#ifndef _LINUX_FS_H #define _LINUX_FS_H /* * This file has definitions for some important file table * structures etc. */ #include #include #include #include /* * It's silly to have NR_OPEN bigger than NR_FILE, but you can change * the file limit at runtime and only root can increase the per-process * nr_file rlimit, so it's safe to set up a ridiculously high absolute * upper limit on files-per-process. * * Some programs (notably those using select()) may have to be * recompiled to take full advantage of the new limits.. */ /* Fixed constants first: */ #undef NR_OPEN #define INR_OPEN_CUR 1024 /* Initial setting for nfile rlimits */ #define INR_OPEN_MAX 4096 /* Hard limit for nfile rlimits */ #define BLOCK_SIZE_BITS 10 #define BLOCK_SIZE (1<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) || \ ((inode)->i_flags & S_SYNC)) #define IS_DIRSYNC(inode) (__IS_FLG(inode, MS_SYNCHRONOUS|MS_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_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_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) /* the read-only stuff doesn't really belong here, but any other place is probably as bad and I don't want to create yet another include file. */ #define BLKROSET _IO(0x12,93) /* set device read-only (0 = read-write) */ #define BLKROGET _IO(0x12,94) /* get read-only status (0 = read_write) */ #define BLKRRPART _IO(0x12,95) /* re-read partition table */ #define BLKGETSIZE _IO(0x12,96) /* return device size /512 (long *arg) */ #define BLKFLSBUF _IO(0x12,97) /* flush buffer cache */ #define BLKRASET _IO(0x12,98) /* set read ahead for block device */ #define BLKRAGET _IO(0x12,99) /* get current read ahead setting */ #define BLKFRASET _IO(0x12,100)/* set filesystem (mm/filemap.c) read-ahead */ #define BLKFRAGET _IO(0x12,101)/* get filesystem (mm/filemap.c) read-ahead */ #define BLKSECTSET _IO(0x12,102)/* set max sectors per request (ll_rw_blk.c) */ #define BLKSECTGET _IO(0x12,103)/* get max sectors per request (ll_rw_blk.c) */ #define BLKSSZGET _IO(0x12,104)/* get block device sector size */ #if 0 #define BLKPG _IO(0x12,105)/* See blkpg.h */ /* Some people are morons. Do not use sizeof! */ #define BLKELVGET _IOR(0x12,106,size_t)/* elevator get */ #define BLKELVSET _IOW(0x12,107,size_t)/* elevator set */ /* This was here just to show that the number is taken - probably all these _IO(0x12,*) ioctls should be moved to blkpg.h. */ #endif /* A jump here: 108-111 have been used for various private purposes. */ #define BLKBSZGET _IOR(0x12,112,size_t) #define BLKBSZSET _IOW(0x12,113,size_t) #define BLKGETSIZE64 _IOR(0x12,114,size_t) /* return device size in bytes (u64 *arg) */ #define BLKTRACESETUP _IOWR(0x12,115,struct blk_user_trace_setup) #define BLKTRACESTART _IO(0x12,116) #define BLKTRACESTOP _IO(0x12,117) #define BLKTRACETEARDOWN _IO(0x12,118) #define BLKDISCARD _IO(0x12,119) #define BLKIOMIN _IO(0x12,120) #define BLKIOOPT _IO(0x12,121) #define BLKALIGNOFF _IO(0x12,122) #define BLKPBSZGET _IO(0x12,123) #define BLKDISCARDZEROES _IO(0x12,124) #define BLKSECDISCARD _IO(0x12,125) #define BLKROTATIONAL _IO(0x12,126) #define BMAP_IOCTL 1 /* obsolete - kept for compatibility */ #define FIBMAP _IO(0x00,1) /* bmap access */ #define FIGETBSZ _IO(0x00,2) /* get the block size used for bmap */ #define FIFREEZE _IOWR('X', 119, int) /* Freeze */ #define FITHAW _IOWR('X', 120, int) /* Thaw */ #define FITRIM _IOWR('X', 121, struct fstrim_range) /* Trim */ #define FS_IOC_GETFLAGS _IOR('f', 1, long) #define FS_IOC_SETFLAGS _IOW('f', 2, long) #define FS_IOC_GETVERSION _IOR('v', 1, long) #define FS_IOC_SETVERSION _IOW('v', 2, long) #define FS_IOC_FIEMAP _IOWR('f', 11, struct fiemap) #define FS_IOC32_GETFLAGS _IOR('f', 1, int) #define FS_IOC32_SETFLAGS _IOW('f', 2, int) #define FS_IOC32_GETVERSION _IOR('v', 1, int) #define FS_IOC32_SETVERSION _IOW('v', 2, int) /* * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS) */ #define FS_SECRM_FL 0x00000001 /* Secure deletion */ #define FS_UNRM_FL 0x00000002 /* Undelete */ #define FS_COMPR_FL 0x00000004 /* Compress file */ #define FS_SYNC_FL 0x00000008 /* Synchronous