// SPDX-License-Identifier: GPL-2.0 /* * linux/fs/namei.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * Some corrections by tytso. */ /* [Feb 1997 T. Schoebel-Theuer] Complete rewrite of the pathname * lookup logic. */ /* [Feb-Apr 2000, AV] Rewrite to the new namespace architecture. */ #include <linux/init.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/wordpart.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/sched/mm.h> #include <linux/fsnotify.h> #include <linux/personality.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/mount.h> #include <linux/audit.h> #include <linux/capability.h> #include <linux/file.h> #include <linux/fcntl.h> #include <linux/device_cgroup.h> #include <linux/fs_struct.h> #include <linux/posix_acl.h> #include <linux/hash.h> #include <linux/bitops.h> #include <linux/init_task.h> #include <linux/uaccess.h> #include "internal.h" #include "mount.h" /* [Feb-1997 T. Schoebel-Theuer] * Fundamental changes in the pathname lookup mechanisms (namei) * were necessary because of omirr. The reason is that omirr needs * to know the _real_ pathname, not the user-supplied one, in case * of symlinks (and also when transname replacements occur). * * The new code replaces the old recursive symlink resolution with * an iterative one (in case of non-nested symlink chains). It does * this with calls to <fs>_follow_link(). * As a side effect, dir_namei(), _namei() and follow_link() are now * replaced with a single function lookup_dentry() that can handle all * the special cases of the former code. * * With the new dcache, the pathname is stored at each inode, at least as * long as the refcount of the inode is positive. As a side effect, the * size of the dcache depends on the inode cache and thus is dynamic. * * [29-Apr-1998 C. Scott Ananian] Updated above description of symlink * resolution to correspond with current state of the code. * * Note that the symlink resolution is not *completely* iterative. * There is still a significant amount of tail- and mid- recursion in * the algorithm. Also, note that <fs>_readlink() is not used in * lookup_dentry(): lookup_dentry() on the result of <fs>_readlink() * may return different results than <fs>_follow_link(). Many virtual * filesystems (including /proc) exhibit this behavior. */ /* [24-Feb-97 T. Schoebel-Theuer] Side effects caused by new implementation: * New symlink semantics: when open() is called with flags O_CREAT | O_EXCL * and the name already exists in form of a symlink, try to create the new * name indicated by the symlink. The old code always complained that the * name already exists, due to not following the symlink even if its target * is nonexistent. The new semantics affects also mknod() and link() when * the name is a symlink pointing to a non-existent name. * * I don't know which semantics is the right one, since I have no access * to standards. But I found by trial that HP-UX 9.0 has the full "new" * semantics implemented, while SunOS 4.1.1 and Solaris (SunOS 5.4) have the * "old" one. Personally, I think the new semantics is much more logical. * Note that "ln old new" where "new" is a symlink pointing to a non-existing * file does succeed in both HP-UX and SunOs, but not in Solaris * and in the old Linux semantics. */ /* [16-Dec-97 Kevin Buhr] For security reasons, we change some symlink * semantics. See the comments in "open_namei" and "do_link" below. * * [10-Sep-98 Alan Modra] Another symlink change. */ /* [Feb-Apr 2000 AV] Complete rewrite. Rules for symlinks: * inside the path - always follow. * in the last component in creation/removal/renaming - never follow. * if LOOKUP_FOLLOW passed - follow. * if the pathname has trailing slashes - follow. * otherwise - don't follow. * (applied in that order). * * [Jun 2000 AV] Inconsistent behaviour of open() in case if flags==O_CREAT * restored for 2.4. This is the last surviving part of old 4.2BSD bug. * During the 2.4 we need to fix the userland stuff depending on it - * hopefully we will be able to get rid of that wart in 2.5. So far only * XEmacs seems to be relying on it... */ /* * [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland) * implemented. Let's see if raised priority of ->s_vfs_rename_mutex gives * any extra contention... */ /* In order to reduce some races, while at the same time doing additional * checking and hopefully speeding things up, we copy filenames to the * kernel data space before using them.. * * POSIX.1 2.4: an empty pathname is invalid (ENOENT). * PATH_MAX includes the nul terminator --RR. */ #define EMBEDDED_NAME_MAX … struct filename * getname_flags(const char __user *filename, int flags) { … } struct filename * getname_uflags(const char __user *filename, int uflags) { … } struct filename * getname(const char __user * filename) { … } struct filename * getname_kernel(const char * filename) { … } EXPORT_SYMBOL(…); void putname(struct filename *name) { … } EXPORT_SYMBOL(…); /** * check_acl - perform ACL permission checking * @idmap: idmap of the mount the inode was found from * @inode: inode to check permissions on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) * * This function performs the ACL permission checking. Since this function * retrieve POSIX acls it needs to know whether it is called from a blocking or * non-blocking context and thus cares about the MAY_NOT_BLOCK bit. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ static int check_acl(struct mnt_idmap *idmap, struct inode *inode, int mask) { … } /** * acl_permission_check - perform basic UNIX permission checking * @idmap: idmap of the mount the inode was found from * @inode: inode to check permissions on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) * * This function performs the basic UNIX permission checking. Since this * function may retrieve POSIX acls it needs to know whether it is called from a * blocking or non-blocking context and thus cares about the MAY_NOT_BLOCK bit. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ static int acl_permission_check(struct mnt_idmap *idmap, struct inode *inode, int mask) { … } /** * generic_permission - check for access rights on a Posix-like filesystem * @idmap: idmap of the mount the inode was found from * @inode: inode to check access rights for * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC, * %MAY_NOT_BLOCK ...) * * Used to check for read/write/execute permissions on a file. * We use "fsuid" for this, letting us set arbitrary permissions * for filesystem access without changing the "normal" uids which * are used for other things. * * generic_permission is rcu-walk aware. It returns -ECHILD in case an rcu-walk * request cannot be satisfied (eg. requires blocking or too much complexity). * It would then be called again in ref-walk mode. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int generic_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { … } EXPORT_SYMBOL(…); /** * do_inode_permission - UNIX permission checking * @idmap: idmap of the mount the inode was found from * @inode: inode to check permissions on * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC ...) * * We _really_ want to just do "generic_permission()" without * even looking at the inode->i_op values. So we keep a cache * flag in inode->i_opflags, that says "this has not special * permission function, use the fast case". */ static inline int do_inode_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { … } /** * sb_permission - Check superblock-level permissions * @sb: Superblock of inode to check permission on * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Separate out file-system wide checks from inode-specific permission checks. */ static int sb_permission(struct super_block *sb, struct inode *inode, int mask) { … } /** * inode_permission - Check for access rights to a given inode * @idmap: idmap of the mount the inode was found from * @inode: Inode to check permission on * @mask: Right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) * * Check for read/write/execute permissions on an inode. We use fs[ug]id for * this, letting us set arbitrary permissions for filesystem access without * changing the "normal" UIDs which are used for other things. * * When checking for MAY_APPEND, MAY_WRITE must also be set in @mask. */ int inode_permission(struct mnt_idmap *idmap, struct inode *inode, int mask) { … } EXPORT_SYMBOL(…); /** * path_get - get a reference to a path * @path: path to get the reference to * * Given a path increment the reference count to the dentry and the vfsmount. */ void path_get(const struct path *path) { … } EXPORT_SYMBOL(…); /** * path_put - put a reference to a path * @path: path to put the reference to * * Given a path decrement the reference count to the dentry and the vfsmount. */ void path_put(const struct path *path) { … } EXPORT_SYMBOL(…); #define EMBEDDED_LEVELS … struct nameidata { … } __randomize_layout; #define ND_ROOT_PRESET … #define ND_ROOT_GRABBED … #define ND_JUMPED … static void __set_nameidata(struct nameidata *p, int dfd, struct filename *name) { … } static inline void set_nameidata(struct nameidata *p, int dfd, struct filename *name, const struct path *root) { … } static void restore_nameidata(void) { … } static bool nd_alloc_stack(struct nameidata *nd) { … } /** * path_connected - Verify that a dentry is below mnt.mnt_root * @mnt: The mountpoint to check. * @dentry: The dentry to check. * * Rename can sometimes move a file or directory outside of a bind * mount, path_connected allows those cases to be detected. */ static bool path_connected(struct vfsmount *mnt, struct dentry *dentry) { … } static void drop_links(struct nameidata *nd) { … } static void leave_rcu(struct nameidata *nd) { … } static void terminate_walk(struct nameidata *nd) { … } /* path_put is needed afterwards regardless of success or failure */ static bool __legitimize_path(struct path *path, unsigned seq, unsigned mseq) { … } static inline bool legitimize_path(struct nameidata *nd, struct path *path, unsigned seq) { … } static bool legitimize_links(struct nameidata *nd) { … } static bool legitimize_root(struct nameidata *nd) { … } /* * Path walking has 2 modes, rcu-walk and ref-walk (see * Documentation/filesystems/path-lookup.txt). In situations when we can't * continue in RCU mode, we attempt to drop out of rcu-walk mode and grab * normal reference counts on dentries and vfsmounts to transition to ref-walk * mode. Refcounts are grabbed at the last known good point before rcu-walk * got stuck, so ref-walk may continue from there. If this is not successful * (eg. a seqcount has changed), then failure is returned and it's up to caller * to restart the path walk from the beginning in ref-walk mode. */ /** * try_to_unlazy - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * Returns: true on success, false on failure * * try_to_unlazy attempts to legitimize the current nd->path and nd->root * for ref-walk mode. * Must be called from rcu-walk context. * Nothing should touch nameidata between try_to_unlazy() failure and * terminate_walk(). */ static bool try_to_unlazy(struct nameidata *nd) { … } /** * try_to_unlazy_next - try to switch to ref-walk mode. * @nd: nameidata pathwalk data * @dentry: next dentry to step into * Returns: true on success, false on failure * * Similar to try_to_unlazy(), but here we have the next dentry already * picked by rcu-walk and want to legitimize that in addition to the current * nd->path and nd->root for ref-walk mode. Must be called from rcu-walk context. * Nothing should touch nameidata between try_to_unlazy_next() failure and * terminate_walk(). */ static bool try_to_unlazy_next(struct nameidata *nd, struct dentry *dentry) { … } static inline int d_revalidate(struct dentry *dentry, unsigned int flags) { … } /** * complete_walk - successful completion of path walk * @nd: pointer nameidata * * If we had been in RCU mode, drop out of it and legitimize nd->path. * Revalidate the final result, unless we'd already done that during * the path walk or the filesystem doesn't ask for it. Return 0 on * success, -error on failure. In case of failure caller does not * need to drop nd->path. */ static int complete_walk(struct nameidata *nd) { … } static int set_root(struct nameidata *nd) { … } static int nd_jump_root(struct nameidata *nd) { … } /* * Helper to directly jump to a known parsed path from ->get_link, * caller must have taken a reference to path beforehand. */ int nd_jump_link(const struct path *path) { … } static inline void put_link(struct nameidata *nd) { … } static int sysctl_protected_symlinks __read_mostly; static int sysctl_protected_hardlinks __read_mostly; static int sysctl_protected_fifos __read_mostly; static int sysctl_protected_regular __read_mostly; #ifdef CONFIG_SYSCTL static struct ctl_table namei_sysctls[] = …; static int __init init_fs_namei_sysctls(void) { … } fs_initcall(init_fs_namei_sysctls); #endif /* CONFIG_SYSCTL */ /** * may_follow_link - Check symlink following for unsafe situations * @nd: nameidata pathwalk data * @inode: Used for idmapping. * * In the case of the sysctl_protected_symlinks sysctl being enabled, * CAP_DAC_OVERRIDE needs to be specifically ignored if the symlink is * in a sticky world-writable directory. This is to protect privileged * processes from failing races against path names that may change out * from under them by way of other users creating malicious symlinks. * It will permit symlinks to be followed only when outside a sticky * world-writable directory, or when the uid of the symlink and follower * match, or when the directory owner matches the symlink's owner. * * Returns 0 if following the symlink is allowed, -ve on error. */ static inline int may_follow_link(struct nameidata *nd, const struct inode *inode) { … } /** * safe_hardlink_source - Check for safe hardlink conditions * @idmap: idmap of the mount the inode was found from * @inode: the source inode to hardlink from * * Return false if at least one of the following conditions: * - inode is not a regular file * - inode is setuid * - inode is setgid and group-exec * - access failure for read and write * * Otherwise returns true. */ static bool safe_hardlink_source(struct mnt_idmap *idmap, struct inode *inode) { … } /** * may_linkat - Check permissions for creating a hardlink * @idmap: idmap of the mount the inode was found from * @link: the source to hardlink from * * Block hardlink when all of: * - sysctl_protected_hardlinks enabled * - fsuid does not match inode * - hardlink source is unsafe (see safe_hardlink_source() above) * - not CAP_FOWNER in a namespace with the inode owner uid mapped * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. * * Returns 0 if successful, -ve on error. */ int may_linkat(struct mnt_idmap *idmap, const struct path *link) { … } /** * may_create_in_sticky - Check whether an O_CREAT open in a sticky directory * should be allowed, or not, on files that already * exist. * @idmap: idmap of the mount the inode was found from * @nd: nameidata pathwalk data * @inode: the inode of the file to open * * Block an O_CREAT open of a FIFO (or a regular file) when: * - sysctl_protected_fifos (or sysctl_protected_regular) is enabled * - the file already exists * - we are in a sticky directory * - we don't own the file * - the owner of the directory doesn't own the file * - the directory is world writable * If the sysctl_protected_fifos (or sysctl_protected_regular) is set to 2 * the directory doesn't have to be world writable: being group writable will * be enough. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. * * Returns 0 if the open is allowed, -ve on error. */ static int may_create_in_sticky(struct mnt_idmap *idmap, struct nameidata *nd, struct inode *const inode) { … } /* * follow_up - Find the mountpoint of path's vfsmount * * Given a path, find the mountpoint of its source file system. * Replace @path with the path of the mountpoint in the parent mount. * Up is towards /. * * Return 1 if we went up a level and 0 if we were already at the * root. */ int follow_up(struct path *path) { … } EXPORT_SYMBOL(…); static bool choose_mountpoint_rcu(struct mount *m, const struct path *root, struct path *path, unsigned *seqp) { … } static bool choose_mountpoint(struct mount *m, const struct path *root, struct path *path) { … } /* * Perform an automount * - return -EISDIR to tell follow_managed() to stop and return the path we * were called with. */ static int follow_automount(struct path *path, int *count, unsigned lookup_flags) { … } /* * mount traversal - out-of-line part. One note on ->d_flags accesses - * dentries are pinned but not locked here, so negative dentry can go * positive right under us. Use of smp_load_acquire() provides a barrier * sufficient for ->d_inode and ->d_flags consistency. */ static int __traverse_mounts(struct path *path, unsigned flags, bool *jumped, int *count, unsigned lookup_flags) { … } static inline int traverse_mounts(struct path *path, bool *jumped, int *count, unsigned lookup_flags) { … } int follow_down_one(struct path *path) { … } EXPORT_SYMBOL(…); /* * Follow down to the covering mount currently visible to userspace. At each * point, the filesystem owning that dentry may be queried as to whether the * caller is permitted to proceed or not. */ int follow_down(struct path *path, unsigned int flags) { … } EXPORT_SYMBOL(…); /* * Try to skip to top of mountpoint pile in rcuwalk mode. Fail if * we meet a managed dentry that would need blocking. */ static bool __follow_mount_rcu(struct nameidata *nd, struct path *path) { … } static inline int handle_mounts(struct nameidata *nd, struct dentry *dentry, struct path *path) { … } /* * This looks up the name in dcache and possibly revalidates the found dentry. * NULL is returned if the dentry does not exist in the cache. */ static struct dentry *lookup_dcache(const struct qstr *name, struct dentry *dir, unsigned int flags) { … } /* * Parent directory has inode locked exclusive. This is one * and only case when ->lookup() gets called on non in-lookup * dentries - as the matter of fact, this only gets called * when directory is guaranteed to have no in-lookup children * at all. */ struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, unsigned int flags) { … } EXPORT_SYMBOL(…); static struct dentry *lookup_fast(struct nameidata *nd) { … } /* Fast lookup failed, do it the slow way */ static struct dentry *__lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { … } static struct dentry *lookup_slow(const struct qstr *name, struct dentry *dir, unsigned int flags) { … } static inline int may_lookup(struct mnt_idmap *idmap, struct nameidata *restrict nd) { … } static int reserve_stack(struct nameidata *nd, struct path *link) { … } enum { … }; static const char *pick_link(struct nameidata *nd, struct path *link, struct inode *inode, int flags) { … } /* * Do we need to follow links? We _really_ want to be able * to do this check without having to look at inode->i_op, * so we keep a cache of "no, this doesn't need follow_link" * for the common case. * * NOTE: dentry must be what nd->next_seq had been sampled from. */ static const char *step_into(struct nameidata *nd, int flags, struct dentry *dentry) { … } static struct dentry *follow_dotdot_rcu(struct nameidata *nd) { … } static struct dentry *follow_dotdot(struct nameidata *nd) { … } static const char *handle_dots(struct nameidata *nd, int type) { … } static const char *walk_component(struct nameidata *nd, int flags) { … } /* * We can do the critical dentry name comparison and hashing * operations one word at a time, but we are limited to: * * - Architectures with fast unaligned word accesses. We could * do a "get_unaligned()" if this helps and is sufficiently * fast. * * - non-CONFIG_DEBUG_PAGEALLOC configurations (so that we * do not trap on the (extremely unlikely) case of a page * crossing operation. * * - Furthermore, we need an efficient 64-bit compile for the * 64-bit case in order to generate the "number of bytes in * the final mask". Again, that could be replaced with a * efficient population count instruction or similar. */ #ifdef CONFIG_DCACHE_WORD_ACCESS #include <asm/word-at-a-time.h> #ifdef HASH_MIX /* Architecture provides HASH_MIX and fold_hash() in <asm/hash.h> */ #elif defined(CONFIG_64BIT) /* * Register pressure in the mixing function is an issue, particularly * on 32-bit x86, but almost any function requires one state value and * one temporary. Instead, use a function designed for two state values * and no temporaries. * * This function cannot create a collision in only two iterations, so * we have two iterations to achieve avalanche. In those two iterations, * we have six layers of mixing, which is enough to spread one bit's * influence out to 2^6 = 64 state bits. * * Rotate constants are scored by considering either 64 one-bit input * deltas or 64*63/2 = 2016 two-bit input deltas, and finding the * probability of that delta causing a change to each of the 128 output * bits, using a sample of random initial states. * * The Shannon entropy of the computed probabilities is then summed * to produce a score. Ideally, any input change has a 50% chance of * toggling any given output bit. * * Mixing scores (in bits) for (12,45): * Input delta: 1-bit 2-bit * 1 round: 713.3 42542.6 * 2 rounds: 2753.7 140389.8 * 3 rounds: 5954.1 233458.2 * 4 rounds: 7862.6 256672.2 * Perfect: 8192 258048 * (64*128) (64*63/2 * 128) */ #define HASH_MIX(x, y, a) … /* * Fold two longs into one 32-bit hash value. This must be fast, but * latency isn't quite as critical, as there is a fair bit of additional * work done before the hash value is used. */ static inline unsigned int fold_hash(unsigned long x, unsigned long y) { … } #else /* 32-bit case */ /* * Mixing scores (in bits) for (7,20): * Input delta: 1-bit 2-bit * 1 round: 330.3 9201.6 * 2 rounds: 1246.4 25475.4 * 3 rounds: 1907.1 31295.1 * 4 rounds: 2042.3 31718.6 * Perfect: 2048 31744 * (32*64) (32*31/2 * 64) */ #define HASH_MIX … static inline unsigned int fold_hash(unsigned long x, unsigned long y) { /* Use arch-optimized multiply if one exists */ return __hash_32(y ^ __hash_32(x)); } #endif /* * Return the hash of a string of known length. This is carfully * designed to match hash_name(), which is the more critical function. * In particular, we must end by hashing a final word containing 0..7 * payload bytes, to match the way that hash_name() iterates until it * finds the delimiter after the name. */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { … } EXPORT_SYMBOL(…); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { … } EXPORT_SYMBOL(…); /* * Calculate the length and hash of the path component, and * return the length as the result. */ static inline const char *hash_name(struct nameidata *nd, const char *name, unsigned long *lastword) { … } /* * Note that the 'last' word is always zero-masked, but * was loaded as a possibly big-endian word. */ #ifdef __BIG_ENDIAN #define LAST_WORD_IS_DOT … #define LAST_WORD_IS_DOTDOT … #endif #else /* !CONFIG_DCACHE_WORD_ACCESS: Slow, byte-at-a-time version */ /* Return the hash of a string of known length */ unsigned int full_name_hash(const void *salt, const char *name, unsigned int len) { unsigned long hash = init_name_hash(salt); while (len--) hash = partial_name_hash((unsigned char)*name++, hash); return end_name_hash(hash); } EXPORT_SYMBOL(full_name_hash); /* Return the "hash_len" (hash and length) of a null-terminated string */ u64 hashlen_string(const void *salt, const char *name) { unsigned long hash = init_name_hash(salt); unsigned long len = 0, c; c = (unsigned char)*name; while (c) { len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } return hashlen_create(end_name_hash(hash), len); } EXPORT_SYMBOL(hashlen_string); /* * We know there's a real path component here of at least * one character. */ static inline const char *hash_name(struct nameidata *nd, const char *name, unsigned long *lastword) { unsigned long hash = init_name_hash(nd->path.dentry); unsigned long len = 0, c, last = 0; c = (unsigned char)*name; do { last = (last << 8) + c; len++; hash = partial_name_hash(c, hash); c = (unsigned char)name[len]; } while (c && c != '/'); // This is reliable for DOT or DOTDOT, since the component // cannot contain NUL characters - top bits being zero means // we cannot have had any other pathnames. *lastword = last; nd->last.hash = end_name_hash(hash); nd->last.len = len; return name + len; } #endif #ifndef LAST_WORD_IS_DOT #define LAST_WORD_IS_DOT … #define LAST_WORD_IS_DOTDOT … #endif /* * Name resolution. * This is the basic name resolution function, turning a pathname into * the final dentry. We expect 'base' to be positive and a directory. * * Returns 0 and nd will have valid dentry and mnt on success. * Returns error and drops reference to input namei data on failure. */ static int link_path_walk(const char *name, struct nameidata *nd) { … } /* must be paired with terminate_walk() */ static const char *path_init(struct nameidata *nd, unsigned flags) { … } static inline const char *lookup_last(struct nameidata *nd) { … } static int handle_lookup_down(struct nameidata *nd) { … } /* Returns 0 and nd will be valid on success; Returns error, otherwise. */ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path) { … } int filename_lookup(int dfd, struct filename *name, unsigned flags, struct path *path, struct path *root) { … } /* Returns 0 and nd will be valid on success; Returns error, otherwise. */ static int path_parentat(struct nameidata *nd, unsigned flags, struct path *parent) { … } /* Note: this does not consume "name" */ static int __filename_parentat(int dfd, struct filename *name, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root) { … } static int filename_parentat(int dfd, struct filename *name, unsigned int flags, struct path *parent, struct qstr *last, int *type) { … } /* does lookup, returns the object with parent locked */ static struct dentry *__kern_path_locked(int dfd, struct filename *name, struct path *path) { … } struct dentry *kern_path_locked(const char *name, struct path *path) { … } struct dentry *user_path_locked_at(int dfd, const char __user *name, struct path *path) { … } EXPORT_SYMBOL(…); int kern_path(const char *name, unsigned int flags, struct path *path) { … } EXPORT_SYMBOL(…); /** * vfs_path_parent_lookup - lookup a parent path relative to a dentry-vfsmount pair * @filename: filename structure * @flags: lookup flags * @parent: pointer to struct path to fill * @last: last component * @type: type of the last component * @root: pointer to struct path of the base directory */ int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root) { … } EXPORT_SYMBOL(…); /** * vfs_path_lookup - lookup a file path relative to a dentry-vfsmount pair * @dentry: pointer to dentry of the base directory * @mnt: pointer to vfs mount of the base directory * @name: pointer to file name * @flags: lookup flags * @path: pointer to struct path to fill */ int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, const char *name, unsigned int flags, struct path *path) { … } EXPORT_SYMBOL(…); static int lookup_one_common(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len, struct qstr *this) { … } /** * try_lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Look up a dentry by name in the dcache, returning NULL if it does not * currently exist. The function does not try to create a dentry. * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The caller must hold base->i_mutex. */ struct dentry *try_lookup_one_len(const char *name, struct dentry *base, int len) { … } EXPORT_SYMBOL(…); /** * lookup_one_len - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The caller must hold base->i_mutex. */ struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) { … } EXPORT_SYMBOL(…); /** * lookup_one - filesystem helper to lookup single pathname component * @idmap: idmap of the mount the lookup is performed from * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The caller must hold base->i_mutex. */ struct dentry *lookup_one(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len) { … } EXPORT_SYMBOL(…); /** * lookup_one_unlocked - filesystem helper to lookup single pathname component * @idmap: idmap of the mount the lookup is performed from * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * Unlike lookup_one_len, it should be called without the parent * i_mutex held, and will take the i_mutex itself if necessary. */ struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len) { … } EXPORT_SYMBOL(…); /** * lookup_one_positive_unlocked - filesystem helper to lookup single * pathname component * @idmap: idmap of the mount the lookup is performed from * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * This helper will yield ERR_PTR(-ENOENT) on negatives. The helper returns * known positive or ERR_PTR(). This is what most of the users want. * * Note that pinned negative with unlocked parent _can_ become positive at any * time, so callers of lookup_one_unlocked() need to be very careful; pinned * positives have >d_inode stable, so this one avoids such problems. * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * The helper should be called without i_mutex held. */ struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len) { … } EXPORT_SYMBOL(…); /** * lookup_one_len_unlocked - filesystem helper