npt_enabled);
+		load_pdptrs(vcpu, vcpu->arch.cr3);
+		break;
+	default:
+		BUG();
+	}
+}
+
 static void svm_set_vintr(struct vcpu_svm *svm)
 {
 	svm->vmcb->control.intercept |= 1ULL << INTERCEPT_VINTR;

@@ -2286,12 +2298,6 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		}
 		vcpu->arch.cr0 = svm->vmcb->save.cr0;
 		vcpu->arch.cr3 = svm->vmcb->save.cr3;
-		if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
-			if (!load_pdptrs(vcpu, vcpu->arch.cr3)) {
-				kvm_inject_gp(vcpu, 0);
-				return 1;
-			}
-		}
 		if (mmu_reload) {
 			kvm_mmu_reset_context(vcpu);
 			kvm_mmu_load(vcpu);

@@ -2642,6 +2648,11 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	svm->next_rip = 0;
 
+	if (npt_enabled) {
+		vcpu->arch.regs_avail &= ~(1 << VCPU_EXREG_PDPTR);
+		vcpu->arch.regs_dirty &= ~(1 << VCPU_EXREG_PDPTR);
+	}
+
 	svm_complete_interrupts(svm);
 }
 

@@ -2750,6 +2761,7 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.set_gdt = svm_set_gdt,
 	.get_dr = svm_get_dr,
 	.set_dr = svm_set_dr,
+	.cache_reg = svm_cache_reg,
 	.get_rflags = svm_get_rflags,
 	.set_rflags = svm_set_rflags,
 

index 752465f..d726dec 100644
@@ -161,6 +161,8 @@ static struct kvm_vmx_segment_field {
 	VMX_SEGMENT_FIELD(LDTR),
 };
 
+static void ept_save_pdptrs(struct kvm_vcpu *vcpu);
+
 /*
  * Keep MSR_K6_STAR at the end, as setup_msrs() will try to optimize it
  * away by decrementing the array size.

@@ -1047,6 +1049,10 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 	case VCPU_REGS_RIP:
 		vcpu->arch.regs[VCPU_REGS_RIP] = vmcs_readl(GUEST_RIP);
 		break;
+	case VCPU_EXREG_PDPTR:
+		if (enable_ept)
+			ept_save_pdptrs(vcpu);
+		break;
 	default:
 		break;
 	}

@@ -1546,6 +1552,10 @@ static void vmx_decache_cr4_guest_bits(struct kvm_vcpu *vcpu)
 
 static void ept_load_pdptrs(struct kvm_vcpu *vcpu)
 {
+	if (!test_bit(VCPU_EXREG_PDPTR,
+		      (unsigned long *)&vcpu->arch.regs_dirty))
+		return;
+
 	if (is_paging(vcpu) && is_pae(vcpu) && !is_long_mode(vcpu)) {
 		vmcs_write64(GUEST_PDPTR0, vcpu->arch.pdptrs[0]);
 		vmcs_write64(GUEST_PDPTR1, vcpu->arch.pdptrs[1]);

@@ -1562,6 +1572,11 @@ static void ept_save_pdptrs(struct kvm_vcpu *vcpu)
 		vcpu->arch.pdptrs[2] = vmcs_read64(GUEST_PDPTR2);
 		vcpu->arch.pdptrs[3] = vmcs_read64(GUEST_PDPTR3);
 	}
+
+	__set_bit(VCPU_EXREG_PDPTR,
+		  (unsigned long *)&vcpu->arch.regs_avail);
+	__set_bit(VCPU_EXREG_PDPTR,
+		  (unsigned long *)&vcpu->arch.regs_dirty);
 }
 
 static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4);

@@ -3255,10 +3270,8 @@ static int vmx_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 	/* Access CR3 don't cause VMExit in paging mode, so we need
 	 * to sync with guest real CR3. */
-	if (enable_ept && is_paging(vcpu)) {
+	if (enable_ept && is_paging(vcpu))
 		vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
-		ept_save_pdptrs(vcpu);
-	}
 
 	if (unlikely(vmx->fail)) {
 		kvm_run->exit_reason = KVM_EXIT_FAIL_ENTRY;

@@ -3567,7 +3580,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 #endif
 	      );
 
-	vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP));
+	vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
+				  | (1 << VCPU_EXREG_PDPTR));
 	vcpu->arch.regs_dirty = 0;
 
 	get_debugreg(vcpu->arch.dr6, 6);

index 75e9df0..2ad8c97 100644
@@ -246,6 +246,10 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3)
 	ret = 1;
 
 	memcpy(vcpu->arch.pdptrs, pdpte, sizeof(vcpu->arch.pdptrs));
+	__set_bit(VCPU_EXREG_PDPTR,
+		  (unsigned long *)&vcpu->arch.regs_avail);
+	__set_bit(VCPU_EXREG_PDPTR,
+		  (unsigned long *)&vcpu->arch.regs_dirty);
 out:
 
 	return ret;

@@ -261,6 +265,10 @@ static bool pdptrs_changed(struct kvm_vcpu *vcpu)
 	if (is_long_mode(vcpu) || !is_pae(vcpu))
 		return false;
 
+	if (!test_bit(VCPU_EXREG_PDPTR,
+		      (unsigned long *)&vcpu->arch.regs_avail))
+		return true;
+
 	r = kvm_read_guest(vcpu->kvm, vcpu->arch.cr3 & ~31u, pdpte, sizeof(pdpte));
 	if (r < 0)
 		goto out;

index d726dec..959cb59 100644
@@ -3153,8 +3153,8 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n",
 			(long unsigned int)exit_qualification);
 		kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
-		kvm_run->hw.hardware_exit_reason = 0;
-		return -ENOTSUPP;
+		kvm_run->hw.hardware_exit_reason = EXIT_REASON_EPT_VIOLATION;
+		return 0;
 	}
 
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);

index c4c7ec2..7549068 100644
@@ -24,7 +24,8 @@ static int coalesced_mmio_in_range(struct kvm_io_device *this,
 {
 	struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
 	struct kvm_coalesced_mmio_zone *zone;
-	int next;
+	struct kvm_coalesced_mmio_ring *ring;
+	unsigned avail;
 	int i;
 
 	if (!is_write)

@@ -40,10 +41,9 @@ static int coalesced_mmio_in_range(struct kvm_io_device *this,
 	 * check if we don't meet the first used entry
 	 * there is always one unused entry in the buffer
 	 */
-
-	next = (dev->kvm->coalesced_mmio_ring->last + 1) %
-							KVM_COALESCED_MMIO_MAX;
-	if (next == dev->kvm->coalesced_mmio_ring->first) {
+	ring = dev->kvm->coalesced_mmio_ring;
+	avail = (ring->first - ring->last - 1) % KVM_COALESCED_MMIO_MAX;
+	if (avail < 1) {
 		/* full */
 		return 0;
 	}

index 0e773fc..a2048ac 100644
@@ -269,7 +269,7 @@ static inline void kvmppc_e500_deliver_tlb_miss(struct kvm_vcpu *vcpu,
 	tlbsel = (vcpu_e500->mas4 >> 28) & 0x1;
 	victim = (tlbsel == 0) ? tlb0_get_next_victim(vcpu_e500) : 0;
 	pidsel = (vcpu_e500->mas4 >> 16) & 0xf;
-	tsized = (vcpu_e500->mas4 >> 8) & 0xf;
+	tsized = (vcpu_e500->mas4 >> 7) & 0x1f;
 
 	vcpu_e500->mas0 = MAS0_TLBSEL(tlbsel) | MAS0_ESEL(victim)
 		| MAS0_NV(vcpu_e500->guest_tlb_nv[tlbsel]);

@@ -309,7 +309,7 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 	vcpu_e500->shadow_pages[tlbsel][esel] = new_page;
 
 	/* Force TS=1 IPROT=0 TSIZE=4KB for all guest mappings. */
-	stlbe->mas1 = MAS1_TSIZE(BOOKE_PAGESZ_4K)
+	stlbe->mas1 = MAS1_TSIZE(BOOK3E_PAGESZ_4K)
 		| MAS1_TID(get_tlb_tid(gtlbe)) | MAS1_TS | MAS1_VALID;
 	stlbe->mas2 = (gvaddr & MAS2_EPN)
 		| e500_shadow_mas2_attrib(gtlbe->mas2,

@@ -545,7 +545,7 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 		case 0:
 			/* TLB0 */
 			gtlbe->mas1 &= ~MAS1_TSIZE(~0);
-			gtlbe->mas1 |= MAS1_TSIZE(BOOKE_PAGESZ_4K);
+			gtlbe->mas1 |= MAS1_TSIZE(BOOK3E_PAGESZ_4K);
 
 			stlbsel = 0;
 			sesel = kvmppc_e500_stlbe_map(vcpu_e500, 0, esel);

@@ -679,14 +679,14 @@ void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *vcpu_e500)
 
 	/* Insert large initial mapping for guest. */
 	tlbe = &vcpu_e500->guest_tlb[1][0];
-	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOKE_PAGESZ_256M);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_256M);
 	tlbe->mas2 = 0;
 	tlbe->mas3 = E500_TLB_SUPER_PERM_MASK;
 	tlbe->mas7 = 0;
 
 	/* 4K map for serial output. Used by kernel wrapper. */
 	tlbe = &vcpu_e500->guest_tlb[1][1];
-	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOKE_PAGESZ_4K);
+	tlbe->mas1 = MAS1_VALID | MAS1_TSIZE(BOOK3E_PAGESZ_4K);
 	tlbe->mas2 = (0xe0004500 & 0xFFFFF000) | MAS2_I | MAS2_G;
 	tlbe->mas3 = (0xe0004500 & 0xFFFFF000) | E500_TLB_SUPER_PERM_MASK;
 	tlbe->mas7 = 0;

index 45b064b..d28e301 100644
@@ -16,7 +16,7 @@
 #define __KVM_E500_TLB_H__
 
 #include <linux/kvm_host.h>
-#include <asm/mmu-fsl-booke.h>
+#include <asm/mmu-book3e.h>
 #include <asm/tlb.h>
 #include <asm/kvm_e500.h>
 

