/*
- * Linux NET3: GRE over IP protocol decoder.
+ * Linux NET3: GRE over IP protocol decoder.
*
* Authors: Alexey Kuznetsov (kuznet@ms2.inr.ac.ru)
*
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
-#include <linux/sched.h>
#include <linux/kernel.h>
#include <asm/uaccess.h>
#include <linux/skbuff.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/netfilter_ipv4.h>
+#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <net/sock.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/rtnetlink.h>
#ifdef CONFIG_IPV6
#include <net/ipv6.h>
solution, but it supposes maintaing new variable in ALL
skb, even if no tunneling is used.
- Current solution: t->recursion lock breaks dead loops. It looks
+ Current solution: t->recursion lock breaks dead loops. It looks
like dev->tbusy flag, but I preferred new variable, because
the semantics is different. One day, when hard_start_xmit
will be multithreaded we will have to use skb->encapsulation.
Alexey Kuznetsov.
*/
+static struct rtnl_link_ops ipgre_link_ops __read_mostly;
static int ipgre_tunnel_init(struct net_device *dev);
static void ipgre_tunnel_setup(struct net_device *dev);
+static int ipgre_tunnel_bind_dev(struct net_device *dev);
/* Fallback tunnel: no source, no destination, no key, no options */
-static int ipgre_fb_tunnel_init(struct net_device *dev);
+#define HASH_SIZE 16
+
+static int ipgre_net_id;
+struct ipgre_net {
+ struct ip_tunnel *tunnels[4][HASH_SIZE];
-static struct net_device *ipgre_fb_tunnel_dev;
+ struct net_device *fb_tunnel_dev;
+};
/* Tunnel hash table */
will match fallback tunnel.
*/
-#define HASH_SIZE 16
-#define HASH(addr) ((addr^(addr>>4))&0xF)
+#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
-static struct ip_tunnel *tunnels[4][HASH_SIZE];
-
-#define tunnels_r_l (tunnels[3])
-#define tunnels_r (tunnels[2])
-#define tunnels_l (tunnels[1])
-#define tunnels_wc (tunnels[0])
+#define tunnels_r_l tunnels[3]
+#define tunnels_r tunnels[2]
+#define tunnels_l tunnels[1]
+#define tunnels_wc tunnels[0]
static DEFINE_RWLOCK(ipgre_lock);
/* Given src, dst and key, find appropriate for input tunnel. */
-static struct ip_tunnel * ipgre_tunnel_lookup(u32 remote, u32 local, u32 key)
+static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev,
+ __be32 remote, __be32 local,
+ __be32 key, __be16 gre_proto)
{
+ struct net *net = dev_net(dev);
+ int link = dev->ifindex;
unsigned h0 = HASH(remote);
unsigned h1 = HASH(key);
- struct ip_tunnel *t;
-
- for (t = tunnels_r_l[h0^h1]; t; t = t->next) {
- if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr) {
- if (t->parms.i_key == key && (t->dev->flags&IFF_UP))
- return t;
- }
+ struct ip_tunnel *t, *sel[4] = { NULL, NULL, NULL, NULL };
+ struct ipgre_net *ign = net_generic(net, ipgre_net_id);
+ int dev_type = (gre_proto == htons(ETH_P_TEB)) ?
+ ARPHRD_ETHER : ARPHRD_IPGRE;
+ int idx;
+
+ for (t = ign->tunnels_r_l[h0^h1]; t; t = t->next) {
+ if (local != t->parms.iph.saddr ||
+ remote != t->parms.iph.daddr ||
+ key != t->parms.i_key ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (t->dev->type != ARPHRD_IPGRE &&
+ t->dev->type != dev_type)
+ continue;
+
+ idx = 0;
+ if (t->parms.link != link)
+ idx |= 1;
+ if (t->dev->type != dev_type)
+ idx |= 2;
+ if (idx == 0)
+ return t;
+ if (sel[idx] == NULL)
+ sel[idx] = t;
}
- for (t = tunnels_r[h0^h1]; t; t = t->next) {
- if (remote == t->parms.iph.daddr) {
- if (t->parms.i_key == key && (t->dev->flags&IFF_UP))
- return t;
- }
+
+ for (t = ign->tunnels_r[h0^h1]; t; t = t->next) {
+ if (remote != t->parms.iph.daddr ||
+ key != t->parms.i_key ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (t->dev->type != ARPHRD_IPGRE &&
+ t->dev->type != dev_type)
+ continue;
+
+ idx = 0;
+ if (t->parms.link != link)
+ idx |= 1;
+ if (t->dev->type != dev_type)
+ idx |= 2;
+ if (idx == 0)
+ return t;
+ if (sel[idx] == NULL)
+ sel[idx] = t;
}
- for (t = tunnels_l[h1]; t; t = t->next) {
- if (local == t->parms.iph.saddr ||
- (local == t->parms.iph.daddr && MULTICAST(local))) {
- if (t->parms.i_key == key && (t->dev->flags&IFF_UP))
- return t;
- }
+
+ for (t = ign->tunnels_l[h1]; t; t = t->next) {
+ if ((local != t->parms.iph.saddr &&
+ (local != t->parms.iph.daddr ||
+ !ipv4_is_multicast(local))) ||
+ key != t->parms.i_key ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (t->dev->type != ARPHRD_IPGRE &&
+ t->dev->type != dev_type)
+ continue;
+
+ idx = 0;
+ if (t->parms.link != link)
+ idx |= 1;
+ if (t->dev->type != dev_type)
+ idx |= 2;
+ if (idx == 0)
+ return t;
+ if (sel[idx] == NULL)
+ sel[idx] = t;
}
- for (t = tunnels_wc[h1]; t; t = t->next) {
- if (t->parms.i_key == key && (t->dev->flags&IFF_UP))
+
+ for (t = ign->tunnels_wc[h1]; t; t = t->next) {
+ if (t->parms.i_key != key ||
+ !(t->dev->flags & IFF_UP))
+ continue;
+
+ if (t->dev->type != ARPHRD_IPGRE &&
+ t->dev->type != dev_type)
+ continue;
+
+ idx = 0;
+ if (t->parms.link != link)
+ idx |= 1;
+ if (t->dev->type != dev_type)
+ idx |= 2;
+ if (idx == 0)
return t;
+ if (sel[idx] == NULL)
+ sel[idx] = t;
}
- if (ipgre_fb_tunnel_dev->flags&IFF_UP)
- return netdev_priv(ipgre_fb_tunnel_dev);
+ for (idx = 1; idx < ARRAY_SIZE(sel); idx++)
+ if (sel[idx] != NULL)
+ return sel[idx];
+
+ if (ign->fb_tunnel_dev->flags & IFF_UP)
+ return netdev_priv(ign->fb_tunnel_dev);
+
return NULL;
}
-static struct ip_tunnel **ipgre_bucket(struct ip_tunnel *t)
+static struct ip_tunnel **__ipgre_bucket(struct ipgre_net *ign,
+ struct ip_tunnel_parm *parms)
{
- u32 remote = t->parms.iph.daddr;
- u32 local = t->parms.iph.saddr;
- u32 key = t->parms.i_key;
+ __be32 remote = parms->iph.daddr;
+ __be32 local = parms->iph.saddr;
+ __be32 key = parms->i_key;
unsigned h = HASH(key);
int prio = 0;
if (local)
prio |= 1;
- if (remote && !MULTICAST(remote)) {
+ if (remote && !ipv4_is_multicast(remote)) {
prio |= 2;
h ^= HASH(remote);
}
- return &tunnels[prio][h];
+ return &ign->tunnels[prio][h];
+}
+
+static inline struct ip_tunnel **ipgre_bucket(struct ipgre_net *ign,
+ struct ip_tunnel *t)
+{
+ return __ipgre_bucket(ign, &t->parms);
}
-static void ipgre_tunnel_link(struct ip_tunnel *t)
+static void ipgre_tunnel_link(struct ipgre_net *ign, struct ip_tunnel *t)
{
- struct ip_tunnel **tp = ipgre_bucket(t);
+ struct ip_tunnel **tp = ipgre_bucket(ign, t);
t->next = *tp;
write_lock_bh(&ipgre_lock);
write_unlock_bh(&ipgre_lock);
}
-static void ipgre_tunnel_unlink(struct ip_tunnel *t)
+static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t)
{
struct ip_tunnel **tp;
- for (tp = ipgre_bucket(t); *tp; tp = &(*tp)->next) {
+ for (tp = ipgre_bucket(ign, t); *tp; tp = &(*tp)->next) {
if (t == *tp) {
write_lock_bh(&ipgre_lock);
*tp = t->next;
}
}
-static struct ip_tunnel * ipgre_tunnel_locate(struct ip_tunnel_parm *parms, int create)
+static struct ip_tunnel *ipgre_tunnel_find(struct net *net,
+ struct ip_tunnel_parm *parms,
+ int type)
{
- u32 remote = parms->iph.daddr;
- u32 local = parms->iph.saddr;
- u32 key = parms->i_key;
- struct ip_tunnel *t, **tp, *nt;
+ __be32 remote = parms->iph.daddr;
+ __be32 local = parms->iph.saddr;
+ __be32 key = parms->i_key;
+ int link = parms->link;
+ struct ip_tunnel *t, **tp;
+ struct ipgre_net *ign = net_generic(net, ipgre_net_id);
+
+ for (tp = __ipgre_bucket(ign, parms); (t = *tp) != NULL; tp = &t->next)
+ if (local == t->parms.iph.saddr &&
+ remote == t->parms.iph.daddr &&
+ key == t->parms.i_key &&
+ link == t->parms.link &&
+ type == t->dev->type)
+ break;
+
+ return t;
+}
+
+static struct ip_tunnel * ipgre_tunnel_locate(struct net *net,
+ struct ip_tunnel_parm *parms, int create)
+{
+ struct ip_tunnel *t, *nt;
struct net_device *dev;
- unsigned h = HASH(key);
- int prio = 0;
char name[IFNAMSIZ];
+ struct ipgre_net *ign = net_generic(net, ipgre_net_id);
- if (local)
- prio |= 1;
- if (remote && !MULTICAST(remote)) {
- prio |= 2;
- h ^= HASH(remote);
- }
- for (tp = &tunnels[prio][h]; (t = *tp) != NULL; tp = &t->next) {
- if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr) {
- if (key == t->parms.i_key)
- return t;
- }
- }
- if (!create)
- return NULL;
+ t = ipgre_tunnel_find(net, parms, ARPHRD_IPGRE);
+ if (t || !create)
+ return t;
if (parms->name[0])
strlcpy(name, parms->name, IFNAMSIZ);
- else {
- int i;
- for (i=1; i<100; i++) {
- sprintf(name, "gre%d", i);
- if (__dev_get_by_name(name) == NULL)
- break;
- }
- if (i==100)
- goto failed;
- }
+ else
+ sprintf(name, "gre%%d");
dev = alloc_netdev(sizeof(*t), name, ipgre_tunnel_setup);
if (!dev)
return NULL;
- dev->init = ipgre_tunnel_init;
+ dev_net_set(dev, net);
+
+ if (strchr(name, '%')) {
+ if (dev_alloc_name(dev, name) < 0)
+ goto failed_free;
+ }
+
nt = netdev_priv(dev);
nt->parms = *parms;
+ dev->rtnl_link_ops = &ipgre_link_ops;
- if (register_netdevice(dev) < 0) {
- free_netdev(dev);
- goto failed;
- }
+ dev->mtu = ipgre_tunnel_bind_dev(dev);
+
+ if (register_netdevice(dev) < 0)
+ goto failed_free;
dev_hold(dev);
- ipgre_tunnel_link(nt);
+ ipgre_tunnel_link(ign, nt);
return nt;
-failed:
+failed_free:
+ free_netdev(dev);
return NULL;
}
static void ipgre_tunnel_uninit(struct net_device *dev)
{
- ipgre_tunnel_unlink(netdev_priv(dev));
+ struct net *net = dev_net(dev);
+ struct ipgre_net *ign = net_generic(net, ipgre_net_id);
+
+ ipgre_tunnel_unlink(ign, netdev_priv(dev));
dev_put(dev);
}
static void ipgre_err(struct sk_buff *skb, u32 info)
{
-#ifndef I_WISH_WORLD_WERE_PERFECT
-/* It is not :-( All the routers (except for Linux) return only
+/* All the routers (except for Linux) return only
8 bytes of packet payload. It means, that precise relaying of
ICMP in the real Internet is absolutely infeasible.
by themself???
*/
- struct iphdr *iph = (struct iphdr*)skb->data;
- u16 *p = (u16*)(skb->data+(iph->ihl<<2));
+ struct iphdr *iph = (struct iphdr *)skb->data;
+ __be16 *p = (__be16*)(skb->data+(iph->ihl<<2));
int grehlen = (iph->ihl<<2) + 4;
- int type = skb->h.icmph->type;
- int code = skb->h.icmph->code;
+ const int type = icmp_hdr(skb)->type;
+ const int code = icmp_hdr(skb)->code;
struct ip_tunnel *t;
- u16 flags;
+ __be16 flags;
flags = p[0];
if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) {
}
read_lock(&ipgre_lock);
- t = ipgre_tunnel_lookup(iph->daddr, iph->saddr, (flags&GRE_KEY) ? *(((u32*)p) + (grehlen>>2) - 1) : 0);
- if (t == NULL || t->parms.iph.daddr == 0 || MULTICAST(t->parms.iph.daddr))
+ t = ipgre_tunnel_lookup(skb->dev, iph->daddr, iph->saddr,
+ flags & GRE_KEY ?
+ *(((__be32 *)p) + (grehlen / 4) - 1) : 0,
+ p[1]);
+ if (t == NULL || t->parms.iph.daddr == 0 ||
+ ipv4_is_multicast(t->parms.iph.daddr))
goto out;
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
out:
read_unlock(&ipgre_lock);
return;
-#else
- struct iphdr *iph = (struct iphdr*)dp;
- struct iphdr *eiph;
- u16 *p = (u16*)(dp+(iph->ihl<<2));
- int type = skb->h.icmph->type;
- int code = skb->h.icmph->code;
- int rel_type = 0;
- int rel_code = 0;
- __be32 rel_info = 0;
- __u32 n = 0;
- u16 flags;
- int grehlen = (iph->ihl<<2) + 4;
- struct sk_buff *skb2;
- struct flowi fl;
- struct rtable *rt;
-
- if (p[1] != htons(ETH_P_IP))
- return;
-
- flags = p[0];
- if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) {
- if (flags&(GRE_VERSION|GRE_ROUTING))
- return;
- if (flags&GRE_CSUM)
- grehlen += 4;
- if (flags&GRE_KEY)
- grehlen += 4;
- if (flags&GRE_SEQ)
- grehlen += 4;
- }
- if (len < grehlen + sizeof(struct iphdr))
- return;
- eiph = (struct iphdr*)(dp + grehlen);
-
- switch (type) {
- default:
- return;
- case ICMP_PARAMETERPROB:
- n = ntohl(skb->h.icmph->un.gateway) >> 24;
- if (n < (iph->ihl<<2))
- return;
-
- /* So... This guy found something strange INSIDE encapsulated
- packet. Well, he is fool, but what can we do ?
- */
- rel_type = ICMP_PARAMETERPROB;
- n -= grehlen;
- rel_info = htonl(n << 24);
- break;
-
- case ICMP_DEST_UNREACH:
- switch (code) {
- case ICMP_SR_FAILED:
- case ICMP_PORT_UNREACH:
- /* Impossible event. */
- return;
- case ICMP_FRAG_NEEDED:
- /* And it is the only really necessary thing :-) */
- n = ntohs(skb->h.icmph->un.frag.mtu);
- if (n < grehlen+68)
- return;
- n -= grehlen;
- /* BSD 4.2 MORE DOES NOT EXIST IN NATURE. */
- if (n > ntohs(eiph->tot_len))
- return;
- rel_info = htonl(n);
- break;
- default:
- /* All others are translated to HOST_UNREACH.
- rfc2003 contains "deep thoughts" about NET_UNREACH,
- I believe, it is just ether pollution. --ANK
- */
- rel_type = ICMP_DEST_UNREACH;
- rel_code = ICMP_HOST_UNREACH;
- break;
- }
- break;
- case ICMP_TIME_EXCEEDED:
- if (code != ICMP_EXC_TTL)
- return;
- break;
- }
-
- /* Prepare fake skb to feed it to icmp_send */
- skb2 = skb_clone(skb, GFP_ATOMIC);
- if (skb2 == NULL)
- return;
- dst_release(skb2->dst);
- skb2->dst = NULL;
- skb_pull(skb2, skb->data - (u8*)eiph);
- skb2->nh.raw = skb2->data;
-
- /* Try to guess incoming interface */
- memset(&fl, 0, sizeof(fl));
- fl.fl4_dst = eiph->saddr;
- fl.fl4_tos = RT_TOS(eiph->tos);
- fl.proto = IPPROTO_GRE;
- if (ip_route_output_key(&rt, &fl)) {
- kfree_skb(skb2);
- return;
- }
- skb2->dev = rt->u.dst.dev;
-
- /* route "incoming" packet */
- if (rt->rt_flags&RTCF_LOCAL) {
- ip_rt_put(rt);
- rt = NULL;
- fl.fl4_dst = eiph->daddr;
- fl.fl4_src = eiph->saddr;
- fl.fl4_tos = eiph->tos;
- if (ip_route_output_key(&rt, &fl) ||
- rt->u.dst.dev->type != ARPHRD_IPGRE) {
- ip_rt_put(rt);
- kfree_skb(skb2);
- return;
- }
- } else {
- ip_rt_put(rt);
- if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos, skb2->dev) ||
- skb2->dst->dev->type != ARPHRD_IPGRE) {
- kfree_skb(skb2);
- return;
- }
- }
-
- /* change mtu on this route */
- if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
- if (n > dst_mtu(skb2->dst)) {
- kfree_skb(skb2);
- return;
- }
- skb2->dst->ops->update_pmtu(skb2->dst, n);
- } else if (type == ICMP_TIME_EXCEEDED) {
- struct ip_tunnel *t = netdev_priv(skb2->dev);
- if (t->parms.iph.ttl) {
- rel_type = ICMP_DEST_UNREACH;
- rel_code = ICMP_HOST_UNREACH;
- }
- }
-
- icmp_send(skb2, rel_type, rel_code, rel_info);
- kfree_skb(skb2);
-#endif
}
static inline void ipgre_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb)
{
if (INET_ECN_is_ce(iph->tos)) {
if (skb->protocol == htons(ETH_P_IP)) {
- IP_ECN_set_ce(skb->nh.iph);
+ IP_ECN_set_ce(ip_hdr(skb));
} else if (skb->protocol == htons(ETH_P_IPV6)) {
- IP6_ECN_set_ce(skb->nh.ipv6h);
+ IP6_ECN_set_ce(ipv6_hdr(skb));
}
}
}
{
struct iphdr *iph;
u8 *h;
- u16 flags;
- u16 csum = 0;
- u32 key = 0;
+ __be16 flags;
+ __sum16 csum = 0;
+ __be32 key = 0;
u32 seqno = 0;
struct ip_tunnel *tunnel;
int offset = 4;
+ __be16 gre_proto;
+ unsigned int len;
if (!pskb_may_pull(skb, 16))
goto drop_nolock;
- iph = skb->nh.iph;
+ iph = ip_hdr(skb);
h = skb->data;
- flags = *(u16*)h;
+ flags = *(__be16*)h;
if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) {
/* - Version must be 0.
if (flags&GRE_CSUM) {
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
- csum = (u16)csum_fold(skb->csum);
+ csum = csum_fold(skb->csum);
if (!csum)
break;
/* fall through */
offset += 4;
}
if (flags&GRE_KEY) {
- key = *(u32*)(h + offset);
+ key = *(__be32*)(h + offset);
offset += 4;
}
if (flags&GRE_SEQ) {
- seqno = ntohl(*(u32*)(h + offset));
+ seqno = ntohl(*(__be32*)(h + offset));
offset += 4;
}
}
+ gre_proto = *(__be16 *)(h + 2);
+
read_lock(&ipgre_lock);
- if ((tunnel = ipgre_tunnel_lookup(iph->saddr, iph->daddr, key)) != NULL) {
+ if ((tunnel = ipgre_tunnel_lookup(skb->dev,
+ iph->saddr, iph->daddr, key,
+ gre_proto))) {
+ struct net_device_stats *stats = &tunnel->dev->stats;
+
secpath_reset(skb);
- skb->protocol = *(u16*)(h + 2);
+ skb->protocol = gre_proto;
/* WCCP version 1 and 2 protocol decoding.
