diff options
Diffstat (limited to 'include/linux/blkdev.h')
| -rw-r--r-- | include/linux/blkdev.h | 1509 |
1 files changed, 1172 insertions, 337 deletions
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6f79d40dd3c..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> @@ -14,41 +16,55 @@ #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; -typedef struct request_queue request_queue_t __deprecated; struct elevator_queue; -typedef struct elevator_queue elevator_t; 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 */ -int put_io_context(struct io_context *ioc); -void exit_io_context(void); -struct io_context *get_io_context(gfp_t gfp_flags, int node); -struct io_context *alloc_io_context(gfp_t gfp_flags, int node); -void copy_io_context(struct io_context **pdst, struct io_context **psrc); +/* + * 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 { - int count[2]; - int starved[2]; - int elvpriv; - mempool_t *rq_pool; - wait_queue_head_t wait[2]; + struct request_queue *q; /* the queue this rl belongs to */ +#ifdef CONFIG_BLK_CGROUP + struct blkcg_gq *blkg; /* blkg this request pool belongs to */ +#endif + /* + * count[], starved[], and wait[] are indexed by + * BLK_RW_SYNC/BLK_RW_ASYNC + */ + int count[2]; + int starved[2]; + mempool_t *rq_pool; + wait_queue_head_t wait[2]; + unsigned int flags; }; /* @@ -61,9 +77,7 @@ enum rq_cmd_type_bits { REQ_TYPE_PM_SUSPEND, /* suspend request */ REQ_TYPE_PM_RESUME, /* resume request */ REQ_TYPE_PM_SHUTDOWN, /* shutdown request */ - REQ_TYPE_FLUSH, /* flush request */ REQ_TYPE_SPECIAL, /* driver defined type */ - REQ_TYPE_LINUX_BLOCK, /* generic block layer message */ /* * for ATA/ATAPI devices. this really doesn't belong here, ide should * use REQ_TYPE_SPECIAL and use rq->cmd[0] with the range of driver @@ -73,101 +87,49 @@ enum rq_cmd_type_bits { REQ_TYPE_ATA_PC, }; -/* - * For request of type REQ_TYPE_LINUX_BLOCK, rq->cmd[0] is the opcode being - * sent down (similar to how REQ_TYPE_BLOCK_PC means that ->cmd[] holds a - * SCSI cdb. - * - * 0x00 -> 0x3f are driver private, to be used for whatever purpose they need, - * typically to differentiate REQ_TYPE_SPECIAL requests. - * - */ -enum { - /* - * just examples for now - */ - REQ_LB_OP_EJECT = 0x40, /* eject request */ - REQ_LB_OP_FLUSH = 0x41, /* flush device */ -}; - -/* - * request type modified bits. first three bits match BIO_RW* bits, important - */ -enum rq_flag_bits { - __REQ_RW, /* not set, read. set, write */ - __REQ_FAILFAST, /* no low level driver retries */ - __REQ_SORTED, /* elevator knows about this request */ - __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ - __REQ_HARDBARRIER, /* may not be passed by drive either */ - __REQ_FUA, /* forced unit access */ - __REQ_NOMERGE, /* don't touch this for merging */ - __REQ_STARTED, /* drive already may have started this one */ - __REQ_DONTPREP, /* don't call prep for this one */ - __REQ_QUEUED, /* uses queueing */ - __REQ_ELVPRIV, /* elevator private data attached */ - __REQ_FAILED, /* set if the request failed */ - __REQ_QUIET, /* don't worry about errors */ - __REQ_PREEMPT, /* set for "ide_preempt" requests */ - __REQ_ORDERED_COLOR, /* is before or after barrier */ - __REQ_RW_SYNC, /* request is sync (O_DIRECT) */ - __REQ_ALLOCED, /* request came from our alloc pool */ - __REQ_RW_META, /* metadata io request */ - __REQ_NR_BITS, /* stops here */ -}; - -#define REQ_RW (1 << __REQ_RW) -#define REQ_FAILFAST (1 << __REQ_FAILFAST) -#define REQ_SORTED (1 << __REQ_SORTED) -#define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER) -#define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER) -#define REQ_FUA (1 << __REQ_FUA) -#define REQ_NOMERGE (1 << __REQ_NOMERGE) -#define REQ_STARTED (1 << __REQ_STARTED) -#define REQ_DONTPREP (1 << __REQ_DONTPREP) -#define REQ_QUEUED (1 << __REQ_QUEUED) -#define REQ_ELVPRIV (1 << __REQ_ELVPRIV) -#define REQ_FAILED (1 << __REQ_FAILED) -#define REQ_QUIET (1 << __REQ_QUIET) -#define REQ_PREEMPT (1 << __REQ_PREEMPT) -#define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR) -#define REQ_RW_SYNC (1 << __REQ_RW_SYNC) -#define REQ_ALLOCED (1 << __REQ_ALLOCED) -#define REQ_RW_META (1 << __REQ_RW_META) - #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 list_head donelist; + 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; - /* Maintain bio traversal state for part by part I/O submission. - * hard_* are block layer internals, no driver should touch them! - */ - - sector_t sector; /* next sector to submit */ - sector_t hard_sector; /* next sector to complete */ - unsigned long nr_sectors; /* no. of sectors left to submit */ - unsigned long hard_nr_sectors; /* no. of sectors left to complete */ - /* no. of sectors left to submit in the current segment */ - unsigned int current_nr_sectors; + int cpu; - /* no. of sectors left to complete