1 files changed, 149 insertions, 115 deletions

diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 807260d03586..4d880551fe6a 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -54,39 +54,31 @@
 #include <net/mip6.h>
 #endif
 
+#include <net/raw.h>
 #include <net/rawv6.h>
 #include <net/xfrm.h>
 
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 
-struct hlist_head raw_v6_htable[RAWV6_HTABLE_SIZE];
-DEFINE_RWLOCK(raw_v6_lock);
+static struct raw_hashinfo raw_v6_hashinfo = {
+	.lock = __RW_LOCK_UNLOCKED(),
+};
 
 static void raw_v6_hash(struct sock *sk)
 {
-	struct hlist_head *list = &raw_v6_htable[inet_sk(sk)->num &
-						 (RAWV6_HTABLE_SIZE - 1)];
-
-	write_lock_bh(&raw_v6_lock);
-	sk_add_node(sk, list);
-	sock_prot_inc_use(sk->sk_prot);
-	write_unlock_bh(&raw_v6_lock);
+	raw_hash_sk(sk, &raw_v6_hashinfo);
 }
 
 static void raw_v6_unhash(struct sock *sk)
 {
-	write_lock_bh(&raw_v6_lock);
-	if (sk_del_node_init(sk))
-		sock_prot_dec_use(sk->sk_prot);
-	write_unlock_bh(&raw_v6_lock);
+	raw_unhash_sk(sk, &raw_v6_hashinfo);
 }
 
 
-/* Grumble... icmp and ip_input want to get at this... */
-struct sock *__raw_v6_lookup(struct sock *sk, unsigned short num,
-			     struct in6_addr *loc_addr, struct in6_addr *rmt_addr,
-			     int dif)
+static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk,
+		unsigned short num, struct in6_addr *loc_addr,
+		struct in6_addr *rmt_addr, int dif)
 {
 	struct hlist_node *node;
 	int is_multicast = ipv6_addr_is_multicast(loc_addr);
@@ -95,6 +87,9 @@ struct sock *__raw_v6_lookup(struct sock *sk, unsigned short num,
 		if (inet_sk(sk)->num == num) {
 			struct ipv6_pinfo *np = inet6_sk(sk);
 
+			if (sk->sk_net != net)
+				continue;
+
 			if (!ipv6_addr_any(&np->daddr) &&
 			    !ipv6_addr_equal(&np->daddr, rmt_addr))
 				continue;
@@ -167,21 +162,22 @@ EXPORT_SYMBOL(rawv6_mh_filter_unregister);
  *
  *	Caller owns SKB so we must make clones.
  */
-int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
+static int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
 {
 	struct in6_addr *saddr;
 	struct in6_addr *daddr;
 	struct sock *sk;
 	int delivered = 0;
 	__u8 hash;
+	struct net *net;
 
 	saddr = &ipv6_hdr(skb)->saddr;
 	daddr = saddr + 1;
 
 	hash = nexthdr & (MAX_INET_PROTOS - 1);
 
-	read_lock(&raw_v6_lock);
-	sk = sk_head(&raw_v6_htable[hash]);
+	read_lock(&raw_v6_hashinfo.lock);
+	sk = sk_head(&raw_v6_hashinfo.ht[hash]);
 
 	/*
 	 *	The first socket found will be delivered after
@@ -191,7 +187,8 @@ int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
 	if (sk == NULL)
 		goto out;
 
-	sk = __raw_v6_lookup(sk, nexthdr, daddr, saddr, IP6CB(skb)->iif);
+	net = skb->dev->nd_net;
+	sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, IP6CB(skb)->iif);
 
 	while (sk) {
 		int filtered;
@@ -234,14 +231,25 @@ int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
 				rawv6_rcv(sk, clone);
 			}
 		}
-		sk = __raw_v6_lookup(sk_next(sk), nexthdr, daddr, saddr,
+		sk = __raw_v6_lookup(net, sk_next(sk), nexthdr, daddr, saddr,
 				     IP6CB(skb)->iif);
 	}
 out:
-	read_unlock(&raw_v6_lock);
+	read_unlock(&raw_v6_hashinfo.lock);
 	return delivered;
 }
 
