diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-13 12:12:44 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-13 12:12:44 -0700 |
commit | 3ad11d7ac8872b1c8da54494721fad8907ee41f7 (patch) | |
tree | 439d7cb75466978be936250c65a27ff05e82d9bc /block/blk-mq-tag.c | |
parent | 857d64485e7c920364688a8a6dd0ffe5774327b6 (diff) | |
parent | 8858e8d98d5457ba23bcd0d99ce23e272b8b09a1 (diff) | |
download | linux-3ad11d7ac8872b1c8da54494721fad8907ee41f7.tar.bz2 |
Merge tag 'block-5.10-2020-10-12' of git://git.kernel.dk/linux-block
Pull block updates from Jens Axboe:
- Series of merge handling cleanups (Baolin, Christoph)
- Series of blk-throttle fixes and cleanups (Baolin)
- Series cleaning up BDI, seperating the block device from the
backing_dev_info (Christoph)
- Removal of bdget() as a generic API (Christoph)
- Removal of blkdev_get() as a generic API (Christoph)
- Cleanup of is-partition checks (Christoph)
- Series reworking disk revalidation (Christoph)
- Series cleaning up bio flags (Christoph)
- bio crypt fixes (Eric)
- IO stats inflight tweak (Gabriel)
- blk-mq tags fixes (Hannes)
- Buffer invalidation fixes (Jan)
- Allow soft limits for zone append (Johannes)
- Shared tag set improvements (John, Kashyap)
- Allow IOPRIO_CLASS_RT for CAP_SYS_NICE (Khazhismel)
- DM no-wait support (Mike, Konstantin)
- Request allocation improvements (Ming)
- Allow md/dm/bcache to use IO stat helpers (Song)
- Series improving blk-iocost (Tejun)
- Various cleanups (Geert, Damien, Danny, Julia, Tetsuo, Tian, Wang,
Xianting, Yang, Yufen, yangerkun)
* tag 'block-5.10-2020-10-12' of git://git.kernel.dk/linux-block: (191 commits)
block: fix uapi blkzoned.h comments
blk-mq: move cancel of hctx->run_work to the front of blk_exit_queue
blk-mq: get rid of the dead flush handle code path
block: get rid of unnecessary local variable
block: fix comment and add lockdep assert
blk-mq: use helper function to test hw stopped
block: use helper function to test queue register
block: remove redundant mq check
block: invoke blk_mq_exit_sched no matter whether have .exit_sched
percpu_ref: don't refer to ref->data if it isn't allocated
block: ratelimit handle_bad_sector() message
blk-throttle: Re-use the throtl_set_slice_end()
blk-throttle: Open code __throtl_de/enqueue_tg()
blk-throttle: Move service tree validation out of the throtl_rb_first()
blk-throttle: Move the list operation after list validation
blk-throttle: Fix IO hang for a corner case
blk-throttle: Avoid tracking latency if low limit is invalid
blk-throttle: Avoid getting the current time if tg->last_finish_time is 0
blk-throttle: Remove a meaningless parameter for throtl_downgrade_state()
block: Remove redundant 'return' statement
...
