| Message ID | 20241010143152.19071-1-adrian.hunter@intel.com |
|---|---|
| State | Superseded |
| Headers | show |
On Thu, Oct 10, 2024 at 05:31:48PM +0300, Adrian Hunter wrote: > Display "feature is not supported" error message if aux_start_paused, > aux_pause or aux_resume result in a perf_event_open() error. > > Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> > Acked-by: Ian Rogers <irogers@google.com> > Reviewed-by: Andi Kleen <ak@linux.intel.com> This patch looks good to me. A case is the Linux kernel has supported aux_pause_resume feature, but the PMU event does not support it. So we might consider to add a extra patch in perf: diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 927aa61e7b14..9a3191df2ec5 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -3373,6 +3373,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, return scnprintf(msg, size, "%s: PMU Hardware doesn't support 'aux_output' feature", evsel__name(evsel)); + if (evsel->core.attr.aux_action) + return scnprintf(msg, size, + "%s: PMU Hardware doesn't support 'aux_action' feature", + evsel__name(evsel)); if (evsel->core.attr.sample_period != 0) return scnprintf(msg, size, "%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'", Thanks, Leo > --- > tools/perf/util/evsel.c | 10 +++++++++- > tools/perf/util/evsel.h | 1 + > 2 files changed, 10 insertions(+), 1 deletion(-) > > diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c > index d34ceab9e454..927aa61e7b14 100644 > --- a/tools/perf/util/evsel.c > +++ b/tools/perf/util/evsel.c > @@ -2147,7 +2147,13 @@ bool evsel__detect_missing_features(struct evsel *evsel) > * Must probe features in the order they were added to the > * perf_event_attr interface. > */ > - if (!perf_missing_features.branch_counters && > + if (!perf_missing_features.aux_pause_resume && > + (evsel->core.attr.aux_pause || evsel->core.attr.aux_resume || > + evsel->core.attr.aux_start_paused)) { > + perf_missing_features.aux_pause_resume = true; > + pr_debug2_peo("Kernel has no aux_pause/aux_resume support, bailing out\n"); > + return false; > + } else if (!perf_missing_features.branch_counters && > (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS)) { > perf_missing_features.branch_counters = true; > pr_debug2("switching off branch counters support\n"); > @@ -3397,6 +3403,8 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target, > return scnprintf(msg, size, "clockid feature not supported."); > if (perf_missing_features.clockid_wrong) > return scnprintf(msg, size, "wrong clockid (%d).", clockid); > + if (perf_missing_features.aux_pause_resume) > + return scnprintf(msg, size, "The 'aux_pause / aux_resume' feature is not supported, update the kernel."); > if (perf_missing_features.aux_output) > return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel."); > if (!target__has_cpu(target)) > diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h > index 15e745a9a798..778fcdb8261f 100644 > --- a/tools/perf/util/evsel.h > +++ b/tools/perf/util/evsel.h > @@ -221,6 +221,7 @@ struct perf_missing_features { > bool weight_struct; > bool read_lost; > bool branch_counters; > + bool aux_pause_resume; > }; > > extern struct perf_missing_features perf_missing_features; > -- > 2.43.0 > >
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h index 0c557f0a17b3..05dcc43f11bb 100644 --- a/tools/include/uapi/linux/perf_event.h +++ b/tools/include/uapi/linux/perf_event.h @@ -369,6 +369,22 @@ enum perf_event_read_format { PERF_FORMAT_MAX = 1U << 5, /* non-ABI */ }; +enum { + PERF_AUX_ACTION_START_PAUSED = 1U << 0, + PERF_AUX_ACTION_PAUSE = 1U << 1, + PERF_AUX_ACTION_RESUME = 1U << 2, + PERF_AUX_ACTION_EMIT = 1U << 3, + PERF_AUX_ACTION_NR = 0x1f << 4, + PERF_AUX_ACTION_NO_IP = 1U << 9, + PERF_AUX_ACTION_PAUSE_ON_EVT = 1U << 10, + PERF_AUX_ACTION_RESUME_ON_EVT = 1U << 11, + PERF_AUX_ACTION_EMIT_ON_EVT = 1U << 12, + PERF_AUX_ACTION_NR_ON_EVT = 0x1f << 13, + PERF_AUX_ACTION_NO_IP_ON_EVT = 1U << 18, + PERF_AUX_ACTION_MASK = ~PERF_AUX_ACTION_START_PAUSED, + PERF_AUX_PAUSE_RESUME_MASK = PERF_AUX_ACTION_PAUSE | PERF_AUX_ACTION_RESUME, +}; + #define PERF_ATTR_SIZE_VER0 64 /* sizeof first published struct */ #define PERF_ATTR_SIZE_VER1 72 /* add: config2 */ #define