[{"id":3678989,"web_url":"http://patchwork.ozlabs.org/comment/3678989/","msgid":"<20260418175451.122193-1-kuba@kernel.org>","date":"2026-04-18T17:54:51","subject":"Re: [PATCH net v2] ibmveth: Disable GSO for packets with small MSS","submitter":{"id":77159,"url":"http://patchwork.ozlabs.org/api/people/77159/","name":"Jakub Kicinski","email":"kuba@kernel.org"},"content":"This is an AI-generated review of your patch. The human sending this\nemail has considered the AI review valid, or at least plausible.\n---\nibmveth: Disable GSO for packets with small MSS\n\nThis commit adds an ndo_features_check callback to the ibmveth driver to\ndisable segmentation offload when the MSS is less than 224 bytes. This\nprevents physical adapters in SEA configurations from freezing when given\nsmall MSS packets.\n\n> diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c\n> --- a/drivers/net/ethernet/ibm/ibmveth.c\n> +++ b/drivers/net/ethernet/ibm/ibmveth.c\n\n[ ... ]\n\n> @@ -1756,6 +1756,25 @@ static int ibmveth_set_mac_addr(struct net_device *dev, void *p)\n> \treturn 0;\n> }\n> \n> +static netdev_features_t ibmveth_features_check(struct sk_buff *skb,\n> +\t\t\t\t\t\tstruct net_device *dev,\n> +\t\t\t\t\t\tnetdev_features_t features)\n> +{\n> +\t/* Some physical adapters do not support segmentation offload with\n> +\t * MSS < 224. Disable GSO for such packets to avoid adapter freeze.\n> +\t */\n> +\tif (skb_is_gso(skb)) {\n\nThe commit message mentions this matches the ibmvnic hardware errata from\ncommit f10b09ef687f. That commit disabled GSO for both gso_size < 224 and\ngso_segs == 1.\n\nBy omitting the check for skb_shinfo(skb)->gso_segs == 1, could a\nsingle-segment GSO packet still cause the adapter to freeze?\n\n> +\t\tif (skb_shinfo(skb)->gso_size < IBMVETH_MIN_LSO_MSS) {\n> +\t\t\tnetdev_warn_once(dev,\n> +\t\t\t\t\t \"MSS %u too small for LSO, disabling GSO\\n\",\n> +\t\t\t\t\t skb_shinfo(skb)->gso_size);\n> +\t\t\tfeatures &= ~NETIF_F_GSO_MASK;\n> +\t\t}\n> +\t}\n> +\n> +\treturn features;\n\nWhen implementing a custom ndo_features_check callback, netif_skb_features()\nwill bypass the standard dflt_features_check() function. Does this mean\nvlan_features_check() is no longer called for this driver?\n\nIf vlan_features_check() is skipped, multi-tagged (QinQ) VLAN packets\nmight retain GSO and protocol-specific checksum offloads that the hardware\nparser cannot handle.\n\nShould this return vlan_features_check(skb, features) instead?\n\n> +}","headers":{"Return-Path":"\n ","X-Original-To":["incoming@patchwork.ozlabs.org","linuxppc-dev@lists.ozlabs.org"],"Delivered-To":"patchwork-incoming@legolas.ozlabs.org","Authentication-Results":["legolas.ozlabs.org;\n\tdkim=pass (2048-bit key;\n unprotected) header.d=kernel.org header.i=@kernel.org header.a=rsa-sha256\n header.s=k20201202 header.b=byRpm4Lh;\n\tdkim-atps=neutral","legolas.