diff options
Diffstat (limited to 'block')
| -rw-r--r-- | block/bfq-iosched.c | 11 | ||||
| -rw-r--r-- | block/bio-integrity.c | 8 | ||||
| -rw-r--r-- | block/bio.c | 131 | ||||
| -rw-r--r-- | block/blk-merge.c | 48 | ||||
| -rw-r--r-- | block/blk-mq-sysfs.c | 15 | ||||
| -rw-r--r-- | block/blk-mq.c | 2 | ||||
| -rw-r--r-- | block/blk-sysfs.c | 3 |
7 files changed, 160 insertions, 58 deletions
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 7d45ac451745..93863c6173e6 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -3314,7 +3314,12 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq) * whether bfqq is being weight-raised, because * bfq_symmetric_scenario() does not take into account also * weight-raised queues (see comments on - * bfq_weights_tree_add()). + * bfq_weights_tree_add()). In particular, if bfqq is being + * weight-raised, it is important to idle only if there are + * other, non-weight-raised queues that may steal throughput + * to bfqq. Actually, we should be even more precise, and + * differentiate between interactive weight raising and + * soft real-time weight raising. * * As a side note, it is worth considering that the above * device-idling countermeasures may however fail in the @@ -3326,7 +3331,8 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq) * to let requests be served in the desired order until all * the requests already queued in the device have been served. */ - asymmetric_scenario = bfqq->wr_coeff > 1 || + asymmetric_scenario = (bfqq->wr_coeff > 1 && + bfqd->wr_busy_queues < bfqd->busy_queues) || !bfq_symmetric_scenario(bfqd); /* @@ -3760,6 +3766,7 @@ static void bfq_exit_icq_bfqq(struct bfq_io_cq *bic, bool is_sync) unsigned long flags; spin_lock_irqsave(&bfqd->lock, flags); + bfqq->bic = NULL; bfq_exit_bfqq(bfqd, bfqq); bic_set_bfqq(bic, NULL, is_sync); spin_unlock_irqrestore(&bfqd->lock, flags); diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 5df32907ff3b..7f8010662437 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -313,8 +313,12 @@ bool bio_integrity_prep(struct bio *bio) ret = bio_integrity_add_page(bio, virt_to_page(buf), bytes, offset); - if (ret == 0) - return false; + if (ret == 0) { + printk(KERN_ERR "could not attach integrity payload\n"); + kfree(buf); + status = BLK_STS_RESOURCE; + goto err_end_io; + } if (ret < bytes) break; diff --git a/block/bio.c b/block/bio.c index d01ab919b313..1384f9790882 100644 --- a/block/bio.c +++ b/block/bio.c @@ -773,7 +773,7 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page return 0; } - if (bio->bi_vcnt >= bio->bi_max_vecs) + if (bio_full(bio)) return 0; /* @@ -821,65 +821,97 @@ int bio_add_pc_page(struct request_queue *q, struct bio *bio, struct page EXPORT_SYMBOL(bio_add_pc_page); /** - * bio_add_page - attempt to add page to bio - * @bio: destination bio - * @page: page to add - * @len: vec entry length - * @offset: vec entry offset + * __bio_try_merge_page - try appending data to an existing bvec. + * @bio: destination bio + * @page: page to add + * @len: length of the data to add + * @off: offset of the data in @page * - * Attempt to add a page to the bio_vec maplist. This will only fail - * if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio. + * Try to add the data at @page + @off to the last bvec of @bio. This is a + * a useful optimisation for file systems with a block size smaller than the + * page size. + * + * Return %true on success or %false on failure. */ -int bio_add_page(struct bio *bio, struct page *page, - unsigned int len, unsigned int offset) +bool __bio_try_merge_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int off) { - struct bio_vec *bv; - - /* - * cloned bio must not modify vec list - */ if (WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED))) - return 0; + return false; - /* - * For filesystems with a blocksize smaller than the pagesize - * we will often