Merge branch 'kvm-updates/2.6.33' of git://git.kernel.org/pub/scm/virt/kvm/kvm

* 'kvm-updates/2.6.33' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (84 commits)
  KVM: VMX: Fix comparison of guest efer with stale host value
  KVM: s390: Fix prefix register checking in arch/s390/kvm/sigp.c
  KVM: Drop user return notifier when disabling virtualization on a cpu
  KVM: VMX: Disable unrestricted guest when EPT disabled
  KVM: x86 emulator: limit instructions to 15 bytes
  KVM: s390: Make psw available on all exits, not just a subset
  KVM: x86: Add KVM_GET/SET_VCPU_EVENTS
  KVM: VMX: Report unexpected simultaneous exceptions as internal errors
  KVM: Allow internal errors reported to userspace to carry extra data
  KVM: Reorder IOCTLs in main kvm.h
  KVM: x86: Polish exception injection via KVM_SET_GUEST_DEBUG
  KVM: only clear irq_source_id if irqchip is present
  KVM: x86: disallow KVM_{SET,GET}_LAPIC without allocated in-kernel lapic
  KVM: x86: disallow multiple KVM_CREATE_IRQCHIP
  KVM: VMX: Remove vmx->msr_offset_efer
  KVM: MMU: update invlpg handler comment
  KVM: VMX: move CR3/PDPTR update to vmx_set_cr3
  KVM: remove duplicated task_switch check
  KVM: powerpc: Fix BUILD_BUG_ON condition
  KVM: VMX: Use shared msr infrastructure
  ...

Trivial conflicts due to new Kconfig options in arch/Kconfig and kernel/Makefile

arch/x86/kvm/Kconfig

@@ -28,6 +28,7 @@ config KVM
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_EVENTFD
 	select KVM_APIC_ARCHITECTURE
+	select USER_RETURN_NOTIFIER
 	---help---
 	  Support hosting fully virtualized guest machines using hardware
 	  virtualization extensions.  You will need a fairly recent

arch/x86/kvm/Makefile

@@ -6,7 +6,8 @@ CFLAGS_svm.o := -I.
 CFLAGS_vmx.o := -I.
 
 kvm-y			+= $(addprefix ../../../virt/kvm/, kvm_main.o ioapic.o \
-				coalesced_mmio.o irq_comm.o eventfd.o)
+				coalesced_mmio.o irq_comm.o eventfd.o \
+				assigned-dev.o)
 kvm-$(CONFIG_IOMMU_API)	+= $(addprefix ../../../virt/kvm/, iommu.o)
 
 kvm-y			+= x86.o mmu.o emulate.o i8259.o irq.o lapic.o \

arch/x86/kvm/emulate.c

@@ -75,6 +75,8 @@
 #define Group       (1<<14)     /* Bits 3:5 of modrm byte extend opcode */
 #define GroupDual   (1<<15)     /* Alternate decoding of mod == 3 */
 #define GroupMask   0xff        /* Group number stored in bits 0:7 */
+/* Misc flags */
+#define No64	    (1<<28)
 /* Source 2 operand type */
 #define Src2None    (0<<29)
 #define Src2CL      (1<<29)
@@ -92,19 +94,23 @@ static u32 opcode_table[256] = {
 	/* 0x00 - 0x07 */
 	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
-	ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0,
+	ByteOp | DstAcc | SrcImm, DstAcc | SrcImm,
+	ImplicitOps | Stack | No64, ImplicitOps | Stack | No64,
 	/* 0x08 - 0x0F */
 	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
-	0, 0, 0, 0,
+	ByteOp | DstAcc | SrcImm, DstAcc | SrcImm,
+	ImplicitOps | Stack | No64, 0,
 	/* 0x10 - 0x17 */
 	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
-	ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0,
+	ByteOp | DstAcc | SrcImm, DstAcc | SrcImm,
+	ImplicitOps | Stack | No64, ImplicitOps | Stack | No64,
 	/* 0x18 - 0x1F */
 	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
-	ByteOp | DstAcc | SrcImm, DstAcc | SrcImm, 0, 0,
+	ByteOp | DstAcc | SrcImm, DstAcc | SrcImm,
+	ImplicitOps | Stack | No64, ImplicitOps | Stack | No64,
 	/* 0x20 - 0x27 */
 	ByteOp | DstMem | SrcReg | ModRM, DstMem | SrcReg | ModRM,
 	ByteOp | DstReg | SrcMem | ModRM, DstReg | SrcMem | ModRM,
@@ -133,7 +139,8 @@ static u32 opcode_table[256] = {
 	DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack,
 	DstReg | Stack, DstReg | Stack, DstReg | Stack, DstReg | Stack,
 	/* 0x60 - 0x67 */
-	0, 0, 0, DstReg | SrcMem32 | ModRM | Mov /* movsxd (x86/64) */ ,
+	ImplicitOps | Stack | No64, ImplicitOps | Stack | No64,
+	0, DstReg | SrcMem32 | ModRM | Mov /* movsxd (x86/64) */ ,
 	0, 0, 0, 0,
 	/* 0x68 - 0x6F */
 	SrcImm | Mov | Stack, 0, SrcImmByte | Mov | Stack, 0,
@@ -158,7 +165,7 @@ static u32 opcode_table[256] = {
 	/* 0x90 - 0x97 */
 	DstReg, DstReg, DstReg, DstReg,	DstReg, DstReg, DstReg, DstReg,
 	/* 0x98 - 0x9F */
-	0, 0, SrcImm | Src2Imm16, 0,
+	0, 0, SrcImm | Src2Imm16 | No64, 0,
 	ImplicitOps | Stack, ImplicitOps | Stack, 0, 0,
 	/* 0xA0 - 0xA7 */
 	ByteOp | DstReg | SrcMem | Mov | MemAbs, DstReg | SrcMem | Mov | MemAbs,
@@ -185,7 +192,7 @@ static u32 opcode_table[256] = {
 	ByteOp | DstMem | SrcImm | ModRM | Mov, DstMem | SrcImm | ModRM | Mov,
 	/* 0xC8 - 0xCF */
 	0, 0, 0, ImplicitOps | Stack,
-	ImplicitOps, SrcImmByte, ImplicitOps, ImplicitOps,
+	ImplicitOps, SrcImmByte, ImplicitOps | No64, ImplicitOps,
 	/* 0xD0 - 0xD7 */
 	ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM,
 	ByteOp | DstMem | SrcImplicit | ModRM, DstMem | SrcImplicit | ModRM,
@@ -198,7 +205,7 @@ static u32 opcode_table[256] = {
 	ByteOp | SrcImmUByte, SrcImmUByte,
 	/* 0xE8 - 0xEF */
 	SrcImm | Stack, SrcImm | ImplicitOps,
-	SrcImmU | Src2Imm16, SrcImmByte | ImplicitOps,
+	SrcImmU | Src2Imm16 | No64, SrcImmByte | ImplicitOps,
 	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
 	SrcNone | ByteOp | ImplicitOps, SrcNone | ImplicitOps,
 	/* 0xF0 - 0xF7 */
@@ -244,11 +251,13 @@ static u32 twobyte_table[256] = {
 	/* 0x90 - 0x9F */
 	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0xA0 - 0xA7 */
-	0, 0, 0, DstMem | SrcReg | ModRM | BitOp,
+	ImplicitOps | Stack, ImplicitOps | Stack,
+	0, DstMem | SrcReg | ModRM | BitOp,
 	DstMem | SrcReg | Src2ImmByte | ModRM,
 	DstMem | SrcReg | Src2CL | ModRM, 0, 0,
 	/* 0xA8 - 0xAF */
-	0, 0, 0, DstMem | SrcReg | ModRM | BitOp,
+	ImplicitOps | Stack, ImplicitOps | Stack,
+	0, DstMem | SrcReg | ModRM | BitOp,
 	DstMem | SrcReg | Src2ImmByte | ModRM,
 	DstMem | SrcReg | Src2CL | ModRM,
 	ModRM, 0,
@@ -613,6 +622,9 @@ static int do_insn_fetch(struct x86_emulate_ctxt *ctxt,
 {
 	int rc = 0;
 
+	/* x86 instructions are limited to 15 bytes. */
+	if (eip + size - ctxt->decode.eip_orig > 15)
+		return X86EMUL_UNHANDLEABLE;
 	eip += ctxt->cs_base;
 	while (size--) {
 		rc = do_fetch_insn_byte(ctxt, ops, eip++, dest++);
@@ -871,7 +883,7 @@ x86_decode_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 	/* Shadow copy of register state. Committed on successful emulation. */
 
 	memset(c, 0, sizeof(struct decode_cache));
-	c->eip = kvm_rip_read(ctxt->vcpu);
+	c->eip = c->eip_orig = kvm_rip_read(ctxt->vcpu);
 	ctxt->cs_base = seg_base(ctxt, VCPU_SREG_CS);
 	memcpy(c->regs, ctxt->vcpu->arch.regs, sizeof c->regs);
 
@@ -962,6 +974,11 @@ done_prefixes:
 		}
 	}
 
+	if (mode == X86EMUL_MODE_PROT64 && (c->d & No64)) {
+		kvm_report_emulation_failure(ctxt->vcpu, "invalid x86/64 instruction");;
+		return -1;
+	}
+
 	if (c->d & Group) {
 		group = c->d & GroupMask;
 		c->modrm = insn_fetch(u8, 1, c->eip);
@@ -1186,6 +1203,69 @@ static int emulate_pop(struct x86_emulate_ctxt *ctxt,
 	return rc;
 }
 
