diff options
Diffstat (limited to 'include/linux/blkdev.h')
| -rw-r--r-- | include/linux/blkdev.h | 188 |
1 files changed, 157 insertions, 31 deletions
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 6aa67e9b2ec0..620345ce3aaa 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -182,7 +182,6 @@ struct gendisk { struct list_head slave_bdevs; #endif struct timer_rand_state *random; - atomic_t sync_io; /* RAID */ struct disk_events *ev; #ifdef CONFIG_BLK_DEV_ZONED @@ -218,6 +217,8 @@ struct gendisk { * devices that do not have multiple independent access ranges. */ struct blk_independent_access_ranges *ia_ranges; + + struct mutex rqos_state_mutex; /* rqos state change mutex */ }; /** @@ -268,10 +269,21 @@ static inline dev_t disk_devt(struct gendisk *disk) return MKDEV(disk->major, disk->first_minor); } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* + * We should strive for 1 << (PAGE_SHIFT + MAX_PAGECACHE_ORDER) + * however we constrain this to what we can validate and test. + */ +#define BLK_MAX_BLOCK_SIZE SZ_64K +#else +#define BLK_MAX_BLOCK_SIZE PAGE_SIZE +#endif + + /* blk_validate_limits() validates bsize, so drivers don't usually need to */ static inline int blk_validate_block_size(unsigned long bsize) { - if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) + if (bsize < 512 || bsize > BLK_MAX_BLOCK_SIZE || !is_power_of_2(bsize)) return -EINVAL; return 0; @@ -325,9 +337,6 @@ typedef unsigned int __bitwise blk_features_t; /* skip this queue in blk_mq_(un)quiesce_tagset */ #define BLK_FEAT_SKIP_TAGSET_QUIESCE ((__force blk_features_t)(1u << 13)) -/* bounce all highmem pages */ -#define BLK_FEAT_BOUNCE_HIGH ((__force blk_features_t)(1u << 14)) - /* undocumented magic for bcache */ #define BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE \ ((__force blk_features_t)(1u << 15)) @@ -341,7 +350,7 @@ typedef unsigned int __bitwise blk_features_t; */ #define BLK_FEAT_INHERIT_MASK \ (BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | BLK_FEAT_ROTATIONAL | \ - BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | BLK_FEAT_BOUNCE_HIGH | \ + BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | \ BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE) /* internal flags in queue_limits.flags */ @@ -399,6 +408,9 @@ struct queue_limits { unsigned short max_integrity_segments; unsigned short max_discard_segments; + unsigned short max_write_streams; + unsigned int write_stream_granularity; + unsigned int max_open_zones; unsigned int max_active_zones; @@ -562,7 +574,22 @@ struct request_queue { struct blk_flush_queue *fq; struct list_head flush_list; + /* + * Protects against I/O scheduler switching, particularly when updating + * q->elevator. Since the elevator update code path may also modify q-> + * nr_requests and wbt latency, this lock also protects the sysfs attrs + * nr_requests and wbt_lat_usec. Additionally the nr_hw_queues update + * may modify hctx tags, reserved-tags and cpumask, so this lock also + * helps protect the hctx sysfs/debugfs attrs. To ensure proper locking + * order during an elevator or nr_hw_queue update, first freeze the + * queue, then acquire ->elevator_lock. + */ + struct mutex elevator_lock; + struct mutex sysfs_lock; + /* + * Protects queue limits and also sysfs attribute read_ahead_kb. + */ struct mutex limits_lock; /* @@ -623,6 +650,8 @@ enum { QUEUE_FLAG_RQ_ALLOC_TIME, /* record rq->alloc_time_ns */ QUEUE_FLAG_HCTX_ACTIVE, /* at least one blk-mq hctx is active */ QUEUE_FLAG_SQ_SCHED, /* single queue style io dispatch */ + QUEUE_FLAG_DISABLE_WBT_DEF, /* for sched to disable/enable wbt */ + QUEUE_FLAG_NO_ELV_SWITCH, /* can't switch elevator any more */ QUEUE_FLAG_MAX }; @@ -658,6 +687,10 @@ void blk_queue_flag_clear(unsigned int flag, struct request_queue *q); #define blk_queue_sq_sched(q) test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags) #define blk_queue_skip_tagset_quiesce(q) \ ((q)->limits.features & BLK_FEAT_SKIP_TAGSET_QUIESCE) +#define blk_queue_disable_wbt(q) \ + test_bit(QUEUE_FLAG_DISABLE_WBT_DEF, &(q)->queue_flags) +#define blk_queue_no_elv_switch(q) \ + test_bit(QUEUE_FLAG_NO_ELV_SWITCH, &(q)->queue_flags) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); @@ -691,23 +724,6 @@ static inline bool blk_queue_is_zoned(struct request_queue *q) (q->limits.features & BLK_FEAT_ZONED); } -#ifdef CONFIG_BLK_DEV_ZONED -static inline unsigned int disk_nr_zones(struct gendisk *disk) -{ - return disk->nr_zones; -} -bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs); -#else /* CONFIG_BLK_DEV_ZONED */ -static inline unsigned int disk_nr_zones(struct gendisk *disk) -{ - return 0; -} -static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) -{ - return false; -} -#endif /* CONFIG_BLK_DEV_ZONED */ - static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) { if (!blk_queue_is_zoned(disk->queue)) @@ -715,11 +731,6 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector) return sector >> ilog2(disk->queue->limits.chunk_sectors); } -static inline unsigned int bdev_nr_zones(struct