linux-kernel - [PATCH 6/7] perf: teach perf inject to merge sched_stat_* and sched

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1320670457-2633428-7-git-send-email-avagin@openvz.org>
Date:	Mon,  7 Nov 2011 15:54:16 +0300
From:	Andrew Vagin <avagin@...nvz.org>
To:	linux-kernel@...r.kernel.org
Cc:	Arun Sharma <asharma@...com>,
	Peter Zijlstra <a.p.zijlstra@...llo.nl>,
	Paul Mackerras <paulus@...ba.org>, Ingo Molnar <mingo@...e.hu>,
	Arnaldo Carvalho de Melo <acme@...stprotocols.net>,
	avagin@...nvz.org, devel@...nvz.org
Subject: [PATCH 6/7] perf: teach perf inject to merge sched_stat_* and sched_switch events

You may want to know where and how long a task is sleeping. A callchain
may be found in sched_switch and a time slice in stat_iowait, so I add
handler in perf inject for merging this events.

My code saves sched_switch event for each process and when it meets
stat_iowait, it reports the sched_switch event, because this event
contains a correct callchain. By another words it replaces all
stat_iowait events on proper sched_switch events.

Signed-off-by: Andrew Vagin <avagin@...nvz.org>
---
 tools/perf/builtin-inject.c |   87 +++++++++++++++++++++++++++++++++++++++++++
 1 files changed, 87 insertions(+), 0 deletions(-)

diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index 8df8b71..d0af19d 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -12,6 +12,8 @@
 #include "util/debug.h"
 
 #include "util/parse-options.h"
+#include "util/trace-event.h"
+
 
 static char		const *input_name	= "-";
 static const char	*output_name		= "-";
@@ -20,6 +22,7 @@ static int		output;
 static u64		bytes_written		= 0;
 
 static bool		inject_build_ids;
+static bool		inject_sched_stat;
 
 static int perf_event__repipe_synth(union perf_event *event,
 				    struct perf_session *session __used)
@@ -179,6 +182,85 @@ repipe:
 	return 0;
 }
 
+struct event_entry
+{
+	struct list_head list;
+	u32 pid;
+	union perf_event event[0];
+};
+
+static LIST_HEAD(samples);
+
+static int perf_event__sched_stat(union perf_event *event,
+				      struct perf_sample *sample,
+				      struct perf_evsel *evsel __used,
+				      struct perf_session *session)
+{
+	int type;
+	struct event *e;
+	const char *evname = NULL;
+	uint32_t size;
+	struct event_entry *ent;
+	union perf_event *event_sw = NULL;
+	struct perf_sample sample_sw;
+	int sched_process_exit;
+
+	size = event->header.size;
+
+	type = trace_parse_common_type(sample->raw_data);
+	e = trace_find_event(type);
+	if (e)
+		evname = e->name;
+
+	sched_process_exit = !strcmp(evname, "sched_process_exit");
+
+	if (!strcmp(evname, "sched_switch") ||  sched_process_exit) {
+		list_for_each_entry(ent, &samples, list)
+			if (sample->pid == ent->pid)
+				break;
+
+		if (&ent->list != &samples) {
+			list_del(&ent->list);
+			free(ent);
+		}
+
+		if (sched_process_exit)
+			return 0;
+
+		ent = malloc(size + sizeof(struct event_entry));
+		ent->pid = sample->pid;
+		memcpy(&ent->event, event, size);
+		list_add(&ent->list, &samples);
+		return 0;
+
+	} else if (!strncmp(evname, "sched_stat_", 11)) {
+		u32 pid;
+
+		pid = raw_field_value(e, "pid", sample->raw_data);
+
+		list_for_each_entry(ent, &samples, list) {
+			if (pid == ent->pid)
+				break;
+		}
+
+		if (&ent->list == &samples) {
+			pr_debug("Could not find sched_switch for pid %u\n", pid);
+			return 0;
+		}
+
+		event_sw = &ent->event[0];
+		perf_session__parse_sample(session, event_sw, &sample_sw);
+		sample_sw.period = sample->period;
+		sample_sw.time = sample->time;
+		perf_session__change_sample(session, event_sw, &sample_sw);
+		perf_event__repipe(event_sw, &sample_sw, session);
+		return 0;
+	}
+
+	perf_event__repipe(event, sample, session);
+
+	return 0;
+}
 struct perf_event_ops inject_ops = {
 	.sample		= perf_event__repipe_sample,
 	.mmap		= perf_event__repipe,
@@ -214,6 +296,9 @@ static int __cmd_inject(void)
 		inject_ops.mmap		= perf_event__repipe_mmap;
 		inject_ops.fork		= perf_event__repipe_task;
 		inject_ops.tracing_data	= perf_event__repipe_tracing_data;
+	} else if (inject_sched_stat) {
+		inject_ops.sample	= perf_event__sched_stat;
+		inject_ops.ordered_samples = true;
 	}
 
 	session = perf_session__new(input_name, O_RDONLY, false, true, &inject_ops);
@@ -241,6 +326,8 @@ static const char * const report_usage[] = {
 static const struct option options[] = {
 	OPT_BOOLEAN('b', "build-ids", &inject_build_ids,
 		    "Inject build-ids into the output stream"),
+	OPT_BOOLEAN('s', "sched-stat", &inject_sched_stat,
+		    "correct call-chains for shed-stat-*"),
 	OPT_STRING('i', "input", &input_name, "file",
 		    "input file name"),
 	OPT_STRING('o', "output", &output_name, "file",
-- 
1.7.1

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