diff options
Diffstat (limited to 'block')
| -rw-r--r-- | block/bio.c | 21 | ||||
| -rw-r--r-- | block/blk-core.c | 4 | ||||
| -rw-r--r-- | block/blk-merge.c | 55 | ||||
| -rw-r--r-- | block/blk-mq.c | 76 | ||||
| -rw-r--r-- | block/blk-throttle.c | 6 | ||||
| -rw-r--r-- | block/elevator.c | 2 |
6 files changed, 93 insertions, 71 deletions
diff --git a/block/bio.c b/block/bio.c index f39477538fef..aa7354088008 100644 --- a/block/bio.c +++ b/block/bio.c @@ -667,18 +667,19 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; - if (bio_op(bio) == REQ_OP_DISCARD) - goto integrity_clone; - - if (bio_op(bio) == REQ_OP_WRITE_SAME) { + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: + break; + case REQ_OP_WRITE_SAME: bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0]; - goto integrity_clone; + break; + default: + bio_for_each_segment(bv, bio_src, iter) + bio->bi_io_vec[bio->bi_vcnt++] = bv; + break; } - bio_for_each_segment(bv, bio_src, iter) - bio->bi_io_vec[bio->bi_vcnt++] = bv; - -integrity_clone: if (bio_integrity(bio_src)) { int ret; @@ -1788,7 +1789,7 @@ struct bio *bio_split(struct bio *bio, int sectors, * Discards need a mutable bio_vec to accommodate the payload * required by the DSM TRIM and UNMAP commands. */ - if (bio_op(bio) == REQ_OP_DISCARD) + if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE) split = bio_clone_bioset(bio, gfp, bs); else split = bio_clone_fast(bio, gfp, bs); diff --git a/block/blk-core.c b/block/blk-core.c index 999442ec4601..36c7ac328d8c 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -515,7 +515,9 @@ EXPORT_SYMBOL_GPL(blk_queue_bypass_end); void blk_set_queue_dying(struct request_queue *q) { - queue_flag_set_unlocked(QUEUE_FLAG_DYING, q); + spin_lock_irq(q->queue_lock); + queue_flag_set(QUEUE_FLAG_DYING, q); + spin_unlock_irq(q->queue_lock); if (q->mq_ops) blk_mq_wake_waiters(q); diff --git a/block/blk-merge.c b/block/blk-merge.c index 3eec75a9e91d..2642e5fc8b69 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -94,9 +94,31 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, bool do_split = true; struct bio *new = NULL; const unsigned max_sectors = get_max_io_size(q, bio); + unsigned bvecs = 0; bio_for_each_segment(bv, bio, iter) { /* + * With arbitrary bio size, the incoming bio may be very + * big. We have to split the bio into small bios so that + * each holds at most BIO_MAX_PAGES bvecs because + * bio_clone() can fail to allocate big bvecs. + * + * It should have been better to apply the limit per + * request queue in which bio_clone() is involved, + * instead of globally. The biggest blocker is the + * bio_clone() in bio bounce. + * + * If bio is splitted by this reason, we should have + * allowed to continue bios merging, but don't do + * that now for making the change simple. + * + * TODO: deal with bio bounce's bio_clone() gracefully + * and convert the global limit into per-queue limit. + */ + if (bvecs++ >= BIO_MAX_PAGES) + goto split; + + /* * If the queue doesn't support SG gaps and adding this * offset would create a gap, disallow it. */ @@ -172,12 +194,18 @@ void blk_queue_split(struct request_queue *q, struct bio **bio, struct bio *split, *res; unsigned nsegs; - if (bio_op(*bio) == REQ_OP_DISCARD) + switch (bio_op(*bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: split = blk_bio_discard_split(q, *bio, bs, &nsegs); - else if (bio_op(*bio) == REQ_OP_WRITE_SAME) + break; + case REQ_OP_WRITE_SAME: split = blk_bio_write_same_split(q, *bio, bs, &nsegs); - else + break; + default: split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs); + break; + } /* physical