diff options
Diffstat (limited to 'include/linux/blkdev.h')
| -rw-r--r-- | include/linux/blkdev.h | 717 |
1 files changed, 560 insertions, 157 deletions
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index aae86fd10c4..8699bcf5f09 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1,12 +1,14 @@ #ifndef _LINUX_BLKDEV_H #define _LINUX_BLKDEV_H +#include <linux/sched.h> + #ifdef CONFIG_BLOCK -#include <linux/sched.h> #include <linux/major.h> #include <linux/genhd.h> #include <linux/list.h> +#include <linux/llist.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/pagemap.h> @@ -14,14 +16,15 @@ #include <linux/wait.h> #include <linux/mempool.h> #include <linux/bio.h> -#include <linux/module.h> #include <linux/stringify.h> #include <linux/gfp.h> #include <linux/bsg.h> #include <linux/smp.h> +#include <linux/rcupdate.h> #include <asm/scatterlist.h> +struct module; struct scsi_ioctl_command; struct request_queue; @@ -30,23 +33,38 @@ struct request_pm_state; struct blk_trace; struct request; struct sg_io_hdr; +struct bsg_job; +struct blkcg_gq; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ +/* + * Maximum number of blkcg policies allowed to be registered concurrently. + * Defined here to simplify include dependency. + */ +#define BLKCG_MAX_POLS 2 + struct request; typedef void (rq_end_io_fn)(struct request *, int); +#define BLK_RL_SYNCFULL (1U << 0) +#define BLK_RL_ASYNCFULL (1U << 1) + struct request_list { + struct request_queue *q; /* the queue this rl belongs to */ +#ifdef CONFIG_BLK_CGROUP + struct blkcg_gq *blkg; /* blkg this request pool belongs to */ +#endif /* * count[], starved[], and wait[] are indexed by * BLK_RW_SYNC/BLK_RW_ASYNC */ - int count[2]; - int starved[2]; - int elvpriv; - mempool_t *rq_pool; - wait_queue_head_t wait[2]; + int count[2]; + int starved[2]; + mempool_t *rq_pool; + wait_queue_head_t wait[2]; + unsigned int flags; }; /* @@ -72,17 +90,22 @@ enum rq_cmd_type_bits { #define BLK_MAX_CDB 16 /* - * try to put the fields that are referenced together in the same cacheline. - * if you modify this structure, be sure to check block/blk-core.c:rq_init() - * as well! + * Try to put the fields that are referenced together in the same cacheline. + * + * If you modify this structure, make sure to update blk_rq_init() and + * especially blk_mq_rq_ctx_init() to take care of the added fields. */ struct request { struct list_head queuelist; - struct call_single_data csd; + union { + struct call_single_data csd; + unsigned long fifo_time; + }; struct request_queue *q; + struct blk_mq_ctx *mq_ctx; - unsigned int cmd_flags; + u64 cmd_flags; enum rq_cmd_type_bits cmd_type; unsigned long atomic_flags; @@ -95,7 +118,18 @@ struct request { struct bio *bio; struct bio *biotail; - struct hlist_node hash; /* merge hash */ + /* + * The hash is used inside the scheduler, and killed once the + * request reaches the dispatch list. The ipi_list is only used + * to queue the request for softirq completion, which is long + * after the request has been unhashed (and even removed from + * the dispatch list). + */ + union { + struct hlist_node hash; /* merge hash */ + struct list_head ipi_list; + }; + /* * The rb_node is only used inside the io scheduler, requests * are pruned when moved to the dispatch queue. So let the @@ -108,15 +142,28 @@ struct request { /* * Three pointers are available for the IO schedulers, if they need - * more they have to dynamically allocate it. + * more they have to dynamically allocate it. Flush requests are + * never put on the IO scheduler. So let the flush fields share + * space with the elevator data. */ - void *elevator_private; - void *elevator_private2; - void *elevator_private3; + union { + struct { + struct io_cq *icq; + void *priv[2]; + } elv; + + struct { + unsigned int seq; + struct list_head list; + rq_end_io_fn *saved_end_io; + } flush; + }; struct gendisk *rq_disk; + struct hd_struct *part; unsigned long start_time; #ifdef CONFIG_BLK_CGROUP + struct request_list *rl; /* rl this rq is alloced from */ unsigned long long start_time_ns; unsigned long long io_start_time_ns; /* when passed to hardware */ #endif @@ -130,10 +177,7 @@ struct request { unsigned short ioprio; - int ref_count; - void *special; /* opaque pointer available for LLD use */ - char *buffer; /* kaddr of the current segment if available */ int tag; int errors; @@ -185,11 +229,12 @@ struct request_pm_state #include <linux/elevator.h> +struct blk_queue_ctx; + typedef void (request_fn_proc) (struct request_queue *q); -typedef int (make_request_fn) (struct request_queue *q, struct bio *bio); +typedef void (make_request_fn) (struct request_queue *q, struct bio *bio); typedef