summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c16
-rw-r--r--net/ipv6/addrlabel.c10
-rw-r--r--net/ipv6/af_inet6.c6
-rw-r--r--net/ipv6/exthdrs_core.c4
-rw-r--r--net/ipv6/fib6_rules.c3
-rw-r--r--net/ipv6/ip6_fib.c9
-rw-r--r--net/ipv6/ip6_output.c22
-rw-r--r--net/ipv6/ip6_tunnel.c153
-rw-r--r--net/ipv6/ip6mr.c1
-rw-r--r--net/ipv6/ndisc.c18
-rw-r--r--net/ipv6/netfilter/ip6_tables.c14
-rw-r--r--net/ipv6/raw.c12
-rw-r--r--net/ipv6/route.c80
-rw-r--r--net/ipv6/sit.c163
-rw-r--r--net/ipv6/tcp_ipv6.c2
-rw-r--r--net/ipv6/xfrm6_policy.c10
-rw-r--r--net/ipv6/xfrm6_state.c33
-rw-r--r--net/ipv6/xfrm6_tunnel.c4
18 files changed, 372 insertions, 188 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 5bc893e..ec7a91d 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -243,7 +243,7 @@ static inline bool addrconf_qdisc_ok(const struct net_device *dev)
/* Check if a route is valid prefix route */
static inline int addrconf_is_prefix_route(const struct rt6_info *rt)
{
- return ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0);
+ return (rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0;
}
static void addrconf_del_timer(struct inet6_ifaddr *ifp)
@@ -1544,7 +1544,7 @@ static int addrconf_ifid_infiniband(u8 *eui, struct net_device *dev)
return 0;
}
-int __ipv6_isatap_ifid(u8 *eui, __be32 addr)
+static int __ipv6_isatap_ifid(u8 *eui, __be32 addr)
{
if (addr == 0)
return -1;
@@ -1560,7 +1560,6 @@ int __ipv6_isatap_ifid(u8 *eui, __be32 addr)
memcpy(eui + 4, &addr, 4);
return 0;
}
-EXPORT_SYMBOL(__ipv6_isatap_ifid);
static int addrconf_ifid_sit(u8 *eui, struct net_device *dev)
{
@@ -4638,10 +4637,12 @@ int __init addrconf_init(void)
if (err < 0) {
printk(KERN_CRIT "IPv6 Addrconf:"
" cannot initialize default policy table: %d.\n", err);
- return err;
+ goto out;
}
- register_pernet_subsys(&addrconf_ops);
+ err = register_pernet_subsys(&addrconf_ops);
+ if (err < 0)
+ goto out_addrlabel;
/* The addrconf netdev notifier requires that loopback_dev
* has it's ipv6 private information allocated and setup
@@ -4693,7 +4694,9 @@ errout:
unregister_netdevice_notifier(&ipv6_dev_notf);
errlo:
unregister_pernet_subsys(&addrconf_ops);
-
+out_addrlabel:
+ ipv6_addr_label_cleanup();
+out:
return err;
}
@@ -4704,6 +4707,7 @@ void addrconf_cleanup(void)
unregister_netdevice_notifier(&ipv6_dev_notf);
unregister_pernet_subsys(&addrconf_ops);
+ ipv6_addr_label_cleanup();
rtnl_lock();
diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c
index f0e774c..c8993e5 100644
--- a/net/ipv6/addrlabel.c
+++ b/net/ipv6/addrlabel.c
@@ -393,6 +393,11 @@ int __init ipv6_addr_label_init(void)
return register_pernet_subsys(&ipv6_addr_label_ops);
}
+void ipv6_addr_label_cleanup(void)
+{
+ unregister_pernet_subsys(&ipv6_addr_label_ops);
+}
+
static const struct nla_policy ifal_policy[IFAL_MAX+1] = {
[IFAL_ADDRESS] = { .len = sizeof(struct in6_addr), },
[IFAL_LABEL] = { .len = sizeof(u32), },
@@ -513,10 +518,9 @@ static int ip6addrlbl_dump(struct sk_buff *skb, struct netlink_callback *cb)
static inline int ip6addrlbl_msgsize(void)
{
- return (NLMSG_ALIGN(sizeof(struct ifaddrlblmsg))
+ return NLMSG_ALIGN(sizeof(struct ifaddrlblmsg))
+ nla_total_size(16) /* IFAL_ADDRESS */
- + nla_total_size(4) /* IFAL_LABEL */
- );
+ + nla_total_size(4); /* IFAL_LABEL */
}
static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr* nlh,
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 4869797..54e8e42 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -468,7 +468,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr,
if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL)
sin->sin6_scope_id = sk->sk_bound_dev_if;
*uaddr_len = sizeof(*sin);
- return(0);
+ return 0;
}
EXPORT_SYMBOL(inet6_getname);
@@ -489,7 +489,7 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
case SIOCADDRT:
case SIOCDELRT:
- return(ipv6_route_ioctl(net, cmd, (void __user *)arg));
+ return ipv6_route_ioctl(net, cmd, (void __user *)arg);
case SIOCSIFADDR:
return addrconf_add_ifaddr(net, (void __user *) arg);
@@ -503,7 +503,7 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
return sk->sk_prot->ioctl(sk, cmd, arg);
}
/*NOTREACHED*/
- return(0);
+ return 0;
}
EXPORT_SYMBOL(inet6_ioctl);
diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c
index e1caa5d..14ed0a9 100644
--- a/net/ipv6/exthdrs_core.c
+++ b/net/ipv6/exthdrs_core.c
@@ -13,12 +13,12 @@ int ipv6_ext_hdr(u8 nexthdr)
/*
* find out if nexthdr is an extension header or a protocol
*/
- return ( (nexthdr == NEXTHDR_HOP) ||
+ return (nexthdr == NEXTHDR_HOP) ||
(nexthdr == NEXTHDR_ROUTING) ||
(nexthdr == NEXTHDR_FRAGMENT) ||
(nexthdr == NEXTHDR_AUTH) ||
(nexthdr == NEXTHDR_NONE) ||
- (nexthdr == NEXTHDR_DEST) );
+ (nexthdr == NEXTHDR_DEST);
}
/*
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index b1108ed..d829874 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -34,11 +34,10 @@ struct dst_entry *fib6_rule_lookup(struct net *net, struct flowi *fl,
{
struct fib_lookup_arg arg = {
.lookup_ptr = lookup,
+ .flags = FIB_LOOKUP_NOREF,
};
fib_rules_lookup(net->ipv6.fib6_rules_ops, fl, flags, &arg);
- if (arg.rule)
- fib_rule_put(arg.rule);
if (arg.result)
return arg.result;
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index b6a5859..de38211 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1500,15 +1500,18 @@ static void fib6_gc_timer_cb(unsigned long arg)
