summary refs log tree commit diff
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/cpuid.c29
-rw-r--r--arch/x86/kvm/cpuid.h1
-rw-r--r--arch/x86/kvm/emulate.c8
-rw-r--r--arch/x86/kvm/irq.c85
-rw-r--r--arch/x86/kvm/lapic.c2
-rw-r--r--arch/x86/kvm/mmu/mmu.c14
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c7
-rw-r--r--arch/x86/kvm/svm/sev.c2
-rw-r--r--arch/x86/kvm/svm/svm.c12
-rw-r--r--arch/x86/kvm/x86.c92
-rw-r--r--arch/x86/kvm/x86.h8
11 files changed, 164 insertions, 96 deletions
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 06a278b3701d..83637a2ff605 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/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);
 
@@ -169,6 +178,8 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	vcpu->arch.cr4_guest_rsvd_bits =
 	    __cr4_reserved_bits(guest_cpuid_has, vcpu);
 
+	vcpu->arch.cr3_lm_rsvd_bits = rsvd_bits(cpuid_maxphyaddr(vcpu), 63);
+
 	/* Invoke the vendor callback only after the above state is updated. */
 	kvm_x86_ops.vcpu_after_set_cpuid(vcpu);
 }
@@ -672,7 +683,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 
 		edx.split.num_counters_fixed = min(cap.num_counters_fixed, MAX_FIXED_COUNTERS);
 		edx.split.bit_width_fixed = cap.bit_width_fixed;
-		edx.split.reserved = 0;
+		edx.split.anythread_deprecated = 1;
+		edx.split.reserved1 = 0;
+		edx.split.reserved2 = 0;
 
 		entry->eax = eax.full;
 		entry->ebx = cap.events_mask;
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index bf8577947ed2..f7a6e8f83783 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/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,
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 0d917eb70319..56cae1ff9e3f 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -4046,6 +4046,12 @@ static int em_clflush(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
+static int em_clflushopt(struct x86_emulate_ctxt *ctxt)
+{
+	/* emulating clflushopt regardless of cpuid */
+	return X86EMUL_CONTINUE;
+}
+
 static int em_movsxd(struct x86_emulate_ctxt *ctxt)
 {
 	ctxt->dst.val = (s32) ctxt->src.val;
@@ -4585,7 +4591,7 @@ static const struct opcode group11[] = {
 };
 
 static const struct gprefix pfx_0f_ae_7 = {
-	I(SrcMem | ByteOp, em_clflush), N, N, N,
+	I(SrcMem | ByteOp, em_clflush), I(SrcMem | ByteOp, em_clflushopt), N, N,
 };
 
 static const struct group_dual group15 = { {
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 99d118ffc67d..814698e5b152 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -40,29 +40,10 @@ static int pending_userspace_extint(struct kvm_vcpu *v)
  * check if there is pending interrupt from
  * non-APIC source without intack.
  */
-static int kvm_cpu_has_extint(struct kvm_vcpu *v)
-{
-	u8 accept = kvm_apic_accept_pic_intr(v);
-
-	if (accept) {
-		if (irqchip_split(v->kvm))
-			return pending_userspace_extint(v);
-		else
-			return v->kvm->arch.vpic->output;
-	} else
-		return 0;
-}
-
-/*
- * check if there is injectable interrupt:
- * when virtual interrupt delivery enabled,
- * interrupt from apic will handled by hardware,
- * we don't need to check it here.
- */
-int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+int kvm_cpu_has_extint(struct kvm_vcpu *v)
 {
 	/*
-	 * FIXME: interrupt.injected represents an interrupt that it's
+	 * FIXME: interrupt.injected represents an interrupt whose
 	 * side-effects have already been applied (e.g. bit from IRR
 	 * already moved to ISR). Therefore, it is incorrect to rely
 	 * on interrupt.injected to know if there is a pending
@@ -75,6 +56,23 @@ int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
 	if (!lapic_in_kernel(v))
 		return v->arch.interrupt.injected;
 
