KVM updates for 2.6.32 merge window (2/4)

index 5f97dbd..b6e4cda 100644
@@ -2673,8 +2673,9 @@ int kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gva_t cr2, u32 error_code)
 		++vcpu->stat.mmio_exits;
 		return 0;
 	case EMULATE_FAIL:
-		kvm_report_emulation_failure(vcpu, "pagetable");
-		return 1;
+		vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+		vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_EMULATION;
+		return 0;
 	default:
 		BUG();
 	}

index 5037e17..6710518 100644
@@ -95,6 +95,10 @@ struct kvm_pit_config {
 #define KVM_EXIT_S390_RESET       14
 #define KVM_EXIT_DCR              15
 #define KVM_EXIT_NMI              16
+#define KVM_EXIT_INTERNAL_ERROR   17
+
+/* For KVM_EXIT_INTERNAL_ERROR */
+#define KVM_INTERNAL_ERROR_EMULATION 1
 
 /* for KVM_RUN, returned by mmap(vcpu_fd, offset=0) */
 struct kvm_run {

@@ -181,6 +185,9 @@ struct kvm_run {
 			__u32 data;
 			__u8  is_write;
 		} dcr;
+		struct {
+			__u32 suberror;
+		} internal;
 		/* Fix the size of the union. */
 		char padding[256];
 	};

index b6e4cda..f85d995 100644
@@ -250,6 +250,15 @@ static int is_rmap_spte(u64 pte)
 	return is_shadow_present_pte(pte);
 }
 
+static int is_last_spte(u64 pte, int level)
+{
+	if (level == PT_PAGE_TABLE_LEVEL)
+		return 1;
+	if (level == PT_DIRECTORY_LEVEL && is_large_pte(pte))
+		return 1;
+	return 0;
+}
+
 static pfn_t spte_to_pfn(u64 pte)
 {
 	return (pte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;

@@ -1313,25 +1322,17 @@ static void kvm_mmu_page_unlink_children(struct kvm *kvm,
 
 	pt = sp->spt;
 
-	if (sp->role.level == PT_PAGE_TABLE_LEVEL) {
-		for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
-			if (is_shadow_present_pte(pt[i]))
-				rmap_remove(kvm, &pt[i]);
-			pt[i] = shadow_trap_nonpresent_pte;
-		}
-		return;
-	}
-
 	for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
 		ent = pt[i];
 
 		if (is_shadow_present_pte(ent)) {
-			if (!is_large_pte(ent)) {
+			if (!is_last_spte(ent, sp->role.level)) {
 				ent &= PT64_BASE_ADDR_MASK;
 				mmu_page_remove_parent_pte(page_header(ent),
 							   &pt[i]);
 			} else {
-				--kvm->stat.lpages;
+				if (is_large_pte(ent))
+					--kvm->stat.lpages;
 				rmap_remove(kvm, &pt[i]);
 			}
 		}

@@ -2381,8 +2382,7 @@ static void mmu_pte_write_zap_pte(struct kvm_vcpu *vcpu,
 
 	pte = *spte;
 	if (is_shadow_present_pte(pte)) {
-		if (sp->role.level == PT_PAGE_TABLE_LEVEL ||
-		    is_large_pte(pte))
+		if (is_last_spte(pte, sp->role.level))
 			rmap_remove(vcpu->kvm, spte);
 		else {
 			child = page_header(pte & PT64_BASE_ADDR_MASK);

index f85d995..fd5579c 100644
@@ -3045,6 +3045,55 @@ static gva_t canonicalize(gva_t gva)
 	return gva;
 }
 
+
+typedef void (*inspect_spte_fn) (struct kvm *kvm, struct kvm_mmu_page *sp,
+				 u64 *sptep);
+
+static void __mmu_spte_walk(struct kvm *kvm, struct kvm_mmu_page *sp,
+			    inspect_spte_fn fn)
+{
+	int i;
+
+	for (i = 0; i < PT64_ENT_PER_PAGE; ++i) {
+		u64 ent = sp->spt[i];
+
+		if (is_shadow_present_pte(ent)) {
+			if (sp->role.level > 1 && !is_large_pte(ent)) {
+				struct kvm_mmu_page *child;
+				child = page_header(ent & PT64_BASE_ADDR_MASK);
+				__mmu_spte_walk(kvm, child, fn);
+			}
+			if (sp->role.level == 1)
+				fn(kvm, sp, &sp->spt[i]);
+		}
+	}
+}
+
+static void mmu_spte_walk(struct kvm_vcpu *vcpu, inspect_spte_fn fn)
+{
+	int i;
+	struct kvm_mmu_page *sp;
+
+	if (!VALID_PAGE(vcpu->arch.mmu.root_hpa))
+		return;
+	if (vcpu->arch.mmu.shadow_root_level == PT64_ROOT_LEVEL) {
+		hpa_t root = vcpu->arch.mmu.root_hpa;
+		sp = page_header(root);
+		__mmu_spte_walk(vcpu->kvm, sp, fn);
+		return;
+	}
+	for (i = 0; i < 4; ++i) {
+		hpa_t root = vcpu->arch.mmu.pae_root[i];
+
+		if (root && VALID_PAGE(root)) {
+			root &= PT64_BASE_ADDR_MASK;
+			sp = page_header(root);
+			__mmu_spte_walk(vcpu->kvm, sp, fn);
+		}
+	}
+	return;
+}
+
 static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte,
 				gva_t va, int level)
 {

@@ -3137,9 +3186,47 @@ static int count_rmaps(struct kvm_vcpu *vcpu)
 	return nmaps;
 }
 
-static int count_writable_mappings(struct kvm_vcpu *vcpu)
+void inspect_spte_has_rmap(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *sptep)
+{
+	unsigned long *rmapp;
+	struct kvm_mmu_page *rev_sp;
+	gfn_t gfn;
+
+	if (*sptep & PT_WRITABLE_MASK) {
+		rev_sp = page_header(__pa(sptep));
+		gfn = rev_sp->gfns[sptep - rev_sp->spt];
+
+		if (!gfn_to_memslot(kvm, gfn)) {
+			if (!printk_ratelimit())
+				return;
+			printk(KERN_ERR "%s: no memslot for gfn %ld\n",
+					 audit_msg, gfn);
+			printk(KERN_ERR "%s: index %ld of sp (gfn=%lx)\n",
+					audit_msg, sptep - rev_sp->spt,
+					rev_sp->gfn);
+			dump_stack();
+			return;
+		}
+
+		rmapp = gfn_to_rmap(kvm, rev_sp->gfns[sptep - rev_sp->spt], 0);
+		if (!*rmapp) {
+			if (!printk_ratelimit())
+				return;
+			printk(KERN_ERR "%s: no rmap for writable spte %llx\n",
+					 audit_msg, *sptep);
+			dump_stack();
+		}
+	}
+
+}
+
+void audit_writable_sptes_have_rmaps(struct kvm_vcpu *vcpu)
+{
+	mmu_spte_walk(vcpu, inspect_spte_has_rmap);
+}
+
+static void check_writable_mappings_rmap(struct kvm_vcpu *vcpu)
 {
-	int nmaps = 0;
 	struct kvm_mmu_page *sp;
 	int i;
 

@@ -3156,20 +3243,16 @@ static int count_writable_mappings(struct kvm_vcpu *vcpu)
 				continue;
 			if (!(ent & PT_WRITABLE_MASK))
 				continue;
-			++nmaps;
+			inspect_spte_has_rmap(vcpu->kvm, sp, &pt[i]);
 		}
 	}
-	return nmaps;
+	return;
 }
 
 static void audit_rmap(struct kvm_vcpu *vcpu)
 {
-	int n_rmap = count_rmaps(vcpu);
-	int n_actual = count_writable_mappings(vcpu);
-
-	if (n_rmap != n_actual)
-		printk(KERN_ERR "%s: (%s) rmap %d actual %d\n",
-		       __func__, audit_msg, n_rmap, n_actual);
+	check_writable_mappings_rmap(vcpu);
+	count_rmaps(vcpu);
 }
 
 static void audit_write_protection(struct kvm_vcpu *vcpu)

@@ -3203,6 +3286,7 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg)
 	audit_rmap(vcpu);
 	audit_write_protection(vcpu);
 	audit_mappings(vcpu);
+	audit_writable_sptes_have_rmaps(vcpu);
 	dbg = olddbg;
 }
 

index fd5579c..4c2585c 100644
@@ -3260,20 +3260,28 @@ static void audit_write_protection(struct kvm_vcpu *vcpu)
 	struct kvm_mmu_page *sp;
 	struct kvm_memory_slot *slot;
 	unsigned long *rmapp;
+	u64 *spte;
 	gfn_t gfn;
 
 	list_for_each_entry(sp, &vcpu->kvm->arch.active_mmu_pages, link) {
 		if (sp->role.direct)
 			continue;
+		if (sp->unsync)
+			continue;
 
 		gfn = unalias_gfn(vcpu->kvm, sp->gfn);
 		slot = gfn_to_memslot_unaliased(vcpu->kvm, sp->gfn);
 		rmapp = &slot->rmap[gfn - slot->base_gfn];
-		if (*rmapp)
-			printk(KERN_ERR "%s: (%s) shadow page has writable"
-			       " mappings: gfn %lx role %x\n",
+
+		spte = rmap_next(vcpu->kvm, rmapp, NULL);
+		while (spte) {
+			if (*spte & PT_WRITABLE_MASK)
+				printk(KERN_ERR "%s: (%s) shadow page has "
+				"writable mappings: gfn %lx role %x\n",
 			       __func__, audit_msg, sp->gfn,
 			       sp->role.word);
+			spte = rmap_next(vcpu->kvm, rmapp, spte);
+		}
 	}
 }
 

index 4c2585c..8643351 100644
@@ -3109,12 +3109,7 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte,
 
 		va = canonicalize(va);
 		if (level > 1) {
-			if (ent == shadow_notrap_nonpresent_pte)
-				printk(KERN_ERR "audit: (%s) nontrapping pte"
-				       " in nonleaf level: levels %d gva %lx"
-				       " level %d pte %llx\n", audit_msg,
-				       vcpu->arch.mmu.root_level, va, level, ent);
-			else
+			if (is_shadow_present_pte(ent))
 				audit_mappings_page(vcpu, ent, va, level - 1);
 		} else {
 			gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, va);

index 8643351..50fe854 100644
@@ -3117,6 +3117,11 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte,
 			pfn_t pfn = gfn_to_pfn(vcpu->kvm, gfn);
 			hpa_t hpa = (hpa_t)pfn << PAGE_SHIFT;
 
+			if (is_error_pfn(pfn)) {
+				kvm_release_pfn_clean(pfn);
+				continue;
+			}
+
 			if (is_shadow_present_pte(ent)
 			    && (ent & PT64_BASE_ADDR_MASK) != hpa)
 				printk(KERN_ERR "xx audit error: (%s) levels %d"

@@ -3288,7 +3293,8 @@ static void kvm_mmu_audit(struct kvm_vcpu *vcpu, const char *msg)
 	audit_msg = msg;
 	audit_rmap(vcpu);
 	audit_write_protection(vcpu);
-	audit_mappings(vcpu);
+	if (strcmp("pre pte write", audit_msg) != 0)
+		audit_mappings(vcpu);
 	audit_writable_sptes_have_rmaps(vcpu);
 	dbg = olddbg;
 }

index 50fe854..780ce3f 100644
@@ -3058,12 +3058,11 @@ static void __mmu_spte_walk(struct kvm *kvm, struct kvm_mmu_page *sp,
 		u64 ent = sp->spt[i];
 
 		if (is_shadow_present_pte(ent)) {
-			if (sp->role.level > 1 && !is_large_pte(ent)) {
+			if (!is_last_spte(ent, sp->role.level)) {
 				struct kvm_mmu_page *child;
 				child = page_header(ent & PT64_BASE_ADDR_MASK);
 				__mmu_spte_walk(kvm, child, fn);
-			}
-			if (sp->role.level == 1)
+			} else
 				fn(kvm, sp, &sp->spt[i]);
 		}
 	}

