Linux-NVME Archive on lore.kernel.org
 help / color / Atom feed
From: Sagi Grimberg <sagi@grimberg.me>
To: linux-nvme@lists.infradead.org, Christoph Hellwig <hch@lst.de>,
	Keith Busch <kbusch@kernel.org>, Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, Ming Lin <mlin@kernel.org>,
	Chao Leng <lengchao@huawei.com>
Subject: [PATCH v4 1/2] blk-mq: add async quiesce interface
Date: Mon, 27 Jul 2020 15:07:16 -0700
Message-ID: <20200727220717.278116-2-sagi@grimberg.me> (raw)
In-Reply-To: <20200727220717.278116-1-sagi@grimberg.me>

Drivers that may have to quiesce a large amount of request queues at once
(e.g. controller or adapter reset). These drivers would benefit from an
async quiesce interface such that the can trigger quiesce asynchronously
and wait for all in parallel.

This leaves the synchronization responsibility to the driver, but adds
a convenient interface to quiesce async and wait in a single pass.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
---
 block/blk-mq.c         | 46 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/blk-mq.h |  4 ++++
 2 files changed, 50 insertions(+)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index abcf590f6238..d913924117d2 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -209,6 +209,52 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
 
+void blk_mq_quiesce_queue_async(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+	int rcu = false;
+
+	blk_mq_quiesce_queue_nowait(q);
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		hctx->rcu_sync = kmalloc(sizeof(*hctx->rcu_sync), GFP_KERNEL);
+		if (!hctx->rcu_sync) {
+			/* fallback to serial rcu sync */
+			if (hctx->flags & BLK_MQ_F_BLOCKING)
+				synchronize_srcu(hctx->srcu);
+			else
+				rcu = true;
+		} else {
+			init_completion(&hctx->rcu_sync->completion);
+			init_rcu_head(&hctx->rcu_sync->head);
+			if (hctx->flags & BLK_MQ_F_BLOCKING)
+				call_srcu(hctx->srcu, &hctx->rcu_sync->head,
+					wakeme_after_rcu);
+			else
+				call_rcu(&hctx->rcu_sync->head,
+					wakeme_after_rcu);
+		}
+	}
+	if (rcu)
+		synchronize_rcu();
+}
+EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_async);
+
+void blk_mq_quiesce_queue_async_wait(struct request_queue *q)
+{
+	struct blk_mq_hw_ctx *hctx;
+	unsigned int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (!hctx->rcu_sync)
+			continue;
+		wait_for_completion(&hctx->rcu_sync->completion);
+		destroy_rcu_head(&hctx->rcu_sync->head);
+	}
+}
+EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_async_wait);
+
 /**
  * blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished
  * @q: request queue.
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 23230c1d031e..7213ce56bb31 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -5,6 +5,7 @@
 #include <linux/blkdev.h>
 #include <linux/sbitmap.h>
 #include <linux/srcu.h>
+#include <linux/rcupdate_wait.h>
 
 struct blk_mq_tags;
 struct blk_flush_queue;
@@ -170,6 +171,7 @@ struct blk_mq_hw_ctx {
 	 */
 	struct list_head	hctx_list;
 
+	struct rcu_synchronize	*rcu_sync;
 	/**
 	 * @srcu: Sleepable RCU. Use as lock when type of the hardware queue is
 	 * blocking (BLK_MQ_F_BLOCKING). Must be the last member - see also
@@ -532,6 +534,8 @@ int blk_mq_map_queues(struct blk_mq_queue_map *qmap);
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
 
 void blk_mq_quiesce_queue_nowait(struct request_queue *q);
+void blk_mq_quiesce_queue_async(struct request_queue *q);
+void blk_mq_quiesce_queue_async_wait(struct request_queue *q);
 
 unsigned int blk_mq_rq_cpu(struct request *rq);
 
-- 
2.25.1


_______________________________________________
Linux-nvme mailing list
Linux-nvme@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-nvme

  reply index

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-07-27 22:07 [PATCH v4 0/2] improve quiesce time for large amount of namespaces Sagi Grimberg
2020-07-27 22:07 ` Sagi Grimberg [this message]
2020-07-27 22:13   ` [PATCH v4 1/2] blk-mq: add async quiesce interface Jens Axboe
2020-07-27 22:37     ` Sagi Grimberg
2020-07-27 22:07 ` [PATCH v4 2/2] nvme: improve quiesce time for large amount of namespaces Sagi Grimberg

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=20200727220717.278116-2-sagi@grimberg.me \
    --to=sagi@grimberg.me \
    --cc=axboe@kernel.dk \
    --cc=hch@lst.de \
    --cc=kbusch@kernel.org \
    --cc=lengchao@huawei.com \
    --cc=linux-block@vger.kernel.org \
    --cc=linux-nvme@lists.infradead.org \
    --cc=mlin@kernel.org \
    /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

Linux-NVME Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-nvme/0 linux-nvme/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-nvme linux-nvme/ https://lore.kernel.org/linux-nvme \
		linux-nvme@lists.infradead.org
	public-inbox-index linux-nvme

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.infradead.lists.linux-nvme


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git