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

Pull kvm fixes from Paolo Bonzini:
 "ARM:
   - fix compilation error when PMD and PUD are folded
   - fix regression in reads-as-zero behaviour of ID_AA64ZFR0_EL1
   - add aarch64 get-reg-list test

  x86:
   - fix semantic conflict between two series merged for 5.10
   - fix (and test) enforcement of paravirtual cpuid features

  selftests:
   - various cleanups to memory management selftests
   - new selftests testcase for performance of dirty logging"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (30 commits)
  KVM: selftests: allow two iterations of dirty_log_perf_test
  KVM: selftests: Introduce the dirty log perf test
  KVM: selftests: Make the number of vcpus global
  KVM: selftests: Make the per vcpu memory size global
  KVM: selftests: Drop pointless vm_create wrapper
  KVM: selftests: Add wrfract to common guest code
  KVM: selftests: Simplify demand_paging_test with timespec_diff_now
  KVM: selftests: Remove address rounding in guest code
  KVM: selftests: Factor code out of demand_paging_test
  KVM: selftests: Use a single binary for dirty/clear log test
  KVM: selftests: Always clear dirty bitmap after iteration
  KVM: selftests: Add blessed SVE registers to get-reg-list
  KVM: selftests: Add aarch64 get-reg-list test
  selftests: kvm: test enforcement of paravirtual cpuid features
  selftests: kvm: Add exception handling to selftests
  selftests: kvm: Clear uc so UCALL_NONE is being properly reported
  selftests: kvm: Fix the segment descriptor layout to match the actual layout
  KVM: x86: handle MSR_IA32_DEBUGCTLMSR with report_ignored_msrs
  kvm: x86: request masterclock update any time guest uses different msr
  kvm: x86: ensure pv_cpuid.features is initialized when enabling cap
  ...

Documentation/virt/kvm/api.rst

@@ -6367,7 +6367,7 @@ accesses that would usually trigger a #GP by KVM into the guest will
 instead get bounced to user space through the KVM_EXIT_X86_RDMSR and
 KVM_EXIT_X86_WRMSR exit notifications.
 
-8.25 KVM_X86_SET_MSR_FILTER
+8.27 KVM_X86_SET_MSR_FILTER
 ---------------------------
 
 :Architectures: x86
@@ -6381,8 +6381,7 @@ In combination with KVM_CAP_X86_USER_SPACE_MSR, this allows user space to
 trap and emulate MSRs that are outside of the scope of KVM as well as
 limit the attack surface on KVM's MSR emulation code.
 
-
-8.26 KVM_CAP_ENFORCE_PV_CPUID
+8.28 KVM_CAP_ENFORCE_PV_CPUID
 -----------------------------
 
 Architectures: x86

arch/arm64/kvm/mmu.c

@@ -788,10 +788,12 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
 	}
 
 	switch (vma_shift) {
+#ifndef __PAGETABLE_PMD_FOLDED
 	case PUD_SHIFT:
 		if (fault_supports_stage2_huge_mapping(memslot, hva, PUD_SIZE))
 			break;
 		fallthrough;
+#endif
 	case CONT_PMD_SHIFT:
 		vma_shift = PMD_SHIFT;
 		fallthrough;

arch/arm64/kvm/sys_regs.c

@@ -1069,7 +1069,7 @@ static bool trap_ptrauth(struct kvm_vcpu *vcpu,
 static unsigned int ptrauth_visibility(const struct kvm_vcpu *vcpu,
 			const struct sys_reg_desc *rd)
 {
-	return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN_USER | REG_HIDDEN_GUEST;
+	return vcpu_has_ptrauth(vcpu) ? 0 : REG_HIDDEN;
 }
 
 #define __PTRAUTH_KEY(k)						\
@@ -1153,6 +1153,22 @@ static u64 read_id_reg(const struct kvm_vcpu *vcpu,
 	return val;
 }
 
+static unsigned int id_visibility(const struct kvm_vcpu *vcpu,
+				  const struct sys_reg_desc *r)
+{
+	u32 id = sys_reg((u32)r->Op0, (u32)r->Op1,
+			 (u32)r->CRn, (u32)r->CRm, (u32)r->Op2);
+
+	switch (id) {
+	case SYS_ID_AA64ZFR0_EL1:
+		if (!vcpu_has_sve(vcpu))
+			return REG_RAZ;
+		break;
+	}
+
+	return 0;
+}
+
 /* cpufeature ID register access trap handlers */
 
 static bool __access_id_reg(struct kvm_vcpu *vcpu,
@@ -1171,7 +1187,9 @@ static bool access_id_reg(struct kvm_vcpu *vcpu,
 			  struct sys_reg_params *p,
 			  const struct sys_reg_desc *r)
 {
-	return __access_id_reg(vcpu, p, r, false);
+	bool raz = sysreg_visible_as_raz(vcpu, r);
+
+	return __access_id_reg(vcpu, p, r, raz);
 }
 
 static bool access_raz_id_reg(struct kvm_vcpu *vcpu,
@@ -1192,72 +1210,7 @@ static unsigned int sve_visibility(const struct kvm_vcpu *vcpu,
 	if (vcpu_has_sve(vcpu))
 		return 0;
 
-	return REG_HIDDEN_USER | REG_HIDDEN_GUEST;
-}
-
-/* Visibility overrides for SVE-specific ID registers */
-static unsigned int sve_id_visibility(const struct kvm_vcpu *vcpu,
-				      const struct sys_reg_desc *rd)
-{
-	if (vcpu_has_sve(vcpu))
-		return 0;
-
-	return REG_HIDDEN_USER;
-}
-
-/* Generate the emulated ID_AA64ZFR0_EL1 value exposed to the guest */
-static u64 guest_id_aa64zfr0_el1(const struct kvm_vcpu *vcpu)
-{
-	if (!vcpu_has_sve(vcpu))
-		return 0;
-
-	return read_sanitised_ftr_reg(SYS_ID_AA64ZFR0_EL1);
-}
-
-static bool access_id_aa64zfr0_el1(struct kvm_vcpu *vcpu,
-				   struct sys_reg_params *p,
-				   const struct sys_reg_desc *rd)
-{
-	if (p->is_write)
-		return write_to_read_only(vcpu, p, rd);
-
-	p->regval = guest_id_aa64zfr0_el1(vcpu);
-	return true;
-}
-
-static int get_id_aa64zfr0_el1(struct kvm_vcpu *vcpu,
-		const struct sys_reg_desc *rd,
-		const struct kvm_one_reg *reg, void __user *uaddr)
-{
-	u64 val;
-
-	if (WARN_ON(!vcpu_has_sve(vcpu)))
-		return -ENOENT;
-
-	val = guest_id_aa64zfr0_el1(vcpu);
-	return reg_to_user(uaddr, &val, reg->id);
-}
-
-static int set_id_aa64zfr0_el1(struct kvm_vcpu *vcpu,
-		const struct sys_reg_desc *rd,
-		const struct kvm_one_reg *reg, void __user *uaddr)
-{
-	const u64 id = sys_reg_to_index(rd);
-	int err;
-	u64 val;
-
-	if (WARN_ON(!vcpu_has_sve(vcpu)))
-		return -ENOENT;
-
-	err = reg_from_user(&val, uaddr, id);
-	if (err)
-		return err;
-
-	/* This is what we mean by invariant: you can't change it. */
-	if (val != guest_id_aa64zfr0_el1(vcpu))
-		return -EINVAL;
-
-	return 0;
+	return REG_HIDDEN;
 }
 
 /*
@@ -1299,13 +1252,17 @@ static int __set_id_reg(const struct kvm_vcpu *vcpu,
 static int get_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		      const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	return __get_id_reg(vcpu, rd, uaddr, false);
+	bool raz = sysreg_visible_as_raz(vcpu, rd);
+
+	return __get_id_reg(vcpu, rd, uaddr, raz);
 }
 
 static int set_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
 		      const struct kvm_one_reg *reg, void __user *uaddr)
 {
-	return __set_id_reg(vcpu, rd, uaddr, false);
+	bool raz = sysreg_visible_as_raz(vcpu, rd);
+
+	return __set_id_reg(vcpu, rd, uaddr, raz);
 }
 
 static int get_raz_id_reg(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd,
@@ -1397,6 +1354,7 @@ static bool access_mte_regs(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 	.access	= access_id_reg,		\
 	.get_user = get_id_reg,			\
 	.set_user = set_id_reg,			\
+	.visibility = id_visibility,		\
 }
 
 /*
@@ -1518,7 +1476,7 @@ static const struct sys_reg_desc sys_reg_descs[] = {
 	ID_SANITISED(ID_AA64PFR1_EL1),
 	ID_UNALLOCATED(4,2),
 	ID_UNALLOCATED(4,3),
-	{ SYS_DESC(SYS_ID_AA64ZFR0_EL1), access_id_aa64zfr0_el1, .get_user = get_id_aa64zfr0_el1, .set_user = set_id_aa64zfr0_el1, .visibility = sve_id_visibility },
+	ID_SANITISED(ID_AA64ZFR0_EL1),
 	ID_UNALLOCATED(4,5),
 	ID_UNALLOCATED(4,6),
 	ID_UNALLOCATED(4,7),
@@ -2185,7 +2143,7 @@ static void perform_access(struct kvm_vcpu *vcpu,
 	trace_kvm_sys_access(*vcpu_pc(vcpu), params, r);
 
