1 files changed, 240 insertions, 8 deletions

diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index b70b48996801..a25c88bc8b75 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -19,10 +19,210 @@ struct nft_flow_offload {
 	struct nft_flowtable	*flowtable;
 };
 
+static enum flow_offload_xmit_type nft_xmit_type(struct dst_entry *dst)
+{
+	if (dst_xfrm(dst))
+		return FLOW_OFFLOAD_XMIT_XFRM;
+
+	return FLOW_OFFLOAD_XMIT_NEIGH;
+}
+
+static void nft_default_forward_path(struct nf_flow_route *route,
+				     struct dst_entry *dst_cache,
+				     enum ip_conntrack_dir dir)
+{
+	route->tuple[!dir].in.ifindex	= dst_cache->dev->ifindex;
+	route->tuple[dir].dst		= dst_cache;
+	route->tuple[dir].xmit_type	= nft_xmit_type(dst_cache);
+}
+
+static bool nft_is_valid_ether_device(const struct net_device *dev)
+{
+	if (!dev || (dev->flags & IFF_LOOPBACK) || dev->type != ARPHRD_ETHER ||
+	    dev->addr_len != ETH_ALEN || !is_valid_ether_addr(dev->dev_addr))
+		return false;
+
+	return true;
+}
+
+static int nft_dev_fill_forward_path(const struct nf_flow_route *route,
+				     const struct dst_entry *dst_cache,
+				     const struct nf_conn *ct,
+				     enum ip_conntrack_dir dir, u8 *ha,
+				     struct net_device_path_stack *stack)
+{
+	const void *daddr = &ct->tuplehash[!dir].tuple.src.u3;
+	struct net_device *dev = dst_cache->dev;
+	struct neighbour *n;
+	u8 nud_state;
+
+	if (!nft_is_valid_ether_device(dev))
+		goto out;
+
+	n = dst_neigh_lookup(dst_cache, daddr);
+	if (!n)
+		return -1;
+
+	read_lock_bh(&n->lock);
+	nud_state = n->nud_state;
+	ether_addr_copy(ha, n->ha);
+	read_unlock_bh(&n->lock);
+	neigh_release(n);
+
+	if (!(nud_state & NUD_VALID))
+		return -1;
+
+out:
+	return dev_fill_forward_path(dev, ha, stack);
+}
+
+struct nft_forward_info {
+	const struct net_device *indev;
+	const struct net_device *outdev;
+	const struct net_device *hw_outdev;
+	struct id {
+		__u16	id;
+		__be16	proto;
+	} encap[NF_FLOW_TABLE_ENCAP_MAX];
+	u8 num_encaps;
+	u8 ingress_vlans;
+	u8 h_source[ETH_ALEN];
+	u8 h_dest[ETH_ALEN];
+	enum flow_offload_xmit_type xmit_type;
+};
+
+static void nft_dev_path_info(const struct net_device_path_stack *stack,
+			      struct nft_forward_info *info,
+			      unsigned char *ha, struct nf_flowtable *flowtable)
+{
+	const struct net_device_path *path;
+	int i;
+
+	memcpy(info->h_dest, ha, ETH_ALEN);
+
+	for (i = 0; i < stack->num_paths; i++) {
+		path = &stack->path[i];
+		switch (path->type) {
+		case DEV_PATH_ETHERNET:
+		case DEV_PATH_DSA:
+		case DEV_PATH_VLAN:
+		case DEV_PATH_PPPOE:
+			info->indev = path->dev;
+			if (is_zero_ether_addr(info->h_source))
+				memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN);
+
+			if (path->type == DEV_PATH_ETHERNET)
+				break;
+			if (path->type == DEV_PATH_DSA) {
+				i = stack->num_paths;
+				break;
+			}
+
+			/* DEV_PATH_VLAN and DEV_PATH_PPPOE */
+			if (info->num_encaps >= NF_FLOW_TABLE_ENCAP_MAX) {
+				info->indev = NULL;
+				break;
+			}
+			if (!info->outdev)
+				info->outdev = path->dev;
+			info->encap[info->num_encaps].id = path->encap.id;
+			info->encap[info->num_encaps].proto = path->encap.proto;
+			info->num_encaps++;
+			if (path->type == DEV_PATH_PPPOE)
+				memcpy(info->h_dest, path->encap.h_dest, ETH_ALEN);
+			break;
+		case DEV_PATH_BRIDGE:
+			if (is_zero_ether_addr(info->h_source))
+				memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN);
+
