diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-01-30 11:19:05 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-01-30 11:19:05 -0800 |
commit | f568849edac8611d603e00bd6cbbcfea09395ae6 (patch) | |
tree | b9472d640fe5d87426d38c9d81d946cf197ad3fb /block | |
parent | d9894c228b11273e720bb63ba120d1d326fe9d94 (diff) | |
parent | 675675ada486dde5bf9aa51665e90706bff11a35 (diff) |
Merge branch 'for-3.14/core' of git://git.kernel.dk/linux-block
Pull core block IO changes from Jens Axboe:
"The major piece in here is the immutable bio_ve series from Kent, the
rest is fairly minor. It was supposed to go in last round, but
various issues pushed it to this release instead. The pull request
contains:
- Various smaller blk-mq fixes from different folks. Nothing major
here, just minor fixes and cleanups.
- Fix for a memory leak in the error path in the block ioctl code
from Christian Engelmayer.
- Header export fix from CaiZhiyong.
- Finally the immutable biovec changes from Kent Overstreet. This
enables some nice future work on making arbitrarily sized bios
possible, and splitting more efficient. Related fixes to immutable
bio_vecs:
- dm-cache immutable fixup from Mike Snitzer.
- btrfs immutable fixup from Muthu Kumar.
- bio-integrity fix from Nic Bellinger, which is also going to stable"
* 'for-3.14/core' of git://git.kernel.dk/linux-block: (44 commits)
xtensa: fixup simdisk driver to work with immutable bio_vecs
block/blk-mq-cpu.c: use hotcpu_notifier()
blk-mq: for_each_* macro correctness
block: Fix memory leak in rw_copy_check_uvector() handling
bio-integrity: Fix bio_integrity_verify segment start bug
block: remove unrelated header files and export symbol
blk-mq: uses page->list incorrectly
blk-mq: use __smp_call_function_single directly
btrfs: fix missing increment of bi_remaining
Revert "block: Warn and free bio if bi_end_io is not set"
block: Warn and free bio if bi_end_io is not set
blk-mq: fix initializing request's start time
block: blk-mq: don't export blk_mq_free_queue()
block: blk-mq: make blk_sync_queue support mq
block: blk-mq: support draining mq queue
dm cache: increment bi_remaining when bi_end_io is restored
block: fixup for generic bio chaining
block: Really silence spurious compiler warnings
block: Silence spurious compiler warnings
block: Kill bio_pair_split()
...
Diffstat (limited to 'block')
-rw-r--r-- | block/blk-core.c | 61 | ||||
-rw-r--r-- | block/blk-exec.c | 4 | ||||
-rw-r--r-- | block/blk-flush.c | 2 | ||||
-rw-r--r-- | block/blk-integrity.c | 40 | ||||
-rw-r--r-- | block/blk-lib.c | 12 | ||||
-rw-r--r-- | block/blk-map.c | 6 | ||||
-rw-r--r-- | block/blk-merge.c | 66 | ||||
-rw-r--r-- | block/blk-mq-cpu.c | 37 | ||||
-rw-r--r-- | block/blk-mq.c | 123 | ||||
-rw-r--r-- | block/blk-mq.h | 3 | ||||
-rw-r--r-- | block/blk-sysfs.c | 1 | ||||
-rw-r--r-- | block/blk-throttle.c | 14 | ||||
-rw-r--r-- | block/cmdline-parser.c | 18 | ||||
-rw-r--r-- | block/elevator.c | 2 | ||||
-rw-r--r-- | block/scsi_ioctl.c | 6 |
15 files changed, 181 insertions, 214 deletions
diff --git a/block/blk-core.c b/block/blk-core.c index 8bdd0121212a..c00e0bdeab4a 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -38,6 +38,7 @@ #include "blk.h" #include "blk-cgroup.h" +#include "blk-mq.h" EXPORT_TRACEPOINT_SYMBOL_GPL(block_bio_remap); EXPORT_TRACEPOINT_SYMBOL_GPL(block_rq_remap); @@ -130,7 +131,7 @@ static void req_bio_endio(struct request *rq, struct bio *bio, bio_advance(bio, nbytes); /* don't actually finish bio if it's part of flush sequence */ - if (bio->bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ)) + if (bio->bi_iter.bi_size == 0 && !