diff options
Diffstat (limited to 'include/linux/blkdev.h')
| -rw-r--r-- | include/linux/blkdev.h | 235 |
1 files changed, 70 insertions, 165 deletions
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 79226ca8f80f..4293dc1cd160 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; @@ -56,7 +54,7 @@ struct blk_stat_callback; * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 3 +#define BLKCG_MAX_POLS 5 typedef void (rq_end_io_fn)(struct request *, blk_status_t); @@ -110,7 +108,7 @@ typedef __u32 __bitwise req_flags_t; #define RQF_QUIET ((__force req_flags_t)(1 << 11)) /* elevator private data attached */ #define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) -/* account I/O stat */ +/* account into disk and partition IO statistics */ #define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) /* request came from our alloc pool */ #define RQF_ALLOCED ((__force req_flags_t)(1 << 14)) @@ -118,7 +116,7 @@ typedef __u32 __bitwise req_flags_t; #define RQF_PM ((__force req_flags_t)(1 << 15)) /* on IO scheduler merge hash */ #define RQF_HASHED ((__force req_flags_t)(1 << 16)) -/* IO stats tracking on */ +/* track IO completion time */ #define RQF_STATS ((__force req_flags_t)(1 << 17)) /* Look at ->special_vec for the actual data payload instead of the bio chain. */ @@ -398,16 +396,13 @@ struct queue_limits { #ifdef CONFIG_BLK_DEV_ZONED -struct blk_zone_report_hdr { - unsigned int nr_zones; - u8 padding[60]; -}; - +extern unsigned int blkdev_nr_zones(struct block_device *bdev); extern int blkdev_report_zones(struct block_device *bdev, sector_t sector, struct blk_zone *zones, unsigned int *nr_zones, gfp_t gfp_mask); extern int blkdev_reset_zones(struct block_device *bdev, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); +extern int blk_revalidate_disk_zones(struct gendisk *disk); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); @@ -416,6 +411,16 @@ extern int blkdev_reset_zones_ioctl(struct block_device *bdev, fmode_t mode, #else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int blkdev_nr_zones(struct block_device *bdev) +{ + return 0; +} + +static inline int blk_revalidate_disk_zones(struct gendisk *disk) +{ + return 0; +} + static inline int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) @@ -442,10 +447,8 @@ 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 @@ -508,6 +511,12 @@ struct request_queue { * various queue flags, see QUEUE_* below */ unsigned long queue_flags; + /* + * Number of contexts that have called blk_set_pm_only(). If this + * counter is above zero then only RQF_PM and RQF_PREEMPT requests are + * processed. + */ + atomic_t pm_only; /* * ida allocated id for this queue. Used to index queues from @@ -592,6 +601,7 @@ 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 @@ -612,6 +622,7 @@ struct request_queue { unsigned int nr_zones; unsigned long *seq_zones_bitmap; unsigned long *seq_zones_wlock; +#endif /* CONFIG_BLK_DEV_ZONED */ /* * sg stuff @@ -681,7 +692,7 @@ struct request_queue { #define QUEUE_FLAG_FAIL_IO 7 /* fake timeout */ #define QUEUE_FLAG_NONROT 9 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ -#define QUEUE_FLAG_IO_STAT 10 /* do IO stats */ +#define QUEUE_FLAG_IO_STAT 10 /* do disk/partitions IO accounting */ #define QUEUE_FLAG_DISCARD 11 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 12 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 13 /* Contributes to random pool */ @@ -695,12 +706,12 @@ struct request_queue { #define QUEUE_FLAG_FUA 21 /* device supports FUA writes */ #define QUEUE_FLAG_FLUSH_NQ 22 /* flush not queueuable */ #define QUEUE_FLAG_DAX 23 /* device supports DAX */ -#define QUEUE_FLAG_STATS 24 /* track rq completion times */ +#define QUEUE_FLAG_STATS 24 /* track IO start and completion times */ #define QUEUE_FLAG_POLL_STATS 25 /* collecting stats for hybrid polling */ #define QUEUE_FLAG_REGISTERED 26 /* queue has been registered to a disk */ #define QUEUE_FLAG_SCSI_PASSTHROUGH 27 /* queue supports SCSI commands */ #define QUEUE_FLAG_QUIESCED 28 /* queue has been quiesced */ -#define QUEUE_FLAG_PREEMPT_ONLY 29 /* only process REQ_PREEMPT requests */ +#define QUEUE_FLAG_PCI_P2PDMA 29 /* device supports PCI p2p requests */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_SAME_COMP) | \ @@ -733,17 +744,18 @@ bool blk_queue_flag_test_and_clear(unsigned int flag, struct request_queue *q); #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_scsi_passthrough(q) \ test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags) +#define blk_queue_pci_p2pdma(q) \ + test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) #define blk_noretry_request(rq) \ ((rq)->cmd_flags & (REQ_FAILFAST_DEV|REQ_FAILFAST_TRANSPORT| \ REQ_FAILFAST_DRIVER)) #define blk_queue_quiesced(q) test_bit(QUEUE_FLAG_QUIESCED, &(q)->queue_flags) -#define blk_queue_preempt_only(q) \ - test_bit(QUEUE_FLAG_PREEMPT_ONLY, &(q)->queue_flags) +#define blk_queue_pm_only(q) atomic_read(&(q)->pm_only) #define blk_queue_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) -extern int blk_set_preempt_only(struct request_queue *q); -extern void blk_clear_preempt_only(struct request_queue *q); +extern void blk_set_pm_only(struct request_queue *q); +extern void blk_clear_pm_only(struct request_queue *q); static inline int queue_in_flight(struct request_queue *q) { @@ -800,9 +812,10 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q) return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } +#ifdef CONFIG_BLK_DEV_ZONED static inline unsigned int blk_queue_nr_zones(struct request_queue *q) { - return q->nr_zones; + return blk_queue_is_zoned(q) ? q->nr_zones : 0; } static inline unsigned int blk_queue_zone_no(struct request_queue *q, @@ -820,6 +833,12 @@ 