netlink: Call cb->done from a worker thread

[ Upstream commit 707693c8 ]

The cb->done interface expects to be called in process context.
This was broken by the netlink RCU conversion.  This patch fixes
it by adding a worker struct to make the cb->done call where
necessary.

Fixes: 21e4902a ("netlink: Lockless lookup with RCU grace...")
Reported-by: Subash Abhinov Kasiviswanathan <subashab@codeaurora.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

net/netlink/af_netlink.c

@@ -924,14 +924,11 @@ static void netlink_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
 	sk_mem_charge(sk, skb->truesize);
 }
 
-static void netlink_sock_destruct(struct sock *sk)
+static void __netlink_sock_destruct(struct sock *sk)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
 
 	if (nlk->cb_running) {
-		if (nlk->cb.done)
-			nlk->cb.done(&nlk->cb);
-
 		module_put(nlk->cb.module);
 		kfree_skb(nlk->cb.skb);
 	}
@@ -960,6 +957,28 @@ static void netlink_sock_destruct(struct sock *sk)
 	WARN_ON(nlk_sk(sk)->groups);
 }
 
+static void netlink_sock_destruct_work(struct work_struct *work)
+{
+	struct netlink_sock *nlk = container_of(work, struct netlink_sock,
+						work);
+
+	nlk->cb.done(&nlk->cb);
+	__netlink_sock_destruct(&nlk->sk);
+}
+
+static void netlink_sock_destruct(struct sock *sk)
+{
+	struct netlink_sock *nlk = nlk_sk(sk);
+
+	if (nlk->cb_running && nlk->cb.done) {
+		INIT_WORK(&nlk->work, netlink_sock_destruct_work);
+		schedule_work(&nlk->work);
+		return;
+	}
+
+	__netlink_sock_destruct(sk);
+}
+
 /* This lock without WQ_FLAG_EXCLUSIVE is good on UP and it is _very_ bad on
  * SMP. Look, when several writers sleep and reader wakes them up, all but one
  * immediately hit write lock and grab all the cpus. Exclusive sleep solves

net/netlink/af_netlink.h

@@ -3,6 +3,7 @@
 
 #include <linux/rhashtable.h>
 #include <linux/atomic.h>
+#include <linux/workqueue.h>
 #include <net/sock.h>
 
 #define NLGRPSZ(x)	(ALIGN(x, sizeof(unsigned long) * 8) / 8)
@@ -53,6 +54,7 @@ struct netlink_sock {
 
 	struct rhash_head	node;
 	struct rcu_head		rcu;
+	struct work_struct	work;
 };
 
 static inline struct netlink_sock *nlk_sk(struct sock *sk)