Supposing the following scenario.
CPU0 CPU1
blk_mq_insert_request() 1) store blk_mq_unquiesce_queue()
blk_mq_run_hw_queue() blk_queue_flag_clear(QUEUE_FLAG_QUIESCED) 3) store
if (blk_queue_quiesced()) 2) load blk_mq_run_hw_queues()
return blk_mq_run_hw_queue()
blk_mq_sched_dispatch_requests() if (!blk_mq_hctx_has_pending()) 4) load
return
The full memory barrier should be inserted between 1) and 2), as well as
between 3) and 4) to make sure that either CPU0 sees QUEUE_FLAG_QUIESCED is
cleared or CPU1 sees dispatch list or setting of bitmap of software queue.
Otherwise, either CPU will not re-run the hardware queue causing starvation.
So the first solution is to 1) add a pair of memory barrier to fix the
problem, another solution is to 2) use hctx->queue->queue_lock to synchronize
QUEUE_FLAG_QUIESCED. Here, we chose 2) to fix it since memory barrier is not
easy to be maintained.
Fixes: f4560ffe8cec1 ("blk-mq: use QUEUE_FLAG_QUIESCED to quiesce queue")
Cc: stable@vger.kernel.org
Cc: Muchun Song <muchun.song@linux.dev>
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
block/blk-mq.c | 47 ++++++++++++++++++++++++++++++++++-------------
1 file changed, 34 insertions(+), 13 deletions(-)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b2d0f22de0c7f..ac39f2a346a52 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2202,6 +2202,24 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
}
EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
+static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx)
+{
+ bool need_run;
+
+ /*
+ * When queue is quiesced, we may be switching io scheduler, or
+ * updating nr_hw_queues, or other things, and we can't run queue
+ * any more, even blk_mq_hctx_has_pending() can't be called safely.
+ *
+ * And queue will be rerun in blk_mq_unquiesce_queue() if it is
+ * quiesced.
+ */
+ __blk_mq_run_dispatch_ops(hctx->queue, false,
+ need_run = !blk_queue_quiesced(hctx->queue) &&
+ blk_mq_hctx_has_pending(hctx));
+ return need_run;
+}
+
/**
* blk_mq_run_hw_queue - Start to run a hardware queue.
* @hctx: Pointer to the hardware queue to run.
@@ -2222,20 +2240,23 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING);
- /*
- * When queue is quiesced, we may be switching io scheduler, or
- * updating nr_hw_queues, or other things, and we can't run queue
- * any more, even __blk_mq_hctx_has_pending() can't be called safely.
- *
- * And queue will be rerun in blk_mq_unquiesce_queue() if it is
- * quiesced.
- */
- __blk_mq_run_dispatch_ops(hctx->queue, false,
- need_run = !blk_queue_quiesced(hctx->queue) &&
- blk_mq_hctx_has_pending(hctx));
+ need_run = blk_mq_hw_queue_need_run(hctx);
+ if (!need_run) {
+ unsigned long flags;
- if (!need_run)
- return;
+ /*
+ * Synchronize with blk_mq_unquiesce_queue(), becuase we check
+ * if hw queue is quiesced locklessly above, we need the use
+ * ->queue_lock to make sure we see the up-to-date status to
+ * not miss rerunning the hw queue.
+ */
+ spin_lock_irqsave(&hctx->queue->queue_lock, flags);
+ need_run = blk_mq_hw_queue_need_run(hctx);
+ spin_unlock_irqrestore(&hctx->queue->queue_lock, flags);
+
+ if (!need_run)
+ return;
+ }
if (async || !cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) {
blk_mq_delay_run_hw_queue(hctx, 0);
--
2.20.1On 9/3/24 2:16 AM, Muchun Song wrote:
> Supposing the following scenario.
>
> CPU0 CPU1
>
> blk_mq_insert_request() 1) store blk_mq_unquiesce_queue()
> blk_mq_run_hw_queue() blk_queue_flag_clear(QUEUE_FLAG_QUIESCED) 3) store
> if (blk_queue_quiesced()) 2) load blk_mq_run_hw_queues()
> return blk_mq_run_hw_queue()
> blk_mq_sched_dispatch_requests() if (!blk_mq_hctx_has_pending()) 4) load
> return
>
> The full memory barrier should be inserted between 1) and 2), as well as
> between 3) and 4) to make sure that either CPU0 sees QUEUE_FLAG_QUIESCED is
> cleared or CPU1 sees dispatch list or setting of bitmap of software queue.
> Otherwise, either CPU will not re-run the hardware queue causing starvation.
>
> So the first solution is to 1) add a pair of memory barrier to fix the
> problem, another solution is to 2) use hctx->queue->queue_lock to synchronize
> QUEUE_FLAG_QUIESCED. Here, we chose 2) to fix it since memory barrier is not
> easy to be maintained.
Same comment here, 72-74 chars wide please.
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index b2d0f22de0c7f..ac39f2a346a52 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -2202,6 +2202,24 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
> }
> EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
>
> +static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx)
> +{
> + bool need_run;
> +
> + /*
> + * When queue is quiesced, we may be switching io scheduler, or
> + * updating nr_hw_queues, or other things, and we can't run queue
> + * any more, even blk_mq_hctx_has_pending() can't be called safely.
> + *
> + * And queue will be rerun in blk_mq_unquiesce_queue() if it is
> + * quiesced.
> + */
> + __blk_mq_run_dispatch_ops(hctx->queue, false,
> + need_run = !blk_queue_quiesced(hctx->queue) &&
> + blk_mq_hctx_has_pending(hctx));
> + return need_run;
> +}
This __blk_mq_run_dispatch_ops() is also way too wide, why didn't you
just break it like where you copied it from?
