perf trace: Introduce --filter-pids

When tracing in X we get event loops due to the tracing activity, i.e.
updates to a gnome-terminal that generate syscalls for X.org, etc.

To get a more useful view of what is happening, syscall wise, system
wide, we need to filter those, like in:

 # ps ax|egrep '981|2296|1519' | grep -v egrep
   981 tty1 Ss+ 5:40 /usr/bin/Xorg :0 -background none ...
  1519 ?    Sl  2:22 /usr/bin/gnome-shell
  2296 ?    Sl  4:16 /usr/libexec/gnome-terminal-server
 #

 # trace -e write --filter-pids 981,2296,1519
    0.385 ( 0.021 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 136) = 136
    0.922 ( 0.014 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 140) = 140
 5006.525 ( 0.029 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 136) = 136
 5007.235 ( 0.023 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 140) = 140
 5177.646 ( 0.018 ms): rtkit-daemon/782 write(fd: 5<anon_inode:[eventfd]>, buf: 0x7f7eea70be88, count: 8) = 8
 8314.497 ( 0.004 ms): gsd-locate-poi/2084 write(fd: 5<anon_inode:[eventfd]>, buf: 0x7fffe96af7b0, count: 8) = 8
 8314.518 ( 0.002 ms): gsd-locate-poi/2084 write(fd: 5<anon_inode:[eventfd]>, buf: 0x7fffe96af0e0, count: 8) = 8
 ^C#

When this option is used the tracer pid is also filtered.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-f5qmiyy7c0uxdm21ncatpeek@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

2 files changed, 50 insertions, 2 deletions

diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 7e1b1f2bb83c..d6778e66fa92 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -55,6 +55,9 @@ OPTIONS
 --uid=::
         Record events in threads owned by uid. Name or number.
 
+--filter-pids=::
+        Filter out events for these pids and for 'trace' itself (comma separated list).
+
 -v::
 --verbose=::
         Verbosity level.
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index cb33e4c8821a..60ccfd52189d 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1229,6 +1229,10 @@ struct trace {
         const char              *last_vfs_getname;
         struct intlist          *tid_list;
         struct intlist          *pid_list;
+        struct {
+                size_t          nr;
+                pid_t           *entries;
+        }                       filter_pids;
         double                  duration_filter;
         double                  runtime_ms;
         struct {
@@ -2157,8 +2161,15 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
          * workload was, and in that case we will fill in the thread_map when
          * we fork the workload in perf_evlist__prepare_workload.
          */
-        if (evlist->threads->map[0] == -1)
-                perf_evlist__set_filter_pid(evlist, getpid());
+        if (trace->filter_pids.nr > 0)
+                err = perf_evlist__set_filter_pids(evlist, trace->filter_pids.nr, trace->filter_pids.entries);
+        else if (evlist->threads->map[0] == -1)
+                err = perf_evlist__set_filter_pid(evlist, getpid());
+
+        if (err < 0) {
+                printf("err=%d,%s\n", -err, strerror(-err));
+                exit(1);
+        }
 
         err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
         if (err < 0)
@@ -2491,6 +2502,38 @@ static int trace__set_duration(const struct option *opt, const char *str,
         return 0;
 }
 
+static int trace__set_filter_pids(const struct option *opt, const char *str,
+                                  int unset __maybe_unused)
+{
+        int ret = -1;
+        size_t i;
+        struct trace *trace = opt->value;
+        /*
+         * FIXME: introduce a intarray class, plain parse csv and create a
+         * { int nr, int entries[] } struct...
+         */
+        struct intlist *list = intlist__new(str);
+
+        if (list == NULL)
+                return -1;
+
+        i = trace->filter_pids.nr = intlist__nr_entries(list) + 1;
+        trace->filter_pids.entries = calloc(i, sizeof(pid_t));
+
+        if (trace->filter_pids.entries == NULL)
+                goto out;
+
+        trace->filter_pids.entries[0] = getpid();
+
+        for (i = 1; i < trace->filter_pids.nr; ++i)
+                trace->filter_pids.entries[i] = intlist__entry(list, i - 1)->i;
+
+        intlist__delete(list);
+        ret = 0;
+out:
+        return ret;
+}
+
 static int trace__open_output(struct trace *trace, const char *filename)
 {
         struct stat st;
@@ -2581,6 +2624,8 @@ int cmd_trace(int argc, const char **argv, const char *prefix __maybe_unused)
                     "trace events on existing process id"),
         OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
                     "trace events on existing thread id"),
+        OPT_CALLBACK(0, "filter-pids", &trace, "float",
+                     "show only events with duration > N.M ms", trace__set_filter_pids),
         OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
                     "system-wide collection from all CPUs"),
         OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",