 	/* Check for regs disabled by runtime config */
-	if (sysreg_hidden_from_guest(vcpu, r)) {
+	if (sysreg_hidden(vcpu, r)) {
 		kvm_inject_undefined(vcpu);
 		return;
 	}
@@ -2684,7 +2642,7 @@ int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg
 		return get_invariant_sys_reg(reg->id, uaddr);
 
 	/* Check for regs disabled by runtime config */
-	if (sysreg_hidden_from_user(vcpu, r))
+	if (sysreg_hidden(vcpu, r))
 		return -ENOENT;
 
 	if (r->get_user)
@@ -2709,7 +2667,7 @@ int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg
 		return set_invariant_sys_reg(reg->id, uaddr);
 
 	/* Check for regs disabled by runtime config */
-	if (sysreg_hidden_from_user(vcpu, r))
+	if (sysreg_hidden(vcpu, r))
 		return -ENOENT;
 
 	if (r->set_user)
@@ -2780,7 +2738,7 @@ static int walk_one_sys_reg(const struct kvm_vcpu *vcpu,
 	if (!(rd->reg || rd->get_user))
 		return 0;
 
-	if (sysreg_hidden_from_user(vcpu, rd))
+	if (sysreg_hidden(vcpu, rd))
 		return 0;
 
 	if (!copy_reg_to_user(rd, uind))

arch/arm64/kvm/sys_regs.h

@@ -59,8 +59,8 @@ struct sys_reg_desc {
 				   const struct sys_reg_desc *rd);
 };
 
-#define REG_HIDDEN_USER		(1 << 0) /* hidden from userspace ioctls */
-#define REG_HIDDEN_GUEST	(1 << 1) /* hidden from guest */
+#define REG_HIDDEN		(1 << 0) /* hidden from userspace and guest */
+#define REG_RAZ			(1 << 1) /* RAZ from userspace and guest */
 
 static __printf(2, 3)
 inline void print_sys_reg_msg(const struct sys_reg_params *p,
@@ -111,22 +111,22 @@ static inline void reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r
 	__vcpu_sys_reg(vcpu, r->reg) = r->val;
 }
 
-static inline bool sysreg_hidden_from_guest(const struct kvm_vcpu *vcpu,
+static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu,
 				 const struct sys_reg_desc *r)
 {
 	if (likely(!r->visibility))
 		return false;
 
-	return r->visibility(vcpu, r) & REG_HIDDEN_GUEST;
+	return r->visibility(vcpu, r) & REG_HIDDEN;
 }
 
-static inline bool sysreg_hidden_from_user(const struct kvm_vcpu *vcpu,
+static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu,
 					 const struct sys_reg_desc *r)
 {
 	if (likely(!r->visibility))
 		return false;
 
-	return r->visibility(vcpu, r) & REG_HIDDEN_USER;
+	return r->visibility(vcpu, r) & REG_RAZ;
 }
 
 static inline int cmp_sys_reg(const struct sys_reg_desc *i1,

arch/x86/kvm/cpuid.c

@@ -90,6 +90,20 @@ static int kvm_check_cpuid(struct kvm_cpuid_entry2 *entries, int nent)
 	return 0;
 }
 
+void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0);
+
+	/*
+	 * save the feature bitmap to avoid cpuid lookup for every PV
+	 * operation
+	 */
+	if (best)
+		vcpu->arch.pv_cpuid.features = best->eax;
+}
+
 void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
@@ -124,13 +138,6 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
 		(best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
 		best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
 
-	/*
-	 * save the feature bitmap to avoid cpuid lookup for every PV
-	 * operation
-	 */
-	if (best)
-		vcpu->arch.pv_cpuid.features = best->eax;
-
 	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT)) {
 		best = kvm_find_cpuid_entry(vcpu, 0x1, 0);
 		if (best)
@@ -162,6 +169,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		vcpu->arch.guest_supported_xcr0 =
 			(best->eax | ((u64)best->edx << 32)) & supported_xcr0;
 
+	kvm_update_pv_runtime(vcpu);
+
 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
 	kvm_mmu_reset_context(vcpu);
 

arch/x86/kvm/cpuid.h

@@ -11,6 +11,7 @@ extern u32 kvm_cpu_caps[NCAPINTS] __read_mostly;
 void kvm_set_cpu_caps(void);
 
 void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu);
+void kvm_update_pv_runtime(struct kvm_vcpu *vcpu);
 struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
 					      u32 function, u32 index);
 int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,

arch/x86/kvm/mmu/mmu.c

@@ -856,13 +856,15 @@ static int pte_list_add(struct kvm_vcpu *vcpu, u64 *spte,
 	} else {
 		rmap_printk("pte_list_add: %p %llx many->many\n", spte, *spte);
 		desc = (struct pte_list_desc *)(rmap_head->val & ~1ul);
-		while (desc->sptes[PTE_LIST_EXT-1] && desc->more) {
-			desc = desc->more;
+		while (desc->sptes[PTE_LIST_EXT-1]) {
 			count += PTE_LIST_EXT;
-		}
-		if (desc->sptes[PTE_LIST_EXT-1]) {
+
+			if (!desc->more) {
 				desc->more = mmu_alloc_pte_list_desc(vcpu);
 				desc = desc->more;
+				break;
+			}
+			desc = desc->more;
 		}
 		for (i = 0; desc->sptes[i]; ++i)
 			++count;

arch/x86/kvm/x86.c

@@ -255,10 +255,9 @@ static struct kmem_cache *x86_emulator_cache;
 
 /*
  * When called, it means the previous get/set msr reached an invalid msr.
- * Return 0 if we want to ignore/silent this failed msr access, or 1 if we want
- * to fail the caller.
+ * Return true if we want to ignore/silent this failed msr access.
  */
-static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
+static bool kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
 				  u64 data, bool write)
 {
 	const char *op = write ? "wrmsr" : "rdmsr";
@@ -268,11 +267,11 @@ static int kvm_msr_ignored_check(struct kvm_vcpu *vcpu, u32 msr,
 			kvm_pr_unimpl("ignored %s: 0x%x data 0x%llx\n",
 				      op, msr, data);
 		/* Mask the error */
-		return 0;
+		return true;
 	} else {
 		kvm_debug_ratelimited("unhandled %s: 0x%x data 0x%llx\n",
 				      op, msr, data);
-		return -ENOENT;
+		return false;
 	}
 }
 
@@ -1416,7 +1415,8 @@ static int do_get_msr_feature(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 	if (r == KVM_MSR_RET_INVALID) {
 		/* Unconditionally clear the output for simplicity */
 		*data = 0;
-		r = kvm_msr_ignored_check(vcpu, index, 0, false);
+		if (kvm_msr_ignored_check(vcpu, index, 0, false))
+			r = 0;
 	}
 
 	if (r)
@@ -1540,7 +1540,7 @@ static int __kvm_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data,
 	struct msr_data msr;
 
 	if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_WRITE))
-		return -EPERM;
+		return KVM_MSR_RET_FILTERED;
 
 	switch (index) {
 	case MSR_FS_BASE:
@@ -1581,7 +1581,8 @@ static int kvm_set_msr_ignored_check(struct kvm_vcpu *vcpu,
 	int ret = __kvm_set_msr(vcpu, index, data, host_initiated);
 
 	if (ret == KVM_MSR_RET_INVALID)
-		ret = kvm_msr_ignored_check(vcpu, index, data, true);
+		if (kvm_msr_ignored_check(vcpu, index, data, true))
+			ret = 0;
 
 	return ret;
 }
@@ -1599,7 +1600,7 @@ int __kvm_get_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
 	int ret;
 
 	if (!host_initiated && !kvm_msr_allowed(vcpu, index, KVM_MSR_FILTER_READ))
-		return -EPERM;
+		return KVM_MSR_RET_FILTERED;
 
 	msr.index = index;
 	msr.host_initiated = host_initiated;
@@ -1618,7 +1619,8 @@ static int kvm_get_msr_ignored_check(struct kvm_vcpu *vcpu,
 	if (ret == KVM_MSR_RET_INVALID) {
 		/* Unconditionally clear *data for simplicity */
 		*data = 0;
-		ret = kvm_msr_ignored_check(vcpu, index, 0, false);
+		if (kvm_msr_ignored_check(vcpu, index, 0, false))
+			ret = 0;
 	}
 
 	return ret;
@@ -1662,9 +1664,9 @@ static int complete_emulated_wrmsr(struct kvm_vcpu *vcpu)
 static u64 kvm_msr_reason(int r)
 {
 	switch (r) {
-	case -ENOENT:
+	case KVM_MSR_RET_INVALID:
 		return KVM_MSR_EXIT_REASON_UNKNOWN;
-	case -EPERM:
+	case KVM_MSR_RET_FILTERED:
 		return KVM_MSR_EXIT_REASON_FILTER;
 	default:
 		return KVM_MSR_EXIT_REASON_INVAL;
@@ -1965,7 +1967,7 @@ static void kvm_write_system_time(struct kvm_vcpu *vcpu, gpa_t system_time,
 	struct kvm_arch *ka = &vcpu->kvm->arch;
 
