---

yaml
---
r: 327761
b: refs/heads/master
c: 8336886
h: refs/heads/master
i:
  327759: 3e4a83b
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 1046716368979dee857a2b8a91c4a8833f21b9cb
+refs/heads/master: 8336886f786fdacbc19b719c1f7ea91eb70706d4

trunk/include/net/request_sock.h

@@ -226,19 +226,6 @@ static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue
 	return req;
 }
 
-static inline struct sock *reqsk_queue_get_child(struct request_sock_queue *queue,
-						 struct sock *parent)
-{
-	struct request_sock *req = reqsk_queue_remove(queue);
-	struct sock *child = req->sk;
-
-	WARN_ON(child == NULL);
-
-	sk_acceptq_removed(parent);
-	__reqsk_free(req);
-	return child;
-}
-
 static inline int reqsk_queue_removed(struct request_sock_queue *queue,
 				      struct request_sock *req)
 {

trunk/include/net/tcp.h

@@ -424,7 +424,8 @@ extern enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *
 						     const struct tcphdr *th);
 extern struct sock * tcp_check_req(struct sock *sk,struct sk_buff *skb,
 				   struct request_sock *req,
-				   struct request_sock **prev);
+				   struct request_sock **prev,
+				   bool fastopen);
 extern int tcp_child_process(struct sock *parent, struct sock *child,
 			     struct sk_buff *skb);
 extern bool tcp_use_frto(struct sock *sk);
@@ -478,7 +479,8 @@ extern int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr,
 extern int tcp_connect(struct sock *sk);
 extern struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 					struct request_sock *req,
-					struct request_values *rvp);
+					struct request_values *rvp,
+					struct tcp_fastopen_cookie *foc);
 extern int tcp_disconnect(struct sock *sk, int flags);
 
 void tcp_connect_init(struct sock *sk);

trunk/net/core/request_sock.c

@@ -15,6 +15,7 @@
 #include <linux/random.h>
 #include <linux/slab.h>
 #include <linux/string.h>
+#include <linux/tcp.h>
 #include <linux/vmalloc.h>
 
 #include <net/request_sock.h>
@@ -130,3 +131,97 @@ void reqsk_queue_destroy(struct request_sock_queue *queue)
 		kfree(lopt);
 }
 
+/*
+ * This function is called to set a Fast Open socket's "fastopen_rsk" field
+ * to NULL when a TFO socket no longer needs to access the request_sock.
+ * This happens only after 3WHS has been either completed or aborted (e.g.,
+ * RST is received).
+ *
+ * Before TFO, a child socket is created only after 3WHS is completed,
+ * hence it never needs to access the request_sock. things get a lot more
+ * complex with TFO. A child socket, accepted or not, has to access its
+ * request_sock for 3WHS processing, e.g., to retransmit SYN-ACK pkts,
+ * until 3WHS is either completed or aborted. Afterwards the req will stay
+ * until either the child socket is accepted, or in the rare case when the
+ * listener is closed before the child is accepted.
+ *
+ * In short, a request socket is only freed after BOTH 3WHS has completed
+ * (or aborted) and the child socket has been accepted (or listener closed).
+ * When a child socket is accepted, its corresponding req->sk is set to
+ * NULL since it's no longer needed. More importantly, "req->sk == NULL"
+ * will be used by the code below to determine if a child socket has been
+ * accepted or not, and the check is protected by the fastopenq->lock
+ * described below.
+ *
+ * Note that fastopen_rsk is only accessed from the child socket's context
+ * with its socket lock held. But a request_sock (req) can be accessed by
+ * both its child socket through fastopen_rsk, and a listener socket through
+ * icsk_accept_queue.rskq_accept_head. To protect the access a simple spin
+ * lock per listener "icsk->icsk_accept_queue.fastopenq->lock" is created.
+ * only in the rare case when both the listener and the child locks are held,
+ * e.g., in inet_csk_listen_stop() do we not need to acquire the lock.
+ * The lock also protects other fields such as fastopenq->qlen, which is
+ * decremented by this function when fastopen_rsk is no longer needed.
+ *
+ * Note that another solution was to simply use the existing socket lock
+ * from the listener. But first socket lock is difficult to use. It is not
+ * a simple spin lock - one must consider sock_owned_by_user() and arrange
+ * to use sk_add_backlog() stuff. But what really makes it infeasible is the
+ * locking hierarchy violation. E.g., inet_csk_listen_stop() may try to
+ * acquire a child's lock while holding listener's socket lock. A corner
+ * case might also exist in tcp_v4_hnd_req() that will trigger this locking
+ * order.
+ *
+ * When a TFO req is created, it needs to sock_hold its listener to prevent
+ * the latter data structure from going away.
+ *
+ * This function also sets "treq->listener" to NULL and unreference listener
+ * socket. treq->listener is used by the listener so it is protected by the
+ * fastopenq->lock in this function.
+ */
+void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
+			   bool reset)
+{
+	struct sock *lsk = tcp_rsk(req)->listener;
+	struct fastopen_queue *fastopenq =
+	    inet_csk(lsk)->icsk_accept_queue.fastopenq;
+
+	BUG_ON(!spin_is_locked(&sk->sk_lock.slock) && !sock_owned_by_user(sk));
+
+	tcp_sk(sk)->fastopen_rsk = NULL;
+	spin_lock_bh(&fastopenq->lock);
+	fastopenq->qlen--;
+	tcp_rsk(req)->listener = NULL;
+	if (req->sk)	/* the child socket hasn't been accepted yet */
+		goto out;
+
+	if (!reset || lsk->sk_state != TCP_LISTEN) {
+		/* If the listener has been closed don't bother with the
+		 * special RST handling below.
+		 */
+		spin_unlock_bh(&fastopenq->lock);
+		sock_put(lsk);
+		reqsk_free(req);
+		return;
+	}
+	/* Wait for 60secs before removing a req that has triggered RST.
+	 * This is a simple defense against TFO spoofing attack - by
+	 * counting the req against fastopen.max_qlen, and disabling
+	 * TFO when the qlen exceeds max_qlen.
+	 *
+	 * For more details see CoNext'11 "TCP Fast Open" paper.
+	 */
+	req->expires = jiffies + 60*HZ;
+	if (fastopenq->rskq_rst_head == NULL)
+		fastopenq->rskq_rst_head = req;
+	else
+		fastopenq->rskq_rst_tail->dl_next = req;
+
+	req->dl_next = NULL;
+	fastopenq->rskq_rst_tail = req;
+	fastopenq->qlen++;
+out:
+	spin_unlock_bh(&fastopenq->lock);
+	sock_put(lsk);
+	return;
+}

