diff options
Diffstat (limited to 'block')
| -rw-r--r-- | block/bfq-iosched.c | 62 | ||||
| -rw-r--r-- | block/bio-integrity.c | 7 | ||||
| -rw-r--r-- | block/bio.c | 9 | ||||
| -rw-r--r-- | block/blk-cgroup.c | 4 | ||||
| -rw-r--r-- | block/blk-core.c | 4 | ||||
| -rw-r--r-- | block/blk-lib.c | 108 | ||||
| -rw-r--r-- | block/blk-mq-debugfs.c | 1 | ||||
| -rw-r--r-- | block/blk-mq-sched.c | 219 | ||||
| -rw-r--r-- | block/blk-mq.c | 137 | ||||
| -rw-r--r-- | block/blk-mq.h | 22 | ||||
| -rw-r--r-- | block/blk-stat.c | 45 | ||||
| -rw-r--r-- | block/blk-throttle.c | 12 | ||||
| -rw-r--r-- | block/blk-timeout.c | 5 | ||||
| -rw-r--r-- | block/blk-wbt.c | 2 | ||||
| -rw-r--r-- | block/blk.h | 7 | ||||
| -rw-r--r-- | block/elevator.c | 67 | ||||
| -rw-r--r-- | block/ioctl.c | 19 | ||||
| -rw-r--r-- | block/kyber-iosched.c | 12 | ||||
| -rw-r--r-- | block/mq-deadline.c | 1 |
19 files changed, 498 insertions, 245 deletions
diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 70f9177c4f5b..889a8549d97f 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -108,6 +108,7 @@ #include "blk-mq-tag.h" #include "blk-mq-sched.h" #include "bfq-iosched.h" +#include "blk-wbt.h" #define BFQ_BFQQ_FNS(name) \ void bfq_mark_bfqq_##name(struct bfq_queue *bfqq) \ @@ -3725,9 +3726,36 @@ void bfq_put_queue(struct bfq_queue *bfqq) if (bfqq->ref) return; - if (bfq_bfqq_sync(bfqq) && !hlist_unhashed(&bfqq->burst_list_node)) { + if (!hlist_unhashed(&bfqq->burst_list_node)) { hlist_del_init(&bfqq->burst_list_node); - bfqq->bfqd->burst_size--; + /* + * Decrement also burst size after the removal, if the + * process associated with bfqq is exiting, and thus + * does not contribute to the burst any longer. This + * decrement helps filter out false positives of large + * bursts, when some short-lived process (often due to + * the execution of commands by some service) happens + * to start and exit while a complex application is + * starting, and thus spawning several processes that + * do I/O (and that *must not* be treated as a large + * burst, see comments on bfq_handle_burst). + * + * In particular, the decrement is performed only if: + * 1) bfqq is not a merged queue, because, if it is, + * then this free of bfqq is not triggered by the exit + * of the process bfqq is associated with, but exactly + * by the fact that bfqq has just been merged. + * 2) burst_size is greater than 0, to handle + * unbalanced decrements. Unbalanced decrements may + * happen in te following case: bfqq is inserted into + * the current burst list--without incrementing + * bust_size--because of a split, but the current + * burst list is not the burst list bfqq belonged to + * (see comments on the case of a split in + * bfq_set_request). + */ + if (bfqq->bic && bfqq->bfqd->burst_size > 0) + bfqq->bfqd->burst_size--; } kmem_cache_free(bfq_pool, bfqq); @@ -4459,6 +4487,34 @@ static struct bfq_queue *bfq_get_bfqq_handle_split(struct bfq_data *bfqd, else { bfq_clear_bfqq_in_large_burst(bfqq); if (bic->was_in_burst_list) + /* + * If bfqq was in the current + * burst list before being + * merged, then we have to add + * it back. And we do not need + * to increase burst_size, as + * we did not decrement + * burst_size when we removed + * bfqq from the burst list as + * a consequence of a merge + * (see comments in + * bfq_put_queue). In this + * respect, it would be rather + * costly to know whether the + * current burst list is still + * the same burst list from + * which bfqq was removed on + * the merge. To avoid this + * cost, if bfqq was in a + * burst list, then we add + * bfqq to the current burst + * list without any further + * check. This can cause + * inappropriate insertions, + * but rarely enough to not + * harm the detection of large + * bursts significantly. + */ hlist_add_head(&bfqq->burst_list_node, &bfqd->burst_list); } @@ -4810,7 +4866,7 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) bfq_init_root_group(bfqd->root_group, bfqd); bfq_init_entity(&bfqd->oom_bfqq.entity, bfqd->root_group); - + wbt_disable_default(q); return 0; out_free: diff --git a/block/bio-integrity.c b/block/bio-integrity.c index 5df32907ff3b..23b42e8aa03e 100644 --- a/block/bio-integrity.c +++ b/block/bio-integrity.c @@ -485,11 +485,8 @@ EXPORT_SYMBOL(bioset_integrity_create); void bioset_integrity_free(struct bio_set *bs) { - if (bs->bio_integrity_pool) - mempool_destroy(bs->bio_integrity_pool); - - if (bs->bvec_integrity_pool) - mempool_destroy(bs->bvec_integrity_pool); + mempool_destroy(bs->bio_integrity_pool); + mempool_destroy(bs->bvec_integrity_pool); } EXPORT_SYMBOL(bioset_integrity_free); diff --git a/block/bio.c b/block/bio.c index 8338304ea256..ae9ad34e6a71 100644 --- a/block/bio.c +++ b/block/bio.c @@ -400,7 +400,7 @@ static void punt_bios_to_rescuer(struct bio_set *bs) /** * bio_alloc_bioset - allocate a bio for I/O - * @gfp_mask: the GFP_ mask given to the slab allocator + * @gfp_mask: the GFP_* mask given to the slab allocator * @nr_iovecs: number of iovecs to pre-allocate * @bs: the bio_set to allocate from. * @@ -1928,11 +1928,8 @@ void bioset_free(struct bio_set *bs) if (bs->rescue_workqueue) destroy_workqueue(bs->rescue_workqueue); - if (bs->bio_pool) - mempool_destroy(bs->bio_pool); - - if (bs->bvec_pool) - mempool_destroy(bs->bvec_pool); + mempool_destroy(bs->bio_pool); + mempool_destroy(bs->bvec_pool); bioset_integrity_free(bs); bio_put_slab(bs); diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index d3f56baee936..e7ec676043b1 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1452,7 +1452,7 @@ int blkcg_policy_register(struct blkcg_policy *pol) return 0; err_free_cpds: - if (pol->cpd_alloc_fn) { + if (pol->cpd_free_fn) { list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { if (blkcg->cpd[pol->plid]) { pol->cpd_free_fn(blkcg->cpd[pol->plid]); @@ -1492,7 +1492,7 @@ void blkcg_policy_unregister(struct blkcg_policy *pol) /* remove cpds and unregister */ mutex_lock(&blkcg_pol_mutex); - if (pol->cpd_alloc_fn) { + if (pol->cpd_free_fn) { list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { if (blkcg->cpd[pol->plid]) { pol->cpd_free_fn(blkcg->cpd[pol->plid]); diff --git a/block/blk-core.c b/block/blk-core.c index 14f7674fa0b1..bb4fce694a60 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -333,6 +333,7 @@ EXPORT_SYMBOL(blk_stop_queue); void blk_sync_queue(struct request_queue *q) { del_timer_sync(&q->timeout); + cancel_work_sync(&q->timeout_work); if (q->mq_ops) { struct blk_mq_hw_ctx *hctx; @@ -718,7 +719,7 @@ static void free_request_size(void *element, void *data) int blk_init_rl(struct request_list *rl, struct request_queue *q, gfp_t gfp_mask) { - if (unlikely(rl->rq_pool)) + if (unlikely(rl->rq_pool) || q->mq_ops) return 0; rl->q = q; @@ -844,6 +845,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) setup_timer(&q->backing_dev_info->laptop_mode_wb_timer, laptop_mode_timer_fn, (unsigned long) q); setup_timer(&q->timeout, blk_rq_timed_out_timer, (unsigned long) q); + INIT_WORK(&q->timeout_work, NULL); INIT_LIST_HEAD(&q->queue_head); INIT_LIST_HEAD(&q->timeout_list); INIT_LIST_HEAD(&q->icq_list); diff --git a/block/blk-lib.c b/block/blk-lib.c index 62240f8832ca..f625fda5f095 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -274,6 +274,40 @@ static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects) return min(pages, (sector_t)BIO_MAX_PAGES); } +static int __blkdev_issue_zero_pages(struct block_device *bdev, + sector_t sector, sector_t nr_sects, gfp_t gfp_mask, + struct bio **biop) +{ + struct request_queue *q = bdev_get_queue(bdev); + struct bio *bio = *biop; + int bi_size = 0; + unsigned int sz; + + if (!q) + return -ENXIO; + + while (nr_sects != 0) { + bio = next_bio(bio, __blkdev_sectors_to_bio_pages(nr_sects), + gfp_mask); + bio->bi_iter.bi_sector = sector; + bio_set_dev(bio, bdev); + bio_set_op_attrs(bio, REQ_OP_WRITE, 0); + + while (nr_sects != 0) { + sz = min((sector_t) PAGE_SIZE, nr_sects << 9); + bi_size = bio_add_page(bio, ZERO_PAGE(0), sz, 0); + nr_sects -= bi_size >> 9; + sector += bi_size >> 9; + if (bi_size < sz) + break; + } + cond_resched(); + } + + *biop = bio; + return 0; +} + /** * __blkdev_issue_zeroout - generate number of zero filed write bios * @bdev: blockdev to issue @@ -287,12 +321,6 @@ static unsigned int __blkdev_sectors_to_bio_pages(sector_t nr_sects) * Zero-fill a block range, either using hardware offload or by explicitly * writing zeroes to the device. * - * Note that this function may fail with -EOPNOTSUPP if the driver signals - * zeroing offload support, but the device fails to process the command (for - * some devices there is no non-destructive way to verify whether this - * operation is actually supported). In this case the caller should call - * retry the call to blkdev_issue_zeroout() and the fallback path will be used. - * * If a device is using logical block provisioning, the underlying space will * not be released if %flags contains BLKDEV_ZERO_NOUNMAP. * @@ -304,9 +332,6 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, unsigned flags) { int ret; - int bi_size = 0; - struct bio *bio = *biop; - unsigned int sz; sector_t bs_mask; bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; @@ -316,30 +341,10 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, gfp_mask, biop, flags); if (ret != -EOPNOTSUPP || (flags & BLKDEV_ZERO_NOFALLBACK)) - goto out; - - ret = 0; - while (nr_sects != 0) { - bio = next_bio(bio, __blkdev_sectors_to_bio_pages(nr_sects), - gfp_mask); - bio->bi_iter.bi_sector = sector; - bio_set_dev(bio, bdev); - bio_set_op_attrs(bio, REQ_OP_WRITE, 0); - - while (nr_sects != 0) { - sz = min((sector_t) PAGE_SIZE, nr_sects << 9); - bi_size = bio_add_page(bio, ZERO_PAGE(0), sz, 0); - nr_sects -= bi_size >> 9; - sector += bi_size >> 9; - if (bi_size < sz) - break; - } - cond_resched(); - } + return ret; - *biop = bio; -out: - return ret; + return __blkdev_issue_zero_pages(bdev, sector, nr_sects, gfp_mask, + biop); } EXPORT_SYMBOL(__blkdev_issue_zeroout); @@ -359,18 +364,49 @@ EXPORT_SYMBOL(__blkdev_issue_zeroout); int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned flags) { - int ret; - struct bio *bio = NULL; + int ret = 0; + sector_t bs_mask; + struct bio *bio; struct blk_plug plug; + bool try_write_zeroes = !!bdev_write_zeroes_sectors(bdev); + bs_mask = (bdev_logical_block_size(bdev) >> 9) - 1; + if ((sector | nr_sects) & bs_mask) + return -EINVAL; + +retry: + bio = NULL; blk_start_plug(&plug); - ret = __blkdev_issue_zeroout(bdev, sector, nr_sects, gfp_mask, - &bio, flags); + if (try_write_zeroes) { + ret = __blkdev_issue_write_zeroes(bdev, sector, nr_sects, + gfp_mask, &bio, flags); + } else if (!