[PATCH v2] perf tools: 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:

 # 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 perf's filter. Now
user is allowed to do the above work with:

  # perf record -e ... --filter='common_pid != $PERFPID' -a sleep 10

This patch adds the variable replacement code to perf_evsel__apply_filter(),
before PERF_EVENT_IOC_SET_FILTER ioctl, so not only 'perf record', all
subcommands which uses filter can utilize $PERFPID.

Andi Kleen sent a similar patch at 2014, but wasn't applied, the
reason is not clear.

Signed-off-by: Wang Nan <wangnan0@xxxxxxxxxx>
---

This patch is based on Arnaldo Carvalho de Melo's git tree:

 https://git.kernel.org/cgit/linux/kernel/git/acme/linux.git/commit/?h=perf/core

---
 tools/perf/Documentation/perf-record.txt |   5 +-
 tools/perf/util/evsel.c                  | 110 ++++++++++++++++++++++++++++++-
 2 files changed, 111 insertions(+), 4 deletions(-)

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 9b9d9d0..9c67482 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -61,7 +61,10 @@ OPTIONS
 	  "perf report" to view group events together.
 
 --filter=<filter>::
-        Event filter.
+        Event filter. $PERFPID is allowed to be used to represent perf's own pid.
+        Note that '$' has special meaning for shell. Don't forget to use ''
+        quotation marks or to use '\' to escape when using '$PERFPID' in command
+        line.
 
 -a::
 --all-cpus::
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 83c0803..7f2a1a5 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -816,12 +816,116 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel, int ncpus, int nthrea
 	return 0;
 }
 
+static int
+perf_evsel__append_filter_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, sizeof(pid_buf), "%d", self_pid);
+		strncat(new_filter, pid_buf, *pspace);
+		*pspace -= strlen(pid_buf);
+		if (*pspace < 0)
+			return -1;
+		return 0;
+	}
+
+	return -1;
+}
+
+static const char *
+perf_evsel__postproc_filter(const char *filter)
+{
+	char *dollar = NULL, *sep = NULL, *p;
+	char *old_filter = NULL, *new_filter = NULL;
+	ssize_t space;
+
+	if (!filter)
+		return NULL;
+
+	dollar = strchr(filter, '$');
+	if (!dollar)
+		return filter;
+
+	p = old_filter = strdup(filter);
+	if (!old_filter) {
+		pr_warning("Can't alloc memory when postprocing filter '%s'\n",
+			   filter);
+		return filter;
+	}
+
+	dollar = old_filter + (dollar - filter);
+
+	/*
+	 * See perf_event_set_filter(). Length of a valid filter is
+	 * limited by page_size.
+	 */
+	new_filter = malloc(page_size);
+	if (!new_filter) {
+		pr_warning("Can't alloc memory when postprocing filter '%s'\n",
+			   filter);
+		goto errout;
+	}
+
+	*new_filter = '\0';
+	space = page_size - 1;
+
+	while (1) {
+		if (dollar)
+			*dollar = '\0';
+		strncat(new_filter, p, space);
+		space -= strlen(p);
+		if (space < 0)
+			goto errout;
+		if (!dollar)
+			break;
+
+		sep = strchr(dollar + 1, ' ');
+		if (sep)
+			*sep = '\0';
+
+		if (perf_evsel__append_filter_token(dollar + 1, new_filter,
+						    &space)) {
+			pr_warning("Filter become too long: '%s'\n", filter);
+			goto errout;
+		}
+
+		if (!sep)
+			break;
+
+		p = sep;
+		*p = ' ';
+		dollar = strchr(p, '$');
+	}
+
+	free(old_filter);
+	return new_filter;
+
+errout:
+	free(old_filter);
+	free(new_filter);
+	return filter;
+}
+
 int perf_evsel__apply_filter(struct perf_evsel *evsel, int ncpus, int nthreads,
 			     const char *filter)
 {
-	return perf_evsel__run_ioctl(evsel, ncpus, nthreads,
-				     PERF_EVENT_IOC_SET_FILTER,
-				     (void *)filter);
+	const char *real_filter;
+	int err;
+
+	real_filter = perf_evsel__postproc_filter(filter);
+	if (!real_filter)
+		real_filter = filter;
+
+	pr_debug("set filter: '%s'\n", real_filter);
+	err = perf_evsel__run_ioctl(evsel, ncpus, nthreads,
+				    PERF_EVENT_IOC_SET_FILTER,
+				    (void *)real_filter);
+	if (real_filter != filter)
+		free((void *)real_filter);
+	return err;
 }
 
 int perf_evsel__set_filter(struct perf_evsel *evsel, const char *filter)
-- 
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/