+static void emulate_push_sreg(struct x86_emulate_ctxt *ctxt, int seg)
+{
+	struct decode_cache *c = &ctxt->decode;
+	struct kvm_segment segment;
+
+	kvm_x86_ops->get_segment(ctxt->vcpu, &segment, seg);
+
+	c->src.val = segment.selector;
+	emulate_push(ctxt);
+}
+
+static int emulate_pop_sreg(struct x86_emulate_ctxt *ctxt,
+			     struct x86_emulate_ops *ops, int seg)
+{
+	struct decode_cache *c = &ctxt->decode;
+	unsigned long selector;
+	int rc;
+
+	rc = emulate_pop(ctxt, ops, &selector, c->op_bytes);
+	if (rc != 0)
+		return rc;
+
+	rc = kvm_load_segment_descriptor(ctxt->vcpu, (u16)selector, 1, seg);
+	return rc;
+}
+
+static void emulate_pusha(struct x86_emulate_ctxt *ctxt)
+{
+	struct decode_cache *c = &ctxt->decode;
+	unsigned long old_esp = c->regs[VCPU_REGS_RSP];
+	int reg = VCPU_REGS_RAX;
+
+	while (reg <= VCPU_REGS_RDI) {
+		(reg == VCPU_REGS_RSP) ?
+		(c->src.val = old_esp) : (c->src.val = c->regs[reg]);
+
+		emulate_push(ctxt);
+		++reg;
+	}
+}
+
+static int emulate_popa(struct x86_emulate_ctxt *ctxt,
+			struct x86_emulate_ops *ops)
+{
+	struct decode_cache *c = &ctxt->decode;
+	int rc = 0;
+	int reg = VCPU_REGS_RDI;
+
+	while (reg >= VCPU_REGS_RAX) {
+		if (reg == VCPU_REGS_RSP) {
+			register_address_increment(c, &c->regs[VCPU_REGS_RSP],
+							c->op_bytes);
+			--reg;
+		}
+
+		rc = emulate_pop(ctxt, ops, &c->regs[reg], c->op_bytes);
+		if (rc != 0)
+			break;
+		--reg;
+	}
+	return rc;
+}
+
 static inline int emulate_grp1a(struct x86_emulate_ctxt *ctxt,
 				struct x86_emulate_ops *ops)
 {
@@ -1707,18 +1787,45 @@ special_insn:
 	      add:		/* add */
 		emulate_2op_SrcV("add", c->src, c->dst, ctxt->eflags);
 		break;
+	case 0x06:		/* push es */
+		emulate_push_sreg(ctxt, VCPU_SREG_ES);
+		break;
+	case 0x07:		/* pop es */
+		rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_ES);
+		if (rc != 0)
+			goto done;
+		break;
 	case 0x08 ... 0x0d:
 	      or:		/* or */
 		emulate_2op_SrcV("or", c->src, c->dst, ctxt->eflags);
 		break;
+	case 0x0e:		/* push cs */
+		emulate_push_sreg(ctxt, VCPU_SREG_CS);
+		break;
 	case 0x10 ... 0x15:
 	      adc:		/* adc */
 		emulate_2op_SrcV("adc", c->src, c->dst, ctxt->eflags);
 		break;
+	case 0x16:		/* push ss */
+		emulate_push_sreg(ctxt, VCPU_SREG_SS);
+		break;
+	case 0x17:		/* pop ss */
+		rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_SS);
+		if (rc != 0)
+			goto done;
+		break;
 	case 0x18 ... 0x1d:
 	      sbb:		/* sbb */
 		emulate_2op_SrcV("sbb", c->src, c->dst, ctxt->eflags);
 		break;
+	case 0x1e:		/* push ds */
+		emulate_push_sreg(ctxt, VCPU_SREG_DS);
+		break;
+	case 0x1f:		/* pop ds */
+		rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_DS);
+		if (rc != 0)
+			goto done;
+		break;
 	case 0x20 ... 0x25:
 	      and:		/* and */
 		emulate_2op_SrcV("and", c->src, c->dst, ctxt->eflags);
@@ -1750,6 +1857,14 @@ special_insn:
 		if (rc != 0)
 			goto done;
 		break;
+	case 0x60:	/* pusha */
+		emulate_pusha(ctxt);
+		break;
+	case 0x61:	/* popa */
+		rc = emulate_popa(ctxt, ops);
+		if (rc != 0)
+			goto done;
+		break;
 	case 0x63:		/* movsxd */
 		if (ctxt->mode != X86EMUL_MODE_PROT64)
 			goto cannot_emulate;
@@ -1761,7 +1876,7 @@ special_insn:
 		break;
 	case 0x6c:		/* insb */
 	case 0x6d:		/* insw/insd */
-		 if (kvm_emulate_pio_string(ctxt->vcpu, NULL,
+		 if (kvm_emulate_pio_string(ctxt->vcpu,
 				1,
 				(c->d & ByteOp) ? 1 : c->op_bytes,
 				c->rep_prefix ?
@@ -1777,7 +1892,7 @@ special_insn:
 		return 0;
 	case 0x6e:		/* outsb */
 	case 0x6f:		/* outsw/outsd */
-		if (kvm_emulate_pio_string(ctxt->vcpu, NULL,
+		if (kvm_emulate_pio_string(ctxt->vcpu,
 				0,
 				(c->d & ByteOp) ? 1 : c->op_bytes,
 				c->rep_prefix ?
@@ -2070,7 +2185,7 @@ special_insn:
 	case 0xef: /* out (e/r)ax,dx */
 		port = c->regs[VCPU_REGS_RDX];
 		io_dir_in = 0;
-	do_io:	if (kvm_emulate_pio(ctxt->vcpu, NULL, io_dir_in,
+	do_io:	if (kvm_emulate_pio(ctxt->vcpu, io_dir_in,
 				   (c->d & ByteOp) ? 1 : c->op_bytes,
 				   port) != 0) {
 			c->eip = saved_eip;
@@ -2297,6 +2412,14 @@ twobyte_insn:
 			jmp_rel(c, c->src.val);
 		c->dst.type = OP_NONE;
 		break;
+	case 0xa0:	  /* push fs */
+		emulate_push_sreg(ctxt, VCPU_SREG_FS);
+		break;
+	case 0xa1:	 /* pop fs */
+		rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_FS);
+		if (rc != 0)
+			goto done;
+		break;
 	case 0xa3:
 	      bt:		/* bt */
 		c->dst.type = OP_NONE;
@@ -2308,6 +2431,14 @@ twobyte_insn:
 	case 0xa5: /* shld cl, r, r/m */
 		emulate_2op_cl("shld", c->src2, c->src, c->dst, ctxt->eflags);
 		break;
+	case 0xa8:	/* push gs */
+		emulate_push_sreg(ctxt, VCPU_SREG_GS);
+		break;
+	case 0xa9:	/* pop gs */
+		rc = emulate_pop_sreg(ctxt, ops, VCPU_SREG_GS);
+		if (rc != 0)
+			goto done;
+		break;
 	case 0xab:
 	      bts:		/* bts */
 		/* only subword offset */

arch/x86/kvm/i8254.c

@@ -688,10 +688,8 @@ static void __inject_pit_timer_intr(struct kvm *kvm)
 	struct kvm_vcpu *vcpu;
 	int i;
 
-	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->irq_lock);
 
 	/*
 	 * Provides NMI watchdog support via Virtual Wire mode.

arch/x86/kvm/i8259.c

@@ -38,7 +38,15 @@ static void pic_clear_isr(struct kvm_kpic_state *s, int irq)
 	s->isr_ack |= (1 << irq);
 	if (s != &s->pics_state->pics[0])
 		irq += 8;
+	/*
+	 * We are dropping lock while calling ack notifiers since ack
+	 * notifier callbacks for assigned devices call into PIC recursively.
+	 * Other interrupt may be delivered to PIC while lock is dropped but
+	 * it should be safe since PIC state is already updated at this stage.
+	 */
+	spin_unlock(&s->pics_state->lock);
 	kvm_notify_acked_irq(s->pics_state->kvm, SELECT_PIC(irq), irq);
+	spin_lock(&s->pics_state->lock);
 }
 
 void kvm_pic_clear_isr_ack(struct kvm *kvm)
@@ -176,16 +184,18 @@ int kvm_pic_set_irq(void *opaque, int irq, int level)
 static inline void pic_intack(struct kvm_kpic_state *s, int irq)
 {
 	s->isr |= 1 << irq;
-	if (s->auto_eoi) {
-		if (s->rotate_on_auto_eoi)
-			s->priority_add = (irq + 1) & 7;
-		pic_clear_isr(s, irq);
-	}
 	/*
 	 * We don't clear a level sensitive interrupt here
 	 */
 	if (!(s->elcr & (1 << irq)))
 		s->irr &= ~(1 << irq);
+
+	if (s->auto_eoi) {
+		if (s->rotate_on_auto_eoi)
+			s->priority_add = (irq + 1) & 7;
+		pic_clear_isr(s, irq);
+	}
+
 }
 
 int kvm_pic_read_irq(struct kvm *kvm)
@@ -225,22 +235,11 @@ int kvm_pic_read_irq(struct kvm *kvm)
 
 void kvm_pic_reset(struct kvm_kpic_state *s)
 {
-	int irq, irqbase, n;
+	int irq;
 	struct kvm *kvm = s->pics_state->irq_request_opaque;
 	struct kvm_vcpu *vcpu0 = kvm->bsp_vcpu;
+	u8 irr = s->irr, isr = s->imr;
 
-	if (s == &s->pics_state->pics[0])
-		irqbase = 0;
-	else
-		irqbase = 8;
-
-	for (irq = 0; irq < PIC_NUM_PINS/2; irq++) {
-		if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0))
-			if (s->irr & (1 << irq) || s->isr & (1 << irq)) {
-				n = irq + irqbase;
-				kvm_notify_acked_irq(kvm, SELECT_PIC(n), n);
-			}
-	}
 	s->last_irr = 0;
 	s->irr = 0;
 	s->imr = 0;
@@ -256,6 +255,13 @@ void kvm_pic_reset(struct kvm_kpic_state *s)
 	s->rotate_on_auto_eoi = 0;
 	s->special_fully_nested_mode = 0;
 	s->init4 = 0;
+
+	for (irq = 0; irq < PIC_NUM_PINS/2; irq++) {
+		if (vcpu0 && kvm_apic_accept_pic_intr(vcpu0))
+			if (irr & (1 << irq) || isr & (1 << irq)) {
+				pic_clear_isr(s, irq);
+			}
+	}
 }
 
 static void pic_ioport_write(void *opaque, u32 addr, u32 val)
@@ -298,9 +304,9 @@ static void pic_ioport_write(void *opaque, u32 addr, u32 val)
 				priority = get_priority(s, s->isr);
 				if (priority != 8) {
 					irq = (priority + s->priority_add) & 7;
-					pic_clear_isr(s, irq);
 					if (cmd == 5)
 						s->priority_add = (irq + 1) & 7;
+					pic_clear_isr(s, irq);
 					pic_update_irq(s->pics_state);
 				}
 				break;

arch/x86/kvm/irq.h

@@ -71,6 +71,7 @@ struct kvm_pic {
 	int output;		/* intr from master PIC */
 	struct kvm_io_device dev;
 	void (*ack_notifier)(void *opaque, int irq);
+	unsigned long irq_states[16];
 };
 
 struct kvm_pic *kvm_create_pic(struct kvm *kvm);
@@ -85,7 +86,11 @@ static inline struct kvm_pic *pic_irqchip(struct kvm *kvm)
 
 static inline int irqchip_in_kernel(struct kvm *kvm)
 {
-	return pic_irqchip(kvm) != NULL;
+	int ret;
+
+	ret = (pic_irqchip(kvm) != NULL);
+	smp_rmb();
+	return ret;
 }
 
 void kvm_pic_reset(struct kvm_kpic_state *s);

arch/x86/kvm/lapic.c

@@ -32,7 +32,6 @@
 #include <asm/current.h>
 #include <asm/apicdef.h>
 #include <asm/atomic.h>
-#include <asm/apicdef.h>
 #include "kvm_cache_regs.h"
 #include "irq.h"
 #include "trace.h"
@@ -471,11 +470,8 @@ static void apic_set_eoi(struct kvm_lapic *apic)
 		trigger_mode = IOAPIC_LEVEL_TRIG;
 	else
 		trigger_mode = IOAPIC_EDGE_TRIG;
-	if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI)) {
-		mutex_lock(&apic->vcpu->kvm->irq_lock);
+	if (!(apic_get_reg(apic, APIC_SPIV) & APIC_SPIV_DIRECTED_EOI))
 		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)
@@ -504,9 +500,7 @@ 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)

arch/x86/kvm/mmu.c

@@ -2789,7 +2789,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code)
 	if (r)
 		goto out;
 
-	er = emulate_instruction(vcpu, vcpu->run, cr2, error_code, 0);
+	er = emulate_instruction(vcpu, cr2, error_code, 0);
 
 	switch (er) {
 	case EMULATE_DONE:
@@ -2800,6 +2800,7 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code)
 	case EMULATE_FAIL:
 		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+		vcpu->run->internal.ndata = 0;
 		return 0;
 	default:
 		BUG();

arch/x86/kvm/paging_tmpl.h

@@ -467,7 +467,6 @@ static void FNAME(invlpg)(struct kvm_vcpu *vcpu, gva_t gva)
 		level = iterator.level;
 		sptep = iterator.sptep;
 
-		/* FIXME: properly handle invlpg on large guest pages */
 		if (level == PT_PAGE_TABLE_LEVEL  ||
 		    ((level == PT_DIRECTORY_LEVEL && is_large_pte(*sptep))) ||
 		    ((level == PT_PDPE_LEVEL && is_large_pte(*sptep)))) {

arch/x86/kvm/svm.c

@@ -46,6 +46,7 @@ MODULE_LICENSE("GPL");
 #define SVM_FEATURE_NPT  (1 << 0)
 #define SVM_FEATURE_LBRV (1 << 1)
 #define SVM_FEATURE_SVML (1 << 2)
+#define SVM_FEATURE_PAUSE_FILTER (1 << 10)
 
 #define NESTED_EXIT_HOST	0	/* Exit handled on host level */
 #define NESTED_EXIT_DONE	1	/* Exit caused nested vmexit  */
@@ -53,15 +54,6 @@ MODULE_LICENSE("GPL");
 
 #define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
 
-/* Turn on to get debugging output*/
-/* #define NESTED_DEBUG */
-
-#ifdef NESTED_DEBUG
-#define nsvm_printk(fmt, args...) printk(KERN_INFO fmt, ## args)
-#else
-#define nsvm_printk(fmt, args...) do {} while(0)
-#endif
-
 static const u32 host_save_user_msrs[] = {
 #ifdef CONFIG_X86_64
 	MSR_STAR, MSR_LSTAR, MSR_CSTAR, MSR_SYSCALL_MASK, MSR_KERNEL_GS_BASE,
@@ -85,6 +77,9 @@ struct nested_state {
 	/* gpa pointers to the real vectors */
 	u64 vmcb_msrpm;
 
+	/* A VMEXIT is required but not yet emulated */
+	bool exit_required;
+
 	/* cache for intercepts of the guest */
 	u16 intercept_cr_read;
 	u16 intercept_cr_write;
@@ -112,6 +107,8 @@ struct vcpu_svm {
 	u32 *msrpm;
 
 	struct nested_state nested;
+
+	bool nmi_singlestep;
 };
 
 /* enable NPT for AMD64 and X86 with PAE */
@@ -286,7 +283,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (!svm->next_rip) {
-		if (emulate_instruction(vcpu, vcpu->run, 0, 0, EMULTYPE_SKIP) !=
+		if (emulate_instruction(vcpu, 0, 0, EMULTYPE_SKIP) !=
 				EMULATE_DONE)
 			printk(KERN_DEBUG "%s: NOP\n", __func__);
 		return;
@@ -316,7 +313,7 @@ static void svm_hardware_disable(void *garbage)
 	cpu_svm_disable();
 }
 
