Merge branch 'kvm-5.16-fixes' into kvm-master

* Fix misuse of gfn-to-pfn cache when recording guest steal time / preempted status

* Fix selftests on APICv machines

* Fix sparse warnings

* Fix detection of KVM features in CPUID

* Cleanups for bogus writes to MSR_KVM_PV_EOI_EN

* Fixes and cleanups for MSR bitmap handling

* Cleanups for INVPCID

* Make x86 KVM_SOFT_MAX_VCPUS consistent with other architectures

arch/x86/include/asm/kvm_host.h

@@ -38,7 +38,6 @@
 #define __KVM_HAVE_ARCH_VCPU_DEBUGFS
 
 #define KVM_MAX_VCPUS 1024
-#define KVM_SOFT_MAX_VCPUS 710
 
 /*
  * In x86, the VCPU ID corresponds to the APIC ID, and APIC IDs
@@ -725,6 +724,7 @@ struct kvm_vcpu_arch {
 
 	int cpuid_nent;
 	struct kvm_cpuid_entry2 *cpuid_entries;
+	u32 kvm_cpuid_base;
 
 	u64 reserved_gpa_bits;
 	int maxphyaddr;
@@ -748,7 +748,7 @@ struct kvm_vcpu_arch {
 		u8 preempted;
 		u64 msr_val;
 		u64 last_steal;
-		struct gfn_to_pfn_cache cache;
+		struct gfn_to_hva_cache cache;
 	} st;
 
 	u64 l1_tsc_offset;
@@ -1034,6 +1034,7 @@ struct kvm_x86_msr_filter {
 #define APICV_INHIBIT_REASON_IRQWIN     3
 #define APICV_INHIBIT_REASON_PIT_REINJ  4
 #define APICV_INHIBIT_REASON_X2APIC	5
+#define APICV_INHIBIT_REASON_BLOCKIRQ	6
 
 struct kvm_arch {
 	unsigned long n_used_mmu_pages;

arch/x86/include/asm/processor.h

@@ -806,11 +806,14 @@ static inline u32 amd_get_nodes_per_socket(void)	{ return 0; }
 static inline u32 amd_get_highest_perf(void)		{ return 0; }
 #endif
 
+#define for_each_possible_hypervisor_cpuid_base(function) \
+	for (function = 0x40000000; function < 0x40010000; function += 0x100)
+
 static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
 {
 	uint32_t base, eax, signature[3];
 
-	for (base = 0x40000000; base < 0x40010000; base += 0x100) {
+	for_each_possible_hypervisor_cpuid_base(base) {
 		cpuid(base, &eax, &signature[0], &signature[1], &signature[2]);
 
 		if (!memcmp(sig, signature, 12) &&

arch/x86/include/uapi/asm/kvm_para.h

@@ -8,6 +8,7 @@
  * should be used to determine that a VM is running under KVM.
  */
 #define KVM_CPUID_SIGNATURE	0x40000000
+#define KVM_SIGNATURE "KVMKVMKVM\0\0\0"
 
 /* This CPUID returns two feature bitmaps in eax, edx. Before enabling
  * a particular paravirtualization, the appropriate feature bit should

arch/x86/kernel/kvm.c

@@ -809,7 +809,7 @@ static noinline uint32_t __kvm_cpuid_base(void)
 		return 0;	/* So we don't blow up on old processors */
 
 	if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
-		return hypervisor_cpuid_base("KVMKVMKVM\0\0\0", 0);
+		return hypervisor_cpuid_base(KVM_SIGNATURE, 0);
 
 	return 0;
 }

arch/x86/kvm/cpuid.c

@@ -99,11 +99,45 @@ static int kvm_check_cpuid(struct kvm_cpuid_entry2 *entries, int nent)
 	return 0;
 }
 
-void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
+static void kvm_update_kvm_cpuid_base(struct kvm_vcpu *vcpu)
 {
-	struct kvm_cpuid_entry2 *best;
+	u32 function;
+	struct kvm_cpuid_entry2 *entry;
+
+	vcpu->arch.kvm_cpuid_base = 0;
+
+	for_each_possible_hypervisor_cpuid_base(function) {
+		entry = kvm_find_cpuid_entry(vcpu, function, 0);
 
