X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fnamei.c;h=432d6bc6fab086ef8254119a0b39fc97bee7025b;hb=e9f7bee1df223dcf83743b46cb06c08d95497ec0;hp=b3f8a1966c9cafe0113370bb5843a9b91b96758f;hpb=cc4e69dee4a080f6eae3f410daec2593f4fa6f00;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/namei.c b/fs/namei.c index b3f8a19..432d6bc 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -28,7 +28,10 @@ #include #include #include +#include #include +#include +#include #include #include @@ -101,7 +104,7 @@ */ /* * [Sep 2001 AV] Single-semaphore locking scheme (kudos to David Holland) - * implemented. Let's see if raised priority of ->s_vfs_rename_sem gives + * implemented. Let's see if raised priority of ->s_vfs_rename_mutex gives * any extra contention... */ @@ -112,7 +115,7 @@ * POSIX.1 2.4: an empty pathname is invalid (ENOENT). * PATH_MAX includes the nul terminator --RR. */ -static inline int do_getname(const char __user *filename, char *page) +static int do_getname(const char __user *filename, char *page) { int retval; unsigned long len = PATH_MAX; @@ -156,7 +159,7 @@ char * getname(const char __user * filename) #ifdef CONFIG_AUDITSYSCALL void putname(const char *name) { - if (unlikely(current->audit_context)) + if (unlikely(!audit_dummy_context())) audit_putname(name); else __putname(name); @@ -224,10 +227,10 @@ int generic_permission(struct inode *inode, int mask, int permission(struct inode *inode, int mask, struct nameidata *nd) { + umode_t mode = inode->i_mode; int retval, submask; if (mask & MAY_WRITE) { - umode_t mode = inode->i_mode; /* * Nobody gets write access to a read-only fs. @@ -244,6 +247,13 @@ int permission(struct inode *inode, int mask, struct nameidata *nd) } + /* + * MAY_EXEC on regular files requires special handling: We override + * filesystem execute permissions if the mode bits aren't set. + */ + if ((mask & MAY_EXEC) && S_ISREG(mode) && !(mode & S_IXUGO)) + return -EACCES; + /* Ordinary permission routines do not understand MAY_APPEND. */ submask = mask & ~MAY_APPEND; if (inode->i_op && inode->i_op->permission) @@ -256,6 +266,38 @@ int permission(struct inode *inode, int mask, struct nameidata *nd) return security_inode_permission(inode, mask, nd); } +/** + * vfs_permission - check for access rights to a given path + * @nd: lookup result that describes the path + * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) + * + * Used to check for read/write/execute permissions on a path. + * We use "fsuid" for this, letting us set arbitrary permissions + * for filesystem access without changing the "normal" uids which + * are used for other things. + */ +int vfs_permission(struct nameidata *nd, int mask) +{ + return permission(nd->dentry->d_inode, mask, nd); +} + +/** + * file_permission - check for additional access rights to a given file + * @file: file to check access rights for + * @mask: right to check for (%MAY_READ, %MAY_WRITE, %MAY_EXEC) + * + * Used to check for read/write/execute permissions on an already opened + * file. + * + * Note: + * Do not use this function in new code. All access checks should + * be done using vfs_permission(). + */ +int file_permission(struct file *file, int mask) +{ + return permission(file->f_dentry->d_inode, mask, NULL); +} + /* * get_write_access() gets write permission for a file. * put_write_access() releases this write permission. @@ -363,7 +405,7 @@ static struct dentry * cached_lookup(struct dentry * parent, struct qstr * name, * short-cut DAC fails, then call permission() to do more * complete permission check. */ -static inline int exec_permission_lite(struct inode *inode, +static int exec_permission_lite(struct inode *inode, struct nameidata *nd) { umode_t mode = inode->i_mode; @@ -406,7 +448,7 @@ static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, s struct dentry * result; struct inode *dir = parent->d_inode; - down(&dir->i_sem); + mutex_lock(&dir->i_mutex); /* * First re-do the cached lookup just in case it was created * while we waited for the directory semaphore.. @@ -432,7 +474,7 @@ static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, s else result = dentry; } - up(&dir->i_sem); + mutex_unlock(&dir->i_mutex); return result; } @@ -440,7 +482,7 @@ static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, s * Uhhuh! Nasty case: the cache was re-populated while * we waited on the semaphore. Need to revalidate. */ - up(&dir->i_sem); + mutex_unlock(&dir->i_mutex); if (result->d_op && result->d_op->d_revalidate) { if (!result->d_op->d_revalidate(result, nd) && !d_invalidate(result)) { dput(result); @@ -453,7 +495,7 @@ static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, s static int __emul_lookup_dentry(const