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

Pull KVM fixes from Paolo Bonzini:
 "Bugfixes for ARM, PPC and x86, plus selftest improvements"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: nVMX: Don't leak L1 MMIO regions to L2
  KVM: SVM: Fix potential wrong physical id in avic_handle_ldr_update
  kvm: clear kvmclock MSR on reset
  KVM: x86: fix bugon.cocci warnings
  KVM: VMX: Remove specialized handling of unexpected exit-reasons
  selftests: kvm: fix sync_regs_test with newer gccs
  selftests: kvm: vmx_dirty_log_test: skip the test when VMX is not supported
  selftests: kvm: consolidate VMX support checks
  selftests: kvm: vmx_set_nested_state_test: don't check for VMX support twice
  KVM: Don't shrink/grow vCPU halt_poll_ns if host side polling is disabled
  selftests: kvm: synchronize .gitignore to Makefile
  kvm: x86: Expose RDPID in KVM_GET_SUPPORTED_CPUID
  KVM: arm64: pmu: Reset sample period on overflow handling
  KVM: arm64: pmu: Set the CHAINED attribute before creating the in-kernel event
  arm64: KVM: Handle PMCR_EL0.LC as RES1 on pure AArch64 systems
  KVM: arm64: pmu: Fix cycle counter truncation
  KVM: PPC: Book3S HV: XIVE: Ensure VP isn't already in use

arch/arm64/kvm/sys_regs.c

@@ -632,6 +632,8 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 	 */
 	val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
 	       | (ARMV8_PMU_PMCR_MASK & 0xdecafbad)) & (~ARMV8_PMU_PMCR_E);
+	if (!system_supports_32bit_el0())
+		val |= ARMV8_PMU_PMCR_LC;
 	__vcpu_sys_reg(vcpu, r->reg) = val;
 }
 
@@ -682,6 +684,8 @@ static bool access_pmcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		val = __vcpu_sys_reg(vcpu, PMCR_EL0);
 		val &= ~ARMV8_PMU_PMCR_MASK;
 		val |= p->regval & ARMV8_PMU_PMCR_MASK;
+		if (!system_supports_32bit_el0())
+			val |= ARMV8_PMU_PMCR_LC;
 		__vcpu_sys_reg(vcpu, PMCR_EL0) = val;
 		kvm_pmu_handle_pmcr(vcpu, val);
 		kvm_vcpu_pmu_restore_guest(vcpu);

arch/powerpc/kvm/book3s_xive.c

@@ -1217,6 +1217,7 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 	struct kvmppc_xive *xive = dev->private;
 	struct kvmppc_xive_vcpu *xc;
 	int i, r = -EBUSY;
+	u32 vp_id;
 
 	pr_devel("connect_vcpu(cpu=%d)\n", cpu);
 
@@ -1228,25 +1229,32 @@ int kvmppc_xive_connect_vcpu(struct kvm_device *dev,
 		return -EPERM;
 	if (vcpu->arch.irq_type != KVMPPC_IRQ_DEFAULT)
 		return -EBUSY;
-	if (kvmppc_xive_find_server(vcpu->kvm, cpu)) {
-		pr_devel("Duplicate !\n");
-		return -EEXIST;
-	}
 	if (cpu >= (KVM_MAX_VCPUS * vcpu->kvm->arch.emul_smt_mode)) {
 		pr_devel("Out of bounds !\n");
 		return -EINVAL;
 	}
-	xc = kzalloc(sizeof(*xc), GFP_KERNEL);
-	if (!xc)
-		return -ENOMEM;
 
