TCP connection repair (v4)

index 43beaca..436f519 100644
@@ -664,7 +664,7 @@ static struct socket *drbd_wait_for_connect(struct drbd_conf *mdev)
 	timeo = mdev->net_conf->try_connect_int * HZ;
 	timeo += (random32() & 1) ? timeo / 7 : -timeo / 7; /* 28.5% random jitter */
 
-	s_listen->sk->sk_reuse    = 1; /* SO_REUSEADDR */
+	s_listen->sk->sk_reuse    = SK_CAN_REUSE; /* SO_REUSEADDR */
 	s_listen->sk->sk_rcvtimeo = timeo;
 	s_listen->sk->sk_sndtimeo = timeo;
 	drbd_setbufsize(s_listen, mdev->net_conf->sndbuf_size,

@@ -841,8 +841,8 @@ retry:
 		}
 	} while (1);
 
-	msock->sk->sk_reuse = 1; /* SO_REUSEADDR */
-	sock->sk->sk_reuse = 1; /* SO_REUSEADDR */
+	msock->sk->sk_reuse = SK_CAN_REUSE; /* SO_REUSEADDR */
+	sock->sk->sk_reuse = SK_CAN_REUSE; /* SO_REUSEADDR */
 
 	sock->sk->sk_allocation = GFP_NOIO;
 	msock->sk->sk_allocation = GFP_NOIO;

index 453a740..9220861 100644
@@ -662,7 +662,7 @@ iscsi_sw_tcp_conn_bind(struct iscsi_cls_session *cls_session,
 
 	/* setup Socket parameters */
 	sk = sock->sk;
-	sk->sk_reuse = 1;
+	sk->sk_reuse = SK_CAN_REUSE;
 	sk->sk_sndtimeo = 15 * HZ; /* FIXME: make it configurable */
 	sk->sk_allocation = GFP_ATOMIC;
 

index 3af1b2c..b9721c1 100644
@@ -2106,7 +2106,7 @@ static int r2net_open_listening_sock(__be32 addr, __be16 port)
 	r2net_listen_sock = sock;
 	INIT_WORK(&r2net_listen_work, r2net_accept_many);
 
-	sock->sk->sk_reuse = 1;
+	sock->sk->sk_reuse = SK_CAN_REUSE;
 	ret = sock->ops->bind(sock, (struct sockaddr *)&sin, sizeof(sin));
 	if (ret < 0) {
 		printk(KERN_ERR "ramster: Error %d while binding socket at "

index 044e7b5..1bfe880 100644
@@ -2005,7 +2005,7 @@ static int o2net_open_listening_sock(__be32 addr, __be16 port)
 	o2net_listen_sock = sock;
 	INIT_WORK(&o2net_listen_work, o2net_accept_many);
 
-	sock->sk->sk_reuse = 1;
+	sock->sk->sk_reuse = SK_CAN_REUSE;
 	ret = sock->ops->bind(sock, (struct sockaddr *)&sin, sizeof(sin));
 	if (ret < 0) {
 		printk(KERN_ERR "o2net: Error %d while binding socket at "

index a6ba1f8..4cdb9b3 100644
@@ -376,6 +376,17 @@ struct sock {
 	void                    (*sk_destruct)(struct sock *sk);
 };
 
+/*
+ * SK_CAN_REUSE and SK_NO_REUSE on a socket mean that the socket is OK
+ * or not whether his port will be reused by someone else. SK_FORCE_REUSE
+ * on a socket means that the socket will reuse everybody else's port
+ * without looking at the other's sk_reuse value.
+ */
+
+#define SK_NO_REUSE	0
+#define SK_CAN_REUSE	1
+#define SK_FORCE_REUSE	2
+
 static inline int sk_peek_offset(struct sock *sk, int flags)
 {
 	if ((flags & MSG_PEEK) && (sk->sk_peek_off >= 0))

index c7e60ea..679c5bb 100644
@@ -561,7 +561,7 @@ int sock_setsockopt(struct socket *sock, int level, int optname,
 			sock_valbool_flag(sk, SOCK_DBG, valbool);
 		break;
 	case SO_REUSEADDR:
-		sk->sk_reuse = valbool;
+		sk->sk_reuse = (valbool ? SK_CAN_REUSE : SK_NO_REUSE);
 		break;
 	case SO_TYPE:
 	case SO_PROTOCOL:

index 71b5edc..fa14ca7 100644
@@ -617,7 +617,7 @@ static int econet_create(struct net *net, struct socket *sock, int protocol,
 	if (sk == NULL)
 		goto out;
 
-	sk->sk_reuse = 1;
+	sk->sk_reuse = SK_CAN_REUSE;
 	sock->ops = &econet_ops;
 	sock_init_data(sock, sk);
 

@@ -1012,7 +1012,7 @@ static int __init aun_udp_initialise(void)
 		return error;
 	}
 
-	udpsock->sk->sk_reuse = 1;
+	udpsock->sk->sk_reuse = SK_CAN_REUSE;
 	udpsock->sk->sk_allocation = GFP_ATOMIC; /* we're going to call it
 						    from interrupts */
 

index 3744c1c..c8f7aee 100644
@@ -350,7 +350,7 @@ lookup_protocol:
 	err = 0;
 	sk->sk_no_check = answer_no_check;
 	if (INET_PROTOSW_REUSE & answer_flags)
-		sk->sk_reuse = 1;
+		sk->sk_reuse = SK_CAN_REUSE;
 
 	inet = inet_sk(sk);
 	inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;

index 7d972f6..95e6159 100644
@@ -182,6 +182,9 @@ have_snum:
 	goto tb_not_found;
 tb_found:
 	if (!hlist_empty(&tb->owners)) {
+		if (sk->sk_reuse == SK_FORCE_REUSE)
+			goto success;
+
 		if (tb->fastreuse > 0 &&
 		    sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
 		    smallest_size == -1) {

index 8ed1b93..499e74e 100644
@@ -180,7 +180,7 @@ lookup_protocol:
 	err = 0;
 	sk->sk_no_check = answer_no_check;
 	if (INET_PROTOSW_REUSE & answer_flags)
-		sk->sk_reuse = 1;
+		sk->sk_reuse = SK_CAN_REUSE;
 
 	inet = inet_sk(sk);
 	inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;

index f4e0b6c..bf5e538 100644
@@ -1368,7 +1368,7 @@ static struct socket *make_receive_sock(struct net *net)
 	 */
 	sk_change_net(sock->sk, net);
 	/* it is equivalent to the REUSEADDR option in user-space */
-	sock->sk->sk_reuse = 1;
+	sock->sk->sk_reuse = SK_CAN_REUSE;
 
 	result = sock->ops->bind(sock, (struct sockaddr *) &mcast_addr,
 			sizeof(struct sockaddr));

index 8b5cc4a..7298137 100644
@@ -145,7 +145,7 @@ int rds_tcp_listen_init(void)
 	if (ret < 0)
 		goto out;
 
-	sock->sk->sk_reuse = 1;
+	sock->sk->sk_reuse = SK_CAN_REUSE;
 	rds_tcp_nonagle(sock);
 
 	write_lock_bh(&sock->sk->sk_callback_lock);

index 824d32f..f0132b2 100644
@@ -1556,7 +1556,7 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
 					(char *)&val, sizeof(val));
 
 	if (type == SOCK_STREAM)
-		sock->sk->sk_reuse = 1;		/* allow address reuse */
+		sock->sk->sk_reuse = SK_CAN_REUSE; /* allow address reuse */
 	error = kernel_bind(sock, sin, len);
 	if (error < 0)
 		goto bummer;

index d5984e3..633fde2 100644
@@ -435,6 +435,9 @@ extern struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 					struct request_values *rvp);
 extern int tcp_disconnect(struct sock *sk, int flags);
 
