Skip to contentSkip to conversation

KVM: x86/pmu: Add hardware Topdown metrics support

PATCH Superseded Zide Chen 4 participants 12 messages Jun 23 – Jun 24

Subsystems (5)
x86 KVM Kselftest perf events +1 more subsystems

v4 of 9 Superseded Latest is v9 →

lore
Share & tools
lore

Zide Chen

author
#0 lore raw

v4 cover KVM: x86/pmu: Add hardware Topdown metrics support

The Top-Down Microarchitecture Analysis (TMA) method is a structured approach for identifying performance bottlenecks in out-of-order processors.

Currently, guests support the TMA method by collecting Topdown events using GP counters, which may trigger multiplexing. To free up scarce GP counters, eliminate multiplexing-induced skew, and obtain coherent Topdown metric ratios, it is desirable to expose fixed counter 3 and the IA32_PERF_METRICS MSR to guests.

Several attempts have been made to virtualize this under the legacy vPMU model [1][2][3], but they were unsuccessful. With the new mediated vPMU, enabling TMA support in guests becomes much simpler. It avoids invasive changes to the perf core, eliminates CPU pinning and fixed-counter affinity issues, and reduces the latge overhead of trapping and emulating MSR accesses.

[1] https://lore.kernel.org/kvm/[email protected]/
[2] https://lore.kernel.org/all/[email protected]/T/
[3] https://lwn.net/ml/linux-kernel/[email protected]/

Tested on an SPR. Without this series, only raw topdown.*_slots events work in the guest, and metric events (e.g. cpu/topdown-bad-spec/) are not available.

With this series, metric events are visible in the guest. Run this command on both host and guest:

$ perf stat --topdown --no-metric-only -- taskset -c 2 perf bench sched messaging

Host results:

# Running 'sched/messaging' benchmark:
# 20 sender and receiver processes per group
# 10 groups == 400 processes run

     Total time: 1.500 [sec]

Performance counter stats for 'taskset -c 2 perf bench sched messaging':

     4,266,060,558      TOPDOWN.SLOTS:u              #     32.0 %  tma_frontend_bound
                                                     #      5.2 %  tma_bad_speculation
       588,397,905      topdown-retiring:u           #     13.8 %  tma_retiring
                                                     #     49.0 %  tma_backend_bound
     1,376,283,990      topdown-fe-bound:u
     2,096,827,304      topdown-be-bound:u
       217,425,841      topdown-bad-spec:u
         5,050,520      INT_MISC.UOP_DROPPING:u

Rebased to kvm-x86/next: c1f730330292

v4 changes:
- patch 3/4: Remove WARN_ON_ONCE() and simply reject the guest accesses by checking host_initiated. (Sashiko)
- patch 3/4: Passthru MSR_PERF_METRICS only if has_mediated_pmu is true. (Sashiko)
v3 changes:
- patch 2/4: Move the non-contiguous counter filter code to pmu.c (Dapeng)
- patch 3/4: Replace WARN_ON() with WARN_ON_ONCE(). (Dapeng)
- patch 4/4: Change abs() with explicit bounds (sum >= 0xfd && sum <= 0x102).
- Minor comment cleanups.

v2 changes:
- As suggested by Dapeng, implement a new selftest patch.
- Don't advertise fixed counter 3 if the host doesn't support it.
- Minor change in patch 1 to remove a magic number.

v3:
https://lore.kernel.org/kvm/[email protected]/T/#t
v2:
https://lore.kernel.org/kvm/[email protected]/T/#u
v1:
https://lore.kernel.org/kvm/[email protected]/T/#t
QEMU:
https://lore.kernel.org/qemu-devel/[email protected]/

Dapeng Mi (2):
KVM: x86/pmu: Support Intel fixed counter 3 on mediated vPMU
KVM: x86/pmu: Support PERF_METRICS MSR in mediated vPMU

Zide Chen (2):
KVM: x86/pmu: Do not map fixed counters >= 3 to generic perf events
KVM: selftests: Add perf_metrics and fixed counter 3 tests

 arch/x86/include/asm/kvm_host.h               |  3 +-
 arch/x86/include/asm/msr-index.h              |  1 +
 arch/x86/include/asm/perf_event.h             |  1 +
 arch/x86/kvm/pmu.c                            | 18 +++++
 arch/x86/kvm/vmx/pmu_intel.c                  | 62 ++++++++++++----
 arch/x86/kvm/vmx/pmu_intel.h                  |  5 ++
 arch/x86/kvm/vmx/vmx.c                        |  6 ++
 arch/x86/kvm/x86.c                            | 10 ++-
 tools/arch/x86/include/asm/msr-index.h        |  1 +
 tools/testing/selftests/kvm/include/x86/pmu.h |  3 +
 .../selftests/kvm/x86/pmu_counters_test.c     | 72 +++++++++++++++++--
 11 files changed, 161 insertions(+), 21 deletions(-)
Signature · 1 line
2.54.0
author
#1 lore raw

PATCH v4 1/4 KVM: x86/pmu: Do not map fixed counters >= 3 to generic perf events

Only fixed counters 0..2 have matching generic cross-platform hardware perf events (INSTRUCTIONS, CPU_CYCLES, REF_CPU_CYCLES). Therefore, perf_get_hw_event_config() is only applicable to these counters.

KVM does not intend to emulate fixed counters >= 3 on legacy (non-mediated) vPMU, while for mediated vPMU, KVM does not care what the fixed counter event mappings are. Therefore, return 0 for their eventsel.

Also remove __always_inline as BUILD_BUG_ON() is no longer needed.

---
v2:
- Replace 3 in "if (index < 3)" with ARRAY_SIZE(fixed_pmc_perf_ids).

---
 arch/x86/kvm/vmx/pmu_intel.c | 26 ++++++++++++++------------
 1 file changed, 14 insertions(+), 12 deletions(-)
arch/x86/kvm/vmx/pmu_intel.c +14 -12
index a73a9515d96c..59b7a90c79e1 100644
@@ -464,28 +464,30 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
  * different perf_event is already utilizing the requested counter, but the end
  * result is the same (ignoring the fact that using a general purpose counter
  * will likely exacerbate counter contention).
- *
- * Forcibly inlined to allow asserting on @index at build time, and there should
- * never be more than one user.
  */
-static __always_inline u64 intel_get_fixed_pmc_eventsel(unsigned int index)
+static u64 intel_get_fixed_pmc_eventsel(unsigned int index)
 {
 	const enum perf_hw_id fixed_pmc_perf_ids[] = {
 		[0] = PERF_COUNT_HW_INSTRUCTIONS,
 		[1] = PERF_COUNT_HW_CPU_CYCLES,
 		[2] = PERF_COUNT_HW_REF_CPU_CYCLES,
 	};
-	u64 eventsel;
-
-	BUILD_BUG_ON(ARRAY_SIZE(fixed_pmc_perf_ids) != KVM_MAX_NR_INTEL_FIXED_COUNTERS);
-	BUILD_BUG_ON(index >= KVM_MAX_NR_INTEL_FIXED_COUNTERS);
+	u64 eventsel = 0;
 
 	/*
-	 * Yell if perf reports support for a fixed counter but perf doesn't
-	 * have a known encoding for the associated general purpose event.
+	 * Fixed counters 3 and above don't have corresponding generic hardware
+	 * perf event, and KVM does not intend to emulate them on non-mediated
+	 * vPMU.
 	 */
-	eventsel = perf_get_hw_event_config(fixed_pmc_perf_ids[index]);
-	WARN_ON_ONCE(!eventsel && index < kvm_pmu_cap.num_counters_fixed);
+	if (index < ARRAY_SIZE(fixed_pmc_perf_ids)) {
+		/*
+		 * Yell if perf reports support for a fixed counter but perf
+		 * doesn't have a known encoding for the associated general
+		 * purpose event.
+		 */
+		eventsel = perf_get_hw_event_config(fixed_pmc_perf_ids[index]);
+		WARN_ON_ONCE(!eventsel && index < kvm_pmu_cap.num_counters_fixed);
+	}
 	return eventsel;
 }
 
Signature · 1 line
2.54.0
author
#2 lore raw

PATCH v4 2/4 KVM: x86/pmu: Support Intel fixed counter 3 on mediated vPMU

In reply to Zide Chen

From: Dapeng Mi <[email protected]>

Starting with Ice Lake, Intel introduced fixed counter 3, which counts TOPDOWN.SLOTS - the number of available slots for an unhalted logical processor. It serves as the denominator for top-level metrics in the Top-down Microarchitecture Analysis method.

