summaryrefslogtreecommitdiffstats
path: root/net/ipv6/ip6_fib.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6/ip6_fib.c')
-rw-r--r--net/ipv6/ip6_fib.c155
1 files changed, 99 insertions, 56 deletions
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index b2d1838897c9..bde57b113009 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -277,7 +277,6 @@ static int fib6_dump_node(struct fib6_walker *w)
w->leaf = rt;
return 1;
}
- WARN_ON(res == 0);
}
w->leaf = NULL;
return 0;
@@ -630,33 +629,59 @@ static bool rt6_qualify_for_ecmp(struct rt6_info *rt)
RTF_GATEWAY;
}
-static int fib6_commit_metrics(struct dst_entry *dst,
- struct nlattr *mx, int mx_len)
+static void fib6_copy_metrics(u32 *mp, const struct mx6_config *mxc)
{
- struct nlattr *nla;
- int remaining;
- u32 *mp;
+ int i;
+
+ for (i = 0; i < RTAX_MAX; i++) {
+ if (test_bit(i, mxc->mx_valid))
+ mp[i] = mxc->mx[i];
+ }
+}
+
+static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc)
+{
+ if (!mxc->mx)
+ return 0;
if (dst->flags & DST_HOST) {
- mp = dst_metrics_write_ptr(dst);
- } else {
- mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
- if (!mp)
+ u32 *mp = dst_metrics_write_ptr(dst);
+
+ if (unlikely(!mp))
return -ENOMEM;
- dst_init_metrics(dst, mp, 0);
- }
- nla_for_each_attr(nla, mx, mx_len, remaining) {
- int type = nla_type(nla);
+ fib6_copy_metrics(mp, mxc);
+ } else {
+ dst_init_metrics(dst, mxc->mx, false);
+
+ /* We've stolen mx now. */
+ mxc->mx = NULL;
+ }
- if (type) {
- if (type > RTAX_MAX)
- return -EINVAL;
+ return 0;
+}
- mp[type - 1] = nla_get_u32(nla);
+static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
+ struct net *net)
+{
+ if (atomic_read(&rt->rt6i_ref) != 1) {
+ /* This route is used as dummy address holder in some split
+ * nodes. It is not leaked, but it still holds other resources,
+ * which must be released in time. So, scan ascendant nodes
+ * and replace dummy references to this route with references
+ * to still alive ones.
+ */
+ while (fn) {
+ if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
+ fn->leaf = fib6_find_prefix(net, fn);
+ atomic_inc(&fn->leaf->rt6i_ref);
+ rt6_release(rt);
+ }
+ fn = fn->parent;
}
+ /* No more references are possible at this point. */
+ BUG_ON(atomic_read(&rt->rt6i_ref) != 1);
}
- return 0;
}
/*
@@ -664,10 +689,11 @@ static int fib6_commit_metrics(struct dst_entry *dst,
*/
static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
- struct nl_info *info, struct nlattr *mx, int mx_len)
+ struct nl_info *info, struct mx6_config *mxc)
{
struct rt6_info *iter = NULL;
struct rt6_info **ins;
+ struct rt6_info **fallback_ins = NULL;
int replace = (info->nlh &&
(info->nlh->nlmsg_flags & NLM_F_REPLACE));
int add = (!info->nlh ||
@@ -691,8 +717,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
(info->nlh->nlmsg_flags & NLM_F_EXCL))
return -EEXIST;
if (replace) {
- found++;
- break;
+ if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) {
+ found++;
+ break;
+ }
+ if (rt_can_ecmp)
+ fallback_ins = fallback_ins ?: ins;
+ goto next_iter;
}
if (iter->dst.dev == rt->dst.dev &&
@@ -728,9 +759,17 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
if (iter->rt6i_metric > rt->rt6i_metric)
break;
+next_iter:
ins = &iter->dst.rt6_next;
}
+ if (fallback_ins && !found) {
+ /* No ECMP-able route found, replace first non-ECMP one */
+ ins = fallback_ins;
+ iter = *ins;
+ found++;
+ }
+
/* Reset round-robin state, if necessary */
if (ins == &fn->leaf)
fn->rr_ptr = NULL;
@@ -773,11 +812,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
pr_warn("NLM_F_CREATE should be set when creating new route\n");
add:
- if (mx) {
- err = fib6_commit_metrics(&rt->dst, mx, mx_len);
- if (err)
- return err;
- }
+ err = fib6_commit_metrics(&rt->dst, mxc);
+ if (err)
+ return err;
+
rt->dst.rt6_next = iter;
*ins = rt;
rt->rt6i_node = fn;
@@ -791,27 +829,49 @@ add:
}
} else {
+ int nsiblings;
+
if (!found) {
if (add)
goto add;
pr_warn("NLM_F_REPLACE set, but no existing node found!\n");
return -ENOENT;
}
- if (mx) {
- err = fib6_commit_metrics(&rt->dst, mx, mx_len);
- if (err)
- return err;
- }
+
+ err = fib6_commit_metrics(&rt->dst, mxc);
+ if (err)
+ return err;
+
*ins = rt;
rt->rt6i_node = fn;
rt->dst.rt6_next = iter->dst.rt6_next;
atomic_inc(&rt->rt6i_ref);
inet6_rt_notify(RTM_NEWROUTE, rt, info);
- rt6_release(iter);
if (!(fn->fn_flags & RTN_RTINFO)) {
info->nl_net->ipv6.rt6_stats->fib_route_nodes++;
fn->fn_flags |= RTN_RTINFO;
}
+ nsiblings = iter->rt6i_nsiblings;
+ fib6_purge_rt(iter, fn, info->nl_net);
+ rt6_release(iter);
+
+ if (nsiblings) {
+ /* Replacing an ECMP route, remove all siblings */
+ ins = &rt->dst.rt6_next;
+ iter = *ins;
+ while (iter) {
+ if (rt6_qualify_for_ecmp(iter)) {
+ *ins = iter->dst.rt6_next;
+ fib6_purge_rt(iter, fn, info->nl_net);
+ rt6_release(iter);
+ nsiblings--;
+ } else {
+ ins = &iter->dst.rt6_next;
+ }
+ iter = *ins;
+ }
+ WARN_ON(nsiblings != 0);
+ }
}
return 0;
@@ -838,8 +898,8 @@ void fib6_force_start_gc(struct net *net)
* with source addr info in sub-trees
*/
-int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
- struct nlattr *mx, int mx_len)
+int fib6_add(struct fib6_node *root, struct rt6_info *rt,
+ struct nl_info *info, struct mx6_config *mxc)
{
struct fib6_node *fn, *pn = NULL;
int err = -ENOMEM;
@@ -934,7 +994,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info,
}
#endif
- err = fib6_add_rt2node(fn, rt, info, mx, mx_len);
+ err = fib6_add_rt2node(fn, rt, info, mxc);
if (!err) {
fib6_start_gc(info->nl_net, rt);
if (!(rt->rt6i_flags & RTF_CACHE))
@@ -1181,7 +1241,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
WARN_ON(fn->fn_flags & RTN_RTINFO);
WARN_ON(fn->fn_flags & RTN_TL_ROOT);
- WARN_ON(fn->leaf != NULL);
+ WARN_ON(fn->leaf);
children = 0;
child = NULL;
@@ -1322,24 +1382,7 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp,
fn = fib6_repair_tree(net, fn);
}
- if (atomic_read(&rt->rt6i_ref) != 1) {
- /* This route is used as dummy address holder in some split
- * nodes. It is not leaked, but it still holds other resources,
- * which must be released in time. So, scan ascendant nodes
- * and replace dummy references to this route with references
- * to still alive ones.
- */
- while (fn) {
- if (!(fn->fn_flags & RTN_RTINFO) && fn->leaf == rt) {
- fn->leaf = fib6_find_prefix(net, fn);
- atomic_inc(&fn->leaf->rt6i_ref);
- rt6_release(rt);
- }
- fn = fn->parent;
- }
- /* No more references are possible at this point. */
- BUG_ON(atomic_read(&rt->rt6i_ref) != 1);
- }
+ fib6_purge_rt(rt, fn, net);
inet6_rt_notify(RTM_DELROUTE, rt, info);
rt6_release(rt);
@@ -1353,7 +1396,7 @@ int fib6_del(struct rt6_info *rt, struct nl_info *info)
#if RT6_DEBUG >= 2
if (rt->dst.obsolete > 0) {
- WARN_ON(fn != NULL);
+ WARN_ON(fn);
return -ENOENT;
}
#endif
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-24 04:21:24 +0100