 	if (vcpu->vcpu_id == 0 && !host_initiated) {
-		if (ka->boot_vcpu_runs_old_kvmclock && old_msr)
+		if (ka->boot_vcpu_runs_old_kvmclock != old_msr)
 			kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 
 		ka->boot_vcpu_runs_old_kvmclock = old_msr;
@@ -3063,7 +3065,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			/* Values other than LBR and BTF are vendor-specific,
 			   thus reserved and should throw a #GP */
 			return 1;
-		}
+		} else if (report_ignored_msrs)
 			vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
 				    __func__, data);
 		break;
@@ -3463,29 +3465,63 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		msr_info->data = vcpu->arch.efer;
 		break;
 	case MSR_KVM_WALL_CLOCK:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
+			return 1;
+
+		msr_info->data = vcpu->kvm->arch.wall_clock;
+		break;
 	case MSR_KVM_WALL_CLOCK_NEW:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
+			return 1;
+
 		msr_info->data = vcpu->kvm->arch.wall_clock;
 		break;
 	case MSR_KVM_SYSTEM_TIME:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE))
+			return 1;
+
+		msr_info->data = vcpu->arch.time;
+		break;
 	case MSR_KVM_SYSTEM_TIME_NEW:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_CLOCKSOURCE2))
+			return 1;
+
 		msr_info->data = vcpu->arch.time;
 		break;
 	case MSR_KVM_ASYNC_PF_EN:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+			return 1;
+
 		msr_info->data = vcpu->arch.apf.msr_en_val;
 		break;
 	case MSR_KVM_ASYNC_PF_INT:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF_INT))
+			return 1;
+
 		msr_info->data = vcpu->arch.apf.msr_int_val;
 		break;
 	case MSR_KVM_ASYNC_PF_ACK:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_ASYNC_PF))
+			return 1;
+
 		msr_info->data = 0;
 		break;
 	case MSR_KVM_STEAL_TIME:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_STEAL_TIME))
+			return 1;
+
 		msr_info->data = vcpu->arch.st.msr_val;
 		break;
 	case MSR_KVM_PV_EOI_EN:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_PV_EOI))
+			return 1;
+
 		msr_info->data = vcpu->arch.pv_eoi.msr_val;
 		break;
 	case MSR_KVM_POLL_CONTROL:
+		if (!guest_pv_has(vcpu, KVM_FEATURE_POLL_CONTROL))
+			return 1;
+
 		msr_info->data = vcpu->arch.msr_kvm_poll_control;
 		break;
 	case MSR_IA32_P5_MC_ADDR:
@@ -4575,6 +4611,8 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
 
 	case KVM_CAP_ENFORCE_PV_FEATURE_CPUID:
 		vcpu->arch.pv_cpuid.enforce = cap->args[0];
+		if (vcpu->arch.pv_cpuid.enforce)
+			kvm_update_pv_runtime(vcpu);
 
 		return 0;
 

arch/x86/kvm/x86.h

@@ -376,7 +376,13 @@ int kvm_handle_memory_failure(struct kvm_vcpu *vcpu, int r,
 int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva);
 bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type);
 
-#define  KVM_MSR_RET_INVALID  2
+/*
+ * Internal error codes that are used to indicate that MSR emulation encountered
+ * an error that should result in #GP in the guest, unless userspace
+ * handles it.
+ */
+#define  KVM_MSR_RET_INVALID	2	/* in-kernel MSR emulation #GP condition */
+#define  KVM_MSR_RET_FILTERED	3	/* #GP due to userspace MSR filter */
 
 #define __cr4_reserved_bits(__cpu_has, __c)             \
 ({                                                      \

tools/testing/selftests/kvm/.gitignore

 # SPDX-License-Identifier: GPL-2.0-only
+/aarch64/get-reg-list
+/aarch64/get-reg-list-sve
 /s390x/memop
 /s390x/resets
 /s390x/sync_regs_test
 /x86_64/cr4_cpuid_sync_test
 /x86_64/debug_regs
 /x86_64/evmcs_test
+/x86_64/kvm_pv_test
 /x86_64/hyperv_cpuid
 /x86_64/mmio_warning_test
 /x86_64/platform_info_test
@@ -24,6 +27,7 @@
 /clear_dirty_log_test
 /demand_paging_test
 /dirty_log_test
+/dirty_log_perf_test
 /kvm_create_max_vcpus
 /set_memory_region_test
 /steal_time

tools/testing/selftests/kvm/Makefile

@@ -34,13 +34,14 @@ ifeq ($(ARCH),s390)
 endif
 
 LIBKVM = lib/assert.c lib/elf.c lib/io.c lib/kvm_util.c lib/sparsebit.c lib/test_util.c
-LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c
+LIBKVM_x86_64 = lib/x86_64/processor.c lib/x86_64/vmx.c lib/x86_64/svm.c lib/x86_64/ucall.c lib/x86_64/handlers.S
 LIBKVM_aarch64 = lib/aarch64/processor.c lib/aarch64/ucall.c
 LIBKVM_s390x = lib/s390x/processor.c lib/s390x/ucall.c
 
 TEST_GEN_PROGS_x86_64 = x86_64/cr4_cpuid_sync_test
 TEST_GEN_PROGS_x86_64 += x86_64/evmcs_test
 TEST_GEN_PROGS_x86_64 += x86_64/hyperv_cpuid
+TEST_GEN_PROGS_x86_64 += x86_64/kvm_pv_test
 TEST_GEN_PROGS_x86_64 += x86_64/mmio_warning_test
 TEST_GEN_PROGS_x86_64 += x86_64/platform_info_test
 TEST_GEN_PROGS_x86_64 += x86_64/set_sregs_test
@@ -58,14 +59,15 @@ TEST_GEN_PROGS_x86_64 += x86_64/xss_msr_test
 TEST_GEN_PROGS_x86_64 += x86_64/debug_regs
 TEST_GEN_PROGS_x86_64 += x86_64/tsc_msrs_test
 TEST_GEN_PROGS_x86_64 += x86_64/user_msr_test
-TEST_GEN_PROGS_x86_64 += clear_dirty_log_test
 TEST_GEN_PROGS_x86_64 += demand_paging_test
 TEST_GEN_PROGS_x86_64 += dirty_log_test
+TEST_GEN_PROGS_x86_64 += dirty_log_perf_test
 TEST_GEN_PROGS_x86_64 += kvm_create_max_vcpus
 TEST_GEN_PROGS_x86_64 += set_memory_region_test
 TEST_GEN_PROGS_x86_64 += steal_time
 
-TEST_GEN_PROGS_aarch64 += clear_dirty_log_test
+TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list
+TEST_GEN_PROGS_aarch64 += aarch64/get-reg-list-sve
 TEST_GEN_PROGS_aarch64 += demand_paging_test
 TEST_GEN_PROGS_aarch64 += dirty_log_test
 TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus
@@ -111,14 +113,21 @@ LDFLAGS += -pthread $(no-pie-option) $(pgste-option)
 include ../lib.mk
 
 STATIC_LIBS := $(OUTPUT)/libkvm.a
-LIBKVM_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM))
-EXTRA_CLEAN += $(LIBKVM_OBJ) $(STATIC_LIBS) cscope.*
+LIBKVM_C := $(filter %.c,$(LIBKVM))
+LIBKVM_S := $(filter %.S,$(LIBKVM))
+LIBKVM_C_OBJ := $(patsubst %.c, $(OUTPUT)/%.o, $(LIBKVM_C))
+LIBKVM_S_OBJ := $(patsubst %.S, $(OUTPUT)/%.o, $(LIBKVM_S))
+EXTRA_CLEAN += $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ) $(STATIC_LIBS) cscope.*
+
+x := $(shell mkdir -p $(sort $(dir $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ))))
+$(LIBKVM_C_OBJ): $(OUTPUT)/%.o: %.c
+	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
-x := $(shell mkdir -p $(sort $(dir $(LIBKVM_OBJ))))
-$(LIBKVM_OBJ): $(OUTPUT)/%.o: %.c
+$(LIBKVM_S_OBJ): $(OUTPUT)/%.o: %.S
 	$(CC) $(CFLAGS) $(CPPFLAGS) $(TARGET_ARCH) -c $< -o $@
 
-$(OUTPUT)/libkvm.a: $(LIBKVM_OBJ)
+LIBKVM_OBJS = $(LIBKVM_C_OBJ) $(LIBKVM_S_OBJ)
+$(OUTPUT)/libkvm.a: $(LIBKVM_OBJS)
 	$(AR) crs $@ $^
 
 x := $(shell mkdir -p $(sort $(dir $(TEST_GEN_PROGS))))

tools/testing/selftests/kvm/aarch64/get-reg-list-sve.c

+// SPDX-License-Identifier: GPL-2.0
+#define REG_LIST_SVE
+#include "get-reg-list.c"

tools/testing/selftests/kvm/clear_dirty_log_test.c

-#define USE_CLEAR_DIRTY_LOG
-#define KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE (1 << 0)
-#define KVM_DIRTY_LOG_INITIALLY_SET         (1 << 1)
-#define KVM_DIRTY_LOG_MANUAL_CAPS   (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \
-		KVM_DIRTY_LOG_INITIALLY_SET)
-#include "dirty_log_test.c"

tools/testing/selftests/kvm/dirty_log_test.c

@@ -128,6 +128,78 @@ static uint64_t host_dirty_count;
 static uint64_t host_clear_count;
 static uint64_t host_track_next_count;
 
