From 764b23bd9af8ff8ecc664816e39d4791b6a72bfd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:36 +0200 Subject: block: mark bd_finish_claiming static Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- fs/block_dev.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'fs') diff --git a/fs/block_dev.c b/fs/block_dev.c index 0ae656e022fd..0e0d43dc27d3 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1187,8 +1187,8 @@ static void bd_clear_claiming(struct block_device *whole, void *holder) * Finish exclusive open of a block device. Mark the device as exlusively * open by the holder and wake up all waiters for exclusive open to finish. */ -void bd_finish_claiming(struct block_device *bdev, struct block_device *whole, - void *holder) +static void bd_finish_claiming(struct block_device *bdev, + struct block_device *whole, void *holder) { spin_lock(&bdev_lock); BUG_ON(!bd_may_claim(bdev, whole, holder)); @@ -1203,7 +1203,6 @@ void bd_finish_claiming(struct block_device *bdev, struct block_device *whole, bd_clear_claiming(whole, holder); spin_unlock(&bdev_lock); } -EXPORT_SYMBOL(bd_finish_claiming); /** * bd_abort_claiming - abort claiming of a block device -- cgit v1.2.3 From 3f1266f1f82d7b8c72472a8921e80aa3e611fb62 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:41 +0200 Subject: block: move block-related definitions out of fs.h Move most of the block related definition out of fs.h into more suitable headers. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/affs/file.c | 1 + fs/hfs/inode.c | 1 + fs/internal.h | 17 ++++++++- fs/ntfs/dir.c | 1 + fs/proc/devices.c | 1 + fs/quota/dquot.c | 1 + fs/reiserfs/procfs.c | 1 + include/linux/blkdev.h | 46 +++++++++++++++++++++++ include/linux/fs.h | 92 ---------------------------------------------- include/linux/genhd.h | 27 ++++++++++++++ include/linux/jbd2.h | 1 + security/loadpin/loadpin.c | 1 + 12 files changed, 96 insertions(+), 94 deletions(-) (limited to 'fs') diff --git a/fs/affs/file.c b/fs/affs/file.c index a85817f54483..a26a0f96c119 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -14,6 +14,7 @@ */ #include +#include #include "affs.h" static struct buffer_head *affs_get_extblock_slow(struct inode *inode, u32 ext); diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index 2f224b98ee94..f35a37c65e5f 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -17,6 +17,7 @@ #include #include #include +#include #include "hfs_fs.h" #include "btree.h" diff --git a/fs/internal.h b/fs/internal.h index 9b863a7bd708..969988d3d397 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -23,7 +23,9 @@ struct user_namespace; extern void __init bdev_cache_init(void); extern int __sync_blockdev(struct block_device *bdev, int wait); - +void iterate_bdevs(void (*)(struct block_device *, void *), void *); +void emergency_thaw_bdev(struct super_block *sb); +void bd_forget(struct inode *inode); #else static inline void bdev_cache_init(void) { @@ -33,7 +35,18 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait) { return 0; } -#endif +static inline void iterate_bdevs(void (*f)(struct block_device *, void *), + void *arg) +{ +} +static inline int emergency_thaw_bdev(struct super_block *sb) +{ + return 0; +} +static inline void bd_forget(struct inode *inode) +{ +} +#endif /* CONFIG_BLOCK */ /* * buffer.c diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index 3c4811469ae8..a87d4391e6b5 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -8,6 +8,7 @@ #include #include +#include #include "dir.h" #include "aops.h" diff --git a/fs/proc/devices.c b/fs/proc/devices.c index 37d38697eaf8..837971e74109 100644 --- a/fs/proc/devices.c +++ b/fs/proc/devices.c @@ -3,6 +3,7 @@ #include #include #include +#include static int devinfo_show(struct seq_file *f, void *v) { diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c index 7b4bac91146b..bb02989d92b6 100644 --- a/fs/quota/dquot.c +++ b/fs/quota/dquot.c @@ -78,6 +78,7 @@ #include #include #include +#include #include "../internal.h" /* ugh */ #include diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c index ff336513c254..155b82870333 100644 --- a/fs/reiserfs/procfs.c +++ b/fs/reiserfs/procfs.c @@ -15,6 +15,7 @@ #include "reiserfs.h" #include #include +#include /* * LOCKING: diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c0701237116d..cf8f692f62a9 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1918,4 +1918,50 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) } #endif /* CONFIG_BLOCK */ +int bdev_read_only(struct block_device *bdev); +int set_blocksize(struct block_device *bdev, int size); + +const char *bdevname(struct block_device *bdev, char *buffer); +struct block_device *lookup_bdev(const char *); + +void blkdev_show(struct seq_file *seqf, off_t offset); + +#define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ +#define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ +#ifdef CONFIG_BLOCK +#define BLKDEV_MAJOR_MAX 512 +#else +#define BLKDEV_MAJOR_MAX 0 +#endif + +int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); +struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, + void *holder); +struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); +struct block_device *bd_start_claiming(struct block_device *bdev, void *holder); +void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, + void *holder); +void blkdev_put(struct block_device *bdev, fmode_t mode); + +struct block_device *bdget(dev_t); +struct block_device *bdgrab(struct block_device *bdev); +void bdput(struct block_device *); + +#ifdef CONFIG_BLOCK +void invalidate_bdev(struct block_device *bdev); +int sync_blockdev(struct block_device *bdev); +#else +static inline void invalidate_bdev(struct block_device *bdev) +{ +} +static inline int sync_blockdev(struct block_device *bdev) +{ + return 0; +} #endif +int fsync_bdev(struct block_device *bdev); + +struct super_block *freeze_bdev(struct block_device *bdev); +int thaw_bdev(struct block_device *bdev, struct super_block *sb); + +#endif /* _LINUX_BLKDEV_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 7f3ae38335d4..add30c3bdf9a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2563,79 +2563,10 @@ static inline bool sb_is_blkdev_sb(struct super_block *sb) return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; } -#ifdef CONFIG_BLOCK -extern int register_blkdev(unsigned int, const char *); -extern void unregister_blkdev(unsigned int, const char *); -extern struct block_device *bdget(dev_t); -extern struct block_device *bdgrab(struct block_device *bdev); -extern void bd_set_size(struct block_device *, loff_t size); -extern void bd_forget(struct inode *inode); -extern void bdput(struct block_device *); -extern void invalidate_bdev(struct block_device *); -extern void iterate_bdevs(void (*)(struct block_device *, void *), void *); -extern int sync_blockdev(struct block_device *bdev); -extern struct super_block *freeze_bdev(struct block_device *); -extern void emergency_thaw_bdev(struct super_block *sb); -extern int thaw_bdev(struct block_device *bdev, struct super_block *sb); -extern int fsync_bdev(struct block_device *); -#else -static inline void bd_forget(struct inode *inode) {} -static inline int sync_blockdev(struct block_device *bdev) { return 0; } -static inline void invalidate_bdev(struct block_device *bdev) {} - -static inline struct super_block *freeze_bdev(struct block_device *sb) -{ - return NULL; -} - -static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb) -{ - return 0; -} - -static inline int emergency_thaw_bdev(struct super_block *sb) -{ - return 0; -} - -static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg) -{ -} -#endif void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; extern const struct file_operations def_chr_fops; -#ifdef CONFIG_BLOCK -extern int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); -extern long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); -extern int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); -extern struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, - void *holder); -extern struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, - void *holder); -extern struct block_device *bd_start_claiming(struct block_device *bdev, - void *holder); -extern void bd_abort_claiming(struct block_device *bdev, - struct block_device *whole, void *holder); -extern void blkdev_put(struct block_device *bdev, fmode_t mode); - -#ifdef CONFIG_SYSFS -extern int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); -extern void bd_unlink_disk_holder(struct block_device *bdev, - struct gendisk *disk); -#else -static inline int bd_link_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ - return 0; -} -static inline void bd_unlink_disk_holder(struct block_device *bdev, - struct gendisk *disk) -{ -} -#endif -#endif /* fs/char_dev.c */ #define CHRDEV_MAJOR_MAX 512 @@ -2666,31 +2597,12 @@ static inline void unregister_chrdev(unsigned int major, const char *name) __unregister_chrdev(major, 0, 256, name); } -/* fs/block_dev.c */ -#define BDEVNAME_SIZE 32 /* Largest string for a blockdev identifier */ -#define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ - -#ifdef CONFIG_BLOCK -#define BLKDEV_MAJOR_MAX 512 -extern const char *bdevname(struct block_device *bdev, char *buffer); -extern struct block_device *lookup_bdev(const char *); -extern void blkdev_show(struct seq_file *,off_t); - -#else -#define BLKDEV_MAJOR_MAX 0 -#endif - extern void init_special_inode(struct inode *, umode_t, dev_t); /* Invalid inode operations -- fs/bad_inode.c */ extern void make_bad_inode(struct inode *); extern bool is_bad_inode(struct inode *); -#ifdef CONFIG_BLOCK -extern int revalidate_disk(struct gendisk *); -extern int check_disk_change(struct block_device *); -extern int __invalidate_device(struct block_device *, bool); -#endif unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); @@ -3090,10 +3002,6 @@ static inline void remove_inode_hash(struct inode *inode) extern void inode_sb_list_add(struct inode *inode); -#ifdef CONFIG_BLOCK -extern int bdev_read_only(struct block_device *); -#endif -extern int set_blocksize(struct block_device *, int); extern int sb_set_blocksize(struct super_block *, int); extern int sb_min_blocksize(struct super_block *, int); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 392aad5e29a2..83f8e0d83228 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -373,6 +373,33 @@ extern void blk_unregister_region(dev_t devt, unsigned long range); #define alloc_disk(minors) alloc_disk_node(minors, NUMA_NO_NODE) +int register_blkdev(unsigned int major, const char *name); +void unregister_blkdev(unsigned int major, const char *name); + +int revalidate_disk(struct gendisk *disk); +int check_disk_change(struct block_device *bdev); +int __invalidate_device(struct block_device *bdev, bool kill_dirty); +void bd_set_size(struct block_device *bdev, loff_t size); + +/* for drivers/char/raw.c: */ +int blkdev_ioctl(struct block_device *, fmode_t, unsigned, unsigned long); +long compat_blkdev_ioctl(struct file *, unsigned, unsigned long); + +#ifdef CONFIG_SYSFS +int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk); +void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk); +#else +static inline int bd_link_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ + return 0; +} +static inline void bd_unlink_disk_holder(struct block_device *bdev, + struct gendisk *disk) +{ +} +#endif /* CONFIG_SYSFS */ + #else /* CONFIG_BLOCK */ static inline void printk_all_partitions(void) { } diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d56128df2aff..4aaa29772bb0 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -27,6 +27,7 @@ #include #include #include +#include #include #endif diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c index ee5cb944f4ad..670a1aebb8a1 100644 --- a/security/loadpin/loadpin.c +++ b/security/loadpin/loadpin.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include /* current */ #include -- cgit v1.2.3 From 621c1f42945e76015c3a585e7a9fe6e71665eba0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:44 +0200 Subject: block: move struct block_device to blk_types.h Move the struct block_device definition together with most of the block layer definitions, as it has nothing to do with the rest of fs.h. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/adfs/super.c | 1 + fs/befs/linuxvfs.c | 1 + fs/efs/super.c | 1 + fs/jfs/jfs_mount.c | 1 + fs/jfs/resize.c | 1 + include/linux/blk_types.h | 39 ++++++++++++++++++++++++++++++++++++++- include/linux/blkdev.h | 1 + include/linux/dasd_mod.h | 2 ++ include/linux/fs.h | 41 ----------------------------------------- 9 files changed, 46 insertions(+), 42 deletions(-) (limited to 'fs') diff --git a/fs/adfs/super.c b/fs/adfs/super.c index a3cc8ecb50da..d553bb5bc17a 100644 --- a/fs/adfs/super.c +++ b/fs/adfs/super.c @@ -12,6 +12,7 @@ #include #include #include +#include #include "adfs.h" #include "dir_f.h" #include "dir_fplus.h" diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 64cdf4d8e424..2482032021ca 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "befs.h" #include "btree.h" diff --git a/fs/efs/super.c b/fs/efs/super.c index 4a6ebff2af76..a4a945d0ac6a 100644 --- a/fs/efs/super.c +++ b/fs/efs/super.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "efs.h" #include diff --git a/fs/jfs/jfs_mount.c b/fs/jfs/jfs_mount.c index eb8b9e233d73..2935d4c776ec 100644 --- a/fs/jfs/jfs_mount.c +++ b/fs/jfs/jfs_mount.c @@ -36,6 +36,7 @@ #include #include +#include #include "jfs_incore.h" #include "jfs_filsys.h" diff --git a/fs/jfs/resize.c b/fs/jfs/resize.c index 66acea9d878b..bde787c354fc 100644 --- a/fs/jfs/resize.c +++ b/fs/jfs/resize.c @@ -6,6 +6,7 @@ #include #include #include +#include #include "jfs_incore.h" #include "jfs_filsys.h" #include "jfs_metapage.h" diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index ccb895f911b1..a602132cbe32 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -14,12 +14,49 @@ struct bio_set; struct bio; struct bio_integrity_payload; struct page; -struct block_device; struct io_context; struct cgroup_subsys_state; typedef void (bio_end_io_t) (struct bio *); struct bio_crypt_ctx; +struct block_device { + dev_t bd_dev; /* not a kdev_t - it's a search key */ + int bd_openers; + struct inode * bd_inode; /* will die */ + struct super_block * bd_super; + struct mutex bd_mutex; /* open/close mutex */ + void * bd_claiming; + void * bd_holder; + int bd_holders; + bool bd_write_holder; +#ifdef CONFIG_SYSFS + struct list_head bd_holder_disks; +#endif + struct block_device * bd_contains; + unsigned bd_block_size; + u8 bd_partno; + struct hd_struct * bd_part; + /* number of times partitions within this device have been opened. */ + unsigned bd_part_count; + int bd_invalidated; + struct gendisk * bd_disk; + struct request_queue * bd_queue; + struct backing_dev_info *bd_bdi; + struct list_head bd_list; + /* + * Private data. You must have bd_claim'ed the block_device + * to use this. NOTE: bd_claim allows an owner to claim + * the same device multiple times, the owner must take special + * care to not mess up bd_private for that case. + */ + unsigned long bd_private; + + /* The counter of freeze processes */ + int bd_fsfreeze_count; + /* Mutex for freeze */ + struct mutex bd_fsfreeze_mutex; +} __randomize_layout; + /* * Block error status values. See block/blk-core:blk_errors for the details. * Alpha cannot write a byte atomically, so we need to use 32-bit value. diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index f788bddc9219..15497782c176 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1930,6 +1930,7 @@ void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, void *holder); void blkdev_put(struct block_device *bdev, fmode_t mode); +struct block_device *I_BDEV(struct inode *inode); struct block_device *bdget(dev_t); struct block_device *bdgrab(struct block_device *bdev); void bdput(struct block_device *); diff --git a/include/linux/dasd_mod.h b/include/linux/dasd_mod.h index d39abad2ff6e..14e6cf8c6267 100644 --- a/include/linux/dasd_mod.h +++ b/include/linux/dasd_mod.h @@ -4,6 +4,8 @@ #include +struct gendisk; + extern int dasd_biodasdinfo(struct gendisk *disk, dasd_information2_t *info); #endif diff --git a/include/linux/fs.h b/include/linux/fs.h index add30c3bdf9a..1d7c4f7465d2 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -470,45 +470,6 @@ struct address_space { * must be enforced here for CRIS, to let the least significant bit * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON. */ -struct request_queue; - -struct block_device { - dev_t bd_dev; /* not a kdev_t - it's a search key */ - int bd_openers; - struct inode * bd_inode; /* will die */ - struct super_block * bd_super; - struct mutex bd_mutex; /* open/close mutex */ - void * bd_claiming; - void * bd_holder; - int bd_holders; - bool bd_write_holder; -#ifdef CONFIG_SYSFS - struct list_head bd_holder_disks; -#endif - struct block_device * bd_contains; - unsigned bd_block_size; - u8 bd_partno; - struct hd_struct * bd_part; - /* number of times partitions within this device have been opened. */ - unsigned bd_part_count; - int bd_invalidated; - struct gendisk * bd_disk; - struct request_queue * bd_queue; - struct backing_dev_info *bd_bdi; - struct list_head bd_list; - /* - * Private data. You must have bd_claim'ed the block_device - * to use this. NOTE: bd_claim allows an owner to claim - * the same device multiple times, the owner must take special - * care to not mess up bd_private for that case. - */ - unsigned long bd_private; - - /* The counter of freeze processes */ - int bd_fsfreeze_count; - /* Mutex for freeze */ - struct mutex bd_fsfreeze_mutex; -} __randomize_layout; /* XArray tags, for tagging dirty and writeback pages in the pagecache. */ #define PAGECACHE_TAG_DIRTY XA_MARK_0 @@ -907,8 +868,6 @@ static inline unsigned imajor(const struct inode *inode) return MAJOR(inode->i_rdev); } -extern struct block_device *I_BDEV(struct inode *inode); - struct fown_struct { rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ -- cgit v1.2.3 From ed9b3196d2b26b5bd3a7e2cd4aec8e389d991fd8 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 10:59:38 +0200 Subject: fs: remove a weird comment in submit_bh_wbc All bios can get remapped if submitted to partitions. No need to comment on that. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/buffer.c | 5 ----- 1 file changed, 5 deletions(-) (limited to 'fs') diff --git a/fs/buffer.c b/fs/buffer.c index 64fe82ec65ff..2725ebbcfdc2 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3040,12 +3040,7 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, if (test_set_buffer_req(bh) && (op == REQ_OP_WRITE)) clear_buffer_write_io_error(bh); - /* - * from here on down, it's all bio -- do the initial mapping, - * submit_bio -> generic_make_request may further map this bio around - */ bio = bio_alloc(GFP_NOIO, 1); - bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_write_hint = write_hint; -- cgit v1.2.3 From 5ff9f19231a0e670b3d79c563f1b0b185abeca91 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Jun 2020 10:01:54 +0200 Subject: block: simplify set_init_blocksize The loop to increase the initial block size doesn't really make any sense, as the AND operation won't match for powers of two if it didn't for the initial block size. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/block_dev.