diff options
Diffstat (limited to 'tools/testing/selftests/drivers/net/hw')
22 files changed, 1513 insertions, 172 deletions
diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile index 85ca4d1ecf9e..78bb0169350b 100644 --- a/tools/testing/selftests/drivers/net/hw/Makefile +++ b/tools/testing/selftests/drivers/net/hw/Makefile @@ -19,7 +19,7 @@ TEST_GEN_FILES := \ TEST_PROGS = \ csum.py \ - devlink_port_split.py \ + devlink_rate_cross_esw.py \ devlink_rate_tc_bw.py \ devmem.py \ ethtool.sh \ @@ -31,9 +31,11 @@ TEST_PROGS = \ 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 \ @@ -45,12 +47,18 @@ TEST_PROGS = \ rss_input_xfrm.py \ toeplitz.py \ tso.py \ + userns_devmem.py \ uso.py \ xdp_metadata.py \ xsk_reconfig.py \ # +TEST_PROGS_EXTENDED := \ + devlink_port_split.py \ +# end of TEST_PROGS_EXTENDED + TEST_FILES := \ + devmem_lib.py \ ethtool_lib.sh \ # diff --git a/tools/testing/selftests/drivers/net/hw/config b/tools/testing/selftests/drivers/net/hw/config index dd50cb8a7911..d89a9ba17655 100644 --- a/tools/testing/selftests/drivers/net/hw/config +++ b/tools/testing/selftests/drivers/net/hw/config @@ -3,14 +3,26 @@ 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_DEVMEM=y CONFIG_NET_IPGRE=y CONFIG_NET_IPGRE_DEMUX=y +CONFIG_NET_IPIP=y CONFIG_NETKIT=y CONFIG_NET_SCH_INGRESS=y +CONFIG_SYNC_FILE=y CONFIG_UDMABUF=y +CONFIG_USER_NS=y CONFIG_VXLAN=y +CONFIG_XFRM_USER=y diff --git a/tools/testing/selftests/drivers/net/hw/csum.py b/tools/testing/selftests/drivers/net/hw/csum.py index 3e3a89a34afe..0e99198f8d39 100755 --- a/tools/testing/selftests/drivers/net/hw/csum.py +++ b/tools/testing/selftests/drivers/net/hw/csum.py @@ -1,7 +1,7 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 -"""Run the tools/testing/selftests/net/csum testsuite.""" +"""Run the tools/testing/selftests/net/lib/csum testsuite.""" from os import path diff --git a/tools/testing/selftests/drivers/net/hw/devlink_rate_cross_esw.py b/tools/testing/selftests/drivers/net/hw/devlink_rate_cross_esw.py new file mode 100755 index 000000000000..4416f024cb76 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/devlink_rate_cross_esw.py @@ -0,0 +1,296 @@ +#!/usr/bin/env python3 +# SPDX-License-Identifier: GPL-2.0 + +""" +Devlink Rate Cross-eswitch Scheduling Test Suite +================================================== + +Control-plane tests for cross-eswitch TX scheduling via devlink-rate. +Validates that VFs from different PFs on the same chip can share +rate groups using the cross-device parent-dev attribute. + +Preconditions: +- NETIF points to a bond device with exactly two interfaces. +- the interfaces must be two PFs from different devices sharing the same chip. +- (for mlx5): the two interfaces are in switchdev mode and configured in a LAG: + - devlink dev eswitch set $DEV1 mode switchdev + - devlink dev eswitch set $DEV2 mode switchdev + - devlink dev param set $DEV1 name esw_multiport value 1 cmode runtime + - devlink dev param set $DEV2 name esw_multiport value 1 cmode runtime +- test cases will be skipped if: + - the number of interfaces in the bond device is != 2. + - the kernel doesn't support devlink rates. + - the devlink API doesn't support cross-device parents (ENODEV). + - cross-esw rate scheduling returns EOPNOTSUPP. +""" + +import errno +import glob +import os +import time + +from lib.py import ksft_pr, ksft_eq, ksft_run, ksft_exit +from lib.py import KsftSkipEx, KsftFailEx +from lib.py import NetDrvEnv, DevlinkFamily +from lib.py import NlError +from lib.py import cmd, defer, ip, tool + + +# --- Discovery and setup --- + + +def get_bond_slaves(bond_ifname): + """Returns sorted list of slave netdev names for a bond.""" + pattern = f"/sys/class/net/{bond_ifname}/lower_*" + lowers = glob.glob(pattern) + if not lowers: + raise KsftSkipEx(f"No bond slaves for {bond_ifname}") + slaves = [] + for path in sorted(lowers): + name = os.path.basename(path) + if name.startswith("lower_"): + name = name[len("lower_"):] + slaves.append(name) + return slaves + + +def discover_pfs(cfg): + """Discovers both PFs from bond slaves.""" + slaves = get_bond_slaves(cfg.ifname) + if len(slaves) != 2: + raise KsftSkipEx(f"Need 2 bond slaves, found {len(slaves)}") + + pf0, pf1 = slaves[0], slaves[1] + ksft_pr(f"PF0: {pf0} PF1: {pf1}") + return pf0, pf1 + + +def get_pci_addr(ifname): + """Resolves PCI address for a network interface.""" + return os.path.basename(os.path.realpath(f"/sys/class/net/{ifname}/device")) + + +def get_vf_port_index(pf_pci): + """Finds devlink port-index for vf0 under pf_pci.""" + ports = tool("devlink", "port show", json=True)["port"] + for port_name, props in ports.items(): + if port_name.startswith(f"pci/{pf_pci}/") and props.get("vfnum") == 0: + return int(port_name.split("/")[-1]) + raise KsftSkipEx(f"VF port not found for {pf_pci}") + + +def cleanup_esw(pf): + """Removes VFs if created by tests.""" + cmd(f"echo 0 > /sys/class/net/{pf}/device/sriov_numvfs", shell=True, fail=False) + + +def setup_esw(pf): + """Creates 1 VF on 'pf'.""" + path = f"/sys/class/net/{pf}/device/sriov_numvfs" + cmd(f"echo 0 > {path}", shell=True) + cmd(f"echo 1 > {path}", shell=True) + defer(cleanup_esw, pf) + time.sleep(2) + + vf_dir = f"/sys/class/net/{pf}/device/virtfn0/net" + entries = os.listdir(vf_dir) if os.path.isdir(vf_dir) else [] + if not entries: + raise KsftSkipEx(f"VF not found for {pf}") + ip(f"link set dev {entries[0]} up") + + pf_pci = get_pci_addr(pf) + vf_idx = get_vf_port_index(pf_pci) + ksft_pr(f"Created