1 files changed, 290 insertions, 10 deletions

diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index a886a47daebd..9efc1a6b8693 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -29,7 +29,7 @@ static struct kvm_event_hw_type_mapping intel_arch_events[] = {
 	[4] = { 0x2e, 0x41, PERF_COUNT_HW_CACHE_MISSES },
 	[5] = { 0xc4, 0x00, PERF_COUNT_HW_BRANCH_INSTRUCTIONS },
 	[6] = { 0xc5, 0x00, PERF_COUNT_HW_BRANCH_MISSES },
-	[7] = { 0x00, 0x30, PERF_COUNT_HW_REF_CPU_CYCLES },
+	[7] = { 0x00, 0x03, PERF_COUNT_HW_REF_CPU_CYCLES },
 };
 
 /* mapping between fixed pmc index and intel_arch_events array */
@@ -152,12 +152,17 @@ static struct kvm_pmc *intel_rdpmc_ecx_to_pmc(struct kvm_vcpu *vcpu,
 	return &counters[array_index_nospec(idx, num_counters)];
 }
 
-static inline bool fw_writes_is_enabled(struct kvm_vcpu *vcpu)
+static inline u64 vcpu_get_perf_capabilities(struct kvm_vcpu *vcpu)
 {
 	if (!guest_cpuid_has(vcpu, X86_FEATURE_PDCM))
-		return false;
+		return 0;
 
-	return vcpu->arch.perf_capabilities & PMU_CAP_FW_WRITES;
+	return vcpu->arch.perf_capabilities;
+}
+
+static inline bool fw_writes_is_enabled(struct kvm_vcpu *vcpu)
+{
+	return (vcpu_get_perf_capabilities(vcpu) & PMU_CAP_FW_WRITES) != 0;
 }
 
 static inline struct kvm_pmc *get_fw_gp_pmc(struct kvm_pmu *pmu, u32 msr)
@@ -168,6 +173,41 @@ static inline struct kvm_pmc *get_fw_gp_pmc(struct kvm_pmu *pmu, u32 msr)
 	return get_gp_pmc(pmu, msr, MSR_IA32_PMC0);
 }
 
+bool intel_pmu_lbr_is_compatible(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * As a first step, a guest could only enable LBR feature if its
+	 * cpu model is the same as the host because the LBR registers
+	 * would be pass-through to the guest and they're model specific.
+	 */
+	return boot_cpu_data.x86_model == guest_cpuid_model(vcpu);
+}
+
+bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu)
+{
+	struct x86_pmu_lbr *lbr = vcpu_to_lbr_records(vcpu);
+
+	return lbr->nr && (vcpu_get_perf_capabilities(vcpu) & PMU_CAP_LBR_FMT);
+}
+
+static bool intel_pmu_is_valid_lbr_msr(struct kvm_vcpu *vcpu, u32 index)
+{
+	struct x86_pmu_lbr *records = vcpu_to_lbr_records(vcpu);
+	bool ret = false;
+
+	if (!intel_pmu_lbr_is_enabled(vcpu))
+		return ret;
+
+	ret = (index == MSR_LBR_SELECT) || (index == MSR_LBR_TOS) ||
+		(index >= records->from && index < records->from + records->nr) ||
+		(index >= records->to && index < records->to + records->nr);
+
+	if (!ret && records->info)
+		ret = (index >= records->info && index < records->info + records->nr);
+
+	return ret;
+}
+
 static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -183,7 +223,8 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 	default:
 		ret = get_gp_pmc(pmu, msr, MSR_IA32_PERFCTR0) ||
 			get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0) ||
-			get_fixed_pmc(pmu, msr) || get_fw_gp_pmc(pmu, msr);
+			get_fixed_pmc(pmu, msr) || get_fw_gp_pmc(pmu, msr) ||
+			intel_pmu_is_valid_lbr_msr(vcpu, msr);
 		break;
 	}
 
@@ -202,6 +243,111 @@ static struct kvm_pmc *intel_msr_idx_to_pmc(struct kvm_vcpu *vcpu, u32 msr)
 	return pmc;
 }
 
