aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4/ip_gre.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4/ip_gre.c')
-rw-r--r--net/ipv4/ip_gre.c1530
1 files changed, 514 insertions, 1016 deletions
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index e7821ba7a9a..9b842544aea 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -10,10 +10,13 @@
*
*/
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
+#include <linux/slab.h>
#include <asm/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
@@ -27,20 +30,25 @@
#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/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
-#include <net/ipip.h>
+#include <net/ip_tunnels.h>
#include <net/arp.h>
#include <net/checksum.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>
+#include <net/gre.h>
-#ifdef CONFIG_IPV6
+#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
@@ -58,16 +66,13 @@
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
- solution, but it supposes maintaing new variable in ALL
+ and silently drop packet when it expires. It is a good
+ solution, but it supposes maintaining new variable in ALL
skb, even if no tunneling is used.
- 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.
-
-
+ 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,
@@ -88,14 +93,14 @@
One of them is to parse packet trying to detect inner encapsulation
made by our node. It is difficult or even impossible, especially,
- taking into account fragmentation. TO be short, tt is not solution at all.
+ taking into account fragmentation. TO be short, ttl is not solution at all.
Current solution: The solution was UNEXPECTEDLY SIMPLE.
We force DF flag on tunnels with preconfigured hop limit,
that is ALL. :-) Well, it does not remove the problem completely,
but exponential growth of network traffic is changed to linear
(branches, that exceed pmtu are pruned) and tunnel mtu
- fastly degrades to value <68, where looping stops.
+ rapidly degrades to value <68, where looping stops.
Yes, it is not good if there exists a router in the loop,
which does not force DF, even when encapsulating packets have DF set.
But it is not our problem! Nobody could accuse us, we made
@@ -103,251 +108,54 @@
fatal route to network, even if it were you who configured
fatal static route: you are innocent. :-)
-
-
- 3. Really, ipv4/ipip.c, ipv4/ip_gre.c and ipv6/sit.c contain
- practically identical code. It would be good to glue them
- together, but it is not very evident, how to make them modular.
- sit is integral part of IPv6, ipip and gre are naturally modular.
- We could extract common parts (hash table, ioctl etc)
- to a separate module (ip_tunnel.c).
-
Alexey Kuznetsov.
*/
-static int ipgre_tunnel_init(struct net_device *dev);
-static void ipgre_tunnel_setup(struct net_device *dev);
-
-/* Fallback tunnel: no source, no destination, no key, no options */
-
-static int ipgre_fb_tunnel_init(struct net_device *dev);
-
-static struct net_device *ipgre_fb_tunnel_dev;
-
-/* Tunnel hash table */
-
-/*
- 4 hash tables:
-
- 3: (remote,local)
- 2: (remote,*)
- 1: (*,local)
- 0: (*,*)
-
- We require exact key match i.e. if a key is present in packet
- it will match only tunnel with the same key; if it is not present,
- it will match only keyless tunnel.
-
- All keysless packets, if not matched configured keyless tunnels
- will match fallback tunnel.
- */
-
-#define HASH_SIZE 16
-#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])
-
-static DEFINE_RWLOCK(ipgre_lock);
-
-/* Given src, dst and key, find appropriate for input tunnel. */
-
-static struct ip_tunnel * ipgre_tunnel_lookup(__be32 remote, __be32 local, __be32 key)
-{
- 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;
- }
- }
- 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 = tunnels_l[h1]; t; t = t->next) {
- if (local == t->parms.iph.saddr ||
- (local == t->parms.iph.daddr &&
- ipv4_is_multicast(local))) {
- if (t->parms.i_key == key && (t->dev->flags&IFF_UP))
- return t;
- }
- }
- for (t = tunnels_wc[h1]; t; t = t->next) {
- if (t->parms.i_key == key && (t->dev->flags&IFF_UP))
- return t;
- }
-
- if (ipgre_fb_tunnel_dev->flags&IFF_UP)
- return netdev_priv(ipgre_fb_tunnel_dev);
- return NULL;
-}
-
-static struct ip_tunnel **__ipgre_bucket(struct ip_tunnel_parm *parms)
-{
- __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 && !ipv4_is_multicast(remote)) {
- prio |= 2;
- h ^= HASH(remote);
- }
-
