6 files changed, 209 insertions, 145 deletions

diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 7c96100b021e..4966b124dc2e 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -1028,52 +1028,4 @@ out_unregister_tcp_proto:
 }
 module_init(inet6_init);
 
-static void __exit inet6_exit(void)
-{
-	if (disable_ipv6_mod)
-		return;
-
-	/* First of all disallow new sockets creation. */
-	sock_unregister(PF_INET6);
-	/* Disallow any further netlink messages */
-	rtnl_unregister_all(PF_INET6);
-
-	udpv6_exit();
-	udplitev6_exit();
-	tcpv6_exit();
-
-	/* Cleanup code parts. */
-	ipv6_packet_cleanup();
-	ipv6_frag_exit();
-	ipv6_exthdrs_exit();
-	addrconf_cleanup();
-	ip6_flowlabel_cleanup();
-	ndisc_late_cleanup();
-	ip6_route_cleanup();
-#ifdef CONFIG_PROC_FS
-
-	/* Cleanup code parts. */
-	if6_proc_exit();
-	ipv6_misc_proc_exit();
-	udplite6_proc_exit();
-	raw6_proc_exit();
-#endif
-	ipv6_netfilter_fini();
-	ipv6_stub = NULL;
-	igmp6_cleanup();
-	ndisc_cleanup();
-	ip6_mr_cleanup();
-	icmpv6_cleanup();
-	rawv6_exit();
-
-	unregister_pernet_subsys(&inet6_net_ops);
-	proto_unregister(&rawv6_prot);
-	proto_unregister(&udplitev6_prot);
-	proto_unregister(&udpv6_prot);
-	proto_unregister(&tcpv6_prot);
-
-	rcu_barrier(); /* Wait for completion of call_rcu()'s */
-}
-module_exit(inet6_exit);
-
 MODULE_ALIAS_NETPROTO(PF_INET6);
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 5bec666aba61..5550a8113a6d 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1529,25 +1529,6 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
 	fib6_walk(&c.w);
 }
 
