#define RT6_TRACE(x...) do { ; } while (0)
#endif
-#define CLONE_OFFLINK_ROUTE 0
-
static struct rt6_info * ip6_rt_copy(struct rt6_info *ort);
static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie);
+static unsigned int ip6_default_advmss(const struct dst_entry *dst);
+static unsigned int ip6_default_mtu(const struct dst_entry *dst);
static struct dst_entry *ip6_negative_advice(struct dst_entry *);
static void ip6_dst_destroy(struct dst_entry *);
static void ip6_dst_ifdown(struct dst_entry *,
struct in6_addr *gwaddr, int ifindex);
#endif
+static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
+{
+ struct rt6_info *rt = (struct rt6_info *) dst;
+ struct inet_peer *peer;
+ u32 *p = NULL;
+
+ if (!rt->rt6i_peer)
+ rt6_bind_peer(rt, 1);
+
+ peer = rt->rt6i_peer;
+ if (peer) {
+ u32 *old_p = __DST_METRICS_PTR(old);
+ unsigned long prev, new;
+
+ p = peer->metrics;
+ if (inet_metrics_new(peer))
+ memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
+
+ new = (unsigned long) p;
+ prev = cmpxchg(&dst->_metrics, old, new);
+
+ if (prev != old) {
+ p = __DST_METRICS_PTR(prev);
+ if (prev & DST_METRICS_READ_ONLY)
+ p = NULL;
+ }
+ }
+ return p;
+}
+
static struct dst_ops ip6_dst_ops_template = {
.family = AF_INET6,
.protocol = cpu_to_be16(ETH_P_IPV6),
.gc = ip6_dst_gc,
.gc_thresh = 1024,
.check = ip6_dst_check,
+ .default_advmss = ip6_default_advmss,
+ .default_mtu = ip6_default_mtu,
+ .cow_metrics = ipv6_cow_metrics,
.destroy = ip6_dst_destroy,
.ifdown = ip6_dst_ifdown,
.negative_advice = ip6_negative_advice,
.local_out = __ip6_local_out,
};
+static unsigned int ip6_blackhole_default_mtu(const struct dst_entry *dst)
+{
+ return 0;
+}
+
static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
{
}
.protocol = cpu_to_be16(ETH_P_IPV6),
.destroy = ip6_dst_destroy,
.check = ip6_dst_check,
+ .default_mtu = ip6_blackhole_default_mtu,
.update_pmtu = ip6_rt_blackhole_update_pmtu,
};
+static const u32 ip6_template_metrics[RTAX_MAX] = {
+ [RTAX_HOPLIMIT - 1] = 255,
+};
+
static struct rt6_info ip6_null_entry_template = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
.__use = 1,
.obsolete = -1,
.error = -ENETUNREACH,
- .metrics = { [RTAX_HOPLIMIT - 1] = 255, },
.input = ip6_pkt_discard,
.output = ip6_pkt_discard_out,
},
.__use = 1,
.obsolete = -1,
.error = -EACCES,
- .metrics = { [RTAX_HOPLIMIT - 1] = 255, },
.input = ip6_pkt_prohibit,
.output = ip6_pkt_prohibit_out,
},
.__use = 1,
.obsolete = -1,
.error = -EINVAL,
- .metrics = { [RTAX_HOPLIMIT - 1] = 255, },
.input = dst_discard,
.output = dst_discard,
},
/* allocate dst with ip6_dst_ops */
static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops)
{
- return (struct rt6_info *)dst_alloc(ops);
+ return (struct rt6_info *)dst_alloc(ops, 0);
}
static void ip6_dst_destroy(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *)dst;
struct inet6_dev *idev = rt->rt6i_idev;
+ struct inet_peer *peer = rt->rt6i_peer;
if (idev != NULL) {
rt->rt6i_idev = NULL;
in6_dev_put(idev);
}
+ if (peer) {
+ rt->rt6i_peer = NULL;
+ inet_putpeer(peer);
+ }
+}
+
+static atomic_t __rt6_peer_genid = ATOMIC_INIT(0);
+
+static u32 rt6_peer_genid(void)
+{
+ return atomic_read(&__rt6_peer_genid);
+}
+
+void rt6_bind_peer(struct rt6_info *rt, int create)
+{
+ struct inet_peer *peer;
+
+ peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create);
+ if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL)
+ inet_putpeer(peer);
+ else
+ rt->rt6i_peer_genid = rt6_peer_genid();
}
static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
{
struct flowi fl = {
.oif = oif,
- .nl_u = {
- .ip6_u = {
- .daddr = *daddr,
- },
- },
+ .fl6_dst = *daddr,
};
struct dst_entry *dst;
int flags = strict ? RT6_LOOKUP_F_IFACE : 0;
if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
- else {
-#if CLONE_OFFLINK_ROUTE
+ else
nrt = rt6_alloc_clone(rt, &fl->fl6_dst);
-#else
- goto out2;
-#endif
- }
dst_release(&rt->dst);
rt = nrt ? : net->ipv6.ip6_null_entry;
int flags = RT6_LOOKUP_F_HAS_SADDR;
struct flowi fl = {
.iif = skb->dev->ifindex,
- .nl_u = {
- .ip6_u = {
- .daddr = iph->daddr,
- .saddr = iph->saddr,
- .flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK,
- },
- },
+ .fl6_dst = iph->daddr,
