diff options
86 files changed, 5640 insertions, 2856 deletions
diff --git a/Documentation/block/null_blk.rst b/Documentation/block/null_blk.rst index edbbab2f12f8..4dd78f24d10a 100644 --- a/Documentation/block/null_blk.rst +++ b/Documentation/block/null_blk.rst @@ -72,6 +72,28 @@ submit_queues=[1..nr_cpus]: Default: 1 hw_queue_depth=[0..qdepth]: Default: 64 The hardware queue depth of the device. +memory_backed=[0/1]: Default: 0 + Whether or not to use a memory buffer to respond to IO requests + + = ============================================= + 0 Transfer no data in response to IO requests + 1 Use a memory buffer to respond to IO requests + = ============================================= + +discard=[0/1]: Default: 0 + Support discard operations (requires memory-backed null_blk device). + + = ===================================== + 0 Do not support discard operations + 1 Enable support for discard operations + = ===================================== + +cache_size=[Size in MB]: Default: 0 + Cache size in MB for memory-backed device. + +mbps=[Maximum bandwidth in MB/s]: Default: 0 (no limit) + Bandwidth limit for device performance. + Multi-queue specific parameters ------------------------------- diff --git a/MAINTAINERS b/MAINTAINERS index 1c42103d889a..a6c5c29e5a0b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -14507,7 +14507,8 @@ S: Supported W: http://git.infradead.org/nvme.git T: git://git.infradead.org/nvme.git F: drivers/nvme/host/ -F: include/linux/nvme.h +F: drivers/nvme/common/ +F: include/linux/nvme* F: include/uapi/linux/nvme_ioctl.h NVM EXPRESS FC TRANSPORT DRIVERS @@ -18838,6 +18839,7 @@ SOFTWARE RAID (Multiple Disks) SUPPORT M: Song Liu <song@kernel.org> L: linux-raid@vger.kernel.org S: Supported +Q: https://patchwork.kernel.org/project/linux-raid/list/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/song/md.git F: drivers/md/Kconfig F: drivers/md/Makefile diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 32929c89ba8a..3f5685c00e36 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -134,7 +134,7 @@ int bio_integrity_add_page(struct bio *bio, struct page *page, iv = bip->bip_vec + bip->bip_vcnt; if (bip->bip_vcnt && - bvec_gap_to_prev(bdev_get_queue(bio->bi_bdev), + bvec_gap_to_prev(&bdev_get_queue(bio->bi_bdev)->limits, &bip->bip_vec[bip->bip_vcnt - 1], offset)) return 0; diff --git a/block/bio.c b/block/bio.c index 6f9f883f9a65..d6eb90d9b20b 100644 --- a/block/bio.c +++ b/block/bio.c @@ -965,7 +965,7 @@ int bio_add_hw_page(struct request_queue *q, struct bio *bio, * would create a gap, disallow it. */ bvec = &bio->bi_io_vec[bio->bi_vcnt - 1]; - if (bvec_gap_to_prev(q, bvec, offset)) + if (bvec_gap_to_prev(&q->limits, bvec, offset)) return 0; } @@ -1151,22 +1151,12 @@ void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter) bio_set_flag(bio, BIO_CLONED); } -static void bio_put_pages(struct page **pages, size_t size, size_t off) -{ - size_t i, nr = DIV_ROUND_UP(size + (off & ~PAGE_MASK), PAGE_SIZE); - - for (i = 0; i < nr; i++) - put_page(pages[i]); -} - static int bio_iov_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { bool same_page = false; if (!__bio_try_merge_page(bio, page, len, offset, &same_page)) { - if (WARN_ON_ONCE(bio_full(bio, len))) - return -EINVAL; __bio_add_page(bio, page, len, offset); return 0; } @@ -1209,8 +1199,9 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; struct page **pages = (struct page **)bv; ssize_t size, left; - unsigned len, i; + unsigned len, i = 0; size_t offset; + int ret = 0; /* * Move page array up in the allocated memory for the bio vecs as far as @@ -1227,32 +1218,40 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) * result to ensure the bio's total size is correct. The remainder of * the iov data will be picked up in the next bio iteration. */ - size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset); - if (size > 0) + size = iov_iter_get_pages(iter, pages, UINT_MAX - bio->bi_iter.bi_size, + nr_pages, &offset); + if (size > 