summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
Diffstat
-rw-r--r--include/linux/netdevice.h13
-rw-r--r--include/net/netfilter/nf_flow_table.h18
-rw-r--r--net/ipv4/ipip.c25
-rw-r--r--net/netfilter/nf_flow_table_core.c3
-rw-r--r--net/netfilter/nf_flow_table_ip.c69
-rw-r--r--net/netfilter/nf_flow_table_path.c38
6 files changed, 153 insertions, 13 deletions
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e808071dbb7d..bf99fe8622da 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -877,6 +877,7 @@ enum net_device_path_type {
DEV_PATH_PPPOE,
DEV_PATH_DSA,
DEV_PATH_MTK_WDMA,
+ DEV_PATH_TUN,
};
struct net_device_path {
@@ -889,6 +890,18 @@ struct net_device_path {
u8 h_dest[ETH_ALEN];
} encap;
struct {
+ union {
+ struct in_addr src_v4;
+ struct in6_addr src_v6;
+ };
+ union {
+ struct in_addr dst_v4;
+ struct in6_addr dst_v6;
+ };
+
+ u8 l3_proto;
+ } tun;
+ struct {
enum {
DEV_PATH_BR_VLAN_KEEP,
DEV_PATH_BR_VLAN_TAG,
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index f7306276ece7..b09c11c048d5 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -107,6 +107,19 @@ enum flow_offload_xmit_type {
#define NF_FLOW_TABLE_ENCAP_MAX 2
+struct flow_offload_tunnel {
+ union {
+ struct in_addr src_v4;
+ struct in6_addr src_v6;
+ };
+ union {
+ struct in_addr dst_v4;
+ struct in6_addr dst_v6;
+ };
+
+ u8 l3_proto;
+};
+
struct flow_offload_tuple {
union {
struct in_addr src_v4;
@@ -130,12 +143,15 @@ struct flow_offload_tuple {
__be16 proto;
} encap[NF_FLOW_TABLE_ENCAP_MAX];
+ struct flow_offload_tunnel tun;
+
/* All members above are keys for lookups, see flow_offload_hash(). */
struct { } __hash;
u8 dir:2,
xmit_type:3,
encap_num:2,
+ tun_num:2,
in_vlan_ingress:2;
u16 mtu;
union {
@@ -206,7 +222,9 @@ struct nf_flow_route {
u16 id;
__be16 proto;
} encap[NF_FLOW_TABLE_ENCAP_MAX];
+ struct flow_offload_tunnel tun;
u8 num_encaps:2,
+ num_tuns:2,
ingress_vlans:2;
} in;
struct {
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 3e03af073a1c..ff95b1b9908e 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -353,6 +353,30 @@ ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd)
return ip_tunnel_ctl(dev, p, cmd);
}
+static int ipip_fill_forward_path(struct net_device_path_ctx *ctx,
+ struct net_device_path *path)
+{
+ struct ip_tunnel *tunnel = netdev_priv(ctx->dev);
+ const struct iphdr *tiph = &tunnel->parms.iph;
+ struct rtable *rt;
+
+ rt = ip_route_output(dev_net(ctx->dev), tiph->daddr, 0, 0, 0,
+ RT_SCOPE_UNIVERSE);
+ if (IS_ERR(rt))
+ return PTR_ERR(rt);
+
+ path->type = DEV_PATH_TUN;
+ path->tun.src_v4.s_addr = tiph->saddr;
+ path->tun.dst_v4.s_addr = tiph->daddr;
+ path->tun.l3_proto = IPPROTO_IPIP;
+ path->dev = ctx->dev;
+
+ ctx->dev = rt->dst.dev;
+ ip_rt_put(rt);
+
+ return 0;
+}
+
static const struct net_device_ops ipip_netdev_ops = {
.ndo_init = ipip_tunnel_init,
.ndo_uninit = ip_tunnel_uninit,
@@ -362,6 +386,7 @@ static const struct net_device_ops ipip_netdev_ops = {
.ndo_get_stats64 = dev_get_tstats64,
.ndo_get_iflink = ip_tunnel_get_iflink,
.ndo_tunnel_ctl = ipip_tunnel_ctl,
+ .ndo_fill_forward_path = ipip_fill_forward_path,
