diff options
Diffstat (limited to 'include/linux/fs.h')
| -rw-r--r-- | include/linux/fs.h | 200 |
1 files changed, 126 insertions, 74 deletions
diff --git a/include/linux/fs.h b/include/linux/fs.h index 6ca11e241a24..0df3e5f0dd2b 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -146,8 +146,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)(1 << 12)) -/* File is huge (eg. /dev/mem): treat loff_t as unsigned */ -#define FMODE_UNSIGNED_OFFSET ((__force fmode_t)(1 << 13)) +/* FMODE_* bit 13 */ /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)(1 << 14)) @@ -409,10 +408,10 @@ struct address_space_operations { int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata); + struct folio **foliop, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, - struct page *page, void *fsdata); + struct folio *folio, void *fsdata); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); @@ -683,7 +682,8 @@ struct inode { #endif /* Misc */ - unsigned long i_state; + u32 i_state; + /* 32-bit hole */ struct rw_semaphore i_rwsem; unsigned long dirtied_when; /* jiffies of first dirtying */ @@ -746,6 +746,21 @@ struct inode { void *i_private; /* fs or device private pointer */ } __randomize_layout; +/* + * Get bit address from inode->i_state to use with wait_var_event() + * infrastructre. + */ +#define inode_state_wait_address(inode, bit) ((char *)&(inode)->i_state + (bit)) + +struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe, + struct inode *inode, u32 bit); + +static inline void inode_wake_up_bit(struct inode *inode, u32 bit) +{ + /* Caller is responsible for correct memory barriers. */ + wake_up_var(inode_state_wait_address(inode, bit)); +} + struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode); static inline unsigned int i_blocksize(const struct inode *node) @@ -948,6 +963,7 @@ static inline unsigned imajor(const struct inode *inode) } struct fown_struct { + struct file *file; /* backpointer for security modules */ rwlock_t lock; /* protects pid, uid, euid fields */ struct pid *pid; /* pid or -pgrp where SIGIO should be sent */ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ @@ -987,52 +1003,69 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) index < ra->start + ra->size); } -/* - * f_{lock,count,pos_lock} members can be highly contended and share - * the same cacheline. f_{lock,mode} are very frequently used together - * and so share the same cacheline as well. The read-mostly - * f_{path,inode,op} are kept on a separate cacheline. +/** + * struct file - Represents a file + * @f_count: reference count + * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context. + * @f_mode: FMODE_* flags often used in hotpaths + * @f_op: file operations + * @f_mapping: Contents of a cacheable, mappable object. + * @private_data: filesystem or driver specific data + * @f_inode: cached inode + * @f_flags: file flags + * @f_iocb_flags: iocb flags + * @f_cred: stashed credentials of creator/opener + * @f_path: path of the file + * @f_pos_lock: lock protecting file position + * @f_pipe: specific to pipes + * @f_pos: file position + * @f_security: LSM security context of this file + * @f_owner: file owner + * @f_wb_err: writeback error + * @f_sb_err: per sb writeback errors + * @f_ep: link of all epoll hooks for this file + * @f_task_work: task work entry point + * @f_llist: work queue entrypoint + * @f_ra: file's readahead state + * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.) */ struct file { + atomic_long_t f_count; + spinlock_t f_lock; + fmode_t f_mode; + const struct file_operations *f_op; + struct address_space *f_mapping; + void *private_data; + struct inode *f_inode; + unsigned int f_flags; + unsigned int f_iocb_flags; + const struct cred *f_cred; + /* --- cacheline 1 boundary (64 bytes) --- */ + struct path f_path; union { - /* fput() uses task work when closing and freeing file (default). */ - struct callback_head f_task_work; - /* fput() must use workqueue (most kernel threads). */ - struct llist_node f_llist; - unsigned int f_iocb_flags; + /* regular files (with FMODE_ATOMIC_POS) and directories */ + struct mutex f_pos_lock; + /* pipes */ + u64 f_pipe; }; - - /* - * Protects f_ep, f_flags. - * Must not be taken from IRQ context. - */ - spinlock_t f_lock; - fmode_t f_mode; - atomic_long_t f_count; - struct mutex f_pos_lock; - loff_t f_pos; - unsigned int f_flags; - struct fown_struct f_owner; - const struct cred *f_cred; - struct file_ra_state f_ra; - struct path f_path; - struct inode *f_inode; /* cached value */ - const struct file_operations *f_op; - - u64 f_version; + loff_t f_pos; #ifdef CONFIG_SECURITY - void *f_security; + void *f_security; #endif - /* needed for tty driver, and maybe others */ - void *private_data; - + /* --- cacheline 2 boundary (128 bytes) --- */ + struct fown_struct *f_owner; + errseq_t f_wb_err; + errseq_t f_sb_err; #ifdef CONFIG_EPOLL - /* Used by fs/eventpoll.c to link all the hooks to this file */ - struct hlist_head *f_ep; -#endif /* #ifdef CONFIG_EPOLL */ - struct address_space *f_mapping; - errseq_t f_wb_err; - errseq_t f_sb_err; /* for syncfs */ + struct hlist_head *f_ep; +#endif + union { + struct callback_head f_task_work; + struct llist_node f_llist; + struct file_ra_state f_ra; + freeptr_t f_freeptr; + }; + /* --- cacheline 3 boundary (192 bytes) --- */ } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ @@ -1077,6 +1110,12 @@ struct file_lease; #define OFFT_OFFSET_MAX type_max(off_t) #endif +int file_f_owner_allocate(struct file *file); +static inline struct fown_struct *file_f_owner(const struct file *file) +{ + return READ_ONCE(file->f_owner); +} + extern void send_sigio(struct fown_struct *fown, int fd, int band); static inline struct inode *file_inode(const struct file *f) @@ -1125,7 +1164,7 @@ extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force extern int f_setown(struct file *filp, int who, int force); extern void f_delown(struct file *filp); extern pid_t f_getown(struct file *filp); -extern int send_sigurg(struct fown_struct *fown); +extern int send_sigurg(struct file *file); /* * sb->s_flags. Note that these mirror the equivalent MS_* flags where @@ -1268,7 +1307,7 @@ struct super_block { time64_t s_time_min; time64_t s_time_max; #ifdef CONFIG_FSNOTIFY - __u32 s_fsnotify_mask; + u32 s_fsnotify_mask; struct fsnotify_sb_info *s_fsnotify_info; #endif @@ -1684,7 +1723,7 @@ static inline bool __sb_start_write_trylock(struct super_block *sb, int level) #define __sb_writers_acquired(sb, lev) \ percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) #define __sb_writers_release(sb, lev) \ - percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) + percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], _THIS_IP_) /** * __sb_write_started - check if sb freeze level is held @@ -2074,6 +2113,8 @@ struct file_operations { #define FOP_DIO_PARALLEL_WRITE ((__force fop_flags_t)(1 << 3)) /* Contains huge pages */ #define FOP_HUGE_PAGES ((__force fop_flags_t)(1 << 4)) +/* Treat loff_t as unsigned (e.g., /dev/mem) */ +#define FOP_UNSIGNED_OFFSET ((__force fop_flags_t)(1 << 5)) /* Wrap a directory iterator that needs exclusive inode access */ int wrap_directory_iterator(struct file *, struct dir_context *, @@ -2373,8 +2414,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * * I_REFERENCED Marks the inode as recently references on the LRU list. * - * I_DIO_WAKEUP Never set. Only used as a key for wait_on_bit(). - * * I_WB_SWITCH Cgroup bdi_writeback switching in progress. Used to * synchronize competing switching instances and to tell * wb stat updates to grab the i_pages lock. See @@ -2397,30 +2436,32 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src, * i_count. * * Q: What is the difference between I_WILL_FREE and