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 AC5A1CA5FDD for ; Fri, 2 Oct 2026 12:43:10 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 4E9C310E54A; Fri, 2 Oct 2026 12:43:10 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=intel.com header.i=@intel.com header.b="B+IWiwYG"; dkim-atps=neutral Received: from mgamail.intel.com (mgamail.intel.com [192.198.163.19]) by gabe.freedesktop.org (Postfix) with ESMTPS id 8919B10E54A for ; Fri, 2 Oct 2026 12:43:09 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1790944990; x=1822480990; h=message-id:subject:from:to:cc:date:in-reply-to: references:content-transfer-encoding:mime-version; bh=pV17yDyLayBJaMKeWhYnaloOLDaj3BpYKbKQGWgLUMQ=; b=B+IWiwYGUmjQcW/w+IxhcIyyVcLfW5XIjdIMPKlR4Y5oc0u/3lzRAG3P aZ57DnIMwqRBcz1vK1M5EpT8CufGCbNYNDScrflKaObU3xg9S5+20x7Vs YLwJfpZ2daYJ0kPxZL5xy7oJTKZ1yiWMGkCeuUZ0AknRKhD/MHaERh20A AjLwrFIVPT0/WwZ5/6x8WDiXhpGlmmQ6FPJt206+kq31IbhmSCHg8iAUR VxbdThI9E3BhLpGSmePe5B47fa8NRQivGW6KIu2Mgvd5gKeEDxV7erJtA AB7MDUCk7LwOJgTJ3Rk5tNe1mZtZ21omtqlPlWjxH8C+j1PNW5dhn8LFo Q==; X-CSE-ConnectionGUID: Ms8MnT+8Sb2GNoB+uze+oQ== X-CSE-MsgGUID: hvRNMkBIRmG6MOmKGd//WA== X-IronPort-AV: E=McAfee;i="6800,10657,11922"; a="90609767" X-IronPort-AV: E=Sophos;i="6.27,136,1787036400"; d="scan'208";a="90609767" Received: from fmviesa010.fm.intel.com ([10.60.135.150]) by fmvoesa113.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 02 Oct 2026 05:43:09 -0700 X-CSE-ConnectionGUID: TNIYoNU5Q66S72FzQPFDpw== X-CSE-MsgGUID: zq69cSJfThuZzr5gvwIYTA== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.27,136,1787036400"; d="scan'208";a="275434223" Received: from hrotuna-mobl2.ger.corp.intel.com (HELO [10.245.244.200]) ([10.245.244.200]) by fmviesa010-auth.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 02 Oct 2026 05:43:08 -0700 Message-ID: <92619c231f212306eb1c0c274b69c47687696159.camel@linux.intel.com> Subject: Re: [PATCH 2/2] drm/xe/vm: make PREFETCH to TT sticky From: Thomas =?ISO-8859-1?Q?Hellstr=F6m?= To: Matthew Auld , intel-xe@lists.freedesktop.org Cc: Matthew Brost , stable@vger.kernel.org Date: Fri, 02 Oct 2026 14:43:05 +0200 In-Reply-To: <20260928164820.1237049-6-matthew.auld@intel.com> References: <20260928164820.1237049-4-matthew.auld@intel.com> <20260928164820.1237049-6-matthew.auld@intel.com> Organization: Intel Sweden AB, Registration Number: 556189-6027 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable User-Agent: Evolution 3.58.3 (3.58.3-2.fc43) MIME-Version: 1.0 X-BeenThere: intel-xe@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel Xe graphics driver List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: intel-xe-bounces@lists.freedesktop.org Sender: "Intel-xe" On Mon, 2026-09-28 at 17:48 +0100, Matthew Auld wrote: > When userspace explicitly requests DRM_XE_VM_BIND_OP_PREFETCH to > system > memory (XE_PL_TT), xe_bo_migrate() moves the buffer object to TT. > However, because XE_PL_TT is marked with TTM_PL_FLAG_FALLBACK in the > buffer's default placement (introduced in commit 5c87fee3c96c > ("drm/xe: > Attempt to bring bos back to VRAM after eviction")), any subsequent > validation during exec immediately migrates the buffer back to VRAM, > completely undoing the userspace prefetch request. >=20 > Use xe_bo_migrate_tt_sticky() when prefetching to XE_PL_TT so that > the > buffer remains resident in system memory across subsequent > validations. >=20 > Assisted-by: LLM > Reported-by: Thomas Hellstr=C3=B6m > Fixes: 5c87fee3c96c ("drm/xe: Attempt to bring bos back to VRAM after > eviction") > Signed-off-by: Matthew Auld > Cc: Matthew Brost > Cc: # v6.12+ I think we need somewhere to clear this stickiness. Perhaps if xe_bo_migrate() is called with another destination than the sticky one, we'd clear it? Thanks, Thomas > --- > =C2=A0drivers/gpu/drm/xe/xe_vm.c | 5 ++++- > =C2=A01 file changed, 4 insertions(+), 1 deletion(-) >=20 > diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c > index 425c678f4480..2068e0cf50ff 100644 > --- a/drivers/gpu/drm/xe/xe_vm.c > +++ b/drivers/gpu/drm/xe/xe_vm.c > @@ -3406,7 +3406,10 @@ static int op_lock_and_prep(struct drm_exec > *exec, struct xe_vm *vm, > =C2=A0 mem_type =3D > region_to_mem_type[region]; > =C2=A0 } > =C2=A0 > - err =3D xe_bo_migrate(bo, mem_type, NULL, > exec); > + if (mem_type =3D=3D XE_PL_TT) > + err =3D xe_bo_migrate_tt_sticky(bo, > NULL, exec); > + else > + err =3D xe_bo_migrate(bo, mem_type, > NULL, exec); > =C2=A0 } > =C2=A0 break; > =C2=A0 }