diff options
Diffstat (limited to 'include/linux/fs.h')
| -rw-r--r-- | include/linux/fs.h | 311 |
1 files changed, 231 insertions, 80 deletions
diff --git a/include/linux/fs.h b/include/linux/fs.h index 803e5a9b2654..13dab191a23e 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2,7 +2,7 @@ #define _LINUX_FS_H #include <linux/linkage.h> -#include <linux/wait.h> +#include <linux/wait_bit.h> #include <linux/kdev_t.h> #include <linux/dcache.h> #include <linux/path.h> @@ -18,8 +18,10 @@ #include <linux/bug.h> #include <linux/mutex.h> #include <linux/rwsem.h> +#include <linux/mm_types.h> #include <linux/capability.h> #include <linux/semaphore.h> +#include <linux/fcntl.h> #include <linux/fiemap.h> #include <linux/rculist_bl.h> #include <linux/atomic.h> @@ -30,6 +32,8 @@ #include <linux/percpu-rwsem.h> #include <linux/workqueue.h> #include <linux/delayed_call.h> +#include <linux/uuid.h> +#include <linux/errseq.h> #include <asm/byteorder.h> #include <uapi/linux/fs.h> @@ -68,6 +72,8 @@ extern int leases_enable, lease_break_time; extern int sysctl_protected_symlinks; extern int sysctl_protected_hardlinks; +typedef __kernel_rwf_t rwf_t; + struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); @@ -142,6 +148,9 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, /* File was opened by fanotify and shouldn't generate fanotify events */ #define FMODE_NONOTIFY ((__force fmode_t)0x4000000) +/* File is capable of returning -EAGAIN if I/O will block */ +#define FMODE_NOWAIT ((__force fmode_t)0x8000000) + /* * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector * that indicates that they should check the contents of the iovec are @@ -261,6 +270,18 @@ struct page; struct address_space; struct writeback_control; +/* + * Write life time hint values. + */ +enum rw_hint { + WRITE_LIFE_NOT_SET = 0, + WRITE_LIFE_NONE = RWH_WRITE_LIFE_NONE, + WRITE_LIFE_SHORT = RWH_WRITE_LIFE_SHORT, + WRITE_LIFE_MEDIUM = RWH_WRITE_LIFE_MEDIUM, + WRITE_LIFE_LONG = RWH_WRITE_LIFE_LONG, + WRITE_LIFE_EXTREME = RWH_WRITE_LIFE_EXTREME, +}; + #define IOCB_EVENTFD (1 << 0) #define IOCB_APPEND (1 << 1) #define IOCB_DIRECT (1 << 2) @@ -268,6 +289,7 @@ struct writeback_control; #define IOCB_DSYNC (1 << 4) #define IOCB_SYNC (1 << 5) #define IOCB_WRITE (1 << 6) +#define IOCB_NOWAIT (1 << 7) struct kiocb { struct file *ki_filp; @@ -275,23 +297,14 @@ struct kiocb { void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); void *private; int ki_flags; -}; + enum rw_hint ki_hint; +} __randomize_layout; static inline bool is_sync_kiocb(struct kiocb *kiocb) { return kiocb->ki_complete == NULL; } -static inline int iocb_flags(struct file *file); - -static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) -{ - *kiocb = (struct kiocb) { - .ki_filp = filp, - .ki_flags = iocb_flags(filp), - }; -} - /* * "descriptor" for what we're up to with a read. * This allows us to use the same read code yet @@ -379,7 +392,7 @@ struct address_space { struct radix_tree_root page_tree; /* radix tree of all pages */ spinlock_t tree_lock; /* and lock protecting it */ atomic_t i_mmap_writable;/* count VM_SHARED mappings */ - struct rb_root i_mmap; /* tree of private and shared mappings */ + struct rb_root_cached i_mmap; /* tree of private and shared mappings */ struct rw_semaphore i_mmap_rwsem; /* protect tree, count, list */ /* Protected by tree_lock together with the radix tree */ unsigned long nrpages; /* number of total pages */ @@ -390,9 +403,10 @@ struct address_space { unsigned long flags; /* error bits */ spinlock_t private_lock; /* for use by the address_space */ gfp_t gfp_mask; /* implicit gfp mask for allocations */ - struct list_head private_list; /* ditto */ + struct list_head private_list; /* for use by the address_space */ void *private_data; /* ditto */ -} __attribute__((aligned(sizeof(long)))); + errseq_t wb_err; +} __attribute__((aligned(sizeof(long)))) __randomize_layout; /* * On most architectures that alignment is already the case; but * must be enforced here for CRIS, to let the least