From c3077b5d97a39223a2d4b95a21ccff660836170f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Jun 2020 08:44:41 +0200 Subject: blk-mq: merge blk-softirq.c into blk-mq.c __blk_complete_request is only called from the blk-mq code, and duplicates a lot of code from blk-mq.c. Move it there to prepare for better code sharing and simplifications. Signed-off-by: Christoph Hellwig Reviewed-by: Daniel Wagner Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 8fd900998b4e..98712cfc7a34 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1078,7 +1078,6 @@ void blk_steal_bios(struct bio_list *list, struct request *rq); extern bool blk_update_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); -extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); /* -- cgit From 15f73f5b3e5958f2d169fe13c420eeeeae07bbf2 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Jun 2020 08:44:47 +0200 Subject: blk-mq: move failure injection out of blk_mq_complete_request Move the call to blk_should_fake_timeout out of blk_mq_complete_request and into the drivers, skipping call sites that are obvious error handlers, and remove the now superflous blk_mq_force_complete_rq helper. This ensures we don't keep injecting errors into completions that just terminate the Linux request after the hardware has been reset or the command has been aborted. Reviewed-by: Daniel Wagner Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index d6fcae17da5a..8e6ab766aef7 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -503,8 +503,7 @@ void __blk_mq_end_request(struct request *rq, blk_status_t error); void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); -bool blk_mq_complete_request(struct request *rq); -void blk_mq_force_complete_rq(struct request *rq); +void blk_mq_complete_request(struct request *rq); bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio, unsigned int nr_segs); bool blk_mq_queue_stopped(struct request_queue *q); @@ -537,6 +536,15 @@ void blk_mq_quiesce_queue_nowait(struct request_queue *q); unsigned int blk_mq_rq_cpu(struct request *rq); +bool __blk_should_fake_timeout(struct request_queue *q); +static inline bool blk_should_fake_timeout(struct request_queue *q) +{ + if (IS_ENABLED(CONFIG_FAIL_IO_TIMEOUT) && + test_bit(QUEUE_FLAG_FAIL_IO, &q->queue_flags)) + return __blk_should_fake_timeout(q); + return false; +} + /** * blk_mq_rq_from_pdu - cast a PDU to a request * @pdu: the PDU (Protocol Data Unit) to be casted -- cgit From 40d09b53bfc557af7481b9d80f060a7ac9c7d314 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Jun 2020 08:44:50 +0200 Subject: blk-mq: add a new blk_mq_complete_request_remote API This is a variant of blk_mq_complete_request_remote that only completes the request if it needs to be bounced to another CPU or a softirq. If the request can be completed locally the function returns false and lets the driver complete it without requring and indirect function call. Reviewed-by: Daniel Wagner Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 8e6ab766aef7..1641ec6cd7e5 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -504,6 +504,7 @@ void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list); void blk_mq_kick_requeue_list(struct request_queue *q); void blk_mq_delay_kick_requeue_list(struct request_queue *q, unsigned long msecs); void blk_mq_complete_request(struct request *rq); +bool blk_mq_complete_request_remote(struct request *rq); bool blk_mq_bio_list_merge(struct request_queue *q, struct list_head *list, struct bio *bio, unsigned int nr_segs); bool blk_mq_queue_stopped(struct request_queue *q); -- cgit From e8c7d14ac6c37c173ec606907d38802b00302988 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 19 Jun 2020 20:47:25 +0000 Subject: block: revert back to synchronous request_queue removal Commit dc9edc44de6c ("block: Fix a blk_exit_rl() regression") merged on v4.12 moved the work behind blk_release_queue() into a workqueue after a splat floated around which indicated some work on blk_release_queue() could sleep in blk_exit_rl(). This splat would be possible when a driver called blk_put_queue() or blk_cleanup_queue() (which calls blk_put_queue() as its final call) from an atomic context. blk_put_queue() decrements the refcount for the request_queue kobject, and upon reaching 0 blk_release_queue() is called. Although blk_exit_rl() is now removed through commit db6d99523560 ("block: remove request_list code") on v5.0, we reserve the right to be able to sleep within blk_release_queue() context. The last reference for the request_queue must not be called from atomic context. *When* the last reference to the request_queue reaches 0 varies, and so let's take the opportunity to document when that is expected to happen and also document the context of the related calls as best as possible so we can avoid future issues, and with the hopes that the synchronous request_queue removal sticks. We revert back to synchronous request_queue removal because asynchronous removal creates a regression with expected userspace interaction with several drivers. An example is when removing the loopback driver, one uses ioctls from userspace to do so, but upon return and if successful, one expects the device to be removed. Likewise if one races to add another device the new one may not be added as it is still being removed. This was expected behavior before and it now fails as the device is still present and busy still. Moving to asynchronous request_queue removal could have broken many scripts which relied on the removal to have been completed if there was no error. Document this expectation as well so that this doesn't regress userspace again. Using asynchronous request_queue removal however has helped us find other bugs. In the future we can test what could break with this arrangement by enabling CONFIG_DEBUG_KOBJECT_RELEASE. While at it, update the docs with the context expectations for the request_queue / gendisk refcount decrement, and make these expectations explicit by using might_sleep(). Fixes: dc9edc44de6c ("block: Fix a blk_exit_rl() regression") Suggested-by: Nicolai Stange Signed-off-by: Luis Chamberlain Reviewed-by: Christoph Hellwig Reviewed-by: Bart Van Assche Cc: Bart Van Assche Cc: Omar Sandoval Cc: Hannes Reinecke Cc: Nicolai Stange Cc: Greg Kroah-Hartman Cc: Michal Hocko Cc: yu kuai Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 98712cfc7a34..e214e0e9f868 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -584,8 +584,6 @@ struct request_queue { size_t