tcp: be more careful in tcp_fragment()

[ Upstream commit b617158dc096709d8600c53b6052144d12b89fab ]

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: f070ef2ac667 ("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: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 36fcd0ad051537583d4d722f5941516156beb16a..21a90fd17853bca1553759263f9084ca59072b25 100644 (file)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1679,6 +1679,11 @@ static inline struct sk_buff *tcp_rtx_queue_head(const struct sock *sk)
        return skb_rb_first(&sk->tcp_rtx_queue);
 }
 
+static inline struct sk_buff *tcp_rtx_queue_tail(const struct sock *sk)
+{
+       return skb_rb_last(&sk->tcp_rtx_queue);
+}
+
 static inline struct sk_buff *tcp_write_queue_head(const struct sock *sk)
 {
        return skb_peek(&sk->sk_write_queue);

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b8b4ae555e34c831723c9c061e62ac0657487ba2..32bd52e06ef1e1b185cc1853962f160315da5613 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1289,6 +1289,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
        struct tcp_sock *tp = tcp_sk(sk);
        struct sk_buff *buff;
        int nsize, old_factor;
+       long limit;
        int nlen;
        u8 flags;
 
@@ -1299,8 +1300,16 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
        if (nsize < 0)
                nsize = 0;
 
-       if (unlikely((sk->sk_wmem_queued >> 1) > sk->sk_sndbuf &&
-                    tcp_queue != TCP_FRAG_IN_WRITE_QUEUE)) {
+       /* 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 &&
+                    tcp_queue != TCP_FRAG_IN_WRITE_QUEUE &&
+                    skb != tcp_rtx_queue_head(sk) &&
+                    skb != tcp_rtx_queue_tail(sk))) {
                NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPWQUEUETOOBIG);
                return -ENOMEM;
        }