Emulating this counter on legacy vPMU would require introducing a new generic perf encoding for the Intel-specific TOPDOWN.SLOTS event in order to call perf_get_hw_event_config(). This is undesirable as it would pollute the generic perf event encoding.

Moreover, KVM does not intend to emulate IA32_PERF_METRICS in the legacy vPMU model, and without IA32_PERF_METRICS, emulating this counter has little practical value. Therefore, expose fixed counter 3 to guests only when mediated vPMU is enabled.

---
v3:
- Move the non-contiguous counter filter code to pmu.c v2:
- Don't advertise fixed counter 3 to userspace if the host doesn't support it.

---
 arch/x86/include/asm/kvm_host.h |  2 +-
 arch/x86/kvm/pmu.c              | 18 ++++++++++++++++++
 arch/x86/kvm/x86.c              |  4 ++--
 3 files changed, 21 insertions(+), 3 deletions(-)
arch/x86/include/asm/kvm_host.h +1 -1
index eee473717c0e..edd414f8ee95 100644
@@ -574,7 +574,7 @@ struct kvm_pmc {
 #define KVM_MAX_NR_GP_COUNTERS		KVM_MAX(KVM_MAX_NR_INTEL_GP_COUNTERS, \
 						KVM_MAX_NR_AMD_GP_COUNTERS)
 
-#define KVM_MAX_NR_INTEL_FIXED_COUNTERS	3
+#define KVM_MAX_NR_INTEL_FIXED_COUNTERS	4
 #define KVM_MAX_NR_AMD_FIXED_COUNTERS	0
 #define KVM_MAX_NR_FIXED_COUNTERS	KVM_MAX(KVM_MAX_NR_INTEL_FIXED_COUNTERS, \
 						KVM_MAX_NR_AMD_FIXED_COUNTERS)
arch/x86/kvm/pmu.c +18 -0
index b92dd2e58335..0faf580782d5 100644
@@ -122,6 +122,8 @@ void kvm_init_pmu_capability(struct kvm_pmu_ops *pmu_ops)
 {
 	bool is_intel = boot_cpu_data.x86_vendor == X86_VENDOR_INTEL;
 	int min_nr_gp_ctrs = pmu_ops->MIN_NR_GP_COUNTERS;
+	union cpuid10_edx edx;
+	u32 eax, ebx, ecx;
 
 	/*
 	 * Hybrid PMUs don't play nice with virtualization without careful
@@ -169,6 +171,22 @@ void kvm_init_pmu_capability(struct kvm_pmu_ops *pmu_ops)
 	kvm_pmu_cap.num_counters_fixed = min(kvm_pmu_cap.num_counters_fixed,
 					     KVM_MAX_NR_FIXED_COUNTERS);
 
+	/*
+	 * Intel platforms may support non-contiguous fixed counters, e.g., some
+	 * E-core based server processors don't implement fixed counter 3.
+	 *
+	 * Before KVM supports non-contiguous fixed counters, make sure only
+	 * contiguous ones are retained in kvm_pmu_cap.
+	 */
+	if (kvm_host_pmu.version >= 5) {
+		cpuid(10, &eax, &ebx, &ecx, &edx.full);
+		if (kvm_pmu_cap.num_counters_fixed > edx.split.num_counters_fixed)
+			kvm_pmu_cap.num_counters_fixed = edx.split.num_counters_fixed;
+	}
+
+	if (!enable_mediated_pmu && kvm_pmu_cap.num_counters_fixed > 3)
+		kvm_pmu_cap.num_counters_fixed = 3;
+
 	kvm_pmu_eventsel.INSTRUCTIONS_RETIRED =
 		perf_get_hw_event_config(PERF_COUNT_HW_INSTRUCTIONS);
 	kvm_pmu_eventsel.BRANCH_INSTRUCTIONS_RETIRED =
arch/x86/kvm/x86.c +2 -2
index d9d51803b7b2..e872398c12fc 100644
@@ -350,7 +350,7 @@ static const u32 msrs_to_save_base[] = {
 
 static const u32 msrs_to_save_pmu[] = {
 	MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1,
-	MSR_ARCH_PERFMON_FIXED_CTR0 + 2,
+	MSR_ARCH_PERFMON_FIXED_CTR2, MSR_ARCH_PERFMON_FIXED_CTR3,
 	MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS,
 	MSR_CORE_PERF_GLOBAL_CTRL,
 	MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG,
@@ -7742,7 +7742,7 @@ static void kvm_init_msr_lists(void)
 {
 	unsigned i;
 
-	BUILD_BUG_ON_MSG(KVM_MAX_NR_FIXED_COUNTERS != 3,
+	BUILD_BUG_ON_MSG(KVM_MAX_NR_FIXED_COUNTERS != 4,
 			 "Please update the fixed PMCs in msrs_to_save_pmu[]");
 
 	num_msrs_to_save = 0;
Signature · 1 line
2.54.0
author
#3 lore raw

PATCH v4 3/4 KVM: x86/pmu: Support PERF_METRICS MSR in mediated vPMU

In reply to Zide Chen

From: Dapeng Mi <[email protected]>

Bit 15 in IA32_PERF_CAPABILITIES indicates that the CPU provides built-in support for Topdown Microarchitecture Analysis (TMA) L1 metrics via the IA32_PERF_METRICS MSR.

Expose this capability only when mediated vPMU is enabled, as emulating IA32_PERF_METRICS in the legacy vPMU model is impractical.

Pass IA32_PERF_METRICS through to the guest only when mediated vPMU is enabled and bit 15 is set in guest IA32_PERF_CAPABILITIES. Allow kvm_pmu_{get,set}_msr() to handle this MSR for host accesses.

Save and restore this MSR on host/guest PMU context switches so that host PMU activity does not clobber the guest value, and guest state is not leaked into the host.

---
v4:
- Remove WARN_ON_ONCE() and simply reject the guest accesses by checking host_initiated. (Sashiko)
- Passthru MSR_PERF_METRICS only if has_mediated_pmu is true. (Sashiko)
- Remove the redundant !! in vcpu_has_perf_metrics().
v3:
- Replace WARN_ON() with WARN_ON_ONCE(). (Dapeng)
- Add comments to explain why don't validate writes on PERF_METRICS.

---
 arch/x86/include/asm/kvm_host.h   |  1 +
 arch/x86/include/asm/msr-index.h  |  1 +
 arch/x86/include/asm/perf_event.h |  1 +
 arch/x86/kvm/vmx/pmu_intel.c      | 38 +++++++++++++++++++++++++++++++
 arch/x86/kvm/vmx/pmu_intel.h      |  5 ++++
 arch/x86/kvm/vmx/vmx.c            |  7 ++++++
 arch/x86/kvm/x86.c                |  6 ++++-
 7 files changed, 58 insertions(+), 1 deletion(-)
arch/x86/include/asm/kvm_host.h +1 -0
index edd414f8ee95..4f549ef012d2 100644
@@ -594,6 +594,7 @@ struct kvm_pmu {
 	u64 global_status_rsvd;
 	u64 reserved_bits;
 	u64 raw_event_mask;
+	u64 perf_metrics;
 	struct kvm_pmc gp_counters[KVM_MAX_NR_GP_COUNTERS];
 	struct kvm_pmc fixed_counters[KVM_MAX_NR_FIXED_COUNTERS];
 
arch/x86/include/asm/msr-index.h +1 -0
index 18c4be75e927..fdcaeb6c8352 100644
@@ -331,6 +331,7 @@
 #define PERF_CAP_PEBS_FORMAT		0xf00
 #define PERF_CAP_FW_WRITES		BIT_ULL(13)
 #define PERF_CAP_PEBS_BASELINE		BIT_ULL(14)
+#define PERF_CAP_PERF_METRICS		BIT_ULL(15)
 #define PERF_CAP_PEBS_TIMING_INFO	BIT_ULL(17)
 #define PERF_CAP_PEBS_MASK		(PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \
 					 PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE | \
arch/x86/include/asm/perf_event.h +1 -0
index 1eb13673e889..bc2e1cbcd9b9 100644
@@ -447,6 +447,7 @@ static inline bool is_topdown_idx(int idx)
 #define GLOBAL_STATUS_ARCH_PEBS_THRESHOLD_BIT	54
 #define GLOBAL_STATUS_ARCH_PEBS_THRESHOLD	BIT_ULL(GLOBAL_STATUS_ARCH_PEBS_THRESHOLD_BIT)
 #define GLOBAL_STATUS_PERF_METRICS_OVF_BIT	48
+#define GLOBAL_STATUS_PERF_METRICS_OVF		BIT_ULL(GLOBAL_STATUS_PERF_METRICS_OVF_BIT)
 