+int raw6_local_deliver(struct sk_buff *skb, int nexthdr)
+{
+	struct sock *raw_sk;
+
+	raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (MAX_INET_PROTOS - 1)]);
+	if (raw_sk && !ipv6_raw_deliver(skb, nexthdr))
+		raw_sk = NULL;
+
+	return raw_sk != NULL;
+}
+
 /* This cleans up af_inet6 a bit. -DaveM */
 static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
@@ -283,7 +291,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 			if (!sk->sk_bound_dev_if)
 				goto out;
 
-			dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if);
+			dev = dev_get_by_index(sk->sk_net, sk->sk_bound_dev_if);
 			if (!dev) {
 				err = -ENODEV;
 				goto out;
@@ -296,7 +304,8 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 		v4addr = LOOPBACK4_IPV6;
 		if (!(addr_type & IPV6_ADDR_MULTICAST))	{
 			err = -EADDRNOTAVAIL;
-			if (!ipv6_chk_addr(&addr->sin6_addr, dev, 0)) {
+			if (!ipv6_chk_addr(sk->sk_net, &addr->sin6_addr,
+					   dev, 0)) {
 				if (dev)
 					dev_put(dev);
 				goto out;
@@ -316,7 +325,7 @@ out:
 	return err;
 }
 
-void rawv6_err(struct sock *sk, struct sk_buff *skb,
+static void rawv6_err(struct sock *sk, struct sk_buff *skb,
 	       struct inet6_skb_parm *opt,
 	       int type, int code, int offset, __be32 info)
 {
@@ -350,18 +359,45 @@ void rawv6_err(struct sock *sk, struct sk_buff *skb,
 	}
 }
 
+void raw6_icmp_error(struct sk_buff *skb, int nexthdr,
+		int type, int code, int inner_offset, __be32 info)
+{
+	struct sock *sk;
+	int hash;
+	struct in6_addr *saddr, *daddr;
+	struct net *net;
+
+	hash = nexthdr & (RAW_HTABLE_SIZE - 1);
+
+	read_lock(&raw_v6_hashinfo.lock);
+	sk = sk_head(&raw_v6_hashinfo.ht[hash]);
+	if (sk != NULL) {
+		saddr = &ipv6_hdr(skb)->saddr;
+		daddr = &ipv6_hdr(skb)->daddr;
+		net = skb->dev->nd_net;
+
+		while ((sk = __raw_v6_lookup(net, sk, nexthdr, saddr, daddr,
+						IP6CB(skb)->iif))) {
+			rawv6_err(sk, skb, NULL, type, code,
+					inner_offset, info);
+			sk = sk_next(sk);
+		}
+	}
+	read_unlock(&raw_v6_hashinfo.lock);
+}
+
 static inline int rawv6_rcv_skb(struct sock * sk, struct sk_buff * skb)
 {
 	if ((raw6_sk(sk)->checksum || sk->sk_filter) &&
 	    skb_checksum_complete(skb)) {
-		/* FIXME: increment a raw6 drops counter here */
+		atomic_inc(&sk->sk_drops);
 		kfree_skb(skb);
 		return 0;
 	}
 
 	/* Charge it to the socket. */
 	if (sock_queue_rcv_skb(sk,skb)<0) {
-		/* FIXME: increment a raw6 drops counter here */
+		atomic_inc(&sk->sk_drops);
 		kfree_skb(skb);
 		return 0;
 	}
@@ -382,6 +418,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb)
 	struct raw6_sock *rp = raw6_sk(sk);
 
 	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) {
+		atomic_inc(&sk->sk_drops);
 		kfree_skb(skb);
 		return NET_RX_DROP;
 	}
@@ -405,7 +442,7 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb)
 
 	if (inet->hdrincl) {
 		if (skb_checksum_complete(skb)) {
-			/* FIXME: increment a raw6 drops counter here */
+			atomic_inc(&sk->sk_drops);
 			kfree_skb(skb);
 			return 0;
 		}
@@ -496,7 +533,7 @@ csum_copy_err:
 	   as some normal condition.
 	 */
 	err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH;
-	/* FIXME: increment a raw6 drops counter here */
+	atomic_inc(&sk->sk_drops);
 	goto out;
 }
 
@@ -618,7 +655,7 @@ static int rawv6_send_hdrinc(struct sock *sk, void *from, int length,
 		goto error_fault;
 
