From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 627D3C61DD6 for ; Wed, 2 Sep 2026 21:21:28 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender:List-Subscribe:List-Help :List-Post:List-Archive:List-Unsubscribe:List-Id:In-Reply-To:Content-Type: MIME-Version:References:Message-ID:Subject:Cc:To:From:Date:Reply-To: Content-Transfer-Encoding:Content-ID:Content-Description:Resent-Date: Resent-From:Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID:List-Owner; bh=SYtMlpnTVCZyNNpnFLfBSqH0ZRU4U9gizBDSOdoTsHk=; b=NwqF1bDOAlaHUGCi8yTuHUr/a+ KL5exsTMGedRh67nf2GptntOx4Qeq/PD92CUIDN4lKe8+1LOcq6dQ8foOf1zdvSO4ejdcCvhtzNpE upwbEcPTuThi2mxcbXmO5+wqFgNrwyrKiuiYILjgCsxRb3G8TffQfJArmZ+yXZw+LEOzcAlc/pc1a zhmyaDpFpNzbOLajBVVRS+rxd2nfuCyYtOKLoTNo2HeOGe9j2ftsqVZBnIayZH/Y3l+8b2ZUBMZ3T nSwPG9kG6p7bSeeeEnAC6WppZV0jYAkFrpn1GYFvVbNS4T3F8Uvr0bvkynxQd4mCu+LPosC0uD8pC AyLMC6Sg==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.99.1 #2 (Red Hat Linux)) id 1x1sOO-0000000FvlB-3Cf5; Wed, 02 Sep 2026 21:21:12 +0000 Received: from mx0a-0031df01.pphosted.com ([205.220.168.131]) by bombadil.infradead.org with esmtps (Exim 4.99.1 #2 (Red Hat Linux)) id 1x1sOL-0000000Fvkm-3HMu for linux-arm-kernel@lists.infradead.org; Wed, 02 Sep 2026 21:21:12 +0000 Received: from pps.filterd (m0279866.ppops.net [127.0.0.1]) by mx0a-0031df01.pphosted.com (8.18.1.11/8.18.1.11) with ESMTP id 682KH3JN1898969 for ; Wed, 2 Sep 2026 21:21:09 GMT DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=qualcomm.com; h= cc:content-type:date:from:in-reply-to:message-id:mime-version :references:subject:to; s=qcppdkim1; bh=SYtMlpnTVCZyNNpnFLfBSqH0 ZRU4U9gizBDSOdoTsHk=; b=JouUdMFvzbWUx1dqVnfs1+3hNYj0jcaY/IFsaE3/ TydRPBETuj3H691I9W/E/IUtI8odJ972Q7e2JY4qhNCDJ/gA0Adop1aeWqkJZUzu 6/J3vy0ZZ5qkvciYOqMhIKtybnIwnkRBHtBlKpsFJeGLvaDi2TMnDrBIENoRVDkH dOwU002UwlnCBucTuvI7XzNh/+0T2qxzjNxoqNwQD986a6XqX2JzNLvQUc7olSKI BdYZZJhuJyxXwXne5dqJb/sCQSUxjELweBGwqOZmdyoXhtS9EC6CYJu8l3aubUlL ZHzuY9+l3DRx/UqVeA9EXiifVxygc7rRiEQvdk56DCdsPQ== Received: from mail-qk1-f197.google.com (mail-qk1-f197.google.com [209.85.222.197]) by mx0a-0031df01.pphosted.com (PPS) with ESMTPS id 4gemb028ux-1 (version=TLSv1.3 cipher=TLS_AES_128_GCM_SHA256 bits=128 verify=NOT) for ; Wed, 02 Sep 2026 21:21:08 +0000 (GMT) Received: by mail-qk1-f197.google.com with SMTP id af79cd13be357-93918756165so406538785a.0 for ; Wed, 02 Sep 2026 14:21:08 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=oss.qualcomm.com; s=google; t=1788384068; x=1788988868; darn=lists.infradead.org; h=in-reply-to:content-disposition:content-type:mime-version :references:message-id:subject:cc:to:from:date:from:to:cc:subject :date:message-id:reply-to:content-type; bh=SYtMlpnTVCZyNNpnFLfBSqH0ZRU4U9gizBDSOdoTsHk=; b=ZGUam1hm8c/9mL6dB/6Em+PJ827EUEcNMtKCvX5t+PhRFII0IBs4OAAjQlhvWE+DXK G7AXMSIArj9qLn8W5WvU5pH+DS9iwH2/lmRtHuOFymtE1q5a0xyjYmyVbpaJRXyGt6HZ bNcLEHFcAsvIWpvu0BxlEiCFscQOdC6Hb8NkA1H7WjILgpaTgzO8VSkp5d3RJbSasKem 7wrpmboSkPjRmY4hi72Zf2TDyOxnsCNNhjMPN2gUjwM9xZQJrX0Shqu7ieLldyHDLRMw