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=lists.ozlabs.org\n (client-ip=112.213.38.117; helo=lists.ozlabs.org;\n envelope-from=linuxppc-dev+bounces-19841-incoming=patchwork.ozlabs.org@lists.ozlabs.org;\n receiver=patchwork.ozlabs.org)","lists.ozlabs.org;\n arc=none smtp.remote-ip=172.105.4.254","lists.ozlabs.org;\n dmarc=pass (p=quarantine dis=none) header.from=kernel.org","lists.ozlabs.org;\n\tdkim=pass (2048-bit key;\n unprotected) header.d=kernel.org header.i=@kernel.org header.a=rsa-sha256\n header.s=k20201202 header.b=byRpm4Lh;\n\tdkim-atps=neutral","lists.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=kernel.org\n (client-ip=172.105.4.254; helo=tor.source.kernel.org;\n envelope-from=kuba@kernel.org; receiver=lists.ozlabs.org)"],"Received":["from lists.ozlabs.org (lists.ozlabs.org [112.213.38.117])\n\t(using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)\n\t key-exchange x25519 server-signature ECDSA (secp384r1 raw public key)\n server-digest SHA384)\n\t(No client certificate requested)\n\tby legolas.ozlabs.org (Postfix) with ESMTPS id 4fyfXm2Ldzz1yCv\n\tfor ; Sun, 19 Apr 2026 03:55:04 +1000 (AEST)","from boromir.ozlabs.org (localhost [127.0.0.1])\n\tby lists.ozlabs.org (Postfix) with ESMTP id 4fyfXk33QCz2ykf;\n\tSun, 19 Apr 2026 03:55:02 +1000 (AEST)","from tor.source.kernel.org (tor.source.kernel.org [172.105.4.254])\n\t(using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)\n\t key-exchange x25519 server-signature RSA-PSS (2048 bits) server-digest\n SHA256)\n\t(No client certificate requested)\n\tby lists.ozlabs.org (Postfix) with ESMTPS id 4fyfXj4NHhz2yL8\n\tfor ; Sun, 19 Apr 2026 03:55:01 +1000 (AEST)","from smtp.kernel.org (transwarp.subspace.kernel.org [100.75.92.58])\n\tby tor.source.kernel.org (Postfix) with ESMTP id D277560138;\n\tSat, 18 Apr 2026 17:54:53 +0000 (UTC)","by smtp.kernel.org (Postfix) with ESMTPSA id D9C4EC19424;\n\tSat, 18 Apr 2026 17:54:52 +0000 (UTC)"],"ARC-Seal":"i=1; a=rsa-sha256; d=lists.ozlabs.org; s=201707; t=1776534902;\n\tcv=none;\n b=WwgFIs88eGKYRgmSYS2wt+YwhfA+vS9Mo8Sqq/DJmX7hOWEv8e6SxrD6yOfqmIGYglzezTL9tO8dbQG/Si+D+09Y9e+tdPdxcbsbHJIOASvQaEXG4TyqnCv/tMB2SpsrM+2BwlZtuIPgQn1cq3OGsAfu0pneErqg6S2xf+zcJfNo9sh7fBrykyRGvmXw97J9VExTYpyvmR/rCZvgmdhJp71unj00I5poaWxULamnsKa8usBw3AHcLqlskbflo8iRdAWzLm6dn6yi+eLAU2qvEnbngIyO0b2gH9Tnm0BrgquiyeDWyHoTN+2HG4sirfTqJDGZcV0SDxATtJnz8dT2Ug==","ARC-Message-Signature":"i=1; a=rsa-sha256; d=lists.ozlabs.org; s=201707;\n\tt=1776534902; c=relaxed/relaxed;\n\tbh=h2xIEuBXOTjV6hITr5aINmbPn8GSgP3ll+4IMrVD8F8=;\n\th=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References:\n\t MIME-Version;\n b=nXklagh1W9kgEbicRBBLlpw21yvmpZcu6j3Yu0ojcfnBF3rZK3h91BKh3b06Lb1b5s0+lOgbam4a0V3V3XZi8n9lUFkKKlzBirswmzrjJMTV73mfgtkSUmX596eALP9rYgG4C5KgWLcgYQZJhiKUJIez1KLUehlPWA6ubR6oIC0KNdprESpA+OKb0paNJTfaGNOx0gWf93GooZIdcWVHGGfgRfpK5w8x/grFyUGhE4MAMLnii4H3nbZ1dom5OqELUkt+h5YNSt+HcUCgKwkqGubotR+6IV58aOd82CXn6FkiKIIGlcABoIuR2DiT0UELjmfWKW4tJLfHy4G6pkg3Ew==","ARC-Authentication-Results":"i=1; lists.ozlabs.org;\n dmarc=pass (p=quarantine