+ .fl6_src = iph->saddr,
+ .fl6_flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK,
.mark = skb->mark,
.proto = iph->nexthdr,
};
{
struct rt6_info *ort = (struct rt6_info *) *dstp;
struct rt6_info *rt = (struct rt6_info *)
- dst_alloc(&ip6_dst_blackhole_ops);
+ dst_alloc(&ip6_dst_blackhole_ops, 1);
struct dst_entry *new = NULL;
if (rt) {
new = &rt->dst;
- atomic_set(&new->__refcnt, 1);
new->__use = 1;
new->input = dst_discard;
new->output = dst_discard;
- memcpy(new->metrics, ort->dst.metrics, RTAX_MAX*sizeof(u32));
+ dst_copy_metrics(new, &ort->dst);
new->dev = ort->dst.dev;
if (new->dev)
dev_hold(new->dev);
rt = (struct rt6_info *) dst;
- if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
+ if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie)) {
+ if (rt->rt6i_peer_genid != rt6_peer_genid()) {
+ if (!rt->rt6i_peer)
+ rt6_bind_peer(rt, 0);
+ rt->rt6i_peer_genid = rt6_peer_genid();
+ }
return dst;
-
+ }
return NULL;
}
if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
rt6->rt6i_flags |= RTF_MODIFIED;
if (mtu < IPV6_MIN_MTU) {
+ u32 features = dst_metric(dst, RTAX_FEATURES);
mtu = IPV6_MIN_MTU;
- dst->metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG;
+ features |= RTAX_FEATURE_ALLFRAG;
+ dst_metric_set(dst, RTAX_FEATURES, features);
}
- dst->metrics[RTAX_MTU-1] = mtu;
- call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst);
+ dst_metric_set(dst, RTAX_MTU, mtu);
}
}
-static int ipv6_get_mtu(struct net_device *dev);
-
-static inline unsigned int ipv6_advmss(struct net *net, unsigned int mtu)
+static unsigned int ip6_default_advmss(const struct dst_entry *dst)
{
+ struct net_device *dev = dst->dev;
+ unsigned int mtu = dst_mtu(dst);
+ struct net *net = dev_net(dev);
+
mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr);
if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss)
return mtu;
}
+static unsigned int ip6_default_mtu(const struct dst_entry *dst)
+{
+ unsigned int mtu = IPV6_MIN_MTU;
+ struct inet6_dev *idev;
+
+ rcu_read_lock();
+ idev = __in6_dev_get(dst->dev);
+ if (idev)
+ mtu = idev->cnf.mtu6;
+ rcu_read_unlock();
+
+ return mtu;
+}
+
static struct dst_entry *icmp6_dst_gc_list;
static DEFINE_SPINLOCK(icmp6_dst_lock);
rt->rt6i_idev = idev;
rt->rt6i_nexthop = neigh;
atomic_set(&rt->dst.__refcnt, 1);
- rt->dst.metrics[RTAX_HOPLIMIT-1] = 255;
- rt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev);
- rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->dst));
+ dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255);
rt->dst.output = ip6_output;
#if 0 /* there's no chance to use these for ndisc */
Remove it only when all the things will work!
*/
-static int ipv6_get_mtu(struct net_device *dev)
-{
- int mtu = IPV6_MIN_MTU;
- struct inet6_dev *idev;
-
- rcu_read_lock();
- idev = __in6_dev_get(dev);
- if (idev)
- mtu = idev->cnf.mtu6;
- rcu_read_unlock();
- return mtu;
-}
-
int ip6_dst_hoplimit(struct dst_entry *dst)
{
- int hoplimit = dst_metric(dst, RTAX_HOPLIMIT);
- if (hoplimit < 0) {
+ int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT);
+ if (hoplimit == 0) {
struct net_device *dev = dst->dev;
struct inet6_dev *idev;
}
return hoplimit;
}
+EXPORT_SYMBOL(ip6_dst_hoplimit);
/*
*
goto out;
}
- rt->dst.metrics[type - 1] = nla_get_u32(nla);
+ dst_metric_set(&rt->dst, type, nla_get_u32(nla));
}
}
}
- if (dst_metric(&rt->dst, RTAX_HOPLIMIT) == 0)
- rt->dst.metrics[RTAX_HOPLIMIT-1] = -1;
- if (!dst_mtu(&rt->dst))
- rt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(dev);
- if (!dst_metric(&rt->dst, RTAX_ADVMSS))
- rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->dst));
rt->dst.dev = dev;
rt->rt6i_idev = idev;
rt->rt6i_table = table;
struct ip6rd_flowi rdfl = {
.fl = {
.oif = dev->ifindex,
- .nl_u = {
- .ip6_u = {
- .daddr = *dest,
- .saddr = *src,
- },
- },
+ .fl6_dst = *dest,
+ .fl6_src = *src,
},
};
ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key);
nrt->rt6i_nexthop = neigh_clone(neigh);
- /* Reset pmtu, it may be better */
- nrt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(neigh->dev);
- nrt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dev_net(neigh->dev),
- dst_mtu(&nrt->dst));
if (ip6_ins_rt(nrt))
goto out;
would return automatically.
