perf session: Fallback to unordered processing if no sample_id_all

If we are running the new perf on an old kernel without support for
sample_id_all, we should fall back to the old unordered processing of
events. If we didn't than we would *always* process events without
timestamps out of order, whether or not we hit a reordering race. In
other words, instead of there being a chance of not attributing samples
correctly, we would guarantee that samples would not be attributed.

While processing all events without timestamps before events with
timestamps may seem like an intuitive solution, it falls down as
PERF_RECORD_EXIT events would also be processed before any samples.
Even with a workaround for that case, samples before/after an exec would
not be attributed correctly.

This patch allows commands to indicate whether they need to fall back to
unordered processing, so that commands that do not care about timestamps
on every event will not be affected. If we do fallback, this will print
out a warning if report -D was invoked.

This patch adds the test in perf_session__new so that we only need to
test once per session. Commands that do not use an event_ops (such as
record and top) can simply pass NULL in it's place.

Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
LKML-Reference: <1291951882-sup-6069@au1.ibm.com>
Signed-off-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/builtin-annotate.c

@@ -382,7 +382,7 @@ static int __cmd_annotate(void)
 	int ret;
 	struct perf_session *session;
 
-	session = perf_session__new(input_name, O_RDONLY, force, false);
+	session = perf_session__new(input_name, O_RDONLY, force, false, &event_ops);
 	if (session == NULL)
 		return -ENOMEM;
 

tools/perf/builtin-buildid-list.c

@@ -39,7 +39,8 @@ static int __cmd_buildid_list(void)
 	int err = -1;
 	struct perf_session *session;
 
-	session = perf_session__new(input_name, O_RDONLY, force, false);
+	session = perf_session__new(input_name, O_RDONLY, force, false,
+				    &build_id__mark_dso_hit_ops);
 	if (session == NULL)
 		return -1;
 

tools/perf/builtin-diff.c

@@ -142,8 +142,8 @@ static int __cmd_diff(void)
 	int ret, i;
 	struct perf_session *session[2];
 
-	session[0] = perf_session__new(input_old, O_RDONLY, force, false);
+	session[0] = perf_session__new(input_old, O_RDONLY, force, false, &event_ops);
-	session[1] = perf_session__new(input_new, O_RDONLY, force, false);
+	session[1] = perf_session__new(input_new, O_RDONLY, force, false, &event_ops);
 	if (session[0] == NULL || session[1] == NULL)
 		return -ENOMEM;
 

tools/perf/builtin-inject.c

@@ -196,7 +196,7 @@ static int __cmd_inject(void)
 		inject_ops.tracing_data	= event__repipe_tracing_data;
 	}
 
-	session = perf_session__new(input_name, O_RDONLY, false, true);
+	session = perf_session__new(input_name, O_RDONLY, false, true, &inject_ops);
 	if (session == NULL)
 		return -ENOMEM;
 

tools/perf/builtin-kmem.c

@@ -481,7 +481,8 @@ static void sort_result(void)
 static int __cmd_kmem(void)
 {
 	int err = -EINVAL;
-	struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false);
+	struct perf_session *session = perf_session__new(input_name, O_RDONLY,
+							 0, false, &event_ops);
 	if (session == NULL)
 		return -ENOMEM;
 

tools/perf/builtin-lock.c

@@ -858,7 +858,7 @@ static struct perf_event_ops eops = {
 
 static int read_events(void)
 {
-	session = perf_session__new(input_name, O_RDONLY, 0, false);
+	session = perf_session__new(input_name, O_RDONLY, 0, false, &eops);
 	if (!session)
 		die("Initializing perf session failed\n");
 

tools/perf/builtin-record.c

@@ -572,7 +572,7 @@ static int __cmd_record(int argc, const char **argv)
 	}
 
 	session = perf_session__new(output_name, O_WRONLY,
-				    write_mode == WRITE_FORCE, false);
+				    write_mode == WRITE_FORCE, false, NULL);
 	if (session == NULL) {
 		pr_err("Not enough memory for reading perf file header\n");
 		return -1;

tools/perf/builtin-report.c

@@ -308,7 +308,7 @@ static int __cmd_report(void)
 
 	signal(SIGINT, sig_handler);
 
