Merge branch 'master' of /home/davem/src/GIT/linux-2.6/

1 files changed, 226 insertions, 167 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 7611af576829..bb481330716f 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -91,6 +91,7 @@ struct vcpu_vmx {
 	} rmode;
 	int vpid;
 	bool emulation_required;
+	enum emulation_result invalid_state_emulation_result;
 
 	/* Support for vnmi-less CPUs */
 	int soft_vnmi_blocked;
@@ -189,21 +190,21 @@ static inline int is_page_fault(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
 			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
+		(INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
 }
 
 static inline int is_no_device(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
 			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
+		(INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
 }
 
 static inline int is_invalid_opcode(u32 intr_info)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
 			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
+		(INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
 }
 
 static inline int is_external_interrupt(u32 intr_info)
@@ -480,8 +481,13 @@ static void update_exception_bitmap(struct kvm_vcpu *vcpu)
 	eb = (1u << PF_VECTOR) | (1u << UD_VECTOR);
 	if (!vcpu->fpu_active)
 		eb |= 1u << NM_VECTOR;
-	if (vcpu->guest_debug.enabled)
-		eb |= 1u << DB_VECTOR;
+	if (vcpu->guest_debug & KVM_GUESTDBG_ENABLE) {
+		if (vcpu->guest_debug &
+		    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+			eb |= 1u << DB_VECTOR;
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+			eb |= 1u << BP_VECTOR;
+	}
 	if (vcpu->arch.rmode.active)
 		eb = ~0;
 	if (vm_need_ept())
@@ -747,29 +753,33 @@ static void vmx_queue_exception(struct kvm_vcpu *vcpu, unsigned nr,
 				bool has_error_code, u32 error_code)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	u32 intr_info = nr | INTR_INFO_VALID_MASK;
 
-	if (has_error_code)
+	if (has_error_code) {
 		vmcs_write32(VM_ENTRY_EXCEPTION_ERROR_CODE, error_code);
+		intr_info |= INTR_INFO_DELIVER_CODE_MASK;
+	}
 
 	if (vcpu->arch.rmode.active) {
 		vmx->rmode.irq.pending = true;
 		vmx->rmode.irq.vector = nr;
 		vmx->rmode.irq.rip = kvm_rip_read(vcpu);
-		if (nr == BP_VECTOR)
+		if (nr == BP_VECTOR || nr == OF_VECTOR)
 			vmx->rmode.irq.rip++;
-		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
-			     nr | INTR_TYPE_SOFT_INTR
-			     | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0)
-			     | INTR_INFO_VALID_MASK);
+		intr_info |= INTR_TYPE_SOFT_INTR;
+		vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
 		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1);
 		kvm_rip_write(vcpu, vmx->rmode.irq.rip - 1);
 		return;
 	}
 
-	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD,
-		     nr | INTR_TYPE_EXCEPTION
-		     | (has_error_code ? INTR_INFO_DELIVER_CODE_MASK : 0)
-		     | INTR_INFO_VALID_MASK);
+	if (nr == BP_VECTOR || nr == OF_VECTOR) {
+		vmcs_write32(VM_ENTRY_INSTRUCTION_LEN, 1);
+		intr_info |= INTR_TYPE_SOFT_EXCEPTION;
+	} else
+		intr_info |= INTR_TYPE_HARD_EXCEPTION;
+
+	vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
 }
 
 static bool vmx_exception_injected(struct kvm_vcpu *vcpu)
@@ -856,11 +866,8 @@ static u64 guest_read_tsc(void)
  * writes 'guest_tsc' into guest's timestamp counter "register"
  * guest_tsc = host_tsc + tsc_offset ==> tsc_offset = guest_tsc - host_tsc
  */
-static void guest_write_tsc(u64 guest_tsc)
+static void guest_write_tsc(u64 guest_tsc, u64 host_tsc)
 {
-	u64 host_tsc;
-
-	rdtscll(host_tsc);
 	vmcs_write64(TSC_OFFSET, guest_tsc - host_tsc);
 }
 
