1 files changed, 71 insertions, 65 deletions

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index fb9e4ac3df22..76861b66bbcf 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1059,8 +1059,8 @@ static void pt_guest_enter(struct vcpu_vmx *vmx)
 	rdmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
 	if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
 		wrmsrl(MSR_IA32_RTIT_CTL, 0);
-		pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_range);
-		pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_range);
+		pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.num_address_ranges);
+		pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.num_address_ranges);
 	}
 }
 
@@ -1070,12 +1070,16 @@ static void pt_guest_exit(struct vcpu_vmx *vmx)
 		return;
 
 	if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
-		pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.addr_range);
-		pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.addr_range);
+		pt_save_msr(&vmx->pt_desc.guest, vmx->pt_desc.num_address_ranges);
+		pt_load_msr(&vmx->pt_desc.host, vmx->pt_desc.num_address_ranges);
 	}
 
-	/* Reload host state (IA32_RTIT_CTL will be cleared on VM exit). */
-	wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+	/*
+	 * KVM requires VM_EXIT_CLEAR_IA32_RTIT_CTL to expose PT to the guest,
+	 * i.e. RTIT_CTL is always cleared on VM-Exit.  Restore it if necessary.
+	 */
+	if (vmx->pt_desc.host.ctl)
+		wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
 }
 
 void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
@@ -1456,16 +1460,16 @@ static int vmx_rtit_ctl_check(struct kvm_vcpu *vcpu, u64 data)
 	 * cause a #GP fault.
 	 */
 	value = (data & RTIT_CTL_ADDR0) >> RTIT_CTL_ADDR0_OFFSET;
-	if ((value && (vmx->pt_desc.addr_range < 1)) || (value > 2))
+	if ((value && (vmx->pt_desc.num_address_ranges < 1)) || (value > 2))
 		return 1;
 	value = (data & RTIT_CTL_ADDR1) >> RTIT_CTL_ADDR1_OFFSET;
-	if ((value && (vmx->pt_desc.addr_range < 2)) || (value > 2))
+	if ((value && (vmx->pt_desc.num_address_ranges < 2)) || (value > 2))
 		return 1;
 	value = (data & RTIT_CTL_ADDR2) >> RTIT_CTL_ADDR2_OFFSET;
-	if ((value && (vmx->pt_desc.addr_range < 3)) || (value > 2))
+	if ((value && (vmx->pt_desc.num_address_ranges < 3)) || (value > 2))
 		return 1;
 	value = (data & RTIT_CTL_ADDR3) >> RTIT_CTL_ADDR3_OFFSET;
-	if ((value && (vmx->pt_desc.addr_range < 4)) || (value > 2))
+	if ((value && (vmx->pt_desc.num_address_ranges < 4)) || (value > 2))
 		return 1;
 
 	return 0;
@@ -1886,8 +1890,7 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B:
 		index = msr_info->index - MSR_IA32_RTIT_ADDR0_A;
 		if (!vmx_pt_mode_is_host_guest() ||
-			(index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps,
-					PT_CAP_num_address_ranges)))
+		    (index >= 2 * vmx->pt_desc.num_address_ranges))
 			return 1;
 		if (index % 2)
 			msr_info->data = vmx->pt_desc.guest.addr_b[index / 2];
@@ -2202,8 +2205,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (!pt_can_write_msr(vmx))
 			return 1;
 		index = msr_info->index - MSR_IA32_RTIT_ADDR0_A;
-		if (index >= 2 * intel_pt_validate_cap(vmx->pt_desc.caps,
-						       PT_CAP_num_address_ranges))
+		if (index >= 2 * vmx->pt_desc.num_address_ranges)
 			return 1;
 		if (is_noncanonical_address(data, vcpu))
 			return 1;
@@ -3879,7 +3881,7 @@ void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu)
 	vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_OUTPUT_BASE, MSR_TYPE_RW, flag);
 	vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_OUTPUT_MASK, MSR_TYPE_RW, flag);
 	vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_CR3_MATCH, MSR_TYPE_RW, flag);
-	for (i = 0; i < vmx->pt_desc.addr_range; i++) {
+	for (i = 0; i < vmx->pt_desc.num_address_ranges; i++) {
 		vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_ADDR0_A + i * 2, MSR_TYPE_RW, flag);
 		vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_ADDR0_B + i * 2, MSR_TYPE_RW, flag);
 	}
@@ -4328,10 +4330,6 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 
 #define VMX_XSS_EXIT_BITMAP 0
 
-/*
- * Noting that the initialization of Guest-state Area of VMCS is in
- * vmx_vcpu_reset().
- */
 static void init_vmcs(struct vcpu_vmx *vmx)
 {
 	if (nested)
@@ -4340,7 +4338,7 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 	if (cpu_has_vmx_msr_bitmap())
 		vmcs_write64(MSR_BITMAP, __pa(vmx->vmcs01.msr_bitmap));
 