VF {vf_idx} on PF {pf} ({pf_pci})") + return pf_pci, vf_idx + + +# --- Rate operation helpers --- + + +def rate_new(devnl, dev_pci, node_name, **kwargs): + """Creates rate node.""" + params = { + "bus-name": "pci", + "dev-name": dev_pci, + "rate-node-name": node_name, + } + params.update(kwargs) + try: + devnl.rate_new(params) + except NlError as e: + if e.error == errno.EOPNOTSUPP: + raise KsftSkipEx("rate_new not supported") from e + raise KsftFailEx("rate_new failed") from e + + +def rate_get(devnl, dev_pci, node_name): + """Gets rate node.""" + params = { + "bus-name": "pci", + "dev-name": dev_pci, + "rate-node-name": node_name, + } + return devnl.rate_get(params) + + +def rate_get_leaf(devnl, dev_pci, port_index): + """Gets rate leaf (VF).""" + params = { + "bus-name": "pci", + "dev-name": dev_pci, + "port-index": port_index, + } + return devnl.rate_get(params) + + +def rate_del(devnl, dev_pci, node_name): + """Deletes rate node.""" + devnl.rate_del({ + "bus-name": "pci", + "dev-name": dev_pci, + "rate-node-name": node_name, + }) + + +def rate_set_leaf(devnl, dev_pci, port_index, **kwargs): + """Sets rate attributes on a leaf (VF).""" + params = { + "bus-name": "pci", + "dev-name": dev_pci, + "port-index": port_index, + } + params.update(kwargs) + try: + devnl.rate_set(params) + except NlError as e: + if e.error == errno.EOPNOTSUPP: + raise KsftSkipEx("rate_set not supported") from e + raise KsftFailEx("rate_set failed") from e + + +def rate_set_leaf_parent(devnl, dev_pci, port_index, + parent_name, parent_dev_pci=None): + """Sets a leaf's parent, optionally cross-esw.""" + params = { + "bus-name": "pci", + "dev-name": dev_pci, + "port-index": port_index, + "rate-parent-node-name": parent_name, + } + if parent_dev_pci: + params["parent-dev"] = { + "bus-name": "pci", + "dev-name": parent_dev_pci, + } + try: + devnl.rate_set(params) + except NlError as e: + if e.error == errno.EOPNOTSUPP: + raise KsftSkipEx("rate_set not supported") from e + if parent_dev_pci and e.error == errno.ENODEV: + raise KsftSkipEx("Cross-esw scheduling not supported") from e + raise KsftFailEx("rate_set failed") from e + + +def rate_clear_leaf_parent(devnl, dev_pci, port_index): + """Clears a leaf's parent.""" + rate_set_leaf_parent(devnl, dev_pci, port_index, "") + + +def rate_set_node(devnl, dev_pci, node_name, **kwargs): + """Sets rate attributes on a node.""" + params = { + "bus-name": "pci", + "dev-name": dev_pci, + "rate-node-name": node_name, + } + params.update(kwargs) + devnl.rate_set(params) + + +# --- Test cases --- + + +def test_same_esw_parent(cfg): + """Assigns PF0's VF to PF0's group (same esw baseline).""" + pf0, _ = discover_pfs(cfg) + pf0_pci, vf0_idx = setup_esw(pf0) + + rate_new(cfg.devnl, pf0_pci, "group0") + defer(rate_del, cfg.devnl, pf0_pci, "group0") + ksft_pr("rate-new succeeded") + + rate_set_leaf_parent(cfg.devnl, pf0_pci, vf0_idx, "group0") + defer(rate_clear_leaf_parent, cfg.devnl, pf0_pci, vf0_idx) + + ksft_pr("Same-esw parent assignment succeeded") + + +def test_cross_esw_parent(cfg): + """Sets cross-esw parent, then clear it.""" + pf0, pf1 = discover_pfs(cfg) + pf0_pci, _ = setup_esw(pf0) + pf1_pci, vf1_idx = setup_esw(pf1) + + rate_new(cfg.devnl, pf0_pci, "group1") + defer(rate_del, cfg.devnl, pf0_pci, "group1") + ksft_pr("rate-new succeeded") + + rate_set_leaf_parent(cfg.devnl, pf1_pci, vf1_idx, + "group1", parent_dev_pci=pf0_pci) + defer(rate_clear_leaf_parent, cfg.devnl, pf1_pci, vf1_idx) + + ksft_pr("Cross-esw parent set and clear succeeded") + + +def test_tx_rates_on_cross_esw(cfg): + """Sets tx_max on group and tx_share on leaves in a cross-esw setup.""" + pf0, pf1 = discover_pfs(cfg) + pf0_pci, vf0_idx = setup_esw(pf0) + pf1_pci, vf1_idx = setup_esw(pf1) + + rate_new(cfg.devnl, pf0_pci, "group2", **{"rate-tx-max": 10000000}) + defer(rate_del, cfg.devnl, pf0_pci, "group2") + ksft_pr("rate-new succeeded") + + rate_set_leaf_parent(cfg.devnl, pf1_pci, vf1_idx, + "group2", parent_dev_pci=pf0_pci) + defer(rate_clear_leaf_parent, cfg.devnl, pf1_pci, vf1_idx) + ksft_pr("set parent cross-esw succeeded") + + rate_set_leaf_parent(cfg.devnl, pf0_pci, vf0_idx, "group2") + defer(rate_clear_leaf_parent, cfg.devnl, pf0_pci, vf0_idx) + ksft_pr("set parent same esw succeeded") + + rate_set_leaf(cfg.devnl, pf0_pci, vf0_idx, **{"rate-tx-share": 1000000}) + rate = rate_get_leaf(cfg.devnl, pf0_pci, vf0_idx) + ksft_eq(rate["rate-tx-share"], 1000000) + rate_set_leaf(cfg.devnl, pf1_pci, vf1_idx, **{"rate-tx-share": 2000000}) + rate = rate_get_leaf(cfg.devnl, pf1_pci, vf1_idx) + ksft_eq(rate["rate-tx-share"], 2000000) + rate_set_node(cfg.devnl, pf0_pci, "group2", **{"rate-tx-max": 250000000}) + rate = rate_get(cfg.devnl, pf0_pci, "group2") + ksft_eq(rate["rate-tx-max"], 250000000) + + ksft_pr("tx_max and tx_share set on cross-esw group") + + +def main() -> None: + """Main function.""" + + with NetDrvEnv(__file__, nsim_test=False) as cfg: + cfg.devnl = DevlinkFamily() + + ksft_run( + cases=[ + test_same_esw_parent, + test_cross_esw_parent, + test_tx_rates_on_cross_esw, + ], + args=(cfg,), + ) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py index ee863e90d1e0..82c11ffc4add 100755 --- a/tools/testing/selftests/drivers/net/hw/devmem.py +++ b/tools/testing/selftests/drivers/net/hw/devmem.py @@ -2,91 +2,47 @@ # SPDX-License-Identifier: GPL-2.0 from os import path -from lib.py import ksft_run, ksft_exit -from lib.py import ksft_eq, KsftSkipEx +from devmem_lib import (setup_test, run_rx, run_tx, run_tx_chunks, run_rx_hds, + run_rx_large_niov) +from lib.py import ksft_run, ksft_exit, ksft_disruptive from lib.py import NetDrvEpEnv -from lib.py import bkg, cmd, rand_port, wait_port_listen -from lib.py import ksft_disruptive - - -def require_devmem(cfg): - 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") @ksft_disruptive def check_rx(cfg) -> None: - require_devmem(cfg) - - port = rand_port() - socat = f"socat -u - TCP{cfg.addr_ipver}:{cfg.baddr}:{port},bind={cfg.remote_baddr}:{port}" - listen_cmd = f"{cfg.bin_local} -l -f {cfg.ifname} -s {cfg.addr} -p {port} -c {cfg.remote_addr} -v 7" - - with bkg(listen_cmd, exit_wait=True) as ncdevmem: - wait_port_listen(port) - cmd(f"yes $(echo -e \x01\x02\x03\x04\x05\x06) | \ - head -c 1K | {socat}", host=cfg.remote, shell=True) - - ksft_eq(ncdevmem.ret, 0) + """Run the devmem RX test.""" + run_rx(cfg) @ksft_disruptive def check_tx(cfg) -> None: - require_devmem(cfg) - - port = rand_port() - listen_cmd = f"socat -U - TCP{cfg.addr_ipver}-LISTEN:{port}" - - with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as socat: - wait_port_listen(port, host=cfg.remote) - cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_local} -f {cfg.ifname} -s {cfg.remote_addr} -p {port}", shell=True) - - ksft_eq(socat.stdout.strip(), "hello\nworld") + """Run the devmem TX test.""" + run_tx(cfg) @ksft_disruptive def check_tx_chunks(cfg) -> None: - require_devmem(cfg) - - port = rand_port() - listen_cmd = f"socat -U - TCP{cfg.addr_ipver}-LISTEN:{port}" - - with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as socat: - wait_port_listen(port, host=cfg.remote) - cmd(f"echo -e \"hello\\nworld\"| {cfg.bin_local} -f {cfg.ifname} -s {cfg.remote_addr} -p {port} -z 3", shell=True) - - ksft_eq(socat.stdout.strip(), "hello\nworld") + """Run the devmem TX chunking test.""" + run_tx_chunks(cfg) def check_rx_hds(cfg) -> None: - """Test HDS splitting across payload sizes.""" - require_devmem(cfg) - - for size in [1, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8192]: - port = rand_port() - listen_cmd = f"{cfg.bin_local} -L -l -f {cfg.ifname} -s {cfg.addr} -p {port}" + """Run the HDS test.""" + run_rx_hds(cfg) - with bkg(listen_cmd, exit_wait=True) as ncdevmem: - wait_port_listen(port) - cmd(f"dd if=/dev/zero bs={size} count=1 2>/dev/null | " + - f"socat -b {size} -u - TCP{cfg.addr_ipver}:{cfg.baddr}:{port},nodelay", - host=cfg.remote, shell=True) - ksft_eq(ncdevmem.ret, 0, f"HDS failed for payload size {size}") +def check_rx_large_niov(cfg) -> None: + """Run the devmem RX test with rx-page-size = 16 KiB.""" + run_rx_large_niov(cfg) def main() -> None: + """Run the devmem test cases.""" with NetDrvEpEnv(__file__) as cfg: - cfg.bin_local = path.abspath(path.dirname(__file__) + "/ncdevmem") - cfg.bin_remote = cfg.remote.deploy(cfg.bin_local) - - ksft_run([check_rx, check_tx, check_tx_chunks, check_rx_hds], - args=(cfg, )) + setup_test(cfg, path.abspath(path.dirname(__file__) + "/ncdevmem")) + ksft_run([check_rx, check_tx, check_tx_chunks, check_rx_hds, + check_rx_large_niov], + args=(cfg,)) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/hw/devmem_lib.py b/tools/testing/selftests/drivers/net/hw/devmem_lib.py new file mode 100644 index 000000000000..3554954a6691 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/devmem_lib.py @@ -0,0 +1,316 @@ +# SPDX-License-Identifier: GPL-2.0 +# pylint: disable=invalid-name,too-many-arguments +"""Shared helpers for devmem TCP selftests.""" + +import os +import re + +from lib.py import (bkg, cmd, defer, ethtool, rand_port, wait_port_listen, + ksft_eq, KsftSkipEx, NetNSEnter, EthtoolFamily, + NetdevFamily) + + +RX_PAGE_SIZE_DEFAULT = 0 +RX_PAGE_SIZE_16K = 16384 + +PROBE_RX_PAGE_SIZES = (RX_PAGE_SIZE_DEFAULT, RX_PAGE_SIZE_16K) + +NR_HUGEPAGES_FILE = "/proc/sys/vm/nr_hugepages" + + +def _is_aligned(value, alignment): + """Equivalent of the kernel IS_ALIGNED(value, alignment). + + alignment must be a power of two. + """ + return (value & (alignment - 1)) == 0 + + +def _restore_nr_hugepages(nr_hugepages): + with open(NR_HUGEPAGES_FILE, 'w', encoding='utf-8') as f: + f.write(str(nr_hugepages)) + + +def _reserve_hugepages(want=64): + """Raise nr_hugepages to @want and arrange for it to be restored.""" + with open(NR_HUGEPAGES_FILE, 'r+', encoding='utf-8') as f: + nr_hugepages = int(f.read().strip()) + if nr_hugepages >= want: + return + f.seek(0) + f.write(str(want)) + defer(_restore_nr_hugepages, nr_hugepages) + + +def _probe_devmem(cfg, rx_page_size): + """Return True if ncdevmem can bind cfg.ifname at @rx_page_size.""" + probe_command = f"{cfg.bin_local} -f {cfg.ifname}" + if rx_page_size != RX_PAGE_SIZE_DEFAULT: + probe_command += f" -b {rx_page_size}" + return cmd(probe_command, fail=False, shell=True).ret == 0 + + +def require_devmem(cfg, rx_page_size=RX_PAGE_SIZE_DEFAULT): + """Probe ncdevmem on cfg.ifname and SKIP the test if devmem isn't supported.""" + if rx_page_size not in PROBE_RX_PAGE_SIZES: + raise RuntimeError( + f"rx-page-size={rx_page_size} is missing from " + f"PROBE_RX_PAGE_SIZES, so it was never probed.") + + if not hasattr(cfg, "devmem_supported"): + _reserve_hugepages() + # Probe every size upfront: in nk tests a leased queue may land in + # ncdevmem's queue range and cause the probe to fail. + cfg.devmem_supported = {size: _probe_devmem(cfg, size) + for size in PROBE_RX_PAGE_SIZES} + + if not cfg.devmem_supported[RX_PAGE_SIZE_DEFAULT]: + raise KsftSkipEx("Test requires devmem support") + + if