tcp: be more careful in tcp_fragment()

BugLink: https://bugs.launchpad.net/bugs/1840335

[ Upstream commit b617158d ]

Some applications set tiny SO_SNDBUF values and expect
TCP to just work. Recent patches to address CVE-2019-11478
broke them in case of losses, since retransmits might
be prevented.

We should allow these flows to make progress.

This patch allows the first and last skb in retransmit queue
to be split even if memory limits are hit.

It also adds the some room due to the fact that tcp_sendmsg()
and tcp_sendpage() might overshoot sk_wmem_queued by about one full
TSO skb (64KB size). Note this allowance was already present
in stable backports for kernels < 4.15

Note for < 4.15 backports :
 tcp_rtx_queue_tail() will probably look like :

static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk)
{
	struct sk_buff *skb = tcp_send_head(sk);

	return skb ? tcp_write_queue_prev(sk, skb) : tcp_write_queue_tail(sk);
}

Fixes: f070ef2a ("tcp: tcp_fragment() should apply sane memory limits")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Andrew Prout <aprout@ll.mit.edu>
Tested-by: Andrew Prout <aprout@ll.mit.edu>
Tested-by: Jonathan Lemon <jonathan.lemon@gmail.com>
Tested-by: Michal Kubecek <mkubecek@suse.cz>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Christoph Paasch <cpaasch@apple.com>
Cc: Jonathan Looney <jtl@netflix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Connor Kuehl <connor.kuehl@canonical.com>
Signed-off-by: Kleber Sacilotto de Souza <kleber.souza@canonical.com>

include/net/tcp.h

@@ -1526,6 +1526,23 @@ static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unli
 		tcp_sk(sk)->highest_sack = NULL;
 }
 
+static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk)
+{
+	struct sk_buff *skb = tcp_write_queue_head(sk);
+
+	if (skb == tcp_send_head(sk))
+		skb = NULL;
+
+	return skb;
+}
+
+static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk)
+{
+	struct sk_buff *skb = tcp_send_head(sk);
+
+	return skb ? tcp_write_queue_prev(sk, skb) : tcp_write_queue_tail(sk);
+}
+
 static inline void __tcp_add_write_queue_tail(struct sock *sk, struct sk_buff *skb)
 {
 	__skb_queue_tail(&sk->sk_write_queue, skb);

net/ipv4/tcp_output.c

@@ -1153,6 +1153,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *buff;
 	int nsize, old_factor;
+	long limit;
 	int nlen;
 	u8 flags;
 
@@ -1163,8 +1164,15 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 	if (nsize < 0)
 		nsize = 0;
 
-	if (unlikely((sk->sk_wmem_queued >> 1) > sk->sk_sndbuf &&
-		     skb != tcp_send_head(sk))) {
+	/* tcp_sendmsg() can overshoot sk_wmem_queued by one full size skb.
+	 * We need some allowance to not penalize applications setting small
+	 * SO_SNDBUF values.
+	 * Also allow first and last skb in retransmit queue to be split.
+	 */
+	limit = sk->sk_sndbuf + 2 * SKB_TRUESIZE(GSO_MAX_SIZE);
+	if (unlikely((sk->sk_wmem_queued >> 1) > limit &&
+		     skb != tcp_rtx_queue_head(sk) &&
+		     skb != tcp_rtx_queue_tail(sk))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG);
 		return -ENOMEM;
 	}