From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-pz2-f42.google.com (mail-pz2-f42.google.com [74.125.228.42]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id E788C40B102 for ; Mon, 21 Sep 2026 20:12:18 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=74.125.228.42 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1790021540; cv=none; b=g/WN7TE9zKwlJ4P9li6Bcu9vIvBMf+aSRVa05CGNeN4d+tyk4pN2l34WPIWegoRaVTG9ITwFxzC+2dbktz6e/yLgNIEbVgA9A3UXi+M2Ij6RHh7lBRTMVvqEoYbCgePzpJJ5IWOgehm7D+fmdjXPejrXop6tPoKbW34MQ4iAcU0= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1790021540; c=relaxed/simple; bh=5T4lbni0PCLYd4q7QXK+iCi30F7GifM33dUtGAiz8DI=; h=From:To:Cc:Subject:Date:Message-ID:MIME-Version; b=GEgR2K7GqTPj1vMFghgTV/kifdsXeAbOMHLtoWfCwGMsWDbnRdt1E6tSkcuAVAHAv1BDKUXpG/NoxNXc0W6Rgy81xPGi1ZEZxgKtu1utgrq0uxZ1HpqJm3fHahrq6kY3qoeWcI8QiftGbwCU8gRMbPDtR8E2YUcK/5KNEz/UmZc= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=b4nXtMe8; arc=none smtp.client-ip=74.125.228.42 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="b4nXtMe8" Received: by mail-pz2-f42.google.com with SMTP id 41be03b00d2f7-cc1cea34ef3so3005564a12.0 for ; Mon, 21 Sep 2026 13:12:18 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1790021538; x=1790626338; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:from:to:cc:subject:date:message-id:reply-to:content-type; bh=pO39sZ0nSfGxxtiUdD70gv53e2K+kwH/We90AH1SI04=; b=b4nXtMe8IDvMXSNRRjRSodAqZ+72bpPQpdXmcp2mFGlnzKRHzTHLcUHUF3uidu67Oz 3U6i66jvvk0C9dqwF3DDkajwz+kVomKCorWmYyClkfcCKIBZrv6xtoR+vML2knovqy/T nQoTQVizEe3fQEIdfdrn0wuiZSmVI+WQzziyrXt3UxnAolJhHtRqxT2jvO0FjNwu7Hxc BwN53+VrsGAGXcRGLlkDOkDvDvYqWGc/lDuMP7XQ7oGUviEJni61kqK6a/43Hgdt22C4 ViSc+C0TbJN3Vgy7mHv2/WmIAlFNveHLypZKLFneM8NvO7CKInT6l5f+tGByHEZus5ht JhWA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20260707; t=1790021538; x=1790626338; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:x-gm-gg:x-gm-message-state:from:to:cc:subject:date :message-id:reply-to:content-type; bh=pO39sZ0nSfGxxtiUdD70gv53e2K+kwH/We90AH1SI04=; b=qxk0hTCg9hYbI5OSpqIzaVkiGk6ptZg+DSXW1q6YwONQ2Vnls/zLx7vfc1zrYyR9YS i7lqqc2ZLJ1jP69YjPq/T8luYcHzeSZVDC727dN9BasNwMZWtcVPMDf4HAfOs7vDHVay pZVX2aJLyWocCEel/U3L6y3XiuCo+753IUkh9TgL8ADGi6Jg8v8UBi2Z6x8NFO01FyML 5JfZJydn0blxYbzFXWgYu2ve+6HvTbXhR8EoghAZLTq5XWDh/xO6cydibAZonl2tw5Rq c/TfLv+z8EL11K2HvB6HG3ZKXKlAhqe+h7gAgbMOphlrrzeCAh/WC7NaIBZ7brVYshpY 9MyQ== X-Gm-Message-State: AFuF++kZGEiVHa/tz/mGO1PF+xOkDNSCe257hOTpRDZyOAFyDOsRpuuH 8LKuOeNQ1bKfcIq36+AfV4HNcrohR5LsP5wePA5bSu+RfsCqYEmtjGNg X-Gm-Gg: AYBFou0+b+kP34c8NsRkOH8LEczzE1bZvZX+MPCrKIzJEfovDI4VP+v4qf3/gEmlB7D katYQIG7rSIuPGMkxau8doVJoSnX2e4Hg9usVgK6acEb1O3LC54A52j466s7o6mPrahUwijLTsV atgsDh+uT4HfI5+oJIA51eRy9ndAKgK+hhFYrqA0UfOXkoO/WuBd2N+1awMJ/LNERvdD0psK8Wc C/HhjBy/wtTnKdRAHdyoQuOlxYMY1m/y9gGDrtIMzT+Ap0HzkvzAbdStu2vOX93Vl5+njObwXXV sfzKMrpnLUkGwixFG3uh6DmTNpFBnj+6sLXtzgQZo993aP5qwayUT4z4R30bmkFWWFEwqNWcfyF pa1L6RpcKu46bZS3ZKfjB3zOpDKJUxevcmN1PReUVr4QyrRbiHRDW5DvRuzOs3T7SVf1uTbHdTV 9uSiqmSyNM6gBkSiFcgJnvIfwPhZeHCAFeq0kvlSuC5jUqtfvo8HvB1zr7c/cTSCLjNqjIOj1nl QiV2r+O8rCsKiuxlEAUqPkWJLsrqaMQyDLM X-Received: by 2002:a05:6a20:748f:b0:3dd:85aa:452d with SMTP id adf61e73a8af0-3dd8c59d659mr17356044637.31.1790021538200; Mon, 21 Sep 2026 13:12:18 -0700 (PDT) Received: from narcisav-mac.thefacebook.com ([2620:10d:c090:400::5:a2c]) by smtp.gmail.com with ESMTPSA id 5a478bee46e88-33e5ec60d1fsm297025eec.28.2026.09.21.13.12.16 (version=TLS1_3 cipher=TLS_CHACHA20_POLY1305_SHA256 bits=256/256); Mon, 21 Sep 2026 13:12:17 -0700 (PDT) From: Narcisa Vasile To: netdev@vger.kernel.org, kuba@kernel.org, daniel.zahka@gmail.com, Andrew Lunn , "David S . Miller" , Eric Dumazet , Paolo Abeni , Shuah Khan , Petr Vorel , Pavan Chebbi Cc: linux-kselftest@vger.kernel.org, linux-kernel@vger.kernel.org, narcisav.kernel@gmail.com Subject: [PATCH net-next] selftests: drv-net: add BIG TCP coverage to TSO test Date: Mon, 21 Sep 2026 13:11:45 -0700 Message-ID: <20260921201145.49875-1-narcisav.kernel@gmail.com> X-Mailer: git-send-email 2.50.1 Precedence: bulk X-Mailing-List: linux-kselftest@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Add IPv4 and IPv6 test cases that exercise GSO packets under BIG TCP size limits. 