(flags & BLKDEV_ZERO_NOFALLBACK)) { + ret = __blkdev_issue_zero_pages(bdev, sector, nr_sects, + gfp_mask, &bio); + } else { + /* No zeroing offload support */ + ret = -EOPNOTSUPP; + } if (ret == 0 && bio) { ret = submit_bio_wait(bio); bio_put(bio); } blk_finish_plug(&plug); + if (ret && try_write_zeroes) { + if (!(flags & BLKDEV_ZERO_NOFALLBACK)) { + try_write_zeroes = false; + goto retry; + } + if (!bdev_write_zeroes_sectors(bdev)) { + /* + * Zeroing offload support was indicated, but the + * device reported ILLEGAL REQUEST (for some devices + * there is no non-destructive way to verify whether + * WRITE ZEROES is actually supported). + */ + ret = -EOPNOTSUPP; + } + } return ret; } diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 980e73095643..7f4a1ba532af 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -54,7 +54,6 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(NOMERGES), QUEUE_FLAG_NAME(SAME_COMP), QUEUE_FLAG_NAME(FAIL_IO), - QUEUE_FLAG_NAME(STACKABLE), QUEUE_FLAG_NAME(NONROT), QUEUE_FLAG_NAME(IO_STAT), QUEUE_FLAG_NAME(DISCARD), diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 4ab69435708c..7775f6b12fa9 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -68,33 +68,123 @@ static void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx) set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); } -static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx) +void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx) { if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) - return false; - - if (hctx->flags & BLK_MQ_F_TAG_SHARED) { - struct request_queue *q = hctx->queue; + return; - if (test_and_clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state)) - atomic_dec(&q->shared_hctx_restart); - } else - clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); + clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state); if (blk_mq_hctx_has_pending(hctx)) { blk_mq_run_hw_queue(hctx, true); - return true; + return; } +} - return false; +/* + * Only SCSI implements .get_budget and .put_budget, and SCSI restarts + * its queue by itself in its completion handler, so we don't need to + * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE. + */ +static void blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) +{ + struct request_queue *q = hctx->queue; + struct elevator_queue *e = q->elevator; + LIST_HEAD(rq_list); + + do { + struct request *rq; + blk_status_t ret; + + if (e->type->ops.mq.has_work && + !e->type->ops.mq.has_work(hctx)) + break; + + ret = blk_mq_get_dispatch_budget(hctx); + if (ret == BLK_STS_RESOURCE) + break; + + rq = e->type->ops.mq.dispatch_request(hctx); + if (!rq) { + blk_mq_put_dispatch_budget(hctx); + break; + } else if (ret != BLK_STS_OK) { + blk_mq_end_request(rq, ret); + continue; + } + + /* + * Now this rq owns the budget which has to be released + * if this rq won't be queued to driver via .queue_rq() + * in blk_mq_dispatch_rq_list(). + */ + list_add(&rq->queuelist, &rq_list); + } while (blk_mq_dispatch_rq_list(q, &rq_list, true)); +} + +static struct blk_mq_ctx *blk_mq_next_ctx(struct blk_mq_hw_ctx *hctx, + struct blk_mq_ctx *ctx) +{ + unsigned idx = ctx->index_hw; + + if (++idx == hctx->nr_ctx) + idx = 0; + + return hctx->ctxs[idx]; } +/* + * Only SCSI implements .get_budget and .put_budget, and SCSI restarts + * its queue by itself in its completion handler, so we don't need to + * restart queue if .get_budget() returns BLK_STS_NO_RESOURCE. + */ +static void blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) +{ + struct request_queue *q = hctx->queue; + LIST_HEAD(rq_list); + struct blk_mq_ctx *ctx = READ_ONCE(hctx->dispatch_from); + + do { + struct request *rq; + blk_status_t ret; + + if (!sbitmap_any_bit_set(&hctx->ctx_map)) + break; + + ret = blk_mq_get_dispatch_budget(hctx); + if (ret == BLK_STS_RESOURCE) + break; + + rq = blk_mq_dequeue_from_ctx(hctx, ctx); + if (!rq) { + blk_mq_put_dispatch_budget(hctx); + break; + } else if (ret != BLK_STS_OK) { + blk_mq_end_request(rq, ret); + continue; + } + + /* + * Now this rq owns the budget which has to be released + * if this rq won't be queued to driver via .queue_rq() + * in blk_mq_dispatch_rq_list(). + */ + list_add(&rq->queuelist, &rq_list); + + /* round robin for fair dispatch */ + ctx = blk_mq_next_ctx(hctx, rq->mq_ctx); + + } while (blk_mq_dispatch_rq_list(q, &rq_list, true)); + + WRITE_ONCE(hctx->dispatch_from, ctx); +} + +/* return true if hw queue need to be run again */ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) { struct request_queue *q = hctx->queue; struct elevator_queue *e = q->elevator; const bool has_sched_dispatch = e && e->type->ops.mq.dispatch_request; - bool