+	if (!kvm_apic_accept_pic_intr(v))
+		return 0;
+
+	if (irqchip_split(v->kvm))
+		return pending_userspace_extint(v);
+	else
+		return v->kvm->arch.vpic->output;
+}
+
+/*
+ * check if there is injectable interrupt:
+ * when virtual interrupt delivery enabled,
+ * interrupt from apic will handled by hardware,
+ * we don't need to check it here.
+ */
+int kvm_cpu_has_injectable_intr(struct kvm_vcpu *v)
+{
 	if (kvm_cpu_has_extint(v))
 		return 1;
 
@@ -91,20 +89,6 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_injectable_intr);
  */
 int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
 {
-	/*
-	 * FIXME: interrupt.injected represents an interrupt that it's
-	 * side-effects have already been applied (e.g. bit from IRR
-	 * already moved to ISR). Therefore, it is incorrect to rely
-	 * on interrupt.injected to know if there is a pending
-	 * interrupt in the user-mode LAPIC.
-	 * This leads to nVMX/nSVM not be able to distinguish
-	 * if it should exit from L2 to L1 on EXTERNAL_INTERRUPT on
-	 * pending interrupt or should re-inject an injected
-	 * interrupt.
-	 */
-	if (!lapic_in_kernel(v))
-		return v->arch.interrupt.injected;
-
 	if (kvm_cpu_has_extint(v))
 		return 1;
 
@@ -118,16 +102,21 @@ EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt);
  */
 static int kvm_cpu_get_extint(struct kvm_vcpu *v)
 {
-	if (kvm_cpu_has_extint(v)) {
-		if (irqchip_split(v->kvm)) {
-			int vector = v->arch.pending_external_vector;
-
-			v->arch.pending_external_vector = -1;
-			return vector;
-		} else
-			return kvm_pic_read_irq(v->kvm); /* PIC */
-	} else
+	if (!kvm_cpu_has_extint(v)) {
+		WARN_ON(!lapic_in_kernel(v));
 		return -1;
+	}
+
+	if (!lapic_in_kernel(v))
+		return v->arch.interrupt.nr;
+
+	if (irqchip_split(v->kvm)) {
+		int vector = v->arch.pending_external_vector;
+
+		v->arch.pending_external_vector = -1;
+		return vector;
+	} else
+		return kvm_pic_read_irq(v->kvm); /* PIC */
 }
 
 /*
@@ -135,13 +124,7 @@ static int kvm_cpu_get_extint(struct kvm_vcpu *v)
  */
 int kvm_cpu_get_interrupt(struct kvm_vcpu *v)
 {
-	int vector;
-
-	if (!lapic_in_kernel(v))
-		return v->arch.interrupt.nr;
-
-	vector = kvm_cpu_get_extint(v);
-
+	int vector = kvm_cpu_get_extint(v);
 	if (vector != -1)
 		return vector;			/* PIC */
 
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 105e7859d1f2..86c33d53c90a 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2465,7 +2465,7 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	u32 ppr;
 
-	if (!kvm_apic_hw_enabled(apic))
+	if (!kvm_apic_present(vcpu))
 		return -1;
 
 	__apic_update_ppr(apic, &ppr);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 1f96adff8dc4..7a6ae9e90bd7 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -856,12 +856,14 @@ 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]) {
-			desc->more = mmu_alloc_pte_list_desc(vcpu);
+
+			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)
@@ -3515,7 +3517,7 @@ static bool get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
 {
 	u64 sptes[PT64_ROOT_MAX_LEVEL];
 	struct rsvd_bits_validate *rsvd_check;
-	int root = vcpu->arch.mmu->root_level;
+	int root = vcpu->arch.mmu->shadow_root_level;
 	int leaf;
 	int level;
 	bool reserved = false;
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 27e381c9da6c..ff28a5c6abd6 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -49,7 +49,14 @@ bool is_tdp_mmu_root(struct kvm *kvm, hpa_t hpa)
 {
 	struct kvm_mmu_page *sp;
 