@@ -925,14 +932,15 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct kvm_msr_entry *msr;
+	u64 host_tsc;
 	int ret = 0;
 
 	switch (msr_index) {
-#ifdef CONFIG_X86_64
 	case MSR_EFER:
 		vmx_load_host_state(vmx);
 		ret = kvm_set_msr_common(vcpu, msr_index, data);
 		break;
+#ifdef CONFIG_X86_64
 	case MSR_FS_BASE:
 		vmcs_writel(GUEST_FS_BASE, data);
 		break;
@@ -950,7 +958,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
 	case MSR_IA32_TIME_STAMP_COUNTER:
-		guest_write_tsc(data);
+		rdtscll(host_tsc);
+		guest_write_tsc(data, host_tsc);
 		break;
 	case MSR_P6_PERFCTR0:
 	case MSR_P6_PERFCTR1:
@@ -999,40 +1008,28 @@ static void vmx_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
 	}
 }
 
-static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_debug_guest *dbg)
+static int set_guest_debug(struct kvm_vcpu *vcpu, struct kvm_guest_debug *dbg)
 {
-	unsigned long dr7 = 0x400;
-	int old_singlestep;
-
-	old_singlestep = vcpu->guest_debug.singlestep;
-
-	vcpu->guest_debug.enabled = dbg->enabled;
-	if (vcpu->guest_debug.enabled) {
-		int i;
+	int old_debug = vcpu->guest_debug;
+	unsigned long flags;
 
-		dr7 |= 0x200;  /* exact */
-		for (i = 0; i < 4; ++i) {
-			if (!dbg->breakpoints[i].enabled)
-				continue;
-			vcpu->guest_debug.bp[i] = dbg->breakpoints[i].address;
-			dr7 |= 2 << (i*2);    /* global enable */
-			dr7 |= 0 << (i*4+16); /* execution breakpoint */
-		}
+	vcpu->guest_debug = dbg->control;
+	if (!(vcpu->guest_debug & KVM_GUESTDBG_ENABLE))
+		vcpu->guest_debug = 0;
 
-		vcpu->guest_debug.singlestep = dbg->singlestep;
-	} else
-		vcpu->guest_debug.singlestep = 0;
-
-	if (old_singlestep && !vcpu->guest_debug.singlestep) {
-		unsigned long flags;
+	if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)
+		vmcs_writel(GUEST_DR7, dbg->arch.debugreg[7]);
+	else
+		vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
 
-		flags = vmcs_readl(GUEST_RFLAGS);
+	flags = vmcs_readl(GUEST_RFLAGS);
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		flags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
+	else if (old_debug & KVM_GUESTDBG_SINGLESTEP)
 		flags &= ~(X86_EFLAGS_TF | X86_EFLAGS_RF);
-		vmcs_writel(GUEST_RFLAGS, flags);
-	}
+	vmcs_writel(GUEST_RFLAGS, flags);
 
 	update_exception_bitmap(vcpu);
-	vmcs_writel(GUEST_DR7, dr7);
 
 	return 0;
 }
@@ -1433,6 +1430,29 @@ continue_rmode:
 	init_rmode(vcpu->kvm);
 }
 
+static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);
+
+	vcpu->arch.shadow_efer = efer;
+	if (!msr)
+		return;
+	if (efer & EFER_LMA) {
+		vmcs_write32(VM_ENTRY_CONTROLS,
+			     vmcs_read32(VM_ENTRY_CONTROLS) |
+			     VM_ENTRY_IA32E_MODE);
+		msr->data = efer;
+	} else {
+		vmcs_write32(VM_ENTRY_CONTROLS,
+			     vmcs_read32(VM_ENTRY_CONTROLS) &
+			     ~VM_ENTRY_IA32E_MODE);
+
+		msr->data = efer & ~EFER_LME;
+	}
+	setup_msrs(vmx);
+}
+
 #ifdef CONFIG_X86_64
 