cmd_size; - struct work_struct release_work; - #define BLK_MAX_WRITE_HINTS 5 u64 write_hints[BLK_MAX_WRITE_HINTS]; }; -- cgit From 85e0cbbb8a79537dbc465e9deb449a08b2b092a6 Mon Sep 17 00:00:00 2001 From: Luis Chamberlain Date: Fri, 19 Jun 2020 20:47:30 +0000 Subject: block: create the request_queue debugfs_dir on registration We were only creating the request_queue debugfs_dir only for make_request block drivers (multiqueue), but never for request-based block drivers. We did this as we were only creating non-blktrace additional debugfs files on that directory for make_request drivers. However, since blktrace *always* creates that directory anyway, we special-case the use of that directory on blktrace. Other than this being an eye-sore, this exposes request-based block drivers to the same debugfs fragile race that used to exist with make_request block drivers where if we start adding files onto that directory we can later run a race with a double removal of dentries on the directory if we don't deal with this carefully on blktrace. Instead, just simplify things by always creating the request_queue debugfs_dir on request_queue registration. Rename the mutex also to reflect the fact that this is used outside of the blktrace context. Signed-off-by: Luis Chamberlain Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index e214e0e9f868..c0701237116d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -528,9 +528,9 @@ struct request_queue { unsigned int sg_timeout; unsigned int sg_reserved_size; int node; + struct mutex debugfs_mutex; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace __rcu *blk_trace; - struct mutex blk_trace_mutex; #endif /* * for flush operations @@ -574,8 +574,9 @@ struct request_queue { struct list_head tag_set_list; struct bio_set bio_split; -#ifdef CONFIG_BLK_DEBUG_FS struct dentry *debugfs_dir; + +#ifdef CONFIG_BLK_DEBUG_FS struct dentry *sched_debugfs_dir; struct dentry *rqos_debugfs_dir; #endif -- cgit From b818f09e46f9f6a66471f81bf83094ff0a477d0c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:35 +0200 Subject: tty/sysrq: emergency_thaw_all does not depend on CONFIG_BLOCK We can also thaw non-block file systems. Remove the CONFIG_BLOCK in sysrq.c after making the prototype available unconditionally. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Reviewed-by: Greg Kroah-Hartman Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 3f881a892ea7..7f40dbafbf6d 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2593,7 +2593,6 @@ 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_all(void); 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 *); @@ -2633,6 +2632,7 @@ static inline bool sb_is_blkdev_sb(struct super_block *sb) return false; } #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; -- cgit 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 --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 7f40dbafbf6d..b1c960e9b84e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2646,8 +2646,6 @@ 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_finish_claiming(struct block_device *bdev, - struct block_device *whole, 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); -- cgit From 7dbac5baa887facf80373825b8f66c626703621f Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:37 +0200 Subject: fs: remove an unused block_device_operations forward declaration Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/fs.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index b1c960e9b84e..0d282c853691 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1774,8 +1774,6 @@ struct dir_context { loff_t pos; }; -struct block_device_operations; - /* These macros are for out of kernel modules to test that * the kernel supports the unlocked_ioctl and compat_ioctl * fields in struct file_operations. */ -- cgit From 4e24566a134ea167441a1ffa3d439a27cf400880 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:38 +0200 Subject: fs: remove the HAVE_UNLOCKED_IOCTL and HAVE_COMPAT_IOCTL defines These are not defined anywhere, and contrary to the comments we really do not care about out of tree code at all. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/fs.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 0d282c853691..224edcc5b56e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1774,12 +1774,6 @@ struct dir_context { loff_t pos; }; -/* These macros are for out of kernel modules to test that - * the kernel supports the unlocked_ioctl and compat_ioctl - * fields in struct file_operations. */ -#define HAVE_COMPAT_IOCTL 1 -#define HAVE_UNLOCKED_IOCTL 1 - /* * These flags let !MMU mmap() govern direct device mapping vs immediate * copying more easily for MAP_PRIVATE, especially for ROM filesystems. -- cgit From 75362a1792d16a61f0277d3610dea2f50a16bf3e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:39 +0200 Subject: fs: remove the mount_bdev and kill_block_super stubs No one calls these functions without CONFIG_BLOCK, so don't bother stubbing them out. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/fs.h | 16 ---------------- 1 file changed, 16 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 224edcc5b56e..9ee09e2b5a97 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2256,18 +2256,9 @@ struct file_system_type { #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME) -#ifdef CONFIG_BLOCK extern struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)); -#else -static inline struct dentry *mount_bdev(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data, - int (*fill_super)(struct super_block *, void *, int)) -{ - return ERR_PTR(-ENODEV); -} -#endif extern struct dentry *mount_single(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)); @@ -2276,14 +2267,7 @@ extern struct dentry *mount_nodev(struct file_system_type *fs_type, int (*fill_super)(struct super_block *, void *, int)); extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path); void generic_shutdown_super(struct super_block *sb); -#ifdef CONFIG_BLOCK void kill_block_super(struct super_block *sb); -#else -static inline void kill_block_super(struct super_block *sb) -{ - BUG(); -} -#endif void kill_anon_super(struct super_block *sb); void kill_litter_super(struct super_block *sb); void deactivate_super(struct super_block *sb); -- cgit From dd0dca223e091bbacdd3c7ce9cf06b373da59816 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:40 +0200 Subject: block: simplify sb_is_blkdev_sb Just use IS_ENABLED instead of providing a stub for !CONFIG_BLOCK. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/fs.h | 18 ++++++------------ 1 file changed, 6 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 9ee09e2b5a97..7f3ae38335d4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2557,6 +2557,12 @@ extern struct kmem_cache *names_cachep; #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) +extern struct super_block *blockdev_superblock; +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 *); @@ -2572,13 +2578,6 @@ 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 *); - -extern struct super_block *blockdev_superblock; - -static inline bool sb_is_blkdev_sb(struct super_block *sb) -{ - return sb == blockdev_superblock; -} #else static inline void bd_forget(struct inode *inode) {} static inline int sync_blockdev(struct block_device *bdev) { return 0; } @@ -2602,11 +2601,6 @@ static inline int emergency_thaw_bdev(struct super_block *sb) static inline void iterate_bdevs(void (*f)(struct block_device *, void *), void *arg) { } - -static inline bool sb_is_blkdev_sb(struct super_block *sb) -{ - return false; -} #endif void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); -- cgit 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 --- include/linux/blkdev.h | 46 +++++++++++++++++++++++++ include/linux/fs.h | 92 -------------------------------------------------- include/linux/genhd.h | 27 +++++++++++++++ include/linux/jbd2.h | 1 + 4 files changed, 74 insertions(+), 92 deletions(-) (limited to 'include/linux') 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 -- cgit From d2de7ea48d83195ef1310555f1fdd9e8e1bab0d3 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:42 +0200 Subject: fs: move the buffer_heads_over_limit stub to buffer_head.h Move the !CONFIG_BLOCK stub to the same place as the non-stub declaration. Signed-off-by: Christoph Hellwig Reviewed-by: Bart Van Assche Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - include/linux/buffer_head.h | 1 + 2 files changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index cf8f692f62a9..c824c6fee35d 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1838,7 +1838,6 @@ struct block_device; /* * stubs for when the block layer is configured out */ -#define buffer_heads_over_limit 0 static inline long nr_blockdev_pages(void) { diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 22fb11e2d2e0..6b47f94378c5 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -406,6 +406,7 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; } static inline void invalidate_inode_buffers(struct inode *inode) {} static inline int remove_inode_buffers(struct inode *inode) { return 1; } static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; } +#define buffer_heads_over_limit 0 #endif /* CONFIG_BLOCK */ #endif /* _LINUX_BUFFER_HEAD_H */ -- cgit From 1a4dcfa8bc10d6bf4f94ac20adc2b30a1da72cfd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 20 Jun 2020 09:16:43 +0200 Subject: block: reduce ifdef CONFIG_BLOCK madness in headers Large part of bio.h, blkdev.h and genhd.h are under ifdef CONFIG_BLOCK for no good reason. Only stub out function that are called from code that is not dependent on CONFIG_BLOCK and leave the harmless other declarations around. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 3 -- include/linux/blkdev.h | 92 ++++++++++++++++++++++---------------------------- include/linux/genhd.h | 14 ++++---- 3 files changed, 46 insertions(+), 63 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 91676d4b2dfe..0282f8aa8593 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -8,8 +8,6 @@ #include #include #include - -#ifdef CONFIG_BLOCK /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ #include @@ -824,5 +822,4 @@ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) bio->bi_opf |= REQ_NOWAIT; } -#endif /* CONFIG_BLOCK */ #endif /* __LINUX_BIO_H */ diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index c824c6fee35d..f788bddc9219 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -4,9 +4,6 @@ #include #include - -#ifdef CONFIG_BLOCK - #include #include #include @@ -1163,13 +1160,13 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, return __blk_rq_map_sg(q, rq, sglist, &last_sg); } extern void blk_dump_rq_flags(struct request *, char *); -extern long nr_blockdev_pages(void); bool __must_check blk_get_queue(struct request_queue *); struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id); extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); +#ifdef CONFIG_BLOCK /* * blk_plug permits building a queue of related requests by holding the I/O * fragments for a short period. This allows merging of sequential requests @@ -1229,9 +1226,47 @@ static inline bool blk_needs_flush_plug(struct task_struct *tsk) !list_empty(&plug->cb_list)); } +int blkdev_issue_flush(struct block_device *, gfp_t); +long nr_blockdev_pages(void); +#else /* CONFIG_BLOCK */ +struct blk_plug { +}; + +static inline void blk_start_plug(struct blk_plug *plug) +{ +} + +static inline void blk_finish_plug(struct blk_plug *plug) +{ +} + +static inline void blk_flush_plug(struct task_struct *task) +{ +} + +static inline void blk_schedule_flush_plug(struct task_struct *task) +{ +} + + +static inline bool blk_needs_flush_plug(struct task_struct *tsk) +{ + return false; +} + +static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask) +{ + return 0; +} + +static inline long nr_blockdev_pages(void) +{ + return 0; +} +#endif /* CONFIG_BLOCK */ + extern void blk_io_schedule(void); -int blkdev_issue_flush(struct block_device *, gfp_t); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); @@ -1831,51 +1866,6 @@ static inline bool blk_req_can_dispatch_to_zone(struct request *rq) } #endif /* CONFIG_BLK_DEV_ZONED */ -#else /* CONFIG_BLOCK */ - -struct block_device; - -/* - * stubs for when the block layer is configured out - */ - -static inline long nr_blockdev_pages(void) -{ - return 0; -} - -struct blk_plug { -}; - -static inline void blk_start_plug(struct blk_plug *plug) -{ -} - -static inline void blk_finish_plug(struct blk_plug *plug) -{ -} - -static inline void blk_flush_plug(struct task_struct *task) -{ -} - -static inline void blk_schedule_flush_plug(struct task_struct *task) -{ -} - - -static inline bool blk_needs_flush_plug(struct task_struct *tsk) -{ - return false; -} - -static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask) -{ - return 0; -} - -#endif /* CONFIG_BLOCK */ - static inline void blk_wake_io_task(struct task_struct *waiter) { /* @@ -1889,7 +1879,6 @@ static inline void blk_wake_io_task(struct task_struct *waiter) wake_up_process(waiter); } -#ifdef CONFIG_BLOCK unsigned long disk_start_io_acct(struct gendisk *disk, unsigned int sectors, unsigned int op); void disk_end_io_acct(struct gendisk *disk, unsigned int op, @@ -1915,7 +1904,6 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time) { return disk_end_io_acct(bio->bi_disk, bio_op(bio), start_time); } -#endif /* CONFIG_BLOCK */ int bdev_read_only(struct block_device *bdev); int set_blocksize(struct block_device *bdev, int size); diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 83f8e0d83228..31a54072ffd6 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -19,8 +19,6 @@ #include #include -#ifdef CONFIG_BLOCK - #define dev_to_disk(device) container_of((device), struct gendisk, part0.