linux-sg2042/net/ipv6/sit.c

1338 lines
30 KiB
C
Raw Normal View History

/*
* IPv6 over IPv4 tunnel device - Simple Internet Transition (SIT)
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
* Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*
* Changes:
* Roger Venning <r.venning@telstra.com>: 6to4 support
* Nate Thompson <nate@thebog.net>: 6to4 support
* Fred Templin <fred.l.templin@boeing.com>: isatap support
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/icmp.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <asm/uaccess.h>
#include <linux/init.h>
#include <linux/netfilter_ipv4.h>
#include <linux/if_ether.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/ip.h>
#include <net/udp.h>
#include <net/icmp.h>
#include <net/ipip.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/dsfield.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
/*
This version of net/ipv6/sit.c is cloned of net/ipv4/ip_gre.c
For comments look at net/ipv4/ip_gre.c --ANK
*/
#define HASH_SIZE 16
#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
static int ipip6_tunnel_init(struct net_device *dev);
static void ipip6_tunnel_setup(struct net_device *dev);
static void ipip6_dev_free(struct net_device *dev);
static int sit_net_id __read_mostly;
struct sit_net {
struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE];
struct ip_tunnel __rcu *tunnels_r[HASH_SIZE];
struct ip_tunnel __rcu *tunnels_l[HASH_SIZE];
struct ip_tunnel __rcu *tunnels_wc[1];
struct ip_tunnel __rcu **tunnels[4];
struct net_device *fb_tunnel_dev;
};
/*
* Locking : hash tables are protected by RCU and RTNL
*/
#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 {
u64 rx_packets;
u64 rx_bytes;
u64 tx_packets;
u64 tx_bytes;
struct u64_stats_sync syncp;
};
static struct rtnl_link_stats64 *ipip6_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *tot)
{
int i;
for_each_possible_cpu(i) {
const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
unsigned int start;
do {
start = u64_stats_fetch_begin_bh(&tstats->syncp);
rx_packets = tstats->rx_packets;
tx_packets = tstats->tx_packets;
rx_bytes = tstats->rx_bytes;
tx_bytes = tstats->tx_bytes;
} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
tot->rx_packets += rx_packets;
tot->tx_packets += tx_packets;
tot->rx_bytes += rx_bytes;
tot->tx_bytes += tx_bytes;
}
tot->rx_errors = dev->stats.rx_errors;
tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
tot->tx_dropped = dev->stats.tx_dropped;
tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
tot->tx_errors = dev->stats.tx_errors;
return tot;
}
/*
* Must be invoked with rcu_read_lock
*/
static struct ip_tunnel *ipip6_tunnel_lookup(struct net *net,
struct net_device *dev, __be32 remote, __be32 local)
{
unsigned int h0 = HASH(remote);
unsigned int h1 = HASH(local);
struct ip_tunnel *t;
struct sit_net *sitn = net_generic(net, sit_net_id);
for_each_ip_tunnel_rcu(sitn->tunnels_r_l[h0 ^ h1]) {
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr &&
(!dev || !t->parms.link || dev->iflink == t->parms.link) &&
(t->dev->flags & IFF_UP))
return t;
}
for_each_ip_tunnel_rcu(sitn->tunnels_r[h0]) {
if (remote == t->parms.iph.daddr &&
(!dev || !t->parms.link || dev->iflink == t->parms.link) &&
(t->dev->flags & IFF_UP))
return t;
}
for_each_ip_tunnel_rcu(sitn->tunnels_l[h1]) {
if (local == t->parms.iph.saddr &&
(!dev || !t->parms.link || dev->iflink == t->parms.link) &&
(t->dev->flags & IFF_UP))
return t;
}
t = rcu_dereference(sitn->tunnels_wc[0]);
if ((t != NULL) && (t->dev->flags & IFF_UP))
return t;
return NULL;
}