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'fs') diff --git a/fs/block_dev.c b/fs/block_dev.c index 0e0d43dc27d3..8b7a9c76d33e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -106,13 +106,7 @@ EXPORT_SYMBOL(invalidate_bdev); static void set_init_blocksize(struct block_device *bdev) { unsigned bsize = bdev_logical_block_size(bdev); - loff_t size = i_size_read(bdev->bd_inode); - while (bsize < PAGE_SIZE) { - if (size & bsize) - break; - bsize <<= 1; - } bdev->bd_block_size = bsize; bdev->bd_inode->i_blkbits = blksize_bits(bsize); } -- cgit v1.2.3 From 6b7b181b67aa8177e57732723106a0411570a86d Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Jun 2020 10:01:55 +0200 Subject: block: remove the bd_block_size field from struct block_device We can trivially calculate the block size from the inodes i_blkbits variable. Use that instead of keeping two redundant copies of the information in slightly different formats. Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/block_dev.c | 9 ++------- include/linux/blk_types.h | 1 - include/linux/blkdev.h | 2 +- 3 files changed, 3 insertions(+), 9 deletions(-) (limited to 'fs') diff --git a/fs/block_dev.c b/fs/block_dev.c index 8b7a9c76d33e..06d31e459048 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -105,10 +105,7 @@ EXPORT_SYMBOL(invalidate_bdev); static void set_init_blocksize(struct block_device *bdev) { - unsigned bsize = bdev_logical_block_size(bdev); - - bdev->bd_block_size = bsize; - bdev->bd_inode->i_blkbits = blksize_bits(bsize); + bdev->bd_inode->i_blkbits = blksize_bits(bdev_logical_block_size(bdev)); } int set_blocksize(struct block_device *bdev, int size) @@ -122,9 +119,8 @@ int set_blocksize(struct block_device *bdev, int size) return -EINVAL; /* Don't change the size if it is same as current */ - if (bdev->bd_block_size != size) { + if (bdev->bd_inode->i_blkbits != blksize_bits(size)) { sync_blockdev(bdev); - bdev->bd_block_size = size; bdev->bd_inode->i_blkbits = blksize_bits(size); kill_bdev(bdev); } @@ -889,7 +885,6 @@ struct block_device *bdget(dev_t dev) bdev->bd_contains = NULL; bdev->bd_super = NULL; bdev->bd_inode = inode; - bdev->bd_block_size = i_blocksize(inode); bdev->bd_part_count = 0; bdev->bd_invalidated = 0; inode->i_mode = S_IFBLK; diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index a602132cbe32..b01cd19bbe8a 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -33,7 +33,6 @@ struct block_device { struct list_head bd_holder_disks; #endif struct block_device * bd_contains; - unsigned bd_block_size; u8 bd_partno; struct hd_struct * bd_part; /* number of times partitions within this device have been opened. */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 1cc913ffdbe2..408eb66a82fd 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1543,7 +1543,7 @@ static inline unsigned int blksize_bits(unsigned int size) static inline unsigned int block_size(struct block_device *bdev) { - return bdev->bd_block_size; + return 1 << bdev->bd_inode->i_blkbits; } int kblockd_schedule_work(struct work_struct *work); -- cgit v1.2.3 From e556f6ba10f0f3c3484a1597382ceaec1e7bc700 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Jun 2020 10:01:56 +0200 Subject: block: remove the bd_queue field from struct block_device Just use bd_disk->queue instead. Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- drivers/dax/super.c | 2 +- drivers/md/md.c | 2 +- drivers/nvme/target/core.c | 2 +- fs/block_dev.c | 11 ++++------- fs/direct-io.c | 4 ++-- fs/xfs/xfs_pwork.c | 2 +- include/linux/blk_types.h | 1 - mm/swapfile.c | 2 +- 8 files changed, 11 insertions(+), 15 deletions(-) (limited to 'fs') diff --git a/drivers/dax/super.c b/drivers/dax/super.c index 8e32345be0f7..f50828526331 100644 --- a/drivers/dax/super.c +++ b/drivers/dax/super.c @@ -59,7 +59,7 @@ EXPORT_SYMBOL(bdev_dax_pgoff); #if IS_ENABLED(CONFIG_FS_DAX) struct dax_device *fs_dax_get_by_bdev(struct block_device *bdev) { - if (!blk_queue_dax(bdev->bd_queue)) + if (!blk_queue_dax(bdev->bd_disk->queue)) return NULL; return dax_get_by_host(bdev->bd_disk->disk_name); } diff --git a/drivers/md/md.c b/drivers/md/md.c index 7b7cb49be351..8bb69c61afe0 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -199,7 +199,7 @@ static int rdevs_init_serial(struct mddev *mddev) static int rdev_need_serial(struct md_rdev *rdev) { return (rdev && rdev->mddev->bitmap_info.max_write_behind > 0 && - rdev->bdev->bd_queue->nr_hw_queues != 1 && + rdev->bdev->bd_disk->queue->nr_hw_queues != 1 && test_bit(WriteMostly, &rdev->flags)); } diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c index 6e2f623e472e..6816507fba58 100644 --- a/drivers/nvme/target/core.c +++ b/drivers/nvme/target/core.c @@ -467,7 +467,7 @@ static int nvmet_p2pmem_ns_enable(struct nvmet_ns *ns) return -EINVAL; } - if (!blk_queue_pci_p2pdma(ns->bdev->bd_queue)) { + if (!blk_queue_pci_p2pdma(ns->bdev->bd_disk->queue)) { pr_err("peer-to-peer DMA is not supported by the driver of %s\n", ns->device_path); return -EINVAL; diff --git a/fs/block_dev.c b/fs/block_dev.c index 06d31e459048..68cb08bc1b7a 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -693,12 +693,12 @@ int bdev_read_page(struct block_device *bdev, sector_t sector, if (!ops->rw_page || bdev_get_integrity(bdev)) return result; - result = blk_queue_enter(bdev->bd_queue, 0); + result = blk_queue_enter(bdev->bd_disk->queue, 0); if (result) return result; result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, REQ_OP_READ); - blk_queue_exit(bdev->bd_queue); + blk_queue_exit(bdev->bd_disk->queue); return result; } @@ -729,7 +729,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, if (!ops->rw_page || bdev_get_integrity(bdev)) return -EOPNOTSUPP; - result = blk_queue_enter(bdev->bd_queue, 0); + result = blk_queue_enter(bdev->bd_disk->queue, 0); if (result) return result; @@ -742,7 +742,7 @@ int bdev_write_page(struct block_device *bdev, sector_t sector, clean_page_buffers(page); unlock_page(page); } - blk_queue_exit(bdev->bd_queue); + blk_queue_exit(bdev->bd_disk->queue); return result; } @@ -1568,7 +1568,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) if (!bdev->bd_openers) { first_open = true; bdev->bd_disk = disk; - bdev->bd_queue = disk->queue; bdev->bd_contains = bdev; bdev->bd_partno = partno; @@ -1589,7 +1588,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) disk_put_part(bdev->bd_part); bdev->bd_part = NULL; bdev->bd_disk = NULL; - bdev->bd_queue = NULL; mutex_unlock(&bdev->bd_mutex); disk_unblock_events(disk); put_disk_and_module(disk); @@ -1666,7 +1664,6 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) disk_put_part(bdev->bd_part); bdev->bd_disk = NULL; bdev->bd_part = NULL; - bdev->bd_queue = NULL; if (bdev != bdev->bd_contains) __blkdev_put(bdev->bd_contains, mode, 1); bdev->bd_contains = NULL; diff --git a/fs/direct-io.c b/fs/direct-io.c index 6d5370eac2a8..183299892465 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1387,8 +1387,8 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, * Attempt to prefetch the pieces we likely need later. */ prefetch(&bdev->bd_disk->part_tbl); - prefetch(bdev->bd_queue); - prefetch((char *)bdev->bd_queue + SMP_CACHE_BYTES); + prefetch(bdev->bd_disk->queue); + prefetch((char *)bdev->bd_disk->queue + SMP_CACHE_BYTES); return do_blockdev_direct_IO(iocb, inode, bdev, iter, get_block, end_io, submit_io, flags); diff --git a/fs/xfs/xfs_pwork.c b/fs/xfs/xfs_pwork.c index 4bcc3e61056c..b03333f1c84a 100644 --- a/fs/xfs/xfs_pwork.c +++ b/fs/xfs/xfs_pwork.c @@ -132,5 +132,5 @@ xfs_pwork_guess_datadev_parallelism( * For now we'll go with the most conservative setting possible, * which is two threads for an SSD and 1 thread everywhere else. */ - return blk_queue_nonrot(btp->bt_bdev->bd_queue) ? 2 : 1; + return blk_queue_nonrot(btp->bt_bdev->bd_disk->queue) ? 2 : 1; } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index b01cd19bbe8a..667cd365fd04 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -39,7 +39,6 @@ struct block_device { unsigned bd_part_count; int bd_invalidated; struct gendisk * bd_disk; - struct request_queue * bd_queue; struct backing_dev_info *bd_bdi; struct list_head bd_list; /* diff --git a/mm/swapfile.c b/mm/swapfile.c index 987276c557d1..6c26916e95fd 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2929,7 +2929,7 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) * write only restriction. Hence zoned block devices are not * suitable for swapping. Disallow them here. */ - if (blk_queue_is_zoned(p->bdev->bd_queue)) + if (blk_queue_is_zoned(p->bdev->bd_disk->queue)) return -EINVAL; p->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { -- cgit v1.2.3 From 1008fe6dc36dd87dfd02d4307f49162f0b4f1665 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Jun 2020 10:01:58 +0200 Subject: block: remove the all_bdevs list Instead just iterate over the inodes for the block device superblock. Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/block_dev.c | 22 +++++++--------------- include/linux/blk_types.h | 1 - 2 files changed, 7 insertions(+), 16 deletions(-) (limited to 'fs') diff --git a/fs/block_dev.c b/fs/block_dev.c index 68cb08bc1b7a..2d2fcb50e78e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -773,7 +773,6 @@ static void init_once(void *foo) memset(bdev, 0, sizeof(*bdev)); mutex_init(&bdev->bd_mutex); - INIT_LIST_HEAD(&bdev->bd_list); #ifdef CONFIG_SYSFS INIT_LIST_HEAD(&bdev->bd_holder_disks); #endif @@ -789,9 +788,6 @@ static void bdev_evict_inode(struct inode *inode) truncate_inode_pages_final(&inode->i_data); invalidate_inode_buffers(inode); /* is it needed here? */ clear_inode(inode); - spin_lock(&bdev_lock); - list_del_init(&bdev->bd_list); - spin_unlock(&bdev_lock); /* Detach inode from wb early as bdi_put() may free bdi->wb */ inode_detach_wb(inode); if (bdev->bd_bdi != &noop_backing_dev_info) { @@ -866,8 +862,6 @@ static int bdev_set(struct inode *inode, void *data) return 0; } -static LIST_HEAD(all_bdevs); - struct block_device *bdget(dev_t dev) { struct block_device *bdev; @@ -892,9 +886,6 @@ struct block_device *bdget(dev_t dev) inode->i_bdev = bdev; inode->i_data.a_ops = &def_blk_aops; mapping_set_gfp_mask(&inode->i_data, GFP_USER); - spin_lock(&bdev_lock); - list_add(&bdev->bd_list, &all_bdevs); - spin_unlock(&bdev_lock); unlock_new_inode(inode); } return bdev; @@ -915,13 +906,14 @@ EXPORT_SYMBOL(bdgrab); long nr_blockdev_pages(void) { - struct block_device *bdev; + struct inode *inode; long ret = 0; - spin_lock(&bdev_lock); - list_for_each_entry(bdev, &all_bdevs, bd_list) { - ret += bdev->bd_inode->i_mapping->nrpages; - } - spin_unlock(&bdev_lock); + + spin_lock(&blockdev_superblock->s_inode_list_lock); + list_for_each_entry(inode, &blockdev_superblock->s_inodes, i_sb_list) + ret += inode->i_mapping->nrpages; + spin_unlock(&blockdev_superblock->s_inode_list_lock); + return ret; } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index b5f7105806e4..07facaf62b72 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -40,7 +40,6 @@ struct block_device { int bd_invalidated; struct gendisk * bd_disk; struct backing_dev_info *bd_bdi; - struct list_head bd_list; /* The counter of freeze processes */ int bd_fsfreeze_count; -- cgit v1.2.3 From 9a3ffbbc6561ff878261727585ef8ee89bb36424 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Jul 2020 14:25:43 +0200 Subject: block: remove flush_disk flush_disk has only two callers, so open code it there. That also helps clarifying the error message for the particular case, and allows to remove setting bd_invalidated in check_disk_size_change, which will be cleared again instantly. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/block_dev.c | 30 +++++++----------------------- 1 file changed, 7 insertions(+), 23 deletions(-) (limited to 'fs') diff --git a/fs/block_dev.c b/fs/block_dev.c index 2d2fcb50e78e..a36d5b6907ea 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1347,26 +1347,6 @@ void bd_unlink_disk_holder(struct block_device *bdev, struct gendisk *disk) EXPORT_SYMBOL_GPL(bd_unlink_disk_holder); #endif -/** - * flush_disk - invalidates all buffer-cache entries on a disk - * - * @bdev: struct block device to be flushed - * @kill_dirty: flag to guide handling of dirty inodes - * - * Invalidates all buffer-cache entries on a disk. It should be called - * when a disk has been changed -- either by a media change or online - * resize. - */ -static void flush_disk(struct block_device *bdev, bool kill_dirty) -{ - if (__invalidate_device(bdev, kill_dirty)) { - printk(KERN_WARNING "VFS: busy inodes on changed media or " - "resized disk %s\n", - bdev->bd_disk ? bdev->bd_disk->disk_name : ""); - } - bdev->bd_invalidated = 1; -} - /** * check_disk_size_change - checks for disk size change and adjusts bdev size. * @disk: struct gendisk to check @@ -1391,8 +1371,9 @@ static void check_disk_size_change(struct gendisk *disk, disk->disk_name, bdev_size, disk_size); } i_size_write(bdev->bd_inode, disk_size); - if (bdev_size > disk_size) - flush_disk(bdev, false); + if (bdev_size > disk_size && __invalidate_device(bdev, false)) + pr_warn("VFS: busy inodes on resized disk %s\n", + disk->disk_name); } bdev->bd_invalidated = 0; } @@ -1451,7 +1432,10 @@ int check_disk_change(struct block_device *bdev) if (!(events & DISK_EVENT_MEDIA_CHANGE)) return 0; - flush_disk(bdev, true); + if (__invalidate_device(bdev, true)) + pr_warn("VFS: busy inodes on changed media %s\n", + disk->disk_name); + bdev->bd_invalidated = 1; if (bdops->revalidate_disk) bdops->revalidate_disk(bdev->bd_disk); return 1; -- cgit v1.2.3 From 13ab64880e80f8bcf541dcd95ddb3fd0dd861fb7 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Jul 2020 14:25:44 +0200 Subject: isofs: remove a stale comment check_disk_change isn't for consumers of the block layer, so remove the comment mentioning it. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- fs/isofs/inode.c | 3 --- 1 file changed, 3 deletions(-) (limited to 'fs') diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c index d634561f871a..78f5c96c76f3 100644 --- a/fs/isofs/inode.c +++ b/fs/isofs/inode.c @@ -612,9 +612,6 @@ static bool rootdir_empty(struct super_block *sb, unsigned long block) /* * Initialize the superblock and read the root inode. - * - * Note: a check_disk_change() has been done immediately prior - * to this call, so we don't need to check again. */ static int isofs_fill_super(struct super_block *s, void *data, int silent) { -- cgit v1.2.3 From 21cf866145047f8bfecb38ec8d2fed64464c074f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 11:06:22 +0200 Subject: writeback: remove bdi->congested_fn Except for pktdvd, the only places setting congested bits are file systems that allocate their own backing_dev_info structures. And pktdvd is a deprecated driver that isn't useful in stack setup either. So remove the dead congested_fn stacking infrastructure. Signed-off-by: Christoph Hellwig Acked-by: Song Liu Acked-by: David Sterba [axboe: fixup unused variables in bcache/request.c] Signed-off-by: Jens Axboe --- drivers/block/drbd/drbd_main.c | 59 ---------------------------------------- drivers/md/bcache/request.c | 47 -------------------------------- drivers/md/bcache/super.c | 1 - drivers/md/dm-cache-target.c | 19 ------------- drivers/md/dm-clone-target.c | 15 ---------- drivers/md/dm-era-target.c | 15 ---------- drivers/md/dm-raid.c | 12 -------- drivers/md/dm-table.c | 37 +------------------------ drivers/md/dm-thin.c | 16 ----------- drivers/md/dm.c | 33 ---------------------- drivers/md/dm.h | 1 - drivers/md/md-linear.c | 24 ---------------- drivers/md/md-multipath.c | 23 ---------------- drivers/md/md.c | 23 ---------------- drivers/md/md.h | 4 --- drivers/md/raid0.c | 16 ----------- drivers/md/raid1.c | 31 --------------------- drivers/md/raid10.c | 26 ------------------ drivers/md/raid5.c | 25 ----------------- fs/btrfs/disk-io.c | 23 ---------------- include/linux/backing-dev-defs.h | 4 --- include/linux/backing-dev.h | 4 --- include/linux/device-mapper.h | 11 -------- 23 files changed, 1 insertion(+), 468 deletions(-) (limited to 'fs') diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 7c34cc0ad8cc..cb687ccdbd96 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -2415,62 +2415,6 @@ static void drbd_cleanup(void) pr_info("module cleanup done.\n"); } -/** - * drbd_congested() - Callback for the flusher thread - * @congested_data: User data - * @bdi_bits: Bits the BDI flusher thread is currently interested in - * - * Returns 1<connection->flags)) { - r |= (1 << WB_async_congested); - /* Without good local data, we would need to read from remote, - * and that would need the worker thread as well, which is - * currently blocked waiting for that usermode helper to - * finish. - */ - if (!get_ldev_if_state(device, D_UP_TO_DATE)) - r |= (1 << WB_sync_congested); - else - put_ldev(device); - r &= bdi_bits; - reason = 'c'; - goto out; - } - - if (get_ldev(device)) { - q = bdev_get_queue(device->ldev->backing_bdev); - r = bdi_congested(q->backing_dev_info, bdi_bits); - put_ldev(device); - if (r) - reason = 'b'; - } - - if (bdi_bits & (1 << WB_async_congested) && - test_bit(NET_CONGESTED, &first_peer_device(device)->connection->flags)) { - r |= (1 << WB_async_congested); - reason = reason == 'b' ? 'a' : 'n'; - } - -out: - device->congestion_reason = reason; - return r; -} - static void drbd_init_workqueue(struct drbd_work_queue* wq) { spin_lock_init(&wq->q_lock); @@ -2825,9 +2769,6 @@ enum drbd_ret_code drbd_create_device(struct drbd_config_context *adm_ctx, unsig /* we have no partitions. we contain only ourselves. */ device->this_bdev->bd_contains = device->this_bdev; - q->backing_dev_info->congested_fn = drbd_congested; - q->backing_dev_info->congested_data = device; - blk_queue_write_cache(q, true, true); /* Setting the max_hw_sectors to an odd value of 8kibyte here This triggers a max_bio_size message upon first attach or connect */ diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c index dd012ebface0..a190bf47076d 100644 --- a/drivers/md/bcache/request.c +++ b/drivers/md/bcache/request.c @@ -1228,36 +1228,8 @@ static int cached_dev_ioctl(struct bcache_device *d, fmode_t mode, return __blkdev_driver_ioctl(dc->bdev, mode, cmd, arg); } -static int cached_dev_congested(void *data, int bits) -{ - struct bcache_device *d = data; - struct cached_dev *dc = container_of(d, struct cached_dev, disk); - struct request_queue *q = bdev_get_queue(dc->bdev); - int ret = 0; - - if (bdi_congested(q->backing_dev_info, bits)) - return 1; - - if (cached_dev_get(dc)) { - unsigned int i; - struct cache *ca; - - for_each_cache(ca, d->c, i) { - q = bdev_get_queue(ca->bdev); - ret |= bdi_congested(q->backing_dev_info, bits); - } - - cached_dev_put(dc); - } - - return ret; -} - void bch_cached_dev_request_init(struct cached_dev *dc) { - struct gendisk *g = dc->disk.disk; - - g->queue->backing_dev_info->congested_fn = cached_dev_congested; dc->disk.cache_miss = cached_dev_cache_miss; dc->disk.ioctl = cached_dev_ioctl; } @@ -1341,27 +1313,8 @@ static int flash_dev_ioctl(struct bcache_device *d, fmode_t mode, return -ENOTTY; } -static int flash_dev_congested(void *data, int bits) -{ - struct bcache_device *d = data; - struct request_queue *q; - struct cache *ca; - unsigned int i; - int ret = 0; - - for_each_cache(ca, d->c, i) { - q = bdev_get_queue(ca->bdev); - ret |= bdi_congested(q->backing_dev_info, bits); - } - - return ret; -} - void bch_flash_dev_request_init(struct bcache_device *d) { - struct gendisk *g = d->disk; - - g->queue->backing_dev_info->congested_fn = flash_dev_congested; d->cache_miss = flash_dev_cache_miss; d->ioctl = flash_dev_ioctl; } diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index de13f6e91696..9e45faa054b6 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -885,7 +885,6 @@ static int bcache_device_init(struct bcache_device *d, unsigned int block_size, return -ENOMEM; d->disk->queue = q; - q->backing_dev_info->congested_data = d; q->limits.max_hw_sectors = UINT_MAX; q->limits.max_sectors = UINT_MAX; q->limits.max_segment_size = UINT_MAX; diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c index 