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); } +#else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int blk_queue_nr_zones(struct request_queue *q) +{ + return 0; +} +#endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) { @@ -1070,6 +1089,7 @@ 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)); @@ -1079,6 +1099,7 @@ 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 @@ -1284,29 +1305,6 @@ extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); /* - * block layer runtime pm functions - */ -#ifdef CONFIG_PM -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); -extern void blk_set_runtime_active(struct request_queue *q); -#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) {} -static inline void blk_set_runtime_active(struct request_queue *q) {} -#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 @@ -1437,8 +1435,6 @@ 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; @@ -1639,15 +1635,6 @@ 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; @@ -1690,94 +1677,6 @@ static inline void put_dev_sector(Sector p) put_page(p.v); } -static inline bool __bvec_gap_to_prev(struct request_queue *q, - struct bio_vec *bprv, unsigned int offset) -{ - return offset || - ((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q)); -} - -/* - * Check if adding a bio_vec after bprv with offset would create a gap in - * the SG list. Most drivers don't care about this, but some do. - */ -static inline bool bvec_gap_to_prev(struct request_queue *q, - struct bio_vec *bprv, unsigned int offset) -{ - if (!queue_virt_boundary(q)) - return false; - return __bvec_gap_to_prev(q, bprv, offset); -} - -/* - * Check if the two bvecs from two bios can be merged to one segment. - * If yes, no need to check gap between the two bios since the 1st bio - * and the 1st bvec in the 2nd bio can be handled in one segment. - */ -static inline bool bios_segs_mergeable(struct request_queue *q, - struct bio *prev, struct bio_vec *prev_last_bv, - struct bio_vec *next_first_bv) -{ - if (!BIOVEC_PHYS_MERGEABLE(prev_last_bv, next_first_bv)) - return false; - if (!BIOVEC_SEG_BOUNDARY(q, prev_last_bv, next_first_bv)) - return false; - if (prev->bi_seg_back_size + next_first_bv->bv_len > - queue_max_segment_size(q)) - return false; - return true; -} - -static inline bool bio_will_gap(struct request_queue *q, - struct request *prev_rq, - struct bio *prev, - struct bio *next) -{ - if (bio_has_data(prev) && queue_virt_boundary(q)) { - struct bio_vec pb, nb; - - /* - * don't merge if the 1st bio starts with non-zero - * offset, otherwise it is quite difficult to respect - * sg gap limit. We work hard to merge a huge number of small - * single bios in case of mkfs. - */ - if (prev_rq) - bio_get_first_bvec(prev_rq->bio, &pb); - else - bio_get_first_bvec(prev, &pb); - if (pb.bv_offset) - return true; - - /* - * We don't need to worry about the situation that the - * merged segment ends in unaligned virt boundary: - * - * - if 'pb' ends aligned, the merged segment ends aligned - * - if 'pb' ends unaligned, the next bio must include - * one single bvec of 'nb', otherwise the 'nb' can't - * merge with 'pb' - */ - bio_get_last_bvec(prev, &pb); - bio_get_first_bvec(next, &nb); - - if (!bios_segs_mergeable(q, prev, &pb, &nb)) - return __bvec_gap_to_prev(q, &pb, nb.bv_offset); - } - - return false; -} - -static inline bool req_gap_back_merge(struct request *req, struct bio *bio) -{ - return bio_will_gap(req->q, req, req->biotail, bio); -} - -static inline bool req_gap_front_merge(struct request *req, struct bio *bio) -{ - return bio_will_gap(req->q, NULL, bio, req->bio); -} - 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); @@ -1857,24 +1756,26 @@ queue_max_integrity_segments(struct request_queue *q) return q->limits.max_integrity_segments; } -static inline bool integrity_req_gap_back_merge(struct request *req, - struct bio *next) +/** + * 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) { - struct bio_integrity_payload *bip = bio_integrity(req->bio); - struct bio_integrity_payload *bip_next = bio_integrity(next); - - return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], - bip_next->bip_vec[0].bv_offset); + return sectors >> (bi->interval_exp - 9); } -static inline bool integrity_req_gap_front_merge(struct request *req, - struct bio *bio) +static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, + unsigned int sectors) { - struct bio_integrity_payload *bip = bio_integrity(bio); - struct bio_integrity_payload *bip_next = bio_integrity(req->bio); - - return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1], - bip_next->bip_vec[0].bv_offset); + return bio_integrity_intervals(bi, sectors) * bi->tuple_size; } #else /* CONFIG_BLK_DEV_INTEGRITY */ @@ -1939,15 +1840,16 @@ static inline bool blk_integrity_merge_bio(struct request_queue *rq, return true; } -static inline bool integrity_req_gap_back_merge(struct request *req, - struct bio *next) +static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, + unsigned int sectors) { - return false; + return 0; } -static inline bool integrity_req_gap_front_merge(struct request *req, - struct bio *bio) + +static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, + unsigned int sectors) { - return false; + return 0; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ @@ -1955,7 +1857,7 @@ static inline bool integrity_req_gap_front_merge(struct request *req, 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, @@ -1967,6 +1869,9 @@ struct block_device_operations { 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); + int (*report_zones)(struct gendisk *, sector_t sector, + struct blk_zone *zones, unsigned int *nr_zones, + gfp_t gfp_mask); struct module *owner; const struct pr_ops *pr_ops; }; |