(rq->cmd_flags & REQ_FLUSH_SEQ)) bio_endio(bio, error); } @@ -245,7 +246,16 @@ EXPORT_SYMBOL(blk_stop_queue); void blk_sync_queue(struct request_queue *q) { del_timer_sync(&q->timeout); - cancel_delayed_work_sync(&q->delay_work); + + if (q->mq_ops) { + struct blk_mq_hw_ctx *hctx; + int i; + + queue_for_each_hw_ctx(q, hctx, i) + cancel_delayed_work_sync(&hctx->delayed_work); + } else { + cancel_delayed_work_sync(&q->delay_work); + } } EXPORT_SYMBOL(blk_sync_queue); @@ -497,8 +507,13 @@ void blk_cleanup_queue(struct request_queue *q) * Drain all requests queued before DYING marking. Set DEAD flag to * prevent that q->request_fn() gets invoked after draining finished. */ - spin_lock_irq(lock); - __blk_drain_queue(q, true); + if (q->mq_ops) { + blk_mq_drain_queue(q); + spin_lock_irq(lock); + } else { + spin_lock_irq(lock); + __blk_drain_queue(q, true); + } queue_flag_set(QUEUE_FLAG_DEAD, q); spin_unlock_irq(lock); @@ -1326,7 +1341,7 @@ void blk_add_request_payload(struct request *rq, struct page *page, bio->bi_io_vec->bv_offset = 0; bio->bi_io_vec->bv_len = len; - bio->bi_size = len; + bio->bi_iter.bi_size = len; bio->bi_vcnt = 1; bio->bi_phys_segments = 1; @@ -1351,7 +1366,7 @@ bool bio_attempt_back_merge(struct request_queue *q, struct request *req, req->biotail->bi_next = bio; req->biotail = bio; - req->__data_len += bio->bi_size; + req->__data_len += bio->bi_iter.bi_size; req->ioprio = ioprio_best(req->ioprio, bio_prio(bio)); blk_account_io_start(req, false); @@ -1380,8 +1395,8 @@ bool bio_attempt_front_merge(struct request_queue *q, struct request *req, * not touch req->buffer either... */ req->buffer = bio_data(bio); - req->__sector = bio->bi_sector; - req->__data_len += bio->bi_size; + req->__sector = bio->bi_iter.bi_sector; + req->__data_len += bio->bi_iter.bi_size; req->ioprio = ioprio_best(req->ioprio, bio_prio(bio)); blk_account_io_start(req, false); @@ -1459,7 +1474,7 @@ void init_request_from_bio(struct request *req, struct bio *bio) req->cmd_flags |= REQ_FAILFAST_MASK; req->errors = 0; - req->__sector = bio->bi_sector; + req->__sector = bio->bi_iter.bi_sector; req->ioprio = bio_prio(bio); blk_rq_bio_prep(req->q, req, bio); } @@ -1583,12 +1598,12 @@ static inline void blk_partition_remap(struct bio *bio) if (bio_sectors(bio) && bdev != bdev->bd_contains) { struct hd_struct *p = bdev->bd_part; - bio->bi_sector += p->start_sect; + bio->bi_iter.bi_sector += p->start_sect; bio->bi_bdev = bdev->bd_contains; trace_block_bio_remap(bdev_get_queue(bio->bi_bdev), bio, bdev->bd_dev, - bio->bi_sector - p->start_sect); + bio->bi_iter.bi_sector - p->start_sect); } } @@ -1654,7 +1669,7 @@ static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors) /* Test device or partition size, when known. */ maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9; if (maxsector) { - sector_t sector = bio->bi_sector; + sector_t sector = bio->bi_iter.bi_sector; if (maxsector < nr_sectors || maxsector - nr_sectors < sector) { /* @@ -1690,7 +1705,7 @@ generic_make_request_checks(struct bio *bio) "generic_make_request: Trying to access " "nonexistent block-device %s (%Lu)\n", bdevname(bio->bi_bdev, b), - (long long) bio->bi_sector); + (long long) bio->bi_iter.bi_sector); goto end_io; } @@ -1704,9 +1719,9 @@ generic_make_request_checks(struct bio *bio) } part = bio->bi_bdev->bd_part; - if (should_fail_request(part, bio->bi_size) || + if (should_fail_request(part, bio->bi_iter.bi_size) || should_fail_request(&part_to_disk(part)->part0, - bio->bi_size)) + bio->bi_iter.bi_size)) goto end_io; /* @@ -1865,7 +1880,7 @@ void submit_bio(int rw, struct bio *bio) if (rw & WRITE) { count_vm_events(PGPGOUT, count); } else { - task_io_account_read(bio->bi_size); + task_io_account_read(bio->bi_iter.bi_size); count_vm_events(PGPGIN, count); } @@ -1874,7 +1889,7 @@ void submit_bio(int rw, struct bio *bio) printk(KERN_DEBUG "%s(%d): %s block %Lu on %s (%u sectors)\n", current->comm, task_pid_nr(current), (rw & WRITE) ? "WRITE" : "READ", - (unsigned long long)bio->bi_sector, + (unsigned long long)bio->bi_iter.bi_sector, bdevname(bio->bi_bdev, b), count); } @@ -2007,7 +2022,7 @@ unsigned int blk_rq_err_bytes(const struct request *rq) for (bio = rq->bio; bio; bio = bio->bi_next) { if ((bio->bi_rw & ff) != ff) break; - bytes += bio->bi_size; + bytes += bio->bi_iter.bi_size; } /* this could lead to infinite loop */ @@ -2378,9 +2393,9 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes) total_bytes = 0; while (req->bio) { struct bio *bio = req->bio; - unsigned bio_bytes = min(bio->bi_size, nr_bytes); + unsigned bio_bytes = min(bio->bi_iter.bi_size, nr_bytes); - if (bio_bytes == bio->bi_size) + if (bio_bytes == bio->bi_iter.bi_size) req->bio = bio->bi_next; req_bio_endio(req, bio, bio_bytes, error); @@ -2728,7 +2743,7 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq, rq->nr_phys_segments = bio_phys_segments(q, bio); rq->buffer = bio_data(bio); } - rq->__data_len = bio->bi_size; + rq->__data_len = bio->bi_iter.bi_size; rq->bio = rq->biotail = bio; if (bio->bi_bdev) @@ -2746,10 +2761,10 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq, void rq_flush_dcache_pages(struct request *rq) { struct req_iterator iter; - struct bio_vec *bvec; + struct bio_vec bvec; rq_for_each_segment(bvec, rq, iter) - flush_dcache_page(bvec->bv_page); + flush_dcache_page(bvec.bv_page); } EXPORT_SYMBOL_GPL(rq_flush_dcache_pages); #endif diff --git a/block/blk-exec.c b/block/blk-exec.c index c3edf9dff566..bbfc072a79c2 100644 --- a/block/blk-exec.c +++ b/block/blk-exec.c @@ -60,6 +60,10 @@ void blk_execute_rq_nowait(struct request_queue *q, struct gendisk *bd_disk, rq->rq_disk = bd_disk; rq->end_io = done; + /* + * don't check dying flag for MQ because the request won't + * be resued after dying flag is set + */ if (q->mq_ops) { blk_mq_insert_request(q, rq, true); return; diff --git a/block/blk-flush.c b/block/blk-flush.c index fb6f3c0ffa49..9288aaf35c21 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -548,7 +548,7 @@ int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask, * copied from blk_rq_pos(rq). */ if (error_sector) - *error_sector = bio->bi_sector; + *error_sector = bio->bi_iter.bi_sector; bio_put(bio); return ret; diff --git a/block/blk-integrity.c b/block/blk-integrity.c index 03cf7179e8ef..7fbab84399e6 100644 --- a/block/blk-integrity.c +++ b/block/blk-integrity.c @@ -43,30 +43,32 @@ static const char *bi_unsupported_name = "unsupported"; */ int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *bio) { - struct bio_vec *iv, *ivprv = NULL; + struct bio_vec iv, ivprv = { NULL }; unsigned int segments = 0; unsigned int seg_size = 0; - unsigned int i = 0; + struct bvec_iter iter; + int prev = 0; - bio_for_each_integrity_vec(iv, bio, i) { + bio_for_each_integrity_vec(iv, bio, iter) { - if (ivprv) { - if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv)) + if (prev) { + if (!BIOVEC_PHYS_MERGEABLE(&ivprv, &iv)) goto new_segment; - if (!BIOVEC_SEG_BOUNDARY(q, ivprv, iv)) + if (!BIOVEC_SEG_BOUNDARY(q, &ivprv, &iv)) goto new_segment; - if (seg_size + iv->bv_len > queue_max_segment_size(q)) + if (seg_size + iv.bv_len > queue_max_segment_size(q)) goto new_segment; - seg_size += iv->bv_len; + seg_size += iv.bv_len; } else { new_segment: segments++; - seg_size = iv->bv_len; + seg_size = iv.bv_len; } + prev = 1; ivprv = iv; } @@ -87,24 +89,25 @@ EXPORT_SYMBOL(blk_rq_count_integrity_sg); int blk_rq_map_integrity_sg(struct request_queue *q, struct bio *bio, struct scatterlist *sglist) { - struct bio_vec *iv, *ivprv = NULL; + struct bio_vec iv, ivprv = { NULL }; struct scatterlist *sg = NULL; unsigned int segments = 0; - unsigned int i = 0; + struct bvec_iter iter; + int prev = 0; - bio_for_each_integrity_vec(iv, bio, i) { + bio_for_each_integrity_vec(iv, bio, iter) { - if (ivprv) { - if (!BIOVEC_PHYS_MERGEABLE(ivprv, iv)) + if (prev) { + if (!BIOVEC_PHYS_MERGEABLE(&ivprv, &iv)) goto new_segment; - if (!BIOVEC_SEG_BOUNDARY(q, ivprv, iv)) + if (!BIOVEC_SEG_BOUNDARY(q, &ivprv, &iv)) goto new_segment; - if (sg->length + iv->bv_len > queue_max_segment_size(q)) + if (sg->length + iv.bv_len > queue_max_segment_size(q)) goto new_segment; - sg->length += iv->bv_len; + sg->length += iv.bv_len; } else { new_segment: if (!sg) @@ -114,10 +117,11 @@ new_segment: sg = sg_next(sg); } - sg_set_page(sg, iv->bv_page, iv->bv_len, iv->bv_offset); + sg_set_page(sg, iv.bv_page, iv.bv_len, iv.bv_offset); segments++; } + prev = 1; ivprv = iv; } diff --git a/block/blk-lib.c b/block/blk-lib.c index 9b5b561cb928..2da76c999ef3 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -108,12 +108,12 @@ int blkdev_issue_discard(struct block_device *bdev, sector_t sector, req_sects = end_sect - sector; } - bio->bi_sector = sector; + bio->bi_iter.bi_sector = sector; bio->bi_end_io = bio_batch_end_io; bio->bi_bdev = bdev; bio->bi_private = &bb; - bio->bi_size = req_sects << 9; + bio->bi_iter.bi_size = req_sects << 9; nr_sects -= req_sects; sector = end_sect; @@ -174,7 +174,7 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, break; } - bio->bi_sector = sector; + bio->bi_iter.bi_sector = sector; bio->bi_end_io = bio_batch_end_io; bio->bi_bdev = bdev; bio->bi_private = &bb; @@ -184,11 +184,11 @@ int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, bio->bi_io_vec->bv_len = bdev_logical_block_size(bdev); if (nr_sects > max_write_same_sectors) { - bio->bi_size = max_write_same_sectors << 9; + bio->bi_iter.bi_size = max_write_same_sectors << 9; nr_sects -= max_write_same_sectors; sector += max_write_same_sectors; } else { - bio->bi_size = nr_sects << 9; + bio->bi_iter.bi_size = nr_sects << 9; nr_sects = 0; } @@ -240,7 +240,7 @@ int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, break; } - bio->bi_sector = sector; + bio->bi_iter.bi_sector = sector; bio->bi_bdev = bdev; bio->bi_end_io = bio_batch_end_io; bio->bi_private = &bb; diff --git a/block/blk-map.c b/block/blk-map.c index 623e1cd4cffe..ae4ae1047fd9 100644 --- a/block/blk-map.c +++ b/block/blk-map.c @@ -20,7 +20,7 @@ int blk_rq_append_bio(struct request_queue *q, struct request *rq, rq->biotail->bi_next = bio; rq->biotail = bio; - rq->__data_len += bio->bi_size; + rq->__data_len += bio->bi_iter.bi_size; } return 0; } @@ -76,7 +76,7 @@ static int __blk_rq_map_user(struct request_queue *q, struct request *rq, ret = blk_rq_append_bio(q, rq, bio); if (!ret) - return bio->bi_size; + return bio->bi_iter.bi_size; /* if it was boucned we must call the end io function */ bio_endio(bio, 0); @@ -220,7 +220,7 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq, if (IS_ERR(bio)) return PTR_ERR(bio); - if (bio->bi_size != len) { + if (bio->bi_iter.bi_size != len) { /* * Grab an extra reference to this bio, as