static struct ip_tunnel __rcu **__ipip6_bucket(struct sit_net *sitn,
struct ip_tunnel_parm *parms)
{
__be32 remote = parms->iph.daddr;
__be32 local = parms->iph.saddr;
unsigned int h = 0;
int prio = 0;
if (remote) {
prio |= 2;
h ^= HASH(remote);
}
if (local) {
prio |= 1;
h ^= HASH(local);
}
return &sitn->tunnels[prio][h];
}
static inline struct ip_tunnel __rcu **ipip6_bucket(struct sit_net *sitn,
struct ip_tunnel *t)
{
return __ipip6_bucket(sitn, &t->parms);
}
static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t)
{
struct ip_tunnel __rcu **tp;
struct ip_tunnel *iter;
for (tp = ipip6_bucket(sitn, t);
(iter = rtnl_dereference(*tp)) != NULL;
tp = &iter->next) {
if (t == iter) {
rcu_assign_pointer(*tp, t->next);
break;
}
}
}
static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t)
{
struct ip_tunnel __rcu **tp = ipip6_bucket(sitn, t);
rcu_assign_pointer(t->next, rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
}
static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
{
#ifdef CONFIG_IPV6_SIT_6RD
struct ip_tunnel *t = netdev_priv(dev);
if (t->dev == sitn->fb_tunnel_dev) {
ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0);
t->ip6rd.relay_prefix = 0;
t->ip6rd.prefixlen = 16;
t->ip6rd.relay_prefixlen = 0;
} else {
struct ip_tunnel *t0 = netdev_priv(sitn->fb_tunnel_dev);
memcpy(&t->ip6rd, &t0->ip6rd, sizeof(t->ip6rd));
}
#endif
}
static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
struct ip_tunnel_parm *parms, int create)
{
__be32 remote = parms->iph.daddr;
__be32 local = parms->iph.saddr;
struct ip_tunnel *t, *nt;
struct ip_tunnel __rcu **tp;
struct net_device *dev;
char name[IFNAMSIZ];
struct sit_net *sitn = net_generic(net, sit_net_id);
for (tp = __ipip6_bucket(sitn, parms);
(t = rtnl_dereference(*tp)) != NULL;
tp = &t->next) {
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr &&
parms->link == t->parms.link) {
if (create)
return NULL;
else
return t;
}
}
if (!create)
goto failed;
if (parms->name[0])
strlcpy(name, parms->name, IFNAMSIZ);
else
strcpy(name, "sit%d");
dev = alloc_netdev(sizeof(*t), name, ipip6_tunnel_setup);
if (dev == NULL)
return NULL;
dev_net_set(dev, net);
nt = netdev_priv(dev);
nt->parms = *parms;
if (ipip6_tunnel_init(dev) < 0)
goto failed_free;
ipip6_tunnel_clone_6rd(dev, sitn);
if (parms->i_flags & SIT_ISATAP)
dev->priv_flags |= IFF_ISATAP;
if (register_netdevice(dev) < 0)
goto failed_free;
strcpy(nt->parms.name, dev->name);
dev_hold(dev);
ipip6_tunnel_link(sitn, nt);
return nt;
failed_free:
ipip6_dev_free(dev);
failed:
return NULL;
}
#define for_each_prl_rcu(start) \
for (prl = rcu_dereference(start); \
prl; \
prl = rcu_dereference(prl->next))
static struct ip_tunnel_prl_entry *
__ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr)
{
struct ip_tunnel_prl_entry *prl;
for_each_prl_rcu(t->prl)
if (prl->addr == addr)
break;
return prl;
}
static int ipip6_tunnel_get_prl(struct ip_tunnel *t,
struct ip_tunnel_prl __user *a)
{
struct ip_tunnel_prl kprl, *kp;
struct ip_tunnel_prl_entry *prl;
unsigned int cmax, c = 0, ca, len;
int ret = 0;
if (copy_from_user(&kprl, a, sizeof(kprl)))
return -EFAULT;
cmax = kprl.datalen / sizeof(kprl);
if (cmax > 1 && kprl.addr != htonl(INADDR_ANY))
cmax = 1;
/* For simple GET or for root users,
* we try harder to allocate.
*/
kp = (cmax <= 1 || capable(CAP_NET_ADMIN)) ?
kcalloc(cmax, sizeof(*kp), GFP_KERNEL) :
NULL;
rcu_read_lock();
ca = t->prl_count < cmax ? t->prl_count : cmax;
if (!kp) {
/* We don't try hard to allocate much memory for
* non-root users.
* For root users, retry allocating enough memory for
* the answer.
