[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20240216235203.229256-2-irogers@google.com>
Date: Fri, 16 Feb 2024 15:51:55 -0800
From: Ian Rogers <irogers@...gle.com>
To: Peter Zijlstra <peterz@...radead.org>, Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>, Namhyung Kim <namhyung@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>, Jiri Olsa <jolsa@...nel.org>,
Ian Rogers <irogers@...gle.com>, Adrian Hunter <adrian.hunter@...el.com>,
Nathan Chancellor <nathan@...nel.org>, Nick Desaulniers <ndesaulniers@...gle.com>,
Bill Wendling <morbo@...gle.com>, Justin Stitt <justinstitt@...gle.com>,
Athira Jajeev <atrajeev@...ux.vnet.ibm.com>, James Clark <james.clark@....com>,
Kan Liang <kan.liang@...ux.intel.com>, Yang Jihong <yangjihong1@...wei.com>,
linux-kernel@...r.kernel.org, linux-perf-users@...r.kernel.org,
llvm@...ts.linux.dev
Subject: [PATCH v5 1/8] perf thread_map: Skip exited threads when scanning /proc
Scanning /proc is inherently racy. Scanning /proc/pid/task within that
is also racy as the pid can terminate. Rather than failing in
__thread_map__new_all_cpus, skip pids for such failures.
Signed-off-by: Ian Rogers <irogers@...gle.com>
---
tools/perf/util/thread_map.c | 9 ++++-----
1 file changed, 4 insertions(+), 5 deletions(-)
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index ea3b431b9783..b5f12390c355 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -109,9 +109,10 @@ static struct perf_thread_map *__thread_map__new_all_cpus(uid_t uid)
snprintf(path, sizeof(path), "/proc/%d/task", pid);
items = scandir(path, &namelist, filter, NULL);
- if (items <= 0)
- goto out_free_closedir;
-
+ if (items <= 0) {
+ pr_debug("scandir for %d returned empty, skipping\n", pid);
+ continue;
+ }
while (threads->nr + items >= max_threads) {
max_threads *= 2;
grow = true;
@@ -152,8 +153,6 @@ static struct perf_thread_map *__thread_map__new_all_cpus(uid_t uid)
for (i = 0; i < items; i++)
zfree(&namelist[i]);
free(namelist);
-
-out_free_closedir:
zfree(&threads);
goto out_closedir;
}
--
2.44.0.rc0.258.g7320e95886-goog
Powered by blists - more mailing lists