Merge v6.1.29linux-rolling-lts

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

5 files changed, 56 insertions, 34 deletions

diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 07254314f3dd..cd2ac9536c99 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -395,30 +395,6 @@ static inline bool vmx_pebs_supported(void)
 	return boot_cpu_has(X86_FEATURE_PEBS) && kvm_pmu_cap.pebs_ept;
 }
 
-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)
-		return 0;
-
-	if (boot_cpu_has(X86_FEATURE_PDCM))
-		rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
-
-	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;
-		if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4)
-			perf_cap &= ~PERF_CAP_PEBS_BASELINE;
-	}
-
-	return perf_cap;
-}
-
 static inline bool cpu_has_notify_vmexit(void)
 {
 	return vmcs_config.cpu_based_2nd_exec_ctrl &
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 8e56ec6e72e9..9d683b6067c7 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -4460,7 +4460,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	 * CR0_GUEST_HOST_MASK is already set in the original vmcs01
 	 * (KVM doesn't change it);
 	 */
-	vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS;
+	vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits();
 	vmx_set_cr0(vcpu, vmcs12->host_cr0);
 
 	/* Same as above - no reason to call set_cr4_guest_host_mask().  */
@@ -4611,7 +4611,7 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
 	 */
 	vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx));
 
-	vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS;
+	vcpu->arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits();
 	vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW));
 
 	vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 10b33da9bd05..9fabfe71fd87 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -631,7 +631,7 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
 		pmu->fixed_counters[i].current_config = 0;
 	}
 
-	vcpu->arch.perf_capabilities = vmx_get_perf_capabilities();
+	vcpu->arch.perf_capabilities = kvm_caps.supported_perf_cap;
 	lbr_desc->records.nr = 0;
 	lbr_desc->event = NULL;
 	lbr_desc->msr_passthrough = false;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 4c9116d223df..07aab8592244 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1879,7 +1879,7 @@ static int vmx_get_msr_feature(struct kvm_msr_entry *msr)
 			return 1;
 		return vmx_get_vmx_msr(&vmcs_config.nested, msr->index, &msr->data);
 	case MSR_IA32_PERF_CAPABILITIES:
-		msr->data = vmx_get_perf_capabilities();
+		msr->data = kvm_caps.supported_perf_cap;
 		return 0;
 	default:
 		return KVM_MSR_RET_INVALID;
@@ -2058,7 +2058,7 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
 	    (host_initiated || guest_cpuid_has(vcpu, X86_FEATURE_BUS_LOCK_DETECT)))
 		debugctl |= DEBUGCTLMSR_BUS_LOCK_DETECT;
 
-	if ((vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT) &&
+	if ((kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT) &&
 	    (host_initiated || intel_pmu_lbr_is_enabled(vcpu)))
 		debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
 
@@ -2371,14 +2371,14 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 			return 1;
 		if (data & PMU_CAP_LBR_FMT) {
 			if ((data & PMU_CAP_LBR_FMT) !=
-			    (vmx_get_perf_capabilities() & PMU_CAP_LBR_FMT))
+			    (kvm_caps.supported_perf_cap & PMU_CAP_LBR_FMT))
 				return 1;
 			if (!cpuid_model_is_consistent(vcpu))
 				return 1;
 		}
 		if (data & PERF_CAP_PEBS_FORMAT) {
 			if ((data & PERF_CAP_PEBS_MASK) !=
-			    (vmx_get_perf_capabilities() & PERF_CAP_PEBS_MASK))
+			    (kvm_caps.supported_perf_cap & PERF_CAP_PEBS_MASK))
 				return 1;
 			if (!guest_cpuid_has(vcpu, X86_FEATURE_DS))
 				return 1;
@@ -4695,7 +4695,7 @@ static void init_vmcs(struct vcpu_vmx *vmx)
 	/* 22.2.1, 20.8.1 */
 	vm_entry_controls_set(vmx, vmx_vmentry_ctrl());
 
-	vmx->vcpu.arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS;
+	vmx->vcpu.arch.cr0_guest_owned_bits = vmx_l1_guest_owned_cr0_bits();
 	vmcs_writel(CR0_GUEST_HOST_MASK, ~vmx->vcpu.arch.cr0_guest_owned_bits);
 
 	set_cr4_guest_host_mask(vmx);
@@ -5417,7 +5417,7 @@ static int handle_cr(struct kvm_vcpu *vcpu)
 		break;
 	case 3: /* lmsw */
 		val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
-		trace_kvm_cr_write(0, (kvm_read_cr0(vcpu) & ~0xful) | val);
+		trace_kvm_cr_write(0, (kvm_read_cr0_bits(vcpu, ~0xful) | val));
 		kvm_lmsw(vcpu, val);
 
 		return kvm_skip_emulated_instruction(vcpu);
@@ -7496,7 +7496,7 @@ static u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	if (!kvm_arch_has_noncoherent_dma(vcpu->kvm))
 		return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT;
 
-	if (kvm_read_cr0(vcpu) & X86_CR0_CD) {
+	if (kvm_read_cr0_bits(vcpu, X86_CR0_CD)) {
 		if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
 			cache = MTRR_TYPE_WRBACK;
 		else
@@ -7702,6 +7702,33 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 	vmx_update_exception_bitmap(vcpu);
 }
 
+static 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)
+		return 0;
+
+	if (boot_cpu_has(X86_FEATURE_PDCM))
+		rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
+
+	if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) {
+		x86_perf_get_lbr(&lbr);
+		if (lbr.nr)
+			perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT;
+	}
+
+	if (vmx_pebs_supported()) {
+		perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK;
+		if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4)
+			perf_cap &= ~PERF_CAP_PEBS_BASELINE;
+	}
+
+	return perf_cap;
+}
+
 static __init void vmx_set_cpu_caps(void)
 {
 	kvm_set_cpu_caps();
@@ -7724,6 +7751,7 @@ static __init void vmx_set_cpu_caps(void)
 
 	if (!enable_pmu)
 		kvm_cpu_cap_clear(X86_FEATURE_PDCM);
+	kvm_caps.supported_perf_cap = vmx_get_perf_capabilities();
 
 	if (!enable_sgx) {
 		kvm_cpu_cap_clear(X86_FEATURE_SGX);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index a3da84f4ea45..e2b04f4c0fef 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -640,6 +640,24 @@ BUILD_CONTROLS_SHADOW(tertiary_exec, TERTIARY_VM_EXEC_CONTROL, 64)
 				(1 << VCPU_EXREG_EXIT_INFO_1) | \
 				(1 << VCPU_EXREG_EXIT_INFO_2))
 
+static inline unsigned long vmx_l1_guest_owned_cr0_bits(void)
+{
+	unsigned long bits = KVM_POSSIBLE_CR0_GUEST_BITS;
+
+	/*
+	 * CR0.WP needs to be intercepted when KVM is shadowing legacy paging
+	 * in order to construct shadow PTEs with the correct protections.
+	 * Note!  CR0.WP technically can be passed through to the guest if
+	 * paging is disabled, but checking CR0.PG would generate a cyclical
+	 * dependency of sorts due to forcing the caller to ensure CR0 holds
+	 * the correct value prior to determining which CR0 bits can be owned
+	 * by L1.  Keep it simple and limit the optimization to EPT.
+	 */
+	if (!enable_ept)
+		bits &= ~X86_CR0_WP;
+	return bits;
+}
+
 static inline struct kvm_vmx *to_kvm_vmx(struct kvm *kvm)
 {
 	return container_of(kvm, struct kvm_vmx, kvm);