did_work = false; LIST_HEAD(rq_list); /* RCU or SRCU read lock is needed before checking quiesced flag */ @@ -122,29 +212,34 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx) * scheduler, we can no longer merge or sort them. So it's best to * leave them there for as long as we can. Mark the hw queue as * needing a restart in that case. + * + * We want to dispatch from the scheduler if there was nothing + * on the dispatch list or we were able to dispatch from the + * dispatch list. */ if (!list_empty(&rq_list)) { blk_mq_sched_mark_restart_hctx(hctx); - did_work = blk_mq_dispatch_rq_list(q, &rq_list); - } else if (!has_sched_dispatch) { + if (blk_mq_dispatch_rq_list(q, &rq_list, false)) { + if (has_sched_dispatch) + blk_mq_do_dispatch_sched(hctx); + else + blk_mq_do_dispatch_ctx(hctx); + } + } else if (has_sched_dispatch) { + blk_mq_do_dispatch_sched(hctx); + } else if (q->mq_ops->get_budget) { + /* + * If we need to get budget before queuing request, we + * dequeue request one by one from sw queue for avoiding + * to mess up I/O merge when dispatch runs out of resource. + * + * TODO: get more budgets, and dequeue more requests in + * one time. + */ + blk_mq_do_dispatch_ctx(hctx); + } else { blk_mq_flush_busy_ctxs(hctx, &rq_list); - blk_mq_dispatch_rq_list(q, &rq_list); - } - - /* - * We want to dispatch from the scheduler if we had no work left - * on the dispatch list, OR if we did have work but weren't able - * to make progress. - */ - if (!did_work && has_sched_dispatch) { - do { - struct request *rq; - - rq = e->type->ops.mq.dispatch_request(hctx); - if (!rq) - break; - list_add(&rq->queuelist, &rq_list); - } while (blk_mq_dispatch_rq_list(q, &rq_list)); + blk_mq_dispatch_rq_list(q, &rq_list, false); } } @@ -277,68 +372,6 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx, return true; } -/** - * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list - * @pos: loop cursor. - * @skip: the list element that will not be examined. Iteration starts at - * @skip->next. - * @head: head of the list to examine. This list must have at least one - * element, namely @skip. - * @member: name of the list_head structure within typeof(*pos). - */ -#define list_for_each_entry_rcu_rr(pos, skip, head, member) \ - for ((pos) = (skip); \ - (pos = (pos)->member.next != (head) ? list_entry_rcu( \ - (pos)->member.next, typeof(*pos), member) : \ - list_entry_rcu((pos)->member.next->next, typeof(*pos), member)), \ - (pos) != (skip); ) - -/* - * Called after a driver tag has been freed to check whether a hctx needs to - * be restarted. Restarts @hctx if its tag set is not shared. Restarts hardware - * queues in a round-robin fashion if the tag set of @hctx is shared with other - * hardware queues. - */ -void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx) -{ - struct blk_mq_tags *const tags = hctx->tags; - struct blk_mq_tag_set *const set = hctx->queue->tag_set; - struct request_queue *const queue = hctx->queue, *q; - struct blk_mq_hw_ctx *hctx2; - unsigned int i, j; - - if (set->flags & BLK_MQ_F_TAG_SHARED) { - /* - * If this is 0, then we know that no hardware queues - * have RESTART marked. We're done. - */ - if (!atomic_read(&queue->shared_hctx_restart)) - return; - - rcu_read_lock(); - list_for_each_entry_rcu_rr(q, queue, &set->tag_list, - tag_set_list) { - queue_for_each_hw_ctx(q, hctx2, i) - if (hctx2->tags == tags && - blk_mq_sched_restart_hctx(hctx2)) - goto done; - } - j = hctx->queue_num + 1; - for (i = 0; i < queue->nr_hw_queues; i++, j++) { - if (j == queue->nr_hw_queues) - j = 0; - hctx2 = queue->queue_hw_ctx[j]; - if (hctx2->tags == tags && - blk_mq_sched_restart_hctx(hctx2)) - break; - } -done: - rcu_read_unlock(); - } else { - blk_mq_sched_restart_hctx(hctx); - } -} - /* * Add flush/fua to the queue. If we fail getting a driver tag, then * punt to the requeue list. Requeue will re-invoke us from a context diff --git a/block/blk-mq.c b/block/blk-mq.c index 7f01d69879d6..e4d2490f4e7e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -481,6 +481,9 @@ void blk_mq_free_request(struct request *rq) wbt_done(q->rq_wb, &rq->issue_stat); + if (blk_rq_rl(rq)) + blk_put_rl(blk_rq_rl(rq)); + clear_bit(REQ_ATOM_STARTED, &rq->atomic_flags); clear_bit(REQ_ATOM_POLL_SLEPT, &rq->atomic_flags); if (rq->tag != -1) @@ -596,22 +599,32 @@ void blk_mq_start_request(struct request *rq) blk_add_timer(rq); - /* - * Ensure that ->deadline is visible before set the started - * flag and clear the completed flag. - */ - smp_mb__before_atomic(); + WARN_ON_ONCE(test_bit(REQ_ATOM_STARTED, &rq->atomic_flags)); /* * Mark us as started and clear complete. Complete might have been * set if requeue raced with timeout, which then marked it as * complete. So be sure to clear complete again when we start * the request, otherwise we'll ignore the completion event. + * + * Ensure that ->deadline is visible before we set STARTED, such that + * blk_mq_check_expired() is guaranteed to observe our ->deadline when + * it observes STARTED. */ - if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) - set_bit(REQ_ATOM_STARTED, &rq->atomic_flags); - if (test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags)) + smp_wmb(); + set_bit(REQ_ATOM_STARTED, &rq->atomic_flags); + if (test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags)) { + /* + * Coherence order guarantees these consecutive stores to a + * single variable propagate in the specified order. Thus the + * clear_bit() is ordered _after_ the set bit. See + * blk_mq_check_expired(). + * + * (the bits must be part of the same byte for this to be + * true). + */ clear_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags); + } if (q->dma_drain_size && blk_rq_bytes(rq)) { /* @@ -781,11 +794,20 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, struct request *rq, void *priv, bool reserved) { struct blk_mq_timeout_data *data = priv; + unsigned long deadline; if (!test_bit(REQ_ATOM_STARTED, &rq->atomic_flags)) return; /* + * Ensures that if we see STARTED we must also see our + * up-to-date deadline, see blk_mq_start_request(). + */ + smp_rmb(); + + deadline = READ_ONCE(rq->deadline); + + /* * The rq being checked may have been freed and reallocated * out already here, we avoid this race by checking rq->deadline * and REQ_ATOM_COMPLETE flag together: @@ -798,11 +820,20 @@ static void blk_mq_check_expired(struct blk_mq_hw_ctx *hctx, * and clearing the flag in blk_mq_start_request(), so * this rq won't be timed out too. */ - if (time_after_eq(jiffies, rq->deadline)) { - if (!blk_mark_rq_complete(rq)) + if (time_after_eq(jiffies, deadline)) { + if (!blk_mark_rq_complete(rq)) { + /* + * Again coherence order ensures that consecutive reads + * from the same variable must be in that order. This + * ensures that if we see COMPLETE clear, we must then + * see STARTED set and we'll ignore this timeout. + * + * (There's also the MB implied by the test_and_clear()) + */ blk_mq_rq_timed_out(rq, reserved); - } else if (!data->next_set || time_after(data->next, rq->deadline)) { - data->next = rq->deadline; + } + } else if (!data->next_set || time_after(data->next, deadline)) { + data->next = deadline; data->next_set = 1; } } @@ -883,6 +914,45 @@ void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list) } EXPORT_SYMBOL_GPL(blk_mq_flush_busy_ctxs); +struct dispatch_rq_data { + struct blk_mq_hw_ctx *hctx; + struct request *rq; +}; + +static bool dispatch_rq_from_ctx(struct sbitmap *sb, unsigned int bitnr, + void *data) +{ + struct dispatch_rq_data *dispatch_data = data; + struct blk_mq_hw_ctx *hctx = dispatch_data->hctx; + struct blk_mq_ctx *ctx = hctx->ctxs[bitnr]; + + spin_lock(&ctx->lock); + if (unlikely(!list_empty(&ctx->rq_list))) { + dispatch_data->rq = list_entry_rq(ctx->rq_list.next); + list_del_init(&dispatch_data->rq->queuelist); + if (list_empty(&ctx->rq_list)) + sbitmap_clear_bit(sb, bitnr); + } + spin_unlock(&ctx->lock); + + return !dispatch_data->rq; +} + +struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, + struct blk_mq_ctx *start) +{ + unsigned off = start ? start->index_hw : 0; + struct dispatch_rq_data data = { + .hctx = hctx, + .rq = NULL, + }; + + __sbitmap_for_each_set(&hctx->ctx_map, off, + dispatch_rq_from_ctx, &data); + + return data.rq; +} + static inline unsigned int queued_to_index(unsigned int queued) { if (!queued) @@ -1017,7 +1087,8 @@ static bool blk_mq_dispatch_wait_add(struct blk_mq_hw_ctx *hctx) return true; } -bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list) +bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, + bool got_budget) { struct blk_mq_hw_ctx *hctx; struct request *rq; @@ -1026,6 +1097,8 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list) if (list_empty(list)) return false; + WARN_ON(!list_is_singular(list) && got_budget); + /* * Now process all the entries, sending them to the driver. */ @@ -1043,16 +1116,30 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list) * The initial allocation attempt failed, so we need to * rerun the hardware queue when a tag is freed. */ - if (!blk_mq_dispatch_wait_add(hctx)) + if (!blk_mq_dispatch_wait_add(hctx)) { + if (got_budget) + blk_mq_put_dispatch_budget(hctx); break; + } /* * It's possible that a tag was freed in the window * between the allocation failure and adding the * hardware queue to the wait queue. */ - if (!blk_mq_get_driver_tag(rq, &hctx, false)) + if (!blk_mq_get_driver_tag(rq, &hctx, false)) { + if (got_budget) + blk_mq_put_dispatch_budget(hctx); break; + } + } + + if (!got_budget) { + ret = blk_mq_get_dispatch_budget(hctx); + if (ret == BLK_STS_RESOURCE) + break; + if (ret != BLK_STS_OK) + goto fail_rq; } list_del_init(&rq->queuelist); @@ -1080,6 +1167,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list) break; } + fail_rq: if (unlikely(ret != BLK_STS_OK)) { errors++; blk_mq_end_request(rq, BLK_STS_IOERR); @@ -1504,6 +1592,8 @@ static void blk_mq_bio_to_request(struct request *rq, struct bio *bio) { blk_init_request_from_bio(rq, bio); + blk_rq_set_rl(rq, blk_get_rl(rq->q, bio)); + blk_account_io_start(rq, true); } @@ -1549,6 +1639,13 @@ static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, if (!blk_mq_get_driver_tag(rq, NULL, false)) goto insert; + ret = blk_mq_get_dispatch_budget(hctx); + if (ret == BLK_STS_RESOURCE) { + blk_mq_put_driver_tag(rq); + goto insert; + } else if (ret != BLK_STS_OK) + goto fail_rq; + new_cookie = request_to_qc_t(hctx, rq); /* @@ -1565,6 +1662,7 @@ static void __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, __blk_mq_requeue_request(rq); goto insert; default: + fail_rq: *cookie = BLK_QC_T_NONE; blk_mq_end_request(rq, ret); return; @@ -2549,6 +2647,9 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) if (!set->ops->queue_rq) return -EINVAL; + if (!set->ops->get_budget ^ !set->ops->put_budget) + return -EINVAL; + if (set->queue_depth > BLK_MQ_MAX_DEPTH) { pr_info("blk-mq: reduced tag depth to %u\n", BLK_MQ_MAX_DEPTH); @@ -2895,6 +2996,12 @@ EXPORT_SYMBOL_GPL(blk_mq_poll); static int __init blk_mq_init(void) { + /* + * See comment in block/blk.h rq_atomic_flags enum + */ + BUILD_BUG_ON((REQ_ATOM_STARTED / BITS_PER_BYTE) != + (REQ_ATOM_COMPLETE / BITS_PER_BYTE)); + cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL, blk_mq_hctx_notify_dead); return 0; diff --git a/block/blk-mq.h b/block/blk-mq.h index ef15b3414da5..522b420dedc0 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -30,11 +30,13 @@ void blk_mq_freeze_queue(struct request_queue *q); void blk_mq_free_queue(struct request_queue *q); int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr); void blk_mq_wake_waiters(struct request_queue *q); -bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *); +bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool); void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list); bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx); bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx, bool wait); +struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, + struct blk_mq_ctx *start); /* * Internal helpers for allocating/freeing the request map @@ -137,4 +139,22 @@ static inline bool blk_mq_hw_queue_mapped(struct blk_mq_hw_ctx *hctx) void blk_mq_in_flight(struct request_queue *q, struct hd_struct *part, unsigned int inflight[2]); +static inline void blk_mq_put_dispatch_budget(struct blk_mq_hw_ctx *hctx) +{ + struct request_queue *q = hctx->queue; + + if (q->mq_ops->put_budget) + q->mq_ops->put_budget(hctx); +} + +static inline blk_status_t blk_mq_get_dispatch_budget( + struct blk_mq_hw_ctx *hctx) +{ + struct request_queue *q = hctx->queue; + + if (q->mq_ops->get_budget) + return q->mq_ops->get_budget(hctx); + return BLK_STS_OK; +} + #endif diff --git a/block/blk-stat.c b/block/blk-stat.c index c52356d90fe3..3a2f3c96f367 100644 --- a/block/blk-stat.c +++ b/block/blk-stat.c @@ -11,8 +11,6 @@ #include "blk-mq.h" #include "blk.h" -#define BLK_RQ_STAT_BATCH 64 - struct blk_queue_stats { struct list_head callbacks; spinlock_t lock; @@ -23,45 +21,21 @@ static void blk_stat_init(struct blk_rq_stat *stat) { stat->min = -1ULL; stat->max = stat->nr_samples = stat->mean = 0; - stat->batch = stat->nr_batch = 0; -} - -static void blk_stat_flush_batch(struct blk_rq_stat *stat) -{ - const s32 nr_batch = READ_ONCE(stat->nr_batch); - const s32 nr_samples = READ_ONCE(stat->nr_samples); - - if (!nr_batch) - return; - if (!nr_samples) - stat->mean = div64_s64(stat->batch, nr_batch); - else { - stat->mean = div64_s64((stat->mean * nr_samples) + - stat->batch, - nr_batch + nr_samples); - } - - stat->nr_samples += nr_batch; - stat->nr_batch = stat->batch = 0; + stat->batch = 0; } +/* src is a per-cpu stat, mean isn't initialized */ static void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src) { - blk_stat_flush_batch(src); - if (!src->nr_samples) return; dst->min = min(dst->min, src->min); dst->max = max(dst->max, src->max); - if (!dst->nr_samples) - dst->mean = src->mean; - else { - dst->mean = div64_s64((src->mean * src->nr_samples) + - (dst->mean * dst->nr_samples), - dst->nr_samples + src->nr_samples); - } + dst->mean = div_u64(src->batch + dst->mean * dst->nr_samples, + dst->nr_samples + src->nr_samples); + dst->nr_samples += src->nr_samples; } @@ -69,13 +43,8 @@ static void __blk_stat_add(struct blk_rq_stat *stat, u64 value) { stat->min = min(stat->min, value); stat->max = max(stat->max, value); - - if (stat->batch + value < stat->batch || - stat->nr_batch + 1 == BLK_RQ_STAT_BATCH) - blk_stat_flush_batch(stat); - stat->batch += value; - stat->nr_batch++; + stat->nr_samples++; } void blk_stat_add(struct request *rq) @@ -84,7 +53,7 @@ void blk_stat_add(struct request *rq) struct blk_stat_callback *cb; struct blk_rq_stat *stat; int bucket; - s64 now, value; + u64 now, value; now = __blk_stat_time(ktime_to_ns(ktime_get())); if (now < blk_stat_time(&rq->issue_stat)) diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 0fea76aa0f3f..fe49c465ec86 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -2112,8 +2112,12 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td) static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio) { #ifdef CONFIG_BLK_DEV_THROTTLING_LOW - if (bio->bi_css) + if (bio->bi_css) { + if (bio->bi_cg_private) + blkg_put(tg_to_blkg(bio->bi_cg_private)); bio->bi_cg_private = tg; + blkg_get(tg_to_blkg(tg)); + } blk_stat_set_issue(&bio->bi_issue_stat, bio_sectors(bio)); #endif } @@ -2283,8 +2287,10 @@ void blk_throtl_bio_endio(struct bio *bio) start_time = blk_stat_time(&bio->bi_issue_stat) >> 10; finish_time = __blk_stat_time(finish_time_ns) >> 10; - if (!start_time || finish_time <= start_time) + if (!start_time || finish_time <= start_time) { + blkg_put(tg_to_blkg(tg)); return; + } lat = finish_time - start_time; /* this is only for bio based driver */ @@ -2314,6 +2320,8 @@ void blk_throtl_bio_endio(struct bio *bio) tg->bio_cnt /= 2; tg->bad_bio_cnt /= 2; } + + blkg_put(tg_to_blkg(tg)); } #endif diff --git a/block/blk-timeout.c b/block/blk-timeout.c index 17ec83bb0900..764ecf9aeb30 100644 --- a/block/blk-timeout.c +++ b/block/blk-timeout.c @@ -134,8 +134,6 @@ void blk_timeout_work(struct work_struct *work) struct request *rq, *tmp; int next_set = 0; - if (blk_queue_enter(q, true)) - return; spin_lock_irqsave(q->queue_lock, flags); list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list) @@ -145,7 +143,6 @@ void blk_timeout_work(struct work_struct *work) mod_timer(&q->timeout, round_jiffies_up(next)); spin_unlock_irqrestore(q->queue_lock, flags); - blk_queue_exit(q); } /** @@ -211,7 +208,7 @@ void blk_add_timer(struct request *req) if (!req->timeout) req->timeout = q->rq_timeout; - req->deadline = jiffies + req->timeout; + WRITE_ONCE(req->deadline, jiffies + req->timeout); /* * Only the non-mq case needs to add the request to a protected list. diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 6a9a0f03a67b..e59d59c11ebb 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -654,7 +654,7 @@ void wbt_set_write_cache(struct rq_wb *rwb, bool write_cache_on) } /* - * Disable wbt, if enabled by default. Only called from CFQ. + * Disable wbt, if enabled by default. */ void wbt_disable_default(struct request_queue *q) { diff --git a/block/blk.h b/block/blk.h index fda5a4632aba..6ac43dfd68a7 100644 --- a/block/blk.h +++ b/block/blk.h @@ -122,8 +122,15 @@ void blk_account_io_done(struct request *req); * Internal atomic flags for request handling */ enum rq_atomic_flags { + /* + * Keep these two bits first - not because we depend on the + * value of them, but we do depend on them being in the same + * byte of storage to ensure ordering on writes. Keeping them + * first will achieve that nicely. + */ REQ_ATOM_COMPLETE = 0, REQ_ATOM_STARTED, + REQ_ATOM_POLL_SLEPT, }; diff --git a/block/elevator.c b/block/elevator.c index 153926a90901..7bda083d5968 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -83,12 +83,25 @@ bool elv_bio_merge_ok(struct request *rq, struct bio *bio) } EXPORT_SYMBOL(elv_bio_merge_ok); -static struct elevator_type *elevator_find(const char *name) +static bool elevator_match(const struct elevator_type *e, const char *name) +{ + if (!strcmp(e->elevator_name, name)) + return true; + if (e->elevator_alias && !strcmp(e->elevator_alias, name)) + return true; + + return false; +} + +/* + * Return scheduler with name 'name' and with matching 'mq capability + */ +static struct elevator_type *elevator_find(const char *name, bool mq) { struct elevator_type *e; list_for_each_entry(e, &elv_list, list) { - if (!strcmp(e->elevator_name, name)) + if (elevator_match(e, name) && (mq == e->uses_mq)) return e; } @@ -100,25 +113,25 @@ static void elevator_put(struct elevator_type *e) module_put(e->elevator_owner); } -static struct elevator_type *elevator_get(const char *name, bool try_loading) +static struct elevator_type *elevator_get(struct request_queue *q, + const char *name, bool try_loading) { struct elevator_type *e; spin_lock(&elv_list_lock); - e = elevator_find(name); + e = elevator_find(name, q->mq_ops != NULL); if (!e && try_loading) { spin_unlock(&elv_list_lock); request_module("%s-iosched", name); spin_lock(&elv_list_lock); - e = elevator_find(name); + e = elevator_find(name, q->mq_ops != NULL); } if (e && !try_module_get(e->elevator_owner)) e = NULL; spin_unlock(&elv_list_lock); - return e; } @@ -144,8 +157,12 @@ void __init load_default_elevator_module(void) if (!chosen_elevator[0]) return; + /* + * Boot parameter is deprecated, we haven't supported that for MQ. + * Only look for non-mq schedulers from here. + */ spin_lock(&elv_list_lock); - e = elevator_find(chosen_elevator); + e = elevator_find(chosen_elevator, false); spin_unlock(&elv_list_lock); if (!e) @@ -202,7 +219,7 @@ int elevator_init(struct request_queue *q, char *name) q->boundary_rq = NULL; if (name) { - e = elevator_get(name, true); + e = elevator_get(q, name, true); if (!e) return -EINVAL; } @@ -214,7 +231,7 @@ int elevator_init(struct request_queue *q, char *name) * allowed from async. */ if (!e && !q->mq_ops && *chosen_elevator) { - e = elevator_get(chosen_elevator, false); + e = elevator_get(q, chosen_elevator, false); if (!e) printk(KERN_ERR "I/O scheduler %s not found\n", chosen_elevator); @@ -229,17 +246,17 @@ int elevator_init(struct request_queue *q, char *name) */ if (q->mq_ops) { if (q->nr_hw_queues == 1) - e = elevator_get("mq-deadline", false); + e = elevator_get(q, "mq-deadline", false); if (!e) return 0; } else - e = elevator_get(CONFIG_DEFAULT_IOSCHED, false); + e = elevator_get(q, CONFIG_DEFAULT_IOSCHED, false); if (!e) { printk(KERN_ERR "Default I/O scheduler not found. " \ "Using noop.