WSnjXTd4HiEULUKOsT9tSRdxveT7/51OdM83DS5xNALJ/bvcXtwG8k/OGkXz9n+dM2sh GshQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1788384068; x=1788988868; h=in-reply-to:content-disposition:content-type:mime-version :references:message-id:subject:cc:to:from:date:x-gm-gg :x-gm-message-state:from:to:cc:subject:date:message-id:reply-to :content-type; bh=SYtMlpnTVCZyNNpnFLfBSqH0ZRU4U9gizBDSOdoTsHk=; b=r+2DJpTjBF8reOb0Fg60FQ8/PVwail11Z8d/v+3Nz2egd8v+Y3Sdf8+VIUBT/bznus fT33ypXzOfsnWX9+0JT+OFv/aKFvACWSyhNuyTX/4IdjO2oyc7QzRtVlnhjDxMfIpXa+ 6vjT9wcx8cvzrr+IdPCeePamyOTpIrHXPj0HWRIb05XIZ3k8DXP8GiYMl5U3Nq7pOnqX LM8KRzm0iu/jTLTJXPXiCsTBuy0VQdU33bDBuQBKJI9T3EyD1sb3c32O3UoDbMoUFZ7p QazCqlGhl+dRZP9bKcITxyqij0tK8Nd/iktrqunwaHyfj1DPe0b+gEQxUqJdYHY/Ro8Y E++w== X-Forwarded-Encrypted: i=1; AKwUvBwcbx5U0tOiGAI3UlBJ5ws2zRQxkE+denB+VgTjHWsD2smtlurZyi6JNE2NbNV8CC5+OL6esbu8YByqjL9vuNq6@lists.infradead.org X-Gm-Message-State: AFuF++lXF3Db8g8yLK8ul/alUx5aV1wHAaqjPlL0aCEgp+Mg8UdPsuqJ 7J9nNl1L1OFZROptgEhwmb0CQn0bzU+CkLm6yFUZuhCZ6zNI14wBwmwTF/Ra6N6Y+J9fDHNpEb7 Sq1oMGhIh/1nLLHovBy0FiRKXpZ55Etk2LnUXw8kBIDc0Wr+t6P1mVqDiOGkVnuKwkw9jEbmsql dbgg== X-Gm-Gg: AYBFou3jf+AeZ954vZp7pwvBXCkRyu9SmkKJhFYvikii8FHSglvWiLNNt46fy5peWDp spZYu379n71rXb0mojivwWHFFjoLetfDUpW/mUWsjx1veZEG3iyUCM6xf9sfmhqytGAuDkVc/08 CqxKXcxH8ZXL2NGvIekxsKbY3BDiJptJieNnDFoiwP2E9LIch3n4S9z2UhZ7WA2+jp2i+g8CGJe r0zMZ/ttblrU66sDpCssJfqs3uY/mqparQQ9mbYEMd1GB7YGxXN4jQDXiznxy0OsPWuLBVSB+wc DRgnEyIn3AGaxsIPbNyBMxLBydfspYImNF1J47YFc0yyV5CxQrY9SvWHgvSz/zOvr6udkK6CXG6 OmG6aQl4HfuOtMg== X-Received: by 2002:a05:620a:6982:b0:937:27fb:96f3 with SMTP id af79cd13be357-93960e05532mr1120929685a.17.1788384067630; Wed, 02 Sep 2026 14:21:07 -0700 (PDT) X-Received: by 2002:a05:620a:6982:b0:937:27fb:96f3 with SMTP id af79cd13be357-93960e05532mr1120916885a.17.1788384066801; Wed, 02 Sep 2026 14:21:06 -0700 (PDT) Received: from localhost ([188.216.77.92]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-48448eeae34sm9438269f8f.32.2026.09.02.14.21.04 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 02 Sep 2026 14:21:05 -0700 (PDT) Date: Wed, 2 Sep 2026 23:21:04 +0200 From: Lorenzo Bianconi To: netdev-bot+sashiko@kernel.org Cc: maxime.chevallier@bootlin.com, andrew+netdev@lunn.ch, davem@davemloft.net, edumazet@google.com, kuba@kernel.org, pabeni@redhat.com, mcoquelin.stm32@gmail.com, alexandre.torgue@foss.st.com, netdev@vger.kernel.org, linux-stm32@st-md-mailman.stormreply.com, linux-arm-kernel@lists.infradead.org Subject: Re: [net-next,v3] net: stmmac: drop the queue-0 pinning for GSO frames Message-ID: References: <20260831-stmmac_select_queue-tso-fix-v3-1-d9c215fe7a85@oss.qualcomm.com> <178837492226.3394541.13110256562881802796@kernel.org> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha512; protocol="application/pgp-signature"; boundary="9jHsxYCOqOIPICRS" Content-Disposition: inline In-Reply-To: <178837492226.3394541.13110256562881802796@kernel.org> X-Proofpoint-ORIG-GUID: zilAjDbEPbBHR2gseul3hmOi8Qe--zq4 X-Proofpoint-Spam-Details-Enc: AW1haW4tMjYwOTAyMDE4OCBTYWx0ZWRfX6exvr9W4ZiVx cfYICHMo5SslGQQL1R7vikA1Zfgjtqbeg8LLVfAfdCHXR0k186/0iO+4kh4OSE4x8cJSCdP3ZIv SNglT6yd7u1Pgnjrj7+SRONa+OfmTKze+M8rM7+hMj1cz+xrUkbp+qidPta0qx/yyQ6/sQ0oJx9 FhE+iKOpzwiQeaRXoDZSrF/0FcUAUjKajIwfa9Bg7cbJ6IrRBElvh0fXXOFyvqCqQ2TXWBPpZUy z8NRdnz4Ft/pak+CtCXXz8Z9Ximn8rFPy6tlx7XcocZXwBxEppeupNw+8+wxgWtyR7E7lXIHzu+ 67D2laRcRzL+OHKI77F8iRLw9bdlyv2TMpkjJpJewIwwdFNWlh7mhz/hwK6ncmjXq2BOrfkKe+e d/GDn+Pk8ZmJDjCbKIHu/2bQ8oGEmwmz+VM7ll5XtQv56mrb7vAxpahElfFjw3NV786STSO3Oeq w+8bVkEUApwgVOIf8gQ== X-Proofpoint-Spam-Info: AW1haW4tMjYwOTAyMDE4OCBTYWx0ZWRfXzUIMyQUhuY1/ p1/QPr4Vvi7ZYaZ/c3xTY8dNO1DEQOME4FcZpJnRebLY8/47Dp7/da4EfrXWcX1BcxaJdoVJS0r GDF6v5tfGv2fyFb6tTkJVbyZMw2/cJ8= X-Authority-Analysis: v=2.4 cv=EuPiaycA c=1 sm=1 tr=0 ts=6a989345 cx=c_pps a=50t2pK5VMbmlHzFWWp8p/g==:117 a=WpTaRW6qxYHRGzLzQsVYzg==:17 a=VdqzKS8jKosA:10 a=s4-Qcg_JpJYA:10 a=VkNPw1HP01LnGYTKEx00:22 a=u7WPNUs3qKkmUXheDGA7:22 a=YMgV9FUhrdKAYTUUvYB2:22 a=VwQbUJbxAAAA:8 a=EUspDBNiAAAA:8 a=9R54UkLUAAAA:8 a=kh2Xnvg0e9x1CB174FoA:9 a=QEXdDO2ut3YA:10 a=ZJvtu0cxrLrnXHhDaDcA:9 a=IoWCM6iH3mJn3m4BftBB:22 a=YTcpBFlVQWkNscrzJ_Dz:22 X-Proofpoint-GUID: zilAjDbEPbBHR2gseul3hmOi8Qe--zq4 X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.293,Aquarius:18.0.1176,Hydra:6.1.134,FMLib:17.12.100.49 definitions=2026-09-02_05,2026-09-02_04,2025-10-01_01 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 phishscore=0 bulkscore=0 adultscore=0 clxscore=1015 spamscore=0 malwarescore=0 suspectscore=0 priorityscore=1501 lowpriorityscore=0 impostorscore=0 classifier=typeunknown authscore=0 authtc= authcc= route=outbound adjust=0 reason=mlx scancount=1 engine=8.22.0-2606150000 definitions=main-2609020188 X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.9.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20260902_142109_850622_743EE276 X-CRM114-Status: GOOD ( 45.50 ) X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=archiver.kernel.org@lists.infradead.org --9jHsxYCOqOIPICRS Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable > Thank you for your contribution! Sashiko AI review found 4 potential > issue(s) to consider: >=20 > Critical: 0 =C2=B7 High: 1 =C2=B7 Medium: 2 =C2=B7 Low: 1 >=20 > - [High] Removing .ndo_select_queue silently disables hardware TSO/USO > for most GSO flows on all in-tree stmmac platforms that mark every TX= =E2=80=A6 > - [Medium] The patch's stated safety property =E2=80=94 'stmmac_features_= check() > already validates each GSO frame against the capabilities of the queue= =E2=80=A6 > - [Medium] The patch deletes the hardware fact that the removed comment > carried ('There is no way to determine the number of TSO/USO capable=E2= =80=A6 > - [Low] The commit claims to fix a real user-visible offload defect > ('This also fixes the case where queue 0 is not TSO-capable while=E2=80= =A6 >=20 > -- >=20 > net: stmmac: drop the queue-0 pinning for GSO frames >=20 > This drops stmmac_select_queue() and its .ndo_select_queue entry so GSO > frames are no longer pinned to TX