[dm-devel] [PATCH v3 01/29] multipathd: uxlsnr: avoid deadlock on exit

[mwilck at suse.com]

From: Martin Wilck <mwilck at suse.com>

The uxlsnr wouldn't always release the client lock when cancelled,
causing a deadlock in uxsock_cleanup(). While this hasn't been
caused by commit 3d611a2, the deadlock seems to have become much
more likely after that patch. Solving this means that we have to
treat reallocation failure of the pollfd array differently.
We will now just ignore any clients above the last valid pfd index.
That's a minor problem, as we're in an OOM situation anyway.

Moreover, client_lock is not a "struct lock", but a plain
pthread_mutex_t.

Fixes: 3d611a2 ("multipathd: cancel threads early during shutdown")
Reviewed-by: Benjamin Marzinski <bmarzins at redhat.com>
Signed-off-by: Martin Wilck <mwilck at suse.com>
---
 multipathd/uxlsnr.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/multipathd/uxlsnr.c b/multipathd/uxlsnr.c
index 1c5ce9d..ce2b680 100644
--- a/multipathd/uxlsnr.c
+++ b/multipathd/uxlsnr.c
@@ -35,6 +35,7 @@
 #include "config.h"
 #include "mpath_cmd.h"
 #include "time-util.h"
+#include "util.h"
 
 #include "main.h"
 #include "cli.h"
@@ -116,7 +117,7 @@ static void _dead_client(struct client *c)
 
 static void dead_client(struct client *c)
 {
-	pthread_cleanup_push(cleanup_lock, &client_lock);
+	pthread_cleanup_push(cleanup_mutex, &client_lock);
 	pthread_mutex_lock(&client_lock);
 	_dead_client(c);
 	pthread_cleanup_pop(1);
@@ -302,10 +303,11 @@ void * uxsock_listen(uxsock_trigger_fn uxsock_trigger, long ux_sock,
 	sigdelset(&mask, SIGUSR1);
 	while (1) {
 		struct client *c, *tmp;
-		int i, poll_count, num_clients;
+		int i, n_pfds, poll_count, num_clients;
 
 		/* setup for a poll */
 		pthread_mutex_lock(&client_lock);
+		pthread_cleanup_push(cleanup_mutex, &client_lock);
 		num_clients = 0;
 		list_for_each_entry(c, &clients, node) {
 			num_clients++;
@@ -322,14 +324,13 @@ void * uxsock_listen(uxsock_trigger_fn uxsock_trigger, long ux_sock,
 						sizeof(struct pollfd));
 			}
 			if (!new) {
-				pthread_mutex_unlock(&client_lock);
 				condlog(0, "%s: failed to realloc %d poll fds",
 					"uxsock", 2 + num_clients);
-				sched_yield();
-				continue;
+				num_clients = old_clients;
+			} else {
+				old_clients = num_clients;
+				polls = new;
 			}
-			old_clients = num_clients;
-			polls = new;
 		}
 		polls[0].fd = ux_sock;
 		polls[0].events = POLLIN;
@@ -347,11 +348,14 @@ void * uxsock_listen(uxsock_trigger_fn uxsock_trigger, long ux_sock,
 			polls[i].fd = c->fd;
 			polls[i].events = POLLIN;
 			i++;
+			if (i >= 2 + num_clients)
+				break;
 		}
-		pthread_mutex_unlock(&client_lock);
+		n_pfds = i;
+		pthread_cleanup_pop(1);
 
 		/* most of our life is spent in this call */
-		poll_count = ppoll(polls, i, &sleep_time, &mask);
+		poll_count = ppoll(polls, n_pfds, &sleep_time, &mask);
 
 		handle_signals(false);
 		if (poll_count == -1) {
@@ -384,7 +388,7 @@ void * uxsock_listen(uxsock_trigger_fn uxsock_trigger, long ux_sock,
 		}
 
 		/* see if a client wants to speak to us */
-		for (i = 2; i < num_clients + 2; i++) {
+		for (i = 2; i < n_pfds; i++) {
 			if (polls[i].revents & POLLIN) {
 				struct timespec start_time;
 
-- 
2.29.0