* [PATCH 1/3] KVM: Selftests: Validate more arch-events in pmu_counters_test
2025-07-12 17:25 [PATCH 0/3] Fix PMU kselftests errors on SRF and CWF Dapeng Mi
@ 2025-07-12 17:25 ` Dapeng Mi
2025-07-12 17:25 ` [PATCH 2/3] KVM: selftests: Relax precise event count validation as overcount issue Dapeng Mi
2025-07-12 17:25 ` [PATCH 3/3] KVM: selftests: Relax branches event count check for event_filter test Dapeng Mi
2 siblings, 0 replies; 4+ messages in thread
From: Dapeng Mi @ 2025-07-12 17:25 UTC (permalink / raw)
To: Sean Christopherson, Paolo Bonzini
Cc: kvm, linux-kernel, Jim Mattson, Mingwei Zhang, Zide Chen,
Das Sandipan, Shukla Manali, Yi Lai, Dapeng Mi, Dapeng Mi
Clearwater Forest introduces 5 new architectural events (4 topdown
level 1 metrics events and LBR inserts event). This patch supports
to validate these 5 newly added events. The detailed info about these
5 events can be found in SDM section 21.2.7 "Pre-defined Architectural
Performance Events".
It becomes unrealistic to traverse all possible combinations of
unavailable events mask (may need dozens of minutes to finish all
possible combination validation). So only limit unavailable events mask
traverse to the first 8 arch-events.
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Tested-by: Yi Lai <yi1.lai@intel.com>
---
tools/testing/selftests/kvm/include/x86/pmu.h | 10 +++++++++
.../selftests/kvm/include/x86/processor.h | 7 +++++-
tools/testing/selftests/kvm/lib/x86/pmu.c | 5 +++++
.../selftests/kvm/x86/pmu_counters_test.c | 22 ++++++++++++++-----
4 files changed, 38 insertions(+), 6 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/x86/pmu.h b/tools/testing/selftests/kvm/include/x86/pmu.h
index 3c10c4dc0ae8..2aabda2da002 100644
--- a/tools/testing/selftests/kvm/include/x86/pmu.h
+++ b/tools/testing/selftests/kvm/include/x86/pmu.h
@@ -61,6 +61,11 @@
#define INTEL_ARCH_BRANCHES_RETIRED RAW_EVENT(0xc4, 0x00)
#define INTEL_ARCH_BRANCHES_MISPREDICTED RAW_EVENT(0xc5, 0x00)
#define INTEL_ARCH_TOPDOWN_SLOTS RAW_EVENT(0xa4, 0x01)
+#define INTEL_ARCH_TOPDOWN_BE_BOUND RAW_EVENT(0xa4, 0x02)
+#define INTEL_ARCH_TOPDOWN_BAD_SPEC RAW_EVENT(0x73, 0x00)
+#define INTEL_ARCH_TOPDOWN_FE_BOUND RAW_EVENT(0x9c, 0x01)
+#define INTEL_ARCH_TOPDOWN_RETIRING RAW_EVENT(0xc2, 0x02)
+#define INTEL_ARCH_LBR_INSERTS RAW_EVENT(0xe4, 0x01)
#define AMD_ZEN_CORE_CYCLES RAW_EVENT(0x76, 0x00)
#define AMD_ZEN_INSTRUCTIONS_RETIRED RAW_EVENT(0xc0, 0x00)
@@ -80,6 +85,11 @@ enum intel_pmu_architectural_events {
INTEL_ARCH_BRANCHES_RETIRED_INDEX,
INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX,
