* [PATCH v2 1/2] KVM: selftests: Test one random GP counter in PMU arch events testcase
2026-08-04 20:40 [PATCH v2 0/2] KVM: selftests: Reduce PMC test runtime by ~17x Sean Christopherson
@ 2026-08-04 20:40 ` Sean Christopherson
2026-08-04 20:40 ` [PATCH v2 2/2] KVM: selftests: Create one VM with many vCPUs for each major PMU counters test Sean Christopherson
1 sibling, 0 replies; 5+ messages in thread
From: Sean Christopherson @ 2026-08-04 20:40 UTC (permalink / raw)
To: Sean Christopherson, Paolo Bonzini; +Cc: kvm, linux-kernel
To significantly reduce the PMU counter test's runtime, without sacrificing
test coverage in the aggregate, test a random GP counter in the arch events
testcase instead of testing every possible GP counter. Testing every PMC
in every run of the test significantly increases the runtime of the test,
without providing an equivalent increase in validation coverage, as the
odds of a KVM having a bug that only affected a subset of counters and only
when testing all other counters are extremely low.
Opportunistically clean up kvm_random_u64_in_range() to eliminate
unnecessary newlines.
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
.../testing/selftests/kvm/include/test_util.h | 4 ++--
tools/testing/selftests/kvm/lib/test_util.c | 22 +++++++++++++++----
.../selftests/kvm/x86/pmu_counters_test.c | 18 +++++++--------
3 files changed, 28 insertions(+), 16 deletions(-)
diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h
index e8356ee54d7b..a6a3e1657895 100644
--- a/tools/testing/selftests/kvm/include/test_util.h
+++ b/tools/testing/selftests/kvm/include/test_util.h
@@ -135,8 +135,8 @@ static inline u64 kvm_random_u64(struct kvm_random_state *state)
return ((u64)kvm_random_u32(state) << 32) | kvm_random_u32(state);
}
-u64 kvm_random_u64_in_range(struct kvm_random_state *state, u64 min,
- u64 max);
+u32 kvm_random_u32_in_range(struct kvm_random_state *state, u32 min, u32 max);
+u64 kvm_random_u64_in_range(struct kvm_random_state *state, u64 min, u64 max);
enum vm_mem_backing_src_type {
VM_MEM_SRC_ANONYMOUS,
diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c
index 6b00ab11f3c0..4dff72f6bd34 100644
--- a/tools/testing/selftests/kvm/lib/test_util.c
+++ b/tools/testing/selftests/kvm/lib/test_util.c
@@ -43,12 +43,26 @@ u32 kvm_random_u32(struct kvm_random_state *state)
return state->seed;
}
+/* Returns a random u32 in the inclusive range [min, max] */
+u32 kvm_random_u32_in_range(struct kvm_random_state *state, u32 min, u32 max)
+{
+ u32 value, range;
+
+ TEST_ASSERT(min <= max, "PEBKAC, min = 0x%x, max = 0x%x", min, max);
+
+ value = kvm_random_u32(state);
+
+ range = max - min;
+ if (range == UINT_MAX)
+ return value;
+
+ return min + (value % (range + 1));
+}
+
/* Returns a random u64 in the inclusive range [min, max] */
-u64 kvm_random_u64_in_range(struct kvm_random_state *state, u64 min,
- u64 max)
+u64 kvm_random_u64_in_range(struct kvm_random_state *state, u64 min, u64 max)