segments can be figured out during splitting */ res = split ? split : *bio; @@ -213,7 +241,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, * This should probably be returning 0, but blk_add_request_payload() * (Christoph!!!!) */ - if (bio_op(bio) == REQ_OP_DISCARD) + if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE) return 1; if (bio_op(bio) == REQ_OP_WRITE_SAME) @@ -385,7 +413,9 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, nsegs = 0; cluster = blk_queue_cluster(q); - if (bio_op(bio) == REQ_OP_DISCARD) { + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: /* * This is a hack - drivers should be neither modifying the * biovec, nor relying on bi_vcnt - but because of @@ -393,19 +423,16 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, * a payload we need to set up here (thank you Christoph) and * bi_vcnt is really the only way of telling if we need to. */ - - if (bio->bi_vcnt) - goto single_segment; - - return 0; - } - - if (bio_op(bio) == REQ_OP_WRITE_SAME) { -single_segment: + if (!bio->bi_vcnt) + return 0; + /* Fall through */ + case REQ_OP_WRITE_SAME: *sg = sglist; bvec = bio_iovec(bio); sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset); return 1; + default: + break; } for_each_bio(bio) diff --git a/block/blk-mq.c b/block/blk-mq.c index e931a0e8e73d..c207fa9870eb 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -296,17 +296,29 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, int rw, if (ret) return ERR_PTR(ret); + /* + * Check if the hardware context is actually mapped to anything. + * If not tell the caller that it should skip this queue. + */ hctx = q->queue_hw_ctx[hctx_idx]; + if (!blk_mq_hw_queue_mapped(hctx)) { + ret = -EXDEV; + goto out_queue_exit; + } ctx = __blk_mq_get_ctx(q, cpumask_first(hctx->cpumask)); blk_mq_set_alloc_data(&alloc_data, q, flags, ctx, hctx); rq = __blk_mq_alloc_request(&alloc_data, rw, 0); if (!rq) { - blk_queue_exit(q); - return ERR_PTR(-EWOULDBLOCK); + ret = -EWOULDBLOCK; + goto out_queue_exit; } return rq; + +out_queue_exit: + blk_queue_exit(q); + return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx); @@ -793,11 +805,12 @@ static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx) struct list_head *dptr; int queued; - WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)); - if (unlikely(test_bit(BLK_MQ_S_STOPPED, &hctx->state))) return; + WARN_ON(!cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask) && + cpu_online(hctx->next_cpu)); + hctx->run++; /* @@ -1036,10 +1049,11 @@ void blk_mq_delay_queue(struct blk_mq_hw_ctx *hctx, unsigned long msecs) EXPORT_SYMBOL(blk_mq_delay_queue); static inline void __blk_mq_insert_req_list(struct blk_mq_hw_ctx *hctx, - struct blk_mq_ctx *ctx, struct request *rq, bool at_head) { + struct blk_mq_ctx *ctx = rq->mq_ctx; + trace_block_rq_insert(hctx->queue, rq); if (at_head) @@ -1053,20 +1067,16 @@ static void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, { struct blk_mq_ctx *ctx = rq->mq_ctx; - __blk_mq_insert_req_list(hctx, ctx, rq, at_head); + __blk_mq_insert_req_list(hctx, rq, at_head); blk_mq_hctx_mark_pending(hctx, ctx); } void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue, - bool async) + bool async) { + struct blk_mq_ctx *ctx = rq->mq_ctx; struct request_queue *q = rq->q; struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *ctx = rq->mq_ctx, *current_ctx; - - current_ctx = blk_mq_get_ctx(q); - if (!cpu_online(ctx->cpu)) - rq->mq_ctx = ctx = current_ctx; hctx = q->mq_ops->map_queue(q, ctx->cpu); @@ -1076,8 +1086,6 @@ void blk_mq_insert_request(struct