 	IP6_INC_STATS(rt->rt6i_idev, IPSTATS_MIB_OUTREQUESTS);
-	err = NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
+	err = NF_HOOK(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
 		      dst_output);
 	if (err > 0)
 		err = np->recverr ? net_xmit_errno(err) : 0;
@@ -843,7 +880,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
 	if (final_p)
 		ipv6_addr_copy(&fl.fl6_dst, final_p);
 
-	if ((err = __xfrm_lookup(&dst, &fl, sk, 1)) < 0) {
+	if ((err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT)) < 0) {
 		if (err == -EREMOTE)
 			err = ip6_dst_blackhole(sk, &dst, &fl);
 		if (err < 0)
@@ -1172,76 +1209,6 @@ struct proto rawv6_prot = {
 };
 
 #ifdef CONFIG_PROC_FS
-struct raw6_iter_state {
-	int bucket;
-};
-
-#define raw6_seq_private(seq) ((struct raw6_iter_state *)(seq)->private)
-
-static struct sock *raw6_get_first(struct seq_file *seq)
-{
-	struct sock *sk;
-	struct hlist_node *node;
-	struct raw6_iter_state* state = raw6_seq_private(seq);
-
-	for (state->bucket = 0; state->bucket < RAWV6_HTABLE_SIZE; ++state->bucket)
-		sk_for_each(sk, node, &raw_v6_htable[state->bucket])
-			if (sk->sk_family == PF_INET6)
-				goto out;
-	sk = NULL;
-out:
-	return sk;
-}
-
-static struct sock *raw6_get_next(struct seq_file *seq, struct sock *sk)
-{
-	struct raw6_iter_state* state = raw6_seq_private(seq);
-
-	do {
-		sk = sk_next(sk);
-try_again:
-		;
-	} while (sk && sk->sk_family != PF_INET6);
-
-	if (!sk && ++state->bucket < RAWV6_HTABLE_SIZE) {
-		sk = sk_head(&raw_v6_htable[state->bucket]);
-		goto try_again;
-	}
-	return sk;
-}
-
-static struct sock *raw6_get_idx(struct seq_file *seq, loff_t pos)
-{
-	struct sock *sk = raw6_get_first(seq);
-	if (sk)
-		while (pos && (sk = raw6_get_next(seq, sk)) != NULL)
-			--pos;
-	return pos ? NULL : sk;
-}
-
-static void *raw6_seq_start(struct seq_file *seq, loff_t *pos)
-{
-	read_lock(&raw_v6_lock);
-	return *pos ? raw6_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
-}
-
-static void *raw6_seq_next(struct seq_file *seq, void *v, loff_t *pos)
-{
-	struct sock *sk;
-
-	if (v == SEQ_START_TOKEN)
-		sk = raw6_get_first(seq);
-	else
-		sk = raw6_get_next(seq, v);
-	++*pos;
-	return sk;
-}
-
-static void raw6_seq_stop(struct seq_file *seq, void *v)
-{
-	read_unlock(&raw_v6_lock);
-}
-
 static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i)
 {
 	struct ipv6_pinfo *np = inet6_sk(sp);
@@ -1254,7 +1221,7 @@ static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i)
 	srcp  = inet_sk(sp)->num;
 	seq_printf(seq,
 		   "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
-		   "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p\n",
+		   "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n",
 		   i,
 		   src->s6_addr32[0], src->s6_addr32[1],
 		   src->s6_addr32[2], src->s6_addr32[3], srcp,
@@ -1266,7 +1233,7 @@ static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i)
 		   0, 0L, 0,
 		   sock_i_uid(sp), 0,
 		   sock_i_ino(sp),
-		   atomic_read(&sp->sk_refcnt), sp);
+		   atomic_read(&sp->sk_refcnt), sp, atomic_read(&sp->sk_drops));
 }
 
 static int raw6_seq_show(struct seq_file *seq, void *v)
@@ -1277,23 +1244,22 @@ static int raw6_seq_show(struct seq_file *seq, void *v)
 			   "local_address                         "
 			   "remote_address                        "
 			   "st tx_queue rx_queue tr tm->when retrnsmt"
-			   "   uid  timeout inode\n");
+			   "   uid  timeout inode  drops\n");
 	else
-		raw6_sock_seq_show(seq, v, raw6_seq_private(seq)->bucket);
+		raw6_sock_seq_show(seq, v, raw_seq_private(seq)->bucket);
 	return 0;
 }
 