char *, struct nameidata *); /* SMP-safe */ -static inline int +static __always_inline int walk_init_root(const char *name, struct nameidata *nd) { read_lock(¤t->fs->lock); @@ -471,7 +513,7 @@ walk_init_root(const char *name, struct nameidata *nd) return 1; } -static inline int __vfs_follow_link(struct nameidata *nd, const char *link) +static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *link) { int res = 0; char *name; @@ -511,7 +553,23 @@ struct path { struct dentry *dentry; }; -static inline int __do_follow_link(struct path *path, struct nameidata *nd) +static inline void dput_path(struct path *path, struct nameidata *nd) +{ + dput(path->dentry); + if (path->mnt != nd->mnt) + mntput(path->mnt); +} + +static inline void path_to_nameidata(struct path *path, struct nameidata *nd) +{ + dput(nd->dentry); + if (nd->mnt != path->mnt) + mntput(nd->mnt); + nd->mnt = path->mnt; + nd->dentry = path->dentry; +} + +static __always_inline int __do_follow_link(struct path *path, struct nameidata *nd) { int error; void *cookie; @@ -520,8 +578,11 @@ static inline int __do_follow_link(struct path *path, struct nameidata *nd) touch_atime(path->mnt, dentry); nd_set_link(nd, NULL); - if (path->mnt == nd->mnt) - mntget(path->mnt); + if (path->mnt != nd->mnt) { + path_to_nameidata(path, nd); + dget(dentry); + } + mntget(path->mnt); cookie = dentry->d_inode->i_op->follow_link(dentry, nd); error = PTR_ERR(cookie); if (!IS_ERR(cookie)) { @@ -538,22 +599,6 @@ static inline int __do_follow_link(struct path *path, struct nameidata *nd) return error; } -static inline void dput_path(struct path *path, struct nameidata *nd) -{ - dput(path->dentry); - if (path->mnt != nd->mnt) - mntput(path->mnt); -} - -static inline void path_to_nameidata(struct path *path, struct nameidata *nd) -{ - dput(nd->dentry); - if (nd->mnt != path->mnt) - mntput(nd->mnt); - nd->mnt = path->mnt; - nd->dentry = path->dentry; -} - /* * This limits recursive symlink follows to 8, while * limiting consecutive symlinks to 40. @@ -657,7 +702,7 @@ int follow_down(struct vfsmount **mnt, struct dentry **dentry) return 0; } -static inline void follow_dotdot(struct nameidata *nd) +static __always_inline void follow_dotdot(struct nameidata *nd) { while(1) { struct vfsmount *parent; @@ -755,7 +800,7 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd) inode = nd->dentry->d_inode; if (nd->depth) - lookup_flags = LOOKUP_FOLLOW; + lookup_flags = LOOKUP_FOLLOW | (nd->flags & LOOKUP_CONTINUE); /* At this point we know we have a real path component. */ for(;;) { @@ -765,9 +810,8 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd) nd->flags |= LOOKUP_CONTINUE; err = exec_permission_lite(inode, nd); - if (err == -EAGAIN) { - err = permission(inode, MAY_EXEC, nd); - } + if (err == -EAGAIN) + err = vfs_permission(nd, MAY_EXEC); if (err) break; @@ -851,7 +895,8 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd) last_with_slashes: lookup_flags |= LOOKUP_FOLLOW | LOOKUP_DIRECTORY; last_component: - nd->flags &= ~LOOKUP_CONTINUE; + /* Clear LOOKUP_CONTINUE iff it was previously unset */ + nd->flags &= lookup_flags | ~LOOKUP_CONTINUE; if (lookup_flags & LOOKUP_PARENT) goto lookup_parent; if (this.name[0] == '.') switch (this.len) { @@ -1031,16 +1076,19 @@ set_it: } /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ -int fastcall path_lookup(const char *name, unsigned int flags, struct nameidata *nd) +static int fastcall do_path_lookup(int dfd, const char *name, + unsigned int flags, struct nameidata *nd) { int retval = 0; + int fput_needed; + struct file *file; nd->last_type = LAST_ROOT; /* if there are only slashes... */ nd->flags = flags; nd->depth = 0; - read_lock(¤t->fs->lock); if (*name=='/') { + read_lock(¤t->fs->lock); if (current->fs->altroot && !(nd->flags & LOOKUP_NOALT)) { nd->mnt = mntget(current->fs->altrootmnt); nd->dentry = dget(current->fs->altroot); @@ -1051,22 +1099,60 @@ int fastcall path_lookup(const char *name, unsigned int flags, struct nameidata } nd->mnt = mntget(current->fs->rootmnt); nd->dentry = dget(current->fs->root); - } else { + read_unlock(¤t->fs->lock); + } else if (dfd == AT_FDCWD) { + read_lock(¤t->fs->lock); nd->mnt = mntget(current->fs->pwdmnt); nd->dentry = dget(current->fs->pwd); + read_unlock(¤t->fs->lock); + } else { + struct dentry *dentry; + + file = fget_light(dfd, &fput_needed); + retval = -EBADF; + if (!file) + goto out_fail; + + dentry = file->f_dentry; + + retval = -ENOTDIR; + if (!S_ISDIR(dentry->d_inode->i_mode)) + goto fput_fail; + + retval = file_permission(file, MAY_EXEC); + if (retval) + goto fput_fail; + + nd->mnt = mntget(file->f_vfsmnt); + nd->dentry = dget(dentry); + + fput_light(file, fput_needed); } - read_unlock(¤t->fs->lock); current->total_link_count = 0; retval = link_path_walk(name, nd); out: - if (unlikely(current->audit_context - && nd && nd->dentry && nd->dentry->d_inode)) - audit_inode(name, nd->dentry->d_inode, flags); + if (likely(retval == 0)) { + if (unlikely(!audit_dummy_context() && nd && nd->dentry && + nd->dentry->d_inode)) + audit_inode(name, nd->dentry->d_inode); + } +out_fail: return retval; + +fput_fail: + fput_light(file, fput_needed); + goto out_fail; } -static int __path_lookup_intent_open(const char *name, unsigned int lookup_flags, - struct nameidata *nd, int open_flags, int create_mode) +int fastcall path_lookup(const char *name, unsigned int flags, + struct nameidata *nd) +{ + return do_path_lookup(AT_FDCWD, name, flags, nd); +} + +static int __path_lookup_intent_open(int dfd, const char *name, + unsigned int lookup_flags, struct nameidata *nd, + int open_flags, int create_mode) { struct file *filp = get_empty_filp(); int err; @@ -1076,7 +1162,7 @@ static int __path_lookup_intent_open(const char *name, unsigned int lookup_flags nd->intent.open.file = filp; nd->intent.open.flags = open_flags; nd->intent.open.create_mode = create_mode; - err = path_lookup(name, lookup_flags|LOOKUP_OPEN, nd); + err = do_path_lookup(dfd, name, lookup_flags|LOOKUP_OPEN, nd); if (IS_ERR(nd->intent.open.file)) { if (err == 0) { err = PTR_ERR(nd->intent.open.file); @@ -1089,31 +1175,34 @@ static int __path_lookup_intent_open(const char *name, unsigned int lookup_flags /** * path_lookup_open - lookup a file path with open intent + * @dfd: the directory to use as base, or AT_FDCWD * @name: pointer to file name * @lookup_flags: lookup intent flags * @nd: pointer to nameidata * @open_flags: open intent flags */ -int path_lookup_open(const char *name, unsigned int lookup_flags, +int path_lookup_open(int dfd, const char *name, unsigned int lookup_flags, struct nameidata *nd, int open_flags) { - return __path_lookup_intent_open(name, lookup_flags, nd, + return __path_lookup_intent_open(dfd, name, lookup_flags, nd, open_flags, 0); } /** * path_lookup_create - lookup a file path with open + create intent + * @dfd: the directory to use as base, or AT_FDCWD * @name: pointer to file name * @lookup_flags: lookup intent flags * @nd: pointer to nameidata * @open_flags: open intent flags * @create_mode: create intent flags */ -int path_lookup_create(const char *name, unsigned int lookup_flags, - struct nameidata *nd, int open_flags, int create_mode) +static int path_lookup_create(int dfd, const char *name, + unsigned int lookup_flags, struct nameidata *nd, + int open_flags, int create_mode) { - return __path_lookup_intent_open(name, lookup_flags|LOOKUP_CREATE, nd, - open_flags, create_mode); + return __path_lookup_intent_open(dfd, name, lookup_flags|LOOKUP_CREATE, + nd, open_flags, create_mode); } int __user_path_lookup_open(const char __user *name, unsigned int lookup_flags, @@ -1123,7 +1212,7 @@ int __user_path_lookup_open(const char __user *name, unsigned int lookup_flags, int err = PTR_ERR(tmp); if (!IS_ERR(tmp)) { - err = __path_lookup_intent_open(tmp, lookup_flags, nd, open_flags, 0); + err = __path_lookup_intent_open(AT_FDCWD, tmp, lookup_flags, nd, open_flags, 0); putname(tmp); } return err; @@ -1173,9 +1262,9 @@ out: return dentry; } -struct dentry * lookup_hash(struct qstr *name, struct dentry * base) +static struct dentry *lookup_hash(struct nameidata *nd) { - return __lookup_hash(name, base, NULL); + return __lookup_hash(&nd->last, nd->dentry, nd); } /* SMP-safe */ @@ -1199,7 +1288,7 @@ struct dentry * lookup_one_len(const char * name, struct dentry * base, int len) } this.hash = end_name_hash(hash); - return lookup_hash(&this, base); + return __lookup_hash(&this, base, NULL); access: return ERR_PTR(-EACCES); } @@ -1215,18 +1304,24 @@ access: * that namei follows links, while lnamei does not. * SMP-safe */ -int fastcall __user_walk(const char __user *name, unsigned flags, struct nameidata *nd) +int fastcall __user_walk_fd(int dfd, const char __user *name, unsigned flags, + struct nameidata *nd) { char *tmp = getname(name); int err = PTR_ERR(tmp); if (!IS_ERR(tmp)) { - err = path_lookup(tmp, flags, nd); + err = do_path_lookup(dfd, tmp, flags, nd); putname(tmp); } return err; } +int fastcall __user_walk(const char __user *name, unsigned flags, struct nameidata *nd) +{ + return __user_walk_fd(AT_FDCWD, name, flags, nd); +} + /* * It's inline, so penalty for filesystems that don't use sticky bit is * minimal. @@ -1261,7 +1356,7 @@ static inline int check_sticky(struct inode *dir, struct inode *inode) * 10. We don't allow removal of NFS sillyrenamed files; it's handled by * nfs_async_unlink(). */ -static inline