request *rq, bool at_head, bool run_queue, if (run_queue) blk_mq_run_hw_queue(hctx, async); - - blk_mq_put_ctx(current_ctx); } static void blk_mq_insert_requests(struct request_queue *q, @@ -1088,14 +1096,9 @@ static void blk_mq_insert_requests(struct request_queue *q, { struct blk_mq_hw_ctx *hctx; - struct blk_mq_ctx *current_ctx; trace_block_unplug(q, depth, !from_schedule); - current_ctx = blk_mq_get_ctx(q); - - if (!cpu_online(ctx->cpu)) - ctx = current_ctx; hctx = q->mq_ops->map_queue(q, ctx->cpu); /* @@ -1107,15 +1110,14 @@ static void blk_mq_insert_requests(struct request_queue *q, struct request *rq; rq = list_first_entry(list, struct request, queuelist); + BUG_ON(rq->mq_ctx != ctx); list_del_init(&rq->queuelist); - rq->mq_ctx = ctx; - __blk_mq_insert_req_list(hctx, ctx, rq, false); + __blk_mq_insert_req_list(hctx, rq, false); } blk_mq_hctx_mark_pending(hctx, ctx); spin_unlock(&ctx->lock); blk_mq_run_hw_queue(hctx, from_schedule); - blk_mq_put_ctx(current_ctx); } static int plug_ctx_cmp(void *priv, struct list_head *a, struct list_head *b) @@ -1630,16 +1632,17 @@ static int blk_mq_alloc_bitmap(struct blk_mq_ctxmap *bitmap, int node) return 0; } +/* + * 'cpu' is going away. splice any existing rq_list entries from this + * software queue to the hw queue dispatch list, and ensure that it + * gets run. + */ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu) { - struct request_queue *q = hctx->queue; struct blk_mq_ctx *ctx; LIST_HEAD(tmp); - /* - * Move ctx entries to new CPU, if this one is going away. - */ - ctx = __blk_mq_get_ctx(q, cpu); + ctx = __blk_mq_get_ctx(hctx->queue, cpu); spin_lock(&ctx->lock); if (!list_empty(&ctx->rq_list)) { @@ -1651,24 +1654,11 @@ static int blk_mq_hctx_cpu_offline(struct blk_mq_hw_ctx *hctx, int cpu) if (list_empty(&tmp)) return NOTIFY_OK; - ctx = blk_mq_get_ctx(q); - spin_lock(&ctx->lock); - - while (!list_empty(&tmp)) { - struct request *rq; - - rq = list_first_entry(&tmp, struct request, queuelist); - rq->mq_ctx = ctx; - list_move_tail(&rq->queuelist, &ctx->rq_list); - } - - hctx = q->mq_ops->map_queue(q, ctx->cpu); - blk_mq_hctx_mark_pending(hctx, ctx); - - spin_unlock(&ctx->lock); + spin_lock(&hctx->lock); + list_splice_tail_init(&tmp, &hctx->dispatch); + spin_unlock(&hctx->lock); blk_mq_run_hw_queue(hctx, true); - blk_mq_put_ctx(ctx); return NOTIFY_OK; } diff --git a/block/blk-throttle.c b/block/blk-throttle.c index f1aba26f4719..a3ea8260c94c 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -780,9 +780,11 @@ static bool tg_may_dispatch(struct throtl_grp *tg, struct bio *bio, /* * If previous slice expired, start a new one otherwise renew/extend * existing slice to make sure it is at least throtl_slice interval - * long since now. + * long since now. New slice is started only for empty throttle group. + * If there is queued bio, that means there should be an active + * slice and it should be extended instead. */ - if (throtl_slice_used(tg, rw)) + if (throtl_slice_used(tg, rw) && !(tg->service_queue.nr_queued[rw])) throtl_start_new_slice(tg, rw); else { if (time_before(tg->slice_end[rw], jiffies + throtl_slice)) diff --git a/block/elevator.c b/block/elevator.c index 7096c22041e7..f7d973a56fd7 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -366,7 +366,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq) list_for_each_prev(entry, &q->queue_head) { struct request *pos = list_entry_rq(entry); - if ((req_op(rq) == REQ_OP_DISCARD) != (req_op(pos) == REQ_OP_DISCARD)) + if (req_op(rq) != req_op(pos)) break; if (rq_data_dir(rq) != rq_data_dir(pos)) break; |