-	best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0);
+		if (entry) {
+			u32 signature[3];
+
+			signature[0] = entry->ebx;
+			signature[1] = entry->ecx;
+			signature[2] = entry->edx;
+
+			BUILD_BUG_ON(sizeof(signature) > sizeof(KVM_SIGNATURE));
+			if (!memcmp(signature, KVM_SIGNATURE, sizeof(signature))) {
+				vcpu->arch.kvm_cpuid_base = function;
+				break;
+			}
+		}
+	}
+}
+
+struct kvm_cpuid_entry2 *kvm_find_kvm_cpuid_features(struct kvm_vcpu *vcpu)
+{
+	u32 base = vcpu->arch.kvm_cpuid_base;
+
+	if (!base)
+		return NULL;
+
+	return kvm_find_cpuid_entry(vcpu, base | KVM_CPUID_FEATURES, 0);
+}
+
+void kvm_update_pv_runtime(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best = kvm_find_kvm_cpuid_features(vcpu);
 
 	/*
 	 * save the feature bitmap to avoid cpuid lookup for every PV
@@ -142,7 +176,7 @@ void kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu)
 		     cpuid_entry_has(best, X86_FEATURE_XSAVEC)))
 		best->ebx = xstate_required_size(vcpu->arch.xcr0, true);
 
-	best = kvm_find_cpuid_entry(vcpu, KVM_CPUID_FEATURES, 0);
+	best = kvm_find_kvm_cpuid_features(vcpu);
 	if (kvm_hlt_in_guest(vcpu->kvm) && best &&
 		(best->eax & (1 << KVM_FEATURE_PV_UNHALT)))
 		best->eax &= ~(1 << KVM_FEATURE_PV_UNHALT);
@@ -239,6 +273,26 @@ u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu)
 	return rsvd_bits(cpuid_maxphyaddr(vcpu), 63);
 }
 
+static int kvm_set_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *e2,
+                        int nent)
+{
+    int r;
+
+    r = kvm_check_cpuid(e2, nent);
+    if (r)
+        return r;
+
+    kvfree(vcpu->arch.cpuid_entries);
+    vcpu->arch.cpuid_entries = e2;
+    vcpu->arch.cpuid_nent = nent;
+
+    kvm_update_kvm_cpuid_base(vcpu);
+    kvm_update_cpuid_runtime(vcpu);
+    kvm_vcpu_after_set_cpuid(vcpu);
+
+    return 0;
+}
+
 /* when an old userspace process fills a new kernel module */
 int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 			     struct kvm_cpuid *cpuid,
@@ -275,18 +329,9 @@ int kvm_vcpu_ioctl_set_cpuid(struct kvm_vcpu *vcpu,
 		e2[i].padding[2] = 0;
 	}
 
-	r = kvm_check_cpuid(e2, cpuid->nent);
-	if (r) {
+	r = kvm_set_cpuid(vcpu, e2, cpuid->nent);
+	if (r)
 		kvfree(e2);
-		goto out_free_cpuid;
-	}
-
-	kvfree(vcpu->arch.cpuid_entries);
-	vcpu->arch.cpuid_entries = e2;
-	vcpu->arch.cpuid_nent = cpuid->nent;
-
-	kvm_update_cpuid_runtime(vcpu);
-	kvm_vcpu_after_set_cpuid(vcpu);
 
 out_free_cpuid:
 	kvfree(e);
@@ -310,20 +355,11 @@ int kvm_vcpu_ioctl_set_cpuid2(struct kvm_vcpu *vcpu,
 			return PTR_ERR(e2);
 	}
 
-	r = kvm_check_cpuid(e2, cpuid->nent);
-	if (r) {
+	r = kvm_set_cpuid(vcpu, e2, cpuid->nent);
+	if (r)
 		kvfree(e2);
-		return r;
-	}
 