int may_delete(struct inode *dir,struct dentry *victim,int isdir) +static int may_delete(struct inode *dir,struct dentry *victim,int isdir) { int error; @@ -1269,6 +1364,7 @@ static inline int may_delete(struct inode *dir,struct dentry *victim,int isdir) return -ENOENT; BUG_ON(victim->d_parent->d_inode != dir); + audit_inode_child(victim->d_name.name, victim->d_inode, dir); error = permission(dir,MAY_WRITE | MAY_EXEC, NULL); if (error) @@ -1334,39 +1430,39 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) struct dentry *p; if (p1 == p2) { - down(&p1->d_inode->i_sem); + mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT); return NULL; } - down(&p1->d_inode->i_sb->s_vfs_rename_sem); + mutex_lock(&p1->d_inode->i_sb->s_vfs_rename_mutex); for (p = p1; p->d_parent != p; p = p->d_parent) { if (p->d_parent == p2) { - down(&p2->d_inode->i_sem); - down(&p1->d_inode->i_sem); + mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_CHILD); return p; } } for (p = p2; p->d_parent != p; p = p->d_parent) { if (p->d_parent == p1) { - down(&p1->d_inode->i_sem); - down(&p2->d_inode->i_sem); + mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD); return p; } } - down(&p1->d_inode->i_sem); - down(&p2->d_inode->i_sem); + mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD); return NULL; } void unlock_rename(struct dentry *p1, struct dentry *p2) { - up(&p1->d_inode->i_sem); + mutex_unlock(&p1->d_inode->i_mutex); if (p1 != p2) { - up(&p2->d_inode->i_sem); - up(&p1->d_inode->i_sb->s_vfs_rename_sem); + mutex_unlock(&p2->d_inode->i_mutex); + mutex_unlock(&p1->d_inode->i_sb->s_vfs_rename_mutex); } } @@ -1388,7 +1484,7 @@ int vfs_create(struct inode *dir, struct dentry *dentry, int mode, DQUOT_INIT(dir); error = dir->i_op->create(dir, dentry, mode, nd); if (!error) - fsnotify_create(dir, dentry->d_name.name); + fsnotify_create(dir, dentry); return error; } @@ -1407,7 +1503,7 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) if (S_ISDIR(inode->i_mode) && (flag & FMODE_WRITE)) return -EISDIR; - error = permission(inode, acc_mode, nd); + error = vfs_permission(nd, acc_mode); if (error) return error; @@ -1459,7 +1555,7 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) if (!error) { DQUOT_INIT(inode); - error = do_truncate(dentry, 0, NULL); + error = do_truncate(dentry, 0, ATTR_MTIME|ATTR_CTIME, NULL); } put_write_access(inode); if (error) @@ -1485,7 +1581,8 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) * for symlinks (where the permissions are checked later). * SMP-safe */ -int open_namei(const char * pathname, int flag, int mode, struct nameidata *nd) +int open_namei(int dfd, const char *pathname, int flag, + int mode, struct nameidata *nd) { int acc_mode, error; struct path path; @@ -1507,7 +1604,8 @@ int open_namei(const char * pathname, int flag, int mode, struct nameidata *nd) * The simplest case - just a plain lookup. */ if (!(flag & O_CREAT)) { - error = path_lookup_open(pathname, lookup_flags(flag), nd, flag); + error = path_lookup_open(dfd, pathname, lookup_flags(flag), + nd, flag); if (error) return error; goto ok; @@ -1516,7 +1614,7 @@ int open_namei(const char * pathname, int flag, int mode, struct nameidata *nd) /* * Create - we need to know the parent. */ - error = path_lookup_create(pathname, LOOKUP_PARENT, nd, flag, mode); + error = path_lookup_create(dfd,pathname,LOOKUP_PARENT,nd,flag,mode); if (error) return error; @@ -1531,23 +1629,29 @@ int open_namei(const char * pathname, int flag, int mode, struct nameidata *nd) dir = nd->dentry; nd->flags &= ~LOOKUP_PARENT; - down(&dir->d_inode->i_sem); - path.dentry = __lookup_hash(&nd->last, nd->dentry, nd); + mutex_lock(&dir->d_inode->i_mutex); + path.dentry = lookup_hash(nd); path.mnt = nd->mnt; do_last: error = PTR_ERR(path.dentry); if (IS_ERR(path.dentry)) { - up(&dir->d_inode->i_sem); + mutex_unlock(&dir->d_inode->i_mutex); goto exit; } + if (IS_ERR(nd->intent.open.file)) { + mutex_unlock(&dir->d_inode->i_mutex); + error = PTR_ERR(nd->intent.open.file); + goto exit_dput; + } + /* Negative dentry, just create the file */ if (!path.dentry->d_inode) { if (!IS_POSIXACL(dir->d_inode)) mode &= ~current->fs->umask; error = vfs_create(dir->d_inode, path.dentry, mode, nd); - up(&dir->d_inode->i_sem); + mutex_unlock(&dir->d_inode->i_mutex); dput(nd->dentry); nd->dentry = path.dentry; if (error) @@ -1561,7 +1665,8 @@ do_last: /* * It already exists. */ - up(&dir->d_inode->i_sem); + mutex_unlock(&dir->d_inode->i_mutex); + audit_inode_update(path.dentry->d_inode); error = -EEXIST; if (flag & O_EXCL) @@ -1572,6 +1677,7 @@ do_last: if (flag & O_NOFOLLOW) goto exit_dput; } + error = -ENOENT; if (!path.dentry->d_inode) goto exit_dput; @@ -1615,8 +1721,14 @@ do_link: if (error) goto exit_dput; error = __do_follow_link(&path, nd); - if (error) + if (error) { + /* Does someone understand code flow here? Or it is only + * me so stupid? Anathema to whoever designed this non-sense + * with "intent.open". + */ + release_open_intent(nd); return error; + } nd->flags &= ~LOOKUP_PARENT; if (nd->last_type == LAST_BIND) goto ok; @@ -1633,8 +1745,8 @@ do_link: goto exit; } dir = nd->dentry; - down(&dir->d_inode->i_sem); - path.dentry = __lookup_hash(&nd->last, nd->dentry, nd); + mutex_lock(&dir->d_inode->i_mutex); + path.dentry = lookup_hash(nd); path.mnt = nd->mnt; __putname(nd->last.name); goto do_last; @@ -1648,13 +1760,13 @@ do_link: * Simple function to lookup and return a dentry and create it * if it doesn't exist. Is SMP-safe. * - * Returns with nd->dentry->d_inode->i_sem locked. + * Returns with nd->dentry->d_inode->i_mutex locked. */ struct dentry *lookup_create(struct nameidata *nd, int is_dir) { struct dentry *dentry = ERR_PTR(-EEXIST); - down(&nd->dentry->d_inode->i_sem); + mutex_lock_nested(&nd->dentry->d_inode->i_mutex, I_MUTEX_PARENT); /* * Yucky last component or no last component at all? * (foo/., foo/.., /////) @@ -1662,11 +1774,13 @@ struct dentry *lookup_create(struct nameidata *nd, int is_dir) if (nd->last_type != LAST_NORM) goto fail; nd->flags &= ~LOOKUP_PARENT; + nd->flags |= LOOKUP_CREATE; + nd->intent.open.flags = O_EXCL; /* * Do the final lookup. */ - dentry = lookup_hash(&nd->last, nd->dentry); + dentry = lookup_hash(nd); if (IS_ERR(dentry)) goto fail; @@ -1707,11 +1821,12 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) DQUOT_INIT(dir); error = dir->i_op->mknod(dir, dentry, mode, dev); if (!error) - fsnotify_create(dir, dentry->d_name.name); + fsnotify_create(dir, dentry); return error; } -asmlinkage long sys_mknod(const char __user * filename, int mode, unsigned dev) +asmlinkage long sys_mknodat(int dfd, const char __user *filename, int mode, + unsigned dev) { int error = 0; char * tmp; @@ -1724,7 +1839,7 @@ asmlinkage long sys_mknod(const char __user * filename, int mode, unsigned dev) if (IS_ERR(tmp)) return PTR_ERR(tmp); - error = path_lookup(tmp, LOOKUP_PARENT, &nd); + error = do_path_lookup(dfd, tmp, LOOKUP_PARENT, &nd); if (error) goto out; dentry = lookup_create(&nd, 0); @@ -1752,7 +1867,7 @@ asmlinkage long sys_mknod(const char __user * filename, int mode, unsigned dev) } dput(dentry); } - up(&nd.dentry->d_inode->i_sem); + mutex_unlock(&nd.dentry->d_inode->i_mutex); path_release(&nd); out: putname(tmp); @@ -1760,6 +1875,11 @@ out: return error; } +asmlinkage long sys_mknod(const char __user *filename, int mode, unsigned dev) +{ + return sys_mknodat(AT_FDCWD, filename, mode, dev); +} + int vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) { int error = may_create(dir, dentry, NULL); @@ -1778,11 +1898,11 @@ int vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) DQUOT_INIT(dir); error = dir->i_op->mkdir(dir, dentry, mode); if (!error) - fsnotify_mkdir(dir, dentry->d_name.name); + fsnotify_mkdir(dir, dentry); return error; } -asmlinkage long sys_mkdir(const char __user * pathname, int mode) +asmlinkage long sys_mkdirat(int dfd, const char __user *pathname, int mode) { int error = 0; char * tmp; @@ -1793,7 +1913,7 @@ asmlinkage long sys_mkdir(const char __user * pathname, int mode) struct dentry *dentry; struct nameidata nd; - error = path_lookup(tmp, LOOKUP_PARENT, &nd); + error = do_path_lookup(dfd, tmp, LOOKUP_PARENT, &nd); if (error) goto out; dentry = lookup_create(&nd, 1); @@ -1804,7 +1924,7 @@ asmlinkage long sys_mkdir(const char __user * pathname, int mode) error = vfs_mkdir(nd.dentry->d_inode, dentry, mode); dput(dentry); } - up(&nd.dentry->d_inode->i_sem); + mutex_unlock(&nd.dentry->d_inode->i_mutex); path_release(&nd); out: putname(tmp); @@ -1813,6 +1933,11 @@ out: return error; } +asmlinkage long sys_mkdir(const char __user *pathname, int mode) +{ + return sys_mkdirat(AT_FDCWD, pathname, mode); +} + /* * We try to drop the dentry early: we should have * a usage count of 2 if we're the only user of this @@ -1853,7 +1978,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry) DQUOT_INIT(dir); - down(&dentry->d_inode->i_sem); + mutex_lock(&dentry->d_inode->i_mutex); dentry_unhash(dentry); if (d_mountpoint(dentry)) error = -EBUSY; @@ -1865,7 +1990,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry) dentry->d_inode->i_flags |= S_DEAD; } } - up(&dentry->d_inode->i_sem); + mutex_unlock(&dentry->d_inode->i_mutex); if (!error) { d_delete(dentry); } @@ -1874,7 +1999,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry) return error; } -asmlinkage long sys_rmdir(const char __user * pathname) +static long