- return &tunnels[prio][h];
-}
-
-static inline struct ip_tunnel **ipgre_bucket(struct ip_tunnel *t)
-{
- return __ipgre_bucket(&t->parms);
-}
-
-static void ipgre_tunnel_link(struct ip_tunnel *t)
-{
- struct ip_tunnel **tp = ipgre_bucket(t);
-
- t->next = *tp;
- write_lock_bh(&ipgre_lock);
- *tp = t;
- write_unlock_bh(&ipgre_lock);
-}
-
-static void ipgre_tunnel_unlink(struct ip_tunnel *t)
-{
- struct ip_tunnel **tp;
+static bool log_ecn_error = true;
+module_param(log_ecn_error, bool, 0644);
+MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
- for (tp = ipgre_bucket(t); *tp; tp = &(*tp)->next) {
- if (t == *tp) {
- write_lock_bh(&ipgre_lock);
- *tp = t->next;
- write_unlock_bh(&ipgre_lock);
- break;
- }
- }
-}
-
-static struct ip_tunnel * ipgre_tunnel_locate(struct ip_tunnel_parm *parms, int create)
-{
- __be32 remote = parms->iph.daddr;
- __be32 local = parms->iph.saddr;
- __be32 key = parms->i_key;
- struct ip_tunnel *t, **tp, *nt;
- struct net_device *dev;
- char name[IFNAMSIZ];
-
- for (tp = __ipgre_bucket(parms); (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;
-
- if (parms->name[0])
- strlcpy(name, parms->name, IFNAMSIZ);
- else
- sprintf(name, "gre%%d");
-
- dev = alloc_netdev(sizeof(*t), name, ipgre_tunnel_setup);
- if (!dev)
- return NULL;
-
- if (strchr(name, '%')) {
- if (dev_alloc_name(dev, name) < 0)
- goto failed_free;
- }
-
- dev->init = ipgre_tunnel_init;
- nt = netdev_priv(dev);
- nt->parms = *parms;
-
- if (register_netdevice(dev) < 0)
- goto failed_free;
-
- dev_hold(dev);
- ipgre_tunnel_link(nt);
- return nt;
-
-failed_free:
- free_netdev(dev);
- return NULL;
-}
-
-static void ipgre_tunnel_uninit(struct net_device *dev)
-{
- ipgre_tunnel_unlink(netdev_priv(dev));
- dev_put(dev);
-}
+static struct rtnl_link_ops ipgre_link_ops __read_mostly;
+static int ipgre_tunnel_init(struct net_device *dev);
+static int ipgre_net_id __read_mostly;
+static int gre_tap_net_id __read_mostly;
-static void ipgre_err(struct sk_buff *skb, u32 info)
+static int ipgre_err(struct sk_buff *skb, u32 info,
+ const struct tnl_ptk_info *tpi)
{
-#ifndef I_WISH_WORLD_WERE_PERFECT
-
-/* It is not :-( 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.
-
- Moreover, Cisco "wise men" put GRE key to the third word
- in GRE header. It makes impossible maintaining even soft state for keyed
- GRE tunnels with enabled checksum. Tell them "thank you".
- Well, I wonder, rfc1812 was written by Cisco employee,
- what the hell these idiots break standrads established
- by themself???
- */
-
- struct iphdr *iph = (struct iphdr*)skb->data;
- __be16 *p = (__be16*)(skb->data+(iph->ihl<<2));
- int grehlen = (iph->ihl<<2) + 4;
+ /* 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.
+
+ Moreover, Cisco "wise men" put GRE key to the third word
+ in GRE header. It makes impossible maintaining even soft
+ state for keyed GRE tunnels with enabled checksum. Tell
+ them "thank you".
+
+ Well, I wonder, rfc1812 was written by Cisco employee,
+ what the hell these idiots break standards established
+ by themselves???
+ */
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn;
+ const struct iphdr *iph;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct ip_tunnel *t;
- __be16 flags;
-
- 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_KEY) {
- grehlen += 4;
- if (flags&GRE_CSUM)
- grehlen += 4;
- }
- }
-
- /* If only 8 bytes returned, keyed message will be dropped here */
- if (skb_headlen(skb) < grehlen)
- return;
switch (type) {
default:
case ICMP_PARAMETERPROB:
- return;
+ return PACKET_RCVD;
case ICMP_DEST_UNREACH:
switch (code) {
case ICMP_SR_FAILED:
case ICMP_PORT_UNREACH:
/* Impossible event. */
- return;
- case ICMP_FRAG_NEEDED:
- /* Soft state for pmtu is maintained by IP core. */
- return;
+ return PACKET_RCVD;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
@@ -358,735 +166,173 @@ static void ipgre_err(struct sk_buff *skb, u32 info)
break;
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
- return;
+ return PACKET_RCVD;
+ break;
+
+ case ICMP_REDIRECT:
break;
}
- read_lock(&ipgre_lock);
- t = ipgre_tunnel_lookup(iph->daddr, iph->saddr, (flags&GRE_KEY) ? *(((__be32*)p) + (grehlen>>2) - 1) : 0);
- if (t == NULL || t->parms.iph.daddr == 0 ||
+ if (tpi->proto == htons(ETH_P_TEB))
+ itn = net_generic(net, gre_tap_net_id);
+ else
+ itn = net_generic(net, ipgre_net_id);
+
+ iph = (const struct iphdr *)(icmp_hdr(skb) + 1);
