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 memory address is
continued phsycally. it makes some delay to submit until merge complete.
bio max size should be limited as a proper size.

When 32MB chunk read with direct I/O option is coming from userspace,
kernel behavior is below now. 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

@@ -284,9 +284,24 @@ void bio_init(struct bio *bio, struct bio_vec *table,
 
 	bio->bi_io_vec = table;
 	bio->bi_max_vecs = max_vecs;
+	bio->bi_max_size = UINT_MAX;
 }
 EXPORT_SYMBOL(bio_init);
 
+void bio_set_dev(struct bio *bio, struct block_device *bdev)
+{
+	if (bio->bi_disk != bdev->bd_disk)
+		bio_clear_flag(bio, BIO_THROTTLED);
+
+	bio->bi_disk = bdev->bd_disk;
+	bio->bi_partno = bdev->bd_partno;
+	bio->bi_max_size = blk_queue_get_max_sectors(bio->bi_disk->queue,
+			bio_op(bio)) << SECTOR_SHIFT;
+
+	bio_associate_blkg(bio);
+}
+EXPORT_SYMBOL(bio_set_dev);
+
 /**
  * bio_reset - reinitialize a bio
  * @bio:	bio to reset
@@ -877,7 +892,7 @@ 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->bi_max_size - len)
 				*same_page = false;
 				return false;
 			}

include/linux/bio.h

@@ -113,7 +113,7 @@ 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->bi_max_size - len)
 		return true;
 
 	return false;
@@ -482,20 +482,13 @@ extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *);
 extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int);
 extern unsigned int bvec_nr_vecs(unsigned short idx);
 extern const char *bio_devname(struct bio *bio, char *buffer);
-
-#define bio_set_dev(bio, bdev) 			\
-do {						\
-	if ((bio)->bi_disk != (bdev)->bd_disk)	\
-		bio_clear_flag(bio, BIO_THROTTLED);\
-	(bio)->bi_disk = (bdev)->bd_disk;	\
-	(bio)->bi_partno = (bdev)->bd_partno;	\
-	bio_associate_blkg(bio);		\
-} while (0)
+extern void bio_set_dev(struct bio *bio, struct block_device *bdev);
 
 #define bio_copy_dev(dst, src)			\
 do {						\
 	(dst)->bi_disk = (src)->bi_disk;	\
 	(dst)->bi_partno = (src)->bi_partno;	\
+	(dst)->bi_max_size = (src)->bi_max_size;\
 	bio_clone_blkg_association(dst, src);	\
 } while (0)
 

include/linux/blk_types.h

@@ -270,6 +270,7 @@ struct bio {
 	 */
 
 	unsigned short		bi_max_vecs;	/* max bvl_vecs we can hold */
+	unsigned int		bi_max_size;	/* max data size we can hold */
 
 	atomic_t		__bi_cnt;	/* pin count */