This patch implements the round-robin BPF MPTCP scheduler, named bpf_rr,
which always picks the next available subflow to send data. If no such
next subflow available, picks the first one.

Signed-off-by: Geliang Tang <geliang.tang@suse.com>
---
 tools/testing/selftests/bpf/bpf_tcp_helpers.h |  2 +
 .../selftests/bpf/progs/mptcp_bpf_rr.c        | 46 +++++++++++++++++++
 2 files changed, 48 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c

diff --git a/tools/testing/selftests/bpf/bpf_tcp_helpers.h b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
index 1b9dd8865ae2..480be2ea7d59 100644
--- a/tools/testing/selftests/bpf/bpf_tcp_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_tcp_helpers.h
@@ -237,6 +237,7 @@ struct mptcp_subflow_context {
 	__u32	token;
 	__u32	padding : 12,
 		backup : 1;
+	struct	sock *tcp_sock;	    /* tcp sk backpointer */
 } __attribute__((preserve_access_index));
 
 struct mptcp_sched_subflow {
@@ -263,6 +264,7 @@ struct mptcp_sched_ops {
 struct mptcp_sock {
 	struct inet_connection_sock	sk;
 
+	struct sock	*last_snd;
 	__u32		token;
 	struct sock	*first;
 	char		ca_name[TCP_CA_NAME_MAX];
diff --git a/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c b/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
new file mode 100644
index 000000000000..de0d893e08b4
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/mptcp_bpf_rr.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2022, SUSE. */
+
+#include <linux/bpf.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+SEC("struct_ops/mptcp_sched_rr_init")
+void BPF_PROG(mptcp_sched_rr_init, const struct mptcp_sock *msk)
+{
+}
+
+SEC("struct_ops/mptcp_sched_rr_release")
+void BPF_PROG(mptcp_sched_rr_release, const struct mptcp_sock *msk)
+{
+}
+
+void BPF_STRUCT_OPS(bpf_rr_get_subflow, const struct mptcp_sock *msk,
+		    struct mptcp_sched_data *data)
+{
+	int nr = 0;
+
+	for (int i = 0; i < MPTCP_SUBFLOWS_MAX; i++) {
+		if (!msk->last_snd || !data->subflows[i].context)
+			break;
+
+		if (data->subflows[i].context->tcp_sock == msk->last_snd) {
+			if (i + 1 == MPTCP_SUBFLOWS_MAX || !data->subflows[i + 1].context)
+				break;
+
+			nr = i + 1;
+			break;
+		}
+	}
+
+	data->subflows[nr].is_scheduled = 1;
+}
+
+SEC(".struct_ops")
+struct mptcp_sched_ops rr = {
+	.init		= (void *)mptcp_sched_rr_init,
+	.release	= (void *)mptcp_sched_rr_release,
+	.get_subflow	= (void *)bpf_rr_get_subflow,
+	.name		= "bpf_rr",
+};
-- 
2.34.1