 #define GLOBAL_CTRL_EN_PERF_METRICS		BIT_ULL(48)
 /*
arch/x86/kvm/vmx/pmu_intel.c +38 -0
index 59b7a90c79e1..2c3367f5e2df 100644
@@ -188,6 +188,8 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 	switch (msr) {
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
 		return kvm_pmu_has_perf_global_ctrl(pmu);
+	case MSR_PERF_METRICS:
+		return vcpu_has_perf_metrics(vcpu);
 	case MSR_IA32_PEBS_ENABLE:
 		ret = vcpu_get_perf_capabilities(vcpu) & PERF_CAP_PEBS_FORMAT;
 		break;
@@ -345,6 +347,11 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
 		msr_info->data = pmu->fixed_ctr_ctrl;
 		break;
+	case MSR_PERF_METRICS:
+		if (!msr_info->host_initiated)
+			return 1;
+		msr_info->data = pmu->perf_metrics;
+		break;
 	case MSR_IA32_PEBS_ENABLE:
 		msr_info->data = pmu->pebs_enable;
 		break;
@@ -394,6 +401,16 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (pmu->fixed_ctr_ctrl != data)
 			reprogram_fixed_counters(pmu, data);
 		break;
+	case MSR_PERF_METRICS:
+		if (!msr_info->host_initiated)
+			return 1;
+
+		/*
+		 * If TMA level 2 is not supported, bits [63:32] are reserved
+		 * and ignored on write, so no validation is needed here.
+		 */
+		pmu->perf_metrics = data;
+		break;
 	case MSR_IA32_PEBS_ENABLE:
 		if (data & pmu->pebs_enable_rsvd)
 			return 1;
@@ -589,6 +606,11 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 		pmu->global_status_rsvd &=
 				~MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI;
 
+	if (perf_capabilities & PERF_CAP_PERF_METRICS) {
+		pmu->global_ctrl_rsvd &= ~GLOBAL_CTRL_EN_PERF_METRICS;
+		pmu->global_status_rsvd &= ~GLOBAL_STATUS_PERF_METRICS_OVF;
+	}
+
 	if (perf_capabilities & PERF_CAP_PEBS_FORMAT) {
 		if (perf_capabilities & PERF_CAP_PEBS_BASELINE) {
 			pmu->pebs_enable_rsvd = counter_rsvd;
@@ -632,6 +654,9 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
 
 static void intel_pmu_reset(struct kvm_vcpu *vcpu)
 {
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+	pmu->perf_metrics = 0;
 	intel_pmu_release_guest_lbr_event(vcpu);
 }
 
@@ -803,6 +828,13 @@ static void intel_mediated_pmu_load(struct kvm_vcpu *vcpu)
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	u64 global_status, toggle;
 
+	/*
+	 * PERF_METRICS MSR must be restored closely after fixed counter 3,
+	 * which was just restored by kvm_pmu_load_guest_pmcs().
+	 */
+	if (vcpu_has_perf_metrics(vcpu))
+		wrmsrq(MSR_PERF_METRICS, pmu->perf_metrics);
+
 	rdmsrq(MSR_CORE_PERF_GLOBAL_STATUS, global_status);
 	toggle = pmu->global_status ^ global_status;
 	if (global_status & toggle)
@@ -831,6 +863,12 @@ static void intel_mediated_pmu_put(struct kvm_vcpu *vcpu)
 	 */
 	if (pmu->fixed_ctr_ctrl_hw)
 		wrmsrq(MSR_CORE_PERF_FIXED_CTR_CTRL, 0);
+
+	if (vcpu_has_perf_metrics(vcpu)) {
+		pmu->perf_metrics = rdpmc(INTEL_PMC_FIXED_RDPMC_METRICS);
+		if (pmu->perf_metrics)
+			wrmsrq(MSR_PERF_METRICS, 0);
+	}
 }
 
 struct kvm_pmu_ops intel_pmu_ops __initdata = {
arch/x86/kvm/vmx/pmu_intel.h +5 -0
index 5d9357640aa1..57705773dc49 100644
@@ -40,4 +40,9 @@ struct lbr_desc {
 
 extern struct x86_pmu_lbr vmx_lbr_caps;
 
+static inline bool vcpu_has_perf_metrics(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_perf_capabilities(vcpu) & PERF_CAP_PERF_METRICS;
+}
+
 #endif /* __KVM_X86_VMX_PMU_INTEL_H */
arch/x86/kvm/vmx/vmx.c +7 -0
index a1a5edb39a7e..584d99ef6026 100644
@@ -4260,6 +4260,10 @@ static void vmx_recalc_pmu_msr_intercepts(struct kvm_vcpu *vcpu)
 				  MSR_TYPE_RW, intercept);
 	vmx_set_intercept_for_msr(vcpu, MSR_CORE_PERF_GLOBAL_OVF_CTRL,
 				  MSR_TYPE_RW, intercept);
+
+	intercept = !has_mediated_pmu || !vcpu_has_perf_metrics(vcpu);
+	vmx_set_intercept_for_msr(vcpu, MSR_PERF_METRICS,
+				  MSR_TYPE_RW, intercept);
 }
 
 static void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
@@ -8084,6 +8088,9 @@ static __init u64 vmx_get_perf_capabilities(void)
 		perf_cap &= ~PERF_CAP_PEBS_BASELINE;
 	}
 
+	if (enable_mediated_pmu)
+		perf_cap |= host_perf_cap & PERF_CAP_PERF_METRICS;
+
 	return perf_cap;
 }
 
arch/x86/kvm/x86.c +5 -1
index e872398c12fc..9623f558f359 100644
@@ -352,7 +352,7 @@ static const u32 msrs_to_save_pmu[] = {
 	MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1,
 	MSR_ARCH_PERFMON_FIXED_CTR2, MSR_ARCH_PERFMON_FIXED_CTR3,
 	MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS,
-	MSR_CORE_PERF_GLOBAL_CTRL,
+	MSR_CORE_PERF_GLOBAL_CTRL, MSR_PERF_METRICS,
 	MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG,
 
 	/* This part of MSRs should match KVM_MAX_NR_INTEL_GP_COUNTERS. */
@@ -7679,6 +7679,10 @@ static void kvm_probe_msr_to_save(u32 msr_index)
 		     intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2))
 			return;
 		break;
+	case MSR_PERF_METRICS:
+		if (!(kvm_caps.supported_perf_cap & PERF_CAP_PERF_METRICS))
+			return;
+		break;
 	case MSR_ARCH_PERFMON_PERFCTR0 ...
 	     MSR_ARCH_PERFMON_PERFCTR0 + KVM_MAX_NR_GP_COUNTERS - 1:
 		if (msr_index - MSR_ARCH_PERFMON_PERFCTR0 >=
Signature · 1 line
2.54.0
#4 lore raw

Re: [PATCH V4 3/4] KVM: x86/pmu: Support PERF_METRICS MSR in mediated vPMU

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider: - [High] Emulation of guest RDMSR and WRMSR for MSR_PERF_METRICS unconditionally injects a #GP fault…

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
- [High] Emulation of guest RDMSR and WRMSR for MSR_PERF_METRICS unconditionally injects a #GP fault, breaking emulation and nested virtualization.
- [High] KVM_SET_MSRS for MSR_PERF_METRICS is silently discarded, breaking live migration of TMA metrics.
- [High] Host Topdown microarchitectural metrics are leaked to the guest via the RDPMC instruction when mediated PMU is enabled but the guest lacks the PERF_METRICS capability. --

commit 3d014d661f0ac59ad10f0335ced10697e72d7bf6
Author: Dapeng Mi <[email protected]>
Subject: KVM: x86/pmu: Support PERF_METRICS MSR in mediated vPMU

This commit exposes the IA32_PERF_METRICS MSR to the guest when mediated vPMU is enabled. It handles the MSR in kvm_pmu_{get,set}_msr() for host accesses and saves/restores the value on PMU context switches to avoid clobbering host data or leaking guest state.