+enum log_mode_t {
+	/* Only use KVM_GET_DIRTY_LOG for logging */
+	LOG_MODE_DIRTY_LOG = 0,
+
+	/* Use both KVM_[GET|CLEAR]_DIRTY_LOG for logging */
+	LOG_MODE_CLEAR_LOG = 1,
+
+	LOG_MODE_NUM,
+
+	/* Run all supported modes */
+	LOG_MODE_ALL = LOG_MODE_NUM,
+};
+
+/* Mode of logging to test.  Default is to run all supported modes */
+static enum log_mode_t host_log_mode_option = LOG_MODE_ALL;
+/* Logging mode for current run */
+static enum log_mode_t host_log_mode;
+
+static bool clear_log_supported(void)
+{
+	return kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+}
+
+static void clear_log_create_vm_done(struct kvm_vm *vm)
+{
+	struct kvm_enable_cap cap = {};
+	u64 manual_caps;
+
+	manual_caps = kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
+	TEST_ASSERT(manual_caps, "MANUAL_CAPS is zero!");
+	manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
+			KVM_DIRTY_LOG_INITIALLY_SET);
+	cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
+	cap.args[0] = manual_caps;
+	vm_enable_cap(vm, &cap);
+}
+
+static void dirty_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
+					  void *bitmap, uint32_t num_pages)
+{
+	kvm_vm_get_dirty_log(vm, slot, bitmap);
+}
+
+static void clear_log_collect_dirty_pages(struct kvm_vm *vm, int slot,
+					  void *bitmap, uint32_t num_pages)
+{
+	kvm_vm_get_dirty_log(vm, slot, bitmap);
+	kvm_vm_clear_dirty_log(vm, slot, bitmap, 0, num_pages);
+}
+
+struct log_mode {
+	const char *name;
+	/* Return true if this mode is supported, otherwise false */
+	bool (*supported)(void);
+	/* Hook when the vm creation is done (before vcpu creation) */
+	void (*create_vm_done)(struct kvm_vm *vm);
+	/* Hook to collect the dirty pages into the bitmap provided */
+	void (*collect_dirty_pages) (struct kvm_vm *vm, int slot,
+				     void *bitmap, uint32_t num_pages);
+} log_modes[LOG_MODE_NUM] = {
+	{
+		.name = "dirty-log",
+		.collect_dirty_pages = dirty_log_collect_dirty_pages,
+	},
+	{
+		.name = "clear-log",
+		.supported = clear_log_supported,
+		.create_vm_done = clear_log_create_vm_done,
+		.collect_dirty_pages = clear_log_collect_dirty_pages,
+	},
+};
+
 /*
  * We use this bitmap to track some pages that should have its dirty
  * bit set in the _next_ iteration.  For example, if we detected the
@@ -137,6 +209,44 @@ static uint64_t host_track_next_count;
  */
 static unsigned long *host_bmap_track;
 
+static void log_modes_dump(void)
+{
+	int i;
+
+	printf("all");
+	for (i = 0; i < LOG_MODE_NUM; i++)
+		printf(", %s", log_modes[i].name);
+	printf("\n");
+}
+
+static bool log_mode_supported(void)
+{
+	struct log_mode *mode = &log_modes[host_log_mode];
+
+	if (mode->supported)
+		return mode->supported();
+
+	return true;
+}
+
+static void log_mode_create_vm_done(struct kvm_vm *vm)
+{
+	struct log_mode *mode = &log_modes[host_log_mode];
+
+	if (mode->create_vm_done)
+		mode->create_vm_done(vm);
+}
+
+static void log_mode_collect_dirty_pages(struct kvm_vm *vm, int slot,
+					 void *bitmap, uint32_t num_pages)
+{
+	struct log_mode *mode = &log_modes[host_log_mode];
+
+	TEST_ASSERT(mode->collect_dirty_pages != NULL,
+		    "collect_dirty_pages() is required for any log mode!");
+	mode->collect_dirty_pages(vm, slot, bitmap, num_pages);
+}
+
 static void generate_random_array(uint64_t *guest_array, uint64_t size)
 {
 	uint64_t i;
@@ -195,7 +305,7 @@ static void vm_dirty_log_verify(enum vm_guest_mode mode, unsigned long *bmap)
 				    page);
 		}
 
-		if (test_bit_le(page, bmap)) {
+		if (test_and_clear_bit_le(page, bmap)) {
 			host_dirty_count++;
 			/*
 			 * If the bit is set, the value written onto
@@ -252,11 +362,12 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
 
 	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
 
-	vm = _vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
+	vm = vm_create(mode, DEFAULT_GUEST_PHY_PAGES + extra_pg_pages, O_RDWR);
 	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
 #ifdef __x86_64__
 	vm_create_irqchip(vm);
 #endif
+	log_mode_create_vm_done(vm);
 	vm_vcpu_add_default(vm, vcpuid, guest_code);
 	return vm;
 }
@@ -264,10 +375,6 @@ static struct kvm_vm *create_vm(enum vm_guest_mode mode, uint32_t vcpuid,
 #define DIRTY_MEM_BITS 30 /* 1G */
 #define PAGE_SHIFT_4K  12
 
-#ifdef USE_CLEAR_DIRTY_LOG
-static u64 dirty_log_manual_caps;
-#endif
-
 static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 		     unsigned long interval, uint64_t phys_offset)
 {
@@ -275,6 +382,12 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	struct kvm_vm *vm;
 	unsigned long *bmap;
 
+	if (!log_mode_supported()) {
+		print_skip("Log mode '%s' not supported",
+			   log_modes[host_log_mode].name);
+		return;
+	}
+
 	/*
 	 * We reserve page table for 2 times of extra dirty mem which
 	 * will definitely cover the original (1G+) test range.  Here
@@ -317,14 +430,6 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	bmap = bitmap_alloc(host_num_pages);
 	host_bmap_track = bitmap_alloc(host_num_pages);
 
-#ifdef USE_CLEAR_DIRTY_LOG
-	struct kvm_enable_cap cap = {};
-
-	cap.cap = KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2;
-	cap.args[0] = dirty_log_manual_caps;
-	vm_enable_cap(vm, &cap);
-#endif
-
 	/* Add an extra memory slot for testing dirty logging */
 	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
 				    guest_test_phys_mem,
@@ -362,11 +467,8 @@ static void run_test(enum vm_guest_mode mode, unsigned long iterations,
 	while (iteration < iterations) {
 		/* Give the vcpu thread some time to dirty some pages */
 		usleep(interval * 1000);
-		kvm_vm_get_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap);
-#ifdef USE_CLEAR_DIRTY_LOG
-		kvm_vm_clear_dirty_log(vm, TEST_MEM_SLOT_INDEX, bmap, 0,
-				       host_num_pages);
-#endif
+		log_mode_collect_dirty_pages(vm, TEST_MEM_SLOT_INDEX,
+					     bmap, host_num_pages);
 		vm_dirty_log_verify(mode, bmap);
 		iteration++;
 		sync_global_to_guest(vm, iteration);
@@ -410,6 +512,9 @@ static void help(char *name)
 	       TEST_HOST_LOOP_INTERVAL);
 	printf(" -p: specify guest physical test memory offset\n"
 	       "     Warning: a low offset can conflict with the loaded test code.\n");
+	printf(" -M: specify the host logging mode "
+	       "(default: run all log modes).  Supported modes: \n\t");
+	log_modes_dump();
 	printf(" -m: specify the guest mode ID to test "
 	       "(default: test all supported modes)\n"
 	       "     This option may be used multiple times.\n"
@@ -429,18 +534,7 @@ int main(int argc, char *argv[])
 	bool mode_selected = false;
 	uint64_t phys_offset = 0;
 	unsigned int mode;
-	int opt, i;
-
-#ifdef USE_CLEAR_DIRTY_LOG
-	dirty_log_manual_caps =
-		kvm_check_cap(KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2);
-	if (!dirty_log_manual_caps) {
-		print_skip("KVM_CLEAR_DIRTY_LOG not available");
-		exit(KSFT_SKIP);
-	}
-	dirty_log_manual_caps &= (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE |
-				  KVM_DIRTY_LOG_INITIALLY_SET);
-#endif
+	int opt, i, j;
 
 #ifdef __x86_64__
 	guest_mode_init(VM_MODE_PXXV48_4K, true, true);
@@ -464,7 +558,7 @@ int main(int argc, char *argv[])
 	guest_mode_init(VM_MODE_P40V48_4K, true, true);
 #endif
 