significant bit @@ -415,6 +429,7 @@ struct block_device { #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; @@ -435,7 +450,7 @@ struct block_device { int bd_fsfreeze_count; /* Mutex for freeze */ struct mutex bd_fsfreeze_mutex; -}; +} __randomize_layout; /* * Radix-tree tags, for tagging dirty and writeback pages within the pagecache @@ -472,7 +487,7 @@ static inline void i_mmap_unlock_read(struct address_space *mapping) */ static inline int mapping_mapped(struct address_space *mapping) { - return !RB_EMPTY_ROOT(&mapping->i_mmap); + return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } /* @@ -592,6 +607,7 @@ struct inode { spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; unsigned int i_blkbits; + enum rw_hint i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED @@ -653,7 +669,7 @@ struct inode { #endif void *i_private; /* fs or device private pointer */ -}; +} __randomize_layout; static inline unsigned int i_blocksize(const struct inode *node) { @@ -846,6 +862,7 @@ struct file { * Must not be taken from IRQ context. */ spinlock_t f_lock; + enum rw_hint f_write_hint; atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; @@ -868,7 +885,9 @@ struct file { struct list_head f_tfile_llink; #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; -} __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ + errseq_t f_wb_err; +} __randomize_layout + __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; @@ -891,9 +910,9 @@ static inline struct file *get_file(struct file *f) /* Page cache limit. The filesystems should put that into their s_maxbytes limits, otherwise bad things can happen in VM. */ #if BITS_PER_LONG==32 -#define MAX_LFS_FILESIZE (((loff_t)PAGE_SIZE << (BITS_PER_LONG-1))-1) +#define MAX_LFS_FILESIZE ((loff_t)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 -#define MAX_LFS_FILESIZE ((loff_t)0x7fffffffffffffffLL) +#define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif #define FL_POSIX 1 @@ -984,7 +1003,6 @@ struct file_lock { unsigned char fl_type; unsigned int fl_pid; int fl_link_cpu; /* what cpu's list is this on? */ - struct pid *fl_nspid; wait_queue_head_t fl_wait; struct file *fl_file; loff_t fl_start; @@ -1005,7 +1023,7 @@ struct file_lock { int state; /* state of grant or error if -ve */ } afs; } fl_u; -}; +} __randomize_layout; struct file_lock_context { spinlock_t flc_lock; @@ -1021,8 +1039,6 @@ struct file_lock_context { #define OFFT_OFFSET_MAX INT_LIMIT(off_t) #endif -#include <linux/fcntl.h> - extern void send_sigio(struct fown_struct *fown, int fd, int band); /* @@ -1038,14 +1054,14 @@ static inline struct inode *locks_inode(const struct file *f) } #ifdef CONFIG_FILE_LOCKING -extern int fcntl_getlk(struct file *, unsigned int, struct flock __user *); +extern int fcntl_getlk(struct file *, unsigned int, struct flock *); extern int fcntl_setlk(unsigned int, struct file *, unsigned int, - struct flock __user *); + struct flock *); #if BITS_PER_LONG == 32 -extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 __user *); +extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); extern int fcntl_setlk64(unsigned int, struct file *, unsigned int, - struct flock64 __user *); + struct flock64 *); #endif extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); @@ -1219,7 +1235,7 @@ static inline struct inode *file_inode(const struct file *f) static inline struct dentry *file_dentry(const struct file *file) { - return d_real(file->f_path.dentry, file_inode(file), 0); + return d_real(file->f_path.dentry, file_inode(file), 0, 0); } static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) @@ -1249,12 +1265,37 @@ extern void fasync_free(struct fasync_struct *); extern void kill_fasync(struct fasync_struct **, int, int); extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force); -extern void f_setown(struct file *filp, unsigned long arg, int force); +extern int f_setown(struct file *filp, unsigned long arg, 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); -struct