static int __net_init fib6_net_init(struct net *net)
{
+ size_t size = sizeof(struct hlist_head) * FIB6_TABLE_HASHSZ;
+
setup_timer(&net->ipv6.ip6_fib_timer, fib6_gc_timer_cb, (unsigned long)net);
net->ipv6.rt6_stats = kzalloc(sizeof(*net->ipv6.rt6_stats), GFP_KERNEL);
if (!net->ipv6.rt6_stats)
goto out_timer;
- net->ipv6.fib_table_hash = kcalloc(FIB6_TABLE_HASHSZ,
- sizeof(*net->ipv6.fib_table_hash),
- GFP_KERNEL);
+ /* Avoid false sharing : Use at least a full cache line */
+ size = max_t(size_t, size, L1_CACHE_BYTES);
+
+ net->ipv6.fib_table_hash = kzalloc(size, GFP_KERNEL);
if (!net->ipv6.fib_table_hash)
goto out_rt6_stats;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1838927..99157b4 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -639,7 +639,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
if (skb_has_frag_list(skb)) {
int first_len = skb_pagelen(skb);
- int truesizes = 0;
+ struct sk_buff *frag2;
if (first_len - hlen > mtu ||
((first_len - hlen) & 7) ||
@@ -651,18 +651,18 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
if (frag->len > mtu ||
((frag->len & 7) && frag->next) ||
skb_headroom(frag) < hlen)
- goto slow_path;
+ goto slow_path_clean;
/* Partially cloned skb? */
if (skb_shared(frag))
- goto slow_path;
+ goto slow_path_clean;
BUG_ON(frag->sk);
if (skb->sk) {
frag->sk = skb->sk;
frag->destructor = sock_wfree;
- truesizes += frag->truesize;
}
+ skb->truesize -= frag->truesize;
}
err = 0;
@@ -693,7 +693,6 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
first_len = skb_pagelen(skb);
skb->data_len = first_len - skb_headlen(skb);
- skb->truesize -= truesizes;
skb->len = first_len;
ipv6_hdr(skb)->payload_len = htons(first_len -
sizeof(struct ipv6hdr));
@@ -756,6 +755,15 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
IPSTATS_MIB_FRAGFAILS);
dst_release(&rt->dst);
return err;
+
+slow_path_clean:
+ skb_walk_frags(skb, frag2) {
+ if (frag2 == frag)
+ break;
+ frag2->sk = NULL;
+ frag2->destructor = NULL;
+ skb->truesize += frag2->truesize;
+ }
}
slow_path:
@@ -870,8 +878,8 @@ static inline int ip6_rt_check(struct rt6key *rt_key,
struct in6_addr *fl_addr,
struct in6_addr *addr_cache)
{
- return ((rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) &&
- (addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache)));
+ return (rt_key->plen != 128 || !ipv6_addr_equal(fl_addr, &rt_key->addr)) &&
+ (addr_cache == NULL || !ipv6_addr_equal(fl_addr, addr_cache));
}
static struct dst_entry *ip6_sk_dst_check(struct sock *sk,
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 29f99dd..c2c0f89 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -75,7 +75,7 @@ MODULE_LICENSE("GPL");
(addr)->s6_addr32[2] ^ (addr)->s6_addr32[3]) & \
(HASH_SIZE - 1))
-static void ip6_tnl_dev_init(struct net_device *dev);
+static int ip6_tnl_dev_init(struct net_device *dev);
static void ip6_tnl_dev_setup(struct net_device *dev);
static int ip6_tnl_net_id __read_mostly;
@@ -83,15 +83,42 @@ struct ip6_tnl_net {
/* the IPv6 tunnel fallback device */
struct net_device *fb_tnl_dev;
/* lists for storing tunnels in use */
- struct ip6_tnl *tnls_r_l[HASH_SIZE];
- struct ip6_tnl *tnls_wc[1];
- struct ip6_tnl **tnls[2];
+ struct ip6_tnl __rcu *tnls_r_l[HASH_SIZE];
+ struct ip6_tnl __rcu *tnls_wc[1];
+ struct ip6_tnl __rcu **tnls[2];
};
+/* often modified stats are per cpu, other are shared (netdev->stats) */
+struct pcpu_tstats {
+ unsigned long rx_packets;
+ unsigned long rx_bytes;
+ unsigned long tx_packets;
+ unsigned long tx_bytes;
+};
+
+static struct net_device_stats *ip6_get_stats(struct net_device *dev)
+{
+ struct pcpu_tstats sum = { 0 };
+ int i;
+
+ for_each_possible_cpu(i) {
+ const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
+
+ sum.rx_packets += tstats->rx_packets;
+ sum.rx_bytes += tstats->rx_bytes;
+ sum.tx_packets += tstats->tx_packets;
+ sum.tx_bytes += tstats->tx_bytes;
+ }
+ dev->stats.rx_packets = sum.rx_packets;
+ dev->stats.rx_bytes = sum.rx_bytes;
+ dev->stats.tx_packets = sum.tx_packets;
+ dev->stats.tx_bytes = sum.tx_bytes;
+ return &dev->stats;
+}
+
/*
- * Locking : hash tables are protected by RCU and a spinlock
+ * Locking : hash tables are protected by RCU and RTNL
*/
-static DEFINE_SPINLOCK(ip6_tnl_lock);
static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t)
{
@@ -138,8 +165,8 @@ static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst)
static struct ip6_tnl *
ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local)
{
- unsigned h0 = HASH(remote);
- unsigned h1 = HASH(local);
+ unsigned int h0 = HASH(remote);
+ unsigned int h1 = HASH(local);
struct ip6_tnl *t;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
@@ -167,7 +194,7 @@ ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local)
* Return: head of IPv6 tunnel list
**/
-static struct ip6_tnl **
+static struct ip6_tnl __rcu **
ip6_tnl_bucket(struct ip6_tnl_net *ip6n, struct ip6_tnl_parm *p)
{
struct in6_addr *remote = &p->raddr;
@@ -190,12 +217,10 @@ ip6_tnl_bucket(struct ip6_tnl_net *ip6n, struct ip6_tnl_parm *p)
static void
ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
{
- struct ip6_tnl **tp = ip6_tnl_bucket(ip6n, &t->parms);
+ struct ip6_tnl __rcu **tp = ip6_tnl_bucket(ip6n, &t->parms);
- spin_lock_bh(&ip6_tnl_lock);