queue 0. The changelog argues the pinni= ng > is redundant because stmmac_features_check() already validates each GSO > frame against the capabilities of the queue it is mapped to. Non-GSO > traffic keeps going through netdev_pick_tx(). >=20 > Link: https://lore.kernel.org/r/20260808-stmmac_select_queue-tso-fix-v2-1= -67175b29772e@oss.qualcomm.com > Link: https://lore.kernel.org/r/20260807-stmmac_select_queue-tso-fix-v1-1= -4c4787bad02b@oss.qualcomm.com >=20 > >From the changelog: >=20 > > This also fixes the case where queue 0 is not TSO-capable while other > > queues are, which previously forced all TSO traffic into software GSO. >=20 > [Severity: Low] > Since this is described as a fix, should it carry a Fixes tag? The queue-0 > pinning being removed came in with commit 4993e5b37e8b ("net: stmmac: > Re-work the queue selection for TSO packets"), which in turn fixed > c5acdbee22a1 ("net: stmmac: Send TSO packets always from Queue 0"). >=20 > The removal also depends on the per-queue checks in > stmmac_features_check() added by commit b55dfb173ce8 ("net: stmmac: move > check for hardware checksum supported") and the surrounding series. Witho= ut > those, backporting this alone removes the only thing that steered GSO > frames to a capable queue. >=20 > Could the changelog name those prerequisites so stable triage has > something to work from? >=20 > The claimed defect itself looks describable from DT, via > stmmac_mtl_setup(): >=20 > plat->tx_queues_cfg[queue].coe_unsupported =3D > of_property_read_bool(q_node, "snps,coe-unsupported"); >=20 > > diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/driver= s/net/ethernet/stmicro/stmmac/stmmac_main.c > > index 66ae365e1c89f..25121d6d84995 100644 > > --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c > > +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c > > @@ -6428,24 +6428,6 @@ static int stmmac_setup_tc(struct net_device *nd= ev, enum tc_setup_type type, > > } > > } > > =20 > > -static u16 stmmac_select_queue(struct net_device *dev, struct sk_buff = *skb, > > - struct net_device *sb_dev) > > -{ > > - int gso =3D skb_shinfo(skb)->gso_type; > > - > > - if (gso & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6 | SKB_GSO_UDP_L4)) { > > - /* > > - * There is no way to determine the number of TSO/USO > > - * capable Queues. Let's use always the Queue 0 > > - * because if TSO/USO is supported then at least this > > - * one will be capable. > > - */ > > - return 0; > > - } >=20 > [Severity: High] > Does this lose hardware TSO/USO for most GSO flows on the in-tree > platforms that mark every TX queue above queue 0 as TBS? >=20 > dwmac-intel.c, dwmac-imx.c, dwmac-mediatek.c, dwmac-qcom-ethqos.c and > stmmac_pci.c all do the equivalent of intel_mgbe_common_data(): >=20 > /* Default TX Q0 to use TSO and rest TXQ for TBS */ > if (i > 0) > plat->tx_queues_cfg[i].tbs_en =3D 1; >=20 > That becomes STMMAC_TBS_AVAIL at open time in __stmmac_setup_dma_desc(), > with no ETF qdisc involved: >=20 > int tbs_en =3D priv->plat->tx_queues_cfg[chan].tbs_en; >=20 > /* Setup per-TXQ tbs flag before TX descriptor alloc */ > tx_q->tbs |=3D tbs_en ? STMMAC_TBS_AVAIL : 0; >=20 > and stmmac_tso_channel_permitted() then returns false for those channels: >=20 > /* TSO and TBS cannot co-exist */ > return !