X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fipv4%2Ftcp_ipv4.c;h=5a1ca2698c885775914f05fe17ae45d485cbddd2;hb=adf30907d63893e4208dfe3f5c88ae12bc2f25d5;hp=37ca3843c40b2a60da712afc4fb943816af5761e;hpb=6eac56040787c3ff604fe7d48bbbb7897cd1387c;p=safe%2Fjmp%2Flinux-2.6

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 37ca384..5a1ca26 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -51,6 +51,7 @@
  */
 
 
+#include <linux/bottom_half.h>
 #include <linux/types.h>
 #include <linux/fcntl.h>
 #include <linux/module.h>
@@ -97,11 +98,7 @@ struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
 }
 #endif
 
-struct inet_hashinfo __cacheline_aligned tcp_hashinfo = {
-	.lhash_lock  = __RW_LOCK_UNLOCKED(tcp_hashinfo.lhash_lock),
-	.lhash_users = ATOMIC_INIT(0),
-	.lhash_wait  = __WAIT_QUEUE_HEAD_INITIALIZER(tcp_hashinfo.lhash_wait),
-};
+struct inet_hashinfo tcp_hashinfo;
 
 static inline __u32 tcp_v4_init_sequence(struct sk_buff *skb)
 {
@@ -492,7 +489,7 @@ void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb)
 		skb->csum_offset = offsetof(struct tcphdr, check);
 	} else {
 		th->check = tcp_v4_check(len, inet->saddr, inet->daddr,
-					 csum_partial((char *)th,
+					 csum_partial(th,
 						      th->doff << 2,
 						      skb->csum));
 	}
@@ -549,7 +546,7 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 	if (th->rst)
 		return;
 
-	if (skb->rtable->rt_type != RTN_LOCAL)
+	if (skb_rtable(skb)->rt_type != RTN_LOCAL)
 		return;
 
 	/* Swap the send and the receive. */
@@ -583,16 +580,17 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 		rep.th.doff = arg.iov[0].iov_len / 4;
 
 		tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[1],
-				     key, ip_hdr(skb)->daddr,
-				     ip_hdr(skb)->saddr, &rep.th);
+				     key, ip_hdr(skb)->saddr,
+				     ip_hdr(skb)->daddr, &rep.th);
 	}
 #endif
 	arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
 				      ip_hdr(skb)->saddr, /* XXX */
-				      sizeof(struct tcphdr), IPPROTO_TCP, 0);
+				      arg.iov[0].iov_len, IPPROTO_TCP, 0);
 	arg.csumoffset = offsetof(struct tcphdr, check) / 2;
+	arg.flags = (sk && inet_sk(sk)->transparent) ? IP_REPLY_ARG_NOSRCCHECK : 0;
 
-	net = dev_net(skb->dst->dev);
+	net = dev_net(skb_dst(skb)->dev);
 	ip_send_reply(net->ipv4.tcp_sock, skb,
 		      &arg, arg.iov[0].iov_len);
 
@@ -606,7 +604,8 @@ static void tcp_v4_send_reset(struct sock *sk, struct sk_buff *skb)
 
 static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 			    u32 win, u32 ts, int oif,
-			    struct tcp_md5sig_key *key)
+			    struct tcp_md5sig_key *key,
+			    int reply_flags)
 {
 	struct tcphdr *th = tcp_hdr(skb);
 	struct {
@@ -618,7 +617,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 			];
 	} rep;
 	struct ip_reply_arg arg;
-	struct net *net = dev_net(skb->dev);
+	struct net *net = dev_net(skb_dst(skb)->dev);
 
 	memset(&rep.th, 0, sizeof(struct tcphdr));
 	memset(&arg, 0, sizeof(arg));
@@ -659,6 +658,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 				    ip_hdr(skb)->daddr, &rep.th);
 	}
 #endif
+	arg.flags = reply_flags;
 	arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,
 				      ip_hdr(skb)->saddr, /* XXX */
 				      arg.iov[0].iov_len, IPPROTO_TCP, 0);
@@ -681,7 +681,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcptw->tw_ts_recent,
 			tw->tw_bound_dev_if,
-			tcp_twsk_md5_key(tcptw)
+			tcp_twsk_md5_key(tcptw),
+			tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0
 			);
 
 	inet_twsk_put(tw);
@@ -694,7 +695,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
 			tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd,
 			req->ts_recent,
 			0,
-			tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr));
+			tcp_v4_md5_do_lookup(sk, ip_hdr(skb)->daddr),
+			inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0);
 }
 