dis=none) header.from=kernel.org;\n dkim=pass (2048-bit key;\n unprotected) header.d=kernel.org header.i=@kernel.org header.a=rsa-sha256\n header.s=k20201202 header.b=byRpm4Lh; dkim-atps=neutral;\n spf=pass (client-ip=172.105.4.254; helo=tor.source.kernel.org;\n envelope-from=kuba@kernel.org;\n receiver=lists.ozlabs.org) smtp.mailfrom=kernel.org","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org;\n\ts=k20201202; t=1776534893;\n\tbh=JdtPqroOunoZJu87mhf+doIJHBz2KVjK3UTYJVQ+Dx0=;\n\th=From:To:Cc:Subject:Date:In-Reply-To:References:From;\n\tb=byRpm4LhvpTnr4z1ujO4rvTYg14RRwjOPCtVBK2ePT6tNfd2XetfFVMOqVNpdyo3k\n\t 85Zn4Rn/GxNywlyeYkZ23LgYxOnemg8Ao32+2+/WiLNgRg9tIE+RFepAjTsVo1u4e8\n\t MkG9hxLzN8eRSS2exa1EdrQRHMw3N7AbY58HSoFLy6vl4JfuGVQkJTNzr6a2PkFrpz\n\t IaznN6CWkWej/KhEjU4SemcsL476+UpkhGzJYPFDeVtmjUXMZP8TzZvVCNy+1kQ6tP\n\t nYCa07ePIXyNIAKvnIRGV7PLkZTf+Js9zFnFU11IBmLN7T8SpKmR1RQACLrAXhShnt\n\t OPxq38yEmLbXQ==","From":"Jakub Kicinski ","To":"mmc@linux.ibm.com","Cc":"Jakub Kicinski ,\n\tnetdev@vger.kernel.org,\n\tdavem@davemloft.net,\n\tedumazet@google.com,\n\tpabeni@redhat.com,\n\thorms@kernel.org,\n\tbjking1@linux.ibm.com,\n\tharen@linux.ibm.com,\n\tricklind@linux.ibm.com,\n\tmaddy@linux.ibm.com,\n\tmpe@ellerman.id.au,\n\tlinuxppc-dev@lists.ozlabs.org,\n\tstable@vger.kernel.org,\n\tshaik.abdulla1@ibm.com,\n\tnaveedaus@in.ibm.com","Subject":"Re: [PATCH net v2] ibmveth: Disable GSO for packets with small MSS","Date":"Sat, 18 Apr 2026 10:54:51 -0700","Message-ID":"<20260418175451.122193-1-kuba@kernel.org>","X-Mailer":"git-send-email 2.53.0","In-Reply-To":"<20260417172910.81433-1-mmc@linux.ibm.com>","References":"<20260417172910.81433-1-mmc@linux.ibm.com>","X-Mailing-List":"linuxppc-dev@lists.ozlabs.org","List-Id":"","List-Help":"","List-Owner":"","List-Post":"","List-Archive":",\n ","List-Subscribe":",\n ,\n ","List-Unsubscribe":"","Precedence":"list","MIME-Version":"1.0","Content-Transfer-Encoding":"8bit","X-Spam-Status":"No, score=-0.2 required=3.0 tests=DKIMWL_WL_HIGH,DKIM_SIGNED,\n\tDKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,SPF_HELO_NONE,SPF_PASS\n\tautolearn=disabled version=4.0.1 OzLabs 8","X-Spam-Checker-Version":"SpamAssassin 4.0.1 (2024-03-25) on lists.ozlabs.org"}},{"id":3679158,"web_url":"http://patchwork.ozlabs.org/comment/3679158/","msgid":"","date":"2026-04-20T00:12:39","subject":"Re: [PATCH net v2] ibmveth: Disable GSO for packets with small MSS","submitter":{"id":91298,"url":"http://patchwork.ozlabs.org/api/people/91298/","name":"mingming cao","email":"mmc@linux.ibm.com"},"content":"On 4/18/26 10:54 AM, Jakub Kicinski wrote:\n> This is an AI-generated review of your patch. The human sending this\n> email has considered the AI review valid, or at least plausible.\n\nThanks for the review and the questions!\n\n> ---\n> ibmveth: Disable GSO for packets with small MSS\n>\n> This commit adds an ndo_features_check callback to the ibmveth driver to\n> disable segmentation offload when the MSS is less than 224 bytes. This\n> prevents physical adapters in SEA configurations from freezing when given\n> small MSS packets.