summaryrefslogtreecommitdiffstats
path: root/net/ipv6/route.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6/route.c')
-rw-r--r--net/ipv6/route.c1895
1 files changed, 1028 insertions, 867 deletions
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index a6598762d2c17..fb956989adaf4 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -63,14 +63,20 @@
#include <net/lwtunnel.h>
#include <net/ip_tunnels.h>
#include <net/l3mdev.h>
-#include <trace/events/fib6.h>
-
+#include <net/ip.h>
#include <linux/uaccess.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
+static int ip6_rt_type_to_error(u8 fib6_type);
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/fib6.h>
+EXPORT_TRACEPOINT_SYMBOL_GPL(fib6_table_lookup);
+#undef CREATE_TRACE_POINTS
+
enum rt6_nud_state {
RT6_NUD_FAIL_HARD = -3,
RT6_NUD_FAIL_PROBE = -2,
@@ -78,7 +84,6 @@ enum rt6_nud_state {
RT6_NUD_SUCCEED = 1
};
-static void ip6_rt_copy_init(struct rt6_info *rt, 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_mtu(const struct dst_entry *dst);
@@ -97,25 +102,24 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu);
static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
-static void rt6_dst_from_metrics_check(struct rt6_info *rt);
-static int rt6_score_route(struct rt6_info *rt, int oif, int strict);
-static size_t rt6_nlmsg_size(struct rt6_info *rt);
-static int rt6_fill_node(struct net *net,
- struct sk_buff *skb, struct rt6_info *rt,
- struct in6_addr *dst, struct in6_addr *src,
+static int rt6_score_route(struct fib6_info *rt, int oif, int strict);
+static size_t rt6_nlmsg_size(struct fib6_info *rt);
+static int rt6_fill_node(struct net *net, struct sk_buff *skb,
+ struct fib6_info *rt, struct dst_entry *dst,
+ struct in6_addr *dest, struct in6_addr *src,
int iif, int type, u32 portid, u32 seq,
unsigned int flags);
-static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
+static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt,
struct in6_addr *daddr,
struct in6_addr *saddr);
#ifdef CONFIG_IPV6_ROUTE_INFO
-static struct rt6_info *rt6_add_route_info(struct net *net,
+static struct fib6_info *rt6_add_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr,
struct net_device *dev,
unsigned int pref);
-static struct rt6_info *rt6_get_route_info(struct net *net,
+static struct fib6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr,
struct net_device *dev);
@@ -184,29 +188,10 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev)
}
}
-static u32 *rt6_pcpu_cow_metrics(struct rt6_info *rt)
-{
- return dst_metrics_write_ptr(&rt->from->dst);
-}
-
-static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
-{
- struct rt6_info *rt = (struct rt6_info *)dst;
-
- if (rt->rt6i_flags & RTF_PCPU)
- return rt6_pcpu_cow_metrics(rt);
- else if (rt->rt6i_flags & RTF_CACHE)
- return NULL;
- else
- return dst_cow_metrics_generic(dst, old);
-}
-
-static inline const void *choose_neigh_daddr(struct rt6_info *rt,
+static inline const void *choose_neigh_daddr(const struct in6_addr *p,
struct sk_buff *skb,
const void *daddr)
{
- struct in6_addr *p = &rt->rt6i_gateway;
-
if (!ipv6_addr_any(p))
return (const void *) p;
else if (skb)
@@ -214,18 +199,27 @@ static inline const void *choose_neigh_daddr(struct rt6_info *rt,
return daddr;
}
-static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst,
- struct sk_buff *skb,
- const void *daddr)
+struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw,
+ struct net_device *dev,
+ struct sk_buff *skb,
+ const void *daddr)
{
- struct rt6_info *rt = (struct rt6_info *) dst;
struct neighbour *n;
- daddr = choose_neigh_daddr(rt, skb, daddr);
- n = __ipv6_neigh_lookup(dst->dev, daddr);
+ daddr = choose_neigh_daddr(gw, skb, daddr);
+ n = __ipv6_neigh_lookup(dev, daddr);
if (n)
return n;
- return neigh_create(&nd_tbl, daddr, dst->dev);
+ return neigh_create(&nd_tbl, daddr, dev);
+}
+
+static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst,
+ struct sk_buff *skb,
+ const void *daddr)
+{
+ const struct rt6_info *rt = container_of(dst, struct rt6_info, dst);
+
+ return ip6_neigh_lookup(&rt->rt6i_gateway, dst->dev, skb, daddr);
}
static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr)
@@ -233,7 +227,7 @@ static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr)
struct net_device *dev = dst->dev;
struct rt6_info *rt = (struct rt6_info *)dst;
- daddr = choose_neigh_daddr(rt, NULL, daddr);
+ daddr = choose_neigh_daddr(&rt->rt6i_gateway, NULL, daddr);
if (!daddr)
return;
if (dev->flags & (IFF_NOARP | IFF_LOOPBACK))
@@ -250,7 +244,7 @@ static struct dst_ops ip6_dst_ops_template = {
.check = ip6_dst_check,
.default_advmss = ip6_default_advmss,
.mtu = ip6_mtu,
- .cow_metrics = ipv6_cow_metrics,
+ .cow_metrics = dst_cow_metrics_generic,
.destroy = ip6_dst_destroy,
.ifdown = ip6_dst_ifdown,
.negative_advice = ip6_negative_advice,
@@ -258,7 +252,7 @@ static struct dst_ops ip6_dst_ops_template = {
.update_pmtu = ip6_rt_update_pmtu,
.redirect = rt6_do_redirect,
.local_out = __ip6_local_out,
- .neigh_lookup = ip6_neigh_lookup,
+ .neigh_lookup = ip6_dst_neigh_lookup,
.confirm_neigh = ip6_confirm_neigh,
};
@@ -288,13 +282,22 @@ static struct dst_ops ip6_dst_blackhole_ops = {
.update_pmtu = ip6_rt_blackhole_update_pmtu,
.redirect = ip6_rt_blackhole_redirect,
.cow_metrics = dst_cow_metrics_generic,
- .neigh_lookup = ip6_neigh_lookup,
+ .neigh_lookup = ip6_dst_neigh_lookup,
};
static const u32 ip6_template_metrics[RTAX_MAX] = {
[RTAX_HOPLIMIT - 1] = 0,
};
+static const struct fib6_info fib6_null_entry_template = {
+ .fib6_flags = (RTF_REJECT | RTF_NONEXTHOP),
+ .fib6_protocol = RTPROT_KERNEL,
+ .fib6_metric = ~(u32)0,
+ .fib6_ref = ATOMIC_INIT(1),
+ .fib6_type = RTN_UNREACHABLE,
+ .fib6_metrics = (struct dst_metrics *)&dst_default_metrics,
+};
+
static const struct rt6_info ip6_null_entry_template = {
.dst = {
.__refcnt = ATOMIC_INIT(1),
@@ -305,9 +308,6 @@ static const struct rt6_info ip6_null_entry_template = {
.output = ip6_pkt_discard_out,
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
- .rt6i_protocol = RTPROT_KERNEL,
- .rt6i_metric = ~(u32) 0,
- .rt6i_ref = ATOMIC_INIT(1),
};
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
@@ -322,9 +322,6 @@ static const struct rt6_info ip6_prohibit_entry_template = {
.output = ip6_pkt_prohibit_out,
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
- .rt6i_protocol = RTPROT_KERNEL,
- .rt6i_metric = ~(u32) 0,
- .rt6i_ref = ATOMIC_INIT(1),
};
static const struct rt6_info ip6_blk_hole_entry_template = {
@@ -337,9 +334,6 @@ static const struct rt6_info ip6_blk_hole_entry_template = {
.output = dst_discard_out,
},
.rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP),
- .rt6i_protocol = RTPROT_KERNEL,
- .rt6i_metric = ~(u32) 0,
- .rt6i_ref = ATOMIC_INIT(1),
};
#endif
@@ -349,14 +343,12 @@ static void rt6_info_init(struct rt6_info *rt)
struct dst_entry *dst = &rt->dst;
memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
- INIT_LIST_HEAD(&rt->rt6i_siblings);
INIT_LIST_HEAD(&rt->rt6i_uncached);
}
/* allocate dst with ip6_dst_ops */
-static struct rt6_info *__ip6_dst_alloc(struct net *net,
- struct net_device *dev,
- int flags)
+struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
+ int flags)
{
struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
1, DST_OBSOLETE_FORCE_CHK, flags);
@@ -368,34 +360,15 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net,
return rt;
}
-
-struct rt6_info *ip6_dst_alloc(struct net *net,
- struct net_device *dev,
- int flags)
-{
- struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags);
-
- if (rt) {
- rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC);
- if (!rt->rt6i_pcpu) {
- dst_release_immediate(&rt->dst);
- return NULL;
- }
- }
-
- return rt;
-}
EXPORT_SYMBOL(ip6_dst_alloc);
static void ip6_dst_destroy(struct dst_entry *dst)
{
struct rt6_info *rt = (struct rt6_info *)dst;
- struct rt6_exception_bucket *bucket;
- struct rt6_info *from = rt->from;
+ struct fib6_info *from;
struct inet6_dev *idev;
dst_destroy_metrics_generic(dst);
- free_percpu(rt->rt6i_pcpu);
rt6_uncached_list_del(rt);
idev = rt->rt6i_idev;
@@ -403,14 +376,12 @@ static void ip6_dst_destroy(struct dst_entry *dst)
rt->rt6i_idev = NULL;
in6_dev_put(idev);
}
- bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, 1);
- if (bucket) {
- rt->rt6i_exception_bucket = NULL;
- kfree(bucket);
- }
- rt->from = NULL;
- dst_release(&from->dst);
+ rcu_read_lock();
+ from = rcu_dereference(rt->from);
+ rcu_assign_pointer(rt->from, NULL);
+ fib6_info_release(from);
+ rcu_read_unlock();
}
static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -440,23 +411,27 @@ static bool __rt6_check_expired(const struct rt6_info *rt)
static bool rt6_check_expired(const struct rt6_info *rt)
{
+ struct fib6_info *from;
+
+ from = rcu_dereference(rt->from);
+
if (rt->rt6i_flags & RTF_EXPIRES) {
if (time_after(jiffies, rt->dst.expires))
return true;
- } else if (rt->from) {
+ } else if (from) {
return rt->dst.obsolete != DST_OBSOLETE_FORCE_CHK ||
- rt6_check_expired(rt->from);
+ fib6_check_expired(from);
}
return false;
}
-static struct rt6_info *rt6_multipath_select(const struct net *net,
- struct rt6_info *match,
- struct flowi6 *fl6, int oif,
- const struct sk_buff *skb,
- int strict)
+struct fib6_info *fib6_multipath_select(const struct net *net,
+ struct fib6_info *match,
+ struct flowi6 *fl6, int oif,
+ const struct sk_buff *skb,
+ int strict)
{
- struct rt6_info *sibling, *next_sibling;
+ struct fib6_info *sibling, *next_sibling;
/* We might have already computed the hash for ICMPv6 errors. In such
* case it will always be non-zero. Otherwise now is the time to do it.
@@ -464,12 +439,15 @@ static struct rt6_info *rt6_multipath_select(const struct net *net,
if (!fl6->mp_hash)
fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL);
- if (fl6->mp_hash <= atomic_read(&match->rt6i_nh_upper_bound))
+ if (fl6->mp_hash <= atomic_read(&match->fib6_nh.nh_upper_bound))
return match;
- list_for_each_entry_safe(sibling, next_sibling, &match->rt6i_siblings,
- rt6i_siblings) {
- if (fl6->mp_hash > atomic_read(&sibling->rt6i_nh_upper_bound))
+ list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings,
+ fib6_siblings) {
+ int nh_upper_bound;
+
+ nh_upper_bound = atomic_read(&sibling->fib6_nh.nh_upper_bound);
+ if (fl6->mp_hash > nh_upper_bound)
continue;
if (rt6_score_route(sibling, oif, strict) < 0)
break;
@@ -484,38 +462,27 @@ static struct rt6_info *rt6_multipath_select(const struct net *net,
* Route lookup. rcu_read_lock() should be held.
*/
-static inline struct rt6_info *rt6_device_match(struct net *net,
- struct rt6_info *rt,
+static inline struct fib6_info *rt6_device_match(struct net *net,
+ struct fib6_info *rt,
const struct in6_addr *saddr,
int oif,
int flags)
{
- struct rt6_info *local = NULL;
- struct rt6_info *sprt;
+ struct fib6_info *sprt;
- if (!oif && ipv6_addr_any(saddr) && !(rt->rt6i_nh_flags & RTNH_F_DEAD))
+ if (!oif && ipv6_addr_any(saddr) &&
+ !(rt->fib6_nh.nh_flags & RTNH_F_DEAD))
return rt;
- for (sprt = rt; sprt; sprt = rcu_dereference(sprt->rt6_next)) {
- struct net_device *dev = sprt->dst.dev;
+ for (sprt = rt; sprt; sprt = rcu_dereference(sprt->fib6_next)) {
+ const struct net_device *dev = sprt->fib6_nh.nh_dev;
- if (sprt->rt6i_nh_flags & RTNH_F_DEAD)
+ if (sprt->fib6_nh.nh_flags & RTNH_F_DEAD)
continue;
if (oif) {
if (dev->ifindex == oif)
return sprt;
- if (dev->flags & IFF_LOOPBACK) {
- if (!sprt->rt6i_idev ||
- sprt->rt6i_idev->dev->ifindex != oif) {
- if (flags & RT6_LOOKUP_F_IFACE)
- continue;
- if (local &&
- local->rt6i_idev->dev->ifindex == oif)
- continue;
- }
- local = sprt;
- }
} else {
if (ipv6_chk_addr(net, saddr, dev,
flags & RT6_LOOKUP_F_IFACE))
@@ -523,15 +490,10 @@ static inline struct rt6_info *rt6_device_match(struct net *net,
}
}
- if (oif) {
- if (local)
- return local;
-
- if (flags & RT6_LOOKUP_F_IFACE)
- return net->ipv6.ip6_null_entry;
- }
+ if (oif && flags & RT6_LOOKUP_F_IFACE)
+ return net->ipv6.fib6_null_entry;
- return rt->rt6i_nh_flags & RTNH_F_DEAD ? net->ipv6.ip6_null_entry : rt;
+ return rt->fib6_nh.nh_flags & RTNH_F_DEAD ? net->ipv6.fib6_null_entry : rt;
}
#ifdef CONFIG_IPV6_ROUTER_PREF
@@ -553,10 +515,13 @@ static void rt6_probe_deferred(struct work_struct *w)
kfree(work);
}
-static void rt6_probe(struct rt6_info *rt)
+static void rt6_probe(struct fib6_info *rt)
{
struct __rt6_probe_work *work;
+ const struct in6_addr *nh_gw;
struct neighbour *neigh;
+ struct net_device *dev;
+
/*
* Okay, this does not seem to be appropriate
* for now, however, we need to check if it
@@ -565,20 +530,25 @@ static void rt6_probe(struct rt6_info *rt)
* Router Reachability Probe MUST be rate-limited
* to no more than one per minute.
