From efe1f3a1d5833c0ddd61ee50dbef8908f65a0a5e Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 22 Jan 2021 10:33:06 +0800 Subject: scsi: sbitmap: Maintain allocation round_robin in sbitmap Currently the allocation round_robin info is maintained by sbitmap_queue. However, bit allocation really belongs to sbitmap. Move it there. Link: https://lore.kernel.org/r/20210122023317.687987-3-ming.lei@redhat.com Cc: Omar Sandoval Cc: Kashyap Desai Cc: Sumanesh Samanta Cc: Ewan D. Milne Cc: Hannes Reinecke Cc: virtualization@lists.linux-foundation.org Tested-by: Sumanesh Samanta Reviewed-by: Hannes Reinecke Signed-off-by: Ming Lei Signed-off-by: Martin K. Petersen --- 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 d4d7c1caa439..f133bbfa6cd4 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2702,7 +2702,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, goto free_cpumask; if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8), - gfp, node)) + gfp, node, false)) goto free_ctxs; hctx->nr_ctx = 0; -- cgit v1.2.3 From c548e62bcf6adc7066ff201e9ecc88e536dd8890 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 22 Jan 2021 10:33:08 +0800 Subject: scsi: sbitmap: Move allocation hint into sbitmap Allocation hint should have belonged to sbitmap. Also, when sbitmap's depth is high and there is no need to use mulitple wakeup queues, user can benefit from percpu allocation hint too. Move allocation hint into sbitmap, then SCSI device queue can benefit from allocation hint when converting to plain sbitmap. Convert vhost/scsi.c to use sbitmap allocation with percpu alloc hint. This is more efficient than the previous approach. Link: https://lore.kernel.org/r/20210122023317.687987-5-ming.lei@redhat.com Cc: Omar Sandoval Cc: Kashyap Desai Cc: Sumanesh Samanta Cc: Ewan D. Milne Cc: Mike Christie Cc: virtualization@lists.linux-foundation.org Tested-by: Sumanesh Samanta Reviewed-by: Hannes Reinecke Signed-off-by: Ming Lei Signed-off-by: Martin K. Petersen --- block/blk-mq.c | 2 +- block/kyber-iosched.c | 2 +- drivers/vhost/scsi.c | 4 +- include/linux/sbitmap.h | 41 +++++++++++------- lib/sbitmap.c | 112 ++++++++++++++++++++++++++++-------------------- 5 files changed, 96 insertions(+), 65 deletions(-) (limited to 'block/blk-mq.c') diff --git a/block/blk-mq.c b/block/blk-mq.c index f133bbfa6cd4..2e8c94e00f58 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2702,7 +2702,7 @@ blk_mq_alloc_hctx(struct request_queue *q, struct blk_mq_tag_set *set, goto free_cpumask; if (sbitmap_init_node(&hctx->ctx_map, nr_cpu_ids, ilog2(8), - gfp, node, false)) + gfp, node, false, false)) goto free_ctxs; hctx->nr_ctx = 0; diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index d39ac13f0105..8969e122f081 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -479,7 +479,7 @@ static int kyber_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx) for (i = 0; i < KYBER_NUM_DOMAINS; i++) { if (sbitmap_init_node(&khd->kcq_map[i], hctx->nr_ctx, ilog2(8), GFP_KERNEL, hctx->numa_node, - false)) { + false, false)) { while (--i >= 0) sbitmap_free(&khd->kcq_map[i]); goto err_kcqs; diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c index 3412a3ad28e6..936584250a0b 100644 --- a/drivers/vhost/scsi.c +++ b/drivers/vhost/scsi.c @@ -614,7 +614,7 @@ vhost_scsi_get_cmd(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg, return ERR_PTR(-EIO); } - tag = sbitmap_get(&svq->scsi_tags, 0); + tag = sbitmap_get(&svq->scsi_tags); if (tag < 0) { pr_err("Unable to obtain tag for vhost_scsi_cmd\n"); return ERR_PTR(-ENOMEM); @@ -1512,7 +1512,7 @@ static int vhost_scsi_setup_vq_cmds(struct vhost_virtqueue *vq, int max_cmds) return 0; if (sbitmap_init_node(&svq->scsi_tags, max_cmds, -1, GFP_KERNEL, - NUMA_NO_NODE, false)) + NUMA_NO_NODE, false, true)) return -ENOMEM; svq->max_cmds = max_cmds; diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h index 734ee6214cd6..247776fcc02c 100644 --- a/include/linux/sbitmap.h +++ b/include/linux/sbitmap.h @@ -65,6 +65,14 @@ struct sbitmap { * @map: Allocated bitmap. */ struct sbitmap_word *map; + + /* + * @alloc_hint: Cache of last successfully allocated or freed bit. + * + * This is per-cpu, which allows multiple users to stick to different + * cachelines until the map is exhausted. + */ + unsigned int __percpu *alloc_hint; }; #define SBQ_WAIT_QUEUES 8 @@ -100,14 +108,6 @@ struct sbitmap_queue { */ struct sbitmap sb; - /* - * @alloc_hint: Cache of last successfully allocated or freed bit. - * - * This is per-cpu, which allows multiple users to stick to different - * cachelines until the map is exhausted. - */ - unsigned int __percpu *alloc_hint; - /** * @wake_batch: Number of bits which must be freed before we wake up any * waiters. @@ -147,11 +147,13 @@ struct sbitmap_queue { * @round_robin: If true, be stricter about allocation order; always allocate * starting from the last allocated bit. This is less efficient * than the default behavior (false). + * @alloc_hint: If true, apply percpu hint for where to start searching for + * a free bit. * * Return: Zero on success or negative errno on failure. */ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, - gfp_t flags, int node, bool round_robin); + gfp_t flags, int node, bool round_robin, bool alloc_hint); /** * sbitmap_free() - Free memory used by a &struct sbitmap. @@ -159,6 +161,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, */ static inline void sbitmap_free(struct sbitmap *sb) { + free_percpu(sb->alloc_hint); kfree(sb->map); sb->map = NULL; } @@ -176,19 +179,17 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth); /** * sbitmap_get() - Try to allocate a free bit from a &struct sbitmap. * @sb: Bitmap to allocate from. - * @alloc_hint: Hint for where to start searching for a free bit. * * This operation provides acquire barrier semantics if it succeeds. * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ -int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint); +int sbitmap_get(struct sbitmap *sb); /** * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap, * limiting the depth used from each word. * @sb: Bitmap to allocate from. - * @alloc_hint: Hint for where to start searching for a free bit. * @shallow_depth: The maximum number of bits to allocate from a single word. * * This rather specific operation allows for having multiple users with @@ -200,8 +201,7 @@ int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint); * * Return: Non-negative allocated bit number if successful, -1 otherwise. */ -int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint, - unsigned long shallow_depth); +int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth); /** * sbitmap_any_bit_set() - Check for a set bit in a &struct sbitmap. @@ -315,6 +315,18 @@ static inline void