updates */ #define FS_IMMUTABLE_FL 0x00000010 /* Immutable file */ #define FS_APPEND_FL 0x00000020 /* writes to file may only append */ #define FS_NODUMP_FL 0x00000040 /* do not dump file */ #define FS_NOATIME_FL 0x00000080 /* do not update atime */ /* Reserved for compression usage... */ #define FS_DIRTY_FL 0x00000100 #define FS_COMPRBLK_FL 0x00000200 /* One or more compressed clusters */ #define FS_NOCOMP_FL 0x00000400 /* Don't compress */ #define FS_ECOMPR_FL 0x00000800 /* Compression error */ /* End compression flags --- maybe not all used */ #define FS_BTREE_FL 0x00001000 /* btree format dir */ #define FS_INDEX_FL 0x00001000 /* hash-indexed directory */ #define FS_IMAGIC_FL 0x00002000 /* AFS directory */ #define FS_JOURNAL_DATA_FL 0x00004000 /* Reserved for ext3 */ #define FS_NOTAIL_FL 0x00008000 /* file tail should not be merged */ #define FS_DIRSYNC_FL 0x00010000 /* dirsync behaviour (directories only) */ #define FS_TOPDIR_FL 0x00020000 /* Top of directory hierarchies*/ #define FS_EXTENT_FL 0x00080000 /* Extents */ #define FS_DIRECTIO_FL 0x00100000 /* Use direct i/o */ #define FS_NOCOW_FL 0x00800000 /* Do not cow file */ #define FS_RESERVED_FL 0x80000000 /* reserved for ext2 lib */ #define FS_FL_USER_VISIBLE 0x0003DFFF /* User visible flags */ #define FS_FL_USER_MODIFIABLE 0x000380FF /* User modifiable flags */ #define SYNC_FILE_RANGE_WAIT_BEFORE 1 #define SYNC_FILE_RANGE_WRITE 2 #define SYNC_FILE_RANGE_WAIT_AFTER 4 #ifdef __KERNEL__ #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 export_operations; struct hd_geometry; struct iovec; struct nameidata; 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; extern void __init inode_init(void); extern void __init inode_init_early(void); extern void __init files_init(unsigned long); extern struct files_stat_struct files_stat; extern unsigned long get_max_files(void); extern 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; struct buffer_head; typedef int (get_block_t)(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create); typedef void (dio_iodone_t)(struct kiocb *iocb, loff_t offset, ssize_t bytes, void *private, int ret, bool is_async); /* * 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_ATTR_FLAG (1 << 10) #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) /* * 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 timespec ia_atime; struct timespec ia_mtime; struct timespec 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 /** * 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_UNINTERRUPTIBLE 0x0001 /* will not do a short write */ #define AOP_FLAG_CONT_EXPAND 0x0002 /* called from cont_expand */ #define AOP_FLAG_NOFS 0x0004 /* 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; struct iov_iter { const struct iovec *iov; unsigned long nr_segs; size_t iov_offset; size_t count; }; size_t iov_iter_copy_from_user_atomic(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes); size_t iov_iter_copy_from_user(struct page *page, struct iov_iter *i, unsigned long offset, size_t bytes); void iov_iter_advance(struct iov_iter *i, size_t bytes); int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes); size_t iov_iter_single_seg_count(struct iov_iter *i); static inline void iov_iter_init(struct iov_iter *i, const struct iovec *iov, unsigned long nr_segs, size_t count, size_t written) { i->iov = iov; i->nr_segs = nr_segs; i->iov_offset = 0; i->count = count + written; iov_iter_advance(i, written); } static inline size_t iov_iter_count(struct iov_iter *i) { return i->count; } /* * "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); 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 long); int (*releasepage) (struct page *, gfp_t); void (*freepage)(struct page *); ssize_t (*direct_IO)(int, struct kiocb *, const struct iovec *iov, loff_t offset, unsigned long nr_segs); int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **, unsigned long *); /* * migrate the contents of a page to the specified target. If sync * is false, it must not block. */ int (*migratepage) (struct address_space *, struct page *, struct page *, enum