+	if (!kvm->arch.tdp_mmu_enabled)
+		return false;
+	if (WARN_ON(!VALID_PAGE(hpa)))
+		return false;
+
 	sp = to_shadow_page(hpa);
+	if (WARN_ON(!sp))
+		return false;
 
 	return sp->tdp_mmu_page && sp->root_count;
 }
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index c0b14106258a..566f4d18185b 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -642,8 +642,8 @@ static int __sev_dbg_decrypt(struct kvm *kvm, unsigned long src_paddr,
 	 * Its safe to read more than we are asked, caller should ensure that
 	 * destination has enough space.
 	 */
-	src_paddr = round_down(src_paddr, 16);
 	offset = src_paddr & 15;
+	src_paddr = round_down(src_paddr, 16);
 	sz = round_up(sz + offset, 16);
 
 	return __sev_issue_dbg_cmd(kvm, src_paddr, dst_paddr, sz, err, false);
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 2f32fd09e259..79b3a564f1c9 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1309,8 +1309,10 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
 		svm->avic_is_running = true;
 
 	svm->msrpm = svm_vcpu_alloc_msrpm();
-	if (!svm->msrpm)
+	if (!svm->msrpm) {
+		err = -ENOMEM;
 		goto error_free_vmcb_page;
+	}
 
 	svm_vcpu_init_msrpm(vcpu, svm->msrpm);
 
@@ -3741,6 +3743,7 @@ static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_cpuid_entry2 *best;
 
 	vcpu->arch.xsaves_enabled = guest_cpuid_has(vcpu, X86_FEATURE_XSAVE) &&
 				    boot_cpu_has(X86_FEATURE_XSAVE) &&
@@ -3753,6 +3756,13 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	/* Check again if INVPCID interception if required */
 	svm_check_invpcid(svm);
 
+	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
+	if (sev_guest(vcpu->kvm)) {
+		best = kvm_find_cpuid_entry(vcpu, 0x8000001F, 0);
+		if (best)
+			vcpu->arch.cr3_lm_rsvd_bits &= ~(1UL << (best->ebx & 0x3f));
+	}
+
 	if (!kvm_vcpu_apicv_active(vcpu))
 		return;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f5ede41bf9e6..e545a8a613b1 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -255,11 +255,10 @@ 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,
-				 u64 data, bool write)
+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;
 	}
 }
 
@@ -1042,7 +1041,7 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3)
 	}
 
 	if (is_long_mode(vcpu) &&
-	    (cr3 & rsvd_bits(cpuid_maxphyaddr(vcpu), 63)))
+	    (cr3 & vcpu->arch.cr3_lm_rsvd_bits))
 		return 1;
 	else if (is_pae_paging(vcpu) &&
 		 !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))
@@ -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;
@@ -3063,9 +3065,9 @@ 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;
-		}
-		vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
-			    __func__, data);
+		} else if (report_ignored_msrs)
+			vcpu_unimpl(vcpu, "%s: MSR_IA32_DEBUGCTLMSR 0x%llx, nop\n",
+				    __func__, data);
 		break;
 	case 0x200 ... 0x2ff:
 		return kvm_mtrr_set_msr(vcpu, msr, data);
@@ -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:
@@ -4015,21 +4051,23 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
 
 static int kvm_cpu_accept_dm_intr(struct kvm_vcpu *vcpu)
 {
+	/*
+	 * We can accept userspace's request for interrupt injection
+	 * as long as we have a place to store the interrupt number.
+	 * The actual injection will happen when the CPU is able to
+	 * deliver the interrupt.
+	 */
+	if (kvm_cpu_has_extint(vcpu))
+		return false;
+
+	/* Acknowledging ExtINT does not happen if LINT0 is masked.  */
 	return (!lapic_in_kernel(vcpu) ||
 		kvm_apic_accept_pic_intr(vcpu));
 }
 
-/*
- * if userspace requested an interrupt window, check that the
- * interrupt window is open.
- *
- * No need to exit to userspace if we already have an interrupt queued.
- */
 static int kvm_vcpu_ready_for_interrupt_injection(struct kvm_vcpu *vcpu)
 {
 	return kvm_arch_interrupt_allowed(vcpu) &&
-		!kvm_cpu_has_interrupt(vcpu) &&
-		!kvm_event_needs_reinjection(vcpu) &&
 		kvm_cpu_accept_dm_intr(vcpu);
 }
 
@@ -4575,6 +4613,8 @@ 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;
 
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 3900ab0c6004..e7ca622a468f 100644
--- a/arch/x86/kvm/x86.h
+++ b/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)             \
 ({                                                      \
generated by cgit-pink 1.4.1 (git 2.36.1) at 2024-10-06 21:19:01 +0000