From c6f2882691e8fd128083abdcc3c5aa5b410c2367 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 29 Oct 2018 10:22:19 -0600 Subject: block: remove q->lld_busy_fn() Nobody is using the legacy path for blk_lld_busy() anymore, remove it. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4293dc1cd160..e867733b761d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -320,7 +320,6 @@ typedef void (unprep_rq_fn) (struct request_queue *, struct request *); struct bio_vec; typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); -typedef int (lld_busy_fn) (struct request_queue *q); typedef int (bsg_job_fn) (struct bsg_job *); typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t); typedef void (exit_rq_fn)(struct request_queue *, struct request *); @@ -466,7 +465,6 @@ struct request_queue { softirq_done_fn *softirq_done_fn; rq_timed_out_fn *rq_timed_out_fn; dma_drain_needed_fn *dma_drain_needed; - lld_busy_fn *lld_busy_fn; /* Called just after a request is allocated */ init_rq_fn *init_rq_fn; /* Called just before a request is freed */ @@ -1255,7 +1253,6 @@ extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); extern int blk_queue_dma_drain(struct request_queue *q, dma_drain_needed_fn *dma_drain_needed, void *buf, unsigned int size); -extern void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *fn); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn); -- cgit v1.2.3-71-gd317 From 771a93c489bf486b957c7399f89ee06d43ba2d93 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 22 Oct 2018 05:12:32 -0600 Subject: block: remove blk_complete_request() It's now unused. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-softirq.c | 20 -------------------- include/linux/blkdev.h | 1 - 2 files changed, 21 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-softirq.c b/block/blk-softirq.c index e47a2f751884..8ca0f6caf174 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -145,26 +145,6 @@ do_local: } EXPORT_SYMBOL(__blk_complete_request); -/** - * blk_complete_request - end I/O on a request - * @req: the request being processed - * - * Description: - * Ends all I/O on a request. It does not handle partial completions, - * unless the driver actually implements this in its completion callback - * through requeueing. The actual completion happens out-of-order, - * through a softirq handler. The user must have registered a completion - * callback through blk_queue_softirq_done(). - **/ -void blk_complete_request(struct request *req) -{ - if (unlikely(blk_should_fake_timeout(req->q))) - return; - if (!blk_mark_rq_complete(req)) - __blk_complete_request(req); -} -EXPORT_SYMBOL(blk_complete_request); - static __init int blk_softirq_init(void) { int i; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e867733b761d..6baea6563364 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1203,7 +1203,6 @@ extern bool __blk_end_request(struct request *rq, blk_status_t error, extern void __blk_end_request_all(struct request *rq, blk_status_t error); extern bool __blk_end_request_cur(struct request *rq, blk_status_t error); -extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); extern void blk_unprep_request(struct request *); -- cgit v1.2.3-71-gd317 From 7ca01926463a15f5d2681458643b2453930b873a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 24 Oct 2018 03:39:36 -0600 Subject: block: remove legacy rq tagging It's now unused, kill it. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- Documentation/block/biodoc.txt | 88 ---------- block/Makefile | 2 +- block/blk-core.c | 6 - block/blk-mq-debugfs.c | 2 - block/blk-mq-tag.c | 6 +- block/blk-sysfs.c | 3 - block/blk-tag.c | 378 ----------------------------------------- include/linux/blkdev.h | 35 ---- 8 files changed, 3 insertions(+), 517 deletions(-) delete mode 100644 block/blk-tag.c (limited to 'include/linux/blkdev.h') diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt index 207eca58efaa..ac18b488cb5e 100644 --- a/Documentation/block/biodoc.txt +++ b/Documentation/block/biodoc.txt @@ -65,7 +65,6 @@ Description of Contents: 3.2.3 I/O completion 3.2.4 Implications for drivers that do not interpret bios (don't handle multiple segments) - 3.2.5 Request command tagging 3.3 I/O submission 4. The I/O scheduler 5. Scalability related changes @@ -708,93 +707,6 @@ is crossed on completion of a transfer. (The end*request* functions should be used if only if the request has come down from block/bio path, not for direct access requests which only specify rq->buffer without a valid rq->bio) -3.2.5 Generic request command tagging - -3.2.5.1 Tag helpers - -Block now offers some simple generic functionality to help support command -queueing (typically known as tagged command queueing), ie manage more than -one outstanding command on a queue at any given time. - - blk_queue_init_tags(struct request_queue *q, int depth) - - Initialize internal command tagging structures for a maximum - depth of 'depth'. - - blk_queue_free_tags((struct request_queue *q) - - Teardown tag info associated with the queue. This will be done - automatically by block if blk_queue_cleanup() is called on a queue - that is using tagging. - -The above are initialization and exit management, the main helpers during -normal operations are: - - blk_queue_start_tag(struct request_queue *q, struct request *rq) - - Start tagged operation for this request. A free tag number between - 0 and 'depth' is assigned to the request (rq->tag holds this number), - and 'rq' is added to the internal tag management. If the maximum depth - for this queue is already achieved (or if the tag wasn't started for - some other reason), 1 is returned. Otherwise 0 is returned. - - blk_queue_end_tag(struct request_queue *q, struct request *rq) - - End tagged operation on this request. 'rq' is removed from the internal - book keeping structures. - -To minimize struct request and queue overhead, the tag helpers utilize some -of the same request members that are used for normal request queue management. -This means that a request cannot both be an active tag and be on the queue -list at the same time. blk_queue_start_tag() will remove the request, but -the driver must remember to call blk_queue_end_tag() before signalling -completion of the request to the block layer. This means ending tag -operations before calling end_that_request_last()! For an example of a user -of these helpers, see the IDE tagged command queueing support. - -3.2.5.2 Tag info - -Some block functions exist to query current tag status or to go from a -tag number to the associated request. These are, in no particular order: - - blk_queue_tagged(q) - - Returns 1 if the queue 'q' is using tagging, 0 if not. - - blk_queue_tag_request(q, tag) - - Returns a pointer to the request associated with tag 'tag'. - - blk_queue_tag_depth(q) - - Return current queue depth. - - blk_queue_tag_queue(q) - - Returns 1 if the queue can accept a new queued command, 0 if we are - at the maximum depth already. - - blk_queue_rq_tagged(rq) - - Returns 1 if the request 'rq' is tagged. - -3.2.5.2 Internal structure - -Internally, block manages tags in the blk_queue_tag structure: - - struct blk_queue_tag { - struct request **tag_index; /* array or pointers to rq */ - unsigned long *tag_map; /* bitmap of free tags */ - struct list_head busy_list; /* fifo list of busy tags */ - int busy; /* queue depth */ - int max_depth; /* max queue depth */ - }; - -Most of the above is simple and straight forward, however busy_list may need -a bit of explaining. Normally we don't care too much about request ordering, -but in the event of any barrier requests in the tag queue we need to ensure -that requests are restarted in the order they were queue. - 3.3 I/O Submission The routine submit_bio() is used to submit a single io. Higher level i/o diff --git a/block/Makefile b/block/Makefile index 27eac600474f..213674c8faaa 100644 --- a/block/Makefile +++ b/block/Makefile @@ -3,7 +3,7 @@ # Makefile for the kernel block layer # -obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \ +obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-sysfs.o \ blk-flush.o blk-settings.o blk-ioc.o blk-map.o \ blk-exec.o blk-merge.o blk-softirq.o blk-timeout.o \ blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \ diff --git a/block/blk-core.c b/block/blk-core.c index 03ef8f0e7dc5..daaed4dfa719 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1658,9 +1658,6 @@ void blk_requeue_request(struct request_queue *q, struct request *rq) trace_block_rq_requeue(q, rq); rq_qos_requeue(q, rq); - if (rq->rq_flags & RQF_QUEUED) - blk_queue_end_tag(q, rq); - BUG_ON(blk_queued_rq(rq)); elv_requeue_request(q, rq); @@ -3174,9 +3171,6 @@ void blk_finish_request(struct request *req, blk_status_t error) if (req->rq_flags & RQF_STATS) blk_stat_add(req, now); - if (req->rq_flags & RQF_QUEUED) - blk_queue_end_tag(q, req); - BUG_ON(blk_queued_rq(req)); if (unlikely(laptop_mode) && !blk_rq_is_passthrough(req)) diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 10b284a1f18d..9ed43a7c70b5 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -112,7 +112,6 @@ static int queue_pm_only_show(void *data, struct seq_file *m) #define QUEUE_FLAG_NAME(name) [QUEUE_FLAG_##name] = #name static const char *const blk_queue_flag_name[] = { - QUEUE_FLAG_NAME(QUEUED), QUEUE_FLAG_NAME(STOPPED), QUEUE_FLAG_NAME(DYING), QUEUE_FLAG_NAME(BYPASS), @@ -318,7 +317,6 @@ static const char *const cmd_flag_name[] = { static const char *const rqf_name[] = { RQF_NAME(SORTED), RQF_NAME(STARTED), - RQF_NAME(QUEUED), RQF_NAME(SOFTBARRIER), RQF_NAME(FLUSH_SEQ), RQF_NAME(MIXED_MERGE), diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index cfda95b85d34..4254e74c1446 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -530,10 +530,8 @@ u32 blk_mq_unique_tag(struct request *rq) struct blk_mq_hw_ctx *hctx; int hwq = 0; - if (q->mq_ops) { - hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu); - hwq = hctx->queue_num; - } + hctx = blk_mq_map_queue(q, rq->mq_ctx->cpu); + hwq = hctx->queue_num; return (hwq << BLK_MQ_UNIQUE_TAG_BITS) | (rq->tag & BLK_MQ_UNIQUE_TAG_MASK); diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 844a454a7b3a..1b82ccfde3fe 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -849,9 +849,6 @@ static void __blk_release_queue(struct work_struct *work) blk_exit_rl(q, &q->root_rl); - if (q->queue_tags) - __blk_queue_free_tags(q); - blk_queue_free_zone_bitmaps(q); if (!q->mq_ops) { diff --git a/block/blk-tag.c b/block/blk-tag.c deleted file mode 100644 index fbc153aef166..000000000000 --- a/block/blk-tag.c +++ /dev/null @@ -1,378 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Functions related to tagged command queuing - */ -#include -#include -#include -#include -#include - -#include "blk.h" - -/** - * blk_queue_find_tag - find a request by its tag and queue - * @q: The request queue for the device - * @tag: The tag of the request - * - * Notes: - * Should be used when a device returns a tag and you want to match - * it with a request. - * - * no locks need be held. - **/ -struct request *blk_queue_find_tag(struct request_queue *q, int tag) -{ - return blk_map_queue_find_tag(q->queue_tags, tag); -} -EXPORT_SYMBOL(blk_queue_find_tag); - -/** - * blk_free_tags - release a given set of tag maintenance info - * @bqt: the tag map to free - * - * Drop the reference count on @bqt and frees it when the last reference - * is dropped. - */ -void blk_free_tags(struct blk_queue_tag *bqt) -{ - if (atomic_dec_and_test(&bqt->refcnt)) { - BUG_ON(find_first_bit(bqt->tag_map, bqt->max_depth) < - bqt->max_depth); - - kfree(bqt->tag_index); - bqt->tag_index = NULL; - - kfree(bqt->tag_map); - bqt->tag_map = NULL; - - kfree(bqt); - } -} -EXPORT_SYMBOL(blk_free_tags); - -/** - * __blk_queue_free_tags - release tag maintenance info - * @q: the request queue for the device - * - * Notes: - * blk_cleanup_queue() will take care of calling this function, if tagging - * has been used. So there's no need to call this directly. - **/ -void __blk_queue_free_tags(struct request_queue *q) -{ - struct blk_queue_tag *bqt = q->queue_tags; - - if (!bqt) - return; - - blk_free_tags(bqt); - - q->queue_tags = NULL; - queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q); -} - -/** - * blk_queue_free_tags - release tag maintenance info - * @q: the request queue for the device - * - * Notes: - * This is used to disable tagged queuing to a device, yet leave - * queue in function. - **/ -void blk_queue_free_tags(struct request_queue *q) -{ - queue_flag_clear_unlocked(QUEUE_FLAG_QUEUED, q); -} -EXPORT_SYMBOL(blk_queue_free_tags); - -static int -init_tag_map(struct request_queue *q, struct blk_queue_tag *tags, int depth) -{ - struct request **tag_index; - unsigned long *tag_map; - int nr_ulongs; - - if (q && depth > q->nr_requests * 2) { - depth = q->nr_requests * 2; - printk(KERN_ERR "%s: adjusted depth to %d\n", - __func__, depth); - } - - tag_index = kcalloc(depth, sizeof(struct request *), GFP_ATOMIC); - if (!tag_index) - goto fail; - - nr_ulongs = ALIGN(depth, BITS_PER_LONG) / BITS_PER_LONG; - tag_map = kcalloc(nr_ulongs, sizeof(unsigned long), GFP_ATOMIC); - if (!tag_map) - goto fail; - - tags->real_max_depth = depth; - tags->max_depth = depth; - tags->tag_index = tag_index; - tags->tag_map = tag_map; - - return 0; -fail: - kfree(tag_index); - return -ENOMEM; -} - -static struct blk_queue_tag *__blk_queue_init_tags(struct request_queue *q, - int depth, int alloc_policy) -{ - struct blk_queue_tag *tags; - - tags = kmalloc(sizeof(struct blk_queue_tag), GFP_ATOMIC); - if (!tags) - goto fail; - - if (init_tag_map(q, tags, depth)) - goto fail; - - atomic_set(&tags->refcnt, 1); - tags->alloc_policy = alloc_policy; - tags->next_tag = 0; - return tags; -fail: - kfree(tags); - return NULL; -} - -/** - * blk_init_tags - initialize the tag info for an external tag map - * @depth: the maximum queue depth supported - * @alloc_policy: tag allocation policy - **/ -struct blk_queue_tag *blk_init_tags(int depth, int alloc_policy) -{ - return __blk_queue_init_tags(NULL, depth, alloc_policy); -} -EXPORT_SYMBOL(blk_init_tags); - -/** - * blk_queue_init_tags - initialize the queue tag info - * @q: the request queue for the device - * @depth: the maximum queue depth supported - * @tags: the tag to use - * @alloc_policy: tag allocation policy - * - * Queue lock must be held here if the function is called to resize an - * existing map. - **/ -int blk_queue_init_tags(struct request_queue *q, int depth, - struct blk_queue_tag *tags, int alloc_policy) -{ - int rc; - - BUG_ON(tags && q->queue_tags && tags != q->queue_tags); - - if (!tags && !q->queue_tags) { - tags = __blk_queue_init_tags(q, depth, alloc_policy); - - if (!tags) - return -ENOMEM; - - } else if (q->queue_tags) { - rc = blk_queue_resize_tags(q, depth); - if (rc) - return rc; - queue_flag_set(QUEUE_FLAG_QUEUED, q); - return 0; - } else - atomic_inc(&tags->refcnt); - - /* - * assign it, all done - */ - q->queue_tags = tags; - queue_flag_set_unlocked(QUEUE_FLAG_QUEUED, q); - return 0; -} -EXPORT_SYMBOL(blk_queue_init_tags); - -/** - * blk_queue_resize_tags - change the queueing depth - * @q: the request queue for the device - * @new_depth: the new max command queueing depth - * - * Notes: - * Must be called with the queue lock held. - **/ -int blk_queue_resize_tags(struct request_queue *q, int new_depth) -{ - struct blk_queue_tag *bqt = q->queue_tags; - struct request **tag_index; - unsigned long *tag_map; - int max_depth, nr_ulongs; - - if (!bqt) - return -ENXIO; - - /* - * if we already have large enough real_max_depth. just - * adjust max_depth. *NOTE* as requests with tag value - * between new_depth and real_max_depth can be in-flight, tag - * map can not be shrunk blindly here. - */ - if (new_depth <= bqt->real_max_depth) { - bqt->max_depth = new_depth; - return 0; - } - - /* - * Currently cannot replace a shared tag map with a new - * one, so error out if this is the case - */ - if (atomic_read(&bqt->refcnt) != 1) - return -EBUSY; - - /* - * save the old state info, so we can copy it back - */ - tag_index = bqt->tag_index; - tag_map = bqt->tag_map; - max_depth = bqt->real_max_depth; - - if (init_tag_map(q, bqt, new_depth)) - return -ENOMEM; - - memcpy(bqt->tag_index, tag_index, max_depth * sizeof(struct request *)); - nr_ulongs = ALIGN(max_depth, BITS_PER_LONG) / BITS_PER_LONG; - memcpy(bqt->tag_map, tag_map, nr_ulongs * sizeof(unsigned long)); - - kfree(tag_index); - kfree(tag_map); - return 0; -} -EXPORT_SYMBOL(blk_queue_resize_tags); - -/** - * blk_queue_end_tag - end tag operations for a request - * @q: the request queue for the device - * @rq: the request that has completed - * - * Description: - * Typically called when end_that_request_first() returns %0, meaning - * all transfers have been done for a request. It's important to call - * this function before end_that_request_last(), as that will put the - * request back on the free list thus corrupting the internal tag list. - **/ -void blk_queue_end_tag(struct request_queue *q, struct request *rq) -{ - struct blk_queue_tag *bqt = q->queue_tags; - unsigned tag = rq->tag; /* negative tags invalid */ - - lockdep_assert_held(q->queue_lock); - - BUG_ON(tag >= bqt->real_max_depth); - - list_del_init(&rq->queuelist); - rq->rq_flags &= ~RQF_QUEUED; - rq->tag = -1; - rq->internal_tag = -1; - - if (unlikely(bqt->tag_index[tag] == NULL)) - printk(KERN_ERR "%s: tag %d is missing\n", - __func__, tag); - - bqt->tag_index[tag] = NULL; - - if (unlikely(!test_bit(tag, bqt->tag_map))) { - printk(KERN_ERR "%s: attempt to clear non-busy tag (%d)\n", - __func__, tag); - return; - } - /* - * The tag_map bit acts as a lock for tag_index[bit], so we need - * unlock memory barrier semantics. - */ - clear_bit_unlock(tag, bqt->tag_map); -} - -/** - * blk_queue_start_tag - find a free tag and assign it - * @q: the request queue for the device - * @rq: the block request that needs tagging - * - * Description: - * This can either be used as a stand-alone helper, or possibly be - * assigned as the queue &prep_rq_fn (in which case &struct request - * automagically gets a tag assigned). Note that this function - * assumes that any type of request can be queued! if this is not - * true for your device, you must check the request type before - * calling this function. The request will also be removed from - * the request queue, so it's the drivers responsibility to readd - * it if it should need to be restarted for some reason. - **/ -int blk_queue_start_tag(struct request_queue *q, struct request *rq) -{ - struct blk_queue_tag *bqt = q->queue_tags; - unsigned max_depth; - int tag; - - lockdep_assert_held(q->queue_lock); - - if (unlikely((rq->rq_flags & RQF_QUEUED))) { - printk(KERN_ERR - "%s: request %p for device [%s] already tagged %d", - __func__, rq, - rq->rq_disk ? rq->rq_disk->disk_name : "?", rq->tag); - BUG(); - } - - /* - * Protect against shared tag maps, as we may not have exclusive - * access to the tag map. - * - * We reserve a few tags just for sync IO, since we don't want - * to starve sync IO on behalf of flooding async IO. - */ - max_depth = bqt->max_depth; - if (!rq_is_sync(rq) && max_depth > 1) { - switch (max_depth) { - case 2: - max_depth = 1; - break; - case 3: - max_depth = 2; - break; - default: - max_depth -= 2; - } - if (q->in_flight[BLK_RW_ASYNC] > max_depth) - return 1; - } - - do { - if (bqt->alloc_policy == BLK_TAG_ALLOC_FIFO) { - tag = find_first_zero_bit(bqt->tag_map, max_depth); - if (tag >= max_depth) - return 1; - } else { - int start = bqt->next_tag; - int size = min_t(int, bqt->max_depth, max_depth + start); - tag = find_next_zero_bit(bqt->tag_map, size, start); - if (tag >= size && start + size > bqt->max_depth) { - size = start + size - bqt->max_depth; - tag = find_first_zero_bit(bqt->tag_map, size); - } - if (tag >= size) - return 1; - } - - } while (test_and_set_bit_lock(tag, bqt->tag_map)); - /* - * We need lock ordering semantics given by test_and_set_bit_lock. - * See blk_queue_end_tag for details. - */ - - bqt->next_tag = (tag + 1) % bqt->max_depth; - rq->rq_flags |= RQF_QUEUED; - rq->tag = tag; - bqt->tag_index[tag] = rq; - blk_start_request(rq); - return 0; -} -EXPORT_SYMBOL(blk_queue_start_tag); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6baea6563364..8afe3331777e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -85,8 +85,6 @@ typedef __u32 __bitwise req_flags_t; #define RQF_SORTED ((__force req_flags_t)(1 << 0)) /* drive already may have started this one */ #define RQF_STARTED ((__force req_flags_t)(1 << 1)) -/* uses tagged queueing */ -#define RQF_QUEUED ((__force req_flags_t)(1 << 2)) /* may not be passed by ioscheduler */ #define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3)) /* request for flush sequence */ @@ -336,15 +334,6 @@ enum blk_queue_state { Queue_up, }; -struct blk_queue_tag { - struct request **tag_index; /* map of busy tags */ - unsigned long *tag_map; /* bit map of free/busy tags */ - int max_depth; /* what we will send to device */ - int real_max_depth; /* what the array can hold */ - atomic_t refcnt; /* map can be shared */ - int alloc_policy; /* tag allocation policy */ - int next_tag; /* next tag */ -}; #define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ #define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */ @@ -568,8 +557,6 @@ struct request_queue { unsigned int dma_pad_mask; unsigned int dma_alignment; - struct blk_queue_tag *queue_tags; - unsigned int nr_sorted; unsigned int in_flight[2]; @@ -680,7 +667,6 @@ struct request_queue { u64 write_hints[BLK_MAX_WRITE_HINTS]; }; -#define QUEUE_FLAG_QUEUED 0 /* uses generic tag queueing */ #define QUEUE_FLAG_STOPPED 1 /* queue is stopped */ #define QUEUE_FLAG_DYING 2 /* queue being torn down */ #define QUEUE_FLAG_BYPASS 3 /* act as dumb FIFO queue */ @@ -724,7 +710,6 @@ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); -#define blk_queue_tagged(q) test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags) #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) #define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) @@ -1359,26 +1344,6 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) !list_empty(&plug->cb_list)); } -/* - * tag stuff - */ -extern int blk_queue_start_tag(struct request_queue *, struct request *); -extern struct request *blk_queue_find_tag(struct request_queue *, int); -extern void blk_queue_end_tag(struct request_queue *, struct request *); -extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *, int); -extern void blk_queue_free_tags(struct request_queue *); -extern int blk_queue_resize_tags(struct request_queue *, int); -extern struct blk_queue_tag *blk_init_tags(int, int); -extern void blk_free_tags(struct blk_queue_tag *); - -static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, - int tag) -{ - if (unlikely(bqt == NULL || tag >= bqt->real_max_depth)) - return NULL; - return bqt->tag_index[tag]; -} - extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); -- cgit v1.2.3-71-gd317 From a1ce35fa49852db60fc6e268038530be533c5b15 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 29 Oct 2018 10:23:51 -0600 Subject: block: remove dead elevator code This removes a bunch of core and elevator related code. On the core front, we remove anything related to queue running, draining, initialization, plugging, and congestions. We also kill anything related to request allocation, merging, retrieval, and completion. Remove any checking for single queue IO schedulers, as they no longer exist. This means we can also delete a bunch of code related to request issue, adding, completion, etc - and all the SQ related ops and helpers. Also kill the load_default_modules(), as all that did was provide for a way to load the default single queue elevator. Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/bfq-iosched.c | 1 - block/blk-core.c | 1749 +--------------------------------------------- block/blk-exec.c | 20 +- block/blk-ioc.c | 33 +- block/blk-merge.c | 5 - block/blk-settings.c | 36 - block/blk-sysfs.c | 36 +- block/blk.h | 51 -- block/elevator.c | 377 +--------- block/kyber-iosched.c | 1 - block/mq-deadline.c | 1 - include/linux/blkdev.h | 93 +-- include/linux/elevator.h | 90 +-- include/linux/init.h | 1 - init/do_mounts_initrd.c | 3 - init/initramfs.c | 6 - init/main.c | 12 - 17 files changed, 75 insertions(+), 2440 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 3a27d31fcda6..44c7e567aa25 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -5745,7 +5745,6 @@ static struct elevator_type iosched_bfq_mq = { .exit_sched = bfq_exit_queue, }, - .uses_mq = true, .icq_size = sizeof(struct bfq_io_cq), .icq_align = __alignof__(struct bfq_io_cq), .elevator_attrs = bfq_attrs, diff --git a/block/blk-core.c b/block/blk-core.c index daaed4dfa719..18538a41a532 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -144,46 +144,6 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q) } EXPORT_SYMBOL_GPL(blk_queue_flag_test_and_clear); -static void blk_clear_congested(struct request_list *rl, int sync) -{ -#ifdef CONFIG_CGROUP_WRITEBACK - clear_wb_congested(rl->blkg->wb_congested, sync); -#else - /* - * If !CGROUP_WRITEBACK, all blkg's map to bdi->wb and we shouldn't - * flip its congestion state for events on other blkcgs. - */ - if (rl == &rl->q->root_rl) - clear_wb_congested(rl->q->backing_dev_info->wb.congested, sync); -#endif -} - -static void blk_set_congested(struct request_list *rl, int sync) -{ -#ifdef CONFIG_CGROUP_WRITEBACK - set_wb_congested(rl->blkg->wb_congested, sync); -#else - /* see blk_clear_congested() */ - if (rl == &rl->q->root_rl) - set_wb_congested(rl->q->backing_dev_info->wb.congested, sync); -#endif -} - -void blk_queue_congestion_threshold(struct request_queue *q) -{ - int nr; - - nr = q->nr_requests - (q->nr_requests / 8) + 1; - if (nr > q->nr_requests) - nr = q->nr_requests; - q->nr_congestion_on = nr; - - nr = q->nr_requests - (q->nr_requests / 8) - (q->nr_requests / 16) - 1; - if (nr < 1) - nr = 1; - q->nr_congestion_off = nr; -} - void blk_rq_init(struct request_queue *q, struct request *rq) { memset(rq, 0, sizeof(*rq)); @@ -292,99 +252,6 @@ void blk_dump_rq_flags(struct request *rq, char *msg) } EXPORT_SYMBOL(blk_dump_rq_flags); -static void blk_delay_work(struct work_struct *work) -{ - struct request_queue *q; - - q = container_of(work, struct request_queue, delay_work.work); - spin_lock_irq(q->queue_lock); - __blk_run_queue(q); - spin_unlock_irq(q->queue_lock); -} - -/** - * blk_delay_queue - restart queueing after defined interval - * @q: The &struct request_queue in question - * @msecs: Delay in msecs - * - * Description: - * Sometimes queueing needs to be postponed for a little while, to allow - * resources to come back. This function will make sure that queueing is - * restarted around the specified time. - */ -void blk_delay_queue(struct request_queue *q, unsigned long msecs) -{ - lockdep_assert_held(q->queue_lock); - WARN_ON_ONCE(q->mq_ops); - - if (likely(!blk_queue_dead(q))) - queue_delayed_work(kblockd_workqueue, &q->delay_work, - msecs_to_jiffies(msecs)); -} -EXPORT_SYMBOL(blk_delay_queue); - -/** - * blk_start_queue_async - asynchronously restart a previously stopped queue - * @q: The &struct request_queue in question - * - * Description: - * blk_start_queue_async() will clear the stop flag on the queue, and - * ensure that the request_fn for the queue is run from an async - * context. - **/ -void blk_start_queue_async(struct request_queue *q) -{ - lockdep_assert_held(q->queue_lock); - WARN_ON_ONCE(q->mq_ops); - - queue_flag_clear(QUEUE_FLAG_STOPPED, q); - blk_run_queue_async(q); -} -EXPORT_SYMBOL(blk_start_queue_async); - -/** - * blk_start_queue - restart a previously stopped queue - * @q: The &struct request_queue in question - * - * Description: - * blk_start_queue() will clear the stop flag on the queue, and call - * the request_fn for the queue if it was in a stopped state when - * entered. Also see blk_stop_queue(). - **/ -void blk_start_queue(struct request_queue *q) -{ - lockdep_assert_held(q->queue_lock); - WARN_ON_ONCE(q->mq_ops); - - queue_flag_clear(QUEUE_FLAG_STOPPED, q); - __blk_run_queue(q); -} -EXPORT_SYMBOL(blk_start_queue); - -/** - * blk_stop_queue - stop a queue - * @q: The &struct request_queue in question - * - * Description: - * The Linux block layer assumes that a block driver will consume all - * entries on the request queue when the request_fn strategy is called. - * Often this will not happen, because of hardware limitations (queue - * depth settings). If a device driver gets a 'queue full' response, - * or if it simply chooses not to queue more I/O at one point, it can - * call this function to prevent the request_fn from being called until - * the driver has signalled it's ready to go again. This happens by calling - * blk_start_queue() to restart queue operations. - **/ -void blk_stop_queue(struct request_queue *q) -{ - lockdep_assert_held(q->queue_lock); - WARN_ON_ONCE(q->mq_ops); - - cancel_delayed_work(&q->delay_work); - queue_flag_set(QUEUE_FLAG_STOPPED, q); -} -EXPORT_SYMBOL(blk_stop_queue); - /** * blk_sync_queue - cancel any pending callbacks on a queue * @q: the queue @@ -415,8 +282,6 @@ void blk_sync_queue(struct request_queue *q) cancel_delayed_work_sync(&q->requeue_work); queue_for_each_hw_ctx(q, hctx, i) cancel_delayed_work_sync(&hctx->run_work); - } else { - cancel_delayed_work_sync(&q->delay_work); } } EXPORT_SYMBOL(blk_sync_queue); @@ -442,250 +307,12 @@ void blk_clear_pm_only(struct request_queue *q) } EXPORT_SYMBOL_GPL(blk_clear_pm_only); -/** - * __blk_run_queue_uncond - run a queue whether or not it has been stopped - * @q: The queue to run - * - * Description: - * Invoke request handling on a queue if there are any pending requests. - * May be used to restart request handling after a request has completed. - * This variant runs the queue whether or not the queue has been - * stopped. Must be called with the queue lock held and interrupts - * disabled. See also @blk_run_queue. - */ -inline void __blk_run_queue_uncond(struct request_queue *q) -{ - lockdep_assert_held(q->queue_lock); - WARN_ON_ONCE(q->mq_ops); - - if (unlikely(blk_queue_dead(q))) - return; - - /* - * Some request_fn implementations, e.g. scsi_request_fn(), unlock - * the queue lock internally. As a result multiple threads may be - * running such a request function concurrently. Keep track of the - * number of active request_fn invocations such that blk_drain_queue() - * can wait until all these request_fn calls have finished. - */ - q->request_fn_active++; - q->request_fn(q); - q->request_fn_active--; -} -EXPORT_SYMBOL_GPL(__blk_run_queue_uncond); - -/** - * __blk_run_queue - run a single device queue - * @q: The queue to run - * - * Description: - * See @blk_run_queue. - */ -void __blk_run_queue(struct request_queue *q) -{ - lockdep_assert_held(q->queue_lock); - WARN_ON_ONCE(q->mq_ops); - - if (unlikely(blk_queue_stopped(q))) - return; - - __blk_run_queue_uncond(q); -} -EXPORT_SYMBOL(__blk_run_queue); - -/** - * blk_run_queue_async - run a single device queue in workqueue context - * @q: The queue to run - * - * Description: - * Tells kblockd to perform the equivalent of @blk_run_queue on behalf - * of us. - * - * Note: - * Since it is not allowed to run q->delay_work after blk_cleanup_queue() - * has canceled q->delay_work, callers must hold the queue lock to avoid - * race conditions between blk_cleanup_queue() and blk_run_queue_async(). - */ -void blk_run_queue_async(struct request_queue *q) -{ - lockdep_assert_held(q->queue_lock); - WARN_ON_ONCE(q->mq_ops); - - if (likely(!blk_queue_stopped(q) && !blk_queue_dead(q))) - mod_delayed_work(kblockd_workqueue, &q->delay_work, 0); -} -EXPORT_SYMBOL(blk_run_queue_async); - -/** - * blk_run_queue - run a single device queue - * @q: The queue to run - * - * Description: - * Invoke request handling on this queue, if it has pending work to do. - * May be used to restart queueing when a request has completed. - */ -void blk_run_queue(struct request_queue *q) -{ - unsigned long flags; - - WARN_ON_ONCE(q->mq_ops); - - spin_lock_irqsave(q->queue_lock, flags); - __blk_run_queue(q); - spin_unlock_irqrestore(q->queue_lock, flags); -} -EXPORT_SYMBOL(blk_run_queue); - void blk_put_queue(struct request_queue *q) { kobject_put(&q->kobj); } EXPORT_SYMBOL(blk_put_queue); -/** - * __blk_drain_queue - drain requests from request_queue - * @q: queue to drain - * @drain_all: whether to drain all requests or only the ones w/ ELVPRIV - * - * Drain requests from @q. If @drain_all is set, all requests are drained. - * If not, only ELVPRIV requests are drained. The caller is responsible - * for ensuring that no new requests which need to be drained are queued. - */ -static void __blk_drain_queue(struct request_queue *q, bool drain_all) - __releases(q->queue_lock) - __acquires(q->queue_lock) -{ - int i; - - lockdep_assert_held(q->queue_lock); - WARN_ON_ONCE(q->mq_ops); - - while (true) { - bool drain = false; - - /* - * The caller might be trying to drain @q before its - * elevator is initialized. - */ - if (q->elevator) - elv_drain_elevator(q); - - blkcg_drain_queue(q); - - /* - * This function might be called on a queue which failed - * driver init after queue creation or is not yet fully - * active yet. Some drivers (e.g. fd and loop) get unhappy - * in such cases. Kick queue iff dispatch queue has - * something on it and @q has request_fn set. - */ - if (!list_empty(&q->queue_head) && q->request_fn) - __blk_run_queue(q); - - drain |= q->nr_rqs_elvpriv; - drain |= q->request_fn_active; - - /* - * Unfortunately, requests are queued at and tracked from - * multiple places and there's no single counter which can - * be drained. Check all the queues and counters. - */ - if (drain_all) { - struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL); - drain |= !list_empty(&q->queue_head); - for (i = 0; i < 2; i++) { - drain |= q->nr_rqs[i]; - drain |= q->in_flight[i]; - if (fq) - drain |= !list_empty(&fq->flush_queue[i]); - } - } - - if (!drain) - break; - - spin_unlock_irq(q->queue_lock); - - msleep(10); - - spin_lock_irq(q->queue_lock); - } - - /* - * With queue marked dead, any woken up waiter will fail the - * allocation path, so the wakeup chaining is lost and we're - * left with hung waiters. We need to wake up those waiters. - */ - if (q->request_fn) { - struct request_list *rl; - - blk_queue_for_each_rl(rl, q) - for (i = 0; i < ARRAY_SIZE(rl->wait); i++) - wake_up_all(&rl->wait[i]); - } -} - -void blk_drain_queue(struct request_queue *q) -{ - spin_lock_irq(q->queue_lock); - __blk_drain_queue(q, true); - spin_unlock_irq(q->queue_lock); -} - -/** - * blk_queue_bypass_start - enter queue bypass mode - * @q: queue of interest - * - * In bypass mode, only the dispatch FIFO queue of @q is used. This - * function makes @q enter bypass mode and drains all requests which were - * throttled or issued before. On return, it's guaranteed that no request - * is being throttled or has ELVPRIV set and blk_queue_bypass() %true - * inside queue or RCU read lock. - */ -void blk_queue_bypass_start(struct request_queue *q) -{ - WARN_ON_ONCE(q->mq_ops); - - spin_lock_irq(q->queue_lock); - q->bypass_depth++; - queue_flag_set(QUEUE_FLAG_BYPASS, q); - spin_unlock_irq(q->queue_lock); - - /* - * Queues start drained. Skip actual draining till init is - * complete. This avoids lenghty delays during queue init which - * can happen many times during boot. - */ - if (blk_queue_init_done(q)) { - spin_lock_irq(q->queue_lock); - __blk_drain_queue(q, false); - spin_unlock_irq(q->queue_lock); - - /* ensure blk_queue_bypass() is %true inside RCU read lock */ - synchronize_rcu(); - } -} -EXPORT_SYMBOL_GPL(blk_queue_bypass_start); - -/** - * blk_queue_bypass_end - leave queue bypass mode - * @q: queue of interest - * - * Leave bypass mode and restore the normal queueing behavior. - * - * Note: although blk_queue_bypass_start() is only called for blk-sq queues, - * this function is called for both blk-sq and blk-mq queues. - */ -void blk_queue_bypass_end(struct request_queue *q) -{ - spin_lock_irq(q->queue_lock); - if (!