diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2022-08-02 13:46:35 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2022-08-02 13:46:35 -0700 |
| commit | c013d0af81f60cc7dbe357c4e2a925fb6738dbfe (patch) | |
| tree | 171dfdf928d0450a3fa98a58b2297d857804bb35 /block | |
| parent | 42df1cbf6a4726934cc5dac12bf263aa73c49fa3 (diff) | |
| parent | 8d9fdb6011b4d413271eba3a62e10f89efecc419 (diff) | |
| download | linux-c013d0af81f60cc7dbe357c4e2a925fb6738dbfe.tar.gz linux-c013d0af81f60cc7dbe357c4e2a925fb6738dbfe.tar.bz2 linux-c013d0af81f60cc7dbe357c4e2a925fb6738dbfe.zip | |
Merge tag 'for-5.20/block-2022-07-29' of git://git.kernel.dk/linux-block
Pull block updates from Jens Axboe:
- Improve the type checking of request flags (Bart)
- Ensure queue mapping for a single queues always picks the right queue
(Bart)
- Sanitize the io priority handling (Jan)
- rq-qos race fix (Jinke)
- Reserved tags handling improvements (John)
- Separate memory alignment from file/disk offset aligment for O_DIRECT
(Keith)
- Add new ublk driver, userspace block driver using io_uring for
communication with the userspace backend (Ming)
- Use try_cmpxchg() to cleanup the code in various spots (Uros)
- Finally remove bdevname() (Christoph)
- Clean up the zoned device handling (Christoph)
- Clean up independent access range support (Christoph)
- Clean up and improve block sysfs handling (Christoph)
- Clean up and improve teardown of block devices.
This turns the usual two step process into something that is simpler
to implement and handle in block drivers (Christoph)
- Clean up chunk size handling (Christoph)
- Misc cleanups and fixes (Bart, Bo, Dan, GuoYong, Jason, Keith, Liu,
Ming, Sebastian, Yang, Ying)
* tag 'for-5.20/block-2022-07-29' of git://git.kernel.dk/linux-block: (178 commits)
ublk_drv: fix double shift bug
ublk_drv: make sure that correct flags(features) returned to userspace
ublk_drv: fix error handling of ublk_add_dev
ublk_drv: fix lockdep warning
block: remove __blk_get_queue
block: call blk_mq_exit_queue from disk_release for never added disks
blk-mq: fix error handling in __blk_mq_alloc_disk
ublk: defer disk allocation
ublk: rewrite ublk_ctrl_get_queue_affinity to not rely on hctx->cpumask
ublk: fold __ublk_create_dev into ublk_ctrl_add_dev
ublk: cleanup ublk_ctrl_uring_cmd
ublk: simplify ublk_ch_open and ublk_ch_release
ublk: remove the empty open and release block device operations
ublk: remove UBLK_IO_F_PREFLUSH
ublk: add a MAINTAINERS entry
block: don't allow the same type rq_qos add more than once
mmc: fix disk/queue leak in case of adding disk failure
ublk_drv: fix an IS_ERR() vs NULL check
ublk: remove UBLK_IO_F_INTEGRITY
ublk_drv: remove unneeded semicolon
...
Diffstat (limited to 'block')
45 files changed, 678 insertions, 688 deletions
diff --git a/block/Kconfig b/block/Kconfig index 50b17e260fa2..444c5ab3b67e 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -147,7 +147,6 @@ config BLK_CGROUP_FC_APPID config BLK_CGROUP_IOCOST bool "Enable support for cost model based cgroup IO controller" depends on BLK_CGROUP - select BLK_RQ_IO_DATA_LEN select BLK_RQ_ALLOC_TIME help Enabling this option enables the .weight interface for cost diff --git a/block/bdev.c b/block/bdev.c index 5fe06c1f2def..ce05175e71ce 100644 --- a/block/bdev.c +++ b/block/bdev.c @@ -54,12 +54,10 @@ static void bdev_write_inode(struct block_device *bdev) while (inode->i_state & I_DIRTY) { spin_unlock(&inode->i_lock); ret = write_inode_now(inode, true); - if (ret) { - char name[BDEVNAME_SIZE]; - pr_warn_ratelimited("VFS: Dirty inode writeback failed " - "for block device %s (err=%d).\n", - bdevname(bdev, name), ret); - } + if (ret) + pr_warn_ratelimited( + "VFS: Dirty inode writeback failed for block device %pg (err=%d).\n", + bdev, ret); spin_lock(&inode->i_lock); } spin_unlock(&inode->i_lock); diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index 09574af83566..30b15a9a47c4 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -220,46 +220,46 @@ void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg) } void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq, - unsigned int op) + blk_opf_t opf) { - blkg_rwstat_add(&bfqg->stats.queued, op, 1); + blkg_rwstat_add(&bfqg->stats.queued, opf, 1); bfqg_stats_end_empty_time(&bfqg->stats); if (!(bfqq == ((struct bfq_data *)bfqg->bfqd)->in_service_queue)) bfqg_stats_set_start_group_wait_time(bfqg, bfqq_group(bfqq)); } -void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) +void bfqg_stats_update_io_remove(struct bfq_group *bfqg, blk_opf_t opf) { - blkg_rwstat_add(&bfqg->stats.queued, op, -1); + blkg_rwstat_add(&bfqg->stats.queued, opf, -1); } -void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) +void bfqg_stats_update_io_merged(struct bfq_group *bfqg, blk_opf_t opf) { - blkg_rwstat_add(&bfqg->stats.merged, op, 1); + blkg_rwstat_add(&bfqg->stats.merged, opf, 1); } void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns, - u64 io_start_time_ns, unsigned int op) + u64 io_start_time_ns, blk_opf_t opf) { struct bfqg_stats *stats = &bfqg->stats; u64 now = ktime_get_ns(); if (now > io_start_time_ns) - blkg_rwstat_add(&stats->service_time, op, + blkg_rwstat_add(&stats->service_time, opf, now - io_start_time_ns); if (io_start_time_ns > start_time_ns) - blkg_rwstat_add(&stats->wait_time, op, + blkg_rwstat_add(&stats->wait_time, opf, io_start_time_ns - start_time_ns); } #else /* CONFIG_BFQ_CGROUP_DEBUG */ void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq, - unsigned int op) { } -void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op) { } -void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op) { } + blk_opf_t opf) { } +void bfqg_stats_update_io_remove(struct bfq_group *bfqg, blk_opf_t opf) { } +void bfqg_stats_update_io_merged(struct bfq_group *bfqg, blk_opf_t opf) { } void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns, - u64 io_start_time_ns, unsigned int op) { } + u64 io_start_time_ns, blk_opf_t opf) { } void bfqg_stats_update_dequeue(struct bfq_group *bfqg) { } void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg) { } void bfqg_stats_update_idle_time(struct bfq_group *bfqg) { } @@ -706,10 +706,10 @@ void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq, } /** - * __bfq_bic_change_cgroup - move @bic to @cgroup. + * __bfq_bic_change_cgroup - move @bic to @bfqg. * @bfqd: the queue descriptor. * @bic: the bic to move. - * @blkcg: the blk-cgroup to move to. + * @bfqg: the group to move to. * * Move bic to blkcg, assuming that bfqd->lock is held; which makes * sure that the reference to cgroup is valid across the call (see @@ -863,6 +863,7 @@ static void bfq_flush_idle_tree(struct bfq_service_tree *st) * @bfqd: the device data structure with the root group. * @entity: the entity to move, if entity is a leaf; or the parent entity * of an active leaf entity to move, if entity is not a leaf. + * @ioprio_class: I/O priority class to reparent. */ static void bfq_reparent_leaf_entity(struct bfq_data *bfqd, struct bfq_entity *entity, @@ -892,6 +893,7 @@ static void bfq_reparent_leaf_entity(struct bfq_data *bfqd, * @bfqd: the device data structure with the root group. * @bfqg: the group to move from. * @st: the service tree to start the search from. + * @ioprio_class: I/O priority class to reparent. */ static void bfq_reparent_active_queues(struct bfq_data *bfqd, struct bfq_group *bfqg, @@ -1471,8 +1473,6 @@ struct bfq_group *bfqq_group(struct bfq_queue *bfqq) return bfqq->bfqd->root_group; } -void bfqg_and_blkg_get(struct bfq_group *bfqg) {} - void bfqg_and_blkg_put(struct bfq_group *bfqg) {} struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node) diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index e6d7e6b01a05..c740b41fe0a4 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -668,19 +668,19 @@ static bool bfqq_request_over_limit(struct bfq_queue *bfqq, int limit) * significantly affect service guarantees coming from the BFQ scheduling * algorithm. */ -static void bfq_limit_depth(unsigned int op, struct blk_mq_alloc_data *data) +static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) { struct bfq_data *bfqd = data->q->elevator->elevator_data; struct bfq_io_cq *bic = bfq_bic_lookup(data->q); - struct bfq_queue *bfqq = bic ? bic_to_bfqq(bic, op_is_sync(op)) : NULL; + struct bfq_queue *bfqq = bic ? bic_to_bfqq(bic, op_is_sync(opf)) : NULL; int depth; unsigned limit = data->q->nr_requests; /* Sync reads have full depth available */ - if (op_is_sync(op) && !op_is_write(op)) { + if (op_is_sync(opf) && !op_is_write(opf)) { depth = 0; } else { - depth = bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(op)]; + depth = bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(opf)]; limit = (limit * depth) >> bfqd->full_depth_shift; } @@ -693,7 +693,7 @@ static void bfq_limit_depth(unsigned int op, struct blk_mq_alloc_data *data) depth = 1; bfq_log(bfqd, "[%s] wr_busy %d sync %d depth %u", - __func__, bfqd->wr_busy_queues, op_is_sync(op), depth); + __func__, bfqd->wr_busy_queues, op_is_sync(opf), depth); if (depth) data->shallow_depth = depth; } @@ -6104,7 +6104,7 @@ static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq) static void bfq_update_insert_stats(struct request_queue *q, struct bfq_queue *bfqq, bool idle_timer_disabled, - unsigned int cmd_flags) + blk_opf_t cmd_flags) { if (!bfqq) return; @@ -6129,7 +6129,7 @@ static void bfq_update_insert_stats(struct request_queue *q, static inline void bfq_update_insert_stats(struct request_queue *q, struct bfq_queue *bfqq, bool idle_timer_disabled, - unsigned int cmd_flags) {} + blk_opf_t cmd_flags) {} #endif /* CONFIG_BFQ_CGROUP_DEBUG */ static struct bfq_queue *bfq_init_rq(struct request *rq); @@ -6141,7 +6141,7 @@ static void bfq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq, struct bfq_data *bfqd = q->elevator->elevator_data; struct bfq_queue *bfqq; bool idle_timer_disabled = false; - unsigned int cmd_flags; + blk_opf_t cmd_flags; LIST_HEAD(free); #ifdef CONFIG_BFQ_GROUP_IOSCHED diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h index ca8177d7bf7c..ad8e513d7e87 100644 --- a/block/bfq-iosched.h +++ b/block/bfq-iosched.h @@ -994,11 +994,11 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg); void bfqg_stats_update_legacy_io(struct request_queue *q, struct request *rq); void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq, - unsigned int op); -void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op); -void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op); + blk_opf_t opf); +void bfqg_stats_update_io_remove(struct bfq_group *bfqg, blk_opf_t opf); +void bfqg_stats_update_io_merged(struct bfq_group *bfqg, blk_opf_t opf); void bfqg_stats_update_completion(struct bfq_group *bfqg, u64 start_time_ns, - u64 io_start_time_ns, unsigned int op); + u64 io_start_time_ns, blk_opf_t opf); void bfqg_stats_update_dequeue(struct bfq_group *bfqg); void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg); void bfqg_stats_update_idle_time(struct bfq_group *bfqg); diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c index f8eb340381cf..983413cdefad 100644 --- a/block/bfq-wf2q.c +++ b/block/bfq-wf2q.c @@ -1360,6 +1360,8 @@ left: /** * __bfq_lookup_next_entity - return the first eligible entity in @st. * @st: the service tree. + * @in_service: whether or not there is an in-service entity for the sched_data + * this active tree belongs to. * * If there is no in-service entity for the sched_data st belongs to, * then return the entity that will be set in service if: @@ -1472,9 +1474,6 @@ static struct bfq_entity *bfq_lookup_next_entity(struct bfq_sched_data *sd, break; } - if (!entity) - return NULL; - return entity; } diff --git a/block/bio.c b/block/bio.c index 51c99f2c5c90..6f9f883f9a65 100644 --- a/block/bio.c +++ b/block/bio.c @@ -239,7 +239,7 @@ static void bio_free(struct bio *bio) * when IO has completed, or when the bio is released. */ void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table, - unsigned short max_vecs, unsigned int opf) + unsigned short max_vecs, blk_opf_t opf) { bio->bi_next = NULL; bio->bi_bdev = bdev; @@ -292,7 +292,7 @@ EXPORT_SYMBOL(bio_init); * preserved are the ones that are initialized by bio_alloc_bioset(). See * comment in struct bio. */ -void bio_reset(struct bio *bio, struct block_device *bdev, unsigned int opf) +void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf) { bio_uninit(bio); memset(bio, 0, BIO_RESET_BYTES); @@ -341,7 +341,7 @@ void bio_chain(struct bio *bio, struct bio *parent) EXPORT_SYMBOL(bio_chain); struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev, - unsigned int nr_pages, unsigned int opf, gfp_t gfp) + unsigned int nr_pages, blk_opf_t opf, gfp_t gfp) { struct bio *new = bio_alloc(bdev, nr_pages, opf, gfp); @@ -409,7 +409,7 @@ static void punt_bios_to_rescuer(struct bio_set *bs) } static struct bio *bio_alloc_percpu_cache(struct block_device *bdev, - unsigned short nr_vecs, unsigned int opf, gfp_t gfp, + unsigned short nr_vecs, blk_opf_t opf, gfp_t gfp, struct bio_set *bs) { struct bio_alloc_cache *cache; @@ -468,7 +468,7 @@ static struct bio *bio_alloc_percpu_cache(struct block_device *bdev, * Returns: Pointer to new bio on success, NULL on failure. */ struct bio *bio_alloc_bioset(struct block_device *bdev, unsigned short nr_vecs, - unsigned int opf, gfp_t gfp_mask, + blk_opf_t opf, gfp_t gfp_mask, struct bio_set *bs) { gfp_t saved_gfp = gfp_mask; @@ -1033,7 +1033,7 @@ int bio_add_zone_append_page(struct bio *bio, struct page *page, if (WARN_ON_ONCE(bio_op(bio) != REQ_OP_ZONE_APPEND)) return 0; - if (WARN_ON_ONCE(!blk_queue_is_zoned(q))) + if (WARN_ON_ONCE(!bdev_is_zoned(bio->bi_bdev))) return 0; return bio_add_hw_page(q, bio, page, len, offset, @@ -1159,6 +1159,37 @@ static void bio_put_pages(struct page **pages, size_t size, size_t off) put_page(pages[i]); } +static int bio_iov_add_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int offset) +{ + bool same_page = false; + + if (!