__dev) #define dev_to_part(device) container_of((device), struct hd_struct, __dev) #define disk_to_dev(disk) (&(disk)->part0.__dev) @@ -337,12 +335,9 @@ static inline void set_capacity(struct gendisk *disk, sector_t size) disk->part0.nr_sects = size; } -extern dev_t blk_lookup_devt(const char *name, int partno); - int bdev_disk_changed(struct block_device *bdev, bool invalidate); int blk_add_partitions(struct gendisk *disk, struct block_device *bdev); int blk_drop_partitions(struct block_device *bdev); -extern void printk_all_partitions(void); extern struct gendisk *__alloc_disk_node(int minors, int node_id); extern struct kobject *get_disk_and_module(struct gendisk *disk); @@ -400,10 +395,13 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, } #endif /* CONFIG_SYSFS */ +#ifdef CONFIG_BLOCK +void printk_all_partitions(void); +dev_t blk_lookup_devt(const char *name, int partno); #else /* CONFIG_BLOCK */ - -static inline void printk_all_partitions(void) { } - +static inline void printk_all_partitions(void) +{ +} static inline dev_t blk_lookup_devt(const char *name, int partno) { dev_t devt = MKDEV(0, 0); -- cgit 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 --- include/linux/blk_types.h | 39 ++++++++++++++++++++++++++++++++++++++- include/linux/blkdev.h | 1 + include/linux/dasd_mod.h | 2 ++ include/linux/fs.h | 41 ----------------------------------------- 4 files changed, 41 insertions(+), 42 deletions(-) (limited to 'include/linux') 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 From db9819c76c1fd48c30699381c94bba5c95dd467e Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 27 Jun 2020 09:31:47 +0200 Subject: block: remove bio_disassociate_blkg bio_disassociate_blkg has two callers, of which one immediately assigns a new value to >bi_blkg. Just open code the function in the two callers. Acked-by: Tejun Heo Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 0282f8aa8593..4cd229e175c0 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -497,13 +497,11 @@ static inline void bio_associate_blkg_from_page(struct bio *bio, #endif #ifdef CONFIG_BLK_CGROUP -void bio_disassociate_blkg(struct bio *bio); void bio_associate_blkg(struct bio *bio); void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); void bio_clone_blkg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ -static inline void bio_disassociate_blkg(struct bio *bio) { } static inline void bio_associate_blkg(struct bio *bio) { } static inline void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) -- cgit From a18b9b1590ca64f877588700de32c9ad236f405c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 27 Jun 2020 09:31:50 +0200 Subject: block: move bio_associate_blkg_from_page to mm/page_io.c bio_associate_blkg_from_page is a special purpose helper for swap bios that doesn't need access to bio internals. Move it to the swap code instead of having it in bio.c. Acked-by: Tejun Heo Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/bio.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bio.h b/include/linux/bio.h index 4cd229e175c0..c6d765382926 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -489,13 +489,6 @@ do { \ #define bio_dev(bio) \ disk_devt((bio)->bi_disk) -#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -void bio_associate_blkg_from_page(struct bio *bio, struct page *page); -#else -static inline void bio_associate_blkg_from_page(struct bio *bio, - struct page *page) { } -#endif - #ifdef CONFIG_BLK_CGROUP void bio_associate_blkg(struct bio *bio); void bio_associate_blkg_from_css(struct bio *bio, -- cgit From 28fc591ff9d64cbc2b780be95ee3fde8f6ade7fd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 27 Jun 2020 09:31:51 +0200 Subject: block: move the bio cgroup associatation helpers to blk-cgroup.c Keep the cgroup code together. Acked-by: Tejun Heo Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 30 ------------------------------ 1 file changed, 30 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index a57ebe2f00ab..60df97202314 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -183,10 +183,6 @@ extern bool blkcg_debug_stats; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); -struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q); -struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q); int blkcg_init_queue(struct request_queue *q); void blkcg_exit_queue(struct request_queue *q); @@ -480,32 +476,6 @@ static inline bool blkg_tryget(struct blkcg_gq *blkg) return blkg && percpu_ref_tryget(&blkg->refcnt); } -/** - * blkg_tryget_closest - try and get a blkg ref on the closet blkg - * @blkg: blkg to get - * - * This needs to be called rcu protected. As the failure mode here is to walk - * up the blkg tree, this ensure that the blkg->parent pointers are always - * valid. This returns the blkg that it ended up taking a reference on or %NULL - * if no reference was taken. - */ -static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) -{ - struct blkcg_gq *ret_blkg = NULL; - - WARN_ON_ONCE(!rcu_read_lock_held()); - - while (blkg) { - if (blkg_tryget(blkg)) { - ret_blkg = blkg; - break; - } - blkg = blkg->parent; - } - - return ret_blkg; -} - /** * blkg_put - put a blkg reference * @blkg: blkg to put -- cgit From 81630e27fff3dc1ccbf64ecb48a70170d7071545 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 27 Jun 2020 09:31:55 +0200 Subject: blk-cgroup: remove the !bio->bi_blkg check in blkcg_bio_issue_check This is purely a sanity check for grave programming errors. Remove it to simplify further work in this area. Acked-by: Tejun Heo Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 15 +-------------- 1 file changed, 1 insertion(+), 14 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 