Test this patch series on Sapphire Rapids and Granite Rapids against perf-based vPMU and mediated vPMU. No failure is found. Thanks. On 2/15/2025 9:36 AM, Sean Christopherson wrote: > v7 of Dapeng's PMU fixes/cleanups series. FWIW, I haven't gone through the > changes all that carefully, I mostly focused on the high level "what" and the > style. > > This blows up without the per-CPU fixes: > https://lore.kernel.org/all/20250215012032.1206409-1-seanjc@xxxxxxxxxx > > v7: > - Rewrite the changelog for the patch that shrinks the size of pmu_counter_t. > - Cosmetic changes. > > v6: https://lore.kernel.org/all/20240914101728.33148-1-dapeng1.mi@xxxxxxxxxxxxxxx > > Dapeng Mi (17): > x86: pmu: Remove blank line and redundant space > x86: pmu: Refine fixed_events[] names > x86: pmu: Align fields in pmu_counter_t to better pack the struct > x86: pmu: Enlarge cnt[] length to 48 in check_counters_many() > x86: pmu: Print measured event count if test fails > x86: pmu: Fix potential out of bound access for fixed events > x86: pmu: Fix cycles event validation failure > x86: pmu: Use macro to replace hard-coded branches event index > x86: pmu: Use macro to replace hard-coded ref-cycles event index > x86: pmu: Use macro to replace hard-coded instructions event index > x86: pmu: Enable and disable PMCs in loop() asm blob > x86: pmu: Improve instruction and branches events verification > x86: pmu: Improve LLC misses event verification > x86: pmu: Adjust lower boundary of llc-misses event to 0 for legacy > CPUs > x86: pmu: Add IBPB indirect jump asm blob > x86: pmu: Adjust lower boundary of branch-misses event > x86: pmu: Optimize emulated instruction validation > > Xiong Zhang (1): > x86: pmu: Remove duplicate code in pmu_init() > > lib/x86/pmu.c | 5 - > x86/pmu.c | 423 ++++++++++++++++++++++++++++++++++++++++---------- > 2 files changed, 342 insertions(+), 86 deletions(-) > > > base-commit: f77fb696cfd0e4a5562cdca189be557946bf522f