sbitmap_deferred_clear_bit(struct sbitmap *sb, unsigned int b set_bit(SB_NR_TO_BIT(sb, bitnr), addr); } +/* + * Pair of sbitmap_get, and this one applies both cleared bit and + * allocation hint. + */ +static inline void sbitmap_put(struct sbitmap *sb, unsigned int bitnr) +{ + sbitmap_deferred_clear_bit(sb, bitnr); + + if (likely(sb->alloc_hint && !sb->round_robin && bitnr < sb->depth)) + *this_cpu_ptr(sb->alloc_hint) = bitnr; +} + static inline int sbitmap_test_bit(struct sbitmap *sb, unsigned int bitnr) { return test_bit(SB_NR_TO_BIT(sb, bitnr), __sbitmap_word(sb, bitnr)); @@ -363,7 +375,6 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, static inline void sbitmap_queue_free(struct sbitmap_queue *sbq) { kfree(sbq->ws); - free_percpu(sbq->alloc_hint); sbitmap_free(&sbq->sb); } diff --git a/lib/sbitmap.c b/lib/sbitmap.c index 2b43a6aefec3..e395435654aa 100644 --- a/lib/sbitmap.c +++ b/lib/sbitmap.c @@ -9,52 +9,51 @@ #include #include -static int init_alloc_hint(struct sbitmap_queue *sbq, gfp_t flags) +static int init_alloc_hint(struct sbitmap *sb, gfp_t flags) { - unsigned depth = sbq->sb.depth; + unsigned depth = sb->depth; - sbq->alloc_hint = alloc_percpu_gfp(unsigned int, flags); - if (!sbq->alloc_hint) + sb->alloc_hint = alloc_percpu_gfp(unsigned int, flags); + if (!sb->alloc_hint) return -ENOMEM; - if (depth && !sbq->sb.round_robin) { + if (depth && !sb->round_robin) { int i; for_each_possible_cpu(i) - *per_cpu_ptr(sbq->alloc_hint, i) = prandom_u32() % depth; + *per_cpu_ptr(sb->alloc_hint, i) = prandom_u32() % depth; } - return 0; } -static inline unsigned update_alloc_hint_before_get(struct sbitmap_queue *sbq, +static inline unsigned update_alloc_hint_before_get(struct sbitmap *sb, unsigned int depth) { unsigned hint; - hint = this_cpu_read(*sbq->alloc_hint); + hint = this_cpu_read(*sb->alloc_hint); if (unlikely(hint >= depth)) { hint = depth ? prandom_u32() % depth : 0; - this_cpu_write(*sbq->alloc_hint, hint); + this_cpu_write(*sb->alloc_hint, hint); } return hint; } -static inline void update_alloc_hint_after_get(struct sbitmap_queue *sbq, +static inline void update_alloc_hint_after_get(struct sbitmap *sb, unsigned int depth, unsigned int hint, unsigned int nr) { if (nr == -1) { /* If the map is full, a hint won't do us much good. */ - this_cpu_write(*sbq->alloc_hint, 0); - } else if (nr == hint || unlikely(sbq->sb.round_robin)) { + this_cpu_write(*sb->alloc_hint, 0); + } else if (nr == hint || unlikely(sb->round_robin)) { /* Only update the hint if we used it. */ hint = nr + 1; if (hint >= depth - 1) hint = 0; - this_cpu_write(*sbq->alloc_hint, hint); + this_cpu_write(*sb->alloc_hint, hint); } } @@ -82,7 +81,8 @@ static inline bool sbitmap_deferred_clear(struct sbitmap_word *map) } int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, - gfp_t flags, int node, bool round_robin) + gfp_t flags, int node, bool round_robin, + bool alloc_hint) { unsigned int bits_per_word; unsigned int i; @@ -114,9 +114,18 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift, return 0; } + if (alloc_hint) { + if (init_alloc_hint(sb, flags)) + return -ENOMEM; + } else { + sb->alloc_hint = NULL; + } + sb->map = kcalloc_node(sb->map_nr, sizeof(*sb->map), flags, node); - if (!sb->map) + if (!sb->map) { + free_percpu(sb->alloc_hint); return -ENOMEM; + } for (i = 0; i < sb->map_nr; i++) { sb->map[i].depth = min(depth, bits_per_word); @@ -196,7 +205,7 @@ static int sbitmap_find_bit_in_index(struct sbitmap *sb, int index, return nr; } -int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint) +static int __sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint) { unsigned int i, index; int nr = -1; @@ -228,10 +237,27 @@ int sbitmap_get(struct sbitmap *sb, unsigned int alloc_hint) return nr; } + +int sbitmap_get(struct sbitmap *sb) +{ + int nr; + unsigned int hint, depth; + + if (WARN_ON_ONCE(unlikely(!sb->alloc_hint))) + return -1; + + depth = READ_ONCE(sb->depth); + hint = update_alloc_hint_before_get(sb, depth); + nr = __sbitmap_get(sb, hint); + update_alloc_hint_after_get(sb, depth, hint, nr); + + return nr; +} EXPORT_SYMBOL_GPL(sbitmap_get); -int sbitmap_get_shallow(struct sbitmap *sb, unsigned int alloc_hint, - unsigned long shallow_depth) +static int __sbitmap_get_shallow(struct sbitmap *sb, + unsigned int alloc_hint, + unsigned long shallow_depth) { unsigned int i, index; int nr = -1; @@ -263,6 +289,22 @@ again: return nr; } + +int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth) +{ + int nr; + unsigned int hint, depth; + + if (WARN_ON_ONCE(unlikely(!sb->alloc_hint))) + return -1; + + depth = READ_ONCE(sb->depth); + hint = update_alloc_hint_before_get(sb, depth); + nr = __sbitmap_get_shallow(sb, hint, shallow_depth); + update_alloc_hint_after_get(sb, depth, hint, nr); + + return nr; +} EXPORT_SYMBOL_GPL(sbitmap_get_shallow); bool sbitmap_any_bit_set(const struct sbitmap *sb) @@ -400,15 +442,10 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, int i; ret = sbitmap_init_node(&sbq->sb, depth, shift, flags, node, - round_robin); + round_robin, true); if (ret) return ret; - if (init_alloc_hint(sbq, flags) != 0) { - sbitmap_free(&sbq->sb); - return -ENOMEM; - } - sbq->min_shallow_depth = UINT_MAX; sbq->wake_batch = sbq_calc_wake_batch(sbq, depth); atomic_set(&sbq->wake_index, 0); @@ -416,7 +453,6 @@ int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth, sbq->ws = kzalloc_node(SBQ_WAIT_QUEUES * sizeof(*sbq->ws), flags, node); if (!sbq->ws) { - free_percpu(sbq->alloc_hint); sbitmap_free(&sbq->sb); return -ENOMEM; } @@ -458,32 +494,16 @@ EXPORT_SYMBOL_GPL(sbitmap_queue_resize); int __sbitmap_queue_get(struct sbitmap_queue *sbq) { - unsigned int hint, depth; - int nr; - - depth = READ_ONCE(sbq->sb.depth); - hint = update_alloc_hint_before_get(sbq, depth); - nr = sbitmap_get(&sbq->sb, hint); - update_alloc_hint_after_get(sbq, depth, hint, nr); - - return nr; + return sbitmap_get(&sbq->sb); } EXPORT_SYMBOL_GPL(__sbitmap_queue_get); int __sbitmap_queue_get_shallow(struct sbitmap_queue *sbq, unsigned int shallow_depth) { - unsigned int hint, depth; - int nr; - WARN_ON_ONCE(shallow_depth < sbq->min_shallow_depth); - depth = READ_ONCE(sbq->sb.depth); - hint = update_alloc_hint_before_get(sbq, depth); - nr = sbitmap_get_shallow(&sbq->sb, hint, shallow_depth); - update_alloc_hint_after_get(sbq, depth, hint, nr); - - return nr; + return sbitmap_get_shallow(&sbq->sb, shallow_depth); } EXPORT_SYMBOL_GPL(__sbitmap_queue_get_shallow); @@ -592,7 +612,7 @@ void sbitmap_queue_clear(struct sbitmap_queue *sbq, unsigned int nr, sbitmap_queue_wake_up(sbq); if (likely(!sbq->sb.round_robin && nr < sbq->sb.depth)) - *per_cpu_ptr(sbq->alloc_hint, cpu) = nr; + *per_cpu_ptr(sbq->sb.alloc_hint, cpu) = nr; } EXPORT_SYMBOL_GPL(sbitmap_queue_clear); @@ -630,7 +650,7 @@ void sbitmap_queue_show(struct sbitmap_queue *sbq, struct seq_file *m) if (!first) seq_puts(m, ", "); first = false; - seq_printf(m, "%u", *per_cpu_ptr(sbq->alloc_hint, i)); + seq_printf(m, "%u", *per_cpu_ptr(sbq->sb.alloc_hint, i)); } seq_puts(m, "}\n"); -- cgit v1.2.3 From 2a5a24aa83382a88c43d18a901fab66e6ffe1199 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 22 Jan 2021 10:33:12 +0800 Subject: scsi: blk-mq: Return budget token from .get_budget callback SCSI uses a global atomic variable to track queue depth for each LUN/request queue. This doesn't scale well when there are lots of CPU cores and the disk is very fast. It has been observed that IOPS is affected a lot by tracking queue depth via sdev->device_busy in the I/O path. Return budget token from .get_budget callback. The budget token can be passed to driver so that we can replace the atomic variable with sbitmap_queue and alleviate the scaling problems that way. Link: https://lore.kernel.org/r/20210122023317.687987-9-ming.lei@redhat.com Cc: Omar Sandoval Cc: Kashyap Desai Cc: Sumanesh Samanta Cc: Ewan D. Milne Tested-by: Sumanesh Samanta Reviewed-by: Hannes Reinecke Signed-off-by: Ming Lei Signed-off-by: Martin K. Petersen --- block/blk-mq-sched.c | 17 +++++++++++++---- block/blk-mq.c | 36 +++++++++++++++++++++++++----------- block/blk-mq.h | 25 +++++++++++++++++++++---- drivers/scsi/scsi_lib.c | 16 +++++++++++----- include/linux/blk-mq.h | 4 ++-- 5 files changed, 72 insertions(+), 26 deletions(-) (limited to 'block/blk-mq.c') diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index ddb65e9e6fd9..712b7f0afd63 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -131,6 +131,7 @@ static int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) do { struct request *rq; + int budget_token; if (e->type->ops.has_work && !e->type->ops.has_work(hctx)) break; @@ -140,12 +141,13 @@ static int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) break; } - if (!blk_mq_get_dispatch_budget(q)) + budget_token = blk_mq_get_dispatch_budget(q); + if (budget_token < 0) break; rq = e->type->ops.dispatch_request(hctx); if (!rq) { - blk_mq_put_dispatch_budget(q); + blk_mq_put_dispatch_budget(q, budget_token); /* * We're releasing without dispatching. Holding the * budget could have blocked any "hctx"s with the @@ -157,6 +159,8 @@ static int __blk_mq_do_dispatch_sched(struct blk_mq_hw_ctx *hctx) break; } + blk_mq_set_rq_budget_token(rq, budget_token); + /* * Now this rq owns the budget which has to be released * if this rq won't be queued to driver via .queue_rq() @@ -230,6 +234,8 @@ static int blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) struct request *rq; do { + int budget_token; + if (!list_empty_careful(&hctx->dispatch)) { ret = -EAGAIN; break; @@ -238,12 +244,13 @@ static int blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) if (!sbitmap_any_bit_set(&hctx->ctx_map)) break; - if (!blk_mq_get_dispatch_budget(q)) + budget_token = blk_mq_get_dispatch_budget(q); + if (budget_token < 0) break; rq = blk_mq_dequeue_from_ctx(hctx, ctx); if (!rq) { - blk_mq_put_dispatch_budget(q); + blk_mq_put_dispatch_budget(q, budget_token); /* * We're releasing without dispatching. Holding the * budget could have blocked any "hctx"s with the @@ -255,6 +262,8 @@ static int blk_mq_do_dispatch_ctx(struct blk_mq_hw_ctx *hctx) break; } + blk_mq_set_rq_budget_token(rq, budget_token); + /* * Now this rq owns the budget which has to be released * if this rq won't be queued to driver via .queue_rq() diff --git a/block/blk-mq.c b/block/blk-mq.c index 2e8c94e00f58..2e825a7a3606 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1277,10 +1277,15 @@ static enum prep_dispatch blk_mq_prep_dispatch_rq(struct request *rq, bool need_budget) { struct blk_mq_hw_ctx *hctx = rq->mq_hctx; + int budget_token = -1; - if (need_budget && !blk_mq_get_dispatch_budget(rq->q)) { - blk_mq_put_driver_tag(rq); - return PREP_DISPATCH_NO_BUDGET; + if (need_budget) { + budget_token = blk_mq_get_dispatch_budget(rq->q); + if (budget_token < 0) { + blk_mq_put_driver_tag(rq); + return PREP_DISPATCH_NO_BUDGET; + } + blk_mq_set_rq_budget_token(rq, budget_token); } if (!blk_mq_get_driver_tag(rq)) { @@ -1297,7 +1302,7 @@ static enum prep_dispatch blk_mq_prep_dispatch_rq(struct request *rq, * together during handling partial dispatch */ if (need_budget) - blk_mq_put_dispatch_budget(rq->q); + blk_mq_put_dispatch_budget(rq->q, budget_token); return PREP_DISPATCH_NO_TAG; } } @@ -1307,12 +1312,16 @@ static enum prep_dispatch blk_mq_prep_dispatch_rq(struct request *rq, /* release all allocated budgets before calling to blk_mq_dispatch_rq_list */ static void blk_mq_release_budgets(struct request_queue *q, - unsigned int nr_budgets) + struct list_head *list) { - int i; + struct request *rq; - for (i = 0; i < nr_budgets; i++) - blk_mq_put_dispatch_budget(q); + list_for_each_entry(rq, list, queuelist) { + int budget_token = blk_mq_get_rq_budget_token(rq); + + if (budget_token >= 0) + blk_mq_put_dispatch_budget(q, budget_token); + } } /* @@ -1410,7 +1419,8 @@ out: (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED); bool no_budget_avail = prep == PREP_DISPATCH_NO_BUDGET; - blk_mq_release_budgets(q, nr_budgets); + if (nr_budgets) + blk_mq_release_budgets(q, list); spin_lock(&hctx->lock); list_splice_tail_init(list, &hctx->dispatch); @@ -2009,6 +2019,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, { struct request_queue *q = rq->q; bool run_queue = true; + int budget_token; /* * RCU or SRCU read lock is needed before checking quiesced flag. @@ -2026,11 +2037,14 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx, if (q->elevator && !bypass_insert) goto insert; - if (!blk_mq_get_dispatch_budget(q)) + budget_token = blk_mq_get_dispatch_budget(q); + if (budget_token < 0) goto insert; + blk_mq_set_rq_budget_token(rq, budget_token); + if (!blk_mq_get_driver_tag(rq)) { - blk_mq_put_dispatch_budget(q); + blk_mq_put_dispatch_budget(q, budget_token); goto insert; } diff --git a/block/blk-mq.h b/block/blk-mq.h index 3616453ca28c..9ce64bc4a6c8 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -187,17 +187,34 @@ unsigned int blk_mq_in_flight(struct request_queue *q, void blk_mq_in_flight_rw(struct request_queue *q, struct block_device *part, unsigned int inflight[2]); -static inline void blk_mq_put_dispatch_budget(struct request_queue *q) +static inline void blk_mq_put_dispatch_budget(struct request_queue *q, + int budget_token) { if (q->mq_ops->put_budget) - q->mq_ops->put_budget(q); + q->mq_ops->put_budget(q, budget_token); } -static inline bool blk_mq_get_dispatch_budget(struct request_queue *q) +static inline int blk_mq_get_dispatch_budget(struct request_queue *q) { if (q->mq_ops->get_budget) return