From 51db1c37ee166159c5753ce8d64d6bacf113e0f0 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Wed, 19 Aug 2020 23:20:19 +0800 Subject: blk-mq: Rename BLK_MQ_F_TAG_SHARED as BLK_MQ_F_TAG_QUEUE_SHARED BLK_MQ_F_TAG_SHARED actually means that tags is shared among request queues, all of which should belong to LUNs attached to same HBA. So rename it to make the point explicitly. [jpg: rebase a few times, add rnbd-clt.c change] Suggested-by: Bart Van Assche Signed-off-by: Ming Lei Signed-off-by: John Garry Tested-by: Douglas Gilbert Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/blk-mq.c | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) (limited to 'block/blk-mq.c') diff --git a/block/blk-mq.c b/block/blk-mq.c index b3d2785eefe9..75031fa1709c 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1124,7 +1124,7 @@ static bool blk_mq_get_driver_tag(struct request *rq) if (rq->tag == BLK_MQ_NO_TAG && !__blk_mq_get_driver_tag(rq)) return false; - if ((hctx->flags & BLK_MQ_F_TAG_SHARED) && + if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) && !(rq->rq_flags & RQF_MQ_INFLIGHT)) { rq->rq_flags |= RQF_MQ_INFLIGHT; atomic_inc(&hctx->nr_active); @@ -1168,7 +1168,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, wait_queue_entry_t *wait; bool ret; - if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) { + if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) { blk_mq_sched_mark_restart_hctx(hctx); /* @@ -1420,7 +1420,7 @@ out: bool needs_restart; /* For non-shared tags, the RESTART check will suffice */ bool no_tag = prep == PREP_DISPATCH_NO_TAG && - (hctx->flags & BLK_MQ_F_TAG_SHARED); + (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED); bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET; blk_mq_release_budgets(q, nr_budgets); @@ -2668,7 +2668,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, spin_lock_init(&hctx->lock); INIT_LIST_HEAD(&hctx->dispatch); hctx->queue = q; - hctx->flags = set->flags & ~BLK_MQ_F_TAG_SHARED; + hctx->flags = set->flags & ~BLK_MQ_F_TAG_QUEUE_SHARED; INIT_LIST_HEAD(&hctx->hctx_list); @@ -2885,9 +2885,9 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared) queue_for_each_hw_ctx(q, hctx, i) { if (shared) - hctx->flags |= BLK_MQ_F_TAG_SHARED; + hctx->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; else - hctx->flags &= ~BLK_MQ_F_TAG_SHARED; + hctx->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; } } @@ -2913,7 +2913,7 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q) list_del(&q->tag_set_list); if (list_is_singular(&set->tag_list)) { /* just transitioned to unshared */ - set->flags &= ~BLK_MQ_F_TAG_SHARED; + set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; /* update existing queue */ blk_mq_update_tag_set_depth(set, false); } @@ -2930,12 +2930,12 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, * Check to see if we're transitioning to shared (from 1 to 2 queues). */ if (!list_empty(&set->tag_list) && - !(set->flags & BLK_MQ_F_TAG_SHARED)) { - set->flags |= BLK_MQ_F_TAG_SHARED; + !(set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) { + set->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; /* update existing queue */ blk_mq_update_tag_set_depth(set, true); } - if (set->flags & BLK_MQ_F_TAG_SHARED) + if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED) queue_set_hctx_shared(q, true); list_add_tail(&q->tag_set_list, &set->tag_list); -- cgit v1.2.3 From 655ac30094da0d724ce66161f15675d30da89cd8 Mon Sep 17 00:00:00 2001 From: Hannes Reinecke Date: Wed, 19 Aug 2020 23:20:20 +0800 Subject: blk-mq: Rename blk_mq_update_tag_set_depth() The function does not set the depth, but rather transitions from shared to non-shared queues and vice versa. So rename it to blk_mq_update_tag_set_shared() to better reflect its purpose. [jpg: take out some unrelated changes in blk_mq_init_bitmap_tags()] Signed-off-by: Hannes Reinecke Signed-off-by: John Garry Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- block/blk-mq.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'block/blk-mq.c') diff --git a/block/blk-mq.c b/block/blk-mq.c index 75031fa1709c..cae46701579c 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2891,8 +2891,8 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared) } } -static void blk_mq_update_tag_set_depth(struct blk_mq_tag_set *set, - bool shared) +static void blk_mq_update_tag_set_shared(struct blk_mq_tag_set *set, + bool shared) { struct request_queue *q; @@ -2915,7 +2915,7 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q) /* just transitioned to unshared */ set->flags &= ~BLK_MQ_F_TAG_QUEUE_SHARED; /* update existing queue */ - blk_mq_update_tag_set_depth(set, false); + blk_mq_update_tag_set_shared(set, false); } mutex_unlock(&set->tag_list_lock); INIT_LIST_HEAD(&q->tag_set_list); @@ -2933,7 +2933,7 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, !(set->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) { set->flags |= BLK_MQ_F_TAG_QUEUE_SHARED; /* update existing queue */ - blk_mq_update_tag_set_depth(set, true); + blk_mq_update_tag_set_shared(set, true); } if (set->flags & BLK_MQ_F_TAG_QUEUE_SHARED) queue_set_hctx_shared(q, true); -- cgit v1.2.3 From 1c0706a70a64eda48477caa880657e07f5196512 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 19 Aug 2020 23:20:22 +0800 Subject: blk-mq: Pass flags for tag init/free Pass hctx/tagset flags argument down to blk_mq_init_tags() and blk_mq_free_tags() for selective init/free. For now, make it include the alloc policy flag, which can be evaluated when needed (in blk_mq_init_tags()). Signed-off-by: John Garry Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- block/blk-mq-sched.c | 11 ++++++++--- block/blk-mq-tag.c | 12 +++++++----- block/blk-mq-tag.h | 7 ++++--- block/blk-mq.c | 23 +++++++++++++---------- block/blk-mq.h | 5 +++-- 5 files changed, 35 insertions(+), 23 deletions(-) (limited to 'block/blk-mq.c') diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 501a85ceaccb..edfc8ea805bc 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -560,9 +560,11 @@ static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { + unsigned int flags = set->flags; + if (hctx->sched_tags) { blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx); - blk_mq_free_rq_map(hctx->sched_tags); + blk_mq_free_rq_map(hctx->sched_tags, flags); hctx->sched_tags = NULL; } } @@ -572,10 +574,11 @@ static int blk_mq_sched_alloc_tags(struct request_queue *q, unsigned int hctx_idx) { struct blk_mq_tag_set *set = q->tag_set; + unsigned int flags = set->flags; int ret; hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests, - set->reserved_tags); + set->reserved_tags, flags); if (!hctx->sched_tags) return -ENOMEM; @@ -593,8 +596,10 @@ static void blk_mq_sched_tags_teardown(struct request_queue *q) int i; queue_for_each_hw_ctx(q, hctx, i) { + unsigned int flags = hctx->flags; + if (hctx->sched_tags) { - blk_mq_free_rq_map(hctx->sched_tags); + blk_mq_free_rq_map(hctx->sched_tags, flags); hctx->sched_tags = NULL; } } diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index c2c9f369d777..0426f01e06a6 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -449,8 +449,9 @@ free_bitmap_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) { @@ -472,7 +473,7 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, 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); @@ -494,6 +495,7 @@ 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; + unsigned int flags = set->flags; struct blk_mq_tags *new; bool ret; @@ -508,17 +510,17 @@ 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 { /* diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 918e2cee4f43..391f68d32fa1 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -21,9 +21,10 @@ struct blk_mq_tags { struct list_head page_list; }; - -extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, unsigned int reserved_tags, int node, int alloc_policy); -extern void blk_mq_free_tags(struct blk_mq_tags *tags); +extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, + unsigned int reserved_tags, + int node, unsigned int flags); +extern void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags); extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, diff --git a/block/blk-mq.c b/block/blk-mq.c index cae46701579c..a39693dbb3c8 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2296,20 +2296,21 @@ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, } } -void blk_mq_free_rq_map(struct blk_mq_tags *tags) +void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags) { kfree(tags->rqs); tags->rqs = NULL; kfree(tags->static_rqs); tags->static_rqs = NULL; - blk_mq_free_tags(tags); + blk_mq_free_tags(tags, flags); } struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int nr_tags, - unsigned int reserved_tags) + unsigned int reserved_tags, + unsigned int flags) { struct blk_mq_tags *tags; int node; @@ -2318,8 +2319,7 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, if (node == NUMA_NO_NODE) node = set->numa_node; - tags = blk_mq_init_tags(nr_tags, reserved_tags, node, - BLK_MQ_FLAG_TO_ALLOC_POLICY(set->flags)); + tags = blk_mq_init_tags(nr_tags, reserved_tags, node, flags); if (!tags) return NULL; @@ -2327,7 +2327,7 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, GFP_NOIO | __GFP_NOWARN | __GFP_NORETRY, node); if (!tags->rqs) { - blk_mq_free_tags(tags); + blk_mq_free_tags(tags, flags); return NULL; } @@ -2336,7 +2336,7 @@ struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, node); if (!tags->static_rqs) { kfree(tags->rqs); - blk_mq_free_tags(tags); + blk_mq_free_tags(tags, flags); return NULL; } @@ -2745,10 +2745,11 @@ static void blk_mq_init_cpu_queues(struct request_queue *q, static bool __blk_mq_alloc_map_and_request(struct blk_mq_tag_set *set, int hctx_idx) { + unsigned int flags = set->flags; int ret = 0; set->tags[hctx_idx] = blk_mq_alloc_rq_map(set, hctx_idx, - set->queue_depth, set->reserved_tags); + set->queue_depth, set->reserved_tags, flags); if (!set->tags[hctx_idx]) return false; @@ -2757,7 +2758,7 @@ static bool __blk_mq_alloc_map_and_request(struct blk_mq_tag_set *set, if (!ret) return true; - blk_mq_free_rq_map(set->tags[hctx_idx]); + blk_mq_free_rq_map(set->tags[hctx_idx], flags); set->tags[hctx_idx] = NULL; return false; } @@ -2765,9 +2766,11 @@ static bool __blk_mq_alloc_map_and_request(struct blk_mq_tag_set *set, static void blk_mq_free_map_and_requests(struct blk_mq_tag_set *set, unsigned int hctx_idx) { + unsigned int flags = set->flags; + if (set->tags && set->tags[hctx_idx]) { blk_mq_free_rqs(set, set->tags[hctx_idx], hctx_idx); - blk_mq_free_rq_map(set->tags[hctx_idx]); + blk_mq_free_rq_map(set->tags[hctx_idx], flags); set->tags[hctx_idx] = NULL; } } diff --git a/block/blk-mq.h b/block/blk-mq.h index 863a2f3346d4..b86e7fe47789 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -53,11 +53,12 @@ struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx, */ void blk_mq_free_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx); -void blk_mq_free_rq_map(struct blk_mq_tags *tags); +void blk_mq_free_rq_map(struct blk_mq_tags *tags, unsigned int flags); struct blk_mq_tags *blk_mq_alloc_rq_map(struct blk_mq_tag_set *set, unsigned int hctx_idx, unsigned int nr_tags, - unsigned int reserved_tags); + unsigned int reserved_tags, + unsigned int flags); int blk_mq_alloc_rqs(struct blk_mq_tag_set *set, struct blk_mq_tags *tags, unsigned int hctx_idx, unsigned int depth); -- cgit v1.2.3 From 222a5ae03cdd12e7643f2f64689a39ed547650cb Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 19 Aug 2020 23:20:23 +0800 Subject: blk-mq: Use pointers for blk_mq_tags bitmap tags Introduce pointers for the blk_mq_tags regular and reserved bitmap tags, with the goal of later being able to use a common shared tag bitmap across all HW contexts in a set. Signed-off-by: John Garry Tested-by: Don Brace #SCSI resv cmds patches used Tested-by: Douglas Gilbert Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/bfq-iosched.c | 4 ++-- block/blk-mq-debugfs.c | 8 ++++---- block/blk-mq-tag.c | 41 ++++++++++++++++++++++------------------- block/blk-mq-tag.h | 7 +++++-- block/blk-mq.c | 8 ++++---- block/kyber-iosched.c | 4 ++-- 6 files changed, 39 insertions(+), 33 deletions(-) (limited to 'block/blk-mq.c') diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index c34b090178a9..418ffd4b5552 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -6372,8 +6372,8 @@ static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx) struct blk_mq_tags *tags = hctx->sched_tags; unsigned int min_shallow; - min_shallow = bfq_update_depths(bfqd, &tags->bitmap_tags); - sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, min_shallow); + min_shallow = bfq_update_depths(bfqd, tags->bitmap_tags); + sbitmap_queue_min_shallow_depth(tags->bitmap_tags, min_shallow); } static int bfq_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int index) diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index a4597febff69..645b7f800cb8 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -452,11 +452,11 @@ static void blk_mq_debugfs_tags_show(struct seq_file *m, atomic_read(&tags->active_queues)); seq_puts(m, "\nbitmap_tags:\n"); - sbitmap_queue_show(&tags->bitmap_tags, m); + sbitmap_queue_show(tags->bitmap_tags, m); if (tags->nr_reserved_tags) { seq_puts(m, "\nbreserved_tags:\n"); - sbitmap_queue_show(&tags->breserved_tags, m); + sbitmap_queue_show(tags->breserved_tags, m); } } @@ -487,7 +487,7 @@ static int hctx_tags_bitmap_show(void *data, struct seq_file *m) if (res) goto out; if (hctx->tags) - sbitmap_bitmap_show(&hctx->tags->bitmap_tags.sb, m); + sbitmap_bitmap_show(&hctx->tags->bitmap_tags->sb, m); mutex_unlock(&q->sysfs_lock); out: @@ -521,7 +521,7 @@ static int hctx_sched_tags_bitmap_show(void *data, struct seq_file *m) if (res) goto out; if (hctx->sched_tags) - sbitmap_bitmap_show(&hctx->sched_tags->bitmap_tags.sb, m); + sbitmap_bitmap_show(&hctx->sched_tags->bitmap_tags->sb, m); mutex_unlock(&q->sysfs_lock); out: diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 0426f01e06a6..77fbeae05745 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -35,9 +35,9 @@ 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); } /* @@ -82,10 +82,10 @@ 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 +131,9 @@ 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 +167,10 @@ 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); } } @@ -298,9 +298,9 @@ 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); } /** @@ -416,8 +416,8 @@ 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); } @@ -435,15 +435,18 @@ static int blk_mq_init_bitmap_tags(struct blk_mq_tags *tags, 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)) + 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)) + if (bt_alloc(&tags->__breserved_tags, tags->nr_reserved_tags, + round_robin, node)) goto free_bitmap_tags; + tags->bitmap_tags = &tags->__bitmap_tags; + tags->breserved_tags = &tags->__breserved_tags; + return 0; free_bitmap_tags: - sbitmap_queue_free(&tags->bitmap_tags); + sbitmap_queue_free(&tags->__bitmap_tags); return -ENOMEM; } @@ -475,8 +478,8 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_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); + sbitmap_queue_free(&tags->__bitmap_tags); + sbitmap_queue_free(&tags->__breserved_tags); kfree(tags); } @@ -527,7 +530,7 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, * 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); } diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 391f68d32fa1..5b6f25bd1966 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -13,8 +13,11 @@ struct blk_mq_tags { atomic_t active_queues; - struct sbitmap_queue bitmap_tags; - struct sbitmap_queue breserved_tags; + struct sbitmap_queue *bitmap_tags; + struct sbitmap_queue *breserved_tags; + + struct sbitmap_queue __bitmap_tags; + struct sbitmap_queue __breserved_tags; struct request **rqs; struct request **static_rqs; diff --git a/block/blk-mq.c b/block/blk-mq.c index a39693dbb3c8..4982bb1d75db 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1096,14 +1096,14 @@ static inline unsigned int queued_to_index(unsigned int queued) static bool __blk_mq_get_driver_tag(struct request *rq) { - struct sbitmap_queue *bt = &rq->mq_hctx->tags->bitmap_tags; + struct sbitmap_queue *bt = rq->mq_hctx->tags->bitmap_tags; unsigned int tag_offset = rq->mq_hctx->tags->nr_reserved_tags; int tag; blk_mq_tag_busy(rq->mq_hctx); if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) { - bt = &rq->mq_hctx->tags->breserved_tags; + bt = rq->mq_hctx->tags->breserved_tags; tag_offset = 0; } @@ -1145,7 +1145,7 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, struct sbitmap_queue *sbq; list_del_init(&wait->entry); - sbq = &hctx->tags->bitmap_tags; + sbq = hctx->tags->bitmap_tags; atomic_dec(&sbq->ws_active); } spin_unlock(&hctx->dispatch_wait_lock); @@ -1163,7 +1163,7 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode, static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx, struct request *rq) { - struct sbitmap_queue *sbq = &hctx->tags->bitmap_tags; + struct sbitmap_queue *sbq = hctx->tags->bitmap_tags; struct wait_queue_head *wq; wait_queue_entry_t *wait; bool ret; diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index 6d4ba0e9688e..dc89199bc8c6 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -359,7 +359,7 @@ static unsigned int kyber_sched_tags_shift(struct request_queue *q) * All of the hardware queues have the same depth, so we can just grab * the shift of the first one. */ - return q->queue_hw_ctx[0]->sched_tags->bitmap_tags.sb.shift; + return q->queue_hw_ctx[0]->sched_tags->bitmap_tags->sb.shift; } static struct kyber_queue_data *kyber_queue_data_alloc(struct request_queue *q) @@ -502,7 +502,7 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) khd->batching = 0; hctx->sched_data = khd; - sbitmap_queue_min_shallow_depth(&hctx->sched_tags->bitmap_tags, + sbitmap_queue_min_shallow_depth(hctx->sched_tags->bitmap_tags, kqd->async_depth); return 0; -- cgit v1.2.3 From 32bc15afed04bd73e29d713d8db47818d6aa89af Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 19 Aug 2020 23:20:24 +0800 Subject: blk-mq: Facilitate a shared sbitmap per tagset Some SCSI HBAs (such as HPSA, megaraid, mpt3sas, hisi_sas_v3 ..) support multiple reply queues with single hostwide tags. In addition, these drivers want to use interrupt assignment in pci_alloc_irq_vectors(PCI_IRQ_AFFINITY). However, as discussed in [0], CPU hotplug may cause in-flight IO completion to not be serviced when an interrupt is shutdown. That problem is solved in commit bf0beec0607d ("blk-mq: drain I/O when all CPUs in a hctx are offline"). However, to take advantage of that blk-mq feature, the HBA HW queuess are required to be mapped to that of the blk-mq hctx's; to do that, the HBA HW queues need to be exposed to the upper layer. In making that transition, the per-SCSI command request tags are no longer unique per Scsi host - they are just unique per hctx. As such, the HBA LLDD would have to generate this tag internally, which has a certain performance