WSL2-Linux-Kernel/net/ipv6/ndisc.c

1728 строки
42 KiB
C
Исходник Обычный вид История

/*
* Neighbour Discovery for IPv6
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <roque@di.fc.ul.pt>
* Mike Shaver <shaver@ingenia.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
/*
* Changes:
*
* Alexey I. Froloff : RFC6106 (DNSSL) support
* Pierre Ynard : export userland ND options
* through netlink (RDNSS support)
* Lars Fenneberg : fixed MTU setting on receipt
* of an RA.
* Janos Farkas : kmalloc failure checks
* Alexey Kuznetsov : state machine reworked
* and moved to net/core.
* Pekka Savola : RFC2461 validation
* YOSHIFUJI Hideaki @USAGI : Verify ND options properly
*/
#define pr_fmt(fmt) "ICMPv6: " fmt
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/sched.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/route.h>
#include <linux/init.h>
#include <linux/rcupdate.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 11:04:11 +03:00
#include <linux/slab.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <linux/if_addr.h>
#include <linux/if_arp.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/jhash.h>
#include <net/sock.h>
#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/protocol.h>
#include <net/ndisc.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/icmp.h>
#include <net/netlink.h>
#include <linux/rtnetlink.h>
#include <net/flow.h>
#include <net/ip6_checksum.h>
#include <net/inet_common.h>
#include <linux/proc_fs.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>
/* Set to 3 to get tracing... */
#define ND_DEBUG 1
#define ND_PRINTK(val, level, fmt, ...) \
do { \
if (val <= ND_DEBUG) \
net_##level##_ratelimited(fmt, ##__VA_ARGS__); \
} while (0)
static u32 ndisc_hash(const void *pkey,
const struct net_device *dev,
__u32 *hash_rnd);
static int ndisc_constructor(struct neighbour *neigh);
static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb);
static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
static int pndisc_constructor(struct pneigh_entry *n);
static void pndisc_destructor(struct pneigh_entry *n);
static void pndisc_redo(struct sk_buff *skb);
static const struct neigh_ops ndisc_generic_ops = {
.family = AF_INET6,
.solicit = ndisc_solicit,
.error_report = ndisc_error_report,
.output = neigh_resolve_output,
.connected_output = neigh_connected_output,
};
static const struct neigh_ops ndisc_hh_ops = {
.family = AF_INET6,
.solicit = ndisc_solicit,
.error_report = ndisc_error_report,
.output = neigh_resolve_output,
.connected_output = neigh_resolve_output,
};
static const struct neigh_ops ndisc_direct_ops = {
.family = AF_INET6,
.output = neigh_direct_output,
.connected_output = neigh_direct_output,
};
struct neigh_table nd_tbl = {
.family = AF_INET6,
.key_len = sizeof(struct in6_addr),
.hash = ndisc_hash,
.constructor = ndisc_constructor,
.pconstructor = pndisc_constructor,
.pdestructor = pndisc_destructor,
.proxy_redo = pndisc_redo,
.id = "ndisc_cache",
.parms = {
.tbl = &nd_tbl,
.base_reachable_time = ND_REACHABLE_TIME,
.retrans_time = ND_RETRANS_TIMER,
.gc_staletime = 60 * HZ,
.reachable_time = ND_REACHABLE_TIME,
.delay_probe_time = 5 * HZ,
neigh: new unresolved queue limits Le mercredi 09 novembre 2011 à 16:21 -0500, David Miller a écrit : > From: David Miller <davem@davemloft.net> > Date: Wed, 09 Nov 2011 16:16:44 -0500 (EST) > > > From: Eric Dumazet <eric.dumazet@gmail.com> > > Date: Wed, 09 Nov 2011 12:14:09 +0100 > > > >> unres_qlen is the number of frames we are able to queue per unresolved > >> neighbour. Its default value (3) was never changed and is responsible > >> for strange drops, especially if IP fragments are used, or multiple > >> sessions start in parallel. Even a single tcp flow can hit this limit. > > ... > > > > Ok, I've applied this, let's see what happens :-) > > Early answer, build fails. > > Please test build this patch with DECNET enabled and resubmit. The > decnet neigh layer still refers to the removed ->queue_len member. > > Thanks. Ouch, this was fixed on one machine yesterday, but not the other one I used this morning, sorry. [PATCH V5 net-next] neigh: new unresolved queue limits unres_qlen is the number of frames we are able to queue per unresolved neighbour. Its default value (3) was never changed and is responsible for strange drops, especially if IP fragments are used, or multiple sessions start in parallel. Even a single tcp flow can hit this limit. $ arp -d 192.168.20.108 ; ping -c 2 -s 8000 192.168.20.108 PING 192.168.20.108 (192.168.20.108) 8000(8028) bytes of data. 8008 bytes from 192.168.20.108: icmp_seq=2 ttl=64 time=0.322 ms Signed-off-by: David S. Miller <davem@davemloft.net>
2011-11-09 16:07:14 +04:00
.queue_len_bytes = 64*1024,
.ucast_probes = 3,
.mcast_probes = 3,
.anycast_delay = 1 * HZ,
.proxy_delay = (8 * HZ) / 10,
.proxy_qlen = 64,
},
.gc_interval = 30 * HZ,
.gc_thresh1 = 128,
.gc_thresh2 = 512,
.gc_thresh3 = 1024,
};
static inline int ndisc_opt_addr_space(struct net_device *dev)
{
return NDISC_OPT_SPACE(dev->addr_len + ndisc_addr_option_pad(dev->type));
}
static u8 *ndisc_fill_addr_option(u8 *opt, int type, void *data,
struct net_device *dev)
{
int pad = ndisc_addr_option_pad(dev->type);
int data_len = dev->addr_len;
int space = NDISC_OPT_SPACE(data_len + pad);
opt[0] = type;
opt[1] = space>>3;
memset(opt + 2, 0, pad);
opt += pad;
space -= pad;
memcpy(opt+2, data, data_len);
data_len += 2;
opt += data_len;
if ((space -= data_len) > 0)
memset(opt, 0, space);
return opt + space;
}
static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
struct nd_opt_hdr *end)
{
int type;
if (!cur || !end || cur >= end)
return NULL;
type = cur->nd_opt_type;
do {
cur = ((void *)cur) + (cur->nd_opt_len << 3);
} while(cur < end && cur->nd_opt_type != type);
return cur <= end && cur->nd_opt_type == type ? cur : NULL;
}
static inline int ndisc_is_useropt(struct nd_opt_hdr *opt)
{
return opt->nd_opt_type == ND_OPT_RDNSS ||
opt->nd_opt_type == ND_OPT_DNSSL;
}
static struct nd_opt_hdr *ndisc_next_useropt(struct nd_opt_hdr *cur,
struct nd_opt_hdr *end)
{
if (!cur || !end || cur >= end)
return NULL;
do {
cur = ((void *)cur) + (cur->nd_opt_len << 3);
} while(cur < end && !ndisc_is_useropt(cur));
return cur <= end && ndisc_is_useropt(cur) ? cur : NULL;
}
struct ndisc_options *ndisc_parse_options(u8 *opt, int opt_len,
struct ndisc_options *ndopts)
{
struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt;
if (!nd_opt || opt_len < 0 || !ndopts)
return NULL;
memset(ndopts, 0, sizeof(*ndopts));
while (opt_len) {
int l;
if (opt_len < sizeof(struct nd_opt_hdr))
return NULL;
l = nd_opt->nd_opt_len << 3;
if (opt_len < l || l == 0)
return NULL;
switch (nd_opt->nd_opt_type) {
case ND_OPT_SOURCE_LL_ADDR:
case ND_OPT_TARGET_LL_ADDR:
case ND_OPT_MTU:
case ND_OPT_REDIRECT_HDR:
if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) {
ND_PRINTK(2, warn,
"%s: duplicated ND6 option found: type=%d\n",
__func__, nd_opt->nd_opt_type);
} else {
ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt;
}
break;
case ND_OPT_PREFIX_INFO:
ndopts->nd_opts_pi_end = nd_opt;
if (!ndopts->nd_opt_array[nd_opt->nd_opt_type])
ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt;
break;
#ifdef CONFIG_IPV6_ROUTE_INFO
case ND_OPT_ROUTE_INFO:
ndopts->nd_opts_ri_end = nd_opt;
if (!ndopts->nd_opts_ri)
ndopts->nd_opts_ri = nd_opt;
break;
#endif
default:
if (ndisc_is_useropt(nd_opt)) {
ndopts->nd_useropts_end = nd_opt;
if (!ndopts->nd_useropts)
ndopts->nd_useropts = nd_opt;
} else {
/*
* Unknown options must be silently ignored,
* to accommodate future extension to the
* protocol.