@@ -59,7 +59,7 @@ extern void kvmppc_e500_tlb_setup(struct kvmppc_vcpu_e500 *);
 /* TLB helper functions */
 static inline unsigned int get_tlb_size(const struct tlbe *tlbe)
 {
-	return (tlbe->mas1 >> 8) & 0xf;
+	return (tlbe->mas1 >> 7) & 0x1f;
 }
 
 static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)

@@ -70,7 +70,7 @@ static inline gva_t get_tlb_eaddr(const struct tlbe *tlbe)
 static inline u64 get_tlb_bytes(const struct tlbe *tlbe)
 {
 	unsigned int pgsize = get_tlb_size(tlbe);
-	return 1ULL << 10 << (pgsize << 1);
+	return 1ULL << 10 << pgsize;
 }
 
 static inline gva_t get_tlb_end(const struct tlbe *tlbe)

index fddc3ed..d4caa61 100644
@@ -153,7 +153,6 @@ struct kvm_vcpu_arch {
 	u32 pid;
 	u32 swap_pid;
 
-	u32 pvr;
 	u32 ccr0;
 	u32 ccr1;
 	u32 dbcr0;

index 674e796..64949ee 100644
@@ -60,9 +60,6 @@ int kvmppc_core_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	kvmppc_e500_tlb_setup(vcpu_e500);
 
-	/* Use the same core vertion as host's */
-	vcpu->arch.pvr = mfspr(SPRN_PVR);
-
 	return 0;
 }
 

index a561d6e..f8b8248 100644
@@ -187,7 +187,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 			case SPRN_SRR1:
 				vcpu->arch.gpr[rt] = vcpu->arch.srr1; break;
 			case SPRN_PVR:
-				vcpu->arch.gpr[rt] = vcpu->arch.pvr; break;
+				vcpu->arch.gpr[rt] = mfspr(SPRN_PVR); break;
 
 			/* Note: mftb and TBRL/TBWL are user-accessible, so
 			 * the guest can always access the real TB anyways.

index 3f76041..be95b8d 100644
@@ -180,6 +180,9 @@ int kvmppc_core_emulate_mfspr(struct kvm_vcpu *vcpu, int sprn, int rt)
 	case SPRN_MMUCSR0:
 		vcpu->arch.gpr[rt] = 0; break;
 
+	case SPRN_MMUCFG:
+		vcpu->arch.gpr[rt] = mfspr(SPRN_MMUCFG); break;
+
 	/* extra exceptions */
 	case SPRN_IVOR32:
 		vcpu->arch.gpr[rt] = vcpu->arch.ivor[BOOKE_IRQPRIO_SPE_UNAVAIL];

index f8b8248..28a8237 100644
@@ -188,6 +188,8 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 				vcpu->arch.gpr[rt] = vcpu->arch.srr1; break;
 			case SPRN_PVR:
 				vcpu->arch.gpr[rt] = mfspr(SPRN_PVR); break;
+			case SPRN_PIR:
+				vcpu->arch.gpr[rt] = mfspr(SPRN_PIR); break;
 
 			/* Note: mftb and TBRL/TBWL are user-accessible, so
 			 * the guest can always access the real TB anyways.

index 4bfd458..a23f42e 100644
@@ -194,7 +194,6 @@ int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
 
 	return highest_irr;
 }
-EXPORT_SYMBOL_GPL(kvm_lapic_find_highest_irr);
 
 static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
 			     int vector, int level, int trig_mode);

@@ -768,7 +767,6 @@ void kvm_lapic_set_tpr(struct kvm_vcpu *vcpu, unsigned long cr8)
 	apic_set_tpr(apic, ((cr8 & 0x0f) << 4)
 		     | (apic_get_reg(apic, APIC_TASKPRI) & 4));
 }
-EXPORT_SYMBOL_GPL(kvm_lapic_set_tpr);
 
 u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
 {

@@ -781,7 +779,6 @@ u64 kvm_lapic_get_cr8(struct kvm_vcpu *vcpu)
 
 	return (tpr & 0xf0) >> 4;
 }
-EXPORT_SYMBOL_GPL(kvm_lapic_get_cr8);
 
 void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 {

@@ -805,12 +802,6 @@ void kvm_lapic_set_base(struct kvm_vcpu *vcpu, u64 value)
 
 }
 
-u64 kvm_lapic_get_base(struct kvm_vcpu *vcpu)
-{
-	return vcpu->arch.apic_base;
-}
-EXPORT_SYMBOL_GPL(kvm_lapic_get_base);
-
 void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic;

@@ -860,7 +851,6 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 		   vcpu, kvm_apic_id(apic),
 		   vcpu->arch.apic_base, apic->base_address);
 }
-EXPORT_SYMBOL_GPL(kvm_lapic_reset);
 
 bool kvm_apic_present(struct kvm_vcpu *vcpu)
 {

@@ -871,7 +861,6 @@ int kvm_lapic_enabled(struct kvm_vcpu *vcpu)
 {
 	return kvm_apic_present(vcpu) && apic_sw_enabled(vcpu->arch.apic);
 }
-EXPORT_SYMBOL_GPL(kvm_lapic_enabled);
 