+static inline void intel_pmu_release_guest_lbr_event(struct kvm_vcpu *vcpu)
+{
+	struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
+
+	if (lbr_desc->event) {
+		perf_event_release_kernel(lbr_desc->event);
+		lbr_desc->event = NULL;
+		vcpu_to_pmu(vcpu)->event_count--;
+	}
+}
+
+int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu)
+{
+	struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct perf_event *event;
+
+	/*
+	 * The perf_event_attr is constructed in the minimum efficient way:
+	 * - set 'pinned = true' to make it task pinned so that if another
+	 *   cpu pinned event reclaims LBR, the event->oncpu will be set to -1;
+	 * - set '.exclude_host = true' to record guest branches behavior;
+	 *
+	 * - set '.config = INTEL_FIXED_VLBR_EVENT' to indicates host perf
+	 *   schedule the event without a real HW counter but a fake one;
+	 *   check is_guest_lbr_event() and __intel_get_event_constraints();
+	 *
+	 * - set 'sample_type = PERF_SAMPLE_BRANCH_STACK' and
+	 *   'branch_sample_type = PERF_SAMPLE_BRANCH_CALL_STACK |
+	 *   PERF_SAMPLE_BRANCH_USER' to configure it as a LBR callstack
+	 *   event, which helps KVM to save/restore guest LBR records
+	 *   during host context switches and reduces quite a lot overhead,
+	 *   check branch_user_callstack() and intel_pmu_lbr_sched_task();
+	 */
+	struct perf_event_attr attr = {
+		.type = PERF_TYPE_RAW,
+		.size = sizeof(attr),
+		.config = INTEL_FIXED_VLBR_EVENT,
+		.sample_type = PERF_SAMPLE_BRANCH_STACK,
+		.pinned = true,
+		.exclude_host = true,
+		.branch_sample_type = PERF_SAMPLE_BRANCH_CALL_STACK |
+					PERF_SAMPLE_BRANCH_USER,
+	};
+
+	if (unlikely(lbr_desc->event)) {
+		__set_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use);
+		return 0;
+	}
+
+	event = perf_event_create_kernel_counter(&attr, -1,
+						current, NULL, NULL);
+	if (IS_ERR(event)) {
+		pr_debug_ratelimited("%s: failed %ld\n",
+					__func__, PTR_ERR(event));
+		return PTR_ERR(event);
+	}
+	lbr_desc->event = event;
+	pmu->event_count++;
+	__set_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use);
+	return 0;
+}
+
+/*
+ * It's safe to access LBR msrs from guest when they have not
+ * been passthrough since the host would help restore or reset
+ * the LBR msrs records when the guest LBR event is scheduled in.
+ */
+static bool intel_pmu_handle_lbr_msrs_access(struct kvm_vcpu *vcpu,
+				     struct msr_data *msr_info, bool read)
+{
+	struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
+	u32 index = msr_info->index;
+
+	if (!intel_pmu_is_valid_lbr_msr(vcpu, index))
+		return false;
+
+	if (!lbr_desc->event && intel_pmu_create_guest_lbr_event(vcpu) < 0)
+		goto dummy;
+
+	/*
+	 * Disable irq to ensure the LBR feature doesn't get reclaimed by the
+	 * host at the time the value is read from the msr, and this avoids the
+	 * host LBR value to be leaked to the guest. If LBR has been reclaimed,
+	 * return 0 on guest reads.
+	 */
+	local_irq_disable();
+	if (lbr_desc->event->state == PERF_EVENT_STATE_ACTIVE) {
+		if (read)
+			rdmsrl(index, msr_info->data);
+		else
+			wrmsrl(index, msr_info->data);
+		__set_bit(INTEL_PMC_IDX_FIXED_VLBR, vcpu_to_pmu(vcpu)->pmc_in_use);
+		local_irq_enable();
+		return true;
+	}
+	clear_bit(INTEL_PMC_IDX_FIXED_VLBR, vcpu_to_pmu(vcpu)->pmc_in_use);
+	local_irq_enable();
+
+dummy:
+	if (read)
+		msr_info->data = 0;
+	return true;
+}
+
 static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -236,7 +382,8 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		} else if ((pmc = get_gp_pmc(pmu, msr, MSR_P6_EVNTSEL0))) {
 			msr_info->data = pmc->eventsel;
 			return 0;
-		}
+		} else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, true))
+			return 0;
 	}
 