I_FREEING? + * + * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait + * upon. There's one free address left. */ -#define I_DIRTY_SYNC (1 << 0) -#define I_DIRTY_DATASYNC (1 << 1) -#define I_DIRTY_PAGES (1 << 2) -#define __I_NEW 3 +#define __I_NEW 0 #define I_NEW (1 << __I_NEW) -#define I_WILL_FREE (1 << 4) -#define I_FREEING (1 << 5) -#define I_CLEAR (1 << 6) -#define __I_SYNC 7 +#define __I_SYNC 1 #define I_SYNC (1 << __I_SYNC) -#define I_REFERENCED (1 << 8) -#define __I_DIO_WAKEUP 9 -#define I_DIO_WAKEUP (1 << __I_DIO_WAKEUP) +#define __I_LRU_ISOLATING 2 +#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) + +#define I_DIRTY_SYNC (1 << 3) +#define I_DIRTY_DATASYNC (1 << 4) +#define I_DIRTY_PAGES (1 << 5) +#define I_WILL_FREE (1 << 6) +#define I_FREEING (1 << 7) +#define I_CLEAR (1 << 8) +#define I_REFERENCED (1 << 9) #define I_LINKABLE (1 << 10) #define I_DIRTY_TIME (1 << 11) -#define I_WB_SWITCH (1 << 13) -#define I_OVL_INUSE (1 << 14) -#define I_CREATING (1 << 15) -#define I_DONTCACHE (1 << 16) -#define I_SYNC_QUEUED (1 << 17) -#define I_PINNING_NETFS_WB (1 << 18) -#define __I_LRU_ISOLATING 19 -#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING) +#define I_WB_SWITCH (1 << 12) +#define I_OVL_INUSE (1 << 13) +#define I_CREATING (1 << 14) +#define I_DONTCACHE (1 << 15) +#define I_SYNC_QUEUED (1 << 16) +#define I_PINNING_NETFS_WB (1 << 17) #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC) #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES) @@ -2554,10 +2595,17 @@ struct super_block *sget(struct file_system_type *type, struct super_block *sget_dev(struct fs_context *fc, dev_t dev); /* Alas, no aliases. Too much hassle with bringing module.h everywhere */ -#define fops_get(fops) \ - (((fops) && try_module_get((fops)->owner) ? (fops) : NULL)) -#define fops_put(fops) \ - do { if (fops) module_put((fops)->owner); } while(0) +#define fops_get(fops) ({ \ + const struct file_operations *_fops = (fops); \ + (((_fops) && try_module_get((_fops)->owner) ? (_fops) : NULL)); \ +}) + +#define fops_put(fops) ({ \ + const struct file_operations *_fops = (fops); \ + if (_fops) \ + module_put((_fops)->owner); \ +}) + /* * This one is to be used *ONLY* from ->open() instances. * fops must be non-NULL, pinned down *and* module dependencies @@ -3183,6 +3231,8 @@ extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize); extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence); extern loff_t generic_file_llseek_size(struct file *file, loff_t offset, int whence, loff_t maxsize, loff_t eof); +loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence, + u64 *cookie); extern loff_t fixed_size_llseek(struct file *file, loff_t offset, int whence, loff_t size); extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t); @@ -3220,7 +3270,9 @@ static inline ssize_t blockdev_direct_IO(struct kiocb *iocb, } #endif +bool inode_dio_finished(const struct inode *inode); void inode_dio_wait(struct inode *inode); +void inode_dio_wait_interruptible(struct inode *inode); /** * inode_dio_begin - signal start of a direct I/O requests @@ -3244,7 +3296,7 @@ static inline void inode_dio_begin(struct inode *inode) static inline void inode_dio_end(struct inode *inode) { if (atomic_dec_and_test(&inode->i_dio_count)) - wake_up_bit(&inode->i_state, __I_DIO_WAKEUP); + wake_up_var(&inode->i_dio_count); } extern void inode_set_flags(struct inode *inode, unsigned int flags, @@ -3337,7 +3389,7 @@ extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter); extern int simple_empty(struct dentry *); extern int simple_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, - struct page **pagep, void **fsdata); + struct folio **foliop, void **fsdata); extern const struct address_space_operations ram_aops; extern int always_delete_dentry(const struct dentry *); extern struct inode *alloc_anon_inode(struct super_block *); |