trunk/net/ipv4/af_inet.c

@@ -149,6 +149,11 @@ void inet_sock_destruct(struct sock *sk)
 		pr_err("Attempt to release alive inet socket %p\n", sk);
 		return;
 	}
+	if (sk->sk_type == SOCK_STREAM) {
+		struct fastopen_queue *fastopenq =
+			inet_csk(sk)->icsk_accept_queue.fastopenq;
+		kfree(fastopenq);
+	}
 
 	WARN_ON(atomic_read(&sk->sk_rmem_alloc));
 	WARN_ON(atomic_read(&sk->sk_wmem_alloc));
@@ -212,6 +217,26 @@ int inet_listen(struct socket *sock, int backlog)
 	 * we can only allow the backlog to be adjusted.
 	 */
 	if (old_state != TCP_LISTEN) {
+		/* Check special setups for testing purpose to enable TFO w/o
+		 * requiring TCP_FASTOPEN sockopt.
+		 * Note that only TCP sockets (SOCK_STREAM) will reach here.
+		 * Also fastopenq may already been allocated because this
+		 * socket was in TCP_LISTEN state previously but was
+		 * shutdown() (rather than close()).
+		 */
+		if ((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) != 0 &&
+		    inet_csk(sk)->icsk_accept_queue.fastopenq == NULL) {
+			if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) != 0)
+				err = fastopen_init_queue(sk, backlog);
+			else if ((sysctl_tcp_fastopen &
+				  TFO_SERVER_WO_SOCKOPT2) != 0)
+				err = fastopen_init_queue(sk,
+				    ((uint)sysctl_tcp_fastopen) >> 16);
+			else
+				err = 0;
+			if (err)
+				goto out;
+		}
 		err = inet_csk_listen_start(sk, backlog);
 		if (err)
 			goto out;
@@ -701,7 +726,8 @@ int inet_accept(struct socket *sock, struct socket *newsock, int flags)
 
 	sock_rps_record_flow(sk2);
 	WARN_ON(!((1 << sk2->sk_state) &
-		  (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE)));
+		  (TCPF_ESTABLISHED | TCPF_SYN_RECV |
+		  TCPF_CLOSE_WAIT | TCPF_CLOSE)));
 
 	sock_graft(sk2, newsock);
 

trunk/net/ipv4/inet_connection_sock.c

@@ -283,7 +283,9 @@ static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
 struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
 	struct sock *newsk;
+	struct request_sock *req;
 	int error;
 
 	lock_sock(sk);
@@ -296,7 +298,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
 		goto out_err;
 