- t->next = *tp;
+ rcu_assign_pointer(t->next , rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
- spin_unlock_bh(&ip6_tnl_lock);
}
/**
@@ -206,18 +231,25 @@ ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
static void
ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
{
- struct ip6_tnl **tp;
-
- for (tp = ip6_tnl_bucket(ip6n, &t->parms); *tp; tp = &(*tp)->next) {
- if (t == *tp) {
- spin_lock_bh(&ip6_tnl_lock);
- *tp = t->next;
- spin_unlock_bh(&ip6_tnl_lock);
+ struct ip6_tnl __rcu **tp;
+ struct ip6_tnl *iter;
+
+ for (tp = ip6_tnl_bucket(ip6n, &t->parms);
+ (iter = rtnl_dereference(*tp)) != NULL;
+ tp = &iter->next) {
+ if (t == iter) {
+ rcu_assign_pointer(*tp, t->next);
break;
}
}
}
+static void ip6_dev_free(struct net_device *dev)
+{
+ free_percpu(dev->tstats);
+ free_netdev(dev);
+}
+
/**
* ip6_tnl_create() - create a new tunnel
* @p: tunnel parameters
@@ -256,7 +288,9 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p)
t = netdev_priv(dev);
t->parms = *p;
- ip6_tnl_dev_init(dev);
+ err = ip6_tnl_dev_init(dev);
+ if (err < 0)
+ goto failed_free;
if ((err = register_netdevice(dev)) < 0)
goto failed_free;
@@ -266,7 +300,7 @@ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct ip6_tnl_parm *p)
return t;
failed_free:
- free_netdev(dev);
+ ip6_dev_free(dev);
failed:
return NULL;
}
@@ -290,10 +324,13 @@ static struct ip6_tnl *ip6_tnl_locate(struct net *net,
{
struct in6_addr *remote = &p->raddr;
struct in6_addr *local = &p->laddr;
+ struct ip6_tnl __rcu **tp;
struct ip6_tnl *t;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
- for (t = *ip6_tnl_bucket(ip6n, p); t; t = t->next) {
+ for (tp = ip6_tnl_bucket(ip6n, p);
+ (t = rtnl_dereference(*tp)) != NULL;
+ tp = &t->next) {
if (ipv6_addr_equal(local, &t->parms.laddr) &&
ipv6_addr_equal(remote, &t->parms.raddr))
return t;
@@ -318,13 +355,10 @@ ip6_tnl_dev_uninit(struct net_device *dev)
struct net *net = dev_net(dev);
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
- if (dev == ip6n->fb_tnl_dev) {
- spin_lock_bh(&ip6_tnl_lock);
- ip6n->tnls_wc[0] = NULL;
- spin_unlock_bh(&ip6_tnl_lock);
- } else {
+ if (dev == ip6n->fb_tnl_dev)
+ rcu_assign_pointer(ip6n->tnls_wc[0], NULL);
+ else
ip6_tnl_unlink(ip6n, t);
- }
ip6_tnl_dst_reset(t);
dev_put(dev);
}
@@ -702,6 +736,8 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr,
&ipv6h->daddr)) != NULL) {
+ struct pcpu_tstats *tstats;
+
if (t->parms.proto != ipproto && t->parms.proto != 0) {
rcu_read_unlock();
goto discard;
@@ -724,10 +760,16 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol,
skb->pkt_type = PACKET_HOST;
memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
- skb_tunnel_rx(skb, t->dev);
+ tstats = this_cpu_ptr(t->dev->tstats);
+ tstats->rx_packets++;
+ tstats->rx_bytes += skb->len;
+
+ __skb_tunnel_rx(skb, t->dev);
dscp_ecn_decapsulate(t, ipv6h, skb);
+
netif_rx(skb);
+
rcu_read_unlock();
return 0;
}
@@ -934,8 +976,10 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
err = ip6_local_out(skb);
if (net_xmit_eval(err) == 0) {
- stats->tx_bytes += pkt_len;
- stats->tx_packets++;
+ struct pcpu_tstats *tstats = this_cpu_ptr(t->dev->tstats);
+
+ tstats->tx_bytes += pkt_len;
+ tstats->tx_packets++;
} else {
stats->tx_errors++;
stats->tx_aborted_errors++;
@@ -1300,12 +1344,14 @@ ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
static const struct net_device_ops ip6_tnl_netdev_ops = {
- .ndo_uninit = ip6_tnl_dev_uninit,
+ .ndo_uninit = ip6_tnl_dev_uninit,
.ndo_start_xmit = ip6_tnl_xmit,
- .ndo_do_ioctl = ip6_tnl_ioctl,
+ .ndo_do_ioctl = ip6_tnl_ioctl,
.ndo_change_mtu = ip6_tnl_change_mtu,
+ .ndo_get_stats = ip6_get_stats,
};
+
/**
* ip6_tnl_dev_setup - setup virtual tunnel device
* @dev: virtual device associated with tunnel
@@ -1317,7 +1363,7 @@ static const struct net_device_ops ip6_tnl_netdev_ops = {
static void ip6_tnl_dev_setup(struct net_device *dev)
{
dev->netdev_ops = &ip6_tnl_netdev_ops;
- dev->destructor = free_netdev;
+ dev->destructor = ip6_dev_free;
dev->type = ARPHRD_TUNNEL6;
dev->hard_header_len = LL_MAX_HEADER + sizeof (struct ipv6hdr);
@@ -1333,12 +1379,17 @@ static void ip6_tnl_dev_setup(struct net_device *dev)
* @dev: virtual device associated with tunnel
**/
-static inline void
+static inline int
ip6_tnl_dev_init_gen(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
+
t->dev = dev;
strcpy(t->parms.name, dev->name);
+ dev->tstats = alloc_percpu(struct pcpu_tstats);
+ if (!dev->tstats)
+ return -ENOMEM;
+ return 0;
}
/**
@@ -1346,11 +1397,15 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
* @dev: virtual device associated with tunnel
**/
-static void ip6_tnl_dev_init(struct net_device *dev)
+static int ip6_tnl_dev_init(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
- ip6_tnl_dev_init_gen(dev);
+ int err = ip6_tnl_dev_init_gen(dev);
+
+ if (err)
+ return err;
ip6_tnl_link_config(t);
+ return 0;
}
/**
@@ -1360,16 +1415,20 @@ static void ip6_tnl_dev_init(struct net_device *dev)
* Return: 0
**/
-static void __net_init ip6_fb_tnl_dev_init(struct net_device *dev)
+static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct net *net = dev_net(dev);
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+ int err = ip6_tnl_dev_init_gen(dev);
+
+ if (err)
+ return err;
- ip6_tnl_dev_init_gen(dev);
t->parms.proto = IPPROTO_IPV6;
