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 lists.ozlabs.org (lists.ozlabs.org [112.213.38.117]) (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 1E1CDD58CB4 for ; Mon, 23 Mar 2026 00:36:42 +0000 (UTC) Received: from boromir.ozlabs.org (localhost [127.0.0.1]) by lists.ozlabs.org (Postfix) with ESMTP id 4ffDkc4pcVz2xls; Mon, 23 Mar 2026 11:36:40 +1100 (AEDT) Authentication-Results: lists.ozlabs.org; arc=none smtp.remote-ip=23.155.224.40 ARC-Seal: i=1; a=rsa-sha256; d=lists.ozlabs.org; s=201707; t=1774226200; cv=none; b=FmCF0KKdWSXbcwtrFNcenZ9oOjGTlda60SnvEr9Iw/kpsyhr2jWeWGTq0lso5ue4WMQM/z+CDmFvVbknk+eo5Nm1vNg0YQSvOBN2QWdBA5DTpGSqyXI5M9AIXZkYB5bfKf+OM5sPOrOA79IAcKyLss2BM7eAiFrtiOd0fa9BndzCkG/ckuZ+CCPc+jttllkvZ2ZadHiWpwOq/ysvxK3aoc48Qy1t96X79PHvFhveAQA5wYkJp7m1jKA5X7lko8RcqTsEKWLPZpJjlScdQ2OvxbSiQEqOtfDZQQ1UmF6KJ5HNpm1n/559jBh7q5+XkGKxN5T7GI/GsbimKi9/PeJVzQ== ARC-Message-Signature: i=1; a=rsa-sha256; d=lists.ozlabs.org; s=201707; t=1774226200; c=relaxed/relaxed; bh=XUNjsJRMkb+HTDokifbsZ9wmoKhH8Iz0vtFPn8y+DV4=; h=Date:From:To:Cc:Message-ID:In-Reply-To:References:Subject: MIME-Version:Content-Type; b=DAmhlyXBb52L+gQmdOeOdxvsBwjy334qz+JXZWhPKgc27hNH08W1gULucCa8MzL+XPdnGBQpcF/OX3mMzsgigtyEta2CNAj0l0ICyzGhqdFikckUR/BmHQdPqLlWsH5qdTu8VBGlL57Fk4YV0jlWy8R8z/OfrshusemnVV+inSpU+i+1EI5pRztmSm0jIVSEWCz2M1mdW6Iuvt2gVzsAfE0QCJNGVbbmHC9HtI2CTQzZfo8Zf0OH98wSyVnPZxGzPL7UfW/eVTpJumRCQ1LJoeVil+081TSFsspaPx5J53ul0GeXZSxff7PtrmcREqhNiFSXWVtN8V9U7lW0zKys4w== ARC-Authentication-Results: i=1; lists.ozlabs.org; dmarc=pass (p=quarantine dis=none) header.from=raptorengineering.com; dkim=pass (1024-bit key; secure) header.d=raptorengineering.com header.i=@raptorengineering.com header.a=rsa-sha256 header.s=B8E824E6-0BE2-11E6-931D-288C65937AAD header.b=ZKV1HFzm; dkim-atps=neutral; spf=pass (client-ip=23.155.224.40; helo=raptorengineering.com; envelope-from=tpearson@raptorengineering.com; receiver=lists.ozlabs.org) smtp.mailfrom=raptorengineering.com Authentication-Results: lists.ozlabs.org; dmarc=pass (p=quarantine dis=none) header.from=raptorengineering.com Authentication-Results: lists.ozlabs.org; dkim=pass (1024-bit key; secure) header.d=raptorengineering.com header.i=@raptorengineering.com header.a=rsa-sha256 header.s=B8E824E6-0BE2-11E6-931D-288C65937AAD header.b=ZKV1HFzm; dkim-atps=neutral Authentication-Results: lists.ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=raptorengineering.com (client-ip=23.155.224.40; helo=raptorengineering.com; envelope-from=tpearson@raptorengineering.com; receiver=lists.ozlabs.org) X-Greylist: delayed 384 seconds by postgrey-1.37 at boromir; Mon, 23 Mar 2026 11:36:37 AEDT Received: from raptorengineering.com (mail.raptorengineering.com [23.155.224.40]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 4ffDkY1BZcz2xd6 for ; Mon, 23 Mar 2026 11:36:37 +1100 (AEDT) Received: from localhost (localhost [127.0.0.1]) by mail.rptsys.com (Postfix) with ESMTP id D96217791C2D; Sun, 22 Mar 2026 19:30:08 -0500 (CDT) Received: from mail.rptsys.com ([127.0.0.1]) by localhost (vali.starlink.edu [127.0.0.1]) (amavisd-new, port 10032) with ESMTP id A-akTtLceq3C; Sun, 22 Mar 2026 19:30:04 -0500 (CDT) Received: from localhost (localhost [127.0.0.1]) by mail.rptsys.com (Postfix) with ESMTP id AE3FC77908D9; Sun, 22 Mar 2026 19:30:04 -0500 (CDT) DKIM-Filter: OpenDKIM Filter v2.10.3 mail.rptsys.com AE3FC77908D9 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=raptorengineering.com; s=B8E824E6-0BE2-11E6-931D-288C65937AAD; t=1774225804; bh=XUNjsJRMkb+HTDokifbsZ9wmoKhH8Iz0vtFPn8y+DV4=; h=Date:From:To:Message-ID:MIME-Version; b=ZKV1HFzmEvDGTobM3UaLN/g+35d0v8QcEGLuYq4dzqkodwkfpVNG6iGZRzaqJFUlN ULLKzY/pPRNHWSAtVoAuwNXehuRtv8vAPjcToBSDBOOTlb1aeQzGkigJFnCpC3bfIo 4MNM1WcPvIyar+DdSwXucIz7HSfXXxJ7UtrDncXU= X-Virus-Scanned: amavisd-new at rptsys.com Received: from mail.rptsys.com ([127.0.0.1]) by localhost (vali.starlink.edu [127.0.0.1]) (amavisd-new, port 10026) with ESMTP id C-xwQSM_Itd6; Sun, 22 Mar 2026 19:30:04 -0500 (CDT) Received: from vali.starlink.edu (localhost [127.0.0.1]) by mail.rptsys.com (Postfix) with ESMTP id 657787790EC7; Sun, 22 Mar 2026 19:30:04 -0500 (CDT) Date: Sun, 22 Mar 2026 19:30:04 -0500 (CDT) From: Timothy Pearson To: Ritesh Harjani Cc: Dan =?utf-8?Q?Hor=C3=A1k?