diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-06-30 12:12:56 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-06-30 12:12:56 -0700 |
commit | df668a5fe461bb9d7e899c538acc7197746038f4 (patch) | |
tree | 315a71104f5cea7feeb56c9f2c768453408b72f7 /block/blk-mq-tag.c | |
parent | df04fbe8680bfe07f3d7487eccff9f768bb02533 (diff) | |
parent | 2705dfb2094777e405e065105e307074af8965c1 (diff) | |
download | linux-df668a5fe461bb9d7e899c538acc7197746038f4.tar.gz linux-df668a5fe461bb9d7e899c538acc7197746038f4.tar.bz2 linux-df668a5fe461bb9d7e899c538acc7197746038f4.zip |
Merge tag 'for-5.14/block-2021-06-29' of git://git.kernel.dk/linux-block
Pull core block updates from Jens Axboe:
- disk events cleanup (Christoph)
- gendisk and request queue allocation simplifications (Christoph)
- bdev_disk_changed cleanups (Christoph)
- IO priority improvements (Bart)
- Chained bio completion trace fix (Edward)
- blk-wbt fixes (Jan)
- blk-wbt enable/disable fix (Zhang)
- Scheduler dispatch improvements (Jan, Ming)
- Shared tagset scheduler improvements (John)
- BFQ updates (Paolo, Luca, Pietro)
- BFQ lock inversion fix (Jan)
- Documentation improvements (Kir)
- CLONE_IO block cgroup fix (Tejun)
- Remove of ancient and deprecated block dump feature (zhangyi)
- Discard merge fix (Ming)
- Misc fixes or followup fixes (Colin, Damien, Dan, Long, Max, Thomas,
Yang)
* tag 'for-5.14/block-2021-06-29' of git://git.kernel.dk/linux-block: (129 commits)
block: fix discard request merge
block/mq-deadline: Remove a WARN_ON_ONCE() call
blk-mq: update hctx->dispatch_busy in case of real scheduler
blk: Fix lock inversion between ioc lock and bfqd lock
bfq: Remove merged request already in bfq_requests_merged()
block: pass a gendisk to bdev_disk_changed
block: move bdev_disk_changed
block: add the events* attributes to disk_attrs
block: move the disk events code to a separate file
block: fix trace completion for chained bio
block/partitions/msdos: Fix typo inidicator -> indicator
block, bfq: reset waker pointer with shared queues
block, bfq: check waker only for queues with no in-flight I/O
block, bfq: avoid delayed merge of async queues
block, bfq: boost throughput by extending queue-merging times
block, bfq: consider also creation time in delayed stable merge
block, bfq: fix delayed stable merge check
block, bfq: let also stably merged queues enjoy weight raising
blk-wbt: make sure throttle is enabled properly
blk-wbt: introduce a new disable state to prevent false positive by rwb_enabled()
...
Diffstat (limited to 'block/blk-mq-tag.c')
-rw-r--r-- | block/blk-mq-tag.c | 114 |
1 files changed, 76 insertions, 38 deletions
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 2a37731e8244..86f87346232a 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -13,6 +13,7 @@ #include <linux/delay.h> #include "blk.h" #include "blk-mq.h" +#include "blk-mq-sched.h" #include "blk-mq-tag.h" /* @@ -199,6 +200,20 @@ struct bt_iter_data { bool reserved; }; +static struct request *blk_mq_find_and_get_req(struct blk_mq_tags *tags, + unsigned int bitnr) +{ + struct request *rq; + unsigned long flags; + + spin_lock_irqsave(&tags->lock, flags); + rq = tags->rqs[bitnr]; + if (!rq || !refcount_inc_not_zero(&rq->ref)) + rq = NULL; + spin_unlock_irqrestore(&tags->lock, flags); + return rq; +} + static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) { struct bt_iter_data *iter_data = data; @@ -206,18 +221,22 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) struct blk_mq_tags *tags = hctx->tags; bool reserved = iter_data->reserved; struct request *rq; + bool ret = true; if (!reserved) bitnr += tags->nr_reserved_tags; - rq = tags->rqs[bitnr]; - /* * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ - if (rq && rq->q == hctx->queue && rq->mq_hctx == hctx) - return iter_data->fn(hctx, rq, iter_data->data, reserved); - return true; + rq = blk_mq_find_and_get_req(tags, bitnr); + if (!rq) + return true; + + if (rq->q == hctx->queue && rq->mq_hctx == hctx) + ret = iter_data->fn(hctx, rq, iter_data->data, reserved); + blk_mq_put_rq_ref(rq); + return ret; } /** @@ -264,6 +283,8 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) struct blk_mq_tags *tags = iter_data->tags; bool reserved = iter_data->flags & BT_TAG_ITER_RESERVED; struct request *rq; + bool ret = true; + bool iter_static_rqs = !!(iter_data->flags & BT_TAG_ITER_STATIC_RQS); if (!reserved) bitnr += tags->nr_reserved_tags; @@ -272,16 +293,19 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) * We can hit rq == NULL here, because the tagging functions * test and set the bit before assigning ->rqs[]. */ - if (iter_data->flags & BT_TAG_ITER_STATIC_RQS) + if (iter_static_rqs) rq = tags->static_rqs[bitnr]; else - rq = tags->rqs[bitnr]; + rq = blk_mq_find_and_get_req(tags, bitnr); if (!rq) return true; - if ((iter_data->flags & BT_TAG_ITER_STARTED) && - !blk_mq_request_started(rq)) - return true; - return iter_data->fn(rq, iter_data->data, reserved); + + if (!