Re: [PATCH v9 08/12] KVM: selftests: Add PERF_METRICS and fixed counter 3 tests

[sashiko-bot@kernel.org]

Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [Medium] selftests: unconditional MSR read causes assertion failure on older kernels
--

commit c5ae582e90bae306393c4bf2f37f04a11e37ba5f
Author: Zide Chen <zide.chen@intel.com>

KVM: selftests: Add PERF_METRICS and fixed counter 3 tests

This commit adds a test case to exercise IA32_PERF_METRICS for Topdown Level
1 metrics. It also extends the PMU selftest to cover Intel fixed counter 3 by
bumping the maximum number of fixed counters and validating functionality.

> diff --git a/tools/testing/selftests/kvm/x86/pmu_counters_test.c b/tools/testing/selftests/kvm/x86/pmu_counters_test.c
> --- a/tools/testing/selftests/kvm/x86/pmu_counters_test.c
> +++ b/tools/testing/selftests/kvm/x86/pmu_counters_test.c
[ ... ]
> @@ -653,8 +657,85 @@ static void test_fixed_counters(u8 pmu_version, u64 perf_capabilities)
[ ... ]
>  static void test_intel_counters(void)
>  {
> +	u64 advertised_perf_caps = kvm_get_feature_msr(MSR_IA32_PERF_CAPABILITIES);

[Severity: Medium]
Will this unconditional MSR read cause an assertion failure on older kernels?

When running the selftest on a host kernel prior to 5.9, KVM does not
expose MSR_IA32_PERF_CAPABILITIES as a feature MSR. Calling
kvm_get_feature_msr() unconditionally in test_intel_counters() causes the
underlying ioctl to fail and return 0, which triggers an assertion failure
rather than skipping the feature gracefully.

Other MSR accesses in this file appear to be guarded by checking
kvm_has_perf_caps first. Could we apply a similar check before reading
advertised_perf_caps so the test remains compatible with older environments?

>  	u8 pmu_version = kvm_cpu_property(X86_PROPERTY_PMU_VERSION);
>  	unsigned int i;
>  	u8 v;
[ ... ]

-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260918193937.569414-1-zide.chen@intel.com?part=8