-	kvfree(vcpu->arch.cpuid_entries);
-	vcpu->arch.cpuid_entries = e2;
-	vcpu->arch.cpuid_nent = cpuid->nent;
-
-	kvm_update_cpuid_runtime(vcpu);
-	kvm_vcpu_after_set_cpuid(vcpu);
-
-	return 0;
+	return r;
 }
 
 int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
@@ -871,8 +907,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 		}
 		break;
 	case KVM_CPUID_SIGNATURE: {
-		static const char signature[12] = "KVMKVMKVM\0\0";
-		const u32 *sigptr = (const u32 *)signature;
+		const u32 *sigptr = (const u32 *)KVM_SIGNATURE;
 		entry->eax = KVM_CPUID_FEATURES;
 		entry->ebx = sigptr[0];
 		entry->ecx = sigptr[1];

arch/x86/kvm/hyperv.c

@@ -1472,7 +1472,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 
 		if (!(data & HV_X64_MSR_VP_ASSIST_PAGE_ENABLE)) {
 			hv_vcpu->hv_vapic = data;
-			if (kvm_lapic_enable_pv_eoi(vcpu, 0, 0))
+			if (kvm_lapic_set_pv_eoi(vcpu, 0, 0))
 				return 1;
 			break;
 		}
@@ -1490,7 +1490,7 @@ static int kvm_hv_set_msr(struct kvm_vcpu *vcpu, u32 msr, u64 data, bool host)
 			return 1;
 		hv_vcpu->hv_vapic = data;
 		kvm_vcpu_mark_page_dirty(vcpu, gfn);
-		if (kvm_lapic_enable_pv_eoi(vcpu,
+		if (kvm_lapic_set_pv_eoi(vcpu,
 					    gfn_to_gpa(gfn) | KVM_MSR_ENABLED,
 					    sizeof(struct hv_vp_assist_page)))
 			return 1;

arch/x86/kvm/lapic.c

@@ -2856,25 +2856,30 @@ int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 reg, u64 *data)
 	return 0;
 }
 
-int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len)
+int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len)
 {
 	u64 addr = data & ~KVM_MSR_ENABLED;
 	struct gfn_to_hva_cache *ghc = &vcpu->arch.pv_eoi.data;
 	unsigned long new_len;
+	int ret;
 
 	if (!IS_ALIGNED(addr, 4))
 		return 1;
 
-	vcpu->arch.pv_eoi.msr_val = data;
-	if (!pv_eoi_enabled(vcpu))
-		return 0;
+	if (data & KVM_MSR_ENABLED) {
+		if (addr == ghc->gpa && len <= ghc->len)
+			new_len = ghc->len;
+		else
+			new_len = len;
 
-	if (addr == ghc->gpa && len <= ghc->len)
-		new_len = ghc->len;
-	else
-		new_len = len;
+		ret = kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len);
+		if (ret)
+			return ret;
+	}
+
+	vcpu->arch.pv_eoi.msr_val = data;
 
-	return kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, addr, new_len);
+	return 0;
 }
 
 int kvm_apic_accept_events(struct kvm_vcpu *vcpu)

arch/x86/kvm/lapic.h

@@ -127,7 +127,7 @@ int kvm_x2apic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 int kvm_hv_vapic_msr_write(struct kvm_vcpu *vcpu, u32 msr, u64 data);
 int kvm_hv_vapic_msr_read(struct kvm_vcpu *vcpu, u32 msr, u64 *data);
 
-int kvm_lapic_enable_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len);
+int kvm_lapic_set_pv_eoi(struct kvm_vcpu *vcpu, u64 data, unsigned long len);
 void kvm_lapic_exit(void);
 
 #define VEC_POS(v) ((v) & (32 - 1))

arch/x86/kvm/mmu/mmu.c

@@ -3191,17 +3191,17 @@ static int fast_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
 			new_spte |= PT_WRITABLE_MASK;
 