bio_unmap_user() * expects to be able to drop it twice as it happens on the diff --git a/block/blk-merge.c b/block/blk-merge.c index 1ffc58977835..8f8adaa95466 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -12,10 +12,11 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, struct bio *bio) { - struct bio_vec *bv, *bvprv = NULL; - int cluster, i, high, highprv = 1; + struct bio_vec bv, bvprv = { NULL }; + int cluster, high, highprv = 1; unsigned int seg_size, nr_phys_segs; struct bio *fbio, *bbio; + struct bvec_iter iter; if (!bio) return 0; @@ -25,25 +26,23 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, seg_size = 0; nr_phys_segs = 0; for_each_bio(bio) { - bio_for_each_segment(bv, bio, i) { + bio_for_each_segment(bv, bio, iter) { /* * the trick here is making sure that a high page is * never considered part of another segment, since that * might change with the bounce page. */ - high = page_to_pfn(bv->bv_page) > queue_bounce_pfn(q); - if (high || highprv) - goto new_segment; - if (cluster) { - if (seg_size + bv->bv_len + high = page_to_pfn(bv.bv_page) > queue_bounce_pfn(q); + if (!high && !highprv && cluster) { + if (seg_size + bv.bv_len > queue_max_segment_size(q)) goto new_segment; - if (!BIOVEC_PHYS_MERGEABLE(bvprv, bv)) + if (!BIOVEC_PHYS_MERGEABLE(&bvprv, &bv)) goto new_segment; - if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bv)) + if (!BIOVEC_SEG_BOUNDARY(q, &bvprv, &bv)) goto new_segment; - seg_size += bv->bv_len; + seg_size += bv.bv_len; bvprv = bv; continue; } @@ -54,7 +53,7 @@ new_segment: nr_phys_segs++; bvprv = bv; - seg_size = bv->bv_len; + seg_size = bv.bv_len; highprv = high; } bbio = bio; @@ -87,6 +86,9 @@ EXPORT_SYMBOL(blk_recount_segments); static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, struct bio *nxt) { + struct bio_vec end_bv = { NULL }, nxt_bv; + struct bvec_iter iter; + if (!blk_queue_cluster(q)) return 0; @@ -97,34 +99,40 @@ static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio, if (!bio_has_data(bio)) return 1; - if (!BIOVEC_PHYS_MERGEABLE(__BVEC_END(bio), __BVEC_START(nxt))) + bio_for_each_segment(end_bv, bio, iter) + if (end_bv.bv_len == iter.bi_size) + break; + + nxt_bv = bio_iovec(nxt); + + if (!BIOVEC_PHYS_MERGEABLE(&end_bv, &nxt_bv)) return 0; /* * bio and nxt are contiguous in memory; check if the queue allows * these two to be merged into one */ - if (BIO_SEG_BOUNDARY(q, bio, nxt)) + if (BIOVEC_SEG_BOUNDARY(q, &end_bv, &nxt_bv)) return 1; return 0; } -static void +static inline void __blk_segment_map_sg(struct request_queue *q, struct bio_vec *bvec, - struct scatterlist *sglist, struct bio_vec **bvprv, + struct scatterlist *sglist, struct bio_vec *bvprv, struct scatterlist **sg, int *nsegs, int *cluster) { int nbytes = bvec->bv_len; - if (*bvprv && *cluster) { + if (*sg && *cluster) { if ((*sg)->length + nbytes > queue_max_segment_size(q)) goto new_segment; - if (!BIOVEC_PHYS_MERGEABLE(*bvprv, bvec)) + if (!BIOVEC_PHYS_MERGEABLE(bvprv, bvec)) goto new_segment; - if (!BIOVEC_SEG_BOUNDARY(q, *bvprv, bvec)) + if (!BIOVEC_SEG_BOUNDARY(q, bvprv, bvec)) goto new_segment; (*sg)->length += nbytes; @@ -150,7 +158,7 @@ new_segment: sg_set_page(*sg, bvec->bv_page, nbytes, bvec->bv_offset); (*nsegs)++; } - *bvprv = bvec; + *bvprv = *bvec; } /* @@ -160,7 +168,7 @@ new_segment: int blk_rq_map_sg(struct request_queue *q, struct request *rq, struct scatterlist *sglist) { - struct bio_vec *bvec, *bvprv; + struct bio_vec bvec, bvprv = { NULL }; struct req_iterator iter; struct scatterlist *sg; int nsegs, cluster; @@ -171,10 +179,9 