bio: limit bio max size

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>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20210503095203.29076-1-nanich.lee@samsung.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

2 files changed, 16 insertions, 2 deletions

diff --git a/block/bio.c b/block/bio.c
index 44205dfb6b60..221dc56ba22f 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -255,6 +255,13 @@ void bio_init(struct bio *bio, struct bio_vec *table,
 }
 EXPORT_SYMBOL(bio_init);
 
+unsigned int bio_max_size(struct bio *bio)
+{
+	struct block_device *bdev = bio->bi_bdev;
+
+	return bdev ? bdev->bd_disk->queue->limits.bio_max_bytes : UINT_MAX;
+}
+
 /**
  * bio_reset - reinitialize a bio
  * @bio:	bio to reset
@@ -866,7 +873,7 @@ 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;
 			}
@@ -995,6 +1002,7 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 {
 	unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt;
 	unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt;
+	unsigned int bytes_left = bio_max_size(bio) - bio->bi_iter.bi_size;
 	struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt;
 	struct page **pages = (struct page **)bv;
 	bool same_page = false;
@@ -1010,7 +1018,8 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter)
 	BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2);
 	pages += entries_left * (PAGE_PTRS_PER_BVEC - 1);
 
-	size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset);
+	size = iov_iter_get_pages(iter, pages, bytes_left, nr_pages,
+				  &offset);
 	if (unlikely(size <= 0))
 		return size ? size : -EFAULT;
 
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 9c009090c4b5..c646503e55d2 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -31,6 +31,7 @@ EXPORT_SYMBOL_GPL(blk_queue_rq_timeout);
  */
 void blk_set_default_limits(struct queue_limits *lim)
 {
+	lim->bio_max_bytes = UINT_MAX;
 	lim->max_segments = BLK_MAX_SEGMENTS;
 	lim->max_discard_segments = 1;
 	lim->max_integrity_segments = 0;
@@ -139,6 +140,10 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto
 				 limits->logical_block_size >> SECTOR_SHIFT);
 	limits->max_sectors = max_sectors;
 
+	if (check_shl_overflow(max_sectors, SECTOR_SHIFT,
+				&limits->bio_max_bytes))
+		limits->bio_max_bytes = UINT_MAX;
+
 	q->backing_dev_info->io_pages = max_sectors >> (PAGE_SHIFT - 9);
 }
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);