diff options
Diffstat (limited to 'block/blk-merge.c')
-rw-r--r-- | block/blk-merge.c | 902 |
1 files changed, 606 insertions, 296 deletions
diff --git a/block/blk-merge.c b/block/blk-merge.c index 17713d7d98d5..65e75efa9bd3 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -6,11 +6,48 @@ #include <linux/module.h> #include <linux/bio.h> #include <linux/blkdev.h> +#include <linux/blk-integrity.h> #include <linux/scatterlist.h> +#include <linux/part_stat.h> +#include <linux/blk-cgroup.h> #include <trace/events/block.h> #include "blk.h" +#include "blk-mq-sched.h" +#include "blk-rq-qos.h" +#include "blk-throttle.h" + +static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) +{ + *bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); +} + +static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) +{ + struct bvec_iter iter = bio->bi_iter; + int idx; + + bio_get_first_bvec(bio, bv); + if (bv->bv_len == bio->bi_iter.bi_size) + return; /* this bio only has a single bvec */ + + bio_advance_iter(bio, &iter, iter.bi_size); + + if (!iter.bi_bvec_done) + idx = iter.bi_idx - 1; + else /* in the middle of bvec */ + idx = iter.bi_idx; + + *bv = bio->bi_io_vec[idx]; + + /* + * iter.bi_bvec_done records actual length of the last bvec + * if this bio ends in the middle of one io vector + */ + if (iter.bi_bvec_done) + bv->bv_len = iter.bi_bvec_done; +} static inline bool bio_will_gap(struct request_queue *q, struct request *prev_rq, struct bio *prev, struct bio *next) @@ -45,7 +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) @@ -58,23 +95,31 @@ 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(const struct queue_limits *lim) +{ + return round_down(UINT_MAX, lim->logical_block_size) >> SECTOR_SHIFT; +} + +static struct bio *bio_split_discard(struct bio *bio, + const 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)) { @@ -91,9 +136,8 @@ 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) @@ -102,253 +146,302 @@ 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, + const struct queue_limits *lim, + unsigned *nsegs, struct bio_set *bs) { - *nsegs = 1; - - if (!q->limits.max_write_zeroes_sectors) + *nsegs = 0; + 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); } -static struct bio *blk_bio_write_same_split(struct request_queue *q, - struct bio *bio, - struct bio_set *bs, - unsigned *nsegs) -{ - *nsegs = 1; - - if (!q->limits.max_write_same_sectors) - return NULL; - - if (bio_sectors(bio) <= q->limits.max_write_same_sectors) - return NULL; - - return bio_split(bio, q->limits.max_write_same_sectors, GFP_NOIO, bs); -} - -static inline unsigned get_max_io_size(struct request_queue *q, - struct bio *bio) +/* + * Return the maximum number of sectors from the start of a bio that may be + * submitted as a single request to a block device. If enough sectors remain, + * align the end to the physical block size. Otherwise align the end to the + * logical block size. This approach minimizes the number of non-aligned + * 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 bio *bio, + const struct queue_limits *lim) { - unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector); - unsigned mask = queue_logical_block_size(q) - 1; - - /* aligned to logical block size */ - sectors &= ~(mask >> 9); + 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 (lim->chunk_sectors) { + max_sectors = min(max_sectors, + blk_chunk_sectors_left(bio->bi_iter.bi_sector, + lim->chunk_sectors)); + } - return sectors; + start = bio->bi_iter.bi_sector & (pbs - 1); + end = (start + max_sectors) & ~(pbs - 1); + if (end > start) + return end - start; + return max_sectors & ~(lbs - 1); } -static unsigned get_max_segment_size(struct request_queue *q, - unsigned offset) +/** + * get_max_segment_size() - maximum number of bytes to add as a single segment + * @lim: Request queue limits. + * @start_page: See below. + * @offset: Offset from @start_page where to add a segment. + * + * Returns the maximum number of bytes that can be added as a single segment. + */ +static inline unsigned get_max_segment_size(const 