--q->bypass_depth) - queue_flag_clear(QUEUE_FLAG_BYPASS, q); - WARN_ON_ONCE(q->bypass_depth < 0); - spin_unlock_irq(q->queue_lock); -} -EXPORT_SYMBOL_GPL(blk_queue_bypass_end); - void blk_set_queue_dying(struct request_queue *q) { blk_queue_flag_set(QUEUE_FLAG_DYING, q); @@ -699,18 +326,6 @@ void blk_set_queue_dying(struct request_queue *q) if (q->mq_ops) blk_mq_wake_waiters(q); - else { - struct request_list *rl; - - spin_lock_irq(q->queue_lock); - blk_queue_for_each_rl(rl, q) { - if (rl->rq_pool) { - wake_up_all(&rl->wait[BLK_RW_SYNC]); - wake_up_all(&rl->wait[BLK_RW_ASYNC]); - } - } - spin_unlock_irq(q->queue_lock); - } /* Make blk_queue_enter() reexamine the DYING flag. */ wake_up_all(&q->mq_freeze_wq); @@ -822,6 +437,7 @@ void blk_cleanup_queue(struct request_queue *q) if (q->mq_ops) blk_mq_free_queue(q); + percpu_ref_exit(&q->q_usage_counter); spin_lock_irq(lock); @@ -1013,8 +629,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, INIT_LIST_HEAD(&q->queue_head); q->last_merge = NULL; - q->end_sector = 0; - q->boundary_rq = NULL; q->id = ida_simple_get(&blk_queue_ida, 0, 0, gfp_mask); if (q->id < 0) @@ -1047,7 +661,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, #ifdef CONFIG_BLK_CGROUP INIT_LIST_HEAD(&q->blkg_list); #endif - INIT_DELAYED_WORK(&q->delay_work, blk_delay_work); kobject_init(&q->kobj, &blk_queue_ktype); @@ -1100,105 +713,6 @@ fail_q: } EXPORT_SYMBOL(blk_alloc_queue_node); -/** - * blk_init_queue - prepare a request queue for use with a block device - * @rfn: The function to be called to process requests that have been - * placed on the queue. - * @lock: Request queue spin lock - * - * Description: - * If a block device wishes to use the standard request handling procedures, - * which sorts requests and coalesces adjacent requests, then it must - * call blk_init_queue(). The function @rfn will be called when there - * are requests on the queue that need to be processed. If the device - * supports plugging, then @rfn may not be called immediately when requests - * are available on the queue, but may be called at some time later instead. - * Plugged queues are generally unplugged when a buffer belonging to one - * of the requests on the queue is needed, or due to memory pressure. - * - * @rfn is not required, or even expected, to remove all requests off the - * queue, but only as many as it can handle at a time. If it does leave - * requests on the queue, it is responsible for arranging that the requests - * get dealt with eventually. - * - * The queue spin lock must be held while manipulating the requests on the - * request queue; this lock will be taken also from interrupt context, so irq - * disabling is needed for it. - * - * Function returns a pointer to the initialized request queue, or %NULL if - * it didn't succeed. - * - * Note: - * blk_init_queue() must be paired with a blk_cleanup_queue() call - * when the block device is deactivated (such as at module unload). - **/ - -struct request_queue *blk_init_queue(request_fn_proc *rfn, spinlock_t *lock) -{ - return blk_init_queue_node(rfn, lock, NUMA_NO_NODE); -} -EXPORT_SYMBOL(blk_init_queue); - -struct request_queue * -blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) -{ - struct request_queue *q; - - q = blk_alloc_queue_node(GFP_KERNEL, node_id, lock); - if (!q) - return NULL; - - q->request_fn = rfn; - if (blk_init_allocated_queue(q) < 0) { - blk_cleanup_queue(q); - return NULL; - } - - return q; -} -EXPORT_SYMBOL(blk_init_queue_node); - -static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio); - - -int blk_init_allocated_queue(struct request_queue *q) -{ - WARN_ON_ONCE(q->mq_ops); - - q->fq = blk_alloc_flush_queue(q, NUMA_NO_NODE, q->cmd_size, GFP_KERNEL); - if (!q->fq) - return -ENOMEM; - - if (q->init_rq_fn && q->init_rq_fn(q, q->fq->flush_rq, GFP_KERNEL)) - goto out_free_flush_queue; - - if (blk_init_rl(&q->root_rl, q, GFP_KERNEL)) - goto out_exit_flush_rq; - - INIT_WORK(&q->timeout_work, blk_timeout_work); - q->queue_flags |= QUEUE_FLAG_DEFAULT; - - /* - * This also sets hw/phys segments, boundary and size - */ - blk_queue_make_request(q, blk_queue_bio); - - q->sg_reserved_size = INT_MAX; - - if (elevator_init(q)) - goto out_exit_flush_rq; - return 0; - -out_exit_flush_rq: - if (q->exit_rq_fn) - q->exit_rq_fn(q, q->fq->flush_rq); -out_free_flush_queue: - blk_free_flush_queue(q->fq); - q->fq = NULL; - return -ENOMEM; -} -EXPORT_SYMBOL(blk_init_allocated_queue); - bool blk_get_queue(struct request_queue *q) { if (likely(!blk_queue_dying(q))) { @@ -1210,477 +724,38 @@ bool blk_get_queue(struct request_queue *q) } EXPORT_SYMBOL(blk_get_queue); -static inline void blk_free_request(struct request_list *rl, struct request *rq) -{ - if (rq->rq_flags & RQF_ELVPRIV) { - elv_put_request(rl->q, rq); - if (rq->elv.icq) - put_io_context(rq->elv.icq->ioc); - } - - mempool_free(rq, rl->rq_pool); -} - -/* - * ioc_batching returns true if the ioc is a valid batching request and - * should be given priority access to a request. +/** + * blk_get_request - allocate a request + * @q: request queue to allocate a request for + * @op: operation (REQ_OP_*) and REQ_* flags, e.g. REQ_SYNC. + * @flags: BLK_MQ_REQ_* flags, e.g. BLK_MQ_REQ_NOWAIT. */ -static inline int ioc_batching(struct request_queue *q, struct io_context *ioc) +struct request *blk_get_request(struct request_queue *q, unsigned int op, + blk_mq_req_flags_t flags) { - if (!ioc) - return 0; + struct request *req; - /* - * Make sure the process is able to allocate at least 1 request - * even if the batch times out, otherwise we could theoretically - * lose wakeups. - */ - return ioc->nr_batch_requests == q->nr_batching || - (ioc->nr_batch_requests > 0 - && time_before(jiffies, ioc->last_waited + BLK_BATCH_TIME)); -} + WARN_ON_ONCE(op & REQ_NOWAIT); + WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PREEMPT)); -/* - * ioc_set_batching sets ioc to be a new "batcher" if it is not one. This - * will cause the process to be a "batcher" on all queues in the system. This - * is the behaviour we want though - once it gets a wakeup it should be given - * a nice run. - */ -static void ioc_set_batching(struct request_queue *q, struct io_context *ioc) -{ - if (!ioc || ioc_batching(q, ioc)) - return; + req = blk_mq_alloc_request(q, op, flags); + if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn) + q->mq_ops->initialize_rq_fn(req); - ioc->nr_batch_requests = q->nr_batching; - ioc->last_waited = jiffies; + return req; } +EXPORT_SYMBOL(blk_get_request); -static void __freed_request(struct request_list *rl, int sync) +static void part_round_stats_single(struct request_queue *q, int cpu, + struct hd_struct *part, unsigned long now, + unsigned int inflight) { - struct request_queue *q = rl->q; - - if (rl->count[sync] < queue_congestion_off_threshold(q)) - blk_clear_congested(rl, sync); - - if (rl->count[sync] + 1 <= q->nr_requests) { - if (waitqueue_active(&rl->wait[sync])) - wake_up(&rl->wait[sync]); - - blk_clear_rl_full(rl, sync); + if (inflight) { + __part_stat_add(cpu, part, time_in_queue, + inflight * (now - part->stamp)); + __part_stat_add(cpu, part, io_ticks, (now - part->stamp)); } -} - -/* - * A request has just been released. Account for it, update the full and - * congestion status, wake up any waiters. Called under q->queue_lock. - */ -static void freed_request(struct request_list *rl, bool sync, - req_flags_t rq_flags) -{ - struct request_queue *q = rl->q; - - q->nr_rqs[sync]--; - rl->count[sync]--; - if (rq_flags & RQF_ELVPRIV) - q->nr_rqs_elvpriv--; - - __freed_request(rl, sync); - - if (unlikely(rl->starved[sync ^ 1])) - __freed_request(rl, sync ^ 1); -} - -int blk_update_nr_requests(struct request_queue *q, unsigned int nr) -{ - struct request_list *rl; - int on_thresh, off_thresh; - - WARN_ON_ONCE(q->mq_ops); - - spin_lock_irq(q->queue_lock); - q->nr_requests = nr; - blk_queue_congestion_threshold(q); - on_thresh = queue_congestion_on_threshold(q); - off_thresh = queue_congestion_off_threshold(q); - - blk_queue_for_each_rl(rl, q) { - if (rl->count[BLK_RW_SYNC] >= on_thresh) - blk_set_congested(rl, BLK_RW_SYNC); - else if (rl->count[BLK_RW_SYNC] < off_thresh) - blk_clear_congested(rl, BLK_RW_SYNC); - - if (rl->count[BLK_RW_ASYNC] >= on_thresh) - blk_set_congested(rl, BLK_RW_ASYNC); - else if (rl->count[BLK_RW_ASYNC] < off_thresh) - blk_clear_congested(rl, BLK_RW_ASYNC); - - if (rl->count[BLK_RW_SYNC] >= q->nr_requests) { - blk_set_rl_full(rl, BLK_RW_SYNC); - } else { - blk_clear_rl_full(rl, BLK_RW_SYNC); - wake_up(&rl->wait[BLK_RW_SYNC]); - } - - if (rl->count[BLK_RW_ASYNC] >= q->nr_requests) { - blk_set_rl_full(rl, BLK_RW_ASYNC); - } else { - blk_clear_rl_full(rl, BLK_RW_ASYNC); - wake_up(&rl->wait[BLK_RW_ASYNC]); - } - } - - spin_unlock_irq(q->queue_lock); - return 0; -} - -/** - * __get_request - get a free request - * @rl: request list to allocate from - * @op: operation and flags - * @bio: bio to allocate request for (can be %NULL) - * @flags: BLQ_MQ_REQ_* flags - * @gfp_mask: allocator flags - * - * Get a free request from @q. This function may fail under memory - * pressure or if @q is dead. - * - * Must be called with @q->queue_lock held and, - * Returns ERR_PTR on failure, with @q->queue_lock held. - * Returns request pointer on success, with @q->queue_lock *not held*. - */ -static struct request *__get_request(struct request_list *rl, unsigned int op, - struct bio *bio, blk_mq_req_flags_t flags, gfp_t gfp_mask) -{ - struct request_queue *q = rl->q; - struct request *rq; - struct elevator_type *et = q->elevator->type; - struct io_context *ioc = rq_ioc(bio); - struct io_cq *icq = NULL; - const bool is_sync = op_is_sync(op); - int may_queue; - req_flags_t rq_flags = RQF_ALLOCED; - - lockdep_assert_held(q->queue_lock); - - if (unlikely(blk_queue_dying(q))) - return ERR_PTR(-ENODEV); - - may_queue = elv_may_queue(q, op); - if (may_queue == ELV_MQUEUE_NO) - goto rq_starved; - - if (rl->count[is_sync]+1 >= queue_congestion_on_threshold(q)) { - if (rl->count[is_sync]+1 >= q->nr_requests) { - /* - * The queue will fill after this allocation, so set - * it as full, and mark this process as "batching". - * This process will be allowed to complete a batch of - * requests, others will be blocked. - */ - if (!blk_rl_full(rl, is_sync)) { - ioc_set_batching(q, ioc); - blk_set_rl_full(rl, is_sync); - } else { - if (may_queue != ELV_MQUEUE_MUST - && !ioc_batching(q, ioc)) { - /* - * The queue is full and the allocating - * process is not a "batcher", and not - * exempted by the IO scheduler - */ - return ERR_PTR(-ENOMEM); - } - } - } - blk_set_congested(rl, is_sync); - } - - /* - * Only allow batching queuers to allocate up to 50% over the defined - * limit of requests, otherwise we could have thousands of requests - * allocated with any setting of ->nr_requests - */ - if (rl->count[is_sync] >= (3 * q->nr_requests / 2)) - return ERR_PTR(-ENOMEM); - - q->nr_rqs[is_sync]++; - rl->count[is_sync]++; - rl->starved[is_sync] = 0; - - /* - * Decide whether the new request will be managed by elevator. If - * so, mark @rq_flags and increment elvpriv. Non-zero elvpriv will - * prevent the current elevator from being destroyed until the new - * request is freed. This guarantees icq's won't be destroyed and - * makes creating new ones safe. - * - * Flush requests do not use the elevator so skip initialization. - * This allows a request to share the flush and elevator data. - * - * Also, lookup icq while holding queue_lock. If it doesn't exist, - * it will be created after releasing queue_lock. - */ - if (!op_is_flush(op) && !blk_queue_bypass(q)) { - rq_flags |= RQF_ELVPRIV; - q->nr_rqs_elvpriv++; - if (et->icq_cache && ioc) - icq = ioc_lookup_icq(ioc, q); - } - - if (blk_queue_io_stat(q)) - rq_flags |= RQF_IO_STAT; - spin_unlock_irq(q->queue_lock); - - /* allocate and init request */ - rq = mempool_alloc(rl->rq_pool, gfp_mask); - if (!rq) - goto fail_alloc; - - blk_rq_init(q, rq); - blk_rq_set_rl(rq, rl); - rq->cmd_flags = op; - rq->rq_flags = rq_flags; - if (flags & BLK_MQ_REQ_PREEMPT) - rq->rq_flags |= RQF_PREEMPT; - - /* init elvpriv */ - if (rq_flags & RQF_ELVPRIV) { - if (unlikely(et->icq_cache && !icq)) { - if (ioc) - icq = ioc_create_icq(ioc, q, gfp_mask); - if (!icq) - goto fail_elvpriv; - } - - rq->elv.icq = icq; - if (unlikely(elv_set_request(q, rq, bio, gfp_mask))) - goto fail_elvpriv; - - /* @rq->elv.icq holds io_context until @rq is freed */ - if (icq) - get_io_context(icq->ioc); - } -out: - /* - * ioc may be NULL here, and ioc_batching will be false. That's - * OK, if the queue is under the request limit then requests need - * not count toward the nr_batch_requests limit. There will always - * be some limit enforced by BLK_BATCH_TIME. - */ - if (ioc_batching(q, ioc)) - ioc->nr_batch_requests--; - - trace_block_getrq(q, bio, op); - return rq; - -fail_elvpriv: - /* - * elvpriv init failed. ioc, icq and elvpriv aren't mempool backed - * and may fail indefinitely under memory pressure and thus - * shouldn't stall IO. Treat this request as !elvpriv. This will - * disturb iosched and blkcg but weird is bettern than dead. - */ - printk_ratelimited(KERN_WARNING "%s: dev %s: request aux data allocation failed, iosched may be disturbed\n", - __func__, dev_name(q->backing_dev_info->dev)); - - rq->rq_flags &= ~RQF_ELVPRIV; - rq->elv.icq = NULL; - - spin_lock_irq(q->queue_lock); - q->nr_rqs_elvpriv--; - spin_unlock_irq(q->queue_lock); - goto out; - -fail_alloc: - /* - * Allocation failed presumably due to memory. Undo anything we - * might have messed up. - * - * Allocating task should really be put onto the front of the wait - * queue, but this is pretty rare. - */ - spin_lock_irq(q->queue_lock); - freed_request(rl, is_sync, rq_flags); - - /* - * in the very unlikely event that allocation failed and no - * requests for this direction was pending, mark us starved so that - * freeing of a request in the other direction will notice - * us. another possible fix would be to split the rq mempool into - * READ and WRITE - */ -rq_starved: - if (unlikely(rl->count[is_sync] == 0)) - rl->starved[is_sync] = 1; - return ERR_PTR(-ENOMEM); -} - -/** - * get_request - get a free request - * @q: request_queue to allocate request from - * @op: operation and flags - * @bio: bio to allocate request for (can be %NULL) - * @flags: BLK_MQ_REQ_* flags. - * @gfp: allocator flags - * - * Get a free request from @q. If %BLK_MQ_REQ_NOWAIT is set in @flags, - * this function keeps retrying under memory pressure and fails iff @q is dead. - * - * Must be called with @q->queue_lock held and, - * Returns ERR_PTR on failure, with @q->queue_lock held. - * Returns request pointer on success, with @q->queue_lock *not held*. - */ -static struct request *get_request(struct request_queue *q, unsigned int op, - struct bio *bio, blk_mq_req_flags_t flags, gfp_t gfp) -{ - const bool is_sync = op_is_sync(op); - DEFINE_WAIT(wait); - struct request_list *rl; - struct request *rq; - - lockdep_assert_held(q->queue_lock); - WARN_ON_ONCE(q->mq_ops); - - rl = blk_get_rl(q, bio); /* transferred to @rq on success */ -retry: - rq = __get_request(rl, op, bio, flags, gfp); - if (!IS_ERR(rq)) - return rq; - - if (op & REQ_NOWAIT) { - blk_put_rl(rl); - return ERR_PTR(-EAGAIN); - } - - if ((flags & BLK_MQ_REQ_NOWAIT) || unlikely(blk_queue_dying(q))) { - blk_put_rl(rl); - return rq; - } - - /* wait on @rl and retry */ - prepare_to_wait_exclusive(&rl->wait[is_sync], &wait, - TASK_UNINTERRUPTIBLE); - - trace_block_sleeprq(q, bio, op); - - spin_unlock_irq(q->queue_lock); - io_schedule(); - - /* - * After sleeping, we become a "batching" process and will be able - * to allocate at least one request, and up to a big batch of them - * for a small period time. See ioc_batching, ioc_set_batching - */ - ioc_set_batching(q, current->io_context); - - spin_lock_irq(q->queue_lock); - finish_wait(&rl->wait[is_sync], &wait); - - goto retry; -} - -/* flags: BLK_MQ_REQ_PREEMPT and/or BLK_MQ_REQ_NOWAIT. */ -static struct request *blk_old_get_request(struct request_queue *q, - unsigned int op, blk_mq_req_flags_t flags) -{ - struct request *rq; - gfp_t gfp_mask = flags & BLK_MQ_REQ_NOWAIT ? GFP_ATOMIC : GFP_NOIO; - int ret = 0; - - WARN_ON_ONCE(q->mq_ops); - - /* create ioc upfront */ - create_io_context(gfp_mask, q->node); - - ret = blk_queue_enter(q, flags); - if (ret) - return ERR_PTR(ret); - spin_lock_irq(q->queue_lock); - rq = get_request(q, op, NULL, flags, gfp_mask); - if (IS_ERR(rq)) { - spin_unlock_irq(q->queue_lock); - blk_queue_exit(q); - return rq; - } - - /* q->queue_lock is unlocked at this point */ - rq->__data_len = 0; - rq->__sector = (sector_t) -1; - rq->bio = rq->biotail = NULL; - return rq; -} - -/** - * blk_get_request - allocate a request - * @q: request queue to allocate a request for - * @op: operation (REQ_OP_*) and REQ_* flags, e.g. REQ_SYNC. - * @flags: BLK_MQ_REQ_* flags, e.g. BLK_MQ_REQ_NOWAIT. - */ -struct request *blk_get_request(struct request_queue *q, unsigned int op, - blk_mq_req_flags_t flags) -{ - struct request *req; - - WARN_ON_ONCE(op & REQ_NOWAIT); - WARN_ON_ONCE(flags & ~(BLK_MQ_REQ_NOWAIT | BLK_MQ_REQ_PREEMPT)); - - if (q->mq_ops) { - req = blk_mq_alloc_request(q, op, flags); - if (!IS_ERR(req) && q->mq_ops->initialize_rq_fn) - q->mq_ops->initialize_rq_fn(req); - } else { - req = blk_old_get_request(q, op, flags); - if (!IS_ERR(req) && q->initialize_rq_fn) - q->initialize_rq_fn(req); - } - - return req; -} -EXPORT_SYMBOL(blk_get_request); - -/** - * blk_requeue_request - put a request back on queue - * @q: request queue where request should be inserted - * @rq: request to be inserted - * - * Description: - * Drivers often keep queueing requests until the hardware cannot accept - * more, when that condition happens we need to put the request back - * on the queue. Must be called with queue lock held. - */ -void blk_requeue_request(struct request_queue *q, struct request *rq) -{ - lockdep_assert_held(q->queue_lock); - WARN_ON_ONCE(q->mq_ops); - - blk_delete_timer(rq); - blk_clear_rq_complete(rq); - trace_block_rq_requeue(q, rq); - rq_qos_requeue(q, rq); - - BUG_ON(blk_queued_rq(rq)); - - elv_requeue_request(q, rq); -} -EXPORT_SYMBOL(blk_requeue_request); - -static void add_acct_request(struct request_queue *q, struct request *rq, - int where) -{ - blk_account_io_start(rq, true); - __elv_add_request(q, rq, where); -} - -static void part_round_stats_single(struct request_queue *q, int cpu, - struct hd_struct *part, unsigned long now, - unsigned int inflight) -{ - if (inflight) { - __part_stat_add(cpu, part, time_in_queue, - inflight * (now - part->stamp)); - __part_stat_add(cpu, part, io_ticks, (now - part->stamp)); - } - part->stamp = now; + part->stamp = now; } /** @@ -1730,61 +805,16 @@ EXPORT_SYMBOL_GPL(part_round_stats); void __blk_put_request(struct request_queue *q, struct request *req) { - req_flags_t rq_flags = req->rq_flags; - if (unlikely(!q)) return; - if (q->mq_ops) { - blk_mq_free_request(req); - return; - } - - lockdep_assert_held(q->queue_lock); - - blk_req_zone_write_unlock(req); - blk_pm_put_request(req); - blk_pm_mark_last_busy(req); - - elv_completed_request(q, req); - - /* this is a bio leak */ - WARN_ON(req->bio != NULL); - - rq_qos_done(q, req); - - /* - * Request may not have originated from ll_rw_blk. if not, - * it didn't come out of our reserved rq pools - */ - if (rq_flags & RQF_ALLOCED) { - struct request_list *rl = blk_rq_rl(req); - bool sync = op_is_sync(req->cmd_flags); - - BUG_ON(!list_empty(&req->queuelist)); - BUG_ON(ELV_ON_HASH(req)); - - blk_free_request(rl, req); - freed_request(rl, sync, rq_flags); - blk_put_rl(rl); - blk_queue_exit(q); - } + blk_mq_free_request(req); } EXPORT_SYMBOL_GPL(__blk_put_request); void blk_put_request(struct request *req) { - struct request_queue *q = req->q; - - if (q->mq_ops) - blk_mq_free_request(req); - else { - unsigned long flags; - - spin_lock_irqsave(q->queue_lock, flags); - __blk_put_request(q, req); - spin_unlock_irqrestore(q->queue_lock, flags); - } + blk_mq_free_request(req); } EXPORT_SYMBOL(blk_put_request); @@ -1893,10 +923,7 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, return false; *request_count = 0; - if (q->mq_ops) - plug_list = &plug->mq_list; - else - plug_list = &plug->list; + plug_list = &plug->mq_list; list_for_each_entry_reverse(rq, plug_list, queuelist) { bool merged = false; @@ -1947,11 +974,7 @@ unsigned int blk_plug_queued_count(struct request_queue *q) if (!plug) goto out; - if (q->mq_ops) - plug_list = &plug->mq_list; - else - plug_list = &plug->list; - + plug_list = &plug->mq_list; list_for_each_entry(rq, plug_list, queuelist) { if (rq->q == q) ret++; @@ -1979,133 +1002,6 @@ void blk_init_request_from_bio(struct request *req, struct bio *bio) } EXPORT_SYMBOL_GPL(blk_init_request_from_bio); -static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio) -{ - struct blk_plug *plug; - int where = ELEVATOR_INSERT_SORT; - struct request *req, *free; - unsigned int request_count = 0; - - /* - * low level driver can indicate that it wants pages above a - * certain limit bounced to low memory (ie for highmem, or even - * ISA dma in theory) - */ - blk_queue_bounce(q, &bio); - - blk_queue_split(q, &bio); - - if (!bio_integrity_prep(bio)) - return BLK_QC_T_NONE; - - if (op_is_flush(bio->bi_opf)) { - spin_lock_irq(q->queue_lock); - where = ELEVATOR_INSERT_FLUSH; - goto get_rq; - } - - /* - * Check if we can merge with the plugged list before grabbing - * any locks. - */ - if (!blk_queue_nomerges(q)) { - if (blk_attempt_plug_merge(q, bio, &request_count, NULL)) - return BLK_QC_T_NONE; - } else - request_count = blk_plug_queued_count(q); - - spin_lock_irq(q->queue_lock); - - switch (elv_merge(q, &req, bio)) { - case ELEVATOR_BACK_MERGE: - if (!bio_attempt_back_merge(q, req, bio)) - break; - elv_bio_merged(q, req, bio); - free = attempt_back_merge(q, req); - if (free) - __blk_put_request(q, free); - else - elv_merged_request(q, req, ELEVATOR_BACK_MERGE); - goto out_unlock; - case ELEVATOR_FRONT_MERGE: - if (!bio_attempt_front_merge(q, req, bio)) - break; - elv_bio_merged(q, req, bio); - free = attempt_front_merge(q, req); - if (free) - __blk_put_request(q, free); - else - elv_merged_request(q, req, ELEVATOR_FRONT_MERGE); - goto out_unlock; - default: - break; - } - -get_rq: - rq_qos_throttle(q, bio, q->queue_lock); - - /* - * Grab a free request. This is might sleep but can not fail. - * Returns with the queue unlocked. - */ - blk_queue_enter_live(q); - req = get_request(q, bio->bi_opf, bio, 0, GFP_NOIO); - if (IS_ERR(req)) { - blk_queue_exit(q); - rq_qos_cleanup(q, bio); - if (PTR_ERR(req) == -ENOMEM) - bio->bi_status = BLK_STS_RESOURCE; - else - bio->bi_status = BLK_STS_IOERR; - bio_endio(bio); - goto out_unlock; - } - - rq_qos_track(q, req, bio); - - /* - * After dropping the lock and possibly sleeping here, our request - * may now be mergeable after it had proven unmergeable (above). - * We don't worry about that case for efficiency. It won't happen - * often, and the elevators are able to handle it. - */ - blk_init_request_from_bio(req, bio); - - if (test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags)) - req->cpu = raw_smp_processor_id(); - - plug = current->plug; - if (plug) { - /* - * If this is the first request added after a plug, fire - * of a plug trace. - * - * @request_count may become stale because of schedule - * out, so check plug list again. - */ - if (!request_count || list_empty(&plug->list)) - trace_block_plug(q); - else { - struct request *last = list_entry_rq(plug->list.prev); - if (request_count >= BLK_MAX_REQUEST_COUNT || - blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE) { - blk_flush_plug_list(plug, false); - trace_block_plug(q); - } - } - list_add_tail(&req->queuelist, &plug->list); - blk_account_io_start(req, true); - } else { - spin_lock_irq(q->queue_lock); - add_acct_request(q, req, where); - __blk_run_queue(q); -out_unlock: - spin_unlock_irq(q->queue_lock); - } - - return BLK_QC_T_NONE; -} - static void handle_bad_sector(struct bio *bio, sector_t maxsector) { char b[BDEVNAME_SIZE]; @@ -2617,9 +1513,6 @@ static int blk_cloned_rq_check_limits(struct request_queue *q, */ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq) { - unsigned long flags; - int where = ELEVATOR_INSERT_BACK; - if (blk_cloned_rq_check_limits(q, rq)) return BLK_STS_IOERR; @@ -2627,38 +1520,15 @@ blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request * should_fail_request(&rq->rq_disk->part0, blk_rq_bytes(rq))) return BLK_STS_IOERR; - if (q->mq_ops) { - if (blk_queue_io_stat(q)) - blk_account_io_start(rq, true); - /* - * Since we have a scheduler attached on the top device, - * bypass a potential scheduler on the bottom device for - * insert. - */ - return blk_mq_request_issue_directly(rq); - } - - spin_lock_irqsave(q->queue_lock, flags); - if (unlikely(blk_queue_dying(q))) { - spin_unlock_irqrestore(q->queue_lock, flags); - return BLK_STS_IOERR; - } + if (blk_queue_io_stat(q)) + blk_account_io_start(rq, true); /* - * Submitting request must be dequeued before calling this function - * because it will be linked to another request_queue + * Since we have a scheduler attached on the top device, + * bypass a potential scheduler on the bottom device for + * insert. */ - BUG_ON(blk_queued_rq(rq)); - - if (op_is_flush(rq->cmd_flags)) - where = ELEVATOR_INSERT_FLUSH; - - add_acct_request(q, rq, where); - if (where == ELEVATOR_INSERT_FLUSH) - __blk_run_queue(q); - spin_unlock_irqrestore(q->queue_lock, flags); - - return BLK_STS_OK; + return blk_mq_request_issue_directly(rq); } EXPORT_SYMBOL_GPL(blk_insert_cloned_request); @@ -2778,225 +1648,6 @@ void blk_account_io_start(struct request *rq, bool new_io) part_stat_unlock(); } -static struct request *elv_next_request(struct request_queue *q) -{ - struct request *rq; - struct blk_flush_queue *fq = blk_get_flush_queue(q, NULL); - - WARN_ON_ONCE(q->mq_ops); - - while (1) { - list_for_each_entry(rq, &q->queue_head, queuelist) { -#ifdef CONFIG_PM - /* - * If a request gets queued in state RPM_SUSPENDED - * then that's a kernel bug. - */ - WARN_ON_ONCE(q->rpm_status == RPM_SUSPENDED); -#endif - return rq; - } - - /* - * Flush request is running and flush request isn't queueable - * in the drive, we can hold the queue till flush request is - * finished. Even we don't do this, driver can't dispatch next - * requests and will requeue them. And this can improve - * throughput too. For example, we have request flush1, write1, - * flush 2. flush1 is dispatched, then queue is hold, write1 - * isn't inserted to queue. After flush1 is finished, flush2 - * will be dispatched. Since disk cache is already clean, - * flush2 will be finished very soon, so looks like flush2 is - * folded to flush1. - * Since the queue is hold, a flag is set to indicate the queue - * should be restarted later. Please see flush_end_io() for - * details. - */ - if (fq->flush_pending_idx != fq->flush_running_idx && - !queue_flush_queueable(q)) { - fq->flush_queue_delayed = 1; - return NULL; - } - if (unlikely(blk_queue_bypass(q)) || - !q->elevator->type->ops.sq.elevator_dispatch_fn(q, 0)) - return NULL; - } -} - -/** - * blk_peek_request - peek at the top of a request queue - * @q: request queue to peek at - * - * Description: - * Return the request at the top of @q. The returned request - * should be started using blk_start_request() before LLD starts - * processing it. - * - * Return: - * Pointer to the request at the top of @q if available. Null - * otherwise. - */ -struct request *blk_peek_request(struct request_queue *q) -{ - struct request *rq; - int ret; - - lockdep_assert_held(q->queue_lock); - WARN_ON_ONCE(q->mq_ops); - - while ((rq = elv_next_request(q)) != NULL) { - if (!(rq->rq_flags & RQF_STARTED)) { - /* - * This is the first time the device driver - * sees this request (possibly after - * requeueing). Notify IO scheduler. - */ - if (rq->rq_flags & RQF_SORTED) - elv_activate_rq(q, rq); - - /* - * just mark as started even if we don't start - * it, a request that has been delayed should - * not be passed by new incoming requests - */ - rq->rq_flags |= RQF_STARTED; - trace_block_rq_issue(q, rq); - } - - if (!q->boundary_rq || q->boundary_rq == rq) { - q->end_sector = rq_end_sector(rq); - q->boundary_rq = NULL; - } - - if (rq->rq_flags & RQF_DONTPREP) - break; - - if (q->dma_drain_size && blk_rq_bytes(rq)) { - /* - * make sure space for the drain appears we - * know we can do this because max_hw_segments - * has been adjusted to be one fewer than the - * device can handle - */ - rq->nr_phys_segments++; - } - - if (!q->prep_rq_fn) - break; - - ret = q->prep_rq_fn(q, rq); - if (ret == BLKPREP_OK) { - break; - } else if (ret == BLKPREP_DEFER) { - /* - * the request may have been (partially) prepped. - * we need to keep this request in the front to - * avoid resource deadlock. RQF_STARTED will - * prevent other fs requests from passing this one. - */ - if (q->dma_drain_size && blk_rq_bytes(rq) && - !(rq->rq_flags & RQF_DONTPREP)) { - /* - * remove the space for the drain we added - * so that we don't add it again - */ - --rq->nr_phys_segments; - } - - rq = NULL; - break; - } else if (ret == BLKPREP_KILL || ret == BLKPREP_INVALID) { - rq->rq_flags |= RQF_QUIET; - /* - * Mark this request as started so we don't trigger - * any debug logic in the end I/O path. - */ - blk_start_request(rq); - __blk_end_request_all(rq, ret == BLKPREP_INVALID ? - BLK_STS_TARGET : BLK_STS_IOERR); - } else { - printk(KERN_ERR "%s: bad return=%d\n", __func__, ret); - break; - } - } - - return rq; -} -EXPORT_SYMBOL(blk_peek_request); - -static void blk_dequeue_request(struct request *rq) -{ - struct request_queue *q = rq->q; - - BUG_ON(list_empty(&rq->queuelist)); - BUG_ON(ELV_ON_HASH(rq)); - - list_del_init(&rq->queuelist); - - /* - * the time frame between a request being removed from the lists - * and to it is freed is accounted as io that is in progress at - * the driver side. - */ - if (blk_account_rq(rq)) - q->in_flight[rq_is_sync(rq)]++; -} - -/** - * blk_start_request - start request processing on the driver - * @req: request to dequeue - * - * Description: - * Dequeue @req and start timeout timer on it. This hands off the - * request to the driver. - */ -void blk_start_request(struct request *req) -{ - lockdep_assert_held(req->q->queue_lock); - WARN_ON_ONCE(req->q->mq_ops); - - blk_dequeue_request(req); - - if (test_bit(QUEUE_FLAG_STATS, &req->q->queue_flags)) { - req->io_start_time_ns = ktime_get_ns(); -#ifdef CONFIG_BLK_DEV_THROTTLING_LOW - req->throtl_size = blk_rq_sectors(req); -#endif - req->rq_flags |= RQF_STATS; - rq_qos_issue(req->q, req); - } - - BUG_ON(blk_rq_is_complete(req)); - blk_add_timer(req); -} -EXPORT_SYMBOL(blk_start_request); - -/** - * blk_fetch_request - fetch a request from a request queue - * @q: request queue to fetch a request from - * - * Description: - * Return the request at the top of @q. The request is started on - * return and LLD can start processing it immediately. - * - * Return: - * Pointer to the request at the top of @q if available. Null - * otherwise. - */ -struct request *blk_fetch_request(struct request_queue *q) -{ - struct request *rq; - - lockdep_assert_held(q->queue_lock); - WARN_ON_ONCE(q->mq_ops); - - rq = blk_peek_request(q); - if (rq) - blk_start_request(rq); - return rq; -} -EXPORT_SYMBOL(blk_fetch_request); - /* * Steal bios from a request and add them to a bio list. * The request must not have been partially completed before. @@ -3122,252 +1773,6 @@ bool blk_update_request(struct request *req, blk_status_t error, } EXPORT_SYMBOL_GPL(blk_update_request); -static bool blk_update_bidi_request(struct request *rq, blk_status_t error, - unsigned int nr_bytes, - unsigned int bidi_bytes) -{ - if (blk_update_request(rq, error, nr_bytes)) - return true; - - /* Bidi request must be completed as a whole */ - if (unlikely(blk_bidi_rq(rq)) && - blk_update_request(rq->next_rq, error, bidi_bytes)) - return true; - - if (blk_queue_add_random(rq->q)) - add_disk_randomness(rq->rq_disk); - - return false; -} - -/** - * blk_unprep_request - unprepare a request - * @req: the request - * - * This function makes a request ready for complete resubmission (or - * completion). It happens only after all error handling is complete, - * so represents the appropriate moment to deallocate any resources - * that were allocated to the request in the prep_rq_fn. The queue - * lock is held when calling this. - */ -void blk_unprep_request(struct request *req) -{ - struct request_queue *q = req->q; - - req->rq_flags &= ~RQF_DONTPREP; - if (q->unprep_rq_fn) - q->unprep_rq_fn(q, req); -} -EXPORT_SYMBOL_GPL(blk_unprep_request); - -void blk_finish_request(struct request *req, blk_status_t error) -{ - struct request_queue *q = req->q; - u64 now = ktime_get_ns(); - - lockdep_assert_held(req->q->queue_lock); - WARN_ON_ONCE(q->mq_ops); - - if (req->rq_flags & RQF_STATS) - blk_stat_add(req, now); - - BUG_ON(blk_queued_rq(req)); - - if (unlikely(laptop_mode) && !blk_rq_is_passthrough(req)) - laptop_io_completion(req->q->backing_dev_info); - - blk_delete_timer(req); - - if (req->rq_flags & RQF_DONTPREP) - blk_unprep_request(req); - - blk_account_io_done(req, now); - - if (req->end_io) { - rq_qos_done(q, req); - req->end_io(req, error); - } else { - if (blk_bidi_rq(req)) - __blk_put_request(req->next_rq->q, req->next_rq); - - __blk_put_request(q, req); - } -} -EXPORT_SYMBOL(blk_finish_request); - -/** - * blk_end_bidi_request - Complete a bidi request - * @rq: the request to complete - * @error: block status code - * @nr_bytes: number of bytes to complete @rq - * @bidi_bytes: number of bytes to complete @rq->next_rq - * - * Description: - * Ends I/O on a number of bytes attached to @rq and @rq->next_rq. - * Drivers that supports bidi can safely call this member for any - * type of request, bidi or uni. In the later case @bidi_bytes is - * just ignored. - * - * Return: - * %false - we are done with this request - * %true - still buffers pending for this request - **/ -static bool blk_end_bidi_request(struct request *rq, blk_status_t error, - unsigned int nr_bytes, unsigned int bidi_bytes) -{ - struct request_queue *q = rq->q; - unsigned long flags; - - WARN_ON_ONCE(q->mq_ops); - - if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes)) - return true; - - spin_lock_irqsave(q->queue_lock, flags); - blk_finish_request(rq, error); - spin_unlock_irqrestore(q->queue_lock, flags); - - return false; -} - -/** - * __blk_end_bidi_request - Complete a bidi request with queue lock held - * @rq: the request to complete - * @error: block status code - * @nr_bytes: number of bytes to complete @rq - * @bidi_bytes: number of bytes to complete @rq->next_rq - * - * Description: - * Identical to blk_end_bidi_request() except that queue lock is - * assumed to be locked on entry and remains so on return. - * - * Return: - * %false - we are done with this request - * %true - still buffers pending for this request - **/ -static bool __blk_end_bidi_request(struct request *rq, blk_status_t error, - unsigned int nr_bytes, unsigned int bidi_bytes) -{ - lockdep_assert_held(rq->q->queue_lock); - WARN_ON_ONCE(rq->q->mq_ops); - - if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes)) - return true; - - blk_finish_request(rq, error); - - return false; -} - -/** - * blk_end_request - Helper function for drivers to complete the request. - * @rq: the request being processed - * @error: block status code - * @nr_bytes: number of bytes to complete - * - * Description: - * Ends I/O on a number of bytes attached to @rq. - * If @rq has leftover, sets it up for the next range of segments. - * - * Return: - * %false - we are done with this request - * %true - still buffers pending for this request - **/ -bool blk_end_request(struct request *rq, blk_status_t error, - unsigned int nr_bytes) -{ - WARN_ON_ONCE(rq->q->mq_ops); - return blk_end_bidi_request(rq, error, nr_bytes, 0); -} -EXPORT_SYMBOL(blk_end_request); - -/** - * blk_end_request_all - Helper function for drives to finish the request. - * @rq: the request to finish - * @error: block status code - * - * Description: - * Completely finish @rq. - */ -void blk_end_request_all(struct request *rq, blk_status_t error) -{ - bool pending; - unsigned int bidi_bytes = 0; - - if (unlikely(blk_bidi_rq(rq))) - bidi_bytes = blk_rq_bytes(rq->next_rq); - - pending = blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes); - BUG_ON(pending); -} -EXPORT_SYMBOL(blk_end_request_all); - -/** - * __blk_end_request - Helper function for drivers to complete the request. - * @rq: the request being processed - * @error: block status code - * @nr_bytes: number of bytes to complete - * - * Description: - * Must be called with queue lock held unlike blk_end_request(). - * - * Return: - * %false - we are done with this request - * %true - still buffers pending for this request - **/ -bool __blk_end_request(struct request *rq, blk_status_t error, - unsigned int nr_bytes) -{ - lockdep_assert_held(rq->q->queue_lock); - WARN_ON_ONCE(rq->q->mq_ops); - - return __blk_end_bidi_request(rq, error, nr_bytes, 0); -} -EXPORT_SYMBOL(__blk_end_request); - -/** - * __blk_end_request_all - Helper function for drives to finish the request. - * @rq: the request to finish - * @error: block status code - * - * Description: - * Completely finish @rq. Must be called with queue lock held. - */ -void __blk_end_request_all(struct request *rq, blk_status_t error) -{ - bool pending; - unsigned int bidi_bytes = 0; - - lockdep_assert_held(rq->q->queue_lock); - WARN_ON_ONCE(rq->q->mq_ops); - - if (unlikely(blk_bidi_rq(rq))) - bidi_bytes = blk_rq_bytes(rq->next_rq); - - pending = __blk_end_bidi_request(rq, error, blk_rq_bytes(rq), bidi_bytes); - BUG_ON(pending); -} -EXPORT_SYMBOL(__blk_end_request_all); - -/** - * __blk_end_request_cur - Helper function to finish the current request chunk. - * @rq: the request to finish the current chunk for - * @error: block status code - * - * Description: - * Complete the current consecutively mapped chunk from @rq. Must - * be called with queue lock held. - * - * Return: - * %false - we are done with this request - * %true - still buffers pending for this request - */ -bool __blk_end_request_cur(struct request *rq, blk_status_t error) -{ - return __blk_end_request(rq, error, blk_rq_cur_bytes(rq)); -} -EXPORT_SYMBOL(__blk_end_request_cur); - void blk_rq_bio_prep(struct request_queue *q, struct request *rq, struct bio *bio) { @@ -3567,7 +1972,6 @@ void blk_start_plug(struct blk_plug *plug) if (tsk->plug) return; - INIT_LIST_HEAD(&plug->list); INIT_LIST_HEAD(&plug->mq_list); INIT_LIST_HEAD(&plug->cb_list); /* @@ -3578,36 +1982,6 @@ void blk_start_plug(struct blk_plug *plug) } EXPORT_SYMBOL(blk_start_plug); -static int plug_rq_cmp(void *priv, struct list_head *a, struct list_head *b) -{ - struct request *rqa = container_of(a, struct request, queuelist); - struct request *rqb = container_of(b, struct request, queuelist); - - return !