PERF_ATTR_SIZE_VER2 80 /* add: branch_sample_type */ @@ -515,10 +531,19 @@ struct perf_event_attr { union { __u32 aux_action; struct { - __u32 aux_start_paused : 1, /* start AUX area tracing paused */ - aux_pause : 1, /* on overflow, pause AUX area tracing */ - aux_resume : 1, /* on overflow, resume AUX area tracing */ - __reserved_3 : 29; + __u32 aux_start_paused : 1, /* start AUX area tracing paused */ + aux_pause : 1, /* on overflow, pause AUX area tracing */ + aux_resume : 1, /* on overflow, resume AUX area tracing */ + aux_emit : 1, /* generate AUX records instead of events */ + aux_nr : 5, /* AUX area tracing reference number */ + aux_no_ip : 1, /* suppress IP in AUX records */ + /* Following apply to event occurrence not overflows */ + aux_pause_on_evt : 1, /* on event, pause AUX area tracing */ + aux_resume_on_evt : 1, /* on event, resume AUX area tracing */ + aux_emit_on_evt : 1, /* generate AUX records instead of events */ + aux_nr_on_evt : 5, /* AUX area tracing reference number */ + aux_no_ip_on_evt : 1, /* suppress IP in AUX records */ + __reserved_3 : 13; }; };
Hi Note for V12: There was a small conflict between the Intel PT changes in "KVM: x86: Fix Intel PT Host/Guest mode when host tracing" and the changes in this patch set, so I have put the patch sets together, along with outstanding fix "perf/x86/intel/pt: Fix buffer full but size is 0 case" Cover letter for KVM changes (patches 2 to 4): There is a long-standing problem whereby running Intel PT on host and guest in Host/Guest mode, causes VM-Entry failure. The motivation for this patch set is to provide a fix for stable kernels prior to the advent of the "Mediated Passthrough vPMU" patch set: https://lore.kernel.org/kvm/20240801045907.4010984-1-mizhang@google.com/ which would render a large part of the fix unnecessary but likely not be suitable for backport to stable due to its size and complexity. Ideally, this patch set would be applied before "Mediated Passthrough vPMU" Note that the fix does not conflict with "Mediated Passthrough vPMU", it is just that "Mediated Passthrough vPMU" will make the code to stop and restart Intel PT unnecessary. Note for V11: Moving aux_paused into a union within struct hw_perf_event caused a regression because aux_paused was being written unconditionally even though it is valid only for AUX (e.g. Intel PT) PMUs. That is fixed in V11. Hardware traces, such as instruction traces, can produce a vast amount of trace data, so being able to reduce tracing to more specific circumstances can be useful. The ability to pause or resume tracing when another event happens, can do that. These patches add such a facilty and show how it would work for Intel Processor Trace. Maintainers of other AUX area tracing implementations are requested to consider if this is something they might employ and then whether or not the ABI would work for them. Note, thank you to James Clark (ARM) for evaluating the API for Coresight. Suzuki K Poulose (ARM) also responded positively to the RFC. Changes to perf tools are now (since V4) fleshed out. Please note, Intel® Architecture Instruction Set Extensions and Future Features Programming Reference March 2024 319433-052, currently: https://cdrdv2.intel.com/v1/dl/getContent/671368 introduces hardware pause / resume for Intel PT in a feature named Intel PT Trigger Tracing. For that more fields in perf_event_attr will be necessary. The main differences are: - it can be applied not just to overflows, but optionally to every event - a packet is emitted into the trace, optionally with IP information - no PMI - works with PMC and DR (breakpoint) events only Here are the proposed additions to perf_event_attr, please comment: Changes in V12: Add previously sent patch "perf/x86/intel/pt: Fix buffer full but size is 0 case" Add previously sent patch set "KVM: x86: Fix Intel PT Host/Guest mode when host tracing" Rebase on current tip plus patch set "KVM: x86: Fix Intel PT Host/Guest mode when host tracing" Changes in V11: perf/core: Add aux_pause, aux_resume, aux_start_paused Make assignment to event->hw.aux_paused conditional on (pmu->capabilities & PERF_PMU_CAP_AUX_PAUSE). perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling Remove definition of has_aux_action() because it has already been added as an inline function. perf/x86/intel/pt: Fix sampling synchronization perf tools: Enable evsel__is_aux_event() to work for ARM/ARM64 perf tools: Enable evsel__is_aux_event() to work for S390_CPUMSF Dropped because they have already been applied Changes in V10: perf/core: Add aux_pause, aux_resume, aux_start_paused Move aux_paused into a union within struct hw_perf_event. Additional comment wrt PERF_EF_PAUSE/PERF_EF_RESUME. Factor out has_aux_action() as an inline function. Use scoped_guard for irqsave. Move calls of perf_event_aux_pause() from __perf_event_output() to __perf_event_overflow(). Changes in V9: perf/x86/intel/pt: Fix sampling synchronization New patch perf/core: Add aux_pause, aux_resume, aux_start_paused Move aux_paused to struct hw_perf_event perf/x86/intel/pt: Add support for pause / resume Add more comments and barriers for resume_allowed and pause_allowed Always use WRITE_ONCE with resume_allowed Changes in V8: perf tools: Parse aux-action Fix clang warning: util/auxtrace.c:821:7: error: missing field 'aux_action' initializer [-Werror,-Wmissing-field-initializers] 821 | {NULL}, | ^ Changes in V7: Add Andi's Reviewed-by for patches 2-12 Re-base Changes in V6: perf/core: Add aux_pause, aux_resume, aux_start_paused Removed READ/WRITE_ONCE from __perf_event_aux_pause() Expanded comment about guarding against NMI Changes in V5: perf/core: Add aux_pause, aux_resume, aux_start_paused Added James' Ack perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling New patch perf tools Added Ian's Ack Changes in V4: perf/core: Add aux_pause, aux_resume, aux_start_paused Rename aux_output_cfg -> aux_action Reorder aux_action bits from: aux_pause, aux_resume, aux_start_paused to: aux_start_paused, aux_pause, aux_resume Fix aux_action bits __u64 -> __u32 coresight: Have a stab at support for pause / resume Dropped perf tools All new patches Changes in RFC V3: coresight: Have a stab at support for pause / resume 'mode' -> 'flags' so it at least compiles Changes in RFC V2: Use ->stop() / ->start() instead of ->pause_resume() Move aux_start_paused bit into aux_output_cfg Tighten up when Intel PT pause / resume is allowed Add an example of how it might work for CoreSight Adrian Hunter (14): perf/x86/intel/pt: Fix buffer full but size is 0 case KVM: x86: Fix Intel PT IA32_RTIT_CTL MSR validation KVM: x86: Fix Intel PT Host/Guest mode when host tracing also KVM: selftests: Add guest Intel PT test perf/core: Add aux_pause, aux_resume, aux_start_paused perf/x86/intel/pt: Add support for pause / resume perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling perf tools: Add aux_start_paused, aux_pause and aux_resume perf tools: Add aux-action config term perf tools: Parse aux-action perf tools: Add missing_features for aux_start_paused, aux_pause, aux_resume perf intel-pt: Improve man page format perf intel-pt: Add documentation for pause / resume perf intel-pt: Add a test for pause / resume arch/x86/events/intel/core.c | 4 +- arch/x86/events/intel/pt.c | 209 +++++++- arch/x86/events/intel/pt.h | 16 + arch/x86/include/asm/intel_pt.h | 4 + arch/x86/kvm/vmx/vmx.c | 26 +- arch/x86/kvm/vmx/vmx.h | 1 - include/linux/perf_event.h | 28 + include/uapi/linux/perf_event.h | 11 +- kernel/events/core.c | 72 ++- kernel/events/internal.h | 1 + tools/include/uapi/linux/perf_event.h | 11 +- tools/perf/Documentation/perf-intel-pt.txt | 596 +++++++++++++-------- tools/perf/Documentation/perf-record.txt | 4 + tools/perf/builtin-record.c | 4 +- tools/perf/tests/shell/test_intel_pt.sh | 28 + tools/perf/util/auxtrace.c | 67 ++- tools/perf/util/auxtrace.h | 6 +- tools/perf/util/evsel.c | 13 +- tools/perf/util/evsel.h | 1 + tools/perf/util/evsel_config.h | 1 + tools/perf/util/parse-events.c | 10 + tools/perf/util/parse-events.h | 1 + tools/perf/util/parse-events.l | 1 + tools/perf/util/perf_event_attr_fprintf.c | 3 + tools/perf/util/pmu.c | 1 + tools/testing/selftests/kvm/Makefile | 1 + .../selftests/kvm/include/x86_64/processor.h | 1 + tools/testing/selftests/kvm/x86_64/intel_pt.c | 381 +++++++++++++ 28 files changed, 1238 insertions(+), 264 deletions(-) create mode 100644 tools/testing/selftests/kvm/x86_64/intel_pt.c Regards Adrian