@@ -3108,10 +3107,9 @@ static void audit_mappings_page(struct kvm_vcpu *vcpu, u64 page_pte,
 			continue;
 
 		va = canonicalize(va);
-		if (level > 1) {
-			if (is_shadow_present_pte(ent))
-				audit_mappings_page(vcpu, ent, va, level - 1);
-		} else {
+		if (is_shadow_present_pte(ent) && !is_last_spte(ent, level))
+			audit_mappings_page(vcpu, ent, va, level - 1);
+		else {
 			gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, va);
 			gfn_t gfn = gpa >> PAGE_SHIFT;
 			pfn_t pfn = gfn_to_pfn(vcpu->kvm, gfn);

@@ -3208,7 +3206,8 @@ void inspect_spte_has_rmap(struct kvm *kvm, struct kvm_mmu_page *sp, u64 *sptep)
 			return;
 		}
 
-		rmapp = gfn_to_rmap(kvm, rev_sp->gfns[sptep - rev_sp->spt], 0);
+		rmapp = gfn_to_rmap(kvm, rev_sp->gfns[sptep - rev_sp->spt],
+				    is_large_pte(*sptep));
 		if (!*rmapp) {
 			if (!printk_ratelimit())
 				return;

index a7fa87b..e1dd47d 100644
@@ -2143,22 +2143,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 		else
 			svm_disable_lbrv(svm);
 		break;
-	case MSR_K7_EVNTSEL0:
-	case MSR_K7_EVNTSEL1:
-	case MSR_K7_EVNTSEL2:
-	case MSR_K7_EVNTSEL3:
-	case MSR_K7_PERFCTR0:
-	case MSR_K7_PERFCTR1:
-	case MSR_K7_PERFCTR2:
-	case MSR_K7_PERFCTR3:
-		/*
-		 * Just discard all writes to the performance counters; this
-		 * should keep both older linux and windows 64-bit guests
-		 * happy
-		 */
-		pr_unimpl(vcpu, "unimplemented perfctr wrmsr: 0x%x data 0x%llx\n", ecx, data);
-
-		break;
 	case MSR_VM_HSAVE_PA:
 		svm->hsave_msr = data;
 		break;

index c08bb4c..6ee9292 100644
@@ -1025,18 +1025,6 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 		rdtscll(host_tsc);
 		guest_write_tsc(data, host_tsc);
 		break;
-	case MSR_P6_PERFCTR0:
-	case MSR_P6_PERFCTR1:
-	case MSR_P6_EVNTSEL0:
-	case MSR_P6_EVNTSEL1:
-		/*
-		 * Just discard all writes to the performance counters; this
-		 * should keep both older linux and windows 64-bit guests
-		 * happy
-		 */
-		pr_unimpl(vcpu, "unimplemented perfctr wrmsr: 0x%x data 0x%llx\n", msr_index, data);
-
-		break;
 	case MSR_IA32_CR_PAT:
 		if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT) {
 			vmcs_write64(GUEST_IA32_PAT, data);

index 89862a8..30492f0 100644
@@ -886,6 +886,36 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	case MSR_IA32_MCG_STATUS:
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
 		return set_msr_mce(vcpu, msr, data);
+
+	/* Performance counters are not protected by a CPUID bit,
+	 * so we should check all of them in the generic path for the sake of
+	 * cross vendor migration.
+	 * Writing a zero into the event select MSRs disables them,
+	 * which we perfectly emulate ;-). Any other value should be at least
+	 * reported, some guests depend on them.
+	 */
+	case MSR_P6_EVNTSEL0:
+	case MSR_P6_EVNTSEL1:
+	case MSR_K7_EVNTSEL0:
+	case MSR_K7_EVNTSEL1:
+	case MSR_K7_EVNTSEL2:
+	case MSR_K7_EVNTSEL3:
+		if (data != 0)
+			pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
+				"0x%x data 0x%llx\n", msr, data);
+		break;
+	/* at least RHEL 4 unconditionally writes to the perfctr registers,
+	 * so we ignore writes to make it happy.
+	 */
+	case MSR_P6_PERFCTR0:
+	case MSR_P6_PERFCTR1:
+	case MSR_K7_PERFCTR0:
+	case MSR_K7_PERFCTR1:
+	case MSR_K7_PERFCTR2:
+	case MSR_K7_PERFCTR3:
+		pr_unimpl(vcpu, "unimplemented perfctr wrmsr: "
+			"0x%x data 0x%llx\n", msr, data);
+		break;
 	default:
 		pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data);
 		return 1;

index e7927a6..272514c 100644
@@ -352,9 +352,16 @@ enum vmcs_field {
 #define VMX_EPT_EXTENT_INDIVIDUAL_ADDR		0
 #define VMX_EPT_EXTENT_CONTEXT			1
 #define VMX_EPT_EXTENT_GLOBAL			2
+
+#define VMX_EPT_EXECUTE_ONLY_BIT		(1ull)
+#define VMX_EPT_PAGE_WALK_4_BIT			(1ull << 6)
+#define VMX_EPTP_UC_BIT				(1ull << 8)
+#define VMX_EPTP_WB_BIT				(1ull << 14)
+#define VMX_EPT_2MB_PAGE_BIT			(1ull << 16)
 #define VMX_EPT_EXTENT_INDIVIDUAL_BIT		(1ull << 24)
 #define VMX_EPT_EXTENT_CONTEXT_BIT		(1ull << 25)
 #define VMX_EPT_EXTENT_GLOBAL_BIT		(1ull << 26)
+
 #define VMX_EPT_DEFAULT_GAW			3
 #define VMX_EPT_MAX_GAW				0x4
 #define VMX_EPT_MT_EPTE_SHIFT			3

index 6ee9292..6610181 100644
@@ -270,6 +270,26 @@ static inline bool cpu_has_vmx_flexpriority(void)
 		cpu_has_vmx_virtualize_apic_accesses();
 }
 
+static inline bool cpu_has_vmx_ept_execute_only(void)
+{
+	return !!(vmx_capability.ept & VMX_EPT_EXECUTE_ONLY_BIT);
+}
+
+static inline bool cpu_has_vmx_eptp_uncacheable(void)
+{
+	return !!(vmx_capability.ept & VMX_EPTP_UC_BIT);
+}
+
+static inline bool cpu_has_vmx_eptp_writeback(void)
+{
+	return !!(vmx_capability.ept & VMX_EPTP_WB_BIT);
+}
+
+static inline bool cpu_has_vmx_ept_2m_page(void)
+{
+	return !!(vmx_capability.ept & VMX_EPT_2MB_PAGE_BIT);
+}
+
 static inline int cpu_has_vmx_invept_individual_addr(void)
 {
 	return !!(vmx_capability.ept & VMX_EPT_EXTENT_INDIVIDUAL_BIT);

index 780ce3f..e18f65b 100644
@@ -1302,6 +1302,11 @@ static bool shadow_walk_okay(struct kvm_shadow_walk_iterator *iterator)
 {
 	if (iterator->level < PT_PAGE_TABLE_LEVEL)
 		return false;
+
+	if (iterator->level == PT_PAGE_TABLE_LEVEL)
+		if (is_large_pte(*iterator->sptep))
+			return false;
+
 	iterator->index = SHADOW_PT_INDEX(iterator->addr, iterator->level);
 	iterator->sptep	= ((u64 *)__va(iterator->shadow_addr)) + iterator->index;
 	return true;

index e18f65b..12974de 100644
@@ -3038,6 +3038,24 @@ out:
 	return r;
 }
 
+int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4])
+{
+	struct kvm_shadow_walk_iterator iterator;
+	int nr_sptes = 0;
+
+	spin_lock(&vcpu->kvm->mmu_lock);
+	for_each_shadow_entry(vcpu, addr, iterator) {
+		sptes[iterator.level-1] = *iterator.sptep;
+		nr_sptes++;
+		if (!is_shadow_present_pte(*iterator.sptep))
+			break;
+	}
+	spin_unlock(&vcpu->kvm->mmu_lock);
+
+	return nr_sptes;
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_get_spte_hierarchy);
+
 #ifdef AUDIT
 
 static const char *audit_msg;

index 016bf71..61a1b38 100644
@@ -37,6 +37,8 @@
 #define PT32_ROOT_LEVEL 2
 #define PT32E_ROOT_LEVEL 3
 
+int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]);
+
 static inline void kvm_mmu_free_some_pages(struct kvm_vcpu *vcpu)
 {
 	if (unlikely(vcpu->kvm->arch.n_free_mmu_pages < KVM_MIN_FREE_MMU_PAGES))

index 6610181..94c07ad 100644
@@ -3227,6 +3227,89 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	return kvm_mmu_page_fault(vcpu, gpa & PAGE_MASK, 0);
 }
 
+static u64 ept_rsvd_mask(u64 spte, int level)
+{
+	int i;
+	u64 mask = 0;
+
+	for (i = 51; i > boot_cpu_data.x86_phys_bits; i--)
+		mask |= (1ULL << i);
+
+	if (level > 2)
+		/* bits 7:3 reserved */
+		mask |= 0xf8;
+	else if (level == 2) {
+		if (spte & (1ULL << 7))
+			/* 2MB ref, bits 20:12 reserved */
+			mask |= 0x1ff000;
+		else
+			/* bits 6:3 reserved */
+			mask |= 0x78;
+	}
+
+	return mask;
+}
+
+static void ept_misconfig_inspect_spte(struct kvm_vcpu *vcpu, u64 spte,
+				       int level)
+{
+	printk(KERN_ERR "%s: spte 0x%llx level %d\n", __func__, spte, level);
+
+	/* 010b (write-only) */
+	WARN_ON((spte & 0x7) == 0x2);
+
+	/* 110b (write/execute) */
+	WARN_ON((spte & 0x7) == 0x6);
+
+	/* 100b (execute-only) and value not supported by logical processor */
+	if (!cpu_has_vmx_ept_execute_only())
+		WARN_ON((spte & 0x7) == 0x4);
+
+	/* not 000b */
+	if ((spte & 0x7)) {
+		u64 rsvd_bits = spte & ept_rsvd_mask(spte, level);
+
+		if (rsvd_bits != 0) {
+			printk(KERN_ERR "%s: rsvd_bits = 0x%llx\n",
+					 __func__, rsvd_bits);
+			WARN_ON(1);
+		}
+
+		if (level == 1 || (level == 2 && (spte & (1ULL << 7)))) {
+			u64 ept_mem_type = (spte & 0x38) >> 3;
+
+			if (ept_mem_type == 2 || ept_mem_type == 3 ||
+			    ept_mem_type == 7) {
+				printk(KERN_ERR "%s: ept_mem_type=0x%llx\n",
+						__func__, ept_mem_type);
+				WARN_ON(1);
+			}
+		}
+	}
+}
+
+static int handle_ept_misconfig(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
+{
+	u64 sptes[4];
+	int nr_sptes, i;
+	gpa_t gpa;
+
+	gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
+
+	printk(KERN_ERR "EPT: Misconfiguration.\n");
+	printk(KERN_ERR "EPT: GPA: 0x%llx\n", gpa);
+
+	nr_sptes = kvm_mmu_get_spte_hierarchy(vcpu, gpa, sptes);
+
+	for (i = PT64_ROOT_LEVEL; i > PT64_ROOT_LEVEL - nr_sptes; --i)
+		ept_misconfig_inspect_spte(vcpu, sptes[i-1], i);
+
+	kvm_run->exit_reason = KVM_EXIT_UNKNOWN;
+	kvm_run->hw.hardware_exit_reason = EXIT_REASON_EPT_MISCONFIG;
+
+	return 0;
+}
+
 static int handle_nmi_window(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	u32 cpu_based_vm_exec_control;

@@ -3306,8 +3389,9 @@ static int (*kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu,
 	[EXIT_REASON_APIC_ACCESS]             = handle_apic_access,
 	[EXIT_REASON_WBINVD]                  = handle_wbinvd,
 	[EXIT_REASON_TASK_SWITCH]             = handle_task_switch,
-	[EXIT_REASON_EPT_VIOLATION]	      = handle_ept_violation,
 	[EXIT_REASON_MCE_DURING_VMENTRY]      = handle_machine_check,
+	[EXIT_REASON_EPT_VIOLATION]	      = handle_ept_violation,
+	[EXIT_REASON_EPT_MISCONFIG]           = handle_ept_misconfig,
 };
 
 static const int kvm_vmx_max_exit_handlers =

index 94c07ad..fc8d49c 100644
@@ -1381,6 +1381,9 @@ static __init int hardware_setup(void)
 	if (!cpu_has_vmx_tpr_shadow())
 		kvm_x86_ops->update_cr8_intercept = NULL;
 