Quoted 4 lines
arch/x86/kvm/vmx/pmu_intel.c +0 -0
index 59b7a90c79e12..2c3367f5e2dfb 100644

[ ... ]

arch/x86/kvm/vmx/pmu_intel.c static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) · line 352

Quoted 7 lines
arch/x86/kvm/vmx/pmu_intel.c +3 -0
@@ -345,6 +347,11 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
 		msr_info->data = pmu->fixed_ctr_ctrl;
 		break;
+	case MSR_PERF_METRICS:
+		if (!msr_info->host_initiated)
+			return 1;

[Severity: High]
If KVM needs to emulate a guest RDMSR instruction targeting MSR_PERF_METRICS, won't this unconditional return inject a #GP fault into the guest?

arch/x86/kvm/vmx/pmu_intel.c static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) · line 406

Quoted 12 lines
arch/x86/kvm/vmx/pmu_intel.c +5 -0
+		msr_info->data = pmu->perf_metrics;
+		break;
 	case MSR_IA32_PEBS_ENABLE:
 		msr_info->data = pmu->pebs_enable;
 		break;
@@ -394,6 +401,16 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (pmu->fixed_ctr_ctrl != data)
 			reprogram_fixed_counters(pmu, data);
 		break;
+	case MSR_PERF_METRICS:
+		if (!msr_info->host_initiated)
+			return 1;

[Severity: High]
Similarly, if KVM emulates a guest WRMSR instruction targeting MSR_PERF_METRICS, does returning 1 here cause the emulator to incorrectly inject a #GP fault?

arch/x86/kvm/vmx/pmu_intel.c static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) · line 412

Quoted 6 lines
arch/x86/kvm/vmx/pmu_intel.c +6 -0
+
+		/*
+		 * If TMA level 2 is not supported, bits [63:32] are reserved
+		 * and ignored on write, so no validation is needed here.
+		 */
+		pmu->perf_metrics = data;

[Severity: High]
When restoring guest state during live migration, userspace calls KVM_SET_MSRS which is wrapped in vcpu_load() and vcpu_put(). Since intel_pmu_set_msr() updates pmu->perf_metrics without updating the hardware MSR, won't the subsequent intel_mediated_pmu_put() during vcpu_put() read the stale hardware MSR and overwrite this newly restored value?

Quoted 4 lines
arch/x86/kvm/vmx/pmu_intel.c +1 -0
+		break;
 	case MSR_IA32_PEBS_ENABLE:
 		if (data & pmu->pebs_enable_rsvd)
 			return 1;

[ ... ]

arch/x86/kvm/vmx/pmu_intel.c static void intel_mediated_pmu_load(struct kvm_vcpu *vcpu) · line 837

Quoted 11 lines
arch/x86/kvm/vmx/pmu_intel.c +7 -0
@@ -803,6 +828,13 @@ static void intel_mediated_pmu_load(struct kvm_vcpu *vcpu)
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	u64 global_status, toggle;
 
+	/*
+	 * PERF_METRICS MSR must be restored closely after fixed counter 3,
+	 * which was just restored by kvm_pmu_load_guest_pmcs().
+	 */
+	if (vcpu_has_perf_metrics(vcpu))
+		wrmsrq(MSR_PERF_METRICS, pmu->perf_metrics);
+

[Severity: High]
If the guest is configured without PERF_CAP_PERF_METRICS but with mediated PMU enabled, RDPMC exiting might be disabled. Since intel_mediated_pmu_load() skips writing to MSR_PERF_METRICS in this case, could the guest execute RDPMC and read the un-scrubbed host metrics, leaking host microarchitectural state?

Quoted 14 lines
arch/x86/kvm/vmx/pmu_intel.c +6 -0
 	rdmsrq(MSR_CORE_PERF_GLOBAL_STATUS, global_status);
 	toggle = pmu->global_status ^ global_status;
 	if (global_status & toggle)
@@ -831,6 +863,12 @@ static void intel_mediated_pmu_put(struct kvm_vcpu *vcpu)
 	 */
 	if (pmu->fixed_ctr_ctrl_hw)
 		wrmsrq(MSR_CORE_PERF_FIXED_CTR_CTRL, 0);
+
+	if (vcpu_has_perf_metrics(vcpu)) {
+		pmu->perf_metrics = rdpmc(INTEL_PMC_FIXED_RDPMC_METRICS);
+		if (pmu->perf_metrics)
+			wrmsrq(MSR_PERF_METRICS, 0);
+	}
 }
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=3
author
#5 lore raw

Re: [PATCH V4 3/4] KVM: x86/pmu: Support PERF_METRICS MSR in mediated vPMU

Quoted 20 lines · On 6/22/2026 11:48 PM, [email protected] wrote:

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
- [High] Emulation of guest RDMSR and WRMSR for MSR_PERF_METRICS unconditionally injects a #GP fault, breaking emulation and nested virtualization.
- [High] KVM_SET_MSRS for MSR_PERF_METRICS is silently discarded, breaking live migration of TMA metrics.
- [High] Host Topdown microarchitectural metrics are leaked to the guest via the RDPMC instruction when mediated PMU is enabled but the guest lacks the PERF_METRICS capability. --

commit 3d014d661f0ac59ad10f0335ced10697e72d7bf6
Author: Dapeng Mi <[email protected]>
Subject: KVM: x86/pmu: Support PERF_METRICS MSR in mediated vPMU

This commit exposes the IA32_PERF_METRICS MSR to the guest when mediated vPMU is enabled. It handles the MSR in kvm_pmu_{get,set}_msr() for host accesses and saves/restores the value on PMU context switches to avoid clobbering host data or leaking guest state.

Quoted 4 lines
arch/x86/kvm/vmx/pmu_intel.c +0 -0
index 59b7a90c79e12..2c3367f5e2dfb 100644

[ ... ]

Quoted 11 lines

arch/x86/kvm/vmx/pmu_intel.c static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) · line 352

Quoted 7 lines
arch/x86/kvm/vmx/pmu_intel.c +3 -0
@@ -345,6 +347,11 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
 		msr_info->data = pmu->fixed_ctr_ctrl;
 		break;
+	case MSR_PERF_METRICS:
+		if (!msr_info->host_initiated)
+			return 1;

[Severity: High]
If KVM needs to emulate a guest RDMSR instruction targeting MSR_PERF_METRICS, won't this unconditional return inject a #GP fault into the guest?

I can't think of a case that KVM needs to emulate RDMSR/WRMSR on MSR_PERF_METRICS.

Quoted 9 lines
Quoted 9 lines
arch/x86/kvm/vmx/pmu_intel.c +2 -0
+		msr_info->data = pmu->perf_metrics;
+		break;
 	case MSR_IA32_PEBS_ENABLE:
 		msr_info->data = pmu->pebs_enable;
 		break;
@@ -394,6 +401,16 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (pmu->fixed_ctr_ctrl != data)
 			reprogram_fixed_counters(pmu, data);
 		break;
Quoted 8 lines

arch/x86/kvm/vmx/pmu_intel.c static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) · line 352

Quoted 3 lines
arch/x86/kvm/vmx/pmu_intel.c +3 -0
+	case MSR_PERF_METRICS:
+		if (!msr_info->host_initiated)
+			return 1;

[Severity: High]
Similarly, if KVM emulates a guest WRMSR instruction targeting MSR_PERF_METRICS, does returning 1 here cause the emulator to incorrectly inject a #GP fault?

Ditto.

Quoted 5 lines
Quoted 5 lines
arch/x86/kvm/vmx/pmu_intel.c +5 -0
+
+		/*
+		 * If TMA level 2 is not supported, bits [63:32] are reserved
+		 * and ignored on write, so no validation is needed here.
+		 */
Quoted 8 lines

arch/x86/kvm/vmx/pmu_intel.c static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) · line 412

Quoted 1 line
arch/x86/kvm/vmx/pmu_intel.c +1 -0
+		pmu->perf_metrics = data;

[Severity: High]
When restoring guest state during live migration, userspace calls KVM_SET_MSRS which is wrapped in vcpu_load() and vcpu_put(). Since intel_pmu_set_msr() updates pmu->perf_metrics without updating the hardware MSR, won't the subsequent intel_mediated_pmu_put() during vcpu_put() read the stale hardware MSR and overwrite this newly restored value?

No, this won't happen.