int (prep_rq_fn) (struct request_queue *, struct request *); typedef void (unprep_rq_fn) (struct request_queue *, struct request *); -typedef void (unplug_fn) (struct request_queue *); struct bio_vec; struct bvec_merge_data { @@ -203,6 +248,7 @@ typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *, typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); typedef int (lld_busy_fn) (struct request_queue *q); +typedef int (bsg_job_fn) (struct bsg_job *); enum blk_eh_timer_return { BLK_EH_NOT_HANDLED, @@ -234,6 +280,7 @@ struct queue_limits { unsigned long seg_boundary_mask; unsigned int max_hw_sectors; + unsigned int chunk_sectors; unsigned int max_sectors; unsigned int max_segment_size; unsigned int physical_block_size; @@ -241,6 +288,7 @@ struct queue_limits { unsigned int io_min; unsigned int io_opt; unsigned int max_discard_sectors; + unsigned int max_write_same_sectors; unsigned int discard_granularity; unsigned int discard_alignment; @@ -250,35 +298,51 @@ struct queue_limits { unsigned char misaligned; unsigned char discard_misaligned; - unsigned char no_cluster; - signed char discard_zeroes_data; + unsigned char cluster; + unsigned char discard_zeroes_data; + unsigned char raid_partial_stripes_expensive; }; -struct request_queue -{ +struct request_queue { /* * Together with queue_head for cacheline sharing */ struct list_head queue_head; struct request *last_merge; struct elevator_queue *elevator; + int nr_rqs[2]; /* # allocated [a]sync rqs */ + int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ /* - * the queue request freelist, one for reads and one for writes + * If blkcg is not used, @q->root_rl serves all requests. If blkcg + * is used, root blkg allocates from @q->root_rl and all other + * blkgs from their own blkg->rl. Which one to use should be + * determined using bio_request_list(). */ - struct request_list rq; + struct request_list root_rl; request_fn_proc *request_fn; make_request_fn *make_request_fn; prep_rq_fn *prep_rq_fn; unprep_rq_fn *unprep_rq_fn; - unplug_fn *unplug_fn; merge_bvec_fn *merge_bvec_fn; softirq_done_fn *softirq_done_fn; rq_timed_out_fn *rq_timed_out_fn; dma_drain_needed_fn *dma_drain_needed; lld_busy_fn *lld_busy_fn; + struct blk_mq_ops *mq_ops; + + unsigned int *mq_map; + + /* sw queues */ + struct blk_mq_ctx __percpu *queue_ctx; + unsigned int nr_queues; + + /* hw dispatch queues */ + struct blk_mq_hw_ctx **queue_hw_ctx; + unsigned int nr_hw_queues; + /* * Dispatch queue sorting */ @@ -286,12 +350,9 @@ struct request_queue struct request *boundary_rq; /* - * Auto-unplugging state + * Delayed queue handling */ - struct timer_list unplug_timer; - int unplug_thresh; /* After this many requests */ - unsigned long unplug_delay; /* After this many jiffies */ - struct work_struct unplug_work; + struct delayed_work delay_work; struct backing_dev_info backing_dev_info; @@ -302,14 +363,20 @@ struct request_queue void *queuedata; /* - * queue needs bounce pages for pages above this limit + * various queue flags, see QUEUE_* below */ - gfp_t bounce_gfp; + unsigned long queue_flags; /* - * various queue flags, see QUEUE_* below + * ida allocated id for this queue. Used to index queues from + * ioctx. */ - unsigned long queue_flags; + int id; + + /* + * queue needs bounce pages for pages above this limit + */ + gfp_t bounce_gfp; /* * protects queue structures from reentrancy. ->__queue_lock should @@ -325,6 +392,17 @@ struct request_queue struct kobject kobj; /* + * mq queue kobject + */ + struct kobject mq_kobj; + +#ifdef CONFIG_PM_RUNTIME + struct device *dev; + int rpm_status; + unsigned int nr_pending; +#endif + + /* * queue settings */ unsigned long nr_requests; /* Max # of requests */ @@ -332,8 +410,8 @@ struct request_queue unsigned int nr_congestion_off; unsigned int nr_batching; - void *dma_drain_buffer; unsigned int dma_drain_size; + void *dma_drain_buffer; unsigned int dma_pad_mask; unsigned int dma_alignment; @@ -342,11 +420,24 @@ struct request_queue unsigned int nr_sorted; unsigned int in_flight[2]; + /* + * Number of active block driver functions for which blk_drain_queue() + * must wait. Must be incremented around functions that unlock the + * queue_lock internally, e.g. scsi_request_fn(). + */ + unsigned int request_fn_active; unsigned int rq_timeout; struct timer_list timeout; struct list_head timeout_list; + struct list_head icq_list; +#ifdef CONFIG_BLK_CGROUP + DECLARE_BITMAP (blkcg_pols, BLKCG_MAX_POLS); + struct blkcg_gq *root_blkg; + struct list_head blkg_list; +#endif + struct queue_limits limits; /* @@ -362,15 +453,27 @@ struct request_queue * for flush operations */ unsigned int flush_flags; - unsigned int flush_seq; - int