linux-block.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Ming Lei <ming.lei@redhat.com>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org, Ming Lei <ming.lei@redhat.com>,
	Bart Van Assche <bvanassche@acm.org>,
	Hannes Reinecke <hare@suse.com>, Christoph Hellwig <hch@lst.de>,
	Thomas Gleixner <tglx@linutronix.de>,
	John Garry <john.garry@huawei.com>
Subject: [PATCH 5/6] blk-mq: disable preempt during allocating request tag
Date: Fri, 15 May 2020 09:41:52 +0800	[thread overview]
Message-ID: <20200515014153.2403464-6-ming.lei@redhat.com> (raw)
In-Reply-To: <20200515014153.2403464-1-ming.lei@redhat.com>

Disable preempt for a little while during allocating request tag, so
request's tag(internal tag) is always allocated on the cpu of data->ctx,
prepare for improving to handle cpu hotplug during allocating request.

In the following patch, hctx->state will be checked to see if it becomes
inactive which is always set on the last CPU of hctx->cpumask.

Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: John Garry <john.garry@huawei.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
---
 block/blk-mq-tag.c | 4 ++++
 block/blk-mq.c     | 4 ++++
 block/blk-mq.h     | 1 +
 3 files changed, 9 insertions(+)

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index c27c6dfc7d36..0ae79ca6e2da 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -152,11 +152,15 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data)
 		if (tag != -1)
 			break;
 
+		if (data->preempt_disabled)
+			preempt_enable();
 		bt_prev = bt;
 		io_schedule();
 
 		sbitmap_finish_wait(bt, ws, &wait);
 
+		if (data->preempt_disabled)
+			preempt_disable();
 		data->ctx = blk_mq_get_ctx(data->q);
 		data->hctx = blk_mq_map_queue(data->q, data->cmd_flags,
 						data->ctx);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 151b63b1f88b..18999198a37f 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -365,6 +365,9 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 	data->q = q;
 
 	WARN_ON_ONCE(data->ctx || data->hctx);
+
+	preempt_disable();
+	data->preempt_disabled = true;
 	data->ctx = blk_mq_get_ctx(q);
 	data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx);
 	if (data->cmd_flags & REQ_NOWAIT)
@@ -387,6 +390,7 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 	}
 
 	tag = blk_mq_get_tag(data);
+	preempt_enable();
 	if (tag == BLK_MQ_TAG_FAIL) {
 		data->ctx = NULL;
 		data->hctx = NULL;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 10bfdfb494fa..5ebc8d8d5a54 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -152,6 +152,7 @@ struct blk_mq_alloc_data {
 	blk_mq_req_flags_t flags;
 	unsigned int shallow_depth;
 	unsigned int cmd_flags;
+	bool preempt_disabled;
 
 	/* input & output parameter */
 	struct blk_mq_ctx *ctx;
-- 
2.25.2


  parent reply	other threads:[~2020-05-15  1:42 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-05-15  1:41 [PATCH 0/6] blk-mq: improvement CPU hotplug(simplified version) Ming Lei
2020-05-15  1:41 ` [PATCH 1/6] blk-mq: allocate request on cpu in hctx->cpumask for blk_mq_alloc_request_hctx Ming Lei
2020-05-15 15:32   ` Christoph Hellwig
2020-05-15  1:41 ` [PATCH 2/6] blk-mq: set data->ctx and data->hctx explicitly in blk_mq_get_request Ming Lei
2020-05-15  1:41 ` [PATCH 3/6] blk-mq: add blk_mq_all_tag_iter Ming Lei
2020-05-15  1:41 ` [PATCH 4/6] blk-mq: prepare for draining IO when hctx's all CPUs are offline Ming Lei
2020-05-15  1:41 ` Ming Lei [this message]
2020-05-15 15:38   ` [PATCH 5/6] blk-mq: disable preempt during allocating request tag Christoph Hellwig
2020-05-15 16:10     ` Christoph Hellwig
2020-05-15  1:41 ` [PATCH 6/6] blk-mq: stop to allocate new requst and drain request before hctx becomes inactive Ming Lei
2020-05-15  3:55   ` Bart Van Assche
2020-05-15  5:20     ` Ming Lei
2020-05-15 15:45 ` [PATCH 0/6] blk-mq: improvement CPU hotplug(simplified version) Christoph Hellwig
2020-05-16 12:35 ` Christoph Hellwig
2020-05-17  4:08   ` Ming Lei
2020-05-17  7:08     ` Christoph Hellwig
2020-05-18  4:07       ` Ming Lei

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=20200515014153.2403464-6-ming.lei@redhat.com \
    --to=ming.lei@redhat.com \
    --cc=axboe@kernel.dk \
    --cc=bvanassche@acm.org \
    --cc=hare@suse.com \
    --cc=hch@lst.de \
    --cc=john.garry@huawei.com \
    --cc=linux-block@vger.kernel.org \
    --cc=tglx@linutronix.de \
    /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;
as well as URLs for NNTP newsgroup(s).