From: Arnaldo Carvalho de Melo <acme@kernel.org>
To: Namhyung Kim <namhyung@kernel.org>
Cc: Ingo Molnar <mingo@kernel.org>,
Thomas Gleixner <tglx@linutronix.de>,
James Clark <james.clark@linaro.org>,
Jiri Olsa <jolsa@kernel.org>, Ian Rogers <irogers@google.com>,
Adrian Hunter <adrian.hunter@intel.com>,
Clark Williams <williams@redhat.com>,
linux-kernel@vger.kernel.org, linux-perf-users@vger.kernel.org,
Arnaldo Carvalho de Melo <acme@redhat.com>,
Sashiko <sashiko-bot@kernel.org>,
stable@vger.kernel.org
Subject: [PATCH v4 10/21] perf evsel: Close the fds opened so far when disabling missing features
Date: Fri, 16 Oct 2026 18:20:51 -0300 [thread overview]
Message-ID: <20261016212102.76550-11-acme@kernel.org> (raw)
In-Reply-To: <20261016212102.76550-1-acme@kernel.org>
From: Arnaldo Carvalho de Melo <acme@redhat.com>
evsel__open_cpu() opens the events one by one and, when an open fails
with EINVAL and evsel__detect_missing_features() has a feature to leave
out, goes back to fallback_missing_features to open them all again from
start_cpu_map_idx, without closing what the abandoned attempt opened:
the fd of every CPU or thread that was opened before the failing one is
overwritten in the FD() array, leaking it.
Close them first, the same way out_close does when returning an error,
leaving the entries at -1 for the retry.
Fixes: af954f76eea5 ("perf tools: Check fallback error and order")
Reported-by: Sashiko <sashiko-bot@kernel.org>
Closes: https://lore.kernel.org/r/sashiko-outbox-173532@kernel.org
Cc: stable@vger.kernel.org
Assisted-by: LLM
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/evsel.c | 30 +++++++++++++++++++++---------
1 file changed, 21 insertions(+), 9 deletions(-)
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 59318fef03cb17ff..d060fca8090f6e26 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -3005,6 +3005,19 @@ static bool evsel__detect_missing_features(struct evsel *evsel, struct perf_cpu
return false;
}
+static void evsel__close_fds(struct evsel *evsel, int start_cpu_map_idx,
+ int cpu_map_idx, int thread, int nthreads)
+{
+ do {
+ while (--thread >= 0) {
+ if (FD(evsel, cpu_map_idx, thread) >= 0)
+ close(FD(evsel, cpu_map_idx, thread));
+ FD(evsel, cpu_map_idx, thread) = -1;
+ }
+ thread = nthreads;
+ } while (--cpu_map_idx >= start_cpu_map_idx);
+}
+
static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
struct perf_thread_map *threads,
int start_cpu_map_idx, int end_cpu_map_idx)
@@ -3150,8 +3163,14 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
if (err == -EMFILE && rlimit__increase_nofile(&set_rlimit))
goto retry_open;
- if (err == -EINVAL && evsel__detect_missing_features(evsel, cpu))
+ if (err == -EINVAL && evsel__detect_missing_features(evsel, cpu)) {
+ /*
+ * The restart opens the events again, so close what this
+ * attempt opened before its entries are overwritten.
+ */
+ evsel__close_fds(evsel, start_cpu_map_idx, idx, thread, nthreads);
goto fallback_missing_features;
+ }
if (evsel__precise_ip_fallback(evsel))
goto retry_open;
@@ -3161,14 +3180,7 @@ static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
threads->err_thread = thread;
old_errno = errno;
- do {
- while (--thread >= 0) {
- if (FD(evsel, idx, thread) >= 0)
- close(FD(evsel, idx, thread));
- FD(evsel, idx, thread) = -1;
- }
- thread = nthreads;
- } while (--idx >= start_cpu_map_idx);
+ evsel__close_fds(evsel, start_cpu_map_idx, idx, thread, nthreads);
errno = old_errno;
out:
if (err)
--
2.55.0
next prev parent reply other threads:[~2026-10-16 21:21 UTC|newest]
Thread overview: 23+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-16 21:20 [PATCH v4 00/21] perf test attr: Report the failures again and cope with more than one core PMU Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 01/21] perf test attr: Fix record dwarf sample_type expectation Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 02/21] perf python: Free the parse error entries when parsing fails Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 03/21] perf test attr: Allow tests to require a core PMU Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 04/21] perf test attr: Fix legacy event encodings in group tests Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 05/21] perf test attr: Fix default stat metrics expectations Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 06/21] perf test attr: Relax group checking for ungrouped expectations Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 07/21] perf evsel: Mark the event as supported when retrying an open Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 08/21] perf test attr: Ignore the core PMU type perf puts in 'config' Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 09/21] perf evsel: Don't dump probe events to PERF_TEST_ATTR Arnaldo Carvalho de Melo
2026-10-16 21:20 ` Arnaldo Carvalho de Melo [this message]
2026-10-16 21:20 ` [PATCH v4 11/21] perf test attr: Introduce mask_bits(), generalizing hide_core_pmu_type() Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 12/21] perf test attr: Accept either sample id bit perf asks for Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 13/21] perf test attr: Ignore the dummy tracking event and the terms it carries Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 14/21] perf test attr: Leave out the events of the other core PMUs Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 15/21] perf test attr: Ignore the group read_format bit the PMU count can remove Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 16/21] perf test attr: State, spelled out in a line, why a test is skipped Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 17/21] perf tests: Introduce a 'needs_mlock' suite flag Arnaldo Carvalho de Melo
2026-10-16 21:20 ` [PATCH v4 18/21] perf tests: Mark the C tests mapping perf ring buffers Arnaldo Carvalho de Melo
2026-10-16 21:21 ` [PATCH v4 19/21] perf tests: Mark the shell tests not " Arnaldo Carvalho de Melo
2026-10-16 21:21 ` [PATCH v4 20/21] perf mutex: Add a robust, process-shared mutex initializer Arnaldo Carvalho de Melo
2026-10-16 21:21 ` [PATCH v4 21/21] perf test: Take turns using the perf mlock budget in the mmaping tests Arnaldo Carvalho de Melo
2026-10-16 22:39 ` [PATCH v4 00/21] perf test attr: Report the failures again and cope with more than one core PMU Ian Rogers
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20261016212102.76550-11-acme@kernel.org \
--to=acme@kernel.org \
--cc=acme@redhat.com \
--cc=adrian.hunter@intel.com \
--cc=irogers@google.com \
--cc=james.clark@linaro.org \
--cc=jolsa@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=namhyung@kernel.org \
--cc=sashiko-bot@kernel.org \
--cc=stable@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=williams@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®