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 9AEB9CA5FA5 for ; Tue, 29 Sep 2026 20:20:06 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 1AA2710F0AB; Tue, 29 Sep 2026 20:20:06 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=kernel.org header.i=@kernel.org header.b="gIRpABkW"; dkim-atps=neutral Received: from sea.source.kernel.org (sea.source.kernel.org [172.234.252.31]) by gabe.freedesktop.org (Postfix) with ESMTPS id CA7AF10F0AB for ; Tue, 29 Sep 2026 20:20:04 +0000 (UTC) Received: from smtp.kernel.org (quasi.space.kernel.org [100.103.45.18]) by sea.source.kernel.org (Postfix) with ESMTP id 81A0040DDF; Tue, 29 Sep 2026 20:20:04 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id 43DF51F000FF; Tue, 29 Sep 2026 20:20:04 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=kernel.org; s=k20260515; t=1790713204; bh=/Uo6Gh8i2wlXIErUANgf6BrNPyO97DrpfrTQi6V2F+I=; h=From:Subject:Reply-To:To:Cc:In-Reply-To:References:Date; b=gIRpABkWO38QUU+cm7eA6Ilkz/iI8s9m1m6EOMZzR2EDqreCOkEpYlV3P0PkhoRu1 h/I4Fpq2F8RgaLnDJMA0FxFCWZdt4h8xeP3INiYFWSuPBepLgHZAcq0MS7AW9JYROY P5Uy2KGwTqB8NbdcxraDL2NgYoFIXBIkg+DuclIOZWsRmZ2cJ8hVWcxkiyppIf3zPW 7lKDliP6vQEiYsRO2FnghScYt/hm9JhTE/XHJmAqsOnQUYl2tq6Pe2DKxN9rFNev2m SAKaG2p/x+UciDFwU603ZrkHT9y4Ch5zn/ZdaAF9TlJ/y736mwmzwc52p8k25b56Rj vRpDIpIuSPRVw== From: sashiko-bot@kernel.org Subject: Re: [PATCH] drm/xe/xe3p: Force non-compressible memory reads to 256B overfetches To: "Daniel Charles" Cc: intel-xe@lists.freedesktop.org In-Reply-To: <20260929200839.843116-1-daniel.charles@intel.com> References: <20260929200839.843116-1-daniel.charles@intel.com> Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Date: Tue, 29 Sep 2026 20:20:03 +0000 Message-Id: <20260929202004.43DF51F000FF@smtp.kernel.org> 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: , Reply-To: sashiko-reviews@lists.linux.dev Errors-To: intel-xe-bounces@lists.freedesktop.org Sender: "Intel-xe" Thank you for your contribution! Sashiko AI review found 1 potential issue(= s) to consider: - [Medium] drm/xe: missing media GT tuning for NONCOMPMEMRD256BOVRFETCHEN -- commit 0d0918701116e6b353267a1af32ce09421b27bbd Author: Daniel Charles drm/xe/xe3p: Force non-compressible memory reads to 256B overfetches This commit adds a tuning entry to set bit 14 (NONCOMPMEMRD256BOVRFETCHEN) of L3SQCREG2 for Xe3p and later platforms to force non-compressible memory reads to 256B overfetches. > diff --git a/drivers/gpu/drm/xe/xe_tuning.c b/drivers/gpu/drm/xe/xe_tunin= g.c > index bcec40ca2d35f..a9bd3f8969a54 100644 > --- a/drivers/gpu/drm/xe/xe_tuning.c > +++ b/drivers/gpu/drm/xe/xe_tuning.c [ ... ] > @@ -100,6 +100,10 @@ VISIBLE_IF_KUNIT const struct xe_rtp_table_sr gt_tun= ings =3D XE_RTP_TABLE_SR( > XE_RTP_ACTIONS(FIELD_SET(GAMSTLB_CTRL, BANK_HASH_MODE, > BANK_HASH_4KB_MODE)) > }, > + { XE_RTP_NAME("Tuning: Force All Non-Compressible Memory Reads to be 25= 6B Overfetches"), > + XE_RTP_RULES(GRAPHICS_VERSION_RANGE(3510, XE_RTP_END_VERSION_UNDEFINE= D)), > + XE_RTP_ACTIONS(SET(L3SQCREG2, NONCOMPMEMRD256BOVRFETCHEN)) > + }, [Severity: Medium] Should this tuning also be applied to the standalone Media GT? Since this rule uses GRAPHICS_VERSION_RANGE(), it evaluates to false for standalone Media GTs when checked in xe_rtp_match_graphics_version_range(). Xe3p platforms feature a standalone Media GT with its own L3 cache controll= ed by XE2LPM_L3SQCREG2. Previous overfetch tunings for the same cache (such as COMPMEMRD256BOVRFETCHEN) provided a companion rule using MEDIA_VERSION_RANG= E. Is there a similar configuration needed here to optimize non-compressible memory reads for the Media GT L3 cache? > ); > EXPORT_SYMBOL_IF_KUNIT(gt_tunings); --=20 Sashiko AI review =C2=B7 https://sashiko.dev/#/patchset/20260929200839.8431= 16-1-daniel.charles@intel.com?part=3D1