[PATCH i-g-t v21 09/36] lib/intel_allocator: Try to stop smoothly instead of deinit

[Zbigniew Kempczyński]

Avoid race when stop was send to allocator thread. We wait around
100 ms to give thread chance to stop smoothly instead of removing
queue and enforcing exiting all blocked message syscalls.

Signed-off-by: Zbigniew Kempczyński <zbigniew.kempczynski at intel.com>
Cc: Dominik Grzegorzek <dominik.grzegorzek at intel.com>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
---
 lib/intel_allocator.c | 26 +++++++++++++++++++++++---
 1 file changed, 23 insertions(+), 3 deletions(-)

diff --git a/lib/intel_allocator.c b/lib/intel_allocator.c
index 4d053c381..113c4aa1a 100644
--- a/lib/intel_allocator.c
+++ b/lib/intel_allocator.c
@@ -55,6 +55,7 @@ static struct igt_map *allocators_map;
 static pthread_mutex_t map_mutex = PTHREAD_MUTEX_INITIALIZER;
 static bool multiprocess;
 static pthread_t allocator_thread;
+static bool allocator_thread_running;
 
 static bool warn_if_not_empty;
 
@@ -475,6 +476,8 @@ static void *allocator_thread_loop(void *data)
 		   (long) allocator_pid, (long) gettid());
 	alloc_info("Entering allocator loop\n");
 
+	WRITE_ONCE(allocator_thread_running, true);
+
 	while (1) {
 		ret = recv_req(channel, &req);
 
@@ -508,6 +511,8 @@ static void *allocator_thread_loop(void *data)
 		}
 	}
 
+	WRITE_ONCE(allocator_thread_running, false);
+
 	return NULL;
 }
 
@@ -545,15 +550,30 @@ void intel_allocator_multiprocess_start(void)
  * Function turns off intel_allocator multiprocess mode what means means
  * stopping allocator thread and deinitializing its data.
  */
+#define STOP_TIMEOUT_MS 100
 void intel_allocator_multiprocess_stop(void)
 {
+	int time_left = STOP_TIMEOUT_MS;
+
 	alloc_info("allocator multiprocess stop\n");
 
 	if (multiprocess) {
 		send_alloc_stop(channel);
-		/* Deinit, this should stop all blocked syscalls, if any */
-		channel->deinit(channel);
-		pthread_join(allocator_thread, NULL);
+
+		/* We prefer joining thread when it is stopped */
+		while (time_left-- > 0 && READ_ONCE(allocator_thread_running))
+			usleep(1000); /* coarse calculation */
+
+		/* Thread has stuck somewhere */
+		if (READ_ONCE(allocator_thread_running)) {
+			/* Deinit, this should stop all blocked syscalls, if any */
+			channel->deinit(channel);
+			pthread_join(allocator_thread, NULL);
+		} else {
+			pthread_join(allocator_thread, NULL);
+			channel->deinit(channel);
+		}
+
 		/* But we're not sure does child will stuck */
 		kill_children(SIGINT);
 		igt_waitchildren_timeout(5, "Stopping children");
-- 
2.26.0