migrate_mode); int (*launder_page) (struct page *); int (*is_partially_uptodate) (struct page *, read_descriptor_t *, unsigned long); 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 backing_dev_info; struct address_space { struct inode *host; /* owner: inode, block_device */ struct radix_tree_root page_tree; /* radix tree of all pages */ spinlock_t tree_lock; /* and lock protecting it */ unsigned int i_mmap_writable;/* count VM_SHARED mappings */ struct prio_tree_root i_mmap; /* tree of private and shared mappings */ struct list_head i_mmap_nonlinear;/*list VM_NONLINEAR mappings */ struct mutex i_mmap_mutex; /* protect tree, count, list */ /* Protected by tree_lock together with the radix tree */ unsigned long nrpages; /* number of total pages */ pgoff_t writeback_index;/* writeback starts here */ const struct address_space_operations *a_ops; /* methods */ unsigned long flags; /* error bits/gfp mask */ struct backing_dev_info *backing_dev_info; /* device readahead, etc */ spinlock_t private_lock; /* for use by the address_space */ struct list_head private_list; /* ditto */ struct address_space *assoc_mapping; /* ditto */ } __attribute__((aligned(sizeof(long)))); /* * 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 */ struct list_head bd_inodes; 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; 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 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; }; /* * Radix-tree tags, for tagging dirty and writeback pages within the pagecache * radix trees */ #define PAGECACHE_TAG_DIRTY 0 #define PAGECACHE_TAG_WRITEBACK 1 #define PAGECACHE_TAG_TOWRITE 2 int mapping_tagged(struct address_space *mapping, int tag); /* * Might pages of this file be mapped into userspace? */ static inline int mapping_mapped(struct address_space *mapping) { return !prio_tree_empty(&mapping->i_mmap) || !list_empty(&mapping->i_mmap_nonlinear); } /* * 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. */ static inline int mapping_writably_mapped(struct address_space *mapping) { return mapping->i_mmap_writable != 0; } /* * 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 IOP_FASTPERM 0x0001 #define IOP_LOOKUP 0x0002 #define IOP_NOFOLLOW 0x0004 /* * 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 timespec i_atime; struct timespec i_mtime; struct timespec i_ctime; spinlock_t i_lock; /* i_blocks, i_bytes, maybe i_size */ unsigned short i_bytes; unsigned int i_blkbits; blkcnt_t i_blocks; #ifdef __NEED_I_SIZE_ORDERED seqcount_t i_size_seqcount; #endif /* Misc */ unsigned long i_state; struct mutex i_mutex; unsigned long dirtied_when; /* jiffies of first dirtying */ struct hlist_node i_hash; struct list_head i_wb_list; /* backing dev IO list */ struct list_head i_lru; /* inode LRU list */ struct list_head i_sb_list; union { struct hlist_head i_dentry; struct rcu_head i_rcu; }; u64 i_version; atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ struct file_lock *i_flock; struct address_space i_data; #ifdef CONFIG_QUOTA struct dquot *i_dquot[MAXQUOTAS]; #endif struct list_head i_devices; union { struct pipe_inode_info *i_pipe; struct block_device *i_bdev; struct cdev *i_cdev; }; __u32 i_generation; #ifdef CONFIG_FSNOTIFY __u32 i_fsnotify_mask; /* all events this inode cares about */ struct hlist_head i_fsnotify_marks; #endif #ifdef CONFIG_IMA atomic_t i_readcount; /* struct files open RO */ #endif void *i_private; /* fs or device private pointer */ }; static inline int inode_unhashed(struct inode *inode) { return hlist_unhashed(&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: quota file * * The locking order between these classes is * parent -> child -> normal -> xattr -> quota */ enum inode_i_mutex_lock_class { I_MUTEX_NORMAL, I_MUTEX_PARENT, I_MUTEX_CHILD, I_MUTEX_XATTR, I_MUTEX_QUOTA }; /* * 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) write_seqcount_begin(&inode->i_size_seqcount); inode->i_size = i_size; write_seqcount_end(&inode->i_size_seqcount); #elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPT) preempt_disable(); inode->i_size = i_size; preempt_enable(); #else