[PATCH bpf-next v5 06/11] bpf: Add sock_ops RTO callback

[Lawrence Brakmo]

Adds an optional call to sock_ops BPF program based on whether the
BPF_SOCK_OPS_RTO_CB_FLAG is set in bpf_sock_ops_flags.
The BPF program is passed 2 arguments: icsk_retransmits and whether the
RTO has expired.

Signed-off-by: Lawrence Brakmo <bra...@fb.com>
---
 include/uapi/linux/bpf.h | 5 +++++
 include/uapi/linux/tcp.h | 3 +++
 net/ipv4/tcp_timer.c     | 7 +++++++
 3 files changed, 15 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 78de185..e74a91b 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1001,6 +1001,11 @@ enum {
                                         * a congestion threshold. RTTs above
                                         * this indicate congestion
                                         */
+       BPF_SOCK_OPS_RTO_CB,            /* Called when an RTO has triggered.
+                                        * Arg1: value of icsk_retransmits
+                                        * Arg2: value of icsk_rto
+                                        * Arg3: whether RTO has expired
+                                        */
 };
 
 #define TCP_BPF_IW             1001    /* Set TCP initial congestion window */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index b4a4f64..089c19e 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -259,6 +259,9 @@ struct tcp_md5sig {
        __u8    tcpm_key[TCP_MD5SIG_MAXKEYLEN];         /* key (binary) */
 };
 
+/* Definitions for bpf_sock_ops_flags */
+#define BPF_SOCK_OPS_RTO_CB_FLAG       (1<<0)
+
 /* INET_DIAG_MD5SIG */
 struct tcp_diag_md5sig {
        __u8    tcpm_family;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 6db3124..257abdd 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -213,11 +213,18 @@ static int tcp_write_timeout(struct sock *sk)
                                                icsk->icsk_user_timeout);
        }
        tcp_fastopen_active_detect_blackhole(sk, expired);
+
+       if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG))
+               tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RTO_CB,
+                                 icsk->icsk_retransmits,
+                                 icsk->icsk_rto, (int)expired);
+
        if (expired) {
                /* Has it gone just too far? */
                tcp_write_err(sk);
                return 1;
        }
+
        return 0;
 }
 
-- 
2.9.5