[PATCH 08/13] perf record: Allow filtering perf's pid via --exclude-perf

[Arnaldo Carvalho de Melo <acme@kernel.org>]

From: Wang Nan <wangnan0@huawei.com>

This patch allows 'perf record' to exclude events issued by perf itself
by '--exclude-perf' option.

Before this patch, when doing something like:

 # perf record -a -e syscalls:sys_enter_write <cmd>

One could easily get result like this:

 # /tmp/perf report --stdio
 ...
  # Overhead  Command  Shared Object       Symbol
  # ........  .......  ..................  ....................
  #
      99.99%  perf     libpthread-2.18.so  [.] __write_nocancel
      0.01%   ls       libc-2.18.so        [.] write
      0.01%   sshd     libc-2.18.so        [.] write
 ...

Where most events are generated by perf itself.

A shell trick can be done to filter perf itself out:

 # cat << EOF > ./tmp
 > #!/bin/sh
 > exec perf record -e ... --filter="common_pid != \$\$" -a sleep 10
 > EOF
 # chmod a+x ./tmp
 # ./tmp

However, doing so is user unfriendly.

This patch extracts evsel iteration framework introduced by patch 'perf
record: Apply filter to all events in a glob matching' into
foreach_evsel_in_last_glob(), and makes exclude_perf() function append
new filter expression to each evsel selected by a '-e' selector.

To avoid losing filters if user pass '--filter' after '--exclude-perf',
this patch uses perf_evsel__append_filter() in both case, instead of
perf_evsel__set_filter() which removes old filter. As a side effect, now
it is possible to use multiple '--filter' option for one selector. They
are combinded with '&&'.

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1436513770-8896-2-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-record.txt | 11 ++++-
 tools/perf/builtin-record.c              |  3 ++
 tools/perf/util/parse-events.c           | 83 +++++++++++++++++++++++++++-----
 tools/perf/util/parse-events.h           |  1 +
 4 files changed, 84 insertions(+), 14 deletions(-)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 5b47b2c88223..29e5307945bf 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -69,7 +69,16 @@ OPTIONS
 	  "perf report" to view group events together.
 
 --filter=<filter>::
-        Event filter.
+        Event filter. This option should follow a event selector (-e) which
+	selects tracepoint event(s). Multiple '--filter' options are combined
+	using '&&'.
+
+--exclude-perf::
+	Don't record events issued by perf itself. This option should follow
+	a event selector (-e) which selects tracepoint event(s). It adds a
+	filter expression 'common_pid != $PERFPID' to filters. If other
+	'--filter' exists, the new filter expression will be combined with
+	them by '&&'.
 
 -a::
 --all-cpus::
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 283fe96bdfc1..1932e27c00d8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -992,6 +992,9 @@ struct option __record_options[] = {
 		     parse_events_option),
 	OPT_CALLBACK(0, "filter", &record.evlist, "filter",
 		     "event filter", parse_filter),
+	OPT_CALLBACK_NOOPT(0, "exclude-perf", &record.evlist,
+			   NULL, "don't record events from perf itself",
+			   exclude_perf),
 	OPT_STRING('p', "pid", &record.opts.target.pid, "pid",
 		    "record events on existing process id"),
 	OPT_STRING('t', "tid", &record.opts.target.tid, "tid",
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index bbb7fbc2857e..4f807fc1b14a 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1167,27 +1167,24 @@ int parse_events_option(const struct option *opt, const char *str,
 	return ret;
 }
 
-int parse_filter(const struct option *opt, const char *str,
-		 int unset __maybe_unused)
+static int
+foreach_evsel_in_last_glob(struct perf_evlist *evlist,
+			   int (*func)(struct perf_evsel *evsel,
+				       const void *arg),
+			   const void *arg)
 {
-	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
 	struct perf_evsel *last = NULL;
+	int err;
 
 	if (evlist->nr_entries > 0)
 		last = perf_evlist__last(evlist);
 
 	do {
-		if (last == NULL || last->attr.type != PERF_TYPE_TRACEPOINT) {
-			fprintf(stderr,
-				"--filter option should follow a -e tracepoint option\n");
-			return -1;
-		}
-
-		if (perf_evsel__set_filter(last, str) < 0) {
-			fprintf(stderr,
-				"not enough memory to hold filter string\n");
+		err = (*func)(last, arg);
+		if (err)
 			return -1;
-		}
+		if (!last)
+			return 0;
 
 		if (last->node.prev == &evlist->entries)
 			return 0;
@@ -1197,6 +1194,66 @@ int parse_filter(const struct option *opt, const char *str,
 	return 0;
 }
 
+static int set_filter(struct perf_evsel *evsel, const void *arg)
+{
+	const char *str = arg;
+
+	if (evsel == NULL || evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+		fprintf(stderr,
+			"--filter option should follow a -e tracepoint option\n");
+		return -1;
+	}
+
+	if (perf_evsel__append_filter(evsel, "&&", str) < 0) {
+		fprintf(stderr,
+			"not enough memory to hold filter string\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+int parse_filter(const struct option *opt, const char *str,
+		 int unset __maybe_unused)
+{
+	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
+
+	return foreach_evsel_in_last_glob(evlist, set_filter,
+					  (const void *)str);
+}
+
+static int add_exclude_perf_filter(struct perf_evsel *evsel,
+				   const void *arg __maybe_unused)
+{
+	char new_filter[64];
+
+	if (evsel == NULL || evsel->attr.type != PERF_TYPE_TRACEPOINT) {
+		fprintf(stderr,
+			"--exclude-perf option should follow a -e tracepoint option\n");
+		return -1;
+	}
+
+	snprintf(new_filter, sizeof(new_filter), "common_pid != %d", getpid());
+
+	if (perf_evsel__append_filter(evsel, "&&", new_filter) < 0) {
+		fprintf(stderr,
+			"not enough memory to hold filter string\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+int exclude_perf(const struct option *opt,
+		 const char *arg __maybe_unused,
+		 int unset __maybe_unused)
+{
+	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
+
+	return foreach_evsel_in_last_glob(evlist, add_exclude_perf_filter,
+					  NULL);
+}
+
 static const char * const event_type_descriptors[] = {
 	"Hardware event",
 	"Software event",
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 131f29b2f132..2063048a4354 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -34,6 +34,7 @@ extern int parse_events(struct perf_evlist *evlist, const char *str,
 			struct parse_events_error *error);
 extern int parse_events_terms(struct list_head *terms, const char *str);
 extern int parse_filter(const struct option *opt, const char *str, int unset);
+extern int exclude_perf(const struct option *opt, const char *arg, int unset);
 
 #define EVENTS_HELP_MAX (128*1024)
 
-- 
2.1.0