inode->i_size = i_size; #endif } /* 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(&init_user_ns, inode->i_uid); } static inline gid_t i_gid_read(const struct inode *inode) { return from_kgid(&init_user_ns, inode->i_gid); } static inline void i_uid_write(struct inode *inode, uid_t uid) { inode->i_uid = make_kuid(&init_user_ns, uid); } static inline void i_gid_write(struct inode *inode, gid_t gid) { inode->i_gid = make_kgid(&init_user_ns, gid); } 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); } #define FILE_MNT_WRITE_TAKEN 1 #define FILE_MNT_WRITE_RELEASED 2 struct file { /* * fu_list becomes invalid after file_free is called and queued via * fu_rcuhead for RCU freeing */ union { struct list_head fu_list; struct rcu_head fu_rcuhead; } f_u; struct path f_path; #define f_dentry f_path.dentry #define f_vfsmnt f_path.mnt const struct file_operations *f_op; /* * Protects f_ep_links, f_flags, f_pos vs i_size in lseek SEEK_CUR. * Must not be taken from IRQ context. */ spinlock_t f_lock; #ifdef CONFIG_SMP int f_sb_list_cpu; #endif atomic_long_t f_count; unsigned int f_flags; fmode_t f_mode; 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; #ifdef CONFIG_DEBUG_WRITECOUNT unsigned long f_mnt_write_state; #endif }; struct file_handle { __u32 handle_bytes; int handle_type; /* file identifier */ unsigned char f_handle[0]; }; #define get_file(x) atomic_long_inc(&(x)->f_count) #define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1) #define file_count(x) atomic_long_read(&(x)->f_count) #ifdef CONFIG_DEBUG_WRITECOUNT static inline void file_take_write(struct file *f) { WARN_ON(f->f_mnt_write_state != 0); f->f_mnt_write_state = FILE_MNT_WRITE_TAKEN; } static inline void file_release_write(struct file *f) { f->f_mnt_write_state |= FILE_MNT_WRITE_RELEASED; } static inline void file_reset_write(struct file *f) { f->f_mnt_write_state = 0; } static inline void file_check_state(struct file *f) { /* * At this point, either both or neither of these bits * should be set. */ WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN); WARN_ON(f->f_mnt_write_state == FILE_MNT_WRITE_RELEASED); } static inline int file_check_writeable(struct file *f) { if (f->f_mnt_write_state == FILE_MNT_WRITE_TAKEN) return 0; printk(KERN_WARNING "writeable file with no " "mnt_want_write()\n"); WARN_ON(1); return -EINVAL; } #else /* !CONFIG_DEBUG_WRITECOUNT */ static inline void file_take_write(struct file *filp) {} static inline void file_release_write(struct file *filp) {} static inline void file_reset_write(struct file *filp) {} static inline void file_check_state(struct file *filp) {} static inline int file_check_writeable(struct file *filp) { return 0; } #endif /* CONFIG_DEBUG_WRITECOUNT */ #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 (((u64)PAGE_CACHE_SIZE << (BITS_PER_LONG-1))-1) #elif BITS_PER_LONG==64 #define MAX_LFS_FILESIZE 0x7fffffffffffffffUL #endif #define FL_POSIX 1 #define FL_FLOCK 2 #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 */ /* * Special return value from posix_lock_file() and vfs_lock_file() for * asynchronous locking. */ #define FILE_LOCK_DEFERRED 1 /* * The POSIX file lock owner is determined by * the "struct files_struct" in the thread group * (or NULL for no owner - BSD locks). * * Lockd stuffs a "host" pointer into this. */ typedef struct files_struct *fl_owner_t; 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 *); void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, struct file_lock *, int); void (*lm_break)(struct file_lock *); int (*lm_change)(struct file_lock **, int); }; struct lock_manager { struct list_head list; }; struct net; void locks_start_grace(struct net *, struct lock_manager *); void locks_end_grace(struct lock_manager *); int locks_in_grace(struct net *); /* that will die - we need it for nfs_lock_info */ #include struct file_lock { struct file_lock *fl_next; /* singly linked list for this inode */ struct list_head fl_link; /* doubly linked list of all locks */ struct list_head fl_block; /* circular list of blocked processes */ fl_owner_t fl_owner; unsigned