(priv->dma_conf.tx_queue[chan].tbs & STMMAC_TBS_AVAIL); >=20 > The commit message says stmmac_features_check() "validates each GSO frame > against the capabilities of the queue it is mapped to", but the check only > demotes the frame, it does not move it: >=20 > if (skb_is_gso(skb)) { > if (!stmmac_tso_channel_permitted(priv, queue) || > !stmmac_tso_valid_packet(skb)) > features &=3D ~NETIF_F_GSO_MASK; >=20 > So with the selector gone, netdev_pick_tx() hashes GSO flows over all N > queues and roughly (N-1)/N of TCP/UDP-GSO flows on these boards end up > segmented in software by validate_xmit_skb() rather than by the MAC. Is > that intended, and if so could the changelog mention the throughput and > CPU cost instead of describing the change as removing something that is > "no longer needed"? >=20 > Would a capability-aware queue selection (or a per-queue TSO map consulted > by the selector) be needed to keep the "Q0 is the TSO queue" contract tho= se > platforms document? We agreed in the previous disucssion to allow the networking stack to decid= e if the selected queue should perform TSO running stmmac_features_check(). Moreover, there is no guarantee queue 0 will always support TSO for all the platforms. >=20 > > - > > - return netdev_pick_tx(dev, skb, NULL) % dev->real_num_tx_queues; > > -} > > - >=20 > [Severity: Medium] > The deleted comment records a hardware fact: there is no way to determine > which TX DMA channels were synthesized with the TSO data path. DWMAC and > XGMAC only expose a single global TSOEN bit, surfaced as > priv->dma_cap.tsoen, and stmmac_hw_setup() programs TSE from it for every > non-TBS channel without any readback: >=20 > if (priv->dma_cap.tsoen && priv->plat->flags & STMMAC_FLAG_TSO_EN) { > for (chan =3D 0; chan < tx_cnt; chan++) { > if (!stmmac_tso_channel_permitted(priv, chan)) > continue; >=20 > stmmac_enable_tso(priv, priv->ioaddr, 1, chan); > } > } >=20 > stmmac_features_check() only knows about tx_queues_cfg[queue].coe_unsuppo= rted > and TBS, so on a part where only a subset of channels implement TSO it > cannot clear NETIF_F_GSO_MASK, and stmmac_xmit() then hands the frame to > stmmac_tso_xmit() on a channel whose DMA does not implement TSE. That > programs an MSS context descriptor plus TDES3 in TSE/THL/payload-length > form on a channel that decodes those bits as CIC and frame length. >=20 > Is there evidence that all channels are TSO-capable on the supported part= s? > If not, would a per-queue tso capability consulted by > stmmac_features_check() be the replacement for the removed workaround? As pointed out above I guess it is up to the networking stack to decide if = hw TSO can be used or the traffic should be segmented in sw. I do not