-void fib6_clean_all_ro(struct net *net, int (*func)(struct rt6_info *, void *arg),
-		    int prune, void *arg)
-{
-	struct fib6_table *table;
-	struct hlist_head *head;
-	unsigned int h;
-
-	rcu_read_lock();
-	for (h = 0; h < FIB6_TABLE_HASHSZ; h++) {
-		head = &net->ipv6.fib_table_hash[h];
-		hlist_for_each_entry_rcu(table, head, tb6_hlist) {
-			read_lock_bh(&table->tb6_lock);
-			fib6_clean_tree(net, &table->tb6_root,
-					func, prune, arg);
-			read_unlock_bh(&table->tb6_lock);
-		}
-	}
-	rcu_read_unlock();
-}
 void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
 		    int prune, void *arg)
 {
@@ -1782,3 +1763,189 @@ void fib6_gc_cleanup(void)
 	unregister_pernet_subsys(&fib6_net_ops);
 	kmem_cache_destroy(fib6_node_kmem);
 }
+
+#ifdef CONFIG_PROC_FS
+
+struct ipv6_route_iter {
+	struct seq_net_private p;
+	struct fib6_walker_t w;
+	loff_t skip;
+	struct fib6_table *tbl;
+	__u32 sernum;
+};
+
+static int ipv6_route_seq_show(struct seq_file *seq, void *v)
+{
+	struct rt6_info *rt = v;
+	struct ipv6_route_iter *iter = seq->private;
+
+	seq_printf(seq, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);
+
+#ifdef CONFIG_IPV6_SUBTREES
+	seq_printf(seq, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen);
+#else
+	seq_puts(seq, "00000000000000000000000000000000 00 ");
+#endif
+	if (rt->rt6i_flags & RTF_GATEWAY)
+		seq_printf(seq, "%pi6", &rt->rt6i_gateway);
+	else
+		seq_puts(seq, "00000000000000000000000000000000");
+
+	seq_printf(seq, " %08x %08x %08x %08x %8s\n",
+		   rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
+		   rt->dst.__use, rt->rt6i_flags,
+		   rt->dst.dev ? rt->dst.dev->name : "");
+	iter->w.leaf = NULL;
+	return 0;
+}
+
+static int ipv6_route_yield(struct fib6_walker_t *w)
+{
+	struct ipv6_route_iter *iter = w->args;
+
+	if (!iter->skip)
+		return 1;
+
+	do {
+		iter->w.leaf = iter->w.leaf->dst.rt6_next;
+		iter->skip--;
+		if (!iter->skip && iter->w.leaf)
+			return 1;
+	} while (iter->w.leaf);
+
+	return 0;
+}
+
+static void ipv6_route_seq_setup_walk(struct ipv6_route_iter *iter)
+{
+	memset(&iter->w, 0, sizeof(iter->w));
+	iter->w.func = ipv6_route_yield;
+	iter->w.root = &iter->tbl->tb6_root;
+	iter->w.state = FWS_INIT;
+	iter->w.node = iter->w.root;
+	iter->w.args = iter;
+	iter->sernum = iter->w.root->fn_sernum;
+	INIT_LIST_HEAD(&iter->w.lh);
+	fib6_walker_link(&iter->w);
+}
+
+static struct fib6_table *ipv6_route_seq_next_table(struct fib6_table *tbl,
+						    struct net *net)
+{
+	unsigned int h;
+	struct hlist_node *node;
+
+	if (tbl) {
+		h = (tbl->tb6_id & (FIB6_TABLE_HASHSZ - 1)) + 1;
+		node = rcu_dereference_bh(hlist_next_rcu(&tbl->tb6_hlist));
+	} else {
+		h = 0;
+		node = NULL;
+	}
+
+	while (!node && h < FIB6_TABLE_HASHSZ) {
+		node = rcu_dereference_bh(
+			hlist_first_rcu(&net->ipv6.fib_table_hash[h++]));
+	}
+	return hlist_entry_safe(node, struct fib6_table, tb6_hlist);
+}
+
+static void ipv6_route_check_sernum(struct ipv6_route_iter *iter)
+{
+	if (iter->sernum != iter->w.root->fn_sernum) {
+		iter->sernum = iter->w.root->fn_sernum;
+		iter->w.state = FWS_INIT;
+		iter->w.node = iter->w.root;
+		WARN_ON(iter->w.skip);
+		iter->w.skip = iter->w.count;
+	}
+}
+
+static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	int r;
+	struct rt6_info *n;
+	struct net *net = seq_file_net(seq);
+	struct ipv6_route_iter *iter = seq->private;
+
+	if (!v)
+		goto iter_table;
+
+	n = ((struct rt6_info *)v)->dst.rt6_next;
+	if (n) {
+		++*pos;
+		return n;
+	}
+
+iter_table:
+	ipv6_route_check_sernum(iter);
+	read_lock(&iter->tbl->tb6_lock);
+	r = fib6_walk_continue(&iter->w);
+	read_unlock(&iter->tbl->tb6_lock);
+	if (r > 0) {
+		if (v)
+			++*pos;
+		return iter->w.leaf;
+	} else if (r < 0) {
+		fib6_walker_unlink(&iter->w);
+		return NULL;
+	}
+	fib6_walker_unlink(&iter->w);
+
+	iter->tbl = ipv6_route_seq_next_table(iter->tbl, net);
+	if (!iter->tbl)
+		return NULL;
+
+	ipv6_route_seq_setup_walk(iter);
+	goto iter_table;
+}
+
+static void *ipv6_route_seq_start(struct seq_file *seq, loff_t *pos)
+	__acquires(RCU_BH)
+{
+	struct net *net = seq_file_net(seq);
+	struct ipv6_route_iter *iter = seq->private;
+
+	rcu_read_lock_bh();
+	iter->tbl = ipv6_route_seq_next_table(NULL, net);
+	iter->skip = *pos;
+
+	if (iter->tbl) {
+		ipv6_route_seq_setup_walk(iter);
+		return ipv6_route_seq_next(seq, NULL, pos);
+	} else {
+		return NULL;
+	}
+}
+
+static bool ipv6_route_iter_active(struct ipv6_route_iter *iter)
+{
+	struct fib6_walker_t *w = &iter->w;
+	return w->node && !(w->state == FWS_U && w->node == w->root);
+}
+
+static void ipv6_route_seq_stop(struct seq_file *seq, void *v)
+	__releases(RCU_BH)
+{
+	struct ipv6_route_iter *iter = seq->private;
+
+	if (ipv6_route_iter_active(iter))
+		fib6_walker_unlink(&iter->w);
+
+	rcu_read_unlock_bh();
+}
+
+static const struct seq_operations ipv6_route_seq_ops = {
+	.start	= ipv6_route_seq_start,
+	.next	= ipv6_route_seq_next,
+	.stop	= ipv6_route_seq_stop,
+	.show	= ipv6_route_seq_show
+};
+
+int ipv6_route_open(struct inode *inode, struct file *file)
+{
+	return seq_open_net(inode, file, &ipv6_route_seq_ops,
+			    sizeof(struct ipv6_route_iter));
+}
+
+#endif /* CONFIG_PROC_FS */
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c979dd96d82a..c3130ffc3bca 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1137,7 +1137,6 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_oif = oif;
 	fl6.flowi6_mark = mark;
-	fl6.flowi6_flags = 0;
 	fl6.daddr = iph->daddr;
 	fl6.saddr = iph->saddr;
 	fl6.flowlabel = ip6_flowinfo(iph);
@@ -1236,7 +1235,6 @@ void ip6_redirect(struct sk_buff *skb, struct net *net, int oif, u32 mark)
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_oif = oif;
 	fl6.flowi6_mark = mark;
-	fl6.flowi6_flags = 0;
 	fl6.daddr = iph->daddr;
 	fl6.saddr = iph->saddr;
 	fl6.flowlabel = ip6_flowinfo(iph);
@@ -1258,7 +1256,6 @@ void ip6_redirect_no_header(struct sk_buff *skb, struct net *net, int oif,
 	memset(&fl6, 0, sizeof(fl6));
 	fl6.flowi6_oif = oif;
 	fl6.flowi6_mark = mark;
-	fl6.flowi6_flags = 0;
 	fl6.daddr = msg->dest;
 	fl6.saddr = iph->daddr;
 
