rds: Fix incorrect statistics counting

In rds_send_xmit() there is logic to batch the sends. However, if
another thread has acquired the lock and has incremented the send_gen,
it is considered a race and we yield. The code incrementing the
s_send_lock_queue_raced statistics counter did not count this event
correctly.
This commit counts the race condition correctly.

Orabug: 26847583

Signed-off-by: Håkon Bugge <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Reviewed-by: Knut Omang <[email protected]>
Reviewed-by: Avinash Repaka <[email protected]>

Acked-by: Santosh Shilimkar <[email protected]>

Orabug: 27364391

(cherry picked from commit e6de6d3)
cherry-pick-repo=linux-uek.git

Conflicts:
	net/rds/send.c

Signed-off-by: Gerd Rausch <[email protected]>
Signed-off-by: Somasundaram Krishnasamy <[email protected]>

Author: Hakon-Bugge

net/rds/send.c

@@ -495,14 +495,18 @@ int rds_send_xmit(struct rds_conn_path *cp)
 	 * some work and we will skip our goto
 	 */
 	if (ret == 0) {
+		bool raced;
+
 		smp_mb();
+		raced = send_gen != READ_ONCE(cp->cp_send_gen);
+
 		if ((test_bit(0, &conn->c_map_queued) ||
-		     !list_empty(&cp->cp_send_queue)) &&
-			send_gen == READ_ONCE(cp->cp_send_gen)) {
-			rds_stats_inc(s_send_lock_queue_raced);
+		    !list_empty(&cp->cp_send_queue)) && !raced) {
 			if (batch_count < send_batch_count)
 				goto restart;
 			queue_delayed_work(cp->cp_wq, &cp->cp_send_w, 1);
+		} else if (raced) {
+			rds_stats_inc(s_send_lock_queue_raced);
 		}
 	}
 out: