diff options
Diffstat (limited to 'block/blk.h')
| -rw-r--r-- | block/blk.h | 780 |
1 files changed, 535 insertions, 245 deletions
diff --git a/block/blk.h b/block/blk.h index b5d1f0fc6547..e4c433f62dfc 100644 --- a/block/blk.h +++ b/block/blk.h @@ -2,73 +2,133 @@ #ifndef BLK_INTERNAL_H #define BLK_INTERNAL_H -#include <linux/idr.h> -#include <linux/blk-mq.h> -#include <linux/part_stat.h> +#include <linux/bio-integrity.h> #include <linux/blk-crypto.h> +#include <linux/lockdep.h> +#include <linux/memblock.h> /* for max_pfn/max_low_pfn */ +#include <linux/sched/sysctl.h> +#include <linux/timekeeping.h> #include <xen/xen.h> #include "blk-crypto-internal.h" -#include "blk-mq.h" -#include "blk-mq-sched.h" + +struct elv_change_ctx; + +/* + * Default upper limit for the software max_sectors limit used for regular I/Os. + * This can be increased through sysfs. + * + * This should not be confused with the max_hw_sector limit that is entirely + * controlled by the block device driver, usually based on hardware limits. + */ +#define BLK_DEF_MAX_SECTORS_CAP (SZ_4M >> SECTOR_SHIFT) + +#define BLK_DEV_MAX_SECTORS (LLONG_MAX >> 9) +#define BLK_MIN_SEGMENT_SIZE 4096 /* Max future timer expiry for timeouts */ #define BLK_MAX_TIMEOUT (5 * HZ) -#ifdef CONFIG_DEBUG_FS +extern const struct kobj_type blk_queue_ktype; extern struct dentry *blk_debugfs_root; -#endif struct blk_flush_queue { + spinlock_t mq_flush_lock; unsigned int flush_pending_idx:1; unsigned int flush_running_idx:1; blk_status_t rq_status; unsigned long flush_pending_since; struct list_head flush_queue[2]; - struct list_head flush_data_in_flight; + unsigned long flush_data_in_flight; struct request *flush_rq; + struct rcu_head rcu_head; +}; + +bool is_flush_rq(struct request *req); + +struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size, + gfp_t flags); +void blk_free_flush_queue(struct blk_flush_queue *q); + +bool __blk_mq_unfreeze_queue(struct request_queue *q, bool force_atomic); +bool blk_queue_start_drain(struct request_queue *q); +bool __blk_freeze_queue_start(struct request_queue *q, + struct task_struct *owner); +int __bio_queue_enter(struct request_queue *q, struct bio *bio); +void submit_bio_noacct_nocheck(struct bio *bio, bool split); +void bio_await_chain(struct bio *bio); + +static inline bool blk_try_enter_queue(struct request_queue *q, bool pm) +{ + rcu_read_lock(); + if (!percpu_ref_tryget_live_rcu(&q->q_usage_counter)) + goto fail; /* - * flush_rq shares tag with this rq, both can't be active - * at the same time + * The code that increments the pm_only counter must ensure that the + * counter is globally visible before the queue is unfrozen. */ - struct request *orig_rq; - struct lock_class_key key; - spinlock_t mq_flush_lock; -}; + if (blk_queue_pm_only(q) && + (!pm || queue_rpm_status(q) == RPM_SUSPENDED)) + goto fail_put; -extern struct kmem_cache *blk_requestq_cachep; -extern struct kobj_type blk_queue_ktype; -extern struct ida blk_queue_ida; + rcu_read_unlock(); + return true; -static inline struct blk_flush_queue * -blk_get_flush_queue(struct request_queue *q, struct blk_mq_ctx *ctx) -{ - return blk_mq_map_queue(q, REQ_OP_FLUSH, ctx)->fq; +fail_put: + blk_queue_exit(q); +fail: + rcu_read_unlock(); + return false; } -static inline void __blk_get_queue(struct request_queue *q) +static inline int bio_queue_enter(struct bio *bio) { - kobject_get(&q->kobj); + struct request_queue *q = bdev_get_queue(bio->bi_bdev); + + if (blk_try_enter_queue(q, false)) { + rwsem_acquire_read(&q->io_lockdep_map, 0, 0, _RET_IP_); + rwsem_release(&q->io_lockdep_map, _RET_IP_); + return 0; + } + return __bio_queue_enter(q, bio); } -static inline bool -is_flush_rq(struct request *req, struct blk_mq_hw_ctx *hctx) +static inline void blk_wait_io(struct completion *done) { - return hctx->fq->flush_rq == req; + /* Prevent hang_check timer from firing at us during very long I/O */ + unsigned long