Make blkdev_issue_discard() submit aligned discard requests
Subsystems (3)
v2 cover Make blkdev_issue_discard() submit aligned discard requests
Users of blkdev_issue_discard(), e.g. blk_ioctl_discard(), expect that this function generates discard request(s) that satisfy block driver alignment requirements. Hence modify blk_bio_discard_split() such that the submitted discard requests are aligned.
Changes compared to v1:
- Moved the code to split discard requests from blkdev_issue_discard() into blk_bio_discard_split().
The patches in this series are:
0001-block-Introduce-blk_round_sect_down.patch 0002-block-Introduce-bio_add_zero_pages.patch 0003-block-Optimize-__blkdev_issue_zeroout.patch 0004-block-Make-blkdev_issue_discard-submit-aligned-disca.patch 0005-brd-Split-bio-if-needed.patch 0006-brd-Accept-non-aligned-discard-requests-with-size-ze.patch
PATCH v2 1/6 block: Introduce blk_round_sect_down()
Move the code for rounding down a sector into a new function.
--- block/blk-lib.c | 32 +++++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-)
block/blk-lib.c +25 -7
@@ -26,6 +26,26 @@ static void bio_batch_end_io(struct bio *bio)bio_put (bio); } +/* +* Return the largest number that is less than or equal to @s and for which +* the remainder of the division by @granularity is @alignment. +*/ +static sector_t blk_round_sect_down (sector_t s,u32 granularity,u32 alignment) +{ +sector_t tmp = s, res = s; +u32 remainder; + +WARN_ON_ONCE (alignment >= granularity); + + remainder =sector_div (tmp, granularity); +if (remainder == alignment) +return res; + res -= remainder - alignment; +if (remainder < alignment) + res -= granularity; +return min (res, s); +} +/** * blkdev_issue_discard - queue a discard * @bdev: blockdev to issue discard for
@@ -73,7 +93,7 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,blk_start_plug (&plug);while (nr_sects) {unsigned int req_sects; -sector_t end_sect, tmp; +sector_t end_sect; bio =bio_alloc (gfp_mask,1 );if (!bio) {
@@ -89,12 +109,10 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector,* misaligned, stop the discard at the previous aligned sector. */ end_sect = sector + req_sects; - tmp = end_sect; -if (req_sects < nr_sects && -sector_div (tmp, granularity) != alignment) { - end_sect = end_sect - alignment; -sector_div (end_sect, granularity); - end_sect = end_sect * granularity + alignment; +if (req_sects < nr_sects) { + end_sect =blk_round_sect_down (end_sect, granularity, + alignment); +WARN_ON_ONCE (end_sect < sector); req_sects = end_sect - sector; }
Signature · 1 line
2.1.4
PATCH v2 2/6 block: Introduce bio_add_zero_pages()
In reply to Bart Van AsscheMove the code for adding one or more zero pages into a new function.
--- block/blk-lib.c | 30 +++++++++++++++++++----------- 1 file changed, 19 insertions(+), 11 deletions(-)
block/blk-lib.c +19 -11
@@ -219,6 +219,22 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, }EXPORT_SYMBOL (blkdev_issue_write_same); +static void bio_add_zero_pages (struct bio *bio,sector_t nr_sects) +{ +unsigned sz; +int ret; + +/* Avoid that bi_size overflows */ + nr_sects =min_t (sector_t, nr_sects,UINT_MAX >>9 ); + +for (; nr_sects !=0 ; nr_sects -= ret >>9 ) { + sz =min_t (unsigned,PAGE_SIZE >>9 , nr_sects) <<9 ; + ret =bio_add_page (bio,ZERO_PAGE (0 ), sz,0 ); +if (ret < sz) +break ; + } +} +/** * blkdev_issue_zeroout - generate number of zero filed write bios * @bdev: blockdev to issue
@@ -236,7 +252,6 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,int ret;struct bio *bio;struct bio_batch bb; -unsigned int sz;DECLARE_COMPLETION_ONSTACK (wait);atomic_set (&bb.done,1 );
@@ -256,16 +271,9 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, bio->bi_bdev = bdev; bio->bi_end_io = bio_batch_end_io; bio->bi_private = &bb; - -while (nr_sects !=0 ) { - sz =min ((sector_t )PAGE_SIZE >>9 , nr_sects); - ret =bio_add_page (bio,ZERO_PAGE (0 ), sz <<9 ,0 ); - nr_sects -= ret >>9 ; - sector += ret >>9 ; -if (ret < (sz <<9 )) -break ; - } - ret =0 ; +bio_add_zero_pages (bio, nr_sects); + nr_sects -= bio->bi_iter.bi_size >>9 ; + sector += bio->bi_iter.bi_size >>9 ;atomic_inc (&bb.done);submit_bio (WRITE , bio); }
Signature · 1 line
2.1.4
PATCH v2 3/6 block: Optimize __blkdev_issue_zeroout()
In reply to Bart Van AsscheAvoid to confuse SCSI target software by ensuring that the WRITE SAME data buffer length matches the block size.
