X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fnamei.c;h=e179f71bfcb058df613f83cb1ff923d47ffc4618;hb=4e5dbb3498e74514b9936d691413afc55fb84ea9;hp=c784e8bb57a35c6fa272ece7303095887ef65e8a;hpb=45c9b11a1d07770cabb48cb0f7960a77650ffc64;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/namei.c b/fs/namei.c index c784e8b..e179f71 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include @@ -31,7 +30,6 @@ #include #include #include -#include #include #include @@ -108,6 +106,8 @@ * any extra contention... */ +static int __link_path_walk(const char *name, struct nameidata *nd); + /* 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.. @@ -159,7 +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); @@ -228,6 +228,10 @@ int generic_permission(struct inode *inode, int mask, int permission(struct inode *inode, int mask, struct nameidata *nd) { int retval, submask; + struct vfsmount *mnt = NULL; + + if (nd) + mnt = nd->path.mnt; if (mask & MAY_WRITE) { umode_t mode = inode->i_mode; @@ -246,13 +250,34 @@ int permission(struct inode *inode, int mask, struct nameidata *nd) return -EACCES; } + if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode)) { + /* + * MAY_EXEC on regular files is denied if the fs is mounted + * with the "noexec" flag. + */ + if (mnt && (mnt->mnt_flags & MNT_NOEXEC)) + return -EACCES; + } /* Ordinary permission routines do not understand MAY_APPEND. */ submask = mask & ~MAY_APPEND; - if (inode->i_op && inode->i_op->permission) + if (inode->i_op && inode->i_op->permission) { retval = inode->i_op->permission(inode, submask, nd); - else + if (!retval) { + /* + * Exec permission on a regular file is denied if none + * of the execute bits are set. + * + * This check should be done by the ->permission() + * method. + */ + if ((mask & MAY_EXEC) && S_ISREG(inode->i_mode) && + !(inode->i_mode & S_IXUGO)) + return -EACCES; + } + } else { retval = generic_permission(inode, submask, NULL); + } if (retval) return retval; @@ -271,7 +296,7 @@ int permission(struct inode *inode, int mask, struct nameidata *nd) */ int vfs_permission(struct nameidata *nd, int mask) { - return permission(nd->dentry->d_inode, mask, nd); + return permission(nd->path.dentry->d_inode, mask, nd); } /** @@ -288,7 +313,7 @@ int vfs_permission(struct nameidata *nd, int mask) */ int file_permission(struct file *file, int mask) { - return permission(file->f_dentry->d_inode, mask, NULL); + return permission(file->f_path.dentry->d_inode, mask, NULL); } /* @@ -324,7 +349,7 @@ int get_write_access(struct inode * inode) int deny_write_access(struct file * file) { - struct inode *inode = file->f_dentry->d_inode; + struct inode *inode = file->f_path.dentry->d_inode; spin_lock(&inode->i_lock); if (atomic_read(&inode->i_writecount) > 0) { @@ -337,21 +362,31 @@ int deny_write_access(struct file * file) return 0; } -void path_release(struct nameidata *nd) +/** + * 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(struct path *path) { - dput(nd->dentry); - mntput(nd->mnt); + mntget(path->mnt); + dget(path->dentry); } +EXPORT_SYMBOL(path_get); -/* - * umount() mustn't call path_release()/mntput() as that would clear - * mnt_expiry_mark +/** + * 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_release_on_umount(struct nameidata *nd) +void path_put(struct path *path) { - dput(nd->dentry); - mntput_no_expire(nd->mnt); + dput(path->dentry); + mntput(path->mnt); } +EXPORT_SYMBOL(path_put); /** * release_open_intent - free up open intent resources @@ -359,12 +394,36 @@ void path_release_on_umount(struct nameidata *nd) */ void release_open_intent(struct nameidata *nd) { - if (nd->intent.open.file->f_dentry == NULL) + if (nd->intent.open.file->f_path.dentry == NULL) put_filp(nd->intent.open.file); else fput(nd->intent.open.file); } +static inline struct dentry * +do_revalidate(struct dentry *dentry, struct nameidata *nd) +{ + int status = dentry->d_op->d_revalidate(dentry, nd); + if (unlikely(status <= 0)) { + /* + * The dentry failed validation. + * If d_revalidate returned 0 attempt to invalidate + * the dentry otherwise d_revalidate is asking us + * to return a fail status. + */ + if (!status) { + if (!d_invalidate(dentry)) { + dput(dentry); + dentry = NULL; + } + } else { + dput(dentry); + dentry = ERR_PTR(status); + } + } + return dentry; +} + /* * Internal lookup() using the new generic dcache. * SMP-safe @@ -379,12 +438,9 @@ static struct dentry * cached_lookup(struct dentry * parent, struct qstr * name, if (!dentry) dentry = d_lookup(parent, name); - if (dentry && dentry->d_op && dentry->d_op->d_revalidate) { - if (!dentry->d_op->d_revalidate(dentry, nd) && !d_invalidate(dentry)) { - dput(dentry); - dentry = NULL; - } - } + if (dentry && dentry->d_op && dentry->d_op->d_revalidate) + dentry = do_revalidate(dentry, nd); + return dentry; } @@ -477,10 +533,9 @@ static struct dentry * real_lookup(struct dentry * parent, struct qstr * name, s */ 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); + result = do_revalidate(result, nd); + if (!result) result = ERR_PTR(-ENOENT); - } } return result; } @@ -491,21 +546,54 @@ static int __emul_lookup_dentry(const char *, struct nameidata *); static __always_inline int walk_init_root(const char *name, struct nameidata *nd) { - 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); - read_unlock(¤t->fs->lock); + struct fs_struct *fs = current->fs; + + read_lock(&fs->lock); + if (fs->altroot.dentry && !