Resguardo inicial

linux-7.2.3/tools/testing/selftests/drivers/net/hw/.gitignore

@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+iou-zcrx
+ncdevmem
+toeplitz

linux-7.2.3/tools/testing/selftests/drivers/net/hw/Makefile

@@ -0,0 +1,91 @@
+# SPDX-License-Identifier: GPL-2.0+ OR MIT
+
+# Check if io_uring supports zero-copy receive
+HAS_IOURING_ZCRX := $(shell \
+	echo -e '#include <liburing.h>\n' \
+	     'void *func = (void *)io_uring_register_ifq;\n' \
+	     'int main() {return 0;}' | \
+	$(CC) -luring -x c - -o /dev/null 2>&1 && echo y)
+
+ifeq ($(HAS_IOURING_ZCRX),y)
+COND_GEN_FILES += iou-zcrx
+else
+$(warning excluding iouring tests, liburing not installed or too old)
+endif
+
+TEST_GEN_FILES := \
+	$(COND_GEN_FILES) \
+# end of TEST_GEN_FILES
+
+TEST_PROGS = \
+	csum.py \
+	devlink_port_split.py \
+	devlink_rate_tc_bw.py \
+	devmem.py \
+	ethtool.sh \
+	ethtool_extended_state.sh \
+	ethtool_mm.sh \
+	ethtool_rmon.sh \
+	ethtool_std_stats.sh \
+	gro_hw.py \
+	hw_stats_l3.sh \
+	hw_stats_l3_gre.sh \
+	iou-zcrx.py \
+	ipsec_vxlan.py \
+	irq.py \
+	loopback.sh \
+	nic_timestamp.py \
+	nk_devmem.py \
+	nk_netns.py \
+	nk_qlease.py \
+	ntuple.py \
+	pp_alloc_fail.py \
+	rss_api.py \
+	rss_ctx.py \
+	rss_drv.py \
+	rss_flow_label.py \
+	rss_input_xfrm.py \
+	toeplitz.py \
+	tso.py \
+	userns_devmem.py \
+	uso.py \
+	xdp_metadata.py \
+	xsk_reconfig.py \
+	#
+
+TEST_FILES := \
+	devmem_lib.py \
+	ethtool_lib.sh \
+	#
+
+TEST_INCLUDES := \
+	$(wildcard lib/py/*.py ../lib/py/*.py) \
+	../../../net/lib.sh \
+	../../../net/forwarding/ipip_lib.sh \
+	../../../net/forwarding/lib.sh \
+	../../../net/forwarding/tc_common.sh \
+	#
+
+# YNL files, must be before "include ..lib.mk"
+YNL_GEN_FILES := \
+	ncdevmem \
+	toeplitz \
+# end of YNL_GEN_FILES
+TEST_GEN_FILES += $(YNL_GEN_FILES)
+TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c))
+
+include ../../../lib.mk
+
+# YNL build
+YNL_GENS := \
+	ethtool \
+	netdev \
+# end of YNL_GENS
+
+include ../../../net/ynl.mk
+
+include ../../../net/bpf.mk
+
+ifeq ($(HAS_IOURING_ZCRX),y)
+$(OUTPUT)/iou-zcrx: LDLIBS += -luring
+endif

linux-7.2.3/tools/testing/selftests/drivers/net/hw/config

@@ -0,0 +1,26 @@
+CONFIG_BPF_SYSCALL=y
+CONFIG_FAIL_FUNCTION=y
+CONFIG_FAULT_INJECTION=y
+CONFIG_FAULT_INJECTION_DEBUG_FS=y
+CONFIG_FUNCTION_ERROR_INJECTION=y
+CONFIG_HUGETLBFS=y
+CONFIG_INET6_ESP=y
+CONFIG_INET6_ESP_OFFLOAD=y
+CONFIG_INET_ESP=y
+CONFIG_INET_ESP_OFFLOAD=y
+CONFIG_IO_URING=y
+CONFIG_IPV6=y
+CONFIG_IPV6_GRE=y
+CONFIG_IPV6_SIT=y
+CONFIG_IPV6_TUNNEL=y
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_CLS_BPF=y
+CONFIG_NET_IPGRE=y
+CONFIG_NET_IPGRE_DEMUX=y
+CONFIG_NET_IPIP=y
+CONFIG_NETKIT=y
+CONFIG_NET_SCH_INGRESS=y
+CONFIG_UDMABUF=y
+CONFIG_USER_NS=y
+CONFIG_VXLAN=y
+CONFIG_XFRM_USER=y

linux-7.2.3/tools/testing/selftests/drivers/net/hw/csum.py

@@ -0,0 +1,110 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""Run the tools/testing/selftests/net/csum testsuite."""
+
+from os import path
+
+from lib.py import ksft_run, ksft_exit, KsftSkipEx
+from lib.py import EthtoolFamily, NetDrvEpEnv
+from lib.py import bkg, cmd, wait_port_listen
+
+def test_receive(cfg, ipver="6", extra_args=None):
+    """Test local nic checksum receive. Remote host sends crafted packets."""
+    if not cfg.have_rx_csum:
+        raise KsftSkipEx(f"Test requires rx checksum offload on {cfg.ifname}")
+
+    ip_args = f"-{ipver} -S {cfg.remote_addr_v[ipver]} -D {cfg.addr_v[ipver]}"
+
+    rx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -n 100 {ip_args} -r 1 -R {extra_args}"
+    tx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -n 100 {ip_args} -r 1 -T {extra_args}"
+
+    with bkg(rx_cmd, exit_wait=True):
+        wait_port_listen(34000, proto="udp")
+        cmd(tx_cmd, host=cfg.remote)
+
+
+def test_transmit(cfg, ipver="6", extra_args=None):
+    """Test local nic checksum transmit. Remote host verifies packets."""
+    if (not cfg.have_tx_csum_generic and
+        not (cfg.have_tx_csum_ipv4 and ipver == "4") and
+        not (cfg.have_tx_csum_ipv6 and ipver == "6")):
+        raise KsftSkipEx(f"Test requires tx checksum offload on {cfg.ifname}")
+
+    ip_args = f"-{ipver} -S {cfg.addr_v[ipver]} -D {cfg.remote_addr_v[ipver]}"
+
+    # Cannot randomize input when calculating zero checksum
+    if extra_args != "-U -Z":
+        extra_args += " -r 1"
+
+    rx_cmd = f"{cfg.bin_remote} -i {cfg.remote_ifname} -L 1 -n 100 {ip_args} -R {extra_args}"
+    tx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -L 1 -n 100 {ip_args} -T {extra_args}"
+
+    with bkg(rx_cmd, host=cfg.remote, exit_wait=True):
+        wait_port_listen(34000, proto="udp", host=cfg.remote)
+        cmd(tx_cmd)
+
+
+def test_builder(name, cfg, ipver="6", tx=False, extra_args=""):
+    """Construct specific tests from the common template.
+
+       Most tests follow the same basic pattern, differing only in
+       Direction of the test and optional flags passed to csum."""
+    def f(cfg):
+        cfg.require_ipver(ipver)
+
+        if tx:
+            test_transmit(cfg, ipver, extra_args)
+        else:
+            test_receive(cfg, ipver, extra_args)
+
+    f.__name__ = f"ipv{ipver}_" + name
+    return f
+
+
+def check_nic_features(cfg) -> None:
+    """Test whether Tx and Rx checksum offload are enabled.
+
+       If the device under test has either off, then skip the relevant tests."""
+    cfg.have_tx_csum_generic = False
+    cfg.have_tx_csum_ipv4 = False
+    cfg.have_tx_csum_ipv6 = False
+    cfg.have_rx_csum = False
+
+    ethnl = EthtoolFamily()
+    features = ethnl.features_get({"header": {"dev-index": cfg.ifindex}})
+    for f in features["active"]["bits"]["bit"]:
+        if f["name"] == "tx-checksum-ip-generic":
+            cfg.have_tx_csum_generic = True
+        elif f["name"] == "tx-checksum-ipv4":
+            cfg.have_tx_csum_ipv4 = True
+        elif f["name"] == "tx-checksum-ipv6":
+            cfg.have_tx_csum_ipv6 = True
+        elif f["name"] == "rx-checksum":
+            cfg.have_rx_csum = True
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        check_nic_features(cfg)
+
+        cfg.bin_local = cfg.net_lib_dir / "csum"
+        cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
+
+        cases = []
+        for ipver in ["4", "6"]:
+            cases.append(test_builder("rx_tcp", cfg, ipver, False, "-t"))
+            cases.append(test_builder("rx_tcp_invalid", cfg, ipver, False, "-t -E"))
+
+            cases.append(test_builder("rx_udp", cfg, ipver, False, ""))
+            cases.append(test_builder("rx_udp_invalid", cfg, ipver, False, "-E"))
+
+            cases.append(test_builder("tx_udp_csum_offload", cfg, ipver, True, "-U"))
+            cases.append(test_builder("tx_udp_zero_checksum", cfg, ipver, True, "-U -Z"))
+
+        ksft_run(cases=cases, args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/devlink_port_split.py

@@ -0,0 +1,309 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from subprocess import PIPE, Popen
+import json
+import time
+import argparse
+import collections
+import sys
+
+#
+# Test port split configuration using devlink-port lanes attribute.
+# The test is skipped in case the attribute is not available.
+#
+# First, check that all the ports with 1 lane fail to split.
+# Second, check that all the ports with more than 1 lane can be split
+# to all valid configurations (e.g., split to 2, split to 4 etc.)
+#
+
+
+# Kselftest framework requirement - SKIP code is 4
+KSFT_SKIP=4
+Port = collections.namedtuple('Port', 'bus_info name')
+
+
+def run_command(cmd, should_fail=False):
+    """
+    Run a command in subprocess.
+    Return: Tuple of (stdout, stderr).
+    """
+
+    p = Popen(cmd, stdout=PIPE, stderr=PIPE, shell=True)
+    stdout, stderr = p.communicate()
+    stdout, stderr = stdout.decode(), stderr.decode()
+
+    if stderr != "" and not should_fail:
+        print("Error sending command: %s" % cmd)
+        print(stdout)
+        print(stderr)
+    return stdout, stderr
+
+
+class devlink_ports(object):
+    """
+    Class that holds information on the devlink ports, required to the tests;
+    if_names: A list of interfaces in the devlink ports.
+    """
+
+    def get_if_names(dev):
+        """
+        Get a list of physical devlink ports.
+        Return: Array of tuples (bus_info/port, if_name).
+        """
+
+        arr = []
+
+        cmd = "devlink -j port show"
+        stdout, stderr = run_command(cmd)
+        assert stderr == ""
+        ports = json.loads(stdout)['port']
+
+        validate_devlink_output(ports, 'flavour')
+
+        for port in ports:
+            if dev in port:
+                if ports[port]['flavour'] == 'physical':
+                    arr.append(Port(bus_info=port, name=ports[port]['netdev']))
+
+        return arr
+
+    def __init__(self, dev):
+        self.if_names = devlink_ports.get_if_names(dev)
+
+
+def get_max_lanes(port):
+    """
+    Get the $port's maximum number of lanes.
+    Return: number of lanes, e.g. 1, 2, 4 and 8.
+    """
+
+    cmd = "devlink -j port show %s" % port
+    stdout, stderr = run_command(cmd)
+    assert stderr == ""
+    values = list(json.loads(stdout)['port'].values())[0]
+
+    if 'lanes' in values:
+        lanes = values['lanes']
+    else:
+        lanes = 0
+    return lanes
+
+
+def get_split_ability(port):
+    """
+    Get the $port split ability.
+    Return: split ability, true or false.
+    """
+
+    cmd = "devlink -j port show %s" % port.name
+    stdout, stderr = run_command(cmd)
+    assert stderr == ""
+    values = list(json.loads(stdout)['port'].values())[0]
+
+    return values['splittable']
+
+
+def split(k, port, should_fail=False):
+    """
+    Split $port into $k ports.
+    If should_fail == True, the split should fail. Otherwise, should pass.
+    Return: Array of sub ports after splitting.
+            If the $port wasn't split, the array will be empty.
+    """
+
+    cmd = "devlink port split %s count %s" % (port.bus_info, k)
+    stdout, stderr = run_command(cmd, should_fail=should_fail)
+
+    if should_fail:
+        if not test(stderr != "", "%s is unsplittable" % port.name):
+            print("split an unsplittable port %s" % port.name)
+            return create_split_group(port, k)
+    else:
+        if stderr == "":
+            return create_split_group(port, k)
+        print("didn't split a splittable port %s" % port.name)
+
+    return []
+
+
+def unsplit(port):
+    """
+    Unsplit $port.
+    """
+
+    cmd = "devlink port unsplit %s" % port
+    stdout, stderr = run_command(cmd)
+    test(stderr == "", "Unsplit port %s" % port)
+
+
+def exists(port, dev):
+    """
+    Check if $port exists in the devlink ports.
+    Return: True is so, False otherwise.
+    """
+
+    return any(dev_port.name == port
+               for dev_port in devlink_ports.get_if_names(dev))
+
+
+def exists_and_lanes(ports, lanes, dev):
+    """
+    Check if every port in the list $ports exists in the devlink ports and has
+    $lanes number of lanes after splitting.
+    Return: True if both are True, False otherwise.
+    """
+
+    for port in ports:
+        max_lanes = get_max_lanes(port)
+        if not exists(port, dev):
+            print("port %s doesn't exist in devlink ports" % port)
+            return False
+        if max_lanes != lanes:
+            print("port %s has %d lanes, but %s were expected"
+                  % (port, lanes, max_lanes))
+            return False
+    return True
+
+
+def test(cond, msg):
+    """
+    Check $cond and print a message accordingly.
+    Return: True is pass, False otherwise.
+    """
+
+    if cond:
+        print("TEST: %-60s [ OK ]" % msg)
+    else:
+        print("TEST: %-60s [FAIL]" % msg)
+
+    return cond
+
+
+def create_split_group(port, k):
+    """
+    Create the split group for $port.
+    Return: Array with $k elements, which are the split port group.
+    """
+
+    return list(port.name + "s" + str(i) for i in range(k))
+
+
+def split_unsplittable_port(port, k):
+    """
+    Test that splitting of unsplittable port fails.
+    """
+
+    # split to max
+    new_split_group = split(k, port, should_fail=True)
+
+    if new_split_group != []:
+        unsplit(port.bus_info)
+
+
+def split_splittable_port(port, k, lanes, dev):
+    """
+    Test that splitting of splittable port passes correctly.
+    """
+
+    new_split_group = split(k, port)
+
+    # Once the split command ends, it takes some time to the sub ifaces'
+    # to get their names. Use udevadm to continue only when all current udev
+    # events are handled.
+    cmd = "udevadm settle"
+    stdout, stderr = run_command(cmd)
+    assert stderr == ""
+
+    if new_split_group != []:
+        test(exists_and_lanes(new_split_group, lanes/k, dev),
+             "split port %s into %s" % (port.name, k))
+
+    unsplit(port.bus_info)
+
+
+def validate_devlink_output(devlink_data, target_property=None):
+    """
+    Determine if test should be skipped by checking:
+      1. devlink_data contains values
+      2. The target_property exist in devlink_data
+    """
+    skip_reason = None
+    if any(devlink_data.values()):
+        if target_property:
+            skip_reason = "{} not found in devlink output, test skipped".format(target_property)
+            for key in devlink_data:
+                if target_property in devlink_data[key]:
+                    skip_reason = None
+    else:
+        skip_reason = 'devlink output is empty, test skipped'
+
+    if skip_reason:
+        print(skip_reason)
+        sys.exit(KSFT_SKIP)
+
+
+def make_parser():
+    parser = argparse.ArgumentParser(description='A test for port splitting.')
+    parser.add_argument('--dev',
+                        help='The devlink handle of the device under test. ' +
+                             'The default is the first registered devlink ' +
+                             'handle.')
+
+    return parser
+
+
+def main(cmdline=None):
+    parser = make_parser()
+    args = parser.parse_args(cmdline)
+
+    dev = args.dev
+    if not dev:
+        cmd = "devlink -j dev show"
+        stdout, stderr = run_command(cmd)
+        assert stderr == ""
+
+        validate_devlink_output(json.loads(stdout))
+        devs = json.loads(stdout)['dev']
+        dev = list(devs.keys())[0]
+
+    cmd = "devlink dev show %s" % dev
+    stdout, stderr = run_command(cmd)
+    if stderr != "":
+        print("devlink device %s can not be found" % dev)
+        sys.exit(1)
+
+    ports = devlink_ports(dev)
+
+    found_max_lanes = False
+    for port in ports.if_names:
+        max_lanes = get_max_lanes(port.name)
+
+        # If max lanes is 0, do not test port splitting at all
+        if max_lanes == 0:
+            continue
+
+        # If 1 lane, shouldn't be able to split
+        elif max_lanes == 1:
+            test(not get_split_ability(port),
+                 "%s should not be able to split" % port.name)
+            split_unsplittable_port(port, max_lanes)
+
+        # Else, splitting should pass and all the split ports should exist.
+        else:
+            lane = max_lanes
+            test(get_split_ability(port),
+                 "%s should be able to split" % port.name)
+            while lane > 1:
+                split_splittable_port(port, lane, max_lanes, dev)
+
+                lane //= 2
+        found_max_lanes = True
+
+    if not found_max_lanes:
+        print(f"Test not started, no port of device {dev} reports max_lanes")
+        sys.exit(KSFT_SKIP)
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/devlink_rate_tc_bw.py

@@ -0,0 +1,439 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Devlink Rate TC Bandwidth Test Suite
+===================================
+
+This test suite verifies the functionality of devlink-rate traffic class (TC)
+bandwidth distribution in a virtualized environment. The tests validate that
+bandwidth can be properly allocated between different traffic classes and
+that TC mapping works as expected.
+
+Test Environment:
+----------------
+- Creates 1 VF
+- Establishes a bridge connecting the VF representor and the uplink representor
+- Sets up 2 VLAN interfaces on the VF with different VLAN IDs (101, 102)
+- Configures different traffic classes (TC3 and TC4) for each VLAN
+
+Test Cases:
+----------
+1. test_no_tc_mapping_bandwidth:
+   - Verifies that without TC mapping, bandwidth is NOT distributed according to
+     the configured 20/80 split between TC3 and TC4
+   - This test should fail if bandwidth matches the 20/80 split without TC
+     mapping
+   - Expected: Bandwidth should NOT be distributed as 20/80
+
+2. test_tc_mapping_bandwidth:
+   - Configures TC mapping using mqprio qdisc
+   - Verifies that with TC mapping, bandwidth IS distributed according to the
+     configured 20/80 split between TC3 and TC4
+   - Expected: Bandwidth should be distributed as 20/80
+
+Bandwidth Distribution:
+----------------------
+- TC3 (VLAN 101): Configured for 20% of total bandwidth
+- TC4 (VLAN 102): Configured for 80% of total bandwidth
+- Total bandwidth: 1Gbps
+- Tolerance: +-12%
+
+Hardware-Specific Behavior (mlx5):
+--------------------------
+mlx5 hardware enforces traffic class separation by ensuring that each transmit
+queue (SQ) is associated with a single TC. If a packet is sent on a queue that
+doesn't match the expected TC (based on DSCP or VLAN priority and hypervisor-set
+mapping), the hardware moves the queue to the correct TC scheduler to preserve
+traffic isolation.
+
+This behavior means that even without explicit TC-to-queue mapping, bandwidth
+enforcement may still appear to work—because the hardware dynamically adjusts
+the scheduling context. However, this can lead to performance issues in high
+rates and HOL blocking if traffic from different TCs is mixed on the same queue.
+"""
+
+import json
+import os
+import subprocess
+import threading
+import time
+
+from lib.py import ksft_pr, ksft_run, ksft_exit
+from lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx
+from lib.py import NetDrvEpEnv, DevlinkFamily
+from lib.py import NlError
+from lib.py import cmd, defer, ethtool, ip
+from lib.py import Iperf3Runner
+
+
+class BandwidthValidator:
+    """
+    Validates total bandwidth and individual shares with tolerance
+    relative to the overall total.
+    """
+
+    def __init__(self, shares):
+        self.tolerance_percent = 12
+        self.expected_total = sum(shares.values())
+        self.bounds = {}
+
+        for name, exp in shares.items():
+            self.bounds[name] = (self.min_expected(exp), self.max_expected(exp))
+
+    def min_expected(self, value):
+        """Calculates the minimum acceptable value based on tolerance."""
+        return value - (self.expected_total * self.tolerance_percent / 100)
+
+    def max_expected(self, value):
+        """Calculates the maximum acceptable value based on tolerance."""
+        return value + (self.expected_total * self.tolerance_percent / 100)
+
+    def bound(self, values):
+        """
+        Return True if all given values fall within tolerance.
+        """
+        for name, value in values.items():
+            low, high = self.bounds[name]
+            if not low <= value <= high:
+                return False
+        return True
+
+
+def setup_vf(cfg, set_tc_mapping=True):
+    """
+    Sets up a VF on the given network interface.
+
+    Enables SR-IOV and switchdev mode, brings the VF interface up,
+    and optionally configures TC mapping using mqprio.
+    """
+    try:
+        cmd(f"devlink dev eswitch set pci/{cfg.pci} mode switchdev")
+        defer(cmd, f"devlink dev eswitch set pci/{cfg.pci} mode legacy")
+    except Exception as exc:
+        raise KsftSkipEx(f"Failed to enable switchdev mode on {cfg.pci}") from exc
+    try:
+        cmd(f"echo 1 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs", shell=True)
+        defer(cmd, f"echo 0 > /sys/class/net/{cfg.ifname}/device/sriov_numvfs", shell=True)
+    except Exception as exc:
+        raise KsftSkipEx(f"Failed to enable SR-IOV on {cfg.ifname}") from exc
+
+    time.sleep(2)
+    vf_ifc = (os.listdir(
+        f"/sys/class/net/{cfg.ifname}/device/virtfn0/net") or [None])[0]
+    if vf_ifc:
+        ip(f"link set dev {vf_ifc} up")
+    else:
+        raise KsftSkipEx("VF interface not found")
+    if set_tc_mapping:
+        cmd(f"tc qdisc add dev {vf_ifc} root handle 5 mqprio mode dcb hw 1 num_tc 8")
+
+    return vf_ifc
+
+
+def setup_vlans_on_vf(vf_ifc):
+    """
+    Sets up two VLAN interfaces on the given VF, each mapped to a different TC.
+    """
+    vlan_configs = [
+        {"vlan_id": 101, "tc": 3, "ip": "198.51.100.1"},
+        {"vlan_id": 102, "tc": 4, "ip": "198.51.100.9"},
+    ]
+
+    for config in vlan_configs:
+        vlan_dev = f"{vf_ifc}.{config['vlan_id']}"
+        ip(f"link add link {vf_ifc} name {vlan_dev} type vlan id {config['vlan_id']}")
+        ip(f"addr add {config['ip']}/29 dev {vlan_dev}")
+        ip(f"link set dev {vlan_dev} up")
+        ip(f"link set dev {vlan_dev} type vlan egress-qos-map 0:{config['tc']}")
+        ksft_pr(f"Created VLAN {vlan_dev} on {vf_ifc} with tc {config['tc']} and IP {config['ip']}")
+
+
+def get_vf_info(cfg):
+    """
+    Finds the VF representor interface and devlink port index
+    for the given PCI device used in the test environment.
+    """
+    cfg.vf_representor = None
+    cfg.vf_port_index = None
+    out = subprocess.check_output(["devlink", "-j", "port", "show"], encoding="utf-8")
+    ports = json.loads(out)["port"]
+
+    for port_name, props in ports.items():
+        netdev = props.get("netdev")
+
+        if (port_name.startswith(f"pci/{cfg.pci}/") and
+            props.get("vfnum") == 0):
+            cfg.vf_representor = netdev
+            cfg.vf_port_index = int(port_name.split("/")[-1])
+            break
+
+
+def setup_bridge(cfg):
+    """
+    Creates and configures a Linux bridge, with both the uplink
+    and VF representor interfaces attached to it.
+    """
+    bridge_name = f"br_{os.getpid()}"
+    ip(f"link add name {bridge_name} type bridge")
+    defer(cmd, f"ip link del name {bridge_name} type bridge")
+
+    ip(f"link set dev {cfg.ifname} master {bridge_name}")
+
+    rep_name = cfg.vf_representor
+    if rep_name:
+        ip(f"link set dev {rep_name} master {bridge_name}")
+        ip(f"link set dev {rep_name} up")
+        ksft_pr(f"Set representor {rep_name} up and added to bridge")
+    else:
+        raise KsftSkipEx("Could not find representor for the VF")
+
+    ip(f"link set dev {bridge_name} up")
+
+
+def setup_devlink_rate(cfg):
+    """
+    Configures devlink rate tx_max and traffic class bandwidth for the VF.
+    """
+    port_index = cfg.vf_port_index
+    if port_index is None:
+        raise KsftSkipEx("Could not find VF port index")
+    try:
+        cfg.devnl.rate_set({
+            "bus-name": "pci",
+            "dev-name": cfg.pci,
+            "port-index": port_index,
+            "rate-tx-max": 125000000,
+            "rate-tc-bws": [
+                {"index": 0, "bw": 0},
+                {"index": 1, "bw": 0},
+                {"index": 2, "bw": 0},
+                {"index": 3, "bw": 20},
+                {"index": 4, "bw": 80},
+                {"index": 5, "bw": 0},
+                {"index": 6, "bw": 0},
+                {"index": 7, "bw": 0},
+            ]
+        })
+    except NlError as exc:
+        if exc.error == 95:  # EOPNOTSUPP
+            raise KsftSkipEx("devlink rate configuration is not supported on the VF") from exc
+        raise KsftFailEx(f"rate_set failed on VF port {port_index}") from exc
+
+
+def setup_remote_vlans(cfg):
+    """
+    Sets up VLAN interfaces on the remote side.
+    """
+    remote_dev = cfg.remote_ifname
+    vlan_ids = [101, 102]
+    remote_ips = ["198.51.100.2", "198.51.100.10"]
+
+    for vlan_id, ip_addr in zip(vlan_ids, remote_ips):
+        vlan_dev = f"{remote_dev}.{vlan_id}"
+        cmd(f"ip link add link {remote_dev} name {vlan_dev} "
+            f"type vlan id {vlan_id}", host=cfg.remote)
+        cmd(f"ip addr add {ip_addr}/29 dev {vlan_dev}", host=cfg.remote)
+        cmd(f"ip link set dev {vlan_dev} up", host=cfg.remote)
+        defer(cmd, f"ip link del {vlan_dev}", host=cfg.remote)
+
+
+def setup_test_environment(cfg, set_tc_mapping=True):
+    """
+    Sets up the complete test environment including VF creation, VLANs,
+    bridge configuration and devlink rate setup.
+    """
+    vf_ifc = setup_vf(cfg, set_tc_mapping)
+    ksft_pr(f"Created VF interface: {vf_ifc}")
+
+    setup_vlans_on_vf(vf_ifc)
+
+    get_vf_info(cfg)
+    setup_bridge(cfg)
+
+    setup_devlink_rate(cfg)
+    setup_remote_vlans(cfg)
+
+
+def measure_bandwidth(cfg, server_ip, client_ip, barrier):
+    """
+    Synchronizes with peers and runs an iperf3-based bandwidth measurement
+    between the given endpoints. Returns average Gbps.
+    """
+    runner = Iperf3Runner(cfg, server_ip=server_ip, client_ip=client_ip)
+    try:
+        barrier.wait(timeout=10)
+    except Exception as exc:
+        raise KsftFailEx("iperf3 barrier wait timed") from exc
+
+    try:
+        bw_gbps = runner.measure_bandwidth(reverse=True)
+    except Exception as exc:
+        raise KsftFailEx("iperf3 bandwidth measurement failed") from exc
+
+    return bw_gbps
+
+
+def run_bandwidth_test(cfg):
+    """
+    Runs parallel bandwidth measurements for each VLAN/TC pair and collects results.
+    """
+    def _run_measure_bandwidth_thread(local_ip, remote_ip, results, barrier, tc_ix):
+        results[tc_ix] = measure_bandwidth(cfg, local_ip, remote_ip, barrier)
+
+    vf_vlan_data = [
+        # (local_ip, remote_ip, TC)
+        ("198.51.100.1",  "198.51.100.2", 3),
+        ("198.51.100.9", "198.51.100.10", 4),
+    ]
+
+    results = {}
+    threads = []
+    start_barrier = threading.Barrier(len(vf_vlan_data))
+
+    for local_ip, remote_ip, tc_ix in vf_vlan_data:
+        thread = threading.Thread(
+            target=_run_measure_bandwidth_thread,
+            args=(local_ip, remote_ip, results, start_barrier, tc_ix)
+        )
+        thread.start()
+        threads.append(thread)
+
+    for thread in threads:
+        thread.join()
+
+    for tc_ix, tc_bw in results.items():
+        if tc_bw is None:
+            raise KsftFailEx("iperf3 failed; cannot evaluate bandwidth")
+
+    return results
+
+
+def calculate_bandwidth_percentages(results):
+    """
+    Calculates the percentage of total bandwidth received by TC3 and TC4.
+    """
+    if 3 not in results or 4 not in results:
+        raise KsftFailEx(f"Missing expected TC results in {results}")
+
+    tc3_bw = results[3]
+    tc4_bw = results[4]
+    total_bw = tc3_bw + tc4_bw
+    tc3_percentage = (tc3_bw / total_bw) * 100
+    tc4_percentage = (tc4_bw / total_bw) * 100
+
+    return {
+        'tc3_bw': tc3_bw,
+        'tc4_bw': tc4_bw,
+        'tc3_percentage': tc3_percentage,
+        'tc4_percentage': tc4_percentage,
+        'total_bw': total_bw
+    }
+
+
+def print_bandwidth_results(bw_data, test_name):
+    """
+    Prints bandwidth measurements and TC usage summary for a given test.
+    """
+    ksft_pr(f"Bandwidth check results {test_name}:")
+    ksft_pr(f"TC 3: {bw_data['tc3_bw']:.2f} Gbits/sec")
+    ksft_pr(f"TC 4: {bw_data['tc4_bw']:.2f} Gbits/sec")
+    ksft_pr(f"Total bandwidth: {bw_data['total_bw']:.2f} Gbits/sec")
+    ksft_pr(f"TC 3 percentage: {bw_data['tc3_percentage']:.1f}%")
+    ksft_pr(f"TC 4 percentage: {bw_data['tc4_percentage']:.1f}%")
+
+
+def verify_total_bandwidth(bw_data, validator):
+    """
+    Ensures the total measured bandwidth falls within the acceptable tolerance.
+    """
+    total = bw_data['total_bw']
+
+    if validator.bound({"total": total}):
+        return
+
+    low, high = validator.bounds["total"]
+
+    if total < low:
+        raise KsftSkipEx(
+            f"Total bandwidth {total:.2f} Gbps < minimum "
+            f"{low:.2f} Gbps; "
+            f"parent tx_max ({validator.expected_total:.1f} G) "
+            f"not reached, cannot validate share"
+        )
+
+    raise KsftFailEx(
+        f"Total bandwidth {total:.2f} Gbps exceeds allowed ceiling "
+        f"{high:.2f} Gbps "
+        f"(VF tx_max set to {validator.expected_total:.1f} G)"
+    )
+
+
+def run_bandwidth_distribution_test(cfg, set_tc_mapping):
+    """
+    Runs parallel bandwidth measurements for both TCs and collects results.
+    """
+    setup_test_environment(cfg, set_tc_mapping)
+    bandwidths = run_bandwidth_test(cfg)
+    bw_data = calculate_bandwidth_percentages(bandwidths)
+    test_name = "with TC mapping" if set_tc_mapping else "without TC mapping"
+    print_bandwidth_results(bw_data, test_name)
+
+    verify_total_bandwidth(bw_data, cfg.traffic_bw_validator)
+
+    return cfg.tc_bw_validator.bound({"tc3": bw_data['tc3_percentage'],
+                                     "tc4": bw_data['tc4_percentage']})
+
+
+def test_no_tc_mapping_bandwidth(cfg):
+    """
+    Verifies that bandwidth is not split 20/80 without traffic class mapping.
+    """
+    pass_bw_msg = "Bandwidth is NOT distributed as 20/80 without TC mapping"
+    fail_bw_msg = "Bandwidth matched 20/80 split without TC mapping"
+    is_mlx5 = "driver: mlx5" in ethtool(f"-i {cfg.ifname}").stdout
+
+    if run_bandwidth_distribution_test(cfg, set_tc_mapping=False):
+        if is_mlx5:
+            raise KsftXfailEx(fail_bw_msg)
+        raise KsftFailEx(fail_bw_msg)
+    if is_mlx5:
+        raise KsftFailEx("mlx5 behavior changed:" + pass_bw_msg)
+    ksft_pr(pass_bw_msg)
+
+
+def test_tc_mapping_bandwidth(cfg):
+    """
+    Verifies that bandwidth is correctly split 20/80 between TC3 and TC4
+    when traffic class mapping is set.
+    """
+    if run_bandwidth_distribution_test(cfg, set_tc_mapping=True):
+        ksft_pr("Bandwidth is distributed as 20/80 with TC mapping")
+    else:
+        raise KsftFailEx("Bandwidth did not match 20/80 split with TC mapping")
+
+
+def main() -> None:
+    """
+    Main entry point for running the test cases.
+    """
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        cfg.devnl = DevlinkFamily()
+
+        cfg.pci = os.path.basename(
+            os.path.realpath(f"/sys/class/net/{cfg.ifname}/device")
+        )
+        if not cfg.pci:
+            raise KsftSkipEx("Could not get PCI address of the interface")
+
+        cfg.traffic_bw_validator = BandwidthValidator({"total": 1})
+        cfg.tc_bw_validator = BandwidthValidator({"tc3": 20, "tc4": 80})
+
+        cases = [test_no_tc_mapping_bandwidth, test_tc_mapping_bandwidth]
+
+        ksft_run(cases=cases, args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/devmem.py

@@ -0,0 +1,43 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from os import path
+from devmem_lib import setup_test, run_rx, run_tx, run_tx_chunks, run_rx_hds
+from lib.py import ksft_run, ksft_exit, ksft_disruptive
+from lib.py import NetDrvEpEnv
+
+
+@ksft_disruptive
+def check_rx(cfg) -> None:
+    """Run the devmem RX test."""
+    run_rx(cfg)
+
+
+@ksft_disruptive
+def check_tx(cfg) -> None:
+    """Run the devmem TX test."""
+    run_tx(cfg)
+
+
+@ksft_disruptive
+def check_tx_chunks(cfg) -> None:
+    """Run the devmem TX chunking test."""
+    run_tx_chunks(cfg)
+
+
+def check_rx_hds(cfg) -> None:
+    """Run the HDS test."""
+    run_rx_hds(cfg)
+
+
+def main() -> None:
+    """Run the devmem test cases."""
+    with NetDrvEpEnv(__file__) as cfg:
+        setup_test(cfg, path.abspath(path.dirname(__file__) + "/ncdevmem"))
+        ksft_run([check_rx, check_tx, check_tx_chunks, check_rx_hds],
+                 args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/devmem_lib.py