dev_hold(dev);
- ip6n->tnls_wc[0] = t;
+ rcu_assign_pointer(ip6n->tnls_wc[0], t);
+ return 0;
}
static struct xfrm6_tunnel ip4ip6_handler __read_mostly = {
@@ -1391,14 +1450,14 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
LIST_HEAD(list);
for (h = 0; h < HASH_SIZE; h++) {
- t = ip6n->tnls_r_l[h];
+ t = rtnl_dereference(ip6n->tnls_r_l[h]);
while (t != NULL) {
unregister_netdevice_queue(t->dev, &list);
- t = t->next;
+ t = rtnl_dereference(t->next);
}
}
- t = ip6n->tnls_wc[0];
+ t = rtnl_dereference(ip6n->tnls_wc[0]);
unregister_netdevice_queue(t->dev, &list);
unregister_netdevice_many(&list);
}
@@ -1419,7 +1478,9 @@ static int __net_init ip6_tnl_init_net(struct net *net)
goto err_alloc_dev;
dev_net_set(ip6n->fb_tnl_dev, net);
- ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
+ err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
+ if (err < 0)
+ goto err_register;
err = register_netdev(ip6n->fb_tnl_dev);
if (err < 0)
@@ -1427,7 +1488,7 @@ static int __net_init ip6_tnl_init_net(struct net *net)
return 0;
err_register:
- free_netdev(ip6n->fb_tnl_dev);
+ ip6_dev_free(ip6n->fb_tnl_dev);
err_alloc_dev:
return err;
}
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 66078da..6f32ffc 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -667,6 +667,7 @@ static int pim6_rcv(struct sk_buff *skb)
skb_tunnel_rx(skb, reg_dev);
netif_rx(skb);
+
dev_put(reg_dev);
return 0;
drop:
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 69a0051..998d6d2 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -91,7 +91,9 @@
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
-static u32 ndisc_hash(const void *pkey, const struct net_device *dev);
+static u32 ndisc_hash(const void *pkey,
+ const struct net_device *dev,
+ __u32 rnd);
static int ndisc_constructor(struct neighbour *neigh);
static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb);
static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
@@ -228,12 +230,12 @@ static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
do {
cur = ((void *)cur) + (cur->nd_opt_len << 3);
} while(cur < end && cur->nd_opt_type != type);
- return (cur <= end && cur->nd_opt_type == type ? cur : NULL);
+ return cur <= end && cur->nd_opt_type == type ? cur : NULL;
}
static inline int ndisc_is_useropt(struct nd_opt_hdr *opt)
{
- return (opt->nd_opt_type == ND_OPT_RDNSS);
+ return opt->nd_opt_type == ND_OPT_RDNSS;
}
static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur,
@@ -244,7 +246,7 @@ static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur,
do {
cur = ((void *)cur) + (cur->nd_opt_len << 3);
} while(cur < end && !ndisc_is_useropt(cur));
- return (cur <= end && ndisc_is_useropt(cur) ? cur : NULL);
+ return cur <= end && ndisc_is_useropt(cur) ? cur : NULL;
}
static struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
@@ -319,7 +321,7 @@ static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p,
int prepad = ndisc_addr_option_pad(dev->type);
if (lladdrlen != NDISC_OPT_SPACE(dev->addr_len + prepad))
return NULL;
- return (lladdr + prepad);
+ return lladdr + prepad;
}
int ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int dir)
@@ -350,7 +352,9 @@ int ndisc_mc_map(struct in6_addr *addr, char *buf, struct net_device *dev, int d
EXPORT_SYMBOL(ndisc_mc_map);
-static u32 ndisc_hash(const void *pkey, const struct net_device *dev)
+static u32 ndisc_hash(const void *pkey,
+ const struct net_device *dev,
+ __u32 hash_rnd)
{
const u32 *p32 = pkey;
u32 addr_hash, i;
@@ -359,7 +363,7 @@ static u32 ndisc_hash(const void *pkey, const struct net_device *dev)
for (i = 0; i < (sizeof(struct in6_addr) / sizeof(u32)); i++)
addr_hash ^= *p32++;
- return jhash_2words(addr_hash, dev->ifindex, nd_tbl.hash_rnd);
+ return jhash_2words(addr_hash, dev->ifindex, hash_rnd);
}
static int ndisc_constructor(struct neighbour *neigh)
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index c683e9e..51df035 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -82,13 +82,13 @@ EXPORT_SYMBOL_GPL(ip6t_alloc_initial_table);
int
ip6t_ext_hdr(u8 nexthdr)
{
- return ( (nexthdr == IPPROTO_HOPOPTS) ||
- (nexthdr == IPPROTO_ROUTING) ||
- (nexthdr == IPPROTO_FRAGMENT) ||
- (nexthdr == IPPROTO_ESP) ||
- (nexthdr == IPPROTO_AH) ||
- (nexthdr == IPPROTO_NONE) ||
- (nexthdr == IPPROTO_DSTOPTS) );
+ return (nexthdr == IPPROTO_HOPOPTS) ||
+ (nexthdr == IPPROTO_ROUTING) ||
+ (nexthdr == IPPROTO_FRAGMENT) ||
+ (nexthdr == IPPROTO_ESP) ||
+ (nexthdr == IPPROTO_AH) ||
+ (nexthdr == IPPROTO_NONE) ||
+ (nexthdr == IPPROTO_DSTOPTS);
}
/* Returns whether matches rule or not. */
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index e677937..45e6efb7 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -764,7 +764,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
return -EINVAL;
if (sin6->sin6_family && sin6->sin6_family != AF_INET6)
- return(-EAFNOSUPPORT);
+ return -EAFNOSUPPORT;
/* port is the proto value [0..255] carried in nexthdr */
proto = ntohs(sin6->sin6_port);
@@ -772,10 +772,10 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk,
if (!proto)
proto = inet->inet_num;
else if (proto != inet->inet_num)
- return(-EINVAL);
+ return -EINVAL;
if (proto > 255)
- return(-EINVAL);
+ return -EINVAL;
daddr = &sin6->sin6_addr;
if (np->sndflow) {
