bpf: Add sock_ops RTO callback

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 <brakmo@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index aa12840..c8cecf9 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -982,7 +982,8 @@ struct bpf_sock_ops {
 };
 
 /* Definitions for bpf_sock_ops_cb_flags */
-#define BPF_SOCK_OPS_ALL_CB_FLAGS       0              /* Mask of all currently
+#define BPF_SOCK_OPS_RTO_CB_FLAG       (1<<0)
+#define BPF_SOCK_OPS_ALL_CB_FLAGS       0x1            /* Mask of all currently
                                                         * supported cb flags
                                                         */
 
@@ -1019,6 +1020,11 @@ 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/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 6db3124..257abdd 100644 (file)
--- 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;
 }