Quoted 9 lines
Quoted 4 lines
arch/x86/kvm/vmx/pmu_intel.c +1 -0
+		break;
 	case MSR_IA32_PEBS_ENABLE:
 		if (data & pmu->pebs_enable_rsvd)
 			return 1;

[ ... ]

Quoted 4 lines
arch/x86/kvm/vmx/pmu_intel.c +0 -0
@@ -803,6 +828,13 @@ static void intel_mediated_pmu_load(struct kvm_vcpu *vcpu)
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	u64 global_status, toggle;
 
Quoted 14 lines

arch/x86/kvm/vmx/pmu_intel.c static void intel_mediated_pmu_load(struct kvm_vcpu *vcpu) · line 837

Quoted 7 lines
arch/x86/kvm/vmx/pmu_intel.c +7 -0
+	/*
+	 * PERF_METRICS MSR must be restored closely after fixed counter 3,
+	 * which was just restored by kvm_pmu_load_guest_pmcs().
+	 */
+	if (vcpu_has_perf_metrics(vcpu))
+		wrmsrq(MSR_PERF_METRICS, pmu->perf_metrics);
+

[Severity: High]
If the guest is configured without PERF_CAP_PERF_METRICS but with mediated PMU enabled, RDPMC exiting might be disabled. Since intel_mediated_pmu_load() skips writing to MSR_PERF_METRICS in this case, could the guest execute RDPMC and read the un-scrubbed host metrics, leaking host microarchitectural state?

You are right. RDPMC exiting needs to be disabled in this case.

Quoted 15 lines
Quoted 14 lines
arch/x86/kvm/vmx/pmu_intel.c +6 -0
 	rdmsrq(MSR_CORE_PERF_GLOBAL_STATUS, global_status);
 	toggle = pmu->global_status ^ global_status;
 	if (global_status & toggle)
@@ -831,6 +863,12 @@ static void intel_mediated_pmu_put(struct kvm_vcpu *vcpu)
 	 */
 	if (pmu->fixed_ctr_ctrl_hw)
 		wrmsrq(MSR_CORE_PERF_FIXED_CTR_CTRL, 0);
+
+	if (vcpu_has_perf_metrics(vcpu)) {
+		pmu->perf_metrics = rdpmc(INTEL_PMC_FIXED_RDPMC_METRICS);
+		if (pmu->perf_metrics)
+			wrmsrq(MSR_PERF_METRICS, 0);
+	}
 }
#6 lore raw

Re: [PATCH V4 3/4] KVM: x86/pmu: Support PERF_METRICS MSR in mediated vPMU

Quoted 18 lines · Zide Chen
Quoted 5 lines · On 6/22/2026 11:48 PM, [email protected] wrote:
Quoted 4 lines
arch/x86/kvm/vmx/pmu_intel.c +0 -0
index 59b7a90c79e12..2c3367f5e2dfb 100644

[ ... ]

Quoted 11 lines

arch/x86/kvm/vmx/pmu_intel.c static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) · line 352

Quoted 7 lines
arch/x86/kvm/vmx/pmu_intel.c +3 -0
@@ -345,6 +347,11 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
 		msr_info->data = pmu->fixed_ctr_ctrl;
 		break;
+	case MSR_PERF_METRICS:
+		if (!msr_info->host_initiated)
+			return 1;

[Severity: High]
If KVM needs to emulate a guest RDMSR instruction targeting MSR_PERF_METRICS, won't this unconditional return inject a #GP fault into the guest?

Quoted 2 lines

I can't think of a case that KVM needs to emulate RDMSR/WRMSR on MSR_PERF_METRICS.

If the literal emulator happens to emulate a RDMSR/WRMSR, KVM should behave correctly. Even if that weren't the case, KVM's implementation should adhere to the architecture. Assuming MSR_PERF_METRICS is read/write, KVM should emulate it as such.

author
#7 lore raw

Re: [PATCH V4 3/4] KVM: x86/pmu: Support PERF_METRICS MSR in mediated vPMU

Quoted 19 lines · Sean Christopherson
Quoted 18 lines · Zide Chen
Quoted 16 lines · On 6/22/2026 11:48 PM, [email protected] wrote:
Quoted 4 lines
arch/x86/kvm/vmx/pmu_intel.c +0 -0
index 59b7a90c79e12..2c3367f5e2dfb 100644

[ ... ]

arch/x86/kvm/vmx/pmu_intel.c static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info) · line 352

Quoted 7 lines
arch/x86/kvm/vmx/pmu_intel.c +3 -0
@@ -345,6 +347,11 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
 		msr_info->data = pmu->fixed_ctr_ctrl;
 		break;
+	case MSR_PERF_METRICS:
+		if (!msr_info->host_initiated)
+			return 1;

[Severity: High]
If KVM needs to emulate a guest RDMSR instruction targeting MSR_PERF_METRICS, won't this unconditional return inject a #GP fault into the guest?

Quoted 7 lines
Quoted 2 lines

I can't think of a case that KVM needs to emulate RDMSR/WRMSR on MSR_PERF_METRICS.

If the literal emulator happens to emulate a RDMSR/WRMSR, KVM should behave correctly. Even if that weren't the case, KVM's implementation should adhere to the architecture. Assuming MSR_PERF_METRICS is read/write, KVM should emulate it as such.

Thanks! I can remove these from {get_set}_msr() handlers.

if (!msr_info->host_initiated)

	return 1;
#8 lore raw

Re: [PATCH V4 3/4] KVM: x86/pmu: Support PERF_METRICS MSR in mediated vPMU

In reply to Zide Chen
Quoted 139 lines · Zide Chen

From: Dapeng Mi <[email protected]>

Bit 15 in IA32_PERF_CAPABILITIES indicates that the CPU provides built-in support for Topdown Microarchitecture Analysis (TMA) L1 metrics via the IA32_PERF_METRICS MSR.

Expose this capability only when mediated vPMU is enabled, as emulating IA32_PERF_METRICS in the legacy vPMU model is impractical.

Pass IA32_PERF_METRICS through to the guest only when mediated vPMU is enabled and bit 15 is set in guest IA32_PERF_CAPABILITIES. Allow kvm_pmu_{get,set}_msr() to handle this MSR for host accesses.

Save and restore this MSR on host/guest PMU context switches so that host PMU activity does not clobber the guest value, and guest state is not leaked into the host.

---
v4:
- Remove WARN_ON_ONCE() and simply reject the guest accesses by checking host_initiated. (Sashiko)
- Passthru MSR_PERF_METRICS only if has_mediated_pmu is true. (Sashiko)
- Remove the redundant !! in vcpu_has_perf_metrics().
v3:
- Replace WARN_ON() with WARN_ON_ONCE(). (Dapeng)
- Add comments to explain why don't validate writes on PERF_METRICS.

---
 arch/x86/include/asm/kvm_host.h   |  1 +
 arch/x86/include/asm/msr-index.h  |  1 +
 arch/x86/include/asm/perf_event.h |  1 +
 arch/x86/kvm/vmx/pmu_intel.c      | 38 +++++++++++++++++++++++++++++++
 arch/x86/kvm/vmx/pmu_intel.h      |  5 ++++
 arch/x86/kvm/vmx/vmx.c            |  7 ++++++
 arch/x86/kvm/x86.c                |  6 ++++-
 7 files changed, 58 insertions(+), 1 deletion(-)
arch/x86/include/asm/kvm_host.h +1 -0
index edd414f8ee95..4f549ef012d2 100644
@@ -594,6 +594,7 @@ struct kvm_pmu {
 	u64 global_status_rsvd;
 	u64 reserved_bits;
 	u64 raw_event_mask;
+	u64 perf_metrics;
 	struct kvm_pmc gp_counters[KVM_MAX_NR_GP_COUNTERS];
 	struct kvm_pmc fixed_counters[KVM_MAX_NR_FIXED_COUNTERS];
 
arch/x86/include/asm/msr-index.h +1 -0
index 18c4be75e927..fdcaeb6c8352 100644
@@ -331,6 +331,7 @@
 #define PERF_CAP_PEBS_FORMAT		0xf00
 #define PERF_CAP_FW_WRITES		BIT_ULL(13)
 #define PERF_CAP_PEBS_BASELINE		BIT_ULL(14)
+#define PERF_CAP_PERF_METRICS		BIT_ULL(15)
 #define PERF_CAP_PEBS_TIMING_INFO	BIT_ULL(17)
 #define PERF_CAP_PEBS_MASK		(PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \
 					 PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE | \
arch/x86/include/asm/perf_event.h +1 -0
index 1eb13673e889..bc2e1cbcd9b9 100644
@@ -447,6 +447,7 @@ static inline bool is_topdown_idx(int idx)
 #define GLOBAL_STATUS_ARCH_PEBS_THRESHOLD_BIT	54
 #define GLOBAL_STATUS_ARCH_PEBS_THRESHOLD	BIT_ULL(GLOBAL_STATUS_ARCH_PEBS_THRESHOLD_BIT)
 #define GLOBAL_STATUS_PERF_METRICS_OVF_BIT	48
+#define GLOBAL_STATUS_PERF_METRICS_OVF		BIT_ULL(GLOBAL_STATUS_PERF_METRICS_OVF_BIT)
 
