Merge branch 'kvm-master' into HEAD

x86:
* Use SRCU to protect zap in __kvm_set_or_clear_apicv_inhibit()

* Make argument order consistent for kvcalloc()

* Userspace API fixes for DEBUGCTL and LBRs

Author: bonzini

arch/x86/kvm/cpuid.c

@@ -1338,7 +1338,7 @@ int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
 	if (sanity_check_entries(entries, cpuid->nent, type))
 		return -EINVAL;
 
-	array.entries = kvcalloc(sizeof(struct kvm_cpuid_entry2), cpuid->nent, GFP_KERNEL);
+	array.entries = kvcalloc(cpuid->nent, sizeof(struct kvm_cpuid_entry2), GFP_KERNEL);
 	if (!array.entries)
 		return -ENOMEM;
 

arch/x86/kvm/vmx/capabilities.h

@@ -24,8 +24,6 @@ extern int __read_mostly pt_mode;
 #define PMU_CAP_FW_WRITES	(1ULL << 13)
 #define PMU_CAP_LBR_FMT		0x3f
 
-#define DEBUGCTLMSR_LBR_MASK		(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI)
-
 struct nested_vmx_msrs {
 	/*
 	 * We only store the "true" versions of the VMX capability MSRs. We
@@ -400,6 +398,7 @@ static inline bool vmx_pebs_supported(void)
 static inline u64 vmx_get_perf_capabilities(void)
 {
 	u64 perf_cap = PMU_CAP_FW_WRITES;
+	struct x86_pmu_lbr lbr;
 	u64 host_perf_cap = 0;
 
 	if (!enable_pmu)
@@ -408,7 +407,8 @@ static inline u64 vmx_get_perf_capabilities(void)
 	if (boot_cpu_has(X86_FEATURE_PDCM))
 		rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
 
-	perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
+	if (x86_perf_get_lbr(&lbr) >= 0 && lbr.nr)
+		perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
 
 	if (vmx_pebs_supported()) {
 		perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK;
@@ -419,19 +419,6 @@ static inline u64 vmx_get_perf_capabilities(void)
 	return perf_cap;
 }
 
-static inline u64 vmx_supported_debugctl(void)
-{
-	u64 debugctl = 0;
-
-	if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT))
-		debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT;
-
-	if (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT)
-		debugctl |= DEBUGCTLMSR_LBR_MASK;
-
-	return debugctl;
-}
-
 static inline bool cpu_has_notify_vmexit(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &

arch/x86/kvm/vmx/vmx.c

@@ -2021,15 +2021,17 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu,
 	return (unsigned long)data;
 }
 
-static u64 vcpu_supported_debugctl(struct kvm_vcpu *vcpu)
+static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
 {
-	u64 debugctl = vmx_supported_debugctl();
+	u64 debugctl = 0;
 
-	if (!intel_pmu_lbr_is_enabled(vcpu))
-		debugctl &= ~DEBUGCTLMSR_LBR_MASK;
+	if (boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT) &&
+	    (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)))
+		debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT;
 
-	if (!guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT))
-		debugctl &= ~DEBUGCTLMSR_BUS_LOCK_DETECT;
+	if ((vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) &&
+	    (host_initiated || intel_pmu_lbr_is_enabled(vcpu)))
+		debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
 
 	return debugctl;
 }
@@ -2103,7 +2105,9 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vmcs_writel(GUEST_SYSENTER_ESP, data);
 		break;
 	case MSR_IA32_DEBUGCTLMSR: {
-		u64 invalid = data & ~vcpu_supported_debugctl(vcpu);
+		u64 invalid;
+
+		invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated);
 		if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) {
 			if (report_ignored_msrs)
 				vcpu_unimpl(vcpu, "%s: BTF|LBR in IA32_DEBUGCTLMSR 0x%llx, nop\n",

arch/x86/kvm/x86.c

@@ -10404,7 +10404,10 @@ void __kvm_set_or_clear_apicv_inhibit(struct kvm *kvm,
 		kvm->arch.apicv_inhibit_reasons = new;
 		if (new) {
 			unsigned long gfn = gpa_to_gfn(APIC_DEFAULT_PHYS_BASE);
+			int idx = srcu_read_lock(&kvm->srcu);
+
 			kvm_zap_gfn_range(kvm, gfn, gfn+1);
+			srcu_read_unlock(&kvm->srcu, idx);
 		}
 	} else {
 		kvm->arch.apicv_inhibit_reasons = new;