bpf: Adds field bpf_sock_ops_cb_flags to tcp_sock

Adds field bpf_sock_ops_cb_flags to tcp_sock and bpf_sock_ops. Its primary
use is to determine if there should be calls to sock_ops bpf program at
various points in the TCP code. The field is initialized to zero,
disabling the calls. A sock_ops BPF program can set it, per connection and
as necessary, when the connection is established.

It also adds support for reading and writting the field within a
sock_ops BPF program. Reading is done by accessing the field directly.
However, writing is done through the helper function
bpf_sock_ops_cb_flags_set, in order to return an error if a BPF program
is trying to set a callback that is not supported in the current kernel
(i.e. running an older kernel). The helper function returns 0 if it was
able to set all of the bits set in the argument, a positive number
containing the bits that could not be set, or -EINVAL if the socket is
not a full TCP socket.

Examples of where one could call the bpf program:

1) When RTO fires
2) When a packet is retransmitted
3) When the connection terminates
4) When a packet is sent
5) When a packet is received

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

1 files changed, 34 insertions, 0 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index c356ec02b1a5..6936d19ac736 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3328,6 +3328,33 @@ static const struct bpf_func_proto bpf_getsockopt_proto = {
 	.arg5_type	= ARG_CONST_SIZE,
 };
 
+BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock,
+	   int, argval)
+{
+	struct sock *sk = bpf_sock->sk;
+	int val = argval & BPF_SOCK_OPS_ALL_CB_FLAGS;
+
+	if (!sk_fullsock(sk))
+		return -EINVAL;
+
+#ifdef CONFIG_INET
+	if (val)
+		tcp_sk(sk)->bpf_sock_ops_cb_flags = val;
+
+	return argval & (~BPF_SOCK_OPS_ALL_CB_FLAGS);
+#else
+	return -EINVAL;
+#endif
+}
+
+static const struct bpf_func_proto bpf_sock_ops_cb_flags_set_proto = {
+	.func		= bpf_sock_ops_cb_flags_set,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *
 bpf_base_func_proto(enum bpf_func_id func_id)
 {
@@ -3510,6 +3537,8 @@ static const struct bpf_func_proto *
 		return &bpf_setsockopt_proto;
 	case BPF_FUNC_getsockopt:
 		return &bpf_getsockopt_proto;
+	case BPF_FUNC_sock_ops_cb_flags_set:
+		return &bpf_sock_ops_cb_flags_set_proto;
 	case BPF_FUNC_sock_map_update:
 		return &bpf_sock_map_update_proto;
 	default:
@@ -4546,6 +4575,11 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 	case offsetof(struct bpf_sock_ops, srtt_us):
 		SOCK_OPS_GET_FIELD(srtt_us, srtt_us, struct tcp_sock);
 		break;
+
+	case offsetof(struct bpf_sock_ops, bpf_sock_ops_cb_flags):
+		SOCK_OPS_GET_FIELD(bpf_sock_ops_cb_flags, bpf_sock_ops_cb_flags,
+				   struct tcp_sock);
+		break;
 	}
 	return insn - insn_buf;
 }