*/
kp = kcalloc(ca, sizeof(*kp), GFP_ATOMIC);
if (!kp) {
ret = -ENOMEM;
goto out;
}
}
c = 0;
for_each_prl_rcu(t->prl) {
if (c >= cmax)
break;
if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr)
continue;
kp[c].addr = prl->addr;
kp[c].flags = prl->flags;
c++;
if (kprl.addr != htonl(INADDR_ANY))
break;
}
out:
rcu_read_unlock();
len = sizeof(*kp) * c;
ret = 0;
if ((len && copy_to_user(a + 1, kp, len)) || put_user(len, &a->datalen))
ret = -EFAULT;
kfree(kp);
return ret;
}
static int
ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg)
{
struct ip_tunnel_prl_entry *p;
int err = 0;
if (a->addr == htonl(INADDR_ANY))
return -EINVAL;
ASSERT_RTNL();
for (p = rtnl_dereference(t->prl); p; p = rtnl_dereference(p->next)) {
if (p->addr == a->addr) {
if (chg) {
p->flags = a->flags;
goto out;
}
err = -EEXIST;
goto out;
}
}
if (chg) {
err = -ENXIO;
goto out;
}
p = kzalloc(sizeof(struct ip_tunnel_prl_entry), GFP_KERNEL);
if (!p) {
err = -ENOBUFS;
goto out;
}
p->next = t->prl;
p->addr = a->addr;
p->flags = a->flags;
t->prl_count++;
rcu_assign_pointer(t->prl, p);
out:
return err;
}
static void prl_list_destroy_rcu(struct rcu_head *head)
{
struct ip_tunnel_prl_entry *p, *n;
p = container_of(head, struct ip_tunnel_prl_entry, rcu_head);
do {
n = rcu_dereference_protected(p->next, 1);
kfree(p);
p = n;
} while (p);
}
static int
ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a)
{
struct ip_tunnel_prl_entry *x;
struct ip_tunnel_prl_entry __rcu **p;
int err = 0;
ASSERT_RTNL();
if (a && a->addr != htonl(INADDR_ANY)) {
for (p = &t->prl;
(x = rtnl_dereference(*p)) != NULL;
p = &x->next) {
if (x->addr == a->addr) {
*p = x->next;
kfree_rcu(x, rcu_head);
t->prl_count--;
goto out;
}
}
err = -ENXIO;
} else {
x = rtnl_dereference(t->prl);
if (x) {
t->prl_count = 0;
call_rcu(&x->rcu_head, prl_list_destroy_rcu);
t->prl = NULL;
}
}
out:
return err;
}
static int
isatap_chksrc(struct sk_buff *skb, const struct iphdr *iph, struct ip_tunnel *t)
{
struct ip_tunnel_prl_entry *p;
int ok = 1;
rcu_read_lock();
p = __ipip6_tunnel_locate_prl(t, iph->saddr);
if (p) {
if (p->flags & PRL_DEFAULT)
skb->ndisc_nodetype = NDISC_NODETYPE_DEFAULT;
else
skb->ndisc_nodetype = NDISC_NODETYPE_NODEFAULT;
} else {
const struct in6_addr *addr6 = &ipv6_hdr(skb)->saddr;
if (ipv6_addr_is_isatap(addr6) &&
(addr6->s6_addr32[3] == iph->saddr) &&
ipv6_chk_prefix(addr6, t->dev))
skb->ndisc_nodetype = NDISC_NODETYPE_HOST;
else
ok = 0;
}
rcu_read_unlock();
return ok;
}
static void ipip6_tunnel_uninit(struct net_device *dev)
{
struct net *net = dev_net(dev);
struct sit_net *sitn = net_generic(net, sit_net_id);
if (dev == sitn->fb_tunnel_dev) {
RCU_INIT_POINTER(sitn->tunnels_wc[0], NULL);
} else {
ipip6_tunnel_unlink(sitn, netdev_priv(dev));
ipip6_tunnel_del_prl(netdev_priv(dev), NULL);
}
dev_put(dev);
}
static int ipip6_err(struct sk_buff *skb, u32 info)
{
/* 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.
*/
const struct iphdr *iph = (const struct iphdr *)skb->data;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct ip_tunnel *t;
int err;
switch (type) {
default:
case ICMP_PARAMETERPROB:
return 0;
case ICMP_DEST_UNREACH:
switch (code) {
case ICMP_SR_FAILED:
case ICMP_PORT_UNREACH:
/* Impossible event. */
return 0;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
I believe they are just ether pollution. --ANK
*/
break;
}
break;
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
return 0;
break;
case ICMP_REDIRECT:
break;
}
err = -ENOENT;
rcu_read_lock();
t = ipip6_tunnel_lookup(dev_net(skb->dev),
skb->dev,
iph->daddr,
iph->saddr);
if (t == NULL)
goto out;
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
ipv4_update_pmtu(skb, dev_net(skb->dev), info,
t->dev->ifindex, 0, IPPROTO_IPV6, 0);
err = 0;
goto out;
}
if (type == ICMP_REDIRECT) {
ipv4_redirect(skb, dev_net(skb->dev), t->dev->ifindex, 0,
IPPROTO_IPV6, 0);
err = 0;
goto out;
}
if (t->parms.iph.daddr == 0)
goto out;
err = 0;
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
goto out;
if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
t->err_count++;
else
t->err_count = 1;
t->err_time = jiffies;
out:
rcu_read_unlock();
return err;
}
static inline void ipip6_ecn_decapsulate(const struct iphdr *iph, struct sk_buff *skb)
{
if (INET_ECN_is_ce(iph->tos))
IP6_ECN_set_ce(ipv6_hdr(skb));
}
static int ipip6_rcv(struct sk_buff *skb)
{
const struct iphdr *iph;
struct ip_tunnel *tunnel;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto out;
iph = ip_hdr(skb);
rcu_read_lock();
tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev,
iph->saddr, iph->daddr);
if (tunnel != NULL) {
struct pcpu_tstats *tstats;
secpath_reset(skb);
skb->mac_header = skb->network_header;
skb_reset_network_header(skb);
IPCB(skb)->flags = 0;
skb->protocol = htons(ETH_P_IPV6);
skb->pkt_type = PACKET_HOST;
if ((tunnel->dev->priv_flags & IFF_ISATAP) &&
!isatap_chksrc(skb, iph, tunnel)) {
tunnel->dev->stats.rx_errors++;
rcu_read_unlock();
kfree_skb(skb);
return 0;
}
tstats = this_cpu_ptr(tunnel->dev->tstats);
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
__skb_tunnel_rx(skb, tunnel->dev);
ipip6_ecn_decapsulate(iph, skb);
netif_rx(skb);
rcu_read_unlock();
return 0;
}
/* no tunnel matched, let upstream know, ipsec may handle it */
rcu_read_unlock();
return 1;
out:
kfree_skb(skb);
return 0;
}
/*
* Returns the embedded IPv4 address if the IPv6 address
* comes from 6rd / 6to4 (RFC 3056) addr space.