@@ -2800,56 +2797,12 @@ static int ip6_route_dev_notify(struct notifier_block *this,
 
 #ifdef CONFIG_PROC_FS
 
-struct rt6_proc_arg
-{
-	char *buffer;
-	int offset;
-	int length;
-	int skip;
-	int len;
-};
-
-static int rt6_info_route(struct rt6_info *rt, void *p_arg)
-{
-	struct seq_file *m = p_arg;
-
-	seq_printf(m, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);
-
-#ifdef CONFIG_IPV6_SUBTREES
-	seq_printf(m, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen);
-#else
-	seq_puts(m, "00000000000000000000000000000000 00 ");
-#endif
-	if (rt->rt6i_flags & RTF_GATEWAY) {
-		seq_printf(m, "%pi6", &rt->rt6i_gateway);
-	} else {
-		seq_puts(m, "00000000000000000000000000000000");
-	}
-	seq_printf(m, " %08x %08x %08x %08x %8s\n",
-		   rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
-		   rt->dst.__use, rt->rt6i_flags,
-		   rt->dst.dev ? rt->dst.dev->name : "");
-	return 0;
-}
-
-static int ipv6_route_show(struct seq_file *m, void *v)
-{
-	struct net *net = (struct net *)m->private;
-	fib6_clean_all_ro(net, rt6_info_route, 0, m);
-	return 0;
-}
-
-static int ipv6_route_open(struct inode *inode, struct file *file)
-{
-	return single_open_net(inode, file, ipv6_route_show);
-}
-
 static const struct file_operations ipv6_route_proc_fops = {
 	.owner		= THIS_MODULE,
 	.open		= ipv6_route_open,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
-	.release	= single_release_net,
+	.release	= seq_release_net,
 };
 
 static int rt6_stats_seq_show(struct seq_file *seq, void *v)
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index bf63ac8a49b9..d703218a653b 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -24,26 +24,21 @@
 #define COOKIEBITS 24	/* Upper bits store count */
 #define COOKIEMASK (((__u32)1 << COOKIEBITS) - 1)
 
-/* Table must be sorted. */
+/* RFC 2460, Section 8.3:
+ * [ipv6 tcp] MSS must be computed as the maximum packet size minus 60 [..]
+ *
+ * Due to IPV6_MIN_MTU=1280 the lowest possible MSS is 1220, which allows
+ * using higher values than ipv4 tcp syncookies.
+ * The other values are chosen based on ethernet (1500 and 9k MTU), plus
+ * one that accounts for common encap (PPPoe) overhead. Table must be sorted.
+ */
 static __u16 const msstab[] = {
-	64,
-	512,
-	536,
-	1280 - 60,
+	1280 - 60, /* IPV6_MIN_MTU - 60 */
 	1480 - 60,
 	1500 - 60,
-	4460 - 60,
 	9000 - 60,
 };
 