overhead. However another problem is that blk-mq assumes the host may accept (Scsi_host.can_queue * #hw queue) commands. In commit 6eb045e092ef ("scsi: core: avoid host-wide host_busy counter for scsi_mq"), the Scsi host busy counter was removed, which would stop the LLDD being sent more than .can_queue commands; however, it should still be ensured that the block layer does not issue more than .can_queue commands to the Scsi host. To solve this problem, introduce a shared sbitmap per blk_mq_tag_set, which may be requested at init time. New flag BLK_MQ_F_TAG_HCTX_SHARED should be set when requesting the tagset to indicate whether the shared sbitmap should be used. Even when BLK_MQ_F_TAG_HCTX_SHARED is set, a full set of tags and requests are still allocated per hctx; the reason for this is that if tags and requests were only allocated for a single hctx - like hctx0 - it may break block drivers which expect a request be associated with a specific hctx, i.e. not always hctx0. This will introduce extra memory usage. This change is based on work originally from Ming Lei in [1] and from Bart's suggestion in [2]. [0] https://lore.kernel.org/linux-block/alpine.DEB.2.21.1904051331270.1802@nanos.tec.linutronix.de/ [1] https://lore.kernel.org/linux-block/20190531022801.10003-1-ming.lei@redhat.com/ [2] https://lore.kernel.org/linux-block/ff77beff-5fd9-9f05-12b6-826922bace1f@huawei.com/T/#m3db0a602f095cbcbff27e9c884d6b4ae826144be Signed-off-by: John Garry Tested-by: Don Brace #SCSI resv cmds patches used Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- block/blk-mq-sched.c | 8 +++++--- block/blk-mq-tag.c | 51 ++++++++++++++++++++++++++++++++++++++++++++++---- block/blk-mq-tag.h | 7 +++++++ block/blk-mq.c | 15 +++++++++++++++ block/blk-mq.h | 5 +++++ include/linux/blk-mq.h | 6 ++++++ 6 files changed, 85 insertions(+), 7 deletions(-) (limited to 'block/blk-mq.c') diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index edfc8ea805bc..86d5545342ff 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -560,7 +560,7 @@ static void blk_mq_sched_free_tags(struct blk_mq_tag_set *set, struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) { - unsigned int flags = set->flags; + unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; if (hctx->sched_tags) { blk_mq_free_rqs(set, hctx->sched_tags, hctx_idx); @@ -574,7 +574,8 @@ static int blk_mq_sched_alloc_tags(struct request_queue *q, unsigned int hctx_idx) { struct blk_mq_tag_set *set = q->tag_set; - unsigned int flags = set->flags; + /* Clear HCTX_SHARED so tags are init'ed */ + unsigned int flags = set->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; int ret; hctx->sched_tags = blk_mq_alloc_rq_map(set, hctx_idx, q->nr_requests, @@ -596,7 +597,8 @@ static void blk_mq_sched_tags_teardown(struct request_queue *q) int i; queue_for_each_hw_ctx(q, hctx, i) { - unsigned int flags = hctx->flags; + /* Clear HCTX_SHARED so tags are freed */ + unsigned int flags = hctx->flags & ~BLK_MQ_F_TAG_HCTX_SHARED; if (hctx->sched_tags) { blk_mq_free_rq_map(hctx->sched_tags, flags); diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 77fbeae05745..c6d7ebc62bdb 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -197,7 +197,7 @@ 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; } @@ -450,6 +450,38 @@ free_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, unsigned int flags) @@ -469,6 +501,9 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_tags, tags->nr_tags = total_tags; tags->nr_reserved_tags = reserved_tags; + 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; @@ -478,8 +513,10 @@ struct blk_mq_tags *blk_mq_init_tags(unsigned int total_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); } @@ -498,7 +535,8 @@ 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; - unsigned int flags = set->flags; + /* 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; @@ -537,6 +575,11 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, 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 diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 5b6f25bd1966..8f4cce52ba2d 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -29,12 +29,19 @@ extern struct blk_mq_tags *blk_mq_init_tags(unsigned int nr_tags, int node, unsigned int flags); extern void blk_mq_free_tags(struct blk_mq_tags *tags, unsigned int flags); +extern int blk_mq_init_shared_sbitmap(struct blk_mq_tag_set *set, + unsigned int flags); +extern void blk_mq_exit_shared_sbitmap(struct blk_mq_tag_set *set); + extern unsigned int blk_mq_get_tag(struct blk_mq_alloc_data *data); extern void blk_mq_put_tag(struct blk_mq_tags *tags, struct blk_mq_ctx *ctx, unsigned int tag); extern int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, struct blk_mq_tags **tags, unsigned int depth, bool can_grow); +extern void blk_mq_tag_resize_shared_sbitmap(struct blk_mq_tag_set *set, + unsigned int size); + extern void blk_mq_tag_wakeup_all(struct blk_mq_tags *tags, bool); void blk_mq_queue_tag_busy_iter(struct request_queue *q, busy_iter_fn *fn, void *priv); diff --git a/block/blk-mq.c b/block/blk-mq.c index 4982bb1d75db..5e8fe795edf1 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3441,11 +3441,21 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) if (ret) goto out_free_mq_map; + if (blk_mq_is_sbitmap_shared(set->flags)) { + if (blk_mq_init_shared_sbitmap(set, set->flags)) { + ret = -ENOMEM; + goto out_free_mq_rq_maps; + } + } + mutex_init(&set->tag_list_lock); INIT_LIST_HEAD(&set->tag_list); return 0; +out_free_mq_rq_maps: + for (i = 0; i < set->nr_hw_queues; i++) + blk_mq_free_map_and_requests(set, i); out_free_mq_map: for (i = 0; i < set->nr_maps; i++) { kfree(set->map[i].mq_map); @@ -3464,6 +3474,9 @@ void blk_mq_free_tag_set(struct blk_mq_tag_set *set) for (i = 0; i < set->nr_hw_queues; i++) blk_mq_free_map_and_requests(set, i); + if (blk_mq_is_sbitmap_shared(set->flags)) + blk_mq_exit_shared_sbitmap(set); + for (j = 0; j < set->nr_maps; j++) { kfree(set->map[j].mq_map); set->map[j].mq_map = NULL; @@ -3500,6 +3513,8 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr) if (!hctx->sched_tags) { ret = blk_mq_tag_update_depth(hctx, &hctx->tags, nr, false); + if (!ret && blk_mq_is_sbitmap_shared(set->flags)) + blk_mq_tag_resize_shared_sbitmap(set, nr); } else { ret = blk_mq_tag_update_depth(hctx, &hctx->sched_tags, nr, true); diff --git a/block/blk-mq.h