DLM: fix race condition between dlm_send and dlm_recv

When kernel_sendpage(in send_to_sock) and kernel_recvmsg
(in receive_from_sock) return error, close_connection may works at the
same time. At that time, they may wait for each other by cancel_work_sync.

Signed-off-by: Tadashi Miyauchi <miayuchi@toshiba-tops.co.jp>
Signed-off-by: Tsutomu Owa <tsutomu.owa@toshiba.co.jp>
Signed-off-by: David Teigland <teigland@redhat.com>

diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 980c58befd533802b0a6c3fde5c4f3cd5dcf3380..420946dcb7caba705e8ee1ebea40e0b97fd34cfa 100644 (file)
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -110,6 +110,7 @@ struct connection {
 #define CF_IS_OTHERCON 5
 #define CF_CLOSE 6
 #define CF_APP_LIMITED 7
+#define CF_CLOSING 8
        struct list_head writequeue;  /* List of outgoing writequeue_entries */
        spinlock_t writequeue_lock;
        int (*rx_action) (struct connection *); /* What to do when active */
@@ -581,9 +582,11 @@ static void make_sockaddr(struct sockaddr_storage *saddr, uint16_t port,
 static void close_connection(struct connection *con, bool and_other,
                             bool tx, bool rx)
 {
-       if (tx && cancel_work_sync(&con->swork))
+       bool closing = test_and_set_bit(CF_CLOSING, &con->flags);
+
+       if (tx && !closing && cancel_work_sync(&con->swork))
                log_print("canceled swork for node %d", con->nodeid);
-       if (rx && cancel_work_sync(&con->rwork))
+       if (rx && !closing && cancel_work_sync(&con->rwork))
                log_print("canceled rwork for node %d", con->nodeid);
 
        mutex_lock(&con->sock_mutex);
@@ -603,6 +606,7 @@ static void close_connection(struct connection *con, bool and_other,
 
        con->retries = 0;
        mutex_unlock(&con->sock_mutex);
+       clear_bit(CF_CLOSING, &con->flags);
 }
 
 /* Data received from remote end */