From df376b2ed51a2777c3398e038992f62523c0f932 Mon Sep 17 00:00:00 2001 From: Johannes Thumshirn Date: Wed, 7 Nov 2018 14:58:14 +0100 Subject: block: respect virtual boundary mask in bvecs With drivers that are settting a virtual boundary constrain, we are seeing a lot of bio splitting and smaller I/Os being submitted to the driver. This happens because the bio gap detection code does not account cases where PAGE_SIZE - 1 is bigger than queue_virt_boundary() and thus will split the bio unnecessarily. Cc: Jan Kara Cc: Bart Van Assche Cc: Ming Lei Reviewed-by: Sagi Grimberg Signed-off-by: Johannes Thumshirn Acked-by: Keith Busch Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-merge.c | 2 +- block/blk.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'block') diff --git a/block/blk-merge.c b/block/blk-merge.c index 6b5ad275ed56..208658a901c6 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -46,7 +46,7 @@ static inline bool bio_will_gap(struct request_queue *q, bio_get_first_bvec(prev_rq->bio, &pb); else bio_get_first_bvec(prev, &pb); - if (pb.bv_offset) + if (pb.bv_offset & queue_virt_boundary(q)) return true; /* diff --git a/block/blk.h b/block/blk.h index a1841b8ff129..c85e53f21cdd 100644 --- a/block/blk.h +++ b/block/blk.h @@ -169,7 +169,7 @@ static inline bool biovec_phys_mergeable(struct request_queue *q, static inline bool __bvec_gap_to_prev(struct request_queue *q, struct bio_vec *bprv, unsigned int offset) { - return offset || + return (offset & queue_virt_boundary(q)) || ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); } -- cgit v1.2.3 From f3587d76da05f68098ddb1cb3c98cc6a9e8a402c Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Wed, 7 Nov 2018 07:37:45 -0700 Subject: block: Clear kernel memory before copying to user If the kernel allocates a bounce buffer for user read data, this memory needs to be cleared before copying it to the user, otherwise it may leak kernel memory to user space. Laurence Oberman Signed-off-by: Keith Busch Signed-off-by: Jens Axboe --- block/bio.c | 1 + 1 file changed, 1 insertion(+) (limited to 'block') diff --git a/block/bio.c b/block/bio.c index 4a5a036268fb..9a9c59067521 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1260,6 +1260,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q, if (ret) goto cleanup; } else { + zero_fill_bio(bio); iov_iter_advance(iter, bio->bi_iter.bi_size); } -- cgit v1.2.3 From 1adfc5e4136f5967d591c399aff95b3b035f16b7 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 29 Oct 2018 20:57:17 +0800 Subject: block: make sure discard bio is aligned with logical block size Obviously the created discard bio has to be aligned with logical block size. This patch introduces the helper of bio_allowed_max_sectors() for this purpose. Cc: stable@vger.kernel.org Cc: Mike Snitzer Cc: Christoph Hellwig Cc: Xiao Ni Cc: Mariusz Dabrowski Fixes: 744889b7cbb56a6 ("block: don't deal with discard limit in blkdev_issue_discard()") Fixes: a22c4d7e34402cc ("block: re-add discard_granularity and alignment checks") Reported-by: Rui Salvaterra Tested-by: Rui Salvaterra Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-lib.c | 3 +-- block/blk-merge.c | 3 ++- block/blk.h | 10 ++++++++++ 3 files changed, 13 insertions(+), 3 deletions(-) (limited to 'block') diff --git a/block/blk-lib.c b/block/blk-lib.c index 76f867ea9a9b..d56fd159d2e8 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -57,8 +57,7 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, if (!req_sects) goto fail; - if (req_sects > UINT_MAX >> 9) - req_sects = UINT_MAX >> 9; + req_sects = min(req_sects, bio_allowed_max_sectors(q)); end_sect = sector + req_sects; diff --git a/block/blk-merge.c b/block/blk-merge.c index 208658a901c6..e7696c47489a 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -90,7 +90,8 @@ static struct bio *blk_bio_discard_split(struct request_queue *q, /* Zero-sector (unknown) and