From: Geliang Tang <tanggeliang@kylinos.cn>

It's necessary to traverse all subflows on the conn_list of an MPTCP
socket and then call kfunc to modify the fields of each subflow. In
kernel space, mptcp_for_each_subflow() helper is used for this:

	mptcp_for_each_subflow(msk, subflow)
		kfunc(subflow);

But in the MPTCP BPF program, this has not yet been implemented. As
Martin suggested recently, this conn_list walking + modify-by-kfunc
usage fits the bpf_iter use case. So this patch adds a new bpf_iter
type named "mptcp_subflow" to do this and implements its helpers
bpf_iter_mptcp_subflow_new()/_next()/_destroy().

Since these bpf_iter mptcp_subflow helpers are invoked in its selftest
in a ftrace hook for mptcp_sched_get_send(), it's necessary to register
them into a BPF_PROG_TYPE_TRACING type kfunc set together with other
two used kfuncs mptcp_subflow_active() and mptcp_subflow_set_scheduled().

Then bpf_for_each() for mptcp_subflow can be used in BPF program like
this:

	bpf_rcu_read_lock();
	bpf_for_each(mptcp_subflow, subflow, msk)
		kfunc(subflow);
	bpf_rcu_read_unlock();

Suggested-by: Martin KaFai Lau <martin.lau@kernel.org>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
---
 net/mptcp/bpf.c | 54 ++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 49 insertions(+), 5 deletions(-)

diff --git a/net/mptcp/bpf.c b/net/mptcp/bpf.c
index 6414824402e6..0b7a0c2634c4 100644
--- a/net/mptcp/bpf.c
+++ b/net/mptcp/bpf.c
@@ -201,9 +201,48 @@ static const struct btf_kfunc_id_set bpf_mptcp_fmodret_set = {
 	.set   = &bpf_mptcp_fmodret_ids,
 };
 
-__diag_push();
-__diag_ignore_all("-Wmissing-prototypes",
-		  "kfuncs which will be used in BPF programs");
+struct bpf_iter_mptcp_subflow {
+	__u64 __opaque[2];
+} __attribute__((aligned(8)));
+
+struct bpf_iter_mptcp_subflow_kern {
+	struct mptcp_sock *msk;
+	struct list_head *pos;
+} __attribute__((aligned(8)));
+
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_iter_mptcp_subflow_new(struct bpf_iter_mptcp_subflow *it,
+					   struct mptcp_sock *msk)
+{
+	struct bpf_iter_mptcp_subflow_kern *kit = (void *)it;
+
+	if (!msk)
+		return -EINVAL;
+
+	kit->msk = msk;
+	kit->pos = &msk->conn_list;
+	return 0;
+}
+
+__bpf_kfunc struct mptcp_subflow_context *
+bpf_iter_mptcp_subflow_next(struct bpf_iter_mptcp_subflow *it)
+{
+	struct bpf_iter_mptcp_subflow_kern *kit = (void *)it;
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_sock *msk = kit->msk;
+
+	subflow = list_entry((kit->pos)->next, struct mptcp_subflow_context, node);
+	if (!msk || list_entry_is_head(subflow, &msk->conn_list, node))
+		return NULL;
+
+	kit->pos = &subflow->node;
+	return subflow;
+}
+
+__bpf_kfunc void bpf_iter_mptcp_subflow_destroy(struct bpf_iter_mptcp_subflow *it)
+{
+}
 
 __bpf_kfunc struct mptcp_subflow_context *
 bpf_mptcp_subflow_ctx_by_pos(const struct mptcp_sched_data *data, unsigned int pos)
@@ -218,12 +257,15 @@ __bpf_kfunc bool bpf_mptcp_subflow_queues_empty(struct sock *sk)
 	return tcp_rtx_queue_empty(sk);
 }
 
-__diag_pop();
+__bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(bpf_mptcp_sched_kfunc_ids)
+BTF_ID_FLAGS(func, bpf_iter_mptcp_subflow_new)
+BTF_ID_FLAGS(func, bpf_iter_mptcp_subflow_next)
+BTF_ID_FLAGS(func, bpf_iter_mptcp_subflow_destroy)
+BTF_ID_FLAGS(func, mptcp_subflow_active)
 BTF_ID_FLAGS(func, mptcp_subflow_set_scheduled)
 BTF_ID_FLAGS(func, bpf_mptcp_subflow_ctx_by_pos)
-BTF_ID_FLAGS(func, mptcp_subflow_active)
 BTF_ID_FLAGS(func, mptcp_set_timeout)
 BTF_ID_FLAGS(func, mptcp_wnd_end)
 BTF_ID_FLAGS(func, tcp_stream_memory_free)
@@ -241,6 +283,8 @@ static int __init bpf_mptcp_kfunc_init(void)
 	int ret;
 
 	ret = register_btf_fmodret_id_set(&bpf_mptcp_fmodret_set);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_TRACING,
+					       &bpf_mptcp_sched_kfunc_set);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
 					       &bpf_mptcp_sched_kfunc_set);
 #ifdef CONFIG_BPF_JIT
-- 
2.43.0