*/
- if (!rt || !(rt->rt6i_flags & RTF_GATEWAY))
+ if (!rt || !(rt->fib6_flags & RTF_GATEWAY))
return;
+
+ nh_gw = &rt->fib6_nh.nh_gw;
+ dev = rt->fib6_nh.nh_dev;
rcu_read_lock_bh();
- neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway);
+ neigh = __ipv6_neigh_lookup_noref(dev, nh_gw);
if (neigh) {
+ struct inet6_dev *idev;
+
if (neigh->nud_state & NUD_VALID)
goto out;
+ idev = __in6_dev_get(dev);
work = NULL;
write_lock(&neigh->lock);
if (!(neigh->nud_state & NUD_VALID) &&
time_after(jiffies,
- neigh->updated +
- rt->rt6i_idev->cnf.rtr_probe_interval)) {
+ neigh->updated + idev->cnf.rtr_probe_interval)) {
work = kmalloc(sizeof(*work), GFP_ATOMIC);
if (work)
__neigh_set_probe_once(neigh);
@@ -590,9 +560,9 @@ static void rt6_probe(struct rt6_info *rt)
if (work) {
INIT_WORK(&work->work, rt6_probe_deferred);
- work->target = rt->rt6i_gateway;
- dev_hold(rt->dst.dev);
- work->dev = rt->dst.dev;
+ work->target = *nh_gw;
+ dev_hold(dev);
+ work->dev = dev;
schedule_work(&work->work);
}
@@ -600,7 +570,7 @@ out:
rcu_read_unlock_bh();
}
#else
-static inline void rt6_probe(struct rt6_info *rt)
+static inline void rt6_probe(struct fib6_info *rt)
{
}
#endif
@@ -608,28 +578,27 @@ static inline void rt6_probe(struct rt6_info *rt)
/*
* Default Router Selection (RFC 2461 6.3.6)
*/
-static inline int rt6_check_dev(struct rt6_info *rt, int oif)
+static inline int rt6_check_dev(struct fib6_info *rt, int oif)
{
- struct net_device *dev = rt->dst.dev;
+ const struct net_device *dev = rt->fib6_nh.nh_dev;
+
if (!oif || dev->ifindex == oif)
return 2;
- if ((dev->flags & IFF_LOOPBACK) &&
- rt->rt6i_idev && rt->rt6i_idev->dev->ifindex == oif)
- return 1;
return 0;
}
-static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt)
+static inline enum rt6_nud_state rt6_check_neigh(struct fib6_info *rt)
{
- struct neighbour *neigh;
enum rt6_nud_state ret = RT6_NUD_FAIL_HARD;
+ struct neighbour *neigh;
- if (rt->rt6i_flags & RTF_NONEXTHOP ||
- !(rt->rt6i_flags & RTF_GATEWAY))
+ if (rt->fib6_flags & RTF_NONEXTHOP ||
+ !(rt->fib6_flags & RTF_GATEWAY))
return RT6_NUD_SUCCEED;
rcu_read_lock_bh();
- neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway);
+ neigh = __ipv6_neigh_lookup_noref(rt->fib6_nh.nh_dev,
+ &rt->fib6_nh.nh_gw);
if (neigh) {
read_lock(&neigh->lock);
if (neigh->nud_state & NUD_VALID)
@@ -650,8 +619,7 @@ static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt)
return ret;
}
-static int rt6_score_route(struct rt6_info *rt, int oif,
- int strict)
+static int rt6_score_route(struct fib6_info *rt, int oif, int strict)
{
int m;
@@ -659,7 +627,7 @@ static int rt6_score_route(struct rt6_info *rt, int oif,
if (!m && (strict & RT6_LOOKUP_F_IFACE))
return RT6_NUD_FAIL_HARD;
#ifdef CONFIG_IPV6_ROUTER_PREF
- m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2;
+ m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->fib6_flags)) << 2;
#endif
if (strict & RT6_LOOKUP_F_REACHABLE) {
int n = rt6_check_neigh(rt);
@@ -669,23 +637,37 @@ static int rt6_score_route(struct rt6_info *rt, int oif,
return m;
}
-static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
- int *mpri, struct rt6_info *match,
+/* called with rc_read_lock held */
+static inline bool fib6_ignore_linkdown(const struct fib6_info *f6i)
+{
+ const struct net_device *dev = fib6_info_nh_dev(f6i);
+ bool rc = false;
+
+ if (dev) {
+ const struct inet6_dev *idev = __in6_dev_get(dev);
+
+ rc = !!idev->cnf.ignore_routes_with_linkdown;
+ }
+
+ return rc;
+}
+
+static struct fib6_info *find_match(struct fib6_info *rt, int oif, int strict,
+ int *mpri, struct fib6_info *match,
bool *do_rr)
{
int m;
bool match_do_rr = false;
- struct inet6_dev *idev = rt->rt6i_idev;
- if (rt->rt6i_nh_flags & RTNH_F_DEAD)
+ if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
goto out;
- if (idev->cnf.ignore_routes_with_linkdown &&
- rt->rt6i_nh_flags & RTNH_F_LINKDOWN &&
+ if (fib6_ignore_linkdown(rt) &&
+ rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN &&
!(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE))
goto out;
- if (rt6_check_expired(rt))
+ if (fib6_check_expired(rt))
goto out;
m = rt6_score_route(rt, oif, strict);
@@ -709,19 +691,19 @@ out:
return match;
}
-static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
- struct rt6_info *leaf,
- struct rt6_info *rr_head,
+static struct fib6_info *find_rr_leaf(struct fib6_node *fn,
+ struct fib6_info *leaf,
+ struct fib6_info *rr_head,
u32 metric, int oif, int strict,
bool *do_rr)
{
- struct rt6_info *rt, *match, *cont;
+ struct fib6_info *rt, *match, *cont;
int mpri = -1;
match = NULL;
cont = NULL;
- for (rt = rr_head; rt; rt = rcu_dereference(rt->rt6_next)) {
- if (rt->rt6i_metric != metric) {
+ for (rt = rr_head; rt; rt = rcu_dereference(rt->fib6_next)) {
+ if (rt->fib6_metric != metric) {
cont = rt;
break;
}
@@ -730,8 +712,8 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
}
for (rt = leaf; rt && rt != rr_head;
- rt = rcu_dereference(rt->rt6_next)) {
- if (rt->rt6i_metric != metric) {
+ rt = rcu_dereference(rt->fib6_next)) {
+ if (rt->fib6_metric != metric) {
cont = rt;
break;
}
@@ -742,22 +724,22 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
if (match || !cont)
return match;
- for (rt = cont; rt; rt = rcu_dereference(rt->rt6_next))
+ for (rt = cont; rt; rt = rcu_dereference(rt->fib6_next))
match = find_match(rt, oif, strict, &mpri, match, do_rr);
return match;
}
-static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn,
+static struct fib6_info *rt6_select(struct net *net, struct fib6_node *fn,
int oif, int strict)
{
- struct rt6_info *leaf = rcu_dereference(fn->leaf);
- struct rt6_info *match, *rt0;
+ struct fib6_info *leaf = rcu_dereference(fn->leaf);
+ struct fib6_info *match, *rt0;
bool do_rr = false;
int key_plen;
- if (!leaf || leaf == net->ipv6.ip6_null_entry)
- return net->ipv6.ip6_null_entry;
+ if (!leaf || leaf == net->ipv6.fib6_null_entry)
+ return net->ipv6.fib6_null_entry;
rt0 = rcu_dereference(fn->rr_ptr);
if (!rt0)
@@ -768,39 +750,39 @@ static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn,
* (This might happen if all routes under fn are deleted from
* the tree and fib6_repair_tree() is called on the node.)
*/
- key_plen = rt0->rt6i_dst.plen;
+ key_plen = rt0->fib6_dst.plen;
#ifdef CONFIG_IPV6_SUBTREES
- if (rt0->rt6i_src.plen)
- key_plen = rt0->rt6i_src.plen;
+ if (rt0->fib6_src.plen)
+ key_plen = rt0->fib6_src.plen;
#endif
if (fn->fn_bit != key_plen)
- return net->ipv6.ip6_null_entry;
+ return net->ipv6.fib6_null_entry;
- match = find_rr_leaf(fn, leaf, rt0, rt0->rt6i_metric, oif, strict,
+ match = find_rr_leaf(fn, leaf, rt0, rt0->fib6_metric, oif, strict,
&do_rr);
if (do_rr) {
- struct rt6_info *next = rcu_dereference(rt0->rt6_next);
+ struct fib6_info *next = rcu_dereference(rt0->fib6_next);
/* no entries matched; do round-robin */
- if (!next || next->rt6i_metric != rt0->rt6i_metric)
+ if (!next || next->fib6_metric != rt0->fib6_metric)
next = leaf;
if (next != rt0) {
- spin_lock_bh(&leaf->rt6i_table->tb6_lock);
+ spin_lock_bh(&leaf->fib6_table->tb6_lock);
/* make sure next is not being deleted from the tree */
- if (next->rt6i_node)
+ if (next->fib6_node)
rcu_assign_pointer(fn->rr_ptr, next);
- spin_unlock_bh(&leaf->rt6i_table->tb6_lock);
+ spin_unlock_bh(&leaf->fib6_table->tb6_lock);
}
}
- return match ? match : net->ipv6.ip6_null_entry;
+ return match ? match : net->ipv6.fib6_null_entry;
}
-static bool rt6_is_gw_or_nonexthop(const struct rt6_info *rt)
+static bool rt6_is_gw_or_nonexthop(const struct fib6_info *rt)
{
- return (rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY));
+ return (rt->fib6_flags & (RTF_NONEXTHOP | RTF_GATEWAY));
}
#ifdef CONFIG_IPV6_ROUTE_INFO
@@ -812,7 +794,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
struct in6_addr prefix_buf, *prefix;
unsigned int pref;
unsigned long lifetime;
- struct rt6_info *rt;
+ struct fib6_info *rt;
if (len < sizeof(struct route_info)) {
return -EINVAL;
@@ -850,13 +832,13 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
}
if (rinfo->prefix_len == 0)
- rt = rt6_get_dflt_router(gwaddr, dev);
+ rt = rt6_get_dflt_router(net, gwaddr, dev);
else
rt = rt6_get_route_info(net, prefix, rinfo->prefix_len,
gwaddr, dev);
if (rt && !lifetime) {
- ip6_del_rt(rt);
+ ip6_del_rt(net, rt);
rt = NULL;
}
@@ -864,21 +846,162 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr,
dev, pref);
else if (rt)
- rt->rt6i_flags = RTF_ROUTEINFO |
- (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
+ rt->fib6_flags = RTF_ROUTEINFO |
+ (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
if (rt) {
if (!addrconf_finite_timeout(lifetime))
- rt6_clean_expires(rt);
+ fib6_clean_expires(rt);
else
- rt6_set_expires(rt, jiffies + HZ * lifetime);
+ fib6_set_expires(rt, jiffies + HZ * lifetime);
- ip6_rt_put(rt);
+ fib6_info_release(rt);
}
return 0;
}
#endif
+/*
+ * Misc support functions
+ */
+
+/* called with rcu_lock held */
+static struct net_device *ip6_rt_get_dev_rcu(struct fib6_info *rt)
+{
+ struct net_device *dev = rt->fib6_nh.nh_dev;
+
+ if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) {
+ /* for copies of local routes, dst->dev needs to be the
+ * device if it is a master device, the master device if
+ * device is enslaved, and the loopback as the default
+ */
+ if (netif_is_l3_slave(dev) &&
+ !rt6_need_strict(&rt->fib6_dst.addr))
+ dev = l3mdev_master_dev_rcu(dev);
+ else if (!netif_is_l3_master(dev))
+ dev = dev_net(dev)->loopback_dev;
+ /* last case is netif_is_l3_master(dev) is true in which
+ * case we want dev returned to be dev
+ */
+ }
+
+ return dev;
+}
+
+static const int fib6_prop[RTN_MAX + 1] = {
+ [RTN_UNSPEC] = 0,
+ [RTN_UNICAST] = 0,
+ [RTN_LOCAL] = 0,
+ [RTN_BROADCAST] = 0,
+ [RTN_ANYCAST] = 0,
+ [RTN_MULTICAST] = 0,
+ [RTN_BLACKHOLE] = -EINVAL,
+ [RTN_UNREACHABLE] = -EHOSTUNREACH,
+ [RTN_PROHIBIT] = -EACCES,
+ [RTN_THROW] = -EAGAIN,
+ [RTN_NAT] = -EINVAL,
+ [RTN_XRESOLVE] = -EINVAL,
+};
+
+static int ip6_rt_type_to_error(u8 fib6_type)
+{
+ return fib6_prop[fib6_type];
+}
+
+static unsigned short fib6_info_dst_flags(struct fib6_info *rt)
+{
+ unsigned short flags = 0;
+
+ if (rt->dst_nocount)
+ flags |= DST_NOCOUNT;
+ if (rt->dst_nopolicy)
+ flags |= DST_NOPOLICY;
+ if (rt->dst_host)
+ flags |= DST_HOST;
+
+ return flags;
+}
+
+static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort)
+{
+ rt->dst.error = ip6_rt_type_to_error(ort->fib6_type);
+
+ switch (ort->fib6_type) {
+ case RTN_BLACKHOLE:
+ rt->dst.output = dst_discard_out;
+ rt->dst.input = dst_discard;
+ break;
+ case RTN_PROHIBIT:
+ rt->dst.output = ip6_pkt_prohibit_out;
+ rt->dst.input = ip6_pkt_prohibit;
+ break;
+ case RTN_THROW:
+ case RTN_UNREACHABLE:
+ default:
+ rt->dst.output = ip6_pkt_discard_out;
+ rt->dst.input = ip6_pkt_discard;
+ break;
+ }
+}
+
+static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort)
+{
+ rt->dst.flags |= fib6_info_dst_flags(ort);
+
+ if (ort->fib6_flags & RTF_REJECT) {
+ ip6_rt_init_dst_reject(rt, ort);
+ return;
+ }
+
+ rt->dst.error = 0;
+ rt->dst.output = ip6_output;
+
+ if (ort->fib6_type == RTN_LOCAL) {
+ rt->dst.input = ip6_input;
+ } else if (ipv6_addr_type(&ort->fib6_dst.addr) & IPV6_ADDR_MULTICAST) {
+ rt->dst.input = ip6_mc_input;
+ } else {
+ rt->dst.input = ip6_forward;
+ }
+
+ if (ort->fib6_nh.nh_lwtstate) {
+ rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate);
+ lwtunnel_set_redirect(&rt->dst);
+ }
+
+ rt->dst.lastuse = jiffies;
+}
+
+static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from)
+{
+ rt->rt6i_flags &= ~RTF_EXPIRES;
+ fib6_info_hold(from);
+ rcu_assign_pointer(rt->from, from);
+ dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true);
+ if (from->fib6_metrics != &dst_default_metrics) {
+ rt->dst._metrics |= DST_METRICS_REFCOUNTED;
+ refcount_inc(&from->fib6_metrics->refcnt);
+ }
+}
+
+static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort)
+{
+ struct net_device *dev = fib6_info_nh_dev(ort);
+
+ ip6_rt_init_dst(rt, ort);
+
+ rt->rt6i_dst = ort->fib6_dst;
+ rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL;
+ rt->rt6i_gateway = ort->fib6_nh.nh_gw;
+ rt->rt6i_flags = ort->fib6_flags;
+ rt6_set_from(rt, ort);
+#ifdef CONFIG_IPV6_SUBTREES
+ rt->rt6i_src = ort->fib6_src;
+#endif
+ rt->rt6i_prefsrc = ort->fib6_prefsrc;
+ rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate);
+}
+
static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
struct in6_addr *saddr)
{
@@ -889,7 +1012,7 @@ static struct fib6_node* fib6_backtrack(struct fib6_node *fn,
pn = rcu_dereference(fn->parent);
sn = FIB6_SUBTREE(pn);
if (sn && sn != fn)
- fn = fib6_lookup(sn, NULL, saddr);
+ fn = fib6_node_lookup(sn, NULL, saddr);
else
fn = pn;
if (fn->fn_flags & RTN_RTINFO)
@@ -914,50 +1037,74 @@ static bool ip6_hold_safe(struct net *net, struct rt6_info **prt,
return false;
}
+/* called with rcu_lock held */
+static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt)
+{
+ unsigned short flags = fib6_info_dst_flags(rt);
+ struct net_device *dev = rt->fib6_nh.nh_dev;
+ struct rt6_info *nrt;
+
+ nrt = ip6_dst_alloc(dev_net(dev), dev, flags);
+ if (nrt)
+ ip6_rt_copy_init(nrt, rt);
+
+ return nrt;
+}
+
static struct rt6_info *ip6_pol_route_lookup(struct net *net,
struct fib6_table *table,
struct flowi6 *fl6,
const struct sk_buff *skb,
int flags)
{
- struct rt6_info *rt, *rt_cache;
+ struct fib6_info *f6i;
struct fib6_node *fn;
+ struct rt6_info *rt;
if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF)
flags &= ~RT6_LOOKUP_F_IFACE;
rcu_read_lock();
- fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
+ fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
restart:
- rt = rcu_dereference(fn->leaf);
- if (!rt) {
- rt = net->ipv6.ip6_null_entry;
+ f6i = rcu_dereference(fn->leaf);
+ if (!f6i) {
+ f6i = net->ipv6.fib6_null_entry;
} else {
- rt = rt6_device_match(net, rt, &fl6->saddr,
+ f6i = rt6_device_match(net, f6i, &fl6->saddr,
fl6->flowi6_oif, flags);
- if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0)
- rt = rt6_multipath_select(net, rt, fl6, fl6->flowi6_oif,
- skb, flags);
+ if (f6i->fib6_nsiblings && fl6->flowi6_oif == 0)
+ f6i = fib6_multipath_select(net, f6i, fl6,
+ fl6->flowi6_oif, skb,
+ flags);
}
- if (rt == net->ipv6.ip6_null_entry) {
+ if (f6i == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto restart;
}
- /* Search through exception table */
- rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr);
- if (rt_cache)
- rt = rt_cache;
- if (ip6_hold_safe(net, &rt, true))
- dst_use_noref(&rt->dst, jiffies);
+ trace_fib6_table_lookup(net, f6i, table, fl6);
- rcu_read_unlock();
+ /* Search through exception table */
+ rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
+ if (rt) {
+ if (ip6_hold_safe(net, &rt, true))
+ dst_use_noref(&rt->dst, jiffies);
+ } else if (f6i == net->ipv6.fib6_null_entry) {
+ rt = net->ipv6.ip6_null_entry;
+ dst_hold(&rt->dst);
+ } else {
+ rt = ip6_create_rt_rcu(f6i);
+ if (!rt) {
+ rt = net->ipv6.ip6_null_entry;
+ dst_hold(&rt->dst);
+ }
+ }
- trace_fib6_table_lookup(net, rt, table, fl6);
+ rcu_read_unlock();
return rt;
-
}
struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6,
@@ -999,55 +1146,28 @@ EXPORT_SYMBOL(rt6_lookup);
* Caller must hold dst before calling it.