-	session = perf_session__new(input_name, O_RDONLY, force, false);
+	session = perf_session__new(input_name, O_RDONLY, force, false, &event_ops);
 	if (session == NULL)
 		return -ENOMEM;
 

tools/perf/builtin-sched.c

@@ -1643,7 +1643,8 @@ static struct perf_event_ops event_ops = {
 static int read_events(void)
 {
 	int err = -EINVAL;
-	struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false);
+	struct perf_session *session = perf_session__new(input_name, O_RDONLY,
+							 0, false, &event_ops);
 	if (session == NULL)
 		return -ENOMEM;
 

tools/perf/builtin-script.c

@@ -779,7 +779,7 @@ int cmd_script(int argc, const char **argv, const char *prefix __used)
 	if (!script_name)
 		setup_pager();
 
-	session = perf_session__new(input_name, O_RDONLY, 0, false);
+	session = perf_session__new(input_name, O_RDONLY, 0, false, &event_ops);
 	if (session == NULL)
 		return -ENOMEM;
 

tools/perf/builtin-timechart.c

@@ -937,7 +937,8 @@ static struct perf_event_ops event_ops = {
 
 static int __cmd_timechart(void)
 {
-	struct perf_session *session = perf_session__new(input_name, O_RDONLY, 0, false);
+	struct perf_session *session = perf_session__new(input_name, O_RDONLY,
+							 0, false, &event_ops);
 	int ret = -EINVAL;
 
 	if (session == NULL)

tools/perf/builtin-top.c

@@ -1272,7 +1272,7 @@ static int __cmd_top(void)
 	 * FIXME: perf_session__new should allow passing a O_MMAP, so that all this
 	 * mmap reading, etc is encapsulated in it. Use O_WRONLY for now.
 	 */
-	struct perf_session *session = perf_session__new(NULL, O_WRONLY, false, false);
+	struct perf_session *session = perf_session__new(NULL, O_WRONLY, false, false, NULL);
 	if (session == NULL)
 		return -ENOMEM;
 

tools/perf/util/session.c

@@ -125,7 +125,9 @@ static void perf_session__destroy_kernel_maps(struct perf_session *self)
 	machines__destroy_guest_kernel_maps(&self->machines);
 }
 
-struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe)
+struct perf_session *perf_session__new(const char *filename, int mode,
+				       bool force, bool repipe,
+				       struct perf_event_ops *ops)
 {
 	size_t len = filename ? strlen(filename) + 1 : 0;
 	struct perf_session *self = zalloc(sizeof(*self) + len);
@@ -170,6 +172,13 @@ struct perf_session *perf_session__new(const char *filename, int mode, bool forc
 	}
 
 	perf_session__update_sample_type(self);
+
+	if (ops && ops->ordering_requires_timestamps &&
+	    ops->ordered_samples && !self->sample_id_all) {
+		dump_printf("WARNING: No sample_id_all support, falling back to unordered processing\n");
+		ops->ordered_samples = false;
+	}
+
 out:
 	return self;
 out_free:

tools/perf/util/session.h

@@ -78,9 +78,12 @@ struct perf_event_ops {
 			build_id;
 	event_op2	finished_round;
 	bool		ordered_samples;
+	bool		ordering_requires_timestamps;
 };
 
-struct perf_session *perf_session__new(const char *filename, int mode, bool force, bool repipe);
+struct perf_session *perf_session__new(const char *filename, int mode,
+				       bool force, bool repipe,
+				       struct perf_event_ops *ops);
 void perf_session__delete(struct perf_session *self);
 
 void perf_event_header__bswap(struct perf_event_header *self);