*/
ND_PRINTK(2, notice,
"%s: ignored unsupported option; type=%d, len=%d\n",
__func__,
nd_opt->nd_opt_type,
nd_opt->nd_opt_len);
}
}
opt_len -= l;
nd_opt = ((void *)nd_opt) + l;
}
return ndopts;
}
int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir)
{
switch (dev->type) {
case ARPHRD_ETHER:
case ARPHRD_IEEE802: /* Not sure. Check it later. --ANK */
case ARPHRD_FDDI:
ipv6_eth_mc_map(addr, buf);
return 0;
case ARPHRD_ARCNET:
ipv6_arcnet_mc_map(addr, buf);
return 0;
case ARPHRD_INFINIBAND:
ipv6_ib_mc_map(addr, dev->broadcast, buf);
return 0;
case ARPHRD_IPGRE:
return ipv6_ipgre_mc_map(addr, dev->broadcast, buf);
default:
if (dir) {
memcpy(buf, dev->broadcast, dev->addr_len);
return 0;
}
}
return -EINVAL;
}
EXPORT_SYMBOL(ndisc_mc_map);
static u32 ndisc_hash(const void *pkey,
const struct net_device *dev,
__u32 *hash_rnd)
{
return ndisc_hashfn(pkey, dev, hash_rnd);
}
static int ndisc_constructor(struct neighbour *neigh)
{
struct in6_addr *addr = (struct in6_addr*)&neigh->primary_key;
struct net_device *dev = neigh->dev;
struct inet6_dev *in6_dev;
struct neigh_parms *parms;
bool is_multicast = ipv6_addr_is_multicast(addr);
in6_dev = in6_dev_get(dev);
if (in6_dev == NULL) {
return -EINVAL;
}
parms = in6_dev->nd_parms;
__neigh_parms_put(neigh->parms);
neigh->parms = neigh_parms_clone(parms);
neigh->type = is_multicast ? RTN_MULTICAST : RTN_UNICAST;
if (!dev->header_ops) {
neigh->nud_state = NUD_NOARP;
neigh->ops = &ndisc_direct_ops;
neigh->output = neigh_direct_output;
} else {
if (is_multicast) {
neigh->nud_state = NUD_NOARP;
ndisc_mc_map(addr, neigh->ha, dev, 1);
} else if (dev->flags&(IFF_NOARP|IFF_LOOPBACK)) {
neigh->nud_state = NUD_NOARP;
memcpy(neigh->ha, dev->dev_addr, dev->addr_len);
if (dev->flags&IFF_LOOPBACK)
neigh->type = RTN_LOCAL;
} else if (dev->flags&IFF_POINTOPOINT) {
neigh->nud_state = NUD_NOARP;
memcpy(neigh->ha, dev->broadcast, dev->addr_len);
}
if (dev->header_ops->cache)
neigh->ops = &ndisc_hh_ops;
else
neigh->ops = &ndisc_generic_ops;
if (neigh->nud_state&NUD_VALID)
neigh->output = neigh->ops->connected_output;
else
neigh->output = neigh->ops->output;
}
in6_dev_put(in6_dev);
return 0;
}
static int pndisc_constructor(struct pneigh_entry *n)
{
struct in6_addr *addr = (struct in6_addr*)&n->key;
struct in6_addr maddr;
struct net_device *dev = n->dev;
if (dev == NULL || __in6_dev_get(dev) == NULL)
return -EINVAL;
addrconf_addr_solict_mult(addr, &maddr);
ipv6_dev_mc_inc(dev, &maddr);
return 0;
}
static void pndisc_destructor(struct pneigh_entry *n)
{
struct in6_addr *addr = (struct in6_addr*)&n->key;
struct in6_addr maddr;
struct net_device *dev = n->dev;
if (dev == NULL || __in6_dev_get(dev) == NULL)
return;
addrconf_addr_solict_mult(addr, &maddr);
ipv6_dev_mc_dec(dev, &maddr);
}
static struct sk_buff *ndisc_build_skb(struct net_device *dev,
const struct in6_addr *daddr,
const struct in6_addr *saddr,
struct icmp6hdr *icmp6h,
const struct in6_addr *target,
int llinfo)
{
struct net *net = dev_net(dev);
struct sock *sk = net->ipv6.ndisc_sk;
struct sk_buff *skb;
struct icmp6hdr *hdr;
int hlen = LL_RESERVED_SPACE(dev);
int tlen = dev->needed_tailroom;
int len;
int err;
u8 *opt;
if (!dev->addr_len)
llinfo = 0;
len = sizeof(struct icmp6hdr) + (target ? sizeof(*target) : 0);
if (llinfo)
len += ndisc_opt_addr_space(dev);
skb = sock_alloc_send_skb(sk,
ndisc: Remove unused space at tail of skb for ndisc messages. (TAKE 3) Currently, the size of skb allocated for NDISC is MAX_HEADER + LL_RESERVED_SPACE(dev) + packet length + dev->needed_tailroom, but only LL_RESERVED_SPACE(dev) bytes is "reserved" for headers. As a result, the skb looks like this (after construction of the message): head data tail end +--------------------------------------------------------------+ + | | | | +--------------------------------------------------------------+ |<-hlen---->|<---ipv6 packet------>|<--tlen-->|<--MAX_HEADER-->| =LL_ = dev RESERVED_ ->needed_ SPACE(dev) tailroom As the name implies, "MAX_HEADER" is used for headers, and should be "reserved" in prior to packet construction. Or, if some space is really required at the tail of ther skb, it should be explicitly documented. We have several option after construction of NDISC message: Option 1: head data tail end +---------------------------------------------+ + | | | +---------------------------------------------+ |<-hlen---->|<---ipv6 packet------>|<--tlen-->| =LL_ = dev RESERVED_ ->needed_ SPACE(dev) tailroom Option 2: head data tail end +--------------------------------------------------+ + | | | +--------------------------------------------------+ |<--MAX_HEADER-->|<---ipv6 packet------>|<--tlen-->| = dev ->needed_ tailroom Option 3: head data tail end +--------------------------------------------------------------+ + | | | | +--------------------------------------------------------------+ |<--MAX_HEADER-->|<-hlen---->|<---ipv6 packet------>|<--tlen-->| =LL_ = dev RESERVED_ ->needed_ SPACE(dev) tailroom Our tunnel drivers try expanding headroom and the space for tunnel encapsulation was not a mandatory space -- so we are not seeing bugs here --, but just for optimization for performance critial situations. Since NDISC messages are not performance critical unlike TCP, and as we know outgoing device, LL_RESERVED_SPACE(dev) should be just enough for the device in most (if not all) cases: LL_RESERVED_SPACE(dev) <= LL_MAX_HEADER <= MAX_HEADER Note that LL_RESERVED_SPACE(dev) is also enough for NDISC over SIT (e.g., ISATAP). So, I think Option 1 is just fine here. Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 07:58:04 +04:00