+	if (enable_ept && !cpu_has_vmx_ept_2m_page())
+		kvm_disable_largepages();
+
 	return alloc_kvm_area();
 }
 

index c6e4d02..6988858 100644
@@ -224,6 +224,7 @@ int kvm_arch_set_memory_region(struct kvm *kvm,
 				struct kvm_userspace_memory_region *mem,
 				struct kvm_memory_slot old,
 				int user_alloc);
+void kvm_disable_largepages(void);
 void kvm_arch_flush_shadow(struct kvm *kvm);
 gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn);
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);

index 777fe53..48d5e69 100644
@@ -85,6 +85,8 @@ static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
 
 static bool kvm_rebooting;
 
+static bool largepages_enabled = true;
+
 #ifdef KVM_CAP_DEVICE_ASSIGNMENT
 static struct kvm_assigned_dev_kernel *kvm_find_assigned_dev(struct list_head *head,
 						      int assigned_dev_id)

@@ -1174,9 +1176,11 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		ugfn = new.userspace_addr >> PAGE_SHIFT;
 		/*
 		 * If the gfn and userspace address are not aligned wrt each
-		 * other, disable large page support for this slot
+		 * other, or if explicitly asked to, disable large page
+		 * support for this slot
 		 */
-		if ((base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE - 1))
+		if ((base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE - 1) ||
+		    !largepages_enabled)
 			for (i = 0; i < largepages; ++i)
 				new.lpage_info[i].write_count = 1;
 	}

@@ -1291,6 +1295,12 @@ out:
 	return r;
 }
 
+void kvm_disable_largepages(void)
+{
+	largepages_enabled = false;
+}
+EXPORT_SYMBOL_GPL(kvm_disable_largepages);
+
 int is_error_page(struct page *page)
 {
 	return page == bad_page;

index 30492f0..a066876 100644
@@ -181,16 +181,22 @@ void kvm_inject_page_fault(struct kvm_vcpu *vcpu, unsigned long addr,
 	++vcpu->stat.pf_guest;
 
 	if (vcpu->arch.exception.pending) {
-		if (vcpu->arch.exception.nr == PF_VECTOR) {
-			printk(KERN_DEBUG "kvm: inject_page_fault:"
-					" double fault 0x%lx\n", addr);
-			vcpu->arch.exception.nr = DF_VECTOR;
-			vcpu->arch.exception.error_code = 0;
-		} else if (vcpu->arch.exception.nr == DF_VECTOR) {
+		switch(vcpu->arch.exception.nr) {
+		case DF_VECTOR:
 			/* triple fault -> shutdown */
 			set_bit(KVM_REQ_TRIPLE_FAULT, &vcpu->requests);
+			return;
+		case PF_VECTOR:
+			vcpu->arch.exception.nr = DF_VECTOR;
+			vcpu->arch.exception.error_code = 0;
+			return;
+		default:
+			/* replace previous exception with a new one in a hope
+			   that instruction re-execution will regenerate lost
+			   exception */
+			vcpu->arch.exception.pending = false;
+			break;
 		}
-		return;
 	}
 	vcpu->arch.cr2 = addr;
 	kvm_queue_exception_e(vcpu, PF_VECTOR, error_code);

index b1694dc..3bde43c 100644
@@ -165,29 +165,46 @@ static int find_highest_vector(void *bitmap)
 
 static inline int apic_test_and_set_irr(int vec, struct kvm_lapic *apic)
 {
+	apic->irr_pending = true;
 	return apic_test_and_set_vector(vec, apic->regs + APIC_IRR);
 }
 
-static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
+static inline int apic_search_irr(struct kvm_lapic *apic)
 {
-	apic_clear_vector(vec, apic->regs + APIC_IRR);
+	return find_highest_vector(apic->regs + APIC_IRR);
 }
 
 static inline int apic_find_highest_irr(struct kvm_lapic *apic)
 {
 	int result;
 
-	result = find_highest_vector(apic->regs + APIC_IRR);
+	if (!apic->irr_pending)
+		return -1;
+
+	result = apic_search_irr(apic);
 	ASSERT(result == -1 || result >= 16);
 
 	return result;
 }
 
+static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
+{
+	apic->irr_pending = false;
+	apic_clear_vector(vec, apic->regs + APIC_IRR);
+	if (apic_search_irr(apic) != -1)
+		apic->irr_pending = true;
+}
+
 int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 	int highest_irr;
 
+	/* This may race with setting of irr in __apic_accept_irq() and
+	 * value returned may be wrong, but kvm_vcpu_kick() in __apic_accept_irq
+	 * will cause vmexit immediately and the value will be recalculated
+	 * on the next vmentry.
+	 */
 	if (!apic)
 		return 0;
 	highest_irr = apic_find_highest_irr(apic);

@@ -843,6 +860,7 @@ void kvm_lapic_reset(struct kvm_vcpu *vcpu)
 		apic_set_reg(apic, APIC_ISR + 0x10 * i, 0);
 		apic_set_reg(apic, APIC_TMR + 0x10 * i, 0);
 	}
+	apic->irr_pending = false;
 	update_divide_count(apic);
 	atomic_set(&apic->lapic_timer.pending, 0);
 	if (kvm_vcpu_is_bsp(vcpu))

index a587f83..3f3ecc6 100644
@@ -12,6 +12,7 @@ struct kvm_lapic {
 	struct kvm_timer lapic_timer;
 	u32 divide_count;
 	struct kvm_vcpu *vcpu;
+	bool irr_pending;
 	struct page *regs_page;
 	void *regs;
 	gpa_t vapic_addr;

index 85cc743..1baed41 100644
@@ -9,12 +9,16 @@ static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer)
 	int restart_timer = 0;
 	wait_queue_head_t *q = &vcpu->wq;
 
-	/* FIXME: this code should not know anything about vcpus */
-	if (!atomic_inc_and_test(&ktimer->pending))
-		set_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
-
-	if (!ktimer->reinject)
-		atomic_set(&ktimer->pending, 1);
+	/*
+	 * There is a race window between reading and incrementing, but we do
+	 * not care about potentially loosing timer events in the !reinject
+	 * case anyway.
+	 */
+	if (ktimer->reinject || !atomic_read(&ktimer->pending)) {
+		/* FIXME: this code should not know anything about vcpus */
+		if (!atomic_inc_and_test(&ktimer->pending))
+			set_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
+	}
 
 	if (waitqueue_active(q))
 		wake_up_interruptible(q);

index 1baed41..eea4043 100644
@@ -15,9 +15,9 @@ static int __kvm_timer_fn(struct kvm_vcpu *vcpu, struct kvm_timer *ktimer)
 	 * case anyway.
 	 */
 	if (ktimer->reinject || !atomic_read(&ktimer->pending)) {
+		atomic_inc(&ktimer->pending);
 		/* FIXME: this code should not know anything about vcpus */
-		if (!atomic_inc_and_test(&ktimer->pending))
-			set_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
+		set_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
 	}
 
 	if (waitqueue_active(q))

index fc8d49c..1a84ca1 100644
@@ -3651,11 +3651,16 @@ static void vmx_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 		"mov %%"R"sp, %c[host_rsp](%0) \n\t"
 		__ex(ASM_VMX_VMWRITE_RSP_RDX) "\n\t"
 		"1: \n\t"
+		/* Reload cr2 if changed */
+		"mov %c[cr2](%0), %%"R"ax \n\t"
+		"mov %%cr2, %%"R"dx \n\t"
+		"cmp %%"R"ax, %%"R"dx \n\t"
+		"je 2f \n\t"
+		"mov %%"R"ax, %%cr2 \n\t"
+		"2: \n\t"
 		/* Check if vmlaunch of vmresume is needed */
 		"cmpl $0, %c[launched](%0) \n\t"
 		/* Load guest registers.  Don't clobber flags. */
-		"mov %c[cr2](%0), %%"R"ax \n\t"
-		"mov %%"R"ax, %%cr2 \n\t"
 		"mov %c[rax](%0), %%"R"ax \n\t"
 		"mov %c[rbx](%0), %%"R"bx \n\t"
 		"mov %c[rdx](%0), %%"R"dx \n\t"

index e1dd47d..5a1f26c 100644
@@ -82,7 +82,6 @@ struct vcpu_svm {
 
 	u64 host_user_msrs[NR_HOST_SAVE_USER_MSRS];
 	u64 host_gs_base;
-	unsigned long host_cr2;
 
 	u32 *msrpm;
 	struct vmcb *hsave;

@@ -187,19 +186,6 @@ static inline void invlpga(unsigned long addr, u32 asid)
 	asm volatile (__ex(SVM_INVLPGA) :: "a"(addr), "c"(asid));
 }
 
-static inline unsigned long kvm_read_cr2(void)
-{
-	unsigned long cr2;
-
-	asm volatile ("mov %%cr2, %0" : "=r" (cr2));
-	return cr2;
-}
-
-static inline void kvm_write_cr2(unsigned long val)
-{
-	asm volatile ("mov %0, %%cr2" :: "r" (val));
-}
-
 static inline void force_new_asid(struct kvm_vcpu *vcpu)
 {
 	to_svm(vcpu)->asid_generation--;

@@ -2528,7 +2514,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	fs_selector = kvm_read_fs();
 	gs_selector = kvm_read_gs();
 	ldt_selector = kvm_read_ldt();
-	svm->host_cr2 = kvm_read_cr2();
 	if (!is_nested(svm))
 		svm->vmcb->save.cr2 = vcpu->arch.cr2;
 	/* required for live migration with NPT */

@@ -2615,8 +2600,6 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	vcpu->arch.regs[VCPU_REGS_RSP] = svm->vmcb->save.rsp;
 	vcpu->arch.regs[VCPU_REGS_RIP] = svm->vmcb->save.rip;
 
-	kvm_write_cr2(svm->host_cr2);
-
 	kvm_load_fs(fs_selector);
 	kvm_load_gs(gs_selector);
 	kvm_load_ldt(ldt_selector);

index 6be7fc2..bd55490 100644
@@ -374,6 +374,7 @@
 /* AMD-V MSRs */
 
 #define MSR_VM_CR                       0xc0010114
+#define MSR_VM_IGNNE                    0xc0010115
 #define MSR_VM_HSAVE_PA                 0xc0010117
 
 #endif /* _ASM_X86_MSR_INDEX_H */

index 5a1f26c..8f80190 100644
@@ -2132,6 +2132,11 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 	case MSR_VM_HSAVE_PA:
 		svm->hsave_msr = data;
 		break;
+	case MSR_VM_CR:
+	case MSR_VM_IGNNE:
+	case MSR_K7_HWCR:
+		pr_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
+		break;
 	default:
 		return kvm_set_msr_common(vcpu, ecx, data);
 	}

index 8f80190..cd5a081 100644
@@ -1883,6 +1883,19 @@ static int clgi_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
 	return 1;
 }
 
+static int invlpga_interception(struct vcpu_svm *svm, struct kvm_run *kvm_run)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	nsvm_printk("INVLPGA\n");
+
+	/* Let's treat INVLPGA the same as INVLPG (can be optimized!) */
+	kvm_mmu_invlpg(vcpu, vcpu->arch.regs[VCPU_REGS_RAX]);
+
+	svm->next_rip = kvm_rip_read(&svm->vcpu) + 3;
+	skip_emulated_instruction(&svm->vcpu);
+	return 1;
+}
+
 static int invalid_op_interception(struct vcpu_svm *svm,
 				   struct kvm_run *kvm_run)
 {