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq, /* * for each bio in rq */ - bvprv = NULL; sg = NULL; rq_for_each_segment(bvec, rq, iter) { - __blk_segment_map_sg(q, bvec, sglist, &bvprv, &sg, + __blk_segment_map_sg(q, &bvec, sglist, &bvprv, &sg, &nsegs, &cluster); } /* segments in rq */ @@ -223,18 +230,17 @@ EXPORT_SYMBOL(blk_rq_map_sg); int blk_bio_map_sg(struct request_queue *q, struct bio *bio, struct scatterlist *sglist) { - struct bio_vec *bvec, *bvprv; + struct bio_vec bvec, bvprv = { NULL }; struct scatterlist *sg; int nsegs, cluster; - unsigned long i; + struct bvec_iter iter; nsegs = 0; cluster = blk_queue_cluster(q); - bvprv = NULL; sg = NULL; - bio_for_each_segment(bvec, bio, i) { - __blk_segment_map_sg(q, bvec, sglist, &bvprv, &sg, + bio_for_each_segment(bvec, bio, iter) { + __blk_segment_map_sg(q, &bvec, sglist, &bvprv, &sg, &nsegs, &cluster); } /* segments in bio */ @@ -543,9 +549,9 @@ bool blk_rq_merge_ok(struct request *rq, struct bio *bio) int blk_try_merge(struct request *rq, struct bio *bio) { - if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_sector) + if (blk_rq_pos(rq) + blk_rq_sectors(rq) == bio->bi_iter.bi_sector) return ELEVATOR_BACK_MERGE; - else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_sector) + else if (blk_rq_pos(rq) - bio_sectors(bio) == bio->bi_iter.bi_sector) return ELEVATOR_FRONT_MERGE; return ELEVATOR_NO_MERGE; } diff --git a/block/blk-mq-cpu.c b/block/blk-mq-cpu.c index 0045ace9bdf0..3146befb56aa 100644 --- a/block/blk-mq-cpu.c +++ b/block/blk-mq-cpu.c @@ -28,36 +28,6 @@ static int blk_mq_main_cpu_notify(struct notifier_block *self, return NOTIFY_OK; } -static void blk_mq_cpu_notify(void *data, unsigned long action, - unsigned int cpu) -{ - if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) { - /* - * If the CPU goes away, ensure that we run any pending - * completions. - */ - struct llist_node *node; - struct request *rq; - - local_irq_disable(); - - node = llist_del_all(&per_cpu(ipi_lists, cpu)); - while (node) { - struct llist_node *next = node->next; - - rq = llist_entry(node, struct request, ll_list); - __blk_mq_end_io(rq, rq->errors); - node = next; - } - - local_irq_enable(); - } -} - -static struct notifier_block __cpuinitdata blk_mq_main_cpu_notifier = { - .notifier_call = blk_mq_main_cpu_notify, -}; - void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier) { BUG_ON(!notifier->notify); @@ -82,12 +52,7 @@ void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier, notifier->data = data; } -static struct blk_mq_cpu_notifier __cpuinitdata cpu_notifier = { - .notify = blk_mq_cpu_notify, -}; - void __init blk_mq_cpu_init(void) { - register_hotcpu_notifier(&blk_mq_main_cpu_notifier); - blk_mq_register_cpu_notifier(&cpu_notifier); + hotcpu_notifier(blk_mq_main_cpu_notify, 0); } diff --git a/block/blk-mq.c b/block/blk-mq.c index c79126e11030..57039fcd9c93 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -27,8 +27,6 @@ static LIST_HEAD(all_q_list); static void __blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx); -DEFINE_PER_CPU(struct llist_head, ipi_lists); - static struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q, unsigned int cpu) { @@ -106,10 +104,13 @@ static int blk_mq_queue_enter(struct request_queue *q) spin_lock_irq(q->queue_lock); ret = wait_event_interruptible_lock_irq(q->mq_freeze_wq, - !blk_queue_bypass(q), *q->queue_lock); + !blk_queue_bypass(q) || blk_queue_dying(q), + *q->queue_lock); /* inc usage with lock hold to avoid freeze_queue runs here */ - if (!ret) + if (!ret && !blk_queue_dying(q)) __percpu_counter_add(&q->mq_usage_counter, 