timeout = sysctl_hung_task_timeout_secs * HZ / 2; + + if (timeout) + while (!wait_for_completion_io_timeout(done, timeout)) + ; + else + wait_for_completion_io(done); } -struct blk_flush_queue *blk_alloc_flush_queue(int node, int cmd_size, - gfp_t flags); -void blk_free_flush_queue(struct blk_flush_queue *q); +struct block_device *blkdev_get_no_open(dev_t dev, bool autoload); +void blkdev_put_no_open(struct block_device *bdev); + +#define BIO_INLINE_VECS 4 +struct bio_vec *bvec_alloc(mempool_t *pool, unsigned short *nr_vecs, + gfp_t gfp_mask); +void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned short nr_vecs); -void blk_freeze_queue(struct request_queue *q); +bool bvec_try_merge_hw_page(struct request_queue *q, struct bio_vec *bv, + struct page *page, unsigned len, unsigned offset); static inline bool biovec_phys_mergeable(struct request_queue *q, struct bio_vec *vec1, struct bio_vec *vec2) { unsigned long mask = queue_segment_boundary(q); - phys_addr_t addr1 = page_to_phys(vec1->bv_page) + vec1->bv_offset; - phys_addr_t addr2 = page_to_phys(vec2->bv_page) + vec2->bv_offset; + phys_addr_t addr1 = bvec_phys(vec1); + phys_addr_t addr2 = bvec_phys(vec2); + + /* + * Merging adjacent physical pages may not work correctly under KMSAN + * if their metadata pages aren't adjacent. Just disable merging. + */ + if (IS_ENABLED(CONFIG_KMSAN)) + return false; if (addr1 + vec1->bv_len != addr2) return false; @@ -79,55 +139,121 @@ static inline bool biovec_phys_mergeable(struct request_queue *q, return true; } -static inline bool __bvec_gap_to_prev(struct request_queue *q, +static inline bool __bvec_gap_to_prev(const struct queue_limits *lim, struct bio_vec *bprv, unsigned int offset) { - return (offset & queue_virt_boundary(q)) || - ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); + return (offset & lim->virt_boundary_mask) || + ((bprv->bv_offset + bprv->bv_len) & lim->virt_boundary_mask); } /* * Check if adding a bio_vec after bprv with offset would create a gap in * the SG list. Most drivers don't care about this, but some do. */ -static inline bool bvec_gap_to_prev(struct request_queue *q, +static inline bool bvec_gap_to_prev(const struct queue_limits *lim, struct bio_vec *bprv, unsigned int offset) { - if (!queue_virt_boundary(q)) + if (!lim->virt_boundary_mask) + return false; + return __bvec_gap_to_prev(lim, bprv, offset); +} + +static inline bool rq_mergeable(struct request *rq) +{ + if (blk_rq_is_passthrough(rq)) + return false; + + if (req_op(rq) == REQ_OP_FLUSH) + return false; + + if (req_op(rq) == REQ_OP_WRITE_ZEROES) + return false; + + if (req_op(rq) == REQ_OP_ZONE_APPEND) + return false; + + if (rq->cmd_flags & REQ_NOMERGE_FLAGS) + return false; + if (rq->rq_flags & RQF_NOMERGE_FLAGS) return false; - return __bvec_gap_to_prev(q, bprv, offset); + + return true; +} + +/* + * There are two different ways to handle DISCARD merges: + * 1) If max_discard_segments > 1, the driver treats every bio as a range and + * send the bios to controller together. The ranges don't need to be + * contiguous. + * 2) Otherwise, the request will be normal read/write requests. The ranges + * need to be contiguous. + */ +static inline bool blk_discard_mergable(struct request *req) +{ + if (req_op(req) == REQ_OP_DISCARD && + queue_max_discard_segments(req->q) > 1) + return true; + return false; +} + +static inline unsigned int blk_rq_get_max_segments(struct request *rq) +{ + if (req_op(rq) == REQ_OP_DISCARD) + return queue_max_discard_segments(rq->q); + return queue_max_segments(rq->q); } -static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio, - unsigned int nr_segs) +static inline unsigned int blk_queue_get_max_sectors(struct request *rq) { - rq->nr_phys_segments = nr_segs; - rq->__data_len = bio->bi_iter.bi_size; - rq->bio = rq->biotail = bio; - rq->ioprio = bio_prio(bio); + struct request_queue *q = rq->q; + enum req_op op = req_op(rq); + + 