@@ -2228,7 +2241,7 @@ static int (*svm_exit_handlers[])(struct vcpu_svm *svm,
 	[SVM_EXIT_INVD]                         = emulate_on_interception,
 	[SVM_EXIT_HLT]				= halt_interception,
 	[SVM_EXIT_INVLPG]			= invlpg_interception,
-	[SVM_EXIT_INVLPGA]			= invalid_op_interception,
+	[SVM_EXIT_INVLPGA]			= invlpga_interception,
 	[SVM_EXIT_IOIO] 		  	= io_interception,
 	[SVM_EXIT_MSR]				= msr_interception,
 	[SVM_EXIT_TASK_SWITCH]			= task_switch_interception,

index cd5a081..b2e23c8 100644
@@ -1615,7 +1615,8 @@ static int nested_svm_vmexit_real(struct vcpu_svm *svm, void *arg1,
 	/* Kill any pending exceptions */
 	if (svm->vcpu.arch.exception.pending == true)
 		nsvm_printk("WARNING: Pending Exception\n");
-	svm->vcpu.arch.exception.pending = false;
+	kvm_clear_exception_queue(&svm->vcpu);
+	kvm_clear_interrupt_queue(&svm->vcpu);
 
 	/* Restore selected save entries */
 	svm->vmcb->save.es = hsave->save.es;

@@ -1683,7 +1684,8 @@ static int nested_svm_vmrun(struct vcpu_svm *svm, void *arg1,
 	svm->nested_vmcb = svm->vmcb->save.rax;
 
 	/* Clear internal status */
-	svm->vcpu.arch.exception.pending = false;
+	kvm_clear_exception_queue(&svm->vcpu);
+	kvm_clear_interrupt_queue(&svm->vcpu);
 
 	/* Save the old vmcb, so we don't need to pick what we save, but
 	   can restore everything when a VMEXIT occurs */

@@ -2363,21 +2365,14 @@ static inline void svm_inject_irq(struct vcpu_svm *svm, int irq)
 		((/*control->int_vector >> 4*/ 0xf) << V_INTR_PRIO_SHIFT);
 }
 
-static void svm_queue_irq(struct kvm_vcpu *vcpu, unsigned nr)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-
-	svm->vmcb->control.event_inj = nr |
-		SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR;
-}
-
 static void svm_set_irq(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	nested_svm_intr(svm);
+	BUG_ON(!(svm->vcpu.arch.hflags & HF_GIF_MASK));
 
-	svm_queue_irq(vcpu, vcpu->arch.interrupt.nr);
+	svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr |
+		SVM_EVTINJ_VALID | SVM_EVTINJ_TYPE_INTR;
 }
 
 static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)

@@ -2405,13 +2400,25 @@ static int svm_interrupt_allowed(struct kvm_vcpu *vcpu)
 	struct vmcb *vmcb = svm->vmcb;
 	return (vmcb->save.rflags & X86_EFLAGS_IF) &&
 		!(vmcb->control.int_state & SVM_INTERRUPT_SHADOW_MASK) &&
-		(svm->vcpu.arch.hflags & HF_GIF_MASK);
+		(svm->vcpu.arch.hflags & HF_GIF_MASK) &&
+		!is_nested(svm);
 }
 
 static void enable_irq_window(struct kvm_vcpu *vcpu)
 {
-	svm_set_vintr(to_svm(vcpu));
-	svm_inject_irq(to_svm(vcpu), 0x0);
+	struct vcpu_svm *svm = to_svm(vcpu);
+	nsvm_printk("Trying to open IRQ window\n");
+
+	nested_svm_intr(svm);
+
+	/* In case GIF=0 we can't rely on the CPU to tell us when
+	 * GIF becomes 1, because that's a separate STGI/VMRUN intercept.
+	 * The next time we get that intercept, this function will be
+	 * called again though and we'll get the vintr intercept. */
+	if (svm->vcpu.arch.hflags & HF_GIF_MASK) {
+		svm_set_vintr(svm);
+		svm_inject_irq(svm, 0x0);
+	}
 }
 
 static void enable_nmi_window(struct kvm_vcpu *vcpu)

@@ -2490,6 +2497,8 @@ static void svm_complete_interrupts(struct vcpu_svm *svm)
 	case SVM_EXITINTINFO_TYPE_EXEPT:
 		/* In case of software exception do not reinject an exception
 		   vector, but re-execute and instruction instead */
+		if (is_nested(svm))
+			break;
 		if (kvm_exception_is_soft(vector))
 			break;
 		if (exitintinfo & SVM_EXITINTINFO_VALID_ERR) {

index c7b0cc2..19027ab 100644
@@ -14,6 +14,7 @@
 #include <linux/types.h>
 #include <linux/mm.h>
 #include <linux/mmu_notifier.h>
+#include <linux/tracepoint.h>
 
 #include <linux/kvm.h>
 #include <linux/kvm_para.h>

@@ -527,6 +528,7 @@ struct kvm_x86_ops {
 	int (*set_tss_addr)(struct kvm *kvm, unsigned int addr);
 	int (*get_tdp_level)(void);
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
+	const struct trace_print_flags *exit_reasons_str;
 };
 
 extern struct kvm_x86_ops *kvm_x86_ops;

index 3bde43c..2e02865 100644
@@ -34,6 +34,7 @@
 #include <asm/atomic.h>
 #include "kvm_cache_regs.h"
 #include "irq.h"
+#include "trace.h"
 
 #ifndef CONFIG_X86_64
 #define mod_64(x, y) ((x) - (y) * div64_u64(x, y))

@@ -515,8 +516,6 @@ static u32 __apic_read(struct kvm_lapic *apic, unsigned int offset)
 {
 	u32 val = 0;
 
-	KVMTRACE_1D(APIC_ACCESS, apic->vcpu, (u32)offset, handler);
-
 	if (offset >= LAPIC_MMIO_LENGTH)
 		return 0;
 

@@ -562,6 +561,8 @@ static void apic_mmio_read(struct kvm_io_device *this,
 	}
 	result = __apic_read(apic, offset & ~0xf);
 
+	trace_kvm_apic_read(offset, result);
+
 	switch (len) {
 	case 1:
 	case 2:

@@ -657,7 +658,7 @@ static void apic_mmio_write(struct kvm_io_device *this,
 
 	offset &= 0xff0;
 
-	KVMTRACE_1D(APIC_ACCESS, apic->vcpu, (u32)offset, handler);
+	trace_kvm_apic_write(offset, val);
 
 	switch (offset) {
 	case APIC_ID:		/* Local APIC ID */

166 lines not on this page · raw message

260 lines not on this page · raw message

204 lines not on this page · raw message

117 lines not on this page · raw message

57 lines not on this page · raw message

index bb8a1b5..94759ed 100644
@@ -20,6 +20,7 @@
  */
 
 #include <linux/kvm_host.h>
+#include <trace/events/kvm.h>
 
 #include <asm/msidef.h>
 #ifdef CONFIG_IA64

@@ -125,6 +126,8 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, int irq, int level)
 	unsigned long *irq_state, sig_level;
 	int ret = -1;
 
+	trace_kvm_set_irq(irq);
+
 	WARN_ON(!mutex_is_locked(&kvm->irq_lock));
 
 	if (irq < KVM_IOAPIC_NUM_PINS) {

@@ -161,6 +164,8 @@ void kvm_notify_acked_irq(struct kvm *kvm, unsigned irqchip, unsigned pin)
 	struct hlist_node *n;
 	unsigned gsi = pin;
 
+	trace_kvm_ack_irq(irqchip, pin);
+
 	list_for_each_entry(e, &kvm->irq_routing, link)
 		if (e->type == KVM_IRQ_ROUTING_IRQCHIP &&
 		    e->irqchip.irqchip == irqchip &&

index 48d5e69..04bdedd 100644
@@ -59,6 +59,9 @@
 #include "irq.h"
 #endif
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/kvm.h>
+
 MODULE_AUTHOR("Qumranet");
 MODULE_LICENSE("GPL");
 

@@ -2718,6 +2721,7 @@ EXPORT_SYMBOL_GPL(kvm_init);
 void kvm_exit(void)
 {
 	kvm_trace_cleanup();
+	tracepoint_synchronize_unregister();
 	misc_deregister(&kvm_dev);
 	kmem_cache_destroy(kvm_vcpu_cache);
 	sysdev_unregister(&kvm_sysdev);

index 892a7a6..57e76b3 100644
@@ -2667,14 +2667,33 @@ int emulate_instruction(struct kvm_vcpu *vcpu,
 
 		r = x86_decode_insn(&vcpu->arch.emulate_ctxt, &emulate_ops);
 
-		/* Reject the instructions other than VMCALL/VMMCALL when
-		 * try to emulate invalid opcode */
+		/* Only allow emulation of specific instructions on #UD
+		 * (namely VMMCALL, sysenter, sysexit, syscall)*/
 		c = &vcpu->arch.emulate_ctxt.decode;
-		if ((emulation_type & EMULTYPE_TRAP_UD) &&
-		    (!(c->twobyte && c->b == 0x01 &&
-		      (c->modrm_reg == 0 || c->modrm_reg == 3) &&
-		       c->modrm_mod == 3 && c->modrm_rm == 1)))
-			return EMULATE_FAIL;
+		if (emulation_type & EMULTYPE_TRAP_UD) {
+			if (!c->twobyte)
+				return EMULATE_FAIL;
+			switch (c->b) {
+			case 0x01: /* VMMCALL */
+				if (c->modrm_mod != 3 || c->modrm_rm != 1)
+					return EMULATE_FAIL;
+				break;
+			case 0x34: /* sysenter */
+			case 0x35: /* sysexit */
+				if (c->modrm_mod != 0 || c->modrm_rm != 0)
+					return EMULATE_FAIL;
+				break;
+			case 0x05: /* syscall */
+				if (c->modrm_mod != 0 || c->modrm_rm != 0)
+					return EMULATE_FAIL;
+				break;
+			default:
+				return EMULATE_FAIL;
+			}
+
+			if (!(c->modrm_reg == 0 || c->modrm_reg == 3))
+				return EMULATE_FAIL;
+		}
 
 		++vcpu->stat.insn_emulation;
 		if (r)  {

index ef4dfca..67af33a 100644
@@ -320,8 +320,11 @@ static u32 group2_table[] = {
 };
 
 /* EFLAGS bit definitions. */
+#define EFLG_VM (1<<17)
+#define EFLG_RF (1<<16)
 #define EFLG_OF (1<<11)
 #define EFLG_DF (1<<10)
+#define EFLG_IF (1<<9)
 #define EFLG_SF (1<<7)
 #define EFLG_ZF (1<<6)
 #define EFLG_AF (1<<4)

index 67af33a..b0da29d 100644
@@ -32,6 +32,8 @@
 #include <linux/module.h>
 #include <asm/kvm_x86_emulate.h>
 
+#include "mmu.h"		/* for is_long_mode() */
+
 /*
  * Opcode effective-address decode tables.
  * Note that we only emulate instructions that have at least one memory

@@ -209,7 +211,7 @@ static u32 opcode_table[256] = {
 
 static u32 twobyte_table[256] = {
 	/* 0x00 - 0x0F */
-	0, Group | GroupDual | Group7, 0, 0, 0, 0, ImplicitOps, 0,
+	0, Group | GroupDual | Group7, 0, 0, 0, ImplicitOps, ImplicitOps, 0,
 	ImplicitOps, ImplicitOps, 0, 0, 0, ImplicitOps | ModRM, 0, 0,
 	/* 0x10 - 0x1F */
 	0, 0, 0, 0, 0, 0, 0, 0, ImplicitOps | ModRM, 0, 0, 0, 0, 0, 0, 0,

@@ -217,7 +219,9 @@ static u32 twobyte_table[256] = {
 	ModRM | ImplicitOps, ModRM, ModRM | ImplicitOps, ModRM, 0, 0, 0, 0,
 	0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0x30 - 0x3F */
-	ImplicitOps, 0, ImplicitOps, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
+	ImplicitOps, 0, ImplicitOps, 0,
+	ImplicitOps, ImplicitOps, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0,
 	/* 0x40 - 0x47 */
 	DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov,
 	DstReg | SrcMem | ModRM | Mov, DstReg | SrcMem | ModRM | Mov,