 static void enter_lmode(struct kvm_vcpu *vcpu)
@@ -1447,13 +1467,8 @@ static void enter_lmode(struct kvm_vcpu *vcpu)
 			     (guest_tr_ar & ~AR_TYPE_MASK)
 			     | AR_TYPE_BUSY_64_TSS);
 	}
-
 	vcpu->arch.shadow_efer |= EFER_LMA;
-
-	find_msr_entry(to_vmx(vcpu), MSR_EFER)->data |= EFER_LMA | EFER_LME;
-	vmcs_write32(VM_ENTRY_CONTROLS,
-		     vmcs_read32(VM_ENTRY_CONTROLS)
-		     | VM_ENTRY_IA32E_MODE);
+	vmx_set_efer(vcpu, vcpu->arch.shadow_efer);
 }
 
 static void exit_lmode(struct kvm_vcpu *vcpu)
@@ -1612,30 +1627,6 @@ static void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	vmcs_writel(GUEST_CR4, hw_cr4);
 }
 
-static void vmx_set_efer(struct kvm_vcpu *vcpu, u64 efer)
-{
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	struct kvm_msr_entry *msr = find_msr_entry(vmx, MSR_EFER);
-
-	vcpu->arch.shadow_efer = efer;
-	if (!msr)
-		return;
-	if (efer & EFER_LMA) {
-		vmcs_write32(VM_ENTRY_CONTROLS,
-				     vmcs_read32(VM_ENTRY_CONTROLS) |
-				     VM_ENTRY_IA32E_MODE);
-		msr->data = efer;
-
-	} else {
-		vmcs_write32(VM_ENTRY_CONTROLS,
-				     vmcs_read32(VM_ENTRY_CONTROLS) &
-				     ~VM_ENTRY_IA32E_MODE);
-
-		msr->data = efer & ~EFER_LME;
-	}
-	setup_msrs(vmx);
-}
-
 static u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg)
 {
 	struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
@@ -1653,7 +1644,7 @@ static void vmx_get_segment(struct kvm_vcpu *vcpu,
 	var->limit = vmcs_read32(sf->limit);
 	var->selector = vmcs_read16(sf->selector);
 	ar = vmcs_read32(sf->ar_bytes);
-	if (ar & AR_UNUSABLE_MASK)
+	if ((ar & AR_UNUSABLE_MASK) && !emulate_invalid_guest_state)
 		ar = 0;
 	var->type = ar & 15;
 	var->s = (ar >> 4) & 1;
@@ -1788,14 +1779,16 @@ static bool code_segment_valid(struct kvm_vcpu *vcpu)
 	vmx_get_segment(vcpu, &cs, VCPU_SREG_CS);
 	cs_rpl = cs.selector & SELECTOR_RPL_MASK;
 
+	if (cs.unusable)
+		return false;
 	if (~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_ACCESSES_MASK))
 		return false;
 	if (!cs.s)
 		return false;
-	if (!(~cs.type & (AR_TYPE_CODE_MASK|AR_TYPE_WRITEABLE_MASK))) {
+	if (cs.type & AR_TYPE_WRITEABLE_MASK) {
 		if (cs.dpl > cs_rpl)
 			return false;
-	} else if (cs.type & AR_TYPE_CODE_MASK) {
+	} else {
 		if (cs.dpl != cs_rpl)
 			return false;
 	}
@@ -1814,7 +1807,9 @@ static bool stack_segment_valid(struct kvm_vcpu *vcpu)
 	vmx_get_segment(vcpu, &ss, VCPU_SREG_SS);
 	ss_rpl = ss.selector & SELECTOR_RPL_MASK;
 
-	if ((ss.type != 3) || (ss.type != 7))
+	if (ss.unusable)
+		return true;
+	if (ss.type != 3 && ss.type != 7)
 		return false;
 	if (!ss.s)
 		return false;
@@ -1834,6 +1829,8 @@ static bool data_segment_valid(struct kvm_vcpu *vcpu, int seg)
 	vmx_get_segment(vcpu, &var, seg);
 	rpl = var.selector & SELECTOR_RPL_MASK;
 
+	if (var.unusable)
+		return true;
 	if (!var.s)
 		return false;
 	if (!var.present)
@@ -1855,9 +1852,11 @@ static bool tr_valid(struct kvm_vcpu *vcpu)
 
 	vmx_get_segment(vcpu, &tr, VCPU_SREG_TR);
 
