[PATCH v4 bpf-next 1/3] bpf: tcp: Handle BPF SYN Cookie in cookie_v[46]_check().

[Kuniyuki Iwashima <kuniyu@amazon.com>]

We will support arbitrary SYN Cookie with BPF in the following
patch.

If BPF prog validates ACK and kfunc allocates reqsk, it will
be carried to cookie_[46]_check() as skb->sk.  Then, we call
cookie_bpf_check() to validate the configuration passed to kfunc.

First, we clear skb->sk, skb->destructor, and req->rsk_listener,
which are needed not to hold refcnt for reqsk and the listener.
See the following patch for details.

Then, we parse TCP options to check if tstamp_ok is discrepant.
If it is invalid, we increment LINUX_MIB_SYNCOOKIESFAILED and send
RST.  If tstamp_ok is valid, we increment LINUX_MIB_SYNCOOKIESRECV.

After that, we check sack_ok and wscale_ok with corresponding
sysctl knobs.  If the test fails, we send RST but do not increment
LINUX_MIB_SYNCOOKIESFAILED.  This behaviour is the same with the
non-BPF cookie handling in cookie_tcp_check().

Finally, we finish initialisation for the remaining fields with
cookie_tcp_reqsk_init().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
---
 include/net/tcp.h     | 21 +++++++++++++++
 net/ipv4/syncookies.c | 62 +++++++++++++++++++++++++++++++++++++++++--
 net/ipv6/syncookies.c |  9 +++++--
 3 files changed, 88 insertions(+), 4 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 973555cb1d3f..842791997f30 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -590,6 +590,27 @@ static inline bool cookie_ecn_ok(const struct net *net, const struct dst_entry *
 		dst_feature(dst, RTAX_FEATURE_ECN);
 }
 
+#if IS_ENABLED(CONFIG_BPF)
+static inline bool cookie_bpf_ok(struct sk_buff *skb)
+{
+	return skb->sk;
+}
+
+struct request_sock *cookie_bpf_check(struct net *net, struct sock *sk,
+				      struct sk_buff *skb);
+#else
+static inline bool cookie_bpf_ok(struct sk_buff *skb)
+{
+	return false;
+}
+
+static inline struct request_sock *cookie_bpf_check(struct net *net, struct sock *sk,
+						    struct sk_buff *skb)
+{
+	return NULL;
+}
+#endif
+
 /* From net/ipv6/syncookies.c */
 int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th);
 struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 61f1c96cfe63..0f9c3aed2014 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -304,6 +304,59 @@ static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_BPF)
+struct request_sock *cookie_bpf_check(struct net *net, struct sock *sk,
+				      struct sk_buff *skb)
+{
+	struct request_sock *req = inet_reqsk(skb->sk);
+	struct inet_request_sock *ireq = inet_rsk(req);
+	struct tcp_request_sock *treq = tcp_rsk(req);
+	struct tcp_options_received tcp_opt;
+	int ret;
+
+	skb->sk = NULL;
+	skb->destructor = NULL;
+	req->rsk_listener = NULL;
+
+	memset(&tcp_opt, 0, sizeof(tcp_opt));
+	tcp_parse_options(net, skb, &tcp_opt, 0, NULL);
+
+	if (ireq->tstamp_ok ^ tcp_opt.saw_tstamp) {
+		__NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESFAILED);
+		goto reset;
+	}
+
+	__NET_INC_STATS(net, LINUX_MIB_SYNCOOKIESRECV);
+
+	if (ireq->tstamp_ok) {
+		if (!READ_ONCE(net->ipv4.sysctl_tcp_timestamps))
+			goto reset;
+
+		req->ts_recent = tcp_opt.rcv_tsval;
+		treq->ts_off = tcp_opt.rcv_tsecr - tcp_ns_to_ts(false, tcp_clock_ns());
+	}
+
+	if (ireq->sack_ok && !READ_ONCE(net->ipv4.sysctl_tcp_sack))
+		goto reset;
+
+	if (ireq->wscale_ok && !READ_ONCE(net->ipv4.sysctl_tcp_window_scaling))
+		goto reset;
+
+	ret = cookie_tcp_reqsk_init(sk, skb, req);
+	if (ret) {
+		reqsk_free(req);
+		req = NULL;
+	}
+
+	return req;
+
+reset:
+	reqsk_free(req);
+	return ERR_PTR(-EINVAL);
+}
+EXPORT_SYMBOL_GPL(cookie_bpf_check);
+#endif
+
 struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
 					    struct sock *sk, struct sk_buff *skb,
 					    struct tcp_options_received *tcp_opt,
@@ -404,7 +457,11 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 	    !th->ack || th->rst)
 		goto out;
 
-	req = cookie_tcp_check(net, sk, skb);
+	if (cookie_bpf_ok(skb))
+		req = cookie_bpf_check(net, sk, skb);
+	else
+		req = cookie_tcp_check(net, sk, skb);
+
 	if (IS_ERR(req))
 		goto out;
 	if (!req)
@@ -454,7 +511,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(&rt->dst, RTAX_INITRWND));
 
-	ireq->rcv_wscale  = rcv_wscale;
+	if (!req->syncookie)
+		ireq->rcv_wscale  = rcv_wscale;
 	ireq->ecn_ok &= cookie_ecn_ok(net, &rt->dst);
 
 	ret = tcp_get_cookie_sock(sk, skb, req, &rt->dst);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index c8d2ca27220c..24224138ba1a 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -182,7 +182,11 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 	    !th->ack || th->rst)
 		goto out;
 
-	req = cookie_tcp_check(net, sk, skb);
+	if (cookie_bpf_ok(skb))
+		req = cookie_bpf_check(net, sk, skb);
+	else
+		req = cookie_tcp_check(net, sk, skb);
+
 	if (IS_ERR(req))
 		goto out;
 	if (!req)
@@ -247,7 +251,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
 				  ireq->wscale_ok, &rcv_wscale,
 				  dst_metric(dst, RTAX_INITRWND));
 
-	ireq->rcv_wscale = rcv_wscale;
+	if (!req->syncookie)
+		ireq->rcv_wscale = rcv_wscale;
 	ireq->ecn_ok &= cookie_ecn_ok(net, dst);
 
 	ret = tcp_get_cookie_sock(sk, skb, req, dst);
-- 
2.30.2