Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
 "Bug fixes, plus a new test case and the associated infrastructure for
  writing nested virtualization tests"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  kvm: selftests: add vmx_tsc_adjust_test
  kvm: x86: move MSR_IA32_TSC handling to x86.c
  X86/KVM: Properly update 'tsc_offset' to represent the running guest
  kvm: selftests: add -std=gnu99 cflags
  x86: Add check for APIC access address for vmentry of L2 guests
  KVM: X86: fix incorrect reference of trace_kvm_pi_irte_update
  X86/KVM: Do not allow DISABLE_EXITS_MWAIT when LAPIC ARAT is not available
  kvm: selftests: fix spelling mistake: "divisable" and "divisible"
  X86/VMX: Disable VMX preemption timer if MWAIT is not intercepted

arch/x86/include/asm/kvm_host.h

@@ -1013,6 +1013,7 @@ struct kvm_x86_ops {
 
 	bool (*has_wbinvd_exit)(void);
 
+	u64 (*read_l1_tsc_offset)(struct kvm_vcpu *vcpu);
 	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
 
 	void (*get_exit_info)(struct kvm_vcpu *vcpu, u64 *info1, u64 *info2);

arch/x86/kvm/svm.c

@@ -1423,12 +1423,23 @@ static void init_sys_seg(struct vmcb_seg *seg, uint32_t type)
 	seg->base = 0;
 }
 
+static u64 svm_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (is_guest_mode(vcpu))
+		return svm->nested.hsave->control.tsc_offset;
+
+	return vcpu->arch.tsc_offset;
+}
+
 static void svm_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u64 g_tsc_offset = 0;
 
 	if (is_guest_mode(vcpu)) {
+		/* Write L1's TSC offset.  */
 		g_tsc_offset = svm->vmcb->control.tsc_offset -
 			       svm->nested.hsave->control.tsc_offset;
 		svm->nested.hsave->control.tsc_offset = offset;
@@ -3322,6 +3333,7 @@ static int nested_svm_vmexit(struct vcpu_svm *svm)
 	/* Restore the original control entries */
 	copy_vmcb_control_area(vmcb, hsave);
 
+	svm->vcpu.arch.tsc_offset = svm->vmcb->control.tsc_offset;
 	kvm_clear_exception_queue(&svm->vcpu);
 	kvm_clear_interrupt_queue(&svm->vcpu);
 
@@ -3482,10 +3494,12 @@ static void enter_svm_guest_mode(struct vcpu_svm *svm, u64 vmcb_gpa,
 	/* We don't want to see VMMCALLs from a nested guest */
 	clr_intercept(svm, INTERCEPT_VMMCALL);
 
+	svm->vcpu.arch.tsc_offset += nested_vmcb->control.tsc_offset;
+	svm->vmcb->control.tsc_offset = svm->vcpu.arch.tsc_offset;
+
 	svm->vmcb->control.virt_ext = nested_vmcb->control.virt_ext;
 	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;
 	svm->vmcb->control.event_inj = nested_vmcb->control.event_inj;
 	svm->vmcb->control.event_inj_err = nested_vmcb->control.event_inj_err;
 
@@ -4035,12 +4049,6 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	switch (msr_info->index) {
-	case MSR_IA32_TSC: {
-		msr_info->data = svm->vmcb->control.tsc_offset +
-			kvm_scale_tsc(vcpu, rdtsc());
-
-		break;
-	}
 	case MSR_STAR:
 		msr_info->data = svm->vmcb->save.star;
 		break;
@@ -4193,9 +4201,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		svm->vmcb->save.g_pat = data;
 		mark_dirty(svm->vmcb, VMCB_NPT);
 		break;
-	case MSR_IA32_TSC:
-		kvm_write_tsc(vcpu, msr);
-		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_IBRS))
@@ -5265,9 +5270,8 @@ static int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 		}
 
 		if (!ret && svm) {
-			trace_kvm_pi_irte_update(svm->vcpu.vcpu_id,
-						 host_irq, e->gsi,
-						 vcpu_info.vector,
+			trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id,
+						 e->gsi, vcpu_info.vector,
 						 vcpu_info.pi_desc_addr, set);
 		}
 