mm_struct; +/* + * sb->s_flags. Note that these mirror the equivalent MS_* flags where + * represented in both. + */ +#define SB_RDONLY 1 /* Mount read-only */ +#define SB_NOSUID 2 /* Ignore suid and sgid bits */ +#define SB_NODEV 4 /* Disallow access to device special files */ +#define SB_NOEXEC 8 /* Disallow program execution */ +#define SB_SYNCHRONOUS 16 /* Writes are synced at once */ +#define SB_MANDLOCK 64 /* Allow mandatory locks on an FS */ +#define SB_DIRSYNC 128 /* Directory modifications are synchronous */ +#define SB_NOATIME 1024 /* Do not update access times. */ +#define SB_NODIRATIME 2048 /* Do not update directory access times */ +#define SB_SILENT 32768 +#define SB_POSIXACL (1<<16) /* VFS does not apply the umask */ +#define SB_KERNMOUNT (1<<22) /* this is a kern_mount call */ +#define SB_I_VERSION (1<<23) /* Update inode I_version field */ +#define SB_LAZYTIME (1<<25) /* Update the on-disk [acm]times lazily */ + +/* These sb flags are internal to the kernel */ +#define SB_SUBMOUNT (1<<26) +#define SB_NOREMOTELOCK (1<<27) +#define SB_NOSEC (1<<28) +#define SB_BORN (1<<29) +#define SB_ACTIVE (1<<30) +#define SB_NOUSER (1<<31) /* * Umount options @@ -1328,8 +1369,8 @@ struct super_block { struct sb_writers s_writers; - char s_id[32]; /* Informational name */ - u8 s_uuid[16]; /* UUID */ + char s_id[32]; /* Informational name */ + uuid_t s_uuid; /* UUID */ void *s_fs_info; /* Filesystem private info */ unsigned int s_max_links; @@ -1351,11 +1392,6 @@ struct super_block { */ char *s_subtype; - /* - * Saved mount options for lazy filesystems using - * generic_show_options() - */ - char __rcu *s_options; const struct dentry_operations *s_d_op; /* default d_op for dentries */ /* @@ -1404,7 +1440,7 @@ struct super_block { spinlock_t s_inode_wblist_lock; struct list_head s_inodes_wb; /* writeback inodes */ -}; +} __randomize_layout; /* Helper functions so that in most cases filesystems will * not need to deal directly with kuid_t and kgid_t and can @@ -1690,7 +1726,7 @@ struct file_operations { u64); ssize_t (*dedupe_file_range)(struct file *, u64, u64, struct file *, u64); -}; +} __randomize_layout; struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); @@ -1739,25 +1775,16 @@ static inline int call_mmap(struct file *file, struct vm_area_struct *vma) return file->f_op->mmap(file, vma); } -static inline int call_fsync(struct file *file, loff_t start, loff_t end, - int datasync) -{ - return file->f_op->fsync(file, start, end, datasync); -} - ssize_t rw_copy_check_uvector(int type, const struct iovec __user * uvector, unsigned long nr_segs, unsigned long fast_segs, struct iovec *fast_pointer, struct iovec **ret_pointer); extern ssize_t __vfs_read(struct file *, char __user *, size_t, loff_t *); -extern ssize_t __vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *); extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *); extern ssize_t vfs_readv(struct file *, const struct iovec __user *, - unsigned long, loff_t *, int); -extern ssize_t vfs_writev(struct file *, const struct iovec __user *, - unsigned long, loff_t *, int); + unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, @@ -1833,7 +1860,7 @@ struct super_operations { * possible to override it selectively if you really wanted to with some * ioctl() that is not currently implemented. * - * Exception: MS_RDONLY is always applied to the entire file system. + * Exception: SB_RDONLY is always applied to the entire file system. * * Unfortunately, it is possible to change a filesystems flags with it mounted * with files in use. This means that all of the inodes will not have their @@ -1842,19 +1869,20 @@ struct super_operations { */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) -#define IS_RDONLY(inode) ((inode)->i_sb->s_flags & MS_RDONLY) -#define IS_SYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS) || \ +static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & MS_RDONLY; } +#define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) +#define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) -#define