Merge branch 'bpf-l2-encap'

Alan Maguire says:

====================
Extend bpf_skb_adjust_room growth to mark inner MAC header so
that L2 encapsulation can be used for tc tunnels.

Patch #1 extends the existing test_tc_tunnel to support UDP
encapsulation; later we want to be able to test MPLS over UDP
and MPLS over GRE encapsulation.

Patch #2 adds the BPF_F_ADJ_ROOM_ENCAP_L2(len) macro, which
allows specification of inner mac length.  Other approaches were
explored prior to taking this approach.  Specifically, I tried
automatically computing the inner mac length on the basis of the
specified flags (so inner maclen for GRE/IPv4 encap is the len_diff
specified to bpf_skb_adjust_room minus GRE + IPv4 header length
for example).  Problem with this is that we don't know for sure
what form of GRE/UDP header we have; is it a full GRE header,
or is it a FOU UDP header or generic UDP encap header? My fear
here was we'd end up with an explosion of flags.  The other approach
tried was to support inner L2 header marking as a separate room
adjustment, i.e. adjust for L3/L4 encap, then call
bpf_skb_adjust_room for L2 encap.  This can be made to work but
because it imposed an order on operations, felt a bit clunky.

Patch #3 syncs tools/ bpf.h.

Patch #4 extends the tests again to support MPLSoverGRE,
MPLSoverUDP, and transparent ethernet bridging (TEB) where
the inner L2 header is an ethernet header.  Testing of BPF
encap against tunnels is done for cases where configuration
of such tunnels is possible (MPLSoverGRE[6], MPLSoverUDP,
gre[6]tap), and skipped otherwise.  Testing of BPF encap/decap
is always carried out.

Changes since v2:
 - updated tools/testing/selftest/bpf/config with FOU/MPLS CONFIG
   variables (patches 1, 4)
 - reduced noise in patch 1 by avoiding unnecessary movement of code
 - eliminated inner_mac variable in bpf_skb_net_grow (patch 2)

Changes since v1:
 - fixed formatting of commit references.
 - BPF_F_ADJ_ROOM_FIXED_GSO flag enabled on all variants (patch 1)
 - fixed fou6 options for UDP encap; checksum errors observed were
   due to the fact fou6 tunnel was not set up with correct ipproto
   options (41 -6).  0 checksums work fine (patch 1)
 - added definitions for mask and shift used in setting L2 length
   (patch 2)
 - allow udp encap with fixed GSO (patch 2)
 - changed "elen" to "l2_len" to be more descriptive (patch 4)
====================
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

include/uapi/linux/bpf.h

@@ -1523,6 +1523,10 @@ union bpf_attr {
  *		* **BPF_F_ADJ_ROOM_ENCAP_L4_UDP **:
  *		  Use with ENCAP_L3 flags to further specify the tunnel type.
  *
+ *		* **BPF_F_ADJ_ROOM_ENCAP_L2(len) **:
+ *		  Use with ENCAP_L3/L4 flags to further specify the tunnel
+ *		  type; **len** is the length of the inner MAC header.
+ *
  * 		A call to this helper is susceptible to change the underlaying
  * 		packet buffer. Therefore, at load time, all checks on pointers
  * 		previously done by the verifier are invalidated and must be
@@ -2664,10 +2668,16 @@ enum bpf_func_id {
 /* BPF_FUNC_skb_adjust_room flags. */
 #define BPF_F_ADJ_ROOM_FIXED_GSO	(1ULL << 0)
 
+#define	BPF_ADJ_ROOM_ENCAP_L2_MASK	0xff
+#define	BPF_ADJ_ROOM_ENCAP_L2_SHIFT	56
+
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	(1ULL << 1)
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	(1ULL << 2)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_GRE	(1ULL << 3)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_UDP	(1ULL << 4)
+#define	BPF_F_ADJ_ROOM_ENCAP_L2(len)	(((__u64)len & \
+					  BPF_ADJ_ROOM_ENCAP_L2_MASK) \
+					 << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
 
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {

net/core/filter.c

@@ -2969,11 +2969,14 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
 #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_L4_UDP | \
+					 BPF_F_ADJ_ROOM_ENCAP_L2( \
+					  BPF_ADJ_ROOM_ENCAP_L2_MASK))
 
 static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 			    u64 flags)
 {
+	u8 inner_mac_len = flags >> BPF_ADJ_ROOM_ENCAP_L2_SHIFT;
 	bool encap = flags & BPF_F_ADJ_ROOM_ENCAP_L3_MASK;
 	u16 mac_len = 0, inner_net = 0, inner_trans = 0;
 	unsigned int gso_type = SKB_GSO_DODGY;
@@ -3008,6 +3011,8 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 
 		mac_len = skb->network_header - skb->mac_header;
 		inner_net = skb->network_header;
+		if (inner_mac_len > len_diff)
+			return -EINVAL;
 		inner_trans = skb->transport_header;
 	}
 
@@ -3016,8 +3021,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 		return ret;
 
 	if (encap) {
-		/* inner mac == inner_net on l3 encap */
-		skb->inner_mac_header = inner_net;
+		skb->inner_mac_header = inner_net - inner_mac_len;
 		skb->inner_network_header = inner_net;
 		skb->inner_transport_header = inner_trans;
 		skb_set_inner_protocol(skb, skb->protocol);
@@ -3031,7 +3035,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 			gso_type |= SKB_GSO_GRE;
 		else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
 			gso_type |= SKB_GSO_IPXIP6;
-		else
+		else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4)
 			gso_type |= SKB_GSO_IPXIP4;
 
 		if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE ||

tools/include/uapi/linux/bpf.h

@@ -1523,6 +1523,10 @@ union bpf_attr {
  *		* **BPF_F_ADJ_ROOM_ENCAP_L4_UDP **:
  *		  Use with ENCAP_L3 flags to further specify the tunnel type.
  *
+ *		* **BPF_F_ADJ_ROOM_ENCAP_L2(len) **:
+ *		  Use with ENCAP_L3/L4 flags to further specify the tunnel
+ *		  type; **len** is the length of the inner MAC header.
+ *
  * 		A call to this helper is susceptible to change the underlaying
  * 		packet buffer. Therefore, at load time, all checks on pointers
  * 		previously done by the verifier are invalidated and must be
@@ -2664,10 +2668,16 @@ enum bpf_func_id {
 /* BPF_FUNC_skb_adjust_room flags. */
 #define BPF_F_ADJ_ROOM_FIXED_GSO	(1ULL << 0)
 
+#define	BPF_ADJ_ROOM_ENCAP_L2_MASK	0xff
+#define	BPF_ADJ_ROOM_ENCAP_L2_SHIFT	56
+
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	(1ULL << 1)
 #define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	(1ULL << 2)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_GRE	(1ULL << 3)
 #define BPF_F_ADJ_ROOM_ENCAP_L4_UDP	(1ULL << 4)
+#define	BPF_F_ADJ_ROOM_ENCAP_L2(len)	(((__u64)len & \
+					  BPF_ADJ_ROOM_ENCAP_L2_MASK) \
+					 << BPF_ADJ_ROOM_ENCAP_L2_SHIFT)
 
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {

tools/testing/selftests/bpf/config

@@ -25,3 +25,11 @@ CONFIG_XDP_SOCKETS=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_IPV6_TUNNEL=y
 CONFIG_IPV6_GRE=y
+CONFIG_NET_FOU=m
+CONFIG_NET_FOU_IP_TUNNELS=y
+CONFIG_IPV6_FOU=m
+CONFIG_IPV6_FOU_TUNNEL=m
+CONFIG_MPLS=y
+CONFIG_NET_MPLS_GSO=m
+CONFIG_MPLS_ROUTING=m
+CONFIG_MPLS_IPTUNNEL=m

tools/testing/selftests/bpf/test_tc_tunnel.sh

@@ -15,6 +15,12 @@ readonly ns2_v4=192.168.1.2
 readonly ns1_v6=fd::1
 readonly ns2_v6=fd::2
 
+# Must match port used by bpf program
+readonly udpport=5555
+# MPLSoverUDP
+readonly mplsudpport=6635
+readonly mplsproto=137
+
 readonly infile="$(mktemp)"
 readonly outfile="$(mktemp)"
 
@@ -38,8 +44,8 @@ setup() {
 	# clamp route to reserve room for tunnel headers
 	ip -netns "${ns1}" -4 route flush table main
 	ip -netns "${ns1}" -6 route flush table main
-	ip -netns "${ns1}" -4 route add "${ns2_v4}" mtu 1476 dev veth1
-	ip -netns "${ns1}" -6 route add "${ns2_v6}" mtu 1456 dev veth1
+	ip -netns "${ns1}" -4 route add "${ns2_v4}" mtu 1458 dev veth1
+	ip -netns "${ns1}" -6 route add "${ns2_v6}" mtu 1438 dev veth1
 
 	sleep 1
 
@@ -86,30 +92,44 @@ set -e
 # no arguments: automated test, run all
 if [[ "$#" -eq "0" ]]; then
 	echo "ipip"
-	$0 ipv4 ipip 100
+	$0 ipv4 ipip none 100
 
 	echo "ip6ip6"
-	$0 ipv6 ip6tnl 100
+	$0 ipv6 ip6tnl none 100
+
+	for mac in none mpls eth ; do
+		echo "ip gre $mac"
+		$0 ipv4 gre $mac 100
+
+		echo "ip6 gre $mac"
+		$0 ipv6 ip6gre $mac 100
+
+		echo "ip gre $mac gso"
+		$0 ipv4 gre $mac 2000
 
-	echo "ip gre"
-	$0 ipv4 gre 100
+		echo "ip6 gre $mac gso"
+		$0 ipv6 ip6gre $mac 2000
 
-	echo "ip6 gre"
-	$0 ipv6 ip6gre 100
+		echo "ip udp $mac"
+		$0 ipv4 udp $mac 100
 
-	echo "ip gre gso"
-	$0 ipv4 gre 2000
+		echo "ip6 udp $mac"
+		$0 ipv6 ip6udp $mac 100
 
-	echo "ip6 gre gso"
-	$0 ipv6 ip6gre 2000
+		echo "ip udp $mac gso"
+		$0 ipv4 udp $mac 2000
+
+		echo "ip6 udp $mac gso"
+		$0 ipv6 ip6udp $mac 2000
+	done
 
 	echo "OK. All tests passed"
 	exit 0
 fi
 
-if [[ "$#" -ne "3" ]]; then
+if [[ "$#" -ne "4" ]]; then
 	echo "Usage: $0"
-	echo "   or: $0 <ipv4|ipv6> <tuntype> <data_len>"
+	echo "   or: $0 <ipv4|ipv6> <tuntype> <none|mpls|eth> <data_len>"
 	exit 1
 fi
 
@@ -117,12 +137,24 @@ case "$1" in
 "ipv4")
 	readonly addr1="${ns1_v4}"
 	readonly addr2="${ns2_v4}"
-	readonly netcat_opt=-4
+	readonly ipproto=4
+	readonly netcat_opt=-${ipproto}
+	readonly foumod=fou
+	readonly foutype=ipip
+	readonly fouproto=4
+	readonly fouproto_mpls=${mplsproto}
+	readonly gretaptype=gretap
 	;;
 "ipv6")
 	readonly addr1="${ns1_v6}"
 	readonly addr2="${ns2_v6}"
-	readonly netcat_opt=-6
+	readonly ipproto=6
+	readonly netcat_opt=-${ipproto}
+	readonly foumod=fou6
+	readonly foutype=ip6tnl
+	readonly fouproto="41 -6"
+	readonly fouproto_mpls="${mplsproto} -6"
+	readonly gretaptype=ip6gretap
 	;;
 *)
 	echo "unknown arg: $1"
@@ -131,9 +163,10 @@ case "$1" in
 esac
 
 readonly tuntype=$2
-readonly datalen=$3
+readonly mac=$3
+readonly datalen=$4
 
-echo "encap ${addr1} to ${addr2}, type ${tuntype}, len ${datalen}"
+echo "encap ${addr1} to ${addr2}, type ${tuntype}, mac ${mac} len ${datalen}"
 
 trap cleanup EXIT
 
@@ -150,16 +183,63 @@ verify_data
 ip netns exec "${ns1}" tc qdisc add dev veth1 clsact
 ip netns exec "${ns1}" tc filter add dev veth1 egress \
 	bpf direct-action object-file ./test_tc_tunnel.o \
-	section "encap_${tuntype}"
+	section "encap_${tuntype}_${mac}"
 echo "test bpf encap without decap (expect failure)"
 server_listen
 ! client_connect
 
+if [[ "$tuntype" =~ "udp" ]]; then
+	# Set up fou tunnel.
+	ttype="${foutype}"
+	targs="encap fou encap-sport auto encap-dport $udpport"
+	# fou may be a module; allow this to fail.
+	modprobe "${foumod}" ||true
+	if [[ "$mac" == "mpls" ]]; then
+		dport=${mplsudpport}
+		dproto=${fouproto_mpls}
+		tmode="mode any ttl 255"
+	else
+		dport=${udpport}
+		dproto=${fouproto}
+	fi
+	ip netns exec "${ns2}" ip fou add port $dport ipproto ${dproto}
+	targs="encap fou encap-sport auto encap-dport $dport"
+elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then
+	ttype=$gretaptype
+else
+	ttype=$tuntype
+	targs=""
+fi
+
 # serverside, insert decap module
 # server is still running
 # client can connect again
-ip netns exec "${ns2}" ip link add dev testtun0 type "${tuntype}" \
-	remote "${addr1}" local "${addr2}"
+ip netns exec "${ns2}" ip link add name testtun0 type "${ttype}" \
+	${tmode} remote "${addr1}" local "${addr2}" $targs
+
+expect_tun_fail=0
+
+if [[ "$tuntype" == "ip6udp" && "$mac" == "mpls" ]]; then
+	# No support for MPLS IPv6 fou tunnel; expect failure.
+	expect_tun_fail=1
+elif [[ "$tuntype" =~ "udp" && "$mac" == "eth" ]]; then
+	# No support for TEB fou tunnel; expect failure.
+	expect_tun_fail=1
+elif [[ "$tuntype" =~ "gre" && "$mac" == "eth" ]]; then
+	# Share ethernet address between tunnel/veth2 so L2 decap works.
+	ethaddr=$(ip netns exec "${ns2}" ip link show veth2 | \
+		  awk '/ether/ { print $2 }')
+	ip netns exec "${ns2}" ip link set testtun0 address $ethaddr
+elif [[ "$mac" == "mpls" ]]; then
+	modprobe mpls_iptunnel ||true
+	modprobe mpls_gso ||true
+	ip netns exec "${ns2}" sysctl -qw net.mpls.platform_labels=65536
+	ip netns exec "${ns2}" ip -f mpls route add 1000 dev lo
+	ip netns exec "${ns2}" ip link set lo up
+	ip netns exec "${ns2}" sysctl -qw net.mpls.conf.testtun0.input=1
+	ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.lo.rp_filter=0
+fi
+
 # Because packets are decapped by the tunnel they arrive on testtun0 from
 # the IP stack perspective.  Ensure reverse path filtering is disabled
 # otherwise we drop the TCP SYN as arriving on testtun0 instead of the
@@ -169,16 +249,22 @@ ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.all.rp_filter=0
 # selected as the max of the "all" and device-specific values.
 ip netns exec "${ns2}" sysctl -qw net.ipv4.conf.testtun0.rp_filter=0
 ip netns exec "${ns2}" ip link set dev testtun0 up
-echo "test bpf encap with tunnel device decap"
-client_connect
-verify_data
+if [[ "$expect_tun_fail" == 1 ]]; then
+	# This tunnel mode is not supported, so we expect failure.
+	echo "test bpf encap with tunnel device decap (expect failure)"
+	! client_connect
+else
+	echo "test bpf encap with tunnel device decap"
+	client_connect
+	verify_data
+	server_listen
+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
 ip netns exec "${ns2}" tc filter add dev veth2 ingress \
 	bpf direct-action object-file ./test_tc_tunnel.o section decap
-server_listen
 echo "test bpf encap with bpf decap"
 client_connect
 verify_data