/* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_H #define _LINUX_FS_H #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include #include struct backing_dev_info; struct bdi_writeback; struct bio; struct export_operations; struct hd_geometry; struct iovec; struct kiocb; struct kobject; struct pipe_inode_info; struct poll_table_struct; struct kstatfs; struct vm_area_struct; struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; struct workqueue_struct; struct iov_iter; struct fscrypt_info; struct fscrypt_operations; struct fs_context; struct fs_parameter_description; extern void __init inode_init(void); extern void __init inode_init_early(void); extern void __init files_init(void); extern void __init files_maxfiles_init(void); extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); extern unsigned int sysctl_nr_open; extern struct inodes_stat_t inodes_stat; extern int leases_enable, lease_break_time; extern int sysctl_protected_symlinks; extern int sysctl_protected_hardlinks; extern int sysctl_protected_fifos; extern int sysctl_protected_regular; 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); typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private); #define MAY_EXEC 0x00000001 #define MAY_WRITE 0x00000002 #define MAY_READ 0x00000004 #define MAY_APPEND 0x00000008 #define MAY_ACCESS 0x00000010 #define MAY_OPEN 0x00000020 #define MAY_CHDIR 0x00000040 /* called from RCU mode, don't block */ #define MAY_NOT_BLOCK 0x00000080 /* * flags in file.f_mode. Note that FMODE_READ and FMODE_WRITE must correspond * to O_WRONLY and O_RDWR via the strange trick in do_dentry_open() */ /* file is open for reading */ #define FMODE_READ ((__force fmode_t)0x1) /* file is open for writing */ #define FMODE_WRITE ((__force fmode_t)0x2) /* file is seekable */ #define FMODE_LSEEK ((__force fmode_t)0x4) /* file can be accessed using pread */ #define FMODE_PREAD ((__force fmode_t)0x8) /* file can be accessed using pwrite */ #define FMODE_PWRITE ((__force fmode_t)0x10) /* File is opened for execution with sys_execve / sys_uselib */ #define FMODE_EXEC ((__force fmode_t)0x20) /* File is opened with O_NDELAY (only set for block devices) */ #define FMODE_NDELAY ((__force fmode_t)0x40) /* File is opened with O_EXCL (only set for block devices) */ #define FMODE_EXCL ((__force fmode_t)0x80) /* File is opened using open(.., 3, ..) and is writeable only for ioctls (specialy hack for floppy.c) */ #define FMODE_WRITE_IOCTL ((__force fmode_t)0x100) /* 32bit hashes as llseek() offset (for directories) */ #define FMODE_32BITHASH ((__force fmode_t)0x200) /* 64bit hashes as llseek() offset (for directories) */ #define FMODE_64BITHASH ((__force fmode_t)0x400) /* * Don't update ctime and mtime. * * Currently a special hack for the XFS open_by_handle ioctl, but we'll * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon. */ #define FMODE_NOCMTIME ((__force fmode_t)0x800) /* Expect random access pattern */ #define FMODE_RANDOM ((__force fmode_t)0x1000) /* File is huge (eg. /dev/kmem): treat loff_t as unsigned */ #define FMODE_UNSIGNED_OFFSET ((__force fmode_t)0x2000) /* File is opened with O_PATH; almost nothing can be done with it */ #define FMODE_PATH ((__force fmode_t)0x4000) /* File needs atomic accesses to f_pos */ #define FMODE_ATOMIC_POS ((__force fmode_t)0x8000) /* Write access to underlying fs */ #define FMODE_WRITER ((__force fmode_t)0x10000) /* Has read method(s) */ #define FMODE_CAN_READ ((__force fmode_t)0x20000) /* Has write method(s) */ #define FMODE_CAN_WRITE ((__force fmode_t)0x40000) #define FMODE_OPENED ((__force fmode_t)0x80000) #define FMODE_CREATED ((__force fmode_t)0x100000) /* File is stream-like */ #define FMODE_STREAM ((__force fmode_t)0x200000) /* 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) /* File represents mount that needs unmounting */ #define FMODE_NEED_UNMOUNT ((__force fmode_t)0x10000000) /* File does not contribute to nr_files count */ #define FMODE_NOACCOUNT ((__force fmode_t)0x20000000) /* * Flag for rw_copy_check_uvector and compat_rw_copy_check_uvector * that indicates that they should check the contents of the iovec are * valid, but not check the memory that the iovec elements * points too. */ #define CHECK_IOVEC_ONLY -1 /* * Attribute flags. These should be or-ed together to figure out what * has been changed! */ #define ATTR_MODE (1 << 0) #define ATTR_UID (1 << 1) #define ATTR_GID (1 << 2) #define ATTR_SIZE (1 << 3) #define ATTR_ATIME (1 << 4) #define ATTR_MTIME (1 << 5) #define ATTR_CTIME (1 << 6) #define ATTR_ATIME_SET (1 << 7) #define ATTR_MTIME_SET (1 << 8) #define ATTR_FORCE (1 << 9) /* Not a change, but a change it */ #define ATTR_KILL_SUID (1 << 11) #define ATTR_KILL_SGID (1 << 12) #define ATTR_FILE (1 << 13) #define ATTR_KILL_PRIV (1 << 14) #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */ #define ATTR_TIMES_SET (1 << 16) #define ATTR_TOUCH (1 << 17) /* * Whiteout is represented by a char device. The following constants define the * mode and device number to use. */ #define WHITEOUT_MODE 0 #define WHITEOUT_DEV 0 /* * This is the Inode Attributes structure, used for notify_change(). It * uses the above definitions as flags, to know which values have changed. * Also, in this manner, a Filesystem can look at only the values it cares * about. Basically, these are the attributes that the VFS layer can * request to change from the FS layer. * * Derek Atkins 94-10-20 */ struct iattr { unsigned int ia_valid; umode_t ia_mode; kuid_t ia_uid; kgid_t ia_gid; loff_t ia_size; struct timespec64 ia_atime; struct timespec64 ia_mtime; struct timespec64 ia_ctime; /* * Not an attribute, but an auxiliary info for filesystems wanting to * implement an ftruncate() like method. NOTE: filesystem should * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL). */ struct file *ia_file; }; /* * Includes for diskquotas. */ #include /* * Maximum number of layers of fs stack. Needs to be limited to * prevent kernel stack overflow */ #define FILESYSTEM_MAX_STACK_DEPTH 2 /** * enum positive_aop_returns - aop return codes with specific semantics * * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has * completed, that the page is still locked, and * should be considered active. The VM uses this hint * to return the page to the active list -- it won't * be a candidate for writeback again in the near * future. Other callers must be careful to unlock * the page if they get this