60df97202314..8e86b598316c 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -543,24 +543,11 @@ static inline void blkcg_bio_issue_init(struct bio *bio) static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { - struct blkcg_gq *blkg; + struct blkcg_gq *blkg = bio->bi_blkg; bool throtl = false; rcu_read_lock(); - - if (!bio->bi_blkg) { - char b[BDEVNAME_SIZE]; - - WARN_ONCE(1, - "no blkg associated for bio on block-device: %s\n", - bio_devname(bio, b)); - bio_associate_blkg(bio); - } - - blkg = bio->bi_blkg; - throtl = blk_throtl_bio(q, blkg, bio); - if (!throtl) { struct blkg_iostat_set *bis; int rwd, cpu; -- cgit From 93b8063804b62b55248e16499d853e1b20eff905 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 27 Jun 2020 09:31:57 +0200 Subject: blk-cgroup: move rcu locking from blkcg_bio_issue_check to blk_throtl_bio The only thing in blkcg_bio_issue_check that needs to be under rcu_read_lock is blk_throtl_bio, so move the locking there. Acked-by: Tejun Heo Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 8e86b598316c..8ab043c911f2 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -546,7 +546,6 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, struct blkcg_gq *blkg = bio->bi_blkg; bool throtl = false; - rcu_read_lock(); throtl = blk_throtl_bio(q, blkg, bio); if (!throtl) { struct blkg_iostat_set *bis; @@ -582,7 +581,6 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkcg_bio_issue_init(bio); - rcu_read_unlock(); return !throtl; } -- cgit From db18a53e5ba840993a3fc908dec648402ed740bd Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Sat, 27 Jun 2020 09:31:58 +0200 Subject: blk-cgroup: remove blkcg_bio_issue_check blkcg_bio_issue_check is a giant inline function that does three entirely different things. Factor out the blk-cgroup related bio initalization into a new helper, and the open code the sequence in the only caller, relying on the fact that all the actual functionality is stubbed out for non-cgroup builds. Acked-by: Tejun Heo Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-cgroup.h | 56 ++-------------------------------------------- 1 file changed, 2 insertions(+), 54 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 8ab043c911f2..431b2d18bf40 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -517,14 +517,6 @@ static inline void blkg_put(struct blkcg_gq *blkg) if (((d_blkg) = __blkg_lookup(css_to_blkcg(pos_css), \ (p_blkg)->q, false))) -#ifdef CONFIG_BLK_DEV_THROTTLING -extern bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, - struct bio *bio); -#else -static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, - struct bio *bio) { return false; } -#endif - bool __blkcg_punt_bio_submit(struct bio *bio); static inline bool blkcg_punt_bio_submit(struct bio *bio) @@ -540,50 +532,6 @@ static inline void blkcg_bio_issue_init(struct bio *bio) bio_issue_init(&bio->bi_issue, bio_sectors(bio)); } -static inline bool blkcg_bio_issue_check(struct request_queue *q, - struct bio *bio) -{ - struct blkcg_gq *blkg = bio->bi_blkg; - bool throtl = false; - - throtl = blk_throtl_bio(q, blkg, bio); - if (!throtl) { - struct blkg_iostat_set *bis; - int rwd, cpu; - - if (op_is_discard(bio->bi_opf)) - rwd = BLKG_IOSTAT_DISCARD; - else if (op_is_write(bio->bi_opf)) - rwd = BLKG_IOSTAT_WRITE; - else - rwd = BLKG_IOSTAT_READ; - - cpu = get_cpu(); - bis = per_cpu_ptr(blkg->iostat_cpu, cpu); - u64_stats_update_begin(&bis->sync); - - /* - * If the bio is flagged with BIO_CGROUP_ACCT it means this is a - * split bio and we would have already accounted for the size of - * the bio. - */ - if (!bio_flagged(bio, BIO_CGROUP_ACCT)) { - bio_set_flag(bio, BIO_CGROUP_ACCT); - bis->cur.bytes[rwd] += bio->bi_iter.bi_size; - } - bis->cur.ios[rwd]++; - - u64_stats_update_end(&bis->sync); - if (cgroup_subsys_on_dfl(io_cgrp_subsys)) - cgroup_rstat_updated(blkg->blkcg->css.cgroup, cpu); - put_cpu(); - } - - blkcg_bio_issue_init(bio); - - return !throtl; -} - static inline void blkcg_use_delay(struct blkcg_gq *blkg) { if (WARN_ON_ONCE(atomic_read(&blkg->use_delay) < 0)) @@ -657,6 +605,7 @@ static inline void blkcg_clear_delay(struct blkcg_gq *blkg) atomic_dec(&blkg->blkcg->css.cgroup->congestion_count); } +void blk_cgroup_bio_start(struct bio *bio); void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta); void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay); void blkcg_maybe_throttle_current(void); @@ -710,8 +659,7 @@ static inline void blkg_put(struct blkcg_gq *blkg) { } static inline bool blkcg_punt_bio_submit(struct bio *bio) { return false; } static inline void blkcg_bio_issue_init(struct bio *bio) { } -static inline bool blkcg_bio_issue_check(struct request_queue *q, - struct bio *bio) { return true; } +static inline void blk_cgroup_bio_start(struct bio *bio) { } #define blk_queue_for_each_rl(rl, q) \ for ((rl) = &(q)->root_rl; (rl); (rl) = NULL) -- cgit From 42fdc5e49c2be97db112d410d07044e0e2c7d5bb Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Jun 2020 17:08:34 +0200 Subject: blk-mq: remove the BLK_MQ_REQ_INTERNAL flag Just check for a non-NULL elevator directly to make the code more clear. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 1641ec6cd7e5..8986e88a986b 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -447,8 +447,6 @@ enum { BLK_MQ_REQ_NOWAIT = (__force blk_mq_req_flags_t)(1 << 0), /* allocate from reserved pool */ BLK_MQ_REQ_RESERVED = (__force blk_mq_req_flags_t)(1 << 1), - /* allocate internal/sched tag */ - BLK_MQ_REQ_INTERNAL = (__force blk_mq_req_flags_t)(1 << 2), /* set RQF_PREEMPT */ BLK_MQ_REQ_PREEMPT = (__force blk_mq_req_flags_t)(1 << 3), }; -- cgit From 65c763694398a2de63803b264dcf906b47f9d4c1 Mon Sep 17 00:00:00 2001 From: Ming Lei Date: Tue, 30 Jun 2020 18:24:56 +0800 Subject: blk-mq: pass request queue into get/put budget callback blk-mq budget is abstract from scsi's device queue depth, and it is always per-request-queue instead of hctx. It can be quite absurd to get a budget from one hctx, then dequeue a request from scheduler queue, and this request may not belong to this hctx, at least for bfq and deadline. So fix the mess and always pass request queue to get/put budget callback. Signed-off-by: Ming Lei Tested-by: Baolin Wang Reviewed-by: Johannes Thumshirn Reviewed-by: Christoph Hellwig Reviewed-by: Douglas Anderson Reviewed-by: Sagi Grimberg Cc: Sagi Grimberg Cc: Baolin Wang Cc: Christoph Hellwig Cc: Douglas Anderson Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 8986e88a986b..faa340b70123 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -270,8 +270,8 @@ struct blk_mq_queue_data { typedef blk_status_t (queue_rq_fn)(struct blk_mq_hw_ctx *, const struct blk_mq_queue_data *); typedef void (commit_rqs_fn)(struct blk_mq_hw_ctx *); -typedef bool (get_budget_fn)(struct blk_mq_hw_ctx *); -typedef void (put_budget_fn)(struct blk_mq_hw_ctx *); +typedef bool (get_budget_fn)(struct request_queue *); +typedef void (put_budget_fn)(struct request_queue *); typedef enum blk_eh_timer_return (timeout_fn)(struct request *, bool); typedef int (init_hctx_fn)(struct blk_mq_hw_ctx *, void *, unsigned int); typedef void (exit_hctx_fn)(struct blk_mq_hw_ctx *, unsigned int); -- cgit From f695ca3886ce72b027af7aa6040cd420cae2088c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 10:59:39 +0200 Subject: block: remove the request_queue argument from blk_queue_split The queue can be trivially derived from the bio, so pass one less argument. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 15497782c176..d002defc1789 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -871,7 +871,7 @@ extern void blk_rq_unprep_clone(struct request *rq); extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); extern int blk_rq_append_bio(struct request *rq, struct bio **bio); -extern void blk_queue_split(struct request_queue *, struct bio **); +extern void blk_queue_split(struct bio **); extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t, unsigned int, void __user *); -- cgit From c62b37d96b6eb3ec5ae4cbe00db107bf15aebc93 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 10:59:43 +0200 Subject: block: move ->make_request_fn to struct block_device_operations The make_request_fn is a little weird in that it sits directly in struct request_queue instead of an operation vector. Replace it with a block_device_operations method called submit_bio (which describes much better what it does). Also remove the request_queue argument to it, as the queue can be derived pretty trivially from the bio. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk-mq.h | 2 +- include/linux/blkdev.h | 7 ++----- include/linux/lightnvm.h | 3 +-- 3 files changed, 4 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index faa340b70123..23230c1d031e 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -596,6 +596,6 @@ static inline void blk_mq_cleanup_rq(struct request *rq) rq->q->mq_ops->cleanup_rq(rq); } -blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio); +blk_qc_t blk_mq_submit_bio(struct bio *bio); #endif diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d002defc1789..083ffc5bc51b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -286,8 +286,6 @@ static inline unsigned short req_get_ioprio(struct request *req) struct blk_queue_ctx; -typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); - struct bio_vec; enum blk_eh_timer_return { @@ -398,8 +396,6 @@ struct request_queue { struct blk_queue_stats *stats; struct rq_qos *rq_qos; - make_request_fn *make_request_fn; - const struct blk_mq_ops *mq_ops; /* sw queues */ @@ -1162,7 +1158,7 @@ static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq, extern void blk_dump_rq_flags(struct request *, char *); bool __must_check blk_get_queue(struct request_queue *); -struct request_queue *blk_alloc_queue(make_request_fn make_request, int node_id); +struct request_queue *blk_alloc_queue(int node_id); extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); @@ -1778,6 +1774,7 @@ static inline void blk_ksm_unregister(struct request_queue *q) { } struct block_device_operations { + blk_qc_t (*submit_bio) (struct bio *bio); int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int); diff --git a/include/linux/lightnvm.h b/include/linux/lightnvm.h index ee8ec2e68055..1db223710b28 100644 --- a/include/linux/lightnvm.h +++ b/include/linux/lightnvm.h @@ -631,7 +631,6 @@ static inline int nvm_next_ppa_in_chk(struct nvm_tgt_dev *dev, return last; } -typedef blk_qc_t (nvm_tgt_make_rq_fn)(struct request_queue *, struct bio *); typedef sector_t (nvm_tgt_capacity_fn)(void *); typedef void *(nvm_tgt_init_fn)(struct nvm_tgt_dev *, struct gendisk *, int flags); @@ -650,7 +649,7 @@ struct nvm_tgt_type { int flags; /* target entry points */ - nvm_tgt_make_rq_fn *make_rq; + const struct block_device_operations *bops; nvm_tgt_capacity_fn *capacity; /* module-specific init/teardown */ -- cgit From ed00aabd5eb9fb44d6aff1173234a2e911b9fead Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 10:59:44 +0200 Subject: block: rename generic_make_request to submit_bio_noacct generic_make_request has always been very confusingly misnamed, so rename it to submit_bio_noacct to make it clear that it is submit_bio minus accounting and a few checks. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 083ffc5bc51b..b73cfa6a5141 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -852,7 +852,7 @@ static inline void rq_flush_dcache_pages(struct request *rq) extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); -extern blk_qc_t generic_make_request(struct bio *bio); +blk_qc_t submit_bio_noacct(struct bio *bio); extern blk_qc_t direct_make_request(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); -- cgit From 5a6c35f9af416114588298aa7a90b15bbed15a41 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 10:59:47 +0200 Subject: block: remove direct_make_request Now that submit_bio_noacct has a decent blk-mq fast path there is no more need for this bypass. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index b73cfa6a5141..1cc913ffdbe2 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -853,7 +853,6 @@ static inline void rq_flush_dcache_pages(struct request *rq) extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); blk_qc_t submit_bio_noacct(struct bio *bio); -extern blk_qc_t direct_make_request(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); extern struct request *blk_get_request(struct request_queue *, unsigned int op, -- cgit 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 --- include/linux/blk_types.h | 1 - include/linux/blkdev.h | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) (limited to 'include/linux') 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 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 --- include/linux/blk_types.