Merge branch 'tcp-fastopen-ipv6'

Yuchung Cheng says:

====================
tcp: IPv6 support for fastopen server

This patch series add IPv6 support for fastopen server. To minimize
code duplication in IPv4 and IPv6, the current v4 only code is
refactored and common code is moved into net/ipv4/tcp_fastopen.c.

Also the current code uses a different function from
tcp_v4_send_synack() to send the first SYN-ACK in fastopen.
The new code eliminates this separate function by refactoring the
child-socket and syn-ack creation code.  After these refactoring
in the first four patches, we can easily add the fastopen code in
IPv6 by changing corresponding IPv6 functions.

Note Fast Open client already supports IPv6. This patch is for
the server-side (passive open) IPv6 support only.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/tcp.h

@@ -366,11 +366,6 @@ static inline bool tcp_passive_fastopen(const struct sock *sk)
 		tcp_sk(sk)->fastopen_rsk != NULL);
 }
 
-static inline bool fastopen_cookie_present(struct tcp_fastopen_cookie *foc)
-{
-	return foc->len != -1;
-}
-
 extern void tcp_sock_destruct(struct sock *sk);
 
 static inline int fastopen_init_queue(struct sock *sk, int backlog)

include/net/tcp.h

@@ -220,8 +220,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define	TFO_SERVER_ENABLE	2
 #define	TFO_CLIENT_NO_COOKIE	4	/* Data in SYN w/o cookie option */
 
-/* Process SYN data but skip cookie validation */
-#define	TFO_SERVER_COOKIE_NOT_CHKED	0x100
 /* Accept SYN data w/o any cookie option */
 #define	TFO_SERVER_COOKIE_NOT_REQD	0x200
 
@@ -230,10 +228,6 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
  */
 #define	TFO_SERVER_WO_SOCKOPT1	0x400
 #define	TFO_SERVER_WO_SOCKOPT2	0x800
-/* Always create TFO child sockets on a TFO listener even when
- * cookie/data not present. (For testing purpose!)
- */
-#define	TFO_SERVER_ALWAYS	0x1000
 
 extern struct inet_timewait_death_row tcp_death_row;
 
@@ -1120,6 +1114,9 @@ static inline void tcp_openreq_init(struct request_sock *req,
 	ireq->ir_num = ntohs(tcp_hdr(skb)->dest);
 }
 
+extern void tcp_openreq_init_rwin(struct request_sock *req,
+				  struct sock *sk, struct dst_entry *dst);
+
 void tcp_enter_memory_pressure(struct sock *sk);
 
 static inline int keepalive_intvl_when(const struct tcp_sock *tp)
@@ -1329,8 +1326,10 @@ void tcp_free_fastopen_req(struct tcp_sock *tp);
 
 extern struct tcp_fastopen_context __rcu *tcp_fastopen_ctx;
 int tcp_fastopen_reset_cipher(void *key, unsigned int len);
-void tcp_fastopen_cookie_gen(__be32 src, __be32 dst,
-			     struct tcp_fastopen_cookie *foc);
+bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
+		      struct request_sock *req,
+		      struct tcp_fastopen_cookie *foc,
+		      struct dst_entry *dst);
 void tcp_fastopen_init_key_once(bool publish);
 #define TCP_FASTOPEN_KEY_LENGTH 16
 

net/ipv4/tcp_fastopen.c

@@ -72,25 +72,224 @@ error:		kfree(ctx);
 	return err;
 }
 
-/* Computes the fastopen cookie for the IP path.
- * The path is a 128 bits long (pad with zeros for IPv4).
- *
- * The caller must check foc->len to determine if a valid cookie
- * has been generated successfully.
-*/
-void tcp_fastopen_cookie_gen(__be32 src, __be32 dst,
-			     struct tcp_fastopen_cookie *foc)
+static bool __tcp_fastopen_cookie_gen(const void *path,
+				      struct tcp_fastopen_cookie *foc)
 {
-	__be32 path[4] = { src, dst, 0, 0 };
 	struct tcp_fastopen_context *ctx;
+	bool ok = false;
 
 	tcp_fastopen_init_key_once(true);
 