__bio_try_merge_page(bio, page, len, offset, &same_page)) { + if (WARN_ON_ONCE(bio_full(bio, len))) + return -EINVAL; + __bio_add_page(bio, page, len, offset); + return 0; + } + + if (same_page) + put_page(page); + return 0; +} + +static int bio_iov_add_zone_append_page(struct bio *bio, struct page *page, + unsigned int len, unsigned int offset) +{ + struct request_queue *q = bdev_get_queue(bio->bi_bdev); + bool same_page = false; + + if (bio_add_hw_page(q, bio, page, len, offset, + queue_max_zone_append_sectors(q), &same_page) != len) + return -EINVAL; + if (same_page) + put_page(page); + return 0; +} + #define PAGE_PTRS_PER_BVEC (sizeof(struct bio_vec) / sizeof(struct page *)) /** @@ -1177,7 +1208,6 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt; struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; struct page **pages = (struct page **)bv; - bool same_page = false; ssize_t size, left; unsigned len, i; size_t offset; @@ -1186,82 +1216,43 @@ static int __bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) * Move page array up in the allocated memory for the bio vecs as far as * possible so that we can start filling biovecs from the beginning * without overwriting the temporary page array. - */ + */ BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2); pages += entries_left * (PAGE_PTRS_PER_BVEC - 1); - size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset); - if (unlikely(size <= 0)) - return size ? size : -EFAULT; - - for (left = size, i = 0; left > 0; left -= len, i++) { - struct page *page = pages[i]; - - len = min_t(size_t, PAGE_SIZE - offset, left); - - if (__bio_try_merge_page(bio, page, len, offset, &same_page)) { - if (same_page) - put_page(page); - } else { - if (WARN_ON_ONCE(bio_full(bio, len))) { - bio_put_pages(pages + i, left, offset); - return -EINVAL; - } - __bio_add_page(bio, page, len, offset); - } - offset = 0; - } - - iov_iter_advance(iter, size); - return 0; -} - -static int __bio_iov_append_get_pages(struct bio *bio, struct iov_iter *iter) -{ - unsigned short nr_pages = bio->bi_max_vecs - bio->bi_vcnt; - unsigned short entries_left = bio->bi_max_vecs - bio->bi_vcnt; - struct request_queue *q = bdev_get_queue(bio->bi_bdev); - unsigned int max_append_sectors = queue_max_zone_append_sectors(q); - struct bio_vec *bv = bio->bi_io_vec + bio->bi_vcnt; - struct page **pages = (struct page **)bv; - ssize_t size, left; - unsigned len, i; - size_t offset; - int ret = 0; - - if (WARN_ON_ONCE(!max_append_sectors)) - return 0; - /* - * Move page array up in the allocated memory for the bio vecs as far as - * possible so that we can start filling biovecs from the beginning - * without overwriting the temporary page array. + * Each segment in the iov is required to be a block size multiple. + * However, we may not be able to get the entire segment if it spans + * more pages than bi_max_vecs allows, so we have to ALIGN_DOWN the + * result to ensure the bio's total size is correct. The remainder of + * the iov data will be picked up in the next bio iteration. */ - BUILD_BUG_ON(PAGE_PTRS_PER_BVEC < 2); - pages += entries_left * (PAGE_PTRS_PER_BVEC - 1); - size = iov_iter_get_pages(iter, pages, LONG_MAX, nr_pages, &offset); + if (size > 0) + size = ALIGN_DOWN(size, bdev_logical_block_size(bio->bi_bdev)); if (unlikely(size <= 0)) return size ? size : -EFAULT; for (left = size, i = 0; left > 0; left -= len, i++) { struct page *page = pages[i]; - bool same_page = false; + int ret; len = min_t(size_t, PAGE_SIZE - offset, left); - if (bio_add_hw_page(q, bio, page, len, offset, - max_append_sectors, &same_page) != len) { + if (bio_op(bio) == REQ_OP_ZONE_APPEND) + ret = bio_iov_add_zone_append_page(bio, page, len, + offset); + else + ret = bio_iov_add_page(bio, page, len, offset); + + if (ret) { bio_put_pages(pages + i, left, offset); - ret = -EINVAL; - break; + return ret; } - if (same_page) - put_page(page); offset = 0; } - iov_iter_advance(iter, size - left); - return ret; + iov_iter_advance(iter, size); + return 0; } /** @@ -1298,10 +1289,7 @@ int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter) } do { - if (bio_op(bio) == REQ_OP_ZONE_APPEND) - ret = __bio_iov_append_get_pages(bio, iter); - else - ret = __bio_iov_iter_get_pages(bio, iter); + ret = __bio_iov_iter_get_pages(bio, iter); } while (!ret && iov_iter_count(iter) && !bio_full(bio, 0)); /* don't account direct I/O as memory stall */ diff --git a/block/blk-cgroup-rwstat.h b/block/blk-cgroup-rwstat.h index 9f2723b34b75..022527b0b043 100644 --- a/block/blk-cgroup-rwstat.h +++ b/block/blk-cgroup-rwstat.h @@ -59,20 +59,20 @@ void blkg_rwstat_recursive_sum(struct blkcg_gq *blkg, struct blkcg_policy *pol, * caller is responsible for synchronizing calls to this function. */ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat, - unsigned int op, uint64_t val) + blk_opf_t opf, uint64_t val) { struct percpu_counter *cnt; - if (op_is_discard(op)) + if (op_is_discard(opf)) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD]; - else if (op_is_write(op)) + else if (op_is_write(opf)) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE]; else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ]; percpu_counter_add_batch(cnt, val, BLKG_STAT_CPU_BATCH); - if (op_is_sync(op)) + if (op_is_sync(opf)) cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_SYNC]; else cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_ASYNC]; diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 764e740b0c0f..869af9d72bcf 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -846,6 +846,21 @@ static void blkg_iostat_sub(struct blkg_iostat *dst, struct blkg_iostat *src) } } +static void blkcg_iostat_update(struct blkcg_gq *blkg, struct blkg_iostat *cur, + struct blkg_iostat *last) +{ + struct blkg_iostat delta; + unsigned long flags; + + /* propagate percpu delta to global */ + flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); + blkg_iostat_set(&delta, cur); + blkg_iostat_sub(&delta, last); + blkg_iostat_add(&blkg->iostat.cur, &delta); + blkg_iostat_add(last, &delta); + u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); +} + static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) { struct blkcg *blkcg = css_to_blkcg(css); @@ -860,8 +875,7 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) { struct blkcg_gq *parent = blkg->parent; struct blkg_iostat_set *bisc = per_cpu_ptr(blkg->iostat_cpu, cpu); - struct blkg_iostat cur, delta; - unsigned long flags; + struct blkg_iostat cur; unsigned int seq; /* fetch the current per-cpu values */ @@ -870,23 +884,12 @@ static void blkcg_rstat_flush(struct cgroup_subsys_state *css, int cpu) blkg_iostat_set(&cur, &bisc->cur); } while (u64_stats_fetch_retry(&bisc->sync, seq)); - /* propagate percpu delta to global */ - flags = u64_stats_update_begin_irqsave(&blkg->iostat.sync); - blkg_iostat_set(&delta, &cur); - blkg_iostat_sub(&delta, &bisc->last); - blkg_iostat_add(&blkg->iostat.cur, &delta); - blkg_iostat_add(&bisc->last, &delta); - u64_stats_update_end_irqrestore(&blkg->iostat.sync, flags); + blkcg_iostat_update(blkg, &cur, &bisc->last); /* propagate global delta to parent (unless that's root) */ - if (parent && parent->parent) { - flags = u64_stats_update_begin_irqsave(&parent->iostat.sync); - blkg_iostat_set(&delta, &blkg->iostat.cur); - blkg_iostat_sub(&delta, &blkg->iostat.last); - blkg_iostat_add(&parent->iostat.cur, &delta); - blkg_iostat_add(&blkg->iostat.last, &delta); - u64_stats_update_end_irqrestore(&parent->iostat.sync, flags); - } + if (parent && parent->parent) + blkcg_iostat_update(parent, &blkg->iostat.cur, + &blkg->iostat.last); } rcu_read_unlock(); @@ -1299,6 +1302,7 @@ int blkcg_init_queue(struct request_queue *q) ret = blk_iolatency_init(q); if (ret) { blk_throtl_exit(q); + blk_ioprio_exit(q); goto err_destroy_all; } @@ -1529,6 +1533,18 @@ void blkcg_deactivate_policy(struct request_queue *q, } EXPORT_SYMBOL_GPL(blkcg_deactivate_policy); +static void blkcg_free_all_cpd(struct blkcg_policy *pol) +{ + struct blkcg *blkcg; + + list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { + if (blkcg->cpd[pol->plid]) { + pol->cpd_free_fn(blkcg->cpd[pol->plid]); + blkcg->cpd[pol->plid] = NULL; + } + } +} + /** * blkcg_policy_register - register a blkcg policy * @pol: blkcg policy to register @@ -1593,14 +1609,9 @@ int blkcg_policy_register(struct blkcg_policy *pol) return 0; err_free_cpds: - if (pol->cpd_free_fn) { - list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { - if (blkcg->cpd[pol->plid]) { - pol->cpd_free_fn(blkcg->cpd[pol->plid]); - blkcg->cpd[pol->plid] = NULL; - } - } - } + if (pol->cpd_free_fn) + blkcg_free_all_cpd(pol); + blkcg_policy[pol->plid] = NULL; err_unlock: mutex_unlock(&blkcg_pol_mutex); @@ -1617,8 +1628,6 @@ EXPORT_SYMBOL_GPL(blkcg_policy_register); */ void blkcg_policy_unregister(struct blkcg_policy *pol) { - struct blkcg *blkcg; - mutex_lock(&blkcg_pol_register_mutex); if (WARN_ON(blkcg_policy[pol->plid] != pol)) @@ -1633,14 +1642,9 @@ void blkcg_policy_unregister(struct blkcg_policy *pol) /* remove cpds and unregister */ mutex_lock(&blkcg_pol_mutex); - if (pol->cpd_free_fn) { - list_for_each_entry(blkcg, &all_blkcgs, all_blkcgs_node) { - if (blkcg->cpd[pol->plid]) { - pol->cpd_free_fn(blkcg->cpd[pol->plid]); - blkcg->cpd[pol->plid] = NULL; - } - } - } + if (pol->cpd_free_fn) + blkcg_free_all_cpd(pol); + blkcg_policy[pol->plid] = NULL; mutex_unlock(&blkcg_pol_mutex); @@ -1696,7 +1700,7 @@ static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now) * everybody is happy with their IO latencies. */ if (time_before64(old + NSEC_PER_SEC, now) && - atomic64_cmpxchg(&blkg->delay_start, old, now) == old) { + atomic64_try_cmpxchg(&blkg->delay_start, &old, now)) { u64 cur = atomic64_read(&blkg->delay_nsec); u64 sub = min_t(u64, blkg->last_delay, now - old); int cur_use = atomic_read(&blkg->use_delay); diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h index d4de0a35e066..d2724d1dd7c9 100644 --- a/block/blk-cgroup.h +++ b/block/blk-cgroup.h @@ -430,12 +430,8 @@ static inline int blkcg_unuse_delay(struct blkcg_gq *blkg) * then check to see if we were the last delay so we can drop the * congestion count on the cgroup. */ - while (old) { - int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1); - if (cur == old) - break; - old = cur; - } + while (old && !atomic_try_cmpxchg(&blkg->use_delay, &old, old - 1)) + ; if (old == 0) return 0; @@ -458,7 +454,7 @@ static inline void blkcg_set_delay(struct blkcg_gq *blkg, u64 delay) int old = atomic_read(&blkg->use_delay); /* We only want 1 person setting the congestion count for this blkg. */ - if (!old && atomic_cmpxchg(&blkg->use_delay, old, -1) == old) + if (!old && atomic_try_cmpxchg(&blkg->use_delay, &old, -1)) atomic_inc(&blkg->blkcg->css.cgroup->congestion_count); atomic64_set(&blkg->delay_nsec, delay); @@ -475,7 +471,7 @@ static inline void blkcg_clear_delay(struct blkcg_gq *blkg) int old = atomic_read(&blkg->use_delay); /* We only want 1 person clearing the congestion count for this blkg. */ - if (old && atomic_cmpxchg(&blkg->use_delay, old, 0) == old) + if (old && atomic_try_cmpxchg(&blkg->use_delay, &old, 0)) atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); } diff --git a/block/blk-core.c b/block/blk-core.c index 27fb1357ad4b..3d286a256d3d 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -136,7 +136,7 @@ static const char *const blk_op_name[] = { * string format. Useful in the debugging and tracing bio or request. For * invalid REQ_OP_XXX it returns string "UNKNOWN". */ -inline const char *blk_op_str(unsigned int op) +inline const char *blk_op_str(enum req_op op) { const char *op_str = "UNKNOWN"; @@ -285,49 +285,6 @@ void blk_queue_start_drain(struct request_queue *q) } /** - * blk_cleanup_queue - shutdown a request queue - * @q: request queue to shutdown - * - * Mark @q DYING, drain all pending requests, mark @q DEAD, destroy and - * put it. All future requests will be failed immediately with -ENODEV. - * - * Context: can sleep - */ -void blk_cleanup_queue(struct request_queue *q) -{ - /* cannot be called from atomic context */ - might_sleep(); - - WARN_ON_ONCE(blk_queue_registered(q)); - - /* mark @q DYING, no new request or merges will be allowed afterwards */ - blk_queue_flag_set(QUEUE_FLAG_DYING, q); - blk_queue_start_drain(q); - - blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q); - blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q); - - /* - * Drain all requests queued before DYING marking. Set DEAD flag to - * prevent that blk_mq_run_hw_queues() accesses the hardware queues - * after draining finished. - */ - blk_freeze_queue(q); - - blk_queue_flag_set(QUEUE_FLAG_DEAD, q); - - blk_sync_queue(q); - if (queue_is_mq(q)) { - blk_mq_cancel_work_sync(q); - blk_mq_exit_queue(q); - } - - /* @q is and will stay empty, shutdown and put */ - blk_put_queue(q); -} -EXPORT_SYMBOL(blk_cleanup_queue); - -/** * blk_queue_enter() - try to increase q->q_usage_counter * @q: request queue pointer * @flags: BLK_MQ_REQ_NOWAIT and/or BLK_MQ_REQ_PM @@ -435,7 +392,7 @@ struct request_queue *blk_alloc_queue(int node_id, bool alloc_srcu) q->last_merge = NULL; - q->id = ida_simple_get(&blk_queue_ida, 0, 0, GFP_KERNEL); + q->id = ida_alloc(&blk_queue_ida, GFP_KERNEL); if (q->id < 0) goto fail_srcu; @@ -485,7 +442,7 @@ fail_stats: fail_split: bioset_exit(&q->bio_split); fail_id: - ida_simple_remove(&blk_queue_ida, q->id); + ida_free(&blk_queue_ida, q->id); fail_srcu: if (alloc_srcu) cleanup_srcu_struct(q->srcu); @@ -504,12 +461,10 @@ fail_q: */ bool blk_get_queue(struct request_queue *q) { - if (likely(!blk_queue_dying(q))) { - __blk_get_queue(q); - return true; - } - - return false; + if (unlikely(blk_queue_dying(q))) + return false; + kobject_get(&q->kobj); + return true; } EXPORT_SYMBOL(blk_get_queue); @@ -608,16 +563,15 @@ static int blk_partition_remap(struct bio *bio) static inline blk_status_t blk_check_zone_append(struct request_queue *q, struct bio *bio) { - sector_t pos = bio->bi_iter.bi_sector; int nr_sectors = bio_sectors(bio); /* Only applicable to zoned block devices */ - if (!blk_queue_is_zoned(q)) + if (!bdev_is_zoned(bio->bi_bdev)) return BLK_STS_NOTSUPP; /* The bio sector must point to the start of a sequential zone */ - if (pos & (blk_queue_zone_sectors(q) - 1) || - !blk_queue_zone_is_seq(q, pos)) + if (bio->bi_iter.bi_sector & (bdev_zone_sectors(bio->bi_bdev) - 1) || + !bio_zone_is_seq(bio)) return BLK_STS_IOERR; /* @@ -762,7 +716,7 @@ void submit_bio_noacct(struct bio *bio) might_sleep(); - plug = blk_mq_plug(q, bio); + plug = blk_mq_plug(bio); if (plug && plug->nowait) bio->bi_opf |= REQ_NOWAIT; @@ -818,11 +772,11 @@ void submit_bio_noacct(struct bio *bio) case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: case REQ_OP_ZONE_FINISH: - if (!blk_queue_is_zoned(q)) + if (!bdev_is_zoned(bio->bi_bdev)) goto not_supported; break; case REQ_OP_ZONE_RESET_ALL: - if (!blk_queue_is_zoned(q) || !blk_queue_zone_resetall(q)) + if (!bdev_is_zoned(bio->bi_bdev) || !blk_queue_zone_resetall(q)) goto not_supported; break; case REQ_OP_WRITE_ZEROES: @@ -987,7 +941,7 @@ void update_io_ticks(struct block_device *part, unsigned long now, bool end) again: stamp = READ_ONCE(part->bd_stamp); if (unlikely(time_after(now, stamp))) { - if (likely(cmpxchg(&part->bd_stamp, stamp, now) == stamp)) + if (likely(try_cmpxchg(&part->bd_stamp, &stamp, now))) __part_stat_add(part, io_ticks, end ? now - stamp : 1); } if (part->bd_partno) { @@ -997,7 +951,7 @@ again: } unsigned long bdev_start_io_acct(struct block_device *bdev, - unsigned int sectors, unsigned int op, + unsigned int sectors, enum req_op op, unsigned long start_time) { const int sgrp = op_stat_group(op); @@ -1038,7 +992,7 @@ unsigned long bio_start_io_acct(struct bio *bio) } EXPORT_SYMBOL_GPL(bio_start_io_acct); -void bdev_end_io_acct(struct block_device *bdev, unsigned int op, +void bdev_end_io_acct(struct block_device *bdev, enum req_op op, unsigned long start_time) { const int sgrp = op_stat_group(op); @@ -1247,7 +1201,7 @@ EXPORT_SYMBOL_GPL(blk_io_schedule); int __init blk_dev_init(void) { - BUILD_BUG_ON(REQ_OP_LAST >= (1 << REQ_OP_BITS)); + BUILD_BUG_ON((__force u32)REQ_OP_LAST >= (1 << REQ_OP_BITS)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * sizeof_field(struct request, cmd_flags)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * diff --git a/block/blk-flush.c b/block/blk-flush.c index c68968724870..d20a0c6b2c66 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -94,7 +94,7 @@ enum { }; static void blk_kick_flush(struct request_queue *q, - struct blk_flush_queue *fq, unsigned int flags); + struct blk_flush_queue *fq, blk_opf_t flags); static inline struct blk_flush_queue * blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx) @@ -173,7 +173,7 @@ static void blk_flush_complete_seq(struct request *rq, { struct request_queue *q = rq->q; struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx]; - unsigned int cmd_flags; + blk_opf_t cmd_flags; BUG_ON(rq->flush.seq & seq); rq->flush.seq |= seq; @@ -290,7 +290,7 @@ bool is_flush_rq(struct request *rq) * */ static void blk_kick_flush(struct request_queue *q, struct blk_flush_queue *fq, - unsigned int flags) + blk_opf_t flags) { struct list_head *pending = &fq->flush_queue[fq->flush_pending_idx]; struct request *first_rq = diff --git a/block/blk-ia-ranges.c b/block/blk-ia-ranges.c index 47c89e65b57f..2bd1d311033b 100644 --- a/block/blk-ia-ranges.c +++ b/block/blk-ia-ranges.c @@ -102,31 +102,18 @@ static struct kobj_type blk_ia_ranges_ktype = { * disk_register_independent_access_ranges - register with sysfs a set of * independent access ranges * @disk: Target disk - * @new_iars: New set of independent access ranges * * Register with sysfs a set of independent access ranges for @disk. - * If @new_iars is not NULL, this set of ranges is registered and the old set - * specified by q->ia_ranges is unregistered. Otherwise, q->ia_ranges is - * registered if it is not already. */ -int disk_register_independent_access_ranges(struct gendisk *disk, - struct blk_independent_access_ranges *new_iars) +int disk_register_independent_access_ranges(struct gendisk *disk) { + struct blk_independent_access_ranges *iars = disk->ia_ranges; struct request_queue *q = disk->queue; - struct blk_independent_access_ranges *iars; int i, ret; lockdep_assert_held(&q->sysfs_dir_lock); lockdep_assert_held(&q->sysfs_lock); - /* If a new range set is specified, unregister the old one */ - if (new_iars) { - if (q->ia_ranges) - disk_unregister_independent_access_ranges(disk); - q->ia_ranges = new_iars; - } - - iars = q->ia_ranges; if (!iars) return 0; @@ -138,7 +125,7 @@ int disk_register_independent_access_ranges(struct gendisk *disk, ret = kobject_init_and_add(&iars->kobj, &blk_ia_ranges_ktype, &q->kobj, "%s", "independent_access_ranges"); if (ret) { - q->ia_ranges = NULL; + disk->ia_ranges = NULL; kobject_put(&iars->kobj); return ret; } @@ -164,7 +151,7 @@ int disk_register_independent_access_ranges(struct gendisk *disk, void disk_unregister_independent_access_ranges(struct gendisk *disk) { struct request_queue *q = disk->queue; - struct blk_independent_access_ranges *iars = q->ia_ranges; + struct blk_independent_access_ranges *iars = disk->ia_ranges; int i; lockdep_assert_held(&q->sysfs_dir_lock); @@ -182,7 +169,7 @@ void disk_unregister_independent_access_ranges(struct gendisk *disk) kfree(iars); } - q->ia_ranges = NULL; + disk->ia_ranges = NULL; } static struct blk_independent_access_range * @@ -210,6 +197,9 @@ static bool disk_check_ia_ranges(struct gendisk *disk, sector_t sector = 0; int i; + if (WARN_ON_ONCE(!iars->nr_ia_ranges)) + return false; + /* * While sorting the ranges in increasing LBA order, check that the * ranges do not overlap, that there are no sector holes and that all @@ -242,7 +232,7 @@ static bool disk_check_ia_ranges(struct gendisk *disk, static bool disk_ia_ranges_changed(struct gendisk *disk, struct blk_independent_access_ranges *new) { - struct blk_independent_access_ranges *old = disk->queue->ia_ranges; + struct blk_independent_access_ranges *old = disk->ia_ranges; int i; if (!old) @@ -298,25 +288,15 @@ void disk_set_independent_access_ranges(struct gendisk *disk, { struct request_queue *q = disk->queue; - if (WARN_ON_ONCE(iars && !iars->nr_ia_ranges)) { + mutex_lock(&q->sysfs_dir_lock); + mutex_lock(&q->sysfs_lock); + if (iars && !disk_check_ia_ranges(disk, iars)) { kfree(iars); iars = NULL; } - - mutex_lock(&q->sysfs_dir_lock); - mutex_lock(&q->sysfs_lock); - - if (iars) { - if (!disk_check_ia_ranges(disk, iars)) { - kfree(iars); - iars = NULL; - goto reg; - } - - if (!disk_ia_ranges_changed(disk, iars)) { - kfree(iars); - goto unlock; - } + if (iars && !disk_ia_ranges_changed(disk, iars)) { + kfree(iars); + goto unlock; } /* @@ -324,17 +304,12 @@ void disk_set_independent_access_ranges(struct gendisk *disk, * revalidation. If that is the case, we need to unregister the old * set of independent access ranges and register the new set. If the * queue is not registered, registration of the device request queue - * will register the independent access ranges, so only swap in the - * new set and free the old one. + * will register the independent access ranges. */ -reg: - if (blk_queue_registered(q)) { - disk_register_independent_access_ranges(disk, iars); - } else { - swap(q->ia_ranges, iars); - kfree(iars); - } - + disk_unregister_independent_access_ranges(disk); + disk->ia_ranges = iars; + if (blk_queue_registered(q)) + disk_register_independent_access_ranges(disk); unlock: mutex_unlock(&q->sysfs_lock); mutex_unlock(&q->sysfs_dir_lock); diff --git a/block/blk-ioc.c b/block/blk-ioc.c index df9cfe4ca532..63fc02042408 100644 --- a/block/blk-ioc.c +++ b/block/blk-ioc.c @@ -247,6 +247,8 @@ static struct io_context *alloc_io_context(gfp_t gfp_flags, int node) INIT_HLIST_HEAD(&ioc->icq_list); INIT_WORK(&ioc->release_work, ioc_release_fn); #endif + ioc->ioprio = IOPRIO_DEFAULT; + return ioc; } diff --git a/block/blk-iocost.c b/block/blk-iocost.c index 33a11ba971ea..7936e5f5821c 100644 --- a/block/blk-iocost.c +++ b/block/blk-iocost.c @@ -2769,7 +2769,7 @@ static void ioc_rqos_done(struct rq_qos *rqos, struct request *rq) if (!ioc->enabled || !rq->alloc_time_ns || !rq->start_time_ns) return; - switch (req_op(rq) & REQ_OP_MASK) { + switch (req_op(rq)) { case REQ_OP_READ: pidx = QOS_RLAT; rw = READ; @@ -2886,15 +2886,21 @@ static int blk_iocost_init(struct request_queue *q) * called before policy activation completion, can't assume that the * target bio has an iocg associated and need to test for NULL iocg. */ - rq_qos_add(q, rqos); + ret = rq_qos_add(q, rqos); + if (ret) + goto err_free_ioc; + ret = blkcg_activate_policy(q, &blkcg_policy_iocost); - if (ret) { - rq_qos_del(q, rqos); - free_percpu(ioc->pcpu_stat); - kfree(ioc); - return ret; - } + if (ret) + goto err_del_qos; return 0; + +err_del_qos: + rq_qos_del(q, rqos); +err_free_ioc: + free_percpu(ioc->pcpu_stat); + kfree(ioc); + return ret; } static struct blkcg_policy_data *ioc_cpd_alloc(gfp_t gfp) diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index 9568bf8dfe82..e285152345a2 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -401,7 +401,6 @@ static void check_scale_change(struct iolatency_grp *iolat) unsigned int cur_cookie; unsigned int our_cookie = atomic_read(&iolat->scale_cookie); u64 scale_lat; - unsigned int old; int direction = 0; if (lat_to_blkg(iolat)->parent == NULL) @@ -422,11 +421,10 @@ static void check_scale_change(struct iolatency_grp *iolat) else return; - old = atomic_cmpxchg(&iolat->scale_cookie, our_cookie, cur_cookie); - - /* Somebody beat us to the punch, just bail. */ - if (old != our_cookie) + if (!atomic_try_cmpxchg(&iolat->scale_cookie, &our_cookie, cur_cookie)) { + /* Somebody beat us to the punch, just bail. */ return; + } if (direction < 0 && iolat->min_lat_nsec) { u64 samples_thresh; @@ -633,8 +631,8 @@ static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio) window_start = atomic64_read(&iolat->window_start); if (now > window_start && (now - window_start) >= iolat->cur_win_nsec) { - if (atomic64_cmpxchg(&iolat->window_start, - window_start, now) == window_start) + if (atomic64_try_cmpxchg(&iolat->window_start, + &window_start, now)) iolatency_check_latencies(iolat, now); } } @@ -773,19 +771,23 @@ int blk_iolatency_init(struct request_queue *q) rqos->ops = &blkcg_iolatency_ops; rqos->q = q; - rq_qos_add(q, rqos); - + ret = rq_qos_add(q, rqos); + if (ret) + goto err_free; ret = blkcg_activate_policy(q, &blkcg_policy_iolatency); - if (ret) { - rq_qos_del(q, rqos); - kfree(blkiolat); - return ret; - } + if (ret) + goto err_qos_del; timer_setup(&blkiolat->timer, blkiolatency_timer_fn, 0); INIT_WORK(&blkiolat->enable_work, blkiolatency_enable_work_fn); return 0; + +err_qos_del: + rq_qos_del(q, rqos); +err_free: + kfree(blkiolat); + return ret; } static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val) diff --git a/block/blk-ioprio.c b/block/blk-ioprio.c index 79e797f5d194..c00060a02c6e 100644 --- a/block/blk-ioprio.c +++ b/block/blk-ioprio.c @@ -62,7 +62,6 @@ struct ioprio_blkg { struct ioprio_blkcg { struct blkcg_policy_data cpd; enum prio_policy prio_policy; - bool prio_set; }; static inline struct ioprio_blkg *pd_to_ioprio(struct blkg_policy_data *pd) @@ -113,7 +112,6 @@ static ssize_t ioprio_set_prio_policy(struct kernfs_open_file *of, char *buf, if (ret < 0) return ret; blkcg->prio_policy = ret; - blkcg->prio_set = true; return nbytes; } @@ -183,26 +181,20 @@ static struct blkcg_policy ioprio_policy = { .pd_free_fn = ioprio_free_pd, }; -struct blk_ioprio { - struct rq_qos rqos; -}; - -static void blkcg_ioprio_track(struct rq_qos *rqos, struct request *rq, - struct bio *bio) +void blkcg_set_ioprio(struct bio *bio) { struct ioprio_blkcg *blkcg = ioprio_blkcg_from_bio(bio); u16 prio; - if (!blkcg->prio_set) + if (!blkcg || blkcg->prio_policy == POLICY_NO_CHANGE) return; /* * Except for IOPRIO_CLASS_NONE, higher I/O priority numbers * correspond to a lower priority. Hence, the max_t() below selects * the lower priority of bi_ioprio and the cgroup I/O priority class. - * If the cgroup policy has been set to POLICY_NO_CHANGE == 0, the - * bio I/O priority is not modified. If the bio I/O priority equals - * IOPRIO_CLASS_NONE, the