From 895b5c9f206eb7d25dc1360a8ccfc5958895eb89 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 29 Sep 2019 20:54:03 +0200 Subject: netfilter: drop bridge nf reset from nf_reset commit 174e23810cd31 ("sk_buff: drop all skb extensions on free and skb scrubbing") made napi recycle always drop skb extensions. The additional skb_ext_del() that is performed via nf_reset on napi skb recycle is not needed anymore. Most nf_reset() calls in the stack are there so queued skb won't block 'rmmod nf_conntrack' indefinitely. This removes the skb_ext_del from nf_reset, and renames it to a more fitting nf_reset_ct(). In a few selected places, add a call to skb_ext_reset to make sure that no active extensions remain. I am submitting this for "net", because we're still early in the release cycle. The patch applies to net-next too, but I think the rename causes needless divergence between those trees. Suggested-by: Eric Dumazet Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipvs/ip_vs_xmit.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 9c464d24beec..888d3068a492 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -613,7 +613,7 @@ static inline int ip_vs_tunnel_xmit_prepare(struct sk_buff *skb, if (unlikely(cp->flags & IP_VS_CONN_F_NFCT)) ret = ip_vs_confirm_conntrack(skb); if (ret == NF_ACCEPT) { - nf_reset(skb); + nf_reset_ct(skb); skb_forward_csum(skb); } return ret; -- cgit v1.2.3 From 34a4c95abd25ab41fb390b985a08a651b1fa0b0f Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Mon, 30 Sep 2019 11:05:49 +0200 Subject: netfilter: nft_connlimit: disable bh on garbage collection BH must be disabled when invoking nf_conncount_gc_list() to perform garbage collection, otherwise deadlock might happen. nf_conncount_add+0x1f/0x50 [nf_conncount] nft_connlimit_eval+0x4c/0xe0 [nft_connlimit] nft_dynset_eval+0xb5/0x100 [nf_tables] nft_do_chain+0xea/0x420 [nf_tables] ? sch_direct_xmit+0x111/0x360 ? noqueue_init+0x10/0x10 ? __qdisc_run+0x84/0x510 ? tcp_packet+0x655/0x1610 [nf_conntrack] ? ip_finish_output2+0x1a7/0x430 ? tcp_error+0x130/0x150 [nf_conntrack] ? nf_conntrack_in+0x1fc/0x4c0 [nf_conntrack] nft_do_chain_ipv4+0x66/0x80 [nf_tables] nf_hook_slow+0x44/0xc0 ip_rcv+0xb5/0xd0 ? ip_rcv_finish_core.isra.19+0x360/0x360 __netif_receive_skb_one_core+0x52/0x70 netif_receive_skb_internal+0x34/0xe0 napi_gro_receive+0xba/0xe0 e1000_clean_rx_irq+0x1e9/0x420 [e1000e] e1000e_poll+0xbe/0x290 [e1000e] net_rx_action+0x149/0x3b0 __do_softirq+0xde/0x2d8 irq_exit+0xba/0xc0 do_IRQ+0x85/0xd0 common_interrupt+0xf/0xf RIP: 0010:nf_conncount_gc_list+0x3b/0x130 [nf_conncount] Fixes: 2f971a8f4255 ("netfilter: nf_conncount: move all list iterations under spinlock") Reported-by: Laura Garcia Liebana Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_connlimit.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c index af1497ab9464..69d6173f91e2 100644 --- a/net/netfilter/nft_connlimit.c +++ b/net/netfilter/nft_connlimit.c @@ -218,8 +218,13 @@ static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx, static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr) { struct nft_connlimit *priv = nft_expr_priv(expr); + bool ret; - return nf_conncount_gc_list(net, &priv->list); + local_bh_disable(); + ret = nf_conncount_gc_list(net, &priv->list); + local_bh_enable(); + + return ret; } static struct nft_expr_type nft_connlimit_type; -- cgit v1.2.3 From e37542ba111f3974dc622ae0a21c1787318de500 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 9 Oct 2019 09:19:13 -0700 Subject: netfilter: conntrack: avoid possible false sharing As hinted by KCSAN, we need at least one READ_ONCE() to prevent a compiler optimization. More details on : https://github.com/google/ktsan/wiki/READ_ONCE-and-WRITE_ONCE#it-may-improve-performance sysbot report : BUG: KCSAN: data-race in __nf_ct_refresh_acct / __nf_ct_refresh_acct read to 0xffff888123eb4f08 of 4 bytes by interrupt on cpu 0: __nf_ct_refresh_acct+0xd4/0x1b0 net/netfilter/nf_conntrack_core.c:1796 nf_ct_refresh_acct include/net/netfilter/nf_conntrack.h:201 [inline] nf_conntrack_tcp_packet+0xd40/0x3390 net/netfilter/nf_conntrack_proto_tcp.c:1161 nf_conntrack_handle_packet net/netfilter/nf_conntrack_core.c:1633 [inline] nf_conntrack_in+0x410/0xaa0 net/netfilter/nf_conntrack_core.c:1727 ipv4_conntrack_in+0x27/0x40 net/netfilter/nf_conntrack_proto.c:178 nf_hook_entry_hookfn include/linux/netfilter.h:135 [inline] nf_hook_slow+0x83/0x160 net/netfilter/core.c:512 nf_hook include/linux/netfilter.h:260 [inline] NF_HOOK include/linux/netfilter.h:303 [inline] ip_rcv+0x12f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:5004 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5118 netif_receive_skb_internal+0x59/0x190 net/core/dev.c:5208 napi_skb_finish net/core/dev.c:5671 [inline] napi_gro_receive+0x28f/0x330 net/core/dev.c:5704 receive_buf+0x284/0x30b0 drivers/net/virtio_net.c:1061 virtnet_receive drivers/net/virtio_net.c:1323 [inline] virtnet_poll+0x436/0x7d0 drivers/net/virtio_net.c:1428 napi_poll net/core/dev.c:6352 [inline] net_rx_action+0x3ae/0xa50 net/core/dev.c:6418 __do_softirq+0x115/0x33f kernel/softirq.c:292 write to 0xffff888123eb4f08 of 4 bytes by task 7191 on cpu 1: __nf_ct_refresh_acct+0xfb/0x1b0 net/netfilter/nf_conntrack_core.c:1797 nf_ct_refresh_acct include/net/netfilter/nf_conntrack.h:201 [inline] nf_conntrack_tcp_packet+0xd40/0x3390 net/netfilter/nf_conntrack_proto_tcp.c:1161 nf_conntrack_handle_packet net/netfilter/nf_conntrack_core.c:1633 [inline] nf_conntrack_in+0x410/0xaa0 net/netfilter/nf_conntrack_core.c:1727 ipv4_conntrack_local+0xbe/0x130 net/netfilter/nf_conntrack_proto.c:200 nf_hook_entry_hookfn include/linux/netfilter.h:135 [inline] nf_hook_slow+0x83/0x160 net/netfilter/core.c:512 nf_hook include/linux/netfilter.h:260 [inline] __ip_local_out+0x1f7/0x2b0 net/ipv4/ip_output.c:114 ip_local_out+0x31/0x90 net/ipv4/ip_output.c:123 __ip_queue_xmit+0x3a8/0xa40 net/ipv4/ip_output.c:532 ip_queue_xmit+0x45/0x60 include/net/ip.h:236 __tcp_transmit_skb+0xdeb/0x1cd0 net/ipv4/tcp_output.c:1158 __tcp_send_ack+0x246/0x300 net/ipv4/tcp_output.c:3685 tcp_send_ack+0x34/0x40 net/ipv4/tcp_output.c:3691 tcp_cleanup_rbuf+0x130/0x360 net/ipv4/tcp.c:1575 Reported by Kernel Concurrency Sanitizer on: CPU: 1 PID: 7191 Comm: syz-fuzzer Not tainted 5.3.0+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Fixes: cc16921351d8 ("netfilter: conntrack: avoid same-timeout update") Signed-off-by: Eric Dumazet Reported-by: syzbot Cc: Jozsef Kadlecsik Cc: Florian Westphal Acked-by: Pablo Neira Ayuso Signed-off-by: Jakub Kicinski --- net/netfilter/nf_conntrack_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/netfilter') diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 0c63120b2db2..5cd610b547e0 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1792,8 +1792,8 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, if (nf_ct_is_confirmed(ct)) extra_jiffies += nfct_time_stamp; - if (ct->timeout != extra_jiffies) - ct->timeout = extra_jiffies; + if (READ_ONCE(ct->timeout) != extra_jiffies) + WRITE_ONCE(ct->timeout, extra_jiffies); acct: if (do_acct) nf_ct_acct_update(ct, ctinfo, skb->len); -- cgit v1.2.3