= , linuxppc-dev , Gaurav Batra , amd-gfx , Donet Tom Message-ID: <1646525566.315562.1774225804200.JavaMail.zimbra@raptorengineeringinc.com> In-Reply-To: <1phlu3bs.ritesh.list@gmail.com> References: <20260313142351.609bc4c3efe1184f64ca5f44@danny.cz> <1phlu3bs.ritesh.list@gmail.com> Subject: Re: amdgpu driver fails to initialize on ppc64le in 7.0-rc1 and newer X-Mailing-List: linuxppc-dev@lists.ozlabs.org List-Id: List-Help: List-Owner: List-Post: List-Archive: , List-Subscribe: , , List-Unsubscribe: Precedence: list MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-Mailer: Zimbra 8.5.0_GA_3042 (ZimbraWebClient - GC145 (Linux)/8.5.0_GA_3042) Thread-Topic: amdgpu driver fails to initialize on ppc64le in 7.0-rc1 and newer Thread-Index: kp4EDOKqz4Lv02hEmHAiKBZnOTq8kA== ----- Original Message ----- > From: "Ritesh Harjani" > To: "Dan Hor=C3=A1k" , "linuxppc-dev" , "Gaurav Batra" > Cc: "amd-gfx" , "Donet Tom" > Sent: Saturday, March 14, 2026 11:25:11 PM > Subject: Re: amdgpu driver fails to initialize on ppc64le in 7.0-rc1 and = newer > Dan Hor=C3=A1k writes: >=20 > +cc Gaurav, >=20 >> Hi, >> >> starting with 7.0-rc1 (meaning 6.19 is OK) the amdgpu driver fails to >> initialize on my Linux/ppc64le Power9 based system (with Radeon Pro WX41= 00) >> with the following in the log >> >> ... >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: GART: 2= 56M >> 0x000000FF00000000 - 0x000000FF0FFFFFFF >=20 > ^^^^ > So looks like this is a PowerNV (Power9) machine. >=20 >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: [drm] D= etected VRAM >> RAM=3D4096M, BAR=3D4096M >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: [drm] R= AM width >> 128bits GDDR5 >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: iommu: = 64-bit OK but >> direct DMA is limited by 0 >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: >> dma_iommu_get_required_mask: returning bypass mask 0xfffffffffffffff >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: 4096M = of VRAM >> memory ready >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: 32570M= of GTT >> memory ready. >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: (-12) f= ailed to >> allocate kernel bo >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: [drm] D= ebug VRAM >> access will use slowpath MM access >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: [drm] G= ART: num cpu >> pages 4096, num gpu pages 65536 >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: [drm] P= CIE GART of >> 256M enabled (table at 0x000000F4FFF80000). >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: (-12) f= ailed to >> allocate kernel bo >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: (-12) c= reate WB bo >> failed >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: >> amdgpu_device_wb_init failed -12 >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: >> amdgpu_device_ip_init failed >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: Fatal e= rror during >> GPU init >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: finishi= ng device. >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: probe w= ith driver >> amdgpu failed with error -12 >> b=C5=99e 05 08:35:40 talos.danny.cz kernel: amdgpu 0000:01:00.0: ttm fi= nalized >> ... >> >> After some hints from Alex and bisecting and other investigation I have >> found that >> https://github.com/torvalds/linux/commit/1471c517cf7dae1a6342fb821d8ed50= 1af956dd0 >> is the culprit and reverting it makes amdgpu load (and work) again. >=20 > Thanks for confirming this. Yes, this was recently added [1] >=20 > [1]: > https://lore.kernel.org/linuxppc-dev/20251107161105.85999-1-gbatra@linux.= ibm.com/ As this patch appears to be primarily aimed at improving performance, and h= as introduced a serious regression into the kernel for a large number of ac= tive users of the PowerNV platform, I would kindly ask that it be reverted = until it can be reworked not to break PowerNV support. Bear in mind there = are other devices that are 40 bit DMA limited, and they are also likely to = break on Linux 7.0. Thank you!