1..2 ok 1 tso.big_tcp_ipv4 ok 2 tso.big_tcp_ipv6 Both of them run the existing tx-tcp-segmentation and tx-tcp6-segmentation tests at the increased TSO maximum. Additionally, reserve a hugepage and transmit its content using MSG_ZEROCOPY to produce skb fragments larger than 65536. Check that the number of retransmissions represents a small percentage of the total packets sent. Record the number of drops before and after the send to catch issues with large frag handling during segmentation. Signed-off-by: Narcisa Vasile --- tools/testing/selftests/drivers/net/hw/tso.py | 161 ++++++++++++++++++ 1 file changed, 161 insertions(+) diff --git a/tools/testing/selftests/drivers/net/hw/tso.py b/tools/testing/selftests/drivers/net/hw/tso.py index 67f6c9ca9a64..176ddf97fabb 100755 --- a/tools/testing/selftests/drivers/net/hw/tso.py +++ b/tools/testing/selftests/drivers/net/hw/tso.py @@ -4,6 +4,7 @@ """A simple test for TSO.""" import fcntl +import mmap import socket import struct import termios @@ -15,6 +16,87 @@ from lib.py import EthtoolFamily, NetdevFamily, NetDrvEpEnv from lib.py import bkg, cmd, defer, ethtool, ip, rand_port, wait_port_listen +MAP_HUGETLB = getattr(mmap, "MAP_HUGETLB", 0x40000) +MSG_ZEROCOPY = getattr(socket, "MSG_ZEROCOPY", 0x4000000) +SO_ZEROCOPY = getattr(socket, "SO_ZEROCOPY", 60) + +GSO_LEGACY_MAX_SIZE = 65536 + +# Pool of the default hugepage size, the one /proc/meminfo reports on. +NR_HUGEPAGES = "/proc/sys/vm/nr_hugepages" + + +def default_huge_page_size(): + """Return the hugepage size in bytes""" + try: + with open("/proc/meminfo", encoding="utf-8") as meminfo: + for line in meminfo: + if line.startswith("Hugepagesize:"): + return int(line.split()[1]) * 1024 + except OSError: + pass + + return 2 * 1024 * 1024 + + +def hugepages_free(): + """Return the number of unused hugepages of the default size.""" + try: + with open("/proc/meminfo", encoding="utf-8") as meminfo: + for line in meminfo: + if line.startswith("HugePages_Free:"): + return int(line.split()[1]) + except OSError: + pass + return 0 + + +def set_nr_hugepages(count): + with open(NR_HUGEPAGES, "w", encoding="utf-8") as sysctl: + sysctl.write(f"{count}\n") + + +def tx_dropped(ifname): + with open(f"/sys/class/net/{ifname}/statistics/tx_dropped", + encoding="utf-8") as counter: + return int(counter.read()) + + +def setup_hugepage(): + """Reserve one hugepage, and put the pool back afterwards.""" + if hugepages_free() >= 1: + return + + try: + with open(NR_HUGEPAGES, encoding="utf-8") as sysctl: + old_count = int(sysctl.read()) + set_nr_hugepages(old_count + 1) + except OSError as error: + raise KsftSkipEx(f"Unable to reserve a hugepage: {error}") from error + + defer(set_nr_hugepages, old_count) + + if hugepages_free() < 1: + raise KsftSkipEx("Unable to reserve a hugepage") + + +def mmap_large_buffer(): + """Allocate a buffer backed by one huge page.""" + size = default_huge_page_size() + + setup_hugepage() + + try: + return mmap.mmap(-1, size, + flags=mmap.MAP_PRIVATE | + mmap.MAP_ANONYMOUS | + MAP_HUGETLB, + prot=mmap.PROT_READ) + except OSError as e: + raise KsftSkipEx(f"Unable to allocate a {size >> 20}MB hugepage " + f"buffer: {e}") from e + + 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): @@ -33,6 +115,32 @@ def tcp_sock_get_retrans(sock): return struct.unpack("I", info[100:104])[0] +def setup_big_tcp(cfg): + """Lift the GSO ceiling to what the device advertises for TSO.""" + if cfg.dev["tso_max_size"] <= GSO_LEGACY_MAX_SIZE: + raise KsftSkipEx("Device does not support BIG TCP") + + ip(f"link set dev {cfg.ifname} " + f"gso_max_size {cfg.dev['tso_max_size']} " + f"gso_ipv4_max_size {cfg.dev['tso_max_size']}") + + defer(ip, f"link set dev {cfg.ifname} " + f"gso_max_size {cfg.dev['gso_max_size']} " + f"gso_ipv4_max_size {cfg.dev['gso_ipv4_max_size']}") + + +def sock_send_zerocopy(sock): + """Send with MSG_ZEROCOPY, return the bytes queued.""" + try: + sock.setsockopt(socket.SOL_SOCKET, SO_ZEROCOPY, 1) + except OSError as e: + raise KsftSkipEx(f"SO_ZEROCOPY not supported: {e}") from e + + with mmap_large_buffer() as tx_buf: + sock.sendall(tx_buf, MSG_ZEROCOPY) + return len(tx_buf) + + def run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso): cfg.require_cmd("socat", local=False, remote=True) @@ -96,6 +204,46 @@ def run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso): 500, comment="Number of LSO wire-packets with LSO disabled") +def run_big_tcp_stream(cfg, ipver, remote_v4, remote_v6): + """Send with MSG_ZEROCOPY out of a huge page, so the frags exceed 64kB.""" + cfg.require_cmd("socat", local=False, remote=True) + + # No clamping, as it would keep the frags under 64kB + port = rand_port() + listen_opts = f"{port},reuseport" + 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): + 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) + + retrans_old = tcp_sock_get_retrans(sock) + drops_old = tx_dropped(cfg.ifname) + + sent = sock_send_zerocopy(sock) + sock_wait_drain(sock) + + drops = tx_dropped(cfg.ifname) - drops_old + retrans = tcp_sock_get_retrans(sock) - retrans_old + sock.close() + + ksft_eq(drops, 0, comment="Driver TX drops during BIG TCP send") + + # Same best effort bound as the plain stream. + total_lso_wire = sent * 0.90 // cfg.dev["mtu"] + ksft_lt(retrans, total_lso_wire / 16) + + def build_tunnel(cfg, outer_ipver, tun_info): local_v4 = NetDrvEpEnv.nsim_v4_pfx + "1" local_v6 = NetDrvEpEnv.nsim_v6_pfx + "1" @@ -147,6 +295,11 @@ def test_builder(name, cfg, outer_ipver, feature, tun=None, inner_ipver=None): if feature not in cfg.hw_features: raise KsftSkipEx(f"Device does not support {feature}") + # Run non-tunnel test cases under the BIG TCP limits too. + big_tcp = "big_tcp" in name + if big_tcp: + setup_big_tcp(cfg) + ipver = outer_ipver if tun: remote_v4, remote_v6 = build_tunnel(cfg, ipver, tun) @@ -159,6 +312,9 @@ def test_builder(name, cfg, outer_ipver, feature, tun=None, inner_ipver=None): ethtool(f"-K {cfg.ifname} {feature} off") run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=False) + if big_tcp: + run_big_tcp_stream(cfg, ipver, remote_v4, remote_v6) + 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: @@ -171,6 +327,9 @@ def test_builder(name, cfg, outer_ipver, feature, tun=None, inner_ipver=None): ethtool(f"-K {cfg.ifname} {feature} on") run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=True) + if big_tcp: + run_big_tcp_stream(cfg, ipver, remote_v4, remote_v6) + f.__name__ = name + ((outer_ipver + "_") if tun else "") + "ipv" + inner_ipver return f @@ -230,6 +389,8 @@ def main() -> None: # name, v4/v6 ethtool_feature tun:(type, args, inner ip versions) ("", "4", "tx-tcp-segmentation", None), ("", "6", "tx-tcp6-segmentation", None), + ("big_tcp_", "4", "tx-tcp-segmentation", None), + ("big_tcp_", "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"))), -- 2.53.0-Meta