{
- u64 value;
- u64 range;
+ u64 value, range;
TEST_ASSERT(min <= max, "PEBKAC, min = 0x%lx, max = 0x%lx", min, max);
diff --git a/tools/testing/selftests/kvm/x86/pmu_counters_test.c b/tools/testing/selftests/kvm/x86/pmu_counters_test.c
index dc6afac3aa91..8abf17cc9469 100644
--- a/tools/testing/selftests/kvm/x86/pmu_counters_test.c
+++ b/tools/testing/selftests/kvm/x86/pmu_counters_test.c
@@ -273,6 +273,7 @@ static void guest_test_arch_event(u8 idx)
struct kvm_x86_pmu_feature gp_event, fixed_event;
u32 base_pmc_msr;
unsigned int i;
+ u64 eventsel;
/* The host side shouldn't invoke this without a guest PMU. */
GUEST_ASSERT(pmu_version);
@@ -287,19 +288,16 @@ static void guest_test_arch_event(u8 idx)
GUEST_ASSERT_EQ(idx, gp_event.f.bit);
GUEST_ASSERT(nr_gp_counters);
+ i = kvm_random_u32_in_range(&kvm_rng, 0, nr_gp_counters - 1);
- for (i = 0; i < nr_gp_counters; i++) {
- u64 eventsel = ARCH_PERFMON_EVENTSEL_OS |
- ARCH_PERFMON_EVENTSEL_ENABLE |
- intel_pmu_arch_events[idx];
+ eventsel = ARCH_PERFMON_EVENTSEL_OS | ARCH_PERFMON_EVENTSEL_ENABLE |
+ intel_pmu_arch_events[idx];
- wrmsr(MSR_P6_EVNTSEL0 + i, 0);
- if (guest_has_perf_global_ctrl)
- wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, BIT_ULL(i));
+ wrmsr(MSR_P6_EVNTSEL0 + i, 0);
+ if (guest_has_perf_global_ctrl)
+ wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, BIT_ULL(i));
- __guest_test_arch_event(idx, i, base_pmc_msr + i,
- MSR_P6_EVNTSEL0 + i, eventsel);
- }
+ __guest_test_arch_event(idx, i, base_pmc_msr + i, MSR_P6_EVNTSEL0 + i, eventsel);
if (!guest_has_perf_global_ctrl)
return;
--
2.55.0.571.g244d577d93-goog
^ permalink raw reply related [flat|nested] 5+ messages in thread* [PATCH v2 2/2] KVM: selftests: Create one VM with many vCPUs for each major PMU counters test
2026-08-04 20:40 [PATCH v2 0/2] KVM: selftests: Reduce PMC test runtime by ~17x Sean Christopherson
2026-08-04 20:40 ` [PATCH v2 1/2] KVM: selftests: Test one random GP counter in PMU arch events testcase Sean Christopherson
@ 2026-08-04 20:40 ` Sean Christopherson
2026-08-04 20:53 ` sashiko-bot
1 sibling, 1 reply; 5+ messages in thread
From: Sean Christopherson @ 2026-08-04 20:40 UTC (permalink / raw)
To: Sean Christopherson, Paolo Bonzini; +Cc: kvm, linux-kernel
To reduce the runtime of the PMU counters test by an order of magnitude,
create one VM per category of test (arch events, GP PMCs, fixed PMCs),
with N vCPUs per VM, where 'N' is the number of testscases to run per
category. The vast majority of the test's runtime is spent creating VMs,
because while creating a VM only takes a few milliseconds, the total time
adds up when creating hundreds of VMs. The only reason the test creates
so many VMs is because KVM disallows changing the virtual PMU model after
a vCPU runs, so rather than create an entirely new VM just to get a "fresh"
vCPUs, simply use a different vCPU.
On an Emerald Rapids host, this reduces the runtime from 75+ seconds to
less than 6 seconds.
