Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Changheun Lee <nanich.lee@samsung.com>
To:     damien.lemoal@wdc.com, bvanassche@acm.org,
        Johannes.Thumshirn@wdc.com, asml.silence@gmail.com,
        axboe@kernel.dk, gregkh@linuxfoundation.org, hch@infradead.org,
        linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
        ming.lei@redhat.com, osandov@fb.com, patchwork-bot@kernel.org,
        tj@kernel.org, tom.leiming@gmail.com
Cc:     jisoo2146.oh@samsung.com, junho89.kim@samsung.com,
        mj0123.lee@samsung.com, seunghwan.hyun@samsung.com,
        sookwan7.kim@samsung.com, woosung2.lee@samsung.com,
        yt0928.kim@samsung.com, Changheun Lee <nanich.lee@samsung.com>
Subject: [PATCH v6 1/3] bio: limit bio max size
Date:   Mon, 12 Apr 2021 11:58:29 +0900
Message-Id: <20210412025831.31498-2-nanich.lee@samsung.com>
In-Reply-To: <20210412025831.31498-1-nanich.lee@samsung.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain; charset="utf-8"
CMS-TYPE: 101P
DLP-Filter: Pass
References: <20210412025831.31498-1-nanich.lee@samsung.com>
        <CGME20210412031616epcas1p4002efe42935c89c66b879f15a7446d7f@epcas1p4.samsung.com>
Precedence: bulk

bio size can grow up to 4GB when muli-page bvec is enabled.
but sometimes it would lead to inefficient behaviors.
in case of large chunk direct I/O, - 32MB chunk read in user space -
all pages for 32MB would be merged to a bio structure if the pages
physical addresses are contiguous. it makes some delay to submit
until merge complete. bio max size should be limited to a proper size.

When 32MB chunk read with direct I/O option is coming from userspace,
kernel behavior is below now in do_direct_IO() loop. it's timeline.

 | bio merge for 32MB. total 8,192 pages are merged.
 | total elapsed time is over 2ms.
 |------------------ ... ----------------------->|
                                                 | 8,192 pages merged a bio.
                                                 | at this time, first bio submit is done.
                                                 | 1 bio is split to 32 read request and issue.
                                                 |--------------->
                                                  |--------------->
                                                   |--------------->
                                                              ......
                                                                   |--------------->
                                                                    |--------------->|
                          total 19ms elapsed to complete 32MB read done from device. |

If bio max size is limited with 1MB, behavior is changed below.

 | bio merge for 1MB. 256 pages are merged for each bio.
 | total 32 bio will be made.
 | total elapsed time is over 2ms. it's same.
 | but, first bio submit timing is fast. about 100us.
 |--->|--->|--->|---> ... -->|--->|--->|--->|--->|
      | 256 pages merged a bio.
      | at this time, first bio submit is done.
      | and 1 read request is issued for 1 bio.
      |--------------->
           |--------------->
                |--------------->
                                      ......
                                                 |--------------->
                                                  |--------------->|
        total 17ms elapsed to complete 32MB read done from device. |

As a result, read request issue timing is faster if bio max size is limited.
Current kernel behavior with multipage bvec, super large bio can be created.
And it lead to delay first I/O request issue.

Signed-off-by: Changheun Lee <nanich.lee@samsung.com>
---
 block/bio.c            | 13 ++++++++++++-
 block/blk-settings.c   | 17 +++++++++++++++++
 include/linux/bio.h    |  2 +-
 include/linux/blkdev.h |  4 ++++
 4 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 50e579088aca..e4d6169106b6 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -255,6 +255,17 @@ void bio_init(struct bio *bio, struct bio_vec *table,
 }
 EXPORT_SYMBOL(bio_init);
 
+unsigned int bio_max_size(struct bio *bio)
+{
+	struct request_queue *q = bio->bi_disk->queue;
+
+	if (blk_queue_limit_bio_size(q))
+		return blk_queue_get_max_sectors(q, bio_op(bio))
+			<< SECTOR_SHIFT;
+
+	return UINT_MAX;
+}
+
 /**
  * bio_reset - reinitialize a bio
  * @bio:	bio to reset
@@ -866,7 +877,7 @@ bool __bio_try_merge_page(struct bio *bio, struct page *page,
 		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
 
 		if (page_is_mergeable(bv, page, len, off, same_page)) {
-			if (bio->bi_iter.bi_size > UINT_MAX - len) {
+			if (bio->bi_iter.bi_size > bio_max_size(bio) - len) {
 				*same_page = false;
 				return false;
 			}
diff --git a/block/blk-settings.c b/block/blk-settings.c
index b4aa2f37fab6..1d94b97cea4f 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -928,6 +928,23 @@ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
 }
 EXPORT_SYMBOL_GPL(blk_queue_set_zoned);
 
+/**
+ * blk_queue_set_limit_bio_size - set limit bio size flag
+ * @q:		the request queue for the device
+ * @limit:	limit bio size on(true), or off
+ *
+ * bio max size will be limited to queue max sectors size,
+ * if limit is true.
+ */
+void blk_queue_set_limit_bio_size(struct request_queue *q, bool limit)
+{
+	if (limit)
+		blk_queue_flag_set(QUEUE_FLAG_LIMIT_BIO_SIZE, q);
+	else
+		blk_queue_flag_clear(QUEUE_FLAG_LIMIT_BIO_SIZE, q);
+}
+EXPORT_SYMBOL_GPL(blk_queue_set_limit_bio_size);
+
 static int __init blk_settings_init(void)
 {
 	blk_max_low_pfn = max_low_pfn - 1;
diff --git a/include/linux/bio.h b/include/linux/bio.h
index d0246c92a6e8..830c784967c0 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -119,7 +119,7 @@ static inline bool bio_full(struct bio *bio, unsigned len)
 	if (bio->bi_vcnt >= bio->bi_max_vecs)
 		return true;
 
-	if (bio->bi_iter.bi_size > UINT_MAX - len)
+	if (bio->bi_iter.bi_size > bio_max_size(bio) - len)
 		return true;
 
 	return false;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 158aefae1030..c69a6ed7a189 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -617,6 +617,7 @@ struct request_queue {
 #define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
 #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_LIMIT_BIO_SIZE 30	/* limit bio size */
 
 #define QUEUE_FLAG_MQ_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_SAME_COMP) |		\
@@ -663,6 +664,8 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_fua(q)	test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags)
 #define blk_queue_registered(q)	test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
 #define blk_queue_nowait(q)	test_bit(QUEUE_FLAG_NOWAIT, &(q)->queue_flags)
+#define blk_queue_limit_bio_size(q)	\
+	test_bit(QUEUE_FLAG_LIMIT_BIO_SIZE, &(q)->queue_flags)
 
 extern void blk_set_pm_only(struct request_queue *q);
 extern void blk_clear_pm_only(struct request_queue *q);
@@ -1183,6 +1186,7 @@ extern void blk_queue_required_elevator_features(struct request_queue *q,
 						 unsigned int features);
 extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
 					      struct device *dev);
+extern void blk_queue_set_limit_bio_size(struct request_queue *q, bool limit);
 
 /*
  * Number of physical segments as sent to the device.
-- 
2.29.0