 	/* We need to synchronize with queue provisioning */
 	mutex_lock(&xive->lock);
+
+	vp_id = kvmppc_xive_vp(xive, cpu);
+	if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) {
+		pr_devel("Duplicate !\n");
+		r = -EEXIST;
+		goto bail;
+	}
+
+	xc = kzalloc(sizeof(*xc), GFP_KERNEL);
+	if (!xc) {
+		r = -ENOMEM;
+		goto bail;
+	}
+
 	vcpu->arch.xive_vcpu = xc;
 	xc->xive = xive;
 	xc->vcpu = vcpu;
 	xc->server_num = cpu;
-	xc->vp_id = kvmppc_xive_vp(xive, cpu);
+	xc->vp_id = vp_id;
 	xc->mfrr = 0xff;
 	xc->valid = true;
 

arch/powerpc/kvm/book3s_xive.h

@@ -220,6 +220,18 @@ static inline u32 kvmppc_xive_vp(struct kvmppc_xive *xive, u32 server)
 	return xive->vp_base + kvmppc_pack_vcpu_id(xive->kvm, server);
 }
 
+static inline bool kvmppc_xive_vp_in_use(struct kvm *kvm, u32 vp_id)
+{
+	struct kvm_vcpu *vcpu = NULL;
+	int i;
+
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		if (vcpu->arch.xive_vcpu && vp_id == vcpu->arch.xive_vcpu->vp_id)
+			return true;
+	}
+	return false;
+}
+
 /*
  * Mapping between guest priorities and host priorities
  * is as follow.

arch/powerpc/kvm/book3s_xive_native.c

@@ -106,6 +106,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
 	struct kvmppc_xive *xive = dev->private;
 	struct kvmppc_xive_vcpu *xc = NULL;
 	int rc;
+	u32 vp_id;
 
 	pr_devel("native_connect_vcpu(server=%d)\n", server_num);
 
@@ -124,7 +125,8 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
 
 	mutex_lock(&xive->lock);
 
-	if (kvmppc_xive_find_server(vcpu->kvm, server_num)) {
+	vp_id = kvmppc_xive_vp(xive, server_num);
+	if (kvmppc_xive_vp_in_use(xive->kvm, vp_id)) {
 		pr_devel("Duplicate !\n");
 		rc = -EEXIST;
 		goto bail;
@@ -141,7 +143,7 @@ int kvmppc_xive_native_connect_vcpu(struct kvm_device *dev,
 	xc->vcpu = vcpu;
 	xc->server_num = server_num;
 
-	xc->vp_id = kvmppc_xive_vp(xive, server_num);
+	xc->vp_id = vp_id;
 	xc->valid = true;
 	vcpu->arch.irq_type = KVMPPC_IRQ_XIVE;
 

arch/x86/include/asm/kvm_host.h

@@ -1189,7 +1189,7 @@ struct kvm_x86_ops {
 	int (*set_nested_state)(struct kvm_vcpu *vcpu,
 				struct kvm_nested_state __user *user_kvm_nested_state,
 				struct kvm_nested_state *kvm_state);
-	void (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
+	bool (*get_vmcs12_pages)(struct kvm_vcpu *vcpu);
 
 	int (*smi_allowed)(struct kvm_vcpu *vcpu);
 	int (*pre_enter_smm)(struct kvm_vcpu *vcpu, char *smstate);

arch/x86/kvm/cpuid.c

@@ -363,7 +363,7 @@ static inline void do_cpuid_7_mask(struct kvm_cpuid_entry2 *entry, int index)
 
 	/* cpuid 7.0.ecx*/
 	const u32 kvm_cpuid_7_0_ecx_x86_features =
-		F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ |
+		F(AVX512VBMI) | F(LA57) | F(PKU) | 0 /*OSPKE*/ | F(RDPID) |
 		F(AVX512_VPOPCNTDQ) | F(UMIP) | F(AVX512_VBMI2) | F(GFNI) |
 		F(VAES) | F(VPCLMULQDQ) | F(AVX512_VNNI) | F(AVX512_BITALG) |
 		F(CLDEMOTE) | F(MOVDIRI) | F(MOVDIR64B) | 0 /*WAITPKG*/;

arch/x86/kvm/lapic.c

@@ -111,11 +111,6 @@ static inline int apic_enabled(struct kvm_lapic *apic)
 	(LVT_MASK | APIC_MODE_MASK | APIC_INPUT_POLARITY | \
 	 APIC_LVT_REMOTE_IRR | APIC_LVT_LEVEL_TRIGGER)
 
-static inline u8 kvm_xapic_id(struct kvm_lapic *apic)
-{
-	return kvm_lapic_get_reg(apic, APIC_ID) >> 24;
-}
-
 static inline u32 kvm_x2apic_id(struct kvm_lapic *apic)
 {
 	return apic->vcpu->vcpu_id;

arch/x86/kvm/lapic.h

@@ -242,4 +242,9 @@ static inline enum lapic_mode kvm_apic_mode(u64 apic_base)
 	return apic_base & (MSR_IA32_APICBASE_ENABLE | X2APIC_ENABLE);
 }
 
+static inline u8 kvm_xapic_id(struct kvm_lapic *apic)
+{
+	return kvm_lapic_get_reg(apic, APIC_ID) >> 24;
+}
+
 #endif

arch/x86/kvm/svm.c

@@ -4591,6 +4591,7 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
 	int ret = 0;
 	struct vcpu_svm *svm = to_svm(vcpu);
 	u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR);
+	u32 id = kvm_xapic_id(vcpu->arch.apic);
 
 	if (ldr == svm->ldr_reg)
 		return 0;
@@ -4598,7 +4599,7 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
 	avic_invalidate_logical_id_entry(vcpu);
 
 	if (ldr)
-		ret = avic_ldr_write(vcpu, vcpu->vcpu_id, ldr);
+		ret = avic_ldr_write(vcpu, id, ldr);
 
 	if (!ret)
 		svm->ldr_reg = ldr;
@@ -4610,8 +4611,7 @@ static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu)
 {
 	u64 *old, *new;
 	struct vcpu_svm *svm = to_svm(vcpu);
-	u32 apic_id_reg = kvm_lapic_get_reg(vcpu->arch.apic, APIC_ID);
-	u32 id = (apic_id_reg >> 24) & 0xff;
+	u32 id = kvm_xapic_id(vcpu->arch.apic);
 
 	if (vcpu->vcpu_id == id)
 		return 0;

arch/x86/kvm/vmx/nested.c

@@ -2917,7 +2917,7 @@ static int nested_vmx_check_vmentry_hw(struct kvm_vcpu *vcpu)
 static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
 						 struct vmcs12 *vmcs12);
 
-static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
+static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -2937,19 +2937,18 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 			vmx->nested.apic_access_page = NULL;
 		}
 		page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr);
-		/*
-		 * If translation failed, no matter: This feature asks
-		 * to exit when accessing the given address, and if it
-		 * can never be accessed, this feature won't do
-		 * anything anyway.
-		 */
 		if (!is_error_page(page)) {
 			vmx->nested.apic_access_page = page;
 			hpa = page_to_phys(vmx->nested.apic_access_page);
 			vmcs_write64(APIC_ACCESS_ADDR, hpa);
 		} else {
-			secondary_exec_controls_clearbit(vmx,
-				SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES);
+			pr_debug_ratelimited("%s: no backing 'struct page' for APIC-access address in vmcs12\n",
+					     __func__);
+			vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+			vcpu->run->internal.suberror =
+				KVM_INTERNAL_ERROR_EMULATION;
+			vcpu->run->internal.ndata = 0;
+			return false;
 		}
 	}
 
@@ -2994,6 +2993,7 @@ static void nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 		exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
 	else
 		exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
+	return true;
 }
 
 /*
@@ -3032,13 +3032,15 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 /*
  * If from_vmentry is false, this is being called from state restore (either RSM
  * or KVM_SET_NESTED_STATE).  Otherwise it's called from vmlaunch/vmresume.
-+ *
-+ * Returns:
-+ *   0 - success, i.e. proceed with actual VMEnter
-+ *   1 - consistency check VMExit
-+ *  -1 - consistency check VMFail
+ *
+ * Returns:
+ *	NVMX_ENTRY_SUCCESS: Entered VMX non-root mode
+ *	NVMX_ENTRY_VMFAIL:  Consistency check VMFail
+ *	NVMX_ENTRY_VMEXIT:  Consistency check VMExit
+ *	NVMX_ENTRY_KVM_INTERNAL_ERROR: KVM internal error
  */
-int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
+enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
+							bool from_vmentry)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
@@ -3081,11 +3083,12 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	prepare_vmcs02_early(vmx, vmcs12);
 
