1 files changed, 92 insertions, 50 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e2951b6edbbc..5e45c2731a5d 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -596,6 +596,8 @@ struct vcpu_vmx {
 	/* Support for PML */
 #define PML_ENTITY_NUM		512
 	struct page *pml_pg;
+
+	u64 current_tsc_ratio;
 };
 
 enum segment_cache_field {
@@ -861,7 +863,6 @@ static unsigned long nested_ept_get_cr3(struct kvm_vcpu *vcpu);
 static u64 construct_eptp(unsigned long root_hpa);
 static void kvm_cpu_vmxon(u64 addr);
 static void kvm_cpu_vmxoff(void);
-static bool vmx_mpx_supported(void);
 static bool vmx_xsaves_supported(void);
 static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr);
 static void vmx_set_segment(struct kvm_vcpu *vcpu,
@@ -961,25 +962,36 @@ static const u32 vmx_msr_index[] = {
 	MSR_EFER, MSR_TSC_AUX, MSR_STAR,
 };
 
-static inline bool is_page_fault(u32 intr_info)
+static inline bool is_exception_n(u32 intr_info, u8 vector)
 {
 	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
 			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | PF_VECTOR | INTR_INFO_VALID_MASK);
+		(INTR_TYPE_HARD_EXCEPTION | vector | INTR_INFO_VALID_MASK);
+}
+
+static inline bool is_debug(u32 intr_info)
+{
+	return is_exception_n(intr_info, DB_VECTOR);
+}
+
+static inline bool is_breakpoint(u32 intr_info)
+{
+	return is_exception_n(intr_info, BP_VECTOR);
+}
+
+static inline bool is_page_fault(u32 intr_info)
+{
+	return is_exception_n(intr_info, PF_VECTOR);
 }
 
 static inline bool is_no_device(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
-			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | NM_VECTOR | INTR_INFO_VALID_MASK);
+	return is_exception_n(intr_info, NM_VECTOR);
 }
 
 static inline bool is_invalid_opcode(u32 intr_info)
 {
-	return (intr_info & (INTR_INFO_INTR_TYPE_MASK | INTR_INFO_VECTOR_MASK |
-			     INTR_INFO_VALID_MASK)) ==
-		(INTR_TYPE_HARD_EXCEPTION | UD_VECTOR | INTR_INFO_VALID_MASK);
+	return is_exception_n(intr_info, UD_VECTOR);
 }
 
 static inline bool is_external_interrupt(u32 intr_info)
@@ -1811,6 +1823,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 			return;
 		}
 		break;
+	case MSR_IA32_PEBS_ENABLE:
+		/* PEBS needs a quiescent period after being disabled (to write
+		 * a record).  Disabling PEBS through VMX MSR swapping doesn't
+		 * provide that period, so a CPU could write host's record into
+		 * guest's memory.
+		 */
+		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 	}
 
 	for (i = 0; i < m->nr; ++i)
@@ -1848,26 +1867,31 @@ static void reload_tss(void)
 
 static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 {
-	u64 guest_efer;
-	u64 ignore_bits;
+	u64 guest_efer = vmx->vcpu.arch.efer;
+	u64 ignore_bits = 0;
 
-	guest_efer = vmx->vcpu.arch.efer;
+	if (!enable_ept) {
+		/*
+		 * NX is needed to handle CR0.WP=1, CR4.SMEP=1.  Testing
+		 * host CPUID is more efficient than testing guest CPUID
+		 * or CR4.  Host SMEP is anyway a requirement for guest SMEP.
+		 */
+		if (boot_cpu_has(X86_FEATURE_SMEP))
+			guest_efer |= EFER_NX;
+		else if (!(guest_efer & EFER_NX))
+			ignore_bits |= EFER_NX;
+	}
 
 	/*
-	 * NX is emulated; LMA and LME handled by hardware; SCE meaningless
-	 * outside long mode
+	 * LMA and LME handled by hardware; SCE meaningless outside long mode.
 	 */
-	ignore_bits = EFER_NX | EFER_SCE;
+	ignore_bits |= EFER_SCE;
 #ifdef CONFIG_X86_64
 	ignore_bits |= EFER_LMA | EFER_LME;
 	/* SCE is meaningful only in long mode on Intel */
 	if (guest_efer & EFER_LMA)
 		ignore_bits &= ~(u64)EFER_SCE;
 #endif
-	guest_efer &= ~ignore_bits;
-	guest_efer |= host_efer & ignore_bits;
-	vmx->guest_msrs[efer_offset].data = guest_efer;
-	vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
 
 	clear_atomic_switch_msr(vmx, MSR_EFER);
 
