userns: move user access out of the mutex

The old code would hold the userns_state_mutex indefinitely if
memdup_user_nul stalled due to e.g. a userfault region. Prevent that by
moving the memdup_user_nul in front of the mutex_lock().

Note: This changes the error precedence of invalid buf/count/*ppos vs
map already written / capabilities missing.

Fixes: 22d917d8 ("userns: Rework the user_namespace adding uid/gid...")
Cc: stable@vger.kernel.org
Signed-off-by: Jann Horn <jannh@google.com>
Acked-by: Christian Brauner <christian@brauner.io>
Acked-by: Serge Hallyn <serge@hallyn.com>
Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>

kernel/user_namespace.c

@@ -859,7 +859,16 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	unsigned idx;
 	struct uid_gid_extent extent;
 	char *kbuf = NULL, *pos, *next_line;
-	ssize_t ret = -EINVAL;
+	ssize_t ret;
+
+	/* Only allow < page size writes at the beginning of the file */
+	if ((*ppos != 0) || (count >= PAGE_SIZE))
+		return -EINVAL;
+
+	/* Slurp in the user data */
+	kbuf = memdup_user_nul(buf, count);
+	if (IS_ERR(kbuf))
+		return PTR_ERR(kbuf);
 
 	/*
 	 * The userns_state_mutex serializes all writes to any given map.
@@ -895,19 +904,6 @@ static ssize_t map_write(struct file *file, const char __user *buf,
 	if (cap_valid(cap_setid) && !file_ns_capable(file, ns, CAP_SYS_ADMIN))
 		goto out;
 
-	/* Only allow < page size writes at the beginning of the file */
-	ret = -EINVAL;
-	if ((*ppos != 0) || (count >= PAGE_SIZE))
-		goto out;
-
-	/* Slurp in the user data */
-	kbuf = memdup_user_nul(buf, count);
-	if (IS_ERR(kbuf)) {
-		ret = PTR_ERR(kbuf);
-		kbuf = NULL;
-		goto out;
-	}
-
 	/* Parse the user data */
 	ret = -EINVAL;
 	pos = kbuf;