*/
-static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info,
- struct mx6_config *mxc,
+static int __ip6_ins_rt(struct fib6_info *rt, struct nl_info *info,
struct netlink_ext_ack *extack)
{
int err;
struct fib6_table *table;
- table = rt->rt6i_table;
+ table = rt->fib6_table;
spin_lock_bh(&table->tb6_lock);
- err = fib6_add(&table->tb6_root, rt, info, mxc, extack);
+ err = fib6_add(&table->tb6_root, rt, info, extack);
spin_unlock_bh(&table->tb6_lock);
return err;
}
-int ip6_ins_rt(struct rt6_info *rt)
+int ip6_ins_rt(struct net *net, struct fib6_info *rt)
{
- struct nl_info info = { .nl_net = dev_net(rt->dst.dev), };
- struct mx6_config mxc = { .mx = NULL, };
+ struct nl_info info = { .nl_net = net, };
- /* Hold dst to account for the reference from the fib6 tree */
- dst_hold(&rt->dst);
- return __ip6_ins_rt(rt, &info, &mxc, NULL);
+ return __ip6_ins_rt(rt, &info, NULL);
}
-/* called with rcu_lock held */
-static struct net_device *ip6_rt_get_dev_rcu(struct rt6_info *rt)
-{
- struct net_device *dev = rt->dst.dev;
-
- if (rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) {
- /* for copies of local routes, dst->dev needs to be the
- * device if it is a master device, the master device if
- * device is enslaved, and the loopback as the default
- */
- if (netif_is_l3_slave(dev) &&
- !rt6_need_strict(&rt->rt6i_dst.addr))
- dev = l3mdev_master_dev_rcu(dev);
- else if (!netif_is_l3_master(dev))
- dev = dev_net(dev)->loopback_dev;
- /* last case is netif_is_l3_master(dev) is true in which
- * case we want dev returned to be dev
- */
- }
-
- return dev;
-}
-
-static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
+static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort,
const struct in6_addr *daddr,
const struct in6_addr *saddr)
{
@@ -1058,26 +1178,20 @@ static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
* Clone the route.
*/
- if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
- ort = ort->from;
-
- rcu_read_lock();
dev = ip6_rt_get_dev_rcu(ort);
- rt = __ip6_dst_alloc(dev_net(dev), dev, 0);
- rcu_read_unlock();
+ rt = ip6_dst_alloc(dev_net(dev), dev, 0);
if (!rt)
return NULL;
ip6_rt_copy_init(rt, ort);
rt->rt6i_flags |= RTF_CACHE;
- rt->rt6i_metric = 0;
rt->dst.flags |= DST_HOST;
rt->rt6i_dst.addr = *daddr;
rt->rt6i_dst.plen = 128;
if (!rt6_is_gw_or_nonexthop(ort)) {
- if (ort->rt6i_dst.plen != 128 &&
- ipv6_addr_equal(&ort->rt6i_dst.addr, daddr))
+ if (ort->fib6_dst.plen != 128 &&
+ ipv6_addr_equal(&ort->fib6_dst.addr, daddr))
rt->rt6i_flags |= RTF_ANYCAST;
#ifdef CONFIG_IPV6_SUBTREES
if (rt->rt6i_src.plen && saddr) {
@@ -1090,45 +1204,44 @@ static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
return rt;
}
-static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt)
+static struct rt6_info *ip6_rt_pcpu_alloc(struct fib6_info *rt)
{
+ unsigned short flags = fib6_info_dst_flags(rt);
struct net_device *dev;
struct rt6_info *pcpu_rt;
rcu_read_lock();
dev = ip6_rt_get_dev_rcu(rt);
- pcpu_rt = __ip6_dst_alloc(dev_net(dev), dev, rt->dst.flags);
+ pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags);
rcu_read_unlock();
if (!pcpu_rt)
return NULL;
ip6_rt_copy_init(pcpu_rt, rt);
- pcpu_rt->rt6i_protocol = rt->rt6i_protocol;
pcpu_rt->rt6i_flags |= RTF_PCPU;
return pcpu_rt;
}
/* It should be called with rcu_read_lock() acquired */
-static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt)
+static struct rt6_info *rt6_get_pcpu_route(struct fib6_info *rt)
{
struct rt6_info *pcpu_rt, **p;
p = this_cpu_ptr(rt->rt6i_pcpu);
pcpu_rt = *p;
- if (pcpu_rt && ip6_hold_safe(NULL, &pcpu_rt, false))
- rt6_dst_from_metrics_check(pcpu_rt);
+ if (pcpu_rt)
+ ip6_hold_safe(NULL, &pcpu_rt, false);
return pcpu_rt;
}
-static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt)
+static struct rt6_info *rt6_make_pcpu_route(struct net *net,
+ struct fib6_info *rt)
{
struct rt6_info *pcpu_rt, *prev, **p;
pcpu_rt = ip6_rt_pcpu_alloc(rt);
if (!pcpu_rt) {
- struct net *net = dev_net(rt->dst.dev);
-
dst_hold(&net->ipv6.ip6_null_entry->dst);
return net->ipv6.ip6_null_entry;
}
@@ -1138,7 +1251,6 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt)
prev = cmpxchg(p, NULL, pcpu_rt);
BUG_ON(prev);
- rt6_dst_from_metrics_check(pcpu_rt);
return pcpu_rt;
}
@@ -1158,9 +1270,8 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket,
return;
net = dev_net(rt6_ex->rt6i->dst.dev);
- rt6_ex->rt6i->rt6i_node = NULL;
hlist_del_rcu(&rt6_ex->hlist);
- rt6_release(rt6_ex->rt6i);
+ dst_release(&rt6_ex->rt6i->dst);
kfree_rcu(rt6_ex, rcu);
WARN_ON_ONCE(!bucket->depth);
bucket->depth--;
@@ -1268,20 +1379,36 @@ __rt6_find_exception_rcu(struct rt6_exception_bucket **bucket,
return NULL;
}
+static unsigned int fib6_mtu(const struct fib6_info *rt)
+{
+ unsigned int mtu;
+
+ if (rt->fib6_pmtu) {
+ mtu = rt->fib6_pmtu;
+ } else {
+ struct net_device *dev = fib6_info_nh_dev(rt);
+ struct inet6_dev *idev;
+
+ rcu_read_lock();
+ idev = __in6_dev_get(dev);
+ mtu = idev->cnf.mtu6;
+ rcu_read_unlock();
+ }
+
+ mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
+
+ return mtu - lwtunnel_headroom(rt->fib6_nh.nh_lwtstate, mtu);
+}
+
static int rt6_insert_exception(struct rt6_info *nrt,
- struct rt6_info *ort)
+ struct fib6_info *ort)
{
- struct net *net = dev_net(ort->dst.dev);
+ struct net *net = dev_net(nrt->dst.dev);
struct rt6_exception_bucket *bucket;
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
int err = 0;
- /* ort can't be a cache or pcpu route */
- if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
- ort = ort->from;
- WARN_ON_ONCE(ort->rt6i_flags & (RTF_CACHE | RTF_PCPU));
-
spin_lock_bh(&rt6_exception_lock);
if (ort->exception_bucket_flushed) {
@@ -1308,19 +1435,19 @@ static int rt6_insert_exception(struct rt6_info *nrt,
* Otherwise, the exception table is indexed by
* a hash of only rt6i_dst.
*/
- if (ort->rt6i_src.plen)
+ if (ort->fib6_src.plen)
src_key = &nrt->rt6i_src.addr;
#endif
/* Update rt6i_prefsrc as it could be changed
* in rt6_remove_prefsrc()
*/
- nrt->rt6i_prefsrc = ort->rt6i_prefsrc;
+ nrt->rt6i_prefsrc = ort->fib6_prefsrc;
/* rt6_mtu_change() might lower mtu on ort.
* Only insert this exception route if its mtu
* is less than ort's mtu value.
*/
- if (nrt->rt6i_pmtu >= dst_mtu(&ort->dst)) {
+ if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(ort)) {
err = -EINVAL;
goto out;
}
@@ -1337,8 +1464,6 @@ static int rt6_insert_exception(struct rt6_info *nrt,
}
rt6_ex->rt6i = nrt;
rt6_ex->stamp = jiffies;
- atomic_inc(&nrt->rt6i_ref);
- nrt->rt6i_node = ort->rt6i_node;
hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain);
bucket->depth++;
net->ipv6.rt6_stats->fib_rt_cache++;
@@ -1351,16 +1476,16 @@ out:
/* Update fn->fn_sernum to invalidate all cached dst */
if (!err) {
- spin_lock_bh(&ort->rt6i_table->tb6_lock);
- fib6_update_sernum(ort);
- spin_unlock_bh(&ort->rt6i_table->tb6_lock);
+ spin_lock_bh(&ort->fib6_table->tb6_lock);
+ fib6_update_sernum(net, ort);
+ spin_unlock_bh(&ort->fib6_table->tb6_lock);
fib6_force_start_gc(net);
}
return err;
}
-void rt6_flush_exceptions(struct rt6_info *rt)
+void rt6_flush_exceptions(struct fib6_info *rt)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
@@ -1390,7 +1515,7 @@ out:
/* Find cached rt in the hash table inside passed in rt
* Caller has to hold rcu_read_lock()
*/
-static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
+static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt,
struct in6_addr *daddr,
struct in6_addr *saddr)
{
@@ -1408,7 +1533,7 @@ static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
* Otherwise, the exception table is indexed by
* a hash of only rt6i_dst.
*/
- if (rt->rt6i_src.plen)
+ if (rt->fib6_src.plen)
src_key = saddr;
#endif
rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
@@ -1420,14 +1545,15 @@ static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt,
}
/* Remove the passed in cached rt from the hash table that contains it */
-int rt6_remove_exception_rt(struct rt6_info *rt)
+static int rt6_remove_exception_rt(struct rt6_info *rt)
{
struct rt6_exception_bucket *bucket;
- struct rt6_info *from = rt->from;
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
+ struct fib6_info *from;
int err;
+ from = rcu_dereference(rt->from);
if (!from ||
!(rt->rt6i_flags & RTF_CACHE))
return -EINVAL;
@@ -1445,7 +1571,7 @@ int rt6_remove_exception_rt(struct rt6_info *rt)
* Otherwise, the exception table is indexed by
* a hash of only rt6i_dst.
*/
- if (from->rt6i_src.plen)
+ if (from->fib6_src.plen)
src_key = &rt->rt6i_src.addr;
#endif
rt6_ex = __rt6_find_exception_spinlock(&bucket,
@@ -1468,7 +1594,7 @@ int rt6_remove_exception_rt(struct rt6_info *rt)
static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
{
struct rt6_exception_bucket *bucket;
- struct rt6_info *from = rt->from;
+ struct fib6_info *from = rt->from;
struct in6_addr *src_key = NULL;
struct rt6_exception *rt6_ex;
@@ -1486,7 +1612,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
* Otherwise, the exception table is indexed by
* a hash of only rt6i_dst.
*/
- if (from->rt6i_src.plen)
+ if (from->fib6_src.plen)
src_key = &rt->rt6i_src.addr;
#endif
rt6_ex = __rt6_find_exception_rcu(&bucket,
@@ -1498,7 +1624,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt)
rcu_read_unlock();
}
-static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt)
+static void rt6_exceptions_remove_prefsrc(struct fib6_info *rt)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
@@ -1540,7 +1666,7 @@ static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev,
}
static void rt6_exceptions_update_pmtu(struct inet6_dev *idev,
- struct rt6_info *rt, int mtu)
+ struct fib6_info *rt, int mtu)
{
struct rt6_exception_bucket *bucket;
struct rt6_exception *rt6_ex;
@@ -1557,12 +1683,12 @@ static void rt6_exceptions_update_pmtu(struct inet6_dev *idev,
struct rt6_info *entry = rt6_ex->rt6i;
/* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected
- * route), the metrics of its rt->dst.from have already
+ * route), the metrics of its rt->from have already
* been updated.