return. Returned by * writepage(); * * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has * unlocked it and the page might have been truncated. * The caller should back up to acquiring a new page and * trying again. The aop will be taking reasonable * precautions not to livelock. If the caller held a page * reference, it should drop it before retrying. Returned * by readpage(). * * address_space_operation functions return these large constants to indicate * special semantics to the caller. These are much larger than the bytes in a * page to allow for functions that return the number of bytes operated on in a * given page. */ enum positive_aop_returns { AOP_WRITEPAGE_ACTIVATE = 0x80000, AOP_TRUNCATED_PAGE = 0x80001, }; #define AOP_FLAG_CONT_EXPAND 0x0001 /* called from cont_expand */ #define AOP_FLAG_NOFS 0x0002 /* used by filesystem to direct * helper code (eg buffer layer) * to clear GFP_FS from alloc */ /* * oh the beauties of C type declarations. */ struct page; struct address_space; struct writeback_control; /* * Write life time hint values. * Stored in struct inode as u8. */ 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) #define IOCB_HIPRI (1 << 3) #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; /* The 'ki_filp' pointer is shared in a union for aio */ randomized_struct_fields_start loff_t ki_pos; void (*ki_complete)(struct kiocb *iocb, long ret, long ret2); void *private; int ki_flags; u16 ki_hint; u16 ki_ioprio; /* See linux/ioprio.h */ unsigned int ki_cookie; /* for ->iopoll */ randomized_struct_fields_end }; static inline bool is_sync_kiocb(struct kiocb *kiocb) { return kiocb->ki_complete == NULL; } /* * "descriptor" for what we're up to with a read. * This allows us to use the same read code yet * have multiple different users of the data that * we read from a file. * * The simplest case just copies the data to user * mode. */ typedef struct { size_t written; size_t count; union { char __user *buf; void *data; } arg; int error; } read_descriptor_t; typedef int (*read_actor_t)(read_descriptor_t *, struct page *, unsigned long, unsigned long); struct address_space_operations { int (*writepage)(struct page *page, struct writeback_control *wbc); int (*readpage)(struct file *, struct page *); /* Write back some dirty pages from this mapping. */ int (*writepages)(struct address_space *, struct writeback_control *); /* Set a page dirty. Return true if this dirtied it */ int (*set_page_dirty)(struct page *page); /* * Reads in the requested pages. Unlike ->readpage(), this is * PURELY used for read-ahead!. */ int (*readpages)(struct file *filp, struct address_space *mapping, struct list_head *pages, unsigned nr_pages); int (*write_begin)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); int (*write_end)(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); /* Unfortunately this kludge is needed for FIBMAP. Don't use it */ sector_t (*bmap)(struct address_space *, sector_t); void (*invalidatepage) (struct page *, unsigned int, unsigned int); int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter); /* * migrate the contents of a page to the specified target. If * migrate_mode is MIGRATE_ASYNC, it must not block. */ int (*migratepage) (struct address_space *, struct page *, struct page *, enum migrate_mode); bool (*isolate_page)(struct page *, isolate_mode_t); void (*putback_page)(struct page *); int (*launder_page) (struct page *); int (*is_partially_uptodate) (struct page *, unsigned long, unsigned long); void (*is_dirty_writeback) (struct page *, bool *, bool *); int (*error_remove_page)(struct address_space *, struct page *); /* swapfile support */ int (*swap_activate)(struct swap_info_struct *sis, struct file *file, sector_t *span); void (*swap_deactivate)(struct file *file); }; extern const struct address_space_operations empty_aops; /* * pagecache_write_begin/pagecache_write_end must be used by general code * to write into the pagecache. */ int pagecache_write_begin(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata); int pagecache_write_end(struct file *, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata); /** * struct address_space - Contents of a cacheable, mappable object. * @host: Owner, either the inode or the block_device. * @i_pages: Cached pages. * @gfp_mask: Memory allocation flags to use for allocating pages. * @i_mmap_writable: Number of VM_SHARED mappings. * @i_mmap: Tree of private and shared mappings. * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable. * @nrpages: Number of page entries, protected by the i_pages lock. * @nrexceptional: Shadow or DAX entries, protected by the i_pages lock. * @writeback_index: Writeback starts here. * @a_ops: Methods. * @flags: Error bits and flags (AS_*). * @wb_err: The most recent error which has occurred. * @private_lock: For use by the owner of the address_space. * @private_list: For use by the owner of the address_space. * @private_data: For use by the owner of the address_space. */ struct address_space { struct inode *host; struct xarray i_pages; gfp_t gfp_mask; atomic_t i_mmap_writable; struct rb_root_cached i_mmap; struct rw_semaphore i_mmap_rwsem; unsigned long nrpages; unsigned long nrexceptional; pgoff_t writeback_index; const struct address_space_operations *a_ops; unsigned long flags; errseq_t wb_err; spinlock_t private_lock; struct list_head private_list; void *private_data; } __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 * 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 #define PAGECACHE_TAG_WRITEBACK XA_MARK_1 #define PAGECACHE_TAG_TOWRITE XA_MARK_2 /* * Returns true if any of the pages in the mapping are marked with the tag. */ static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag) { return xa_marked(&mapping->i_pages, tag); } static inline void i_mmap_lock_write(struct address_space *mapping) { down_write(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_write(struct address_space *mapping) { up_write(&mapping->i_mmap_rwsem); } static inline void i_mmap_lock_read(struct address_space *mapping) { down_read(&mapping->i_mmap_rwsem); } static inline void i_mmap_unlock_read(struct address_space *mapping) { up_read(&mapping->i_mmap_rwsem); } /* * Might pages of this file be mapped into userspace? */ static inline int mapping_mapped(struct address_space *mapping) { return !RB_EMPTY_ROOT(&mapping->i_mmap.rb_root); } /* * Might pages of this file have been modified in userspace? * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap_pgoff * marks vma as VM_SHARED if it is shared, and the file was opened for * writing i.e. vma may be mprotected writable even if now readonly. * * If i_mmap_writable is negative, no new writable mappings are allowed. You * can only deny writable mappings, if none exists right now. */ static inline int mapping_writably_mapped(struct address_space *mapping) { return atomic_read(&mapping->i_mmap_writable) > 0; } static inline int mapping_map_writable(struct address_space *mapping) { return atomic_inc_unless_negative(&mapping->i_mmap_writable) ? 