in the current segment */ - unsigned int hard_cur_sectors; + /* the following two fields are internal, NEVER access directly */ + unsigned int __data_len; /* total data len */ + sector_t __sector; /* sector cursor */ 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 @@ -179,49 +141,61 @@ struct request { }; /* - * two pointers are available for the IO schedulers, if they need - * more they have to dynamically allocate it. + * Three pointers are available for the IO schedulers, if they need + * 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; + 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 /* Number of scatter-gather DMA addr+len pairs after * physical address coalescing is performed. */ unsigned short nr_phys_segments; - - /* Number of scatter-gather addr+len pairs after - * physical and DMA remapping hardware coalescing is performed. - * This is the number of scatter-gather entries the driver - * will actually have to deal with after DMA mapping is done. - */ - unsigned short nr_hw_segments; +#if defined(CONFIG_BLK_DEV_INTEGRITY) + unsigned short nr_integrity_segments; +#endif unsigned short ioprio; - void *special; - char *buffer; + void *special; /* opaque pointer available for LLD use */ int tag; int errors; - int ref_count; - /* * when request is used as a packet command carrier */ - unsigned int cmd_len; - unsigned char cmd[BLK_MAX_CDB]; + unsigned char __cmd[BLK_MAX_CDB]; + unsigned char *cmd; + unsigned short cmd_len; - unsigned int data_len; unsigned int extra_len; /* length of alignment and padding */ unsigned int sense_len; - void *data; + unsigned int resid_len; /* residual count */ void *sense; + unsigned long deadline; + struct list_head timeout_list; unsigned int timeout; int retries; @@ -235,6 +209,11 @@ struct request { struct request *next_rq; }; +static inline unsigned short req_get_ioprio(struct request *req) +{ + return req->ioprio; +} + /* * State information carried for REQ_TYPE_PM_SUSPEND and REQ_TYPE_PM_RESUME * requests. Some step values could eventually be made generic. @@ -250,16 +229,34 @@ 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 (unplug_fn) (struct request_queue *); +typedef void (unprep_rq_fn) (struct request_queue *, struct request *); struct bio_vec; -typedef int (merge_bvec_fn) (struct request_queue *, struct bio *, struct bio_vec *); -typedef void (prepare_flush_fn) (struct request_queue *, struct request *); +struct bvec_merge_data { + struct block_device *bi_bdev; + sector_t bi_sector; + unsigned bi_size; + unsigned long bi_rw; +}; +typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *, + struct bio_vec *); typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); +typedef int (lld_busy_fn) (struct request_queue *q); +typedef int (bsg_job_fn) (struct bsg_job *); + +enum blk_eh_timer_return { + BLK_EH_NOT_HANDLED, + BLK_EH_HANDLED, + BLK_EH_RESET_TIMER, +}; + +typedef enum blk_eh_timer_return (rq_timed_out_fn)(struct request *); enum blk_queue_state { Queue_down, @@ -275,28 +272,76 @@ struct blk_queue_tag { atomic_t refcnt; /* map can be shared */ }; -struct request_queue -{ +#define BLK_SCSI_MAX_CMDS (256) +#define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) + +struct queue_limits { + unsigned long bounce_pfn; + 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; + unsigned int alignment_offset; + 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; + + unsigned short logical_block_size; + unsigned short max_segments; + unsigned short max_integrity_segments; + + unsigned char misaligned; + unsigned char discard_misaligned; + unsigned char cluster; + unsigned char discard_zeroes_data; + unsigned char raid_partial_stripes_expensive; +}; + +struct request_queue { /* * Together with queue_head for cacheline sharing */ struct list_head queue_head; struct request *last_merge; - elevator_t *elevator; + 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; - unplug_fn *unplug_fn; + unprep_rq_fn *unprep_rq_fn; merge_bvec_fn *merge_bvec_fn; - prepare_flush_fn *prepare_flush_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 @@ -305,12 +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; @@ -321,15 +363,20 @@ struct request_queue void *queuedata; /* - * queue needs bounce pages for pages above this limit + * various queue flags, see QUEUE_* below */ - unsigned long bounce_pfn; - 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 @@ -345,6 +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 */ @@ -352,16 +410,8 @@ struct request_queue unsigned int nr_congestion_off; unsigned int nr_batching; - unsigned int max_sectors; - unsigned int max_hw_sectors; - unsigned short max_phys_segments; - unsigned short max_hw_segments; - unsigned short hardsect_size; - unsigned int max_segment_size; - - unsigned long seg_boundary_mask; - void *dma_drain_buffer; unsigned int dma_drain_size; + void *dma_drain_buffer; unsigned int dma_pad_mask; unsigned int dma_alignment; @@ -369,7 +419,26 @@ struct request_queue struct list_head tag_busy_list; unsigned int nr_sorted; - unsigned int in_flight; + 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; /* * sg stuff @@ -381,141 +450,259 @@ struct request_queue struct blk_trace *blk_trace; #endif /* - * reserved for flush operations + * for flush operations */ - unsigned int ordered, next_ordered, ordseq; - int orderr, ordcolor; - struct request pre_flush_rq, bar_rq, post_flush_rq; - struct request *orig_bar_rq; + unsigned int flush_flags; + 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 + +#ifdef CONFIG_BLK_DEV_THROTTLING + /* 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_READFULL 3 /* read queue has been filled */ -#define QUEUE_FLAG_WRITEFULL 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 */ - -enum { - /* - * Hardbarrier is supported with one of the following methods. - * - * NONE : hardbarrier unsupported - * DRAIN : ordering by draining is enough - * DRAIN_FLUSH : ordering by draining w/ pre and post flushes - * DRAIN_FUA : ordering by draining w/ pre flush and FUA write - * TAG : ordering by tag is enough - * TAG_FLUSH : ordering by tag w/ pre and post flushes - * TAG_FUA : ordering by tag w/ pre flush and FUA write - */ - QUEUE_ORDERED_NONE = 0x00, - QUEUE_ORDERED_DRAIN = 0x01, - QUEUE_ORDERED_TAG = 0x02, - - QUEUE_ORDERED_PREFLUSH = 0x10, - QUEUE_ORDERED_POSTFLUSH = 0x20, - QUEUE_ORDERED_FUA = 0x40, - - QUEUE_ORDERED_DRAIN_FLUSH = QUEUE_ORDERED_DRAIN | - QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH, - QUEUE_ORDERED_DRAIN_FUA = QUEUE_ORDERED_DRAIN | - QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_FUA, - QUEUE_ORDERED_TAG_FLUSH = QUEUE_ORDERED_TAG | - QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_POSTFLUSH, - QUEUE_ORDERED_TAG_FUA = QUEUE_ORDERED_TAG | - QUEUE_ORDERED_PREFLUSH | QUEUE_ORDERED_FUA, +#define QUEUE_FLAG_SYNCFULL 3 /* read queue has been filled */ +#define QUEUE_FLAG_ASYNCFULL 4 /* write queue has been filled */ +#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 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_STACKABLE) | \ + (1 << QUEUE_FLAG_SAME_COMP) | \ + (1 << QUEUE_FLAG_ADD_RANDOM)) + +#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) +{ + if (q->queue_lock) + lockdep_assert_held(q->queue_lock); +} - /* - * Ordered operation sequence - */ - QUEUE_ORDSEQ_STARTED = 0x01, /* flushing in progress */ - QUEUE_ORDSEQ_DRAIN = 0x02, /* waiting for the queue to be drained */ - QUEUE_ORDSEQ_PREFLUSH = 0x04, /* pre-flushing in progress */ - QUEUE_ORDSEQ_BAR = 0x08, /* original barrier req in progress */ - QUEUE_ORDSEQ_POSTFLUSH = 0x10, /* post-flushing in progress */ - QUEUE_ORDSEQ_DONE = 0x20, -}; +static inline void queue_flag_set_unlocked(unsigned int flag, + struct request_queue *q) +{ + __set_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_flushing(q) ((q)->ordseq) +static inline int queue_flag_test_and_clear(unsigned int flag, + struct request_queue *q) +{ + queue_lockdep_assert_held(q); + + if (test_bit(flag, &q->queue_flags)) { + __clear_bit(flag, &q->queue_flags); + return 1; + } + + return 0; +} + +static inline int queue_flag_test_and_set(unsigned int flag, + struct request_queue *q) +{ + queue_lockdep_assert_held(q); + + if (!test_bit(flag, &q->queue_flags)) { + __set_bit(flag, &q->queue_flags); + return 0; + } + + return 1; +} -#define blk_fs_request(rq) ((rq)->cmd_type == REQ_TYPE_FS) -#define blk_pc_request(rq) ((rq)->cmd_type == REQ_TYPE_BLOCK_PC) -#define blk_special_request(rq) ((rq)->cmd_type == REQ_TYPE_SPECIAL) -#define blk_sense_request(rq) ((rq)->cmd_type == REQ_TYPE_SENSE) +static inline void queue_flag_set(unsigned int flag, struct request_queue *q) +{ + queue_lockdep_assert_held(q); + __set_bit(flag, &q->queue_flags); +} + +static inline void queue_flag_clear_unlocked(unsigned int flag, + struct request_queue *q) +{ + __clear_bit(flag, &q->queue_flags); +} + +static inline int queue_in_flight(struct request_queue *q) +{ + return q->in_flight[0] + q->in_flight[1]; +} -#define blk_noretry_request(rq) ((rq)->cmd_flags & REQ_FAILFAST) -#define blk_rq_started(rq) ((rq)->cmd_flags & REQ_STARTED) +static inline void queue_flag_clear(unsigned int flag, struct request_queue *q) +{ + queue_lockdep_assert_held(q); + __clear_bit(flag, &q->queue_flags); +} -#define blk_account_rq(rq) (blk_rq_started(rq) && blk_fs_request(rq)) +#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) +#define blk_queue_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) +#define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) +#define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) +#define blk_queue_stackable(q) \ + test_bit(QUEUE_FLAG_STACKABLE, &(q)->queue_flags) +#define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) +#define blk_queue_secdiscard(q) (blk_queue_discard(q) && \ + test_bit(QUEUE_FLAG_SECDISCARD, &(q)->queue_flags)) + +#define blk_noretry_request(rq) \ + ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ + REQ_FAILFAST_DRIVER)) + +#define blk_account_rq(rq) \ + (((rq)->cmd_flags & REQ_STARTED) && \ + ((rq)->cmd_type == REQ_TYPE_FS)) -#define blk_pm_suspend_request(rq) ((rq)->cmd_type == REQ_TYPE_PM_SUSPEND) -#define blk_pm_resume_request(rq) ((rq)->cmd_type == REQ_TYPE_PM_RESUME) #define blk_pm_request(rq) \ - (blk_pm_suspend_request(rq) || blk_pm_resume_request(rq)) + ((rq)->cmd_type == REQ_TYPE_PM_SUSPEND || \ + (rq)->cmd_type == REQ_TYPE_PM_RESUME) -#define blk_sorted_rq(rq) ((rq)->cmd_flags & REQ_SORTED) -#define blk_barrier_rq(rq) ((rq)->cmd_flags & REQ_HARDBARRIER) -#define blk_fua_rq(rq) ((rq)->cmd_flags & REQ_FUA) +#define blk_rq_cpu_valid(rq) ((rq)->cpu != -1) #define blk_bidi_rq(rq) ((rq)->next_rq != NULL) -#define blk_empty_barrier(rq) (blk_barrier_rq(rq) && blk_fs_request(rq) && !(rq)->hard_nr_sectors) /* rq->queuelist of dequeued request must be list_empty() */ #define blk_queued_rq(rq) (!list_empty(&(rq)->queuelist)) #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) -#define rq_data_dir(rq) ((rq)->cmd_flags & 1) +#define rq_data_dir(rq) (((rq)->cmd_flags & 1) != 0) /* - * We regard a request as sync, if it's a READ or a SYNC write. + * Driver can handle struct request, if it either has an old style + * request_fn defined, or is blk-mq based. */ -#define rq_is_sync(rq) (rq_data_dir((rq)) == READ || (rq)->cmd_flags & REQ_RW_SYNC) -#define rq_is_meta(rq) ((rq)->cmd_flags & REQ_RW_META) +static inline bool queue_is_rq_based(struct request_queue *q) +{ + return q->request_fn || q->mq_ops; +} -static inline int blk_queue_full(struct request_queue *q, int rw) +static inline unsigned int blk_queue_cluster(struct request_queue *q) { - if (rw == READ) - return test_bit(QUEUE_FLAG_READFULL, &q->queue_flags); - return test_bit(QUEUE_FLAG_WRITEFULL, &q->queue_flags); + return q->limits.cluster; } -static inline void blk_set_queue_full(struct request_queue *q, int rw) +/* + * We regard a request as sync, if either a read or a sync write + */ +static inline bool rw_is_sync(unsigned int rw_flags) { - if (rw == READ) - set_bit(QUEUE_FLAG_READFULL, &q->queue_flags); - else - set_bit(QUEUE_FLAG_WRITEFULL, &q->queue_flags); + return !(rw_flags & REQ_WRITE) || (rw_flags & REQ_SYNC); } -static inline void blk_clear_queue_full(struct request_queue *q, int rw) +static inline bool rq_is_sync(struct request *rq) { - if (rw == READ) - clear_bit(QUEUE_FLAG_READFULL, &q->queue_flags); - else - clear_bit(QUEUE_FLAG_WRITEFULL, &q->queue_flags); + return rw_is_sync(rq->cmd_flags); } +static inline bool blk_rl_full(struct request_list *rl, bool sync) +{ + unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; -/* - * 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_HARDBARRIER | REQ_SOFTBARRIER) -#define rq_mergeable(rq) \ - (!((rq)->cmd_flags & RQ_NOMERGE_FLAGS) && blk_fs_request((rq))) + return rl->flags & flag; +} + +static inline void blk_set_rl_full(struct request_list *rl, bool sync) +{ + unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; + + rl->flags |= flag; +} + +static inline void blk_clear_rl_full(struct request_list *rl, bool sync) +{ + unsigned int flag = sync ? BLK_RL_SYNCFULL : BLK_RL_ASYNCFULL; + + rl->flags &= ~flag; +} + +static inline bool rq_mergeable(struct request *rq) +{ + if (rq->cmd_type != REQ_TYPE_FS) + return false; + + 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 @@ -533,14 +720,20 @@ extern unsigned long blk_max_low_pfn, blk_max_pfn; * BLK_BOUNCE_ANY : don't bounce anything * BLK_BOUNCE_ISA : bounce pages above ISA DMA boundary */ + +#if BITS_PER_LONG == 32 #define BLK_BOUNCE_HIGH ((u64)blk_max_low_pfn << PAGE_SHIFT) -#define BLK_BOUNCE_ANY ((u64)blk_max_pfn << PAGE_SHIFT) -#define BLK_BOUNCE_ISA (ISA_DMA_THRESHOLD) +#else +#define BLK_BOUNCE_HIGH -1ULL +#endif +#define BLK_BOUNCE_ANY (-1ULL) +#define BLK_BOUNCE_ISA (DMA_BIT_MASK(24)) /* * default timeout for SG_IO if none specified */ #define BLK_DEFAULT_SG_TIMEOUT (60 * HZ) +#define BLK_MIN_SG_TIMEOUT (7 * HZ) #ifdef CONFIG_BOUNCE extern int init_emergency_isa_pool(void); @@ -555,137 +748,248 @@ static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio) } #endif /* CONFIG_MMU */ +struct rq_map_data { + struct page **pages; + int page_order; + int nr_entries; + unsigned long offset; + int null_mapped; + int from_user; +}; + struct req_iterator { - int i; + struct bvec_iter iter; struct bio *bio; }; /* This should not be used directly - use rq_for_each_segment */ +#define for_each_bio(_bio) \ + for (; _bio; _bio = _bio->bi_next) #define __rq_for_each_bio(_bio, rq) \ if ((rq->bio)) \ for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next) #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(bvec, _iter) \ + (_iter.bio->bi_next == NULL && \ + bio_iter_last(bvec, _iter.iter)) -#define rq_iter_last(rq, _iter) \ - (_iter.bio->bi_next == NULL && _iter.i == _iter.bio->bi_vcnt-1) +#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +# error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" +#endif +#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE +extern void rq_flush_dcache_pages(struct request *rq); +#else +static inline void rq_flush_dcache_pages(struct request *rq) +{ +} +#endif 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 *); extern void __blk_put_request(struct request_queue *, struct request *); -extern void blk_end_sync_rq(struct request *rq, int error); extern struct request *blk_get_request(struct request_queue *, int, gfp_t); -extern void blk_insert_request(struct request_queue *, struct request *, int, void *); +extern struct request *blk_make_request(struct request_queue *, struct bio *, + gfp_t); +extern void blk_rq_set_block_pc(struct request *); extern void blk_requeue_request(struct request_queue *, struct request *); -extern void blk_plug_device(struct request_queue *); -extern int blk_remove_plug(struct request_queue *); +extern void blk_add_request_payload(struct request *rq, struct page *page, + unsigned int len); +extern int blk_rq_check_limits(struct request_queue *q, struct request *rq); +extern int blk_lld_busy(struct request_queue *q); +extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, + struct bio_set *bs, gfp_t gfp_mask, + int (*bio_ctr)(struct bio *, struct bio *, void *), + void *data); +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_delay_queue(struct request_queue *, unsigned long); extern void blk_recount_segments(struct request_queue *, struct bio *); -extern int scsi_cmd_ioctl(struct file *, struct request_queue *, - struct gendisk *, unsigned int, void __user *); -extern int sg_scsi_ioctl(struct file *, struct request_queue *, - struct gendisk *, struct scsi_ioctl_command __user *); +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 *); -/* - * Temporary export, until SCSI gets fixed up. - */ -extern int blk_rq_append_bio(struct request_queue *q, struct request *rq, - struct bio *bio); +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 * put back. */ -static inline void blk_clear_queue_congested(struct request_queue *q, int rw) +static inline void blk_clear_queue_congested(struct request_queue *q, int sync) { - clear_bdi_congested(&q->backing_dev_info, rw); + clear_bdi_congested(&q->backing_dev_info, sync); } /* * A queue has just entered congestion. Flag that in the queue's VM-visible * state flags and increment the global gounter of congested queues. */ -static inline void blk_set_queue_congested(struct request_queue *q, int rw) +static inline void blk_set_queue_congested(struct request_queue *q, int sync) { - set_bdi_congested(&q->backing_dev_info, rw); + set_bdi_congested(&q->backing_dev_info, sync); } 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 *q); extern void blk_run_queue(struct request_queue *); -extern void blk_start_queueing(struct request_queue *); -extern int blk_rq_map_user(struct request_queue *, struct request *, void __user *, unsigned long); +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 sg_iovec *, int, unsigned int); + 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 int blk_verify_command(unsigned char *, int); -extern void blk_unplug(struct request_queue *q); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { return bdev->bd_disk->queue; } -static inline void blk_run_backing_dev(struct backing_dev_info *bdi, - struct page *page) +/* + * blk_rq_pos() : the current sector + * blk_rq_bytes() : bytes left in the entire request + * blk_rq_cur_bytes() : bytes left in the current segment + * blk_rq_err_bytes() : bytes left till the next error boundary + * blk_rq_sectors() : sectors left in the entire request + * blk_rq_cur_sectors() : sectors left in the current segment + */ +static inline sector_t blk_rq_pos(const struct request *rq) +{ + return rq->__sector; +} + +static inline unsigned int blk_rq_bytes(const struct request *rq) +{ + return rq->__data_len; +} + +static inline int blk_rq_cur_bytes(const struct request *rq) +{ + return rq->bio ? bio_cur_bytes(rq->bio) : 0; +} + +extern unsigned int blk_rq_err_bytes(const struct request *rq); + +static inline unsigned int blk_rq_sectors(const struct request *rq) +{ + return blk_rq_bytes(rq) >> 9; +} + +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) { - if (bdi && bdi->unplug_io_fn) - bdi->unplug_io_fn(bdi, page); + 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 void blk_run_address_space(struct address_space *mapping) +static inline unsigned int blk_rq_count_bios(struct request *rq) { - if (mapping) - blk_run_backing_dev(mapping->backing_dev_info, NULL); + unsigned int nr_bios = 0; + struct bio *bio; + + __rq_for_each_bio(bio, rq) + nr_bios++; + + return nr_bios; } /* - * blk_end_request() and friends. - * __blk_end_request() and end_request() must be called with - * the request queue spinlock acquired. + * Request issue related functions. + */ +extern struct request *blk_peek_request(struct request_queue *q); +extern void blk_start_request(struct request *rq); +extern struct request *blk_fetch_request(struct request_queue *q); + +/* + * Request completion related functions. + * + * blk_update_request() completes given number of bytes and updates + * the request without completing it. + * + * blk_end_request() and friends. __blk_end_request() must be called + * with the request queue spinlock acquired. * * Several drivers define their own end_request and call * blk_end_request() for parts of the original function. * This prevents code duplication in drivers. */ -extern int blk_end_request(struct request *rq, int error, - unsigned int nr_bytes); -extern int __blk_end_request(struct request *rq, int error, - unsigned int nr_bytes); -extern int blk_end_bidi_request(struct request *rq, int error, - unsigned int nr_bytes, unsigned int bidi_bytes); -extern void end_request(struct request *, int); -extern void end_queued_request(struct request *, int); -extern void end_dequeued_request(struct request *, int); -extern int blk_end_request_callback(struct request *rq, int error, - unsigned int nr_bytes, - int (drv_callback)(struct request *)); -extern void blk_complete_request(struct request *); - -/* - * blk_end_request() takes bytes instead of sectors as a complete size. - * blk_rq_bytes() returns bytes left to complete in the entire request. - * blk_rq_cur_bytes() returns bytes left to complete in the current segment. - */ -extern unsigned int blk_rq_bytes(struct request *rq); -extern unsigned int blk_rq_cur_bytes(struct request *rq); +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); +extern bool blk_end_request_cur(struct request *rq, int error); +extern bool blk_end_request_err(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); +extern bool __blk_end_request_cur(struct request *rq, int error); +extern bool __blk_end_request_err(struct request *rq, int error); -static inline void blkdev_dequeue_request(struct request *req) -{ - elv_dequeue_request(req->q, req); -} +extern void blk_complete_request(struct request *); +extern void __blk_complete_request(struct request *); +extern void blk_abort_request(struct request *); +extern void blk_unprep_request(struct request *); /* * Access functions for manipulating queue properties @@ -693,49 +997,151 @@ static inline void blkdev_dequeue_request(struct request *req) extern struct request_queue *blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id); extern struct request_queue *blk_init_queue(request_fn_proc *, spinlock_t *); +extern 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_queue_max_sectors(struct request_queue *, unsigned int); -extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short); -extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short); +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_hardsect_size(struct request_queue *, unsigned short); +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, + unsigned int alignment); +extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); +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, + sector_t offset); +extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, + sector_t offset); extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b); extern void blk_queue_dma_pad(struct request_queue *, unsigned int); +extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); extern int blk_queue_dma_drain(struct request_queue *q, dma_drain_needed_fn *dma_drain_needed, void *buf, unsigned int size); +extern void blk_queue_lld_busy(struct request_queue *q, lld_busy_fn *fn); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_prep_rq(struct request_queue *, prep_rq_fn *pfn); +extern void blk_queue_unprep_rq(struct request_queue *, unprep_rq_fn *ufn); extern void blk_queue_merge_bvec(struct request_queue *, merge_bvec_fn *); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_softirq_done(struct request_queue *, softirq_done_fn *); +extern void blk_queue_rq_timed_out(struct request_queue *, rq_timed_out_fn *); +extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); +extern void blk_queue_flush(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_queue_ordered(struct request_queue *, unsigned, prepare_flush_fn *); -extern int blk_do_ordered(struct request_queue *, struct request **); -extern unsigned blk_ordered_cur_seq(struct request_queue *); -extern unsigned blk_ordered_req_seq(struct request *); -extern void blk_ordered_complete_seq(struct request_queue *, unsigned, int); 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 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_queue_tag_depth(q) ((q)->queue_tags->busy) -#define blk_queue_tag_queue(q) ((q)->queue_tags->busy < (q)->queue_tags->max_depth) -#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 *); @@ -754,30 +1160,210 @@ static inline struct request *blk_map_queue_find_tag(struct blk_queue_tag *bqt, return bqt->tag_index[tag]; } -extern int blkdev_issue_flush(struct block_device *, sector_t *); +#define BLKDEV_DISCARD_SECURE 0x01 /* secure discard */ + +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, + sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags) +{ + return blkdev_issue_discard(sb->s_bdev, block << (sb->s_blocksize_bits - 9), + nr_blocks << (sb->s_blocksize_bits - 9), + gfp_mask, flags); +} +static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, + sector_t nr_blocks, gfp_t gfp_mask) +{ + return blkdev_issue_zeroout(sb->s_bdev, + block << (sb->s_blocksize_bits - 9), + nr_blocks << (sb->s_blocksize_bits - 9), + gfp_mask); +} -#define MAX_PHYS_SEGMENTS 128 -#define MAX_HW_SEGMENTS 128 -#define SAFE_MAX_SECTORS 255 -#define BLK_DEF_MAX_SECTORS 1024 +extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); -#define MAX_SEGMENT_SIZE 65536 +enum blk_default_limits { + BLK_MAX_SEGMENTS = 128, + BLK_SAFE_MAX_SECTORS = 255, + BLK_DEF_MAX_SECTORS = 1024, + BLK_MAX_SEGMENT_SIZE = 65536, + BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, +}; #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist) -static inline int queue_hardsect_size(struct request_queue *q) +static inline unsigned long queue_bounce_pfn(struct request_queue *q) +{ + return q->limits.bounce_pfn; +} + +static inline unsigned long queue_segment_boundary(struct request_queue *q) +{ + return q->limits.seg_boundary_mask; +} + +static inline unsigned int queue_max_sectors(struct request_queue *q) +{ + return q->limits.max_sectors; +} + +static inline unsigned int queue_max_hw_sectors(struct request_queue *q) +{ + return q->limits.max_hw_sectors; +} + +static inline unsigned short queue_max_segments(struct request_queue *q) +{ + return q->limits.max_segments; +} + +static inline unsigned int queue_max_segment_size(struct request_queue *q) +{ + return q->limits.max_segment_size; +} + +static inline unsigned short queue_logical_block_size(struct request_queue *q) { int retval = 512; - if (q && q->hardsect_size) - retval = q->hardsect_size; + if (q && q->limits.logical_block_size) + retval = q->limits.logical_block_size; return retval; } -static inline int bdev_hardsect_size(struct block_device *bdev) +static inline unsigned short bdev_logical_block_size(struct block_device *bdev) +{ + return queue_logical_block_size(bdev_get_queue(bdev)); +} + +static inline unsigned int queue_physical_block_size(struct request_queue *q) +{ + return q->limits.physical_block_size; +} + +static inline unsigned int bdev_physical_block_size(struct block_device *bdev) +{ + return queue_physical_block_size(bdev_get_queue(bdev)); +} + +static inline unsigned int queue_io_min(struct request_queue *q) +{ + return q->limits.io_min; +} + +static inline int bdev_io_min(struct block_device *bdev) +{ + return queue_io_min(bdev_get_queue(bdev)); +} + +static inline unsigned int queue_io_opt(struct request_queue *q) +{ + return q->limits.io_opt; +} + +static inline int bdev_io_opt(struct block_device *bdev) +{ + return queue_io_opt(bdev_get_queue(bdev)); +} + +static inline int queue_alignment_offset(struct request_queue *q) +{ + if (q->limits.misaligned) + return -1; + + return q->limits.alignment_offset; +} + +static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) +{ + unsigned int granularity = max(lim->physical_block_size, lim->io_min); + unsigned int alignment = (sector << 9) & (granularity - 1); + + return (granularity + lim->alignment_offset - alignment) + & (granularity - 1); +} + +static inline int bdev_alignment_offset(struct block_device *bdev) +{ + struct request_queue *q = bdev_get_queue(bdev); + + if (q->limits.misaligned) + return -1; + + if (bdev != bdev->bd_contains) + return bdev->bd_part->alignment_offset; + + return q->limits.alignment_offset; +} + +static inline int queue_discard_alignment(struct request_queue *q) +{ + if (q->limits.discard_misaligned) + return -1; + + return q->limits.discard_alignment; +} + +static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) +{ + 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; + + /* 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.max_discard_sectors && q->limits.discard_zeroes_data == 1) + return 1; + + return 0; +} + +static inline unsigned int bdev_discard_zeroes_data(struct block_device *bdev) { - return queue_hardsect_size(bdev_get_queue(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) @@ -785,6 +1371,13 @@ static inline int queue_dma_alignment(struct request_queue *q) return q ? q->dma_alignment : 511; } +static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr, + unsigned int len) +{ + unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask; + return !(addr & alignment) && !(len & alignment); +} + /* assumes size > 256 */ static inline unsigned int blksize_bits(unsigned int size) { @@ -801,6 +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 *); @@ -812,15 +1410,232 @@ static inline void put_dev_sector(Sector p) struct work_struct; int kblockd_schedule_work(struct work_struct *work); -void kblockd_flush_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 +/* + * This should not be using sched_clock(). A real patch is in progress + * to fix this up, until that is in place we need to disable preemption + * around sched_clock() in this function and set_io_start_time_ns(). + */ +static inline void set_start_time_ns(struct request *req) +{ + preempt_disable(); + req->start_time_ns = sched_clock(); + preempt_enable(); +} + +static inline void set_io_start_time_ns(struct request *req) +{ + preempt_disable(); + req->io_start_time_ns = sched_clock(); + preempt_enable(); +} + +static inline uint64_t rq_start_time_ns(struct request *req) +{ + return req->start_time_ns; +} + +static inline uint64_t rq_io_start_time_ns(struct request *req) +{ + return req->io_start_time_ns; +} +#else +static inline void set_start_time_ns(struct request *req) {} +static inline void set_io_start_time_ns(struct request *req) {} +static inline uint64_t rq_start_time_ns(struct request *req) +{ + return 0; +} +static inline uint64_t rq_io_start_time_ns(struct request *req) +{ + return 0; +} +#endif #define MODULE_ALIAS_BLOCKDEV(major,minor) \ MODULE_ALIAS("block-major-" __stringify(major) "-" __stringify(minor)) #define MODULE_ALIAS_BLOCKDEV_MAJOR(major) \ MODULE_ALIAS("block-major-" __stringify(major) "-*") +#if defined(CONFIG_BLK_DEV_INTEGRITY) + +#define INTEGRITY_FLAG_READ 2 /* verify data integrity on read */ +#define INTEGRITY_FLAG_WRITE 4 /* generate data integrity on write */ +struct blk_integrity_exchg { + void *prot_buf; + void *data_buf; + sector_t sector; + unsigned int data_size; + unsigned short sector_size; + const char *disk_name; +}; + +typedef void (integrity_gen_fn) (struct blk_integrity_exchg *); +typedef int (integrity_vrfy_fn) (struct blk_integrity_exchg *); +typedef void (integrity_set_tag_fn) (void *, void *, unsigned int); +typedef void (integrity_get_tag_fn) (void *, void *, unsigned int); + +struct blk_integrity { + integrity_gen_fn *generate_fn; + integrity_vrfy_fn *verify_fn; + integrity_set_tag_fn *set_tag_fn; + integrity_get_tag_fn *get_tag_fn; + + unsigned short flags; + unsigned short tuple_size; + unsigned short sector_size; + unsigned short tag_size; + + const char *name; + + 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 *); +extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, + struct scatterlist *); +extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); +extern int blk_integrity_merge_rq(struct request_queue *, struct request *, + struct request *); +extern int blk_integrity_merge_bio(struct request_queue *, struct request *, + struct bio *); + +static inline +struct blk_integrity *bdev_get_integrity(struct block_device *bdev) +{ + return bdev->bd_disk->integrity; +} + +static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) +{ + return disk->integrity; +} + +static inline int blk_integrity_rq(struct request *rq) +{ + if (rq->bio == NULL) + return 0; + + return bio_integrity(rq->bio); +} + +static inline void blk_queue_max_integrity_segments(struct request_queue *q, + unsigned int segs) +{ + q->limits.max_integrity_segments = segs; +} + +static inline unsigned short +queue_max_integrity_segments(struct request_queue *q) +{ + return q->limits.max_integrity_segments; +} + +#else /* CONFIG_BLK_DEV_INTEGRITY */ + +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); + 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 *); + int (*getgeo)(struct block_device *, struct hd_geometry *); + /* this callback is with swap_lock and sometimes page table lock held */ + void (*swap_slot_free_notify) (struct block_device *, unsigned long); + struct module *owner; +}; + +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 */ @@ -831,16 +1646,36 @@ static inline long nr_blockdev_pages(void) return 0; } -static inline void exit_io_context(void) +struct blk_plug { +}; + +static inline void blk_start_plug(struct blk_plug *plug) { } -struct io_context; -static inline int put_io_context(struct io_context *ioc) +static inline void blk_finish_plug(struct blk_plug *plug) { - return 1; } +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 */ |