b/block/blk-mq.h index b86e7fe47789..3acdb56065e1 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -159,6 +159,11 @@ struct blk_mq_alloc_data { struct blk_mq_hw_ctx *hctx; }; +static inline bool blk_mq_is_sbitmap_shared(unsigned int flags) +{ + return flags & BLK_MQ_F_TAG_HCTX_SHARED; +} + static inline struct blk_mq_tags *blk_mq_tags_from_data(struct blk_mq_alloc_data *data) { if (data->q->elevator) diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 982c4f92b63c..df7b903ce7ae 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -231,6 +231,9 @@ enum hctx_type { * @flags: Zero or more BLK_MQ_F_* flags. * @driver_data: Pointer to data owned by the block driver that created this * tag set. + * @__bitmap_tags: A shared tags sbitmap, used over all hctx's + * @__breserved_tags: + * A shared reserved tags sbitmap, used over all hctx's * @tags: Tag sets. One tag set per hardware queue. Has @nr_hw_queues * elements. * @tag_list_lock: Serializes tag_list accesses. @@ -250,6 +253,8 @@ struct blk_mq_tag_set { unsigned int flags; void *driver_data; + struct sbitmap_queue __bitmap_tags; + struct sbitmap_queue __breserved_tags; struct blk_mq_tags **tags; struct mutex tag_list_lock; @@ -384,6 +389,7 @@ enum { * completing IO: */ BLK_MQ_F_STACKING = 1 << 2, + BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3, BLK_MQ_F_BLOCKING = 1 << 5, BLK_MQ_F_NO_SCHED = 1 << 6, BLK_MQ_F_ALLOC_POLICY_START_BIT = 8, -- cgit v1.2.3 From bccf5e26d99c28980bd6ced474422a1b18402263 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 19 Aug 2020 23:20:26 +0800 Subject: blk-mq: Record nr_active_requests per queue for when using shared sbitmap The per-hctx nr_active value can no longer be used to fairly assign a share of tag depth per request queue for when using a shared sbitmap, as it does not consider that the tags are shared tags over all hctx's. For this case, record the nr_active_requests per request_queue, and make the judgement based on that value. Co-developed-with: Kashyap Desai Signed-off-by: John Garry Tested-by: Don Brace #SCSI resv cmds patches used Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- block/blk-core.c | 2 ++ block/blk-mq.c | 4 ++-- block/blk-mq.h | 26 ++++++++++++++++++++++++-- include/linux/blkdev.h | 2 ++ 4 files changed, 30 insertions(+), 4 deletions(-) (limited to 'block/blk-mq.c') diff --git a/block/blk-core.c b/block/blk-core.c index 9f2a99abeeb9..093649bd252e 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -543,6 +543,8 @@ struct request_queue *blk_alloc_queue(int node_id) q->backing_dev_info->capabilities = BDI_CAP_CGROUP_WRITEBACK; q->node = node_id; + atomic_set(&q->nr_active_requests_shared_sbitmap, 0); + timer_setup(&q->backing_dev_info->laptop_mode_wb_timer, laptop_mode_timer_fn, 0); timer_setup(&q->timeout, blk_rq_timed_out_timer, 0); diff --git a/block/blk-mq.c b/block/blk-mq.c index 5e8fe795edf1..ffc5ad0c91b7 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -519,7 +519,7 @@ void blk_mq_free_request(struct request *rq) ctx->rq_completed[rq_is_sync(rq)]++; if (rq->rq_flags & RQF_MQ_INFLIGHT) - atomic_dec(&hctx->nr_active); + __blk_mq_dec_active_requests(hctx); if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq))) laptop_io_completion(q->backing_dev_info); @@ -1127,7 +1127,7 @@ static bool blk_mq_get_driver_tag(struct request *rq) if ((hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) && !(rq->rq_flags & RQF_MQ_INFLIGHT)) { rq->rq_flags |= RQF_MQ_INFLIGHT; - atomic_inc(&hctx->nr_active); + __blk_mq_inc_active_requests(hctx); } hctx->tags->rqs[rq->tag] = rq; return true; diff --git a/block/blk-mq.h b/block/blk-mq.h index 56dc37c21908..25ec73078e95 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -199,6 +199,28 @@ static inline bool blk_mq_get_dispatch_budget(struct request_queue *q) return true; } +static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx) +{ + if (blk_mq_is_sbitmap_shared(hctx->flags)) + atomic_inc(&hctx->queue->nr_active_requests_shared_sbitmap); + else + atomic_inc(&hctx->nr_active); +} + +static inline void __blk_mq_dec_active_requests(struct blk_mq_hw_ctx *hctx) +{ + if (blk_mq_is_sbitmap_shared(hctx->flags)) + atomic_dec(&hctx->queue->nr_active_requests_shared_sbitmap); + else + atomic_dec(&hctx->nr_active); +} + +static inline int __blk_mq_active_requests(struct blk_mq_hw_ctx *hctx) +{ + if (blk_mq_is_sbitmap_shared(hctx->flags)) + return atomic_read(&hctx->queue->nr_active_requests_shared_sbitmap); + return atomic_read(&hctx->nr_active); +} static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, struct request *rq) { @@ -207,7 +229,7 @@ static inline void __blk_mq_put_driver_tag(struct blk_mq_hw_ctx *hctx, if (rq->rq_flags & RQF_MQ_INFLIGHT) { rq->rq_flags &= ~RQF_MQ_INFLIGHT; - atomic_dec(&hctx->nr_active); + __blk_mq_dec_active_requests(hctx); } } @@ -287,7 +309,7 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, * Allow at least some tags */ depth = max((bt->sb.depth + users - 1) / users, 4U); - return atomic_read(&hctx->nr_active) < depth; + return __blk_mq_active_requests(hctx) < depth; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d0d61bc81615..6277aee2aeaa 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -485,6 +485,8 @@ struct request_queue { struct timer_list timeout; struct work_struct timeout_work; + atomic_t nr_active_requests_shared_sbitmap; + struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS); -- cgit v1.2.3 From f1b49fdc1c64db110aa1315831e5fe0f8599fa56 Mon Sep 17 00:00:00 2001 From: John Garry Date: Wed, 19 Aug 2020 23:20:27 +0800 Subject: blk-mq: Record active_queues_shared_sbitmap per tag_set for when using shared sbitmap For when using a shared sbitmap, no longer should the number of active request queues per hctx be relied on for when judging how to share the tag bitmap. Instead maintain the number of active request queues per tag_set, and make the judgement based on that. Originally-from: Kashyap Desai Signed-off-by: John Garry Tested-by: Don Brace #SCSI resv cmds patches used Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 33 +++++++++++++++++++++++++-------- block/blk-mq.c | 2 ++ block/blk-mq.h | 16 +++++++++++++--- include/linux/blk-mq.h | 1 + include/linux/blkdev.h | 1 + 5 files changed, 42 insertions(+), 11 deletions(-) (limited to 'block/blk-mq.c') diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index c6d7ebc62bdb..c31c4a0478a5 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; } @@ -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); } diff --git a/block/blk-mq.c b/block/blk-mq.c index ffc5ad0c91b7..eff9d987f85b 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3442,6 +3442,8 @@ int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set) goto out_free_mq_map; if (blk_mq_is_sbitmap_shared(set->flags)) { + atomic_set(&set->active_queues_shared_sbitmap, 0); + if (blk_mq_init_shared_sbitmap(set, set->flags)) { ret = -ENOMEM; goto out_free_mq_rq_maps; diff --git a/block/blk-mq.h b/block/blk-mq.h index 25ec73078e95..a52703c98b77 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -292,8 +292,6 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, if (!hctx || !