[PATCH net-next 2/2] net/smc: reduce TX slot contention with exclusive wait

[D. Wythe]

smc_wr_tx_get_free_slot() waits for a free TX slot with
wait_event_interruptible_timeout(). Since the wait_event family
enqueues waiters as non-exclusive, wake_up() may wake multiple
waiters even though only one can use the slot, causing
thundering-herd contention when slots are scarce.

Use an exclusive wait loop with prepare_to_wait_exclusive() so
wake_up() wakes only one waiter per freed slot.
smc_wr_wakeup_tx_wait() still uses wake_up_all() during link
teardown, so teardown behavior is unchanged.

Performance measured with netperf TCP_RR (63 flows, 200B write /
1000B read, 60s duration):

+-------------------------------+---------------+---------------+
| smcr_max_conns_per_lgr        | 32            | 255           |
|-------------------------------+---------------+---------------|
| before                        | 4.85 Gb/s     | 657.95 Mb/s   |
|-------------------------------+---------------+---------------|
| after                         | 5.01 Gb/s     | 2.2 Gb/s      |
+-------------------------------+---------------+---------------+

Signed-off-by: D. Wythe <alibuda@xxxxxxxxxxxxxxxxx>
---
 net/smc/smc_wr.c | 32 ++++++++++++++++++++++----------
 1 file changed, 22 insertions(+), 10 deletions(-)

diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index 48037a3d97a3..0a6f2befb0e2 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -159,9 +159,11 @@ int smc_wr_tx_get_free_slot(struct smc_link *link,
 			    struct smc_rdma_wr **wr_rdma_buf,
 			    struct smc_wr_tx_pend_priv **wr_pend_priv)
 {
+	unsigned long timeout = SMC_WR_TX_WAIT_FREE_SLOT_TIME;
 	struct smc_link_group *lgr = smc_get_lgr(link);
 	struct smc_wr_tx_pend *wr_pend;
 	u32 idx = link->wr_tx_cnt;
+	DEFINE_WAIT(wait);
 	int rc;
 
 	*wr_buf = NULL;
@@ -171,17 +173,27 @@ int smc_wr_tx_get_free_slot(struct smc_link *link,
 		if (rc)
 			return rc;
 	} else {
-		rc = wait_event_interruptible_timeout(
-			link->wr_tx_wait,
-			!smc_link_sendable(link) ||
-			lgr->terminating ||
-			(smc_wr_tx_get_free_slot_index(link, &idx) != -EBUSY),
-			SMC_WR_TX_WAIT_FREE_SLOT_TIME);
-		if (!rc) {
-			/* timeout - terminate link */
-			smcr_link_down_cond_sched(link);
-			return -EPIPE;
+		rc = 0;
+		for (;;) {
+			prepare_to_wait_exclusive(&link->wr_tx_wait, &wait,
+						  TASK_INTERRUPTIBLE);
+			if (!smc_link_sendable(link) || lgr->terminating ||
+			    smc_wr_tx_get_free_slot_index(link, &idx) != -EBUSY)
+				break;
+			timeout = schedule_timeout(timeout);
+			if (!timeout) {
+				/* timeout - terminate link */
+				smcr_link_down_cond_sched(link);
+				break;
+			}
+			if (signal_pending(current)) {
+				rc = -ERESTARTSYS;
+				break;
+			}
 		}
+		finish_wait(&link->wr_tx_wait, &wait);
+		if (rc)
+			return rc;
 		if (idx == link->wr_tx_cnt)
 			return -EPIPE;
 	}
-- 
2.45.0