Merge branch 'bpf: Add ipip6 and ip6ip decap support for bpf_skb_adjust_room()'

Ziyang Xuan says:

====================

Add ipip6 and ip6ip decap support for bpf_skb_adjust_room().
Main use case is for using cls_bpf on ingress hook to decapsulate
IPv4 over IPv6 and IPv6 over IPv4 tunnel packets.

And add ipip6 and ip6ip decap testcases to verify that
bpf_skb_adjust_room() correctly decapsulate ipip6 and ip6ip
tunnel packets.

$./test_tc_tunnel.sh
ipip
encap 192.168.1.1 to 192.168.1.2, type ipip, mac none len 100
test basic connectivity
0
test bpf encap without decap (expect failure)
Ncat: TIMEOUT.
1
test bpf encap with tunnel device decap
0
test bpf encap with bpf decap
0
OK
ipip6
encap 192.168.1.1 to 192.168.1.2, type ipip6, mac none len 100
test basic connectivity
0
test bpf encap without decap (expect failure)
Ncat: TIMEOUT.
1
test bpf encap with tunnel device decap
0
test bpf encap with bpf decap
0
OK
ip6ip6
encap fd::1 to fd::2, type ip6tnl, mac none len 100
test basic connectivity
0
test bpf encap without decap (expect failure)
Ncat: TIMEOUT.
1
test bpf encap with tunnel device decap
0
test bpf encap with bpf decap
0
OK
sit
encap fd::1 to fd::2, type sit, mac none len 100
test basic connectivity
0
test bpf encap without decap (expect failure)
Ncat: TIMEOUT.
1
test bpf encap with tunnel device decap
0
test bpf encap with bpf decap
0
OK
...
OK. All tests passed

v3:
  - Fix compilation failure of selftests/bpf.
  - Combine two new branches in bpf_skb_adjust_room().
  - Simplify description for new flags BPF_F_ADJ_ROOM_DECAP_L3_IP*.

v2:
  - Use decap flags to indicate the new IP header.
    Do not rely on skb->encapsulation.
====================
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>

include/uapi/linux/bpf.h

@@ -2647,6 +2647,11 @@ union bpf_attr {
  *		  Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the
  *		  L2 type as Ethernet.
  *
+ *		* **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**,
+ *		  **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**:
+ *		  Indicate the new IP header version after decapsulating the outer
+ *		  IP header. Used when the inner and outer IP versions are different.
+ *
  * 		A call to this helper is susceptible to change the underlying
  * 		packet buffer. Therefore, at load time, all checks on pointers
  * 		previously done by the verifier are invalidated and must be
@@ -5807,6 +5812,8 @@ enum {
 	BPF_F_ADJ_ROOM_ENCAP_L4_UDP	= (1ULL << 4),
 	BPF_F_ADJ_ROOM_NO_CSUM_RESET	= (1ULL << 5),
 	BPF_F_ADJ_ROOM_ENCAP_L2_ETH	= (1ULL << 6),
+	BPF_F_ADJ_ROOM_DECAP_L3_IPV4	= (1ULL << 7),
+	BPF_F_ADJ_ROOM_DECAP_L3_IPV6	= (1ULL << 8),
 };
 
 enum {

net/core/filter.c

@@ -3381,13 +3381,17 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
 #define BPF_F_ADJ_ROOM_ENCAP_L3_MASK	(BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 | \
 					 BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
 
+#define BPF_F_ADJ_ROOM_DECAP_L3_MASK	(BPF_F_ADJ_ROOM_DECAP_L3_IPV4 | \
+					 BPF_F_ADJ_ROOM_DECAP_L3_IPV6)
+
 #define BPF_F_ADJ_ROOM_MASK		(BPF_F_ADJ_ROOM_FIXED_GSO | \
 					 BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \
 					 BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \
 					 BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \
 					 BPF_F_ADJ_ROOM_ENCAP_L2_ETH | \
 					 BPF_F_ADJ_ROOM_ENCAP_L2( \
-					  BPF_ADJ_ROOM_ENCAP_L2_MASK))
+					  BPF_ADJ_ROOM_ENCAP_L2_MASK) | \
+					 BPF_F_ADJ_ROOM_DECAP_L3_MASK)
 
 static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 			    u64 flags)
@@ -3501,6 +3505,7 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
 	int ret;
 
 	if (unlikely(flags & ~(BPF_F_ADJ_ROOM_FIXED_GSO |
+			       BPF_F_ADJ_ROOM_DECAP_L3_MASK |
 			       BPF_F_ADJ_ROOM_NO_CSUM_RESET)))
 		return -EINVAL;
 
@@ -3519,6 +3524,14 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
 	if (unlikely(ret < 0))
 		return ret;
 