 /*
@@ -721,7 +723,7 @@ static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
 		th->check = tcp_v4_check(skb->len,
 					 ireq->loc_addr,
 					 ireq->rmt_addr,
-					 csum_partial((char *)th, skb->len,
+					 csum_partial(th, skb->len,
 						      skb->csum));
 
 		err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
@@ -1134,10 +1136,9 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb)
 
 	if (genhash || memcmp(hash_location, newhash, 16) != 0) {
 		if (net_ratelimit()) {
-			printk(KERN_INFO "MD5 Hash failed for "
-			       "(" NIPQUAD_FMT ", %d)->(" NIPQUAD_FMT ", %d)%s\n",
-			       NIPQUAD(iph->saddr), ntohs(th->source),
-			       NIPQUAD(iph->daddr), ntohs(th->dest),
+			printk(KERN_INFO "MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n",
+			       &iph->saddr, ntohs(th->source),
+			       &iph->daddr, ntohs(th->dest),
 			       genhash ? " tcp_v4_calc_md5_hash failed" : "");
 		}
 		return 1;
@@ -1184,7 +1185,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 #endif
 
 	/* Never answer to SYNs send to broadcast or multicast */
-	if (skb->rtable->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
+	if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
 		goto drop;
 
 	/* TW buckets are converted to open requests without
@@ -1225,26 +1226,19 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	if (want_cookie && !tmp_opt.saw_tstamp)
 		tcp_clear_options(&tmp_opt);
 
-	if (tmp_opt.saw_tstamp && !tmp_opt.rcv_tsval) {
-		/* Some OSes (unknown ones, but I see them on web server, which
-		 * contains information interesting only for windows'
-		 * users) do not send their stamp in SYN. It is easy case.
-		 * We simply do not advertise TS support.
-		 */
-		tmp_opt.saw_tstamp = 0;
-		tmp_opt.tstamp_ok  = 0;
-	}
 	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
 
 	tcp_openreq_init(req, &tmp_opt, skb);
 
-	if (security_inet_conn_request(sk, skb, req))
-		goto drop_and_free;
-
 	ireq = inet_rsk(req);
 	ireq->loc_addr = daddr;
 	ireq->rmt_addr = saddr;
+	ireq->no_srccheck = inet_sk(sk)->transparent;
 	ireq->opt = tcp_v4_save_options(sk, skb);
+
+	if (security_inet_conn_request(sk, skb, req))
+		goto drop_and_free;
+
 	if (!want_cookie)
 		TCP_ECN_create_request(req, tcp_hdr(skb));
 
@@ -1291,10 +1285,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 			 * to destinations, already remembered
 			 * to the moment of synflood.
 			 */
-			LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open "
-				       "request from " NIPQUAD_FMT "/%u\n",
-				       NIPQUAD(saddr),
-				       ntohs(tcp_hdr(skb)->source));
+			LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open request from %pI4/%u\n",
+				       &saddr, ntohs(tcp_hdr(skb)->source));
 			goto drop_and_release;
 		}
 
@@ -1364,6 +1356,10 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	tcp_mtup_init(newsk);
 	tcp_sync_mss(newsk, dst_mtu(dst));
 	newtp->advmss = dst_metric(dst, RTAX_ADVMSS);
+	if (tcp_sk(sk)->rx_opt.user_mss &&
+	    tcp_sk(sk)->rx_opt.user_mss < newtp->advmss)
+		newtp->advmss = tcp_sk(sk)->rx_opt.user_mss;
+
 	tcp_initialize_rcv_mss(newsk);
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1567,8 +1563,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
 	TCP_SKB_CB(skb)->flags	 = iph->tos;
 	TCP_SKB_CB(skb)->sacked	 = 0;
 
-	sk = __inet_lookup(net, &tcp_hashinfo, iph->saddr,
-			th->source, iph->daddr, th->dest, inet_iif(skb));
+	sk = __inet_lookup_skb(&tcp_hashinfo, skb, th->source, th->dest);
 	if (!sk)
 		goto no_tcp_socket;
 