@@ -985,7 +985,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname,
/* You may get strange result with a positive odd offset;
RFC2292bis agrees with me. */
if (val > 0 && (val&1))
- return(-EINVAL);
+ return -EINVAL;
if (val < 0) {
rp->checksum = 0;
} else {
@@ -997,7 +997,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname,
break;
default:
- return(-ENOPROTOOPT);
+ return -ENOPROTOOPT;
}
}
@@ -1190,7 +1190,7 @@ static int rawv6_init_sk(struct sock *sk)
default:
break;
}
- return(0);
+ return 0;
}
struct proto rawv6_prot = {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d126365..25661f9 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -109,7 +109,6 @@ static struct dst_ops ip6_dst_ops_template = {
.link_failure = ip6_link_failure,
.update_pmtu = ip6_rt_update_pmtu,
.local_out = __ip6_local_out,
- .entries = ATOMIC_INIT(0),
};
static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
@@ -122,7 +121,6 @@ static struct dst_ops ip6_dst_blackhole_ops = {
.destroy = ip6_dst_destroy,
.check = ip6_dst_check,
.update_pmtu = ip6_rt_blackhole_update_pmtu,
- .entries = ATOMIC_INIT(0),
};
static struct rt6_info ip6_null_entry_template = {
@@ -217,14 +215,14 @@ static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
static __inline__ int rt6_check_expired(const struct rt6_info *rt)
{
- return (rt->rt6i_flags & RTF_EXPIRES &&
- time_after(jiffies, rt->rt6i_expires));
+ return (rt->rt6i_flags & RTF_EXPIRES) &&
+ time_after(jiffies, rt->rt6i_expires);
}
static inline int rt6_need_strict(struct in6_addr *daddr)
{
- return (ipv6_addr_type(daddr) &
- (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK));
+ return ipv6_addr_type(daddr) &
+ (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
}
/*
@@ -440,7 +438,7 @@ static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
__func__, match);
net = dev_net(rt0->rt6i_dev);
- return (match ? match : net->ipv6.ip6_null_entry);
+ return match ? match : net->ipv6.ip6_null_entry;
}
#ifdef CONFIG_IPV6_ROUTE_INFO
@@ -670,7 +668,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad
if (net_ratelimit())
printk(KERN_WARNING
- "Neighbour table overflow.\n");
+ "ipv6: Neighbour table overflow.\n");
dst_free(&rt->dst);
return NULL;
}
@@ -859,7 +857,7 @@ int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl
dst_release(*dstp);
*dstp = new;
- return (new ? 0 : -ENOMEM);
+ return new ? 0 : -ENOMEM;
}
EXPORT_SYMBOL_GPL(ip6_dst_blackhole);
@@ -1058,19 +1056,22 @@ static int ip6_dst_gc(struct dst_ops *ops)
int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity;
int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout;
unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc;
+ int entries;
+ entries = dst_entries_get_fast(ops);
if (time_after(rt_last_gc + rt_min_interval, now) &&
- atomic_read(&ops->entries) <= rt_max_size)
+ entries <= rt_max_size)
goto out;
net->ipv6.ip6_rt_gc_expire++;
fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net);
net->ipv6.ip6_rt_last_gc = now;
- if (atomic_read(&ops->entries) < ops->gc_thresh)
+ entries = dst_entries_get_slow(ops);
+ if (entries < ops->gc_thresh)
net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1;
out:
net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity;
- return (atomic_read(&ops->entries) > rt_max_size);
+ return entries > rt_max_size;
}
/* Clean host part of a prefix. Not necessary in radix tree,
@@ -1169,6 +1170,8 @@ int ip6_route_add(struct fib6_config *cfg)
if (addr_type & IPV6_ADDR_MULTICAST)
rt->dst.input = ip6_mc_input;
+ else if (cfg->fc_flags & RTF_LOCAL)
+ rt->dst.input = ip6_input;
else
rt->dst.input = ip6_forward;
@@ -1190,7 +1193,8 @@ int ip6_route_add(struct fib6_config *cfg)
they would result in kernel looping; promote them to reject routes
*/
if ((cfg->fc_flags & RTF_REJECT) ||
- (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK))) {
+ (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK)
+ && !(cfg->fc_flags&RTF_LOCAL))) {
/* hold loopback dev/idev if we haven't done so. */
if (dev != net->loopback_dev) {
if (dev) {
@@ -1556,14 +1560,13 @@ out:
* i.e. Path MTU discovery
*/
-void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
- struct net_device *dev, u32 pmtu)
+static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr,
+ struct net *net, u32 pmtu, int ifindex)
{
struct rt6_info *rt, *nrt;
- struct net *net = dev_net(dev);
int allfrag = 0;
- rt = rt6_lookup(net, daddr, saddr, dev->ifindex, 0);
+ rt = rt6_lookup(net, daddr, saddr, ifindex, 0);
if (rt == NULL)
return;
@@ -1631,6 +1634,27 @@ out:
dst_release(&rt->dst);
}
+void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
+ struct net_device *dev, u32 pmtu)
+{
+ struct net *net = dev_net(dev);
+
+ /*
+ * RFC 1981 states that a node "MUST reduce the size of the packets it
+ * is sending along the path" that caused the Packet Too Big message.
+ * Since it's not possible in the general case to determine which
+ * interface was used to send the original packet, we update the MTU
+ * on the interface that will be used to send future packets. We also
+ * update the MTU on the interface that received the Packet Too Big in
+ * case the original packet was forced out that interface with
+ * SO_BINDTODEVICE or similar. This is the next best thing to the
+ * correct behaviour, which would be to update the MTU on all
+ * interfaces.