INTEL_ARCH_TOPDOWN_SLOTS_INDEX,
+ INTEL_ARCH_TOPDOWN_BE_BOUND_INDEX,
+ INTEL_ARCH_TOPDOWN_BAD_SPEC_INDEX,
+ INTEL_ARCH_TOPDOWN_FE_BOUND_INDEX,
+ INTEL_ARCH_TOPDOWN_RETIRING_INDEX,
+ INTEL_ARCH_LBR_INSERTS_INDEX,
NR_INTEL_ARCH_EVENTS,
};
diff --git a/tools/testing/selftests/kvm/include/x86/processor.h b/tools/testing/selftests/kvm/include/x86/processor.h
index 2efb05c2f2fb..232964f2a687 100644
--- a/tools/testing/selftests/kvm/include/x86/processor.h
+++ b/tools/testing/selftests/kvm/include/x86/processor.h
@@ -265,7 +265,7 @@ struct kvm_x86_cpu_property {
#define X86_PROPERTY_PMU_NR_GP_COUNTERS KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 8, 15)
#define X86_PROPERTY_PMU_GP_COUNTERS_BIT_WIDTH KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 16, 23)
#define X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH KVM_X86_CPU_PROPERTY(0xa, 0, EAX, 24, 31)
-#define X86_PROPERTY_PMU_EVENTS_MASK KVM_X86_CPU_PROPERTY(0xa, 0, EBX, 0, 7)
+#define X86_PROPERTY_PMU_EVENTS_MASK KVM_X86_CPU_PROPERTY(0xa, 0, EBX, 0, 12)
#define X86_PROPERTY_PMU_FIXED_COUNTERS_BITMASK KVM_X86_CPU_PROPERTY(0xa, 0, ECX, 0, 31)
#define X86_PROPERTY_PMU_NR_FIXED_COUNTERS KVM_X86_CPU_PROPERTY(0xa, 0, EDX, 0, 4)
#define X86_PROPERTY_PMU_FIXED_COUNTERS_BIT_WIDTH KVM_X86_CPU_PROPERTY(0xa, 0, EDX, 5, 12)
@@ -332,6 +332,11 @@ struct kvm_x86_pmu_feature {
#define X86_PMU_FEATURE_BRANCH_INSNS_RETIRED KVM_X86_PMU_FEATURE(EBX, 5)
#define X86_PMU_FEATURE_BRANCHES_MISPREDICTED KVM_X86_PMU_FEATURE(EBX, 6)
#define X86_PMU_FEATURE_TOPDOWN_SLOTS KVM_X86_PMU_FEATURE(EBX, 7)
+#define X86_PMU_FEATURE_TOPDOWN_BE_BOUND KVM_X86_PMU_FEATURE(EBX, 8)
+#define X86_PMU_FEATURE_TOPDOWN_BAD_SPEC KVM_X86_PMU_FEATURE(EBX, 9)
+#define X86_PMU_FEATURE_TOPDOWN_FE_BOUND KVM_X86_PMU_FEATURE(EBX, 10)
+#define X86_PMU_FEATURE_TOPDOWN_RETIRING KVM_X86_PMU_FEATURE(EBX, 11)
+#define X86_PMU_FEATURE_LBR_INSERTS KVM_X86_PMU_FEATURE(EBX, 12)
#define X86_PMU_FEATURE_INSNS_RETIRED_FIXED KVM_X86_PMU_FEATURE(ECX, 0)
#define X86_PMU_FEATURE_CPU_CYCLES_FIXED KVM_X86_PMU_FEATURE(ECX, 1)
diff --git a/tools/testing/selftests/kvm/lib/x86/pmu.c b/tools/testing/selftests/kvm/lib/x86/pmu.c
index f31f0427c17c..5ab44bf54773 100644
--- a/tools/testing/selftests/kvm/lib/x86/pmu.c
+++ b/tools/testing/selftests/kvm/lib/x86/pmu.c
@@ -19,6 +19,11 @@ const uint64_t intel_pmu_arch_events[] = {
INTEL_ARCH_BRANCHES_RETIRED,
INTEL_ARCH_BRANCHES_MISPREDICTED,
INTEL_ARCH_TOPDOWN_SLOTS,
+ INTEL_ARCH_TOPDOWN_BE_BOUND,
+ INTEL_ARCH_TOPDOWN_BAD_SPEC,
+ INTEL_ARCH_TOPDOWN_FE_BOUND,