q->mq_ops->get_budget(q); - return true; + return 0; +} + +static inline void blk_mq_set_rq_budget_token(struct request *rq, int token) +{ + if (token < 0) + return; + + if (rq->q->mq_ops->set_rq_budget_token) + rq->q->mq_ops->set_rq_budget_token(rq, token); +} + +static inline int blk_mq_get_rq_budget_token(struct request *rq) +{ + if (rq->q->mq_ops->get_rq_budget_token) + return rq->q->mq_ops->get_rq_budget_token(rq); + return -1; } static inline void __blk_mq_inc_active_requests(struct blk_mq_hw_ctx *hctx) diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c index 02da34ab335d..dae9f66caffd 100644 --- a/drivers/scsi/scsi_lib.c +++ b/drivers/scsi/scsi_lib.c @@ -329,6 +329,7 @@ void scsi_device_unbusy(struct scsi_device *sdev, struct scsi_cmnd *cmd) atomic_dec(&starget->target_busy); atomic_dec(&sdev->device_busy); + cmd->budget_token = -1; } static void scsi_kick_queue(struct request_queue *q) @@ -1143,6 +1144,7 @@ void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd) unsigned long jiffies_at_alloc; int retries, to_clear; bool in_flight; + int budget_token = cmd->budget_token; if (!blk_rq_is_scsi(rq) && !(flags & SCMD_INITIALIZED)) { flags |= SCMD_INITIALIZED; @@ -1171,6 +1173,7 @@ void scsi_init_command(struct scsi_device *dev, struct scsi_cmnd *cmd) cmd->retries = retries; if (in_flight) __set_bit(SCMD_STATE_INFLIGHT, &cmd->state); + cmd->budget_token = budget_token; } @@ -1605,19 +1608,19 @@ static void scsi_mq_done(struct scsi_cmnd *cmd) blk_mq_complete_request(cmd->request); } -static void scsi_mq_put_budget(struct request_queue *q) +static void scsi_mq_put_budget(struct request_queue *q, int budget_token) { struct scsi_device *sdev = q->queuedata; atomic_dec(&sdev->device_busy); } -static bool scsi_mq_get_budget(struct request_queue *q) +static int scsi_mq_get_budget(struct request_queue *q) { struct scsi_device *sdev = q->queuedata; if (scsi_dev_queue_ready(q, sdev)) - return true; + return 0; atomic_inc(&sdev->restarts); @@ -1639,7 +1642,7 @@ static bool scsi_mq_get_budget(struct request_queue *q) if (unlikely(atomic_read(&sdev->device_busy) == 0 && !scsi_device_blocked(sdev))) blk_mq_delay_run_hw_queues(sdev->request_queue, SCSI_QUEUE_DELAY); - return false; + return -1; } static void scsi_mq_set_rq_budget_token(struct request *req, int token) @@ -1667,6 +1670,8 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx, blk_status_t ret; int reason; + WARN_ON_ONCE(cmd->budget_token < 0); + /* * If the device is not in running state we will reject some or all * commands. @@ -1718,7 +1723,8 @@ out_dec_target_busy: if (scsi_target(sdev)->can_queue > 0) atomic_dec(&scsi_target(sdev)->target_busy); out_put_budget: - scsi_mq_put_budget(q); + scsi_mq_put_budget(q, cmd->budget_token); + cmd->budget_token = -1; switch (ret) { case BLK_STS_OK: break; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 5fae401f083d..3bd3ee651143 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -306,12 +306,12 @@ struct blk_mq_ops { * reserved budget. Also we have to handle failure case * of .get_budget for avoiding I/O deadlock. */ - bool (*get_budget)(struct request_queue *); + int (*get_budget)(struct request_queue *); /** * @put_budget: Release the reserved budget. */ - void (*put_budget)(struct request_queue *); + void (*put_budget)(struct request_queue *, int); /* * @set_rq_budget_toekn: store rq's budget token -- cgit v1.2.3