\n>\n>> diff --git a/drivers/net/ethernet/ibm/ibmveth.c b/drivers/net/ethernet/ibm/ibmveth.c\n>> --- a/drivers/net/ethernet/ibm/ibmveth.c\n>> +++ b/drivers/net/ethernet/ibm/ibmveth.c\n> [ ... ]\n>\n>> @@ -1756,6 +1756,25 @@ static int ibmveth_set_mac_addr(struct net_device *dev, void *p)\n>> \treturn 0;\n>> }\n>> \n>> +static netdev_features_t ibmveth_features_check(struct sk_buff *skb,\n>> +\t\t\t\t\t\tstruct net_device *dev,\n>> +\t\t\t\t\t\tnetdev_features_t features)\n>> +{\n>> +\t/* Some physical adapters do not support segmentation offload with\n>> +\t * MSS < 224. Disable GSO for such packets to avoid adapter freeze.\n>> +\t */\n>> +\tif (skb_is_gso(skb)) {\n> The commit message mentions this matches the ibmvnic hardware errata from\n> commit f10b09ef687f. That commit disabled GSO for both gso_size < 224 and\n> gso_segs == 1.\n>\n> By omitting the check for skb_shinfo(skb)->gso_segs == 1, could a\n> single-segment GSO packet still cause the adapter to freeze?\nGood question. Unlike ibmvnic, ibmveth does not need to check for \nsingle-segment GSO packets (gso_segs == 1).\n\nIn ibmvnic, the firmware processes all GSO packets, including \nsingle-segment ones, through the same LSO code path. This means even \ngso_segs == 1 packets can trigger the hardware errata.\n\nIn ibmveth, the PowerVM hypervisor intelligently bypasses the LSO path \nfor single-segment packets. When gso_segs == 1, the hypervisor treats \nthe packet as a regular (non-GSO) packet and transmits it directly \nwithout invoking the problematic hardware segmentation logic. Therefore, \nsingle-segment GSO packets never reach the code path that causes the freeze.\n\nThis architectural difference is why ibmvnic needs the gso_segs check \nbut ibmveth does not.\n>\n>> +\t\tif (skb_shinfo(skb)->gso_size < IBMVETH_MIN_LSO_MSS) {\n>> +\t\t\tnetdev_warn_once(dev,\n>> +\t\t\t\t\t \"MSS %u too small for LSO, disabling GSO\\n\",\n>> +\t\t\t\t\t skb_shinfo(skb)->gso_size);\n>> +\t\t\tfeatures &= ~NETIF_F_GSO_MASK;\n>> +\t\t}\n>> +\t}\n>> +\n>> +\treturn features;\n> When implementing a custom ndo_features_check callback, netif_skb_features()\n> will bypass the standard dflt_features_check() function. Does this mean\n> vlan_features_check() is no longer called for this driver?\n>\n> If vlan_features_check() is skipped, multi-tagged (QinQ) VLAN packets\n> might retain GSO and protocol-specific checksum offloads that the hardware\n> parser cannot handle.\n>\n> Should this return vlan_features_check(skb, features) instead?\n\nYou’re correct about the interaction with the default feature filtering. \nWith a custom ndo_features_check(), the standard dflt_features_check() \npath is bypassed, so vlan_features_check() must be called explicitly to \npreserve existing VLAN/QinQ and checksum handling.