do_rmdir(int dfd, const char __user *pathname) { int error = 0; char * name; @@ -1885,7 +2010,7 @@ asmlinkage long sys_rmdir(const char __user * pathname) if(IS_ERR(name)) return PTR_ERR(name); - error = path_lookup(name, LOOKUP_PARENT, &nd); + error = do_path_lookup(dfd, name, LOOKUP_PARENT, &nd); if (error) goto exit; @@ -1900,14 +2025,14 @@ asmlinkage long sys_rmdir(const char __user * pathname) error = -EBUSY; goto exit1; } - down(&nd.dentry->d_inode->i_sem); - dentry = lookup_hash(&nd.last, nd.dentry); + mutex_lock_nested(&nd.dentry->d_inode->i_mutex, I_MUTEX_PARENT); + dentry = lookup_hash(&nd); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { error = vfs_rmdir(nd.dentry->d_inode, dentry); dput(dentry); } - up(&nd.dentry->d_inode->i_sem); + mutex_unlock(&nd.dentry->d_inode->i_mutex); exit1: path_release(&nd); exit: @@ -1915,6 +2040,11 @@ exit: return error; } +asmlinkage long sys_rmdir(const char __user *pathname) +{ + return do_rmdir(AT_FDCWD, pathname); +} + int vfs_unlink(struct inode *dir, struct dentry *dentry) { int error = may_delete(dir, dentry, 0); @@ -1927,7 +2057,7 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry) DQUOT_INIT(dir); - down(&dentry->d_inode->i_sem); + mutex_lock(&dentry->d_inode->i_mutex); if (d_mountpoint(dentry)) error = -EBUSY; else { @@ -1935,7 +2065,7 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry) if (!error) error = dir->i_op->unlink(dir, dentry); } - up(&dentry->d_inode->i_sem); + mutex_unlock(&dentry->d_inode->i_mutex); /* We don't d_delete() NFS sillyrenamed files--they still exist. */ if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) { @@ -1947,11 +2077,11 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry) /* * Make sure that the actual truncation of the file will occur outside its - * directory's i_sem. Truncate can take a long time if there is a lot of + * 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. */ -asmlinkage long sys_unlink(const char __user * pathname) +static long do_unlinkat(int dfd, const char __user *pathname) { int error = 0; char * name; @@ -1963,14 +2093,14 @@ asmlinkage long sys_unlink(const char __user * pathname) if(IS_ERR(name)) return PTR_ERR(name); - error = path_lookup(name, LOOKUP_PARENT, &nd); + error = do_path_lookup(dfd, name, LOOKUP_PARENT, &nd); if (error) goto exit; error = -EISDIR; if (nd.last_type != LAST_NORM) goto exit1; - down(&nd.dentry->d_inode->i_sem); - dentry = lookup_hash(&nd.last, nd.dentry); + mutex_lock_nested(&nd.dentry->d_inode->i_mutex, I_MUTEX_PARENT); + dentry = lookup_hash(&nd); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { /* Why not before? Because we want correct error value */ @@ -1983,7 +2113,7 @@ asmlinkage long sys_unlink(const char __user * pathname) exit2: dput(dentry); } - up(&nd.dentry->d_inode->i_sem); + mutex_unlock(&nd.dentry->d_inode->i_mutex); if (inode) iput(inode); /* truncate the inode here */ exit1: @@ -1998,6 +2128,22 @@ slashes: goto exit2; } +asmlinkage long sys_unlinkat(int dfd, const char __user *pathname, int flag) +{ + if ((flag & ~AT_REMOVEDIR) != 0) + return -EINVAL; + + if (flag & AT_REMOVEDIR) + return do_rmdir(dfd, pathname); + + return do_unlinkat(dfd, pathname); +} + +asmlinkage long sys_unlink(const char __user *pathname) +{ + return do_unlinkat(AT_FDCWD, pathname); +} + int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname, int mode) { int error = may_create(dir, dentry, NULL); @@ -2015,11 +2161,12 @@ int vfs_symlink(struct inode *dir, struct dentry *dentry, const char *oldname, i DQUOT_INIT(dir); error = dir->i_op->symlink(dir, dentry, oldname); if (!error) - fsnotify_create(dir, dentry->d_name.name); + fsnotify_create(dir, dentry); return error; } -asmlinkage long sys_symlink(const char __user * oldname, const char __user * newname) +asmlinkage long sys_symlinkat(const char __user *oldname, + int newdfd, const char __user *newname) { int error = 0; char * from; @@ -2034,7 +2181,7 @@ asmlinkage long sys_symlink(const char __user * oldname, const char __user * new struct dentry *dentry; struct nameidata nd; - error = path_lookup(to, LOOKUP_PARENT, &nd); + error = do_path_lookup(newdfd, to, LOOKUP_PARENT, &nd); if (error) goto out; dentry = lookup_create(&nd, 0); @@ -2043,7 +2190,7 @@ asmlinkage long sys_symlink(const char __user * oldname, const char __user * new error = vfs_symlink(nd.dentry->d_inode, dentry, from, S_IALLUGO); dput(dentry); } - up(&nd.dentry->d_inode->i_sem); + mutex_unlock(&nd.dentry->d_inode->i_mutex); path_release(&nd); out: putname(to); @@ -2052,6 +2199,11 @@ out: return error; } +asmlinkage long sys_symlink(const char __user *oldname, const char __user *newname) +{ + return