aboutsummaryrefslogtreecommitdiff
path: root/fs/namespace.c
diff options
context:
space:
mode:
Diffstat (limited to 'fs/namespace.c')
-rw-r--r--fs/namespace.c93
1 files changed, 71 insertions, 22 deletions
diff --git a/fs/namespace.c b/fs/namespace.c
index 5b66b2b3624d..da23ad8a2c85 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1322,14 +1322,15 @@ static inline void namespace_lock(void)
down_write(&namespace_sem);
}
+enum umount_tree_flags {
+ UMOUNT_SYNC = 1,
+ UMOUNT_PROPAGATE = 2,
+};
/*
* mount_lock must be held
* namespace_sem must be held for write
- * how = 0 => just this tree, don't propagate
- * how = 1 => propagate; we know that nobody else has reference to any victims
- * how = 2 => lazy umount
*/
-void umount_tree(struct mount *mnt, int how)
+static void umount_tree(struct mount *mnt, enum umount_tree_flags how)
{
HLIST_HEAD(tmp_list);
struct mount *p;
@@ -1343,7 +1344,7 @@ void umount_tree(struct mount *mnt, int how)
hlist_for_each_entry(p, &tmp_list, mnt_hash)
list_del_init(&p->mnt_child);
- if (how)
+ if (how & UMOUNT_PROPAGATE)
propagate_umount(&tmp_list);
hlist_for_each_entry(p, &tmp_list, mnt_hash) {
@@ -1351,7 +1352,7 @@ void umount_tree(struct mount *mnt, int how)
list_del_init(&p->mnt_list);
__touch_mnt_namespace(p->mnt_ns);
p->mnt_ns = NULL;
- if (how < 2)
+ if (how & UMOUNT_SYNC)
p->mnt.mnt_flags |= MNT_SYNC_UMOUNT;
if (mnt_has_parent(p)) {
hlist_del_init(&p->mnt_mp_list);
@@ -1369,6 +1370,8 @@ void umount_tree(struct mount *mnt, int how)
}
if (last) {
last->mnt_hash.next = unmounted.first;
+ if (unmounted.first)
+ unmounted.first->pprev = &last->mnt_hash.next;
unmounted.first = tmp_list.first;
unmounted.first->pprev = &unmounted.first;
}
@@ -1454,14 +1457,14 @@ static int do_umount(struct mount *mnt, int flags)
if (flags & MNT_DETACH) {
if (!list_empty(&mnt->mnt_list))
- umount_tree(mnt, 2);
+ umount_tree(mnt, UMOUNT_PROPAGATE);
retval = 0;
} else {
shrink_submounts(mnt);
retval = -EBUSY;
if (!propagate_mount_busy(mnt, 2)) {
if (!list_empty(&mnt->mnt_list))
- umount_tree(mnt, 1);
+ umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC);
retval = 0;
}
}
@@ -1487,13 +1490,13 @@ void __detach_mounts(struct dentry *dentry)
namespace_lock();
mp = lookup_mountpoint(dentry);
- if (!mp)
+ if (IS_ERR_OR_NULL(mp))
goto out_unlock;
lock_mount_hash();
while (!hlist_empty(&mp->m_list)) {
mnt = hlist_entry(mp->m_list.first, struct mount, mnt_mp_list);
- umount_tree(mnt, 2);
+ umount_tree(mnt, 0);
}
unlock_mount_hash();
put_mountpoint(mp);
@@ -1544,6 +1547,9 @@ SYSCALL_DEFINE2(umount, char __user *, name, int, flags)
goto dput_and_out;
if (mnt->mnt.mnt_flags & MNT_LOCKED)
goto dput_and_out;
+ retval = -EPERM;
+ if (flags & MNT_FORCE && !capable(CAP_SYS_ADMIN))
+ goto dput_and_out;
retval = do_umount(mnt, flags);
dput_and_out:
@@ -1657,7 +1663,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
out:
if (res) {
lock_mount_hash();
- umount_tree(res, 0);
+ umount_tree(res, UMOUNT_SYNC);
unlock_mount_hash();
}
return q;
@@ -1669,8 +1675,11 @@ struct vfsmount *collect_mounts(struct path *path)
{
struct mount *tree;
namespace_lock();
- tree = copy_tree(real_mount(path->mnt), path->dentry,
- CL_COPY_ALL | CL_PRIVATE);
+ if (!check_mnt(real_mount(path->mnt)))
+ tree = ERR_PTR(-EINVAL);
+ else
+ tree = copy_tree(real_mount(path->mnt), path->dentry,
+ CL_COPY_ALL | CL_PRIVATE);
namespace_unlock();
if (IS_ERR(tree))
return ERR_CAST(tree);
@@ -1681,7 +1690,7 @@ void drop_collected_mounts(struct vfsmount *mnt)
{
namespace_lock();
lock_mount_hash();
- umount_tree(real_mount(mnt), 0);
+ umount_tree(real_mount(mnt), UMOUNT_SYNC);
unlock_mount_hash();
namespace_unlock();
}
@@ -1864,7 +1873,7 @@ static int attach_recursive_mnt(struct mount *source_mnt,
out_cleanup_ids:
while (!hlist_empty(&tree_list)) {