-static void svm_hardware_enable(void *garbage)
+static int svm_hardware_enable(void *garbage)
 {
 
 	struct svm_cpu_data *svm_data;
@@ -325,16 +322,21 @@ static void svm_hardware_enable(void *garbage)
 	struct desc_struct *gdt;
 	int me = raw_smp_processor_id();
 
+	rdmsrl(MSR_EFER, efer);
+	if (efer & EFER_SVME)
+		return -EBUSY;
+
 	if (!has_svm()) {
-		printk(KERN_ERR "svm_cpu_init: err EOPNOTSUPP on %d\n", me);
-		return;
+		printk(KERN_ERR "svm_hardware_enable: err EOPNOTSUPP on %d\n",
+		       me);
+		return -EINVAL;
 	}
 	svm_data = per_cpu(svm_data, me);
 
 	if (!svm_data) {
-		printk(KERN_ERR "svm_cpu_init: svm_data is NULL on %d\n",
+		printk(KERN_ERR "svm_hardware_enable: svm_data is NULL on %d\n",
 		       me);
-		return;
+		return -EINVAL;
 	}
 
 	svm_data->asid_generation = 1;
@@ -345,11 +347,12 @@ static void svm_hardware_enable(void *garbage)
 	gdt = (struct desc_struct *)gdt_descr.base;
 	svm_data->tss_desc = (struct kvm_ldttss_desc *)(gdt + GDT_ENTRY_TSS);
 
-	rdmsrl(MSR_EFER, efer);
 	wrmsrl(MSR_EFER, efer | EFER_SVME);
 
 	wrmsrl(MSR_VM_HSAVE_PA,
 	       page_to_pfn(svm_data->save_area) << PAGE_SHIFT);
+
+	return 0;
 }
 
 static void svm_cpu_uninit(int cpu)
@@ -476,7 +479,7 @@ static __init int svm_hardware_setup(void)
 		kvm_enable_efer_bits(EFER_SVME);
 	}
 
-	for_each_online_cpu(cpu) {
+	for_each_possible_cpu(cpu) {
 		r = svm_cpu_init(cpu);
 		if (r)
 			goto err;
@@ -510,7 +513,7 @@ static __exit void svm_hardware_unsetup(void)
 {
 	int cpu;
 
-	for_each_online_cpu(cpu)
+	for_each_possible_cpu(cpu)
 		svm_cpu_uninit(cpu);
 
 	__free_pages(pfn_to_page(iopm_base >> PAGE_SHIFT), IOPM_ALLOC_ORDER);
@@ -625,11 +628,12 @@ static void init_vmcb(struct vcpu_svm *svm)
 	save->rip = 0x0000fff0;
 	svm->vcpu.arch.regs[VCPU_REGS_RIP] = save->rip;
 
-	/*
-	 * cr0 val on cpu init should be 0x60000010, we enable cpu
-	 * cache by default. the orderly way is to enable cache in bios.
+	/* This is the guest-visible cr0 value.
+	 * svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
 	 */
-	save->cr0 = 0x00000010 | X86_CR0_PG | X86_CR0_WP;
+	svm->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
+	kvm_set_cr0(&svm->vcpu, svm->vcpu.arch.cr0);
+
 	save->cr4 = X86_CR4_PAE;
 	/* rdx = ?? */
 
@@ -644,8 +648,6 @@ static void init_vmcb(struct vcpu_svm *svm)
 		control->intercept_cr_write &= ~(INTERCEPT_CR0_MASK|
 						 INTERCEPT_CR3_MASK);
 		save->g_pat = 0x0007040600070406ULL;
-		/* enable caching because the QEMU Bios doesn't enable it */
-		save->cr0 = X86_CR0_ET;
 		save->cr3 = 0;
 		save->cr4 = 0;
 	}
@@ -654,6 +656,11 @@ static void init_vmcb(struct vcpu_svm *svm)
 	svm->nested.vmcb = 0;
 	svm->vcpu.arch.hflags = 0;
 
+	if (svm_has(SVM_FEATURE_PAUSE_FILTER)) {
+		control->pause_filter_count = 3000;
+		control->intercept |= (1ULL << INTERCEPT_PAUSE);
+	}
+
 	enable_gif(svm);
 }
 
@@ -758,14 +765,13 @@ static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	int i;
 
 	if (unlikely(cpu != vcpu->cpu)) {
-		u64 tsc_this, delta;
+		u64 delta;
 
 		/*
 		 * Make sure that the guest sees a monotonically
 		 * increasing TSC.
 		 */
-		rdtscll(tsc_this);
-		delta = vcpu->arch.host_tsc - tsc_this;
+		delta = vcpu->arch.host_tsc - native_read_tsc();
 		svm->vmcb->control.tsc_offset += delta;
 		if (is_nested(svm))
 			svm->nested.hsave->control.tsc_offset += delta;
@@ -787,7 +793,7 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu)
 	for (i = 0; i < NR_HOST_SAVE_USER_MSRS; i++)
 		wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]);
 
-	rdtscll(vcpu->arch.host_tsc);
+	vcpu->arch.host_tsc = native_read_tsc();
 }
 
 static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
@@ -1045,7 +1051,7 @@ static void update_db_intercept(struct kvm_vcpu *vcpu)
 	svm->vmcb->control.intercept_exceptions &=
 		~((1 << DB_VECTOR) | (1 << BP_VECTOR));
 
-	if (vcpu->arch.singlestep)
+	if (svm->nmi_singlestep)
 		svm->vmcb->control.intercept_exceptions |= (1 << DB_VECTOR);
 
 	if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
@@ -1060,26 +1066,16 @@ static void update_db_intercept(struct kvm_vcpu *vcpu)
 		vcpu->guest_debug = 0;
 }
 
-static int svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
+static void svm_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
 {
-	int old_debug = vcpu->guest_debug;
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	vcpu->guest_debug = dbg->control;
-
-	update_db_intercept(vcpu);
-
 	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
 		svm->vmcb->save.dr7 = dbg->arch.debugreg[7];
 	else
 		svm->vmcb->save.dr7 = vcpu->arch.dr7;
 
-	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
-		svm->vmcb->save.rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
-	else if (old_debug & KVM_GUESTDBG_SINGLESTEP)
-		svm->vmcb->save.rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
-
-	return 0;
+	update_db_intercept(vcpu);
 }
 
 static void load_host_msrs(struct kvm_vcpu *vcpu)
@@ -1180,7 +1176,7 @@ static void svm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long value,
 	}
 }
 
-static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int pf_interception(struct vcpu_svm *svm)
 {
 	u64 fault_address;
 	u32 error_code;
@@ -1194,17 +1190,19 @@ static int pf_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return kvm_mmu_page_fault(&svm->vcpu, fault_address, error_code);
 }
 
-static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int db_interception(struct vcpu_svm *svm)
 {
+	struct kvm_run *kvm_run = svm->vcpu.run;
+
 	if (!(svm->vcpu.guest_debug &
 	      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
-		!svm->vcpu.arch.singlestep) {
+		!svm->nmi_singlestep) {
 		kvm_queue_exception(&svm->vcpu, DB_VECTOR);
 		return 1;
 	}
 
-	if (svm->vcpu.arch.singlestep) {
-		svm->vcpu.arch.singlestep = false;
+	if (svm->nmi_singlestep) {
+		svm->nmi_singlestep = false;
 		if (!(svm->vcpu.guest_debug & KVM_GUESTDBG_SINGLESTEP))
 			svm->vmcb->save.rflags &=
 				~(X86_EFLAGS_TF | X86_EFLAGS_RF);
@@ -1223,25 +1221,27 @@ static int db_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int bp_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int bp_interception(struct vcpu_svm *svm)
 {
+	struct kvm_run *kvm_run = svm->vcpu.run;
+
 	kvm_run->exit_reason = KVM_EXIT_DEBUG;
 	kvm_run->debug.arch.pc = svm->vmcb->save.cs.base + svm->vmcb->save.rip;
 	kvm_run->debug.arch.exception = BP_VECTOR;
 	return 0;
 }
 
-static int ud_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int ud_interception(struct vcpu_svm *svm)
 {
 	int er;
 
-	er = emulate_instruction(&svm->vcpu, kvm_run, 0, 0, EMULTYPE_TRAP_UD);
+	er = emulate_instruction(&svm->vcpu, 0, 0, EMULTYPE_TRAP_UD);
 	if (er != EMULATE_DONE)
 		kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 	return 1;
 }
 
-static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int nm_interception(struct vcpu_svm *svm)
 {
 	svm->vmcb->control.intercept_exceptions &= ~(1 << NM_VECTOR);
 	if (!(svm->vcpu.arch.cr0 & X86_CR0_TS))
@@ -1251,7 +1251,7 @@ static int nm_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int mc_interception(struct vcpu_svm *svm)
 {
 	/*
 	 * On an #MC intercept the MCE handler is not called automatically in
@@ -1264,8 +1264,10 @@ static int mc_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int shutdown_interception(struct vcpu_svm *svm)
 {
+	struct kvm_run *kvm_run = svm->vcpu.run;
+
 	/*
 	 * VMCB is undefined after a SHUTDOWN intercept
 	 * so reinitialize it.
@@ -1277,7 +1279,7 @@ static int shutdown_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 0;
 }
 
-static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int io_interception(struct vcpu_svm *svm)
 {
 	u32 io_info = svm->vmcb->control.exit_info_1; /* address size bug? */
 	int size, in, string;
@@ -1291,7 +1293,7 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 
 	if (string) {
 		if (emulate_instruction(&svm->vcpu,
-					kvm_run, 0, 0, 0) == EMULATE_DO_MMIO)
+					0, 0, 0) == EMULATE_DO_MMIO)
 			return 0;
 		return 1;
 	}
@@ -1301,33 +1303,33 @@ static int io_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	size = (io_info & SVM_IOIO_SIZE_MASK) >> SVM_IOIO_SIZE_SHIFT;
 
 	skip_emulated_instruction(&svm->vcpu);
-	return kvm_emulate_pio(&svm->vcpu, kvm_run, in, size, port);
+	return kvm_emulate_pio(&svm->vcpu, in, size, port);
 }
 
-static int nmi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int nmi_interception(struct vcpu_svm *svm)
 {
 	return 1;
 }
 
-static int intr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int intr_interception(struct vcpu_svm *svm)
 {
 	++svm->vcpu.stat.irq_exits;
 	return 1;
 }
 
-static int nop_on_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int nop_on_interception(struct vcpu_svm *svm)
 {
 	return 1;
 }
 
-static int halt_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int halt_interception(struct vcpu_svm *svm)
 {
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 1;
 	skip_emulated_instruction(&svm->vcpu);
 	return kvm_emulate_halt(&svm->vcpu);
 }
 
-static int vmmcall_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int vmmcall_interception(struct vcpu_svm *svm)
 {
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
 	skip_emulated_instruction(&svm->vcpu);
@@ -1378,8 +1380,15 @@ static inline int nested_svm_intr(struct vcpu_svm *svm)
 
 	svm->vmcb->control.exit_code = SVM_EXIT_INTR;
 
-	if (nested_svm_exit_handled(svm)) {
-		nsvm_printk("VMexit -> INTR\n");
+	if (svm->nested.intercept & 1ULL) {
+		/*
+		 * The #vmexit can't be emulated here directly because this
+		 * code path runs with irqs and preemtion disabled. A
+		 * #vmexit emulation might sleep. Only signal request for
+		 * the #vmexit here.
+		 */
+		svm->nested.exit_required = true;
+		trace_kvm_nested_intr_vmexit(svm->vmcb->save.rip);
 		return 1;
 	}
 
@@ -1390,10 +1399,7 @@ static void *nested_svm_map(struct vcpu_svm *svm, u64 gpa, enum km_type idx)
 {
 	struct page *page;
 
-	down_read(&current->mm->mmap_sem);
 	page = gfn_to_page(svm->vcpu.kvm, gpa >> PAGE_SHIFT);
-	up_read(&current->mm->mmap_sem);
-
 	if (is_error_page(page))
 		goto error;
 
@@ -1532,14 +1538,12 @@ static int nested_svm_exit_handled(struct vcpu_svm *svm)
 	}
 	default: {
 		u64 exit_bits = 1ULL << (exit_code - SVM_EXIT_INTR);
-		nsvm_printk("exit code: 0x%x\n", exit_code);
 		if (svm->nested.intercept & exit_bits)
 			vmexit = NESTED_EXIT_DONE;
 	}
 	}
 
 	if (vmexit == NESTED_EXIT_DONE) {
-		nsvm_printk("#VMEXIT reason=%04x\n", exit_code);
 		nested_svm_vmexit(svm);
 	}
 
@@ -1584,6 +1588,12 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	struct vmcb *hsave = svm->nested.hsave;
 	struct vmcb *vmcb = svm->vmcb;
 
+	trace_kvm_nested_vmexit_inject(vmcb->control.exit_code,
+				       vmcb->control.exit_info_1,
+				       vmcb->control.exit_info_2,
+				       vmcb->control.exit_int_info,
+				       vmcb->control.exit_int_info_err);
+
 	nested_vmcb = nested_svm_map(svm, svm->nested.vmcb, KM_USER0);
 	if (!nested_vmcb)
 		return 1;
@@ -1617,6 +1627,22 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	nested_vmcb->control.exit_info_2       = vmcb->control.exit_info_2;
 	nested_vmcb->control.exit_int_info     = vmcb->control.exit_int_info;
 	nested_vmcb->control.exit_int_info_err = vmcb->control.exit_int_info_err;
+
+	/*
+	 * If we emulate a VMRUN/#VMEXIT in the same host #vmexit cycle we have
+	 * to make sure that we do not lose injected events. So check event_inj
+	 * here and copy it to exit_int_info if it is valid.
+	 * Exit_int_info and event_inj can't be both valid because the case
+	 * below only happens on a VMRUN instruction intercept which has
+	 * no valid exit_int_info set.
+	 */
+	if (vmcb->control.event_inj & SVM_EVTINJ_VALID) {
+		struct vmcb_control_area *nc = &nested_vmcb->control;
+
+		nc->exit_int_info     = vmcb->control.event_inj;
+		nc->exit_int_info_err = vmcb->control.event_inj_err;
+	}
+
 	nested_vmcb->control.tlb_ctl           = 0;
 	nested_vmcb->control.event_inj         = 0;
 	nested_vmcb->control.event_inj_err     = 0;
@@ -1628,10 +1654,6 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	/* Restore the original control entries */
 	copy_vmcb_control_area(vmcb, hsave);
 
-	/* Kill any pending exceptions */
-	if (svm->vcpu.arch.exception.pending == true)
-		nsvm_printk("WARNING: Pending Exception\n");
-
 	kvm_clear_exception_queue(&svm->vcpu);
 	kvm_clear_interrupt_queue(&svm->vcpu);
 
@@ -1702,6 +1724,12 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
 	/* nested_vmcb is our indicator if nested SVM is activated */
 	svm->nested.vmcb = svm->vmcb->save.rax;
 
+	trace_kvm_nested_vmrun(svm->vmcb->save.rip - 3, svm->nested.vmcb,
+			       nested_vmcb->save.rip,
+			       nested_vmcb->control.int_ctl,
+			       nested_vmcb->control.event_inj,
+			       nested_vmcb->control.nested_ctl);
+
 	/* Clear internal status */
 	kvm_clear_exception_queue(&svm->vcpu);
 	kvm_clear_interrupt_queue(&svm->vcpu);
@@ -1789,28 +1817,15 @@ static bool nested_svm_vmrun(struct vcpu_svm *svm)
 	svm->nested.intercept            = nested_vmcb->control.intercept;
 
 	force_new_asid(&svm->vcpu);
-	svm->vmcb->control.exit_int_info = nested_vmcb->control.exit_int_info;
-	svm->vmcb->control.exit_int_info_err = nested_vmcb->control.exit_int_info_err;
 	svm->vmcb->control.int_ctl = nested_vmcb->control.int_ctl | V_INTR_MASKING_MASK;
-	if (nested_vmcb->control.int_ctl & V_IRQ_MASK) {
-		nsvm_printk("nSVM Injecting Interrupt: 0x%x\n",
-				nested_vmcb->control.int_ctl);
-	}
 	if (nested_vmcb->control.int_ctl & V_INTR_MASKING_MASK)
 		svm->vcpu.arch.hflags |= HF_VINTR_MASK;
 	else
 		svm->vcpu.arch.hflags &= ~HF_VINTR_MASK;
 
-	nsvm_printk("nSVM exit_int_info: 0x%x | int_state: 0x%x\n",
-			nested_vmcb->control.exit_int_info,
-			nested_vmcb->control.int_state);
-
 	svm->vmcb->control.int_vector = nested_vmcb->control.int_vector;
 	svm->vmcb->control.int_state = nested_vmcb->control.int_state;
 	svm->vmcb->control.tsc_offset += nested_vmcb->control.tsc_offset;
-	if (nested_vmcb->control.event_inj & SVM_EVTINJ_VALID)
-		nsvm_printk("Injecting Event: 0x%x\n",
-				nested_vmcb->control.event_inj);
 	svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
 	svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
 
@@ -1837,7 +1852,7 @@ static void nested_svm_vmloadsave(struct vmcb *from_vmcb, struct vmcb *to_vmcb)
 	to_vmcb->save.sysenter_eip = from_vmcb->save.sysenter_eip;
 }
 
-static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int vmload_interception(struct vcpu_svm *svm)
 {
 	struct vmcb *nested_vmcb;
 
@@ -1857,7 +1872,7 @@ static int vmload_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int vmsave_interception(struct vcpu_svm *svm)
 {
 	struct vmcb *nested_vmcb;
 
@@ -1877,10 +1892,8 @@ static int vmsave_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int vmrun_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int vmrun_interception(struct vcpu_svm *svm)
 {
-	nsvm_printk("VMrun\n");
-
 	if (nested_svm_check_permissions(svm))
 		return 1;
 
@@ -1907,7 +1920,7 @@ failed:
 	return 1;
 }
 
-static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int stgi_interception(struct vcpu_svm *svm)
 {
 	if (nested_svm_check_permissions(svm))
 		return 1;
@@ -1920,7 +1933,7 @@ static int stgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int clgi_interception(struct vcpu_svm *svm)
 {
 	if (nested_svm_check_permissions(svm))
 		return 1;
@@ -1937,10 +1950,12 @@ static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int invlpga_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int invlpga_interception(struct vcpu_svm *svm)
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
-	nsvm_printk("INVLPGA\n");
+
+	trace_kvm_invlpga(svm->vmcb->save.rip, vcpu->arch.regs[VCPU_REGS_RCX],
+			  vcpu->arch.regs[VCPU_REGS_RAX]);
 
 	/* Let's treat INVLPGA the same as INVLPG (can be optimized!) */
 	kvm_mmu_invlpg(vcpu, vcpu->arch.regs[VCPU_REGS_RAX]);
@@ -1950,15 +1965,21 @@ static int invlpga_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int invalid_op_interception(struct vcpu_svm *svm,
-				   struct kvm_run *kvm_run)
+static int skinit_interception(struct vcpu_svm *svm)
+{
+	trace_kvm_skinit(svm->vmcb->save.rip, svm->vcpu.arch.regs[VCPU_REGS_RAX]);
+
+	kvm_queue_exception(&svm->vcpu, UD_VECTOR);
+	return 1;
+}
+
+static int invalid_op_interception(struct vcpu_svm *svm)
 {
 	kvm_queue_exception(&svm->vcpu, UD_VECTOR);
 	return 1;
 }
 
-static int task_switch_interception(struct vcpu_svm *svm,
-				    struct kvm_run *kvm_run)
+static int task_switch_interception(struct vcpu_svm *svm)
 {
 	u16 tss_selector;
 	int reason;
@@ -2008,14 +2029,14 @@ static int task_switch_interception(struct vcpu_svm *svm,
 	return kvm_task_switch(&svm->vcpu, tss_selector, reason);
 }
 
-static int cpuid_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int cpuid_interception(struct vcpu_svm *svm)
 {
 	svm->next_rip = kvm_rip_read(&svm->vcpu) + 2;
 	kvm_emulate_cpuid(&svm->vcpu);
 	return 1;
 }
 
-static int iret_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int iret_interception(struct vcpu_svm *svm)
 {
 	++svm->vcpu.stat.nmi_window_exits;
 	svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
@@ -2023,26 +2044,27 @@ static int iret_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int invlpg_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int invlpg_interception(struct vcpu_svm *svm)
 {
-	if (emulate_instruction(&svm->vcpu, kvm_run, 0, 0, 0) != EMULATE_DONE)
+	if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE)
 		pr_unimpl(&svm->vcpu, "%s: failed\n", __func__);
 	return 1;
 }
 
-static int emulate_on_interception(struct vcpu_svm *svm,
-				   struct kvm_run *kvm_run)
+static int emulate_on_interception(struct vcpu_svm *svm)
 {
-	if (emulate_instruction(&svm->vcpu, NULL, 0, 0, 0) != EMULATE_DONE)
+	if (emulate_instruction(&svm->vcpu, 0, 0, 0) != EMULATE_DONE)
 		pr_unimpl(&svm->vcpu, "%s: failed\n", __func__);
 	return 1;
 }
 
-static int cr8_write_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int cr8_write_interception(struct vcpu_svm *svm)
 {
+	struct kvm_run *kvm_run = svm->vcpu.run;
+
 	u8 cr8_prev = kvm_get_cr8(&svm->vcpu);
 	/* instruction emulation calls kvm_set_cr8() */
-	emulate_instruction(&svm->vcpu, NULL, 0, 0, 0);
+	emulate_instruction(&svm->vcpu, 0, 0, 0);
 	if (irqchip_in_kernel(svm->vcpu.kvm)) {
 		svm->vmcb->control.intercept_cr_write &= ~INTERCEPT_CR8_MASK;
 		return 1;
@@ -2128,7 +2150,7 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 *data)
 	return 0;
 }
 
-static int rdmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int rdmsr_interception(struct vcpu_svm *svm)
 {
 	u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
 	u64 data;
@@ -2221,7 +2243,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 	return 0;
 }
 
-static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int wrmsr_interception(struct vcpu_svm *svm)
 {
 	u32 ecx = svm->vcpu.arch.regs[VCPU_REGS_RCX];
 	u64 data = (svm->vcpu.arch.regs[VCPU_REGS_RAX] & -1u)
@@ -2237,17 +2259,18 @@ static int wrmsr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
-static int msr_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+static int msr_interception(struct vcpu_svm *svm)
 {
 	if (svm->vmcb->control.exit_info_1)
-		return wrmsr_interception(svm, kvm_run);
+		return wrmsr_interception(svm);
 	else
-		return rdmsr_interception(svm, kvm_run);
+		return rdmsr_interception(svm);
 }
 
-static int interrupt_window_interception(struct vcpu_svm *svm,
-				   struct kvm_run *kvm_run)
+static int interrupt_window_interception(struct vcpu_svm *svm)
 {
+	struct kvm_run *kvm_run = svm->vcpu.run;
+
 	svm_clear_vintr(svm);
 	svm->vmcb->control.int_ctl &= ~V_IRQ_MASK;
 	/*
@@ -2265,8 +2288,13 @@ static int interrupt_window_interception(struct vcpu_svm *svm,
 	return 1;
 }
 
-static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
-				      struct kvm_run *kvm_run) = {
+static int pause_interception(struct vcpu_svm *svm)
+{
+	kvm_vcpu_on_spin(&(svm->vcpu));
+	return 1;
+}
+
+static int (*svm_exit_handlers[])(struct vcpu_svm *svm) = {
 	[SVM_EXIT_READ_CR0]           		= emulate_on_interception,
 	[SVM_EXIT_READ_CR3]           		= emulate_on_interception,
 	[SVM_EXIT_READ_CR4]           		= emulate_on_interception,
@@ -2301,6 +2329,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
 	[SVM_EXIT_CPUID]			= cpuid_interception,
 	[SVM_EXIT_IRET]                         = iret_interception,
 	[SVM_EXIT_INVD]                         = emulate_on_interception,
+	[SVM_EXIT_PAUSE]			= pause_interception,
 	[SVM_EXIT_HLT]				= halt_interception,
 	[SVM_EXIT_INVLPG]			= invlpg_interception,
 	[SVM_EXIT_INVLPGA]			= invlpga_interception,
@@ -2314,26 +2343,36 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
 	[SVM_EXIT_VMSAVE]			= vmsave_interception,
 	[SVM_EXIT_STGI]				= stgi_interception,
 	[SVM_EXIT_CLGI]				= clgi_interception,
-	[SVM_EXIT_SKINIT]			= invalid_op_interception,
+	[SVM_EXIT_SKINIT]			= skinit_interception,
 	[SVM_EXIT_WBINVD]                       = emulate_on_interception,
 	[SVM_EXIT_MONITOR]			= invalid_op_interception,
 	[SVM_EXIT_MWAIT]			= invalid_op_interception,
 	[SVM_EXIT_NPF]				= pf_interception,
 };
 