sys_symlinkat(oldname, AT_FDCWD, newname); +} + int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_dentry) { struct inode *inode = old_dentry->d_inode; @@ -2081,12 +2233,12 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de if (error) return error; - down(&old_dentry->d_inode->i_sem); + mutex_lock(&old_dentry->d_inode->i_mutex); DQUOT_INIT(dir); error = dir->i_op->link(old_dentry, dir, new_dentry); - up(&old_dentry->d_inode->i_sem); + mutex_unlock(&old_dentry->d_inode->i_mutex); if (!error) - fsnotify_create(dir, new_dentry->d_name.name); + fsnotify_create(dir, new_dentry); return error; } @@ -2099,21 +2251,28 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de * with linux 2.0, and to avoid hard-linking to directories * and other special files. --ADM */ -asmlinkage long sys_link(const char __user * oldname, const char __user * newname) +asmlinkage long sys_linkat(int olddfd, const char __user *oldname, + int newdfd, const char __user *newname, + int flags) { struct dentry *new_dentry; struct nameidata nd, old_nd; int error; char * to; + if ((flags & ~AT_SYMLINK_FOLLOW) != 0) + return -EINVAL; + to = getname(newname); if (IS_ERR(to)) return PTR_ERR(to); - error = __user_walk(oldname, 0, &old_nd); + error = __user_walk_fd(olddfd, oldname, + flags & AT_SYMLINK_FOLLOW ? LOOKUP_FOLLOW : 0, + &old_nd); if (error) goto exit; - error = path_lookup(to, LOOKUP_PARENT, &nd); + error = do_path_lookup(newdfd, to, LOOKUP_PARENT, &nd); if (error) goto out; error = -EXDEV; @@ -2125,7 +2284,7 @@ asmlinkage long sys_link(const char __user * oldname, const char __user * newnam error = vfs_link(old_nd.dentry, nd.dentry->d_inode, new_dentry); dput(new_dentry); } - up(&nd.dentry->d_inode->i_sem); + mutex_unlock(&nd.dentry->d_inode->i_mutex); out_release: path_release(&nd); out: @@ -2136,6 +2295,11 @@ exit: return error; } +asmlinkage long sys_link(const char __user *oldname, const char __user *newname) +{ + return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0); +} + /* * 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... @@ -2143,17 +2307,17 @@ exit: * a) we can get into loop creation. Check is done in is_subdir(). * b) race potential - two innocent renames can create a loop together. * That's where 4.4 screws up. Current fix: serialization on - * sb->s_vfs_rename_sem. We might be more accurate, but that's another + * sb->s_vfs_rename_mutex. We might be more accurate, but that's another * story. * c) we have to lock _three_ objects - parents and victim (if it exists). - * And that - after we got ->i_sem on parents (until then we don't know + * 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_sem _and_ that parent of the object we + * 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_sem. + * 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. @@ -2163,9 +2327,9 @@ exit: * stuff into VFS), but the former is not going away. Solution: the same * trick as in rmdir(). * e) conversion from fhandle to dentry may come in the wrong moment - when - * we are removing the target. Solution: we will have to grab ->i_sem + * 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_sem on parents, which works but leads to some truely excessive + * ->i_mutex on parents, which works but leads to some truely excessive * locking]. */ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry, @@ -2190,7 +2354,7 @@ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry, target = new_dentry->d_inode; if (target) { - down(&target->i_sem); + mutex_lock(&target->i_mutex); dentry_unhash(new_dentry); } if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry)) @@ -2200,7 +2364,7 @@ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry, if (target) { if (!error) target->i_flags |= S_DEAD; - up(&target->i_sem); + mutex_unlock(&target->i_mutex); if (d_unhashed(new_dentry)) d_rehash(new_dentry); dput(new_dentry); @@ -2223,7 +2387,7 @@ static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry, dget(new_dentry); target = new_dentry->d_inode; if (target) - down(&target->i_sem); + mutex_lock(&target->i_mutex); if (d_mountpoint(old_dentry)||d_mountpoint(new_dentry)) error = -EBUSY; else @@ -2234,7 +2398,7 @@ static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry, d_move(old_dentry, new_dentry); } if (target) - up(&target->i_sem); + mutex_unlock(&target->i_mutex); dput(new_dentry); return error; } @@ -2282,7 +2446,8 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, return error; } -static inline int do_rename(const char * oldname, const char * newname) +static int do_rename(int olddfd, const char *oldname, + int newdfd, const char *newname) { int error = 0; struct dentry * old_dir, * new_dir; @@ -2290,11 +2455,11 @@ static inline int do_rename(const char * oldname, const char * newname) struct dentry * trap; struct nameidata oldnd, newnd; - error = path_lookup(oldname, LOOKUP_PARENT, &oldnd); + error = do_path_lookup(olddfd, oldname, LOOKUP_PARENT, &oldnd); if (error) goto exit; - error = path_lookup(newname, LOOKUP_PARENT, &newnd); + error = do_path_lookup(newdfd, newname, LOOKUP_PARENT, &newnd); if (error) goto exit1; @@ -2313,7 +2478,7 @@ static inline int do_rename(const char * oldname, const char * newname) trap = lock_rename(new_dir, old_dir); - old_dentry = lookup_hash(&oldnd.last, old_dir); + old_dentry = lookup_hash(&oldnd); error = PTR_ERR(old_dentry); if (IS_ERR(old_dentry)) goto exit3; @@ -2333,7 +2498,7 @@ static inline int do_rename(const char * oldname, const char * newname) error = -EINVAL; if (old_dentry == trap) goto exit4; - new_dentry = lookup_hash(&newnd.last, new_dir); + new_dentry = lookup_hash(&newnd); error = PTR_ERR(new_dentry); if (IS_ERR(new_dentry)) goto exit4; @@ -2358,7 +2523,8 @@ exit: return error; } -asmlinkage long sys_rename(const char __user * oldname, const char __user * newname) +asmlinkage long sys_renameat(int olddfd, const char __user *oldname, + int newdfd, const char __user *newname) { int error; char * from; @@ -2370,13 +2536,18 @@ asmlinkage long sys_rename(const char __user * oldname, const char __user * newn to = getname(newname); error = PTR_ERR(to); if (!IS_ERR(to)) { - error = do_rename(from,to); + error = do_rename(olddfd, from, newdfd, to); putname(to); } putname(from); return error; } +asmlinkage long sys_rename(const char __user *oldname, const char __user *newname) +{ + return sys_renameat(AT_FDCWD, oldname, AT_FDCWD, newname); +} + int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen, const char *link) { int len; @@ -2425,8 +2596,7 @@ static char *page_getlink(struct dentry * dentry, struct page **ppage) { struct page * page; struct address_space *mapping = dentry->d_inode->i_mapping; - page = read_cache_page(mapping, 0, (filler_t *)mapping->a_ops->readpage, - NULL); + page = read_mapping_page(mapping, 0, NULL); if (IS_ERR(page)) goto sync_fail; wait_on_page_locked(page); @@ -2472,22 +2642,35 @@ void page_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie) } } -int page_symlink(struct inode *inode, const char *symname, int len) +int __page_symlink(struct inode *inode, const char *symname, int len, + gfp_t gfp_mask) { struct address_space *mapping = inode->i_mapping; - struct page *page = grab_cache_page(mapping, 0); + struct page *page; int err = -ENOMEM; char *kaddr; +retry: + page = find_or_create_page(mapping, 0, gfp_mask); if (!page) goto fail; err = mapping->a_ops->prepare_write(NULL, page, 0, len-1); + if (err == AOP_TRUNCATED_PAGE) { + page_cache_release(page); + goto retry; + } if (err) goto fail_map; kaddr = kmap_atomic(page, KM_USER0); memcpy(kaddr, symname, len-1); kunmap_atomic(kaddr, KM_USER0); - mapping->a_ops->commit_write(NULL, page, 0, len-1); + err = mapping->a_ops->commit_write(NULL, page, 0, len-1); + if (err == AOP_TRUNCATED_PAGE) { + page_cache_release(page); + goto retry; + } + if (err) + goto fail_map; /* * Notice that we are _not_ going to block here - end of page is * unmapped, so this will only try to map the rest of page, see @@ -2497,7 +2680,8 @@ int page_symlink(struct inode *inode, const char *symname, int len) */ if (!PageUptodate(page)) { err = mapping->a_ops->readpage(NULL, page); - wait_on_page_locked(page); + if (err != AOP_TRUNCATED_PAGE) + wait_on_page_locked(page); } else { unlock_page(page); } @@ -2513,6 +2697,12 @@ fail: return err; } +int page_symlink(struct inode *inode, const char *symname, int len) +{ + return __page_symlink(inode, symname, len, + mapping_gfp_mask(inode->i_mapping)); +} + struct inode_operations page_symlink_inode_operations = { .readlink = generic_readlink, .follow_link = page_follow_link_light, @@ -2520,22 +2710,25 @@ struct inode_operations page_symlink_inode_operations = { }; EXPORT_SYMBOL(__user_walk); +EXPORT_SYMBOL(__user_walk_fd); EXPORT_SYMBOL(follow_down); EXPORT_SYMBOL(follow_up); EXPORT_SYMBOL(get_write_access); /* binfmt_aout */ EXPORT_SYMBOL(getname); EXPORT_SYMBOL(lock_rename); -EXPORT_SYMBOL(lookup_hash); EXPORT_SYMBOL(lookup_one_len); EXPORT_SYMBOL(page_follow_link_light); EXPORT_SYMBOL(page_put_link); EXPORT_SYMBOL(page_readlink); +EXPORT_SYMBOL(__page_symlink); EXPORT_SYMBOL(page_symlink); EXPORT_SYMBOL(page_symlink_inode_operations); EXPORT_SYMBOL(path_lookup); EXPORT_SYMBOL(path_release); EXPORT_SYMBOL(path_walk); EXPORT_SYMBOL(permission); +EXPORT_SYMBOL(vfs_permission); +EXPORT_SYMBOL(file_permission); EXPORT_SYMBOL(unlock_rename); EXPORT_SYMBOL(vfs_create); EXPORT_SYMBOL(vfs_follow_link);