\n\nThank you for catching this! I'll send v3 shortly with:\n1. The vlan_features_check() call added\n2. Updated commit message explaining why gso_segs check is not needed \nfor ibmveth\n\nBest regards,\n\nMingming\n\n\n>> +}","headers":{"Return-Path":"\n ","X-Original-To":["incoming@patchwork.ozlabs.org","linuxppc-dev@lists.ozlabs.org"],"Delivered-To":"patchwork-incoming@legolas.ozlabs.org","Authentication-Results":["legolas.ozlabs.org;\n\tdkim=pass (2048-bit key;\n unprotected) header.d=ibm.com header.i=@ibm.com header.a=rsa-sha256\n header.s=pp1 header.b=YMCfY0nv;\n\tdkim-atps=neutral","legolas.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=lists.ozlabs.org\n (client-ip=2404:9400:21b9:f100::1; helo=lists.ozlabs.org;\n envelope-from=linuxppc-dev+bounces-19843-incoming=patchwork.ozlabs.org@lists.ozlabs.org;\n receiver=patchwork.ozlabs.org)","lists.ozlabs.org;\n arc=none smtp.remote-ip=148.163.156.1","lists.ozlabs.org;\n dmarc=pass (p=none dis=none) header.from=linux.ibm.com","lists.ozlabs.org;\n\tdkim=pass (2048-bit key;\n unprotected) header.d=ibm.com header.i=@ibm.com header.a=rsa-sha256\n header.s=pp1 header.b=YMCfY0nv;\n\tdkim-atps=neutral","lists.ozlabs.org;\n spf=pass (sender SPF authorized) smtp.mailfrom=linux.ibm.com\n (client-ip=148.163.156.1; helo=mx0a-001b2d01.pphosted.com;\n envelope-from=mmc@linux.ibm.com; receiver=lists.ozlabs.org)"],"Received":["from lists.ozlabs.org (lists.ozlabs.org\n [IPv6:2404:9400:21b9:f100::1])\n\t(using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)\n\t key-exchange x25519 server-signature ECDSA (secp384r1 raw public key)\n server-digest SHA384)\n\t(No client certificate requested)\n\tby legolas.ozlabs.org (Postfix) with ESMTPS id 4fzQtb2ZQ4z1yCv\n\tfor ; Mon, 20 Apr 2026 10:13:11 +1000 (AEST)","from boromir.ozlabs.org (localhost [127.0.0.1])\n\tby lists.ozlabs.org (Postfix) with ESMTP id 4fzQtT2VQRz2yl2;\n\tMon, 20 Apr 2026 10:13:05 +1000 (AEST)","from mx0a-001b2d01.pphosted.com (mx0a-001b2d01.pphosted.com\n [148.163.156.1])\n\t(using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)\n\t key-exchange x25519 server-signature RSA-PSS (2048 bits) server-digest\n SHA256)\n\t(No client certificate requested)\n\tby lists.ozlabs.org (Postfix) with ESMTPS id 4fzQtR58fRz2xSF\n\tfor ; Mon, 20 Apr 2026 10:13:03 +1000 (AEST)","from pps.filterd (m0353729.ppops.net [127.0.0.1])\n\tby mx0a-001b2d01.pphosted.com (8.18.1.11/8.18.1.11) with ESMTP id\n 63JJjOLY2986195;\n\tMon, 20 Apr 2026 00:12:46 GMT","from ppma13.dal12v.mail.ibm.com\n (dd.9e.1632.ip4.static.sl-reverse.com [50.22.158.221])\n\tby mx0a-001b2d01.pphosted.com (PPS) with ESMTPS id 4dm2j6dj2m-1\n\t(version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT);\n\tMon, 20 Apr 2026 00:12:45 +0000 (GMT)","from pps.filterd (ppma13.dal12v.mail.ibm.com [127.0.0.1])\n\tby ppma13.dal12v.mail.ibm.com (8.18.1.7/8.18.1.7) with ESMTP id\n 63K05Ktf031623;\n\tMon, 20 Apr 2026 00:12:44 GMT","from smtprelay05.dal12v.mail.ibm.com ([172.16.1.7])\n\tby ppma13.dal12v.mail.ibm.com (PPS) with ESMTPS id 4dmpgg2mms-1\n\t(version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT);\n\tMon, 20 Apr 2026 00:12:44 +0000 (GMT)","from smtpav02.wdc07v.mail.ibm.com (smtpav02.wdc07v.mail.ibm.com\n [10.39.53.229])\n\tby smtprelay05.dal12v.mail.