(nd->flags & LOOKUP_NOALT)) { + nd->path = fs->altroot; + path_get(&fs->altroot); + read_unlock(&fs->lock); if (__emul_lookup_dentry(name,nd)) return 0; - read_lock(¤t->fs->lock); + read_lock(&fs->lock); } - nd->mnt = mntget(current->fs->rootmnt); - nd->dentry = dget(current->fs->root); - read_unlock(¤t->fs->lock); + nd->path = fs->root; + path_get(&fs->root); + read_unlock(&fs->lock); return 1; } +/* + * Wrapper to retry pathname resolution whenever the underlying + * file system returns an ESTALE. + * + * Retry the whole path once, forcing real lookup requests + * instead of relying on the dcache. + */ +static __always_inline int link_path_walk(const char *name, struct nameidata *nd) +{ + struct path save = nd->path; + int result; + + /* make sure the stuff we saved doesn't go away */ + dget(save.dentry); + mntget(save.mnt); + + result = __link_path_walk(name, nd); + if (result == -ESTALE) { + /* nd->path had been dropped */ + nd->path = save; + dget(nd->path.dentry); + mntget(nd->path.mnt); + nd->flags |= LOOKUP_REVAL; + result = __link_path_walk(name, nd); + } + + path_put(&save); + + return result; +} + static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *link) { int res = 0; @@ -514,7 +602,7 @@ static __always_inline int __vfs_follow_link(struct nameidata *nd, const char *l goto fail; if (*link == '/') { - path_release(nd); + path_put(&nd->path); if (!walk_init_root(link, nd)) /* weird __emul_prefix() stuff did it */ goto out; @@ -530,36 +618,31 @@ out: */ name = __getname(); if (unlikely(!name)) { - path_release(nd); + path_put(&nd->path); return -ENOMEM; } strcpy(name, nd->last.name); nd->last.name = name; return 0; fail: - path_release(nd); + path_put(&nd->path); return PTR_ERR(link); } -struct path { - struct vfsmount *mnt; - struct dentry *dentry; -}; - -static inline void dput_path(struct path *path, struct nameidata *nd) +static void path_put_conditional(struct path *path, struct nameidata *nd) { dput(path->dentry); - if (path->mnt != nd->mnt) + if (path->mnt != nd->path.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; + dput(nd->path.dentry); + if (nd->path.mnt != path->mnt) + mntput(nd->path.mnt); + nd->path.mnt = path->mnt; + nd->path.dentry = path->dentry; } static __always_inline int __do_follow_link(struct path *path, struct nameidata *nd) @@ -571,7 +654,7 @@ static __always_inline int __do_follow_link(struct path *path, struct nameidata touch_atime(path->mnt, dentry); nd_set_link(nd, NULL); - if (path->mnt != nd->mnt) { + if (path->mnt != nd->path.mnt) { path_to_nameidata(path, nd); dget(dentry); } @@ -586,8 +669,7 @@ static __always_inline int __do_follow_link(struct path *path, struct nameidata if (dentry->d_inode->i_op->put_link) dentry->d_inode->i_op->put_link(dentry, nd, cookie); } - dput(dentry); - mntput(path->mnt); + path_put(path); return error; } @@ -619,8 +701,8 @@ static inline int do_follow_link(struct path *path, struct nameidata *nd) nd->depth--; return err; loop: - dput_path(path, nd); - path_release(nd); + path_put_conditional(path, nd); + path_put(&nd->path); return err; } @@ -697,39 +779,41 @@ int follow_down(struct vfsmount **mnt, struct dentry **dentry) static __always_inline void follow_dotdot(struct nameidata *nd) { + struct fs_struct *fs = current->fs; + while(1) { struct vfsmount *parent; - struct dentry *old = nd->dentry; + struct dentry *old = nd->path.dentry; - read_lock(¤t->fs->lock); - if (nd->dentry == current->fs->root && - nd->mnt == current->fs->rootmnt) { - read_unlock(¤t->fs->lock); + read_lock(&fs->lock); + if (nd->path.dentry == fs->root.dentry && + nd->path.mnt == fs->root.mnt) { + read_unlock(&fs->lock); break; } - read_unlock(¤t->fs->lock); + read_unlock(&fs->lock); spin_lock(&dcache_lock); - if (nd->dentry != nd->mnt->mnt_root) { - nd->dentry = dget(nd->dentry->d_parent); + if (nd->path.dentry != nd->path.mnt->mnt_root) { + nd->path.dentry = dget(nd->path.dentry->d_parent); spin_unlock(&dcache_lock); dput(old); break; } spin_unlock(&dcache_lock); spin_lock(&vfsmount_lock); - parent = nd->mnt->mnt_parent; - if (parent == nd->mnt) { + parent = nd->path.mnt->mnt_parent; + if (parent == nd->path.mnt) { spin_unlock(&vfsmount_lock); break; } mntget(parent); - nd->dentry = dget(nd->mnt->mnt_mountpoint); + nd->path.dentry = dget(nd->path.mnt->mnt_mountpoint); spin_unlock(&vfsmount_lock); dput(old); - mntput(nd->mnt); - nd->mnt = parent; + mntput(nd->path.mnt); + nd->path.mnt = parent; } - follow_mount(&nd->mnt, &nd->dentry); + follow_mount(&nd->path.mnt, &nd->path.dentry); } /* @@ -740,8 +824,8 @@ static __always_inline void follow_dotdot(struct nameidata *nd) static int do_lookup(struct nameidata *nd, struct qstr *name, struct path *path) { - struct vfsmount *mnt = nd->mnt; - struct dentry *dentry = __d_lookup(nd->dentry, name); + struct vfsmount *mnt = nd->path.mnt; + struct dentry *dentry = __d_lookup(nd->path.dentry, name); if (!dentry) goto need_lookup; @@ -754,18 +838,18 @@ done: return 0; need_lookup: - dentry = real_lookup(nd->dentry, name, nd); + dentry = real_lookup(nd->path.dentry, name, nd); if (IS_ERR(dentry)) goto fail; goto done; need_revalidate: - if (dentry->d_op->d_revalidate(dentry, nd)) - goto done; - if (d_invalidate(dentry)) - goto done; - dput(dentry); - goto need_lookup; + dentry = do_revalidate(dentry, nd); + if (!dentry) + goto need_lookup; + if (IS_ERR(dentry)) + goto fail; + goto done; fail: return PTR_ERR(dentry); @@ -779,7 +863,7 @@ fail: * Returns 0 and nd will have valid dentry and mnt on success. * Returns error and drops reference to input namei data on failure. */ -static fastcall int __link_path_walk(const char * name, struct nameidata *nd) +static int __link_path_walk(const char *name, struct nameidata *nd) { struct path next; struct inode *inode; @@ -791,7 +875,7 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd) if (!*name) goto return_reval; - inode = nd->dentry->d_inode; + inode = nd->path.dentry->d_inode; if (nd->depth) lookup_flags = LOOKUP_FOLLOW | (nd->flags & LOOKUP_CONTINUE); @@ -839,7 +923,7 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd) if (this.name[1] != '.') break; follow_dotdot(nd); - inode = nd->dentry->d_inode; + inode = nd->path.dentry->d_inode; /* fallthrough */ case 1: continue; @@ -848,8 +932,9 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd) * See if the low-level filesystem might want * to use its own hash.. */ - if (nd->dentry->d_op && nd->dentry->d_op->d_hash) { - err = nd->dentry->d_op->d_hash(nd->dentry, &this); + if (nd->path.dentry->d_op && nd->path.dentry->d_op->d_hash) { + err = nd->path.dentry->d_op->d_hash(nd->path.dentry, + &this); if (err < 0) break; } @@ -871,7 +956,7 @@ static fastcall int __link_path_walk(const char * name, struct nameidata *nd) if (err) goto return_err; err = -ENOENT; - inode = nd->dentry->d_inode; + inode = nd->path.dentry->d_inode; if (!inode) break; err = -ENOTDIR; @@ -899,13 +984,14 @@ last_component: if (this.name[1] != '.') break; follow_dotdot(nd); - inode = nd->dentry->d_inode; + inode = nd->path.dentry->d_inode; /* fallthrough */ case 1: goto return_reval; } - if (nd->dentry->d_op && nd->dentry->d_op->d_hash) { - err = nd->dentry->d_op->d_hash(nd->dentry, &this); + if (nd->path.dentry->d_op && nd->path.dentry->d_op->d_hash) { + err = nd->path.dentry->d_op->d_hash(nd->path.dentry, + &this); if (err < 0) break; } @@ -918,7 +1004,7 @@ last_component: err = do_follow_link(&next, nd); if (err) goto return_err; - inode = nd->dentry->d_inode; + inode = nd->path.dentry->d_inode; } else path_to_nameidata(&next, nd); err = -ENOENT; @@ -946,56 +1032,26 @@ return_reval: * We bypassed the ordinary revalidation routines. * We may need to check the cached dentry for staleness. */ - if (nd->dentry && nd->dentry->d_sb && - (nd->dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)) { + if (nd->path.dentry && nd->path.dentry->d_sb && + (nd->path.dentry->d_sb->s_type->fs_flags & FS_REVAL_DOT)) { err = -ESTALE; /* Note: we do not d_invalidate() */ - if (!nd->dentry->d_op->d_revalidate(nd->dentry, nd)) + if (!nd->path.dentry->d_op->d_revalidate( + nd->path.dentry, nd)) break; } return_base: return 0; out_dput: - dput_path(&next, nd); + path_put_conditional(&next, nd); break; } - path_release(nd); + path_put(&nd->path); return_err: return err; } -/* - * Wrapper to retry pathname resolution whenever the underlying - * file system returns an ESTALE. - * - * Retry the whole path once, forcing real lookup requests - * instead of relying on the dcache. - */ -int fastcall link_path_walk(const char *name, struct nameidata *nd) -{ - struct nameidata save = *nd; - int result; - - /* make sure the stuff we saved doesn't go away */ - dget(save.dentry); - mntget(save.mnt); - - result = __link_path_walk(name, nd); - if (result == -ESTALE) { - *nd = save; - dget(nd->dentry); - mntget(nd->mnt); - nd->flags |= LOOKUP_REVAL; - result = __link_path_walk(name, nd); - } - - dput(save.dentry); - mntput(save.mnt); - - return result; -} - -int fastcall path_walk(const char * name, struct nameidata *nd) +static int path_walk(const char *name, struct nameidata *nd) { current->total_link_count = 0; return link_path_walk(name, nd); @@ -1010,30 +1066,30 @@ static int __emul_lookup_dentry(const char *name, struct nameidata *nd) if (path_walk(name, nd)) return 0; /* something went wrong... */ - if (!nd->dentry->d_inode || S_ISDIR(nd->dentry->d_inode->i_mode)) { - struct dentry *old_dentry = nd->dentry; - struct vfsmount *old_mnt = nd->mnt; + if (!nd->path.dentry->d_inode || + S_ISDIR(nd->path.dentry->d_inode->i_mode)) { + struct path old_path = nd->path; struct qstr last = nd->last; int last_type = nd->last_type; + struct fs_struct *fs = current->fs; + /* - * NAME was not found in alternate root or it's a directory. Try to find - * it in the normal root: + * NAME was not found in alternate root or it's a directory. + * Try to find it in the normal root: */ nd->last_type = LAST_ROOT; - read_lock(¤t->fs->lock); - nd->mnt = mntget(current->fs->rootmnt); - nd->dentry = dget(current->fs->root); - read_unlock(¤t->fs->lock); + read_lock(&fs->lock); + nd->path = fs->root; + path_get(&fs->root); + read_unlock(&fs->lock); if (path_walk(name, nd) == 0) { - if (nd->dentry->d_inode) { - dput(old_dentry); - mntput(old_mnt); + if (nd->path.dentry->d_inode) { + path_put(&old_path); return 1; } - path_release(nd); + path_put(&nd->path); } - nd->dentry = old_dentry; - nd->mnt = old_mnt; + nd->path = old_path; nd->last = last; nd->last_type = last_type; } @@ -1044,60 +1100,55 @@ void set_fs_altroot(void) { char *emul = __emul_prefix(); struct nameidata nd; - struct vfsmount *mnt = NULL, *oldmnt; - struct dentry *dentry = NULL, *olddentry; + struct path path = {}, old_path; int err; + struct fs_struct *fs = current->fs; if (!emul) goto set_it; err = path_lookup(emul, LOOKUP_FOLLOW|LOOKUP_DIRECTORY|LOOKUP_NOALT, &nd); - if (!err) { - mnt = nd.mnt; - dentry = nd.dentry; - } + if (!err) + path = nd.path; set_it: - write_lock(¤t->fs->lock); - oldmnt = current->fs->altrootmnt; - olddentry = current->fs->altroot; - current->fs->altrootmnt = mnt; - current->fs->altroot = dentry; - write_unlock(¤t->fs->lock); - if (olddentry) { - dput(olddentry); - mntput(oldmnt); - } + write_lock(&fs->lock); + old_path = fs->altroot; + fs->altroot = path; + write_unlock(&fs->lock); + if (old_path.dentry) + path_put(&old_path); } /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */ -static int fastcall do_path_lookup(int dfd, const char *name, +static int do_path_lookup(int dfd, const char *name, unsigned int flags, struct nameidata *nd) { int retval = 0; int fput_needed; struct file *file; + struct fs_struct *fs = current->fs; nd->last_type = LAST_ROOT; /* if there are only slashes... */ nd->flags = flags; nd->depth = 0; 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); - read_unlock(¤t->fs->lock); + read_lock(&fs->lock); + if (fs->altroot.dentry && !