rx_page_size != RX_PAGE_SIZE_DEFAULT: + page_size = os.sysconf("SC_PAGE_SIZE") + if not _is_aligned(rx_page_size, page_size): + raise KsftSkipEx( + f"rx-page-size={rx_page_size} is invalid for this platform " + f"(must be a multiple of PAGE_SIZE={page_size})") + + if not cfg.devmem_supported[rx_page_size]: + raise KsftSkipEx( + f"Test requires devmem rx-page-size={rx_page_size} support") + + +def configure_nic(cfg): + """Channels, rings, RSS, queue lease for netkit devmem.""" + if not hasattr(cfg, "devmem_supported"): + raise RuntimeError( + "require_devmem() must be called before configure_nic(), which " + "may lease a queue away and make later probes fail.") + + 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) + + 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': 'unknown', + '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, + rx_page_size=RX_PAGE_SIZE_DEFAULT): + """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") + if rx_page_size != RX_PAGE_SIZE_DEFAULT: + extras.append(f"-b {rx_page_size}") + + 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_large_niov(cfg): + """Run the devmem RX test with a large niov (rx-page-size > PAGE_SIZE). + + Sweep payload sizes that straddle the niov boundary: below, equal to, + and above rx_page_size, to exercise sub-niov, exact-niov, and multi-niov + RX paths. + """ + require_devmem(cfg, rx_page_size=RX_PAGE_SIZE_16K) + _reserve_hugepages() + configure_nic(cfg) + netns = getattr(cfg, "netns", None) + + for size in [1024, 4096, 8192, 16384, 32768, 65536]: + port = rand_port() + socat = socat_send(cfg, port) + listen_cmd = ncdevmem_rx(cfg, port, + flow_steer=not netns, + rx_page_size=RX_PAGE_SIZE_16K) + data_pipe = (f"yes $(echo -e \x01\x02\x03\x04\x05\x06) | " + f"head -c {size} | {socat}") + with bkg(listen_cmd, exit_wait=True, ns=netns) as ncdevmem: + wait_port_listen(port, proto="tcp", ns=netns) + cmd(data_pipe, host=cfg.remote, shell=True) + ksft_eq(ncdevmem.ret, 0, + f"large-niov failed for payload size {size}") + + +def run_rx_hds(cfg): + """Run the HDS test by running devmem RX across a segment size sweep.""" + require_devmem(cfg) + configure_nic(cfg) + netns = getattr(cfg, "netns", None) + + for size in [1, 8, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096, 8192]: + port = rand_port() + + listen_cmd = ncdevmem_rx(cfg, port, verify=False, + fail_on_linear=True) + socat = socat_send(cfg, port, buf_size=size) + + with bkg(listen_cmd, exit_wait=True, ns=netns) as ncdevmem: + wait_port_listen(port, proto="tcp", ns=netns) + cmd(f"dd if=/dev/zero bs={size} count=1 2>/dev/null | " + f"{socat}", host=cfg.remote, shell=True) + ksft_eq(ncdevmem.ret, 0, f"HDS failed for payload size {size}") diff --git a/tools/testing/selftests/drivers/net/hw/ethtool_rmon.sh b/tools/testing/selftests/drivers/net/hw/ethtool_rmon.sh index 2ec19edddfaa..a074834cbe59 100755 --- a/tools/testing/selftests/drivers/net/hw/ethtool_rmon.sh +++ b/tools/testing/selftests/drivers/net/hw/ethtool_rmon.sh @@ -65,6 +65,8 @@ bucket_test() run_on "$iface" \ "$MZ" "$iface" -q -c "$num_tx" -p "$len" -a own -b bcast -d 10us + hw_stats_settle "$iface" + after=$(run_on "$iface" ethtool --json -S "$iface" --groups rmon | \ jq -r ".[0].rmon[\"${set}-pktsNtoM\"][$bucket].val") diff --git a/tools/testing/selftests/drivers/net/hw/ethtool_std_stats.sh b/tools/testing/selftests/drivers/net/hw/ethtool_std_stats.sh index c085d2a4c989..09f8128c51f3 100755 --- a/tools/testing/selftests/drivers/net/hw/ethtool_std_stats.sh +++ b/tools/testing/selftests/drivers/net/hw/ethtool_std_stats.sh @@ -43,10 +43,12 @@ traffic_test() done # shellcheck disable=SC2086 # needs split options - run_on "$iface" "$MZ" "$iface" -q -c "$num_tx" $pkt_format + run_on "$iface" "$MZ" "$iface" -q -d 10usec -c "$num_tx" $pkt_format # shellcheck disable=SC2086 # needs split options - run_on "$neigh" "$MZ" "$neigh" -q -c "$num_rx" $pkt_format + run_on "$neigh" "$MZ" "$neigh" -q -d 10usec -c "$num_rx" $pkt_format + + hw_stats_settle "$int" for i in "${!counters[@]}"; do read -r int grp cnt target exact_check xfail_message \ diff --git a/tools/testing/selftests/drivers/net/hw/gro_hw.py b/tools/testing/selftests/drivers/net/hw/gro_hw.py index 10e08b22ee0e..70e76e3888bd 100755 --- a/tools/testing/selftests/drivers/net/hw/gro_hw.py +++ b/tools/testing/selftests/drivers/net/hw/gro_hw.py @@ -51,11 +51,21 @@ def _resolve_dmac(cfg, ipver): 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-*")) diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.c b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c index 240d13dbc54e..f6a8fc5fac24 100644 --- a/tools/testing/selftests/drivers/net/hw/iou-zcrx.c +++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.c @@ -351,9 +351,6 @@ static void run_server(void) if (ret < 0) error(1, 0, "bind()"); - if (listen(fd, 1024) < 0) - error(1, 0, "listen()"); - flags |= IORING_SETUP_COOP_TASKRUN; flags |= IORING_SETUP_SINGLE_ISSUER; flags |= IORING_SETUP_DEFER_TASKRUN; @@ -366,6 +363,9 @@ static void run_server(void) if (cfg_dry_run) return; + if (listen(fd, 1024) < 0) + error(1, 0, "listen()"); + add_accept(&ring, fd); tstop = gettimeofday_ms() + 5000; diff --git a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py index e81724cb5542..b7a225fe4bea 100755 --- a/tools/testing/selftests/drivers/net/hw/iou-zcrx.py +++ b/tools/testing/selftests/drivers/net/hw/iou-zcrx.py @@ -2,6 +2,7 @@ # 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 @@ -41,6 +42,23 @@ def