+			switch (path->bridge.vlan_mode) {
+			case DEV_PATH_BR_VLAN_UNTAG_HW:
+				info->ingress_vlans |= BIT(info->num_encaps - 1);
+				break;
+			case DEV_PATH_BR_VLAN_TAG:
+				info->encap[info->num_encaps].id = path->bridge.vlan_id;
+				info->encap[info->num_encaps].proto = path->bridge.vlan_proto;
+				info->num_encaps++;
+				break;
+			case DEV_PATH_BR_VLAN_UNTAG:
+				info->num_encaps--;
+				break;
+			case DEV_PATH_BR_VLAN_KEEP:
+				break;
+			}
+			info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT;
+			break;
+		default:
+			info->indev = NULL;
+			break;
+		}
+	}
+	if (!info->outdev)
+		info->outdev = info->indev;
+
+	info->hw_outdev = info->indev;
+
+	if (nf_flowtable_hw_offload(flowtable) &&
+	    nft_is_valid_ether_device(info->indev))
+		info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT;
+}
+
+static bool nft_flowtable_find_dev(const struct net_device *dev,
+				   struct nft_flowtable *ft)
+{
+	struct nft_hook *hook;
+	bool found = false;
+
+	list_for_each_entry_rcu(hook, &ft->hook_list, list) {
+		if (hook->ops.dev != dev)
+			continue;
+
+		found = true;
+		break;
+	}
+
+	return found;
+}
+
+static void nft_dev_forward_path(struct nf_flow_route *route,
+				 const struct nf_conn *ct,
+				 enum ip_conntrack_dir dir,
+				 struct nft_flowtable *ft)
+{
+	const struct dst_entry *dst = route->tuple[dir].dst;
+	struct net_device_path_stack stack;
+	struct nft_forward_info info = {};
+	unsigned char ha[ETH_ALEN];
+	int i;
+
+	if (nft_dev_fill_forward_path(route, dst, ct, dir, ha, &stack) >= 0)
+		nft_dev_path_info(&stack, &info, ha, &ft->data);
+
+	if (!info.indev || !nft_flowtable_find_dev(info.indev, ft))
+		return;
+
+	route->tuple[!dir].in.ifindex = info.indev->ifindex;
+	for (i = 0; i < info.num_encaps; i++) {
+		route->tuple[!dir].in.encap[i].id = info.encap[i].id;
+		route->tuple[!dir].in.encap[i].proto = info.encap[i].proto;
+	}
+	route->tuple[!dir].in.num_encaps = info.num_encaps;
+	route->tuple[!dir].in.ingress_vlans = info.ingress_vlans;
+
+	if (info.xmit_type == FLOW_OFFLOAD_XMIT_DIRECT) {
+		memcpy(route->tuple[dir].out.h_source, info.h_source, ETH_ALEN);
+		memcpy(route->tuple[dir].out.h_dest, info.h_dest, ETH_ALEN);
+		route->tuple[dir].out.ifindex = info.outdev->ifindex;
+		route->tuple[dir].out.hw_ifindex = info.hw_outdev->ifindex;
+		route->tuple[dir].xmit_type = info.xmit_type;
+	}
+}
+
 static int nft_flow_route(const struct nft_pktinfo *pkt,
 			  const struct nf_conn *ct,
 			  struct nf_flow_route *route,
-			  enum ip_conntrack_dir dir)
+			  enum ip_conntrack_dir dir,
+			  struct nft_flowtable *ft)
 {
 	struct dst_entry *this_dst = skb_dst(pkt->skb);
 	struct dst_entry *other_dst = NULL;
@@ -32,11 +232,21 @@ 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.saddr = ct->tuplehash[!dir].tuple.src.u3.ip;
 		fl.u.ip4.flowi4_oif = nft_in(pkt)->ifindex;
+		fl.u.ip4.flowi4_iif = this_dst->dev->ifindex;
+		fl.u.ip4.flowi4_tos = RT_TOS(ip_hdr(pkt->skb)->tos);
+		fl.u.ip4.flowi4_mark = pkt->skb->mark;
+		fl.u.ip4.flowi4_flags = FLOWI_FLAG_ANYSRC;
 		break;
 	case NFPROTO_IPV6:
 		fl.u.ip6.daddr = ct->tuplehash[dir].tuple.src.u3.in6;
+		fl.u.ip6.saddr = ct->tuplehash[!dir].tuple.src.u3.in6;
 		fl.u.ip6.flowi6_oif = nft_in(pkt)->ifindex;
+		fl.u.ip6.flowi6_iif = this_dst->dev->ifindex;
+		fl.u.ip6.flowlabel = ip6_flowinfo(ipv6_hdr(pkt->skb));
+		fl.u.ip6.flowi6_mark = pkt->skb->mark;
+		fl.u.ip6.flowi6_flags = FLOWI_FLAG_ANYSRC;
 		break;
 	}
 