 	rcu_read_lock();
 	ctx = rcu_dereference(tcp_fastopen_ctx);
 	if (ctx) {
-		crypto_cipher_encrypt_one(ctx->tfm, foc->val, (__u8 *)path);
+		crypto_cipher_encrypt_one(ctx->tfm, foc->val, path);
 		foc->len = TCP_FASTOPEN_COOKIE_SIZE;
+		ok = true;
 	}
 	rcu_read_unlock();
+	return ok;
+}
+
+/* Generate the fastopen cookie by doing aes128 encryption on both
+ * the source and destination addresses. Pad 0s for IPv4 or IPv4-mapped-IPv6
+ * addresses. For the longer IPv6 addresses use CBC-MAC.
+ *
+ * XXX (TFO) - refactor when TCP_FASTOPEN_COOKIE_SIZE != AES_BLOCK_SIZE.
+ */
+static bool tcp_fastopen_cookie_gen(struct request_sock *req,
+				    struct sk_buff *syn,
+				    struct tcp_fastopen_cookie *foc)
+{
+	if (req->rsk_ops->family == AF_INET) {
+		const struct iphdr *iph = ip_hdr(syn);
+
+		__be32 path[4] = { iph->saddr, iph->daddr, 0, 0 };
+		return __tcp_fastopen_cookie_gen(path, foc);
+	}
+
+#if IS_ENABLED(CONFIG_IPV6)
+	if (req->rsk_ops->family == AF_INET6) {
+		const struct ipv6hdr *ip6h = ipv6_hdr(syn);
+		struct tcp_fastopen_cookie tmp;
+
+		if (__tcp_fastopen_cookie_gen(&ip6h->saddr, &tmp)) {
+			struct in6_addr *buf = (struct in6_addr *) tmp.val;
+			int i = 4;
+
+			for (i = 0; i < 4; i++)
+				buf->s6_addr32[i] ^= ip6h->daddr.s6_addr32[i];
+			return __tcp_fastopen_cookie_gen(buf, foc);
+		}
+	}
+#endif
+	return false;
+}
+
+static bool tcp_fastopen_create_child(struct sock *sk,
+				      struct sk_buff *skb,
+				      struct dst_entry *dst,
+				      struct request_sock *req)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
+	struct sock *child;
+
+	req->num_retrans = 0;
+	req->num_timeout = 0;
+	req->sk = NULL;
+
+	child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL);
+	if (child == NULL)
+		return false;
+
+	spin_lock(&queue->fastopenq->lock);
+	queue->fastopenq->qlen++;
+	spin_unlock(&queue->fastopenq->lock);
+
+	/* Initialize the child socket. Have to fix some values to take
+	 * into account the child is a Fast Open socket and is created
+	 * only out of the bits carried in the SYN packet.
+	 */
+	tp = tcp_sk(child);
+
+	tp->fastopen_rsk = req;
+	/* Do a hold on the listner sk so that if the listener is being
+	 * closed, the child that has been accepted can live on and still
+	 * access listen_lock.
+	 */
+	sock_hold(sk);
+	tcp_rsk(req)->listener = sk;
+
+	/* RFC1323: The window in SYN & SYN/ACK segments is never
+	 * scaled. So correct it appropriately.
+	 */
+	tp->snd_wnd = ntohs(tcp_hdr(skb)->window);
+
+	/* Activate the retrans timer so that SYNACK can be retransmitted.
+	 * The request socket is not added to the SYN table of the parent
+	 * because it's been added to the accept queue directly.
+	 */
+	inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
+				  TCP_TIMEOUT_INIT, TCP_RTO_MAX);
+
+	/* Add the child socket directly into the accept queue */
+	inet_csk_reqsk_queue_add(sk, req, child);
+
+	/* Now finish processing the fastopen child socket. */
+	inet_csk(child)->icsk_af_ops->rebuild_header(child);
+	tcp_init_congestion_control(child);
+	tcp_mtup_init(child);
+	tcp_init_metrics(child);
+	tcp_init_buffer_space(child);
+
+	/* Queue the data carried in the SYN packet. We need to first
+	 * bump skb's refcnt because the caller will attempt to free it.
+	 *
+	 * XXX (TFO) - we honor a zero-payload TFO request for now,
+	 * (any reason not to?) but no need to queue the skb since