*/
static inline
__be32 try_6rd(const struct in6_addr *v6dst, struct ip_tunnel *tunnel)
{
__be32 dst = 0;
#ifdef CONFIG_IPV6_SIT_6RD
if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix,
tunnel->ip6rd.prefixlen)) {
unsigned int pbw0, pbi0;
int pbi1;
u32 d;
pbw0 = tunnel->ip6rd.prefixlen >> 5;
pbi0 = tunnel->ip6rd.prefixlen & 0x1f;
d = (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >>
tunnel->ip6rd.relay_prefixlen;
pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen;
if (pbi1 > 0)
d |= ntohl(v6dst->s6_addr32[pbw0 + 1]) >>
(32 - pbi1);
dst = tunnel->ip6rd.relay_prefix | htonl(d);
}
#else
if (v6dst->s6_addr16[0] == htons(0x2002)) {
/* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */
memcpy(&dst, &v6dst->s6_addr16[1], 4);
}
#endif
return dst;
}
/*
* This function assumes it is being called from dev_queue_xmit()
* and that skb is filled properly by that function.
*/
static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct pcpu_tstats *tstats;
const struct iphdr *tiph = &tunnel->parms.iph;
const struct ipv6hdr *iph6 = ipv6_hdr(skb);
u8 tos = tunnel->parms.iph.tos;
__be16 df = tiph->frag_off;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
__be32 dst = tiph->daddr;
struct flowi4 fl4;
int mtu;
const struct in6_addr *addr6;
int addr_type;
if (skb->protocol != htons(ETH_P_IPV6))
goto tx_error;
if (tos == 1)
tos = ipv6_get_dsfield(iph6);
/* ISATAP (RFC4214) - must come before 6to4 */
if (dev->priv_flags & IFF_ISATAP) {
struct neighbour *neigh = NULL;
bool do_tx_error = false;
if (skb_dst(skb))
neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr);
if (neigh == NULL) {
net_dbg_ratelimited("sit: nexthop == NULL\n");
goto tx_error;
}
addr6 = (const struct in6_addr *)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if ((addr_type & IPV6_ADDR_UNICAST) &&
ipv6_addr_is_isatap(addr6))
dst = addr6->s6_addr32[3];
else
do_tx_error = true;
neigh_release(neigh);
if (do_tx_error)
goto tx_error;
}
if (!dst)
dst = try_6rd(&iph6->daddr, tunnel);
if (!dst) {
struct neighbour *neigh = NULL;
bool do_tx_error = false;
if (skb_dst(skb))
neigh = dst_neigh_lookup(skb_dst(skb), &iph6->daddr);
if (neigh == NULL) {
net_dbg_ratelimited("sit: nexthop == NULL\n");
goto tx_error;
}
addr6 = (const 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)
dst = addr6->s6_addr32[3];
else
do_tx_error = true;
neigh_release(neigh);
if (do_tx_error)
goto tx_error;
}
rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
dst, tiph->saddr,
0, 0,
IPPROTO_IPV6, RT_TOS(tos),
tunnel->parms.link);
if (IS_ERR(rt)) {
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
if (rt->rt_type != RTN_UNICAST) {
ip_rt_put(rt);
dev->stats.tx_carrier_errors++;
goto tx_error_icmp;
}
tdev = rt->dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
dev->stats.collisions++;
goto tx_error;
}
if (df) {
mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr);
if (mtu < 68) {
dev->stats.collisions++;
ip_rt_put(rt);
goto tx_error;
}
if (mtu < IPV6_MIN_MTU) {
mtu = IPV6_MIN_MTU;
df = 0;
}
if (tunnel->parms.iph.daddr && skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
if (skb->len > mtu) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
ip_rt_put(rt);
goto tx_error;
}
}
if (tunnel->err_count > 0) {
if (time_before(jiffies,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom = LL_RESERVED_SPACE(tdev)+sizeof(struct iphdr);
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);
dev->stats.tx_dropped++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
dev_kfree_skb(skb);