* - Change protocol to IP
* - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
*/
- if (flags == 0 &&
- skb->protocol == __constant_htons(ETH_P_WCCP)) {
- skb->protocol = __constant_htons(ETH_P_IP);
- if ((*(h + offset) & 0xF0) != 0x40)
+ if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
+ skb->protocol = htons(ETH_P_IP);
+ if ((*(h + offset) & 0xF0) != 0x40)
offset += 4;
}
- skb->mac.raw = skb->nh.raw;
- skb->nh.raw = __pskb_pull(skb, offset);
- skb_postpull_rcsum(skb, skb->h.raw, offset);
+ skb->mac_header = skb->network_header;
+ __pskb_pull(skb, offset);
+ skb_postpull_rcsum(skb, skb_transport_header(skb), offset);
skb->pkt_type = PACKET_HOST;
#ifdef CONFIG_NET_IPGRE_BROADCAST
- if (MULTICAST(iph->daddr)) {
+ if (ipv4_is_multicast(iph->daddr)) {
/* Looped back packet, drop it! */
- if (((struct rtable*)skb->dst)->fl.iif == 0)
+ if (skb->rtable->fl.iif == 0)
goto drop;
- tunnel->stat.multicast++;
+ stats->multicast++;
skb->pkt_type = PACKET_BROADCAST;
}
#endif
if (((flags&GRE_CSUM) && csum) ||
(!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) {
- tunnel->stat.rx_crc_errors++;
- tunnel->stat.rx_errors++;
+ stats->rx_crc_errors++;
+ 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)) {
- tunnel->stat.rx_fifo_errors++;
- tunnel->stat.rx_errors++;
+ stats->rx_fifo_errors++;
+ stats->rx_errors++;
goto drop;
}
tunnel->i_seqno = seqno + 1;
}
- tunnel->stat.rx_packets++;
- tunnel->stat.rx_bytes += skb->len;
+
+ len = skb->len;
+
+ /* 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++;
+ goto drop;
+ }
+
+ iph = ip_hdr(skb);
+ skb->protocol = eth_type_trans(skb, tunnel->dev);
+ skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+ }
+
+ stats->rx_packets++;
+ stats->rx_bytes += len;
skb->dev = tunnel->dev;
dst_release(skb->dst);
skb->dst = NULL;
nf_reset(skb);
+
+ skb_reset_network_header(skb);
ipgre_ecn_decapsulate(iph, skb);
+
netif_rx(skb);
read_unlock(&ipgre_lock);
return(0);
static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
- struct net_device_stats *stats = &tunnel->stat;
- struct iphdr *old_iph = skb->nh.iph;
+ struct net_device_stats *stats = &tunnel->dev->stats;
+ struct iphdr *old_iph = ip_hdr(skb);
struct iphdr *tiph;
u8 tos;
- u16 df;
+ __be16 df;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *iph; /* Our new IP header */
- int max_headroom; /* The extra header space needed */
+ unsigned int max_headroom; /* The extra header space needed */
int gre_hlen;
- u32 dst;
+ __be32 dst;
int mtu;
if (tunnel->recursion++) {
- tunnel->stat.collisions++;
+ stats->collisions++;
goto tx_error;
}
- if (dev->hard_header) {
+ if (dev->type == ARPHRD_ETHER)
+ IPCB(skb)->flags = 0;
+
+ if (dev->header_ops && dev->type == ARPHRD_IPGRE) {
gre_hlen = 0;
- tiph = (struct iphdr*)skb->data;
+ tiph = (struct iphdr *)skb->data;
} else {
gre_hlen = tunnel->hlen;
tiph = &tunnel->parms.iph;
/* NBMA tunnel */
if (skb->dst == NULL) {
- tunnel->stat.tx_fifo_errors++;
+ stats->tx_fifo_errors++;
goto tx_error;
}
if (skb->protocol == htons(ETH_P_IP)) {
- rt = (struct rtable*)skb->dst;
+ rt = skb->rtable;
if ((dst = rt->rt_gateway) == 0)
goto tx_error_icmp;
}
if (neigh == NULL)
goto tx_error;
- addr6 = (struct in6_addr*)&neigh->primary_key;
+ addr6 = (struct in6_addr *)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if (addr_type == IPV6_ADDR_ANY) {
- addr6 = &skb->nh.ipv6h->daddr;
+ addr6 = &ipv6_hdr(skb)->daddr;
addr_type = ipv6_addr_type(addr6);
}
.saddr = tiph->saddr,
.tos = RT_TOS(tos) } },
.proto = IPPROTO_GRE };
- if (ip_route_output_key(&rt, &fl)) {
- tunnel->stat.tx_carrier_errors++;
+ if (ip_route_output_key(dev_net(dev), &rt, &fl)) {
+ stats->tx_carrier_errors++;
goto tx_error;
}
}
if (tdev == dev) {
ip_rt_put(rt);
- tunnel->stat.collisions++;
+ stats->collisions++;
goto tx_error;
}
df = tiph->frag_off;
if (df)
- mtu = dst_mtu(&rt->u.dst) - tunnel->hlen;
+ mtu = dst_mtu(&rt->u.dst) - dev->hard_header_len - tunnel->hlen;
else
mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu;
}
#ifdef CONFIG_IPV6
else if (skb->protocol == htons(ETH_P_IPV6)) {
- struct rt6_info *rt6 = (struct rt6_info*)skb->dst;
+ struct rt6_info *rt6 = (struct rt6_info *)skb->dst;
if (rt6 && mtu < dst_mtu(skb->dst) && mtu >= IPV6_MIN_MTU) {
- if ((tunnel->parms.iph.daddr && !MULTICAST(tunnel->parms.iph.daddr)) ||
+ if ((tunnel->parms.iph.daddr &&
+ !ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
rt6->rt6i_dst.plen == 128) {
rt6->rt6i_flags |= RTF_MODIFIED;
skb->dst->metrics[RTAX_MTU-1] = mtu;
max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen;
- if (skb_headroom(skb) < max_headroom || skb_cloned(skb) || skb_shared(skb)) {
+ if (skb_headroom(skb) < max_headroom || skb_shared(skb)||
+ (skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb) {
ip_rt_put(rt);
- stats->tx_dropped++;
+ stats->tx_dropped++;
dev_kfree_skb(skb);
tunnel->recursion--;
return 0;
skb_set_owner_w(new_skb, skb->sk);
dev_kfree_skb(skb);
skb = new_skb;
- old_iph = skb->nh.iph;
+ old_iph = ip_hdr(skb);
}
- skb->h.raw = skb->nh.raw;
- skb->nh.raw = skb_push(skb, gre_hlen);
+ skb_reset_transport_header(skb);
+ skb_push(skb, gre_hlen);
+ skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
IPSKB_REROUTED);
* Push down and install the IPIP header.
*/
- iph = skb->nh.iph;
+ iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
iph->ttl = old_iph->ttl;
#ifdef CONFIG_IPV6
else if (skb->protocol == htons(ETH_P_IPV6))
- iph->ttl = ((struct ipv6hdr*)old_iph)->hop_limit;
+ iph->ttl = ((struct ipv6hdr *)old_iph)->hop_limit;
#endif
else
iph->ttl = dst_metric(&rt->u.dst, RTAX_HOPLIMIT);
}
- ((u16*)(iph+1))[0] = tunnel->parms.o_flags;
- ((u16*)(iph+1))[1] = skb->protocol;
+ ((__be16 *)(iph + 1))[0] = tunnel->parms.o_flags;
+ ((__be16 *)(iph + 1))[1] = (dev->type == ARPHRD_ETHER) ?