one-sector granularities are the same. */ granularity = max(q->limits.discard_granularity >> 9, 1U); - max_discard_sectors = min(q->limits.max_discard_sectors, UINT_MAX >> 9); + max_discard_sectors = min(q->limits.max_discard_sectors, + bio_allowed_max_sectors(q)); max_discard_sectors -= max_discard_sectors % granularity; if (unlikely(!max_discard_sectors)) { diff --git a/block/blk.h b/block/blk.h index c85e53f21cdd..0089fefdf771 100644 --- a/block/blk.h +++ b/block/blk.h @@ -395,6 +395,16 @@ static inline unsigned long blk_rq_deadline(struct request *rq) return rq->__deadline & ~0x1UL; } +/* + * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size + * is defined as 'unsigned int', meantime it has to aligned to with logical + * block size which is the minimum accepted unit by hardware. + */ +static inline unsigned int bio_allowed_max_sectors(struct request_queue *q) +{ + return round_down(UINT_MAX, queue_logical_block_size(q)) >> 9; +} + /* * Internal io_context interface */ -- cgit v1.2.3 From ba5d73851e71847ba7f7f4c27a1a6e1f5ab91c79 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 29 Oct 2018 20:57:18 +0800 Subject: block: cleanup __blkdev_issue_discard() Cleanup __blkdev_issue_discard() a bit: - remove local variable of 'end_sect' - remove code block of 'fail' Cc: Mike Snitzer Cc: Christoph Hellwig Cc: Xiao Ni Cc: Mariusz Dabrowski Tested-by: Rui Salvaterra Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-lib.c | 23 ++++++----------------- 1 file changed, 6 insertions(+), 17 deletions(-) (limited to 'block') diff --git a/block/blk-lib.c b/block/blk-lib.c index d56fd159d2e8..d58d5d87dd88 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -51,15 +51,12 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, if ((sector | nr_sects) & bs_mask) return -EINVAL; - while (nr_sects) { - unsigned int req_sects = nr_sects; - sector_t end_sect; - - if (!req_sects) - goto fail; - req_sects = min(req_sects, bio_allowed_max_sectors(q)); + if (!nr_sects) + return -EINVAL; - end_sect = sector + req_sects; + while (nr_sects) { + unsigned int req_sects = min_t(unsigned int, nr_sects, + bio_allowed_max_sectors(q)); bio = blk_next_bio(bio, 0, gfp_mask); bio->bi_iter.bi_sector = sector; @@ -67,8 +64,8 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, bio_set_op_attrs(bio, op, 0); bio->bi_iter.bi_size = req_sects << 9; + sector += req_sects; nr_sects -= req_sects; - sector = end_sect; /* * We can loop for a long time in here, if someone does @@ -81,14 +78,6 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, *biop = bio; return 0; - -fail: - if (bio) { - submit_bio_wait(bio); - bio_put(bio); - } - *biop = NULL; - return -EOPNOTSUPP; } EXPORT_SYMBOL(__blkdev_issue_discard); -- cgit v1.2.3 From 34ffec60b27aa81d04e274e71e4c6ef740f75fc7 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 29 Oct 2018 20:57:19 +0800 Subject: block: make sure writesame bio is aligned with logical block size Obviously the created writesame bio has to be aligned with logical block size, and use bio_allowed_max_sectors() to retrieve this number. Cc: stable@vger.kernel.org Cc: Mike Snitzer Cc: Christoph Hellwig Cc: Xiao Ni Cc: Mariusz Dabrowski Fixes: b49a0871be31a745b2ef ("block: remove split code in blkdev_issue_{discard,write_same}") Tested-by: Rui Salvaterra Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-lib.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'block') diff --git a/block/blk-lib.c b/block/blk-lib.c index d58d5d87dd88..e8b3bb9bf375 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -149,7 +149,7 @@ static int __blkdev_issue_write_same(struct block_device *bdev, sector_t sector, return -EOPNOTSUPP; /* Ensure that max_write_same_sectors doesn't overflow bi_size */ - max_write_same_sectors = UINT_MAX >> 9; + max_write_same_sectors = bio_allowed_max_sectors(q); while (nr_sects) { bio = blk_next_bio(bio, 1, gfp_mask); -- cgit v1.2.3