From 310529e663ed975d564cf029f878583e70c3b8a3 Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Sun, 30 Dec 2018 17:27:43 +0100 Subject: [PATCH 1/7] netfilter: nf_tables: Fix for endless loop when dumping ruleset __nf_tables_dump_rules() stores the current idx value into cb->args[0] before returning to caller. With multiple chains present, cb->args[0] is therefore updated after each chain's rules have been traversed. This though causes the final nf_tables_dump_rules() run (which should return an skb->len of zero since no rules are left to dump) to continue dumping rules for each but the first chain. Fix this by moving the cb->args[0] update to nf_tables_dump_rules(). With no final action to be performed anymore in __nf_tables_dump_rules(), drop 'out_unfinished' jump label and 'rc' variable - instead return the appropriate value directly. Fixes: 241faeceb849c ("netfilter: nf_tables: Speed up selective rule dumps") Signed-off-by: Phil Sutter Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 2b0a93300dd7..e3ddd8e95e58 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2304,7 +2304,6 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, struct net *net = sock_net(skb->sk); unsigned int s_idx = cb->args[0]; const struct nft_rule *rule; - int rc = 1; list_for_each_entry_rcu(rule, &chain->rules, list) { if (!nft_is_active(net, rule)) @@ -2321,16 +2320,13 @@ static int __nf_tables_dump_rules(struct sk_buff *skb, NLM_F_MULTI | NLM_F_APPEND, table->family, table, chain, rule) < 0) - goto out_unfinished; + return 1; nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: (*idx)++; } - rc = 0; -out_unfinished: - cb->args[0] = *idx; - return rc; + return 0; } static int nf_tables_dump_rules(struct sk_buff *skb, @@ -2382,6 +2378,8 @@ static int nf_tables_dump_rules(struct sk_buff *skb, } done: rcu_read_unlock(); + + cb->args[0] = idx; return skb->len; } From b91d9036883793122cf6575ca4dfbfbdd201a83d Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Fri, 4 Jan 2019 17:56:16 +0900 Subject: [PATCH 2/7] netfilter: nf_tables: fix leaking object reference count There is no code that decreases the reference count of stateful objects in error path of the nft_add_set_elem(). this causes a leak of reference count of stateful objects. Test commands: $nft add table ip filter $nft add counter ip filter c1 $nft add map ip filter m1 { type ipv4_addr : counter \;} $nft add element ip filter m1 { 1 : c1 } $nft add element ip filter m1 { 1 : c1 } $nft delete element ip filter m1 { 1 } $nft delete counter ip filter c1 Result: Error: Could not process rule: Device or resource busy delete counter ip filter c1 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^ At the second 'nft add element ip filter m1 { 1 : c1 }', the reference count of the 'c1' is increased then it tries to insert into the 'm1'. but the 'm1' already has same element so it returns -EEXIST. But it doesn't decrease the reference count of the 'c1' in the error path. Due to a leak of the reference count of the 'c1', the 'c1' can't be removed by 'nft delete counter ip filter c1'. Fixes: 8aeff920dcc9 ("netfilter: nf_tables: add stateful object reference to set elements") Signed-off-by: Taehee Yoo Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index e3ddd8e95e58..dcea979423bc 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4506,6 +4506,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err5: kfree(trans); err4: + if (obj) + obj->use--; kfree(elem.priv); err3: if (nla[NFTA_SET_ELEM_DATA] != NULL) From 715849ab31f8e57bbad84cc6c38912aeba6beb21 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Tue, 8 Jan 2019 23:18:58 +0100 Subject: [PATCH 3/7] netfilter: nf_tables: selective rule dump needs table to be specified Table needs to be specified for selective rule dumps per chain. Fixes: 241faeceb849c ("netfilter: nf_tables: Speed up selective rule dumps") Reported-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index dcea979423bc..fb07f6cfc719 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2350,7 +2350,7 @@ static int nf_tables_dump_rules(struct sk_buff *skb, if (ctx && ctx->table && strcmp(ctx->table, table->name) != 0) continue; - if (ctx && ctx->chain) { + if (ctx && ctx->table && ctx->chain) { struct rhlist_head *list, *tmp; list = rhltable_lookup(&table->chains_ht, ctx->chain, From a799aea0988ea0d1b1f263e996fdad2f6133c680 Mon Sep 17 00:00:00 2001 From: wenxu Date: Wed, 9 Jan 2019 10:40:11 +0800 Subject: [PATCH 4/7] netfilter: nft_flow_offload: Fix reverse route lookup Using the following example: client 1.1.1.7 ---> 2.2.2.7 which dnat to 10.0.0.7 server The first reply packet (ie. syn+ack) uses an incorrect destination address for the reverse route lookup since it uses: daddr = ct->tuplehash[!dir].tuple.dst.u3.ip; which is 2.2.2.7 in the scenario that is described above, while this should be: daddr = ct->tuplehash[dir].tuple.src.u3.ip; that is 10.0.0.7. Signed-off-by: wenxu Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_flow_offload.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 974525eb92df..ccdb8f5ababb 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -29,10 +29,10 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, memset(&fl, 0, sizeof(fl)); switch (nft_pf(pkt)) { case NFPROTO_IPV4: - fl.u.ip4.daddr = ct->tuplehash[!dir].tuple.dst.u3.ip; + fl.u.ip4.daddr = ct->tuplehash[dir].tuple.src.u3.ip; break; case NFPROTO_IPV6: - fl.u.ip6.daddr = ct->tuplehash[!dir].tuple.dst.u3.in6; + fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6; break; } From e2c8d550a973bb34fc28bc8d0ec996f84562fb8a Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Wed, 2 Jan 2019 19:14:31 -0800 Subject: [PATCH 5/7] netfilter: ebtables: account ebt_table_info to kmemcg The [ip,ip6,arp]_tables use x_tables_info internally and the underlying memory is already accounted to kmemcg. Do the same for ebtables. The syzbot, by using setsockopt(EBT_SO_SET_ENTRIES), was able to OOM the whole system from a restricted memcg, a potential DoS. By accounting the ebt_table_info, the memory used for ebt_table_info can be contained within the memcg of the allocating process. However the lifetime of ebt_table_info is independent of the allocating process and is tied to the network namespace. So, the oom-killer will not be able to relieve the memory pressure due to ebt_table_info memory. The memory for ebt_table_info is allocated through vmalloc. Currently vmalloc does not handle the oom-killed allocating process correctly and one large allocation can bypass memcg limit enforcement. So, with this patch, at least the small allocations will be contained. For large allocations, we need to fix vmalloc. Reported-by: syzbot+7713f3aa67be76b1552c@syzkaller.appspotmail.com Signed-off-by: Shakeel Butt Reviewed-by: Kirill Tkhai Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/ebtables.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 491828713e0b..5e55cef0cec3 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1137,14 +1137,16 @@ static int do_replace(struct net *net, const void __user *user, tmp.name[sizeof(tmp.name) - 1] = 0; countersize = COUNTER_OFFSET(tmp.nentries) * nr_cpu_ids; - newinfo = vmalloc(sizeof(*newinfo) + countersize); + newinfo = __vmalloc(sizeof(*newinfo) + countersize, GFP_KERNEL_ACCOUNT, + PAGE_KERNEL); if (!newinfo) return -ENOMEM; if (countersize) memset(newinfo->counters, 0, countersize); - newinfo->entries = vmalloc(tmp.entries_size); + newinfo->entries = __vmalloc(tmp.entries_size, GFP_KERNEL_ACCOUNT, + PAGE_KERNEL); if (!newinfo->entries) { ret = -ENOMEM; goto free_newinfo; From 10f4e765879e514e1ce7f52ed26603047af196e2 Mon Sep 17 00:00:00 2001 From: wenxu Date: Thu, 10 Jan 2019 14:51:35 +0800 Subject: [PATCH 6/7] netfilter: nft_flow_offload: fix interaction with vrf slave device In the forward chain, the iif is changed from slave device to master vrf device. Thus, flow offload does not find a match on the lower slave device. This patch uses the cached route, ie. dst->dev, to update the iif and oif fields in the flow entry. After this patch, the following example works fine: # ip addr add dev eth0 1.1.1.1/24 # ip addr add dev eth1 10.0.0.1/24 # ip link add user1 type vrf table 1 # ip l set user1 up # ip l set dev eth0 master user1 # ip l set dev eth1 master user1 # nft add table firewall # nft add flowtable f fb1 { hook ingress priority 0 \; devices = { eth0, eth1 } \; } # nft add chain f ftb-all {type filter hook forward priority 0 \; policy accept \; } # nft add rule f ftb-all ct zone 1 ip protocol tcp flow offload @fb1 # nft add rule f ftb-all ct zone 1 ip protocol udp flow offload @fb1 Signed-off-by: wenxu Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_flow_table.h | 1 - net/netfilter/nf_flow_table_core.c | 5 +++-- net/netfilter/nft_flow_offload.c | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 7d5cda7ce32a..3e370cb36263 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -84,7 +84,6 @@ struct flow_offload { struct nf_flow_route { struct { struct dst_entry *dst; - int ifindex; } tuple[FLOW_OFFLOAD_DIR_MAX]; }; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index fa0844e2a68d..c0c72ae9df42 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -28,6 +28,7 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct, { struct flow_offload_tuple *ft = &flow->tuplehash[dir].tuple; struct nf_conntrack_tuple *ctt = &ct->tuplehash[dir].tuple; + struct dst_entry *other_dst = route->tuple[!dir].dst; struct dst_entry *dst = route->tuple[dir].dst; ft->dir = dir; @@ -50,8 +51,8 @@ flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct, ft->src_port = ctt->src.u.tcp.port; ft->dst_port = ctt->dst.u.tcp.port; - ft->iifidx = route->tuple[dir].ifindex; - ft->oifidx = route->tuple[!dir].ifindex; + ft->iifidx = other_dst->dev->ifindex; + ft->oifidx = dst->dev->ifindex; ft->dst_cache = dst; } diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index ccdb8f5ababb..188c6bbf4e16 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -30,9 +30,11 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, switch (nft_pf(pkt)) { case NFPROTO_IPV4: fl.u.ip4.daddr = ct->tuplehash[dir].tuple.src.u3.ip; + fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex; break; case NFPROTO_IPV6: fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6; + fl.u.ip6.flowi6_oif = nft_in(pkt)->ifindex; break; } @@ -41,9 +43,7 @@ static int nft_flow_route(const struct nft_pktinfo *pkt, return -ENOENT; route->tuple[dir].dst = this_dst; - route->tuple[dir].ifindex = nft_in(pkt)->ifindex; route->tuple[!dir].dst = other_dst; - route->tuple[!dir].ifindex = nft_out(pkt)->ifindex; return 0; } From 2314e879747e82896f51cce4488f6a00f3e1af7b Mon Sep 17 00:00:00 2001 From: Henry Yen Date: Mon, 14 Jan 2019 17:59:43 +0800 Subject: [PATCH 7/7] netfilter: nft_flow_offload: fix checking method of conntrack helper This patch uses nfct_help() to detect whether an established connection needs conntrack helper instead of using test_bit(IPS_HELPER_BIT, &ct->status). The reason is that IPS_HELPER_BIT is only set when using explicit CT target. However, in the case that a device enables conntrack helper via command "echo 1 > /proc/sys/net/netfilter/nf_conntrack_helper", the status of IPS_HELPER_BIT will not present any change, and consequently it loses the checking ability in the context. Signed-off-by: Henry Yen Reviewed-by: Ryder Lee Tested-by: John Crispin Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_flow_offload.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 188c6bbf4e16..6e6b9adf7d38 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -12,6 +12,7 @@ #include #include #include +#include struct nft_flow_offload { struct nft_flowtable *flowtable; @@ -66,6 +67,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, { struct nft_flow_offload *priv = nft_expr_priv(expr); struct nf_flowtable *flowtable = &priv->flowtable->data; + const struct nf_conn_help *help; enum ip_conntrack_info ctinfo; struct nf_flow_route route; struct flow_offload *flow; @@ -88,7 +90,8 @@ static void nft_flow_offload_eval(const struct nft_expr *expr, goto out; } - if (test_bit(IPS_HELPER_BIT, &ct->status)) + help = nfct_help(ct); + if (help) goto out; if (ctinfo == IP_CT_NEW ||