tcp: must unclone packets before mangling them

[ Upstream commit c52e2421 ]

TCP stack should make sure it owns skbs before mangling them.

We had various crashes using bnx2x, and it turned out gso_size
was cleared right before bnx2x driver was populating TC descriptor
of the _previous_ packet send. TCP stack can sometime retransmit
packets that are still in Qdisc.

Of course we could make bnx2x driver more robust (using
ACCESS_ONCE(shinfo->gso_size) for example), but the bug is TCP stack.

We have identified two points where skb_unclone() was needed.

This patch adds a WARN_ON_ONCE() to warn us if we missed another
fix of this kind.

Kudos to Neal for finding the root cause of this bug. Its visible
using small MSS.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Willy Tarreau <w@1wt.eu>

include/linux/skbuff.h

@@ -641,6 +641,16 @@ static inline int skb_cloned(const struct sk_buff *skb)
 	       (atomic_read(&skb_shinfo(skb)->dataref) & SKB_DATAREF_MASK) != 1;
 }
 
+static inline int skb_unclone(struct sk_buff *skb, gfp_t pri)
+{
+	might_sleep_if(pri & __GFP_WAIT);
+
+	if (skb_cloned(skb))
+		return pskb_expand_head(skb, 0, 0, pri);
+
+	return 0;
+}
+
 /**
  *	skb_header_cloned - is the header a clone
  *	@skb: buffer to check

net/ipv4/tcp_output.c

@@ -744,6 +744,9 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
 static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb,
 				 unsigned int mss_now)
 {
+	/* Make sure we own this skb before messing gso_size/gso_segs */
+	WARN_ON_ONCE(skb_cloned(skb));
+
 	if (skb->len <= mss_now || !sk_can_gso(sk) ||
 	    skb->ip_summed == CHECKSUM_NONE) {
 		/* Avoid the costly divide in the normal
@@ -824,9 +827,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 	if (nsize < 0)
 		nsize = 0;
 
-	if (skb_cloned(skb) &&
-	    skb_is_nonlinear(skb) &&
-	    pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+	if (skb_unclone(skb, GFP_ATOMIC))
 		return -ENOMEM;
 
 	/* Get a new skb... force flag on. */
@@ -1932,6 +1933,8 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		int oldpcount = tcp_skb_pcount(skb);
 
 		if (unlikely(oldpcount > 1)) {
+			if (skb_unclone(skb, GFP_ATOMIC))
+				return -ENOMEM;
 			tcp_init_tso_segs(sk, skb, cur_mss);
 			tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb));
 		}