think al= ways use queue 0 for TSO is the right approach. >=20 > > static int stmmac_set_mac_address(struct net_device *ndev, void *addr) > > { > > struct stmmac_priv *priv =3D netdev_priv(ndev); > > @@ -7302,7 +7284,6 @@ static const struct net_device_ops stmmac_netdev_= ops =3D { > > .ndo_eth_ioctl =3D stmmac_ioctl, > > .ndo_get_stats64 =3D stmmac_get_stats64, > > .ndo_setup_tc =3D stmmac_setup_tc, > > - .ndo_select_queue =3D stmmac_select_queue, >=20 > [Severity: Medium] > Does the "features_check validates the queue it is mapped to" argument ho= ld > on the AF_PACKET PACKET_QDISC_BYPASS path? __dev_direct_xmit() runs the > feature validation before assigning the real queue: >=20 > net/core/dev.c:__dev_direct_xmit() { > ... > skb =3D validate_xmit_skb_list(skb, dev, &again); > if (skb !=3D orig_skb) > goto drop; >=20 > skb_set_queue_mapping(skb, queue_id); > ... > } >=20 > and with .ndo_select_queue gone, packet_pick_tx_queue() takes the else > branch, so queue_id can be any queue: >=20 > net/packet/af_packet.c:packet_pick_tx_queue() { > ... > skb_record_rx_queue(skb, cpu % dev->real_num_tx_queues); > if (ops->ndo_select_queue) { > queue_index =3D ops->ndo_select_queue(dev, skb, NULL); > queue_index =3D netdev_cap_txqueue(dev, queue_index); > } else { > queue_index =3D netdev_pick_tx(dev, skb, NULL); > } > ... > } >=20 > The mapping stmmac_features_check() reads via skb_get_queue_mapping() is > therefore (cpu % real_num_tx_queues) + 1, not queue_id. When the evaluated > queue is TSO-permitted but the queue actually used is not, NETIF_F_GSO_MA= SK > survives and stmmac_xmit() dispatches unconditionally: >=20 > if (skb_is_gso(skb)) > return stmmac_tso_xmit(skb, dev); >=20 > Before this patch the same ordering existed but was harmless, because > packet_pick_tx_queue() consulted ndo_select_queue and GSO frames always > went out on queue 0. Is something needed to close that now? >=20 > Separately, that mapping can be real_num_tx_queues itself when > cpu % real_num_tx_queues =3D=3D real_num_tx_queues - 1. Can this read past > priv->plat->tx_queues_cfg[] and priv->dma_conf.tx_queue[] in > stmmac_features_check() when real_num_tx_queues =3D=3D MTL_MAX_TX_QUEUES? I guess this issue was already present even before this patch (e.g. for non= -TSO traffic transmitted by a AF_PACKET socket where PACKET_QDISC_BYPASS is enabled). I guess we should fix it with a dedicated patch (e.g. verifying queue is never greater than MTL_MAX_TX_QUEUES in stmmac_features_check()). Regards, Lorenzo >=20 > --=20 > Sashiko AI review =C2=B7 https://netdev-ai.bots.linux.dev/sashiko/#/patch= set/20260831-stmmac_select_queue-tso-fix-v3-1-d9c215fe7a85%40oss.qualcomm.c= om --9jHsxYCOqOIPICRS Content-Type: application/pgp-signature; name=signature.asc -----BEGIN PGP SIGNATURE----- iHUEABYKAB0WIQTquNwa3Txd3rGGn7Y6cBh0uS2trAUCapiTQAAKCRA6cBh0uS2t rIIVAP0a0Fhz/sKVZ2P09QB0lqSrGCT/eq3TpkJ4fcTGHBcpggD/XcFsHrENORZH DSkHDXJbeUtuotkDXHxGvcahut8V1gI= =mF4n -----END PGP SIGNATURE----- --9jHsxYCOqOIPICRS--