(sizeof(struct ipv6hdr) +
len + hlen + tlen),
1, &err);
if (!skb) {
ND_PRINTK(0, err, "ND: %s failed to allocate an skb, err=%d\n",
__func__, err);
return NULL;
}
skb_reserve(skb, hlen);
ip6_nd_hdr(sk, skb, dev, saddr, daddr, IPPROTO_ICMPV6, len);
skb->transport_header = skb->tail;
skb_put(skb, len);
hdr = (struct icmp6hdr *)skb_transport_header(skb);
memcpy(hdr, icmp6h, sizeof(*hdr));
opt = skb_transport_header(skb) + sizeof(struct icmp6hdr);
if (target) {
*(struct in6_addr *)opt = *target;
opt += sizeof(*target);
}
if (llinfo)
ndisc_fill_addr_option(opt, llinfo, dev->dev_addr, dev);
hdr->icmp6_cksum = csum_ipv6_magic(saddr, daddr, len,
IPPROTO_ICMPV6,
csum_partial(hdr,
len, 0));
return skb;
}
static void ndisc_send_skb(struct sk_buff *skb, struct net_device *dev,
const struct in6_addr *daddr,
const struct in6_addr *saddr,
struct icmp6hdr *icmp6h)
{
struct flowi6 fl6;
struct dst_entry *dst;
struct net *net = dev_net(dev);
struct sock *sk = net->ipv6.ndisc_sk;
struct inet6_dev *idev;
int err;
u8 type;
type = icmp6h->icmp6_type;
icmpv6_flow_init(sk, &fl6, type, saddr, daddr, dev->ifindex);
dst = icmp6_dst_alloc(dev, &fl6);
if (IS_ERR(dst)) {
kfree_skb(skb);
return;
}
skb_dst_set(skb, dst);
rcu_read_lock();
idev = __in6_dev_get(dst->dev);
IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len);
err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, skb, NULL, dst->dev,
dst_output);
if (!err) {
ICMP6MSGOUT_INC_STATS(net, idev, type);
ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
}
rcu_read_unlock();
}
/*
* Send a Neighbour Discover packet
*/
static void __ndisc_send(struct net_device *dev,
const struct in6_addr *daddr,
const struct in6_addr *saddr,
struct icmp6hdr *icmp6h, const struct in6_addr *target,
int llinfo)
{
struct sk_buff *skb;
skb = ndisc_build_skb(dev, daddr, saddr, icmp6h, target, llinfo);
if (!skb)
return;
ndisc_send_skb(skb, dev, daddr, saddr, icmp6h);
}
static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh,
const struct in6_addr *daddr,
const struct in6_addr *solicited_addr,
bool router, bool solicited, bool override, bool inc_opt)
{
struct in6_addr tmpaddr;
struct inet6_ifaddr *ifp;
const struct in6_addr *src_addr;
struct icmp6hdr icmp6h = {
.icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT,
};
/* for anycast or proxy, solicited_addr != src_addr */
ifp = ipv6_get_ifaddr(dev_net(dev), solicited_addr, dev, 1);
if (ifp) {
src_addr = solicited_addr;
if (ifp->flags & IFA_F_OPTIMISTIC)
override = 0;
inc_opt |= ifp->idev->cnf.force_tllao;
in6_ifa_put(ifp);
} else {
if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr,
inet6_sk(dev_net(dev)->ipv6.ndisc_sk)->srcprefs,
&tmpaddr))
return;
src_addr = &tmpaddr;
}
icmp6h.icmp6_router = router;
icmp6h.icmp6_solicited = solicited;
icmp6h.icmp6_override = override;
__ndisc_send(dev, daddr, src_addr, &icmp6h, solicited_addr,
inc_opt ? ND_OPT_TARGET_LL_ADDR : 0);
}
static void ndisc_send_unsol_na(struct net_device *dev)
{
struct inet6_dev *idev;
struct inet6_ifaddr *ifa;
idev = in6_dev_get(dev);
if (!idev)
return;
read_lock_bh(&idev->lock);
list_for_each_entry(ifa, &idev->addr_list, if_list) {
ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &ifa->addr,
/*router=*/ !!idev->cnf.forwarding,
/*solicited=*/ false, /*override=*/ true,
/*inc_opt=*/ true);
}
read_unlock_bh(&idev->lock);
in6_dev_put(idev);
}
void ndisc_send_ns(struct net_device *dev, struct neighbour *neigh,
const struct in6_addr *solicit,
const struct in6_addr *daddr, const struct in6_addr *saddr)
{
struct in6_addr addr_buf;
struct icmp6hdr icmp6h = {
.icmp6_type = NDISC_NEIGHBOUR_SOLICITATION,
};
if (saddr == NULL) {
if (ipv6_get_lladdr(dev, &addr_buf,
(IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)))
return;
saddr = &addr_buf;
}
__ndisc_send(dev, daddr, saddr, &icmp6h, solicit,
!ipv6_addr_any(saddr) ? ND_OPT_SOURCE_LL_ADDR : 0);
}
void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr,
const struct in6_addr *daddr)
{
struct icmp6hdr icmp6h = {
.icmp6_type = NDISC_ROUTER_SOLICITATION,
};
int send_sllao = dev->addr_len;
#ifdef CONFIG_IPV6_OPTIMISTIC_DAD
/*
* According to section 2.2 of RFC 4429, we must not
* send router solicitations with a sllao from
* optimistic addresses, but we may send the solicitation
* if we don't include the sllao. So here we check
* if our address is optimistic, and if so, we
* suppress the inclusion of the sllao.
*/
if (send_sllao) {
struct inet6_ifaddr *ifp = ipv6_get_ifaddr(dev_net(dev), saddr,
dev, 1);
if (ifp) {
if (ifp->flags & IFA_F_OPTIMISTIC) {
send_sllao = 0;
}
in6_ifa_put(ifp);
} else {
send_sllao = 0;
}
}
#endif
__ndisc_send(dev, daddr, saddr, &icmp6h, NULL,
send_sllao ? ND_OPT_SOURCE_LL_ADDR : 0);
}
static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb)
{
/*
* "The sender MUST return an ICMP
* destination unreachable"
*/
dst_link_failure(skb);
kfree_skb(skb);
}
/* Called with locked neigh: either read or both */
static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb)
{
struct in6_addr *saddr = NULL;
struct in6_addr mcaddr;
struct net_device *dev = neigh->dev;
struct in6_addr *target = (struct in6_addr *)&neigh->primary_key;
int probes = atomic_read(&neigh->probes);
if (skb && ipv6_chk_addr(dev_net(dev), &ipv6_hdr(skb)->saddr, dev, 1))
saddr = &ipv6_hdr(skb)->saddr;
if ((probes -= neigh->parms->ucast_probes) < 0) {
if (!(neigh->nud_state & NUD_VALID)) {
ND_PRINTK(1, dbg,
"%s: trying to ucast probe in NUD_INVALID: %pI6\n",
__func__, target);
}
ndisc_send_ns(dev, neigh, target, target, saddr);
} else if ((probes -= neigh->parms->app_probes) < 0) {
#ifdef CONFIG_ARPD
neigh_app_ns(neigh);
#endif
} else {
addrconf_addr_solict_mult(target, &mcaddr);
ndisc_send_ns(dev, NULL, target, &mcaddr, saddr);
}
}
static int pndisc_is_router(const void *pkey,
struct net_device *dev)
{
struct pneigh_entry *n;
int ret = -1;
read_lock_bh(&nd_tbl.lock);
n = __pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev);
if (n)
ret = !!(n->flags & NTF_ROUTER);
read_unlock_bh(&nd_tbl.lock);
return ret;
}
static void ndisc_recv_ns(struct sk_buff *skb)
{
struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
u8 *lladdr = NULL;
u32 ndoptlen = skb->tail - (skb->transport_header +
offsetof(struct nd_msg, opt));
struct ndisc_options ndopts;
struct net_device *dev = skb->dev;
struct inet6_ifaddr *ifp;
struct inet6_dev *idev = NULL;
struct neighbour *neigh;
int dad = ipv6_addr_any(saddr);
bool inc;
int is_router = -1;
if (skb->len < sizeof(struct nd_msg)) {
ND_PRINTK(2, warn, "NS: packet too short\n");
return;
}
if (ipv6_addr_is_multicast(&msg->target)) {
ND_PRINTK(2, warn, "NS: multicast target address\n");
return;
}
/*
* RFC2461 7.1.1:
* DAD has to be destined for solicited node multicast address.
*/
if (dad && !ipv6_addr_is_solict_mult(daddr)) {
ND_PRINTK(2, warn, "NS: bad DAD packet (wrong destination)\n");
return;
}
if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) {
ND_PRINTK(2, warn, "NS: invalid ND options\n");
return;
}
if (ndopts.nd_opts_src_lladdr) {
lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, dev);
if (!lladdr) {
ND_PRINTK(2, warn,
"NS: invalid link-layer address length\n");
return;
}
/* RFC2461 7.1.1:
* If the IP source address is the unspecified address,
* there MUST NOT be source link-layer address option
* in the message.
*/
if (dad) {
ND_PRINTK(2, warn,
"NS: bad DAD packet (link-layer address option)\n");
return;
}
}
inc = ipv6_addr_is_multicast(daddr);
ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1);
if (ifp) {
if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) {
if (dad) {
/*
* We are colliding with another node
* who is doing DAD
* so fail our DAD process
*/
addrconf_dad_failure(ifp);
return;
} else {
/*
* This is not a dad solicitation.
* If we are an optimistic node,
* we should respond.
* Otherwise, we should ignore it.
*/
if (!(ifp->flags & IFA_F_OPTIMISTIC))
goto out;
}
}
idev = ifp->idev;
} else {
struct net *net = dev_net(dev);
idev = in6_dev_get(dev);
if (!idev) {
/* XXX: count this drop? */
return;
}
if (ipv6_chk_acast_addr(net, dev, &msg->target) ||
(idev->cnf.forwarding &&
(net->ipv6.devconf_all->proxy_ndp || idev->cnf.proxy_ndp) &&
(is_router = pndisc_is_router(&msg->target, dev)) >= 0)) {
if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) &&
skb->pkt_type != PACKET_HOST &&
inc != 0 &&
idev->nd_parms->proxy_delay != 0) {
/*
* for anycast or proxy,
* sender should delay its response
* by a random time between 0 and
* MAX_ANYCAST_DELAY_TIME seconds.
* (RFC2461) -- yoshfuji
*/
struct sk_buff *n = skb_clone(skb, GFP_ATOMIC);
if (n)
pneigh_enqueue(&nd_tbl, idev->nd_parms, n);
goto out;
}
} else
goto out;
}
if (is_router < 0)
is_router = idev->cnf.forwarding;
if (dad) {
ndisc_send_na(dev, NULL, &in6addr_linklocal_allnodes, &msg->target,
!!is_router, false, (ifp != NULL), true);
goto out;
}
if (inc)
NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_mcast);
else
NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_ucast);
/*
* update / create cache entry
* for the source address
*/
neigh = __neigh_lookup(&nd_tbl, saddr, dev,
!inc || lladdr || !dev->addr_len);
if (neigh)
neigh_update(neigh, lladdr, NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE);
if (neigh || !dev->header_ops) {
ndisc_send_na(dev, neigh, saddr, &msg->target,
!!is_router,
true, (ifp != NULL && inc), inc);
if (neigh)
neigh_release(neigh);
}
out:
if (ifp)
in6_ifa_put(ifp);
else
in6_dev_put(idev);
}
static void ndisc_recv_na(struct sk_buff *skb)
{
struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
u8 *lladdr = NULL;
u32 ndoptlen = skb->tail - (skb->transport_header +
offsetof(struct nd_msg, opt));
struct ndisc_options ndopts;
struct net_device *dev = skb->dev;
struct inet6_ifaddr *ifp;
struct neighbour *neigh;
if (skb->len < sizeof(struct nd_msg)) {
ND_PRINTK(2, warn, "NA: packet too short\n");
return;
}
if (ipv6_addr_is_multicast(&msg->target)) {
ND_PRINTK(2, warn, "NA: target address is multicast\n");
return;
}
if (ipv6_addr_is_multicast(daddr) &&
msg->icmph.icmp6_solicited) {
ND_PRINTK(2, warn, "NA: solicited NA is multicasted\n");
return;
}
if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts)) {
ND_PRINTK(2, warn, "NS: invalid ND option\n");
return;
}
if (ndopts.nd_opts_tgt_lladdr) {
lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, dev);
if (!lladdr) {
ND_PRINTK(2, warn,
"NA: invalid link-layer address length\n");
return;
}
}
ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1);
if (ifp) {
if (skb->pkt_type != PACKET_LOOPBACK
&& (ifp->flags & IFA_F_TENTATIVE)) {
addrconf_dad_failure(ifp);
return;
}
/* What should we make now? The advertisement
is invalid, but ndisc specs say nothing
about it. It could be misconfiguration, or
an smart proxy agent tries to help us :-)
We should not print the error if NA has been
received from loopback - it is just our own
unsolicited advertisement.
*/
if (skb->pkt_type != PACKET_LOOPBACK)
ND_PRINTK(1, warn,
"NA: someone advertises our address %pI6 on %s!\n",
&ifp->addr, ifp->idev->dev->name);
in6_ifa_put(ifp);
return;
}
neigh = neigh_lookup(&nd_tbl, &msg->target, dev);
if (neigh) {
u8 old_flags = neigh->flags;
struct net *net = dev_net(dev);
if (neigh->nud_state & NUD_FAILED)
goto out;
/*
* Don't update the neighbor cache entry on a proxy NA from
* ourselves because either the proxied node is off link or it
* has already sent a NA to us.