 /*
  *----------------------------------------------------------------------

@@ -970,7 +959,6 @@ nomem_free_apic:
 nomem:
 	return -ENOMEM;
 }
-EXPORT_SYMBOL_GPL(kvm_create_lapic);
 
 int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
 {

index 2520922..bf94a45 100644
@@ -72,8 +72,10 @@ static void pic_clear_isr(struct kvm_kpic_state *s, int irq)
 void kvm_pic_clear_isr_ack(struct kvm *kvm)
 {
 	struct kvm_pic *s = pic_irqchip(kvm);
+	pic_lock(s);
 	s->pics[0].isr_ack = 0xff;
 	s->pics[1].isr_ack = 0xff;
+	pic_unlock(s);
 }
 
 /*

index 7549068..397f419 100644
@@ -31,10 +31,6 @@ static int coalesced_mmio_in_range(struct kvm_io_device *this,
 	if (!is_write)
 		return 0;
 
-	/* kvm->lock is taken by the caller and must be not released before
-         * dev.read/write
-         */
-
 	/* Are we able to batch it ? */
 
 	/* last is the first free entry

@@ -43,7 +39,7 @@ static int coalesced_mmio_in_range(struct kvm_io_device *this,
 	 */
 	ring = dev->kvm->coalesced_mmio_ring;
 	avail = (ring->first - ring->last - 1) % KVM_COALESCED_MMIO_MAX;
-	if (avail < 1) {
+	if (avail < KVM_MAX_VCPUS) {
 		/* full */
 		return 0;
 	}

@@ -70,7 +66,7 @@ static void coalesced_mmio_write(struct kvm_io_device *this,
 	struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
 	struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring;
 
-	/* kvm->lock must be taken by caller before call to in_range()*/
+	spin_lock(&dev->lock);
 
 	/* copy data in first free entry of the ring */
 

@@ -79,6 +75,7 @@ static void coalesced_mmio_write(struct kvm_io_device *this,
 	memcpy(ring->coalesced_mmio[ring->last].data, val, len);
 	smp_wmb();
 	ring->last = (ring->last + 1) % KVM_COALESCED_MMIO_MAX;
+	spin_unlock(&dev->lock);
 }
 
 static void coalesced_mmio_destructor(struct kvm_io_device *this)

@@ -101,6 +98,7 @@ int kvm_coalesced_mmio_init(struct kvm *kvm)
 	dev = kzalloc(sizeof(struct kvm_coalesced_mmio_dev), GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;
+	spin_lock_init(&dev->lock);
 	kvm_iodevice_init(&dev->dev, &coalesced_mmio_ops);
 	dev->kvm = kvm;
 	kvm->coalesced_mmio_dev = dev;

index 5ac0ec6..4b49f27 100644
@@ -12,6 +12,7 @@
 struct kvm_coalesced_mmio_dev {
 	struct kvm_io_device dev;
 	struct kvm *kvm;
+	spinlock_t lock;
 	int nb_zones;
 	struct kvm_coalesced_mmio_zone zone[KVM_COALESCED_MMIO_ZONE_MAX];
 };

index 19240fe..0c71688 100644
@@ -124,7 +124,6 @@ struct kvm_kernel_irq_routing_entry {
 };
 
 struct kvm {
-	struct mutex lock; /* protects the vcpus array and APIC accesses */
 	spinlock_t mmu_lock;
 	spinlock_t requests_lock;
 	struct rw_semaphore slots_lock;

@@ -134,6 +133,7 @@ struct kvm {
 					KVM_PRIVATE_MEM_SLOTS];
 	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
 	struct list_head vm_list;
+	struct mutex lock;
 	struct kvm_io_bus mmio_bus;
 	struct kvm_io_bus pio_bus;
 #ifdef CONFIG_HAVE_KVM_EVENTFD

@@ -150,6 +150,7 @@ struct kvm {
 	struct kvm_coalesced_mmio_ring *coalesced_mmio_ring;
 #endif
 
+	struct mutex irq_lock;
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
 	struct list_head irq_routing; /* of kvm_kernel_irq_routing_entry */
 	struct hlist_head mask_notifier_list;

index 469b9fa..2a56671 100644
@@ -243,6 +243,7 @@ static void ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
 	ioapic_debug("addr %lx\n", (unsigned long)addr);
 	ASSERT(!(addr & 0xf));	/* check alignment */
 
+	mutex_lock(&ioapic->kvm->irq_lock);
 	addr &= 0xff;
 	switch (addr) {
 	case IOAPIC_REG_SELECT:

@@ -269,6 +270,7 @@ static void ioapic_mmio_read(struct kvm_io_device *this, gpa_t addr, int len,
 	default:
 		printk(KERN_WARNING "ioapic: wrong length %d\n", len);
 	}
+	mutex_unlock(&ioapic->kvm->irq_lock);
 }
 
 static void ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,

@@ -280,6 +282,8 @@ static void ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
 	ioapic_debug("ioapic_mmio_write addr=%p len=%d val=%p\n",
 		     (void*)addr, len, val);
 	ASSERT(!(addr & 0xf));	/* check alignment */
+
+	mutex_lock(&ioapic->kvm->irq_lock);
 	if (len == 4 || len == 8)
 		data = *(u32 *) val;
 	else {

@@ -305,6 +309,7 @@ static void ioapic_mmio_write(struct kvm_io_device *this, gpa_t addr, int len,
 	default:
 		break;
 	}
+	mutex_unlock(&ioapic->kvm->irq_lock);
 }
 
 void kvm_ioapic_reset(struct kvm_ioapic *ioapic)

index d1f9c87..d47e660 100644
@@ -982,6 +982,7 @@ static struct kvm *kvm_create_vm(void)
 	kvm_io_bus_init(&kvm->pio_bus);
 	kvm_irqfd_init(kvm);
 	mutex_init(&kvm->lock);
+	mutex_init(&kvm->irq_lock);
 	kvm_io_bus_init(&kvm->mmio_bus);
 	init_rwsem(&kvm->slots_lock);
 	atomic_set(&kvm->users_count, 1);

index 3199221..8dde369 100644
@@ -1000,10 +1000,10 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			goto out;
 		if (irqchip_in_kernel(kvm)) {
 			__s32 status;
-			mutex_lock(&kvm->lock);
+			mutex_lock(&kvm->irq_lock);
 			status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
 				    irq_event.irq, irq_event.level);
-			mutex_unlock(&kvm->lock);
+			mutex_unlock(&kvm->irq_lock);
 			if (ioctl == KVM_IRQ_LINE_STATUS) {
 				irq_event.status = status;
 				if (copy_to_user(argp, &irq_event,

index 977af7a..3837db6 100644
@@ -654,10 +654,10 @@ static void __inject_pit_timer_intr(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 	int i;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->irq_lock);
 	kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 1);
 	kvm_set_irq(kvm, kvm->arch.vpit->irq_source_id, 0, 0);
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->irq_lock);
 
 	/*
 	 * Provides NMI watchdog support via Virtual Wire mode.

index a23f42e..44f20cd 100644
@@ -424,7 +424,9 @@ static void apic_set_eoi(struct kvm_lapic *apic)
 		trigger_mode = IOAPIC_LEVEL_TRIG;
 	else
 		trigger_mode = IOAPIC_EDGE_TRIG;
+	mutex_lock(&apic->vcpu->kvm->irq_lock);
 	kvm_ioapic_update_eoi(apic->vcpu->kvm, vector, trigger_mode);
+	mutex_unlock(&apic->vcpu->kvm->irq_lock);
 }
 
 static void apic_send_ipi(struct kvm_lapic *apic)

@@ -448,7 +450,9 @@ static void apic_send_ipi(struct kvm_lapic *apic)
 		   irq.trig_mode, irq.level, irq.dest_mode, irq.delivery_mode,
 		   irq.vector);
 
+	mutex_lock(&apic->vcpu->kvm->irq_lock);
 	kvm_irq_delivery_to_apic(apic->vcpu->kvm, apic, &irq);
+	mutex_unlock(&apic->vcpu->kvm->irq_lock);
 }
 
 static u32 apic_get_tmcct(struct kvm_lapic *apic)

index 2ad8c97..05cbe83 100644
@@ -2136,10 +2136,10 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			goto out;
 		if (irqchip_in_kernel(kvm)) {
 			__s32 status;
-			mutex_lock(&kvm->lock);
+			mutex_lock(&kvm->irq_lock);
 			status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
 					irq_event.irq, irq_event.level);
-			mutex_unlock(&kvm->lock);
+			mutex_unlock(&kvm->irq_lock);
 			if (ioctl == KVM_IRQ_LINE_STATUS) {
 				irq_event.status = status;
 				if (copy_to_user(argp, &irq_event,

@@ -2385,12 +2385,11 @@ mmio:
 	 */
 	mutex_lock(&vcpu->kvm->lock);
 	mmio_dev = vcpu_find_mmio_dev(vcpu, gpa, bytes, 0);
+	mutex_unlock(&vcpu->kvm->lock);
 	if (mmio_dev) {
 		kvm_iodevice_read(mmio_dev, gpa, bytes, val);
-		mutex_unlock(&vcpu->kvm->lock);
 		return X86EMUL_CONTINUE;
 	}
-	mutex_unlock(&vcpu->kvm->lock);
 
 	vcpu->mmio_needed = 1;
 	vcpu->mmio_phys_addr = gpa;

