[PATCH v5 bpf-next 5/6] bpf: tcp: Support arbitrary SYN Cookie.

[Kuniyuki Iwashima <kuniyu@amazon.com>]

This patch adds a new kfunc available at TC hook to support arbitrary
SYN Cookie.

The basic usage is as follows:

    struct tcp_cookie_attributes attr = {
        .tcp_opt = {
            .mss_clamp = mss,
            .wscale_ok = wscale_ok,
            .rcv_scale = recv_scale, /* Server's WScale < 15 */
            .snd_scale = send_scale, /* Client's WScale < 15 */
            .tstamp_ok = tstamp_ok,
            .rcv_tsval = tsval,
            .rcv_tsecr = tsecr,
            .sack_ok = sack_ok,
        },
        .ecn_ok = ecn_ok,
        .usec_ts_ok = usec_ts_ok,
    };

    skc = bpf_skc_lookup_tcp(...);
    sk = (struct sock *)bpf_skc_to_tcp_sock(skc);
    bpf_sk_assign_tcp_reqsk(skb, sk, attr, sizeof(attr));
    bpf_sk_release(skc);

bpf_sk_assign_tcp_reqsk() takes skb, a listener sk, and struct
tcp_cookie_attributes and allocates reqsk and configures it.  Then,
bpf_sk_assign_tcp_reqsk() links reqsk with skb and the listener.

The notable thing here is that we do not hold refcnt for both reqsk
and listener.  To differentiate that, we mark reqsk->syncookie, which
is only used in TX for now.  So, if reqsk->syncookie is 1 in RX, it
means that the reqsk is allocated by kfunc.

When skb is freed, sock_pfree() checks if reqsk->syncookie is 1,
and in that case, we set NULL to reqsk->rsk_listener before calling
reqsk_free() as reqsk does not hold a refcnt of the listener.

When the TCP stack looks up a socket from the skb, we steal the
listener from the reqsk in skb_steal_sock() and create a full sk
in cookie_v[46]_check().

The refcnt of reqsk will finally be set to 1 in tcp_get_cookie_sock()
after creating a full sk.

Note that we can use the unused bits in struct tcp_options_received
and extend struct tcp_cookie_attributes in the future when we add a
new attribute that is determined in 3WHS.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
---
 include/net/tcp.h |   6 +++
 net/core/filter.c | 118 +++++++++++++++++++++++++++++++++++++++++++++-
 net/core/sock.c   |  14 +++++-
 3 files changed, 134 insertions(+), 4 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index b5d7149eb0f8..6e3ee9036ecb 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -600,6 +600,12 @@ static inline bool cookie_ecn_ok(const struct net *net, const struct dst_entry *
 }
 
 #if IS_ENABLED(CONFIG_BPF)
+struct tcp_cookie_attributes {
+	struct tcp_options_received tcp_opt;
+	bool ecn_ok;
+	bool usec_ts_ok;
+} __packed;
+
 static inline bool cookie_bpf_ok(struct sk_buff *skb)
 {
 	return skb->sk;
diff --git a/net/core/filter.c b/net/core/filter.c
index adcfc2c25754..713feacb3ad3 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -11816,6 +11816,110 @@ __bpf_kfunc int bpf_sock_addr_set_sun_path(struct bpf_sock_addr_kern *sa_kern,
 