@@ -7102,6 +7106,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
 
 	.has_wbinvd_exit = svm_has_wbinvd_exit,
 
+	.read_l1_tsc_offset = svm_read_l1_tsc_offset,
 	.write_tsc_offset = svm_write_tsc_offset,
 
 	.set_tdp_cr3 = set_tdp_cr3,

arch/x86/kvm/vmx.c

@@ -2880,18 +2880,15 @@ static void setup_msrs(struct vcpu_vmx *vmx)
 		vmx_update_msr_bitmap(&vmx->vcpu);
 }
 
-/*
- * reads and returns guest's timestamp counter "register"
- * guest_tsc = (host_tsc * tsc multiplier) >> 48 + tsc_offset
- * -- Intel TSC Scaling for Virtualization White Paper, sec 1.3
- */
-static u64 guest_read_tsc(struct kvm_vcpu *vcpu)
+static u64 vmx_read_l1_tsc_offset(struct kvm_vcpu *vcpu)
 {
-	u64 host_tsc, tsc_offset;
+	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 
-	host_tsc = rdtsc();
-	tsc_offset = vmcs_read64(TSC_OFFSET);
-	return kvm_scale_tsc(vcpu, host_tsc) + tsc_offset;
+	if (is_guest_mode(vcpu) &&
+	    (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING))
+		return vcpu->arch.tsc_offset - vmcs12->tsc_offset;
+
+	return vcpu->arch.tsc_offset;
 }
 
 /*
@@ -3524,9 +3521,6 @@ static int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 #endif
 	case MSR_EFER:
 		return kvm_get_msr_common(vcpu, msr_info);
-	case MSR_IA32_TSC:
-		msr_info->data = guest_read_tsc(vcpu);
-		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
@@ -3646,9 +3640,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		vmcs_write64(GUEST_BNDCFGS, data);
 		break;
-	case MSR_IA32_TSC:
-		kvm_write_tsc(vcpu, msr_info);
-		break;
 	case MSR_IA32_SPEC_CTRL:
 		if (!msr_info->host_initiated &&
 		    !guest_cpuid_has(vcpu, X86_FEATURE_IBRS) &&
@@ -10608,6 +10599,16 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 	return true;
 }
 
+static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu,
+					  struct vmcs12 *vmcs12)
+{
+	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES) &&
+	    !page_address_valid(vcpu, vmcs12->apic_access_addr))
+		return -EINVAL;
+	else
+		return 0;
+}
+
 static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
 					   struct vmcs12 *vmcs12)
 {
@@ -11176,11 +11177,8 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
 	}
 
-	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
-		vmcs_write64(TSC_OFFSET,
-			vcpu->arch.tsc_offset + vmcs12->tsc_offset);
-	else
-		vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+
 	if (kvm_has_tsc_control)
 		decache_tsc_multiplier(vmx);
 
@@ -11299,6 +11297,9 @@ static int check_vmentry_prereqs(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	if (nested_vmx_check_msr_bitmap_controls(vcpu, vmcs12))
 		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
 
+	if (nested_vmx_check_apic_access_controls(vcpu, vmcs12))
+		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
+
 	if (nested_vmx_check_tpr_shadow_controls(vcpu, vmcs12))
 		return VMXERR_ENTRY_INVALID_CONTROL_FIELD;
 
@@ -11420,6 +11421,7 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	u32 msr_entry_idx;
 	u32 exit_qual;
+	int r;
 
 	enter_guest_mode(vcpu);
 
@@ -11429,26 +11431,21 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	vmx_switch_vmcs(vcpu, &vmx->nested.vmcs02);
 	vmx_segment_cache_clear(vmx);
 
-	if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual)) {
-		leave_guest_mode(vcpu);
-		vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-		nested_vmx_entry_failure(vcpu, vmcs12,
-					 EXIT_REASON_INVALID_STATE, exit_qual);
-		return 1;
-	}
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+		vcpu->arch.tsc_offset += vmcs12->tsc_offset;
+
+	r = EXIT_REASON_INVALID_STATE;
+	if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &exit_qual))
+		goto fail;
 
 	nested_get_vmcs12_pages(vcpu, vmcs12);
 