@@ -1878,16 +1902,21 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 	 */
 	if (cpu_has_load_ia32_efer ||
 	    (enable_ept && ((vmx->vcpu.arch.efer ^ host_efer) & EFER_NX))) {
-		guest_efer = vmx->vcpu.arch.efer;
 		if (!(guest_efer & EFER_LMA))
 			guest_efer &= ~EFER_LME;
 		if (guest_efer != host_efer)
 			add_atomic_switch_msr(vmx, MSR_EFER,
 					      guest_efer, host_efer);
 		return false;
-	}
+	} else {
+		guest_efer &= ~ignore_bits;
+		guest_efer |= host_efer & ignore_bits;
 
-	return true;
+		vmx->guest_msrs[efer_offset].data = guest_efer;
+		vmx->guest_msrs[efer_offset].mask = ~ignore_bits;
+
+		return true;
+	}
 }
 
 static unsigned long segment_base(u16 selector)
@@ -2127,14 +2156,16 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 		rdmsrl(MSR_IA32_SYSENTER_ESP, sysenter_esp);
 		vmcs_writel(HOST_IA32_SYSENTER_ESP, sysenter_esp); /* 22.2.3 */
 
-		/* Setup TSC multiplier */
-		if (cpu_has_vmx_tsc_scaling())
-			vmcs_write64(TSC_MULTIPLIER,
-				     vcpu->arch.tsc_scaling_ratio);
-
 		vmx->loaded_vmcs->cpu = cpu;
 	}
 
+	/* Setup TSC multiplier */
+	if (kvm_has_tsc_control &&
+	    vmx->current_tsc_ratio != vcpu->arch.tsc_scaling_ratio) {
+		vmx->current_tsc_ratio = vcpu->arch.tsc_scaling_ratio;
+		vmcs_write64(TSC_MULTIPLIER, vmx->current_tsc_ratio);
+	}
+
 	vmx_vcpu_pi_load(vcpu, cpu);
 }
 
@@ -2584,7 +2615,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
 		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT;
 
-	if (vmx_mpx_supported())
+	if (kvm_mpx_supported())
 		vmx->nested.nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS;
 
 	/* We support free control of debug control saving. */
@@ -2605,7 +2636,7 @@ static void nested_vmx_setup_ctls_msrs(struct vcpu_vmx *vmx)
 		VM_ENTRY_LOAD_IA32_PAT;
 	vmx->nested.nested_vmx_entry_ctls_high |=
 		(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
-	if (vmx_mpx_supported())
+	if (kvm_mpx_supported())
 		vmx->nested.nested_vmx_entry_ctls_high |= VM_ENTRY_LOAD_BNDCFGS;
 
 	/* We support free control of debug control loading. */
@@ -2849,7 +2880,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = vmcs_readl(GUEST_SYSENTER_ESP);
 		break;
 	case MSR_IA32_BNDCFGS:
-		if (!vmx_mpx_supported())
+		if (!kvm_mpx_supported())
 			return 1;
 		msr_info->data = vmcs_read64(GUEST_BNDCFGS);
 		break;
@@ -2926,7 +2957,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
 	case MSR_IA32_BNDCFGS:
-		if (!vmx_mpx_supported())
+		if (!kvm_mpx_supported())
 			return 1;
 		vmcs_write64(GUEST_BNDCFGS, data);
 		break;
@@ -3399,7 +3430,7 @@ static void init_vmcs_shadow_fields(void)
 	for (i = j = 0; i < max_shadow_read_write_fields; i++) {
 		switch (shadow_read_write_fields[i]) {
 		case GUEST_BNDCFGS:
-			if (!vmx_mpx_supported())
+			if (!kvm_mpx_supported())
 				continue;
 			break;
 		default:
@@ -5608,11 +5639,8 @@ static int handle_dr(struct kvm_vcpu *vcpu)
 	}
 
 	if (vcpu->guest_debug == 0) {
-		u32 cpu_based_vm_exec_control;
-
-		cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
-		cpu_based_vm_exec_control &= ~CPU_BASED_MOV_DR_EXITING;
-		vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+		vmcs_clear_bits(CPU_BASED_VM_EXEC_CONTROL,
+				CPU_BASED_MOV_DR_EXITING);
 