0 : -EPERM; } static inline void mapping_unmap_writable(struct address_space *mapping) { atomic_dec(&mapping->i_mmap_writable); } static inline int mapping_deny_writable(struct address_space *mapping) { return atomic_dec_unless_positive(&mapping->i_mmap_writable) ? 0 : -EBUSY; } static inline void mapping_allow_writable(struct address_space *mapping) { atomic_inc(&mapping->i_mmap_writable); } /* * Use sequence counter to get consistent i_size on 32-bit processors. */ #if BITS_PER_LONG==32 && defined(CONFIG_SMP) #include #define __NEED_I_SIZE_ORDERED #define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount) #else #define i_size_ordered_init(inode) do { } while (0) #endif struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) #define ACL_DONT_CACHE ((void *)(-3)) static inline struct posix_acl * uncached_acl_sentinel(struct task_struct *task) { return (void *)task + 1; } static inline bool is_uncached_acl(struct posix_acl *acl) { return (long)acl & 1; } #define IOP_FASTPERM 0x0001 #define IOP_LOOKUP 0x0002 #define IOP_NOFOLLOW 0x0004 #define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 struct fsnotify_mark_connector; /* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning * of the 'struct inode' */ struct inode { umode_t i_mode; unsigned short i_opflags; kuid_t i_uid; kgid_t i_gid; unsigned int i_flags; #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; #endif const struct inode_operations *i_op; struct super_block *i_sb; struct address_space *i_mapping; #ifdef CONFIG_SECURITY void *i_security; #endif /* Stat data, not accessed from path walking */ unsigned long i_ino; /* * Filesystems may only read i_nlink directly. They shall use the * following functions for modification: * * (set|clear|inc|drop)_nlink * inode_(inc|dec)_link_count */ union { const unsigned int i_nlink; unsigned int __i_nlink; }; dev_t i_rdev; loff_t i_size; struct timespec64 i_atime; struct timespec64 i_mtime; struct timespec64 i_ctime; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; u8 i_blkbits; u8 i_write_hint; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; #endif /* Misc */ unsigned long i_state; struct rw_semaphore i_rwsem; unsigned long dirtied_when; /* jiffies of first dirtying */ unsigned long dirtied_time_when; struct hlist_node i_hash; struct list_head i_io_list; /* backing dev IO list */ #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *i_wb; /* the associated cgroup wb */ /* foreign inode detection, see wbc_detach_inode() */ int i_wb_frn_winner; u16 i_wb_frn_avg_time; u16 i_wb_frn_history; #endif struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; struct list_head i_wb_list; /* backing dev writeback list */ union { struct hlist_head i_dentry; struct rcu_head i_rcu; }; atomic64_t i_version; atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; #ifdef CONFIG_IMA atomic_t i_readcount; /* struct files open RO */ #endif union { const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ void (*free_inode)(struct inode *); }; struct file_lock_context *i_flctx; struct address_space i_data; struct list_head i_devices; union { struct pipe_inode_info *i_pipe; struct block_device *i_bdev; struct cdev *i_cdev; char *i_link; unsigned i_dir_seq; }; __u32 i_generation; #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ struct fsnotify_mark_connector __rcu *i_fsnotify_marks; #endif #ifdef CONFIG_FS_ENCRYPTION struct fscrypt_info *i_crypt_info; #endif void *i_private; /* fs or device private pointer */ } __randomize_layout; static inline unsigned int i_blocksize(const struct inode *node) { return (1 << node->i_blkbits); } static inline int inode_unhashed(struct inode *inode) { return hlist_unhashed(&inode->i_hash); } /* * __mark_inode_dirty expects inodes to be hashed. Since we don't * want special inodes in the fileset inode space, we make them * appear hashed, but do not put on any lists. hlist_del() * will work fine and require no locking. */ static inline void inode_fake_hash(struct inode *inode) { hlist_add_fake(&inode->i_hash); } /* * inode->i_mutex nesting subclasses for the lock validator: * * 0: the object of the current VFS operation * 1: parent * 2: child/target * 3: xattr * 4: second non-directory * 5: second parent (when locking independent directories in rename) * * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two * non-directories at once. * * The locking order between these classes is * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory */ enum inode_i_mutex_lock_class { I_MUTEX_NORMAL, I_MUTEX_PARENT, I_MUTEX_CHILD, I_MUTEX_XATTR, I_MUTEX_NONDIR2, I_MUTEX_PARENT2, }; static inline void inode_lock(struct inode *inode) { down_write(&inode->i_rwsem); } static inline void inode_unlock(struct inode *inode) { up_write(&inode->i_rwsem); } static inline void inode_lock_shared(struct inode *inode) { down_read(&inode->i_rwsem); } static inline void inode_unlock_shared(struct inode *inode) { up_read(&inode->i_rwsem); } static inline int inode_trylock(struct inode *inode) { return down_write_trylock(&inode->i_rwsem); } static inline int inode_trylock_shared(struct inode *inode) { return down_read_trylock(&inode->i_rwsem); } static inline int inode_is_locked(struct inode *inode) { return rwsem_is_locked(&inode->i_rwsem); } static inline void inode_lock_nested(struct inode *inode, unsigned subclass) { down_write_nested(&inode->i_rwsem, subclass); } static inline void inode_lock_shared_nested(struct inode *inode, unsigned subclass) { down_read_nested(&inode->i_rwsem, subclass); } void lock_two_nondirectories(struct inode *, struct inode*); void unlock_two_nondirectories(struct inode *, struct inode*); /* * NOTE: in a 32bit arch with a preemptable kernel and * an UP compile the i_size_read/write must be atomic * with respect to the local cpu (unlike