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; - /* default segment boundary mask means no boundary limit */ - if (mask == BLK_SEG_BOUNDARY_MASK) - return queue_max_segment_size(q); + offset = mask & (page_to_phys(start_page) + offset); - return min_t(unsigned long, mask - (mask & offset) + 1, - queue_max_segment_size(q)); + /* + * Prevent an overflow if mask = ULONG_MAX and offset = 0 by adding 1 + * after having calculated the minimum. + */ + return min(mask - offset, (unsigned long)lim->max_segment_size - 1) + 1; } -/* - * Split the bvec @bv into segments, and update all kinds of - * variables. +/** + * bvec_split_segs - verify whether or not a bvec should be split in the middle + * @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 + * bio without exceeding @max_segs + * @bytes: [in,out] Number of bytes in the bio being built. Incremented + * by the number of bytes from @bv that may be appended to that + * bio without exceeding @max_bytes + * @max_segs: [in] upper bound for *@nsegs + * @max_bytes: [in] upper bound for *@bytes + * + * When splitting a bio, it can happen that a bvec is encountered that is too + * big to fit in a single segment and hence that it has to be split in the + * middle. This function verifies whether or not that should happen. The value + * %true is returned if and only if appending the entire @bv to a bio with + * *@nsegs segments and *@sectors sectors would make that bio unacceptable for + * the block driver. */ -static bool bvec_split_segs(struct request_queue *q, struct bio_vec *bv, - unsigned *nsegs, unsigned *sectors, unsigned max_segs) +static bool bvec_split_segs(const struct queue_limits *lim, + const struct bio_vec *bv, unsigned *nsegs, unsigned *bytes, + unsigned max_segs, unsigned max_bytes) { - unsigned len = bv->bv_len; + unsigned max_len = min(max_bytes, UINT_MAX) - *bytes; + unsigned len = min(bv->bv_len, max_len); unsigned total_len = 0; - unsigned new_nsegs = 0, seg_size = 0; + unsigned seg_size = 0; - /* - * Multi-page bvec may be too big to hold in one segment, so the - * current bvec has to be splitted as multiple segments. - */ - while (len && new_nsegs + *nsegs < max_segs) { - seg_size = get_max_segment_size(q, bv->bv_offset + total_len); + while (len && *nsegs < max_segs) { + seg_size = get_max_segment_size(lim, bv->bv_page, + bv->bv_offset + total_len); seg_size = min(seg_size, len); - new_nsegs++; + (*nsegs)++; total_len += seg_size; len -= seg_size; - if ((bv->bv_offset + total_len) & queue_virt_boundary(q)) + if ((bv->bv_offset + total_len) & lim->virt_boundary_mask) break; } - if (new_nsegs) { - *nsegs += new_nsegs; - if (sectors) - *sectors += total_len >> 9; - } + *bytes += total_len; - /* split in the middle of the bvec if len != 0 */ - return !!len; + /* tell the caller to split the bvec if it is too big to fit */ + return len > 0 || bv->bv_len > max_len; } -static struct bio *blk_bio_segment_split(struct request_queue *q, - struct bio *bio, - struct bio_set *bs, - unsigned *segs) +/** + * bio_split_rw - split a bio in two bios + * @bio: [in] bio to be split + * @lim: [in] queue limits to split based on + * @segs: [out] number of segments in the bio with the first half of the sectors + * @bs: [in] bio set to allocate the clone from + * @max_bytes: [in] maximum number of bytes per bio + * + * Clone @bio, update the bi_iter of the clone to represent the first sectors + * of @bio and update @bio->bi_iter to represent the remaining sectors. The + * following is guaranteed for the cloned bio: + * - That it has at most @max_bytes worth of data + * - That it has at most queue_max_segments(@q) segments. + * + * Except for discard requests the cloned bio will point at the bi_io_vec of + * the original bio. It is the responsibility of the caller to ensure that the + * original bio is not freed before the cloned bio. The caller is also + * responsible for ensuring that @bs is only destroyed after processing of the + * split bio has finished. + */ +struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim, + unsigned *segs, struct