From: Wei Wang <wei...@google.com>

If we move all cached dst into the exception table under the main route,
current rt6_mtu_change() will no longer be able to access them.
This commit makes rt6_mtu_change_route() function to also go through all
cached routes in the exception table under the main route and do proper
updates on the mtu.
This is a preparation in order to move all cached routes into the
exception table.

Signed-off-by: Wei Wang <wei...@google.com>
Signed-off-by: Martin KaFai Lau <ka...@fb.com>
Signed-off-by: Eric Dumazet <eduma...@google.com>
---
 net/ipv6/route.c | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index f52ac57dcc99..d9805a857809 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1269,6 +1269,14 @@ static int rt6_insert_exception(struct rt6_info *nrt,
         * in rt6_remove_prefsrc()
         */
        nrt->rt6i_prefsrc = ort->rt6i_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)) {
+               err = -EINVAL;
+               goto out;
+       }
 
        rt6_ex = __rt6_find_exception_spinlock(&bucket, &nrt->rt6i_dst.addr,
                                               src_key);
@@ -1457,6 +1465,32 @@ static void rt6_exceptions_remove_prefsrc(struct 
rt6_info *rt)
        }
 }
 
+static void rt6_exceptions_update_pmtu(struct rt6_info *rt, int mtu)
+{
+       struct rt6_exception_bucket *bucket;
+       struct rt6_exception *rt6_ex;
+       int i;
+
+       bucket = rcu_dereference_protected(rt->rt6i_exception_bucket,
+                                       lockdep_is_held(&rt6_exception_lock));
+
+       if (bucket) {
+               for (i = 0; i < FIB6_EXCEPTION_BUCKET_SIZE; i++) {
+                       hlist_for_each_entry(rt6_ex, &bucket->chain, hlist) {
+                               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 has already
+                                * been updated.
+                                */
+                               if (entry->rt6i_pmtu && entry->rt6i_pmtu > mtu)
+                                       entry->rt6i_pmtu = mtu;
+                       }
+                       bucket++;
+               }
+       }
+}
+
 struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table,
                               int oif, struct flowi6 *fl6, int flags)
 {
@@ -3296,6 +3330,10 @@ static int rt6_mtu_change_route(struct rt6_info *rt, 
void *p_arg)
        if (rt->dst.dev == arg->dev &&
            dst_metric_raw(&rt->dst, RTAX_MTU) &&
            !dst_metric_locked(&rt->dst, RTAX_MTU)) {
+               spin_lock_bh(&rt6_exception_lock);
+               /* This case will be removed once the exception table
+                * is hooked up.
+                */
                if (rt->rt6i_flags & RTF_CACHE) {
                        /* For RTF_CACHE with rt6i_pmtu == 0
                         * (i.e. a redirected route),
@@ -3309,6 +3347,8 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void 
*p_arg)
                            dst_mtu(&rt->dst) == idev->cnf.mtu6)) {
                        dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
                }
+               rt6_exceptions_update_pmtu(rt, arg->mtu);
+               spin_unlock_bh(&rt6_exception_lock);
        }
        return 0;
 }
-- 
2.14.2.920.gcf0c67979c-goog

Reply via email to