linux_dsm_epyc7002/net/ipv6/ip6_tunnel.c

2328 lines
56 KiB
C
Raw Normal View History

/*
* IPv6 tunneling device
* Linux INET6 implementation
*
* Authors:
* Ville Nuorvala <vnuorval@tcs.hut.fi>
* Yasuyuki Kozakai <kozakai@linux-ipv6.org>
*
* Based on:
* linux/net/ipv6/sit.c and linux/net/ipv4/ipip.c
*
* RFC 2473
*
* 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.
*
*/
#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/sockios.h>
#include <linux/icmp.h>
#include <linux/if.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/icmpv6.h>
#include <linux/init.h>
#include <linux/route.h>
#include <linux/rtnetlink.h>
#include <linux/netfilter_ipv6.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 15:04:11 +07:00
#include <linux/slab.h>
#include <linux/hash.h>
#include <linux/etherdevice.h>
#include <linux/uaccess.h>
#include <linux/atomic.h>
#include <net/icmp.h>
#include <net/ip.h>
#include <net/ip_tunnels.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/ip6_tunnel.h>
#include <net/xfrm.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/dst_metadata.h>
MODULE_AUTHOR("Ville Nuorvala");
MODULE_DESCRIPTION("IPv6 tunneling device");
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK("ip6tnl");
MODULE_ALIAS_NETDEV("ip6tnl0");
#define IP6_TUNNEL_HASH_SIZE_SHIFT 5
#define IP6_TUNNEL_HASH_SIZE (1 << IP6_TUNNEL_HASH_SIZE_SHIFT)
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");
static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2)
{
u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2);
return hash_32(hash, IP6_TUNNEL_HASH_SIZE_SHIFT);
}
static int ip6_tnl_dev_init(struct net_device *dev);
static void ip6_tnl_dev_setup(struct net_device *dev);
static struct rtnl_link_ops ip6_link_ops __read_mostly;
netns: make struct pernet_operations::id unsigned int Make struct pernet_operations::id unsigned. There are 2 reasons to do so: 1) This field is really an index into an zero based array and thus is unsigned entity. Using negative value is out-of-bound access by definition. 2) On x86_64 unsigned 32-bit data which are mixed with pointers via array indexing or offsets added or subtracted to pointers are preffered to signed 32-bit data. "int" being used as an array index needs to be sign-extended to 64-bit before being used. void f(long *p, int i) { g(p[i]); } roughly translates to movsx rsi, esi mov rdi, [rsi+...] call g MOVSX is 3 byte instruction which isn't necessary if the variable is unsigned because x86_64 is zero extending by default. Now, there is net_generic() function which, you guessed it right, uses "int" as an array index: static inline void *net_generic(const struct net *net, int id) { ... ptr = ng->ptr[id - 1]; ... } And this function is used a lot, so those sign extensions add up. Patch snipes ~1730 bytes on allyesconfig kernel (without all junk messing with code generation): add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) Unfortunately some functions actually grow bigger. This is a semmingly random artefact of code generation with register allocator being used differently. gcc decides that some variable needs to live in new r8+ registers and every access now requires REX prefix. Or it is shifted into r12, so [r12+0] addressing mode has to be used which is longer than [r8] However, overall balance is in negative direction: add/remove: 0/0 grow/shrink: 70/598 up/down: 396/-2126 (-1730) function old new delta nfsd4_lock 3886 3959 +73 tipc_link_build_proto_msg 1096 1140 +44 mac80211_hwsim_new_radio 2776 2808 +32 tipc_mon_rcv 1032 1058 +26 svcauth_gss_legacy_init 1413 1429 +16 tipc_bcbase_select_primary 379 392 +13 nfsd4_exchange_id 1247 1260 +13 nfsd4_setclientid_confirm 782 793 +11 ... put_client_renew_locked 494 480 -14 ip_set_sockfn_get 730 716 -14 geneve_sock_add 829 813 -16 nfsd4_sequence_done 721 703 -18 nlmclnt_lookup_host 708 686 -22 nfsd4_lockt 1085 1063 -22 nfs_get_client 1077 1050 -27 tcf_bpf_init 1106 1076 -30 nfsd4_encode_fattr 5997 5930 -67 Total: Before=154856051, After=154854321, chg -0.00% Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2016-11-17 08:58:21 +07:00
static unsigned int ip6_tnl_net_id __read_mostly;
struct ip6_tnl_net {
/* the IPv6 tunnel fallback device */
struct net_device *fb_tnl_dev;
/* lists for storing tunnels in use */
struct ip6_tnl __rcu *tnls_r_l[IP6_TUNNEL_HASH_SIZE];
struct ip6_tnl __rcu *tnls_wc[1];
struct ip6_tnl __rcu **tnls[2];
struct ip6_tnl __rcu *collect_md_tun;
};
static struct net_device_stats *ip6_get_stats(struct net_device *dev)
{
struct pcpu_sw_netstats tmp, sum = { 0 };
int i;
for_each_possible_cpu(i) {
unsigned int start;
const struct pcpu_sw_netstats *tstats =
per_cpu_ptr(dev->tstats, i);
do {
start = u64_stats_fetch_begin_irq(&tstats->syncp);
tmp.rx_packets = tstats->rx_packets;
tmp.rx_bytes = tstats->rx_bytes;
tmp.tx_packets = tstats->tx_packets;
tmp.tx_bytes = tstats->tx_bytes;
} while (u64_stats_fetch_retry_irq(&tstats->syncp, start));
sum.rx_packets += tmp.rx_packets;
sum.rx_bytes += tmp.rx_bytes;
sum.tx_packets += tmp.tx_packets;
sum.tx_bytes += tmp.tx_bytes;
}
dev->stats.rx_packets = sum.rx_packets;
dev->stats.rx_bytes = sum.rx_bytes;
dev->stats.tx_packets = sum.tx_packets;
dev->stats.tx_bytes = sum.tx_bytes;
return &dev->stats;
}
/**
* ip6_tnl_lookup - fetch tunnel matching the end-point addresses
* @remote: the address of the tunnel exit-point
* @local: the address of the tunnel entry-point
*
* Return:
* tunnel matching given end-points if found,
* else fallback tunnel if its device is up,
* else %NULL
**/
#define for_each_ip6_tunnel_rcu(start) \
for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
static struct ip6_tnl *
ip6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_addr *local)
{
unsigned int hash = HASH(remote, local);
struct ip6_tnl *t;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
struct in6_addr any;
for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
if (ipv6_addr_equal(local, &t->parms.laddr) &&
ipv6_addr_equal(remote, &t->parms.raddr) &&
(t->dev->flags & IFF_UP))
return t;
}
memset(&any, 0, sizeof(any));
hash = HASH(&any, local);
for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
if (ipv6_addr_equal(local, &t->parms.laddr) &&
ipv6_addr_any(&t->parms.raddr) &&
(t->dev->flags & IFF_UP))
return t;
}
hash = HASH(remote, &any);
for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[hash]) {
if (ipv6_addr_equal(remote, &t->parms.raddr) &&
ipv6_addr_any(&t->parms.laddr) &&
(t->dev->flags & IFF_UP))
return t;
}
t = rcu_dereference(ip6n->collect_md_tun);
if (t && t->dev->flags & IFF_UP)
return t;
t = rcu_dereference(ip6n->tnls_wc[0]);
if (t && (t->dev->flags & IFF_UP))
return t;
return NULL;
}
/**
* ip6_tnl_bucket - get head of list matching given tunnel parameters
* @p: parameters containing tunnel end-points
*
* Description:
* ip6_tnl_bucket() returns the head of the list matching the
* &struct in6_addr entries laddr and raddr in @p.
*
* Return: head of IPv6 tunnel list
**/
static struct ip6_tnl __rcu **
ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct __ip6_tnl_parm *p)
{
const struct in6_addr *remote = &p->raddr;
const struct in6_addr *local = &p->laddr;
unsigned int h = 0;
int prio = 0;
if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) {
prio = 1;
h = HASH(remote, local);
}
return &ip6n->tnls[prio][h];
}
/**
* ip6_tnl_link - add tunnel to hash table
* @t: tunnel to be added
**/
static void
ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
{
struct ip6_tnl __rcu **tp = ip6_tnl_bucket(ip6n, &t->parms);
if (t->parms.collect_md)
rcu_assign_pointer(ip6n->collect_md_tun, t);
rcu_assign_pointer(t->next , rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
}
/**
* ip6_tnl_unlink - remove tunnel from hash table
* @t: tunnel to be removed
**/
static void
ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
{
struct ip6_tnl __rcu **tp;
struct ip6_tnl *iter;
if (t->parms.collect_md)
rcu_assign_pointer(ip6n->collect_md_tun, NULL);
for (tp = ip6_tnl_bucket(ip6n, &t->parms);
(iter = rtnl_dereference(*tp)) != NULL;
tp = &iter->next) {
if (t == iter) {
rcu_assign_pointer(*tp, t->next);
break;
}
}
}
static void ip6_dev_free(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
gro_cells_destroy(&t->gro_cells);
dst_cache_destroy(&t->dst_cache);
free_percpu(dev->tstats);
}
static int ip6_tnl_create2(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct net *net = dev_net(dev);
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
int err;
t = netdev_priv(dev);
dev->rtnl_link_ops = &ip6_link_ops;
err = register_netdevice(dev);
if (err < 0)
goto out;
strcpy(t->parms.name, dev->name);
dev_hold(dev);
ip6_tnl_link(ip6n, t);
return 0;
out:
return err;
}
/**
* ip6_tnl_create - create a new tunnel
* @p: tunnel parameters
* @pt: pointer to new tunnel
*
* Description:
* Create tunnel matching given parameters.
*
* Return:
* created tunnel or error pointer
**/
static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p)
{
struct net_device *dev;
struct ip6_tnl *t;
char name[IFNAMSIZ];
int err = -ENOMEM;
if (p->name[0])
strlcpy(name, p->name, IFNAMSIZ);
else
sprintf(name, "ip6tnl%%d");
dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN,
ip6_tnl_dev_setup);
if (!dev)
goto failed;
dev_net_set(dev, net);
t = netdev_priv(dev);
t->parms = *p;
t->net = dev_net(dev);
err = ip6_tnl_create2(dev);
if (err < 0)
goto failed_free;
return t;
failed_free:
net: Fix inconsistent teardown and release of private netdev state. Network devices can allocate reasources and private memory using netdev_ops->ndo_init(). However, the release of these resources can occur in one of two different places. Either netdev_ops->ndo_uninit() or netdev->destructor(). The decision of which operation frees the resources depends upon whether it is necessary for all netdev refs to be released before it is safe to perform the freeing. netdev_ops->ndo_uninit() presumably can occur right after the NETDEV_UNREGISTER notifier completes and the unicast and multicast address lists are flushed. netdev->destructor(), on the other hand, does not run until the netdev references all go away. Further complicating the situation is that netdev->destructor() almost universally does also a free_netdev(). This creates a problem for the logic in register_netdevice(). Because all callers of register_netdevice() manage the freeing of the netdev, and invoke free_netdev(dev) if register_netdevice() fails. If netdev_ops->ndo_init() succeeds, but something else fails inside of register_netdevice(), it does call ndo_ops->ndo_uninit(). But it is not able to invoke netdev->destructor(). This is because netdev->destructor() will do a free_netdev() and then the caller of register_netdevice() will do the same. However, this means that the resources that would normally be released by netdev->destructor() will not be. Over the years drivers have added local hacks to deal with this, by invoking their destructor parts by hand when register_netdevice() fails. Many drivers do not try to deal with this, and instead we have leaks. Let's close this hole by formalizing the distinction between what private things need to be freed up by netdev->destructor() and whether the driver needs unregister_netdevice() to perform the free_netdev(). netdev->priv_destructor() performs all actions to free up the private resources that used to be freed by netdev->destructor(), except for free_netdev(). netdev->needs_free_netdev is a boolean that indicates whether free_netdev() should be done at the end of unregister_netdevice(). Now, register_netdevice() can sanely release all resources after ndo_ops->ndo_init() succeeds, by invoking both ndo_ops->ndo_uninit() and netdev->priv_destructor(). And at the end of unregister_netdevice(), we invoke netdev->priv_destructor() and optionally call free_netdev(). Signed-off-by: David S. Miller <davem@davemloft.net>
2017-05-08 23:52:56 +07:00
free_netdev(dev);
failed:
return ERR_PTR(err);
}
/**
* ip6_tnl_locate - find or create tunnel matching given parameters
* @p: tunnel parameters
* @create: != 0 if allowed to create new tunnel if no match found
*
* Description:
* ip6_tnl_locate() first tries to locate an existing tunnel
* based on @parms. If this is unsuccessful, but @create is set a new
* tunnel device is created and registered for use.