to lookup single pathname component * @name: pathname component to lookup * @base: base directory to lookup from * @len: maximum length @len should be interpreted to * * Note that this routine is purely a helper for filesystem usage and should * not be called by generic code. * * Unlike lookup_one_len, it should be called without the parent * i_mutex held, and will take the i_mutex itself if necessary. */ struct dentry *lookup_one_len_unlocked(const char *name, struct dentry *base, int len) { … } EXPORT_SYMBOL(…); /* * Like lookup_one_len_unlocked(), except that it yields ERR_PTR(-ENOENT) * on negatives. Returns known positive or ERR_PTR(); that's what * most of the users want. Note that pinned negative with unlocked parent * _can_ become positive at any time, so callers of lookup_one_len_unlocked() * need to be very careful; pinned positives have ->d_inode stable, so * this one avoids such problems. */ struct dentry *lookup_positive_unlocked(const char *name, struct dentry *base, int len) { … } EXPORT_SYMBOL(…); #ifdef CONFIG_UNIX98_PTYS int path_pts(struct path *path) { … } #endif int user_path_at(int dfd, const char __user *name, unsigned flags, struct path *path) { … } EXPORT_SYMBOL(…); int __check_sticky(struct mnt_idmap *idmap, struct inode *dir, struct inode *inode) { … } EXPORT_SYMBOL(…); /* * Check whether we can remove a link victim from directory dir, check * whether the type of victim is right. * 1. We can't do it if dir is read-only (done in permission()) * 2. We should have write and exec permissions on dir * 3. We can't remove anything from append-only dir * 4. We can't do anything with immutable dir (done in permission()) * 5. If the sticky bit on dir is set we should either * a. be owner of dir, or * b. be owner of victim, or * c. have CAP_FOWNER capability * 6. If the victim is append-only or immutable we can't do antyhing with * links pointing to it. * 7. If the victim has an unknown uid or gid we can't change the inode. * 8. If we were asked to remove a directory and victim isn't one - ENOTDIR. * 9. If we were asked to remove a non-directory and victim isn't one - EISDIR. * 10. We can't remove a root or mountpoint. * 11. We don't allow removal of NFS sillyrenamed files; it's handled by * nfs_async_unlink(). */ static int may_delete(struct mnt_idmap *idmap, struct inode *dir, struct dentry *victim, bool isdir) { … } /* Check whether we can create an object with dentry child in directory * dir. * 1. We can't do it if child already exists (open has special treatment for * this case, but since we are inlined it's OK) * 2. We can't do it if dir is read-only (done in permission()) * 3. We can't do it if the fs can't represent the fsuid or fsgid. * 4. We should have write and exec permissions on dir * 5. We can't do it if dir is immutable (done in permission()) */ static inline int may_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *child) { … } // p1 != p2, both are on the same filesystem, ->s_vfs_rename_mutex is held static struct dentry *lock_two_directories(struct dentry *p1, struct dentry *p2) { … } /* * p1 and p2 should be directories on the same fs. */ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) { … } EXPORT_SYMBOL(…); /* * c1 and p2 should be on the same fs. */ struct dentry *lock_rename_child(struct dentry *c1, struct dentry *p2) { … } EXPORT_SYMBOL(…); void unlock_rename(struct dentry *p1, struct dentry *p2) { … } EXPORT_SYMBOL(…); /** * vfs_prepare_mode - prepare the mode to be used for a new inode * @idmap: idmap of the mount the inode was found from * @dir: parent directory of the new inode * @mode: mode of the new inode * @mask_perms: allowed permission by the vfs * @type: type of file to be created * * This helper consolidates and enforces vfs restrictions on the @mode of a new * object to be created. * * Umask stripping depends on whether the filesystem supports POSIX ACLs (see * the kernel documentation for mode_strip_umask()). Moving umask stripping * after setgid stripping allows the same ordering for both non-POSIX ACL and * POSIX ACL supporting filesystems. * * Note that it's currently valid for @type to be 0 if a directory is created. * Filesystems raise that flag individually and we need to check whether each * filesystem can deal with receiving S_IFDIR from the vfs before we enforce a * non-zero type. * * Returns: mode to be passed to the filesystem */ static inline umode_t vfs_prepare_mode(struct mnt_idmap *idmap, const struct inode *dir, umode_t mode, umode_t mask_perms, umode_t type) { … } /** * vfs_create - create new file * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child file * @mode: mode of the child file * @want_excl: whether the file must not yet exist * * Create a new file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool want_excl) { … } EXPORT_SYMBOL(…); int vfs_mkobj(struct dentry *dentry, umode_t mode, int (*f)(struct dentry *, umode_t, void *), void *arg) { … } EXPORT_SYMBOL(…); bool may_open_dev(const struct path *path) { … } static int may_open(struct mnt_idmap *idmap, const struct path *path, int acc_mode, int flag) { … } static int handle_truncate(struct mnt_idmap *idmap, struct file *filp) { … } static inline int open_to_namei_flags(int flag) { … } static int may_o_create(struct mnt_idmap *idmap, const struct path *dir, struct dentry *dentry, umode_t mode) { … } /* * Attempt to atomically look up, create and open a file from a negative * dentry. * * Returns 0 if successful. The file will have been created and attached to * @file by the filesystem calling finish_open(). * * If the file was looked up only or didn't need creating, FMODE_OPENED won't * be set. The caller will need to perform the open themselves. @path will * have been updated to point to the new dentry. This may be negative. * * Returns an error code otherwise. */ static struct dentry *atomic_open(struct nameidata *nd, struct dentry *dentry, struct file *file, int open_flag, umode_t mode) { … } /* * Look up and maybe create and open the last component. * * Must be called with parent locked (exclusive in O_CREAT case). * * Returns 0 on success, that is, if * the file was successfully atomically created (if necessary) and opened, or * the file was not completely opened at this time, though lookups and * creations were performed. * These case are distinguished by presence of FMODE_OPENED on file->f_mode. * In the latter case dentry returned in @path might be negative if O_CREAT * hadn't been specified. * * An error code is returned on failure. */ static struct dentry *lookup_open(struct nameidata *nd, struct file *file, const struct open_flags *op, bool got_write) { … } static const char *open_last_lookups(struct nameidata *nd, struct file *file, const struct open_flags *op) { … } /* * Handle the last step of open() */ static int do_open(struct nameidata *nd, struct file *file, const struct open_flags *op) { … } /** * vfs_tmpfile - create tmpfile * @idmap: idmap of the mount the inode was found from * @parentpath: pointer to the path of the base directory * @file: file descriptor of the new tmpfile * @mode: mode of the new tmpfile * * Create a temporary file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_tmpfile(struct mnt_idmap *idmap, const struct path *parentpath, struct file *file, umode_t mode) { … } /** * kernel_tmpfile_open - open a tmpfile for kernel internal use * @idmap: idmap of the mount the inode was found from * @parentpath: path of the base directory * @mode: mode of the new tmpfile * @open_flag: flags * @cred: credentials for open * * Create and open a temporary file. The file is not accounted in nr_files, * hence this is only for kernel internal use, and must not be installed into * file tables or such. */ struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, const struct path *parentpath, umode_t mode, int open_flag, const struct cred *cred) { … } EXPORT_SYMBOL(…); static int do_tmpfile(struct nameidata *nd, unsigned flags, const struct open_flags *op, struct file *file) { … } static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file) { … } static struct file *path_openat(struct nameidata *nd, const struct open_flags *op, unsigned flags) { … } struct file *do_filp_open(int dfd, struct filename *pathname, const struct open_flags *op) { … } struct file *do_file_open_root(const struct path *root, const char *name, const struct open_flags *op) { … } static struct dentry *filename_create(int dfd, struct filename *name, struct path *path, unsigned int lookup_flags) { … } struct dentry *kern_path_create(int dfd, const char *pathname, struct path *path, unsigned int lookup_flags) { … } EXPORT_SYMBOL(…); void done_path_create(struct path *path, struct dentry *dentry) { … } EXPORT_SYMBOL(…); inline struct dentry *user_path_create(int dfd, const char __user *pathname, struct path *path, unsigned int lookup_flags) { … } EXPORT_SYMBOL(…); /** * vfs_mknod - create device node or file * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child device node * @mode: mode of the child device node * @dev: device number of device to create * * Create a device node or file. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { … } EXPORT_SYMBOL(…); static int may_mknod(umode_t mode) { … } static int do_mknodat(int dfd, struct filename *name, umode_t mode, unsigned int dev) { … } SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, umode_t, mode, unsigned int, dev) { … } SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, dev) { … } /** * vfs_mkdir - create directory * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child directory * @mode: mode of the child directory * * Create a directory. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { … } EXPORT_SYMBOL(…); int do_mkdirat(int dfd, struct filename *name, umode_t mode) { … } SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, umode_t, mode) { … } SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode) { … } /** * vfs_rmdir - remove directory * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child directory * * Remove a directory. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { … } EXPORT_SYMBOL(…); int do_rmdir(int dfd, struct filename *name) { … } SYSCALL_DEFINE1(rmdir, const char __user *, pathname) { … } /** * vfs_unlink - unlink a filesystem object * @idmap: idmap of the mount the inode was found from * @dir: parent directory * @dentry: victim * @delegated_inode: returns victim inode, if the inode is delegated. * * The caller must hold dir->i_mutex. * * If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and * return a reference to the inode in delegated_inode. The caller * should then break the delegation on that inode and retry. Because * breaking a delegation may take a long time, the caller should drop * dir->i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_unlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, struct inode **delegated_inode) { … } EXPORT_SYMBOL(…); /* * Make sure that the actual truncation of the file will occur outside its * directory's i_mutex. Truncate can take a long time if there is a lot of * writeout happening, and we don't want to prevent access to the directory * while waiting on the I/O. */ int do_unlinkat(int dfd, struct filename *name) { … } SYSCALL_DEFINE3(unlinkat, int, dfd, const char __user *, pathname, int, flag) { … } SYSCALL_DEFINE1(unlink, const char __user *, pathname) { … } /** * vfs_symlink - create symlink * @idmap: idmap of the mount the inode was found from * @dir: inode of the parent directory * @dentry: dentry of the child symlink file * @oldname: name of the file to link to * * Create a symlink. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *oldname) { … } EXPORT_SYMBOL(…); int do_symlinkat(struct filename *from, int newdfd, struct filename *to) { … } SYSCALL_DEFINE3(symlinkat, const char __user *, oldname, int, newdfd, const char __user *, newname) { … } SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newname) { … } /** * vfs_link - create a new link * @old_dentry: object to be linked * @idmap: idmap of the mount * @dir: new parent * @new_dentry: where to create the new link * @delegated_inode: returns inode needing a delegation break * * The caller must hold dir->i_mutex * * If vfs_link discovers a delegation on the to-be-linked file in need * of breaking, it will return -EWOULDBLOCK and return a reference to the * inode in delegated_inode. The caller should then break the delegation * and retry. Because breaking a delegation may take a long time, the * caller should drop the i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * * If the inode has been found through an idmapped mount the idmap of * the vfsmount must be passed through @idmap. This function will then take * care to map the inode according to @idmap before checking permissions. * On non-idmapped mounts or if permission checking is to be performed on the * raw inode simply pass @nop_mnt_idmap. */ int vfs_link(struct dentry *old_dentry, struct mnt_idmap *idmap, struct inode *dir, struct dentry *new_dentry, struct inode **delegated_inode) { … } EXPORT_SYMBOL(…); /* * Hardlinks are often used in delicate situations. We avoid * security-related surprises by not following symlinks on the * newname. --KAB * * We don't follow them on the oldname either to be compatible * with linux 2.0, and to avoid hard-linking to directories * and other special files. --ADM */ int do_linkat(int olddfd, struct filename *old, int newdfd, struct filename *new, int flags) { … } SYSCALL_DEFINE5(linkat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, int, flags) { … } SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname) { … } /** * vfs_rename - rename a filesystem object * @rd: pointer to &struct renamedata info * * The caller must hold multiple mutexes--see lock_rename()). * * If vfs_rename discovers a delegation in need of breaking at either * the source or destination, it will return -EWOULDBLOCK and return a * reference to the inode in delegated_inode. The caller should then * break the delegation and retry. Because breaking a delegation may * take a long time, the caller should drop all locks before doing * so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. * * The worst of all namespace operations - renaming directory. "Perverted" * doesn't even start to describe it. Somebody in UCB had a heck of a trip... * Problems: * * a) we can get into loop creation. * b) race potential - two innocent renames can create a loop together. * That's where 4.4BSD screws up. Current fix: serialization on * sb->s_vfs_rename_mutex. We might be more accurate, but that's another * story. * c) we may have to lock up to _four_ objects - parents and victim (if it exists), * and source (if it's a non-directory or a subdirectory that moves to * different parent). * And that - after we got ->i_mutex on parents (until then we don't know * whether the target exists). Solution: try to be smart with locking * order for inodes. We rely on the fact that tree topology may change * only under ->s_vfs_rename_mutex _and_ that parent of the object we * move will be locked. Thus we can rank directories by the tree * (ancestors first) and rank all non-directories after them. * That works since everybody except rename does "lock parent, lookup, * lock child" and rename is under ->s_vfs_rename_mutex. * HOWEVER, it relies on the assumption that any object with ->lookup() * has no more than 1 dentry. If "hybrid" objects will ever appear, * we'd better make sure that there's no link(2) for them. * d) conversion from fhandle to dentry may come in the wrong moment - when * we are removing the target. Solution: we will have to grab ->i_mutex * in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on * ->i_mutex on parents, which works but leads to some truly excessive * locking]. */ int vfs_rename(struct renamedata *rd) { … } EXPORT_SYMBOL(…); int do_renameat2(int olddfd, struct filename *from, int newdfd, struct filename *to, unsigned int flags) { … } SYSCALL_DEFINE5(renameat2, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname, unsigned int, flags) { … } SYSCALL_DEFINE4(renameat, int, olddfd, const char __user *, oldname, int, newdfd, const char __user *, newname) { … } SYSCALL_DEFINE2(rename, const char __user *, oldname, const char __user *, newname) { … } int readlink_copy(char __user *buffer, int buflen, const char *link) { … } /** * vfs_readlink - copy symlink body into userspace buffer * @dentry: dentry on which to get symbolic link * @buffer: user memory pointer * @buflen: size of buffer * * Does not touch atime. That's up to the caller if necessary * * Does not call security hook. */ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen) { … } EXPORT_SYMBOL(…); /** * vfs_get_link - get symlink body * @dentry: dentry on which to get symbolic link * @done: caller needs to free returned data with this * * Calls security hook and i_op->get_link() on the supplied inode. * * It does not touch atime. That's up to the caller if necessary. * * Does not work on "special" symlinks like /proc/$$/fd/N */ const char *vfs_get_link(struct dentry *dentry, struct delayed_call *done) { … } EXPORT_SYMBOL(…); /* get the link contents into pagecache */ const char *page_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *callback) { … } EXPORT_SYMBOL(…); void page_put_link(void *arg) { … } EXPORT_SYMBOL(…); int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) { … } EXPORT_SYMBOL(…); int page_symlink(struct inode *inode, const char *symname, int len) { … } EXPORT_SYMBOL(…); const struct inode_operations page_symlink_inode_operations = …; EXPORT_SYMBOL(…);