+ t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags,
+ iph->daddr, iph->saddr, tpi->key);
+
+ if (t == NULL)
+ return PACKET_REJECT;
+
+ if (t->parms.iph.daddr == 0 ||
ipv4_is_multicast(t->parms.iph.daddr))
- goto out;
+ return PACKET_RCVD;
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
- goto out;
+ return PACKET_RCVD;
- if (jiffies - t->err_time < IPTUNNEL_ERR_TIMEO)
+ if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
t->err_count++;
else
t->err_count = 1;
t->err_time = jiffies;
-out:
- read_unlock(&ipgre_lock);
- return;
-#else
- struct iphdr *iph = (struct iphdr*)dp;
- struct iphdr *eiph;
- __be16 *p = (__be16*)(dp+(iph->ihl<<2));
- const int type = icmp_hdr(skb)->type;
- const int code = icmp_hdr(skb)->code;
- int rel_type = 0;
- int rel_code = 0;
- __be32 rel_info = 0;
- __u32 n = 0;
- __be16 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(icmp_hdr(skb)->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(icmp_hdr(skb)->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);
- skb_reset_network_header(skb2);
-
- /* 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(&init_net, &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(&init_net, &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
+ return PACKET_RCVD;
}
-static inline void ipgre_ecn_decapsulate(struct iphdr *iph, struct sk_buff *skb)
+static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi)
{
- if (INET_ECN_is_ce(iph->tos)) {
- if (skb->protocol == htons(ETH_P_IP)) {
- IP_ECN_set_ce(ip_hdr(skb));
- } else if (skb->protocol == htons(ETH_P_IPV6)) {
- IP6_ECN_set_ce(ipv6_hdr(skb));
- }
- }
-}
-
-static inline u8
-ipgre_ecn_encapsulate(u8 tos, struct iphdr *old_iph, struct sk_buff *skb)
-{
- u8 inner = 0;
- if (skb->protocol == htons(ETH_P_IP))
- inner = old_iph->tos;
- else if (skb->protocol == htons(ETH_P_IPV6))
- inner = ipv6_get_dsfield((struct ipv6hdr *)old_iph);
- return INET_ECN_encapsulate(tos, inner);
-}
-
-static int ipgre_rcv(struct sk_buff *skb)
-{
- struct iphdr *iph;
- u8 *h;
- __be16 flags;
- __sum16 csum = 0;
- __be32 key = 0;
- u32 seqno = 0;
+ struct net *net = dev_net(skb->dev);
+ struct ip_tunnel_net *itn;
+ const struct iphdr *iph;
struct ip_tunnel *tunnel;
- int offset = 4;
- if (!pskb_may_pull(skb, 16))
- goto drop_nolock;
+ if (tpi->proto == htons(ETH_P_TEB))
+ itn = net_generic(net, gre_tap_net_id);
+ else
+ itn = net_generic(net, ipgre_net_id);
iph = ip_hdr(skb);
- h = skb->data;
- flags = *(__be16*)h;
-
- if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) {
- /* - Version must be 0.
- - We do not support routing headers.
- */
- if (flags&(GRE_VERSION|GRE_ROUTING))
- goto drop_nolock;
-
- if (flags&GRE_CSUM) {
- switch (skb->ip_summed) {
- case CHECKSUM_COMPLETE:
- csum = csum_fold(skb->csum);
- if (!csum)
- break;
- /* fall through */
- case CHECKSUM_NONE:
- skb->csum = 0;
- csum = __skb_checksum_complete(skb);
- skb->ip_summed = CHECKSUM_COMPLETE;
- }
- offset += 4;
- }
- if (flags&GRE_KEY) {
- key = *(__be32*)(h + offset);
- offset += 4;
- }
- if (flags&GRE_SEQ) {
- seqno = ntohl(*(__be32*)(h + offset));
- offset += 4;
- }
- }
+ tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags,
+ iph->saddr, iph->daddr, tpi->key);
- read_lock(&ipgre_lock);
- if ((tunnel = ipgre_tunnel_lookup(iph->saddr, iph->daddr, key)) != NULL) {
- secpath_reset(skb);
-
- skb->protocol = *(__be16*)(h + 2);
- /* 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 == htons(ETH_P_WCCP)) {
- skb->protocol = htons(ETH_P_IP);
- if ((*(h + offset) & 0xF0) != 0x40)
- offset += 4;
- }
-
- skb->mac_header = skb->network_header;
- __pskb_pull(skb, offset);
- skb_reset_network_header(skb);
- skb_postpull_rcsum(skb, skb_transport_header(skb), offset);
- skb->pkt_type = PACKET_HOST;
-#ifdef CONFIG_NET_IPGRE_BROADCAST
- if (ipv4_is_multicast(iph->daddr)) {
- /* Looped back packet, drop it! */
- if (((struct rtable*)skb->dst)->fl.iif == 0)
- goto drop;
- tunnel->stat.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++;
- 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++;
- goto drop;
- }
- tunnel->i_seqno = seqno + 1;
- }
- tunnel->stat.rx_packets++;
- tunnel->stat.rx_bytes += skb->len;
- skb->dev = tunnel->dev;
- dst_release(skb->dst);
- skb->dst = NULL;
- nf_reset(skb);
- ipgre_ecn_decapsulate(iph, skb);
- netif_rx(skb);
- read_unlock(&ipgre_lock);
- return(0);
+ if (tunnel) {
+ skb_pop_mac_header(skb);
+ ip_tunnel_rcv(tunnel, skb, tpi, log_ecn_error);