*
* Return:
* matching tunnel or error pointer
**/
static struct ip6_tnl *ip6_tnl_locate(struct net *net,
struct __ip6_tnl_parm *p, int create)
{
const struct in6_addr *remote = &p->raddr;
const struct in6_addr *local = &p->laddr;
struct ip6_tnl __rcu **tp;
struct ip6_tnl *t;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
for (tp = ip6_tnl_bucket(ip6n, p);
(t = rtnl_dereference(*tp)) != NULL;
tp = &t->next) {
if (ipv6_addr_equal(local, &t->parms.laddr) &&
ipv6_addr_equal(remote, &t->parms.raddr)) {
if (create)
return ERR_PTR(-EEXIST);
return t;
}
}
if (!create)
return ERR_PTR(-ENODEV);
return ip6_tnl_create(net, p);
}
/**
* ip6_tnl_dev_uninit - tunnel device uninitializer
* @dev: the device to be destroyed
*
* Description:
* ip6_tnl_dev_uninit() removes tunnel from its list
**/
static void
ip6_tnl_dev_uninit(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct net *net = t->net;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
if (dev == ip6n->fb_tnl_dev)
RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL);
else
ip6_tnl_unlink(ip6n, t);
dst_cache_reset(&t->dst_cache);
dev_put(dev);
}
/**
* parse_tvl_tnl_enc_lim - handle encapsulation limit option
* @skb: received socket buffer
*
* Return:
* 0 if none was found,
* else index to encapsulation limit
**/
__u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw)
{
const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw;
unsigned int nhoff = raw - skb->data;
unsigned int off = nhoff + sizeof(*ipv6h);
u8 next, nexthdr = ipv6h->nexthdr;
while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) {
struct ipv6_opt_hdr *hdr;
u16 optlen;
if (!pskb_may_pull(skb, off + sizeof(*hdr)))
break;
hdr = (struct ipv6_opt_hdr *)(skb->data + off);
if (nexthdr == NEXTHDR_FRAGMENT) {
struct frag_hdr *frag_hdr = (struct frag_hdr *) hdr;
if (frag_hdr->frag_off)
break;
optlen = 8;
} else if (nexthdr == NEXTHDR_AUTH) {
optlen = (hdr->hdrlen + 2) << 2;
} else {
optlen = ipv6_optlen(hdr);
}
/* cache hdr->nexthdr, since pskb_may_pull() might
* invalidate hdr
*/
next = hdr->nexthdr;
if (nexthdr == NEXTHDR_DEST) {
u16 i = 2;
/* Remember : hdr is no longer valid at this point. */
if (!pskb_may_pull(skb, off + optlen))
break;
while (1) {
struct ipv6_tlv_tnl_enc_lim *tel;
/* No more room for encapsulation limit */
if (i + sizeof(*tel) > optlen)
break;
tel = (struct ipv6_tlv_tnl_enc_lim *)(skb->data + off + i);
/* return index of option if found and valid */
if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT &&
tel->length == 1)
return i + off - nhoff;
/* else jump to next option */
if (tel->type)
i += tel->length + 2;
else
i++;
}
}
nexthdr = next;
off += optlen;
}
return 0;
}
EXPORT_SYMBOL(ip6_tnl_parse_tlv_enc_lim);
/**
* ip6_tnl_err - tunnel error handler
*
* Description:
* ip6_tnl_err() should handle errors in the tunnel according
* to the specifications in RFC 2473.
**/
[INET]: Introduce tunnel4/tunnel6 Basically this patch moves the generic tunnel protocol stuff out of xfrm4_tunnel/xfrm6_tunnel and moves it into the new files of tunnel4.c and tunnel6 respectively. The reason for this is that the problem that Hugo uncovered is only the tip of the iceberg. The real problem is that when we removed the dependency of ipip on xfrm4_tunnel we didn't really consider the module case at all. For instance, as it is it's possible to build both ipip and xfrm4_tunnel as modules and if the latter is loaded then ipip simply won't load. After considering the alternatives I've decided that the best way out of this is to restore the dependency of ipip on the non-xfrm-specific part of xfrm4_tunnel. This is acceptable IMHO because the intention of the removal was really to be able to use ipip without the xfrm subsystem. This is still preserved by this patch. So now both ipip/xfrm4_tunnel depend on the new tunnel4.c which handles the arbitration between the two. The order of processing is determined by a simple integer which ensures that ipip gets processed before xfrm4_tunnel. The situation for ICMP handling is a little bit more complicated since we may not have enough information to determine who it's for. It's not a big deal at the moment since the xfrm ICMP handlers are basically no-ops. In future we can deal with this when we look at ICMP caching in general. The user-visible change to this is the removal of the TUNNEL Kconfig prompts. This makes sense because it can only be used through IPCOMP as it stands. The addition of the new modules shouldn't introduce any problems since module dependency will cause them to be loaded. Oh and I also turned some unnecessary pskb's in IPv6 related to this patch to skb's. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:12:13 +07:00
static int
ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt,
u8 *type, u8 *code, int *msg, __u32 *info, int offset)
{
const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data;
struct net *net = dev_net(skb->dev);
u8 rel_type = ICMPV6_DEST_UNREACH;
u8 rel_code = ICMPV6_ADDR_UNREACH;
__u32 rel_info = 0;
struct ip6_tnl *t;
[INET]: Introduce tunnel4/tunnel6 Basically this patch moves the generic tunnel protocol stuff out of xfrm4_tunnel/xfrm6_tunnel and moves it into the new files of tunnel4.c and tunnel6 respectively. The reason for this is that the problem that Hugo uncovered is only the tip of the iceberg. The real problem is that when we removed the dependency of ipip on xfrm4_tunnel we didn't really consider the module case at all. For instance, as it is it's possible to build both ipip and xfrm4_tunnel as modules and if the latter is loaded then ipip simply won't load. After considering the alternatives I've decided that the best way out of this is to restore the dependency of ipip on the non-xfrm-specific part of xfrm4_tunnel. This is acceptable IMHO because the intention of the removal was really to be able to use ipip without the xfrm subsystem. This is still preserved by this patch. So now both ipip/xfrm4_tunnel depend on the new tunnel4.c which handles the arbitration between the two. The order of processing is determined by a simple integer which ensures that ipip gets processed before xfrm4_tunnel. The situation for ICMP handling is a little bit more complicated since we may not have enough information to determine who it's for. It's not a big deal at the moment since the xfrm ICMP handlers are basically no-ops. In future we can deal with this when we look at ICMP caching in general. The user-visible change to this is the removal of the TUNNEL Kconfig prompts. This makes sense because it can only be used through IPCOMP as it stands. The addition of the new modules shouldn't introduce any problems since module dependency will cause them to be loaded. Oh and I also turned some unnecessary pskb's in IPv6 related to this patch to skb's. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:12:13 +07:00
int err = -ENOENT;
int rel_msg = 0;
u8 tproto;
__u16 len;
/* If the packet doesn't contain the original IPv6 header we are
in trouble since we might need the source address for further
processing of the error. */
rcu_read_lock();
t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->daddr, &ipv6h->saddr);
if (!t)
goto out;
locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE() Please do not apply this to mainline directly, instead please re-run the coccinelle script shown below and apply its output. For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't harmful, and changing them results in churn. However, for some features, the read/write distinction is critical to correct operation. To distinguish these cases, separate read/write accessors must be used. This patch migrates (most) remaining ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following coccinelle script: ---- // Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and // WRITE_ONCE() // $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: davem@davemloft.net Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-24 04:07:29 +07:00
tproto = READ_ONCE(t->parms.proto);
if (tproto != ipproto && tproto != 0)
goto out;
[INET]: Introduce tunnel4/tunnel6 Basically this patch moves the generic tunnel protocol stuff out of xfrm4_tunnel/xfrm6_tunnel and moves it into the new files of tunnel4.c and tunnel6 respectively. The reason for this is that the problem that Hugo uncovered is only the tip of the iceberg. The real problem is that when we removed the dependency of ipip on xfrm4_tunnel we didn't really consider the module case at all. For instance, as it is it's possible to build both ipip and xfrm4_tunnel as modules and if the latter is loaded then ipip simply won't load. After considering the alternatives I've decided that the best way out of this is to restore the dependency of ipip on the non-xfrm-specific part of xfrm4_tunnel. This is acceptable IMHO because the intention of the removal was really to be able to use ipip without the xfrm subsystem. This is still preserved by this patch. So now both ipip/xfrm4_tunnel depend on the new tunnel4.c which handles the arbitration between the two. The order of processing is determined by a simple integer which ensures that ipip gets processed before xfrm4_tunnel. The situation for ICMP handling is a little bit more complicated since we may not have enough information to determine who it's for. It's not a big deal at the moment since the xfrm ICMP handlers are basically no-ops. In future we can deal with this when we look at ICMP caching in general. The user-visible change to this is the removal of the TUNNEL Kconfig prompts. This makes sense because it can only be used through IPCOMP as it stands. The addition of the new modules shouldn't introduce any problems since module dependency will cause them to be loaded. Oh and I also turned some unnecessary pskb's in IPv6 related to this patch to skb's. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:12:13 +07:00
err = 0;
switch (*type) {
struct ipv6_tlv_tnl_enc_lim *tel;
__u32 mtu, teli;
case ICMPV6_DEST_UNREACH:
net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n",
t->parms.name);
rel_msg = 1;
break;
case ICMPV6_TIME_EXCEED:
if ((*code) == ICMPV6_EXC_HOPLIMIT) {
net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n",
t->parms.name);
rel_msg = 1;
}
break;
case ICMPV6_PARAMPROB:
teli = 0;
if ((*code) == ICMPV6_HDR_FIELD)
teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data);
if (teli && teli == *info - 2) {
tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli];
if (tel->encap_limit == 0) {
net_dbg_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n",
t->parms.name);
rel_msg = 1;
}
} else {
net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n",
t->parms.name);
}
break;
case ICMPV6_PKT_TOOBIG:
ip6_update_pmtu(skb, net, htonl(*info), 0, 0,
sock_net_uid(net, NULL));
mtu = *info - offset;
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
len = sizeof(*ipv6h) + ntohs(ipv6h->payload_len);
if (len > mtu) {
rel_type = ICMPV6_PKT_TOOBIG;
rel_code = 0;
rel_info = mtu;
rel_msg = 1;
}
break;
case NDISC_REDIRECT:
ip6_redirect(skb, net, skb->dev->ifindex, 0,
sock_net_uid(net, NULL));
break;
}
*type = rel_type;
*code = rel_code;
*info = rel_info;
*msg = rel_msg;
out:
rcu_read_unlock();
return err;
}
static int
ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
__u32 rel_info = ntohl(info);
const struct iphdr *eiph;
struct sk_buff *skb2;
int err, rel_msg = 0;
u8 rel_type = type;
u8 rel_code = code;
struct rtable *rt;
struct flowi4 fl4;
err = ip6_tnl_err(skb, IPPROTO_IPIP, opt, &rel_type, &rel_code,
&rel_msg, &rel_info, offset);
if (err < 0)
return err;
if (rel_msg == 0)
return 0;
switch (rel_type) {
case ICMPV6_DEST_UNREACH:
if (rel_code != ICMPV6_ADDR_UNREACH)
return 0;
rel_type = ICMP_DEST_UNREACH;
rel_code = ICMP_HOST_UNREACH;
break;
case ICMPV6_PKT_TOOBIG:
if (rel_code != 0)
return 0;
rel_type = ICMP_DEST_UNREACH;
rel_code = ICMP_FRAG_NEEDED;
break;
default:
return 0;
}
if (!pskb_may_pull(skb, offset + sizeof(struct iphdr)))
return 0;
skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
return 0;
skb_dst_drop(skb2);
skb_pull(skb2, offset);
skb_reset_network_header(skb2);
eiph = ip_hdr(skb2);
/* Try to guess incoming interface */
rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->saddr,
0, 0, 0, IPPROTO_IPIP, RT_TOS(eiph->tos), 0);
if (IS_ERR(rt))
goto out;
skb2->dev = rt->dst.dev;
ip_rt_put(rt);
/* route "incoming" packet */
if (rt->rt_flags & RTCF_LOCAL) {
rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL,
eiph->daddr, eiph->saddr, 0, 0,
IPPROTO_IPIP, RT_TOS(eiph->tos), 0);
if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL) {
if (!IS_ERR(rt))
ip_rt_put(rt);
goto out;
}
skb_dst_set(skb2, &rt->dst);
} else {
if (ip_route_input(skb2, eiph->daddr, eiph->saddr, eiph->tos,
skb2->dev) ||
skb_dst(skb2)->dev->type != ARPHRD_TUNNEL)
goto out;
}
/* change mtu on this route */
if (rel_type == ICMP_DEST_UNREACH && rel_code == ICMP_FRAG_NEEDED) {
if (rel_info > dst_mtu(skb_dst(skb2)))
goto out;
skb_dst_update_pmtu(skb2, rel_info);
}
icmp_send(skb2, rel_type, rel_code, htonl(rel_info));
out:
kfree_skb(skb2);
return 0;
}
static int
ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
__u32 rel_info = ntohl(info);
int err, rel_msg = 0;
u8 rel_type = type;
u8 rel_code = code;
err = ip6_tnl_err(skb, IPPROTO_IPV6, opt, &rel_type, &rel_code,
&rel_msg, &rel_info, offset);
if (err < 0)
return err;
if (rel_msg && pskb_may_pull(skb, offset + sizeof(struct ipv6hdr))) {
struct rt6_info *rt;
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (!skb2)
return 0;
skb_dst_drop(skb2);
skb_pull(skb2, offset);
skb_reset_network_header(skb2);
/* Try to guess incoming interface */
rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr,
NULL, 0, skb2, 0);
if (rt && rt->dst.dev)
skb2->dev = rt->dst.dev;
icmpv6_send(skb2, rel_type, rel_code, rel_info);
ip6_rt_put(rt);
kfree_skb(skb2);
}
return 0;
}
static int ip4ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t,
const struct ipv6hdr *ipv6h,
struct sk_buff *skb)
{
__u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK;
if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY)
ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, dsfield);
return IP6_ECN_decapsulate(ipv6h, skb);
}
static int ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t,
const struct ipv6hdr *ipv6h,
struct sk_buff *skb)
{
if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY)
ipv6_copy_dscp(ipv6_get_dsfield(ipv6h), ipv6_hdr(skb));
return IP6_ECN_decapsulate(ipv6h, skb);
}
__u32 ip6_tnl_get_cap(struct ip6_tnl *t,
const struct in6_addr *laddr,
const struct in6_addr *raddr)
{
struct __ip6_tnl_parm *p = &t->parms;
int ltype = ipv6_addr_type(laddr);
int rtype = ipv6_addr_type(raddr);
__u32 flags = 0;
if (ltype == IPV6_ADDR_ANY || rtype == IPV6_ADDR_ANY) {
flags = IP6_TNL_F_CAP_PER_PACKET;
} else if (ltype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) &&
rtype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) &&
!((ltype|rtype) & IPV6_ADDR_LOOPBACK) &&
(!((ltype|rtype) & IPV6_ADDR_LINKLOCAL) || p->link)) {
if (ltype&IPV6_ADDR_UNICAST)
flags |= IP6_TNL_F_CAP_XMIT;
if (rtype&IPV6_ADDR_UNICAST)
flags |= IP6_TNL_F_CAP_RCV;
}
return flags;
}
EXPORT_SYMBOL(ip6_tnl_get_cap);
/* called with rcu_read_lock() */
int ip6_tnl_rcv_ctl(struct ip6_tnl *t,
const struct in6_addr *laddr,
const struct in6_addr *raddr)
{
struct __ip6_tnl_parm *p = &t->parms;
int ret = 0;
struct net *net = t->net;
if ((p->flags & IP6_TNL_F_CAP_RCV) ||
((p->flags & IP6_TNL_F_CAP_PER_PACKET) &&
(ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_RCV))) {
struct net_device *ldev = NULL;
if (p->link)
ldev = dev_get_by_index_rcu(net, p->link);
if ((ipv6_addr_is_multicast(laddr) ||
net/ipv6: Change address check to always take a device argument ipv6_chk_addr_and_flags determines if an address is a local address and optionally if it is an address on a specific device. For example, it is called by ip6_route_info_create to determine if a given gateway address is a local address. The address check currently does not consider L3 domains and as a result does not allow a route to be added in one VRF if the nexthop points to an address in a second VRF. e.g., $ ip route add 2001:db8:1::/64 vrf r2 via 2001:db8:102::23 Error: Invalid gateway address. where 2001:db8:102::23 is an address on an interface in vrf r1. ipv6_chk_addr_and_flags needs to allow callers to always pass in a device with a separate argument to not limit the address to the specific device. The device is used used to determine the L3 domain of interest. To that end add an argument to skip the device check and update callers to always pass a device where possible and use the new argument to mean any address in the domain. Update a handful of users of ipv6_chk_addr with a NULL dev argument. This patch handles the change to these callers without adding the domain check. ip6_validate_gw needs to handle 2 cases - one where the device is given as part of the nexthop spec and the other where the device is resolved. There is at least 1 VRF case where deferring the check to only after the route lookup has resolved the device fails with an unintuitive error "RTNETLINK answers: No route to host" as opposed to the preferred "Error: Gateway can not be a local address." The 'no route to host' error is because of the fallback to a full lookup. The check is done twice to avoid this error. Signed-off-by: David Ahern <dsahern@gmail.com> Reviewed-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-13 22:29:37 +07:00
likely(ipv6_chk_addr_and_flags(net, laddr, ldev, false,
0, IFA_F_TENTATIVE))) &&
((p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) ||
net/ipv6: Change address check to always take a device argument ipv6_chk_addr_and_flags determines if an address is a local address and optionally if it is an address on a specific device. For example, it is called by ip6_route_info_create to determine if a given gateway address is a local address. The address check currently does not consider L3 domains and as a result does not allow a route to be added in one VRF if the nexthop points to an address in a second VRF. e.g., $ ip route add 2001:db8:1::/64 vrf r2 via 2001:db8:102::23 Error: Invalid gateway address. where 2001:db8:102::23 is an address on an interface in vrf r1. ipv6_chk_addr_and_flags needs to allow callers to always pass in a device with a separate argument to not limit the address to the specific device. The device is used used to determine the L3 domain of interest. To that end add an argument to skip the device check and update callers to always pass a device where possible and use the new argument to mean any address in the domain. Update a handful of users of ipv6_chk_addr with a NULL dev argument. This patch handles the change to these callers without adding the domain check. ip6_validate_gw needs to handle 2 cases - one where the device is given as part of the nexthop spec and the other where the device is resolved. There is at least 1 VRF case where deferring the check to only after the route lookup has resolved the device fails with an unintuitive error "RTNETLINK answers: No route to host" as opposed to the preferred "Error: Gateway can not be a local address." The 'no route to host' error is because of the fallback to a full lookup. The check is done twice to avoid this error. Signed-off-by: David Ahern <dsahern@gmail.com> Reviewed-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-13 22:29:37 +07:00
likely(!ipv6_chk_addr_and_flags(net, raddr, ldev, true,
0, IFA_F_TENTATIVE))))
ret = 1;
}
return ret;
}
EXPORT_SYMBOL_GPL(ip6_tnl_rcv_ctl);
static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
const struct tnl_ptk_info *tpi,
struct metadata_dst *tun_dst,
int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t,
const struct ipv6hdr *ipv6h,
struct sk_buff *skb),
bool log_ecn_err)
{
struct pcpu_sw_netstats *tstats;
const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
int err;
if ((!(tpi->flags & TUNNEL_CSUM) &&
(tunnel->parms.i_flags & TUNNEL_CSUM)) ||
((tpi->flags & TUNNEL_CSUM) &&
!(tunnel->parms.i_flags & TUNNEL_CSUM))) {
tunnel->dev->stats.rx_crc_errors++;
tunnel->dev->stats.rx_errors++;
goto drop;
}
if (tunnel->parms.i_flags & TUNNEL_SEQ) {
if (!(tpi->flags & TUNNEL_SEQ) ||
(tunnel->i_seqno &&
(s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) {
tunnel->dev->stats.rx_fifo_errors++;
tunnel->dev->stats.rx_errors++;
goto drop;
}
tunnel->i_seqno = ntohl(tpi->seq) + 1;
}
skb->protocol = tpi->proto;
/* Warning: All skb pointers will be invalidated! */
if (tunnel->dev->type == ARPHRD_ETHER) {
if (!pskb_may_pull(skb, ETH_HLEN)) {
tunnel->dev->stats.rx_length_errors++;
tunnel->dev->stats.rx_errors++;
goto drop;
}
ipv6h = ipv6_hdr(skb);
skb->protocol = eth_type_trans(skb, tunnel->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
} else {
skb->dev = tunnel->dev;
}
skb_reset_network_header(skb);
memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
__skb_tunnel_rx(skb, tunnel->dev, tunnel->net);
err = dscp_ecn_decapsulate(tunnel, ipv6h, skb);
if (unlikely(err)) {
if (log_ecn_err)
net_info_ratelimited("non-ECT from %pI6 with DS=%#x\n",
&ipv6h->saddr,
ipv6_get_dsfield(ipv6h));
if (err > 1) {
++tunnel->dev->stats.rx_frame_errors;
++tunnel->dev->stats.rx_errors;
goto drop;
}
}
tstats = this_cpu_ptr(tunnel->dev->tstats);
u64_stats_update_begin(&tstats->syncp);
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev)));
if (tun_dst)
skb_dst_set(skb, (struct dst_entry *)tun_dst);
gro_cells_receive(&tunnel->gro_cells, skb);
return 0;
drop:
if (tun_dst)
dst_release((struct dst_entry *)tun_dst);
kfree_skb(skb);
return 0;
}
int ip6_tnl_rcv(struct ip6_tnl *t, struct sk_buff *skb,
const struct tnl_ptk_info *tpi,
struct metadata_dst *tun_dst,
bool log_ecn_err)
{
return __ip6_tnl_rcv(t, skb, tpi, tun_dst, ip6ip6_dscp_ecn_decapsulate,
log_ecn_err);
}
EXPORT_SYMBOL(ip6_tnl_rcv);
static const struct tnl_ptk_info tpi_v6 = {
/* no tunnel info required for ipxip6. */
.proto = htons(ETH_P_IPV6),
};
static const struct tnl_ptk_info tpi_v4 = {
/* no tunnel info required for ipxip6. */
.proto = htons(ETH_P_IP),
};
static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto,
const struct tnl_ptk_info *tpi,
int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t,
const struct ipv6hdr *ipv6h,
struct sk_buff *skb))
{
struct ip6_tnl *t;
const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
struct metadata_dst *tun_dst = NULL;
int ret = -1;
rcu_read_lock();
t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr);
if (t) {
locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE() Please do not apply this to mainline directly, instead please re-run the coccinelle script shown below and apply its output. For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't harmful, and changing them results in churn. However, for some features, the read/write distinction is critical to correct operation. To distinguish these cases, separate read/write accessors must be used. This patch migrates (most) remaining ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following coccinelle script: ---- // Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and // WRITE_ONCE() // $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: davem@davemloft.net Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-24 04:07:29 +07:00
u8 tproto = READ_ONCE(t->parms.proto);
if (tproto != ipproto && tproto != 0)
goto drop;
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
goto drop;
if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr))
goto drop;
if (iptunnel_pull_header(skb, 0, tpi->proto, false))
goto drop;
if (t->parms.collect_md) {
tun_dst = ipv6_tun_rx_dst(skb, 0, 0, 0);
if (!tun_dst)
goto drop;
}
ret = __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate,
log_ecn_error);
}
rcu_read_unlock();
return ret;
drop:
rcu_read_unlock();
kfree_skb(skb);
return 0;
}
static int ip4ip6_rcv(struct sk_buff *skb)
{
return ipxip6_rcv(skb, IPPROTO_IPIP, &tpi_v4,
ip4ip6_dscp_ecn_decapsulate);
}
static int ip6ip6_rcv(struct sk_buff *skb)
{
return ipxip6_rcv(skb, IPPROTO_IPV6, &tpi_v6,
ip6ip6_dscp_ecn_decapsulate);
}
struct ipv6_tel_txoption {
struct ipv6_txoptions ops;
__u8 dst_opt[8];
};
static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit)
{
memset(opt, 0, sizeof(struct ipv6_tel_txoption));
opt->dst_opt[2] = IPV6_TLV_TNL_ENCAP_LIMIT;
opt->dst_opt[3] = 1;
opt->dst_opt[4] = encap_limit;
opt->dst_opt[5] = IPV6_TLV_PADN;
opt->dst_opt[6] = 1;
opt->ops.dst1opt = (struct ipv6_opt_hdr *) opt->dst_opt;
opt->ops.opt_nflen = 8;
}
/**
* ip6_tnl_addr_conflict - compare packet addresses to tunnel's own
* @t: the outgoing tunnel device
* @hdr: IPv6 header from the incoming packet
*
* Description:
* Avoid trivial tunneling loop by checking that tunnel exit-point
* doesn't match source of incoming packet.
