diff options
| author | Eric Dumazet <edumazet@google.com> | 2025-03-12 08:39:07 +0000 |
|---|---|---|
| committer | Paolo Abeni <pabeni@redhat.com> | 2025-03-18 13:44:59 +0100 |
| commit | 15492700ac41459b54a6683490adcee350ab11e3 (patch) | |
| tree | 647a127cb5c0e71727b4fdfee02830fb4353edc2 | |
| parent | 3c6b97a9d52031804b40e956a63994ea5513aae8 (diff) | |
| download | linux-15492700ac41459b54a6683490adcee350ab11e3.tar.gz linux-15492700ac41459b54a6683490adcee350ab11e3.tar.bz2 linux-15492700ac41459b54a6683490adcee350ab11e3.zip | |
tcp: cache RTAX_QUICKACK metric in a hot cache line
tcp_in_quickack_mode() is called from input path for small packets.
It calls __sk_dst_get() which reads sk->sk_dst_cache which has been
put in sock_read_tx group (for good reasons).
Then dst_metric(dst, RTAX_QUICKACK) also needs extra cache line misses.
Cache RTAX_QUICKACK in icsk->icsk_ack.dst_quick_ack to no longer pull
these cache lines for the cases a delayed ACK is scheduled.
After this patch TCP receive path does not longer access sock_read_tx
group.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250312083907.1931644-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
| -rw-r--r-- | include/net/inet_connection_sock.h | 3 | ||||
| -rw-r--r-- | net/core/sock.c | 6 | ||||
| -rw-r--r-- | net/ipv4/tcp_input.c | 3 |
3 files changed, 8 insertions, 4 deletions
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index d9978ffacc97..f736d3097e43 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -117,7 +117,8 @@ struct inet_connection_sock { #define ATO_BITS 8 __u32 ato:ATO_BITS, /* Predicted tick of soft clock */ lrcv_flowlabel:20, /* last received ipv6 flowlabel */ - unused:4; + dst_quick_ack:1, /* cache dst RTAX_QUICKACK */ + unused:3; unsigned long timeout; /* Currently scheduled timeout */ __u32 lrcvtime; /* timestamp of last received data packet */ __u16 last_seg_size; /* Size of last incoming segment */ diff --git a/net/core/sock.c b/net/core/sock.c index a0598518ce89..323892066def 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2565,8 +2565,12 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst) u32 max_segs = 1; sk->sk_route_caps = dst->dev->features; - if (sk_is_tcp(sk)) + if (sk_is_tcp(sk)) { + struct inet_connection_sock *icsk = inet_csk(sk); + sk->sk_route_caps |= NETIF_F_GSO; + icsk->icsk_ack.dst_quick_ack = dst_metric(dst, RTAX_QUICKACK); + } if (sk->sk_route_caps & NETIF_F_GSO) sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE; if (unlikely(sk->sk_gso_disabled)) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5c270cf96678..72382ee4456d 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -334,9 +334,8 @@ static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) static bool tcp_in_quickack_mode(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); - const struct dst_entry *dst = __sk_dst_get(sk); - return (dst && dst_metric(dst, RTAX_QUICKACK)) || + return icsk->icsk_ack.dst_quick_ack || (icsk->icsk_ack.quick && !inet_csk_in_pingpong_mode(sk)); } |