+	if (tr.unusable)
+		return false;
 	if (tr.selector & SELECTOR_TI_MASK)	/* TI = 1 */
 		return false;
-	if ((tr.type != 3) || (tr.type != 11)) /* TODO: Check if guest is in IA32e mode */
+	if (tr.type != 3 && tr.type != 11) /* TODO: Check if guest is in IA32e mode */
 		return false;
 	if (!tr.present)
 		return false;
@@ -1871,6 +1870,8 @@ static bool ldtr_valid(struct kvm_vcpu *vcpu)
 
 	vmx_get_segment(vcpu, &ldtr, VCPU_SREG_LDTR);
 
+	if (ldtr.unusable)
+		return true;
 	if (ldtr.selector & SELECTOR_TI_MASK)	/* TI = 1 */
 		return false;
 	if (ldtr.type != 2)
@@ -2112,7 +2113,7 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 {
 	u32 host_sysenter_cs, msr_low, msr_high;
 	u32 junk;
-	u64 host_pat;
+	u64 host_pat, tsc_this, tsc_base;
 	unsigned long a;
 	struct descriptor_table dt;
 	int i;
@@ -2240,6 +2241,12 @@ static int vmx_vcpu_setup(struct vcpu_vmx *vmx)
 	vmcs_writel(CR0_GUEST_HOST_MASK, ~0UL);
 	vmcs_writel(CR4_GUEST_HOST_MASK, KVM_GUEST_CR4_MASK);
 
+	tsc_base = vmx->vcpu.kvm->arch.vm_init_tsc;
+	rdtscll(tsc_this);
+	if (tsc_this < vmx->vcpu.kvm->arch.vm_init_tsc)
+		tsc_base = tsc_this;
+
+	guest_write_tsc(0, tsc_base);
 
 	return 0;
 }
@@ -2319,7 +2326,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 		kvm_rip_write(vcpu, 0);
 	kvm_register_write(vcpu, VCPU_REGS_RSP, 0);
 
-	/* todo: dr0 = dr1 = dr2 = dr3 = 0; dr6 = 0xffff0ff0 */
 	vmcs_writel(GUEST_DR7, 0x400);
 
 	vmcs_writel(GUEST_GDTR_BASE, 0);
@@ -2332,8 +2338,6 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 	vmcs_write32(GUEST_INTERRUPTIBILITY_INFO, 0);
 	vmcs_write32(GUEST_PENDING_DBG_EXCEPTIONS, 0);
 
-	guest_write_tsc(0);
-
 	/* Special registers */
 	vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
 
@@ -2486,6 +2490,11 @@ static void do_interrupt_requests(struct kvm_vcpu *vcpu,
 {
 	vmx_update_window_states(vcpu);
 
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
+				GUEST_INTR_STATE_STI |
+				GUEST_INTR_STATE_MOV_SS);
+
 	if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) {
 		if (vcpu->arch.interrupt.pending) {
 			enable_nmi_window(vcpu);
@@ -2536,24 +2545,6 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
 	return 0;
 }
 
-static void kvm_guest_debug_pre(struct kvm_vcpu *vcpu)
-{
-	struct kvm_guest_debug *dbg = &vcpu->guest_debug;
-
-	set_debugreg(dbg->bp[0], 0);
-	set_debugreg(dbg->bp[1], 1);
-	set_debugreg(dbg->bp[2], 2);
-	set_debugreg(dbg->bp[3], 3);
-
-	if (dbg->singlestep) {
-		unsigned long flags;
-
-		flags = vmcs_readl(GUEST_RFLAGS);
-		flags |= X86_EFLAGS_TF | X86_EFLAGS_RF;
-		vmcs_writel(GUEST_RFLAGS, flags);
-	}
-}
-
 static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 				  int vec, u32 err_code)
 {
@@ -2570,9 +2561,17 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 	 *        the required debugging infrastructure rework.
 	 */
 	switch (vec) {
-	case DE_VECTOR:
 	case DB_VECTOR:
+		if (vcpu->guest_debug &
+		    (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+			return 0;
+		kvm_queue_exception(vcpu, vec);
+		return 1;
 	case BP_VECTOR:
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+			return 0;
+		/* fall through */
+	case DE_VECTOR:
 	case OF_VECTOR:
 	case BR_VECTOR:
 	case UD_VECTOR:
@@ -2589,8 +2588,8 @@ static int handle_rmode_exception(struct kvm_vcpu *vcpu,
 static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u32 intr_info, error_code;
-	unsigned long cr2, rip;
+	u32 intr_info, ex_no, error_code;
+	unsigned long cr2, rip, dr6;
 	u32 vect_info;
 	enum emulation_result er;
 