> +
> /**
> * blk_mq_run_hw_queue - Start to run a hardware queue.
> * @hctx: Pointer to the hardware queue to run.
> @@ -2222,20 +2240,23 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
>
> might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING);
>
> - /*
> - * When queue is quiesced, we may be switching io scheduler, or
> - * updating nr_hw_queues, or other things, and we can't run queue
> - * any more, even __blk_mq_hctx_has_pending() can't be called safely.
> - *
> - * And queue will be rerun in blk_mq_unquiesce_queue() if it is
> - * quiesced.
> - */
> - __blk_mq_run_dispatch_ops(hctx->queue, false,
> - need_run = !blk_queue_quiesced(hctx->queue) &&
> - blk_mq_hctx_has_pending(hctx));
> + need_run = blk_mq_hw_queue_need_run(hctx);
> + if (!need_run) {
> + unsigned long flags;
>
> - if (!need_run)
> - return;
> + /*
> + * synchronize with blk_mq_unquiesce_queue(), becuase we check
> + * if hw queue is quiesced locklessly above, we need the use
> + * ->queue_lock to make sure we see the up-to-date status to
> + * not miss rerunning the hw queue.
> + */
> + spin_lock_irqsave(&hctx->queue->queue_lock, flags);
> + need_run = blk_mq_hw_queue_need_run(hctx);
> + spin_unlock_irqrestore(&hctx->queue->queue_lock, flags);
> +
> + if (!need_run)
> + return;
> + }
Is this not solvable on the unquiesce side instead? It's rather a shame
to add overhead to the fast path to avoid a race with something that's
super unlikely, like quisce.
--
Jens Axboe
> On Sep 10, 2024, at 21:22, Jens Axboe <axboe@kernel.dk> wrote:
>
> On 9/3/24 2:16 AM, Muchun Song wrote:
>> Supposing the following scenario.
>>
>> CPU0 CPU1
>>
>> blk_mq_insert_request() 1) store blk_mq_unquiesce_queue()
>> blk_mq_run_hw_queue() blk_queue_flag_clear(QUEUE_FLAG_QUIESCED) 3) store
>> if (blk_queue_quiesced()) 2) load blk_mq_run_hw_queues()
>> return blk_mq_run_hw_queue()
>> blk_mq_sched_dispatch_requests() if (!blk_mq_hctx_has_pending()) 4) load
>> return
>>
>> The full memory barrier should be inserted between 1) and 2), as well as
>> between 3) and 4) to make sure that either CPU0 sees QUEUE_FLAG_QUIESCED is
>> cleared or CPU1 sees dispatch list or setting of bitmap of software queue.
>> Otherwise, either CPU will not re-run the hardware queue causing starvation.
>>
>> So the first solution is to 1) add a pair of memory barrier to fix the
>> problem, another solution is to 2) use hctx->queue->queue_lock to synchronize
>> QUEUE_FLAG_QUIESCED. Here, we chose 2) to fix it since memory barrier is not
>> easy to be maintained.
>
> Same comment here, 72-74 chars wide please.
OK.
>
>> diff --git a/block/blk-mq.c b/block/blk-mq.c
>> index b2d0f22de0c7f..ac39f2a346a52 100644
>> --- a/block/blk-mq.c
>> +++ b/block/blk-mq.c
>> @@ -2202,6 +2202,24 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
>> }
>> EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
>>
>> +static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx)
>> +{
>> + bool need_run;
>> +
>> + /*
>> + * When queue is quiesced, we may be switching io scheduler, or
>> + * updating nr_hw_queues, or other things, and we can't run queue
>> + * any more, even blk_mq_hctx_has_pending() can't be called safely.
>> + *
>> + * And queue will be rerun in blk_mq_unquiesce_queue() if it is
>> + * quiesced.
>> + */
>> + __blk_mq_run_dispatch_ops(hctx->queue, false,
>> + need_run = !blk_queue_quiesced(hctx->queue) &&
>> + blk_mq_hctx_has_pending(hctx));
>> + return need_run;
>> +}
>
> This __blk_mq_run_dispatch_ops() is also way too wide, why didn't you
> just break it like where you copied it from?
I thought the rule allows max 80 chars pre line, so I adjusted
the code to let them align with the above "(". Seems you prefer
the previous way, I can keep it the same as before.
Muchun,
Thanks.
>
>> +
>> /**
>> * blk_mq_run_hw_queue - Start to run a hardware queue.
>> * @hctx: Pointer to the hardware queue to run.
>> @@ -2222,20 +2240,23 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
>>
>> might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING);
>>
>> - /*
>> - * When queue is quiesced, we may be switching io scheduler, or
>> - * updating nr_hw_queues, or other things, and we can't run queue
>> - * any more, even __blk_mq_hctx_has_pending() can't be called safely.
>> - *
>> - * And queue will be rerun in blk_mq_unquiesce_queue() if it is
>> - * quiesced.
>> - */
>> - __blk_mq_run_dispatch_ops(hctx->queue, false,
>> - need_run = !blk_queue_quiesced(hctx->queue) &&
>> - blk_mq_hctx_has_pending(hctx));
>> + need_run = blk_mq_hw_queue_need_run(hctx);
>> + if (!need_run) {
>> + unsigned long flags;
>>
>> - if (!need_run)
>> - return;
>> + /*
>> + * synchronize with blk_mq_unquiesce_queue(), becuase we check
>> + * if hw queue is quiesced locklessly above, we need the use
>> + * ->queue_lock to make sure we see the up-to-date status to
>> + * not miss rerunning the hw queue.
