public inbox for linux-nvme@lists.infradead.org
 help / color / mirror / Atom feed
From: Chao Leng <lengchao@huawei.com>
To: <linux-nvme@lists.infradead.org>, <linux-block@vger.kernel.org>
Cc: <hch@lst.de>, <sagi@grimberg.me>, <kbusch@kernel.org>,
	<lengchao@huawei.com>, <axboe@kernel.dk>, <ming.lei@redhat.com>,
	<paulmck@kernel.org>
Subject: [PATCH v3 1/2] blk-mq: add tagset quiesce interface
Date: Thu, 20 Oct 2022 11:53:47 +0800	[thread overview]
Message-ID: <20221020035348.10163-2-lengchao@huawei.com> (raw)
In-Reply-To: <20221020035348.10163-1-lengchao@huawei.com>

Drivers that have shared tagsets may need to quiesce potentially a lot
of request queues that all share a single tagset (e.g. nvme). Add an
interface to quiesce all the queues on a given tagset. This interface is
useful because it can speedup the quiesce by doing it in parallel.

For tagsets that have BLK_MQ_F_BLOCKING set, we first call
start_poll_synchronize_srcu for all queues of the tagset, and then call
poll_state_synchronize_srcu such that all of them wait for the same srcu
elapsed period. For tagsets that don't have BLK_MQ_F_BLOCKING set,
we simply call a single synchronize_rcu as this is sufficient.

Because some queues should not need to be quiesced(e.g. nvme connect_q)
when quiesce the tagset. So introduce QUEUE_FLAG_SKIP_TAGSET_QUIESCE to
tagset quiesce interface to skip the queue.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Chao Leng <lengchao@huawei.com>
---
 block/blk-mq.c         | 76 ++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/blk-mq.h |  2 ++
 include/linux/blkdev.h |  3 ++
 3 files changed, 81 insertions(+)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 8070b6c10e8d..f064ecda425b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -311,6 +311,82 @@ void blk_mq_unquiesce_queue(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);
 
+static void blk_mq_quiesce_blocking_tagset(struct blk_mq_tag_set *set)
+{
+	int i, count = 0;
+	struct request_queue *q;
+	unsigned long *rcu;
+
+	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+		if (blk_queue_skip_tagset_quiesce(q))
+			continue;
+
+		blk_mq_quiesce_queue_nowait(q);
+		count++;
+	}
+
+	rcu = kvmalloc(count * sizeof(*rcu), GFP_KERNEL);
+	if (rcu) {
+		i = 0;
+		list_for_each_entry(q, &set->tag_list, tag_set_list) {
+			if (blk_queue_skip_tagset_quiesce(q))
+				continue;
+
+			rcu[i++] = start_poll_synchronize_srcu(q->srcu);
+		}
+
+		i = 0;
+		list_for_each_entry(q, &set->tag_list, tag_set_list) {
+			if (blk_queue_skip_tagset_quiesce(q))
+				continue;
+
+			if (!poll_state_synchronize_srcu(q->srcu, rcu[i++]))
+				synchronize_srcu(q->srcu);
+		}
+
+		kvfree(rcu);
+	} else {
+		list_for_each_entry(q, &set->tag_list, tag_set_list)
+			synchronize_srcu(q->srcu);
+	}
+}
+
+static void blk_mq_quiesce_nonblocking_tagset(struct blk_mq_tag_set *set)
+{
+	struct request_queue *q;
+
+	list_for_each_entry(q, &set->tag_list, tag_set_list) {
+		if (blk_queue_skip_tagset_quiesce(q))
+			continue;
+
+		blk_mq_quiesce_queue_nowait(q);
+	}
+	synchronize_rcu();
+}
+
+void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set)
+{
+	mutex_lock(&set->tag_list_lock);
+	if (set->flags & BLK_MQ_F_BLOCKING)
+		blk_mq_quiesce_blocking_tagset(set);
+	else
+		blk_mq_quiesce_nonblocking_tagset(set);
+
+	mutex_unlock(&set->tag_list_lock);
+}
+EXPORT_SYMBOL_GPL(blk_mq_quiesce_tagset);
+
+void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set)
+{
+	struct request_queue *q;
+
+	mutex_lock(&set->tag_list_lock);
+	list_for_each_entry(q, &set->tag_list, tag_set_list)
+		blk_mq_unquiesce_queue(q);
+	mutex_unlock(&set->tag_list_lock);
+}
+EXPORT_SYMBOL_GPL(blk_mq_unquiesce_tagset);
+
 void blk_mq_wake_waiters(struct request_queue *q)
 {
 	struct blk_mq_hw_ctx *hctx;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index ba18e9bdb799..1df47606d0a7 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -877,6 +877,8 @@ void blk_mq_start_hw_queues(struct request_queue *q);
 void blk_mq_start_stopped_hw_queue(struct blk_mq_hw_ctx *hctx, bool async);
 void blk_mq_start_stopped_hw_queues(struct request_queue *q, bool async);
 void blk_mq_quiesce_queue(struct request_queue *q);
+void blk_mq_quiesce_tagset(struct blk_mq_tag_set *set);
+void blk_mq_unquiesce_tagset(struct blk_mq_tag_set *set);
 void blk_mq_wait_quiesce_done(struct request_queue *q);
 void blk_mq_unquiesce_queue(struct request_queue *q);
 void blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 50e358a19d98..efa3fa771dce 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -579,6 +579,7 @@ struct request_queue {
 #define QUEUE_FLAG_HCTX_ACTIVE	28	/* at least one blk-mq hctx is active */
 #define QUEUE_FLAG_NOWAIT       29	/* device supports NOWAIT */
 #define QUEUE_FLAG_SQ_SCHED     30	/* single queue style io dispatch */
+#define QUEUE_FLAG_SKIP_TAGSET_QUIESCE	31 /* quiesce_tagset skip the queue*/
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1UL << QUEUE_FLAG_IO_STAT) |		\
 				 (1UL << QUEUE_FLAG_SAME_COMP) |	\
@@ -619,6 +620,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #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)
+#define blk_queue_skip_tagset_quiesce(q) \
+	test_bit(QUEUE_FLAG_SKIP_TAGSET_QUIESCE, &(q)->queue_flags)
 
 extern void blk_set_pm_only(struct request_queue *q);
 extern void blk_clear_pm_only(struct request_queue *q);
-- 
2.16.4



  reply	other threads:[~2022-10-20  3:54 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-10-20  3:53 [PATCH v2 0/2] improve nvme quiesce time for large amount of namespaces Chao Leng
2022-10-20  3:53 ` Chao Leng [this message]
2022-10-20 16:11   ` [PATCH v3 1/2] blk-mq: add tagset quiesce interface Paul E. McKenney
2022-10-20  3:53 ` [PATCH v3 2/2] nvme: use blk_mq_[un]quiesce_tagset Chao Leng
2022-10-20  6:11   ` Sagi Grimberg
2022-10-20  9:47     ` Chao Leng
2022-10-20  6:34 ` [PATCH v2 0/2] improve nvme quiesce time for large amount of namespaces Christoph Hellwig
2022-10-20  9:36   ` Chao Leng

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20221020035348.10163-2-lengchao@huawei.com \
    --to=lengchao@huawei.com \
    --cc=axboe@kernel.dk \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=ming.lei@redhat.com \
    --cc=paulmck@kernel.org \
    --cc=sagi@grimberg.me \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox