linux-kernel - [PATCH RESEND net-next v2 4/5] tcp: fix stretch ACK bugs in Veno

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1584340511-9870-5-git-send-email-yangpc@wangsu.com>
Date:   Mon, 16 Mar 2020 14:35:10 +0800
From:   Pengcheng Yang <yangpc@...gsu.com>
To:     edumazet@...gle.com, ncardwell@...gle.com, davem@...emloft.net
Cc:     netdev@...r.kernel.org, linux-kernel@...r.kernel.org,
        Pengcheng Yang <yangpc@...gsu.com>
Subject: [PATCH RESEND net-next v2 4/5] tcp: fix stretch ACK bugs in Veno

Change Veno to properly handle stretch ACKs in additive
increase mode by passing in the count of ACKed packets
to tcp_cong_avoid_ai().

Signed-off-by: Pengcheng Yang <yangpc@...gsu.com>
---
 net/ipv4/tcp_veno.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index 857491c..50a9a6e 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -154,8 +154,9 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 
 		if (tcp_in_slow_start(tp)) {
 			/* Slow start. */
-			tcp_slow_start(tp, acked);
-			goto done;
+			acked = tcp_slow_start(tp, acked);
+			if (!acked)
+				goto done;
 		}
 
 		/* Congestion avoidance. */
@@ -163,7 +164,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 			/* In the "non-congestive state", increase cwnd
 			 * every rtt.
 			 */
-			tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
+			tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked);
 		} else {
 			/* In the "congestive state", increase cwnd
 			 * every other rtt.
@@ -177,7 +178,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked)
 					veno->inc = 1;
 				tp->snd_cwnd_cnt = 0;
 			} else
-				tp->snd_cwnd_cnt++;
+				tp->snd_cwnd_cnt += acked;
 		}
 done:
 		if (tp->snd_cwnd < 2)
-- 
1.8.3.1