+	r = EXIT_REASON_MSR_LOAD_FAIL;
 	msr_entry_idx = nested_vmx_load_msr(vcpu,
 					    vmcs12->vm_entry_msr_load_addr,
 					    vmcs12->vm_entry_msr_load_count);
-	if (msr_entry_idx) {
-		leave_guest_mode(vcpu);
-		vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-		nested_vmx_entry_failure(vcpu, vmcs12,
-				EXIT_REASON_MSR_LOAD_FAIL, msr_entry_idx);
-		return 1;
-	}
+	if (msr_entry_idx)
+		goto fail;
 
 	/*
 	 * Note no nested_vmx_succeed or nested_vmx_fail here. At this point
@@ -11457,6 +11454,14 @@ static int enter_vmx_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	 * the success flag) when L2 exits (see nested_vmx_vmexit()).
 	 */
 	return 0;
+
+fail:
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+	leave_guest_mode(vcpu);
+	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+	nested_vmx_entry_failure(vcpu, vmcs12, r, exit_qual);
+	return 1;
 }
 
 /*
@@ -12028,6 +12033,9 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 
 	leave_guest_mode(vcpu);
 
+	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+		vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
+
 	if (likely(!vmx->fail)) {
 		if (exit_reason == -1)
 			sync_vmcs12(vcpu, vmcs12);
@@ -12224,10 +12232,16 @@ static inline int u64_shl_div_u64(u64 a, unsigned int shift,
 
 static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-	u64 tscl = rdtsc();
-	u64 guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
-	u64 delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
+	struct vcpu_vmx *vmx;
+	u64 tscl, guest_tscl, delta_tsc;
+
+	if (kvm_mwait_in_guest(vcpu->kvm))
+		return -EOPNOTSUPP;
+
+	vmx = to_vmx(vcpu);
+	tscl = rdtsc();
+	guest_tscl = kvm_read_l1_tsc(vcpu, tscl);
+	delta_tsc = max(guest_deadline_tsc, guest_tscl) - guest_tscl;
 
 	/* Convert to host delta tsc if tsc scaling is enabled */
 	if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&
@@ -12533,7 +12547,7 @@ static int vmx_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 		vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
 		vcpu_info.vector = irq.vector;
 
-		trace_kvm_pi_irte_update(vcpu->vcpu_id, host_irq, e->gsi,
+		trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
 				vcpu_info.vector, vcpu_info.pi_desc_addr, set);
 
 		if (set)
@@ -12712,6 +12726,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 
 	.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
 
+	.read_l1_tsc_offset = vmx_read_l1_tsc_offset,
 	.write_tsc_offset = vmx_write_tsc_offset,
 
 	.set_tdp_cr3 = vmx_set_cr3,

arch/x86/kvm/x86.c

@@ -1490,7 +1490,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
 
 static void update_ia32_tsc_adjust_msr(struct kvm_vcpu *vcpu, s64 offset)
 {
-	u64 curr_offset = vcpu->arch.tsc_offset;
+	u64 curr_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu);
 	vcpu->arch.ia32_tsc_adjust_msr += offset - curr_offset;
 }
 
@@ -1532,7 +1532,9 @@ static u64 kvm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 
 u64 kvm_read_l1_tsc(struct kvm_vcpu *vcpu, u64 host_tsc)
 {
-	return vcpu->arch.tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
+	u64 tsc_offset = kvm_x86_ops->read_l1_tsc_offset(vcpu);
+
+	return tsc_offset + kvm_scale_tsc(vcpu, host_tsc);
 }
 EXPORT_SYMBOL_GPL(kvm_read_l1_tsc);
 
