Re: [PATCH v1 3/3] blk-mq: start to freeze queue just after setting dying
From: Bart Van Assche <hidden>
Date: 2017-03-17 17:34:36
Also in:
lkml
Subsystem:
block layer, the rest · Maintainers:
Jens Axboe, Linus Torvalds
On Fri, 2017-03-17 at 17:57 +0800, Ming Lei wrote:
quoted hunk ↗ jump to hunk
Before commit 780db2071a(blk-mq: decouble blk-mq freezing from generic bypassing), the dying flag is checked before entering queue, and Tejun converts the checking into .mq_freeze_depth, and assumes the counter is increased just after dying flag is set. Unfortunately we doesn't do that in blk_set_queue_dying(). =20 This patch calls blk_mq_freeze_queue_start() for blk-mq in blk_set_queue_dying(), so that we can block new I/O coming once the queue is set as dying. =20 Given blk_set_queue_dying() is always called in remove path of block device, and queue will be cleaned up later, we don't need to worry about undoing the counter. =20 Cc: Bart Van Assche <redacted> Cc: Tejun Heo <tj@kernel.org> Signed-off-by: Ming Lei <tom.leiming@gmail.com> --- block/blk-core.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) =20diff --git a/block/blk-core.c b/block/blk-core.c index d772c221cc17..62d4967c369f 100644 --- a/block/blk-core.c +++ b/block/blk-core.c@@ -500,9 +500,12 @@ void blk_set_queue_dying(struct request_queue *q) queue_flag_set(QUEUE_FLAG_DYING, q); spin_unlock_irq(q->queue_lock);=20 - if (q->mq_ops) + if (q->mq_ops) { blk_mq_wake_waiters(q); - else { + + /* block new I/O coming */ + blk_mq_freeze_queue_start(q); + } else { struct request_list *rl; =20 spin_lock_irq(q->queue_lock);
Hello Ming,
I think we need the queue freezing not only for blk-mq but also for blk-sq.
Since the queue flags and the mq_freeze_depth are stored in different
variables we need to prevent that the CPU reorders the stores to these
variables. The comment about=A0blk_mq_freeze_queue_start() should be more
clear. How about something like the patch below?
[PATCH] blk-mq: Force block layer users to check the "dying" flag=A0after i=
t has been set
Commit 780db2071ac4 removed the blk_queue_dying() check from the
hot path of blk_mq_queue_enter() although that check is necessary
when cleaning up a queue. Hence make sure that blk_queue_enter()
and blk_mq_queue_enter() check the dying flag after it has been set.
Because blk_set_queue_dying() is only called from the remove path
of a block device we don't need to worry about unfreezing the queue.
Fixes: commit 780db2071ac4 ("blk-mq: decouble blk-mq freezing from generic =
bypassing")
---
=A0block/blk-core.c | 13 +++++++++++++
=A01 file changed, 13 insertions(+)
diff --git a/block/blk-core.c b/block/blk-core.c
index d772c221cc17..730f715b72ff 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c@@ -500,6 +500,19 @@ void blk_set_queue_dying(struct request_queue *q)=A0 queue_flag_set(QUEUE_FLAG_DYING, q);
=A0 spin_unlock_irq(q->queue_lock);
=A0
+ /*
+ =A0* Avoid that the updates of the queue flags and q_usage_counter
+ =A0* are reordered.
+ =A0*/
+ smp_wmb();
+
+ /*
+ =A0* Force blk_queue_enter() and blk_mq_queue_enter() to check the
+ =A0* "dying" flag. Despite its name, blk_mq_freeze_queue_start()
+ =A0* affects blk-sq and blk-mq queues.
+ =A0*/
+ blk_mq_freeze_queue_start(q);
+
=A0 if (q->mq_ops)
=A0 blk_mq_wake_waiters(q);
=A0 else {
Thanks,
Bart.