(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) return true; - if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) - return true; /* * Don't try dividing an ant @@ -301,7 +299,19 @@ static inline bool hctx_may_queue(struct blk_mq_hw_ctx *hctx, if (bt->sb.depth == 1) return true; - users = atomic_read(&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(BLK_MQ_S_TAG_ACTIVE, &q->queue_flags)) + return true; + users = atomic_read(&set->active_queues_shared_sbitmap); + } else { + if (!test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) + return true; + users = atomic_read(&hctx->tags->active_queues); + } + if (!users) return true; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index df7b903ce7ae..8279c807e1f3 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -252,6 +252,7 @@ struct blk_mq_tag_set { unsigned int timeout; unsigned int flags; void *driver_data; + atomic_t active_queues_shared_sbitmap; struct sbitmap_queue __bitmap_tags; struct sbitmap_queue __breserved_tags; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6277aee2aeaa..7d82959e7b86 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -618,6 +618,7 @@ struct request_queue { #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ #define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ #define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ +#define QUEUE_FLAG_HCTX_ACTIVE 28 /* at least one blk-mq hctx is active */ #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP)) -- cgit v1.2.3 From b445547ec1bbd3e7bf4b1c142550942f70527d95 Mon Sep 17 00:00:00 2001 From: Kashyap Desai Date: Wed, 19 Aug 2020 23:20:28 +0800 Subject: blk-mq, elevator: Count requests per hctx to improve performance High CPU utilization on "native_queued_spin_lock_slowpath" due to lock contention is possible for mq-deadline and bfq IO schedulers when nr_hw_queues is more than one. It is because kblockd work queue can submit IO from all online CPUs (through blk_mq_run_hw_queues()) even though only one hctx has pending commands. The elevator callback .has_work for mq-deadline and bfq scheduler considers pending work if there are any IOs on request queue but it does not account hctx context. Add a per-hctx 'elevator_queued' count to the hctx to avoid triggering the elevator even though there are no requests queued. [jpg: Relocated atomic_dec() in dd_dispatch_request(), update commit message per Kashyap] Signed-off-by: Kashyap Desai Signed-off-by: Hannes Reinecke Signed-off-by: John Garry Tested-by: Douglas Gilbert Signed-off-by: Jens Axboe --- block/bfq-iosched.c | 5 +++++ block/blk-mq.c | 1 + block/mq-deadline.c | 6 ++++++ include/linux/blk-mq.h | 4 ++++ 4 files changed, 16 insertions(+) (limited to 'block/blk-mq.c') diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 418ffd4b5552..a251b80d8ee5 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -4640,6 +4640,9 @@ static bool bfq_has_work(struct blk_mq_hw_ctx *hctx) { struct bfq_data *bfqd = hctx->queue->elevator->elevator_data; + if (!atomic_read(&hctx->elevator_queued)) + return false; + /* * Avoiding lock: a race on bfqd->busy_queues should cause at * most a call to dispatch for nothing @@ -5554,6 +5557,7 @@ static void bfq_insert_requests(struct blk_mq_hw_ctx *hctx, rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); bfq_insert_request(hctx, rq, at_head); + atomic_inc(&hctx->elevator_queued); } } @@ -5933,6 +5937,7 @@ static void bfq_finish_requeue_request(struct request *rq) bfq_completed_request(bfqq, bfqd); bfq_finish_requeue_request_body(bfqq); + atomic_dec(&rq->mq_hctx->elevator_queued); spin_unlock_irqrestore(&bfqd->lock, flags); } else { diff --git a/block/blk-mq.c b/block/blk-mq.c index eff9d987f85b..4abb71459f94 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2660,6 +2660,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, goto free_hctx; atomic_set(&hctx->nr_active, 0); + atomic_set(&hctx->elevator_queued, 0); if (node == NUMA_NO_NODE) node = set->numa_node; hctx->numa_node = node; diff --git a/block/mq-deadline.c b/block/mq-deadline.c index b57470e154c8..800ac902809b 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -386,6 +386,8 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx) spin_lock(&dd->lock); rq = __dd_dispatch_request(dd); spin_unlock(&dd->lock); + if (rq) + atomic_dec(&rq->mq_hctx->elevator_queued); return rq; } @@ -533,6 +535,7 @@ static void dd_insert_requests(struct blk_mq_hw_ctx *hctx, rq = list_first_entry(list, struct request, queuelist); list_del_init(&rq->queuelist); dd_insert_request(hctx, rq, at_head); + atomic_inc(&hctx->elevator_queued); } spin_unlock(&dd->lock); } @@ -579,6 +582,9 @@ static bool dd_has_work(struct blk_mq_hw_ctx *hctx) { struct deadline_data *dd = hctx->queue->elevator->elevator_data; + if (!atomic_read(&hctx->elevator_queued)) + return false; + return !list_empty_careful(&dd->dispatch) || !list_empty_careful(&dd->fifo_list[0]) || !list_empty_careful(&dd->fifo_list[1]); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 8279c807e1f3..b23eeca4d677 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -139,6 +139,10 @@ struct blk_mq_hw_ctx { * shared across request queues. */ atomic_t nr_active; + /** + * @elevator_queued: Number of queued requests on hctx. + */ + atomic_t elevator_queued; /** @cpuhp_online: List to store request if CPU is going to die */ struct hlist_node cpuhp_online; -- cgit v1.2.3 From 285008501c65a3fcee05d2c2c26cbf629ceff2f0 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 11 Sep 2020 18:41:14 +0800 Subject: blk-mq: always allow reserved allocation in hctx_may_queue NVMe shares tagset between fabric queue and admin queue or between connect_q and NS queue, so hctx_may_queue() can be called to allocate request for these queues. Tags can be reserved in these tagset. Before error recovery, there is often lots of in-flight requests which can't be completed, and new reserved request may be needed in error recovery path. However, hctx_may_queue() can always return false because there is too many in-flight requests which can't be completed during error handling. Finally, nothing can proceed. Fix this issue by always allowing reserved tag allocation in hctx_may_queue(). This is reasonable because reserved tags are supposed to always be available. Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Cc: David Milburn Cc: Ewan D. Milne Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-mq-tag.c | 3 ++- block/blk-mq.c | 5 +++-- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'block/blk-mq.c') diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index c31c4a0478a5..aacf10decdbd 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -76,7 +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) diff --git a/block/blk-mq.c b/block/blk-mq.c index 4abb71459f94..e04b759add75 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1105,10 +1105,11 @@ static bool __blk_mq_get_driver_tag(struct request *rq) if (blk_mq_tag_is_reserved(rq->mq_hctx->sched_tags, rq->internal_tag)) { bt = rq->mq_hctx->tags->breserved_tags; tag_offset = 0; + } else { + if (!hctx_may_queue(rq->mq_hctx, bt)) + return false; } - if (!hctx_may_queue(rq->mq_hctx, bt)) - return false; tag = __sbitmap_queue_get(bt); if (tag == BLK_MQ_NO_TAG) return false; -- cgit v1.2.3 From 8229cca8c3ea70bcb3b73aa105ae1d00aafbd3c8 Mon Sep 17 00:00:00 2001 From: Xianting Tian Date: Sat, 26 Sep 2020 10:39:47 +0800 Subject: blk-mq: add cond_resched() in __blk_mq_alloc_rq_maps() We found blk_mq_alloc_rq_maps() takes more time in kernel space when testing nvme device hot-plugging. The test and anlysis as below. Debug code, 1, blk_mq_alloc_rq_maps(): u64 start, end; depth = set->queue_depth; start = ktime_get_ns(); pr_err("[%d:%s switch:%ld,%ld] queue depth %d, nr_hw_queues %d\n", current->pid, current->comm, current->nvcsw, current->nivcsw, set->queue_depth, set->nr_hw_queues); do { err = __blk_mq_alloc_rq_maps(set); if (!err) break; set->queue_depth >>= 1; if (set->queue_depth < set->reserved_tags + BLK_MQ_TAG_MIN) { err = -ENOMEM; break; } } while (set->queue_depth); end = ktime_get_ns(); pr_err("[%d:%s switch:%ld,%ld] all hw queues init cost time %lld ns\n", current->pid, current->comm, current->nvcsw, current->nivcsw, end - start); 2, __blk_mq_alloc_rq_maps(): u64 start, end; for (i = 0; i < set->nr_hw_queues; i++) { start = ktime_get_ns(); if (!__blk_mq_alloc_rq_map(set, i)) goto out_unwind; end = ktime_get_ns(); pr_err("hw queue %d init cost time %lld ns\n", i, end - start); } Test nvme hot-plugging with above debug code, we found it totally cost more than 3ms in kernel space without being scheduled out when alloc rqs for all 16 hw queues with depth 1023, each hw queue cost about 140-250us. The cost time will be increased with hw queue number and queue depth increasing. And in an extreme case, if __blk_mq_alloc_rq_maps() returns -ENOMEM, it will try "queue_depth >>= 1", more time will be consumed. [ 428.428771] nvme nvme0: pci function 10000:01:00.0 [ 428.428798] nvme 10000:01:00.0: enabling device (0000 -> 0002) [ 428.428806] pcieport 10000:00:00.0: can't derive routing for PCI INT A [ 428.428809] nvme 10000:01:00.0: PCI INT A: no GSI [ 432.593374] [4688:kworker/u33:8 switch:663,2] queue depth 30, nr_hw_queues 1 [ 432.593404] hw queue 0 init cost time 22883 ns [ 432.593408] [4688:kworker/u33:8 switch:663,2] all hw queues init cost time 35960 ns [ 432.595953] nvme nvme0: 16/0/0 default/read/poll queues [ 432.595958] [4688:kworker/u33:8 switch:700,2] queue depth 1023, nr_hw_queues 16 [ 432.596203] hw queue 0 init cost time 242630 ns [ 432.596441] hw queue 1 init cost time 235913 ns [ 432.596659] hw queue 2 init cost time 216461 ns [ 432.596877] hw queue 3 init cost time 215851 ns [ 432.597107] hw queue 4 init cost time 228406 ns [ 432.597336] hw queue 5 init cost time 227298 ns [ 432.597564] hw queue 6 init cost time 224633 ns [ 432.597785] hw queue 7 init cost time 219954 ns [ 432.597937] hw queue 8 init cost time 150930 ns [ 432.598082] hw queue 9 init cost time 143496 ns [ 432.598231] hw queue 10 init cost time 147261 ns [ 432.598397] hw queue 11 init cost time 164522 ns [ 432.598542] hw queue 12 init cost time 143401 ns [ 432.598692] hw queue 13 init cost time 148934 ns [ 432.598841] hw queue 14 init cost time 147194 ns [ 432.598991] hw queue 15 init cost time 148942 ns [ 432.598993] [4688:kworker/u33:8 switch:700,2] all hw queues init cost time 3035099 ns [ 432.602611] nvme0n1: p1 So use this patch to trigger schedule between each hw queue init, to avoid other threads getting stuck. It is not in atomic context when executing __blk_mq_alloc_rq_maps(), so it is safe to call cond_resched(). Signed-off-by: Xianting Tian Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- block/blk-mq.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'block/blk-mq.c') diff --git a/block/blk-mq.c b/block/blk-mq.c index e04b759add75..176698b2285b 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3261,9 +3261,11 @@ static int __blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set) { int i; - for (i = 0; i < set->nr_hw_queues; i++) + for (i = 0; i < set->nr_hw_queues; i++) { if (!