net: Clone skb before setting peeked flag

[ Upstream commit 738ac1eb ]

Shared skbs must not be modified and this is crucial for broadcast
and/or multicast paths where we use it as an optimisation to avoid
unnecessary cloning.

The function skb_recv_datagram breaks this rule by setting peeked
without cloning the skb first.  This causes funky races which leads
to double-free.

This patch fixes this by cloning the skb and replacing the skb
in the list when setting skb->peeked.

Fixes: a59322be ("[UDP]: Only increment counter on first peek/recv")
Reported-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

net/core/datagram.c

@@ -130,6 +130,35 @@ static int wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
 	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
@@ -164,7 +193,9 @@ static int wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
 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()
@@ -183,8 +214,6 @@ 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;
@@ -198,7 +227,11 @@ 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);
@@ -222,6 +255,8 @@ 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;