(nd->flags & LOOKUP_NOALT)) { + nd->path = fs->altroot; + path_get(&fs->altroot); + read_unlock(&fs->lock); if (__emul_lookup_dentry(name,nd)) goto out; /* found in altroot */ - read_lock(¤t->fs->lock); + read_lock(&fs->lock); } - nd->mnt = mntget(current->fs->rootmnt); - nd->dentry = dget(current->fs->root); - read_unlock(¤t->fs->lock); + nd->path = fs->root; + path_get(&fs->root); + read_unlock(&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); + read_lock(&fs->lock); + nd->path = fs->pwd; + path_get(&fs->pwd); + read_unlock(&fs->lock); } else { struct dentry *dentry; @@ -1106,7 +1157,7 @@ static int fastcall do_path_lookup(int dfd, const char *name, if (!file) goto out_fail; - dentry = file->f_dentry; + dentry = file->f_path.dentry; retval = -ENOTDIR; if (!S_ISDIR(dentry->d_inode->i_mode)) @@ -1116,19 +1167,17 @@ static int fastcall do_path_lookup(int dfd, const char *name, if (retval) goto fput_fail; - nd->mnt = mntget(file->f_vfsmnt); - nd->dentry = dget(dentry); + nd->path = file->f_path; + path_get(&file->f_path); fput_light(file, fput_needed); } - current->total_link_count = 0; - retval = link_path_walk(name, nd); + + retval = path_walk(name, nd); out: - if (likely(retval == 0)) { - if (unlikely(current->audit_context && nd && nd->dentry && - nd->dentry->d_inode)) - audit_inode(name, nd->dentry->d_inode); - } + if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry && + nd->path.dentry->d_inode)) + audit_inode(name, nd->path.dentry); out_fail: return retval; @@ -1137,12 +1186,43 @@ fput_fail: goto out_fail; } -int fastcall path_lookup(const char *name, unsigned int flags, +int path_lookup(const char *name, unsigned int flags, struct nameidata *nd) { return do_path_lookup(AT_FDCWD, name, flags, nd); } +/** + * 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 + * @nd: pointer to nameidata + */ +int vfs_path_lookup(struct dentry *dentry, struct vfsmount *mnt, + const char *name, unsigned int flags, + struct nameidata *nd) +{ + int retval; + + /* same as do_path_lookup */ + nd->last_type = LAST_ROOT; + nd->flags = flags; + nd->depth = 0; + + nd->path.mnt = mntget(mnt); + nd->path.dentry = dget(dentry); + + retval = path_walk(name, nd); + if (unlikely(!retval && !audit_dummy_context() && nd->path.dentry && + nd->path.dentry->d_inode)) + audit_inode(name, nd->path.dentry); + + return retval; + +} + static int __path_lookup_intent_open(int dfd, const char *name, unsigned int lookup_flags, struct nameidata *nd, int open_flags, int create_mode) @@ -1159,7 +1239,7 @@ static int __path_lookup_intent_open(int dfd, const char *name, if (IS_ERR(nd->intent.open.file)) { if (err == 0) { err = PTR_ERR(nd->intent.open.file); - path_release(nd); + path_put(&nd->path); } } else if (err != 0) release_open_intent(nd); @@ -1211,22 +1291,14 @@ int __user_path_lookup_open(const char __user *name, unsigned int lookup_flags, return err; } -/* - * Restricted form of lookup. Doesn't follow links, single-component only, - * needs parent already locked. Doesn't follow mounts. - * SMP-safe. - */ -static struct dentry * __lookup_hash(struct qstr *name, struct dentry * base, struct nameidata *nd) +static struct dentry *__lookup_hash(struct qstr *name, + struct dentry *base, struct nameidata *nd) { - struct dentry * dentry; + struct dentry *dentry; struct inode *inode; int err; inode = base->d_inode; - err = permission(inode, MAY_EXEC, nd); - dentry = ERR_PTR(err); - if (err) - goto out; /* * See if the low-level filesystem might want @@ -1255,49 +1327,92 @@ out: return dentry; } +/* + * Restricted form of lookup. Doesn't follow links, single-component only, + * needs parent already locked. Doesn't follow mounts. + * SMP-safe. + */ static struct dentry *lookup_hash(struct nameidata *nd) { - return __lookup_hash(&nd->last, nd->dentry, nd); + int err; + + err = permission(nd->path.dentry->d_inode, MAY_EXEC, nd); + if (err) + return ERR_PTR(err); + return __lookup_hash(&nd->last, nd->path.dentry, nd); } -/* SMP-safe */ -struct dentry * lookup_one_len(const char * name, struct dentry * base, int len) +static int __lookup_one_len(const char *name, struct qstr *this, + struct dentry *base, int len) { unsigned long hash; - struct qstr this; unsigned int c; - this.name = name; - this.len = len; + this->name = name; + this->len = len; if (!len) - goto access; + return -EACCES; hash = init_name_hash(); while (len--) { c = *(const unsigned char *)name++; if (c == '/' || c == '\0') - goto access; + return -EACCES; hash = partial_name_hash(c, hash); } - this.hash = end_name_hash(hash); + this->hash = end_name_hash(hash); + return 0; +} + +/** + * 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. Also note that by using this function the + * nameidata argument is passed to the filesystem methods and a filesystem + * using this helper needs to be prepared for that. + */ +struct dentry *lookup_one_len(const char *name, struct dentry *base, int len) +{ + int err; + struct qstr this; + + err = __lookup_one_len(name, &this, base, len); + if (err) + return ERR_PTR(err); + err = permission(base->d_inode, MAY_EXEC, NULL); + if (err) + return ERR_PTR(err); return __lookup_hash(&this, base, NULL); -access: - return ERR_PTR(-EACCES); } -/* - * namei() +/** + * lookup_one_noperm - bad hack for sysfs + * @name: pathname component to lookup + * @base: base directory to lookup from * - * is used by most simple commands to get the inode of a specified name. - * Open, link etc use their own routines, but this is enough for things - * like 'chmod' etc. + * This is a variant of lookup_one_len that doesn't perform any permission + * checks. It's a horrible hack to work around the braindead sysfs + * architecture and should not be used anywhere else. * - * namei exists in two versions: namei/lnamei. The only difference is - * that namei follows links, while lnamei does not. - * SMP-safe + * DON'T USE THIS FUNCTION EVER, thanks. */ -int fastcall __user_walk_fd(int dfd, const char __user *name, unsigned flags, +struct dentry *lookup_one_noperm(const char *name, struct dentry *base) +{ + int err; + struct qstr this; + + err = __lookup_one_len(name, &this, base, strlen(name)); + if (err) + return ERR_PTR(err); + return __lookup_hash(&this, base, NULL); +} + +int __user_walk_fd(int dfd, const char __user *name, unsigned flags, struct nameidata *nd) { char *tmp = getname(name); @@ -1310,7 +1425,7 @@ int fastcall __user_walk_fd(int dfd, const char __user *name, unsigned flags, return err; } -int fastcall __user_walk(const char __user *name, unsigned flags, struct nameidata *nd) +int __user_walk(const char __user *name, unsigned flags, struct nameidata *nd) { return __user_walk_fd(AT_FDCWD, name, flags, nd); } @@ -1357,7 +1472,7 @@ static 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->i_ino); + audit_inode_child(victim->d_name.name, victim, dir); error = permission(dir,MAY_WRITE | MAY_EXEC, NULL); if (error) @@ -1423,7 +1538,7 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) struct dentry *p; if (p1 == p2) { - mutex_lock(&p1->d_inode->i_mutex); + mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT); return NULL; } @@ -1431,22 +1546,22 @@ struct dentry *lock_rename(struct dentry *p1, struct dentry *p2) for (p = p1; p->d_parent != p; p = p->d_parent) { if (p->d_parent == p2) { - mutex_lock(&p2->d_inode->i_mutex); - mutex_lock(&p1->d_inode->i_mutex); + 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) { - mutex_lock(&p1->d_inode->i_mutex); - mutex_lock(&p2->d_inode->i_mutex); + mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD); return p; } } - mutex_lock(&p1->d_inode->i_mutex); - mutex_lock(&p2->d_inode->i_mutex); + mutex_lock_nested(&p1->d_inode->i_mutex, I_MUTEX_PARENT); + mutex_lock_nested(&p2->d_inode->i_mutex, I_MUTEX_CHILD); return NULL; } @@ -1483,7 +1598,7 @@ int vfs_create(struct inode *dir, struct dentry *dentry, int mode, int may_open(struct nameidata *nd, int acc_mode, int flag) { - struct dentry *dentry = nd->dentry; + struct dentry *dentry = nd->path.dentry; struct inode *inode = dentry->d_inode; int error; @@ -1493,13 +1608,9 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) if (S_ISLNK(inode->i_mode)) return -ELOOP; - if (S_ISDIR(inode->i_mode) && (flag & FMODE_WRITE)) + if (S_ISDIR(inode->i_mode) && (acc_mode & MAY_WRITE)) return -EISDIR; - error = vfs_permission(nd, acc_mode); - if (error) - return error; - /* * FIFO's, sockets and device files are special: they don't * actually live on the filesystem itself, and as such you @@ -1508,12 +1619,15 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) if (S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) { flag &= ~O_TRUNC; } else if (S_ISBLK(inode->i_mode) || S_ISCHR(inode->i_mode)) { - if (nd->mnt->mnt_flags & MNT_NODEV) + if (nd->path.mnt->mnt_flags & MNT_NODEV) return -EACCES; flag &= ~O_TRUNC; - } else if (IS_RDONLY(inode) && (flag & FMODE_WRITE)) - return -EROFS; + } + + error = vfs_permission(nd, acc_mode); + if (error) + return error; /* * An append-only file must be opened in append mode for writing. */ @@ -1526,7 +1640,7 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) /* O_NOATIME can only be set by the owner or superuser */ if (flag & O_NOATIME) - if (current->fsuid != inode->i_uid && !capable(CAP_FOWNER)) + if (!is_owner_or_cap(inode)) return -EPERM; /* @@ -1547,8 +1661,10 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) error = locks_verify_locked(inode); if (!error) { DQUOT_INIT(inode); - - error = do_truncate(dentry, 0, ATTR_MTIME|ATTR_CTIME, NULL); + + error = do_truncate(dentry, 0, + ATTR_MTIME|ATTR_CTIME|ATTR_OPEN, + NULL); } put_write_access(inode); if (error) @@ -1561,26 +1677,79 @@ int may_open(struct nameidata *nd, int acc_mode, int flag) } /* - * open_namei() - * - * namei for open - this is in fact almost the whole open-routine. + * Be careful about ever adding any more callers of this + * function. Its flags must be in the namei format, not + * what get passed to sys_open(). + */ +static int __open_namei_create(struct nameidata *nd, struct path *path, + int flag, int mode) +{ + int error; + struct dentry *dir = nd->path.dentry; + + if (!IS_POSIXACL(dir->d_inode)) + mode &= ~current->fs->umask; + error = vfs_create(dir->d_inode, path->dentry, mode, nd); + mutex_unlock(&dir->d_inode->i_mutex); + dput(nd->path.dentry); + nd->path.dentry = path->dentry; + if (error) + return error; + /* Don't check for write permission, don't truncate */ + return may_open(nd, 0, flag & ~O_TRUNC); +} + +/* + * Note that while the flag value (low two bits) for sys_open means: + * 00 - read-only + * 01 - write-only + * 10 - read-write + * 11 - special + * it is changed into + * 00 - no permissions needed + * 01 - read-permission + * 10 - write-permission + * 11 - read-write + * for the internal routines (ie open_namei()/follow_link() etc) + * This is more logical, and also allows the 00 "no perm needed" + * to be used for symlinks (where the permissions are checked + * later). * - * Note that the low bits of "flag" aren't the same as in the open - * system call - they are 00 - no permissions needed - * 01 - read permission needed - * 10 - write permission needed - * 11 - read/write permissions needed - * which is a lot more logical, and also allows the "no perm" needed - * for symlinks (where the permissions are checked later). - * SMP-safe +*/ +static inline int open_to_namei_flags(int flag) +{ + if ((flag+1) & O_ACCMODE) + flag++; + return flag; +} + +static int open_will_write_to_fs(int flag, struct inode *inode) +{ + /* + * We'll never write to the fs underlying + * a device file. + */ + if (special_file(inode->i_mode)) + return 0; + return (flag & O_TRUNC); +} + +/* + * Note that the low bits of the passed in "open_flag" + * are not the same as in the local variable "flag". See + * open_to_namei_flags() for more details. */ -int open_namei(int dfd, const char *pathname, int flag, - int mode, struct nameidata *nd) +struct file *do_filp_open(int dfd, const char *pathname, + int open_flag, int mode) { + struct file *filp; + struct nameidata nd; int acc_mode, error; struct path path; struct dentry *dir; int count = 0; + int will_write; + int flag = open_to_namei_flags(open_flag); acc_mode = ACC_MODE(flag); @@ -1598,18 +1767,19 @@ int open_namei(int dfd, const char *pathname, int flag, */ if (!(flag & O_CREAT)) { error = path_lookup_open(dfd, pathname, lookup_flags(flag), - nd, flag); + &nd, flag); if (error) - return error; + return ERR_PTR(error); goto ok; } /* * Create - we need to know the parent. */ - error = path_lookup_create(dfd,pathname,LOOKUP_PARENT,nd,flag,mode); + error = path_lookup_create(dfd, pathname, LOOKUP_PARENT, + &nd, flag, mode); if (error) - return error; + return ERR_PTR(error); /* * We have the parent and last component. First of all, check @@ -1617,14 +1787,14 @@ int open_namei(int dfd, const char *pathname, int flag, * will not do. */ error = -EISDIR; - if (nd->last_type != LAST_NORM || nd->last.name[nd->last.len]) + if (nd.last_type != LAST_NORM || nd.last.name[nd.last.len]) goto exit; - dir = nd->dentry; - nd->flags &= ~LOOKUP_PARENT; + dir = nd.path.dentry; + nd.flags &= ~LOOKUP_PARENT; mutex_lock(&dir->d_inode->i_mutex); - path.dentry = lookup_hash(nd); - path.mnt = nd->mnt; + path.dentry = lookup_hash(&nd); + path.mnt = nd.path.mnt; do_last: error = PTR_ERR(path.dentry); @@ -1633,32 +1803,38 @@ do_last: 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; + if (IS_ERR(nd.intent.open.file)) { + error = PTR_ERR(nd.intent.open.file); + goto exit_mutex_unlock; } /* 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); - mutex_unlock(&dir->d_inode->i_mutex); - dput(nd->dentry); - nd->dentry = path.dentry; + /* + * This write is needed to ensure that a + * ro->rw transition does not occur between + * the time when the file is created and when + * a permanent write count is taken through + * the 'struct file' in nameidata_to_filp(). + */ + error = mnt_want_write(nd.path.mnt); if (error) + goto exit_mutex_unlock; + error = __open_namei_create(&nd, &path, flag, mode); + if (error) { + mnt_drop_write(nd.path.mnt); goto exit; - /* Don't check for write permission, don't truncate */ - acc_mode = 0; - flag &= ~O_TRUNC; - goto ok; + } + filp = nameidata_to_filp(&nd, open_flag); + mnt_drop_write(nd.path.mnt); + return filp; } /* * It already exists. */ mutex_unlock(&dir->d_inode->i_mutex); + audit_inode(pathname, path.dentry); error = -EEXIST; if (flag & O_EXCL) @@ -1669,29 +1845,59 @@ do_last: if (flag & O_NOFOLLOW) goto exit_dput; } + error = -ENOENT; if (!path.dentry->d_inode) goto exit_dput; if (path.dentry->d_inode->i_op && path.dentry->d_inode->i_op->follow_link) goto do_link; - path_to_nameidata(&path, nd); + path_to_nameidata(&path, &nd); error = -EISDIR; if (path.dentry->d_inode && S_ISDIR(path.dentry->d_inode->i_mode)) goto exit; ok: - error = may_open(nd, acc_mode, flag); - if (error) + /* + * Consider: + * 1. may_open() truncates a file + * 2. a rw->ro mount transition occurs + * 3. nameidata_to_filp() fails due to + * the ro mount. + * That would be inconsistent, and should + * be avoided. Taking this mnt write here + * ensures that (2) can not occur. + */ + will_write = open_will_write_to_fs(flag, nd.path.dentry->d_inode); + if (will_write) { + error = mnt_want_write(nd.path.mnt); + if (error) + goto exit; + } + error = may_open(&nd, acc_mode, flag); + if (error) { + if (will_write) + mnt_drop_write(nd.path.mnt); goto exit; - return 0; + } + filp = nameidata_to_filp(&nd, open_flag); + /* + * It is now safe to drop the mnt write + * because the filp has had a write taken + * on its behalf. + */ + if (will_write) + mnt_drop_write(nd.path.mnt); + return filp; +exit_mutex_unlock: + mutex_unlock(&dir->d_inode->i_mutex); exit_dput: - dput_path(&path, nd); + path_put_conditional(&path, &nd); exit: - if (!IS_ERR(nd->intent.open.file)) - release_open_intent(nd); - path_release(nd); - return error; + if (!IS_ERR(nd.intent.open.file)) + release_open_intent(&nd); + path_put(&nd.path); + return ERR_PTR(error); do_link: error = -ELOOP; @@ -1707,37 +1913,60 @@ do_link: * stored in nd->last.name and we will have to putname() it when we * are done. Procfs-like symlinks just set LAST_BIND. */ - nd->flags |= LOOKUP_PARENT; - error = security_inode_follow_link(path.dentry, nd); + nd.flags |= LOOKUP_PARENT; + error = security_inode_follow_link(path.dentry, &nd); if (error) goto exit_dput; - error = __do_follow_link(&path, nd); - if (error) - return error; - nd->flags &= ~LOOKUP_PARENT; - if (nd->last_type == LAST_BIND) + error = __do_follow_link(&path, &nd); + 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 ERR_PTR(error); + } + nd.flags &= ~LOOKUP_PARENT; + if (nd.last_type == LAST_BIND) goto ok; error = -EISDIR; - if (nd->last_type != LAST_NORM) + if (nd.last_type != LAST_NORM) goto exit; - if (nd->last.name[nd->last.len]) { - __putname(nd->last.name); + if (nd.last.name[nd.last.len]) { + __putname(nd.last.name); goto exit; } error = -ELOOP; if (count++==32) { - __putname(nd->last.name); + __putname(nd.last.name); goto exit; } - dir = nd->dentry; + dir = nd.path.dentry; mutex_lock(&dir->d_inode->i_mutex); - path.dentry = lookup_hash(nd); - path.mnt = nd->mnt; - __putname(nd->last.name); + path.dentry = lookup_hash(&nd); + path.mnt = nd.path.mnt; + __putname(nd.last.name); goto do_last; } /** + * filp_open - open file and return file pointer + * + * @filename: path to open + * @flags: open flags as per the open(2) second argument + * @mode: mode for the new file if O_CREAT is set, else ignored + * + * This is the helper to open a file from kernelspace if you really + * have to. But in generally you should not do this, so please move + * along, nothing to see here.. + */ +struct file *filp_open(const char *filename, int flags, int mode) +{ + return do_filp_open(AT_FDCWD, filename, flags, mode); +} +EXPORT_SYMBOL(filp_open); + +/** * lookup_create - lookup a dentry, creating it if it doesn't exist * @nd: nameidata info * @is_dir: directory flag @@ -1745,13 +1974,13 @@ 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_mutex locked. + * Returns with nd->path.dentry->d_inode->i_mutex locked. */ struct dentry *lookup_create(struct nameidata *nd, int is_dir) { struct dentry *dentry = ERR_PTR(-EEXIST); - mutex_lock(&nd->dentry->d_inode->i_mutex); + mutex_lock_nested(&nd->path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); /* * Yucky last component or no last component at all? * (foo/., foo/.., /////) @@ -1759,6 +1988,8 @@ 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. @@ -1808,6 +2039,23 @@ int vfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) return error; } +static int may_mknod(mode_t mode) +{ + switch (mode & S_IFMT) { + case S_IFREG: + case S_IFCHR: + case S_IFBLK: + case S_IFIFO: + case S_IFSOCK: + case 0: /* zero mode translates to S_IFREG */ + return 0; + case S_IFDIR: + return -EPERM; + default: + return -EINVAL; + } +} + asmlinkage long sys_mknodat(int dfd, const char __user *filename, int mode, unsigned dev) { @@ -1826,32 +2074,36 @@ asmlinkage long sys_mknodat(int dfd, const char __user *filename, int mode, if (error) goto out; dentry = lookup_create(&nd, 0); - error = PTR_ERR(dentry); - - if (!IS_POSIXACL(nd.dentry->d_inode)) + if (IS_ERR(dentry)) { + error = PTR_ERR(dentry); + goto out_unlock; + } + if (!IS_POSIXACL(nd.path.dentry->d_inode)) mode &= ~current->fs->umask; - if (!IS_ERR(dentry)) { - switch (mode & S_IFMT) { + error = may_mknod(mode); + if (error) + goto out_dput; + error = mnt_want_write(nd.path.mnt); + if (error) + goto out_dput; + switch (mode & S_IFMT) { case 0: case S_IFREG: - error = vfs_create(nd.dentry->d_inode,dentry,mode,&nd); + error = vfs_create(nd.path.dentry->d_inode,dentry,mode,&nd); break; case S_IFCHR: case S_IFBLK: - error = vfs_mknod(nd.dentry->d_inode,dentry,mode, + error = vfs_mknod(nd.path.dentry->d_inode,dentry,mode, new_decode_dev(dev)); break; case S_IFIFO: case S_IFSOCK: - error = vfs_mknod(nd.dentry->d_inode,dentry,mode,0); + error = vfs_mknod(nd.path.dentry->d_inode,dentry,mode,0); break; - case S_IFDIR: - error = -EPERM; - break; - default: - error = -EINVAL; - } - dput(dentry); } - mutex_unlock(&nd.dentry->d_inode->i_mutex); - path_release(&nd); + mnt_drop_write(nd.path.mnt); +out_dput: + dput(dentry); +out_unlock: + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + path_put(&nd.path); out: putname(tmp); @@ -1889,30 +2141,37 @@ asmlinkage long sys_mkdirat(int dfd, const char __user *pathname, int mode) { int error = 0; char * tmp; + struct dentry *dentry; + struct nameidata nd; tmp = getname(pathname); error = PTR_ERR(tmp); - if (!IS_ERR(tmp)) { - struct dentry *dentry; - struct nameidata nd; + if (IS_ERR(tmp)) + goto out_err; - error = do_path_lookup(dfd, tmp, LOOKUP_PARENT, &nd); - if (error) - goto out; - dentry = lookup_create(&nd, 1); - error = PTR_ERR(dentry); - if (!IS_ERR(dentry)) { - if (!IS_POSIXACL(nd.dentry->d_inode)) - mode &= ~current->fs->umask; - error = vfs_mkdir(nd.dentry->d_inode, dentry, mode); - dput(dentry); - } - mutex_unlock(&nd.dentry->d_inode->i_mutex); - path_release(&nd); -out: - putname(tmp); - } + error = do_path_lookup(dfd, tmp, LOOKUP_PARENT, &nd); + if (error) + goto out; + dentry = lookup_create(&nd, 1); + error = PTR_ERR(dentry); + if (IS_ERR(dentry)) + goto out_unlock; + if (!IS_POSIXACL(nd.path.dentry->d_inode)) + mode &= ~current->fs->umask; + error = mnt_want_write(nd.path.mnt); + if (error) + goto out_dput; + error = vfs_mkdir(nd.path.dentry->d_inode, dentry, mode); + mnt_drop_write(nd.path.mnt); +out_dput: + dput(dentry); +out_unlock: + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + path_put(&nd.path); +out: + putname(tmp); +out_err: return error; } @@ -1939,8 +2198,7 @@ asmlinkage long sys_mkdir(const char __user *pathname, int mode) void dentry_unhash(struct dentry *dentry) { dget(dentry); - if (atomic_read(&dentry->d_count)) - shrink_dcache_parent(dentry); + shrink_dcache_parent(dentry); spin_lock(&dcache_lock); spin_lock(&dentry->d_lock); if (atomic_read(&dentry->d_count) == 2) @@ -2008,16 +2266,22 @@ static long do_rmdir(int dfd, const char __user *pathname) error = -EBUSY; goto exit1; } - mutex_lock(&nd.dentry->d_inode->i_mutex); + mutex_lock_nested(&nd.path.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); - } - mutex_unlock(&nd.dentry->d_inode->i_mutex); + if (IS_ERR(dentry)) + goto exit2; + error = mnt_want_write(nd.path.mnt); + if (error) + goto exit3; + error = vfs_rmdir(nd.path.dentry->d_inode, dentry); + mnt_drop_write(nd.path.mnt); +exit3: + dput(dentry); +exit2: + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); exit1: - path_release(&nd); + path_put(&nd.path); exit: putname(name); return error; @@ -2052,6 +2316,7 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry) /* We don't d_delete() NFS sillyrenamed files--they still exist. */ if (!error && !(dentry->d_flags & DCACHE_NFSFS_RENAMED)) { + fsnotify_link_count(dentry->d_inode); d_delete(dentry); } @@ -2082,7 +2347,7 @@ static long do_unlinkat(int dfd, const char __user *pathname) error = -EISDIR; if (nd.last_type != LAST_NORM) goto exit1; - mutex_lock(&nd.dentry->d_inode->i_mutex); + mutex_lock_nested(&nd.path.dentry->d_inode->i_mutex, I_MUTEX_PARENT); dentry = lookup_hash(&nd); error = PTR_ERR(dentry); if (!IS_ERR(dentry)) { @@ -2092,15 +2357,19 @@ static long do_unlinkat(int dfd, const char __user *pathname) inode = dentry->d_inode; if (inode) atomic_inc(&inode->i_count); - error = vfs_unlink(nd.dentry->d_inode, dentry); + error = mnt_want_write(nd.path.mnt); + if (error) + goto exit2; + error = vfs_unlink(nd.path.dentry->d_inode, dentry); + mnt_drop_write(nd.path.mnt); exit2: dput(dentry); } - mutex_unlock(&nd.dentry->d_inode->i_mutex); + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); if (inode) iput(inode); /* truncate the inode here */ exit1: - path_release(&nd); + path_put(&nd.path); exit: putname(name); return error; @@ -2154,30 +2423,38 @@ asmlinkage long sys_symlinkat(const char __user *oldname, int error = 0; char * from; char * to; + struct dentry *dentry; + struct nameidata nd; from = getname(oldname); if(IS_ERR(from)) return PTR_ERR(from); to = getname(newname); error = PTR_ERR(to); - if (!IS_ERR(to)) { - struct dentry *dentry; - struct nameidata nd; + if (IS_ERR(to)) + goto out_putname; - error = do_path_lookup(newdfd, to, LOOKUP_PARENT, &nd); - if (error) - goto out; - dentry = lookup_create(&nd, 0); - error = PTR_ERR(dentry); - if (!IS_ERR(dentry)) { - error = vfs_symlink(nd.dentry->d_inode, dentry, from, S_IALLUGO); - dput(dentry); - } - mutex_unlock(&nd.dentry->d_inode->i_mutex); - path_release(&nd); + error = do_path_lookup(newdfd, to, LOOKUP_PARENT, &nd); + if (error) + goto out; + dentry = lookup_create(&nd, 0); + error = PTR_ERR(dentry); + if (IS_ERR(dentry)) + goto out_unlock; + + error = mnt_want_write(nd.path.mnt); + if (error) + goto out_dput; + error = vfs_symlink(nd.path.dentry->d_inode, dentry, from, S_IALLUGO); + mnt_drop_write(nd.path.mnt); +out_dput: + dput(dentry); +out_unlock: + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); + path_put(&nd.path); out: - putname(to); - } + putname(to); +out_putname: putname(from); return error; } @@ -2221,7 +2498,7 @@ int vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *new_de error = dir->i_op->link(old_dentry, dir, new_dentry); mutex_unlock(&old_dentry->d_inode->i_mutex); if (!error) - fsnotify_create(dir, new_dentry); + fsnotify_link(dir, old_dentry->d_inode, new_dentry); return error; } @@ -2259,19 +2536,25 @@ asmlinkage long sys_linkat(int olddfd, const char __user *oldname, if (error) goto out; error = -EXDEV; - if (old_nd.mnt != nd.mnt) + if (old_nd.path.mnt != nd.path.mnt) goto out_release; new_dentry = lookup_create(&nd, 0); error = PTR_ERR(new_dentry); - if (!IS_ERR(new_dentry)) { - error = vfs_link(old_nd.dentry, nd.dentry->d_inode, new_dentry); - dput(new_dentry); - } - mutex_unlock(&nd.dentry->d_inode->i_mutex); + if (IS_ERR(new_dentry)) + goto out_unlock; + error = mnt_want_write(nd.path.mnt); + if (error) + goto out_dput; + error = vfs_link(old_nd.path.dentry, nd.path.dentry->d_inode, new_dentry); + mnt_drop_write(nd.path.mnt); +out_dput: + dput(new_dentry); +out_unlock: + mutex_unlock(&nd.path.dentry->d_inode->i_mutex); out_release: - path_release(&nd); + path_put(&nd.path); out: - path_release(&old_nd); + path_put(&old_nd.path); exit: putname(to); @@ -2353,7 +2636,8 @@ static int vfs_rename_dir(struct inode *old_dir, struct dentry *old_dentry, dput(new_dentry); } if (!error) - d_move(old_dentry,new_dentry); + if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) + d_move(old_dentry,new_dentry); return error; } @@ -2376,8 +2660,7 @@ static int vfs_rename_other(struct inode *old_dir, struct dentry *old_dentry, else error = old_dir->i_op->rename(old_dir, old_dentry, new_dir, new_dentry); if (!error) { - /* The following d_move() should become unconditional */ - if (!(old_dir->i_sb->s_type->fs_flags & FS_ODD_RENAME)) + if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) d_move(old_dentry, new_dentry); } if (target) @@ -2422,7 +2705,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (!error) { const char *new_name = old_dentry->d_name.name; fsnotify_move(old_dir, new_dir, old_name, new_name, is_dir, - new_dentry->d_inode, old_dentry->d_inode); + new_dentry->d_inode, old_dentry); } fsnotify_oldname_free(old_name); @@ -2447,15 +2730,15 @@ static int do_rename(int olddfd, const char *oldname, goto exit1; error = -EXDEV; - if (oldnd.mnt != newnd.mnt) + if (oldnd.path.mnt != newnd.path.mnt) goto exit2; - old_dir = oldnd.dentry; + old_dir = oldnd.path.dentry; error = -EBUSY; if (oldnd.last_type != LAST_NORM) goto exit2; - new_dir = newnd.dentry; + new_dir = newnd.path.dentry; if (newnd.last_type != LAST_NORM) goto exit2; @@ -2490,8 +2773,12 @@ static int do_rename(int olddfd, const char *oldname, if (new_dentry == trap) goto exit5; + error = mnt_want_write(oldnd.path.mnt); + if (error) + goto exit5; error = vfs_rename(old_dir->d_inode, old_dentry, new_dir->d_inode, new_dentry); + mnt_drop_write(oldnd.path.mnt); exit5: dput(new_dentry); exit4: @@ -2499,9 +2786,9 @@ exit4: exit3: unlock_rename(new_dir, old_dir); exit2: - path_release(&newnd); + path_put(&newnd.path); exit1: - path_release(&oldnd); + path_put(&oldnd.path); exit: return error; } @@ -2581,19 +2868,9 @@ static char *page_getlink(struct dentry * dentry, struct page **ppage) struct address_space *mapping = dentry->d_inode->i_mapping; page = read_mapping_page(mapping, 0, NULL); if (IS_ERR(page)) - goto sync_fail; - wait_on_page_locked(page); - if (!PageUptodate(page)) - goto async_fail; + return (char*)page; *ppage = page; return kmap(page); - -async_fail: - page_cache_release(page); - return ERR_PTR(-EIO); - -sync_fail: - return (char*)page; } int page_readlink(struct dentry *dentry, char __user *buffer, int buflen) @@ -2630,52 +2907,29 @@ int __page_symlink(struct inode *inode, const char *symname, int len, { struct address_space *mapping = inode->i_mapping; struct page *page; - int err = -ENOMEM; + void *fsdata; + int err; 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; - } + err = pagecache_write_begin(NULL, mapping, 0, len-1, + AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata); if (err) - goto fail_map; + goto fail; + kaddr = kmap_atomic(page, KM_USER0); memcpy(kaddr, symname, len-1); kunmap_atomic(kaddr, KM_USER0); - 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 - * that it is unmapped (typically even will not look into inode - - * ->i_size will be enough for everything) and zero it out. - * OTOH it's obviously correct and should make the page up-to-date. - */ - if (!PageUptodate(page)) { - err = mapping->a_ops->readpage(NULL, page); - if (err != AOP_TRUNCATED_PAGE) - wait_on_page_locked(page); - } else { - unlock_page(page); - } - page_cache_release(page); + + err = pagecache_write_end(NULL, mapping, 0, len-1, len-1, + page, fsdata); if (err < 0) goto fail; + if (err < len-1) + goto retry; + mark_inode_dirty(inode); return 0; -fail_map: - unlock_page(page); - page_cache_release(page); fail: return err; } @@ -2686,7 +2940,7 @@ int page_symlink(struct inode *inode, const char *symname, int len) mapping_gfp_mask(inode->i_mapping)); } -struct inode_operations page_symlink_inode_operations = { +const struct inode_operations page_symlink_inode_operations = { .readlink = generic_readlink, .follow_link = page_follow_link_light, .put_link = page_put_link, @@ -2707,8 +2961,7 @@ 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(vfs_path_lookup); EXPORT_SYMBOL(permission); EXPORT_SYMBOL(vfs_permission); EXPORT_SYMBOL(file_permission);