+ return PACKET_RCVD;
}
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
-
-drop:
- read_unlock(&ipgre_lock);
-drop_nolock:
- kfree_skb(skb);
- return(0);
+ return PACKET_REJECT;
}
-static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
+static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
+ const struct iphdr *tnl_params,
+ __be16 proto)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
- struct net_device_stats *stats = &tunnel->stat;
- 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 iphdr *iph; /* Our new IP header */
- unsigned int max_headroom; /* The extra header space needed */
- int gre_hlen;
- __be32 dst;
- int mtu;
-
- if (tunnel->recursion++) {
- tunnel->stat.collisions++;
- goto tx_error;
- }
-
- if (dev->header_ops) {
- gre_hlen = 0;
- tiph = (struct iphdr*)skb->data;
- } else {
- gre_hlen = tunnel->hlen;
- tiph = &tunnel->parms.iph;
- }
-
- if ((dst = tiph->daddr) == 0) {
- /* NBMA tunnel */
-
- if (skb->dst == NULL) {
- tunnel->stat.tx_fifo_errors++;
- goto tx_error;
- }
-
- if (skb->protocol == htons(ETH_P_IP)) {
- rt = (struct rtable*)skb->dst;
- if ((dst = rt->rt_gateway) == 0)
- goto tx_error_icmp;
- }
-#ifdef CONFIG_IPV6
- else if (skb->protocol == htons(ETH_P_IPV6)) {
- struct in6_addr *addr6;
- int addr_type;
- struct neighbour *neigh = skb->dst->neighbour;
-
- if (neigh == NULL)
- goto tx_error;
-
- addr6 = (struct in6_addr*)&neigh->primary_key;
- addr_type = ipv6_addr_type(addr6);
-
- if (addr_type == IPV6_ADDR_ANY) {
- addr6 = &ipv6_hdr(skb)->daddr;
- addr_type = ipv6_addr_type(addr6);
- }
-
- if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
- goto tx_error_icmp;
-
- dst = addr6->s6_addr32[3];
- }
-#endif
- else
- goto tx_error;
- }
-
- tos = tiph->tos;
- if (tos&1) {
- if (skb->protocol == htons(ETH_P_IP))
- tos = old_iph->tos;
- tos &= ~1;
- }
-
- {
- 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(&init_net, &rt, &fl)) {
- tunnel->stat.tx_carrier_errors++;
- goto tx_error;
- }
- }
- tdev = rt->u.dst.dev;
+ struct tnl_ptk_info tpi;
- if (tdev == dev) {
- ip_rt_put(rt);
- tunnel->stat.collisions++;
- goto tx_error;
- }
-
- df = tiph->frag_off;
- if (df)
- mtu = dst_mtu(&rt->u.dst) - tunnel->hlen;
- else
- mtu = skb->dst ? dst_mtu(skb->dst) : dev->mtu;
+ tpi.flags = tunnel->parms.o_flags;
+ tpi.proto = proto;
+ tpi.key = tunnel->parms.o_key;
+ if (tunnel->parms.o_flags & TUNNEL_SEQ)
+ tunnel->o_seqno++;
+ tpi.seq = htonl(tunnel->o_seqno);
- if (skb->dst)
- skb->dst->ops->update_pmtu(skb->dst, mtu);
+ /* Push GRE header. */
+ gre_build_header(skb, &tpi, tunnel->hlen);
- if (skb->protocol == htons(ETH_P_IP)) {
- df |= (old_iph->frag_off&htons(IP_DF));
+ ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol);
+}
- if ((old_iph->frag_off&htons(IP_DF)) &&
- mtu < ntohs(old_iph->tot_len)) {
- icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
- ip_rt_put(rt);
- goto tx_error;
- }
- }
-#ifdef CONFIG_IPV6
- else if (skb->protocol == htons(ETH_P_IPV6)) {
- 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 &&
- !ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
- rt6->rt6i_dst.plen == 128) {
- rt6->rt6i_flags |= RTF_MODIFIED;
- skb->dst->metrics[RTAX_MTU-1] = mtu;
- }
- }
+static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
+ struct net_device *dev)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ const struct iphdr *tnl_params;
- if (mtu >= IPV6_MIN_MTU && mtu < skb->len - tunnel->hlen + gre_hlen) {
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
- ip_rt_put(rt);
- goto tx_error;
- }
- }
-#endif
+ skb = gre_handle_offloads(skb, !!(tunnel->parms.o_flags&TUNNEL_CSUM));
+ if (IS_ERR(skb))
+ goto out;
- if (tunnel->err_count > 0) {
- if (jiffies - tunnel->err_time < IPTUNNEL_ERR_TIMEO) {
- tunnel->err_count--;
+ if (dev->header_ops) {
+ /* Need space for new headers */
+ if (skb_cow_head(skb, dev->needed_headroom -
+ (tunnel->hlen + sizeof(struct iphdr))))
+ goto free_skb;
- dst_link_failure(skb);
- } else
- tunnel->err_count = 0;
- }
+ tnl_params = (const struct iphdr *)skb->data;
- max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen;
-
- 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++;
- dev_kfree_skb(skb);
- tunnel->recursion--;
- return 0;
- }
- if (skb->sk)
- skb_set_owner_w(new_skb, skb->sk);
- dev_kfree_skb(skb);
- skb = new_skb;
- old_iph = ip_hdr(skb);
- }
+ /* Pull skb since ip_tunnel_xmit() needs skb->data pointing
+ * to gre header.