set_flow_rule_rss(cfg, rss_ctx_id): 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'] @@ -100,12 +118,22 @@ def rss(cfg): 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}" @@ -121,6 +149,7 @@ def test_zcrx(cfg, setup) -> None: ]) 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" @@ -134,6 +163,7 @@ 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: @@ -144,7 +174,10 @@ def test_zcrx_large_chunks(cfg) -> None: defer(lambda: open(hp_file, 'w', encoding='utf-8').write(str(nr_hugepages))) single(cfg) - rx_cmd = f"{cfg.bin_local} -s -p {cfg.port} -i {cfg.ifname} -q {cfg.target} -x 2" + 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) @@ -154,6 +187,9 @@ def test_zcrx_large_chunks(cfg) -> None: 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) diff --git a/tools/testing/selftests/drivers/net/hw/ipsec_vxlan.py b/tools/testing/selftests/drivers/net/hw/ipsec_vxlan.py new file mode 100755 index 000000000000..0740a4d85240 --- /dev/null +++ b/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() diff --git a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py index 84a4dab6c649..8a58cb17cc06 100644 --- a/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py +++ b/tools/testing/selftests/drivers/net/hw/lib/py/__init__.py @@ -18,7 +18,7 @@ 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 + 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 @@ -34,7 +34,7 @@ try: from drivers.net.lib.py import GenerateTraffic, Remote, Iperf3Runner from drivers.net.lib.py import NetDrvEnv, NetDrvEpEnv, NetDrvContEnv - __all__ = ["NetNS", "NetNSEnter", "NetdevSimDev", + __all__ = ["NetNS", "NetNSEnter", "NetdevSimDev", "UserNetNS", "EthtoolFamily", "NetdevFamily", "NetshaperFamily", "NlError", "RtnlFamily", "DevlinkFamily", "PSPFamily", "Netlink", "CmdExitFailure", diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c index e098d6534c3c..918e3b51f3b8 100644 --- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c +++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c @@ -40,6 +40,7 @@ #include <linux/uio.h> #include <stdarg.h> +#include <stdint.h> #include <stdio.h> #include <stdlib.h> #include <unistd.h> @@ -61,6 +62,7 @@ #include <sys/time.h> #include <linux/memfd.h> +#include <sys/param.h> #include <linux/dma-buf.h> #include <linux/errqueue.h> #include <linux/udmabuf.h> @@ -79,6 +81,7 @@ #define PAGE_SHIFT 12 #define TEST_PREFIX "ncdevmem" #define NUM_PAGES 16000 +#define MB(x) ((x) << 20) #ifndef MSG_SOCK_DEVMEM #define MSG_SOCK_DEVMEM 0x2000000 @@ -93,12 +96,14 @@ static char *port; static size_t do_validation; static int start_queue = -1; static int num_queues = -1; +static int skip_config; static char *ifname; static unsigned int ifindex; static unsigned int dmabuf_id; static uint32_t tx_dmabuf_id; static int waittime_ms = 500; static bool fail_on_linear; +static uint32_t rx_page_size; /* System state loaded by current_config_load() */ #define MAX_FLOWS 8 @@ -141,6 +146,7 @@ static struct memory_buffer *udmabuf_alloc(size_t size) { struct udmabuf_create create; struct memory_buffer *ctx; + unsigned int memfd_flags; int ret; ctx = malloc(sizeof(*ctx)); @@ -149,15 +155,20 @@ static struct memory_buffer *udmabuf_alloc(size_t size) ctx->size = size; - ctx->devfd = open("/dev/udmabuf", O_RDWR); + ctx->devfd = open("/dev/udmabuf", O_RDONLY); if (ctx->devfd < 0) { pr_err("[skip,no-udmabuf: Unable to access DMA buffer device file]"); goto err_free_ctx; } - ctx->memfd = memfd_create("udmabuf-test", MFD_ALLOW_SEALING); + memfd_flags = MFD_ALLOW_SEALING; + if (rx_page_size > getpagesize()) + memfd_flags |= MFD_HUGETLB | MFD_HUGE_2MB; + + ctx->memfd = memfd_create("udmabuf-test", memfd_flags); if (ctx->memfd < 0) { - pr_err("[skip,no-memfd]"); + pr_err("[skip,no-memfd%s]", + (memfd_flags & MFD_HUGETLB) ? " (need hugepages)" : ""); goto err_close_dev; } @@ -167,6 +178,11 @@ static struct memory_buffer *udmabuf_alloc(size_t size) goto err_close_memfd; } + if (memfd_flags & MFD_HUGETLB) { + size = roundup(size, MB(2)); + ctx->size = size; + } + ret = ftruncate(ctx->memfd, size); if (ret == -1) { pr_err("[FAIL,memfd-truncate]"); @@ -698,6 +714,8 @@ static int bind_rx_queue(unsigned int ifindex, unsigned int dmabuf_fd, netdev_bind_rx_req_set_ifindex(req, ifindex); netdev_bind_rx_req_set_fd(req, dmabuf_fd); __netdev_bind_rx_req_set_queues(req, queues, n_queue_index); + if (rx_page_size) + netdev_bind_rx_req_set_rx_page_size(req, rx_page_size); rsp = netdev_bind_rx(*ys, req); if (!rsp) { @@ -828,7 +846,7 @@ static struct netdev_queue_id *create_queues(void) static int do_server(struct memory_buffer *mem) { - struct ethtool_rings_get_rsp *ring_config; + struct ethtool_rings_get_rsp *ring_config = NULL; char ctrl_data[sizeof(int) * 20000]; size_t non_page_aligned_frags = 0; struct sockaddr_in6 client_addr; @@ -851,27 +869,29 @@ static int do_server(struct memory_buffer *mem) return -1; } - ring_config = get_ring_config(); - if (!ring_config) { - pr_err("Failed to get current ring configuration"); - return -1; - } + if (!skip_config) { + ring_config = get_ring_config(); + if (!ring_config) { + pr_err("Failed to get current ring configuration"); + return -1; + } - if (configure_headersplit(ring_config, 1)) { - pr_err("Failed to enable TCP header split"); - goto err_free_ring_config; - } + if (configure_headersplit(ring_config, 1)) { + pr_err("Failed to enable TCP header split"); + goto err_free_ring_config; + } - /* Configure RSS to divert all traffic from our devmem queues */ - if (configure_rss()) { - pr_err("Failed to configure rss"); - goto err_reset_headersplit; - } + /* Configure RSS to divert all traffic from our devmem queues */ + if (configure_rss()) { + pr_err("Failed to configure rss"); + goto err_reset_headersplit; + } - /* Flow steer our devmem flows to start_queue */ - if (configure_flow_steering(&server_sin)) { - pr_err("Failed to configure flow steering"); - goto err_reset_rss; + /* Flow steer our devmem flows to start_queue */ + if (configure_flow_steering(&server_sin)) { + pr_err("Failed to configure flow steering"); + goto err_reset_rss; + } } if (bind_rx_queue(ifindex, mem->fd, create_queues(), num_queues, &ys)) { @@ -1052,13 +1072,17 @@ err_free_tmp: err_unbind: ynl_sock_destroy(ys); err_reset_flow_steering: - reset_flow_steering(); + if (!skip_config) + reset_flow_steering(); err_reset_rss: - reset_rss(); + if (!skip_config) + reset_rss(); err_reset_headersplit: - restore_ring_config(ring_config); + if (!skip_config) + restore_ring_config(ring_config); err_free_ring_config: - ethtool_rings_get_rsp_free(ring_config); + if (!skip_config) + ethtool_rings_get_rsp_free(ring_config); return err; } @@ -1404,7 +1428,7 @@ int main(int argc, char *argv[]) int is_server = 0, opt; int ret, err = 1; - while ((opt = getopt(argc, argv, "Lls:c:p:v:q:t:f:z:")) != -1) { + while ((opt = getopt(argc, argv, "Lls:c:p:v:q:t:f:z:nb:")) != -1) { switch (opt) { case 'L': fail_on_linear = true; @@ -1436,6 +1460,22 @@ int main(int argc, char *argv[]) case 'z': max_chunk = atoi(optarg); break; + case 'n': + skip_config = 1; + break; + case 'b': { + unsigned long val; + + errno = 0; + val = strtoul(optarg, NULL, 0); + if ((val == ULONG_MAX && errno == ERANGE) || + val > UINT32_MAX) { + pr_err("invalid rx_page_size: %s", optarg); + return 1; + } + rx_page_size = val; + break; + } case '?': fprintf(stderr, "unknown option: %c\n", optopt); break; diff --git a/tools/testing/selftests/drivers/net/hw/nk_devmem.py b/tools/testing/selftests/drivers/net/hw/nk_devmem.py new file mode 100755 index 000000000000..61c6f31f01e5 --- /dev/null +++ b/tools/testing/selftests/drivers/net/hw/nk_devmem.py @@ -0,0 +1,52 @@ +#!/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, + run_rx_large_niov) +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 check_nk_rx_large_niov(cfg) -> None: + """Run the devmem RX large-niov test through netkit.""" + run_rx_large_niov(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, check_nk_rx_large_niov], args=(cfg,)) + ksft_exit() + + +if __name__ == "__main__": + main() diff --git a/tools/testing/selftests/drivers/net/hw/nk_primary_rx_redirect.bpf.c b/tools/testing/selftests/drivers/net/hw/nk_primary_rx_redirect.bpf.c new file mode 100644 index 000000000000..46ff494b23de --- /dev/null +++ b/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"; diff --git a/tools/testing/selftests/drivers/net/hw/nk_qlease.py b/tools/testing/selftests/drivers/net/hw/nk_qlease.py index aa83dc321328..4f53034c9a50 100755 --- a/tools/testing/selftests/drivers/net/hw/nk_qlease.py +++ b/tools/testing/selftests/drivers/net/hw/nk_qlease.py @@ -18,8 +18,10 @@ from lib.py import ( NetNSEnter, EthtoolFamily, NetdevFamily, + RtnlFamily, ) from lib.py import ( + Netlink, bkg, cmd, defer, @@ -30,10 +32,138 @@ from lib.py import ( ) 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 set_flow_rule(cfg): + +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 {cfg.src_queue}" + 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) @@ -41,6 +171,8 @@ def set_flow_rule(cfg): 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}}) @@ -65,40 +197,121 @@ def test_iou_zcrx(cfg) -> None: }, ) - ethtool(f"-X {cfg.ifname} equal {cfg.src_queue}") + ethtool(f"-X {cfg.ifname} equal {src_queue}") defer(ethtool, f"-X {cfg.ifname} default") - flow_rule_id = set_flow_rule(cfg) + flow_rule_id = set_flow_rule(cfg, src_queue) defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}") - rx_cmd = f"ip netns exec {cfg.netns.name} {cfg.bin_local} -s -p {cfg.port} -i {cfg._nk_guest_ifname} -q {cfg.nk_queue}" + 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): + 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": cfg.src_queue, "type": "rx"} + {"ifindex": cfg.ifindex, "id": src_queue, "type": "rx"} ) - ksft_eq(queue_info["id"], cfg.src_queue) + 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"], cfg.nk_queue) + 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}}) @@ -123,18 +336,21 @@ def test_attach_xdp_with_mp(cfg) -> None: }, ) - ethtool(f"-X {cfg.ifname} equal {cfg.src_queue}") + ethtool(f"-X {cfg.ifname} equal {src_queue}") defer(ethtool, f"-X {cfg.ifname} default") netdevnl = NetdevFamily() - rx_cmd = f"ip netns exec {cfg.netns.name} {cfg.bin_local} -s -p {cfg.port} -i {cfg._nk_guest_ifname} -q {cfg.nk_queue}" - with bkg(rx_cmd): + 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": cfg.src_queue, "type": "rx"} + {"ifindex": cfg.ifindex, "id": src_queue, "type": "rx"} ) ksft_in("io-uring", queue_info) @@ -144,13 +360,15 @@ def test_attach_xdp_with_mp(cfg) -> None: time.sleep(0.1) queue_info = netdevnl.queue_get( - {"ifindex": cfg.ifindex, "id": cfg.src_queue, "type": "rx"} + {"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}}) @@ -175,16 +393,19 @@ def test_destroy(cfg) -> None: }, ) - ethtool(f"-X {cfg.ifname} equal {cfg.src_queue}") + ethtool(f"-X {cfg.ifname} equal {src_queue}") defer(ethtool, f"-X {cfg.ifname} default") - rx_cmd = f"ip netns exec {cfg.netns.name} {cfg.bin_local} -s -p {cfg.port} -i {cfg._nk_guest_ifname} -q {cfg.nk_queue}" - rx_proc = cmd(rx_cmd, background=True) + 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": cfg.src_queue, "type": "rx"} + {"ifindex": cfg.ifindex, "id": src_queue, "type": "rx"} ) ksft_in("io-uring", queue_info) @@ -193,23 +414,20 @@ def test_destroy(cfg) -> None: kill_timer = threading.Timer(1, rx_proc.proc.terminate) kill_timer.start() - ip(f"link del dev {cfg._nk_host_ifname}") + ip(f"link del dev {cfg.nk_host_ifname}") kill_timer.join() - cfg._nk_host_ifname = None - cfg._nk_guest_ifname = None + cfg.nk_host_ifname = None + cfg.nk_guest_ifname = None queue_info = netdevnl.queue_get( - {"ifindex": cfg.ifindex, "id": cfg.src_queue, "type": "rx"} + {"ifindex": cfg.ifindex, "id": src_queue, "type": "rx"} ) ksft_not_in("io-uring", queue_info) - cmd(f"tc filter del dev {cfg.ifname} ingress pref {cfg._bpf_prog_pref}") - cfg._tc_attached = False - - flow_rule_id = set_flow_rule(cfg) + 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 {cfg.src_queue}" + 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") @@ -217,7 +435,7 @@ def test_destroy(cfg) -> None: # 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": cfg.src_queue, "type": "rx"} + {"ifindex": cfg.ifindex, "id": src_queue, "type": "rx"} ) ksft_not_in("io-uring", queue_info) @@ -230,32 +448,14 @@ def main() -> None: cfg.bin_remote = cfg.remote.deploy(cfg.bin_local) cfg.port = rand_port() - 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") - - cfg.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": cfg.src_queue, "type": "rx"}, - "netns-id": 0, - }, - } - ) - cfg.nk_queue = bind_result["id"] - - # test_destroy must be last because it destroys the netkit devices ksft_run( - [test_iou_zcrx, test_attrs, test_attach_xdp_with_mp, test_destroy], + [ + test_iou_zcrx, + test_iou_zcrx_large_buf, + test_attrs, + test_attach_xdp_with_mp, + test_destroy, + ], args=(cfg,), ) ksft_exit() diff --git a/tools/testing/selftests/drivers/net/hw/ntuple.py b/tools/testing/selftests/drivers/net/hw/ntuple.py index 232733142c02..ef4604bfa8ef 100755 --- a/tools/testing/selftests/drivers/net/hw/ntuple.py +++ b/tools/testing/selftests/drivers/net/hw/ntuple.py @@ -22,7 +22,10 @@ class NtupleField(Enum): def _require_ntuple(cfg): features = ethtool(f"-k {cfg.ifname}", json=True)[0] if not features["ntuple-filters"]["active"]: - raise KsftSkipEx("Ntuple filters not enabled on the device: " + str(features["ntuple-filters"])) + 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): diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py index 51f4e7bc3e5d..5b25fa89c629 100755 --- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py +++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py @@ -9,7 +9,7 @@ from lib.py import ksft_disruptive from lib.py import ksft_run, ksft_pr, ksft_exit from lib.py import ksft_eq, ksft_ne, ksft_ge, ksft_in, ksft_lt, ksft_true, ksft_raises from lib.py import NetDrvEpEnv -from lib.py import EthtoolFamily, NetdevFamily +from lib.py import EthtoolFamily, NetdevFamily, NlError from lib.py import KsftSkipEx, KsftFailEx from lib.py import rand_port, rand_ports from lib.py import cmd, ethtool, ip, defer, CmdExitFailure, wait_file @@ -57,9 +57,10 @@ def ethtool_create(cfg, act, opts): def require_ntuple(cfg): features = ethtool(f"-k {cfg.ifname}", json=True)[0] if not features["ntuple-filters"]["active"]: - # ntuple is more of a capability than a config knob, don't bother - # trying to enable it (until some driver actually needs it). - raise KsftSkipEx("Ntuple filters not enabled on the device: " + str(features["ntuple-filters"])) + 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 require_context_cnt(cfg, need_cnt): @@ -650,9 +651,14 @@ def test_rss_context_overlap(cfg, other_ctx=0): ntuple = defer(ethtool, f"-N {cfg.ifname} delete {ntuple_id}") # Test the main context - cnts = _get_rx_cnts(cfg) - GenerateTraffic(cfg, port=port).wait_pkts_and_stop(20000) - cnts = _get_rx_cnts(cfg, prev=cnts) + attempts = 3 + for attempt in range(attempts): + cnts = _get_rx_cnts(cfg) + GenerateTraffic(cfg, port=port).wait_pkts_and_stop(20000) + cnts = _get_rx_cnts(cfg, prev=cnts) + if sum(cnts[:2]) >= 7000 and sum(cnts[2:4]) >= 7000: + break + ksft_pr(f"Skewed queue distribution, attempt {attempt + 1}/{attempts}: " + str(cnts)) ksft_ge(sum(cnts[ :4]), 20000, "traffic on main context: " + str(cnts)) ksft_ge(sum(cnts[ :2]), 7000, "traffic on main context (1/2): " + str(cnts)) @@ -828,6 +834,94 @@ def test_rss_default_context_rule(cfg): 'noise' : (0, 1) }) +def _set_flow_hash(cfg, fl_type, fields, context=0): + req = {"header": {"dev-index": cfg.ifindex}, + "flow-hash": {fl_type: fields}} + if context: + req["context"] = context + cfg.ethnl.rss_set(req) + + +def _get_flow_hash(cfg, fl_type, context=0): + req = {"header": {"dev-index": cfg.ifindex}} + if context: + req["context"] = context + rss = cfg.ethnl.rss_get(req) + return rss.get("flow-hash", {}).get(fl_type, set()) + + +def test_rss_context_flow_hash(cfg): + """ + Validate, with traffic, that an additional RSS context honors the + flow-hash field selection. If the driver lacks per-context field + configuration ("ops->rxfh_per_ctx_fields") fall back to setting the + fields on the main context, which the kernel applies device-wide. + """ + + require_ntuple(cfg) + + queue_cnt = len(_get_rx_cnts(cfg)) + if queue_cnt < 6: + try: + ksft_pr(f"Increasing queue count {queue_cnt} -> 6") + ethtool(f"-L {cfg.ifname} combined 