Diffstat (limited to 'block/blk-mq-tag.c')
-rw-r--r-- | block/blk-mq-tag.c | 156 |
1 files changed, 111 insertions, 45 deletions
diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 32d82e23b095..9c92053e704d 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -23,9 +23,18 @@ */ bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { - if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) && - !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) - atomic_inc(&hctx->tags->active_queues); + if (blk_mq_is_sbitmap_shared(hctx->flags)) { + struct request_queue *q = hctx->queue; + struct blk_mq_tag_set *set = q->tag_set; + + if (!test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) && + !test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) + atomic_inc(&set->active_queues_shared_sbitmap); + } else { + if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) && + !test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) + atomic_inc(&hctx->tags->active_queues); + } return true; } @@ -35,9 +44,9 @@ bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) */ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve) { - sbitmap_queue_wake_all(&tags->bitmap_tags); + sbitmap_queue_wake_all(tags->bitmap_tags); if (include_reserve) - sbitmap_queue_wake_all(&tags->breserved_tags); + sbitmap_queue_wake_all(tags->breserved_tags); } /* @@ -47,11 +56,19 @@ void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool include_reserve) void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) { struct blk_mq_tags *tags = hctx->tags; - - if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) - return; - - atomic_dec(&tags->active_queues); + struct request_queue *q = hctx->queue; + struct blk_mq_tag_set *set = q->tag_set; + + if (blk_mq_is_sbitmap_shared(hctx->flags)) { + if (!test_and_clear_bit(QUEUE_FLAG_HCTX_ACTIVE, + &q->queue_flags)) + return; + atomic_dec(&set->active_queues_shared_sbitmap); + } else { + if (!test_and_clear_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) + return; + atomic_dec(&tags->active_queues); + } blk_mq_tag_wakeup_all(tags, false); } @@ -59,7 +76,8 @@ void __blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) static int __blk_mq_get_tag(struct blk_mq_alloc_data *data, struct sbitmap_queue *bt) { - if (!data->q->elevator && !hctx_may_queue(data->hctx, bt)) + if (!data->q->elevator && !(data->flags & BLK_MQ_REQ_RESERVED) && + !hctx_may_queue(data->hctx, bt)) return BLK_MQ_NO_TAG; if (data->shallow_depth) @@ -82,10 +100,10 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) WARN_ON_ONCE(1); return BLK_MQ_NO_TAG; } - bt = &tags->breserved_tags; + bt = tags->breserved_tags; tag_offset = 0; } else { - bt = &tags->bitmap_tags; + bt = tags->bitmap_tags; tag_offset = tags->nr_reserved_tags; } @@ -131,9 +149,9 @@ unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data) data->ctx); tags = blk_mq_tags_from_data(data); if (data->flags & BLK_MQ_REQ_RESERVED) - bt = &tags->breserved_tags; + bt = tags->breserved_tags; else - bt = &tags->bitmap_tags; + bt = tags->bitmap_tags; /* * If destination hw queue is changed, fake wake up on @@ -167,10 +185,10 @@ void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, const int real_tag = tag - tags->nr_reserved_tags; BUG_ON(real_tag >= tags->nr_tags); - sbitmap_queue_clear(&tags->bitmap_tags, real_tag, ctx->cpu); + sbitmap_queue_clear(tags->bitmap_tags, real_tag, ctx->cpu); } else { BUG_ON(tag >= tags->nr_reserved_tags); - sbitmap_queue_clear(&tags->breserved_tags, tag, ctx->cpu); + sbitmap_queue_clear(tags->breserved_tags, tag, ctx->cpu); } } @@ -197,7 +215,7 @@ static bool bt_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 (rq && rq->q == hctx->queue) + if (rq && rq->q == hctx->queue && rq->mq_hctx == hctx) return iter_data->fn(hctx, rq, iter_data->data, reserved); return true; } @@ -298,9 +316,9 @@ static void __blk_mq_all_tag_iter(struct blk_mq_tags *tags, WARN_ON_ONCE(flags & BT_TAG_ITER_RESERVED); if (tags->nr_reserved_tags) - bt_tags_for_each(tags, &tags->breserved_tags, fn, priv, + bt_tags_for_each(tags, tags->breserved_tags, fn, priv, flags | BT_TAG_ITER_RESERVED); - bt_tags_for_each(tags, &tags->bitmap_tags, fn, priv, flags); + bt_tags_for_each(tags, tags->bitmap_tags, fn, priv, flags); } /** @@ -398,9 +416,7 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, /* * __blk_mq_update_nr_hw_queues() updates nr_hw_queues