diff mbox series

[v5,bpf-next,3/3] selftests/bpf: Add selftest for bpf_xdp_flow_lookup kfunc

Message ID 6472c7a775f6a329d16352092071fda8676c2809.1718379122.git.lorenzo@kernel.org (mailing list archive)
State Changes Requested
Delegated to: BPF
Headers show
Series netfilter: Add the capability to offload flowtable in XDP layer | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for bpf-next, async
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 850 this patch: 850
netdev/build_tools success Errors and warnings before: 0 this patch: 0
netdev/cc_maintainers warning 10 maintainers not CCed: jolsa@kernel.org shuah@kernel.org john.fastabend@gmail.com haoluo@google.com song@kernel.org mykolal@fb.com yonghong.song@linux.dev sdf@google.com kpsingh@kernel.org linux-kselftest@vger.kernel.org
netdev/build_clang success Errors and warnings before: 854 this patch: 854
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 859 this patch: 859
netdev/checkpatch warning WARNING: added, moved or deleted file(s), does MAINTAINERS need updating? WARNING: quoted string split across lines
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
bpf/vmtest-bpf-next-PR success PR summary
bpf/vmtest-bpf-next-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-next-VM_Test-0 success Logs for Lint
bpf/vmtest-bpf-next-VM_Test-2 success Logs for Unittests
bpf/vmtest-bpf-next-VM_Test-3 success Logs for Validate matrix.py
bpf/vmtest-bpf-next-VM_Test-5 success Logs for aarch64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-4 success Logs for aarch64-gcc / build / build for aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-10 success Logs for aarch64-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-12 success Logs for s390x-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-11 success Logs for s390x-gcc / build / build for s390x with gcc
bpf/vmtest-bpf-next-VM_Test-18 success Logs for set-matrix
bpf/vmtest-bpf-next-VM_Test-17 success Logs for s390x-gcc / veristat
bpf/vmtest-bpf-next-VM_Test-20 success Logs for x86_64-gcc / build-release
bpf/vmtest-bpf-next-VM_Test-19 success Logs for x86_64-gcc / build / build for x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-35 success Logs for x86_64-llvm-18 / build / build for x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-34 success Logs for x86_64-llvm-17 / veristat
bpf/vmtest-bpf-next-VM_Test-36 success Logs for x86_64-llvm-18 / build-release / build for x86_64 with llvm-18-O2
bpf/vmtest-bpf-next-VM_Test-42 success Logs for x86_64-llvm-18 / veristat
bpf/vmtest-bpf-next-VM_Test-28 success Logs for x86_64-llvm-17 / build / build for x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-29 success Logs for x86_64-llvm-17 / build-release / build for x86_64 with llvm-17-O2
bpf/vmtest-bpf-next-VM_Test-6 success Logs for aarch64-gcc / test (test_maps, false, 360) / test_maps on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-9 success Logs for aarch64-gcc / test (test_verifier, false, 360) / test_verifier on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-8 success Logs for aarch64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-7 success Logs for aarch64-gcc / test (test_progs, false, 360) / test_progs on aarch64 with gcc
bpf/vmtest-bpf-next-VM_Test-33 success Logs for x86_64-llvm-17 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-32 success Logs for x86_64-llvm-17 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-38 success Logs for x86_64-llvm-18 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-37 success Logs for x86_64-llvm-18 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-40 success Logs for x86_64-llvm-18 / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-41 success Logs for x86_64-llvm-18 / test (test_verifier, false, 360) / test_verifier on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-23 success Logs for x86_64-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-21 success Logs for x86_64-gcc / test (test_maps, false, 360) / test_maps on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-26 success Logs for x86_64-gcc / test (test_verifier, false, 360) / test_verifier on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-22 success Logs for x86_64-gcc / test (test_progs, false, 360) / test_progs on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-27 success Logs for x86_64-gcc / veristat / veristat on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-24 success Logs for x86_64-gcc / test (test_progs_no_alu32_parallel, true, 30) / test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-25 success Logs for x86_64-gcc / test (test_progs_parallel, true, 30) / test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-next-VM_Test-30 success Logs for x86_64-llvm-17 / test (test_maps, false, 360) / test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-31 success Logs for x86_64-llvm-17 / test (test_progs, false, 360) / test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-next-VM_Test-39 success Logs for x86_64-llvm-18 / test (test_progs_cpuv4, false, 360) / test_progs_cpuv4 on x86_64 with llvm-18
bpf/vmtest-bpf-next-VM_Test-16 success Logs for s390x-gcc / test (test_verifier, false, 360) / test_verifier on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-13 success Logs for s390x-gcc / test (test_maps, false, 360) / test_maps on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-15 success Logs for s390x-gcc / test (test_progs_no_alu32, false, 360) / test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-next-VM_Test-14 success Logs for s390x-gcc / test (test_progs, false, 360) / test_progs on s390x with gcc

Commit Message

Lorenzo Bianconi June 14, 2024, 3:40 p.m. UTC 
Introduce e2e selftest for bpf_xdp_flow_lookup kfunc through
xdp_flowtable utility.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
 tools/testing/selftests/bpf/config            |  13 ++
 .../selftests/bpf/prog_tests/xdp_flowtable.c  | 168 ++++++++++++++++++
 .../selftests/bpf/progs/xdp_flowtable.c       | 146 +++++++++++++++
 3 files changed, 327 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c
 create mode 100644 tools/testing/selftests/bpf/progs/xdp_flowtable.c

Comments

Daniel Borkmann June 28, 2024, 9:29 p.m. UTC | #1 
On 6/14/24 5:40 PM, Lorenzo Bianconi wrote:
[...]
> +void test_xdp_flowtable(void)
> +{
> +	struct xdp_flowtable *skel = NULL;
> +	struct nstoken *tok = NULL;
> +	int iifindex, stats_fd;
> +	__u32 value, key = 0;
> +	struct bpf_link *link;
> +
> +	if (SYS_NOFAIL("nft -v")) {
> +		fprintf(stdout, "Missing required nft tool\n");
> +		test__skip();
> +		return;

Bit unfortunate that upstream CI skips the test case at the moment:

   #542/2   xdp_devmap_attach/DEVMAP with frags programs in entries:OK
   #542/3   xdp_devmap_attach/Verifier check of DEVMAP programs:OK
   #542     xdp_devmap_attach:OK
   #543     xdp_do_redirect:OK
   #544     xdp_flowtable:SKIP
[...]

> +out:
> +	xdp_flowtable__destroy(skel);
> +	if (tok)
> +		close_netns(tok);
> +	SYS_NOFAIL("ip netns del " TX_NETNS_NAME);
> +	SYS_NOFAIL("ip netns del " RX_NETNS_NAME);
> +}
> diff --git a/tools/testing/selftests/bpf/progs/xdp_flowtable.c b/tools/testing/selftests/bpf/progs/xdp_flowtable.c
> new file mode 100644
> index 0000000000000..8297b30b0764b
> --- /dev/null
> +++ b/tools/testing/selftests/bpf/progs/xdp_flowtable.c
> @@ -0,0 +1,146 @@
> +// SPDX-License-Identifier: GPL-2.0
> +#define BPF_NO_KFUNC_PROTOTYPES
> +#include <vmlinux.h>
> +#include <bpf/bpf_helpers.h>
> +#include <bpf/bpf_endian.h>
> +
> +#define MAX_ERRNO	4095

nit: unused?

> +#define ETH_P_IP	0x0800
> +#define ETH_P_IPV6	0x86dd
> +#define IP_MF		0x2000	/* "More Fragments" */
> +#define IP_OFFSET	0x1fff	/* "Fragment Offset" */
> +#define AF_INET		2
> +#define AF_INET6	10
> +
> +struct bpf_flowtable_opts___local {
> +	s32 error;
> +};
> +
> +struct flow_offload_tuple_rhash *
> +bpf_xdp_flow_lookup(struct xdp_md *, struct bpf_fib_lookup *,
> +		    struct bpf_flowtable_opts___local *, u32) __ksym;
> +
> +struct {
> +	__uint(type, BPF_MAP_TYPE_ARRAY);
> +	__type(key, __u32);
> +	__type(value, __u32);
> +	__uint(max_entries, 1);
> +} stats SEC(".maps");
> +
[...]
Lorenzo Bianconi June 29, 2024, 8:11 p.m. UTC | #2 
> On 6/14/24 5:40 PM, Lorenzo Bianconi wrote:
> [...]
> > +void test_xdp_flowtable(void)
> > +{
> > +	struct xdp_flowtable *skel = NULL;
> > +	struct nstoken *tok = NULL;
> > +	int iifindex, stats_fd;
> > +	__u32 value, key = 0;
> > +	struct bpf_link *link;
> > +
> > +	if (SYS_NOFAIL("nft -v")) {
> > +		fprintf(stdout, "Missing required nft tool\n");
> > +		test__skip();
> > +		return;
> 
> Bit unfortunate that upstream CI skips the test case at the moment:

yep, we are missing nft utility there.

> 
>   #542/2   xdp_devmap_attach/DEVMAP with frags programs in entries:OK
>   #542/3   xdp_devmap_attach/Verifier check of DEVMAP programs:OK
>   #542     xdp_devmap_attach:OK
>   #543     xdp_do_redirect:OK
>   #544     xdp_flowtable:SKIP
> [...]
> 
> > +out:
> > +	xdp_flowtable__destroy(skel);
> > +	if (tok)
> > +		close_netns(tok);
> > +	SYS_NOFAIL("ip netns del " TX_NETNS_NAME);
> > +	SYS_NOFAIL("ip netns del " RX_NETNS_NAME);
> > +}
> > diff --git a/tools/testing/selftests/bpf/progs/xdp_flowtable.c b/tools/testing/selftests/bpf/progs/xdp_flowtable.c
> > new file mode 100644
> > index 0000000000000..8297b30b0764b
> > --- /dev/null
> > +++ b/tools/testing/selftests/bpf/progs/xdp_flowtable.c
> > @@ -0,0 +1,146 @@
> > +// SPDX-License-Identifier: GPL-2.0
> > +#define BPF_NO_KFUNC_PROTOTYPES
> > +#include <vmlinux.h>
> > +#include <bpf/bpf_helpers.h>
> > +#include <bpf/bpf_endian.h>
> > +
> > +#define MAX_ERRNO	4095
> 
> nit: unused?

ack, I will remove it in v6.

Regards,
Lorenzo

> 
> > +#define ETH_P_IP	0x0800
> > +#define ETH_P_IPV6	0x86dd
> > +#define IP_MF		0x2000	/* "More Fragments" */
> > +#define IP_OFFSET	0x1fff	/* "Fragment Offset" */
> > +#define AF_INET		2
> > +#define AF_INET6	10
> > +
> > +struct bpf_flowtable_opts___local {
> > +	s32 error;
> > +};
> > +
> > +struct flow_offload_tuple_rhash *
> > +bpf_xdp_flow_lookup(struct xdp_md *, struct bpf_fib_lookup *,
> > +		    struct bpf_flowtable_opts___local *, u32) __ksym;
> > +
> > +struct {
> > +	__uint(type, BPF_MAP_TYPE_ARRAY);
> > +	__type(key, __u32);
> > +	__type(value, __u32);
> > +	__uint(max_entries, 1);
> > +} stats SEC(".maps");
> > +
> [...]
Daniel Borkmann July 1, 2024, 8:07 a.m. UTC | #3 
On 6/29/24 10:11 PM, Lorenzo Bianconi wrote:
>> On 6/14/24 5:40 PM, Lorenzo Bianconi wrote:
>> [...]
>>> +void test_xdp_flowtable(void)
>>> +{
>>> +	struct xdp_flowtable *skel = NULL;
>>> +	struct nstoken *tok = NULL;
>>> +	int iifindex, stats_fd;
>>> +	__u32 value, key = 0;
>>> +	struct bpf_link *link;
>>> +
>>> +	if (SYS_NOFAIL("nft -v")) {
>>> +		fprintf(stdout, "Missing required nft tool\n");
>>> +		test__skip();
>>> +		return;
>>
>> Bit unfortunate that upstream CI skips the test case at the moment:
> 
> yep, we are missing nft utility there.

Ok, not a blocker imho, but if you could work with Manu to get this
enabled in the CI, that would be great so that the test can actually
run.

Thanks,
Daniel
diff mbox series

Patch

diff --git a/tools/testing/selftests/bpf/config b/tools/testing/selftests/bpf/config
index 2fb16da78dce8..5291e97df7494 100644
--- a/tools/testing/selftests/bpf/config
+++ b/tools/testing/selftests/bpf/config
@@ -83,6 +83,19 @@  CONFIG_NF_CONNTRACK_MARK=y
 CONFIG_NF_CONNTRACK_ZONES=y
 CONFIG_NF_DEFRAG_IPV4=y
 CONFIG_NF_DEFRAG_IPV6=y
+CONFIG_NF_TABLES=y
+CONFIG_NF_TABLES_INET=y
+CONFIG_NF_TABLES_NETDEV=y
+CONFIG_NF_TABLES_IPV4=y
+CONFIG_NF_TABLES_IPV6=y
+CONFIG_NETFILTER_INGRESS=y
+CONFIG_NF_FLOW_TABLE=y
+CONFIG_NF_FLOW_TABLE_INET=y
+CONFIG_NETFILTER_NETLINK=y
+CONFIG_NFT_FLOW_OFFLOAD=y
+CONFIG_IP_NF_IPTABLES=y
+CONFIG_IP6_NF_IPTABLES=y
+CONFIG_IP6_NF_FILTER=y
 CONFIG_NF_NAT=y
 CONFIG_RC_CORE=y
 CONFIG_SECURITY=y
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c
new file mode 100644
index 0000000000000..e1bf141d34015
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_flowtable.c
@@ -0,0 +1,168 @@ 
+// SPDX-License-Identifier: GPL-2.0
+#include <test_progs.h>
+#include <network_helpers.h>
+#include <bpf/btf.h>
+#include <linux/if_link.h>
+#include <linux/udp.h>
+#include <net/if.h>
+#include <unistd.h>
+
+#include "xdp_flowtable.skel.h"
+
+#define TX_NETNS_NAME	"ns0"
+#define RX_NETNS_NAME	"ns1"
+
+#define TX_NAME		"v0"
+#define FORWARD_NAME	"v1"
+#define RX_NAME		"d0"
+
+#define TX_MAC		"00:00:00:00:00:01"
+#define FORWARD_MAC	"00:00:00:00:00:02"
+#define RX_MAC		"00:00:00:00:00:03"
+#define DST_MAC		"00:00:00:00:00:04"
+
+#define TX_ADDR		"10.0.0.1"
+#define FORWARD_ADDR	"10.0.0.2"
+#define RX_ADDR		"20.0.0.1"
+#define DST_ADDR	"20.0.0.2"
+
+#define PREFIX_LEN	"8"
+#define N_PACKETS	10
+#define UDP_PORT	12345
+#define UDP_PORT_STR	"12345"
+
+static int send_udp_traffic(void)
+{
+	struct sockaddr_storage addr;
+	int i, sock;
+
+	if (make_sockaddr(AF_INET, DST_ADDR, UDP_PORT, &addr, NULL))
+		return -EINVAL;
+
+	sock = socket(AF_INET, SOCK_DGRAM, 0);
+	if (sock < 0)
+		return sock;
+
+	for (i = 0; i < N_PACKETS; i++) {
+		unsigned char buf[] = { 0xaa, 0xbb, 0xcc };
+		int n;
+
+		n = sendto(sock, buf, sizeof(buf), MSG_NOSIGNAL | MSG_CONFIRM,
+			   (struct sockaddr *)&addr, sizeof(addr));
+		if (n != sizeof(buf)) {
+			close(sock);
+			return -EINVAL;
+		}
+
+		usleep(50000); /* 50ms */
+	}
+	close(sock);
+
+	return 0;
+}
+
+void test_xdp_flowtable(void)
+{
+	struct xdp_flowtable *skel = NULL;
+	struct nstoken *tok = NULL;
+	int iifindex, stats_fd;
+	__u32 value, key = 0;
+	struct bpf_link *link;
+
+	if (SYS_NOFAIL("nft -v")) {
+		fprintf(stdout, "Missing required nft tool\n");
+		test__skip();
+		return;
+	}
+
+	SYS(out, "ip netns add " TX_NETNS_NAME);
+	SYS(out, "ip netns add " RX_NETNS_NAME);
+
+	tok = open_netns(RX_NETNS_NAME);
+	if (!ASSERT_OK_PTR(tok, "setns"))
+		goto out;
+
+	SYS(out, "sysctl -qw net.ipv4.conf.all.forwarding=1");
+
+	SYS(out, "ip link add " TX_NAME " type veth peer " FORWARD_NAME);
+	SYS(out, "ip link set " TX_NAME " netns " TX_NETNS_NAME);
+	SYS(out, "ip link set dev " FORWARD_NAME " address " FORWARD_MAC);
+	SYS(out,
+	    "ip addr add " FORWARD_ADDR "/" PREFIX_LEN " dev " FORWARD_NAME);
+	SYS(out, "ip link set dev " FORWARD_NAME " up");
+
+	SYS(out, "ip link add " RX_NAME " type dummy");
+	SYS(out, "ip link set dev " RX_NAME " address " RX_MAC);
+	SYS(out, "ip addr add " RX_ADDR "/" PREFIX_LEN " dev " RX_NAME);
+	SYS(out, "ip link set dev " RX_NAME " up");
+
+	/* configure the flowtable */
+	SYS(out, "nft add table ip filter");
+	SYS(out,
+	    "nft add flowtable ip filter f { hook ingress priority 0\\; "
+	    "devices = { " FORWARD_NAME ", " RX_NAME " }\\; }");
+	SYS(out,
+	    "nft add chain ip filter forward "
+	    "{ type filter hook forward priority 0\\; }");
+	SYS(out,
+	    "nft add rule ip filter forward ip protocol udp th dport "
+	    UDP_PORT_STR " flow add @f");
+
+	/* Avoid ARP calls */
+	SYS(out,
+	    "ip -4 neigh add " DST_ADDR " lladdr " DST_MAC " dev " RX_NAME);
+
+	close_netns(tok);
+	tok = open_netns(TX_NETNS_NAME);
+	if (!ASSERT_OK_PTR(tok, "setns"))
+		goto out;
+
+	SYS(out, "ip addr add " TX_ADDR "/" PREFIX_LEN " dev " TX_NAME);
+	SYS(out, "ip link set dev " TX_NAME " address " TX_MAC);
+	SYS(out, "ip link set dev " TX_NAME " up");
+	SYS(out, "ip route add default via " FORWARD_ADDR);
+
+	close_netns(tok);
+	tok = open_netns(RX_NETNS_NAME);
+	if (!ASSERT_OK_PTR(tok, "setns"))
+		goto out;
+
+	iifindex = if_nametoindex(FORWARD_NAME);
+	if (!ASSERT_NEQ(iifindex, 0, "iifindex"))
+		goto out;
+
+	skel = xdp_flowtable__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel"))
+		goto out;
+
+	link = bpf_program__attach_xdp(skel->progs.xdp_flowtable_do_lookup,
+				       iifindex);
+	if (!ASSERT_OK_PTR(link, "prog_attach"))
+		goto out;
+
+	close_netns(tok);
+	tok = open_netns(TX_NETNS_NAME);
+	if (!ASSERT_OK_PTR(tok, "setns"))
+		goto out;
+
+	if (!ASSERT_OK(send_udp_traffic(), "send udp"))
+		goto out;
+
+	close_netns(tok);
+	tok = open_netns(RX_NETNS_NAME);
+	if (!ASSERT_OK_PTR(tok, "setns"))
+		goto out;
+
+	stats_fd = bpf_map__fd(skel->maps.stats);
+	if (!ASSERT_OK(bpf_map_lookup_elem(stats_fd, &key, &value),
+		       "bpf_map_update_elem stats"))
+		goto out;
+
+	ASSERT_GE(value, N_PACKETS - 2, "bpf_xdp_flow_lookup failed");
+out:
+	xdp_flowtable__destroy(skel);
+	if (tok)
+		close_netns(tok);
+	SYS_NOFAIL("ip netns del " TX_NETNS_NAME);
+	SYS_NOFAIL("ip netns del " RX_NETNS_NAME);
+}
diff --git a/tools/testing/selftests/bpf/progs/xdp_flowtable.c b/tools/testing/selftests/bpf/progs/xdp_flowtable.c
new file mode 100644
index 0000000000000..8297b30b0764b
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/xdp_flowtable.c
@@ -0,0 +1,146 @@ 
+// SPDX-License-Identifier: GPL-2.0
+#define BPF_NO_KFUNC_PROTOTYPES
+#include <vmlinux.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define MAX_ERRNO	4095
+
+#define ETH_P_IP	0x0800
+#define ETH_P_IPV6	0x86dd
+#define IP_MF		0x2000	/* "More Fragments" */
+#define IP_OFFSET	0x1fff	/* "Fragment Offset" */
+#define AF_INET		2
+#define AF_INET6	10
+
+struct bpf_flowtable_opts___local {
+	s32 error;
+};
+
+struct flow_offload_tuple_rhash *
+bpf_xdp_flow_lookup(struct xdp_md *, struct bpf_fib_lookup *,
+		    struct bpf_flowtable_opts___local *, u32) __ksym;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(max_entries, 1);
+} stats SEC(".maps");
+
+static bool xdp_flowtable_offload_check_iphdr(struct iphdr *iph)
+{
+	/* ip fragmented traffic */
+	if (iph->frag_off & bpf_htons(IP_MF | IP_OFFSET))
+		return false;
+
+	/* ip options */
+	if (iph->ihl * 4 != sizeof(*iph))
+		return false;
+
+	if (iph->ttl <= 1)
+		return false;
+
+	return true;
+}
+
+static bool xdp_flowtable_offload_check_tcp_state(void *ports, void *data_end,
+						  u8 proto)
+{
+	if (proto == IPPROTO_TCP) {
+		struct tcphdr *tcph = ports;
+
+		if (tcph + 1 > data_end)
+			return false;
+
+		if (tcph->fin || tcph->rst)
+			return false;
+	}
+
+	return true;
+}
+
+SEC("xdp.frags")
+int xdp_flowtable_do_lookup(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	struct bpf_flowtable_opts___local opts = {};
+	struct flow_offload_tuple_rhash *tuplehash;
+	struct bpf_fib_lookup tuple = {
+		.ifindex = ctx->ingress_ifindex,
+	};
+	void *data = (void *)(long)ctx->data;
+	struct ethhdr *eth = data;
+	struct flow_ports *ports;
+	__u32 *val, key = 0;
+
+	if (eth + 1 > data_end)
+		return XDP_DROP;
+
+	switch (eth->h_proto) {
+	case bpf_htons(ETH_P_IP): {
+		struct iphdr *iph = data + sizeof(*eth);
+
+		ports = (struct flow_ports *)(iph + 1);
+		if (ports + 1 > data_end)
+			return XDP_PASS;
+
+		/* sanity check on ip header */
+		if (!xdp_flowtable_offload_check_iphdr(iph))
+			return XDP_PASS;
+
+		if (!xdp_flowtable_offload_check_tcp_state(ports, data_end,
+							   iph->protocol))
+			return XDP_PASS;
+
+		tuple.family		= AF_INET;
+		tuple.tos		= iph->tos;
+		tuple.l4_protocol	= iph->protocol;
+		tuple.tot_len		= bpf_ntohs(iph->tot_len);
+		tuple.ipv4_src		= iph->saddr;
+		tuple.ipv4_dst		= iph->daddr;
+		tuple.sport		= ports->source;
+		tuple.dport		= ports->dest;
+		break;
+	}
+	case bpf_htons(ETH_P_IPV6): {
+		struct in6_addr *src = (struct in6_addr *)tuple.ipv6_src;
+		struct in6_addr *dst = (struct in6_addr *)tuple.ipv6_dst;
+		struct ipv6hdr *ip6h = data + sizeof(*eth);
+
+		ports = (struct flow_ports *)(ip6h + 1);
+		if (ports + 1 > data_end)
+			return XDP_PASS;
+
+		if (ip6h->hop_limit <= 1)
+			return XDP_PASS;
+
+		if (!xdp_flowtable_offload_check_tcp_state(ports, data_end,
+							   ip6h->nexthdr))
+			return XDP_PASS;
+
+		tuple.family		= AF_INET6;
+		tuple.l4_protocol	= ip6h->nexthdr;
+		tuple.tot_len		= bpf_ntohs(ip6h->payload_len);
+		*src			= ip6h->saddr;
+		*dst			= ip6h->daddr;
+		tuple.sport		= ports->source;
+		tuple.dport		= ports->dest;
+		break;
+	}
+	default:
+		return XDP_PASS;
+	}
+
+	tuplehash = bpf_xdp_flow_lookup(ctx, &tuple, &opts, sizeof(opts));
+	if (!tuplehash)
+		return XDP_PASS;
+
+	val = bpf_map_lookup_elem(&stats, &key);
+	if (val)
+		__sync_add_and_fetch(val, 1);
+
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";