 #define GLOBAL_CTRL_EN_PERF_METRICS		BIT_ULL(48)
 /*
arch/x86/kvm/vmx/pmu_intel.c +25 -0
index 59b7a90c79e1..2c3367f5e2df 100644
@@ -188,6 +188,8 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 	switch (msr) {
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
 		return kvm_pmu_has_perf_global_ctrl(pmu);
+	case MSR_PERF_METRICS:
+		return vcpu_has_perf_metrics(vcpu);
 	case MSR_IA32_PEBS_ENABLE:
 		ret = vcpu_get_perf_capabilities(vcpu) & PERF_CAP_PEBS_FORMAT;
 		break;
@@ -345,6 +347,11 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
 		msr_info->data = pmu->fixed_ctr_ctrl;
 		break;
+	case MSR_PERF_METRICS:
+		if (!msr_info->host_initiated)
+			return 1;
+		msr_info->data = pmu->perf_metrics;
+		break;
 	case MSR_IA32_PEBS_ENABLE:
 		msr_info->data = pmu->pebs_enable;
 		break;
@@ -394,6 +401,16 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (pmu->fixed_ctr_ctrl != data)
 			reprogram_fixed_counters(pmu, data);
 		break;
+	case MSR_PERF_METRICS:
+		if (!msr_info->host_initiated)
+			return 1;
+
+		/*
+		 * If TMA level 2 is not supported, bits [63:32] are reserved
+		 * and ignored on write, so no validation is needed here.
+		 */
+		pmu->perf_metrics = data;
+		break;
 	case MSR_IA32_PEBS_ENABLE:
 		if (data & pmu->pebs_enable_rsvd)
 			return 1;
@@ -589,6 +606,11 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 		pmu->global_status_rsvd &=
 				~MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI;
 
+	if (perf_capabilities & PERF_CAP_PERF_METRICS) {
+		pmu->global_ctrl_rsvd &= ~GLOBAL_CTRL_EN_PERF_METRICS;
+		pmu->global_status_rsvd &= ~GLOBAL_STATUS_PERF_METRICS_OVF;
+	}
+
 	if (perf_capabilities & PERF_CAP_PEBS_FORMAT) {
 		if (perf_capabilities & PERF_CAP_PEBS_BASELINE) {
 			pmu->pebs_enable_rsvd = counter_rsvd;
@@ -632,6 +654,9 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
 
 static void intel_pmu_reset(struct kvm_vcpu *vcpu)
 {
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+	pmu->perf_metrics = 0;
 	intel_pmu_release_guest_lbr_event(vcpu);
 }
 

arch/x86/kvm/vmx/pmu_intel.c static void intel_mediated_pmu_load(struct kvm_vcpu *vcpu) · line 836

Quoted 9 lines
arch/x86/kvm/vmx/pmu_intel.c +6 -0
@@ -803,6 +828,13 @@ static void intel_mediated_pmu_load(struct kvm_vcpu *vcpu)
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	u64 global_status, toggle;
 
+	/*
+	 * PERF_METRICS MSR must be restored closely after fixed counter 3,
+	 * which was just restored by kvm_pmu_load_guest_pmcs().
+	 */
+	if (vcpu_has_perf_metrics(vcpu))
+		wrmsrq(MSR_PERF_METRICS, pmu->perf_metrics);

Copy Sashiko's comments here.

"

[Severity: High]
If the guest is configured without PERF_CAP_PERF_METRICS but with mediated PMU enabled, RDPMC exiting might be disabled. Since intel_mediated_pmu_load() skips writing to MSR_PERF_METRICS in this case, could the guest execute RDPMC and read the un-scrubbed host metrics, leaking host microarchitectural state?

"

This is a real concern. Besides MSR interception, we need to care about the rdpmc interception. When the guest has different configuration on perf metrics with host, rdpmc needs to be intercepted. Thanks.

Quoted 80 lines
arch/x86/kvm/vmx/pmu_intel.c +7 -0
+
 	rdmsrq(MSR_CORE_PERF_GLOBAL_STATUS, global_status);
 	toggle = pmu->global_status ^ global_status;
 	if (global_status & toggle)
@@ -831,6 +863,12 @@ static void intel_mediated_pmu_put(struct kvm_vcpu *vcpu)
 	 */
 	if (pmu->fixed_ctr_ctrl_hw)
 		wrmsrq(MSR_CORE_PERF_FIXED_CTR_CTRL, 0);
+
+	if (vcpu_has_perf_metrics(vcpu)) {
+		pmu->perf_metrics = rdpmc(INTEL_PMC_FIXED_RDPMC_METRICS);
+		if (pmu->perf_metrics)
+			wrmsrq(MSR_PERF_METRICS, 0);
+	}
 }
 
 struct kvm_pmu_ops intel_pmu_ops __initdata = {
arch/x86/kvm/vmx/pmu_intel.h +5 -0
index 5d9357640aa1..57705773dc49 100644
@@ -40,4 +40,9 @@ struct lbr_desc {
 
 extern struct x86_pmu_lbr vmx_lbr_caps;
 
+static inline bool vcpu_has_perf_metrics(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_perf_capabilities(vcpu) & PERF_CAP_PERF_METRICS;
+}
+
 #endif /* __KVM_X86_VMX_PMU_INTEL_H */
arch/x86/kvm/vmx/vmx.c +7 -0
index a1a5edb39a7e..584d99ef6026 100644
@@ -4260,6 +4260,10 @@ static void vmx_recalc_pmu_msr_intercepts(struct kvm_vcpu *vcpu)
 				  MSR_TYPE_RW, intercept);
 	vmx_set_intercept_for_msr(vcpu, MSR_CORE_PERF_GLOBAL_OVF_CTRL,
 				  MSR_TYPE_RW, intercept);
+
+	intercept = !has_mediated_pmu || !vcpu_has_perf_metrics(vcpu);
+	vmx_set_intercept_for_msr(vcpu, MSR_PERF_METRICS,
+				  MSR_TYPE_RW, intercept);
 }
 
 static void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
@@ -8084,6 +8088,9 @@ static __init u64 vmx_get_perf_capabilities(void)
 		perf_cap &= ~PERF_CAP_PEBS_BASELINE;
 	}
 
+	if (enable_mediated_pmu)
+		perf_cap |= host_perf_cap & PERF_CAP_PERF_METRICS;
+
 	return perf_cap;
 }
 
arch/x86/kvm/x86.c +5 -1
index e872398c12fc..9623f558f359 100644
@@ -352,7 +352,7 @@ static const u32 msrs_to_save_pmu[] = {
 	MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1,
 	MSR_ARCH_PERFMON_FIXED_CTR2, MSR_ARCH_PERFMON_FIXED_CTR3,
 	MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS,
-	MSR_CORE_PERF_GLOBAL_CTRL,
+	MSR_CORE_PERF_GLOBAL_CTRL, MSR_PERF_METRICS,
 	MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG,
 
 	/* This part of MSRs should match KVM_MAX_NR_INTEL_GP_COUNTERS. */
@@ -7679,6 +7679,10 @@ static void kvm_probe_msr_to_save(u32 msr_index)
 		     intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2))
 			return;
 		break;
+	case MSR_PERF_METRICS:
+		if (!(kvm_caps.supported_perf_cap & PERF_CAP_PERF_METRICS))
+			return;
+		break;
 	case MSR_ARCH_PERFMON_PERFCTR0 ...
 	     MSR_ARCH_PERFMON_PERFCTR0 + KVM_MAX_NR_GP_COUNTERS - 1:
 		if (msr_index - MSR_ARCH_PERFMON_PERFCTR0 >=
author
#9 lore raw

Re: [PATCH V4 3/4] KVM: x86/pmu: Support PERF_METRICS MSR in mediated vPMU

Quoted 162 lines · Dapeng
Quoted 139 lines · Zide Chen

From: Dapeng Mi <[email protected]>

Bit 15 in IA32_PERF_CAPABILITIES indicates that the CPU provides built-in support for Topdown Microarchitecture Analysis (TMA) L1 metrics via the IA32_PERF_METRICS MSR.

Expose this capability only when mediated vPMU is enabled, as emulating IA32_PERF_METRICS in the legacy vPMU model is impractical.