*
* Return:
* 1 if conflict,
* 0 else
**/
static inline bool
ip6_tnl_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr)
{
return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr);
}
int ip6_tnl_xmit_ctl(struct ip6_tnl *t,
const struct in6_addr *laddr,
const struct in6_addr *raddr)
{
struct __ip6_tnl_parm *p = &t->parms;
int ret = 0;
struct net *net = t->net;
if (t->parms.collect_md)
return 1;
if ((p->flags & IP6_TNL_F_CAP_XMIT) ||
((p->flags & IP6_TNL_F_CAP_PER_PACKET) &&
(ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_XMIT))) {
struct net_device *ldev = NULL;
rcu_read_lock();
if (p->link)
ldev = dev_get_by_index_rcu(net, p->link);
net/ipv6: Change address check to always take a device argument ipv6_chk_addr_and_flags determines if an address is a local address and optionally if it is an address on a specific device. For example, it is called by ip6_route_info_create to determine if a given gateway address is a local address. The address check currently does not consider L3 domains and as a result does not allow a route to be added in one VRF if the nexthop points to an address in a second VRF. e.g., $ ip route add 2001:db8:1::/64 vrf r2 via 2001:db8:102::23 Error: Invalid gateway address. where 2001:db8:102::23 is an address on an interface in vrf r1. ipv6_chk_addr_and_flags needs to allow callers to always pass in a device with a separate argument to not limit the address to the specific device. The device is used used to determine the L3 domain of interest. To that end add an argument to skip the device check and update callers to always pass a device where possible and use the new argument to mean any address in the domain. Update a handful of users of ipv6_chk_addr with a NULL dev argument. This patch handles the change to these callers without adding the domain check. ip6_validate_gw needs to handle 2 cases - one where the device is given as part of the nexthop spec and the other where the device is resolved. There is at least 1 VRF case where deferring the check to only after the route lookup has resolved the device fails with an unintuitive error "RTNETLINK answers: No route to host" as opposed to the preferred "Error: Gateway can not be a local address." The 'no route to host' error is because of the fallback to a full lookup. The check is done twice to avoid this error. Signed-off-by: David Ahern <dsahern@gmail.com> Reviewed-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-13 22:29:37 +07:00
if (unlikely(!ipv6_chk_addr_and_flags(net, laddr, ldev, false,
0, IFA_F_TENTATIVE)))
pr_warn("%s xmit: Local address not yet configured!\n",
p->name);
else if (!(p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) &&
!ipv6_addr_is_multicast(raddr) &&
net/ipv6: Change address check to always take a device argument ipv6_chk_addr_and_flags determines if an address is a local address and optionally if it is an address on a specific device. For example, it is called by ip6_route_info_create to determine if a given gateway address is a local address. The address check currently does not consider L3 domains and as a result does not allow a route to be added in one VRF if the nexthop points to an address in a second VRF. e.g., $ ip route add 2001:db8:1::/64 vrf r2 via 2001:db8:102::23 Error: Invalid gateway address. where 2001:db8:102::23 is an address on an interface in vrf r1. ipv6_chk_addr_and_flags needs to allow callers to always pass in a device with a separate argument to not limit the address to the specific device. The device is used used to determine the L3 domain of interest. To that end add an argument to skip the device check and update callers to always pass a device where possible and use the new argument to mean any address in the domain. Update a handful of users of ipv6_chk_addr with a NULL dev argument. This patch handles the change to these callers without adding the domain check. ip6_validate_gw needs to handle 2 cases - one where the device is given as part of the nexthop spec and the other where the device is resolved. There is at least 1 VRF case where deferring the check to only after the route lookup has resolved the device fails with an unintuitive error "RTNETLINK answers: No route to host" as opposed to the preferred "Error: Gateway can not be a local address." The 'no route to host' error is because of the fallback to a full lookup. The check is done twice to avoid this error. Signed-off-by: David Ahern <dsahern@gmail.com> Reviewed-by: Ido Schimmel <idosch@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2018-03-13 22:29:37 +07:00
unlikely(ipv6_chk_addr_and_flags(net, raddr, ldev,
true, 0, IFA_F_TENTATIVE)))
pr_warn("%s xmit: Routing loop! Remote address found on this node!\n",
p->name);
else
ret = 1;
rcu_read_unlock();
}
return ret;
}
EXPORT_SYMBOL_GPL(ip6_tnl_xmit_ctl);
/**
* ip6_tnl_xmit - encapsulate packet and send
* @skb: the outgoing socket buffer
* @dev: the outgoing tunnel device
* @dsfield: dscp code for outer header
* @fl6: flow of tunneled packet
* @encap_limit: encapsulation limit
* @pmtu: Path MTU is stored if packet is too big
* @proto: next header value
*
* Description:
* Build new header and do some sanity checks on the packet before sending
* it.
*
* Return:
* 0 on success
* -1 fail
* %-EMSGSIZE message too big. return mtu in this case.
**/
int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
struct flowi6 *fl6, int encap_limit, __u32 *pmtu,
__u8 proto)
{
struct ip6_tnl *t = netdev_priv(dev);
struct net *net = t->net;
struct net_device_stats *stats = &t->dev->stats;
struct ipv6hdr *ipv6h;
struct ipv6_tel_txoption opt;
struct dst_entry *dst = NULL, *ndst = NULL;
struct net_device *tdev;
int mtu;
unsigned int eth_hlen = t->dev->type == ARPHRD_ETHER ? ETH_HLEN : 0;
unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen;
unsigned int max_headroom = psh_hlen;
bool use_cache = false;
u8 hop_limit;
int err = -1;
if (t->parms.collect_md) {
hop_limit = skb_tunnel_info(skb)->key.ttl;
goto route_lookup;
} else {
hop_limit = t->parms.hop_limit;
}
/* NBMA tunnel */
if (ipv6_addr_any(&t->parms.raddr)) {
if (skb->protocol == htons(ETH_P_IPV6)) {
struct in6_addr *addr6;
struct neighbour *neigh;
int addr_type;
if (!skb_dst(skb))
goto tx_err_link_failure;
neigh = dst_neigh_lookup(skb_dst(skb),
&ipv6_hdr(skb)->daddr);
if (!neigh)
goto tx_err_link_failure;
addr6 = (struct in6_addr *)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if (addr_type == IPV6_ADDR_ANY)
addr6 = &ipv6_hdr(skb)->daddr;
memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
neigh_release(neigh);
}
} else if (t->parms.proto != 0 && !(t->parms.flags &
(IP6_TNL_F_USE_ORIG_TCLASS |
IP6_TNL_F_USE_ORIG_FWMARK))) {
/* enable the cache only if neither the outer protocol nor the
* routing decision depends on the current inner header value
*/
use_cache = true;
}
if (use_cache)
dst = dst_cache_get(&t->dst_cache);
if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr))
goto tx_err_link_failure;
if (!dst) {
route_lookup:
/* add dsfield to flowlabel for route lookup */
fl6->flowlabel = ip6_make_flowinfo(dsfield, fl6->flowlabel);
dst = ip6_route_output(net, NULL, fl6);
if (dst->error)
goto tx_err_link_failure;
dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0);
if (IS_ERR(dst)) {
err = PTR_ERR(dst);
dst = NULL;
goto tx_err_link_failure;
}
if (t->parms.collect_md &&
ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev,
&fl6->daddr, 0, &fl6->saddr))
goto tx_err_link_failure;
ndst = dst;
}
tdev = dst->dev;
if (tdev == dev) {
stats->collisions++;
net_warn_ratelimited("%s: Local routing loop detected!\n",
t->parms.name);
goto tx_err_dst_release;
}
mtu = dst_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen;
if (encap_limit >= 0) {
max_headroom += 8;
mtu -= 8;
}
if (skb->protocol == htons(ETH_P_IPV6)) {
if (mtu < IPV6_MIN_MTU)
mtu = IPV6_MIN_MTU;
} else if (mtu < 576) {
mtu = 576;
}
skb_dst_update_pmtu(skb, mtu);
if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
*pmtu = mtu;
err = -EMSGSIZE;
goto tx_err_dst_release;
}
if (t->err_count > 0) {
if (time_before(jiffies,
t->err_time + IP6TUNNEL_ERR_TIMEO)) {
t->err_count--;
dst_link_failure(skb);
} else {
t->err_count = 0;
}
}
skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev)));
/*
* Okay, now see if we can stuff it in the buffer as-is.
*/
max_headroom += LL_RESERVED_SPACE(tdev);
if (skb_headroom(skb) < max_headroom || skb_shared(skb) ||
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
struct sk_buff *new_skb;
new_skb = skb_realloc_headroom(skb, max_headroom);
if (!new_skb)
goto tx_err_dst_release;
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
consume_skb(skb);
skb = new_skb;
}
if (t->parms.collect_md) {
if (t->encap.type != TUNNEL_ENCAP_NONE)
goto tx_err_dst_release;
} else {
if (use_cache && ndst)
dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr);
}
skb_dst_set(skb, dst);
if (encap_limit >= 0) {
init_tel_txopt(&opt, encap_limit);
ipv6_push_frag_opts(skb, &opt.ops, &proto);
}
hop_limit = hop_limit ? : ip6_dst_hoplimit(dst);
/* Calculate max headroom for all the headers and adjust
* needed_headroom if necessary.
*/
max_headroom = LL_RESERVED_SPACE(dst->dev) + sizeof(struct ipv6hdr)
+ dst->header_len + t->hlen;
if (max_headroom > dev->needed_headroom)
dev->needed_headroom = max_headroom;
err = ip6_tnl_encap(skb, t, &proto, fl6);
if (err)
return err;
skb_push(skb, sizeof(struct ipv6hdr));
skb_reset_network_header(skb);
ipv6h = ipv6_hdr(skb);
ip6_flow_hdr(ipv6h, dsfield,
ip6_make_flowlabel(net, skb, fl6->flowlabel, true, fl6));
ipv6h->hop_limit = hop_limit;
ipv6h->nexthdr = proto;
ipv6h->saddr = fl6->saddr;
ipv6h->daddr = fl6->daddr;
ip6tunnel_xmit(NULL, skb, dev);
return 0;
tx_err_link_failure:
stats->tx_carrier_errors++;
dst_link_failure(skb);
tx_err_dst_release:
dst_release(dst);
return err;
}
EXPORT_SYMBOL(ip6_tnl_xmit);
static inline int
ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
const struct iphdr *iph = ip_hdr(skb);
int encap_limit = -1;
struct flowi6 fl6;
__u8 dsfield;
__u32 mtu;
u8 tproto;
int err;
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE() Please do not apply this to mainline directly, instead please re-run the coccinelle script shown below and apply its output. For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't harmful, and changing them results in churn. However, for some features, the read/write distinction is critical to correct operation. To distinguish these cases, separate read/write accessors must be used. This patch migrates (most) remaining ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following coccinelle script: ---- // Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and // WRITE_ONCE() // $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: davem@davemloft.net Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-24 04:07:29 +07:00
tproto = READ_ONCE(t->parms.proto);
if (tproto != IPPROTO_IPIP && tproto != 0)
return -1;
if (t->parms.collect_md) {
struct ip_tunnel_info *tun_info;
const struct ip_tunnel_key *key;
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
ip_tunnel_info_af(tun_info) != AF_INET6))
return -1;
key = &tun_info->key;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_IPIP;
fl6.daddr = key->u.ipv6.dst;
fl6.flowlabel = key->label;
dsfield = key->tos;
} else {
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
encap_limit = t->parms.encap_limit;
memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_IPIP;
if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
dsfield = ipv4_get_dsfield(iph);
else
dsfield = ip6_tclass(t->parms.flowinfo);
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
fl6.flowi6_mark = skb->mark;
else
fl6.flowi6_mark = t->parms.fwmark;
}
fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
return -1;
dsfield = INET_ECN_encapsulate(dsfield, ipv4_get_dsfield(iph));
skb_set_inner_ipproto(skb, IPPROTO_IPIP);
err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
IPPROTO_IPIP);
if (err != 0) {
/* XXX: send ICMP error even if DF is not set. */
if (err == -EMSGSIZE)
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
htonl(mtu));
return -1;
}
return 0;
}
static inline int
ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct ipv6hdr *ipv6h = ipv6_hdr(skb);
int encap_limit = -1;
__u16 offset;
struct flowi6 fl6;
__u8 dsfield;
__u32 mtu;
u8 tproto;
int err;
locking/atomics: COCCINELLE/treewide: Convert trivial ACCESS_ONCE() patterns to READ_ONCE()/WRITE_ONCE() Please do not apply this to mainline directly, instead please re-run the coccinelle script shown below and apply its output. For several reasons, it is desirable to use {READ,WRITE}_ONCE() in preference to ACCESS_ONCE(), and new code is expected to use one of the former. So far, there's been no reason to change most existing uses of ACCESS_ONCE(), as these aren't harmful, and changing them results in churn. However, for some features, the read/write distinction is critical to correct operation. To distinguish these cases, separate read/write accessors must be used. This patch migrates (most) remaining ACCESS_ONCE() instances to {READ,WRITE}_ONCE(), using the following coccinelle script: ---- // Convert trivial ACCESS_ONCE() uses to equivalent READ_ONCE() and // WRITE_ONCE() // $ make coccicheck COCCI=/home/mark/once.cocci SPFLAGS="--include-headers" MODE=patch virtual patch @ depends on patch @ expression E1, E2; @@ - ACCESS_ONCE(E1) = E2 + WRITE_ONCE(E1, E2) @ depends on patch @ expression E; @@ - ACCESS_ONCE(E) + READ_ONCE(E) ---- Signed-off-by: Mark Rutland <mark.rutland@arm.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: davem@davemloft.net Cc: linux-arch@vger.kernel.org Cc: mpe@ellerman.id.au Cc: shuah@kernel.org Cc: snitzer@redhat.com Cc: thor.thayer@linux.intel.com Cc: tj@kernel.org Cc: viro@zeniv.linux.org.uk Cc: will.deacon@arm.com Link: http://lkml.kernel.org/r/1508792849-3115-19-git-send-email-paulmck@linux.vnet.ibm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2017-10-24 04:07:29 +07:00
tproto = READ_ONCE(t->parms.proto);
if ((tproto != IPPROTO_IPV6 && tproto != 0) ||
ip6_tnl_addr_conflict(t, ipv6h))
return -1;
if (t->parms.collect_md) {
struct ip_tunnel_info *tun_info;
const struct ip_tunnel_key *key;
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
ip_tunnel_info_af(tun_info) != AF_INET6))
return -1;
key = &tun_info->key;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_IPV6;
fl6.daddr = key->u.ipv6.dst;
fl6.flowlabel = key->label;
dsfield = key->tos;
} else {
offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb));
/* ip6_tnl_parse_tlv_enc_lim() might have reallocated skb->head */
ipv6h = ipv6_hdr(skb);
if (offset > 0) {
struct ipv6_tlv_tnl_enc_lim *tel;
tel = (void *)&skb_network_header(skb)[offset];
if (tel->encap_limit == 0) {
icmpv6_send(skb, ICMPV6_PARAMPROB,
ICMPV6_HDR_FIELD, offset + 2);
return -1;
}
encap_limit = tel->encap_limit - 1;
} else if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) {
encap_limit = t->parms.encap_limit;
}
memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_IPV6;
if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS)
dsfield = ipv6_get_dsfield(ipv6h);
else
dsfield = ip6_tclass(t->parms.flowinfo);
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL)
fl6.flowlabel |= ip6_flowlabel(ipv6h);
if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK)
fl6.flowi6_mark = skb->mark;
else
fl6.flowi6_mark = t->parms.fwmark;
}
fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6))
return -1;
dsfield = INET_ECN_encapsulate(dsfield, ipv6_get_dsfield(ipv6h));
skb_set_inner_ipproto(skb, IPPROTO_IPV6);
err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
IPPROTO_IPV6);
if (err != 0) {
if (err == -EMSGSIZE)
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
return -1;
}
return 0;
}
static netdev_tx_t
ip6_tnl_start_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct net_device_stats *stats = &t->dev->stats;
int ret;
switch (skb->protocol) {
case htons(ETH_P_IP):
ret = ip4ip6_tnl_xmit(skb, dev);
break;
case htons(ETH_P_IPV6):
ret = ip6ip6_tnl_xmit(skb, dev);
break;
default:
goto tx_err;
}
if (ret < 0)
goto tx_err;
return NETDEV_TX_OK;
tx_err:
stats->tx_errors++;
stats->tx_dropped++;
kfree_skb(skb);
return NETDEV_TX_OK;
}
static void ip6_tnl_link_config(struct ip6_tnl *t)
{
struct net_device *dev = t->dev;
struct __ip6_tnl_parm *p = &t->parms;
struct flowi6 *fl6 = &t->fl.u.ip6;
int t_hlen;
memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr));
memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr));
/* Set up flowi template */
fl6->saddr = p->laddr;
fl6->daddr = p->raddr;
fl6->flowi6_oif = p->link;
fl6->flowlabel = 0;
if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS))
fl6->flowlabel |= IPV6_TCLASS_MASK & p->flowinfo;
if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL))
fl6->flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo;
p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV|IP6_TNL_F_CAP_PER_PACKET);
p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr);
if (p->flags&IP6_TNL_F_CAP_XMIT && p->flags&IP6_TNL_F_CAP_RCV)
dev->flags |= IFF_POINTOPOINT;
else
dev->flags &= ~IFF_POINTOPOINT;
t->tun_hlen = 0;
t->hlen = t->encap_hlen + t->tun_hlen;
t_hlen = t->hlen + sizeof(struct ipv6hdr);
if (p->flags & IP6_TNL_F_CAP_XMIT) {
int strict = (ipv6_addr_type(&p->raddr) &
(IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL));
struct rt6_info *rt = rt6_lookup(t->net,
&p->raddr, &p->laddr,
p->link, NULL, strict);
if (!rt)
return;
if (rt->dst.dev) {
dev->hard_header_len = rt->dst.dev->hard_header_len +
t_hlen;
dev->mtu = rt->dst.dev->mtu - t_hlen;
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
dev->mtu -= 8;
if (dev->mtu < IPV6_MIN_MTU)
dev->mtu = IPV6_MIN_MTU;
}
ip6_rt_put(rt);
}
}
/**
* ip6_tnl_change - update the tunnel parameters
* @t: tunnel to be changed
* @p: tunnel configuration parameters
*
* Description:
* ip6_tnl_change() updates the tunnel parameters
**/
static int
ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
{
t->parms.laddr = p->laddr;
t->parms.raddr = p->raddr;
t->parms.flags = p->flags;
t->parms.hop_limit = p->hop_limit;
t->parms.encap_limit = p->encap_limit;
t->parms.flowinfo = p->flowinfo;
t->parms.link = p->link;
t->parms.proto = p->proto;
t->parms.fwmark = p->fwmark;
dst_cache_reset(&t->dst_cache);
ip6_tnl_link_config(t);
return 0;
}
static int ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
{
struct net *net = t->net;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
int err;
ip6_tnl_unlink(ip6n, t);
synchronize_net();
err = ip6_tnl_change(t, p);
ip6_tnl_link(ip6n, t);
netdev_state_change(t->dev);
return err;
}
static int ip6_tnl0_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p)
{
/* for default tnl0 device allow to change only the proto */
t->parms.proto = p->proto;
netdev_state_change(t->dev);
return 0;
}
static void
ip6_tnl_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm *u)
{
p->laddr = u->laddr;
p->raddr = u->raddr;
p->flags = u->flags;
p->hop_limit = u->hop_limit;
p->encap_limit = u->encap_limit;
p->flowinfo = u->flowinfo;
p->link = u->link;
p->proto = u->proto;
memcpy(p->name, u->name, sizeof(u->name));
}
static void
ip6_tnl_parm_to_user(struct ip6_tnl_parm *u, const struct __ip6_tnl_parm *p)
{
u->laddr = p->laddr;
u->raddr = p->raddr;
u->flags = p->flags;
u->hop_limit = p->hop_limit;
u->encap_limit = p->encap_limit;
u->flowinfo = p->flowinfo;
u->link = p->link;
u->proto = p->proto;
memcpy(u->name, p->name, sizeof(u->name));
}
/**
* ip6_tnl_ioctl - configure ipv6 tunnels from userspace
* @dev: virtual device associated with tunnel
* @ifr: parameters passed from userspace
* @cmd: command to be performed
*
* Description:
* ip6_tnl_ioctl() is used for managing IPv6 tunnels
* from userspace.
*
* The possible commands are the following:
* %SIOCGETTUNNEL: get tunnel parameters for device
* %SIOCADDTUNNEL: add tunnel matching given tunnel parameters
* %SIOCCHGTUNNEL: change tunnel parameters to those given
* %SIOCDELTUNNEL: delete tunnel
*
* The fallback device "ip6tnl0", created during module
* initialization, can be used for creating other tunnel devices.
*
* Return:
* 0 on success,
* %-EFAULT if unable to copy data to or from userspace,
* %-EPERM if current process hasn't %CAP_NET_ADMIN set
* %-EINVAL if passed tunnel parameters are invalid,
* %-EEXIST if changing a tunnel's parameters would cause a conflict
* %-ENODEV if attempting to change or delete a nonexisting device
**/
static int
ip6_tnl_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
{
int err = 0;
struct ip6_tnl_parm p;
struct __ip6_tnl_parm p1;
struct ip6_tnl *t = netdev_priv(dev);
struct net *net = t->net;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
memset(&p1, 0, sizeof(p1));
switch (cmd) {
case SIOCGETTUNNEL:
if (dev == ip6n->fb_tnl_dev) {
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) {
err = -EFAULT;
break;
}
ip6_tnl_parm_from_user(&p1, &p);
t = ip6_tnl_locate(net, &p1, 0);
if (IS_ERR(t))
t = netdev_priv(dev);
} else {
memset(&p, 0, sizeof(p));
}
ip6_tnl_parm_to_user(&p, &t->parms);
if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) {
err = -EFAULT;
}
break;
case SIOCADDTUNNEL:
case SIOCCHGTUNNEL:
err = -EPERM;
net: Allow userns root to control ipv6 Allow an unpriviled user who has created a user namespace, and then created a network namespace to effectively use the new network namespace, by reducing capable(CAP_NET_ADMIN) and capable(CAP_NET_RAW) calls to be ns_capable(net->user_ns, CAP_NET_ADMIN), or capable(net->user_ns, CAP_NET_RAW) calls. Settings that merely control a single network device are allowed. Either the network device is a logical network device where restrictions make no difference or the network device is hardware NIC that has been explicity moved from the initial network namespace. In general policy and network stack state changes are allowed while resource control is left unchanged. Allow the SIOCSIFADDR ioctl to add ipv6 addresses. Allow the SIOCDIFADDR ioctl to delete ipv6 addresses. Allow the SIOCADDRT ioctl to add ipv6 routes. Allow the SIOCDELRT ioctl to delete ipv6 routes. Allow creation of ipv6 raw sockets. Allow setting the IPV6_JOIN_ANYCAST socket option. Allow setting the IPV6_FL_A_RENEW parameter of the IPV6_FLOWLABEL_MGR socket option. Allow setting the IPV6_TRANSPARENT socket option. Allow setting the IPV6_HOPOPTS socket option. Allow setting the IPV6_RTHDRDSTOPTS socket option. Allow setting the IPV6_DSTOPTS socket option. Allow setting the IPV6_IPSEC_POLICY socket option. Allow setting the IPV6_XFRM_POLICY socket option. Allow sending packets with the IPV6_2292HOPOPTS control message. Allow sending packets with the IPV6_2292DSTOPTS control message. Allow sending packets with the IPV6_RTHDRDSTOPTS control message. Allow setting the multicast routing socket options on non multicast routing sockets. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL, and SIOCDELTUNNEL ioctls for setting up, changing and deleting tunnels over ipv6. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL, SIOCDELTUNNEL ioctls for setting up, changing and deleting ipv6 over ipv4 tunnels. Allow the SIOCADDPRL, SIOCDELPRL, SIOCCHGPRL ioctls for adding, deleting, and changing the potential router list for ISATAP tunnels. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-16 10:03:06 +07:00
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
break;
err = -EFAULT;
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
break;
err = -EINVAL;
if (p.proto != IPPROTO_IPV6 && p.proto != IPPROTO_IPIP &&
p.proto != 0)
break;
ip6_tnl_parm_from_user(&p1, &p);
t = ip6_tnl_locate(net, &p1, cmd == SIOCADDTUNNEL);
if (cmd == SIOCCHGTUNNEL) {
if (!IS_ERR(t)) {
if (t->dev != dev) {
err = -EEXIST;
break;
}
} else
t = netdev_priv(dev);
if (dev == ip6n->fb_tnl_dev)
err = ip6_tnl0_update(t, &p1);
else
err = ip6_tnl_update(t, &p1);
}
if (!IS_ERR(t)) {
err = 0;
ip6_tnl_parm_to_user(&p, &t->parms);
if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p)))
err = -EFAULT;
} else {
err = PTR_ERR(t);
}
break;
case SIOCDELTUNNEL:
err = -EPERM;
net: Allow userns root to control ipv6 Allow an unpriviled user who has created a user namespace, and then created a network namespace to effectively use the new network namespace, by reducing capable(CAP_NET_ADMIN) and capable(CAP_NET_RAW) calls to be ns_capable(net->user_ns, CAP_NET_ADMIN), or capable(net->user_ns, CAP_NET_RAW) calls. Settings that merely control a single network device are allowed. Either the network device is a logical network device where restrictions make no difference or the network device is hardware NIC that has been explicity moved from the initial network namespace. In general policy and network stack state changes are allowed while resource control is left unchanged. Allow the SIOCSIFADDR ioctl to add ipv6 addresses. Allow the SIOCDIFADDR ioctl to delete ipv6 addresses. Allow the SIOCADDRT ioctl to add ipv6 routes. Allow the SIOCDELRT ioctl to delete ipv6 routes. Allow creation of ipv6 raw sockets. Allow setting the IPV6_JOIN_ANYCAST socket option. Allow setting the IPV6_FL_A_RENEW parameter of the IPV6_FLOWLABEL_MGR socket option. Allow setting the IPV6_TRANSPARENT socket option. Allow setting the IPV6_HOPOPTS socket option. Allow setting the IPV6_RTHDRDSTOPTS socket option. Allow setting the IPV6_DSTOPTS socket option. Allow setting the IPV6_IPSEC_POLICY socket option. Allow setting the IPV6_XFRM_POLICY socket option. Allow sending packets with the IPV6_2292HOPOPTS control message. Allow sending packets with the IPV6_2292DSTOPTS control message. Allow sending packets with the IPV6_RTHDRDSTOPTS control message. Allow setting the multicast routing socket options on non multicast routing sockets. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL, and SIOCDELTUNNEL ioctls for setting up, changing and deleting tunnels over ipv6. Allow the SIOCADDTUNNEL, SIOCCHGTUNNEL, SIOCDELTUNNEL ioctls for setting up, changing and deleting ipv6 over ipv4 tunnels. Allow the SIOCADDPRL, SIOCDELPRL, SIOCCHGPRL ioctls for adding, deleting, and changing the potential router list for ISATAP tunnels. Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-16 10:03:06 +07:00
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
break;
if (dev == ip6n->fb_tnl_dev) {
err = -EFAULT;
if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p)))
break;
err = -ENOENT;
ip6_tnl_parm_from_user(&p1, &p);
t = ip6_tnl_locate(net, &p1, 0);
if (IS_ERR(t))
break;
err = -EPERM;
if (t->dev == ip6n->fb_tnl_dev)
break;
dev = t->dev;
}
err = 0;
unregister_netdevice(dev);
break;
default:
err = -EINVAL;
}
return err;
}
/**
* ip6_tnl_change_mtu - change mtu manually for tunnel device
* @dev: virtual device associated with tunnel
* @new_mtu: the new mtu
*
* Return:
* 0 on success,
* %-EINVAL if mtu too small
**/
int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
{
struct ip6_tnl *tnl = netdev_priv(dev);
if (tnl->parms.proto == IPPROTO_IPV6) {
if (new_mtu < IPV6_MIN_MTU)
return -EINVAL;
} else {
if (new_mtu < ETH_MIN_MTU)
return -EINVAL;
}
if (new_mtu > 0xFFF8 - dev->hard_header_len)
return -EINVAL;
dev->mtu = new_mtu;
return 0;
}
EXPORT_SYMBOL(ip6_tnl_change_mtu);
int ip6_tnl_get_iflink(const struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
return t->parms.link;
}
EXPORT_SYMBOL(ip6_tnl_get_iflink);
int ip6_tnl_encap_add_ops(const struct ip6_tnl_encap_ops *ops,
unsigned int num)
{
if (num >= MAX_IPTUN_ENCAP_OPS)
return -ERANGE;
return !cmpxchg((const struct ip6_tnl_encap_ops **)
&ip6tun_encaps[num],
NULL, ops) ? 0 : -1;
}
EXPORT_SYMBOL(ip6_tnl_encap_add_ops);
int ip6_tnl_encap_del_ops(const struct ip6_tnl_encap_ops *ops,
unsigned int num)
{
int ret;
if (num >= MAX_IPTUN_ENCAP_OPS)
return -ERANGE;
ret = (cmpxchg((const struct ip6_tnl_encap_ops **)
&ip6tun_encaps[num],
ops, NULL) == ops) ? 0 : -1;
synchronize_net();
return ret;
}
EXPORT_SYMBOL(ip6_tnl_encap_del_ops);
int ip6_tnl_encap_setup(struct ip6_tnl *t,
struct ip_tunnel_encap *ipencap)
{
int hlen;
memset(&t->encap, 0, sizeof(t->encap));
hlen = ip6_encap_hlen(ipencap);
if (hlen < 0)
return hlen;
t->encap.type = ipencap->type;
t->encap.sport = ipencap->sport;
t->encap.dport = ipencap->dport;
t->encap.flags = ipencap->flags;
t->encap_hlen = hlen;
t->hlen = t->encap_hlen + t->tun_hlen;
return 0;
}
EXPORT_SYMBOL_GPL(ip6_tnl_encap_setup);
static const struct net_device_ops ip6_tnl_netdev_ops = {
.ndo_init = ip6_tnl_dev_init,
.ndo_uninit = ip6_tnl_dev_uninit,
.ndo_start_xmit = ip6_tnl_start_xmit,
.ndo_do_ioctl = ip6_tnl_ioctl,
.ndo_change_mtu = ip6_tnl_change_mtu,
.ndo_get_stats = ip6_get_stats,
.ndo_get_iflink = ip6_tnl_get_iflink,
};
#define IPXIPX_FEATURES (NETIF_F_SG | \
NETIF_F_FRAGLIST | \
NETIF_F_HIGHDMA | \
NETIF_F_GSO_SOFTWARE | \
NETIF_F_HW_CSUM)
/**
* ip6_tnl_dev_setup - setup virtual tunnel device
* @dev: virtual device associated with tunnel
*
* Description:
* Initialize function pointers and device parameters
**/
static void ip6_tnl_dev_setup(struct net_device *dev)
{
dev->netdev_ops = &ip6_tnl_netdev_ops;