int fl_flags; unsigned char fl_type; unsigned int fl_pid; struct pid *fl_nspid; 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 */ } afs; } fl_u; }; /* 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 #include extern void send_sigio(struct fown_struct *fown, int fd, int band); #ifdef CONFIG_FILE_LOCKING extern int fcntl_getlk(struct file *, struct flock __user *); extern int fcntl_setlk(unsigned int, struct file *, unsigned int, struct flock __user *); #if BITS_PER_LONG == 32 extern int fcntl_getlk64(struct file *, struct flock64 __user *); extern int fcntl_setlk64(unsigned int, struct file *, unsigned int, struct flock64 __user *); #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(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_lock(struct file_lock *, const struct file_lock *); extern void locks_remove_posix(struct file *, fl_owner_t); extern void locks_remove_flock(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 posix_lock_file_wait(struct file *, struct file_lock *); extern int posix_unblock_lock(struct file *, 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 flock_lock_file_wait(struct file *filp, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags); extern void lease_get_mtime(struct inode *, struct timespec *time); extern int generic_setlease(struct file *, long, struct file_lock **); extern int vfs_setlease(struct file *, long, struct file_lock **); extern int lease_modify(struct file_lock **, int); extern int lock_may_read(struct inode *, loff_t start, unsigned long count); extern int lock_may_write(struct inode *, loff_t start, unsigned long count); extern void locks_delete_block(struct file_lock *waiter); extern void lock_flocks(void); extern void unlock_flocks(void); #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, 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, 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 0; } static inline int fcntl_getlease(struct file *filp) { return 0; } static inline void locks_init_lock(struct file_lock *fl) { return; } static inline void __locks_copy_lock(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_flock(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 posix_lock_file_wait(struct file *filp, struct file_lock *fl) { return -ENOLCK; } static inline int posix_unblock_lock(struct file *filp, 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 flock_lock_file_wait(struct file *filp, struct file_lock *request) { return -ENOLCK; } static inline int __break_lease(struct inode *inode, unsigned int mode) { return 0; } static inline void lease_get_mtime(struct inode *inode, struct timespec *time) { return; } static inline int generic_setlease(struct file *filp, long arg, struct file_lock **flp) { return -EINVAL; } static inline int vfs_setlease(struct file *filp, long arg, struct file_lock **lease) { return -EINVAL; } static inline int lease_modify(struct file_lock **before, int arg) { return -EINVAL; } static inline int lock_may_read(struct inode *inode, loff_t start, unsigned long len) { return 1; } static inline int lock_may_write(struct inode *inode, loff_t start, unsigned long len) { return 1; } static inline void locks_delete_block(struct file_lock *waiter) { } static inline void lock_flocks(void) { } static inline void unlock_flocks(void) { } #endif /* !CONFIG_FILE_LOCKING */ struct fasync_struct { spinlock_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 int __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); struct mm_struct; /* * 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 */ extern struct list_head super_blocks; extern spinlock_t sb_lock; /* 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 { /* Counters for counting writers at each level */ struct percpu_counter counter[SB_FREEZE_LEVELS]; wait_queue_head_t wait; /* queue for waiting for writers / faults to finish */ int frozen; /* Is sb frozen? */ wait_queue_head_t wait_unfrozen; /* queue for waiting for sb to be thawed */ #ifdef CONFIG_DEBUG_LOCK_ALLOC struct lockdep_map lock_map[SB_FREEZE_LEVELS]; #endif }; 