From: Eric W. Biederman Date: Wed, 2 Oct 2013 01:33:48 +0000 (-0700) Subject: vfs: Lazily remove mounts on unlinked files and directories. X-Git-Url: http://git.lede-project.org./?a=commitdiff_plain;h=8ed936b5671bfb33d89bc60bdcc7cf0470ba52fe;p=openwrt%2Fstaging%2Fblogic.git vfs: Lazily remove mounts on unlinked files and directories. With the introduction of mount namespaces and bind mounts it became possible to access files and directories that on some paths are mount points but are not mount points on other paths. It is very confusing when rm -rf somedir returns -EBUSY simply because somedir is mounted somewhere else. With the addition of user namespaces allowing unprivileged mounts this condition has gone from annoying to allowing a DOS attack on other users in the system. The possibility for mischief is removed by updating the vfs to support rename, unlink and rmdir on a dentry that is a mountpoint and by lazily unmounting mountpoints on deleted dentries. In particular this change allows rename, unlink and rmdir system calls on a dentry without a mountpoint in the current mount namespace to succeed, and it allows rename, unlink, and rmdir performed on a distributed filesystem to update the vfs cache even if when there is a mount in some namespace on the original dentry. There are two common patterns of maintaining mounts: Mounts on trusted paths with the parent directory of the mount point and all ancestory directories up to / owned by root and modifiable only by root (i.e. /media/xxx, /dev, /dev/pts, /proc, /sys, /sys/fs/cgroup/{cpu, cpuacct, ...}, /usr, /usr/local). Mounts on unprivileged directories maintained by fusermount. In the case of mounts in trusted directories owned by root and modifiable only by root the current parent directory permissions are sufficient to ensure a mount point on a trusted path is not removed or renamed by anyone other than root, even if there is a context where the there are no mount points to prevent this. In the case of mounts in directories owned by less privileged users races with users modifying the path of a mount point are already a danger. fusermount already uses a combination of chdir, /proc//fd/NNN, and UMOUNT_NOFOLLOW to prevent these races. The removable of global rename, unlink, and rmdir protection really adds nothing new to consider only a widening of the attack window, and fusermount is already safe against unprivileged users modifying the directory simultaneously. In principle for perfect userspace programs returning -EBUSY for unlink, rmdir, and rename of dentires that have mounts in the local namespace is actually unnecessary. Unfortunately not all userspace programs are perfect so retaining -EBUSY for unlink, rmdir and rename of dentries that have mounts in the current mount namespace plays an important role of maintaining consistency with historical behavior and making imperfect userspace applications hard to exploit. v2: Remove spurious old_dentry. v3: Optimized shrink_submounts_and_drop Removed unsued afs label v4: Simplified the changes to check_submounts_and_drop Do not rename check_submounts_and_drop shrink_submounts_and_drop Document what why we need atomicity in check_submounts_and_drop Rely on the parent inode mutex to make d_revalidate and d_invalidate an atomic unit. v5: Refcount the mountpoint to detach in case of simultaneous renames. Reviewed-by: Miklos Szeredi Signed-off-by: "Eric W. Biederman" Signed-off-by: Al Viro --- diff --git a/fs/dcache.c b/fs/dcache.c index 8150e4e9e88b..484114a4db93 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -1343,36 +1343,39 @@ void shrink_dcache_for_umount(struct super_block *sb) } } -static enum d_walk_ret check_and_collect(void *_data, struct dentry *dentry) +struct detach_data { + struct select_data select; + struct dentry *mountpoint; +}; +static enum d_walk_ret detach_and_collect(void *_data, struct dentry *dentry) { - struct select_data *data = _data; + struct detach_data *data = _data; if (d_mountpoint(dentry)) { - data->found = -EBUSY; + __dget_dlock(dentry); + data->mountpoint = dentry; return D_WALK_QUIT; } - return select_collect(_data, dentry); + return select_collect(&data->select, dentry); } static void check_and_drop(void *_data) { - struct select_data *data = _data; + struct detach_data *data = _data; - if (d_mountpoint(data->start)) - data->found = -EBUSY; - if (!data->found) - __d_drop(data->start); + if (!data->mountpoint && !data->select.found) + __d_drop(data->select.start); } /** - * check_submounts_and_drop - prune dcache, check for submounts and drop + * check_submounts_and_drop - detach submounts, prune dcache, and drop * - * All done as a single atomic operation relative to has_unlinked_ancestor(). - * Returns 0 if successfully unhashed @parent. If there were submounts then - * return -EBUSY. + * The final d_drop is done as an atomic operation relative to + * rename_lock ensuring there are no races with d_set_mounted. This + * ensures there are no unhashed dentries on the path to a mountpoint. * - * @dentry: dentry to prune and drop + * @dentry: dentry to detach, prune and drop */ int check_submounts_and_drop(struct dentry *dentry) { @@ -1385,19 +1388,24 @@ int check_submounts_and_drop(struct dentry *dentry) } for (;;) { - struct select_data data; + struct detach_data data; - INIT_LIST_HEAD(&data.dispose); - data.start = dentry; - data.found = 0; + data.mountpoint = NULL; + INIT_LIST_HEAD(&data.select.dispose); + data.select.start = dentry; + data.select.found = 0; + + d_walk(dentry, &data, detach_and_collect, check_and_drop); - d_walk(dentry, &data, check_and_collect, check_and_drop); - ret = data.found; + if (data.select.found) + shrink_dentry_list(&data.select.dispose); - if (!list_empty(&data.dispose)) - shrink_dentry_list(&data.dispose); + if (data.mountpoint) { + detach_mounts(data.mountpoint); + dput(data.mountpoint); + } - if (ret <= 0) + if (!data.mountpoint && !data.select.found) break; cond_resched(); @@ -2639,10 +2647,8 @@ static struct dentry *__d_unalias(struct inode *inode, goto out_err; m2 = &alias->d_parent->d_inode->i_mutex; out_unalias: - if (likely(!d_mountpoint(alias))) { - __d_move(alias, dentry, false); - ret = alias; - } + __d_move(alias, dentry, false); + ret = alias; out_err: spin_unlock(&inode->i_lock); if (m2) diff --git a/fs/namei.c b/fs/namei.c index a3a14b033b0d..2ba10904dba0 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -3567,8 +3567,6 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry) error = -EBUSY; if (is_local_mountpoint(dentry)) goto out; - if (d_mountpoint(dentry)) - goto out; error = security_inode_rmdir(dir, dentry); if (error) @@ -3581,6 +3579,7 @@ int vfs_rmdir(struct inode *dir, struct dentry *dentry) dentry->d_inode->i_flags |= S_DEAD; dont_mount(dentry); + detach_mounts(dentry); out: mutex_unlock(&dentry->d_inode->i_mutex); @@ -3683,7 +3682,7 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate return -EPERM; mutex_lock(&target->i_mutex); - if (is_local_mountpoint(dentry) || d_mountpoint(dentry)) + if (is_local_mountpoint(dentry)) error = -EBUSY; else { error = security_inode_unlink(dir, dentry); @@ -3692,8 +3691,10 @@ int vfs_unlink(struct inode *dir, struct dentry *dentry, struct inode **delegate if (error) goto out; error = dir->i_op->unlink(dir, dentry); - if (!error) + if (!error) { dont_mount(dentry); + detach_mounts(dentry); + } } } out: @@ -4130,8 +4131,6 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, error = -EBUSY; if (is_local_mountpoint(old_dentry) || is_local_mountpoint(new_dentry)) goto out; - if (d_mountpoint(old_dentry) || d_mountpoint(new_dentry)) - goto out; if (max_links && new_dir != old_dir) { error = -EMLINK; @@ -4168,6 +4167,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry, if (is_dir) target->i_flags |= S_DEAD; dont_mount(new_dentry); + detach_mounts(new_dentry); } if (!(old_dir->i_sb->s_type->fs_flags & FS_RENAME_DOES_D_MOVE)) { if (!(flags & RENAME_EXCHANGE))