*/
- if (entry->rt6i_pmtu &&
+ if (dst_metric_raw(&entry->dst, RTAX_MTU) &&
rt6_mtu_change_route_allowed(idev, entry, mtu))
- entry->rt6i_pmtu = mtu;
+ dst_metric_set(&entry->dst, RTAX_MTU, mtu);
}
bucket++;
}
@@ -1570,7 +1696,7 @@ static void rt6_exceptions_update_pmtu(struct inet6_dev *idev,
#define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE)
-static void rt6_exceptions_clean_tohost(struct rt6_info *rt,
+static void rt6_exceptions_clean_tohost(struct fib6_info *rt,
struct in6_addr *gateway)
{
struct rt6_exception_bucket *bucket;
@@ -1649,7 +1775,7 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket,
gc_args->more++;
}
-void rt6_age_exceptions(struct rt6_info *rt,
+void rt6_age_exceptions(struct fib6_info *rt,
struct fib6_gc_args *gc_args,
unsigned long now)
{
@@ -1680,32 +1806,22 @@ void rt6_age_exceptions(struct rt6_info *rt,
rcu_read_unlock_bh();
}
-struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
- int oif, struct flowi6 *fl6,
- const struct sk_buff *skb, int flags)
+/* must be called with rcu lock held */
+struct fib6_info *fib6_table_lookup(struct net *net, struct fib6_table *table,
+ int oif, struct flowi6 *fl6, int strict)
{
struct fib6_node *fn, *saved_fn;
- struct rt6_info *rt, *rt_cache;
- int strict = 0;
+ struct fib6_info *f6i;
- strict |= flags & RT6_LOOKUP_F_IFACE;
- strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
- if (net->ipv6.devconf_all->forwarding == 0)
- strict |= RT6_LOOKUP_F_REACHABLE;
-
- rcu_read_lock();
-
- fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
+ fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
saved_fn = fn;
if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF)
oif = 0;
redo_rt6_select:
- rt = rt6_select(net, fn, oif, strict);
- if (rt->rt6i_nsiblings)
- rt = rt6_multipath_select(net, rt, fl6, oif, skb, strict);
- if (rt == net->ipv6.ip6_null_entry) {
+ f6i = rt6_select(net, fn, oif, strict);
+ if (f6i == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto redo_rt6_select;
@@ -1717,45 +1833,57 @@ redo_rt6_select:
}
}
- /*Search through exception table */
- rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr);
- if (rt_cache)
- rt = rt_cache;
+ trace_fib6_table_lookup(net, f6i, table, fl6);
- if (rt == net->ipv6.ip6_null_entry) {
+ return f6i;
+}
+
+struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
+ int oif, struct flowi6 *fl6,
+ const struct sk_buff *skb, int flags)
+{
+ struct fib6_info *f6i;
+ struct rt6_info *rt;
+ int strict = 0;
+
+ strict |= flags & RT6_LOOKUP_F_IFACE;
+ strict |= flags & RT6_LOOKUP_F_IGNORE_LINKSTATE;
+ if (net->ipv6.devconf_all->forwarding == 0)
+ strict |= RT6_LOOKUP_F_REACHABLE;
+
+ rcu_read_lock();
+
+ f6i = fib6_table_lookup(net, table, oif, fl6, strict);
+ if (f6i->fib6_nsiblings)
+ f6i = fib6_multipath_select(net, f6i, fl6, oif, skb, strict);
+
+ if (f6i == net->ipv6.fib6_null_entry) {
+ rt = net->ipv6.ip6_null_entry;
rcu_read_unlock();
dst_hold(&rt->dst);
- trace_fib6_table_lookup(net, rt, table, fl6);
return rt;
- } else if (rt->rt6i_flags & RTF_CACHE) {
- if (ip6_hold_safe(net, &rt, true)) {
+ }
+
+ /*Search through exception table */
+ rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr);
+ if (rt) {
+ if (ip6_hold_safe(net, &rt, true))
dst_use_noref(&rt->dst, jiffies);
- rt6_dst_from_metrics_check(rt);
- }
+
rcu_read_unlock();
- trace_fib6_table_lookup(net, rt, table, fl6);
return rt;
} else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) &&
- !(rt->rt6i_flags & RTF_GATEWAY))) {
+ !(f6i->fib6_flags & RTF_GATEWAY))) {
/* Create a RTF_CACHE clone which will not be
* owned by the fib6 tree. It is for the special case where
* the daddr in the skb during the neighbor look-up is different
* from the fl6->daddr used to look-up route here.
*/
-
struct rt6_info *uncached_rt;
- if (ip6_hold_safe(net, &rt, true)) {
- dst_use_noref(&rt->dst, jiffies);
- } else {
- rcu_read_unlock();
- uncached_rt = rt;
- goto uncached_rt_out;
- }
- rcu_read_unlock();
+ uncached_rt = ip6_rt_cache_alloc(f6i, &fl6->daddr, NULL);
- uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL);
- dst_release(&rt->dst);
+ rcu_read_unlock();
if (uncached_rt) {
/* Uncached_rt's refcnt is taken during ip6_rt_cache_alloc()
@@ -1768,36 +1896,21 @@ redo_rt6_select:
dst_hold(&uncached_rt->dst);
}
-uncached_rt_out:
- trace_fib6_table_lookup(net, uncached_rt, table, fl6);
return uncached_rt;
-
} else {
/* Get a percpu copy */
struct rt6_info *pcpu_rt;
- dst_use_noref(&rt->dst, jiffies);
local_bh_disable();
- pcpu_rt = rt6_get_pcpu_route(rt);
-
- if (!pcpu_rt) {
- /* atomic_inc_not_zero() is needed when using rcu */
- if (atomic_inc_not_zero(&rt->rt6i_ref)) {
- /* No dst_hold() on rt is needed because grabbing
- * rt->rt6i_ref makes sure rt can't be released.
- */
- pcpu_rt = rt6_make_pcpu_route(rt);
- rt6_release(rt);
- } else {
- /* rt is already removed from tree */
- pcpu_rt = net->ipv6.ip6_null_entry;
- dst_hold(&pcpu_rt->dst);
- }
- }
+ pcpu_rt = rt6_get_pcpu_route(f6i);
+
+ if (!pcpu_rt)
+ pcpu_rt = rt6_make_pcpu_route(net, f6i);
+
local_bh_enable();
rcu_read_unlock();
- trace_fib6_table_lookup(net, pcpu_rt, table, fl6);
+
return pcpu_rt;
}
}
@@ -1868,7 +1981,7 @@ out:
} else {
keys->addrs.v6addrs.src = key_iph->saddr;
keys->addrs.v6addrs.dst = key_iph->daddr;
- keys->tags.flow_label = ip6_flowinfo(key_iph);
+ keys->tags.flow_label = ip6_flowlabel(key_iph);
keys->basic.ip_proto = key_iph->nexthdr;
}
}
@@ -1889,7 +2002,7 @@ u32 rt6_multipath_hash(const struct net *net, const struct flowi6 *fl6,
} else {
hash_keys.addrs.v6addrs.src = fl6->saddr;
hash_keys.addrs.v6addrs.dst = fl6->daddr;
- hash_keys.tags.flow_label = (__force u32)fl6->flowlabel;
+ hash_keys.tags.flow_label = (__force u32)flowi6_get_flowlabel(fl6);
hash_keys.basic.ip_proto = fl6->flowi6_proto;
}
break;
@@ -2020,7 +2133,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
rt->rt6i_idev = in6_dev_get(loopback_dev);
rt->rt6i_gateway = ort->rt6i_gateway;
rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU;
- rt->rt6i_metric = 0;
memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key));
#ifdef CONFIG_IPV6_SUBTREES
@@ -2036,18 +2148,27 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
* Destination cache support functions
*/
-static void rt6_dst_from_metrics_check(struct rt6_info *rt)
+static bool fib6_check(struct fib6_info *f6i, u32 cookie)
{
- if (rt->from &&
- dst_metrics_ptr(&rt->dst) != dst_metrics_ptr(&rt->from->dst))
- dst_init_metrics(&rt->dst, dst_metrics_ptr(&rt->from->dst), true);
+ u32 rt_cookie = 0;
+
+ if (!fib6_get_cookie_safe(f6i, &rt_cookie) || rt_cookie != cookie)
+ return false;
+
+ if (fib6_check_expired(f6i))
+ return false;
+
+ return true;
}
-static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
+static struct dst_entry *rt6_check(struct rt6_info *rt,
+ struct fib6_info *from,
+ u32 cookie)
{
u32 rt_cookie = 0;
- if (!rt6_get_cookie_safe(rt, &rt_cookie) || rt_cookie != cookie)
+ if ((from && !fib6_get_cookie_safe(from, &rt_cookie)) ||
+ rt_cookie != cookie)
return NULL;
if (rt6_check_expired(rt))
@@ -2056,11 +2177,13 @@ static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie)
return &rt->dst;
}
-static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie)
+static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt,
+ struct fib6_info *from,
+ u32 cookie)
{
if (!__rt6_check_expired(rt) &&
rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK &&
- rt6_check(rt->from, cookie))
+ fib6_check(from, cookie))
return &rt->dst;
else
return NULL;
@@ -2068,22 +2191,30 @@ static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie)
static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
{
+ struct dst_entry *dst_ret;
+ struct fib6_info *from;
struct rt6_info *rt;
- rt = (struct rt6_info *) dst;
+ rt = container_of(dst, struct rt6_info, dst);
+
+ rcu_read_lock();
/* All IPV6 dsts are created with ->obsolete set to the value
* DST_OBSOLETE_FORCE_CHK which forces validation calls down
* into this function always.
*/
- rt6_dst_from_metrics_check(rt);
+ from = rcu_dereference(rt->from);
- if (rt->rt6i_flags & RTF_PCPU ||
- (unlikely(!list_empty(&rt->rt6i_uncached)) && rt->from))
- return rt6_dst_from_check(rt, cookie);
+ if (from && (rt->rt6i_flags & RTF_PCPU ||
+ unlikely(!list_empty(&rt->rt6i_uncached))))
+ dst_ret = rt6_dst_from_check(rt, from, cookie);
else
- return rt6_check(rt, cookie);
+ dst_ret = rt6_check(rt, from, cookie);
+
+ rcu_read_unlock();
+
+ return dst_ret;
}
static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
@@ -2092,10 +2223,12 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
if (rt) {
if (rt->rt6i_flags & RTF_CACHE) {
+ rcu_read_lock();
if (rt6_check_expired(rt)) {
- ip6_del_rt(rt);
+ rt6_remove_exception_rt(rt);
dst = NULL;
}
+ rcu_read_unlock();
} else {
dst_release(dst);
dst = NULL;
@@ -2112,35 +2245,60 @@ static void ip6_link_failure(struct sk_buff *skb)
rt = (struct rt6_info *) skb_dst(skb);
if (rt) {
+ rcu_read_lock();
if (rt->rt6i_flags & RTF_CACHE) {
if (dst_hold_safe(&rt->dst))
- ip6_del_rt(rt);
+ rt6_remove_exception_rt(rt);
} else {
+ struct fib6_info *from;
struct fib6_node *fn;
- rcu_read_lock();
- fn = rcu_dereference(rt->rt6i_node);
- if (fn && (rt->rt6i_flags & RTF_DEFAULT))
- fn->fn_sernum = -1;
- rcu_read_unlock();
+ from = rcu_dereference(rt->from);
+ if (from) {
+ fn = rcu_dereference(from->fib6_node);
+ if (fn && (rt->rt6i_flags & RTF_DEFAULT))
+ fn->fn_sernum = -1;
+ }
}
+ rcu_read_unlock();
}
}
+static void rt6_update_expires(struct rt6_info *rt0, int timeout)
+{
+ if (!(rt0->rt6i_flags & RTF_EXPIRES)) {
+ struct fib6_info *from;
+
+ rcu_read_lock();
+ from = rcu_dereference(rt0->from);
+ if (from)
+ rt0->dst.expires = from->expires;
+ rcu_read_unlock();
+ }
+
+ dst_set_expires(&rt0->dst, timeout);
+ rt0->rt6i_flags |= RTF_EXPIRES;
+}
+
static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
{
struct net *net = dev_net(rt->dst.dev);
+ dst_metric_set(&rt->dst, RTAX_MTU, mtu);
rt->rt6i_flags |= RTF_MODIFIED;
- rt->rt6i_pmtu = mtu;
rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
}
static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
{
+ bool from_set;
+
+ rcu_read_lock();
+ from_set = !!rcu_dereference(rt->from);
+ rcu_read_unlock();
+
return !(rt->rt6i_flags & RTF_CACHE) &&
- (rt->rt6i_flags & RTF_PCPU ||
- rcu_access_pointer(rt->rt6i_node));
+ (rt->rt6i_flags & RTF_PCPU || from_set);
}
static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
@@ -2176,14 +2334,18 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
if (rt6->rt6i_flags & RTF_CACHE)
rt6_update_exception_stamp_rt(rt6);
} else if (daddr) {
+ struct fib6_info *from;
struct rt6_info *nrt6;
- nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr);
+ rcu_read_lock();
+ from = rcu_dereference(rt6->from);
+ nrt6 = ip6_rt_cache_alloc(from, daddr, saddr);
if (nrt6) {
rt6_do_update_pmtu(nrt6, mtu);
- if (rt6_insert_exception(nrt6, rt6))
+ if (rt6_insert_exception(nrt6, from))
dst_release_immediate(&nrt6->dst);
}
+ rcu_read_unlock();
}
}
@@ -2264,7 +2426,8 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
int flags)
{
struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6;
- struct rt6_info *rt, *rt_cache;
+ struct rt6_info *ret = NULL, *rt_cache;
+ struct fib6_info *rt;
struct fib6_node *fn;
/* Get the "current" route for this destination and
@@ -2278,32 +2441,32 @@ static struct rt6_info *__ip6_route_redirect(struct net *net,
*/
rcu_read_lock();
- fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
+ fn = fib6_node_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr);
restart:
for_each_fib6_node_rt_rcu(fn) {
- if (rt->rt6i_nh_flags & RTNH_F_DEAD)
+ if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
continue;
- if (rt6_check_expired(rt))
+ if (fib6_check_expired(rt))
continue;
- if (rt->dst.error)
+ if (rt->fib6_flags & RTF_REJECT)
break;
- if (!(rt->rt6i_flags & RTF_GATEWAY))
+ if (!(rt->fib6_flags & RTF_GATEWAY))
continue;
- if (fl6->flowi6_oif != rt->dst.dev->ifindex)
+ if (fl6->flowi6_oif != rt->fib6_nh.nh_dev->ifindex)
continue;
/* rt_cache's gateway might be different from its 'parent'
* in the case of an ip redirect.
* So we keep searching in the exception table if the gateway
* is different.