with preempt disabled), * but they don't need to be atomic with respect to other cpus like in * true SMP (so they need either to either locally disable irq around * the read or for example on x86 they can be still implemented as a * cmpxchg8b without the need of the lock prefix). For SMP compiles * and 64bit archs it makes no difference if preempt is enabled or not. */ static inline loff_t i_size_read(const struct inode *inode) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) loff_t i_size; unsigned int seq; do { seq = read_seqcount_begin(&inode->i_size_seqcount); i_size = inode->i_size; } while (read_seqcount_retry(&inode->i_size_seqcount, seq)); return i_size; #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) loff_t i_size; preempt_disable(); i_size = inode->i_size; preempt_enable(); return i_size; #else return inode->i_size; #endif } /* * NOTE: unlike i_size_read(), i_size_write() does need locking around it * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount * can be lost, resulting in subsequent i_size_read() calls spinning forever. */ static inline void i_size_write(struct inode *inode, loff_t i_size) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) preempt_disable(); write_seqcount_begin(&inode->i_size_seqcount); inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); preempt_enable(); #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) preempt_disable(); inode->i_size = i_size; preempt_enable(); #else inode->i_size = i_size; #endif } static inline unsigned iminor(const struct inode *inode) { return MINOR(inode->i_rdev); } 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 */ enum pid_type pid_type; /* Kind of process group SIGIO should be sent to */ kuid_t uid, euid; /* uid/euid of process setting the owner */ int signum; /* posix.1b rt signal to be delivered on IO */ }; /* * Track a single file's readahead state */ struct file_ra_state { pgoff_t start; /* where readahead started */ unsigned int size; /* # of readahead pages */ unsigned int async_size; /* do asynchronous readahead when there are only # of pages ahead */ unsigned int ra_pages; /* Maximum readahead window */ unsigned int mmap_miss; /* Cache miss stat for mmap accesses */ loff_t prev_pos; /* Cache last read() position */ }; /* * Check if @index falls in the readahead windows. */ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index) { return (index >= ra->start && index < ra->start + ra->size); } struct file { union { struct llist_node fu_llist; struct rcu_head fu_rcuhead; } f_u; struct path f_path; struct inode *f_inode; /* cached value */ const struct file_operations *f_op; /* * Protects f_ep_links, f_flags. * 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; struct mutex f_pos_lock; loff_t f_pos; struct fown_struct f_owner; const struct cred *f_cred; struct file_ra_state f_ra; u64 f_version; #ifdef CONFIG_SECURITY void *f_security; #endif /* needed for tty driver, and maybe others */ void *private_data; #ifdef CONFIG_EPOLL /* Used by fs/eventpoll.c to link all the hooks to this file */ struct list_head f_ep_links; struct list_head f_tfile_llink; #endif /* #ifdef CONFIG_EPOLL */ struct address_space *f_mapping; errseq_t f_wb_err; } __randomize_layout __attribute__((aligned(4))); /* lest something weird decides that 2 is OK */ struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ unsigned char f_handle[0]; }; static inline struct file *get_file(struct file *f) { atomic_long_inc(&f->f_count); return f; } #define get_file_rcu_many(x, cnt) \ atomic_long_add_unless(&(x)->f_count, (cnt), 0) #define get_file_rcu(x) get_file_rcu_many((x), 1) #define file_count(x) atomic_long_read(&(x)->f_count) #define MAX_NON_LFS ((1UL<<31) - 1) /* 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)ULONG_MAX << PAGE_SHIFT) #elif BITS_PER_LONG==64 #define MAX_LFS_FILESIZE ((loff_t)LLONG_MAX) #endif #define FL_POSIX 1 #define FL_FLOCK 2 #define FL_DELEG 4 /* NFSv4 delegation */ #define FL_ACCESS 8 /* not trying to lock, just looking */ #define FL_EXISTS 16 /* when unlocking, test for existence */ #define FL_LEASE 32 /* lease held on this file */ #define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ #define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ #define FL_UNLOCK_PENDING 512 /* Lease is being broken */ #define FL_OFDLCK 1024 /* lock is "owned" by struct file */ #define FL_LAYOUT 2048 /* outstanding pNFS layout */ #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) /* * Special return value from posix_lock_file() and vfs_lock_file() for * asynchronous locking. */ #define FILE_LOCK_DEFERRED 1 /* legacy typedef, should eventually be removed */ typedef void *fl_owner_t; struct file_lock; struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); }; struct lock_manager_operations { int (*lm_compare_owner)(struct file_lock *, struct file_lock *); unsigned long (*lm_owner_key)(struct file_lock *); fl_owner_t (*lm_get_owner)(fl_owner_t); void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); bool (*lm_break)(struct file_lock *); int (*lm_change)(struct file_lock *, int, struct list_head *); void (*lm_setup)(struct file_lock *, void **); }; struct lock_manager { struct list_head list; /* * NFSv4 and up also want opens blocked during the grace period; * NLM doesn't care: */ bool block_opens; }; struct net; void locks_start_grace(struct net *, struct lock_manager *); void locks_end_grace(struct lock_manager *); bool locks_in_grace(struct net *); bool opens_in_grace(struct net *); /* that will die - we need it for nfs_lock_info */ #include /* * struct file_lock represents a generic "file lock". It's used to represent * POSIX byte range locks, BSD (flock) locks, and leases. It's important to * note that the same struct is used to represent both a request for a lock and * the lock itself, but the same object is never used for both. * * FIXME: should we create a separate "struct lock_request" to help distinguish * these two uses? * * The varous i_flctx lists are ordered by: * * 1) lock owner * 2) lock range start * 3) lock range end * * Obviously, the last two criteria only matter for POSIX locks. */ struct file_lock { struct file_lock *fl_blocker; /* The lock, that is blocking us */ struct list_head fl_list; /* link into file_lock_context */ struct hlist_node fl_link; /* node in global lists */ struct list_head fl_blocked_requests; /* list of requests with * ->fl_blocker pointing here */ struct list_head fl_blocked_member; /* node in * ->fl_blocker->fl_blocked_requests */ fl_owner_t fl_owner; unsigned int fl_flags; unsigned char fl_type; unsigned int fl_pid; int fl_link_cpu; /* what cpu's list is this on? */ wait_queue_head_t fl_wait; struct file *fl_file; loff_t fl_start; loff_t fl_end; struct fasync_struct * fl_fasync; /* for lease break notifications */ /* for lease breaks: */ unsigned long fl_break_time; unsigned long fl_downgrade_time; const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ union { struct nfs_lock_info nfs_fl; struct nfs4_lock_info nfs4_fl; struct { struct list_head link; /* link in AFS vnode's pending_locks list */ int state; /* state of grant or error if -ve */ unsigned int debug_id; } afs; } fl_u; } __randomize_layout; struct file_lock_context { spinlock_t flc_lock; struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; }; /* The following constant reflects the upper bound of the file/locking space */ #ifndef OFFSET_MAX #define INT_LIMIT(x) (~((x)1 << (sizeof(x)*8 - 1))) #define OFFSET_MAX INT_LIMIT(loff_t) #define OFFT_OFFSET_MAX INT_LIMIT(off_t) #endif extern void send_sigio(struct fown_struct *fown, int fd, int band); #define locks_inode(f) file_inode(f) #ifdef CONFIG_FILE_LOCKING extern int fcntl_getlk(struct file *, unsigned int, struct flock *); extern int fcntl_setlk(unsigned int, struct file *, unsigned int, struct flock *); #if BITS_PER_LONG == 32 extern int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); extern int fcntl_setlk64(unsigned int, struct file *, unsigned int, struct flock64 *); #endif extern int fcntl_setlease(unsigned int fd, struct file *filp, long arg); extern int fcntl_getlease(struct file *filp); /* fs/locks.c */ void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); extern void locks_init_lock(struct file_lock *); extern struct file_lock * locks_alloc_lock(void); extern void locks_copy_lock(struct file_lock *, struct file_lock *); extern void locks_copy_conflock(struct file_lock *, struct file_lock *); extern void locks_remove_posix(struct file *, fl_owner_t); extern void locks_remove_file(struct file *); extern void locks_release_private(struct file_lock *); extern void posix_test_lock(struct file *, struct file_lock *); extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); extern int locks_delete_block(struct file_lock *); extern int vfs_test_lock(struct file *, struct file_lock *); extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); extern int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); extern void lease_get_mtime(struct inode *, struct timespec64 *time); extern int generic_setlease(struct file *, long, struct file_lock **, void **priv); extern int vfs_setlease(struct file *, long, struct file_lock **, void **); extern int lease_modify(struct file_lock *, int, struct list_head *); struct files_struct; extern void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) { return -EINVAL; } static inline int fcntl_setlk(unsigned int fd, struct file *file, unsigned int cmd, struct flock __user *user) { return -EACCES; } #if BITS_PER_LONG == 32 static inline int fcntl_getlk64(struct file *file, unsigned int cmd, struct flock64 __user *user) { return -EINVAL; } static inline int fcntl_setlk64(unsigned int fd, struct file *file, unsigned int cmd, struct flock64 __user *user) { return -EACCES; } #endif static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg) { return -EINVAL; } static inline int fcntl_getlease(struct file *filp) { return F_UNLCK; } static inline void locks_free_lock_context(struct inode *inode) { } static inline void locks_init_lock(struct file_lock *fl) { return; } static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) { return; } static inline void locks_remove_file(struct file *filp) { return; } static inline void posix_test_lock(struct file *filp, struct file_lock *fl) { return; } static inline int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return -ENOLCK; } static inline int locks_delete_block(struct file_lock *waiter) { return -ENOENT; } static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { return -ENOLCK; } static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { return -ENOLCK; } static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { return 0; } static inline void lease_get_mtime(struct inode *inode, struct timespec64 *time) { return; } static inline int generic_setlease(struct file *filp, long arg, struct file_lock **flp, void **priv) { return -EINVAL; } static inline int vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv) { return -EINVAL; } static inline int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) { return -EINVAL; } struct files_struct; static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} #endif /* !CONFIG_FILE_LOCKING */ static inline struct inode *file_inode(const struct file *f) { return f->f_inode; } static inline struct dentry *file_dentry(const struct file *file) { return d_real(file->f_path.dentry, file_inode(file)); } static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) { return locks_lock_inode_wait(locks_inode(filp), fl); } struct fasync_struct { rwlock_t fa_lock; int magic; int fa_fd; struct fasync_struct *fa_next; /* singly linked list */ struct file *fa_file; struct rcu_head fa_rcu; }; #define FASYNC_MAGIC 0x4601 /* SMP safe fasync helpers: */ extern int fasync_helper(int, struct file *, int, struct fasync_struct **); extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *); extern int fasync_remove_entry(struct file *, struct fasync_struct **); extern struct fasync_struct *fasync_alloc(void); extern void fasync_free(struct fasync_struct *); /* can be called from interrupts */ extern void kill_fasync(struct fasync_struct **, int, int); extern void __f_setown(struct file *filp, struct pid *, enum pid_type, 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); /* * 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_FORCE (1<<27) #define SB_NOSEC (1<<28) #define SB_BORN (1<<29) #define SB_ACTIVE (1<<30) #define SB_NOUSER (1<<31) /* * Umount options */ #define MNT_FORCE 0x00000001 /* Attempt to forcibily umount */ #define MNT_DETACH 0x00000002 /* Just detach from the tree */ #define MNT_EXPIRE 0x00000004 /* Mark for expiry */ #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ /* sb->s_iflags */ #define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ #define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ #define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ #define SB_I_MULTIROOT 0x00000008 /* Multiple roots to the dentry tree */ /* sb->s_iflags to limit user namespace mounts */ #define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 /* Possible states of 'frozen' field */ enum { SB_UNFROZEN = 0, /* FS is unfrozen */ SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop * internal threads if needed) */ SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ }; #define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) struct sb_writers { int frozen; /* Is sb frozen? */ wait_queue_head_t wait_unfrozen; /* for get_super_thawed() */ struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; }; struct super_block { struct list_head s_list; /* Keep this first */ dev_t s_dev; /* search index; _not_ kdev_t */ unsigned char s_blocksize_bits; unsigned long s_blocksize; loff_t s_maxbytes; /* Max file size */ struct file_system_type *s_type; const struct super_operations *s_op; const struct dquot_operations *dq_op; const struct quotactl_ops *s_qcop; const struct export_operations *s_export_op; unsigned long s_flags; unsigned long s_iflags; /* internal SB_I_* flags */ unsigned long s_magic; struct dentry *s_root; struct rw_semaphore s_umount; int s_count; atomic_t s_active; #ifdef CONFIG_SECURITY void *s_security; #endif const struct xattr_handler **s_xattr; #ifdef CONFIG_FS_ENCRYPTION const struct fscrypt_operations *s_cop; #endif struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ struct list_head s_mounts; /* list of mounts; _not_ for fs use */ struct block_device *s_bdev; struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct hlist_node s_instances; unsigned int s_quota_types; /* Bitmask of supported quota types */ struct quota_info s_dquot; /* Diskquota specific options */ struct sb_writers s_writers; /* * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and * s_fsnotify_marks together for cache efficiency. They are frequently * accessed and rarely modified. */ void *s_fs_info; /* Filesystem private info */ /* Granularity of c/m/atime in ns (cannot be worse than a second) */ u32 s_time_gran; #ifdef CONFIG_FSNOTIFY __u32 s_fsnotify_mask; struct fsnotify_mark_connector __rcu *s_fsnotify_marks; #endif char s_id[32]; /* Informational name */ uuid_t s_uuid; /* UUID */ unsigned int s_max_links; fmode_t s_mode; /* * The next field is for VFS *only*. No filesystems have any business * even looking at it. You had been warned. */ struct mutex s_vfs_rename_mutex; /* Kludge */ /* * Filesystem subtype. If non-empty the filesystem type field * in /proc/mounts will be "type.subtype" */ const char *s_subtype; const struct dentry_operations *s_d_op; /* default d_op for dentries */ /* * Saved pool identifier for cleancache (-1 means none) */ int cleancache_poolid; struct shrinker s_shrink; /* per-sb shrinker handle */ /* Number of inodes with nlink == 0 but still referenced */ atomic_long_t s_remove_count; /* Pending fsnotify inode refs */ atomic_long_t s_fsnotify_inode_refs; /* Being remounted read-only */ int s_readonly_remount; /* AIO completions deferred from interrupt context */ struct workqueue_struct *s_dio_done_wq; struct hlist_head s_pins; /* * Owning user namespace and default context in which to * interpret filesystem uids, gids, quotas, device nodes, * xattrs and security labels. */ struct user_namespace *s_user_ns; /* * The list_lru structure is essentially just a pointer to a table * of per-node lru lists, each of which has its own spinlock. * There is no need to put them into separate cachelines. */ struct list_lru s_dentry_lru; struct list_lru s_inode_lru; struct rcu_head rcu; struct work_struct destroy_work; struct mutex s_sync_lock; /* sync serialisation lock */ /* * Indicates how deep in a filesystem stack this SB is */ int s_stack_depth; /* s_inode_list_lock protects s_inodes */ spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; struct list_head s_inodes; /* all inodes */ 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 * instead deal with the raw numeric values that are stored * in the filesystem. */ static inline uid_t i_uid_read(const struct inode *inode) { return from_kuid(inode->i_sb->s_user_ns, inode->i_uid); } static inline gid_t i_gid_read(const struct inode *inode) { return from_kgid(inode->i_sb->s_user_ns, inode->i_gid); } static inline void i_uid_write(struct inode *inode, uid_t uid) { inode->i_uid = make_kuid(inode->i_sb->s_user_ns, uid); } static inline void i_gid_write(struct inode *inode, gid_t gid) { inode->i_gid = make_kgid(inode->i_sb->s_user_ns, gid); } extern struct timespec64 timespec64_trunc(struct timespec64 t, unsigned gran); extern struct timespec64 current_time(struct inode *inode); /* * Snapshotting support. */ void __sb_end_write(struct super_block *sb, int level); int __sb_start_write(struct super_block *sb, int level, bool wait); #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_) /** * sb_end_write - drop write access to a superblock * @sb: the super we wrote to * * Decrement number of writers to the filesystem. Wake up possible waiters * wanting to freeze the filesystem. */ static inline void sb_end_write(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_WRITE); } /** * sb_end_pagefault - drop write access to a superblock from a page fault * @sb: the super we wrote to * * Decrement number of processes handling write page fault to the filesystem. * Wake up possible waiters wanting to freeze the filesystem. */ static inline void sb_end_pagefault(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_PAGEFAULT); } /** * sb_end_intwrite - drop write access to a superblock for internal fs purposes * @sb: the super we wrote to * * Decrement fs-internal number of writers to the filesystem. Wake up possible * waiters wanting to freeze the filesystem. */ static inline void sb_end_intwrite(struct super_block *sb) { __sb_end_write(sb, SB_FREEZE_FS); } /** * sb_start_write - get write access to a superblock * @sb: the super we write to * * When a process wants to write data or metadata to a file system (i.e. dirty * a page or an inode), it should embed the operation in a sb_start_write() - * sb_end_write() pair to get exclusion against file system freezing. This * function increments number of writers preventing freezing. If the file * system is already frozen, the function waits until the file system