From 8272c58d085e5611a7f839fa32e148ae62446375 Mon Sep 17 00:00:00 2001

From: Jason Baron <jbaron@akamai.com>

Date: Thu, 14 Jul 2016 11:38:40 -0400

Subject: [PATCH] tcp: enable per-socket rate limiting of all 'challenge acks'

The per-socket rate limit for 'challenge acks' was introduced in the

context of limiting ack loops:

commit f2b2c582e824 ("tcp: mitigate ACK loops for connections as tcp_sock")

And I think it can be extended to rate limit all 'challenge acks' on a

per-socket basis.

Since we have the global tcp_challenge_ack_limit, this patch allows for

tcp_challenge_ack_limit to be set to a large value and effectively rely on

the per-socket limit, or set tcp_challenge_ack_limit to a lower value and

still prevents a single connections from consuming the entire challenge ack

quota.

It further moves in the direction of eliminating the global limit at some

point, as Eric Dumazet has suggested. This a follow-up to:

Subject: tcp: make challenge acks less predictable

Cc: Eric Dumazet <edumazet@google.com>

Cc: David S. Miller <davem@davemloft.net>

Cc: Neal Cardwell <ncardwell@google.com>

Cc: Yuchung Cheng <ycheng@google.com>

Cc: Yue Cao <ycao009@ucr.edu>

Signed-off-by: Jason Baron <jbaron@akamai.com>

Signed-off-by: David S. Miller <davem@davemloft.net>

---

 net/ipv4/tcp_input.c | 39 ++++++++++++++++++++++-----------------

 1 file changed, 22 insertions(+), 17 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c

index 8c011359646b..796315104ad7 100644

--- a/net/ipv4/tcp_input.c

+++ b/net/ipv4/tcp_input.c

@@ -3423,6 +3423,23 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32

 	return flag;

 }

+static bool __tcp_oow_rate_limited(struct net *net, int mib_idx,

+				   u32 *last_oow_ack_time)

+{

+	if (*last_oow_ack_time) {

+		s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time);

+

+		if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {

+			NET_INC_STATS(net, mib_idx);

+			return true;	/* rate-limited: don't send yet! */

+		}

+	}

+

+	*last_oow_ack_time = tcp_time_stamp;

+

+	return false;	/* not rate-limited: go ahead, send dupack now! */

+}

+

 /* Return true if we're currently rate-limiting out-of-window ACKs and

  * thus shouldn't send a dupack right now. We rate-limit dupacks in

  * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS

@@ -3436,21 +3453,9 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb,

 	/* Data packets without SYNs are not likely part of an ACK loop. */

 	if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) &&

 	    !tcp_hdr(skb)->syn)

-		goto not_rate_limited;

-

-	if (*last_oow_ack_time) {

-		s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time);

-

-		if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) {

-			NET_INC_STATS_BH(net, mib_idx);

-			return true;	/* rate-limited: don't send yet! */

-		}

-	}

-

-	*last_oow_ack_time = tcp_time_stamp;

+		return false;

-not_rate_limited:

-	return false;	/* not rate-limited: go ahead, send dupack now! */

+	return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time);

 }

 /* RFC 5961 7 [ACK Throttling] */

@@ -3463,9 +3468,9 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)

 	u32 count, now;

 	/* First check our per-socket dupack rate limit. */

-	if (tcp_oow_rate_limited(sock_net(sk), skb,

-				 LINUX_MIB_TCPACKSKIPPEDCHALLENGE,

-				 &tp->last_oow_ack_time))

+	if (__tcp_oow_rate_limited(sock_net(sk),

+				   LINUX_MIB_TCPACKSKIPPEDCHALLENGE,

+				   &tp->last_oow_ack_time))

 		return;

 	/* Then check host-wide RFC 5961 rate limit. */

-- 

2.7.4