bio_set *bs, unsigned max_bytes) { struct bio_vec bv, bvprv, *bvprvp = NULL; struct bvec_iter iter; - unsigned nsegs = 0, sectors = 0; - bool do_split = true; - struct bio *new = NULL; - const unsigned max_sectors = get_max_io_size(q, bio); - const unsigned max_segs = queue_max_segments(q); + unsigned nsegs = 0, bytes = 0; bio_for_each_bvec(bv, bio, iter) { /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. */ - if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset)) + if (bvprvp && bvec_gap_to_prev(lim, bvprvp, bv.bv_offset)) goto split; - if (sectors + (bv.bv_len >> 9) > max_sectors) { - /* - * Consider this a new segment if we're splitting in - * the middle of this vector. - */ - if (nsegs < max_segs && - sectors < max_sectors) { - /* split in the middle of bvec */ - bv.bv_len = (max_sectors - sectors) << 9; - bvec_split_segs(q, &bv, &nsegs, - §ors, max_segs); - } - goto split; + if (nsegs < lim->max_segments && + bytes + bv.bv_len <= max_bytes && + bv.bv_offset + bv.bv_len <= PAGE_SIZE) { + nsegs++; + bytes += bv.bv_len; + } else { + if (bvec_split_segs(lim, &bv, &nsegs, &bytes, + lim->max_segments, max_bytes)) + goto split; } - if (nsegs == max_segs) - goto split; - bvprv = bv; bvprvp = &bvprv; - - if (bv.bv_offset + bv.bv_len <= PAGE_SIZE) { - nsegs++; - sectors += bv.bv_len >> 9; - } else if (bvec_split_segs(q, &bv, &nsegs, §ors, - max_segs)) { - goto split; - } } - do_split = false; + *segs = nsegs; + return NULL; split: + /* + * We can't sanely support splitting for a REQ_NOWAIT bio. End it + * with EAGAIN if splitting is required and return an error pointer. + */ + if (bio->bi_opf & REQ_NOWAIT) { + bio->bi_status = BLK_STS_AGAIN; + bio_endio(bio); + return ERR_PTR(-EAGAIN); + } + *segs = nsegs; - if (do_split) { - new = bio_split(bio, sectors, GFP_NOIO, bs); - if (new) - bio = new; - } + /* + * Individual bvecs might not be logical block aligned. Round down the + * split size so that each bio is properly block size aligned, even if + * we do not use the full hardware limits. + */ + bytes = ALIGN_DOWN(bytes, lim->logical_block_size); - return do_split ? new : NULL; + /* + * Bio splitting may cause subtle trouble such as hang when doing sync + * iopoll in direct IO routine. Given performance gain of iopoll for + * big IO can be trival, disable iopoll when split needed. + */ + bio_clear_polled(bio); + return bio_split(bio, bytes >> SECTOR_SHIFT, GFP_NOIO, bs); } +EXPORT_SYMBOL_GPL(bio_split_rw); -void blk_queue_split(struct request_queue *q, struct bio **bio) +/** + * __bio_split_to_limits - split a bio to fit the queue limits + * @bio: bio to be split + * @lim: queue limits to split based on + * @nr_segs: returns the number of segments in the returned bio + * + * Check if @bio needs splitting based on the queue limits, and if so split off + * a bio fitting the limits from the beginning of @bio and return it. @bio is + * shortened to the remainder and re-submitted. + * + * The split bio is allocated from @q->bio_split, which is provided by the + * block layer. + */ +struct bio *__bio_split_to_limits(struct bio *bio, + const struct queue_limits *lim, + unsigned int *nr_segs) { - struct bio *split, *res; - unsigned nsegs; + struct bio_set *bs = &bio->bi_bdev->bd_disk->bio_split; + struct bio *split; - switch (bio_op(*bio)) { + switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: - split = blk_bio_discard_split(q, *bio, &q->bio_split, &nsegs); + split = bio_split_discard(bio, lim, nr_segs, bs); break; case REQ_OP_WRITE_ZEROES: - split = blk_bio_write_zeroes_split(q, *bio, &q->bio_split, &nsegs); - break; - case REQ_OP_WRITE_SAME: - split = blk_bio_write_same_split(q, *bio, &q->bio_split, &nsegs); + split = bio_split_write_zeroes(bio, lim, nr_segs, bs); break; default: - split = blk_bio_segment_split(q, *bio, &q->bio_split, &nsegs); + split = bio_split_rw(bio, lim, nr_segs, bs, + get_max_io_size(bio, lim) << SECTOR_SHIFT); + if (IS_ERR(split)) + return NULL; break; } - /* physical segments can be figured out during splitting */ - res = split ? split : *bio; - res->bi_phys_segments = nsegs; - bio_set_flag(res, BIO_SEG_VALID); - if (split) { - /* there isn't chance to merge the splitted bio */ + /* there isn't chance to merge the split bio */ split->bi_opf |= REQ_NOMERGE; - /* - * Since we're recursing into make_request here, ensure - * that we mark this bio as already having entered the queue. - * If not, and the queue is going away, we can get stuck - * forever on waiting for the queue reference to drop. But - * that will never happen, as we're already holding a - * reference to it. - */ - bio_set_flag(*bio, BIO_QUEUE_ENTERED); - - bio_chain(split, *bio); - trace_block_split(q, split, (*bio)->bi_iter.bi_sector); - generic_make_request(*bio); - *bio = split; + blkcg_bio_issue_init(split); + bio_chain(split, bio); + trace_block_split(split, bio->bi_iter.bi_sector); + submit_bio_noacct(bio); + return split; } + return bio; } -EXPORT_SYMBOL(blk_queue_split); -static unsigned int __blk_recalc_rq_segments(struct request_queue *q, - struct bio *bio) +/** + * bio_split_to_limits - split a bio to fit the queue limits + * @bio: bio to be split + * + * Check if @bio needs splitting based on the queue limits of @bio->bi_bdev, and + * if so split off a bio fitting the limits from the beginning of @bio and + * return it. @bio is shortened to the remainder and re-submitted. + * + * The split bio is allocated from @q->bio_split, which is provided by the + * block layer. + */ +struct bio *bio_split_to_limits(struct bio *bio) +{ + const struct queue_limits *lim = &bdev_get_queue(bio->bi_bdev)->limits; + unsigned int nr_segs; + + if (bio_may_exceed_limits(bio, lim)) + return __bio_split_to_limits(bio, lim, &nr_segs); + return bio; +} +EXPORT_SYMBOL(bio_split_to_limits); + +unsigned int blk_recalc_rq_segments(struct request *rq) { unsigned int nr_phys_segs = 0; - struct bvec_iter iter; + unsigned int bytes = 0; + struct req_iterator iter; struct bio_vec bv; - if (!bio) + if (!rq->bio) return 0; - switch (bio_op(bio)) { + switch (bio_op(rq->bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: + if (queue_max_discard_segments(rq->q) > 1) { + struct bio *bio = rq->bio; + + for_each_bio(bio) + nr_phys_segs++; + return nr_phys_segs; + } + return 1; case REQ_OP_WRITE_ZEROES: return 0; - case REQ_OP_WRITE_SAME: - return 1; - } - - for_each_bio(bio) { - bio_for_each_bvec(bv, bio, iter) - bvec_split_segs(q, &bv, &nr_phys_segs, NULL, UINT_MAX); + default: + break; } + rq_for_each_bvec(bv, rq, iter) + bvec_split_segs(&rq->q->limits, &bv, &nr_phys_segs, &bytes, + UINT_MAX, UINT_MAX); return nr_phys_segs; } -void blk_recalc_rq_segments(struct request *rq) -{ - rq->nr_phys_segments = __blk_recalc_rq_segments(rq->q, rq->bio); -} - -void blk_recount_segments(struct request_queue *q, struct bio *bio) -{ - struct bio *nxt = bio->bi_next; - - bio->bi_next = NULL; - bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio); - bio->bi_next = nxt; - - bio_set_flag(bio, BIO_SEG_VALID); -} - static inline struct scatterlist *blk_next_sg(struct scatterlist **sg, struct scatterlist *sglist) { @@ -375,7 +468,8 @@ static unsigned blk_bvec_map_sg(struct request_queue *q, while (nbytes > 0) { unsigned offset = bvec->bv_offset + total; - unsigned len = min(get_max_segment_size(q, offset), nbytes); + unsigned len = min(get_max_segment_size(&q->limits, + bvec->bv_page, offset), nbytes); struct page *page = bvec->bv_page; /* @@ -434,7 +528,7 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, struct scatterlist *sglist, struct scatterlist **sg) { - struct bio_vec uninitialized_var(bvec), bvprv = { NULL }; + struct bio_vec bvec, bvprv = { NULL }; struct bvec_iter iter; int nsegs = 0; bool new_bio = false; @@ -470,44 +564,18 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, * map a request to scatterlist, return number of sg entries setup. Caller * must make sure sg can hold rq->nr_phys_segments entries */ -int blk_rq_map_sg(struct request_queue *q, struct request *rq, - struct scatterlist *sglist) +int __blk_rq_map_sg(struct request_queue *q, struct request *rq, + struct scatterlist *sglist, struct scatterlist **last_sg) { - struct scatterlist *sg = NULL; int nsegs = 0; if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) - nsegs = __blk_bvec_map_sg(rq->special_vec, sglist, &sg); - else if (rq->bio && bio_op(rq->bio) == REQ_OP_WRITE_SAME) - nsegs = __blk_bvec_map_sg(bio_iovec(rq->bio), sglist, &sg); + nsegs = __blk_bvec_map_sg(rq->special_vec, sglist, last_sg); else if (rq->bio) - nsegs = __blk_bios_map_sg(q, rq->bio, sglist, &sg); - - if (unlikely(rq->rq_flags & RQF_COPY_USER) && - (blk_rq_bytes(rq) & q->dma_pad_mask)) { - unsigned int pad_len = - (q->dma_pad_mask & ~blk_rq_bytes(rq)) + 1; - - sg->length += pad_len; - rq->extra_len += pad_len; - } - - if (q->dma_drain_size && q->dma_drain_needed(rq)) { - if (op_is_write(req_op(rq))) - memset(q->dma_drain_buffer, 0, q->dma_drain_size); - - sg_unmark_end(sg); - sg = sg_next(sg); - sg_set_page(sg, virt_to_page(q->dma_drain_buffer), - q->dma_drain_size, - ((unsigned long)q->dma_drain_buffer) & - (PAGE_SIZE - 1)); - nsegs++; - rq->extra_len += q->dma_drain_size; - } + nsegs = __blk_bios_map_sg(q, rq->bio, sglist, last_sg); - if (sg) - sg_mark_end(sg); + if (*last_sg) + sg_mark_end(*last_sg); /* * Something must have been wrong if the figured number of @@ -517,18 +585,40 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq, return nsegs; } -EXPORT_SYMBOL(blk_rq_map_sg); +EXPORT_SYMBOL(__blk_rq_map_sg); -static inline int ll_new_hw_segment(struct request_queue *q, - struct request *req, - struct bio *bio) +static inline unsigned int blk_rq_get_max_sectors(struct request *rq, + sector_t offset) { - int nr_phys_segs = bio_phys_segments(q, bio); + struct request_queue *q = rq->q; + unsigned int max_sectors; + + if (blk_rq_is_passthrough(rq)) + return q->limits.max_hw_sectors; + + max_sectors = blk_queue_get_max_sectors(q, req_op(rq)); + if (!q->limits.chunk_sectors || + req_op(rq) == REQ_OP_DISCARD || + req_op(rq) == REQ_OP_SECURE_ERASE) + return max_sectors; + return min(max_sectors, + blk_chunk_sectors_left(offset, q->limits.chunk_sectors)); +} + +static inline int ll_new_hw_segment(struct request *req, struct bio *bio, + unsigned int nr_phys_segs) +{ + if (!blk_cgroup_mergeable(req, bio)) + goto no_merge; - if (req->nr_phys_segments + nr_phys_segs > queue_max_segments(q)) + if (blk_integrity_merge_bio(req->q, req, bio) == false) goto no_merge; - if (blk_integrity_merge_bio(q, req, bio) == false) + /* discard request merge won't add new segment */ + if (req_op(req) == REQ_OP_DISCARD) + return 1; + + if (req->nr_phys_segments + nr_phys_segs > blk_rq_get_max_segments(req)) goto no_merge; /* @@ -539,51 +629,45 @@ static inline int ll_new_hw_segment(struct request_queue *q, return 1; no_merge: - req_set_nomerge(q, req); + req_set_nomerge(req->q, req); return 0; } -int ll_back_merge_fn(struct request_queue *q, struct request *req, - struct bio *bio) +int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs) { if (req_gap_back_merge(req, bio)) return 0; if (blk_integrity_rq(req) && integrity_req_gap_back_merge(req, bio)) return 0; + if (!bio_crypt_ctx_back_mergeable(req, bio)) + return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, blk_rq_pos(req))) { - req_set_nomerge(q, req); + req_set_nomerge(req->q, req); return 0; } - if (!bio_flagged(req->biotail, BIO_SEG_VALID)) - blk_recount_segments(q, req->biotail); - if (!bio_flagged(bio, BIO_SEG_VALID)) - blk_recount_segments(q, bio); - return ll_new_hw_segment(q, req, bio); + return ll_new_hw_segment(req, bio, nr_segs); } -int ll_front_merge_fn(struct request_queue *q, struct request *req, - struct bio *bio) +static int ll_front_merge_fn(struct request *req, struct bio *bio, + unsigned int nr_segs) { - if (req_gap_front_merge(req, bio)) return 0; if (blk_integrity_rq(req) && integrity_req_gap_front_merge(req, bio)) return 0; + if (!bio_crypt_ctx_front_mergeable(req, bio)) + return 0; if (blk_rq_sectors(req) + bio_sectors(bio) > blk_rq_get_max_sectors(req, bio->bi_iter.bi_sector)) { - req_set_nomerge(q, req); + req_set_nomerge(req->q, req); return 0; } - if (!bio_flagged(bio, BIO_SEG_VALID)) - blk_recount_segments(q, bio); - if (!bio_flagged(req->bio, BIO_SEG_VALID)) - blk_recount_segments(q, req->bio); - return ll_new_hw_segment(q, req, bio); + return ll_new_hw_segment(req, bio, nr_segs); } static bool req_attempt_discard_merge(struct request_queue *q, struct request *req, @@ -620,12 +704,18 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req, return 0; total_phys_segments = req->nr_phys_segments + next->nr_phys_segments; - if (total_phys_segments > queue_max_segments(q)) + if (total_phys_segments > blk_rq_get_max_segments(req)) + return 0; + + if (!blk_cgroup_mergeable(req, next->bio)) return 0; if (blk_integrity_merge_rq(q, req, next) == false) return 0; + if (!bio_crypt_ctx_merge_rq(req, next)) + return 0; + /* Merge is OK... */ req->nr_phys_segments = total_phys_segments; return 1; @@ -642,7 +732,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req, */ void blk_rq_set_mixed_merge(struct request *rq) { - unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; + blk_opf_t ff = rq->cmd_flags & REQ_FAILFAST_MASK; struct bio *bio; if (rq->rq_flags & RQF_MIXED_MERGE) @@ -661,34 +751,40 @@ void blk_rq_set_mixed_merge(struct request *rq) rq->rq_flags |= RQF_MIXED_MERGE; } -static void blk_account_io_merge(struct request *req) +static inline blk_opf_t bio_failfast(const struct bio *bio) { - if (blk_do_io_stat(req)) { - struct hd_struct *part; + if (bio->bi_opf & REQ_RAHEAD) + return REQ_FAILFAST_MASK; - part_stat_lock(); - part = req->part; + return bio->bi_opf & REQ_FAILFAST_MASK; +} - part_dec_in_flight(req->q, part, rq_data_dir(req)); +/* + * After we are marked as MIXED_MERGE, any new RA bio has to be updated + * as failfast, and request's failfast has to be updated in case of + * front merge. + */ +static inline void blk_update_mixed_merge(struct request *req, + struct bio *bio, bool front_merge) +{ + if (req->rq_flags & RQF_MIXED_MERGE) { + if (bio->bi_opf & REQ_RAHEAD) + bio->bi_opf |= REQ_FAILFAST_MASK; - hd_struct_put(part); - part_stat_unlock(); + if (front_merge) { + req->cmd_flags &= ~REQ_FAILFAST_MASK; + req->cmd_flags |= bio->bi_opf & REQ_FAILFAST_MASK; + } } } -/* - * Two cases of handling DISCARD merge: - * If max_discard_segments > 1, the driver takes every bio - * as a range and send them to controller together. The ranges - * needn't to be contiguous. - * Otherwise, the bios/requests will be handled as same as - * others which should be contiguous. - */ -static inline bool blk_discard_mergable(struct request *req) + +static void blk_account_io_merge_request(struct request *req) { - if (req_op(req) == REQ_OP_DISCARD && - queue_max_discard_segments(req->q) > 1) - return true; - return false; + if (blk_do_io_stat(req)) { + part_stat_lock(); + part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); + part_stat_unlock(); + } } static enum elv_merge blk_try_req_merge(struct request *req, @@ -715,19 +811,7 @@ static struct request *attempt_merge(struct request_queue *q, if (req_op(req) != req_op(next)) return NULL; - if (rq_data_dir(req) != rq_data_dir(next) - || req->rq_disk != next->rq_disk) - return NULL; - - if (req_op(req) == REQ_OP_WRITE_SAME && - !blk_write_same_mergeable(req->bio, next->bio)) - return NULL; - - /* - * Don't allow merge of different write hints, or for a hint with - * non-hint IO. - */ - if (req->write_hint != next->write_hint) + if (rq_data_dir(req) != rq_data_dir(next)) return NULL; if (req->ioprio != next->ioprio) @@ -783,10 +867,14 @@ static struct request *attempt_merge(struct request_queue *q, if (!blk_discard_mergable(req)) elv_merge_requests(q, req, next); + blk_crypto_rq_put_keyslot(next); + /* * 'next' is going away, so update stats accordingly */ - blk_account_io_merge(next); + blk_account_io_merge_request(next); + + trace_block_rq_merge(next); /* * ownership of bio passed from next to req, return 'next' for @@ -796,7 +884,8 @@ static struct request *attempt_merge(struct request_queue *q, return next; } -struct request *attempt_back_merge(struct request_queue *q, struct request *rq) +static struct request *attempt_back_merge(struct