[PATCH v5 13/17] perf intel-tpebs: Fix race in tpebs_stop() and tpebs_cmd.out fd handling

[Ian Rogers <irogers@google.com>]

In tpebs_stop(), read tpebs_reader_thread into a local variable before
releasing tpebs_mtx to call pthread_join().

Transfer ownership of tpebs_cmd.out to __sample_reader() by passing it as
the thread argument and setting tpebs_cmd.out = -1 in
evsel__tpebs_open() so tpebs_stop() does not double-close the fd closed
by perf_session__delete(). Also reset tpebs_cmd.pid = 0 and tpebs_cmd.out = -1 and return early if
start_command() fails in evsel__tpebs_start_perf_record(), as
start_command() closes the pipe internally and may leave cmd->pid = -1
on error, and join tpebs_reader_thread on error in evsel__tpebs_open()
if it was already started.

Include <pthread.h>, <signal.h>, <stdint.h>, <stdlib.h>, <string.h>, and
<unistd.h> explicitly.

Signed-off-by: Ian Rogers <irogers@google.com>
---
 tools/perf/util/intel-tpebs.c | 51 ++++++++++++++++++++++++++++++-----
 1 file changed, 44 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/intel-tpebs.c b/tools/perf/util/intel-tpebs.c
index 7c0b8b15bd10..47c939fc2058 100644
--- a/tools/perf/util/intel-tpebs.c
+++ b/tools/perf/util/intel-tpebs.c
@@ -27,6 +27,12 @@
 #include <errno.h>
 #include <poll.h>
 #include <math.h>
+#include <pthread.h>
+#include <signal.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
 
 #define PERF_DATA		"-"
 
@@ -120,10 +126,15 @@ static int evsel__tpebs_start_perf_record(struct evsel *evsel)
 	tpebs_cmd.out = -1;
 	ret = start_command(&tpebs_cmd);
 	zfree(&tpebs_cmd.argv);
+	if (ret) {
+		tpebs_cmd.pid = 0;
+		tpebs_cmd.out = -1;
+		return ret;
+	}
 	list_for_each_entry(t, &tpebs_results, nd)
 		t->started = true;
 
-	return ret;
+	return 0;
 }
 
 static bool is_child_pid(pid_t parent, pid_t child)
@@ -220,13 +231,13 @@ static int process_sample_event(const struct perf_tool *tool __maybe_unused,
 	return 0;
 }
 
-static void *__sample_reader(void *arg __maybe_unused)
+static void *__sample_reader(void *arg)
 {
 	struct perf_session *session;
 	struct perf_data data = {
 		.mode = PERF_DATA_MODE_READ,
 		.path = PERF_DATA,
-		.file.fd = tpebs_cmd.out,
+		.file.fd = (int)(intptr_t)arg,
 	};
 	struct perf_tool tool;
 
@@ -236,8 +247,10 @@ static void *__sample_reader(void *arg __maybe_unused)
 	tool.attr = perf_event__process_attr;
 
 	session = perf_session__new(&data, &tool);
-	if (IS_ERR(session))
+	if (IS_ERR(session)) {
+		close(data.file.fd);
 		return NULL;
+	}
 	perf_session__process_events(session);
 	perf_session__delete(session);
 
@@ -331,12 +344,19 @@ static int tpebs_stop(void) __must_hold(tpebs_mtx_get())
 	/* Like tpebs_start, we should only run tpebs_end once. */
 	if (tpebs_cmd.pid != 0) {
 		pid_t actual_pid = tpebs_cmd.pid;
+		pthread_t reader_thread;
 
 		tpebs_stopping = true;
 		tpebs_send_record_cmd(EVLIST_CTL_CMD_STOP_TAG);
+		/*
+		 * tpebs_results is empty when stopping; clear pid so
+		 * process_sample_event() ignores any late samples while
+		 * draining the pipe.
+		 */
 		tpebs_cmd.pid = 0;
+		reader_thread = tpebs_reader_thread;
 		mutex_unlock(tpebs_mtx_get());
-		pthread_join(tpebs_reader_thread, NULL);
+		pthread_join(reader_thread, NULL);
 		mutex_lock(tpebs_mtx_get());
 		if (control_fd[0] >= 0) {
 			close(control_fd[0]);
@@ -515,6 +535,7 @@ int evsel__tpebs_open(struct evsel *evsel)
 	int ret;
 	bool tpebs_empty;
 	bool started_process = false;
+	bool started_thread = false;
 
 	/* We should only run tpebs_start when tpebs_recording is enabled. */
 	if (!tpebs_recording)
@@ -567,12 +588,15 @@ int evsel__tpebs_open(struct evsel *evsel)
 			goto out;
 
 		if (pthread_create(&tpebs_reader_thread, /*attr=*/NULL, __sample_reader,
-				   /*arg=*/NULL)) {
+				   (void *)(intptr_t)tpebs_cmd.out)) {
 			kill(tpebs_cmd.pid, SIGTERM);
 			pr_err("Could not create thread to process sample data.\n");
 			ret = -1;
 			goto out;
 		}
+		/* __sample_reader now owns and closes the output fd. */
+		tpebs_cmd.out = -1;
+		started_thread = true;
 		ret = tpebs_send_record_cmd(EVLIST_CTL_CMD_ENABLE_TAG);
 	}
 out:
@@ -586,9 +610,22 @@ int evsel__tpebs_open(struct evsel *evsel)
 
 		if (started_process) {
 			if (tpebs_cmd.pid > 0) {
-				kill(tpebs_cmd.pid, SIGTERM);
+				pid_t actual_pid = tpebs_cmd.pid;
+
+				tpebs_stopping = true;
+				kill(actual_pid, SIGTERM);
+				tpebs_cmd.pid = 0;
+				if (started_thread) {
+					pthread_t reader_thread = tpebs_reader_thread;
+
+					mutex_unlock(tpebs_mtx_get());
+					pthread_join(reader_thread, NULL);
+					mutex_lock(tpebs_mtx_get());
+				}
+				tpebs_cmd.pid = actual_pid;
 				finish_command(&tpebs_cmd);
 				tpebs_cmd.pid = 0;
+				tpebs_stopping = false;
 			}
 			if (tpebs_cmd.out >= 0) {
 				close(tpebs_cmd.out);
-- 
2.56.0.212.g129ede20d9-goog