[Cluster-devel] [PATCH 01/18] [try #2] DLM: Eliminate CF_CONNECT_PENDING flag

[tsutomu.owa at toshiba.co.jp]

Before this patch, there was a flag in the con structure that was
used to determine whether or not a connect was needed. The bit was
set here and there, and cleared here and there, so it left some
race conditions: the bit was set, work was queued, then the worker
cleared the bit, allowing someone else to set it while the worker
ran. For the most part, this worked okay, but we got into trouble
if connections were lost and it needed to reconnect.

This patch eliminates the flag in favor of simply checking if we
actually have a sock pointer while protected by the mutex.

Signed-off-by: Bob Peterson <rpeterso at redhat.com>
Reviewed-by: Tadashi Miyauchi <miyauchi at toshiba-tops.co.jp>
---
 fs/dlm/lowcomms.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 7d398d3..41bf93a 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -107,7 +107,6 @@ struct connection {
 	unsigned long flags;
 #define CF_READ_PENDING 1
 #define CF_WRITE_PENDING 2
-#define CF_CONNECT_PENDING 3
 #define CF_INIT_PENDING 4
 #define CF_IS_OTHERCON 5
 #define CF_CLOSE 6
@@ -435,8 +434,8 @@ static inline void lowcomms_connect_sock(struct connection *con)
 {
 	if (test_bit(CF_CLOSE, &con->flags))
 		return;
-	if (!test_and_set_bit(CF_CONNECT_PENDING, &con->flags))
-		queue_work(send_workqueue, &con->swork);
+	queue_work(send_workqueue, &con->swork);
+	cond_resched();
 }
 
 static void lowcomms_state_change(struct sock *sk)
@@ -579,7 +578,6 @@ 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)
 {
-	clear_bit(CF_CONNECT_PENDING, &con->flags);
 	clear_bit(CF_WRITE_PENDING, &con->flags);
 	if (tx && cancel_work_sync(&con->swork))
 		log_print("canceled swork for node %d", con->nodeid);
@@ -1098,7 +1096,6 @@ static void sctp_connect_to_sock(struct connection *con)
 			  con->retries, result);
 		mutex_unlock(&con->sock_mutex);
 		msleep(1000);
-		clear_bit(CF_CONNECT_PENDING, &con->flags);
 		lowcomms_connect_sock(con);
 		return;
 	}
@@ -1194,7 +1191,6 @@ static void tcp_connect_to_sock(struct connection *con)
 			  con->retries, result);
 		mutex_unlock(&con->sock_mutex);
 		msleep(1000);
-		clear_bit(CF_CONNECT_PENDING, &con->flags);
 		lowcomms_connect_sock(con);
 		return;
 	}
@@ -1593,7 +1589,7 @@ static void process_send_sockets(struct work_struct *work)
 {
 	struct connection *con = container_of(work, struct connection, swork);
 
-	if (test_and_clear_bit(CF_CONNECT_PENDING, &con->flags))
+	if (con->sock == NULL) /* not mutex protected so check it inside too */
 		con->connect_action(con);
 	if (test_and_clear_bit(CF_WRITE_PENDING, &con->flags))
 		send_to_sock(con);
-- 
2.7.4