commit b36e4523d4d5 ("netfilter: nf_conncount: fix garbage collection confirm race")
An iptable rule like the following on a multicore systems will result in accepting more connections than set in the rule.
iptables -A INPUT -p tcp -m tcp --syn --dport 7777 -m connlimit \ --connlimit-above 2000 --connlimit-mask 0 -j DROP
In check_hlist function, connections that are found in saved connections but not in netfilter conntrack are deleted, assuming that those connections do not exist anymore. But for multi core systems, there exists a small time window, when a connection has been added to the xt_connlimit maintained rb-tree but has not yet made to netfilter conntrack table. This causes concurrent connections to return incorrect counts and go over limit set in iptable rule.
The fix has been partially backported from the above mentioned upstream commit. Introduce timestamp and the owning cpu.
Signed-off-by: Alakesh Haloi alakeshh@amazon.com Cc: Pablo Neira Ayuso pablo@netfilter.org Cc: Jozsef Kadlecsik kadlec@blackhole.kfki.hu Cc: Florian Westphal fw@strlen.de Cc: "David S. Miller" davem@davemloft.net Cc: stable@vger.kernel.org # v4.15 and before Cc: netdev@vger.kernel.org Cc: Dmitry Andrianov dmitry.andrianov@alertme.com Cc: Justin Pettit jpettit@vmware.com Cc: Yi-Hung Wei yihung.wei@gmail.com --- net/netfilter/xt_connlimit.c | 28 ++++++++++++++++++++++++++-- 1 file changed, 26 insertions(+), 2 deletions(-)
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index ffa8eec..e7b092b 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -47,6 +47,8 @@ struct xt_connlimit_conn { struct hlist_node node; struct nf_conntrack_tuple tuple; union nf_inet_addr addr; + int cpu; + u32 jiffies32; };
struct xt_connlimit_rb { @@ -126,6 +128,8 @@ static bool add_hlist(struct hlist_head *head, return false; conn->tuple = *tuple; conn->addr = *addr; + conn->cpu = raw_smp_processor_id(); + conn->jiffies32 = (u32)jiffies; hlist_add_head(&conn->node, head); return true; } @@ -148,8 +152,26 @@ static unsigned int check_hlist(struct net *net, hlist_for_each_entry_safe(conn, n, head, node) { found = nf_conntrack_find_get(net, zone, &conn->tuple); if (found == NULL) { - hlist_del(&conn->node); - kmem_cache_free(connlimit_conn_cachep, conn); + /* If connection is not found, it may be because + * it has not made into conntrack table yet. We + * check if it is a recently created connection + * on a different core and do not delete it in that + * case. + */ + + unsigned long a, b; + int cpu = raw_smp_processor_id(); + __u32 age; + + b = conn->jiffies; + a = (u32)jiffies; + age = a - b; + if (conn->cpu != cpu && age <= 2) { + length++; + } else { + hlist_del(&conn->node); + kmem_cache_free(connlimit_conn_cachep, conn); + } continue; }
@@ -271,6 +293,8 @@ static void tree_nodes_free(struct rb_root *root,
conn->tuple = *tuple; conn->addr = *addr; + conn->cpu = raw_smp_processor_id(); + conn->jiffies32 = (u32)jiffies; rbconn->addr = *addr;
INIT_HLIST_HEAD(&rbconn->hhead);