__blk_mq_alloc_map_and_request(set, i)) goto out_unwind; + cond_resched(); + } return 0; -- cgit v1.2.3 From 93f221ae08381e994ac9f9ff6aa743e612e49718 Mon Sep 17 00:00:00 2001 From: Eric Biggers Date: Tue, 15 Sep 2020 20:53:14 -0700 Subject: block: make blk_crypto_rq_bio_prep() able to fail blk_crypto_rq_bio_prep() assumes its gfp_mask argument always includes __GFP_DIRECT_RECLAIM, so that the mempool_alloc() will always succeed. However, blk_crypto_rq_bio_prep() might be called with GFP_ATOMIC via setup_clone() in drivers/md/dm-rq.c. This case isn't currently reachable with a bio that actually has an encryption context. However, it's fragile to rely on this. Just make blk_crypto_rq_bio_prep() able to fail. Suggested-by: Satya Tangirala Signed-off-by: Eric Biggers Reviewed-by: Mike Snitzer Reviewed-by: Satya Tangirala Cc: Miaohe Lin Signed-off-by: Jens Axboe --- block/blk-core.c | 8 +++++--- block/blk-crypto-internal.h | 21 ++++++++++++++++----- block/blk-crypto.c | 18 +++++++----------- block/blk-mq.c | 7 ++++++- 4 files changed, 34 insertions(+), 20 deletions(-) (limited to 'block/blk-mq.c') diff --git a/block/blk-core.c b/block/blk-core.c index 4884f1e7451b..3b01e7f3c7a3 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1617,8 +1617,10 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, if (rq->bio) { rq->biotail->bi_next = bio; rq->biotail = bio; - } else + } else { rq->bio = rq->biotail = bio; + } + bio = NULL; } /* Copy attributes of the original request to the clone request. */ @@ -1631,8 +1633,8 @@ int blk_rq_prep_clone(struct request *rq, struct request *rq_src, rq->nr_phys_segments = rq_src->nr_phys_segments; rq->ioprio = rq_src->ioprio; - if (rq->bio) - blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask); + if (rq->bio && blk_crypto_rq_bio_prep(rq, rq->bio, gfp_mask) < 0) + goto free_and_out; return 0; diff --git a/block/blk-crypto-internal.h b/block/blk-crypto-internal.h index d2b0f565d83c..0d36aae538d7 100644 --- a/block/blk-crypto-internal.h +++ b/block/blk-crypto-internal.h @@ -142,13 +142,24 @@ static inline void blk_crypto_free_request(struct request *rq) __blk_crypto_free_request(rq); } -void __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio, - gfp_t gfp_mask); -static inline void blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio, - gfp_t gfp_mask) +int __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio, + gfp_t gfp_mask); +/** + * blk_crypto_rq_bio_prep - Prepare a request's crypt_ctx when its first bio + * is inserted + * @rq: The request to prepare + * @bio: The first bio being inserted into the request + * @gfp_mask: Memory allocation flags + * + * Return: 0 on success, -ENOMEM if out of memory. -ENOMEM is only possible if + * @gfp_mask doesn't include %__GFP_DIRECT_RECLAIM. + */ +static inline int blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio, + gfp_t gfp_mask) { if (bio_has_crypt_ctx(bio)) - __blk_crypto_rq_bio_prep(rq, bio, gfp_mask); + return __blk_crypto_rq_bio_prep(rq, bio, gfp_mask); + return 0; } /** diff --git a/block/blk-crypto.c b/block/blk-crypto.c index a3f27a19067c..bbe7974fd74f 100644 --- a/block/blk-crypto.c +++ b/block/blk-crypto.c @@ -283,20 +283,16 @@ fail: return false; } -/** - * __blk_crypto_rq_bio_prep - Prepare a request's crypt_ctx when its first bio - * is inserted - * - * @rq: The request to prepare - * @bio: The first bio being inserted into the request - * @gfp_mask: gfp mask - */ -void __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio, - gfp_t gfp_mask) +int __blk_crypto_rq_bio_prep(struct request *rq, struct bio *bio, + gfp_t gfp_mask) { - if (!rq->crypt_ctx) + if (!rq->crypt_ctx) { rq->crypt_ctx = mempool_alloc(bio_crypt_ctx_pool, gfp_mask); + if (!rq->crypt_ctx) + return -ENOMEM; + } *rq->crypt_ctx = *bio->bi_crypt_context; + return 0; } /** diff --git a/block/blk-mq.c b/block/blk-mq.c index 176698b2285b..2e4b3cad2a61 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1940,13 +1940,18 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) static void blk_mq_bio_to_request(struct request *rq, struct bio *bio, unsigned int nr_segs) { + int err; + if (bio->bi_opf & REQ_RAHEAD) rq->cmd_flags |= REQ_FAILFAST_MASK; rq->__sector = bio->bi_iter.bi_sector; rq->write_hint = bio->bi_write_hint; blk_rq_bio_prep(rq, bio, nr_segs); - blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO); + + /* This can't fail, since GFP_NOIO includes __GFP_DIRECT_RECLAIM. */ + err = blk_crypto_rq_bio_prep(rq, bio, GFP_NOIO); + WARN_ON_ONCE(err); blk_account_io_start(rq); } -- cgit v1.2.3 From a926c7afffcc0f2e35e6acbccb16921bacf34617 Mon Sep 17 00:00:00 2001 From: Gabriel Krisman Bertazi Date: Tue, 6 Oct 2020 15:41:25 -0400 Subject: block: Consider only dispatched requests for inflight statistic According to Documentation/block/stat.rst, inflight should not include I/O requests that are in the queue but not yet dispatched to the device, but blk-mq identifies as inflight any request that has a tag allocated, which, for queues without elevator, happens at request allocation time and before it is queued in the ctx (default case in blk_mq_submit_bio). In addition, current behavior is different for queues with elevator from queues without it, since for the former the driver tag is allocated at dispatch time. A more precise approach would be to only consider requests with state MQ_RQ_IN_FLIGHT. This effectively reverts commit 6131837b1de6 ("blk-mq: count allocated but not started requests in iostats inflight") to consolidate blk-mq behavior with itself (elevator case) and with original documentation, but it differs from the behavior used by the legacy path. This version differs from v1 by using blk_mq_rq_state to access the state attribute. Avoid using blk_mq_request_started, which was suggested, since we don't want to include MQ_RQ_COMPLETE. Signed-off-by: Gabriel Krisman Bertazi Cc: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-mq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'block/blk-mq.c') diff --git a/block/blk-mq.c b/block/blk-mq.c index 2e4b3cad2a61..c5fefd39d0c0 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -105,7 +105,7 @@ static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx, { struct mq_inflight *mi = priv; - if (rq->part == mi->part) + if (rq->part == mi->part && blk_mq_rq_state(rq) == MQ_RQ_IN_FLIGHT) mi->inflight[rq_data_dir(rq)]++; return true; -- cgit v1.2.3 From 0841031ab9a8fb2551880c24a8419997b8e834bc Mon Sep 17 00:00:00 2001 From: Yufen Yu Date: Thu, 8 Oct 2020 23:26:30 -0400 Subject: blk-mq: use helper function to test hw stopped We have introduced helper function blk_mq_hctx_stopped() to test BLK_MQ_S_STOPPED. Signed-off-by: Yufen Yu Signed-off-by: Jens Axboe --- block/blk-mq.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'block/blk-mq.c') diff --git a/block/blk-mq.c b/block/blk-mq.c index c5fefd39d0c0..e11ee801ba19 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1807,7 +1807,7 @@ static void blk_mq_run_work_fn(struct work_struct *work) /* * If we are stopped, don't run the queue. */ - if (test_bit(BLK_MQ_S_STOPPED, &hctx->state)) + if (blk_mq_hctx_stopped(hctx)) return; __blk_mq_run_hw_queue(hctx); -- cgit v1.2.3