child = hlist_entry(tree_list.first, struct mount, mnt_hash);
- umount_tree(child, 0);
+ umount_tree(child, UMOUNT_SYNC);
}
unlock_mount_hash();
cleanup_group_ids(source_mnt, NULL);
@@ -2041,7 +2050,7 @@ static int do_loopback(struct path *path, const char *old_name,
err = graft_tree(mnt, parent, mp);
if (err) {
lock_mount_hash();
- umount_tree(mnt, 0);
+ umount_tree(mnt, UMOUNT_SYNC);
unlock_mount_hash();
}
out2:
@@ -2098,7 +2107,13 @@ static int do_remount(struct path *path, int flags, int mnt_flags,
}
if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
!(mnt_flags & MNT_NODEV)) {
- return -EPERM;
+ /* Was the nodev implicitly added in mount? */
+ if ((mnt->mnt_ns->user_ns != &init_user_ns) &&
+ !(sb->s_type->fs_flags & FS_USERNS_DEV_MOUNT)) {
+ mnt_flags |= MNT_NODEV;
+ } else {
+ return -EPERM;
+ }
}
if ((mnt->mnt.mnt_flags & MNT_LOCK_NOSUID) &&
!(mnt_flags & MNT_NOSUID)) {
@@ -2282,6 +2297,8 @@ unlock:
return err;
}
+static bool fs_fully_visible(struct file_system_type *fs_type, int *new_mnt_flags);
+
/*
* create a new mount for userspace and request it to be added into the
* namespace's tree
@@ -2313,6 +2330,10 @@ static int do_new_mount(struct path *path, const char *fstype, int flags,
flags |= MS_NODEV;
mnt_flags |= MNT_NODEV | MNT_LOCK_NODEV;
}
+ if (type->fs_flags & FS_USERNS_VISIBLE) {
+ if (!fs_fully_visible(type, &mnt_flags))
+ return -EPERM;
+ }
}
mnt = vfs_kern_mount(type, flags, name, data);
@@ -2406,7 +2427,7 @@ void mark_mounts_for_expiry(struct list_head *mounts)
while (!list_empty(&graveyard)) {
mnt = list_first_entry(&graveyard, struct mount, mnt_expire);
touch_mnt_namespace(mnt->mnt_ns);
- umount_tree(mnt, 1);
+ umount_tree(mnt, UMOUNT_PROPAGATE|UMOUNT_SYNC);
}
unlock_mount_hash();
namespace_unlock();
@@ -2477,7 +2498,7 @@ static void shrink_submounts(struct mount *mnt)
m = list_first_entry(&graveyard, struct mount,
mnt_expire);
touch_mnt_namespace(m->mnt_ns);
- umount_tree(m, 1);
+ umount_tree(m, UMOUNT_PROPAGATE|UMOUNT_SYNC);
}
}
}
@@ -3110,9 +3131,10 @@ bool current_chrooted(void)
return chrooted;
}
-bool fs_fully_visible(struct file_system_type *type)
+static bool fs_fully_visible(struct file_system_type *type, int *new_mnt_flags)
{
struct mnt_namespace *ns = current->nsproxy->mnt_ns;
+ int new_flags = *new_mnt_flags;
struct mount *mnt;
bool visible = false;
@@ -3125,16 +3147,43 @@ bool fs_fully_visible(struct file_system_type *type)
if (mnt->mnt.mnt_sb->s_type != type)
continue;
- /* This mount is not fully visible if there are any child mounts
- * that cover anything except for empty directories.
+ /* This mount is not fully visible if it's root directory
+ * is not the root directory of the filesystem.
+ */
+ if (mnt->mnt.mnt_root != mnt->mnt.mnt_sb->s_root)
+ continue;
+
+ /* Verify the mount flags are equal to or more permissive
+ * than the proposed new mount.
+ */
+ if ((mnt->mnt.mnt_flags & MNT_LOCK_READONLY) &&
+ !(new_flags & MNT_READONLY))
+ continue;
+ if ((mnt->mnt.mnt_flags & MNT_LOCK_NODEV) &&
+ !(new_flags & MNT_NODEV))
+ continue;
+ if ((mnt->mnt.mnt_flags & MNT_LOCK_ATIME) &&
+ ((mnt->mnt.mnt_flags & MNT_ATIME_MASK) != (new_flags & MNT_ATIME_MASK)))
+ continue;
+
+ /* This mount is not fully visible if there are any
+ * locked child mounts that cover anything except for
+ * empty directories.
*/
list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
struct inode *inode = child->mnt_mountpoint->d_inode;
+ /* Only worry about locked mounts */
+ if (!(mnt->mnt.mnt_flags & MNT_LOCKED))
+ continue;
if (!S_ISDIR(inode->i_mode))
goto next;
if (inode->i_nlink > 2)
goto next;
}
+ /* Preserve the locked attributes */
+ *new_mnt_flags |= mnt->mnt.mnt_flags & (MNT_LOCK_READONLY | \
+ MNT_LOCK_NODEV | \
+ MNT_LOCK_ATIME);
visible = true;
goto found;
next: ;
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-27 20:32:37 +0000