summaryrefslogtreecommitdiff
path: root/net/ipv4/ip_gre.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2010-10-23 11:47:02 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-10-23 11:47:02 -0700
commit5f05647dd81c11a6a165ccc8f0c1370b16f3bcb0 (patch)
tree7851ef1c93aa1aba7ef327ca4b75fd35e6d10f29 /net/ipv4/ip_gre.c
parent02f36038c568111ad4fc433f6fa760ff5e38fab4 (diff)
parentec37a48d1d16c30b655ac5280209edf52a6775d4 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1699 commits) bnx2/bnx2x: Unsupported Ethtool operations should return -EINVAL. vlan: Calling vlan_hwaccel_do_receive() is always valid. tproxy: use the interface primary IP address as a default value for --on-ip tproxy: added IPv6 support to the socket match cxgb3: function namespace cleanup tproxy: added IPv6 support to the TPROXY target tproxy: added IPv6 socket lookup function to nf_tproxy_core be2net: Changes to use only priority codes allowed by f/w tproxy: allow non-local binds of IPv6 sockets if IP_TRANSPARENT is enabled tproxy: added tproxy sockopt interface in the IPV6 layer tproxy: added udp6_lib_lookup function tproxy: added const specifiers to udp lookup functions tproxy: split off ipv6 defragmentation to a separate module l2tp: small cleanup nf_nat: restrict ICMP translation for embedded header can: mcp251x: fix generation of error frames can: mcp251x: fix endless loop in interrupt handler if CANINTF_MERRF is set can-raw: add msg_flags to distinguish local traffic 9p: client code cleanup rds: make local functions/variables static ... Fix up conflicts in net/core/dev.c, drivers/net/pcmcia/smc91c92_cs.c and drivers/net/wireless/ath/ath9k/debug.c as per David
Diffstat (limited to 'net/ipv4/ip_gre.c')
-rw-r--r--net/ipv4/ip_gre.c237
1 files changed, 154 insertions, 83 deletions
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 35c93e8b6a46..d0ffcbe369b7 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -44,6 +44,7 @@
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
+#include <net/gre.h>
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
#include <net/ipv6.h>
@@ -63,13 +64,13 @@
We cannot track such dead loops during route installation,
it is infeasible task. The most general solutions would be
to keep skb->encapsulation counter (sort of local ttl),
- and silently drop packet when it expires. It is the best
+ and silently drop packet when it expires. It is a good
solution, but it supposes maintaing new variable in ALL
skb, even if no tunneling is used.
- Current solution: HARD_TX_LOCK lock breaks dead loops.
-
-
+ Current solution: xmit_recursion breaks dead loops. This is a percpu
+ counter, since when we enter the first ndo_xmit(), cpu migration is
+ forbidden. We force an exit if this counter reaches RECURSION_LIMIT
2. Networking dead loops would not kill routers, but would really
kill network. IP hop limit plays role of "t->recursion" in this case,
@@ -128,7 +129,7 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev);
static int ipgre_net_id __read_mostly;
struct ipgre_net {
- struct ip_tunnel *tunnels[4][HASH_SIZE];
+ struct ip_tunnel __rcu *tunnels[4][HASH_SIZE];
struct net_device *fb_tunnel_dev;
};
@@ -158,13 +159,40 @@ struct ipgre_net {
#define tunnels_l tunnels[1]
#define tunnels_wc tunnels[0]
/*
- * Locking : hash tables are protected by RCU and a spinlock
+ * Locking : hash tables are protected by RCU and RTNL
*/
-static DEFINE_SPINLOCK(ipgre_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 *ipgre_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;
+}
+
/* Given src, dst and key, find appropriate for input tunnel. */
static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev,
@@ -173,8 +201,8 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev,
{
struct net *net = dev_net(dev);
int link = dev->ifindex;
- unsigned h0 = HASH(remote);
- unsigned h1 = HASH(key);
+ unsigned int h0 = HASH(remote);
+ unsigned int h1 = HASH(key);
struct ip_tunnel *t, *cand = NULL;
struct ipgre_net *ign = net_generic(net, ipgre_net_id);
int dev_type = (gre_proto == htons(ETH_P_TEB)) ?