flush_err; - struct request flush_rq; - struct request *orig_flush_rq; - struct list_head pending_flushes; + unsigned int flush_not_queueable:1; + unsigned int flush_queue_delayed:1; + unsigned int flush_pending_idx:1; + unsigned int flush_running_idx:1; + unsigned long flush_pending_since; + struct list_head flush_queue[2]; + struct list_head flush_data_in_flight; + struct request *flush_rq; + spinlock_t mq_flush_lock; + + struct list_head requeue_list; + spinlock_t requeue_lock; + struct work_struct requeue_work; struct mutex sysfs_lock; + int bypass_depth; + #if defined(CONFIG_BLK_DEV_BSG) + bsg_job_fn *bsg_job_fn; + int bsg_job_size; struct bsg_class_device bsg_dev; #endif @@ -378,44 +481,51 @@ struct request_queue /* Throttle data */ struct throtl_data *td; #endif + struct rcu_head rcu_head; + wait_queue_head_t mq_freeze_wq; + struct percpu_counter mq_usage_counter; + struct list_head all_q_node; + + struct blk_mq_tag_set *tag_set; + struct list_head tag_set_list; }; -#define QUEUE_FLAG_CLUSTER 0 /* cluster several segments into 1 */ #define QUEUE_FLAG_QUEUED 1 /* uses generic tag queueing */ #define QUEUE_FLAG_STOPPED 2 /* queue is stopped */ #define QUEUE_FLAG_SYNCFULL 3 /* read queue has been filled */ #define QUEUE_FLAG_ASYNCFULL 4 /* write queue has been filled */ -#define QUEUE_FLAG_DEAD 5 /* queue being torn down */ -#define QUEUE_FLAG_REENTER 6 /* Re-entrancy avoidance */ -#define QUEUE_FLAG_PLUGGED 7 /* queue is plugged */ -#define QUEUE_FLAG_ELVSWITCH 8 /* don't use elevator, just do FIFO */ -#define QUEUE_FLAG_BIDI 9 /* queue supports bidi requests */ -#define QUEUE_FLAG_NOMERGES 10 /* disable merge attempts */ -#define QUEUE_FLAG_SAME_COMP 11 /* force complete on same CPU */ -#define QUEUE_FLAG_FAIL_IO 12 /* fake timeout */ -#define QUEUE_FLAG_STACKABLE 13 /* supports request stacking */ -#define QUEUE_FLAG_NONROT 14 /* non-rotational device (SSD) */ +#define QUEUE_FLAG_DYING 5 /* queue being torn down */ +#define QUEUE_FLAG_BYPASS 6 /* act as dumb FIFO queue */ +#define QUEUE_FLAG_BIDI 7 /* queue supports bidi requests */ +#define QUEUE_FLAG_NOMERGES 8 /* disable merge attempts */ +#define QUEUE_FLAG_SAME_COMP 9 /* complete on same CPU-group */ +#define QUEUE_FLAG_FAIL_IO 10 /* fake timeout */ +#define QUEUE_FLAG_STACKABLE 11 /* supports request stacking */ +#define QUEUE_FLAG_NONROT 12 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ -#define QUEUE_FLAG_IO_STAT 15 /* do IO stats */ -#define QUEUE_FLAG_DISCARD 16 /* supports DISCARD */ -#define QUEUE_FLAG_NOXMERGES 17 /* No extended merges */ -#define QUEUE_FLAG_ADD_RANDOM 18 /* Contributes to random pool */ -#define QUEUE_FLAG_SECDISCARD 19 /* supports SECDISCARD */ +#define QUEUE_FLAG_IO_STAT 13 /* do IO stats */ +#define QUEUE_FLAG_DISCARD 14 /* supports DISCARD */ +#define QUEUE_FLAG_NOXMERGES 15 /* No extended merges */ +#define QUEUE_FLAG_ADD_RANDOM 16 /* Contributes to random pool */ +#define QUEUE_FLAG_SECDISCARD 17 /* supports SECDISCARD */ +#define QUEUE_FLAG_SAME_FORCE 18 /* force complete on same CPU */ +#define QUEUE_FLAG_DEAD 19 /* queue tear-down finished */ +#define QUEUE_FLAG_INIT_DONE 20 /* queue is initialized */ +#define QUEUE_FLAG_NO_SG_MERGE 21 /* don't attempt to merge SG segments*/ +#define QUEUE_FLAG_SG_GAPS 22 /* queue doesn't support SG gaps */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ - (1 << QUEUE_FLAG_CLUSTER) | \ (1 << QUEUE_FLAG_STACKABLE) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ (1 << QUEUE_FLAG_ADD_RANDOM)) -static inline int queue_is_locked(struct request_queue *q) +#define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ + (1 << QUEUE_FLAG_SAME_COMP)) + +static inline void queue_lockdep_assert_held(struct request_queue *q) { -#ifdef CONFIG_SMP - spinlock_t *lock = q->queue_lock; - return lock && spin_is_locked(lock); -#else - return 1; -#endif + if (q->queue_lock) + lockdep_assert_held(q->queue_lock); } static inline void queue_flag_set_unlocked(unsigned int flag, @@ -427,7 +537,7 @@ static inline void queue_flag_set_unlocked(unsigned int flag, static inline int queue_flag_test_and_clear(unsigned int flag, struct request_queue *q) { - WARN_ON_ONCE(!queue_is_locked(q)); + queue_lockdep_assert_held(q); if (test_bit(flag, &q->queue_flags)) { __clear_bit(flag, &q->queue_flags); @@ -440,7 +550,7 @@ static inline int queue_flag_test_and_clear(unsigned int flag, static inline int queue_flag_test_and_set(unsigned int flag, struct request_queue *q) { - WARN_ON_ONCE(!queue_is_locked(q)); + queue_lockdep_assert_held(q); if (!test_bit(flag, &q->queue_flags)) { __set_bit(flag, &q->queue_flags); @@ -452,7 +562,7 @@ static inline int queue_flag_test_and_set(unsigned