6") + defer(ethtool, f"-L {cfg.ifname} combined {queue_cnt}") + except CmdExitFailure as exc: + raise KsftSkipEx("Not enough queues for the test") from exc + + fl_type = f"tcp{cfg.addr_ipver}" + if not _get_flow_hash(cfg, fl_type): + raise KsftSkipEx(f"Device does not report flow-hash for {fl_type}") + + # Reserve queues 0/1 for main, build a new context spanning 2..5 + ethtool(f"-X {cfg.ifname} equal 2") + defer(ethtool, f"-X {cfg.ifname} default") + ctx_id = ethtool_create(cfg, "-X", "context new start 2 equal 4") + defer(ethtool, f"-X {cfg.ifname} context {ctx_id} delete") + + port = rand_port() + flow = f"flow-type {fl_type} dst-ip {cfg.addr} dst-port {port} context {ctx_id}" + ntuple = ethtool_create(cfg, "-N", flow) + defer(ethtool, f"-N {cfg.ifname} delete {ntuple}") + + ip_only = {"ip-src", "ip-dst"} + ip_l4 = ip_only | {"l4-b-0-1", "l4-b-2-3"} + + # Try per-context flow-hash; fall back to main context if unsupported. + cfg_ctx = ctx_id + try: + orig = _get_flow_hash(cfg, fl_type, context=ctx_id) + _set_flow_hash(cfg, fl_type, ip_only, context=ctx_id) + except NlError: + ksft_pr("Per-context flow-hash not supported, using device-wide") + cfg_ctx = 0 + orig = _get_flow_hash(cfg, fl_type) + _set_flow_hash(cfg, fl_type, ip_only) + defer(_set_flow_hash, cfg, fl_type, orig, context=cfg_ctx) + + def measure(): + cnts = _get_rx_cnts(cfg) + GenerateTraffic(cfg, port=port).wait_pkts_and_stop(20000) + cnts = _get_rx_cnts(cfg, prev=cnts) + ctx_cnts = cnts[2:6] + directed = sum(ctx_cnts) + used = sum(1 for c in ctx_cnts if c > directed / 200) + return cnts, directed, used + + # IP-only hash: iperf3 streams share src/dst IP, all should land on the + # same queue inside the context's range. + cnts, directed, used = measure() + ksft_ge(directed, 20000, f"traffic on context {ctx_id} (IP-only): {cnts}") + ksft_eq(used, 1, f"IP-only hash should use one queue in context {ctx_id}, got: {cnts}") + + # IP+L4 hash: streams have distinct src ports, traffic should spread. + _set_flow_hash(cfg, fl_type, ip_l4, context=cfg_ctx) + + cnts, directed, used = measure() + ksft_ge(directed, 20000, f"traffic on context {ctx_id} (IP+L4): {cnts}") + ksft_ge(used, 2, f"IP+L4 hash should spread across context {ctx_id} queues, got: {cnts}") + + @ksft_disruptive def test_rss_context_persist_ifupdown(cfg, pre_down=False): """ @@ -935,6 +1029,7 @@ def main() -> None: test_flow_add_context_missing, test_delete_rss_context_busy, test_rss_ntuple_addition, test_rss_default_context_rule, + test_rss_context_flow_hash, test_rss_context_persist_create_and_ifdown, test_rss_context_persist_ifdown_and_create], args=(cfg, )) diff --git a/tools/testing/selftests/drivers/net/hw/toeplitz.py b/tools/testing/selftests/drivers/net/hw/toeplitz.py index cd7e080e6f84..571732198b93 100755 --- a/tools/testing/selftests/drivers/net/hw/toeplitz.py +++ b/tools/testing/selftests/drivers/net/hw/toeplitz.py @@ -21,6 +21,8 @@ from lib.py import ksft_variants, KsftNamedVariant, KsftSkipEx, KsftFailEx ETH_RSS_HASH_TOP = 1 # Must match RPS_MAX_CPUS in toeplitz.c RPS_MAX_CPUS = 16 +# Cap Rx queues so IRQ pinning leaves free CPUs in the RPS_MAX_CPUS range +QUEUE_CAP = 8 def _check_rps_and_rfs_not_configured(cfg): @@ -48,6 +50,25 @@ def _get_cpu_for_irq(irq): return int(data) +def _cap_queue_count(cfg): + ehdr = {"header": {"dev-index": cfg.ifindex}} + chans = cfg.ethnl.channels_get(ehdr) + + config = {} + restore = {} + for key in ("combined-count", "rx-count"): + cur = chans.get(key, 0) + if cur > QUEUE_CAP: + config[key] = QUEUE_CAP + restore[key] = cur + + if not config: + return + + cfg.ethnl.channels_set(ehdr | config) + defer(cfg.ethnl.channels_set, ehdr | restore) + + def _get_irq_cpus(cfg): """ Read the list of IRQs for the device Rx queues. @@ -177,6 +198,7 @@ def test(cfg, proto_flag, ipver, grp): ] if grp: + _cap_queue_count(cfg) _check_rps_and_rfs_not_configured(cfg) if grp == "rss": irq_cpus = ",".join([str(x) for x in _get_irq_cpus(cfg)]) diff --git a/tools/testing/selftests/drivers/net/hw/tso.py b/tools/testing/selftests/drivers/net/hw/tso.py index bb675e3dac88..67f6c9ca9a64 100755 --- a/tools/testing/selftests/drivers/net/hw/tso.py +++ b/tools/testing/selftests/drivers/net/hw/tso.py @@ -1,7 +1,7 @@ #!/usr/bin/env python3 # SPDX-License-Identifier: GPL-2.0 -"""Run the tools/testing/selftests/net/csum testsuite.""" +"""A simple test for TSO.""" import fcntl import socket @@ -187,28 +187,24 @@ def query_nic_features(cfg) -> None: cfg.wanted_features.add(f["name"]) cfg.hw_features = set() - hw_all_features_cmd = "" for f in features["hw"]["bits"]["bit"]: if f.get("value", False): - feature = f["name"] - cfg.hw_features.add(feature) - hw_all_features_cmd += f" {feature} on" - try: - ethtool(f"-K {cfg.ifname} {hw_all_features_cmd}") - except Exception as e: - ksft_pr(f"WARNING: failure enabling all hw features: {e}") - ksft_pr("partial gso feature detection may be impacted") + 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 = cfg.hw_features - no_partial + cfg.partial_features = seg_features - no_partial ethtool(f"-K {cfg.ifname} tx-gso-partial on") restore_wanted_features(cfg) @@ -239,6 +235,9 @@ def main() -> None: ("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 = [] diff --git a/tools/testing/selftests/drivers/net/hw/userns_devmem.py b/tools/testing/selftests/drivers/net/hw/userns_devmem.py new file mode 100755 index 000000000000..2aaf6ea81715 --- /dev/null +++ b/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() |