*/
- if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) {
+ if (!ipv6_addr_equal(&rdfl->gateway, &rt->fib6_nh.nh_gw)) {
rt_cache = rt6_find_cached_rt(rt,
&fl6->daddr,
&fl6->saddr);
if (rt_cache &&
ipv6_addr_equal(&rdfl->gateway,
&rt_cache->rt6i_gateway)) {
- rt = rt_cache;
+ ret = rt_cache;
break;
}
continue;
@@ -2312,25 +2475,28 @@ restart:
}
if (!rt)
- rt = net->ipv6.ip6_null_entry;
- else if (rt->dst.error) {
- rt = net->ipv6.ip6_null_entry;
+ rt = net->ipv6.fib6_null_entry;
+ else if (rt->fib6_flags & RTF_REJECT) {
+ ret = net->ipv6.ip6_null_entry;
goto out;
}
- if (rt == net->ipv6.ip6_null_entry) {
+ if (rt == net->ipv6.fib6_null_entry) {
fn = fib6_backtrack(fn, &fl6->saddr);
if (fn)
goto restart;
}
out:
- ip6_hold_safe(net, &rt, true);
+ if (ret)
+ dst_hold(&ret->dst);
+ else
+ ret = ip6_create_rt_rcu(rt);
rcu_read_unlock();
trace_fib6_table_lookup(net, rt, table, fl6);
- return rt;
+ return ret;
};
static struct dst_entry *ip6_route_redirect(struct net *net,
@@ -2422,12 +2588,8 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst)
static unsigned int ip6_mtu(const struct dst_entry *dst)
{
- const struct rt6_info *rt = (const struct rt6_info *)dst;
- unsigned int mtu = rt->rt6i_pmtu;
struct inet6_dev *idev;
-
- if (mtu)
- goto out;
+ unsigned int mtu;
mtu = dst_metric_raw(dst, RTAX_MTU);
if (mtu)
@@ -2447,6 +2609,54 @@ out:
return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
}
+/* MTU selection:
+ * 1. mtu on route is locked - use it
+ * 2. mtu from nexthop exception
+ * 3. mtu from egress device
+ *
+ * based on ip6_dst_mtu_forward and exception logic of
+ * rt6_find_cached_rt; called with rcu_read_lock
+ */
+u32 ip6_mtu_from_fib6(struct fib6_info *f6i, struct in6_addr *daddr,
+ struct in6_addr *saddr)
+{
+ struct rt6_exception_bucket *bucket;
+ struct rt6_exception *rt6_ex;
+ struct in6_addr *src_key;
+ struct inet6_dev *idev;
+ u32 mtu = 0;
+
+ if (unlikely(fib6_metric_locked(f6i, RTAX_MTU))) {
+ mtu = f6i->fib6_pmtu;
+ if (mtu)
+ goto out;
+ }
+
+ src_key = NULL;
+#ifdef CONFIG_IPV6_SUBTREES
+ if (f6i->fib6_src.plen)
+ src_key = saddr;
+#endif
+
+ bucket = rcu_dereference(f6i->rt6i_exception_bucket);
+ rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key);
+ if (rt6_ex && !rt6_check_expired(rt6_ex->rt6i))
+ mtu = dst_metric_raw(&rt6_ex->rt6i->dst, RTAX_MTU);
+
+ if (likely(!mtu)) {
+ struct net_device *dev = fib6_info_nh_dev(f6i);
+
+ mtu = IPV6_MIN_MTU;
+ idev = __in6_dev_get(dev);
+ if (idev && idev->cnf.mtu6 > mtu)
+ mtu = idev->cnf.mtu6;
+ }
+
+ mtu = min_t(unsigned int, mtu, IP6_MAX_MTU);
+out:
+ return mtu - lwtunnel_headroom(fib6_info_nh_lwt(f6i), mtu);
+}
+
struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
struct flowi6 *fl6)
{
@@ -2511,60 +2721,22 @@ out:
return entries > rt_max_size;
}
-static int ip6_convert_metrics(struct mx6_config *mxc,
- const struct fib6_config *cfg)
+static int ip6_convert_metrics(struct net *net, struct fib6_info *rt,
+ struct fib6_config *cfg)
{
- struct net *net = cfg->fc_nlinfo.nl_net;
- bool ecn_ca = false;
- struct nlattr *nla;
- int remaining;
- u32 *mp;
+ struct dst_metrics *p;
if (!cfg->fc_mx)
return 0;
- mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
- if (unlikely(!mp))
+ p = kzalloc(sizeof(*rt->fib6_metrics), GFP_KERNEL);
+ if (unlikely(!p))
return -ENOMEM;
- nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
- int type = nla_type(nla);
- u32 val;
-
- if (!type)
- continue;
- if (unlikely(type > RTAX_MAX))
- goto err;
-
- if (type == RTAX_CC_ALGO) {
- char tmp[TCP_CA_NAME_MAX];
-
- nla_strlcpy(tmp, nla, sizeof(tmp));
- val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca);
- if (val == TCP_CA_UNSPEC)
- goto err;
- } else {
- val = nla_get_u32(nla);
- }
- if (type == RTAX_HOPLIMIT && val > 255)
- val = 255;
- if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
- goto err;
-
- mp[type - 1] = val;
- __set_bit(type - 1, mxc->mx_valid);
- }
-
- if (ecn_ca) {
- __set_bit(RTAX_FEATURES - 1, mxc->mx_valid);
- mp[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
- }
+ refcount_set(&p->refcnt, 1);
+ rt->fib6_metrics = p;
- mxc->mx = mp;
- return 0;
- err:
- kfree(mp);
- return -EINVAL;
+ return ip_metrics_convert(net, cfg->fc_mx, cfg->fc_mx_len, p->metrics);
}
static struct rt6_info *ip6_nh_lookup_table(struct net *net,
@@ -2750,11 +2922,12 @@ out:
return err;
}
-static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
+static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
+ gfp_t gfp_flags,
struct netlink_ext_ack *extack)
{
struct net *net = cfg->fc_nlinfo.nl_net;
- struct rt6_info *rt = NULL;
+ struct fib6_info *rt = NULL;
struct net_device *dev = NULL;
struct inet6_dev *idev = NULL;
struct fib6_table *table;
@@ -2773,6 +2946,11 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
goto out;
}
+ if (cfg->fc_type > RTN_MAX) {
+ NL_SET_ERR_MSG(extack, "Invalid route type");
+ goto out;
+ }
+
if (cfg->fc_dst_len > 128) {
NL_SET_ERR_MSG(extack, "Invalid prefix length");
goto out;
@@ -2831,35 +3009,30 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
if (!table)
goto out;
- rt = ip6_dst_alloc(net, NULL,
- (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT);
+ err = -ENOMEM;
+ rt = fib6_info_alloc(gfp_flags);
+ if (!rt)
+ goto out;
+
+ if (cfg->fc_flags & RTF_ADDRCONF)
+ rt->dst_nocount = true;
- if (!rt) {
- err = -ENOMEM;
+ err = ip6_convert_metrics(net, rt, cfg);
+ if (err < 0)
goto out;
- }
if (cfg->fc_flags & RTF_EXPIRES)
- rt6_set_expires(rt, jiffies +
+ fib6_set_expires(rt, jiffies +
clock_t_to_jiffies(cfg->fc_expires));
else
- rt6_clean_expires(rt);
+ fib6_clean_expires(rt);
if (cfg->fc_protocol == RTPROT_UNSPEC)
cfg->fc_protocol = RTPROT_BOOT;
- rt->rt6i_protocol = cfg->fc_protocol;
+ rt->fib6_protocol = cfg->fc_protocol;
addr_type = ipv6_addr_type(&cfg->fc_dst);
- if (addr_type & IPV6_ADDR_MULTICAST)
- rt->dst.input = ip6_mc_input;
- else if (cfg->fc_flags & RTF_LOCAL)
- rt->dst.input = ip6_input;
- else
- rt->dst.input = ip6_forward;
-
- rt->dst.output = ip6_output;
-
if (cfg->fc_encap) {
struct lwtunnel_state *lwtstate;
@@ -2868,22 +3041,23 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
&lwtstate, extack);
if (err)
goto out;
- rt->dst.lwtstate = lwtstate_get(lwtstate);
- lwtunnel_set_redirect(&rt->dst);
+ rt->fib6_nh.nh_lwtstate = lwtstate_get(lwtstate);
}
- ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
- rt->rt6i_dst.plen = cfg->fc_dst_len;
- if (rt->rt6i_dst.plen == 128)
- rt->dst.flags |= DST_HOST;
+ ipv6_addr_prefix(&rt->fib6_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
+ rt->fib6_dst.plen = cfg->fc_dst_len;
+ if (rt->fib6_dst.plen == 128)
+ rt->dst_host = true;
#ifdef CONFIG_IPV6_SUBTREES
- ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len);
- rt->rt6i_src.plen = cfg->fc_src_len;
+ ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len);
+ rt->fib6_src.plen = cfg->fc_src_len;
#endif
- rt->rt6i_metric = cfg->fc_metric;
- rt->rt6i_nh_weight = 1;
+ rt->fib6_metric = cfg->fc_metric;
+ rt->fib6_nh.nh_weight = 1;
+
+ rt->fib6_type = cfg->fc_type;
/* We cannot add true routes via loopback here,
they would result in kernel looping; promote them to reject routes
@@ -2906,28 +3080,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
goto out;
}
}
- rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP;
- switch (cfg->fc_type) {
- case RTN_BLACKHOLE:
- rt->dst.error = -EINVAL;
- rt->dst.output = dst_discard_out;
- rt->dst.input = dst_discard;
- break;
- case RTN_PROHIBIT:
- rt->dst.error = -EACCES;
- rt->dst.output = ip6_pkt_prohibit_out;
- rt->dst.input = ip6_pkt_prohibit;
- break;
- case RTN_THROW:
- case RTN_UNREACHABLE:
- default:
- rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN
- : (cfg->fc_type == RTN_UNREACHABLE)
- ? -EHOSTUNREACH : -ENETUNREACH;
- rt->dst.output = ip6_pkt_discard_out;
- rt->dst.input = ip6_pkt_discard;
- break;
- }
+ rt->fib6_flags = RTF_REJECT|RTF_NONEXTHOP;
goto install_route;
}
@@ -2936,7 +3089,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
if (err)
goto out;
- rt->rt6i_gateway = cfg->fc_gateway;
+ rt->fib6_nh.nh_gw = cfg->fc_gateway;
}
err = -ENODEV;
@@ -2961,96 +3114,82 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg,
err = -EINVAL;
goto out;
}
- rt->rt6i_prefsrc.addr = cfg->fc_prefsrc;
- rt->rt6i_prefsrc.plen = 128;
+ rt->fib6_prefsrc.addr = cfg->fc_prefsrc;
+ rt->fib6_prefsrc.plen = 128;
} else
- rt->rt6i_prefsrc.plen = 0;
+ rt->fib6_prefsrc.plen = 0;
- rt->rt6i_flags = cfg->fc_flags;
+ rt->fib6_flags = cfg->fc_flags;
install_route:
- if (!(rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) &&
+ if (!(rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) &&
!netif_carrier_ok(dev))
- rt->rt6i_nh_flags |= RTNH_F_LINKDOWN;
- rt->rt6i_nh_flags |= (cfg->fc_flags & RTNH_F_ONLINK);
- rt->dst.dev = dev;
- rt->rt6i_idev = idev;
- rt->rt6i_table = table;
+ rt->fib6_nh.nh_flags |= RTNH_F_LINKDOWN;
+ rt->fib6_nh.nh_flags |= (cfg->fc_flags & RTNH_F_ONLINK);
+ rt->fib6_nh.nh_dev = dev;
+ rt->fib6_table = table;
cfg->fc_nlinfo.nl_net = dev_net(dev);
+ if (idev)
+ in6_dev_put(idev);
+
return rt;
out:
if (dev)
dev_put(dev);
if (idev)
in6_dev_put(idev);
- if (rt)
- dst_release_immediate(&rt->dst);
+ fib6_info_release(rt);
return ERR_PTR(err);
}
-int ip6_route_add(struct fib6_config *cfg,
+int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
struct netlink_ext_ack *extack)
{
- struct mx6_config mxc = { .mx = NULL, };
- struct rt6_info *rt;
+ struct fib6_info *rt;
int err;
- rt = ip6_route_info_create(cfg, extack);
- if (IS_ERR(rt)) {
- err = PTR_ERR(rt);
- rt = NULL;
- goto out;
- }
-
- err = ip6_convert_metrics(&mxc, cfg);
- if (err)
- goto out;
-
- err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc, extack);
-
- kfree(mxc.mx);
+ rt = ip6_route_info_create(cfg, gfp_flags, extack);
+ if (IS_ERR(rt))
+ return PTR_ERR(rt);
- return err;
-out:
- if (rt)
- dst_release_immediate(&rt->dst);
+ err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, extack);
+ fib6_info_release(rt);
return err;
}
-static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
+static int __ip6_del_rt(struct fib6_info *rt, struct nl_info *info)
{
- int err;
+ struct net *net = info->nl_net;
struct fib6_table *table;
- struct net *net = dev_net(rt->dst.dev);
+ int err;
- if (rt == net->ipv6.ip6_null_entry) {
+ if (rt == net->ipv6.fib6_null_entry) {
err = -ENOENT;
goto out;
}
- table = rt->rt6i_table;
+ table = rt->fib6_table;
spin_lock_bh(&table->tb6_lock);
err = fib6_del(rt, info);
spin_unlock_bh(&table->tb6_lock);
out:
- ip6_rt_put(rt);
+ fib6_info_release(rt);
return err;
}
-int ip6_del_rt(struct rt6_info *rt)
+int ip6_del_rt(struct net *net, struct fib6_info *rt)
{
- struct nl_info info = {
- .nl_net = dev_net(rt->dst.dev),
- };
+ struct nl_info info = { .nl_net = net };
+
return __ip6_del_rt(rt, &info);
}
-static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
+static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg)
{
struct nl_info *info = &cfg->fc_nlinfo;
struct net *net = info->nl_net;
@@ -3058,20 +3197,20 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
struct fib6_table *table;
int err = -ENOENT;
- if (rt == net->ipv6.ip6_null_entry)
+ if (rt == net->ipv6.fib6_null_entry)
goto out_put;
- table = rt->rt6i_table;
+ table = rt->fib6_table;
spin_lock_bh(&table->tb6_lock);
- if (rt->rt6i_nsiblings && cfg->fc_delete_all_nh) {
- struct rt6_info *sibling, *next_sibling;
+ if (rt->fib6_nsiblings && cfg->fc_delete_all_nh) {
+ struct fib6_info *sibling, *next_sibling;
/* prefer to send a single notification with all hops */
skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any());
if (skb) {
u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
- if (rt6_fill_node(net, skb, rt,
+ if (rt6_fill_node(net, skb, rt, NULL,
NULL, NULL, 0, RTM_DELROUTE,
info->portid, seq, 0) < 0) {
kfree_skb(skb);
@@ -3081,8 +3220,8 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
}
list_for_each_entry_safe(sibling, next_sibling,
- &rt->rt6i_siblings,
- rt6i_siblings) {
+ &rt->fib6_siblings,
+ fib6_siblings) {
err = fib6_del(sibling, info);
if (err)
goto out_unlock;
@@ -3093,7 +3232,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg)
out_unlock:
spin_unlock_bh(&table->tb6_lock);
out_put:
- ip6_rt_put(rt);
+ fib6_info_release(rt);
if (skb) {
rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE,
@@ -3102,11 +3241,28 @@ out_put:
return err;
}
+static int ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg)
+{
+ int rc = -ESRCH;
+
+ if (cfg->fc_ifindex && rt->dst.dev->ifindex != cfg->fc_ifindex)
+ goto out;
+
+ if (cfg->fc_flags & RTF_GATEWAY &&
+ !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
+ goto out;
+ if (dst_hold_safe(&rt->dst))
+ rc = rt6_remove_exception_rt(rt);
+out:
+ return rc;
+}
+
static int ip6_route_del(struct fib6_config *cfg,
struct netlink_ext_ack *extack)
{
- struct rt6_info *rt, *rt_cache;
+ struct rt6_info *rt_cache;
struct fib6_table *table;
+ struct fib6_info *rt;
struct fib6_node *fn;
int err = -ESRCH;
@@ -3126,25 +3282,31 @@ static int ip6_route_del(struct fib6_config *cfg,
if (fn) {
for_each_fib6_node_rt_rcu(fn) {
if (cfg->fc_flags & RTF_CACHE) {
+ int rc;
+
rt_cache = rt6_find_cached_rt(rt, &cfg->fc_dst,
&cfg->fc_src);
- if (!rt_cache)
- continue;
- rt = rt_cache;
+ if (rt_cache) {
+ rc = ip6_del_cached_rt(rt_cache, cfg);
+ if (rc != -ESRCH) {
+ rcu_read_unlock();
+ return rc;
+ }
+ }
+ continue;
}
if (cfg->fc_ifindex &&
- (!rt->dst.dev ||
- rt->dst.dev->ifindex != cfg->fc_ifindex))
+ (!rt->fib6_nh.nh_dev ||
+ rt->fib6_nh.nh_dev->ifindex != cfg->fc_ifindex))
continue;
if (cfg->fc_flags & RTF_GATEWAY &&
- !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
+ !ipv6_addr_equal(&cfg->fc_gateway, &rt->fib6_nh.nh_gw))
continue;
- if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric)
+ if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric)
continue;
- if (cfg->fc_protocol && cfg->fc_protocol != rt->rt6i_protocol)
+ if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol)
continue;
- if (!dst_hold_safe(&rt->dst))
- break;
+ fib6_info_hold(rt);
rcu_read_unlock();