(iter_data->flags & BT_TAG_ITER_STARTED) || + blk_mq_request_started(rq)) + ret = iter_data->fn(rq, iter_data->data, reserved); + if (!iter_static_rqs) + blk_mq_put_rq_ref(rq); + return ret; } /** @@ -348,6 +372,9 @@ void blk_mq_all_tag_iter(struct blk_mq_tags *tags, busy_tag_iter_fn *fn, * indicates whether or not @rq is a reserved request. Return * true to continue iterating tags, false to stop. * @priv: Will be passed as second argument to @fn. + * + * We grab one request reference before calling @fn and release it after + * @fn returns. */ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, busy_tag_iter_fn *fn, void *priv) @@ -445,39 +472,54 @@ static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth, node); } -static int blk_mq_init_bitmap_tags(struct blk_mq_tags *tags, - int node, int alloc_policy) +int blk_mq_init_bitmaps(struct sbitmap_queue *bitmap_tags, + struct sbitmap_queue *breserved_tags, + unsigned int queue_depth, unsigned int reserved, + int node, int alloc_policy) { - unsigned int depth = tags->nr_tags - tags->nr_reserved_tags; + unsigned int depth = queue_depth - reserved; bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR; - if (bt_alloc(&tags->__bitmap_tags, depth, round_robin, node)) + if (bt_alloc(bitmap_tags, depth, round_robin, node)) return -ENOMEM; - if (bt_alloc(&tags->__breserved_tags, tags->nr_reserved_tags, - round_robin, node)) + if (bt_alloc(breserved_tags, reserved, round_robin, node)) goto free_bitmap_tags; + return 0; + +free_bitmap_tags: + sbitmap_queue_free(bitmap_tags); + return -ENOMEM; +} + +static int blk_mq_init_bitmap_tags(struct blk_mq_tags *tags, + int node, int alloc_policy) +{ + int ret; + + ret = blk_mq_init_bitmaps(&tags->__bitmap_tags, + &tags->__breserved_tags, + tags->nr_tags, tags->nr_reserved_tags, + node, alloc_policy); + if (ret) + return ret; + tags->bitmap_tags = &tags->__bitmap_tags; tags->breserved_tags = &tags->__breserved_tags; return 0; -free_bitmap_tags: - sbitmap_queue_free(&tags->__bitmap_tags); - return -ENOMEM; } -int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int flags) +int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set) { - unsigned int depth = set->queue_depth - set->reserved_tags; int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags); - bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR; - int i, node = set->numa_node; + int i, ret; - if (bt_alloc(&set->__bitmap_tags, depth, round_robin, node)) - return -ENOMEM; - if (bt_alloc(&set->__breserved_tags, set->reserved_tags, - round_robin, node)) - goto free_bitmap_tags; + ret = blk_mq_init_bitmaps(&set->__bitmap_tags, &set->__breserved_tags, + set->queue_depth, set->reserved_tags, + set->numa_node, alloc_policy); + if (ret) + return ret; for (i = 0; i < set->nr_hw_queues; i++) { struct blk_mq_tags *tags = set->tags[i]; @@ -487,9 +529,6 @@ int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int flags) } return 0; -free_bitmap_tags: - sbitmap_queue_free(&set->__bitmap_tags); - return -ENOMEM; } void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set) @@ -516,6 +555,7 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, tags->nr_tags = total_tags; tags->nr_reserved_tags = reserved_tags; + spin_lock_init(&tags->lock); if (blk_mq_is_sbitmap_shared(flags)) return tags; @@ -551,8 +591,6 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, */ if (tdepth > tags->nr_tags) { struct blk_mq_tag_set *set = hctx->queue->tag_set; - /* Only sched tags can grow, so clear HCTX_SHARED flag */ - unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; struct blk_mq_tags *new; bool ret; @@ -563,21 +601,21 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, * We need some sort of upper limit, set it high enough that * no valid use cases should require more. */ - if (tdepth > 16 * BLKDEV_MAX_RQ) + if (tdepth > MAX_SCHED_RQ) return -EINVAL; new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth, - tags->nr_reserved_tags, flags); + tags->nr_reserved_tags, set->flags); if (!new) return -ENOMEM; ret = blk_mq_alloc_rqs(set, new, hctx->queue_num, tdepth); if (ret) { - blk_mq_free_rq_map(new, flags); + blk_mq_free_rq_map(new, set->flags); return -ENOMEM; } blk_mq_free_rqs(set, *tagsptr, hctx->queue_num); - blk_mq_free_rq_map(*tagsptr, flags); + blk_mq_free_rq_map(*tagsptr, set->flags); *tagsptr = new; } else { /* |