 	if (from_vmentry) {
-		nested_get_vmcs12_pages(vcpu);
+		if (unlikely(!nested_get_vmcs12_pages(vcpu)))
+			return NVMX_VMENTRY_KVM_INTERNAL_ERROR;
 
 		if (nested_vmx_check_vmentry_hw(vcpu)) {
 			vmx_switch_vmcs(vcpu, &vmx->vmcs01);
-			return -1;
+			return NVMX_VMENTRY_VMFAIL;
 		}
 
 		if (nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual))
@@ -3149,7 +3152,7 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	 * returned as far as L1 is concerned. It will only return (and set
 	 * the success flag) when L2 exits (see nested_vmx_vmexit()).
 	 */
-	return 0;
+	return NVMX_VMENTRY_SUCCESS;
 
 	/*
 	 * A failed consistency check that leads to a VMExit during L1's
@@ -3165,14 +3168,14 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 	vmx_switch_vmcs(vcpu, &vmx->vmcs01);
 
 	if (!from_vmentry)
-		return 1;
+		return NVMX_VMENTRY_VMEXIT;
 
 	load_vmcs12_host_state(vcpu, vmcs12);
 	vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY;
 	vmcs12->exit_qualification = exit_qual;
 	if (enable_shadow_vmcs || vmx->nested.hv_evmcs)
 		vmx->nested.need_vmcs12_to_shadow_sync = true;
-	return 1;
+	return NVMX_VMENTRY_VMEXIT;
 }
 
 /*
@@ -3182,9 +3185,9 @@ int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry)
 static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 {
 	struct vmcs12 *vmcs12;
+	enum nvmx_vmentry_status status;
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu);
-	int ret;
 
 	if (!nested_vmx_check_permission(vcpu))
 		return 1;
@@ -3244,13 +3247,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 	 * the nested entry.
 	 */
 	vmx->nested.nested_run_pending = 1;
-	ret = nested_vmx_enter_non_root_mode(vcpu, true);
-	vmx->nested.nested_run_pending = !ret;
-	if (ret > 0)
-		return 1;
-	else if (ret)
-		return nested_vmx_failValid(vcpu,
-			VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+	status = nested_vmx_enter_non_root_mode(vcpu, true);
+	if (unlikely(status != NVMX_VMENTRY_SUCCESS))
+		goto vmentry_failed;
 
 	/* Hide L1D cache contents from the nested guest.  */
 	vmx->vcpu.arch.l1tf_flush_l1d = true;
@@ -3281,6 +3280,15 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		return kvm_vcpu_halt(vcpu);
 	}
 	return 1;
+
+vmentry_failed:
+	vmx->nested.nested_run_pending = 0;
+	if (status == NVMX_VMENTRY_KVM_INTERNAL_ERROR)
+		return 0;
+	if (status == NVMX_VMENTRY_VMEXIT)
+		return 1;
+	WARN_ON_ONCE(status != NVMX_VMENTRY_VMFAIL);
+	return nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
 }
 
 /*

arch/x86/kvm/vmx/nested.h

@@ -6,6 +6,16 @@
 #include "vmcs12.h"
 #include "vmx.h"
 
+/*
+ * Status returned by nested_vmx_enter_non_root_mode():
+ */
+enum nvmx_vmentry_status {
+	NVMX_VMENTRY_SUCCESS,		/* Entered VMX non-root mode */
+	NVMX_VMENTRY_VMFAIL,		/* Consistency check VMFail */
+	NVMX_VMENTRY_VMEXIT,		/* Consistency check VMExit */
+	NVMX_VMENTRY_KVM_INTERNAL_ERROR,/* KVM internal error */
+};
+
 void vmx_leave_nested(struct kvm_vcpu *vcpu);
 void nested_vmx_setup_ctls_msrs(struct nested_vmx_msrs *msrs, u32 ept_caps,
 				bool apicv);
@@ -13,7 +23,8 @@ void nested_vmx_hardware_unsetup(void);
 __init int nested_vmx_hardware_setup(int (*exit_handlers[])(struct kvm_vcpu *));
 void nested_vmx_vcpu_setup(void);
 void nested_vmx_free_vcpu(struct kvm_vcpu *vcpu);
-int nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu, bool from_vmentry);
+enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
+						     bool from_vmentry);
 bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason);
 void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 		       u32 exit_intr_info, unsigned long exit_qualification);

arch/x86/kvm/vmx/vmx.c

@@ -5543,14 +5543,6 @@ static int handle_encls(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
-static int handle_unexpected_vmexit(struct kvm_vcpu *vcpu)
-{
-	kvm_skip_emulated_instruction(vcpu);
-	WARN_ONCE(1, "Unexpected VM-Exit Reason = 0x%x",
-		vmcs_read32(VM_EXIT_REASON));
-	return 1;
-}
-
 /*
  * The exit handlers return 1 if the exit was handled fully and guest execution
  * may resume.  Otherwise they set the kvm_run parameter to indicate what needs
@@ -5602,15 +5594,11 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
 	[EXIT_REASON_INVVPID]                 = handle_vmx_instruction,
 	[EXIT_REASON_RDRAND]                  = handle_invalid_op,
 	[EXIT_REASON_RDSEED]                  = handle_invalid_op,
-	[EXIT_REASON_XSAVES]                  = handle_unexpected_vmexit,
-	[EXIT_REASON_XRSTORS]                 = handle_unexpected_vmexit,
 	[EXIT_REASON_PML_FULL]		      = handle_pml_full,
 	[EXIT_REASON_INVPCID]                 = handle_invpcid,
 	[EXIT_REASON_VMFUNC]		      = handle_vmx_instruction,
 	[EXIT_REASON_PREEMPTION_TIMER]	      = handle_preemption_timer,
 	[EXIT_REASON_ENCLS]		      = handle_encls,
-	[EXIT_REASON_UMWAIT]                  = handle_unexpected_vmexit,
-	[EXIT_REASON_TPAUSE]                  = handle_unexpected_vmexit,
 };
 
 static const int kvm_vmx_max_exit_handlers =

arch/x86/kvm/x86.c

@@ -360,8 +360,7 @@ EXPORT_SYMBOL_GPL(kvm_set_apic_base);
 asmlinkage __visible void kvm_spurious_fault(void)
 {
 	/* Fault while not rebooting.  We want the trace. */
-	if (!kvm_rebooting)
-		BUG();
+	BUG_ON(!kvm_rebooting);
 }
 EXPORT_SYMBOL_GPL(kvm_spurious_fault);
 
@@ -2537,6 +2536,7 @@ static int kvm_pv_enable_async_pf(struct kvm_vcpu *vcpu, u64 data)
 static void kvmclock_reset(struct kvm_vcpu *vcpu)
 {
 	vcpu->arch.pv_time_enabled = false;
+	vcpu->arch.time = 0;
 }
 
 static void kvm_vcpu_flush_tlb(struct kvm_vcpu *vcpu, bool invalidate_gpa)
@@ -2702,8 +2702,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_KVM_SYSTEM_TIME: {
 		struct kvm_arch *ka = &vcpu->kvm->arch;
 
-		kvmclock_reset(vcpu);
-
 		if (vcpu->vcpu_id == 0 && !msr_info->host_initiated) {
 			bool tmp = (msr == MSR_KVM_SYSTEM_TIME);
 
@@ -2717,14 +2715,13 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		kvm_make_request(KVM_REQ_GLOBAL_CLOCK_UPDATE, vcpu);
 
 		/* we verify if the enable bit is set... */
+		vcpu->arch.pv_time_enabled = false;
 		if (!(data & 1))
 			break;
 