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
.../selftests/kvm/x86/pmu_counters_test.c | 212 ++++++++++--------
1 file changed, 122 insertions(+), 90 deletions(-)
diff --git a/tools/testing/selftests/kvm/x86/pmu_counters_test.c b/tools/testing/selftests/kvm/x86/pmu_counters_test.c
index 8abf17cc9469..c7c566220381 100644
--- a/tools/testing/selftests/kvm/x86/pmu_counters_test.c
+++ b/tools/testing/selftests/kvm/x86/pmu_counters_test.c
@@ -87,14 +87,18 @@ static struct kvm_intel_pmu_event intel_event_to_feature(u8 idx)
return __intel_event_to_feature[idx];
}
-static struct kvm_vm *pmu_vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
- void *guest_code,
- u8 pmu_version,
- u64 perf_capabilities)
+static struct kvm_vm *pmu_vm_create_with_vcpus(u32 nr_vcpus, void *guest_code,
+ u8 pmu_version,
+ u64 perf_capabilities,
+ struct kvm_vcpu **__vcpus[])
{
+ struct kvm_vcpu **vcpus = calloc(nr_vcpus, sizeof(struct kvm_vcpu));
struct kvm_vm *vm;
+ int i;
- vm = vm_create_with_one_vcpu(vcpu, guest_code);
+ *__vcpus = vcpus;
+
+ vm = vm_create_with_vcpus(nr_vcpus, guest_code, vcpus);
sync_global_to_guest(vm, kvm_pmu_version);
sync_global_to_guest(vm, hardware_pmu_arch_events);
@@ -102,13 +106,22 @@ static struct kvm_vm *pmu_vm_create_with_one_vcpu(struct kvm_vcpu **vcpu,
* Set PERF_CAPABILITIES before PMU version as KVM disallows enabling
* features via PERF_CAPABILITIES if the guest doesn't have a vPMU.
*/
- if (kvm_has_perf_caps)
- vcpu_set_msr(*vcpu, MSR_IA32_PERF_CAPABILITIES, perf_capabilities);
+ for (i = 0; i < nr_vcpus; i++) {
+ if (kvm_has_perf_caps)
+ vcpu_set_msr(vcpus[i], MSR_IA32_PERF_CAPABILITIES, perf_capabilities);
+
+ vcpu_set_cpuid_property(vcpus[i], X86_PROPERTY_PMU_VERSION, pmu_version);
+ }
- vcpu_set_cpuid_property(*vcpu, X86_PROPERTY_PMU_VERSION, pmu_version);
return vm;
}
+static void pmu_vm_free(struct kvm_vm *vm, struct kvm_vcpu **vcpus)
+{
+ kvm_vm_free(vm);
+ free(vcpus);
+}
+
static void run_vcpu(struct kvm_vcpu *vcpu)
{
struct ucall uc;
@@ -326,30 +339,72 @@ static void guest_test_arch_events(void)
GUEST_DONE();
}
-static void test_arch_events(u8 pmu_version, u64 perf_capabilities,
- u8 length, u32 unavailable_mask)
+static void __test_arch_events(struct kvm_vcpu *vcpu, u64 perf_capabilities,
+ u8 length, u32 unavailable_mask)
{
- struct kvm_vcpu *vcpu;
- struct kvm_vm *vm;
-
- /* Testing arch events requires a vPMU (there are no negative tests). */
- if (!pmu_version)
- return;
-
unavailable_mask &= GENMASK(X86_PROPERTY_PMU_EVENTS_MASK.hi_bit,
X86_PROPERTY_PMU_EVENTS_MASK.lo_bit);
- vm = pmu_vm_create_with_one_vcpu(&vcpu, guest_test_arch_events,
- pmu_version, perf_capabilities);
-
vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_EBX_BIT_VECTOR_LENGTH,
length);
vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_EVENTS_MASK,
unavailable_mask);
run_vcpu(vcpu);
+}
- kvm_vm_free(vm);
+static void test_arch_events(u8 pmu_version, u64 perf_capabilities)
+{
+ struct kvm_vcpu **vcpus;
+ struct kvm_vm *vm;
+ int i = 0;
+ u32 k;
+ u8 j;
+
+ /*
+ * To keep the total runtime reasonable, test only a handful of select,
+ * semi-arbitrary values for the mask of unavailable PMU events. Test
+ * 0 (all events available) and all ones (no events available) as well
+ * as alternating bit sequencues, e.g. to detect if KVM is checking the
+ * wrong bit(s).
