diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-01 10:39:57 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-05-01 10:39:57 -0700 |
commit | 694752922b12bd318aa80191bd9d8c3dcfb39055 (patch) | |
tree | 5afe83fd99100bea546dd5a1c1f778c58f41e5c0 /include/linux/blkdev.h | |
parent | a351e9b9fc24e982ec2f0e76379a49826036da12 (diff) | |
parent | 9438b3e080beccf6022138ea62192d55cc7dc4ed (diff) | |
download | linux-694752922b12bd318aa80191bd9d8c3dcfb39055.tar.gz linux-694752922b12bd318aa80191bd9d8c3dcfb39055.tar.xz |
Merge branch 'for-4.12/block' of git://git.kernel.dk/linux-block
Pull block layer updates from Jens Axboe:
- Add BFQ IO scheduler under the new blk-mq scheduling framework. BFQ
was initially a fork of CFQ, but subsequently changed to implement
fairness based on B-WF2Q+, a modified variant of WF2Q. BFQ is meant
to be used on desktop type single drives, providing good fairness.
From Paolo.
- Add Kyber IO scheduler. This is a full multiqueue aware scheduler,
using a scalable token based algorithm that throttles IO based on
live completion IO stats, similary to blk-wbt. From Omar.
- A series from Jan, moving users to separately allocated backing
devices. This continues the work of separating backing device life
times, solving various problems with hot removal.
- A series of updates for lightnvm, mostly from Javier. Includes a
'pblk' target that exposes an open channel SSD as a physical block
device.
- A series of fixes and improvements for nbd from Josef.
- A series from Omar, removing queue sharing between devices on mostly
legacy drivers. This helps us clean up other bits, if we know that a
queue only has a single device backing. This has been overdue for
more than a decade.
- Fixes for the blk-stats, and improvements to unify the stats and user
windows. This both improves blk-wbt, and enables other users to
register a need to receive IO stats for a device. From Omar.
- blk-throttle improvements from Shaohua. This provides a scalable
framework for implementing scalable priotization - particularly for
blk-mq, but applicable to any type of block device. The interface is
marked experimental for now.
- Bucketized IO stats for IO polling from Stephen Bates. This improves
efficiency of polled workloads in the presence of mixed block size
IO.
- A few fixes for opal, from Scott.
- A few pulls for NVMe, including a lot of fixes for NVMe-over-fabrics.
From a variety of folks, mostly Sagi and James Smart.
- A series from Bart, improving our exposed info and capabilities from
the blk-mq debugfs support.
- A series from Christoph, cleaning up how handle WRITE_ZEROES.
- A series from Christoph, cleaning up the block layer handling of how
we track errors in a request. On top of being a nice cleanup, it also
shrinks the size of struct request a bit.
- Removal of mg_disk and hd (sorry Linus) by Christoph. The former was
never used by platforms, and the latter has outlived it's usefulness.
- Various little bug fixes and cleanups from a wide variety of folks.
* 'for-4.12/block' of git://git.kernel.dk/linux-block: (329 commits)
block: hide badblocks attribute by default
blk-mq: unify hctx delay_work and run_work
block: add kblock_mod_delayed_work_on()
blk-mq: unify hctx delayed_run_work and run_work
nbd: fix use after free on module unload
MAINTAINERS: bfq: Add Paolo as maintainer for the BFQ I/O scheduler
blk-mq-sched: alloate reserved tags out of normal pool
mtip32xx: use runtime tag to initialize command header
scsi: Implement blk_mq_ops.show_rq()
blk-mq: Add blk_mq_ops.show_rq()
blk-mq: Show operation, cmd_flags and rq_flags names
blk-mq: Make blk_flags_show() callers append a newline character
blk-mq: Move the "state" debugfs attribute one level down
blk-mq: Unregister debugfs attributes earlier
blk-mq: Only unregister hctxs for which registration succeeded
blk-mq-debugfs: Rename functions for registering and unregistering the mq directory
blk-mq: Let blk_mq_debugfs_register() look up the queue name
blk-mq: Register <dev>/queue/mq after having registered <dev>/queue
ide-pm: always pass 0 error to ide_complete_rq in ide_do_devset
ide-pm: always pass 0 error to __blk_end_request_all
..