 	return 1;
@@ -307,7 +454,8 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 				reprogram_gp_counter(pmc, data);
 				return 0;
 			}
-		}
+		} else if (intel_pmu_handle_lbr_msrs_access(vcpu, msr_info, false))
+			return 0;
 	}
 
 	return 1;
@@ -316,6 +464,8 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 {
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
+
 	struct x86_pmu_capability x86_pmu;
 	struct kvm_cpuid_entry2 *entry;
 	union cpuid10_eax eax;
@@ -327,7 +477,6 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 	pmu->counter_bitmask[KVM_PMC_FIXED] = 0;
 	pmu->version = 0;
 	pmu->reserved_bits = 0xffffffff00200000ull;
-	vcpu->arch.perf_capabilities = 0;
 
 	entry = kvm_find_cpuid_entry(vcpu, 0xa, 0);
 	if (!entry)
@@ -340,12 +489,12 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 		return;
 
 	perf_get_x86_pmu_capability(&x86_pmu);
-	if (guest_cpuid_has(vcpu, X86_FEATURE_PDCM))
-		vcpu->arch.perf_capabilities = vmx_get_perf_capabilities();
 
 	pmu->nr_arch_gp_counters = min_t(int, eax.split.num_counters,
 					 x86_pmu.num_counters_gp);
+	eax.split.bit_width = min_t(int, eax.split.bit_width, x86_pmu.bit_width_gp);
 	pmu->counter_bitmask[KVM_PMC_GP] = ((u64)1 << eax.split.bit_width) - 1;
+	eax.split.mask_length = min_t(int, eax.split.mask_length, x86_pmu.events_mask_len);
 	pmu->available_event_types = ~entry->ebx &
 					((1ull << eax.split.mask_length) - 1);
 
@@ -355,6 +504,8 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 		pmu->nr_arch_fixed_counters =
 			min_t(int, edx.split.num_counters_fixed,
 			      x86_pmu.num_counters_fixed);
+		edx.split.bit_width_fixed = min_t(int,
+			edx.split.bit_width_fixed, x86_pmu.bit_width_fixed);
 		pmu->counter_bitmask[KVM_PMC_FIXED] =
 			((u64)1 << edx.split.bit_width_fixed) - 1;
 	}
@@ -381,12 +532,21 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 		INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters);
 
 	nested_vmx_pmu_entry_exit_ctls_update(vcpu);
+
+	if (intel_pmu_lbr_is_compatible(vcpu))
+		x86_perf_get_lbr(&lbr_desc->records);
+	else
+		lbr_desc->records.nr = 0;
+
+	if (lbr_desc->records.nr)
+		bitmap_set(pmu->all_valid_pmc_idx, INTEL_PMC_IDX_FIXED_VLBR, 1);
 }
 
 static void intel_pmu_init(struct kvm_vcpu *vcpu)
 {
 	int i;
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
 
 	for (i = 0; i < INTEL_PMC_MAX_GENERIC; i++) {
 		pmu->gp_counters[i].type = KVM_PMC_GP;
@@ -401,6 +561,11 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
 		pmu->fixed_counters[i].idx = i + INTEL_PMC_IDX_FIXED;
 		pmu->fixed_counters[i].current_config = 0;
 	}
+
+	vcpu->arch.perf_capabilities = vmx_get_perf_capabilities();
+	lbr_desc->records.nr = 0;
+	lbr_desc->event = NULL;
+	lbr_desc->msr_passthrough = false;
 }
 
 static void intel_pmu_reset(struct kvm_vcpu *vcpu)
@@ -425,6 +590,119 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu)
 
