[PATCH] perf record: Allow passing perf's own pid to '--filter'

[Wang Nan]

This patch allows passing perf's own PID to '--filter' by using
'@PERFPID'. This should be useful when system-widely capturing
tracepoints events.

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 introduces '@PERFPID' placeholder to '--filter' options. Now
user is allowed to the above work with:

  # perf record -e ... --filter="common_pid != @PERFPID' sleep 10

Signed-off-by: Wang Nan <wangnan0@xxxxxxxxxx>
---
 tools/perf/Documentation/perf-record.txt |  1 +
 tools/perf/util/parse-events.c           | 96 ++++++++++++++++++++++++++++++++
 2 files changed, 97 insertions(+)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 9b9d9d0..c2902d2 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -62,6 +62,7 @@ OPTIONS
 
 --filter=<filter>::
         Event filter.
+        String '@PERFPID' is allowed to be used to represent pid of 'perf' itself.
 
 -a::
 --all-cpus::
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index aaee24c..2d62957 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1175,6 +1175,101 @@ int parse_events_option(const struct option *opt, const char *str,
 	return ret;
 }
 
+#ifndef PAGE_SIZE
+# define PAGE_SIZE 4096
+#endif
+static int
+postproc_filter_append_token(const char *key, char *new_filter,
+			     ssize_t *pspace)
+{
+	if (strcmp(key, "PERFPID") == 0) {
+		char pid_buf[32];
+		pid_t self_pid = getpid();
+
+		snprintf(pid_buf, 32, "%d", self_pid);
+		strncat(new_filter, pid_buf, *pspace);
+		*pspace -= strlen(pid_buf);
+		if (*pspace < 0)
+			return -1;
+		return 0;
+	}
+
+	return -1;
+}
+
+static void postproc_filter(struct perf_evsel *evsel)
+{
+	char *at = NULL, *sep = NULL, *old_filter, *new_filter;
+	ssize_t space;
+
+	if (!evsel->filter)
+		return;
+
+	old_filter = evsel->filter;
+	at = strchr(old_filter, '@');
+	if (!at)
+		return;
+
+	/*
+	 * See perf_event_set_filter(). Length of a valid filter is
+	 * limited by PAGE_SIZE.
+	 */
+	new_filter = malloc(PAGE_SIZE);
+	if (!new_filter) {
+		fprintf(stderr, "No enough memory for post proc filter '%s'\n",
+			old_filter);
+		return;
+	}
+	*new_filter = '\0';
+	space = PAGE_SIZE - 1;
+
+	while (1) {
+		if (at)
+			*at = '\0';
+		strncat(new_filter, old_filter, space);
+		space -= strlen(old_filter);
+		if (space < 0)
+			goto errout;
+		if (!at)
+			break;
+		*at = '@';
+
+		sep = strchr(at + 1, ' ');
+		if (sep)
+			*sep = '\0';
+
+		if (postproc_filter_append_token(at + 1, new_filter, &space))
+			goto errout;
+
+		if (!sep)
+			break;
+		*sep = ' ';
+
+		old_filter = sep;
+		at = strchr(old_filter, '@');
+	}
+
+	free(evsel->filter);
+	/*
+	 * It is safe to use new_filter directly. However, try to
+	 * release some memory by strdup() a smaller string and free
+	 * new_filter, which takes a full page.
+	 */
+	evsel->filter = strdup(new_filter);
+	if (!evsel->filter)
+		evsel->filter = new_filter;
+	else
+		free(new_filter);
+	return;
+errout:
+	if (at)
+		*at = '@';
+	if (sep)
+		*sep = ' ';
+	fprintf(stderr, "Can't post proc filter '%s'\n", evsel->filter);
+	free(new_filter);
+}
+
 int parse_filter(const struct option *opt, const char *str,
 		 int unset __maybe_unused)
 {
@@ -1196,6 +1291,7 @@ int parse_filter(const struct option *opt, const char *str,
 		return -1;
 	}
 
+	postproc_filter(last);
 	return 0;
 }
 
-- 
1.8.3.4

--
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/