diff options
Diffstat (limited to 'include/linux/blkdev.h')
| -rw-r--r-- | include/linux/blkdev.h | 281 |
1 files changed, 167 insertions, 114 deletions
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 87d94be7825a..69e7da33ca49 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -24,6 +24,7 @@ #include <linux/sbitmap.h> #include <linux/uuid.h> #include <linux/xarray.h> +#include <linux/file.h> struct module; struct request_queue; @@ -42,7 +43,7 @@ struct blk_crypto_profile; extern const struct device_type disk_type; extern const struct device_type part_type; -extern struct class block_class; +extern const struct class block_class; /* * Maximum number of blkcg policies allowed to be registered concurrently. @@ -108,6 +109,7 @@ struct blk_integrity { const struct blk_integrity_profile *profile; unsigned char flags; unsigned char tuple_size; + unsigned char pi_offset; unsigned char interval_exp; unsigned char tag_size; }; @@ -124,6 +126,10 @@ typedef unsigned int __bitwise blk_mode_t; #define BLK_OPEN_NDELAY ((__force blk_mode_t)(1 << 3)) /* open for "writes" only for ioctls (specialy hack for floppy.c) */ #define BLK_OPEN_WRITE_IOCTL ((__force blk_mode_t)(1 << 4)) +/* open is exclusive wrt all other BLK_OPEN_WRITE opens to the device */ +#define BLK_OPEN_RESTRICT_WRITES ((__force blk_mode_t)(1 << 5)) +/* return partition scanning errors */ +#define BLK_OPEN_STRICT_SCAN ((__force blk_mode_t)(1 << 6)) struct gendisk { /* @@ -187,8 +193,6 @@ struct gendisk { * blk_mq_unfreeze_queue(). */ unsigned int nr_zones; - unsigned int max_open_zones; - unsigned int max_active_zones; unsigned long *conv_zones_bitmap; unsigned long *seq_zones_wlock; #endif /* CONFIG_BLK_DEV_ZONED */ @@ -264,18 +268,6 @@ static inline bool blk_op_is_passthrough(blk_opf_t op) } /* - * Zoned block device models (zoned limit). - * - * Note: This needs to be ordered from the least to the most severe - * restrictions for the inheritance in blk_stack_limits() to work. - */ -enum blk_zoned_model { - BLK_ZONED_NONE = 0, /* Regular block device */ - BLK_ZONED_HA, /* Host-aware zoned block device */ - BLK_ZONED_HM, /* Host-managed zoned block device */ -}; - -/* * BLK_BOUNCE_NONE: never bounce (default) * BLK_BOUNCE_HIGH: bounce all highmem pages */ @@ -302,6 +294,7 @@ struct queue_limits { unsigned int io_opt; unsigned int max_discard_sectors; unsigned int max_hw_discard_sectors; + unsigned int max_user_discard_sectors; unsigned int max_secure_erase_sectors; unsigned int max_write_zeroes_sectors; unsigned int max_zone_append_sectors; @@ -316,7 +309,9 @@ struct queue_limits { unsigned char misaligned; unsigned char discard_misaligned; unsigned char raid_partial_stripes_expensive; - enum blk_zoned_model zoned; + bool zoned; + unsigned int max_open_zones; + unsigned int max_active_zones; /* * Drivers that set dma_alignment to less than 511 must be prepared to @@ -329,24 +324,15 @@ struct queue_limits { typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); -void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model); +void disk_set_zoned(struct gendisk *disk); -#ifdef CONFIG_BLK_DEV_ZONED #define BLK_ALL_ZONES ((unsigned int)-1) int blkdev_report_zones(struct block_device *bdev, sector_t sector, - unsigned int nr_zones, report_zones_cb cb, void *data); -unsigned int bdev_nr_zones(struct block_device *bdev); -extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, - sector_t sectors, sector_t nr_sectors, - gfp_t gfp_mask); + unsigned int nr_zones, report_zones_cb cb, void *data); +int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op, + sector_t sectors, sector_t nr_sectors); int blk_revalidate_disk_zones(struct gendisk *disk, - void (*update_driver_data)(struct gendisk *disk)); -#else /* CONFIG_BLK_DEV_ZONED */ -static inline unsigned int bdev_nr_zones(struct block_device *bdev) -{ - return 0; -} -#endif /* CONFIG_BLK_DEV_ZONED */ + void (*update_driver_data)(struct gendisk *disk)); /* * Independent access ranges: struct blk_independent_access_range describes @@ -376,59 +362,51 @@ struct blk_independent_access_ranges { }; struct request_queue { - struct request *last_merge; - struct elevator_queue *elevator; - - struct percpu_ref q_usage_counter; + /* + * The queue owner gets to use this for whatever they like. + * ll_rw_blk doesn't touch it. + */ + void *queuedata; - struct