[PATCH v5 bpf-next 09/10] bpf: tcp: Add kfunc to adjust sk->sk_rcvlowat.

[Kuniyuki Iwashima <kuniyu@google.com>]

bpf_tcp_ops.{enqueue,dequeue}_rcvq() were added to parse skb and
adjust sk->sk_rcvlowat dynamically to suppress unnecessary wakeups.

Let's add a new kfunc to set sk->sk_rcvlowat.

Negative values are clamped to INT_MAX, consistent with SO_RCVLOWAT.

For enqueue_rcvq(), wakeup is set to false because:

  * tcp_data_ready() is always called after the hooks in
    tcp_queue_rcv() and tcp_ofo_queue().

  * when tcp_fastopen_add_skb() is called for TFO SYN, the socket is
    not yet accept()ed, and when called for TFO SYN+ACK, the socket
    is woken up by sk->sk_state_change() anyway.

For dequeue_rcvq(), wakeup is set to true because tcp_data_ready()
is not called in that path.

An alternative would be to support bpf_setsockopt() for these
hooks.

However, that approach involves excessive conditionals and an
unnecessary memcpy(), costs we do not want to pay for every skb
in the TCP fast path.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Tested-by: Clément Léger <cleger@meta.com>
Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
Reviewed-by: Amery Hung <ameryhung@gmail.com>
---
 net/ipv4/bpf_tcp_ops.c | 46 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/net/ipv4/bpf_tcp_ops.c b/net/ipv4/bpf_tcp_ops.c
index 8182037c4269..2ba73dd6c52c 100644
--- a/net/ipv4/bpf_tcp_ops.c
+++ b/net/ipv4/bpf_tcp_ops.c
@@ -361,12 +361,31 @@ __bpf_kfunc int bpf_tcp_ops_set_flags(struct tcp_sock *tp, u32 enable, u32 disab
 	return 0;
 }
 
+__bpf_kfunc int bpf_tcp_ops_set_rcvlowat(struct sock *sk, int rcvlowat,
+					 const struct bpf_prog_aux *aux)
+{
+	u32 moff = aux->attach_st_ops_member_off;
+	bool wakeup = false;
+
+	if (moff == offsetof(struct bpf_tcp_ops, dequeue_rcvq))
+		wakeup = true;
+
+	if (rcvlowat < 0)
+		rcvlowat = INT_MAX;
+
+	return __tcp_set_rcvlowat(sk, rcvlowat, wakeup);
+}
+
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(bpf_tcp_ops_set_flags_kfunc_set)
 BTF_ID_FLAGS(func, bpf_tcp_ops_set_flags)
 BTF_KFUNCS_END(bpf_tcp_ops_set_flags_kfunc_set)
 
+BTF_KFUNCS_START(bpf_tcp_ops_set_rcvlowat_kfunc_set)
+BTF_ID_FLAGS(func, bpf_tcp_ops_set_rcvlowat, KF_IMPLICIT_ARGS)
+BTF_KFUNCS_END(bpf_tcp_ops_set_rcvlowat_kfunc_set)
+
 static int bpf_tcp_ops_set_flags_kfunc_filter(const struct bpf_prog *prog,
 					      u32 kfunc_id)
 {
@@ -390,6 +409,31 @@ static const struct btf_kfunc_id_set bpf_tcp_ops_set_flags_kfunc_id_set = {
 	.filter = bpf_tcp_ops_set_flags_kfunc_filter,
 };
 
+static int bpf_tcp_ops_set_rcvlowat_kfunc_filter(const struct bpf_prog *prog,
+						 u32 kfunc_id)
+{
+	u32 moff;
+
+	if (!btf_id_set8_contains(&bpf_tcp_ops_set_rcvlowat_kfunc_set, kfunc_id))
+		return 0;
+
+	if (prog->aux->st_ops != &bpf_tcp_ops)
+		return -EACCES;
+
+	moff = prog->aux->attach_st_ops_member_off;
+	if (moff != offsetof(struct bpf_tcp_ops, enqueue_rcvq) &&
+	    moff != offsetof(struct bpf_tcp_ops, dequeue_rcvq))
+		return -EACCES;
+
+	return 0;
+}
+
+static const struct btf_kfunc_id_set bpf_tcp_ops_set_rcvlowat_kfunc_id_set = {
+	.owner = THIS_MODULE,
+	.set = &bpf_tcp_ops_set_rcvlowat_kfunc_set,
+	.filter = bpf_tcp_ops_set_rcvlowat_kfunc_filter,
+};
+
 static int __init __bpf_tcp_ops_init(void)
 {
 	int ret;
@@ -399,6 +443,8 @@ static int __init __bpf_tcp_ops_init(void)
 	/* BPF_PROG_TYPE_CGROUP_{SOCKOPT,SKB} share BTF_KFUNC_HOOK_CGROUP. */
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCKOPT,
 					       &bpf_tcp_ops_set_flags_kfunc_id_set);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
+					       &bpf_tcp_ops_set_rcvlowat_kfunc_id_set);
 	ret = ret ?: register_bpf_struct_ops(&bpf_tcp_ops, bpf_tcp_ops);
 
 	return ret;
-- 
2.56.0.360.g66cac248cb-goog