@@ -44,8 +254,14 @@ static int nft_flow_route(const struct nft_pktinfo *pkt,
 	if (!other_dst)
 		return -ENOENT;
 
-	route->tuple[dir].dst		= this_dst;
-	route->tuple[!dir].dst		= other_dst;
+	nft_default_forward_path(route, this_dst, dir);
+	nft_default_forward_path(route, other_dst, !dir);
+
+	if (route->tuple[dir].xmit_type	== FLOW_OFFLOAD_XMIT_NEIGH &&
+	    route->tuple[!dir].xmit_type == FLOW_OFFLOAD_XMIT_NEIGH) {
+		nft_dev_forward_path(route, ct, dir, ft);
+		nft_dev_forward_path(route, ct, !dir, ft);
+	}
 
 	return 0;
 }
@@ -74,8 +290,8 @@ 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;
 	struct tcphdr _tcph, *tcph = NULL;
+	struct nf_flow_route route = {};
 	enum ip_conntrack_info ctinfo;
-	struct nf_flow_route route;
 	struct flow_offload *flow;
 	enum ip_conntrack_dir dir;
 	struct nf_conn *ct;
@@ -90,19 +306,33 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 
 	switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum) {
 	case IPPROTO_TCP:
-		tcph = skb_header_pointer(pkt->skb, pkt->xt.thoff,
+		tcph = skb_header_pointer(pkt->skb, nft_thoff(pkt),
 					  sizeof(_tcph), &_tcph);
-		if (unlikely(!tcph || tcph->fin || tcph->rst))
+		if (unlikely(!tcph || tcph->fin || tcph->rst ||
+			     !nf_conntrack_tcp_established(ct)))
 			goto out;
 		break;
 	case IPPROTO_UDP:
 		break;
+#ifdef CONFIG_NF_CT_PROTO_GRE
+	case IPPROTO_GRE: {
+		struct nf_conntrack_tuple *tuple;
+
+		if (ct->status & IPS_NAT_MASK)
+			goto out;
+		tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple;
+		/* No support for GRE v1 */
+		if (tuple->src.u.gre.key || tuple->dst.u.gre.key)
+			goto out;
+		break;
+	}
+#endif
 	default:
 		goto out;
 	}
 
 	if (nf_ct_ext_exist(ct, NF_CT_EXT_HELPER) ||
-	    ct->status & IPS_SEQ_ADJUST)
+	    ct->status & (IPS_SEQ_ADJUST | IPS_NAT_CLASH))
 		goto out;
 
 	if (!nf_ct_is_confirmed(ct))
@@ -112,7 +342,7 @@ static void nft_flow_offload_eval(const struct nft_expr *expr,
 		goto out;
 
 	dir = CTINFO2DIR(ctinfo);
-	if (nft_flow_route(pkt, ct, &route, dir) < 0)
+	if (nft_flow_route(pkt, ct, &route, dir, priv->flowtable) < 0)
 		goto err_flow_route;
 
 	flow = flow_offload_alloc(ct);
@@ -227,6 +457,7 @@ static const struct nft_expr_ops nft_flow_offload_ops = {
 	.destroy	= nft_flow_offload_destroy,
 	.validate	= nft_flow_offload_validate,
 	.dump		= nft_flow_offload_dump,
+	.reduce		= NFT_REDUCE_READONLY,
 };
 
 static struct nft_expr_type nft_flow_offload_type __read_mostly = {
@@ -286,3 +517,4 @@ module_exit(nft_flow_offload_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
 MODULE_ALIAS_NFT_EXPR("flow_offload");
+MODULE_DESCRIPTION("nftables hardware flow offload module");