+ htons(ETH_P_TEB) : skb->protocol;
if (tunnel->parms.o_flags&(GRE_KEY|GRE_CSUM|GRE_SEQ)) {
- u32 *ptr = (u32*)(((u8*)iph) + tunnel->hlen - 4);
+ __be32 *ptr = (__be32*)(((u8*)iph) + tunnel->hlen - 4);
if (tunnel->parms.o_flags&GRE_SEQ) {
++tunnel->o_seqno;
}
if (tunnel->parms.o_flags&GRE_CSUM) {
*ptr = 0;
- *(__u16*)ptr = ip_compute_csum((void*)(iph+1), skb->len - sizeof(struct iphdr));
+ *(__sum16*)ptr = ip_compute_csum((void*)(iph+1), skb->len - sizeof(struct iphdr));
}
}
return 0;
}
+static int ipgre_tunnel_bind_dev(struct net_device *dev)
+{
+ struct net_device *tdev = NULL;
+ struct ip_tunnel *tunnel;
+ struct iphdr *iph;
+ int hlen = LL_MAX_HEADER;
+ int mtu = ETH_DATA_LEN;
+ int addend = sizeof(struct iphdr) + 4;
+
+ tunnel = netdev_priv(dev);
+ iph = &tunnel->parms.iph;
+
+ /* 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 rtable *rt;
+ if (!ip_route_output_key(dev_net(dev), &rt, &fl)) {
+ tdev = rt->u.dst.dev;
+ ip_rt_put(rt);
+ }
+
+ if (dev->type != ARPHRD_ETHER)
+ dev->flags |= IFF_POINTOPOINT;
+ }
+
+ if (!tdev && tunnel->parms.link)
+ tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
+
+ if (tdev) {
+ hlen = tdev->hard_header_len + tdev->needed_headroom;
+ mtu = tdev->mtu;
+ }
+ dev->iflink = tunnel->parms.link;
+
+ /* Precalculate GRE options length */
+ if (tunnel->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) {
+ if (tunnel->parms.o_flags&GRE_CSUM)
+ addend += 4;
+ if (tunnel->parms.o_flags&GRE_KEY)
+ addend += 4;
+ if (tunnel->parms.o_flags&GRE_SEQ)
+ addend += 4;
+ }
+ dev->needed_headroom = addend + hlen;
+ mtu -= dev->hard_header_len - addend;
+
+ if (mtu < 68)
+ mtu = 68;
+
+ tunnel->hlen = addend;
+
+ return mtu;
+}
+
static int
ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
{
int err = 0;
struct ip_tunnel_parm p;
struct ip_tunnel *t;
+ struct net *net = dev_net(dev);
+ struct ipgre_net *ign = net_generic(net, ipgre_net_id);
switch (cmd) {
case SIOCGETTUNNEL:
t = NULL;
- if (dev == ipgre_fb_tunnel_dev) {
+ if (dev == ign->fb_tunnel_dev) {
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
err = -EFAULT;
break;
}
- t = ipgre_tunnel_locate(&p, 0);
+ t = ipgre_tunnel_locate(net, &p, 0);
}
if (t == NULL)
t = netdev_priv(dev);
if (!(p.o_flags&GRE_KEY))
p.o_key = 0;
- t = ipgre_tunnel_locate(&p, cmd == SIOCADDTUNNEL);
+ t = ipgre_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL);
- if (dev != ipgre_fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
+ if (dev != ign->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
if (t != NULL) {
if (t->dev != dev) {
err = -EEXIST;
break;
}
} else {
- unsigned nflags=0;
+ unsigned nflags = 0;
t = netdev_priv(dev);
- if (MULTICAST(p.iph.daddr))
+ if (ipv4_is_multicast(p.iph.daddr))
nflags = IFF_BROADCAST;
else if (p.iph.daddr)
nflags = IFF_POINTOPOINT;
err = -EINVAL;
break;
}
- ipgre_tunnel_unlink(t);
+ ipgre_tunnel_unlink(ign, t);
t->parms.iph.saddr = p.iph.saddr;
t->parms.iph.daddr = p.iph.daddr;
t->parms.i_key = p.i_key;
t->parms.o_key = p.o_key;
memcpy(dev->dev_addr, &p.iph.saddr, 4);
memcpy(dev->broadcast, &p.iph.daddr, 4);
- ipgre_tunnel_link(t);
+ ipgre_tunnel_link(ign, t);
netdev_state_change(dev);
}
}
t->parms.iph.ttl = p.iph.ttl;
t->parms.iph.tos = p.iph.tos;
t->parms.iph.frag_off = p.iph.frag_off;
+ if (t->parms.link != p.link) {
+ t->parms.link = p.link;
+ dev->mtu = ipgre_tunnel_bind_dev(dev);
+ netdev_state_change(dev);
+ }
}
if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p)))
err = -EFAULT;
if (!capable(CAP_NET_ADMIN))
goto done;
- if (dev == ipgre_fb_tunnel_dev) {
+ if (dev == ign->fb_tunnel_dev) {
err = -EFAULT;
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
goto done;
err = -ENOENT;
- if ((t = ipgre_tunnel_locate(&p, 0)) == NULL)
+ if ((t = ipgre_tunnel_locate(net, &p, 0)) == NULL)
goto done;
err = -EPERM;
- if (t == netdev_priv(ipgre_fb_tunnel_dev))
+ if (t == netdev_priv(ign->fb_tunnel_dev))
goto done;
dev = t->dev;
}
- err = unregister_netdevice(dev);
+ unregister_netdevice(dev);
+ err = 0;
break;
default:
return err;
}
-static struct net_device_stats *ipgre_tunnel_get_stats(struct net_device *dev)
-{
- return &(((struct ip_tunnel*)netdev_priv(dev))->stat);
-}
-
static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
- if (new_mtu < 68 || new_mtu > 0xFFF8 - tunnel->hlen)
+ if (new_mtu < 68 ||
+ new_mtu > 0xFFF8 - dev->hard_header_len - tunnel->hlen)
return -EINVAL;
dev->mtu = new_mtu;
return 0;
}
-#ifdef CONFIG_NET_IPGRE_BROADCAST
/* Nice toy. Unfortunately, useless in real life :-)
It allows to construct virtual multiprotocol broadcast "LAN"
over the Internet, provided multicast routing is tuned.
so that I had to set ARPHRD_IPGRE to a random value.
I have an impression, that Cisco could make something similar,
but this feature is apparently missing in IOS<=11.2(8).
-
+
I set up 10.66.66/24 and fec0:6666:6666::0/96 as virtual networks
with broadcast 224.66.66.66. If you have access to mbone, play with me :-)
*/
-static int ipgre_header(struct sk_buff *skb, struct net_device *dev, unsigned short type,
- void *daddr, void *saddr, unsigned len)
+static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
+ unsigned short type,
+ const void *daddr, const void *saddr, unsigned len)
{
struct ip_tunnel *t = netdev_priv(dev);
struct iphdr *iph = (struct iphdr *)skb_push(skb, t->hlen);
- u16 *p = (u16*)(iph+1);
+ __be16 *p = (__be16*)(iph+1);
memcpy(iph, &t->parms.iph, sizeof(struct iphdr));
p[0] = t->parms.o_flags;
p[1] = htons(type);
/*
- * Set the source hardware address.
