bpf: Add BPF_SOCK_OPS_RETRANS_CB

Adds support for calling sock_ops BPF program when there is a
retransmission. Three arguments are used; one for the sequence number,
another for the number of segments retransmitted, and the last one for
the return value of tcp_transmit_skb (0 => success).
Does not include syn-ack retransmissions.

New op: BPF_SOCK_OPS_RETRANS_CB.

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 46520eae37fa9a6161c97af356909574be8cfe23..31c93a0bdbc296a3461e792ebc66752cfac76631 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1005,7 +1005,8 @@ struct bpf_sock_ops {
 
 /* Definitions for bpf_sock_ops_cb_flags */
 #define BPF_SOCK_OPS_RTO_CB_FLAG       (1<<0)
-#define BPF_SOCK_OPS_ALL_CB_FLAGS       0x1            /* Mask of all currently
+#define BPF_SOCK_OPS_RETRANS_CB_FLAG   (1<<1)
+#define BPF_SOCK_OPS_ALL_CB_FLAGS       0x3            /* Mask of all currently
                                                         * supported cb flags
                                                         */
 
@@ -1047,6 +1048,12 @@ 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
+                                        * Arg3: return value of
+                                        *       tcp_transmit_skb (0 => success)
+                                        */
 };
 
 #define TCP_BPF_IW             1001    /* Set TCP initial congestion window */

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d12f7f71c1c404710a3a5cbe2e1e3f5fdbbed379..e9f985e42405a38fc95980da5debb7ac8b51fbb5 100644 (file)
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2905,6 +2905,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
                err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
        }
 
+       if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG))
+               tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB,
+                                 TCP_SKB_CB(skb)->seq, segs, err);
+
        if (likely(!err)) {
                TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
                trace_tcp_retransmit_skb(sk, skb);