@@ -289,13 +317,13 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev,
return NULL;
}
-static struct ip_tunnel **__ipgre_bucket(struct ipgre_net *ign,
+static struct ip_tunnel __rcu **__ipgre_bucket(struct ipgre_net *ign,
struct ip_tunnel_parm *parms)
{
__be32 remote = parms->iph.daddr;
__be32 local = parms->iph.saddr;
__be32 key = parms->i_key;
- unsigned h = HASH(key);
+ unsigned int h = HASH(key);
int prio = 0;
if (local)
@@ -308,7 +336,7 @@ static struct ip_tunnel **__ipgre_bucket(struct ipgre_net *ign,
return &ign->tunnels[prio][h];
}
-static inline struct ip_tunnel **ipgre_bucket(struct ipgre_net *ign,
+static inline struct ip_tunnel __rcu **ipgre_bucket(struct ipgre_net *ign,
struct ip_tunnel *t)
{
return __ipgre_bucket(ign, &t->parms);
@@ -316,23 +344,22 @@ static inline struct ip_tunnel **ipgre_bucket(struct ipgre_net *ign,
static void ipgre_tunnel_link(struct ipgre_net *ign, struct ip_tunnel *t)
{
- struct ip_tunnel **tp = ipgre_bucket(ign, t);
+ struct ip_tunnel __rcu **tp = ipgre_bucket(ign, t);
- spin_lock_bh(&ipgre_lock);
- t->next = *tp;
+ rcu_assign_pointer(t->next, rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
- spin_unlock_bh(&ipgre_lock);
}
static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t)
{
- struct ip_tunnel **tp;
-
- for (tp = ipgre_bucket(ign, t); *tp; tp = &(*tp)->next) {
- if (t == *tp) {
- spin_lock_bh(&ipgre_lock);
- *tp = t->next;
- spin_unlock_bh(&ipgre_lock);
+ struct ip_tunnel __rcu **tp;
+ struct ip_tunnel *iter;
+
+ for (tp = ipgre_bucket(ign, t);
+ (iter = rtnl_dereference(*tp)) != NULL;
+ tp = &iter->next) {
+ if (t == iter) {
+ rcu_assign_pointer(*tp, t->next);
break;
}
}
@@ -346,10 +373,13 @@ static struct ip_tunnel *ipgre_tunnel_find(struct net *net,
__be32 local = parms->iph.saddr;
__be32 key = parms->i_key;
int link = parms->link;
- struct ip_tunnel *t, **tp;
+ struct ip_tunnel *t;
+ struct ip_tunnel __rcu **tp;
struct ipgre_net *ign = net_generic(net, ipgre_net_id);
- for (tp = __ipgre_bucket(ign, parms); (t = *tp) != NULL; tp = &t->next)
+ for (tp = __ipgre_bucket(ign, parms);
+ (t = rtnl_dereference(*tp)) != NULL;
+ tp = &t->next)
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr &&
key == t->parms.i_key &&
@@ -360,7 +390,7 @@ static struct ip_tunnel *ipgre_tunnel_find(struct net *net,
return t;
}
-static struct ip_tunnel * ipgre_tunnel_locate(struct net *net,
+static struct ip_tunnel *ipgre_tunnel_locate(struct net *net,
struct ip_tunnel_parm *parms, int create)
{
struct ip_tunnel *t, *nt;
@@ -582,7 +612,7 @@ static int ipgre_rcv(struct sk_buff *skb)
if ((tunnel = ipgre_tunnel_lookup(skb->dev,
iph->saddr, iph->daddr, key,
gre_proto))) {
- struct net_device_stats *stats = &tunnel->dev->stats;
+ struct pcpu_tstats *tstats;
secpath_reset(skb);
@@ -606,22 +636,22 @@ static int ipgre_rcv(struct sk_buff *skb)
/* Looped back packet, drop it! */
if (skb_rtable(skb)->fl.iif == 0)
goto drop;
- stats->multicast++;
+ tunnel->dev->stats.multicast++;
