netdev - [PATCH net-next,RFC 10/13] netfilter: nf_flow_table: add flowtable for early ingress hook

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20180614141947.3580-11-pablo@netfilter.org>
Date:   Thu, 14 Jun 2018 16:19:44 +0200
From:   Pablo Neira Ayuso <pablo@...filter.org>
To:     netfilter-devel@...r.kernel.org
Cc:     netdev@...r.kernel.org, steffen.klassert@...unet.com
Subject: [PATCH net-next,RFC 10/13] netfilter: nf_flow_table: add flowtable for early ingress hook

Add the new flowtable type for the early ingress hook, this allows
us to combine the custom GRO chaining with the flowtable abstraction
to define fastpaths.

Signed-off-by: Pablo Neira Ayuso <pablo@...filter.org>
Signed-off-by: Steffen Klassert <steffen.klassert@...unet.com>
---
 include/net/netfilter/nf_flow_table.h   |  3 ++
 net/ipv4/netfilter/nf_flow_table_ipv4.c | 11 ++++++
 net/netfilter/nf_flow_table_ip.c        | 62 +++++++++++++++++++++++++++++++++
 3 files changed, 76 insertions(+)

diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 4606bad41155..e270269dd1e8 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -126,6 +126,9 @@ unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 				     const struct nf_hook_state *state);
 unsigned int nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 				       const struct nf_hook_state *state);
+unsigned int nf_flow_offload_early_ingress_ip_hook(void *priv,
+						   struct sk_buff *skb,
+						   const struct nf_hook_state *state);
 
 #define MODULE_ALIAS_NF_FLOWTABLE(family)	\
 	MODULE_ALIAS("nf-flowtable-" __stringify(family))
diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c
index 681c0d5c47d7..b771000ca894 100644
--- a/net/ipv4/netfilter/nf_flow_table_ipv4.c
+++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c
@@ -14,15 +14,26 @@ static struct nf_flowtable_type flowtable_ipv4 = {
 	.owner		= THIS_MODULE,
 };
 
+static struct nf_flowtable_type flowtable_ipv4_early = {
+	.family		= NFPROTO_IPV4,
+	.hooknum	= NF_NETDEV_EARLY_INGRESS,
+	.init		= nf_flow_table_init,
+	.free		= nf_flow_table_free,
+	.hook		= nf_flow_offload_early_ingress_ip_hook,
+	.owner		= THIS_MODULE,
+};
+
 static int __init nf_flow_ipv4_module_init(void)
 {
 	nft_register_flowtable_type(&flowtable_ipv4);
+	nft_register_flowtable_type(&flowtable_ipv4_early);
 
 	return 0;
 }
 
 static void __exit nf_flow_ipv4_module_exit(void)
 {
+	nft_unregister_flowtable_type(&flowtable_ipv4_early);
 	nft_unregister_flowtable_type(&flowtable_ipv4);
 }
 
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 15ed91309992..0828e49bd95e 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -11,6 +11,7 @@
 #include <net/ip6_route.h>
 #include <net/neighbour.h>
 #include <net/netfilter/nf_flow_table.h>
+#include <net/xfrm.h>
 /* For layer 4 checksum field offset. */
 #include <linux/tcp.h>
 #include <linux/udp.h>
@@ -487,3 +488,64 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 	return NF_STOLEN;
 }
 EXPORT_SYMBOL_GPL(nf_flow_offload_ipv6_hook);
+
+unsigned int
+nf_flow_offload_early_ingress_ip_hook(void *priv, struct sk_buff *skb,
+				      const struct nf_hook_state *state)
+{
+	struct flow_offload_tuple_rhash *tuplehash;
+	struct nf_flowtable *flow_table = priv;
+	struct flow_offload_tuple tuple = {};
+	enum flow_offload_tuple_dir dir;
+	struct flow_offload *flow;
+	struct net_device *outdev;
+	const struct rtable *rt;
+	unsigned int thoff;
+	struct iphdr *iph;
+
+	if (skb->protocol != htons(ETH_P_IP))
+		return NF_ACCEPT;
+
+	if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0)
+		return NF_ACCEPT;
+
+	tuplehash = flow_offload_lookup(flow_table, &tuple);
+	if (tuplehash == NULL)
+		return NF_ACCEPT;
+
+	outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx);
+	if (!outdev)
+		return NF_ACCEPT;
+
+	dir = tuplehash->tuple.dir;
+	flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]);
+	rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache;
+
+	if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)) &&
+	    (ip_hdr(skb)->frag_off & htons(IP_DF)) != 0)
+		return NF_ACCEPT;
+
+	if (skb_try_make_writable(skb, sizeof(*iph)))
+		return NF_DROP;
+
+	thoff = ip_hdr(skb)->ihl * 4;
+	if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff))
+		return NF_ACCEPT;
+
+	if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) &&
+	    nf_flow_nat_ip(flow, skb, thoff, dir) < 0)
+		return NF_DROP;
+
+	flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT;
+
+	skb_dst_set_noref(skb, flow->tuplehash[dir].tuple.dst_cache);
+
+	if (skb_dst(skb)->xfrm &&
+	    !xfrm_dev_offload_ok(skb, skb_dst(skb)->xfrm))
+		return NF_ACCEPT;
+
+	NAPI_GRO_CB(skb)->is_ffwd = 1;
+
+	return NF_STOLEN;
+}
+EXPORT_SYMBOL_GPL(nf_flow_offload_early_ingress_ip_hook);
-- 
2.11.0