+	/* Match skb->protocol to new outer l3 protocol */
+	if (skb->protocol == htons(ETH_P_IP) &&
+	    flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV6)
+		skb->protocol = htons(ETH_P_IPV6);
+	else if (skb->protocol == htons(ETH_P_IPV6) &&
+		 flags & BPF_F_ADJ_ROOM_DECAP_L3_IPV4)
+		skb->protocol = htons(ETH_P_IP);
+
 	if (skb_is_gso(skb)) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
@@ -3608,6 +3621,22 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 		return -ENOTSUPP;
 	}
 
+	if (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) {
+		if (!shrink)
+			return -EINVAL;
+
+		switch (flags & BPF_F_ADJ_ROOM_DECAP_L3_MASK) {
+		case BPF_F_ADJ_ROOM_DECAP_L3_IPV4:
+			len_min = sizeof(struct iphdr);
+			break;
+		case BPF_F_ADJ_ROOM_DECAP_L3_IPV6:
+			len_min = sizeof(struct ipv6hdr);
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
 	len_cur = skb->len - skb_network_offset(skb);
 	if ((shrink && (len_diff_abs >= len_cur ||
 			len_cur - len_diff_abs < len_min)) ||

tools/include/uapi/linux/bpf.h

@@ -2647,6 +2647,11 @@ union bpf_attr {
  *		  Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the
  *		  L2 type as Ethernet.
  *
+ *		* **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**,
+ *		  **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**:
+ *		  Indicate the new IP header version after decapsulating the outer
+ *		  IP header. Used when the inner and outer IP versions are different.
+ *
  * 		A call to this helper is susceptible to change the underlying
  * 		packet buffer. Therefore, at load time, all checks on pointers
  * 		previously done by the verifier are invalidated and must be
@@ -5807,6 +5812,8 @@ enum {
 	BPF_F_ADJ_ROOM_ENCAP_L4_UDP	= (1ULL << 4),
 	BPF_F_ADJ_ROOM_NO_CSUM_RESET	= (1ULL << 5),
 	BPF_F_ADJ_ROOM_ENCAP_L2_ETH	= (1ULL << 6),
+	BPF_F_ADJ_ROOM_DECAP_L3_IPV4    = (1ULL << 7),
+	BPF_F_ADJ_ROOM_DECAP_L3_IPV6    = (1ULL << 8),
 };
 
 enum {

tools/testing/selftests/bpf/progs/test_tc_tunnel.c

@@ -38,6 +38,10 @@ static const int cfg_udp_src = 20000;
 #define	VXLAN_FLAGS     0x8
 #define	VXLAN_VNI       1
 
+#ifndef NEXTHDR_DEST
+#define NEXTHDR_DEST	60
+#endif
+
 /* MPLS label 1000 with S bit (last label) set and ttl of 255. */
 static const __u32 mpls_label = __bpf_constant_htonl(1000 << 12 |
 						     MPLS_LS_S_MASK | 0xff);
@@ -363,6 +367,61 @@ static __always_inline int __encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
 	return TC_ACT_OK;
 }
 
+static int encap_ipv6_ipip6(struct __sk_buff *skb)
+{
+	struct iphdr iph_inner;
+	struct v6hdr h_outer;
+	struct tcphdr tcph;
+	struct ethhdr eth;
+	__u64 flags;
+	int olen;
+
+	if (bpf_skb_load_bytes(skb, ETH_HLEN, &iph_inner,
+			       sizeof(iph_inner)) < 0)
+		return TC_ACT_OK;
+
+	/* filter only packets we want */
+	if (bpf_skb_load_bytes(skb, ETH_HLEN + (iph_inner.ihl << 2),
+			       &tcph, sizeof(tcph)) < 0)
+		return TC_ACT_OK;
+
+	if (tcph.dest != __bpf_constant_htons(cfg_port))
+		return TC_ACT_OK;
+
+	olen = sizeof(h_outer.ip);
+
+	flags = BPF_F_ADJ_ROOM_FIXED_GSO | BPF_F_ADJ_ROOM_ENCAP_L3_IPV6;
+
+	/* add room between mac and network header */
+	if (bpf_skb_adjust_room(skb, olen, BPF_ADJ_ROOM_MAC, flags))
+		return TC_ACT_SHOT;
+
+	/* prepare new outer network header */
+	memset(&h_outer.ip, 0, sizeof(h_outer.ip));
+	h_outer.ip.version = 6;
+	h_outer.ip.hop_limit = iph_inner.ttl;
+	h_outer.ip.saddr.s6_addr[1] = 0xfd;
+	h_outer.ip.saddr.s6_addr[15] = 1;
+	h_outer.ip.daddr.s6_addr[1] = 0xfd;
+	h_outer.ip.daddr.s6_addr[15] = 2;
+	h_outer.ip.payload_len = iph_inner.tot_len;
+	h_outer.ip.nexthdr = IPPROTO_IPIP;
+
+	/* store new outer network header */
+	if (bpf_skb_store_bytes(skb, ETH_HLEN, &h_outer, olen,
+				BPF_F_INVALIDATE_HASH) < 0)
+		return TC_ACT_SHOT;
+
+	/* update eth->h_proto */
+	if (bpf_skb_load_bytes(skb, 0, &eth, sizeof(eth)) < 0)
+		return TC_ACT_SHOT;
+	eth.h_proto = bpf_htons(ETH_P_IPV6);
+	if (bpf_skb_store_bytes(skb, 0, &eth, sizeof(eth), 0) < 0)
+		return TC_ACT_SHOT;
+
+	return TC_ACT_OK;
+}
+
 static __always_inline int encap_ipv6(struct __sk_buff *skb, __u8 encap_proto,
 				      __u16 l2_proto)
 {
@@ -461,6 +520,15 @@ int __encap_ip6tnl_none(struct __sk_buff *skb)
 		return TC_ACT_OK;
 }
 
+SEC("encap_ipip6_none")
+int __encap_ipip6_none(struct __sk_buff *skb)
+{
+	if (skb->protocol == __bpf_constant_htons(ETH_P_IP))
+		return encap_ipv6_ipip6(skb);
+	else
+		return TC_ACT_OK;
+}
+
 SEC("encap_ip6gre_none")
 int __encap_ip6gre_none(struct __sk_buff *skb)
 {
@@ -528,13 +596,33 @@ int __encap_ip6vxlan_eth(struct __sk_buff *skb)
 
 static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 {
+	__u64 flags = BPF_F_ADJ_ROOM_FIXED_GSO;
+	struct ipv6_opt_hdr ip6_opt_hdr;
 	struct gre_hdr greh;
 	struct udphdr udph;
 	int olen = len;
 
 	switch (proto) {
 	case IPPROTO_IPIP:
+		flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4;
+		break;
 	case IPPROTO_IPV6:
+		flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6;
+		break;
+	case NEXTHDR_DEST:
+		if (bpf_skb_load_bytes(skb, off + len, &ip6_opt_hdr,
+				       sizeof(ip6_opt_hdr)) < 0)
+			return TC_ACT_OK;
+		switch (ip6_opt_hdr.nexthdr) {
+		case IPPROTO_IPIP:
+			flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV4;
+			break;
+		case IPPROTO_IPV6:
+			flags |= BPF_F_ADJ_ROOM_DECAP_L3_IPV6;
+			break;
+		default:
+			return TC_ACT_OK;
+		}
 		break;
 	case IPPROTO_GRE:
 		olen += sizeof(struct gre_hdr);
@@ -569,8 +657,7 @@ static int decap_internal(struct __sk_buff *skb, int off, int len, char proto)
 		return TC_ACT_OK;
 	}
 
-	if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC,
-				BPF_F_ADJ_ROOM_FIXED_GSO))
+	if (bpf_skb_adjust_room(skb, -olen, BPF_ADJ_ROOM_MAC, flags))
 		return TC_ACT_SHOT;
 
 	return TC_ACT_OK;

tools/testing/selftests/bpf/test_tc_tunnel.sh

@@ -100,6 +100,9 @@ if [[ "$#" -eq "0" ]]; then
 	echo "ipip"
 	$0 ipv4 ipip none 100
 
+	echo "ipip6"
+	$0 ipv4 ipip6 none 100
+
 	echo "ip6ip6"
 	$0 ipv6 ip6tnl none 100
 
@@ -224,6 +227,9 @@ elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then
 elif [[ "$tuntype" =~ "vxlan" && "$mac" == "eth" ]]; then
 	ttype="vxlan"
 	targs="id 1 dstport 8472 udp6zerocsumrx"
+elif [[ "$tuntype" == "ipip6" ]]; then
+	ttype="ip6tnl"
+	targs=""
 else
 	ttype=$tuntype
 	targs=""
@@ -233,6 +239,9 @@ fi
 if [[ "${tuntype}" == "sit" ]]; then
 	link_addr1="${ns1_v4}"
 	link_addr2="${ns2_v4}"
+elif [[ "${tuntype}" == "ipip6" ]]; then
+	link_addr1="${ns1_v6}"
+	link_addr2="${ns2_v6}"
 else
 	link_addr1="${addr1}"
 	link_addr2="${addr2}"
@@ -287,12 +296,6 @@ else
 	server_listen
 fi
 
-# bpf_skb_net_shrink does not take tunnel flags yet, cannot update L3.
-if [[ "${tuntype}" == "sit" ]]; then
-	echo OK
-	exit 0
-fi
-
 # serverside, use BPF for decap
 ip netns exec "${ns2}" ip link del dev testtun0
 ip netns exec "${ns2}" tc qdisc add dev veth2 clsact