*/
if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) &&
net->ipv6.devconf_all->forwarding && net->ipv6.devconf_all->proxy_ndp &&
pneigh_lookup(&nd_tbl, net, &msg->target, dev, 0)) {
/* XXX: idev->cnf.proxy_ndp */
goto out;
}
neigh_update(neigh, lladdr,
msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
(msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)|
NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
(msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0));
if ((old_flags & ~neigh->flags) & NTF_ROUTER) {
/*
* Change: router to host
*/
struct rt6_info *rt;
rt = rt6_get_dflt_router(saddr, dev);
if (rt)
ip6_del_rt(rt);
}
out:
neigh_release(neigh);
}
}
static void ndisc_recv_rs(struct sk_buff *skb)
{
struct rs_msg *rs_msg = (struct rs_msg *)skb_transport_header(skb);
unsigned long ndoptlen = skb->len - sizeof(*rs_msg);
struct neighbour *neigh;
struct inet6_dev *idev;
const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
struct ndisc_options ndopts;
u8 *lladdr = NULL;
if (skb->len < sizeof(*rs_msg))
return;
idev = __in6_dev_get(skb->dev);
if (!idev) {
ND_PRINTK(1, err, "RS: can't find in6 device\n");
return;
}
/* Don't accept RS if we're not in router mode */
if (!idev->cnf.forwarding)
goto out;
/*
* Don't update NCE if src = ::;
* this implies that the source node has no ip address assigned yet.
*/
if (ipv6_addr_any(saddr))
goto out;
/* Parse ND options */
if (!ndisc_parse_options(rs_msg->opt, ndoptlen, &ndopts)) {
ND_PRINTK(2, notice, "NS: invalid ND option, ignored\n");
goto out;
}
if (ndopts.nd_opts_src_lladdr) {
lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr,
skb->dev);
if (!lladdr)
goto out;
}
neigh = __neigh_lookup(&nd_tbl, saddr, skb->dev, 1);
if (neigh) {
neigh_update(neigh, lladdr, NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE_ISROUTER);
neigh_release(neigh);
}
out:
return;
}
static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt)
{
struct icmp6hdr *icmp6h = (struct icmp6hdr *)skb_transport_header(ra);
struct sk_buff *skb;
struct nlmsghdr *nlh;
struct nduseroptmsg *ndmsg;
struct net *net = dev_net(ra->dev);
int err;
int base_size = NLMSG_ALIGN(sizeof(struct nduseroptmsg)
+ (opt->nd_opt_len << 3));
size_t msg_size = base_size + nla_total_size(sizeof(struct in6_addr));
skb = nlmsg_new(msg_size, GFP_ATOMIC);
if (skb == NULL) {
err = -ENOBUFS;
goto errout;
}
nlh = nlmsg_put(skb, 0, 0, RTM_NEWNDUSEROPT, base_size, 0);
if (nlh == NULL) {
goto nla_put_failure;
}
ndmsg = nlmsg_data(nlh);
ndmsg->nduseropt_family = AF_INET6;
ndmsg->nduseropt_ifindex = ra->dev->ifindex;
ndmsg->nduseropt_icmp_type = icmp6h->icmp6_type;
ndmsg->nduseropt_icmp_code = icmp6h->icmp6_code;
ndmsg->nduseropt_opts_len = opt->nd_opt_len << 3;
memcpy(ndmsg + 1, opt, opt->nd_opt_len << 3);
if (nla_put(skb, NDUSEROPT_SRCADDR, sizeof(struct in6_addr),
&ipv6_hdr(ra)->saddr))
goto nla_put_failure;
nlmsg_end(skb, nlh);
2009-02-25 10:18:28 +03:00
rtnl_notify(skb, net, 0, RTNLGRP_ND_USEROPT, NULL, GFP_ATOMIC);
return;
nla_put_failure:
nlmsg_free(skb);
err = -EMSGSIZE;
errout:
rtnl_set_sk_err(net, RTNLGRP_ND_USEROPT, err);
}
static void ndisc_router_discovery(struct sk_buff *skb)
{
struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb);
struct neighbour *neigh = NULL;
struct inet6_dev *in6_dev;
struct rt6_info *rt = NULL;
int lifetime;
struct ndisc_options ndopts;
int optlen;
unsigned int pref = 0;
__u8 * opt = (__u8 *)(ra_msg + 1);
optlen = (skb->tail - skb->transport_header) - sizeof(struct ra_msg);
if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) {
ND_PRINTK(2, warn, "RA: source address is not link-local\n");
return;
}
if (optlen < 0) {
ND_PRINTK(2, warn, "RA: packet too short\n");
return;
}
#ifdef CONFIG_IPV6_NDISC_NODETYPE
if (skb->ndisc_nodetype == NDISC_NODETYPE_HOST) {
ND_PRINTK(2, warn, "RA: from host or unauthorized router\n");
return;
}
#endif
/*
* set the RA_RECV flag in the interface
*/
in6_dev = __in6_dev_get(skb->dev);
if (in6_dev == NULL) {
ND_PRINTK(0, err, "RA: can't find inet6 device for %s\n",
skb->dev->name);
return;
}
if (!ndisc_parse_options(opt, optlen, &ndopts)) {
ND_PRINTK(2, warn, "RA: invalid ND options\n");
return;
}
if (!ipv6_accept_ra(in6_dev))
goto skip_linkparms;
#ifdef CONFIG_IPV6_NDISC_NODETYPE
/* skip link-specific parameters from interior routers */
if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT)
goto skip_linkparms;
#endif
if (in6_dev->if_flags & IF_RS_SENT) {
/*
* flag that an RA was received after an RS was sent
* out on this interface.
*/
in6_dev->if_flags |= IF_RA_RCVD;
}
/*
* Remember the managed/otherconf flags from most recently
* received RA message (RFC 2462) -- yoshfuji
*/
in6_dev->if_flags = (in6_dev->if_flags & ~(IF_RA_MANAGED |
IF_RA_OTHERCONF)) |
(ra_msg->icmph.icmp6_addrconf_managed ?
IF_RA_MANAGED : 0) |
(ra_msg->icmph.icmp6_addrconf_other ?
