[PATCH net-next 4/4] selftests: drv-net: xdp: Add rss_hash metadata tests

[Chris J Arges]

This test loads xdp_metadata.bpf which calls bpf_xdp_metadata_rx_hash() on
incoming packets. The metadata from that packet is then sent to a BPF
map for validation. It borrows structure from xdp.py, reusing common
functions.

The test checks the device's xdp-rx-metadata-features via netlink
before running and skips on devices that do not advertise hash support.
This allows the tests to pass, but one can override the device and test on
HW or veth devices.

The test is fairly simple and just verifies that a TCP or UDP packet can be
identified as an L4 flow. This minimal test also passes if run on a veth
device.

Signed-off-by: Chris J Arges <carges@xxxxxxxxxxxxxx>
---
 tools/testing/selftests/drivers/net/Makefile  |   1 +
 .../selftests/drivers/net/xdp_metadata.py     | 144 ++++++++++++++++
 .../selftests/net/lib/xdp_metadata.bpf.c      | 163 ++++++++++++++++++
 3 files changed, 308 insertions(+)
 create mode 100644 tools/testing/selftests/drivers/net/xdp_metadata.py
 create mode 100644 tools/testing/selftests/net/lib/xdp_metadata.bpf.c

diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile
index 8154d6d429d3..6f9708e8d05a 100644
--- a/tools/testing/selftests/drivers/net/Makefile
+++ b/tools/testing/selftests/drivers/net/Makefile
@@ -23,6 +23,7 @@ TEST_PROGS := \
 	shaper.py \
 	stats.py \
 	xdp.py \
+	xdp_metadata.py \
 # end of TEST_PROGS
 
 # YNL files, must be before "include ..lib.mk"
diff --git a/tools/testing/selftests/drivers/net/xdp_metadata.py b/tools/testing/selftests/drivers/net/xdp_metadata.py
new file mode 100644
index 000000000000..7b8a3d00b0ac
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/xdp_metadata.py
@@ -0,0 +1,144 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Tests for XDP metadata kfuncs (e.g. bpf_xdp_metadata_rx_hash).
+
+These tests load device-bound XDP programs from xdp_metadata.bpf.o
+that call metadata kfuncs, send traffic, and verify the extracted
+metadata via BPF maps.
+"""
+from lib.py import ksft_run, ksft_exit, ksft_ge, ksft_ne, ksft_pr
+from lib.py import KsftNamedVariant, ksft_variants
+from lib.py import CmdExitFailure, KsftSkipEx, NetDrvEpEnv
+from lib.py import NetdevFamily
+from lib.py import bkg, cmd, rand_port, wait_port_listen
+from lib.py import ip, bpftool, defer
+from lib.py import bpf_map_set, bpf_map_dump, bpf_prog_map_ids
+
+
+def _load_xdp_metadata_prog(cfg, prog_name, bpf_file="xdp_metadata.bpf.o"):
+    """Load a device-bound XDP metadata program and return prog/map info.
+
+    Returns:
+        dict with 'id', 'name', and 'maps' (name -> map_id).
+    """
+    abs_path = cfg.net_lib_dir / bpf_file
+    pin_dir = "/sys/fs/bpf/xdp_metadata_test"
+
+    cmd(f"rm -rf {pin_dir}", shell=True, fail=False)
+    cmd(f"mkdir -p {pin_dir}", shell=True)
+
+    try:
+        bpftool(f"prog loadall {abs_path} {pin_dir} type xdp "
+                f"xdpmeta_dev {cfg.ifname}")
+    except CmdExitFailure as e:
+        cmd(f"rm -rf {pin_dir}", shell=True, fail=False)
+        raise KsftSkipEx(
+            f"Failed to load device-bound XDP program '{prog_name}'"
+        ) from e
+    defer(cmd, f"rm -rf {pin_dir}", shell=True, fail=False)
+
+    pin_path = f"{pin_dir}/{prog_name}"
+    ip(f"link set dev {cfg.ifname} xdpdrv pinned {pin_path}")
+    defer(ip, f"link set dev {cfg.ifname} xdpdrv off")
+
+    xdp_info = ip(f"-d link show dev {cfg.ifname}", json=True)[0]
+    prog_id = xdp_info["xdp"]["prog"]["id"]
+
+    return {"id": prog_id,
+            "name": xdp_info["xdp"]["prog"]["name"],
+            "maps": bpf_prog_map_ids(prog_id)}
+
+
+def _send_probe(cfg, port, proto="tcp"):
+    """Send a single payload from the remote end using socat.
+
+    Args:
+        cfg: Configuration object containing network settings.
+        port: Port number for the exchange.
+        proto: Protocol to use, either "tcp" or "udp".
+    """
+    cfg.require_cmd("socat", remote=True)
+
+    if proto == "tcp":
+        rx_cmd = f"socat -{cfg.addr_ipver} -T 2 TCP-LISTEN:{port},reuseport STDOUT"
+        tx_cmd = f"echo -n rss_hash_test | socat -t 2 -u STDIN TCP:{cfg.baddr}:{port}"
+    else:
+        rx_cmd = f"socat -{cfg.addr_ipver} -T 2 -u UDP-RECV:{port},reuseport STDOUT"
+        tx_cmd = f"echo -n rss_hash_test | socat -t 2 -u STDIN UDP:{cfg.baddr}:{port}"
+
+    with bkg(rx_cmd, exit_wait=True):
+        wait_port_listen(port, proto=proto)
+        cmd(tx_cmd, host=cfg.remote, shell=True)
+
+
+# BPF map keys matching the enums in xdp_metadata.bpf.c
+_SETUP_KEY_PORT = 1
+
+_RSS_KEY_HASH = 0
+_RSS_KEY_TYPE = 1
+_RSS_KEY_PKT_CNT = 2
+_RSS_KEY_ERR_CNT = 3
+
+
+@ksft_variants([
+    KsftNamedVariant("tcp", "tcp"),
+    KsftNamedVariant("udp", "udp"),
+])
+def test_xdp_rss_hash(cfg, proto):
+    """Test RSS hash metadata extraction via bpf_xdp_metadata_rx_hash().
+
+    This test will only run on devices that support xdp-rx-metadata-features.
+
+    Loads the xdp_rss_hash program from xdp_metadata, sends a packet using
+    the specified protocol, and verifies that the program extracted a non-zero
+    hash with an L4 hash type.
+    """
+    dev_info = cfg.netnl.dev_get({"ifindex": cfg.ifindex})
+    rx_meta = dev_info.get("xdp-rx-metadata-features", [])
+    if "hash" not in rx_meta:
+        raise KsftSkipEx("device does not support XDP rx hash metadata")
+
+    prog_info = _load_xdp_metadata_prog(cfg, "xdp_rss_hash")
+
+    port = rand_port()
+    bpf_map_set("map_xdp_setup", _SETUP_KEY_PORT, port)
+
+    rss_map_id = prog_info["maps"]["map_rss"]
+
+    _send_probe(cfg, port, proto=proto)
+
+    rss = bpf_map_dump(rss_map_id)
+
+    pkt_cnt = rss.get(_RSS_KEY_PKT_CNT, 0)
+    err_cnt = rss.get(_RSS_KEY_ERR_CNT, 0)
+    hash_val = rss.get(_RSS_KEY_HASH, 0)
+    hash_type = rss.get(_RSS_KEY_TYPE, 0)
+
+    ksft_ge(pkt_cnt, 1, "should have received at least one packet")
+    ksft_pr(f"  RSS hash error count: {err_cnt}")
+
+    ksft_ne(hash_val, 0,
+            f"RSS hash should be non-zero for {proto.upper()} traffic")
+    ksft_pr(f"  RSS hash: {hash_val:#010x}")
+
+    ksft_pr(f"  RSS hash type: {hash_type:#06x}")
+    XDP_RSS_L4 = 0x8  # BIT(3) from enum xdp_rss_hash_type
+    ksft_ne(hash_type & XDP_RSS_L4, 0,
+            f"RSS hash type should include L4 for {proto.upper()} traffic")
+
+
+def main():
+    with NetDrvEpEnv(__file__) as cfg:
+        cfg.netnl = NetdevFamily()
+        ksft_run(
+            [
+                test_xdp_rss_hash,
+            ],
+            args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/net/lib/xdp_metadata.bpf.c b/tools/testing/selftests/net/lib/xdp_metadata.bpf.c
new file mode 100644
index 000000000000..f71f59215239
--- /dev/null
+++ b/tools/testing/selftests/net/lib/xdp_metadata.bpf.c
@@ -0,0 +1,163 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <stddef.h>
+#include <linux/bpf.h>
+#include <linux/in.h>
+#include <linux/if_ether.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+
+enum {
+	XDP_PORT = 1,
+	XDP_PROTO = 4,
+} xdp_map_setup_keys;
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 5);
+	__type(key, __u32);
+	__type(value, __s32);
+} map_xdp_setup SEC(".maps");
+
+/* RSS hash results: key 0 = hash, key 1 = hash type,
+ * key 2 = packet count, key 3 = error count.
+ */
+enum {
+	RSS_KEY_HASH = 0,
+	RSS_KEY_TYPE = 1,
+	RSS_KEY_PKT_CNT = 2,
+	RSS_KEY_ERR_CNT = 3,
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__type(key, __u32);
+	__type(value, __u32);
+	__uint(max_entries, 4);
+} map_rss SEC(".maps");
+
+/* Mirror of enum xdp_rss_hash_type from include/net/xdp.h.
+ * Needed because the enum is not part of UAPI headers.
+ */
+enum xdp_rss_hash_type {
+	XDP_RSS_L3_IPV4 = 1U << 0,
+	XDP_RSS_L3_IPV6 = 1U << 1,
+	XDP_RSS_L3_DYNHDR = 1U << 2,
+	XDP_RSS_L4 = 1U << 3,
+	XDP_RSS_L4_TCP = 1U << 4,
+	XDP_RSS_L4_UDP = 1U << 5,
+	XDP_RSS_L4_SCTP = 1U << 6,
+	XDP_RSS_L4_IPSEC = 1U << 7,
+	XDP_RSS_L4_ICMP = 1U << 8,
+};
+
+extern int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, __u32 *hash,
+				    enum xdp_rss_hash_type *rss_type) __ksym;
+
+static __always_inline __u16 get_dest_port(void *l4, void *data_end,
+					   __u8 protocol)
+{
+	if (protocol == IPPROTO_UDP) {
+		struct udphdr *udp = l4;
+
+		if ((void *)(udp + 1) > data_end)
+			return 0;
+		return udp->dest;
+	} else if (protocol == IPPROTO_TCP) {
+		struct tcphdr *tcp = l4;
+
+		if ((void *)(tcp + 1) > data_end)
+			return 0;
+		return tcp->dest;
+	}
+
+	return 0;
+}
+
+SEC("xdp")
+int xdp_rss_hash(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+	enum xdp_rss_hash_type rss_type = 0;
+	struct ethhdr *eth = data;
+	__u8 l4_proto = 0;
+	__u32 hash = 0;
+	__u32 key, val;
+	void *l4 = NULL;
+	__u32 *cnt;
+	int ret;
+
+	if ((void *)(eth + 1) > data_end)
+		return XDP_PASS;
+
+	if (eth->h_proto == bpf_htons(ETH_P_IP)) {
+		struct iphdr *iph = (void *)(eth + 1);
+
+		if ((void *)(iph + 1) > data_end)
+			return XDP_PASS;
+		l4_proto = iph->protocol;
+		l4 = (void *)(iph + 1);
+	} else if (eth->h_proto == bpf_htons(ETH_P_IPV6)) {
+		struct ipv6hdr *ip6h = (void *)(eth + 1);
+
+		if ((void *)(ip6h + 1) > data_end)
+			return XDP_PASS;
+		l4_proto = ip6h->nexthdr;
+		l4 = (void *)(ip6h + 1);
+	}
+
+	if (!l4)
+		return XDP_PASS;
+
+	/* Filter on the configured protocol (map_xdp_setup key XDP_PROTO).
+	 * When set, only process packets matching the requested L4 protocol.
+	 */
+	key = XDP_PROTO;
+	__s32 *proto_cfg = bpf_map_lookup_elem(&map_xdp_setup, &key);
+
+	if (proto_cfg && *proto_cfg != 0 && l4_proto != (__u8)*proto_cfg)
+		return XDP_PASS;
+
+	/* Filter on the configured port (map_xdp_setup key XDP_PORT).
+	 * Only applies to protocols with ports (UDP, TCP).
+	 */
+	key = XDP_PORT;
+	__s32 *port_cfg = bpf_map_lookup_elem(&map_xdp_setup, &key);
+
+	if (port_cfg && *port_cfg != 0) {
+		__u16 dest = get_dest_port(l4, data_end, l4_proto);
+
+		if (!dest || bpf_ntohs(dest) != (__u16)*port_cfg)
+			return XDP_PASS;
+	}
+
+	ret = bpf_xdp_metadata_rx_hash(ctx, &hash, &rss_type);
+	if (ret < 0) {
+		key = RSS_KEY_ERR_CNT;
+		cnt = bpf_map_lookup_elem(&map_rss, &key);
+		if (cnt)
+			__sync_fetch_and_add(cnt, 1);
+		return XDP_PASS;
+	}
+
+	key = RSS_KEY_HASH;
+	bpf_map_update_elem(&map_rss, &key, &hash, BPF_ANY);
+
+	key = RSS_KEY_TYPE;
+	val = (__u32)rss_type;
+	bpf_map_update_elem(&map_rss, &key, &val, BPF_ANY);
+
+	key = RSS_KEY_PKT_CNT;
+	cnt = bpf_map_lookup_elem(&map_rss, &key);
+	if (cnt)
+		__sync_fetch_and_add(cnt, 1);
+
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
2.43.0