@@ -2440,12 +2439,11 @@ mmio:
 	 */
 	mutex_lock(&vcpu->kvm->lock);
 	mmio_dev = vcpu_find_mmio_dev(vcpu, gpa, bytes, 1);
+	mutex_unlock(&vcpu->kvm->lock);
 	if (mmio_dev) {
 		kvm_iodevice_write(mmio_dev, gpa, bytes, val);
-		mutex_unlock(&vcpu->kvm->lock);
 		return X86EMUL_CONTINUE;
 	}
-	mutex_unlock(&vcpu->kvm->lock);
 
 	vcpu->mmio_needed = 1;
 	vcpu->mmio_phys_addr = gpa;

@@ -2768,7 +2766,6 @@ static void kernel_pio(struct kvm_io_device *pio_dev,
 {
 	/* TODO: String I/O for in kernel device */
 
-	mutex_lock(&vcpu->kvm->lock);
 	if (vcpu->arch.pio.in)
 		kvm_iodevice_read(pio_dev, vcpu->arch.pio.port,
 				  vcpu->arch.pio.size,

@@ -2777,7 +2774,6 @@ static void kernel_pio(struct kvm_io_device *pio_dev,
 		kvm_iodevice_write(pio_dev, vcpu->arch.pio.port,
 				   vcpu->arch.pio.size,
 				   pd);
-	mutex_unlock(&vcpu->kvm->lock);
 }
 
 static void pio_string_write(struct kvm_io_device *pio_dev,

@@ -2787,14 +2783,12 @@ static void pio_string_write(struct kvm_io_device *pio_dev,
 	void *pd = vcpu->arch.pio_data;
 	int i;
 
-	mutex_lock(&vcpu->kvm->lock);
 	for (i = 0; i < io->cur_count; i++) {
 		kvm_iodevice_write(pio_dev, io->port,
 				   io->size,
 				   pd);
 		pd += io->size;
 	}
-	mutex_unlock(&vcpu->kvm->lock);
 }
 
 static struct kvm_io_device *vcpu_find_pio_dev(struct kvm_vcpu *vcpu,

@@ -2831,7 +2825,9 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 	val = kvm_register_read(vcpu, VCPU_REGS_RAX);
 	memcpy(vcpu->arch.pio_data, &val, 4);
 
+	mutex_lock(&vcpu->kvm->lock);
 	pio_dev = vcpu_find_pio_dev(vcpu, port, size, !in);
+	mutex_unlock(&vcpu->kvm->lock);
 	if (pio_dev) {
 		kernel_pio(pio_dev, vcpu, vcpu->arch.pio_data);
 		complete_pio(vcpu);

@@ -2895,9 +2891,12 @@ int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 
 	vcpu->arch.pio.guest_gva = address;
 
+	mutex_lock(&vcpu->kvm->lock);
 	pio_dev = vcpu_find_pio_dev(vcpu, port,
 				    vcpu->arch.pio.cur_count,
 				    !vcpu->arch.pio.in);
+	mutex_unlock(&vcpu->kvm->lock);
+
 	if (!vcpu->arch.pio.in) {
 		/* string PIO write */
 		ret = pio_copy_data(vcpu);

index 0c71688..a29ea03 100644
@@ -371,7 +371,8 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level);
 void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin);
 void kvm_register_irq_ack_notifier(struct kvm *kvm,
 				   struct kvm_irq_ack_notifier *kian);
-void kvm_unregister_irq_ack_notifier(struct kvm_irq_ack_notifier *kian);
+void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
+				   struct kvm_irq_ack_notifier *kian);
 int kvm_request_irq_source_id(struct kvm *kvm);
 void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
 

index 3140123..4092b8d 100644
@@ -57,10 +57,10 @@ irqfd_inject(struct work_struct *work)
 	struct _irqfd *irqfd = container_of(work, struct _irqfd, inject);
 	struct kvm *kvm = irqfd->kvm;
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->irq_lock);
 	kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 1);
 	kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, 0);
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->irq_lock);
 }
 
 /*

index ddc17f0..08a9a49 100644
@@ -62,6 +62,8 @@ int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
 	int i, r = -1;
 	struct kvm_vcpu *vcpu, *lowest = NULL;
 
+	WARN_ON(!mutex_is_locked(&kvm->irq_lock));
+
 	if (irq->dest_mode == 0 && irq->dest_id == 0xff &&
 			kvm_is_dm_lowest_prio(irq))
 		printk(KERN_INFO "kvm: apic: phys broadcast and lowest prio\n");

@@ -113,7 +115,7 @@ static int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
 	return kvm_irq_delivery_to_apic(kvm, NULL, &irq);
 }
 
-/* This should be called with the kvm->lock mutex held
+/* This should be called with the kvm->irq_lock mutex held
  * Return value:
  *  < 0   Interrupt was ignored (masked or not delivered for other reasons)
  *  = 0   Interrupt was coalesced (previous irq is still pending)

@@ -125,6 +127,8 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level)
 	unsigned long *irq_state, sig_level;
 	int ret = -1;
 
+	WARN_ON(!mutex_is_locked(&kvm->irq_lock));
+
 	if (irq < KVM_IOAPIC_NUM_PINS) {
 		irq_state = (unsigned long *)&kvm->arch.irq_states[irq];
 

