[PATCH 3.10 005/139] udp: consistently apply ufo or fragmentation

[Willy Tarreau]

From: Willem de Bruijn <willemb@xxxxxxxxxx>

commit 85f1bd9a7b5a79d5baa8bf44af19658f7bf77bfa upstream.

When iteratively building a UDP datagram with MSG_MORE and that
datagram exceeds MTU, consistently choose UFO or fragmentation.

Once skb_is_gso, always apply ufo. Conversely, once a datagram is
split across multiple skbs, do not consider ufo.

Sendpage already maintains the first invariant, only add the second.
IPv6 does not have a sendpage implementation to modify.

A gso skb must have a partial checksum, do not follow sk_no_check_tx
in udp_send_skb.

Found by syzkaller.

[gregkh - tweaks for 3.18 for ipv6, hopefully they are correct...]
[wt: s/skb_is_gso/skb_has_frags for 3.10]

Fixes: e89e9cf539a2 ("[IPv4/IPv6]: UFO Scatter-gather approach")
Reported-by: Andrey Konovalov <andreyknvl@xxxxxxxxxx>
Signed-off-by: Willem de Bruijn <willemb@xxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Willy Tarreau <w@xxxxxx>
---
 net/ipv4/ip_output.c  | 7 +++++--
 net/ipv4/udp.c        | 2 +-
 net/ipv6/ip6_output.c | 7 ++++---
 3 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 5f077ef..40faf48 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -846,10 +846,12 @@ static int __ip_append_data(struct sock *sk,
 		csummode = CHECKSUM_PARTIAL;
 
 	cork->length += length;
-	if (((length > mtu) || (skb && skb_has_frags(skb))) &&
+	if ((skb && skb_has_frags(skb)) ||
+	    ((length > mtu) &&
+	    (skb_queue_len(queue) <= 1) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
-	    (sk->sk_type == SOCK_DGRAM)) {
+	    (sk->sk_type == SOCK_DGRAM))) {
 		err = ip_ufo_append_data(sk, queue, getfrag, from, length,
 					 hh_len, fragheaderlen, transhdrlen,
 					 maxfraglen, flags);
@@ -1160,6 +1162,7 @@ ssize_t	ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
 
 	cork->length += size;
 	if ((size + skb->len > mtu) &&
+	    (skb_queue_len(&sk->sk_write_queue) == 1) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO)) {
 		skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 68174e4..882b23e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -763,7 +763,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
 	if (is_udplite)  				 /*     UDP-Lite      */
 		csum = udplite_csum(skb);
 
-	else if (sk->sk_no_check == UDP_CSUM_NOXMIT) {   /* UDP csum disabled */
+	else if (sk->sk_no_check == UDP_CSUM_NOXMIT && !skb_has_frags(skb)) {   /* UDP csum off */
 
 		skb->ip_summed = CHECKSUM_NONE;
 		goto send;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 17a88eb..3a65b9a 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1288,11 +1288,12 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
 
 	skb = skb_peek_tail(&sk->sk_write_queue);
 	cork->length += length;
-	if (((length > mtu) ||
-	     (skb && skb_has_frags(skb))) &&
+	if ((skb && skb_has_frags(skb)) ||
+	    (((length + fragheaderlen) > mtu) &&
+	    (skb_queue_len(&sk->sk_write_queue) <= 1) &&
 	    (sk->sk_protocol == IPPROTO_UDP) &&
 	    (rt->dst.dev->features & NETIF_F_UFO) &&
-	    (sk->sk_type == SOCK_DGRAM)) {
+	    (sk->sk_type == SOCK_DGRAM))) {
 		err = ip6_ufo_append_data(sk, getfrag, from, length,
 					  hh_len, fragheaderlen,
 					  transhdrlen, mtu, flags, rt);
-- 
2.8.0.rc2.1.gbe9624a