@@ -1988,6 +1992,9 @@ twobyte_insn:
 			goto cannot_emulate;
 		}
 		break;
+	case 0x05: 		/* syscall */
+		goto cannot_emulate;
+		break;
 	case 0x06:
 		emulate_clts(ctxt->vcpu);
 		c->dst.type = OP_NONE;

@@ -2054,6 +2061,12 @@ twobyte_insn:
 		rc = X86EMUL_CONTINUE;
 		c->dst.type = OP_NONE;
 		break;
+	case 0x34:		/* sysenter */
+		goto cannot_emulate;
+		break;
+	case 0x35:		/* sysexit */
+		goto cannot_emulate;
+		break;
 	case 0x40 ... 0x4f:	/* cmov */
 		c->dst.val = c->dst.orig_val = c->src.val;
 		if (!test_cc(c->b, ctxt->eflags))

index b0da29d..4d7256d 100644
@@ -1397,6 +1397,85 @@ static void toggle_interruptibility(struct x86_emulate_ctxt *ctxt, u32 mask)
 		ctxt->interruptibility = mask;
 }
 
+static inline void
+setup_syscalls_segments(struct x86_emulate_ctxt *ctxt,
+	struct kvm_segment *cs, struct kvm_segment *ss)
+{
+	memset(cs, 0, sizeof(struct kvm_segment));
+	kvm_x86_ops->get_segment(ctxt->vcpu, cs, VCPU_SREG_CS);
+	memset(ss, 0, sizeof(struct kvm_segment));
+
+	cs->l = 0;		/* will be adjusted later */
+	cs->base = 0;		/* flat segment */
+	cs->g = 1;		/* 4kb granularity */
+	cs->limit = 0xffffffff;	/* 4GB limit */
+	cs->type = 0x0b;	/* Read, Execute, Accessed */
+	cs->s = 1;
+	cs->dpl = 0;		/* will be adjusted later */
+	cs->present = 1;
+	cs->db = 1;
+
+	ss->unusable = 0;
+	ss->base = 0;		/* flat segment */
+	ss->limit = 0xffffffff;	/* 4GB limit */
+	ss->g = 1;		/* 4kb granularity */
+	ss->s = 1;
+	ss->type = 0x03;	/* Read/Write, Accessed */
+	ss->db = 1;		/* 32bit stack segment */
+	ss->dpl = 0;
+	ss->present = 1;
+}
+
+static int
+emulate_syscall(struct x86_emulate_ctxt *ctxt)
+{
+	struct decode_cache *c = &ctxt->decode;
+	struct kvm_segment cs, ss;
+	u64 msr_data;
+
+	/* syscall is not available in real mode */
+	if (c->lock_prefix || ctxt->mode == X86EMUL_MODE_REAL
+		|| !(ctxt->vcpu->arch.cr0 & X86_CR0_PE))
+		return -1;
+
+	setup_syscalls_segments(ctxt, &cs, &ss);
+
+	kvm_x86_ops->get_msr(ctxt->vcpu, MSR_STAR, &msr_data);
+	msr_data >>= 32;
+	cs.selector = (u16)(msr_data & 0xfffc);
+	ss.selector = (u16)(msr_data + 8);
+
+	if (is_long_mode(ctxt->vcpu)) {
+		cs.db = 0;
+		cs.l = 1;
+	}
+	kvm_x86_ops->set_segment(ctxt->vcpu, &cs, VCPU_SREG_CS);
+	kvm_x86_ops->set_segment(ctxt->vcpu, &ss, VCPU_SREG_SS);
+
+	c->regs[VCPU_REGS_RCX] = c->eip;
+	if (is_long_mode(ctxt->vcpu)) {
+#ifdef CONFIG_X86_64
+		c->regs[VCPU_REGS_R11] = ctxt->eflags & ~EFLG_RF;
+
+		kvm_x86_ops->get_msr(ctxt->vcpu,
+			ctxt->mode == X86EMUL_MODE_PROT64 ?
+			MSR_LSTAR : MSR_CSTAR, &msr_data);
+		c->eip = msr_data;
+
+		kvm_x86_ops->get_msr(ctxt->vcpu, MSR_SYSCALL_MASK, &msr_data);
+		ctxt->eflags &= ~(msr_data | EFLG_RF);
+#endif
+	} else {
+		/* legacy mode */
+		kvm_x86_ops->get_msr(ctxt->vcpu, MSR_STAR, &msr_data);
+		c->eip = (u32)msr_data;
+
+		ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF);
+	}
+
+	return 0;
+}
+
 int
 x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 {

@@ -1993,7 +2072,10 @@ twobyte_insn:
 		}
 		break;
 	case 0x05: 		/* syscall */
-		goto cannot_emulate;
+		if (emulate_syscall(ctxt) == -1)
+			goto cannot_emulate;
+		else
+			goto writeback;
 		break;
 	case 0x06:
 		emulate_clts(ctxt->vcpu);

index 4d7256d..7a9bddb 100644
@@ -1476,6 +1476,71 @@ emulate_syscall(struct x86_emulate_ctxt *ctxt)
 	return 0;
 }
 
+static int
+emulate_sysenter(struct x86_emulate_ctxt *ctxt)
+{
+	struct decode_cache *c = &ctxt->decode;
+	struct kvm_segment cs, ss;
+	u64 msr_data;
+
+	/* inject #UD if LOCK prefix is used */
+	if (c->lock_prefix)
+		return -1;
+
+	/* inject #GP if in real mode or paging is disabled */
+	if (ctxt->mode == X86EMUL_MODE_REAL ||
+		!(ctxt->vcpu->arch.cr0 & X86_CR0_PE)) {
+		kvm_inject_gp(ctxt->vcpu, 0);
+		return -1;
+	}
+
+	/* XXX sysenter/sysexit have not been tested in 64bit mode.
+	* Therefore, we inject an #UD.
+	*/
+	if (ctxt->mode == X86EMUL_MODE_PROT64)
+		return -1;
+
+	setup_syscalls_segments(ctxt, &cs, &ss);
+
+	kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_CS, &msr_data);
+	switch (ctxt->mode) {
+	case X86EMUL_MODE_PROT32:
+		if ((msr_data & 0xfffc) == 0x0) {
+			kvm_inject_gp(ctxt->vcpu, 0);
+			return -1;
+		}
+		break;
+	case X86EMUL_MODE_PROT64:
+		if (msr_data == 0x0) {
+			kvm_inject_gp(ctxt->vcpu, 0);
+			return -1;
+		}
+		break;
+	}
+
+	ctxt->eflags &= ~(EFLG_VM | EFLG_IF | EFLG_RF);
+	cs.selector = (u16)msr_data;
+	cs.selector &= ~SELECTOR_RPL_MASK;
+	ss.selector = cs.selector + 8;
+	ss.selector &= ~SELECTOR_RPL_MASK;
+	if (ctxt->mode == X86EMUL_MODE_PROT64
+		|| is_long_mode(ctxt->vcpu)) {
+		cs.db = 0;
+		cs.l = 1;
+	}
+
+	kvm_x86_ops->set_segment(ctxt->vcpu, &cs, VCPU_SREG_CS);
+	kvm_x86_ops->set_segment(ctxt->vcpu, &ss, VCPU_SREG_SS);
+
+	kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_EIP, &msr_data);
+	c->eip = msr_data;
+
+	kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_ESP, &msr_data);
+	c->regs[VCPU_REGS_RSP] = msr_data;
+
+	return 0;
+}
+
 int
 x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 {

@@ -2144,7 +2209,10 @@ twobyte_insn:
 		c->dst.type = OP_NONE;
 		break;
 	case 0x34:		/* sysenter */
-		goto cannot_emulate;
+		if (emulate_sysenter(ctxt) == -1)
+			goto cannot_emulate;
+		else
+			goto writeback;
 		break;
 	case 0x35:		/* sysexit */
 		goto cannot_emulate;

index 7a9bddb..c6663d4 100644
@@ -1541,6 +1541,73 @@ emulate_sysenter(struct x86_emulate_ctxt *ctxt)
 	return 0;
 }
 
+static int
+emulate_sysexit(struct x86_emulate_ctxt *ctxt)
+{
+	struct decode_cache *c = &ctxt->decode;
+	struct kvm_segment cs, ss;
+	u64 msr_data;
+	int usermode;
+
+	/* inject #UD if LOCK prefix is used */
+	if (c->lock_prefix)
+		return -1;
+
+	/* inject #GP if in real mode or paging is disabled */
+	if (ctxt->mode == X86EMUL_MODE_REAL
+		|| !(ctxt->vcpu->arch.cr0 & X86_CR0_PE)) {
+		kvm_inject_gp(ctxt->vcpu, 0);
+		return -1;
+	}
+
+	/* sysexit must be called from CPL 0 */
+	if (kvm_x86_ops->get_cpl(ctxt->vcpu) != 0) {
+		kvm_inject_gp(ctxt->vcpu, 0);
+		return -1;
+	}
+
+	setup_syscalls_segments(ctxt, &cs, &ss);
+
+	if ((c->rex_prefix & 0x8) != 0x0)
+		usermode = X86EMUL_MODE_PROT64;
+	else
+		usermode = X86EMUL_MODE_PROT32;
+
+	cs.dpl = 3;
+	ss.dpl = 3;
+	kvm_x86_ops->get_msr(ctxt->vcpu, MSR_IA32_SYSENTER_CS, &msr_data);
+	switch (usermode) {
+	case X86EMUL_MODE_PROT32:
+		cs.selector = (u16)(msr_data + 16);
+		if ((msr_data & 0xfffc) == 0x0) {
+			kvm_inject_gp(ctxt->vcpu, 0);
+			return -1;
+		}
+		ss.selector = (u16)(msr_data + 24);
+		break;
+	case X86EMUL_MODE_PROT64:
+		cs.selector = (u16)(msr_data + 32);
+		if (msr_data == 0x0) {
+			kvm_inject_gp(ctxt->vcpu, 0);
+			return -1;
+		}
+		ss.selector = cs.selector + 8;
+		cs.db = 0;
+		cs.l = 1;
+		break;
+	}
+	cs.selector |= SELECTOR_RPL_MASK;
+	ss.selector |= SELECTOR_RPL_MASK;
+
+	kvm_x86_ops->set_segment(ctxt->vcpu, &cs, VCPU_SREG_CS);
+	kvm_x86_ops->set_segment(ctxt->vcpu, &ss, VCPU_SREG_SS);
+
+	c->eip = ctxt->vcpu->arch.regs[VCPU_REGS_RDX];
+	c->regs[VCPU_REGS_RSP] = ctxt->vcpu->arch.regs[VCPU_REGS_RCX];
+
+	return 0;
+}
+
 int
 x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 {

@@ -2215,7 +2282,10 @@ twobyte_insn:
 			goto writeback;
 		break;
 	case 0x35:		/* sysexit */
-		goto cannot_emulate;
+		if (emulate_sysexit(ctxt) == -1)
+			goto cannot_emulate;
+		else
+			goto writeback;
 		break;
 	case 0x40 ... 0x4f:	/* cmov */
 		c->dst.val = c->dst.orig_val = c->src.val;

index 04bdedd..1da8072 100644
@@ -1199,6 +1199,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		if (old.npages)
 			kvm_arch_flush_shadow(kvm);
 	}
+#else  /* not defined CONFIG_S390 */
+	new.user_alloc = user_alloc;
+	if (user_alloc)
+		new.userspace_addr = mem->userspace_addr;
 #endif /* not defined CONFIG_S390 */
 
 	if (!npages)

index cafdcee..b16d636 100644
@@ -234,6 +234,7 @@ unsigned long vma_kernel_pagesize(struct vm_area_struct *vma)
 
 	return 1UL << (hstate->order + PAGE_SHIFT);
 }
+EXPORT_SYMBOL_GPL(vma_kernel_pagesize);
 
 /*
  * Return the page size being used by the MMU to back a VMA. In the majority

index 9cf1c4b..d9b6325 100644
@@ -235,7 +235,8 @@ struct kvm_vm_data {
 #define KVM_REQ_PTC_G		32
 #define KVM_REQ_RESUME		33
 