Pass IA32_PERF_METRICS through to the guest only when mediated vPMU is enabled and bit 15 is set in guest IA32_PERF_CAPABILITIES. Allow kvm_pmu_{get,set}_msr() to handle this MSR for host accesses.

Save and restore this MSR on host/guest PMU context switches so that host PMU activity does not clobber the guest value, and guest state is not leaked into the host.

---
v4:
- Remove WARN_ON_ONCE() and simply reject the guest accesses by checking host_initiated. (Sashiko)
- Passthru MSR_PERF_METRICS only if has_mediated_pmu is true. (Sashiko)
- Remove the redundant !! in vcpu_has_perf_metrics().
v3:
- Replace WARN_ON() with WARN_ON_ONCE(). (Dapeng)
- Add comments to explain why don't validate writes on PERF_METRICS.

---
 arch/x86/include/asm/kvm_host.h   |  1 +
 arch/x86/include/asm/msr-index.h  |  1 +
 arch/x86/include/asm/perf_event.h |  1 +
 arch/x86/kvm/vmx/pmu_intel.c      | 38 +++++++++++++++++++++++++++++++
 arch/x86/kvm/vmx/pmu_intel.h      |  5 ++++
 arch/x86/kvm/vmx/vmx.c            |  7 ++++++
 arch/x86/kvm/x86.c                |  6 ++++-
 7 files changed, 58 insertions(+), 1 deletion(-)
arch/x86/include/asm/kvm_host.h +1 -0
index edd414f8ee95..4f549ef012d2 100644
@@ -594,6 +594,7 @@ struct kvm_pmu {
 	u64 global_status_rsvd;
 	u64 reserved_bits;
 	u64 raw_event_mask;
+	u64 perf_metrics;
 	struct kvm_pmc gp_counters[KVM_MAX_NR_GP_COUNTERS];
 	struct kvm_pmc fixed_counters[KVM_MAX_NR_FIXED_COUNTERS];
 
arch/x86/include/asm/msr-index.h +1 -0
index 18c4be75e927..fdcaeb6c8352 100644
@@ -331,6 +331,7 @@
 #define PERF_CAP_PEBS_FORMAT		0xf00
 #define PERF_CAP_FW_WRITES		BIT_ULL(13)
 #define PERF_CAP_PEBS_BASELINE		BIT_ULL(14)
+#define PERF_CAP_PERF_METRICS		BIT_ULL(15)
 #define PERF_CAP_PEBS_TIMING_INFO	BIT_ULL(17)
 #define PERF_CAP_PEBS_MASK		(PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \
 					 PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE | \
arch/x86/include/asm/perf_event.h +1 -0
index 1eb13673e889..bc2e1cbcd9b9 100644
@@ -447,6 +447,7 @@ static inline bool is_topdown_idx(int idx)
 #define GLOBAL_STATUS_ARCH_PEBS_THRESHOLD_BIT	54
 #define GLOBAL_STATUS_ARCH_PEBS_THRESHOLD	BIT_ULL(GLOBAL_STATUS_ARCH_PEBS_THRESHOLD_BIT)
 #define GLOBAL_STATUS_PERF_METRICS_OVF_BIT	48
+#define GLOBAL_STATUS_PERF_METRICS_OVF		BIT_ULL(GLOBAL_STATUS_PERF_METRICS_OVF_BIT)
 
 #define GLOBAL_CTRL_EN_PERF_METRICS		BIT_ULL(48)
 /*
arch/x86/kvm/vmx/pmu_intel.c +25 -0
index 59b7a90c79e1..2c3367f5e2df 100644
@@ -188,6 +188,8 @@ static bool intel_is_valid_msr(struct kvm_vcpu *vcpu, u32 msr)
 	switch (msr) {
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
 		return kvm_pmu_has_perf_global_ctrl(pmu);
+	case MSR_PERF_METRICS:
+		return vcpu_has_perf_metrics(vcpu);
 	case MSR_IA32_PEBS_ENABLE:
 		ret = vcpu_get_perf_capabilities(vcpu) & PERF_CAP_PEBS_FORMAT;
 		break;
@@ -345,6 +347,11 @@ static int intel_pmu_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
 		msr_info->data = pmu->fixed_ctr_ctrl;
 		break;
+	case MSR_PERF_METRICS:
+		if (!msr_info->host_initiated)
+			return 1;
+		msr_info->data = pmu->perf_metrics;
+		break;
 	case MSR_IA32_PEBS_ENABLE:
 		msr_info->data = pmu->pebs_enable;
 		break;
@@ -394,6 +401,16 @@ static int intel_pmu_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		if (pmu->fixed_ctr_ctrl != data)
 			reprogram_fixed_counters(pmu, data);
 		break;
+	case MSR_PERF_METRICS:
+		if (!msr_info->host_initiated)
+			return 1;
+
+		/*
+		 * If TMA level 2 is not supported, bits [63:32] are reserved
+		 * and ignored on write, so no validation is needed here.
+		 */
+		pmu->perf_metrics = data;
+		break;
 	case MSR_IA32_PEBS_ENABLE:
 		if (data & pmu->pebs_enable_rsvd)
 			return 1;
@@ -589,6 +606,11 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
 		pmu->global_status_rsvd &=
 				~MSR_CORE_PERF_GLOBAL_OVF_CTRL_TRACE_TOPA_PMI;
 
+	if (perf_capabilities & PERF_CAP_PERF_METRICS) {
+		pmu->global_ctrl_rsvd &= ~GLOBAL_CTRL_EN_PERF_METRICS;
+		pmu->global_status_rsvd &= ~GLOBAL_STATUS_PERF_METRICS_OVF;
+	}
+
 	if (perf_capabilities & PERF_CAP_PEBS_FORMAT) {
 		if (perf_capabilities & PERF_CAP_PEBS_BASELINE) {
 			pmu->pebs_enable_rsvd = counter_rsvd;
@@ -632,6 +654,9 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
 
 static void intel_pmu_reset(struct kvm_vcpu *vcpu)
 {
+	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
+
+	pmu->perf_metrics = 0;
 	intel_pmu_release_guest_lbr_event(vcpu);
 }
 

arch/x86/kvm/vmx/pmu_intel.c static void intel_mediated_pmu_load(struct kvm_vcpu *vcpu) · line 836

Quoted 9 lines
arch/x86/kvm/vmx/pmu_intel.c +6 -0
@@ -803,6 +828,13 @@ static void intel_mediated_pmu_load(struct kvm_vcpu *vcpu)
 	struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
 	u64 global_status, toggle;
 
+	/*
+	 * PERF_METRICS MSR must be restored closely after fixed counter 3,
+	 * which was just restored by kvm_pmu_load_guest_pmcs().
+	 */
+	if (vcpu_has_perf_metrics(vcpu))
+		wrmsrq(MSR_PERF_METRICS, pmu->perf_metrics);

Copy Sashiko's comments here.

"

[Severity: High]
If the guest is configured without PERF_CAP_PERF_METRICS but with mediated PMU enabled, RDPMC exiting might be disabled. Since intel_mediated_pmu_load() skips writing to MSR_PERF_METRICS in this case, could the guest execute RDPMC and read the un-scrubbed host metrics, leaking host microarchitectural state?

Quoted 5 lines

"

This is a real concern. Besides MSR interception, we need to care about the rdpmc interception. When the guest has different configuration on perf metrics with host, rdpmc needs to be intercepted. Thanks.

Yes, my bad! This actuallly was in the initial implementation.