+ */
+ skb_pull(skb, tunnel->hlen + sizeof(struct iphdr));
+ } else {
+ if (skb_cow_head(skb, dev->needed_headroom))
+ goto free_skb;
- skb->transport_header = skb->network_header;
- 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);
- dst_release(skb->dst);
- skb->dst = &rt->u.dst;
-
- /*
- * Push down and install the IPIP header.
- */
-
- iph = ip_hdr(skb);
- iph->version = 4;
- iph->ihl = sizeof(struct iphdr) >> 2;
- iph->frag_off = df;
- iph->protocol = IPPROTO_GRE;
- iph->tos = ipgre_ecn_encapsulate(tos, old_iph, skb);
- iph->daddr = rt->rt_dst;
- iph->saddr = rt->rt_src;
-
- if ((iph->ttl = tiph->ttl) == 0) {
- if (skb->protocol == htons(ETH_P_IP))
- iph->ttl = old_iph->ttl;
-#ifdef CONFIG_IPV6
- else if (skb->protocol == htons(ETH_P_IPV6))
- iph->ttl = ((struct ipv6hdr*)old_iph)->hop_limit;
-#endif
- else
- iph->ttl = dst_metric(&rt->u.dst, RTAX_HOPLIMIT);
+ tnl_params = &tunnel->parms.iph;
}
- ((__be16*)(iph+1))[0] = tunnel->parms.o_flags;
- ((__be16*)(iph+1))[1] = skb->protocol;
+ __gre_xmit(skb, dev, tnl_params, skb->protocol);
- if (tunnel->parms.o_flags&(GRE_KEY|GRE_CSUM|GRE_SEQ)) {
- __be32 *ptr = (__be32*)(((u8*)iph) + tunnel->hlen - 4);
+ return NETDEV_TX_OK;
- if (tunnel->parms.o_flags&GRE_SEQ) {
- ++tunnel->o_seqno;
- *ptr = htonl(tunnel->o_seqno);
- ptr--;
- }
- if (tunnel->parms.o_flags&GRE_KEY) {
- *ptr = tunnel->parms.o_key;
- ptr--;
- }
- if (tunnel->parms.o_flags&GRE_CSUM) {
- *ptr = 0;
- *(__sum16*)ptr = ip_compute_csum((void*)(iph+1), skb->len - sizeof(struct iphdr));
- }
- }
-
- nf_reset(skb);
-
- IPTUNNEL_XMIT();
- tunnel->recursion--;
- return 0;
-
-tx_error_icmp:
- dst_link_failure(skb);
-
-tx_error:
- stats->tx_errors++;
- dev_kfree_skb(skb);
- tunnel->recursion--;
- return 0;
+free_skb:
+ kfree_skb(skb);
+out:
+ dev->stats.tx_dropped++;
+ return NETDEV_TX_OK;
}
-static void ipgre_tunnel_bind_dev(struct net_device *dev)
+static netdev_tx_t gre_tap_xmit(struct sk_buff *skb,
+ 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;
+ struct ip_tunnel *tunnel = netdev_priv(dev);
- /* Guess output device to choose reasonable mtu and hard_header_len */
+ skb = gre_handle_offloads(skb, !!(tunnel->parms.o_flags&TUNNEL_CSUM));
+ if (IS_ERR(skb))
+ goto out;
- 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(&init_net, &rt, &fl)) {
- tdev = rt->u.dst.dev;
- ip_rt_put(rt);
- }
- dev->flags |= IFF_POINTOPOINT;
- }
+ if (skb_cow_head(skb, dev->needed_headroom))
+ goto free_skb;
- if (!tdev && tunnel->parms.link)
- tdev = __dev_get_by_index(&init_net, tunnel->parms.link);
+ __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB));
- if (tdev) {
- hlen = tdev->hard_header_len;
- 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->hard_header_len = hlen + addend;
- dev->mtu = mtu - addend;
- tunnel->hlen = addend;
+ return NETDEV_TX_OK;
+free_skb:
+ kfree_skb(skb);
+out:
+ dev->stats.tx_dropped++;
+ return NETDEV_TX_OK;
}
-static int
-ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
+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;
- switch (cmd) {
- case SIOCGETTUNNEL:
- t = NULL;
- if (dev == ipgre_fb_tunnel_dev) {
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
- err = -EFAULT;
- break;
- }
- t = ipgre_tunnel_locate(&p, 0);
- }
- if (t == NULL)
- t = netdev_priv(dev);
- memcpy(&p, &t->parms, sizeof(p));
- if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
- err = -EFAULT;
- break;
-
- case SIOCADDTUNNEL:
- case SIOCCHGTUNNEL:
- err = -EPERM;
- if (!capable(CAP_NET_ADMIN))
- goto done;
-
- err = -EFAULT;
- if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
- goto done;
-
- err = -EINVAL;
+ if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
+ return -EFAULT;
+ if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) {
if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE ||
p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)) ||
((p.i_flags|p.o_flags)&(GRE_VERSION|GRE_ROUTING)))
- goto done;
- if (p.iph.ttl)
- p.iph.frag_off |= htons(IP_DF);
-
- if (!(p.i_flags&GRE_KEY))
- p.i_key = 0;
- if (!(p.o_flags&GRE_KEY))
- p.o_key = 0;
-
- t = ipgre_tunnel_locate(&p, cmd == SIOCADDTUNNEL);
-