-static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
+static int handle_exit(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_run *kvm_run = vcpu->run;
 	u32 exit_code = svm->vmcb->control.exit_code;
 
 	trace_kvm_exit(exit_code, svm->vmcb->save.rip);
 
+	if (unlikely(svm->nested.exit_required)) {
+		nested_svm_vmexit(svm);
+		svm->nested.exit_required = false;
+
+		return 1;
+	}
+
 	if (is_nested(svm)) {
 		int vmexit;
 
-		nsvm_printk("nested handle_exit: 0x%x | 0x%lx | 0x%lx | 0x%lx\n",
-			    exit_code, svm->vmcb->control.exit_info_1,
-			    svm->vmcb->control.exit_info_2, svm->vmcb->save.rip);
+		trace_kvm_nested_vmexit(svm->vmcb->save.rip, exit_code,
+					svm->vmcb->control.exit_info_1,
+					svm->vmcb->control.exit_info_2,
+					svm->vmcb->control.exit_int_info,
+					svm->vmcb->control.exit_int_info_err);
 
 		vmexit = nested_svm_exit_special(svm);
 
@@ -2383,7 +2422,7 @@ static int handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		return 0;
 	}
 
-	return svm_exit_handlers[exit_code](svm, kvm_run);
+	return svm_exit_handlers[exit_code](svm);
 }
 
 static void reload_tss(struct kvm_vcpu *vcpu)
@@ -2460,20 +2499,47 @@ static int svm_nmi_allowed(struct kvm_vcpu *vcpu)
 		!(svm->vcpu.arch.hflags & HF_NMI_MASK);
 }
 
+static bool svm_get_nmi_mask(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	return !!(svm->vcpu.arch.hflags & HF_NMI_MASK);
+}
+
+static void svm_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (masked) {
+		svm->vcpu.arch.hflags |= HF_NMI_MASK;
+		svm->vmcb->control.intercept |= (1UL << INTERCEPT_IRET);
+	} else {
+		svm->vcpu.arch.hflags &= ~HF_NMI_MASK;
+		svm->vmcb->control.intercept &= ~(1UL << INTERCEPT_IRET);
+	}
+}
+
 static int svm_interrupt_allowed(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb *vmcb = svm->vmcb;
-	return (vmcb->save.rflags & X86_EFLAGS_IF) &&
-		!(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) &&
-		gif_set(svm) &&
-		!(is_nested(svm) && (svm->vcpu.arch.hflags & HF_VINTR_MASK));
+	int ret;
+
+	if (!gif_set(svm) ||
+	     (vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK))
+		return 0;
+
+	ret = !!(vmcb->save.rflags & X86_EFLAGS_IF);
+
+	if (is_nested(svm))
+		return ret && !(svm->vcpu.arch.hflags & HF_VINTR_MASK);
+
+	return ret;
 }
 
 static void enable_irq_window(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	nsvm_printk("Trying to open IRQ window\n");
 
 	nested_svm_intr(svm);
 
@@ -2498,7 +2564,7 @@ static void enable_nmi_window(struct kvm_vcpu *vcpu)
 	/* Something prevents NMI from been injected. Single step over
 	   possible problem (IRET or exception injection or interrupt
 	   shadow) */
-	vcpu->arch.singlestep = true;
+	svm->nmi_singlestep = true;
 	svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
 	update_db_intercept(vcpu);
 }
@@ -2588,13 +2654,20 @@ static void svm_complete_interrupts(struct vcpu_svm *svm)
 #define R "e"
 #endif
 
-static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u16 fs_selector;
 	u16 gs_selector;
 	u16 ldt_selector;
 
+	/*
+	 * A vmexit emulation is required before the vcpu can be executed
+	 * again.
+	 */
+	if (unlikely(svm->nested.exit_required))
+		return;
+
 	svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
 	svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
 	svm->vmcb->save.rip = vcpu->arch.regs[VCPU_REGS_RIP];
@@ -2893,6 +2966,8 @@ static struct kvm_x86_ops svm_x86_ops = {
 	.queue_exception = svm_queue_exception,
 	.interrupt_allowed = svm_interrupt_allowed,
 	.nmi_allowed = svm_nmi_allowed,
+	.get_nmi_mask = svm_get_nmi_mask,
+	.set_nmi_mask = svm_set_nmi_mask,
 	.enable_nmi_window = enable_nmi_window,
 	.enable_irq_window = enable_irq_window,
 	.update_cr8_intercept = update_cr8_intercept,

arch/x86/kvm/trace.h

@@ -349,6 +349,171 @@ TRACE_EVENT(kvm_apic_accept_irq,
 		  __entry->coalesced ? " (coalesced)" : "")
 );
 
+/*
+ * Tracepoint for nested VMRUN
+ */
+TRACE_EVENT(kvm_nested_vmrun,
+	    TP_PROTO(__u64 rip, __u64 vmcb, __u64 nested_rip, __u32 int_ctl,
+		     __u32 event_inj, bool npt),
+	    TP_ARGS(rip, vmcb, nested_rip, int_ctl, event_inj, npt),
+
+	TP_STRUCT__entry(
+		__field(	__u64,		rip		)
+		__field(	__u64,		vmcb		)
+		__field(	__u64,		nested_rip	)
+		__field(	__u32,		int_ctl		)
+		__field(	__u32,		event_inj	)
+		__field(	bool,		npt		)
+	),
+
+	TP_fast_assign(
+		__entry->rip		= rip;
+		__entry->vmcb		= vmcb;
+		__entry->nested_rip	= nested_rip;
+		__entry->int_ctl	= int_ctl;
+		__entry->event_inj	= event_inj;
+		__entry->npt		= npt;
+	),
+
+	TP_printk("rip: 0x%016llx vmcb: 0x%016llx nrip: 0x%016llx int_ctl: 0x%08x "
+		  "event_inj: 0x%08x npt: %s\n",
+		__entry->rip, __entry->vmcb, __entry->nested_rip,
+		__entry->int_ctl, __entry->event_inj,
+		__entry->npt ? "on" : "off")
+);
+
+/*
+ * Tracepoint for #VMEXIT while nested
+ */
+TRACE_EVENT(kvm_nested_vmexit,
+	    TP_PROTO(__u64 rip, __u32 exit_code,
+		     __u64 exit_info1, __u64 exit_info2,
+		     __u32 exit_int_info, __u32 exit_int_info_err),
+	    TP_ARGS(rip, exit_code, exit_info1, exit_info2,
+		    exit_int_info, exit_int_info_err),
+
+	TP_STRUCT__entry(
+		__field(	__u64,		rip			)
+		__field(	__u32,		exit_code		)
+		__field(	__u64,		exit_info1		)
+		__field(	__u64,		exit_info2		)
+		__field(	__u32,		exit_int_info		)
+		__field(	__u32,		exit_int_info_err	)
+	),
+
+	TP_fast_assign(
+		__entry->rip			= rip;
+		__entry->exit_code		= exit_code;
+		__entry->exit_info1		= exit_info1;
+		__entry->exit_info2		= exit_info2;
+		__entry->exit_int_info		= exit_int_info;
+		__entry->exit_int_info_err	= exit_int_info_err;
+	),
+	TP_printk("rip: 0x%016llx reason: %s ext_inf1: 0x%016llx "
+		  "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n",
+		  __entry->rip,
+		  ftrace_print_symbols_seq(p, __entry->exit_code,
+					   kvm_x86_ops->exit_reasons_str),
+		  __entry->exit_info1, __entry->exit_info2,
+		  __entry->exit_int_info, __entry->exit_int_info_err)
+);
+
+/*
+ * Tracepoint for #VMEXIT reinjected to the guest
+ */
+TRACE_EVENT(kvm_nested_vmexit_inject,
+	    TP_PROTO(__u32 exit_code,
+		     __u64 exit_info1, __u64 exit_info2,
+		     __u32 exit_int_info, __u32 exit_int_info_err),
+	    TP_ARGS(exit_code, exit_info1, exit_info2,
+		    exit_int_info, exit_int_info_err),
+
+	TP_STRUCT__entry(
+		__field(	__u32,		exit_code		)
+		__field(	__u64,		exit_info1		)
+		__field(	__u64,		exit_info2		)
+		__field(	__u32,		exit_int_info		)
+		__field(	__u32,		exit_int_info_err	)
+	),
+
+	TP_fast_assign(
+		__entry->exit_code		= exit_code;
+		__entry->exit_info1		= exit_info1;
+		__entry->exit_info2		= exit_info2;
+		__entry->exit_int_info		= exit_int_info;
+		__entry->exit_int_info_err	= exit_int_info_err;
+	),
+
+	TP_printk("reason: %s ext_inf1: 0x%016llx "
+		  "ext_inf2: 0x%016llx ext_int: 0x%08x ext_int_err: 0x%08x\n",
+		  ftrace_print_symbols_seq(p, __entry->exit_code,
+					   kvm_x86_ops->exit_reasons_str),
+		__entry->exit_info1, __entry->exit_info2,
+		__entry->exit_int_info, __entry->exit_int_info_err)
+);
+
+/*
+ * Tracepoint for nested #vmexit because of interrupt pending
+ */
+TRACE_EVENT(kvm_nested_intr_vmexit,
+	    TP_PROTO(__u64 rip),
+	    TP_ARGS(rip),
+
+	TP_STRUCT__entry(
+		__field(	__u64,	rip	)
+	),
+
+	TP_fast_assign(
+		__entry->rip	=	rip
+	),
+
+	TP_printk("rip: 0x%016llx\n", __entry->rip)
+);
+
+/*
+ * Tracepoint for nested #vmexit because of interrupt pending
+ */
+TRACE_EVENT(kvm_invlpga,
+	    TP_PROTO(__u64 rip, int asid, u64 address),
+	    TP_ARGS(rip, asid, address),
+
+	TP_STRUCT__entry(
+		__field(	__u64,	rip	)
+		__field(	int,	asid	)
+		__field(	__u64,	address	)
+	),
+
+	TP_fast_assign(
+		__entry->rip		=	rip;
+		__entry->asid		=	asid;
+		__entry->address	=	address;
+	),
+
+	TP_printk("rip: 0x%016llx asid: %d address: 0x%016llx\n",
+		  __entry->rip, __entry->asid, __entry->address)
+);
+
+/*
+ * Tracepoint for nested #vmexit because of interrupt pending
+ */
+TRACE_EVENT(kvm_skinit,
+	    TP_PROTO(__u64 rip, __u32 slb),
+	    TP_ARGS(rip, slb),
+
+	TP_STRUCT__entry(
+		__field(	__u64,	rip	)
+		__field(	__u32,	slb	)
+	),
+
+	TP_fast_assign(
+		__entry->rip		=	rip;
+		__entry->slb		=	slb;
+	),
+
+	TP_printk("rip: 0x%016llx slb: 0x%08x\n",
+		  __entry->rip, __entry->slb)
+);
+
 #endif /* _TRACE_KVM_H */
 
 /* This part must be outside protection */

arch/x86/kvm/x86.c

@@ -37,6 +37,7 @@
 #include <linux/iommu.h>
 #include <linux/intel-iommu.h>
 #include <linux/cpufreq.h>
+#include <linux/user-return-notifier.h>
 #include <trace/events/kvm.h>
 #undef TRACE_INCLUDE_FILE
 #define CREATE_TRACE_POINTS
@@ -88,6 +89,25 @@ EXPORT_SYMBOL_GPL(kvm_x86_ops);
 int ignore_msrs = 0;
 module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR);
 
+#define KVM_NR_SHARED_MSRS 16
+
+struct kvm_shared_msrs_global {
+	int nr;
+	struct kvm_shared_msr {
+		u32 msr;
+		u64 value;
+	} msrs[KVM_NR_SHARED_MSRS];
+};
+
+struct kvm_shared_msrs {
+	struct user_return_notifier urn;
+	bool registered;
+	u64 current_value[KVM_NR_SHARED_MSRS];
+};
+
+static struct kvm_shared_msrs_global __read_mostly shared_msrs_global;
+static DEFINE_PER_CPU(struct kvm_shared_msrs, shared_msrs);
+
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "pf_fixed", VCPU_STAT(pf_fixed) },
 	{ "pf_guest", VCPU_STAT(pf_guest) },
@@ -124,6 +144,72 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ NULL }
 };
 
