diff options
Diffstat (limited to 'include/linux/blkdev.h')
| -rw-r--r-- | include/linux/blkdev.h | 184 |
1 files changed, 78 insertions, 106 deletions
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 5c4eee043191..d6869e0e2b64 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -27,8 +27,6 @@ #include <linux/percpu-refcount.h> #include <linux/scatterlist.h> #include <linux/blkzoned.h> -#include <linux/seqlock.h> -#include <linux/u64_stats_sync.h> struct module; struct scsi_ioctl_command; @@ -42,7 +40,7 @@ struct bsg_job; struct blkcg_gq; struct blk_flush_queue; struct pr_ops; -struct rq_wb; +struct rq_qos; struct blk_queue_stats; struct blk_stat_callback; @@ -125,16 +123,25 @@ typedef __u32 __bitwise req_flags_t; #define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) /* The per-zone write lock is held for this request */ #define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) -/* timeout is expired */ -#define RQF_MQ_TIMEOUT_EXPIRED ((__force req_flags_t)(1 << 20)) /* already slept for hybrid poll */ -#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 21)) +#define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20)) +/* ->timeout has been called, don't expire again */ +#define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) /* + * Request state for blk-mq. + */ +enum mq_rq_state { + MQ_RQ_IDLE = 0, + MQ_RQ_IN_FLIGHT = 1, + MQ_RQ_COMPLETE = 2, +}; + +/* * 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 @@ -205,9 +212,20 @@ struct request { struct gendisk *rq_disk; struct hd_struct *part; - unsigned long start_time; - struct blk_issue_stat issue_stat; - /* Number of scatter-gather DMA addr+len pairs after + /* Time that I/O was submitted to the kernel. */ + u64 start_time_ns; + /* Time that I/O was submitted to the device. */ + u64 io_start_time_ns; + +#ifdef CONFIG_BLK_WBT + unsigned short wbt_flags; +#endif +#ifdef CONFIG_BLK_DEV_THROTTLING_LOW + unsigned short throtl_size; +#endif + + /* + * Number of scatter-gather DMA addr+len pairs after * physical address coalescing is performed. */ unsigned short nr_phys_segments; @@ -219,32 +237,14 @@ struct request { unsigned short write_hint; unsigned short ioprio; - unsigned int timeout; - void *special; /* opaque pointer available for LLD use */ unsigned int extra_len; /* length of alignment and padding */ - /* - * On blk-mq, the lower bits of ->gstate (generation number and - * state) carry the MQ_RQ_* state value and the upper bits the - * generation number which is monotonically incremented and used to - * distinguish the reuse instances. - * - * ->gstate_seq allows updates to ->gstate and other fields - * (currently ->deadline) during request start to be read - * atomically from the timeout path, so that it can operate on a - * coherent set of information. - */ - seqcount_t gstate_seq; - u64 gstate; + enum mq_rq_state state; + refcount_t ref; - /* - * ->aborted_gstate is used by the timeout to claim a specific - * recycle instance of this request. See blk_mq_timeout_work(). - */ - struct u64_stats_sync aborted_gstate_sync; - u64 aborted_gstate; + unsigned int timeout; /* access through blk_rq_set_deadline, blk_rq_deadline */ unsigned long __deadline; @@ -267,8 +267,6 @@ struct request { #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 }; @@ -328,9 +326,8 @@ typedef int (init_rq_fn)(struct request_queue *, struct request *, gfp_t); typedef void (exit_rq_fn)(struct request_queue *, struct request *); enum blk_eh_timer_return { - BLK_EH_NOT_HANDLED, - BLK_EH_HANDLED, - BLK_EH_RESET_TIMER, + BLK_EH_DONE, /* drivers has completed the command */ + BLK_EH_RESET_TIMER, /* reset timer and try again */ }; typedef enum blk_eh_timer_return (rq_timed_out_fn)(struct request *); @@ -443,10 +440,8 @@ struct request_queue { int nr_rqs[2]; /* # allocated [a]sync rqs */ int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ - atomic_t shared_hctx_restart; - struct blk_queue_stats *stats; - struct rq_wb *rq_wb; + struct rq_qos *rq_qos; /* * If blkcg is not used, @q->root_rl serves all requests. If blkcg @@ -563,7 +558,6 @@ struct request_queue { unsigned int dma_alignment; struct blk_queue_tag *queue_tags; - struct list_head tag_busy_list; unsigned int nr_sorted; unsigned int in_flight[2]; @@ -594,6 +588,7 @@ struct request_queue { struct queue_limits limits; +#ifdef CONFIG_BLK_DEV_ZONED /* * Zoned block device information for request dispatch control. * nr_zones is the total number of zones of the device. This is always @@ -614,6 +609,7 @@ struct request_queue { unsigned int nr_zones; unsigned long *seq_zones_bitmap; unsigned long *seq_zones_wlock; +#endif /* CONFIG_BLK_DEV_ZONED */ /* * sg stuff @@ -655,7 +651,7 @@ struct request_queue { struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; - struct bio_set *bio_split; + struct bio_set bio_split; #ifdef CONFIG_BLK_DEBUG_FS struct dentry *debugfs_dir; @@ -802,11 +798,7 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q) return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } -static inline unsigned int blk_queue_nr_zones(struct request_queue *q) -{ - return q->nr_zones; -} - +#ifdef CONFIG_BLK_DEV_ZONED static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { @@ -822,6 +814,7 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q, return false; return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap); } +#endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) { @@ -967,11 +960,8 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_init_request_from_bio(struct request *req, struct bio *bio); extern void blk_put_request(struct request *); extern void __blk_put_request(struct request_queue *, struct request *); -extern struct request *blk_get_request_flags(struct request_queue *, - unsigned int op, - blk_mq_req_flags_t flags); extern struct request *blk_get_request(struct request_queue *, unsigned int op, - gfp_t gfp_mask); + blk_mq_req_flags_t flags); extern void blk_requeue_request(struct request_queue *, struct request *); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, @@ -1075,6 +1065,7 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT; } +#ifdef CONFIG_BLK_DEV_ZONED static inline unsigned int blk_rq_zone_no(struct request *rq) { return blk_queue_zone_no(rq->q, blk_rq_pos(rq)); @@ -1084,6 +1075,7 @@ static inline unsigned int blk_rq_zone_is_seq(struct request *rq) { return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq)); } +#endif /* CONFIG_BLK_DEV_ZONED */ /* * Some commands like WRITE SAME have a payload or data transfer size which @@ -1124,8 +1116,8 @@ static inline unsigned int blk_max_size_offset(struct request_queue *q, if (!q->limits.chunk_sectors) return q->limits.max_sectors; - return q->limits.chunk_sectors - - (offset & (q->limits.chunk_sectors - 1)); + return min(q->limits.max_sectors, (unsigned int)(q->limits.chunk_sectors - + (offset & (q->limits.chunk_sectors - 1)))); } static inline unsigned int blk_rq_get_max_sectors(struct request *rq, @@ -1379,7 +1371,6 @@ extern void blk_queue_end_tag(struct request_queue *, struct request *); extern int blk_queue_init_tags(struct request_queue *, int, struct blk_queue_tag *, int); extern void blk_queue_free_tags(struct request_queue *); extern int blk_queue_resize_tags(struct request_queue *, int); -extern void blk_queue_invalidate_tags(struct request_queue *); extern struct blk_queue_tag *blk_init_tags(int, int); extern void blk_free_tags(struct blk_queue_tag *); @@ -1443,8 +1434,6 @@ enum blk_default_limits { BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, }; -#define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist) - static inline unsigned long queue_segment_boundary(struct request_queue *q) { return q->limits.seg_boundary_mask; @@ -1645,15 +1634,6 @@ static inline unsigned int bdev_zone_sectors(struct block_device *bdev) return 0; } -static inline unsigned int bdev_nr_zones(struct block_device *bdev) -{ - struct request_queue *q = bdev_get_queue(bdev); - - if (q) - return blk_queue_nr_zones(q); - return 0; -} - static inline int queue_dma_alignment(struct request_queue *q) { return q ? q->dma_alignment : 511; @@ -1788,48 +1768,6 @@ int kblockd_schedule_work(struct work_struct *work); int kblockd_schedule_work_on(int cpu, struct work_struct *work); int kblockd_mod_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) \ @@ -1925,6 +1863,28 @@ static inline bool integrity_req_gap_front_merge(struct request *req, bip_next->bip_vec[0].bv_offset); } +/** + * bio_integrity_intervals - Return number of integrity intervals for a bio + * @bi: blk_integrity profile for device + * @sectors: Size of the bio in 512-byte sectors + * + * Description: The block layer calculates everything in 512 byte + * sectors but integrity metadata is done in terms of the data integrity + * interval size of the storage device. Convert the block layer sectors + * to the appropriate number of integrity intervals. + */ +static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, + unsigned int sectors) +{ + return sectors >> (bi->interval_exp - 9); +} + +static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, + unsigned int sectors) +{ + return bio_integrity_intervals(bi, sectors) * bi->tuple_size; +} + #else /* CONFIG_BLK_DEV_INTEGRITY */ struct bio; @@ -1998,12 +1958,24 @@ static inline bool integrity_req_gap_front_merge(struct request *req, return false; } +static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, + unsigned int sectors) +{ + return 0; +} + +static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, + unsigned int sectors) +{ + 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 *, bool); + int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); unsigned int (*check_events) (struct gendisk *disk, |