block_device *bdev) -{ - return disk_nr_zones(bdev->bd_disk); -} - static inline unsigned int bdev_max_open_zones(struct block_device *bdev) { return bdev->bd_disk->queue->limits.max_open_zones; @@ -826,6 +837,106 @@ static inline u64 sb_bdev_nr_blocks(struct super_block *sb) (sb->s_blocksize_bits - SECTOR_SHIFT); } +#ifdef CONFIG_BLK_DEV_ZONED +static inline unsigned int disk_nr_zones(struct gendisk *disk) +{ + return disk->nr_zones; +} + +/** + * bio_needs_zone_write_plugging - Check if a BIO needs to be handled with zone + * write plugging + * @bio: The BIO being submitted + * + * Return true whenever @bio execution needs to be handled through zone + * write plugging (using blk_zone_plug_bio()). Return false otherwise. + */ +static inline bool bio_needs_zone_write_plugging(struct bio *bio) +{ + enum req_op op = bio_op(bio); + + /* + * Only zoned block devices have a zone write plug hash table. But not + * all of them have one (e.g. DM devices may not need one). + */ + if (!bio->bi_bdev->bd_disk->zone_wplugs_hash) + return false; + + /* Only write operations need zone write plugging. */ + if (!op_is_write(op)) + return false; + + /* Ignore empty flush */ + if (op_is_flush(bio->bi_opf) && !bio_sectors(bio)) + return false; + + /* Ignore BIOs that already have been handled by zone write plugging. */ + if (bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING)) + return false; + + /* + * All zone write operations must be handled through zone write plugging + * using blk_zone_plug_bio(). + */ + switch (op) { + case REQ_OP_ZONE_APPEND: + case REQ_OP_WRITE: + case REQ_OP_WRITE_ZEROES: + case REQ_OP_ZONE_FINISH: + case REQ_OP_ZONE_RESET: + case REQ_OP_ZONE_RESET_ALL: + return true; + default: + return false; + } +} + +bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs); + +/** + * disk_zone_capacity - returns the zone capacity of zone containing @sector + * @disk: disk to work with + * @sector: sector number within the querying zone + * + * Returns the zone capacity of a zone containing @sector. @sector can be any + * sector in the zone. + */ +static inline unsigned int disk_zone_capacity(struct gendisk *disk, + sector_t sector) +{ + sector_t zone_sectors = disk->queue->limits.chunk_sectors; + + if (sector + zone_sectors >= get_capacity(disk)) + return disk->last_zone_capacity; + return disk->zone_capacity; +} +static inline unsigned int bdev_zone_capacity(struct block_device *bdev, + sector_t pos) +{ + return disk_zone_capacity(bdev->bd_disk, pos); +} +#else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int disk_nr_zones(struct gendisk *disk) +{ + return 0; +} + +static inline bool bio_needs_zone_write_plugging(struct bio *bio) +{ + return false; +} + +static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs) +{ + return false; +} +#endif /* CONFIG_BLK_DEV_ZONED */ + +static inline unsigned int bdev_nr_zones(struct block_device *bdev) +{ + return disk_nr_zones(bdev->bd_disk); +} + int bdev_disk_changed(struct gendisk *disk, bool invalidate); void put_disk(struct gendisk *disk); @@ -1244,6 +1355,13 @@ static inline unsigned int bdev_max_segments(struct block_device *bdev) return queue_max_segments(bdev_get_queue(bdev)); } +static inline unsigned short bdev_max_write_streams(struct block_device *bdev) +{ + if (bdev_is_partition(bdev)) + return 0; + return bdev_limits(bdev)->max_write_streams; +} + static inline unsigned queue_logical_block_size(const struct request_queue *q) { return q->limits.logical_block_size; @@ -1398,6 +1516,13 @@ static inline bool bdev_is_zone_start(struct block_device *bdev, return bdev_offset_from_zone_start(bdev, sector) == 0; } +/* Check whether @sector is a multiple of the zone size. */ +static inline bool bdev_is_zone_aligned(struct block_device *bdev, + sector_t sector) +{ + return bdev_is_zone_start(bdev, sector); +} + /** * bdev_zone_is_seq - check if a sector belongs to a sequential write zone * @bdev: block device to check @@ -1593,6 +1718,7 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) return bio_end_io_acct_remapped(bio, start_time, bio->bi_bdev); } +int bdev_validate_blocksize(struct block_device *bdev, int block_size); int set_blocksize(struct file *file, int size); int lookup_bdev(const char *pathname, dev_t *dev); @@ -1660,7 +1786,7 @@ int sync_blockdev(struct block_device *bdev); int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend); int sync_blockdev_nowait(struct block_device *bdev); void sync_bdevs(bool wait); -void bdev_statx(struct path *, struct kstat *, u32); +void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask); void printk_all_partitions(void); int __init early_lookup_bdev(const char *pathname, dev_t *dev); #else @@ -1678,8 +1804,8 @@ static inline int sync_blockdev_nowait(struct block_device *bdev) static inline void sync_bdevs(bool wait) { } -static inline void bdev_statx(struct path *path, struct kstat *stat, - u32 request_mask) +static inline void bdev_statx(const struct path *path, struct kstat *stat, + u32 request_mask) { } static inline void printk_all_partitions(void) |