+ */
+ const u32 unavailable_masks[] = {
+ 0x0,
+ 0xffffffffu,
+ 0xaaaaaaaau,
+ 0x55555555u,
+ 0xf0f0f0f0u,
+ 0x0f0f0f0fu,
+ 0xa0a0a0a0u,
+ 0x0a0a0a0au,
+ 0x50505050u,
+ 0x05050505u,
+ };
+
+ pr_info("Testing arch events, PMU version %u, perf_caps = %lx\n",
+ pmu_version, perf_capabilities);
+
+ /* Testing arch events requires a vPMU (there are no negative tests). */
+ if (!pmu_version)
+ return;
+
+ vm = pmu_vm_create_with_vcpus((NR_INTEL_ARCH_EVENTS + 2) * ARRAY_SIZE(unavailable_masks),
+ guest_test_arch_events, pmu_version,
+ perf_capabilities, &vcpus);
+
+ /*
+ * Test single bits for all PMU version and lengths up the number of
+ * events +1 (to verify KVM doesn't do weird things if the guest length
+ * is greater than the host length). Explicitly test a mask of '0' and
+ * all ones i.e. all events being available and unavailable.
+ */
+ for (j = 0; j <= NR_INTEL_ARCH_EVENTS + 1; j++) {
+ for (k = 1; k < ARRAY_SIZE(unavailable_masks); k++)
+ __test_arch_events(vcpus[i++], perf_capabilities, j,
+ unavailable_masks[k]);
+ }
+
+ pmu_vm_free(vm, vcpus);
}
/*
@@ -493,21 +548,27 @@ static void guest_test_gp_counters(void)
GUEST_DONE();
}
-static void test_gp_counters(u8 pmu_version, u64 perf_capabilities,
- u8 nr_gp_counters)
+static void test_gp_counters(u8 pmu_version, u64 perf_capabilities)
{
- struct kvm_vcpu *vcpu;
+ u8 nr_gp_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS);
+ struct kvm_vcpu **vcpus;
struct kvm_vm *vm;
+ u8 j;
- vm = pmu_vm_create_with_one_vcpu(&vcpu, guest_test_gp_counters,
- pmu_version, perf_capabilities);
+ pr_info("Testing %u GP counters, PMU version %u, perf_caps = %lx\n",
+ nr_gp_counters, pmu_version, perf_capabilities);
- vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_NR_GP_COUNTERS,
- nr_gp_counters);
+ vm = pmu_vm_create_with_vcpus(nr_gp_counters + 1, guest_test_gp_counters,
+ pmu_version, perf_capabilities, &vcpus);
- run_vcpu(vcpu);
+ for (j = 0; j <= nr_gp_counters; j++) {
+ vcpu_set_cpuid_property(vcpus[j], X86_PROPERTY_PMU_NR_GP_COUNTERS,
+ nr_gp_counters);
- kvm_vm_free(vm);
+ run_vcpu(vcpus[j]);
+ }
+
+ pmu_vm_free(vm, vcpus);
}
static void guest_test_fixed_counters(void)
@@ -559,59 +620,53 @@ static void guest_test_fixed_counters(void)
GUEST_DONE();
}
-static void test_fixed_counters(u8 pmu_version, u64 perf_capabilities,
- u8 nr_fixed_counters, u32 supported_bitmask)
+static void __test_fixed_counters(struct kvm_vcpu *vcpu, u8 nr_fixed_counters,
+ u32 supported_bitmask)
{
- struct kvm_vcpu *vcpu;
- struct kvm_vm *vm;
-
- vm = pmu_vm_create_with_one_vcpu(&vcpu, guest_test_fixed_counters,
- pmu_version, perf_capabilities);
-
vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_FIXED_COUNTERS_BITMASK,
supported_bitmask);
vcpu_set_cpuid_property(vcpu, X86_PROPERTY_PMU_NR_FIXED_COUNTERS,
nr_fixed_counters);
run_vcpu(vcpu);
-
- kvm_vm_free(vm);
}
-static void test_intel_counters(void)