@@ -2649,14 +2648,30 @@ static int handle_exception(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		return 1;
 	}
 
-	if ((intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK)) ==
-	    (INTR_TYPE_EXCEPTION | 1)) {
+	ex_no = intr_info & INTR_INFO_VECTOR_MASK;
+	switch (ex_no) {
+	case DB_VECTOR:
+		dr6 = vmcs_readl(EXIT_QUALIFICATION);
+		if (!(vcpu->guest_debug &
+		      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) {
+			vcpu->arch.dr6 = dr6 | DR6_FIXED_1;
+			kvm_queue_exception(vcpu, DB_VECTOR);
+			return 1;
+		}
+		kvm_run->debug.arch.dr6 = dr6 | DR6_FIXED_1;
+		kvm_run->debug.arch.dr7 = vmcs_readl(GUEST_DR7);
+		/* fall through */
+	case BP_VECTOR:
 		kvm_run->exit_reason = KVM_EXIT_DEBUG;
-		return 0;
+		kvm_run->debug.arch.pc = vmcs_readl(GUEST_CS_BASE) + rip;
+		kvm_run->debug.arch.exception = ex_no;
+		break;
+	default:
+		kvm_run->exit_reason = KVM_EXIT_EXCEPTION;
+		kvm_run->ex.exception = ex_no;
+		kvm_run->ex.error_code = error_code;
+		break;
 	}
-	kvm_run->exit_reason = KVM_EXIT_EXCEPTION;
-	kvm_run->ex.exception = intr_info & INTR_INFO_VECTOR_MASK;
-	kvm_run->ex.error_code = error_code;
 	return 0;
 }
 
@@ -2677,7 +2692,7 @@ static int handle_triple_fault(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	unsigned long exit_qualification;
-	int size, down, in, string, rep;
+	int size, in, string;
 	unsigned port;
 
 	++vcpu->stat.io_exits;
@@ -2693,8 +2708,6 @@ static int handle_io(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 
 	size = (exit_qualification & 7) + 1;
 	in = (exit_qualification & 8) != 0;
-	down = (vmcs_readl(GUEST_RFLAGS) & X86_EFLAGS_DF) != 0;
-	rep = (exit_qualification & 32) != 0;
 	port = exit_qualification >> 16;
 
 	skip_emulated_instruction(vcpu);
@@ -2795,21 +2808,44 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	unsigned long val;
 	int dr, reg;
 