(rqa->q < rqb->q || - (rqa->q == rqb->q && blk_rq_pos(rqa) < blk_rq_pos(rqb))); -} - -/* - * If 'from_schedule' is true, then postpone the dispatch of requests - * until a safe kblockd context. We due this to avoid accidental big - * additional stack usage in driver dispatch, in places where the originally - * plugger did not intend it. - */ -static void queue_unplugged(struct request_queue *q, unsigned int depth, - bool from_schedule) - __releases(q->queue_lock) -{ - lockdep_assert_held(q->queue_lock); - - trace_block_unplug(q, depth, !from_schedule); - - if (from_schedule) - blk_run_queue_async(q); - else - __blk_run_queue(q); - spin_unlock_irq(q->queue_lock); -} - static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule) { LIST_HEAD(callbacks); @@ -3652,65 +2026,10 @@ EXPORT_SYMBOL(blk_check_plugged); void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule) { - struct request_queue *q; - struct request *rq; - LIST_HEAD(list); - unsigned int depth; - flush_plug_callbacks(plug, from_schedule); if (!list_empty(&plug->mq_list)) blk_mq_flush_plug_list(plug, from_schedule); - - if (list_empty(&plug->list)) - return; - - list_splice_init(&plug->list, &list); - - list_sort(NULL, &list, plug_rq_cmp); - - q = NULL; - depth = 0; - - while (!list_empty(&list)) { - rq = list_entry_rq(list.next); - list_del_init(&rq->queuelist); - BUG_ON(!rq->q); - if (rq->q != q) { - /* - * This drops the queue lock - */ - if (q) - queue_unplugged(q, depth, from_schedule); - q = rq->q; - depth = 0; - spin_lock_irq(q->queue_lock); - } - - /* - * Short-circuit if @q is dead - */ - if (unlikely(blk_queue_dying(q))) { - __blk_end_request_all(rq, BLK_STS_IOERR); - continue; - } - - /* - * rq is already accounted, so use raw insert - */ - if (op_is_flush(rq->cmd_flags)) - __elv_add_request(q, rq, ELEVATOR_INSERT_FLUSH); - else - __elv_add_request(q, rq, ELEVATOR_INSERT_SORT_MERGE); - - depth++; - } - - /* - * This drops the queue lock - */ - if (q) - queue_unplugged(q, depth, from_schedule); } void blk_finish_plug(struct blk_plug *plug) diff --git a/block/blk-exec.c b/block/blk-exec.c index f7b292f12449..a34b7d918742 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -48,8 +48,6 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, struct request *rq, int at_head, rq_end_io_fn *done) { - int where = at_head ? ELEVATOR_INSERT_FRONT : ELEVATOR_INSERT_BACK; - WARN_ON(irqs_disabled()); WARN_ON(!blk_rq_is_passthrough(rq)); @@ -60,23 +58,7 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, * don't check dying flag for MQ because the request won't * be reused after dying flag is set */ - if (q->mq_ops) { - blk_mq_sched_insert_request(rq, at_head, true, false); - return; - } - - spin_lock_irq(q->queue_lock); - - if (unlikely(blk_queue_dying(q))) { - rq->rq_flags |= RQF_QUIET; - __blk_end_request_all(rq, BLK_STS_IOERR); - spin_unlock_irq(q->queue_lock); - return; - } - - __elv_add_request(q, rq, where); - __blk_run_queue(q); - spin_unlock_irq(q->queue_lock); + blk_mq_sched_insert_request(rq, at_head, true, false); } EXPORT_SYMBOL_GPL(blk_execute_rq_nowait); diff --git a/block/blk-ioc.c b/block/blk-ioc.c index 01580f88fcb3..391128456aec 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -48,10 +48,8 @@ static void ioc_exit_icq(struct io_cq *icq) if (icq->flags & ICQ_EXITED) return; - if (et->uses_mq && et->ops.mq.exit_icq) + if (et->ops.mq.exit_icq) et->ops.mq.exit_icq(icq); - else if (!et->uses_mq && et->ops.sq.elevator_exit_icq_fn) - et->ops.sq.elevator_exit_icq_fn(icq); icq->flags |= ICQ_EXITED; } @@ -187,25 +185,13 @@ void put_io_context_active(struct io_context *ioc) * reverse double locking. Read comment in ioc_release_fn() for * explanation on the nested locking annotation. */ -retry: spin_lock_irqsave_nested(&ioc->lock, flags, 1); hlist_for_each_entry(icq, &ioc->icq_list, ioc_node) { if (icq->flags & ICQ_EXITED) continue; et = icq->q->elevator->type; - if (et->uses_mq) { - ioc_exit_icq(icq); - } else { - if (spin_trylock(icq->q->queue_lock)) { - ioc_exit_icq(icq); - spin_unlock(icq->q->queue_lock); - } else { - spin_unlock_irqrestore(&ioc->lock, flags); - cpu_relax(); - goto retry; - } - } + ioc_exit_icq(icq); } spin_unlock_irqrestore(&ioc->lock, flags); @@ -232,7 +218,7 @@ static void __ioc_clear_queue(struct list_head *icq_list) while (!list_empty(icq_list)) { struct io_cq *icq = list_entry(icq_list->next, - struct io_cq, q_node); + struct io_cq, q_node); struct io_context *ioc = icq->ioc; spin_lock_irqsave(&ioc->lock, flags); @@ -253,14 +239,9 @@ void ioc_clear_queue(struct request_queue *q) spin_lock_irq(q->queue_lock); list_splice_init(&q->icq_list, &icq_list); + spin_unlock_irq(q->queue_lock); - if (q->mq_ops) { - spin_unlock_irq(q->queue_lock); - __ioc_clear_queue(&icq_list); - } else { - __ioc_clear_queue(&icq_list); - spin_unlock_irq(q->queue_lock); - } + __ioc_clear_queue(&icq_list); } int create_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node) @@ -415,10 +396,8 @@ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q, if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) { hlist_add_head(&icq->ioc_node, &ioc->icq_list); list_add(&icq->q_node, &q->icq_list); - if (et->uses_mq && et->ops.mq.init_icq) + if (et->ops.mq.init_icq) et->ops.mq.init_icq(icq); - else if (!et->uses_mq && et->ops.sq.elevator_init_icq_fn) - et->ops.sq.elevator_init_icq_fn(icq); } else { kmem_cache_free(et->icq_cache, icq); icq = ioc_lookup_icq(ioc, q); diff --git a/block/blk-merge.c b/block/blk-merge.c index 6b5ad275ed56..c068c30b0c35 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -862,13 +862,8 @@ struct request *attempt_front_merge(struct request_queue *q, struct request *rq) int blk_attempt_req_merge(struct request_queue *q, struct request *rq, struct request *next) { - struct elevator_queue *e = q->elevator; struct request *free; - if (!e->uses_mq && e->type->ops.sq.elevator_allow_rq_merge_fn) - if (!e->type->ops.sq.elevator_allow_rq_merge_fn(q, rq, next)) - return 0; - free = attempt_merge(q, rq, next); if (free) { __blk_put_request(q, free); diff --git a/block/blk-settings.c b/block/blk-settings.c index ac8b8ba4b126..39c3c301a687 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -20,40 +20,6 @@ EXPORT_SYMBOL(blk_max_low_pfn); unsigned long blk_max_pfn; -/** - * blk_queue_prep_rq - set a prepare_request function for queue - * @q: queue - * @pfn: prepare_request function - * - * It's possible for a queue to register a prepare_request callback which - * is invoked before the request is handed to the request_fn. The goal of - * the function is to prepare a request for I/O, it can be used to build a - * cdb from the request data for instance. - * - */ -void blk_queue_prep_rq(struct request_queue *q, prep_rq_fn *pfn) -{ - q->prep_rq_fn = pfn; -} -EXPORT_SYMBOL(blk_queue_prep_rq); - -/** - * blk_queue_unprep_rq - set an unprepare_request function for queue - * @q: queue - * @ufn: unprepare_request function - * - * It's possible for a queue to register an unprepare_request callback - * which is invoked before the request is finally completed. The goal - * of the function is to deallocate any data that was allocated in the - * prepare_request callback. - * - */ -void blk_queue_unprep_rq(struct request_queue *q, unprep_rq_fn *ufn) -{ - q->unprep_rq_fn = ufn; -} -EXPORT_SYMBOL(blk_queue_unprep_rq); - void blk_queue_softirq_done(struct request_queue *q, softirq_done_fn *fn) { q->softirq_done_fn = fn; @@ -163,8 +129,6 @@ void blk_queue_make_request(struct request_queue *q, make_request_fn *mfn) q->make_request_fn = mfn; blk_queue_dma_alignment(q, 511); - blk_queue_congestion_threshold(q); - q->nr_batching = BLK_BATCH_REQ; blk_set_default_limits(&q->limits); } diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 1b82ccfde3fe..d4b1b84ba8ca 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -68,7 +68,7 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count) unsigned long nr; int ret, err; - if (!q->request_fn && !q->mq_ops) + if (!q->mq_ops) return -EINVAL; ret = queue_var_store(&nr, page, count); @@ -78,11 +78,7 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count) if (nr < BLKDEV_MIN_RQ) nr = BLKDEV_MIN_RQ; - if (q->request_fn) - err = blk_update_nr_requests(q, nr); - else - err = blk_mq_update_nr_requests(q, nr); - + err = blk_mq_update_nr_requests(q, nr); if (err) return err; @@ -463,20 +459,14 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page, * ends up either enabling or disabling wbt completely. We can't * have IO inflight if that happens. */ - if (q->mq_ops) { - blk_mq_freeze_queue(q); - blk_mq_quiesce_queue(q); - } else - blk_queue_bypass_start(q); + blk_mq_freeze_queue(q); + blk_mq_quiesce_queue(q); wbt_set_min_lat(q, val); wbt_update_limits(q); - if (q->mq_ops) { - blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); - } else - blk_queue_bypass_end(q); + blk_mq_unquiesce_queue(q); + blk_mq_unfreeze_queue(q); return count; } @@ -847,17 +837,10 @@ static void __blk_release_queue(struct work_struct *work) blk_free_queue_stats(q->stats); - blk_exit_rl(q, &q->root_rl); - blk_queue_free_zone_bitmaps(q); - if (!q->mq_ops) { - if (q->exit_rq_fn) - q->exit_rq_fn(q, q->fq->flush_rq); - blk_free_flush_queue(q->fq); - } else { + if (q->mq_ops) blk_mq_release(q); - } blk_trace_shutdown(q); @@ -920,7 +903,6 @@ int blk_register_queue(struct gendisk *disk) if (!blk_queue_init_done(q)) { queue_flag_set_unlocked(QUEUE_FLAG_INIT_DONE, q); percpu_ref_switch_to_percpu(&q->q_usage_counter); - blk_queue_bypass_end(q); } ret = blk_trace_init_sysfs(dev); @@ -947,7 +929,7 @@ int blk_register_queue(struct gendisk *disk) blk_throtl_register_queue(q); - if (q->request_fn || (q->mq_ops && q->elevator)) { + if ((q->mq_ops && q->elevator)) { ret = elv_register_queue(q); if (ret) { mutex_unlock(&q->sysfs_lock); @@ -1005,7 +987,7 @@ void blk_unregister_queue(struct gendisk *disk) blk_trace_remove_sysfs(disk_to_dev(disk)); mutex_lock(&q->sysfs_lock); - if (q->request_fn || (q->mq_ops && q->elevator)) + if (q->mq_ops && q->elevator) elv_unregister_queue(q); mutex_unlock(&q->sysfs_lock); diff --git a/block/blk.h b/block/blk.h index 57a302bf5a70..e2604ae7ddfa 100644 --- a/block/blk.h +++ b/block/blk.h @@ -7,12 +7,6 @@ #include #include "blk-mq.h" -/* Amount of time in which a process may batch requests */ -#define BLK_BATCH_TIME (HZ/50UL) - -/* Number of requests a "batching" process may submit */ -#define BLK_BATCH_REQ 32 - /* Max future timer expiry for timeouts */ #define BLK_MAX_TIMEOUT (5 * HZ) @@ -132,9 +126,6 @@ void blk_exit_rl(struct request_queue *q, struct request_list *rl); void blk_exit_queue(struct request_queue *q); void blk_rq_bio_prep(struct request_queue *q, struct request *rq, struct bio *bio); -void blk_queue_bypass_start(struct request_queue *q); -void blk_queue_bypass_end(struct request_queue *q); -void __blk_queue_free_tags(struct request_queue *q); void blk_freeze_queue(struct request_queue *q); static inline void blk_queue_enter_live(struct request_queue *q) @@ -281,23 +272,6 @@ static inline bool blk_rq_is_complete(struct request *rq) void blk_insert_flush(struct request *rq); -static inline void elv_activate_rq(struct request_queue *q, struct request *rq) -{ - struct elevator_queue *e = q->elevator; - - if (e->type->ops.sq.elevator_activate_req_fn) - e->type->ops.sq.elevator_activate_req_fn(q, rq); -} - -static inline void elv_deactivate_rq(struct request_queue *q, struct request *rq) -{ - struct elevator_queue *e = q->elevator; - - if (e->type->ops.sq.elevator_deactivate_req_fn) - e->type->ops.sq.elevator_deactivate_req_fn(q, rq); -} - -int elevator_init(struct request_queue *); int elevator_init_mq(struct request_queue *q); int elevator_switch_mq(struct request_queue *q, struct elevator_type *new_e); @@ -332,31 +306,8 @@ void blk_rq_set_mixed_merge(struct request *rq); bool blk_rq_merge_ok(struct request *rq, struct bio *bio); enum elv_merge blk_try_merge(struct request *rq, struct bio *bio); -void blk_queue_congestion_threshold(struct request_queue *q); - int blk_dev_init(void); - -/* - * Return the threshold (number of used requests) at which the queue is - * considered to be congested. It include a little hysteresis to keep the - * context switch rate down. - */ -static inline int queue_congestion_on_threshold(struct request_queue *q) -{ - return q->nr_congestion_on; -} - -/* - * The threshold at which a queue is considered to be uncongested - */ -static inline int queue_congestion_off_threshold(struct request_queue *q) -{ - return q->nr_congestion_off; -} - -extern int blk_update_nr_requests(struct request_queue *, unsigned int); - /* * Contribute to IO statistics IFF: * @@ -478,8 +429,6 @@ static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio) } #endif /* CONFIG_BOUNCE */ -extern void blk_drain_queue(struct request_queue *q); - #ifdef CONFIG_BLK_CGROUP_IOLATENCY extern int blk_iolatency_init(struct request_queue *q); #else diff --git a/block/elevator.c b/block/elevator.c index 54e1adac26c5..334097c54b08 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -61,10 +61,8 @@ static int elv_iosched_allow_bio_merge(struct request *rq, struct bio *bio) struct request_queue *q = rq->q; struct elevator_queue *e = q->elevator; - if (e->uses_mq && e->type->ops.mq.allow_merge) + if (e->type->ops.mq.allow_merge) return e->type->ops.mq.allow_merge(q, rq, bio); - else if (!e->uses_mq && e->type->ops.sq.elevator_allow_bio_merge_fn) - return e->type->ops.sq.elevator_allow_bio_merge_fn(q, rq, bio); return 1; } @@ -95,14 +93,14 @@ static bool elevator_match(const struct elevator_type *e, const char *name) } /* - * Return scheduler with name 'name' and with matching 'mq capability + * Return scheduler with name 'name' */ -static struct elevator_type *elevator_find(const char *name, bool mq) +static struct elevator_type *elevator_find(const char *name) { struct elevator_type *e; list_for_each_entry(e, &elv_list, list) { - if (elevator_match(e, name) && (mq == e->uses_mq)) + if (elevator_match(e, name)) return e; } @@ -121,12 +119,12 @@ static struct elevator_type *elevator_get(struct request_queue *q, spin_lock(&elv_list_lock); - e = elevator_find(name, q->mq_ops != NULL); + e = elevator_find(name); if (!e && try_loading) { spin_unlock(&elv_list_lock); request_module("%s-iosched", name); spin_lock(&elv_list_lock); - e = elevator_find(name, q->mq_ops != NULL); + e = elevator_find(name); } if (e && !try_module_get(e->elevator_owner)) @@ -150,26 +148,6 @@ static int __init elevator_setup(char *str) __setup("elevator=", elevator_setup); -/* called during boot to load the elevator chosen by the elevator param */ -void __init load_default_elevator_module(void) -{ - struct elevator_type *e; - - if (!chosen_elevator[0]) - return; - - /* - * Boot parameter is deprecated, we haven't supported that for MQ. - * Only look for non-mq schedulers from here. - */ - spin_lock(&elv_list_lock); - e = elevator_find(chosen_elevator, false); - spin_unlock(&elv_list_lock); - - if (!e) - request_module("%s-iosched", chosen_elevator); -} - static struct kobj_type elv_ktype; struct elevator_queue *elevator_alloc(struct request_queue *q, @@ -185,7 +163,6 @@ struct elevator_queue *elevator_alloc(struct request_queue *q, kobject_init(&eq->kobj, &elv_ktype); mutex_init(&eq->sysfs_lock); hash_init(eq->hash); - eq->uses_mq = e->uses_mq; return eq; } @@ -200,52 +177,11 @@ static void elevator_release(struct kobject *kobj) kfree(e); } -/* - * Use the default elevator specified by config boot param for non-mq devices, - * or by config option. Don't try to load modules as we could be running off - * async and request_module() isn't allowed from async. - */ -int elevator_init(struct request_queue *q) -{ - struct elevator_type *e = NULL; - int err = 0; - - /* - * q->sysfs_lock must be held to provide mutual exclusion between - * elevator_switch() and here. - */ - mutex_lock(&q->sysfs_lock); - if (unlikely(q->elevator)) - goto out_unlock; - - if (*chosen_elevator) { - e = elevator_get(q, chosen_elevator, false); - if (!e) - printk(KERN_ERR "I/O scheduler %s not found\n", - chosen_elevator); - } - - if (!e) { - printk(KERN_ERR - "Default I/O scheduler not found. Using noop.\n"); - e = elevator_get(q, "noop", false); - } - - err = e->ops.sq.elevator_init_fn(q, e); - if (err) - elevator_put(e); -out_unlock: - mutex_unlock(&q->sysfs_lock); - return err; -} - void elevator_exit(struct request_queue *q, struct elevator_queue *e) { mutex_lock(&e->sysfs_lock); - if (e->uses_mq && e->type->ops.mq.exit_sched) + if (e->type->ops.mq.exit_sched) blk_mq_exit_sched(q, e); - else if (!e->uses_mq && e->type->ops.sq.elevator_exit_fn) - e->type->ops.sq.elevator_exit_fn(e); mutex_unlock(&e->sysfs_lock); kobject_put(&e->kobj); @@ -393,10 +329,8 @@ enum elv_merge elv_merge(struct request_queue *q, struct request **req, return ELEVATOR_BACK_MERGE; } - if (e->uses_mq && e->type->ops.mq.request_merge) + if (e->type->ops.mq.request_merge) return e->type->ops.mq.request_merge(q, req, bio); - else if (!e->uses_mq && e->type->ops.sq.elevator_merge_fn) - return e->type->ops.sq.elevator_merge_fn(q, req, bio); return ELEVATOR_NO_MERGE; } @@ -447,10 +381,8 @@ void elv_merged_request(struct request_queue *q, struct request *rq, { struct elevator_queue *e = q->elevator; - if (e->uses_mq && e->type->ops.mq.request_merged) + if (e->type->ops.mq.request_merged) e->type->ops.mq.request_merged(q, rq, type); - else if (!e->uses_mq && e->type->ops.sq.elevator_merged_fn) - e->type->ops.sq.elevator_merged_fn(q, rq, type); if (type == ELEVATOR_BACK_MERGE) elv_rqhash_reposition(q, rq); @@ -464,13 +396,8 @@ void elv_merge_requests(struct request_queue *q, struct request *rq, struct elevator_queue *e = q->elevator; bool next_sorted = false; - if (e->uses_mq && e->type->ops.mq.requests_merged) + if (e->type->ops.mq.requests_merged) e->type->ops.mq.requests_merged(q, rq, next); - else if (e->type->ops.sq.elevator_merge_req_fn) { - next_sorted = (__force bool)(next->rq_flags & RQF_SORTED); - if (next_sorted) - e->type->ops.sq.elevator_merge_req_fn(q, rq, next); - } elv_rqhash_reposition(q, rq); @@ -482,156 +409,12 @@ void elv_merge_requests(struct request_queue *q, struct request *rq, q->last_merge = rq; } -void elv_bio_merged(struct request_queue *q, struct request *rq, - struct bio *bio) -{ - struct elevator_queue *e = q->elevator; - - if (WARN_ON_ONCE(e->uses_mq)) - return; - - if (e->type->ops.sq.elevator_bio_merged_fn) - e->type->ops.sq.elevator_bio_merged_fn(q, rq, bio); -} - -void elv_requeue_request(struct request_queue *q, struct request *rq) -{ - /* - * it already went through dequeue, we need to decrement the - * in_flight count again - */ - if (blk_account_rq(rq)) { - q->in_flight[rq_is_sync(rq)]--; - if (rq->rq_flags & RQF_SORTED) - elv_deactivate_rq(q, rq); - } - - rq->rq_flags &= ~RQF_STARTED; - - blk_pm_requeue_request(rq); - - __elv_add_request(q, rq, ELEVATOR_INSERT_REQUEUE); -} - -void elv_drain_elevator(struct request_queue *q) -{ - struct elevator_queue *e = q->elevator; - static int printed; - - if (WARN_ON_ONCE(e->uses_mq)) - return; - - lockdep_assert_held(q->queue_lock); - - while (e->type->ops.sq.elevator_dispatch_fn(q, 1)) - ; - if (q->nr_sorted && !blk_queue_is_zoned(q) && printed++ < 10 ) { - printk(KERN_ERR "%s: forced dispatching is broken " - "(nr_sorted=%u), please report this\n", - q->elevator->type->elevator_name, q->nr_sorted); - } -} - -void __elv_add_request(struct request_queue *q, struct request *rq, int where) -{ - trace_block_rq_insert(q, rq); - - blk_pm_add_request(q, rq); - - rq->q = q; - - if (rq->rq_flags & RQF_SOFTBARRIER) { - /* barriers are scheduling boundary, update end_sector */ - if (!blk_rq_is_passthrough(rq)) { - q->end_sector = rq_end_sector(rq); - q->boundary_rq = rq; - } - } else if (!(rq->rq_flags & RQF_ELVPRIV) && - (where == ELEVATOR_INSERT_SORT || - where == ELEVATOR_INSERT_SORT_MERGE)) - where = ELEVATOR_INSERT_BACK; - - switch (where) { - case ELEVATOR_INSERT_REQUEUE: - case ELEVATOR_INSERT_FRONT: - rq->rq_flags |= RQF_SOFTBARRIER; - list_add(&rq->queuelist, &q->queue_head); - break; - - case ELEVATOR_INSERT_BACK: - rq->rq_flags |= RQF_SOFTBARRIER; - elv_drain_elevator(q); - list_add_tail(&rq->queuelist, &q->queue_head); - /* - * We kick the queue here for the following reasons. - * - The elevator might have returned NULL previously - * to delay requests and returned them now. As the - * queue wasn't empty before this request, ll_rw_blk - * won't run the queue on return, resulting in hang. - * - Usually, back inserted requests won't be merged - * with anything. There's no point in delaying queue - * processing. - */ - __blk_run_queue(q); - break; - - case ELEVATOR_INSERT_SORT_MERGE: - /* - * If we succeed in merging this request with one in the - * queue already, we are done - rq has now been freed, - * so no need to do anything further. - */ - if (elv_attempt_insert_merge(q, rq)) - break; - /* fall through */ - case ELEVATOR_INSERT_SORT: - BUG_ON(blk_rq_is_passthrough(rq)); - rq->rq_flags |= RQF_SORTED; - q->nr_sorted++; - if (rq_mergeable(rq)) { - elv_rqhash_add(q, rq); - if (!q->last_merge) - q->last_merge = rq; - } - - /* - * Some ioscheds (cfq) run q->request_fn directly, so - * rq cannot be accessed after calling - * elevator_add_req_fn. - */ - q->elevator->type->ops.sq.elevator_add_req_fn(q, rq); - break; - - case ELEVATOR_INSERT_FLUSH: - rq->rq_flags |= RQF_SOFTBARRIER; - blk_insert_flush(rq); - break; - default: - printk(KERN_ERR "%s: bad insertion point %d\n", - __func__, where); - BUG(); - } -} -EXPORT_SYMBOL(__elv_add_request); - -void elv_add_request(struct request_queue *q, struct request *rq, int where) -{ - unsigned long flags; - - spin_lock_irqsave(q->queue_lock, flags); - __elv_add_request(q, rq, where); - spin_unlock_irqrestore(q->queue_lock, flags); -} -EXPORT_SYMBOL(elv_add_request); - struct request *elv_latter_request(struct request_queue *q, struct request *rq) { struct elevator_queue *e = q->elevator; - if (e->uses_mq && e->type->ops.mq.next_request) + if (e->type->ops.mq.next_request) return e->type->ops.mq.next_request(q, rq); - else if (!e->uses_mq && e->type->ops.sq.elevator_latter_req_fn) - return e->type->ops.sq.elevator_latter_req_fn(q, rq); return NULL; } @@ -640,66 +423,10 @@ struct request *elv_former_request(struct request_queue *q, struct request *rq) { struct elevator_queue *e = q->elevator; - if (e->uses_mq && e->type->ops.mq.former_request) + if (e->type->ops.mq.former_request) return e->type->ops.mq.former_request(q, rq); - if (!e->uses_mq && e->type->ops.sq.elevator_former_req_fn) - return e->type->ops.sq.elevator_former_req_fn(q, rq); - return NULL; -} - -int elv_set_request(struct request_queue *q, struct request *rq, - struct bio *bio, gfp_t gfp_mask) -{ - struct elevator_queue *e = q->elevator; - - if (WARN_ON_ONCE(e->uses_mq)) - return 0; - if (e->type->ops.sq.elevator_set_req_fn) - return e->type->ops.sq.elevator_set_req_fn(q, rq, bio, gfp_mask); - return 0; -} - -void elv_put_request(struct request_queue *q, struct request *rq) -{ - struct elevator_queue *e = q->elevator; - - if (WARN_ON_ONCE(e->uses_mq)) - return; - - if (e->type->ops.sq.elevator_put_req_fn) - e->type->ops.sq.elevator_put_req_fn(rq); -} - -int elv_may_queue(struct request_queue *q, unsigned int op) -{ - struct elevator_queue *e = q->elevator; - - if (WARN_ON_ONCE(e->uses_mq)) - return 0; - - if (e->type->ops.sq.elevator_may_queue_fn) - return e->type->ops.sq.elevator_may_queue_fn(q, op); - - return ELV_MQUEUE_MAY; -} - -void elv_completed_request(struct request_queue *q, struct request *rq) -{ - struct elevator_queue *e = q->elevator; - - if (WARN_ON_ONCE(e->uses_mq)) - return; - - /* - * request is released from the driver, io must be done - */ - if (blk_account_rq(rq)) { - q->in_flight[rq_is_sync(rq)]--; - if ((rq->rq_flags & RQF_SORTED) && - e->type->ops.sq.elevator_completed_req_fn) - e->type->ops.sq.elevator_completed_req_fn(q, rq); - } + return NULL; } #define to_elv(atr) container_of((atr), struct elv_fs_entry, attr) @@ -768,8 +495,6 @@ int elv_register_queue(struct request_queue *q) } kobject_uevent(&e->kobj, KOBJ_ADD); e->registered = 1; - if (!e->uses_mq && e->type->ops.sq.elevator_registered_fn) - e->type->ops.sq.elevator_registered_fn(q); } return error; } @@ -809,7 +534,7 @@ int elv_register(struct elevator_type *e) /* register, don't allow duplicate names */ spin_lock(&elv_list_lock); - if (elevator_find(e->elevator_name, e->uses_mq)) { + if (elevator_find(e->elevator_name)) { spin_unlock(&elv_list_lock); kmem_cache_destroy(e->icq_cache); return -EBUSY; @@ -919,71 +644,17 @@ out_unlock: */ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e) { - struct elevator_queue *old = q->elevator; - bool old_registered = false; int err; lockdep_assert_held(&q->sysfs_lock); - if (q->mq_ops) { - blk_mq_freeze_queue(q); - blk_mq_quiesce_queue(q); - - err = elevator_switch_mq(q, new_e); - - blk_mq_unquiesce_queue(q); - blk_mq_unfreeze_queue(q); - - return err; - } - - /* - * Turn on BYPASS and drain all requests w/ elevator private data. - * Block layer doesn't call into a quiesced elevator - all requests - * are directly put on the dispatch list without elevator data - * using INSERT_BACK. All requests have SOFTBARRIER set and no - * merge happens either. - */ - if (old) { - old_registered = old->registered; - - blk_queue_bypass_start(q); - - /* unregister and clear all auxiliary data of the old elevator */ - if (old_registered) - elv_unregister_queue(q); - - ioc_clear_queue(q); - } - - /* allocate, init and register new elevator */ - err = new_e->ops.sq.elevator_init_fn(q, new_e); - if (err) - goto fail_init; - - err = elv_register_queue(q); - if (err) - goto fail_register; - - /* done, kill the old one and finish */ - if (old) { - elevator_exit(q, old); - blk_queue_bypass_end(q); - } - - blk_add_trace_msg(q, "elv switch: %s", new_e->elevator_name); + blk_mq_freeze_queue(q); + blk_mq_quiesce_queue(q); - return 0; + err = elevator_switch_mq(q, new_e); -fail_register: - elevator_exit(q, q->elevator); -fail_init: - /* switch failed, restore and re-register old elevator */ - if (old) { - q->elevator = old; - elv_register_queue(q); - blk_queue_bypass_end(q); - } + blk_mq_unquiesce_queue(q); + blk_mq_unfreeze_queue(q); return err; } @@ -1032,7 +703,7 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name, { int ret; - if (!(q->mq_ops || q->request_fn) || !elv_support_iosched(q)) + if (!q->mq_ops || !elv_support_iosched(q)) return count; ret = __elevator_change(q, name); @@ -1047,7 +718,6 @@ ssize_t elv_iosched_show(struct request_queue *q, char *name) struct elevator_queue *e = q->elevator; struct elevator_type *elv = NULL; struct elevator_type *__e; - bool uses_mq = q->mq_ops != NULL; int len = 0; if (!queue_is_rq_based(q)) @@ -1060,14 +730,11 @@ ssize_t elv_iosched_show(struct request_queue *q, char *name) spin_lock(&elv_list_lock); list_for_each_entry(__e, &elv_list, list) { - if (elv && elevator_match(elv, __e->elevator_name) && - (__e->uses_mq == uses_mq)) { + if (elv && elevator_match(elv, __e->elevator_name)) { len += sprintf(name+len, "[%s] ", elv->elevator_name); continue; } - if (__e->uses_mq && q->mq_ops && elv_support_iosched(q)) - len += sprintf(name+len, "%s ", __e->elevator_name); - else if (!__e->uses_mq && !q->mq_ops) + if (elv_support_iosched(q)) len += sprintf(name+len, "%s ", __e->elevator_name); } spin_unlock(&elv_list_lock); diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index eccac01a10b6..728757a34fa0 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -1032,7 +1032,6 @@ static struct elevator_type kyber_sched = { .dispatch_request = kyber_dispatch_request, .has_work = kyber_has_work, }, - .uses_mq = true, #ifdef CONFIG_BLK_DEBUG_FS .queue_debugfs_attrs = kyber_queue_debugfs_attrs, .hctx_debugfs_attrs = kyber_hctx_debugfs_attrs, diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 099a9e05854c..513edefd10fd 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -777,7 +777,6 @@ static struct elevator_type mq_deadline = { .exit_sched = dd_exit_queue, }, - .uses_mq = true, #ifdef CONFIG_BLK_DEBUG_FS .queue_debugfs_attrs = deadline_queue_debugfs_attrs, #endif diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8afe3331777e..a9f6db8abcda 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -58,9 +58,6 @@ struct blk_stat_callback; typedef void (rq_end_io_fn)(struct request *, blk_status_t); -#define BLK_RL_SYNCFULL (1U << 0) -#define BLK_RL_ASYNCFULL (1U << 1) - struct request_list { struct request_queue *q; /* the queue this rl belongs to */ #ifdef CONFIG_BLK_CGROUP @@ -309,11 +306,8 @@ static inline unsigned short req_get_ioprio(struct request *req) struct blk_queue_ctx; -typedef void (request_fn_proc) (struct request_queue *q); typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); typedef bool (poll_q_fn) (struct request_queue *q, blk_qc_t); -typedef int (prep_rq_fn) (struct request_queue *, struct request *); -typedef void (unprep_rq_fn) (struct request_queue *, struct request *); struct bio_vec; typedef void (softirq_done_fn)(struct request *); @@ -432,8 +426,6 @@ struct request_queue { struct list_head queue_head; struct request *last_merge; struct elevator_queue *elevator; - int nr_rqs[2]; /* # allocated [a]sync rqs */ - int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ struct blk_queue_stats *stats; struct rq_qos *rq_qos; @@ -446,11 +438,8 @@ struct request_queue { */ struct request_list root_rl; - request_fn_proc *request_fn; make_request_fn *make_request_fn; poll_q_fn *poll_fn; - prep_rq_fn *prep_rq_fn; - unprep_rq_fn *unprep_rq_fn; softirq_done_fn *softirq_done_fn; rq_timed_out_fn *rq_timed_out_fn; dma_drain_needed_fn *dma_drain_needed; @@ -458,8 +447,6 @@ struct request_queue { init_rq_fn *init_rq_fn; /* Called just before a request is freed */ exit_rq_fn *exit_rq_fn; - /* Called from inside blk_get_request() */ - void (*initialize_rq_fn)(struct request *rq); const struct blk_mq_ops *mq_ops; @@ -475,17 +462,6 @@ struct request_queue { struct blk_mq_hw_ctx **queue_hw_ctx; unsigned int nr_hw_queues; - /* - * Dispatch queue sorting - */ - sector_t end_sector; - struct request *boundary_rq; - - /* - * Delayed queue handling - */ - struct delayed_work delay_work; - struct backing_dev_info *backing_dev_info; /* @@ -548,9 +524,6 @@ struct request_queue { * queue settings */ unsigned long nr_requests; /* Max # of requests */ - unsigned int nr_congestion_on; - unsigned int nr_congestion_off; - unsigned int nr_batching; unsigned int dma_drain_size; void *dma_drain_buffer; @@ -560,13 +533,6 @@ struct request_queue { unsigned int nr_sorted; unsigned int in_flight[2]; - /* - * Number of active block driver functions for which blk_drain_queue() - * must wait. Must be incremented around functions that unlock the - * queue_lock internally, e.g. scsi_request_fn(). - */ - unsigned int request_fn_active; - unsigned int rq_timeout; int poll_nsec; @@ -740,11 +706,6 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); -static inline int queue_in_flight(struct request_queue *q) -{ - return q->in_flight[0] + q->in_flight[1]; -} - static inline bool blk_account_rq(struct request *rq) { return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); @@ -765,7 +726,7 @@ static inline bool blk_account_rq(struct request *rq) */ static inline bool queue_is_rq_based(struct request_queue *q) { - return q->request_fn || q->mq_ops; + return q->mq_ops; } static inline unsigned int blk_queue_cluster(struct request_queue *q) @@ -828,27 +789,6 @@ static inline bool rq_is_sync(struct request *rq) return op_is_sync(rq->cmd_flags); } -static inline bool blk_rl_full(struct request_list *rl, bool sync) -{ - unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; - - return rl->flags & flag; -} - -static inline void blk_set_rl_full(struct request_list *rl, bool sync) -{ - unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; - - rl->flags |= flag; -} - -static inline void blk_clear_rl_full(struct request_list *rl, bool sync) -{ - unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; - - rl->flags &= ~flag; -} - static inline bool rq_mergeable(struct request *rq) { if (blk_rq_is_passthrough(rq)) @@ -969,7 +909,6 @@ extern void blk_put_request(struct request *); extern void __blk_put_request(struct request_queue *, struct request *); extern struct request *blk_get_request(struct request_queue *, unsigned int op, blk_mq_req_flags_t flags); -extern void blk_requeue_request(struct request_queue *, struct request *); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, @@ -979,7 +918,6 @@ extern void blk_rq_unprep_clone(struct request *rq); extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); extern int blk_rq_append_bio(struct request *rq, struct bio **bio); -extern void blk_delay_queue(struct request_queue *, unsigned long); extern void blk_queue_split(struct request_queue *, struct bio **); extern void blk_recount_segments(struct request_queue *, struct bio *); extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); @@ -992,15 +930,7 @@ extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags); extern void blk_queue_exit(struct request_queue *q); -extern void blk_start_queue(struct request_queue *q); -extern void blk_start_queue_async(struct request_queue *q); -extern void blk_stop_queue(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); -extern void __blk_stop_queue(struct request_queue *q); -extern void __blk_run_queue(struct request_queue *q); -extern void __blk_run_queue_uncond(struct request_queue *q); -extern void blk_run_queue(struct request_queue *); -extern void blk_run_queue_async(struct request_queue *q); extern int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); @@ -1155,13 +1085,6 @@ static inline unsigned int blk_rq_count_bios(struct request *rq) return nr_bios; } -/* - * Request issue related functions. - */ -extern struct request *blk_peek_request(struct request_queue *q); -extern void blk_start_request(struct request *rq); -extern struct request *blk_fetch_request(struct request_queue *q); - void blk_steal_bios(struct bio_list *list, struct request *rq); /* @@ -1179,9 +1102,6 @@ void blk_steal_bios(struct bio_list *list, struct request *rq); */ extern bool blk_update_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); -extern void blk_finish_request(struct request *rq, blk_status_t error); -extern bool blk_end_request(struct request *rq, blk_status_t error, - unsigned int nr_bytes); extern void blk_end_request_all(struct request *rq, blk_status_t error); extern bool __blk_end_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); @@ -1190,15 +1110,10 @@ extern bool __blk_end_request_cur(struct request *rq, blk_status_t error); extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); -extern void blk_unprep_request(struct request *); /* * Access functions for manipulating queue properties */ -extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn, - spinlock_t *lock, int node_id); -extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *); -extern int blk_init_allocated_queue(struct request_queue *); extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); @@ -1239,8 +1154,6 @@ extern int blk_queue_dma_drain(struct request_queue *q, void *buf, unsigned int size); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); -extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn); -extern void blk_queue_unprep_rq(struct request_queue *, unprep_rq_fn *ufn); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); @@ -1298,7 +1211,6 @@ extern void blk_set_queue_dying(struct request_queue *); * schedule() where blk_schedule_flush_plug() is called. */ struct blk_plug { - struct list_head list; /* requests */ struct list_head mq_list; /* blk-mq requests */ struct list_head cb_list; /* md requires an unplug callback */ }; @@ -1339,8 +1251,7 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) struct blk_plug *plug = tsk->plug; return plug && - (!list_empty(&plug->list) || - !list_empty(&plug->mq_list) || + (!list_empty(&plug->mq_list) || !list_empty(&plug->cb_list)); } diff --git a/include/linux/elevator.h b/include/linux/elevator.h index 015bb59c0331..158004f1754d 100644 --- a/include/linux/elevator.h +++ b/include/linux/elevator.h @@ -23,74 +23,6 @@ enum elv_merge { ELEVATOR_DISCARD_MERGE = 3, }; -typedef enum elv_merge (elevator_merge_fn) (struct request_queue *, struct request **, - struct bio *); - -typedef void (elevator_merge_req_fn) (struct request_queue *, struct request *, struct request *); - -typedef void (elevator_merged_fn) (struct request_queue *, struct request *, enum elv_merge); - -typedef int (elevator_allow_bio_merge_fn) (struct request_queue *, - struct request *, struct bio *); - -typedef int (elevator_allow_rq_merge_fn) (struct request_queue *, - struct request *, struct request *); - -typedef void (elevator_bio_merged_fn) (struct request_queue *, - struct request *, struct bio *); - -typedef int (elevator_dispatch_fn) (struct request_queue *, int); - -typedef void (elevator_add_req_fn) (struct request_queue *, struct request *); -typedef struct request *(elevator_request_list_fn) (struct request_queue *, struct request *); -typedef void (elevator_completed_req_fn) (struct request_queue *, struct request *); -typedef int (elevator_may_queue_fn) (struct request_queue *, unsigned int); - -typedef void (elevator_init_icq_fn) (struct io_cq *); -typedef void (elevator_exit_icq_fn) (struct io_cq *); -typedef int (elevator_set_req_fn) (struct request_queue *, struct request *, - struct bio *, gfp_t); -typedef void (elevator_put_req_fn) (struct request *); -typedef void (elevator_activate_req_fn) (struct request_queue *, struct request *); -typedef void (elevator_deactivate_req_fn) (struct request_queue *, struct request *); - -typedef int (elevator_init_fn) (struct request_queue *, - struct elevator_type *e); -typedef void (elevator_exit_fn) (struct elevator_queue *); -typedef void (elevator_registered_fn) (struct request_queue *); - -struct elevator_ops -{ - elevator_merge_fn *elevator_merge_fn; - elevator_merged_fn *elevator_merged_fn; - elevator_merge_req_fn *elevator_merge_req_fn; - elevator_allow_bio_merge_fn *elevator_allow_bio_merge_fn; - elevator_allow_rq_merge_fn *elevator_allow_rq_merge_fn; - elevator_bio_merged_fn *elevator_bio_merged_fn; - - elevator_dispatch_fn *elevator_dispatch_fn; - elevator_add_req_fn *elevator_add_req_fn; - elevator_activate_req_fn *elevator_activate_req_fn; - elevator_deactivate_req_fn *elevator_deactivate_req_fn; - - elevator_completed_req_fn *elevator_completed_req_fn; - - elevator_request_list_fn *elevator_former_req_fn; - elevator_request_list_fn *elevator_latter_req_fn; - - elevator_init_icq_fn *elevator_init_icq_fn; /* see iocontext.h */ - elevator_exit_icq_fn *elevator_exit_icq_fn; /* ditto */ - - elevator_set_req_fn *elevator_set_req_fn; - elevator_put_req_fn *elevator_put_req_fn; - - elevator_may_queue_fn *elevator_may_queue_fn; - - elevator_init_fn *elevator_init_fn; - elevator_exit_fn *elevator_exit_fn; - elevator_registered_fn *elevator_registered_fn; -}; - struct blk_mq_alloc_data; struct blk_mq_hw_ctx; @@ -138,16 +70,15 @@ struct elevator_type /* fields provided by elevator implementation */ union { - struct elevator_ops sq; struct elevator_mq_ops mq; } ops; + size_t icq_size; /* see iocontext.h */ size_t icq_align; /* ditto */ struct elv_fs_entry *elevator_attrs; char elevator_name[ELV_NAME_MAX]; const char *elevator_alias; struct module *elevator_owner; - bool uses_mq; #ifdef CONFIG_BLK_DEBUG_FS const struct blk_mq_debugfs_attr *queue_debugfs_attrs; const struct blk_mq_debugfs_attr *hctx_debugfs_attrs; @@ -175,40 +106,25 @@ struct elevator_queue struct kobject kobj; struct mutex sysfs_lock; unsigned int registered:1; - unsigned int uses_mq:1; DECLARE_HASHTABLE(hash, ELV_HASH_BITS); }; /* * block elevator interface */ -extern void elv_dispatch_sort(struct request_queue *, struct request *); -extern void elv_dispatch_add_tail(struct request_queue *, struct request *); -extern void elv_add_request(struct request_queue *, struct request *, int); -extern void __elv_add_request(struct request_queue *, struct request *, int); extern enum elv_merge elv_merge(struct request_queue *, struct request **, struct bio *); extern void elv_merge_requests(struct request_queue *, struct request *, struct request *); extern void elv_merged_request(struct request_queue *, struct request *, enum elv_merge); -extern void elv_bio_merged(struct request_queue *q, struct request *, - struct bio *); extern bool elv_attempt_insert_merge(struct request_queue *, struct request *); -extern void elv_requeue_request(struct request_queue *, struct request *); extern struct request *elv_former_request(struct request_queue *, struct request *); extern struct request *elv_latter_request(struct request_queue *, struct request *); -extern int elv_may_queue(struct request_queue *, unsigned int); -extern void elv_completed_request(struct request_queue *, struct request *); -extern int elv_set_request(struct request_queue *q, struct request *rq, - struct bio *bio, gfp_t gfp_mask); -extern void elv_put_request(struct request_queue *, struct request *); -extern void elv_drain_elevator(struct request_queue *); /* * io scheduler registration */ -extern void __init load_default_elevator_module(void); extern int elv_register(struct elevator_type *); extern void elv_unregister(struct elevator_type *); @@ -260,9 +176,5 @@ enum { #define rq_entry_fifo(ptr) list_entry((ptr), struct request, queuelist) #define rq_fifo_clear(rq) list_del_init(&(rq)->queuelist) -#else /* CONFIG_BLOCK */ - -static inline void load_default_elevator_module(void) { } - #endif /* CONFIG_BLOCK */ #endif diff --git a/include/linux/init.h b/include/linux/init.h index 9c2aba1dbabf..5255069f5a9f 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -146,7 +146,6 @@ extern unsigned int reset_devices; /* used by init/main.c */ void setup_arch(char **); void prepare_namespace(void); -void __init load_default_modules(void); int __init init_rootfs(void); #if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_STRICT_MODULE_RWX) diff --git a/init/do_mounts_initrd.c b/init/do_mounts_initrd.c index d1a5d885ce13..73e02ea5d5d1 100644 --- a/init/do_mounts_initrd.c +++ b/init/do_mounts_initrd.c @@ -53,9 +53,6 @@ static void __init handle_initrd(void) ksys_mkdir("/old", 0700); ksys_chdir("/old"); - /* try loading default modules from initrd */ - load_default_modules(); - /* * In case that a resume from disk is carried out by linuxrc or one of * its children, we need to tell the freezer not to wait for us. diff --git a/init/initramfs.c b/init/initramfs.c index 640557788026..96af18fec4d0 100644 --- a/init/initramfs.c +++ b/init/initramfs.c @@ -644,12 +644,6 @@ static int __init populate_rootfs(void) #endif } flush_delayed_fput(); - /* - * Try loading default modules from initramfs. This gives - * us a chance to load before device_initcalls. - */ - load_default_modules(); - return 0; } rootfs_initcall(populate_rootfs); diff --git a/init/main.c b/init/main.c index ee147103ba1b..ca0cdb0c388b 100644 --- a/init/main.c +++ b/init/main.c @@ -996,17 +996,6 @@ static void __init do_pre_smp_initcalls(void) do_one_initcall(initcall_from_entry(fn)); } -/* - * This function requests modules which should be loaded by default and is - * called twice right after initrd is mounted and right before init is - * exec'd. If such modules are on either initrd or rootfs, they will be - * loaded before control is passed to userland. - */ -void __init load_default_modules(void) -{ - load_default_elevator_module(); -} - static int run_init_process(const char *init_filename) { argv_init[0] = init_filename; @@ -1180,5 +1169,4 @@ static noinline void __init kernel_init_freeable(void) */ integrity_load_keys(); - load_default_modules(); } -- cgit v1.2.3-71-gd317 From 92bc5a24844ada9b010f03c49a493e3edeadaa54 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 24 Oct 2018 13:52:28 -0600 Subject: block: remove __blk_put_request() Now there's no difference between blk_put_request() and __blk_put_request() anymore, get rid of the underscore version and convert the few callers. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-core.c | 9 --------- block/blk-merge.c | 2 +- drivers/scsi/osd/osd_initiator.c | 4 ++-- drivers/scsi/osst.c | 2 +- drivers/scsi/scsi_error.c | 2 +- drivers/scsi/sg.c | 2 +- drivers/scsi/st.c | 2 +- drivers/target/target_core_pscsi.c | 2 +- include/linux/blkdev.h | 1 - 9 files changed, 8 insertions(+), 18 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 18538a41a532..700dd4587282 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -803,15 +803,6 @@ void part_round_stats(struct request_queue *q, int cpu, struct hd_struct *part) } EXPORT_SYMBOL_GPL(part_round_stats); -void __blk_put_request(struct request_queue *q, struct request *req) -{ - if (unlikely(!q)) - return; - - blk_mq_free_request(req); -} -EXPORT_SYMBOL_GPL(__blk_put_request); - void blk_put_request(struct request *req) { blk_mq_free_request(req); diff --git a/block/blk-merge.c b/block/blk-merge.c index c068c30b0c35..3d073305da33 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -866,7 +866,7 @@ int blk_attempt_req_merge(struct request_queue *q, struct request *rq, free = attempt_merge(q, rq, next); if (free) { - __blk_put_request(q, free); + blk_put_request(free); return 1; } diff --git a/drivers/scsi/osd/osd_initiator.c b/drivers/scsi/osd/osd_initiator.c index e19fa883376f..60cf7c5eb880 100644 --- a/drivers/scsi/osd/osd_initiator.c +++ b/drivers/scsi/osd/osd_initiator.c @@ -506,11 +506,11 @@ static void osd_request_async_done(struct request *req, blk_status_t error) _set_error_resid(or, req, error); if (req->next_rq) { - __blk_put_request(req->q, req->next_rq); + blk_put_request(req->next_rq); req->next_rq = NULL; } - __blk_put_request(req->q, req); + blk_put_request(req); or->request = NULL; or->in.req = NULL; or->out.req = NULL; diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c index 7a1a1edde35d..664c1238a87f 100644 --- a/drivers/scsi/osst.c +++ b/drivers/scsi/osst.c @@ -341,7 +341,7 @@ static void osst_end_async(struct request *req, blk_status_t status) blk_rq_unmap_user(SRpnt->bio); } - __blk_put_request(req->q, req); + blk_put_request(req); } /* osst_request memory management */ diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c index fff128aa9ec2..dd338a8cd275 100644 --- a/drivers/scsi/scsi_error.c +++ b/drivers/scsi/scsi_error.c @@ -1932,7 +1932,7 @@ maybe_retry: static void eh_lock_door_done(struct request *req, blk_status_t status) { - __blk_put_request(req->q, req); + blk_put_request(req); } /** diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c index c6ad00703c5b..4e27460ec926 100644 --- a/drivers/scsi/sg.c +++ b/drivers/scsi/sg.c @@ -1390,7 +1390,7 @@ sg_rq_end_io(struct request *rq, blk_status_t status) */ srp->rq = NULL; scsi_req_free_cmd(scsi_req(rq)); - __blk_put_request(rq->q, rq); + blk_put_request(rq); write_lock_irqsave(&sfp->rq_list_lock, iflags); if (unlikely(srp->orphan)) { diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index 307df2fa39a3..7ff22d3f03e3 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -530,7 +530,7 @@ static void st_scsi_execute_end(struct request *req, blk_status_t status) complete(SRpnt->waiting); blk_rq_unmap_user(tmp); - __blk_put_request(req->q, req); + blk_put_request(req); } static int st_scsi_execute(struct st_request *SRpnt, const unsigned char *cmd, diff --git a/drivers/target/target_core_pscsi.c b/drivers/target/target_core_pscsi.c index 47d76c862014..c062d363dce3 100644 --- a/drivers/target/target_core_pscsi.c +++ b/drivers/target/target_core_pscsi.c @@ -1094,7 +1094,7 @@ static void pscsi_req_done(struct request *req, blk_status_t status) break; } - __blk_put_request(req->q, req); + blk_put_request(req); kfree(pt); } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index a9f6db8abcda..c502a7f40e84 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -906,7 +906,6 @@ extern blk_qc_t direct_make_request(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_init_request_from_bio(struct request *req, struct bio *bio); extern void blk_put_request(struct request *); -extern void __blk_put_request(struct request_queue *, struct request *); extern struct request *blk_get_request(struct request_queue *, unsigned int op, blk_mq_req_flags_t flags); extern int blk_lld_busy(struct request_queue *q); -- cgit v1.2.3-71-gd317 From 4316b79e4321d4140164e42f228778e5bc66c84f Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 29 Oct 2018 10:25:07 -0600 Subject: block: kill legacy parts of timeout handling The only user of legacy timing now is BSG, which is invoked from the mq timeout handler. Kill the legacy code, and rename the q->rq_timed_out_fn to q->bsg_job_timeout_fn. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-core.c | 1 - block/blk-settings.c | 7 ---- block/blk-timeout.c | 99 ++++---------------------------------------------- block/blk.h | 1 - block/bsg-lib.c | 6 +-- include/linux/blkdev.h | 4 +- 6 files changed, 11 insertions(+), 107 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 700dd4587282..ccfe2a65cc22 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -656,7 +656,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, laptop_mode_timer_fn, 0); timer_setup(&q->timeout, blk_rq_timed_out_timer, 0); INIT_WORK(&q->timeout_work, NULL); - INIT_LIST_HEAD(&q->timeout_list); INIT_LIST_HEAD(&q->icq_list); #ifdef CONFIG_BLK_CGROUP INIT_LIST_HEAD(&q->blkg_list); diff --git a/block/blk-settings.c b/block/blk-settings.c index 39c3c301a687..e3f07d94b18d 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -32,13 +32,6 @@ void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout) } EXPORT_SYMBOL_GPL(blk_queue_rq_timeout); -void blk_queue_rq_timed_out(struct request_queue *q, rq_timed_out_fn *fn) -{ - WARN_ON_ONCE(q->mq_ops); - q->rq_timed_out_fn = fn; -} -EXPORT_SYMBOL_GPL(blk_queue_rq_timed_out); - /** * blk_set_default_limits - reset limits to default values * @lim: the queue_limits structure to reset diff --git a/block/blk-timeout.c b/block/blk-timeout.c index f2cfd56e1606..6428d458072a 100644 --- a/block/blk-timeout.c +++ b/block/blk-timeout.c @@ -78,70 +78,6 @@ void blk_delete_timer(struct request *req) list_del_init(&req->timeout_list); } -static void blk_rq_timed_out(struct request *req) -{ - struct request_queue *q = req->q; - enum blk_eh_timer_return ret = BLK_EH_RESET_TIMER; - - if (q->rq_timed_out_fn) - ret = q->rq_timed_out_fn(req); - switch (ret) { - case BLK_EH_RESET_TIMER: - blk_add_timer(req); - blk_clear_rq_complete(req); - break; - case BLK_EH_DONE: - /* - * LLD handles this for now but in the future - * we can send a request msg to abort the command - * and we can move more of the generic scsi eh code to - * the blk layer. - */ - break; - default: - printk(KERN_ERR "block: bad eh return: %d\n", ret); - break; - } -} - -static void blk_rq_check_expired(struct request *rq, unsigned long *next_timeout, - unsigned int *next_set) -{ - const unsigned long deadline = blk_rq_deadline(rq); - - if (time_after_eq(jiffies, deadline)) { - list_del_init(&rq->timeout_list); - - /* - * Check if we raced with end io completion - */ - if (!blk_mark_rq_complete(rq)) - blk_rq_timed_out(rq); - } else if (!*next_set || time_after(*next_timeout, deadline)) { - *next_timeout = deadline; - *next_set = 1; - } -} - -void blk_timeout_work(struct work_struct *work) -{ - struct request_queue *q = - container_of(work, struct request_queue, timeout_work); - unsigned long flags, next = 0; - struct request *rq, *tmp; - int next_set = 0; - - spin_lock_irqsave(q->queue_lock, flags); - - list_for_each_entry_safe(rq, tmp, &q->timeout_list, timeout_list) - blk_rq_check_expired(rq, &next, &next_set); - - if (next_set) - mod_timer(&q->timeout, round_jiffies_up(next)); - - spin_unlock_irqrestore(q->queue_lock, flags); -} - /** * blk_abort_request -- Request request recovery for the specified command * @req: pointer to the request of interest @@ -153,20 +89,13 @@ void blk_timeout_work(struct work_struct *work) */ void blk_abort_request(struct request *req) { - if (req->q->mq_ops) { - /* - * All we need to ensure is that timeout scan takes place - * immediately and that scan sees the new timeout value. - * No need for fancy synchronizations. - */ - blk_rq_set_deadline(req, jiffies); - kblockd_schedule_work(&req->q->timeout_work); - } else { - if (blk_mark_rq_complete(req)) - return; - blk_delete_timer(req); - blk_rq_timed_out(req); - } + /* + * All we need to ensure is that timeout scan takes place + * immediately and that scan sees the new timeout value. + * No need for fancy synchronizations. + */ + blk_rq_set_deadline(req, jiffies); + kblockd_schedule_work(&req->q->timeout_work); } EXPORT_SYMBOL_GPL(blk_abort_request); @@ -194,13 +123,6 @@ void blk_add_timer(struct request *req) struct request_queue *q = req->q; unsigned long expiry; - if (!q->mq_ops) - lockdep_assert_held(q->queue_lock); - - /* blk-mq has its own handler, so we don't need ->rq_timed_out_fn */ - if (!q->mq_ops && !q->rq_timed_out_fn) - return; - BUG_ON(!list_empty(&req->timeout_list)); /* @@ -213,13 +135,6 @@ void blk_add_timer(struct request *req) req->rq_flags &= ~RQF_TIMED_OUT; blk_rq_set_deadline(req, jiffies + req->timeout); - /* - * Only the non-mq case needs to add the request to a protected list. - * For the mq case we simply scan the tag map. - */ - if (!q->mq_ops) - list_add_tail(&req->timeout_list, &req->q->timeout_list); - /* * If the timer isn't already pending or this timeout is earlier * than an existing one, modify the timer. Round up to next nearest diff --git a/block/blk.h b/block/blk.h index e2604ae7ddfa..4ae6cacb4548 100644 --- a/block/blk.h +++ b/block/blk.h @@ -224,7 +224,6 @@ static inline bool bio_integrity_endio(struct bio *bio) } #endif /* CONFIG_BLK_DEV_INTEGRITY */ -void blk_timeout_work(struct work_struct *work); unsigned long blk_rq_timeout(unsigned long timeout); void blk_add_timer(struct request *req); void blk_delete_timer(struct request *); diff --git a/block/bsg-lib.c b/block/bsg-lib.c index faf20f4500c9..f38c7bc272c0 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -307,8 +307,8 @@ static enum blk_eh_timer_return bsg_timeout(struct request *rq, bool reserved) enum blk_eh_timer_return ret = BLK_EH_DONE; struct request_queue *q = rq->q; - if (q->rq_timed_out_fn) - ret = q->rq_timed_out_fn(rq); + if (q->bsg_job_timeout_fn) + ret = q->bsg_job_timeout_fn(rq); return ret; } @@ -357,9 +357,9 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name, q->queuedata = dev; q->bsg_job_fn = job_fn; + q->bsg_job_timeout_fn = timeout; blk_queue_flag_set(QUEUE_FLAG_BIDI, q); blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT); - q->rq_timed_out_fn = timeout; ret = bsg_register_queue(q, dev, name, &bsg_transport_ops); if (ret) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c502a7f40e84..0364fc53f5c8 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -441,7 +441,6 @@ struct request_queue { make_request_fn *make_request_fn; poll_q_fn *poll_fn; softirq_done_fn *softirq_done_fn; - rq_timed_out_fn *rq_timed_out_fn; dma_drain_needed_fn *dma_drain_needed; /* Called just after a request is allocated */ init_rq_fn *init_rq_fn; @@ -541,7 +540,6 @@ struct request_queue { struct timer_list timeout; struct work_struct timeout_work; - struct list_head timeout_list; struct list_head icq_list; #ifdef CONFIG_BLK_CGROUP @@ -601,6 +599,7 @@ struct request_queue { #if defined(CONFIG_BLK_DEV_BSG) bsg_job_fn *bsg_job_fn; + rq_timed_out_fn *bsg_job_timeout_fn; struct bsg_class_device bsg_dev; #endif @@ -1156,7 +1155,6 @@ extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); -extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); -- cgit v1.2.3-71-gd317 From 1028e4b335665290dc563d5272f3c6b84e7fd66e Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 29 Oct 2018 09:47:17 -0600 Subject: bsg: move bsg-lib parts outside of request queue Get rid of the special bsg job fn and timeout handler, move them into a private bsg_set instead. Mostly from Christoph, with fixes for error handling and cleanups. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/bsg-lib.c | 43 +++++++++++++++++++++++++++---------------- include/linux/blkdev.h | 5 ----- include/linux/bsg-lib.h | 5 ++++- 3 files changed, 31 insertions(+), 22 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/bsg-lib.c b/block/bsg-lib.c index f38c7bc272c0..192129856342 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -31,6 +31,12 @@ #define uptr64(val) ((void __user *)(uintptr_t)(val)) +struct bsg_set { + struct blk_mq_tag_set tag_set; + bsg_job_fn *job_fn; + bsg_timeout_fn *timeout_fn; +}; + static int bsg_transport_check_proto(struct sg_io_v4 *hdr) { if (hdr->protocol != BSG_PROTOCOL_SCSI || @@ -239,6 +245,8 @@ static blk_status_t bsg_queue_rq(struct blk_mq_hw_ctx *hctx, struct request_queue *q = hctx->queue; struct device *dev = q->queuedata; struct request *req = bd->rq; + struct bsg_set *bset = + container_of(q->tag_set, struct bsg_set, tag_set); int ret; blk_mq_start_request(req); @@ -249,7 +257,7 @@ static blk_status_t bsg_queue_rq(struct blk_mq_hw_ctx *hctx, if (!bsg_prepare_job(dev, req)) return BLK_STS_IOERR; - ret = q->bsg_job_fn(blk_mq_rq_to_pdu(req)); + ret = bset->job_fn(blk_mq_rq_to_pdu(req)); if (ret) return BLK_STS_IOERR; @@ -292,25 +300,25 @@ static void bsg_exit_rq(struct blk_mq_tag_set *set, struct request *req, void bsg_remove_queue(struct request_queue *q) { if (q) { - struct blk_mq_tag_set *set = q->tag_set; + struct bsg_set *bset = + container_of(q->tag_set, struct bsg_set, tag_set); bsg_unregister_queue(q); blk_cleanup_queue(q); - blk_mq_free_tag_set(set); - kfree(set); + blk_mq_free_tag_set(&bset->tag_set); + kfree(bset); } } EXPORT_SYMBOL_GPL(bsg_remove_queue); static enum blk_eh_timer_return bsg_timeout(struct request *rq, bool reserved) { - enum blk_eh_timer_return ret = BLK_EH_DONE; - struct request_queue *q = rq->q; - - if (q->bsg_job_timeout_fn) - ret = q->bsg_job_timeout_fn(rq); + struct bsg_set *bset = + container_of(rq->q->tag_set, struct bsg_set, tag_set); - return ret; + if (!bset->timeout_fn) + return BLK_EH_DONE; + return bset->timeout_fn(rq); } static const struct blk_mq_ops bsg_mq_ops = { @@ -330,16 +338,21 @@ static const struct blk_mq_ops bsg_mq_ops = { * @dd_job_size: size of LLD data needed for each job */ struct request_queue *bsg_setup_queue(struct device *dev, const char *name, - bsg_job_fn *job_fn, rq_timed_out_fn *timeout, int dd_job_size) + bsg_job_fn *job_fn, bsg_timeout_fn *timeout, int dd_job_size) { + struct bsg_set *bset; struct blk_mq_tag_set *set; struct request_queue *q; int ret = -ENOMEM; - set = kzalloc(sizeof(*set), GFP_KERNEL); - if (!set) + bset = kzalloc(sizeof(*bset), GFP_KERNEL); + if (!bset) return ERR_PTR(-ENOMEM); + bset->job_fn = job_fn; + bset->timeout_fn = timeout; + + set = &bset->tag_set; set->ops = &bsg_mq_ops, set->nr_hw_queues = 1; set->queue_depth = 128; @@ -356,8 +369,6 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name, } q->queuedata = dev; - q->bsg_job_fn = job_fn; - q->bsg_job_timeout_fn = timeout; blk_queue_flag_set(QUEUE_FLAG_BIDI, q); blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT); @@ -374,7 +385,7 @@ out_cleanup_queue: out_queue: blk_mq_free_tag_set(set); out_tag_set: - kfree(set); + kfree(bset); return ERR_PTR(ret); } EXPORT_SYMBOL_GPL(bsg_setup_queue); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0364fc53f5c8..877a3d235c45 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -312,7 +312,6 @@ typedef bool (poll_q_fn) (struct request_queue *q, blk_qc_t); struct bio_vec; typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); -typedef int (bsg_job_fn) (struct bsg_job *); typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t); typedef void (exit_rq_fn)(struct request_queue *, struct request *); @@ -321,8 +320,6 @@ enum blk_eh_timer_return { BLK_EH_RESET_TIMER, /* reset timer and try again */ }; -typedef enum blk_eh_timer_return (rq_timed_out_fn)(struct request *); - enum blk_queue_state { Queue_down, Queue_up, @@ -598,8 +595,6 @@ struct request_queue { atomic_t mq_freeze_depth; #if defined(CONFIG_BLK_DEV_BSG) - bsg_job_fn *bsg_job_fn; - rq_timed_out_fn *bsg_job_timeout_fn; struct bsg_class_device bsg_dev; #endif diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h index 9c9b134b1fa5..b356e0006731 100644 --- a/include/linux/bsg-lib.h +++ b/include/linux/bsg-lib.h @@ -31,6 +31,9 @@ struct device; struct scatterlist; struct request_queue; +typedef int (bsg_job_fn) (struct bsg_job *); +typedef enum blk_eh_timer_return (bsg_timeout_fn)(struct request *); + struct bsg_buffer { unsigned int payload_len; int sg_cnt; @@ -72,7 +75,7 @@ struct bsg_job { void bsg_job_done(struct bsg_job *job, int result, unsigned int reply_payload_rcv_len); struct request_queue *bsg_setup_queue(struct device *dev, const char *name, - bsg_job_fn *job_fn, rq_timed_out_fn *timeout, int dd_job_size); + bsg_job_fn *job_fn, bsg_timeout_fn *timeout, int dd_job_size); void bsg_remove_queue(struct request_queue *q); void bsg_job_put(struct bsg_job *job); int __must_check bsg_job_get(struct bsg_job *job); -- cgit v1.2.3-71-gd317 From db6d995235606191fa9db0c717e9d843200b71ea Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 2 Nov 2018 08:46:15 -0600 Subject: block: remove request_list code It's now dead code, nobody uses it. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 47 ---------------------- block/blk-core.c | 75 ----------------------------------- block/blk-mq.c | 4 -- block/blk.h | 3 -- include/linux/blk-cgroup.h | 97 ---------------------------------------------- include/linux/blkdev.h | 34 ---------------- 6 files changed, 260 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 41b2470042d1..6c65791bc3fe 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -76,9 +76,6 @@ static void blkg_free(struct blkcg_gq *blkg) if (blkg->pd[i]) blkcg_policy[i]->pd_free_fn(blkg->pd[i]); - if (blkg->blkcg != &blkcg_root) - blk_exit_rl(blkg->q, &blkg->rl); - blkg_rwstat_exit(&blkg->stat_ios); blkg_rwstat_exit(&blkg->stat_bytes); kfree(blkg); @@ -112,13 +109,6 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, blkg->blkcg = blkcg; atomic_set(&blkg->refcnt, 1); - /* root blkg uses @q->root_rl, init rl only for !root blkgs */ - if (blkcg != &blkcg_root) { - if (blk_init_rl(&blkg->rl, q, gfp_mask)) - goto err_free; - blkg->rl.blkg = blkg; - } - for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; struct blkg_policy_data *pd; @@ -377,7 +367,6 @@ static void blkg_destroy_all(struct request_queue *q) } q->root_blkg = NULL; - q->root_rl.blkg = NULL; } /* @@ -403,41 +392,6 @@ void __blkg_release_rcu(struct rcu_head *rcu_head) } EXPORT_SYMBOL_GPL(__blkg_release_rcu); -/* - * The next function used by blk_queue_for_each_rl(). It's a bit tricky - * because the root blkg uses @q->root_rl instead of its own rl. - */ -struct request_list *__blk_queue_next_rl(struct request_list *rl, - struct request_queue *q) -{ - struct list_head *ent; - struct blkcg_gq *blkg; - - /* - * Determine the current blkg list_head. The first entry is - * root_rl which is off @q->blkg_list and mapped to the head. - */ - if (rl == &q->root_rl) { - ent = &q->blkg_list; - /* There are no more block groups, hence no request lists */ - if (list_empty(ent)) - return NULL; - } else { - blkg = container_of(rl, struct blkcg_gq, rl); - ent = &blkg->q_node; - } - - /* walk to the next list_head, skip root blkcg */ - ent = ent->next; - if (ent == &q->root_blkg->q_node) - ent = ent->next; - if (ent == &q->blkg_list) - return NULL; - - blkg = container_of(ent, struct blkcg_gq, q_node); - return &blkg->rl; -} - static int blkcg_reset_stats(struct cgroup_subsys_state *css, struct cftype *cftype, u64 val) { @@ -1230,7 +1184,6 @@ int blkcg_init_queue(struct request_queue *q) if (IS_ERR(blkg)) goto err_unlock; q->root_blkg = blkg; - q->root_rl.blkg = blkg; spin_unlock_irq(q->queue_lock); rcu_read_unlock(); diff --git a/block/blk-core.c b/block/blk-core.c index ccfe2a65cc22..45f5c5898fd7 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -450,81 +450,6 @@ void blk_cleanup_queue(struct request_queue *q) } EXPORT_SYMBOL(blk_cleanup_queue); -/* Allocate memory local to the request queue */ -static void *alloc_request_simple(gfp_t gfp_mask, void *data) -{ - struct request_queue *q = data; - - return kmem_cache_alloc_node(request_cachep, gfp_mask, q->node); -} - -static void free_request_simple(void *element, void *data) -{ - kmem_cache_free(request_cachep, element); -} - -static void *alloc_request_size(gfp_t gfp_mask, void *data) -{ - struct request_queue *q = data; - struct request *rq; - - rq = kmalloc_node(sizeof(struct request) + q->cmd_size, gfp_mask, - q->node); - if (rq && q->init_rq_fn && q->init_rq_fn(q, rq, gfp_mask) < 0) { - kfree(rq); - rq = NULL; - } - return rq; -} - -static void free_request_size(void *element, void *data) -{ - struct request_queue *q = data; - - if (q->exit_rq_fn) - q->exit_rq_fn(q, element); - kfree(element); -} - -int blk_init_rl(struct request_list *rl, struct request_queue *q, - gfp_t gfp_mask) -{ - if (unlikely(rl->rq_pool) || q->mq_ops) - return 0; - - rl->q = q; - rl->count[BLK_RW_SYNC] = rl->count[BLK_RW_ASYNC] = 0; - rl->starved[BLK_RW_SYNC] = rl->starved[BLK_RW_ASYNC] = 0; - init_waitqueue_head(&rl->wait[BLK_RW_SYNC]); - init_waitqueue_head(&rl->wait[BLK_RW_ASYNC]); - - if (q->cmd_size) { - rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, - alloc_request_size, free_request_size, - q, gfp_mask, q->node); - } else { - rl->rq_pool = mempool_create_node(BLKDEV_MIN_RQ, - alloc_request_simple, free_request_simple, - q, gfp_mask, q->node); - } - if (!rl->rq_pool) - return -ENOMEM; - - if (rl != &q->root_rl) - WARN_ON_ONCE(!blk_get_queue(q)); - - return 0; -} - -void blk_exit_rl(struct request_queue *q, struct request_list *rl) -{ - if (rl->rq_pool) { - mempool_destroy(rl->rq_pool); - if (rl != &q->root_rl) - blk_put_queue(q); - } -} - struct request_queue *blk_alloc_queue(gfp_t gfp_mask) { return blk_alloc_queue_node(gfp_mask, NUMA_NO_NODE, NULL); diff --git a/block/blk-mq.c b/block/blk-mq.c index d106d7a970cc..2600cba56408 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -326,10 +326,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, rq->end_io_data = NULL; rq->next_rq = NULL; -#ifdef CONFIG_BLK_CGROUP - rq->rl = NULL; -#endif - data->ctx->rq_dispatched[op_is_sync(op)]++; refcount_set(&rq->ref, 1); return rq; diff --git a/block/blk.h b/block/blk.h index 4ae6cacb4548..e925cf4fe4de 100644 --- a/block/blk.h +++ b/block/blk.h @@ -120,9 +120,6 @@ struct blk_flush_queue *blk_alloc_flush_queue(struct request_queue *q, int node, int cmd_size, gfp_t flags); void blk_free_flush_queue(struct blk_flush_queue *q); -int blk_init_rl(struct request_list *rl, struct request_queue *q, - gfp_t gfp_mask); -void blk_exit_rl(struct request_queue *q, struct request_list *rl); void blk_exit_queue(struct request_queue *q); void blk_rq_bio_prep(struct request_queue *q, struct request *rq, struct bio *bio); diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 6d766a19f2bb..1b299e025e83 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -122,9 +122,6 @@ struct blkcg_gq { /* all non-root blkcg_gq's are guaranteed to have access to parent */ struct blkcg_gq *parent; - /* request allocation list for this blkcg-q pair */ - struct request_list rl; - /* reference count */ atomic_t refcnt; @@ -515,94 +512,6 @@ static inline void blkg_put(struct blkcg_gq *blkg) if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q, false))) -/** - * blk_get_rl - get request_list to use - * @q: request_queue of interest - * @bio: bio which will be attached to the allocated request (may be %NULL) - * - * The caller wants to allocate a request from @q to use for @bio. Find - * the request_list to use and obtain a reference on it. Should be called - * under queue_lock. This function is guaranteed to return non-%NULL - * request_list. - */ -static inline struct request_list *blk_get_rl(struct request_queue *q, - struct bio *bio) -{ - struct blkcg *blkcg; - struct blkcg_gq *blkg; - - rcu_read_lock(); - - blkcg = bio_blkcg(bio); - - /* bypass blkg lookup and use @q->root_rl directly for root */ - if (blkcg == &blkcg_root) - goto root_rl; - - /* - * Try to use blkg->rl. blkg lookup may fail under memory pressure - * or if either the blkcg or queue is going away. Fall back to - * root_rl in such cases. - */ - blkg = blkg_lookup(blkcg, q); - if (unlikely(!blkg)) - goto root_rl; - - blkg_get(blkg); - rcu_read_unlock(); - return &blkg->rl; -root_rl: - rcu_read_unlock(); - return &q->root_rl; -} - -/** - * blk_put_rl - put request_list - * @rl: request_list to put - * - * Put the reference acquired by blk_get_rl(). Should be called under - * queue_lock. - */ -static inline void blk_put_rl(struct request_list *rl) -{ - if (rl->blkg->blkcg != &blkcg_root) - blkg_put(rl->blkg); -} - -/** - * blk_rq_set_rl - associate a request with a request_list - * @rq: request of interest - * @rl: target request_list - * - * Associate @rq with @rl so that accounting and freeing can know the - * request_list @rq came from. - */ -static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) -{ - rq->rl = rl; -} - -/** - * blk_rq_rl - return the request_list a request came from - * @rq: request of interest - * - * Return the request_list @rq is allocated from. - */ -static inline struct request_list *blk_rq_rl(struct request *rq) -{ - return rq->rl; -} - -struct request_list *__blk_queue_next_rl(struct request_list *rl, - struct request_queue *q); -/** - * blk_queue_for_each_rl - iterate through all request_lists of a request_queue - * - * Should be used under queue_lock. - */ -#define blk_queue_for_each_rl(rl, q) \ - for ((rl) = &(q)->root_rl; (rl); (rl) = __blk_queue_next_rl((rl), (q))) - static inline int blkg_stat_init(struct blkg_stat *stat, gfp_t gfp) { int ret; @@ -939,12 +848,6 @@ static inline char *blkg_path(struct blkcg_gq *blkg) { return NULL; } static inline void blkg_get(struct blkcg_gq *blkg) { } static inline void blkg_put(struct blkcg_gq *blkg) { } -static inline struct request_list *blk_get_rl(struct request_queue *q, - struct bio *bio) { return &q->root_rl; } -static inline void blk_put_rl(struct request_list *rl) { } -static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { } -static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; } - static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { return true; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 877a3d235c45..e0c661a95c39 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -58,22 +58,6 @@ struct blk_stat_callback; typedef void (rq_end_io_fn)(struct request *, blk_status_t); -struct request_list { - struct request_queue *q; /* the queue this rl belongs to */ -#ifdef CONFIG_BLK_CGROUP - struct blkcg_gq *blkg; /* blkg this request pool belongs to */ -#endif - /* - * count[], starved[], and wait[] are indexed by - * BLK_RW_SYNC/BLK_RW_ASYNC - */ - int count[2]; - int starved[2]; - mempool_t *rq_pool; - wait_queue_head_t wait[2]; - unsigned int flags; -}; - /* * request flags */ typedef __u32 __bitwise req_flags_t; @@ -259,10 +243,6 @@ struct request { /* for bidi */ struct request *next_rq; - -#ifdef CONFIG_BLK_CGROUP - struct request_list *rl; /* rl this rq is alloced from */ -#endif }; static inline bool blk_op_is_scsi(unsigned int op) @@ -312,8 +292,6 @@ typedef bool (poll_q_fn) (struct request_queue *q, blk_qc_t); struct bio_vec; typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); -typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t); -typedef void (exit_rq_fn)(struct request_queue *, struct request *); enum blk_eh_timer_return { BLK_EH_DONE, /* drivers has completed the command */ @@ -427,22 +405,10 @@ struct request_queue { struct blk_queue_stats *stats; struct rq_qos *rq_qos; - /* - * If blkcg is not used, @q->root_rl serves all requests. If blkcg - * is used, root blkg allocates from @q->root_rl and all other - * blkgs from their own blkg->rl. Which one to use should be - * determined using bio_request_list(). - */ - struct request_list root_rl; - make_request_fn *make_request_fn; poll_q_fn *poll_fn; softirq_done_fn *softirq_done_fn; dma_drain_needed_fn *dma_drain_needed; - /* Called just after a request is allocated */ - init_rq_fn *init_rq_fn; - /* Called just before a request is freed */ - exit_rq_fn *exit_rq_fn; const struct blk_mq_ops *mq_ops; -- cgit v1.2.3-71-gd317 From 7d692330e7cd581ccfee982334bf06b236cb999a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 24 Oct 2018 10:48:12 -0600 Subject: block: get rid of blk_queued_rq() No point in hiding what this does, just open code it in the one spot where we are still using it. Reviewed-by: Hannes Reinecke Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-mq.c | 2 +- include/linux/blkdev.h | 2 -- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-mq.c b/block/blk-mq.c index 2600cba56408..b49f5bd86f42 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -692,7 +692,7 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list) /* this request will be re-inserted to io scheduler queue */ blk_mq_sched_requeue_request(rq); - BUG_ON(blk_queued_rq(rq)); + BUG_ON(!list_empty(&rq->queuelist)); blk_mq_add_to_requeue_list(rq, true, kick_requeue_list); } EXPORT_SYMBOL(blk_mq_requeue_request); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e0c661a95c39..c675e2b5af62 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -673,8 +673,6 @@ static inline bool blk_account_rq(struct request *rq) #define blk_rq_cpu_valid(rq) ((rq)->cpu != -1) #define blk_bidi_rq(rq) ((rq)->next_rq != NULL) -/* rq->queuelist of dequeued request must be list_empty() */ -#define blk_queued_rq(rq) (!list_empty(&(rq)->queuelist)) #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) -- cgit v1.2.3-71-gd317 From c7bb9ad1744ea14e61e5fff99ee5282709b0c9d9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 31 Oct 2018 09:43:30 -0600 Subject: block: get rid of q->softirq_done_fn() With the legacy path gone, all we do is funnel it through the mq_ops->complete() operation. Tested-by: Ming Lei Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-mq.c | 17 ++++++++--------- block/blk-settings.c | 6 ------ block/blk-softirq.c | 4 ++-- include/linux/blk-mq.h | 3 ++- include/linux/blkdev.h | 3 --- 5 files changed, 12 insertions(+), 21 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-mq.c b/block/blk-mq.c index b49f5bd86f42..5e7982918c54 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -546,13 +546,15 @@ EXPORT_SYMBOL(blk_mq_end_request); static void __blk_mq_complete_request_remote(void *data) { struct request *rq = data; + struct request_queue *q = rq->q; - rq->q->softirq_done_fn(rq); + q->mq_ops->complete(rq); } static void __blk_mq_complete_request(struct request *rq) { struct blk_mq_ctx *ctx = rq->mq_ctx; + struct request_queue *q = rq->q; bool shared = false; int cpu; @@ -568,18 +570,18 @@ static void __blk_mq_complete_request(struct request *rq) * So complete IO reqeust in softirq context in case of single queue * for not degrading IO performance by irqsoff latency. */ - if (rq->q->nr_hw_queues == 1) { + if (q->nr_hw_queues == 1) { __blk_complete_request(rq); return; } - if (!test_bit(QUEUE_FLAG_SAME_COMP, &rq->q->queue_flags)) { - rq->q->softirq_done_fn(rq); + if (!test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags)) { + q->mq_ops->complete(rq); return; } cpu = get_cpu(); - if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags)) + if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags)) shared = cpus_share_cache(cpu, ctx->cpu); if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) { @@ -588,7 +590,7 @@ static void __blk_mq_complete_request(struct request *rq) rq->csd.flags = 0; smp_call_function_single_async(ctx->cpu, &rq->csd); } else { - rq->q->softirq_done_fn(rq); + q->mq_ops->complete(rq); } put_cpu(); } @@ -2701,9 +2703,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, */ q->poll_nsec = -1; - if (set->ops->complete) - blk_queue_softirq_done(q, set->ops->complete); - blk_mq_init_cpu_queues(q, set->nr_hw_queues); blk_mq_add_queue_tag_set(set, q); blk_mq_map_swqueue(q); diff --git a/block/blk-settings.c b/block/blk-settings.c index e3f07d94b18d..cca83590a1dc 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -20,12 +20,6 @@ EXPORT_SYMBOL(blk_max_low_pfn); unsigned long blk_max_pfn; -void blk_queue_softirq_done(struct request_queue *q, softirq_done_fn *fn) -{ - q->softirq_done_fn = fn; -} -EXPORT_SYMBOL(blk_queue_softirq_done); - void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout) { q->rq_timeout = timeout; diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 8ca0f6caf174..727d64436ec4 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -34,7 +34,7 @@ static __latent_entropy void blk_done_softirq(struct softirq_action *h) rq = list_entry(local_list.next, struct request, ipi_list); list_del_init(&rq->ipi_list); - rq->q->softirq_done_fn(rq); + rq->q->mq_ops->complete(rq); } } @@ -102,7 +102,7 @@ void __blk_complete_request(struct request *req) unsigned long flags; bool shared = false; - BUG_ON(!q->softirq_done_fn); + BUG_ON(!q->mq_ops->complete); local_irq_save(flags); cpu = smp_processor_id(); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 5c8418ebbfd6..9dd574e5436a 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -115,6 +115,7 @@ typedef void (busy_tag_iter_fn)(struct request *, void *, bool); typedef int (poll_fn)(struct blk_mq_hw_ctx *, unsigned int); typedef int (map_queues_fn)(struct blk_mq_tag_set *set); typedef bool (busy_fn)(struct request_queue *); +typedef void (complete_fn)(struct request *); struct blk_mq_ops { @@ -142,7 +143,7 @@ struct blk_mq_ops { */ poll_fn *poll; - softirq_done_fn *complete; + complete_fn *complete; /* * Called when the block layer side of a hardware queue has been diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c675e2b5af62..d4104844d6bb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -290,7 +290,6 @@ typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); typedef bool (poll_q_fn) (struct request_queue *q, blk_qc_t); struct bio_vec; -typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); enum blk_eh_timer_return { @@ -407,7 +406,6 @@ struct request_queue { make_request_fn *make_request_fn; poll_q_fn *poll_fn; - softirq_done_fn *softirq_done_fn; dma_drain_needed_fn *dma_drain_needed; const struct blk_mq_ops *mq_ops; @@ -1113,7 +1111,6 @@ extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); -extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); -- cgit v1.2.3-71-gd317 From 9cf2bab6307659b940da65d16dcc8f82c69f3a97 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 31 Oct 2018 17:01:22 -0600 Subject: block: kill request ->cpu member This was used for completion placement for the legacy path, but for mq we have rq->mq_ctx->cpu for that. Add a helper to get the request CPU assignment, as the mq_ctx type is private to blk-mq. Reviewed-by: Omar Sandoval Signed-off-by: Jens Axboe --- block/blk-core.c | 2 -- block/blk-merge.c | 2 -- block/blk-mq.c | 7 ++++++- block/blk-softirq.c | 2 +- drivers/scsi/bnx2i/bnx2i_hwi.c | 8 +------- drivers/scsi/csiostor/csio_scsi.c | 8 +------- drivers/scsi/qla2xxx/qla_os.c | 2 +- include/linux/blk-mq.h | 2 ++ include/linux/blkdev.h | 2 -- 9 files changed, 12 insertions(+), 23 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index a14dab57ff8b..3daab9df24e0 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -145,7 +145,6 @@ void blk_rq_init(struct request_queue *q, struct request *rq) INIT_LIST_HEAD(&rq->queuelist); INIT_LIST_HEAD(&rq->timeout_list); - rq->cpu = -1; rq->q = q; rq->__sector = (sector_t) -1; INIT_HLIST_NODE(&rq->hash); @@ -1770,7 +1769,6 @@ EXPORT_SYMBOL_GPL(blk_rq_unprep_clone); */ static void __blk_rq_prep_clone(struct request *dst, struct request *src) { - dst->cpu = src->cpu; dst->__sector = blk_rq_pos(src); dst->__data_len = blk_rq_bytes(src); if (src->rq_flags & RQF_SPECIAL_PAYLOAD) { diff --git a/block/blk-merge.c b/block/blk-merge.c index a399b2fa8bc8..91b2af332a84 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -806,8 +806,6 @@ static struct request *attempt_merge(struct request_queue *q, blk_account_io_merge(next); req->ioprio = ioprio_best(req->ioprio, next->ioprio); - if (blk_rq_cpu_valid(next)) - req->cpu = next->cpu; /* * ownership of bio passed from next to req, return 'next' for diff --git a/block/blk-mq.c b/block/blk-mq.c index 5e7982918c54..67a2bafd4b29 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -297,7 +297,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, rq->q = data->q; rq->mq_ctx = data->ctx; rq->rq_flags = rq_flags; - rq->cpu = -1; rq->cmd_flags = op; if (data->flags & BLK_MQ_REQ_PREEMPT) rq->rq_flags |= RQF_PREEMPT; @@ -3282,6 +3281,12 @@ static bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie) return __blk_mq_poll(hctx, rq); } +unsigned int blk_mq_rq_cpu(struct request *rq) +{ + return rq->mq_ctx->cpu; +} +EXPORT_SYMBOL(blk_mq_rq_cpu); + static int __init blk_mq_init(void) { cpuhp_setup_state_multi(CPUHP_BLK_MQ_DEAD, "block/mq:dead", NULL, diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 727d64436ec4..1534066e306e 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -98,7 +98,7 @@ static int blk_softirq_cpu_dead(unsigned int cpu) void __blk_complete_request(struct request *req) { struct request_queue *q = req->q; - int cpu, ccpu = q->mq_ops ? req->mq_ctx->cpu : req->cpu; + int cpu, ccpu = req->mq_ctx->cpu; unsigned long flags; bool shared = false; diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c index e9e669a6c2bc..6bad2689edd4 100644 --- a/drivers/scsi/bnx2i/bnx2i_hwi.c +++ b/drivers/scsi/bnx2i/bnx2i_hwi.c @@ -1906,7 +1906,6 @@ static int bnx2i_queue_scsi_cmd_resp(struct iscsi_session *session, struct iscsi_task *task; struct scsi_cmnd *sc; int rc = 0; - int cpu; spin_lock(&session->back_lock); task = iscsi_itt_to_task(bnx2i_conn->cls_conn->dd_data, @@ -1917,14 +1916,9 @@ static int bnx2i_queue_scsi_cmd_resp(struct iscsi_session *session, } sc = task->sc; - if (!blk_rq_cpu_valid(sc->request)) - cpu = smp_processor_id(); - else - cpu = sc->request->cpu; - spin_unlock(&session->back_lock); - p = &per_cpu(bnx2i_percpu, cpu); + p = &per_cpu(bnx2i_percpu, blk_mq_rq_cpu(sc->request)); spin_lock(&p->p_work_lock); if (unlikely(!p->iothread)) { rc = -EINVAL; diff --git a/drivers/scsi/csiostor/csio_scsi.c b/drivers/scsi/csiostor/csio_scsi.c index 8c15b7acb4b7..a95debbea0e4 100644 --- a/drivers/scsi/csiostor/csio_scsi.c +++ b/drivers/scsi/csiostor/csio_scsi.c @@ -1780,16 +1780,10 @@ csio_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *cmnd) int nsge = 0; int rv = SCSI_MLQUEUE_HOST_BUSY, nr; int retval; - int cpu; struct csio_scsi_qset *sqset; struct fc_rport *rport = starget_to_rport(scsi_target(cmnd->device)); - if (!blk_rq_cpu_valid(cmnd->request)) - cpu = smp_processor_id(); - else - cpu = cmnd->request->cpu; - - sqset = &hw->sqset[ln->portid][cpu]; + sqset = &hw->sqset[ln->portid][blk_mq_rq_cpu(cmnd->request)]; nr = fc_remote_port_chkready(rport); if (nr) { diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c index 4ea9f2b4e04f..29dfd1bd164d 100644 --- a/drivers/scsi/qla2xxx/qla_os.c +++ b/drivers/scsi/qla2xxx/qla_os.c @@ -1460,7 +1460,7 @@ __qla2xxx_eh_generic_reset(char *name, enum nexus_wait_type type, goto eh_reset_failed; } err = 2; - if (do_reset(fcport, cmd->device->lun, cmd->request->cpu + 1) + if (do_reset(fcport, cmd->device->lun, blk_mq_rq_cpu(cmd->request) + 1) != QLA_SUCCESS) { ql_log(ql_log_warn, vha, 0x800c, "do_reset failed for cmd=%p.