acl: handle idmapped mounts

The posix acl permission checking helpers determine whether a caller is
privileged over an inode according to the acls associated with the
inode. Add helpers that make it possible to handle acls on idmapped
mounts.

The vfs and the filesystems targeted by this first iteration make use of
posix_acl_fix_xattr_from_user() and posix_acl_fix_xattr_to_user() to
translate basic posix access and default permissions such as the
ACL_USER and ACL_GROUP type according to the initial user namespace (or
the superblock's user namespace) to and from the caller's current user
namespace. Adapt these two helpers to handle idmapped mounts whereby we
either map from or into the mount's user namespace depending on in which
direction we're translating.
Similarly, cap_convert_nscap() is used by the vfs to translate user
namespace and non-user namespace aware filesystem capabilities from the
superblock's user namespace to the caller's user namespace. Enable it to
handle idmapped mounts by accounting for the mount's user namespace.

In addition the fileystems targeted in the first iteration of this patch
series make use of the posix_acl_chmod() and, posix_acl_update_mode()
helpers. Both helpers perform permission checks on the target inode. Let
them handle idmapped mounts. These two helpers are called when posix
acls are set by the respective filesystems to handle this case we extend
the ->set() method to take an additional user namespace argument to pass
the mount's user namespace down.

Link: https://lore.kernel.org/r/20210121131959.646623-9-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: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>

1 files changed, 38 insertions, 7 deletions

diff --git a/security/commoncap.c b/security/commoncap.c
index 88ee345f7bfa..c3fd9b86ea9a 100644
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -450,16 +450,33 @@ int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer,
 	return size;
 }
 
+/**
+ * rootid_from_xattr - translate root uid of vfs caps
+ *
+ * @value:	vfs caps value which may be modified by this function
+ * @size:	size of @ivalue
+ * @task_ns:	user namespace of the caller
+ * @mnt_userns:	user namespace of the mount the inode was found from
+ *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
+ */
 static kuid_t rootid_from_xattr(const void *value, size_t size,
-				struct user_namespace *task_ns)
+				struct user_namespace *task_ns,
+				struct user_namespace *mnt_userns)
 {
 	const struct vfs_ns_cap_data *nscap = value;
+	kuid_t rootkid;
 	uid_t rootid = 0;
 
 	if (size == XATTR_CAPS_SZ_3)
 		rootid = le32_to_cpu(nscap->rootid);
 
-	return make_kuid(task_ns, rootid);
+	rootkid = make_kuid(task_ns, rootid);
+	return kuid_from_mnt(mnt_userns, rootkid);
 }
 
 static bool validheader(size_t size, const struct vfs_cap_data *cap)
@@ -467,13 +484,27 @@ static bool validheader(size_t size, const struct vfs_cap_data *cap)
 	return is_v2header(size, cap) || is_v3header(size, cap);
 }
 
-/*
+/**
+ * cap_convert_nscap - check vfs caps
+ *
+ * @mnt_userns:	user namespace of the mount the inode was found from
+ * @dentry:	used to retrieve inode to check permissions on
+ * @ivalue:	vfs caps value which may be modified by this function
+ * @size:	size of @ivalue
+ *
  * User requested a write of security.capability.  If needed, update the
  * xattr to change from v2 to v3, or to fixup the v3 rootid.
  *
+ * If the inode has been found through an idmapped mount the user namespace of
+ * the vfsmount must be passed through @mnt_userns. This function will then
+ * take care to map the inode according to @mnt_userns before checking
+ * permissions. On non-idmapped mounts or if permission checking is to be
+ * performed on the raw inode simply passs init_user_ns.
+ *
  * If all is ok, we return the new size, on error return < 0.
  */
-int cap_convert_nscap(struct dentry *dentry, const void **ivalue, size_t size)
+int cap_convert_nscap(struct user_namespace *mnt_userns, struct dentry *dentry,
+		      const void **ivalue, size_t size)
 {
 	struct vfs_ns_cap_data *nscap;
 	uid_t nsrootid;
@@ -489,14 +520,14 @@ int cap_convert_nscap(struct dentry *dentry, const void **ivalue, size_t size)
 		return -EINVAL;
 	if (!validheader(size, cap))
 		return -EINVAL;
-	if (!capable_wrt_inode_uidgid(&init_user_ns, inode, CAP_SETFCAP))
+	if (!capable_wrt_inode_uidgid(mnt_userns, inode, CAP_SETFCAP))
 		return -EPERM;
-	if (size == XATTR_CAPS_SZ_2)
+	if (size == XATTR_CAPS_SZ_2 && (mnt_userns == &init_user_ns))
 		if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP))
 			/* user is privileged, just write the v2 */
 			return size;
 
-	rootid = rootid_from_xattr(*ivalue, size, task_ns);
+	rootid = rootid_from_xattr(*ivalue, size, task_ns, mnt_userns);
 	if (!uid_valid(rootid))
 		return -EINVAL;