[PATCH v2 bpf-next 09/11] bpf: Add BPF_SOCK_OPS_RETRANS_CB

[Lawrence Brakmo]

Adds support for calling sock_ops BPF program when there is a
retransmission. Two arguments are used; one for the sequence number and
other for the number of segments retransmitted. Does not include syn-ack
retransmissions.

New op: BPF_SOCK_OPS_RETRANS_CB.

Signed-off-by: Lawrence Brakmo <bra...@fb.com>
---
 include/uapi/linux/bpf.h | 4 ++++
 include/uapi/linux/tcp.h | 1 +
 net/ipv4/tcp_output.c    | 3 +++
 3 files changed, 8 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 5bead0e..415b951 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1020,6 +1020,10 @@ enum {
                                         * Arg2: value of icsk_rto
                                         * Arg3: whether RTO has expired
                                         */
+       BPF_SOCK_OPS_RETRANS_CB,        /* Called when skb is retransmitted.
+                                        * Arg1: sequence number of 1st byte
+                                        * Arg2: # segments
+                                        */
 };
 
 #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 089c19e..dc36d3c 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -261,6 +261,7 @@ struct tcp_md5sig {
 
 /* Definitions for bpf_sock_ops_flags */
 #define BPF_SOCK_OPS_RTO_CB_FLAG       (1<<0)
+#define BPF_SOCK_OPS_RETRANS_CB_FLAG   (1<<1)
 
 /* INET_DIAG_MD5SIG */
 struct tcp_diag_md5sig {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index b093985..8109675 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2907,6 +2907,9 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff 
*skb, int segs)
        if (likely(!err)) {
                TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
                trace_tcp_retransmit_skb(sk, skb);
+               if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG))
+                       tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_RETRANS_CB,
+                                         TCP_SKB_CB(skb)->seq, segs);
        } else if (err != -EBUSY) {
                NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL);
        }
-- 
2.9.5