+ * Set the source hardware address.
*/
-
+
if (saddr)
memcpy(&iph->saddr, saddr, 4);
memcpy(&iph->daddr, daddr, 4);
return t->hlen;
}
- if (iph->daddr && !MULTICAST(iph->daddr))
+ if (iph->daddr && !ipv4_is_multicast(iph->daddr))
return t->hlen;
-
+
return -t->hlen;
}
+static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
+{
+ struct iphdr *iph = (struct iphdr *) skb_mac_header(skb);
+ memcpy(haddr, &iph->saddr, 4);
+ return 4;
+}
+
+static const struct header_ops ipgre_header_ops = {
+ .create = ipgre_header,
+ .parse = ipgre_header_parse,
+};
+
+#ifdef CONFIG_NET_IPGRE_BROADCAST
static int ipgre_open(struct net_device *dev)
{
struct ip_tunnel *t = netdev_priv(dev);
- if (MULTICAST(t->parms.iph.daddr)) {
+ if (ipv4_is_multicast(t->parms.iph.daddr)) {
struct flowi fl = { .oif = t->parms.link,
.nl_u = { .ip4_u =
{ .daddr = t->parms.iph.daddr,
.tos = RT_TOS(t->parms.iph.tos) } },
.proto = IPPROTO_GRE };
struct rtable *rt;
- if (ip_route_output_key(&rt, &fl))
+ if (ip_route_output_key(dev_net(dev), &rt, &fl))
return -EADDRNOTAVAIL;
dev = rt->u.dst.dev;
ip_rt_put(rt);
static int ipgre_close(struct net_device *dev)
{
struct ip_tunnel *t = netdev_priv(dev);
- if (MULTICAST(t->parms.iph.daddr) && t->mlink) {
- struct in_device *in_dev = inetdev_by_index(t->mlink);
+
+ 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) {
ip_mc_dec_group(in_dev, t->parms.iph.daddr);
in_dev_put(in_dev);
#endif
+static const struct net_device_ops ipgre_netdev_ops = {
+ .ndo_init = ipgre_tunnel_init,
+ .ndo_uninit = ipgre_tunnel_uninit,
+#ifdef CONFIG_NET_IPGRE_BROADCAST
+ .ndo_open = ipgre_open,
+ .ndo_stop = ipgre_close,
+#endif
+ .ndo_start_xmit = ipgre_tunnel_xmit,
+ .ndo_do_ioctl = ipgre_tunnel_ioctl,
+ .ndo_change_mtu = ipgre_tunnel_change_mtu,
+};
+
static void ipgre_tunnel_setup(struct net_device *dev)
{
- SET_MODULE_OWNER(dev);
- dev->uninit = ipgre_tunnel_uninit;
+ dev->netdev_ops = &ipgre_netdev_ops;
dev->destructor = free_netdev;
- dev->hard_start_xmit = ipgre_tunnel_xmit;
- dev->get_stats = ipgre_tunnel_get_stats;
- dev->do_ioctl = ipgre_tunnel_ioctl;
- dev->change_mtu = ipgre_tunnel_change_mtu;
dev->type = ARPHRD_IPGRE;
- dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr) + 4;
+ dev->needed_headroom = LL_MAX_HEADER + sizeof(struct iphdr) + 4;
dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr) - 4;
dev->flags = IFF_NOARP;
dev->iflink = 0;
dev->addr_len = 4;
+ dev->features |= NETIF_F_NETNS_LOCAL;
}
static int ipgre_tunnel_init(struct net_device *dev)
{
- struct net_device *tdev = NULL;
struct ip_tunnel *tunnel;
struct iphdr *iph;
- int hlen = LL_MAX_HEADER;
- int mtu = ETH_DATA_LEN;
- int addend = sizeof(struct iphdr) + 4;
tunnel = netdev_priv(dev);
iph = &tunnel->parms.iph;
memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
- /* Guess output device to choose reasonable mtu and hard_header_len */
-
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 rtable *rt;
- if (!ip_route_output_key(&rt, &fl)) {
- tdev = rt->u.dst.dev;
- ip_rt_put(rt);
- }
-
- dev->flags |= IFF_POINTOPOINT;
-
#ifdef CONFIG_NET_IPGRE_BROADCAST
- if (MULTICAST(iph->daddr)) {
+ if (ipv4_is_multicast(iph->daddr)) {
if (!iph->saddr)
return -EINVAL;
dev->flags = IFF_BROADCAST;
- dev->hard_header = ipgre_header;
- dev->open = ipgre_open;
- dev->stop = ipgre_close;
+ dev->header_ops = &ipgre_header_ops;
}
#endif
- }
-
- if (!tdev && tunnel->parms.link)
- tdev = __dev_get_by_index(tunnel->parms.link);
-
- if (tdev) {
- hlen = tdev->hard_header_len;
- mtu = tdev->mtu;
- }
- dev->iflink = tunnel->parms.link;
+ } else
+ dev->header_ops = &ipgre_header_ops;
- /* Precalculate GRE options length */
- if (tunnel->parms.o_flags&(GRE_CSUM|GRE_KEY|GRE_SEQ)) {
- if (tunnel->parms.o_flags&GRE_CSUM)
- addend += 4;
- if (tunnel->parms.o_flags&GRE_KEY)
- addend += 4;
- if (tunnel->parms.o_flags&GRE_SEQ)
- addend += 4;
- }
- dev->hard_header_len = hlen + addend;
- dev->mtu = mtu - addend;
- tunnel->hlen = addend;
return 0;
}
-static int __init ipgre_fb_tunnel_init(struct net_device *dev)
+static void ipgre_fb_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
+ struct ipgre_net *ign = net_generic(dev_net(dev), ipgre_net_id);
tunnel->dev = dev;
strcpy(tunnel->parms.name, dev->name);
tunnel->hlen = sizeof(struct iphdr) + 4;
dev_hold(dev);
- tunnels_wc[0] = tunnel;
- return 0;
+ ign->tunnels_wc[0] = tunnel;
}
static struct net_protocol ipgre_protocol = {
.handler = ipgre_rcv,
.err_handler = ipgre_err,
+ .netns_ok = 1,
+};
+
+static void ipgre_destroy_tunnels(struct ipgre_net *ign)
+{
+ int prio;
+
+ for (prio = 0; prio < 4; prio++) {
+ int h;
+ for (h = 0; h < HASH_SIZE; h++) {
+ struct ip_tunnel *t;
+ while ((t = ign->tunnels[prio][h]) != NULL)
+ unregister_netdevice(t->dev);
+ }
+ }
+}
+
+static int ipgre_init_net(struct net *net)
+{
+ int err;
+ struct ipgre_net *ign;
+
+ err = -ENOMEM;
+ ign = kzalloc(sizeof(struct ipgre_net), GFP_KERNEL);