@@ -0,0 +1,222 @@
+# SPDX-License-Identifier: GPL-2.0
+"""Shared helpers for devmem TCP selftests."""
+
+import re
+
+from lib.py import (bkg, cmd, defer, ethtool, rand_port, wait_port_listen,
+                    ksft_eq, KsftSkipEx, NetNSEnter, EthtoolFamily,
+                    NetdevFamily)
+
+
+def require_devmem(cfg):
+    """Probe ncdevmem on cfg.ifname and SKIP the test if devmem isn't supported."""
+    if not hasattr(cfg, "devmem_probed"):
+        probe_command = f"{cfg.bin_local} -f {cfg.ifname}"
+        cfg.devmem_supported = cmd(probe_command, fail=False, shell=True).ret == 0
+        cfg.devmem_probed = True
+
+    if not cfg.devmem_supported:
+        raise KsftSkipEx("Test requires devmem support")
+
+
+def configure_nic(cfg):
+    """Channels, rings, RSS, queue lease for netkit devmem."""
+    if not hasattr(cfg, 'netns'):
+        return
+
+    cfg.require_ipver('6')
+    ethnl = EthtoolFamily()
+
+    channels = ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    channels = channels['combined-count']
+    if channels < 2:
+        raise KsftSkipEx(
+            'Test requires NETIF with at least 2 combined channels'
+        )
+
+    rings = ethnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    orig_rx_rings = rings['rx']
+    orig_hds_thresh = rings.get('hds-thresh', 0)
+    orig_data_split = rings.get('tcp-data-split', 'unknown')
+
+    ethnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                     'tcp-data-split': 'enabled',
+                     'hds-thresh': 0,
+                     'rx': min(64, orig_rx_rings)})
+    defer(ethnl.rings_set, {'header': {'dev-index': cfg.ifindex},
+                            'tcp-data-split': orig_data_split,
+                            'hds-thresh': orig_hds_thresh,
+                            'rx': orig_rx_rings})
+
+    cfg.src_queue = channels - 1
+    ethtool(f"-X {cfg.ifname} equal {cfg.src_queue}")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    if not hasattr(cfg, 'nk_queue'):
+        with NetNSEnter(str(cfg.netns)):
+            netdevnl = NetdevFamily()
+            lease_result = netdevnl.queue_create({
+                "ifindex": cfg.nk_guest_ifindex,
+                "type": "rx",
+                "lease": {
+                    "ifindex": cfg.ifindex,
+                    "queue": {"id": cfg.src_queue, "type": "rx"},
+                    "netns-id": 0,
+                },
+            })
+            cfg.nk_queue = lease_result['id']
+
+
+def set_flow_rule(cfg, port):
+    """Install a flow rule steering to src_queue and return the flow rule ID."""
+    output = ethtool(
+        f"-N {cfg.ifname} flow-type tcp6 dst-port {port}"
+        f" action {cfg.src_queue}"
+    ).stdout
+    return int(re.search(r'ID (\d+)', output).group(1))
+
+
+def ncdevmem_rx(cfg, port, verify=True, fail_on_linear=False, flow_steer=False):
+    """Build the ncdevmem RX listener command."""
+    if hasattr(cfg, 'netns'):
+        flow_rule_id = set_flow_rule(cfg, port)
+        defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}")
+
+        ifname = cfg.nk_guest_ifname
+        addr = cfg.nk_guest_ipv6
+        extras = [f"-t {cfg.nk_queue}", "-q 1", "-n"]
+    else:
+        ifname = cfg.ifname
+        addr = cfg.addr
+        extras = []
+        if flow_steer:
+            extras.append(f"-c {cfg.remote_addr}")
+
+    if verify:
+        extras.append("-v 7")
+    if fail_on_linear:
+        extras.append("-L")
+
+    parts = [cfg.bin_local, "-l", f"-f {ifname}", f"-s {addr}",
+             f"-p {port}", *extras]
+    return " ".join(parts)
+
+
+def ncdevmem_tx(cfg, port, chunk_size=0):
+    """Build the ncdevmem TX send command."""
+    if hasattr(cfg, 'netns'):
+        ifname = cfg.nk_guest_ifname
+        addr = cfg.remote_addr_v['6']
+        extras = ["-t 0", "-q 1", "-n"]
+    else:
+        ifname = cfg.ifname
+        addr = cfg.remote_addr
+        extras = []
+
+    if chunk_size:
+        extras.append(f"-z {chunk_size}")
+
+    parts = [cfg.bin_local, f"-f {ifname}", f"-s {addr}",
+             f"-p {port}", *extras]
+    return " ".join(parts)
+
+
+def socat_send(cfg, port, buf_size=0):
+    """Socat command for sending to the devmem listener.
+
+    When buf_size > 0, force one TCP segment per write of exactly that size by
+    setting socat's buffer (-b) and disabling Nagle (TCP_NODELAY).
+    """
+    proto = f"TCP{cfg.addr_ipver}"
+
+    if hasattr(cfg, 'netns'):
+        addr = f"[{cfg.nk_guest_ipv6}]"
+    else:
+        addr = cfg.baddr
+
+    suffix = f",bind={cfg.remote_baddr}:{port}"
+
+    buf = ""
+    if buf_size:
+        buf = f"-b {buf_size}"
+        suffix += ",nodelay"
+
+    return f"socat {buf} -u - {proto}:{addr}:{port}{suffix}"
+
+
+def socat_listen(cfg, port):
+    """Socat listen command for TX tests."""
+    return f"socat -U - TCP{cfg.addr_ipver}-LISTEN:{port}"
+
+
+def setup_test(cfg, bin_local):
+    """Stash the local ncdevmem path on cfg and deploy it to the remote."""
+    cfg.bin_local = bin_local
+    cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
+
+
+def run_rx(cfg):
+    """Run the devmem RX test."""
+    require_devmem(cfg)
+    configure_nic(cfg)
+    port = rand_port()
+    socat = socat_send(cfg, port)
+    data_pipe = (f"yes $(echo -e \x01\x02\x03\x04\x05\x06) | head -c 1K"
+                 f" | {socat}")
+    netns = getattr(cfg, "netns", None)
+
+    listen_cmd = ncdevmem_rx(cfg, port, flow_steer=not hasattr(cfg, 'netns'))
+    with bkg(listen_cmd, exit_wait=True, ns=netns) as ncdevmem:
+        wait_port_listen(port, proto="tcp", ns=netns)
+        cmd(data_pipe, host=cfg.remote, shell=True)
+    ksft_eq(ncdevmem.ret, 0)
+
+
+def run_tx(cfg):
+    """Run the devmem TX test."""
+    require_devmem(cfg)
+    configure_nic(cfg)
+    netns = getattr(cfg, "netns", None)
+    port = rand_port()
+    tx_cmd = ncdevmem_tx(cfg, port)
+    listen_cmd = socat_listen(cfg, port)
+
+    with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as socat:
+        wait_port_listen(port, host=cfg.remote)
+        cmd(f"bash -c 'echo -e \"hello\\nworld\" | {tx_cmd}'", ns=netns, shell=True)
+    ksft_eq(socat.stdout.strip(), "hello\nworld")
+
+
+def run_tx_chunks(cfg):
+    """Run the devmem TX chunking test."""
+    require_devmem(cfg)
+    configure_nic(cfg)
+    netns = getattr(cfg, "netns", None)
+    port = rand_port()
+    tx_cmd = ncdevmem_tx(cfg, port, chunk_size=3)
+    listen_cmd = socat_listen(cfg, port)
+
+    with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as socat:
+        wait_port_listen(port, host=cfg.remote)
+        cmd(f"bash -c 'echo -e \"hello\\nworld\" | {tx_cmd}'", ns=netns, shell=True)
+    ksft_eq(socat.stdout.strip(), "hello\nworld")
+
+
+def run_rx_hds(cfg):
+    """Run the HDS test by running devmem RX across a segment size sweep."""
+    require_devmem(cfg)
+    configure_nic(cfg)
+    netns = getattr(cfg, "netns", None)
+
+    for size in [1, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8192]:
+        port = rand_port()
+
+        listen_cmd = ncdevmem_rx(cfg, port, verify=False,
+                                 fail_on_linear=True)
+        socat = socat_send(cfg, port, buf_size=size)
+
+        with bkg(listen_cmd, exit_wait=True, ns=netns) as ncdevmem:
+            wait_port_listen(port, proto="tcp", ns=netns)
+            cmd(f"dd if=/dev/zero bs={size} count=1 2>/dev/null | "
+                f"{socat}", host=cfg.remote, shell=True)
+        ksft_eq(ncdevmem.ret, 0, f"HDS failed for payload size {size}")

linux-7.2.3/tools/testing/selftests/drivers/net/hw/ethtool.sh

@@ -0,0 +1,297 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	same_speeds_autoneg_off
+	different_speeds_autoneg_off
+	combination_of_neg_on_and_off
+	advertise_subset_of_speeds
+	check_highest_speed_is_chosen
+	different_speeds_autoneg_on
+"
+NUM_NETIFS=2
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+source ethtool_lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/24
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1 192.0.2.1/24
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.2/24
+}
+
+h2_destroy()
+{
+	simple_if_fini $h2 192.0.2.2/24
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	h2=${NETIFS[p2]}
+
+	h1_create
+	h2_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	h2_destroy
+	h1_destroy
+}
+
+same_speeds_autoneg_off()
+{
+	# Check that when each of the reported speeds is forced, the links come
+	# up and are operational.
+	local -a speeds_arr=($(common_speeds_get $h1 $h2 0 0))
+
+	for speed in "${speeds_arr[@]}"; do
+		RET=0
+		ethtool_set $h1 speed $speed autoneg off
+		ethtool_set $h2 speed $speed autoneg off
+
+		setup_wait_dev_with_timeout $h1
+		setup_wait_dev_with_timeout $h2
+		ping_do $h1 192.0.2.2
+		check_err $? "ping with speed $speed autoneg off"
+		log_test "force speed $speed on both ends"
+	done
+
+	ethtool -s $h2 autoneg on
+	ethtool -s $h1 autoneg on
+}
+
+different_speeds_autoneg_off()
+{
+	# Test that when we force different speeds, links are not up and ping
+	# fails.
+	RET=0
+
+	local -a speeds_arr=($(different_speeds_get $h1 $h2 0 0))
+	local speed1=${speeds_arr[0]}
+	local speed2=${speeds_arr[1]}
+
+	ethtool_set $h1 speed $speed1 autoneg off
+	ethtool_set $h2 speed $speed2 autoneg off
+
+	setup_wait_dev_with_timeout $h1
+	setup_wait_dev_with_timeout $h2
+	ping_do $h1 192.0.2.2
+	check_fail $? "ping with different speeds"
+
+	log_test "force of different speeds autoneg off"
+
+	ethtool -s $h2 autoneg on
+	ethtool -s $h1 autoneg on
+}
+
+combination_of_neg_on_and_off()
+{
+	# Test that when one device is forced to a speed supported by both
+	# endpoints and the other device is configured to autoneg on, the links
+	# are up and ping passes.
+	local -a speeds_arr=($(common_speeds_get $h1 $h2 0 1))
+
+	for speed in "${speeds_arr[@]}"; do
+		RET=0
+		ethtool_set $h1 speed $speed autoneg off
+
+		setup_wait_dev_with_timeout $h1
+		setup_wait_dev_with_timeout $h2
+		ping_do $h1 192.0.2.2
+		check_err $? "ping with h1-speed=$speed autoneg off, h2 autoneg on"
+		log_test "force speed $speed vs. autoneg"
+	done
+
+	ethtool -s $h1 autoneg on
+}
+
+hex_speed_value_get()
+{
+	local speed=$1; shift
+
+	local shift_size=${speed_values[$speed]}
+	speed=$((0x1 << $"shift_size"))
+	printf "%#x" "$speed"
+}
+
+subset_of_common_speeds_get()
+{
+	local dev1=$1; shift
+	local dev2=$1; shift
+	local adver=$1; shift
+
+	local -a speeds_arr=($(common_speeds_get $dev1 $dev2 0 $adver))
+	local speed_to_advertise=0
+	local speed_to_remove=${speeds_arr[0]}
+	speed_to_remove+='base'
+
+	local -a speeds_mode_arr=($(common_speeds_get $dev1 $dev2 1 $adver))
+
+	for speed in ${speeds_mode_arr[@]}; do
+		if [[ $speed != $speed_to_remove* ]]; then
+			speed=$(hex_speed_value_get $speed)
+			speed_to_advertise=$(($speed_to_advertise | \
+						$speed))
+		fi
+
+	done
+
+	# Convert to hex.
+	printf "%#x" "$speed_to_advertise"
+}
+
+speed_to_advertise_get()
+{
+	# The function returns the hex number that is composed by OR-ing all
+	# the modes corresponding to the provided speed.
+	local speed_without_mode=$1; shift
+	local supported_speeds=("$@"); shift
+	local speed_to_advertise=0
+
+	speed_without_mode+='base'
+
+	for speed in ${supported_speeds[@]}; do
+		if [[ $speed == $speed_without_mode* ]]; then
+			speed=$(hex_speed_value_get $speed)
+			speed_to_advertise=$(($speed_to_advertise | \
+						$speed))
+		fi
+
+	done
+
+	# Convert to hex.
+	printf "%#x" "$speed_to_advertise"
+}
+
+advertise_subset_of_speeds()
+{
+	# Test that when one device advertises a subset of speeds and another
+	# advertises a specific speed (but all modes of this speed), the links
+	# are up and ping passes.
+	RET=0
+
+	local speed_1_to_advertise=$(subset_of_common_speeds_get $h1 $h2 1)
+	ethtool_set $h1 advertise $speed_1_to_advertise
+
+	if [ $RET != 0 ]; then
+		log_test "advertise subset of speeds"
+		return
+	fi
+
+	local -a speeds_arr_without_mode=($(common_speeds_get $h1 $h2 0 1))
+	# Check only speeds that h1 advertised. Remove the first speed.
+	unset speeds_arr_without_mode[0]
+	local -a speeds_arr_with_mode=($(common_speeds_get $h1 $h2 1 1))
+
+	for speed_value in ${speeds_arr_without_mode[@]}; do
+		RET=0
+		local speed_2_to_advertise=$(speed_to_advertise_get $speed_value \
+			"${speeds_arr_with_mode[@]}")
+		ethtool_set $h2 advertise $speed_2_to_advertise
+
+		setup_wait_dev_with_timeout $h1
+		setup_wait_dev_with_timeout $h2
+		ping_do $h1 192.0.2.2
+		check_err $? "ping with h1=$speed_1_to_advertise, h2=$speed_2_to_advertise ($speed_value)"
+
+		log_test "advertise $speed_1_to_advertise vs. $speed_2_to_advertise"
+	done
+
+	ethtool -s $h2 autoneg on
+	ethtool -s $h1 autoneg on
+}
+
+check_highest_speed_is_chosen()
+{
+	# Test that when one device advertises a subset of speeds, the other
+	# chooses the highest speed. This test checks configuration without
+	# traffic.
+	RET=0
+
+	local max_speed
+	local chosen_speed
+	local speed_to_advertise=$(subset_of_common_speeds_get $h1 $h2 1)
+
+	ethtool_set $h1 advertise $speed_to_advertise
+
+	if [ $RET != 0 ]; then
+		log_test "check highest speed"
+		return
+	fi
+
+	local -a speeds_arr=($(common_speeds_get $h1 $h2 0 1))
+
+	max_speed=${speeds_arr[0]}
+	for current in ${speeds_arr[@]}; do
+		if [[ $current -gt $max_speed ]]; then
+			max_speed=$current
+		fi
+	done
+
+	setup_wait_dev_with_timeout $h1
+	setup_wait_dev_with_timeout $h2
+	chosen_speed=$(ethtool $h1 | grep 'Speed:')
+	chosen_speed=${chosen_speed%"Mb/s"*}
+	chosen_speed=${chosen_speed#*"Speed: "}
+	((chosen_speed == max_speed))
+	check_err $? "h1 advertise $speed_to_advertise, h2 sync to speed $chosen_speed"
+
+	log_test "check highest speed"
+
+	ethtool -s $h2 autoneg on
+	ethtool -s $h1 autoneg on
+}
+
+different_speeds_autoneg_on()
+{
+	# Test that when we configure links to advertise different speeds,
+	# links are not up and ping fails.
+	RET=0
+
+	local -a speeds=($(different_speeds_get $h1 $h2 1 1))
+	local speed1=${speeds[0]}
+	local speed2=${speeds[1]}
+
+	speed1=$(hex_speed_value_get $speed1)
+	speed2=$(hex_speed_value_get $speed2)
+
+	ethtool_set $h1 advertise $speed1
+	ethtool_set $h2 advertise $speed2
+
+	if (($RET)); then
+		setup_wait_dev_with_timeout $h1
+		setup_wait_dev_with_timeout $h2
+		ping_do $h1 192.0.2.2
+		check_fail $? "ping with different speeds autoneg on"
+	fi
+
+	log_test "advertise different speeds autoneg on"
+
+	ethtool -s $h2 autoneg on
+	ethtool -s $h1 autoneg on
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+declare -gA speed_values
+eval "speed_values=($(speeds_arr_get))"
+
+tests_run
+
+exit $EXIT_STATUS

linux-7.2.3/tools/testing/selftests/drivers/net/hw/ethtool_extended_state.sh

@@ -0,0 +1,116 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	autoneg
+	autoneg_force_mode
+	no_cable
+"
+
+NUM_NETIFS=2
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+source ethtool_lib.sh
+
+TIMEOUT=$((WAIT_TIMEOUT * 1000)) # ms
+
+setup_prepare()
+{
+	swp1=${NETIFS[p1]}
+	swp2=${NETIFS[p2]}
+	swp3=$NETIF_NO_CABLE
+}
+
+ethtool_ext_state()
+{
+	local dev=$1; shift
+	local expected_ext_state=$1; shift
+	local expected_ext_substate=${1:-""}; shift
+
+	local ext_state=$(ethtool $dev | grep "Link detected" \
+		| cut -d "(" -f2 | cut -d ")" -f1)
+	local ext_substate=$(echo $ext_state | cut -sd "," -f2 \
+		| sed -e 's/^[[:space:]]*//')
+	ext_state=$(echo $ext_state | cut -d "," -f1)
+
+	if [[ $ext_state != $expected_ext_state ]]; then
+		echo "Expected \"$expected_ext_state\", got \"$ext_state\""
+		return 1
+	fi
+	if [[ $ext_substate != $expected_ext_substate ]]; then
+		echo "Expected \"$expected_ext_substate\", got \"$ext_substate\""
+		return 1
+	fi
+}
+
+autoneg()
+{
+	local msg
+
+	RET=0
+
+	ip link set dev $swp1 up
+
+	msg=$(busywait $TIMEOUT ethtool_ext_state $swp1 \
+			"Autoneg" "No partner detected")
+	check_err $? "$msg"
+
+	log_test "Autoneg, No partner detected"
+
+	ip link set dev $swp1 down
+}
+
+autoneg_force_mode()
+{
+	local msg
+
+	RET=0
+
+	ip link set dev $swp1 up
+	ip link set dev $swp2 up
+
+	local -a speeds_arr=($(different_speeds_get $swp1 $swp2 0 0))
+	local speed1=${speeds_arr[0]}
+	local speed2=${speeds_arr[1]}
+
+	ethtool_set $swp1 speed $speed1 autoneg off
+	ethtool_set $swp2 speed $speed2 autoneg off
+
+	msg=$(busywait $TIMEOUT ethtool_ext_state $swp1 \
+			"Autoneg" "No partner detected during force mode")
+	check_err $? "$msg"
+
+	msg=$(busywait $TIMEOUT ethtool_ext_state $swp2 \
+			"Autoneg" "No partner detected during force mode")
+	check_err $? "$msg"
+
+	log_test "Autoneg, No partner detected during force mode"
+
+	ethtool -s $swp2 autoneg on
+	ethtool -s $swp1 autoneg on
+
+	ip link set dev $swp2 down
+	ip link set dev $swp1 down
+}
+
+no_cable()
+{
+	local msg
+
+	RET=0
+
+	ip link set dev $swp3 up
+
+	msg=$(busywait $TIMEOUT ethtool_ext_state $swp3 "No cable")
+	check_err $? "$msg"
+
+	log_test "No cable"
+
+	ip link set dev $swp3 down
+}
+
+setup_prepare
+
+tests_run
+
+exit $EXIT_STATUS

linux-7.2.3/tools/testing/selftests/drivers/net/hw/ethtool_lib.sh

@@ -0,0 +1,120 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+speeds_arr_get()
+{
+	cmd='/ETHTOOL_LINK_MODE_[^[:space:]]*_BIT[[:space:]]+=[[:space:]]+/ \
+		{sub(/,$/, "") \
+		sub(/ETHTOOL_LINK_MODE_/,"") \
+		sub(/_BIT/,"") \
+		sub(/_Full/,"/Full") \
+		sub(/_Half/,"/Half");\
+		print "["$1"]="$3}'
+
+	awk "${cmd}" /usr/include/linux/ethtool.h
+}
+
+ethtool_set()
+{
+	local cmd="$@"
+	local out=$(ethtool -s $cmd 2>&1 | wc -l)
+
+	check_err $out "error in configuration. $cmd"
+}
+
+dev_linkmodes_params_get()
+{
+	local dev=$1; shift
+	local adver=$1; shift
+	local -a linkmodes_params
+	local param_count
+	local arr
+
+	if (($adver)); then
+		mode="Advertised link modes"
+	else
+		mode="Supported link modes"
+	fi
+
+	local -a dev_linkmodes=($(dev_speeds_get $dev 1 $adver))
+	for ((i=0; i<${#dev_linkmodes[@]}; i++)); do
+		linkmodes_params[$i]=$(echo -e "${dev_linkmodes[$i]}" | \
+			# Replaces all non numbers with spaces
+			sed -e 's/[^0-9]/ /g' | \
+			# Squeeze spaces in sequence to 1 space
+			tr -s ' ')
+		# Count how many numbers were found in the linkmode
+		param_count=$(echo "${linkmodes_params[$i]}" | wc -w)
+		if [[ $param_count -eq 1 ]]; then
+			linkmodes_params[$i]="${linkmodes_params[$i]} 1"
+		elif [[ $param_count -ge 3 ]]; then
+			arr=(${linkmodes_params[$i]})
+			# Take only first two params
+			linkmodes_params[$i]=$(echo "${arr[@]:0:2}")
+		fi
+	done
+	echo ${linkmodes_params[@]}
+}
+
+dev_speeds_get()
+{
+	local dev=$1; shift
+	local with_mode=$1; shift
+	local adver=$1; shift
+	local speeds_str
+
+	if (($adver)); then
+		mode="Advertised link modes"
+	else
+		mode="Supported link modes"
+	fi
+
+	speeds_str=$(ethtool "$dev" | \
+		# Snip everything before the link modes section.
+		sed -n '/'"$mode"':/,$p' | \
+		# Quit processing the rest at the start of the next section.
+		# When checking, skip the header of this section (hence the 2,).
+		sed -n '2,${/^[\t][^ \t]/q};p' | \
+		# Drop the section header of the current section.
+		cut -d':' -f2)
+
+	local -a speeds_arr=($speeds_str)
+	if [[ $with_mode -eq 0 ]]; then
+		for ((i=0; i<${#speeds_arr[@]}; i++)); do
+			speeds_arr[$i]=${speeds_arr[$i]%base*}
+		done
+	fi
+	echo ${speeds_arr[@]}
+}
+
+common_speeds_get()
+{
+	dev1=$1; shift
+	dev2=$1; shift
+	with_mode=$1; shift
+	adver=$1; shift
+
+	local -a dev1_speeds=($(dev_speeds_get $dev1 $with_mode $adver))
+	local -a dev2_speeds=($(dev_speeds_get $dev2 $with_mode $adver))
+
+	comm -12 \
+		<(printf '%s\n' "${dev1_speeds[@]}" | sort -u) \
+		<(printf '%s\n' "${dev2_speeds[@]}" | sort -u)
+}
+
+different_speeds_get()
+{
+	local dev1=$1; shift
+	local dev2=$1; shift
+	local with_mode=$1; shift
+	local adver=$1; shift
+
+	local -a speeds_arr
+
+	speeds_arr=($(common_speeds_get $dev1 $dev2 $with_mode $adver))
+	if [[ ${#speeds_arr[@]} < 2 ]]; then
+		check_err 1 "cannot check different speeds. There are not enough speeds"
+	fi
+
+	echo ${speeds_arr[0]} ${speeds_arr[1]}
+}

linux-7.2.3/tools/testing/selftests/drivers/net/hw/ethtool_mm.sh

@@ -0,0 +1,341 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	manual_with_verification_h1_to_h2
+	manual_with_verification_h2_to_h1
+	manual_without_verification_h1_to_h2
+	manual_without_verification_h2_to_h1
+	manual_failed_verification_h1_to_h2
+	manual_failed_verification_h2_to_h1
+	lldp
+"
+
+NUM_NETIFS=2
+REQUIRE_MZ=no
+PREEMPTIBLE_PRIO=0
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+
+traffic_test()
+{
+	local if=$1; shift
+	local src=$1; shift
+	local num_pkts=10000
+	local before=
+	local after=
+	local delta=
+
+	if [ ${has_pmac_stats[$if]} = false ]; then
+		src="aggregate"
+	fi
+
+	before=$(ethtool_std_stats_get $if "eth-mac" "FramesTransmittedOK" $src)
+
+	$MZ $if -q -c $num_pkts -p 64 -b bcast -t ip -R $PREEMPTIBLE_PRIO
+
+	after=$(ethtool_std_stats_get $if "eth-mac" "FramesTransmittedOK" $src)
+
+	delta=$((after - before))
+
+	# Allow an extra 1% tolerance for random packets sent by the stack
+	[ $delta -ge $num_pkts ] && [ $delta -le $((num_pkts + 100)) ]
+}
+
+manual_with_verification()
+{
+	local tx=$1; shift
+	local rx=$1; shift
+
+	RET=0
+
+	# It isn't completely clear from IEEE 802.3-2018 Figure 99-5: Transmit
+	# Processing state diagram whether the "send_r" variable (send response
+	# to verification frame) should be taken into consideration while the
+	# MAC Merge TX direction is disabled. That being said, at least the
+	# NXP ENETC does not, and requires tx-enabled on in order to respond to
+	# the link partner's verification frames.
+	ethtool --set-mm $rx tx-enabled on
+	ethtool --set-mm $tx verify-enabled on tx-enabled on
+
+	# Wait for verification to finish
+	sleep 1
+
+	ethtool --json --show-mm $tx | jq -r '.[]."verify-status"' | \
+		grep -q 'SUCCEEDED'
+	check_err "$?" "Verification did not succeed"
+
+	ethtool --json --show-mm $tx | jq -r '.[]."tx-active"' | grep -q 'true'
+	check_err "$?" "pMAC TX is not active"
+
+	traffic_test $tx "pmac"
+	check_err "$?" "Traffic did not get sent through $tx's pMAC"
+
+	ethtool --set-mm $tx verify-enabled off tx-enabled off
+	ethtool --set-mm $rx tx-enabled off
+
+	log_test "Manual configuration with verification: $tx to $rx"
+}
+
+manual_with_verification_h1_to_h2()
+{
+	manual_with_verification $h1 $h2
+}
+
+manual_with_verification_h2_to_h1()
+{
+	manual_with_verification $h2 $h1
+}
+
+manual_without_verification()
+{
+	local tx=$1; shift
+	local rx=$1; shift
+
+	RET=0
+
+	ethtool --set-mm $tx verify-enabled off tx-enabled on
+
+	ethtool --json --show-mm $tx | jq -r '.[]."verify-status"' | \
+		grep -q 'DISABLED'
+	check_err "$?" "Verification is not disabled"
+
+	ethtool --json --show-mm $tx | jq -r '.[]."tx-active"' | grep -q 'true'
+	check_err "$?" "pMAC TX is not active"
+
+	traffic_test $tx "pmac"
+	check_err "$?" "Traffic did not get sent through $tx's pMAC"
+
+	ethtool --set-mm $tx verify-enabled off tx-enabled off
+
+	log_test "Manual configuration without verification: $tx to $rx"
+}
+
+manual_without_verification_h1_to_h2()
+{
+	manual_without_verification $h1 $h2
+}
+
+manual_without_verification_h2_to_h1()
+{
+	manual_without_verification $h2 $h1
+}
+
+manual_failed_verification()
+{
+	local tx=$1; shift
+	local rx=$1; shift
+
+	RET=0
+
+	ethtool --set-mm $rx pmac-enabled off
+	ethtool --set-mm $tx verify-enabled on tx-enabled on
+
+	# Wait for verification to time out
+	sleep 1
+
+	ethtool --json --show-mm $tx | jq -r '.[]."verify-status"' | \
+		grep -q 'SUCCEEDED'
+	check_fail "$?" "Verification succeeded when it shouldn't have"
+
+	ethtool --json --show-mm $tx | jq -r '.[]."tx-active"' | grep -q 'true'
+	check_fail "$?" "pMAC TX is active when it shouldn't have"
+
+	traffic_test $tx "emac"
+	check_err "$?" "Traffic did not get sent through $tx's eMAC"
+
+	ethtool --set-mm $tx verify-enabled off tx-enabled off
+	ethtool --set-mm $rx pmac-enabled on
+
+	log_test "Manual configuration with failed verification: $tx to $rx"
+}
+
+manual_failed_verification_h1_to_h2()
+{
+	manual_failed_verification $h1 $h2
+}
+
+manual_failed_verification_h2_to_h1()
+{
+	manual_failed_verification $h2 $h1
+}
+
+smallest_supported_add_frag_size()
+{
+	local iface=$1
+	local rx_min_frag_size=
+
+	rx_min_frag_size=$(ethtool --json --show-mm $iface | \
+		jq '.[]."rx-min-frag-size"')
+
+	if [ $rx_min_frag_size -le 60 ]; then
+		echo 0
+	elif [ $rx_min_frag_size -le 124 ]; then
+		echo 1
+	elif [ $rx_min_frag_size -le 188 ]; then
+		echo 2
+	elif [ $rx_min_frag_size -le 252 ]; then
+		echo 3
+	else
+		echo "$iface: RX min frag size $rx_min_frag_size cannot be advertised over LLDP"
+		exit 1
+	fi
+}
+
+expected_add_frag_size()
+{
+	local iface=$1
+	local requested=$2
+	local min=$(smallest_supported_add_frag_size $iface)
+
+	[ $requested -le $min ] && echo $min || echo $requested
+}
+
+lldp_change_add_frag_size()
+{
+	local add_frag_size=$1
+	local pattern=
+
+	lldptool -T -i $h1 -V addEthCaps addFragSize=$add_frag_size >/dev/null
+	# Wait for TLVs to be received
+	sleep 2
+	pattern=$(printf "Additional fragment size: %d" \
+			 $(expected_add_frag_size $h1 $add_frag_size))
+	lldptool -i $h2 -t -n -V addEthCaps | grep -q "$pattern"
+}
+
+lldp()
+{
+	RET=0
+
+	systemctl start lldpad
+
+	# Configure the interfaces to receive and transmit LLDPDUs
+	lldptool -L -i $h1 adminStatus=rxtx >/dev/null
+	lldptool -L -i $h2 adminStatus=rxtx >/dev/null
+
+	# Enable the transmission of Additional Ethernet Capabilities TLV
+	lldptool -T -i $h1 -V addEthCaps enableTx=yes >/dev/null
+	lldptool -T -i $h2 -V addEthCaps enableTx=yes >/dev/null
+
+	# Wait for TLVs to be received
+	sleep 2
+
+	lldptool -i $h1 -t -n -V addEthCaps | \
+		grep -q "Preemption capability active"
+	check_err "$?" "$h1 pMAC TX is not active"
+
+	lldptool -i $h2 -t -n -V addEthCaps | \
+		grep -q "Preemption capability active"
+	check_err "$?" "$h2 pMAC TX is not active"
+
+	lldp_change_add_frag_size 3
+	check_err "$?" "addFragSize 3"
+
+	lldp_change_add_frag_size 2
+	check_err "$?" "addFragSize 2"
+
+	lldp_change_add_frag_size 1
+	check_err "$?" "addFragSize 1"
+
+	lldp_change_add_frag_size 0
+	check_err "$?" "addFragSize 0"
+
+	traffic_test $h1 "pmac"
+	check_err "$?" "Traffic did not get sent through $h1's pMAC"
+
+	traffic_test $h2 "pmac"
+	check_err "$?" "Traffic did not get sent through $h2's pMAC"
+
+	systemctl stop lldpad
+
+	log_test "LLDP"
+}
+
+h1_create()
+{
+	ip link set dev $h1 up
+
+	tc qdisc add dev $h1 root mqprio num_tc 4 map 0 1 2 3 \
+		queues 1@0 1@1 1@2 1@3 \
+		fp P E E E \
+		hw 1
+
+	ethtool --set-mm $h1 pmac-enabled on tx-enabled off verify-enabled off
+}
+
+h2_create()
+{
+	ip link set dev $h2 up
+
+	ethtool --set-mm $h2 pmac-enabled on tx-enabled off verify-enabled off
+
+	tc qdisc add dev $h2 root mqprio num_tc 4 map 0 1 2 3 \
+		queues 1@0 1@1 1@2 1@3 \
+		fp P E E E \
+		hw 1
+}
+
+h1_destroy()
+{
+	ethtool --set-mm $h1 pmac-enabled off tx-enabled off verify-enabled off
+
+	tc qdisc del dev $h1 root
+
+	ip link set dev $h1 down
+}
+
+h2_destroy()
+{
+	tc qdisc del dev $h2 root
+
+	ethtool --set-mm $h2 pmac-enabled off tx-enabled off verify-enabled off
+
+	ip link set dev $h2 down
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	h2=${NETIFS[p2]}
+
+	h1_create
+	h2_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	h2_destroy
+	h1_destroy
+}
+
+check_ethtool_mm_support
+check_tc_fp_support
+require_command lldptool
+bail_on_lldpad "autoconfigure the MAC Merge layer" "configure it manually"
+
+for netif in ${NETIFS[@]}; do
+	ethtool --show-mm $netif 2>&1 &> /dev/null
+	if [[ $? -ne 0 ]]; then
+		echo "SKIP: $netif does not support MAC Merge"
+		exit $ksft_skip
+	fi
+
+	if check_ethtool_pmac_std_stats_support $netif eth-mac; then
+		has_pmac_stats[$netif]=true
+	else
+		has_pmac_stats[$netif]=false
+		echo "$netif does not report pMAC statistics, falling back to aggregate"
+	fi
+done
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS

linux-7.2.3/tools/testing/selftests/drivers/net/hw/ethtool_rmon.sh

@@ -0,0 +1,159 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#shellcheck disable=SC2034 # SC does not see the global variables
+#shellcheck disable=SC2317,SC2329 # unused functions
+
+ALL_TESTS="
+	rmon_rx_histogram
+	rmon_tx_histogram
+"
+
+: "${DRIVER_TEST_CONFORMANT:=yes}"
+NUM_NETIFS=2
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+source "$lib_dir"/../../../kselftest/ktap_helpers.sh
+
+UINT32_MAX=$((2**32 - 1))
+ETH_FCS_LEN=4
+ETH_HLEN=$((6+6+2))
+TEST_NAME=$(basename "$0" .sh)
+
+declare -A netif_mtu
+
+ensure_mtu()
+{
+	local iface=$1; shift
+	local len=$1; shift
+	local required=$((len - ETH_HLEN - ETH_FCS_LEN))
+	local current
+
+	current=$(run_on "$iface" \
+		ip -j link show dev "$iface" | jq -r '.[0].mtu')
+	if [ "$current" -lt "$required" ]; then
+		run_on "$iface" ip link set dev "$iface" mtu "$required" \
+			|| return 1
+	fi
+}
+
+bucket_test()
+{
+	local iface=$1; shift
+	local neigh=$1; shift
+	local set=$1; shift
+	local bucket=$1; shift
+	local len=$1; shift
+	local num_rx=10000
+	local num_tx=20000
+	local expected=
+	local before=
+	local after=
+	local delta=
+
+	# Mausezahn does not include FCS bytes in its length - but the
+	# histogram counters do
+	len=$((len - ETH_FCS_LEN))
+	len=$((len > 0 ? len : 0))
+
+	before=$(run_on "$iface" ethtool --json -S "$iface" --groups rmon | \
+		jq -r ".[0].rmon[\"${set}-pktsNtoM\"][$bucket].val")
+
+	# Send 10k one way and 20k in the other, to detect counters
+	# mapped to the wrong direction
+	run_on "$neigh" \
+		"$MZ" "$neigh" -q -c "$num_rx" -p "$len" -a own -b bcast -d 10us
+	run_on "$iface" \
+		"$MZ" "$iface" -q -c "$num_tx" -p "$len" -a own -b bcast -d 10us
+
+	after=$(run_on "$iface" ethtool --json -S "$iface" --groups rmon | \
+		jq -r ".[0].rmon[\"${set}-pktsNtoM\"][$bucket].val")
+
+	delta=$((after - before))
+
+	expected=$([ "$set" = rx ] && echo "$num_rx" || echo "$num_tx")
+
+	[ "$delta" -ge "$expected" ] && [ "$delta" -le "$UINT32_MAX" ]
+}
+
+rmon_histogram()
+{
+	local iface=$1; shift
+	local neigh=$1; shift
+	local set=$1; shift
+	local nbuckets=0
+	local step=
+
+	while read -r -a bucket; do
+		step="$set-pkts${bucket[0]}to${bucket[1]}"
+
+		for if in "$iface" "$neigh"; do
+			if ! ensure_mtu "$if" "${bucket[0]}"; then
+				ktap_print_msg "$if does not support the required MTU for $step"
+				ktap_test_xfail "$TEST_NAME.$step"
+				return
+			fi
+		done
+
+		if ! bucket_test "$iface" "$neigh" "$set" "$nbuckets" "${bucket[0]}"; then
+			ktap_test_fail "$TEST_NAME.$step"
+			return 1
+		fi
+		ktap_test_pass "$TEST_NAME.$step"
+		nbuckets=$((nbuckets + 1))
+	done < <(run_on "$iface" ethtool --json -S "$iface" --groups rmon | \
+		jq -r ".[0].rmon[\"${set}-pktsNtoM\"][]|[.low, .high]|@tsv" 2>/dev/null)
+
+	if [ "$nbuckets" -eq 0 ]; then
+		ktap_print_msg "$iface does not support $set histogram counters"
+		return
+	fi
+}
+
+rmon_rx_histogram()
+{
+	rmon_histogram "$h1" "$h2" rx
+}
+
+rmon_tx_histogram()
+{
+	rmon_histogram "$h1" "$h2" tx
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	h2=${NETIFS[p2]}
+
+	for iface in "$h1" "$h2"; do
+		netif_mtu["$iface"]=$(run_on "$iface" \
+			ip -j link show dev "$iface" | jq -r '.[0].mtu')
+	done
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	# Do not bring down the interfaces, just configure the initial MTU
+	for iface in "$h2" "$h1"; do
+		run_on "$iface" ip link set dev "$iface" \
+			mtu "${netif_mtu[$iface]}"
+	done
+}
+
+check_ethtool_counter_group_support
+trap cleanup EXIT
+
+bucket_count=$(ethtool --json -S "${NETIFS[p1]}" --groups rmon | \
+	jq -r '.[0].rmon |
+		"\((."rx-pktsNtoM" | length) +
+		   (."tx-pktsNtoM" | length))"')
+ktap_print_header
+ktap_set_plan "$bucket_count"
+
+setup_prepare
+setup_wait
+
+tests_run
+
+ktap_finished

linux-7.2.3/tools/testing/selftests/drivers/net/hw/ethtool_std_stats.sh

@@ -0,0 +1,206 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#shellcheck disable=SC2034 # SC does not see the global variables
+#shellcheck disable=SC2317,SC2329 # unused functions
+
+ALL_TESTS="
+	test_eth_ctrl_stats
+	test_eth_mac_stats
+	test_pause_stats
+"
+: "${DRIVER_TEST_CONFORMANT:=yes}"
+STABLE_MAC_ADDRS=yes
+NUM_NETIFS=2
+lib_dir=$(dirname "$0")
+# shellcheck source=./../../../net/forwarding/lib.sh
+source "$lib_dir"/../../../net/forwarding/lib.sh
+# shellcheck source=./../../../kselftest/ktap_helpers.sh
+source "$lib_dir"/../../../kselftest/ktap_helpers.sh
+
+UINT32_MAX=$((2**32 - 1))
+SUBTESTS=0
+TEST_NAME=$(basename "$0" .sh)
+
+traffic_test()
+{
+	local iface=$1; shift
+	local neigh=$1; shift
+	local num_tx=$1; shift
+	local pkt_format="$1"; shift
+	local -a counters=("$@")
+	local int grp cnt target exact_check
+	local before after delta
+	local num_rx=$((num_tx * 2))
+	local xfail_message
+	local src="aggregate"
+	local i
+
+	for i in "${!counters[@]}"; do
+		read -r int grp cnt target exact_check xfail_message \
+			<<< "${counters[$i]}"
+
+		before[i]=$(ethtool_std_stats_get "$int" "$grp" "$cnt" "$src")
+	done
+
+	# shellcheck disable=SC2086 # needs split options
+	run_on "$iface" "$MZ" "$iface" -q -c "$num_tx" $pkt_format
+
+	# shellcheck disable=SC2086 # needs split options
+	run_on "$neigh" "$MZ" "$neigh" -q -c "$num_rx" $pkt_format
+
+	for i in "${!counters[@]}"; do
+		read -r int grp cnt target exact_check xfail_message \
+			<<< "${counters[$i]}"
+
+		after[i]=$(ethtool_std_stats_get "$int" "$grp" "$cnt" "$src")
+		if [[ "${after[$i]}" == "null" ]]; then
+			ktap_test_skip "$TEST_NAME.$grp-$cnt"
+			continue;
+		fi
+
+		delta=$((after[i] - before[i]))
+
+		if [ "$exact_check" -ne 0 ]; then
+			[ "$delta" -eq "$target" ]
+		else
+			[ "$delta" -ge "$target" ] && \
+			[ "$delta" -le "$UINT32_MAX" ]
+		fi
+		err="$?"
+
+		if [[ $err != 0  ]] && [[ -n $xfail_message ]]; then
+			ktap_print_msg "$xfail_message"
+			ktap_test_xfail "$TEST_NAME.$grp-$cnt"
+			continue;
+		fi
+
+		if [[ $err != 0 ]]; then
+			ktap_print_msg "$grp-$cnt is not valid on $int (expected $target, got $delta)"
+			ktap_test_fail "$TEST_NAME.$grp-$cnt"
+		else
+			ktap_test_pass "$TEST_NAME.$grp-$cnt"
+		fi
+	done
+}
+
+test_eth_ctrl_stats()
+{
+	local pkt_format="-a own -b bcast 88:08 -p 64"
+	local num_pkts=1000
+	local -a counters
+
+	counters=("$h1 eth-ctrl MACControlFramesTransmitted $num_pkts 0")
+	traffic_test "$h1" "$h2" "$num_pkts" "$pkt_format" \
+		"${counters[@]}"
+
+	counters=("$h1 eth-ctrl MACControlFramesReceived $num_pkts 0")
+	traffic_test "$h2" "$h1" "$num_pkts" "$pkt_format" \
+		"${counters[@]}"
+}
+SUBTESTS=$((SUBTESTS + 2))
+
+test_eth_mac_stats()
+{
+	local pkt_size=100
+	local pkt_size_fcs=$((pkt_size + 4))
+	local bcast_pkt_format="-a own -b bcast -p $pkt_size"
+	local mcast_pkt_format="-a own -b 01:00:5E:00:00:01 -p $pkt_size"
+	local num_pkts=2000
+	local octets=$((pkt_size_fcs * num_pkts))
+	local -a counters error_cnt collision_cnt
+
+	# Error counters should be exactly zero
+	counters=("$h1 eth-mac FrameCheckSequenceErrors 0 1"
+		  "$h1 eth-mac AlignmentErrors 0 1"
+		  "$h1 eth-mac FramesLostDueToIntMACXmitError 0 1"
+		  "$h1 eth-mac CarrierSenseErrors 0 1"
+		  "$h1 eth-mac FramesLostDueToIntMACRcvError 0 1"
+		  "$h1 eth-mac InRangeLengthErrors 0 1"
+		  "$h1 eth-mac OutOfRangeLengthField 0 1"
+		  "$h1 eth-mac FrameTooLongErrors 0 1"
+		  "$h1 eth-mac FramesAbortedDueToXSColls 0 1")
+	traffic_test "$h1" "$h2" "$num_pkts" "$bcast_pkt_format" \
+		"${counters[@]}"
+
+	# Collision related counters should also be zero
+	counters=("$h1 eth-mac SingleCollisionFrames 0 1"
+		  "$h1 eth-mac MultipleCollisionFrames 0 1"
+		  "$h1 eth-mac FramesWithDeferredXmissions 0 1"
+		  "$h1 eth-mac LateCollisions 0 1"
+		  "$h1 eth-mac FramesWithExcessiveDeferral 0 1")
+	traffic_test "$h1" "$h2" "$num_pkts" "$bcast_pkt_format" \
+		"${counters[@]}"
+
+	counters=("$h1 eth-mac BroadcastFramesXmittedOK $num_pkts 0"
+		  "$h1 eth-mac OctetsTransmittedOK $octets 0")
+	traffic_test "$h1" "$h2" "$num_pkts" "$bcast_pkt_format" \
+		"${counters[@]}"
+
+	counters=("$h1 eth-mac BroadcastFramesReceivedOK $num_pkts 0"
+		  "$h1 eth-mac OctetsReceivedOK $octets 0")
+	traffic_test "$h2" "$h1" "$num_pkts" "$bcast_pkt_format" \
+		"${counters[@]}"
+
+	counters=("$h1 eth-mac FramesTransmittedOK $num_pkts 0"
+		  "$h1 eth-mac MulticastFramesXmittedOK $num_pkts 0")
+	traffic_test "$h1" "$h2" "$num_pkts" "$mcast_pkt_format" \
+		"${counters[@]}"
+
+	counters=("$h1 eth-mac FramesReceivedOK $num_pkts 0"
+		  "$h1 eth-mac MulticastFramesReceivedOK $num_pkts 0")
+	traffic_test "$h2" "$h1" "$num_pkts" "$mcast_pkt_format" \
+		"${counters[@]}"
+}
+SUBTESTS=$((SUBTESTS + 22))
+
+test_pause_stats()
+{
+	local pkt_format="-a own -b 01:80:c2:00:00:01 88:08:00:01:00:01"
+	local xfail_message="software sent pause frames not detected"
+	local num_pkts=2000
+	local -a counters
+	local int
+	local i
+
+	# Check that there is pause frame support
+	for ((i = 1; i <= NUM_NETIFS; ++i)); do
+		int="${NETIFS[p$i]}"
+		if ! run_on "$int" ethtool -I --json -a "$int" > /dev/null 2>&1; then
+			ktap_test_skip "$TEST_NAME.tx_pause_frames"
+			ktap_test_skip "$TEST_NAME.rx_pause_frames"
+			return
+		fi
+	done
+
+	counters=("$h1 pause tx_pause_frames $num_pkts 0 $xfail_message")
+	traffic_test "$h1" "$h2" "$num_pkts" "$pkt_format" \
+		"${counters[@]}"
+
+	counters=("$h1 pause rx_pause_frames $num_pkts 0")
+	traffic_test "$h2" "$h1" "$num_pkts" "$pkt_format" \
+		"${counters[@]}"
+}
+SUBTESTS=$((SUBTESTS + 2))
+
+setup_prepare()
+{
+	local iface
+
+	h1=${NETIFS[p1]}
+	h2=${NETIFS[p2]}
+
+	h2_mac=$(mac_get "$h2")
+}
+
+ktap_print_header
+ktap_set_plan $SUBTESTS
+
+check_ethtool_counter_group_support
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+ktap_finished

linux-7.2.3/tools/testing/selftests/drivers/net/hw/gro_hw.py

@@ -0,0 +1,304 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+HW GRO tests focusing on device machinery like stats, rather than protocol
+processing.
+"""
+
+import glob
+import re
+
+from lib.py import ksft_run, ksft_exit, ksft_pr
+from lib.py import ksft_eq, ksft_ge, ksft_variants
+from lib.py import NetDrvEpEnv, NetdevFamily
+from lib.py import KsftSkipEx
+from lib.py import bkg, cmd, defer, ethtool, ip
+
+
+# gro.c uses hardcoded DPORT=8000
+GRO_DPORT = 8000
+
+
+def _get_queue_stats(cfg, queue_id):
+    """Get stats for a specific Rx queue."""
+    cfg.wait_hw_stats_settle()
+    data = cfg.netnl.qstats_get({"ifindex": cfg.ifindex, "scope": ["queue"]},
+                                dump=True)
+    for q in data:
+        if q.get('queue-type') == 'rx' and q.get('queue-id') == queue_id:
+            return q
+    return {}
+
+
+def _resolve_dmac(cfg, ipver):
+    """Find the destination MAC address for sending packets."""
+    attr = "dmac" + ipver
+    if hasattr(cfg, attr):
+        return getattr(cfg, attr)
+
+    route = ip(f"-{ipver} route get {cfg.addr_v[ipver]}",
+               json=True, host=cfg.remote)[0]
+    gw = route.get("gateway")
+    if not gw:
+        setattr(cfg, attr, cfg.dev['address'])
+        return getattr(cfg, attr)
+
+    cmd(f"ping -c1 -W0 -I{cfg.remote_ifname} {gw}", host=cfg.remote)
+    neigh = ip(f"neigh get {gw} dev {cfg.remote_ifname}",
+               json=True, host=cfg.remote)[0]
+    setattr(cfg, attr, neigh['lladdr'])
+    return getattr(cfg, attr)
+
+
+def _require_ntuple(cfg):
+    features = ethtool(f"-k {cfg.ifname}", json=True)[0]
+    if not features["ntuple-filters"]["active"]:
+        if features["ntuple-filters"]["fixed"]:
+            raise KsftSkipEx("Device does not support ntuple-filters")
+        ethtool(f"-K {cfg.ifname} ntuple-filters on")
+        defer(ethtool, f"-K {cfg.ifname} ntuple-filters off")
+
+
+def _setup_isolated_queue(cfg):
+    """Set up an isolated queue for testing using ntuple filter.
+
+    Remove queue 1 from the default RSS context and steer test traffic to it.
+    """
+    _require_ntuple(cfg)
+    test_queue = 1
+
+    qcnt = len(glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*"))
+    if qcnt < 2:
+        raise KsftSkipEx(f"Need at least 2 queues, have {qcnt}")
+
+    # Remove queue 1 from default RSS context by setting its weight to 0
+    weights = ["1"] * qcnt
+    weights[test_queue] = "0"
+    ethtool(f"-X {cfg.ifname} weight " + " ".join(weights))
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    # Set up ntuple filter to steer our test traffic to the isolated queue
+    flow  = f"flow-type tcp{cfg.addr_ipver} "
+    flow += f"dst-ip {cfg.addr} dst-port {GRO_DPORT} action {test_queue}"
+    output = ethtool(f"-N {cfg.ifname} {flow}").stdout
+    ntuple_id = int(output.split()[-1])
+    defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}")
+
+    return test_queue
+
+
+def _run_gro_test(cfg, test_name, num_flows=None, ignore_fail=False,
+                  order_check=False):
+    """Run gro binary with given test and return output."""
+    if not hasattr(cfg, "bin_remote"):
+        cfg.bin_local = cfg.net_lib_dir / "gro"
+        cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
+
+    ipver = cfg.addr_ipver
+    protocol = f"--ipv{ipver}"
+    dmac = _resolve_dmac(cfg, ipver)
+
+    base_args = [
+        protocol,
+        f"--dmac {dmac}",
+        f"--smac {cfg.remote_dev['address']}",
+        f"--daddr {cfg.addr}",
+        f"--saddr {cfg.remote_addr_v[ipver]}",
+        f"--test {test_name}",
+    ]
+    if num_flows:
+        base_args.append(f"--num-flows {num_flows}")
+    if order_check:
+        base_args.append("--order-check")
+
+    args = " ".join(base_args)
+
+    rx_cmd = f"{cfg.bin_local} {args} --rx --iface {cfg.ifname}"
+    tx_cmd = f"{cfg.bin_remote} {args} --iface {cfg.remote_ifname}"
+
+    with bkg(rx_cmd, ksft_ready=True, exit_wait=True, fail=False) as rx_proc:
+        cmd(tx_cmd, host=cfg.remote)
+
+    if not ignore_fail:
+        ksft_eq(rx_proc.ret, 0)
+        if rx_proc.ret != 0:
+            ksft_pr(rx_proc)
+
+    return rx_proc.stdout
+
+
+def _require_hw_gro_stats(cfg, queue_id):
+    """Check if device reports HW GRO stats for the queue."""
+    stats = _get_queue_stats(cfg, queue_id)
+    required = ['rx-packets', 'rx-hw-gro-packets', 'rx-hw-gro-wire-packets']
+    for stat in required:
+        if stat not in stats:
+            raise KsftSkipEx(f"Driver does not report '{stat}' via qstats")
+
+
+def _set_ethtool_feat(cfg, current, feats):
+    """Set ethtool features with defer to restore original state."""
+    s2n = {True: "on", False: "off"}
+
+    new = ["-K", cfg.ifname]
+    old = ["-K", cfg.ifname]
+    no_change = True
+    for name, state in feats.items():
+        new += [name, s2n[state]]
+        old += [name, s2n[current[name]["active"]]]
+
+        if current[name]["active"] != state:
+            no_change = False
+            if current[name]["fixed"]:
+                raise KsftSkipEx(f"Device does not support {name}")
+    if no_change:
+        return
+
+    eth_cmd = ethtool(" ".join(new))
+    defer(ethtool, " ".join(old))
+
+    # If ethtool printed something kernel must have modified some features
+    if eth_cmd.stdout:
+        ksft_pr(eth_cmd)
+
+
+def _setup_hw_gro(cfg):
+    """Enable HW GRO on the device, disabling SW GRO."""
+    feat = ethtool(f"-k {cfg.ifname}", json=True)[0]
+
+    # Try to disable SW GRO and enable HW GRO
+    _set_ethtool_feat(cfg, feat,
+                      {"generic-receive-offload": False,
+                       "rx-gro-hw": True,
+                       "large-receive-offload": False})
+
+    # Some NICs treat HW GRO as a GRO sub-feature so disabling GRO
+    # will also clear HW GRO. Use a hack of installing XDP generic
+    # to skip SW GRO, even when enabled.
+    feat = ethtool(f"-k {cfg.ifname}", json=True)[0]
+    if not feat["rx-gro-hw"]["active"]:
+        ksft_pr("Driver clears HW GRO when SW GRO is cleared, using generic XDP workaround")
+        prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
+        ip(f"link set dev {cfg.ifname} xdpgeneric obj {prog} sec xdp")
+        defer(ip, f"link set dev {cfg.ifname} xdpgeneric off")
+
+        # Attaching XDP may change features, fetch the latest state
+        feat = ethtool(f"-k {cfg.ifname}", json=True)[0]
+
+        _set_ethtool_feat(cfg, feat,
+                          {"generic-receive-offload": True,
+                           "rx-gro-hw": True,
+                           "large-receive-offload": False})
+
+
+def _check_gro_stats(cfg, test_queue, stats_before,
+                     expect_rx, expect_gro, expect_wire):
+    """Validate GRO stats against expected values."""
+    stats_after = _get_queue_stats(cfg, test_queue)
+
+    rx_delta = (stats_after.get('rx-packets', 0) -
+                stats_before.get('rx-packets', 0))
+    gro_delta = (stats_after.get('rx-hw-gro-packets', 0) -
+                 stats_before.get('rx-hw-gro-packets', 0))
+    wire_delta = (stats_after.get('rx-hw-gro-wire-packets', 0) -
+                  stats_before.get('rx-hw-gro-wire-packets', 0))
+
+    ksft_eq(rx_delta, expect_rx, comment="rx-packets")
+    ksft_eq(gro_delta, expect_gro, comment="rx-hw-gro-packets")
+    ksft_eq(wire_delta, expect_wire, comment="rx-hw-gro-wire-packets")
+
+
+def test_gro_stats_single(cfg):
+    """
+    Test that a single packet doesn't affect GRO stats.
+
+    Send a single packet that cannot be coalesced (nothing to coalesce with).
+    GRO stats should not increase since no coalescing occurred.
+    rx-packets should increase by 2 (1 data + 1 FIN).
+    """
+    _setup_hw_gro(cfg)
+
+    test_queue = _setup_isolated_queue(cfg)
+    _require_hw_gro_stats(cfg, test_queue)
+
+    stats_before = _get_queue_stats(cfg, test_queue)
+
+    _run_gro_test(cfg, "single")
+
+    # 1 data + 1 FIN = 2 rx-packets, no coalescing
+    _check_gro_stats(cfg, test_queue, stats_before,
+                     expect_rx=2, expect_gro=0, expect_wire=0)
+
+
+def test_gro_stats_full(cfg):
+    """
+    Test GRO stats when overwhelming HW GRO capacity.
+
+    Send 500 flows to exceed HW GRO flow capacity on a single queue.
+    This should result in some packets not being coalesced.
+    Validate that qstats match what gro.c observed.
+    """
+    _setup_hw_gro(cfg)
+
+    test_queue = _setup_isolated_queue(cfg)
+    _require_hw_gro_stats(cfg, test_queue)
+
+    num_flows = 500
+    stats_before = _get_queue_stats(cfg, test_queue)
+
+    # Run capacity test - will likely fail because not all packets coalesce
+    output = _run_gro_test(cfg, "capacity", num_flows=num_flows,
+                           ignore_fail=True)
+
+    # Parse gro.c output: "STATS: received=X wire=Y coalesced=Z"
+    match = re.search(r'STATS: received=(\d+) wire=(\d+) coalesced=(\d+)',
+                      output)
+    if not match:
+        raise KsftSkipEx(f"Could not parse gro.c output: {output}")
+
+    rx_frames = int(match.group(2))
+    gro_coalesced = int(match.group(3))
+
+    ksft_ge(gro_coalesced, 1,
+            comment="At least some packets should coalesce")
+
+    # received + 1 FIN, coalesced super-packets, coalesced * 2 wire packets
+    _check_gro_stats(cfg, test_queue, stats_before,
+                     expect_rx=rx_frames + 1,
+                     expect_gro=gro_coalesced,
+                     expect_wire=gro_coalesced * 2)
+
+
+@ksft_variants([4, 32, 512])
+def test_gro_order(cfg, num_flows):
+    """
+    Test that HW GRO preserves packet ordering between flows.
+
+    Packets may get delayed until the aggregate is released,
+    but reordering between aggregates and packet terminating
+    the aggregate and normal packets should not happen.
+
+    Note that this test is stricter than truly required.
+    Reordering packets between flows should not cause issues.
+    This test will also fail if traffic is run over an ECMP fabric.
+    """
+    _setup_hw_gro(cfg)
+    _setup_isolated_queue(cfg)
+
+    _run_gro_test(cfg, "capacity", num_flows=num_flows, order_check=True)
+
+
+def main() -> None:
+    """ Ksft boiler plate main """
+
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        cfg.netnl = NetdevFamily()
+        ksft_run([test_gro_stats_single,
+                  test_gro_stats_full,
+                  test_gro_order], args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/hw_stats_l3.sh

@@ -0,0 +1,334 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# +--------------------+                     +----------------------+
+# | H1                 |                     |                   H2 |
+# |                    |                     |                      |
+# |          $h1.200 + |                     | + $h2.200            |
+# |     192.0.2.1/28 | |                     | | 192.0.2.18/28      |
+# | 2001:db8:1::1/64 | |                     | | 2001:db8:2::1/64   |
+# |                  | |                     | |                    |
+# |              $h1 + |                     | + $h2                |
+# |                  | |                     | |                    |
+# +------------------|-+                     +-|--------------------+
+#                    |                         |
+# +------------------|-------------------------|--------------------+
+# | SW               |                         |                    |
+# |                  |                         |                    |
+# |             $rp1 +                         + $rp2               |
+# |                  |                         |                    |
+# |         $rp1.200 +                         + $rp2.200           |
+# |     192.0.2.2/28                             192.0.2.17/28      |
+# | 2001:db8:1::2/64                             2001:db8:2::2/64   |
+# |                                                                 |
+# +-----------------------------------------------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	test_stats_rx_ipv4
+	test_stats_tx_ipv4
+	test_stats_rx_ipv6
+	test_stats_tx_ipv6
+	respin_enablement
+	test_stats_rx_ipv4
+	test_stats_tx_ipv4
+	test_stats_rx_ipv6
+	test_stats_tx_ipv6
+	reapply_config
+	ping_ipv4
+	ping_ipv6
+	test_stats_rx_ipv4
+	test_stats_tx_ipv4
+	test_stats_rx_ipv6
+	test_stats_tx_ipv6
+	test_stats_report_rx
+	test_stats_report_tx
+	test_destroy_enabled
+	test_double_enable
+"
+NUM_NETIFS=4
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+source "$lib_dir"/../../../net/forwarding/tc_common.sh
+
+h1_create()
+{
+	simple_if_init $h1
+	vlan_create $h1 200 v$h1 192.0.2.1/28 2001:db8:1::1/64
+	ip route add 192.0.2.16/28 vrf v$h1 nexthop via 192.0.2.2
+	ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+	ip -6 route del 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2
+	ip route del 192.0.2.16/28 vrf v$h1 nexthop via 192.0.2.2
+	vlan_destroy $h1 200
+	simple_if_fini $h1
+}
+
+h2_create()
+{
+	simple_if_init $h2
+	vlan_create $h2 200 v$h2 192.0.2.18/28 2001:db8:2::1/64
+	ip route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.17
+	ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::2
+}
+
+h2_destroy()
+{
+	ip -6 route del 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::2
+	ip route del 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.17
+	vlan_destroy $h2 200
+	simple_if_fini $h2
+}
+
+router_rp1_200_create()
+{
+	ip link add name $rp1.200 link $rp1 type vlan id 200
+	ip link set dev $rp1.200 addrgenmode eui64
+	ip link set dev $rp1.200 up
+	ip address add dev $rp1.200 192.0.2.2/28
+	ip address add dev $rp1.200 2001:db8:1::2/64
+	ip stats set dev $rp1.200 l3_stats on
+}
+
+router_rp1_200_destroy()
+{
+	ip stats set dev $rp1.200 l3_stats off
+	ip address del dev $rp1.200 2001:db8:1::2/64
+	ip address del dev $rp1.200 192.0.2.2/28
+	ip link del dev $rp1.200
+}
+
+router_create()
+{
+	ip link set dev $rp1 up
+	router_rp1_200_create
+
+	ip link set dev $rp2 up
+	vlan_create $rp2 200 "" 192.0.2.17/28 2001:db8:2::2/64
+}
+
+router_destroy()
+{
+	vlan_destroy $rp2 200
+	ip link set dev $rp2 down
+
+	router_rp1_200_destroy
+	ip link set dev $rp1 down
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rp1=${NETIFS[p2]}
+
+	rp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	rp1mac=$(mac_get $rp1)
+	rp2mac=$(mac_get $rp2)
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1.200 192.0.2.18 " IPv4"
+}
+
+ping_ipv6()
+{
+	ping_test $h1.200 2001:db8:2::1 " IPv6"
+}
+
+send_packets_rx_ipv4()
+{
+	# Send 21 packets instead of 20, because the first one might trap and go
+	# through the SW datapath, which might not bump the HW counter.
+	$MZ $h1.200 -c 21 -d 20msec -p 100 \
+	    -a own -b $rp1mac -A 192.0.2.1 -B 192.0.2.18 \
+	    -q -t udp sp=54321,dp=12345
+}
+
+send_packets_rx_ipv6()
+{
+	$MZ $h1.200 -6 -c 21 -d 20msec -p 100 \
+	    -a own -b $rp1mac -A 2001:db8:1::1 -B 2001:db8:2::1 \
+	    -q -t udp sp=54321,dp=12345
+}
+
+send_packets_tx_ipv4()
+{
+	$MZ $h2.200 -c 21 -d 20msec -p 100 \
+	    -a own -b $rp2mac -A 192.0.2.18 -B 192.0.2.1 \
+	    -q -t udp sp=54321,dp=12345
+}
+
+send_packets_tx_ipv6()
+{
+	$MZ $h2.200 -6 -c 21 -d 20msec -p 100 \
+	    -a own -b $rp2mac -A 2001:db8:2::1 -B 2001:db8:1::1 \
+	    -q -t udp sp=54321,dp=12345
+}
+
+___test_stats()
+{
+	local dir=$1; shift
+	local prot=$1; shift
+
+	local a
+	local b
+
+	a=$(hw_stats_get l3_stats $rp1.200 ${dir} packets)
+	send_packets_${dir}_${prot}
+	"$@"
+	b=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= $a + 20" \
+		       hw_stats_get l3_stats $rp1.200 ${dir} packets)
+	check_err $? "Traffic not reflected in the counter: $a -> $b"
+}
+
+__test_stats()
+{
+	local dir=$1; shift
+	local prot=$1; shift
+
+	RET=0
+	___test_stats "$dir" "$prot"
+	log_test "Test $dir packets: $prot"
+}
+
+test_stats_rx_ipv4()
+{
+	__test_stats rx ipv4
+}
+
+test_stats_tx_ipv4()
+{
+	__test_stats tx ipv4
+}
+
+test_stats_rx_ipv6()
+{
+	__test_stats rx ipv6
+}
+
+test_stats_tx_ipv6()
+{
+	__test_stats tx ipv6
+}
+
+# Make sure everything works well even after stats have been disabled and
+# reenabled on the same device without touching the L3 configuration.
+respin_enablement()
+{
+	log_info "Turning stats off and on again"
+	ip stats set dev $rp1.200 l3_stats off
+	ip stats set dev $rp1.200 l3_stats on
+}
+
+# For the initial run, l3_stats is enabled on a completely set up netdevice. Now
+# do it the other way around: enabling the L3 stats on an L2 netdevice, and only
+# then apply the L3 configuration.
+reapply_config()
+{
+	log_info "Reapplying configuration"
+
+	router_rp1_200_destroy
+
+	ip link add name $rp1.200 link $rp1 type vlan id 200
+	ip link set dev $rp1.200 addrgenmode none
+	ip stats set dev $rp1.200 l3_stats on
+	ip link set dev $rp1.200 addrgenmode eui64
+	ip link set dev $rp1.200 up
+	ip address add dev $rp1.200 192.0.2.2/28
+	ip address add dev $rp1.200 2001:db8:1::2/64
+}
+
+__test_stats_report()
+{
+	local dir=$1; shift
+	local prot=$1; shift
+
+	local a
+	local b
+
+	RET=0
+
+	a=$(hw_stats_get l3_stats $rp1.200 ${dir} packets)
+	send_packets_${dir}_${prot}
+	ip address flush dev $rp1.200
+	b=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= $a + 20" \
+		       hw_stats_get l3_stats $rp1.200 ${dir} packets)
+	check_err $? "Traffic not reflected in the counter: $a -> $b"
+	log_test "Test ${dir} packets: stats pushed on loss of L3"
+
+	ip stats set dev $rp1.200 l3_stats off
+	ip link del dev $rp1.200
+	router_rp1_200_create
+}
+
+test_stats_report_rx()
+{
+	__test_stats_report rx ipv4
+}
+
+test_stats_report_tx()
+{
+	__test_stats_report tx ipv4
+}
+
+test_destroy_enabled()
+{
+	RET=0
+
+	ip link del dev $rp1.200
+	router_rp1_200_create
+
+	log_test "Destroy l3_stats-enabled netdev"
+}
+
+test_double_enable()
+{
+	RET=0
+	___test_stats rx ipv4 \
+		ip stats set dev $rp1.200 l3_stats on
+	log_test "Test stat retention across a spurious enablement"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+used=$(ip -j stats show dev $rp1.200 group offload subgroup hw_stats_info |
+	   jq '.[].info.l3_stats.used')
+[[ $used = true ]]
+check_err $? "hw_stats_info.used=$used"
+log_test "l3_stats offloaded"
+tests_run
+
+exit $EXIT_STATUS

linux-7.2.3/tools/testing/selftests/drivers/net/hw/hw_stats_l3_gre.sh

@@ -0,0 +1,111 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test L3 stats on IP-in-IP GRE tunnel without key.
+
+# This test uses flat topology for IP tunneling tests. See ipip_lib.sh for more
+# details.
+
+ALL_TESTS="
+	ping_ipv4
+	test_stats_rx
+	test_stats_tx
+"
+NUM_NETIFS=6
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/lib.sh
+source "$lib_dir"/../../../net/forwarding/ipip_lib.sh
+source "$lib_dir"/../../../net/forwarding/tc_common.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	ol1=${NETIFS[p2]}
+
+	ul1=${NETIFS[p3]}
+	ul2=${NETIFS[p4]}
+
+	ol2=${NETIFS[p5]}
+	h2=${NETIFS[p6]}
+
+	ol1mac=$(mac_get $ol1)
+
+	forwarding_enable
+	vrf_prepare
+	h1_create
+	h2_create
+	sw1_flat_create gre $ol1 $ul1
+	sw2_flat_create gre $ol2 $ul2
+	ip stats set dev g1a l3_stats on
+	ip stats set dev g2a l3_stats on
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip stats set dev g1a l3_stats off
+	ip stats set dev g2a l3_stats off
+
+	sw2_flat_destroy $ol2 $ul2
+	sw1_flat_destroy $ol1 $ul1
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+	forwarding_restore
+}
+
+ping_ipv4()
+{
+	RET=0
+
+	ping_test $h1 192.0.2.18 " gre flat"
+}
+
+send_packets_ipv4()
+{
+	# Send 21 packets instead of 20, because the first one might trap and go
+	# through the SW datapath, which might not bump the HW counter.
+	$MZ $h1 -c 21 -d 20msec -p 100 \
+	    -a own -b $ol1mac -A 192.0.2.1 -B 192.0.2.18 \
+	    -q -t udp sp=54321,dp=12345
+}
+
+test_stats()
+{
+	local dev=$1; shift
+	local dir=$1; shift
+
+	local a
+	local b
+
+	RET=0
+
+	a=$(hw_stats_get l3_stats $dev $dir packets)
+	send_packets_ipv4
+	b=$(busywait "$TC_HIT_TIMEOUT" until_counter_is ">= $a + 20" \
+		     hw_stats_get l3_stats $dev $dir packets)
+	check_err $? "Traffic not reflected in the counter: $a -> $b"
+
+	log_test "Test $dir packets: $prot"
+}
+
+test_stats_tx()
+{
+	test_stats g1a tx
+}
+
+test_stats_rx()
+{
+	test_stats g2a rx
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS

linux-7.2.3/tools/testing/selftests/drivers/net/hw/iou-zcrx.c

@@ -0,0 +1,512 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <assert.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <limits.h>
+#include <stdbool.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+#include <linux/mman.h>
+#include <linux/errqueue.h>
+#include <linux/if_packet.h>
+#include <linux/ipv6.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+#include <sys/epoll.h>
+#include <sys/ioctl.h>
+#include <sys/mman.h>
+#include <sys/resource.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <sys/un.h>
+#include <sys/wait.h>
+
+#include <liburing.h>
+
+#define SKIP_CODE	42
+
+struct t_io_uring_zcrx_ifq_reg {
+	__u32	if_idx;
+	__u32	if_rxq;
+	__u32	rq_entries;
+	__u32	flags;
+
+	__u64	area_ptr; /* pointer to struct io_uring_zcrx_area_reg */
+	__u64	region_ptr; /* struct io_uring_region_desc * */
+
+	struct io_uring_zcrx_offsets offsets;
+	__u32	zcrx_id;
+	__u32	rx_buf_len;
+	__u64	__resv[3];
+};
+
+static long page_size;
+#define AREA_SIZE (8192 * page_size)
+#define SEND_SIZE (512 * 4096)
+#define min(a, b) \
+	({ \
+		typeof(a) _a = (a); \
+		typeof(b) _b = (b); \
+		_a < _b ? _a : _b; \
+	})
+#define min_t(t, a, b) \
+	({ \
+		t _ta = (a); \
+		t _tb = (b); \
+		min(_ta, _tb); \
+	})
+
+#define ALIGN_UP(v, align) (((v) + (align) - 1) & ~((align) - 1))
+
+static int cfg_server;
+static int cfg_client;
+static int cfg_port = 8000;
+static int cfg_payload_len;
+static const char *cfg_ifname;
+static int cfg_queue_id = -1;
+static bool cfg_oneshot;
+static int cfg_oneshot_recvs;
+static int cfg_send_size = SEND_SIZE;
+static struct sockaddr_in6 cfg_addr;
+static unsigned int cfg_rx_buf_len;
+static bool cfg_dry_run;
+
+static char *payload;
+static void *area_ptr;
+static void *ring_ptr;
+static size_t ring_size;
+static struct io_uring_zcrx_rq rq_ring;
+static unsigned long area_token;
+static int connfd;
+static bool stop;
+static size_t received;
+
+static unsigned long gettimeofday_ms(void)
+{
+	struct timeval tv;
+
+	gettimeofday(&tv, NULL);
+	return (tv.tv_sec * 1000) + (tv.tv_usec / 1000);
+}
+
+static int parse_address(const char *str, int port, struct sockaddr_in6 *sin6)
+{
+	int ret;
+
+	sin6->sin6_family = AF_INET6;
+	sin6->sin6_port = htons(port);
+
+	ret = inet_pton(sin6->sin6_family, str, &sin6->sin6_addr);
+	if (ret != 1) {
+		/* fallback to plain IPv4 */
+		ret = inet_pton(AF_INET, str, &sin6->sin6_addr.s6_addr32[3]);
+		if (ret != 1)
+			return -1;
+
+		/* add ::ffff prefix */
+		sin6->sin6_addr.s6_addr32[0] = 0;
+		sin6->sin6_addr.s6_addr32[1] = 0;
+		sin6->sin6_addr.s6_addr16[4] = 0;
+		sin6->sin6_addr.s6_addr16[5] = 0xffff;
+	}
+
+	return 0;
+}
+
+static inline size_t get_refill_ring_size(unsigned int rq_entries)
+{
+	size_t size;
+
+	ring_size = rq_entries * sizeof(struct io_uring_zcrx_rqe);
+	/* add space for the header (head/tail/etc.) */
+	ring_size += page_size;
+	return ALIGN_UP(ring_size, page_size);
+}
+
+static void setup_zcrx(struct io_uring *ring)
+{
+	unsigned int ifindex;
+	unsigned int rq_entries = 4096;
+	int ret;
+
+	ifindex = if_nametoindex(cfg_ifname);
+	if (!ifindex)
+		error(1, 0, "bad interface name: %s", cfg_ifname);
+
+	if (cfg_rx_buf_len && cfg_rx_buf_len != page_size) {
+		area_ptr = mmap(NULL,
+				AREA_SIZE,
+				PROT_READ | PROT_WRITE,
+				MAP_ANONYMOUS | MAP_PRIVATE |
+				MAP_HUGETLB | MAP_HUGE_2MB,
+				-1,
+				0);
+		if (area_ptr == MAP_FAILED) {
+			printf("Can't allocate huge pages\n");
+			exit(SKIP_CODE);
+		}
+	} else {
+		area_ptr = mmap(NULL,
+				AREA_SIZE,
+				PROT_READ | PROT_WRITE,
+				MAP_ANONYMOUS | MAP_PRIVATE,
+				0,
+				0);
+		if (area_ptr == MAP_FAILED)
+			error(1, 0, "mmap(): zero copy area");
+	}
+
+	ring_size = get_refill_ring_size(rq_entries);
+	ring_ptr = mmap(NULL,
+			ring_size,
+			PROT_READ | PROT_WRITE,
+			MAP_ANONYMOUS | MAP_PRIVATE,
+			0,
+			0);
+
+	struct io_uring_region_desc region_reg = {
+		.size = ring_size,
+		.user_addr = (__u64)(unsigned long)ring_ptr,
+		.flags = IORING_MEM_REGION_TYPE_USER,
+	};
+
+	struct io_uring_zcrx_area_reg area_reg = {
+		.addr = (__u64)(unsigned long)area_ptr,
+		.len = AREA_SIZE,
+		.flags = 0,
+	};
+
+	struct t_io_uring_zcrx_ifq_reg reg = {
+		.if_idx = ifindex,
+		.if_rxq = cfg_queue_id,
+		.rq_entries = rq_entries,
+		.area_ptr = (__u64)(unsigned long)&area_reg,
+		.region_ptr = (__u64)(unsigned long)&region_reg,
+		.rx_buf_len = cfg_rx_buf_len,
+	};
+
+	ret = io_uring_register_ifq(ring, (void *)&reg);
+	if (cfg_rx_buf_len && (ret == -EINVAL || ret == -EOPNOTSUPP ||
+			       ret == -ERANGE)) {
+		printf("Large chunks are not supported %i\n", ret);
+		exit(SKIP_CODE);
+	} else if (ret) {
+		error(1, 0, "io_uring_register_ifq(): %d", ret);
+	}
+
+	rq_ring.khead = (unsigned int *)((char *)ring_ptr + reg.offsets.head);
+	rq_ring.ktail = (unsigned int *)((char *)ring_ptr + reg.offsets.tail);
+	rq_ring.rqes = (struct io_uring_zcrx_rqe *)((char *)ring_ptr + reg.offsets.rqes);
+	rq_ring.rq_tail = 0;
+	rq_ring.ring_entries = reg.rq_entries;
+
+	area_token = area_reg.rq_area_token;
+}
+
+static void add_accept(struct io_uring *ring, int sockfd)
+{
+	struct io_uring_sqe *sqe;
+
+	sqe = io_uring_get_sqe(ring);
+
+	io_uring_prep_accept(sqe, sockfd, NULL, NULL, 0);
+	sqe->user_data = 1;
+}
+
+static void add_recvzc(struct io_uring *ring, int sockfd)
+{
+	struct io_uring_sqe *sqe;
+
+	sqe = io_uring_get_sqe(ring);
+
+	io_uring_prep_rw(IORING_OP_RECV_ZC, sqe, sockfd, NULL, 0, 0);
+	sqe->ioprio |= IORING_RECV_MULTISHOT;
+	sqe->user_data = 2;
+}
+
+static void add_recvzc_oneshot(struct io_uring *ring, int sockfd, size_t len)
+{
+	struct io_uring_sqe *sqe;
+
+	sqe = io_uring_get_sqe(ring);
+
+	io_uring_prep_rw(IORING_OP_RECV_ZC, sqe, sockfd, NULL, len, 0);
+	sqe->ioprio |= IORING_RECV_MULTISHOT;
+	sqe->user_data = 2;
+}
+
+static void process_accept(struct io_uring *ring, struct io_uring_cqe *cqe)
+{
+	if (cqe->res < 0)
+		error(1, 0, "accept()");
+	if (connfd)
+		error(1, 0, "Unexpected second connection");
+
+	connfd = cqe->res;
+	if (cfg_oneshot)
+		add_recvzc_oneshot(ring, connfd, page_size);
+	else
+		add_recvzc(ring, connfd);
+}
+
+static void process_recvzc(struct io_uring *ring, struct io_uring_cqe *cqe)
+{
+	unsigned rq_mask = rq_ring.ring_entries - 1;
+	struct io_uring_zcrx_cqe *rcqe;
+	struct io_uring_zcrx_rqe *rqe;
+	struct io_uring_sqe *sqe;
+	uint64_t mask;
+	char *data;
+	ssize_t n;
+	int i;
+
+	if (cqe->res == 0 && cqe->flags == 0 && cfg_oneshot_recvs == 0) {
+		stop = true;
+		return;
+	}
+
+	if (cqe->res < 0)
+		error(1, 0, "recvzc(): %d", cqe->res);
+
+	if (cfg_oneshot) {
+		if (cqe->res == 0 && cqe->flags == 0 && cfg_oneshot_recvs) {
+			add_recvzc_oneshot(ring, connfd, page_size);
+			cfg_oneshot_recvs--;
+		}
+	} else if (!(cqe->flags & IORING_CQE_F_MORE)) {
+		add_recvzc(ring, connfd);
+	}
+
+	rcqe = (struct io_uring_zcrx_cqe *)(cqe + 1);
+
+	n = cqe->res;
+	mask = (1ULL << IORING_ZCRX_AREA_SHIFT) - 1;
+	data = (char *)area_ptr + (rcqe->off & mask);
+
+	for (i = 0; i < n; i++) {
+		if (*(data + i) != payload[(received + i)])
+			error(1, 0, "payload mismatch at %d", i);
+	}
+	received += n;
+
+	rqe = &rq_ring.rqes[(rq_ring.rq_tail & rq_mask)];
+	rqe->off = (rcqe->off & ~IORING_ZCRX_AREA_MASK) | area_token;
+	rqe->len = cqe->res;
+	io_uring_smp_store_release(rq_ring.ktail, ++rq_ring.rq_tail);
+}
+
+static void server_loop(struct io_uring *ring)
+{
+	struct io_uring_cqe *cqe;
+	unsigned int count = 0;
+	unsigned int head;
+	int i, ret;
+
+	io_uring_submit_and_wait(ring, 1);
+
+	io_uring_for_each_cqe(ring, head, cqe) {
+		if (cqe->user_data == 1)
+			process_accept(ring, cqe);
+		else if (cqe->user_data == 2)
+			process_recvzc(ring, cqe);
+		else
+			error(1, 0, "unknown cqe");
+		count++;
+	}
+	io_uring_cq_advance(ring, count);
+}
+
+static void run_server(void)
+{
+	unsigned int flags = 0;
+	struct io_uring ring;
+	int fd, enable, ret;
+	uint64_t tstop;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd == -1)
+		error(1, 0, "socket()");
+
+	enable = 1;
+	ret = setsockopt(fd, SOL_SOCKET, SO_REUSEADDR, &enable, sizeof(int));
+	if (ret < 0)
+		error(1, 0, "setsockopt(SO_REUSEADDR)");
+
+	ret = bind(fd, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr));
+	if (ret < 0)
+		error(1, 0, "bind()");
+
+	flags |= IORING_SETUP_COOP_TASKRUN;
+	flags |= IORING_SETUP_SINGLE_ISSUER;
+	flags |= IORING_SETUP_DEFER_TASKRUN;
+	flags |= IORING_SETUP_SUBMIT_ALL;
+	flags |= IORING_SETUP_CQE32;
+
+	io_uring_queue_init(512, &ring, flags);
+
+	setup_zcrx(&ring);
+	if (cfg_dry_run)
+		return;
+
+	if (listen(fd, 1024) < 0)
+		error(1, 0, "listen()");
+
+	add_accept(&ring, fd);
+
+	tstop = gettimeofday_ms() + 5000;
+	while (!stop && gettimeofday_ms() < tstop)
+		server_loop(&ring);
+
+	if (!stop)
+		error(1, 0, "test failed\n");
+}
+
+static void run_client(void)
+{
+	ssize_t to_send = cfg_send_size;
+	ssize_t sent = 0;
+	ssize_t chunk, res;
+	int fd;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd == -1)
+		error(1, 0, "socket()");
+
+	if (connect(fd, (struct sockaddr *)&cfg_addr, sizeof(cfg_addr)))
+		error(1, 0, "connect()");
+
+	while (to_send) {
+		void *src = &payload[sent];
+
+		chunk = min_t(ssize_t, cfg_payload_len, to_send);
+		res = send(fd, src, chunk, 0);
+		if (res < 0)
+			error(1, 0, "send(): %zd", sent);
+		sent += res;
+		to_send -= res;
+	}
+
+	close(fd);
+}
+
+static void usage(const char *filepath)
+{
+	error(1, 0, "Usage: %s (-4|-6) (-s|-c) -h<server_ip> -p<port> "
+		    "-l<payload_size> -i<ifname> -q<rxq_id>", filepath);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	const int max_payload_len = SEND_SIZE -
+				    sizeof(struct ipv6hdr) -
+				    sizeof(struct tcphdr) -
+				    40 /* max tcp options */;
+	struct sockaddr_in6 *addr6 = (void *) &cfg_addr;
+	char *addr = NULL;
+	int ret;
+	int c;
+
+	if (argc <= 1)
+		usage(argv[0]);
+	cfg_payload_len = max_payload_len;
+
+	while ((c = getopt(argc, argv, "sch:p:l:i:q:o:z:x:d")) != -1) {
+		switch (c) {
+		case 's':
+			if (cfg_client)
+				error(1, 0, "Pass one of -s or -c");
+			cfg_server = 1;
+			break;
+		case 'c':
+			if (cfg_server)
+				error(1, 0, "Pass one of -s or -c");
+			cfg_client = 1;
+			break;
+		case 'h':
+			addr = optarg;
+			break;
+		case 'p':
+			cfg_port = strtoul(optarg, NULL, 0);
+			break;
+		case 'l':
+			cfg_payload_len = strtoul(optarg, NULL, 0);
+			break;
+		case 'i':
+			cfg_ifname = optarg;
+			break;
+		case 'q':
+			cfg_queue_id = strtoul(optarg, NULL, 0);
+			break;
+		case 'o': {
+			cfg_oneshot = true;
+			cfg_oneshot_recvs = strtoul(optarg, NULL, 0);
+			break;
+		}
+		case 'z':
+			cfg_send_size = strtoul(optarg, NULL, 0);
+			break;
+		case 'x':
+			cfg_rx_buf_len = page_size * strtoul(optarg, NULL, 0);
+			break;
+		case 'd':
+			cfg_dry_run = true;
+			break;
+		}
+	}
+
+	if (cfg_server && addr)
+		error(1, 0, "Receiver cannot have -h specified");
+
+	memset(addr6, 0, sizeof(*addr6));
+	addr6->sin6_family = AF_INET6;
+	addr6->sin6_port = htons(cfg_port);
+	addr6->sin6_addr = in6addr_any;
+	if (addr) {
+		ret = parse_address(addr, cfg_port, addr6);
+		if (ret)
+			error(1, 0, "receiver address parse error: %s", addr);
+	}
+
+	if (cfg_payload_len > max_payload_len)
+		error(1, 0, "-l: payload exceeds max (%d)", max_payload_len);
+}
+
+int main(int argc, char **argv)
+{
+	const char *cfg_test = argv[argc - 1];
+	int i;
+
+	page_size = sysconf(_SC_PAGESIZE);
+	if (page_size < 0)
+		return 1;
+
+	if (posix_memalign((void **)&payload, page_size, SEND_SIZE))
+		return 1;
+
+	parse_opts(argc, argv);
+
+	for (i = 0; i < SEND_SIZE; i++)
+		payload[i] = 'a' + (i % 26);
+
+	if (cfg_server)
+		run_server();
+	else if (cfg_client)
+		run_client();
+
+	return 0;
+}

linux-7.2.3/tools/testing/selftests/drivers/net/hw/iou-zcrx.py

@@ -0,0 +1,210 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import re
+import resource
+import time
+from os import path
+from lib.py import ksft_run, ksft_exit, KsftSkipEx, ksft_variants, KsftNamedVariant
+from lib.py import NetDrvEpEnv
+from lib.py import bkg, cmd, defer, ethtool, rand_port, wait_port_listen
+from lib.py import EthtoolFamily, NetdevFamily
+
+SKIP_CODE = 42
+
+
+def mp_clear_wait(cfg):
+    """Wait for io_uring memory providers to clear from all device queues."""
+    deadline = time.time() + 5
+    while time.time() < deadline:
+        queues = cfg.netnl.queue_get({'ifindex': cfg.ifindex}, dump=True)
+        if not any('io-uring' in q for q in queues):
+            return
+        time.sleep(0.1)
+    raise TimeoutError("Timed out waiting for memory provider to clear")
+
+
+def create_rss_ctx(cfg):
+    output = ethtool(f"-X {cfg.ifname} context new start {cfg.target} equal 1").stdout
+    values = re.search(r'New RSS context is (\d+)', output).group(1)
+    return int(values)
+
+
+def set_flow_rule(cfg):
+    output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {cfg.port} action {cfg.target}").stdout
+    values = re.search(r'ID (\d+)', output).group(1)
+    return int(values)
+
+
+def set_flow_rule_rss(cfg, rss_ctx_id):
+    output = ethtool(f"-N {cfg.ifname} flow-type tcp6 dst-port {cfg.port} context {rss_ctx_id}").stdout
+    values = re.search(r'ID (\d+)', output).group(1)
+    return int(values)
+
+
+def check_iou_rx_buf_len(cfg, expected_rx_buf_len):
+    """Check the io-uring memory provider exposes the expected rx_buf_len."""
+    q = cfg.netnl.queue_get({'ifindex': cfg.ifindex, 'type': 'rx', 'id': cfg.target})
+    napi_id = q['napi-id']
+    pools = cfg.netnl.page_pool_get({}, dump=True)
+    pools = [p for p in pools if p.get('napi-id') == napi_id
+             and 'io-uring' in p]
+    if len(pools) != 1:
+        raise Exception(f"Expected 1 io-uring page pool, found {len(pools)}")
+    rx_buf_len = pools[0]['io-uring'].get('rx-buf-len')
+    if rx_buf_len is None:
+        raise KsftSkipEx("io-uring 'rx-buf-len' attribute not supported")
+    if rx_buf_len != expected_rx_buf_len:
+        raise Exception(f'Expected io-uring rx-buf-len {expected_rx_buf_len}, '
+                        f'got {rx_buf_len}')
+
+
+def single(cfg):
+    channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    channels = channels['combined-count']
+    if channels < 2:
+        raise KsftSkipEx('Test requires NETIF with at least 2 combined channels')
+
+    rings = cfg.ethnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    rx_rings = rings['rx']
+    hds_thresh = rings.get('hds-thresh', 0)
+
+    cfg.ethnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                         'tcp-data-split': 'enabled',
+                         'hds-thresh': 0,
+                         'rx': 64})
+    defer(cfg.ethnl.rings_set, {'header': {'dev-index': cfg.ifindex},
+                                'tcp-data-split': 'unknown',
+                                'hds-thresh': hds_thresh,
+                                'rx': rx_rings})
+    defer(mp_clear_wait, cfg)
+
+    cfg.target = channels - 1
+    ethtool(f"-X {cfg.ifname} equal {cfg.target}")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    flow_rule_id = set_flow_rule(cfg)
+    defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}")
+
+
+def rss(cfg):
+    channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    channels = channels['combined-count']
+    if channels < 2:
+        raise KsftSkipEx('Test requires NETIF with at least 2 combined channels')
+
+    rings = cfg.ethnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    rx_rings = rings['rx']
+    hds_thresh = rings.get('hds-thresh', 0)
+
+    cfg.ethnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                         'tcp-data-split': 'enabled',
+                         'hds-thresh': 0,
+                         'rx': 64})
+    defer(cfg.ethnl.rings_set, {'header': {'dev-index': cfg.ifindex},
+                                'tcp-data-split': 'unknown',
+                                'hds-thresh': hds_thresh,
+                                'rx': rx_rings})
+    defer(mp_clear_wait, cfg)
+
+    cfg.target = channels - 1
+    ethtool(f"-X {cfg.ifname} equal {cfg.target}")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    rss_ctx_id = create_rss_ctx(cfg)
+    defer(ethtool, f"-X {cfg.ifname} delete context {rss_ctx_id}")
+
+    flow_rule_id = set_flow_rule_rss(cfg, rss_ctx_id)
+    defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}")
+
+
+def _require_ntuple(cfg):
+    features = ethtool(f"-k {cfg.ifname}", json=True)[0]
+    if not features["ntuple-filters"]["active"]:
+        if features["ntuple-filters"]["fixed"]:
+            raise KsftSkipEx("Device does not support ntuple-filters")
+        ethtool(f"-K {cfg.ifname} ntuple-filters on")
+        defer(ethtool, f"-K {cfg.ifname} ntuple-filters off")
+
+
+@ksft_variants([
+    KsftNamedVariant("single", single),
+    KsftNamedVariant("rss", rss),
+])
+def test_zcrx(cfg, setup) -> None:
+    cfg.require_ipver('6')
+    _require_ntuple(cfg)
+
+    setup(cfg)
+    rx_cmd = f"{cfg.bin_local} -s -p {cfg.port} -i {cfg.ifname} -q {cfg.target}"
+    tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {cfg.port} -l 12840"
+    with bkg(rx_cmd, exit_wait=True):
+        wait_port_listen(cfg.port, proto="tcp")
+        cmd(tx_cmd, host=cfg.remote)
+
+
+@ksft_variants([
+    KsftNamedVariant("single", single),
+    KsftNamedVariant("rss", rss),
+])
+def test_zcrx_oneshot(cfg, setup) -> None:
+    cfg.require_ipver('6')
+    _require_ntuple(cfg)
+
+    setup(cfg)
+    rx_cmd = f"{cfg.bin_local} -s -p {cfg.port} -i {cfg.ifname} -q {cfg.target} -o 4"
+    tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {cfg.port} -l 4096 -z 16384"
+    with bkg(rx_cmd, exit_wait=True):
+        wait_port_listen(cfg.port, proto="tcp")
+        cmd(tx_cmd, host=cfg.remote)
+
+
+def test_zcrx_large_chunks(cfg) -> None:
+    """Test zcrx with large buffer chunks."""
+
+    cfg.require_ipver('6')
+    _require_ntuple(cfg)
+
+    hp_file = "/proc/sys/vm/nr_hugepages"
+    with open(hp_file, 'r+', encoding='utf-8') as f:
+        nr_hugepages = int(f.read().strip())
+        if nr_hugepages < 64:
+            f.seek(0)
+            f.write("64")
+            defer(lambda: open(hp_file, 'w', encoding='utf-8').write(str(nr_hugepages)))
+
+    single(cfg)
+    page_size = resource.getpagesize()
+    nr_pages = 2
+    rx_buf_len = nr_pages * page_size
+    rx_cmd = f"{cfg.bin_local} -s -p {cfg.port} -i {cfg.ifname} -q {cfg.target} -x {nr_pages}"
+    tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {cfg.port} -l 12840"
+
+    probe = cmd(rx_cmd + " -d", fail=False)
+    if probe.ret == SKIP_CODE:
+        raise KsftSkipEx(probe.stdout.strip())
+
+    mp_clear_wait(cfg)
+    with bkg(rx_cmd, exit_wait=True):
+        wait_port_listen(cfg.port, proto="tcp")
+
+        check_iou_rx_buf_len(cfg, rx_buf_len)
+
+        cmd(tx_cmd, host=cfg.remote)
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__) as cfg:
+        cfg.bin_local = path.abspath(path.dirname(__file__) + "/../../../drivers/net/hw/iou-zcrx")
+        cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
+
+        cfg.ethnl = EthtoolFamily()
+        cfg.netnl = NetdevFamily()
+        cfg.port = rand_port()
+        ksft_run(globs=globals(), cases=[test_zcrx, test_zcrx_oneshot,
+                                        test_zcrx_large_chunks], args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/ipsec_vxlan.py

@@ -0,0 +1,204 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+"""Traffic test for VXLAN + IPsec crypto-offload."""
+
+import os
+
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge
+from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx
+from lib.py import CmdExitFailure, NetDrvEpEnv, cmd, defer, ethtool, ip
+from lib.py import Iperf3Runner
+
+# Inner tunnel addresses - TEST-NET-2 (RFC 5737) / doc prefix (RFC 3849)
+INNER_V4_LOCAL = "198.51.100.1"
+INNER_V4_REMOTE = "198.51.100.2"
+INNER_V6_LOCAL = "2001:db8:100::1"
+INNER_V6_REMOTE = "2001:db8:100::2"
+
+# ESP parameters
+SPI_OUT = "0x1000"
+SPI_IN = "0x1001"
+# 128-bit key + 32-bit salt = 20 bytes hex, 128-bit ICV
+ESP_AEAD = "aead 'rfc4106(gcm(aes))' 0x" + "01" * 20 + " 128"
+
+
+def xfrm(args, host=None):
+    """Runs 'ip xfrm' via shell to preserve parentheses in algo names."""
+    cmd(f"ip xfrm {args}", shell=True, host=host)
+
+
+def check_xfrm_offload_support():
+    """Skips if iproute2 lacks xfrm offload support."""
+    out = cmd("ip xfrm state help", fail=False)
+    if "offload" not in out.stdout + out.stderr:
+        raise KsftSkipEx("iproute2 too old, missing xfrm offload")
+
+
+def check_esp_hw_offload(cfg):
+    """Skips if device lacks esp-hw-offload support."""
+    check_xfrm_offload_support()
+    try:
+        feat = ethtool(f"-k {cfg.ifname}", json=True)[0]
+    except (CmdExitFailure, IndexError) as e:
+        raise KsftSkipEx(f"can't query features: {e}") from e
+    if not feat.get("esp-hw-offload", {}).get("active"):
+        raise KsftSkipEx("Device does not support esp-hw-offload")
+
+
+def get_tx_drops(cfg):
+    """Returns TX dropped counter from the physical device."""
+    stats = ip("-s -s link show dev " + cfg.ifname, json=True)[0]
+    return stats["stats64"]["tx"]["dropped"]
+
+
+def setup_vxlan_ipsec(cfg, outer_ipver, inner_ipver):
+    """Sets up VXLAN tunnel with IPsec transport-mode crypto-offload."""
+    vxlan_name = f"vx{os.getpid()}"
+    local_addr = cfg.addr_v[outer_ipver]
+    remote_addr = cfg.remote_addr_v[outer_ipver]
+
+    if inner_ipver == "4":
+        inner_local = f"{INNER_V4_LOCAL}/24"
+        inner_remote = f"{INNER_V4_REMOTE}/24"
+        addr_extra = ""
+    else:
+        inner_local = f"{INNER_V6_LOCAL}/64"
+        inner_remote = f"{INNER_V6_REMOTE}/64"
+        addr_extra = " nodad"
+
+    if outer_ipver == "6":
+        vxlan_opts = "udp6zerocsumtx udp6zerocsumrx"
+    else:
+        vxlan_opts = "noudpcsum"
+
+    # VXLAN tunnel - local side
+    ip(f"link add {vxlan_name} type vxlan id 100 dstport 4789 {vxlan_opts} "
+       f"local {local_addr} remote {remote_addr} dev {cfg.ifname}")
+    defer(ip, f"link del {vxlan_name}")
+    ip(f"addr add {inner_local} dev {vxlan_name}{addr_extra}")
+    ip(f"link set {vxlan_name} up")
+
+    # VXLAN tunnel - remote side
+    ip(f"link add {vxlan_name} type vxlan id 100 dstport 4789 {vxlan_opts} "
+       f"local {remote_addr} remote {local_addr} dev {cfg.remote_ifname}",
+       host=cfg.remote)
+    defer(ip, f"link del {vxlan_name}", host=cfg.remote)
+    ip(f"addr add {inner_remote} dev {vxlan_name}{addr_extra}",
+       host=cfg.remote)
+    ip(f"link set {vxlan_name} up", host=cfg.remote)
+
+    # xfrm state - local outbound SA
+    xfrm(f"state add src {local_addr} dst {remote_addr} "
+         f"proto esp spi {SPI_OUT} "
+         f"{ESP_AEAD} "
+         f"mode transport offload crypto dev {cfg.ifname} dir out")
+    defer(xfrm, f"state del src {local_addr} dst {remote_addr} "
+                f"proto esp spi {SPI_OUT}")
+
+    # xfrm state - local inbound SA
+    xfrm(f"state add src {remote_addr} dst {local_addr} "
+         f"proto esp spi {SPI_IN} "
+         f"{ESP_AEAD} "
+         f"mode transport offload crypto dev {cfg.ifname} dir in")
+    defer(xfrm, f"state del src {remote_addr} dst {local_addr} "
+                f"proto esp spi {SPI_IN}")
+
+    # xfrm state - remote outbound SA (mirror, software crypto)
+    xfrm(f"state add src {remote_addr} dst {local_addr} "
+         f"proto esp spi {SPI_IN} "
+         f"{ESP_AEAD} "
+         f"mode transport",
+         host=cfg.remote)
+    defer(xfrm, f"state del src {remote_addr} dst {local_addr} "
+                f"proto esp spi {SPI_IN}", host=cfg.remote)
+
+    # xfrm state - remote inbound SA (mirror, software crypto)
+    xfrm(f"state add src {local_addr} dst {remote_addr} "
+         f"proto esp spi {SPI_OUT} "
+         f"{ESP_AEAD} "
+         f"mode transport",
+         host=cfg.remote)
+    defer(xfrm, f"state del src {local_addr} dst {remote_addr} "
+                f"proto esp spi {SPI_OUT}", host=cfg.remote)
+
+    # xfrm policy - local out
+    xfrm(f"policy add src {local_addr} dst {remote_addr} "
+         f"proto udp dport 4789 dir out "
+         f"tmpl src {local_addr} dst {remote_addr} proto esp mode transport")
+    defer(xfrm, f"policy del src {local_addr} dst {remote_addr} "
+                f"proto udp dport 4789 dir out")
+
+    # xfrm policy - local in
+    xfrm(f"policy add src {remote_addr} dst {local_addr} "
+         f"proto udp dport 4789 dir in "
+         f"tmpl src {remote_addr} dst {local_addr} proto esp mode transport")
+    defer(xfrm, f"policy del src {remote_addr} dst {local_addr} "
+                f"proto udp dport 4789 dir in")
+
+    # xfrm policy - remote out
+    xfrm(f"policy add src {remote_addr} dst {local_addr} "
+         f"proto udp dport 4789 dir out "
+         f"tmpl src {remote_addr} dst {local_addr} proto esp mode transport",
+         host=cfg.remote)
+    defer(xfrm, f"policy del src {remote_addr} dst {local_addr} "
+                f"proto udp dport 4789 dir out", host=cfg.remote)
+
+    # xfrm policy - remote in
+    xfrm(f"policy add src {local_addr} dst {remote_addr} "
+         f"proto udp dport 4789 dir in "
+         f"tmpl src {local_addr} dst {remote_addr} proto esp mode transport",
+         host=cfg.remote)
+    defer(xfrm, f"policy del src {local_addr} dst {remote_addr} "
+                f"proto udp dport 4789 dir in", host=cfg.remote)
+
+
+def _vxlan_ipsec_variants():
+    """Generates outer/inner IP version variants."""
+    for outer in ["4", "6"]:
+        for inner in ["4", "6"]:
+            yield KsftNamedVariant(f"outer_v{outer}_inner_v{inner}", outer, inner)
+
+
+@ksft_variants(_vxlan_ipsec_variants())
+def test_vxlan_ipsec_crypto_offload(cfg, outer_ipver, inner_ipver):
+    """Tests VXLAN+IPsec crypto-offload has no TX drops."""
+    cfg.require_ipver(outer_ipver)
+    check_esp_hw_offload(cfg)
+
+    setup_vxlan_ipsec(cfg, outer_ipver, inner_ipver)
+
+    if inner_ipver == "4":
+        inner_local = INNER_V4_LOCAL
+        inner_remote = INNER_V4_REMOTE
+        ping = "ping"
+    else:
+        inner_local = INNER_V6_LOCAL
+        inner_remote = INNER_V6_REMOTE
+        ping = "ping -6"
+
+    cmd(f"{ping} -c 1 -W 2 {inner_remote}")
+
+    drops_before = get_tx_drops(cfg)
+
+    runner = Iperf3Runner(cfg, server_ip=inner_local,
+                          client_ip=inner_remote)
+    bw_gbps = runner.measure_bandwidth(reverse=True)
+
+    cfg.wait_hw_stats_settle()
+    drops_after = get_tx_drops(cfg)
+
+    ksft_eq(drops_after - drops_before, 0,
+            comment="TX drops during VXLAN+IPsec")
+    ksft_ge(bw_gbps, 0.1,
+            comment="Minimum 100Mbps over VXLAN+IPsec")
+
+
+def main():
+    """Runs VXLAN+IPsec crypto-offload GSO selftest."""
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        ksft_run([test_vxlan_ipsec_crypto_offload], args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/irq.py