@@ -1591,14 +1586,14 @@ process:
 #ifdef CONFIG_NET_DMA
 		struct tcp_sock *tp = tcp_sk(sk);
 		if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-			tp->ucopy.dma_chan = get_softnet_dma();
+			tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
 		if (tp->ucopy.dma_chan)
 			ret = tcp_v4_do_rcv(sk, skb);
 		else
 #endif
 		{
 			if (!tcp_prequeue(sk, skb))
-			ret = tcp_v4_do_rcv(sk, skb);
+				ret = tcp_v4_do_rcv(sk, skb);
 		}
 	} else
 		sk_add_backlog(sk, skb);
@@ -1795,7 +1790,9 @@ static int tcp_v4_init_sock(struct sock *sk)
 	sk->sk_sndbuf = sysctl_tcp_wmem[1];
 	sk->sk_rcvbuf = sysctl_tcp_rmem[1];
 
-	atomic_inc(&tcp_sockets_allocated);
+	local_bh_disable();
+	percpu_counter_inc(&tcp_sockets_allocated);
+	local_bh_enable();
 
 	return 0;
 }
@@ -1843,7 +1840,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 		sk->sk_sndmsg_page = NULL;
 	}
 
-	atomic_dec(&tcp_sockets_allocated);
+	percpu_counter_dec(&tcp_sockets_allocated);
 }
 
 EXPORT_SYMBOL(tcp_v4_destroy_sock);
@@ -1851,32 +1848,35 @@ EXPORT_SYMBOL(tcp_v4_destroy_sock);
 #ifdef CONFIG_PROC_FS
 /* Proc filesystem TCP sock list dumping. */
 
-static inline struct inet_timewait_sock *tw_head(struct hlist_head *head)
+static inline struct inet_timewait_sock *tw_head(struct hlist_nulls_head *head)
 {
-	return hlist_empty(head) ? NULL :
+	return hlist_nulls_empty(head) ? NULL :
 		list_entry(head->first, struct inet_timewait_sock, tw_node);
 }
 
 static inline struct inet_timewait_sock *tw_next(struct inet_timewait_sock *tw)
 {
-	return tw->tw_node.next ?
-		hlist_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
+	return !is_a_nulls(tw->tw_node.next) ?
+		hlist_nulls_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
 }
 
 static void *listening_get_next(struct seq_file *seq, void *cur)
 {
 	struct inet_connection_sock *icsk;
-	struct hlist_node *node;
+	struct hlist_nulls_node *node;
 	struct sock *sk = cur;
-	struct tcp_iter_state* st = seq->private;
+	struct inet_listen_hashbucket *ilb;
+	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
 
 	if (!sk) {
 		st->bucket = 0;
-		sk = sk_head(&tcp_hashinfo.listening_hash[0]);
+		ilb = &tcp_hashinfo.listening_hash[0];
+		spin_lock_bh(&ilb->lock);
+		sk = sk_nulls_head(&ilb->head);
 		goto get_sk;
 	}
-
+	ilb = &tcp_hashinfo.listening_hash[st->bucket];
 	++st->num;
 
 	if (st->state == TCP_SEQ_STATE_OPENREQ) {
@@ -1909,7 +1909,7 @@ get_req:
 		sk = sk_next(sk);
 	}
 get_sk:
-	sk_for_each_from(sk, node) {
+	sk_nulls_for_each_from(sk, node) {
 		if (sk->sk_family == st->family && net_eq(sock_net(sk), net)) {
 			cur = sk;
 			goto out;
@@ -1926,8 +1926,11 @@ start_req:
 		}
 		read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
 	}
+	spin_unlock_bh(&ilb->lock);
 	if (++st->bucket < INET_LHTABLE_SIZE) {
-		sk = sk_head(&tcp_hashinfo.listening_hash[st->bucket]);
+		ilb = &tcp_hashinfo.listening_hash[st->bucket];
+		spin_lock_bh(&ilb->lock);
+		sk = sk_nulls_head(&ilb->head);
 		goto get_sk;
 	}
 	cur = NULL;
@@ -1948,28 +1951,28 @@ static void *listening_get_idx(struct seq_file *seq, loff_t *pos)
 
 static inline int empty_bucket(struct tcp_iter_state *st)
 {
-	return hlist_empty(&tcp_hashinfo.ehash[st->bucket].chain) &&
-		hlist_empty(&tcp_hashinfo.ehash[st->bucket].twchain);
+	return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain) &&
+		hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].twchain);
 }
 
 static void *established_get_first(struct seq_file *seq)
 {
-	struct tcp_iter_state* st = seq->private;
+	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
 	void *rc = NULL;
 
 	for (st->bucket = 0; st->bucket < tcp_hashinfo.ehash_size; ++st->bucket) {
 		struct sock *sk;
-		struct hlist_node *node;
+		struct hlist_nulls_node *node;
 		struct inet_timewait_sock *tw;
-		rwlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket);
+		spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket);
 
 		/* Lockless fast path for the common case of empty buckets */
 		if (empty_bucket(st))
 			continue;
 
-		read_lock_bh(lock);
-		sk_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) {
+		spin_lock_bh(lock);
+		sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) {
 			if (sk->sk_family != st->family ||
 			    !net_eq(sock_net(sk), net)) {
 				continue;
@@ -1987,7 +1990,7 @@ static void *established_get_first(struct seq_file *seq)
 			rc = tw;
 			goto out;
 		}
-		read_unlock_bh(lock);
+		spin_unlock_bh(lock);
 		st->state = TCP_SEQ_STATE_ESTABLISHED;
 	}
 out:
@@ -1998,8 +2001,8 @@ static void *established_get_next(struct seq_file *seq, void *cur)
 {
 	struct sock *sk = cur;
 	struct inet_timewait_sock *tw;
-	struct hlist_node *node;
-	struct tcp_iter_state* st = seq->private;
+	struct hlist_nulls_node *node;
+	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
 
 	++st->num;
@@ -2015,7 +2018,7 @@ get_tw:
 			cur = tw;
 			goto out;
 		}
-		read_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
+		spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
 		st->state = TCP_SEQ_STATE_ESTABLISHED;
 
 		/* Look for next non empty bucket */
@@ -2025,12 +2028,12 @@ get_tw:
 		if (st->bucket >= tcp_hashinfo.ehash_size)
 			return NULL;
 
-		read_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
-		sk = sk_head(&tcp_hashinfo.ehash[st->bucket].chain);
+		spin_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
+		sk = sk_nulls_head(&tcp_hashinfo.ehash[st->bucket].chain);
 	} else
-		sk = sk_next(sk);
+		sk = sk_nulls_next(sk);
 
-	sk_for_each_from(sk, node) {
+	sk_nulls_for_each_from(sk, node) {
 		if (sk->sk_family == st->family && net_eq(sock_net(sk), net))
 			goto found;
 	}
@@ -2058,14 +2061,12 @@ static void *established_get_idx(struct seq_file *seq, loff_t pos)
 static void *tcp_get_idx(struct seq_file *seq, loff_t pos)
 {
 	void *rc;
-	struct tcp_iter_state* st = seq->private;
+	struct tcp_iter_state *st = seq->private;
 
-	inet_listen_lock(&tcp_hashinfo);
 	st->state = TCP_SEQ_STATE_LISTENING;
 	rc	  = listening_get_idx(seq, &pos);
 
 	if (!rc) {
-		inet_listen_unlock(&tcp_hashinfo);
 		st->state = TCP_SEQ_STATE_ESTABLISHED;
 		rc	  = established_get_idx(seq, pos);
 	}
@@ -2075,7 +2076,7 @@ static void *tcp_get_idx(struct seq_file *seq, loff_t pos)
 
 static void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
 {
-	struct tcp_iter_state* st = seq->private;
+	struct tcp_iter_state *st = seq->private;
 	st->state = TCP_SEQ_STATE_LISTENING;
 	st->num = 0;
 	return *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
@@ -2084,7 +2085,7 @@ static void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
 static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
 	void *rc = NULL;
-	struct tcp_iter_state* st;
+	struct tcp_iter_state *st;
 
