net: nexthop: fix percpu use-after-free in remove_nh_grp_entry

When removing a nexthop from a group, remove_nh_grp_entry() publishes
the new group via rcu_assign_pointer() then immediately frees the
removed entry's percpu stats with free_percpu(). However, the
synchronize_net() grace period in the caller remove_nexthop_from_groups()
runs after the free. RCU readers that entered before the publish still
see the old group and can dereference the freed stats via
nh_grp_entry_stats_inc() -> get_cpu_ptr(nhge->stats), causing a
use-after-free on percpu memory.

Fix by deferring the free_percpu() until after synchronize_net() in the
caller. Removed entries are chained via nh_list onto a local deferred
free list. After the grace period completes and all RCU readers have
finished, the percpu stats are safely freed.

Fixes: f4676ea74b85 ("net: nexthop: Add nexthop group entry stats")
Cc: stable@vger.kernel.org
Signed-off-by: Mehul Rao <mehulrao@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20260306233821.196789-1-mehulrao@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 1aa2b05ee8de856d187b198beb9af699921caa49..c942f12822363c68fc2bdb8a8f252028ab229380 100644 (file)
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -2002,7 +2002,8 @@ static void nh_hthr_group_rebalance(struct nh_group *nhg)
 }
 
 static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
-                               struct nl_info *nlinfo)
+                               struct nl_info *nlinfo,
+                               struct list_head *deferred_free)
 {
        struct nh_grp_entry *nhges, *new_nhges;
        struct nexthop *nhp = nhge->nh_parent;
@@ -2062,8 +2063,8 @@ static void remove_nh_grp_entry(struct net *net, struct nh_grp_entry *nhge,
        rcu_assign_pointer(nhp->nh_grp, newg);
 
        list_del(&nhge->nh_list);
-       free_percpu(nhge->stats);
        nexthop_put(nhge->nh);
+       list_add(&nhge->nh_list, deferred_free);
 
        /* Removal of a NH from a resilient group is notified through
         * bucket notifications.
@@ -2083,6 +2084,7 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
                                       struct nl_info *nlinfo)
 {
        struct nh_grp_entry *nhge, *tmp;
+       LIST_HEAD(deferred_free);
 
        /* If there is nothing to do, let's avoid the costly call to
         * synchronize_net()
@@ -2091,10 +2093,16 @@ static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
                return;
 
        list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list)
-               remove_nh_grp_entry(net, nhge, nlinfo);
+               remove_nh_grp_entry(net, nhge, nlinfo, &deferred_free);
 
        /* make sure all see the newly published array before releasing rtnl */
        synchronize_net();
+
+       /* Now safe to free percpu stats — all RCU readers have finished */
+       list_for_each_entry_safe(nhge, tmp, &deferred_free, nh_list) {
+               list_del(&nhge->nh_list);
+               free_percpu(nhge->stats);
+       }
 }
 
 static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)