tcp: mitigate ACK loops for connections as tcp_timewait_sock

Ensure that in state FIN_WAIT2 or TIME_WAIT, where the connection is
represented by a tcp_timewait_sock, we rate limit dupacks in response
to incoming packets (a) with TCP timestamps that fail PAWS checks, or
(b) with sequence numbers that are out of the acceptable window.

We do not send a dupack in response to out-of-window packets if it has
been less than sysctl_tcp_invalid_ratelimit (default 500ms) since we
last sent a dupack in response to an out-of-window packet.

Reported-by: Avery Fay <avery@mixpanel.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 66d85a80a1ec551d4dfbe44a4f7d1ee1fd97e7ee..1a7adb411647436feac207029d8e8efe19ac1193 100644 (file)
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -342,6 +342,10 @@ struct tcp_timewait_sock {
        u32                       tw_rcv_wnd;
        u32                       tw_ts_offset;
        u32                       tw_ts_recent;
+
+       /* The time we sent the last out-of-window ACK: */
+       u32                       tw_last_oow_ack_time;
+
        long                      tw_ts_recent_stamp;
 #ifdef CONFIG_TCP_MD5SIG
        struct tcp_md5sig_key     *tw_md5_key;

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 98a840561ec8638498703533b2662cdfb9134a5e..dd11ac7798c626d9abe3fbada06fadc99eafe378 100644 (file)
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -58,6 +58,25 @@ static bool tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win)
        return seq == e_win && seq == end_seq;
 }
 
+static enum tcp_tw_status
+tcp_timewait_check_oow_rate_limit(struct inet_timewait_sock *tw,
+                                 const struct sk_buff *skb, int mib_idx)
+{
+       struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
+
+       if (!tcp_oow_rate_limited(twsk_net(tw), skb, mib_idx,
+                                 &tcptw->tw_last_oow_ack_time)) {
+               /* Send ACK. Note, we do not put the bucket,
+                * it will be released by caller.
+                */
+               return TCP_TW_ACK;
+       }
+
+       /* We are rate-limiting, so just release the tw sock and drop skb. */
+       inet_twsk_put(tw);
+       return TCP_TW_SUCCESS;
+}
+
 /*
  * * Main purpose of TIME-WAIT state is to close connection gracefully,
  *   when one of ends sits in LAST-ACK or CLOSING retransmitting FIN
@@ -116,7 +135,8 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
                    !tcp_in_window(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq,
                                   tcptw->tw_rcv_nxt,
                                   tcptw->tw_rcv_nxt + tcptw->tw_rcv_wnd))
-                       return TCP_TW_ACK;
+                       return tcp_timewait_check_oow_rate_limit(
+                               tw, skb, LINUX_MIB_TCPACKSKIPPEDFINWAIT2);
 
                if (th->rst)
                        goto kill;
@@ -250,10 +270,8 @@ kill:
                        inet_twsk_schedule(tw, &tcp_death_row, TCP_TIMEWAIT_LEN,
                                           TCP_TIMEWAIT_LEN);
 
-               /* Send ACK. Note, we do not put the bucket,
-                * it will be released by caller.
-                */
-               return TCP_TW_ACK;
+               return tcp_timewait_check_oow_rate_limit(
+                       tw, skb, LINUX_MIB_TCPACKSKIPPEDTIMEWAIT);
        }
        inet_twsk_put(tw);
        return TCP_TW_SUCCESS;
@@ -289,6 +307,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
                tcptw->tw_ts_recent     = tp->rx_opt.ts_recent;
                tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp;
                tcptw->tw_ts_offset     = tp->tsoffset;
+               tcptw->tw_last_oow_ack_time = 0;
 
 #if IS_ENABLED(CONFIG_IPV6)
                if (tw->tw_family == PF_INET6) {