>> + */
>> + spin_lock_irqsave(&hctx->queue->queue_lock, flags);
>> + need_run = blk_mq_hw_queue_need_run(hctx);
>> + spin_unlock_irqrestore(&hctx->queue->queue_lock, flags);
>> +
>> + if (!need_run)
>> + return;
>> + }
>
> Is this not solvable on the unquiesce side instead? It's rather a shame
> to add overhead to the fast path to avoid a race with something that's
> super unlikely, like quisce.
>
> --
> Jens Axboe
On Tue, Sep 10, 2024 at 07:22:16AM -0600, Jens Axboe wrote:
> On 9/3/24 2:16 AM, Muchun Song wrote:
> > Supposing the following scenario.
> >
> > CPU0 CPU1
> >
> > blk_mq_insert_request() 1) store blk_mq_unquiesce_queue()
> > blk_mq_run_hw_queue() blk_queue_flag_clear(QUEUE_FLAG_QUIESCED) 3) store
> > if (blk_queue_quiesced()) 2) load blk_mq_run_hw_queues()
> > return blk_mq_run_hw_queue()
> > blk_mq_sched_dispatch_requests() if (!blk_mq_hctx_has_pending()) 4) load
> > return
> >
> > The full memory barrier should be inserted between 1) and 2), as well as
> > between 3) and 4) to make sure that either CPU0 sees QUEUE_FLAG_QUIESCED is
> > cleared or CPU1 sees dispatch list or setting of bitmap of software queue.
> > Otherwise, either CPU will not re-run the hardware queue causing starvation.
> >
> > So the first solution is to 1) add a pair of memory barrier to fix the
> > problem, another solution is to 2) use hctx->queue->queue_lock to synchronize
> > QUEUE_FLAG_QUIESCED. Here, we chose 2) to fix it since memory barrier is not
> > easy to be maintained.
>
> Same comment here, 72-74 chars wide please.
>
> > diff --git a/block/blk-mq.c b/block/blk-mq.c
> > index b2d0f22de0c7f..ac39f2a346a52 100644
> > --- a/block/blk-mq.c
> > +++ b/block/blk-mq.c
> > @@ -2202,6 +2202,24 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
> > }
> > EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
> >
> > +static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx)
> > +{
> > + bool need_run;
> > +
> > + /*
> > + * When queue is quiesced, we may be switching io scheduler, or
> > + * updating nr_hw_queues, or other things, and we can't run queue
> > + * any more, even blk_mq_hctx_has_pending() can't be called safely.
> > + *
> > + * And queue will be rerun in blk_mq_unquiesce_queue() if it is
> > + * quiesced.
> > + */
> > + __blk_mq_run_dispatch_ops(hctx->queue, false,
> > + need_run = !blk_queue_quiesced(hctx->queue) &&
> > + blk_mq_hctx_has_pending(hctx));
> > + return need_run;
> > +}
>
> This __blk_mq_run_dispatch_ops() is also way too wide, why didn't you
> just break it like where you copied it from?
>
> > +
> > /**
> > * blk_mq_run_hw_queue - Start to run a hardware queue.
> > * @hctx: Pointer to the hardware queue to run.
> > @@ -2222,20 +2240,23 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
> >
> > might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING);
> >
> > - /*
> > - * When queue is quiesced, we may be switching io scheduler, or
> > - * updating nr_hw_queues, or other things, and we can't run queue
> > - * any more, even __blk_mq_hctx_has_pending() can't be called safely.
> > - *
> > - * And queue will be rerun in blk_mq_unquiesce_queue() if it is
> > - * quiesced.
> > - */
> > - __blk_mq_run_dispatch_ops(hctx->queue, false,
> > - need_run = !blk_queue_quiesced(hctx->queue) &&
> > - blk_mq_hctx_has_pending(hctx));
> > + need_run = blk_mq_hw_queue_need_run(hctx);
> > + if (!need_run) {
> > + unsigned long flags;
> >
> > - if (!need_run)
> > - return;
> > + /*
> > + * synchronize with blk_mq_unquiesce_queue(), becuase we check
> > + * if hw queue is quiesced locklessly above, we need the use
> > + * ->queue_lock to make sure we see the up-to-date status to
> > + * not miss rerunning the hw queue.
> > + */
> > + spin_lock_irqsave(&hctx->queue->queue_lock, flags);
> > + need_run = blk_mq_hw_queue_need_run(hctx);
> > + spin_unlock_irqrestore(&hctx->queue->queue_lock, flags);
> > +
> > + if (!need_run)
> > + return;
> > + }
>
> Is this not solvable on the unquiesce side instead? It's rather a shame
> to add overhead to the fast path to avoid a race with something that's
> super unlikely, like quisce.
Yeah, it can be solved by adding synchronize_rcu()/srcu() in unquiesce
side, but SCSI may call it in non-sleepable context via scsi_internal_device_unblock_nowait().
Thanks,
Ming
> On Sep 11, 2024, at 11:54, Ming Lei <ming.lei@redhat.com> wrote:
>
> On Tue, Sep 10, 2024 at 07:22:16AM -0600, Jens Axboe wrote:
>> On 9/3/24 2:16 AM, Muchun Song wrote:
>>> Supposing the following scenario.
>>>
>>> CPU0 CPU1
>>>
>>> blk_mq_insert_request() 1) store blk_mq_unquiesce_queue()
>>> blk_mq_run_hw_queue() blk_queue_flag_clear(QUEUE_FLAG_QUIESCED) 3) store
>>> if (blk_queue_quiesced()) 2) load blk_mq_run_hw_queues()
>>> return blk_mq_run_hw_queue()
>>> blk_mq_sched_dispatch_requests() if (!blk_mq_hctx_has_pending()) 4) load
>>> return
>>>
>>> The full memory barrier should be inserted between 1) and 2), as well as
>>> between 3) and 4) to make sure that either CPU0 sees QUEUE_FLAG_QUIESCED is
>>> cleared or CPU1 sees dispatch list or setting of bitmap of software queue.