- if (dev != ipgre_fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
- if (t != NULL) {
- if (t->dev != dev) {
- err = -EEXIST;
- break;
- }
- } else {
- unsigned nflags=0;
-
- t = netdev_priv(dev);
-
- 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)) {
- err = -EINVAL;
- break;
- }
- ipgre_tunnel_unlink(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);
- netdev_state_change(dev);
- }
- }
-
- if (t) {
- err = 0;
- if (cmd == SIOCCHGTUNNEL) {
- 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;
- ipgre_tunnel_bind_dev(dev);
- netdev_state_change(dev);
- }
- }
- if (copy_to_user(ifr->ifr_ifru.ifru_data, &t->parms, sizeof(p)))
- err = -EFAULT;
- } else
- err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT);
- break;
-
- case SIOCDELTUNNEL:
- err = -EPERM;
- if (!capable(CAP_NET_ADMIN))
- goto done;
-
- if (dev == ipgre_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)
- goto done;
- err = -EPERM;
- if (t == netdev_priv(ipgre_fb_tunnel_dev))
- goto done;
- dev = t->dev;
- }
- unregister_netdevice(dev);
- err = 0;
- break;
-
- default:
- err = -EINVAL;
+ return -EINVAL;
}
+ p.i_flags = gre_flags_to_tnl_flags(p.i_flags);
+ p.o_flags = gre_flags_to_tnl_flags(p.o_flags);
-done:
- return err;
-}
+ err = ip_tunnel_ioctl(dev, &p, cmd);
+ if (err)
+ return err;
-static struct net_device_stats *ipgre_tunnel_get_stats(struct net_device *dev)
-{
- return &(((struct ip_tunnel*)netdev_priv(dev))->stat);
-}
+ p.i_flags = tnl_flags_to_gre_flags(p.i_flags);
+ p.o_flags = tnl_flags_to_gre_flags(p.o_flags);
-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)
- return -EINVAL;
- dev->mtu = new_mtu;
+ if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
+ return -EFAULT;
return 0;
}
@@ -1116,41 +362,36 @@ static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu)
...
ftp fec0:6666:6666::193.233.7.65
...
-
*/
-
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);
- __be16 *p = (__be16*)(iph+1);
+ struct iphdr *iph;
+ struct gre_base_hdr *greh;
- memcpy(iph, &t->parms.iph, sizeof(struct iphdr));
- p[0] = t->parms.o_flags;
- p[1] = htons(type);
+ iph = (struct iphdr *)skb_push(skb, t->hlen + sizeof(*iph));
+ greh = (struct gre_base_hdr *)(iph+1);
+ greh->flags = tnl_flags_to_gre_flags(t->parms.o_flags);
+ greh->protocol = htons(type);
- /*
- * Set the source hardware address.
- */
+ memcpy(iph, &t->parms.iph, sizeof(struct iphdr));
+ /* Set the source hardware address. */
if (saddr)
memcpy(&iph->saddr, saddr, 4);
-
- if (daddr) {
+ if (daddr)
memcpy(&iph->daddr, daddr, 4);
- return t->hlen;
- }
- if (iph->daddr && !ipv4_is_multicast(iph->daddr))
- return t->hlen;
+ if (iph->daddr)
+ return t->hlen + sizeof(*iph);
- return -t->hlen;
+ return -(t->hlen + sizeof(*iph));
}
static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr)
{
- struct iphdr *iph = (struct iphdr*) skb_mac_header(skb);
+ const struct iphdr *iph = (const struct iphdr *) skb_mac_header(skb);
memcpy(haddr, &iph->saddr, 4);
return 4;
}
@@ -1166,16 +407,18 @@ 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 flowi4 fl4;
struct rtable *rt;
- if (ip_route_output_key(&init_net, &rt, &fl))
+
+ rt = ip_route_output_gre(t->net, &fl4,
+ t->parms.iph.daddr,
+ t->parms.iph.saddr,
+ t->parms.o_key,
+ RT_TOS(t->parms.iph.tos),
+ t->parms.link);
+ if (IS_ERR(rt))
return -EADDRNOTAVAIL;
- dev = rt->u.dst.dev;
+ dev = rt->dst.dev;
ip_rt_put(rt);
if (__in_dev_get_rtnl(dev) == NULL)
return -EADDRNOTAVAIL;
@@ -1188,51 +431,80 @@ static int ipgre_open(struct net_device *dev)
static int ipgre_close(struct net_device *dev)
{
struct ip_tunnel *t = netdev_priv(dev);
+
if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) {
struct in_device *in_dev;
- in_dev = inetdev_by_index(dev->nd_net, t->mlink);
- if (in_dev) {
+ in_dev = inetdev_by_index(t->net, t->mlink);
+ if (in_dev)
ip_mc_dec_group(in_dev, t->parms.iph.daddr);
- in_dev_put(in_dev);
- }
}
return 0;
}
+#endif
+static const struct net_device_ops ipgre_netdev_ops = {
+ .ndo_init = ipgre_tunnel_init,
+ .ndo_uninit = ip_tunnel_uninit,
+#ifdef CONFIG_NET_IPGRE_BROADCAST
+ .ndo_open = ipgre_open,
+ .ndo_stop = ipgre_close,
#endif
+ .ndo_start_xmit = ipgre_xmit,