+ if (ign == NULL)
+ goto err_alloc;
+
+ err = net_assign_generic(net, ipgre_net_id, ign);
+ if (err < 0)
+ goto err_assign;
+
+ ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "gre0",
+ ipgre_tunnel_setup);
+ if (!ign->fb_tunnel_dev) {
+ err = -ENOMEM;
+ goto err_alloc_dev;
+ }
+ dev_net_set(ign->fb_tunnel_dev, net);
+
+ ipgre_fb_tunnel_init(ign->fb_tunnel_dev);
+ ign->fb_tunnel_dev->rtnl_link_ops = &ipgre_link_ops;
+
+ if ((err = register_netdev(ign->fb_tunnel_dev)))
+ goto err_reg_dev;
+
+ return 0;
+
+err_reg_dev:
+ free_netdev(ign->fb_tunnel_dev);
+err_alloc_dev:
+ /* nothing */
+err_assign:
+ kfree(ign);
+err_alloc:
+ return err;
+}
+
+static void ipgre_exit_net(struct net *net)
+{
+ struct ipgre_net *ign;
+
+ ign = net_generic(net, ipgre_net_id);
+ rtnl_lock();
+ ipgre_destroy_tunnels(ign);
+ rtnl_unlock();
+ kfree(ign);
+}
+
+static struct pernet_operations ipgre_net_ops = {
+ .init = ipgre_init_net,
+ .exit = ipgre_exit_net,
+};
+
+static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+ __be16 flags;
+
+ if (!data)
+ return 0;
+
+ flags = 0;
+ if (data[IFLA_GRE_IFLAGS])
+ flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]);
+ if (data[IFLA_GRE_OFLAGS])
+ flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]);
+ if (flags & (GRE_VERSION|GRE_ROUTING))
+ return -EINVAL;
+
+ return 0;
+}
+
+static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[])
+{
+ __be32 daddr;
+
+ if (tb[IFLA_ADDRESS]) {
+ if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
+ return -EINVAL;
+ if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
+ return -EADDRNOTAVAIL;
+ }
+
+ if (!data)
+ goto out;
+
+ if (data[IFLA_GRE_REMOTE]) {
+ memcpy(&daddr, nla_data(data[IFLA_GRE_REMOTE]), 4);
+ if (!daddr)
+ return -EINVAL;
+ }
+
+out:
+ return ipgre_tunnel_validate(tb, data);
+}
+
+static void ipgre_netlink_parms(struct nlattr *data[],
+ struct ip_tunnel_parm *parms)
+{
+ memset(parms, 0, sizeof(*parms));
+
+ parms->iph.protocol = IPPROTO_GRE;
+
+ if (!data)
+ return;
+
+ if (data[IFLA_GRE_LINK])
+ parms->link = nla_get_u32(data[IFLA_GRE_LINK]);
+
+ if (data[IFLA_GRE_IFLAGS])
+ parms->i_flags = nla_get_be16(data[IFLA_GRE_IFLAGS]);
+
+ if (data[IFLA_GRE_OFLAGS])
+ parms->o_flags = nla_get_be16(data[IFLA_GRE_OFLAGS]);
+
+ if (data[IFLA_GRE_IKEY])
+ parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]);
+
+ if (data[IFLA_GRE_OKEY])
+ parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]);
+
+ if (data[IFLA_GRE_LOCAL])
+ parms->iph.saddr = nla_get_be32(data[IFLA_GRE_LOCAL]);
+
+ if (data[IFLA_GRE_REMOTE])
+ parms->iph.daddr = nla_get_be32(data[IFLA_GRE_REMOTE]);
+
+ if (data[IFLA_GRE_TTL])
+ parms->iph.ttl = nla_get_u8(data[IFLA_GRE_TTL]);
+
+ if (data[IFLA_GRE_TOS])
+ parms->iph.tos = nla_get_u8(data[IFLA_GRE_TOS]);
+
+ if (!data[IFLA_GRE_PMTUDISC] || nla_get_u8(data[IFLA_GRE_PMTUDISC]))
+ parms->iph.frag_off = htons(IP_DF);
+}
+
+static int ipgre_tap_init(struct net_device *dev)
+{
+ struct ip_tunnel *tunnel;
+
+ tunnel = netdev_priv(dev);
+
+ tunnel->dev = dev;
+ strcpy(tunnel->parms.name, dev->name);
+
+ ipgre_tunnel_bind_dev(dev);
+
+ return 0;
+}
+
+static const struct net_device_ops ipgre_tap_netdev_ops = {
+ .ndo_init = ipgre_tap_init,
+ .ndo_uninit = ipgre_tunnel_uninit,
+ .ndo_start_xmit = ipgre_tunnel_xmit,
+ .ndo_set_mac_address = eth_mac_addr,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_change_mtu = ipgre_tunnel_change_mtu,
+};
+
+static void ipgre_tap_setup(struct net_device *dev)
+{
+
+ ether_setup(dev);
+
+ dev->netdev_ops = &ipgre_netdev_ops;
+ dev->destructor = free_netdev;
+
+ dev->iflink = 0;
+ dev->features |= NETIF_F_NETNS_LOCAL;
+}
+
+static int ipgre_newlink(struct net_device *dev, struct nlattr *tb[],
+ struct nlattr *data[])
+{
+ struct ip_tunnel *nt;
+ struct net *net = dev_net(dev);
+ struct ipgre_net *ign = net_generic(net, ipgre_net_id);
+ int mtu;
+ int err;
+
+ nt = netdev_priv(dev);
+ ipgre_netlink_parms(data, &nt->parms);
+
+ if (ipgre_tunnel_find(net, &nt->parms, dev->type))
+ return -EEXIST;
+
+ if (dev->type == ARPHRD_ETHER && !tb[IFLA_ADDRESS])
+ random_ether_addr(dev->dev_addr);
+
+ mtu = ipgre_tunnel_bind_dev(dev);
+ if (!tb[IFLA_MTU])
+ dev->mtu = mtu;
+
+ err = register_netdevice(dev);
+ if (err)
+ goto out;
+
+ dev_hold(dev);
+ ipgre_tunnel_link(ign, nt);
+
+out:
+ return err;
+}
+
+static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
+ struct nlattr *data[])
+{
+ struct ip_tunnel *t, *nt;
+ struct net *net = dev_net(dev);
+ struct ipgre_net *ign = net_generic(net, ipgre_net_id);
+ struct ip_tunnel_parm p;
+ int mtu;
+
+ if (dev == ign->fb_tunnel_dev)
+ return -EINVAL;
+
+ nt = netdev_priv(dev);
+ ipgre_netlink_parms(data, &p);
+
+ t = ipgre_tunnel_locate(net, &p, 0);
+
+ if (t) {
+ if (t->dev != dev)
+ return -EEXIST;
+ } else {
+ unsigned nflags = 0;
+
+ t = nt;
+
+ if (ipv4_is_multicast(p.iph.daddr))
+ nflags = IFF_BROADCAST;