is * thawed. * * Since freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. Generally, * freeze protection should be the outermost lock. In particular, we have: * * sb_start_write * -> i_mutex (write path, truncate, directory ops, ...) * -> s_umount (freeze_super, thaw_super) */ static inline void sb_start_write(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_WRITE, true); } static inline int sb_start_write_trylock(struct super_block *sb) { return __sb_start_write(sb, SB_FREEZE_WRITE, false); } /** * sb_start_pagefault - get write access to a superblock from a page fault * @sb: the super we write to * * When a process starts handling write page fault, it should embed the * operation into sb_start_pagefault() - sb_end_pagefault() pair to get * exclusion against file system freezing. This is needed since the page fault * is going to dirty a page. This function increments number of running page * faults preventing freezing. If the file system is already frozen, the * function waits until the file system is thawed. * * Since page fault freeze protection behaves as a lock, users have to preserve * ordering of freeze protection and other filesystem locks. It is advised to * put sb_start_pagefault() close to mmap_sem in lock ordering. Page fault * handling code implies lock dependency: * * mmap_sem * -> sb_start_pagefault */ static inline void sb_start_pagefault(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_PAGEFAULT, true); } /* * sb_start_intwrite - get write access to a superblock for internal fs purposes * @sb: the super we write to * * This is the third level of protection against filesystem freezing. It is * free for use by a filesystem. The only requirement is that it must rank * below sb_start_pagefault. * * For example filesystem can call sb_start_intwrite() when starting a * transaction which somewhat eases handling of freezing for internal sources * of filesystem changes (internal fs threads, discarding preallocation on file * close, etc.). */ static inline void sb_start_intwrite(struct super_block *sb) { __sb_start_write(sb, SB_FREEZE_FS, true); } static inline int sb_start_intwrite_trylock(struct super_block *sb) { return __sb_start_write(sb, SB_FREEZE_FS, false); } extern bool inode_owner_or_capable(const struct inode *inode); /* * VFS helper functions.. */ extern int vfs_create(struct inode *, struct dentry *, umode_t, bool); extern int vfs_mkdir(struct inode *, struct dentry *, umode_t); extern int vfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); extern int vfs_symlink(struct inode *, struct dentry *, const char *); extern int vfs_link(struct dentry *, struct inode *, struct dentry *, struct inode **); extern int vfs_rmdir(struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *, struct inode **); extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *, struct inode **, unsigned int); extern int vfs_whiteout(struct inode *, struct dentry *); extern struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag); int vfs_mkobj(struct dentry *, umode_t, int (*f)(struct dentry *, umode_t, void *), void *); extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg); /* * VFS file helper functions. */ extern void inode_init_owner(struct inode *inode, const struct inode *dir, umode_t mode); extern bool may_open_dev(const struct path *path); /* * VFS FS_IOC_FIEMAP helper definitions. */ struct fiemap_extent_info { unsigned int fi_flags; /* Flags as passed from user */ unsigned int fi_extents_mapped; /* Number of mapped extents */ unsigned int fi_extents_max; /* Size of fiemap_extent array */ struct fiemap_extent __user *fi_extents_start; /* Start of fiemap_extent array */ }; int fiemap_fill_next_extent(struct fiemap_extent_info *info, u64 logical, u64 phys, u64 len, u32 flags); int fiemap_check_flags(struct fiemap_extent_info *fieinfo, u32 fs_flags); /* * This is the "filldir" function type, used by readdir() to let * the kernel specify what kind of dirent layout it wants to have. * This allows the kernel to read directories into kernel space or * to have different dirent layouts depending on the binary type. */ struct dir_context; typedef int (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64, unsigned); struct dir_context { filldir_t actor; 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. */ #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. * * NOMMU_MAP_COPY: Copy can be mapped (MAP_PRIVATE) * NOMMU_MAP_DIRECT: Can be mapped directly (MAP_SHARED) * NOMMU_MAP_READ: Can be mapped for reading * NOMMU_MAP_WRITE: Can be mapped for writing * NOMMU_MAP_EXEC: Can be mapped for execution */ #define NOMMU_MAP_COPY 0x00000001 #define NOMMU_MAP_DIRECT 0x00000008 #define NOMMU_MAP_READ VM_MAYREAD #define NOMMU_MAP_WRITE VM_MAYWRITE #define NOMMU_MAP_EXEC VM_MAYEXEC #define NOMMU_VMFLAGS \ (NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC) /* * These flags control the behavior of the remap_file_range function pointer. * If it is called with len == 0 that means "remap to end of source file". * See Documentation/filesystems/vfs.txt for more details about this call. * * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ #define REMAP_FILE_DEDUP (1 << 0) #define REMAP_FILE_CAN_SHORTEN (1 << 1) /* * These flags signal that the caller is ok with altering various aspects of * the behavior of the remap operation. The changes must be made by the * implementation; the vfs remap helper functions can take advantage of them. * Flags in this category exist to preserve the quirky behavior of the hoisted * btrfs clone/dedupe ioctls. */ #define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) struct iov_iter; struct file_operations { struct module *owner; loff_t (*llseek) (struct file *, loff_t, int); ssize_t (*read) (struct file *, char __user *, size_t, loff_t *); ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *); ssize_t (*read_iter) (struct kiocb *, struct iov_iter *); ssize_t (*write_iter) (struct kiocb *, struct iov_iter *); int (*iopoll)(struct kiocb *kiocb, bool spin); int (*iterate) (struct file *, struct dir_context *); int (*iterate_shared) (struct file *, struct dir_context *); __poll_t (*poll) (struct file *, struct poll_table_struct *); long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long); long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); unsigned long mmap_supported_flags; int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); int (*fsync) (struct file *, loff_t, loff_t, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); int (*check_flags)(int); int (*flock) (struct file *, int, struct file_lock *); ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int); ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int); int (*setlease)(struct file *, long, struct file_lock **, void **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); void (*show_fdinfo)(struct seq_file *m, struct file *f); #ifndef CONFIG_MMU unsigned (*mmap_capabilities)(struct file *); #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); int (*create) (struct inode *,struct dentry *, umode_t, bool); int (*link) (struct dentry *,struct inode *,struct dentry *); int (*unlink) (struct inode *,struct dentry *); int (*symlink) (struct inode *,struct dentry *,const char *); int (*mkdir) (struct inode *,struct dentry *,umode_t); int (*rmdir) (struct inode *,struct dentry *); int (*mknod) (struct inode *,struct dentry *,umode_t,dev_t); int (*rename) (struct inode *, struct dentry *, struct inode *, struct dentry *, unsigned int); int (*setattr) (struct dentry *, struct iattr *); int (*getattr) (const struct path *, struct kstat *, u32, unsigned int); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); int (*update_time)(struct inode *, struct timespec64 *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode); int (*tmpfile) (struct inode *, struct dentry *, umode_t); int (*set_acl)(struct inode *, struct posix_acl *, int); } ____cacheline_aligned; static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio, struct iov_iter *iter) { return file->f_op->read_iter(kio, iter); } static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio, struct iov_iter *iter) { return file->f_op->write_iter(kio, iter); } static inline int call_mmap(struct file *file, struct vm_area_struct *vma) { return file->f_op->mmap(file, vma); } 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_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 *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t *count, unsigned int remap_flags); extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags); struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); void (*destroy_inode)(struct inode *); void (*free_inode)(struct inode *); void (*dirty_inode) (struct inode *, int flags); int (*write_inode) (struct inode *, struct writeback_control *wbc); int (*drop_inode) (struct inode *); void (*evict_inode) (struct inode *); void (*put_super) (struct super_block *); int (*sync_fs)(struct super_block *sb, int wait); int (*freeze_super) (struct super_block *); int (*freeze_fs) (struct super_block *); int (*thaw_super) (struct super_block *); int (*unfreeze_fs) (struct super_block *); int (*statfs) (struct dentry *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*umount_begin) (struct super_block *); int (*show_options)(struct seq_file *, struct dentry *); int (*show_devname)(struct seq_file *, struct dentry *); int (*show_path)(struct seq_file *, struct dentry *); int (*show_stats)(struct seq_file *, struct dentry *); #ifdef CONFIG_QUOTA ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); struct dquot **(*get_dquots)(struct inode *); #endif int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); long (*nr_cached_objects)(struct super_block *, struct shrink_control *); long (*free_cached_objects)(struct super_block *, struct shrink_control *); }; /* * Inode flags - they have no relation to superblock flags now */ #define S_SYNC 1 /* Writes are synced at once */ #define S_NOATIME 2 /* Do not update access times */ #define S_APPEND 4 /* Append-only file */ #define S_IMMUTABLE 8 /* Immutable file */ #define S_DEAD 16 /* removed, but still open directory */ #define S_NOQUOTA 32 /* Inode is not counted to quota */ #define S_DIRSYNC 64 /* Directory modifications are synchronous */ #define S_NOCMTIME 128 /* Do not update file c/mtime */ #define S_SWAPFILE 256 /* Do not truncate: swapon got its bmaps */ #define S_PRIVATE 512 /* Inode is fs-internal */ #define S_IMA 1024 /* Inode has an associated IMA struct */ #define S_AUTOMOUNT 2048 /* Automount/referral quasi-directory */ #define S_NOSEC 4096 /* no suid or xattr security attributes */ #ifdef CONFIG_FS_DAX #define S_DAX 8192 /* Direct Access, avoiding the page cache */ #else #define S_DAX 0 /* Make all the DAX code disappear */ #endif #define S_ENCRYPTED 16384 /* Encrypted file (using fs/crypto/) */ #define S_CASEFOLD 32768 /* Casefolded file */ /* * Note that nosuid etc flags are inode-specific: setting some file-system * flags just means all the inodes inherit those flags by default. It might be * possible to override it selectively if you really wanted to with some * ioctl() that is not currently implemented. * * 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 * i_flags updated. Hence, i_flags no longer inherit the superblock mount * flags, so these have to be checked separately. -- rmk@arm.uk.linux.org */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_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, SB_SYNCHRONOUS|SB_DIRSYNC) || \ ((inode)->i_flags & (S_SYNC|S_DIRSYNC))) #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, SB_POSIXACL) #define IS_DEADDIR(inode) ((inode)->i_flags & S_DEAD) #define IS_NOCMTIME(inode) ((inode)->i_flags & S_NOCMTIME) #define IS_SWAPFILE(inode) ((inode)->i_flags & S_SWAPFILE) #define IS_PRIVATE(inode) ((inode)->i_flags & S_PRIVATE) #define IS_IMA(inode) ((inode)->i_flags & S_IMA) #define IS_AUTOMOUNT(inode) ((inode)->i_flags & S_AUTOMOUNT) #define IS_NOSEC(inode) ((inode)->i_flags & S_NOSEC) #define IS_DAX(inode) ((inode)->i_flags & S_DAX) #define IS_ENCRYPTED(inode) ((inode)->i_flags & S_ENCRYPTED) #define IS_CASEFOLDED(inode) ((inode)->i_flags & S_CASEFOLD) #define IS_WHITEOUT(inode) (S_ISCHR(inode->i_mode) && \ (inode)->i_rdev == WHITEOUT_DEV) 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 u16 ki_hint_validate(enum rw_hint hint) { typeof(((struct kiocb *)0)->ki_hint) max_hint = -1; if (hint <= max_hint) return hint; return 0; } 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 = ki_hint_validate(file_write_hint(filp)), .ki_ioprio = get_current_ioprio(), }; } /* * Inode state bits. Protected by inode->i_lock * * Three bits determine the dirty state of the inode, I_DIRTY_SYNC, * I_DIRTY_DATASYNC and I_DIRTY_PAGES. * * Four bits define the lifetime of an