IF_RA_OTHERCONF : 0);
if (!in6_dev->cnf.accept_ra_defrtr)
goto skip_defrtr;
if (ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, NULL, 0))
goto skip_defrtr;
lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime);
#ifdef CONFIG_IPV6_ROUTER_PREF
pref = ra_msg->icmph.icmp6_router_pref;
/* 10b is handled as if it were 00b (medium) */
if (pref == ICMPV6_ROUTER_PREF_INVALID ||
!in6_dev->cnf.accept_ra_rtr_pref)
pref = ICMPV6_ROUTER_PREF_MEDIUM;
#endif
rt = rt6_get_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev);
if (rt) {
neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr);
if (!neigh) {
ND_PRINTK(0, err,
"RA: %s got default router without neighbour\n",
__func__);
ip6_rt_put(rt);
return;
}
}
if (rt && lifetime == 0) {
ip6_del_rt(rt);
rt = NULL;
}
if (rt == NULL && lifetime) {
ND_PRINTK(3, dbg, "RA: adding default router\n");
rt = rt6_add_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev, pref);
if (rt == NULL) {
ND_PRINTK(0, err,
"RA: %s failed to add default route\n",
__func__);
return;
}
neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr);
if (neigh == NULL) {
ND_PRINTK(0, err,
"RA: %s got default router without neighbour\n",
__func__);
ip6_rt_put(rt);
return;
}
neigh->flags |= NTF_ROUTER;
} else if (rt) {
rt->rt6i_flags = (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
}
if (rt)
rt6_set_expires(rt, jiffies + (HZ * lifetime));
if (ra_msg->icmph.icmp6_hop_limit) {
in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
if (rt)
dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
ra_msg->icmph.icmp6_hop_limit);
}
skip_defrtr:
/*
* Update Reachable Time and Retrans Timer
*/
if (in6_dev->nd_parms) {
unsigned long rtime = ntohl(ra_msg->retrans_timer);
if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/HZ) {
rtime = (rtime*HZ)/1000;
if (rtime < HZ/10)
rtime = HZ/10;
in6_dev->nd_parms->retrans_time = rtime;
in6_dev->tstamp = jiffies;
inet6_ifinfo_notify(RTM_NEWLINK, in6_dev);
}
rtime = ntohl(ra_msg->reachable_time);
if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/(3*HZ)) {
rtime = (rtime*HZ)/1000;
if (rtime < HZ/10)
rtime = HZ/10;
if (rtime != in6_dev->nd_parms->base_reachable_time) {
in6_dev->nd_parms->base_reachable_time = rtime;
in6_dev->nd_parms->gc_staletime = 3 * rtime;
in6_dev->nd_parms->reachable_time = neigh_rand_reach_time(rtime);
in6_dev->tstamp = jiffies;
inet6_ifinfo_notify(RTM_NEWLINK, in6_dev);
}
}
}
skip_linkparms:
/*
* Process options.
*/
if (!neigh)
neigh = __neigh_lookup(&nd_tbl, &ipv6_hdr(skb)->saddr,
skb->dev, 1);
if (neigh) {
u8 *lladdr = NULL;
if (ndopts.nd_opts_src_lladdr) {
lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr,
skb->dev);
if (!lladdr) {
ND_PRINTK(2, warn,
"RA: invalid link-layer address length\n");
goto out;
}
}
neigh_update(neigh, lladdr, NUD_STALE,
NEIGH_UPDATE_F_WEAK_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE|
NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
NEIGH_UPDATE_F_ISROUTER);
}
if (!ipv6_accept_ra(in6_dev))
goto out;
#ifdef CONFIG_IPV6_ROUTE_INFO
if (ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, NULL, 0))
goto skip_routeinfo;
if (in6_dev->cnf.accept_ra_rtr_pref && ndopts.nd_opts_ri) {
struct nd_opt_hdr *p;
for (p = ndopts.nd_opts_ri;
p;
p = ndisc_next_option(p, ndopts.nd_opts_ri_end)) {
struct route_info *ri = (struct route_info *)p;
#ifdef CONFIG_IPV6_NDISC_NODETYPE
if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT &&
ri->prefix_len == 0)
continue;
#endif
if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen)
continue;
rt6_route_rcv(skb->dev, (u8*)p, (p->nd_opt_len) << 3,
&ipv6_hdr(skb)->saddr);
}
}
skip_routeinfo:
#endif
#ifdef CONFIG_IPV6_NDISC_NODETYPE
/* skip link-specific ndopts from interior routers */
if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT)
goto out;
#endif
if (in6_dev->cnf.accept_ra_pinfo && ndopts.nd_opts_pi) {
struct nd_opt_hdr *p;
for (p = ndopts.nd_opts_pi;
p;
p = ndisc_next_option(p, ndopts.nd_opts_pi_end)) {
addrconf_prefix_rcv(skb->dev, (u8 *)p,
(p->nd_opt_len) << 3,
ndopts.nd_opts_src_lladdr != NULL);
}
}
if (ndopts.nd_opts_mtu) {
__be32 n;
u32 mtu;
memcpy(&n, ((u8*)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu));
mtu = ntohl(n);
if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) {
ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu);
} else if (in6_dev->cnf.mtu6 != mtu) {
in6_dev->cnf.mtu6 = mtu;
if (rt)
dst_metric_set(&rt->dst, RTAX_MTU, mtu);
rt6_mtu_change(skb->dev, mtu);
}
}
if (ndopts.nd_useropts) {
struct nd_opt_hdr *p;
for (p = ndopts.nd_useropts;
p;
p = ndisc_next_useropt(p, ndopts.nd_useropts_end)) {
ndisc_ra_useropt(skb, p);
}
}
if (ndopts.nd_opts_tgt_lladdr || ndopts.nd_opts_rh) {
ND_PRINTK(2, warn, "RA: invalid RA options\n");
}
out:
ip6_rt_put(rt);
if (neigh)
neigh_release(neigh);
}
static void ndisc_redirect_rcv(struct sk_buff *skb)
{
u8 *hdr;
struct ndisc_options ndopts;
struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb);
u32 ndoptlen = skb->tail - (skb->transport_header +
offsetof(struct rd_msg, opt));
#ifdef CONFIG_IPV6_NDISC_NODETYPE
switch (skb->ndisc_nodetype) {
case NDISC_NODETYPE_HOST:
case NDISC_NODETYPE_NODEFAULT:
ND_PRINTK(2, warn,
"Redirect: from host or unauthorized router\n");
return;
}
#endif
if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) {
ND_PRINTK(2, warn,
"Redirect: source address is not link-local\n");
return;
}
if (!ndisc_parse_options(msg->opt, ndoptlen, &ndopts))
return;
if (!ndopts.nd_opts_rh)
return;
hdr = (u8 *)ndopts.nd_opts_rh;
hdr += 8;
if (!pskb_pull(skb, hdr - skb_transport_header(skb)))
return;
icmpv6_notify(skb, NDISC_REDIRECT, 0, 0);
}
void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
{
struct net_device *dev = skb->dev;
struct net *net = dev_net(dev);
struct sock *sk = net->ipv6.ndisc_sk;
int len = sizeof(struct rd_msg);
struct inet_peer *peer;
struct sk_buff *buff;
struct rd_msg *msg;
struct in6_addr saddr_buf;
struct rt6_info *rt;
struct dst_entry *dst;
struct inet6_dev *idev;
struct flowi6 fl6;
u8 *opt;
int hlen, tlen;
int rd_len;
int err;
u8 ha_buf[MAX_ADDR_LEN], *ha = NULL;
bool ret;
if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) {
ND_PRINTK(2, warn, "Redirect: no link-local address on %s\n",
dev->name);
return;
}
if (!ipv6_addr_equal(&ipv6_hdr(skb)->daddr, target) &&
[IPv6]: Fix ICMPv6 redirect handling with target multicast address When the ICMPv6 Target address is multicast, Linux processes the redirect instead of dropping it. The problem is in this code in ndisc_redirect_rcv(): if (ipv6_addr_equal(dest, target)) { on_link = 1; } else if (!(ipv6_addr_type(target) & IPV6_ADDR_LINKLOCAL)) { ND_PRINTK2(KERN_WARNING "ICMPv6 Redirect: target address is not link-local.\n"); return; } This second check will succeed if the Target address is, for example, FF02::1 because it has link-local scope. Instead, it should be checking if it's a unicast link-local address, as stated in RFC 2461/4861 Section 8.1: - The ICMP Target Address is either a link-local address (when redirected to a router) or the same as the ICMP Destination Address (when redirected to the on-link destination). I know this doesn't explicitly say unicast link-local address, but it's implied. This bug is preventing Linux kernels from achieving IPv6 Logo Phase II certification because of a recent error that was found in the TAHI test suite - Neighbor Disovery suite test 206 (v6LC.2.3.6_G) had the multicast address in the Destination field instead of Target field, so we were passing the test. This won't be the case anymore. The patch below fixes this problem, and also fixes ndisc_send_redirect() to not send an invalid redirect with a multicast address in the Target field. I re-ran the TAHI Neighbor Discovery section to make sure Linux passes all 245 tests now. Signed-off-by: Brian Haley <brian.haley@hp.com> Acked-by: David L Stevens <dlstevens@us.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-10-08 11:12:05 +04:00