IS_DIRSYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS|MS_DIRSYNC) || \ +#define IS_DIRSYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) -#define IS_MANDLOCK(inode) __IS_FLG(inode, MS_MANDLOCK) -#define IS_NOATIME(inode) __IS_FLG(inode, MS_RDONLY|MS_NOATIME) -#define IS_I_VERSION(inode) __IS_FLG(inode, MS_I_VERSION) +#define IS_MANDLOCK(inode) __IS_FLG(inode, SB_MANDLOCK) +#define IS_NOATIME(inode) __IS_FLG(inode, SB_RDONLY|SB_NOATIME) +#define IS_I_VERSION(inode) __IS_FLG(inode, SB_I_VERSION) #define IS_NOQUOTA(inode) ((inode)->i_flags & S_NOQUOTA) #define IS_APPEND(inode) ((inode)->i_flags & S_APPEND) #define IS_IMMUTABLE(inode) ((inode)->i_flags & S_IMMUTABLE) -#define IS_POSIXACL(inode) __IS_FLG(inode, MS_POSIXACL) +#define IS_POSIXACL(inode) __IS_FLG(inode, SB_POSIXACL) #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) @@ -1873,6 +1901,25 @@ static inline bool HAS_UNMAPPED_ID(struct inode *inode) return !uid_valid(inode->i_uid) || !gid_valid(inode->i_gid); } +static inline enum rw_hint file_write_hint(struct file *file) +{ + if (file->f_write_hint != WRITE_LIFE_NOT_SET) + return file->f_write_hint; + + return file_inode(file)->i_write_hint; +} + +static inline int iocb_flags(struct file *file); + +static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp) +{ + *kiocb = (struct kiocb) { + .ki_filp = filp, + .ki_flags = iocb_flags(filp), + .ki_hint = file_write_hint(filp), + }; +} + /* * Inode state bits. Protected by inode->i_lock * @@ -1929,6 +1976,9 @@ static inline bool HAS_UNMAPPED_ID(struct inode *inode) * wb stat updates to grab mapping->tree_lock. See * inode_switch_wb_work_fn() for details. * + * I_OVL_INUSE Used by overlayfs to get exclusive ownership on upper + * and work dirs among overlayfs mounts. + * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #define I_DIRTY_SYNC (1 << 0) @@ -1949,6 +1999,7 @@ static inline bool HAS_UNMAPPED_ID(struct inode *inode) #define __I_DIRTY_TIME_EXPIRED 12 #define I_DIRTY_TIME_EXPIRED (1 << __I_DIRTY_TIME_EXPIRED) #define I_WB_SWITCH (1 << 13) +#define I_OVL_INUSE (1 << 14) #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) @@ -2152,7 +2203,7 @@ static inline int __mandatory_lock(struct inode *ino) } /* - * ... and these candidates should be on MS_MANDLOCK mounted fs, + * ... and these candidates should be on SB_MANDLOCK mounted fs, * otherwise these will be advisory locks */ @@ -2445,9 +2496,13 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev, #endif /* fs/char_dev.c */ -#define CHRDEV_MAJOR_HASH_SIZE 255 +#define CHRDEV_MAJOR_MAX 512 /* Marks the bottom of the first segment of free char majors */ #define CHRDEV_MAJOR_DYN_END 234 +/* Marks the top and bottom of the second segment of free char majors */ +#define CHRDEV_MAJOR_DYN_EXT_START 511 +#define CHRDEV_MAJOR_DYN_EXT_END 384 + extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *); extern int register_chrdev_region(dev_t, unsigned, const char *); extern int __register_chrdev(unsigned int major, unsigned int baseminor, @@ -2474,14 +2529,14 @@ static inline void unregister_chrdev(unsigned int major, const char *name) #define BDEVT_SIZE 10 /* Largest string for MAJ:MIN for blkdev */ #ifdef CONFIG_BLOCK -#define BLKDEV_MAJOR_HASH_SIZE 255 +#define BLKDEV_MAJOR_MAX 512 extern const char *__bdevname(dev_t, char *buffer); 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_HASH_SIZE 0 +#define BLKDEV_MAJOR_MAX 0 #endif extern void init_special_inode(struct inode *, umode_t, dev_t); @@ -2513,10 +2568,19 @@ extern int invalidate_inode_pages2_range(struct address_space *mapping, extern int write_inode_now(struct inode *, int); extern int filemap_fdatawrite(struct address_space *); extern int filemap_flush(struct address_space *); -extern int filemap_fdatawait(struct address_space *); -extern void filemap_fdatawait_keep_errors(struct address_space *); +extern int filemap_fdatawait_keep_errors(struct address_space *mapping); extern int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); + +static inline int filemap_fdatawait(struct address_space *mapping) +{ + return filemap_fdatawait_range(mapping, 0, LLONG_MAX); +} + +extern bool filemap_range_has_page(struct address_space *, loff_t lstart, + loff_t lend); +extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, + loff_t lend); extern int filemap_write_and_wait(struct address_space *mapping); extern int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); @@ -2525,6 +2589,67 @@ extern int __filemap_fdatawrite_range(struct address_space *mapping, extern int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); extern int filemap_check_errors(struct address_space *mapping); +extern void __filemap_set_wb_err(struct address_space *mapping, int err); + +extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, + loff_t lend); +extern int __must_check file_check_and_advance_wb_err(struct file *file); +extern int __must_check file_write_and_wait_range(struct file *file, + loff_t start, loff_t end); + +static inline int file_write_and_wait(struct file *file) +{ + return file_write_and_wait_range(file, 0, LLONG_MAX); +} + +/** + * filemap_set_wb_err - set a writeback error on an address_space + * @mapping: mapping in which to set writeback error + * @err: error to be set in mapping + * + * When writeback fails in some way, we must record that error so that + * userspace can be informed when fsync and the like are called. We endeavor + * to report errors on any file that was open at the time of the error. Some + * internal callers also need to know when writeback errors have occurred. + * + * When a writeback error occurs, most filesystems will want to call + * filemap_set_wb_err to record the error in the mapping so that it will be + * automatically reported whenever fsync is called on the file. + */ +static inline void filemap_set_wb_err(struct address_space *mapping, int err) +{ + /* Fastpath for common case of no error */ + if (unlikely(err)) + __filemap_set_wb_err(mapping, err); +} + +/** + * filemap_check_wb_error - has an error occurred since the mark was sampled? + * @mapping: mapping to check for writeback errors + * @since: previously-sampled errseq_t + * + * Grab the errseq_t value from the mapping, and see if it has changed "since" + * the given value was sampled. + * + * If it has then report the latest error set, otherwise return 0. + */ +static inline int filemap_check_wb_err(struct address_space *mapping, + errseq_t since) +{ + return errseq_check(&mapping->wb_err, since); +} + +/** + * filemap_sample_wb_err - sample the current errseq_t to test for later errors + * @mapping: mapping to be sampled + * + * Writeback errors are always reported relative to a particular sample point + * in the past. This function provides those sample points. + */ +static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) +{ + return errseq_sample(&mapping->wb_err); +} extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync); @@ -2688,15 +2813,15 @@ static inline const char *kernel_read_file_id_str(enum kernel_read_file_id id) return kernel_read_file_str[id]; } -extern int kernel_read(struct file *, loff_t, char *, unsigned long); extern int kernel_read_file(struct file *, void **, loff_t *, loff_t, enum kernel_read_file_id); -extern int kernel_read_file_from_path(char *, void **, loff_t *, loff_t, +extern int kernel_read_file_from_path(const char *, void **, loff_t *, loff_t, enum kernel_read_file_id); extern int kernel_read_file_from_fd(int, void **, loff_t *, loff_t, enum kernel_read_file_id); -extern ssize_t kernel_write(struct file *, const char *, size_t, loff_t); -extern ssize_t __kernel_write(struct file *, const char *, size_t, loff_t *); +extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *); +extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *); +extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *); extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ @@ -2747,6 +2872,7 @@ static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { }; #endif extern void unlock_new_inode(struct inode *); extern unsigned int get_next_ino(void); +extern void evict_inodes(struct super_block *sb); extern void __iget(struct inode * inode); extern void iget_failed(struct inode *); @@ -2789,8 +2915,10 @@ extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *); extern ssize_t generic_perform_write(struct file *, struct iov_iter *, loff_t); -ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos); -ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos); +ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos, + rwf_t flags); +ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos, + rwf_t flags); /* fs/block_dev.c */ extern ssize_t blkdev_read_iter(struct kiocb *iocb, struct iov_iter *to); @@ -2843,7 +2971,7 @@ enum { DIO_SKIP_DIO_COUNT = 0x08, }; -void dio_end_io(struct bio *bio, int error); +void dio_end_io(struct bio *bio); ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, struct block_device *bdev, struct iov_iter *iter, @@ -2912,6 +3040,10 @@ void __inode_add_bytes(struct inode *inode, loff_t bytes); void inode_add_bytes(struct inode *inode, loff_t bytes); void __inode_sub_bytes(struct inode *inode, loff_t bytes); void inode_sub_bytes(struct inode *inode, loff_t bytes); +static inline loff_t __inode_get_bytes(struct inode *inode) +{ + return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes; +} loff_t inode_get_bytes(struct inode *inode); void inode_set_bytes(struct inode *inode, loff_t bytes); const char *simple_get_link(struct dentry *, struct inode *, @@ -2936,8 +3068,7 @@ static inline int vfs_lstat(const char __user *name, struct kstat *stat) static inline int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat, int flags) { - return vfs_statx(dfd, filename, flags | AT_NO_AUTOMOUNT, - stat, STATX_BASIC_STATS); + return vfs_statx(dfd, filename, flags, stat, STATX_BASIC_STATS); } static inline int vfs_fstat(int fd, struct kstat *stat) { @@ -2956,7 +3087,7 @@ extern int generic_block_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len, get_block_t *get_block); -extern void get_filesystem(struct file_system_type *fs); +extern struct file_system_type *get_filesystem(struct file_system_type *fs); extern void put_filesystem(struct file_system_type *fs); extern struct file_system_type *get_fs_type(const char *name); extern struct super_block *get_super(struct block_device *); @@ -3033,15 +3164,16 @@ extern void setattr_copy(struct inode *inode, const struct iattr *attr); extern int file_update_time(struct file *file); -extern int generic_show_options(struct seq_file *m, struct dentry *root); -extern void save_mount_options(struct super_block *sb, char *options); -extern void replace_mount_options(struct super_block *sb, char *options); - static inline bool io_is_direct(struct file *filp) { return (filp->f_flags & O_DIRECT) || IS_DAX(filp->f_mapping->host); } +static inline bool vma_is_dax(struct vm_area_struct *vma) +{ + return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host); +} + static inline int iocb_flags(struct file *file) { int res = 0; @@ -3056,6 +3188,25 @@ static inline int iocb_flags(struct file *file) return res; } +static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags) +{ + if (unlikely(flags & ~RWF_SUPPORTED)) + return -EOPNOTSUPP; + + if (flags & RWF_NOWAIT) { + if (!(ki->ki_filp->f_mode & FMODE_NOWAIT)) + return -EOPNOTSUPP; + ki->ki_flags |= IOCB_NOWAIT; + } + if (flags & RWF_HIPRI) + ki->ki_flags |= IOCB_HIPRI; + if (flags & RWF_DSYNC) + ki->ki_flags |= IOCB_DSYNC; + if (flags & RWF_SYNC) + ki->ki_flags |= (IOCB_DSYNC | IOCB_SYNC); + return 0; +} + static inline ino_t parent_ino(struct dentry *dentry) { ino_t res; @@ -3168,7 +3319,7 @@ static inline int check_sticky(struct inode *dir, struct inode *inode) static inline void inode_has_no_xattr(struct inode *inode) { - if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC)) + if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC)) inode->i_flags |= S_NOSEC; } |