request_queue *q, + struct request *rq) { struct request *next = elv_latter_request(q, rq); @@ -806,7 +895,8 @@ struct request *attempt_back_merge(struct request_queue *q, struct request *rq) return NULL; } -struct request *attempt_front_merge(struct request_queue *q, struct request *rq) +static struct request *attempt_front_merge(struct request_queue *q, + struct request *rq) { struct request *prev = elv_former_request(q, rq); @@ -816,18 +906,15 @@ struct request *attempt_front_merge(struct request_queue *q, struct request *rq) return NULL; } -int blk_attempt_req_merge(struct request_queue *q, struct request *rq, - struct request *next) +/* + * Try to merge 'next' into 'rq'. Return true if the merge happened, false + * otherwise. The caller is responsible for freeing 'next' if the merge + * happened. + */ +bool blk_attempt_req_merge(struct request_queue *q, struct request *rq, + struct request *next) { - struct request *free; - - free = attempt_merge(q, rq, next); - if (free) { - blk_put_request(free); - return 1; - } - - return 0; + return attempt_merge(q, rq, next); } bool blk_rq_merge_ok(struct request *rq, struct bio *bio) @@ -842,24 +929,16 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) if (bio_data_dir(bio) != rq_data_dir(rq)) return false; - /* must be same device */ - if (rq->rq_disk != bio->bi_disk) + /* don't merge across cgroup boundaries */ + if (!blk_cgroup_mergeable(rq, bio)) return false; /* only merge integrity protected bio into ditto rq */ if (blk_integrity_merge_bio(rq->q, rq, bio) == false) return false; - /* must be using the same buffer */ - if (req_op(rq) == REQ_OP_WRITE_SAME && - !blk_write_same_mergeable(rq->bio, bio)) - return false; - - /* - * Don't allow merge of different write hints, or for a hint with - * non-hint IO. - */ - if (rq->write_hint != bio->bi_write_hint) + /* Only merge if the crypt contexts are compatible */ + if (!bio_crypt_rq_ctx_compatible(rq, bio)) return false; if (rq->ioprio != bio_prio(bio)) @@ -878,3 +957,234 @@ enum elv_merge blk_try_merge(struct request *rq, struct bio *bio) return ELEVATOR_FRONT_MERGE; return ELEVATOR_NO_MERGE; } + +static void blk_account_io_merge_bio(struct request *req) +{ + if (!blk_do_io_stat(req)) + return; + + part_stat_lock(); + part_stat_inc(req->part, merges[op_stat_group(req_op(req))]); + part_stat_unlock(); +} + +enum bio_merge_status { + BIO_MERGE_OK, + BIO_MERGE_NONE, + BIO_MERGE_FAILED, +}; + +static enum bio_merge_status bio_attempt_back_merge(struct request *req, + struct bio *bio, unsigned int nr_segs) +{ + const blk_opf_t ff = bio_failfast(bio); + + if (!ll_back_merge_fn(req, bio, nr_segs)) + return BIO_MERGE_FAILED; + + trace_block_bio_backmerge(bio); + rq_qos_merge(req->q, req, bio); + + if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) + blk_rq_set_mixed_merge(req); + + blk_update_mixed_merge(req, bio, false); + + req->biotail->bi_next = bio; + req->biotail = bio; + req->__data_len += bio->bi_iter.bi_size; + + bio_crypt_free_ctx(bio); + + blk_account_io_merge_bio(req); + return BIO_MERGE_OK; +} + +static enum bio_merge_status bio_attempt_front_merge(struct request *req, + struct bio *bio, unsigned int nr_segs) +{ + const blk_opf_t ff = bio_failfast(bio); + + if (!ll_front_merge_fn(req, bio, nr_segs)) + return BIO_MERGE_FAILED; + + trace_block_bio_frontmerge(bio); + rq_qos_merge(req->q, req, bio); + + if ((req->cmd_flags & REQ_FAILFAST_MASK) != ff) + blk_rq_set_mixed_merge(req); + + blk_update_mixed_merge(req, bio, true); + + bio->bi_next = req->bio; + req->bio = bio; + + req->__sector = bio->bi_iter.bi_sector; + req->__data_len += bio->bi_iter.bi_size; + + bio_crypt_do_front_merge(req, bio); + + blk_account_io_merge_bio(req); + return BIO_MERGE_OK; +} + +static enum bio_merge_status bio_attempt_discard_merge(struct request_queue *q, + struct request *req, struct bio *bio) +{ + unsigned short segments = blk_rq_nr_discard_segments(req); + + if (segments >= queue_max_discard_segments(q)) + goto no_merge; + if (blk_rq_sectors(req) + bio_sectors(bio) > + blk_rq_get_max_sectors(req, blk_rq_pos(req))) + goto