>>> Otherwise, either CPU will not re-run the hardware queue causing starvation.
>>>
>>> So the first solution is to 1) add a pair of memory barrier to fix the
>>> problem, another solution is to 2) use hctx->queue->queue_lock to synchronize
>>> QUEUE_FLAG_QUIESCED. Here, we chose 2) to fix it since memory barrier is not
>>> easy to be maintained.
>>
>> Same comment here, 72-74 chars wide please.
>>
>>> diff --git a/block/blk-mq.c b/block/blk-mq.c
>>> index b2d0f22de0c7f..ac39f2a346a52 100644
>>> --- a/block/blk-mq.c
>>> +++ b/block/blk-mq.c
>>> @@ -2202,6 +2202,24 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
>>> }
>>> EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
>>>
>>> +static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx)
>>> +{
>>> + bool need_run;
>>> +
>>> + /*
>>> + * When queue is quiesced, we may be switching io scheduler, or
>>> + * updating nr_hw_queues, or other things, and we can't run queue
>>> + * any more, even blk_mq_hctx_has_pending() can't be called safely.
>>> + *
>>> + * And queue will be rerun in blk_mq_unquiesce_queue() if it is
>>> + * quiesced.
>>> + */
>>> + __blk_mq_run_dispatch_ops(hctx->queue, false,
>>> + need_run = !blk_queue_quiesced(hctx->queue) &&
>>> + blk_mq_hctx_has_pending(hctx));
>>> + return need_run;
>>> +}
>>
>> This __blk_mq_run_dispatch_ops() is also way too wide, why didn't you
>> just break it like where you copied it from?
>>
>>> +
>>> /**
>>> * blk_mq_run_hw_queue - Start to run a hardware queue.
>>> * @hctx: Pointer to the hardware queue to run.
>>> @@ -2222,20 +2240,23 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
>>>
>>> might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING);
>>>
>>> - /*
>>> - * When queue is quiesced, we may be switching io scheduler, or
>>> - * updating nr_hw_queues, or other things, and we can't run queue
>>> - * any more, even __blk_mq_hctx_has_pending() can't be called safely.
>>> - *
>>> - * And queue will be rerun in blk_mq_unquiesce_queue() if it is
>>> - * quiesced.
>>> - */
>>> - __blk_mq_run_dispatch_ops(hctx->queue, false,
>>> - need_run = !blk_queue_quiesced(hctx->queue) &&
>>> - blk_mq_hctx_has_pending(hctx));
>>> + need_run = blk_mq_hw_queue_need_run(hctx);
>>> + if (!need_run) {
>>> + unsigned long flags;
>>>
>>> - if (!need_run)
>>> - return;
>>> + /*
>>> + * synchronize with blk_mq_unquiesce_queue(), becuase we check
>>> + * if hw queue is quiesced locklessly above, we need the use
>>> + * ->queue_lock to make sure we see the up-to-date status to
>>> + * not miss rerunning the hw queue.
>>> + */
>>> + spin_lock_irqsave(&hctx->queue->queue_lock, flags);
>>> + need_run = blk_mq_hw_queue_need_run(hctx);
>>> + spin_unlock_irqrestore(&hctx->queue->queue_lock, flags);
>>> +
>>> + if (!need_run)
>>> + return;
>>> + }
>>
>> Is this not solvable on the unquiesce side instead? It's rather a shame
>> to add overhead to the fast path to avoid a race with something that's
>> super unlikely, like quisce.
>
> Yeah, it can be solved by adding synchronize_rcu()/srcu() in unquiesce
> side, but SCSI may call it in non-sleepable context via scsi_internal_device_unblock_nowait().
Hi Ming and Jens,
I use call_srcu/call_rcu to make it non-sleepable. Does this make sense to you?
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 12bf38bec1044..86cdff28b2ce6 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -247,6 +247,13 @@ void blk_mq_quiesce_queue(struct request_queue *q)
}
EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);
+static void blk_mq_run_hw_queues_rcu(struct rcu_head *rh)
+{
+ struct request_queue *q = container_of(rh, struct request_queue,
+ rcu_head);
+ blk_mq_run_hw_queues(q, true);
+}
+
/*
* blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue()
* @q: request queue.
@@ -269,8 +276,13 @@ void blk_mq_unquiesce_queue(struct request_queue *q)
spin_unlock_irqrestore(&q->queue_lock, flags);
/* dispatch requests which are inserted during quiescing */
- if (run_queue)
- blk_mq_run_hw_queues(q, true);
+ if (run_queue) {
+ if (q->tag_set->flags & BLK_MQ_F_BLOCKING)
+ call_srcu(q->tag_set->srcu, &q->rcu_head,
+ blk_mq_run_hw_queues_rcu);
+ else
+ call_rcu(&q->rcu_head, blk_mq_run_hw_queues_rcu);
+ }
}
EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);
>
>
> Thanks,
> Ming
> On Sep 12, 2024, at 11:27, Muchun Song <muchun.song@linux.dev> wrote:
>
>
>
>> On Sep 11, 2024, at 11:54, Ming Lei <ming.lei@redhat.com> wrote:
>>
>> On Tue, Sep 10, 2024 at 07:22:16AM -0600, Jens Axboe wrote:
>>> On 9/3/24 2:16 AM, Muchun Song wrote:
>>>> Supposing the following scenario.
