From: Lawrence Brakmo <brakmo@fb.com>
Date: Fri, 30 Jun 2017 20:02:42 -0700
Subject: bpf: Support for per connection SYN/SYN-ACK RTOs
Patch-mainline: v4.13-rc1
Git-commit: 8550f328f45db6d37981eb2041bc465810245c03
References: bsc#1109837
This patch adds support for setting a per connection SYN and
SYN_ACK RTOs from within a BPF_SOCK_OPS program. For example,
to set small RTOs when it is known both hosts are within a
datacenter.
Signed-off-by: Lawrence Brakmo <brakmo@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Acked-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
---
include/net/tcp.h | 11 +++++++++++
include/uapi/linux/bpf.h | 3 +++
net/ipv4/tcp_input.c | 3 ++-
net/ipv4/tcp_output.c | 2 +-
4 files changed, 17 insertions(+), 2 deletions(-)
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2053,4 +2053,15 @@ static inline int tcp_call_bpf(struct so
}
#endif
+static inline u32 tcp_timeout_init(struct sock *sk)
+{
+ int timeout;
+
+ timeout = tcp_call_bpf(sk, BPF_SOCK_OPS_TIMEOUT_INIT);
+
+ if (timeout <= 0)
+ timeout = TCP_TIMEOUT_INIT;
+ return timeout;
+}
+
#endif /* _TCP_H */
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -745,6 +745,9 @@ struct bpf_sock_ops {
*/
enum {
BPF_SOCK_OPS_VOID,
+ BPF_SOCK_OPS_TIMEOUT_INIT, /* Should return SYN-RTO value to use or
+ * -1 if default value should be used
+ */
};
#endif /* _UAPI__LINUX_BPF_H__ */
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6404,7 +6404,8 @@ int tcp_conn_request(struct request_sock
} else {
tcp_rsk(req)->tfo_listener = false;
if (!want_cookie)
- inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+ inet_csk_reqsk_queue_hash_add(sk, req,
+ tcp_timeout_init((struct sock *)req));
af_ops->send_synack(sk, dst, &fl, req, &foc,
!want_cookie ? TCP_SYNACK_NORMAL :
TCP_SYNACK_COOKIE);
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -3328,7 +3328,7 @@ static void tcp_connect_init(struct sock
tp->rcv_wup = tp->rcv_nxt;
tp->copied_seq = tp->rcv_nxt;
- inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
+ inet_csk(sk)->icsk_rto = tcp_timeout_init(sk);
inet_csk(sk)->icsk_retransmits = 0;
tcp_clear_retrans(tp);
}