 	/* Find already established connection */
-	if (reqsk_queue_empty(&icsk->icsk_accept_queue)) {
+	if (reqsk_queue_empty(queue)) {
 		long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
 
 		/* If this is a non blocking socket don't sleep */
@@ -308,14 +310,32 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
 		if (error)
 			goto out_err;
 	}
-
-	newsk = reqsk_queue_get_child(&icsk->icsk_accept_queue, sk);
-	WARN_ON(newsk->sk_state == TCP_SYN_RECV);
+	req = reqsk_queue_remove(queue);
+	newsk = req->sk;
+
+	sk_acceptq_removed(sk);
+	if (sk->sk_type == SOCK_STREAM && queue->fastopenq != NULL) {
+		spin_lock_bh(&queue->fastopenq->lock);
+		if (tcp_rsk(req)->listener) {
+			/* We are still waiting for the final ACK from 3WHS
+			 * so can't free req now. Instead, we set req->sk to
+			 * NULL to signify that the child socket is taken
+			 * so reqsk_fastopen_remove() will free the req
+			 * when 3WHS finishes (or is aborted).
+			 */
+			req->sk = NULL;
+			req = NULL;
+		}
+		spin_unlock_bh(&queue->fastopenq->lock);
+	}
 out:
 	release_sock(sk);
+	if (req)
+		__reqsk_free(req);
 	return newsk;
 out_err:
 	newsk = NULL;
+	req = NULL;
 	*err = error;
 	goto out;
 }
@@ -720,13 +740,14 @@ EXPORT_SYMBOL_GPL(inet_csk_listen_start);
 void inet_csk_listen_stop(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct request_sock_queue *queue = &icsk->icsk_accept_queue;
 	struct request_sock *acc_req;
 	struct request_sock *req;
 
 	inet_csk_delete_keepalive_timer(sk);
 
 	/* make all the listen_opt local to us */
-	acc_req = reqsk_queue_yank_acceptq(&icsk->icsk_accept_queue);
+	acc_req = reqsk_queue_yank_acceptq(queue);
 
 	/* Following specs, it would be better either to send FIN
 	 * (and enter FIN-WAIT-1, it is normal close)
@@ -736,7 +757,7 @@ void inet_csk_listen_stop(struct sock *sk)
 	 * To be honest, we are not able to make either
 	 * of the variants now.			--ANK
 	 */
-	reqsk_queue_destroy(&icsk->icsk_accept_queue);
+	reqsk_queue_destroy(queue);
 
 	while ((req = acc_req) != NULL) {
 		struct sock *child = req->sk;
@@ -754,6 +775,19 @@ void inet_csk_listen_stop(struct sock *sk)
 
 		percpu_counter_inc(sk->sk_prot->orphan_count);
 
+		if (sk->sk_type == SOCK_STREAM && tcp_rsk(req)->listener) {
+			BUG_ON(tcp_sk(child)->fastopen_rsk != req);
+			BUG_ON(sk != tcp_rsk(req)->listener);
+
+			/* Paranoid, to prevent race condition if
+			 * an inbound pkt destined for child is
+			 * blocked by sock lock in tcp_v4_rcv().
+			 * Also to satisfy an assertion in
+			 * tcp_v4_destroy_sock().
+			 */
+			tcp_sk(child)->fastopen_rsk = NULL;
+			sock_put(sk);
+		}
 		inet_csk_destroy_sock(child);
 
 		bh_unlock_sock(child);
@@ -763,6 +797,17 @@ void inet_csk_listen_stop(struct sock *sk)
 		sk_acceptq_removed(sk);
 		__reqsk_free(req);
 	}
+	if (queue->fastopenq != NULL) {
+		/* Free all the reqs queued in rskq_rst_head. */
+		spin_lock_bh(&queue->fastopenq->lock);
+		acc_req = queue->fastopenq->rskq_rst_head;
+		queue->fastopenq->rskq_rst_head = NULL;
+		spin_unlock_bh(&queue->fastopenq->lock);
+		while ((req = acc_req) != NULL) {
+			acc_req = req->dl_next;
+			__reqsk_free(req);
+		}
+	}
 	WARN_ON(sk->sk_ack_backlog);
 }
 EXPORT_SYMBOL_GPL(inet_csk_listen_stop);

trunk/net/ipv4/syncookies.c

@@ -319,6 +319,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
 	ireq->tstamp_ok		= tcp_opt.saw_tstamp;
 	req->ts_recent		= tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
 	treq->snt_synack	= tcp_opt.saw_tstamp ? tcp_opt.rcv_tsecr : 0;
+	treq->listener		= NULL;
 
 	/* We throwed the options of the initial SYN away, so we hope
 	 * the ACK carries the same options again (see RFC1122 4.2.3.8)