-	/*
-	 * FIXME: this code assumes the host is debugging the guest.
-	 *        need to deal with guest debugging itself too.
-	 */
+	dr = vmcs_readl(GUEST_DR7);
+	if (dr & DR7_GD) {
+		/*
+		 * As the vm-exit takes precedence over the debug trap, we
+		 * need to emulate the latter, either for the host or the
+		 * guest debugging itself.
+		 */
+		if (vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP) {
+			kvm_run->debug.arch.dr6 = vcpu->arch.dr6;
+			kvm_run->debug.arch.dr7 = dr;
+			kvm_run->debug.arch.pc =
+				vmcs_readl(GUEST_CS_BASE) +
+				vmcs_readl(GUEST_RIP);
+			kvm_run->debug.arch.exception = DB_VECTOR;
+			kvm_run->exit_reason = KVM_EXIT_DEBUG;
+			return 0;
+		} else {
+			vcpu->arch.dr7 &= ~DR7_GD;
+			vcpu->arch.dr6 |= DR6_BD;
+			vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
+			kvm_queue_exception(vcpu, DB_VECTOR);
+			return 1;
+		}
+	}
+
 	exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-	dr = exit_qualification & 7;
-	reg = (exit_qualification >> 8) & 15;
-	if (exit_qualification & 16) {
-		/* mov from dr */
+	dr = exit_qualification & DEBUG_REG_ACCESS_NUM;
+	reg = DEBUG_REG_ACCESS_REG(exit_qualification);
+	if (exit_qualification & TYPE_MOV_FROM_DR) {
 		switch (dr) {
+		case 0 ... 3:
+			val = vcpu->arch.db[dr];
+			break;
 		case 6:
-			val = 0xffff0ff0;
+			val = vcpu->arch.dr6;
 			break;
 		case 7:
-			val = 0x400;
+			val = vcpu->arch.dr7;
 			break;
 		default:
 			val = 0;
@@ -2817,7 +2853,38 @@ static int handle_dr(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		kvm_register_write(vcpu, reg, val);
 		KVMTRACE_2D(DR_READ, vcpu, (u32)dr, (u32)val, handler);
 	} else {
-		/* mov to dr */
+		val = vcpu->arch.regs[reg];
+		switch (dr) {
+		case 0 ... 3:
+			vcpu->arch.db[dr] = val;
+			if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP))
+				vcpu->arch.eff_db[dr] = val;
+			break;
+		case 4 ... 5:
+			if (vcpu->arch.cr4 & X86_CR4_DE)
+				kvm_queue_exception(vcpu, UD_VECTOR);
+			break;
+		case 6:
+			if (val & 0xffffffff00000000ULL) {
+				kvm_queue_exception(vcpu, GP_VECTOR);
+				break;
+			}
+			vcpu->arch.dr6 = (val & DR6_VOLATILE) | DR6_FIXED_1;
+			break;
+		case 7:
+			if (val & 0xffffffff00000000ULL) {
+				kvm_queue_exception(vcpu, GP_VECTOR);
+				break;
+			}
+			vcpu->arch.dr7 = (val & DR7_VOLATILE) | DR7_FIXED_1;
+			if (!(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP)) {
+				vmcs_writel(GUEST_DR7, vcpu->arch.dr7);
+				vcpu->arch.switch_db_regs =
+					(val & DR7_BP_EN_MASK);
+			}
+			break;
+		}
+		KVMTRACE_2D(DR_WRITE, vcpu, (u32)dr, (u32)val, handler);
 	}
 	skip_emulated_instruction(vcpu);
 	return 1;
@@ -2968,17 +3035,25 @@ static int handle_task_switch(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 	tss_selector = exit_qualification;
 
-	return kvm_task_switch(vcpu, tss_selector, reason);
+	if (!kvm_task_switch(vcpu, tss_selector, reason))
+		return 0;
+
+	/* clear all local breakpoint enable flags */
+	vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55);
+
+	/*
+	 * TODO: What about debug traps on tss switch?
+	 *       Are we supposed to inject them and update dr6?
+	 */
+
+	return 1;
 }
 
 static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	u64 exit_qualification;
-	enum emulation_result er;
 	gpa_t gpa;
-	unsigned long hva;
 	int gla_validity;
-	int r;
 
 	exit_qualification = vmcs_read64(EXIT_QUALIFICATION);
 
@@ -3001,32 +3076,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	}
 
 	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
-	hva = gfn_to_hva(vcpu->kvm, gpa >> PAGE_SHIFT);
-	if (!kvm_is_error_hva(hva)) {
-		r = kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0);
-		if (r < 0) {
-			printk(KERN_ERR "EPT: Not enough memory!\n");
-			return -ENOMEM;
-		}
-		return 1;
-	} else {
-		/* must be MMIO */
-		er = emulate_instruction(vcpu, kvm_run, 0, 0, 0);
-
-		if (er == EMULATE_FAIL) {
-			printk(KERN_ERR
-			 "EPT: Fail to handle EPT violation vmexit!er is %d\n",
-			 er);
-			printk(KERN_ERR "EPT: GPA: 0x%lx, GVA: 0x%lx\n",
-			 (long unsigned int)vmcs_read64(GUEST_PHYSICAL_ADDRESS),
-			 (long unsigned int)vmcs_read64(GUEST_LINEAR_ADDRESS));
-			printk(KERN_ERR "EPT: Exit qualification is 0x%lx\n",
-				(long unsigned int)exit_qualification);
-			return -ENOTSUPP;
-		} else if (er == EMULATE_DO_MMIO)
-			return 0;
-	}
-	return 1;
+	return kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0);
 }
 