 		/*
 		 * No more DR vmexits; force a reload of the debug registers
@@ -5649,8 +5677,6 @@ static void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val)
 
 static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
 {
-	u32 cpu_based_vm_exec_control;
-
 	get_debugreg(vcpu->arch.db[0], 0);
 	get_debugreg(vcpu->arch.db[1], 1);
 	get_debugreg(vcpu->arch.db[2], 2);
@@ -5659,10 +5685,7 @@ static void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
 	vcpu->arch.dr7 = vmcs_readl(GUEST_DR7);
 
 	vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT;
-
-	cpu_based_vm_exec_control = vmcs_read32(CPU_BASED_VM_EXEC_CONTROL);
-	cpu_based_vm_exec_control |= CPU_BASED_MOV_DR_EXITING;
-	vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, cpu_based_vm_exec_control);
+	vmcs_set_bits(CPU_BASED_VM_EXEC_CONTROL, CPU_BASED_MOV_DR_EXITING);
 }
 
 static void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
@@ -5747,8 +5770,7 @@ static int handle_halt(struct kvm_vcpu *vcpu)
 
 static int handle_vmcall(struct kvm_vcpu *vcpu)
 {
-	kvm_emulate_hypercall(vcpu);
-	return 1;
+	return kvm_emulate_hypercall(vcpu);
 }
 
 static int handle_invd(struct kvm_vcpu *vcpu)
@@ -6435,8 +6457,8 @@ static struct loaded_vmcs *nested_get_current_vmcs02(struct vcpu_vmx *vmx)
 
 	if (vmx->nested.vmcs02_num >= max(VMCS02_POOL_SIZE, 1)) {
 		/* Recycle the least recently used VMCS. */
-		item = list_entry(vmx->nested.vmcs02_pool.prev,
-			struct vmcs02_list, list);
+		item = list_last_entry(&vmx->nested.vmcs02_pool,
+				       struct vmcs02_list, list);
 		item->vmptr = vmx->nested.current_vmptr;
 		list_move(&item->list, &vmx->nested.vmcs02_pool);
 		return &item->vmcs02;
@@ -7752,6 +7774,13 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
 		else if (is_no_device(intr_info) &&
 			 !(vmcs12->guest_cr0 & X86_CR0_TS))
 			return false;
+		else if (is_debug(intr_info) &&
+			 vcpu->guest_debug &
+			 (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
+			return false;
+		else if (is_breakpoint(intr_info) &&
+			 vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
+			return false;
 		return vmcs12->exception_bitmap &
 				(1u << (intr_info & INTR_INFO_VECTOR_MASK));
 	case EXIT_REASON_EXTERNAL_INTERRUPT:
@@ -10256,7 +10285,7 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 	vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS);
 	vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP);
 	vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
-	if (vmx_mpx_supported())
+	if (kvm_mpx_supported())
 		vmcs12->guest_bndcfgs = vmcs_read64(GUEST_BNDCFGS);
 	if (nested_cpu_has_xsaves(vmcs12))
 		vmcs12->xss_exit_bitmap = vmcs_read64(XSS_EXIT_BITMAP);
@@ -10764,13 +10793,26 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 		 */
 
 		kvm_set_msi_irq(e, &irq);
-		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu))
+		if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu)) {
+			/*
+			 * Make sure the IRTE is in remapped mode if
+			 * we don't handle it in posted mode.
+			 */
+			ret = irq_set_vcpu_affinity(host_irq, NULL);
+			if (ret < 0) {
+				printk(KERN_INFO
+				   "failed to back to remapped mode, irq: %u\n",
+				   host_irq);
+				goto out;
+			}
+
 			continue;
+		}
 
 		vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
 		vcpu_info.vector = irq.vector;
 
-		trace_kvm_pi_irte_update(vcpu->vcpu_id, e->gsi,
+		trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi,
 				vcpu_info.vector, vcpu_info.pi_desc_addr, set);
 
 		if (set)