skb->pkt_type = PACKET_BROADCAST;
}
#endif
if (((flags&GRE_CSUM) && csum) ||
(!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) {
- stats->rx_crc_errors++;
- stats->rx_errors++;
+ tunnel->dev->stats.rx_crc_errors++;
+ tunnel->dev->stats.rx_errors++;
goto drop;
}
if (tunnel->parms.i_flags&GRE_SEQ) {
if (!(flags&GRE_SEQ) ||
(tunnel->i_seqno && (s32)(seqno - tunnel->i_seqno) < 0)) {
- stats->rx_fifo_errors++;
- stats->rx_errors++;
+ tunnel->dev->stats.rx_fifo_errors++;
+ tunnel->dev->stats.rx_errors++;
goto drop;
}
tunnel->i_seqno = seqno + 1;
@@ -630,8 +660,8 @@ static int ipgre_rcv(struct sk_buff *skb)
/* Warning: All skb pointers will be invalidated! */
if (tunnel->dev->type == ARPHRD_ETHER) {
if (!pskb_may_pull(skb, ETH_HLEN)) {
- stats->rx_length_errors++;
- stats->rx_errors++;
+ tunnel->dev->stats.rx_length_errors++;
+ tunnel->dev->stats.rx_errors++;
goto drop;
}
@@ -640,14 +670,19 @@ static int ipgre_rcv(struct sk_buff *skb)
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
}
- 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);
skb_reset_network_header(skb);
ipgre_ecn_decapsulate(iph, skb);
netif_rx(skb);
+
rcu_read_unlock();
- return(0);
+ return 0;
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
@@ -655,20 +690,19 @@ drop:
rcu_read_unlock();
drop_nolock:
kfree_skb(skb);
- return(0);
+ return 0;
}
static netdev_tx_t ipgre_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 *old_iph = ip_hdr(skb);
struct iphdr *tiph;
u8 tos;
__be16 df;
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 */
int gre_hlen;
@@ -690,7 +724,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
/* NBMA tunnel */
if (skb_dst(skb) == NULL) {
- stats->tx_fifo_errors++;
+ dev->stats.tx_fifo_errors++;
goto tx_error;
}
@@ -736,14 +770,20 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
}
{
- struct flowi fl = { .oif = tunnel->parms.link,
- .nl_u = { .ip4_u =
- { .daddr = dst,
- .saddr = tiph->saddr,
- .tos = RT_TOS(tos) } },
- .proto = IPPROTO_GRE };
+ struct flowi fl = {
+ .oif = tunnel->parms.link,
+ .nl_u = {
+ .ip4_u = {
+ .daddr = dst,
+ .saddr = tiph->saddr,
+ .tos = RT_TOS(tos)
+ }
+ },
+ .proto = IPPROTO_GRE
+ }
+;
if (ip_route_output_key(dev_net(dev), &rt, &fl)) {
- stats->tx_carrier_errors++;
+ dev->stats.tx_carrier_errors++;
goto tx_error;
}
}
@@ -751,7 +791,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
if (tdev == dev) {
ip_rt_put(rt);
- stats->collisions++;
+ dev->stats.collisions++;
goto tx_error;
}
@@ -814,7 +854,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
dev->needed_headroom = max_headroom;
if (!new_skb) {
ip_rt_put(rt);
- txq->tx_dropped++;
+ dev->stats.tx_dropped++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
@@ -881,15 +921,15 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
}
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;
}
@@ -909,13 +949,19 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev)
/* Guess output device to choose reasonable mtu and needed_headroom */
