Re: [PATCH net-next 3/3] selftests: drv-net: add a simple TSO test

[Stanislav Fomichev <stfomichev@gmail.com>]

On 02/12, Jakub Kicinski wrote:
> Add a simple test for TSO. Send a few MB of data and check device
> stats to verify that the device was performing segmentation.
> Do the same thing over a few tunnel types.
> 
> Injecting GSO packets directly would give us more ability to test
> corner cases, but perhaps starting simple is good enough?
> 
>   # ./ksft-net-drv/drivers/net/hw/tso.py
>   # Detected qstat for LSO wire-packets
>   KTAP version 1
>   1..14
>   ok 1 tso.ipv4 # SKIP Test requires IPv4 connectivity
>   ok 2 tso.vxlan4_ipv4 # SKIP Test requires IPv4 connectivity
>   ok 3 tso.vxlan6_ipv4 # SKIP Test requires IPv4 connectivity
>   ok 4 tso.vxlan_csum4_ipv4 # SKIP Test requires IPv4 connectivity
>   ok 5 tso.vxlan_csum6_ipv4 # SKIP Test requires IPv4 connectivity
>   ok 6 tso.gre4_ipv4 # SKIP Test requires IPv4 connectivity
>   ok 7 tso.gre6_ipv4 # SKIP Test requires IPv4 connectivity
>   ok 8 tso.ipv6
>   ok 9 tso.vxlan4_ipv6
>   ok 10 tso.vxlan6_ipv6
>   ok 11 tso.vxlan_csum4_ipv6
>   ok 12 tso.vxlan_csum6_ipv6
>   ok 13 tso.gre4_ipv6
>   ok 14 tso.gre6_ipv6
>   # Totals: pass:7 fail:0 xfail:0 xpass:0 skip:7 error:0
> 
> Note that the test currently depends on the driver reporting
> the LSO count via qstat, which appears to be relatively rare
> (virtio, cisco/enic, sfc/efc; but virtio needs host support).
> 
> Signed-off-by: Jakub Kicinski <kuba@kernel.org>
> ---
>  .../testing/selftests/drivers/net/hw/Makefile |   1 +
>  tools/testing/selftests/drivers/net/hw/tso.py | 226 ++++++++++++++++++
>  2 files changed, 227 insertions(+)
>  create mode 100755 tools/testing/selftests/drivers/net/hw/tso.py
> 
> diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
> index 21ba64ce1e34..ae783e18be83 100644
> --- a/tools/testing/selftests/drivers/net/hw/Makefile
> +++ b/tools/testing/selftests/drivers/net/hw/Makefile
> @@ -15,6 +15,7 @@ TEST_PROGS = \
>  	nic_performance.py \
>  	pp_alloc_fail.py \
>  	rss_ctx.py \
> +	tso.py \
>  	#
>  
>  TEST_FILES := \
> diff --git a/tools/testing/selftests/drivers/net/hw/tso.py b/tools/testing/selftests/drivers/net/hw/tso.py
> new file mode 100755
> index 000000000000..ee3e207d85b3
> --- /dev/null
> +++ b/tools/testing/selftests/drivers/net/hw/tso.py
> @@ -0,0 +1,226 @@
> +#!/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, ipv4, remote_v4, remote_v6, should_lso):
> +    cfg.require_cmd("socat", remote=True)
> +
> +    port = rand_port()
> +    listen_cmd = f"socat -{cfg.addr_ipver} -t 2 -u TCP-LISTEN:{port},reuseport /dev/null,ignoreeof"
> +
> +    with bkg(listen_cmd, host=cfg.remote) as nc:
> +        wait_port_listen(port, host=cfg.remote)
> +
> +        if ipv4:
> +            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]
> +
> +        # No math behind the 10 here, but try to catch cases where
> +        # TCP falls back to non-LSO.
> +        ksft_lt(tcp_sock_get_retrans(sock), 10)
> +        sock.close()
> +
> +        # Check that at least 90% of the data was sent as LSO packets.
> +        # System noise may cause false negatives, it is what it is.
> +        total_lso_wire  = len(buf) * 0.90 // cfg.dev["mtu"]
> +        total_lso_super = len(buf) * 0.90 // cfg.dev["tso_max_size"]
> +        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'],
> +                        100, 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'],
> +                        1000, comment="Number of LSO wire-packets with LSO disabled")

Why do you expect there to be some noise (100/1000) with the feature
disabled?