-	while ((opt = getopt(argc, argv, "hi:I:p:m:")) != -1) {
+	while ((opt = getopt(argc, argv, "hi:I:p:m:M:")) != -1) {
 		switch (opt) {
 		case 'i':
 			iterations = strtol(optarg, NULL, 10);
@@ -486,6 +580,26 @@ int main(int argc, char *argv[])
 				    "Guest mode ID %d too big", mode);
 			guest_modes[mode].enabled = true;
 			break;
+		case 'M':
+			if (!strcmp(optarg, "all")) {
+				host_log_mode_option = LOG_MODE_ALL;
+				break;
+			}
+			for (i = 0; i < LOG_MODE_NUM; i++) {
+				if (!strcmp(optarg, log_modes[i].name)) {
+					pr_info("Setting log mode to: '%s'\n",
+						optarg);
+					host_log_mode_option = i;
+					break;
+				}
+			}
+			if (i == LOG_MODE_NUM) {
+				printf("Log mode '%s' invalid. Please choose "
+				       "from: ", optarg);
+				log_modes_dump();
+				exit(1);
+			}
+			break;
 		case 'h':
 		default:
 			help(argv[0]);
@@ -507,8 +621,19 @@ int main(int argc, char *argv[])
 		TEST_ASSERT(guest_modes[i].supported,
 			    "Guest mode ID %d (%s) not supported.",
 			    i, vm_guest_mode_string(i));
+		if (host_log_mode_option == LOG_MODE_ALL) {
+			/* Run each log mode */
+			for (j = 0; j < LOG_MODE_NUM; j++) {
+				pr_info("Testing Log Mode '%s'\n",
+					log_modes[j].name);
+				host_log_mode = j;
 				run_test(i, iterations, interval, phys_offset);
 			}
+		} else {
+			host_log_mode = host_log_mode_option;
+			run_test(i, iterations, interval, phys_offset);
+		}
+	}
 
 	return 0;
 }

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

@@ -63,9 +63,11 @@ enum vm_mem_backing_src_type {
 
 int kvm_check_cap(long cap);
 int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap);
+int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
+		    struct kvm_enable_cap *cap);
+void vm_enable_dirty_ring(struct kvm_vm *vm, uint32_t ring_size);
 
 struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
-struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm);
 void kvm_vm_free(struct kvm_vm *vmp);
 void kvm_vm_restart(struct kvm_vm *vmp, int perm);
 void kvm_vm_release(struct kvm_vm *vmp);
@@ -149,6 +151,7 @@ void vcpu_set_guest_debug(struct kvm_vm *vm, uint32_t vcpuid,
 			  struct kvm_guest_debug *debug);
 void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
 		       struct kvm_mp_state *mp_state);
+struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid);
 void vcpu_regs_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
 void vcpu_regs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_regs *regs);
 
@@ -294,6 +297,8 @@ int vm_create_device(struct kvm_vm *vm, struct kvm_create_device *cd);
 	memcpy(&(g), _p, sizeof(g));				\
 })
 
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid);
+
 /* Common ucalls */
 enum {
 	UCALL_NONE,

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

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * tools/testing/selftests/kvm/include/perf_test_util.h
+ *
+ * Copyright (C) 2020, Google LLC.
+ */
+
+#ifndef SELFTEST_KVM_PERF_TEST_UTIL_H
+#define SELFTEST_KVM_PERF_TEST_UTIL_H
+
+#include "kvm_util.h"
+#include "processor.h"
+
+#define MAX_VCPUS 512
+
+#define PAGE_SHIFT_4K  12
+#define PTES_PER_4K_PT 512
+
+#define TEST_MEM_SLOT_INDEX		1
+
+/* Default guest test virtual memory offset */
+#define DEFAULT_GUEST_TEST_MEM		0xc0000000
+
+#define DEFAULT_PER_VCPU_MEM_SIZE	(1 << 30) /* 1G */
+
+/*
+ * Guest physical memory offset of the testing memory slot.
+ * This will be set to the topmost valid physical address minus
+ * the test memory size.
+ */
+static uint64_t guest_test_phys_mem;
+
+/*
+ * Guest virtual memory offset of the testing memory slot.
+ * Must not conflict with identity mapped test code.
+ */
+static uint64_t guest_test_virt_mem = DEFAULT_GUEST_TEST_MEM;
+static uint64_t guest_percpu_mem_size = DEFAULT_PER_VCPU_MEM_SIZE;
+
+/* Number of VCPUs for the test */
+static int nr_vcpus = 1;
+
+struct vcpu_args {
+	uint64_t gva;
+	uint64_t pages;
+
+	/* Only used by the host userspace part of the vCPU thread */
+	int vcpu_id;
+};
+
+struct perf_test_args {
+	struct kvm_vm *vm;
+	uint64_t host_page_size;
+	uint64_t guest_page_size;
+	int wr_fract;
+
+	struct vcpu_args vcpu_args[MAX_VCPUS];
+};
+
+static struct perf_test_args perf_test_args;
+
+/*
+ * Continuously write to the first 8 bytes of each page in the
+ * specified region.
+ */
+static void guest_code(uint32_t vcpu_id)
+{
+	struct vcpu_args *vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+	uint64_t gva;
+	uint64_t pages;
+	int i;
+
+	/* Make sure vCPU args data structure is not corrupt. */
+	GUEST_ASSERT(vcpu_args->vcpu_id == vcpu_id);
+
+	gva = vcpu_args->gva;
+	pages = vcpu_args->pages;
+
+	while (true) {
+		for (i = 0; i < pages; i++) {
+			uint64_t addr = gva + (i * perf_test_args.guest_page_size);
+
+			if (i % perf_test_args.wr_fract == 0)
+				*(uint64_t *)addr = 0x0123456789ABCDEF;
+			else
+				READ_ONCE(*(uint64_t *)addr);
+		}
+
+		GUEST_SYNC(1);
+	}
+}
+
+static struct kvm_vm *create_vm(enum vm_guest_mode mode, int vcpus,
+				uint64_t vcpu_memory_bytes)
+{
+	struct kvm_vm *vm;
+	uint64_t pages = DEFAULT_GUEST_PHY_PAGES;
+	uint64_t guest_num_pages;
+
+	/* Account for a few pages per-vCPU for stacks */
+	pages += DEFAULT_STACK_PGS * vcpus;
+
+	/*
+	 * Reserve twice the ammount of memory needed to map the test region and
+	 * the page table / stacks region, at 4k, for page tables. Do the
+	 * calculation with 4K page size: the smallest of all archs. (e.g., 64K
+	 * page size guest will need even less memory for page tables).
+	 */
+	pages += (2 * pages) / PTES_PER_4K_PT;
+	pages += ((2 * vcpus * vcpu_memory_bytes) >> PAGE_SHIFT_4K) /
+		 PTES_PER_4K_PT;
+	pages = vm_adjust_num_guest_pages(mode, pages);
+
+	pr_info("Testing guest mode: %s\n", vm_guest_mode_string(mode));
+
+	vm = vm_create(mode, pages, O_RDWR);
+	kvm_vm_elf_load(vm, program_invocation_name, 0, 0);
+#ifdef __x86_64__
+	vm_create_irqchip(vm);
+#endif
+
+	perf_test_args.vm = vm;
+	perf_test_args.guest_page_size = vm_get_page_size(vm);
+	perf_test_args.host_page_size = getpagesize();
+
+	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.guest_page_size == 0,
+		    "Guest memory size is not guest page size aligned.");
+
+	guest_num_pages = (vcpus * vcpu_memory_bytes) /
+			  perf_test_args.guest_page_size;
+	guest_num_pages = vm_adjust_num_guest_pages(mode, guest_num_pages);
+
+	/*
+	 * If there should be more memory in the guest test region than there
+	 * can be pages in the guest, it will definitely cause problems.
+	 */
+	TEST_ASSERT(guest_num_pages < vm_get_max_gfn(vm),
+		    "Requested more guest memory than address space allows.\n"
+		    "    guest pages: %lx max gfn: %x vcpus: %d wss: %lx]\n",
+		    guest_num_pages, vm_get_max_gfn(vm), vcpus,
+		    vcpu_memory_bytes);
+
+	TEST_ASSERT(vcpu_memory_bytes % perf_test_args.host_page_size == 0,
+		    "Guest memory size is not host page size aligned.");
+
+	guest_test_phys_mem = (vm_get_max_gfn(vm) - guest_num_pages) *
+			      perf_test_args.guest_page_size;
+	guest_test_phys_mem &= ~(perf_test_args.host_page_size - 1);
+
+#ifdef __s390x__
+	/* Align to 1M (segment size) */
+	guest_test_phys_mem &= ~((1 << 20) - 1);
+#endif
+
+	pr_info("guest physical test memory offset: 0x%lx\n", guest_test_phys_mem);
+
+	/* Add an extra memory slot for testing */
+	vm_userspace_mem_region_add(vm, VM_MEM_SRC_ANONYMOUS,
+				    guest_test_phys_mem,
+				    TEST_MEM_SLOT_INDEX,
+				    guest_num_pages, 0);
+
+	/* Do mapping for the demand paging memory slot */
+	virt_map(vm, guest_test_virt_mem, guest_test_phys_mem, guest_num_pages, 0);
+
+	ucall_init(vm, NULL);
+
+	return vm;
+}
+
+static void add_vcpus(struct kvm_vm *vm, int vcpus, uint64_t vcpu_memory_bytes)
+{
+	vm_paddr_t vcpu_gpa;
+	struct vcpu_args *vcpu_args;
+	int vcpu_id;
+
+	for (vcpu_id = 0; vcpu_id < vcpus; vcpu_id++) {
+		vcpu_args = &perf_test_args.vcpu_args[vcpu_id];
+
+		vm_vcpu_add_default(vm, vcpu_id, guest_code);
+
+#ifdef __x86_64__
+		vcpu_set_cpuid(vm, vcpu_id, kvm_get_supported_cpuid());
+#endif
+
+		vcpu_args->vcpu_id = vcpu_id;
+		vcpu_args->gva = guest_test_virt_mem +
+				 (vcpu_id * vcpu_memory_bytes);
+		vcpu_args->pages = vcpu_memory_bytes /
+				   perf_test_args.guest_page_size;
+
+		vcpu_gpa = guest_test_phys_mem + (vcpu_id * vcpu_memory_bytes);
+		pr_debug("Added VCPU %d with test mem gpa [%lx, %lx)\n",
+			 vcpu_id, vcpu_gpa, vcpu_gpa + vcpu_memory_bytes);
+	}
+}
+
+#endif /* SELFTEST_KVM_PERF_TEST_UTIL_H */

