diff options
| author | Eric Dumazet <edumazet@google.com> | 2025-10-20 11:44:03 -0400 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2025-10-23 16:20:45 +0200 |
| commit | bcdbf4d7d9138d57ac33fe80242e308f587a1b36 (patch) | |
| tree | cec867d97382df2f96c669918482ddfe1875ba58 | |
| parent | f620d9ba4a099d6bd8909586270e04d64a5affb0 (diff) | |
| download | linux-bcdbf4d7d9138d57ac33fe80242e308f587a1b36.tar.gz linux-bcdbf4d7d9138d57ac33fe80242e308f587a1b36.tar.bz2 linux-bcdbf4d7d9138d57ac33fe80242e308f587a1b36.zip | |
tcp: cache RTAX_QUICKACK metric in a hot cache line
[ Upstream commit 15492700ac41459b54a6683490adcee350ab11e3 ]
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>
Stable-dep-of: 833d4313bc1e ("mptcp: reset blackhole on success with non-loopback ifaces")
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
| -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 4bd93571e6c1..bcc138ff087b 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -116,7 +116,8 @@ 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 d392cb37a864..b5723adab4eb 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2547,8 +2547,12 @@ 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 4c8d84fc27ca..1d9e93a04930 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -331,9 +331,8 @@ 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)); } |