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 gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (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 E4CD2C44501 for ; Wed, 15 Jul 2026 22:52:04 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 7B32610E247; Wed, 15 Jul 2026 22:52:04 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=gmail.com header.i=@gmail.com header.b="GfpCvBHy"; dkim-atps=neutral Received: from mail-wr1-f44.google.com (mail-wr1-f44.google.com [209.85.221.44]) by gabe.freedesktop.org (Postfix) with ESMTPS id CD13510E247 for ; Wed, 15 Jul 2026 22:52:02 +0000 (UTC) Received: by mail-wr1-f44.google.com with SMTP id ffacd0b85a97d-47d70879764so4157355f8f.2 for ; Wed, 15 Jul 2026 15:52:02 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1784155921; x=1784760721; darn=lists.freedesktop.org; h=content-type:content-transfer-encoding:mime-version:references :in-reply-to:message-id:date:subject:to:from:from:to:cc:subject:date :message-id:reply-to:content-type; bh=6aBuWvd4jPDPONcxOqIGGTxip/syZyM9G94JPQhCOjg=; b=GfpCvBHyEOBuEM9MrXUtNvy1MFuvv7ZVrufzBkJXobN9BtyLTdCZNCFeY72h7kbYab Hn0yJnxNOV3zv6tC79MIM5TgOzs3SZ9wDyK/D2zIx+vAMi8NAPVStlEVPwzcek+ZI8zj wsseptTQ9+NF+g7YwAkn2rCrcV49zdVBCjz1lU2xswCyjEh7RFi29fjdzfj4nV8xC92k Ue3OB0uBVD4RA0d5GKh2QpXdAN6zGAIZmX1DhMZG+8+sJcwMyU46kG5timUPnMW0movC +Xp1A7MlVwmrMK4TgUr/hfR9NQxoKGuEhajP2nrXdeVl352G6kAyZkWdeo3BLlNsIQfa vsVw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1784155921; x=1784760721; h=content-type:content-transfer-encoding:mime-version:references :in-reply-to:message-id:date:subject:to:from:x-gm-gg :x-gm-message-state:from:to:cc:subject:date:message-id:reply-to :content-type; bh=6aBuWvd4jPDPONcxOqIGGTxip/syZyM9G94JPQhCOjg=; b=gtodIaTZbew9L8V55rbShm8Oht128VZDQS3Ullu1vcp/tOSwncTqp7O3cbMhcbc2pt 3HVSsNfIlLcgLs1wdsAsGyQ0W8UFS5vUxKWNFoUSLsDm7iMnK4Gn9qd947twhOkKuQH5 oNU8yy+QLhYtUINU/NpRmwE9Z0k5au4ol9B2SYebfz8+KMqxYXndgsVTxzZjK9FvO9Gf Meke2TjrXPouMZOx3Y9ShE2knynuG50ozZ8//MsCzqLUVyuYlvrwR29dDwC143HU0lR2 llKz0ETZHkrZFWp5wnSa7CZHZ1v5DIOV1TJ85cZ7uisGHNisxoIeELaHGHzUYlA3lbfn P8aw== X-Gm-Message-State: AOJu0YwZBghQ/q/uWwwTGMnJdEaZixAceKBPWFFlLp/qOxaFkr3KR0p3 vG27HHKtRB/Hm9/OBu3hbGjNuy725alpP7pupXGlWuhl3FICY3AaIMMqvJCcD50W X-Gm-Gg: AfdE7ck8dqM80vnK3rGJlVMhSIcsiyo8cX6Phw5Nll/u6OP7rcSwCh/LtX6fvEyX6Il r5ztpzZ6785OBWFAsRyafvQ+2W8sMN/aA+3vEiy+88QiBrGaOeZBBBX3krauURM522pnQMTfIO7 XoTucY0KJHKRTQqU1ibhF9qoMPm+T7Z04LZWIghIBhsjyOOQ4BuSGn6byR5tzvHoUNMrbt4nlrw OeF1uyIumB23Pf4+y4t02CA7NdVgMg5WknlXkgXtPzDRq3mUp1q5GDz3cjVAidmCC2wnoqSRMWz wUU3X0T6+aECjLxPmV3l93iZ6aU4wknNau64kieDESeYKEPNIiSCRefS/LnLgQVw68CwxaPiiHc +CeJKrrHNkyeSOlKyAKaS/mKDuCZHiBuNxeTllssOkgnBnm7m/9olCfe2xqQycV3wkpKea7YzUj knVr3T+gvu+Wp7yK5PAxj2PlOoSxu7f3HC2JLjdaBrcj6vvaaL X-Received: by 2002:a05:6000:1889:b0:47a:1f6b:ddb8 with SMTP id ffacd0b85a97d-47f4fceef45mr5753768f8f.39.1784155921082; Wed, 15 Jul 2026 15:52:01 -0700 (PDT) Received: from timur-hyperion.localnet (5401D94C.dsl.pool.telekom.hu. [84.1.217.76]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-47f464c25b2sm19885731f8f.30.2026.07.15.15.51.59 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 15 Jul 2026 15:51:59 -0700 (PDT) From: Timur =?UTF-8?B?S3Jpc3TDs2Y=?= To: amd-gfx@lists.freedesktop.org, Alexander.Deucher@amd.com, Natalie Vock , Amir Shetaia , Marek =?UTF-8?B?T2zFocOhaw==?