blk_queue_stats *stats; - struct rq_qos *rq_qos; - struct mutex rq_qos_mutex; + struct elevator_queue *elevator; const struct blk_mq_ops *mq_ops; /* sw queues */ struct blk_mq_ctx __percpu *queue_ctx; + /* + * various queue flags, see QUEUE_* below + */ + unsigned long queue_flags; + + unsigned int rq_timeout; + unsigned int queue_depth; + refcount_t refs; + /* hw dispatch queues */ - struct xarray hctx_table; unsigned int nr_hw_queues; + struct xarray hctx_table; - /* - * The queue owner gets to use this for whatever they like. - * ll_rw_blk doesn't touch it. - */ - void *queuedata; - - /* - * 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 requests are processed. - */ - atomic_t pm_only; + struct percpu_ref q_usage_counter; - /* - * ida allocated id for this queue. Used to index queues from - * ioctx. - */ - int id; + struct request *last_merge; spinlock_t queue_lock; - struct gendisk *disk; + int quiesce_depth; - refcount_t refs; + struct gendisk *disk; /* * mq queue kobject */ struct kobject *mq_kobj; + struct queue_limits limits; + #ifdef CONFIG_BLK_DEV_INTEGRITY struct blk_integrity integrity; #endif /* CONFIG_BLK_DEV_INTEGRITY */ @@ -439,24 +417,40 @@ struct request_queue { #endif /* - * queue settings + * Number of contexts that have called blk_set_pm_only(). If this + * counter is above zero then only RQF_PM requests are processed. */ - unsigned long nr_requests; /* Max # of requests */ + atomic_t pm_only; + + struct blk_queue_stats *stats; + struct rq_qos *rq_qos; + struct mutex rq_qos_mutex; + + /* + * ida allocated id for this queue. Used to index queues from + * ioctx. + */ + int id; unsigned int dma_pad_mask; + /* + * queue settings + */ + unsigned long nr_requests; /* Max # of requests */ + #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct blk_crypto_profile *crypto_profile; struct kobject *crypto_kobject; #endif - unsigned int rq_timeout; - struct timer_list timeout; struct work_struct timeout_work; atomic_t nr_active_requests_shared_tags; + unsigned int required_elevator_features; + struct blk_mq_tags *sched_shared_tags; struct list_head icq_list; @@ -467,11 +461,12 @@ struct request_queue { struct mutex blkcg_mutex; #endif - struct queue_limits limits; + int node; - unsigned int required_elevator_features; + spinlock_t requeue_lock; + struct list_head requeue_list; + struct delayed_work requeue_work; - int node; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace __rcu *blk_trace; #endif @@ -481,12 +476,9 @@ struct request_queue { struct blk_flush_queue *fq; struct list_head flush_list; - struct list_head requeue_list; - spinlock_t requeue_lock; - struct delayed_work requeue_work; - struct mutex sysfs_lock; struct mutex sysfs_dir_lock; + struct mutex limits_lock; /* * for reusing dead hctx instance in case of updating @@ -509,8 +501,6 @@ struct request_queue { */ struct mutex mq_freeze_lock; - int quiesce_depth; - struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; @@ -538,6 +528,7 @@ struct request_queue { #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ #define QUEUE_FLAG_SYNCHRONOUS 11 /* always completes in submit context */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ +#define QUEUE_FLAG_HW_WC 13 /* Write back caching supported */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ #define QUEUE_FLAG_STABLE_WRITES 15 /* don't modify blks until WB is done */ #define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ @@ -622,26 +613,14 @@ static inline enum rpm_status queue_rpm_status(struct request_queue *q) } #endif -static inline enum blk_zoned_model -blk_queue_zoned_model(struct request_queue *q) -{ - if (IS_ENABLED(CONFIG_BLK_DEV_ZONED)) - return q->limits.zoned; - return BLK_ZONED_NONE; -} - static inline bool blk_queue_is_zoned(struct request_queue *q) { - switch (blk_queue_zoned_model(q)) { - case BLK_ZONED_HA: - case BLK_ZONED_HM: - return true; - default: - return false; - } + return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && q->limits.zoned; } #ifdef CONFIG_BLK_DEV_ZONED +unsigned int bdev_nr_zones(struct block_device *bdev); + static inline unsigned int disk_nr_zones(struct gendisk *disk) { return blk_queue_is_zoned(disk->queue) ? disk->nr_zones : 0; @@ -666,26 +645,31 @@ static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector) static inline void