@@ -175,19 +179,26 @@ void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
 void kvm_register_irq_ack_notifier(struct kvm *kvm,
 				   struct kvm_irq_ack_notifier *kian)
 {
+	mutex_lock(&kvm->irq_lock);
 	hlist_add_head(&kian->link, &kvm->arch.irq_ack_notifier_list);
+	mutex_unlock(&kvm->irq_lock);
 }
 
-void kvm_unregister_irq_ack_notifier(struct kvm_irq_ack_notifier *kian)
+void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
+				    struct kvm_irq_ack_notifier *kian)
 {
+	mutex_lock(&kvm->irq_lock);
 	hlist_del_init(&kian->link);
+	mutex_unlock(&kvm->irq_lock);
 }
 
-/* The caller must hold kvm->lock mutex */
 int kvm_request_irq_source_id(struct kvm *kvm)
 {
 	unsigned long *bitmap = &kvm->arch.irq_sources_bitmap;
-	int irq_source_id = find_first_zero_bit(bitmap,
+	int irq_source_id;
+
+	mutex_lock(&kvm->irq_lock);
+	irq_source_id = find_first_zero_bit(bitmap,
 				sizeof(kvm->arch.irq_sources_bitmap));
 
 	if (irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) {

@@ -197,6 +208,7 @@ int kvm_request_irq_source_id(struct kvm *kvm)
 
 	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
 	set_bit(irq_source_id, bitmap);
+	mutex_unlock(&kvm->irq_lock);
 
 	return irq_source_id;
 }

@@ -207,6 +219,7 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
 
 	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
 
+	mutex_lock(&kvm->irq_lock);
 	if (irq_source_id < 0 ||
 	    irq_source_id >= sizeof(kvm->arch.irq_sources_bitmap)) {
 		printk(KERN_ERR "kvm: IRQ source ID out of range!\n");

@@ -215,19 +228,24 @@ void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
 	for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++)
 		clear_bit(irq_source_id, &kvm->arch.irq_states[i]);
 	clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
+	mutex_unlock(&kvm->irq_lock);
 }
 
 void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
 				    struct kvm_irq_mask_notifier *kimn)
 {
+	mutex_lock(&kvm->irq_lock);
 	kimn->irq = irq;
 	hlist_add_head(&kimn->link, &kvm->mask_notifier_list);
+	mutex_unlock(&kvm->irq_lock);
 }
 
 void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
 				      struct kvm_irq_mask_notifier *kimn)
 {
+	mutex_lock(&kvm->irq_lock);
 	hlist_del(&kimn->link);
+	mutex_unlock(&kvm->irq_lock);
 }
 
 void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask)

@@ -235,6 +253,8 @@ void kvm_fire_mask_notifiers(struct kvm *kvm, int irq, bool mask)
 	struct kvm_irq_mask_notifier *kimn;
 	struct hlist_node *n;
 
+	WARN_ON(!mutex_is_locked(&kvm->irq_lock));
+
 	hlist_for_each_entry(kimn, n, &kvm->mask_notifier_list, link)
 		if (kimn->irq == irq)
 			kimn->func(kimn, mask);

@@ -250,7 +270,9 @@ static void __kvm_free_irq_routing(struct list_head *irq_routing)
 
 void kvm_free_irq_routing(struct kvm *kvm)
 {
+	mutex_lock(&kvm->irq_lock);
 	__kvm_free_irq_routing(&kvm->irq_routing);
+	mutex_unlock(&kvm->irq_lock);
 }
 
 static int setup_routing_entry(struct kvm_kernel_irq_routing_entry *e,

@@ -325,13 +347,13 @@ int kvm_set_irq_routing(struct kvm *kvm,
 		e = NULL;
 	}
 
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->irq_lock);
 	list_splice(&kvm->irq_routing, &tmp);
 	INIT_LIST_HEAD(&kvm->irq_routing);
 	list_splice(&irq_list, &kvm->irq_routing);
 	INIT_LIST_HEAD(&irq_list);
 	list_splice(&tmp, &irq_list);
-	mutex_unlock(&kvm->lock);
+	mutex_unlock(&kvm->irq_lock);
 
 	r = 0;
 

index d47e660..0d481b2 100644
@@ -62,6 +62,12 @@
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 
+/*
+ * Ordering of locks:
+ *
+ * 		kvm->lock --> kvm->irq_lock
+ */
+
 DEFINE_SPINLOCK(kvm_lock);
 LIST_HEAD(vm_list);
 

@@ -126,11 +132,7 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
 				    interrupt_work);
 	kvm = assigned_dev->kvm;
 
-	/* This is taken to safely inject irq inside the guest. When
-	 * the interrupt injection (or the ioapic code) uses a
-	 * finer-grained lock, update this
-	 */
-	mutex_lock(&kvm->lock);
+	mutex_lock(&kvm->irq_lock);
 	spin_lock_irq(&assigned_dev->assigned_dev_lock);
 	if (assigned_dev->irq_requested_type & KVM_DEV_IRQ_HOST_MSIX) {
 		struct kvm_guest_msix_entry *guest_entries =

