*/
/*
* [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...
*/
#ifdef CONFIG_AUDITSYSCALL
void putname(const char *name)
{
- if (unlikely(current->audit_context))
+ if (unlikely(!audit_dummy_context()))
audit_putname(name);
else
__putname(name);
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.
}
+ /*
+ * 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)
struct dentry *dentry;
};
+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;
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)) {
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.
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);
}
nd->mnt = mntget(current->fs->rootmnt);
nd->dentry = dget(current->fs->root);
+ 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 unlock_fail;
+ goto out_fail;
dentry = file->f_dentry;
retval = -ENOTDIR;
if (!S_ISDIR(dentry->d_inode->i_mode))
- goto fput_unlock_fail;
+ goto fput_fail;
retval = file_permission(file, MAY_EXEC);
if (retval)
- goto fput_unlock_fail;
+ 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_unlock_fail:
+fput_fail:
fput_light(file, fput_needed);
-unlock_fail:
- read_unlock(¤t->fs->lock);
- return retval;
+ goto out_fail;
}
int fastcall path_lookup(const char *name, unsigned int flags,
return dentry;
}
-struct dentry * lookup_hash(struct nameidata *nd)
+static struct dentry *lookup_hash(struct nameidata *nd)
{
return __lookup_hash(&nd->last, nd->dentry, nd);
}
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)
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;
}
- 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) {
- 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;
}
mutex_unlock(&p1->d_inode->i_mutex);
if (p1 != p2) {
mutex_unlock(&p2->d_inode->i_mutex);
- up(&p1->d_inode->i_sb->s_vfs_rename_sem);
+ mutex_unlock(&p1->d_inode->i_sb->s_vfs_rename_mutex);
}
}
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;
}
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))
* It already exists.
*/
mutex_unlock(&dir->d_inode->i_mutex);
+ audit_inode_update(path.dentry->d_inode);
error = -EEXIST;
if (flag & O_EXCL)
if (flag & O_NOFOLLOW)
goto exit_dput;
}
+
error = -ENOENT;
if (!path.dentry->d_inode)
goto exit_dput;
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;
{
struct dentry *dentry = ERR_PTR(-EEXIST);
- mutex_lock(&nd->dentry->d_inode->i_mutex);
+ mutex_lock_nested(&nd->dentry->d_inode->i_mutex, I_MUTEX_PARENT);
/*
* Yucky last component or no last component at all?
* (foo/., foo/.., /////)
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.
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;
}
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;
}
error = -EBUSY;
goto exit1;
}
- mutex_lock(&nd.dentry->d_inode->i_mutex);
+ 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 = -EISDIR;
if (nd.last_type != LAST_NORM)
goto exit1;
- mutex_lock(&nd.dentry->d_inode->i_mutex);
+ mutex_lock_nested(&nd.dentry->d_inode->i_mutex, I_MUTEX_PARENT);
dentry = lookup_hash(&nd);
error = PTR_ERR(dentry);
if (!IS_ERR(dentry)) {
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;
}
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->d_name.name);
+ fsnotify_create(dir, new_dentry);
return error;
}
* and other special files. --ADM
*/
asmlinkage long sys_linkat(int olddfd, const char __user *oldname,
- int newdfd, const char __user *newname)
+ 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_fd(olddfd, oldname, 0, &old_nd);
+ error = __user_walk_fd(olddfd, oldname,
+ flags & AT_SYMLINK_FOLLOW ? LOOKUP_FOLLOW : 0,
+ &old_nd);
if (error)
goto exit;
error = do_path_lookup(newdfd, to, LOOKUP_PARENT, &nd);
asmlinkage long sys_link(const char __user *oldname, const char __user *newname)
{
- return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname);
+ return sys_linkat(AT_FDCWD, oldname, AT_FDCWD, newname, 0);
}
/*
* 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_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.
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;
}
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)
{
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);
}
}
-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
*/
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);
}
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,
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);