+void tcp_connect_init(struct sock *sk);
+void tcp_finish_connect(struct sock *sk, struct sk_buff *skb);
+void tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int hdrlen);
 
 /* From syncookies.c */
 extern __u32 syncookie_secret[2][16-4+SHA_DIGEST_WORDS];

index c53e8a8..bb4200f 100644
@@ -919,7 +919,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 	int iovlen, flags, err, copied;
-	int mss_now, size_goal;
+	int mss_now = 0, size_goal;
 	bool sg;
 	long timeo;
 

106 lines not on this page · raw message

index de8790c..db126a6 100644
@@ -2561,7 +2561,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
 EXPORT_SYMBOL(tcp_make_synack);
 
 /* Do all connect socket setups that can be done AF independent. */
-static void tcp_connect_init(struct sock *sk)
+void tcp_connect_init(struct sock *sk)
 {
 	const struct dst_entry *dst = __sk_dst_get(sk);
 	struct tcp_sock *tp = tcp_sk(sk);

@@ -2616,6 +2616,7 @@ static void tcp_connect_init(struct sock *sk)
 	tp->snd_una = tp->write_seq;
 	tp->snd_sml = tp->write_seq;
 	tp->snd_up = tp->write_seq;
+	tp->snd_nxt = tp->write_seq;
 	tp->rcv_nxt = 0;
 	tp->rcv_wup = 0;
 	tp->copied_seq = 0;

@@ -2641,7 +2642,6 @@ int tcp_connect(struct sock *sk)
 	/* Reserve space for headers. */
 	skb_reserve(buff, MAX_TCP_HEADER);
 
-	tp->snd_nxt = tp->write_seq;
 	tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
 	TCP_ECN_send_syn(sk, buff);
 

index b6c62d2..4e90e6a 100644
@@ -106,6 +106,16 @@ enum {
 #define TCP_THIN_LINEAR_TIMEOUTS 16      /* Use linear timeouts for thin streams*/
 #define TCP_THIN_DUPACK         17      /* Fast retrans. after 1 dupack */
 #define TCP_USER_TIMEOUT	18	/* How long for loss retry before timeout */
+#define TCP_REPAIR		19	/* TCP sock is under repair right now */
+#define TCP_REPAIR_QUEUE	20
+#define TCP_QUEUE_SEQ		21
+
+enum {
+	TCP_NO_QUEUE,
+	TCP_RECV_QUEUE,
+	TCP_SEND_QUEUE,
+	TCP_QUEUES_NR,
+};
 
 /* for TCP_INFO socket option */
 #define TCPI_OPT_TIMESTAMPS	1

@@ -353,7 +363,9 @@ struct tcp_sock {
 	u8	nonagle     : 4,/* Disable Nagle algorithm?             */
 		thin_lto    : 1,/* Use linear timeouts for thin streams */
 		thin_dupack : 1,/* Fast retransmit on first dupack      */
-		unused      : 2;
+		repair      : 1,
+		unused      : 1;
+	u8	repair_queue;
 
 /* RTT measurement */
 	u32	srtt;		/* smoothed round trip time << 3	*/

index 633fde2..b4ccb8a 100644
@@ -612,6 +612,8 @@ static inline u32 tcp_receive_window(const struct tcp_sock *tp)
  */
 extern u32 __tcp_select_window(struct sock *sk);
 
+void tcp_send_window_probe(struct sock *sk);
+
 /* TCP timestamps are only 32-bits, this causes a slight
  * complication on 64-bit systems since we store a snapshot
  * of jiffies in the buffer control blocks below.  We decided

98 lines not on this page · raw message

index 0cb86ce..ba6dad8 100644
@@ -138,6 +138,14 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 }
 EXPORT_SYMBOL_GPL(tcp_twsk_unique);
 