};
#define IPIP_FEATURES (NETIF_F_SG | \
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 6c6a5165f993..06e8251a6644 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -118,7 +118,10 @@ static int flow_offload_fill_route(struct flow_offload *flow,
flow_tuple->in_vlan_ingress |= BIT(j);
j++;
}
+
+ flow_tuple->tun = route->tuple[dir].in.tun;
flow_tuple->encap_num = route->tuple[dir].in.num_encaps;
+ flow_tuple->tun_num = route->tuple[dir].in.num_tuns;
switch (route->tuple[dir].xmit_type) {
case FLOW_OFFLOAD_XMIT_DIRECT:
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 083ceb64ac17..d6a1f0cda189 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -145,8 +145,11 @@ static bool ip_has_options(unsigned int thoff)
static void nf_flow_tuple_encap(struct sk_buff *skb,
struct flow_offload_tuple *tuple)
{
+ __be16 inner_proto = skb->protocol;
struct vlan_ethhdr *veth;
struct pppoe_hdr *phdr;
+ struct iphdr *iph;
+ u16 offset = 0;
int i = 0;
if (skb_vlan_tag_present(skb)) {
@@ -159,13 +162,26 @@ static void nf_flow_tuple_encap(struct sk_buff *skb,
veth = (struct vlan_ethhdr *)skb_mac_header(skb);
tuple->encap[i].id = ntohs(veth->h_vlan_TCI);
tuple->encap[i].proto = skb->protocol;
+ inner_proto = veth->h_vlan_encapsulated_proto;
+ offset += VLAN_HLEN;
break;
case htons(ETH_P_PPP_SES):
phdr = (struct pppoe_hdr *)skb_network_header(skb);
tuple->encap[i].id = ntohs(phdr->sid);
tuple->encap[i].proto = skb->protocol;
+ inner_proto = *((__be16 *)(phdr + 1));
+ offset += PPPOE_SES_HLEN;
break;
}
+
+ if (inner_proto == htons(ETH_P_IP)) {
+ iph = (struct iphdr *)(skb_network_header(skb) + offset);
+ if (iph->protocol == IPPROTO_IPIP) {
+ tuple->tun.dst_v4.s_addr = iph->daddr;
+ tuple->tun.src_v4.s_addr = iph->saddr;
+ tuple->tun.l3_proto = IPPROTO_IPIP;
+ }
+ }
}
struct nf_flowtable_ctx {
@@ -277,11 +293,46 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb,
return NF_STOLEN;
}
+static bool nf_flow_ip4_tunnel_proto(struct sk_buff *skb, u32 *psize)
+{
+ struct iphdr *iph;
+ u16 size;
+
+ if (!pskb_may_pull(skb, sizeof(*iph) + *psize))
+ return false;
+
+ iph = (struct iphdr *)(skb_network_header(skb) + *psize);
+ size = iph->ihl << 2;
+
+ if (ip_is_fragment(iph) || unlikely(ip_has_options(size)))
+ return false;
+
+ if (iph->ttl <= 1)
+ return false;
+
+ if (iph->protocol == IPPROTO_IPIP)
+ *psize += size;
+
+ return true;
+}
+
+static void nf_flow_ip4_tunnel_pop(struct sk_buff *skb)
+{
+ struct iphdr *iph = (struct iphdr *)skb_network_header(skb);
+
+ if (iph->protocol != IPPROTO_IPIP)
+ return;
+
+ skb_pull(skb, iph->ihl << 2);
+ skb_reset_network_header(skb);
+}
+
static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto,
u32 *offset)
{
+ __be16 inner_proto = skb->protocol;
struct vlan_ethhdr *veth;
- __be16 inner_proto;
+ bool ret = false;
switch (skb->protocol) {
case htons(ETH_P_8021Q):
@@ -291,19 +342,23 @@ static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto,
veth = (struct vlan_ethhdr *)skb_mac_header(skb);
if (veth->h_vlan_encapsulated_proto == proto) {
*offset += VLAN_HLEN;
- return true;