@@ -0,0 +1,99 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from lib.py import ksft_run, ksft_exit
+from lib.py import ksft_ge, ksft_eq
+from lib.py import KsftSkipEx
+from lib.py import ksft_disruptive
+from lib.py import EthtoolFamily, NetdevFamily
+from lib.py import NetDrvEnv
+from lib.py import cmd, ip, defer
+
+
+def read_affinity(irq) -> str:
+    with open(f'/proc/irq/{irq}/smp_affinity', 'r') as fp:
+        return fp.read().lstrip("0,").strip()
+
+
+def write_affinity(irq, what) -> str:
+    if what != read_affinity(irq):
+        with open(f'/proc/irq/{irq}/smp_affinity', 'w') as fp:
+            fp.write(what)
+
+
+def check_irqs_reported(cfg) -> None:
+    """ Check that device reports IRQs for NAPI instances """
+    napis = cfg.netnl.napi_get({"ifindex": cfg.ifindex}, dump=True)
+    irqs = sum(['irq' in x for x in napis])
+
+    ksft_ge(irqs, 1)
+    ksft_eq(irqs, len(napis))
+
+
+def _check_reconfig(cfg, reconfig_cb) -> None:
+    napis = cfg.netnl.napi_get({"ifindex": cfg.ifindex}, dump=True)
+    for n in reversed(napis):
+        if 'irq' in n:
+            break
+    else:
+        raise KsftSkipEx(f"Device has no NAPI with IRQ attribute (#napis: {len(napis)}")
+
+    old = read_affinity(n['irq'])
+    # pick an affinity that's not the current one
+    new = "3" if old != "3" else "5"
+    write_affinity(n['irq'], new)
+    defer(write_affinity, n['irq'], old)
+
+    reconfig_cb(cfg)
+
+    ksft_eq(read_affinity(n['irq']), new, comment="IRQ affinity changed after reconfig")
+
+
+def check_reconfig_queues(cfg) -> None:
+    def reconfig(cfg) -> None:
+        channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+        if channels['combined-count'] == 0:
+            rx_type = 'rx'
+        else:
+            rx_type = 'combined'
+        cur_queue_cnt = channels[f'{rx_type}-count']
+        max_queue_cnt = channels[f'{rx_type}-max']
+
+        cmd(f"ethtool -L {cfg.ifname} {rx_type} 1")
+        cmd(f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}")
+        cmd(f"ethtool -L {cfg.ifname} {rx_type} {cur_queue_cnt}")
+
+    _check_reconfig(cfg, reconfig)
+
+
+def check_reconfig_xdp(cfg) -> None:
+    def reconfig(cfg) -> None:
+        ip(f"link set dev %s xdp obj %s sec xdp" %
+           (cfg.ifname, cfg.net_lib_dir / "xdp_dummy.bpf.o"))
+        ip(f"link set dev %s xdp off" % cfg.ifname)
+
+    _check_reconfig(cfg, reconfig)
+
+
+@ksft_disruptive
+def check_down(cfg) -> None:
+    def reconfig(cfg) -> None:
+        ip("link set dev %s down" % cfg.ifname)
+        ip("link set dev %s up" % cfg.ifname)
+
+    _check_reconfig(cfg, reconfig)
+
+
+def main() -> None:
+    with NetDrvEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        cfg.netnl = NetdevFamily()
+
+        ksft_run([check_irqs_reported, check_reconfig_queues,
+                  check_reconfig_xdp, check_down],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py

@@ -0,0 +1,56 @@
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Driver test environment (hardware-only tests).
+NetDrvEnv and NetDrvEpEnv are the main environment classes.
+NetDrvContEnv extends NetDrvEpEnv with netkit container support.
+Former is for local host only tests, latter creates / connects
+to a remote endpoint. See NIPA wiki for more information about
+running and writing driver tests.
+"""
+
+import sys
+from pathlib import Path
+
+KSFT_DIR = (Path(__file__).parent / "../../../../..").resolve()
+
+try:
+    sys.path.append(KSFT_DIR.as_posix())
+
+    # Import one by one to avoid pylint false positives
+    from net.lib.py import NetNS, NetNSEnter, NetdevSimDev, UserNetNS
+    from net.lib.py import EthtoolFamily, NetdevFamily, NetshaperFamily, \
+        NlError, RtnlFamily, DevlinkFamily, PSPFamily, Netlink
+    from net.lib.py import CmdExitFailure
+    from net.lib.py import bkg, cmd, bpftool, bpftrace, defer, ethtool, \
+        fd_read_timeout, ip, rand_port, rand_ports, wait_port_listen, \
+        wait_file, tool
+    from net.lib.py import bpf_map_set, bpf_map_dump, bpf_prog_map_ids
+    from net.lib.py import KsftSkipEx, KsftFailEx, KsftXfailEx
+    from net.lib.py import ksft_disruptive, ksft_exit, ksft_pr, ksft_run, \
+        ksft_setup, ksft_variants, KsftNamedVariant
+    from net.lib.py import ksft_eq, ksft_ge, ksft_in, ksft_is, ksft_lt, \
+        ksft_ne, ksft_not_in, ksft_raises, ksft_true, ksft_gt, ksft_not_none
+    from drivers.net.lib.py import GenerateTraffic, Remote, Iperf3Runner
+    from drivers.net.lib.py import NetDrvEnv, NetDrvEpEnv, NetDrvContEnv
+
+    __all__ = ["NetNS", "NetNSEnter", "NetdevSimDev", "UserNetNS",
+               "EthtoolFamily", "NetdevFamily", "NetshaperFamily",
+               "NlError", "RtnlFamily", "DevlinkFamily", "PSPFamily", "Netlink",
+               "CmdExitFailure",
+               "bkg", "cmd", "bpftool", "bpftrace", "defer", "ethtool",
+               "fd_read_timeout", "ip", "rand_port", "rand_ports",
+               "wait_port_listen", "wait_file", "tool",
+               "bpf_map_set", "bpf_map_dump", "bpf_prog_map_ids",
+               "KsftSkipEx", "KsftFailEx", "KsftXfailEx",
+               "ksft_disruptive", "ksft_exit", "ksft_pr", "ksft_run",
+               "ksft_setup", "ksft_variants", "KsftNamedVariant",
+               "ksft_eq", "ksft_ge", "ksft_in", "ksft_is", "ksft_lt",
+               "ksft_ne", "ksft_not_in", "ksft_raises", "ksft_true", "ksft_gt",
+               "ksft_not_none", "ksft_not_none",
+               "NetDrvEnv", "NetDrvEpEnv", "NetDrvContEnv", "GenerateTraffic",
+               "Remote", "Iperf3Runner"]
+except ModuleNotFoundError as e:
+    print("Failed importing `net` library from kernel sources")
+    print(str(e))
+    sys.exit(4)

linux-7.2.3/tools/testing/selftests/drivers/net/hw/loopback.sh

@@ -0,0 +1,103 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+ALL_TESTS="loopback_test"
+NUM_NETIFS=2
+lib_dir=$(dirname "$0")
+source "$lib_dir"/../../../net/forwarding/tc_common.sh
+source "$lib_dir"/../../../net/forwarding/lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/24
+	tc qdisc add dev $h1 clsact
+}
+
+h1_destroy()
+{
+	tc qdisc del dev $h1 clsact
+	simple_if_fini $h1 192.0.2.1/24
+}
+
+h2_create()
+{
+	simple_if_init $h2
+}
+
+h2_destroy()
+{
+	simple_if_fini $h2
+}
+
+loopback_test()
+{
+	RET=0
+
+	tc filter add dev $h1 ingress protocol arp pref 1 handle 101 flower \
+		skip_hw arp_op reply arp_tip 192.0.2.1 action drop
+
+	$MZ $h1 -c 1 -t arp -q
+
+	tc_check_packets "dev $h1 ingress" 101 1
+	check_fail $? "Matched on a filter without loopback setup"
+
+	ethtool -K $h1 loopback on
+	check_err $? "Failed to enable loopback"
+
+	setup_wait_dev $h1
+
+	$MZ $h1 -c 1 -t arp -q
+
+	tc_check_packets "dev $h1 ingress" 101 1
+	check_err $? "Did not match on filter with loopback"
+
+	ethtool -K $h1 loopback off
+	check_err $? "Failed to disable loopback"
+
+	$MZ $h1 -c 1 -t arp -q
+
+	tc_check_packets "dev $h1 ingress" 101 2
+	check_fail $? "Matched on a filter after loopback was removed"
+
+	tc filter del dev $h1 ingress protocol arp pref 1 handle 101 flower
+
+	log_test "loopback"
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	h2=${NETIFS[p2]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	if ethtool -k $h1 | grep loopback | grep -q fixed; then
+		log_test "SKIP: dev $h1 does not support loopback feature"
+		exit $ksft_skip
+	fi
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS

linux-7.2.3/tools/testing/selftests/drivers/net/hw/nic_timestamp.py

@@ -0,0 +1,225 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+# pylint: disable=locally-disabled, invalid-name, attribute-defined-outside-init, too-few-public-methods
+
+"""
+Tests related to configuration of HW timestamping
+"""
+
+import errno
+import ctypes
+import fcntl
+import socket
+from lib.py import ksft_run, ksft_exit, ksft_ge, ksft_eq, KsftSkipEx
+from lib.py import NetDrvEnv, EthtoolFamily, NlError
+
+
+SIOCSHWTSTAMP = 0x89b0
+SIOCGHWTSTAMP = 0x89b1
+class hwtstamp_config(ctypes.Structure):
+    """ Python copy of struct hwtstamp_config """
+    _fields_ = [
+        ("flags", ctypes.c_int),
+        ("tx_type", ctypes.c_int),
+        ("rx_filter", ctypes.c_int),
+    ]
+
+
+class ifreq(ctypes.Structure):
+    """ Python copy of struct ifreq """
+    _fields_ = [
+        ("ifr_name", ctypes.c_char * 16),
+        ("ifr_data", ctypes.POINTER(hwtstamp_config)),
+    ]
+
+
+def __get_hwtimestamp_support(cfg):
+    """ Retrieve supported configuration information """
+
+    try:
+        tsinfo = cfg.ethnl.tsinfo_get({'header': {'dev-name': cfg.ifname}})
+    except NlError as e:
+        if e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("timestamping configuration is not supported") from e
+        raise
+
+    ctx = {}
+    tx = tsinfo.get('tx-types', {})
+    rx = tsinfo.get('rx-filters', {})
+
+    bits = tx.get('bits', {})
+    ctx['tx'] = bits.get('bit', [])
+    bits = rx.get('bits', {})
+    ctx['rx'] = bits.get('bit', [])
+    return ctx
+
+
+def __get_hwtimestamp_config_ioctl(cfg):
+    """ Retrieve current TS configuration information (via ioctl) """
+
+    config = hwtstamp_config()
+
+    req = ifreq()
+    req.ifr_name = cfg.ifname.encode()
+    req.ifr_data = ctypes.pointer(config)
+
+    try:
+        sock = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
+        fcntl.ioctl(sock.fileno(), SIOCGHWTSTAMP, req)
+        sock.close()
+
+    except OSError as e:
+        if e.errno == errno.EOPNOTSUPP:
+            raise KsftSkipEx("timestamping configuration is not supported via ioctl") from e
+        raise
+    return config
+
+
+def __get_hwtimestamp_config(cfg):
+    """ Retrieve current TS configuration information (via netLink) """
+
+    try:
+        tscfg = cfg.ethnl.tsconfig_get({'header': {'dev-name': cfg.ifname}})
+    except NlError as e:
+        if e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("timestamping configuration is not supported via netlink") from e
+        raise
+    return tscfg
+
+
+def __set_hwtimestamp_config_ioctl(cfg, ts):
+    """ Setup new TS configuration information (via ioctl) """
+    config = hwtstamp_config()
+    config.rx_filter = ts['rx-filters']['bits']['bit'][0]['index']
+    config.tx_type = ts['tx-types']['bits']['bit'][0]['index']
+    req = ifreq()
+    req.ifr_name = cfg.ifname.encode()
+    req.ifr_data = ctypes.pointer(config)
+    try:
+        sock = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
+        fcntl.ioctl(sock.fileno(), SIOCSHWTSTAMP, req)
+        sock.close()
+
+    except OSError as e:
+        if e.errno == errno.EOPNOTSUPP:
+            raise KsftSkipEx("timestamping configuration is not supported via ioctl") from e
+        raise
+
+
+def __set_hwtimestamp_config(cfg, ts):
+    """ Setup new TS configuration information (via netlink) """
+
+    ts['header'] = {'dev-name': cfg.ifname}
+    try:
+        res = cfg.ethnl.tsconfig_set(ts)
+    except NlError as e:
+        if e.error == errno.EOPNOTSUPP:
+            raise KsftSkipEx("timestamping configuration is not supported via netlink") from e
+        raise
+    return res
+
+
+def __perform_hwtstamp_tx(cfg, is_ioctl):
+    """
+    Test TX timestamp configuration via either netlink or ioctl.
+    The driver should apply provided config and report back proper state.
+    """
+
+    orig_tscfg = __get_hwtimestamp_config(cfg)
+    ts = __get_hwtimestamp_support(cfg)
+    tx = ts['tx']
+    for t in tx:
+        res = None
+        tscfg = orig_tscfg
+        tscfg['tx-types']['bits']['bit'] = [t]
+        if is_ioctl:
+            __set_hwtimestamp_config_ioctl(cfg, tscfg)
+        else:
+            res = __set_hwtimestamp_config(cfg, tscfg)
+        if res is None:
+            res = __get_hwtimestamp_config(cfg)
+        resioctl = __get_hwtimestamp_config_ioctl(cfg)
+        ksft_eq(res['tx-types']['bits']['bit'], [t])
+        ksft_eq(resioctl.tx_type, t['index'])
+    __set_hwtimestamp_config(cfg, orig_tscfg)
+
+def test_hwtstamp_tx_netlink(cfg):
+    """
+    Test TX timestamp configuration setup via netlink.
+    The driver should apply provided config and report back proper state.
+    """
+    __perform_hwtstamp_tx(cfg, False)
+
+
+def test_hwtstamp_tx_ioctl(cfg):
+    """
+    Test TX timestamp configuration setup via ioctl.
+    The driver should apply provided config and report back proper state.
+    """
+    __perform_hwtstamp_tx(cfg, True)
+
+
+def __perform_hwtstamp_rx(cfg, is_ioctl):
+    """
+    Test RX timestamp configuration.
+    The filter configuration is taken from the list of supported filters.
+    The driver should apply the config without error and report back proper state.
+    Some extension of the timestamping scope is allowed for PTP filters.
+    """
+
+    orig_tscfg = __get_hwtimestamp_config(cfg)
+    ts = __get_hwtimestamp_support(cfg)
+    rx = ts['rx']
+    for r in rx:
+        res = None
+        tscfg = orig_tscfg
+        tscfg['rx-filters']['bits']['bit'] = [r]
+        if is_ioctl:
+            __set_hwtimestamp_config_ioctl(cfg, tscfg)
+        else:
+            res = __set_hwtimestamp_config(cfg, tscfg)
+        if res is None:
+            res = __get_hwtimestamp_config(cfg)
+        resioctl = __get_hwtimestamp_config_ioctl(cfg)
+        ksft_eq(resioctl.rx_filter, res['rx-filters']['bits']['bit'][0]['index'])
+        if r['index'] == 0 or r['index'] == 1:
+            ksft_eq(res['rx-filters']['bits']['bit'][0]['index'], r['index'])
+        else:
+            # the driver can fallback to some value which has higher coverage for timestamping
+            ksft_ge(res['rx-filters']['bits']['bit'][0]['index'], r['index'])
+    __set_hwtimestamp_config(cfg, orig_tscfg)
+
+
+def test_hwtstamp_rx_netlink(cfg):
+    """
+    Test RX timestamp configuration via netlink.
+    The filter configuration is taken from the list of supported filters.
+    The driver should apply the config without error and report back proper state.
+    Some extension of the timestamping scope is allowed for PTP filters.
+    """
+    __perform_hwtstamp_rx(cfg, False)
+
+
+def test_hwtstamp_rx_ioctl(cfg):
+    """
+    Test RX timestamp configuration via ioctl.
+    The filter configuration is taken from the list of supported filters.
+    The driver should apply the config without error and report back proper state.
+    Some extension of the timestamping scope is allowed for PTP filters.
+    """
+    __perform_hwtstamp_rx(cfg, True)
+
+
+def main() -> None:
+    """ Ksft boiler plate main """
+
+    with NetDrvEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        ksft_run([test_hwtstamp_tx_ioctl, test_hwtstamp_tx_netlink,
+                  test_hwtstamp_rx_ioctl, test_hwtstamp_rx_netlink],
+                 args=(cfg,))
+        ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/nk_devmem.py

@@ -0,0 +1,46 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+"""Test devmem TCP with netkit."""
+
+import os
+from devmem_lib import setup_test, run_rx, run_tx, run_tx_chunks, run_rx_hds
+from lib.py import ksft_run, ksft_exit, ksft_disruptive
+from lib.py import NetDrvContEnv
+
+
+@ksft_disruptive
+def check_nk_rx(cfg) -> None:
+    """Run the devmem RX test through netkit."""
+    run_rx(cfg)
+
+
+@ksft_disruptive
+def check_nk_tx(cfg) -> None:
+    """Run the devmem TX test through netkit."""
+    run_tx(cfg)
+
+
+@ksft_disruptive
+def check_nk_tx_chunks(cfg) -> None:
+    """Run the devmem TX chunking test through netkit."""
+    run_tx_chunks(cfg)
+
+
+def check_nk_rx_hds(cfg) -> None:
+    """Run the HDS test through netkit."""
+    run_rx_hds(cfg)
+
+
+def main() -> None:
+    """Run the netkit devmem test cases."""
+    with NetDrvContEnv(__file__, rxqueues=2, primary_rx_redirect=True) as cfg:
+        setup_test(cfg,
+                   os.path.join(os.path.dirname(os.path.abspath(__file__)),
+                                "ncdevmem"))
+        ksft_run([check_nk_rx, check_nk_tx, check_nk_tx_chunks,
+                  check_nk_rx_hds], args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/nk_forward.bpf.c

@@ -0,0 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+#include <linux/if_ether.h>
+#include <linux/ipv6.h>
+#include <linux/in6.h>
+#include <bpf/bpf_endian.h>
+#include <bpf/bpf_helpers.h>
+
+#define TC_ACT_OK 0
+#define ETH_P_IPV6 0x86DD
+
+#define ctx_ptr(field)		((void *)(long)(field))
+
+#define v6_p64_equal(a, b)	(a.s6_addr32[0] == b.s6_addr32[0] && \
+				 a.s6_addr32[1] == b.s6_addr32[1])
+
+volatile __u32 netkit_ifindex;
+volatile __u8 ipv6_prefix[16];
+
+SEC("tc/ingress")
+int tc_redirect_peer(struct __sk_buff *skb)
+{
+	void *data_end = ctx_ptr(skb->data_end);
+	void *data = ctx_ptr(skb->data);
+	struct in6_addr *peer_addr;
+	struct ipv6hdr *ip6h;
+	struct ethhdr *eth;
+
+	peer_addr = (struct in6_addr *)ipv6_prefix;
+
+	if (skb->protocol != bpf_htons(ETH_P_IPV6))
+		return TC_ACT_OK;
+
+	eth = data;
+	if ((void *)(eth + 1) > data_end)
+		return TC_ACT_OK;
+
+	ip6h = data + sizeof(struct ethhdr);
+	if ((void *)(ip6h + 1) > data_end)
+		return TC_ACT_OK;
+
+	if (!v6_p64_equal(ip6h->daddr, (*peer_addr)))
+		return TC_ACT_OK;
+
+	return bpf_redirect_peer(netkit_ifindex, 0);
+}
+
+char __license[] SEC("license") = "GPL";

linux-7.2.3/tools/testing/selftests/drivers/net/hw/nk_netns.py

@@ -0,0 +1,29 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Test exercising NetDrvContEnv() itself, a NetDrvContEnv() selftest.
+"""
+
+from lib.py import ksft_run, ksft_exit
+from lib.py import NetDrvContEnv
+from lib.py import cmd
+
+
+def test_ping(cfg) -> None:
+    """ Run ping between the container and the remote system. """
+    cfg.require_ipver("6")
+
+    cmd(f"ping -c 1 -W5 {cfg.nk_guest_ipv6}", host=cfg.remote)
+    cmd(f"ping -c 1 -W5 {cfg.remote_addr_v['6']}", ns=cfg.netns)
+
+
+def main() -> None:
+    """ Ksft boiler plate main """
+    with NetDrvContEnv(__file__) as cfg:
+        ksft_run([test_ping], args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/nk_primary_rx_redirect.bpf.c

@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ipv6.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+#define ctx_ptr(field)		((void *)(long)(field))
+
+volatile __u32 phys_ifindex;
+
+SEC("tc/ingress")
+int nk_primary_rx_redirect(struct __sk_buff *skb)
+{
+	void *data_end = ctx_ptr(skb->data_end);
+	void *data = ctx_ptr(skb->data);
+	struct ethhdr *eth;
+	struct ipv6hdr *ip6h;
+
+	eth = data;
+	if ((void *)(eth + 1) > data_end)
+		return TC_ACT_OK;
+
+	if (eth->h_proto != bpf_htons(ETH_P_IPV6))
+		return TC_ACT_OK;
+
+	ip6h = data + sizeof(struct ethhdr);
+	if ((void *)(ip6h + 1) > data_end)
+		return TC_ACT_OK;
+
+	if (ip6h->nexthdr == IPPROTO_ICMPV6)
+		return TC_ACT_OK;
+
+	return bpf_redirect_neigh(phys_ifindex, NULL, 0, 0);
+}
+
+char __license[] SEC("license") = "GPL";

linux-7.2.3/tools/testing/selftests/drivers/net/hw/nk_qlease.py

@@ -0,0 +1,465 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import re
+import time
+import threading
+from os import path
+from lib.py import (
+    ksft_run,
+    ksft_exit,
+    ksft_eq,
+    ksft_in,
+    ksft_not_in,
+    ksft_raises,
+)
+from lib.py import (
+    NetDrvContEnv,
+    NetNSEnter,
+    EthtoolFamily,
+    NetdevFamily,
+    RtnlFamily,
+)
+from lib.py import (
+    Netlink,
+    bkg,
+    cmd,
+    defer,
+    ethtool,
+    ip,
+    rand_port,
+    wait_port_listen,
+)
+from lib.py import KsftSkipEx, CmdExitFailure
+
+# iou-zcrx exits with 42 from setup_zcrx() when the NIC does not advertise
+# QCFG_RX_PAGE_SIZE (or otherwise rejects the requested rx_buf_len).
+SKIP_CODE = 42
+
+
+def _restore_hugepages(count):
+    with open("/proc/sys/vm/nr_hugepages", "w", encoding="utf-8") as f:
+        f.write(str(count))
+
+
+def _mp_clear_wait(cfg, src_queue):
+    """Wait for the io_uring memory provider to clear from the leased
+    physical queue; io_uring tears it down asynchronously after the
+    process holding the ifq exits."""
+    netdevnl = NetdevFamily()
+    deadline = time.time() + 5
+    while time.time() < deadline:
+        queue_info = netdevnl.queue_get(
+            {"ifindex": cfg.ifindex, "id": src_queue, "type": "rx"}
+        )
+        if "io-uring" not in queue_info:
+            return
+        time.sleep(0.1)
+    raise TimeoutError("Timed out waiting for memory provider to clear")
+
+
+def _create_netkit_pair(cfg, rxqueues=2):
+    if cfg.nk_host_ifname:
+        cmd(f"ip link del dev {cfg.nk_host_ifname}", fail=False)
+        cfg.nk_host_ifname = None
+        cfg.nk_guest_ifname = None
+    cfg.detach_bpf()
+
+    all_links = ip("-d link show", json=True)
+    old_idxs = {
+        link["ifindex"]
+        for link in all_links
+        if link.get("linkinfo", {}).get("info_kind") == "netkit"
+    }
+
+    rtnl = RtnlFamily()
+    rtnl.newlink(
+        {
+            "linkinfo": {
+                "kind": "netkit",
+                "data": {
+                    "mode": "l2",
+                    "policy": "forward",
+                    "peer-policy": "forward",
+                },
+            },
+            "num-rx-queues": rxqueues,
+        },
+        flags=[Netlink.NLM_F_CREATE, Netlink.NLM_F_EXCL],
+    )
+
+    all_links = ip("-d link show", json=True)
+    nk_links = [
+        link
+        for link in all_links
+        if link.get("linkinfo", {}).get("info_kind") == "netkit"
+        and link["ifindex"] not in old_idxs
+    ]
+    if len(nk_links) != 2:
+        raise KsftSkipEx("Failed to create netkit pair")
+
+    nk_links.sort(key=lambda x: x["ifindex"])
+    cfg.nk_host_ifname = nk_links[1]["ifname"]
+    cfg.nk_guest_ifname = nk_links[0]["ifname"]
+    cfg.nk_host_ifindex = nk_links[1]["ifindex"]
+    cfg.nk_guest_ifindex = nk_links[0]["ifindex"]
+
+    ip(f"link set dev {cfg.nk_guest_ifname} netns {cfg.netns.name}")
+    ip(f"link set dev {cfg.nk_host_ifname} up")
+    ip(f"-6 addr add fe80::1/64 dev {cfg.nk_host_ifname} nodad")
+    ip(
+        f"-6 route add {cfg.nk_guest_ipv6}/128 via fe80::2 "
+        f"dev {cfg.nk_host_ifname}"
+    )
+    ip(f"link set dev {cfg.nk_guest_ifname} up", ns=cfg.netns)
+    ip(f"-6 addr add fe80::2/64 dev {cfg.nk_guest_ifname}", ns=cfg.netns)
+    ip(
+        f"-6 addr add {cfg.nk_guest_ipv6}/64 dev {cfg.nk_guest_ifname} nodad",
+        ns=cfg.netns,
+    )
+    ip(
+        f"-6 route add default via fe80::1 dev {cfg.nk_guest_ifname}",
+        ns=cfg.netns,
+    )
+
+    cfg.attach_bpf()
+
+
+def _setup_lease(cfg, rxqueues=2):
+    _create_netkit_pair(cfg, rxqueues=rxqueues)
+
+    ethnl = EthtoolFamily()
+    channels = ethnl.channels_get({"header": {"dev-index": cfg.ifindex}})[
+        "combined-count"
+    ]
+    if channels < 2:
+        raise KsftSkipEx(
+            "Test requires NETIF with at least 2 combined channels"
+        )
+    src_queue = channels - 1
+
+    with NetNSEnter(str(cfg.netns)):
+        netdevnl = NetdevFamily()
+        bind_result = netdevnl.queue_create(
+            {
+                "ifindex": cfg.nk_guest_ifindex,
+                "type": "rx",
+                "lease": {
+                    "ifindex": cfg.ifindex,
+                    "queue": {"id": src_queue, "type": "rx"},
+                    "netns-id": 0,
+                },
+            }
+        )
+    return src_queue, bind_result["id"]
+
+
+def _teardown_netkit(cfg):
+    if cfg.nk_host_ifname:
+        cmd(f"ip link del dev {cfg.nk_host_ifname}", fail=False)
+        cfg.nk_host_ifname = None
+        cfg.nk_guest_ifname = None
+
+
+def set_flow_rule(cfg, src_queue):
+    output = ethtool(
+        f"-N {cfg.ifname} flow-type tcp6 dst-port {cfg.port} action {src_queue}"
+    ).stdout
+    values = re.search(r"ID (\d+)", output).group(1)
+    return int(values)
+
+
+def test_iou_zcrx(cfg) -> None:
+    cfg.require_ipver("6")
+    src_queue, nk_queue = _setup_lease(cfg)
+    defer(_teardown_netkit, cfg)
+    ethnl = EthtoolFamily()
+
+    rings = ethnl.rings_get({"header": {"dev-index": cfg.ifindex}})
+    rx_rings = rings["rx"]
+    hds_thresh = rings.get("hds-thresh", 0)
+
+    ethnl.rings_set(
+        {
+            "header": {"dev-index": cfg.ifindex},
+            "tcp-data-split": "enabled",
+            "hds-thresh": 0,
+            "rx": 64,
+        }
+    )
+    defer(
+        ethnl.rings_set,
+        {
+            "header": {"dev-index": cfg.ifindex},
+            "tcp-data-split": "unknown",
+            "hds-thresh": hds_thresh,
+            "rx": rx_rings,
+        },
+    )
+
+    ethtool(f"-X {cfg.ifname} equal {src_queue}")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    flow_rule_id = set_flow_rule(cfg, src_queue)
+    defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}")
+
+    rx_cmd = (
+        f"{cfg.bin_local} -s -p {cfg.port} "
+        f"-i {cfg.nk_guest_ifname} -q {nk_queue}"
+    )
+    tx_cmd = f"{cfg.bin_remote} -c -h {cfg.nk_guest_ipv6} -p {cfg.port} -l 12840"
+    with bkg(rx_cmd, exit_wait=True, ns=cfg.netns):
+        wait_port_listen(cfg.port, proto="tcp", ns=cfg.netns)
+        cmd(tx_cmd, host=cfg.remote)
+
+
+def test_iou_zcrx_large_buf(cfg) -> None:
+    """iou-zcrx with rx_buf_len > page size, going through a netkit-leased
+    queue. Exercises the queue rx-buf-len path via netif_mp_open_rxq()'s
+    lease redirect: the netkit ifindex is opaque to io_uring, but
+    rx_page_size is honoured by the *physical* qops because the lease
+    pointer rewrites the request from netkit onto the leased physical
+    rxq before supported_params/validate_qcfg are consulted.
+    """
+    cfg.require_ipver("6")
+    src_queue, nk_queue = _setup_lease(cfg)
+    defer(_teardown_netkit, cfg)
+    ethnl = EthtoolFamily()
+
+    with open("/proc/sys/vm/nr_hugepages", "r+", encoding="utf-8") as f:
+        nr_hugepages = int(f.read().strip())
+        if nr_hugepages < 64:
+            f.seek(0)
+            f.write("64")
+            defer(_restore_hugepages, nr_hugepages)
+
+    rings = ethnl.rings_get({"header": {"dev-index": cfg.ifindex}})
+    rx_rings = rings["rx"]
+    hds_thresh = rings.get("hds-thresh", 0)
+
+    ethnl.rings_set(
+        {
+            "header": {"dev-index": cfg.ifindex},
+            "tcp-data-split": "enabled",
+            "hds-thresh": 0,
+            "rx": 64,
+        }
+    )
+    defer(
+        ethnl.rings_set,
+        {
+            "header": {"dev-index": cfg.ifindex},
+            "tcp-data-split": "unknown",
+            "hds-thresh": hds_thresh,
+            "rx": rx_rings,
+        },
+    )
+
+    ethtool(f"-X {cfg.ifname} equal {src_queue}")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    flow_rule_id = set_flow_rule(cfg, src_queue)
+    defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}")
+
+    # -x 2 asks iou-zcrx for rx_buf_len = 2 * page_size (8 KiB on x86_64),
+    # backed by a 2 MiB hugepage area so the chunks are physically
+    # contiguous, which is what zcrx requires for non-default rx_buf_len.
+    rx_cmd = (
+        f"{cfg.bin_local} -s -p {cfg.port} "
+        f"-i {cfg.nk_guest_ifname} -q {nk_queue} -x 2"
+    )
+    tx_cmd = f"{cfg.bin_remote} -c -h {cfg.nk_guest_ipv6} -p {cfg.port} -l 12840"
+
+    # Probe via -d (dry run): exits with SKIP_CODE if the leased physical
+    # qops doesn't advertise QCFG_RX_PAGE_SIZE (e.g. older bnxt FW/HW).
+    probe = cmd(rx_cmd + " -d", fail=False, ns=cfg.netns)
+    if probe.ret == SKIP_CODE:
+        msg = probe.stdout.strip() or "rx_buf_len not supported by leased NIC"
+        raise KsftSkipEx(msg)
+
+    # A successful dry run still registered the zcrx ifq on the leased
+    # physical queue; wait for its async teardown before the real server
+    # binds the same queue.
+    _mp_clear_wait(cfg, src_queue)
+
+    with bkg(rx_cmd, exit_wait=True, ns=cfg.netns):
+        wait_port_listen(cfg.port, proto="tcp", ns=cfg.netns)
+        cmd(tx_cmd, host=cfg.remote)
+
+
+def test_attrs(cfg) -> None:
+    cfg.require_ipver("6")
+    src_queue, nk_queue = _setup_lease(cfg)
+    defer(_teardown_netkit, cfg)
+    netdevnl = NetdevFamily()
+    queue_info = netdevnl.queue_get(
+        {"ifindex": cfg.ifindex, "id": src_queue, "type": "rx"}
+    )
+
+    ksft_eq(queue_info["id"], src_queue)
+    ksft_eq(queue_info["type"], "rx")
+    ksft_eq(queue_info["ifindex"], cfg.ifindex)
+
+    ksft_in("lease", queue_info)
+    lease = queue_info["lease"]
+    ksft_eq(lease["ifindex"], cfg.nk_guest_ifindex)
+    ksft_eq(lease["queue"]["id"], nk_queue)
+    ksft_eq(lease["queue"]["type"], "rx")
+    ksft_in("netns-id", lease)
+
+
+def test_attach_xdp_with_mp(cfg) -> None:
+    cfg.require_ipver("6")
+    src_queue, nk_queue = _setup_lease(cfg)
+    defer(_teardown_netkit, cfg)
+    ethnl = EthtoolFamily()
+
+    rings = ethnl.rings_get({"header": {"dev-index": cfg.ifindex}})
+    rx_rings = rings["rx"]
+    hds_thresh = rings.get("hds-thresh", 0)
+
+    ethnl.rings_set(
+        {
+            "header": {"dev-index": cfg.ifindex},
+            "tcp-data-split": "enabled",
+            "hds-thresh": 0,
+            "rx": 64,
+        }
+    )
+    defer(
+        ethnl.rings_set,
+        {
+            "header": {"dev-index": cfg.ifindex},
+            "tcp-data-split": "unknown",
+            "hds-thresh": hds_thresh,
+            "rx": rx_rings,
+        },
+    )
+
+    ethtool(f"-X {cfg.ifname} equal {src_queue}")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    netdevnl = NetdevFamily()
+
+    rx_cmd = (
+        f"{cfg.bin_local} -s -p {cfg.port} "
+        f"-i {cfg.nk_guest_ifname} -q {nk_queue}"
+    )
+    with bkg(rx_cmd, ns=cfg.netns):
+        wait_port_listen(cfg.port, proto="tcp", ns=cfg.netns)
+
+        time.sleep(0.1)
+        queue_info = netdevnl.queue_get(
+            {"ifindex": cfg.ifindex, "id": src_queue, "type": "rx"}
+        )
+        ksft_in("io-uring", queue_info)
+
+        prog = cfg.net_lib_dir / "xdp_dummy.bpf.o"
+        with ksft_raises(CmdExitFailure):
+            ip(f"link set dev {cfg.ifname} xdp obj {prog} sec xdp.frags")
+
+    time.sleep(0.1)
+    queue_info = netdevnl.queue_get(
+        {"ifindex": cfg.ifindex, "id": src_queue, "type": "rx"}
+    )
+    ksft_not_in("io-uring", queue_info)
+
+
+def test_destroy(cfg) -> None:
+    cfg.require_ipver("6")
+    src_queue, nk_queue = _setup_lease(cfg)
+    defer(_teardown_netkit, cfg)
+    ethnl = EthtoolFamily()
+
+    rings = ethnl.rings_get({"header": {"dev-index": cfg.ifindex}})
+    rx_rings = rings["rx"]
+    hds_thresh = rings.get("hds-thresh", 0)
+
+    ethnl.rings_set(
+        {
+            "header": {"dev-index": cfg.ifindex},
+            "tcp-data-split": "enabled",
+            "hds-thresh": 0,
+            "rx": 64,
+        }
+    )
+    defer(
+        ethnl.rings_set,
+        {
+            "header": {"dev-index": cfg.ifindex},
+            "tcp-data-split": "unknown",
+            "hds-thresh": hds_thresh,
+            "rx": rx_rings,
+        },
+    )
+
+    ethtool(f"-X {cfg.ifname} equal {src_queue}")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    rx_cmd = (
+        f"{cfg.bin_local} -s -p {cfg.port} "
+        f"-i {cfg.nk_guest_ifname} -q {nk_queue}"
+    )
+    rx_proc = cmd(rx_cmd, background=True, ns=cfg.netns)
+    wait_port_listen(cfg.port, proto="tcp", ns=cfg.netns)
+
+    netdevnl = NetdevFamily()
+    queue_info = netdevnl.queue_get(
+        {"ifindex": cfg.ifindex, "id": src_queue, "type": "rx"}
+    )
+    ksft_in("io-uring", queue_info)
+
+    # ip link del will wait for all refs to drop first, but iou-zcrx is holding
+    # onto a ref. Terminate iou-zcrx async via a thread after a delay.
+    kill_timer = threading.Timer(1, rx_proc.proc.terminate)
+    kill_timer.start()
+
+    ip(f"link del dev {cfg.nk_host_ifname}")
+    kill_timer.join()
+    cfg.nk_host_ifname = None
+    cfg.nk_guest_ifname = None
+
+    queue_info = netdevnl.queue_get(
+        {"ifindex": cfg.ifindex, "id": src_queue, "type": "rx"}
+    )
+    ksft_not_in("io-uring", queue_info)
+
+    flow_rule_id = set_flow_rule(cfg, src_queue)
+    defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}")
+
+    rx_cmd = f"{cfg.bin_local} -s -p {cfg.port} -i {cfg.ifname} -q {src_queue}"
+    tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {cfg.port} -l 12840"
+    with bkg(rx_cmd, exit_wait=True):
+        wait_port_listen(cfg.port, proto="tcp")
+        cmd(tx_cmd, host=cfg.remote)
+    # Short delay since iou cleanup is async and takes a bit of time.
+    time.sleep(0.1)
+    queue_info = netdevnl.queue_get(
+        {"ifindex": cfg.ifindex, "id": src_queue, "type": "rx"}
+    )
+    ksft_not_in("io-uring", queue_info)
+
+
+def main() -> None:
+    with NetDrvContEnv(__file__, rxqueues=2) as cfg:
+        cfg.bin_local = path.abspath(
+            path.dirname(__file__) + "/../../../drivers/net/hw/iou-zcrx"
+        )
+        cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
+        cfg.port = rand_port()
+
+        ksft_run(
+            [
+                test_iou_zcrx,
+                test_iou_zcrx_large_buf,
+                test_attrs,
+                test_attach_xdp_with_mp,
+                test_destroy,
+            ],
+            args=(cfg,),
+        )
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/ntuple.py