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_magic; struct dentry *s_root; struct rw_semaphore s_umount; struct mutex s_lock; int s_count; atomic_t s_active; #ifdef CONFIG_SECURITY void *s_security; #endif const struct xattr_handler **s_xattr; struct list_head s_inodes; /* all inodes */ struct hlist_bl_head s_anon; /* anonymous dentries for (nfs) exporting */ #ifdef CONFIG_SMP struct list_head __percpu *s_files; #else struct list_head s_files; #endif struct list_head s_mounts; /* list of mounts; _not_ for fs use */ /* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */ struct list_head s_dentry_lru; /* unused dentry lru */ int s_nr_dentry_unused; /* # of dentry on lru */ /* s_inode_lru_lock protects s_inode_lru and s_nr_inodes_unused */ spinlock_t s_inode_lru_lock ____cacheline_aligned_in_smp; struct list_head s_inode_lru; /* unused inode lru */ int s_nr_inodes_unused; /* # of inodes on lru */ struct block_device *s_bdev; struct backing_dev_info *s_bdi; struct mtd_info *s_mtd; struct hlist_node s_instances; struct quota_info s_dquot; /* Diskquota specific options */ struct sb_writers s_writers; char s_id[32]; /* Informational name */ u8 s_uuid[16]; /* UUID */ void *s_fs_info; /* Filesystem private info */ unsigned int s_max_links; fmode_t s_mode; /* Granularity of c/m/atime in ns. Cannot be worse than a second */ u32 s_time_gran; /* * 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" */ 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 */ /* * 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; /* Being remounted read-only */ int s_readonly_remount; }; /* superblock cache pruning functions */ extern void prune_icache_sb(struct super_block *sb, int nr_to_scan); extern void prune_dcache_sb(struct super_block *sb, int nr_to_scan); extern struct timespec current_fs_time(struct super_block *sb); /* * Snapshotting support. */ void __sb_end_write(struct super_block *sb, int level); int __sb_start_write(struct super_block *sb, int level, bool wait); /** * 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); } extern bool inode_owner_or_capable(const struct inode *inode); /* not quite ready to be deprecated, but... */ extern void lock_super(struct super_block *); extern void unlock_super(struct super_block *); /* * 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 *); extern int vfs_rmdir(struct inode *, struct dentry *); extern int vfs_unlink(struct inode *, struct dentry *); extern int vfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); /* * VFS dentry helper functions. */ extern void dentry_unhash(struct dentry *dentry); /* * VFS file helper functions. */ extern void inode_init_owner(struct inode *inode, const struct inode *dir, umode_t mode); /* * 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); /* * File types * * NOTE! These match bits 12..15 of stat.st_mode * (ie "(i_mode >> 12) & 15"). */ #define DT_UNKNOWN 0 #define DT_FIFO 1 #define DT_CHR 2 #define DT_DIR 4 #define DT_BLK 6 #define DT_REG 8 #define DT_LNK 10 #define DT_SOCK 12 #define DT_WHT 14 /* * 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. */ typedef int (*filldir_t)(void *, const char *, int, loff_t, u64, unsigned); 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 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 (*aio_read) (struct kiocb *, const struct iovec *, unsigned long, loff_t); ssize_t (*aio_write) (struct kiocb *, const struct iovec *, unsigned long, loff_t); int (*readdir) (struct file *, void *, filldir_t); unsigned int (*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 *); 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 (*aio_fsync) (struct kiocb *, 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 **); long (*fallocate)(struct file *file, int mode, loff_t offset, loff_t len); }; struct inode_operations { struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int); void * (*follow_link) (struct dentry *, struct nameidata *); int (*permission) (struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); int (*readlink) (struct dentry *, char __user *,int); void (*put_link) (struct dentry *, struct