 			/*
-			 * Do not fix write-permission on the large spte.  Since
-			 * we only dirty the first page into the dirty-bitmap in
+			 * Do not fix write-permission on the large spte when
+			 * dirty logging is enabled. Since we only dirty the
+			 * first page into the dirty-bitmap in
 			 * fast_pf_fix_direct_spte(), other pages are missed
 			 * if its slot has dirty logging enabled.
 			 *
 			 * Instead, we let the slow page fault path create a
 			 * normal spte to fix the access.
-			 *
-			 * See the comments in kvm_arch_commit_memory_region().
 			 */
-			if (sp->role.level > PG_LEVEL_4K)
+			if (sp->role.level > PG_LEVEL_4K &&
+			    kvm_slot_dirty_track_enabled(fault->slot))
 				break;
 		}
 

arch/x86/kvm/mmu/tdp_mmu.c

@@ -897,7 +897,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
 					  struct kvm_page_fault *fault,
 					  struct tdp_iter *iter)
 {
-	struct kvm_mmu_page *sp = sptep_to_sp(iter->sptep);
+	struct kvm_mmu_page *sp = sptep_to_sp(rcu_dereference(iter->sptep));
 	u64 new_spte;
 	int ret = RET_PF_FIXED;
 	bool wrprot = false;

arch/x86/kvm/pmu.c

@@ -319,7 +319,7 @@ void kvm_pmu_handle_event(struct kvm_vcpu *vcpu)
 }
 
 /* check if idx is a valid index to access PMU */
-int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
+bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 {
 	return kvm_x86_ops.pmu_ops->is_valid_rdpmc_ecx(vcpu, idx);
 }

arch/x86/kvm/pmu.h

@@ -32,7 +32,7 @@ struct kvm_pmu_ops {
 	struct kvm_pmc *(*rdpmc_ecx_to_pmc)(struct kvm_vcpu *vcpu,
 		unsigned int idx, u64 *mask);
 	struct kvm_pmc *(*msr_idx_to_pmc)(struct kvm_vcpu *vcpu, u32 msr);
-	int (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx);
+	bool (*is_valid_rdpmc_ecx)(struct kvm_vcpu *vcpu, unsigned int idx);
 	bool (*is_valid_msr)(struct kvm_vcpu *vcpu, u32 msr);
 	int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
 	int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
@@ -149,7 +149,7 @@ void reprogram_counter(struct kvm_pmu *pmu, int pmc_idx);
 void kvm_pmu_deliver_pmi(struct kvm_vcpu *vcpu);
 void kvm_pmu_handle_event(struct kvm_vcpu *vcpu);
 int kvm_pmu_rdpmc(struct kvm_vcpu *vcpu, unsigned pmc, u64 *data);
-int kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx);
+bool kvm_pmu_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx);
 bool kvm_pmu_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr);
 int kvm_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
 int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);

arch/x86/kvm/svm/avic.c

@@ -904,7 +904,8 @@ bool svm_check_apicv_inhibit_reasons(ulong bit)
 			  BIT(APICV_INHIBIT_REASON_NESTED) |
 			  BIT(APICV_INHIBIT_REASON_IRQWIN) |
 			  BIT(APICV_INHIBIT_REASON_PIT_REINJ) |
-			  BIT(APICV_INHIBIT_REASON_X2APIC);
+			  BIT(APICV_INHIBIT_REASON_X2APIC) |
+			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ);
 
 	return supported & BIT(bit);
 }

arch/x86/kvm/svm/pmu.c

@@ -181,14 +181,13 @@ static struct kvm_pmc *amd_pmc_idx_to_pmc(struct kvm_pmu *pmu, int pmc_idx)
 	return get_gp_pmc_amd(pmu, base + pmc_idx, PMU_TYPE_COUNTER);
 }
 
-/* returns 0 if idx's corresponding MSR exists; otherwise returns 1. */
-static int amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
+static bool amd_is_valid_rdpmc_ecx(struct kvm_vcpu *vcpu, unsigned int idx)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 
 	idx &= ~(3u << 30);
 
-	return (idx >= pmu->nr_arch_gp_counters);
+	return idx < pmu->nr_arch_gp_counters;
 }
 
 /* idx is the ECX register of RDPMC instruction */

arch/x86/kvm/svm/svm.c

@@ -3121,11 +3121,6 @@ static int invpcid_interception(struct kvm_vcpu *vcpu)
 	type = svm->vmcb->control.exit_info_2;
 	gva = svm->vmcb->control.exit_info_1;
 
-	if (type > 3) {
-		kvm_inject_gp(vcpu, 0);
-		return 1;
-	}
-
 	return kvm_handle_invpcid(vcpu, type, gva);
 }