+ .ndo_do_ioctl = ipgre_tunnel_ioctl,
+ .ndo_change_mtu = ip_tunnel_change_mtu,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
+};
+
+#define GRE_FEATURES (NETIF_F_SG | \
+ NETIF_F_FRAGLIST | \
+ NETIF_F_HIGHDMA | \
+ NETIF_F_HW_CSUM)
static void ipgre_tunnel_setup(struct net_device *dev)
{
- dev->uninit = ipgre_tunnel_uninit;
- 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->netdev_ops = &ipgre_netdev_ops;
dev->type = ARPHRD_IPGRE;
- dev->hard_header_len = 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;
+ ip_tunnel_setup(dev, ipgre_net_id);
}
-static int ipgre_tunnel_init(struct net_device *dev)
+static void __gre_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel;
- struct iphdr *iph;
tunnel = netdev_priv(dev);
- iph = &tunnel->parms.iph;
+ tunnel->hlen = ip_gre_calc_hlen(tunnel->parms.o_flags);
+ tunnel->parms.iph.protocol = IPPROTO_GRE;
+
+ dev->needed_headroom = LL_MAX_HEADER + sizeof(struct iphdr) + 4;
+ dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr) - 4;
+
+ dev->features |= GRE_FEATURES;
+ dev->hw_features |= GRE_FEATURES;
+
+ if (!(tunnel->parms.o_flags & TUNNEL_SEQ)) {
+ /* TCP offload with GRE SEQ is not supported. */
+ dev->features |= NETIF_F_GSO_SOFTWARE;
+ dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+ /* Can use a lockless transmit, unless we generate
+ * output sequences
+ */
+ dev->features |= NETIF_F_LLTX;
+ }
+}
+
+static int ipgre_tunnel_init(struct net_device *dev)
+{
+ struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct iphdr *iph = &tunnel->parms.iph;
- tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
+ __gre_tunnel_init(dev);
- memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
- memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
+ memcpy(dev->dev_addr, &iph->saddr, 4);
+ memcpy(dev->broadcast, &iph->daddr, 4);
- ipgre_tunnel_bind_dev(dev);
+ dev->flags = IFF_NOARP;
+ dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
+ dev->addr_len = 4;
if (iph->daddr) {
#ifdef CONFIG_NET_IPGRE_BROADCAST
@@ -1241,100 +513,326 @@ static int ipgre_tunnel_init(struct net_device *dev)
return -EINVAL;
dev->flags = IFF_BROADCAST;
dev->header_ops = &ipgre_header_ops;
- dev->open = ipgre_open;
- dev->stop = ipgre_close;
}
#endif
} else
dev->header_ops = &ipgre_header_ops;
+ return ip_tunnel_init(dev);
+}
+
+static struct gre_cisco_protocol ipgre_protocol = {
+ .handler = ipgre_rcv,
+ .err_handler = ipgre_err,
+ .priority = 0,
+};
+
+static int __net_init ipgre_init_net(struct net *net)
+{
+ return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL);
+}
+
+static void __net_exit ipgre_exit_net(struct net *net)
+{
+ struct ip_tunnel_net *itn = net_generic(net, ipgre_net_id);
+ ip_tunnel_delete_net(itn, &ipgre_link_ops);
+}
+
+static struct pernet_operations ipgre_net_ops = {
+ .init = ipgre_init_net,
+ .exit = ipgre_exit_net,
+ .id = &ipgre_net_id,
+ .size = sizeof(struct ip_tunnel_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 __init ipgre_fb_tunnel_init(struct net_device *dev)
+static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[])
{
- struct ip_tunnel *tunnel = netdev_priv(dev);
- struct iphdr *iph = &tunnel->parms.iph;
+ __be32 daddr;
- tunnel->dev = dev;
- strcpy(tunnel->parms.name, dev->name);
+ 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 nlattr *tb[],
+ struct ip_tunnel_parm *parms)
+{
+ memset(parms, 0, sizeof(*parms));
+
+ parms->iph.protocol = IPPROTO_GRE;
- iph->version = 4;
- iph->protocol = IPPROTO_GRE;
- iph->ihl = 5;
- tunnel->hlen = sizeof(struct iphdr) + 4;
+ 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 = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_IFLAGS]));
+
+ if (data[IFLA_GRE_OFLAGS])
+ parms->o_flags = gre_flags_to_tnl_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);
+}
- dev_hold(dev);
- tunnels_wc[0] = tunnel;
+static int gre_tap_init(struct net_device *dev)
+{
+ __gre_tunnel_init(dev);
+
+ return ip_tunnel_init(dev);
+}
+
+static const struct net_device_ops gre_tap_netdev_ops = {
+ .ndo_init = gre_tap_init,
+ .ndo_uninit = ip_tunnel_uninit,
+ .ndo_start_xmit = gre_tap_xmit,
+ .ndo_set_mac_address = eth_mac_addr,
+ .ndo_validate_addr = eth_validate_addr,
