Commit df548e62 authored by Jakub Kicinski's avatar Jakub Kicinski
Browse files

Merge branch 'selftests-drv-net-iou-zcrx-improve-stability-and-make-the-large-chunk-test-work' 

Jakub Kicinski says:

====================
selftests: drv-net: iou-zcrx: improve stability and make the large chunk test work

The iou-zcrx test hasn't been passing in NIPA, I assumed it's because
we're missing iouring changes, but it's still failing after the merge
window. Turns out there was a bug in the implementation which was fixed
separately via the iouring tree. With that out of the way the tests
are passing but flaky. Patch 1 deals with the flakiness.

While looking at this I also noticed that the large chunk test isn't
running at all. So fix and enable it (patches 2 and 3).
====================

Link: https://patch.msgid.link/20260227171305.2848240-1-kuba@kernel.org


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parents 8341c989 c7b22841

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

+31 −26
Original line number Diff line number Diff line
@@ -2,14 +2,27 @@ 
# SPDX-License-Identifier: GPL-2.0



import re

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

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)
@@ -46,6 +59,7 @@ def single(cfg): 
                                '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}")
@@ -73,6 +87,7 @@ def rss(cfg): 
                                '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}")
@@ -120,36 +135,24 @@ def test_zcrx_large_chunks(cfg) -> None: 


    cfg.require_ipver('6')



    combined_chans = _get_combined_channels(cfg)

    if combined_chans < 2:

        raise KsftSkipEx('at least 2 combined channels required')

    (rx_ring, hds_thresh) = _get_current_settings(cfg)

    port = rand_port()



    ethtool(f"-G {cfg.ifname} tcp-data-split on")

    defer(ethtool, f"-G {cfg.ifname} tcp-data-split auto")



    ethtool(f"-G {cfg.ifname} hds-thresh 0")

    defer(ethtool, f"-G {cfg.ifname} hds-thresh {hds_thresh}")



    ethtool(f"-G {cfg.ifname} rx 64")

    defer(ethtool, f"-G {cfg.ifname} rx {rx_ring}")

    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)))



    ethtool(f"-X {cfg.ifname} equal {combined_chans - 1}")

    defer(ethtool, f"-X {cfg.ifname} default")



    flow_rule_id = _set_flow_rule(cfg, port, combined_chans - 1)

    defer(ethtool, f"-N {cfg.ifname} delete {flow_rule_id}")



    rx_cmd = f"{cfg.bin_local} -s -p {port} -i {cfg.ifname} -q {combined_chans - 1} -x 2"

    tx_cmd = f"{cfg.bin_remote} -c -h {cfg.addr_v['6']} -p {port} -l 12840"

    single(cfg)

    rx_cmd = f"{cfg.bin_local} -s -p {cfg.port} -i {cfg.ifname} -q {cfg.target} -x 2"

    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)

        raise KsftSkipEx(probe.stdout.strip())



    with bkg(rx_cmd, exit_wait=True):

        wait_port_listen(port, proto="tcp")

        wait_port_listen(cfg.port, proto="tcp")

        cmd(tx_cmd, host=cfg.remote)
@@ -159,8 +162,10 @@ def main() -> None: 
        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], args=(cfg, ))

        ksft_run(globs=globals(), cases=[test_zcrx, test_zcrx_oneshot,

                                        test_zcrx_large_chunks], args=(cfg, ))

    ksft_exit()