+static void kvm_on_user_return(struct user_return_notifier *urn)
+{
+	unsigned slot;
+	struct kvm_shared_msr *global;
+	struct kvm_shared_msrs *locals
+		= container_of(urn, struct kvm_shared_msrs, urn);
+
+	for (slot = 0; slot < shared_msrs_global.nr; ++slot) {
+		global = &shared_msrs_global.msrs[slot];
+		if (global->value != locals->current_value[slot]) {
+			wrmsrl(global->msr, global->value);
+			locals->current_value[slot] = global->value;
+		}
+	}
+	locals->registered = false;
+	user_return_notifier_unregister(urn);
+}
+
+void kvm_define_shared_msr(unsigned slot, u32 msr)
+{
+	int cpu;
+	u64 value;
+
+	if (slot >= shared_msrs_global.nr)
+		shared_msrs_global.nr = slot + 1;
+	shared_msrs_global.msrs[slot].msr = msr;
+	rdmsrl_safe(msr, &value);
+	shared_msrs_global.msrs[slot].value = value;
+	for_each_online_cpu(cpu)
+		per_cpu(shared_msrs, cpu).current_value[slot] = value;
+}
+EXPORT_SYMBOL_GPL(kvm_define_shared_msr);
+
+static void kvm_shared_msr_cpu_online(void)
+{
+	unsigned i;
+	struct kvm_shared_msrs *locals = &__get_cpu_var(shared_msrs);
+
+	for (i = 0; i < shared_msrs_global.nr; ++i)
+		locals->current_value[i] = shared_msrs_global.msrs[i].value;
+}
+
+void kvm_set_shared_msr(unsigned slot, u64 value, u64 mask)
+{
+	struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs);
+
+	if (((value ^ smsr->current_value[slot]) & mask) == 0)
+		return;
+	smsr->current_value[slot] = value;
+	wrmsrl(shared_msrs_global.msrs[slot].msr, value);
+	if (!smsr->registered) {
+		smsr->urn.on_user_return = kvm_on_user_return;
+		user_return_notifier_register(&smsr->urn);
+		smsr->registered = true;
+	}
+}
+EXPORT_SYMBOL_GPL(kvm_set_shared_msr);
+
+static void drop_user_return_notifiers(void *ignore)
+{
+	struct kvm_shared_msrs *smsr = &__get_cpu_var(shared_msrs);
+
+	if (smsr->registered)
+		kvm_on_user_return(&smsr->urn);
+}
+
 unsigned long segment_base(u16 selector)
 {
 	struct descriptor_table gdt;
@@ -485,16 +571,19 @@ static inline u32 bit(int bitno)
  * and KVM_SET_MSRS, and KVM_GET_MSR_INDEX_LIST.
  *
  * This list is modified at module load time to reflect the
- * capabilities of the host cpu.
+ * capabilities of the host cpu. This capabilities test skips MSRs that are
+ * kvm-specific. Those are put in the beginning of the list.
  */
+
+#define KVM_SAVE_MSRS_BEGIN	2
 static u32 msrs_to_save[] = {
+	MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
 	MSR_IA32_SYSENTER_CS, MSR_IA32_SYSENTER_ESP, MSR_IA32_SYSENTER_EIP,
 	MSR_K6_STAR,
 #ifdef CONFIG_X86_64
 	MSR_CSTAR, MSR_KERNEL_GS_BASE, MSR_SYSCALL_MASK, MSR_LSTAR,
 #endif
-	MSR_IA32_TSC, MSR_KVM_SYSTEM_TIME, MSR_KVM_WALL_CLOCK,
-	MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
+	MSR_IA32_TSC, MSR_IA32_PERF_STATUS, MSR_IA32_CR_PAT, MSR_VM_HSAVE_PA
 };
 
 static unsigned num_msrs_to_save;
@@ -678,7 +767,8 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 	/* With all the info we got, fill in the values */
 
 	vcpu->hv_clock.system_time = ts.tv_nsec +
-				     (NSEC_PER_SEC * (u64)ts.tv_sec);
+				     (NSEC_PER_SEC * (u64)ts.tv_sec) + v->kvm->arch.kvmclock_offset;
+
 	/*
 	 * The interface expects us to write an even number signaling that the
 	 * update is finished. Since the guest won't see the intermediate
@@ -836,6 +926,38 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	return 0;
 }
 
+static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data)
+{
+	struct kvm *kvm = vcpu->kvm;
+	int lm = is_long_mode(vcpu);
+	u8 *blob_addr = lm ? (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_64
+		: (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_32;
+	u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64
+		: kvm->arch.xen_hvm_config.blob_size_32;
+	u32 page_num = data & ~PAGE_MASK;
+	u64 page_addr = data & PAGE_MASK;
+	u8 *page;
+	int r;
+
+	r = -E2BIG;
+	if (page_num >= blob_size)
+		goto out;
+	r = -ENOMEM;
+	page = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!page)
+		goto out;
+	r = -EFAULT;
+	if (copy_from_user(page, blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE))
+		goto out_free;
+	if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE))
+		goto out_free;
+	r = 0;
+out_free:
+	kfree(page);
+out:
+	return r;
+}
+
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	switch (msr) {
@@ -951,6 +1073,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 			"0x%x data 0x%llx\n", msr, data);
 		break;
 	default:
+		if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
+			return xen_hvm_config(vcpu, data);
 		if (!ignore_msrs) {
 			pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n",
 				msr, data);
@@ -1225,6 +1349,9 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_PIT2:
 	case KVM_CAP_PIT_STATE2:
 	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
+	case KVM_CAP_XEN_HVM:
+	case KVM_CAP_ADJUST_CLOCK:
+	case KVM_CAP_VCPU_EVENTS:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -1239,8 +1366,8 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_NR_MEMSLOTS:
 		r = KVM_MEMORY_SLOTS;
 		break;
-	case KVM_CAP_PV_MMU:
-		r = !tdp_enabled;
+	case KVM_CAP_PV_MMU:	/* obsolete */
+		r = 0;
 		break;
 	case KVM_CAP_IOMMU:
 		r = iommu_found();
@@ -1327,6 +1454,12 @@ out:
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	kvm_x86_ops->vcpu_load(vcpu, cpu);
+	if (unlikely(per_cpu(cpu_tsc_khz, cpu) == 0)) {
+		unsigned long khz = cpufreq_quick_get(cpu);
+		if (!khz)
+			khz = tsc_khz;
+		per_cpu(cpu_tsc_khz, cpu) = khz;
+	}
 	kvm_request_guest_time_update(vcpu);
 }
 
@@ -1760,6 +1893,61 @@ static int kvm_vcpu_ioctl_x86_set_mce(struct kvm_vcpu *vcpu,
 	return 0;
 }
 
+static void kvm_vcpu_ioctl_x86_get_vcpu_events(struct kvm_vcpu *vcpu,
+					       struct kvm_vcpu_events *events)
+{
+	vcpu_load(vcpu);
+
+	events->exception.injected = vcpu->arch.exception.pending;
+	events->exception.nr = vcpu->arch.exception.nr;
+	events->exception.has_error_code = vcpu->arch.exception.has_error_code;
+	events->exception.error_code = vcpu->arch.exception.error_code;
+
+	events->interrupt.injected = vcpu->arch.interrupt.pending;
+	events->interrupt.nr = vcpu->arch.interrupt.nr;
+	events->interrupt.soft = vcpu->arch.interrupt.soft;
+
+	events->nmi.injected = vcpu->arch.nmi_injected;
+	events->nmi.pending = vcpu->arch.nmi_pending;
+	events->nmi.masked = kvm_x86_ops->get_nmi_mask(vcpu);
+
+	events->sipi_vector = vcpu->arch.sipi_vector;
+
+	events->flags = 0;
+
+	vcpu_put(vcpu);
+}
+
+static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
+					      struct kvm_vcpu_events *events)
+{
+	if (events->flags)
+		return -EINVAL;
+
+	vcpu_load(vcpu);
+
+	vcpu->arch.exception.pending = events->exception.injected;
+	vcpu->arch.exception.nr = events->exception.nr;
+	vcpu->arch.exception.has_error_code = events->exception.has_error_code;
+	vcpu->arch.exception.error_code = events->exception.error_code;
+
+	vcpu->arch.interrupt.pending = events->interrupt.injected;
+	vcpu->arch.interrupt.nr = events->interrupt.nr;
+	vcpu->arch.interrupt.soft = events->interrupt.soft;
+	if (vcpu->arch.interrupt.pending && irqchip_in_kernel(vcpu->kvm))
+		kvm_pic_clear_isr_ack(vcpu->kvm);
+
+	vcpu->arch.nmi_injected = events->nmi.injected;
+	vcpu->arch.nmi_pending = events->nmi.pending;
+	kvm_x86_ops->set_nmi_mask(vcpu, events->nmi.masked);
+
+	vcpu->arch.sipi_vector = events->sipi_vector;
+
+	vcpu_put(vcpu);
+
+	return 0;
+}
+
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
@@ -1770,6 +1958,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 
 	switch (ioctl) {
 	case KVM_GET_LAPIC: {
+		r = -EINVAL;
+		if (!vcpu->arch.apic)
+			goto out;
 		lapic = kzalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
 
 		r = -ENOMEM;
@@ -1785,6 +1976,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		break;
 	}
 	case KVM_SET_LAPIC: {
+		r = -EINVAL;
+		if (!vcpu->arch.apic)
+			goto out;
 		lapic = kmalloc(sizeof(struct kvm_lapic_state), GFP_KERNEL);
 		r = -ENOMEM;
 		if (!lapic)
@@ -1911,6 +2105,27 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = kvm_vcpu_ioctl_x86_set_mce(vcpu, &mce);
 		break;
 	}
+	case KVM_GET_VCPU_EVENTS: {
+		struct kvm_vcpu_events events;
+
+		kvm_vcpu_ioctl_x86_get_vcpu_events(vcpu, &events);
+
+		r = -EFAULT;
+		if (copy_to_user(argp, &events, sizeof(struct kvm_vcpu_events)))
+			break;
+		r = 0;
+		break;
+	}
+	case KVM_SET_VCPU_EVENTS: {
+		struct kvm_vcpu_events events;
+
+		r = -EFAULT;
+		if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events)))
+			break;
+
+		r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events);
+		break;
+	}
 	default:
 		r = -EINVAL;
 	}
@@ -2039,9 +2254,7 @@ static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
 			sizeof(struct kvm_pic_state));
 		break;
 	case KVM_IRQCHIP_IOAPIC:
-		memcpy(&chip->chip.ioapic,
-			ioapic_irqchip(kvm),
-			sizeof(struct kvm_ioapic_state));
+		r = kvm_get_ioapic(kvm, &chip->chip.ioapic);
 		break;
 	default:
 		r = -EINVAL;
@@ -2071,11 +2284,7 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
 		spin_unlock(&pic_irqchip(kvm)->lock);
 		break;
 	case KVM_IRQCHIP_IOAPIC:
-		mutex_lock(&kvm->irq_lock);
-		memcpy(ioapic_irqchip(kvm),
-			&chip->chip.ioapic,
-			sizeof(struct kvm_ioapic_state));
-		mutex_unlock(&kvm->irq_lock);
+		r = kvm_set_ioapic(kvm, &chip->chip.ioapic);
 		break;
 	default:
 		r = -EINVAL;
@@ -2183,7 +2392,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 {
 	struct kvm *kvm = filp->private_data;
 	void __user *argp = (void __user *)arg;
-	int r = -EINVAL;
+	int r = -ENOTTY;
 	/*
 	 * This union makes it completely explicit to gcc-3.x
 	 * that these two variables' stack usage should be
@@ -2245,25 +2454,39 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		if (r)
 			goto out;
 		break;
-	case KVM_CREATE_IRQCHIP:
+	case KVM_CREATE_IRQCHIP: {
+		struct kvm_pic *vpic;
+
+		mutex_lock(&kvm->lock);
+		r = -EEXIST;
+		if (kvm->arch.vpic)
+			goto create_irqchip_unlock;
 		r = -ENOMEM;
-		kvm->arch.vpic = kvm_create_pic(kvm);
-		if (kvm->arch.vpic) {
+		vpic = kvm_create_pic(kvm);
+		if (vpic) {
 			r = kvm_ioapic_init(kvm);
 			if (r) {
-				kfree(kvm->arch.vpic);
-				kvm->arch.vpic = NULL;
-				goto out;
+				kfree(vpic);
+				goto create_irqchip_unlock;
 			}
 		} else
-			goto out;
+			goto create_irqchip_unlock;
+		smp_wmb();
+		kvm->arch.vpic = vpic;
+		smp_wmb();
 		r = kvm_setup_default_irq_routing(kvm);
 		if (r) {
+			mutex_lock(&kvm->irq_lock);
 			kfree(kvm->arch.vpic);
 			kfree(kvm->arch.vioapic);
-			goto out;
+			kvm->arch.vpic = NULL;
+			kvm->arch.vioapic = NULL;
+			mutex_unlock(&kvm->irq_lock);
 		}
+	create_irqchip_unlock:
+		mutex_unlock(&kvm->lock);
 		break;
+	}
 	case KVM_CREATE_PIT:
 		u.pit_config.flags = KVM_PIT_SPEAKER_DUMMY;
 		goto create_pit;
@@ -2293,10 +2516,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
 			goto out;
 		if (irqchip_in_kernel(kvm)) {
 			__s32 status;
-			mutex_lock(&kvm->irq_lock);
 			status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
 					irq_event.irq, irq_event.level);
-			mutex_unlock(&kvm->irq_lock);
 			if (ioctl == KVM_IRQ_LINE_STATUS) {
 				irq_event.status = status;
 				if (copy_to_user(argp, &irq_event,
@@ -2422,6 +2643,55 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
+	case KVM_XEN_HVM_CONFIG: {
+		r = -EFAULT;
+		if (copy_from_user(&kvm->arch.xen_hvm_config, argp,
+				   sizeof(struct kvm_xen_hvm_config)))
+			goto out;
+		r = -EINVAL;
+		if (kvm->arch.xen_hvm_config.flags)
+			goto out;
+		r = 0;
+		break;
+	}
+	case KVM_SET_CLOCK: {
+		struct timespec now;
+		struct kvm_clock_data user_ns;
+		u64 now_ns;
+		s64 delta;
+
+		r = -EFAULT;
+		if (copy_from_user(&user_ns, argp, sizeof(user_ns)))
+			goto out;
+
+		r = -EINVAL;
+		if (user_ns.flags)
+			goto out;
+
+		r = 0;
+		ktime_get_ts(&now);
+		now_ns = timespec_to_ns(&now);
+		delta = user_ns.clock - now_ns;
+		kvm->arch.kvmclock_offset = delta;
+		break;
+	}
+	case KVM_GET_CLOCK: {
+		struct timespec now;
+		struct kvm_clock_data user_ns;
+		u64 now_ns;
+
+		ktime_get_ts(&now);
+		now_ns = timespec_to_ns(&now);
+		user_ns.clock = kvm->arch.kvmclock_offset + now_ns;
+		user_ns.flags = 0;
+
+		r = -EFAULT;
+		if (copy_to_user(argp, &user_ns, sizeof(user_ns)))
+			goto out;
+		r = 0;
+		break;
+	}
+
 	default:
 		;
 	}
@@ -2434,7 +2704,8 @@ static void kvm_init_msr_list(void)
 	u32 dummy[2];
 	unsigned i, j;
 