if (iph->daddr) {
- struct flowi fl = { .oif = tunnel->parms.link,
- .nl_u = { .ip4_u =
- { .daddr = iph->daddr,
- .saddr = iph->saddr,
- .tos = RT_TOS(iph->tos) } },
- .proto = IPPROTO_GRE };
+ struct flowi fl = {
+ .oif = tunnel->parms.link,
+ .nl_u = {
+ .ip4_u = {
+ .daddr = iph->daddr,
+ .saddr = iph->saddr,
+ .tos = RT_TOS(iph->tos)
+ }
+ },
+ .proto = IPPROTO_GRE
+ };
struct rtable *rt;
+
if (!ip_route_output_key(dev_net(dev), &rt, &fl)) {
tdev = rt->dst.dev;
ip_rt_put(rt);
@@ -1012,7 +1058,7 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
break;
}
} else {
- unsigned nflags = 0;
+ unsigned int nflags = 0;
t = netdev_priv(dev);
@@ -1125,7 +1171,7 @@ static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
unsigned short type,
- const void *daddr, const void *saddr, unsigned len)
+ const void *daddr, const void *saddr, unsigned int len)
{
struct ip_tunnel *t = netdev_priv(dev);
struct iphdr *iph = (struct iphdr *)skb_push(skb, t->hlen);
@@ -1167,13 +1213,19 @@ static int ipgre_open(struct net_device *dev)
struct ip_tunnel *t = netdev_priv(dev);
if (ipv4_is_multicast(t->parms.iph.daddr)) {
- struct flowi fl = { .oif = t->parms.link,
- .nl_u = { .ip4_u =
- { .daddr = t->parms.iph.daddr,
- .saddr = t->parms.iph.saddr,
- .tos = RT_TOS(t->parms.iph.tos) } },
- .proto = IPPROTO_GRE };
+ struct flowi fl = {
+ .oif = t->parms.link,
+ .nl_u = {
+ .ip4_u = {
+ .daddr = t->parms.iph.daddr,
+ .saddr = t->parms.iph.saddr,
+ .tos = RT_TOS(t->parms.iph.tos)
+ }
+ },
+ .proto = IPPROTO_GRE
+ };
struct rtable *rt;
+
if (ip_route_output_key(dev_net(dev), &rt, &fl))
return -EADDRNOTAVAIL;
dev = rt->dst.dev;
@@ -1193,10 +1245,8 @@ static int ipgre_close(struct net_device *dev)
if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) {
struct in_device *in_dev;
in_dev = inetdev_by_index(dev_net(dev), t->mlink);
- if (in_dev) {
+ if (in_dev)
ip_mc_dec_group(in_dev, t->parms.iph.daddr);
- in_dev_put(in_dev);
- }
}
return 0;
}
@@ -1213,12 +1263,19 @@ static const struct net_device_ops ipgre_netdev_ops = {
.ndo_start_xmit = ipgre_tunnel_xmit,
.ndo_do_ioctl = ipgre_tunnel_ioctl,
.ndo_change_mtu = ipgre_tunnel_change_mtu,
+ .ndo_get_stats = ipgre_get_stats,
};
+static void ipgre_dev_free(struct net_device *dev)
+{
+ free_percpu(dev->tstats);
+ free_netdev(dev);
+}
+
static void ipgre_tunnel_setup(struct net_device *dev)
{
dev->netdev_ops = &ipgre_netdev_ops;
- dev->destructor = free_netdev;
+ dev->destructor = ipgre_dev_free;
dev->type = ARPHRD_IPGRE;
dev->needed_headroom = LL_MAX_HEADER + sizeof(struct iphdr) + 4;
@@ -1256,6 +1313,10 @@ static int ipgre_tunnel_init(struct net_device *dev)
} else
dev->header_ops = &ipgre_header_ops;
+ dev->tstats = alloc_percpu(struct pcpu_tstats);
+ if (!dev->tstats)
+ return -ENOMEM;
+
return 0;
}
@@ -1274,14 +1335,13 @@ static void ipgre_fb_tunnel_init(struct net_device *dev)
tunnel->hlen = sizeof(struct iphdr) + 4;
dev_hold(dev);
- ign->tunnels_wc[0] = tunnel;