/* if gateway was specified only delete the one hop */
@@ -3166,6 +3328,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
struct ndisc_options ndopts;
struct inet6_dev *in6_dev;
struct neighbour *neigh;
+ struct fib6_info *from;
struct rd_msg *msg;
int optlen, on_link;
u8 *lladdr;
@@ -3247,7 +3410,12 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
NEIGH_UPDATE_F_ISROUTER)),
NDISC_REDIRECT, &ndopts);
- nrt = ip6_rt_cache_alloc(rt, &msg->dest, NULL);
+ rcu_read_lock();
+ from = rcu_dereference(rt->from);
+ fib6_info_hold(from);
+ rcu_read_unlock();
+
+ nrt = ip6_rt_cache_alloc(from, &msg->dest, NULL);
if (!nrt)
goto out;
@@ -3255,14 +3423,13 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
if (on_link)
nrt->rt6i_flags &= ~RTF_GATEWAY;
- nrt->rt6i_protocol = RTPROT_REDIRECT;
nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key;
/* No need to remove rt from the exception table if rt is
* a cached route because rt6_insert_exception() will
* takes care of it
*/
- if (rt6_insert_exception(nrt, rt)) {
+ if (rt6_insert_exception(nrt, from)) {
dst_release_immediate(&nrt->dst);
goto out;
}
@@ -3274,47 +3441,12 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu
call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);
out:
+ fib6_info_release(from);
neigh_release(neigh);
}
-/*
- * Misc support functions
- */
-
-static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
-{
- BUG_ON(from->from);
-
- rt->rt6i_flags &= ~RTF_EXPIRES;
- dst_hold(&from->dst);
- rt->from = from;
- dst_init_metrics(&rt->dst, dst_metrics_ptr(&from->dst), true);
-}
-
-static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort)
-{
- rt->dst.input = ort->dst.input;
- rt->dst.output = ort->dst.output;
- rt->rt6i_dst = ort->rt6i_dst;
- rt->dst.error = ort->dst.error;
- rt->rt6i_idev = ort->rt6i_idev;
- if (rt->rt6i_idev)
- in6_dev_hold(rt->rt6i_idev);
- rt->dst.lastuse = jiffies;
- rt->rt6i_gateway = ort->rt6i_gateway;
- rt->rt6i_flags = ort->rt6i_flags;
- rt6_set_from(rt, ort);
- rt->rt6i_metric = ort->rt6i_metric;
-#ifdef CONFIG_IPV6_SUBTREES
- rt->rt6i_src = ort->rt6i_src;
-#endif
- rt->rt6i_prefsrc = ort->rt6i_prefsrc;
- rt->rt6i_table = ort->rt6i_table;
- rt->dst.lwtstate = lwtstate_get(ort->dst.lwtstate);
-}
-
#ifdef CONFIG_IPV6_ROUTE_INFO
-static struct rt6_info *rt6_get_route_info(struct net *net,
+static struct fib6_info *rt6_get_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr,
struct net_device *dev)
@@ -3322,7 +3454,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO;
int ifindex = dev->ifindex;
struct fib6_node *fn;
- struct rt6_info *rt = NULL;
+ struct fib6_info *rt = NULL;
struct fib6_table *table;
table = fib6_get_table(net, tb_id);
@@ -3335,13 +3467,13 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
goto out;
for_each_fib6_node_rt_rcu(fn) {
- if (rt->dst.dev->ifindex != ifindex)
+ if (rt->fib6_nh.nh_dev->ifindex != ifindex)
continue;
- if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
+ if ((rt->fib6_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
continue;
- if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr))
+ if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr))
continue;
- ip6_hold_safe(NULL, &rt, false);
+ fib6_info_hold(rt);
break;
}
out:
@@ -3349,7 +3481,7 @@ out:
return rt;
}
-static struct rt6_info *rt6_add_route_info(struct net *net,
+static struct fib6_info *rt6_add_route_info(struct net *net,
const struct in6_addr *prefix, int prefixlen,
const struct in6_addr *gwaddr,
struct net_device *dev,
@@ -3362,6 +3494,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
RTF_UP | RTF_PREF(pref),
.fc_protocol = RTPROT_RA,
+ .fc_type = RTN_UNICAST,
.fc_nlinfo.portid = 0,
.fc_nlinfo.nlh = NULL,
.fc_nlinfo.nl_net = net,
@@ -3375,36 +3508,39 @@ static struct rt6_info *rt6_add_route_info(struct net *net,
if (!prefixlen)
cfg.fc_flags |= RTF_DEFAULT;
- ip6_route_add(&cfg, NULL);
+ ip6_route_add(&cfg, GFP_ATOMIC, NULL);
return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev);
}
#endif
-struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_device *dev)
+struct fib6_info *rt6_get_dflt_router(struct net *net,
+ const struct in6_addr *addr,
+ struct net_device *dev)
{
u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT;
- struct rt6_info *rt;
+ struct fib6_info *rt;
struct fib6_table *table;
- table = fib6_get_table(dev_net(dev), tb_id);
+ table = fib6_get_table(net, tb_id);
if (!table)
return NULL;
rcu_read_lock();
for_each_fib6_node_rt_rcu(&table->tb6_root) {
- if (dev == rt->dst.dev &&
- ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
- ipv6_addr_equal(&rt->rt6i_gateway, addr))
+ if (dev == rt->fib6_nh.nh_dev &&
+ ((rt->fib6_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
+ ipv6_addr_equal(&rt->fib6_nh.nh_gw, addr))
break;
}
if (rt)
- ip6_hold_safe(NULL, &rt, false);
+ fib6_info_hold(rt);
rcu_read_unlock();
return rt;
}
-struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
+struct fib6_info *rt6_add_dflt_router(struct net *net,
+ const struct in6_addr *gwaddr,
struct net_device *dev,
unsigned int pref)
{
@@ -3415,14 +3551,15 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
.fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
RTF_UP | RTF_EXPIRES | RTF_PREF(pref),
.fc_protocol = RTPROT_RA,
+ .fc_type = RTN_UNICAST,
.fc_nlinfo.portid = 0,
.fc_nlinfo.nlh = NULL,
- .fc_nlinfo.nl_net = dev_net(dev),
+ .fc_nlinfo.nl_net = net,
};
cfg.fc_gateway = *gwaddr;
- if (!ip6_route_add(&cfg, NULL)) {
+ if (!ip6_route_add(&cfg, GFP_ATOMIC, NULL)) {
struct fib6_table *table;
table = fib6_get_table(dev_net(dev), cfg.fc_table);
@@ -3430,24 +3567,25 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
table->flags |= RT6_TABLE_HAS_DFLT_ROUTER;
}
- return rt6_get_dflt_router(gwaddr, dev);
+ return rt6_get_dflt_router(net, gwaddr, dev);
}
-static void __rt6_purge_dflt_routers(struct fib6_table *table)
+static void __rt6_purge_dflt_routers(struct net *net,
+ struct fib6_table *table)
{
- struct rt6_info *rt;
+ struct fib6_info *rt;
restart:
rcu_read_lock();
for_each_fib6_node_rt_rcu(&table->tb6_root) {
- if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
- (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) {
- if (dst_hold_safe(&rt->dst)) {
- rcu_read_unlock();
- ip6_del_rt(rt);
- } else {
- rcu_read_unlock();
- }
+ struct net_device *dev = fib6_info_nh_dev(rt);
+ struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL;
+
+ if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) &&
+ (!idev || idev->cnf.accept_ra != 2)) {
+ fib6_info_hold(rt);
+ rcu_read_unlock();
+ ip6_del_rt(net, rt);
goto restart;
}
}
@@ -3468,7 +3606,7 @@ void rt6_purge_dflt_routers(struct net *net)
head = &net->ipv6.fib_table_hash[h];
hlist_for_each_entry_rcu(table, head, tb6_hlist) {
if (table->flags & RT6_TABLE_HAS_DFLT_ROUTER)
- __rt6_purge_dflt_routers(table);
+ __rt6_purge_dflt_routers(net, table);
}
}
@@ -3489,6 +3627,7 @@ static void rtmsg_to_fib6_config(struct net *net,
cfg->fc_dst_len = rtmsg->rtmsg_dst_len;
cfg->fc_src_len = rtmsg->rtmsg_src_len;
cfg->fc_flags = rtmsg->rtmsg_flags;
+ cfg->fc_type = rtmsg->rtmsg_type;
cfg->fc_nlinfo.nl_net = net;
@@ -3518,7 +3657,7 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg)
rtnl_lock();
switch (cmd) {
case SIOCADDRT:
- err = ip6_route_add(&cfg, NULL);
+ err = ip6_route_add(&cfg, GFP_KERNEL, NULL);
break;
case SIOCDELRT:
err = ip6_route_del(&cfg, NULL);
@@ -3546,7 +3685,8 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
case IPSTATS_MIB_INNOROUTES:
type = ipv6_addr_type(&ipv6_hdr(skb)->daddr);
if (type == IPV6_ADDR_ANY) {
- IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst),
+ IP6_INC_STATS(dev_net(dst->dev),
+ __in6_dev_get_safely(skb->dev),
IPSTATS_MIB_INADDRERRORS);
break;
}
@@ -3587,40 +3727,40 @@ static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff
* Allocate a dst for local (unicast / anycast) address.
*/
-struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
- const struct in6_addr *addr,
- bool anycast)
+struct fib6_info *addrconf_f6i_alloc(struct net *net,
+ struct inet6_dev *idev,
+ const struct in6_addr *addr,
+ bool anycast, gfp_t gfp_flags)
{
u32 tb_id;
- struct net *net = dev_net(idev->dev);
struct net_device *dev = idev->dev;
- struct rt6_info *rt;
+ struct fib6_info *f6i;
- rt = ip6_dst_alloc(net, dev, DST_NOCOUNT);
- if (!rt)
+ f6i = fib6_info_alloc(gfp_flags);
+ if (!f6i)
return ERR_PTR(-ENOMEM);
- in6_dev_hold(idev);
-
- rt->dst.flags |= DST_HOST;
- rt->dst.input = ip6_input;
- rt->dst.output = ip6_output;
- rt->rt6i_idev = idev;
-
- rt->rt6i_protocol = RTPROT_KERNEL;
- rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP;
- if (anycast)
- rt->rt6i_flags |= RTF_ANYCAST;
- else
- rt->rt6i_flags |= RTF_LOCAL;
+ f6i->dst_nocount = true;
+ f6i->dst_host = true;
+ f6i->fib6_protocol = RTPROT_KERNEL;
+ f6i->fib6_flags = RTF_UP | RTF_NONEXTHOP;
+ if (anycast) {
+ f6i->fib6_type = RTN_ANYCAST;
+ f6i->fib6_flags |= RTF_ANYCAST;
+ } else {
+ f6i->fib6_type = RTN_LOCAL;
+ f6i->fib6_flags |= RTF_LOCAL;
+ }
- rt->rt6i_gateway = *addr;
- rt->rt6i_dst.addr = *addr;
- rt->rt6i_dst.plen = 128;
+ f6i->fib6_nh.nh_gw = *addr;
+ dev_hold(dev);
+ f6i->fib6_nh.nh_dev = dev;
+ f6i->fib6_dst.addr = *addr;
+ f6i->fib6_dst.plen = 128;
tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL;
- rt->rt6i_table = fib6_get_table(net, tb_id);
+ f6i->fib6_table = fib6_get_table(net, tb_id);
- return rt;
+ return f6i;
}
/* remove deleted ip from prefsrc entries */
@@ -3630,18 +3770,18 @@ struct arg_dev_net_ip {
struct in6_addr *addr;
};
-static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg)
+static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg)
{
struct net_device *dev = ((struct arg_dev_net_ip *)arg)->dev;
struct net *net = ((struct arg_dev_net_ip *)arg)->net;
struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr;
- if (((void *)rt->dst.dev == dev || !dev) &&
- rt != net->ipv6.ip6_null_entry &&
- ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) {
+ if (((void *)rt->fib6_nh.nh_dev == dev || !dev) &&
+ rt != net->ipv6.fib6_null_entry &&
+ ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr)) {
spin_lock_bh(&rt6_exception_lock);
/* remove prefsrc entry */
- rt->rt6i_prefsrc.plen = 0;
+ rt->fib6_prefsrc.plen = 0;
/* need to update cache as well */
rt6_exceptions_remove_prefsrc(rt);
spin_unlock_bh(&rt6_exception_lock);
@@ -3663,12 +3803,12 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp)
#define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY)
/* Remove routers and update dst entries when gateway turn into host. */
-static int fib6_clean_tohost(struct rt6_info *rt, void *arg)
+static int fib6_clean_tohost(struct fib6_info *rt, void *arg)
{
struct in6_addr *gateway = (struct in6_addr *)arg;
- if (((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) &&
- ipv6_addr_equal(gateway, &rt->rt6i_gateway)) {
+ if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) &&
+ ipv6_addr_equal(gateway, &rt->fib6_nh.nh_gw)) {
return -1;
}
@@ -3694,85 +3834,85 @@ struct arg_netdev_event {
};
};
-static struct rt6_info *rt6_multipath_first_sibling(const struct rt6_info *rt)
+static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt)
{
- struct rt6_info *iter;
+ struct fib6_info *iter;
struct fib6_node *fn;
- fn = rcu_dereference_protected(rt->rt6i_node,
- lockdep_is_held(&rt->rt6i_table->tb6_lock));
+ fn = rcu_dereference_protected(rt->fib6_node,
+ lockdep_is_held(&rt->fib6_table->tb6_lock));
iter = rcu_dereference_protected(fn->leaf,
- lockdep_is_held(&rt->rt6i_table->tb6_lock));
+ lockdep_is_held(&rt->fib6_table->tb6_lock));
while (iter) {
- if (iter->rt6i_metric == rt->rt6i_metric &&
- rt6_qualify_for_ecmp(iter))
+ if (iter->fib6_metric == rt->fib6_metric &&
+ iter->fib6_nsiblings)
return iter;
- iter = rcu_dereference_protected(iter->rt6_next,
- lockdep_is_held(&rt->rt6i_table->tb6_lock));
+ iter = rcu_dereference_protected(iter->fib6_next,
+ lockdep_is_held(&rt->fib6_table->tb6_lock));
}
return NULL;
}
-static bool rt6_is_dead(const struct rt6_info *rt)
+static bool rt6_is_dead(const struct fib6_info *rt)
{
- if (rt->rt6i_nh_flags & RTNH_F_DEAD ||
- (rt->rt6i_nh_flags & RTNH_F_LINKDOWN &&
- rt->rt6i_idev->cnf.ignore_routes_with_linkdown))
+ if (rt->fib6_nh.nh_flags & RTNH_F_DEAD ||
+ (rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN &&
+ fib6_ignore_linkdown(rt)))
return true;
return false;
}
-static int rt6_multipath_total_weight(const struct rt6_info *rt)
+static int rt6_multipath_total_weight(const struct fib6_info *rt)
{
- struct rt6_info *iter;
+ struct fib6_info *iter;
int total = 0;
if (!rt6_is_dead(rt))
- total += rt->rt6i_nh_weight;
+ total += rt->fib6_nh.nh_weight;
- list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings) {
+ list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) {
if (!rt6_is_dead(iter))
- total += iter->rt6i_nh_weight;
+ total += iter->fib6_nh.nh_weight;
}
return total;
}
-static void rt6_upper_bound_set(struct rt6_info *rt, int *weight, int total)
+static void rt6_upper_bound_set(struct fib6_info *rt, int *weight, int total)
{
int upper_bound = -1;
if (!rt6_is_dead(rt)) {
- *weight += rt->rt6i_nh_weight;
+ *weight += rt->fib6_nh.nh_weight;
upper_bound = DIV_ROUND_CLOSEST_ULL((u64) (*weight) << 31,
total) - 1;
}
- atomic_set(&rt->rt6i_nh_upper_bound, upper_bound);
+ atomic_set(&rt->fib6_nh.nh_upper_bound, upper_bound);
}
-static void rt6_multipath_upper_bound_set(struct rt6_info *rt, int total)
+static void rt6_multipath_upper_bound_set(struct fib6_info *rt, int total)
{
- struct rt6_info *iter;
+ struct fib6_info *iter;
int weight = 0;
rt6_upper_bound_set(rt, &weight, total);
- list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings)
+ list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
rt6_upper_bound_set(iter, &weight, total);
}
-void rt6_multipath_rebalance(struct rt6_info *rt)
+void rt6_multipath_rebalance(struct fib6_info *rt)
{
- struct rt6_info *first;
+ struct fib6_info *first;
int total;
/* In case the entire multipath route was marked for flushing,
* then there is no need to rebalance upon the removal of every
* sibling route.