\n", cmd); diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 9dd574e5436a..d83a26fb37e5 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -300,6 +300,8 @@ void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues); void blk_mq_quiesce_queue_nowait(struct request_queue *q); +unsigned int blk_mq_rq_cpu(struct request *rq); + /** * blk_mq_mark_complete() - Set request state to complete * @rq: request to set to complete state diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d4104844d6bb..c8fa4d3d7fee 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -130,7 +130,6 @@ struct request { struct request_queue *q; struct blk_mq_ctx *mq_ctx; - int cpu; unsigned int cmd_flags; /* op and common flags */ req_flags_t rq_flags; @@ -669,7 +668,6 @@ static inline bool blk_account_rq(struct request *rq) return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); } -#define blk_rq_cpu_valid(rq) ((rq)->cpu != -1) #define blk_bidi_rq(rq) ((rq)->next_rq != NULL) #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) -- cgit v1.2.3-71-gd317 From a8908939af569ce2419f43fd56eeaf003bc3d85d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 16 Oct 2018 14:23:06 -0600 Subject: blk-mq: kill q->mq_map It's just a pointer to set->mq_map, use that instead. Move the assignment a bit earlier, so we always know it's valid. Reviewed-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: Bart Van Assche Reviewed-by: Keith Busch Signed-off-by: Jens Axboe --- block/blk-mq.c | 13 ++++--------- block/blk-mq.h | 4 +++- include/linux/blkdev.h | 2 -- 3 files changed, 7 insertions(+), 12 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-mq.c b/block/blk-mq.c index 67a2bafd4b29..766facfa1f08 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2322,7 +2322,7 @@ static void blk_mq_map_swqueue(struct request_queue *q) * If the cpu isn't present, the cpu is mapped to first hctx. */ for_each_possible_cpu(i) { - hctx_idx = q->mq_map[i]; + hctx_idx = set->mq_map[i]; /* unmapped hw queue can be remapped after CPU topo changed */ if (!set->tags[hctx_idx] && !__blk_mq_alloc_rq_map(set, hctx_idx)) { @@ -2332,7 +2332,7 @@ static void blk_mq_map_swqueue(struct request_queue *q) * case, remap the current ctx to hctx[0] which * is guaranteed to always have tags allocated */ - q->mq_map[i] = 0; + set->mq_map[i] = 0; } ctx = per_cpu_ptr(q->queue_ctx, i); @@ -2430,8 +2430,6 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q) static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, struct request_queue *q) { - q->tag_set = set; - mutex_lock(&set->tag_list_lock); /* @@ -2468,8 +2466,6 @@ void blk_mq_release(struct request_queue *q) kobject_put(&hctx->kobj); } - q->mq_map = NULL; - kfree(q->queue_hw_ctx); /* @@ -2589,7 +2585,7 @@ static void blk_mq_realloc_hw_ctxs(struct blk_mq_tag_set *set, int node; struct blk_mq_hw_ctx *hctx; - node = blk_mq_hw_queue_to_node(q->mq_map, i); + node = blk_mq_hw_queue_to_node(set->mq_map, i); /* * If the hw queue has been mapped to another numa node, * we need to realloc the hctx. If allocation fails, fallback @@ -2666,8 +2662,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, if (!q->queue_hw_ctx) goto err_percpu; - q->mq_map = set->mq_map; - blk_mq_realloc_hw_ctxs(set, q); if (!q->nr_hw_queues) goto err_hctxs; @@ -2676,6 +2670,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, blk_queue_rq_timeout(q, set->timeout ? set->timeout : 30 * HZ); q->nr_queues = nr_cpu_ids; + q->tag_set = set; q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT; diff --git a/block/blk-mq.h b/block/blk-mq.h index 9497b47e2526..9536be06d022 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -75,7 +75,9 @@ extern int blk_mq_hw_queue_to_node(unsigned int *map, unsigned int); static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, int cpu) { - return q->queue_hw_ctx[q->mq_map[cpu]]; + struct blk_mq_tag_set *set = q->tag_set; + + return q->queue_hw_ctx[set->mq_map[cpu]]; } /* diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c8fa4d3d7fee..2ae7465d68ab 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -409,8 +409,6 @@ struct request_queue { const struct blk_mq_ops *mq_ops; - unsigned int *mq_map; - /* sw queues */ struct blk_mq_ctx __percpu *queue_ctx; unsigned int nr_queues; -- cgit v1.2.3-71-gd317 From ea4f995ee8b8f0578b3319949f2edd5d812fdb0a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 29 Oct 2018 15:06:13 -0600 Subject: blk-mq: cache request hardware queue mapping We call blk_mq_map_queue() a lot, at least two times for each request per IO, sometimes more. Since we now have an indirect call as well in that function. cache the mapping so we don't have to re-call blk_mq_map_queue() for the same request multiple times. Reviewed-by: Keith Busch Reviewed-by: Sagi Grimberg Reviewed-by: Hannes Reinecke Signed-off-by: Jens Axboe --- block/blk-flush.c | 12 ++++-------- block/blk-mq-debugfs.c | 4 +--- block/blk-mq-sched.c | 6 ++---- block/blk-mq-tag.c | 9 +-------- block/blk-mq.c | 22 +++++++++------------- block/blk-mq.h | 5 +---- include/linux/blkdev.h | 1 + 7 files changed, 19 insertions(+), 40 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-flush.c b/block/blk-flush.c index 77e9f5b2ee05..c53197dcdd70 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -215,7 +215,7 @@ static void flush_end_io(struct request *flush_rq, blk_status_t error) /* release the tag's ownership to the req cloned from */ spin_lock_irqsave(&fq->mq_flush_lock, flags); - hctx = blk_mq_map_queue(q, flush_rq->cmd_flags, flush_rq->mq_ctx->cpu); + hctx = flush_rq->mq_hctx; if (!q->elevator) { blk_mq_tag_set_rq(hctx, flush_rq->tag, fq->orig_rq); flush_rq->tag = -1; @@ -262,7 +262,6 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, struct request *first_rq = list_first_entry(pending, struct request, flush.list); struct request *flush_rq = fq->flush_rq; - struct blk_mq_hw_ctx *hctx; /* C1 described at the top of this file */ if (fq->flush_pending_idx != fq->flush_running_idx || list_empty(pending)) @@ -297,13 +296,12 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, * just for cheating put/get driver tag. */ flush_rq->mq_ctx = first_rq->mq_ctx; + flush_rq->mq_hctx = first_rq->mq_hctx; if (!q->elevator) { fq->orig_rq = first_rq; flush_rq->tag = first_rq->tag; - hctx = blk_mq_map_queue(q, first_rq->cmd_flags, - first_rq->mq_ctx->cpu); - blk_mq_tag_set_rq(hctx, first_rq->tag, flush_rq); + blk_mq_tag_set_rq(flush_rq->mq_hctx, first_rq->tag, flush_rq); } else { flush_rq->internal_tag = first_rq->internal_tag; } @@ -320,13 +318,11 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, static void mq_flush_data_end_io(struct request *rq, blk_status_t error) { struct request_queue *q = rq->q; - struct blk_mq_hw_ctx *hctx; + struct blk_mq_hw_ctx *hctx = rq->mq_hctx; struct blk_mq_ctx *ctx = rq->mq_ctx; unsigned long flags; struct blk_flush_queue *fq = blk_get_flush_queue(q, ctx); - hctx = blk_mq_map_queue(q, rq->cmd_flags, ctx->cpu); - if (q->elevator) { WARN_ON(rq->tag < 0); blk_mq_put_driver_tag_hctx(hctx, rq); diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index fac70c81b7de..cde19be36135 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -427,10 +427,8 @@ struct show_busy_params { static void hctx_show_busy_rq(struct request *rq, void *data, bool reserved) { const struct show_busy_params *params = data; - struct blk_mq_hw_ctx *hctx; - hctx = blk_mq_map_queue(rq->q, rq->cmd_flags, rq->mq_ctx->cpu); - if (hctx == params->hctx) + if (rq->mq_hctx == params->hctx) __blk_mq_debugfs_rq_show(params->m, list_entry_rq(&rq->queuelist)); } diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index bbabc3877d5a..641df3f00632 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -366,9 +366,7 @@ void blk_mq_sched_insert_request(struct request *rq, bool at_head, struct request_queue *q = rq->q; struct elevator_queue *e = q->elevator; struct blk_mq_ctx *ctx = rq->mq_ctx; - struct blk_mq_hw_ctx *hctx; - - hctx = blk_mq_map_queue(q, rq->cmd_flags, ctx->cpu); + struct blk_mq_hw_ctx *hctx = rq->mq_hctx; /* flush rq in flush machinery need to be dispatched directly */ if (!(rq->rq_flags & RQF_FLUSH_SEQ) && op_is_flush(rq->cmd_flags)) { @@ -407,7 +405,7 @@ void blk_mq_sched_insert_requests(struct request_queue *q, /* For list inserts, requests better be on the same hw queue */ rq = list_first_entry(list, struct request, queuelist); - hctx = blk_mq_map_queue(q, rq->cmd_flags, ctx->cpu); + hctx = rq->mq_hctx; e = hctx->queue->elevator; if (e && e->type->ops.insert_requests) diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 478a959357f5..fb836d818b80 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -527,14 +527,7 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx, */ u32 blk_mq_unique_tag(struct request *rq) { - struct request_queue *q = rq->q; - struct blk_mq_hw_ctx *hctx; - int hwq = 0; - - hctx = blk_mq_map_queue(q, rq->cmd_flags, rq->mq_ctx->cpu); - hwq = hctx->queue_num; - - return (hwq << BLK_MQ_UNIQUE_TAG_BITS) | + return (rq->mq_hctx->queue_num << BLK_MQ_UNIQUE_TAG_BITS) | (rq->tag & BLK_MQ_UNIQUE_TAG_MASK); } EXPORT_SYMBOL(blk_mq_unique_tag); diff --git a/block/blk-mq.c b/block/blk-mq.c index ccf135cf41b0..6b2859d3ad23 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -300,6 +300,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, /* csd/requeue_work/fifo_time is initialized before use */ rq->q = data->q; rq->mq_ctx = data->ctx; + rq->mq_hctx = data->hctx; rq->rq_flags = rq_flags; rq->cmd_flags = op; if (data->flags & BLK_MQ_REQ_PREEMPT) @@ -472,10 +473,11 @@ static void __blk_mq_free_request(struct request *rq) { struct request_queue *q = rq->q; struct blk_mq_ctx *ctx = rq->mq_ctx; - struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->cmd_flags, ctx->cpu); + struct blk_mq_hw_ctx *hctx = rq->mq_hctx; const int sched_tag = rq->internal_tag; blk_pm_mark_last_busy(rq); + rq->mq_hctx = NULL; if (rq->tag != -1) blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag); if (sched_tag != -1) @@ -489,7 +491,7 @@ void blk_mq_free_request(struct request *rq) struct request_queue *q = rq->q; struct elevator_queue *e = q->elevator; struct blk_mq_ctx *ctx = rq->mq_ctx; - struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, rq->cmd_flags, ctx->cpu); + struct blk_mq_hw_ctx *hctx = rq->mq_hctx; if (rq->rq_flags & RQF_ELVPRIV) { if (e && e->type->ops.finish_request) @@ -983,7 +985,7 @@ bool blk_mq_get_driver_tag(struct request *rq) { struct blk_mq_alloc_data data = { .q = rq->q, - .hctx = blk_mq_map_queue(rq->q, rq->cmd_flags, rq->mq_ctx->cpu), + .hctx = rq->mq_hctx, .flags = BLK_MQ_REQ_NOWAIT, .cmd_flags = rq->cmd_flags, }; @@ -1149,7 +1151,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list, rq = list_first_entry(list, struct request, queuelist); - hctx = blk_mq_map_queue(rq->q, rq->cmd_flags, rq->mq_ctx->cpu); + hctx = rq->mq_hctx; if (!got_budget && !blk_mq_get_dispatch_budget(hctx)) break; @@ -1579,9 +1581,7 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, */ void blk_mq_request_bypass_insert(struct request *rq, bool run_queue) { - struct blk_mq_ctx *ctx = rq->mq_ctx; - struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(rq->q, rq->cmd_flags, - ctx->cpu); + struct blk_mq_hw_ctx *hctx = rq->mq_hctx; spin_lock(&hctx->lock); list_add_tail(&rq->queuelist, &hctx->dispatch); @@ -1790,9 +1790,7 @@ blk_status_t blk_mq_request_issue_directly(struct request *rq) blk_status_t ret; int srcu_idx; blk_qc_t unused_cookie; - struct blk_mq_ctx *ctx = rq->mq_ctx; - struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(rq->q, rq->cmd_flags, - ctx->cpu); + struct blk_mq_hw_ctx *hctx = rq->mq_hctx; hctx_lock(hctx, &srcu_idx); ret = __blk_mq_try_issue_directly(hctx, rq, &unused_cookie, true); @@ -1917,9 +1915,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_mq_put_ctx(data.ctx); if (same_queue_rq) { - data.hctx = blk_mq_map_queue(q, - same_queue_rq->cmd_flags, - same_queue_rq->mq_ctx->cpu); + data.hctx = same_queue_rq->mq_hctx; blk_mq_try_issue_directly(data.hctx, same_queue_rq, &cookie); } diff --git a/block/blk-mq.h b/block/blk-mq.h index 053862270125..facb6e9ddce4 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -223,13 +223,10 @@ static inline void blk_mq_put_driver_tag_hctx(struct blk_mq_hw_ctx *hctx, static inline void blk_mq_put_driver_tag(struct request *rq) { - struct blk_mq_hw_ctx *hctx; - if (rq->tag == -1 || rq->internal_tag == -1) return; - hctx = blk_mq_map_queue(rq->q, rq->cmd_flags, rq->mq_ctx->cpu); - __blk_mq_put_driver_tag(hctx, rq); + __blk_mq_put_driver_tag(rq->mq_hctx, rq); } static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2ae7465d68ab..9b1f470cc784 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -129,6 +129,7 @@ enum mq_rq_state { struct request { struct request_queue *q; struct blk_mq_ctx *mq_ctx; + struct blk_mq_hw_ctx *mq_hctx; unsigned int cmd_flags; /* op and common flags */ req_flags_t rq_flags; -- cgit v1.2.3-71-gd317 From 9d037ad707ed6069fbea4e38e6ee37e027b13f1d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 9 Nov 2018 19:37:44 +0100 Subject: block: remove req->timeout_list Unused now that the legacy request path is gone. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 1 - block/blk-mq.c | 1 - block/blk-timeout.c | 12 ------------ block/blk.h | 2 -- include/linux/blkdev.h | 2 -- 5 files changed, 18 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 3daab9df24e0..fdc0ad2686c4 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -144,7 +144,6 @@ void blk_rq_init(struct request_queue *q, struct request *rq) memset(rq, 0, sizeof(*rq)); INIT_LIST_HEAD(&rq->queuelist); - INIT_LIST_HEAD(&rq->timeout_list); rq->q = q; rq->__sector = (sector_t) -1; INIT_HLIST_NODE(&rq->hash); diff --git a/block/blk-mq.c b/block/blk-mq.c index 4880e13e2394..411be60d0cb6 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -327,7 +327,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, rq->extra_len = 0; rq->__deadline = 0; - INIT_LIST_HEAD(&rq->timeout_list); rq->timeout = 0; rq->end_io = NULL; diff --git a/block/blk-timeout.c b/block/blk-timeout.c index 6428d458072a..006cff4390c0 100644 --- a/block/blk-timeout.c +++ b/block/blk-timeout.c @@ -68,16 +68,6 @@ ssize_t part_timeout_store(struct device *dev, struct device_attribute *attr, #endif /* CONFIG_FAIL_IO_TIMEOUT */ -/* - * blk_delete_timer - Delete/cancel timer for a given function. - * @req: request that we are canceling timer for - * - */ -void blk_delete_timer(struct request *req) -{ - list_del_init(&req->timeout_list); -} - /** * blk_abort_request -- Request request recovery for the specified command * @req: pointer to the request of interest @@ -123,8 +113,6 @@ void blk_add_timer(struct request *req) struct request_queue *q = req->q; unsigned long expiry; - BUG_ON(!list_empty(&req->timeout_list)); - /* * Some LLDs, like scsi, peek at the timeout to prevent a * command from being retried forever. diff --git a/block/blk.h b/block/blk.h index 78ae94886acf..41b64e6e101b 100644 --- a/block/blk.h +++ b/block/blk.h @@ -222,8 +222,6 @@ static inline bool bio_integrity_endio(struct bio *bio) unsigned long blk_rq_timeout(unsigned long timeout); void blk_add_timer(struct request *req); -void blk_delete_timer(struct request *); - bool bio_attempt_front_merge(struct request_queue *q, struct request *req, struct bio *bio); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9b1f470cc784..dc2a6f625ecb 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -228,8 +228,6 @@ struct request { /* access through blk_rq_set_deadline, blk_rq_deadline */ unsigned long __deadline; - struct list_head timeout_list; - union { struct __call_single_data csd; u64 fifo_time; -- cgit v1.2.3-71-gd317 From 0e17e06cbf7ede285ab74bab44d888b40c21f828 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 9 Nov 2018 14:42:41 +0100 Subject: block: remove the BLKPREP_* values. Unused now. Reviewed-by: Johannes Thumshirn Reviewed-by: Bart Van Assche Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 10 ---------- 1 file changed, 10 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index dc2a6f625ecb..e67ad2dd025e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -776,16 +776,6 @@ static inline unsigned int blk_queue_depth(struct request_queue *q) return q->nr_requests; } -/* - * q->prep_rq_fn return values - */ -enum { - BLKPREP_OK, /* serve it */ - BLKPREP_KILL, /* fatal error, kill, return -EIO */ - BLKPREP_DEFER, /* leave on queue */ - BLKPREP_INVALID, /* invalid command, kill, return -EREMOTEIO */ -}; - extern unsigned long blk_max_low_pfn, blk_max_pfn; /* -- cgit v1.2.3-71-gd317 From 7ff4f8035695984c513598e2d49c8277d5d234ca Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 14 Nov 2018 15:22:49 -0700 Subject: block: remove dead queue members No more users of ->in_flight[] or ->nr_sorted, get rid of them. Fixes: a1ce35fa4985 ("block: remove dead elevator code") Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e67ad2dd025e..c961329be96b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -486,9 +486,6 @@ struct request_queue { unsigned int dma_pad_mask; unsigned int dma_alignment; - unsigned int nr_sorted; - unsigned int in_flight[2]; - unsigned int rq_timeout; int poll_nsec; -- cgit v1.2.3-71-gd317 From 8f4236d9008b0973a8281256ccfde6913cdec6cb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Nov 2018 17:02:04 +0100 Subject: block: remove QUEUE_FLAG_BYPASS and ->bypass Unused since the removal of the legacy request code. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 15 --------------- block/blk-core.c | 21 --------------------- block/blk-mq-debugfs.c | 1 - block/blk-throttle.c | 3 --- include/linux/blk-cgroup.h | 6 +----- include/linux/blkdev.h | 3 --- 6 files changed, 1 insertion(+), 48 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 6c65791bc3fe..a95cddb39f1c 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -270,13 +270,6 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, WARN_ON_ONCE(!rcu_read_lock_held()); lockdep_assert_held(q->queue_lock); - /* - * This could be the first entry point of blkcg implementation and - * we shouldn't allow anything to go through for a bypassing queue. - */ - if (unlikely(blk_queue_bypass(q))) - return ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY); - blkg = __blkg_lookup(blkcg, q, true); if (blkg) return blkg; @@ -741,14 +734,6 @@ static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg, if (!blkcg_policy_enabled(q, pol)) return ERR_PTR(-EOPNOTSUPP); - - /* - * This could be the first entry point of blkcg implementation and - * we shouldn't allow anything to go through for a bypassing queue. - */ - if (unlikely(blk_queue_bypass(q))) - return ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY); - return __blkg_lookup(blkcg, q, true /* update_hint */); } diff --git a/block/blk-core.c b/block/blk-core.c index fdc0ad2686c4..1c9b6975cf0a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -370,18 +370,6 @@ void blk_cleanup_queue(struct request_queue *q) blk_set_queue_dying(q); spin_lock_irq(lock); - /* - * A dying queue is permanently in bypass mode till released. Note - * that, unlike blk_queue_bypass_start(), we aren't performing - * synchronize_rcu() after entering bypass mode to avoid the delay - * as some drivers create and destroy a lot of queues while - * probing. This is still safe because blk_release_queue() will be - * called only after the queue refcnt drops to zero and nothing, - * RCU or not, would be traversing the queue by then. - */ - q->bypass_depth++; - queue_flag_set(QUEUE_FLAG_BYPASS, q); - queue_flag_set(QUEUE_FLAG_NOMERGES, q); queue_flag_set(QUEUE_FLAG_NOXMERGES, q); queue_flag_set(QUEUE_FLAG_DYING, q); @@ -589,15 +577,6 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, q->queue_lock = lock ? : &q->__queue_lock; - /* - * A queue starts its life with bypass turned on to avoid - * unnecessary bypass on/off overhead and nasty surprises during - * init. The initial bypass will be finished when the queue is - * registered by blk_register_queue(). - */ - q->bypass_depth = 1; - queue_flag_set_unlocked(QUEUE_FLAG_BYPASS, q); - init_waitqueue_head(&q->mq_freeze_wq); /* diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index f021f4817b80..a32bb79d6c95 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -114,7 +114,6 @@ static int queue_pm_only_show(void *data, struct seq_file *m) static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(STOPPED), QUEUE_FLAG_NAME(DYING), - QUEUE_FLAG_NAME(BYPASS), QUEUE_FLAG_NAME(BIDI), QUEUE_FLAG_NAME(NOMERGES), QUEUE_FLAG_NAME(SAME_COMP), diff --git a/block/blk-throttle.c b/block/blk-throttle.c index db1a3a2ae006..8e6f3c9821c2 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -2145,9 +2145,6 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, throtl_update_latency_buckets(td); - if (unlikely(blk_queue_bypass(q))) - goto out_unlock; - blk_throtl_assoc_bio(tg, bio); blk_throtl_update_idletime(tg); diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 1b299e025e83..2c68efc603bd 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -325,16 +325,12 @@ static inline struct blkcg_gq *__blkg_lookup(struct blkcg *blkcg, * @q: request_queue of interest * * Lookup blkg for the @blkcg - @q pair. This function should be called - * under RCU read lock and is guaranteed to return %NULL if @q is bypassing - * - see blk_queue_bypass_start() for details. + * under RCU read loc. */ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, struct request_queue *q) { WARN_ON_ONCE(!rcu_read_lock_held()); - - if (unlikely(blk_queue_bypass(q))) - return NULL; return __blkg_lookup(blkcg, q, false); } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c961329be96b..dd1e53fd4acf 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -548,7 +548,6 @@ struct request_queue { struct mutex sysfs_lock; - int bypass_depth; atomic_t mq_freeze_depth; #if defined(CONFIG_BLK_DEV_BSG) @@ -586,7 +585,6 @@ struct request_queue { #define QUEUE_FLAG_STOPPED 1 /* queue is stopped */ #define QUEUE_FLAG_DYING 2 /* queue being torn down */ -#define QUEUE_FLAG_BYPASS 3 /* act as dumb FIFO queue */ #define QUEUE_FLAG_BIDI 4 /* queue supports bidi requests */ #define QUEUE_FLAG_NOMERGES 5 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 6 /* complete on same CPU-group */ @@ -630,7 +628,6 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) #define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) -#define blk_queue_bypass(q) test_bit(QUEUE_FLAG_BYPASS, &(q)->queue_flags) #define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ -- cgit v1.2.3-71-gd317 From 079076b3416e78ba2bb3ce38e05e320c388c3120 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Nov 2018 17:02:05 +0100 Subject: block: remove deadline __deadline manipulation helpers No users left since the removal of the legacy request interface, we can remove all the magic bit stealing now and make it a normal field. But use WRITE_ONCE/READ_ONCE on the new deadline field, given that we don't seem to have any mechanism to guarantee a new value actually gets seen by other threads. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-mq.c | 4 ++-- block/blk-timeout.c | 8 +++++--- block/blk.h | 35 ----------------------------------- include/linux/blkdev.h | 4 +--- 4 files changed, 8 insertions(+), 43 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-mq.c b/block/blk-mq.c index 411be60d0cb6..4c82b4b4fa3e 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -325,7 +325,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, rq->special = NULL; /* tag was already set */ rq->extra_len = 0; - rq->__deadline = 0; + WRITE_ONCE(rq->deadline, 0); rq->timeout = 0; @@ -839,7 +839,7 @@ static bool blk_mq_req_expired(struct request *rq, unsigned long *next) if (rq->rq_flags & RQF_TIMED_OUT) return false; - deadline = blk_rq_deadline(rq); + deadline = READ_ONCE(rq->deadline); if (time_after_eq(jiffies, deadline)) return true; diff --git a/block/blk-timeout.c b/block/blk-timeout.c index 006cff4390c0..3b0179fbdd6a 100644 --- a/block/blk-timeout.c +++ b/block/blk-timeout.c @@ -84,7 +84,7 @@ void blk_abort_request(struct request *req) * immediately and that scan sees the new timeout value. * No need for fancy synchronizations. */ - blk_rq_set_deadline(req, jiffies); + WRITE_ONCE(req->deadline, jiffies); kblockd_schedule_work(&req->q->timeout_work); } EXPORT_SYMBOL_GPL(blk_abort_request); @@ -121,14 +121,16 @@ void blk_add_timer(struct request *req) req->timeout = q->rq_timeout; req->rq_flags &= ~RQF_TIMED_OUT; - blk_rq_set_deadline(req, jiffies + req->timeout); + + expiry = jiffies + req->timeout; + WRITE_ONCE(req->deadline, expiry); /* * If the timer isn't already pending or this timeout is earlier * than an existing one, modify the timer. Round up to next nearest * second. */ - expiry = blk_rq_timeout(round_jiffies_up(blk_rq_deadline(req))); + expiry = blk_rq_timeout(round_jiffies_up(expiry)); if (!timer_pending(&q->timeout) || time_before(expiry, q->timeout.expires)) { diff --git a/block/blk.h b/block/blk.h index 41b64e6e101b..08a5845b03ba 100644 --- a/block/blk.h +++ b/block/blk.h @@ -238,26 +238,6 @@ void blk_account_io_start(struct request *req, bool new_io); void blk_account_io_completion(struct request *req, unsigned int bytes); void blk_account_io_done(struct request *req, u64 now); -/* - * EH timer and IO completion will both attempt to 'grab' the request, make - * sure that only one of them succeeds. Steal the bottom bit of the - * __deadline field for this. - */ -static inline int blk_mark_rq_complete(struct request *rq) -{ - return test_and_set_bit(0, &rq->__deadline); -} - -static inline void blk_clear_rq_complete(struct request *rq) -{ - clear_bit(0, &rq->__deadline); -} - -static inline bool blk_rq_is_complete(struct request *rq) -{ - return test_bit(0, &rq->__deadline); -} - /* * Internal elevator interface */ @@ -322,21 +302,6 @@ static inline void req_set_nomerge(struct request_queue *q, struct request *req) q->last_merge = NULL; } -/* - * Steal a bit from this field for legacy IO path atomic IO marking. Note that - * setting the deadline clears the bottom bit, potentially clearing the - * completed bit. The user has to be OK with this (current ones are fine). - */ -static inline void blk_rq_set_deadline(struct request *rq, unsigned long time) -{ - rq->__deadline = time & ~0x1UL; -} - -static inline unsigned long blk_rq_deadline(struct request *rq) -{ - return rq->__deadline & ~0x1UL; -} - /* * Internal io_context interface */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index dd1e53fd4acf..60507ab7b358 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -224,9 +224,7 @@ struct request { refcount_t ref; unsigned int timeout; - - /* access through blk_rq_set_deadline, blk_rq_deadline */ - unsigned long __deadline; + unsigned long deadline; union { struct __call_single_data csd; -- cgit v1.2.3-71-gd317 From 57d74df90783f6a6b3e79dfdd2a567ce5db3b790 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Nov 2018 17:02:07 +0100 Subject: block: use atomic bitops for ->queue_flags ->queue_flags is generally not set or cleared in the fast path, and also generally set or cleared one flag at a time. Make use of the normal atomic bitops for it so that we don't need to take the queue_lock, which is otherwise mostly unused in the core block layer now. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 54 +++++++----------------------------------------- block/blk-mq.c | 2 +- block/blk-settings.c | 10 ++++----- block/blk-sysfs.c | 28 +++++++++++-------------- block/blk.h | 56 -------------------------------------------------- include/linux/blkdev.h | 1 - 6 files changed, 24 insertions(+), 127 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 1c9b6975cf0a..5c8e66a09d82 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -74,11 +74,7 @@ static struct workqueue_struct *kblockd_workqueue; */ void blk_queue_flag_set(unsigned int flag, struct request_queue *q) { - unsigned long flags; - - spin_lock_irqsave(q->queue_lock, flags); - queue_flag_set(flag, q); - spin_unlock_irqrestore(q->queue_lock, flags); + set_bit(flag, &q->queue_flags); } EXPORT_SYMBOL(blk_queue_flag_set); @@ -89,11 +85,7 @@ EXPORT_SYMBOL(blk_queue_flag_set); */ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q) { - unsigned long flags; - - spin_lock_irqsave(q->queue_lock, flags); - queue_flag_clear(flag, q); - spin_unlock_irqrestore(q->queue_lock, flags); + clear_bit(flag, &q->queue_flags); } EXPORT_SYMBOL(blk_queue_flag_clear); @@ -107,38 +99,10 @@ EXPORT_SYMBOL(blk_queue_flag_clear); */ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q) { - unsigned long flags; - bool res; - - spin_lock_irqsave(q->queue_lock, flags); - res = queue_flag_test_and_set(flag, q); - spin_unlock_irqrestore(q->queue_lock, flags); - - return res; + return test_and_set_bit(flag, &q->queue_flags); } EXPORT_SYMBOL_GPL(blk_queue_flag_test_and_set); -/** - * blk_queue_flag_test_and_clear - atomically test and clear a queue flag - * @flag: flag to be cleared - * @q: request queue - * - * Returns the previous value of @flag - 0 if the flag was not set and 1 if - * the flag was set. - */ -bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q) -{ - unsigned long flags; - bool res; - - spin_lock_irqsave(q->queue_lock, flags); - res = queue_flag_test_and_clear(flag, q); - spin_unlock_irqrestore(q->queue_lock, flags); - - return res; -} -EXPORT_SYMBOL_GPL(blk_queue_flag_test_and_clear); - void blk_rq_init(struct request_queue *q, struct request *rq) { memset(rq, 0, sizeof(*rq)); @@ -368,12 +332,10 @@ void blk_cleanup_queue(struct request_queue *q) /* mark @q DYING, no new request or merges will be allowed afterwards */ mutex_lock(&q->sysfs_lock); blk_set_queue_dying(q); - spin_lock_irq(lock); - queue_flag_set(QUEUE_FLAG_NOMERGES, q); - queue_flag_set(QUEUE_FLAG_NOXMERGES, q); - queue_flag_set(QUEUE_FLAG_DYING, q); - spin_unlock_irq(lock); + blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q); + blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q); + blk_queue_flag_set(QUEUE_FLAG_DYING, q); mutex_unlock(&q->sysfs_lock); /* @@ -384,9 +346,7 @@ void blk_cleanup_queue(struct request_queue *q) rq_qos_exit(q); - spin_lock_irq(lock); - queue_flag_set(QUEUE_FLAG_DEAD, q); - spin_unlock_irq(lock); + blk_queue_flag_set(QUEUE_FLAG_DEAD, q); /* * make sure all in-progress dispatch are completed because diff --git a/block/blk-mq.c b/block/blk-mq.c index 4c82b4b4fa3e..e2717e843727 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2756,7 +2756,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, q->queue_flags |= QUEUE_FLAG_MQ_DEFAULT; if (!(set->flags & BLK_MQ_F_SG_MERGE)) - queue_flag_set_unlocked(QUEUE_FLAG_NO_SG_MERGE, q); + blk_queue_flag_set(QUEUE_FLAG_NO_SG_MERGE, q); q->sg_reserved_size = INT_MAX; diff --git a/block/blk-settings.c b/block/blk-settings.c index cca83590a1dc..3abe831e92c8 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -834,16 +834,14 @@ EXPORT_SYMBOL(blk_set_queue_depth); */ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua) { - spin_lock_irq(q->queue_lock); if (wc) - queue_flag_set(QUEUE_FLAG_WC, q); + blk_queue_flag_set(QUEUE_FLAG_WC, q); else - queue_flag_clear(QUEUE_FLAG_WC, q); + blk_queue_flag_clear(QUEUE_FLAG_WC, q); if (fua) - queue_flag_set(QUEUE_FLAG_FUA, q); + blk_queue_flag_set(QUEUE_FLAG_FUA, q); else - queue_flag_clear(QUEUE_FLAG_FUA, q); - spin_unlock_irq(q->queue_lock); + blk_queue_flag_clear(QUEUE_FLAG_FUA, q); wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); } diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index d4b1b84ba8ca..22fd086eba9f 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -316,14 +316,12 @@ static ssize_t queue_nomerges_store(struct request_queue *q, const char *page, if (ret < 0) return ret; - spin_lock_irq(q->queue_lock); - queue_flag_clear(QUEUE_FLAG_NOMERGES, q); - queue_flag_clear(QUEUE_FLAG_NOXMERGES, q); + blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, q); + blk_queue_flag_clear(QUEUE_FLAG_NOXMERGES, q); if (nm == 2) - queue_flag_set(QUEUE_FLAG_NOMERGES, q); + blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q); else if (nm) - queue_flag_set(QUEUE_FLAG_NOXMERGES, q); - spin_unlock_irq(q->queue_lock); + blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q); return ret; } @@ -347,18 +345,16 @@ queue_rq_affinity_store(struct request_queue *q, const char *page, size_t count) if (ret < 0) return ret; - spin_lock_irq(q->queue_lock); if (val == 2) { - queue_flag_set(QUEUE_FLAG_SAME_COMP, q); - queue_flag_set(QUEUE_FLAG_SAME_FORCE, q); + blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, q); + blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, q); } else if (val == 1) { - queue_flag_set(QUEUE_FLAG_SAME_COMP, q); - queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q); + blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, q); + blk_queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q); } else if (val == 0) { - queue_flag_clear(QUEUE_FLAG_SAME_COMP, q); - queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q); + blk_queue_flag_clear(QUEUE_FLAG_SAME_COMP, q); + blk_queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q); } - spin_unlock_irq(q->queue_lock); #endif return ret; } @@ -889,7 +885,7 @@ int blk_register_queue(struct gendisk *disk) WARN_ONCE(test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags), "%s is registering an already registered queue\n", kobject_name(&dev->kobj)); - queue_flag_set_unlocked(QUEUE_FLAG_REGISTERED, q); + blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q); /* * SCSI probing may synchronously create and destroy a lot of @@ -901,7 +897,7 @@ int blk_register_queue(struct gendisk *disk) * request_queues for non-existent devices never get registered. */ if (!blk_queue_init_done(q)) { - queue_flag_set_unlocked(QUEUE_FLAG_INIT_DONE, q); + blk_queue_flag_set(QUEUE_FLAG_INIT_DONE, q); percpu_ref_switch_to_percpu(&q->q_usage_counter); } diff --git a/block/blk.h b/block/blk.h index 08a5845b03ba..f2ddc71e93da 100644 --- a/block/blk.h +++ b/block/blk.h @@ -48,62 +48,6 @@ static inline void queue_lockdep_assert_held(struct request_queue *q) lockdep_assert_held(q->queue_lock); } -static inline void queue_flag_set_unlocked(unsigned int flag, - struct request_queue *q) -{ - if (test_bit(QUEUE_FLAG_INIT_DONE, &q->queue_flags) && - kref_read(&q->kobj.kref)) - lockdep_assert_held(q->queue_lock); - __set_bit(flag, &q->queue_flags); -} - -static inline void queue_flag_clear_unlocked(unsigned int flag, - struct request_queue *q) -{ - if (test_bit(QUEUE_FLAG_INIT_DONE, &q->queue_flags) && - kref_read(&q->kobj.kref)) - lockdep_assert_held(q->queue_lock); - __clear_bit(flag, &q->queue_flags); -} - -static inline int queue_flag_test_and_clear(unsigned int flag, - struct request_queue *q) -{ - queue_lockdep_assert_held(q); - - if (test_bit(flag, &q->queue_flags)) { - __clear_bit(flag, &q->queue_flags); - return 1; - } - - return 0; -} - -static inline int queue_flag_test_and_set(unsigned int flag, - struct request_queue *q) -{ - queue_lockdep_assert_held(q); - - if (!test_bit(flag, &q->queue_flags)) { - __set_bit(flag, &q->queue_flags); - return 0; - } - - return 1; -} - -static inline void queue_flag_set(unsigned int flag, struct request_queue *q) -{ - queue_lockdep_assert_held(q); - __set_bit(flag, &q->queue_flags); -} - -static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) -{ - queue_lockdep_assert_held(q); - __clear_bit(flag, &q->queue_flags); -} - static inline struct blk_flush_queue * blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 60507ab7b358..30d8e0fbd104 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -621,7 +621,6 @@ struct request_queue { void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); -bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) -- cgit v1.2.3-71-gd317 From 6d46964230d182c4b6097379738849a809d791dc Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 14 Nov 2018 17:02:18 +0100 Subject: block: remove the lock argument to blk_alloc_queue_node With the legacy request path gone there is no real need to override the queue_lock. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 16 +++------------- block/blk-mq.c | 2 +- drivers/block/drbd/drbd_main.c | 2 +- drivers/block/null_blk_main.c | 3 +-- drivers/block/umem.c | 2 +- drivers/lightnvm/core.c | 2 +- drivers/md/dm.c | 2 +- drivers/nvdimm/pmem.c | 2 +- drivers/nvme/host/multipath.c | 2 +- include/linux/blkdev.h | 3 +-- 10 files changed, 12 insertions(+), 24 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 5c8e66a09d82..3f94c9de0252 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -393,7 +393,7 @@ EXPORT_SYMBOL(blk_cleanup_queue); struct request_queue *blk_alloc_queue(gfp_t gfp_mask) { - return blk_alloc_queue_node(gfp_mask, NUMA_NO_NODE, NULL); + return blk_alloc_queue_node(gfp_mask, NUMA_NO_NODE); } EXPORT_SYMBOL(blk_alloc_queue); @@ -473,17 +473,8 @@ static void blk_rq_timed_out_timer(struct timer_list *t) * blk_alloc_queue_node - allocate a request queue * @gfp_mask: memory allocation flags * @node_id: NUMA node to allocate memory from - * @lock: For legacy queues, pointer to a spinlock that will be used to e.g. - * serialize calls to the legacy .request_fn() callback. Ignored for - * blk-mq request queues. - * - * Note: pass the queue lock as the third argument to this function instead of - * setting the queue lock pointer explicitly to avoid triggering a sporadic - * crash in the blkcg code. This function namely calls blkcg_init_queue() and - * the queue lock pointer must be set before blkcg_init_queue() is called. */ -struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, - spinlock_t *lock) +struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) { struct request_queue *q; int ret; @@ -534,8 +525,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, #endif mutex_init(&q->sysfs_lock); spin_lock_init(&q->__queue_lock); - - q->queue_lock = lock ? : &q->__queue_lock; + q->queue_lock = &q->__queue_lock; init_waitqueue_head(&q->mq_freeze_wq); diff --git a/block/blk-mq.c b/block/blk-mq.c index a3f057fdd045..3b823891b3ef 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2548,7 +2548,7 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) { struct request_queue *uninit_q, *q; - uninit_q = blk_alloc_queue_node(GFP_KERNEL, set->numa_node, NULL); + uninit_q = blk_alloc_queue_node(GFP_KERNEL, set->numa_node); if (!uninit_q) return ERR_PTR(-ENOMEM); diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index b66c59ce6260..f973a2a845c8 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2792,7 +2792,7 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig drbd_init_set_defaults(device); - q = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE, NULL); + q = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE); if (!q) goto out_no_q; device->rq_queue = q; diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 63c23fcfc4df..62c9654b9ce8 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1659,8 +1659,7 @@ static int null_add_dev(struct nullb_device *dev) } null_init_queues(nullb); } else if (dev->queue_mode == NULL_Q_BIO) { - nullb->q = blk_alloc_queue_node(GFP_KERNEL, dev->home_node, - NULL); + nullb->q = blk_alloc_queue_node(GFP_KERNEL, dev->home_node); if (!nullb->q) { rv = -ENOMEM; goto out_cleanup_queues; diff --git a/drivers/block/umem.c b/drivers/block/umem.c index 8a27b5adc2b3..aa035cf8a51d 100644 --- a/drivers/block/umem.c +++ b/drivers/block/umem.c @@ -888,7 +888,7 @@ static int mm_pci_probe(struct pci_dev *dev, const struct pci_device_id *id) card->biotail = &card->bio; spin_lock_init(&card->lock); - card->queue = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE, NULL); + card->queue = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE); if (!card->queue) goto failed_alloc; diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c index efb976a863d2..60ab11fcc81c 100644 --- a/drivers/lightnvm/core.c +++ b/drivers/lightnvm/core.c @@ -389,7 +389,7 @@ static int nvm_create_tgt(struct nvm_dev *dev, struct nvm_ioctl_create *create) goto err_dev; } - tqueue = blk_alloc_queue_node(GFP_KERNEL, dev->q->node, NULL); + tqueue = blk_alloc_queue_node(GFP_KERNEL, dev->q->node); if (!tqueue) { ret = -ENOMEM; goto err_disk; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index c510179a7f84..a733e4c920af 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1896,7 +1896,7 @@ static struct mapped_device *alloc_dev(int minor) INIT_LIST_HEAD(&md->table_devices); spin_lock_init(&md->uevent_lock); - md->queue = blk_alloc_queue_node(GFP_KERNEL, numa_node_id, NULL); + md->queue = blk_alloc_queue_node(GFP_KERNEL, numa_node_id); if (!md->queue) goto bad; md->queue->queuedata = md; diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c index 0e39e3d1846f..f7019294740c 100644 --- a/drivers/nvdimm/pmem.c +++ b/drivers/nvdimm/pmem.c @@ -393,7 +393,7 @@ static int pmem_attach_disk(struct device *dev, return -EBUSY; } - q = blk_alloc_queue_node(GFP_KERNEL, dev_to_node(dev), NULL); + q = blk_alloc_queue_node(GFP_KERNEL, dev_to_node(dev)); if (!q) return -ENOMEM; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 5e3cc8c59a39..b82b0d3ca39a 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -276,7 +276,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head) if (!(ctrl->subsys->cmic & (1 << 1)) || !multipath) return 0; - q = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE, NULL); + q = blk_alloc_queue_node(GFP_KERNEL, NUMA_NO_NODE); if (!q) goto out; q->queuedata = head; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 30d8e0fbd104..c4a3a660e3f0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1122,8 +1122,7 @@ extern long nr_blockdev_pages(void); bool __must_check blk_get_queue(struct request_queue *); struct request_queue *blk_alloc_queue(gfp_t); -struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id, - spinlock_t *lock); +struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id); extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); -- cgit v1.2.3-71-gd317 From 0d945c1f966b2bcb67bb12be749da0a7fb00201b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 15 Nov 2018 12:17:28 -0700 Subject: block: remove the queue_lock indirection With the legacy request path gone there is no good reason to keep queue_lock as a pointer, we can always use the embedded lock now. Reviewed-by: Hannes Reinecke Signed-off-by: Christoph Hellwig Fixed floppy and blk-cgroup missing conversions and half done edits. Signed-off-by: Jens Axboe --- block/bfq-cgroup.c | 2 +- block/bfq-iosched.c | 16 ++++++------ block/blk-cgroup.c | 62 +++++++++++++++++++++++----------------------- block/blk-core.c | 10 +------- block/blk-ioc.c | 14 +++++------ block/blk-iolatency.c | 4 +-- block/blk-mq-sched.c | 4 +-- block/blk-pm.c | 20 +++++++-------- block/blk-pm.h | 6 ++--- block/blk-sysfs.c | 4 +-- block/blk-throttle.c | 22 ++++++++-------- drivers/block/floppy.c | 8 +++--- drivers/block/pktcdvd.c | 4 +-- drivers/ide/ide-pm.c | 10 ++++---- include/linux/blk-cgroup.h | 4 +-- include/linux/blkdev.h | 8 +----- 16 files changed, 92 insertions(+), 106 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 9fe5952d117d..a7a1712632b0 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -334,7 +334,7 @@ static void bfqg_stats_xfer_dead(struct bfq_group *bfqg) parent = bfqg_parent(bfqg); - lockdep_assert_held(bfqg_to_blkg(bfqg)->q->queue_lock); + lockdep_assert_held(&bfqg_to_blkg(bfqg)->q->queue_lock); if (unlikely(!parent)) return; diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index c7636cbefc85..67b22c924aee 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -399,9 +399,9 @@ static struct bfq_io_cq *bfq_bic_lookup(struct bfq_data *bfqd, unsigned long flags; struct bfq_io_cq *icq; - spin_lock_irqsave(q->queue_lock, flags); + spin_lock_irqsave(&q->queue_lock, flags); icq = icq_to_bic(ioc_lookup_icq(ioc, q)); - spin_unlock_irqrestore(q->queue_lock, flags); + spin_unlock_irqrestore(&q->queue_lock, flags); return icq; } @@ -4034,7 +4034,7 @@ static void bfq_update_dispatch_stats(struct request_queue *q, * In addition, the following queue lock guarantees that * bfqq_group(bfqq) exists as well. */ - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); if (idle_timer_disabled) /* * Since the idle timer has been disabled, @@ -4053,7 +4053,7 @@ static void bfq_update_dispatch_stats(struct request_queue *q, bfqg_stats_set_start_empty_time(bfqg); bfqg_stats_update_io_remove(bfqg, rq->cmd_flags); } - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); } #else static inline void bfq_update_dispatch_stats(struct request_queue *q, @@ -4637,11 +4637,11 @@ static void bfq_update_insert_stats(struct request_queue *q, * In addition, the following queue lock guarantees that * bfqq_group(bfqq) exists as well. */ - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); bfqg_stats_update_io_add(bfqq_group(bfqq), bfqq, cmd_flags); if (idle_timer_disabled) bfqg_stats_update_idle_time(bfqq_group(bfqq)); - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); } #else static inline void bfq_update_insert_stats(struct request_queue *q, @@ -5382,9 +5382,9 @@ static int bfq_init_queue(struct request_queue *q, struct elevator_type *e) } eq->elevator_data = bfqd; - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); q->elevator = eq; - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); /* * Our fallback bfqq if bfq_find_alloc_queue() runs into OOM issues. diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 3ba23b9bfeb9..0f6b44614165 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -147,7 +147,7 @@ struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, blkg = radix_tree_lookup(&blkcg->blkg_tree, q->id); if (blkg && blkg->q == q) { if (update_hint) { - lockdep_assert_held(q->queue_lock); + lockdep_assert_held(&q->queue_lock); rcu_assign_pointer(blkcg->blkg_hint, blkg); } return blkg; @@ -170,7 +170,7 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, int i, ret; WARN_ON_ONCE(!rcu_read_lock_held()); - lockdep_assert_held(q->queue_lock); + lockdep_assert_held(&q->queue_lock); /* blkg holds a reference to blkcg */ if (!css_tryget_online(&blkcg->css)) { @@ -268,7 +268,7 @@ struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct blkcg_gq *blkg; WARN_ON_ONCE(!rcu_read_lock_held()); - lockdep_assert_held(q->queue_lock); + lockdep_assert_held(&q->queue_lock); blkg = __blkg_lookup(blkcg, q, true); if (blkg) @@ -299,7 +299,7 @@ static void blkg_destroy(struct blkcg_gq *blkg) struct blkcg_gq *parent = blkg->parent; int i; - lockdep_assert_held(blkg->q->queue_lock); + lockdep_assert_held(&blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); /* Something wrong if we are trying to remove same group twice */ @@ -349,7 +349,7 @@ static void blkg_destroy_all(struct request_queue *q) { struct blkcg_gq *blkg, *n; - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); list_for_each_entry_safe(blkg, n, &q->blkg_list, q_node) { struct blkcg *blkcg = blkg->blkcg; @@ -359,7 +359,7 @@ static void blkg_destroy_all(struct request_queue *q) } q->root_blkg = NULL; - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); } /* @@ -454,10 +454,10 @@ void blkcg_print_blkgs(struct seq_file *sf, struct blkcg *blkcg, rcu_read_lock(); hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { - spin_lock_irq(blkg->q->queue_lock); + spin_lock_irq(&blkg->q->queue_lock); if (blkcg_policy_enabled(blkg->q, pol)) total += prfill(sf, blkg->pd[pol->plid], data); - spin_unlock_irq(blkg->q->queue_lock); + spin_unlock_irq(&blkg->q->queue_lock); } rcu_read_unlock(); @@ -655,7 +655,7 @@ u64 blkg_stat_recursive_sum(struct blkcg_gq *blkg, struct cgroup_subsys_state *pos_css; u64 sum = 0; - lockdep_assert_held(blkg->q->queue_lock); + lockdep_assert_held(&blkg->q->queue_lock); rcu_read_lock(); blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) { @@ -698,7 +698,7 @@ struct blkg_rwstat blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkg_rwstat sum = { }; int i; - lockdep_assert_held(blkg->q->queue_lock); + lockdep_assert_held(&blkg->q->queue_lock); rcu_read_lock(); blkg_for_each_descendant_pre(pos_blkg, pos_css, blkg) { @@ -729,7 +729,7 @@ static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg, struct request_queue *q) { WARN_ON_ONCE(!rcu_read_lock_held()); - lockdep_assert_held(q->queue_lock); + lockdep_assert_held(&q->queue_lock); if (!blkcg_policy_enabled(q, pol)) return ERR_PTR(-EOPNOTSUPP); @@ -750,7 +750,7 @@ static struct blkcg_gq *blkg_lookup_check(struct blkcg *blkcg, */ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, char *input, struct blkg_conf_ctx *ctx) - __acquires(rcu) __acquires(disk->queue->queue_lock) + __acquires(rcu) __acquires(&disk->queue->queue_lock) { struct gendisk *disk; struct request_queue *q; @@ -778,7 +778,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, q = disk->queue; rcu_read_lock(); - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); blkg = blkg_lookup_check(blkcg, pol, q); if (IS_ERR(blkg)) { @@ -805,7 +805,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, } /* Drop locks to do new blkg allocation with GFP_KERNEL. */ - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); new_blkg = blkg_alloc(pos, q, GFP_KERNEL); @@ -815,7 +815,7 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, } rcu_read_lock(); - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); blkg = blkg_lookup_check(pos, pol, q); if (IS_ERR(blkg)) { @@ -843,7 +843,7 @@ success: return 0; fail_unlock: - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); fail: put_disk_and_module(disk); @@ -868,9 +868,9 @@ fail: * with blkg_conf_prep(). */ void blkg_conf_finish(struct blkg_conf_ctx *ctx) - __releases(ctx->disk->queue->queue_lock) __releases(rcu) + __releases(&ctx->disk->queue->queue_lock) __releases(rcu) { - spin_unlock_irq(ctx->disk->queue->queue_lock); + spin_unlock_irq(&ctx->disk->queue->queue_lock); rcu_read_unlock(); put_disk_and_module(ctx->disk); } @@ -903,7 +903,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) */ off += scnprintf(buf+off, size-off, "%s ", dname); - spin_lock_irq(blkg->q->queue_lock); + spin_lock_irq(&blkg->q->queue_lock); rwstat = blkg_rwstat_recursive_sum(blkg, NULL, offsetof(struct blkcg_gq, stat_bytes)); @@ -917,7 +917,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v) wios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]); dios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_DISCARD]); - spin_unlock_irq(blkg->q->queue_lock); + spin_unlock_irq(&blkg->q->queue_lock); if (rbytes || wbytes || rios || wios) { has_stats = true; @@ -1038,9 +1038,9 @@ void blkcg_destroy_blkgs(struct blkcg *blkcg) struct blkcg_gq, blkcg_node); struct request_queue *q = blkg->q; - if (spin_trylock(q->queue_lock)) { + if (spin_trylock(&q->queue_lock)) { blkg_destroy(blkg); - spin_unlock(q->queue_lock); + spin_unlock(&q->queue_lock); } else { spin_unlock_irq(&blkcg->lock); cpu_relax(); @@ -1161,12 +1161,12 @@ int blkcg_init_queue(struct request_queue *q) /* Make sure the root blkg exists. */ rcu_read_lock(); - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); blkg = blkg_create(&blkcg_root, q, new_blkg); if (IS_ERR(blkg)) goto err_unlock; q->root_blkg = blkg; - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); if (preloaded) @@ -1185,7 +1185,7 @@ err_destroy_all: blkg_destroy_all(q); return ret; err_unlock: - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); rcu_read_unlock(); if (preloaded) radix_tree_preload_end(); @@ -1200,7 +1200,7 @@ err_unlock: */ void blkcg_drain_queue(struct request_queue *q) { - lockdep_assert_held(q->queue_lock); + lockdep_assert_held(&q->queue_lock); /* * @q could be exiting and already have destroyed all blkgs as @@ -1335,7 +1335,7 @@ pd_prealloc: } } - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); list_for_each_entry(blkg, &q->blkg_list, q_node) { struct blkg_policy_data *pd; @@ -1347,7 +1347,7 @@ pd_prealloc: if (!pd) swap(pd, pd_prealloc); if (!pd) { - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); goto pd_prealloc; } @@ -1361,7 +1361,7 @@ pd_prealloc: __set_bit(pol->plid, q->blkcg_pols); ret = 0; - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); out_bypass_end: if (q->mq_ops) blk_mq_unfreeze_queue(q); @@ -1390,7 +1390,7 @@ void blkcg_deactivate_policy(struct request_queue *q, if (q->mq_ops) blk_mq_freeze_queue(q); - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); __clear_bit(pol->plid, q->blkcg_pols); @@ -1403,7 +1403,7 @@ void blkcg_deactivate_policy(struct request_queue *q, } } - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); if (q->mq_ops) blk_mq_unfreeze_queue(q); diff --git a/block/blk-core.c b/block/blk-core.c index 3f94c9de0252..92b6b200e9fb 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -327,8 +327,6 @@ void blk_exit_queue(struct request_queue *q) */ void blk_cleanup_queue(struct request_queue *q) { - spinlock_t *lock = q->queue_lock; - /* mark @q DYING, no new request or merges will be allowed afterwards */ mutex_lock(&q->sysfs_lock); blk_set_queue_dying(q); @@ -381,11 +379,6 @@ void blk_cleanup_queue(struct request_queue *q) percpu_ref_exit(&q->q_usage_counter); - spin_lock_irq(lock); - if (q->queue_lock != &q->__queue_lock) - q->queue_lock = &q->__queue_lock; - spin_unlock_irq(lock); - /* @q is and will stay empty, shutdown and put */ blk_put_queue(q); } @@ -524,8 +517,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) mutex_init(&q->blk_trace_mutex); #endif mutex_init(&q->sysfs_lock); - spin_lock_init(&q->__queue_lock); - q->queue_lock = &q->__queue_lock; + spin_lock_init(&q->queue_lock); init_waitqueue_head(&q->mq_freeze_wq); diff --git a/block/blk-ioc.c b/block/blk-ioc.c index f91ca6b70d6a..5ed59ac6ae58 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -110,9 +110,9 @@ static void ioc_release_fn(struct work_struct *work) struct io_cq, ioc_node); struct request_queue *q = icq->q; - if (spin_trylock(q->queue_lock)) { + if (spin_trylock(&q->queue_lock)) { ioc_destroy_icq(icq); - spin_unlock(q->queue_lock); + spin_unlock(&q->queue_lock); } else { spin_unlock_irqrestore(&ioc->lock, flags); cpu_relax(); @@ -233,9 +233,9 @@ void ioc_clear_queue(struct request_queue *q) { LIST_HEAD(icq_list); - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); list_splice_init(&q->icq_list, &icq_list); - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); __ioc_clear_queue(&icq_list); } @@ -326,7 +326,7 @@ struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q) { struct io_cq *icq; - lockdep_assert_held(q->queue_lock); + lockdep_assert_held(&q->queue_lock); /* * icq's are indexed from @ioc using radix tree and hint pointer, @@ -385,7 +385,7 @@ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q, INIT_HLIST_NODE(&icq->ioc_node); /* lock both q and ioc and try to link @icq */ - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); spin_lock(&ioc->lock); if (likely(!radix_tree_insert(&ioc->icq_tree, q->id, icq))) { @@ -401,7 +401,7 @@ struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q, } spin_unlock(&ioc->lock); - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); radix_tree_preload_end(); return icq; } diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index 8edf1b353ad1..5f7f1773be61 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -485,11 +485,11 @@ static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio) bio_associate_blkcg(bio, &blkcg->css); blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) { - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); blkg = blkg_lookup_create(blkcg, q); if (IS_ERR(blkg)) blkg = NULL; - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); } if (!blkg) goto out; diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c index 66fda19be5a3..d084f731d104 100644 --- a/block/blk-mq-sched.c +++ b/block/blk-mq-sched.c @@ -37,9 +37,9 @@ void blk_mq_sched_assign_ioc(struct request *rq, struct bio *bio) struct io_context *ioc = rq_ioc(bio); struct io_cq *icq; - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); icq = ioc_lookup_icq(ioc, q); - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); if (!icq) { icq = ioc_create_icq(ioc, q, GFP_ATOMIC); diff --git a/block/blk-pm.c b/block/blk-pm.c index f8fdae01bea2..0a028c189897 100644 --- a/block/blk-pm.c +++ b/block/blk-pm.c @@ -89,12 +89,12 @@ int blk_pre_runtime_suspend(struct request_queue *q) /* Switch q_usage_counter back to per-cpu mode. */ blk_mq_unfreeze_queue(q); - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); if (ret < 0) pm_runtime_mark_last_busy(q->dev); else q->rpm_status = RPM_SUSPENDING; - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); if (ret) blk_clear_pm_only(q); @@ -121,14 +121,14 @@ void blk_post_runtime_suspend(struct request_queue *q, int err) if (!q->dev) return; - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); if (!err) { q->rpm_status = RPM_SUSPENDED; } else { q->rpm_status = RPM_ACTIVE; pm_runtime_mark_last_busy(q->dev); } - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); if (err) blk_clear_pm_only(q); @@ -151,9 +151,9 @@ void blk_pre_runtime_resume(struct request_queue *q) if (!q->dev) return; - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); q->rpm_status = RPM_RESUMING; - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); } EXPORT_SYMBOL(blk_pre_runtime_resume); @@ -176,7 +176,7 @@ void blk_post_runtime_resume(struct request_queue *q, int err) if (!q->dev) return; - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); if (!err) { q->rpm_status = RPM_ACTIVE; pm_runtime_mark_last_busy(q->dev); @@ -184,7 +184,7 @@ void blk_post_runtime_resume(struct request_queue *q, int err) } else { q->rpm_status = RPM_SUSPENDED; } - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); if (!err) blk_clear_pm_only(q); @@ -207,10 +207,10 @@ EXPORT_SYMBOL(blk_post_runtime_resume); */ void blk_set_runtime_active(struct request_queue *q) { - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); q->rpm_status = RPM_ACTIVE; pm_runtime_mark_last_busy(q->dev); pm_request_autosuspend(q->dev); - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); } EXPORT_SYMBOL(blk_set_runtime_active); diff --git a/block/blk-pm.h b/block/blk-pm.h index a8564ea72a41..ea5507d23e75 100644 --- a/block/blk-pm.h +++ b/block/blk-pm.h @@ -21,7 +21,7 @@ static inline void blk_pm_mark_last_busy(struct request *rq) static inline void blk_pm_requeue_request(struct request *rq) { - lockdep_assert_held(rq->q->queue_lock); + lockdep_assert_held(&rq->q->queue_lock); if (rq->q->dev && !(rq->rq_flags & RQF_PM)) rq->q->nr_pending--; @@ -30,7 +30,7 @@ static inline void blk_pm_requeue_request(struct request *rq) static inline void blk_pm_add_request(struct request_queue *q, struct request *rq) { - lockdep_assert_held(q->queue_lock); + lockdep_assert_held(&q->queue_lock); if (q->dev && !(rq->rq_flags & RQF_PM)) q->nr_pending++; @@ -38,7 +38,7 @@ static inline void blk_pm_add_request(struct request_queue *q, static inline void blk_pm_put_request(struct request *rq) { - lockdep_assert_held(rq->q->queue_lock); + lockdep_assert_held(&rq->q->queue_lock); if (rq->q->dev && !(rq->rq_flags & RQF_PM)) --rq->q->nr_pending; diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 22fd086eba9f..1e370207a20e 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -238,10 +238,10 @@ queue_max_sectors_store(struct request_queue *q, const char *page, size_t count) if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb) return -EINVAL; - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); q->limits.max_sectors = max_sectors_kb << 1; q->backing_dev_info->io_pages = max_sectors_kb >> (PAGE_SHIFT - 10); - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); return ret; } diff --git a/block/blk-throttle.c b/block/blk-throttle.c index a665b0950369..d0a23f0bb3ed 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -1243,7 +1243,7 @@ static void throtl_pending_timer_fn(struct timer_list *t) bool dispatched; int ret; - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); if (throtl_can_upgrade(td, NULL)) throtl_upgrade_state(td); @@ -1266,9 +1266,9 @@ again: break; /* this dispatch windows is still open, relax and repeat */ - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); cpu_relax(); - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); } if (!dispatched) @@ -1290,7 +1290,7 @@ again: queue_work(kthrotld_workqueue, &td->dispatch_work); } out_unlock: - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); } /** @@ -1314,11 +1314,11 @@ static void blk_throtl_dispatch_work_fn(struct work_struct *work) bio_list_init(&bio_list_on_stack); - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); for (rw = READ; rw <= WRITE; rw++) while ((bio = throtl_pop_queued(&td_sq->queued[rw], NULL))) bio_list_add(&bio_list_on_stack, bio); - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); if (!bio_list_empty(&bio_list_on_stack)) { blk_start_plug(&plug); @@ -2141,7 +2141,7 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, if (bio_flagged(bio, BIO_THROTTLED) || !tg->has_rules[rw]) goto out; - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); throtl_update_latency_buckets(td); @@ -2224,7 +2224,7 @@ again: } out_unlock: - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); out: bio_set_flag(bio, BIO_THROTTLED); @@ -2345,7 +2345,7 @@ static void tg_drain_bios(struct throtl_service_queue *parent_sq) * Dispatch all currently throttled bios on @q through ->make_request_fn(). */ void blk_throtl_drain(struct request_queue *q) - __releases(q->queue_lock) __acquires(q->queue_lock) + __releases(&q->queue_lock) __acquires(&q->queue_lock) { struct throtl_data *td = q->td; struct blkcg_gq *blkg; @@ -2368,7 +2368,7 @@ void blk_throtl_drain(struct request_queue *q) tg_drain_bios(&td->service_queue); rcu_read_unlock(); - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); /* all bios now should be in td->service_queue, issue them */ for (rw = READ; rw <= WRITE; rw++) @@ -2376,7 +2376,7 @@ void blk_throtl_drain(struct request_queue *q) NULL))) generic_make_request(bio); - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); } int blk_throtl_init(struct request_queue *q) diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c index a8cfa011c284..eeb4be8d000b 100644 --- a/drivers/block/floppy.c +++ b/drivers/block/floppy.c @@ -2255,9 +2255,9 @@ static void request_done(int uptodate) DRS->maxtrack = 1; /* unlock chained buffers */ - spin_lock_irqsave(q->queue_lock, flags); + spin_lock_irqsave(&q->queue_lock, flags); floppy_end_request(req, 0); - spin_unlock_irqrestore(q->queue_lock, flags); + spin_unlock_irqrestore(&q->queue_lock, flags); } else { if (rq_data_dir(req) == WRITE) { /* record write error information */ @@ -2269,9 +2269,9 @@ static void request_done(int uptodate) DRWE->last_error_sector = blk_rq_pos(req); DRWE->last_error_generation = DRS->generation; } - spin_lock_irqsave(q->queue_lock, flags); + spin_lock_irqsave(&q->queue_lock, flags); floppy_end_request(req, BLK_STS_IOERR); - spin_unlock_irqrestore(q->queue_lock, flags); + spin_unlock_irqrestore(&q->queue_lock, flags); } } diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c index 9381f4e3b221..4adf4c8861cd 100644 --- a/drivers/block/pktcdvd.c +++ b/drivers/block/pktcdvd.c @@ -2203,9 +2203,9 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write) * Some CDRW drives can not handle writes larger than one packet, * even if the size is a multiple of the packet size. */ - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); blk_queue_max_hw_sectors(q, pd->settings.size); - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); set_bit(PACKET_WRITABLE, &pd->flags); } else { pkt_set_speed(pd, MAX_SPEED, MAX_SPEED); diff --git a/drivers/ide/ide-pm.c b/drivers/ide/ide-pm.c index a8c53c98252d..51fe10ac02fa 100644 --- a/drivers/ide/ide-pm.c +++ b/drivers/ide/ide-pm.c @@ -44,15 +44,15 @@ static int ide_pm_execute_rq(struct request *rq) { struct request_queue *q = rq->q; - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); if (unlikely(blk_queue_dying(q))) { rq->rq_flags |= RQF_QUIET; scsi_req(rq)->result = -ENXIO; - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); blk_mq_end_request(rq, BLK_STS_OK); return -ENXIO; } - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); blk_execute_rq(q, NULL, rq, true); return scsi_req(rq)->result ? -EIO : 0; @@ -214,12 +214,12 @@ void ide_complete_pm_rq(ide_drive_t *drive, struct request *rq) printk("%s: completing PM request, %s\n", drive->name, (ide_req(rq)->type == ATA_PRIV_PM_SUSPEND) ? "suspend" : "resume"); #endif - spin_lock_irqsave(q->queue_lock, flags); + spin_lock_irqsave(&q->queue_lock, flags); if (ide_req(rq)->type == ATA_PRIV_PM_SUSPEND) blk_mq_stop_hw_queues(q); else drive->dev_flags &= ~IDE_DFLAG_BLOCKED; - spin_unlock_irqrestore(q->queue_lock, flags); + spin_unlock_irqrestore(&q->queue_lock, flags); drive->hwif->rq = NULL; diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 2c68efc603bd..a9e2e2037129 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -717,11 +717,11 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) { - spin_lock_irq(q->queue_lock); + spin_lock_irq(&q->queue_lock); blkg = blkg_lookup_create(blkcg, q); if (IS_ERR(blkg)) blkg = NULL; - spin_unlock_irq(q->queue_lock); + spin_unlock_irq(&q->queue_lock); } throtl = blk_throtl_bio(q, blkg, bio); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c4a3a660e3f0..1d185f1fc333 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -446,13 +446,7 @@ struct request_queue { */ gfp_t bounce_gfp; - /* - * protects queue structures from reentrancy. ->__queue_lock should - * _never_ be used directly, it is queue private. always use - * ->queue_lock. - */ - spinlock_t __queue_lock; - spinlock_t *queue_lock; + spinlock_t queue_lock; /* * queue kobject -- cgit v1.2.3-71-gd317 From 344e9ffcbd1898e1dc04085564a6e05c30ea8199 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Thu, 15 Nov 2018 12:22:51 -0700 Subject: block: add queue_is_mq() helper Various spots check for q->mq_ops being non-NULL, but provide a helper to do this instead. Where the ->mq_ops != NULL check is redundant, remove it. Since mq == rq-based now that legacy is gone, get rid of the queue_is_rq_based() and just use queue_is_mq() everywhere. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 8 ++++---- block/blk-core.c | 12 ++++++------ block/blk-flush.c | 3 +-- block/blk-mq.c | 2 +- block/blk-sysfs.c | 14 +++++++------- block/blk-throttle.c | 2 +- block/blk-wbt.c | 2 +- block/blk-zoned.c | 2 +- block/bsg.c | 2 +- block/elevator.c | 11 +++++------ block/genhd.c | 8 ++++---- drivers/md/dm-rq.c | 2 +- drivers/md/dm-table.c | 4 ++-- include/linux/blkdev.h | 6 +----- 14 files changed, 36 insertions(+), 42 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 0f6b44614165..63d226a084cd 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1324,7 +1324,7 @@ int blkcg_activate_policy(struct request_queue *q, if (blkcg_policy_enabled(q, pol)) return 0; - if (q->mq_ops) + if (queue_is_mq(q)) blk_mq_freeze_queue(q); pd_prealloc: if (!pd_prealloc) { @@ -1363,7 +1363,7 @@ pd_prealloc: spin_unlock_irq(&q->queue_lock); out_bypass_end: - if (q->mq_ops) + if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); if (pd_prealloc) pol->pd_free_fn(pd_prealloc); @@ -1387,7 +1387,7 @@ void blkcg_deactivate_policy(struct request_queue *q, if (!blkcg_policy_enabled(q, pol)) return; - if (q->mq_ops) + if (queue_is_mq(q)) blk_mq_freeze_queue(q); spin_lock_irq(&q->queue_lock); @@ -1405,7 +1405,7 @@ void blkcg_deactivate_policy(struct request_queue *q, spin_unlock_irq(&q->queue_lock); - if (q->mq_ops) + if (queue_is_mq(q)) blk_mq_unfreeze_queue(q); } EXPORT_SYMBOL_GPL(blkcg_deactivate_policy); diff --git a/block/blk-core.c b/block/blk-core.c index 92b6b200e9fb..0b684a520a11 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -232,7 +232,7 @@ void blk_sync_queue(struct request_queue *q) del_timer_sync(&q->timeout); cancel_work_sync(&q->timeout_work); - if (q->mq_ops) { + if (queue_is_mq(q)) { struct blk_mq_hw_ctx *hctx; int i; @@ -281,7 +281,7 @@ void blk_set_queue_dying(struct request_queue *q) */ blk_freeze_queue_start(q); - if (q->mq_ops) + if (queue_is_mq(q)) blk_mq_wake_waiters(q); /* Make blk_queue_enter() reexamine the DYING flag. */ @@ -356,7 +356,7 @@ void blk_cleanup_queue(struct request_queue *q) * blk_freeze_queue() should be enough for cases of passthrough * request. */ - if (q->mq_ops && blk_queue_init_done(q)) + if (queue_is_mq(q) && blk_queue_init_done(q)) blk_mq_quiesce_queue(q); /* for synchronous bio-based driver finish in-flight integrity i/o */ @@ -374,7 +374,7 @@ void blk_cleanup_queue(struct request_queue *q) blk_exit_queue(q); - if (q->mq_ops) + if (queue_is_mq(q)) blk_mq_free_queue(q); percpu_ref_exit(&q->q_usage_counter); @@ -982,7 +982,7 @@ generic_make_request_checks(struct bio *bio) * For a REQ_NOWAIT based request, return -EOPNOTSUPP * if queue is not a request based queue. */ - if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_rq_based(q)) + if ((bio->bi_opf & REQ_NOWAIT) && !queue_is_mq(q)) goto not_supported; if (should_fail_bio(bio)) @@ -1657,7 +1657,7 @@ EXPORT_SYMBOL_GPL(rq_flush_dcache_pages); */ int blk_lld_busy(struct request_queue *q) { - if (q->mq_ops && q->mq_ops->busy) + if (queue_is_mq(q) && q->mq_ops->busy) return q->mq_ops->busy(q); return 0; diff --git a/block/blk-flush.c b/block/blk-flush.c index fcd18b158fd6..a3fc7191c694 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -273,8 +273,7 @@ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, * assigned to empty flushes, and we deadlock if we are expecting * other requests to make progress. Don't defer for that case. */ - if (!list_empty(&fq->flush_data_in_flight) && - !(q->mq_ops && q->elevator) && + if (!list_empty(&fq->flush_data_in_flight) && q->elevator && time_before(jiffies, fq->flush_pending_since + FLUSH_PENDING_TIMEOUT)) return; diff --git a/block/blk-mq.c b/block/blk-mq.c index 3b823891b3ef..32b246ed44c0 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -150,7 +150,7 @@ void blk_freeze_queue_start(struct request_queue *q) freeze_depth = atomic_inc_return(&q->mq_freeze_depth); if (freeze_depth == 1) { percpu_ref_kill(&q->q_usage_counter); - if (q->mq_ops) + if (queue_is_mq(q)) blk_mq_run_hw_queues(q, false); } } diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 1e370207a20e..80eef48fddc8 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -68,7 +68,7 @@ queue_requests_store(struct request_queue *q, const char *page, size_t count) unsigned long nr; int ret, err; - if (!q->mq_ops) + if (!queue_is_mq(q)) return -EINVAL; ret = queue_var_store(&nr, page, count); @@ -835,12 +835,12 @@ static void __blk_release_queue(struct work_struct *work) blk_queue_free_zone_bitmaps(q); - if (q->mq_ops) + if (queue_is_mq(q)) blk_mq_release(q); blk_trace_shutdown(q); - if (q->mq_ops) + if (queue_is_mq(q)) blk_mq_debugfs_unregister(q); bioset_exit(&q->bio_split); @@ -914,7 +914,7 @@ int blk_register_queue(struct gendisk *disk) goto unlock; } - if (q->mq_ops) { + if (queue_is_mq(q)) { __blk_mq_register_dev(dev, q); blk_mq_debugfs_register(q); } @@ -925,7 +925,7 @@ int blk_register_queue(struct gendisk *disk) blk_throtl_register_queue(q); - if ((q->mq_ops && q->elevator)) { + if (q->elevator) { ret = elv_register_queue(q); if (ret) { mutex_unlock(&q->sysfs_lock); @@ -974,7 +974,7 @@ void blk_unregister_queue(struct gendisk *disk) * Remove the sysfs attributes before unregistering the queue data * structures that can be modified through sysfs. */ - if (q->mq_ops) + if (queue_is_mq(q)) blk_mq_unregister_dev(disk_to_dev(disk), q); mutex_unlock(&q->sysfs_lock); @@ -983,7 +983,7 @@ void blk_unregister_queue(struct gendisk *disk) blk_trace_remove_sysfs(disk_to_dev(disk)); mutex_lock(&q->sysfs_lock); - if (q->mq_ops && q->elevator) + if (q->elevator) elv_unregister_queue(q); mutex_unlock(&q->sysfs_lock); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index d0a23f0bb3ed..8f0a104770ee 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -2456,7 +2456,7 @@ void blk_throtl_register_queue(struct request_queue *q) td->throtl_slice = DFL_THROTL_SLICE_HD; #endif - td->track_bio_latency = !queue_is_rq_based(q); + td->track_bio_latency = !queue_is_mq(q); if (!td->track_bio_latency) blk_stat_enable_accounting(q); } diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 9f142b84dc85..d051ebfb4852 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -701,7 +701,7 @@ void wbt_enable_default(struct request_queue *q) if (!test_bit(QUEUE_FLAG_REGISTERED, &q->queue_flags)) return; - if (q->mq_ops && IS_ENABLED(CONFIG_BLK_WBT_MQ)) + if (queue_is_mq(q) && IS_ENABLED(CONFIG_BLK_WBT_MQ)) wbt_init(q); } EXPORT_SYMBOL_GPL(wbt_enable_default); diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 13ba2011a306..e9c332b1d9da 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -421,7 +421,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk) * BIO based queues do not use a scheduler so only q->nr_zones * needs to be updated so that the sysfs exposed value is correct. */ - if (!queue_is_rq_based(q)) { + if (!queue_is_mq(q)) { q->nr_zones = nr_zones; return 0; } diff --git a/block/bsg.c b/block/bsg.c index 9a442c23a715..44f6028b9567 100644 --- a/block/bsg.c +++ b/block/bsg.c @@ -471,7 +471,7 @@ int bsg_register_queue(struct request_queue *q, struct device *parent, /* * we need a proper transport to send commands, not a stacked device */ - if (!queue_is_rq_based(q)) + if (!queue_is_mq(q)) return 0; bcd = &q->bsg_dev; diff --git a/block/elevator.c b/block/elevator.c index 796436270682..f05e90d4e695 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -667,7 +667,7 @@ static int __elevator_change(struct request_queue *q, const char *name) /* * Special case for mq, turn off scheduling */ - if (q->mq_ops && !strncmp(name, "none", 4)) + if (!strncmp(name, "none", 4)) return elevator_switch(q, NULL); strlcpy(elevator_name, name, sizeof(elevator_name)); @@ -685,8 +685,7 @@ static int __elevator_change(struct request_queue *q, const char *name) static inline bool elv_support_iosched(struct request_queue *q) { - if (q->mq_ops && q->tag_set && (q->tag_set->flags & - BLK_MQ_F_NO_SCHED)) + if (q->tag_set && (q->tag_set->flags & BLK_MQ_F_NO_SCHED)) return false; return true; } @@ -696,7 +695,7 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name, { int ret; - if (!q->mq_ops || !elv_support_iosched(q)) + if (!queue_is_mq(q) || !elv_support_iosched(q)) return count; ret = __elevator_change(q, name); @@ -713,7 +712,7 @@ ssize_t elv_iosched_show(struct request_queue *q, char *name) struct elevator_type *__e; int len = 0; - if (!queue_is_rq_based(q)) + if (!queue_is_mq(q)) return sprintf(name, "none\n"); if (!q->elevator) @@ -732,7 +731,7 @@ ssize_t elv_iosched_show(struct request_queue *q, char *name) } spin_unlock(&elv_list_lock); - if (q->mq_ops && q->elevator) + if (q->elevator) len += sprintf(name+len, "none"); len += sprintf(len+name, "\n"); diff --git a/block/genhd.c b/block/genhd.c index cff6bdf27226..0145bcb0cc76 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -47,7 +47,7 @@ static void disk_release_events(struct gendisk *disk); void part_inc_in_flight(struct request_queue *q, struct hd_struct *part, int rw) { - if (q->mq_ops) + if (queue_is_mq(q)) return; atomic_inc(&part->in_flight[rw]); @@ -57,7 +57,7 @@ void part_inc_in_flight(struct request_queue *q, struct hd_struct *part, int rw) void part_dec_in_flight(struct request_queue *q, struct hd_struct *part, int rw) { - if (q->mq_ops) + if (queue_is_mq(q)) return; atomic_dec(&part->in_flight[rw]); @@ -68,7 +68,7 @@ void part_dec_in_flight(struct request_queue *q, struct hd_struct *part, int rw) void part_in_flight(struct request_queue *q, struct hd_struct *part, unsigned int inflight[2]) { - if (q->mq_ops) { + if (queue_is_mq(q)) { blk_mq_in_flight(q, part, inflight); return; } @@ -85,7 +85,7 @@ void part_in_flight(struct request_queue *q, struct hd_struct *part, void part_in_flight_rw(struct request_queue *q, struct hd_struct *part, unsigned int inflight[2]) { - if (q->mq_ops) { + if (queue_is_mq(q)) { blk_mq_in_flight_rw(q, part, inflight); return; } diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c index 7cd36e4d1310..1f1fe9a618ea 100644 --- a/drivers/md/dm-rq.c +++ b/drivers/md/dm-rq.c @@ -43,7 +43,7 @@ static unsigned dm_get_blk_mq_queue_depth(void) int dm_request_based(struct mapped_device *md) { - return queue_is_rq_based(md->queue); + return queue_is_mq(md->queue); } void dm_start_queue(struct request_queue *q) diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 9038c302d5c2..844f7d0f2ef8 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -919,12 +919,12 @@ static int device_is_rq_based(struct dm_target *ti, struct dm_dev *dev, struct request_queue *q = bdev_get_queue(dev->bdev); struct verify_rq_based_data *v = data; - if (q->mq_ops) + if (queue_is_mq(q)) v->mq_count++; else v->sq_count++; - return queue_is_rq_based(q); + return queue_is_mq(q); } static int dm_table_determine_type(struct dm_table *t) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1d185f1fc333..41aaa05e42c1 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -656,11 +656,7 @@ static inline bool blk_account_rq(struct request *rq) #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) -/* - * Driver can handle struct request, if it either has an old style - * request_fn defined, or is blk-mq based. - */ -static inline bool queue_is_rq_based(struct request_queue *q) +static inline bool queue_is_mq(struct request_queue *q) { return q->mq_ops; } -- cgit v1.2.3-71-gd317 From 0619317ff8baa2da9238191ad5167ed3618c16d9 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 13 Nov 2018 21:16:54 -0700 Subject: block: add polled wakeup task helper If we're polling for IO on a device that doesn't use interrupts, then IO completion loop (and wake of task) is done by submitting task itself. If that is the case, then we don't need to enter the wake_up_process() function, we can simply mark ourselves as TASK_RUNNING. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/block_dev.c | 4 ++-- fs/iomap.c | 2 +- include/linux/blkdev.h | 13 +++++++++++++ mm/page_io.c | 2 +- 4 files changed, 17 insertions(+), 4 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/fs/block_dev.c b/fs/block_dev.c index c039abfb2052..9fe56672cfe5 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -181,7 +181,7 @@ static void blkdev_bio_end_io_simple(struct bio *bio) struct task_struct *waiter = bio->bi_private; WRITE_ONCE(bio->bi_private, NULL); - wake_up_process(waiter); + blk_wake_io_task(waiter); } static ssize_t @@ -305,7 +305,7 @@ static void blkdev_bio_end_io(struct bio *bio) struct task_struct *waiter = dio->waiter; WRITE_ONCE(dio->waiter, NULL); - wake_up_process(waiter); + blk_wake_io_task(waiter); } } diff --git a/fs/iomap.c b/fs/iomap.c index f61d13dfdf09..b0462b363bad 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1525,7 +1525,7 @@ static void iomap_dio_bio_end_io(struct bio *bio) if (dio->wait_for_completion) { struct task_struct *waiter = dio->submit.waiter; WRITE_ONCE(dio->submit.waiter, NULL); - wake_up_process(waiter); + blk_wake_io_task(waiter); } else if (dio->flags & IOMAP_DIO_WRITE) { struct inode *inode = file_inode(dio->iocb->ki_filp); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 41aaa05e42c1..91c44f7a7f62 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1772,4 +1772,17 @@ static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask, #endif /* CONFIG_BLOCK */ +static inline void blk_wake_io_task(struct task_struct *waiter) +{ + /* + * If we're polling, the task itself is doing the completions. For + * that case, we don't need to signal a wakeup, it's enough to just + * mark us as RUNNING. + */ + if (waiter == current) + __set_current_state(TASK_RUNNING); + else + wake_up_process(waiter); +} + #endif diff --git a/mm/page_io.c b/mm/page_io.c index d4d1c89bcddd..57572ff46016 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -140,7 +140,7 @@ out: unlock_page(page); WRITE_ONCE(bio->bi_private, NULL); bio_put(bio); - wake_up_process(waiter); + blk_wake_io_task(waiter); put_task_struct(waiter); } -- cgit v1.2.3-71-gd317 From 2b78eae147a13ab2ca7caa121dd3fca2eecf8613 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 16 Nov 2018 09:10:01 +0100 Subject: block: remove the rq_alloc_data request_queue field Reviewed-by: Omar Sandoval Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 91c44f7a7f62..1ad6eafc43f2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -567,7 +567,6 @@ struct request_queue { bool mq_sysfs_init_done; size_t cmd_size; - void *rq_alloc_data; struct work_struct release_work; -- cgit v1.2.3-71-gd317 From 85f4d4b65fdd67f1d6dc9eeb1d91923cef07eb6a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 6 Nov 2018 13:30:55 -0700 Subject: block: have ->poll_fn() return number of entries polled We currently only really support sync poll, ie poll with 1 IO in flight. This prepares us for supporting async poll. Note that the returned value isn't necessarily 100% accurate. If poll races with IRQ completion, we assume that the fact that the task is now runnable means we found at least one entry. In reality it could be more than 1, or not even 1. This is fine, the caller will just need to take this into account. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-mq.c | 18 +++++++++--------- drivers/nvme/host/multipath.c | 4 ++-- include/linux/blkdev.h | 2 +- 3 files changed, 12 insertions(+), 12 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-mq.c b/block/blk-mq.c index 7fc4abb4cc36..52b1c97cd7c6 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -38,7 +38,7 @@ #include "blk-mq-sched.h" #include "blk-rq-qos.h" -static bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie); +static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie); static void blk_mq_poll_stats_start(struct request_queue *q); static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb); @@ -3305,7 +3305,7 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q, return true; } -static bool __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq) +static int __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq) { struct request_queue *q = hctx->queue; long state; @@ -3318,7 +3318,7 @@ static bool __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq) * straight to the busy poll loop. */ if (blk_mq_poll_hybrid_sleep(q, hctx, rq)) - return true; + return 1; hctx->poll_considered++; @@ -3332,30 +3332,30 @@ static bool __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq) if (ret > 0) { hctx->poll_success++; __set_current_state(TASK_RUNNING); - return true; + return ret; } if (signal_pending_state(state, current)) __set_current_state(TASK_RUNNING); if (current->state == TASK_RUNNING) - return true; + return 1; if (ret < 0) break; cpu_relax(); } __set_current_state(TASK_RUNNING); - return false; + return 0; } -static bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie) +static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie) { struct blk_mq_hw_ctx *hctx; struct request *rq; if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) - return false; + return 0; hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)]; if (!blk_qc_t_is_internal(cookie)) @@ -3369,7 +3369,7 @@ static bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie) * so we should be safe with just the NULL check. */ if (!rq) - return false; + return 0; } return __blk_mq_poll(hctx, rq); diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 8b841f39734c..f9eeb3b58632 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -220,11 +220,11 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q, return ret; } -static bool nvme_ns_head_poll(struct request_queue *q, blk_qc_t qc) +static int nvme_ns_head_poll(struct request_queue *q, blk_qc_t qc) { struct nvme_ns_head *head = q->queuedata; struct nvme_ns *ns; - bool found = false; + int found = 0; int srcu_idx; srcu_idx = srcu_read_lock(&head->srcu); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1ad6eafc43f2..e97c0a3b2262 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -283,7 +283,7 @@ static inline unsigned short req_get_ioprio(struct request *req) struct blk_queue_ctx; typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); -typedef bool (poll_q_fn) (struct request_queue *q, blk_qc_t); +typedef int (poll_q_fn) (struct request_queue *q, blk_qc_t); struct bio_vec; typedef int (dma_drain_needed_fn)(struct request *); -- cgit v1.2.3-71-gd317 From 1db4909e76f64a85f4aaa187f0f683f5c85a471d Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 20 Nov 2018 09:44:35 +0800 Subject: blk-mq: not embed .mq_kobj and ctx->kobj into queue instance Even though .mq_kobj, ctx->kobj and q->kobj share same lifetime from block layer's view, actually they don't because userspace may grab one kobject anytime via sysfs. This patch fixes the issue by the following approach: 1) introduce 'struct blk_mq_ctxs' for holding .mq_kobj and managing all ctxs 2) free all allocated ctxs and the 'blk_mq_ctxs' instance in release handler of .mq_kobj 3) grab one ref of .mq_kobj before initializing each ctx->kobj, so that .mq_kobj is always released after all ctxs are freed. This patch fixes kernel panic issue during booting when DEBUG_KOBJECT_RELEASE is enabled. Reported-by: Guenter Roeck Cc: "jianchao.wang" Tested-by: Guenter Roeck Reviewed-by: Greg Kroah-Hartman Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-mq-sysfs.c | 34 ++++++++++++++++++++++++---------- block/blk-mq.c | 39 ++++++++++++++++++++++++++++++++------- block/blk-mq.h | 6 ++++++ include/linux/blkdev.h | 2 +- 4 files changed, 63 insertions(+), 18 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index 3d25b9c419e9..6efef1f679f0 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -15,6 +15,18 @@ static void blk_mq_sysfs_release(struct kobject *kobj) { + struct blk_mq_ctxs *ctxs = container_of(kobj, struct blk_mq_ctxs, kobj); + + free_percpu(ctxs->queue_ctx); + kfree(ctxs); +} + +static void blk_mq_ctx_sysfs_release(struct kobject *kobj) +{ + struct blk_mq_ctx *ctx = container_of(kobj, struct blk_mq_ctx, kobj); + + /* ctx->ctxs won't be released until all ctx are freed */ + kobject_put(&ctx->ctxs->kobj); } static void blk_mq_hw_sysfs_release(struct kobject *kobj) @@ -213,7 +225,7 @@ static struct kobj_type blk_mq_ktype = { static struct kobj_type blk_mq_ctx_ktype = { .sysfs_ops = &blk_mq_sysfs_ops, .default_attrs = default_ctx_attrs, - .release = blk_mq_sysfs_release, + .release = blk_mq_ctx_sysfs_release, }; static struct kobj_type blk_mq_hw_ktype = { @@ -245,7 +257,7 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx) if (!hctx->nr_ctx) return 0; - ret = kobject_add(&hctx->kobj, &q->mq_kobj, "%u", hctx->queue_num); + ret = kobject_add(&hctx->kobj, q->mq_kobj, "%u", hctx->queue_num); if (ret) return ret; @@ -268,8 +280,8 @@ void blk_mq_unregister_dev(struct device *dev, struct request_queue *q) queue_for_each_hw_ctx(q, hctx, i) blk_mq_unregister_hctx(hctx); - kobject_uevent(&q->mq_kobj, KOBJ_REMOVE); - kobject_del(&q->mq_kobj); + kobject_uevent(q->mq_kobj, KOBJ_REMOVE); + kobject_del(q->mq_kobj); kobject_put(&dev->kobj); q->mq_sysfs_init_done = false; @@ -289,7 +301,7 @@ void blk_mq_sysfs_deinit(struct request_queue *q) ctx = per_cpu_ptr(q->queue_ctx, cpu); kobject_put(&ctx->kobj); } - kobject_put(&q->mq_kobj); + kobject_put(q->mq_kobj); } void blk_mq_sysfs_init(struct request_queue *q) @@ -297,10 +309,12 @@ void blk_mq_sysfs_init(struct request_queue *q) struct blk_mq_ctx *ctx; int cpu; - kobject_init(&q->mq_kobj, &blk_mq_ktype); + kobject_init(q->mq_kobj, &blk_mq_ktype); for_each_possible_cpu(cpu) { ctx = per_cpu_ptr(q->queue_ctx, cpu); + + kobject_get(q->mq_kobj); kobject_init(&ctx->kobj, &blk_mq_ctx_ktype); } } @@ -313,11 +327,11 @@ int __blk_mq_register_dev(struct device *dev, struct request_queue *q) WARN_ON_ONCE(!q->kobj.parent); lockdep_assert_held(&q->sysfs_lock); - ret = kobject_add(&q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq"); + ret = kobject_add(q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq"); if (ret < 0) goto out; - kobject_uevent(&q->mq_kobj, KOBJ_ADD); + kobject_uevent(q->mq_kobj, KOBJ_ADD); queue_for_each_hw_ctx(q, hctx, i) { ret = blk_mq_register_hctx(hctx); @@ -334,8 +348,8 @@ unreg: while (--i >= 0) blk_mq_unregister_hctx(q->queue_hw_ctx[i]); - kobject_uevent(&q->mq_kobj, KOBJ_REMOVE); - kobject_del(&q->mq_kobj); + kobject_uevent(q->mq_kobj, KOBJ_REMOVE); + kobject_del(q->mq_kobj); kobject_put(&dev->kobj); return ret; } diff --git a/block/blk-mq.c b/block/blk-mq.c index 174384eaace7..b16204df65d1 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2515,6 +2515,34 @@ static void blk_mq_add_queue_tag_set(struct blk_mq_tag_set *set, mutex_unlock(&set->tag_list_lock); } +/* All allocations will be freed in release handler of q->mq_kobj */ +static int blk_mq_alloc_ctxs(struct request_queue *q) +{ + struct blk_mq_ctxs *ctxs; + int cpu; + + ctxs = kzalloc(sizeof(*ctxs), GFP_KERNEL); + if (!ctxs) + return -ENOMEM; + + ctxs->queue_ctx = alloc_percpu(struct blk_mq_ctx); + if (!ctxs->queue_ctx) + goto fail; + + for_each_possible_cpu(cpu) { + struct blk_mq_ctx *ctx = per_cpu_ptr(ctxs->queue_ctx, cpu); + ctx->ctxs = ctxs; + } + + q->mq_kobj = &ctxs->kobj; + q->queue_ctx = ctxs->queue_ctx; + + return 0; + fail: + kfree(ctxs); + return -ENOMEM; +} + /* * It is the actual release handler for mq, but we do it from * request queue's release handler for avoiding use-after-free @@ -2540,8 +2568,6 @@ void blk_mq_release(struct request_queue *q) * both share lifetime with request queue. */ blk_mq_sysfs_deinit(q); - - free_percpu(q->queue_ctx); } struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) @@ -2731,8 +2757,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, if (!q->poll_cb) goto err_exit; - q->queue_ctx = alloc_percpu(struct blk_mq_ctx); - if (!q->queue_ctx) + if (blk_mq_alloc_ctxs(q)) goto err_exit; /* init q->mq_kobj and sw queues' kobjects */ @@ -2742,7 +2767,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, q->queue_hw_ctx = kcalloc_node(q->nr_queues, sizeof(*(q->queue_hw_ctx)), GFP_KERNEL, set->numa_node); if (!q->queue_hw_ctx) - goto err_percpu; + goto err_sys_init; blk_mq_realloc_hw_ctxs(set, q); if (!q->nr_hw_queues) @@ -2794,8 +2819,8 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, err_hctxs: kfree(q->queue_hw_ctx); -err_percpu: - free_percpu(q->queue_ctx); +err_sys_init: + blk_mq_sysfs_deinit(q); err_exit: q->mq_ops = NULL; return ERR_PTR(-ENOMEM); diff --git a/block/blk-mq.h b/block/blk-mq.h index facb6e9ddce4..9ae8e9f8f8b1 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -7,6 +7,11 @@ struct blk_mq_tag_set; +struct blk_mq_ctxs { + struct kobject kobj; + struct blk_mq_ctx __percpu *queue_ctx; +}; + /** * struct blk_mq_ctx - State for a software queue facing the submitting CPUs */ @@ -27,6 +32,7 @@ struct blk_mq_ctx { unsigned long ____cacheline_aligned_in_smp rq_completed[2]; struct request_queue *queue; + struct blk_mq_ctxs *ctxs; struct kobject kobj; } ____cacheline_aligned_in_smp; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e97c0a3b2262..9b53db06ad08 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -456,7 +456,7 @@ struct request_queue { /* * mq queue kobject */ - struct kobject mq_kobj; + struct kobject *mq_kobj; #ifdef CONFIG_BLK_DEV_INTEGRITY struct blk_integrity integrity; -- cgit v1.2.3-71-gd317 From 1052b8ac5282daf35df331edcbdb645839d17e6a Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 26 Nov 2018 08:21:49 -0700 Subject: blk-mq: when polling for IO, look for any completion If we want to support async IO polling, then we have to allow finding completions that aren't just for the one we are looking for. Always pass in -1 to the mq_ops->poll() helper, and have that return how many events were found in this poll loop. Signed-off-by: Jens Axboe --- block/blk-core.c | 13 +++++++-- block/blk-mq.c | 71 ++++++++++++++++++++++++------------------------ drivers/nvme/host/pci.c | 14 +++++----- drivers/nvme/host/rdma.c | 39 ++++++++++---------------- include/linux/blkdev.h | 2 +- 5 files changed, 70 insertions(+), 69 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 04f5be473638..03c4202b69bf 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1273,10 +1273,19 @@ blk_qc_t submit_bio(struct bio *bio) } EXPORT_SYMBOL(submit_bio); -bool blk_poll(struct request_queue *q, blk_qc_t cookie) +/** + * blk_poll - poll for IO completions + * @q: the queue + * @cookie: cookie passed back at IO submission time + * + * Description: + * Poll for completions on the passed in queue. Returns number of + * completed entries found. + */ +int blk_poll(struct request_queue *q, blk_qc_t cookie) { if (!q->poll_fn || !blk_qc_t_valid(cookie)) - return false; + return 0; if (current->plug) blk_flush_plug_list(current->plug, false); diff --git a/block/blk-mq.c b/block/blk-mq.c index b16204df65d1..ec6c79578332 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -3285,15 +3285,12 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q, return false; /* - * poll_nsec can be: + * If we get here, hybrid polling is enabled. Hence poll_nsec can be: * - * -1: don't ever hybrid sleep * 0: use half of prev avg * >0: use this specific value */ - if (q->poll_nsec == -1) - return false; - else if (q->poll_nsec > 0) + if (q->poll_nsec > 0) nsecs = q->poll_nsec; else nsecs = blk_mq_poll_nsecs(q, hctx, rq); @@ -3330,11 +3327,41 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q, return true; } -static int __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq) +static bool blk_mq_poll_hybrid(struct request_queue *q, + struct blk_mq_hw_ctx *hctx, blk_qc_t cookie) { - struct request_queue *q = hctx->queue; + struct request *rq; + + if (q->poll_nsec == -1) + return false; + + if (!blk_qc_t_is_internal(cookie)) + rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie)); + else { + rq = blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(cookie)); + /* + * With scheduling, if the request has completed, we'll + * get a NULL return here, as we clear the sched tag when + * that happens. The request still remains valid, like always, + * so we should be safe with just the NULL check. + */ + if (!rq) + return false; + } + + return blk_mq_poll_hybrid_sleep(q, hctx, rq); +} + +static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie) +{ + struct blk_mq_hw_ctx *hctx; long state; + if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) + return 0; + + hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)]; + /* * If we sleep, have the caller restart the poll loop to reset * the state. Like for the other success return cases, the @@ -3342,7 +3369,7 @@ static int __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq) * the IO isn't complete, we'll get called again and will go * straight to the busy poll loop. */ - if (blk_mq_poll_hybrid_sleep(q, hctx, rq)) + if (blk_mq_poll_hybrid(q, hctx, cookie)) return 1; hctx->poll_considered++; @@ -3353,7 +3380,7 @@ static int __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq) hctx->poll_invoked++; - ret = q->mq_ops->poll(hctx, rq->tag); + ret = q->mq_ops->poll(hctx, -1U); if (ret > 0) { hctx->poll_success++; __set_current_state(TASK_RUNNING); @@ -3374,32 +3401,6 @@ static int __blk_mq_poll(struct blk_mq_hw_ctx *hctx, struct request *rq) return 0; } -static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie) -{ - struct blk_mq_hw_ctx *hctx; - struct request *rq; - - if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) - return 0; - - hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)]; - if (!blk_qc_t_is_internal(cookie)) - rq = blk_mq_tag_to_rq(hctx->tags, blk_qc_t_to_tag(cookie)); - else { - rq = blk_mq_tag_to_rq(hctx->sched_tags, blk_qc_t_to_tag(cookie)); - /* - * With scheduling, if the request has completed, we'll - * get a NULL return here, as we clear the sched tag when - * that happens. The request still remains valid, like always, - * so we should be safe with just the NULL check. - */ - if (!rq) - return 0; - } - - return __blk_mq_poll(hctx, rq); -} - unsigned int blk_mq_rq_cpu(struct request *rq) { return rq->mq_ctx->cpu; diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 57e790391b82..de50d80ecc84 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -1012,15 +1012,15 @@ static inline void nvme_update_cq_head(struct nvme_queue *nvmeq) } } -static inline bool nvme_process_cq(struct nvme_queue *nvmeq, u16 *start, - u16 *end, int tag) +static inline int nvme_process_cq(struct nvme_queue *nvmeq, u16 *start, + u16 *end, unsigned int tag) { - bool found = false; + int found = 0; *start = nvmeq->cq_head; - while (!found && nvme_cqe_pending(nvmeq)) { - if (nvmeq->cqes[nvmeq->cq_head].command_id == tag) - found = true; + while (nvme_cqe_pending(nvmeq)) { + if (tag == -1U || nvmeq->cqes[nvmeq->cq_head].command_id == tag) + found++; nvme_update_cq_head(nvmeq); } *end = nvmeq->cq_head; @@ -1062,7 +1062,7 @@ static irqreturn_t nvme_irq_check(int irq, void *data) static int __nvme_poll(struct nvme_queue *nvmeq, unsigned int tag) { u16 start, end; - bool found; + int found; if (!nvme_cqe_pending(nvmeq)) return 0; diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c index d181cafedc58..c2c3e1a5b7af 100644 --- a/drivers/nvme/host/rdma.c +++ b/drivers/nvme/host/rdma.c @@ -1409,12 +1409,11 @@ static void nvme_rdma_submit_async_event(struct nvme_ctrl *arg) WARN_ON_ONCE(ret); } -static int nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue, - struct nvme_completion *cqe, struct ib_wc *wc, int tag) +static void nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue, + struct nvme_completion *cqe, struct ib_wc *wc) { struct request *rq; struct nvme_rdma_request *req; - int ret = 0; rq = blk_mq_tag_to_rq(nvme_rdma_tagset(queue), cqe->command_id); if (!rq) { @@ -1422,7 +1421,7 @@ static int nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue, "tag 0x%x on QP %#x not found\n", cqe->command_id, queue->qp->qp_num); nvme_rdma_error_recovery(queue->ctrl); - return ret; + return; } req = blk_mq_rq_to_pdu(rq); @@ -1437,6 +1436,8 @@ static int nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue, nvme_rdma_error_recovery(queue->ctrl); } } else if (req->mr) { + int ret; + ret = nvme_rdma_inv_rkey(queue, req); if (unlikely(ret < 0)) { dev_err(queue->ctrl->ctrl.device, @@ -1445,19 +1446,14 @@ static int nvme_rdma_process_nvme_rsp(struct nvme_rdma_queue *queue, nvme_rdma_error_recovery(queue->ctrl); } /* the local invalidation completion will end the request */ - return 0; + return; } - if (refcount_dec_and_test(&req->ref)) { - if (rq->tag == tag) - ret = 1; + if (refcount_dec_and_test(&req->ref)) nvme_end_request(rq, req->status, req->result); - } - - return ret; } -static int __nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc, int tag) +static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc) { struct nvme_rdma_qe *qe = container_of(wc->wr_cqe, struct nvme_rdma_qe, cqe); @@ -1465,11 +1461,10 @@ static int __nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc, int tag) struct ib_device *ibdev = queue->device->dev; struct nvme_completion *cqe = qe->data; const size_t len = sizeof(struct nvme_completion); - int ret = 0; if (unlikely(wc->status != IB_WC_SUCCESS)) { nvme_rdma_wr_error(cq, wc, "RECV"); - return 0; + return; } ib_dma_sync_single_for_cpu(ibdev, qe->dma, len, DMA_FROM_DEVICE); @@ -1484,16 +1479,10 @@ static int __nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc, int tag) nvme_complete_async_event(&queue->ctrl->ctrl, cqe->status, &cqe->result); else - ret = nvme_rdma_process_nvme_rsp(queue, cqe, wc, tag); + nvme_rdma_process_nvme_rsp(queue, cqe, wc); ib_dma_sync_single_for_device(ibdev, qe->dma, len, DMA_FROM_DEVICE); nvme_rdma_post_recv(queue, qe); - return ret; -} - -static void nvme_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc) -{ - __nvme_rdma_recv_done(cq, wc, -1); } static int nvme_rdma_conn_established(struct nvme_rdma_queue *queue) @@ -1758,10 +1747,12 @@ static int nvme_rdma_poll(struct blk_mq_hw_ctx *hctx, unsigned int tag) struct ib_cqe *cqe = wc.wr_cqe; if (cqe) { - if (cqe->done == nvme_rdma_recv_done) - found |= __nvme_rdma_recv_done(cq, &wc, tag); - else + if (cqe->done == nvme_rdma_recv_done) { + nvme_rdma_recv_done(cq, &wc); + found++; + } else { cqe->done(cq, &wc); + } } } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 9b53db06ad08..f3015e9b5ae3 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -867,7 +867,7 @@ extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, int blk_status_to_errno(blk_status_t status); blk_status_t errno_to_blk_status(int errno); -bool blk_poll(struct request_queue *q, blk_qc_t cookie); +int blk_poll(struct request_queue *q, blk_qc_t cookie); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { -- cgit v1.2.3-71-gd317 From 0a1b8b87d064a47fad9ec475316002da28559207 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Mon, 26 Nov 2018 08:24:43 -0700 Subject: block: make blk_poll() take a parameter on whether to spin or not blk_poll() has always kept spinning until it found an IO. This is fine for SYNC polling, since we need to find one request we have pending, but in preparation for ASYNC polling it can be beneficial to just check if we have any entries available or not. Existing callers are converted to pass in 'spin == true', to retain the old behavior. Signed-off-by: Jens Axboe --- block/blk-core.c | 9 ++++++--- block/blk-mq.c | 6 +++--- drivers/nvme/host/multipath.c | 4 ++-- fs/block_dev.c | 4 ++-- fs/direct-io.c | 2 +- fs/iomap.c | 2 +- include/linux/blkdev.h | 4 ++-- mm/page_io.c | 2 +- 8 files changed, 18 insertions(+), 15 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 03c4202b69bf..9af56dbb84f1 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1277,19 +1277,22 @@ EXPORT_SYMBOL(submit_bio); * blk_poll - poll for IO completions * @q: the queue * @cookie: cookie passed back at IO submission time + * @spin: whether to spin for completions * * Description: * Poll for completions on the passed in queue. Returns number of - * completed entries found. + * completed entries found. If @spin is true, then blk_poll will continue + * looping until at least one completion is found, unless the task is + * otherwise marked running (or we need to reschedule). */ -int blk_poll(struct request_queue *q, blk_qc_t cookie) +int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin) { if (!q->poll_fn || !blk_qc_t_valid(cookie)) return 0; if (current->plug) blk_flush_plug_list(current->plug, false); - return q->poll_fn(q, cookie); + return q->poll_fn(q, cookie, spin); } EXPORT_SYMBOL_GPL(blk_poll); diff --git a/block/blk-mq.c b/block/blk-mq.c index b66cca3ce1e5..c2751f0a3ccc 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -38,7 +38,7 @@ #include "blk-mq-sched.h" #include "blk-rq-qos.h" -static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie); +static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, bool spin); static void blk_mq_poll_stats_start(struct request_queue *q); static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb); @@ -3352,7 +3352,7 @@ static bool blk_mq_poll_hybrid(struct request_queue *q, return blk_mq_poll_hybrid_sleep(q, hctx, rq); } -static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie) +static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, bool spin) { struct blk_mq_hw_ctx *hctx; long state; @@ -3392,7 +3392,7 @@ static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie) if (current->state == TASK_RUNNING) return 1; - if (ret < 0) + if (ret < 0 || !spin) break; cpu_relax(); } diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index f9eeb3b58632..ffebdd0ae34b 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -220,7 +220,7 @@ static blk_qc_t nvme_ns_head_make_request(struct request_queue *q, return ret; } -static int nvme_ns_head_poll(struct request_queue *q, blk_qc_t qc) +static int nvme_ns_head_poll(struct request_queue *q, blk_qc_t qc, bool spin) { struct nvme_ns_head *head = q->queuedata; struct nvme_ns *ns; @@ -230,7 +230,7 @@ static int nvme_ns_head_poll(struct request_queue *q, blk_qc_t qc) srcu_idx = srcu_read_lock(&head->srcu); ns = srcu_dereference(head->current_path[numa_node_id()], &head->srcu); if (likely(ns && nvme_path_is_optimized(ns))) - found = ns->queue->poll_fn(q, qc); + found = ns->queue->poll_fn(q, qc, spin); srcu_read_unlock(&head->srcu, srcu_idx); return found; } diff --git a/fs/block_dev.c b/fs/block_dev.c index 64ba27b8b754..d233a59ea364 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -243,7 +243,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter, break; if (!(iocb->ki_flags & IOCB_HIPRI) || - !blk_poll(bdev_get_queue(bdev), qc)) + !blk_poll(bdev_get_queue(bdev), qc, true)) io_schedule(); } __set_current_state(TASK_RUNNING); @@ -423,7 +423,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) break; if (!(iocb->ki_flags & IOCB_HIPRI) || - !blk_poll(bdev_get_queue(bdev), qc)) + !blk_poll(bdev_get_queue(bdev), qc, true)) io_schedule(); } __set_current_state(TASK_RUNNING); diff --git a/fs/direct-io.c b/fs/direct-io.c index ea07d5a34317..a5a4e5a1423e 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -518,7 +518,7 @@ static struct bio *dio_await_one(struct dio *dio) dio->waiter = current; spin_unlock_irqrestore(&dio->bio_lock, flags); if (!(dio->iocb->ki_flags & IOCB_HIPRI) || - !blk_poll(dio->bio_disk->queue, dio->bio_cookie)) + !blk_poll(dio->bio_disk->queue, dio->bio_cookie, true)) io_schedule(); /* wake up sets us TASK_RUNNING */ spin_lock_irqsave(&dio->bio_lock, flags); diff --git a/fs/iomap.c b/fs/iomap.c index c5df035ace6f..74c1f37f0fd6 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1896,7 +1896,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (!(iocb->ki_flags & IOCB_HIPRI) || !dio->submit.last_queue || !blk_poll(dio->submit.last_queue, - dio->submit.cookie)) + dio->submit.cookie, true)) io_schedule(); } __set_current_state(TASK_RUNNING); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f3015e9b5ae3..e3c0a8ec16a7 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -283,7 +283,7 @@ static inline unsigned short req_get_ioprio(struct request *req) struct blk_queue_ctx; typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); -typedef int (poll_q_fn) (struct request_queue *q, blk_qc_t); +typedef int (poll_q_fn) (struct request_queue *q, blk_qc_t, bool spin); struct bio_vec; typedef int (dma_drain_needed_fn)(struct request *); @@ -867,7 +867,7 @@ extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, int blk_status_to_errno(blk_status_t status); blk_status_t errno_to_blk_status(int errno); -int blk_poll(struct request_queue *q, blk_qc_t cookie); +int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { diff --git a/mm/page_io.c b/mm/page_io.c index a7271fa481f6..5bdfd21c1bd9 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -410,7 +410,7 @@ int swap_readpage(struct page *page, bool synchronous) if (!READ_ONCE(bio->bi_private)) break; - if (!blk_poll(disk->queue, qc)) + if (!blk_poll(disk->queue, qc, true)) break; } __set_current_state(TASK_RUNNING); -- cgit v1.2.3-71-gd317 From 5f0ed774ed2914decfd397569fface997532e94d Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 23 Nov 2018 22:04:33 -0700 Subject: block: sum requests in the plug structure This isn't exactly the same as the previous count, as it includes requests for all devices. But that really doesn't matter, if we have more than the threshold (16) queued up, flush it. It's not worth it to have an expensive list loop for this. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 30 ++++-------------------------- block/blk-mq.c | 16 +++++----------- block/blk.h | 2 -- include/linux/blkdev.h | 1 + 4 files changed, 10 insertions(+), 39 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index 9af56dbb84f1..be9233400314 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -736,7 +736,6 @@ no_merge: * Caller must ensure !blk_queue_nomerges(q) beforehand. */ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, - unsigned int *request_count, struct request **same_queue_rq) { struct blk_plug *plug; @@ -746,22 +745,19 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, plug = current->plug; if (!plug) return false; - *request_count = 0; plug_list = &plug->mq_list; list_for_each_entry_reverse(rq, plug_list, queuelist) { bool merged = false; - if (rq->q == q) { - (*request_count)++; + if (rq->q == q && same_queue_rq) { /* * Only blk-mq multiple hardware queues case checks the * rq in the same queue, there should be only one such * rq in a queue **/ - if (same_queue_rq) - *same_queue_rq = rq; + *same_queue_rq = rq; } if (rq->q != q || !blk_rq_merge_ok(rq, bio)) @@ -788,26 +784,6 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, return false; } -unsigned int blk_plug_queued_count(struct request_queue *q) -{ - struct blk_plug *plug; - struct request *rq; - struct list_head *plug_list; - unsigned int ret = 0; - - plug = current->plug; - if (!plug) - goto out; - - plug_list = &plug->mq_list; - list_for_each_entry(rq, plug_list, queuelist) { - if (rq->q == q) - ret++; - } -out: - return ret; -} - void blk_init_request_from_bio(struct request *req, struct bio *bio) { if (bio->bi_opf & REQ_RAHEAD) @@ -1803,6 +1779,8 @@ void blk_start_plug(struct blk_plug *plug) INIT_LIST_HEAD(&plug->mq_list); INIT_LIST_HEAD(&plug->cb_list); + plug->rq_count = 0; + /* * Store ordering should not be needed here, since a potential * preempt will imply a full memory barrier diff --git a/block/blk-mq.c b/block/blk-mq.c index cda698804422..7b7dff85cf6c 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1675,6 +1675,7 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) unsigned int depth; list_splice_init(&plug->mq_list, &list); + plug->rq_count = 0; list_sort(NULL, &list, plug_rq_cmp); @@ -1871,7 +1872,6 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) const int is_flush_fua = op_is_flush(bio->bi_opf); struct blk_mq_alloc_data data = { .flags = 0, .cmd_flags = bio->bi_opf }; struct request *rq; - unsigned int request_count = 0; struct blk_plug *plug; struct request *same_queue_rq = NULL; blk_qc_t cookie; @@ -1884,7 +1884,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) return BLK_QC_T_NONE; if (!is_flush_fua && !blk_queue_nomerges(q) && - blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq)) + blk_attempt_plug_merge(q, bio, &same_queue_rq)) return BLK_QC_T_NONE; if (blk_mq_sched_bio_merge(q, bio)) @@ -1915,20 +1915,12 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) blk_insert_flush(rq); blk_mq_run_hw_queue(data.hctx, true); } else if (plug && q->nr_hw_queues == 1) { + unsigned int request_count = plug->rq_count; struct request *last = NULL; blk_mq_put_ctx(data.ctx); blk_mq_bio_to_request(rq, bio); - /* - * @request_count may become stale because of schedule - * out, so check the list again. - */ - if (list_empty(&plug->mq_list)) - request_count = 0; - else if (blk_queue_nomerges(q)) - request_count = blk_plug_queued_count(q); - if (!request_count) trace_block_plug(q); else @@ -1941,6 +1933,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) } list_add_tail(&rq->queuelist, &plug->mq_list); + plug->rq_count++; } else if (plug && !blk_queue_nomerges(q)) { blk_mq_bio_to_request(rq, bio); @@ -1956,6 +1949,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) if (same_queue_rq) list_del_init(&same_queue_rq->queuelist); list_add_tail(&rq->queuelist, &plug->mq_list); + plug->rq_count++; blk_mq_put_ctx(data.ctx); diff --git a/block/blk.h b/block/blk.h index 610948157a5b..848278c52030 100644 --- a/block/blk.h +++ b/block/blk.h @@ -161,9 +161,7 @@ bool bio_attempt_back_merge(struct request_queue *q, struct request *req, bool bio_attempt_discard_merge(struct request_queue *q, struct request *req, struct bio *bio); bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, - unsigned int *request_count, struct request **same_queue_rq); -unsigned int blk_plug_queued_count(struct request_queue *q); void blk_account_io_start(struct request *req, bool new_io); void blk_account_io_completion(struct request *req, unsigned int bytes); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e3c0a8ec16a7..02732cae6080 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1130,6 +1130,7 @@ extern void blk_set_queue_dying(struct request_queue *); struct blk_plug { struct list_head mq_list; /* blk-mq requests */ struct list_head cb_list; /* md requires an unplug callback */ + unsigned short rq_count; }; #define BLK_MAX_REQUEST_COUNT 16 #define BLK_PLUG_FLUSH_SIZE (128 * 1024) -- cgit v1.2.3-71-gd317 From ce5b009cff1961137127edf91f44effd0eec8ffd Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 27 Nov 2018 17:13:56 -0700 Subject: block: improve logic around when to sort a plug list Only do it if we have requests for multiple queues in the same plug. Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 1 + block/blk-mq.c | 23 ++++++++++++++++++----- include/linux/blkdev.h | 1 + 3 files changed, 20 insertions(+), 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index be9233400314..d107d016b92b 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1780,6 +1780,7 @@ void blk_start_plug(struct blk_plug *plug) INIT_LIST_HEAD(&plug->mq_list); INIT_LIST_HEAD(&plug->cb_list); plug->rq_count = 0; + plug->multiple_queues = false; /* * Store ordering should not be needed here, since a potential diff --git a/block/blk-mq.c b/block/blk-mq.c index 5f4b93f424b4..2a1a653a8054 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1677,7 +1677,8 @@ void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule) list_splice_init(&plug->mq_list, &list); plug->rq_count = 0; - list_sort(NULL, &list, plug_rq_cmp); + if (plug->rq_count > 2 && plug->multiple_queues) + list_sort(NULL, &list, plug_rq_cmp); this_q = NULL; this_hctx = NULL; @@ -1866,6 +1867,20 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx, } } +static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq) +{ + list_add_tail(&rq->queuelist, &plug->mq_list); + plug->rq_count++; + if (!plug->multiple_queues && !list_is_singular(&plug->mq_list)) { + struct request *tmp; + + tmp = list_first_entry(&plug->mq_list, struct request, + queuelist); + if (tmp->q != rq->q) + plug->multiple_queues = true; + } +} + static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) { const int is_sync = op_is_sync(bio->bi_opf); @@ -1932,8 +1947,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) trace_block_plug(q); } - list_add_tail(&rq->queuelist, &plug->mq_list); - plug->rq_count++; + blk_add_rq_to_plug(plug, rq); } else if (plug && !blk_queue_nomerges(q)) { blk_mq_bio_to_request(rq, bio); @@ -1950,8 +1964,7 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) list_del_init(&same_queue_rq->queuelist); plug->rq_count--; } - list_add_tail(&rq->queuelist, &plug->mq_list); - plug->rq_count++; + blk_add_rq_to_plug(plug, rq); blk_mq_put_ctx(data.ctx); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 02732cae6080..08d940f85fa0 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1131,6 +1131,7 @@ struct blk_plug { struct list_head mq_list; /* blk-mq requests */ struct list_head cb_list; /* md requires an unplug callback */ unsigned short rq_count; + bool multiple_queues; }; #define BLK_MAX_REQUEST_COUNT 16 #define BLK_PLUG_FLUSH_SIZE (128 * 1024) -- cgit v1.2.3-71-gd317 From 529262d56dbebe6a26df5d2fd24cc0e1bc8579e5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sun, 2 Dec 2018 17:46:26 +0100 Subject: block: remove ->poll_fn This was intended to support users like nvme multipath, but is just getting in the way and adding another indirect call. Reviewed-by: Sagi Grimberg Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- block/blk-core.c | 23 ----------------------- block/blk-mq.c | 24 +++++++++++++++++++----- include/linux/blkdev.h | 2 -- 3 files changed, 19 insertions(+), 30 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-core.c b/block/blk-core.c index a1a5e1c14898..ad59102ee30a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1250,29 +1250,6 @@ blk_qc_t submit_bio(struct bio *bio) } EXPORT_SYMBOL(submit_bio); -/** - * blk_poll - poll for IO completions - * @q: the queue - * @cookie: cookie passed back at IO submission time - * @spin: whether to spin for completions - * - * Description: - * Poll for completions on the passed in queue. Returns number of - * completed entries found. If @spin is true, then blk_poll will continue - * looping until at least one completion is found, unless the task is - * otherwise marked running (or we need to reschedule). - */ -int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin) -{ - if (!q->poll_fn || !blk_qc_t_valid(cookie)) - return 0; - - if (current->plug) - blk_flush_plug_list(current->plug, false); - return q->poll_fn(q, cookie, spin); -} -EXPORT_SYMBOL_GPL(blk_poll); - /** * blk_cloned_rq_check_limits - Helper function to check a cloned request * for new the queue limits diff --git a/block/blk-mq.c b/block/blk-mq.c index e09d7f500077..50d529602e05 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -38,7 +38,6 @@ #include "blk-mq-sched.h" #include "blk-rq-qos.h" -static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, bool spin); static void blk_mq_poll_stats_start(struct request_queue *q); static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb); @@ -2838,8 +2837,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, spin_lock_init(&q->requeue_lock); blk_queue_make_request(q, blk_mq_make_request); - if (q->mq_ops->poll) - q->poll_fn = blk_mq_poll; /* * Do this after blk_queue_make_request() overrides it... @@ -3400,14 +3397,30 @@ static bool blk_mq_poll_hybrid(struct request_queue *q, return blk_mq_poll_hybrid_sleep(q, hctx, rq); } -static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, bool spin) +/** + * blk_poll - poll for IO completions + * @q: the queue + * @cookie: cookie passed back at IO submission time + * @spin: whether to spin for completions + * + * Description: + * Poll for completions on the passed in queue. Returns number of + * completed entries found. If @spin is true, then blk_poll will continue + * looping until at least one completion is found, unless the task is + * otherwise marked running (or we need to reschedule). + */ +int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin) { struct blk_mq_hw_ctx *hctx; long state; - if (!test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) + if (!blk_qc_t_valid(cookie) || + !test_bit(QUEUE_FLAG_POLL, &q->queue_flags)) return 0; + if (current->plug) + blk_flush_plug_list(current->plug, false); + hctx = q->queue_hw_ctx[blk_qc_t_to_queue_num(cookie)]; /* @@ -3448,6 +3461,7 @@ static int blk_mq_poll(struct request_queue *q, blk_qc_t cookie, bool spin) __set_current_state(TASK_RUNNING); return 0; } +EXPORT_SYMBOL_GPL(blk_poll); unsigned int blk_mq_rq_cpu(struct request *rq) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 08d940f85fa0..0b3874bdbc6a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -283,7 +283,6 @@ static inline unsigned short req_get_ioprio(struct request *req) struct blk_queue_ctx; typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); -typedef int (poll_q_fn) (struct request_queue *q, blk_qc_t, bool spin); struct bio_vec; typedef int (dma_drain_needed_fn)(struct request *); @@ -401,7 +400,6 @@ struct request_queue { struct rq_qos *rq_qos; make_request_fn *make_request_fn; - poll_q_fn *poll_fn; dma_drain_needed_fn *dma_drain_needed; const struct blk_mq_ops *mq_ops; -- cgit v1.2.3-71-gd317 From 6e0de61107f03c3222550d9b548cd331d31d82d1 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 5 Dec 2018 06:50:40 -0700 Subject: blk-mq: remove QUEUE_FLAG_POLL from default MQ flags We only support polling if we have poll queues now, but the flag is being set by default. Remove the default QUEUE_FLAG_POLL setting, we'll set it in blk_mq_init_allocated_queue() if we have poll queues available for this device. Fixes: 6544d229bf43 ("block: enable polling by default if a poll map is initalized") Reported-by: Kirill Tkhai Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0b3874bdbc6a..81f1b105946b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -606,8 +606,7 @@ struct request_queue { (1 << QUEUE_FLAG_ADD_RANDOM)) #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_SAME_COMP) | \ - (1 << QUEUE_FLAG_POLL)) + (1 << QUEUE_FLAG_SAME_COMP)) void blk_queue_flag_set(unsigned int flag, struct request_queue *q); void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); -- cgit v1.2.3-71-gd317 From cc56694f132a8f5fa9334e3afe990de8c3378866 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Mon, 17 Dec 2018 09:46:00 +0800 Subject: blk-mq-debugfs: support rq_qos blk-mq-debugfs has been proved as very helpful for debug some tough issues, such as IO hang. We have seen blk-wbt related IO hang several times, even inside Red Hat BZ, there is such report not sovled yet, so this patch adds support debugfs on rq_qos. Cc: Bart Van Assche Cc: Omar Sandoval Cc: Christoph Hellwig Cc: Josef Bacik Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++++++ block/blk-mq-debugfs.h | 17 ++++++++++++++++ block/blk-rq-qos.c | 2 ++ block/blk-rq-qos.h | 24 ++++++++++++++++++++++ include/linux/blkdev.h | 1 + 5 files changed, 98 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index a32bb79d6c95..2793e91bc7a4 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -23,6 +23,7 @@ #include "blk-mq.h" #include "blk-mq-debugfs.h" #include "blk-mq-tag.h" +#include "blk-rq-qos.h" static void print_stat(struct seq_file *m, struct blk_rq_stat *stat) { @@ -856,6 +857,15 @@ int blk_mq_debugfs_register(struct request_queue *q) goto err; } + if (q->rq_qos) { + struct rq_qos *rqos = q->rq_qos; + + while (rqos) { + blk_mq_debugfs_register_rqos(rqos); + rqos = rqos->next; + } + } + return 0; err: @@ -978,6 +988,50 @@ void blk_mq_debugfs_unregister_sched(struct request_queue *q) q->sched_debugfs_dir = NULL; } +void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos) +{ + debugfs_remove_recursive(rqos->debugfs_dir); + rqos->debugfs_dir = NULL; +} + +int blk_mq_debugfs_register_rqos(struct rq_qos *rqos) +{ + struct request_queue *q = rqos->q; + const char *dir_name = rq_qos_id_to_name(rqos->id); + + if (!q->debugfs_dir) + return -ENOENT; + + if (rqos->debugfs_dir || !rqos->ops->debugfs_attrs) + return 0; + + if (!q->rqos_debugfs_dir) { + q->rqos_debugfs_dir = debugfs_create_dir("rqos", + q->debugfs_dir); + if (!q->rqos_debugfs_dir) + return -ENOMEM; + } + + rqos->debugfs_dir = debugfs_create_dir(dir_name, + rqos->q->rqos_debugfs_dir); + if (!rqos->debugfs_dir) + return -ENOMEM; + + if (!debugfs_create_files(rqos->debugfs_dir, rqos, + rqos->ops->debugfs_attrs)) + goto err; + return 0; + err: + blk_mq_debugfs_unregister_rqos(rqos); + return -ENOMEM; +} + +void blk_mq_debugfs_unregister_queue_rqos(struct request_queue *q) +{ + debugfs_remove_recursive(q->rqos_debugfs_dir); + q->rqos_debugfs_dir = NULL; +} + int blk_mq_debugfs_register_sched_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx) { diff --git a/block/blk-mq-debugfs.h b/block/blk-mq-debugfs.h index a9160be12be0..8c9012a578c1 100644 --- a/block/blk-mq-debugfs.h +++ b/block/blk-mq-debugfs.h @@ -31,6 +31,10 @@ void blk_mq_debugfs_unregister_sched(struct request_queue *q); int blk_mq_debugfs_register_sched_hctx(struct request_queue *q, struct blk_mq_hw_ctx *hctx); void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx); + +int blk_mq_debugfs_register_rqos(struct rq_qos *rqos); +void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos); +void blk_mq_debugfs_unregister_queue_rqos(struct request_queue *q); #else static inline int blk_mq_debugfs_register(struct request_queue *q) { @@ -78,6 +82,19 @@ static inline int blk_mq_debugfs_register_sched_hctx(struct request_queue *q, static inline void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx) { } + +static inline int blk_mq_debugfs_register_rqos(struct rq_qos *rqos) +{ + return 0; +} + +static inline void blk_mq_debugfs_unregister_rqos(struct rq_qos *rqos) +{ +} + +static inline void blk_mq_debugfs_unregister_queue_rqos(struct request_queue *q) +{ +} #endif #ifdef CONFIG_BLK_DEBUG_FS_ZONED diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index e932ef9d2718..d169d7188fa6 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -264,6 +264,8 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data, void rq_qos_exit(struct request_queue *q) { + blk_mq_debugfs_unregister_queue_rqos(q); + while (q->rq_qos) { struct rq_qos *rqos = q->rq_qos; q->rq_qos = rqos->next; diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index 8678875de420..3c85f26d3846 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -7,6 +7,10 @@ #include #include +#include "blk-mq-debugfs.h" + +struct blk_mq_debugfs_attr; + enum rq_qos_id { RQ_QOS_WBT, RQ_QOS_CGROUP, @@ -22,6 +26,9 @@ struct rq_qos { struct request_queue *q; enum rq_qos_id id; struct rq_qos *next; +#ifdef CONFIG_BLK_DEBUG_FS + struct dentry *debugfs_dir; +#endif }; struct rq_qos_ops { @@ -33,6 +40,7 @@ struct rq_qos_ops { void (*done_bio)(struct rq_qos *, struct bio *); void (*cleanup)(struct rq_qos *, struct bio *); void (*exit)(struct rq_qos *); + const struct blk_mq_debugfs_attr *debugfs_attrs; }; struct rq_depth { @@ -66,6 +74,17 @@ static inline struct rq_qos *blkcg_rq_qos(struct request_queue *q) return rq_qos_id(q, RQ_QOS_CGROUP); } +static inline const char *rq_qos_id_to_name(enum rq_qos_id id) +{ + switch (id) { + case RQ_QOS_WBT: + return "wbt"; + case RQ_QOS_CGROUP: + return "cgroup"; + } + return "unknown"; +} + static inline void rq_wait_init(struct rq_wait *rq_wait) { atomic_set(&rq_wait->inflight, 0); @@ -76,6 +95,9 @@ static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos) { rqos->next = q->rq_qos; q->rq_qos = rqos; + + if (rqos->ops->debugfs_attrs) + blk_mq_debugfs_register_rqos(rqos); } static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) @@ -91,6 +113,8 @@ static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) } prev = cur; } + + blk_mq_debugfs_unregister_rqos(rqos); } typedef bool (acquire_inflight_cb_t)(struct rq_wait *rqw, void *private_data); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 81f1b105946b..45552e6eae1e 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -560,6 +560,7 @@ struct request_queue { #ifdef CONFIG_BLK_DEBUG_FS struct dentry *debugfs_dir; struct dentry *sched_debugfs_dir; + struct dentry *rqos_debugfs_dir; #endif bool mq_sysfs_init_done; -- cgit v1.2.3-71-gd317 From 38417468d4f05cfed62fca8f407d2df0cbe3fcc8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 13 Dec 2018 16:17:10 +0100 Subject: scsi: block: remove the cluster flag Now that the the SCSI layer replaced the use of the cluster flag with segment size limits and the DMA boundary we can remove the cluster flag from the block layer. Signed-off-by: Christoph Hellwig Reviewed-by: Jens Axboe Signed-off-by: Martin K. Petersen --- block/blk-merge.c | 18 +++++++----------- block/blk-settings.c | 3 --- block/blk-sysfs.c | 5 +---- include/linux/blkdev.h | 6 ------ 4 files changed, 8 insertions(+), 24 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-merge.c b/block/blk-merge.c index 6b5ad275ed56..4478d53cc6ee 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -194,7 +194,7 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, goto split; } - if (bvprvp && blk_queue_cluster(q)) { + if (bvprvp) { if (seg_size + bv.bv_len > queue_max_segment_size(q)) goto new_segment; if (!biovec_phys_mergeable(q, bvprvp, &bv)) @@ -294,7 +294,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, bool no_sg_merge) { struct bio_vec bv, bvprv = { NULL }; - int cluster, prev = 0; + int prev = 0; unsigned int seg_size, nr_phys_segs; struct bio *fbio, *bbio; struct bvec_iter iter; @@ -312,7 +312,6 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, } fbio = bio; - cluster = blk_queue_cluster(q); seg_size = 0; nr_phys_segs = 0; for_each_bio(bio) { @@ -324,7 +323,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, if (no_sg_merge) goto new_segment; - if (prev && cluster) { + if (prev) { if (seg_size + bv.bv_len > queue_max_segment_size(q)) goto new_segment; @@ -395,9 +394,6 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, { struct bio_vec end_bv = { NULL }, nxt_bv; - if (!blk_queue_cluster(q)) - return 0; - if (bio->bi_seg_back_size + nxt->bi_seg_front_size > queue_max_segment_size(q)) return 0; @@ -414,12 +410,12 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, static inline void __blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec, struct scatterlist *sglist, struct bio_vec *bvprv, - struct scatterlist **sg, int *nsegs, int *cluster) + struct scatterlist **sg, int *nsegs) { int nbytes = bvec->bv_len; - if (*sg && *cluster) { + if (*sg) { if ((*sg)->length + nbytes > queue_max_segment_size(q)) goto new_segment; if (!biovec_phys_mergeable(q, bvprv, bvec)) @@ -465,12 +461,12 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, { struct bio_vec bvec, bvprv = { NULL }; struct bvec_iter iter; - int cluster = blk_queue_cluster(q), nsegs = 0; + int nsegs = 0; for_each_bio(bio) bio_for_each_segment(bvec, bio, iter) __blk_segment_map_sg(q, &bvec, sglist, &bvprv, sg, - &nsegs, &cluster); + &nsegs); return nsegs; } diff --git a/block/blk-settings.c b/block/blk-settings.c index 696c04c1ab6c..9c8b62f8c180 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -109,7 +109,6 @@ void blk_set_default_limits(struct queue_limits *lim) lim->alignment_offset = 0; lim->io_opt = 0; lim->misaligned = 0; - lim->cluster = 1; lim->zoned = BLK_ZONED_NONE; } EXPORT_SYMBOL(blk_set_default_limits); @@ -602,8 +601,6 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, t->io_min = max(t->io_min, b->io_min); t->io_opt = lcm_not_zero(t->io_opt, b->io_opt); - t->cluster &= b->cluster; - /* Physical block size a multiple of the logical block size? */ if (t->physical_block_size & (t->logical_block_size - 1)) { t->physical_block_size = t->logical_block_size; diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 844a454a7b3a..5144707f25ea 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -136,10 +136,7 @@ static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char * static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page) { - if (blk_queue_cluster(q)) - return queue_var_show(queue_max_segment_size(q), (page)); - - return queue_var_show(PAGE_SIZE, (page)); + return queue_var_show(queue_max_segment_size(q), (page)); } static ssize_t queue_logical_block_size_show(struct request_queue *q, char *page) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 4293dc1cd160..653ae90eec0b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -389,7 +389,6 @@ struct queue_limits { unsigned char misaligned; unsigned char discard_misaligned; - unsigned char cluster; unsigned char raid_partial_stripes_expensive; enum blk_zoned_model zoned; }; @@ -785,11 +784,6 @@ static inline bool queue_is_rq_based(struct request_queue *q) return q->request_fn || q->mq_ops; } -static inline unsigned int blk_queue_cluster(struct request_queue *q) -{ - return q->limits.cluster; -} - static inline enum blk_zoned_model blk_queue_zoned_model(struct request_queue *q) { -- cgit v1.2.3-71-gd317 From 69ed175c195595c73901e18366cb0ebeaeb68b8a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 9 Nov 2018 19:35:11 +0100 Subject: scsi: block: remove req->special No users left. Signed-off-by: Christoph Hellwig Acked-by: Jens Axboe Signed-off-by: Martin K. Petersen --- block/blk-mq.c | 1 - drivers/scsi/sd.c | 2 -- include/linux/blkdev.h | 2 -- 3 files changed, 5 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-mq.c b/block/blk-mq.c index 3ba37b9e15e9..502cbf964a3b 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -331,7 +331,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, #if defined(CONFIG_BLK_DEV_INTEGRITY) rq->nr_integrity_segments = 0; #endif - rq->special = NULL; /* tag was already set */ rq->extra_len = 0; WRITE_ONCE(rq->deadline, 0); diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c index 3db9b1fe7516..c124459041dc 100644 --- a/drivers/scsi/sd.c +++ b/drivers/scsi/sd.c @@ -1171,8 +1171,6 @@ static blk_status_t sd_setup_read_write_cmnd(struct scsi_cmnd *cmd) if (ret != BLK_STS_OK) return ret; - WARN_ON_ONCE(cmd != rq->special); - if (!scsi_device_online(sdp) || sdp->changed) { scmd_printk(KERN_ERR, cmd, "device offline or changed\n"); return BLK_STS_IOERR; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 338604dff7d0..fd1450d53f1c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -216,8 +216,6 @@ struct request { unsigned short write_hint; unsigned short ioprio; - void *special; /* opaque pointer available for LLD use */ - unsigned int extra_len; /* length of alignment and padding */ enum mq_rq_state state; -- cgit v1.2.3-71-gd317 From 8b3238cabd50e2715b6544e724e74685209b190a Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 6 Dec 2018 08:01:10 -0800 Subject: scsi: block: remove bidi support Unused now, and another field in struct request bites the dust. Signed-off-by: Christoph Hellwig Acked-by: Jens Axboe Signed-off-by: Martin K. Petersen --- block/blk-mq-debugfs.c | 1 - block/blk-mq.c | 3 --- include/linux/blkdev.h | 6 ------ 3 files changed, 10 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 90d68760af08..ac832547160a 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -115,7 +115,6 @@ static int queue_pm_only_show(void *data, struct seq_file *m) static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(STOPPED), QUEUE_FLAG_NAME(DYING), - QUEUE_FLAG_NAME(BIDI), QUEUE_FLAG_NAME(NOMERGES), QUEUE_FLAG_NAME(SAME_COMP), QUEUE_FLAG_NAME(FAIL_IO), diff --git a/block/blk-mq.c b/block/blk-mq.c index 502cbf964a3b..820d131a6893 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -339,7 +339,6 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, rq->end_io = NULL; rq->end_io_data = NULL; - rq->next_rq = NULL; data->ctx->rq_dispatched[op_is_sync(op)]++; refcount_set(&rq->ref, 1); @@ -549,8 +548,6 @@ inline void __blk_mq_end_request(struct request *rq, blk_status_t error) rq_qos_done(rq->q, rq); rq->end_io(rq, error); } else { - if (unlikely(blk_bidi_rq(rq))) - blk_mq_free_request(rq->next_rq); blk_mq_free_request(rq); } } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index fd1450d53f1c..21beb456b97a 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -234,9 +234,6 @@ struct request { */ rq_end_io_fn *end_io; void *end_io_data; - - /* for bidi */ - struct request *next_rq; }; static inline bool blk_op_is_scsi(unsigned int op) @@ -572,7 +569,6 @@ struct request_queue { #define QUEUE_FLAG_STOPPED 1 /* queue is stopped */ #define QUEUE_FLAG_DYING 2 /* queue being torn down */ -#define QUEUE_FLAG_BIDI 4 /* queue supports bidi requests */ #define QUEUE_FLAG_NOMERGES 5 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 6 /* complete on same CPU-group */ #define QUEUE_FLAG_FAIL_IO 7 /* fake timeout */ @@ -644,8 +640,6 @@ static inline bool blk_account_rq(struct request *rq) return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); } -#define blk_bidi_rq(rq) ((rq)->next_rq != NULL) - #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) #define rq_data_dir(rq) (op_is_write(req_op(rq)) ? WRITE : READ) -- cgit v1.2.3-71-gd317 From d11a3998985b351aaab6bbdc23bc884bd5e815c8 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 9 Feb 2019 15:40:24 -0700 Subject: block: kill QUEUE_FLAG_FLUSH_NQ We have various helpers for setting/clearing this flag, and also a helper to check if the queue supports queueable flushes or not. But nobody uses them anymore, kill it with fire. Signed-off-by: Jens Axboe --- block/blk-mq-debugfs.c | 1 - block/blk-settings.c | 9 --------- drivers/ata/libata-scsi.c | 2 -- drivers/block/null_blk_main.c | 1 - include/linux/blkdev.h | 7 ------- 5 files changed, 20 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index f8120832ca7b..c782e81db627 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -132,7 +132,6 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(POLL), QUEUE_FLAG_NAME(WC), QUEUE_FLAG_NAME(FUA), - QUEUE_FLAG_NAME(FLUSH_NQ), QUEUE_FLAG_NAME(DAX), QUEUE_FLAG_NAME(STATS), QUEUE_FLAG_NAME(POLL_STATS), diff --git a/block/blk-settings.c b/block/blk-settings.c index 3e7038e475ee..6375afaedcec 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -799,15 +799,6 @@ void blk_queue_update_dma_alignment(struct request_queue *q, int mask) } EXPORT_SYMBOL(blk_queue_update_dma_alignment); -void blk_queue_flush_queueable(struct request_queue *q, bool queueable) -{ - if (queueable) - blk_queue_flag_clear(QUEUE_FLAG_FLUSH_NQ, q); - else - blk_queue_flag_set(QUEUE_FLAG_FLUSH_NQ, q); -} -EXPORT_SYMBOL_GPL(blk_queue_flush_queueable); - /** * blk_set_queue_depth - tell the block layer about the device queue depth * @q: the request queue for the device diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index 3d4887d0e84a..dfe66d00dd5b 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -1318,8 +1318,6 @@ static int ata_scsi_dev_config(struct scsi_device *sdev, scsi_change_queue_depth(sdev, depth); } - blk_queue_flush_queueable(q, false); - if (dev->flags & ATA_DFLAG_TRUSTED) sdev->security_supported = 1; diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c index 62c9654b9ce8..83c38a6217d7 100644 --- a/drivers/block/null_blk_main.c +++ b/drivers/block/null_blk_main.c @@ -1678,7 +1678,6 @@ static int null_add_dev(struct nullb_device *dev) if (dev->cache_size > 0) { set_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags); blk_queue_write_cache(nullb->q, true, true); - blk_queue_flush_queueable(nullb->q, true); } if (dev->zoned) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 338604dff7d0..24ccab51085f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -592,7 +592,6 @@ struct request_queue { #define QUEUE_FLAG_POLL 19 /* IO polling enabled if set */ #define QUEUE_FLAG_WC 20 /* Write back caching */ #define QUEUE_FLAG_FUA 21 /* device supports FUA writes */ -#define QUEUE_FLAG_FLUSH_NQ 22 /* flush not queueuable */ #define QUEUE_FLAG_DAX 23 /* device supports DAX */ #define QUEUE_FLAG_STATS 24 /* track IO start and completion times */ #define QUEUE_FLAG_POLL_STATS 25 /* collecting stats for hybrid polling */ @@ -1069,7 +1068,6 @@ extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); -extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); /* @@ -1446,11 +1444,6 @@ static inline unsigned int block_size(struct block_device *bdev) return bdev->bd_block_size; } -static inline bool queue_flush_queueable(struct request_queue *q) -{ - return !test_bit(QUEUE_FLAG_FLUSH_NQ, &q->queue_flags); -} - typedef struct {struct page *v;} Sector; unsigned char *read_dev_sector(struct block_device *, sector_t, Sector *); -- cgit v1.2.3-71-gd317 From eca7abf31abba2acac445ec6a1d3f94cf0cab918 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Sat, 9 Feb 2019 15:42:07 -0700 Subject: block: queue flag cleanup We have QUEUE_FLAG_DEFAULT defined, but it's not used anymore since the legacy IO stack is gone. Kill it. Sanitize the queue flags in general, they use spaces (for some reason), and the space is pretty sparse. With the flags renumbered, we can more clearly see how many we have available. Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 58 +++++++++++++++++++++++--------------------------- 1 file changed, 27 insertions(+), 31 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 24ccab51085f..3603270cb82d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -572,37 +572,33 @@ struct request_queue { u64 write_hints[BLK_MAX_WRITE_HINTS]; }; -#define QUEUE_FLAG_STOPPED 1 /* queue is stopped */ -#define QUEUE_FLAG_DYING 2 /* queue being torn down */ -#define QUEUE_FLAG_BIDI 4 /* queue supports bidi requests */ -#define QUEUE_FLAG_NOMERGES 5 /* disable merge attempts */ -#define QUEUE_FLAG_SAME_COMP 6 /* complete on same CPU-group */ -#define QUEUE_FLAG_FAIL_IO 7 /* fake timeout */ -#define QUEUE_FLAG_NONROT 9 /* non-rotational device (SSD) */ -#define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ -#define QUEUE_FLAG_IO_STAT 10 /* do disk/partitions IO accounting */ -#define QUEUE_FLAG_DISCARD 11 /* supports DISCARD */ -#define QUEUE_FLAG_NOXMERGES 12 /* No extended merges */ -#define QUEUE_FLAG_ADD_RANDOM 13 /* Contributes to random pool */ -#define QUEUE_FLAG_SECERASE 14 /* supports secure erase */ -#define QUEUE_FLAG_SAME_FORCE 15 /* force complete on same CPU */ -#define QUEUE_FLAG_DEAD 16 /* queue tear-down finished */ -#define QUEUE_FLAG_INIT_DONE 17 /* queue is initialized */ -#define QUEUE_FLAG_NO_SG_MERGE 18 /* don't attempt to merge SG segments*/ -#define QUEUE_FLAG_POLL 19 /* IO polling enabled if set */ -#define QUEUE_FLAG_WC 20 /* Write back caching */ -#define QUEUE_FLAG_FUA 21 /* device supports FUA writes */ -#define QUEUE_FLAG_DAX 23 /* device supports DAX */ -#define QUEUE_FLAG_STATS 24 /* track IO start and completion times */ -#define QUEUE_FLAG_POLL_STATS 25 /* collecting stats for hybrid polling */ -#define QUEUE_FLAG_REGISTERED 26 /* queue has been registered to a disk */ -#define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */ -#define QUEUE_FLAG_QUIESCED 28 /* queue has been quiesced */ -#define QUEUE_FLAG_PCI_P2PDMA 29 /* device supports PCI p2p requests */ - -#define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_SAME_COMP) | \ - (1 << QUEUE_FLAG_ADD_RANDOM)) +#define QUEUE_FLAG_STOPPED 0 /* queue is stopped */ +#define QUEUE_FLAG_DYING 1 /* queue being torn down */ +#define QUEUE_FLAG_BIDI 2 /* queue supports bidi requests */ +#define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */ +#define QUEUE_FLAG_SAME_COMP 4 /* complete on same CPU-group */ +#define QUEUE_FLAG_FAIL_IO 5 /* fake timeout */ +#define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */ +#define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ +#define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ +#define QUEUE_FLAG_DISCARD 8 /* supports DISCARD */ +#define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ +#define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ +#define QUEUE_FLAG_SECERASE 11 /* supports secure erase */ +#define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ +#define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ +#define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ +#define QUEUE_FLAG_NO_SG_MERGE 15 /* don't attempt to merge SG segments*/ +#define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ +#define QUEUE_FLAG_WC 17 /* Write back caching */ +#define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ +#define QUEUE_FLAG_DAX 19 /* device supports DAX */ +#define QUEUE_FLAG_STATS 20 /* track IO start and completion times */ +#define QUEUE_FLAG_POLL_STATS 21 /* collecting stats for hybrid polling */ +#define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */ +#define QUEUE_FLAG_SCSI_PASSTHROUGH 23 /* queue supports SCSI commands */ +#define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */ +#define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP)) -- cgit v1.2.3-71-gd317 From d18d91740ad22e9d7998884c4d80523d0ba95ddf Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 15 Feb 2019 19:13:11 +0800 Subject: block: introduce bio_for_each_bvec() and rq_for_each_bvec() bio_for_each_bvec() is used for iterating over multi-page bvec for bio split & merge code. rq_for_each_bvec() can be used for drivers which may handle the multi-page bvec directly, so far loop is one perfect use case. Reviewed-by: Christoph Hellwig Reviewed-by: Omar Sandoval Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bio.h | 10 ++++++++++ include/linux/blkdev.h | 4 ++++ 2 files changed, 14 insertions(+) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/bio.h b/include/linux/bio.h index 72b4f7be2106..7ef8a7505c0a 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -156,6 +156,16 @@ static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, #define bio_for_each_segment(bvl, bio, iter) \ __bio_for_each_segment(bvl, bio, iter, (bio)->bi_iter) +#define __bio_for_each_bvec(bvl, bio, iter, start) \ + for (iter = (start); \ + (iter).bi_size && \ + ((bvl = mp_bvec_iter_bvec((bio)->bi_io_vec, (iter))), 1); \ + bio_advance_iter((bio), &(iter), (bvl).bv_len)) + +/* iterate over multi-page bvec */ +#define bio_for_each_bvec(bvl, bio, iter) \ + __bio_for_each_bvec(bvl, bio, iter, (bio)->bi_iter) + #define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len) static inline unsigned bio_segments(struct bio *bio) diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 3603270cb82d..b6292d469ea4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -792,6 +792,10 @@ struct req_iterator { __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_segment(bvl, _iter.bio, _iter.iter) +#define rq_for_each_bvec(bvl, _rq, _iter) \ + __rq_for_each_bio(_iter.bio, _rq) \ + bio_for_each_bvec(bvl, _iter.bio, _iter.iter) + #define rq_iter_last(bvec, _iter) \ (_iter.bio->bi_next == NULL && \ bio_iter_last(bvec, _iter.iter)) -- cgit v1.2.3-71-gd317 From 2705c93742e91730d335838025d75d8043861174 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Fri, 15 Feb 2019 19:13:23 +0800 Subject: block: kill QUEUE_FLAG_NO_SG_MERGE Since bdced438acd83ad83a6c ("block: setup bi_phys_segments after splitting"), physical segment number is mainly figured out in blk_queue_split() for fast path, and the flag of BIO_SEG_VALID is set there too. Now only blk_recount_segments() and blk_recalc_rq_segments() use this flag. Basically blk_recount_segments() is bypassed in fast path given BIO_SEG_VALID is set in blk_queue_split(). For another user of blk_recalc_rq_segments(): - run in partial completion branch of blk_update_request, which is an unusual case - run in blk_cloned_rq_check_limits(), still not a big problem if the flag is killed since dm-rq is the only user. Multi-page bvec is enabled now, not doing S/G merging is rather pointless with the current setup of the I/O path, as it isn't going to save you a significant amount of cycles. Reviewed-by: Christoph Hellwig Reviewed-by: Omar Sandoval Signed-off-by: Ming Lei Signed-off-by: Jens Axboe --- block/blk-merge.c | 31 ++++++------------------------- block/blk-mq-debugfs.c | 1 - block/blk-mq.c | 3 --- drivers/md/dm-table.c | 13 ------------- include/linux/blkdev.h | 1 - 5 files changed, 6 insertions(+), 43 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-merge.c b/block/blk-merge.c index 1912499b08b7..bed065904677 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -358,8 +358,7 @@ void blk_queue_split(struct request_queue *q, struct bio **bio) EXPORT_SYMBOL(blk_queue_split); static unsigned int __blk_recalc_rq_segments(struct request_queue *q, - struct bio *bio, - bool no_sg_merge) + struct bio *bio) { struct bio_vec bv, bvprv = { NULL }; int prev = 0; @@ -385,13 +384,6 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, nr_phys_segs = 0; for_each_bio(bio) { bio_for_each_bvec(bv, bio, iter) { - /* - * If SG merging is disabled, each bio vector is - * a segment - */ - if (no_sg_merge) - goto new_segment; - if (prev) { if (seg_size + bv.bv_len > queue_max_segment_size(q)) @@ -421,27 +413,16 @@ new_segment: void blk_recalc_rq_segments(struct request *rq) { - bool no_sg_merge = !!test_bit(QUEUE_FLAG_NO_SG_MERGE, - &rq->q->queue_flags); - - rq->nr_phys_segments = __blk_recalc_rq_segments(rq->q, rq->bio, - no_sg_merge); + rq->nr_phys_segments = __blk_recalc_rq_segments(rq->q, rq->bio); } void blk_recount_segments(struct request_queue *q, struct bio *bio) { - unsigned short seg_cnt = bio_segments(bio); - - if (test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags) && - (seg_cnt < queue_max_segments(q))) - bio->bi_phys_segments = seg_cnt; - else { - struct bio *nxt = bio->bi_next; + struct bio *nxt = bio->bi_next; - bio->bi_next = NULL; - bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio, false); - bio->bi_next = nxt; - } + bio->bi_next = NULL; + bio->bi_phys_segments = __blk_recalc_rq_segments(q, bio); + bio->bi_next = nxt; bio_set_flag(bio, BIO_SEG_VALID); } diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index c782e81db627..697d6213c82b 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -128,7 +128,6 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(SAME_FORCE), QUEUE_FLAG_NAME(DEAD), QUEUE_FLAG_NAME(INIT_DONE), - QUEUE_FLAG_NAME(NO_SG_MERGE), QUEUE_FLAG_NAME(POLL), QUEUE_FLAG_NAME(WC), QUEUE_FLAG_NAME(FUA), diff --git a/block/blk-mq.c b/block/blk-mq.c index 44d471ff8754..fa508ee31742 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2837,9 +2837,6 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, set->map[HCTX_TYPE_POLL].nr_queues) blk_queue_flag_set(QUEUE_FLAG_POLL, q); - if (!(set->flags & BLK_MQ_F_SG_MERGE)) - blk_queue_flag_set(QUEUE_FLAG_NO_SG_MERGE, q); - q->sg_reserved_size = INT_MAX; INIT_DELAYED_WORK(&q->requeue_work, blk_mq_requeue_work); diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 4b1be754cc41..ba9481f1bf3c 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -1698,14 +1698,6 @@ static int device_is_not_random(struct dm_target *ti, struct dm_dev *dev, return q && !blk_queue_add_random(q); } -static int queue_supports_sg_merge(struct dm_target *ti, struct dm_dev *dev, - sector_t start, sector_t len, void *data) -{ - struct request_queue *q = bdev_get_queue(dev->bdev); - - return q && !test_bit(QUEUE_FLAG_NO_SG_MERGE, &q->queue_flags); -} - static bool dm_table_all_devices_attribute(struct dm_table *t, iterate_devices_callout_fn func) { @@ -1902,11 +1894,6 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q, if (!dm_table_supports_write_zeroes(t)) q->limits.max_write_zeroes_sectors = 0; - if (dm_table_all_devices_attribute(t, queue_supports_sg_merge)) - blk_queue_flag_clear(QUEUE_FLAG_NO_SG_MERGE, q); - else - blk_queue_flag_set(QUEUE_FLAG_NO_SG_MERGE, q); - dm_table_verify_integrity(t); /* diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b6292d469ea4..faed9d9eb84c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -588,7 +588,6 @@ struct request_queue { #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ -#define QUEUE_FLAG_NO_SG_MERGE 15 /* don't attempt to merge SG segments*/ #define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ #define QUEUE_FLAG_WC 17 /* Write back caching */ #define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ -- cgit v1.2.3-71-gd317 From 29ece8b4354f8c5eaee798a3d8a1b356efee426f Mon Sep 17 00:00:00 2001 From: Yufen Yu Date: Mon, 18 Mar 2019 22:44:41 +0800 Subject: block: add BLK_MQ_POLL_CLASSIC for hybrid poll and return EINVAL for unexpected value For q->poll_nsec == -1, means doing classic poll, not hybrid poll. We introduce a new flag BLK_MQ_POLL_CLASSIC to replace -1, which may make code much easier to read. Additionally, since val is an int obtained with kstrtoint(), val can be a negative value other than -1, so return -EINVAL for that case. Thanks to Damien Le Moal for some good suggestion. Reviewed-by: Damien Le Moal Signed-off-by: Yufen Yu Signed-off-by: Jens Axboe --- block/blk-mq.c | 4 ++-- block/blk-sysfs.c | 12 +++++++----- include/linux/blkdev.h | 3 +++ 3 files changed, 12 insertions(+), 7 deletions(-) (limited to 'include/linux/blkdev.h') diff --git a/block/blk-mq.c b/block/blk-mq.c index ea01c23b58a3..76a3f78c566a 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -2856,7 +2856,7 @@ struct request_queue *blk_mq_init_allocated_queue(struct blk_mq_tag_set *set, /* * Default to classic polling */ - q->poll_nsec = -1; + q->poll_nsec = BLK_MQ_POLL_CLASSIC; blk_mq_init_cpu_queues(q, set->nr_hw_queues); blk_mq_add_queue_tag_set(set, q); @@ -3391,7 +3391,7 @@ static bool blk_mq_poll_hybrid(struct request_queue *q, { struct request *rq; - if (q->poll_nsec == -1) + if (q->poll_nsec == BLK_MQ_POLL_CLASSIC) return false; if (!blk_qc_t_is_internal(cookie)) diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 59685918167e..422327089e0f 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -360,8 +360,8 @@ static ssize_t queue_poll_delay_show(struct request_queue *q, char *page) { int val; - if (q->poll_nsec == -1) - val = -1; + if (q->poll_nsec == BLK_MQ_POLL_CLASSIC) + val = BLK_MQ_POLL_CLASSIC; else val = q->poll_nsec / 1000; @@ -380,10 +380,12 @@ static ssize_t queue_poll_delay_store(struct request_queue *q, const char *page, if (err < 0) return err; - if (val == -1) - q->poll_nsec = -1; - else + if (val == BLK_MQ_POLL_CLASSIC) + q->poll_nsec = BLK_MQ_POLL_CLASSIC; + else if (val >= 0) q->poll_nsec = val * 1000; + else + return -EINVAL; return count; } diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0de92b29f589..5c58a3b2bf00 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -50,6 +50,9 @@ struct blk_stat_callback; /* Must be consistent with blk_mq_poll_stats_bkt() */ #define BLK_MQ_POLL_STATS_BKTS 16 +/* Doing classic polling */ +#define BLK_MQ_POLL_CLASSIC -1 + /* * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. -- cgit v1.2.3-71-gd317 From b40fabc05ea047f6af5933d26a5483873340b0d4 Mon Sep 17 00:00:00 2001 From: Hou Tao Date: Fri, 19 Apr 2019 10:31:27 +0800 Subject: block: kill all_q_node in request_queue all_q_node has not been used since commit 4b855ad37194 ("blk-mq: Create hctx for each present CPU"), so remove it. Reviewed-by: Chaitanya Kulkarni Reviewed-by: Ming Lei Signed-off-by: Hou Tao Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux/blkdev.h') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5c58a3b2bf00..317ab30d2904 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -548,7 +548,6 @@ struct request_queue { struct rcu_head rcu_head; wait_queue_head_t mq_freeze_wq; struct percpu_ref q_usage_counter; - struct list_head all_q_node; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; -- cgit v1.2.3-71-gd317