>>>>
>>>> CPU0 CPU1
>>>>
>>>> blk_mq_insert_request() 1) store blk_mq_unquiesce_queue()
>>>> blk_mq_run_hw_queue() blk_queue_flag_clear(QUEUE_FLAG_QUIESCED) 3) store
>>>> if (blk_queue_quiesced()) 2) load blk_mq_run_hw_queues()
>>>> return blk_mq_run_hw_queue()
>>>> blk_mq_sched_dispatch_requests() if (!blk_mq_hctx_has_pending()) 4) load
>>>> return
>>>>
>>>> The full memory barrier should be inserted between 1) and 2), as well as
>>>> between 3) and 4) to make sure that either CPU0 sees QUEUE_FLAG_QUIESCED is
>>>> cleared or CPU1 sees dispatch list or setting of bitmap of software queue.
>>>> Otherwise, either CPU will not re-run the hardware queue causing starvation.
>>>>
>>>> So the first solution is to 1) add a pair of memory barrier to fix the
>>>> problem, another solution is to 2) use hctx->queue->queue_lock to synchronize
>>>> QUEUE_FLAG_QUIESCED. Here, we chose 2) to fix it since memory barrier is not
>>>> easy to be maintained.
>>>
>>> Same comment here, 72-74 chars wide please.
>>>
>>>> diff --git a/block/blk-mq.c b/block/blk-mq.c
>>>> index b2d0f22de0c7f..ac39f2a346a52 100644
>>>> --- a/block/blk-mq.c
>>>> +++ b/block/blk-mq.c
>>>> @@ -2202,6 +2202,24 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
>>>> }
>>>> EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
>>>>
>>>> +static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx)
>>>> +{
>>>> + bool need_run;
>>>> +
>>>> + /*
>>>> + * When queue is quiesced, we may be switching io scheduler, or
>>>> + * updating nr_hw_queues, or other things, and we can't run queue
>>>> + * any more, even blk_mq_hctx_has_pending() can't be called safely.
>>>> + *
>>>> + * And queue will be rerun in blk_mq_unquiesce_queue() if it is
>>>> + * quiesced.
>>>> + */
>>>> + __blk_mq_run_dispatch_ops(hctx->queue, false,
>>>> + need_run = !blk_queue_quiesced(hctx->queue) &&
>>>> + blk_mq_hctx_has_pending(hctx));
>>>> + return need_run;
>>>> +}
>>>
>>> This __blk_mq_run_dispatch_ops() is also way too wide, why didn't you
>>> just break it like where you copied it from?
>>>
>>>> +
>>>> /**
>>>> * blk_mq_run_hw_queue - Start to run a hardware queue.
>>>> * @hctx: Pointer to the hardware queue to run.
>>>> @@ -2222,20 +2240,23 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
>>>>
>>>> might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING);
>>>>
>>>> - /*
>>>> - * When queue is quiesced, we may be switching io scheduler, or
>>>> - * updating nr_hw_queues, or other things, and we can't run queue
>>>> - * any more, even __blk_mq_hctx_has_pending() can't be called safely.
>>>> - *
>>>> - * And queue will be rerun in blk_mq_unquiesce_queue() if it is
>>>> - * quiesced.
>>>> - */
>>>> - __blk_mq_run_dispatch_ops(hctx->queue, false,
>>>> - need_run = !blk_queue_quiesced(hctx->queue) &&
>>>> - blk_mq_hctx_has_pending(hctx));
>>>> + need_run = blk_mq_hw_queue_need_run(hctx);
>>>> + if (!need_run) {
>>>> + unsigned long flags;
>>>>
>>>> - if (!need_run)
>>>> - return;
>>>> + /*
>>>> + * synchronize with blk_mq_unquiesce_queue(), becuase we check
>>>> + * if hw queue is quiesced locklessly above, we need the use
>>>> + * ->queue_lock to make sure we see the up-to-date status to
>>>> + * not miss rerunning the hw queue.
>>>> + */
>>>> + spin_lock_irqsave(&hctx->queue->queue_lock, flags);
>>>> + need_run = blk_mq_hw_queue_need_run(hctx);
>>>> + spin_unlock_irqrestore(&hctx->queue->queue_lock, flags);
>>>> +
>>>> + if (!need_run)
>>>> + return;
>>>> + }
>>>
>>> Is this not solvable on the unquiesce side instead? It's rather a shame
>>> to add overhead to the fast path to avoid a race with something that's
>>> super unlikely, like quisce.
>>
>> Yeah, it can be solved by adding synchronize_rcu()/srcu() in unquiesce
>> side, but SCSI may call it in non-sleepable context via scsi_internal_device_unblock_nowait().
>
> Hi Ming and Jens,
>
> I use call_srcu/call_rcu to make it non-sleepable. Does this make sense to you?
Sorry for the noise. call_srcu/call_rcu can't be easy to do this.
Because call_srcu/call_rcu could be issued twice if users try to
unquiesce the queue again before the callback of
blk_mq_run_hw_queues_rcu has been executed.
Thanks.
>
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index 12bf38bec1044..86cdff28b2ce6 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -247,6 +247,13 @@ void blk_mq_quiesce_queue(struct request_queue *q)
> }
> EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);
>
> +static void blk_mq_run_hw_queues_rcu(struct rcu_head *rh)
> +{
> + struct request_queue *q = container_of(rh, struct request_queue,
> + rcu_head);
> + blk_mq_run_hw_queues(q, true);
> +}
> +
> /*
> * blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue()
> * @q: request queue.