net: Fix inconsistent teardown and release of private netdev state. Network devices can allocate reasources and private memory using netdev_ops->ndo_init(). However, the release of these resources can occur in one of two different places. Either netdev_ops->ndo_uninit() or netdev->destructor(). The decision of which operation frees the resources depends upon whether it is necessary for all netdev refs to be released before it is safe to perform the freeing. netdev_ops->ndo_uninit() presumably can occur right after the NETDEV_UNREGISTER notifier completes and the unicast and multicast address lists are flushed. netdev->destructor(), on the other hand, does not run until the netdev references all go away. Further complicating the situation is that netdev->destructor() almost universally does also a free_netdev(). This creates a problem for the logic in register_netdevice(). Because all callers of register_netdevice() manage the freeing of the netdev, and invoke free_netdev(dev) if register_netdevice() fails. If netdev_ops->ndo_init() succeeds, but something else fails inside of register_netdevice(), it does call ndo_ops->ndo_uninit(). But it is not able to invoke netdev->destructor(). This is because netdev->destructor() will do a free_netdev() and then the caller of register_netdevice() will do the same. However, this means that the resources that would normally be released by netdev->destructor() will not be. Over the years drivers have added local hacks to deal with this, by invoking their destructor parts by hand when register_netdevice() fails. Many drivers do not try to deal with this, and instead we have leaks. Let's close this hole by formalizing the distinction between what private things need to be freed up by netdev->destructor() and whether the driver needs unregister_netdevice() to perform the free_netdev(). netdev->priv_destructor() performs all actions to free up the private resources that used to be freed by netdev->destructor(), except for free_netdev(). netdev->needs_free_netdev is a boolean that indicates whether free_netdev() should be done at the end of unregister_netdevice(). Now, register_netdevice() can sanely release all resources after ndo_ops->ndo_init() succeeds, by invoking both ndo_ops->ndo_uninit() and netdev->priv_destructor(). And at the end of unregister_netdevice(), we invoke netdev->priv_destructor() and optionally call free_netdev(). Signed-off-by: David S. Miller <davem@davemloft.net>
2017-05-08 23:52:56 +07:00
dev->needs_free_netdev = true;
dev->priv_destructor = ip6_dev_free;
dev->type = ARPHRD_TUNNEL6;
dev->flags |= IFF_NOARP;
dev->addr_len = sizeof(struct in6_addr);
dev->features |= NETIF_F_LLTX;
netif_keep_dst(dev);
dev->features |= IPXIPX_FEATURES;
dev->hw_features |= IPXIPX_FEATURES;
/* This perm addr will be used as interface identifier by IPv6 */
dev->addr_assign_type = NET_ADDR_RANDOM;
eth_random_addr(dev->perm_addr);
}
/**
* ip6_tnl_dev_init_gen - general initializer for all tunnel devices
* @dev: virtual device associated with tunnel
**/
static inline int
ip6_tnl_dev_init_gen(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
int ret;
int t_hlen;
t->dev = dev;
t->net = dev_net(dev);
dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
ret = dst_cache_init(&t->dst_cache, GFP_KERNEL);
if (ret)
goto free_stats;
ret = gro_cells_init(&t->gro_cells, dev);
if (ret)
goto destroy_dst;
t->tun_hlen = 0;
t->hlen = t->encap_hlen + t->tun_hlen;
t_hlen = t->hlen + sizeof(struct ipv6hdr);
dev->type = ARPHRD_TUNNEL6;
dev->hard_header_len = LL_MAX_HEADER + t_hlen;
dev->mtu = ETH_DATA_LEN - t_hlen;
if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
dev->mtu -= 8;
dev->min_mtu = ETH_MIN_MTU;
dev->max_mtu = 0xFFF8 - dev->hard_header_len;
return 0;
destroy_dst:
dst_cache_destroy(&t->dst_cache);
free_stats:
free_percpu(dev->tstats);
dev->tstats = NULL;
return ret;
}
/**
* ip6_tnl_dev_init - initializer for all non fallback tunnel devices
* @dev: virtual device associated with tunnel
**/
static int ip6_tnl_dev_init(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
int err = ip6_tnl_dev_init_gen(dev);
if (err)
return err;
ip6_tnl_link_config(t);
if (t->parms.collect_md) {
dev->features |= NETIF_F_NETNS_LOCAL;
netif_keep_dst(dev);
}
return 0;
}
/**
* ip6_fb_tnl_dev_init - initializer for fallback tunnel device
* @dev: fallback device
*
* Return: 0
**/
static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev)
{
struct ip6_tnl *t = netdev_priv(dev);
struct net *net = dev_net(dev);
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
t->parms.proto = IPPROTO_IPV6;
dev_hold(dev);
rcu_assign_pointer(ip6n->tnls_wc[0], t);
return 0;
}
static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
u8 proto;
if (!data || !data[IFLA_IPTUN_PROTO])
return 0;
proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
if (proto != IPPROTO_IPV6 &&
proto != IPPROTO_IPIP &&
proto != 0)
return -EINVAL;
return 0;
}
static void ip6_tnl_netlink_parms(struct nlattr *data[],
struct __ip6_tnl_parm *parms)
{
memset(parms, 0, sizeof(*parms));
if (!data)
return;
if (data[IFLA_IPTUN_LINK])
parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]);
if (data[IFLA_IPTUN_LOCAL])
parms->laddr = nla_get_in6_addr(data[IFLA_IPTUN_LOCAL]);
if (data[IFLA_IPTUN_REMOTE])
parms->raddr = nla_get_in6_addr(data[IFLA_IPTUN_REMOTE]);
if (data[IFLA_IPTUN_TTL])
parms->hop_limit = nla_get_u8(data[IFLA_IPTUN_TTL]);
if (data[IFLA_IPTUN_ENCAP_LIMIT])
parms->encap_limit = nla_get_u8(data[IFLA_IPTUN_ENCAP_LIMIT]);
if (data[IFLA_IPTUN_FLOWINFO])
parms->flowinfo = nla_get_be32(data[IFLA_IPTUN_FLOWINFO]);
if (data[IFLA_IPTUN_FLAGS])
parms->flags = nla_get_u32(data[IFLA_IPTUN_FLAGS]);
if (data[IFLA_IPTUN_PROTO])
parms->proto = nla_get_u8(data[IFLA_IPTUN_PROTO]);
if (data[IFLA_IPTUN_COLLECT_METADATA])
parms->collect_md = true;
if (data[IFLA_IPTUN_FWMARK])
parms->fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]);
}
static bool ip6_tnl_netlink_encap_parms(struct nlattr *data[],
struct ip_tunnel_encap *ipencap)
{
bool ret = false;
memset(ipencap, 0, sizeof(*ipencap));
if (!data)
return ret;
if (data[IFLA_IPTUN_ENCAP_TYPE]) {
ret = true;
ipencap->type = nla_get_u16(data[IFLA_IPTUN_ENCAP_TYPE]);
}
if (data[IFLA_IPTUN_ENCAP_FLAGS]) {
ret = true;
ipencap->flags = nla_get_u16(data[IFLA_IPTUN_ENCAP_FLAGS]);
}
if (data[IFLA_IPTUN_ENCAP_SPORT]) {
ret = true;
ipencap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]);
}
if (data[IFLA_IPTUN_ENCAP_DPORT]) {
ret = true;
ipencap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]);
}
return ret;
}
static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
struct nlattr *tb[], struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct net *net = dev_net(dev);
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
struct ip_tunnel_encap ipencap;
struct ip6_tnl *nt, *t;
int err;
nt = netdev_priv(dev);
if (ip6_tnl_netlink_encap_parms(data, &ipencap)) {
err = ip6_tnl_encap_setup(nt, &ipencap);
if (err < 0)
return err;
}
ip6_tnl_netlink_parms(data, &nt->parms);
if (nt->parms.collect_md) {
if (rtnl_dereference(ip6n->collect_md_tun))
return -EEXIST;
} else {
t = ip6_tnl_locate(net, &nt->parms, 0);
if (!IS_ERR(t))
return -EEXIST;
}
err = ip6_tnl_create2(dev);
if (!err && tb[IFLA_MTU])
ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU]));
return err;
}
static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[],
struct nlattr *data[],
struct netlink_ext_ack *extack)
{
struct ip6_tnl *t = netdev_priv(dev);
struct __ip6_tnl_parm p;
struct net *net = t->net;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
struct ip_tunnel_encap ipencap;
if (dev == ip6n->fb_tnl_dev)
return -EINVAL;
if (ip6_tnl_netlink_encap_parms(data, &ipencap)) {
int err = ip6_tnl_encap_setup(t, &ipencap);
if (err < 0)
return err;
}
ip6_tnl_netlink_parms(data, &p);
if (p.collect_md)
return -EINVAL;
t = ip6_tnl_locate(net, &p, 0);
if (!IS_ERR(t)) {
if (t->dev != dev)
return -EEXIST;
} else
t = netdev_priv(dev);
return ip6_tnl_update(t, &p);
}
static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head)
{
struct net *net = dev_net(dev);
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
if (dev != ip6n->fb_tnl_dev)
unregister_netdevice_queue(dev, head);
}
static size_t ip6_tnl_get_size(const struct net_device *dev)
{
return
/* IFLA_IPTUN_LINK */
nla_total_size(4) +
/* IFLA_IPTUN_LOCAL */
nla_total_size(sizeof(struct in6_addr)) +
/* IFLA_IPTUN_REMOTE */
nla_total_size(sizeof(struct in6_addr)) +
/* IFLA_IPTUN_TTL */
nla_total_size(1) +
/* IFLA_IPTUN_ENCAP_LIMIT */
nla_total_size(1) +
/* IFLA_IPTUN_FLOWINFO */
nla_total_size(4) +
/* IFLA_IPTUN_FLAGS */
nla_total_size(4) +
/* IFLA_IPTUN_PROTO */
nla_total_size(1) +
/* IFLA_IPTUN_ENCAP_TYPE */
nla_total_size(2) +
/* IFLA_IPTUN_ENCAP_FLAGS */
nla_total_size(2) +
/* IFLA_IPTUN_ENCAP_SPORT */
nla_total_size(2) +
/* IFLA_IPTUN_ENCAP_DPORT */
nla_total_size(2) +
/* IFLA_IPTUN_COLLECT_METADATA */
nla_total_size(0) +
/* IFLA_IPTUN_FWMARK */
nla_total_size(4) +
0;
}
static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
struct ip6_tnl *tunnel = netdev_priv(dev);
struct __ip6_tnl_parm *parm = &tunnel->parms;
if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) ||
nla_put_in6_addr(skb, IFLA_IPTUN_LOCAL, &parm->laddr) ||
nla_put_in6_addr(skb, IFLA_IPTUN_REMOTE, &parm->raddr) ||
nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) ||
nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) ||
nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) ||
nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags) ||
nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto) ||
nla_put_u32(skb, IFLA_IPTUN_FWMARK, parm->fwmark))
goto nla_put_failure;
if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, tunnel->encap.type) ||
nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT, tunnel->encap.sport) ||
nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT, tunnel->encap.dport) ||
nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS, tunnel->encap.flags))
goto nla_put_failure;
if (parm->collect_md)
if (nla_put_flag(skb, IFLA_IPTUN_COLLECT_METADATA))
goto nla_put_failure;
return 0;
nla_put_failure:
return -EMSGSIZE;
}
struct net *ip6_tnl_get_link_net(const struct net_device *dev)
{
struct ip6_tnl *tunnel = netdev_priv(dev);
return tunnel->net;
}
EXPORT_SYMBOL(ip6_tnl_get_link_net);
static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = {
[IFLA_IPTUN_LINK] = { .type = NLA_U32 },
[IFLA_IPTUN_LOCAL] = { .len = sizeof(struct in6_addr) },
[IFLA_IPTUN_REMOTE] = { .len = sizeof(struct in6_addr) },
[IFLA_IPTUN_TTL] = { .type = NLA_U8 },
[IFLA_IPTUN_ENCAP_LIMIT] = { .type = NLA_U8 },
[IFLA_IPTUN_FLOWINFO] = { .type = NLA_U32 },
[IFLA_IPTUN_FLAGS] = { .type = NLA_U32 },
[IFLA_IPTUN_PROTO] = { .type = NLA_U8 },
[IFLA_IPTUN_ENCAP_TYPE] = { .type = NLA_U16 },
[IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 },
[IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 },
[IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 },