-	for (i = j = 0; i < ARRAY_SIZE(msrs_to_save); i++) {
+	/* skip the first msrs in the list. KVM-specific */
+	for (i = j = KVM_SAVE_MSRS_BEGIN; i < ARRAY_SIZE(msrs_to_save); i++) {
 		if (rdmsr_safe(msrs_to_save[i], &dummy[0], &dummy[1]) < 0)
 			continue;
 		if (j < i)
@@ -2758,13 +3029,13 @@ static void cache_all_regs(struct kvm_vcpu *vcpu)
 }
 
 int emulate_instruction(struct kvm_vcpu *vcpu,
-			struct kvm_run *run,
 			unsigned long cr2,
 			u16 error_code,
 			int emulation_type)
 {
 	int r, shadow_mask;
 	struct decode_cache *c;
+	struct kvm_run *run = vcpu->run;
 
 	kvm_clear_exception_queue(vcpu);
 	vcpu->arch.mmio_fault_cr2 = cr2;
@@ -2784,7 +3055,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 		kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
 
 		vcpu->arch.emulate_ctxt.vcpu = vcpu;
-		vcpu->arch.emulate_ctxt.eflags = kvm_x86_ops->get_rflags(vcpu);
+		vcpu->arch.emulate_ctxt.eflags = kvm_get_rflags(vcpu);
 		vcpu->arch.emulate_ctxt.mode =
 			(vcpu->arch.emulate_ctxt.eflags & X86_EFLAGS_VM)
 			? X86EMUL_MODE_REAL : cs_l
@@ -2862,7 +3133,7 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 		return EMULATE_DO_MMIO;
 	}
 
-	kvm_x86_ops->set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
+	kvm_set_rflags(vcpu, vcpu->arch.emulate_ctxt.eflags);
 
 	if (vcpu->mmio_is_write) {
 		vcpu->mmio_needed = 0;
@@ -2970,8 +3241,7 @@ static int pio_string_write(struct kvm_vcpu *vcpu)
 	return r;
 }
 
-int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
-		  int size, unsigned port)
+int kvm_emulate_pio(struct kvm_vcpu *vcpu, int in, int size, unsigned port)
 {
 	unsigned long val;
 
@@ -3000,7 +3270,7 @@ int kvm_emulate_pio(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
 }
 EXPORT_SYMBOL_GPL(kvm_emulate_pio);
 
-int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, struct kvm_run *run, int in,
+int kvm_emulate_pio_string(struct kvm_vcpu *vcpu, int in,
 		  int size, unsigned long count, int down,
 		  gva_t address, int rep, unsigned port)
 {
@@ -3073,9 +3343,6 @@ static void bounce_off(void *info)
 	/* nothing */
 }
 
-static unsigned int  ref_freq;
-static unsigned long tsc_khz_ref;
-
 static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 				     void *data)
 {
@@ -3084,14 +3351,11 @@ static int kvmclock_cpufreq_notifier(struct notifier_block *nb, unsigned long va
 	struct kvm_vcpu *vcpu;
 	int i, send_ipi = 0;
 
-	if (!ref_freq)
-		ref_freq = freq->old;
-
 	if (val == CPUFREQ_PRECHANGE && freq->old > freq->new)
 		return 0;
 	if (val == CPUFREQ_POSTCHANGE && freq->old < freq->new)
 		return 0;
-	per_cpu(cpu_tsc_khz, freq->cpu) = cpufreq_scale(tsc_khz_ref, ref_freq, freq->new);
+	per_cpu(cpu_tsc_khz, freq->cpu) = freq->new;
 
 	spin_lock(&kvm_lock);
 	list_for_each_entry(kvm, &vm_list, vm_list) {
@@ -3128,9 +3392,28 @@ static struct notifier_block kvmclock_cpufreq_notifier_block = {
         .notifier_call  = kvmclock_cpufreq_notifier
 };
 
+static void kvm_timer_init(void)
+{
+	int cpu;
+
+	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
+					  CPUFREQ_TRANSITION_NOTIFIER);
+		for_each_online_cpu(cpu) {
+			unsigned long khz = cpufreq_get(cpu);
+			if (!khz)
+				khz = tsc_khz;
+			per_cpu(cpu_tsc_khz, cpu) = khz;
+		}
+	} else {
+		for_each_possible_cpu(cpu)
+			per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
+	}
+}
+
 int kvm_arch_init(void *opaque)
 {
-	int r, cpu;
+	int r;
 	struct kvm_x86_ops *ops = (struct kvm_x86_ops *)opaque;
 
 	if (kvm_x86_ops) {
@@ -3162,13 +3445,7 @@ int kvm_arch_init(void *opaque)
 	kvm_mmu_set_mask_ptes(PT_USER_MASK, PT_ACCESSED_MASK,
 			PT_DIRTY_MASK, PT64_NX_MASK, 0);
 
-	for_each_possible_cpu(cpu)
-		per_cpu(cpu_tsc_khz, cpu) = tsc_khz;
-	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
-		tsc_khz_ref = tsc_khz;
-		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
-					  CPUFREQ_TRANSITION_NOTIFIER);
-	}
+	kvm_timer_init();
 
 	return 0;
 
@@ -3296,7 +3573,7 @@ void realmode_lmsw(struct kvm_vcpu *vcpu, unsigned long msw,
 		   unsigned long *rflags)
 {
 	kvm_lmsw(vcpu, msw);
-	*rflags = kvm_x86_ops->get_rflags(vcpu);
+	*rflags = kvm_get_rflags(vcpu);
 }
 
 unsigned long realmode_get_cr(struct kvm_vcpu *vcpu, int cr)
@@ -3334,7 +3611,7 @@ void realmode_set_cr(struct kvm_vcpu *vcpu, int cr, unsigned long val,
 	switch (cr) {
 	case 0:
 		kvm_set_cr0(vcpu, mk_cr_64(vcpu->arch.cr0, val));
-		*rflags = kvm_x86_ops->get_rflags(vcpu);
+		*rflags = kvm_get_rflags(vcpu);
 		break;
 	case 2:
 		vcpu->arch.cr2 = val;
@@ -3454,18 +3731,18 @@ EXPORT_SYMBOL_GPL(kvm_emulate_cpuid);
  *
  * No need to exit to userspace if we already have an interrupt queued.
  */
-static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu,
-					  struct kvm_run *kvm_run)
+static int dm_request_for_irq_injection(struct kvm_vcpu *vcpu)
 {
 	return (!irqchip_in_kernel(vcpu->kvm) && !kvm_cpu_has_interrupt(vcpu) &&
-		kvm_run->request_interrupt_window &&
+		vcpu->run->request_interrupt_window &&
 		kvm_arch_interrupt_allowed(vcpu));
 }
 
-static void post_kvm_run_save(struct kvm_vcpu *vcpu,
-			      struct kvm_run *kvm_run)
+static void post_kvm_run_save(struct kvm_vcpu *vcpu)
 {
-	kvm_run->if_flag = (kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
+	struct kvm_run *kvm_run = vcpu->run;
+
+	kvm_run->if_flag = (kvm_get_rflags(vcpu) & X86_EFLAGS_IF) != 0;
 	kvm_run->cr8 = kvm_get_cr8(vcpu);
 	kvm_run->apic_base = kvm_get_apic_base(vcpu);
 	if (irqchip_in_kernel(vcpu->kvm))
@@ -3526,7 +3803,7 @@ static void update_cr8_intercept(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->update_cr8_intercept(vcpu, tpr, max_irr);
 }
 
-static void inject_pending_event(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static void inject_pending_event(struct kvm_vcpu *vcpu)
 {
 	/* try to reinject previous events if any */
 	if (vcpu->arch.exception.pending) {
@@ -3562,11 +3839,11 @@ static void inject_pending_event(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 }
 
-static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 {
 	int r;
 	bool req_int_win = !irqchip_in_kernel(vcpu->kvm) &&
-		kvm_run->request_interrupt_window;
+		vcpu->run->request_interrupt_window;
 
 	if (vcpu->requests)
 		if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
@@ -3587,12 +3864,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 			kvm_x86_ops->tlb_flush(vcpu);
 		if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS,
 				       &vcpu->requests)) {
-			kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS;
+			vcpu->run->exit_reason = KVM_EXIT_TPR_ACCESS;
 			r = 0;
 			goto out;
 		}
 		if (test_and_clear_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests)) {
-			kvm_run->exit_reason = KVM_EXIT_SHUTDOWN;
+			vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
 			r = 0;
 			goto out;
 		}
@@ -3616,7 +3893,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		goto out;
 	}
 
-	inject_pending_event(vcpu, kvm_run);
+	inject_pending_event(vcpu);
 
 	/* enable NMI/IRQ window open exits if needed */
 	if (vcpu->arch.nmi_pending)
@@ -3642,7 +3919,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 
 	trace_kvm_entry(vcpu->vcpu_id);
-	kvm_x86_ops->run(vcpu, kvm_run);
+	kvm_x86_ops->run(vcpu);
 
 	/*
 	 * If the guest has used debug registers, at least dr7
@@ -3684,13 +3961,13 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	kvm_lapic_sync_from_vapic(vcpu);
 
-	r = kvm_x86_ops->handle_exit(kvm_run, vcpu);
+	r = kvm_x86_ops->handle_exit(vcpu);
 out:
 	return r;
 }
 
 
-static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+static int __vcpu_run(struct kvm_vcpu *vcpu)
 {
 	int r;
 
@@ -3710,7 +3987,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	r = 1;
 	while (r > 0) {
 		if (vcpu->arch.mp_state == KVM_MP_STATE_RUNNABLE)
-			r = vcpu_enter_guest(vcpu, kvm_run);
+			r = vcpu_enter_guest(vcpu);
 		else {
 			up_read(&vcpu->kvm->slots_lock);
 			kvm_vcpu_block(vcpu);
@@ -3738,14 +4015,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		if (kvm_cpu_has_pending_timer(vcpu))
 			kvm_inject_pending_timer_irqs(vcpu);
 
