netdev - [RFC PATCH 16/28] tcp: allow embedding leftover into option padding

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: <1584524289-24187-16-git-send-email-ilpo.jarvinen@helsinki.fi>
Date:   Wed, 18 Mar 2020 11:37:57 +0200
From:   Ilpo Järvinen <ilpo.jarvinen@...sinki.fi>
To:     netdev@...r.kernel.org
Cc:     Yuchung Cheng <ycheng@...gle.com>,
        Neal Cardwell <ncardwell@...gle.com>,
        Eric Dumazet <eric.dumazet@...il.com>,
        Olivier Tilmans <olivier.tilmans@...ia-bell-labs.com>
Subject: [RFC PATCH 16/28] tcp: allow embedding leftover into option padding

From: Ilpo Järvinen <ilpo.jarvinen@...helsinki.fi>

There is some waste space in the option usage due to padding
of 32-bit fields. AccECN option can take advantage of those
few bytes as its tail is often consuming just a few odd bytes.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@...helsinki.fi>
---
 net/ipv4/tcp_output.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index adc22d0d75fd..9ff6d14363df 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -504,6 +504,8 @@ static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts)
 #endif
 }
 
+#define NOP_LEFTOVER	((TCPOPT_NOP << 8) | TCPOPT_NOP)
+
 /* Write previously computed TCP options to the packet.
  *
  * Beware: Something in the Internet is very sensitive to the ordering of
@@ -521,6 +523,8 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 			      struct tcp_out_options *opts)
 {
 	u16 options = opts->options;	/* mungable copy */
+	u16 leftover_bytes = NOP_LEFTOVER;	/* replace next NOPs if avail */
+	int leftover_size = 2;
 
 	if (unlikely(OPTION_MD5 & options)) {
 		*ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
@@ -554,17 +558,22 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 	}
 
 	if (unlikely(OPTION_SACK_ADVERTISE & options)) {
-		*ptr++ = htonl((TCPOPT_NOP << 24) |
-			       (TCPOPT_NOP << 16) |
+		*ptr++ = htonl((leftover_bytes << 16) |
 			       (TCPOPT_SACK_PERM << 8) |
 			       TCPOLEN_SACK_PERM);
+		leftover_bytes = NOP_LEFTOVER;
 	}
 
 	if (unlikely(OPTION_WSCALE & options)) {
-		*ptr++ = htonl((TCPOPT_NOP << 24) |
+		u8 highbyte = TCPOPT_NOP;
+
+		if (unlikely(leftover_size == 1))
+			highbyte = leftover_bytes >> 8;
+		*ptr++ = htonl((highbyte << 24) |
 			       (TCPOPT_WINDOW << 16) |
 			       (TCPOLEN_WINDOW << 8) |
 			       opts->ws);
+		leftover_bytes = NOP_LEFTOVER;
 	}
 
 	if (unlikely(opts->num_sack_blocks)) {
@@ -572,8 +581,7 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 			tp->duplicate_sack : tp->selective_acks;
 		int this_sack;
 
-		*ptr++ = htonl((TCPOPT_NOP  << 24) |
-			       (TCPOPT_NOP  << 16) |
+		*ptr++ = htonl((leftover_bytes << 16) |
 			       (TCPOPT_SACK <<  8) |
 			       (TCPOLEN_SACK_BASE + (opts->num_sack_blocks *
 						     TCPOLEN_SACK_PERBLOCK)));
@@ -585,6 +593,10 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
 		}
 
 		tp->rx_opt.dsack = 0;
+	} else if (unlikely(leftover_bytes != NOP_LEFTOVER)) {
+		*ptr++ = htonl((leftover_bytes << 16) |
+			       (TCPOPT_NOP << 8) |
+			       TCPOPT_NOP);
 	}
 
 	if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) {
-- 
2.20.1