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; - if (bio->bi_disk) - rq->rq_disk = bio->bi_disk; + if (rq->cmd_flags & REQ_ATOMIC) + return q->limits.atomic_write_max_sectors; + + return q->limits.max_sectors; } #ifdef CONFIG_BLK_DEV_INTEGRITY void blk_flush_integrity(void); -bool __bio_integrity_endio(struct bio *); void bio_integrity_free(struct bio *bio); + +/* + * Integrity payloads can either be owned by the submitter, in which case + * bio_uninit will free them, or owned and generated by the block layer, + * in which case we'll verify them here (for reads) and free them before + * the bio is handed back to the submitted. + */ +bool __bio_integrity_endio(struct bio *bio); static inline bool bio_integrity_endio(struct bio *bio) { - if (bio_integrity(bio)) + struct bio_integrity_payload *bip = bio_integrity(bio); + + if (bip && (bip->bip_flags & BIP_BLOCK_INTEGRITY)) return __bio_integrity_endio(bio); return true; } +bool blk_integrity_merge_rq(struct request_queue *, struct request *, + struct request *); +bool blk_integrity_merge_bio(struct request_queue *, struct request *, + struct bio *); + static inline bool integrity_req_gap_back_merge(struct request *req, struct bio *next) { struct bio_integrity_payload *bip = bio_integrity(req->bio); struct bio_integrity_payload *bip_next = bio_integrity(next); - return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], + return bvec_gap_to_prev(&req->q->limits, + &bip->bip_vec[bip->bip_vcnt - 1], bip_next->bip_vec[0].bv_offset); } @@ -137,13 +263,23 @@ static inline bool integrity_req_gap_front_merge(struct request *req, struct bio_integrity_payload *bip = bio_integrity(bio); struct bio_integrity_payload *bip_next = bio_integrity(req->bio); - return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], + return bvec_gap_to_prev(&req->q->limits, + &bip->bip_vec[bip->bip_vcnt - 1], bip_next->bip_vec[0].bv_offset); } -void blk_integrity_add(struct gendisk *); -void blk_integrity_del(struct gendisk *); +extern const struct attribute_group blk_integrity_attr_group; #else /* CONFIG_BLK_DEV_INTEGRITY */ +static inline bool blk_integrity_merge_rq(struct request_queue *rq, + struct request *r1, struct request *r2) +{ + return true; +} +static inline bool blk_integrity_merge_bio(struct request_queue *rq, + struct request *r, struct bio *b) +{ + return true; +} static inline bool integrity_req_gap_back_merge(struct request *req, struct bio *next) { @@ -165,53 +301,41 @@ static inline bool bio_integrity_endio(struct bio *bio) static inline void bio_integrity_free(struct bio *bio) { } -static inline void blk_integrity_add(struct gendisk *disk) -{ -} -static inline void blk_integrity_del(struct gendisk *disk) -{ -} #endif /* CONFIG_BLK_DEV_INTEGRITY */ unsigned long blk_rq_timeout(unsigned long timeout); void blk_add_timer(struct request *req); -bool bio_attempt_front_merge(struct request *req, struct bio *bio, - unsigned int nr_segs); -bool bio_attempt_back_merge(struct request *req, struct bio *bio, - unsigned int nr_segs); -bool bio_attempt_discard_merge(struct request_queue *q, struct request *req, - struct bio *bio); +enum bio_merge_status { + BIO_MERGE_OK, + BIO_MERGE_NONE, + BIO_MERGE_FAILED, +}; + +enum bio_merge_status bio_attempt_back_merge(struct request *req, + struct bio *bio, unsigned int nr_segs); bool blk_attempt_plug_merge(struct request_queue *q, struct bio *bio, - unsigned int nr_segs, struct request **same_queue_rq); + unsigned int nr_segs); +bool blk_bio_list_merge(struct request_queue *q, struct list_head *list, + struct bio *bio, unsigned int nr_segs); -void blk_account_io_start(struct request *req); -void blk_account_io_done(struct request *req, u64 now); +/* + * Plug flush limits + */ +#define BLK_MAX_REQUEST_COUNT 32 +#define BLK_PLUG_FLUSH_SIZE (128 * 1024) /* * Internal elevator interface */ #define ELV_ON_HASH(rq) ((rq)->rq_flags & RQF_HASHED) -void blk_insert_flush(struct