@@ -149,7 +151,7 @@ static void kvm_assigned_dev_interrupt_work_handler(struct work_struct *work)
 			    assigned_dev->guest_irq, 1);
 
 	spin_unlock_irq(&assigned_dev->assigned_dev_lock);
-	mutex_unlock(&assigned_dev->kvm->lock);
+	mutex_unlock(&assigned_dev->kvm->irq_lock);
 }
 
 static irqreturn_t kvm_assigned_dev_intr(int irq, void *dev_id)

@@ -207,7 +209,7 @@ static void kvm_assigned_dev_ack_irq(struct kvm_irq_ack_notifier *kian)
 static void deassign_guest_irq(struct kvm *kvm,
 			       struct kvm_assigned_dev_kernel *assigned_dev)
 {
-	kvm_unregister_irq_ack_notifier(&assigned_dev->ack_notifier);
+	kvm_unregister_irq_ack_notifier(kvm, &assigned_dev->ack_notifier);
 	assigned_dev->ack_notifier.gsi = -1;
 
 	if (assigned_dev->irq_source_id != -1)

index 1cc901e..a1a96a5 100644
@@ -37,12 +37,14 @@
 #define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS |	\
 				  0xFFFFFF0000000000ULL)
 
-#define KVM_GUEST_CR0_MASK				   \
-	(X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE \
-	 | X86_CR0_NW | X86_CR0_CD)
+#define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST				\
+	(X86_CR0_WP | X86_CR0_NE | X86_CR0_NW | X86_CR0_CD)
+#define KVM_GUEST_CR0_MASK						\
+	(KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
+#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST				\
+	(X86_CR0_WP | X86_CR0_NE | X86_CR0_TS | X86_CR0_MP)
 #define KVM_VM_CR0_ALWAYS_ON						\
-	(X86_CR0_PG | X86_CR0_PE | X86_CR0_WP | X86_CR0_NE | X86_CR0_TS \
-	 | X86_CR0_MP)
+	(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
 #define KVM_GUEST_CR4_MASK						\
 	(X86_CR4_VME | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_PGE | X86_CR4_VMXE)
 #define KVM_PMODE_VM_CR4_ALWAYS_ON (X86_CR4_PAE | X86_CR4_VMXE)

index 11be5ad..e7927a6 100644
@@ -55,6 +55,7 @@
 #define SECONDARY_EXEC_ENABLE_EPT               0x00000002
 #define SECONDARY_EXEC_ENABLE_VPID              0x00000020
 #define SECONDARY_EXEC_WBINVD_EXITING		0x00000040
+#define SECONDARY_EXEC_UNRESTRICTED_GUEST	0x00000080
 
 
 #define PIN_BASED_EXT_INTR_MASK                 0x00000001

125 lines not on this page · raw message

index 632a856..f1dada0 100644
@@ -495,11 +495,6 @@ struct kvm_irqfd {
  * ioctls for VM fds
  */
 #define KVM_SET_MEMORY_REGION     _IOW(KVMIO, 0x40, struct kvm_memory_region)
-#define KVM_SET_NR_MMU_PAGES      _IO(KVMIO, 0x44)
-#define KVM_GET_NR_MMU_PAGES      _IO(KVMIO, 0x45)
-#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46,\
-					struct kvm_userspace_memory_region)
-#define KVM_SET_TSS_ADDR          _IO(KVMIO, 0x47)
 /*
  * KVM_CREATE_VCPU receives as a parameter the vcpu slot, and returns
  * a vcpu fd.

@@ -507,6 +502,11 @@ struct kvm_irqfd {
 #define KVM_CREATE_VCPU           _IO(KVMIO,  0x41)
 #define KVM_GET_DIRTY_LOG         _IOW(KVMIO, 0x42, struct kvm_dirty_log)
 #define KVM_SET_MEMORY_ALIAS      _IOW(KVMIO, 0x43, struct kvm_memory_alias)
+#define KVM_SET_NR_MMU_PAGES      _IO(KVMIO, 0x44)
+#define KVM_GET_NR_MMU_PAGES      _IO(KVMIO, 0x45)
+#define KVM_SET_USER_MEMORY_REGION _IOW(KVMIO, 0x46,\
+					struct kvm_userspace_memory_region)
+#define KVM_SET_TSS_ADDR          _IO(KVMIO, 0x47)
 /* Device model IOC */
 #define KVM_CREATE_IRQCHIP	  _IO(KVMIO,  0x60)
 #define KVM_IRQ_LINE		  _IOW(KVMIO, 0x61, struct kvm_irq_level)

index a1a96a5..c7b0cc2 100644
@@ -340,16 +340,6 @@ struct kvm_vcpu_arch {
 		u8 nr;
 	} interrupt;
 
-	struct {
-		int vm86_active;
-		u8 save_iopl;
-		struct kvm_save_segment {
-			u16 selector;
-			unsigned long base;
-			u32 limit;
-			u32 ar;
-		} tr, es, ds, fs, gs;
-	} rmode;
 	int halt_request; /* real mode on Intel only */
 
 	int cpuid_nent;

196 lines not on this page · raw message