cgroup I/O priority is assigned to the bio. + * If the bio I/O priority equals IOPRIO_CLASS_NONE, the cgroup I/O + * priority is assigned to the bio. */ prio = max_t(u16, bio->bi_ioprio, IOPRIO_PRIO_VALUE(blkcg->prio_policy, 0)); @@ -210,49 +202,14 @@ static void blkcg_ioprio_track(struct rq_qos *rqos, struct request *rq, bio->bi_ioprio = prio; } -static void blkcg_ioprio_exit(struct rq_qos *rqos) +void blk_ioprio_exit(struct request_queue *q) { - struct blk_ioprio *blkioprio_blkg = - container_of(rqos, typeof(*blkioprio_blkg), rqos); - - blkcg_deactivate_policy(rqos->q, &ioprio_policy); - kfree(blkioprio_blkg); + blkcg_deactivate_policy(q, &ioprio_policy); } -static struct rq_qos_ops blkcg_ioprio_ops = { - .track = blkcg_ioprio_track, - .exit = blkcg_ioprio_exit, -}; - int blk_ioprio_init(struct request_queue *q) { - struct blk_ioprio *blkioprio_blkg; - struct rq_qos *rqos; - int ret; - - blkioprio_blkg = kzalloc(sizeof(*blkioprio_blkg), GFP_KERNEL); - if (!blkioprio_blkg) - return -ENOMEM; - - ret = blkcg_activate_policy(q, &ioprio_policy); - if (ret) { - kfree(blkioprio_blkg); - return ret; - } - - rqos = &blkioprio_blkg->rqos; - rqos->id = RQ_QOS_IOPRIO; - rqos->ops = &blkcg_ioprio_ops; - rqos->q = q; - - /* - * Registering the rq-qos policy after activating the blk-cgroup - * policy guarantees that ioprio_blkcg_from_bio(bio) != NULL in the - * rq-qos callbacks. - */ - rq_qos_add(q, rqos); - - return 0; + return blkcg_activate_policy(q, &ioprio_policy); } static int __init ioprio_init(void) diff --git a/block/blk-ioprio.h b/block/blk-ioprio.h index a7785c2f1aea..5a1eb550e178 100644 --- a/block/blk-ioprio.h +++ b/block/blk-ioprio.h @@ -6,14 +6,23 @@ #include <linux/kconfig.h> struct request_queue; +struct bio; #ifdef CONFIG_BLK_CGROUP_IOPRIO int blk_ioprio_init(struct request_queue *q); +void blk_ioprio_exit(struct request_queue *q); +void blkcg_set_ioprio(struct bio *bio); #else static inline int blk_ioprio_init(struct request_queue *q) { return 0; } +static inline void blk_ioprio_exit(struct request_queue *q) +{ +} +static inline void blkcg_set_ioprio(struct bio *bio) +{ +} #endif #endif /* _BLK_IOPRIO_H_ */ diff --git a/block/blk-lib.c b/block/blk-lib.c index 09b7e1200c0f..67e6dbc1ae81 100644 --- a/block/blk-lib.c +++ b/block/blk-lib.c @@ -48,10 +48,8 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, /* In case the discard granularity isn't set by buggy device driver */ if (WARN_ON_ONCE(!bdev_discard_granularity(bdev))) { - char dev_name[BDEVNAME_SIZE]; - - bdevname(bdev, dev_name); - pr_err_ratelimited("%s: Error: discard_granularity is 0.\n", dev_name); + pr_err_ratelimited("%pg: Error: discard_granularity is 0.\n", + bdev); return -EOPNOTSUPP; } diff --git a/block/blk-merge.c b/block/blk-merge.c index f5e6527ebc9c..4c8a699754c9 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -164,18 +164,21 @@ static struct bio *blk_bio_write_zeroes_split(struct request_queue *q, static inline unsigned get_max_io_size(struct request_queue *q, struct bio *bio) { - unsigned sectors = blk_max_size_offset(q, bio->bi_iter.bi_sector, 0); - unsigned max_sectors = sectors; unsigned pbs = queue_physical_block_size(q) >> SECTOR_SHIFT; unsigned lbs = queue_logical_block_size(q) >> SECTOR_SHIFT; - unsigned start_offset = bio->bi_iter.bi_sector & (pbs - 1); + unsigned max_sectors = queue_max_sectors(q), start, end; - max_sectors += start_offset; - max_sectors &= ~(pbs - 1); - if (max_sectors > start_offset) - return max_sectors - start_offset; + if (q->limits.chunk_sectors) { + max_sectors = min(max_sectors, + blk_chunk_sectors_left(bio->bi_iter.bi_sector, + q->limits.chunk_sectors)); + } - return sectors & ~(lbs - 1); + start = bio->bi_iter.bi_sector & (pbs - 1); + end = (start + max_sectors) & ~(pbs - 1); + if (end > start) + return end - start; + return max_sectors & ~(lbs - 1); } static inline unsigned get_max_segment_size(const struct request_queue *q, @@ -201,11 +204,11 @@ static inline unsigned get_max_segment_size(const struct request_queue *q, * @nsegs: [in,out] Number of segments in the bio being built. Incremented * by the number of segments from @bv that may be appended to that * bio without exceeding @max_segs - * @sectors: [in,out] Number of sectors in the bio being built. Incremented - * by the number of sectors from @bv that may be appended to that - * bio without exceeding @max_sectors + * @bytes: [in,out] Number of bytes in the bio being built. Incremented + * by the number of bytes from @bv that may be appended to that + * bio without exceeding @max_bytes * @max_segs: [in] upper bound for *@nsegs - * @max_sectors: [in] upper bound for *@sectors + * @max_bytes: [in] upper bound for *@bytes * * When splitting a bio, it can happen that a bvec is encountered that is too * big to fit in a single segment and hence that it has to be split in the @@ -216,10 +219,10 @@ static inline unsigned get_max_segment_size(const struct request_queue *q, */ static bool bvec_split_segs(const struct request_queue *q, const struct bio_vec *bv, unsigned *nsegs, - unsigned *sectors, unsigned max_segs, - unsigned max_sectors) + unsigned *bytes, unsigned max_segs, + unsigned max_bytes) { - unsigned max_len = (min(max_sectors, UINT_MAX >> 9) - *sectors) << 9; + unsigned max_len = min(max_bytes, UINT_MAX) - *bytes; unsigned len = min(bv->bv_len, max_len); unsigned total_len = 0; unsigned seg_size = 0; @@ -237,7 +240,7 @@ static bool bvec_split_segs(const struct request_queue *q, break; } - *sectors += total_len >> 9; + *bytes += total_len; /* tell the caller to split the bvec if it is too big to fit */ return len > 0 || bv->bv_len > max_len; @@ -269,8 +272,8 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, { struct bio_vec bv, bvprv, *bvprvp = NULL; struct bvec_iter iter; - unsigned nsegs = 0, sectors = 0; - const unsigned max_sectors = get_max_io_size(q, bio); + unsigned nsegs = 0, bytes = 0; + const unsigned max_bytes = get_max_io_size(q, bio) << 9; const unsigned max_segs = queue_max_segments(q); bio_for_each_bvec(bv, bio, iter) { @@ -282,12 +285,12 @@ static struct bio *blk_bio_segment_split(struct request_queue *q, goto split; if (nsegs < max_segs && - sectors + (bv.bv_len >> 9) <= max_sectors && + bytes + bv.bv_len <= max_bytes && bv.bv_offset + bv.bv_len <= PAGE_SIZE) { nsegs++; - sectors += bv.bv_len >> 9; - } else if (bvec_split_segs(q, &bv, &nsegs, §ors, max_segs, - max_sectors)) { + bytes += bv.bv_len; + } else if (bvec_split_segs(q, &bv, &nsegs, &bytes, max_segs, + max_bytes)) { goto split; } @@ -301,12 +304,19 @@ split: *segs = nsegs; /* + * Individual bvecs might not be logical block aligned. Round down the + * split size so that each bio is properly block size aligned, even if + * we do not use the full hardware limits. + */ + bytes = ALIGN_DOWN(bytes, queue_logical_block_size(q)); + + /* * Bio splitting may cause subtle trouble such as hang when doing sync * iopoll in direct IO routine. Given performance gain of iopoll for * big IO can be trival, disable iopoll when split needed. */ bio_clear_polled(bio); - return bio_split(bio, sectors, GFP_NOIO, bs); + return bio_split(bio, bytes >> SECTOR_SHIFT, GFP_NOIO, bs); } /** @@ -376,7 +386,7 @@ EXPORT_SYMBOL(blk_queue_split); unsigned int blk_recalc_rq_segments(struct request *rq) { unsigned int nr_phys_segs = 0; - unsigned int nr_sectors = 0; + unsigned int bytes = 0; struct req_iterator iter; struct bio_vec bv; @@ -396,10 +406,12 @@ unsigned int blk_recalc_rq_segments(struct request *rq) return 1; case REQ_OP_WRITE_ZEROES: return 0; + default: + break; } rq_for_each_bvec(bv, rq, iter) - bvec_split_segs(rq->q, &bv, &nr_phys_segs, &nr_sectors, + bvec_split_segs(rq->q, &bv, &nr_phys_segs, &bytes, UINT_MAX, UINT_MAX); return nr_phys_segs; } @@ -560,17 +572,18 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq, sector_t offset) { struct request_queue *q = rq->q; + unsigned int max_sectors; if (blk_rq_is_passthrough(rq)) return q->limits.max_hw_sectors; + max_sectors = blk_queue_get_max_sectors(q, req_op(rq)); if (!q->limits.chunk_sectors || req_op(rq) == REQ_OP_DISCARD || req_op(rq) == REQ_OP_SECURE_ERASE) - return blk_queue_get_max_sectors(q, req_op(rq)); - - return min(blk_max_size_offset(q, offset, 0), - blk_queue_get_max_sectors(q, req_op(rq))); + return max_sectors; + return min(max_sectors, + blk_chunk_sectors_left(offset, q->limits.chunk_sectors)); } static inline int ll_new_hw_segment(struct request *req, struct bio *bio, @@ -700,7 +713,7 @@ static int ll_merge_requests_fn(struct request_queue *q, struct request *req, */ void blk_rq_set_mixed_merge(struct request *rq) { - unsigned int ff = rq->cmd_flags & REQ_FAILFAST_MASK; + blk_opf_t ff = rq->cmd_flags & REQ_FAILFAST_MASK; struct bio *bio; if (rq->rq_flags & RQF_MIXED_MERGE) @@ -916,7 +929,7 @@ enum bio_merge_status { static enum bio_merge_status bio_attempt_back_merge(struct request *req, struct bio *bio, unsigned int nr_segs) { - const int ff = bio->bi_opf & REQ_FAILFAST_MASK; + const blk_opf_t ff = bio->bi_opf & REQ_FAILFAST_MASK; if (!ll_back_merge_fn(req, bio, nr_segs)) return BIO_MERGE_FAILED; @@ -940,7 +953,7 @@ static enum bio_merge_status bio_attempt_back_merge(struct request *req, static enum bio_merge_status bio_attempt_front_merge(struct request *req, struct bio *bio, unsigned int nr_segs) { - const int ff = bio->bi_opf & REQ_FAILFAST_MASK; + const blk_opf_t ff = bio->bi_opf & REQ_FAILFAST_MASK; if (!ll_front_merge_fn(req, bio, nr_segs)) return BIO_MERGE_FAILED; @@ -1041,7 +1054,7 @@ bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, struct blk_plug *plug; struct request *rq; - plug = blk_mq_plug(q, bio); + plug = blk_mq_plug(bio); if (!plug || rq_list_empty(plug->mq_list)) return false; diff --git a/block/blk-mq-debugfs-zoned.c b/block/blk-mq-debugfs-zoned.c index 038cb627c868..a77b099c34b7 100644 --- a/block/blk-mq-debugfs-zoned.c +++ b/block/blk-mq-debugfs-zoned.c @@ -11,11 +11,11 @@ int queue_zone_wlock_show(void *data, struct seq_file *m) struct request_queue *q = data; unsigned int i; - if (!q->seq_zones_wlock) + if (!q->disk->seq_zones_wlock) return 0; - for (i = 0; i < q->nr_zones; i++) - if (test_bit(i, q->seq_zones_wlock)) + for (i = 0; i < q->disk->nr_zones; i++) + if (test_bit(i, q->disk->seq_zones_wlock)) seq_printf(m, "%u\n", i); return 0; diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index 4d1ce9ef4318..8559cea7f300 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -116,7 +116,6 @@ static const char *const blk_queue_flag_name[] = { QUEUE_FLAG_NAME(NOXMERGES), QUEUE_FLAG_NAME(ADD_RANDOM), QUEUE_FLAG_NAME(SAME_FORCE), - QUEUE_FLAG_NAME(DEAD), QUEUE_FLAG_NAME(INIT_DONE), QUEUE_FLAG_NAME(STABLE_WRITES), QUEUE_FLAG_NAME(POLL), @@ -151,11 +150,10 @@ static ssize_t queue_state_write(void *data, const char __user *buf, char opbuf[16] = { }, *op; /* - * The "state" attribute is removed after blk_cleanup_queue() has called - * blk_mq_free_queue(). Return if QUEUE_FLAG_DEAD has been set to avoid - * triggering a use-after-free. + * The "state" attribute is removed when the queue is removed. Don't + * allow setting the state on a dying queue to avoid a use-after-free. */ - if (blk_queue_dead(q)) + if (blk_queue_dying(q)) return -ENOENT; if (count >= sizeof(opbuf)) { @@ -306,7 +304,7 @@ static const char *blk_mq_rq_state_name(enum mq_rq_state rq_state) int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq) { const struct blk_mq_ops *const mq_ops = rq->q->mq_ops; - const unsigned int op = req_op(rq); + const enum req_op op = req_op(rq); const char *op_str = blk_op_str(op); seq_printf(m, "%p {.op=", rq); @@ -315,8 +313,8 @@ int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq) else seq_printf(m, "%s", op_str); seq_puts(m, ", .cmd_flags="); - blk_flags_show(m, rq->cmd_flags & ~REQ_OP_MASK, cmd_flag_name, - ARRAY_SIZE(cmd_flag_name)); + blk_flags_show(m, (__force unsigned int)(rq->cmd_flags & ~REQ_OP_MASK), + cmd_flag_name, ARRAY_SIZE(cmd_flag_name)); seq_puts(m, ", .rq_flags="); blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name, ARRAY_SIZE(rqf_name)); @@ -377,7 +375,7 @@ struct show_busy_params { * e.g. due to a concurrent blk_mq_finish_request() call. Returns true to * keep iterating requests. */ -static bool hctx_show_busy_rq(struct request *rq, void *data, bool reserved) +static bool hctx_show_busy_rq(struct request *rq, void *data) { const struct show_busy_params *params = data; @@ -730,6 +728,9 @@ void blk_mq_debugfs_register_hctx(struct request_queue *q, char name[20]; int i; + if (!q->debugfs_dir) + return; + snprintf(name, sizeof(name), "hctx%u", hctx->queue_num); hctx->debugfs_dir = debugfs_create_dir(name, q->debugfs_dir); diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index c08426975856..93997d297d42 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -203,23 +203,6 @@ static int blk_mq_register_hctx(struct blk_mq_hw_ctx *hctx) return ret; } -void blk_mq_unregister_dev(struct device *dev, struct request_queue *q) -{ - struct blk_mq_hw_ctx *hctx; - unsigned long i; - - lockdep_assert_held(&q->sysfs_dir_lock); - - 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_put(&dev->kobj); - - q->mq_sysfs_init_done = false; -} - void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx) { kobject_init(&hctx->kobj, &blk_mq_hw_ktype); @@ -252,16 +235,16 @@ void blk_mq_sysfs_init(struct request_queue *q) } } -int __blk_mq_register_dev(struct device *dev, struct request_queue *q) +int