[CRIU] [PATCH] pidns: remove recursion from free_pid_ns

[Andrew Vagin]

Here is a stack trace of recursion:
free_pid_ns(parent)
  put_pid_ns(parent)
    kref_put(&ns->kref, free_pid_ns);
      free_pid_ns

This patch turns recursion into loops.

pidns can be nested many times, so in case of recursion
a simple user space program can provoke a kernel panic
due to exceed of a kernel stack.

Cc: Andrew Morton <akpm at linux-foundation.org>
Cc: Oleg Nesterov <oleg at redhat.com>
Cc: "Eric W. Biederman" <ebiederm at xmission.com>
Cc: Cyrill Gorcunov <gorcunov at openvz.org>
Cc: Pavel Emelyanov <xemul at parallels.com>
Signed-off-by: Andrew Vagin <avagin at openvz.org>
---
 include/linux/kref.h   |   12 ++++++++++++
 kernel/pid_namespace.c |   17 +++++++++++++----
 2 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/include/linux/kref.h b/include/linux/kref.h
index 65af688..d234199 100644
--- a/include/linux/kref.h
+++ b/include/linux/kref.h
@@ -95,6 +95,18 @@ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)
 	return kref_sub(kref, 1, release);
 }
 
+/**
+ * kref_put - decrement refcount for object.
+ * @kref: object.
+ *
+ * Decrement the refcount.
+ * Return 1 if refcount is zero.
+ */
+static inline int __kref_put(struct kref *kref)
+{
+	return atomic_sub_and_test(1, &kref->refcount);
+}
+
 static inline int kref_put_mutex(struct kref *kref,
 				 void (*release)(struct kref *kref),
 				 struct mutex *lock)
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index b17bf93..632eb88 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -138,11 +138,20 @@ void free_pid_ns(struct kref *kref)
 
 	ns = container_of(kref, struct pid_namespace, kref);
 
-	parent = ns->parent;
-	destroy_pid_namespace(ns);
+	while (1) {
 
-	if (parent != NULL)
-		put_pid_ns(parent);
+		parent = ns->parent;
+		destroy_pid_namespace(ns);
+
+		if (parent == NULL || parent == &init_pid_ns)
+			break;
+
+		/* kref_put cannot be used for avoiding recursion */
+		if (__kref_put(&parent->kref) == 0)
+			break;
+
+		ns = parent;
+	}
 }
 
 void zap_pid_ns_processes(struct pid_namespace *pid_ns)
-- 
1.7.1