| Message ID | 20220823093221.38075-1-likexu@tencent.com (mailing list archive) |
|---|---|
| Headers | show |
| Series | x86/pmu: Corner cases fixes and optimization | expand |
On Tue, Aug 23, 2022, Like Xu wrote: > Good well-designed tests can help us find more bugs, especially when > the test steps differ from the Linux kernel behaviour in terms of the > timing of access to virtualized hw resources. > > In this patch series, there are three small optimization (006/007/008), > one hardware surprise (001), and most of these fixes have stepped > on my little toes. > > Please feel free to run tests, add more or share comments. > > Previous: > https://lore.kernel.org/kvm/20220721103549.49543-1-likexu@tencent.com/ > https://lore.kernel.org/kvm/20220803130124.72340-1-likexu@tencent.com/ > > V2 -> V2 RESEND Changelog: > - The "pebs_capable" fix has been merged into tip/perf/tree tree; > - Move the other two AMD vPMU optimization here; This is not a RESEND. These things very much matter because I'm sitting here trying to figure out whether I need to review this "v2", which is really v3, or whether I can just review the real v2. Don't add "RESEND" when you are submitting a modified version of your patch or patch series - "RESEND" only applies to resubmission of a patch or patch series which have not been modified in any way from the previous submission.
On 31/8/2022 1:29 am, Sean Christopherson wrote: > On Tue, Aug 23, 2022, Like Xu wrote: >> Good well-designed tests can help us find more bugs, especially when >> the test steps differ from the Linux kernel behaviour in terms of the >> timing of access to virtualized hw resources. >> >> In this patch series, there are three small optimization (006/007/008), >> one hardware surprise (001), and most of these fixes have stepped >> on my little toes. >> >> Please feel free to run tests, add more or share comments. >> >> Previous: >> https://lore.kernel.org/kvm/20220721103549.49543-1-likexu@tencent.com/ >> https://lore.kernel.org/kvm/20220803130124.72340-1-likexu@tencent.com/ >> >> V2 -> V2 RESEND Changelog: >> - The "pebs_capable" fix has been merged into tip/perf/tree tree; >> - Move the other two AMD vPMU optimization here; > > This is not a RESEND. These things very much matter because I'm sitting here > trying to figure out whether I need to review this "v2", which is really v3, or > whether I can just review the real v2. > > Don't add "RESEND" when you are submitting a modified version of your > patch or patch series - "RESEND" only applies to resubmission of a > patch or patch series which have not been modified in any way from the > previous submission. Roger that. Thanks for your detailed comments and all of that will be applied in V3. The new AMD vPMU testcases[1] will also help guard future related changes. [1] https://lore.kernel.org/kvm/20220819110939.78013-1-likexu@tencent.com/ Thanks, Like Xu
Good well-designed tests can help us find more bugs, especially when the test steps differ from the Linux kernel behaviour in terms of the timing of access to virtualized hw resources. In this patch series, there are three small optimization (006/007/008), one hardware surprise (001), and most of these fixes have stepped on my little toes. Please feel free to run tests, add more or share comments. Previous: https://lore.kernel.org/kvm/20220721103549.49543-1-likexu@tencent.com/ https://lore.kernel.org/kvm/20220803130124.72340-1-likexu@tencent.com/ V2 -> V2 RESEND Changelog: - The "pebs_capable" fix has been merged into tip/perf/tree tree; - Move the other two AMD vPMU optimization here; Like Xu (8): perf/x86/core: Completely disable guest PEBS via guest's global_ctrl KVM: x86/pmu: Avoid setting BIT_ULL(-1) to pmu->host_cross_mapped_mask KVM: x86/pmu: Don't generate PEBS records for emulated instructions KVM: x86/pmu: Avoid using PEBS perf_events for normal counters KVM: x86/pmu: Defer reprogram_counter() to kvm_pmu_handle_event() KVM: x86/pmu: Defer counter emulated overflow via pmc->stale_counter KVM: x86/svm/pmu: Direct access pmu->gp_counter[] to implement amd_*_to_pmc() KVM: x86/svm/pmu: Rewrite get_gp_pmc_amd() for more counters scalability arch/x86/events/intel/core.c | 3 +- arch/x86/include/asm/kvm_host.h | 6 +- arch/x86/kvm/pmu.c | 47 ++++++++----- arch/x86/kvm/pmu.h | 6 +- arch/x86/kvm/svm/pmu.c | 116 +++++--------------------------- arch/x86/kvm/vmx/pmu_intel.c | 30 ++++----- 6 files changed, 73 insertions(+), 135 deletions(-)