net: Clone skb before setting peeked flag

commit 738ac1ebb96d02e0d23bc320302a6ea94c612dec upstream.

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: a59322be07c9 ("[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>
[bwh: Backported to 3.2: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>

1 files changed, 38 insertions, 4 deletions

diff --git a/net/core/datagram.c b/net/core/datagram.c
index 6f54d0a..eaa1d32 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -128,6 +128,35 @@ 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
@@ -160,7 +189,9 @@ out_noerr:
 struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
 				    int *peeked, int *err)
 {
+	struct sk_buff_head *queue = &sk->sk_receive_queue;
 	struct sk_buff *skb;
+	unsigned long cpu_flags;
 	long timeo;
 	/*
 	 * Caller is allowed not to check sk->sk_err before skb_recv_datagram()
@@ -179,15 +210,16 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned 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;
-
 		spin_lock_irqsave(&queue->lock, cpu_flags);
 		skb = skb_peek(queue);
 		if (skb) {
 			*peeked = skb->peeked;
 			if (flags & MSG_PEEK) {
-				skb->peeked = 1;
+
+				error = skb_set_peeked(skb);
+				if (error)
+					goto unlock_err;
+
 				atomic_inc(&skb->users);
 			} else
 				__skb_unlink(skb, queue);
@@ -206,6 +238,8 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags,
 
 	return NULL;
 
+unlock_err:
+	spin_unlock_irqrestore(&queue->lock, cpu_flags);
 no_packet:
 	*err = error;
 	return NULL;