= , Mario Limonciello , Tvrtko Ursulin , Felix Kuehling , Lijo Lazar , Siwei He , Philip Yang , Mukul Joshi , Christian =?UTF-8?B?S8O2bmln?= Subject: Re: [PATCH 02/14] drm/amdgpu/gfxhub: Enable retry fault interrupts when needed Date: Thu, 16 Jul 2026 00:51:57 +0200 Message-ID: In-Reply-To: References: <20260701161721.85681-1-timur.kristof@gmail.com> <2821958.vuYhMxLoTh@timur-max> MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" X-BeenThere: amd-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Discussion list for AMD gfx List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: amd-gfx-bounces@lists.freedesktop.org Sender: "amd-gfx" On Thursday, July 2, 2026 2:02:50=E2=80=AFPM Central European Summer Time C= hristian=20 K=C3=B6nig wrote: > On 7/2/26 11:14, Timur Krist=C3=B3f wrote: > > On 2026. j=C3=BAlius 2., cs=C3=BCt=C3=B6rt=C3=B6k 10:10:10 k=C3=B6z=C3= =A9p-eur=C3=B3pai ny=C3=A1ri id=C5=91 Christian > > K=C3=B6nig>=20 > > wrote: > >> On 7/1/26 18:17, Timur Krist=C3=B3f wrote: > >>> Enable retry fault interrupts when initializing the GFXHUB > >>> system aperture registers according to whether retrying > >>> page faults is enabled in amdgpu (ie. amdgpu.noretry=3D0). > >>>=20 > >>> Needs to be done for each GFXHUB version at once, > >>> because none of them actually enabled this interrupt. > >>=20 > >> Thinking more about it we are clearly missing something here. The retry > >> fault interrupt itself should be enabled all the time. > >=20 > > Why would it be enabled all the time? > > I haven't seen any retry faults on neither Navi 3 nor Navi 4 without > > enabling the ENABLE_RETRY_FAULT_INTERRUPT bit. >=20 > As far as I understand it the GCVM_L2_PROTECTION_FAULT_CNTL2 is actually a > debug register for the fault behavior of the GC block. After our last conversation I tested this again and I can confirm that I do= NOT=20 get any retry fault interrupts on Navi 3 if I remove the code that enables= =20 this bit. That makes me think this is not enabled by default. > According to the register spec for Navi 44 the ENABLE_RETRY_FAULT_INTERRU= PT > should be default 1 and always be set under normal cricumstances. This is definitely not the case on Navi 31 and also on Strix Halo. I haven't checked on Navi 4x but judging by the fact that the gfxhub_v12_1= =20 code has to enable this bit explicitly, I doubt it would be enabled on Navi= 4x=20 either. > >> IIRC only the RETRY_PERMISSION_OR_INVALID_PAGE_FAULT bit in the > >> VM_CONTEXT0_CNTL register should be set or cleared by the kernel driver > >> or > >> firmware to control if the HW retries the access or not. > >=20 > > That is clearly not the case on GFX12.1 and I haven't seen any indicati= on > > that it would be different on GFX11.x and 12.0 either. >=20 > Mhm, then either the FW or golden register settings for that register is = not > correct. >=20 > That we set ACTIVE_PAGE_MIGRATION_PTE_READ_RETRY to one is rather strange= as > well since we don't use that feature in the Linux driver. >=20 > My suggestion is to always set the ENABLE_RETRY_FAULT_INTERRUPT in > GCVM_L2_PROTECTION_FAULT_CNTL2 no matter what the noretry flag says, but > I'm going to ask Alex and our ROCm people about that again when I have > time. I don't see why we should enable this bit when we don't want to enable retr= y=20 faults. Thanks & best regards, Timur