*/
- if (!rt->rt6i_nsiblings || rt->should_flush)
+ if (!rt->fib6_nsiblings || rt->should_flush)
return;
/* During lookup routes are evaluated in order, so we need to
@@ -3787,14 +3927,14 @@ void rt6_multipath_rebalance(struct rt6_info *rt)
rt6_multipath_upper_bound_set(first, total);
}
-static int fib6_ifup(struct rt6_info *rt, void *p_arg)
+static int fib6_ifup(struct fib6_info *rt, void *p_arg)
{
const struct arg_netdev_event *arg = p_arg;
- const struct net *net = dev_net(arg->dev);
+ struct net *net = dev_net(arg->dev);
- if (rt != net->ipv6.ip6_null_entry && rt->dst.dev == arg->dev) {
- rt->rt6i_nh_flags &= ~arg->nh_flags;
- fib6_update_sernum_upto_root(dev_net(rt->dst.dev), rt);
+ if (rt != net->ipv6.fib6_null_entry && rt->fib6_nh.nh_dev == arg->dev) {
+ rt->fib6_nh.nh_flags &= ~arg->nh_flags;
+ fib6_update_sernum_upto_root(net, rt);
rt6_multipath_rebalance(rt);
}
@@ -3816,95 +3956,96 @@ void rt6_sync_up(struct net_device *dev, unsigned int nh_flags)
fib6_clean_all(dev_net(dev), fib6_ifup, &arg);
}
-static bool rt6_multipath_uses_dev(const struct rt6_info *rt,
+static bool rt6_multipath_uses_dev(const struct fib6_info *rt,
const struct net_device *dev)
{
- struct rt6_info *iter;
+ struct fib6_info *iter;
- if (rt->dst.dev == dev)
+ if (rt->fib6_nh.nh_dev == dev)
return true;
- list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings)
- if (iter->dst.dev == dev)
+ list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
+ if (iter->fib6_nh.nh_dev == dev)
return true;
return false;
}
-static void rt6_multipath_flush(struct rt6_info *rt)
+static void rt6_multipath_flush(struct fib6_info *rt)
{
- struct rt6_info *iter;
+ struct fib6_info *iter;
rt->should_flush = 1;
- list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings)
+ list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
iter->should_flush = 1;
}
-static unsigned int rt6_multipath_dead_count(const struct rt6_info *rt,
+static unsigned int rt6_multipath_dead_count(const struct fib6_info *rt,
const struct net_device *down_dev)
{
- struct rt6_info *iter;
+ struct fib6_info *iter;
unsigned int dead = 0;
- if (rt->dst.dev == down_dev || rt->rt6i_nh_flags & RTNH_F_DEAD)
+ if (rt->fib6_nh.nh_dev == down_dev ||
+ rt->fib6_nh.nh_flags & RTNH_F_DEAD)
dead++;
- list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings)
- if (iter->dst.dev == down_dev ||
- iter->rt6i_nh_flags & RTNH_F_DEAD)
+ list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
+ if (iter->fib6_nh.nh_dev == down_dev ||
+ iter->fib6_nh.nh_flags & RTNH_F_DEAD)
dead++;
return dead;
}
-static void rt6_multipath_nh_flags_set(struct rt6_info *rt,
+static void rt6_multipath_nh_flags_set(struct fib6_info *rt,
const struct net_device *dev,
unsigned int nh_flags)
{
- struct rt6_info *iter;
+ struct fib6_info *iter;
- if (rt->dst.dev == dev)
- rt->rt6i_nh_flags |= nh_flags;
- list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings)
- if (iter->dst.dev == dev)
- iter->rt6i_nh_flags |= nh_flags;
+ if (rt->fib6_nh.nh_dev == dev)
+ rt->fib6_nh.nh_flags |= nh_flags;
+ list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings)
+ if (iter->fib6_nh.nh_dev == dev)
+ iter->fib6_nh.nh_flags |= nh_flags;
}
/* called with write lock held for table with rt */
-static int fib6_ifdown(struct rt6_info *rt, void *p_arg)
+static int fib6_ifdown(struct fib6_info *rt, void *p_arg)
{
const struct arg_netdev_event *arg = p_arg;
const struct net_device *dev = arg->dev;
- const struct net *net = dev_net(dev);
+ struct net *net = dev_net(dev);
- if (rt == net->ipv6.ip6_null_entry)
+ if (rt == net->ipv6.fib6_null_entry)
return 0;
switch (arg->event) {
case NETDEV_UNREGISTER:
- return rt->dst.dev == dev ? -1 : 0;
+ return rt->fib6_nh.nh_dev == dev ? -1 : 0;
case NETDEV_DOWN:
if (rt->should_flush)
return -1;
- if (!rt->rt6i_nsiblings)
- return rt->dst.dev == dev ? -1 : 0;
+ if (!rt->fib6_nsiblings)
+ return rt->fib6_nh.nh_dev == dev ? -1 : 0;
if (rt6_multipath_uses_dev(rt, dev)) {
unsigned int count;
count = rt6_multipath_dead_count(rt, dev);
- if (rt->rt6i_nsiblings + 1 == count) {
+ if (rt->fib6_nsiblings + 1 == count) {
rt6_multipath_flush(rt);
return -1;
}
rt6_multipath_nh_flags_set(rt, dev, RTNH_F_DEAD |
RTNH_F_LINKDOWN);
- fib6_update_sernum(rt);
+ fib6_update_sernum(net, rt);
rt6_multipath_rebalance(rt);
}
return -2;
case NETDEV_CHANGE:
- if (rt->dst.dev != dev ||
- rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST))
+ if (rt->fib6_nh.nh_dev != dev ||
+ rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST))
break;
- rt->rt6i_nh_flags |= RTNH_F_LINKDOWN;
+ rt->fib6_nh.nh_flags |= RTNH_F_LINKDOWN;
rt6_multipath_rebalance(rt);
break;
}
@@ -3936,7 +4077,7 @@ struct rt6_mtu_change_arg {
unsigned int mtu;
};
-static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
+static int rt6_mtu_change_route(struct fib6_info *rt, void *p_arg)
{
struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg;
struct inet6_dev *idev;
@@ -3956,12 +4097,15 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
Since RFC 1981 doesn't include administrative MTU increase
update PMTU increase is a MUST. (i.e. jumbo frame)
*/
- if (rt->dst.dev == arg->dev &&
- !dst_metric_locked(&rt->dst, RTAX_MTU)) {
+ if (rt->fib6_nh.nh_dev == arg->dev &&
+ !fib6_metric_locked(rt, RTAX_MTU)) {
+ u32 mtu = rt->fib6_pmtu;
+
+ if (mtu >= arg->mtu ||
+ (mtu < arg->mtu && mtu == idev->cnf.mtu6))
+ fib6_metric_set(rt, RTAX_MTU, arg->mtu);
+
spin_lock_bh(&rt6_exception_lock);
- if (dst_metric_raw(&rt->dst, RTAX_MTU) &&
- rt6_mtu_change_route_allowed(idev, rt, arg->mtu))
- dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
rt6_exceptions_update_pmtu(idev, rt, arg->mtu);
spin_unlock_bh(&rt6_exception_lock);
}
@@ -3993,6 +4137,9 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
[RTA_UID] = { .type = NLA_U32 },
[RTA_MARK] = { .type = NLA_U32 },
[RTA_TABLE] = { .type = NLA_U32 },
+ [RTA_IP_PROTO] = { .type = NLA_U8 },
+ [RTA_SPORT] = { .type = NLA_U16 },
+ [RTA_DPORT] = { .type = NLA_U16 },
};
static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -4122,9 +4269,8 @@ errout:
}
struct rt6_nh {
- struct rt6_info *rt6_info;
+ struct fib6_info *fib6_info;
struct fib6_config r_cfg;
- struct mx6_config mxc;
struct list_head next;
};
@@ -4139,23 +4285,25 @@ static void ip6_print_replace_route_err(struct list_head *rt6_nh_list)
}
}
-static int ip6_route_info_append(struct list_head *rt6_nh_list,
- struct rt6_info *rt, struct fib6_config *r_cfg)
+static int ip6_route_info_append(struct net *net,
+ struct list_head *rt6_nh_list,
+ struct fib6_info *rt,
+ struct fib6_config *r_cfg)
{
struct rt6_nh *nh;
int err = -EEXIST;
list_for_each_entry(nh, rt6_nh_list, next) {
- /* check if rt6_info already exists */
- if (rt6_duplicate_nexthop(nh->rt6_info, rt))
+ /* check if fib6_info already exists */
+ if (rt6_duplicate_nexthop(nh->fib6_info, rt))
return err;
}
nh = kzalloc(sizeof(*nh), GFP_KERNEL);
if (!nh)
return -ENOMEM;
- nh->rt6_info = rt;
- err = ip6_convert_metrics(&nh->mxc, r_cfg);
+ nh->fib6_info = rt;
+ err = ip6_convert_metrics(net, rt, r_cfg);
if (err) {
kfree(nh);
return err;
@@ -4166,8 +4314,8 @@ static int ip6_route_info_append(struct list_head *rt6_nh_list,
return 0;
}
-static void ip6_route_mpath_notify(struct rt6_info *rt,
- struct rt6_info *rt_last,
+static void ip6_route_mpath_notify(struct fib6_info *rt,
+ struct fib6_info *rt_last,
struct nl_info *info,
__u16 nlflags)
{
@@ -4177,10 +4325,10 @@ static void ip6_route_mpath_notify(struct rt6_info *rt,
* nexthop. Since sibling routes are always added at the end of
* the list, find the first sibling of the last route appended
*/
- if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->rt6i_nsiblings) {
- rt = list_first_entry(&rt_last->rt6i_siblings,
- struct rt6_info,
- rt6i_siblings);
+ if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) {
+ rt = list_first_entry(&rt_last->fib6_siblings,
+ struct fib6_info,
+ fib6_siblings);
}
if (rt)
@@ -4190,11 +4338,11 @@ static void ip6_route_mpath_notify(struct rt6_info *rt,
static int ip6_route_multipath_add(struct fib6_config *cfg,
struct netlink_ext_ack *extack)
{
- struct rt6_info *rt_notif = NULL, *rt_last = NULL;
+ struct fib6_info *rt_notif = NULL, *rt_last = NULL;
struct nl_info *info = &cfg->fc_nlinfo;
struct fib6_config r_cfg;
struct rtnexthop *rtnh;
- struct rt6_info *rt;
+ struct fib6_info *rt;
struct rt6_nh *err_nh;
struct rt6_nh *nh, *nh_safe;
__u16 nlflags;
@@ -4214,7 +4362,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
rtnh = (struct rtnexthop *)cfg->fc_mp;
/* Parse a Multipath Entry and build a list (rt6_nh_list) of
- * rt6_info structs per nexthop
+ * fib6_info structs per nexthop
*/
while (rtnh_ok(rtnh, remaining)) {
memcpy(&r_cfg, cfg, sizeof(*cfg));
@@ -4237,18 +4385,19 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
}
r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK);
- rt = ip6_route_info_create(&r_cfg, extack);
+ rt = ip6_route_info_create(&r_cfg, GFP_KERNEL, extack);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
rt = NULL;
goto cleanup;
}
- rt->rt6i_nh_weight = rtnh->rtnh_hops + 1;
+ rt->fib6_nh.nh_weight = rtnh->rtnh_hops + 1;
- err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg);
+ err = ip6_route_info_append(info->nl_net, &rt6_nh_list,
+ rt, &r_cfg);
if (err) {
- dst_release_immediate(&rt->dst);
+ fib6_info_release(rt);
goto cleanup;
}
@@ -4263,14 +4412,20 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
err_nh = NULL;
list_for_each_entry(nh, &rt6_nh_list, next) {
- rt_last = nh->rt6_info;
- err = __ip6_ins_rt(nh->rt6_info, info, &nh->mxc, extack);
- /* save reference to first route for notification */
- if (!rt_notif && !err)
- rt_notif = nh->rt6_info;
-
- /* nh->rt6_info is used or freed at this point, reset to NULL*/
- nh->rt6_info = NULL;
+ err = __ip6_ins_rt(nh->fib6_info, info, extack);
+ fib6_info_release(nh->fib6_info);
+
+ if (!err) {
+ /* save reference to last route successfully inserted */
+ rt_last = nh->fib6_info;
+
+ /* save reference to first route for notification */
+ if (!rt_notif)
+ rt_notif = nh->fib6_info;
+ }
+
+ /* nh->fib6_info is used or freed at this point, reset to NULL*/
+ nh->fib6_info = NULL;
if (err) {
if (replace && nhn)
ip6_print_replace_route_err(&rt6_nh_list);
@@ -4287,6 +4442,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg,
*/
cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL |
NLM_F_REPLACE);
+ cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_APPEND;
nhn++;
}
@@ -4311,9 +4467,8 @@ add_errout:
cleanup:
list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) {
- if (nh->rt6_info)
- dst_release_immediate(&nh->rt6_info->dst);
- kfree(nh->mxc.mx);
+ if (nh->fib6_info)
+ fib6_info_release(nh->fib6_info);
list_del(&nh->next);
kfree(nh);
}
@@ -4390,20 +4545,20 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
if (cfg.fc_mp)
return ip6_route_multipath_add(&cfg, extack);
else
- return ip6_route_add(&cfg, extack);
+ return ip6_route_add(&cfg, GFP_KERNEL, extack);
}
-static size_t rt6_nlmsg_size(struct rt6_info *rt)
+static size_t rt6_nlmsg_size(struct fib6_info *rt)
{
int nexthop_len = 0;
- if (rt->rt6i_nsiblings) {
+ if (rt->fib6_nsiblings) {
nexthop_len = nla_total_size(0) /* RTA_MULTIPATH */
+ NLA_ALIGN(sizeof(struct rtnexthop))
+ nla_total_size(16) /* RTA_GATEWAY */
- + lwtunnel_get_encap_size(rt->dst.lwtstate);
+ + lwtunnel_get_encap_size(rt->fib6_nh.nh_lwtstate);
- nexthop_len *= rt->rt6i_nsiblings;
+ nexthop_len *= rt->fib6_nsiblings;
}
return NLMSG_ALIGN(sizeof(struct rtmsg))
@@ -4419,38 +4574,41 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt)
+ nla_total_size(sizeof(struct rta_cacheinfo))
+ nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */
+ nla_total_size(1) /* RTA_PREF */
- + lwtunnel_get_encap_size(rt->dst.lwtstate)
+ + lwtunnel_get_encap_size(rt->fib6_nh.nh_lwtstate)
+ nexthop_len;
}
-static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt,
+static int rt6_nexthop_info(struct sk_buff *skb, struct fib6_info *rt,
unsigned int *flags, bool skip_oif)
{
- if (rt->rt6i_nh_flags & RTNH_F_DEAD)
+ if (rt->fib6_nh.nh_flags & RTNH_F_DEAD)
*flags |= RTNH_F_DEAD;
- if (rt->rt6i_nh_flags & RTNH_F_LINKDOWN) {