+ INTEL_ARCH_TOPDOWN_RETIRING,
+ INTEL_ARCH_LBR_INSERTS,
};
kvm_static_assert(ARRAY_SIZE(intel_pmu_arch_events) == NR_INTEL_ARCH_EVENTS);
diff --git a/tools/testing/selftests/kvm/x86/pmu_counters_test.c b/tools/testing/selftests/kvm/x86/pmu_counters_test.c
index 8aaaf25b6111..342a72420177 100644
--- a/tools/testing/selftests/kvm/x86/pmu_counters_test.c
+++ b/tools/testing/selftests/kvm/x86/pmu_counters_test.c
@@ -75,6 +75,11 @@ static struct kvm_intel_pmu_event intel_event_to_feature(uint8_t idx)
[INTEL_ARCH_BRANCHES_RETIRED_INDEX] = { X86_PMU_FEATURE_BRANCH_INSNS_RETIRED, X86_PMU_FEATURE_NULL },
[INTEL_ARCH_BRANCHES_MISPREDICTED_INDEX] = { X86_PMU_FEATURE_BRANCHES_MISPREDICTED, X86_PMU_FEATURE_NULL },
[INTEL_ARCH_TOPDOWN_SLOTS_INDEX] = { X86_PMU_FEATURE_TOPDOWN_SLOTS, X86_PMU_FEATURE_TOPDOWN_SLOTS_FIXED },
+ [INTEL_ARCH_TOPDOWN_BE_BOUND_INDEX] = { X86_PMU_FEATURE_TOPDOWN_BE_BOUND, X86_PMU_FEATURE_NULL },
+ [INTEL_ARCH_TOPDOWN_BAD_SPEC_INDEX] = { X86_PMU_FEATURE_TOPDOWN_BAD_SPEC, X86_PMU_FEATURE_NULL },
+ [INTEL_ARCH_TOPDOWN_FE_BOUND_INDEX] = { X86_PMU_FEATURE_TOPDOWN_FE_BOUND, X86_PMU_FEATURE_NULL },
+ [INTEL_ARCH_TOPDOWN_RETIRING_INDEX] = { X86_PMU_FEATURE_TOPDOWN_RETIRING, X86_PMU_FEATURE_NULL },
+ [INTEL_ARCH_LBR_INSERTS_INDEX] = { X86_PMU_FEATURE_LBR_INSERTS, X86_PMU_FEATURE_NULL },
};
kvm_static_assert(ARRAY_SIZE(__intel_event_to_feature) == NR_INTEL_ARCH_EVENTS);
@@ -171,9 +176,12 @@ static void guest_assert_event_count(uint8_t idx, uint32_t pmc, uint32_t pmc_msr
fallthrough;
case INTEL_ARCH_CPU_CYCLES_INDEX:
case INTEL_ARCH_REFERENCE_CYCLES_INDEX:
+ case INTEL_ARCH_TOPDOWN_BE_BOUND_INDEX:
+ case INTEL_ARCH_TOPDOWN_FE_BOUND_INDEX:
GUEST_ASSERT_NE(count, 0);
break;
case INTEL_ARCH_TOPDOWN_SLOTS_INDEX:
+ case INTEL_ARCH_TOPDOWN_RETIRING_INDEX:
__GUEST_ASSERT(count >= NUM_INSNS_RETIRED,
"Expected top-down slots >= %u, got count = %lu",
NUM_INSNS_RETIRED, count);
@@ -612,15 +620,19 @@ static void test_intel_counters(void)
pr_info("Testing arch events, PMU version %u, perf_caps = %lx\n",
v, perf_caps[i]);
/*
- * To keep the total runtime reasonable, test every
- * possible non-zero, non-reserved bitmap combination
- * only with the native PMU version and the full bit
- * vector length.
+ * To keep the total runtime reasonable, especially after
+ * the total number of arch-events increasing to 13, It's
+ * impossible to test every possible non-zero, non-reserved
+ * bitmap combination. Only test the first 8-bits combination
+ * with the native PMU version and the full bit vector length.