int flag, static inline void queue_flag_set(unsigned int flag, struct request_queue *q) { - WARN_ON_ONCE(!queue_is_locked(q)); + queue_lockdep_assert_held(q); __set_bit(flag, &q->queue_flags); } @@ -469,13 +579,16 @@ static inline int queue_in_flight(struct request_queue *q) static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) { - WARN_ON_ONCE(!queue_is_locked(q)); + queue_lockdep_assert_held(q); __clear_bit(flag, &q->queue_flags); } -#define blk_queue_plugged(q) test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags) #define blk_queue_tagged(q) test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags) #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) +#define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) +#define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(q)->queue_flags) +#define blk_queue_bypass(q) test_bit(QUEUE_FLAG_BYPASS, &(q)->queue_flags) +#define blk_queue_init_done(q) test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags) #define blk_queue_nomerges(q) test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags) #define blk_queue_noxmerges(q) \ test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags) @@ -494,8 +607,7 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define blk_account_rq(rq) \ (((rq)->cmd_flags & REQ_STARTED) && \ - ((rq)->cmd_type == REQ_TYPE_FS || \ - ((rq)->cmd_flags & REQ_DISCARD))) + ((rq)->cmd_type == REQ_TYPE_FS)) #define blk_pm_request(rq) \ ((rq)->cmd_type == REQ_TYPE_PM_SUSPEND || \ @@ -508,7 +620,21 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) -#define rq_data_dir(rq) ((rq)->cmd_flags & 1) +#define rq_data_dir(rq) (((rq)->cmd_flags & 1) != 0) + +/* + * Driver can handle struct request, if it either has an old style + * request_fn defined, or is blk-mq based. + */ +static inline bool queue_is_rq_based(struct request_queue *q) +{ + return q->request_fn || q->mq_ops; +} + +static inline unsigned int blk_queue_cluster(struct request_queue *q) +{ + return q->limits.cluster; +} /* * We regard a request as sync, if either a read or a sync write @@ -523,40 +649,60 @@ static inline bool rq_is_sync(struct request *rq) return rw_is_sync(rq->cmd_flags); } -static inline int blk_queue_full(struct request_queue *q, int sync) +static inline bool blk_rl_full(struct request_list *rl, bool sync) { - if (sync) - return test_bit(QUEUE_FLAG_SYNCFULL, &q->queue_flags); - return test_bit(QUEUE_FLAG_ASYNCFULL, &q->queue_flags); + unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; + + return rl->flags & flag; } -static inline void blk_set_queue_full(struct request_queue *q, int sync) +static inline void blk_set_rl_full(struct request_list *rl, bool sync) { - if (sync) - queue_flag_set(QUEUE_FLAG_SYNCFULL, q); - else - queue_flag_set(QUEUE_FLAG_ASYNCFULL, q); + unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; + + rl->flags |= flag; } -static inline void blk_clear_queue_full(struct request_queue *q, int sync) +static inline void blk_clear_rl_full(struct request_list *rl, bool sync) { - if (sync) - queue_flag_clear(QUEUE_FLAG_SYNCFULL, q); - else - queue_flag_clear(QUEUE_FLAG_ASYNCFULL, q); + unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; + + rl->flags &= ~flag; } +static inline bool rq_mergeable(struct request *rq) +{ + if (rq->cmd_type != REQ_TYPE_FS) + return false; -/* - * mergeable request must not have _NOMERGE or _BARRIER bit set, nor may - * it already be started by driver. - */ -#define RQ_NOMERGE_FLAGS \ - (REQ_NOMERGE | REQ_STARTED | REQ_SOFTBARRIER | REQ_FLUSH | REQ_FUA) -#define rq_mergeable(rq) \ - (!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && \ - (((rq)->cmd_flags & REQ_DISCARD) || \ - (rq)->cmd_type == REQ_TYPE_FS)) + if (rq->cmd_flags & REQ_NOMERGE_FLAGS) + return false; + + return true; +} + +static inline bool blk_check_merge_flags(unsigned int flags1, + unsigned int flags2) +{ + if ((flags1 & REQ_DISCARD) != (flags2 & REQ_DISCARD)) + return false; + + if ((flags1 & REQ_SECURE) != (flags2 & REQ_SECURE)) + return false; + + if ((flags1 & REQ_WRITE_SAME) != (flags2 & REQ_WRITE_SAME)) + return false; + + return true; +} + +static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b) +{ + if (bio_data(a) == bio_data(b)) + return true; + + return false; +} /* * q->prep_rq_fn return values @@ -612,7 +758,7 @@ struct rq_map_data { }; struct req_iterator { - int i; + struct bvec_iter iter; struct bio *bio; }; @@ -625,10 +771,11 @@ struct req_iterator { #define rq_for_each_segment(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ - bio_for_each_segment(bvl, _iter.bio, _iter.i) + bio_for_each_segment(bvl, _iter.bio, _iter.iter) -#define rq_iter_last(rq, _iter) \ - (_iter.bio->bi_next == NULL && _iter.i == _iter.bio->bi_vcnt-1) +#define rq_iter_last(bvec, _iter) \ + (_iter.bio->bi_next == NULL && \ + bio_iter_last(bvec, _iter.iter)) #ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE # error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" @@ -643,7 +790,6 @@ static inline void rq_flush_dcache_pages(struct request *rq) extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); -extern void register_disk(struct gendisk *dev); extern void generic_make_request(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); @@ -651,7 +797,7 @@ extern void __blk_put_request(struct request_queue *, struct request *); extern struct request *blk_get_request(struct request_queue *, int, gfp_t); extern struct request *blk_make_request(struct request_queue *, struct bio *, gfp_t); -extern void blk_insert_request(struct request_queue *, struct request *, int, void *); +extern void blk_rq_set_block_pc(struct request *); extern void blk_requeue_request(struct request_queue *, struct request *); extern void blk_add_request_payload(struct request *rq, struct page *page, unsigned int len); @@ -664,15 +810,18 @@ extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, extern void blk_rq_unprep_clone(struct request *rq); extern int blk_insert_cloned_request(struct request_queue *q, struct request *rq); -extern void blk_plug_device(struct request_queue *); -extern void blk_plug_device_unlocked(struct request_queue *); -extern int blk_remove_plug(struct request_queue *); +extern void blk_delay_queue(struct request_queue *, unsigned long); extern void blk_recount_segments(struct request_queue *, struct bio *); +extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); +extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t, + unsigned int, void __user *); extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, unsigned int, void __user *); extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, struct scsi_ioctl_command __user *); +extern void blk_queue_bio(struct request_queue *q, struct bio *bio); + /* * A queue has just exitted congestion. Note this in the global counter of * congested queues, and wake up anyone who was waiting for requests to be @@ -696,21 +845,21 @@ extern void blk_start_queue(struct request_queue *q); extern void blk_stop_queue(struct request_queue *q); extern void blk_sync_queue(struct request_queue *q); extern void __blk_stop_queue(struct request_queue *q); -extern void __blk_run_queue(struct request_queue *); +extern void __blk_run_queue(struct request_queue *q); extern void blk_run_queue(struct request_queue *); +extern void blk_run_queue_async(struct request_queue *q); extern int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); extern int blk_rq_unmap_user(struct bio *); extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t); extern int blk_rq_map_user_iov(struct request_queue *, struct request *, - struct rq_map_data *, struct sg_iovec *, int, - unsigned int, gfp_t); + struct rq_map_data *, const struct sg_iovec *, + int, unsigned int, gfp_t); extern int blk_execute_rq(struct request_queue *, struct gendisk *, struct request *, int); extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, struct request *, int, rq_end_io_fn *); -extern void blk_unplug(struct request_queue *q); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { @@ -752,6 +901,57 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) return blk_rq_cur_bytes(rq) >> 9; } +static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, + unsigned int cmd_flags) +{ + if (unlikely(cmd_flags & REQ_DISCARD)) + return min(q->limits.max_discard_sectors, UINT_MAX >> 9); + + if (unlikely(cmd_flags & REQ_WRITE_SAME)) + return q->limits.max_write_same_sectors; + + return q->limits.max_sectors; +} + +/* + * Return maximum size of a request at given offset. Only valid for + * file system requests. + */ +static inline unsigned int blk_max_size_offset(struct request_queue *q, + sector_t offset) +{ + if (!q->limits.chunk_sectors) + return q->limits.max_sectors; + + return q->limits.chunk_sectors - + (offset & (q->limits.chunk_sectors - 1)); +} + +static inline unsigned int blk_rq_get_max_sectors(struct request *rq) +{ + struct request_queue *q = rq->q; + + if (unlikely(rq->cmd_type == REQ_TYPE_BLOCK_PC)) + return q->limits.max_hw_sectors; + + if (!q->limits.chunk_sectors) + return blk_queue_get_max_sectors(q, rq->cmd_flags); + + return min(blk_max_size_offset(q, blk_rq_pos(rq)), + blk_queue_get_max_sectors(q, rq->cmd_flags)); +} + +static inline unsigned int blk_rq_count_bios(struct request *rq) +{ + unsigned int nr_bios = 0; + struct bio *bio; + + __rq_for_each_bio(bio, rq) + nr_bios++; + + return nr_bios; +} + /* * Request issue related functions. */ @@ -774,6 +974,7 @@ extern struct request *blk_fetch_request(struct request_queue *q); */ extern bool blk_update_request(struct request *rq, int error, unsigned int nr_bytes); +extern void blk_finish_request(struct request *rq, int error); extern bool blk_end_request(struct request *rq, int error, unsigned int nr_bytes); extern void blk_end_request_all(struct request *rq, int error); @@ -788,7 +989,6 @@ extern bool __blk_end_request_err(struct request *rq, int error); extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); -extern void blk_abort_queue(struct request_queue *); extern void blk_unprep_request(struct request *); /* @@ -796,20 +996,21 @@ extern void blk_unprep_request(struct request *); */ extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id); -extern struct request_queue *blk_init_allocated_queue_node(struct request_queue *, - request_fn_proc *, - spinlock_t *, int node_id); extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *); extern struct request_queue *blk_init_allocated_queue(struct request_queue *, request_fn_proc *, spinlock_t *); extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); +extern void blk_limits_max_hw_sectors(struct queue_limits *, unsigned int); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); +extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); +extern void blk_queue_max_write_same_sectors(struct request_queue *q, + unsigned int max_write_same_sectors); extern void blk_queue_logical_block_size(struct request_queue *, unsigned short); extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); extern void blk_queue_alignment_offset(struct request_queue *q, @@ -819,6 +1020,7 @@ extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); extern void blk_set_default_limits(struct queue_limits *lim); +extern void blk_set_stacking_limits(struct queue_limits *lim); extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b, sector_t offset); extern int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev, @@ -842,22 +1044,104 @@ extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_flush(struct request_queue *q, unsigned int flush); +extern void blk_queue_flush_queueable(struct request_queue *q, bool queueable); extern struct backing_dev_info *blk_get_backing_dev_info(struct block_device *bdev); extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *); +extern int blk_bio_map_sg(struct request_queue *q, struct bio *bio, + struct scatterlist *sglist); extern void blk_dump_rq_flags(struct request *, char *); -extern void generic_unplug_device(struct request_queue *); extern long nr_blockdev_pages(void); -int blk_get_queue(struct request_queue *); +bool __must_check blk_get_queue(struct request_queue *); struct request_queue *blk_alloc_queue(gfp_t); struct request_queue *blk_alloc_queue_node(gfp_t, int); extern void blk_put_queue(struct request_queue *); /* + * block layer runtime pm functions + */ +#ifdef CONFIG_PM_RUNTIME +extern void blk_pm_runtime_init(struct request_queue *q, struct device *dev); +extern int blk_pre_runtime_suspend(struct request_queue *q); +extern void blk_post_runtime_suspend(struct request_queue *q, int err); +extern void blk_pre_runtime_resume(struct request_queue *q); +extern void blk_post_runtime_resume(struct request_queue *q, int err); +#else +static inline void blk_pm_runtime_init(struct request_queue *q, + struct device *dev) {} +static inline int blk_pre_runtime_suspend(struct request_queue *q) +{ + return -ENOSYS; +} +static inline void blk_post_runtime_suspend(struct request_queue *q, int err) {} +static inline void blk_pre_runtime_resume(struct request_queue *q) {} +static inline void blk_post_runtime_resume(struct request_queue *q, int err) {} +#endif + +/* + * blk_plug permits building a queue of related requests by holding the I/O + * fragments for a short period. This allows merging of sequential requests + * into single larger request. As the requests are moved from a per-task list to + * the device's request_queue in a batch, this results in improved scalability + * as the lock contention for request_queue lock is reduced. + * + * It is ok not to disable preemption when adding the request to the plug list + * or when attempting a merge, because blk_schedule_flush_list() will only flush + * the plug list when the task sleeps by itself. For details, please see + * schedule() where blk_schedule_flush_plug() is called. + */ +struct blk_plug { + struct list_head list; /* requests */ + struct list_head mq_list; /* blk-mq requests */ + struct list_head cb_list; /* md requires an unplug callback */ +}; +#define BLK_MAX_REQUEST_COUNT 16 + +struct blk_plug_cb; +typedef void (*blk_plug_cb_fn)(struct blk_plug_cb *, bool); +struct blk_plug_cb { + struct list_head list; + blk_plug_cb_fn callback; + void *data; +}; +extern struct blk_plug_cb *blk_check_plugged(blk_plug_cb_fn unplug, + void *data, int size); +extern void blk_start_plug(struct blk_plug *); +extern void blk_finish_plug(struct blk_plug *); +extern void blk_flush_plug_list(struct blk_plug *, bool); + +static inline void blk_flush_plug(struct task_struct *tsk) +{ + struct blk_plug *plug = tsk->plug; + + if (plug) + blk_flush_plug_list(plug, false); +} + +static inline void blk_schedule_flush_plug(struct task_struct *tsk) +{ + struct blk_plug *plug = tsk->plug; + + if (plug) + blk_flush_plug_list(plug, true); +} + +static inline bool blk_needs_flush_plug(struct task_struct *tsk) +{ + struct blk_plug *plug = tsk->plug; + + return plug && + (!list_empty(&plug->list) || + !list_empty(&plug->mq_list) || + !list_empty(&plug->cb_list)); +} + +/* * tag stuff */ -#define blk_rq_tagged(rq) ((rq)->cmd_flags & REQ_QUEUED) +#define blk_rq_tagged(rq) \ + ((rq)->mq_ctx || ((rq)->cmd_flags & REQ_QUEUED)) extern int blk_queue_start_tag(struct request_queue *, struct request *); extern struct request *blk_queue_find_tag(struct request_queue *, int); extern void blk_queue_end_tag(struct request_queue *, struct request *); @@ -881,6 +1165,8 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); +extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, struct page *page); extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask); static inline int sb_issue_discard(struct super_block *sb, sector_t block, @@ -1026,15 +1312,40 @@ static inline int queue_discard_alignment(struct request_queue *q) static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) { - unsigned int alignment = (sector << 9) & (lim->discard_granularity - 1); + unsigned int alignment, granularity, offset; + + if (!lim->max_discard_sectors) + return 0; + + /* Why are these in bytes, not sectors? */ + alignment = lim->discard_alignment >> 9; + granularity = lim->discard_granularity >> 9; + if (!granularity) + return 0; - return (lim->discard_granularity + lim->discard_alignment - alignment) - & (lim->discard_granularity - 1); + /* Offset of the partition start in 'granularity' sectors */ + offset = sector_div(sector, granularity); + + /* And why do we do this modulus *again* in blkdev_issue_discard()? */ + offset = (granularity + alignment - offset) % granularity; + + /* Turn it back into bytes, gaah */ + return offset << 9; +} + +static inline int bdev_discard_alignment(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (bdev != bdev->bd_contains) + return bdev->bd_part->discard_alignment; + + return q->limits.discard_alignment; } static inline unsigned int queue_discard_zeroes_data(struct request_queue *q) { - if (q->limits.discard_zeroes_data == 1) + if (q->limits.max_discard_sectors && q->limits.discard_zeroes_data == 1) return 1; return 0; @@ -1045,6 +1356,16 @@ static inline unsigned int bdev_discard_zeroes_data(struct block_device *bdev) return queue_discard_zeroes_data(bdev_get_queue(bdev)); } +static inline unsigned int bdev_write_same(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q) + return q->limits.max_write_same_sectors; + + return 0; +} + static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; @@ -1073,6 +1394,11 @@ static inline unsigned int block_size(struct block_device *bdev) return bdev->bd_block_size; } +static inline bool queue_flush_queueable(struct request_queue *q) +{ + return !q->flush_not_queueable; +} + typedef struct {struct page *v;} Sector; unsigned char *read_dev_sector(struct block_device *, sector_t, Sector *); @@ -1083,8 +1409,9 @@ static inline void put_dev_sector(Sector p) } struct work_struct; -int kblockd_schedule_work(struct request_queue *q, struct work_struct *work); -int kblockd_schedule_delayed_work(struct request_queue *q, struct delayed_work *dwork, unsigned long delay); +int kblockd_schedule_work(struct work_struct *work); +int kblockd_schedule_delayed_work(struct delayed_work *dwork, unsigned long delay); +int kblockd_schedule_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); #ifdef CONFIG_BLK_CGROUP /* @@ -1128,24 +1455,6 @@ static inline uint64_t rq_io_start_time_ns(struct request *req) } #endif -#ifdef CONFIG_BLK_DEV_THROTTLING -extern int blk_throtl_init(struct request_queue *q); -extern void blk_throtl_exit(struct request_queue *q); -extern int blk_throtl_bio(struct request_queue *q, struct bio **bio); -extern void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay); -extern void