tcp: shrink per-packet memset in __tcp_transmit_skb()

Use struct_group() to group the three fields in tcp_out_options that are
read unconditionally by tcp_options_write() and bpf_skops_write_hdr_opt()
(mss, bpf_opt_len, num_sack_blocks), then replace the full-struct memset
with a targeted memset of only that group.

struct tcp_out_options is 40 bytes without MPTCP and 96 bytes with
CONFIG_MPTCP=y (typical distro config). Every remaining field is either
assigned before first use by tcp_established_options()/tcp_syn_options(),
or gated behind its OPTION_* flag in tcp_options_write(). This memset
runs on every transmitted TCP packet, so shrinking it from 96 (or 40)
bytes to 4 bytes reduces per-packet overhead on the hot path.

Assembly comparison (x86-64, GCC 13, CONFIG_MPTCP=y):

  Before: rep stos zeroing 96 bytes (5 instructions, 12 8-byte stores)
  After:  movl $0x0 zeroing 4 bytes (1 instruction, 1 store)

Also add opts->options = 0 at the top of tcp_syn_options(), which
already used |= without a prior clear. tcp_established_options() already
clears opts->options at its top.

Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Signed-off-by: Keita Morisaki <kmta1236@gmail.com>
Acked-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20260304111517.2088694-1-kmta1236@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This commit is contained in:
Keita Morisaki 2026-03-04 20:15:17 +09:00 committed by Jakub Kicinski
parent 752941e3fa
commit cfcceb7a39

View File

@ -429,14 +429,19 @@ static void smc_options_write(__be32 *ptr, u16 *options)
}
struct tcp_out_options {
/* Following group is cleared in __tcp_transmit_skb() */
struct_group(cleared,
u16 mss; /* 0 to disable */
u8 bpf_opt_len; /* length of BPF hdr option */
u8 num_sack_blocks; /* number of SACK blocks to include */
);
/* Caution: following fields are not cleared in __tcp_transmit_skb() */
u16 options; /* bit field of OPTION_* */
u16 mss; /* 0 to disable */
u8 ws; /* window scale, 0 to disable */
u8 num_sack_blocks; /* number of SACK blocks to include */
u8 num_accecn_fields:7, /* number of AccECN fields needed */
use_synack_ecn_bytes:1; /* Use synack_ecn_bytes or not */
u8 hash_size; /* bytes in hash_location */
u8 bpf_opt_len; /* length of BPF hdr option */
__u8 *hash_location; /* temporary pointer, overloaded */
__u32 tsval, tsecr; /* need to include OPTION_TS */
struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */
@ -965,6 +970,8 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
struct tcp_fastopen_request *fastopen = tp->fastopen_req;
bool timestamps;
opts->options = 0;
/* Better than switch (key.type) as it has static branches */
if (tcp_key_is_md5(key)) {
timestamps = false;
@ -1565,7 +1572,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
inet = inet_sk(sk);
tcb = TCP_SKB_CB(skb);
memset(&opts, 0, sizeof(opts));
memset(&opts.cleared, 0, sizeof(opts.cleared));
tcp_get_current_key(sk, &key);
if (unlikely(tcb->tcp_flags & TCPHDR_SYN)) {