ipv6_addr_type(target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) {
ND_PRINTK(2, warn,
"Redirect: target address is not link-local unicast\n");
[IPV6]: fix BUG of ndisc_send_redirect() When I tested IPv6 redirect function about kernel 2.6.19.1, and found that the kernel can send redirect packets whose target address is global address, and the target is not the actual endpoint of communication. But the criteria conform to RFC2461, the target address defines as following: Target Address An IP address that is a better first hop to use for he ICMP Destination Address. When the target is the actual endpoint of communication, i.e., the destination is a neighbor, the Target Address field MUST contain the same value as the ICMP Destination Address field. Otherwise the target is a better first-hop router and the Target Address MUST be the router's link-local address so that hosts can uniquely identify routers. According to this definition, when a router redirect to a host, the target address either the better first-hop router's link-local address or the same as the ICMP destination address field. But the function of ndisc_send_redirect() in net/ipv6/ndisc.c, does not check the target address correctly. There is another definition about receive Redirect message in RFC2461: 8.1. Validation of Redirect Messages A host MUST silently discard any received Redirect message that does not satisfy all of the following validity checks: ...... - The ICMP Target Address is either a link-local address (when redirected to a router) or the same as the ICMP Destination Address (when redirected to the on-link destination). ...... And the receive redirect function of ndisc_redirect_rcv() implemented this definition, checks the target address correctly. if (ipv6_addr_equal(dest, target)) { on_link = 1; } else if (!(ipv6_addr_type(target) & IPV6_ADDR_LINKLOCAL)) { ND_PRINTK2(KERN_WARNING "ICMPv6 Redirect: target address is not link-local.\n"); return; } So, I think the send redirect function must check the target address also. Signed-off-by: Li Yewang <lyw@nanjing-fnst.com> Acked-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-01-31 01:33:20 +03:00
return;
}
icmpv6_flow_init(sk, &fl6, NDISC_REDIRECT,
&saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex);
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
dst_release(dst);
return;
}
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
if (IS_ERR(dst))
return;
rt = (struct rt6_info *) dst;
if (rt->rt6i_flags & RTF_GATEWAY) {
ND_PRINTK(2, warn,
"Redirect: destination is not a neighbour\n");
goto release;
}
peer = inet_getpeer_v6(net->ipv6.peers, &rt->rt6i_dst.addr, 1);
ret = inet_peer_xrlim_allow(peer, 1*HZ);
if (peer)
inet_putpeer(peer);
if (!ret)
goto release;
if (dev->addr_len) {
struct neighbour *neigh = dst_neigh_lookup(skb_dst(skb), target);
if (!neigh) {
ND_PRINTK(2, warn,
"Redirect: no neigh for target address\n");
goto release;
}
read_lock_bh(&neigh->lock);
if (neigh->nud_state & NUD_VALID) {
memcpy(ha_buf, neigh->ha, dev->addr_len);
read_unlock_bh(&neigh->lock);
ha = ha_buf;
len += ndisc_opt_addr_space(dev);
} else
read_unlock_bh(&neigh->lock);
neigh_release(neigh);
}
rd_len = min_t(unsigned int,
IPV6_MIN_MTU-sizeof(struct ipv6hdr)-len, skb->len + 8);
rd_len &= ~0x7;
len += rd_len;
hlen = LL_RESERVED_SPACE(dev);
tlen = dev->needed_tailroom;
buff = sock_alloc_send_skb(sk,
ndisc: Remove unused space at tail of skb for ndisc messages. (TAKE 3) Currently, the size of skb allocated for NDISC is MAX_HEADER + LL_RESERVED_SPACE(dev) + packet length + dev->needed_tailroom, but only LL_RESERVED_SPACE(dev) bytes is "reserved" for headers. As a result, the skb looks like this (after construction of the message): head data tail end +--------------------------------------------------------------+ + | | | | +--------------------------------------------------------------+ |<-hlen---->|<---ipv6 packet------>|<--tlen-->|<--MAX_HEADER-->| =LL_ = dev RESERVED_ ->needed_ SPACE(dev) tailroom As the name implies, "MAX_HEADER" is used for headers, and should be "reserved" in prior to packet construction. Or, if some space is really required at the tail of ther skb, it should be explicitly documented. We have several option after construction of NDISC message: Option 1: head data tail end +---------------------------------------------+ + | | | +---------------------------------------------+ |<-hlen---->|<---ipv6 packet------>|<--tlen-->| =LL_ = dev RESERVED_ ->needed_ SPACE(dev) tailroom Option 2: head data tail end +--------------------------------------------------+ + | | | +--------------------------------------------------+ |<--MAX_HEADER-->|<---ipv6 packet------>|<--tlen-->| = dev ->needed_ tailroom Option 3: head data tail end +--------------------------------------------------------------+ + | | | | +--------------------------------------------------------------+ |<--MAX_HEADER-->|<-hlen---->|<---ipv6 packet------>|<--tlen-->| =LL_ = dev RESERVED_ ->needed_ SPACE(dev) tailroom Our tunnel drivers try expanding headroom and the space for tunnel encapsulation was not a mandatory space -- so we are not seeing bugs here --, but just for optimization for performance critial situations. Since NDISC messages are not performance critical unlike TCP, and as we know outgoing device, LL_RESERVED_SPACE(dev) should be just enough for the device in most (if not all) cases: LL_RESERVED_SPACE(dev) <= LL_MAX_HEADER <= MAX_HEADER Note that LL_RESERVED_SPACE(dev) is also enough for NDISC over SIT (e.g., ISATAP). So, I think Option 1 is just fine here. Signed-off-by: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> Acked-by: Eric Dumazet <edumazet@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-04 07:58:04 +04:00
(sizeof(struct ipv6hdr) +
len + hlen + tlen),
1, &err);
if (buff == NULL) {
ND_PRINTK(0, err,
"Redirect: %s failed to allocate an skb, err=%d\n",
__func__, err);
goto release;
}
skb_reserve(buff, hlen);
ip6_nd_hdr(sk, buff, dev, &saddr_buf, &ipv6_hdr(skb)->saddr,
IPPROTO_ICMPV6, len);
skb_set_transport_header(buff, skb_tail_pointer(buff) - buff->data);
skb_put(buff, len);
msg = (struct rd_msg *)icmp6_hdr(buff);
memset(&msg->icmph, 0, sizeof(struct icmp6hdr));
msg->icmph.icmp6_type = NDISC_REDIRECT;
/*
* copy target and destination addresses
*/
msg->target = *target;
msg->dest = ipv6_hdr(skb)->daddr;
opt = msg->opt;
/*
* include target_address option
*/
if (ha)
opt = ndisc_fill_addr_option(opt, ND_OPT_TARGET_LL_ADDR, ha, dev);
/*
* build redirect option and copy skb over to the new packet.