blk_mq_sysfs_register(struct gendisk *disk) { + struct request_queue *q = disk->queue; struct blk_mq_hw_ctx *hctx; unsigned long i, j; int ret; - WARN_ON_ONCE(!q->kobj.parent); lockdep_assert_held(&q->sysfs_dir_lock); - ret = kobject_add(q->mq_kobj, kobject_get(&dev->kobj), "%s", "mq"); + ret = kobject_add(q->mq_kobj, &disk_to_dev(disk)->kobj, "mq"); if (ret < 0) goto out; @@ -286,11 +269,27 @@ unreg: kobject_uevent(q->mq_kobj, KOBJ_REMOVE); kobject_del(q->mq_kobj); - kobject_put(&dev->kobj); return ret; } -void blk_mq_sysfs_unregister(struct request_queue *q) +void blk_mq_sysfs_unregister(struct gendisk *disk) +{ + struct request_queue *q = disk->queue; + struct blk_mq_hw_ctx *hctx; + unsigned long i; + + lockdep_assert_held(&q->sysfs_dir_lock); + + 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); + + q->mq_sysfs_init_done = false; +} + +void blk_mq_sysfs_unregister_hctxs(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; @@ -306,7 +305,7 @@ unlock: mutex_unlock(&q->sysfs_dir_lock); } -int blk_mq_sysfs_register(struct request_queue *q) +int blk_mq_sysfs_register_hctxs(struct request_queue *q) { struct blk_mq_hw_ctx *hctx; unsigned long i; diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c index 2dcd738c6952..8e3b36d1cb57 100644 --- a/block/blk-mq-tag.c +++ b/block/blk-mq-tag.c @@ -37,29 +37,25 @@ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags, * to get tag when first time, the other shared-tag users could reserve * budget for it. */ -bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) +void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { unsigned int users; if (blk_mq_is_shared_tags(hctx->flags)) { struct request_queue *q = hctx->queue; - if (test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags) || - test_and_set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) { - return true; - } + if (test_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags)) + return; + set_bit(QUEUE_FLAG_HCTX_ACTIVE, &q->queue_flags); } else { - if (test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state) || - test_and_set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) { - return true; - } + if (test_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state)) + return; + set_bit(BLK_MQ_S_TAG_ACTIVE, &hctx->state); } users = atomic_inc_return(&hctx->tags->active_queues); blk_mq_update_wake_batch(hctx->tags, users); - - return true; } /* @@ -266,7 +262,6 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) struct blk_mq_hw_ctx *hctx = iter_data->hctx; struct request_queue *q = iter_data->q; struct blk_mq_tag_set *set = q->tag_set; - bool reserved = iter_data->reserved; struct blk_mq_tags *tags; struct request *rq; bool ret = true; @@ -276,7 +271,7 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) else tags = hctx->tags; - if (!reserved) + if (!iter_data->reserved) bitnr += tags->nr_reserved_tags; /* * We can hit rq == NULL here, because the tagging functions @@ -287,7 +282,7 @@ static bool bt_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) return true; if (rq->q == q && (!hctx || rq->mq_hctx == hctx)) - ret = iter_data->fn(rq, iter_data->data, reserved); + ret = iter_data->fn(rq, iter_data->data); blk_mq_put_rq_ref(rq); return ret; } @@ -337,12 +332,11 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) { struct bt_tags_iter_data *iter_data = data; struct blk_mq_tags *tags = iter_data->tags; - bool reserved = iter_data->flags & BT_TAG_ITER_RESERVED; struct request *rq; bool ret = true; bool iter_static_rqs = !!(iter_data->flags & BT_TAG_ITER_STATIC_RQS); - if (!reserved) + if (!(iter_data->flags & BT_TAG_ITER_RESERVED)) bitnr += tags->nr_reserved_tags; /* @@ -358,7 +352,7 @@ static bool bt_tags_iter(struct sbitmap *bitmap, unsigned int bitnr, void *data) if (!(iter_data->flags & BT_TAG_ITER_STARTED) || blk_mq_request_started(rq)) - ret = iter_data->fn(rq, iter_data->data, reserved); + ret = iter_data->fn(rq, iter_data->data); if (!iter_static_rqs) blk_mq_put_rq_ref(rq); return ret; @@ -448,8 +442,7 @@ void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset, } EXPORT_SYMBOL(blk_mq_tagset_busy_iter); -static bool blk_mq_tagset_count_completed_rqs(struct request *rq, - void *data, bool reserved) +static bool blk_mq_tagset_count_completed_rqs(struct request *rq, void *data) { unsigned *count = data; diff --git a/block/blk-mq-tag.h b/block/blk-mq-tag.h index 5668e28be0b7..91ff37e3b43d 100644 --- a/block/blk-mq-tag.h +++ b/block/blk-mq-tag.h @@ -47,15 +47,13 @@ enum { BLK_MQ_TAG_MAX = BLK_MQ_NO_TAG - 1, }; -extern bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *); +extern void __blk_mq_tag_busy(struct blk_mq_hw_ctx *); extern void __blk_mq_tag_idle(struct blk_mq_hw_ctx *); -static inline bool blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) +static inline void blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx) { - if (!(hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED)) - return false; - - return __blk_mq_tag_busy(hctx); + if (hctx->flags & BLK_MQ_F_TAG_QUEUE_SHARED) + __blk_mq_tag_busy(hctx); } static inline void blk_mq_tag_idle(struct blk_mq_hw_ctx *hctx) diff --git a/block/blk-mq.c b/block/blk-mq.c index 93d9d60980fb..70177ee74295 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -42,6 +42,7 @@ #include "blk-stat.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h" +#include "blk-ioprio.h" static DEFINE_PER_CPU(struct llist_head, blk_cpu_done); @@ -128,8 +129,7 @@ struct mq_inflight { unsigned int inflight[2]; }; -static bool blk_mq_check_inflight(struct request *rq, void *priv, - bool reserved) +static bool blk_mq_check_inflight(struct request *rq, void *priv) { struct mq_inflight *mi = priv; @@ -474,6 +474,9 @@ retry: if (!(data->rq_flags & RQF_ELV)) blk_mq_tag_busy(data->hctx); + if (data->flags & BLK_MQ_REQ_RESERVED) + data->rq_flags |= RQF_RESV; + /* * Try batched alloc if we want more than 1 tag. */ @@ -507,13 +510,13 @@ retry: alloc_time_ns); } -struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op, +struct request *blk_mq_alloc_request(struct request_queue *q, blk_opf_t opf, blk_mq_req_flags_t flags) { struct blk_mq_alloc_data data = { .q = q, .flags = flags, - .cmd_flags = op, + .cmd_flags = opf, .nr_tags = 1, }; struct request *rq; @@ -537,12 +540,12 @@ out_queue_exit: EXPORT_SYMBOL(blk_mq_alloc_request); struct request *blk_mq_alloc_request_hctx(struct request_queue *q, - unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx) + blk_opf_t opf, blk_mq_req_flags_t flags, unsigned int hctx_idx) { struct blk_mq_alloc_data data = { .q = q, .flags = flags, - .cmd_flags = op, + .cmd_flags = opf, .nr_tags = 1, }; u64 alloc_time_ns = 0; @@ -588,6 +591,9 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, else data.rq_flags |= RQF_ELV; + if (flags & BLK_MQ_REQ_RESERVED) + data.rq_flags |= RQF_RESV; + ret = -EWOULDBLOCK; tag = blk_mq_get_tag(&data); if (tag == BLK_MQ_NO_TAG) @@ -654,7 +660,7 @@ void blk_dump_rq_flags(struct request *rq, char *msg) { printk(KERN_INFO "%s: dev %s: flags=%llx\n", msg, rq->q->disk ? rq->q->disk->disk_name : "?", - (unsigned long long) rq->cmd_flags); + (__force unsigned long long) rq->cmd_flags); printk(KERN_INFO " sector %llu, nr/cnr %u/%u\n", (unsigned long long)blk_rq_pos(rq), @@ -707,8 +713,9 @@ static void blk_print_req_error(struct request *req, blk_status_t status) "phys_seg %u prio class %u\n", blk_status_to_str(status), req->q->disk ? req->q->disk->disk_name : "?", - blk_rq_pos(req), req_op(req), blk_op_str(req_op(req)), - req->cmd_flags & ~REQ_OP_MASK, + blk_rq_pos(req), (__force u32)req_op(req), + blk_op_str(req_op(req)), + (__force u32)(req->cmd_flags & ~REQ_OP_MASK), req->nr_phys_segments, IOPRIO_PRIO_CLASS(req->ioprio)); } @@ -1393,8 +1400,7 @@ void blk_mq_delay_kick_requeue_list(struct request_queue *q, } EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list); -static bool blk_mq_rq_inflight(struct request *rq, void *priv, - bool reserved) +static bool blk_mq_rq_inflight(struct request *rq, void *priv) { /* * If we find a request that isn't idle we know the queue is busy @@ -1420,13 +1426,13 @@ bool blk_mq_queue_inflight(struct request_queue *q) } EXPORT_SYMBOL_GPL(blk_mq_queue_inflight); -static void blk_mq_rq_timed_out(struct request *req, bool reserved) +static void blk_mq_rq_timed_out(struct request *req) { req->rq_flags |= RQF_TIMED_OUT; if (req->q->mq_ops->timeout) { enum blk_eh_timer_return ret; - ret = req->q->mq_ops->timeout(req, reserved); + ret = req->q->mq_ops->timeout(req); if (ret == BLK_EH_DONE) return; WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER); @@ -1463,7 +1469,7 @@ void blk_mq_put_rq_ref(struct request *rq) __blk_mq_free_request(rq); } -static bool blk_mq_check_expired(struct request *rq, void *priv, bool reserved) +static bool blk_mq_check_expired(struct request *rq, void *priv) { unsigned long *next = priv; @@ -1475,7 +1481,7 @@ static bool blk_mq_check_expired(struct request *rq, void *priv, bool reserved) * from blk_mq_check_expired(). */ if (blk_mq_req_expired(rq, next)) - blk_mq_rq_timed_out(rq, reserved); + blk_mq_rq_timed_out(rq); return true; } @@ -2085,14 +2091,10 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async, return; if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) { - int cpu = get_cpu(); - if (cpumask_test_cpu(cpu, hctx->cpumask)) { + if (cpumask_test_cpu(raw_smp_processor_id(), hctx->cpumask)) { __blk_mq_run_hw_queue(hctx); - put_cpu(); return; } - - put_cpu(); } kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work, @@ -2156,7 +2158,7 @@ static struct blk_mq_hw_ctx *blk_mq_get_sq_hctx(struct request_queue *q) * just causes lock contention inside the scheduler and pointless cache * bouncing. */ - struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, 0, ctx); + struct blk_mq_hw_ctx *hctx = ctx->hctxs[HCTX_TYPE_DEFAULT]; if (!blk_mq_hctx_stopped(hctx)) return hctx; @@ -2783,6 +2785,14 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q, return rq; } +static void bio_set_ioprio(struct bio *bio) +{ + /* Nobody set ioprio so far? Initialize it based on task's nice value */ + if (IOPRIO_PRIO_CLASS(bio->bi_ioprio) == IOPRIO_CLASS_NONE) + bio->bi_ioprio = get_current_ioprio(); + blkcg_set_ioprio(bio); +} + /** * blk_mq_submit_bio - Create and send a request to block device. * @bio: Bio pointer. @@ -2799,7 +2809,7 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q, void blk_mq_submit_bio(struct bio *bio) { struct request_queue *q = bdev_get_queue(bio->bi_bdev); - struct blk_plug *plug = blk_mq_plug(q, bio); + struct blk_plug *plug = blk_mq_plug(bio); const int is_sync = op_is_sync(bio->bi_opf); struct request *rq; unsigned int nr_segs = 1; @@ -2812,6 +2822,8 @@ void blk_mq_submit_bio(struct bio *bio) if (!bio_integrity_prep(bio)) return; + bio_set_ioprio(bio); + rq = blk_mq_get_cached_request(q, plug, &bio, nr_segs); if (!rq) { if (!bio) @@ -3276,7 +3288,7 @@ struct rq_iter_data { bool has_rq; }; -static bool blk_mq_has_request(struct request *rq, void *data, bool reserved) +static bool blk_mq_has_request(struct request *rq, void *data) { struct rq_iter_data *iter_data = data; @@ -3895,7 +3907,7 @@ static struct request_queue *blk_mq_init_queue_data(struct blk_mq_tag_set *set, q->queuedata = queuedata; ret = blk_mq_init_allocated_queue(set, q); if (ret) { - blk_cleanup_queue(q); + blk_put_queue(q); return ERR_PTR(ret); } return q; @@ -3907,6 +3919,35 @@ struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *set) } EXPORT_SYMBOL(blk_mq_init_queue); +/** + * blk_mq_destroy_queue - shutdown a request queue + * @q: request queue to shutdown + * + * This shuts down a request queue allocated by blk_mq_init_queue() and drops + * the initial reference. All future requests will failed with -ENODEV. + * + * Context: can sleep + */ +void blk_mq_destroy_queue(struct request_queue *q) +{ + WARN_ON_ONCE(!queue_is_mq(q)); + WARN_ON_ONCE(blk_queue_registered(q)); + + might_sleep(); + + blk_queue_flag_set(QUEUE_FLAG_DYING, q); + blk_queue_start_drain(q); + blk_freeze_queue(q); + + blk_sync_queue(q); + blk_mq_cancel_work_sync(q); + blk_mq_exit_queue(q); + + /* @q is and will stay empty, shutdown and put */ + blk_put_queue(q); +} +EXPORT_SYMBOL(blk_mq_destroy_queue); + struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata, struct lock_class_key *lkclass) { @@ -3919,13 +3960,23 @@ struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata, disk = __alloc_disk_node(q, set->numa_node, lkclass); if (!disk) { - blk_cleanup_queue(q); + blk_mq_destroy_queue(q); return ERR_PTR(-ENOMEM); } + set_bit(GD_OWNS_QUEUE, &disk->state); return disk; } EXPORT_SYMBOL(__blk_mq_alloc_disk); +struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q, + struct lock_class_key *lkclass) +{ + if (!blk_get_queue(q)) + return NULL; + return __alloc_disk_node(q, NUMA_NO_NODE, lkclass); +} +EXPORT_SYMBOL(blk_mq_alloc_disk_for_queue); + static struct blk_mq_hw_ctx *blk_mq_alloc_and_init_hctx( struct blk_mq_tag_set *set, struct request_queue *q, int hctx_idx, int node) @@ -4513,7 +4564,7 @@ static void __blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, list_for_each_entry(q, &set->tag_list, tag_set_list) { blk_mq_debugfs_unregister_hctxs(q); - blk_mq_sysfs_unregister(q); + blk_mq_sysfs_unregister_hctxs(q); } prev_nr_hw_queues = set->nr_hw_queues; @@ -4544,7 +4595,7 @@ fallback: reregister: list_for_each_entry(q, &set->tag_list, tag_set_list) { - blk_mq_sysfs_register(q); + blk_mq_sysfs_register_hctxs(q); blk_mq_debugfs_register_hctxs(q); } diff --git a/block/blk-mq.h b/block/blk-mq.h index 2615bd58bad3..8ca453ac243d 100644 --- a/block/blk-mq.h +++ b/block/blk-mq.h @@ -86,16 +86,16 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue_type(struct request_queue * return xa_load(&q->hctx_table, q->tag_set->map[type].mq_map[cpu]); } -static inline enum hctx_type blk_mq_get_hctx_type(unsigned int flags) +static inline enum hctx_type blk_mq_get_hctx_type(blk_opf_t opf) { enum hctx_type type = HCTX_TYPE_DEFAULT; /* * The caller ensure that if REQ_POLLED, poll must be enabled. */ - if (flags & REQ_POLLED) + if (opf & REQ_POLLED) type = HCTX_TYPE_POLL; - else if ((flags & REQ_OP_MASK) == REQ_OP_READ) + else if ((opf & REQ_OP_MASK) == REQ_OP_READ) type = HCTX_TYPE_READ; return type; } @@ -103,14 +103,14 @@ static inline enum hctx_type blk_mq_get_hctx_type(unsigned int flags) /* * blk_mq_map_queue() - map (cmd_flags,type) to hardware queue * @q: request queue - * @flags: request command flags + * @opf: operation type (REQ_OP_*) and flags (e.g. REQ_POLLED). * @ctx: software queue cpu ctx */ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, - unsigned int flags, + blk_opf_t opf, struct blk_mq_ctx *ctx) { - return ctx->hctxs[blk_mq_get_hctx_type(flags)]; + return ctx->hctxs[blk_mq_get_hctx_type(opf)]; } /* @@ -118,9 +118,10 @@ static inline struct blk_mq_hw_ctx *blk_mq_map_queue(struct request_queue *q, */ extern void blk_mq_sysfs_init(struct request_queue *q); extern void blk_mq_sysfs_deinit(struct request_queue *q); -extern int __blk_mq_register_dev(struct device *dev, struct request_queue *q); -extern int blk_mq_sysfs_register(struct request_queue *q); -extern void blk_mq_sysfs_unregister(struct request_queue *q); +int blk_mq_sysfs_register(struct gendisk *disk); +void blk_mq_sysfs_unregister(struct gendisk *disk); +int blk_mq_sysfs_register_hctxs(struct request_queue *q); +void blk_mq_sysfs_unregister_hctxs(struct request_queue *q); extern void blk_mq_hctx_kobj_init(struct blk_mq_hw_ctx *hctx); void blk_mq_free_plug_rqs(struct blk_plug *plug); void blk_mq_flush_plug_list(struct blk_plug *plug, bool from_schedule); @@ -151,7 +152,7 @@ struct blk_mq_alloc_data { struct request_queue *q; blk_mq_req_flags_t flags; unsigned int shallow_depth; - unsigned int cmd_flags; + blk_opf_t cmd_flags; req_flags_t rq_flags; /* allocate multiple requests/tags in one go */ @@ -293,7 +294,6 @@ static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap) /* * blk_mq_plug() - Get caller context plug - * @q: request queue * @bio : the bio being submitted by the caller context * * Plugging, by design, may delay the insertion of BIOs into the elevator in @@ -304,23 +304,22 @@ static inline void blk_mq_clear_mq_map(struct blk_mq_queue_map *qmap) * order. While this is not a problem with regular block devices, this ordering * change can cause write BIO failures with zoned block devices as these * require sequential write patterns to zones. Prevent this from happening by - * ignoring the plug state of a BIO issuing context if the target request queue - * is for a zoned block device and the BIO to plug is a write operation. + * ignoring the plug state of a BIO issuing context if it is for a zoned block + * device and the BIO to plug is a write operation. * * Return current->plug if the bio can be plugged and NULL otherwise */ -static inline struct blk_plug *blk_mq_plug(struct request_queue *q, - struct bio *bio) +static inline struct blk_plug *blk_mq_plug( struct bio *bio) { + /* Zoned block device write operation case: do not plug the BIO */ + if (bdev_is_zoned(bio->bi_bdev) && op_is_write(bio_op(bio))) + return NULL; + /* * For regular block devices or read operations, use the context plug * which may be NULL if blk_start_plug() was not executed. */ - if (!blk_queue_is_zoned(q) || !op_is_write(bio_op(bio))) - return current->plug; - - /* Zoned block device write operation case: do not plug the BIO */ - return NULL; + return current->plug; } /* Free all requests on the list */ diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c index d3a75693adbf..88f0fe7dcf54 100644 --- a/block/blk-rq-qos.c +++ b/block/blk-rq-qos.c @@ -10,16 +10,10 @@ static bool atomic_inc_below(atomic_t *v, unsigned int below) { unsigned int cur = atomic_read(v); - for (;;) { - unsigned int old; - + do { if (cur >= below) return false; - old = atomic_cmpxchg(v, cur, cur + 1); - if (old == cur) - break; - cur = old; - } + } while (!atomic_try_cmpxchg(v, &cur, cur + 1)); return true; } diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index 0e46052b018a..08b856570ad1 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -86,7 +86,7 @@ static inline void rq_wait_init(struct rq_wait *rq_wait) init_waitqueue_head(&rq_wait->wait); } -static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos) +static inline int rq_qos_add(struct request_queue *q, struct rq_qos *rqos) { /* * No IO can be in-flight when adding rqos, so freeze queue, which @@ -98,6 +98,8 @@ static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos) blk_mq_freeze_queue(q); spin_lock_irq(&q->queue_lock); + if (rq_qos_id(q, rqos->id)) + goto ebusy; rqos->next = q->rq_qos; q->rq_qos = rqos; spin_unlock_irq(&q->queue_lock); @@ -109,6 +111,13 @@ static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos) blk_mq_debugfs_register_rqos(rqos); mutex_unlock(&q->debugfs_mutex); } + + return 0; +ebusy: + spin_unlock_irq(&q->queue_lock); + blk_mq_unfreeze_queue(q); + return -EBUSY; + } static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos) diff --git a/block/blk-settings.c b/block/blk-settings.c index 6ccceb421ed2..8bb9eef5310e 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -893,18 +893,19 @@ static bool disk_has_partitions(struct gendisk *disk) } /** - * blk_queue_set_zoned - configure a disk queue zoned model. + * disk_set_zoned - configure the zoned model for a disk * @disk: the gendisk of the queue to configure * @model: the zoned model to set * - * Set the zoned model of the request queue of @disk according to @model. + * Set the zoned model of @disk to @model. + * * When @model is BLK_ZONED_HM (host managed), this should be called only * if zoned block device support is enabled (CONFIG_BLK_DEV_ZONED option). * If @model specifies BLK_ZONED_HA (host aware), the effective model used * depends on CONFIG_BLK_DEV_ZONED settings and on the existence of partitions * on the disk. */ -void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model) +void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model) { struct request_queue *q = disk->queue; @@ -945,10 +946,10 @@ void blk_queue_set_zoned(struct gendisk *disk, enum blk_zoned_model model) blk_queue_zone_write_granularity(q, queue_logical_block_size(q)); } else { - blk_queue_clear_zone_settings(q); + disk_clear_zone_settings(disk); } } -EXPORT_SYMBOL_GPL(blk_queue_set_zoned); +EXPORT_SYMBOL_GPL(disk_set_zoned); int bdev_alignment_offset(struct block_device *bdev) { diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 9b905e9443e4..c0303026752d 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -274,6 +274,11 @@ static ssize_t queue_virt_boundary_mask_show(struct request_queue *q, char *page return queue_var_show(q->limits.virt_boundary_mask, page); } +static ssize_t queue_dma_alignment_show(struct request_queue *q, char *page) +{ + return queue_var_show(queue_dma_alignment(q), page); +} + #define QUEUE_SYSFS_BIT_FNS(name, flag, neg) \ static ssize_t \ queue_##name##_show(struct request_queue *q, char *page) \ @@ -320,17 +325,17 @@ static ssize_t queue_zoned_show(struct request_queue *q, char *page) static ssize_t queue_nr_zones_show(struct request_queue *q, char *page) { - return queue_var_show(blk_queue_nr_zones(q), page); + return queue_var_show(disk_nr_zones(q->disk), page); } static ssize_t queue_max_open_zones_show(struct request_queue *q, char *page) { - return queue_var_show(queue_max_open_zones(q), page); + return queue_var_show(bdev_max_open_zones(q->disk->part0), page); } static ssize_t queue_max_active_zones_show(struct request_queue *q, char *page) { - return queue_var_show(queue_max_active_zones(q), page); + return queue_var_show(bdev_max_active_zones(q->disk->part0), page); } static ssize_t queue_nomerges_show(struct request_queue *q, char *page) @@ -606,6 +611,7 @@ QUEUE_RO_ENTRY(queue_dax, "dax"); QUEUE_RW_ENTRY(queue_io_timeout, "io_timeout"); QUEUE_RW_ENTRY(queue_wb_lat, "wbt_lat_usec"); QUEUE_RO_ENTRY(queue_virt_boundary_mask, "virt_boundary_mask"); +QUEUE_RO_ENTRY(queue_dma_alignment, "dma_alignment"); #ifdef CONFIG_BLK_DEV_THROTTLING_LOW QUEUE_RW_ENTRY(blk_throtl_sample_time, "throttle_sample_time"); @@ -667,6 +673,7 @@ static struct attribute *queue_attrs[] = { &blk_throtl_sample_time_entry.attr, #endif &queue_virt_boundary_mask_entry.attr, + &queue_dma_alignment_entry.attr, NULL, }; @@ -748,11 +755,6 @@ static void blk_free_queue_rcu(struct rcu_head *rcu_head) * decremented with blk_put_queue(). Once the refcount reaches 0 this function * is called. * - * For drivers that have a request_queue on a gendisk and added with - * __device_add_disk() the refcount to request_queue will reach 0 with - * the last put_disk() called by the driver. For drivers which don't use - * __device_add_disk() this happens with blk_cleanup_queue(). - * * Drivers exist which depend on the release of the request_queue to be * synchronous, it should not be deferred. * @@ -774,8 +776,6 @@ static void blk_release_queue(struct kobject *kobj) blk_free_queue_stats(q->stats); kfree(q->poll_stat); - blk_queue_free_zone_bitmaps(q); - if (queue_is_mq(q)) blk_mq_release(q); @@ -784,7 +784,7 @@ static void blk_release_queue(struct kobject *kobj) if (blk_queue_has_srcu(q)) cleanup_srcu_struct(q->srcu); - ida_simple_remove(&blk_queue_ida, q->id); + ida_free(&blk_queue_ida, q->id); call_rcu(&q->rcu_head, blk_free_queue_rcu); } @@ -793,7 +793,13 @@ static const struct sysfs_ops queue_sysfs_ops = { .store = queue_attr_store, }; +static const struct attribute_group *blk_queue_attr_groups[] = { + &queue_attr_group, + NULL +}; + struct kobj_type blk_queue_ktype = { + .default_groups = blk_queue_attr_groups, .sysfs_ops = &queue_sysfs_ops, .release = blk_release_queue, }; @@ -804,32 +810,17 @@ struct kobj_type blk_queue_ktype = { */ int blk_register_queue(struct gendisk *disk) { - int ret; - struct device *dev = disk_to_dev(disk); struct request_queue *q = disk->queue; - - ret = blk_trace_init_sysfs(dev); - if (ret) - return ret; + int ret; mutex_lock(&q->sysfs_dir_lock); - ret = kobject_add(&q->kobj, kobject_get(&dev->kobj), "%s", "queue"); - if (ret < 0) { - blk_trace_remove_sysfs(dev); - goto unlock; - } - - ret = sysfs_create_group(&q->kobj, &queue_attr_group); - if (ret) { - blk_trace_remove_sysfs(dev); - kobject_del(&q->kobj); - kobject_put(&dev->kobj); + ret = kobject_add(&q->kobj, &disk_to_dev(disk)->kobj, "queue"); + if (ret < 0) goto unlock; - } if (queue_is_mq(q)) - __blk_mq_register_dev(dev, q); + blk_mq_sysfs_register(disk); mutex_lock(&q->sysfs_lock); mutex_lock(&q->debugfs_mutex); @@ -839,7 +830,7 @@ int blk_register_queue(struct gendisk *disk) blk_mq_debugfs_register(q); mutex_unlock(&q->debugfs_mutex); - ret = disk_register_independent_access_ranges(disk, NULL); + ret = disk_register_independent_access_ranges(disk); if (ret) goto put_dev; @@ -888,8 +879,6 @@ put_dev: mutex_unlock(&q->sysfs_lock); mutex_unlock(&q->sysfs_dir_lock); kobject_del(&q->kobj); - blk_trace_remove_sysfs(dev); - kobject_put(&dev->kobj); return ret; } @@ -927,9 +916,8 @@ void blk_unregister_queue(struct gendisk *disk) * structures that can be modified through sysfs. */ if (queue_is_mq(q)) - blk_mq_unregister_dev(disk_to_dev(disk), q); + blk_mq_sysfs_unregister(disk); blk_crypto_sysfs_unregister(q); - blk_trace_remove_sysfs(disk_to_dev(disk)); mutex_lock(&q->sysfs_lock); elv_unregister_queue(q); @@ -948,6 +936,4 @@ void blk_unregister_queue(struct gendisk *disk) q->sched_debugfs_dir = NULL; q->rqos_debugfs_dir = NULL; mutex_unlock(&q->debugfs_mutex); - - kobject_put(&disk_to_dev(disk)->kobj); } diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 139b2d7a99e2..9f5fe62afff9 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -2203,8 +2203,9 @@ out_unlock: #ifdef CONFIG_BLK_DEV_THROTTLING_LOW static void throtl_track_latency(struct throtl_data *td, sector_t size, - int op, unsigned long time) + enum req_op op, unsigned long time) { + const bool rw = op_is_write(op); struct latency_bucket *latency; int index; @@ -2215,10 +2216,10 @@ static void throtl_track_latency(struct throtl_data *td, sector_t size, index = request_bucket_index(size); - latency = get_cpu_ptr(td->latency_buckets[op]); + latency = get_cpu_ptr(td->latency_buckets[rw]); latency[index].total_latency += time; latency[index].samples++; - put_cpu_ptr(td->latency_buckets[op]); + put_cpu_ptr(td->latency_buckets[rw]); } void blk_throtl_stat_add(struct request *rq, u64 time_ns) diff --git a/block/blk-wbt.c b/block/blk-wbt.c index 0c119be0e813..a9982000b667 100644 --- a/block/blk-wbt.c +++ b/block/blk-wbt.c @@ -451,7 +451,7 @@ static bool close_io(struct rq_wb *rwb) #define REQ_HIPRIO (REQ_SYNC | REQ_META | REQ_PRIO) -static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw) +static inline unsigned int get_limit(struct rq_wb *rwb, blk_opf_t opf) { unsigned int limit; @@ -462,7 +462,7 