 static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
@@ -3046,7 +3096,7 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
 				struct kvm_run *kvm_run)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	int err;
+	enum emulation_result err = EMULATE_DONE;
 
 	preempt_enable();
 	local_irq_enable();
@@ -3071,10 +3121,7 @@ static void handle_invalid_guest_state(struct kvm_vcpu *vcpu,
 	local_irq_disable();
 	preempt_disable();
 
-	/* Guest state should be valid now except if we need to
-	 * emulate an MMIO */
-	if (guest_state_valid(vcpu))
-		vmx->emulation_required = 0;
+	vmx->invalid_state_emulation_result = err;
 }
 
 /*
@@ -3123,8 +3170,11 @@ static int kvm_handle_exit(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 
 	/* If we need to emulate an MMIO from handle_invalid_guest_state
 	 * we just return 0 */
-	if (vmx->emulation_required && emulate_invalid_guest_state)
-		return 0;
+	if (vmx->emulation_required && emulate_invalid_guest_state) {
+		if (guest_state_valid(vcpu))
+			vmx->emulation_required = 0;
+		return vmx->invalid_state_emulation_result != EMULATE_DO_MMIO;
+	}
 
 	/* Access CR3 don't cause VMExit in paging mode, so we need
 	 * to sync with guest real CR3. */
@@ -3238,7 +3288,8 @@ static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
 			vmx->vcpu.arch.nmi_injected = false;
 	}
 	kvm_clear_exception_queue(&vmx->vcpu);
-	if (idtv_info_valid && type == INTR_TYPE_EXCEPTION) {
+	if (idtv_info_valid && (type == INTR_TYPE_HARD_EXCEPTION ||
+				type == INTR_TYPE_SOFT_EXCEPTION)) {
 		if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) {
 			error = vmcs_read32(IDT_VECTORING_ERROR_CODE);
 			kvm_queue_exception_e(&vmx->vcpu, vector, error);
@@ -3259,6 +3310,11 @@ static void vmx_intr_assist(struct kvm_vcpu *vcpu)
 
 	vmx_update_window_states(vcpu);
 
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)
+		vmcs_clear_bits(GUEST_INTERRUPTIBILITY_INFO,
+				GUEST_INTR_STATE_STI |
+				GUEST_INTR_STATE_MOV_SS);
+
 	if (vcpu->arch.nmi_pending && !vcpu->arch.nmi_injected) {
 		if (vcpu->arch.interrupt.pending) {
 			enable_nmi_window(vcpu);
@@ -3347,6 +3403,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	 */
 	vmcs_writel(HOST_CR0, read_cr0());
 
+	set_debugreg(vcpu->arch.dr6, 6);
+
 	asm(
 		/* Store host registers */
 		"push %%"R"dx; push %%"R"bp;"
@@ -3441,6 +3499,8 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP));
 	vcpu->arch.regs_dirty = 0;
 
+	get_debugreg(vcpu->arch.dr6, 6);
+
 	vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
 	if (vmx->rmode.irq.pending)
 		fixup_rmode_irq(vmx);
@@ -3595,7 +3655,6 @@ static struct kvm_x86_ops vmx_x86_ops = {
 	.vcpu_put = vmx_vcpu_put,
 
 	.set_guest_debug = set_guest_debug,
-	.guest_debug_pre = kvm_guest_debug_pre,
 	.get_msr = vmx_get_msr,
 	.set_msr = vmx_set_msr,
 	.get_segment_base = vmx_get_segment_base,