> @@ -269,8 +276,13 @@ void blk_mq_unquiesce_queue(struct request_queue *q)
> spin_unlock_irqrestore(&q->queue_lock, flags);
>
> /* dispatch requests which are inserted during quiescing */
> - if (run_queue)
> - blk_mq_run_hw_queues(q, true);
> + if (run_queue) {
> + if (q->tag_set->flags & BLK_MQ_F_BLOCKING)
> + call_srcu(q->tag_set->srcu, &q->rcu_head,
> + blk_mq_run_hw_queues_rcu);
> + else
> + call_rcu(&q->rcu_head, blk_mq_run_hw_queues_rcu);
> + }
> }
> EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);
>
>>
>>
>> Thanks,
>> Ming
> On Sep 11, 2024, at 11:54, Ming Lei <ming.lei@redhat.com> wrote:
>
> On Tue, Sep 10, 2024 at 07:22:16AM -0600, Jens Axboe wrote:
>> On 9/3/24 2:16 AM, Muchun Song wrote:
>>> Supposing the following scenario.
>>>
>>> CPU0 CPU1
>>>
>>> blk_mq_insert_request() 1) store blk_mq_unquiesce_queue()
>>> blk_mq_run_hw_queue() blk_queue_flag_clear(QUEUE_FLAG_QUIESCED) 3) store
>>> if (blk_queue_quiesced()) 2) load blk_mq_run_hw_queues()
>>> return blk_mq_run_hw_queue()
>>> blk_mq_sched_dispatch_requests() if (!blk_mq_hctx_has_pending()) 4) load
>>> return
>>>
>>> The full memory barrier should be inserted between 1) and 2), as well as
>>> between 3) and 4) to make sure that either CPU0 sees QUEUE_FLAG_QUIESCED is
>>> cleared or CPU1 sees dispatch list or setting of bitmap of software queue.
>>> Otherwise, either CPU will not re-run the hardware queue causing starvation.
>>>
>>> So the first solution is to 1) add a pair of memory barrier to fix the
>>> problem, another solution is to 2) use hctx->queue->queue_lock to synchronize
>>> QUEUE_FLAG_QUIESCED. Here, we chose 2) to fix it since memory barrier is not
>>> easy to be maintained.
>>
>> Same comment here, 72-74 chars wide please.
>>
>>> diff --git a/block/blk-mq.c b/block/blk-mq.c
>>> index b2d0f22de0c7f..ac39f2a346a52 100644
>>> --- a/block/blk-mq.c
>>> +++ b/block/blk-mq.c
>>> @@ -2202,6 +2202,24 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
>>> }
>>> EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
>>>
>>> +static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx)
>>> +{
>>> + bool need_run;
>>> +
>>> + /*
>>> + * When queue is quiesced, we may be switching io scheduler, or
>>> + * updating nr_hw_queues, or other things, and we can't run queue
>>> + * any more, even blk_mq_hctx_has_pending() can't be called safely.
>>> + *
>>> + * And queue will be rerun in blk_mq_unquiesce_queue() if it is
>>> + * quiesced.
>>> + */
>>> + __blk_mq_run_dispatch_ops(hctx->queue, false,
>>> + need_run = !blk_queue_quiesced(hctx->queue) &&
>>> + blk_mq_hctx_has_pending(hctx));
>>> + return need_run;
>>> +}
>>
>> This __blk_mq_run_dispatch_ops() is also way too wide, why didn't you
>> just break it like where you copied it from?
>>
>>> +
>>> /**
>>> * blk_mq_run_hw_queue - Start to run a hardware queue.
>>> * @hctx: Pointer to the hardware queue to run.
>>> @@ -2222,20 +2240,23 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
>>>
>>> might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING);
>>>
>>> - /*
>>> - * When queue is quiesced, we may be switching io scheduler, or
>>> - * updating nr_hw_queues, or other things, and we can't run queue
>>> - * any more, even __blk_mq_hctx_has_pending() can't be called safely.
>>> - *
>>> - * And queue will be rerun in blk_mq_unquiesce_queue() if it is
>>> - * quiesced.
>>> - */
>>> - __blk_mq_run_dispatch_ops(hctx->queue, false,
>>> - need_run = !blk_queue_quiesced(hctx->queue) &&
>>> - blk_mq_hctx_has_pending(hctx));
>>> + need_run = blk_mq_hw_queue_need_run(hctx);
>>> + if (!need_run) {
>>> + unsigned long flags;
>>>
>>> - if (!need_run)
>>> - return;
>>> + /*
>>> + * synchronize with blk_mq_unquiesce_queue(), becuase we check
>>> + * if hw queue is quiesced locklessly above, we need the use
>>> + * ->queue_lock to make sure we see the up-to-date status to
>>> + * not miss rerunning the hw queue.
>>> + */
>>> + spin_lock_irqsave(&hctx->queue->queue_lock, flags);
>>> + need_run = blk_mq_hw_queue_need_run(hctx);
>>> + spin_unlock_irqrestore(&hctx->queue->queue_lock, flags);
>>> +
>>> + if (!need_run)
>>> + return;
>>> + }
>>
>> Is this not solvable on the unquiesce side instead? It's rather a shame
>> to add overhead to the fast path to avoid a race with something that's
>> super unlikely, like quisce.
>
> Yeah, it can be solved by adding synchronize_rcu()/srcu() in unquiesce
> side, but SCSI may call it in non-sleepable context via scsi_internal_device_unblock_nowait().