@@ -0,0 +1,165 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+"""Test ethtool NFC (ntuple) flow steering rules."""
+
+import random
+from enum import Enum, auto
+from lib.py import ksft_run, ksft_exit
+from lib.py import ksft_eq, ksft_ge
+from lib.py import ksft_variants, KsftNamedVariant
+from lib.py import EthtoolFamily, NetDrvEpEnv, NetdevFamily
+from lib.py import KsftSkipEx
+from lib.py import cmd, ethtool, defer, rand_ports, bkg, wait_port_listen
+
+
+class NtupleField(Enum):
+    SRC_IP = auto()
+    DST_IP = auto()
+    SRC_PORT = auto()
+    DST_PORT = auto()
+
+
+def _require_ntuple(cfg):
+    features = ethtool(f"-k {cfg.ifname}", json=True)[0]
+    if not features["ntuple-filters"]["active"]:
+        if features["ntuple-filters"]["fixed"]:
+            raise KsftSkipEx("Device does not support ntuple-filters")
+        ethtool(f"-K {cfg.ifname} ntuple-filters on")
+        defer(ethtool, f"-K {cfg.ifname} ntuple-filters off")
+
+
+def _get_rx_cnts(cfg, prev=None):
+    """Get Rx packet counts for all queues, as a simple list of integers
+       if @prev is specified the prev counts will be subtracted"""
+    cfg.wait_hw_stats_settle()
+    data = cfg.netdevnl.qstats_get({"ifindex": cfg.ifindex, "scope": ["queue"]}, dump=True)
+    data = [x for x in data if x['queue-type'] == "rx"]
+    max_q = max([x["queue-id"] for x in data])
+    queue_stats = [0] * (max_q + 1)
+    for q in data:
+        queue_stats[q["queue-id"]] = q["rx-packets"]
+        if prev and q["queue-id"] < len(prev):
+            queue_stats[q["queue-id"]] -= prev[q["queue-id"]]
+    return queue_stats
+
+
+def _ntuple_rule_add(cfg, flow_spec):
+    """Install an NFC rule via ethtool."""
+
+    output = ethtool(f"-N {cfg.ifname} {flow_spec}").stdout
+    rule_id = int(output.split()[-1])
+    defer(ethtool, f"-N {cfg.ifname} delete {rule_id}")
+
+
+def _setup_isolated_queue(cfg):
+    """Default all traffic to queue 0, and pick a random queue to
+       steer NFC traffic to."""
+
+    channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    ch_max = channels['combined-max']
+    qcnt = channels['combined-count']
+
+    if ch_max < 2:
+        raise KsftSkipEx(f"Need at least 2 combined channels, max is {ch_max}")
+
+    desired_queues = min(ch_max, 4)
+    if qcnt >= desired_queues:
+        desired_queues = qcnt
+    else:
+        ethtool(f"-L {cfg.ifname} combined {desired_queues}")
+        defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+
+    ethtool(f"-X {cfg.ifname} equal 1")
+    defer(ethtool, f"-X {cfg.ifname} default")
+
+    return random.randint(1, desired_queues - 1)
+
+
+def _send_traffic(cfg, ipver, proto, dst_port, src_port, pkt_cnt=40):
+    """Generate traffic with the desired flow signature."""
+
+    cfg.require_cmd("socat", remote=True)
+
+    socat_proto = proto.upper()
+    dst_addr = f"[{cfg.addr_v['6']}]" if ipver == '6' else cfg.addr_v['4']
+
+    extra_opts = ",nodelay" if proto == "tcp" else ",shut-null"
+
+    listen_cmd = (f"socat -{ipver} -t 2 -u "
+                  f"{socat_proto}-LISTEN:{dst_port},reuseport /dev/null")
+    with bkg(listen_cmd, exit_wait=True):
+        wait_port_listen(dst_port, proto=proto)
+        send_cmd = f"""
+        bash -c 'for i in $(seq {pkt_cnt}); do echo msg; sleep 0.02; done' |
+        socat -{ipver} -u - \
+            {socat_proto}:{dst_addr}:{dst_port},sourceport={src_port},reuseaddr{extra_opts}
+        """
+        cmd(send_cmd, shell=True, host=cfg.remote)
+
+
+def _add_ntuple_rule_and_send_traffic(cfg, ipver, proto, fields, test_queue):
+    ports = rand_ports(2)
+    src_port = ports[0]
+    dst_port = ports[1]
+    flow_parts = [f"flow-type {proto}{ipver}"]
+
+    for field in fields:
+        if field == NtupleField.SRC_IP:
+            flow_parts.append(f"src-ip {cfg.remote_addr_v[ipver]}")
+        elif field == NtupleField.DST_IP:
+            flow_parts.append(f"dst-ip {cfg.addr_v[ipver]}")
+        elif field == NtupleField.SRC_PORT:
+            flow_parts.append(f"src-port {src_port}")
+        elif field == NtupleField.DST_PORT:
+            flow_parts.append(f"dst-port {dst_port}")
+
+    flow_parts.append(f"action {test_queue}")
+    _ntuple_rule_add(cfg, " ".join(flow_parts))
+    _send_traffic(cfg, ipver, proto, dst_port=dst_port, src_port=src_port)
+
+
+def _ntuple_variants():
+    for ipver in ["4", "6"]:
+        for proto in ["tcp", "udp"]:
+            for fields in [[NtupleField.SRC_IP],
+                           [NtupleField.DST_IP],
+                           [NtupleField.SRC_PORT],
+                           [NtupleField.DST_PORT],
+                           [NtupleField.SRC_IP, NtupleField.DST_IP],
+                           [NtupleField.SRC_IP, NtupleField.DST_IP,
+                            NtupleField.SRC_PORT, NtupleField.DST_PORT]]:
+                name = ".".join(f.name.lower() for f in fields)
+                yield KsftNamedVariant(f"{proto}{ipver}.{name}",
+                                      ipver, proto, fields)
+
+
+@ksft_variants(_ntuple_variants())
+def queue(cfg, ipver, proto, fields):
+    """Test that an NFC rule steers traffic to the correct queue."""
+
+    cfg.require_ipver(ipver)
+    _require_ntuple(cfg)
+
+    test_queue = _setup_isolated_queue(cfg)
+
+    cnts = _get_rx_cnts(cfg)
+    _add_ntuple_rule_and_send_traffic(cfg, ipver, proto, fields, test_queue)
+    cnts = _get_rx_cnts(cfg, prev=cnts)
+
+    ksft_ge(cnts[test_queue], 40, f"Traffic on test queue {test_queue}: {cnts}")
+    sum_idle = sum(cnts) - cnts[0] - cnts[test_queue]
+    ksft_eq(sum_idle, 0, f"Traffic on idle queues: {cnts}")
+
+
+def main() -> None:
+    """Ksft boilerplate main."""
+
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        cfg.netdevnl = NetdevFamily()
+        ksft_run([queue], args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/pp_alloc_fail.py

@@ -0,0 +1,144 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Test driver resilience vs page pool allocation failures.
+"""
+
+import errno
+import time
+import math
+import os
+from lib.py import ksft_run, ksft_exit, ksft_pr
+from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import NetdevFamily, NlError
+from lib.py import NetDrvEpEnv
+from lib.py import cmd, tool, GenerateTraffic
+
+
+def _write_fail_config(config):
+    for key, value in config.items():
+        path = "/sys/kernel/debug/fail_function/"
+        with open(path + key, "w", encoding='ascii') as fp:
+            fp.write(str(value) + "\n")
+
+
+def _enable_pp_allocation_fail():
+    if not os.path.exists("/sys/kernel/debug/fail_function"):
+        raise KsftSkipEx("Kernel built without function error injection (or DebugFS)")
+
+    if not os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_netmems"):
+        _write_fail_config({"inject": "page_pool_alloc_netmems"})
+
+    _write_fail_config({
+        "verbose": 0,
+        "interval": 511,
+        "probability": 100,
+        "times": -1,
+    })
+
+
+def _disable_pp_allocation_fail():
+    if not os.path.exists("/sys/kernel/debug/fail_function"):
+        return
+
+    if os.path.exists("/sys/kernel/debug/fail_function/page_pool_alloc_netmems"):
+        _write_fail_config({"inject": ""})
+
+    _write_fail_config({
+        "probability": 0,
+        "times": 0,
+    })
+
+
+def test_pp_alloc(cfg, netdevnl):
+    """
+    Configure page pool allocation fail injection while traffic is running.
+    """
+
+    def get_stats():
+        return netdevnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+
+    def check_traffic_flowing():
+        stat1 = get_stats()
+        time.sleep(1)
+        stat2 = get_stats()
+        if stat2['rx-packets'] - stat1['rx-packets'] < 4000:
+            raise KsftFailEx("Traffic seems low:", stat2['rx-packets'] - stat1['rx-packets'])
+
+
+    try:
+        stats = get_stats()
+    except NlError as e:
+        if e.nl_msg.error == -errno.EOPNOTSUPP:
+            stats = {}
+        else:
+            raise
+    if 'rx-alloc-fail' not in stats:
+        raise KsftSkipEx("Driver does not report 'rx-alloc-fail' via qstats")
+
+    set_g = False
+    traffic = None
+    try:
+        traffic = GenerateTraffic(cfg)
+
+        check_traffic_flowing()
+
+        _enable_pp_allocation_fail()
+
+        s1 = get_stats()
+        time.sleep(3)
+        s2 = get_stats()
+
+        seen_fails = s2['rx-alloc-fail'] - s1['rx-alloc-fail']
+        if seen_fails < 1:
+            raise KsftSkipEx("Allocation failures not increasing")
+        pkts = s2['rx-packets'] - s1['rx-packets']
+        # Expecting one failure per 512 buffers, 3.1x safety margin
+        want_fails = math.floor(pkts / 512 / 3.1)
+        if seen_fails < want_fails:
+            raise KsftSkipEx("Allocation increasing too slowly", seen_fails,
+                             "packets:", pkts)
+        ksft_pr(f"Seen: pkts:{pkts} fails:{seen_fails} (pass thrs:{want_fails})")
+
+        # Basic failures are fine, try to wobble some settings to catch extra failures
+        check_traffic_flowing()
+        g = tool("ethtool", "-g " + cfg.ifname, json=True)[0]
+        if 'rx' in g and g["rx"] * 2 <= g["rx-max"]:
+            new_g = g['rx'] * 2
+        elif 'rx' in g:
+            new_g = g['rx'] // 2
+        else:
+            new_g = None
+
+        if new_g:
+            set_g = cmd(f"ethtool -G {cfg.ifname} rx {new_g}", fail=False).ret == 0
+            if set_g:
+                ksft_pr("ethtool -G change retval: success")
+            else:
+                ksft_pr("ethtool -G change retval: did not succeed", new_g)
+        else:
+            ksft_pr("ethtool -G change retval: did not try")
+
+        time.sleep(0.1)
+        check_traffic_flowing()
+    finally:
+        _disable_pp_allocation_fail()
+        if traffic:
+            traffic.stop()
+        time.sleep(0.1)
+        if set_g:
+            cmd(f"ethtool -G {cfg.ifname} rx {g['rx']}")
+
+
+def main() -> None:
+    """ Ksft boiler plate main """
+    netdevnl = NetdevFamily()
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+
+        ksft_run([test_pp_alloc], args=(cfg, netdevnl, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/rss_api.py

@@ -0,0 +1,476 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+API level tests for RSS (mostly Netlink vs IOCTL).
+"""
+
+import errno
+import glob
+import random
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_is, ksft_ne, ksft_raises
+from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import defer, ethtool, CmdExitFailure
+from lib.py import EthtoolFamily, NlError
+from lib.py import NetDrvEnv
+
+
+def _require_2qs(cfg):
+    qcnt = len(glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*"))
+    if qcnt < 2:
+        raise KsftSkipEx(f"Local has only {qcnt} queues")
+    return qcnt
+
+
+def _ethtool_create(cfg, act, opts):
+    output = ethtool(f"{act} {cfg.ifname} {opts}").stdout
+    # Output will be something like: "New RSS context is 1" or
+    # "Added rule with ID 7", we want the integer from the end
+    return int(output.split()[-1])
+
+
+def _ethtool_get_cfg(cfg, fl_type, to_nl=False):
+    descr = ethtool(f"-n {cfg.ifname} rx-flow-hash {fl_type}").stdout
+
+    if to_nl:
+        converter = {
+            "IP SA": "ip-src",
+            "IP DA": "ip-dst",
+            "L4 bytes 0 & 1 [TCP/UDP src port]": "l4-b-0-1",
+            "L4 bytes 2 & 3 [TCP/UDP dst port]": "l4-b-2-3",
+        }
+
+        ret = set()
+    else:
+        converter = {
+            "IP SA": "s",
+            "IP DA": "d",
+            "L3 proto": "t",
+            "L4 bytes 0 & 1 [TCP/UDP src port]": "f",
+            "L4 bytes 2 & 3 [TCP/UDP dst port]": "n",
+        }
+
+        ret = ""
+
+    for line in descr.split("\n")[1:-2]:
+        # if this raises we probably need to add more keys to converter above
+        if to_nl:
+            ret.add(converter[line])
+        else:
+            ret += converter[line]
+    return ret
+
+
+def test_rxfh_nl_set_fail(cfg):
+    """
+    Test error path of Netlink SET.
+    """
+    _require_2qs(cfg)
+
+    ethnl = EthtoolFamily()
+    ethnl.ntf_subscribe("monitor")
+
+    with ksft_raises(NlError):
+        ethnl.rss_set({"header": {"dev-name": "lo"},
+                       "indir": None})
+
+    with ksft_raises(NlError):
+        ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                       "indir": [100000]})
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    ksft_is(ntf, None)
+
+
+def test_rxfh_nl_set_indir(cfg):
+    """
+    Test setting indirection table via Netlink.
+    """
+    qcnt = _require_2qs(cfg)
+
+    # Test some SETs with a value
+    reset = defer(cfg.ethnl.rss_set,
+                  {"header": {"dev-index": cfg.ifindex}, "indir": None})
+    cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                       "indir": [1]})
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    ksft_eq(set(rss.get("indir", [-1])), {1})
+
+    cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                       "indir": [0, 1]})
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    ksft_eq(set(rss.get("indir", [-1])), {0, 1})
+
+    # Make sure we can't set the queue count below max queue used
+    with ksft_raises(CmdExitFailure):
+        ethtool(f"-L {cfg.ifname} combined 0 rx 1")
+    with ksft_raises(CmdExitFailure):
+        ethtool(f"-L {cfg.ifname} combined 1 rx 0")
+
+    # Test reset back to default
+    reset.exec()
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    ksft_eq(set(rss.get("indir", [-1])), set(range(qcnt)))
+
+
+def test_rxfh_nl_set_indir_ctx(cfg):
+    """
+    Test setting indirection table for a custom context via Netlink.
+    """
+    _require_2qs(cfg)
+
+    # Get setting for ctx 0, we'll make sure they don't get clobbered
+    dflt = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+
+    # Create context
+    ctx_id = _ethtool_create(cfg, "-X", "context new")
+    defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete")
+
+    cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                       "context": ctx_id, "indir": [1]})
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex},
+                             "context": ctx_id})
+    ksft_eq(set(rss.get("indir", [-1])), {1})
+
+    ctx0 = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    ksft_eq(ctx0, dflt)
+
+    cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                       "context": ctx_id, "indir": [0, 1]})
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex},
+                             "context": ctx_id})
+    ksft_eq(set(rss.get("indir", [-1])), {0, 1})
+
+    ctx0 = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    ksft_eq(ctx0, dflt)
+
+    # Make sure we can't set the queue count below max queue used
+    with ksft_raises(CmdExitFailure):
+        ethtool(f"-L {cfg.ifname} combined 0 rx 1")
+    with ksft_raises(CmdExitFailure):
+        ethtool(f"-L {cfg.ifname} combined 1 rx 0")
+
+
+def test_rxfh_indir_ntf(cfg):
+    """
+    Check that Netlink notifications are generated when RSS indirection
+    table was modified.
+    """
+    _require_2qs(cfg)
+
+    ethnl = EthtoolFamily()
+    ethnl.ntf_subscribe("monitor")
+
+    ethtool(f"--disable-netlink -X {cfg.ifname} weight 0 1")
+    reset = defer(ethtool, f"-X {cfg.ifname} default")
+
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("No notification received")
+    ksft_eq(ntf["name"], "rss-ntf")
+    ksft_eq(set(ntf["msg"]["indir"]), {1})
+
+    reset.exec()
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("No notification received after reset")
+    ksft_eq(ntf["name"], "rss-ntf")
+    ksft_is(ntf["msg"].get("context"), None)
+    ksft_ne(set(ntf["msg"]["indir"]), {1})
+
+
+def test_rxfh_indir_ctx_ntf(cfg):
+    """
+    Check that Netlink notifications are generated when RSS indirection
+    table was modified on an additional RSS context.
+    """
+    _require_2qs(cfg)
+
+    ctx_id = _ethtool_create(cfg, "-X", "context new")
+    defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete")
+
+    ethnl = EthtoolFamily()
+    ethnl.ntf_subscribe("monitor")
+
+    ethtool(f"--disable-netlink -X {cfg.ifname} context {ctx_id} weight 0 1")
+
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("No notification received")
+    ksft_eq(ntf["name"], "rss-ntf")
+    ksft_eq(ntf["msg"].get("context"), ctx_id)
+    ksft_eq(set(ntf["msg"]["indir"]), {1})
+
+
+def test_rxfh_nl_set_key(cfg):
+    """
+    Test setting hashing key via Netlink.
+    """
+
+    dflt = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    defer(cfg.ethnl.rss_set,
+          {"header": {"dev-index": cfg.ifindex},
+           "hkey": dflt["hkey"], "indir": None})
+
+    # Empty key should error out
+    with ksft_raises(NlError) as cm:
+        cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                           "hkey": None})
+    ksft_eq(cm.exception.nl_msg.extack['bad-attr'], '.hkey')
+
+    # Set key to random
+    mod = random.randbytes(len(dflt["hkey"]))
+    cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                       "hkey": mod})
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    ksft_eq(rss.get("hkey", [-1]), mod)
+
+    # Set key to random and indir tbl to something at once
+    mod = random.randbytes(len(dflt["hkey"]))
+    cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                       "indir": [0, 1], "hkey": mod})
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    ksft_eq(rss.get("hkey", [-1]), mod)
+    ksft_eq(set(rss.get("indir", [-1])), {0, 1})
+
+
+def test_rxfh_fields(cfg):
+    """
+    Test reading Rx Flow Hash over Netlink.
+    """
+
+    flow_types = ["tcp4", "tcp6", "udp4", "udp6"]
+    ethnl = EthtoolFamily()
+
+    cfg_nl = ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    for fl_type in flow_types:
+        one = _ethtool_get_cfg(cfg, fl_type, to_nl=True)
+        ksft_eq(one, cfg_nl["flow-hash"][fl_type],
+                comment="Config for " + fl_type)
+
+
+def test_rxfh_fields_set(cfg):
+    """ Test configuring Rx Flow Hash over Netlink. """
+
+    flow_types = ["tcp4", "tcp6", "udp4", "udp6"]
+
+    # Collect current settings
+    cfg_old = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    # symmetric hashing is config-order-sensitive make sure we leave
+    # symmetric mode, or make the flow-hash sym-compatible first
+    changes = [{"flow-hash": cfg_old["flow-hash"],},
+               {"input-xfrm": cfg_old.get("input-xfrm", {}),}]
+    if cfg_old.get("input-xfrm"):
+        changes = list(reversed(changes))
+    for old in changes:
+        defer(cfg.ethnl.rss_set, {"header": {"dev-index": cfg.ifindex},} | old)
+
+    # symmetric hashing prevents some of the configs below
+    if cfg_old.get("input-xfrm"):
+        cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                           "input-xfrm": {}})
+
+    for fl_type in flow_types:
+        cur = _ethtool_get_cfg(cfg, fl_type)
+        if cur == "sdfn":
+            change_nl = {"ip-src", "ip-dst"}
+            change_ic = "sd"
+        else:
+            change_nl = {"l4-b-0-1", "l4-b-2-3", "ip-src", "ip-dst"}
+            change_ic = "sdfn"
+
+        cfg.ethnl.rss_set({
+            "header": {"dev-index": cfg.ifindex},
+            "flow-hash": {fl_type: change_nl}
+        })
+        reset = defer(ethtool, f"--disable-netlink -N {cfg.ifname} "
+                      f"rx-flow-hash {fl_type} {cur}")
+
+        cfg_nl = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+        ksft_eq(change_nl, cfg_nl["flow-hash"][fl_type],
+                comment=f"Config for {fl_type} over Netlink")
+        cfg_ic = _ethtool_get_cfg(cfg, fl_type)
+        ksft_eq(change_ic, cfg_ic,
+                comment=f"Config for {fl_type} over IOCTL")
+
+        reset.exec()
+        cfg_nl = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+        ksft_eq(cfg_old["flow-hash"][fl_type], cfg_nl["flow-hash"][fl_type],
+                comment=f"Un-config for {fl_type} over Netlink")
+        cfg_ic = _ethtool_get_cfg(cfg, fl_type)
+        ksft_eq(cur, cfg_ic, comment=f"Un-config for {fl_type} over IOCTL")
+
+    # Try to set multiple at once, the defer was already installed at the start
+    change = {"ip-src"}
+    if change == cfg_old["flow-hash"]["tcp4"]:
+        change = {"ip-dst"}
+    cfg.ethnl.rss_set({
+        "header": {"dev-index": cfg.ifindex},
+        "flow-hash": {x: change for x in flow_types}
+    })
+
+    cfg_nl = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    for fl_type in flow_types:
+        ksft_eq(change, cfg_nl["flow-hash"][fl_type],
+                comment=f"multi-config for {fl_type} over Netlink")
+
+
+def test_rxfh_fields_set_xfrm(cfg):
+    """ Test changing Rx Flow Hash vs xfrm_input at once.  """
+
+    def set_rss(cfg, xfrm, fh):
+        cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                           "input-xfrm": xfrm, "flow-hash": fh})
+
+    # Install the reset handler
+    cfg_old = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    # symmetric hashing is config-order-sensitive make sure we leave
+    # symmetric mode, or make the flow-hash sym-compatible first
+    changes = [{"flow-hash": cfg_old["flow-hash"],},
+               {"input-xfrm": cfg_old.get("input-xfrm", {}),}]
+    if cfg_old.get("input-xfrm"):
+        changes = list(reversed(changes))
+    for old in changes:
+        defer(cfg.ethnl.rss_set, {"header": {"dev-index": cfg.ifindex},} | old)
+
+    # Make sure we start with input-xfrm off, and tcp4 config non-sym
+    set_rss(cfg, {}, {})
+    set_rss(cfg, {}, {"tcp4": {"ip-src"}})
+
+    # Setting sym and fixing tcp4 config not expected to pass right now
+    with ksft_raises(NlError):
+        set_rss(cfg, {"sym-xor"}, {"tcp4": {"ip-src", "ip-dst"}})
+    # One at a time should work, hopefully
+    set_rss(cfg, 0, {"tcp4": {"ip-src", "ip-dst"}})
+    no_support = False
+    try:
+        set_rss(cfg, {"sym-xor"}, {})
+    except NlError:
+        try:
+            set_rss(cfg, {"sym-or-xor"}, {})
+        except NlError:
+            no_support = True
+    if no_support:
+        raise KsftSkipEx("no input-xfrm supported")
+    # Disabling two at once should not work either without kernel changes
+    with ksft_raises(NlError):
+        set_rss(cfg, {}, {"tcp4": {"ip-src"}})
+
+
+def test_rxfh_fields_ntf(cfg):
+    """ Test Rx Flow Hash notifications. """
+
+    cur = _ethtool_get_cfg(cfg, "tcp4")
+    if cur == "sdfn":
+        change = {"ip-src", "ip-dst"}
+    else:
+        change = {"l4-b-0-1", "l4-b-2-3", "ip-src", "ip-dst"}
+
+    ethnl = EthtoolFamily()
+    ethnl.ntf_subscribe("monitor")
+
+    ethnl.rss_set({
+        "header": {"dev-index": cfg.ifindex},
+        "flow-hash": {"tcp4": change}
+    })
+    reset = defer(ethtool,
+                  f"--disable-netlink -N {cfg.ifname} rx-flow-hash tcp4 {cur}")
+
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("No notification received after IOCTL change")
+    ksft_eq(ntf["name"], "rss-ntf")
+    ksft_eq(ntf["msg"]["flow-hash"]["tcp4"], change)
+    ksft_eq(next(ethnl.poll_ntf(duration=0.01), None), None)
+
+    reset.exec()
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("No notification received after Netlink change")
+    ksft_eq(ntf["name"], "rss-ntf")
+    ksft_ne(ntf["msg"]["flow-hash"]["tcp4"], change)
+    ksft_eq(next(ethnl.poll_ntf(duration=0.01), None), None)
+
+
+def test_rss_ctx_add(cfg):
+    """ Test creating an additional RSS context via Netlink """
+
+    _require_2qs(cfg)
+
+    # Test basic creation
+    ctx = cfg.ethnl.rss_create_act({"header": {"dev-index": cfg.ifindex}})
+    d = defer(ethtool, f"-X {cfg.ifname} context {ctx.get('context')} delete")
+    ksft_ne(ctx.get("context", 0), 0)
+    ksft_ne(set(ctx.get("indir", [0])), {0},
+            comment="Driver should init the indirection table")
+
+    # Try requesting the ID we just got allocated
+    with ksft_raises(NlError) as cm:
+        ctx = cfg.ethnl.rss_create_act({
+            "header": {"dev-index": cfg.ifindex},
+            "context": ctx.get("context"),
+        })
+        ethtool(f"-X {cfg.ifname} context {ctx.get('context')} delete")
+    d.exec()
+    ksft_eq(cm.exception.nl_msg.error, -errno.EBUSY)
+
+    # Test creating with a specified RSS table, and context ID
+    ctx_id = ctx.get("context")
+    ctx = cfg.ethnl.rss_create_act({
+        "header": {"dev-index": cfg.ifindex},
+        "context": ctx_id,
+        "indir": [1],
+    })
+    ethtool(f"-X {cfg.ifname} context {ctx.get('context')} delete")
+    ksft_eq(ctx.get("context"), ctx_id)
+    ksft_eq(set(ctx.get("indir", [0])), {1})
+
+
+def test_rss_ctx_ntf(cfg):
+    """ Test notifications for creating additional RSS contexts """
+
+    ethnl = EthtoolFamily()
+    ethnl.ntf_subscribe("monitor")
+
+    # Create / delete via Netlink
+    ctx = cfg.ethnl.rss_create_act({"header": {"dev-index": cfg.ifindex}})
+    cfg.ethnl.rss_delete_act({
+        "header": {"dev-index": cfg.ifindex},
+        "context": ctx["context"],
+    })
+
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("[NL] No notification after context creation")
+    ksft_eq(ntf["name"], "rss-create-ntf")
+    ksft_eq(ctx, ntf["msg"])
+
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("[NL] No notification after context deletion")
+    ksft_eq(ntf["name"], "rss-delete-ntf")
+
+    # Create / deleve via IOCTL
+    ctx_id = _ethtool_create(cfg, "--disable-netlink -X", "context new")
+    ethtool(f"--disable-netlink -X {cfg.ifname} context {ctx_id} delete")
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("[IOCTL] No notification after context creation")
+    ksft_eq(ntf["name"], "rss-create-ntf")
+
+    ntf = next(ethnl.poll_ntf(duration=0.2), None)
+    if ntf is None:
+        raise KsftFailEx("[IOCTL] No notification after context deletion")
+    ksft_eq(ntf["name"], "rss-delete-ntf")
+
+
+def main() -> None:
+    """ Ksft boiler plate main """
+
+    with NetDrvEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/rss_drv.py

@@ -0,0 +1,313 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Driver-related behavior tests for RSS.
+"""
+
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge
+from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx, ksft_raises
+from lib.py import defer, ethtool, CmdExitFailure
+from lib.py import EthtoolFamily, NlError
+from lib.py import NetDrvEnv
+
+
+def _is_power_of_two(n):
+    return n > 0 and (n & (n - 1)) == 0
+
+
+def _get_rss(cfg, context=0):
+    return ethtool(f"-x {cfg.ifname} context {context}", json=True)[0]
+
+
+def _test_rss_indir_size(cfg, qcnt, context=0):
+    """Test that indirection table size is at least 4x queue count."""
+    ethtool(f"-L {cfg.ifname} combined {qcnt}")
+
+    rss = _get_rss(cfg, context=context)
+    indir = rss['rss-indirection-table']
+    ksft_ge(len(indir), 4 * qcnt, "Table smaller than 4x")
+    return len(indir)
+
+
+def _maybe_create_context(cfg, create_context):
+    """ Either create a context and return its ID or return 0 for main ctx """
+    if not create_context:
+        return 0
+    try:
+        ctx = cfg.ethnl.rss_create_act({'header': {'dev-index': cfg.ifindex}})
+        ctx_id = ctx['context']
+        defer(cfg.ethnl.rss_delete_act,
+              {'header': {'dev-index': cfg.ifindex}, 'context': ctx_id})
+    except NlError:
+        raise KsftSkipEx("Device does not support additional RSS contexts")
+
+    return ctx_id
+
+
+def _require_dynamic_indir_size(cfg, ch_max):
+    """Skip if the device does not dynamically size its indirection table."""
+    ethtool(f"-X {cfg.ifname} default")
+    ethtool(f"-L {cfg.ifname} combined 2")
+    small = len(_get_rss(cfg)['rss-indirection-table'])
+    ethtool(f"-L {cfg.ifname} combined {ch_max}")
+    large = len(_get_rss(cfg)['rss-indirection-table'])
+
+    if small == large:
+        raise KsftSkipEx("Device does not dynamically size indirection table")
+
+
+@ksft_variants([
+    KsftNamedVariant("main", False),
+    KsftNamedVariant("ctx", True),
+])
+def indir_size_4x(cfg, create_context):
+    """
+    Test that the indirection table has at least 4 entries per queue.
+    Empirically network-heavy workloads like memcache suffer with the 33%
+    imbalance of a 2x indirection table size.
+    4x table translates to a 16% imbalance.
+    """
+    channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    ch_max = channels.get('combined-max', 0)
+    qcnt = channels['combined-count']
+
+    if ch_max < 3:
+        raise KsftSkipEx(f"Not enough queues for the test: max={ch_max}")
+
+    defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+    ethtool(f"-L {cfg.ifname} combined 3")
+
+    ctx_id = _maybe_create_context(cfg, create_context)
+
+    indir_sz = _test_rss_indir_size(cfg, 3, context=ctx_id)
+
+    # Test with max queue count (max - 1 if max is a power of two)
+    test_max = ch_max - 1 if _is_power_of_two(ch_max) else ch_max
+    if test_max > 3 and indir_sz < test_max * 4:
+        _test_rss_indir_size(cfg, test_max, context=ctx_id)
+
+
+@ksft_variants([
+    KsftNamedVariant("main", False),
+    KsftNamedVariant("ctx", True),
+])
+def resize_periodic(cfg, create_context):
+    """Test that a periodic indirection table survives channel changes.
+
+    Set a non-default periodic table ([3, 2, 1, 0] x N) via netlink,
+    reduce channels to trigger a fold, then increase to trigger an
+    unfold. Using a reversed pattern (instead of [0, 1, 2, 3]) ensures
+    the test can distinguish a correct fold from a driver that silently
+    resets the table to defaults. Verify the exact pattern is preserved
+    and the size tracks the channel count.
+    """
+    channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    ch_max = channels.get('combined-max', 0)
+    qcnt = channels['combined-count']
+
+    if ch_max < 4:
+        raise KsftSkipEx(f"Not enough queues for the test: max={ch_max}")
+
+    defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+
+    _require_dynamic_indir_size(cfg, ch_max)
+
+    ctx_id = _maybe_create_context(cfg, create_context)
+
+    # Set a non-default periodic pattern via netlink.
+    # Send only 4 entries (user_size=4) so the kernel replicates it
+    # to fill the device table. This allows folding down to 4 entries.
+    rss = _get_rss(cfg, context=ctx_id)
+    orig_size = len(rss['rss-indirection-table'])
+    pattern = [3, 2, 1, 0]
+    req = {'header': {'dev-index': cfg.ifindex}, 'indir': pattern}
+    if ctx_id:
+        req['context'] = ctx_id
+    else:
+        defer(ethtool, f"-X {cfg.ifname} default")
+    cfg.ethnl.rss_set(req)
+
+    # Shrink — should fold
+    ethtool(f"-L {cfg.ifname} combined 4")
+    rss = _get_rss(cfg, context=ctx_id)
+    indir = rss['rss-indirection-table']
+
+    ksft_ge(orig_size, len(indir), "Table did not shrink")
+    ksft_eq(indir, [3, 2, 1, 0] * (len(indir) // 4),
+            "Folded table has wrong pattern")
+
+    # Grow back — should unfold
+    ethtool(f"-L {cfg.ifname} combined {ch_max}")
+    rss = _get_rss(cfg, context=ctx_id)
+    indir = rss['rss-indirection-table']
+
+    ksft_eq(len(indir), orig_size, "Table size not restored")
+    ksft_eq(indir, [3, 2, 1, 0] * (len(indir) // 4),
+            "Unfolded table has wrong pattern")
+
+
+@ksft_variants([
+    KsftNamedVariant("main", False),
+    KsftNamedVariant("ctx", True),
+])
+def resize_below_user_size_reject(cfg, create_context):
+    """Test that shrinking below user_size is rejected.
+
+    Send a table via netlink whose size (user_size) sits between
+    the small and large device table sizes. The table is periodic,
+    so folding would normally succeed, but the user_size floor must
+    prevent it.
+    """
+    channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    ch_max = channels.get('combined-max', 0)
+    qcnt = channels['combined-count']
+
+    if ch_max < 4:
+        raise KsftSkipEx(f"Not enough queues for the test: max={ch_max}")
+
+    defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+
+    _require_dynamic_indir_size(cfg, ch_max)
+
+    ctx_id = _maybe_create_context(cfg, create_context)
+
+    # Measure the table size at max channels
+    rss = _get_rss(cfg, context=ctx_id)
+    big_size = len(rss['rss-indirection-table'])
+
+    # Measure the table size at reduced channels
+    ethtool(f"-L {cfg.ifname} combined 4")
+    rss = _get_rss(cfg, context=ctx_id)
+    small_size = len(rss['rss-indirection-table'])
+    ethtool(f"-L {cfg.ifname} combined {ch_max}")
+
+    if small_size >= big_size:
+        raise KsftSkipEx("Table did not shrink at reduced channels")
+
+    # Find a user_size
+    user_size = None
+    for div in [2, 4]:
+        candidate = big_size // div
+        if candidate > small_size and big_size % candidate == 0:
+            user_size = candidate
+            break
+    if user_size is None:
+        raise KsftSkipEx("No suitable user_size between small and big table")
+
+    # Send a periodic sub-table of exactly user_size entries.
+    # Pattern safe for 4 channels.
+    pattern = [0, 1, 2, 3] * (user_size // 4)
+    if len(pattern) != user_size:
+        raise KsftSkipEx(f"user_size ({user_size}) not divisible by 4")
+    req = {'header': {'dev-index': cfg.ifindex}, 'indir': pattern}
+    if ctx_id:
+        req['context'] = ctx_id
+    else:
+        defer(ethtool, f"-X {cfg.ifname} default")
+    cfg.ethnl.rss_set(req)
+
+    # Shrink channels — table would go to small_size < user_size.
+    # The table is periodic so folding would work, but user_size
+    # floor must reject it.
+    with ksft_raises(CmdExitFailure):
+        ethtool(f"-L {cfg.ifname} combined 4")
+
+
+@ksft_variants([
+    KsftNamedVariant("main", False),
+    KsftNamedVariant("ctx", True),
+])
+def resize_nonperiodic_reject(cfg, create_context):
+    """Test that a non-periodic table blocks channel reduction.
+
+    Set equal weight across all queues so the table is not periodic
+    at any smaller size, then verify channel reduction is rejected.
+    An additional context with a periodic table is created to verify
+    that validation catches the non-periodic one even when others
+    are fine.
+    """
+    channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    ch_max = channels.get('combined-max', 0)
+    qcnt = channels['combined-count']
+
+    if ch_max < 4:
+        raise KsftSkipEx(f"Not enough queues for the test: max={ch_max}")
+
+    defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+
+    _require_dynamic_indir_size(cfg, ch_max)
+
+    ctx_id = _maybe_create_context(cfg, create_context)
+    ctx_ref = f"context {ctx_id}" if ctx_id else ""
+
+    # Create an extra context with a periodic (foldable) table so that
+    # the validation must iterate all contexts to find the bad one.
+    extra_ctx = _maybe_create_context(cfg, True)
+    ethtool(f"-X {cfg.ifname} context {extra_ctx} equal 2")
+
+    ethtool(f"-X {cfg.ifname} {ctx_ref} equal {ch_max}")
+    if not create_context:
+        defer(ethtool, f"-X {cfg.ifname} default")
+
+    with ksft_raises(CmdExitFailure):
+        ethtool(f"-L {cfg.ifname} combined 2")
+
+
+@ksft_variants([
+    KsftNamedVariant("main", False),
+    KsftNamedVariant("ctx", True),
+])
+def resize_nonperiodic_no_corruption(cfg, create_context):
+    """Test that a failed resize does not corrupt table or channel count.
+
+    Set a non-periodic table, attempt a channel reduction (which must
+    fail), then verify both the indirection table contents and the
+    channel count are unchanged.
+    """
+    channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    ch_max = channels.get('combined-max', 0)
+    qcnt = channels['combined-count']
+
+    if ch_max < 4:
+        raise KsftSkipEx(f"Not enough queues for the test: max={ch_max}")
+
+    defer(ethtool, f"-L {cfg.ifname} combined {qcnt}")
+
+    _require_dynamic_indir_size(cfg, ch_max)
+
+    ctx_id = _maybe_create_context(cfg, create_context)
+    ctx_ref = f"context {ctx_id}" if ctx_id else ""
+
+    ethtool(f"-X {cfg.ifname} {ctx_ref} equal {ch_max}")
+    if not create_context:
+        defer(ethtool, f"-X {cfg.ifname} default")
+
+    rss_before = _get_rss(cfg, context=ctx_id)
+
+    with ksft_raises(CmdExitFailure):
+        ethtool(f"-L {cfg.ifname} combined 2")
+
+    rss_after = _get_rss(cfg, context=ctx_id)
+    ksft_eq(rss_after['rss-indirection-table'],
+            rss_before['rss-indirection-table'],
+            "Indirection table corrupted after failed resize")
+
+    channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+    ksft_eq(channels['combined-count'], ch_max,
+            "Channel count changed after failed resize")
+
+
+def main() -> None:
+    """ Ksft boiler plate main """
+    with NetDrvEnv(__file__) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        ksft_run([indir_size_4x, resize_periodic,
+                  resize_below_user_size_reject,
+                  resize_nonperiodic_reject,
+                  resize_nonperiodic_no_corruption], args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/rss_flow_label.py

@@ -0,0 +1,172 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Tests for RSS hashing on IPv6 Flow Label.
+"""
+
+import glob
+import os
+import socket
+from lib.py import CmdExitFailure
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge, ksft_in, \
+    ksft_not_in, ksft_raises, KsftSkipEx
+from lib.py import bkg, cmd, defer, fd_read_timeout, rand_port
+from lib.py import NetDrvEpEnv
+
+
+def _check_system(cfg):
+    if not hasattr(socket, "SO_INCOMING_CPU"):
+        raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11")
+
+    qcnt = len(glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*"))
+    if qcnt < 2:
+        raise KsftSkipEx(f"Local has only {qcnt} queues")
+
+    for f in [f"/sys/class/net/{cfg.ifname}/queues/rx-0/rps_flow_cnt",
+              f"/sys/class/net/{cfg.ifname}/queues/rx-0/rps_cpus"]:
+        try:
+            with open(f, 'r') as fp:
+                setting = fp.read().strip()
+                # CPU mask will be zeros and commas
+                if setting.replace("0", "").replace(",", ""):
+                    raise KsftSkipEx(f"RPS/RFS is configured: {f}: {setting}")
+        except FileNotFoundError:
+            pass
+
+    # 1 is the default, if someone changed it we probably shouldn"t mess with it
+    af = cmd("cat /proc/sys/net/ipv6/auto_flowlabels", host=cfg.remote).stdout
+    if af.strip() != "1":
+        raise KsftSkipEx("Remote does not have auto_flowlabels enabled")
+
+
+def _ethtool_get_cfg(cfg, fl_type):
+    descr = cmd(f"ethtool -n {cfg.ifname} rx-flow-hash {fl_type}").stdout
+
+    converter = {
+        "IP SA": "s",
+        "IP DA": "d",
+        "L3 proto": "t",
+        "L4 bytes 0 & 1 [TCP/UDP src port]": "f",
+        "L4 bytes 2 & 3 [TCP/UDP dst port]": "n",
+        "IPv6 Flow Label": "l",
+    }
+
+    ret = ""
+    for line in descr.split("\n")[1:-2]:
+        # if this raises we probably need to add more keys to converter above
+        ret += converter[line]
+    return ret
+
+
+def _traffic(cfg, one_sock, one_cpu):
+    local_port  = rand_port(socket.SOCK_DGRAM)
+    remote_port = rand_port(socket.SOCK_DGRAM)
+
+    sock = socket.socket(socket.AF_INET6, socket.SOCK_DGRAM)
+    sock.bind(("", local_port))
+    sock.connect((cfg.remote_addr_v["6"], 0))
+    if one_sock:
+        send = f"exec 5<>/dev/udp/{cfg.addr_v['6']}/{local_port}; " \
+                "for i in `seq 20`; do echo a >&5; sleep 0.02; done; exec 5>&-"
+    else:
+        send = "for i in `seq 20`; do echo a | socat -t0.02 - UDP6:" \
+              f"[{cfg.addr_v['6']}]:{local_port},sourceport={remote_port}; done"
+
+    cpus = set()
+    with bkg(send, shell=True, host=cfg.remote, exit_wait=True):
+        for _ in range(20):
+            fd_read_timeout(sock.fileno(), 1)
+            cpu = sock.getsockopt(socket.SOL_SOCKET, socket.SO_INCOMING_CPU)
+            cpus.add(cpu)
+
+    if one_cpu:
+        ksft_eq(len(cpus), 1,
+                f"{one_sock=} - expected one CPU, got traffic on: {cpus=}")
+    else:
+        ksft_ge(len(cpus), 2,
+                f"{one_sock=} - expected many CPUs, got traffic on: {cpus=}")
+
+
+def test_rss_flow_label(cfg):
+    """
+    Test hashing on IPv6 flow label. Send traffic over a single socket
+    and over multiple sockets. Depend on the remote having auto-label
+    enabled so that it randomizes the label per socket.
+    """
+
+    cfg.require_ipver("6")
+    cfg.require_cmd("socat", remote=True)
+    _check_system(cfg)
+
+    # Enable flow label hashing for UDP6
+    initial = _ethtool_get_cfg(cfg, "udp6")
+    no_lbl = initial.replace("l", "")
+    if "l" not in initial:
+        try:
+            cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 l{no_lbl}")
+        except CmdExitFailure as exc:
+            raise KsftSkipEx("Device doesn't support Flow Label for UDP6") from exc
+
+        defer(cmd, f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {initial}")
+
+    _traffic(cfg, one_sock=True, one_cpu=True)
+    _traffic(cfg, one_sock=False, one_cpu=False)
+
+    # Disable it, we should see no hashing (reset was already defer()ed)
+    cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {no_lbl}")
+
+    _traffic(cfg, one_sock=False, one_cpu=True)
+
+
+def _check_v4_flow_types(cfg):
+    for fl_type in ["tcp4", "udp4", "ah4", "esp4", "sctp4"]:
+        try:
+            cur = cmd(f"ethtool -n {cfg.ifname} rx-flow-hash {fl_type}").stdout
+            ksft_not_in("Flow Label", cur,
+                        comment=f"{fl_type=} has Flow Label:" + cur)
+        except CmdExitFailure:
+            # Probably does not support this flow type
+            pass
+
+
+def test_rss_flow_label_6only(cfg):
+    """
+    Test interactions with IPv4 flow types. It should not be possible to set
+    IPv6 Flow Label hashing for an IPv4 flow type. The Flow Label should also
+    not appear in the IPv4 "current config".
+    """
+
+    with ksft_raises(CmdExitFailure) as cm:
+        cmd(f"ethtool -N {cfg.ifname} rx-flow-hash tcp4 sdfnl")
+    ksft_in("Invalid argument", cm.exception.cmd.stderr)
+
+    _check_v4_flow_types(cfg)
+
+    # Try to enable Flow Labels and check again, in case it leaks thru
+    initial = _ethtool_get_cfg(cfg, "udp6")
+    no_lbl = initial.replace("l", "")
+    if "l" not in initial:
+        try:
+            cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 l{no_lbl}")
+        except CmdExitFailure as exc:
+            raise KsftSkipEx("Device doesn't support Flow Label for UDP6") from exc
+    else:
+        cmd(f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {no_lbl}")
+    restore = defer(cmd, f"ethtool -N {cfg.ifname} rx-flow-hash udp6 {initial}")
+
+    _check_v4_flow_types(cfg)
+    restore.exec()
+    _check_v4_flow_types(cfg)
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        ksft_run([test_rss_flow_label,
+                  test_rss_flow_label_6only],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py

@@ -0,0 +1,124 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import multiprocessing
+import socket
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge, cmd, fd_read_timeout
+from lib.py import NetDrvEpEnv
+from lib.py import EthtoolFamily, NetdevFamily, NlError
+from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import defer, ksft_pr, rand_port
+
+
+def traffic(cfg, local_port, remote_port, ipver):
+    af_inet = socket.AF_INET if ipver == "4" else socket.AF_INET6
+    sock = socket.socket(af_inet, socket.SOCK_DGRAM)
+    sock.bind(("", local_port))
+    sock.connect((cfg.remote_addr_v[ipver], remote_port))
+    tgt = f"{ipver}:[{cfg.addr_v[ipver]}]:{local_port},sourceport={remote_port}"
+    cmd("echo a | socat - UDP" + tgt, host=cfg.remote)
+    fd_read_timeout(sock.fileno(), 5)
+    return sock.getsockopt(socket.SOL_SOCKET, socket.SO_INCOMING_CPU)
+
+
+def _rss_input_xfrm_try_enable(cfg):
+    """
+    Check if symmetric input-xfrm is already enabled, if not try to enable it
+    and register a cleanup.
+    """
+    rss = cfg.ethnl.rss_get({'header': {'dev-name': cfg.ifname}})
+    orig_xfrm = rss.get('input-xfrm', set())
+    sym_xfrm = set(filter(lambda x: 'sym' in x, orig_xfrm))
+
+    if sym_xfrm:
+        ksft_pr("Sym input xfrm already enabled:", sym_xfrm)
+        return sym_xfrm
+
+    for xfrm in cfg.ethnl.consts["input-xfrm"].entries:
+        # Skip non-symmetric transforms
+        if "sym" not in xfrm:
+            continue
+
+        try_xfrm = {xfrm} | orig_xfrm
+        try:
+            cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                               "input-xfrm": try_xfrm})
+        except NlError:
+            continue
+
+        ksft_pr("Sym input xfrm configured:", try_xfrm)
+        defer(cfg.ethnl.rss_set,
+              {"header": {"dev-index": cfg.ifindex},
+               "input-xfrm": orig_xfrm})
+        return {xfrm}
+
+    return set()
+
+
+def test_rss_input_xfrm(cfg, ipver):
+    """
+    Test symmetric input_xfrm.
+    If symmetric RSS hash is configured, send traffic twice, swapping the
+    src/dst UDP ports, and verify that the same queue is receiving the traffic
+    in both cases (IPs are constant).
+    """
+
+    if multiprocessing.cpu_count() < 2:
+        raise KsftSkipEx("Need at least two CPUs to test symmetric RSS hash")
+
+    cfg.require_cmd("socat", local=False, remote=True)
+
+    if not hasattr(socket, "SO_INCOMING_CPU"):
+        raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11")
+
+    # Check for symmetric xor/or-xor
+    input_xfrm = _rss_input_xfrm_try_enable(cfg)
+    if not input_xfrm:
+        raise KsftSkipEx("Symmetric RSS hash not supported by device")
+
+    cpus = set()
+    successful = 0
+    for _ in range(100):
+        try:
+            port1 = rand_port(socket.SOCK_DGRAM)
+            port2 = rand_port(socket.SOCK_DGRAM)
+            cpu1 = traffic(cfg, port1, port2, ipver)
+            cpu2 = traffic(cfg, port2, port1, ipver)
+            cpus.update([cpu1, cpu2])
+            ksft_eq(
+                cpu1, cpu2, comment=f"Received traffic on different cpus with ports ({port1 = }, {port2 = }) while symmetric hash is configured")
+
+            successful += 1
+            if successful == 10:
+                break
+        except:
+            continue
+    else:
+        raise KsftFailEx("Failed to run traffic")
+
+    ksft_ge(len(cpus), 2,
+            comment=f"Received traffic on less than two cpus {cpus = }")
+
+
+def test_rss_input_xfrm_ipv4(cfg):
+    cfg.require_ipver("4")
+    test_rss_input_xfrm(cfg, "4")
+
+
+def test_rss_input_xfrm_ipv6(cfg):
+    cfg.require_ipver("6")
+    test_rss_input_xfrm(cfg, "6")
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        cfg.netdevnl = NetdevFamily()
+
+        ksft_run([test_rss_input_xfrm_ipv4, test_rss_input_xfrm_ipv6],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/settings

@@ -0,0 +1 @@
+timeout=0

linux-7.2.3/tools/testing/selftests/drivers/net/hw/toeplitz.c

@@ -0,0 +1,673 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Toeplitz test
+ *
+ * 1. Read packets and their rx_hash using PF_PACKET/TPACKET_V3
+ * 2. Compute the rx_hash in software based on the packet contents
+ * 3. Compare the two
+ *
+ * Optionally, either '-C $rx_irq_cpu_list' or '-r $rps_bitmap' may be given.
+ *
+ * If '-C $rx_irq_cpu_list' is given, also
+ *
+ * 4. Identify the cpu on which the packet arrived with PACKET_FANOUT_CPU
+ * 5. Compute the rxqueue that RSS would select based on this rx_hash
+ * 6. Using the $rx_irq_cpu_list map, identify the arriving cpu based on rxq irq
+ * 7. Compare the cpus from 4 and 6
+ *
+ * Else if '-r $rps_bitmap' is given, also
+ *
+ * 4. Identify the cpu on which the packet arrived with PACKET_FANOUT_CPU
+ * 5. Compute the cpu that RPS should select based on rx_hash and $rps_bitmap
+ * 6. Compare the cpus from 4 and 5
+ */
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <getopt.h>
+#include <linux/filter.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <net/if.h>
+#include <netdb.h>
+#include <netinet/ip.h>
+#include <netinet/ip6.h>
+#include <netinet/tcp.h>
+#include <netinet/udp.h>
+#include <poll.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <stdint.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/mman.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+#include <sys/sysinfo.h>
+#include <sys/time.h>
+#include <sys/types.h>
+#include <unistd.h>
+
+#include <ynl.h>
+#include "ethtool-user.h"
+
+#include "kselftest.h"
+#include "../../../net/lib/ksft.h"
+
+#define TOEPLITZ_KEY_MIN_LEN	40
+#define TOEPLITZ_KEY_MAX_LEN	256
+
+#define TOEPLITZ_STR_LEN(K)	(((K) * 3) - 1)	/* hex encoded: AA:BB:CC:...:ZZ */
+#define TOEPLITZ_STR_MIN_LEN	TOEPLITZ_STR_LEN(TOEPLITZ_KEY_MIN_LEN)
+#define TOEPLITZ_STR_MAX_LEN	TOEPLITZ_STR_LEN(TOEPLITZ_KEY_MAX_LEN)
+
+#define FOUR_TUPLE_MAX_LEN	((sizeof(struct in6_addr) * 2) + (sizeof(uint16_t) * 2))
+
+#define RSS_MAX_CPUS (1 << 16)	/* real constraint is PACKET_FANOUT_MAX */
+#define RSS_MAX_INDIR	(1 << 16)
+
+#define RPS_MAX_CPUS 16UL	/* must be a power of 2 */
+
+#define MIN_PKT_SAMPLES 40	/* minimum number of packets to receive */
+
+/* configuration options (cmdline arguments) */
+static uint16_t cfg_dport =	8000;
+static int cfg_family =		AF_INET6;
+static char *cfg_ifname =	"eth0";
+static int cfg_num_queues;
+static int cfg_num_rps_cpus;
+static bool cfg_sink;
+static int cfg_type =		SOCK_STREAM;
+static int cfg_timeout_msec =	1000;
+static bool cfg_verbose;
+
+/* global vars */
+static int num_cpus;
+static int ring_block_nr;
+static int ring_block_sz;
+
+/* stats */
+static int frames_received;
+static int frames_nohash;
+static int frames_error;
+
+#define log_verbose(args...)	do { if (cfg_verbose) fprintf(stderr, args); } while (0)
+
+/* tpacket ring */
+struct ring_state {
+	int fd;
+	char *mmap;
+	int idx;
+	int cpu;
+};
+
+static unsigned int rx_irq_cpus[RSS_MAX_CPUS];	/* map from rxq to cpu */
+static int rps_silo_to_cpu[RPS_MAX_CPUS];
+static unsigned char toeplitz_key[TOEPLITZ_KEY_MAX_LEN];
+static unsigned int rss_indir_tbl[RSS_MAX_INDIR];
+static unsigned int rss_indir_tbl_size;
+static struct ring_state rings[RSS_MAX_CPUS];
+
+static inline uint32_t toeplitz(const unsigned char *four_tuple,
+				const unsigned char *key)
+{
+	int i, bit, ret = 0;
+	uint32_t key32;
+
+	key32 = ntohl(*((uint32_t *)key));
+	key += 4;
+
+	for (i = 0; i < FOUR_TUPLE_MAX_LEN; i++) {
+		for (bit = 7; bit >= 0; bit--) {
+			if (four_tuple[i] & (1 << bit))
+				ret ^= key32;
+
+			key32 <<= 1;
+			key32 |= !!(key[0] & (1 << bit));
+		}
+		key++;
+	}
+
+	return ret;
+}
+
+/* Compare computed cpu with arrival cpu from packet_fanout_cpu */
+static void verify_rss(uint32_t rx_hash, int cpu)
+{
+	int queue;
+
+	if (rss_indir_tbl_size)
+		queue = rss_indir_tbl[rx_hash % rss_indir_tbl_size];
+	else
+		queue = rx_hash % cfg_num_queues;
+
+	log_verbose(" rxq %d (cpu %d)", queue, rx_irq_cpus[queue]);
+	if (rx_irq_cpus[queue] != cpu) {
+		log_verbose(". error: rss cpu mismatch (%d)", cpu);
+		frames_error++;
+	}
+}
+
+static void verify_rps(uint64_t rx_hash, int cpu)
+{
+	int silo = (rx_hash * cfg_num_rps_cpus) >> 32;
+
+	log_verbose(" silo %d (cpu %d)", silo, rps_silo_to_cpu[silo]);
+	if (rps_silo_to_cpu[silo] != cpu) {
+		log_verbose(". error: rps cpu mismatch (%d)", cpu);
+		frames_error++;
+	}
+}
+
+static void log_rxhash(int cpu, uint32_t rx_hash,
+		       const char *addrs, int addr_len)
+{
+	char saddr[INET6_ADDRSTRLEN], daddr[INET6_ADDRSTRLEN];
+	uint16_t *ports;
+
+	if (!inet_ntop(cfg_family, addrs, saddr, sizeof(saddr)) ||
+	    !inet_ntop(cfg_family, addrs + addr_len, daddr, sizeof(daddr)))
+		error(1, 0, "address parse error");
+
+	ports = (void *)addrs + (addr_len * 2);
+	log_verbose("cpu %d: rx_hash 0x%08x [saddr %s daddr %s sport %02hu dport %02hu]",
+		    cpu, rx_hash, saddr, daddr,
+		    ntohs(ports[0]), ntohs(ports[1]));
+}
+
+/* Compare computed rxhash with rxhash received from tpacket_v3 */
+static void verify_rxhash(const char *pkt, uint32_t rx_hash, int cpu)
+{
+	unsigned char four_tuple[FOUR_TUPLE_MAX_LEN] = {0};
+	uint32_t rx_hash_sw;
+	const char *addrs;
+	int addr_len;
+
+	if (cfg_family == AF_INET) {
+		addr_len = sizeof(struct in_addr);
+		addrs = pkt + offsetof(struct iphdr, saddr);
+	} else {
+		addr_len = sizeof(struct in6_addr);
+		addrs = pkt + offsetof(struct ip6_hdr, ip6_src);
+	}
+
+	memcpy(four_tuple, addrs, (addr_len * 2) + (sizeof(uint16_t) * 2));
+	rx_hash_sw = toeplitz(four_tuple, toeplitz_key);
+
+	if (cfg_verbose)
+		log_rxhash(cpu, rx_hash, addrs, addr_len);
+
+	if (rx_hash != rx_hash_sw) {
+		log_verbose(" != expected 0x%x\n", rx_hash_sw);
+		frames_error++;
+		return;
+	}
+
+	log_verbose(" OK");
+	if (cfg_num_queues)
+		verify_rss(rx_hash, cpu);
+	else if (cfg_num_rps_cpus)
+		verify_rps(rx_hash, cpu);
+	log_verbose("\n");
+}
+
+static char *recv_frame(const struct ring_state *ring, char *frame)
+{
+	struct tpacket3_hdr *hdr = (void *)frame;
+
+	if (hdr->hv1.tp_rxhash)
+		verify_rxhash(frame + hdr->tp_net, hdr->hv1.tp_rxhash,
+			      ring->cpu);
+	else
+		frames_nohash++;
+
+	return frame + hdr->tp_next_offset;
+}
+
+/* A single TPACKET_V3 block can hold multiple frames */
+static bool recv_block(struct ring_state *ring)
+{
+	struct tpacket_block_desc *block;
+	char *frame;
+	int i;
+
+	block = (void *)(ring->mmap + ring->idx * ring_block_sz);
+	if (!(block->hdr.bh1.block_status & TP_STATUS_USER))
+		return false;
+
+	frame = (char *)block;
+	frame += block->hdr.bh1.offset_to_first_pkt;
+
+	for (i = 0; i < block->hdr.bh1.num_pkts; i++) {
+		frame = recv_frame(ring, frame);
+		frames_received++;
+	}
+
+	block->hdr.bh1.block_status = TP_STATUS_KERNEL;
+	ring->idx = (ring->idx + 1) % ring_block_nr;
+
+	return true;
+}
+
+/* simple test: process all rings until MIN_PKT_SAMPLES packets are received,
+ * or the test times out.
+ */
+static void process_rings(void)
+{
+	struct timeval start, now;
+	bool pkts_found = true;
+	long elapsed_usec;
+	int i;
+
+	gettimeofday(&start, NULL);
+
+	do {
+		if (!pkts_found)
+			usleep(100);
+
+		pkts_found = false;
+		for (i = 0; i < num_cpus; i++)
+			pkts_found |= recv_block(&rings[i]);
+
+		gettimeofday(&now, NULL);
+		elapsed_usec = (now.tv_sec - start.tv_sec) * 1000000 +
+			       (now.tv_usec - start.tv_usec);
+	} while (frames_received - frames_nohash < MIN_PKT_SAMPLES &&
+		 elapsed_usec < cfg_timeout_msec * 1000);
+
+	fprintf(stderr, "count: pass=%u nohash=%u fail=%u\n",
+		frames_received - frames_nohash - frames_error,
+		frames_nohash, frames_error);
+}
+
+static char *setup_ring(int fd)
+{
+	struct tpacket_req3 req3 = {0};
+	void *ring;
+
+	req3.tp_retire_blk_tov = cfg_timeout_msec / 8;
+	req3.tp_feature_req_word = TP_FT_REQ_FILL_RXHASH;
+
+	req3.tp_frame_size = 2048;
+	req3.tp_frame_nr = 1 << 10;
+	req3.tp_block_nr = 16;
+
+	req3.tp_block_size = req3.tp_frame_size * req3.tp_frame_nr;
+	req3.tp_block_size /= req3.tp_block_nr;
+
+	if (setsockopt(fd, SOL_PACKET, PACKET_RX_RING, &req3, sizeof(req3)))
+		error(1, errno, "setsockopt PACKET_RX_RING");
+
+	ring_block_sz = req3.tp_block_size;
+	ring_block_nr = req3.tp_block_nr;
+
+	ring = mmap(0, req3.tp_block_size * req3.tp_block_nr,
+		    PROT_READ | PROT_WRITE,
+		    MAP_SHARED | MAP_LOCKED | MAP_POPULATE, fd, 0);
+	if (ring == MAP_FAILED)
+		error(1, 0, "mmap failed");
+
+	return ring;
+}
+
+static void __set_filter(int fd, int off_proto, uint8_t proto, int off_dport)
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_LD  + BPF_B   + BPF_ABS, SKF_AD_OFF + SKF_AD_PKTTYPE),
+		BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, PACKET_HOST, 0, 4),
+		BPF_STMT(BPF_LD  + BPF_B   + BPF_ABS, off_proto),
+		BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, proto, 0, 2),
+		BPF_STMT(BPF_LD  + BPF_H   + BPF_ABS, off_dport),
+		BPF_JUMP(BPF_JMP + BPF_JEQ + BPF_K, cfg_dport, 1, 0),
+		BPF_STMT(BPF_RET + BPF_K, 0),
+		BPF_STMT(BPF_RET + BPF_K, 0xFFFF),
+	};
+	struct sock_fprog prog = {};
+
+	prog.filter = filter;
+	prog.len = ARRAY_SIZE(filter);
+	if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &prog, sizeof(prog)))
+		error(1, errno, "setsockopt filter");
+}
+
+/* filter on transport protocol and destination port */
+static void set_filter(int fd)
+{
+	const int off_dport = offsetof(struct tcphdr, dest);	/* same for udp */
+	uint8_t proto;
+
+	proto = cfg_type == SOCK_STREAM ? IPPROTO_TCP : IPPROTO_UDP;
+	if (cfg_family == AF_INET)
+		__set_filter(fd, offsetof(struct iphdr, protocol), proto,
+			     sizeof(struct iphdr) + off_dport);
+	else
+		__set_filter(fd, offsetof(struct ip6_hdr, ip6_nxt), proto,
+			     sizeof(struct ip6_hdr) + off_dport);
+}
+
+/* drop everything: used temporarily during setup */
+static void set_filter_null(int fd)
+{
+	struct sock_filter filter[] = {
+		BPF_STMT(BPF_RET + BPF_K, 0),
+	};
+	struct sock_fprog prog = {};
+
+	prog.filter = filter;
+	prog.len = ARRAY_SIZE(filter);
+	if (setsockopt(fd, SOL_SOCKET, SO_ATTACH_FILTER, &prog, sizeof(prog)))
+		error(1, errno, "setsockopt filter");
+}
+
+static int create_ring(char **ring)
+{
+	struct fanout_args args = {
+		.id = 1,
+		.type_flags = PACKET_FANOUT_CPU,
+		.max_num_members = RSS_MAX_CPUS
+	};
+	struct sockaddr_ll ll = { 0 };
+	int fd, val;
+
+	fd = socket(PF_PACKET, SOCK_DGRAM, 0);
+	if (fd == -1)
+		error(1, errno, "socket creation failed");
+
+	val = TPACKET_V3;
+	if (setsockopt(fd, SOL_PACKET, PACKET_VERSION, &val, sizeof(val)))
+		error(1, errno, "setsockopt PACKET_VERSION");
+	*ring = setup_ring(fd);
+
+	/* block packets until all rings are added to the fanout group:
+	 * else packets can arrive during setup and get misclassified
+	 */
+	set_filter_null(fd);
+
+	ll.sll_family = AF_PACKET;
+	ll.sll_ifindex = if_nametoindex(cfg_ifname);
+	ll.sll_protocol = cfg_family == AF_INET ? htons(ETH_P_IP) :
+						  htons(ETH_P_IPV6);
+	if (bind(fd, (void *)&ll, sizeof(ll)))
+		error(1, errno, "bind");
+
+	/* must come after bind: verifies all programs in group match */
+	if (setsockopt(fd, SOL_PACKET, PACKET_FANOUT, &args, sizeof(args))) {
+		/* on failure, retry using old API if that is sufficient:
+		 * it has a hard limit of 256 sockets, so only try if
+		 * (a) only testing rxhash, not RSS or (b) <= 256 cpus.
+		 * in this API, the third argument is left implicit.
+		 */
+		if (cfg_num_queues || num_cpus > 256 ||
+		    setsockopt(fd, SOL_PACKET, PACKET_FANOUT,
+			       &args, sizeof(uint32_t)))
+			error(1, errno, "setsockopt PACKET_FANOUT cpu");
+	}
+
+	return fd;
+}
+
+/* setup inet(6) socket to blackhole the test traffic, if arg '-s' */
+static int setup_sink(void)
+{
+	int fd, val;
+
+	fd = socket(cfg_family, cfg_type, 0);
+	if (fd == -1)
+		error(1, errno, "socket %d.%d", cfg_family, cfg_type);
+
+	val = 1 << 20;
+	if (setsockopt(fd, SOL_SOCKET, SO_RCVBUFFORCE, &val, sizeof(val)))
+		error(1, errno, "setsockopt rcvbuf");
+
+	return fd;
+}
+
+static void setup_rings(void)
+{
+	int i;
+
+	for (i = 0; i < num_cpus; i++) {
+		rings[i].cpu = i;
+		rings[i].fd = create_ring(&rings[i].mmap);
+	}
+
+	/* accept packets once all rings in the fanout group are up */
+	for (i = 0; i < num_cpus; i++)
+		set_filter(rings[i].fd);
+}
+
+static void cleanup_rings(void)
+{
+	int i;
+
+	for (i = 0; i < num_cpus; i++) {
+		if (munmap(rings[i].mmap, ring_block_nr * ring_block_sz))
+			error(1, errno, "munmap");
+		if (close(rings[i].fd))
+			error(1, errno, "close");
+	}
+}
+
+static void parse_cpulist(const char *arg)
+{
+	do {
+		rx_irq_cpus[cfg_num_queues++] = strtol(arg, NULL, 10);
+
+		arg = strchr(arg, ',');
+		if (!arg)
+			break;
+		arg++;			// skip ','
+	} while (1);
+}
+
+static void show_cpulist(void)
+{
+	int i;
+
+	for (i = 0; i < cfg_num_queues; i++)
+		fprintf(stderr, "rxq %d: cpu %d\n", i, rx_irq_cpus[i]);
+}
+
+static void show_silos(void)
+{
+	int i;
+
+	for (i = 0; i < cfg_num_rps_cpus; i++)
+		fprintf(stderr, "silo %d: cpu %d\n", i, rps_silo_to_cpu[i]);
+}
+
+static void parse_toeplitz_key(const char *str, int slen, unsigned char *key)
+{
+	int i, ret, off;
+
+	if (slen < TOEPLITZ_STR_MIN_LEN ||
+	    slen > TOEPLITZ_STR_MAX_LEN + 1)
+		error(1, 0, "invalid toeplitz key");
+
+	for (i = 0, off = 0; off < slen; i++, off += 3) {
+		ret = sscanf(str + off, "%hhx", &key[i]);
+		if (ret != 1)
+			error(1, 0, "key parse error at %d off %d len %d",
+			      i, off, slen);
+	}
+}
+
+static void parse_rps_bitmap(const char *arg)
+{
+	unsigned long bitmap;
+	int i;
+
+	bitmap = strtoul(arg, NULL, 0);
+
+	if (bitmap & ~((1UL << RPS_MAX_CPUS) - 1))
+		error(1, 0, "rps bitmap 0x%lx out of bounds, max cpu %lu",
+		      bitmap, RPS_MAX_CPUS - 1);
+
+	for (i = 0; i < RPS_MAX_CPUS; i++)
+		if (bitmap & 1UL << i)
+			rps_silo_to_cpu[cfg_num_rps_cpus++] = i;
+}
+
+static void read_rss_dev_info_ynl(void)
+{
+	struct ethtool_rss_get_req *req;
+	struct ethtool_rss_get_rsp *rsp;
+	struct ynl_sock *ys;
+
+	ys = ynl_sock_create(&ynl_ethtool_family, NULL);
+	if (!ys)
+		error(1, errno, "ynl_sock_create failed");
+
+	req = ethtool_rss_get_req_alloc();
+	if (!req)
+		error(1, errno, "ethtool_rss_get_req_alloc failed");
+
+	ethtool_rss_get_req_set_header_dev_name(req, cfg_ifname);
+
+	rsp = ethtool_rss_get(ys, req);
+	if (!rsp)
+		error(1, ys->err.code, "YNL: %s", ys->err.msg);
+
+	if (!rsp->_len.hkey)
+		error(1, 0, "RSS key not available for %s", cfg_ifname);
+
+	if (rsp->_len.hkey < TOEPLITZ_KEY_MIN_LEN ||
+	    rsp->_len.hkey > TOEPLITZ_KEY_MAX_LEN)
+		error(1, 0, "RSS key length %u out of bounds [%u, %u]",
+		      rsp->_len.hkey, TOEPLITZ_KEY_MIN_LEN,
+		      TOEPLITZ_KEY_MAX_LEN);
+
+	memcpy(toeplitz_key, rsp->hkey, rsp->_len.hkey);
+
+	if (rsp->_count.indir > RSS_MAX_INDIR)
+		error(1, 0, "RSS indirection table too large (%u > %u)",
+		      rsp->_count.indir, RSS_MAX_INDIR);
+
+	/* If indir table not available we'll fallback to simple modulo math */
+	if (rsp->_count.indir) {
+		memcpy(rss_indir_tbl, rsp->indir,
+		       rsp->_count.indir * sizeof(rss_indir_tbl[0]));
+		rss_indir_tbl_size = rsp->_count.indir;
+
+		log_verbose("RSS indirection table size: %u\n",
+			    rss_indir_tbl_size);
+	}
+
+	ethtool_rss_get_rsp_free(rsp);
+	ethtool_rss_get_req_free(req);
+	ynl_sock_destroy(ys);
+}
+
+static void parse_opts(int argc, char **argv)
+{
+	static struct option long_options[] = {
+	    {"dport",	required_argument, 0, 'd'},
+	    {"cpus",	required_argument, 0, 'C'},
+	    {"key",	required_argument, 0, 'k'},
+	    {"iface",	required_argument, 0, 'i'},
+	    {"ipv4",	no_argument, 0, '4'},
+	    {"ipv6",	no_argument, 0, '6'},
+	    {"sink",	no_argument, 0, 's'},
+	    {"tcp",	no_argument, 0, 't'},
+	    {"timeout",	required_argument, 0, 'T'},
+	    {"udp",	no_argument, 0, 'u'},
+	    {"verbose",	no_argument, 0, 'v'},
+	    {"rps",	required_argument, 0, 'r'},
+	    {0, 0, 0, 0}
+	};
+	bool have_toeplitz = false;
+	int index, c;
+
+	while ((c = getopt_long(argc, argv, "46C:d:i:k:r:stT:uv", long_options, &index)) != -1) {
+		switch (c) {
+		case '4':
+			cfg_family = AF_INET;
+			break;
+		case '6':
+			cfg_family = AF_INET6;
+			break;
+		case 'C':
+			parse_cpulist(optarg);
+			break;
+		case 'd':
+			cfg_dport = strtol(optarg, NULL, 0);
+			break;
+		case 'i':
+			cfg_ifname = optarg;
+			break;
+		case 'k':
+			parse_toeplitz_key(optarg, strlen(optarg),
+					   toeplitz_key);
+			have_toeplitz = true;
+			break;
+		case 'r':
+			parse_rps_bitmap(optarg);
+			break;
+		case 's':
+			cfg_sink = true;
+			break;
+		case 't':
+			cfg_type = SOCK_STREAM;
+			break;
+		case 'T':
+			cfg_timeout_msec = strtol(optarg, NULL, 0);
+			break;
+		case 'u':
+			cfg_type = SOCK_DGRAM;
+			break;
+		case 'v':
+			cfg_verbose = true;
+			break;
+
+		default:
+			error(1, 0, "unknown option %c", optopt);
+			break;
+		}
+	}
+
+	if (!have_toeplitz)
+		read_rss_dev_info_ynl();
+
+	num_cpus = get_nprocs();
+	if (num_cpus > RSS_MAX_CPUS)
+		error(1, 0, "increase RSS_MAX_CPUS");
+
+	if (cfg_num_queues && cfg_num_rps_cpus)
+		error(1, 0,
+		      "Can't supply both RSS cpus ('-C') and RPS map ('-r')");
+	if (cfg_verbose) {
+		show_cpulist();
+		show_silos();
+	}
+}
+
+int main(int argc, char **argv)
+{
+	const int min_tests = 10;
+	int fd_sink = -1;
+
+	parse_opts(argc, argv);
+
+	if (cfg_sink)
+		fd_sink = setup_sink();
+
+	setup_rings();
+
+	/* Signal to test framework that we're ready to receive */
+	ksft_ready();
+
+	process_rings();
+	cleanup_rings();
+
+	if (cfg_sink && close(fd_sink))
+		error(1, errno, "close sink");
+
+	if (frames_received - frames_nohash < min_tests)
+		error(1, 0, "too few frames for verification");
+
+	return frames_error;
+}

linux-7.2.3/tools/testing/selftests/drivers/net/hw/toeplitz.py

@@ -0,0 +1,216 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""
+Toeplitz Rx hashing test:
+ - rxhash (the hash value calculation itself);
+ - RSS mapping from rxhash to rx queue;
+ - RPS mapping from rxhash to cpu.
+"""
+
+import glob
+import os
+import socket
+from lib.py import ksft_run, ksft_exit, ksft_pr
+from lib.py import NetDrvEpEnv, EthtoolFamily, NetdevFamily
+from lib.py import cmd, bkg, rand_port, defer
+from lib.py import ksft_in
+from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx, KsftFailEx
+
+# "define" for the ID of the Toeplitz hash function
+ETH_RSS_HASH_TOP = 1
+# Must match RPS_MAX_CPUS in toeplitz.c
+RPS_MAX_CPUS = 16
+
+
+def _check_rps_and_rfs_not_configured(cfg):
+    """Verify that RPS is not already configured."""
+
+    for rps_file in glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*/rps_cpus"):
+        with open(rps_file, "r", encoding="utf-8") as fp:
+            val = fp.read().strip()
+            if set(val) - {"0", ","}:
+                raise KsftSkipEx(f"RPS already configured on {rps_file}: {val}")
+
+    rfs_file = "/proc/sys/net/core/rps_sock_flow_entries"
+    with open(rfs_file, "r", encoding="utf-8") as fp:
+        val = fp.read().strip()
+        if val != "0":
+            raise KsftSkipEx(f"RFS already configured {rfs_file}: {val}")
+
+
+def _get_cpu_for_irq(irq):
+    with open(f"/proc/irq/{irq}/smp_affinity_list", "r",
+              encoding="utf-8") as fp:
+        data = fp.read().strip()
+        if "," in data or "-" in data:
+            raise KsftFailEx(f"IRQ{irq} is not mapped to a single core: {data}")
+        return int(data)
+
+
+def _get_irq_cpus(cfg):
+    """
+    Read the list of IRQs for the device Rx queues.
+    """
+    queues = cfg.netnl.queue_get({"ifindex": cfg.ifindex}, dump=True)
+    napis = cfg.netnl.napi_get({"ifindex": cfg.ifindex}, dump=True)
+
+    # Remap into ID-based dicts
+    napis = {n["id"]: n for n in napis}
+    queues = {f"{q['type']}{q['id']}": q for q in queues}
+
+    cpus = []
+    for rx in range(9999):
+        name = f"rx{rx}"
+        if name not in queues:
+            break
+        cpus.append(_get_cpu_for_irq(napis[queues[name]["napi-id"]]["irq"]))
+
+    return cpus
+
+
+def _get_unused_rps_cpus(cfg, count=2):
+    """
+    Get CPUs that are not used by Rx queues for RPS.
+    Returns a list of at least 'count' CPU numbers within
+    the RPS_MAX_CPUS supported range.
+    """
+
+    # Get CPUs used by Rx queues
+    rx_cpus = set(_get_irq_cpus(cfg))
+
+    # Get total number of CPUs, capped by RPS_MAX_CPUS
+    num_cpus = min(os.cpu_count(), RPS_MAX_CPUS)
+
+    # Find unused CPUs
+    unused_cpus = [cpu for cpu in range(num_cpus) if cpu not in rx_cpus]
+
+    if len(unused_cpus) < count:
+        raise KsftSkipEx(f"Need at least {count} CPUs in range 0..{num_cpus - 1} not used by Rx queues, found {len(unused_cpus)}")
+
+    return unused_cpus[:count]
+
+
+def _configure_rps(cfg, rps_cpus):
+    """Configure RPS for all Rx queues."""
+
+    mask = 0
+    for cpu in rps_cpus:
+        mask |= (1 << cpu)
+
+    mask = hex(mask)
+
+    # Set RPS bitmap for all rx queues
+    for rps_file in glob.glob(f"/sys/class/net/{cfg.ifname}/queues/rx-*/rps_cpus"):
+        with open(rps_file, "w", encoding="utf-8") as fp:
+            # sysfs expects hex without '0x' prefix, toeplitz.c needs the prefix
+            fp.write(mask[2:])
+
+    return mask
+
+
+def _send_traffic(cfg, proto_flag, ipver, port):
+    """Send 20 packets of requested type."""
+
+    # Determine protocol and IP version for socat
+    if proto_flag == "-u":
+        proto = "UDP"
+    else:
+        proto = "TCP"
+
+    baddr = f"[{cfg.addr_v['6']}]" if ipver == "6" else cfg.addr_v["4"]
+
+    # Run socat in a loop to send traffic periodically
+    # Use sh -c with a loop similar to toeplitz_client.sh
+    socat_cmd = f"""
+    for i in `seq 20`; do
+        echo "msg $i" | socat -{ipver} -t 0.1 - {proto}:{baddr}:{port};
+        sleep 0.001;
+    done
+    """
+
+    cmd(socat_cmd, shell=True, host=cfg.remote)
+
+
+def _test_variants():
+    for grp in ["", "rss", "rps"]:
+        for l4 in ["tcp", "udp"]:
+            for l3 in ["4", "6"]:
+                name = f"{l4}_ipv{l3}"
+                if grp:
+                    name = f"{grp}_{name}"
+                yield KsftNamedVariant(name, "-" + l4[0], l3, grp)
+
+
+@ksft_variants(_test_variants())
+def test(cfg, proto_flag, ipver, grp):
+    """Run a single toeplitz test."""
+
+    cfg.require_ipver(ipver)
+
+    # Check that rxhash is enabled
+    ksft_in("receive-hashing: on", cmd(f"ethtool -k {cfg.ifname}").stdout)
+
+    rss = cfg.ethnl.rss_get({"header": {"dev-index": cfg.ifindex}})
+    # Make sure NIC is configured to use Toeplitz hash, and no key xfrm.
+    if rss.get('hfunc') != ETH_RSS_HASH_TOP or rss.get('input-xfrm'):
+        cfg.ethnl.rss_set({"header": {"dev-index": cfg.ifindex},
+                           "hfunc": ETH_RSS_HASH_TOP,
+                           "input-xfrm": {}})
+        defer(cfg.ethnl.rss_set, {"header": {"dev-index": cfg.ifindex},
+                                  "hfunc": rss.get('hfunc'),
+                                  "input-xfrm": rss.get('input-xfrm', {})
+                                  })
+
+    port = rand_port(socket.SOCK_DGRAM)
+
+    toeplitz_path = cfg.test_dir / "toeplitz"
+    rx_cmd = [
+        str(toeplitz_path),
+        "-" + ipver,
+        proto_flag,
+        "-d", str(port),
+        "-i", cfg.ifname,
+        "-T", "4000",
+        "-s",
+        "-v"
+    ]
+
+    if grp:
+        _check_rps_and_rfs_not_configured(cfg)
+    if grp == "rss":
+        irq_cpus = ",".join([str(x) for x in _get_irq_cpus(cfg)])
+        rx_cmd += ["-C", irq_cpus]
+        ksft_pr(f"RSS using CPUs: {irq_cpus}")
+    elif grp == "rps":
+        # Get CPUs not used by Rx queues and configure them for RPS
+        rps_cpus = _get_unused_rps_cpus(cfg, count=2)
+        rps_mask = _configure_rps(cfg, rps_cpus)
+        defer(_configure_rps, cfg, [])
+        rx_cmd += ["-r", rps_mask]
+        ksft_pr(f"RPS using CPUs: {rps_cpus}, mask: {rps_mask}")
+
+    # Run rx in background, it will exit once it has seen enough packets
+    with bkg(" ".join(rx_cmd), ksft_ready=True, exit_wait=True) as rx_proc:
+        while rx_proc.proc.poll() is None:
+            _send_traffic(cfg, proto_flag, ipver, port)
+
+    # Check rx result
+    ksft_pr("Receiver output:")
+    ksft_pr(rx_proc.stdout.strip().replace('\n', '\n# '))
+    if rx_proc.stderr:
+        ksft_pr(rx_proc.stderr.strip().replace('\n', '\n# '))
+
+
+def main() -> None:
+    """Ksft boilerplate main."""
+
+    with NetDrvEpEnv(__file__) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        cfg.netnl = NetdevFamily()
+        ksft_run(cases=[test], args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/tso.py

@@ -0,0 +1,263 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""Run the tools/testing/selftests/net/csum testsuite."""
+
+import fcntl
+import socket
+import struct
+import termios
+import time
+
+from lib.py import ksft_pr, ksft_run, ksft_exit, KsftSkipEx, KsftXfailEx
+from lib.py import ksft_eq, ksft_ge, ksft_lt
+from lib.py import EthtoolFamily, NetdevFamily, NetDrvEpEnv
+from lib.py import bkg, cmd, defer, ethtool, ip, rand_port, wait_port_listen
+
+
+def sock_wait_drain(sock, max_wait=1000):
+    """Wait for all pending write data on the socket to get ACKed."""
+    for _ in range(max_wait):
+        one = b'\0' * 4
+        outq = fcntl.ioctl(sock.fileno(), termios.TIOCOUTQ, one)
+        outq = struct.unpack("I", outq)[0]
+        if outq == 0:
+            break
+        time.sleep(0.01)
+    ksft_eq(outq, 0)
+
+
+def tcp_sock_get_retrans(sock):
+    """Get the number of retransmissions for the TCP socket."""
+    info = sock.getsockopt(socket.SOL_TCP, socket.TCP_INFO, 512)
+    return struct.unpack("I", info[100:104])[0]
+
+
+def run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso):
+    cfg.require_cmd("socat", local=False, remote=True)
+
+    # Set recv window clamp to avoid overwhelming receiver on debug kernels
+    # the 200k clamp should still let use reach > 15Gbps on real HW
+    port = rand_port()
+    listen_opts = f"{port},reuseport,tcp-window-clamp=200000"
+    listen_cmd = f"socat -{ipver} -t 2 -u TCP-LISTEN:{listen_opts} /dev/null,ignoreeof"
+
+    with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as nc:
+        wait_port_listen(port, host=cfg.remote)
+
+        if ipver == "4":
+            sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+            sock.connect((remote_v4, port))
+        else:
+            sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
+            sock.connect((remote_v6, port))
+
+        # Small send to make sure the connection is working.
+        sock.send("ping".encode())
+        sock_wait_drain(sock)
+
+        # Send 4MB of data, record the LSO packet count.
+        qstat_old = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+        buf = b"0" * 1024 * 1024 * 4
+        sock.send(buf)
+        sock_wait_drain(sock)
+        qstat_new = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+
+        # Check that at least 90% of the data was sent as LSO packets.
+        # System noise may cause false negatives. Also header overheads
+        # will add up to 5% of extra packes... The check is best effort.
+        total_lso_wire  = len(buf) * 0.90 // cfg.dev["mtu"]
+        total_lso_super = len(buf) * 0.90 // cfg.dev["tso_max_size"]
+
+        # Make sure we have order of magnitude more LSO packets than
+        # retransmits, in case TCP retransmitted all the LSO packets.
+        ksft_lt(tcp_sock_get_retrans(sock), total_lso_wire / 16)
+        sock.close()
+
+        if should_lso:
+            if cfg.have_stat_super_count:
+                ksft_ge(qstat_new['tx-hw-gso-packets'] -
+                        qstat_old['tx-hw-gso-packets'],
+                        total_lso_super,
+                        comment="Number of LSO super-packets with LSO enabled")
+            if cfg.have_stat_wire_count:
+                ksft_ge(qstat_new['tx-hw-gso-wire-packets'] -
+                        qstat_old['tx-hw-gso-wire-packets'],
+                        total_lso_wire,
+                        comment="Number of LSO wire-packets with LSO enabled")
+        else:
+            if cfg.have_stat_super_count:
+                ksft_lt(qstat_new['tx-hw-gso-packets'] -
+                        qstat_old['tx-hw-gso-packets'],
+                        15, comment="Number of LSO super-packets with LSO disabled")
+            if cfg.have_stat_wire_count:
+                ksft_lt(qstat_new['tx-hw-gso-wire-packets'] -
+                        qstat_old['tx-hw-gso-wire-packets'],
+                        500, comment="Number of LSO wire-packets with LSO disabled")
+
+
+def build_tunnel(cfg, outer_ipver, tun_info):
+    local_v4  = NetDrvEpEnv.nsim_v4_pfx + "1"
+    local_v6  = NetDrvEpEnv.nsim_v6_pfx + "1"
+    remote_v4 = NetDrvEpEnv.nsim_v4_pfx + "2"
+    remote_v6 = NetDrvEpEnv.nsim_v6_pfx + "2"
+
+    local_addr  = cfg.addr_v[outer_ipver]
+    remote_addr = cfg.remote_addr_v[outer_ipver]
+
+    tun_type = tun_info[0]
+    tun_arg  = tun_info[1]
+    ip(f"link add {tun_type}-ksft type {tun_type} {tun_arg} local {local_addr} remote {remote_addr} dev {cfg.ifname}")
+    defer(ip, f"link del {tun_type}-ksft")
+    ip(f"link set dev {tun_type}-ksft up")
+    ip(f"addr add {local_v4}/24 dev {tun_type}-ksft")
+    ip(f"addr add {local_v6}/64 dev {tun_type}-ksft")
+
+    ip(f"link add {tun_type}-ksft type {tun_type} {tun_arg} local {remote_addr} remote {local_addr} dev {cfg.remote_ifname}",
+        host=cfg.remote)
+    defer(ip, f"link del {tun_type}-ksft", host=cfg.remote)
+    ip(f"link set dev {tun_type}-ksft up", host=cfg.remote)
+    ip(f"addr add {remote_v4}/24 dev {tun_type}-ksft", host=cfg.remote)
+    ip(f"addr add {remote_v6}/64 dev {tun_type}-ksft", host=cfg.remote)
+
+    return remote_v4, remote_v6
+
+
+def restore_wanted_features(cfg):
+    features_cmd = ""
+    for feature in cfg.hw_features:
+        setting = "on" if feature in cfg.wanted_features else "off"
+        features_cmd += f" {feature} {setting}"
+    try:
+        ethtool(f"-K {cfg.ifname} {features_cmd}")
+    except Exception as e:
+        ksft_pr(f"WARNING: failure restoring wanted features: {e}")
+
+
+def test_builder(name, cfg, outer_ipver, feature, tun=None, inner_ipver=None):
+    """Construct specific tests from the common template."""
+    def f(cfg):
+        cfg.require_ipver(outer_ipver)
+        defer(restore_wanted_features, cfg)
+
+        if not cfg.have_stat_super_count and \
+           not cfg.have_stat_wire_count:
+            raise KsftSkipEx(f"Device does not support LSO queue stats")
+
+        if feature not in cfg.hw_features:
+            raise KsftSkipEx(f"Device does not support {feature}")
+
+        ipver = outer_ipver
+        if tun:
+            remote_v4, remote_v6 = build_tunnel(cfg, ipver, tun)
+            ipver = inner_ipver
+        else:
+            remote_v4 = cfg.remote_addr_v["4"]
+            remote_v6 = cfg.remote_addr_v["6"]
+
+        # First test without the feature enabled.
+        ethtool(f"-K {cfg.ifname} {feature} off")
+        run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=False)
+
+        ethtool(f"-K {cfg.ifname} tx-gso-partial off")
+        ethtool(f"-K {cfg.ifname} tx-tcp-mangleid-segmentation off")
+        if feature in cfg.partial_features:
+            ethtool(f"-K {cfg.ifname} tx-gso-partial on")
+            if ipver == "4":
+                ksft_pr("Testing with mangleid enabled")
+                ethtool(f"-K {cfg.ifname} tx-tcp-mangleid-segmentation on")
+
+        # Full feature enabled.
+        ethtool(f"-K {cfg.ifname} {feature} on")
+        run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=True)
+
+    f.__name__ = name + ((outer_ipver + "_") if tun else "") + "ipv" + inner_ipver
+    return f
+
+
+def query_nic_features(cfg) -> None:
+    """Query and cache the NIC features."""
+    cfg.have_stat_super_count = False
+    cfg.have_stat_wire_count = False
+
+    features = cfg.ethnl.features_get({"header": {"dev-index": cfg.ifindex}})
+
+    cfg.wanted_features = set()
+    for f in features["wanted"]["bits"]["bit"]:
+        cfg.wanted_features.add(f["name"])
+
+    cfg.hw_features = set()
+    for f in features["hw"]["bits"]["bit"]:
+        if f.get("value", False):
+            cfg.hw_features.add(f["name"])
+
+    # Check which features are supported via GSO partial
+    cfg.partial_features = set()
+    if 'tx-gso-partial' in cfg.hw_features:
+        seg_features = {f for f in cfg.hw_features if "segmentation" in f}
+        ethtool(f"-K {cfg.ifname} " +
+                " ".join(f"{f} on" for f in seg_features))
+
+        ethtool(f"-K {cfg.ifname} tx-gso-partial off")
+
+        no_partial = set()
+        features = cfg.ethnl.features_get({"header": {"dev-index": cfg.ifindex}})
+        for f in features["active"]["bits"]["bit"]:
+            no_partial.add(f["name"])
+        cfg.partial_features = seg_features - no_partial
+        ethtool(f"-K {cfg.ifname} tx-gso-partial on")
+
+    restore_wanted_features(cfg)
+
+    stats = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)
+    if stats:
+        if 'tx-hw-gso-packets' in stats[0]:
+            ksft_pr("Detected qstat for LSO super-packets")
+            cfg.have_stat_super_count = True
+        if 'tx-hw-gso-wire-packets' in stats[0]:
+            ksft_pr("Detected qstat for LSO wire-packets")
+            cfg.have_stat_wire_count = True
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        cfg.netnl = NetdevFamily()
+
+        query_nic_features(cfg)
+
+        test_info = (
+            # name,       v4/v6  ethtool_feature               tun:(type, args, inner ip versions)
+            ("",           "4", "tx-tcp-segmentation",         None),
+            ("",           "6", "tx-tcp6-segmentation",        None),
+            ("vxlan",      "4", "tx-udp_tnl-segmentation",     ("vxlan", "id 100 dstport 4789 noudpcsum", ("4", "6"))),
+            ("vxlan",      "6", "tx-udp_tnl-segmentation",     ("vxlan", "id 100 dstport 4789 udp6zerocsumtx udp6zerocsumrx", ("4", "6"))),
+            ("vxlan_csum", "", "tx-udp_tnl-csum-segmentation", ("vxlan", "id 100 dstport 4789 udpcsum", ("4", "6"))),
+            ("gre",        "4", "tx-gre-segmentation",         ("gre",   "", ("4", "6"))),
+            ("gre",        "6", "tx-gre-segmentation",         ("ip6gre","", ("4", "6"))),
+            ("ip",         "6", "tx-ipxip6-segmentation",      ("ip6tnl","mode any", ("4", "6"))),
+            ("ip",         "4", "tx-ipxip4-segmentation",      ("sit","", ("6", ))),
+            ("ip",         "4", "tx-ipxip4-segmentation",      ("ipip","", ("4", ))),
+        )
+
+        cases = []
+        for outer_ipver in ["4", "6"]:
+            for info in test_info:
+                # Skip if test which only works for a specific IP version
+                if info[1] and outer_ipver != info[1]:
+                    continue
+
+                if info[3]:
+                    cases += [
+                        test_builder(info[0], cfg, outer_ipver, info[2], info[3], inner_ipver)
+                        for inner_ipver in info[3][2]
+                    ]
+                else:
+                    cases.append(test_builder(info[0], cfg, outer_ipver, info[2], None, outer_ipver))
+
+        ksft_run(cases=cases, args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/userns_devmem.py

@@ -0,0 +1,49 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+"""
+Devmem tests for non-init userns.
+"""
+
+import os
+
+from devmem_lib import run_rx, run_rx_hds, run_tx, run_tx_chunks, setup_test
+from lib.py import NetDrvContEnv, ksft_disruptive, ksft_exit, ksft_run
+
+
+@ksft_disruptive
+def check_userns_rx(cfg) -> None:
+    """Run the devmem RX test through non-init userns netkit."""
+    run_rx(cfg)
+
+
+@ksft_disruptive
+def check_userns_tx(cfg) -> None:
+    """Run the devmem TX test through non-init userns netkit."""
+    run_tx(cfg)
+
+
+@ksft_disruptive
+def check_userns_tx_chunks(cfg) -> None:
+    """Run the devmem TX chunking test through non-init userns netkit."""
+    run_tx_chunks(cfg)
+
+
+def check_userns_rx_hds(cfg) -> None:
+    """Run the HDS test through non-init userns netkit."""
+    run_rx_hds(cfg)
+
+
+def main() -> None:
+    """Run userns devmem RX selftests against the test environment."""
+    with NetDrvContEnv(__file__, userns=True, rxqueues=2,
+                       primary_rx_redirect=True) as cfg:
+        setup_test(cfg,
+                   os.path.join(os.path.dirname(os.path.abspath(__file__)),
+                                "ncdevmem"))
+        ksft_run([check_userns_rx, check_userns_tx, check_userns_tx_chunks,
+                  check_userns_rx_hds], args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/uso.py

@@ -0,0 +1,103 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""Test USO
+
+Sends large UDP datagrams with UDP_SEGMENT and verifies that the peer
+receives the expected total payload and that the NIC transmitted at least
+the expected number of segments.
+"""
+import random
+import socket
+import string
+
+from lib.py import ksft_run, ksft_exit, KsftSkipEx
+from lib.py import ksft_eq, ksft_ge, ksft_variants, KsftNamedVariant
+from lib.py import NetDrvEpEnv
+from lib.py import bkg, defer, ethtool, ip, rand_port, wait_port_listen
+
+# python doesn't expose this constant, so we need to hardcode it to enable UDP
+# segmentation for large payloads
+UDP_SEGMENT = 103
+
+
+def _send_uso(cfg, ipver, mss, total_payload, port):
+    if ipver == "4":
+        sock = socket.socket(socket.AF_INET, socket.SOCK_DGRAM)
+        dst = (cfg.remote_addr_v["4"], port)
+    else:
+        sock = socket.socket(socket.AF_INET6, socket.SOCK_DGRAM)
+        dst = (cfg.remote_addr_v["6"], port)
+
+    sock.setsockopt(socket.IPPROTO_UDP, UDP_SEGMENT, mss)
+    payload = ''.join(random.choice(string.ascii_lowercase)
+                      for _ in range(total_payload))
+    sock.sendto(payload.encode(), dst)
+    sock.close()
+
+
+def _get_tx_packets(cfg):
+    stats = ip(f"-s link show dev {cfg.ifname}", json=True)[0]
+    return stats['stats64']['tx']['packets']
+
+
+def _test_uso(cfg, ipver, mss, total_payload):
+    cfg.require_ipver(ipver)
+    cfg.require_cmd("socat", remote=True)
+
+    features = ethtool(f"-k {cfg.ifname}", json=True)
+    uso_was_on = features[0]["tx-udp-segmentation"]["active"]
+
+    try:
+        ethtool(f"-K {cfg.ifname} tx-udp-segmentation on")
+    except Exception as exc:
+        raise KsftSkipEx(
+            "Device does not support tx-udp-segmentation") from exc
+    if not uso_was_on:
+        defer(ethtool, f"-K {cfg.ifname} tx-udp-segmentation off")
+
+    expected_segs = (total_payload + mss - 1) // mss
+
+    port = rand_port(stype=socket.SOCK_DGRAM)
+    rx_cmd = f"socat -{ipver} -T 2 -u UDP-LISTEN:{port},reuseport STDOUT"
+
+    tx_before = _get_tx_packets(cfg)
+
+    with bkg(rx_cmd, host=cfg.remote, exit_wait=True) as rx:
+        wait_port_listen(port, proto="udp", host=cfg.remote)
+        _send_uso(cfg, ipver, mss, total_payload, port)
+
+    ksft_eq(len(rx.stdout), total_payload,
+            comment=f"Received {len(rx.stdout)}B, expected {total_payload}B")
+
+    cfg.wait_hw_stats_settle()
+
+    tx_after = _get_tx_packets(cfg)
+    tx_delta = tx_after - tx_before
+
+    ksft_ge(tx_delta, expected_segs,
+            comment=f"Expected >= {expected_segs} tx packets, got {tx_delta}")
+
+
+def _uso_variants():
+    for ipver in ["4", "6"]:
+        yield KsftNamedVariant(f"v{ipver}_partial", ipver, 1400, 1400 * 10 + 500)
+        yield KsftNamedVariant(f"v{ipver}_exact", ipver, 1400, 1400 * 5)
+
+
+@ksft_variants(_uso_variants())
+def test_uso(cfg, ipver, mss, total_payload):
+    """Send a USO datagram and verify the peer receives the expected segments."""
+    _test_uso(cfg, ipver, mss, total_payload)
+
+
+def main() -> None:
+    """Run USO tests."""
+    with NetDrvEpEnv(__file__) as cfg:
+        ksft_run([test_uso],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/xdp_metadata.py

@@ -0,0 +1,146 @@
+#!/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_eq, 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
+
+XDP_RSS_L4 = 0x8  # BIT(3) from enum xdp_rss_hash_type
+
+
+@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, comment="should have received at least one packet")
+    ksft_eq(err_cnt, 0, comment=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}")
+    ksft_ne(hash_type & XDP_RSS_L4, 0,
+            f"RSS hash type should include L4 for {proto.upper()} traffic")
+
+
+def main():
+    """Run XDP metadata kfunc tests against a real device."""
+    with NetDrvEpEnv(__file__) as cfg:
+        cfg.netnl = NetdevFamily()
+        ksft_run(
+            [
+                test_xdp_rss_hash,
+            ],
+            args=(cfg,))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

linux-7.2.3/tools/testing/selftests/drivers/net/hw/xsk_reconfig.py

@@ -0,0 +1,60 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+# This is intended to be run on a virtio-net guest interface.
+# The test binds the XDP socket to the interface without setting
+# the fill ring to trigger delayed refill_work. This helps to
+# make it easier to reproduce the deadlock when XDP program,
+# XDP socket bind/unbind, rx ring resize race with refill_work on
+# the buggy kernel.
+#
+# The Qemu command to setup virtio-net
+# -netdev tap,id=hostnet1,vhost=on,script=no,downscript=no
+# -device virtio-net-pci,netdev=hostnet1,iommu_platform=on,disable-legacy=on
+
+from lib.py import ksft_exit, ksft_run
+from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import NetDrvEnv
+from lib.py import bkg, ip, cmd, ethtool
+import time
+
+def _get_rx_ring_entries(cfg):
+    output = ethtool(f"-g {cfg.ifname}", json=True)
+    return output[0]["rx"]
+
+def setup_xsk(cfg, xdp_queue_id = 0) -> bkg:
+    # Probe for support
+    xdp = cmd(f'{cfg.net_lib_dir / "xdp_helper"} - -', fail=False)
+    if xdp.ret == 255:
+        raise KsftSkipEx('AF_XDP unsupported')
+    elif xdp.ret > 0:
+        raise KsftFailEx('unable to create AF_XDP socket')
+
+    try:
+        return bkg(f'{cfg.net_lib_dir / "xdp_helper"} {cfg.ifindex} ' \
+                   '{xdp_queue_id} -z', ksft_wait=3)
+    except:
+        raise KsftSkipEx('Failed to bind XDP socket in zerocopy.\n' \
+                         'Please consider adding iommu_platform=on ' \
+                         'when setting up virtio-net-pci')
+
+def check_xdp_bind(cfg):
+    with setup_xsk(cfg):
+        ip(f"link set dev %s xdp obj %s sec xdp" %
+           (cfg.ifname, cfg.net_lib_dir / "xdp_dummy.bpf.o"))
+        ip(f"link set dev %s xdp off" % cfg.ifname)
+
+def check_rx_resize(cfg):
+    with setup_xsk(cfg):
+        rx_ring = _get_rx_ring_entries(cfg)
+        ethtool(f"-G %s rx %d" % (cfg.ifname, rx_ring // 2))
+        ethtool(f"-G %s rx %d" % (cfg.ifname, rx_ring))
+
+def main():
+    with NetDrvEnv(__file__, nsim_test=False) as cfg:
+        ksft_run([check_xdp_bind, check_rx_resize],
+                 args=(cfg, ))
+    ksft_exit()
+
+if __name__ == "__main__":
+    main()