*/
if (v == pmu_version) {
- for (k = 1; k < (BIT(NR_INTEL_ARCH_EVENTS) - 1); k++)
+ int max_events = min(NR_INTEL_ARCH_EVENTS, 8);
+
+ for (k = 1; k < (BIT(max_events) - 1); k++)
test_arch_events(v, perf_caps[i], NR_INTEL_ARCH_EVENTS, k);
}
+
/*
* Test single bits for all PMU version and lengths up
* the number of events +1 (to verify KVM doesn't do
--
2.43.0
^ permalink raw reply [flat|nested] 4+ messages in thread* [PATCH 2/3] KVM: selftests: Relax precise event count validation as overcount issue
2025-07-12 17:25 [PATCH 0/3] Fix PMU kselftests errors on SRF and CWF Dapeng Mi
2025-07-12 17:25 ` [PATCH 1/3] KVM: Selftests: Validate more arch-events in pmu_counters_test Dapeng Mi
@ 2025-07-12 17:25 ` Dapeng Mi
2025-07-12 17:25 ` [PATCH 3/3] KVM: selftests: Relax branches event count check for event_filter test Dapeng Mi
2 siblings, 0 replies; 4+ messages in thread
From: Dapeng Mi @ 2025-07-12 17:25 UTC (permalink / raw)
To: Sean Christopherson, Paolo Bonzini
Cc: kvm, linux-kernel, Jim Mattson, Mingwei Zhang, Zide Chen,
Das Sandipan, Shukla Manali, Yi Lai, Dapeng Mi, dongsheng,
Dapeng Mi
From: dongsheng <dongsheng.x.zhang@intel.com>
For Intel Atom CPUs, the PMU events "Instruction Retired" or
"Branch Instruction Retired" may be overcounted for some certain
instructions, like FAR CALL/JMP, RETF, IRET, VMENTRY/VMEXIT/VMPTRLD
and complex SGX/SMX/CSTATE instructions/flows.
The detailed information can be found in the errata (section SRF7):
https://edc.intel.com/content/www/us/en/design/products-and-solutions/processors-and-chipsets/sierra-forest/xeon-6700-series-processor-with-e-cores-specification-update/errata-details/
For the Atom platforms before Sierra Forest (including Sierra Forest),
Both 2 events "Instruction Retired" and "Branch Instruction Retired" would
be overcounted on these certain instructions, but for Clearwater Forest
only "Instruction Retired" event is overcounted on these instructions.
As the overcount issue on VM-Exit/VM-Entry, it has no way to validate
the precise count for these 2 events on these affected Atom platforms,
so just relax the precise event count check for these 2 events on these
Atom platforms.
Signed-off-by: dongsheng <dongsheng.x.zhang@intel.com>
Co-developed-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Tested-by: Yi Lai <yi1.lai@intel.com>
---
tools/testing/selftests/kvm/include/x86/pmu.h | 9 +++++
tools/testing/selftests/kvm/lib/x86/pmu.c | 38 +++++++++++++++++++
.../selftests/kvm/x86/pmu_counters_test.c | 17 ++++++++-
3 files changed, 62 insertions(+), 2 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/x86/pmu.h b/tools/testing/selftests/kvm/include/x86/pmu.h
index 2aabda2da002..db14c08abc59 100644
--- a/tools/testing/selftests/kvm/include/x86/pmu.h
+++ b/tools/testing/selftests/kvm/include/x86/pmu.h
@@ -104,4 +104,13 @@ enum amd_pmu_zen_events {
extern const uint64_t intel_pmu_arch_events[];
extern const uint64_t amd_pmu_zen_events[];
+/*
+ * Flags for "Instruction Retired" and "Branch Instruction Retired"
+ * overcount flaws.
+ */
+#define INST_RETIRED_OVERCOUNT BIT(0)
+#define BR_RETIRED_OVERCOUNT BIT(1)
+
+extern uint32_t detect_inst_overcount_flags(void);
+
#endif /* SELFTEST_KVM_PMU_H */
diff --git a/tools/testing/selftests/kvm/lib/x86/pmu.c b/tools/testing/selftests/kvm/lib/x86/pmu.c
index 5ab44bf54773..fd4ed577c88f 100644
--- a/tools/testing/selftests/kvm/lib/x86/pmu.c
+++ b/tools/testing/selftests/kvm/lib/x86/pmu.c
@@ -8,6 +8,7 @@
#include <linux/kernel.h>
#include "kvm_util.h"
+#include "processor.h"
#include "pmu.h"
const uint64_t intel_pmu_arch_events[] = {
@@ -34,3 +35,40 @@ const uint64_t amd_pmu_zen_events[] = {
AMD_ZEN_BRANCHES_MISPREDICTED,
};
kvm_static_assert(ARRAY_SIZE(amd_pmu_zen_events) == NR_AMD_ZEN_EVENTS);
+
+/*
+ * For Intel Atom CPUs, the PMU events "Instruction Retired" or
+ * "Branch Instruction Retired" may be overcounted for some certain
+ * instructions, like FAR CALL/JMP, RETF, IRET, VMENTRY/VMEXIT/VMPTRLD
+ * and complex SGX/SMX/CSTATE instructions/flows.
+ *
+ * The detailed information can be found in the errata (section SRF7):
+ * https://edc.intel.com/content/www/us/en/design/products-and-solutions/processors-and-chipsets/sierra-forest/xeon-6700-series-processor-with-e-cores-specification-update/errata-details/
+ *
+ * For the Atom platforms before Sierra Forest (including Sierra Forest),
+ * Both 2 events "Instruction Retired" and "Branch Instruction Retired" would
+ * be overcounted on these certain instructions, but for Clearwater Forest
+ * only "Instruction Retired" event is overcounted on these instructions.
+ */
+uint32_t detect_inst_overcount_flags(void)
+{
+ uint32_t eax, ebx, ecx, edx;
+ uint32_t flags = 0;
+
+ cpuid(1, &eax, &ebx, &ecx, &edx);
+ if (x86_family(eax) == 0x6) {
+ switch (x86_model(eax)) {
+ case 0xDD: /* Clearwater Forest */
+ flags = INST_RETIRED_OVERCOUNT;
+ break;
+ case 0xAF: /* Sierra Forest */
+ case 0x4D: /* Avaton, Rangely */
+ case 0x5F: /* Denverton */
+ case 0x86: /* Jacobsville */
+ flags = INST_RETIRED_OVERCOUNT | BR_RETIRED_OVERCOUNT;
+ break;
+ }
+ }
+
+ return flags;
+}
diff --git a/tools/testing/selftests/kvm/x86/pmu_counters_test.c b/tools/testing/selftests/kvm/x86/pmu_counters_test.c
index 342a72420177..074cdf323406 100644
--- a/tools/testing/selftests/kvm/x86/pmu_counters_test.c
+++ b/tools/testing/selftests/kvm/x86/pmu_counters_test.c
@@ -52,6 +52,9 @@ struct kvm_intel_pmu_event {
struct kvm_x86_pmu_feature fixed_event;
};
+
+static uint8_t inst_overcount_flags;
+
/*
* Wrap the array to appease the compiler, as the macros used to construct each
* kvm_x86_pmu_feature use syntax that's only valid in function scope, and the
@@ -163,10 +166,18 @@ static void guest_assert_event_count(uint8_t idx, uint32_t pmc, uint32_t pmc_msr
switch (idx) {
case INTEL_ARCH_INSTRUCTIONS_RETIRED_INDEX:
- GUEST_ASSERT_EQ(count, NUM_INSNS_RETIRED);
+ /* Relax precise count check due to VM-EXIT/VM-ENTRY overcount issue */
+ if (inst_overcount_flags & INST_RETIRED_OVERCOUNT)
+ GUEST_ASSERT(count >= NUM_INSNS_RETIRED);
+ else
+ GUEST_ASSERT_EQ(count, NUM_INSNS_RETIRED);
break;
case INTEL_ARCH_BRANCHES_RETIRED_INDEX:
- GUEST_ASSERT_EQ(count, NUM_BRANCH_INSNS_RETIRED);
+ /* Relax precise count check due to VM-EXIT/VM-ENTRY overcount issue */
+ if (inst_overcount_flags & BR_RETIRED_OVERCOUNT)
+ GUEST_ASSERT(count >= NUM_BRANCH_INSNS_RETIRED);
+ else
+ GUEST_ASSERT_EQ(count, NUM_BRANCH_INSNS_RETIRED);
break;
case INTEL_ARCH_LLC_REFERENCES_INDEX:
case INTEL_ARCH_LLC_MISSES_INDEX:
@@ -335,6 +346,7 @@ static void test_arch_events(uint8_t pmu_version, uint64_t perf_capabilities,
length);
vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_EVENTS_MASK,
unavailable_mask);
+ sync_global_to_guest(vm, inst_overcount_flags);
run_vcpu(vcpu);
@@ -673,6 +685,7 @@ int main(int argc, char *argv[])
kvm_pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION);
kvm_has_perf_caps = kvm_cpu_has(X86_FEATURE_PDCM);
+ inst_overcount_flags = detect_inst_overcount_flags();
test_intel_counters();
--
2.43.0
^ permalink raw reply [flat|nested] 4+ messages in thread* [PATCH 3/3] KVM: selftests: Relax branches event count check for event_filter test
2025-07-12 17:25 [PATCH 0/3] Fix PMU kselftests errors on SRF and CWF Dapeng Mi
2025-07-12 17:25 ` [PATCH 1/3] KVM: Selftests: Validate more arch-events in pmu_counters_test Dapeng Mi
2025-07-12 17:25 ` [PATCH 2/3] KVM: selftests: Relax precise event count validation as overcount issue Dapeng Mi
@ 2025-07-12 17:25 ` Dapeng Mi
2 siblings, 0 replies; 4+ messages in thread
From: Dapeng Mi @ 2025-07-12 17:25 UTC (permalink / raw)
To: Sean Christopherson, Paolo Bonzini
Cc: kvm, linux-kernel, Jim Mattson, Mingwei Zhang, Zide Chen,
Das Sandipan, Shukla Manali, Yi Lai, Dapeng Mi, Dapeng Mi
As the branches event overcount issue on Atom platforms, once there are
VM-Exits triggered (external interrupts) in the guest loop, the measured
branch event count could be larger than NUM_BRANCHES, this would lead to
the pmu_event_filter_test print warning to info the measured branches
event count is mismatched with expected number (NUM_BRANCHES).
To eliminate this warning, relax the branches event count check on the
Atom platform which have the branches event overcount issue.
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Tested-by: Yi Lai <yi1.lai@intel.com>
---
tools/testing/selftests/kvm/x86/pmu_event_filter_test.c | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c
index c15513cd74d1..9c1a92f05786 100644
--- a/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c
+++ b/tools/testing/selftests/kvm/x86/pmu_event_filter_test.c
@@ -60,6 +60,8 @@ struct {
uint64_t instructions_retired;
} pmc_results;
+static uint8_t inst_overcount_flags;
+
/*
* If we encounter a #GP during the guest PMU sanity check, then the guest
* PMU is not functional. Inform the hypervisor via GUEST_SYNC(0).
@@ -214,8 +216,10 @@ static void remove_event(struct __kvm_pmu_event_filter *f, uint64_t event)
do { \
uint64_t br = pmc_results.branches_retired; \
uint64_t ir = pmc_results.instructions_retired; \
+ bool br_matched = inst_overcount_flags & BR_RETIRED_OVERCOUNT ? \
+ br >= NUM_BRANCHES : br == NUM_BRANCHES; \
\
- if (br && br != NUM_BRANCHES) \
+ if (br && !br_matched) \
pr_info("%s: Branch instructions retired = %lu (expected %u)\n", \
__func__, br, NUM_BRANCHES); \
TEST_ASSERT(br, "%s: Branch instructions retired = %lu (expected > 0)", \
@@ -850,6 +854,9 @@ int main(int argc, char *argv[])
if (use_amd_pmu())
test_amd_deny_list(vcpu);
+ if (use_intel_pmu())
+ inst_overcount_flags = detect_inst_overcount_flags();
+
test_without_filter(vcpu);
test_member_deny_list(vcpu);
test_member_allow_list(vcpu);
--
2.43.0
^ permalink raw reply [flat|nested] 4+ messages in thread