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 EF0F6C5DF8E for ; Fri, 21 Aug 2026 20:07:50 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 8813F10F3BA; Fri, 21 Aug 2026 20:07:50 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=intel.com header.i=@intel.com header.b="Rsqf1W11"; dkim-atps=neutral Received: from mgamail.intel.com (mgamail.intel.com [198.175.65.18]) by gabe.freedesktop.org (Postfix) with ESMTPS id D9AE410E34F for ; Fri, 21 Aug 2026 20:07:37 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1787342858; x=1818878858; h=from:to:subject:date:message-id:mime-version: content-transfer-encoding; bh=m4JMcWtUGsjAmrvoFe0gDNWF/bZx1VgBl/V1YYcr+6k=; b=Rsqf1W11wTnmCJdlF2/1LeA8Fx6DYiuUw8jyZZ5Z1XbdM5OPSMM87Fqk c1ZjcgBcYbCm3hzGlcYtUninHsk5vC8xz47g8eJBzfizIwJBxBWo2gFUY 3Zg0EJxhWLxCpWVCFIqix3RBqXn1sKDHbu2kB+MgQjBkoVXPrGU5boJEE r5h2xhJy2fb7Mv/pSovIxi9HJK9+ewKnmMQVGUAoiZPn2bnNXbQGzC61O x80MyNn9FH5toS2YkVdm8zOdxByEzrbVai40odhgNmfoaNmQFlLaUAN+X oEDlhROldU98b6C4jmpunInIQP7yJB3xNkE0qfaqpm4NgU9VlDIn4qPJh w==; X-CSE-ConnectionGUID: FLh9TV0jRBuMlt2OVpve8g== X-CSE-MsgGUID: IPUEEeJcTT2UecSq6sD24w== X-IronPort-AV: E=McAfee;i="6800,10657,11882"; a="87957213" X-IronPort-AV: E=Sophos;i="6.25,235,1779174000"; d="scan'208";a="87957213" Received: from orviesa007.jf.intel.com ([10.64.159.147]) by orvoesa110.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 21 Aug 2026 13:07:37 -0700 X-CSE-ConnectionGUID: 6MFasjL9Q3G5lHwfGjNBiA== X-CSE-MsgGUID: ir1+mWSMQa6pyufVQ+QQtw== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.25,235,1779174000"; d="scan'208";a="266491041" Received: from orsosgc001.jf.intel.com ([10.88.27.185]) by orviesa007-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 21 Aug 2026 13:07:38 -0700 From: Umesh Nerlige Ramappa To: intel-xe@lists.freedesktop.org, Ashutosh Dixit Subject: [PATCH 0/3] Modify the SW tail logic in OA Date: Fri, 21 Aug 2026 13:07:29 -0700 Message-ID: <20260821200728.1048699-5-umesh.nerlige.ramappa@intel.com> X-Mailer: git-send-email 2.51.0 MIME-Version: 1.0 Content-Transfer-Encoding: 8bit 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" OA unit updates the HW TAIL register to indicate that a new report is available, although it does not guarantee that the report is visible in memory. Also the currently running workload contributes to some latency in seeing this report in memory. In the past we would set some fields in the OA report and check if the fields are populated to non-zero values by the HW, but this is no longer sufficient since some parts of the report may land out of order under heavy workloads. Drop this WA and add a new logic that just waits for a fixed number of HW TAIL report increments before returning data to the user. User will always see the reports lagging by this fixed number, however we do not have realtime use cases for OAG since OAG reports are mainly post processed. v2: Rebase v3: Add Sashiko's review comments v4: Rebase, checkpatch fixes v5: Add Ashutosh's review comments Signed-off-by: Umesh Nerlige Ramappa Umesh Nerlige Ramappa (3): drm/xe/xe_oa: Clear status only if relevant bits are set drm/xe/xe_oa: Avoid checking and setting fields in the OA report drm/xe/xe_oa: Add a lag to the reports that is exported to user drivers/gpu/drm/xe/xe_oa.c | 99 ++++++-------------------------------- 1 file changed, 16 insertions(+), 83 deletions(-) -- 2.51.0