+ */
+ rt6_do_pmtu_disc(daddr, saddr, net, pmtu, 0);
+ rt6_do_pmtu_disc(daddr, saddr, net, pmtu, dev->ifindex);
+}
+
/*
* Misc support functions
*/
@@ -2082,6 +2106,9 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
if (rtm->rtm_type == RTN_UNREACHABLE)
cfg->fc_flags |= RTF_REJECT;
+ if (rtm->rtm_type == RTN_LOCAL)
+ cfg->fc_flags |= RTF_LOCAL;
+
cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid;
cfg->fc_nlinfo.nlh = nlh;
cfg->fc_nlinfo.nl_net = sock_net(skb->sk);
@@ -2202,6 +2229,8 @@ static int rt6_fill_node(struct net *net,
NLA_PUT_U32(skb, RTA_TABLE, table);
if (rt->rt6i_flags&RTF_REJECT)
rtm->rtm_type = RTN_UNREACHABLE;
+ else if (rt->rt6i_flags&RTF_LOCAL)
+ rtm->rtm_type = RTN_LOCAL;
else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK))
rtm->rtm_type = RTN_LOCAL;
else
@@ -2496,7 +2525,7 @@ static int rt6_stats_seq_show(struct seq_file *seq, void *v)
net->ipv6.rt6_stats->fib_rt_alloc,
net->ipv6.rt6_stats->fib_rt_entries,
net->ipv6.rt6_stats->fib_rt_cache,
- atomic_read(&net->ipv6.ip6_dst_ops.entries),
+ dst_entries_get_slow(&net->ipv6.ip6_dst_ops),
net->ipv6.rt6_stats->fib_discarded_routes);
return 0;
@@ -2638,11 +2667,14 @@ static int __net_init ip6_route_net_init(struct net *net)
memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template,
sizeof(net->ipv6.ip6_dst_ops));
+ if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0)
+ goto out_ip6_dst_ops;
+
net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template,
sizeof(*net->ipv6.ip6_null_entry),
GFP_KERNEL);
if (!net->ipv6.ip6_null_entry)
- goto out_ip6_dst_ops;
+ goto out_ip6_dst_entries;
net->ipv6.ip6_null_entry->dst.path =
(struct dst_entry *)net->ipv6.ip6_null_entry;
net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops;
@@ -2692,6 +2724,8 @@ out_ip6_prohibit_entry:
out_ip6_null_entry:
kfree(net->ipv6.ip6_null_entry);
#endif
+out_ip6_dst_entries:
+ dst_entries_destroy(&net->ipv6.ip6_dst_ops);
out_ip6_dst_ops:
goto out;
}
@@ -2730,10 +2764,14 @@ int __init ip6_route_init(void)
if (!ip6_dst_ops_template.kmem_cachep)
goto out;
- ret = register_pernet_subsys(&ip6_route_net_ops);
+ ret = dst_entries_init(&ip6_dst_blackhole_ops);
if (ret)
goto out_kmem_cache;
+ ret = register_pernet_subsys(&ip6_route_net_ops);
+ if (ret)
+ goto out_dst_entries;
+
ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep;
/* Registering of the loopback is done before this portion of code,
@@ -2780,6 +2818,8 @@ out_fib6_init:
fib6_gc_cleanup();
out_register_subsys:
unregister_pernet_subsys(&ip6_route_net_ops);
+out_dst_entries:
+ dst_entries_destroy(&ip6_dst_blackhole_ops);
out_kmem_cache:
kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep);
goto out;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 86618eb..367a6cc 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -63,36 +63,63 @@
#define HASH_SIZE 16
#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
-static void ipip6_tunnel_init(struct net_device *dev);
+static int ipip6_tunnel_init(struct net_device *dev);
static void ipip6_tunnel_setup(struct net_device *dev);
+static void ipip6_dev_free(struct net_device *dev);
static int sit_net_id __read_mostly;
struct sit_net {
- struct ip_tunnel *tunnels_r_l[HASH_SIZE];
- struct ip_tunnel *tunnels_r[HASH_SIZE];
- struct ip_tunnel *tunnels_l[HASH_SIZE];
- struct ip_tunnel *tunnels_wc[1];
- struct ip_tunnel **tunnels[4];
+ struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE];
+ struct ip_tunnel __rcu *tunnels_r[HASH_SIZE];
+ struct ip_tunnel __rcu *tunnels_l[HASH_SIZE];
+ struct ip_tunnel __rcu *tunnels_wc[1];
+ struct ip_tunnel __rcu **tunnels[4];
struct net_device *fb_tunnel_dev;
};
/*
- * Locking : hash tables are protected by RCU and a spinlock
+ * Locking : hash tables are protected by RCU and RTNL
*/
-static DEFINE_SPINLOCK(ipip6_lock);
#define for_each_ip_tunnel_rcu(start) \
for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
+/* often modified stats are per cpu, other are shared (netdev->stats) */
+struct pcpu_tstats {
+ unsigned long rx_packets;
+ unsigned long rx_bytes;
+ unsigned long tx_packets;
+ unsigned long tx_bytes;
+};
+
+static struct net_device_stats *ipip6_get_stats(struct net_device *dev)
+{
+ struct pcpu_tstats sum = { 0 };
+ int i;
+
+ for_each_possible_cpu(i) {
+ const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
+
+ sum.rx_packets += tstats->rx_packets;
+ sum.rx_bytes += tstats->rx_bytes;
+ sum.tx_packets += tstats->tx_packets;
+ sum.tx_bytes += tstats->tx_bytes;
+ }
+ dev->stats.rx_packets = sum.rx_packets;
+ dev->stats.rx_bytes = sum.rx_bytes;
+ dev->stats.tx_packets = sum.tx_packets;
+ dev->stats.tx_bytes = sum.tx_bytes;
+ return &dev->stats;
+}
/*
* Must be invoked with rcu_read_lock
*/
static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net,
struct net_device *dev, __be32 remote, __be32 local)
{
- unsigned h0 = HASH(remote);
- unsigned h1 = HASH(local);
+ unsigned int h0 = HASH(remote);
+ unsigned int h1 = HASH(local);
struct ip_tunnel *t;
struct sit_net *sitn = net_generic(net, sit_net_id);
@@ -121,12 +148,12 @@ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net,
return NULL;
}
-static struct ip_tunnel **__ipip6_bucket(struct sit_net *sitn,
+static struct ip_tunnel __rcu **__ipip6_bucket(struct sit_net *sitn,
struct ip_tunnel_parm *parms)
{
__be32 remote = parms->iph.daddr;
__be32 local = parms->iph.saddr;
- unsigned h = 0;
+ unsigned int h = 0;
int prio = 0;
if (remote) {
@@ -140,7 +167,7 @@ static struct ip_tunnel **__ipip6_bucket(struct sit_net *sitn,
return &sitn->tunnels[prio][h];
}
-static inline struct ip_tunnel **ipip6_bucket(struct sit_net *sitn,
+static inline struct ip_tunnel __rcu **ipip6_bucket(struct sit_net *sitn,
struct ip_tunnel *t)
{
return __ipip6_bucket(sitn, &t->parms);
@@ -148,13 +175,14 @@ static inline struct ip_tunnel **ipip6_bucket(struct sit_net *sitn,
static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t)
{
- struct ip_tunnel **tp;
-
- for (tp = ipip6_bucket(sitn, t); *tp; tp = &(*tp)->next) {
- if (t == *tp) {
- spin_lock_bh(&ipip6_lock);
- *tp = t->next;
- spin_unlock_bh(&ipip6_lock);
+ struct ip_tunnel __rcu **tp;
+ struct ip_tunnel *iter;
+
+ for (tp = ipip6_bucket(sitn, t);
+ (iter = rtnl_dereference(*tp)) != NULL;
+ tp = &iter->next) {
+ if (t == iter) {
+ rcu_assign_pointer(*tp, t->next);
break;
}
}
@@ -162,12 +190,10 @@ static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t)
static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t)
{
- struct ip_tunnel **tp = ipip6_bucket(sitn, t);
+ struct ip_tunnel __rcu **tp = ipip6_bucket(sitn, t);
- spin_lock_bh(&ipip6_lock);
- t->next = *tp;
+ rcu_assign_pointer(t->next, rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
- spin_unlock_bh(&ipip6_lock);
}
static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
@@ -187,17 +213,20 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
#endif
}
-static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
+static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
struct ip_tunnel_parm *parms, int create)
{
__be32 remote = parms->iph.daddr;
__be32 local = parms->iph.saddr;
- struct ip_tunnel *t, **tp, *nt;
+ struct ip_tunnel *t, *nt;
+ struct ip_tunnel __rcu **tp;
struct net_device *dev;
char name[IFNAMSIZ];
struct sit_net *sitn = net_generic(net, sit_net_id);
- for (tp = __ipip6_bucket(sitn, parms); (t = *tp) != NULL; tp = &t->next) {
+ for (tp = __ipip6_bucket(sitn, parms);
+ (t = rtnl_dereference(*tp)) != NULL;
+ tp = &t->next) {
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr &&
parms->link == t->parms.link) {
@@ -213,7 +242,7 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
if (parms->name[0])
strlcpy(name, parms->name, IFNAMSIZ);
else
- sprintf(name, "sit%%d");
+ strcpy(name, "sit%d");
dev = alloc_netdev(sizeof(*t), name, ipip6_tunnel_setup);
if (dev == NULL)
@@ -229,7 +258,8 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
nt = netdev_priv(dev);
nt->parms = *parms;
- ipip6_tunnel_init(dev);
+ if (ipip6_tunnel_init(dev) < 0)
+ goto failed_free;
ipip6_tunnel_clone_6rd(dev, sitn);
if (parms->i_flags & SIT_ISATAP)
@@ -244,7 +274,7 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
return nt;
failed_free:
- free_netdev(dev);
+ ipip6_dev_free(dev);
failed:
return NULL;
}
@@ -340,7 +370,7 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg)
ASSERT_RTNL();
- for (p = t->prl; p; p = p->next) {
+ for (p = rtnl_dereference(t->prl); p; p = rtnl_dereference(p->next)) {
if (p->addr == a->addr) {
if (chg) {
p->flags = a->flags;
@@ -451,15 +481,12 @@ static void ipip6_tunnel_uninit(struct net_device *dev)
struct sit_net *sitn = net_generic(net, sit_net_id);
if (dev == sitn->fb_tunnel_dev) {
- spin_lock_bh(&ipip6_lock);
- sitn->tunnels_wc[0] = NULL;
- spin_unlock_bh(&ipip6_lock);
- dev_put(dev);
+ rcu_assign_pointer(sitn->tunnels_wc[0], NULL);
} else {
ipip6_tunnel_unlink(sitn, netdev_priv(dev));
ipip6_tunnel_del_prl(netdev_priv(dev), NULL);
- dev_put(dev);
}
+ dev_put(dev);
}
@@ -548,6 +575,8 @@ static int ipip6_rcv(struct sk_buff *skb)
tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
iph->saddr, iph->daddr);
if (tunnel != NULL) {
+ struct pcpu_tstats *tstats;
+
secpath_reset(skb);
skb->mac_header = skb->network_header;
skb_reset_network_header(skb);
@@ -563,10 +592,16 @@ static int ipip6_rcv(struct sk_buff *skb)
return 0;
}
- skb_tunnel_rx(skb, tunnel->dev);
+ tstats = this_cpu_ptr(tunnel->dev->tstats);
+ tstats->rx_packets++;
+ tstats->rx_bytes += skb->len;
+
+ __skb_tunnel_rx(skb, tunnel->dev);
ipip6_ecn_decapsulate(iph, skb);
+
netif_rx(skb);
+
rcu_read_unlock();
return 0;
}
@@ -590,7 +625,7 @@ __be32 try_6rd(struct in6_addr *v6dst, struct ip_tunnel *tunnel)
#ifdef CONFIG_IPV6_SIT_6RD
if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix,
tunnel->ip6rd.prefixlen)) {
- unsigned pbw0, pbi0;
+ unsigned int pbw0, pbi0;
int pbi1;
u32 d;
@@ -625,14 +660,13 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
- struct net_device_stats *stats = &dev->stats;
- struct netdev_queue *txq = netdev_get_tx_queue(dev, 0);
+ struct pcpu_tstats *tstats;
struct iphdr *tiph = &tunnel->parms.iph;
struct ipv6hdr *iph6 = ipv6_hdr(skb);
u8 tos = tunnel->parms.iph.tos;
__be16 df = tiph->frag_off;
struct rtable *rt; /* Route to the other host */
- struct net_device *tdev; /* Device to other host */
+ struct net_device *tdev; /* Device to other host */
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst = tiph->daddr;
@@ -703,20 +737,20 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
.oif = tunnel->parms.link,
.proto = IPPROTO_IPV6 };
if (ip_route_output_key(dev_net(dev), &rt, &fl)) {
- stats->tx_carrier_errors++;
+ dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
}
if (rt->rt_type != RTN_UNICAST) {
ip_rt_put(rt);
- stats->tx_carrier_errors++;
+ dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
tdev = rt->dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
- stats->collisions++;
+ dev->stats.collisions++;
goto tx_error;
}
@@ -724,7 +758,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
if (mtu < 68) {
- stats->collisions++;
+ dev->stats.collisions++;
ip_rt_put(rt);
goto tx_error;
}
@@ -763,7 +797,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
- txq->tx_dropped++;
+ dev->stats.tx_dropped++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
@@ -799,14 +833,14 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
iph->ttl = iph6->hop_limit;
nf_reset(skb);
-
- IPTUNNEL_XMIT();
+ tstats = this_cpu_ptr(dev->tstats);
+ __IPTUNNEL_XMIT(tstats, &dev->stats);
return NETDEV_TX_OK;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
- stats->tx_errors++;
+ dev->stats.tx_errors++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
@@ -1083,12 +1117,19 @@ static const struct net_device_ops ipip6_netdev_ops = {
.ndo_start_xmit = ipip6_tunnel_xmit,
.ndo_do_ioctl = ipip6_tunnel_ioctl,
.ndo_change_mtu = ipip6_tunnel_change_mtu,
+ .ndo_get_stats = ipip6_get_stats,
};
+static void ipip6_dev_free(struct net_device *dev)
+{
+ free_percpu(dev->tstats);
+ free_netdev(dev);
+}
+
static void ipip6_tunnel_setup(struct net_device *dev)
{