*/
memset(opt, 0, 8);
*(opt++) = ND_OPT_REDIRECT_HDR;
*(opt++) = (rd_len >> 3);
opt += 6;
memcpy(opt, ipv6_hdr(skb), rd_len - 8);
msg->icmph.icmp6_cksum = csum_ipv6_magic(&saddr_buf, &ipv6_hdr(skb)->saddr,
len, IPPROTO_ICMPV6,
csum_partial(msg, len, 0));
skb_dst_set(buff, dst);
rcu_read_lock();
idev = __in6_dev_get(dst->dev);
IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len);
err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, buff, NULL, dst->dev,
dst_output);
if (!err) {
ICMP6MSGOUT_INC_STATS(net, idev, NDISC_REDIRECT);
ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
}
rcu_read_unlock();
return;
release:
dst_release(dst);
}
static void pndisc_redo(struct sk_buff *skb)
{
ndisc_recv_ns(skb);
kfree_skb(skb);
}
int ndisc_rcv(struct sk_buff *skb)
{
struct nd_msg *msg;
if (!pskb_may_pull(skb, skb->len))
return 0;
msg = (struct nd_msg *)skb_transport_header(skb);
__skb_push(skb, skb->data - skb_transport_header(skb));
if (ipv6_hdr(skb)->hop_limit != 255) {
ND_PRINTK(2, warn, "NDISC: invalid hop-limit: %d\n",
ipv6_hdr(skb)->hop_limit);
return 0;
}
if (msg->icmph.icmp6_code != 0) {
ND_PRINTK(2, warn, "NDISC: invalid ICMPv6 code: %d\n",
msg->icmph.icmp6_code);
return 0;
}
memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
switch (msg->icmph.icmp6_type) {
case NDISC_NEIGHBOUR_SOLICITATION:
ndisc_recv_ns(skb);
break;
case NDISC_NEIGHBOUR_ADVERTISEMENT:
ndisc_recv_na(skb);
break;
case NDISC_ROUTER_SOLICITATION:
ndisc_recv_rs(skb);
break;
case NDISC_ROUTER_ADVERTISEMENT:
ndisc_router_discovery(skb);
break;
case NDISC_REDIRECT:
ndisc_redirect_rcv(skb);
break;
}
return 0;
}
static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
struct net_device *dev = ptr;
struct net *net = dev_net(dev);
struct inet6_dev *idev;
switch (event) {
case NETDEV_CHANGEADDR:
neigh_changeaddr(&nd_tbl, dev);
fib6_run_gc(~0UL, net);
idev = in6_dev_get(dev);
if (!idev)
break;
if (idev->cnf.ndisc_notify)
ndisc_send_unsol_na(dev);
in6_dev_put(idev);
break;
case NETDEV_DOWN:
neigh_ifdown(&nd_tbl, dev);
fib6_run_gc(~0UL, net);
break;
case NETDEV_NOTIFY_PEERS:
ndisc_send_unsol_na(dev);
break;
default:
break;
}
return NOTIFY_DONE;
}
static struct notifier_block ndisc_netdev_notifier = {
.notifier_call = ndisc_netdev_event,
};
#ifdef CONFIG_SYSCTL
static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl,
const char *func, const char *dev_name)
{
static char warncomm[TASK_COMM_LEN];
static int warned;
if (strcmp(warncomm, current->comm) && warned < 5) {
strcpy(warncomm, current->comm);
pr_warn("process `%s' is using deprecated sysctl (%s) net.ipv6.neigh.%s.%s - use net.ipv6.neigh.%s.%s_ms instead\n",
warncomm, func,
dev_name, ctl->procname,
dev_name, ctl->procname);
warned++;
}
}
int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct net_device *dev = ctl->extra1;
struct inet6_dev *idev;
int ret;
if ((strcmp(ctl->procname, "retrans_time") == 0) ||
(strcmp(ctl->procname, "base_reachable_time") == 0))
ndisc_warn_deprecated_sysctl(ctl, "syscall", dev ? dev->name : "default");
if (strcmp(ctl->procname, "retrans_time") == 0)
ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
else if (strcmp(ctl->procname, "base_reachable_time") == 0)
ret = proc_dointvec_jiffies(ctl, write,
buffer, lenp, ppos);
else if ((strcmp(ctl->procname, "retrans_time_ms") == 0) ||
(strcmp(ctl->procname, "base_reachable_time_ms") == 0))
ret = proc_dointvec_ms_jiffies(ctl, write,
buffer, lenp, ppos);
else
ret = -1;
if (write && ret == 0 && dev && (idev = in6_dev_get(dev)) != NULL) {
if (ctl->data == &idev->nd_parms->base_reachable_time)
idev->nd_parms->reachable_time = neigh_rand_reach_time(idev->nd_parms->base_reachable_time);
idev->tstamp = jiffies;
inet6_ifinfo_notify(RTM_NEWLINK, idev);
in6_dev_put(idev);
}
return ret;
}
#endif
static int __net_init ndisc_net_init(struct net *net)
{
struct ipv6_pinfo *np;
struct sock *sk;
int err;
err = inet_ctl_sock_create(&sk, PF_INET6,
SOCK_RAW, IPPROTO_ICMPV6, net);
if (err < 0) {
ND_PRINTK(0, err,
"NDISC: Failed to initialize the control socket (err %d)\n",
err);
return err;
}
net->ipv6.ndisc_sk = sk;
np = inet6_sk(sk);
np->hop_limit = 255;
/* Do not loopback ndisc messages */
np->mc_loop = 0;
return 0;
}
static void __net_exit ndisc_net_exit(struct net *net)
{
inet_ctl_sock_destroy(net->ipv6.ndisc_sk);
}
static struct pernet_operations ndisc_net_ops = {
.init = ndisc_net_init,
.exit = ndisc_net_exit,
};
int __init ndisc_init(void)
{
int err;
err = register_pernet_subsys(&ndisc_net_ops);
if (err)
return err;
/*
* Initialize the neighbour table
*/
neigh_table_init(&nd_tbl);
#ifdef CONFIG_SYSCTL
err = neigh_sysctl_register(NULL, &nd_tbl.parms, "ipv6",
&ndisc_ifinfo_sysctl_change);
if (err)
goto out_unregister_pernet;
#endif
err = register_netdevice_notifier(&ndisc_netdev_notifier);
if (err)
goto out_unregister_sysctl;
out:
return err;
out_unregister_sysctl:
#ifdef CONFIG_SYSCTL
neigh_sysctl_unregister(&nd_tbl.parms);
out_unregister_pernet:
#endif
unregister_pernet_subsys(&ndisc_net_ops);
goto out;
}
void ndisc_cleanup(void)
{
unregister_netdevice_notifier(&ndisc_netdev_notifier);
#ifdef CONFIG_SYSCTL
neigh_sysctl_unregister(&nd_tbl.parms);
#endif
neigh_table_clear(&nd_tbl);
unregister_pernet_subsys(&ndisc_net_ops);
}