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

@@ -64,5 +64,7 @@ int64_t timespec_to_ns(struct timespec ts);
 struct timespec timespec_add_ns(struct timespec ts, int64_t ns);
 struct timespec timespec_add(struct timespec ts1, struct timespec ts2);
 struct timespec timespec_sub(struct timespec ts1, struct timespec ts2);
+struct timespec timespec_diff_now(struct timespec start);
+struct timespec timespec_div(struct timespec ts, int divisor);
 
 #endif /* SELFTEST_KVM_TEST_UTIL_H */

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

@@ -36,6 +36,8 @@
 #define X86_CR4_SMAP		(1ul << 21)
 #define X86_CR4_PKE		(1ul << 22)
 
+#define UNEXPECTED_VECTOR_PORT 0xfff0u
+
 /* General Registers in 64-Bit Mode */
 struct gpr64_regs {
 	u64 rax;
@@ -59,7 +61,7 @@ struct gpr64_regs {
 struct desc64 {
 	uint16_t limit0;
 	uint16_t base0;
-	unsigned base1:8, s:1, type:4, dpl:2, p:1;
+	unsigned base1:8, type:4, s:1, dpl:2, p:1;
 	unsigned limit1:4, avl:1, l:1, db:1, g:1, base2:8;
 	uint32_t base3;
 	uint32_t zero1;
@@ -239,6 +241,11 @@ static inline struct desc_ptr get_idt(void)
 	return idt;
 }
 
+static inline void outl(uint16_t port, uint32_t value)
+{
+	__asm__ __volatile__("outl %%eax, %%dx" : : "d"(port), "a"(value));
+}
+
 #define SET_XMM(__var, __xmm) \
 	asm volatile("movq %0, %%"#__xmm : : "r"(__var) : #__xmm)
 
@@ -338,6 +345,35 @@ uint32_t kvm_get_cpuid_max_basic(void);
 uint32_t kvm_get_cpuid_max_extended(void);
 void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits);
 
+struct ex_regs {
+	uint64_t rax, rcx, rdx, rbx;
+	uint64_t rbp, rsi, rdi;
+	uint64_t r8, r9, r10, r11;
+	uint64_t r12, r13, r14, r15;
+	uint64_t vector;
+	uint64_t error_code;
+	uint64_t rip;
+	uint64_t cs;
+	uint64_t rflags;
+};
+
+void vm_init_descriptor_tables(struct kvm_vm *vm);
+void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid);
+void vm_handle_exception(struct kvm_vm *vm, int vector,
+			void (*handler)(struct ex_regs *));
+
+/*
+ * set_cpuid() - overwrites a matching cpuid entry with the provided value.
+ *		 matches based on ent->function && ent->index. returns true
+ *		 if a match was found and successfully overwritten.
+ * @cpuid: the kvm cpuid list to modify.
+ * @ent: cpuid entry to insert
+ */
+bool set_cpuid(struct kvm_cpuid2 *cpuid, struct kvm_cpuid_entry2 *ent);
+
+uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
+		       uint64_t a3);
+
 /*
  * Basic CPU control in CR0
  */

tools/testing/selftests/kvm/lib/aarch64/processor.c

@@ -350,3 +350,7 @@ void vcpu_args_set(struct kvm_vm *vm, uint32_t vcpuid, unsigned int num, ...)
 
 	va_end(ap);
 }
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+}

tools/testing/selftests/kvm/lib/aarch64/ucall.c

@@ -94,6 +94,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
 	struct kvm_run *run = vcpu_state(vm, vcpu_id);
 	struct ucall ucall = {};
 
+	if (uc)
+		memset(uc, 0, sizeof(*uc));
+
 	if (run->exit_reason == KVM_EXIT_MMIO &&
 	    run->mmio.phys_addr == (uint64_t)ucall_exit_mmio_addr) {
 		vm_vaddr_t gva;

tools/testing/selftests/kvm/lib/kvm_util.c

@@ -86,6 +86,34 @@ int vm_enable_cap(struct kvm_vm *vm, struct kvm_enable_cap *cap)
 	return ret;
 }
 
+/* VCPU Enable Capability
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpu_id - VCPU
+ *   cap - Capability
+ *
+ * Output Args: None
+ *
+ * Return: On success, 0. On failure a TEST_ASSERT failure is produced.
+ *
+ * Enables a capability (KVM_CAP_*) on the VCPU.
+ */
+int vcpu_enable_cap(struct kvm_vm *vm, uint32_t vcpu_id,
+		    struct kvm_enable_cap *cap)
+{
+	struct vcpu *vcpu = vcpu_find(vm, vcpu_id);
+	int r;
+
+	TEST_ASSERT(vcpu, "cannot find vcpu %d", vcpu_id);
+
+	r = ioctl(vcpu->fd, KVM_ENABLE_CAP, cap);
+	TEST_ASSERT(!r, "KVM_ENABLE_CAP vCPU ioctl failed,\n"
+			"  rc: %i, errno: %i", r, errno);
+
+	return r;
+}
+
 static void vm_open(struct kvm_vm *vm, int perm)
 {
 	vm->kvm_fd = open(KVM_DEV_PATH, perm);
@@ -152,7 +180,7 @@ _Static_assert(sizeof(vm_guest_mode_params)/sizeof(struct vm_guest_mode_params)
  * descriptor to control the created VM is created with the permissions
  * given by perm (e.g. O_RDWR).
  */
-struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
+struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 {
 	struct kvm_vm *vm;
 
@@ -243,11 +271,6 @@ struct kvm_vm *_vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
 	return vm;
 }
 
-struct kvm_vm *vm_create(enum vm_guest_mode mode, uint64_t phy_pages, int perm)
-{
-	return _vm_create(mode, phy_pages, perm);
-}
-
 /*
  * VM Restart
  *
@@ -1204,6 +1227,9 @@ int _vcpu_run(struct kvm_vm *vm, uint32_t vcpuid)
 	do {
 		rc = ioctl(vcpu->fd, KVM_RUN, NULL);
 	} while (rc == -1 && errno == EINTR);
+
+	assert_on_unhandled_exception(vm, vcpuid);
+
 	return rc;
 }
 
@@ -1260,6 +1286,35 @@ void vcpu_set_mp_state(struct kvm_vm *vm, uint32_t vcpuid,
 		"rc: %i errno: %i", ret, errno);
 }
 
+/*
+ * VM VCPU Get Reg List
+ *
+ * Input Args:
+ *   vm - Virtual Machine
+ *   vcpuid - VCPU ID
+ *
+ * Output Args:
+ *   None
+ *
+ * Return:
+ *   A pointer to an allocated struct kvm_reg_list
+ *
+ * Get the list of guest registers which are supported for
+ * KVM_GET_ONE_REG/KVM_SET_ONE_REG calls
+ */
+struct kvm_reg_list *vcpu_get_reg_list(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct kvm_reg_list reg_list_n = { .n = 0 }, *reg_list;
+	int ret;
+
+	ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, &reg_list_n);
+	TEST_ASSERT(ret == -1 && errno == E2BIG, "KVM_GET_REG_LIST n=0");
+	reg_list = calloc(1, sizeof(*reg_list) + reg_list_n.n * sizeof(__u64));
+	reg_list->n = reg_list_n.n;
+	vcpu_ioctl(vm, vcpuid, KVM_GET_REG_LIST, reg_list);
+	return reg_list;
+}
+
 /*
  * VM VCPU Regs Get
  *

tools/testing/selftests/kvm/lib/kvm_util_internal.h

@@ -50,6 +50,8 @@ struct kvm_vm {
 	vm_paddr_t pgd;
 	vm_vaddr_t gdt;
 	vm_vaddr_t tss;
+	vm_vaddr_t idt;
+	vm_vaddr_t handlers;
 };
 
 struct vcpu *vcpu_find(struct kvm_vm *vm, uint32_t vcpuid);

tools/testing/selftests/kvm/lib/s390x/processor.c

@@ -241,3 +241,7 @@ void vcpu_dump(FILE *stream, struct kvm_vm *vm, uint32_t vcpuid, uint8_t indent)
 	fprintf(stream, "%*spstate: psw: 0x%.16llx:0x%.16llx\n",
 		indent, "", vcpu->state->psw_mask, vcpu->state->psw_addr);
 }
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+}

tools/testing/selftests/kvm/lib/s390x/ucall.c

@@ -38,6 +38,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
 	struct kvm_run *run = vcpu_state(vm, vcpu_id);
 	struct ucall ucall = {};
 