--- block/blk-lib.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-)
block/blk-lib.c +8 -5
@@ -249,7 +249,9 @@ static void bio_add_zero_pages(struct bio *bio, sector_t nr_sects)static int __blkdev_issue_zeroout (struct block_device *bdev,sector_t sector,sector_t nr_sects,gfp_t gfp_mask) { -int ret; +int ret =0 ; +struct request_queue *q =bdev_get_queue (bdev); +unsigned req_sects;struct bio *bio;struct bio_batch bb;DECLARE_COMPLETION_ONSTACK (wait);
@@ -258,7 +260,6 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, bb.error =0 ; bb.wait = &wait; - ret =0 ;while (nr_sects !=0 ) { bio =bio_alloc (gfp_mask,min (nr_sects, (sector_t )BIO_MAX_PAGES ));
@@ -271,9 +272,11 @@ static int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, bio->bi_bdev = bdev; bio->bi_end_io = bio_batch_end_io; bio->bi_private = &bb; -bio_add_zero_pages (bio, nr_sects); - nr_sects -= bio->bi_iter.bi_size >>9 ; - sector += bio->bi_iter.bi_size >>9 ; +bio_add_zero_pages (bio, q->limits.logical_block_size); + req_sects =min_t (sector_t, nr_sects,UINT_MAX >>9 ); + bio->bi_iter.bi_size = req_sects <<9 ; + nr_sects -= req_sects; + sector += req_sects;atomic_inc (&bb.done);submit_bio (WRITE , bio); }
Signature · 1 line
2.1.4
PATCH v2 4/6 block: Make blkdev_issue_discard() submit aligned discard requests
In reply to Bart Van AsscheSplit discard requests as follows:
* If the start sector is not aligned, an initial write request up to the first aligned sector.
* A discard request from the first aligned sector in the range up to the last aligned sector in the discarded range.
* If the end sector is not aligned, a final write request from the last aligned sector up to the end.
Note: if the start and/or end sectors are not aligned and if the range is small enough the discard request will be submitted with bi_size == 0.
--- block/blk-lib.c | 4 ++-- block/blk-merge.c | 55 ++++++++++++++++++++++++++++++------------------------- block/blk.h | 3 +++ 3 files changed, 35 insertions(+), 27 deletions(-)
block/blk-lib.c +2 -2
@@ -30,7 +30,7 @@ static void bio_batch_end_io(struct bio *bio)* Return the largest number that is less than or equal to @s and for which * the remainder of the division by @granularity is @alignment. */ -static sector_t blk_round_sect_down (sector_t s,u32 granularity,u32 alignment) +sector_t blk_round_sect_down (sector_t s,u32 granularity,u32 alignment) {sector_t tmp = s, res = s;u32 remainder;
@@ -219,7 +219,7 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, }EXPORT_SYMBOL (blkdev_issue_write_same); -static void bio_add_zero_pages (struct bio *bio,sector_t nr_sects) +void bio_add_zero_pages (struct bio *bio,sector_t nr_sects) {unsigned sz;int ret;
block/blk-merge.c +30 -25
72 lines not on this page · raw message
block/blk.h +3 -0
@@ -36,6 +36,9 @@ extern struct kmem_cache *request_cachep;extern struct kobj_type blk_queue_ktype;extern struct ida blk_queue_ida; +sector_t blk_round_sect_down (sector_t s,u32 granularity,u32 alignment); +void bio_add_zero_pages (struct bio *bio,sector_t nr_sects); +static inline struct blk_flush_queue *blk_get_flush_queue (struct request_queue *q,struct blk_mq_ctx *ctx) {
Signature · 1 line
2.1.4
PATCH v2 5/6 brd: Split bio if needed
In reply to Bart Van AsscheIf a bio is submitted to the brd driver that does not satisfy the requirements of this driver, split the bio.
--- block/blk-merge.c | 2 +- drivers/block/brd.c | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-)
block/blk-merge.c +1 -1
@@ -39,7 +39,7 @@ static struct bio *blk_bio_discard_split(struct request_queue *q,if (end == end_r &&bio_sectors (bio) == end_r - start)return NULL ;return bio_split (bio, end_r - start,GFP_NOIO , bs); - }else if (q->limits.discard_zeroes_data) { + }else if (q->limits.discard_zeroes_data && start < end) { end =min (end, start_r + granularity); wr =bio_alloc_bioset (GFP_NOIO , end - start, bs);if (WARN_ON_ONCE (!wr))
drivers/block/brd.c +2 -0
@@ -336,6 +336,8 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)if (bio_end_sector (bio) >get_capacity (bdev->bd_disk)) goto io_error; +blk_queue_split (q, &bio, q->bio_split); +if (unlikely (bio->bi_rw &REQ_DISCARD )) {if (sector & ((PAGE_SIZE >>SECTOR_SHIFT ) -1 ) || bio->bi_iter.bi_size & ~PAGE_MASK )
Signature · 1 line
2.1.4
PATCH v2 6/6 brd: Accept non-aligned discard requests with size zero
In reply to Bart Van Assche--- drivers/block/brd.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)
drivers/block/brd.c +3 -2
@@ -339,8 +339,9 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)blk_queue_split (q, &bio, q->bio_split);if (unlikely (bio->bi_rw &REQ_DISCARD )) { -if (sector & ((PAGE_SIZE >>SECTOR_SHIFT ) -1 ) || - bio->bi_iter.bi_size & ~PAGE_MASK ) +if (bio->bi_iter.bi_size && + (sector & ((PAGE_SIZE >>SECTOR_SHIFT ) -1 ) || + bio->bi_iter.bi_size & ~PAGE_MASK )) goto io_error;discard_from_brd (brd, sector, bio->bi_iter.bi_size); goto out;
Signature · 1 line
2.1.4
Re: [PATCH 3/6] block: Optimize __blkdev_issue_zeroout()
In reply to Bart Van AsscheQuoted 2 lines · Bart Van Assche
Avoid to confuse SCSI target software by ensuring that the WRITE SAME data buffer length matches the block size.
(replying to my own e-mail)
Please ignore this patch - it is wrong. Apparently my jet lag has not yet completely disappeared ...
Bart.
Re: [PATCH 1/6] block: Introduce blk_round_sect_down()
In reply to Bart Van AsscheLooks good,
Re: [PATCH 2/6] block: Introduce bio_add_zero_pages()
In reply to Bart Van AsscheLooks good,