nameidata *, void *); 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 *); void (*truncate) (struct inode *); int (*setattr) (struct dentry *, struct iattr *); int (*getattr) (struct vfsmount *mnt, struct dentry *, struct kstat *); int (*setxattr) (struct dentry *, const char *,const void *,size_t,int); ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t); ssize_t (*listxattr) (struct dentry *, char *, size_t); int (*removexattr) (struct dentry *, const char *); int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len); int (*update_time)(struct inode *, struct timespec *, int); int (*atomic_open)(struct inode *, struct dentry *, struct file *, unsigned open_flag, umode_t create_mode, int *opened); } ____cacheline_aligned; struct seq_file; 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_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *); extern ssize_t vfs_writev(struct file *, const struct iovec __user *, unsigned long, loff_t *); struct super_operations { struct inode *(*alloc_inode)(struct super_block *sb); void (*destroy_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_fs) (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); #endif int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t); int (*nr_cached_objects)(struct super_block *); void (*free_cached_objects)(struct super_block *, int); }; /* * 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 inode. Initially, inodes are I_NEW, * until that flag is cleared. I_WILL_FREE, I_FREEING and I_CLEAR are set at * various stages of removing an inode. * * Two bits are used for locking and completion notification, I_NEW and I_SYNC. * * I_DIRTY_SYNC Inode is dirty, but doesn't have to be written on * fdatasync(). i_atime is the usual cause. * I_DIRTY_DATASYNC Data-related inode changes pending. We keep track of * these changes separately from I_DIRTY_SYNC so that we * don't have to write inode on fdatasync() when only * mtime has changed in it. * I_DIRTY_PAGES Inode has dirty pages. Inode itself may be clean. * I_NEW Serves as both a mutex and completion notification. * New inodes set I_NEW. If two processes both create * the same inode, one of them will release its inode and * wait for I_NEW to be released before returning. * Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can * also cause waiting on I_NEW, without I_NEW actually * being set. find_inode() uses this to prevent returning * nearly-dead inodes. * I_WILL_FREE Must be set when calling write_inode_now() if i_count * is zero. I_FREEING must be set when I_WILL_FREE is * cleared. * I_FREEING Set when inode is about to be freed but still has dirty * pages or buffers attached or the inode itself is still * dirty. * I_CLEAR Added by clear_inode(). In this state the inode is * clean and can be destroyed. Inode keeps I_FREEING. * * Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are * prohibited for many purposes. iget() must wait for * the inode to be completely released, then create it * anew. Other functions will just ignore such inodes, * if appropriate. I_NEW is used for waiting. * * I_SYNC Writeback of inode is running. The bit is set during * data writeback, and cleared with a wakeup on the bit * address once it is done. The bit is also used to pin * the inode in memory for flusher thread. * * 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(). * * Q: What is the difference between I_WILL_FREE and I_FREEING? */ #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 (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 << __I_SYNC) #define I_REFERENCED (1 << 8) #define __I_DIO_WAKEUP 9 #define I_DIO_WAKEUP (1 << I_DIO_WAKEUP) #define I_DIRTY (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_PAGES) extern void __mark_inode_dirty(struct inode *, int); static inline void mark_inode_dirty(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY); } static inline void mark_inode_dirty_sync(struct inode *inode) { __mark_inode_dirty(inode, I_DIRTY_SYNC); } extern void inc_nlink(struct inode *inode); extern void drop_nlink(struct inode *inode); extern void clear_nlink(st