and queue_hw_ctx * while the queue is frozen. So we can use q_usage_counter to avoid - * racing with it. __blk_mq_update_nr_hw_queues() uses - * synchronize_rcu() to ensure this function left the critical section - * below. + * racing with it. */ if (!percpu_ref_tryget(&q->q_usage_counter)) return; @@ -416,8 +432,8 @@ void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, continue; if (tags->nr_reserved_tags) - bt_for_each(hctx, &tags->breserved_tags, fn, priv, true); - bt_for_each(hctx, &tags->bitmap_tags, fn, priv, false); + bt_for_each(hctx, tags->breserved_tags, fn, priv, true); + bt_for_each(hctx, tags->bitmap_tags, fn, priv, false); } blk_queue_exit(q); } @@ -429,30 +445,64 @@ static int bt_alloc(struct sbitmap_queue *bt, unsigned int depth, node); } -static struct blk_mq_tags *blk_mq_init_bitmap_tags(struct blk_mq_tags *tags, - int node, int alloc_policy) +static int blk_mq_init_bitmap_tags(struct blk_mq_tags *tags, + int node, int alloc_policy) { unsigned int depth = tags->nr_tags - tags->nr_reserved_tags; bool round_robin = alloc_policy == BLK_TAG_ALLOC_RR; - if (bt_alloc(&tags->bitmap_tags, depth, round_robin, node)) - goto free_tags; - if (bt_alloc(&tags->breserved_tags, tags->nr_reserved_tags, round_robin, - node)) + if (bt_alloc(&tags->__bitmap_tags, depth, round_robin, node)) + return -ENOMEM; + if (bt_alloc(&tags->__breserved_tags, tags->nr_reserved_tags, + round_robin, node)) goto free_bitmap_tags; - return tags; + tags->bitmap_tags = &tags->__bitmap_tags; + tags->breserved_tags = &tags->__breserved_tags; + + return 0; free_bitmap_tags: - sbitmap_queue_free(&tags->bitmap_tags); -free_tags: - kfree(tags); - return NULL; + sbitmap_queue_free(&tags->__bitmap_tags); + return -ENOMEM; +} + +int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int flags) +{ + 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; + + 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; + + for (i = 0; i < set->nr_hw_queues; i++) { + struct blk_mq_tags *tags = set->tags[i]; + + tags->bitmap_tags = &set->__bitmap_tags; + tags->breserved_tags = &set->__breserved_tags; + } + + 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) +{ + sbitmap_queue_free(&set->__bitmap_tags); + sbitmap_queue_free(&set->__breserved_tags); } struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, unsigned int reserved_tags, - int node, int alloc_policy) + int node, unsigned int flags) { + int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(flags); struct blk_mq_tags *tags; if (total_tags > BLK_MQ_TAG_MAX) { @@ -467,13 +517,22 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, tags->nr_tags = total_tags; tags->nr_reserved_tags = reserved_tags; - return blk_mq_init_bitmap_tags(tags, node, alloc_policy); + if (flags & BLK_MQ_F_TAG_HCTX_SHARED) + return tags; + + if (blk_mq_init_bitmap_tags(tags, node, alloc_policy) < 0) { + kfree(tags); + return NULL; + } + return tags; } -void blk_mq_free_tags(struct blk_mq_tags *tags) +void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags) { - sbitmap_queue_free(&tags->bitmap_tags); - sbitmap_queue_free(&tags->breserved_tags); + if (!(flags & BLK_MQ_F_TAG_HCTX_SHARED)) { + sbitmap_queue_free(tags->bitmap_tags); + sbitmap_queue_free(tags->breserved_tags); + } kfree(tags); } @@ -492,6 +551,8 @@ 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; @@ -506,30 +567,35 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, return -EINVAL; new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth, - tags->nr_reserved_tags); + tags->nr_reserved_tags, flags); if (!new) return -ENOMEM; ret = blk_mq_alloc_rqs(set, new, hctx->queue_num, tdepth); if (ret) { - blk_mq_free_rq_map(new); + blk_mq_free_rq_map(new, flags); return -ENOMEM; } blk_mq_free_rqs(set, *tagsptr, hctx->queue_num); - blk_mq_free_rq_map(*tagsptr); + blk_mq_free_rq_map(*tagsptr, flags); *tagsptr = new; } else { /* * Don't need (or can't) update reserved tags here, they * remain static and should never need resizing. */ - sbitmap_queue_resize(&tags->bitmap_tags, + sbitmap_queue_resize(tags->bitmap_tags, tdepth - tags->nr_reserved_tags); } return 0; } +void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, unsigned int size) +{ + sbitmap_queue_resize(&set->__bitmap_tags, size - set->reserved_tags); +} + /** * blk_mq_unique_tag() - return a tag that is unique queue-wide * @rq: request for which to compute a unique tag |