9eccced92896..96c93802ee4d 100644 --- a/drivers/md/dm-cache-target.c +++ b/drivers/md/dm-cache-target.c @@ -421,8 +421,6 @@ struct cache { struct rw_semaphore quiesce_lock; - struct dm_target_callbacks callbacks; - /* * origin_blocks entries, discarded if set. */ @@ -2423,20 +2421,6 @@ static void set_cache_size(struct cache *cache, dm_cblock_t size) cache->cache_size = size; } -static int is_congested(struct dm_dev *dev, int bdi_bits) -{ - struct request_queue *q = bdev_get_queue(dev->bdev); - return bdi_congested(q->backing_dev_info, bdi_bits); -} - -static int cache_is_congested(struct dm_target_callbacks *cb, int bdi_bits) -{ - struct cache *cache = container_of(cb, struct cache, callbacks); - - return is_congested(cache->origin_dev, bdi_bits) || - is_congested(cache->cache_dev, bdi_bits); -} - #define DEFAULT_MIGRATION_THRESHOLD 2048 static int cache_create(struct cache_args *ca, struct cache **result) @@ -2471,9 +2455,6 @@ static int cache_create(struct cache_args *ca, struct cache **result) goto bad; } - cache->callbacks.congested_fn = cache_is_congested; - dm_table_add_target_callbacks(ti->table, &cache->callbacks); - cache->metadata_dev = ca->metadata_dev; cache->origin_dev = ca->origin_dev; cache->cache_dev = ca->cache_dev; diff --git a/drivers/md/dm-clone-target.c b/drivers/md/dm-clone-target.c index 59ed8a67c2e3..bdb255edc200 100644 --- a/drivers/md/dm-clone-target.c +++ b/drivers/md/dm-clone-target.c @@ -68,7 +68,6 @@ struct hash_table_bucket; struct clone { struct dm_target *ti; - struct dm_target_callbacks callbacks; struct dm_dev *metadata_dev; struct dm_dev *dest_dev; @@ -1518,18 +1517,6 @@ error: DMEMIT("Error"); } -static int clone_is_congested(struct dm_target_callbacks *cb, int bdi_bits) -{ - struct request_queue *dest_q, *source_q; - struct clone *clone = container_of(cb, struct clone, callbacks); - - source_q = bdev_get_queue(clone->source_dev->bdev); - dest_q = bdev_get_queue(clone->dest_dev->bdev); - - return (bdi_congested(dest_q->backing_dev_info, bdi_bits) | - bdi_congested(source_q->backing_dev_info, bdi_bits)); -} - static sector_t get_dev_size(struct dm_dev *dev) { return i_size_read(dev->bdev->bd_inode) >> SECTOR_SHIFT; @@ -1930,8 +1917,6 @@ static int clone_ctr(struct dm_target *ti, unsigned int argc, char **argv) goto out_with_mempool; mutex_init(&clone->commit_lock); - clone->callbacks.congested_fn = clone_is_congested; - dm_table_add_target_callbacks(ti->table, &clone->callbacks); /* Enable flushes */ ti->num_flush_bios = 1; diff --git a/drivers/md/dm-era-target.c b/drivers/md/dm-era-target.c index 566ddbdb16a4..b24e3839bb3a 100644 --- a/drivers/md/dm-era-target.c +++ b/drivers/md/dm-era-target.c @@ -1137,7 +1137,6 @@ static int metadata_get_stats(struct era_metadata *md, void *ptr) struct era { struct dm_target *ti; - struct dm_target_callbacks callbacks; struct dm_dev *metadata_dev; struct dm_dev *origin_dev; @@ -1375,18 +1374,6 @@ static void stop_worker(struct era *era) /*---------------------------------------------------------------- * Target methods *--------------------------------------------------------------*/ -static int dev_is_congested(struct dm_dev *dev, int bdi_bits) -{ - struct request_queue *q = bdev_get_queue(dev->bdev); - return bdi_congested(q->backing_dev_info, bdi_bits); -} - -static int era_is_congested(struct dm_target_callbacks *cb, int bdi_bits) -{ - struct era *era = container_of(cb, struct era, callbacks); - return dev_is_congested(era->origin_dev, bdi_bits); -} - static void era_destroy(struct era *era) { if (era->md) @@ -1514,8 +1501,6 @@ static int era_ctr(struct dm_target *ti, unsigned argc, char **argv) ti->flush_supported = true; ti->num_discard_bios = 1; - era->callbacks.congested_fn = era_is_congested; - dm_table_add_target_callbacks(ti->table, &era->callbacks); return 0; } diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c index 10e8b2fe787b..d9e270957e18 100644 --- a/drivers/md/dm-raid.c +++ b/drivers/md/dm-raid.c @@ -242,7 +242,6 @@ struct raid_set { struct mddev md; struct raid_type *raid_type; - struct dm_target_callbacks callbacks; sector_t array_sectors; sector_t dev_sectors; @@ -1705,13 +1704,6 @@ static void do_table_event(struct work_struct *ws) dm_table_event(rs->ti->table); } -static int raid_is_congested(struct dm_target_callbacks *cb, int bits) -{ - struct raid_set *rs = container_of(cb, struct raid_set, callbacks); - - return mddev_congested(&rs->md, bits); -} - /* * Make sure a valid takover (level switch) is being requested on @rs * @@ -3248,9 +3240,6 @@ size_check: goto bad_md_start; } - rs->callbacks.congested_fn = raid_is_congested; - dm_table_add_target_callbacks(ti->table, &rs->callbacks); - /* If raid4/5/6 journal mode explicitly requested (only possible with journal dev) -> set it */ if (test_bit(__CTR_FLAG_JOURNAL_MODE, &rs->ctr_flags)) { r = r5c_journal_mode_set(&rs->md, rs->journal_dev.mode); @@ -3310,7 +3299,6 @@ static void raid_dtr(struct dm_target *ti) { struct raid_set *rs = ti->private; - list_del_init(&rs->callbacks.list); md_stop(&rs->md); raid_set_free(rs); } diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c index 8277b959e00b..0ea5b7367179 100644 --- a/drivers/md/dm-table.c +++ b/drivers/md/dm-table.c @@ -64,8 +64,6 @@ struct dm_table { void *event_context; struct dm_md_mempools *mempools; - - struct list_head target_callbacks; }; /* @@ -190,7 +188,6 @@ int dm_table_create(struct dm_table **result, fmode_t mode, return -ENOMEM; INIT_LIST_HEAD(&t->devices); - INIT_LIST_HEAD(&t->target_callbacks); if (!num_targets) num_targets = KEYS_PER_NODE; @@ -361,7 +358,7 @@ static int device_area_is_invalid(struct dm_target *ti, struct dm_dev *dev, * This upgrades the mode on an already open dm_dev, being * careful to leave things as they were if we fail to reopen the * device and not to touch the existing bdev field in case - * it is accessed concurrently inside dm_table_any_congested(). + * it is accessed concurrently. */ static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode, struct mapped_device *md) @@ -2052,38 +2049,6 @@ int dm_table_resume_targets(struct dm_table *t) return 0; } -void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb) -{ - list_add(&cb->list, &t->target_callbacks); -} -EXPORT_SYMBOL_GPL(dm_table_add_target_callbacks); - -int dm_table_any_congested(struct dm_table *t, int bdi_bits) -{ - struct dm_dev_internal *dd; - struct list_head *devices = dm_table_get_devices(t); - struct dm_target_callbacks *cb; - int r = 0; - - list_for_each_entry(dd, devices, list) { - struct request_queue *q = bdev_get_queue(dd->dm_dev->bdev); - char b[BDEVNAME_SIZE]; - - if (likely(q)) - r |= bdi_congested(q->backing_dev_info, bdi_bits); - else - DMWARN_LIMIT("%s: any_congested: nonexistent device %s", - dm_device_name(t->md), - bdevname(dd->dm_dev->bdev, b)); - } - - list_for_each_entry(cb, &t->target_callbacks, list) - if (cb->congested_fn) - r |= cb->congested_fn(cb, bdi_bits); - - return r; -} - struct mapped_device *dm_table_get_md(struct dm_table *t) { return t->md; diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index fe2de2888709..fff4c50df74d 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -326,7 +326,6 @@ struct pool_c { struct pool *pool; struct dm_dev *data_dev; struct dm_dev *metadata_dev; - struct dm_target_callbacks callbacks; dm_block_t low_water_blocks; struct pool_features requested_pf; /* Features requested during table load */ @@ -2796,18 +2795,6 @@ static int thin_bio_map(struct dm_target *ti, struct bio *bio) } } -static int pool_is_congested(struct dm_target_callbacks *cb, int bdi_bits) -{ - struct pool_c *pt = container_of(cb, struct pool_c, callbacks); - struct request_queue *q; - - if (get_pool_mode(pt->pool) == PM_OUT_OF_DATA_SPACE) - return 1; - - q = bdev_get_queue(pt->data_dev->bdev); - return bdi_congested(q->backing_dev_info, bdi_bits); -} - static void requeue_bios(struct pool *pool) { struct thin_c *tc; @@ -3420,9 +3407,6 @@ static int pool_ctr(struct dm_target *ti, unsigned argc, char **argv) dm_pool_register_pre_commit_callback(pool->pmd, metadata_pre_commit_callback, pool); - pt->callbacks.congested_fn = pool_is_congested; - dm_table_add_target_callbacks(ti->table, &pt->callbacks); - mutex_unlock(&dm_thin_pool_table.mutex); return 0; diff --git a/drivers/md/dm.c b/drivers/md/dm.c index 48bfd41658aa..e2148fcb88bb 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1821,31 +1821,6 @@ static blk_qc_t dm_submit_bio(struct bio *bio) return ret; } -static int dm_any_congested(void *congested_data, int bdi_bits) -{ - int r = bdi_bits; - struct mapped_device *md = congested_data; - struct dm_table *map; - - if (!test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) { - if (dm_request_based(md)) { - /* - * With request-based DM we only need to check the - * top-level queue for congestion. - */ - struct backing_dev_info *bdi = md->queue->backing_dev_info; - r = bdi->wb.congested & bdi_bits; - } else { - map = dm_get_live_table_fast(md); - if (map) - r = dm_table_any_congested(map, bdi_bits); - dm_put_live_table_fast(md); - } - } - - return r; -} - /*----------------------------------------------------------------- * An IDR is used to keep track of allocated minor numbers. *---------------------------------------------------------------*/ @@ -2284,12 +2259,6 @@ struct queue_limits *dm_get_queue_limits(struct mapped_device *md) } EXPORT_SYMBOL_GPL(dm_get_queue_limits); -static void dm_init_congested_fn(struct mapped_device *md) -{ - md->queue->backing_dev_info->congested_data = md; - md->queue->backing_dev_info->congested_fn = dm_any_congested; -} - /* * Setup the DM device's queue based on md's type */ @@ -2306,12 +2275,10 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t) DMERR("Cannot initialize queue for request-based dm-mq mapped device"); return r; } - dm_init_congested_fn(md); break; case DM_TYPE_BIO_BASED: case DM_TYPE_DAX_BIO_BASED: case DM_TYPE_NVME_BIO_BASED: - dm_init_congested_fn(md); break; case DM_TYPE_NONE: WARN_ON_ONCE(true); diff --git a/drivers/md/dm.h b/drivers/md/dm.h index d7c4f6606b5f..4f5fe664d05a 100644 --- a/drivers/md/dm.h +++ b/drivers/md/dm.h @@ -63,7 +63,6 @@ void dm_table_presuspend_targets(struct dm_table *t); void dm_table_presuspend_undo_targets(struct dm_table *t); void dm_table_postsuspend_targets(struct dm_table *t); int dm_table_resume_targets(struct dm_table *t); -int dm_table_any_congested(struct dm_table *t, int bdi_bits); enum dm_queue_mode dm_table_get_type(struct dm_table *t); struct target_type *dm_table_get_immutable_target_type(struct dm_table *t); struct dm_target *dm_table_get_immutable_target(struct dm_table *t); diff --git a/drivers/md/md-linear.c b/drivers/md/md-linear.c index 8efada3ee16f..c2ae9125c4c3 100644 --- a/drivers/md/md-linear.c +++ b/drivers/md/md-linear.c @@ -46,29 +46,6 @@ static inline struct dev_info *which_dev(struct mddev *mddev, sector_t sector) return conf->disks + lo; } -/* - * In linear_congested() conf->raid_disks is used as a copy of - * mddev->raid_disks to iterate conf->disks[], because conf->raid_disks - * and conf->disks[] are created in linear_conf(), they are always - * consitent with each other, but mddev->raid_disks does not. - */ -static int linear_congested(struct mddev *mddev, int bits) -{ - struct linear_conf *conf; - int i, ret = 0; - - rcu_read_lock(); - conf = rcu_dereference(mddev->private); - - for (i = 0; i < conf->raid_disks && !ret ; i++) { - struct request_queue *q = bdev_get_queue(conf->disks[i].rdev->bdev); - ret |= bdi_congested(q->backing_dev_info, bits); - } - - rcu_read_unlock(); - return ret; -} - static sector_t linear_size(struct mddev *mddev, sector_t sectors, int raid_disks) { struct linear_conf *conf; @@ -322,7 +299,6 @@ static struct md_personality linear_personality = .hot_add_disk = linear_add, .size = linear_size, .quiesce = linear_quiesce, - .congested = linear_congested, }; static int __init linear_init (void) diff --git a/drivers/md/md-multipath.c b/drivers/md/md-multipath.c index 277fdfd9ee54..776bbe542db5 100644 --- a/drivers/md/md-multipath.c +++ b/drivers/md/md-multipath.c @@ -151,28 +151,6 @@ static void multipath_status(struct seq_file *seq, struct mddev *mddev) seq_putc(seq, ']'); } -static int multipath_congested(struct mddev *mddev, int bits) -{ - struct mpconf *conf = mddev->private; - int i, ret = 0; - - rcu_read_lock(); - for (i = 0; i < mddev->raid_disks ; i++) { - struct md_rdev *rdev = rcu_dereference(conf->multipaths[i].rdev); - if (rdev && !test_bit(Faulty, &rdev->flags)) { - struct request_queue *q = bdev_get_queue(rdev->bdev); - - ret |= bdi_congested(q->backing_dev_info, bits); - /* Just like multipath_map, we just check the - * first available device - */ - break; - } - } - rcu_read_unlock(); - return ret; -} - /* * Careful, this can execute in IRQ contexts as well! */ @@ -478,7 +456,6 @@ static struct md_personality multipath_personality = .hot_add_disk = multipath_add_disk, .hot_remove_disk= multipath_remove_disk, .size = multipath_size, - .congested = multipath_congested, }; static int __init multipath_init (void) diff --git a/drivers/md/md.c b/drivers/md/md.c index 77dfe4765c31..96b28f6d025c 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -549,26 +549,6 @@ void mddev_resume(struct mddev *mddev) } EXPORT_SYMBOL_GPL(mddev_resume); -int mddev_congested(struct mddev *mddev, int bits) -{ - struct md_personality *pers = mddev->pers; - int ret = 0; - - rcu_read_lock(); - if (mddev->suspended) - ret = 1; - else if (pers && pers->congested) - ret = pers->congested(mddev, bits); - rcu_read_unlock(); - return ret; -} -EXPORT_SYMBOL_GPL(mddev_congested); -static int md_congested(void *data, int bits) -{ - struct mddev *mddev = data; - return mddev_congested(mddev, bits); -} - /* * Generic flush handling for md */ @@ -5965,8 +5945,6 @@ int md_run(struct mddev *mddev) blk_queue_flag_set(QUEUE_FLAG_NONROT, mddev->queue); else blk_queue_flag_clear(QUEUE_FLAG_NONROT, mddev->queue); - mddev->queue->backing_dev_info->congested_data = mddev; - mddev->queue->backing_dev_info->congested_fn = md_congested; } if (pers->sync_request) { if (mddev->kobj.sd && @@ -6351,7 +6329,6 @@ static int do_md_stop(struct mddev *mddev, int mode, __md_stop_writes(mddev); __md_stop(mddev); - mddev->queue->backing_dev_info->congested_fn = NULL; /* tell userspace to handle 'inactive' */ sysfs_notify_dirent_safe(mddev->sysfs_state); diff --git a/drivers/md/md.h b/drivers/md/md.h index 612814d07d35..e2f1ad9afc48 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -597,9 +597,6 @@ struct md_personality * array. */ void *(*takeover) (struct mddev *mddev); - /* congested implements bdi.congested_fn(). - * Will not be called while array is 'suspended' */ - int (*congested)(struct mddev *mddev, int bits); /* Changes the consistency policy of an active array. */ int (*change_consistency_policy)(struct mddev *mddev, const char *buf); }; @@ -710,7 +707,6 @@ extern void md_done_sync(struct mddev *mddev, int blocks, int ok); extern void md_error(struct mddev *mddev, struct md_rdev *rdev); extern void md_finish_reshape(struct mddev *mddev); -extern int mddev_congested(struct mddev *mddev, int bits); extern bool __must_check md_flush_request(struct mddev *mddev, struct bio *bio); extern void md_super_write(struct mddev *mddev, struct md_rdev *rdev, sector_t sector, int size, struct page *page); diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index e9e91c8d8afc..f54a449f97aa 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -29,21 +29,6 @@ module_param(default_layout, int, 0644); (1L << MD_HAS_PPL) | \ (1L << MD_HAS_MULTIPLE_PPLS)) -static int raid0_congested(struct mddev *mddev, int bits) -{ - struct r0conf *conf = mddev->private; - struct md_rdev **devlist = conf->devlist; - int raid_disks = conf->strip_zone[0].nb_dev; - int i, ret = 0; - - for (i = 0; i < raid_disks && !ret ; i++) { - struct request_queue *q = bdev_get_queue(devlist[i]->bdev); - - ret |= bdi_congested(q->backing_dev_info, bits); - } - return ret; -} - /* * inform the user of the raid configuration */ @@ -818,7 +803,6 @@ static struct md_personality raid0_personality= .size = raid0_size, .takeover = raid0_takeover, .quiesce = raid0_quiesce, - .congested = raid0_congested, }; static int __init raid0_init (void) diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c index 2aa2649cca66..960d854c07f8 100644 --- a/drivers/md/raid1.c +++ b/drivers/md/raid1.c @@ -786,36 +786,6 @@ static int read_balance(struct r1conf *conf, struct r1bio *r1_bio, int *max_sect return best_disk; } -static int raid1_congested(struct mddev *mddev, int bits) -{ - struct r1conf *conf = mddev->private; - int i, ret = 0; - - if ((bits & (1 << WB_async_congested)) && - conf->pending_count >= max_queued_requests) - return 1; - - rcu_read_lock(); - for (i = 0; i < conf->raid_disks * 2; i++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); - if (rdev && !test_bit(Faulty, &rdev->flags)) { - struct request_queue *q = bdev_get_queue(rdev->bdev); - - BUG_ON(!q); - - /* Note the '|| 1' - when read_balance prefers - * non-congested targets, it can be removed - */ - if ((bits & (1 << WB_async_congested)) || 1) - ret |= bdi_congested(q->backing_dev_info, bits); - else - ret &= bdi_congested(q->backing_dev_info, bits); - } - } - rcu_read_unlock(); - return ret; -} - static void flush_bio_list(struct r1conf *conf, struct bio *bio) { /* flush any pending bitmap writes to disk before proceeding w/ I/O */ @@ -3396,7 +3366,6 @@ static struct md_personality raid1_personality = .check_reshape = raid1_reshape, .quiesce = raid1_quiesce, .takeover = raid1_takeover, - .congested = raid1_congested, }; static int __init raid_init(void) diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index e45fd56cf584..353288bc4cb7 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -848,31 +848,6 @@ static struct md_rdev *read_balance(struct r10conf *conf, return rdev; } -static int raid10_congested(struct mddev *mddev, int bits) -{ - struct r10conf *conf = mddev->private; - int i, ret = 0; - - if ((bits & (1 << WB_async_congested)) && - conf->pending_count >= max_queued_requests) - return 1; - - rcu_read_lock(); - for (i = 0; - (i < conf->geo.raid_disks || i < conf->prev.raid_disks) - && ret == 0; - i++) { - struct md_rdev *rdev = rcu_dereference(conf->mirrors[i].rdev); - if (rdev && !test_bit(Faulty, &rdev->flags)) { - struct request_queue *q = bdev_get_queue(rdev->bdev); - - ret |= bdi_congested(q->backing_dev_info, bits); - } - } - rcu_read_unlock(); - return ret; -} - static void flush_pending_writes(struct r10conf *conf) { /* Any writes that have been queued but are awaiting @@ -4929,7 +4904,6 @@ static struct md_personality raid10_personality = .start_reshape = raid10_start_reshape, .finish_reshape = raid10_finish_reshape, .update_reshape_pos = raid10_update_reshape_pos, - .congested = raid10_congested, }; static int __init raid_init(void) diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 8dea4398b191..774ea893d47e 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -5099,28 +5099,6 @@ static void activate_bit_delay(struct r5conf *conf, } } -static int raid5_congested(struct mddev *mddev, int bits) -{ - struct r5conf *conf = mddev->private; - - /* No difference between reads and writes. Just check - * how busy the stripe_cache is - */ - - if (test_bit(R5_INACTIVE_BLOCKED, &conf->cache_state)) - return 1; - - /* Also checks whether there is pressure on r5cache log space */ - if (test_bit(R5C_LOG_TIGHT, &conf->cache_state)) - return 1; - if (conf->quiesce) - return 1; - if (atomic_read(&conf->empty_inactive_list_nr)) - return 1; - - return 0; -} - static int in_chunk_boundary(struct mddev *mddev, struct bio *bio) { struct r5conf *conf = mddev->private; @@ -8427,7 +8405,6 @@ static struct md_personality raid6_personality = .finish_reshape = raid5_finish_reshape, .quiesce = raid5_quiesce, .takeover = raid6_takeover, - .congested = raid5_congested, .change_consistency_policy = raid5_change_consistency_policy, }; static struct md_personality raid5_personality = @@ -8452,7 +8429,6 @@ static struct md_personality raid5_personality = .finish_reshape = raid5_finish_reshape, .quiesce = raid5_quiesce, .takeover = raid5_takeover, - .congested = raid5_congested, .change_consistency_policy = raid5_change_consistency_policy, }; @@ -8478,7 +8454,6 @@ static struct md_personality raid4_personality = .finish_reshape = raid5_finish_reshape, .quiesce = raid5_quiesce, .takeover = raid4_takeover, - .congested = raid5_congested, .change_consistency_policy = raid5_change_consistency_policy, }; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 7c6f0bbb54a5..eb5f2506cede 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1616,27 +1616,6 @@ fail: return ERR_PTR(ret); } -static int btrfs_congested_fn(void *congested_data, int bdi_bits) -{ - struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data; - int ret = 0; - struct btrfs_device *device; - struct backing_dev_info *bdi; - - rcu_read_lock(); - list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) { - if (!device->bdev) - continue; - bdi = device->bdev->bd_bdi; - if (bdi_congested(bdi, bdi_bits)) { - ret = 1; - break; - } - } - rcu_read_unlock(); - return ret; -} - /* * called by the kthread helper functions to finally call the bio end_io * functions. This is where read checksum verification actually happens @@ -3051,8 +3030,6 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_sb_buffer; } - sb->s_bdi->congested_fn = btrfs_congested_fn; - sb->s_bdi->congested_data = fs_info; sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK; sb->s_bdi->ra_pages = VM_READAHEAD_PAGES; sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super); diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 1cec4521e1fb..fff9367a6348 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -33,8 +33,6 @@ enum wb_congested_state { WB_sync_congested, /* The sync queue is getting full */ }; -typedef int (congested_fn)(void *, int); - enum wb_stat_item { WB_RECLAIMABLE, WB_WRITEBACK, @@ -170,8 +168,6 @@ struct backing_dev_info { struct list_head bdi_list; unsigned long ra_pages; /* max readahead in PAGE_SIZE units */ unsigned long io_pages; /* max allowed IO size */ - congested_fn *congested_fn; /* Function pointer if device is md/dm */ - void *congested_data; /* Pointer to aux data for congested func */ struct kref refcnt; /* Reference counter for the structure */ unsigned int capabilities; /* Device capabilities */ diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 9173d2c22b4a..0b06b2d26c9a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -169,10 +169,6 @@ static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) { - struct backing_dev_info *bdi = wb->bdi; - - if (bdi->congested_fn) - return bdi->congested_fn(bdi->congested_data, cong_bits); return wb->congested & cong_bits; } diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h index 8750f2dc5613..d5306d9c29c4 100644 --- a/include/linux/device-mapper.h +++ b/include/linux/device-mapper.h @@ -322,12 +322,6 @@ struct dm_target { bool discards_supported:1; }; -/* Each target can link one of these into the table */ -struct dm_target_callbacks { - struct list_head list; - int (*congested_fn) (struct dm_target_callbacks *, int); -}; - void *dm_per_bio_data(struct bio *bio, size_t data_size); struct bio *dm_bio_from_per_bio_data(void *data, size_t data_size); unsigned dm_bio_get_target_bio_nr(const struct bio *bio); @@ -477,11 +471,6 @@ int dm_table_create(struct dm_table **result, fmode_t mode, int dm_table_add_target(struct dm_table *t, const char *type, sector_t start, sector_t len, char *params); -/* - * Target_ctr should call this if it needs to add any callbacks. - */ -void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb); - /* * Target can use this to set the table's type. * Can only ever be called from a target's ctr. -- cgit v1.2.3 From c5638ab417660e2c5d681aed5ce76df992982dbb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Jul 2020 16:33:07 +0200 Subject: block: simplify the restart case in __blkdev_get Insted of duplicating all the cleanup logic jump to the code that cleans up anyway, and restart after that. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- fs/block_dev.c | 25 ++++++++++--------------- 1 file changed, 10 insertions(+), 15 deletions(-) (limited to 'fs') diff --git a/fs/block_dev.c b/fs/block_dev.c index a36d5b6907ea..376832250c8e 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1517,7 +1517,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) int ret; int partno; int perm = 0; - bool first_open = false; + bool first_open = false, need_restart; if (mode & FMODE_READ) perm |= MAY_READ; @@ -1533,7 +1533,7 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) } restart: - + need_restart = false; ret = -ENXIO; disk = bdev_get_gendisk(bdev, &partno); if (!disk) @@ -1556,19 +1556,12 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) ret = 0; if (disk->fops->open) { ret = disk->fops->open(bdev, mode); - if (ret == -ERESTARTSYS) { - /* Lost a race with 'disk' being - * deleted, try again. - * See md.c - */ - disk_put_part(bdev->bd_part); - bdev->bd_part = NULL; - bdev->bd_disk = NULL; - mutex_unlock(&bdev->bd_mutex); - disk_unblock_events(disk); - put_disk_and_module(disk); - goto restart; - } + /* + * If we lost a race with 'disk' being deleted, + * try again. See md.c + */ + if (ret == -ERESTARTSYS) + need_restart = true; } if (!ret) { @@ -1647,6 +1640,8 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) mutex_unlock(&bdev->bd_mutex); disk_unblock_events(disk); put_disk_and_module(disk); + if (need_restart) + goto restart; out: return ret; -- cgit v1.2.3 From 58e46ed9cc634b3c64ea402789f8a92ce45cee48 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Jul 2020 16:33:08 +0200 Subject: block: refactor bd_start_claiming Move the locking and assignment of bd_claiming from bd_start_claiming to bd_prepare_to_claim. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- fs/block_dev.c | 33 +++++++++++++-------------------- 1 file changed, 13 insertions(+), 20 deletions(-) (limited to 'fs') diff --git a/fs/block_dev.c b/fs/block_dev.c index 376832250c8e..b7b2ee4b288a 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1015,19 +1015,14 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, } /** - * bd_prepare_to_claim - prepare to claim a block device + * bd_prepare_to_claim - claim a block device * @bdev: block device of interest * @whole: the whole device containing @bdev, may equal @bdev * @holder: holder trying to claim @bdev * - * Prepare to claim @bdev. This function fails if @bdev is already - * claimed by another holder and waits if another claiming is in - * progress. This function doesn't actually claim. On successful - * return, the caller has ownership of bd_claiming and bd_holder[s]. - * - * CONTEXT: - * spin_lock(&bdev_lock). Might release bdev_lock, sleep and regrab - * it multiple times. + * Claim @bdev. This function fails if @bdev is already claimed by another + * holder and waits if another claiming is in progress. return, the caller + * has ownership of bd_claiming and bd_holder[s]. * * RETURNS: * 0 if @bdev can be claimed, -EBUSY otherwise. @@ -1036,9 +1031,12 @@ static int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole, void *holder) { retry: + spin_lock(&bdev_lock); /* if someone else claimed, fail */ - if (!bd_may_claim(bdev, whole, holder)) + if (!bd_may_claim(bdev, whole, holder)) { + spin_unlock(&bdev_lock); return -EBUSY; + } /* if claiming is already in progress, wait for it to finish */ if (whole->bd_claiming) { @@ -1049,11 +1047,12 @@ retry: spin_unlock(&bdev_lock); schedule(); finish_wait(wq, &wait); - spin_lock(&bdev_lock); goto retry; } /* yay, all mine */ + whole->bd_claiming = holder; + spin_unlock(&bdev_lock); return 0; } @@ -1134,19 +1133,13 @@ struct block_device *bd_start_claiming(struct block_device *bdev, void *holder) if (!whole) return ERR_PTR(-ENOMEM); - /* prepare to claim, if successful, mark claiming in progress */ - spin_lock(&bdev_lock); - err = bd_prepare_to_claim(bdev, whole, holder); - if (err == 0) { - whole->bd_claiming = holder; - spin_unlock(&bdev_lock); - return whole; - } else { - spin_unlock(&bdev_lock); + if (err) { bdput(whole); return ERR_PTR(err); } + + return whole; } EXPORT_SYMBOL(bd_start_claiming); -- cgit v1.2.3 From ecbe6bc0003bfd5bf8581cb679cae0eb944432cb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Jul 2020 16:33:09 +0200 Subject: block: use bd_prepare_to_claim directly in the loop driver The arcane magic in bd_start_claiming is only needed to be able to claim a block_device that hasn't been fully set up. Switch the loop driver that claims from the ioctl path with a fully set up struct block_device to just use the much simpler bd_prepare_to_claim directly. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- drivers/block/loop.c | 7 +++---- fs/block_dev.c | 9 +++++---- include/linux/blkdev.h | 3 ++- 3 files changed, 10 insertions(+), 9 deletions(-) (limited to 'fs') diff --git a/drivers/block/loop.c b/drivers/block/loop.c index a943207705dd..d18160146226 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1090,11 +1090,10 @@ static int loop_configure(struct loop_device *lo, fmode_t mode, * here to avoid changing device under exclusive owner. */ if (!