1, 1000000); + else if (blk_queue_dying(q)) + ret = -ENODEV; spin_unlock_irq(q->queue_lock); return ret; @@ -120,6 +121,22 @@ static void blk_mq_queue_exit(struct request_queue *q) __percpu_counter_add(&q->mq_usage_counter, -1, 1000000); } +static void __blk_mq_drain_queue(struct request_queue *q) +{ + while (true) { + s64 count; + + spin_lock_irq(q->queue_lock); + count = percpu_counter_sum(&q->mq_usage_counter); + spin_unlock_irq(q->queue_lock); + + if (count == 0) + break; + blk_mq_run_queues(q, false); + msleep(10); + } +} + /* * Guarantee no request is in use, so we can change any data structure of * the queue afterward. @@ -133,21 +150,13 @@ static void blk_mq_freeze_queue(struct request_queue *q) queue_flag_set(QUEUE_FLAG_BYPASS, q); spin_unlock_irq(q->queue_lock); - if (!drain) - return; - - while (true) { - s64 count; - - spin_lock_irq(q->queue_lock); - count = percpu_counter_sum(&q->mq_usage_counter); - spin_unlock_irq(q->queue_lock); + if (drain) + __blk_mq_drain_queue(q); +} - if (count == 0) - break; - blk_mq_run_queues(q, false); - msleep(10); - } +void blk_mq_drain_queue(struct request_queue *q) +{ + __blk_mq_drain_queue(q); } static void blk_mq_unfreeze_queue(struct request_queue *q) @@ -179,6 +188,8 @@ static void blk_mq_rq_ctx_init(struct request_queue *q, struct blk_mq_ctx *ctx, rq->mq_ctx = ctx; rq->cmd_flags = rw_flags; + rq->start_time = jiffies; + set_start_time_ns(rq); ctx->rq_dispatched[rw_is_sync(rw_flags)]++; } @@ -305,7 +316,7 @@ void blk_mq_complete_request(struct request *rq, int error) struct bio *next = bio->bi_next; bio->bi_next = NULL; - bytes += bio->bi_size; + bytes += bio->bi_iter.bi_size; blk_mq_bio_endio(rq, bio, error); bio = next; } @@ -326,55 +337,12 @@ void __blk_mq_end_io(struct request *rq, int error) blk_mq_complete_request(rq, error); } -#if defined(CONFIG_SMP) - -/* - * Called with interrupts disabled. - */ -static void ipi_end_io(void *data) -{ - struct llist_head *list = &per_cpu(ipi_lists, smp_processor_id()); - struct llist_node *entry, *next; - struct request *rq; - - entry = llist_del_all(list); - - while (entry) { - next = entry->next; - rq = llist_entry(entry, struct request, ll_list); - __blk_mq_end_io(rq, rq->errors); - entry = next; - } -} - -static int ipi_remote_cpu(struct blk_mq_ctx *ctx, const int cpu, - struct request *rq, const int error) +static void blk_mq_end_io_remote(void *data) { - struct call_single_data *data = &rq->csd; - - rq->errors = error; - rq->ll_list.next = NULL; + struct request *rq = data; - /* - * If the list is non-empty, an existing IPI must already - * be "in flight". If that is the case, we need not schedule - * a new one. - */ - if (llist_add(&rq->ll_list, &per_cpu(ipi_lists, ctx->cpu))) { - data->func = ipi_end_io; - data->flags = 0; - __smp_call_function_single(ctx->cpu, data, 0); - } - - return true; -} -#else /* CONFIG_SMP */ -static int ipi_remote_cpu(struct blk_mq_ctx *ctx, const int cpu, - struct request *rq, const int error) -{ - return false; + __blk_mq_end_io(rq, rq->errors); } -#endif /* * End IO on this request on a multiqueue enabled driver. We'll either do @@ -390,11 +358,15 @@ void blk_mq_end_io(struct request *rq, int error) return __blk_mq_end_io(rq, error); cpu = get_cpu(); - - if (cpu == ctx->cpu || !cpu_online(ctx->cpu) || - !ipi_remote_cpu(ctx, cpu, rq, error)) + if (cpu != ctx->cpu && cpu_online(ctx->cpu)) { + rq->errors = error; + rq->csd.func = blk_mq_end_io_remote; + rq->csd.info = rq; + rq->csd.flags = 0; + __smp_call_function_single(ctx->cpu, &rq->csd, 0); + } else { __blk_mq_end_io(rq, error); - + } put_cpu(); } EXPORT_SYMBOL(blk_mq_end_io); @@ -1091,8 +1063,8 @@ static void blk_mq_free_rq_map(struct blk_mq_hw_ctx *hctx) struct page *page; while (!list_empty(&hctx->page_list)) { - page = list_first_entry(&hctx->page_list, struct page, list); - list_del_init(&page->list); + page = list_first_entry(&hctx->page_list, struct page, lru); + list_del_init(&page->lru); __free_pages(page, page->private); } @@ -1156,7 +1128,7 @@ static int blk_mq_init_rq_map(struct blk_mq_hw_ctx *hctx, break; page->private = this_order; - list_add_tail(&page->list, &hctx->page_list); + list_add_tail(&page->lru, &hctx->page_list); p = page_address(page); entries_per_page = order_to_size(this_order) / rq_size; @@ -1429,7 +1401,6 @@ void blk_mq_free_queue(struct request_queue *q) int i; queue_for_each_hw_ctx(q, hctx, i) { - cancel_delayed_work_sync(&hctx->delayed_work); kfree(hctx->ctx_map); kfree(hctx->ctxs); blk_mq_free_rq_map(hctx); @@ -1451,7 +1422,6 @@ void blk_mq_free_queue(struct request_queue *q) list_del_init(&q->all_q_node); mutex_unlock(&all_q_mutex); } -EXPORT_SYMBOL(blk_mq_free_queue); /* Basically redo blk_mq_init_queue with queue frozen */ static void blk_mq_queue_reinit(struct request_queue *q) @@ -1495,11 +1465,6 @@ static int blk_mq_queue_reinit_notify(struct notifier_block *nb, static int __init blk_mq_init(void) { - unsigned int i; - - for_each_possible_cpu(i) - init_llist_head(&per_cpu(ipi_lists, i)); - blk_mq_cpu_init(); /* Must be called after percpu_counter_hotcpu_callback() */ diff --git a/block/blk-mq.h b/block/blk-mq.h index 52bf1f96a2c2..5c3917984b00 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -27,6 +27,8 @@ void blk_mq_complete_request(struct request *rq, int error); void blk_mq_run_request(struct request *rq, bool run_queue, bool async); void blk_mq_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async); void blk_mq_init_flush(struct request_queue *q); +void blk_mq_drain_queue(struct request_queue *q); +void blk_mq_free_queue(struct request_queue *q); /* * CPU hotplug helpers @@ -38,7 +40,6 @@ void blk_mq_init_cpu_notifier(struct blk_mq_cpu_notifier *notifier, void blk_mq_register_cpu_notifier(struct blk_mq_cpu_notifier *notifier); void blk_mq_unregister_cpu_notifier(struct blk_mq_cpu_notifier *notifier); void blk_mq_cpu_init(void); -DECLARE_PER_CPU(struct llist_head, ipi_lists); /* * CPU -> queue mappings diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 97779522472f..8095c4a21fc0 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -11,6 +11,7 @@ #include "blk.h" #include "blk-cgroup.h" +#include "blk-mq.h" struct queue_sysfs_entry { struct attribute attr; diff --git a/block/blk-throttle.c b/block/blk-throttle.c index a760857e6b62..1474c3ab7e72 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -877,14 +877,14 @@ static bool tg_with_in_bps_limit(struct throtl_grp *tg, struct bio *bio, do_div(tmp, HZ); bytes_allowed = tmp; - if (tg->bytes_disp[rw] + bio->bi_size <= bytes_allowed) { + if (tg->bytes_disp[rw] + bio->bi_iter.bi_size <= bytes_allowed) { if (wait) *wait = 0; return 1; } /* Calc approx time to dispatch */ - extra_bytes = tg->bytes_disp[rw] + bio->bi_size - bytes_allowed; + extra_bytes = tg->bytes_disp[rw] + bio->bi_iter.bi_size - bytes_allowed; jiffy_wait = div64_u64(extra_bytes * HZ, tg->bps[rw]); if (!jiffy_wait) @@ -987,7 +987,7 @@ static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio) bool rw = bio_data_dir(bio); /* Charge the bio to the group */ - tg->bytes_disp[rw] += bio->bi_size; + tg->bytes_disp[rw] += bio->bi_iter.bi_size; tg->io_disp[rw]++; /* |