+	if (uc)
+		memset(uc, 0, sizeof(*uc));
+
 	if (run->exit_reason == KVM_EXIT_S390_SIEIC &&
 	    run->s390_sieic.icptcode == 4 &&
 	    (run->s390_sieic.ipa >> 8) == 0x83 &&    /* 0x83 means DIAGNOSE */

tools/testing/selftests/kvm/lib/test_util.c

@@ -4,10 +4,13 @@
  *
  * Copyright (C) 2020, Google LLC.
  */
-#include <stdlib.h>
+
+#include <assert.h>
 #include <ctype.h>
 #include <limits.h>
-#include <assert.h>
+#include <stdlib.h>
+#include <time.h>
+
 #include "test_util.h"
 
 /*
@@ -81,6 +84,21 @@ struct timespec timespec_sub(struct timespec ts1, struct timespec ts2)
 	return timespec_add_ns((struct timespec){0}, ns1 - ns2);
 }
 
+struct timespec timespec_diff_now(struct timespec start)
+{
+	struct timespec end;
+
+	clock_gettime(CLOCK_MONOTONIC, &end);
+	return timespec_sub(end, start);
+}
+
+struct timespec timespec_div(struct timespec ts, int divisor)
+{
+	int64_t ns = timespec_to_ns(ts) / divisor;
+
+	return timespec_add_ns((struct timespec){0}, ns);
+}
+
 void print_skip(const char *fmt, ...)
 {
 	va_list ap;

tools/testing/selftests/kvm/lib/x86_64/handlers.S

+handle_exception:
+	push %r15
+	push %r14
+	push %r13
+	push %r12
+	push %r11
+	push %r10
+	push %r9
+	push %r8
+
+	push %rdi
+	push %rsi
+	push %rbp
+	push %rbx
+	push %rdx
+	push %rcx
+	push %rax
+	mov %rsp, %rdi
+
+	call route_exception
+
+	pop %rax
+	pop %rcx
+	pop %rdx
+	pop %rbx
+	pop %rbp
+	pop %rsi
+	pop %rdi
+	pop %r8
+	pop %r9
+	pop %r10
+	pop %r11
+	pop %r12
+	pop %r13
+	pop %r14
+	pop %r15
+
+	/* Discard vector and error code. */
+	add $16, %rsp
+	iretq
+
+/*
+ * Build the handle_exception wrappers which push the vector/error code on the
+ * stack and an array of pointers to those wrappers.
+ */
+.pushsection .rodata
+.globl idt_handlers
+idt_handlers:
+.popsection
+
+.macro HANDLERS has_error from to
+	vector = \from
+	.rept \to - \from + 1
+	.align 8
+
+	/* Fetch current address and append it to idt_handlers. */
+	current_handler = .
+.pushsection .rodata
+.quad current_handler
+.popsection
+
+	.if ! \has_error
+	pushq $0
+	.endif
+	pushq $vector
+	jmp handle_exception
+	vector = vector + 1
+	.endr
+.endm
+
+.global idt_handler_code
+idt_handler_code:
+	HANDLERS has_error=0 from=0  to=7
+	HANDLERS has_error=1 from=8  to=8
+	HANDLERS has_error=0 from=9  to=9
+	HANDLERS has_error=1 from=10 to=14
+	HANDLERS has_error=0 from=15 to=16
+	HANDLERS has_error=1 from=17 to=17
+	HANDLERS has_error=0 from=18 to=255
+
+.section        .note.GNU-stack, "", %progbits

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

@@ -12,9 +12,18 @@
 #include "../kvm_util_internal.h"
 #include "processor.h"
 
+#ifndef NUM_INTERRUPTS
+#define NUM_INTERRUPTS 256
+#endif
+
+#define DEFAULT_CODE_SELECTOR 0x8
+#define DEFAULT_DATA_SELECTOR 0x10
+
 /* Minimum physical address used for virtual translation tables. */
 #define KVM_GUEST_PAGE_TABLE_MIN_PADDR 0x180000
 
+vm_vaddr_t exception_handlers;
+
 /* Virtual translation table structure declarations */
 struct pageMapL4Entry {
 	uint64_t present:1;
@@ -392,11 +401,12 @@ static void kvm_seg_fill_gdt_64bit(struct kvm_vm *vm, struct kvm_segment *segp)
 	desc->limit0 = segp->limit & 0xFFFF;
 	desc->base0 = segp->base & 0xFFFF;
 	desc->base1 = segp->base >> 16;
-	desc->s = segp->s;
 	desc->type = segp->type;
+	desc->s = segp->s;
 	desc->dpl = segp->dpl;
 	desc->p = segp->present;
 	desc->limit1 = segp->limit >> 16;
+	desc->avl = segp->avl;
 	desc->l = segp->l;
 	desc->db = segp->db;
 	desc->g = segp->g;
@@ -556,9 +566,9 @@ static void vcpu_setup(struct kvm_vm *vm, int vcpuid, int pgd_memslot, int gdt_m
 		sregs.efer |= (EFER_LME | EFER_LMA | EFER_NX);
 
 		kvm_seg_set_unusable(&sregs.ldt);
-		kvm_seg_set_kernel_code_64bit(vm, 0x8, &sregs.cs);
-		kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.ds);
-		kvm_seg_set_kernel_data_64bit(vm, 0x10, &sregs.es);
+		kvm_seg_set_kernel_code_64bit(vm, DEFAULT_CODE_SELECTOR, &sregs.cs);
+		kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.ds);
+		kvm_seg_set_kernel_data_64bit(vm, DEFAULT_DATA_SELECTOR, &sregs.es);
 		kvm_setup_tss_64bit(vm, &sregs.tr, 0x18, gdt_memslot, pgd_memslot);
 		break;
 
@@ -1118,3 +1128,131 @@ void kvm_get_cpu_address_width(unsigned int *pa_bits, unsigned int *va_bits)
 		*va_bits = (entry->eax >> 8) & 0xff;
 	}
 }
+
+struct idt_entry {
+	uint16_t offset0;
+	uint16_t selector;
+	uint16_t ist : 3;
+	uint16_t : 5;
+	uint16_t type : 4;
+	uint16_t : 1;
+	uint16_t dpl : 2;
+	uint16_t p : 1;
+	uint16_t offset1;
+	uint32_t offset2; uint32_t reserved;
+};
+
+static void set_idt_entry(struct kvm_vm *vm, int vector, unsigned long addr,
+			  int dpl, unsigned short selector)
+{
+	struct idt_entry *base =
+		(struct idt_entry *)addr_gva2hva(vm, vm->idt);
+	struct idt_entry *e = &base[vector];
+
+	memset(e, 0, sizeof(*e));
+	e->offset0 = addr;
+	e->selector = selector;
+	e->ist = 0;
+	e->type = 14;
+	e->dpl = dpl;
+	e->p = 1;
+	e->offset1 = addr >> 16;
+	e->offset2 = addr >> 32;
+}
+
+void kvm_exit_unexpected_vector(uint32_t value)
+{
+	outl(UNEXPECTED_VECTOR_PORT, value);
+}
+
+void route_exception(struct ex_regs *regs)
+{
+	typedef void(*handler)(struct ex_regs *);
+	handler *handlers = (handler *)exception_handlers;
+
+	if (handlers && handlers[regs->vector]) {
+		handlers[regs->vector](regs);
+		return;
+	}
+
+	kvm_exit_unexpected_vector(regs->vector);
+}
+
+void vm_init_descriptor_tables(struct kvm_vm *vm)
+{
+	extern void *idt_handlers;
+	int i;
+
+	vm->idt = vm_vaddr_alloc(vm, getpagesize(), 0x2000, 0, 0);
+	vm->handlers = vm_vaddr_alloc(vm, 256 * sizeof(void *), 0x2000, 0, 0);
+	/* Handlers have the same address in both address spaces.*/
+	for (i = 0; i < NUM_INTERRUPTS; i++)
+		set_idt_entry(vm, i, (unsigned long)(&idt_handlers)[i], 0,
+			DEFAULT_CODE_SELECTOR);
+}
+
+void vcpu_init_descriptor_tables(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	struct kvm_sregs sregs;
+
+	vcpu_sregs_get(vm, vcpuid, &sregs);
+	sregs.idt.base = vm->idt;
+	sregs.idt.limit = NUM_INTERRUPTS * sizeof(struct idt_entry) - 1;
+	sregs.gdt.base = vm->gdt;
+	sregs.gdt.limit = getpagesize() - 1;
+	kvm_seg_set_kernel_data_64bit(NULL, DEFAULT_DATA_SELECTOR, &sregs.gs);
+	vcpu_sregs_set(vm, vcpuid, &sregs);
+	*(vm_vaddr_t *)addr_gva2hva(vm, (vm_vaddr_t)(&exception_handlers)) = vm->handlers;
+}
+
+void vm_handle_exception(struct kvm_vm *vm, int vector,
+			 void (*handler)(struct ex_regs *))
+{
+	vm_vaddr_t *handlers = (vm_vaddr_t *)addr_gva2hva(vm, vm->handlers);
+
+	handlers[vector] = (vm_vaddr_t)handler;
+}
+
+void assert_on_unhandled_exception(struct kvm_vm *vm, uint32_t vcpuid)
+{
+	if (vcpu_state(vm, vcpuid)->exit_reason == KVM_EXIT_IO
+		&& vcpu_state(vm, vcpuid)->io.port == UNEXPECTED_VECTOR_PORT
+		&& vcpu_state(vm, vcpuid)->io.size == 4) {
+		/* Grab pointer to io data */
+		uint32_t *data = (void *)vcpu_state(vm, vcpuid)
+			+ vcpu_state(vm, vcpuid)->io.data_offset;
+
+		TEST_ASSERT(false,
+			    "Unexpected vectored event in guest (vector:0x%x)",
+			    *data);
+	}
+}
+
+bool set_cpuid(struct kvm_cpuid2 *cpuid,
+	       struct kvm_cpuid_entry2 *ent)
+{
+	int i;
+
+	for (i = 0; i < cpuid->nent; i++) {
+		struct kvm_cpuid_entry2 *cur = &cpuid->entries[i];
+
+		if (cur->function != ent->function || cur->index != ent->index)
+			continue;
+
+		memcpy(cur, ent, sizeof(struct kvm_cpuid_entry2));
+		return true;
+	}
+
+	return false;
+}
+
+uint64_t kvm_hypercall(uint64_t nr, uint64_t a0, uint64_t a1, uint64_t a2,
+		       uint64_t a3)
+{
+	uint64_t r;
+
+	asm volatile("vmcall"
+		     : "=a"(r)
+		     : "b"(a0), "c"(a1), "d"(a2), "S"(a3));
+	return r;
+}