-#define KVM_PAGES_PER_HPAGE	1
+#define KVM_NR_PAGE_SIZES	1
+#define KVM_PAGES_PER_HPAGE(x)	1
 
 struct kvm;
 struct kvm_vcpu;

index d4caa61..c9c930e 100644
@@ -34,7 +34,8 @@
 #define KVM_COALESCED_MMIO_PAGE_OFFSET 1
 
 /* We don't currently support large pages. */
-#define KVM_PAGES_PER_HPAGE (1UL << 31)
+#define KVM_NR_PAGE_SIZES	1
+#define KVM_PAGES_PER_HPAGE(x)	(1UL<<31)
 
 struct kvm;
 struct kvm_run;

index 75535d4..78e07a6 100644
@@ -40,7 +40,11 @@ struct sca_block {
 	struct sca_entry cpu[64];
 } __attribute__((packed));
 
-#define KVM_PAGES_PER_HPAGE 256
+#define KVM_NR_PAGE_SIZES 2
+#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + ((x) - 1) * 8)
+#define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x))
+#define KVM_HPAGE_MASK(x)	(~(KVM_HPAGE_SIZE(x) - 1))
+#define KVM_PAGES_PER_HPAGE(x)	(KVM_HPAGE_SIZE(x) / PAGE_SIZE)
 
 #define CPUSTAT_HOST       0x80000000
 #define CPUSTAT_WAIT       0x10000000

index 19027ab..30b625d 100644
@@ -54,12 +54,12 @@
 #define INVALID_PAGE (~(hpa_t)0)
 #define UNMAPPED_GVA (~(gpa_t)0)
 
-/* shadow tables are PAE even on non-PAE hosts */
-#define KVM_HPAGE_SHIFT 21
-#define KVM_HPAGE_SIZE (1UL << KVM_HPAGE_SHIFT)
-#define KVM_HPAGE_MASK (~(KVM_HPAGE_SIZE - 1))
-
-#define KVM_PAGES_PER_HPAGE (KVM_HPAGE_SIZE / PAGE_SIZE)
+/* KVM Hugepage definitions for x86 */
+#define KVM_NR_PAGE_SIZES	2
+#define KVM_HPAGE_SHIFT(x)	(PAGE_SHIFT + (((x) - 1) * 9))
+#define KVM_HPAGE_SIZE(x)	(1UL << KVM_HPAGE_SHIFT(x))
+#define KVM_HPAGE_MASK(x)	(~(KVM_HPAGE_SIZE(x) - 1))
+#define KVM_PAGES_PER_HPAGE(x)	(KVM_HPAGE_SIZE(x) / PAGE_SIZE)
 
 #define DE_VECTOR 0
 #define DB_VECTOR 1

index 12974de..b67585c 100644
@@ -394,9 +394,9 @@ static int *slot_largepage_idx(gfn_t gfn, struct kvm_memory_slot *slot)
 {
 	unsigned long idx;
 
-	idx = (gfn / KVM_PAGES_PER_HPAGE) -
-	      (slot->base_gfn / KVM_PAGES_PER_HPAGE);
-	return &slot->lpage_info[idx].write_count;
+	idx = (gfn / KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL)) -
+	      (slot->base_gfn / KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL));
+	return &slot->lpage_info[0][idx].write_count;
 }
 
 static void account_shadowed(struct kvm *kvm, gfn_t gfn)

@@ -485,10 +485,10 @@ static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, int lpage)
 	if (!lpage)
 		return &slot->rmap[gfn - slot->base_gfn];
 
-	idx = (gfn / KVM_PAGES_PER_HPAGE) -
-	      (slot->base_gfn / KVM_PAGES_PER_HPAGE);
+	idx = (gfn / KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL)) -
+	      (slot->base_gfn / KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL));
 
-	return &slot->lpage_info[idx].rmap_pde;
+	return &slot->lpage_info[0][idx].rmap_pde;
 }
 
 /*

@@ -731,11 +731,11 @@ static int kvm_handle_hva(struct kvm *kvm, unsigned long hva,
 		end = start + (memslot->npages << PAGE_SHIFT);
 		if (hva >= start && hva < end) {
 			gfn_t gfn_offset = (hva - start) >> PAGE_SHIFT;
+			int idx = gfn_offset /
+			          KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL);
 			retval |= handler(kvm, &memslot->rmap[gfn_offset]);
 			retval |= handler(kvm,
-					  &memslot->lpage_info[
-						  gfn_offset /
-						  KVM_PAGES_PER_HPAGE].rmap_pde);
+					&memslot->lpage_info[0][idx].rmap_pde);
 		}
 	}
 

@@ -1876,8 +1876,9 @@ static int nonpaging_map(struct kvm_vcpu *vcpu, gva_t v, int write, gfn_t gfn)
 	pfn_t pfn;
 	unsigned long mmu_seq;
 
-	if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
-		gfn &= ~(KVM_PAGES_PER_HPAGE-1);
+	if (is_largepage_backed(vcpu, gfn &
+			~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1))) {
+		gfn &= ~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1);
 		largepage = 1;
 	}
 

@@ -2082,8 +2083,9 @@ static int tdp_page_fault(struct kvm_vcpu *vcpu, gva_t gpa,
 	if (r)
 		return r;
 
-	if (is_largepage_backed(vcpu, gfn & ~(KVM_PAGES_PER_HPAGE-1))) {
-		gfn &= ~(KVM_PAGES_PER_HPAGE-1);
+	if (is_largepage_backed(vcpu, gfn &
+			~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1))) {
+		gfn &= ~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1);
 		largepage = 1;
 	}
 	mmu_seq = vcpu->kvm->mmu_notifier_seq;

@@ -2485,7 +2487,7 @@ static void mmu_guess_page_from_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	gfn = (gpte & PT64_BASE_ADDR_MASK) >> PAGE_SHIFT;
 
 	if (is_large_pte(gpte) && is_largepage_backed(vcpu, gfn)) {
-		gfn &= ~(KVM_PAGES_PER_HPAGE-1);
+		gfn &= ~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1);
 		vcpu->arch.update_pte.largepage = 1;
 	}
 	vcpu->arch.update_pte.mmu_seq = vcpu->kvm->mmu_notifier_seq;

index 322e811..53e129c 100644
@@ -401,7 +401,8 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, gva_t addr,
 
 	if (walker.level == PT_DIRECTORY_LEVEL) {
 		gfn_t large_gfn;
-		large_gfn = walker.gfn & ~(KVM_PAGES_PER_HPAGE-1);
+		large_gfn = walker.gfn &
+			~(KVM_PAGES_PER_HPAGE(PT_DIRECTORY_LEVEL) - 1);
 		if (is_largepage_backed(vcpu, large_gfn)) {
 			walker.gfn = large_gfn;
 			largepage = 1;

index 6988858..06af936 100644
@@ -103,7 +103,7 @@ struct kvm_memory_slot {
 	struct {
 		unsigned long rmap_pde;
 		int write_count;
-	} *lpage_info;
+	} *lpage_info[KVM_NR_PAGE_SIZES - 1];
 	unsigned long userspace_addr;
 	int user_alloc;
 };

98 lines not on this page · raw message

index 15fc95b..bcd00c7 100644
@@ -345,9 +345,7 @@ static void pit_load_count(struct kvm *kvm, int channel, u32 val)
 
 void kvm_pit_load_count(struct kvm *kvm, int channel, u32 val)
 {
-	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	pit_load_count(kvm, channel, val);
-	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 }
 
 static inline struct kvm_pit *dev_to_pit(struct kvm_io_device *dev)

index 57e76b3..e9b0982 100644
@@ -1987,19 +1987,25 @@ static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
 	r = 0;
 	switch (chip->chip_id) {
 	case KVM_IRQCHIP_PIC_MASTER:
+		spin_lock(&pic_irqchip(kvm)->lock);
 		memcpy(&pic_irqchip(kvm)->pics[0],
 			&chip->chip.pic,
 			sizeof(struct kvm_pic_state));
+		spin_unlock(&pic_irqchip(kvm)->lock);
 		break;
 	case KVM_IRQCHIP_PIC_SLAVE:
+		spin_lock(&pic_irqchip(kvm)->lock);
 		memcpy(&pic_irqchip(kvm)->pics[1],
 			&chip->chip.pic,
 			sizeof(struct kvm_pic_state));
+		spin_unlock(&pic_irqchip(kvm)->lock);
 		break;
 	case KVM_IRQCHIP_IOAPIC:
+		mutex_lock(&kvm->irq_lock);
 		memcpy(ioapic_irqchip(kvm),
 			&chip->chip.ioapic,
 			sizeof(struct kvm_ioapic_state));
+		mutex_unlock(&kvm->irq_lock);
 		break;
 	default:
 		r = -EINVAL;

@@ -2013,7 +2019,9 @@ static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 {
 	int r = 0;
 
+	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	memcpy(ps, &kvm->arch.vpit->pit_state, sizeof(struct kvm_pit_state));
+	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	return r;
 }
 

@@ -2021,8 +2029,10 @@ static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
 {
 	int r = 0;
 
+	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	memcpy(&kvm->arch.vpit->pit_state, ps, sizeof(struct kvm_pit_state));
 	kvm_pit_load_count(kvm, 0, ps->channels[0].count);
+	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	return r;
 }
 

@@ -2031,7 +2041,9 @@ static int kvm_vm_ioctl_reinject(struct kvm *kvm,
 {
 	if (!kvm->arch.vpit)
 		return -ENXIO;
+	mutex_lock(&kvm->arch.vpit->pit_state.lock);
 	kvm->arch.vpit->pit_state.pit_timer.reinject = control->pit_reinject;
+	mutex_unlock(&kvm->arch.vpit->pit_state.lock);
 	return 0;
 }
 

index 8361662..f1e2e8c 100644
@@ -2274,10 +2274,12 @@ static long kvm_vm_ioctl(struct file *filp,
 #ifdef CONFIG_KVM_APIC_ARCHITECTURE
 	case KVM_SET_BOOT_CPU_ID:
 		r = 0;
+		mutex_lock(&kvm->lock);
 		if (atomic_read(&kvm->online_vcpus) != 0)
 			r = -EBUSY;
 		else
 			kvm->bsp_vcpu_id = arg;
+		mutex_unlock(&kvm->lock);
 		break;
 #endif
 	default:

index 081d00a..d664157 100644
@@ -2138,7 +2138,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, unsigned ecx, u64 data)
 		break;
 	case MSR_VM_CR:
 	case MSR_VM_IGNNE:
-	case MSR_K7_HWCR:
 		pr_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
 		break;
 	default:

index e9b0982..cae5b12 100644
@@ -833,6 +833,14 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	case MSR_EFER:
 		set_efer(vcpu, data);
 		break;
+	case MSR_K7_HWCR:
+		data &= ~(u64)0x40;	/* ignore flush filter disable */
+		if (data != 0) {
+			pr_unimpl(vcpu, "unimplemented HWCR wrmsr: 0x%llx\n",
+				data);
+			return 1;
+		}
+		break;
 	case MSR_IA32_DEBUGCTLMSR:
 		if (!data) {
 			/* We support the non-activated case already */

index cae5b12..6aace61 100644
@@ -1038,6 +1038,7 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_P6_EVNTSEL0:
 	case MSR_P6_EVNTSEL1:
 	case MSR_K7_EVNTSEL0:
+	case MSR_K8_INT_PENDING_MSG:
 		data = 0;
 		break;
 	case MSR_MTRRcap:

index 6aace61..0be75d5 100644
@@ -83,6 +83,9 @@ struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
 struct kvm_x86_ops *kvm_x86_ops;
 EXPORT_SYMBOL_GPL(kvm_x86_ops);
 
+int ignore_msrs = 0;
+module_param_named(ignore_msrs, ignore_msrs, bool, S_IRUGO | S_IWUSR);
+
 struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "pf_fixed", VCPU_STAT(pf_fixed) },
 	{ "pf_guest", VCPU_STAT(pf_guest) },

@@ -930,8 +933,15 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 			"0x%x data 0x%llx\n", msr, data);
 		break;
 	default:
-		pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n", msr, data);
-		return 1;
+		if (!ignore_msrs) {
+			pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n",
+				msr, data);
+			return 1;
+		} else {
+			pr_unimpl(vcpu, "ignored wrmsr: 0x%x data %llx\n",
+				msr, data);
+			break;
+		}
 	}
 	return 0;
 }

