diff mbox series

[net-next,19/44] tcp: allow embedding leftover into option padding

Message ID 20241015102940.26157-20-chia-yu.chang@nokia-bell-labs.com (mailing list archive)
State Changes Requested
Delegated to: Netdev Maintainers
Headers show
Series DualPI2, Accurate ECN, TCP Prague patch series | expand

Checks

Context Check Description
netdev/series_format fail Series longer than 15 patches
netdev/tree_selection success Clearly marked for net-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 5 this patch: 5
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers fail 4 maintainers not CCed: edumazet@google.com pabeni@redhat.com dsahern@kernel.org kuba@kernel.org
netdev/build_clang success Errors and warnings before: 5 this patch: 5
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 4 this patch: 4
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 61 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 1 this patch: 1
netdev/source_inline success Was 0 now: 0

Commit Message

Chia-Yu Chang (Nokia) Oct. 15, 2024, 10:29 a.m. UTC 
From: Ilpo Järvinen <ij@kernel.org>

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 <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
---
 net/ipv4/tcp_output.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)
diff mbox series

Patch

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ebda1b71d489..becaf0e2ffce 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -703,6 +703,8 @@  static __be32 *process_tcp_ao_options(struct tcp_sock *tp,
 	return ptr;
 }
 
+#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
@@ -722,7 +724,9 @@  static void tcp_options_write(struct tcphdr *th, struct tcp_sock *tp,
 			      struct tcp_key *key)
 {
 	__be32 *ptr = (__be32 *)(th + 1);
+	u16 leftover_bytes = NOP_LEFTOVER;	/* replace next NOPs if avail */
 	u16 options = opts->options;	/* mungable copy */
+	int leftover_size = 2;
 
 	if (tcp_key_is_md5(key)) {
 		*ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
@@ -757,17 +761,22 @@  static void tcp_options_write(struct tcphdr *th, 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)) {
@@ -775,8 +784,7 @@  static void tcp_options_write(struct tcphdr *th, 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)));
@@ -788,6 +796,10 @@  static void tcp_options_write(struct tcphdr *th, 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)) {