Quoted 81 lines
Quoted 80 lines
arch/x86/kvm/vmx/pmu_intel.c +7 -0
+
 	rdmsrq(MSR_CORE_PERF_GLOBAL_STATUS, global_status);
 	toggle = pmu->global_status ^ global_status;
 	if (global_status & toggle)
@@ -831,6 +863,12 @@ static void intel_mediated_pmu_put(struct kvm_vcpu *vcpu)
 	 */
 	if (pmu->fixed_ctr_ctrl_hw)
 		wrmsrq(MSR_CORE_PERF_FIXED_CTR_CTRL, 0);
+
+	if (vcpu_has_perf_metrics(vcpu)) {
+		pmu->perf_metrics = rdpmc(INTEL_PMC_FIXED_RDPMC_METRICS);
+		if (pmu->perf_metrics)
+			wrmsrq(MSR_PERF_METRICS, 0);
+	}
 }
 
 struct kvm_pmu_ops intel_pmu_ops __initdata = {
arch/x86/kvm/vmx/pmu_intel.h +5 -0
index 5d9357640aa1..57705773dc49 100644
@@ -40,4 +40,9 @@ struct lbr_desc {
 
 extern struct x86_pmu_lbr vmx_lbr_caps;
 
+static inline bool vcpu_has_perf_metrics(struct kvm_vcpu *vcpu)
+{
+	return vcpu_get_perf_capabilities(vcpu) & PERF_CAP_PERF_METRICS;
+}
+
 #endif /* __KVM_X86_VMX_PMU_INTEL_H */
arch/x86/kvm/vmx/vmx.c +7 -0
index a1a5edb39a7e..584d99ef6026 100644
@@ -4260,6 +4260,10 @@ static void vmx_recalc_pmu_msr_intercepts(struct kvm_vcpu *vcpu)
 				  MSR_TYPE_RW, intercept);
 	vmx_set_intercept_for_msr(vcpu, MSR_CORE_PERF_GLOBAL_OVF_CTRL,
 				  MSR_TYPE_RW, intercept);
+
+	intercept = !has_mediated_pmu || !vcpu_has_perf_metrics(vcpu);
+	vmx_set_intercept_for_msr(vcpu, MSR_PERF_METRICS,
+				  MSR_TYPE_RW, intercept);
 }
 
 static void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
@@ -8084,6 +8088,9 @@ static __init u64 vmx_get_perf_capabilities(void)
 		perf_cap &= ~PERF_CAP_PEBS_BASELINE;
 	}
 
+	if (enable_mediated_pmu)
+		perf_cap |= host_perf_cap & PERF_CAP_PERF_METRICS;
+
 	return perf_cap;
 }
 
arch/x86/kvm/x86.c +5 -1
index e872398c12fc..9623f558f359 100644
@@ -352,7 +352,7 @@ static const u32 msrs_to_save_pmu[] = {
 	MSR_ARCH_PERFMON_FIXED_CTR0, MSR_ARCH_PERFMON_FIXED_CTR1,
 	MSR_ARCH_PERFMON_FIXED_CTR2, MSR_ARCH_PERFMON_FIXED_CTR3,
 	MSR_CORE_PERF_FIXED_CTR_CTRL, MSR_CORE_PERF_GLOBAL_STATUS,
-	MSR_CORE_PERF_GLOBAL_CTRL,
+	MSR_CORE_PERF_GLOBAL_CTRL, MSR_PERF_METRICS,
 	MSR_IA32_PEBS_ENABLE, MSR_IA32_DS_AREA, MSR_PEBS_DATA_CFG,
 
 	/* This part of MSRs should match KVM_MAX_NR_INTEL_GP_COUNTERS. */
@@ -7679,6 +7679,10 @@ static void kvm_probe_msr_to_save(u32 msr_index)
 		     intel_pt_validate_hw_cap(PT_CAP_num_address_ranges) * 2))
 			return;
 		break;
+	case MSR_PERF_METRICS:
+		if (!(kvm_caps.supported_perf_cap & PERF_CAP_PERF_METRICS))
+			return;
+		break;
 	case MSR_ARCH_PERFMON_PERFCTR0 ...
 	     MSR_ARCH_PERFMON_PERFCTR0 + KVM_MAX_NR_GP_COUNTERS - 1:
 		if (msr_index - MSR_ARCH_PERFMON_PERFCTR0 >=
author
#10 lore raw

PATCH v4 4/4 KVM: selftests: Add perf_metrics and fixed counter 3 tests

In reply to Zide Chen

Add a selftest to exercise IA32_PERF_METRICS, i.e. architectural support for Topdown (TMA) Level 1 metrics, enumerated by IA32_PERF_CAPABILITIES[15].

Only check for non-zero metrics, as they are derived and depend on the workload, CPU model, and host scheduling, making precise expectations fragile.

Extend the PMU selftest to cover Intel fixed counter 3 by bumping MAX_NR_FIXED_COUNTERS to 4 and validating basic functionality.

---
v3:
- Slightly reword comment to explain the sum of topdown metrics is close to 100%.
- Change abs() with explicit bounds (sum >= 0xfd && sum <= 0x102) for better readability.
v2:
- New patch.
---

---
 tools/arch/x86/include/asm/msr-index.h        |  1 +
 tools/testing/selftests/kvm/include/x86/pmu.h |  3 +
 .../selftests/kvm/x86/pmu_counters_test.c     | 72 +++++++++++++++++--
 3 files changed, 71 insertions(+), 5 deletions(-)
tools/arch/x86/include/asm/msr-index.h +1 -0
index eff29645719b..e7745e2cd543 100644
@@ -331,6 +331,7 @@
 #define PERF_CAP_PEBS_FORMAT		0xf00
 #define PERF_CAP_FW_WRITES		BIT_ULL(13)
 #define PERF_CAP_PEBS_BASELINE		BIT_ULL(14)
+#define PERF_CAP_PERF_METRICS		BIT_ULL(15)
 #define PERF_CAP_PEBS_TIMING_INFO	BIT_ULL(17)
 #define PERF_CAP_PEBS_MASK		(PERF_CAP_PEBS_TRAP | PERF_CAP_ARCH_REG | \
 					 PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE | \
tools/testing/selftests/kvm/include/x86/pmu.h +3 -0
index 608ed83d7c6a..6c19503e0bb7 100644
@@ -52,6 +52,9 @@
 /* Fixed PMC controls, Intel only. */
 #define FIXED_PMC_GLOBAL_CTRL_ENABLE(_idx)	BIT_ULL((32 + (_idx)))
 
+/* PERF_METRICS enable, Intel only. */
+#define PERF_METRICS_GLOBAL_CTRL_ENABLE		BIT_ULL(48)
+
 #define FIXED_PMC_KERNEL			BIT_ULL(0)
 #define FIXED_PMC_USER				BIT_ULL(1)
 #define FIXED_PMC_ANYTHREAD			BIT_ULL(2)
tools/testing/selftests/kvm/x86/pmu_counters_test.c +67 -5

127 lines not on this page · raw message

Signature · 1 line
2.54.0
#11 lore raw

Re: [PATCH V4 4/4] KVM: selftests: Add perf_metrics and fixed counter 3 tests

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider: - [High] KVM's emulator unconditionally injects a #GP on guest accesses to MSR_PERF_METRICS, breaking…

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] KVM's emulator unconditionally injects a #GP on guest accesses to MSR_PERF_METRICS, breaking instruction emulation and nested virtualization. The selftest omits forced emulation coverage that would expose this. --

commit f588cce382d8777ebda7951bd3447ee7ba4c18ff
Author: Zide Chen <[email protected]>

KVM: selftests: Add perf_metrics and fixed counter 3 tests

Add a selftest to exercise IA32_PERF_METRICS, i.e. architectural support for Topdown (TMA) Level 1 metrics, enumerated by IA32_PERF_CAPABILITIES[15].

Quoted 4 lines
tools/testing/selftests/kvm/x86/pmu_counters_test.c +0 -0
index dc6afac3aa919..d4688a7d1e556 100644

[ ... ]

Quoted 6 lines
tools/testing/selftests/kvm/x86/pmu_counters_test.c +2 -0
@@ -318,6 +322,56 @@ static void guest_test_arch_event(u8 idx)
 				FIXED_PMC_GLOBAL_CTRL_ENABLE(i));
 }
 
+static void guest_test_perf_metrics(void)
+{

[ ... ]

tools/testing/selftests/kvm/x86/pmu_counters_test.c static void guest_test_arch_event(u8 idx) · line 373

Quoted 7 lines
tools/testing/selftests/kvm/x86/pmu_counters_test.c +7 -0
+	/* Sanity check after PERF_METRICS disabled. */
+	__asm__ __volatile__("loop ." : "+c"((int){NUM_LOOPS}));
+	GUEST_ASSERT_EQ(rdmsr(MSR_PERF_METRICS), metrics);
+	wrmsr(MSR_PERF_METRICS, 0xdeaddead);
+
+	GUEST_ASSERT_EQ(rdmsr(MSR_PERF_METRICS), 0xdeaddead);
+}

[Severity: High]
Should this test include forced emulation (e.g., using KVM_FEP) coverage for these MSR_PERF_METRICS accesses?

Currently, the selftest relies purely on native rdmsr/wrmsr execution. If these instructions were emulated, it would expose an issue in intel_pmu_get_msr() and intel_pmu_set_msr() where KVM's emulator unconditionally injects a #GP on guest accesses because they return 1 when !msr_info->host_initiated.

Could we add forced emulation coverage to catch emulator issues that break instruction emulation and nested virtualization?

Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=4