 static const struct seq_operations raw6_seq_ops = {
-	.start =	raw6_seq_start,
-	.next =		raw6_seq_next,
-	.stop =		raw6_seq_stop,
+	.start =	raw_seq_start,
+	.next =		raw_seq_next,
+	.stop =		raw_seq_stop,
 	.show =		raw6_seq_show,
 };
 
 static int raw6_seq_open(struct inode *inode, struct file *file)
 {
-	return seq_open_private(file, &raw6_seq_ops,
-			sizeof(struct raw6_iter_state));
+	return raw_seq_open(inode, file, &raw_v6_hashinfo, PF_INET6);
 }
 
 static const struct file_operations raw6_seq_fops = {
@@ -1301,18 +1267,86 @@ static const struct file_operations raw6_seq_fops = {
 	.open =		raw6_seq_open,
 	.read =		seq_read,
 	.llseek =	seq_lseek,
-	.release =	seq_release_private,
+	.release =	seq_release_net,
 };
 
-int __init raw6_proc_init(void)
+static int raw6_init_net(struct net *net)
 {
-	if (!proc_net_fops_create(&init_net, "raw6", S_IRUGO, &raw6_seq_fops))
+	if (!proc_net_fops_create(net, "raw6", S_IRUGO, &raw6_seq_fops))
 		return -ENOMEM;
+
 	return 0;
 }
 
+static void raw6_exit_net(struct net *net)
+{
+	proc_net_remove(net, "raw6");
+}
+
+static struct pernet_operations raw6_net_ops = {
+	.init = raw6_init_net,
+	.exit = raw6_exit_net,
+};
+
+int __init raw6_proc_init(void)
+{
+	return register_pernet_subsys(&raw6_net_ops);
+}
+
 void raw6_proc_exit(void)
 {
-	proc_net_remove(&init_net, "raw6");
+	unregister_pernet_subsys(&raw6_net_ops);
 }
 #endif	/* CONFIG_PROC_FS */
+
+/* Same as inet6_dgram_ops, sans udp_poll.  */
+static const struct proto_ops inet6_sockraw_ops = {
+	.family		   = PF_INET6,
+	.owner		   = THIS_MODULE,
+	.release	   = inet6_release,
+	.bind		   = inet6_bind,
+	.connect	   = inet_dgram_connect,	/* ok		*/
+	.socketpair	   = sock_no_socketpair,	/* a do nothing	*/
+	.accept		   = sock_no_accept,		/* a do nothing	*/
+	.getname	   = inet6_getname,
+	.poll		   = datagram_poll,		/* ok		*/
+	.ioctl		   = inet6_ioctl,		/* must change  */
+	.listen		   = sock_no_listen,		/* ok		*/
+	.shutdown	   = inet_shutdown,		/* ok		*/
+	.setsockopt	   = sock_common_setsockopt,	/* ok		*/
+	.getsockopt	   = sock_common_getsockopt,	/* ok		*/
+	.sendmsg	   = inet_sendmsg,		/* ok		*/
+	.recvmsg	   = sock_common_recvmsg,	/* ok		*/
+	.mmap		   = sock_no_mmap,
+	.sendpage	   = sock_no_sendpage,
+#ifdef CONFIG_COMPAT
+	.compat_setsockopt = compat_sock_common_setsockopt,
+	.compat_getsockopt = compat_sock_common_getsockopt,
+#endif
+};
+
+static struct inet_protosw rawv6_protosw = {
+	.type		= SOCK_RAW,
+	.protocol	= IPPROTO_IP,	/* wild card */
+	.prot		= &rawv6_prot,
+	.ops		= &inet6_sockraw_ops,
+	.capability	= CAP_NET_RAW,
+	.no_check	= UDP_CSUM_DEFAULT,
+	.flags		= INET_PROTOSW_REUSE,
+};
+
+int __init rawv6_init(void)
+{
+	int ret;
+
+	ret = inet6_register_protosw(&rawv6_protosw);
+	if (ret)
+		goto out;
+out:
+	return ret;
+}
+
+void rawv6_exit(void)
+{
+	inet6_unregister_protosw(&rawv6_protosw);
+}