skb = new_skb;
iph6 = ipv6_hdr(skb);
}
skb->transport_header = skb->network_header;
skb_push(skb, sizeof(struct iphdr));
skb_reset_network_header(skb);
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
IPCB(skb)->flags = 0;
skb_dst_drop(skb);
skb_dst_set(skb, &rt->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_IPV6;
iph->tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
iph->daddr = fl4.daddr;
iph->saddr = fl4.saddr;
if ((iph->ttl = tiph->ttl) == 0)
iph->ttl = iph6->hop_limit;
nf_reset(skb);
tstats = this_cpu_ptr(dev->tstats);
__IPTUNNEL_XMIT(tstats, &dev->stats);
return NETDEV_TX_OK;
tx_error_icmp:
dst_link_failure(skb);
tx_error:
dev->stats.tx_errors++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
static void ipip6_tunnel_bind_dev(struct net_device *dev)
{
struct net_device *tdev = NULL;
struct ip_tunnel *tunnel;
const struct iphdr *iph;
struct flowi4 fl4;
tunnel = netdev_priv(dev);
iph = &tunnel->parms.iph;
if (iph->daddr) {
struct rtable *rt = ip_route_output_ports(dev_net(dev), &fl4, NULL,
iph->daddr, iph->saddr,
0, 0,
IPPROTO_IPV6,
RT_TOS(iph->tos),
tunnel->parms.link);
if (!IS_ERR(rt)) {
tdev = rt->dst.dev;
ip_rt_put(rt);
}
dev->flags |= IFF_POINTOPOINT;
}
if (!tdev && tunnel->parms.link)
tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
if (tdev) {
dev->hard_header_len = tdev->hard_header_len + sizeof(struct iphdr);
dev->mtu = tdev->mtu - sizeof(struct iphdr);
if (dev->mtu < IPV6_MIN_MTU)
dev->mtu = IPV6_MIN_MTU;
}
dev->iflink = tunnel->parms.link;
}
static int
ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd)
{
int err = 0;
struct ip_tunnel_parm p;
struct ip_tunnel_prl prl;
struct ip_tunnel *t;
struct net *net = dev_net(dev);
struct sit_net *sitn = net_generic(net, sit_net_id);
#ifdef CONFIG_IPV6_SIT_6RD
struct ip_tunnel_6rd ip6rd;
#endif
switch (cmd) {
case SIOCGETTUNNEL:
#ifdef CONFIG_IPV6_SIT_6RD
case SIOCGET6RD:
#endif
t = NULL;
if (dev == sitn->fb_tunnel_dev) {
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
err = -EFAULT;
break;
}
t = ipip6_tunnel_locate(net, &p, 0);
}
if (t == NULL)
t = netdev_priv(dev);
err = -EFAULT;
if (cmd == SIOCGETTUNNEL) {
memcpy(&p, &t->parms, sizeof(p));
if (copy_to_user(ifr->ifr_ifru.ifru_data, &p,
sizeof(p)))
goto done;
#ifdef CONFIG_IPV6_SIT_6RD
} else {
ip6rd.prefix = t->ip6rd.prefix;
ip6rd.relay_prefix = t->ip6rd.relay_prefix;
ip6rd.prefixlen = t->ip6rd.prefixlen;
ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen;
if (copy_to_user(ifr->ifr_ifru.ifru_data, &ip6rd,
sizeof(ip6rd)))
goto done;
#endif
}
err = 0;
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 (p.iph.version != 4 || p.iph.protocol != IPPROTO_IPV6 ||
p.iph.ihl != 5 || (p.iph.frag_off&htons(~IP_DF)))
goto done;
if (p.iph.ttl)
p.iph.frag_off |= htons(IP_DF);
t = ipip6_tunnel_locate(net, &p, cmd == SIOCADDTUNNEL);
if (dev != sitn->fb_tunnel_dev && cmd == SIOCCHGTUNNEL) {
if (t != NULL) {
if (t->dev != dev) {
err = -EEXIST;
break;
}
} else {
if (((dev->flags&IFF_POINTOPOINT) && !p.iph.daddr) ||
(!(dev->flags&IFF_POINTOPOINT) && p.iph.daddr)) {
err = -EINVAL;
break;
}
t = netdev_priv(dev);
ipip6_tunnel_unlink(sitn, t);
synchronize_net();
t->parms.iph.saddr = p.iph.saddr;
t->parms.iph.daddr = p.iph.daddr;
memcpy(dev->dev_addr, &p.iph.saddr, 4);
memcpy(dev->broadcast, &p.iph.daddr, 4);
ipip6_tunnel_link(sitn, 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;
if (t->parms.link != p.link) {
t->parms.link = p.link;
ipip6_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 == sitn->fb_tunnel_dev) {