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') 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; /* -- cgit From 47b5e00322a3033851ab304f3c3873aebdfb4979 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Fri, 26 Jun 2020 10:01:57 +0200 Subject: block: remove the unused bd_private field from struct block_device Reviewed-by: Johannes Thumshirn Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 7 ------- 1 file changed, 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 667cd365fd04..b5f7105806e4 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -41,13 +41,6 @@ struct block_device { struct gendisk * bd_disk; 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; -- cgit 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 --- include/linux/blk_types.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') 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 From a564e23f0f99759f453dbefcb9160dec6d99df96 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Jul 2020 14:25:41 +0200 Subject: md: switch to ->check_events for media change notifications md is the last driver using the legacy media_changed method. Switch it over to (not so) new ->clear_events approach, which also removes the need for the ->revalidate_disk method. Signed-off-by: Christoph Hellwig [axboe: remove unused 'bdops' variable in disk_clear_events()] Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 408eb66a82fd..71173a1ffa8b 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -1781,8 +1781,6 @@ struct block_device_operations { int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); - /* ->media_changed() is DEPRECATED, use ->check_events() instead */ - int (*media_changed) (struct gendisk *); void (*unlock_native_capacity) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); -- cgit From 8c22eb3a77373c616f141b56f44ef225ee15c96b Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 8 Jul 2020 14:25:42 +0200 Subject: cdrom: remove the unused cdrom_media_changed function As well as the ->media_changed method. All these are left over from before the drivers were switched over to the check_events scheme. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/cdrom.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h index 8543fa59da72..f48d0a31deae 100644 --- a/include/linux/cdrom.h +++ b/include/linux/cdrom.h @@ -73,7 +73,6 @@ struct cdrom_device_ops { int (*drive_status) (struct cdrom_device_info *, int); unsigned int (*check_events) (struct cdrom_device_info *cdi, unsigned int clearing, int slot); - int (*media_changed) (struct cdrom_device_info *, int); int (*tray_move) (struct cdrom_device_info *, int); int (*lock_door) (struct cdrom_device_info *, int); int (*select_speed) (struct cdrom_device_info *, int); @@ -107,7 +106,6 @@ extern int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi, unsigned int clearing); -extern int cdrom_media_changed(struct cdrom_device_info *); extern int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi); extern void unregister_cdrom(struct cdrom_device_info *cdi); -- cgit From 492d76b215660be833f12c3fa7cf2faf39434841 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 11:06:20 +0200 Subject: writeback: remove {set,clear}_wb_congested Just merge them into their only callers. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index 90a7e844a098..cc5aa1f32b91 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -232,18 +232,8 @@ enum { BLK_RW_SYNC = 1, }; -void clear_wb_congested(struct bdi_writeback_congested *congested, int sync); -void set_wb_congested(struct bdi_writeback_congested *congested, int sync); - -static inline void clear_bdi_congested(struct backing_dev_info *bdi, int sync) -{ - clear_wb_congested(bdi->wb.congested, sync); -} - -static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync) -{ - set_wb_congested(bdi->wb.congested, sync); -} +void clear_bdi_congested(struct backing_dev_info *bdi, int sync); +void set_bdi_congested(struct backing_dev_info *bdi, int sync); struct wb_lock_cookie { bool locked; -- cgit From 8c911f3d4c074a17955a1757c9d1d5a9a5209ca5 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 1 Jul 2020 11:06:21 +0200 Subject: writeback: remove struct bdi_writeback_congested We never set any congested bits in the group writeback instances of it. And for the simpler bdi-wide case a simple scalar field is all that that is needed. Signed-off-by: Christoph Hellwig Signed-off-by: Jens Axboe --- include/linux/backing-dev-defs.h | 25 +------------------------ include/linux/backing-dev.h | 18 +----------------- include/linux/blk-cgroup.h | 6 ------ 3 files changed, 2 insertions(+), 47 deletions(-) (limited to 'include/linux') diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index cc5aa1f32b91..1cec4521e1fb 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -87,26 +87,6 @@ struct wb_completion { #define DEFINE_WB_COMPLETION(cmpl, bdi) \ struct wb_completion cmpl = WB_COMPLETION_INIT(bdi) -/* - * For cgroup writeback, multiple wb's may map to the same blkcg. Those - * wb's can operate mostly independently but should share the congested - * state. To facilitate such sharing, the congested state is tracked using - * the following struct which is created on demand, indexed by blkcg ID on - * its bdi, and refcounted. - */ -struct bdi_writeback_congested { - unsigned long state; /* WB_[a]sync_congested flags */ - refcount_t refcnt; /* nr of attached wb's and blkg */ - -#ifdef CONFIG_CGROUP_WRITEBACK - struct backing_dev_info *__bdi; /* the associated bdi, set to NULL - * on bdi unregistration. For memcg-wb - * internal use only! */ - int blkcg_id; /* ID of the associated blkcg */ - struct rb_node rb_node; /* on bdi->cgwb_congestion_tree */ -#endif -}; - /* * Each wb (bdi_writeback) can perform writeback operations, is measured * and throttled, independently. Without cgroup writeback, each bdi @@ -140,7 +120,7 @@ struct bdi_writeback { struct percpu_counter stat[NR_WB_STAT_ITEMS]; - struct bdi_writeback_congested *congested; + unsigned long congested; /* WB_[a]sync_congested flags */ unsigned long bw_time_stamp; /* last time write bw is updated */ unsigned long dirtied_stamp; @@ -208,11 +188,8 @@ struct backing_dev_info { struct list_head wb_list; /* list of all wbs */ #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ - struct rb_root cgwb_congested_tree; /* their congested states */ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */ -#else - struct bdi_writeback_congested *wb_congested; #endif wait_queue_head_t wb_waitq; diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 6b3504bf7a42..9173d2c22b4a 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -173,7 +173,7 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) if (bdi->congested_fn) return bdi->congested_fn(bdi->congested_data, cong_bits); - return wb->congested->state & cong_bits; + return wb->congested & cong_bits; } long congestion_wait(int sync, long timeout); @@ -224,9 +224,6 @@ static inline int bdi_sched_wait(void *word) #ifdef CONFIG_CGROUP_WRITEBACK -struct bdi_writeback_congested * -wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp); -void wb_congested_put(struct bdi_writeback_congested *congested); struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css); struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, @@ -404,19 +401,6 @@ static inline bool inode_cgwb_enabled(struct inode *inode) return false; } -static inline struct bdi_writeback_congested * -wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) -{ - refcount_inc(&bdi->wb_congested->refcnt); - return bdi->wb_congested; -} - -static inline void wb_congested_put(struct bdi_writeback_congested *congested) -{ - if (refcount_dec_and_test(&congested->refcnt)) - kfree(congested); -} - static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { return &bdi->wb; diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 431b2d18bf40..c8fc9792ac77 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -109,12 +109,6 @@ struct blkcg_gq { struct hlist_node blkcg_node; struct blkcg *blkcg; - /* - * Each blkg gets congested separately and the congestion state is - * propagated to the matching bdi_writeback_congested. - */ - struct bdi_writeback_congested *wb_congested; - /* all non-root blkcg_gq's are guaranteed to have access to parent */ struct blkcg_gq *parent; -- cgit 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 --- include/linux/backing-dev-defs.h | 4 ---- include/linux/backing-dev.h | 4 ---- include/linux/device-mapper.h | 11 ----------- 3 files changed, 19 deletions(-) (limited to 'include/linux') 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 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 --- include/linux/blkdev.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') 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 From ecdef9f459ad24bf987267df6c25967819016707 Mon Sep 17 00:00:00 2001 From: Coly Li Date: Fri, 17 Jul 2020 10:42:29 +0800 Subject: block: change REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL to be odd numbers Currently REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL are defined as even numbers 6 and 8, such zone reset bios are treated as READ bios by bio_data_dir(), which is obviously misleading. The macro bio_data_dir() is defined in include/linux/bio.h as, 55 #define bio_data_dir(bio) \ 56 (op_is_write(bio_op(bio)) ? WRITE : READ) And op_is_write() is defined in include/linux/blk_types.h as, 397 static inline bool op_is_write(unsigned int op) 398 { 399 return (op & 1); 400 } The convention of op_is_write() is when there is data transfer then the op code should be odd number, and treat as a write op. bio_data_dir() treats all bio direction as READ if op_is_write() reports false, and WRITE if op_is_write() reports true. Because REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL are even numbers, although they don't transfer data but reporting them as READ bio by bio_data_dir() is misleading and might be wrong. Because these two commands will reset the writer pointers of the resetting zones, and all content after the reset write pointer will be invalid and unaccessible, obviously they are not READ bios in any means. This patch changes REQ_OP_ZONE_RESET from 6 to 15, and changes REQ_OP_ZONE_RESET_ALL from 8 to 17. Now bios with these two op code can be treated as WRITE by bio_data_dir(). Although they don't transfer data, now we keep them consistent with REQ_OP_DISCARD and REQ_OP_WRITE_ZEROES with the ituition that they change on-media content and should be WRITE request. Signed-off-by: Coly Li Reviewed-by: Damien Le Moal Reviewed-by: Chaitanya Kulkarni Cc: Christoph Hellwig Cc: Hannes Reinecke Cc: Jens Axboe Cc: Johannes Thumshirn Cc: Keith Busch Cc: Shaun Tancheff Signed-off-by: Jens Axboe --- include/linux/blk_types.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 07facaf62b72..4ecf4fed171f 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -327,12 +327,8 @@ enum req_opf { REQ_OP_DISCARD = 3, /* securely erase sectors */ REQ_OP_SECURE_ERASE = 5, - /* reset a zone write pointer */ - REQ_OP_ZONE_RESET = 6, /* write the same sector many times */ REQ_OP_WRITE_SAME = 7, - /* reset all the zone present on the device */ - REQ_OP_ZONE_RESET_ALL = 8, /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = 9, /* Open a zone */ @@ -343,6 +339,10 @@ enum req_opf { REQ_OP_ZONE_FINISH = 12, /* write data at the current zone write pointer */ REQ_OP_ZONE_APPEND = 13, + /* reset a zone write pointer */ + REQ_OP_ZONE_RESET = 15, + /* reset all the zone present on the device */ + REQ_OP_ZONE_RESET_ALL = 17, /* SCSI passthrough using struct scsi_request */ REQ_OP_SCSI_IN = 32, -- cgit From ef45fe470e1e5410db4af87abc5d5055427945ac Mon Sep 17 00:00:00 2001 From: Boris Burkov Date: Mon, 1 Jun 2020 13:12:05 -0700 Subject: blk-cgroup: show global disk stats in root cgroup io.stat In order to improve consistency and usability in cgroup stat accounting, we would like to support the root cgroup's io.stat. Since the root cgroup has processes doing io even if the system has no explicitly created cgroups, we need to be careful to avoid overhead in that case. For that reason, the rstat algorithms don't handle the root cgroup, so just turning the file on wouldn't give correct statistics. To get around this, we simulate flushing the iostat struct by filling it out directly from global disk stats. The result is a root cgroup io.stat file consistent with both /proc/diskstats and io.stat. Note that in order to collect the disk stats, we needed to iterate over devices. To facilitate that, we had to change the linkage of a disk_type to external so that it can be used from blk-cgroup.c to iterate over disks. Suggested-by: Tejun Heo Signed-off-by: Boris Burkov Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- include/linux/genhd.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/genhd.h b/include/linux/genhd.h index 31a54072ffd6..4ab853461dff 100644 --- a/include/linux/genhd.h +++ b/include/linux/genhd.h @@ -24,6 +24,7 @@ #define disk_to_dev(disk) (&(disk)->part0.__dev) #define part_to_dev(part) (&((part)->__dev)) +extern const struct device_type disk_type; extern struct device_type part_type; extern struct class block_class; -- cgit