+ else if (p.iph.daddr)
+ nflags = IFF_POINTOPOINT;
+
+ if ((dev->flags ^ nflags) &
+ (IFF_POINTOPOINT | IFF_BROADCAST))
+ return -EINVAL;
+
+ ipgre_tunnel_unlink(ign, t);
+ t->parms.iph.saddr = p.iph.saddr;
+ t->parms.iph.daddr = p.iph.daddr;
+ t->parms.i_key = p.i_key;
+ memcpy(dev->dev_addr, &p.iph.saddr, 4);
+ memcpy(dev->broadcast, &p.iph.daddr, 4);
+ ipgre_tunnel_link(ign, t);
+ netdev_state_change(dev);
+ }
+
+ t->parms.o_key = p.o_key;
+ t->parms.iph.ttl = p.iph.ttl;
+ t->parms.iph.tos = p.iph.tos;
+ t->parms.iph.frag_off = p.iph.frag_off;
+
+ if (t->parms.link != p.link) {
+ t->parms.link = p.link;
+ mtu = ipgre_tunnel_bind_dev(dev);
+ if (!tb[IFLA_MTU])
+ dev->mtu = mtu;
+ netdev_state_change(dev);
+ }
+
+ return 0;
+}
+
+static size_t ipgre_get_size(const struct net_device *dev)
+{
+ return
+ /* IFLA_GRE_LINK */
+ nla_total_size(4) +
+ /* IFLA_GRE_IFLAGS */
+ nla_total_size(2) +
+ /* IFLA_GRE_OFLAGS */
+ nla_total_size(2) +
+ /* IFLA_GRE_IKEY */
+ nla_total_size(4) +
+ /* IFLA_GRE_OKEY */
+ nla_total_size(4) +
+ /* IFLA_GRE_LOCAL */
+ nla_total_size(4) +
+ /* IFLA_GRE_REMOTE */
+ nla_total_size(4) +
+ /* IFLA_GRE_TTL */
+ nla_total_size(1) +
+ /* IFLA_GRE_TOS */
+ nla_total_size(1) +
+ /* IFLA_GRE_PMTUDISC */
+ nla_total_size(1) +
+ 0;
+}
+
+static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+ struct ip_tunnel *t = netdev_priv(dev);
+ struct ip_tunnel_parm *p = &t->parms;
+
+ NLA_PUT_U32(skb, IFLA_GRE_LINK, p->link);
+ NLA_PUT_BE16(skb, IFLA_GRE_IFLAGS, p->i_flags);
+ NLA_PUT_BE16(skb, IFLA_GRE_OFLAGS, p->o_flags);
+ NLA_PUT_BE32(skb, IFLA_GRE_IKEY, p->i_key);
+ NLA_PUT_BE32(skb, IFLA_GRE_OKEY, p->o_key);
+ NLA_PUT_BE32(skb, IFLA_GRE_LOCAL, p->iph.saddr);
+ NLA_PUT_BE32(skb, IFLA_GRE_REMOTE, p->iph.daddr);
+ NLA_PUT_U8(skb, IFLA_GRE_TTL, p->iph.ttl);
+ NLA_PUT_U8(skb, IFLA_GRE_TOS, p->iph.tos);
+ NLA_PUT_U8(skb, IFLA_GRE_PMTUDISC, !!(p->iph.frag_off & htons(IP_DF)));
+
+ return 0;
+
+nla_put_failure:
+ return -EMSGSIZE;
+}
+
+static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = {
+ [IFLA_GRE_LINK] = { .type = NLA_U32 },
+ [IFLA_GRE_IFLAGS] = { .type = NLA_U16 },
+ [IFLA_GRE_OFLAGS] = { .type = NLA_U16 },
+ [IFLA_GRE_IKEY] = { .type = NLA_U32 },
+ [IFLA_GRE_OKEY] = { .type = NLA_U32 },
+ [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) },
+ [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) },
+ [IFLA_GRE_TTL] = { .type = NLA_U8 },
+ [IFLA_GRE_TOS] = { .type = NLA_U8 },
+ [IFLA_GRE_PMTUDISC] = { .type = NLA_U8 },
+};
+
+static struct rtnl_link_ops ipgre_link_ops __read_mostly = {
+ .kind = "gre",
+ .maxtype = IFLA_GRE_MAX,
+ .policy = ipgre_policy,
+ .priv_size = sizeof(struct ip_tunnel),
+ .setup = ipgre_tunnel_setup,
+ .validate = ipgre_tunnel_validate,
+ .newlink = ipgre_newlink,
+ .changelink = ipgre_changelink,
+ .get_size = ipgre_get_size,
+ .fill_info = ipgre_fill_info,
};
+static struct rtnl_link_ops ipgre_tap_ops __read_mostly = {
+ .kind = "gretap",
+ .maxtype = IFLA_GRE_MAX,
+ .policy = ipgre_policy,
+ .priv_size = sizeof(struct ip_tunnel),
+ .setup = ipgre_tap_setup,
+ .validate = ipgre_tap_validate,
+ .newlink = ipgre_newlink,
+ .changelink = ipgre_changelink,
+ .get_size = ipgre_get_size,
+ .fill_info = ipgre_fill_info,
+};
/*
* And now the modules code and kernel interface.
return -EAGAIN;
}
- ipgre_fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "gre0",
- ipgre_tunnel_setup);
- if (!ipgre_fb_tunnel_dev) {
- err = -ENOMEM;
- goto err1;
- }
+ err = register_pernet_gen_device(&ipgre_net_id, &ipgre_net_ops);
+ if (err < 0)
+ goto gen_device_failed;
+
+ err = rtnl_link_register(&ipgre_link_ops);
+ if (err < 0)
+ goto rtnl_link_failed;
- ipgre_fb_tunnel_dev->init = ipgre_fb_tunnel_init;
+ err = rtnl_link_register(&ipgre_tap_ops);
+ if (err < 0)
+ goto tap_ops_failed;
- if ((err = register_netdev(ipgre_fb_tunnel_dev)))
- goto err2;
out:
return err;
-err2:
- free_netdev(ipgre_fb_tunnel_dev);
-err1:
+
+tap_ops_failed:
+ rtnl_link_unregister(&ipgre_link_ops);
+rtnl_link_failed:
+ unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops);
+gen_device_failed:
inet_del_protocol(&ipgre_protocol, IPPROTO_GRE);
goto out;
}
-static void __exit ipgre_destroy_tunnels(void)
-{
- int prio;
-
- for (prio = 0; prio < 4; prio++) {
- int h;
- for (h = 0; h < HASH_SIZE; h++) {
- struct ip_tunnel *t;
- while ((t = tunnels[prio][h]) != NULL)
- unregister_netdevice(t->dev);
- }
- }
-}
-
static void __exit ipgre_fini(void)
{
+ rtnl_link_unregister(&ipgre_tap_ops);
+ rtnl_link_unregister(&ipgre_link_ops);
+ unregister_pernet_gen_device(ipgre_net_id, &ipgre_net_ops);
if (inet_del_protocol(&ipgre_protocol, IPPROTO_GRE) < 0)
printk(KERN_INFO "ipgre close: can't remove protocol\n");
-
- rtnl_lock();
- ipgre_destroy_tunnels();
- rtnl_unlock();
}
module_init(ipgre_init);
module_exit(ipgre_fini);
MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("gre");
+MODULE_ALIAS_RTNL_LINK("gretap");