0) { + nr_pages = DIV_ROUND_UP(offset + size, PAGE_SIZE); size = ALIGN_DOWN(size, bdev_logical_block_size(bio->bi_bdev)); - if (unlikely(size <= 0)) - return size ? size : -EFAULT; + } else + nr_pages = 0; + + if (unlikely(size <= 0)) { + ret = size ? size : -EFAULT; + goto out; + } for (left = size, i = 0; left > 0; left -= len, i++) { struct page *page = pages[i]; - int ret; len = min_t(size_t, PAGE_SIZE - offset, left); - if (bio_op(bio) == REQ_OP_ZONE_APPEND) + if (bio_op(bio) == REQ_OP_ZONE_APPEND) { ret = bio_iov_add_zone_append_page(bio, page, len, offset); - else - ret = bio_iov_add_page(bio, page, len, offset); + if (ret) + break; + } else + bio_iov_add_page(bio, page, len, offset); - if (ret) { - bio_put_pages(pages + i, left, offset); - return ret; - } offset = 0; } - iov_iter_advance(iter, size); - return 0; + iov_iter_advance(iter, size - left); +out: + while (i < nr_pages) + put_page(pages[i++]); + + return ret; } /** diff --git a/block/blk-core.c b/block/blk-core.c index 3d286a256d3d..a0d1104c5590 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -377,7 +377,6 @@ static void blk_timeout_work(struct work_struct *work) struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu) { struct request_queue *q; - int ret; q = kmem_cache_alloc_node(blk_get_queue_kmem_cache(alloc_srcu), GFP_KERNEL | __GFP_ZERO, node_id); @@ -396,13 +395,9 @@ struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu) if (q->id < 0) goto fail_srcu; - ret = bioset_init(&q->bio_split, BIO_POOL_SIZE, 0, 0); - if (ret) - goto fail_id; - q->stats = blk_alloc_queue_stats(); if (!q->stats) - goto fail_split; + goto fail_id; q->node = node_id; @@ -439,8 +434,6 @@ struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu) fail_stats: blk_free_queue_stats(q->stats); -fail_split: - bioset_exit(&q->bio_split); fail_id: ida_free(&blk_queue_ida, q->id); fail_srcu: diff --git a/block/blk-merge.c b/block/blk-merge.c index 4c8a699754c9..ff04e9290715 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -82,7 +82,7 @@ static inline bool bio_will_gap(struct request_queue *q, bio_get_first_bvec(next, &nb); if (biovec_phys_mergeable(q, &pb, &nb)) return false; - return __bvec_gap_to_prev(q, &pb, nb.bv_offset); + return __bvec_gap_to_prev(&q->limits, &pb, nb.bv_offset); } static inline bool req_gap_back_merge(struct request *req, struct bio *bio) @@ -95,23 +95,30 @@ static inline bool req_gap_front_merge(struct request *req, struct bio *bio) return bio_will_gap(req->q, NULL, bio, req->bio); } -static struct bio *blk_bio_discard_split(struct request_queue *q, - struct bio *bio, - struct bio_set *bs, - unsigned *nsegs) +/* + * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size + * is defined as 'unsigned int', meantime it has to be aligned to with the + * logical block size, which is the minimum accepted unit by hardware. + */ +static unsigned int bio_allowed_max_sectors(struct queue_limits *lim) +{ + return round_down(UINT_MAX, lim->logical_block_size) >> SECTOR_SHIFT; +} + +static struct bio *bio_split_discard(struct bio *bio, struct queue_limits *lim, + unsigned *nsegs, struct bio_set *bs) { unsigned int max_discard_sectors, granularity; - int alignment; sector_t tmp; unsigned split_sectors; *nsegs = 1; /* Zero-sector (unknown) and one-sector granularities are the same. */ - granularity = max(q->limits.discard_granularity >> 9, 1U); + granularity = max(lim->discard_granularity >> 9, 1U); - max_discard_sectors = min(q->limits.max_discard_sectors, - bio_allowed_max_sectors(q)); + max_discard_sectors = + min(lim->max_discard_sectors, bio_allowed_max_sectors(lim)); max_discard_sectors -= max_discard_sectors % granularity; if (unlikely(!max_discard_sectors)) { @@ -128,9 +135,8 @@ static struct bio *blk_bio_discard_split(struct request_queue *q, * If the next starting sector would be misaligned, stop the discard at * the previous aligned sector. */ - alignment = (q->limits.discard_alignment >> 9) % granularity; - - tmp = bio->bi_iter.bi_sector + split_sectors - alignment; + tmp = bio->bi_iter.bi_sector + split_sectors - + ((lim->discard_alignment >> 9) % granularity); tmp = sector_div(tmp, granularity); if (split_sectors > tmp) @@ -139,18 +145,15 @@ static struct bio *blk_bio_discard_split(struct request_queue *q, return bio_split(bio, split_sectors, GFP_NOIO, bs); } -static struct bio *blk_bio_write_zeroes_split(struct request_queue *q, - struct bio *bio, struct bio_set *bs, unsigned *nsegs) +static struct bio *bio_split_write_zeroes(struct bio *bio, + struct queue_limits *lim, unsigned *nsegs, struct bio_set *bs) { *nsegs = 0; - - if (!q->limits.max_write_zeroes_sectors) + if (!lim->max_write_zeroes_sectors) return NULL; - - if (bio_sectors(bio) <= q->limits.max_write_zeroes_sectors) + if (bio_sectors(bio) <= lim->max_write_zeroes_sectors) return NULL; - - return bio_split(bio, q->limits.max_write_zeroes_sectors, GFP_NOIO, bs); + return bio_split(bio, lim->max_write_zeroes_sectors, GFP_NOIO, bs); } /* @@ -161,17 +164,17 @@ static struct bio *blk_bio_write_zeroes_split(struct request_queue *q, * requests that are submitted to a block device if the start of a bio is not * aligned to a physical block boundary. */ -static inline unsigned get_max_io_size(struct request_queue *q, - struct bio *bio) +static inline unsigned get_max_io_size(struct bio *bio, + struct queue_limits *lim) { - unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT; - unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT; - unsigned max_sectors = queue_max_sectors(q), start, end; + unsigned pbs = lim->physical_block_size >> SECTOR_SHIFT; + unsigned lbs = lim->logical_block_size >> SECTOR_SHIFT; + unsigned max_sectors = lim->max_sectors, start, end; - if (q->limits.chunk_sectors) { + if (lim->chunk_sectors) { max_sectors = min(max_sectors, blk_chunk_sectors_left(bio->bi_iter.bi_sector, - q->limits.chunk_sectors)); + lim->chunk_sectors)); } start = bio->bi_iter.bi_sector & (pbs - 1); @@ -181,11 +184,10 @@ static inline unsigned get_max_io_size(struct request_queue *q, return max_sectors & ~(lbs - 1); } -static inline unsigned get_max_segment_size(const struct request_queue *q, - struct page *start_page, - unsigned long offset) +static inline unsigned get_max_segment_size(struct queue_limits *lim, + struct page *start_page, unsigned long offset) { - unsigned long mask = queue_segment_boundary(q); + unsigned long mask = lim->seg_boundary_mask; offset = mask & (page_to_phys(start_page) + offset); @@ -194,12 +196,12 @@ static inline unsigned get_max_segment_size(const struct request_queue *q, * on 32bit arch, use queue's max segment size when that happens. */ return min_not_zero(mask - offset + 1, - (unsigned long)queue_max_segment_size(q)); + (unsigned long)lim->max_segment_size); } /** * bvec_split_segs - verify whether or not a bvec should be split in the middle - * @q: [in] request queue associated with the bio associated with @bv + * @lim: [in] queue limits to split based on * @bv: [in] bvec to examine * @nsegs: [in,out] Number of segments in the bio being built. Incremented * by the number of segments from @bv that may be appended to that @@ -217,10 +219,9 @@ static inline unsigned get_max_segment_size(const struct request_queue *q, * *@nsegs segments and *@sectors sectors would make that bio unacceptable for * the block driver. */ -static bool bvec_split_segs(const struct request_queue *q, - const struct bio_vec *bv, unsigned *nsegs, - unsigned *bytes, unsigned max_segs, - unsigned max_bytes) +static bool bvec_split_segs(struct queue_limits *lim, const struct bio_vec *bv, + unsigned *nsegs, unsigned *bytes, unsigned max_segs, + unsigned max_bytes) { unsigned max_len = min(max_bytes, UINT_MAX) - *bytes; unsigned len = min(bv->bv_len, max_len); @@ -228,7 +229,7 @@ static bool bvec_split_segs(const struct request_queue *q, unsigned seg_size = 0; while (len && *nsegs < max_segs) { - seg_size = get_max_segment_size(q, bv->bv_page, + seg_size = get_max_segment_size(lim, bv->bv_page, bv->bv_offset + total_len); seg_s |