From: Leo Yan <leo.yan@linaro.org>
To: Arnaldo Carvalho de Melo <acme@kernel.org>,
Namhyung Kim <namhyung@kernel.org>,
Ingo Molnar <mingo@redhat.com>,
Mark Rutland <mark.rutland@arm.com>,
Alexander Shishkin <alexander.shishkin@linux.intel.com>,
Jiri Olsa <jolsa@kernel.org>,
Adrian Hunter <adrian.hunter@intel.com>,
linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: Leo Yan <leo.yan@linaro.org>
Subject: [PATCH] perf record: Fix segmentation fault in record__read_lost_samples()
Date: Sat, 24 Sep 2022 19:33:46 +0800 [thread overview]
Message-ID: <20220924113346.1110909-1-leo.yan@linaro.org> (raw)
Commit a49aa8a54e86 ("perf record: Read and inject LOST_SAMPLES events")
causes segmentation fault when run the "perf mem record" command in
unprivileged mode, the output log is:
$ ./perf mem record --all-user -o perf_test.data -- ./test_program
Error:
Access to performance monitoring and observability operations is limited.
Consider adjusting /proc/sys/kernel/perf_event_paranoid setting to open
access to performance monitoring and observability operations for processes
without CAP_PERFMON, CAP_SYS_PTRACE or CAP_SYS_ADMIN Linux capability.
More information can be found at 'Perf events and tool security' document:
https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html
perf_event_paranoid setting is 4:
-1: Allow use of (almost) all events by all users
Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK
>= 0: Disallow raw and ftrace function tracepoint access
>= 1: Disallow CPU event access
>= 2: Disallow kernel profiling
To make the adjusted perf_event_paranoid setting permanent preserve it
in /etc/sysctl.conf (e.g. kernel.perf_event_paranoid = <setting>)
perf: Segmentation fault
Obtained 16 stack frames.
./perf(dump_stack+0x31) [0x55b7aa1e8070]
./perf(sighandler_dump_stack+0x36) [0x55b7aa1e815e]
./perf(+0xc9120) [0x55b7aa0a9120]
/lib/x86_64-linux-gnu/libc.so.6(+0x4251f) [0x7fd03ef8151f]
./perf(+0xccaca) [0x55b7aa0acaca]
./perf(+0xcf4ab) [0x55b7aa0af4ab]
./perf(cmd_record+0xd50) [0x55b7aa0b28df]
./perf(+0x112f77) [0x55b7aa0f2f77]
./perf(cmd_mem+0x53b) [0x55b7aa0f406c]
./perf(+0x19979c) [0x55b7aa17979c]
./perf(+0x199a37) [0x55b7aa179a37]
./perf(+0x199b95) [0x55b7aa179b95]
./perf(main+0x2c7) [0x55b7aa179fbd]
/lib/x86_64-linux-gnu/libc.so.6(+0x29d8f) [0x7fd03ef68d8f]
/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0x7f) [0x7fd03ef68e3f]
./perf(_start+0x24) [0x55b7aa089974]
Segmentation fault (core dumped)
In the unprivileged mode perf fails to open PMU event, the function
record__open() returns error and "session->evlist" is NULL; this leads
to segmentation fault when iterates "session->evlist" in the function
record__read_lost_samples().
This patch checks "session->evlist" in record__read_lost_samples(), if
"session->evlist" is NULL then the function directly bails out to avoid
segmentation fault.
Fixes: a49aa8a54e86 ("perf record: Read and inject LOST_SAMPLES events")
Signed-off-by: Leo Yan <leo.yan@linaro.org>
---
tools/perf/builtin-record.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 02e38f50a138..012b46dd4999 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -1888,6 +1888,10 @@ static void record__read_lost_samples(struct record *rec)
struct perf_record_lost_samples *lost;
struct evsel *evsel;
+ /* No any event is opened, directly bail out */
+ if (!session->evlist)
+ return;
+
lost = zalloc(PERF_SAMPLE_MAX_SIZE);
if (lost == NULL) {
pr_debug("Memory allocation failed\n");
--
2.34.1
next reply other threads:[~2022-09-24 11:33 UTC|newest]
Thread overview: 7+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-24 11:33 Leo Yan [this message]
2022-09-24 16:52 ` [PATCH] perf record: Fix segmentation fault in record__read_lost_samples() Namhyung Kim
2022-09-25 1:12 ` Leo Yan
2022-09-26 13:03 ` Arnaldo Carvalho de Melo
2022-09-26 12:59 ` Arnaldo Carvalho de Melo
2022-09-26 14:54 ` Leo Yan
2022-09-26 19:16 ` Arnaldo Carvalho de Melo
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=20220924113346.1110909-1-leo.yan@linaro.org \
--to=leo.yan@linaro.org \
--cc=acme@kernel.org \
--cc=adrian.hunter@intel.com \
--cc=alexander.shishkin@linux.intel.com \
--cc=jolsa@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-perf-users@vger.kernel.org \
--cc=mark.rutland@arm.com \
--cc=mingo@redhat.com \
--cc=namhyung@kernel.org \
/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;
as well as URLs for NNTP newsgroup(s).