Add a test case 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. Signed-off-by: Zide Chen --- v7: - Use RDPMC instead of RDMSR in PERF_METRICS sanity test. v6: - Move perf metrics test out of test_arch_events(); it doesn't belong there, and this also avoids redundant runs of perf metrics test. - Correct the +/-3 error margin. 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 | 94 ++++++++++++++++++- 3 files changed, 93 insertions(+), 5 deletions(-) diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h index eff29645719b..e7745e2cd543 100644 --- a/tools/arch/x86/include/asm/msr-index.h +++ b/tools/arch/x86/include/asm/msr-index.h @@ -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 | \ diff --git a/tools/testing/selftests/kvm/include/x86/pmu.h b/tools/testing/selftests/kvm/include/x86/pmu.h index 608ed83d7c6a..6c19503e0bb7 100644 --- a/tools/testing/selftests/kvm/include/x86/pmu.h +++ b/tools/testing/selftests/kvm/include/x86/pmu.h @@ -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) diff --git a/tools/testing/selftests/kvm/x86/pmu_counters_test.c b/tools/testing/selftests/kvm/x86/pmu_counters_test.c index dc6afac3aa91..8294a0089a85 100644 --- a/tools/testing/selftests/kvm/x86/pmu_counters_test.c +++ b/tools/testing/selftests/kvm/x86/pmu_counters_test.c @@ -3,6 +3,7 @@ * Copyright (C) 2023, Tencent, Inc. */ #include +#include #include "pmu.h" #include "processor.h" @@ -241,17 +242,20 @@ do { \ ); \ } while (0) -#define GUEST_TEST_EVENT(_idx, _pmc, _pmc_msr, _ctrl_msr, _value, FEP) \ +#define GUEST_RUN_PAYLOAD(_ctrl_msr, _value, FEP) \ do { \ - wrmsr(_pmc_msr, 0); \ - \ if (this_cpu_has(X86_FEATURE_CLFLUSHOPT)) \ GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflushopt %[m]", FEP); \ else if (this_cpu_has(X86_FEATURE_CLFLUSH)) \ GUEST_MEASURE_EVENT(_ctrl_msr, _value, "clflush %[m]", FEP); \ else \ GUEST_MEASURE_EVENT(_ctrl_msr, _value, "nop", FEP); \ - \ +} while (0) + +#define GUEST_TEST_EVENT(_idx, _pmc, _pmc_msr, _ctrl_msr, _value, FEP) \ +do { \ + wrmsr(_pmc_msr, 0); \ + GUEST_RUN_PAYLOAD(_ctrl_msr, _value, FEP); \ guest_assert_event_count(_idx, _pmc, _pmc_msr); \ } while (0) @@ -361,7 +365,7 @@ static void test_arch_events(u8 pmu_version, u64 perf_capabilities, * other than PMCs in the future. */ #define MAX_NR_GP_COUNTERS 8 -#define MAX_NR_FIXED_COUNTERS 3 +#define MAX_NR_FIXED_COUNTERS 4 #define GUEST_ASSERT_PMC_MSR_ACCESS(insn, msr, expect_gp, vector) \ __GUEST_ASSERT(expect_gp ? vector == GP_VECTOR : !vector, \ @@ -580,11 +584,81 @@ static void test_fixed_counters(u8 pmu_version, u64 perf_capabilities, kvm_vm_free(vm); } +static void __guest_test_perf_metrics(void) +{ + int retiring, bad_spec, fe_bound, be_bound, sum; + u64 global_ctrl, metrics; + + if ((guest_get_pmu_version() < 2) || /* Does guest have GLOBAL_CTRL? */ + !this_cpu_has(X86_FEATURE_PDCM) || + !(rdmsr(MSR_IA32_PERF_CAPABILITIES) & PERF_CAP_PERF_METRICS)) + return; + + wrmsr(MSR_CORE_PERF_GLOBAL_CTRL, 0); + wrmsr(MSR_CORE_PERF_FIXED_CTR3, 0); + wrmsr(MSR_PERF_METRICS, 0); + + /* Enable fixed ctr3 (TOPDOWN.SLOTS) and PERF_METRICS. */ + wrmsr(MSR_CORE_PERF_FIXED_CTR_CTRL, FIXED_PMC_CTRL(3, FIXED_PMC_KERNEL)); + global_ctrl = FIXED_PMC_GLOBAL_CTRL_ENABLE(3) | + PERF_METRICS_GLOBAL_CTRL_ENABLE; + + GUEST_RUN_PAYLOAD(MSR_CORE_PERF_GLOBAL_CTRL, global_ctrl, ""); + + /* Check test results. */ + metrics = rdmsr(MSR_PERF_METRICS); + retiring = FIELD_GET(GENMASK_ULL(7, 0), metrics); + bad_spec = FIELD_GET(GENMASK_ULL(15, 8), metrics); + fe_bound = FIELD_GET(GENMASK_ULL(23, 16), metrics); + be_bound = FIELD_GET(GENMASK_ULL(31, 24), metrics); + + /* + * Be conservative: the measured payload definitely retires work, so + * Retiring should be non-zero. + */ + GUEST_ASSERT_NE(metrics, 0ULL); + GUEST_ASSERT_NE(retiring, 0ULL); + + /* + * Each level-1 Topdown metric is an integer fraction of 0xff. + * A +/-3 error margin is chosen for a loose sanity check. + */ + sum = retiring + bad_spec + fe_bound + be_bound; + GUEST_ASSERT(sum >= 0xfc && sum <= 0x102); + + /* 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_test_rdpmc(INTEL_RDPMC_METRICS, true, 0xdeaddead); +} + +static void guest_test_perf_metrics(void) +{ + __guest_test_perf_metrics(); + GUEST_DONE(); +} + +static void test_perf_metrics(u8 pmu_version, u64 perf_capabilities) +{ + struct kvm_vcpu *vcpu; + struct kvm_vm *vm; + + vm = pmu_vm_create_with_one_vcpu(&vcpu, guest_test_perf_metrics, + pmu_version, perf_capabilities); + + run_vcpu(vcpu); + + kvm_vm_free(vm); +} + static void test_intel_counters(void) { 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); u8 pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION); + u64 advertised_perf_caps = kvm_get_feature_msr(MSR_IA32_PERF_CAPABILITIES); unsigned int i; u8 v, j; u32 k; @@ -592,6 +666,7 @@ static void test_intel_counters(void) const u64 perf_caps[] = { 0, PMU_CAP_FW_WRITES, + PERF_CAP_PERF_METRICS, }; /* @@ -649,6 +724,10 @@ static void test_intel_counters(void) if (!kvm_has_perf_caps && perf_caps[i]) continue; + /* Ignore unsupported features. */ + if (perf_caps[i] & ~advertised_perf_caps) + continue; + pr_info("Testing arch events, PMU version %u, perf_caps = %lx\n", v, perf_caps[i]); @@ -675,6 +754,11 @@ static void test_intel_counters(void) for (k = 0; k <= (BIT(nr_fixed_counters) - 1); k++) test_fixed_counters(v, perf_caps[i], j, k); } + + pr_info("Testing Perf Metrics, PMU version %u, perf_caps = %lx\n", + v, perf_caps[i]); + + test_perf_metrics(v, perf_caps[i]); } } } -- 2.54.0