*/
if (rt->rt6i_flags & RTF_CACHE) {
- rt->dst.metrics[RTAX_MTU-1] = pmtu;
- if (allfrag)
- rt->dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG;
+ dst_metric_set(&rt->dst, RTAX_MTU, pmtu);
+ if (allfrag) {
+ u32 features = dst_metric(&rt->dst, RTAX_FEATURES);
+ features |= RTAX_FEATURE_ALLFRAG;
+ dst_metric_set(&rt->dst, RTAX_FEATURES, features);
+ }
dst_set_expires(&rt->dst, net->ipv6.sysctl.ip6_rt_mtu_expires);
rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES;
goto out;
nrt = rt6_alloc_clone(rt, daddr);
if (nrt) {
- nrt->dst.metrics[RTAX_MTU-1] = pmtu;
- if (allfrag)
- nrt->dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG;
+ dst_metric_set(&nrt->dst, RTAX_MTU, pmtu);
+ if (allfrag) {
+ u32 features = dst_metric(&nrt->dst, RTAX_FEATURES);
+ features |= RTAX_FEATURE_ALLFRAG;
+ dst_metric_set(&nrt->dst, RTAX_FEATURES, features);
+ }
/* According to RFC 1981, detecting PMTU increase shouldn't be
* happened within 5 mins, the recommended timer is 10 mins.
rt->dst.input = ort->dst.input;
rt->dst.output = ort->dst.output;
- memcpy(rt->dst.metrics, ort->dst.metrics, RTAX_MAX*sizeof(u32));
+ dst_copy_metrics(&rt->dst, &ort->dst);
rt->dst.error = ort->dst.error;
rt->dst.dev = ort->dst.dev;
if (rt->dst.dev)
rt->dst.output = ip6_output;
rt->rt6i_dev = net->loopback_dev;
rt->rt6i_idev = idev;
- rt->dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev);
- rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, dst_mtu(&rt->dst));
- rt->dst.metrics[RTAX_HOPLIMIT-1] = -1;
+ dst_metric_set(&rt->dst, RTAX_HOPLIMIT, -1);
rt->dst.obsolete = -1;
rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP;
static int fib6_ifdown(struct rt6_info *rt, void *arg)
{
- struct net_device *dev = ((struct arg_dev_net *)arg)->dev;
- struct net *net = ((struct arg_dev_net *)arg)->net;
+ const struct arg_dev_net *adn = arg;
+ const struct net_device *dev = adn->dev;
- if (((void *)rt->rt6i_dev == dev || dev == NULL) &&
- rt != net->ipv6.ip6_null_entry) {
+ if ((rt->rt6i_dev == dev || dev == NULL) &&
+ rt != adn->net->ipv6.ip6_null_entry) {
RT6_TRACE("deleted by ifdown %p\n", rt);
return -1;
}
{
struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg;
struct inet6_dev *idev;
- struct net *net = dev_net(arg->dev);
/* In IPv6 pmtu discovery is not optional,
so that RTAX_MTU lock cannot disable it.
(dst_mtu(&rt->dst) >= arg->mtu ||
(dst_mtu(&rt->dst) < arg->mtu &&
dst_mtu(&rt->dst) == idev->cnf.mtu6))) {
- rt->dst.metrics[RTAX_MTU-1] = arg->mtu;
- rt->dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(net, arg->mtu);
+ dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
}
return 0;
}
NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
}
- if (rtnetlink_put_metrics(skb, rt->dst.metrics) < 0)
+ if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
goto nla_put_failure;
if (rt->dst.neighbour)
#ifdef CONFIG_PROC_FS
-#define RT6_INFO_LEN (32 + 4 + 32 + 4 + 32 + 40 + 5 + 1)
-
struct rt6_proc_arg
{
char *buffer;
net->ipv6.ip6_null_entry->dst.path =
(struct dst_entry *)net->ipv6.ip6_null_entry;
net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops;
+ dst_init_metrics(&net->ipv6.ip6_null_entry->dst,
+ ip6_template_metrics, true);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template,
net->ipv6.ip6_prohibit_entry->dst.path =
(struct dst_entry *)net->ipv6.ip6_prohibit_entry;
net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops;
+ dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst,
+ ip6_template_metrics, true);
net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template,
sizeof(*net->ipv6.ip6_blk_hole_entry),
net->ipv6.ip6_blk_hole_entry->dst.path =
(struct dst_entry *)net->ipv6.ip6_blk_hole_entry;
net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops;
+ dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst,
+ ip6_template_metrics, true);
#endif
net->ipv6.sysctl.flush_delay = 0;
projects / ~andy / linux / blobdiff