request *rq); - -void elevator_init_mq(struct request_queue *q); -int elevator_switch_mq(struct request_queue *q, - struct elevator_type *new_e); -void __elevator_exit(struct request_queue *, struct elevator_queue *); -int elv_register_queue(struct request_queue *q, bool uevent); -void elv_unregister_queue(struct request_queue *q); - -static inline void elevator_exit(struct request_queue *q, - struct elevator_queue *e) -{ - lockdep_assert_held(&q->sysfs_lock); - - blk_mq_sched_free_requests(q); - __elevator_exit(q, e); -} +bool blk_insert_flush(struct request *rq); -struct hd_struct *__disk_get_part(struct gendisk *disk, int partno); +void elv_update_nr_hw_queues(struct request_queue *q, + struct elv_change_ctx *ctx); +void elevator_set_default(struct request_queue *q); +void elevator_set_none(struct request_queue *q); ssize_t part_size_show(struct device *dev, struct device_attribute *attr, char *buf); @@ -223,46 +347,110 @@ ssize_t part_fail_show(struct device *dev, struct device_attribute *attr, char *buf); ssize_t part_fail_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count); - -#ifdef CONFIG_FAIL_IO_TIMEOUT -int blk_should_fake_timeout(struct request_queue *); ssize_t part_timeout_show(struct device *, struct device_attribute *, char *); ssize_t part_timeout_store(struct device *, struct device_attribute *, const char *, size_t); -#else -static inline int blk_should_fake_timeout(struct request_queue *q) + +struct bio *bio_split_discard(struct bio *bio, const struct queue_limits *lim, + unsigned *nsegs); +struct bio *bio_split_write_zeroes(struct bio *bio, + const struct queue_limits *lim, unsigned *nsegs); +struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim, + unsigned *nr_segs); +struct bio *bio_split_zone_append(struct bio *bio, + const struct queue_limits *lim, unsigned *nr_segs); + +/* + * All drivers must accept single-segments bios that are smaller than PAGE_SIZE. + * + * This is a quick and dirty check that relies on the fact that bi_io_vec[0] is + * always valid if a bio has data. The check might lead to occasional false + * positives when bios are cloned, but compared to the performance impact of + * cloned bios themselves the loop below doesn't matter anyway. + */ +static inline bool bio_may_need_split(struct bio *bio, + const struct queue_limits *lim) { - return 0; + if (lim->chunk_sectors) + return true; + if (bio->bi_vcnt != 1) + return true; + return bio->bi_io_vec->bv_len + bio->bi_io_vec->bv_offset > + lim->max_fast_segment_size; +} + +/** + * __bio_split_to_limits - split a bio to fit the queue limits + * @bio: bio to be split + * @lim: queue limits to split based on + * @nr_segs: returns the number of segments in the returned bio + * + * Check if @bio needs splitting based on the queue limits, and if so split off + * a bio fitting the limits from the beginning of @bio and return it. @bio is + * shortened to the remainder and re-submitted. + * + * The split bio is allocated from @q->bio_split, which is provided by the + * block layer. + */ +static inline struct bio *__bio_split_to_limits(struct bio *bio, + const struct queue_limits *lim, unsigned int *nr_segs) +{ + switch (bio_op(bio)) { + case REQ_OP_READ: + case REQ_OP_WRITE: + if (bio_may_need_split(bio, lim)) + return bio_split_rw(bio, lim, nr_segs); + *nr_segs = 1; + return bio; + case REQ_OP_ZONE_APPEND: + return bio_split_zone_append(bio, lim, nr_segs); + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: + return bio_split_discard(bio, lim, nr_segs); + case REQ_OP_WRITE_ZEROES: + return bio_split_write_zeroes(bio, lim, nr_segs); + default: + /* other operations can't be split */ + *nr_segs = 0; + return bio; + } +} + +/** + * get_max_segment_size() - maximum number of bytes to add as a single segment + * @lim: Request queue limits. + * @paddr: address of the range to add + * @len: maximum length available to add at @paddr + * + * Returns the maximum