no_merge; + + rq_qos_merge(q, req, bio); + + req->biotail->bi_next = bio; + req->biotail = bio; + req->__data_len += bio->bi_iter.bi_size; + req->nr_phys_segments = segments + 1; + + blk_account_io_merge_bio(req); + return BIO_MERGE_OK; +no_merge: + req_set_nomerge(q, req); + return BIO_MERGE_FAILED; +} + +static enum bio_merge_status blk_attempt_bio_merge(struct request_queue *q, + struct request *rq, + struct bio *bio, + unsigned int nr_segs, + bool sched_allow_merge) +{ + if (!blk_rq_merge_ok(rq, bio)) + return BIO_MERGE_NONE; + + switch (blk_try_merge(rq, bio)) { + case ELEVATOR_BACK_MERGE: + if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio)) + return bio_attempt_back_merge(rq, bio, nr_segs); + break; + case ELEVATOR_FRONT_MERGE: + if (!sched_allow_merge || blk_mq_sched_allow_merge(q, rq, bio)) + return bio_attempt_front_merge(rq, bio, nr_segs); + break; + case ELEVATOR_DISCARD_MERGE: + return bio_attempt_discard_merge(q, rq, bio); + default: + return BIO_MERGE_NONE; + } + + return BIO_MERGE_FAILED; +} + +/** + * blk_attempt_plug_merge - try to merge with %current's plugged list + * @q: request_queue new bio is being queued at + * @bio: new bio being queued + * @nr_segs: number of segments in @bio + * from the passed in @q already in the plug list + * + * Determine whether @bio being queued on @q can be merged with the previous + * request on %current's plugged list. Returns %true if merge was successful, + * otherwise %false. + * + * Plugging coalesces IOs from the same issuer for the same purpose without + * going through @q->queue_lock. As such it's more of an issuing mechanism + * than scheduling, and the request, while may have elvpriv data, is not + * added on the elevator at this point. In addition, we don't have + * reliable access to the elevator outside queue lock. Only check basic + * merging parameters without querying the elevator. + * + * Caller must ensure !blk_queue_nomerges(q) beforehand. + */ +bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, + unsigned int nr_segs) +{ + struct blk_plug *plug; + struct request *rq; + + plug = blk_mq_plug(bio); + if (!plug || rq_list_empty(plug->mq_list)) + return false; + + rq_list_for_each(&plug->mq_list, rq) { + if (rq->q == q) { + if (blk_attempt_bio_merge(q, rq, bio, nr_segs, false) == + BIO_MERGE_OK) + return true; + break; + } + + /* + * Only keep iterating plug list for merges if we have multiple + * queues + */ + if (!plug->multiple_queues) + break; + } + return false; +} + +/* + * Iterate list of requests and see if we can merge this bio with any + * of them. + */ +bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, + struct bio *bio, unsigned int nr_segs) +{ + struct request *rq; + int checked = 8; + + list_for_each_entry_reverse(rq, list, queuelist) { + if (!checked--) + break; + + switch (blk_attempt_bio_merge(q, rq, bio, nr_segs, true)) { + case BIO_MERGE_NONE: + continue; + case BIO_MERGE_OK: + return true; + case BIO_MERGE_FAILED: + return false; + } + + } + + return false; +} +EXPORT_SYMBOL_GPL(blk_bio_list_merge); + +bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio, + unsigned int nr_segs, struct request **merged_request) +{ + struct request *rq; + + switch (elv_merge(q, &rq, bio)) { + case ELEVATOR_BACK_MERGE: + if (!blk_mq_sched_allow_merge(q, rq, bio)) + return false; + if (bio_attempt_back_merge(rq, bio, nr_segs) != BIO_MERGE_OK) + return false; + *merged_request = attempt_back_merge(q, rq); + if (!*merged_request) + elv_merged_request(q, rq, ELEVATOR_BACK_MERGE); + return true; + case ELEVATOR_FRONT_MERGE: + if (!blk_mq_sched_allow_merge(q, rq, bio)) + return false; + if (bio_attempt_front_merge(rq, bio, nr_segs) != BIO_MERGE_OK) + return false; + *merged_request = attempt_front_merge(q, rq); + if (!*merged_request) + elv_merged_request(q, rq, ELEVATOR_FRONT_MERGE); + return true; + case ELEVATOR_DISCARD_MERGE: + return bio_attempt_discard_merge(q, rq, bio) == BIO_MERGE_OK; + default: + return false; + } +} +EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge); |