err = -EFAULT;
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
goto done;
err = -ENOENT;
if ((t = ipip6_tunnel_locate(net, &p, 0)) == NULL)
goto done;
err = -EPERM;
if (t == netdev_priv(sitn->fb_tunnel_dev))
goto done;
dev = t->dev;
}
unregister_netdevice(dev);
err = 0;
break;
case SIOCGETPRL:
err = -EINVAL;
if (dev == sitn->fb_tunnel_dev)
goto done;
err = -ENOENT;
if (!(t = netdev_priv(dev)))
goto done;
err = ipip6_tunnel_get_prl(t, ifr->ifr_ifru.ifru_data);
break;
case SIOCADDPRL:
case SIOCDELPRL:
case SIOCCHGPRL:
err = -EPERM;
if (!capable(CAP_NET_ADMIN))
goto done;
err = -EINVAL;
if (dev == sitn->fb_tunnel_dev)
goto done;
err = -EFAULT;
if (copy_from_user(&prl, ifr->ifr_ifru.ifru_data, sizeof(prl)))
goto done;
err = -ENOENT;
if (!(t = netdev_priv(dev)))
goto done;
switch (cmd) {
case SIOCDELPRL:
err = ipip6_tunnel_del_prl(t, &prl);
break;
case SIOCADDPRL:
case SIOCCHGPRL:
err = ipip6_tunnel_add_prl(t, &prl, cmd == SIOCCHGPRL);
break;
}
netdev_state_change(dev);
break;
#ifdef CONFIG_IPV6_SIT_6RD
case SIOCADD6RD:
case SIOCCHG6RD:
case SIOCDEL6RD:
err = -EPERM;
if (!capable(CAP_NET_ADMIN))
goto done;
err = -EFAULT;
if (copy_from_user(&ip6rd, ifr->ifr_ifru.ifru_data,
sizeof(ip6rd)))
goto done;
t = netdev_priv(dev);
if (cmd != SIOCDEL6RD) {
struct in6_addr prefix;
__be32 relay_prefix;
err = -EINVAL;
if (ip6rd.relay_prefixlen > 32 ||
ip6rd.prefixlen + (32 - ip6rd.relay_prefixlen) > 64)
goto done;
ipv6_addr_prefix(&prefix, &ip6rd.prefix,
ip6rd.prefixlen);
if (!ipv6_addr_equal(&prefix, &ip6rd.prefix))
goto done;
if (ip6rd.relay_prefixlen)
relay_prefix = ip6rd.relay_prefix &
htonl(0xffffffffUL <<
(32 - ip6rd.relay_prefixlen));
else
relay_prefix = 0;
if (relay_prefix != ip6rd.relay_prefix)
goto done;
t->ip6rd.prefix = prefix;
t->ip6rd.relay_prefix = relay_prefix;
t->ip6rd.prefixlen = ip6rd.prefixlen;
t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen;
} else
ipip6_tunnel_clone_6rd(dev, sitn);
err = 0;
break;
#endif
default:
err = -EINVAL;
}
done:
return err;
}
static int ipip6_tunnel_change_mtu(struct net_device *dev, int new_mtu)
{
if (new_mtu < IPV6_MIN_MTU || new_mtu > 0xFFF8 - sizeof(struct iphdr))
return -EINVAL;
dev->mtu = new_mtu;
return 0;
}
static const struct net_device_ops ipip6_netdev_ops = {
.ndo_uninit = ipip6_tunnel_uninit,
.ndo_start_xmit = ipip6_tunnel_xmit,
.ndo_do_ioctl = ipip6_tunnel_ioctl,
.ndo_change_mtu = ipip6_tunnel_change_mtu,
.ndo_get_stats64= ipip6_get_stats64,
};
static void ipip6_dev_free(struct net_device *dev)
{
free_percpu(dev->tstats);
free_netdev(dev);
}
static void ipip6_tunnel_setup(struct net_device *dev)
{
dev->netdev_ops = &ipip6_netdev_ops;
dev->destructor = ipip6_dev_free;
dev->type = ARPHRD_SIT;
dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr);
dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr);
dev->flags = IFF_NOARP;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
dev->iflink = 0;
dev->addr_len = 4;
dev->features |= NETIF_F_NETNS_LOCAL;
dev->features |= NETIF_F_LLTX;
}
static int ipip6_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
tunnel->dev = dev;
memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4);
memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4);
ipip6_tunnel_bind_dev(dev);
dev->tstats = alloc_percpu(struct pcpu_tstats);
if (!dev->tstats)
return -ENOMEM;
return 0;
}
static int __net_init ipip6_fb_tunnel_init(struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct iphdr *iph = &tunnel->parms.iph;
struct net *net = dev_net(dev);