+	 * there is no data. How about SYN+FIN?
+	 */
+	if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1) {
+		skb = skb_get(skb);
+		skb_dst_drop(skb);
+		__skb_pull(skb, tcp_hdr(skb)->doff * 4);
+		skb_set_owner_r(skb, child);
+		__skb_queue_tail(&child->sk_receive_queue, skb);
+		tp->syn_data_acked = 1;
+	}
+	tcp_rsk(req)->rcv_nxt = tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+	sk->sk_data_ready(sk);
+	bh_unlock_sock(child);
+	sock_put(child);
+	WARN_ON(req->sk == NULL);
+	return true;
+}
+EXPORT_SYMBOL(tcp_fastopen_create_child);
+
+static bool tcp_fastopen_queue_check(struct sock *sk)
+{
+	struct fastopen_queue *fastopenq;
+
+	/* Make sure the listener has enabled fastopen, and we don't
+	 * exceed the max # of pending TFO requests allowed before trying
+	 * to validating the cookie in order to avoid burning CPU cycles
+	 * unnecessarily.
+	 *
+	 * XXX (TFO) - The implication of checking the max_qlen before
+	 * processing a cookie request is that clients can't differentiate
+	 * between qlen overflow causing Fast Open to be disabled
+	 * temporarily vs a server not supporting Fast Open at all.
+	 */
+	fastopenq = inet_csk(sk)->icsk_accept_queue.fastopenq;
+	if (fastopenq == NULL || fastopenq->max_qlen == 0)
+		return false;
+
+	if (fastopenq->qlen >= fastopenq->max_qlen) {
+		struct request_sock *req1;
+		spin_lock(&fastopenq->lock);
+		req1 = fastopenq->rskq_rst_head;
+		if ((req1 == NULL) || time_after(req1->expires, jiffies)) {
+			spin_unlock(&fastopenq->lock);
+			NET_INC_STATS_BH(sock_net(sk),
+					 LINUX_MIB_TCPFASTOPENLISTENOVERFLOW);
+			return false;
+		}
+		fastopenq->rskq_rst_head = req1->dl_next;
+		fastopenq->qlen--;
+		spin_unlock(&fastopenq->lock);
+		reqsk_free(req1);
+	}
+	return true;
+}
+
+/* Returns true if we should perform Fast Open on the SYN. The cookie (foc)
+ * may be updated and return the client in the SYN-ACK later. E.g., Fast Open
+ * cookie request (foc->len == 0).
+ */
+bool tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
+		      struct request_sock *req,
+		      struct tcp_fastopen_cookie *foc,
+		      struct dst_entry *dst)
+{
+	struct tcp_fastopen_cookie valid_foc = { .len = -1 };
+	bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
+
+	if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) &&
+	      (syn_data || foc->len >= 0) &&
+	      tcp_fastopen_queue_check(sk))) {
+		foc->len = -1;
+		return false;
+	}
+
+	if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD))
+		goto fastopen;
+
+	if (tcp_fastopen_cookie_gen(req, skb, &valid_foc) &&
+	    foc->len == TCP_FASTOPEN_COOKIE_SIZE &&
+	    foc->len == valid_foc.len &&
+	    !memcmp(foc->val, valid_foc.val, foc->len)) {
+		/* Cookie is valid. Create a (full) child socket to accept
+		 * the data in SYN before returning a SYN-ACK to ack the
+		 * data. If we fail to create the socket, fall back and
+		 * ack the ISN only but includes the same cookie.
+		 *
+		 * Note: Data-less SYN with valid cookie is allowed to send
+		 * data in SYN_RECV state.
+		 */
+fastopen:
+		if (tcp_fastopen_create_child(sk, skb, dst, req)) {
+			foc->len = -1;
+			NET_INC_STATS_BH(sock_net(sk),
+					 LINUX_MIB_TCPFASTOPENPASSIVE);
+			return true;
+		}
+	}
+
+	NET_INC_STATS_BH(sock_net(sk), foc->len ?
+			 LINUX_MIB_TCPFASTOPENPASSIVEFAIL :
+			 LINUX_MIB_TCPFASTOPENCOOKIEREQD);
+	*foc = valid_foc;
+	return false;
 }
+EXPORT_SYMBOL(tcp_try_fastopen);