+ .ndo_change_mtu = ip_tunnel_change_mtu,
+ .ndo_get_stats64 = ip_tunnel_get_stats64,
+};
+
+static void ipgre_tap_setup(struct net_device *dev)
+{
+ ether_setup(dev);
+ dev->netdev_ops = &gre_tap_netdev_ops;
+ dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
+ ip_tunnel_setup(dev, gre_tap_net_id);
+}
+
+static int ipgre_newlink(struct net *src_net, struct net_device *dev,
+ struct nlattr *tb[], struct nlattr *data[])
+{
+ struct ip_tunnel_parm p;
+
+ ipgre_netlink_parms(data, tb, &p);
+ return ip_tunnel_newlink(dev, tb, &p);
+}
+
+static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
+ struct nlattr *data[])
+{
+ struct ip_tunnel_parm p;
+
+ ipgre_netlink_parms(data, tb, &p);
+ return ip_tunnel_changelink(dev, tb, &p);
+}
+
+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;
+
+ if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) ||
+ nla_put_be16(skb, IFLA_GRE_IFLAGS, tnl_flags_to_gre_flags(p->i_flags)) ||
+ nla_put_be16(skb, IFLA_GRE_OFLAGS, tnl_flags_to_gre_flags(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))))
+ goto nla_put_failure;
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 net_protocol ipgre_protocol = {
- .handler = ipgre_rcv,
- .err_handler = ipgre_err,
+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,
+ .dellink = ip_tunnel_dellink,
+ .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,
+ .dellink = ip_tunnel_dellink,
+ .get_size = ipgre_get_size,
+ .fill_info = ipgre_fill_info,
+};
-/*
- * And now the modules code and kernel interface.
- */
+static int __net_init ipgre_tap_init_net(struct net *net)
+{
+ return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, NULL);
+}
+
+static void __net_exit ipgre_tap_exit_net(struct net *net)
+{
+ struct ip_tunnel_net *itn = net_generic(net, gre_tap_net_id);
+ ip_tunnel_delete_net(itn, &ipgre_tap_ops);
+}
+
+static struct pernet_operations ipgre_tap_net_ops = {
+ .init = ipgre_tap_init_net,
+ .exit = ipgre_tap_exit_net,
+ .id = &gre_tap_net_id,
+ .size = sizeof(struct ip_tunnel_net),
+};
static int __init ipgre_init(void)
{
int err;
- printk(KERN_INFO "GRE over IPv4 tunneling driver\n");
+ pr_info("GRE over IPv4 tunneling driver\n");
- if (inet_add_protocol(&ipgre_protocol, IPPROTO_GRE) < 0) {
- printk(KERN_INFO "ipgre init: can't add protocol\n");
- return -EAGAIN;
- }
+ err = register_pernet_device(&ipgre_net_ops);
+ if (err < 0)
+ return err;
+
+ err = register_pernet_device(&ipgre_tap_net_ops);
+ if (err < 0)
+ goto pnet_tap_faied;
- ipgre_fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "gre0",
- ipgre_tunnel_setup);
- if (!ipgre_fb_tunnel_dev) {
- err = -ENOMEM;
- goto err1;
+ err = gre_cisco_register(&ipgre_protocol);
+ if (err < 0) {
+ pr_info("%s: can't add protocol\n", __func__);
+ goto add_proto_failed;
}
- ipgre_fb_tunnel_dev->init = ipgre_fb_tunnel_init;
+ err = rtnl_link_register(&ipgre_link_ops);
+ if (err < 0)
+ goto rtnl_link_failed;
- if ((err = register_netdev(ipgre_fb_tunnel_dev)))
- goto err2;
-out:
- return err;
-err2:
- free_netdev(ipgre_fb_tunnel_dev);
-err1:
- inet_del_protocol(&ipgre_protocol, IPPROTO_GRE);
- goto out;
-}
+ err = rtnl_link_register(&ipgre_tap_ops);
+ if (err < 0)
+ goto tap_ops_failed;
-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);
- }
- }
+ return 0;
+
+tap_ops_failed:
+ rtnl_link_unregister(&ipgre_link_ops);
+rtnl_link_failed:
+ gre_cisco_unregister(&ipgre_protocol);
+add_proto_failed:
+ unregister_pernet_device(&ipgre_tap_net_ops);
+pnet_tap_faied:
+ unregister_pernet_device(&ipgre_net_ops);
+ return err;
}
static void __exit ipgre_fini(void)
{
- 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();
+ rtnl_link_unregister(&ipgre_tap_ops);
+ rtnl_link_unregister(&ipgre_link_ops);
+ gre_cisco_unregister(&ipgre_protocol);
+ unregister_pernet_device(&ipgre_tap_net_ops);
+ unregister_pernet_device(&ipgre_net_ops);
}
module_init(ipgre_init);
module_exit(ipgre_fini);
MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("gre");
+MODULE_ALIAS_RTNL_LINK("gretap");
+MODULE_ALIAS_NETDEV("gre0");
+MODULE_ALIAS_NETDEV("gretap0");
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-11-10 08:30:06 +0000