number of bytes of the range starting at @paddr that can + * be added to a single segment. + */ +static inline unsigned get_max_segment_size(const struct queue_limits *lim, + phys_addr_t paddr, unsigned int len) +{ + /* + * Prevent an overflow if mask = ULONG_MAX and offset = 0 by adding 1 + * after having calculated the minimum. + */ + return min_t(unsigned long, len, + min(lim->seg_boundary_mask - (lim->seg_boundary_mask & paddr), + (unsigned long)lim->max_segment_size - 1) + 1); } -#endif -void __blk_queue_split(struct request_queue *q, struct bio **bio, - unsigned int *nr_segs); int ll_back_merge_fn(struct request *req, struct bio *bio, unsigned int nr_segs); -int ll_front_merge_fn(struct request *req, struct bio *bio, - unsigned int nr_segs); -struct request *attempt_back_merge(struct request_queue *q, struct request *rq); -struct request *attempt_front_merge(struct request_queue *q, struct request *rq); -int blk_attempt_req_merge(struct request_queue *q, struct request *rq, +bool blk_attempt_req_merge(struct request_queue *q, struct request *rq, struct request *next); unsigned int blk_recalc_rq_segments(struct request *rq); -void blk_rq_set_mixed_merge(struct request *rq); bool blk_rq_merge_ok(struct request *rq, struct bio *bio); enum elv_merge blk_try_merge(struct request *rq, struct bio *bio); +int blk_set_default_limits(struct queue_limits *lim); +void blk_apply_bdi_limits(struct backing_dev_info *bdi, + struct queue_limits *lim); int blk_dev_init(void); -/* - * Contribute to IO statistics IFF: - * - * a) it's attached to a gendisk, and - * b) the queue had IO stats enabled when this request was started - */ -static inline bool blk_do_io_stat(struct request *rq) -{ - return rq->rq_disk && (rq->rq_flags & RQF_IO_STAT); -} +void update_io_ticks(struct block_device *part, unsigned long now, bool end); static inline void req_set_nomerge(struct request_queue *q, struct request *req) { @@ -272,172 +460,274 @@ static inline void req_set_nomerge(struct request_queue *q, struct request *req) } /* - * The max size one bio can handle is UINT_MAX becasue bvec_iter.bi_size - * is defined as 'unsigned int', meantime it has to aligned to with logical - * block size which is the minimum accepted unit by hardware. - */ -static inline unsigned int bio_allowed_max_sectors(struct request_queue *q) -{ - return round_down(UINT_MAX, queue_logical_block_size(q)) >> 9; -} - -/* * Internal io_context interface */ -void get_io_context(struct io_context *ioc); -struct io_cq *ioc_lookup_icq(struct io_context *ioc, struct request_queue *q); -struct io_cq *ioc_create_icq(struct io_context *ioc, struct request_queue *q, - gfp_t gfp_mask); +struct io_cq *ioc_find_get_icq(struct request_queue *q); +struct io_cq *ioc_lookup_icq(struct request_queue *q); +#ifdef CONFIG_BLK_ICQ void ioc_clear_queue(struct request_queue *q); - -int create_task_io_context(struct task_struct *task, gfp_t gfp_mask, int node); - -/* - * Internal throttling interface - */ -#ifdef CONFIG_BLK_DEV_THROTTLING -extern int blk_throtl_init(struct request_queue *q); -extern void blk_throtl_exit(struct request_queue *q); -extern void blk_throtl_register_queue(struct request_queue *q); -#else /* CONFIG_BLK_DEV_THROTTLING */ -static inline int blk_throtl_init(struct request_queue *q) { return 0; } -static inline void blk_throtl_exit(struct request_queue *q) { } -static inline void blk_throtl_register_queue(struct request_queue *q) { } -#endif /* CONFIG_BLK_DEV_THROTTLING */ -#ifdef CONFIG_BLK_DEV_THROTTLING_LOW -extern ssize_t blk_throtl_sample_time_show(struct request_queue *q, char *page); -extern ssize_t blk_throtl_sample_time_store(struct request_queue *q, - const char *page, size_t count); -extern void blk_throtl_bio_endio(struct bio *bio); -extern void blk_throtl_stat_add(struct request *rq, u64 time); #else -static inline void blk_throtl_bio_endio(struct bio *bio) { } -static inline void