-		if (kvm_gfn_to_hva_cache_init(vcpu->kvm,
+		if (!kvm_gfn_to_hva_cache_init(vcpu->kvm,
 		     &vcpu->arch.pv_time, data & ~1ULL,
 		     sizeof(struct pvclock_vcpu_time_info)))
-			vcpu->arch.pv_time_enabled = false;
-		else
 			vcpu->arch.pv_time_enabled = true;
 
 		break;
@@ -7941,8 +7938,12 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 	bool req_immediate_exit = false;
 
 	if (kvm_request_pending(vcpu)) {
-		if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu))
-			kvm_x86_ops->get_vmcs12_pages(vcpu);
+		if (kvm_check_request(KVM_REQ_GET_VMCS12_PAGES, vcpu)) {
+			if (unlikely(!kvm_x86_ops->get_vmcs12_pages(vcpu))) {
+				r = 0;
+				goto out;
+			}
+		}
 		if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu))
 			kvm_mmu_unload(vcpu);
 		if (kvm_check_request(KVM_REQ_MIGRATE_TIMER, vcpu))

tools/testing/selftests/kvm/.gitignore

 /s390x/sync_regs_test
+/s390x/memop
 /x86_64/cr4_cpuid_sync_test
 /x86_64/evmcs_test
 /x86_64/hyperv_cpuid
@@ -9,6 +10,7 @@
 /x86_64/state_test
 /x86_64/sync_regs_test
 /x86_64/vmx_close_while_nested_test
+/x86_64/vmx_dirty_log_test
 /x86_64/vmx_set_nested_state_test
 /x86_64/vmx_tsc_adjust_test
 /clear_dirty_log_test

tools/testing/selftests/kvm/include/x86_64/vmx.h

@@ -580,6 +580,8 @@ bool prepare_for_vmx_operation(struct vmx_pages *vmx);
 void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp);
 bool load_vmcs(struct vmx_pages *vmx);
 
+void nested_vmx_check_supported(void);
+
 void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
 		   uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot);
 void nested_map(struct vmx_pages *vmx, struct kvm_vm *vm,

tools/testing/selftests/kvm/lib/x86_64/vmx.c

@@ -376,6 +376,16 @@ void prepare_vmcs(struct vmx_pages *vmx, void *guest_rip, void *guest_rsp)
 	init_vmcs_guest_state(guest_rip, guest_rsp);
 }
 
+void nested_vmx_check_supported(void)
+{
+	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
+
+	if (!(entry->ecx & CPUID_VMX)) {
+		fprintf(stderr, "nested VMX not enabled, skipping test\n");
+		exit(KSFT_SKIP);
+	}
+}
+
 void nested_pg_map(struct vmx_pages *vmx, struct kvm_vm *vm,
 	 	   uint64_t nested_paddr, uint64_t paddr, uint32_t eptp_memslot)
 {

tools/testing/selftests/kvm/x86_64/sync_regs_test.c

@@ -22,18 +22,19 @@
 
 #define VCPU_ID 5
 
+#define UCALL_PIO_PORT ((uint16_t)0x1000)
+
+/*
+ * ucall is embedded here to protect against compiler reshuffling registers
+ * before calling a function. In this test we only need to get KVM_EXIT_IO
+ * vmexit and preserve RBX, no additional information is needed.
+ */
 void guest_code(void)
 {
-	/*
-	 * use a callee-save register, otherwise the compiler
-	 * saves it around the call to GUEST_SYNC.
-	 */
-	register u32 stage asm("rbx");
-	for (;;) {
-		GUEST_SYNC(0);
-		stage++;
-		asm volatile ("" : : "r" (stage));
-	}
+	asm volatile("1: in %[port], %%al\n"
+		     "add $0x1, %%rbx\n"
+		     "jmp 1b"
+		     : : [port] "d" (UCALL_PIO_PORT) : "rax", "rbx");
 }
 
 static void compare_regs(struct kvm_regs *left, struct kvm_regs *right)

tools/testing/selftests/kvm/x86_64/vmx_close_while_nested_test.c

@@ -53,12 +53,8 @@ static void l1_guest_code(struct vmx_pages *vmx_pages)
 int main(int argc, char *argv[])
 {
 	vm_vaddr_t vmx_pages_gva;
-	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
-	if (!(entry->ecx & CPUID_VMX)) {
-		fprintf(stderr, "nested VMX not enabled, skipping test\n");
-		exit(KSFT_SKIP);
-	}
+	nested_vmx_check_supported();
 