[IFLA_IPTUN_COLLECT_METADATA] = { .type = NLA_FLAG },
[IFLA_IPTUN_FWMARK] = { .type = NLA_U32 },
};
static struct rtnl_link_ops ip6_link_ops __read_mostly = {
.kind = "ip6tnl",
.maxtype = IFLA_IPTUN_MAX,
.policy = ip6_tnl_policy,
.priv_size = sizeof(struct ip6_tnl),
.setup = ip6_tnl_dev_setup,
.validate = ip6_tnl_validate,
.newlink = ip6_tnl_newlink,
.changelink = ip6_tnl_changelink,
.dellink = ip6_tnl_dellink,
.get_size = ip6_tnl_get_size,
.fill_info = ip6_tnl_fill_info,
.get_link_net = ip6_tnl_get_link_net,
};
static struct xfrm6_tunnel ip4ip6_handler __read_mostly = {
.handler = ip4ip6_rcv,
.err_handler = ip4ip6_err,
.priority = 1,
};
static struct xfrm6_tunnel ip6ip6_handler __read_mostly = {
.handler = ip6ip6_rcv,
.err_handler = ip6ip6_err,
[INET]: Introduce tunnel4/tunnel6 Basically this patch moves the generic tunnel protocol stuff out of xfrm4_tunnel/xfrm6_tunnel and moves it into the new files of tunnel4.c and tunnel6 respectively. The reason for this is that the problem that Hugo uncovered is only the tip of the iceberg. The real problem is that when we removed the dependency of ipip on xfrm4_tunnel we didn't really consider the module case at all. For instance, as it is it's possible to build both ipip and xfrm4_tunnel as modules and if the latter is loaded then ipip simply won't load. After considering the alternatives I've decided that the best way out of this is to restore the dependency of ipip on the non-xfrm-specific part of xfrm4_tunnel. This is acceptable IMHO because the intention of the removal was really to be able to use ipip without the xfrm subsystem. This is still preserved by this patch. So now both ipip/xfrm4_tunnel depend on the new tunnel4.c which handles the arbitration between the two. The order of processing is determined by a simple integer which ensures that ipip gets processed before xfrm4_tunnel. The situation for ICMP handling is a little bit more complicated since we may not have enough information to determine who it's for. It's not a big deal at the moment since the xfrm ICMP handlers are basically no-ops. In future we can deal with this when we look at ICMP caching in general. The user-visible change to this is the removal of the TUNNEL Kconfig prompts. This makes sense because it can only be used through IPCOMP as it stands. The addition of the new modules shouldn't introduce any problems since module dependency will cause them to be loaded. Oh and I also turned some unnecessary pskb's in IPv6 related to this patch to skb's. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2006-03-28 16:12:13 +07:00
.priority = 1,
};
static void __net_exit ip6_tnl_destroy_tunnels(struct net *net, struct list_head *list)
{
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
struct net_device *dev, *aux;
int h;
struct ip6_tnl *t;
for_each_netdev_safe(net, dev, aux)
if (dev->rtnl_link_ops == &ip6_link_ops)
unregister_netdevice_queue(dev, list);
for (h = 0; h < IP6_TUNNEL_HASH_SIZE; h++) {
t = rtnl_dereference(ip6n->tnls_r_l[h]);
while (t) {
/* If dev is in the same netns, it has already
* been added to the list by the previous loop.
*/
if (!net_eq(dev_net(t->dev), net))
unregister_netdevice_queue(t->dev, list);
t = rtnl_dereference(t->next);
}
}
}
static int __net_init ip6_tnl_init_net(struct net *net)
{
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
struct ip6_tnl *t = NULL;
int err;
ip6n->tnls[0] = ip6n->tnls_wc;
ip6n->tnls[1] = ip6n->tnls_r_l;
if (!net_has_fallback_tunnels(net))
return 0;
err = -ENOMEM;
ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6tnl0",
NET_NAME_UNKNOWN, ip6_tnl_dev_setup);
if (!ip6n->fb_tnl_dev)
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 08:26:26 +07:00
dev_net_set(ip6n->fb_tnl_dev, net);
ip6n->fb_tnl_dev->rtnl_link_ops = &ip6_link_ops;
/* FB netdevice is special: we have one, and only one per netns.
* Allowing to move it to another netns is clearly unsafe.
*/
ip6n->fb_tnl_dev->features |= NETIF_F_NETNS_LOCAL;
err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
if (err < 0)
goto err_register;
err = register_netdev(ip6n->fb_tnl_dev);
if (err < 0)
goto err_register;
t = netdev_priv(ip6n->fb_tnl_dev);
strcpy(t->parms.name, ip6n->fb_tnl_dev->name);
return 0;
err_register:
net: Fix inconsistent teardown and release of private netdev state. Network devices can allocate reasources and private memory using netdev_ops->ndo_init(). However, the release of these resources can occur in one of two different places. Either netdev_ops->ndo_uninit() or netdev->destructor(). The decision of which operation frees the resources depends upon whether it is necessary for all netdev refs to be released before it is safe to perform the freeing. netdev_ops->ndo_uninit() presumably can occur right after the NETDEV_UNREGISTER notifier completes and the unicast and multicast address lists are flushed. netdev->destructor(), on the other hand, does not run until the netdev references all go away. Further complicating the situation is that netdev->destructor() almost universally does also a free_netdev(). This creates a problem for the logic in register_netdevice(). Because all callers of register_netdevice() manage the freeing of the netdev, and invoke free_netdev(dev) if register_netdevice() fails. If netdev_ops->ndo_init() succeeds, but something else fails inside of register_netdevice(), it does call ndo_ops->ndo_uninit(). But it is not able to invoke netdev->destructor(). This is because netdev->destructor() will do a free_netdev() and then the caller of register_netdevice() will do the same. However, this means that the resources that would normally be released by netdev->destructor() will not be. Over the years drivers have added local hacks to deal with this, by invoking their destructor parts by hand when register_netdevice() fails. Many drivers do not try to deal with this, and instead we have leaks. Let's close this hole by formalizing the distinction between what private things need to be freed up by netdev->destructor() and whether the driver needs unregister_netdevice() to perform the free_netdev(). netdev->priv_destructor() performs all actions to free up the private resources that used to be freed by netdev->destructor(), except for free_netdev(). netdev->needs_free_netdev is a boolean that indicates whether free_netdev() should be done at the end of unregister_netdevice(). Now, register_netdevice() can sanely release all resources after ndo_ops->ndo_init() succeeds, by invoking both ndo_ops->ndo_uninit() and netdev->priv_destructor(). And at the end of unregister_netdevice(), we invoke netdev->priv_destructor() and optionally call free_netdev(). Signed-off-by: David S. Miller <davem@davemloft.net>
2017-05-08 23:52:56 +07:00
free_netdev(ip6n->fb_tnl_dev);
err_alloc_dev:
return err;
}
static void __net_exit ip6_tnl_exit_batch_net(struct list_head *net_list)
{
struct net *net;
LIST_HEAD(list);
rtnl_lock();
list_for_each_entry(net, net_list, exit_list)
ip6_tnl_destroy_tunnels(net, &list);
unregister_netdevice_many(&list);
rtnl_unlock();
}
static struct pernet_operations ip6_tnl_net_ops = {
.init = ip6_tnl_init_net,
.exit_batch = ip6_tnl_exit_batch_net,
.id = &ip6_tnl_net_id,
.size = sizeof(struct ip6_tnl_net),
.async = true,
};
/**
* ip6_tunnel_init - register protocol and reserve needed resources
*
* Return: 0 on success
**/
static int __init ip6_tunnel_init(void)
{
int err;
ip6_tunnel: do not allow loading ip6_tunnel if ipv6 is disabled in cmdline If ipv6 has been disabled from cmdline since kernel started, it makes no sense to allow users to create any ip6 tunnel. Otherwise, it could some potential problem. Jianlin found a kernel crash caused by this in ip6_gre when he set ipv6.disable=1 in grub: [ 209.588865] Unable to handle kernel paging request for data at address 0x00000080 [ 209.588872] Faulting instruction address: 0xc000000000a3aa6c [ 209.588879] Oops: Kernel access of bad area, sig: 11 [#1] [ 209.589062] NIP [c000000000a3aa6c] fib_rules_lookup+0x4c/0x260 [ 209.589071] LR [c000000000b9ad90] fib6_rule_lookup+0x50/0xb0 [ 209.589076] Call Trace: [ 209.589097] fib6_rule_lookup+0x50/0xb0 [ 209.589106] rt6_lookup+0xc4/0x110 [ 209.589116] ip6gre_tnl_link_config+0x214/0x2f0 [ip6_gre] [ 209.589125] ip6gre_newlink+0x138/0x3a0 [ip6_gre] [ 209.589134] rtnl_newlink+0x798/0xb80 [ 209.589142] rtnetlink_rcv_msg+0xec/0x390 [ 209.589151] netlink_rcv_skb+0x138/0x150 [ 209.589159] rtnetlink_rcv+0x48/0x70 [ 209.589169] netlink_unicast+0x538/0x640 [ 209.589175] netlink_sendmsg+0x40c/0x480 [ 209.589184] ___sys_sendmsg+0x384/0x4e0 [ 209.589194] SyS_sendmsg+0xd4/0x140 [ 209.589201] SyS_socketcall+0x3e0/0x4f0 [ 209.589209] system_call+0x38/0xe0 This patch is to return -EOPNOTSUPP in ip6_tunnel_init if ipv6 has been disabled from cmdline. Reported-by: Jianlin Shi <jishi@redhat.com> Signed-off-by: Xin Long <lucien.xin@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-15 14:58:33 +07:00
if (!ipv6_mod_enabled())
return -EOPNOTSUPP;
err = register_pernet_device(&ip6_tnl_net_ops);
if (err < 0)
goto out_pernet;
err = xfrm6_tunnel_register(&ip4ip6_handler, AF_INET);
if (err < 0) {
pr_err("%s: can't register ip4ip6\n", __func__);
goto out_ip4ip6;
}
err = xfrm6_tunnel_register(&ip6ip6_handler, AF_INET6);
if (err < 0) {
pr_err("%s: can't register ip6ip6\n", __func__);
goto out_ip6ip6;
}
err = rtnl_link_register(&ip6_link_ops);
if (err < 0)
goto rtnl_link_failed;
return 0;
rtnl_link_failed:
xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6);
out_ip6ip6:
xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET);
out_ip4ip6:
unregister_pernet_device(&ip6_tnl_net_ops);
out_pernet:
return err;
}
/**
* ip6_tunnel_cleanup - free resources and unregister protocol
**/
static void __exit ip6_tunnel_cleanup(void)
{
rtnl_link_unregister(&ip6_link_ops);
if (xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET))
pr_info("%s: can't deregister ip4ip6\n", __func__);
if (xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6))
pr_info("%s: can't deregister ip6ip6\n", __func__);
unregister_pernet_device(&ip6_tnl_net_ops);
}
module_init(ip6_tunnel_init);
module_exit(ip6_tunnel_cleanup);