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id\n 63K0CgYo27918956\n\t(version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK);\n\tMon, 20 Apr 2026 00:12:42 GMT","from smtpav02.wdc07v.mail.ibm.com (unknown [127.0.0.1])\n\tby IMSVA (Postfix) with ESMTP id 3BE1B58058;\n\tMon, 20 Apr 2026 00:12:42 +0000 (GMT)","from smtpav02.wdc07v.mail.ibm.com (unknown [127.0.0.1])\n\tby IMSVA (Postfix) with ESMTP id 7AB205805B;\n\tMon, 20 Apr 2026 00:12:40 +0000 (GMT)","from [9.61.89.198] (unknown [9.61.89.198])\n\tby smtpav02.wdc07v.mail.ibm.com (Postfix) with ESMTP;\n\tMon, 20 Apr 2026 00:12:40 +0000 (GMT)"],"ARC-Seal":"i=1; a=rsa-sha256; d=lists.ozlabs.org; s=201707; t=1776643985;\n\tcv=none;\n b=fmTiLC7pl6QbKCxX9a6SGWpuLdaW3mGF8GwXPeLwRSM33OnLAjbhP4qXIAoK2ROGjuCJHsn4LLamCqT1fC8ash9jUCKyemYSJBn8bioaAJZHNYf3ozjDYAixXNCXgBaQx5pj9N6RQ3NTYYHyAPQpWSkVlYADnK4FZUJVpvynRN9UYrF3MTaVoIwRhjOFcZjibCKjeRR0BvoJt3xNgykcrHIeNqmkvSP4wMR+P8vwo6FqqJQwIqahFGfiFtsx3yZx5JOeCHgciNFVU40Ndklp90QYcN0dw28bUVcBPucvwwUJaefSVrQOfj9SRTpuoVX2pBmItkqZbO7AfjPiOQl6Jg==","ARC-Message-Signature":"i=1; a=rsa-sha256; d=lists.ozlabs.org; s=201707;\n\tt=1776643985; c=relaxed/relaxed;\n\tbh=aZBdItkfAsnP3W4OIPRwFKg8WBJUd9YO47VwRzMsse4=;\n\th=Message-ID:Date:MIME-Version:Subject:To:Cc:References:From:\n\t In-Reply-To:Content-Type;\n b=Z4Iy7W6uigNQrX+XRLO1Qb7BRkw1GilG39bvYcoGrcgzzz/PSqdF4z1qubO2e69MfJMKN+X53D3LPl2cy/40VEDzRhH2e2zM7v2xjenfHmTimVdS3a9tSCQmLVm0MnGm9HyhE0pBsctKWKCKDKjqrTb9ylcWsV/QM9sPt/sAgYwSCZ82NCaX867MyXiZ7WU3zMjmTeF3fFe3h3dLr/mDzlSFJzefBWpZi6R9ta0UbQq/1bOpg7tmMZH7ZfHmRZDD8ousuzXfWXmenDsiz5J6zylf2dzxXU5RJ6CU+IVlSzSQJyU7xIxNFtCYlwa5lPYJxsj3CWsXA/urQIx+pBE0dg==","ARC-Authentication-Results":"i=1; lists.ozlabs.org;\n dmarc=pass (p=none dis=none) header.from=linux.ibm.com;\n dkim=pass (2048-bit key;\n unprotected) header.d=ibm.com header.i=@ibm.com header.a=rsa-sha256\n header.s=pp1 header.b=YMCfY0nv; dkim-atps=neutral;\n spf=pass (client-ip=148.163.156.1; helo=mx0a-001b2d01.pphosted.com;\n envelope-from=mmc@linux.ibm.com;\n receiver=lists.ozlabs.org) smtp.mailfrom=linux.ibm.com","DKIM-Signature":"v=1; a=rsa-sha256; c=relaxed/relaxed; d=ibm.com; h=cc\n\t:content-transfer-encoding:content-type:date:from:in-reply-to\n\t:message-id:mime-version:references:subject:to; s=pp1; bh=aZBdIt\n\tkfAsnP3W4OIPRwFKg8WBJUd9YO47VwRzMsse4=; b=YMCfY0nvUOHNNv1jrxoaGT\n\tHCdM/0wahsGi1rWOXRjIBLkUl6sfW84NefA+Q6ax5sIY9GgaxO2g3zF6yTBh6Lvz\n\t/8m10na03tz6nLUl4rXq/FBOOJbWEbGhd8Rv7iRckYfBXf1csEREf1mUGgzILOTq\n\tzT0BoAJqyJ4L6TZEQFjNVKJbfL2lOYQUzwFvrtsvaZI+NQwY+O13gSqDe3/BvdiC\n\tKM5oZtUQGS5dB6AuQPWm9HeWoAzXURJFPrvSeu9NfPapm/TYmdtqeNCrlKvJUVI8\n\trxIFCoXFgaH1bvh2xYU8UHqlDZNg0v5a3V4h9EJLMqGPUs9826k3zryY8erlcV8g\n\t==","Message-ID":"","Date":"Sun, 