netdev - [PATCH net] tcp: Retain ECT bits for tos reflection

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-next>] [day] [month] [year] [list]

Date:   Tue,  8 Dec 2020 09:55:08 -0800
From:   Wei Wang <weiwan@...gle.com>
To:     Jakub Kicinski <kuba@...nel.org>,
        David Miller <davem@...emloft.net>, netdev@...r.kernel.org
Cc:     Alexander Duyck <alexanderduyck@...com>,
        Eric Dumazet <edumazet@...gle.com>
Subject: [PATCH net] tcp: Retain ECT bits for tos reflection

For DCTCP, we have to retain the ECT bits set by the congestion control
algorithm on the socket when reflecting syn TOS in syn-ack, in order to
make ECN work properly.

Fixes: ac8f1710c12b ("tcp: reflect tos value received in SYN to the socket")
Reported-by: Alexander Duyck <alexanderduyck@...com>
Signed-off-by: Wei Wang <weiwan@...gle.com>
Reviewed-by: Eric Dumazet <edumazet@...gle.com>
---
 net/ipv4/tcp_ipv4.c | 7 +++++--
 net/ipv6/tcp_ipv6.c | 7 +++++--
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 8391aa29e7a4..595dcc3afac5 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -984,7 +984,8 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst,
 		__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
 
 		tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
-				tcp_rsk(req)->syn_tos & ~INET_ECN_MASK :
+				(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
+				(inet_sk(sk)->tos & INET_ECN_MASK) :
 				inet_sk(sk)->tos;
 
 		if (!INET_ECN_is_capable(tos) &&
@@ -1541,7 +1542,9 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 		inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen;
 	newinet->inet_id = prandom_u32();
 
-	/* Set ToS of the new socket based upon the value of incoming SYN. */
+	/* Set ToS of the new socket based upon the value of incoming SYN.
+	 * ECT bits are set later in tcp_init_transfer().
+	 */
 	if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
 		newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 992cbf3eb9e3..f676f176eb6b 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -528,7 +528,8 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst,
 			fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts));
 
 		tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
-				tcp_rsk(req)->syn_tos & ~INET_ECN_MASK :
+				(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
+				(np->tclass & INET_ECN_MASK) :
 				np->tclass;
 
 		if (!INET_ECN_is_capable(tclass) &&
@@ -1320,7 +1321,9 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 	if (np->repflow)
 		newnp->flow_label = ip6_flowlabel(ipv6_hdr(skb));
 
-	/* Set ToS of the new socket based upon the value of incoming SYN. */
+	/* Set ToS of the new socket based upon the value of incoming SYN.
+	 * ECT bits are set later in tcp_init_transfer().
+	 */
 	if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
 		newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
 
-- 
2.29.2.576.ga3fc446d84-goog