1 files changed, 84 insertions, 43 deletions

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 7ce9f3f669e6..0319311dbdbb 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -806,9 +806,65 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 	return &emptyconstraint;
 }
 
-static inline bool pebs_is_enabled(struct cpu_hw_events *cpuc)
+/*
+ * We need the sched_task callback even for per-cpu events when we use
+ * the large interrupt threshold, such that we can provide PID and TID
+ * to PEBS samples.
+ */
+static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc)
+{
+	return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs);
+}
+
+static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
+{
+	struct debug_store *ds = cpuc->ds;
+	u64 threshold;
+
+	if (cpuc->n_pebs == cpuc->n_large_pebs) {
+		threshold = ds->pebs_absolute_maximum -
+			x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+	} else {
+		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
+	}
+
+	ds->pebs_interrupt_threshold = threshold;
+}
+
+static void
+pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct pmu *pmu)
 {
-	return (cpuc->pebs_enabled & ((1ULL << MAX_PEBS_EVENTS) - 1));
+	/*
+	 * Make sure we get updated with the first PEBS
+	 * event. It will trigger also during removal, but
+	 * that does not hurt:
+	 */
+	bool update = cpuc->n_pebs == 1;
+
+	if (needed_cb != pebs_needs_sched_cb(cpuc)) {
+		if (!needed_cb)
+			perf_sched_cb_inc(pmu);
+		else
+			perf_sched_cb_dec(pmu);
+
+		update = true;
+	}
+
+	if (update)
+		pebs_update_threshold(cpuc);
+}
+
+void intel_pmu_pebs_add(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	bool needed_cb = pebs_needs_sched_cb(cpuc);
+
+	cpuc->n_pebs++;
+	if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+		cpuc->n_large_pebs++;
+
+	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
 }
 
 void intel_pmu_pebs_enable(struct perf_event *event)
@@ -816,12 +872,9 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 	struct debug_store *ds = cpuc->ds;
-	bool first_pebs;
-	u64 threshold;
 
 	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
 
-	first_pebs = !pebs_is_enabled(cpuc);
 	cpuc->pebs_enabled |= 1ULL << hwc->idx;
 
 	if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT)
@@ -830,46 +883,34 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 		cpuc->pebs_enabled |= 1ULL << 63;
 
 	/*
-	 * When the event is constrained enough we can use a larger
-	 * threshold and run the event with less frequent PMI.
+	 * Use auto-reload if possible to save a MSR write in the PMI.
+	 * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
 	 */
-	if (hwc->flags & PERF_X86_EVENT_FREERUNNING) {
-		threshold = ds->pebs_absolute_maximum -
-			x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
-
-		if (first_pebs)
-			perf_sched_cb_inc(event->ctx->pmu);
-	} else {
-		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
-
-		/*
-		 * If not all events can use larger buffer,
-		 * roll back to threshold = 1
-		 */
-		if (!first_pebs &&
-		    (ds->pebs_interrupt_threshold > threshold))
-			perf_sched_cb_dec(event->ctx->pmu);
-	}
-
-	/* Use auto-reload if possible to save a MSR write in the PMI */
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
 		ds->pebs_event_reset[hwc->idx] =
 			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
 	}
+}
+
+void intel_pmu_pebs_del(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+	bool needed_cb = pebs_needs_sched_cb(cpuc);
 
-	if (first_pebs || ds->pebs_interrupt_threshold > threshold)
-		ds->pebs_interrupt_threshold = threshold;
+	cpuc->n_pebs--;
+	if (hwc->flags & PERF_X86_EVENT_FREERUNNING)
+		cpuc->n_large_pebs--;
+
+	pebs_update_state(needed_cb, cpuc, event->ctx->pmu);
 }
 
 void intel_pmu_pebs_disable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
-	struct debug_store *ds = cpuc->ds;
-	bool large_pebs = ds->pebs_interrupt_threshold >
-		ds->pebs_buffer_base + x86_pmu.pebs_record_size;
 
-	if (large_pebs)
+	if (cpuc->n_pebs == cpuc->n_large_pebs)
 		intel_pmu_drain_pebs_buffer();
 
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
@@ -879,9 +920,6 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 	else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST)
 		cpuc->pebs_enabled &= ~(1ULL << 63);
 
-	if (large_pebs && !pebs_is_enabled(cpuc))
-		perf_sched_cb_dec(event->ctx->pmu);
-
 	if (cpuc->enabled)
 		wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
 
@@ -1274,18 +1312,18 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		struct pebs_record_nhm *p = at;
 		u64 pebs_status;
 
-		/* PEBS v3 has accurate status bits */
+		pebs_status = p->status & cpuc->pebs_enabled;
+		pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+
+		/* PEBS v3 has more accurate status bits */
 		if (x86_pmu.intel_cap.pebs_format >= 3) {
-			for_each_set_bit(bit, (unsigned long *)&p->status,
-					 MAX_PEBS_EVENTS)
+			for_each_set_bit(bit, (unsigned long *)&pebs_status,
+					 x86_pmu.max_pebs_events)
 				counts[bit]++;
 
 			continue;
 		}
 
-		pebs_status = p->status & cpuc->pebs_enabled;
-		pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
-
 		/*
 		 * On some CPUs the PEBS status can be zero when PEBS is
 		 * racing with clearing of GLOBAL_STATUS.
@@ -1333,8 +1371,11 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 			continue;
 
 		event = cpuc->events[bit];
-		WARN_ON_ONCE(!event);
-		WARN_ON_ONCE(!event->attr.precise_ip);
+		if (WARN_ON_ONCE(!event))
+			continue;
+
+		if (WARN_ON_ONCE(!event->attr.precise_ip))
+			continue;
 
 		/* log dropped samples number */
 		if (error[bit])