\n"); - e = elevator_get("noop", false); + e = elevator_get(q, "noop", false); } } @@ -905,7 +922,7 @@ int elv_register(struct elevator_type *e) /* register, don't allow duplicate names */ spin_lock(&elv_list_lock); - if (elevator_find(e->elevator_name)) { + if (elevator_find(e->elevator_name, e->uses_mq)) { spin_unlock(&elv_list_lock); if (e->icq_cache) kmem_cache_destroy(e->icq_cache); @@ -915,9 +932,9 @@ int elv_register(struct elevator_type *e) spin_unlock(&elv_list_lock); /* print pretty message */ - if (!strcmp(e->elevator_name, chosen_elevator) || + if (elevator_match(e, chosen_elevator) || (!*chosen_elevator && - !strcmp(e->elevator_name, CONFIG_DEFAULT_IOSCHED))) + elevator_match(e, CONFIG_DEFAULT_IOSCHED))) def = " (default)"; printk(KERN_INFO "io scheduler %s registered%s\n", e->elevator_name, @@ -1066,25 +1083,15 @@ static int __elevator_change(struct request_queue *q, const char *name) return elevator_switch(q, NULL); strlcpy(elevator_name, name, sizeof(elevator_name)); - e = elevator_get(strstrip(elevator_name), true); + e = elevator_get(q, strstrip(elevator_name), true); if (!e) return -EINVAL; - if (q->elevator && - !strcmp(elevator_name, q->elevator->type->elevator_name)) { + if (q->elevator && elevator_match(q->elevator->type, elevator_name)) { elevator_put(e); return 0; } - if (!e->uses_mq && q->mq_ops) { - elevator_put(e); - return -EINVAL; - } - if (e->uses_mq && !q->mq_ops) { - elevator_put(e); - return -EINVAL; - } - return elevator_switch(q, e); } @@ -1116,9 +1123,10 @@ ssize_t elv_iosched_show(struct request_queue *q, char *name) struct elevator_queue *e = q->elevator; struct elevator_type *elv = NULL; struct elevator_type *__e; + bool uses_mq = q->mq_ops != NULL; int len = 0; - if (!blk_queue_stackable(q)) + if (!queue_is_rq_based(q)) return sprintf(name, "none\n"); if (!q->elevator) @@ -1128,7 +1136,8 @@ ssize_t elv_iosched_show(struct request_queue *q, char *name) spin_lock(&elv_list_lock); list_for_each_entry(__e, &elv_list, list) { - if (elv && !strcmp(elv->elevator_name, __e->elevator_name)) { + if (elv && elevator_match(elv, __e->elevator_name) && + (__e->uses_mq == uses_mq)) { len += sprintf(name+len, "[%s] ", elv->elevator_name); continue; } diff --git a/block/ioctl.c b/block/ioctl.c index 0de02ee67eed..1668506d8ed8 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -202,10 +202,16 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, { uint64_t range[2]; uint64_t start, len; + struct request_queue *q = bdev_get_queue(bdev); + struct address_space *mapping = bdev->bd_inode->i_mapping; + if (!(mode & FMODE_WRITE)) return -EBADF; + if (!blk_queue_discard(q)) + return -EOPNOTSUPP; + if (copy_from_user(range, (void __user *)arg, sizeof(range))) return -EFAULT; @@ -216,12 +222,12 @@ static int blk_ioctl_discard(struct block_device *bdev, fmode_t mode, return -EINVAL; if (len & 511) return -EINVAL; - start >>= 9; - len >>= 9; - if (start + len > (i_size_read(bdev->bd_inode) >> 9)) + if (start + len > i_size_read(bdev->bd_inode)) return -EINVAL; - return blkdev_issue_discard(bdev, start, len, GFP_KERNEL, flags); + truncate_inode_pages_range(mapping, start, start + len); + return blkdev_issue_discard(bdev, start >> 9, len >> 9, + GFP_KERNEL, flags); } static int blk_ioctl_zeroout(struct block_device *bdev, fmode_t mode, @@ -437,11 +443,12 @@ static int blkdev_roset(struct block_device *bdev, fmode_t mode, { int ret, n; + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + ret = __blkdev_driver_ioctl(bdev, mode, cmd, arg); if (!is_unrecognized_ioctl(ret)) return ret; - if (!capable(CAP_SYS_ADMIN)) - return -EACCES; if (get_user(n, (int __user *)arg)) return -EFAULT; set_device_ro(bdev, n); diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index f58cab82105b..b4df317c2916 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -541,9 +541,17 @@ static int kyber_get_domain_token(struct kyber_queue_data *kqd, /* * Try again in case a token was freed before we got on the wait - * queue. + * queue. The waker may have already removed the entry from the + * wait queue, but list_del_init() is okay with that. */ nr = __sbitmap_queue_get(domain_tokens); + if (nr >= 0) { + unsigned long flags; + + spin_lock_irqsave(&ws->wait.lock, flags); + list_del_init(&wait->entry); + spin_unlock_irqrestore(&ws->wait.lock, flags); + } } return nr; } @@ -641,7 +649,7 @@ static bool kyber_has_work(struct blk_mq_hw_ctx *hctx) if (!list_empty_careful(&khd->rqs[i])) return true; } - return false; + return sbitmap_any_bit_set(&hctx->ctx_map); } #define KYBER_LAT_SHOW_STORE(op) \ diff --git a/block/mq-deadline.c b/block/mq-deadline.c index a1cad4331edd..0179e484ec98 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -657,6 +657,7 @@ static struct elevator_type mq_deadline = { #endif .elevator_attrs = deadline_attrs, .elevator_name = "mq-deadline", + .elevator_alias = "deadline", .elevator_owner = THIS_MODULE, }; MODULE_ALIAS("mq-deadline-iosched"); |