 	return 0;
 }
+
+__bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct sk_buff *skb, struct sock *sk,
+					struct tcp_cookie_attributes *attr,
+					int attr__sz)
+{
+#if IS_ENABLED(CONFIG_SYN_COOKIES)
+	const struct request_sock_ops *ops;
+	struct inet_request_sock *ireq;
+	struct tcp_request_sock *treq;
+	struct request_sock *req;
+	struct net *net;
+	__u16 min_mss;
+	u32 tsoff = 0;
+
+	if (attr__sz != sizeof(*attr) || attr->tcp_opt.unused)
+		return -EINVAL;
+
+	if (!sk)
+		return -EINVAL;
+
+	if (!skb_at_tc_ingress(skb))
+		return -EINVAL;
+
+	net = dev_net(skb->dev);
+	if (net != sock_net(sk))
+		return -ENETUNREACH;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		ops = &tcp_request_sock_ops;
+		min_mss = 536;
+		break;
+#if IS_BUILTIN(CONFIG_IPV6)
+	case htons(ETH_P_IPV6):
+		ops = &tcp6_request_sock_ops;
+		min_mss = IPV6_MIN_MTU - 60;
+		break;
+#endif
+	default:
+		return -EINVAL;
+	}
+
+	if (sk->sk_type != SOCK_STREAM || sk->sk_state != TCP_LISTEN)
+		return -EINVAL;
+
+	if (attr->tcp_opt.mss_clamp < min_mss)
+		return -EINVAL;
+
+	if (attr->tcp_opt.wscale_ok) {
+		if (!READ_ONCE(net->ipv4.sysctl_tcp_window_scaling))
+			return -EINVAL;
+
+		if (attr->tcp_opt.snd_wscale > TCP_MAX_WSCALE ||
+		    attr->tcp_opt.rcv_wscale > TCP_MAX_WSCALE)
+			return -EINVAL;
+	}
+
+	if (attr->tcp_opt.sack_ok && !READ_ONCE(net->ipv4.sysctl_tcp_sack))
+		return -EINVAL;
+
+	if (attr->tcp_opt.tstamp_ok) {
+		if (!READ_ONCE(net->ipv4.sysctl_tcp_timestamps))
+			return -EINVAL;
+
+		tsoff = attr->tcp_opt.rcv_tsecr -
+			tcp_ns_to_ts(attr->usec_ts_ok, tcp_clock_ns());
+	}
+
+	if (sk_is_mptcp(sk))
+		req = mptcp_subflow_reqsk_alloc(ops, sk, false);
+	else
+		req = inet_reqsk_alloc(ops, sk, false);
+
+	if (!req)
+		return -ENOMEM;
+
+	ireq = inet_rsk(req);
+	treq = tcp_rsk(req);
+
+	req->rsk_listener = sk;
+	req->syncookie = 1;
+	req->mss = attr->tcp_opt.mss_clamp;
+	req->ts_recent = attr->tcp_opt.rcv_tsval;
+
+	ireq->snd_wscale = attr->tcp_opt.snd_wscale;
+	ireq->rcv_wscale = attr->tcp_opt.rcv_wscale;
+	ireq->tstamp_ok	= attr->tcp_opt.tstamp_ok;
+	ireq->sack_ok = attr->tcp_opt.sack_ok;
+	ireq->wscale_ok = attr->tcp_opt.wscale_ok;
+	ireq->ecn_ok = attr->ecn_ok;
+
+	treq->req_usec_ts = attr->usec_ts_ok;
+	treq->ts_off = tsoff;
+
+	skb_orphan(skb);
+	skb->sk = req_to_sk(req);
+	skb->destructor = sock_pfree;
+
+	return 0;
+#else
+	return -EOPNOTSUPP;
+#endif
+}
+
 __bpf_kfunc_end_defs();
 
 int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
@@ -11844,6 +11948,10 @@ BTF_SET8_START(bpf_kfunc_check_set_sock_addr)
 BTF_ID_FLAGS(func, bpf_sock_addr_set_sun_path)
 BTF_SET8_END(bpf_kfunc_check_set_sock_addr)
 
+BTF_SET8_START(bpf_kfunc_check_set_tcp_reqsk)
+BTF_ID_FLAGS(func, bpf_sk_assign_tcp_reqsk)
+BTF_SET8_END(bpf_kfunc_check_set_tcp_reqsk)
+
 static const struct btf_kfunc_id_set bpf_kfunc_set_skb = {
 	.owner = THIS_MODULE,
 	.set = &bpf_kfunc_check_set_skb,
@@ -11859,6 +11967,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_sock_addr = {
 	.set = &bpf_kfunc_check_set_sock_addr,
 };
 
+static const struct btf_kfunc_id_set bpf_kfunc_set_tcp_reqsk = {
+	.owner = THIS_MODULE,
+	.set = &bpf_kfunc_check_set_tcp_reqsk,
+};
+
 static int __init bpf_kfunc_init(void)
 {
 	int ret;
@@ -11874,8 +11987,9 @@ static int __init bpf_kfunc_init(void)
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_LWT_SEG6LOCAL, &bpf_kfunc_set_skb);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_NETFILTER, &bpf_kfunc_set_skb);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp);
-	return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
-						&bpf_kfunc_set_sock_addr);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
+					       &bpf_kfunc_set_sock_addr);
+	return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk);
 }
 late_initcall(bpf_kfunc_init);
 
diff --git a/net/core/sock.c b/net/core/sock.c
index fef349dd72fa..998950e97dfe 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2579,8 +2579,18 @@ EXPORT_SYMBOL(sock_efree);
 #ifdef CONFIG_INET
 void sock_pfree(struct sk_buff *skb)
 {
-	if (sk_is_refcounted(skb->sk))
-		sock_gen_put(skb->sk);
+	struct sock *sk = skb->sk;
+
+	if (!sk_is_refcounted(sk))
+		return;
+
+	if (sk->sk_state == TCP_NEW_SYN_RECV && inet_reqsk(sk)->syncookie) {
+		inet_reqsk(sk)->rsk_listener = NULL;
+		reqsk_free(inet_reqsk(sk));
+		return;
+	}
+
+	sock_gen_put(sk);
 }
 EXPORT_SYMBOL(sock_pfree);
 #endif /* CONFIG_INET */
-- 
2.30.2