disk_set_max_open_zones(struct gendisk *disk, unsigned int max_open_zones) { - disk->max_open_zones = max_open_zones; + disk->queue->limits.max_open_zones = max_open_zones; } static inline void disk_set_max_active_zones(struct gendisk *disk, unsigned int max_active_zones) { - disk->max_active_zones = max_active_zones; + disk->queue->limits.max_active_zones = max_active_zones; } static inline unsigned int bdev_max_open_zones(struct block_device *bdev) { - return bdev->bd_disk->max_open_zones; + return bdev->bd_disk->queue->limits.max_open_zones; } static inline unsigned int bdev_max_active_zones(struct block_device *bdev) { - return bdev->bd_disk->max_active_zones; + return bdev->bd_disk->queue->limits.max_active_zones; } #else /* CONFIG_BLK_DEV_ZONED */ +static inline unsigned int bdev_nr_zones(struct block_device *bdev) +{ + return 0; +} + static inline unsigned int disk_nr_zones(struct gendisk *disk) { return 0; @@ -750,7 +734,8 @@ static inline int bdev_read_only(struct block_device *bdev) } bool set_capacity_and_notify(struct gendisk *disk, sector_t size); -bool disk_force_media_change(struct gendisk *disk, unsigned int events); +void disk_force_media_change(struct gendisk *disk); +void bdev_mark_dead(struct block_device *bdev, bool surprise); void add_disk_randomness(struct gendisk *disk) __latent_entropy; void rand_initialize_disk(struct gendisk *disk); @@ -784,22 +769,26 @@ static inline u64 sb_bdev_nr_blocks(struct super_block *sb) int bdev_disk_changed(struct gendisk *disk, bool invalidate); void put_disk(struct gendisk *disk); -struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass); +struct gendisk *__blk_alloc_disk(struct queue_limits *lim, int node, + struct lock_class_key *lkclass); /** * blk_alloc_disk - allocate a gendisk structure + * @lim: queue limits to be used for this disk. * @node_id: numa node to allocate on * * Allocate and pre-initialize a gendisk structure for use with BIO based * drivers. * + * Returns an ERR_PTR on error, else the allocated disk. + * * Context: can sleep */ -#define blk_alloc_disk(node_id) \ +#define blk_alloc_disk(lim, node_id) \ ({ \ static struct lock_class_key __key; \ \ - __blk_alloc_disk(node_id, &__key); \ + __blk_alloc_disk(lim, node_id, &__key); \ }) int __register_blkdev(unsigned int major, const char *name, @@ -809,7 +798,6 @@ int __register_blkdev(unsigned int major, const char *name, void unregister_blkdev(unsigned int major, const char *name); bool disk_check_media_change(struct gendisk *disk); -int __invalidate_device(struct block_device *bdev, bool kill_dirty); void set_capacity(struct gendisk *disk, sector_t size); #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED @@ -846,6 +834,7 @@ extern const char *blk_op_str(enum req_op op); int blk_status_to_errno(blk_status_t status); blk_status_t errno_to_blk_status(int errno); +const char *blk_status_to_str(blk_status_t status); /* only poll the hardware once, don't continue until a completion was found */ #define BLK_POLL_ONESHOT (1 << 0) @@ -882,6 +871,29 @@ static inline unsigned int blk_chunk_sectors_left(sector_t offset, return chunk_sectors - (offset & (chunk_sectors - 1)); } +/** + * queue_limits_start_update - start an atomic update of queue limits + * @q: queue to update + * + * This functions starts an atomic update of the queue limits. It takes a lock + * to prevent other updates and returns a snapshot of the current limits that + * the caller can modify. The caller must call queue_limits_commit_update() + * to finish the update. + * + * Context: process context. The caller must have frozen the queue or ensured + * that there is outstanding I/O by other means. + */ +static inline struct queue_limits +queue_limits_start_update(struct request_queue *q) + __acquires(q->limits_lock) +{ + mutex_lock(&q->limits_lock); + return q->limits; +} +int queue_limits_commit_update(struct request_queue *q, + struct queue_limits *lim); +int queue_limits_set(struct request_queue *q, struct queue_limits *lim); + /* * Access functions for manipulating queue properties */ @@ -915,8 +927,8 @@ extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); 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 void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, - sector_t offset); +void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev, + sector_t