5 files changed, 64 insertions, 18 deletions

diff --git a/net/core/datagram.c b/net/core/datagram.c
index b80fb91bb3f7..4967262b2707 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -131,6 +131,35 @@ out_noerr:
 	goto out;
 }
 
+static int skb_set_peeked(struct sk_buff *skb)
+{
+	struct sk_buff *nskb;
+
+	if (skb->peeked)
+		return 0;
+
+	/* We have to unshare an skb before modifying it. */
+	if (!skb_shared(skb))
+		goto done;
+
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (!nskb)
+		return -ENOMEM;
+
+	skb->prev->next = nskb;
+	skb->next->prev = nskb;
+	nskb->prev = skb->prev;
+	nskb->next = skb->next;
+
+	consume_skb(skb);
+	skb = nskb;
+
+done:
+	skb->peeked = 1;
+
+	return 0;
+}
+
 /**
  *	__skb_recv_datagram - Receive a datagram skbuff
  *	@sk: socket
@@ -165,7 +194,9 @@ out_noerr:
 struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 				    int *peeked, int *off, int *err)
 {
+	struct sk_buff_head *queue = &sk->sk_receive_queue;
 	struct sk_buff *skb, *last;
+	unsigned long cpu_flags;
 	long timeo;
 	/*
 	 * Caller is allowed not to check sk->sk_err before skb_recv_datagram()
@@ -184,8 +215,6 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 		 * Look at current nfs client by the way...
 		 * However, this function was correct in any case. 8)
 		 */
-		unsigned long cpu_flags;
-		struct sk_buff_head *queue = &sk->sk_receive_queue;
 		int _off = *off;
 
 		last = (struct sk_buff *)queue;
@@ -199,7 +228,11 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 					_off -= skb->len;
 					continue;
 				}
-				skb->peeked = 1;
+
+				error = skb_set_peeked(skb);
+				if (error)
+					goto unlock_err;
+
 				atomic_inc(&skb->users);
 			} else
 				__skb_unlink(skb, queue);
@@ -223,6 +256,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
 
 	return NULL;
 
+unlock_err:
+	spin_unlock_irqrestore(&queue->lock, cpu_flags);
 no_packet:
 	*err = error;
 	return NULL;
@@ -622,7 +657,8 @@ __sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
 		    !skb->csum_complete_sw)
 			netdev_rx_csum_fault(skb->dev);
 	}
-	skb->csum_valid = !sum;
+	if (!skb_shared(skb))
+		skb->csum_valid = !sum;
 	return sum;
 }
 EXPORT_SYMBOL(__skb_checksum_complete_head);
@@ -642,11 +678,13 @@ __sum16 __skb_checksum_complete(struct sk_buff *skb)
 			netdev_rx_csum_fault(skb->dev);
 	}
 
-	/* Save full packet checksum */
-	skb->csum = csum;
-	skb->ip_summed = CHECKSUM_COMPLETE;
-	skb->csum_complete_sw = 1;
-	skb->csum_valid = !sum;
+	if (!skb_shared(skb)) {
+		/* Save full packet checksum */
+		skb->csum = csum;
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		skb->csum_complete_sw = 1;
+		skb->csum_valid = !sum;
+	}
 
 	return sum;
 }
diff --git a/net/core/dst.c b/net/core/dst.c
index e956ce6d1378..002144bea935 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -284,7 +284,9 @@ void dst_release(struct dst_entry *dst)
 		int newrefcnt;
 
 		newrefcnt = atomic_dec_return(&dst->__refcnt);
-		WARN_ON(newrefcnt < 0);
+		if (unlikely(newrefcnt < 0))
+			net_warn_ratelimited("%s: dst:%p refcnt:%d\n",
+					     __func__, dst, newrefcnt);
 		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt)
 			call_rcu(&dst->rcu_head, dst_destroy_rcu);
 	}
diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c
index 1f2a126f4ffa..6441f47b1a8f 100644
--- a/net/core/netclassid_cgroup.c
+++ b/net/core/netclassid_cgroup.c
@@ -23,7 +23,8 @@ static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state
 
 struct cgroup_cls_state *task_cls_state(struct task_struct *p)
 {
-	return css_cls_state(task_css(p, net_cls_cgrp_id));
+	return css_cls_state(task_css_check(p, net_cls_cgrp_id,
+					    rcu_read_lock_bh_held()));
 }
 EXPORT_SYMBOL_GPL(task_cls_state);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9e433d58d265..dc004b1e1f85 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1804,10 +1804,13 @@ static int do_setlink(const struct sk_buff *skb,
 			goto errout;
 
 		nla_for_each_nested(attr, tb[IFLA_VF_PORTS], rem) {
-			if (nla_type(attr) != IFLA_VF_PORT)
-				continue;
-			err = nla_parse_nested(port, IFLA_PORT_MAX,
-				attr, ifla_port_policy);
+			if (nla_type(attr) != IFLA_VF_PORT ||
+			    nla_len(attr) < NLA_HDRLEN) {
+				err = -EINVAL;
+				goto errout;
+			}
+			err = nla_parse_nested(port, IFLA_PORT_MAX, attr,
+					       ifla_port_policy);
 			if (err < 0)
 				goto errout;
 			if (!port[IFLA_PORT_VF]) {
diff --git a/net/core/sock.c b/net/core/sock.c
index 08f16db46070..193901d09757 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1497,7 +1497,8 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		sock_copy(newsk, sk);
 
 		/* SANITY */
-		get_net(sock_net(newsk));
+		if (likely(newsk->sk_net_refcnt))
+			get_net(sock_net(newsk));
 		sk_node_init(&newsk->sk_node);
 		sock_lock_init(newsk);
 		bh_lock_sock(newsk);
@@ -1967,20 +1968,21 @@ static void __release_sock(struct sock *sk)
  * sk_wait_data - wait for data to arrive at sk_receive_queue
  * @sk:    sock to wait on
  * @timeo: for how long
+ * @skb:   last skb seen on sk_receive_queue
  *
  * Now socket state including sk->sk_err is changed only under lock,
  * hence we may omit checks after joining wait queue.
  * We check receive queue before schedule() only as optimization;
  * it is very likely that release_sock() added new data.
  */
-int sk_wait_data(struct sock *sk, long *timeo)
+int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb)
 {
 	int rc;
 	DEFINE_WAIT(wait);
 
 	prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
 	set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
-	rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue));
+	rc = sk_wait_event(sk, timeo, skb_peek_tail(&sk->sk_receive_queue) != skb);
 	clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
 	finish_wait(sk_sleep(sk), &wait);
 	return rc;