+static int tcp_repair_connect(struct sock *sk)
+{
+	tcp_connect_init(sk);
+	tcp_finish_connect(sk, NULL);
+
+	return 0;
+}
+
 /* This will initiate an outgoing connection. */
 int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {

@@ -196,7 +204,8 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		/* Reset inherited state */
 		tp->rx_opt.ts_recent	   = 0;
 		tp->rx_opt.ts_recent_stamp = 0;
-		tp->write_seq		   = 0;
+		if (likely(!tp->repair))
+			tp->write_seq	   = 0;
 	}
 
 	if (tcp_death_row.sysctl_tw_recycle &&

@@ -247,7 +256,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	sk->sk_gso_type = SKB_GSO_TCPV4;
 	sk_setup_caps(sk, &rt->dst);
 
-	if (!tp->write_seq)
+	if (!tp->write_seq && likely(!tp->repair))
 		tp->write_seq = secure_tcp_sequence_number(inet->inet_saddr,
 							   inet->inet_daddr,
 							   inet->inet_sport,

@@ -255,7 +264,11 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	inet->inet_id = tp->write_seq ^ jiffies;
 
-	err = tcp_connect(sk);
+	if (likely(!tp->repair))
+		err = tcp_connect(sk);
+	else
+		err = tcp_repair_connect(sk);
+
 	rt = NULL;
 	if (err)
 		goto failure;

index db126a6..fa442a6 100644
@@ -2617,9 +2617,11 @@ void tcp_connect_init(struct sock *sk)
 	tp->snd_sml = tp->write_seq;
 	tp->snd_up = tp->write_seq;
 	tp->snd_nxt = tp->write_seq;
-	tp->rcv_nxt = 0;
-	tp->rcv_wup = 0;
-	tp->copied_seq = 0;
+
+	if (likely(!tp->repair))
+		tp->rcv_nxt = 0;
+	tp->rcv_wup = tp->rcv_nxt;
+	tp->copied_seq = tp->rcv_nxt;
 
 	inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT;
 	inet_csk(sk)->icsk_retransmits = 0;

@@ -2790,6 +2792,14 @@ static int tcp_xmit_probe_skb(struct sock *sk, int urgent)
 	return tcp_transmit_skb(sk, skb, 0, GFP_ATOMIC);
 }
 
+void tcp_send_window_probe(struct sock *sk)
+{
+	if (sk->sk_state == TCP_ESTABLISHED) {
+		tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
+		tcp_xmit_probe_skb(sk, 0);
+	}
+}
+
 /* Initiate keepalive or window probe from timer. */
 int tcp_write_wakeup(struct sock *sk)
 {

index e38d6f2..47e2f49 100644
@@ -912,6 +912,39 @@ static inline int select_size(const struct sock *sk, bool sg)
 	return tmp;
 }
 
+static int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
+{
+	struct sk_buff *skb;
+	struct tcp_skb_cb *cb;
+	struct tcphdr *th;
+
+	skb = alloc_skb(size + sizeof(*th), sk->sk_allocation);
+	if (!skb)
+		goto err;
+
+	th = (struct tcphdr *)skb_put(skb, sizeof(*th));
+	skb_reset_transport_header(skb);
+	memset(th, 0, sizeof(*th));
+
+	if (memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size))
+		goto err_free;
+
+	cb = TCP_SKB_CB(skb);
+
+	TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
+	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + size;
+	TCP_SKB_CB(skb)->ack_seq = tcp_sk(sk)->snd_una - 1;
+
+	tcp_queue_rcv(sk, skb, sizeof(*th));
+
+	return size;
+
+err_free:
+	kfree_skb(skb);
+err:
+	return -ENOMEM;
+}
+
 int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		size_t size)
 {

@@ -933,6 +966,19 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
 			goto out_err;
 