-	vmcs_write64(VMCS_LINK_POINTER, -1ull); /* 22.3.1.5 */
+	vmcs_write64(VMCS_LINK_POINTER, INVALID_GPA); /* 22.3.1.5 */
 
 	/* Control */
 	pin_controls_set(vmx, vmx_pin_based_exec_ctrl(vmx));
@@ -4436,10 +4434,40 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 	vmx_setup_uret_msrs(vmx);
 }
 
+static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+	init_vmcs(vmx);
+
+	if (nested)
+		memcpy(&vmx->nested.msrs, &vmcs_config.nested, sizeof(vmx->nested.msrs));
+
+	vcpu_setup_sgx_lepubkeyhash(vcpu);
+
+	vmx->nested.posted_intr_nv = -1;
+	vmx->nested.vmxon_ptr = INVALID_GPA;
+	vmx->nested.current_vmptr = INVALID_GPA;
+	vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID;
+
+	vcpu->arch.microcode_version = 0x100000000ULL;
+	vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED;
+
+	/*
+	 * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
+	 * or POSTED_INTR_WAKEUP_VECTOR.
+	 */
+	vmx->pi_desc.nv = POSTED_INTR_VECTOR;
+	vmx->pi_desc.sn = 1;
+}
+
 static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	if (!init_event)
+		__vmx_vcpu_reset(vcpu);
+
 	vmx->rmode.vm86_active = 0;
 	vmx->spec_ctrl = 0;
 
@@ -4449,6 +4477,7 @@ static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 	kvm_set_cr8(vcpu, 0);
 
 	vmx_segment_cache_clear(vmx);
+	kvm_register_mark_available(vcpu, VCPU_EXREG_SEGMENTS);
 
 	seg_setup(VCPU_SREG_CS);
 	vmcs_write16(GUEST_CS_SELECTOR, 0xf000);
@@ -5379,10 +5408,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
 
 		if (vmx->emulation_required && !vmx->rmode.vm86_active &&
 		    vcpu->arch.exception.pending) {
-			vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
-			vcpu->run->internal.suberror =
-						KVM_INTERNAL_ERROR_EMULATION;
-			vcpu->run->internal.ndata = 0;
+			kvm_prepare_emulation_failure_exit(vcpu);
 			return 0;
 		}
 
@@ -5633,11 +5659,13 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 static const int kvm_vmx_max_exit_handlers =
 	ARRAY_SIZE(kvm_vmx_exit_handlers);
 
-static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2,
+static void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
+			      u64 *info1, u64 *info2,
 			      u32 *intr_info, u32 *error_code)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+	*reason = vmx->exit_reason.full;
 	*info1 = vmx_get_exit_qual(vcpu);
 	if (!(vmx->exit_reason.failed_vmentry)) {
 		*info2 = vmx->idt_vectoring_info;
@@ -6406,6 +6434,7 @@ static bool vmx_has_emulated_msr(struct kvm *kvm, u32 index)
 	case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
 		return nested;
 	case MSR_AMD64_VIRT_SPEC_CTRL:
+	case MSR_AMD64_TSC_RATIO:
 		/* This is AMD only.  */
 		return false;
 	default:
@@ -6782,7 +6811,7 @@ static fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	if (likely(!vmx->exit_reason.failed_vmentry))
 		vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
 
-	trace_kvm_exit(vmx->exit_reason.full, vcpu, KVM_ISA_VMX);
+	trace_kvm_exit(vcpu, KVM_ISA_VMX);
 
 	if (unlikely(vmx->exit_reason.failed_vmentry))
 		return EXIT_FASTPATH_NONE;
@@ -6813,7 +6842,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 {
 	struct vmx_uret_msr *tsx_ctrl;
 	struct vcpu_vmx *vmx;
-	int i, cpu, err;
+	int i, err;
 
 	BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0);
 	vmx = to_vmx(vcpu);
@@ -6834,10 +6863,8 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 			goto free_vpid;
 	}
 
-	for (i = 0; i < kvm_nr_uret_msrs; ++i) {
-		vmx->guest_uret_msrs[i].data = 0;
+	for (i = 0; i < kvm_nr_uret_msrs; ++i)
 		vmx->guest_uret_msrs[i].mask = -1ull;
-	}
 	if (boot_cpu_has(X86_FEATURE_RTM)) {
 		/*
 		 * TSX_CTRL_CPUID_CLEAR is handled in the CPUID interception.
@@ -6874,12 +6901,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 	}
 
 	vmx->loaded_vmcs = &vmx->vmcs01;
-	cpu = get_cpu();
-	vmx_vcpu_load(vcpu, cpu);
-	vcpu->cpu = cpu;
-	init_vmcs(vmx);
-	vmx_vcpu_put(vcpu);
-	put_cpu();
+
 	if (cpu_need_virtualize_apic_accesses(vcpu)) {
 		err = alloc_apic_access_page(vcpu->kvm);
 		if (err)
@@ -6892,27 +6914,6 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 			goto free_vmcs;
 	}
 
