fs: take i_mutex during prepare_binprm for set[ug]id executables

[ Upstream commit 8b01fc86 ]

This prevents a race between chown() and execve(), where chowning a
setuid-user binary to root would momentarily make the binary setuid
root.

This patch was mostly written by Linus Torvalds.
Signed-off-by: Jann Horn <jann@thejh.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>

fs/exec.c

@@ -1250,44 +1250,64 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 	spin_unlock(&p->fs->lock);
 }
 
-/*
- * Fill the binprm structure from the inode.
- * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
- *
- * This may be called multiple times for binary chains (scripts for example).
- */
-int prepare_binprm(struct linux_binprm *bprm)
+static void bprm_fill_uid(struct linux_binprm *bprm)
 {
-	struct inode *inode = file_inode(bprm->file);
-	umode_t mode = inode->i_mode;
-	int retval;
-
+	struct inode *inode;
+	unsigned int mode;
+	kuid_t uid;
+	kgid_t gid;
 
 	/* clear any previous set[ug]id data from a previous binary */
 	bprm->cred->euid = current_euid();
 	bprm->cred->egid = current_egid();
 
-	if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) &&
-	    !task_no_new_privs(current) &&
-	    kuid_has_mapping(bprm->cred->user_ns, inode->i_uid) &&
-	    kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) {
-		/* Set-uid? */
+	if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)
+		return;
+
+	if (task_no_new_privs(current))
+		return;
+
+	inode = file_inode(bprm->file);
+	mode = READ_ONCE(inode->i_mode);
+	if (!(mode & (S_ISUID|S_ISGID)))
+		return;
+
+	/* Be careful if suid/sgid is set */
+	mutex_lock(&inode->i_mutex);
+
+	/* reload atomically mode/uid/gid now that lock held */
+	mode = inode->i_mode;
+	uid = inode->i_uid;
+	gid = inode->i_gid;
+	mutex_unlock(&inode->i_mutex);
+
+	/* We ignore suid/sgid if there are no mappings for them in the ns */
+	if (!kuid_has_mapping(bprm->cred->user_ns, uid) ||
+		 !kgid_has_mapping(bprm->cred->user_ns, gid))
+		return;
+
 	if (mode & S_ISUID) {
 		bprm->per_clear |= PER_CLEAR_ON_SETID;
-			bprm->cred->euid = inode->i_uid;
+		bprm->cred->euid = uid;
 	}
 
-		/* Set-gid? */
-		/*
-		 * If setgid is set but no group execute bit then this
-		 * is a candidate for mandatory locking, not a setgid
-		 * executable.
-		 */
 	if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
 		bprm->per_clear |= PER_CLEAR_ON_SETID;
-			bprm->cred->egid = inode->i_gid;
-		}
+		bprm->cred->egid = gid;
 	}
+}
+
+/*
+ * Fill the binprm structure from the inode.
+ * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
+ *
+ * This may be called multiple times for binary chains (scripts for example).
+ */
+int prepare_binprm(struct linux_binprm *bprm)
+{
+	int retval;
+
+	bprm_fill_uid(bprm);
 
 	/* fill in binprm security blob */
 	retval = security_bprm_set_creds(bprm);