-/*
- * This (misnamed) value is the age of syncookie which is permitted.
- * Its ideal value should be dependent on TCP_TIMEOUT_INIT and
- * sysctl_tcp_retries1. It's a rather complicated formula (exponential
- * backoff) to compute at runtime so it's currently hardcoded here.
- */
-#define COUNTER_TRIES 4
-
 static inline struct sock *get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 					   struct request_sock *req,
 					   struct dst_entry *dst)
@@ -86,8 +81,9 @@ static u32 cookie_hash(const struct in6_addr *saddr, const struct in6_addr *dadd
 static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
 				   const struct in6_addr *daddr,
 				   __be16 sport, __be16 dport, __u32 sseq,
-				   __u32 count, __u32 data)
+				   __u32 data)
 {
+	u32 count = tcp_cookie_time();
 	return (cookie_hash(saddr, daddr, sport, dport, 0, 0) +
 		sseq + (count << COOKIEBITS) +
 		((cookie_hash(saddr, daddr, sport, dport, count, 1) + data)
@@ -96,15 +92,14 @@ static __u32 secure_tcp_syn_cookie(const struct in6_addr *saddr,
 
 static __u32 check_tcp_syn_cookie(__u32 cookie, const struct in6_addr *saddr,
 				  const struct in6_addr *daddr, __be16 sport,
-				  __be16 dport, __u32 sseq, __u32 count,
-				  __u32 maxdiff)
+				  __be16 dport, __u32 sseq)
 {
-	__u32 diff;
+	__u32 diff, count = tcp_cookie_time();
 
 	cookie -= cookie_hash(saddr, daddr, sport, dport, 0, 0) + sseq;
 
 	diff = (count - (cookie >> COOKIEBITS)) & ((__u32) -1 >> COOKIEBITS);
-	if (diff >= maxdiff)
+	if (diff >= MAX_SYNCOOKIE_AGE)
 		return (__u32)-1;
 
 	return (cookie -
@@ -125,8 +120,7 @@ u32 __cookie_v6_init_sequence(const struct ipv6hdr *iph,
 	*mssp = msstab[mssind];
 
 	return secure_tcp_syn_cookie(&iph->saddr, &iph->daddr, th->source,
-				     th->dest, ntohl(th->seq),
-				     jiffies / (HZ * 60), mssind);
+				     th->dest, ntohl(th->seq), mssind);
 }
 EXPORT_SYMBOL_GPL(__cookie_v6_init_sequence);
 
@@ -146,8 +140,7 @@ int __cookie_v6_check(const struct ipv6hdr *iph, const struct tcphdr *th,
 {
 	__u32 seq = ntohl(th->seq) - 1;
 	__u32 mssind = check_tcp_syn_cookie(cookie, &iph->saddr, &iph->daddr,
-					    th->source, th->dest, seq,
-					    jiffies / (HZ * 60), COUNTER_TRIES);
+					    th->source, th->dest, seq);
 
 	return mssind < ARRAY_SIZE(msstab) ? msstab[mssind] : 0;
 }
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 5c71501fc917..dde8bad04481 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1811,7 +1811,7 @@ static void get_timewait6_sock(struct seq_file *seq,
 	const struct in6_addr *dest, *src;
 	__u16 destp, srcp;
 	const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw);
-	long delta = tw->tw_ttd - jiffies;
+	s32 delta = tw->tw_ttd - inet_tw_time_stamp();
 
 	dest = &tw6->tw_v6_daddr;
 	src  = &tw6->tw_v6_rcv_saddr;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 72b7eaaf3ca0..37532478e3ba 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -57,8 +57,6 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
 {
 	const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr;
 	const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2);
-	__be32 sk1_rcv_saddr = sk_rcv_saddr(sk);
-	__be32 sk2_rcv_saddr = sk_rcv_saddr(sk2);
 	int sk_ipv6only = ipv6_only_sock(sk);
 	int sk2_ipv6only = inet_v6_ipv6only(sk2);
 	int addr_type = ipv6_addr_type(sk_rcv_saddr6);
@@ -67,8 +65,8 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2)
 	/* if both are mapped, treat as IPv4 */
 	if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED)
 		return (!sk2_ipv6only &&
-			(!sk1_rcv_saddr || !sk2_rcv_saddr ||
-			  sk1_rcv_saddr == sk2_rcv_saddr));
+			(!sk->sk_rcv_saddr || !sk2->sk_rcv_saddr ||
+			  sk->sk_rcv_saddr == sk2->sk_rcv_saddr));
 
 	if (addr_type2 == IPV6_ADDR_ANY &&
 	    !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
@@ -551,8 +549,10 @@ static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	int rc;
 
-	if (!ipv6_addr_any(&inet6_sk(sk)->daddr))
+	if (!ipv6_addr_any(&inet6_sk(sk)->daddr)) {
 		sock_rps_save_rxhash(sk, skb);
+		sk_mark_napi_id(sk, skb);
+	}
 
 	rc = sock_queue_rcv_skb(sk, skb);
 	if (rc < 0) {
@@ -846,7 +846,6 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	if (sk != NULL) {
 		int ret;
 
-		sk_mark_napi_id(sk, skb);
 		ret = udpv6_queue_rcv_skb(sk, skb);
 		sock_put(sk);