throtl_shutdown_timer_wq(struct request_queue *q); -#else /* CONFIG_BLK_DEV_THROTTLING */ -static inline int blk_throtl_bio(struct request_queue *q, struct bio **bio) -{ - return 0; -} - -static inline int blk_throtl_init(struct request_queue *q) { return 0; } -static inline int blk_throtl_exit(struct request_queue *q) { return 0; } -static inline void throtl_schedule_delayed_work(struct request_queue *q, unsigned long delay) {} -static inline void throtl_shutdown_timer_wq(struct request_queue *q) {} -#endif /* CONFIG_BLK_DEV_THROTTLING */ - #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ @@ -1186,6 +1495,7 @@ struct blk_integrity { struct kobject kobj; }; +extern bool blk_integrity_is_initialized(struct gendisk *); extern int blk_integrity_register(struct gendisk *, struct blk_integrity *); extern void blk_integrity_unregister(struct gendisk *); extern int blk_integrity_compare(struct gendisk *, struct gendisk *); @@ -1230,28 +1540,84 @@ queue_max_integrity_segments(struct request_queue *q) #else /* CONFIG_BLK_DEV_INTEGRITY */ -#define blk_integrity_rq(rq) (0) -#define blk_rq_count_integrity_sg(a, b) (0) -#define blk_rq_map_integrity_sg(a, b, c) (0) -#define bdev_get_integrity(a) (0) -#define blk_get_integrity(a) (0) -#define blk_integrity_compare(a, b) (0) -#define blk_integrity_register(a, b) (0) -#define blk_integrity_unregister(a) do { } while (0); -#define blk_queue_max_integrity_segments(a, b) do { } while (0); -#define queue_max_integrity_segments(a) (0) -#define blk_integrity_merge_rq(a, b, c) (0) -#define blk_integrity_merge_bio(a, b, c) (0) +struct bio; +struct block_device; +struct gendisk; +struct blk_integrity; + +static inline int blk_integrity_rq(struct request *rq) +{ + return 0; +} +static inline int blk_rq_count_integrity_sg(struct request_queue *q, + struct bio *b) +{ + return 0; +} +static inline int blk_rq_map_integrity_sg(struct request_queue *q, + struct bio *b, + struct scatterlist *s) +{ + return 0; +} +static inline struct blk_integrity *bdev_get_integrity(struct block_device *b) +{ + return 0; +} +static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) +{ + return NULL; +} +static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b) +{ + return 0; +} +static inline int blk_integrity_register(struct gendisk *d, + struct blk_integrity *b) +{ + return 0; +} +static inline void blk_integrity_unregister(struct gendisk *d) +{ +} +static inline void blk_queue_max_integrity_segments(struct request_queue *q, + unsigned int segs) +{ +} +static inline unsigned short queue_max_integrity_segments(struct request_queue *q) +{ + return 0; +} +static inline int blk_integrity_merge_rq(struct request_queue *rq, + struct request *r1, + struct request *r2) +{ + return 0; +} +static inline int blk_integrity_merge_bio(struct request_queue *rq, + struct request *r, + struct bio *b) +{ + return 0; +} +static inline bool blk_integrity_is_initialized(struct gendisk *g) +{ + return 0; +} #endif /* CONFIG_BLK_DEV_INTEGRITY */ struct block_device_operations { int (*open) (struct block_device *, fmode_t); - int (*release) (struct gendisk *, fmode_t); + void (*release) (struct gendisk *, fmode_t); + int (*rw_page)(struct block_device *, sector_t, struct page *, int rw); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*direct_access) (struct block_device *, sector_t, void **, unsigned long *); + unsigned int (*check_events) (struct gendisk *disk, + unsigned int clearing); + /* ->media_changed() is DEPRECATED, use ->check_events() instead */ int (*media_changed) (struct gendisk *); void (*unlock_native_capacity) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); @@ -1263,7 +1629,13 @@ struct block_device_operations { extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, unsigned long); +extern int bdev_read_page(struct block_device *, sector_t, struct page *); +extern int bdev_write_page(struct block_device *, sector_t, struct page *, + struct writeback_control *); #else /* CONFIG_BLOCK */ + +struct block_device; + /* * stubs for when the block layer is configured out */ @@ -1274,6 +1646,37 @@ static inline long nr_blockdev_pages(void) return 0; } +struct blk_plug { +}; + +static inline void blk_start_plug(struct blk_plug *plug) +{ +} + +static inline void blk_finish_plug(struct blk_plug *plug) +{ +} + +static inline void blk_flush_plug(struct task_struct *task) +{ +} + +static inline void blk_schedule_flush_plug(struct task_struct *task) +{ +} + + +static inline bool blk_needs_flush_plug(struct task_struct *tsk) +{ + return false; +} + +static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask, + sector_t *error_sector) +{ + return 0; +} + #endif /* CONFIG_BLOCK */ #endif |