 	pmu->fixed_ctr_ctrl = pmu->global_ctrl = pmu->global_status =
 		pmu->global_ovf_ctrl = 0;
+
+	intel_pmu_release_guest_lbr_event(vcpu);
+}
+
+/*
+ * Emulate LBR_On_PMI behavior for 1 < pmu.version < 4.
+ *
+ * If Freeze_LBR_On_PMI = 1, the LBR is frozen on PMI and
+ * the KVM emulates to clear the LBR bit (bit 0) in IA32_DEBUGCTL.
+ *
+ * Guest needs to re-enable LBR to resume branches recording.
+ */
+static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu)
+{
+	u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL);
+
+	if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) {
+		data &= ~DEBUGCTLMSR_LBR;
+		vmcs_write64(GUEST_IA32_DEBUGCTL, data);
+	}
+}
+
+static void intel_pmu_deliver_pmi(struct kvm_vcpu *vcpu)
+{
+	u8 version = vcpu_to_pmu(vcpu)->version;
+
+	if (!intel_pmu_lbr_is_enabled(vcpu))
+		return;
+
+	if (version > 1 && version < 4)
+		intel_pmu_legacy_freezing_lbrs_on_pmi(vcpu);
+}
+
+static void vmx_update_intercept_for_lbr_msrs(struct kvm_vcpu *vcpu, bool set)
+{
+	struct x86_pmu_lbr *lbr = vcpu_to_lbr_records(vcpu);
+	int i;
+
+	for (i = 0; i < lbr->nr; i++) {
+		vmx_set_intercept_for_msr(vcpu, lbr->from + i, MSR_TYPE_RW, set);
+		vmx_set_intercept_for_msr(vcpu, lbr->to + i, MSR_TYPE_RW, set);
+		if (lbr->info)
+			vmx_set_intercept_for_msr(vcpu, lbr->info + i, MSR_TYPE_RW, set);
+	}
+
+	vmx_set_intercept_for_msr(vcpu, MSR_LBR_SELECT, MSR_TYPE_RW, set);
+	vmx_set_intercept_for_msr(vcpu, MSR_LBR_TOS, MSR_TYPE_RW, set);
+}
+
+static inline void vmx_disable_lbr_msrs_passthrough(struct kvm_vcpu *vcpu)
+{
+	struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
+
+	if (!lbr_desc->msr_passthrough)
+		return;
+
+	vmx_update_intercept_for_lbr_msrs(vcpu, true);
+	lbr_desc->msr_passthrough = false;
+}
+
+static inline void vmx_enable_lbr_msrs_passthrough(struct kvm_vcpu *vcpu)
+{
+	struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
+
+	if (lbr_desc->msr_passthrough)
+		return;
+
+	vmx_update_intercept_for_lbr_msrs(vcpu, false);
+	lbr_desc->msr_passthrough = true;
+}
+
+/*
+ * Higher priority host perf events (e.g. cpu pinned) could reclaim the
+ * pmu resources (e.g. LBR) that were assigned to the guest. This is
+ * usually done via ipi calls (more details in perf_install_in_context).
+ *
+ * Before entering the non-root mode (with irq disabled here), double
+ * confirm that the pmu features enabled to the guest are not reclaimed
+ * by higher priority host events. Otherwise, disallow vcpu's access to
+ * the reclaimed features.
+ */
+void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)
+{
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+	struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
+
+	if (!lbr_desc->event) {
+		vmx_disable_lbr_msrs_passthrough(vcpu);
+		if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)
+			goto warn;
+		if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use))
+			goto warn;
+		return;
+	}
+
+	if (lbr_desc->event->state < PERF_EVENT_STATE_ACTIVE) {
+		vmx_disable_lbr_msrs_passthrough(vcpu);
+		__clear_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use);
+		goto warn;
+	} else
+		vmx_enable_lbr_msrs_passthrough(vcpu);
+
+	return;
+
+warn:
+	pr_warn_ratelimited("kvm: vcpu-%d: fail to passthrough LBR.\n",
+		vcpu->vcpu_id);
+}
+
+static void intel_pmu_cleanup(struct kvm_vcpu *vcpu)
+{
+	if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR))
+		intel_pmu_release_guest_lbr_event(vcpu);
 }
 
 struct kvm_pmu_ops intel_pmu_ops = {
@@ -441,4 +719,6 @@ struct kvm_pmu_ops intel_pmu_ops = {
 	.refresh = intel_pmu_refresh,
 	.init = intel_pmu_init,
 	.reset = intel_pmu_reset,
+	.deliver_pmi = intel_pmu_deliver_pmi,
+	.cleanup = intel_pmu_cleanup,
 };