 	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());

tools/testing/selftests/kvm/x86_64/vmx_dirty_log_test.c

@@ -78,6 +78,8 @@ int main(int argc, char *argv[])
 	struct ucall uc;
 	bool done = false;
 
+	nested_vmx_check_supported();
+
 	/* Create VM */
 	vm = vm_create_default(VCPU_ID, 0, l1_guest_code);
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());

tools/testing/selftests/kvm/x86_64/vmx_set_nested_state_test.c

@@ -224,7 +224,6 @@ int main(int argc, char *argv[])
 {
 	struct kvm_vm *vm;
 	struct kvm_nested_state state;
-	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
 	have_evmcs = kvm_check_cap(KVM_CAP_HYPERV_ENLIGHTENED_VMCS);
 
@@ -237,10 +236,7 @@ int main(int argc, char *argv[])
 	 * AMD currently does not implement set_nested_state, so for now we
 	 * just early out.
 	 */
-	if (!(entry->ecx & CPUID_VMX)) {
-		fprintf(stderr, "nested VMX not enabled, skipping test\n");
-		exit(KSFT_SKIP);
-	}
+	nested_vmx_check_supported();
 
 	vm = vm_create_default(VCPU_ID, 0, 0);
 
@@ -271,12 +267,7 @@ int main(int argc, char *argv[])
 	state.flags = KVM_STATE_NESTED_RUN_PENDING;
 	test_nested_state_expect_einval(vm, &state);
 
-	/*
-	 * TODO: When SVM support is added for KVM_SET_NESTED_STATE
-	 *       add tests here to support it like VMX.
-	 */
-	if (entry->ecx & CPUID_VMX)
-		test_vmx_nested_state(vm);
+	test_vmx_nested_state(vm);
 
 	kvm_vm_free(vm);
 	return 0;

tools/testing/selftests/kvm/x86_64/vmx_tsc_adjust_test.c

@@ -128,12 +128,8 @@ static void report(int64_t val)
 int main(int argc, char *argv[])
 {
 	vm_vaddr_t vmx_pages_gva;
-	struct kvm_cpuid_entry2 *entry = kvm_get_supported_cpuid_entry(1);
 
-	if (!(entry->ecx & CPUID_VMX)) {
-		fprintf(stderr, "nested VMX not enabled, skipping test\n");
-		exit(KSFT_SKIP);
-	}
+	nested_vmx_check_supported();
 
 	vm = vm_create_default(VCPU_ID, 0, (void *) l1_guest_code);
 	vcpu_set_cpuid(vm, VCPU_ID, kvm_get_supported_cpuid());

virt/kvm/arm/pmu.c

@@ -8,6 +8,7 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <linux/perf_event.h>
+#include <linux/perf/arm_pmu.h>
 #include <linux/uaccess.h>
 #include <asm/kvm_emulate.h>
 #include <kvm/arm_pmu.h>
@@ -146,8 +147,7 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
 	if (kvm_pmu_pmc_is_chained(pmc) &&
 	    kvm_pmu_idx_is_high_counter(select_idx))
 		counter = upper_32_bits(counter);
-
-	else if (!kvm_pmu_idx_is_64bit(vcpu, select_idx))
+	else if (select_idx != ARMV8_PMU_CYCLE_IDX)
 		counter = lower_32_bits(counter);
 
 	return counter;
@@ -193,7 +193,7 @@ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc)
  */
 static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
 {
-	u64 counter, reg;
+	u64 counter, reg, val;
 
 	pmc = kvm_pmu_get_canonical_pmc(pmc);
 	if (!pmc->perf_event)
@@ -201,16 +201,19 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
 
