[Devel] [PATCH rh7 08/19] ms/netfilter: conntrack: consider ct netns in early_drop logic

[Konstantin Khorenko]

From: Florian Westphal <fw at strlen.de>

When iterating, skip conntrack entries living in a different netns.

We could ignore netns and kill some other non-assured one, but it
has two problems:

- a netns can kill non-assured conntracks in other namespace
- we would start to 'over-subscribe' the affected/overlimit netns.

Signed-off-by: Florian Westphal <fw at strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo at netfilter.org>

https://jira.sw.ru/browse/PSBM-103515

(cherry picked from commit 3e86638e9a0be8bcf7db007909d8307b8b9f8e3b)
Signed-off-by: Konstantin Khorenko <khorenko at virtuozzo.com>
---
 net/netfilter/nf_conntrack_core.c | 43 +++++++++++++++++++++++----------------
 1 file changed, 25 insertions(+), 18 deletions(-)

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 997ac5139547d..08bf2c9cb44ca 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -891,18 +891,20 @@ static noinline int early_drop(struct net *net, unsigned int _hash)
 {
 	/* Use oldest entry, which is roughly LRU */
 	struct nf_conntrack_tuple_hash *h;
-	struct nf_conn *ct = NULL, *tmp;
+	struct nf_conn *tmp;
 	struct hlist_nulls_node *n;
-	unsigned int i = 0, cnt = 0;
-	int dropped = 0;
-	unsigned int hash, sequence;
+	unsigned int i, hash, sequence;
+	struct nf_conn *ct = NULL;
 	spinlock_t *lockp;
+	bool ret = false;
+
+	i = 0;
 
 	local_bh_disable();
 restart:
 	sequence = read_seqcount_begin(&nf_conntrack_generation);
-	hash = scale_hash(_hash);
-	for (; i < nf_conntrack_htable_size; i++) {
+	for (; i < NF_CT_EVICTION_RANGE; i++) {
+		hash = scale_hash(_hash++);
 		lockp = &nf_conntrack_locks[hash % CONNTRACK_LOCKS];
 		spin_lock(lockp);
 		if (read_seqcount_retry(&nf_conntrack_generation, sequence)) {
@@ -912,35 +914,40 @@ static noinline int early_drop(struct net *net, unsigned int _hash)
 		hlist_nulls_for_each_entry_rcu(h, n, &nf_conntrack_hash[hash],
 					       hnnode) {
 			tmp = nf_ct_tuplehash_to_ctrack(h);
-			if (!test_bit(IPS_ASSURED_BIT, &tmp->status) &&
-			    !nf_ct_is_dying(tmp) &&
-			    atomic_inc_not_zero(&tmp->ct_general.use)) {
+
+			if (test_bit(IPS_ASSURED_BIT, &tmp->status) ||
+			    !net_eq(nf_ct_net(tmp), net) ||
+			    nf_ct_is_dying(tmp))
+				continue;
+
+			if (atomic_inc_not_zero(&tmp->ct_general.use)) {
 				ct = tmp;
 				break;
 			}
-			cnt++;
 		}
 
-		hash = (hash + 1) % nf_conntrack_htable_size;
 		spin_unlock(lockp);
-
-		if (ct || cnt >= NF_CT_EVICTION_RANGE)
+		if (ct)
 			break;
-
 	}
+
 	local_bh_enable();
 
 	if (!ct)
-		return dropped;
+		return false;
 
-	if (del_timer(&ct->timeout)) {
+	/* kill only if in same netns -- might have moved due to
+	 * SLAB_DESTROY_BY_RCU rules
+	 */
+	if (net_eq(nf_ct_net(ct), net) && del_timer(&ct->timeout)) {
 		if (nf_ct_delete(ct, 0, 0)) {
-			dropped = 1;
 			NF_CT_STAT_INC_ATOMIC(net, early_drop);
+			ret = true;
 		}
 	}
+
 	nf_ct_put(ct);
-	return dropped;
+	return ret;
 }
 
 void init_nf_conntrack_hash_rnd(void)
-- 
2.15.1