struct sit_net *sitn = net_generic(net, sit_net_id);
tunnel->dev = dev;
strcpy(tunnel->parms.name, dev->name);
iph->version = 4;
iph->protocol = IPPROTO_IPV6;
iph->ihl = 5;
iph->ttl = 64;
dev->tstats = alloc_percpu(struct pcpu_tstats);
if (!dev->tstats)
return -ENOMEM;
dev_hold(dev);
rcu_assign_pointer(sitn->tunnels_wc[0], tunnel);
return 0;
}
static struct xfrm_tunnel sit_handler __read_mostly = {
.handler = ipip6_rcv,
.err_handler = ipip6_err,
.priority = 1,
};
static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head)
{
int prio;
for (prio = 1; prio < 4; prio++) {
int h;
for (h = 0; h < HASH_SIZE; h++) {
struct ip_tunnel *t;
t = rtnl_dereference(sitn->tunnels[prio][h]);
while (t != NULL) {
unregister_netdevice_queue(t->dev, head);
t = rtnl_dereference(t->next);
}
}
}
}
static int __net_init sit_init_net(struct net *net)
{
struct sit_net *sitn = net_generic(net, sit_net_id);
struct ip_tunnel *t;
int err;
sitn->tunnels[0] = sitn->tunnels_wc;
sitn->tunnels[1] = sitn->tunnels_l;
sitn->tunnels[2] = sitn->tunnels_r;
sitn->tunnels[3] = sitn->tunnels_r_l;
sitn->fb_tunnel_dev = alloc_netdev(sizeof(struct ip_tunnel), "sit0",
ipip6_tunnel_setup);
if (!sitn->fb_tunnel_dev) {
err = -ENOMEM;
goto err_alloc_dev;
}
net: fix tunnels in netns after ndo_ changes dev_net_set() should be the very first thing after alloc_netdev(). "ndo_" changes turned simple assignment (which is OK to do before netns assignment) into quite non-trivial operation (which is not OK, init_net was used). This leads to incomplete initialisation of tunnel device in netns. BUG: unable to handle kernel NULL pointer dereference at 00000004 IP: [<c02efdb5>] ip6_tnl_exit_net+0x37/0x4f *pde = 00000000 Oops: 0000 [#1] PREEMPT DEBUG_PAGEALLOC last sysfs file: /sys/class/net/lo/operstate Pid: 10, comm: netns Not tainted (2.6.28-rc6 #1) EIP: 0060:[<c02efdb5>] EFLAGS: 00010246 CPU: 0 EIP is at ip6_tnl_exit_net+0x37/0x4f EAX: 00000000 EBX: 00000020 ECX: 00000000 EDX: 00000003 ESI: c5caef30 EDI: c782bbe8 EBP: c7909f50 ESP: c7909f48 DS: 007b ES: 007b FS: 0000 GS: 0000 SS: 0068 Process netns (pid: 10, ti=c7908000 task=c7905780 task.ti=c7908000) Stack: c03e75e0 c7390bc8 c7909f60 c0245448 c7390bd8 c7390bf0 c7909fa8 c012577a 00000000 00000002 00000000 c0125736 c782bbe8 c7909f90 c0308fe3 c782bc04 c7390bd4 c0245406 c084b718 c04f0770 c03ad785 c782bbe8 c782bc04 c782bc0c Call Trace: [<c0245448>] ? cleanup_net+0x42/0x82 [<c012577a>] ? run_workqueue+0xd6/0x1ae [<c0125736>] ? run_workqueue+0x92/0x1ae [<c0308fe3>] ? schedule+0x275/0x285 [<c0245406>] ? cleanup_net+0x0/0x82 [<c0125ae1>] ? worker_thread+0x81/0x8d [<c0128344>] ? autoremove_wake_function+0x0/0x33 [<c0125a60>] ? worker_thread+0x0/0x8d [<c012815c>] ? kthread+0x39/0x5e [<c0128123>] ? kthread+0x0/0x5e [<c0103b9f>] ? kernel_thread_helper+0x7/0x10 Code: db e8 05 ff ff ff 89 c6 e8 dc 04 f6 ff eb 08 8b 40 04 e8 38 89 f5 ff 8b 44 9e 04 85 c0 75 f0 43 83 fb 20 75 f2 8b 86 84 00 00 00 <8b> 40 04 e8 1c 89 f5 ff e8 98 04 f6 ff 89 f0 e8 f8 63 e6 ff 5b EIP: [<c02efdb5>] ip6_tnl_exit_net+0x37/0x4f SS:ESP 0068:c7909f48 ---[ end trace 6c2f2328fccd3e0c ]--- Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-11-24 09:26:26 +08:00
dev_net_set(sitn->fb_tunnel_dev, net);
err = ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
if (err)
goto err_dev_free;
ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
if ((err = register_netdev(sitn->fb_tunnel_dev)))
goto err_reg_dev;
t = netdev_priv(sitn->fb_tunnel_dev);
strcpy(t->parms.name, sitn->fb_tunnel_dev->name);
return 0;
err_reg_dev:
dev_put(sitn->fb_tunnel_dev);
err_dev_free:
ipip6_dev_free(sitn->fb_tunnel_dev);
err_alloc_dev:
return err;
}
static void __net_exit sit_exit_net(struct net *net)
{
struct sit_net *sitn = net_generic(net, sit_net_id);
LIST_HEAD(list);
rtnl_lock();
sit_destroy_tunnels(sitn, &list);
unregister_netdevice_queue(sitn->fb_tunnel_dev, &list);
unregister_netdevice_many(&list);
rtnl_unlock();
}
static struct pernet_operations sit_net_ops = {
.init = sit_init_net,
.exit = sit_exit_net,
.id = &sit_net_id,
.size = sizeof(struct sit_net),
};
static void __exit sit_cleanup(void)
{
xfrm4_tunnel_deregister(&sit_handler, AF_INET6);
unregister_pernet_device(&sit_net_ops);
rcu_barrier(); /* Wait for completion of call_rcu()'s */
}
static int __init sit_init(void)
{
int err;
pr_info("IPv6 over IPv4 tunneling driver\n");
err = register_pernet_device(&sit_net_ops);
if (err < 0)
return err;
err = xfrm4_tunnel_register(&sit_handler, AF_INET6);
if (err < 0) {
unregister_pernet_device(&sit_net_ops);
pr_info("%s: can't add protocol\n", __func__);
}
return err;
}
module_init(sit_init);
module_exit(sit_cleanup);
MODULE_LICENSE("GPL");
net: don't allow CAP_NET_ADMIN to load non-netdev kernel modules Since a8f80e8ff94ecba629542d9b4b5f5a8ee3eb565c any process with CAP_NET_ADMIN may load any module from /lib/modules/. This doesn't mean that CAP_NET_ADMIN is a superset of CAP_SYS_MODULE as modules are limited to /lib/modules/**. However, CAP_NET_ADMIN capability shouldn't allow anybody load any module not related to networking. This patch restricts an ability of autoloading modules to netdev modules with explicit aliases. This fixes CVE-2011-1019. Arnd Bergmann suggested to leave untouched the old pre-v2.6.32 behavior of loading netdev modules by name (without any prefix) for processes with CAP_SYS_MODULE to maintain the compatibility with network scripts that use autoloading netdev modules by aliases like "eth0", "wlan0". Currently there are only three users of the feature in the upstream kernel: ipip, ip_gre and sit. root@albatros:~# capsh --drop=$(seq -s, 0 11),$(seq -s, 13 34) -- root@albatros:~# grep Cap /proc/$$/status CapInh: 0000000000000000 CapPrm: fffffff800001000 CapEff: fffffff800001000 CapBnd: fffffff800001000 root@albatros:~# modprobe xfs FATAL: Error inserting xfs (/lib/modules/2.6.38-rc6-00001-g2bf4ca3/kernel/fs/xfs/xfs.ko): Operation not permitted root@albatros:~# lsmod | grep xfs root@albatros:~# ifconfig xfs xfs: error fetching interface information: Device not found root@albatros:~# lsmod | grep xfs root@albatros:~# lsmod | grep sit root@albatros:~# ifconfig sit sit: error fetching interface information: Device not found root@albatros:~# lsmod | grep sit root@albatros:~# ifconfig sit0 sit0 Link encap:IPv6-in-IPv4 NOARP MTU:1480 Metric:1 root@albatros:~# lsmod | grep sit sit 10457 0 tunnel4 2957 1 sit For CAP_SYS_MODULE module loading is still relaxed: root@albatros:~# grep Cap /proc/$$/status CapInh: 0000000000000000 CapPrm: ffffffffffffffff CapEff: ffffffffffffffff CapBnd: ffffffffffffffff root@albatros:~# ifconfig xfs xfs: error fetching interface information: Device not found root@albatros:~# lsmod | grep xfs xfs 745319 0 Reference: https://lkml.org/lkml/2011/2/24/203 Signed-off-by: Vasiliy Kulikov <segoon@openwall.com> Signed-off-by: Michael Tokarev <mjt@tls.msk.ru> Acked-by: David S. Miller <davem@davemloft.net> Acked-by: Kees Cook <kees.cook@canonical.com> Signed-off-by: James Morris <jmorris@namei.org>
2011-03-02 05:33:13 +08:00
MODULE_ALIAS_NETDEV("sit0");