Another approach will be like the fix for BLK_MQ_S_STOPPED (in patch 3),
we could add a pair of mb into blk_queue_quiesced() and
blk_mq_unquiesce_queue(). In which case, the fix will not affect any fast
path, only slow path need the barrier overhead.
diff --git a/block/blk-mq.c b/block/blk-mq.c
index b2d0f22de0c7f..45588ddb08d6b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -264,6 +264,12 @@ void blk_mq_unquiesce_queue(struct request_queue *q)
;
} else if (!--q->quiesce_depth) {
blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q);
+ /*
+ * Pairs with the smp_mb() in blk_queue_quiesced() to order the
+ * clearing of QUEUE_FLAG_QUIESCED above and the checking of
+ * dispatch list in the subsequent routine.
+ */
+ smp_mb__after_atomic();
run_queue = true;
}
spin_unlock_irqrestore(&q->queue_lock, flags);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b8196e219ac22..7a71462892b66 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -628,7 +628,25 @@ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
#define blk_noretry_request(rq) \
((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
REQ_FAILFAST_DRIVER))
-#define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags)
+
+static inline bool blk_queue_quiesced(struct request_queue *q)
+{
+ /* Fast path: hardware queue is unquiesced most of the time. */
+ if (likely(!test_bit(QUEUE_FLAG_QUIESCED, &q->queue_flags)))
+ return false;
+
+ /*
+ * This barrier is used to order adding of dispatch list before and
+ * the test of QUEUE_FLAG_QUIESCED below. Pairs with the memory barrier
+ * in blk_mq_unquiesce_queue() so that dispatch code could either see
+ * QUEUE_FLAG_QUIESCED is cleared or dispatch list is not empty to
+ * avoid missing dispatching requests.
+ */
+ smp_mb();
+
+ return test_bit(QUEUE_FLAG_QUIESCED, &q->queue_flags);
+}
+
#define blk_queue_pm_only(q) atomic_read(&(q)->pm_only)
#define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
#define blk_queue_sq_sched(q) test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags)
Muchun,
Thanks.
>
>
> Thanks,
> Ming
> On Sep 11, 2024, at 11:59, Muchun Song <muchun.song@linux.dev> wrote:
>
>
>
>> On Sep 11, 2024, at 11:54, Ming Lei <ming.lei@redhat.com> wrote:
>>
>>> On Tue, Sep 10, 2024 at 07:22:16AM -0600, Jens Axboe wrote:
>>> On 9/3/24 2:16 AM, Muchun Song wrote:
>>>> Supposing the following scenario.
>>>>
>>>> CPU0 CPU1
>>>>
>>>> blk_mq_insert_request() 1) store blk_mq_unquiesce_queue()
>>>> blk_mq_run_hw_queue() blk_queue_flag_clear(QUEUE_FLAG_QUIESCED) 3) store
>>>> if (blk_queue_quiesced()) 2) load blk_mq_run_hw_queues()
>>>> return blk_mq_run_hw_queue()
>>>> blk_mq_sched_dispatch_requests() if (!blk_mq_hctx_has_pending()) 4) load
>>>> return
>>>>
>>>> The full memory barrier should be inserted between 1) and 2), as well as
>>>> between 3) and 4) to make sure that either CPU0 sees QUEUE_FLAG_QUIESCED is
>>>> cleared or CPU1 sees dispatch list or setting of bitmap of software queue.
>>>> Otherwise, either CPU will not re-run the hardware queue causing starvation.
>>>>
>>>> So the first solution is to 1) add a pair of memory barrier to fix the
>>>> problem, another solution is to 2) use hctx->queue->queue_lock to synchronize
>>>> QUEUE_FLAG_QUIESCED. Here, we chose 2) to fix it since memory barrier is not
>>>> easy to be maintained.
>>>
>>> Same comment here, 72-74 chars wide please.
>>>
>>>> diff --git a/block/blk-mq.c b/block/blk-mq.c
>>>> index b2d0f22de0c7f..ac39f2a346a52 100644
>>>> --- a/block/blk-mq.c
>>>> +++ b/block/blk-mq.c
>>>> @@ -2202,6 +2202,24 @@ void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs)
>>>> }
>>>> EXPORT_SYMBOL(blk_mq_delay_run_hw_queue);
>>>>
>>>> +static inline bool blk_mq_hw_queue_need_run(struct blk_mq_hw_ctx *hctx)
>>>> +{
>>>> + bool need_run;
>>>> +
>>>> + /*
>>>> + * When queue is quiesced, we may be switching io scheduler, or
>>>> + * updating nr_hw_queues, or other things, and we can't run queue
>>>> + * any more, even blk_mq_hctx_has_pending() can't be called safely.
>>>> + *
>>>> + * And queue will be rerun in blk_mq_unquiesce_queue() if it is
>>>> + * quiesced.
>>>> + */
>>>> + __blk_mq_run_dispatch_ops(hctx->queue, false,
>>>> + need_run = !blk_queue_quiesced(hctx->queue) &&
>>>> + blk_mq_hctx_has_pending(hctx));
>>>> + return need_run;
>>>> +}
>>>
>>> This __blk_mq_run_dispatch_ops() is also way too wide, why didn't you
>>> just break it like where you copied it from?
>>>
>>>> +
>>>> /**
>>>> * blk_mq_run_hw_queue - Start to run a hardware queue.
>>>> * @hctx: Pointer to the hardware queue to run.
>>>> @@ -2222,20 +2240,23 @@ void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async)
>>>>
>>>> might_sleep_if(!async && hctx->flags & BLK_MQ_F_BLOCKING);
>>>>
>>>> - /*
>>>> - * When queue is quiesced, we may be switching io scheduler, or
>>>> - * updating nr_hw_queues, or other things, and we can't run queue
>>>> - * any more, even __blk_mq_hctx_has_pending() can't be called safely.