@@ -1078,8 +1088,14 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata)
 	case MSR_IA32_MC0_CTL ... MSR_IA32_MC0_CTL + 4 * KVM_MAX_MCE_BANKS - 1:
 		return get_msr_mce(vcpu, msr, pdata);
 	default:
-		pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
-		return 1;
+		if (!ignore_msrs) {
+			pr_unimpl(vcpu, "unhandled rdmsr: 0x%x\n", msr);
+			return 1;
+		} else {
+			pr_unimpl(vcpu, "ignored rdmsr: 0x%x\n", msr);
+			data = 0;
+		}
+		break;
 	}
 	*pdata = data;
 	return 0;

index 4a16f47..ff3cb63 100644
@@ -30,6 +30,7 @@
 #include "timing.h"
 
 #include "44x_tlb.h"
+#include "trace.h"
 
 #ifndef PPC44x_TLBE_SIZE
 #define PPC44x_TLBE_SIZE	PPC44x_TLB_4K

@@ -263,7 +264,7 @@ static void kvmppc_44x_shadow_release(struct kvmppc_vcpu_44x *vcpu_44x,
 
 	/* XXX set tlb_44x_index to stlb_index? */
 
-	KVMTRACE_1D(STLB_INVAL, &vcpu_44x->vcpu, stlb_index, handler);
+	trace_kvm_stlb_inval(stlb_index);
 }
 
 void kvmppc_mmu_destroy(struct kvm_vcpu *vcpu)

@@ -365,8 +366,8 @@ void kvmppc_mmu_map(struct kvm_vcpu *vcpu, u64 gvaddr, gpa_t gpaddr,
 	/* Insert shadow mapping into hardware TLB. */
 	kvmppc_44x_tlbe_set_modified(vcpu_44x, victim);
 	kvmppc_44x_tlbwe(victim, &stlbe);
-	KVMTRACE_5D(STLB_WRITE, vcpu, victim, stlbe.tid, stlbe.word0, stlbe.word1,
-	            stlbe.word2, handler);
+	trace_kvm_stlb_write(victim, stlbe.tid, stlbe.word0, stlbe.word1,
+			     stlbe.word2);
 }
 
 /* For a particular guest TLB entry, invalidate the corresponding host TLB

@@ -485,8 +486,8 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 		kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
 	}
 
-	KVMTRACE_5D(GTLB_WRITE, vcpu, gtlb_index, tlbe->tid, tlbe->word0,
-	            tlbe->word1, tlbe->word2, handler);
+	trace_kvm_gtlb_write(gtlb_index, tlbe->tid, tlbe->word0, tlbe->word1,
+			     tlbe->word2);
 
 	kvmppc_set_exit_type(vcpu, EMULATED_TLBWE_EXITS);
 	return EMULATE_DONE;

index a2048ac..fb1e1dc 100644
@@ -22,6 +22,7 @@
 
 #include "../mm/mmu_decl.h"
 #include "e500_tlb.h"
+#include "trace.h"
 
 #define to_htlb1_esel(esel) (tlb1_entry_num - (esel) - 1)
 

@@ -224,9 +225,8 @@ static void kvmppc_e500_stlbe_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,
 
 	kvmppc_e500_shadow_release(vcpu_e500, tlbsel, esel);
 	stlbe->mas1 = 0;
-	KVMTRACE_5D(STLB_INVAL, &vcpu_e500->vcpu, index_of(tlbsel, esel),
-			stlbe->mas1, stlbe->mas2, stlbe->mas3, stlbe->mas7,
-			handler);
+	trace_kvm_stlb_inval(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
+			     stlbe->mas3, stlbe->mas7);
 }
 
 static void kvmppc_e500_tlb1_invalidate(struct kvmppc_vcpu_e500 *vcpu_e500,

@@ -319,9 +319,8 @@ static inline void kvmppc_e500_shadow_map(struct kvmppc_vcpu_e500 *vcpu_e500,
 				vcpu_e500->vcpu.arch.msr & MSR_PR);
 	stlbe->mas7 = (hpaddr >> 32) & MAS7_RPN;
 
-	KVMTRACE_5D(STLB_WRITE, &vcpu_e500->vcpu, index_of(tlbsel, esel),
-			stlbe->mas1, stlbe->mas2, stlbe->mas3, stlbe->mas7,
-			handler);
+	trace_kvm_stlb_write(index_of(tlbsel, esel), stlbe->mas1, stlbe->mas2,
+			     stlbe->mas3, stlbe->mas7);
 }
 
 /* XXX only map the one-one case, for now use TLB0 */

@@ -535,9 +534,8 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 	gtlbe->mas3 = vcpu_e500->mas3;
 	gtlbe->mas7 = vcpu_e500->mas7;
 
-	KVMTRACE_5D(GTLB_WRITE, vcpu, vcpu_e500->mas0,
-			gtlbe->mas1, gtlbe->mas2, gtlbe->mas3, gtlbe->mas7,
-			handler);
+	trace_kvm_gtlb_write(vcpu_e500->mas0, gtlbe->mas1, gtlbe->mas2,
+			     gtlbe->mas3, gtlbe->mas7);
 
 	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
 	if (tlbe_is_host_safe(vcpu, gtlbe)) {

index 28a8237..7737146 100644
@@ -29,6 +29,7 @@
 #include <asm/kvm_ppc.h>
 #include <asm/disassemble.h>
 #include "timing.h"
+#include "trace.h"
 
 #define OP_TRAP 3
 

@@ -419,7 +420,7 @@ int kvmppc_emulate_instruction(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		}
 	}
 
-	KVMTRACE_3D(PPC_INSTR, vcpu, inst, (int)vcpu->arch.pc, emulated, entryexit);
+	trace_kvm_ppc_instr(inst, vcpu->arch.pc, emulated);
 
 	if (advance)
 		vcpu->arch.pc += 4; /* Advance past emulated instruction. */

index 7ad30e0..0341391 100644
@@ -31,6 +31,9 @@
 #include "timing.h"
 #include "../mm/mmu_decl.h"
 
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
 gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
 {
 	return gfn;

104 lines not on this page · raw message

index 6710518..76c6408 100644
@@ -14,7 +14,7 @@
 
 #define KVM_API_VERSION 12
 
-/* for KVM_TRACE_ENABLE */
+/* for KVM_TRACE_ENABLE, deprecated */
 struct kvm_user_trace_setup {
 	__u32 buf_size; /* sub_buffer size of each per-cpu */
 	__u32 buf_nr; /* the number of sub_buffers of each per-cpu */

@@ -325,35 +325,6 @@ struct kvm_guest_debug {
 #define KVM_TRC_CYCLE_SIZE      8
 #define KVM_TRC_EXTRA_MAX       7
 
-/* This structure represents a single trace buffer record. */
-struct kvm_trace_rec {
-	/* variable rec_val
-	 * is split into:
-	 * bits 0 - 27  -> event id
-	 * bits 28 -30  -> number of extra data args of size u32
-	 * bits 31      -> binary indicator for if tsc is in record
-	 */
-	__u32 rec_val;
-	__u32 pid;
-	__u32 vcpu_id;
-	union {
-		struct {
-			__u64 timestamp;
-			__u32 extra_u32[KVM_TRC_EXTRA_MAX];
-		} __attribute__((packed)) timestamp;
-		struct {
-			__u32 extra_u32[KVM_TRC_EXTRA_MAX];
-		} notimestamp;
-	} u;
-};
-
-#define TRACE_REC_EVENT_ID(val) \
-		(0x0fffffff & (val))
-#define TRACE_REC_NUM_DATA_ARGS(val) \
-		(0x70000000 & ((val) << 28))
-#define TRACE_REC_TCS(val) \
-		(0x80000000 & ((val) << 31))
-
 #define KVMIO 0xAE
 
 /*

index 06af936..0604d56 100644
@@ -482,37 +482,6 @@ struct kvm_stats_debugfs_item {
 extern struct kvm_stats_debugfs_item debugfs_entries[];
 extern struct dentry *kvm_debugfs_dir;
 
-#define KVMTRACE_5D(evt, vcpu, d1, d2, d3, d4, d5, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 5, d1, d2, d3, d4, d5)
-#define KVMTRACE_4D(evt, vcpu, d1, d2, d3, d4, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 4, d1, d2, d3, d4, 0)
-#define KVMTRACE_3D(evt, vcpu, d1, d2, d3, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 3, d1, d2, d3, 0, 0)
-#define KVMTRACE_2D(evt, vcpu, d1, d2, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 2, d1, d2, 0, 0, 0)
-#define KVMTRACE_1D(evt, vcpu, d1, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 1, d1, 0, 0, 0, 0)
-#define KVMTRACE_0D(evt, vcpu, name) \
-	trace_mark(kvm_trace_##name, "%u %p %u %u %u %u %u %u", KVM_TRC_##evt, \
-						vcpu, 0, 0, 0, 0, 0, 0)
-
-#ifdef CONFIG_KVM_TRACE
-int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg);
-void kvm_trace_cleanup(void);
-#else
-static inline
-int kvm_trace_ioctl(unsigned int ioctl, unsigned long arg)
-{
-	return -EINVAL;
-}
-#define kvm_trace_cleanup() ((void)0)
-#endif
-
 #ifdef KVM_ARCH_WANT_MMU_NOTIFIER
 static inline int mmu_notifier_retry(struct kvm_vcpu *vcpu, unsigned long mmu_seq)
 {

index f1e2e8c..bbb4029 100644
@@ -2398,7 +2398,7 @@ static long kvm_dev_ioctl(struct file *filp,
 	case KVM_TRACE_ENABLE:
 	case KVM_TRACE_PAUSE:
 	case KVM_TRACE_DISABLE:
-		r = kvm_trace_ioctl(ioctl, arg);
+		r = -EOPNOTSUPP;
 		break;
 	default:
 		return kvm_arch_dev_ioctl(filp, ioctl, arg);

@@ -2748,7 +2748,6 @@ EXPORT_SYMBOL_GPL(kvm_init);
 
 void kvm_exit(void)
 {
-	kvm_trace_cleanup();
 	tracepoint_synchronize_unregister();
 	misc_deregister(&kvm_dev);
 	kmem_cache_destroy(kvm_vcpu_cache);

285 lines not on this page · raw message

index 0604d56..4ea42c9 100644
@@ -538,7 +538,7 @@ static inline void kvm_irqfd_release(struct kvm *kvm) {}
 #ifdef CONFIG_KVM_APIC_ARCHITECTURE
 static inline bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
 {
-	return vcpu->kvm->bsp_vcpu == vcpu;
+	return vcpu->kvm->bsp_vcpu_id == vcpu->vcpu_id;
 }
 #endif
 #endif

index 2c67f5a..06e38b2 100644
@@ -20,6 +20,9 @@
 
 struct kvm_io_device;
 
+/**
+ * kvm_io_device_ops are called under kvm slots_lock.
+ **/
 struct kvm_io_device_ops {
 	void (*read)(struct kvm_io_device *this,
 		     gpa_t addr,

index 397f419..b40946c 100644
@@ -115,16 +115,16 @@ int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
 	if (dev == NULL)
 		return -EINVAL;
 
-	mutex_lock(&kvm->lock);
+	down_write(&kvm->slots_lock);
 	if (dev->nb_zones >= KVM_COALESCED_MMIO_ZONE_MAX) {
-		mutex_unlock(&kvm->lock);
+		up_write(&kvm->slots_lock);
 		return -ENOBUFS;
 	}
 
 	dev->zone[dev->nb_zones] = *zone;
 	dev->nb_zones++;
 
-	mutex_unlock(&kvm->lock);
+	up_write(&kvm->slots_lock);
 	return 0;
 }
 

@@ -138,7 +138,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
 	if (dev == NULL)
 		return -EINVAL;
 
-	mutex_lock(&kvm->lock);
+	down_write(&kvm->slots_lock);
 
 	i = dev->nb_zones;
 	while(i) {

@@ -156,7 +156,7 @@ int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
 		i--;
 	}
 