+ if (rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN) {
*flags |= RTNH_F_LINKDOWN;
- if (rt->rt6i_idev->cnf.ignore_routes_with_linkdown)
+
+ rcu_read_lock();
+ if (fib6_ignore_linkdown(rt))
*flags |= RTNH_F_DEAD;
+ rcu_read_unlock();
}
- if (rt->rt6i_flags & RTF_GATEWAY) {
- if (nla_put_in6_addr(skb, RTA_GATEWAY, &rt->rt6i_gateway) < 0)
+ if (rt->fib6_flags & RTF_GATEWAY) {
+ if (nla_put_in6_addr(skb, RTA_GATEWAY, &rt->fib6_nh.nh_gw) < 0)
goto nla_put_failure;
}
- *flags |= (rt->rt6i_nh_flags & RTNH_F_ONLINK);
- if (rt->rt6i_nh_flags & RTNH_F_OFFLOAD)
+ *flags |= (rt->fib6_nh.nh_flags & RTNH_F_ONLINK);
+ if (rt->fib6_nh.nh_flags & RTNH_F_OFFLOAD)
*flags |= RTNH_F_OFFLOAD;
/* not needed for multipath encoding b/c it has a rtnexthop struct */
- if (!skip_oif && rt->dst.dev &&
- nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex))
+ if (!skip_oif && rt->fib6_nh.nh_dev &&
+ nla_put_u32(skb, RTA_OIF, rt->fib6_nh.nh_dev->ifindex))
goto nla_put_failure;
- if (rt->dst.lwtstate &&
- lwtunnel_fill_encap(skb, rt->dst.lwtstate) < 0)
+ if (rt->fib6_nh.nh_lwtstate &&
+ lwtunnel_fill_encap(skb, rt->fib6_nh.nh_lwtstate) < 0)
goto nla_put_failure;
return 0;
@@ -4460,8 +4618,9 @@ nla_put_failure:
}
/* add multipath next hop */
-static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt)
+static int rt6_add_nexthop(struct sk_buff *skb, struct fib6_info *rt)
{
+ const struct net_device *dev = rt->fib6_nh.nh_dev;
struct rtnexthop *rtnh;
unsigned int flags = 0;
@@ -4469,8 +4628,8 @@ static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt)
if (!rtnh)
goto nla_put_failure;
- rtnh->rtnh_hops = rt->rt6i_nh_weight - 1;
- rtnh->rtnh_ifindex = rt->dst.dev ? rt->dst.dev->ifindex : 0;
+ rtnh->rtnh_hops = rt->fib6_nh.nh_weight - 1;
+ rtnh->rtnh_ifindex = dev ? dev->ifindex : 0;
if (rt6_nexthop_info(skb, rt, &flags, true) < 0)
goto nla_put_failure;
@@ -4486,16 +4645,16 @@ nla_put_failure:
return -EMSGSIZE;
}
-static int rt6_fill_node(struct net *net,
- struct sk_buff *skb, struct rt6_info *rt,
- struct in6_addr *dst, struct in6_addr *src,
+static int rt6_fill_node(struct net *net, struct sk_buff *skb,
+ struct fib6_info *rt, struct dst_entry *dst,
+ struct in6_addr *dest, struct in6_addr *src,
int iif, int type, u32 portid, u32 seq,
unsigned int flags)
{
- u32 metrics[RTAX_MAX];
struct rtmsg *rtm;
struct nlmsghdr *nlh;
- long expires;
+ long expires = 0;
+ u32 *pmetrics;
u32 table;
nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags);
@@ -4504,53 +4663,31 @@ static int rt6_fill_node(struct net *net,
rtm = nlmsg_data(nlh);
rtm->rtm_family = AF_INET6;
- rtm->rtm_dst_len = rt->rt6i_dst.plen;
- rtm->rtm_src_len = rt->rt6i_src.plen;
+ rtm->rtm_dst_len = rt->fib6_dst.plen;
+ rtm->rtm_src_len = rt->fib6_src.plen;
rtm->rtm_tos = 0;
- if (rt->rt6i_table)
- table = rt->rt6i_table->tb6_id;
+ if (rt->fib6_table)
+ table = rt->fib6_table->tb6_id;
else
table = RT6_TABLE_UNSPEC;
rtm->rtm_table = table;
if (nla_put_u32(skb, RTA_TABLE, table))
goto nla_put_failure;
- if (rt->rt6i_flags & RTF_REJECT) {
- switch (rt->dst.error) {
- case -EINVAL:
- rtm->rtm_type = RTN_BLACKHOLE;
- break;
- case -EACCES:
- rtm->rtm_type = RTN_PROHIBIT;
- break;
- case -EAGAIN:
- rtm->rtm_type = RTN_THROW;
- break;
- default:
- rtm->rtm_type = RTN_UNREACHABLE;
- break;
- }
- }
- else if (rt->rt6i_flags & RTF_LOCAL)
- rtm->rtm_type = RTN_LOCAL;
- else if (rt->rt6i_flags & RTF_ANYCAST)
- rtm->rtm_type = RTN_ANYCAST;
- else if (rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK))
- rtm->rtm_type = RTN_LOCAL;
- else
- rtm->rtm_type = RTN_UNICAST;
+
+ rtm->rtm_type = rt->fib6_type;
rtm->rtm_flags = 0;
rtm->rtm_scope = RT_SCOPE_UNIVERSE;
- rtm->rtm_protocol = rt->rt6i_protocol;
+ rtm->rtm_protocol = rt->fib6_protocol;
- if (rt->rt6i_flags & RTF_CACHE)
+ if (rt->fib6_flags & RTF_CACHE)
rtm->rtm_flags |= RTM_F_CLONED;
- if (dst) {
- if (nla_put_in6_addr(skb, RTA_DST, dst))
+ if (dest) {
+ if (nla_put_in6_addr(skb, RTA_DST, dest))
goto nla_put_failure;
rtm->rtm_dst_len = 128;
} else if (rtm->rtm_dst_len)
- if (nla_put_in6_addr(skb, RTA_DST, &rt->rt6i_dst.addr))
+ if (nla_put_in6_addr(skb, RTA_DST, &rt->fib6_dst.addr))
goto nla_put_failure;
#ifdef CONFIG_IPV6_SUBTREES
if (src) {
@@ -4558,12 +4695,12 @@ static int rt6_fill_node(struct net *net,
goto nla_put_failure;
rtm->rtm_src_len = 128;
} else if (rtm->rtm_src_len &&
- nla_put_in6_addr(skb, RTA_SRC, &rt->rt6i_src.addr))
+ nla_put_in6_addr(skb, RTA_SRC, &rt->fib6_src.addr))
goto nla_put_failure;
#endif
if (iif) {
#ifdef CONFIG_IPV6_MROUTE
- if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) {
+ if (ipv6_addr_is_multicast(&rt->fib6_dst.addr)) {
int err = ip6mr_get_route(net, skb, rtm, portid);
if (err == 0)
@@ -4574,34 +4711,32 @@ static int rt6_fill_node(struct net *net,
#endif
if (nla_put_u32(skb, RTA_IIF, iif))
goto nla_put_failure;
- } else if (dst) {
+ } else if (dest) {
struct in6_addr saddr_buf;
- if (ip6_route_get_saddr(net, rt, dst, 0, &saddr_buf) == 0 &&
+ if (ip6_route_get_saddr(net, rt, dest, 0, &saddr_buf) == 0 &&
nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf))
goto nla_put_failure;
}
- if (rt->rt6i_prefsrc.plen) {
+ if (rt->fib6_prefsrc.plen) {
struct in6_addr saddr_buf;
- saddr_buf = rt->rt6i_prefsrc.addr;
+ saddr_buf = rt->fib6_prefsrc.addr;
if (nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf))
goto nla_put_failure;
}
- memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics));
- if (rt->rt6i_pmtu)
- metrics[RTAX_MTU - 1] = rt->rt6i_pmtu;
- if (rtnetlink_put_metrics(skb, metrics) < 0)
+ pmetrics = dst ? dst_metrics_ptr(dst) : rt->fib6_metrics->metrics;
+ if (rtnetlink_put_metrics(skb, pmetrics) < 0)
goto nla_put_failure;
- if (nla_put_u32(skb, RTA_PRIORITY, rt->rt6i_metric))
+ if (nla_put_u32(skb, RTA_PRIORITY, rt->fib6_metric))
goto nla_put_failure;
/* For multipath routes, walk the siblings list and add
* each as a nexthop within RTA_MULTIPATH.
*/
- if (rt->rt6i_nsiblings) {
- struct rt6_info *sibling, *next_sibling;
+ if (rt->fib6_nsiblings) {
+ struct fib6_info *sibling, *next_sibling;
struct nlattr *mp;
mp = nla_nest_start(skb, RTA_MULTIPATH);
@@ -4612,7 +4747,7 @@ static int rt6_fill_node(struct net *net,
goto nla_put_failure;
list_for_each_entry_safe(sibling, next_sibling,
- &rt->rt6i_siblings, rt6i_siblings) {
+ &rt->fib6_siblings, fib6_siblings) {
if (rt6_add_nexthop(skb, sibling) < 0)
goto nla_put_failure;
}
@@ -4623,12 +4758,15 @@ static int rt6_fill_node(struct net *net,
goto nla_put_failure;
}
- expires = (rt->rt6i_flags & RTF_EXPIRES) ? rt->dst.expires - jiffies : 0;
+ if (rt->fib6_flags & RTF_EXPIRES) {
+ expires = dst ? dst->expires : rt->expires;
+ expires -= jiffies;
+ }
- if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0)
+ if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0)
goto nla_put_failure;
- if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags)))
+ if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->fib6_flags)))
goto nla_put_failure;
@@ -4640,12 +4778,12 @@ nla_put_failure:
return -EMSGSIZE;
}
-int rt6_dump_route(struct rt6_info *rt, void *p_arg)
+int rt6_dump_route(struct fib6_info *rt, void *p_arg)
{
struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg;
struct net *net = arg->net;
- if (rt == net->ipv6.ip6_null_entry)
+ if (rt == net->ipv6.fib6_null_entry)
return 0;
if (nlmsg_len(arg->cb->nlh) >= sizeof(struct rtmsg)) {
@@ -4653,16 +4791,15 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg)
/* user wants prefix routes only */
if (rtm->rtm_flags & RTM_F_PREFIX &&
- !(rt->rt6i_flags & RTF_PREFIX_RT)) {
+ !(rt->fib6_flags & RTF_PREFIX_RT)) {
/* success since this is not a prefix route */
return 1;
}
}
- return rt6_fill_node(net,
- arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE,
- NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq,
- NLM_F_MULTI);
+ return rt6_fill_node(net, arg->skb, rt, NULL, NULL, NULL, 0,
+ RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).portid,
+ arg->cb->nlh->nlmsg_seq, NLM_F_MULTI);
}
static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
@@ -4671,6 +4808,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
struct net *net = sock_net(in_skb->sk);
struct nlattr *tb[RTA_MAX+1];
int err, iif = 0, oif = 0;
+ struct fib6_info *from;
struct dst_entry *dst;
struct rt6_info *rt;
struct sk_buff *skb;
@@ -4718,6 +4856,19 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
else
fl6.flowi6_uid = iif ? INVALID_UID : current_uid();
+ if (tb[RTA_SPORT])
+ fl6.fl6_sport = nla_get_be16(tb[RTA_SPORT]);
+
+ if (tb[RTA_DPORT])
+ fl6.fl6_dport = nla_get_be16(tb[RTA_DPORT]);
+
+ if (tb[RTA_IP_PROTO]) {
+ err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO],
+ &fl6.flowi6_proto, extack);
+ if (err)
+ goto errout;
+ }
+
if (iif) {
struct net_device *dev;
int flags = 0;
@@ -4759,14 +4910,6 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
goto errout;
}
- if (fibmatch && rt->from) {
- struct rt6_info *ort = rt->from;
-
- dst_hold(&ort->dst);
- ip6_rt_put(rt);
- rt = ort;
- }
-
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (!skb) {
ip6_rt_put(rt);
@@ -4775,14 +4918,21 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
}
skb_dst_set(skb, &rt->dst);
+
+ rcu_read_lock();
+ from = rcu_dereference(rt->from);
+
if (fibmatch)
- err = rt6_fill_node(net, skb, rt, NULL, NULL, iif,
+ err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif,
RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
nlh->nlmsg_seq, 0);
else
- err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif,
- RTM_NEWROUTE, NETLINK_CB(in_skb).portid,
- nlh->nlmsg_seq, 0);
+ err = rt6_fill_node(net, skb, from, dst, &fl6.daddr,
+ &fl6.saddr, iif, RTM_NEWROUTE,
+ NETLINK_CB(in_skb).portid, nlh->nlmsg_seq,
+ 0);
+ rcu_read_unlock();
+
if (err < 0) {
kfree_skb(skb);
goto errout;
@@ -4793,7 +4943,7 @@ errout:
return err;
}
-void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info,
+void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
unsigned int nlm_flags)
{
struct sk_buff *skb;
@@ -4808,8 +4958,8 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info,
if (!skb)
goto errout;
- err = rt6_fill_node(net, skb, rt, NULL, NULL, 0,
- event, info->portid, seq, nlm_flags);
+ err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0,
+ event, info->portid, seq, nlm_flags);
if (err < 0) {
/* -EMSGSIZE implies BUG in rt6_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
@@ -4834,6 +4984,7 @@ static int ip6_route_dev_notify(struct notifier_block *this,
return NOTIFY_OK;
if (event == NETDEV_REGISTER) {
+ net->ipv6.fib6_null_entry->fib6_nh.nh_dev = dev;
net->ipv6.ip6_null_entry->dst.dev = dev;
net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
@@ -5010,11 +5161,17 @@ static int __net_init ip6_route_net_init(struct net *net)
if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0)
goto out_ip6_dst_ops;
+ net->ipv6.fib6_null_entry = kmemdup(&fib6_null_entry_template,
+ sizeof(*net->ipv6.fib6_null_entry),
+ GFP_KERNEL);
+ if (!net->ipv6.fib6_null_entry)
+ goto out_ip6_dst_entries;
+
net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template,
sizeof(*net->ipv6.ip6_null_entry),
GFP_KERNEL);
if (!net->ipv6.ip6_null_entry)
- goto out_ip6_dst_entries;
+ goto out_fib6_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);
@@ -5061,6 +5218,8 @@ out_ip6_prohibit_entry:
out_ip6_null_entry:
kfree(net->ipv6.ip6_null_entry);
#endif
+out_fib6_null_entry:
+ kfree(net->ipv6.fib6_null_entry);
out_ip6_dst_entries:
dst_entries_destroy(&net->ipv6.ip6_dst_ops);
out_ip6_dst_ops:
@@ -5069,6 +5228,7 @@ out_ip6_dst_ops:
static void __net_exit ip6_route_net_exit(struct net *net)
{
+ kfree(net->ipv6.fib6_null_entry);
kfree(net->ipv6.ip6_null_entry);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
kfree(net->ipv6.ip6_prohibit_entry);
@@ -5141,6 +5301,7 @@ void __init ip6_route_init_special_entries(void)
/* Registering of the loopback is done before this portion of code,
* the loopback reference in rt6_info will not be taken, do it
* manually for init_net */
+ init_net.ipv6.fib6_null_entry->fib6_nh.nh_dev = init_net.loopback_dev;
init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev;
init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES