tcp: metrics: Fix rcu-race when deleting multiple entries

In bbf852b96ebdc6d1 I introduced the tmlist, which allows to delete
multiple entries from the cache that match a specified destination if no
source-IP is specified.

However, as the cache is an RCU-list, we should not create this tmlist, as
it will change the tcpm_next pointer of the element that will be deleted
and so a thread iterating over the cache's entries while holding the
RCU-lock might get "redirected" to this tmlist.

This patch fixes this, by reverting back to the old behavior prior to
bbf852b96ebdc6d1, which means that we simply change the tcpm_next
pointer of the previous element (pp) to jump over the one we are
deleting.
The difference is that we call kfree_rcu() directly on the cache entry,
which allows us to delete multiple entries from the list.

Fixes: bbf852b96ebdc6d1 (tcp: metrics: Delete all entries matching a certain destination)
Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 5 insertions, 9 deletions

diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index fa950941de65..9ae48b4a37d1 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -1019,13 +1019,13 @@ static int tcp_metrics_flush_all(struct net *net)
 static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info)
 {
         struct tcpm_hash_bucket *hb;
-        struct tcp_metrics_block *tm, *tmlist = NULL;
+        struct tcp_metrics_block *tm;
         struct tcp_metrics_block __rcu **pp;
         struct inetpeer_addr saddr, daddr;
         unsigned int hash;
         struct net *net = genl_info_net(info);
         int ret;
-        bool src = true;
+        bool src = true, found = false;
 
         ret = parse_nl_addr(info, &daddr, &hash, 1);
         if (ret < 0)
@@ -1044,19 +1044,15 @@ static int tcp_metrics_nl_cmd_del(struct sk_buff *skb, struct genl_info *info)
                 if (addr_same(&tm->tcpm_daddr, &daddr) &&
                     (!src || addr_same(&tm->tcpm_saddr, &saddr))) {
                         *pp = tm->tcpm_next;
-                        tm->tcpm_next = tmlist;
-                        tmlist = tm;
+                        kfree_rcu(tm, rcu_head);
+                        found = true;
                 } else {
                         pp = &tm->tcpm_next;
                 }
         }
         spin_unlock_bh(&tcp_metrics_lock);
-        if (!tmlist)
+        if (!found)
                 return -ESRCH;
-        for (tm = tmlist; tm; tm = tmlist) {
-                tmlist = tm->tcpm_next;
-                kfree_rcu(tm, rcu_head);
-        }
         return 0;
 }