+ inner_proto = proto;
+ ret = true;
}
break;
case htons(ETH_P_PPP_SES):
if (nf_flow_pppoe_proto(skb, &inner_proto) &&
inner_proto == proto) {
*offset += PPPOE_SES_HLEN;
- return true;
+ ret = true;
}
break;
}
- return false;
+ if (inner_proto == htons(ETH_P_IP))
+ ret = nf_flow_ip4_tunnel_proto(skb, offset);
+
+ return ret;
}
static void nf_flow_encap_pop(struct sk_buff *skb,
@@ -331,6 +386,9 @@ static void nf_flow_encap_pop(struct sk_buff *skb,
break;
}
}
+
+ if (skb->protocol == htons(ETH_P_IP))
+ nf_flow_ip4_tunnel_pop(skb);
}
struct nf_flow_xmit {
@@ -356,8 +414,7 @@ nf_flow_offload_lookup(struct nf_flowtable_ctx *ctx,
{
struct flow_offload_tuple tuple = {};
- if (skb->protocol != htons(ETH_P_IP) &&
- !nf_flow_skb_encap_protocol(skb, htons(ETH_P_IP), &ctx->offset))
+ if (!nf_flow_skb_encap_protocol(skb, htons(ETH_P_IP), &ctx->offset))
return NULL;
if (nf_flow_tuple_ip(ctx, skb, &tuple) < 0)
diff --git a/net/netfilter/nf_flow_table_path.c b/net/netfilter/nf_flow_table_path.c
index eb9b33a1873a..73717cc32df5 100644
--- a/net/netfilter/nf_flow_table_path.c
+++ b/net/netfilter/nf_flow_table_path.c
@@ -80,6 +80,8 @@ struct nft_forward_info {
__be16 proto;
} encap[NF_FLOW_TABLE_ENCAP_MAX];
u8 num_encaps;
+ struct flow_offload_tunnel tun;
+ u8 num_tuns;
u8 ingress_vlans;
u8 h_source[ETH_ALEN];
u8 h_dest[ETH_ALEN];
@@ -102,6 +104,7 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack,
case DEV_PATH_DSA:
case DEV_PATH_VLAN:
case DEV_PATH_PPPOE:
+ case DEV_PATH_TUN:
info->indev = path->dev;
if (is_zero_ether_addr(info->h_source))
memcpy(info->h_source, path->dev->dev_addr, ETH_ALEN);
@@ -113,14 +116,27 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack,
break;
}
- /* DEV_PATH_VLAN and DEV_PATH_PPPOE */
- if (info->num_encaps >= NF_FLOW_TABLE_ENCAP_MAX) {
- info->indev = NULL;
- break;
+ /* DEV_PATH_VLAN, DEV_PATH_PPPOE and DEV_PATH_TUN */
+ if (path->type == DEV_PATH_TUN) {
+ if (info->num_tuns) {
+ info->indev = NULL;
+ break;
+ }
+ info->tun.src_v6 = path->tun.src_v6;
+ info->tun.dst_v6 = path->tun.dst_v6;
+ info->tun.l3_proto = path->tun.l3_proto;
+ info->num_tuns++;
+ } else {
+ if (info->num_encaps >= NF_FLOW_TABLE_ENCAP_MAX) {
+ info->indev = NULL;
+ break;
+ }
+ info->encap[info->num_encaps].id =
+ path->encap.id;
+ info->encap[info->num_encaps].proto =
+ path->encap.proto;
+ info->num_encaps++;
}
- 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;
@@ -203,6 +219,14 @@ static void nft_dev_forward_path(struct nf_flow_route *route,
route->tuple[!dir].in.encap[i].id = info.encap[i].id;
route->tuple[!dir].in.encap[i].proto = info.encap[i].proto;
}
+
+ if (info.num_tuns) {
+ route->tuple[!dir].in.tun.src_v6 = info.tun.dst_v6;
+ route->tuple[!dir].in.tun.dst_v6 = info.tun.src_v6;
+ route->tuple[!dir].in.tun.l3_proto = info.tun.l3_proto;
+ route->tuple[!dir].in.num_tuns = info.num_tuns;
+ }
+
route->tuple[!dir].in.num_encaps = info.num_encaps;
route->tuple[!dir].in.ingress_vlans = info.ingress_vlans;
route->tuple[dir].out.ifindex = info.outdev->ifindex;
generated by cgit v1.2.3 (git 2.25.1) at 2025-12-22 16:40:21 +0000