From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (prime256v1) server-digest SHA256) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id B16D5606A319 for ; Thu, 22 Oct 2026 12:04:00 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key, unprotected) header.d=utexas.edu header.i=@utexas.edu header.a=rsa-sha256 header.s=google header.b=vhDjfD3i Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 770C8112524; Thu, 22 Oct 2026 12:03:55 +0000 (UTC) Received: from mail-oo1-f52.google.com (mail-oo1-f52.google.com [209.85.161.52]) by gabe.freedesktop.org (Postfix) with ESMTPS id 07DC510E0B6 for ; Thu, 22 Oct 2026 02:28:11 +0000 (UTC) Received: by mail-oo1-f52.google.com with SMTP id 006d021491bc7-704597ef1d8so612768eaf.3 for ; Wed, 21 Oct 2026 19:28:11 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=utexas.edu; s=google; t=1792636091; x=1793240891; darn=lists.freedesktop.org; h=mime-version:content-transfer-encoding:content-type:references :in-reply-to:cc:date:subject:to:from:message-id:from:to:cc:subject :date:message-id:reply-to:content-type; bh=xruEMXmxKsYyy3/7Uv5aUsYVZ6xRBTshqU8cnD7X6m8=; b=vhDjfD3iElhly3hWPPl+XJWyPkfzarNKzuDZJstiR4az/d4xJI9wscSrt5GpUsjkIt t17sSteBRk5RWIF7wbmLEXLgj0s+HA7VQYORZojFn30RKLPVfddylWcCFGlEOW30yKCZ e34BPAYDdFPvgfM+tjbGVNLCbN7g7+HKfyvhFAKtEJjxmO/skulx6+aiaYrlqtUSnNL9 eDhvSv9+8vPjvNPp5Py7zJ8l62+DJ0cnzzGuaK0JgjMW48fozw1QMzhEloKS7brskJy8 9zyLKf2IFyD7cYjIYVj8frKEG4QE2uYj0tkpn+tZyHwVHwXMOBVYBakl6xp1b8O4t6v6 vdAQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20260707; t=1792636091; x=1793240891; h=mime-version:content-transfer-encoding:content-type:references :in-reply-to:cc:date:subject:to:from:message-id:x-gm-gg :x-gm-message-state:from:to:cc:subject:date:message-id:reply-to :content-type; bh=xruEMXmxKsYyy3/7Uv5aUsYVZ6xRBTshqU8cnD7X6m8=; b=CjR7/ZeAb1uXobpcBYHDMwo71tt1f/X8eSh9e49NyHjCfAG4b5WOPNBMOBrJc4lONn mibmPn+x49/AiWvDWe/FXdzFxph/3RB/7X3Cc66w+CGlDTr74jWvOjiWcqDXUhWg1qPu IerFJUr3upV2OBTtZQK9m5Bz0hzpGHdr+gd1G4Vi+I/a96MUVKvlL76Msn7b6+DzJ8Pa nfmFEPiEHUcWnvp7Y0I+X6QiE8Uv5q+MJAaqwqeCHggrLFGQ8GfzCMy027ZMgVTR6QSs V9BL2xsIyxCh0/UahJLA6n9Iocj8AiKl5ayHE+thFq4ysfl7zu/nmQaE75WZvPsw4GAX FjtA== X-Forwarded-Encrypted: i=1; AKwUvBxyunlX5NMBGy5V0VqX+rR6puG+bg2Wi+0Au54CUroL+pcgzeJPMgfI2l+1b0l3bp5i001CRKj+Hw==@lists.freedesktop.org X-Gm-Message-State: AFq9FYK2Be2q2b4i++HswrqZlXwev7vujpYZFxDX92VGXAuD6MXK5tKE Zw13dWDThPkLL9U5KgEZhO9Q/JOVcfkUO1szl1bnoYRzWoLiq2mUIEycy4BplJanGZE= X-Gm-Gg: AYBFou0T0j3adIRPFdMQi+AjLPV+lAZH6iRNWZ9ttQDSlh9+/8GCKe/GSyQJhBnY52+ ayWddpi8AzSfmVSxlxSEtgWKYnnPbDC18FJyaiHancKit1KrTHF7EpcIgfQQx2MczNzB/EPeTGw ZsSYkOfTSJBItTGSKsrvXbkP5EaBkSbIwOAXII9AyGd3iV7KTHv+QZKn/G+3wPW8uiM/RhzEwEK 1dRG5p3b37ekGrNoYvwPxvNzpq2I3VK6fmhYlP8R0a0AG/G8I+dtyFbyoTxY1eWaeUO5jalwgzR UQ3SO8V1HXwiP9iqYNuegdalC/mtSzZpSXNd4hBEn7IQKBgETgo6yX/A7Ktkf+YsdgiyNVGpOhs kKazoWsZxQONq0o44gticIyQvcXoA7PZHTYBLvS+WUWpL8/QSM+BRm7dBQIVKbdlcbHnHff2g/2 MWFQvRLTU+6jqXH1FvaL971BUAzCWlhj9L7Czj/D4gVDM1VL6Iztn9wUDulffcrC1XHfcdjRk8h 6QCK2p3RtSS+jbTIhvhj6X7WHMwYwl7qlZDY5g4RQb3T+HLICcTGlPcmOMIlJnfiSobLyDil7Cq +L11DU4fv4Hlf7hkPM6bCMM3zeqgQZ/gBPE30B7X9Wd9NLAJokV19t+Jcyn7SV6cFC2K0+Ps3EU QzQwVl1UPK/i3O4gI5mkv1j8xIyYFo+4q2QnUVOUoli9SnEUFtAnrERCW9iqeIb6C+GLvMVA2YW in9OFHQW5Ye+ZEQswvx58= X-Received: by 2002:a05:6820:813:b0:6b7:8396:f3d6 with SMTP id 006d021491bc7-70941fbb729mr2897081eaf.56.1792636090730; Wed, 21 Oct 2026 19:28:10 -0700 (PDT) Received: from 1.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.ip6.arpa ([173.174.112.101]) by smtp.gmail.com with ESMTPSA id 586e51a60fabf-4a7d5eb8fc0sm3431624fac.1.2026.10.21.19.28.09 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Wed, 21 Oct 2026 19:28:10 -0700 (PDT) Message-ID: <6ad974ba.a8122b97.39a7e6.f867@mx.google.com> From: karim.sabar@utexas.edu To: matthew.brost@intel.com Subject: Re: [PATCH] drm/xe: Use kvmalloc for the VMA ops page-table update array Date: Wed, 21 Oct 2026 21:28:08 -0500 Cc: thomas.hellstrom@linux.intel.com, rodrigo.vivi@intel.com, airlied@gmail.com, simona@ffwll.ch, intel-xe@lists.freedesktop.org, dri-devel@lists.freedesktop.org, linux-kernel@vger.kernel.org, stable@vger.kernel.org In-Reply-To: References: Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-Archived-By: MIME-Version: 1.0 X-Mailman-Approved-At: Thu, 22 Oct 2026 12:03:54 +0000 X-BeenThere: intel-xe@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel Xe graphics driver List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "Intel-xe" X-Spam-Status: No, score=-20.8 required=3.0 tests=BAYES_00,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,HEADER_FROM_DIFFERENT_DOMAINS, INCLUDES_CR_TRAILER,INCLUDES_PATCH,MAILING_LIST_MULTI, MENTIONS_GIT_HOSTING,SPF_HELO_NONE,SPF_PASS autolearn=unavailable autolearn_force=no version=4.0.1 X-Spam-Checker-Version: SpamAssassin 4.0.1 (2024-03-26) on aws-us-west-2-korg-listserv-alma10-1 Hey Matthew! Sounds good to me, the fallback of trying to bind the vma one at a time sound= s good to me. And it is actually a bit broader than my patch since it covers = the -ENOBUFS case as well. It should also be easy to get through drm-xe-fixes= and then backported the normal way. I can write it as a v2 & test it on my Panther Lake device, I have a small re= pro that does about 20,000 mappings and fails after suspend (every time witho= ut the fix). If you'd prefer to write it, I can test your patch as well. Thanks, Karim On Wed, 21 Oct 2026 11:57:48 -0700, Matthew Brost wrote: > On Tue, Oct 20, 2026 at 07:08:27PM -0500, karim.sabar@utexas.edu wrote: >> From: Karim Sabar >>=20 > > Thanks for the patch. I do see the problem in the old code. > Unfortunately, we will not be able to pull this into drm-xe-next or > drm-xe-fixes, as 7.3 is already out and 0e33330f1238 is included in our > 7.4 PR. As a result, this would need to go directly to stable. > > There is also a risk that predates the series containing 0e33330f1238. > If the bind has to run on the GPU, you can still get -ENOBUFS later in > the bind pipeline if the bind is too large to fit into the > migration-layer BB. If that occurs, the proper fix may actually be in > xe_vm_validate_rebind(). If xe_vm_rebind() fails with -ENOBUFS or > -ENOMEM, we could call a new function, such as xe_vm_rebind_iterative(), > which would run each VMA requiring a rebind in its own job. This is > effectively what Mesa does in userspace when a bind operation returns > -ENOBUFS. > > We could probably still pull that approach into drm-xe-fixes + have > naturally backport to stable, and it may ultimately be the better > solution. > > Let me know what you think. I can give this an RB, but I'd like to hold > off until we've settled on the solution we want to pursue here. > > Matt > >> Big games die after every s2idle resume on flat-CCS iGPUs. The exec >> ioctl keeps returning -ENOMEM even with 11-16 GB of RAM free. >>=20 >> On suspend xe_bo_evict_all_user() evicts every user BO in XE_PL_TT on >> these parts. On resume the first exec rebinds every VMA in one go and >> xe_vma_ops_alloc() kmallocs one 384-byte op per VMA as a single array. >> Final Fantasy VII Rebirth has about 33,500 VMAs which means a 12.9 MB >> array. It's over the 4 MB KMALLOC_MAX_SIZE and can never succeed. >> __GFP_NOWARN keeps it out of dmesg. >>=20 >> Data from a Panther Lake handheld (SteamOS kernel 7.2.7), kretprobes >> after resume: >> xe_vma_ops_alloc -ENOMEM on 63 of 63 attempts >> xe_vm_rebind -ENOMEM on 63 of 63 attempts >> BO validate, TTM populate, PT prepare never failed >>=20 >> The array is only used by the CPU and doesn't need to be contiguous. >> This switches it to kvmalloc and kvfree. >>=20 >> With the same change applied as a module on that kernel, the game >> survives every sleep I tried with zero ENOMEM. The biggest array was >> 30,753 ops (11.8 MB). >>=20 >> drm-xe-next already does this through commit 0e33330f1238 ("drm/xe: Add >> struct xe_pt_job_ops"), but that's part of a big series that won't go >> to stable. >>=20 >> I tracked this down and tested it on my own device. I used an AI >> assistant to help with the debugging, i.e the kprobe tracing and >> reading through the xe code. I ran every test, picked the fix and >> reviewed the change myself. >>=20 >> What I couldn't do: this is build-tested on drm-xe-fixes but only >> run-tested on the SteamOS 7.2.7 kernel through an equivalent module, >> not on a mainline kernel. >>=20 >> Fixes: 2e524668c440 ("drm/xe: Add xe_vm_pgtable_update_op to xe_vma_ops") >> Cc: stable@vger.kernel.org # v6.11+ >> Assisted-by: Claude:claude-opus-5-5 >> Signed-off-by: Karim Sabar >> --- >> Downstream SteamOS report with the same data: https://github.com/ValveSoft= ware/SteamOS/issues/2962 >> --- >> drivers/gpu/drm/xe/xe_vm.c | 8 ++++---- >> 1 file changed, 4 insertions(+), 4 deletions(-) >>=20 >> diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c >> index 99e42bd29..5caef443b 100644 >> --- a/drivers/gpu/drm/xe/xe_vm.c >> +++ b/drivers/gpu/drm/xe/xe_vm.c >> @@ -703,9 +703,9 @@ static int xe_vma_ops_alloc(struct xe_vma_ops *vops, b= ool array_of_binds) >> continue; >> =20 >> vops->pt_update_ops[i].ops =3D >> - kmalloc_objs(*vops->pt_update_ops[i].ops, >> - vops->pt_update_ops[i].num_ops, >> - GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN); >> + kvmalloc_objs(*vops->pt_update_ops[i].ops, >> + vops->pt_update_ops[i].num_ops, >> + GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN); >> if (!vops->pt_update_ops[i].ops) >> return array_of_binds ? -ENOBUFS : -ENOMEM; >> } >> @@ -742,7 +742,7 @@ static void xe_vma_ops_fini(struct xe_vma_ops *vops) >> xe_vma_svm_prefetch_ops_fini(vops); >> =20 >> for (i =3D 0; i < XE_MAX_TILES_PER_DEVICE; ++i) >> - kfree(vops->pt_update_ops[i].ops); >> + kvfree(vops->pt_update_ops[i].ops); >> } >> =20 >> static void xe_vma_ops_incr_pt_update_ops(struct xe_vma_ops *vops, u8 til= e_mask, int inc_val) >>=20 >> --- >> base-commit: d2ce8fcd778ee6d92748c92d23a56d4416c29d86 >> change-id: 20261020-xe-kvmalloc-vma-ops-2637ebf81cfd >>=20 >> Best regards, >> -- =20 >> Karim Sabar >>