+static void test_fixed_counters(u8 pmu_version, u64 perf_capabilities)
{
u8 nr_fixed_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_FIXED_COUNTERS);
- u8 nr_gp_counters = kvm_cpu_property(X86_PROPERTY_PMU_NR_GP_COUNTERS);
+ struct kvm_vcpu **vcpus;
+ struct kvm_vm *vm;
+ int i = 0;
+ u32 k;
+ u8 j;
+
+ pr_info("Testing %u fixed counters, PMU version %u, perf_caps = %lx\n",
+ nr_fixed_counters, pmu_version, perf_capabilities);
+
+
+ vm = pmu_vm_create_with_vcpus((nr_fixed_counters + 1) * BIT(nr_fixed_counters),
+ guest_test_fixed_counters,
+ pmu_version, perf_capabilities, &vcpus);
+
+ for (j = 0; j <= nr_fixed_counters; j++) {
+ for (k = 0; k <= (BIT(nr_fixed_counters) - 1); k++)
+ __test_fixed_counters(vcpus[i++], j, k);
+ }
+
+ pmu_vm_free(vm, vcpus);
+}
+
+static void test_intel_counters(void)
+{
u8 pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION);
unsigned int i;
- u8 v, j;
- u32 k;
+ u8 v;
const u64 perf_caps[] = {
0,
PMU_CAP_FW_WRITES,
};
- /*
- * To keep the total runtime reasonable, test only a handful of select,
- * semi-arbitrary values for the mask of unavailable PMU events. Test
- * 0 (all events available) and all ones (no events available) as well
- * as alternating bit sequencues, e.g. to detect if KVM is checking the
- * wrong bit(s).
- */
- const u32 unavailable_masks[] = {
- 0x0,
- 0xffffffffu,
- 0xaaaaaaaau,
- 0x55555555u,
- 0xf0f0f0f0u,
- 0x0f0f0f0fu,
- 0xa0a0a0a0u,
- 0x0a0a0a0au,
- 0x50505050u,
- 0x05050505u,
- };
-
/*
* Test up to PMU v5, which is the current maximum version defined by
* Intel, i.e. is the last version that is guaranteed to be backwards
@@ -647,32 +702,9 @@ static void test_intel_counters(void)
if (!kvm_has_perf_caps && perf_caps[i])
continue;
- pr_info("Testing arch events, PMU version %u, perf_caps = %lx\n",
- v, perf_caps[i]);
-
- /*
- * Test single bits for all PMU version and lengths up
- * the number of events +1 (to verify KVM doesn't do
- * weird things if the guest length is greater than the
- * host length). Explicitly test a mask of '0' and all
- * ones i.e. all events being available and unavailable.
- */
- for (j = 0; j <= NR_INTEL_ARCH_EVENTS + 1; j++) {
- for (k = 1; k < ARRAY_SIZE(unavailable_masks); k++)
- test_arch_events(v, perf_caps[i], j, unavailable_masks[k]);
- }
-
- pr_info("Testing GP counters, PMU version %u, perf_caps = %lx\n",
- v, perf_caps[i]);
- for (j = 0; j <= nr_gp_counters; j++)
- test_gp_counters(v, perf_caps[i], j);
-
- pr_info("Testing fixed counters, PMU version %u, perf_caps = %lx\n",
- v, perf_caps[i]);
- for (j = 0; j <= nr_fixed_counters; j++) {
- for (k = 0; k <= (BIT(nr_fixed_counters) - 1); k++)
- test_fixed_counters(v, perf_caps[i], j, k);
- }
+ test_arch_events(v, perf_caps[i]);
+ test_gp_counters(v, perf_caps[i]);
+ test_fixed_counters(v, perf_caps[i]);
}
}
}
--
2.55.0.571.g244d577d93-goog
^ permalink raw reply related [flat|nested] 5+ messages in thread