@@ -2362,6 +2364,9 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		vcpu->arch.smbase = data;
 		break;
+	case MSR_IA32_TSC:
+		kvm_write_tsc(vcpu, msr_info);
+		break;
 	case MSR_SMI_COUNT:
 		if (!msr_info->host_initiated)
 			return 1;
@@ -2605,6 +2610,9 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_IA32_UCODE_REV:
 		msr_info->data = vcpu->arch.microcode_version;
 		break;
+	case MSR_IA32_TSC:
+		msr_info->data = kvm_scale_tsc(vcpu, rdtsc()) + vcpu->arch.tsc_offset;
+		break;
 	case MSR_MTRRcap:
 	case 0x200 ... 0x2ff:
 		return kvm_mtrr_get_msr(vcpu, msr_info->index, &msr_info->data);
@@ -2819,7 +2827,8 @@ static int msr_io(struct kvm_vcpu *vcpu, struct kvm_msrs __user *user_msrs,
 static inline bool kvm_can_mwait_in_guest(void)
 {
 	return boot_cpu_has(X86_FEATURE_MWAIT) &&
-		!boot_cpu_has_bug(X86_BUG_MONITOR);
+		!boot_cpu_has_bug(X86_BUG_MONITOR) &&
+		boot_cpu_has(X86_FEATURE_ARAT);
 }
 
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)

tools/testing/selftests/kvm/Makefile

@@ -4,17 +4,18 @@ top_srcdir = ../../../../
 UNAME_M := $(shell uname -m)
 
 LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c
-LIBKVM_x86_64 = lib/x86.c
+LIBKVM_x86_64 = lib/x86.c lib/vmx.c
 
 TEST_GEN_PROGS_x86_64 = set_sregs_test
 TEST_GEN_PROGS_x86_64 += sync_regs_test
+TEST_GEN_PROGS_x86_64 += vmx_tsc_adjust_test
 
 TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(UNAME_M))
 LIBKVM += $(LIBKVM_$(UNAME_M))
 
 INSTALL_HDR_PATH = $(top_srcdir)/usr
 LINUX_HDR_PATH = $(INSTALL_HDR_PATH)/include/
-CFLAGS += -O2 -g -I$(LINUX_HDR_PATH) -Iinclude -I$(<D)
+CFLAGS += -O2 -g -std=gnu99 -I$(LINUX_HDR_PATH) -Iinclude -I$(<D)
 
 # After inclusion, $(OUTPUT) is defined and
 # $(TEST_GEN_PROGS) starts with $(OUTPUT)/

tools/testing/selftests/kvm/include/kvm_util.h

@@ -112,24 +112,27 @@ void virt_pg_map(struct kvm_vm *vm, uint64_t vaddr, uint64_t paddr,
 vm_paddr_t vm_phy_page_alloc(struct kvm_vm *vm,
 	vm_paddr_t paddr_min, uint32_t memslot);
 
-void kvm_get_supported_cpuid(struct kvm_cpuid2 *cpuid);
+struct kvm_cpuid2 *kvm_get_supported_cpuid(void);
 void vcpu_set_cpuid(
 	struct kvm_vm *vm, uint32_t vcpuid, struct kvm_cpuid2 *cpuid);
 
-struct kvm_cpuid2 *allocate_kvm_cpuid2(void);
 struct kvm_cpuid_entry2 *
-find_cpuid_index_entry(struct kvm_cpuid2 *cpuid, uint32_t function,
-		       uint32_t index);
+kvm_get_supported_cpuid_index(uint32_t function, uint32_t index);
 
 static inline struct kvm_cpuid_entry2 *
-find_cpuid_entry(struct kvm_cpuid2 *cpuid, uint32_t function)
+kvm_get_supported_cpuid_entry(uint32_t function)
 {
-	return find_cpuid_index_entry(cpuid, function, 0);
+	return kvm_get_supported_cpuid_index(function, 0);
 }
 
 struct kvm_vm *vm_create_default(uint32_t vcpuid, void *guest_code);
 void vm_vcpu_add_default(struct kvm_vm *vm, uint32_t vcpuid, void *guest_code);
 
+typedef void (*vmx_guest_code_t)(vm_vaddr_t vmxon_vaddr,
+				 vm_paddr_t vmxon_paddr,
+				 vm_vaddr_t vmcs_vaddr,
+				 vm_paddr_t vmcs_paddr);
+
 struct kvm_userspace_memory_region *
 kvm_userspace_memory_region_find(struct kvm_vm *vm, uint64_t start,
 				 uint64_t end);