diff mbox series

[5.13,374/800] block, bfq: reset waker pointer with shared queues

Message ID 20210712061006.872749843@linuxfoundation.org
State New
Headers show
Series None | expand

Commit Message

Greg KH July 12, 2021, 6:06 a.m. UTC 
From: Paolo Valente <paolo.valente@linaro.org>


[ Upstream commit 9a2ac41b13c573703d6689f51f3e27dd658324be ]

Commit 85686d0dc194 ("block, bfq: keep shared queues out of the waker
mechanism") leaves shared bfq_queues out of the waker-detection
mechanism. It attains this goal by not updating the pointer
last_completed_rq_bfqq, if the last request completed belongs to a
shared bfq_queue (so that the pointer will not point to the shared
bfq_queue).

Yet this has a side effect: the pointer last_completed_rq_bfqq keeps
pointing, deceptively, to a bfq_queue that actually is not the last
one to have had a request completed. As a consequence, such a
bfq_queue may deceptively be considered as a waker of some bfq_queue,
even of some shared bfq_queue.

To address this issue, reset last_completed_rq_bfqq if the last
request completed belongs to a shared queue.

Fixes: 85686d0dc194 ("block, bfq: keep shared queues out of the waker mechanism")
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>

Link: https://lore.kernel.org/r/20210619140948.98712-8-paolo.valente@linaro.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Signed-off-by: Sasha Levin <sashal@kernel.org>

---
 block/bfq-iosched.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

-- 
2.30.2
diff mbox series

Patch

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 7c62bf093199..2a2e6e4ff0b4 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -6143,11 +6143,13 @@  static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 	 * of other queues. But a false waker will unjustly steal
 	 * bandwidth to its supposedly woken queue. So considering
 	 * also shared queues in the waking mechanism may cause more
-	 * control troubles than throughput benefits. Then do not set
-	 * last_completed_rq_bfqq to bfqq if bfqq is a shared queue.
+	 * control troubles than throughput benefits. Then reset
+	 * last_completed_rq_bfqq if bfqq is a shared queue.
 	 */
 	if (!bfq_bfqq_coop(bfqq))
 		bfqd->last_completed_rq_bfqq = bfqq;
+	else
+		bfqd->last_completed_rq_bfqq = NULL;
 
 	/*
 	 * If we are waiting to discover whether the request pattern