The following commit has been merged into the perf/core branch of tip:
Commit-ID: f9bdf1f953392c9edd69a7f884f78c0390127029 Gitweb: https://git.kernel.org/tip/f9bdf1f953392c9edd69a7f884f78c0390127029 Author: Kan Liang kan.liang@linux.intel.com AuthorDate: Tue, 21 Jan 2025 07:23:01 -08:00 Committer: Peter Zijlstra peterz@infradead.org CommitterDate: Wed, 05 Feb 2025 10:29:45 +01:00
perf/x86/intel: Avoid disable PMU if !cpuc->enabled in sample read
The WARN_ON(this_cpu_read(cpu_hw_events.enabled)) in the intel_pmu_save_and_restart_reload() is triggered, when sampling read topdown events.
In a NMI handler, the cpu_hw_events.enabled is set and used to indicate the status of core PMU. The generic pmu->pmu_disable_count, updated in the perf_pmu_disable/enable pair, is not touched. However, the perf_pmu_disable/enable pair is invoked when sampling read in a NMI handler. The cpuc->enabled is mistakenly set by the perf_pmu_enable().
Avoid disabling PMU if the core PMU is already disabled. Merge the logic together.
Fixes: 7b2c05a15d29 ("perf/x86/intel: Generic support for hardware TopDown metrics") Suggested-by: Peter Zijlstra (Intel) peterz@infradead.org Signed-off-by: Kan Liang kan.liang@linux.intel.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20250121152303.3128733-2-kan.liang@linux.intel.com --- arch/x86/events/intel/core.c | 41 +++++++++++++++++++---------------- arch/x86/events/intel/ds.c | 11 +--------- arch/x86/events/perf_event.h | 2 +- 3 files changed, 25 insertions(+), 29 deletions(-)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index 2acea83..1ccc961 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -2785,28 +2785,33 @@ static u64 icl_update_topdown_event(struct perf_event *event)
DEFINE_STATIC_CALL(intel_pmu_update_topdown_event, x86_perf_event_update);
-static void intel_pmu_read_topdown_event(struct perf_event *event) +static void intel_pmu_read_event(struct perf_event *event) { - struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + if (event->hw.flags & (PERF_X86_EVENT_AUTO_RELOAD | PERF_X86_EVENT_TOPDOWN)) { + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + bool pmu_enabled = cpuc->enabled;
- /* Only need to call update_topdown_event() once for group read. */ - if ((cpuc->txn_flags & PERF_PMU_TXN_READ) && - !is_slots_event(event)) - return; + /* Only need to call update_topdown_event() once for group read. */ + if (is_metric_event(event) && (cpuc->txn_flags & PERF_PMU_TXN_READ)) + return;
- perf_pmu_disable(event->pmu); - static_call(intel_pmu_update_topdown_event)(event); - perf_pmu_enable(event->pmu); -} + cpuc->enabled = 0; + if (pmu_enabled) + intel_pmu_disable_all();
-static void intel_pmu_read_event(struct perf_event *event) -{ - if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) - intel_pmu_auto_reload_read(event); - else if (is_topdown_count(event)) - intel_pmu_read_topdown_event(event); - else - x86_perf_event_update(event); + if (is_topdown_event(event)) + static_call(intel_pmu_update_topdown_event)(event); + else + intel_pmu_drain_pebs_buffer(); + + cpuc->enabled = pmu_enabled; + if (pmu_enabled) + intel_pmu_enable_all(0); + + return; + } + + x86_perf_event_update(event); }
static void intel_pmu_enable_fixed(struct perf_event *event) diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 322963b..eb14b46 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -953,7 +953,7 @@ unlock: return 1; }
-static inline void intel_pmu_drain_pebs_buffer(void) +void intel_pmu_drain_pebs_buffer(void) { struct perf_sample_data data;
@@ -2094,15 +2094,6 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit) return NULL; }
-void intel_pmu_auto_reload_read(struct perf_event *event) -{ - WARN_ON(!(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)); - - perf_pmu_disable(event->pmu); - intel_pmu_drain_pebs_buffer(); - perf_pmu_enable(event->pmu); -} - /* * Special variant of intel_pmu_save_and_restart() for auto-reload. */ diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index 084e919..536a112 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -1644,7 +1644,7 @@ void intel_pmu_pebs_disable_all(void);
void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
-void intel_pmu_auto_reload_read(struct perf_event *event); +void intel_pmu_drain_pebs_buffer(void);
void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);