From a53b42c11815d2357e31a9403ae3950517525894 Mon Sep 17 00:00:00 2001 From: Tan Hu Date: Wed, 25 Jul 2018 15:23:07 +0800 Subject: ipvs: fix race between ip_vs_conn_new() and ip_vs_del_dest() We came across infinite loop in ipvs when using ipvs in docker env. When ipvs receives new packets and cannot find an ipvs connection, it will create a new connection, then if the dest is unavailable (i.e. IP_VS_DEST_F_AVAILABLE), the packet will be dropped sliently. But if the dropped packet is the first packet of this connection, the connection control timer never has a chance to start and the ipvs connection cannot be released. This will lead to memory leak, or infinite loop in cleanup_net() when net namespace is released like this: ip_vs_conn_net_cleanup at ffffffffa0a9f31a [ip_vs] __ip_vs_cleanup at ffffffffa0a9f60a [ip_vs] ops_exit_list at ffffffff81567a49 cleanup_net at ffffffff81568b40 process_one_work at ffffffff810a851b worker_thread at ffffffff810a9356 kthread at ffffffff810b0b6f ret_from_fork at ffffffff81697a18 race condition: CPU1 CPU2 ip_vs_in() ip_vs_conn_new() ip_vs_del_dest() __ip_vs_unlink_dest() ~IP_VS_DEST_F_AVAILABLE cp->dest && !IP_VS_DEST_F_AVAILABLE __ip_vs_conn_put ... cleanup_net ---> infinite looping Fix this by checking whether the timer already started. Signed-off-by: Tan Hu Reviewed-by: Jiang Biao Acked-by: Julian Anastasov Acked-by: Simon Horman Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_core.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 0679dd101e72..7ca926a03b81 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1972,13 +1972,20 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ - if (sysctl_expire_nodest_conn(ipvs)) { + __u32 flags = cp->flags; + + /* when timer already started, silently drop the packet.*/ + if (timer_pending(&cp->timer)) + __ip_vs_conn_put(cp); + else + ip_vs_conn_put(cp); + + if (sysctl_expire_nodest_conn(ipvs) && + !(flags & IP_VS_CONN_F_ONE_PACKET)) { /* try to expire the connection immediately */ ip_vs_conn_expire_now(cp); } - /* don't restart its timer, and silently - drop the packet. */ - __ip_vs_conn_put(cp); + return NF_DROP; } -- cgit v1.2.3-59-g8ed1b