>>>> - *
>>>> - * And queue will be rerun in blk_mq_unquiesce_queue() if it is
>>>> - * quiesced.
>>>> - */
>>>> - __blk_mq_run_dispatch_ops(hctx->queue, false,
>>>> - need_run = !blk_queue_quiesced(hctx->queue) &&
>>>> - blk_mq_hctx_has_pending(hctx));
>>>> + need_run = blk_mq_hw_queue_need_run(hctx);
>>>> + if (!need_run) {
>>>> + unsigned long flags;
>>>>
>>>> - if (!need_run)
>>>> - return;
>>>> + /*
>>>> + * synchronize with blk_mq_unquiesce_queue(), becuase we check
>>>> + * if hw queue is quiesced locklessly above, we need the use
>>>> + * ->queue_lock to make sure we see the up-to-date status to
>>>> + * not miss rerunning the hw queue.
>>>> + */
>>>> + spin_lock_irqsave(&hctx->queue->queue_lock, flags);
>>>> + need_run = blk_mq_hw_queue_need_run(hctx);
>>>> + spin_unlock_irqrestore(&hctx->queue->queue_lock, flags);
>>>> +
>>>> + if (!need_run)
>>>> + return;
>>>> + }
>>>
>>> Is this not solvable on the unquiesce side instead? It's rather a shame
>>> to add overhead to the fast path to avoid a race with something that's
>>> super unlikely, like quisce.
>>
>> Yeah, it can be solved by adding synchronize_rcu()/srcu() in unquiesce
>> side, but SCSI may call it in non-sleepable context via scsi_internal_device_unblock_nowait().
>
> Another approach will be like the fix for BLK_MQ_S_STOPPED (in patch 3),
> we could add a pair of mb into blk_queue_quiesced() and
> blk_mq_unquiesce_queue(). In which case, the fix will not affect any fast
> path, only slow path need the barrier overhead.
I misunderstood Jens’s question. I think Ming is right.
This approach only tries to reduce the overhead as
much
as possible even for slow path compared to
spinlock_based approach.
Not solving the problem only from the unquiesce side.
Muchun,
Thanks.
>
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index b2d0f22de0c7f..45588ddb08d6b 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -264,6 +264,12 @@ void blk_mq_unquiesce_queue(struct request_queue *q)
> ;
> } else if (!--q->quiesce_depth) {
> blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q);
> + /*
> + * Pairs with the smp_mb() in blk_queue_quiesced() to order the
> + * clearing of QUEUE_FLAG_QUIESCED above and the checking of
> + * dispatch list in the subsequent routine.
> + */
> + smp_mb__after_atomic();
> run_queue = true;
> }
> spin_unlock_irqrestore(&q->queue_lock, flags);
> diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
> index b8196e219ac22..7a71462892b66 100644
> --- a/include/linux/blkdev.h
> +++ b/include/linux/blkdev.h
> @@ -628,7 +628,25 @@ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
> #define blk_noretry_request(rq) \
> ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \
> REQ_FAILFAST_DRIVER))
> -#define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags)
> +
> +static inline bool blk_queue_quiesced(struct request_queue *q)
> +{
> + /* Fast path: hardware queue is unquiesced most of the time. */
> + if (likely(!test_bit(QUEUE_FLAG_QUIESCED, &q->queue_flags)))
> + return false;
> +
> + /*
> + * This barrier is used to order adding of dispatch list before and
> + * the test of QUEUE_FLAG_QUIESCED below. Pairs with the memory barrier
> + * in blk_mq_unquiesce_queue() so that dispatch code could either see
> + * QUEUE_FLAG_QUIESCED is cleared or dispatch list is not empty to
> + * avoid missing dispatching requests.
> + */
> + smp_mb();
> +
> + return test_bit(QUEUE_FLAG_QUIESCED, &q->queue_flags);
> +}
> +
> #define blk_queue_pm_only(q) atomic_read(&(q)->pm_only)
> #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
> #define blk_queue_sq_sched(q) test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags)
>
> Muchun,
> Thanks.
>
>>
>>
>> Thanks,
>> Ming
>
>
On Tue, Sep 03, 2024 at 04:16:52PM +0800, Muchun Song wrote:
> Supposing the following scenario.
>
> CPU0 CPU1
>
> blk_mq_insert_request() 1) store blk_mq_unquiesce_queue()
> blk_mq_run_hw_queue() blk_queue_flag_clear(QUEUE_FLAG_QUIESCED) 3) store
> if (blk_queue_quiesced()) 2) load blk_mq_run_hw_queues()
> return blk_mq_run_hw_queue()
> blk_mq_sched_dispatch_requests() if (!blk_mq_hctx_has_pending()) 4) load
> return
>
> The full memory barrier should be inserted between 1) and 2), as well as
> between 3) and 4) to make sure that either CPU0 sees QUEUE_FLAG_QUIESCED is
> cleared or CPU1 sees dispatch list or setting of bitmap of software queue.
> Otherwise, either CPU will not re-run the hardware queue causing starvation.
>
> So the first solution is to 1) add a pair of memory barrier to fix the
> problem, another solution is to 2) use hctx->queue->queue_lock to synchronize
> QUEUE_FLAG_QUIESCED. Here, we chose 2) to fix it since memory barrier is not
> easy to be maintained.
>
> Fixes: f4560ffe8cec1 ("blk-mq: use QUEUE_FLAG_QUIESCED to quiesce queue")
> Cc: stable@vger.kernel.org
> Cc: Muchun Song <muchun.song@linux.dev>
> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
thanks,
Ming
© 2016 - 2025 Red Hat, Inc.