 	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
 
-	if (kvm_pmu_pmc_is_chained(pmc)) {
-		reg = PMEVCNTR0_EL0 + pmc->idx;
-		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
-		__vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter);
+	if (pmc->idx == ARMV8_PMU_CYCLE_IDX) {
+		reg = PMCCNTR_EL0;
+		val = counter;
 	} else {
-		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
-		       ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
-		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
+		reg = PMEVCNTR0_EL0 + pmc->idx;
+		val = lower_32_bits(counter);
 	}
 
+	__vcpu_sys_reg(vcpu, reg) = val;
+
+	if (kvm_pmu_pmc_is_chained(pmc))
+		__vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter);
+
 	kvm_pmu_release_perf_event(pmc);
 }
 
@@ -440,8 +443,25 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
 				  struct pt_regs *regs)
 {
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(perf_event->pmu);
 	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
 	int idx = pmc->idx;
+	u64 period;
+
+	cpu_pmu->pmu.stop(perf_event, PERF_EF_UPDATE);
+
+	/*
+	 * Reset the sample period to the architectural limit,
+	 * i.e. the point where the counter overflows.
+	 */
+	period = -(local64_read(&perf_event->count));
+
+	if (!kvm_pmu_idx_is_64bit(vcpu, pmc->idx))
+		period &= GENMASK(31, 0);
+
+	local64_set(&perf_event->hw.period_left, 0);
+	perf_event->attr.sample_period = period;
+	perf_event->hw.sample_period = period;
 
 	__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx);
 
@@ -449,6 +469,8 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
 		kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 		kvm_vcpu_kick(vcpu);
 	}
+
+	cpu_pmu->pmu.start(perf_event, PERF_EF_RELOAD);
 }
 
 /**
@@ -567,12 +589,12 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 		 * high counter.
 		 */
 		attr.sample_period = (-counter) & GENMASK(63, 0);
+		if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1))
+			attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
+
 		event = perf_event_create_kernel_counter(&attr, -1, current,
 							 kvm_pmu_perf_overflow,
 							 pmc + 1);
-
-		if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1))
-			attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
 	} else {
 		/* The initial sample period (overflow count) of an event. */
 		if (kvm_pmu_idx_is_64bit(vcpu, pmc->idx))

virt/kvm/kvm_main.c

@@ -2360,20 +2360,23 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	kvm_arch_vcpu_unblocking(vcpu);
 	block_ns = ktime_to_ns(cur) - ktime_to_ns(start);
 
-	if (!vcpu_valid_wakeup(vcpu))
-		shrink_halt_poll_ns(vcpu);
-	else if (halt_poll_ns) {
-		if (block_ns <= vcpu->halt_poll_ns)
-			;
-		/* we had a long block, shrink polling */
-		else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns)
+	if (!kvm_arch_no_poll(vcpu)) {
+		if (!vcpu_valid_wakeup(vcpu)) {
 			shrink_halt_poll_ns(vcpu);
-		/* we had a short halt and our poll time is too small */
-		else if (vcpu->halt_poll_ns < halt_poll_ns &&
-			block_ns < halt_poll_ns)
-			grow_halt_poll_ns(vcpu);
-	} else
-		vcpu->halt_poll_ns = 0;
+		} else if (halt_poll_ns) {
+			if (block_ns <= vcpu->halt_poll_ns)
+				;
+			/* we had a long block, shrink polling */
+			else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns)
+				shrink_halt_poll_ns(vcpu);
+			/* we had a short halt and our poll time is too small */
+			else if (vcpu->halt_poll_ns < halt_poll_ns &&
+				block_ns < halt_poll_ns)
+				grow_halt_poll_ns(vcpu);
+		} else {
+			vcpu->halt_poll_ns = 0;
+		}
+	}
 
 	trace_kvm_vcpu_wakeup(block_ns, waited, vcpu_valid_wakeup(vcpu));
 	kvm_arch_vcpu_block_finish(vcpu);