-	if (nested)
-		memcpy(&vmx->nested.msrs, &vmcs_config.nested, sizeof(vmx->nested.msrs));
-	else
-		memset(&vmx->nested.msrs, 0, sizeof(vmx->nested.msrs));
-
-	vcpu_setup_sgx_lepubkeyhash(vcpu);
-
-	vmx->nested.posted_intr_nv = -1;
-	vmx->nested.current_vmptr = -1ull;
-	vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID;
-
-	vcpu->arch.microcode_version = 0x100000000ULL;
-	vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED;
-
-	/*
-	 * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
-	 * or POSTED_INTR_WAKEUP_VECTOR.
-	 */
-	vmx->pi_desc.nv = POSTED_INTR_VECTOR;
-	vmx->pi_desc.sn = 1;
-
 	return 0;
 
 free_vmcs:
@@ -7127,12 +7128,13 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
 	}
 
 	/* Get the number of configurable Address Ranges for filtering */
-	vmx->pt_desc.addr_range = intel_pt_validate_cap(vmx->pt_desc.caps,
+	vmx->pt_desc.num_address_ranges = intel_pt_validate_cap(vmx->pt_desc.caps,
 						PT_CAP_num_address_ranges);
 
 	/* Initialize and clear the no dependency bits */
 	vmx->pt_desc.ctl_bitmask = ~(RTIT_CTL_TRACEEN | RTIT_CTL_OS |
-			RTIT_CTL_USR | RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC);
+			RTIT_CTL_USR | RTIT_CTL_TSC_EN | RTIT_CTL_DISRETC |
+			RTIT_CTL_BRANCH_EN);
 
 	/*
 	 * If CPUID.(EAX=14H,ECX=0):EBX[0]=1 CR3Filter can be set otherwise
@@ -7150,12 +7152,11 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
 				RTIT_CTL_CYC_THRESH | RTIT_CTL_PSB_FREQ);
 
 	/*
-	 * If CPUID.(EAX=14H,ECX=0):EBX[3]=1 MTCEn BranchEn and
-	 * MTCFreq can be set
+	 * If CPUID.(EAX=14H,ECX=0):EBX[3]=1 MTCEn and MTCFreq can be set
 	 */
 	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_mtc))
 		vmx->pt_desc.ctl_bitmask &= ~(RTIT_CTL_MTC_EN |
-				RTIT_CTL_BRANCH_EN | RTIT_CTL_MTC_RANGE);
+					      RTIT_CTL_MTC_RANGE);
 
 	/* If CPUID.(EAX=14H,ECX=0):EBX[4]=1 FUPonPTW and PTWEn can be set */
 	if (intel_pt_validate_cap(vmx->pt_desc.caps, PT_CAP_ptwrite))
@@ -7175,7 +7176,7 @@ static void update_intel_pt_cfg(struct kvm_vcpu *vcpu)
 		vmx->pt_desc.ctl_bitmask &= ~RTIT_CTL_FABRIC_EN;
 
 	/* unmask address range configure area */
-	for (i = 0; i < vmx->pt_desc.addr_range; i++)
+	for (i = 0; i < vmx->pt_desc.num_address_ranges; i++)
 		vmx->pt_desc.ctl_bitmask &= ~(0xfULL << (32 + i * 4));
 }
 
@@ -7551,6 +7552,8 @@ static void vmx_migrate_timers(struct kvm_vcpu *vcpu)
 
 static void hardware_unsetup(void)
 {
+	kvm_set_posted_intr_wakeup_handler(NULL);
+
 	if (nested)
 		nested_vmx_hardware_unsetup();
 
@@ -7566,6 +7569,8 @@ static bool vmx_check_apicv_inhibit_reasons(ulong bit)
 }
 
 static struct kvm_x86_ops vmx_x86_ops __initdata = {
+	.name = "kvm_intel",
+
 	.hardware_unsetup = hardware_unsetup,
 
 	.hardware_enable = hardware_enable,
@@ -7879,8 +7884,6 @@ static __init int hardware_setup(void)
 		vmx_x86_ops.request_immediate_exit = __kvm_request_immediate_exit;
 	}
 
-	kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler);
-
 	kvm_mce_cap_supported |= MCG_LMCE_P;
 
 	if (pt_mode != PT_MODE_SYSTEM && pt_mode != PT_MODE_HOST_GUEST)
@@ -7904,6 +7907,9 @@ static __init int hardware_setup(void)
 	r = alloc_kvm_area();
 	if (r)
 		nested_vmx_hardware_unsetup();
+
+	kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler);
+
 	return r;
 }