be called with the same page as last time and - * a consecutive offset. Optimize this special case. - */ if (bio->bi_vcnt > 0) { - bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; + struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1]; - if (page == bv->bv_page && - offset == bv->bv_offset + bv->bv_len) { + if (page == bv->bv_page && off == bv->bv_offset + bv->bv_len) { bv->bv_len += len; - goto done; + bio->bi_iter.bi_size += len; + return true; } } + return false; +} +EXPORT_SYMBOL_GPL(__bio_try_merge_page); - if (bio->bi_vcnt >= bio->bi_max_vecs) - return 0; +/** + * __bio_add_page - add page to a bio in a new segment + * @bio: destination bio + * @page: page to add + * @len: length of the data to add + * @off: offset of the data in @page + * + * Add the data at @page + @off to @bio as a new bvec. The caller must ensure + * that @bio has space for another bvec. + */ +void __bio_add_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int off) +{ + struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt]; - bv = &bio->bi_io_vec[bio->bi_vcnt]; - bv->bv_page = page; - bv->bv_len = len; - bv->bv_offset = offset; + WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); + WARN_ON_ONCE(bio_full(bio)); + + bv->bv_page = page; + bv->bv_offset = off; + bv->bv_len = len; - bio->bi_vcnt++; -done: bio->bi_iter.bi_size += len; + bio->bi_vcnt++; +} +EXPORT_SYMBOL_GPL(__bio_add_page); + +/** + * bio_add_page - attempt to add page to bio + * @bio: destination bio + * @page: page to add + * @len: vec entry length + * @offset: vec entry offset + * + * Attempt to add a page to the bio_vec maplist. This will only fail + * if either bio->bi_vcnt == bio->bi_max_vecs or it's a cloned bio. + */ +int bio_add_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int offset) +{ + if (!__bio_try_merge_page(bio, page, len, offset)) { + if (bio_full(bio)) + return 0; + __bio_add_page(bio, page, len, offset); + } return len; } EXPORT_SYMBOL(bio_add_page); /** - * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio + * __bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio * @bio: bio to add pages to * @iter: iov iterator describing the region to be mapped * - * Pins as many pages from *iter and appends them to @bio's bvec array. The + * Pins pages from *iter and appends them to @bio's bvec array. The * pages will have to be released using put_page() when done. + * For multi-segment *iter, this function only adds pages from the + * the next non-empty segment of the iov iterator. */ -int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) +static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) { unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt, idx; struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; @@ -916,6 +948,33 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) iov_iter_advance(iter, size); return 0; } + +/** + * bio_iov_iter_get_pages - pin user or kernel pages and add them to a bio + * @bio: bio to add pages to + * @iter: iov iterator describing the region to be mapped + * + * Pins pages from *iter and appends them to @bio's bvec array. The + * pages will have to be released using put_page() when done. + * The function tries, but does not guarantee, to pin as many pages as + * fit into the bio, or are requested in *iter, whatever is smaller. + * If MM encounters an error pinning the requested pages, it stops. + * Error is returned only if 0 pages could be pinned. + */ +int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) +{ + unsigned short orig_vcnt = bio->bi_vcnt; + + do { + int ret = __bio_iov_iter_get_pages(bio, iter); + + if (unlikely(ret)) + return bio->bi_vcnt > orig_vcnt ? 