-	mutex_unlock(&kvm->lock);
+	up_write(&kvm->slots_lock);
 
 	return 0;
 }

index 0be75d5..7ce6367 100644
@@ -2188,7 +2188,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 				   sizeof(struct kvm_pit_config)))
 			goto out;
 	create_pit:
-		mutex_lock(&kvm->lock);
+		down_write(&kvm->slots_lock);
 		r = -EEXIST;
 		if (kvm->arch.vpit)
 			goto create_pit_unlock;

@@ -2197,7 +2197,7 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		if (kvm->arch.vpit)
 			r = 0;
 	create_pit_unlock:
-		mutex_unlock(&kvm->lock);
+		up_write(&kvm->slots_lock);
 		break;
 	case KVM_IRQ_LINE_STATUS:
 	case KVM_IRQ_LINE: {

index bcd00c7..4082cdd 100644
@@ -583,6 +583,7 @@ static const struct kvm_io_device_ops speaker_dev_ops = {
 	.in_range = speaker_in_range,
 };
 
+/* Caller must have writers lock on slots_lock */
 struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 {
 	struct kvm_pit *pit;

@@ -621,11 +622,11 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 	kvm_register_irq_mask_notifier(kvm, 0, &pit->mask_notifier);
 
 	kvm_iodevice_init(&pit->dev, &pit_dev_ops);
-	kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev);
+	__kvm_io_bus_register_dev(&kvm->pio_bus, &pit->dev);
 
 	if (flags & KVM_PIT_SPEAKER_DUMMY) {
 		kvm_iodevice_init(&pit->speaker_dev, &speaker_dev_ops);
-		kvm_io_bus_register_dev(&kvm->pio_bus, &pit->speaker_dev);
+		__kvm_io_bus_register_dev(&kvm->pio_bus, &pit->speaker_dev);
 	}
 
 	return pit;

index 148c52a..1851aec 100644
@@ -548,6 +548,6 @@ struct kvm_pic *kvm_create_pic(struct kvm *kvm)
 	 * Initialize PIO device
 	 */
 	kvm_iodevice_init(&s->dev, &picdev_ops);
-	kvm_io_bus_register_dev(&kvm->pio_bus, &s->dev);
+	kvm_io_bus_register_dev(kvm, &kvm->pio_bus, &s->dev);
 	return s;
 }

index 4ea42c9..96c8c0b 100644
@@ -42,6 +42,7 @@
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID	0
 
+struct kvm;
 struct kvm_vcpu;
 extern struct kmem_cache *kvm_vcpu_cache;
 

@@ -61,7 +62,9 @@ void kvm_io_bus_init(struct kvm_io_bus *bus);
 void kvm_io_bus_destroy(struct kvm_io_bus *bus);
 struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus,
 					  gpa_t addr, int len, int is_write);
-void kvm_io_bus_register_dev(struct kvm_io_bus *bus,
+void __kvm_io_bus_register_dev(struct kvm_io_bus *bus,
+			       struct kvm_io_device *dev);
+void kvm_io_bus_register_dev(struct kvm *kvm, struct kvm_io_bus *bus,
 			     struct kvm_io_device *dev);
 
 struct kvm_vcpu {

index b40946c..7b7cc9f 100644
@@ -102,7 +102,7 @@ int kvm_coalesced_mmio_init(struct kvm *kvm)
 	kvm_iodevice_init(&dev->dev, &coalesced_mmio_ops);
 	dev->kvm = kvm;
 	kvm->coalesced_mmio_dev = dev;
-	kvm_io_bus_register_dev(&kvm->mmio_bus, &dev->dev);
+	kvm_io_bus_register_dev(kvm, &kvm->mmio_bus, &dev->dev);
 
 	return 0;
 }

index 0532fa6..0eca54e 100644
@@ -343,7 +343,7 @@ int kvm_ioapic_init(struct kvm *kvm)
 	kvm_ioapic_reset(ioapic);
 	kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
 	ioapic->kvm = kvm;
-	kvm_io_bus_register_dev(&kvm->mmio_bus, &ioapic->dev);
+	kvm_io_bus_register_dev(kvm, &kvm->mmio_bus, &ioapic->dev);
 	return 0;
 }
 

index bbb4029..0edc366 100644
@@ -2527,7 +2527,17 @@ struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus,
 	return NULL;
 }
 
-void kvm_io_bus_register_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev)
+void kvm_io_bus_register_dev(struct kvm *kvm, struct kvm_io_bus *bus,
+			     struct kvm_io_device *dev)
+{
+	down_write(&kvm->slots_lock);
+	__kvm_io_bus_register_dev(bus, dev);
+	up_write(&kvm->slots_lock);
+}
+
+/* An unlocked version. Caller must have write lock on slots_lock. */
+void __kvm_io_bus_register_dev(struct kvm_io_bus *bus,
+			     struct kvm_io_device *dev)
 {
 	BUG_ON(bus->dev_count > (NR_IOBUS_DEVS-1));
 

index 5c766bd..d7aa6bb 100644
@@ -210,16 +210,6 @@ int kvm_dev_ioctl_check_extension(long ext)
 
 }
 
-static struct kvm_io_device *vcpu_find_mmio_dev(struct kvm_vcpu *vcpu,
-					gpa_t addr, int len, int is_write)
-{
-	struct kvm_io_device *dev;
-
-	dev = kvm_io_bus_find_dev(&vcpu->kvm->mmio_bus, addr, len, is_write);
-
-	return dev;
-}
-
 static int handle_vm_error(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	kvm_run->exit_reason = KVM_EXIT_UNKNOWN;

@@ -231,6 +221,7 @@ static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 {
 	struct kvm_mmio_req *p;
 	struct kvm_io_device *mmio_dev;
+	int r;
 
 	p = kvm_get_vcpu_ioreq(vcpu);
 

@@ -247,16 +238,13 @@ static int handle_mmio(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
 	kvm_run->exit_reason = KVM_EXIT_MMIO;
 	return 0;
 mmio:
-	mmio_dev = vcpu_find_mmio_dev(vcpu, p->addr, p->size, !p->dir);
-	if (mmio_dev) {
-		if (!p->dir)
-			kvm_iodevice_write(mmio_dev, p->addr, p->size,
-						&p->data);
-		else
-			kvm_iodevice_read(mmio_dev, p->addr, p->size,
-						&p->data);
-
-	} else
+	if (p->dir)
+		r = kvm_io_bus_read(&vcpu->kvm->mmio_bus, p->addr,
+				    p->size, &p->data);
+	else
+		r = kvm_io_bus_write(&vcpu->kvm->mmio_bus, p->addr,
+				     p->size, &p->data);
+	if (r)
 		printk(KERN_ERR"kvm: No iodevice found! addr:%lx\n", p->addr);
 	p->state = STATE_IORESP_READY;
 

118 lines not on this page · raw message

index 1851aec..1d1bb75 100644
@@ -430,8 +430,7 @@ static u32 elcr_ioport_read(void *opaque, u32 addr1)
 	return s->elcr;
 }
 
-static int picdev_in_range(struct kvm_io_device *this, gpa_t addr,
-			   int len, int is_write)
+static int picdev_in_range(gpa_t addr)
 {
 	switch (addr) {
 	case 0x20:

@@ -451,16 +450,18 @@ static inline struct kvm_pic *to_pic(struct kvm_io_device *dev)
 	return container_of(dev, struct kvm_pic, dev);
 }
 
-static void picdev_write(struct kvm_io_device *this,
+static int picdev_write(struct kvm_io_device *this,
 			 gpa_t addr, int len, const void *val)
 {
 	struct kvm_pic *s = to_pic(this);
 	unsigned char data = *(unsigned char *)val;
+	if (!picdev_in_range(addr))
+		return -EOPNOTSUPP;
 
 	if (len != 1) {
 		if (printk_ratelimit())
 			printk(KERN_ERR "PIC: non byte write\n");
-		return;
+		return 0;
 	}
 	pic_lock(s);
 	switch (addr) {

@@ -476,18 +477,21 @@ static void picdev_write(struct kvm_io_device *this,
 		break;
 	}
 	pic_unlock(s);
+	return 0;
 }
 
-static void picdev_read(struct kvm_io_device *this,
-			gpa_t addr, int len, void *val)
+static int picdev_read(struct kvm_io_device *this,
+		       gpa_t addr, int len, void *val)
 {
 	struct kvm_pic *s = to_pic(this);
 	unsigned char data = 0;
+	if (!picdev_in_range(addr))
+		return -EOPNOTSUPP;
 
 	if (len != 1) {
 		if (printk_ratelimit())
 			printk(KERN_ERR "PIC: non byte read\n");
-		return;
+		return 0;
 	}
 	pic_lock(s);
 	switch (addr) {

@@ -504,6 +508,7 @@ static void picdev_read(struct kvm_io_device *this,
 	}
 	*(unsigned char *)val = data;
 	pic_unlock(s);
+	return 0;
 }
 
 /*

@@ -526,7 +531,6 @@ static void pic_irq_request(void *opaque, int level)
 static const struct kvm_io_device_ops picdev_ops = {
 	.read     = picdev_read,
 	.write    = picdev_write,
-	.in_range = picdev_in_range,
 };
 
 struct kvm_pic *kvm_create_pic(struct kvm *kvm)

100 lines not on this page · raw message

201 lines not on this page · raw message

index 96c8c0b..077e8bb 100644
@@ -60,8 +60,10 @@ struct kvm_io_bus {
 
 void kvm_io_bus_init(struct kvm_io_bus *bus);
 void kvm_io_bus_destroy(struct kvm_io_bus *bus);
-struct kvm_io_device *kvm_io_bus_find_dev(struct kvm_io_bus *bus,
-					  gpa_t addr, int len, int is_write);
+int kvm_io_bus_write(struct kvm_io_bus *bus, gpa_t addr, int len,
+		     const void *val);
+int kvm_io_bus_read(struct kvm_io_bus *bus, gpa_t addr, int len,
+		    void *val);
 void __kvm_io_bus_register_dev(struct kvm_io_bus *bus,
 			       struct kvm_io_device *dev);
 void kvm_io_bus_register_dev(struct kvm *kvm, struct kvm_io_bus *bus,

index 7b7cc9f..0352f81 100644
@@ -19,18 +19,14 @@ static inline struct kvm_coalesced_mmio_dev *to_mmio(struct kvm_io_device *dev)
 	return container_of(dev, struct kvm_coalesced_mmio_dev, dev);
 }
 
-static int coalesced_mmio_in_range(struct kvm_io_device *this,
-				   gpa_t addr, int len, int is_write)
+static int coalesced_mmio_in_range(struct kvm_coalesced_mmio_dev *dev,
+				   gpa_t addr, int len)
 {
-	struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
 	struct kvm_coalesced_mmio_zone *zone;
 	struct kvm_coalesced_mmio_ring *ring;
 	unsigned avail;
 	int i;
 
-	if (!is_write)
-		return 0;
-
 	/* Are we able to batch it ? */
 
 	/* last is the first free entry

@@ -60,11 +56,13 @@ static int coalesced_mmio_in_range(struct kvm_io_device *this,
 	return 0;
 }
 
-static void coalesced_mmio_write(struct kvm_io_device *this,
-				 gpa_t addr, int len, const void *val)
+static int coalesced_mmio_write(struct kvm_io_device *this,
+				gpa_t addr, int len, const void *val)
 {
 	struct kvm_coalesced_mmio_dev *dev = to_mmio(this);
 	struct kvm_coalesced_mmio_ring *ring = dev->kvm->coalesced_mmio_ring;
+	if (!coalesced_mmio_in_range(dev, addr, len))
+		return -EOPNOTSUPP;
 
 	spin_lock(&dev->lock);
 

@@ -76,6 +74,7 @@ static void coalesced_mmio_write(struct kvm_io_device *this,
 	smp_wmb();
 	ring->last = (ring->last + 1) % KVM_COALESCED_MMIO_MAX;
 	spin_unlock(&dev->lock);
+	return 0;
 }
 
 static void coalesced_mmio_destructor(struct kvm_io_device *this)