commoncap: handle idmapped mounts

When interacting with user namespace and non-user namespace aware
filesystem capabilities the vfs will perform various security checks to
determine whether or not the filesystem capabilities can be used by the
caller, whether they need to be removed and so on. The main
infrastructure for this resides in the capability codepaths but they are
called through the LSM security infrastructure even though they are not
technically an LSM or optional. This extends the existing security hooks
security_inode_removexattr(), security_inode_killpriv(),
security_inode_getsecurity() to pass down the mount's user namespace and
makes them aware of idmapped mounts.

In order to actually get filesystem capabilities from disk the
capability infrastructure exposes the get_vfs_caps_from_disk() helper.
For user namespace aware filesystem capabilities a root uid is stored
alongside the capabilities.

In order to determine whether the caller can make use of the filesystem
capability or whether it needs to be ignored it is translated according
to the superblock's user namespace. If it can be translated to uid 0
according to that id mapping the caller can use the filesystem
capabilities stored on disk. If we are accessing the inode that holds
the filesystem capabilities through an idmapped mount we map the root
uid according to the mount's user namespace. Afterwards the checks are
identical to non-idmapped mounts: reading filesystem caps from disk
enforces that the root uid associated with the filesystem capability
must have a mapping in the superblock's user namespace and that the
caller is either in the same user namespace or is a descendant of the
superblock's user namespace. For filesystems that are mountable inside
user namespace the caller can just mount the filesystem and won't
usually need to idmap it. If they do want to idmap it they can create an
idmapped mount and mark it with a user namespace they created and which
is thus a descendant of s_user_ns. For filesystems that are not
mountable inside user namespaces the descendant rule is trivially true
because the s_user_ns will be the initial 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/20210121131959.646623-11-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>
Acked-by: James Morris <jamorris@linux.microsoft.com>
Signed-off-by: Christian Brauner <christian.brauner@ubuntu.com>

1 files changed, 12 insertions, 8 deletions

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 2efedd7001b2..9719dd124221 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3119,7 +3119,8 @@ static bool has_cap_mac_admin(bool audit)
 	return true;
 }
 
-static int selinux_inode_setxattr(struct dentry *dentry, const char *name,
+static int selinux_inode_setxattr(struct user_namespace *mnt_userns,
+				  struct dentry *dentry, const char *name,
 				  const void *value, size_t size, int flags)
 {
 	struct inode *inode = d_backing_inode(dentry);
@@ -3140,13 +3141,13 @@ static int selinux_inode_setxattr(struct dentry *dentry, const char *name,
 	}
 
 	if (!selinux_initialized(&selinux_state))
-		return (inode_owner_or_capable(&init_user_ns, inode) ? 0 : -EPERM);
+		return (inode_owner_or_capable(mnt_userns, inode) ? 0 : -EPERM);
 
 	sbsec = inode->i_sb->s_security;
 	if (!(sbsec->flags & SBLABEL_MNT))
 		return -EOPNOTSUPP;
 
-	if (!inode_owner_or_capable(&init_user_ns, inode))
+	if (!inode_owner_or_capable(mnt_userns, inode))
 		return -EPERM;
 
 	ad.type = LSM_AUDIT_DATA_DENTRY;
@@ -3267,10 +3268,11 @@ static int selinux_inode_listxattr(struct dentry *dentry)
 	return dentry_has_perm(cred, dentry, FILE__GETATTR);
 }
 
-static int selinux_inode_removexattr(struct dentry *dentry, const char *name)
+static int selinux_inode_removexattr(struct user_namespace *mnt_userns,
+				     struct dentry *dentry, const char *name)
 {
 	if (strcmp(name, XATTR_NAME_SELINUX)) {
-		int rc = cap_inode_removexattr(dentry, name);
+		int rc = cap_inode_removexattr(mnt_userns, dentry, name);
 		if (rc)
 			return rc;
 
@@ -3336,7 +3338,9 @@ static int selinux_path_notify(const struct path *path, u64 mask,
  *
  * Permission check is handled by selinux_inode_getxattr hook.
  */
-static int selinux_inode_getsecurity(struct inode *inode, const char *name, void **buffer, bool alloc)
+static int selinux_inode_getsecurity(struct user_namespace *mnt_userns,
+				     struct inode *inode, const char *name,
+				     void **buffer, bool alloc)
 {
 	u32 size;
 	int error;
@@ -6533,8 +6537,8 @@ static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen)
 static int selinux_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen)
 {
 	int len = 0;
-	len = selinux_inode_getsecurity(inode, XATTR_SELINUX_SUFFIX,
-						ctx, true);
+	len = selinux_inode_getsecurity(&init_user_ns, inode,
+					XATTR_SELINUX_SUFFIX, ctx, true);
 	if (len < 0)
 		return len;
 	*ctxlen = len;