0 : ret; + + } while (iov_iter_count(iter) && !bio_full(bio)); + + return 0; +} EXPORT_SYMBOL_GPL(bio_iov_iter_get_pages); struct submit_bio_ret { diff --git a/block/blk-merge.c b/block/blk-merge.c index 8d60a5bbcef9..f61b50a01bc7 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -659,6 +659,31 @@ static void blk_account_io_merge(struct request *req) part_stat_unlock(); } } +/* + * 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) +{ + if (req_op(req) == REQ_OP_DISCARD && + queue_max_discard_segments(req->q) > 1) + return true; + return false; +} + +enum elv_merge blk_try_req_merge(struct request *req, struct request *next) +{ + if (blk_discard_mergable(req)) + return ELEVATOR_DISCARD_MERGE; + else if (blk_rq_pos(req) + blk_rq_sectors(req) == blk_rq_pos(next)) + return ELEVATOR_BACK_MERGE; + + return ELEVATOR_NO_MERGE; +} /* * For non-mq, this has to be called with the request spinlock acquired. @@ -676,12 +701,6 @@ static struct request *attempt_merge(struct request_queue *q, if (req_op(req) != req_op(next)) return NULL; - /* - * not contiguous - */ - if (blk_rq_pos(req) + blk_rq_sectors(req) != blk_rq_pos(next)) - return NULL; - if (rq_data_dir(req) != rq_data_dir(next) || req->rq_disk != next->rq_disk || req_no_special_merge(next)) @@ -705,11 +724,19 @@ static struct request *attempt_merge(struct request_queue *q, * counts here. Handle DISCARDs separately, as they * have separate settings. */ - if (req_op(req) == REQ_OP_DISCARD) { + + switch (blk_try_req_merge(req, next)) { + case ELEVATOR_DISCARD_MERGE: if (!req_attempt_discard_merge(q, req, next)) return NULL; - } else if (!ll_merge_requests_fn(q, req, next)) + break; + case ELEVATOR_BACK_MERGE: + if (!ll_merge_requests_fn(q, req, next)) + return NULL; + break; + default: return NULL; + } /* * If failfast settings disagree or any of the two is already @@ -738,7 +765,7 @@ static struct request *attempt_merge(struct request_queue *q, req->__data_len += blk_rq_bytes(next); - if (req_op(req) != REQ_OP_DISCARD) + if (!blk_discard_mergable(req)) elv_merge_requests(q, req, next); /* @@ -834,8 +861,7 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) enum elv_merge blk_try_merge(struct request *rq, struct bio *bio) { - if (req_op(rq) == REQ_OP_DISCARD && - queue_max_discard_segments(rq->q) > 1) + if (blk_discard_mergable(rq)) return ELEVATOR_DISCARD_MERGE; else if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector) return ELEVATOR_BACK_MERGE; diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index a54b4b070f1c..de209d60a662 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -145,20 +145,25 @@ static ssize_t blk_mq_hw_sysfs_nr_reserved_tags_show(struct blk_mq_hw_ctx *hctx, static ssize_t blk_mq_hw_sysfs_cpus_show(struct blk_mq_hw_ctx *hctx, char *page) { + const size_t size = PAGE_SIZE - 1; unsigned int i, first = 1; - ssize_t ret = 0; + int ret = 0, pos = 0; for_each_cpu(i, hctx->cpumask) { if (first) - ret += sprintf(ret + page, "%u", i); + ret = snprintf(pos + page, size - pos, "%u", i); else - ret += sprintf(ret + page, ", %u", i); + ret = snprintf(pos + page, size - pos, ", %u", i); + + if (ret >= size - pos) + break; first = 0; + pos += ret; } - ret += sprintf(ret + page, "\n"); - return ret; + ret = snprintf(pos + page, size + 1 - pos, "\n"); + return pos + ret; } static struct attribute *default_ctx_attrs[] = { diff --git a/block/blk-mq.c b/block/blk-mq.c index f7427d6b6588..3875729f31c5 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2295,8 +2295,6 @@ void blk_mq_release(struct request_queue *q) struct blk_mq_hw_ctx *hctx; unsigned int i; - cancel_delayed_work_sync(&q->requeue_work); - /* hctx kobj stays in hctx */ queue_for_each_hw_ctx(q, hctx, i) { if (!hctx) diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index d0ec0d55d3d0..dfc391df0ffe 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -811,6 +811,9 @@ static void __blk_release_queue(struct work_struct *work) blk_free_queue_stats(q->stats); + if (q->mq_ops) + cancel_delayed_work_sync(&q->requeue_work); + blk_exit_rl(q, &q->root_rl); if (q->queue_tags) |