[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20200310123635.620435587@linuxfoundation.org>
Date: Tue, 10 Mar 2020 13:37:29 +0100
From: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To: linux-kernel@...r.kernel.org
Cc: Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
stable@...r.kernel.org, Patrick Dung <patdung100@...il.com>,
Oleksandr Natalenko <oleksandr@...alenko.name>,
Paolo Valente <paolo.valente@...aro.org>,
Jens Axboe <axboe@...nel.dk>, Sasha Levin <sashal@...nel.org>
Subject: [PATCH 5.4 003/168] block, bfq: do not insert oom queue into position tree
From: Paolo Valente <paolo.valente@...aro.org>
[ Upstream commit 32c59e3a9a5a0b180dd015755d6d18ca31e55935 ]
BFQ maintains an ordered list, implemented with an RB tree, of
head-request positions of non-empty bfq_queues. This position tree,
inherited from CFQ, is used to find bfq_queues that contain I/O close
to each other. BFQ merges these bfq_queues into a single shared queue,
if this boosts throughput on the device at hand.
There is however a special-purpose bfq_queue that does not participate
in queue merging, the oom bfq_queue. Yet, also this bfq_queue could be
wrongly added to the position tree. So bfqq_find_close() could return
the oom bfq_queue, which is a source of further troubles in an
out-of-memory situation. This commit prevents the oom bfq_queue from
being inserted into the position tree.
Tested-by: Patrick Dung <patdung100@...il.com>
Tested-by: Oleksandr Natalenko <oleksandr@...alenko.name>
Signed-off-by: Paolo Valente <paolo.valente@...aro.org>
Signed-off-by: Jens Axboe <axboe@...nel.dk>
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
block/bfq-iosched.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 5498d05b873d3..955daa29303a8 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -614,6 +614,10 @@ bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq)
bfqq->pos_root = NULL;
}
+ /* oom_bfqq does not participate in queue merging */
+ if (bfqq == &bfqd->oom_bfqq)
+ return;
+
/*
* bfqq cannot be merged any longer (see comments in
* bfq_setup_cooperator): no point in adding bfqq into the
--
2.20.1
Powered by blists - more mailing lists