Diffstat (limited to 'include/linux/blkdev.h')
-rw-r--r-- | include/linux/blkdev.h | 76 |
1 files changed, 30 insertions, 46 deletions
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 01a696b0a4d3..83d28623645f 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -40,15 +40,20 @@ struct blkcg_gq; struct blk_flush_queue; struct pr_ops; struct rq_wb; +struct blk_queue_stats; +struct blk_stat_callback; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ +/* Must be consisitent with blk_mq_poll_stats_bkt() */ +#define BLK_MQ_POLL_STATS_BKTS 16 + /* * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 2 +#define BLKCG_MAX_POLS 3 typedef void (rq_end_io_fn)(struct request *, int); @@ -173,6 +178,7 @@ struct request { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; void *completion_data; + int error_count; /* for legacy drivers, don't use */ }; /* @@ -213,16 +219,14 @@ struct request { unsigned short ioprio; - void *special; /* opaque pointer available for LLD use */ + unsigned int timeout; - int errors; + void *special; /* opaque pointer available for LLD use */ unsigned int extra_len; /* length of alignment and padding */ unsigned long deadline; struct list_head timeout_list; - unsigned int timeout; - int retries; /* * completion callback. @@ -337,7 +341,6 @@ struct queue_limits { unsigned char misaligned; unsigned char discard_misaligned; unsigned char cluster; - unsigned char discard_zeroes_data; unsigned char raid_partial_stripes_expensive; enum blk_zoned_model zoned; }; @@ -388,6 +391,7 @@ struct request_queue { int nr_rqs[2]; /* # allocated [a]sync rqs */ int nr_rqs_elvpriv; /* # allocated rqs w/ elvpriv */ + struct blk_queue_stats *stats; struct rq_wb *rq_wb; /* @@ -505,8 +509,6 @@ struct request_queue { unsigned int nr_sorted; unsigned int in_flight[2]; - struct blk_rq_stat rq_stats[2]; - /* * Number of active block driver functions for which blk_drain_queue() * must wait. Must be incremented around functions that unlock the @@ -516,6 +518,10 @@ struct request_queue { unsigned int rq_timeout; int poll_nsec; + + struct blk_stat_callback *poll_cb; + struct blk_rq_stat poll_stat[BLK_MQ_POLL_STATS_BKTS]; + struct timer_list timeout; struct work_struct timeout_work; struct list_head timeout_list; @@ -610,6 +616,8 @@ struct request_queue { #define QUEUE_FLAG_FLUSH_NQ 25 /* flush not queueuable */ #define QUEUE_FLAG_DAX 26 /* device supports DAX */ #define QUEUE_FLAG_STATS 27 /* track rq completion times */ +#define QUEUE_FLAG_POLL_STATS 28 /* collecting stats for hybrid polling */ +#define QUEUE_FLAG_REGISTERED 29 /* queue has been registered to a disk */ #define QUEUE_FLAG_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << QUEUE_FLAG_STACKABLE) | \ @@ -918,6 +926,7 @@ extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); extern blk_qc_t generic_make_request(struct bio *bio); 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(struct request_queue *, int, gfp_t); @@ -963,7 +972,7 @@ extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, uns extern int blk_rq_map_user_iov(struct request_queue *, struct request *, struct rq_map_data *, const struct iov_iter *, gfp_t); -extern int blk_execute_rq(struct request_queue *, struct gendisk *, +extern void 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 *); @@ -1081,20 +1090,6 @@ static inline unsigned int blk_rq_count_bios(struct request *rq) } /* - * blk_rq_set_prio - associate a request with prio from ioc - * @rq: request of interest - * @ioc: target iocontext - * - * Assocate request prio with ioc prio so request based drivers - * can leverage priority information. - */ -static inline void blk_rq_set_prio(struct request *rq, struct io_context *ioc) -{ - if (ioc) - rq->ioprio = ioc->ioprio; -} - -/* * Request issue related functions. */ extern struct request *blk_peek_request(struct request_queue *q); @@ -1120,13 +1115,10 @@ 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); extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); @@ -1329,23 +1321,27 @@ 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 *, gfp_t, sector_t *); +extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, + sector_t nr_sects, gfp_t gfp_mask, struct page *page); #define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ -#define BLKDEV_DISCARD_ZERO (1 << 1) /* must reliably zero data */ -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_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, int flags, struct bio **biop); -extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, struct page *page); + +#define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ +#define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ + extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct bio **biop, - bool discard); + unsigned flags); extern int blkdev_issue_zeroout(struct block_device *bdev, sector_t sector, - sector_t nr_sects, gfp_t gfp_mask, bool discard); + sector_t nr_sects, gfp_t gfp_mask, unsigned flags); + static inline int sb_issue_discard(struct super_block *sb, sector_t block, sector_t nr_blocks, gfp_t gfp_mask, unsigned long flags) { @@ -1359,7 +1355,7 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block, return blkdev_issue_zeroout(sb->s_bdev, block << (sb->s_blocksize_bits - 9), nr_blocks << (sb->s_blocksize_bits - 9), - gfp_mask, true); + gfp_mask, 0); } extern int blk_verify_command(unsigned char *cmd, fmode_t has_write_perm); @@ -1529,19 +1525,6 @@ static inline int bdev_discard_alignment(struct block_device *bdev) 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_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); @@ -1726,6 +1709,7 @@ int kblockd_schedule_work(struct work_struct *work); int kblockd_schedule_work_on(int cpu, 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); +int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay); #ifdef CONFIG_BLK_CGROUP /* |