-		if (dm_request_for_irq_injection(vcpu, kvm_run)) {
+		if (dm_request_for_irq_injection(vcpu)) {
 			r = -EINTR;
-			kvm_run->exit_reason = KVM_EXIT_INTR;
+			vcpu->run->exit_reason = KVM_EXIT_INTR;
 			++vcpu->stat.request_irq_exits;
 		}
 		if (signal_pending(current)) {
 			r = -EINTR;
-			kvm_run->exit_reason = KVM_EXIT_INTR;
+			vcpu->run->exit_reason = KVM_EXIT_INTR;
 			++vcpu->stat.signal_exits;
 		}
 		if (need_resched()) {
@@ -3756,7 +4033,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 
 	up_read(&vcpu->kvm->slots_lock);
-	post_kvm_run_save(vcpu, kvm_run);
+	post_kvm_run_save(vcpu);
 
 	vapic_exit(vcpu);
 
@@ -3789,15 +4066,13 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		if (r)
 			goto out;
 	}
-#if CONFIG_HAS_IOMEM
 	if (vcpu->mmio_needed) {
 		memcpy(vcpu->mmio_data, kvm_run->mmio.data, 8);
 		vcpu->mmio_read_completed = 1;
 		vcpu->mmio_needed = 0;
 
 		down_read(&vcpu->kvm->slots_lock);
-		r = emulate_instruction(vcpu, kvm_run,
-					vcpu->arch.mmio_fault_cr2, 0,
+		r = emulate_instruction(vcpu, vcpu->arch.mmio_fault_cr2, 0,
 					EMULTYPE_NO_DECODE);
 		up_read(&vcpu->kvm->slots_lock);
 		if (r == EMULATE_DO_MMIO) {
@@ -3808,12 +4083,11 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 			goto out;
 		}
 	}
-#endif
 	if (kvm_run->exit_reason == KVM_EXIT_HYPERCALL)
 		kvm_register_write(vcpu, VCPU_REGS_RAX,
 				     kvm_run->hypercall.ret);
 
-	r = __vcpu_run(vcpu, kvm_run);
+	r = __vcpu_run(vcpu);
 
 out:
 	if (vcpu->sigset_active)
@@ -3847,13 +4121,7 @@ int kvm_arch_vcpu_ioctl_get_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 #endif
 
 	regs->rip = kvm_rip_read(vcpu);
-	regs->rflags = kvm_x86_ops->get_rflags(vcpu);
-
-	/*
-	 * Don't leak debug flags in case they were set for guest debugging
-	 */
-	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
-		regs->rflags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
+	regs->rflags = kvm_get_rflags(vcpu);
 
 	vcpu_put(vcpu);
 
@@ -3881,12 +4149,10 @@ int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
 	kvm_register_write(vcpu, VCPU_REGS_R13, regs->r13);
 	kvm_register_write(vcpu, VCPU_REGS_R14, regs->r14);
 	kvm_register_write(vcpu, VCPU_REGS_R15, regs->r15);
-
 #endif
 
 	kvm_rip_write(vcpu, regs->rip);
-	kvm_x86_ops->set_rflags(vcpu, regs->rflags);
-
+	kvm_set_rflags(vcpu, regs->rflags);
 
 	vcpu->arch.exception.pending = false;
 
@@ -4105,7 +4371,7 @@ static int is_vm86_segment(struct kvm_vcpu *vcpu, int seg)
 {
 	return (seg != VCPU_SREG_LDTR) &&
 		(seg != VCPU_SREG_TR) &&
-		(kvm_x86_ops->get_rflags(vcpu) & X86_EFLAGS_VM);
+		(kvm_get_rflags(vcpu) & X86_EFLAGS_VM);
 }
 
 int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector,
@@ -4133,7 +4399,7 @@ static void save_state_to_tss32(struct kvm_vcpu *vcpu,
 {
 	tss->cr3 = vcpu->arch.cr3;
 	tss->eip = kvm_rip_read(vcpu);
-	tss->eflags = kvm_x86_ops->get_rflags(vcpu);
+	tss->eflags = kvm_get_rflags(vcpu);
 	tss->eax = kvm_register_read(vcpu, VCPU_REGS_RAX);
 	tss->ecx = kvm_register_read(vcpu, VCPU_REGS_RCX);
 	tss->edx = kvm_register_read(vcpu, VCPU_REGS_RDX);
@@ -4157,7 +4423,7 @@ static int load_state_from_tss32(struct kvm_vcpu *vcpu,
 	kvm_set_cr3(vcpu, tss->cr3);
 
 	kvm_rip_write(vcpu, tss->eip);
-	kvm_x86_ops->set_rflags(vcpu, tss->eflags | 2);
+	kvm_set_rflags(vcpu, tss->eflags | 2);
 
 	kvm_register_write(vcpu, VCPU_REGS_RAX, tss->eax);
 	kvm_register_write(vcpu, VCPU_REGS_RCX, tss->ecx);
@@ -4195,7 +4461,7 @@ static void save_state_to_tss16(struct kvm_vcpu *vcpu,
 				struct tss_segment_16 *tss)
 {
 	tss->ip = kvm_rip_read(vcpu);
-	tss->flag = kvm_x86_ops->get_rflags(vcpu);
+	tss->flag = kvm_get_rflags(vcpu);
 	tss->ax = kvm_register_read(vcpu, VCPU_REGS_RAX);
 	tss->cx = kvm_register_read(vcpu, VCPU_REGS_RCX);
 	tss->dx = kvm_register_read(vcpu, VCPU_REGS_RDX);
@@ -4210,14 +4476,13 @@ static void save_state_to_tss16(struct kvm_vcpu *vcpu,
 	tss->ss = get_segment_selector(vcpu, VCPU_SREG_SS);
 	tss->ds = get_segment_selector(vcpu, VCPU_SREG_DS);
 	tss->ldt = get_segment_selector(vcpu, VCPU_SREG_LDTR);
-	tss->prev_task_link = get_segment_selector(vcpu, VCPU_SREG_TR);
 }
 
 static int load_state_from_tss16(struct kvm_vcpu *vcpu,
 				 struct tss_segment_16 *tss)
 {
 	kvm_rip_write(vcpu, tss->ip);
-	kvm_x86_ops->set_rflags(vcpu, tss->flag | 2);
+	kvm_set_rflags(vcpu, tss->flag | 2);
 	kvm_register_write(vcpu, VCPU_REGS_RAX, tss->ax);
 	kvm_register_write(vcpu, VCPU_REGS_RCX, tss->cx);
 	kvm_register_write(vcpu, VCPU_REGS_RDX, tss->dx);
@@ -4363,15 +4628,10 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 	}
 
 	if (reason == TASK_SWITCH_IRET) {
-		u32 eflags = kvm_x86_ops->get_rflags(vcpu);
-		kvm_x86_ops->set_rflags(vcpu, eflags & ~X86_EFLAGS_NT);
+		u32 eflags = kvm_get_rflags(vcpu);
+		kvm_set_rflags(vcpu, eflags & ~X86_EFLAGS_NT);
 	}
 
-	/* set back link to prev task only if NT bit is set in eflags
-	   note that old_tss_sel is not used afetr this point */
-	if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE)
-		old_tss_sel = 0xffff;
-
 	/* set back link to prev task only if NT bit is set in eflags
 	   note that old_tss_sel is not used afetr this point */
 	if (reason != TASK_SWITCH_CALL && reason != TASK_SWITCH_GATE)
@@ -4385,8 +4645,8 @@ int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason)
 					 old_tss_base, &nseg_desc);
 
 	if (reason == TASK_SWITCH_CALL || reason == TASK_SWITCH_GATE) {
-		u32 eflags = kvm_x86_ops->get_rflags(vcpu);
-		kvm_x86_ops->set_rflags(vcpu, eflags | X86_EFLAGS_NT);
+		u32 eflags = kvm_get_rflags(vcpu);
+		kvm_set_rflags(vcpu, eflags | X86_EFLAGS_NT);
 	}
 
 	if (reason != TASK_SWITCH_IRET) {
@@ -4438,8 +4698,10 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 	mmu_reset_needed |= vcpu->arch.cr4 != sregs->cr4;
 	kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
-	if (!is_long_mode(vcpu) && is_pae(vcpu))
+	if (!is_long_mode(vcpu) && is_pae(vcpu)) {
 		load_pdptrs(vcpu, vcpu->arch.cr3);
+		mmu_reset_needed = 1;
+	}
 
 	if (mmu_reset_needed)
 		kvm_mmu_reset_context(vcpu);
@@ -4480,12 +4742,32 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 					struct kvm_guest_debug *dbg)
 {
+	unsigned long rflags;
 	int i, r;
 
 	vcpu_load(vcpu);
 
-	if ((dbg->control & (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) ==
-	    (KVM_GUESTDBG_ENABLE | KVM_GUESTDBG_USE_HW_BP)) {
+	if (dbg->control & (KVM_GUESTDBG_INJECT_DB | KVM_GUESTDBG_INJECT_BP)) {
+		r = -EBUSY;
+		if (vcpu->arch.exception.pending)
+			goto unlock_out;
+		if (dbg->control & KVM_GUESTDBG_INJECT_DB)
+			kvm_queue_exception(vcpu, DB_VECTOR);
+		else
+			kvm_queue_exception(vcpu, BP_VECTOR);
+	}
+
+	/*
+	 * Read rflags as long as potentially injected trace flags are still
+	 * filtered out.
+	 */
+	rflags = kvm_get_rflags(vcpu);
+
+	vcpu->guest_debug = dbg->control;
+	if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE))
+		vcpu->guest_debug = 0;
+
+	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
 		for (i = 0; i < KVM_NR_DB_REGS; ++i)
 			vcpu->arch.eff_db[i] = dbg->arch.debugreg[i];
 		vcpu->arch.switch_db_regs =
@@ -4496,13 +4778,23 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 		vcpu->arch.switch_db_regs = (vcpu->arch.dr7 & DR7_BP_EN_MASK);
 	}
 
-	r = kvm_x86_ops->set_guest_debug(vcpu, dbg);
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+		vcpu->arch.singlestep_cs =
+			get_segment_selector(vcpu, VCPU_SREG_CS);
+		vcpu->arch.singlestep_rip = kvm_rip_read(vcpu);
+	}
 
-	if (dbg->control & KVM_GUESTDBG_INJECT_DB)
-		kvm_queue_exception(vcpu, DB_VECTOR);
-	else if (dbg->control & KVM_GUESTDBG_INJECT_BP)
-		kvm_queue_exception(vcpu, BP_VECTOR);
+	/*
+	 * Trigger an rflags update that will inject or remove the trace
+	 * flags.
+	 */
+	kvm_set_rflags(vcpu, rflags);
 
+	kvm_x86_ops->set_guest_debug(vcpu, dbg);
+
+	r = 0;
+
+unlock_out:
 	vcpu_put(vcpu);
 
 	return r;
@@ -4703,14 +4995,26 @@ int kvm_arch_vcpu_reset(struct kvm_vcpu *vcpu)
 	return kvm_x86_ops->vcpu_reset(vcpu);
 }
 
-void kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void *garbage)
 {
-	kvm_x86_ops->hardware_enable(garbage);
+	/*
+	 * Since this may be called from a hotplug notifcation,
+	 * we can't get the CPU frequency directly.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+		int cpu = raw_smp_processor_id();
+		per_cpu(cpu_tsc_khz, cpu) = 0;
+	}
+
+	kvm_shared_msr_cpu_online();
+
+	return kvm_x86_ops->hardware_enable(garbage);
 }
 
 void kvm_arch_hardware_disable(void *garbage)
 {
 	kvm_x86_ops->hardware_disable(garbage);
+	drop_user_return_notifiers(garbage);
 }
 
 int kvm_arch_hardware_setup(void)
@@ -4948,8 +5252,36 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu)
 	return kvm_x86_ops->interrupt_allowed(vcpu);
 }
 
+unsigned long kvm_get_rflags(struct kvm_vcpu *vcpu)
+{
+	unsigned long rflags;
+
+	rflags = kvm_x86_ops->get_rflags(vcpu);
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		rflags &= ~(unsigned long)(X86_EFLAGS_TF | X86_EFLAGS_RF);
+	return rflags;
+}
+EXPORT_SYMBOL_GPL(kvm_get_rflags);
+
+void kvm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
+{
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP &&
+	    vcpu->arch.singlestep_cs ==
+			get_segment_selector(vcpu, VCPU_SREG_CS) &&
+	    vcpu->arch.singlestep_rip == kvm_rip_read(vcpu))
+		rflags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
+	kvm_x86_ops->set_rflags(vcpu, rflags);
+}
+EXPORT_SYMBOL_GPL(kvm_set_rflags);
+
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_msr);
 EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_cr);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmrun);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_vmexit_inject);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intr_vmexit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_invlpga);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_skinit);