+	if (unlikely(tp->repair)) {
+		if (tp->repair_queue == TCP_RECV_QUEUE) {
+			copied = tcp_send_rcvq(sk, msg, size);
+			goto out;
+		}
+
+		err = -EINVAL;
+		if (tp->repair_queue == TCP_NO_QUEUE)
+			goto out_err;
+
+		/* 'common' sending to sendq */
+	}
+
 	/* This should be in poll */
 	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
 

@@ -1089,7 +1135,7 @@ new_segment:
 			if ((seglen -= copy) == 0 && iovlen == 0)
 				goto out;
 
-			if (skb->len < max || (flags & MSG_OOB))
+			if (skb->len < max || (flags & MSG_OOB) || unlikely(tp->repair))
 				continue;
 
 			if (forced_push(tp)) {

@@ -1102,7 +1148,7 @@ new_segment:
 wait_for_sndbuf:
 			set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
 wait_for_memory:
-			if (copied)
+			if (copied && likely(!tp->repair))
 				tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
 
 			if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)

@@ -1113,7 +1159,7 @@ wait_for_memory:
 	}
 
 out:
-	if (copied)
+	if (copied && likely(!tp->repair))
 		tcp_push(sk, flags, mss_now, tp->nonagle);
 	release_sock(sk);
 	return copied;

@@ -1187,6 +1233,24 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags)
 	return -EAGAIN;
 }
 
+static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
+{
+	struct sk_buff *skb;
+	int copied = 0, err = 0;
+
+	/* XXX -- need to support SO_PEEK_OFF */
+
+	skb_queue_walk(&sk->sk_write_queue, skb) {
+		err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, skb->len);
+		if (err)
+			break;
+
+		copied += skb->len;
+	}
+
+	return err ?: copied;
+}
+
 /* Clean up the receive buffer for full frames taken by the user,
  * then send an ACK if necessary.  COPIED is the number of bytes
  * tcp_recvmsg has given to the user so far, it speeds up the

@@ -1432,6 +1496,21 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (flags & MSG_OOB)
 		goto recv_urg;
 
+	if (unlikely(tp->repair)) {
+		err = -EPERM;
+		if (!(flags & MSG_PEEK))
+			goto out;
+
+		if (tp->repair_queue == TCP_SEND_QUEUE)
+			goto recv_sndq;
+
+		err = -EINVAL;
+		if (tp->repair_queue == TCP_NO_QUEUE)
+			goto out;
+
+		/* 'common' recv queue MSG_PEEK-ing */
+	}
+
 	seq = &tp->copied_seq;
 	if (flags & MSG_PEEK) {
 		peek_seq = tp->copied_seq;

@@ -1783,6 +1862,10 @@ out:
 recv_urg:
 	err = tcp_recv_urg(sk, msg, len, flags);
 	goto out;
+
+recv_sndq:
+	err = tcp_peek_sndq(sk, msg, len);
+	goto out;
 }
 EXPORT_SYMBOL(tcp_recvmsg);
 

index fa442a6..57a834c 100644
@@ -2796,6 +2796,7 @@ void tcp_send_window_probe(struct sock *sk)
 {
 	if (sk->sk_state == TCP_ESTABLISHED) {
 		tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
+		tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq;
 		tcp_xmit_probe_skb(sk, 0);
 	}
 }

index 47e2f49..b4e690d 100644
@@ -2659,6 +2659,8 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		val = tp->mss_cache;
 		if (!val && ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)))
 			val = tp->rx_opt.user_mss;
+		if (tp->repair)
+			val = tp->rx_opt.mss_clamp;
 		break;
 	case TCP_NODELAY:
 		val = !!(tp->nonagle&TCP_NAGLE_OFF);

index 4e90e6a..9865936 100644
@@ -109,6 +109,7 @@ enum {
 #define TCP_REPAIR		19	/* TCP sock is under repair right now */
 #define TCP_REPAIR_QUEUE	20
 #define TCP_QUEUE_SEQ		21
+#define TCP_REPAIR_OPTIONS	22
 
 enum {
 	TCP_NO_QUEUE,

83 lines not on this page · raw message