dev->netdev_ops = &ipip6_netdev_ops;
- dev->destructor = free_netdev;
+ dev->destructor = ipip6_dev_free;
dev->type = ARPHRD_SIT;
dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr);
@@ -1098,9 +1139,10 @@ static void ipip6_tunnel_setup(struct net_device *dev)
dev->iflink = 0;
dev->addr_len = 4;
dev->features |= NETIF_F_NETNS_LOCAL;
+ dev->features |= NETIF_F_LLTX;
}
-static void ipip6_tunnel_init(struct net_device *dev)
+static int ipip6_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
@@ -1111,9 +1153,14 @@ static void ipip6_tunnel_init(struct net_device *dev)
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
ipip6_tunnel_bind_dev(dev);
+ dev->tstats = alloc_percpu(struct pcpu_tstats);
+ if (!dev->tstats)
+ return -ENOMEM;
+
+ return 0;
}
-static void __net_init ipip6_fb_tunnel_init(struct net_device *dev)
+static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
@@ -1128,8 +1175,12 @@ static void __net_init ipip6_fb_tunnel_init(struct net_device *dev)
iph->ihl = 5;
iph->ttl = 64;
+ dev->tstats = alloc_percpu(struct pcpu_tstats);
+ if (!dev->tstats)
+ return -ENOMEM;
dev_hold(dev);
sitn->tunnels_wc[0] = tunnel;
+ return 0;
}
static struct xfrm_tunnel sit_handler __read_mostly = {
@@ -1173,7 +1224,10 @@ static int __net_init sit_init_net(struct net *net)
}
dev_net_set(sitn->fb_tunnel_dev, net);
- ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
+ err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
+ if (err)
+ goto err_dev_free;
+
ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
if ((err = register_netdev(sitn->fb_tunnel_dev)))
@@ -1183,7 +1237,8 @@ static int __net_init sit_init_net(struct net *net)
err_reg_dev:
dev_put(sitn->fb_tunnel_dev);
- free_netdev(sitn->fb_tunnel_dev);
+err_dev_free:
+ ipip6_dev_free(sitn->fb_tunnel_dev);
err_alloc_dev:
return err;
}
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index ba5258ef..7e41e2c 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -139,7 +139,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
return -EINVAL;
if (usin->sin6_family != AF_INET6)
- return(-EAFNOSUPPORT);
+ return -EAFNOSUPPORT;
memset(&fl, 0, sizeof(fl));
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 6baeabb..7e74023 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -199,7 +199,7 @@ static inline int xfrm6_garbage_collect(struct dst_ops *ops)
struct net *net = container_of(ops, struct net, xfrm.xfrm6_dst_ops);
xfrm6_policy_afinfo.garbage_collect(net);
- return (atomic_read(&ops->entries) > ops->gc_thresh * 2);
+ return dst_entries_get_fast(ops) > ops->gc_thresh * 2;
}
static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu)
@@ -255,7 +255,6 @@ static struct dst_ops xfrm6_dst_ops = {
.ifdown = xfrm6_dst_ifdown,
.local_out = __ip6_local_out,
.gc_thresh = 1024,
- .entries = ATOMIC_INIT(0),
};
static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
@@ -312,11 +311,13 @@ int __init xfrm6_init(void)
*/
gc_thresh = FIB6_TABLE_HASHSZ * 8;
xfrm6_dst_ops.gc_thresh = (gc_thresh < 1024) ? 1024 : gc_thresh;
+ dst_entries_init(&xfrm6_dst_ops);
ret = xfrm6_policy_init();
- if (ret)
+ if (ret) {
+ dst_entries_destroy(&xfrm6_dst_ops);
goto out;
-
+ }
ret = xfrm6_state_init();
if (ret)
goto out_policy;
@@ -341,4 +342,5 @@ void xfrm6_fini(void)
//xfrm6_input_fini();
xfrm6_policy_fini();
xfrm6_state_fini();
+ dst_entries_destroy(&xfrm6_dst_ops);
}
diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c
index f417b77..a67575d 100644
--- a/net/ipv6/xfrm6_state.c
+++ b/net/ipv6/xfrm6_state.c
@@ -20,23 +20,27 @@
#include <net/addrconf.h>
static void
-__xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl,
- struct xfrm_tmpl *tmpl,
- xfrm_address_t *daddr, xfrm_address_t *saddr)
+__xfrm6_init_tempsel(struct xfrm_selector *sel, struct flowi *fl)
{
/* Initialize temporary selector matching only
* to current session. */
- ipv6_addr_copy((struct in6_addr *)&x->sel.daddr, &fl->fl6_dst);
- ipv6_addr_copy((struct in6_addr *)&x->sel.saddr, &fl->fl6_src);
- x->sel.dport = xfrm_flowi_dport(fl);
- x->sel.dport_mask = htons(0xffff);
- x->sel.sport = xfrm_flowi_sport(fl);
- x->sel.sport_mask = htons(0xffff);
- x->sel.family = AF_INET6;
- x->sel.prefixlen_d = 128;
- x->sel.prefixlen_s = 128;
- x->sel.proto = fl->proto;
- x->sel.ifindex = fl->oif;
+ ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl->fl6_dst);
+ ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl->fl6_src);
+ sel->dport = xfrm_flowi_dport(fl);
+ sel->dport_mask = htons(0xffff);
+ sel->sport = xfrm_flowi_sport(fl);
+ sel->sport_mask = htons(0xffff);
+ sel->family = AF_INET6;
+ sel->prefixlen_d = 128;
+ sel->prefixlen_s = 128;
+ sel->proto = fl->proto;
+ sel->ifindex = fl->oif;
+}
+
+static void
+xfrm6_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl,
+ xfrm_address_t *daddr, xfrm_address_t *saddr)
+{
x->id = tmpl->id;
if (ipv6_addr_any((struct in6_addr*)&x->id.daddr))
memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr));
@@ -168,6 +172,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = {
.eth_proto = htons(ETH_P_IPV6),
.owner = THIS_MODULE,
.init_tempsel = __xfrm6_init_tempsel,
+ .init_temprop = xfrm6_init_temprop,
.tmpl_sort = __xfrm6_tmpl_sort,
.state_sort = __xfrm6_state_sort,
.output = xfrm6_output,
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index ac7584b..2969cad 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -199,7 +199,7 @@ static void x6spi_destroy_rcu(struct rcu_head *head)
container_of(head, struct xfrm6_tunnel_spi, rcu_head));
}
-void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr)
+static void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr)
{
struct xfrm6_tunnel_net *xfrm6_tn = xfrm6_tunnel_pernet(net);
struct xfrm6_tunnel_spi *x6spi;
@@ -223,8 +223,6 @@ void xfrm6_tunnel_free_spi(struct net *net, xfrm_address_t *saddr)
spin_unlock_bh(&xfrm6_tunnel_spi_lock);
}
-EXPORT_SYMBOL(xfrm6_tunnel_free_spi);
-
static int xfrm6_tunnel_output(struct xfrm_state *x, struct sk_buff *skb)
{
skb_push(skb, -skb_network_offset(skb));
generated by cgit v0.10.2 at 2024-09-15 22:46:26 (GMT)