+ rcu_assign_pointer(ign->tunnels_wc[0], tunnel);
}
-static const struct net_protocol ipgre_protocol = {
- .handler = ipgre_rcv,
- .err_handler = ipgre_err,
- .netns_ok = 1,
+static const struct gre_protocol ipgre_protocol = {
+ .handler = ipgre_rcv,
+ .err_handler = ipgre_err,
};
static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head)
@@ -1291,11 +1351,13 @@ static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head)
for (prio = 0; prio < 4; prio++) {
int h;
for (h = 0; h < HASH_SIZE; h++) {
- struct ip_tunnel *t = ign->tunnels[prio][h];
+ struct ip_tunnel *t;
+
+ t = rtnl_dereference(ign->tunnels[prio][h]);
while (t != NULL) {
unregister_netdevice_queue(t->dev, head);
- t = t->next;
+ t = rtnl_dereference(t->next);
}
}
}
@@ -1441,6 +1503,10 @@ static int ipgre_tap_init(struct net_device *dev)
ipgre_tunnel_bind_dev(dev);
+ dev->tstats = alloc_percpu(struct pcpu_tstats);
+ if (!dev->tstats)
+ return -ENOMEM;
+
return 0;
}
@@ -1451,6 +1517,7 @@ static const struct net_device_ops ipgre_tap_netdev_ops = {
.ndo_set_mac_address = eth_mac_addr,
.ndo_validate_addr = eth_validate_addr,
.ndo_change_mtu = ipgre_tunnel_change_mtu,
+ .ndo_get_stats = ipgre_get_stats,
};
static void ipgre_tap_setup(struct net_device *dev)
@@ -1459,7 +1526,7 @@ static void ipgre_tap_setup(struct net_device *dev)
ether_setup(dev);
dev->netdev_ops = &ipgre_tap_netdev_ops;
- dev->destructor = free_netdev;
+ dev->destructor = ipgre_dev_free;
dev->iflink = 0;
dev->features |= NETIF_F_NETNS_LOCAL;
@@ -1487,6 +1554,10 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nla
if (!tb[IFLA_MTU])
dev->mtu = mtu;
+ /* Can use a lockless transmit, unless we generate output sequences */
+ if (!(nt->parms.o_flags & GRE_SEQ))
+ dev->features |= NETIF_F_LLTX;
+
err = register_netdevice(dev);
if (err)
goto out;
@@ -1522,7 +1593,7 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
t = nt;
if (dev->type != ARPHRD_ETHER) {
- unsigned nflags = 0;
+ unsigned int nflags = 0;
if (ipv4_is_multicast(p.iph.daddr))
nflags = IFF_BROADCAST;
@@ -1663,7 +1734,7 @@ static int __init ipgre_init(void)
if (err < 0)
return err;
- err = inet_add_protocol(&ipgre_protocol, IPPROTO_GRE);
+ err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO);
if (err < 0) {
printk(KERN_INFO "ipgre init: can't add protocol\n");
goto add_proto_failed;
@@ -1683,7 +1754,7 @@ out:
tap_ops_failed:
rtnl_link_unregister(&ipgre_link_ops);
rtnl_link_failed:
- inet_del_protocol(&ipgre_protocol, IPPROTO_GRE);
+ gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO);
add_proto_failed:
unregister_pernet_device(&ipgre_net_ops);
goto out;
@@ -1693,7 +1764,7 @@ static void __exit ipgre_fini(void)
{
rtnl_link_unregister(&ipgre_tap_ops);
rtnl_link_unregister(&ipgre_link_ops);
- if (inet_del_protocol(&ipgre_protocol, IPPROTO_GRE) < 0)
+ if (gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO) < 0)
printk(KERN_INFO "ipgre close: can't remove protocol\n");
unregister_pernet_device(&ipgre_net_ops);
}