nbd: clear DISCONNECT_REQUESTED flag once disconnection occurs.

When a userspace client requests a NBD device be disconnected, the
DISCONNECT_REQUESTED flag is set. While this flag is set, the driver
will not inform userspace when a connection is closed.

Unfortunately the flag was never cleared, so once a disconnect was
requested the driver would thereafter never tell userspace about a
closed connection. Thus when connections failed due to timeout, no
attempt to reconnect was made and eventually the device would fail.

Fix by clearing the DISCONNECT_REQUESTED flag (and setting the
DISCONNECTED flag) once all connections are closed.

Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Kevin Vigor <kvigor@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 8860b24..a6e3a6f 100644 (file)
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -216,7 +216,15 @@ static void nbd_mark_nsock_dead(struct nbd_device *nbd, struct nbd_sock *nsock,
        }
        if (!nsock->dead) {
                kernel_sock_shutdown(nsock->sock, SHUT_RDWR);
-               atomic_dec(&nbd->config->live_connections);
+               if (atomic_dec_return(&nbd->config->live_connections) == 0) {
+                       if (test_and_clear_bit(NBD_DISCONNECT_REQUESTED,
+                                              &nbd->config->runtime_flags)) {
+                               set_bit(NBD_DISCONNECTED,
+                                       &nbd->config->runtime_flags);
+                               dev_info(nbd_to_dev(nbd),
+                                       "Disconnected due to user request.\n");
+                       }
+               }
        }
        nsock->dead = true;
        nsock->pending = NULL;
@@ -310,7 +318,9 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req,
 
        if (config->num_connections > 1) {
                dev_err_ratelimited(nbd_to_dev(nbd),
-                                   "Connection timed out, retrying\n");
+                                   "Connection timed out, retrying (%d/%d alive)\n",
+                                   atomic_read(&config->live_connections),
+                                   config->num_connections);
                /*
                 * Hooray we have more connections, requeue this IO, the submit
                 * path will put it on a real connection.
@@ -733,10 +743,9 @@ static int wait_for_reconnect(struct nbd_device *nbd)
                return 0;
        if (test_bit(NBD_DISCONNECTED, &config->runtime_flags))
                return 0;
-       wait_event_timeout(config->conn_wait,
-                          atomic_read(&config->live_connections),
-                          config->dead_conn_timeout);
-       return atomic_read(&config->live_connections);
+       return wait_event_timeout(config->conn_wait,
+                                 atomic_read(&config->live_connections) > 0,
+                                 config->dead_conn_timeout) > 0;
 }
 
 static int nbd_handle_cmd(struct nbd_cmd *cmd, int index)