Fix recursive lock in free_uid()/free_user_ns()

free_uid() and free_user_ns() are corecursive when CONFIG_USER_SCHED=n,
but free_user_ns() is called from free_uid() by way of uid_hash_remove(),
which requires uidhash_lock to be held.  free_user_ns() then calls
free_uid() to complete the destruction.

Fix this by deferring the destruction of the user_namespace.

Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 18 insertions, 4 deletions

diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index 315bcd3..cc4f453 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -13,6 +13,7 @@ struct user_namespace {
 	struct kref		kref;
 	struct hlist_head	uidhash_table[UIDHASH_SZ];
 	struct user_struct	*creator;
+	struct work_struct	destroyer;
 };
 
 extern struct user_namespace init_user_ns;
diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c
index 7908431..076c7c8 100644
--- a/kernel/user_namespace.c
+++ b/kernel/user_namespace.c
@@ -60,12 +60,25 @@ int create_user_ns(struct cred *new)
 	return 0;
 }
 
-void free_user_ns(struct kref *kref)
+/*
+ * Deferred destructor for a user namespace.  This is required because
+ * free_user_ns() may be called with uidhash_lock held, but we need to call
+ * back to free_uid() which will want to take the lock again.
+ */
+static void free_user_ns_work(struct work_struct *work)
 {
-	struct user_namespace *ns;
-
-	ns = container_of(kref, struct user_namespace, kref);
+	struct user_namespace *ns =
+		container_of(work, struct user_namespace, destroyer);
 	free_uid(ns->creator);
 	kfree(ns);
 }
+
+void free_user_ns(struct kref *kref)
+{
+	struct user_namespace *ns =
+		container_of(kref, struct user_namespace, kref);
+
+	INIT_WORK(&ns->destroyer, free_user_ns_work);
+	schedule_work(&ns->destroyer);
+}
 EXPORT_SYMBOL(free_user_ns);