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

@@ -40,6 +40,9 @@ uint64_t get_ucall(struct kvm_vm *vm, uint32_t vcpu_id, struct ucall *uc)
 	struct kvm_run *run = vcpu_state(vm, vcpu_id);
 	struct ucall ucall = {};
 
+	if (uc)
+		memset(uc, 0, sizeof(*uc));
+
 	if (run->exit_reason == KVM_EXIT_IO && run->io.port == UCALL_PIO_PORT) {
 		struct kvm_regs regs;
 

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

+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2020, Google LLC.
+ *
+ * Tests for KVM paravirtual feature disablement
+ */
+#include <asm/kvm_para.h>
+#include <linux/kvm_para.h>
+#include <stdint.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+#include "processor.h"
+
+extern unsigned char rdmsr_start;
+extern unsigned char rdmsr_end;
+
+static u64 do_rdmsr(u32 idx)
+{
+	u32 lo, hi;
+
+	asm volatile("rdmsr_start: rdmsr;"
+		     "rdmsr_end:"
+		     : "=a"(lo), "=c"(hi)
+		     : "c"(idx));
+
+	return (((u64) hi) << 32) | lo;
+}
+
+extern unsigned char wrmsr_start;
+extern unsigned char wrmsr_end;
+
+static void do_wrmsr(u32 idx, u64 val)
+{
+	u32 lo, hi;
+
+	lo = val;
+	hi = val >> 32;
+
+	asm volatile("wrmsr_start: wrmsr;"
+		     "wrmsr_end:"
+		     : : "a"(lo), "c"(idx), "d"(hi));
+}
+
+static int nr_gp;
+
+static void guest_gp_handler(struct ex_regs *regs)
+{
+	unsigned char *rip = (unsigned char *)regs->rip;
+	bool r, w;
+
+	r = rip == &rdmsr_start;
+	w = rip == &wrmsr_start;
+	GUEST_ASSERT(r || w);
+
+	nr_gp++;
+
+	if (r)
+		regs->rip = (uint64_t)&rdmsr_end;
+	else
+		regs->rip = (uint64_t)&wrmsr_end;
+}
+
+struct msr_data {
+	uint32_t idx;
+	const char *name;
+};
+
+#define TEST_MSR(msr) { .idx = msr, .name = #msr }
+#define UCALL_PR_MSR 0xdeadbeef
+#define PR_MSR(msr) ucall(UCALL_PR_MSR, 1, msr)
+
+/*
+ * KVM paravirtual msrs to test. Expect a #GP if any of these msrs are read or
+ * written, as the KVM_CPUID_FEATURES leaf is cleared.
+ */
+static struct msr_data msrs_to_test[] = {
+	TEST_MSR(MSR_KVM_SYSTEM_TIME),
+	TEST_MSR(MSR_KVM_SYSTEM_TIME_NEW),
+	TEST_MSR(MSR_KVM_WALL_CLOCK),
+	TEST_MSR(MSR_KVM_WALL_CLOCK_NEW),
+	TEST_MSR(MSR_KVM_ASYNC_PF_EN),
+	TEST_MSR(MSR_KVM_STEAL_TIME),
+	TEST_MSR(MSR_KVM_PV_EOI_EN),
+	TEST_MSR(MSR_KVM_POLL_CONTROL),
+	TEST_MSR(MSR_KVM_ASYNC_PF_INT),
+	TEST_MSR(MSR_KVM_ASYNC_PF_ACK),
+};
+
+static void test_msr(struct msr_data *msr)
+{
+	PR_MSR(msr);
+	do_rdmsr(msr->idx);
+	GUEST_ASSERT(READ_ONCE(nr_gp) == 1);
+
+	nr_gp = 0;
+	do_wrmsr(msr->idx, 0);
+	GUEST_ASSERT(READ_ONCE(nr_gp) == 1);
+	nr_gp = 0;
+}
+
+struct hcall_data {
+	uint64_t nr;
+	const char *name;
+};
+
+#define TEST_HCALL(hc) { .nr = hc, .name = #hc }
+#define UCALL_PR_HCALL 0xdeadc0de
+#define PR_HCALL(hc) ucall(UCALL_PR_HCALL, 1, hc)
+
+/*
+ * KVM hypercalls to test. Expect -KVM_ENOSYS when called, as the corresponding
+ * features have been cleared in KVM_CPUID_FEATURES.
+ */
+static struct hcall_data hcalls_to_test[] = {
+	TEST_HCALL(KVM_HC_KICK_CPU),
+	TEST_HCALL(KVM_HC_SEND_IPI),
+	TEST_HCALL(KVM_HC_SCHED_YIELD),
+};
+
+static void test_hcall(struct hcall_data *hc)
+{
+	uint64_t r;
+
+	PR_HCALL(hc);
+	r = kvm_hypercall(hc->nr, 0, 0, 0, 0);
+	GUEST_ASSERT(r == -KVM_ENOSYS);
+}
+
+static void guest_main(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(msrs_to_test); i++) {
+		test_msr(&msrs_to_test[i]);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(hcalls_to_test); i++) {
+		test_hcall(&hcalls_to_test[i]);
+	}
+
+	GUEST_DONE();
+}
+
+static void clear_kvm_cpuid_features(struct kvm_cpuid2 *cpuid)
+{
+	struct kvm_cpuid_entry2 ent = {0};
+
+	ent.function = KVM_CPUID_FEATURES;
+	TEST_ASSERT(set_cpuid(cpuid, &ent),
+		    "failed to clear KVM_CPUID_FEATURES leaf");
+}
+
+static void pr_msr(struct ucall *uc)
+{
+	struct msr_data *msr = (struct msr_data *)uc->args[0];
+
+	pr_info("testing msr: %s (%#x)\n", msr->name, msr->idx);
+}
+
+static void pr_hcall(struct ucall *uc)
+{
+	struct hcall_data *hc = (struct hcall_data *)uc->args[0];
+
+	pr_info("testing hcall: %s (%lu)\n", hc->name, hc->nr);
+}
+
+static void handle_abort(struct ucall *uc)
+{
+	TEST_FAIL("%s at %s:%ld", (const char *)uc->args[0],
+		  __FILE__, uc->args[1]);
+}
+
+#define VCPU_ID 0
+
+static void enter_guest(struct kvm_vm *vm)
+{
+	struct kvm_run *run;
+	struct ucall uc;
+	int r;
+
+	run = vcpu_state(vm, VCPU_ID);
+
+	while (true) {
+		r = _vcpu_run(vm, VCPU_ID);
+		TEST_ASSERT(!r, "vcpu_run failed: %d\n", r);
+		TEST_ASSERT(run->exit_reason == KVM_EXIT_IO,
+			    "unexpected exit reason: %u (%s)",
+			    run->exit_reason, exit_reason_str(run->exit_reason));
+
+		switch (get_ucall(vm, VCPU_ID, &uc)) {
+		case UCALL_PR_MSR:
+			pr_msr(&uc);
+			break;
+		case UCALL_PR_HCALL:
+			pr_hcall(&uc);
+			break;
+		case UCALL_ABORT:
+			handle_abort(&uc);
+			return;
+		case UCALL_DONE:
+			return;
+		}
+	}
+}
+
+int main(void)
+{
+	struct kvm_enable_cap cap = {0};
+	struct kvm_cpuid2 *best;
+	struct kvm_vm *vm;
+
+	if (!kvm_check_cap(KVM_CAP_ENFORCE_PV_FEATURE_CPUID)) {
+		pr_info("will skip kvm paravirt restriction tests.\n");
+		return 0;
+	}
+
+	vm = vm_create_default(VCPU_ID, 0, guest_main);
+
+	cap.cap = KVM_CAP_ENFORCE_PV_FEATURE_CPUID;
+	cap.args[0] = 1;
+	vcpu_enable_cap(vm, VCPU_ID, &cap);
+
+	best = kvm_get_supported_cpuid();
+	clear_kvm_cpuid_features(best);
+	vcpu_set_cpuid(vm, VCPU_ID, best);
+
+	vm_init_descriptor_tables(vm);
+	vcpu_init_descriptor_tables(vm, VCPU_ID);
+	vm_handle_exception(vm, GP_VECTOR, guest_gp_handler);
+
+	enter_guest(vm);
+	kvm_vm_free(vm);
+}