Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
From:   Yu Kuai <yukuai3@huawei.com>
To:     <axboe@kernel.dk>, <yukuai3@huawei.com>,
        <andriy.shevchenko@linux.intel.com>, <john.garry@huawei.com>,
        <ming.lei@redhat.com>
CC:     <linux-block@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
        <yi.zhang@huawei.com>
Subject: [PATCH -next RFC v2 6/8] blk-mq: force tag preemption for split bios
Date:   Fri, 8 Apr 2022 15:39:14 +0800
Message-ID: <20220408073916.1428590-7-yukuai3@huawei.com>
In-Reply-To: <20220408073916.1428590-1-yukuai3@huawei.com>
References: <20220408073916.1428590-1-yukuai3@huawei.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 7BIT
Content-Type:   text/plain; charset=US-ASCII
Precedence: bulk

For HDD, sequential io is much faster than random io, thus it's better
to issue split io continuously. However, this is broken when tag preemption
is disabled, because wakers can only get one tag each time.

Thus tag preemption should be disabled for split bios, specifically the
first bio won't preempt tag, and following split bios will preempt tag.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 block/blk-merge.c         | 9 ++++++++-
 block/blk-mq.c            | 1 +
 include/linux/blk_types.h | 4 ++++
 3 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 7771dacc99cb..cab6ca681513 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -343,12 +343,19 @@ void __blk_queue_split(struct request_queue *q, struct bio **bio,
 
 	if (split) {
 		/* there isn't chance to merge the splitted bio */
-		split->bi_opf |= REQ_NOMERGE;
+		split->bi_opf |= (REQ_NOMERGE | REQ_SPLIT);
+		if ((*bio)->bi_opf & REQ_SPLIT)
+			split->bi_opf |= REQ_PREEMPT;
+		else
+			(*bio)->bi_opf |= REQ_SPLIT;
 
 		bio_chain(split, *bio);
 		trace_block_split(split, (*bio)->bi_iter.bi_sector);
 		submit_bio_noacct(*bio);
 		*bio = split;
+	} else {
+		if ((*bio)->bi_opf & REQ_SPLIT)
+			(*bio)->bi_opf |= REQ_PREEMPT;
 	}
 }
 
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ed3ed86f7dd2..909420c5186c 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2737,6 +2737,7 @@ static struct request *blk_mq_get_new_requests(struct request_queue *q,
 		.q		= q,
 		.nr_tags	= 1,
 		.cmd_flags	= bio->bi_opf,
+		.preemption	= (bio->bi_opf & REQ_PREEMPT),
 	};
 	struct request *rq;
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index c62274466e72..6b56e271f926 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -418,6 +418,8 @@ enum req_flag_bits {
 	/* for driver use */
 	__REQ_DRV,
 	__REQ_SWAP,		/* swapping request. */
+	__REQ_SPLIT,
+	__REQ_PREEMPT,
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -443,6 +445,8 @@ enum req_flag_bits {
 
 #define REQ_DRV			(1ULL << __REQ_DRV)
 #define REQ_SWAP		(1ULL << __REQ_SWAP)
+#define REQ_SPLIT		(1ULL << __REQ_SPLIT)
+#define REQ_PREEMPT		(1ULL << __REQ_PREEMPT)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
-- 
2.31.1