open: handle idmapped mounts

For core file operations such as changing directories or chrooting,
determining file access, changing mode or ownership the vfs will verify
that the caller is privileged over the inode. Extend the various helpers
to handle idmapped mounts. If the inode is accessed through an idmapped
mount map it into the mount's user namespace. Afterwards the permissions
checks are identical to non-idmapped mounts. When changing file
ownership we need to map the uid and gid from the mount's user
namespace. If the initial user namespace is passed nothing changes so
non-idmapped mounts will see identical behavior as before.

Link: https://lore.kernel.org/r/20210121131959.646623-17-christian.brauner@ubuntu.com
Cc: Christoph Hellwig <hch@lst.de>
Cc: David Howells <dhowells@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Reviewed-by: James Morris <jamorris@linux.microsoft.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>

diff --git a/fs/open.c b/fs/open.c
index 8b3f3eb..4ec3979 100644 (file)
--- a/fs/open.c
+++ b/fs/open.c
@@ -438,7 +438,7 @@ retry:
                        goto out_path_release;
        }
 
-       res = inode_permission(&init_user_ns, inode, mode | MAY_ACCESS);
+       res = inode_permission(mnt_user_ns(path.mnt), inode, mode | MAY_ACCESS);
        /* SuS v2 requires we report a read only fs too */
        if (res || !(mode & S_IWOTH) || special_file(inode->i_mode))
                goto out_path_release;
@@ -582,8 +582,8 @@ retry_deleg:
                goto out_unlock;
        newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO);
        newattrs.ia_valid = ATTR_MODE | ATTR_CTIME;
-       error = notify_change(&init_user_ns, path->dentry, &newattrs,
-                             &delegated_inode);
+       error = notify_change(mnt_user_ns(path->mnt), path->dentry,
+                             &newattrs, &delegated_inode);
 out_unlock:
        inode_unlock(inode);
        if (delegated_inode) {
@@ -644,6 +644,7 @@ SYSCALL_DEFINE2(chmod, const char __user *, filename, umode_t, mode)
 
 int chown_common(const struct path *path, uid_t user, gid_t group)
 {
+       struct user_namespace *mnt_userns;
        struct inode *inode = path->dentry->d_inode;
        struct inode *delegated_inode = NULL;
        int error;
@@ -654,6 +655,10 @@ int chown_common(const struct path *path, uid_t user, gid_t group)
        uid = make_kuid(current_user_ns(), user);
        gid = make_kgid(current_user_ns(), group);
 
+       mnt_userns = mnt_user_ns(path->mnt);
+       uid = kuid_from_mnt(mnt_userns, uid);
+       gid = kgid_from_mnt(mnt_userns, gid);
+
 retry_deleg:
        newattrs.ia_valid =  ATTR_CTIME;
        if (user != (uid_t) -1) {
@@ -674,7 +679,7 @@ retry_deleg:
        inode_lock(inode);
        error = security_path_chown(path, uid, gid);
        if (!error)
-               error = notify_change(&init_user_ns, path->dentry, &newattrs,
+               error = notify_change(mnt_userns, path->dentry, &newattrs,
                                      &delegated_inode);
        inode_unlock(inode);
        if (delegated_inode) {