 	if (v == SEQ_START_TOKEN) {
 		rc = tcp_get_idx(seq, 0);
@@ -2097,7 +2098,6 @@ static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	case TCP_SEQ_STATE_LISTENING:
 		rc = listening_get_next(seq, v);
 		if (!rc) {
-			inet_listen_unlock(&tcp_hashinfo);
 			st->state = TCP_SEQ_STATE_ESTABLISHED;
 			rc	  = established_get_first(seq);
 		}
@@ -2114,7 +2114,7 @@ out:
 
 static void tcp_seq_stop(struct seq_file *seq, void *v)
 {
-	struct tcp_iter_state* st = seq->private;
+	struct tcp_iter_state *st = seq->private;
 
 	switch (st->state) {
 	case TCP_SEQ_STATE_OPENREQ:
@@ -2124,12 +2124,12 @@ static void tcp_seq_stop(struct seq_file *seq, void *v)
 		}
 	case TCP_SEQ_STATE_LISTENING:
 		if (v != SEQ_START_TOKEN)
-			inet_listen_unlock(&tcp_hashinfo);
+			spin_unlock_bh(&tcp_hashinfo.listening_hash[st->bucket].lock);
 		break;
 	case TCP_SEQ_STATE_TIME_WAIT:
 	case TCP_SEQ_STATE_ESTABLISHED:
 		if (v)
-			read_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
+			spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
 		break;
 	}
 }
@@ -2275,7 +2275,7 @@ static void get_timewait4_sock(struct inet_timewait_sock *tw,
 
 static int tcp4_seq_show(struct seq_file *seq, void *v)
 {
-	struct tcp_iter_state* st;
+	struct tcp_iter_state *st;
 	int len;
 
 	if (v == SEQ_START_TOKEN) {
@@ -2341,6 +2341,41 @@ void tcp4_proc_exit(void)
 }
 #endif /* CONFIG_PROC_FS */
 
+struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+{
+	struct iphdr *iph = skb_gro_network_header(skb);
+
+	switch (skb->ip_summed) {
+	case CHECKSUM_COMPLETE:
+		if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr,
+				  skb->csum)) {
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+			break;
+		}
+
+		/* fall through */
+	case CHECKSUM_NONE:
+		NAPI_GRO_CB(skb)->flush = 1;
+		return NULL;
+	}
+
+	return tcp_gro_receive(head, skb);
+}
+EXPORT_SYMBOL(tcp4_gro_receive);
+
+int tcp4_gro_complete(struct sk_buff *skb)
+{
+	struct iphdr *iph = ip_hdr(skb);
+	struct tcphdr *th = tcp_hdr(skb);
+
+	th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb),
+				  iph->saddr, iph->daddr, 0);
+	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
+
+	return tcp_gro_complete(skb);
+}
+EXPORT_SYMBOL(tcp4_gro_complete);
+
 struct proto tcp_prot = {
 	.name			= "TCP",
 	.owner			= THIS_MODULE,
@@ -2369,6 +2404,7 @@ struct proto tcp_prot = {
 	.sysctl_rmem		= sysctl_tcp_rmem,
 	.max_header		= MAX_TCP_HEADER,
 	.obj_size		= sizeof(struct tcp_sock),
+	.slab_flags		= SLAB_DESTROY_BY_RCU,
 	.twsk_prot		= &tcp_timewait_sock_ops,
 	.rsk_prot		= &tcp_request_sock_ops,
 	.h.hashinfo		= &tcp_hashinfo,
@@ -2388,6 +2424,7 @@ static int __net_init tcp_sk_init(struct net *net)
 static void __net_exit tcp_sk_exit(struct net *net)
 {
 	inet_ctl_sock_destroy(net->ipv4.tcp_sock);
+	inet_twsk_purge(net, &tcp_hashinfo, &tcp_death_row, AF_INET);
 }
 
 static struct pernet_operations __net_initdata tcp_sk_ops = {
@@ -2397,7 +2434,8 @@ static struct pernet_operations __net_initdata tcp_sk_ops = {
 
 void __init tcp_v4_init(void)
 {
-	if (register_pernet_device(&tcp_sk_ops))
+	inet_hashinfo_init(&tcp_hashinfo);
+	if (register_pernet_subsys(&tcp_sk_ops))
 		panic("Failed to create the TCP control socket.\n");
 }