tcp: attach SYNACK messages to request sockets instead of listener
If a listen backlog is very big (to avoid syncookies), then
the listener sk->sk_wmem_alloc is the main source of false
sharing, as we need to touch it twice per SYNACK re-transmit
and TX completion.
(One SYN packet takes listener lock once, but up to 6 SYNACK
are generated)
By attaching the skb to the request socket, we remove this
source of contention.
Tested:
listen(fd, 10485760); // single listener (no SO_REUSEPORT)
16 RX/TX queue NIC
Sustain a SYNFLOOD attack of ~320,000 SYN per second,
Sending ~1,400,000 SYNACK per second.
Perf profiles now show listener spinlock being next bottleneck.
20.29% [kernel] [k] queued_spin_lock_slowpath
10.06% [kernel] [k] __inet_lookup_established
5.12% [kernel] [k] reqsk_timer_handler
3.22% [kernel] [k] get_next_timer_interrupt
3.00% [kernel] [k] tcp_make_synack
2.77% [kernel] [k] ipt_do_table
2.70% [kernel] [k] run_timer_softirq
2.50% [kernel] [k] ip_finish_output
2.04% [kernel] [k] cascade
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 225e956..a6be56d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -462,7 +462,8 @@
int tcp_connect(struct sock *sk);
struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
struct request_sock *req,
- struct tcp_fastopen_cookie *foc);
+ struct tcp_fastopen_cookie *foc,
+ bool attach_req);
int tcp_disconnect(struct sock *sk, int flags);
void tcp_finish_connect(struct sock *sk, struct sk_buff *skb);
@@ -1715,7 +1716,8 @@
__u32 (*init_seq)(const struct sk_buff *skb);
int (*send_synack)(const struct sock *sk, struct dst_entry *dst,
struct flowi *fl, struct request_sock *req,
- u16 queue_mapping, struct tcp_fastopen_cookie *foc);
+ u16 queue_mapping, struct tcp_fastopen_cookie *foc,
+ bool attach_req);
};
#ifdef CONFIG_SYN_COOKIES