RDS: Use a generation counter to avoid rds_send_xmit loop

rds_send_xmit is required to loop around after it releases the lock
because someone else could done a trylock, found someone working on the
list and backed off.

But, once we drop our lock, it is possible that someone else does come
in and make progress on the list.  We should detect this and not loop
around if another process is actually working on the list.

This patch adds a generation counter that is bumped every time we
get the lock and do some send work.  If the retry notices someone else
has bumped the generation counter, it does not need to loop around and
continue working.

Signed-off-by: Chris Mason <chris.mason@oracle.com>
Signed-off-by: Andy Grover <andy.grover@oracle.com>

1 files changed, 7 insertions, 4 deletions

diff --git a/net/rds/send.c b/net/rds/send.c
index de5693cdcef..663fd60b40c 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -112,6 +112,7 @@ int rds_send_xmit(struct rds_connection *conn)
 	unsigned int tmp;
 	struct scatterlist *sg;
 	int ret = 0;
+	int gen = 0;
 	LIST_HEAD(to_be_dropped);
 
 restart:
@@ -134,6 +135,8 @@ restart:
 	if (conn->c_trans->xmit_prepare)
 		conn->c_trans->xmit_prepare(conn);
 
+	gen = atomic_inc_return(&conn->c_send_generation);
+
 	/*
 	 * spin trying to push headers and data down the connection until
 	 * the connection doesn't make forward progress.
@@ -359,13 +362,13 @@ restart:
 	if (ret == 0) {
 		/* A simple bit test would be way faster than taking the
 		 * spin lock */
-		spin_lock_irqsave(&conn->c_lock, flags);
+		smp_mb();
 		if (!list_empty(&conn->c_send_queue)) {
 			rds_stats_inc(s_send_lock_queue_raced);
-			spin_unlock_irqrestore(&conn->c_lock, flags);
-			goto restart;
+			if (gen == atomic_read(&conn->c_send_generation)) {
+				goto restart;
+			}
 		}
-		spin_unlock_irqrestore(&conn->c_lock, flags);
 	}
 out:
 	return ret;