Received-SPF: softfail (google.com: domain of transitioning linux-kernel-owner@vger.kernel.org does not designate 23.128.96.19 as permitted sender) client-ip=23.128.96.19;
From:   Changbin Du <changbin.du@gmail.com>
To:     Arnaldo Carvalho de Melo <acme@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@redhat.com>
Cc:     Mark Rutland <mark.rutland@arm.com>,
        Alexander Shishkin <alexander.shishkin@linux.intel.com>,
        Jiri Olsa <jolsa@redhat.com>,
        Namhyung Kim <namhyung@kernel.org>,
        linux-perf-users@vger.kernel.org, linux-kernel@vger.kernel.org,
        Changbin Du <changbin.du@gmail.com>
Subject: [PATCH] perf trace: Avoid early exit due SIGCHLD from non-workload processes
Date:   Tue,  8 Feb 2022 22:07:25 +0800
Message-Id: <20220208140725.3947-1-changbin.du@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

The function trace__symbols_init() runs "perf-read-vdso32" and that ends up
with a SIGCHLD delivered to 'perf'. And this SIGCHLD make perf exit early.

'perf trace' should exit only if the SIGCHLD is from our workload process.
So let's use sigaction() instead of signal() to match such condition.

Signed-off-by: Changbin Du <changbin.du@gmail.com>
---
 tools/perf/builtin-trace.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 32844d8a0ea5..d03556c14b0a 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1536,13 +1536,20 @@ static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
 	return fprintf(fp, "         ? ");
 }
 
+static pid_t workload_pid = -1;
 static bool done = false;
 static bool interrupted = false;
 
-static void sig_handler(int sig)
+static void sighandler_interrupt(int sig __maybe_unused)
 {
-	done = true;
-	interrupted = sig == SIGINT;
+	done = interrupted = true;
+}
+
+static void sighandler_chld(int sig __maybe_unused, siginfo_t *info,
+			    void *context __maybe_unused)
+{
+	if (info->si_pid == workload_pid)
+		done = true;
 }
 
 static size_t trace__fprintf_comm_tid(struct trace *trace, struct thread *thread, FILE *fp)
@@ -3938,7 +3945,6 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 	bool draining = false;
 
 	trace->live = true;
-	signal(SIGCHLD, sig_handler);
 
 	if (!trace->raw_augmented_syscalls) {
 		if (trace->trace_syscalls && trace__add_syscall_newtp(trace))
@@ -4018,6 +4024,7 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 			fprintf(trace->output, "Couldn't run the workload!\n");
 			goto out_delete_evlist;
 		}
+		workload_pid = evlist->workload.pid;
 	}
 
 	err = evlist__open(evlist);
@@ -4887,10 +4894,14 @@ int cmd_trace(int argc, const char **argv)
 	const char * const trace_subcommands[] = { "record", NULL };
 	int err = -1;
 	char bf[BUFSIZ];
+	struct sigaction sigchld_act = { 0 };
 
 	signal(SIGSEGV, sighandler_dump_stack);
 	signal(SIGFPE, sighandler_dump_stack);
-	signal(SIGINT, sig_handler);
+	signal(SIGINT, sighandler_interrupt);
+	sigchld_act.sa_flags = SA_SIGINFO;
+	sigchld_act.sa_sigaction = sighandler_chld;
+	sigaction(SIGCHLD, &sigchld_act, NULL);
 
 	trace.evlist = evlist__new();
 	trace.sctbl = syscalltbl__new();
-- 
2.25.1