[PATCH V11 09/15] perf: make events stream always parsable

[Adrian Hunter <adrian.hunter@intel.com>]

The event stream is not always parsable because the format of a sample
is dependent on the sample_type of the selected event.  When there
is more than one selected event and the sample_types are not the
same then parsing becomes problematic.  A sample can be matched to its
selected event using the ID that is allocated when the event is opened.
Unfortunately, to get the ID from the sample means first parsing it.

This patch adds a new sample format bit PERF_SAMPLE_IDENTIFER that puts
the ID at a fixed position so that the ID can be retrieved without
parsing the sample.  For sample events, that is the first position
immediately after the header.  For non-sample events, that is the last
position.

In this respect parsing samples requires that the sample_type and ID
values are recorded.  For example, perf tools records struct perf_event_attr
and the IDs within the perf.data file.  Those must be read first
before it is possible to parse samples found later in the perf.data file.

Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
 include/uapi/linux/perf_event.h | 27 ++++++++++++++++++++-------
 kernel/events/core.c            | 11 ++++++++++-
 2 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 62c25a2..42cb7b6 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -134,8 +134,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_STACK_USER			= 1U << 13,
 	PERF_SAMPLE_WEIGHT			= 1U << 14,
 	PERF_SAMPLE_DATA_SRC			= 1U << 15,
+	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
 
-	PERF_SAMPLE_MAX = 1U << 16,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 17,		/* non-ABI */
 };
 
 /*
@@ -492,12 +493,12 @@ enum perf_event_type {
 	/*
 	 * If perf_event_attr.sample_id_all is set then all event types will
 	 * have the sample_type selected fields related to where/when
-	 * (identity) an event took place (TID, TIME, ID, CPU, STREAM_ID)
-	 * described in PERF_RECORD_SAMPLE below, it will be stashed just after
-	 * the perf_event_header and the fields already present for the existing
-	 * fields, i.e. at the end of the payload. That way a newer perf.data
-	 * file will be supported by older perf tools, with these new optional
-	 * fields being ignored.
+	 * (identity) an event took place (TID, TIME, ID, STREAM_ID, CPU,
+	 * IDENTIFIER) described in PERF_RECORD_SAMPLE below, it will be stashed
+	 * just after the perf_event_header and the fields already present for
+	 * the existing fields, i.e. at the end of the payload. That way a newer
+	 * perf.data file will be supported by older perf tools, with these new
+	 * optional fields being ignored.
 	 *
 	 * struct sample_id {
 	 * 	{ u32			pid, tid; } && PERF_SAMPLE_TID
@@ -505,7 +506,12 @@ enum perf_event_type {
 	 * 	{ u64			id;       } && PERF_SAMPLE_ID
 	 * 	{ u64			stream_id;} && PERF_SAMPLE_STREAM_ID
 	 * 	{ u32			cpu, res; } && PERF_SAMPLE_CPU
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
 	 * } && perf_event_attr::sample_id_all
+	 *
+	 * Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.  The
+	 * advantage of PERF_SAMPLE_IDENTIFIER is that its position is fixed
+	 * relative to header.size.
 	 */
 
 	/*
@@ -594,6 +600,13 @@ enum perf_event_type {
 	 * struct {
 	 *	struct perf_event_header	header;
 	 *
+	 *	#
+	 *	# Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.
+	 *	# The advantage of PERF_SAMPLE_IDENTIFIER is that its position
+	 *	# is fixed relative to header.
+	 *	#
+	 *
+	 *	{ u64			id;	  } && PERF_SAMPLE_IDENTIFIER
 	 *	{ u64			ip;	  } && PERF_SAMPLE_IP
 	 *	{ u32			pid, tid; } && PERF_SAMPLE_TID
 	 *	{ u64			time;     } && PERF_SAMPLE_TIME
diff --git a/kernel/events/core.c b/kernel/events/core.c
index e82e700..776e17d 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1213,6 +1213,9 @@ static void perf_event__id_header_size(struct perf_event *event)
 	if (sample_type & PERF_SAMPLE_TIME)
 		size += sizeof(data->time);
 
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		size += sizeof(data->id);
+
 	if (sample_type & PERF_SAMPLE_ID)
 		size += sizeof(data->id);
 
@@ -4284,7 +4287,7 @@ static void __perf_event_header__init_id(struct perf_event_header *header,
 	if (sample_type & PERF_SAMPLE_TIME)
 		data->time = perf_clock();
 
-	if (sample_type & PERF_SAMPLE_ID)
+	if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER))
 		data->id = primary_event_id(event);
 
 	if (sample_type & PERF_SAMPLE_STREAM_ID)
@@ -4323,6 +4326,9 @@ static void __perf_event__output_id_sample(struct perf_output_handle *handle,
 
 	if (sample_type & PERF_SAMPLE_CPU)
 		perf_output_put(handle, data->cpu_entry);
+
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		perf_output_put(handle, data->id);
 }
 
 void perf_event__output_id_sample(struct perf_event *event,
@@ -4436,6 +4442,9 @@ void perf_output_sample(struct perf_output_handle *handle,
 
 	perf_output_put(handle, *header);
 
+	if (sample_type & PERF_SAMPLE_IDENTIFIER)
+		perf_output_put(handle, data->id);
+
 	if (sample_type & PERF_SAMPLE_IP)
 		perf_output_put(handle, data->ip);
 
-- 
1.7.11.7