From: Jens Axboe Date: Tue, 7 Oct 2014 14:39:20 +0000 (-0600) Subject: blk-mq: fix potential hang if rolling wakeup depth is too high X-Git-Tag: v3.17.3~232 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=7d515b57a1457c9dc4113bc471e686f2b7e79474;p=thirdparty%2Fkernel%2Fstable.git blk-mq: fix potential hang if rolling wakeup depth is too high commit abab13b5c4fd1fec4f9a61622548012d93dc2831 upstream. We currently divide the queue depth by 4 as our batch wakeup count, but we split the wakeups over BT_WAIT_QUEUES number of wait queues. This defaults to 8. If the product of the resulting batch wake count and BT_WAIT_QUEUES is higher than the device queue depth, we can get into a situation where a task goes to sleep waiting for a request, but never gets woken up. Reported-by: Bart Van Assche Fixes: 4bb659b156996 Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index c1b92426c95e2..74a4168ea34e7 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -463,8 +463,8 @@ static void bt_update_count(struct blk_mq_bitmap_tags *bt, } bt->wake_cnt = BT_WAIT_BATCH; - if (bt->wake_cnt > depth / 4) - bt->wake_cnt = max(1U, depth / 4); + if (bt->wake_cnt > depth / BT_WAIT_QUEUES) + bt->wake_cnt = max(1U, depth / BT_WAIT_QUEUES); bt->depth = depth; }