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw) if (!rwb_enabled(rwb)) return UINT_MAX; - if ((rw & REQ_OP_MASK) == REQ_OP_DISCARD) + if ((opf & REQ_OP_MASK) == REQ_OP_DISCARD) return rwb->wb_background; /* @@ -473,9 +473,9 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw) * the idle limit, or go to normal if we haven't had competing * IO for a bit. */ - if ((rw & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd()) + if ((opf & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd()) limit = rwb->rq_depth.max_depth; - else if ((rw & REQ_BACKGROUND) || close_io(rwb)) { + else if ((opf & REQ_BACKGROUND) || close_io(rwb)) { /* * If less than 100ms since we completed unrelated IO, * limit us to half the depth for background writeback. @@ -490,13 +490,13 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw) struct wbt_wait_data { struct rq_wb *rwb; enum wbt_flags wb_acct; - unsigned long rw; + blk_opf_t opf; }; static bool wbt_inflight_cb(struct rq_wait *rqw, void *private_data) { struct wbt_wait_data *data = private_data; - return rq_wait_inc_below(rqw, get_limit(data->rwb, data->rw)); + return rq_wait_inc_below(rqw, get_limit(data->rwb, data->opf)); } static void wbt_cleanup_cb(struct rq_wait *rqw, void *private_data) @@ -510,13 +510,13 @@ static void wbt_cleanup_cb(struct rq_wait *rqw, void *private_data) * the timer to kick off queuing again. */ static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct, - unsigned long rw) + blk_opf_t opf) { struct rq_wait *rqw = get_rq_wait(rwb, wb_acct); struct wbt_wait_data data = { .rwb = rwb, .wb_acct = wb_acct, - .rw = rw, + .opf = opf, }; rq_qos_wait(rqw, &data, wbt_inflight_cb, wbt_cleanup_cb); @@ -670,7 +670,7 @@ u64 wbt_default_latency_nsec(struct request_queue *q) static int wbt_data_dir(const struct request *rq) { - const int op = req_op(rq); + const enum req_op op = req_op(rq); if (op == REQ_OP_READ) return READ; @@ -820,6 +820,7 @@ int wbt_init(struct request_queue *q) { struct rq_wb *rwb; int i; + int ret; rwb = kzalloc(sizeof(*rwb), GFP_KERNEL); if (!rwb) @@ -846,7 +847,10 @@ int wbt_init(struct request_queue *q) /* * Assign rwb and add the stats callback. */ - rq_qos_add(q, &rwb->rqos); + ret = rq_qos_add(q, &rwb->rqos); + if (ret) + goto err_free; + blk_stat_add_callback(q, rwb->cb); rwb->min_lat_nsec = wbt_default_latency_nsec(q); @@ -855,4 +859,10 @@ int wbt_init(struct request_queue *q) wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags)); return 0; + +err_free: + blk_stat_free_callback(rwb->cb); + kfree(rwb); + return ret; + } diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 38cd840d8838..a264621d4905 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -57,10 +57,10 @@ EXPORT_SYMBOL_GPL(blk_zone_cond_str); */ bool blk_req_needs_zone_write_lock(struct request *rq) { - if (!rq->q->seq_zones_wlock) + if (blk_rq_is_passthrough(rq)) return false; - if (blk_rq_is_passthrough(rq)) + if (!rq->q->disk->seq_zones_wlock) return false; switch (req_op(rq)) { @@ -77,7 +77,7 @@ bool blk_req_zone_write_trylock(struct request *rq) { unsigned int zno = blk_rq_zone_no(rq); - if (test_and_set_bit(zno, rq->q->seq_zones_wlock)) + if (test_and_set_bit(zno, rq->q->disk->seq_zones_wlock)) return false; WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED); @@ -90,7 +90,7 @@ EXPORT_SYMBOL_GPL(blk_req_zone_write_trylock); void __blk_req_zone_write_lock(struct request *rq) { if (WARN_ON_ONCE(test_and_set_bit(blk_rq_zone_no(rq), - rq->q->seq_zones_wlock))) + rq->q->disk->seq_zones_wlock))) return; WARN_ON_ONCE(rq->rq_flags & RQF_ZONE_WRITE_LOCKED); @@ -101,28 +101,29 @@ EXPORT_SYMBOL_GPL(__blk_req_zone_write_lock); void __blk_req_zone_write_unlock(struct request *rq) { rq->rq_flags &= ~RQF_ZONE_WRITE_LOCKED; - if (rq->q->seq_zones_wlock) + if (rq->q->disk->seq_zones_wlock) WARN_ON_ONCE(!test_and_clear_bit(blk_rq_zone_no(rq), - rq->q->seq_zones_wlock)); + rq->q->disk->seq_zones_wlock)); } EXPORT_SYMBOL_GPL(__blk_req_zone_write_unlock); /** - * blkdev_nr_zones - Get number of zones - * @disk: Target gendisk + * bdev_nr_zones - Get number of zones + * @bdev: Target device * * Return the total number of zones of a zoned block device. For a block * device without zone capabilities, the number of zones is always 0. */ -unsigned int blkdev_nr_zones(struct gendisk *disk) +unsigned int bdev_nr_zones(struct block_device *bdev) { - sector_t zone_sectors = blk_queue_zone_sectors(disk->queue); + sector_t zone_sectors = bdev_zone_sectors(bdev); - if (!blk_queue_is_zoned(disk->queue)) + if (!bdev_is_zoned(bdev)) return 0; - return (get_capacity(disk) + zone_sectors - 1) >> ilog2(zone_sectors); + return (bdev_nr_sectors(bdev) + zone_sectors - 1) >> + ilog2(zone_sectors); } -EXPORT_SYMBOL_GPL(blkdev_nr_zones); +EXPORT_SYMBOL_GPL(bdev_nr_zones); /** * blkdev_report_zones - Get zones information @@ -149,8 +150,7 @@ int blkdev_report_zones(struct block_device *bdev, sector_t sector, struct gendisk *disk = bdev->bd_disk; sector_t capacity = get_capacity(disk); - if (!blk_queue_is_zoned(bdev_get_queue(bdev)) || - WARN_ON_ONCE(!disk->fops->report_zones)) + if (!bdev_is_zoned(bdev) || WARN_ON_ONCE(!disk->fops->report_zones)) return -EOPNOTSUPP; if (!nr_zones || sector >= capacity) @@ -189,27 +189,26 @@ static int blk_zone_need_reset_cb(struct blk_zone *zone, unsigned int idx, static int blkdev_zone_reset_all_emulated(struct block_device *bdev, gfp_t gfp_mask) { - struct request_queue *q = bdev_get_queue(bdev); - sector_t capacity = get_capacity(bdev->bd_disk); - sector_t zone_sectors = blk_queue_zone_sectors(q); + struct gendisk *disk = bdev->bd_disk; + sector_t capacity = bdev_nr_sectors(bdev); + sector_t zone_sectors = bdev_zone_sectors(bdev); unsigned long *need_reset; struct bio *bio = NULL; sector_t sector = 0; int ret; - need_reset = blk_alloc_zone_bitmap(q->node, q->nr_zones); + need_reset = blk_alloc_zone_bitmap(disk->queue->node, disk->nr_zones); if (!need_reset) return -ENOMEM; - ret = bdev->bd_disk->fops->report_zones(bdev->bd_disk, 0, - q->nr_zones, blk_zone_need_reset_cb, - need_reset); + ret = disk->fops->report_zones(disk, 0, disk->nr_zones, + blk_zone_need_reset_cb, need_reset); if (ret < 0) goto out_free_need_reset; ret = 0; while (sector < capacity) { - if (!test_bit(blk_queue_zone_no(q, sector), need_reset)) { + if (!test_bit(disk_zone_no(disk, sector), need_reset)) { sector += zone_sectors; continue; } @@ -257,18 +256,17 @@ static int blkdev_zone_reset_all(struct block_device *bdev, gfp_t gfp_mask) * The operation to execute on each zone can be a zone reset, open, close * or finish request. */ -int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, - sector_t sector, sector_t nr_sectors, - gfp_t gfp_mask) +int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, + sector_t sector, sector_t nr_sectors, gfp_t gfp_mask) { struct request_queue *q = bdev_get_queue(bdev); - sector_t zone_sectors = blk_queue_zone_sectors(q); - sector_t capacity = get_capacity(bdev->bd_disk); + sector_t zone_sectors = bdev_zone_sectors(bdev); + sector_t capacity = bdev_nr_sectors(bdev); sector_t end_sector = sector + nr_sectors; struct bio *bio = NULL; int ret = 0; - if (!blk_queue_is_zoned(q)) + if (!bdev_is_zoned(bdev)) return -EOPNOTSUPP; if (bdev_read_only(bdev)) @@ -350,7 +348,7 @@ int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, if (!q) return -ENXIO; - if (!blk_queue_is_zoned(q)) + if (!bdev_is_zoned(bdev)) return -ENOTTY; if (copy_from_user(&rep, argp, sizeof(struct blk_zone_report))) @@ -398,7 +396,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, void __user *argp = (void __user *)arg; struct request_queue *q; struct blk_zone_range zrange; - enum req_opf op; + enum req_op op; int ret; if (!argp) @@ -408,7 +406,7 @@ int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, if (!q) return -ENXIO; - if (!blk_queue_is_zoned(q)) + if (!bdev_is_zoned(bdev)) return -ENOTTY; if (!(mode & FMODE_WRITE)) @@ -450,12 +448,12 @@ fail: return ret; } -void blk_queue_free_zone_bitmaps(struct request_queue *q) +void disk_free_zone_bitmaps(struct gendisk *disk) { - kfree(q->conv_zones_bitmap); - q->conv_zones_bitmap = NULL; - kfree(q->seq_zones_wlock); - q->seq_zones_wlock = NULL; + kfree(disk->conv_zones_bitmap); + disk->conv_zones_bitmap = NULL; + kfree(disk->seq_zones_wlock); + disk->seq_zones_wlock = NULL; } struct blk_revalidate_zone_args { @@ -605,15 +603,15 @@ int blk_revalidate_disk_zones(struct gendisk *disk, blk_mq_freeze_queue(q); if (ret > 0) { blk_queue_chunk_sectors(q, args.zone_sectors); - q->nr_zones = args.nr_zones; - swap(q->seq_zones_wlock, args.seq_zones_wlock); - swap(q->conv_zones_bitmap, args.conv_zones_bitmap); + disk->nr_zones = args.nr_zones; + swap(disk->seq_zones_wlock, args.seq_zones_wlock); + swap(disk->conv_zones_bitmap, args.conv_zones_bitmap); if (update_driver_data) update_driver_data(disk); ret = 0; } else { pr_warn("%s: failed to revalidate zones\n", disk->disk_name); - blk_queue_free_zone_bitmaps(q); + disk_free_zone_bitmaps(disk); } blk_mq_unfreeze_queue(q); @@ -623,16 +621,18 @@ int blk_revalidate_disk_zones(struct gendisk *disk, } EXPORT_SYMBOL_GPL(blk_revalidate_disk_zones); -void blk_queue_clear_zone_settings(struct request_queue *q) +void disk_clear_zone_settings(struct gendisk *disk) { + struct request_queue *q = disk->queue; + blk_mq_freeze_queue(q); - blk_queue_free_zone_bitmaps(q); + disk_free_zone_bitmaps(disk); blk_queue_flag_clear(QUEUE_FLAG_ZONE_RESETALL, q); q->required_elevator_features &= ~ELEVATOR_F_ZBD_SEQ_WRITE; - q->nr_zones = 0; - q->max_open_zones = 0; - q->max_active_zones = 0; + disk->nr_zones = 0; + disk->max_open_zones = 0; + disk->max_active_zones = 0; q->limits.chunk_sectors = 0; q->limits.zone_write_granularity = 0; q->limits.max_zone_append_sectors = 0; diff --git a/block/blk.h b/block/blk.h index 434017701403..1d83b1d41cd1 100644 --- a/block/blk.h +++ b/block/blk.h @@ -31,11 +31,6 @@ extern struct kmem_cache *blk_requestq_srcu_cachep; extern struct kobj_type blk_queue_ktype; extern struct ida blk_queue_ida; -static inline void __blk_get_queue(struct request_queue *q) -{ - kobject_get(&q->kobj); -} - bool is_flush_rq(struct request *req); struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size, @@ -159,6 +154,19 @@ static inline bool blk_discard_mergable(struct request *req) return false; } +static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, + enum req_op op) +{ + if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)) + return min(q->limits.max_discard_sectors, + UINT_MAX >> SECTOR_SHIFT); + + if (unlikely(op == REQ_OP_WRITE_ZEROES)) + return q->limits.max_write_zeroes_sectors; + + return q->limits.max_sectors; +} + #ifdef CONFIG_BLK_DEV_INTEGRITY void blk_flush_integrity(void); bool __bio_integrity_endio(struct bio *); @@ -392,11 +400,11 @@ static inline int blk_iolatency_init(struct request_queue *q) { return 0; } #endif #ifdef CONFIG_BLK_DEV_ZONED -void blk_queue_free_zone_bitmaps(struct request_queue *q); -void blk_queue_clear_zone_settings(struct request_queue *q); +void disk_free_zone_bitmaps(struct gendisk *disk); +void disk_clear_zone_settings(struct gendisk *disk); #else -static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {} -static inline void blk_queue_clear_zone_settings(struct request_queue *q) {} +static inline void disk_free_zone_bitmaps(struct gendisk *disk) {} +static inline void disk_clear_zone_settings(struct gendisk *disk) {} #endif int blk_alloc_ext_minor(void); @@ -411,6 +419,9 @@ int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start, sector_t length); void blk_drop_partitions(struct gendisk *disk); +struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, + struct lock_class_key *lkclass); + int bio_add_hw_page(struct request_queue *q, struct bio *bio, struct page *page, unsigned int len, unsigned int offset, unsigned int max_sectors, bool *same_page); @@ -436,13 +447,14 @@ extern struct device_attribute dev_attr_events; extern struct device_attribute dev_attr_events_async; extern struct device_attribute dev_attr_events_poll_msecs; +extern struct attribute_group blk_trace_attr_group; + long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); extern const struct address_space_operations def_blk_aops; -int disk_register_independent_access_ranges(struct gendisk *disk, - struct blk_independent_access_ranges *new_iars); +int disk_register_independent_access_ranges(struct gendisk *disk); void disk_unregister_independent_access_ranges(struct gendisk *disk); #ifdef CONFIG_FAIL_MAKE_REQUEST diff --git a/block/bounce.c b/block/bounce.c index 8f7b6fe3b4db..c8f487af7be3 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -205,19 +205,26 @@ void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig) int rw = bio_data_dir(*bio_orig); struct bio_vec *to, from; struct bvec_iter iter; - unsigned i = 0; + unsigned i = 0, bytes = 0; bool bounce = false; - int sectors = 0; + int sectors; bio_for_each_segment(from, *bio_orig, iter) { if (i++ < BIO_MAX_VECS) - sectors += from.bv_len >> 9; + bytes += from.bv_len; if (PageHighMem(from.bv_page)) bounce = true; } if (!bounce) return; + /* + * Individual bvecs might not be logical block aligned. Round down + * the split size so that each bio is properly block size aligned, + * even if we do not use the full hardware limits. + */ + sectors = ALIGN_DOWN(bytes, queue_logical_block_size(q)) >> + SECTOR_SHIFT; if (sectors < bio_sectors(*bio_orig)) { bio = bio_split(*bio_orig, sectors, GFP_NOIO, &bounce_bio_split); bio_chain(bio, *bio_orig); diff --git a/block/bsg-lib.c b/block/bsg-lib.c index acfe1357bf6c..d6f5dcdce748 100644 --- a/block/bsg-lib.c +++ b/block/bsg-lib.c @@ -324,14 +324,14 @@ void bsg_remove_queue(struct request_queue *q) container_of(q->tag_set, struct bsg_set, tag_set); bsg_unregister_queue(bset->bd); - blk_cleanup_queue(q); + blk_mq_destroy_queue(q); 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) +static enum blk_eh_timer_return bsg_timeout(struct request *rq) { struct bsg_set *bset = container_of(rq->q->tag_set, struct bsg_set, tag_set); @@ -399,7 +399,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name, return q; out_cleanup_queue: - blk_cleanup_queue(q); + blk_mq_destroy_queue(q); out_queue: blk_mq_free_tag_set(set); out_tag_set: diff --git a/block/elevator.h b/block/elevator.h index 16cd8bdedb7e..3f0593b3bf9d 100644 --- a/block/elevator.h +++ b/block/elevator.h @@ -34,7 +34,7 @@ struct elevator_mq_ops { int (*request_merge)(struct request_queue *q, struct request **, struct bio *); void (*request_merged)(struct request_queue *, struct request *, enum elv_merge); void (*requests_merged)(struct request_queue *, struct request *, struct request *); - void (*limit_depth)(unsigned int, struct blk_mq_alloc_data *); + void (*limit_depth)(blk_opf_t, struct blk_mq_alloc_data *); void (*prepare_request)(struct request *); void (*finish_request)(struct request *); void (*insert_requests)(struct blk_mq_hw_ctx *, struct list_head *, bool); diff --git a/block/fops.c b/block/fops.c index d6b3276a6c68..29066ac5a2fa 100644 --- a/block/fops.c +++ b/block/fops.c @@ -32,14 +32,21 @@ static int blkdev_get_block(struct inode *inode, sector_t iblock, return 0; } -static unsigned int dio_bio_write_op(struct kiocb *iocb) +static blk_opf_t dio_bio_write_op(struct kiocb *iocb) { - unsigned int op = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE; + blk_opf_t opf = REQ_OP_WRITE | REQ_SYNC | REQ_IDLE; /* avoid the need for a I/O completion work item */ if (iocb->ki_flags & IOCB_DSYNC) - op |= REQ_FUA; - return op; + opf |= REQ_FUA; + return opf; +} + +static bool blkdev_dio_unaligned(struct block_device *bdev, loff_t pos, + struct iov_iter *iter) +{ + return pos & (bdev_logical_block_size(bdev) - 1) || + !bdev_iter_is_aligned(bdev, iter); } #define DIO_INLINE_BIO_VECS 4 @@ -54,8 +61,7 @@ static ssize_t __blkdev_direct_IO_simple(struct kiocb *iocb, struct bio bio; ssize_t ret; - if ((pos | iov_iter_alignment(iter)) & - (bdev_logical_block_size(bdev) - 1)) + if (blkdev_dio_unaligned(bdev, pos, iter)) return -EINVAL; if (nr_pages <= DIO_INLINE_BIO_VECS) @@ -169,12 +175,11 @@ static ssize_t __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, struct blkdev_dio *dio; struct bio *bio; bool is_read = (iov_iter_rw(iter) == READ), is_sync; - unsigned int opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb); + blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb); loff_t pos = iocb->ki_pos; int ret = 0; - if ((pos | iov_iter_alignment(iter)) & - (bdev_logical_block_size(bdev) - 1)) + if (blkdev_dio_unaligned(bdev, pos, iter)) return -EINVAL; if (iocb->ki_flags & IOCB_ALLOC_CACHE) @@ -292,14 +297,13 @@ static ssize_t __blkdev_direct_IO_async(struct kiocb *iocb, { struct block_device *bdev = iocb->ki_filp->private_data; bool is_read = iov_iter_rw(iter) == READ; - unsigned int opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb); + blk_opf_t opf = is_read ? REQ_OP_READ : dio_bio_write_op(iocb); struct blkdev_dio *dio; struct bio *bio; loff_t pos = iocb->ki_pos; int ret = 0; - if ((pos | iov_iter_alignment(iter)) & - (bdev_logical_block_size(bdev) - 1)) + if (blkdev_dio_unaligned(bdev, pos, iter)) return -EINVAL; if (iocb->ki_flags & IOCB_ALLOC_CACHE) diff --git a/block/genhd.c b/block/genhd.c index 278227ba1d53..e1d5b10ac193 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -101,29 +101,6 @@ bool set_capacity_and_notify(struct gendisk *disk, sector_t size) } EXPORT_SYMBOL_GPL(set_capacity_and_notify); -/* - * Format the device name of the indicated block device into the supplied buffer - * and return a pointer to that same buffer for convenience. - * - * Note: do not use this in new code, use the %pg specifier to sprintf and - * printk insted. - */ -const char *bdevname(struct block_device *bdev, char *buf) -{ - struct gendisk *hd = bdev->bd_disk; - int partno = bdev->bd_partno; - - if (!partno) - snprintf(buf, BDEVNAME_SIZE, "%s", hd->disk_name); - else if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) - snprintf(buf, BDEVNAME_SIZE, "%sp%d", hd->disk_name, partno); - else - snprintf(buf, BDEVNAME_SIZE, "%s%d", hd->disk_name, partno); - - return buf; -} -EXPORT_SYMBOL(bdevname); - static void part_stat_read_all(struct block_device *part, struct disk_stats *stat) { @@ -617,6 +594,8 @@ void del_gendisk(struct gendisk *disk) * Fail any new I/O. */ set_bit(GD_DEAD, &disk->state); + if (test_bit(GD_OWNS_QUEUE, &disk->state)) + blk_queue_flag_set(QUEUE_FLAG_DYING, q); set_capacity(disk, 0); /* @@ -663,11 +642,16 @@ void del_gendisk(struct gendisk *disk) blk_mq_unquiesce_queue(q); /* - * Allow using passthrough request again after the queue is torn down. + * If the disk does not own the queue, allow using passthrough requests + * again. Else leave the queue frozen to fail all I/O. */ - blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q); - __blk_mq_unfreeze_queue(q, true); - + if (!test_bit(GD_OWNS_QUEUE, &disk->state)) { + blk_queue_flag_clear(QUEUE_FLAG_INIT_DONE, q); + __blk_mq_unfreeze_queue(q, true); + } else { + if (queue_is_mq(q)) + blk_mq_exit_queue(q); + } } EXPORT_SYMBOL(del_gendisk); @@ -1127,6 +1111,9 @@ static struct attribute_group disk_attr_group = { static const struct attribute_group *disk_attr_groups[] = { &disk_attr_group, +#ifdef CONFIG_BLK_DEV_IO_TRACE + &blk_trace_attr_group, +#endif NULL }; @@ -1151,10 +1138,23 @@ static void disk_release(struct device *dev) might_sleep(); WARN_ON_ONCE(disk_live(disk)); + /* + * To undo the all initialization from blk_mq_init_allocated_queue in + * case of a probe failure where add_disk is never called we have to + * call blk_mq_exit_queue here. We can't do this for the more common + * teardown case (yet) as the tagset can be gone by the time the disk + * is released once it was added. + */ + if (queue_is_mq(disk->queue) && + test_bit(GD_OWNS_QUEUE, &disk->state) && + !test_bit(GD_ADDED, &disk->state)) + blk_mq_exit_queue(disk->queue); + blkcg_exit_queue(disk->queue); disk_release_events(disk); kfree(disk->random); + disk_free_zone_bitmaps(disk); xa_destroy(&disk->part_tbl); disk->queue->disk = NULL; @@ -1338,9 +1338,6 @@ struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, { struct gendisk *disk; - if (!blk_get_queue(q)) - return NULL; - disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id); if (!disk) goto out_put_queue; @@ -1391,7 +1388,6 @@ out_put_queue: blk_put_queue(q); return NULL; } -EXPORT_SYMBOL(__alloc_disk_node); struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass) { @@ -1404,9 +1400,10 @@ struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass) disk = __alloc_disk_node(q, node, lkclass); if (!disk) { - blk_cleanup_queue(q); + blk_put_queue(q); return NULL; } + set_bit(GD_OWNS_QUEUE, &disk->state); return disk; } EXPORT_SYMBOL(__blk_alloc_disk); @@ -1418,6 +1415,9 @@ EXPORT_SYMBOL(__blk_alloc_disk); * This decrements the refcount for the struct gendisk. When this reaches 0 * we'll have disk_release() called. * + * Note: for blk-mq disk put_disk must be called before freeing the tag_set + * when handling probe errors (that is before add_disk() is called). + * * Context: Any context, but the last reference must not be dropped from * atomic context. */ @@ -1428,22 +1428,6 @@ void put_disk(struct gendisk *disk) } EXPORT_SYMBOL(put_disk); -/** - * blk_cleanup_disk - shutdown a gendisk allocated by blk_alloc_disk - * @disk: gendisk to shutdown - * - * Mark the queue hanging off @disk DYING, drain all pending requests, then mark - * the queue DEAD, destroy and put it and the gendisk structure. - * - * Context: can sleep - */ -void blk_cleanup_disk(struct gendisk *disk) -{ - blk_cleanup_queue(disk->queue); - put_disk(disk); -} -EXPORT_SYMBOL(blk_cleanup_disk); - static void set_disk_ro_uevent(struct gendisk *gd, int ro) { char event[] = "DISK_RO=1"; diff --git a/block/ioctl.c b/block/ioctl.c index 46949f1b0dba..60121e89052b 100644 --- a/block/ioctl.c +++ b/block/ioctl.c @@ -495,7 +495,7 @@ static int blkdev_common_ioctl(struct block_device *bdev, fmode_t mode, case BLKGETZONESZ: return put_uint(argp, bdev_zone_sectors(bdev)); case BLKGETNRZONES: - return put_uint(argp, blkdev_nr_zones(bdev->bd_disk)); + return put_uint(argp, bdev_nr_zones(bdev)); case BLKROGET: return put_int(argp, bdev_read_only(bdev) != 0); case BLKSSZGET: /* get block device logical block size */ diff --git a/block/ioprio.c b/block/ioprio.c index 2fe068fcaad5..32a456b45804 100644 --- a/block/ioprio.c +++ b/block/ioprio.c @@ -138,6 +138,32 @@ out: return ret; } +/* + * If the task has set an I/O priority, use that. Otherwise, return + * the default I/O priority. + * + * Expected to be called for current task or with task_lock() held to keep + * io_context stable. + */ +int __get_task_ioprio(struct task_struct *p) +{ + struct io_context *ioc = p->io_context; + int prio; + + if (p != current) + lockdep_assert_held(&p->alloc_lock); + if (ioc) + prio = ioc->ioprio; + else + prio = IOPRIO_DEFAULT; + + if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE) + prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p), + task_nice_ioprio(p)); + return prio; +} +EXPORT_SYMBOL_GPL(__get_task_ioprio); + static int get_task_ioprio(struct task_struct *p) { int ret; @@ -145,22 +171,38 @@ static int get_task_ioprio(struct task_struct *p) ret = security_task_getioprio(p); if (ret) goto out; - ret = IOPRIO_DEFAULT; + task_lock(p); + ret = __get_task_ioprio(p); + task_unlock(p); +out: + return ret; +} + +/* + * Return raw IO priority value as set by userspace. We use this for + * ioprio_get(pid, IOPRIO_WHO_PROCESS) so that we keep historical behavior and + * also so that userspace can distinguish unset IO priority (which just gets + * overriden based on task's nice value) from IO priority set to some value. + */ +static int get_task_raw_ioprio(struct task_struct *p) +{ + int ret; + + ret = security_task_getioprio(p); + if (ret) + goto out; task_lock(p); if (p->io_context) ret = p->io_context->ioprio; + else + ret = IOPRIO_DEFAULT; task_unlock(p); out: return ret; } -int ioprio_best(unsigned short aprio, unsigned short bprio) +static int ioprio_best(unsigned short aprio, unsigned short bprio) { - if (!ioprio_valid(aprio)) - aprio = IOPRIO_DEFAULT; - if (!ioprio_valid(bprio)) - bprio = IOPRIO_DEFAULT; - return min(aprio, bprio); } @@ -181,7 +223,7 @@ SYSCALL_DEFINE2(ioprio_get, int, which, int, who) else p = find_task_by_vpid(who); if (p) - ret = get_task_ioprio(p); + ret = get_task_raw_ioprio(p); break; case IOPRIO_WHO_PGRP: if (!who) diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c index 8f7c745b4a57..b05357bced99 100644 --- a/block/kyber-iosched.c +++ b/block/kyber-iosched.c @@ -195,9 +195,9 @@ struct kyber_hctx_data { static int kyber_domain_wake(wait_queue_entry_t *wait, unsigned mode, int flags, void *key); -static unsigned int kyber_sched_domain(unsigned int op) +static unsigned int kyber_sched_domain(blk_opf_t opf) { - switch (op & REQ_OP_MASK) { + switch (opf & REQ_OP_MASK) { case REQ_OP_READ: return KYBER_READ; case REQ_OP_WRITE: @@ -553,13 +553,13 @@ static void rq_clear_domain_token(struct kyber_queue_data *kqd, } } -static void kyber_limit_depth(unsigned int op, struct blk_mq_alloc_data *data) +static void kyber_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) { /* * We use the scheduler tags as per-hardware queue queueing tokens. * Async requests can be limited at this stage. */ - if (!op_is_sync(op)) { + if (!op_is_sync(opf)) { struct kyber_queue_data *kqd = data->q->elevator->elevator_data; data->shallow_depth = kqd->async_depth; diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 1a9e835e816c..5639921dfa92 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -543,12 +543,12 @@ unlock: * Called by __blk_mq_alloc_request(). The shallow_depth value set by this * function is used by __blk_mq_get_tag(). */ -static void dd_limit_depth(unsigned int op, struct blk_mq_alloc_data *data) +static void dd_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data) { struct deadline_data *dd = data->q->elevator->elevator_data; /* Do not throttle synchronous reads. */ - if (op_is_sync(op) && !op_is_write(op)) + if (op_is_sync(opf) && !op_is_write(opf)) return; /* diff --git a/block/partitions/core.c b/block/partitions/core.c index 8a0ec929023b..1a45b1dd6491 100644 --- a/block/partitions/core.c +++ b/block/partitions/core.c @@ -9,7 +9,6 @@ #include <linux/slab.h> #include <linux/ctype.h> #include <linux/vmalloc.h> -#include <linux/blktrace_api.h> #include <linux/raid/detect.h> #include "check.h" @@ -331,7 +330,7 @@ static struct block_device *add_partition(struct gendisk *disk, int partno, case BLK_ZONED_HA: pr_info("%s: disabling host aware zoned block device support due to partitions\n", disk->disk_name); - blk_queue_set_zoned(disk, BLK_ZONED_NONE); + disk_set_zoned(disk, BLK_ZONED_NONE); break; case BLK_ZONED_NONE: break; |