(mode & FMODE_EXCL)) { - claimed_bdev = bd_start_claiming(bdev, loop_configure); - if (IS_ERR(claimed_bdev)) { - error = PTR_ERR(claimed_bdev); + claimed_bdev = bdev->bd_contains; + error = bd_prepare_to_claim(bdev, claimed_bdev, loop_configure); + if (error) goto out_putf; - } } error = mutex_lock_killable(&loop_ctl_mutex); diff --git a/fs/block_dev.c b/fs/block_dev.c index b7b2ee4b288a..ee80bd81af74 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1027,8 +1027,8 @@ static bool bd_may_claim(struct block_device *bdev, struct block_device *whole, * RETURNS: * 0 if @bdev can be claimed, -EBUSY otherwise. */ -static int bd_prepare_to_claim(struct block_device *bdev, - struct block_device *whole, void *holder) +int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole, + void *holder) { retry: spin_lock(&bdev_lock); @@ -1055,6 +1055,7 @@ retry: spin_unlock(&bdev_lock); return 0; } +EXPORT_SYMBOL_GPL(bd_prepare_to_claim); /* only for the loop driver */ static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno) { @@ -1100,7 +1101,8 @@ static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno) * Pointer to the block device containing @bdev on success, ERR_PTR() * value on failure. */ -struct block_device *bd_start_claiming(struct block_device *bdev, void *holder) +static struct block_device *bd_start_claiming(struct block_device *bdev, + void *holder) { struct gendisk *disk; struct block_device *whole; @@ -1141,7 +1143,6 @@ struct block_device *bd_start_claiming(struct block_device *bdev, void *holder) return whole; } -EXPORT_SYMBOL(bd_start_claiming); static void bd_clear_claiming(struct block_device *whole, void *holder) { diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 71173a1ffa8b..06995b96e946 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1919,7 +1919,8 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder); struct block_device *blkdev_get_by_path(const char *path, fmode_t mode, void *holder); struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder); -struct block_device *bd_start_claiming(struct block_device *bdev, void *holder); +int bd_prepare_to_claim(struct block_device *bdev, struct block_device *whole, + void *holder); void bd_abort_claiming(struct block_device *bdev, struct block_device *whole, void *holder); void blkdev_put(struct block_device *bdev, fmode_t mode); -- cgit v1.2.3 From 5b642d8b9f2ef1212f33dfc337816e6b4ab83bb3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 16 Jul 2020 16:33:10 +0200 Subject: block: integrate bd_start_claiming into __blkdev_get bd_start_claiming duplicates a lot of the work done in __blkdev_get. Integrate the two functions to avoid the duplicate work, and to do the right thing for the md -ERESTARTSYS corner case. Signed-off-by: Christoph Hellwig Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- fs/block_dev.c | 177 ++++++++++++++++++--------------------------------------- 1 file changed, 55 insertions(+), 122 deletions(-) (limited to 'fs') diff --git a/fs/block_dev.c b/fs/block_dev.c index ee80bd81af74..3f94a06a0946 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1078,72 +1078,6 @@ static struct gendisk *bdev_get_gendisk(struct block_device *bdev, int *partno) return disk; } -/** - * bd_start_claiming - start claiming a block device - * @bdev: block device of interest - * @holder: holder trying to claim @bdev - * - * @bdev is about to be opened exclusively. Check @bdev can be opened - * exclusively and mark that an exclusive open is in progress. Each - * successful call to this function must be matched with a call to - * either bd_finish_claiming() or bd_abort_claiming() (which do not - * fail). - * - * This function is used to gain exclusive access to the block device - * without actually causing other exclusive open attempts to fail. It - * should be used when the open sequence itself requires exclusive - * access but may subsequently fail. - * - * CONTEXT: - * Might sleep. - * - * RETURNS: - * Pointer to the block device containing @bdev on success, ERR_PTR() - * value on failure. - */ -static struct block_device *bd_start_claiming(struct block_device *bdev, - void *holder) -{ - struct gendisk *disk; - struct block_device *whole; - int partno, err; - - might_sleep(); - - /* - * @bdev might not have been initialized properly yet, look up - * and grab the outer block device the hard way. - */ - disk = bdev_get_gendisk(bdev, &partno); - if (!disk) - return ERR_PTR(-ENXIO); - - /* - * Normally, @bdev should equal what's returned from bdget_disk() - * if partno is 0; however, some drivers (floppy) use multiple - * bdev's for the same physical device and @bdev may be one of the - * aliases. Keep @bdev if partno is 0. This means claimer - * tracking is broken for those devices but it has always been that - * way. - */ - if (partno) - whole = bdget_disk(disk, 0); - else - whole = bdgrab(bdev); - - put_disk_and_module(disk); - if (!whole) - return ERR_PTR(-ENOMEM); - - err = bd_prepare_to_claim(bdev, whole, holder); - if (err) { - bdput(whole); - return ERR_PTR(err); - } - - return whole; -} - static void bd_clear_claiming(struct block_device *whole, void *holder) { lockdep_assert_held(&bdev_lock); @@ -1156,7 +1090,7 @@ static void bd_clear_claiming(struct block_device *whole, void *holder) /** * bd_finish_claiming - finish claiming of a block device * @bdev: block device of interest - * @whole: whole block device (returned from bd_start_claiming()) + * @whole: whole block device * @holder: holder that has claimed @bdev * * Finish exclusive open of a block device. Mark the device as exlusively @@ -1182,7 +1116,7 @@ static void bd_finish_claiming(struct block_device *bdev, /** * bd_abort_claiming - abort claiming of a block device * @bdev: block device of interest - * @whole: whole block device (returned from bd_start_claiming()) + * @whole: whole block device * @holder: holder that has claimed @bdev * * Abort claiming of a block device when the exclusive open failed. This can be @@ -1505,13 +1439,15 @@ EXPORT_SYMBOL_GPL(bdev_disk_changed); * mutex_lock_nested(whole->bd_mutex, 1) */ -static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) +static int __blkdev_get(struct block_device *bdev, fmode_t mode, void *holder, + int for_part) { + struct block_device *whole = NULL, *claiming = NULL; struct gendisk *disk; int ret; int partno; int perm = 0; - bool first_open = false, need_restart; + bool first_open = false, unblock_events = true, need_restart; if (mode & FMODE_READ) perm |= MAY_READ; @@ -1533,6 +1469,25 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) if (!disk) goto out; + if (partno) { + whole = bdget_disk(disk, 0); + if (!whole) { + ret = -ENOMEM; + goto out_put_disk; + } + } + + if (!for_part && (mode & FMODE_EXCL)) { + WARN_ON_ONCE(!holder); + if (whole) + claiming = whole; + else + claiming = bdev; + ret = bd_prepare_to_claim(bdev, claiming, holder); + if (ret) + goto out_put_whole; + } + disk_block_events(disk); mutex_lock_nested(&bdev->bd_mutex, for_part); if (!bdev->bd_openers) { @@ -1576,18 +1531,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) if (ret) goto out_clear; } else { - struct block_device *whole; - whole = bdget_disk(disk, 0); - ret = -ENOMEM; - if (!whole) - goto out_clear; BUG_ON(for_part); - ret = __blkdev_get(whole, mode, 1); - if (ret) { - bdput(whole); + ret = __blkdev_get(whole, mode, NULL, 1); + if (ret) goto out_clear; - } - bdev->bd_contains = whole; + bdev->bd_contains = bdgrab(whole); bdev->bd_part = disk_get_part(disk, partno); if (!(disk->flags & GENHD_FL_UP) || !bdev->bd_part || !bdev->bd_part->nr_sects) { @@ -1616,11 +1564,30 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) bdev->bd_openers++; if (for_part) bdev->bd_part_count++; + if (claiming) + bd_finish_claiming(bdev, claiming, holder); + + /* + * Block event polling for write claims if requested. Any write holder + * makes the write_holder state stick until all are released. This is + * good enough and tracking individual writeable reference is too + * fragile given the way @mode is used in blkdev_get/put(). + */ + if (claiming && (mode & FMODE_WRITE) && !bdev->bd_write_holder && + (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) { + bdev->bd_write_holder = true; + unblock_events = false; + } mutex_unlock(&bdev->bd_mutex); - disk_unblock_events(disk); + + if (unblock_events) + disk_unblock_events(disk); + /* only one opener holds refs to the module and disk */ if (!first_open) put_disk_and_module(disk); + if (whole) + bdput(whole); return 0; out_clear: @@ -1631,13 +1598,18 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) __blkdev_put(bdev->bd_contains, mode, 1); bdev->bd_contains = NULL; out_unlock_bdev: + if (claiming) + bd_abort_claiming(bdev, claiming, holder); mutex_unlock(&bdev->bd_mutex); disk_unblock_events(disk); + out_put_whole: + if (whole) + bdput(whole); + out_put_disk: put_disk_and_module(disk); if (need_restart) goto restart; out: - return ret; } @@ -1662,50 +1634,11 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part) */ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder) { - struct block_device *whole = NULL; int res; - WARN_ON_ONCE((mode & FMODE_EXCL) && !holder); - - if ((mode & FMODE_EXCL) && holder) { - whole = bd_start_claiming(bdev, holder); - if (IS_ERR(whole)) { - bdput(bdev); - return PTR_ERR(whole); - } - } - - res = __blkdev_get(bdev, mode, 0); - - if (whole) { - struct gendisk *disk = whole->bd_disk; - - /* finish claiming */ - mutex_lock(&bdev->bd_mutex); - if (!res) - bd_finish_claiming(bdev, whole, holder); - else - bd_abort_claiming(bdev, whole, holder); - /* - * Block event polling for write claims if requested. Any - * write holder makes the write_holder state stick until - * all are released. This is good enough and tracking - * individual writeable reference is too fragile given the - * way @mode is used in blkdev_get/put(). - */ - if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder && - (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) { - bdev->bd_write_holder = true; - disk_block_events(disk); - } - - mutex_unlock(&bdev->bd_mutex); - bdput(whole); - } - + res =__blkdev_get(bdev, mode, holder, 0); if (res) bdput(bdev); - return res; } EXPORT_SYMBOL(blkdev_get); -- cgit v1.2.3