[PATCH V8 7/8] perf, x86: introduce PERF_RECORD_LOST_SAMPLES

[Kan Liang]

From: Kan Liang <kan.liang@xxxxxxxxx>

After enlarging the PEBS interrupt threshold, there may be some mixed up
PEBS samples which are discarded by kernel. This patch drives the kernel
to emit a PERF_RECORD_LOST_SAMPLES record with the number of possible
discards when it is impossible to demux the samples. It makes sure the
user is not left in the dark about such discards.

Signed-off-by: Kan Liang <kan.liang@xxxxxxxxx>
---
 arch/x86/kernel/cpu/perf_event_intel_ds.c | 16 ++++++++++----
 include/linux/perf_event.h                |  3 +++
 include/uapi/linux/perf_event.h           | 12 +++++++++++
 kernel/events/core.c                      | 35 +++++++++++++++++++++++++++++++
 4 files changed, 62 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index fc03e7a..cdd331f 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -1127,6 +1127,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 	void *base, *at, *top;
 	int bit;
 	short counts[MAX_PEBS_EVENTS] = {};
+	short error[MAX_PEBS_EVENTS] = {};
 
 	if (!x86_pmu.pebs_active)
 		return;
@@ -1170,21 +1171,28 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 			/* slow path */
 			pebs_status = p->status & cpuc->pebs_enabled;
 			pebs_status &= (1ULL << MAX_PEBS_EVENTS) - 1;
-			if (pebs_status != (1 << bit))
+			if (pebs_status != (1 << bit)) {
+				error[bit]++;
 				continue;
+			}
 		}
 		counts[bit]++;
 	}
 
 	for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
-		if (counts[bit] == 0)
+		if ((counts[bit] == 0) && (error[bit] == 0))
 			continue;
 		event = cpuc->events[bit];
 		WARN_ON_ONCE(!event);
 		WARN_ON_ONCE(!event->attr.precise_ip);
 
-		__intel_pmu_pebs_event(event, iregs, base,
-				       top, bit, counts[bit]);
+		/* log dropped samples number */
+		if (error[bit])
+			perf_log_lost_samples(event, error[bit]);
+
+		if (counts[bit])
+			__intel_pmu_pebs_event(event, iregs, base,
+					       top, bit, counts[bit]);
 	}
 }
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index bed1b6f..d47d792 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -747,6 +747,9 @@ perf_event__output_id_sample(struct perf_event *event,
 			     struct perf_output_handle *handle,
 			     struct perf_sample_data *sample);
 
+extern void
+perf_log_lost_samples(struct perf_event *event, u64 lost);
+
 static inline bool is_sampling_event(struct perf_event *event)
 {
 	return event->attr.sample_period != 0;
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 309211b..2c1ae5c 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -800,6 +800,18 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_ITRACE_START		= 12,
 
+	/*
+	 * Records the dropped/lost sample number.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				id;
+	 *	u64				lost;
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_LOST_SAMPLES		= 13,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4d221a4..1337fe3 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5927,6 +5927,41 @@ void perf_event_aux_event(struct perf_event *event, unsigned long head,
 }
 
 /*
+ * Lost/dropped samples logging
+ */
+void perf_log_lost_samples(struct perf_event *event, u64 lost)
+{
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	int ret;
+
+	struct {
+		struct perf_event_header	header;
+		u64				id;
+		u64				lost;
+	} lost_samples_event = {
+		.header = {
+			.type = PERF_RECORD_LOST_SAMPLES,
+			.misc = 0,
+			.size = sizeof(lost_samples_event),
+		},
+		.id		= event->id,
+		.lost		= lost,
+	};
+
+	perf_event_header__init_id(&lost_samples_event.header, &sample, event);
+
+	ret = perf_output_begin(&handle, event,
+				lost_samples_event.header.size);
+	if (ret)
+		return;
+
+	perf_output_put(&handle, lost_samples_event);
+	perf_event__output_id_sample(event, &handle, &sample);
+	perf_output_end(&handle);
+}
+
+/*
  * IRQ throttle logging
  */
 
-- 
1.8.3.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/