19 Apr 2026 17:12:39 -0700","X-Mailing-List":"linuxppc-dev@lists.ozlabs.org","List-Id":"","List-Help":"","List-Owner":"","List-Post":"","List-Archive":",\n ","List-Subscribe":",\n ,\n ","List-Unsubscribe":"","Precedence":"list","MIME-Version":"1.0","User-Agent":"Mozilla Thunderbird","Subject":"Re: [PATCH net v2] ibmveth: Disable GSO for packets with small MSS","To":"Jakub Kicinski ","Cc":"netdev@vger.kernel.org, davem@davemloft.net, edumazet@google.com,\n pabeni@redhat.com, horms@kernel.org, bjking1@linux.ibm.com,\n haren@linux.ibm.com, ricklind@linux.ibm.com, maddy@linux.ibm.com,\n mpe@ellerman.id.au, linuxppc-dev@lists.ozlabs.org,\n stable@vger.kernel.org, shaik.abdulla1@ibm.com, naveedaus@in.ibm.com","References":"<20260417172910.81433-1-mmc@linux.ibm.com>\n <20260418175451.122193-1-kuba@kernel.org>","Content-Language":"en-US","From":"mingming cao ","In-Reply-To":"<20260418175451.122193-1-kuba@kernel.org>","Content-Type":"text/plain; charset=UTF-8; format=flowed","Content-Transfer-Encoding":"8bit","X-TM-AS-GCONF":"00","X-Proofpoint-Reinject":"loops=2 maxloops=12","X-Proofpoint-Spam-Details-Enc":"AW1haW4tMjYwNDE5MDI1NSBTYWx0ZWRfXywkL4mbph7pn\n y9NDpS8ktWEK/Wt4Fwq5/CuAM97+q0nNiMhqGZaFuUiQw9x1UCKTP/kkMPoF7J1fRI9KDZWut9T\n P6MiRMGKehdZtNTgQLsvcMnwuWQDrOpTYJd8baM/IM5HZc7QQd4ojtHZTXuVNVHVYe0Y4LHkUy8\n NLXDUIQyljIQdV/2gUNYnMZnRxeV9F4/XSM3cTdU4uyborwffjqa3yZNNJ+REwSF8X0BXgHHV9D\n XURHdprmg7h/F8Lyp/aDfZN4bs547Ay8rRr/LF4UFwawjc0/8UfBU0kWrbasJrnjrLUhifaP5fo\n yZ3oB8TRpMysbe1KB3sdrIgAgH7raUfWm3i2SmhibM2HlOo2RxuwTzeE2HVK86A1TgDWoBud/Ck\n 2+Gnh8NnRboVZPUgCc6J5xTbI1lpjtjH+rGkQbUGfehvw0910gk2l0UApS1sayntunEe6ZKUeP5\n GxSKH4WS5DraFJaozAQ==","X-Proofpoint-GUID":"t6hNByzCcWjgl0WInHRfkkYPE8JpykPZ","X-Authority-Analysis":"v=2.4 cv=SOJykuvH c=1 sm=1 tr=0 ts=69e56f7d cx=c_pps\n a=AfN7/Ok6k8XGzOShvHwTGQ==:117 a=AfN7/Ok6k8XGzOShvHwTGQ==:17\n a=IkcTkHD0fZMA:10 a=A5OVakUREuEA:10 a=VkNPw1HP01LnGYTKEx00:22\n a=RnoormkPH1_aCDwRdu11:22 a=uAbxVGIbfxUO_5tXvNgY:22 a=sDADSKU7Kdt2IJdVO5YA:9\n a=3ZKOabzyN94A:10 a=QEXdDO2ut3YA:10","X-Proofpoint-ORIG-GUID":"e1yCFhD-mX4ZlgjEllJFepkfqH0W5lmS","X-Proofpoint-Virus-Version":"vendor=baseguard\n engine=ICAP:2.0.293,Aquarius:18.0.1143,Hydra:6.1.51,FMLib:17.12.100.49\n definitions=2026-04-19_07,2026-04-17_04,2025-10-01_01","X-Proofpoint-Spam-Details":"rule=outbound_notspam policy=outbound score=0\n malwarescore=0 spamscore=0 priorityscore=1501 lowpriorityscore=0\n clxscore=1015 phishscore=0 suspectscore=0 adultscore=0 impostorscore=0\n bulkscore=0 classifier=typeunknown authscore=0 authtc= authcc= route=outbound\n adjust=0 reason=mlx scancount=1 engine=8.22.0-2604070000\n definitions=main-2604190255","X-Spam-Status":"No, score=-0.7 required=3.0 tests=DKIM_SIGNED,DKIM_VALID,\n\tRCVD_IN_DNSWL_LOW,RCVD_IN_MSPIKE_H4,RCVD_IN_MSPIKE_WL,SPF_HELO_NONE,\n\tSPF_PASS autolearn=disabled version=4.0.1 OzLabs 8","X-Spam-Checker-Version":"SpamAssassin 4.0.1 (2024-03-25) on lists.ozlabs.org"}}]