blk_throtl_stat_add(struct request *rq, u64 time) { } -#endif +static inline void ioc_clear_queue(struct request_queue *q) +{ +} +#endif /* CONFIG_BLK_ICQ */ -#ifdef CONFIG_BOUNCE -extern int init_emergency_isa_pool(void); -extern void blk_queue_bounce(struct request_queue *q, struct bio **bio); -#else -static inline int init_emergency_isa_pool(void) +#ifdef CONFIG_BLK_DEV_ZONED +void disk_init_zone_resources(struct gendisk *disk); +void disk_free_zone_resources(struct gendisk *disk); +static inline bool bio_zone_write_plugging(struct bio *bio) { - return 0; + return bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING); } -static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio) +static inline bool blk_req_bio_is_zone_append(struct request *rq, + struct bio *bio) { + return req_op(rq) == REQ_OP_ZONE_APPEND || + bio_flagged(bio, BIO_EMULATES_ZONE_APPEND); } -#endif /* CONFIG_BOUNCE */ - -#ifdef CONFIG_BLK_CGROUP_IOLATENCY -extern int blk_iolatency_init(struct request_queue *q); -#else -static inline int blk_iolatency_init(struct request_queue *q) { return 0; } -#endif +void blk_zone_write_plug_bio_merged(struct bio *bio); +void blk_zone_write_plug_init_request(struct request *rq); +void blk_zone_append_update_request_bio(struct request *rq, struct bio *bio); +void blk_zone_mgmt_bio_endio(struct bio *bio); +void blk_zone_write_plug_bio_endio(struct bio *bio); +static inline void blk_zone_bio_endio(struct bio *bio) +{ + /* + * Zone management BIOs may impact zone write plugs (e.g. a zone reset + * changes a zone write plug zone write pointer offset), but these + * operation do not go through zone write plugging as they may operate + * on zones that do not have a zone write + * plug. blk_zone_mgmt_bio_endio() handles the potential changes to zone + * write plugs that are present. + */ + if (op_is_zone_mgmt(bio_op(bio))) { + blk_zone_mgmt_bio_endio(bio); + return; + } -struct bio *blk_next_bio(struct bio *bio, unsigned int nr_pages, gfp_t gfp); + /* + * For write BIOs to zoned devices, signal the completion of the BIO so + * that the next write BIO can be submitted by zone write plugging. + */ + if (bio_zone_write_plugging(bio)) + blk_zone_write_plug_bio_endio(bio); +} -#ifdef CONFIG_BLK_DEV_ZONED -void blk_queue_free_zone_bitmaps(struct request_queue *q); -#else -static inline void blk_queue_free_zone_bitmaps(struct request_queue *q) {} -#endif +void blk_zone_write_plug_finish_request(struct request *rq); +static inline void blk_zone_finish_request(struct request *rq) +{ + if (rq->rq_flags & RQF_ZONE_WRITE_PLUGGING) + blk_zone_write_plug_finish_request(rq); +} +int blkdev_report_zones_ioctl(struct block_device *bdev, unsigned int cmd, + unsigned long arg); +int blkdev_zone_mgmt_ioctl(struct block_device *bdev, blk_mode_t mode, + unsigned int cmd, unsigned long arg); +#else /* CONFIG_BLK_DEV_ZONED */ +static inline void disk_init_zone_resources(struct gendisk *disk) +{ +} +static inline void disk_free_zone_resources(struct gendisk *disk) +{ +} +static inline bool bio_zone_write_plugging(struct bio *bio) +{ + return false; +} +static inline bool blk_req_bio_is_zone_append(struct request *req, + struct bio *bio) +{ + return false; +} +static inline void blk_zone_write_plug_bio_merged(struct bio *bio) +{ +} +static inline void blk_zone_write_plug_init_request(struct request *rq) +{ +} +static inline void blk_zone_append_update_request_bio(struct request *rq, + struct bio *bio) +{ +} +static inline void blk_zone_bio_endio(struct bio *bio) +{ +} +static inline void blk_zone_finish_request(struct request *rq) +{ +} +static inline int blkdev_report_zones_ioctl(struct block_device *bdev, + unsigned int cmd, unsigned long arg) +{ + return -ENOTTY; +} +static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, + blk_mode_t mode, unsigned int cmd, unsigned long arg) +{ + return -ENOTTY; +} +#endif /* CONFIG_BLK_DEV_ZONED */ -struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector); +struct block_device *bdev_alloc(struct gendisk *disk, u8 partno); +void bdev_add(struct block_device *bdev, dev_t dev); +void bdev_unhash(struct block_device *bdev); +void bdev_drop(struct block_device *bdev); -int blk_alloc_devt(struct hd_struct *part, dev_t *devt); -void blk_free_devt(dev_t devt); -void blk_invalidate_devt(dev_t devt); -char *disk_name(struct gendisk *hd, int partno, char *buf); +int blk_alloc_ext_minor(void); +void blk_free_ext_minor(unsigned int minor); #define ADDPART_FLAG_NONE 0 #define ADDPART_FLAG_RAID 1 #define ADDPART_FLAG_WHOLEDISK 2 -void delete_partition(struct gendisk *disk, struct hd_struct *part); -int bdev_add_partition(struct block_device *bdev, int partno, - sector_t start, sector_t length); -int bdev_del_partition(struct block_device *bdev, int partno); -int bdev_resize_partition(struct block_device *bdev, int partno, - sector_t start, sector_t length); -int disk_expand_part_tbl(struct gendisk *disk, int target); -int hd_ref_init(struct hd_struct *part); +#define ADDPART_FLAG_READONLY 4 +int bdev_add_partition(struct gendisk *disk, int partno, sector_t start, + sector_t length); +int bdev_del_partition(struct gendisk *disk, int partno); +int bdev_resize_partition(struct gendisk *disk, int partno, sector_t start, + sector_t length); +void drop_partition(struct block_device *part); -/* no need to get/put refcount of part0 */ -static inline int hd_struct_try_get(struct hd_struct *part) -{ - if (part->partno) - return percpu_ref_tryget_live(&part->ref); - return 1; -} +void bdev_set_nr_sectors(struct block_device *bdev, sector_t sectors); -static inline void hd_struct_put(struct hd_struct *part) +struct gendisk *__alloc_disk_node(struct request_queue *q, int node_id, + struct lock_class_key *lkclass); + +/* + * Clean up a page appropriately, where the page may be pinned, may have a + * ref taken on it or neither. + */ +static inline void bio_release_page(struct bio *bio, struct page *page) { - if (part->partno) - percpu_ref_put(&part->ref); + if (bio_flagged(bio, BIO_PAGE_PINNED)) + unpin_user_page(page); } -static inline void hd_free_part(struct hd_struct *part) +struct request_queue *blk_alloc_queue(struct queue_limits *lim, int node_id); + +int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode); + +int disk_alloc_events(struct gendisk *disk); +void disk_add_events(struct gendisk *disk); +void disk_del_events(struct gendisk *disk); +void disk_release_events(struct gendisk *disk); +void disk_block_events(struct gendisk *disk); +void disk_unblock_events(struct gendisk *disk); +void disk_flush_events(struct gendisk *disk, unsigned int mask); +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; + +blk_mode_t file_to_blk_mode(struct file *file); +int truncate_bdev_range(struct block_device *bdev, blk_mode_t mode, + loff_t lstart, loff_t lend); +long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg); +int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags); +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); +void disk_unregister_independent_access_ranges(struct gendisk *disk); + +int should_fail_bio(struct bio *bio); +#ifdef CONFIG_FAIL_MAKE_REQUEST +bool should_fail_request(struct block_device *part, unsigned int bytes); +#else /* CONFIG_FAIL_MAKE_REQUEST */ +static inline bool should_fail_request(struct block_device *part, + unsigned int bytes) { - free_percpu(part->dkstats); - kfree(part->info); - percpu_ref_exit(&part->ref); + return false; } +#endif /* CONFIG_FAIL_MAKE_REQUEST */ /* - * Any access of part->nr_sects which is not protected by partition - * bd_mutex or gendisk bdev bd_mutex, should be done using this - * accessor function. + * Optimized request reference counting. Ideally we'd make timeouts be more + * clever, as that's the only reason we need references at all... But until + * this happens, this is faster than using refcount_t. Also