offset, const char *pfx); extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); @@ -963,6 +975,7 @@ struct blk_plug { /* if ios_left is > 1, we can batch tag/rq allocations */ struct request *cached_rq; + u64 cur_ktime; unsigned short nr_ios; unsigned short rq_count; @@ -993,6 +1006,18 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async) __blk_flush_plug(plug, async); } +/* + * tsk == current here + */ +static inline void blk_plug_invalidate_ts(struct task_struct *tsk) +{ + struct blk_plug *plug = tsk->plug; + + if (plug) + plug->cur_ktime = 0; + current->flags &= ~PF_BLOCK_TS; +} + int blkdev_issue_flush(struct block_device *bdev); long nr_blockdev_pages(void); #else /* CONFIG_BLOCK */ @@ -1016,6 +1041,10 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async) { } +static inline void blk_plug_invalidate_ts(struct task_struct *tsk) +{ +} + static inline int blkdev_issue_flush(struct block_device *bdev) { return 0; @@ -1078,7 +1107,14 @@ enum blk_default_limits { BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, }; -#define BLK_DEF_MAX_SECTORS 2560u +/* + * Default upper limit for the software max_sectors limit used for + * regular file system I/O. This can be increased through sysfs. + * + * Not to be confused with the max_hw_sector limit that is entirely + * controlled by the driver, usually based on hardware limits. + */ +#define BLK_DEF_MAX_SECTORS_CAP 2560u static inline unsigned long queue_segment_boundary(const struct request_queue *q) { @@ -1257,11 +1293,6 @@ static inline bool bdev_nowait(struct block_device *bdev) return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags); } -static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) -{ - return blk_queue_zoned_model(bdev_get_queue(bdev)); -} - static inline bool bdev_is_zoned(struct block_device *bdev) { return blk_queue_is_zoned(bdev_get_queue(bdev)); @@ -1460,30 +1491,53 @@ void blkdev_show(struct seq_file *seqf, off_t offset); #endif struct blk_holder_ops { - void (*mark_dead)(struct block_device *bdev); + void (*mark_dead)(struct block_device *bdev, bool surprise); + + /* + * Sync the file system mounted on the block device. + */ + void (*sync)(struct block_device *bdev); + + /* + * Freeze the file system mounted on the block device. + */ + int (*freeze)(struct block_device *bdev); + + /* + * Thaw the file system mounted on the block device. + */ + int (*thaw)(struct block_device *bdev); }; /* + * For filesystems using @fs_holder_ops, the @holder argument passed to + * helpers used to open and claim block devices via + * bd_prepare_to_claim() must point to a superblock. + */ +extern const struct blk_holder_ops fs_holder_ops; + +/* * Return the correct open flags for blkdev_get_by_* for super block flags * as stored in sb->s_flags. */ #define sb_open_mode(flags) \ - (BLK_OPEN_READ | (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE)) + (BLK_OPEN_READ | BLK_OPEN_RESTRICT_WRITES | \ + (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE)) -struct block_device *blkdev_get_by_dev(dev_t dev, blk_mode_t mode, void *holder, +struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops); -struct block_device *blkdev_get_by_path(const char *path, blk_mode_t mode, +struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode, void *holder, const struct blk_holder_ops *hops); int bd_prepare_to_claim(struct block_device *bdev, void *holder, const struct blk_holder_ops *hops); void bd_abort_claiming(struct block_device *bdev, void *holder); -void blkdev_put(struct block_device *bdev, void *holder); /* just for blk-cgroup, don't use elsewhere */ struct block_device *blkdev_get_no_open(dev_t dev); void blkdev_put_no_open(struct block_device *bdev); struct block_device *I_BDEV(struct inode *inode); +struct block_device *file_bdev(struct file *bdev_file); #ifdef CONFIG_BLOCK void invalidate_bdev(struct block_device *bdev); @@ -1521,10 +1575,9 @@ static inline int early_lookup_bdev(const char *pathname, dev_t *dev) } #endif /* CONFIG_BLOCK */ -int fsync_bdev(struct block_device *bdev); - -int freeze_bdev(struct block_device *bdev); -int thaw_bdev(struct block_device *bdev); +int bdev_freeze(struct block_device *bdev); +int bdev_thaw(struct block_device *bdev); +void bdev_fput(struct file *bdev_file); struct io_comp_batch { struct request *req_list; |