see: * - * Code written along the lines of i_size_read() and i_size_write(). - * CONFIG_PREEMPTION case optimizes the case of UP kernel with preemption - * on. + * abc54d634334 ("io_uring: switch to atomic_t for io_kiocb reference count") */ -static inline sector_t part_nr_sects_read(struct hd_struct *part) -{ -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - sector_t nr_sects; - unsigned seq; - do { - seq = read_seqcount_begin(&part->nr_sects_seq); - nr_sects = part->nr_sects; - } while (read_seqcount_retry(&part->nr_sects_seq, seq)); - return nr_sects; -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) - sector_t nr_sects; - - preempt_disable(); - nr_sects = part->nr_sects; - preempt_enable(); - return nr_sects; -#else - return part->nr_sects; -#endif +#define req_ref_zero_or_close_to_overflow(req) \ + ((unsigned int) atomic_read(&(req->ref)) + 127u <= 127u) + +static inline bool req_ref_inc_not_zero(struct request *req) +{ + return atomic_inc_not_zero(&req->ref); } -/* - * Should be called with mutex lock held (typically bd_mutex) of partition - * to provide mutual exlusion among writers otherwise seqcount might be - * left in wrong state leaving the readers spinning infinitely. - */ -static inline void part_nr_sects_write(struct hd_struct *part, sector_t size) -{ -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - preempt_disable(); - write_seqcount_begin(&part->nr_sects_seq); - part->nr_sects = size; - write_seqcount_end(&part->nr_sects_seq); - preempt_enable(); -#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION) - preempt_disable(); - part->nr_sects = size; - preempt_enable(); -#else - part->nr_sects = size; -#endif +static inline bool req_ref_put_and_test(struct request *req) +{ + WARN_ON_ONCE(req_ref_zero_or_close_to_overflow(req)); + return atomic_dec_and_test(&req->ref); } -struct request_queue *__blk_alloc_queue(int node_id); +static inline void req_ref_set(struct request *req, int value) +{ + atomic_set(&req->ref, value); +} -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); +static inline int req_ref_read(struct request *req) +{ + return atomic_read(&req->ref); +} + +static inline u64 blk_time_get_ns(void) +{ + struct blk_plug *plug = current->plug; + + if (!plug || !in_task()) + return ktime_get_ns(); + + /* + * 0 could very well be a valid time, but rather than flag "this is + * a valid timestamp" separately, just accept that we'll do an extra + * ktime_get_ns() if we just happen to get 0 as the current time. + */ + if (!plug->cur_ktime) { + plug->cur_ktime = ktime_get_ns(); + current->flags |= PF_BLOCK_TS; + } + return plug->cur_ktime; +} + +static inline ktime_t blk_time_get(void) +{ + return ns_to_ktime(blk_time_get_ns()); +} + +void bdev_release(struct file *bdev_file); +int bdev_open(struct block_device *bdev, blk_mode_t mode, void *holder, + const struct blk_holder_ops *hops, struct file *bdev_file); +int bdev_permission(dev_t dev, blk_mode_t mode, void *holder); + +void blk_integrity_generate(struct bio *bio); +void blk_integrity_verify_iter(struct bio *bio, struct bvec_iter *saved_iter); +void blk_integrity_prepare(struct request *rq); +void blk_integrity_complete(struct request *rq, unsigned int nr_bytes); + +#ifdef CONFIG_LOCKDEP +static inline void blk_freeze_acquire_lock(struct request_queue *q) +{ + if (!q->mq_freeze_disk_dead) + rwsem_acquire(&q->io_lockdep_map, 0, 1, _RET_IP_); + if (!q->mq_freeze_queue_dying) + rwsem_acquire(&q->q_lockdep_map, 0, 1, _RET_IP_); +} + +static inline void blk_unfreeze_release_lock(struct request_queue *q) +{ + if (!q->mq_freeze_queue_dying) + rwsem_release(&q->q_lockdep_map, _RET_IP_); + if (!q->mq_freeze_disk_dead) + rwsem_release(&q->io_lockdep_map, _RET_IP_); +} +#else +static inline void blk_freeze_acquire_lock(struct request_queue *q) +{ +} +static inline void blk_unfreeze_release_lock(struct request_queue *q) +{ +} +#endif #endif /* BLK_INTERNAL_H */ |