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 109DEC87FDA for ; Fri, 8 Aug 2025 19:08:10 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id BC60E10E978; Fri, 8 Aug 2025 19:08:10 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=intel.com header.i=@intel.com header.b="ZOa2sYVK"; dkim-atps=neutral Received: from mgamail.intel.com (mgamail.intel.com [192.198.163.19]) by gabe.freedesktop.org (Postfix) with ESMTPS id 8658110E975 for ; Fri, 8 Aug 2025 19:08:09 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1754680089; x=1786216089; h=date:from:to:cc:subject:message-id:references: content-transfer-encoding:in-reply-to:mime-version; bh=+8GKzvIOfwh3RinCPHnqsyxMHwt2NOrtAKQ8xiI36PY=; b=ZOa2sYVKHlJNP/n65a/Yx3TNmjznJ9Im+paxNJidQhZ2Q8TVGZdgySxQ YqzWx+KS+GyQdTjhJrvEGW2IlyltJPD3+GxIw+wXQMGhP8Ao79CeQLCK2 TkX4JJINWddaXik5psiOY2lwLwb8KpF5H5TR7WKiaY8oWn7XRdHXJyMJl NhTTG9UxSfjT4jv8W/gjeDFQoHxrpZS8oHcodUkkZlIUkZGRiJGkHMXmu 2D8Jt34PUuG54UsaZSz5NEx+NHDGeYEzViTlQlJiMwHluDauaUsBf75Gw IWrPuUj0/yj56ZScha+MnQd0IEvOKpHdA8t63X4b1bzUUq2WfNMnwgkNk w==; X-CSE-ConnectionGUID: kQvcXU+SRNuYbUo1VzJJ0g== X-CSE-MsgGUID: uoL0z68VTT2VFC1kxJkpYQ== X-IronPort-AV: E=McAfee;i="6800,10657,11515"; a="56069532" X-IronPort-AV: E=Sophos;i="6.17,274,1747724400"; d="scan'208";a="56069532" Received: from fmviesa005.fm.intel.com ([10.60.135.145]) by fmvoesa113.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 08 Aug 2025 12:08:09 -0700 X-CSE-ConnectionGUID: 4e7xmLLaTnKrIX6ilMXijA== X-CSE-MsgGUID: rQhyxSz3TFCFI0SvwGNPsA== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.17,274,1747724400"; d="scan'208";a="169625309" Received: from fmsmsx901.amr.corp.intel.com ([10.18.126.90]) by fmviesa005.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 08 Aug 2025 12:08:09 -0700 Received: from FMSMSX902.amr.corp.intel.com (10.18.126.91) by fmsmsx901.amr.corp.intel.com (10.18.126.90) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.2.1748.26; Fri, 8 Aug 2025 12:08:08 -0700 Received: from fmsedg903.ED.cps.intel.com (10.1.192.145) by FMSMSX902.amr.corp.intel.com (10.18.126.91) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.2.1748.26 via Frontend Transport; Fri, 8 Aug 2025 12:08:08 -0700 Received: from NAM12-DM6-obe.outbound.protection.outlook.com (40.107.243.83) by edgegateway.intel.com (192.55.55.83) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.2.1748.26; Fri, 8 Aug 2025 12:08:08 -0700 ARC-Seal: i=1; a=rsa-sha256; s=arcselector10001; d=microsoft.com; cv=none; b=XLmcRb4VrPaDE4/RiMAeSOKLGCqA2qZPZ6BcDoidNWPXRgKxK8KlAluJyGjbtJ/ha6dvNXPR55KJzkHAVo2ih/B+ltwKcjP6K2YkR/xYigMg+fLtkwPFVw0W5DqYytHUcsyHZrf2n62/uMUV5aR/KD/1S+MnwAeEvuxreo9Z3wR6M8liUozelpr0HcwyMDsAUP9vi++3bFpn88Oo4B+pwLt1zk2ela2SbW2mKcchNQNJ/NS5xCIN5a7bsyu3ts4QDs+j4KwWX0UYdRgZZIHwFFP1zZGtftql+YTioC9R5B36Eg1SfmIMZbJKO81nN6r4/YYUid4wG+zKGpKs8lxRTQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector10001; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-AntiSpam-MessageData-ChunkCount:X-MS-Exchange-AntiSpam-MessageData-0:X-MS-Exchange-AntiSpam-MessageData-1; bh=h8pU5ggevSVOqOoFQ8ysozqYS8EHa2xSTn9cQjbSyE0=; b=bDQ/P4T8kXC5QPjnFFub7DrWwD7Cwu9zcECPH19XMTxgX0c4Ahnjor4+tpGfom7Wk4uMJgIVxsD1xkbDe1sUtp3Kz/oIqfugpyfzJTNhhtcj4bpEpJYpF80tBgG/T89cYc9MhKXN+/XLXB+O10hfQXR22YLBLTrbZY9snAFpaJ393AYjmLPHZouiJFQDgNH9Q0I5mG/P2FBAtXf3bX3jNTxmNqMLk8m6eQXqNAnYvfOvS+IJw/4TeuGXYVTKwDA19bvJ2K9U+DH5hPeWyNgPQrX2ftBnJ4RoaeRZ8097cH8DDO0PuC7dYOl/4HH+lPA/Xw6aIEcO209WbC+e1BrqLQ== ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=intel.com; dmarc=pass action=none header.from=intel.com; dkim=pass header.d=intel.com; arc=none Authentication-Results: dkim=none (message not signed) header.d=none;dmarc=none action=none header.from=intel.com; Received: from BL3PR11MB6508.namprd11.prod.outlook.com (2603:10b6:208:38f::5) by SN7PR11MB6922.namprd11.prod.outlook.com (2603:10b6:806:2a9::9) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.9009.15; Fri, 8 Aug 2025 19:08:06 +0000 Received: from BL3PR11MB6508.namprd11.prod.outlook.com ([fe80::1a0f:84e3:d6cd:e51]) by BL3PR11MB6508.namprd11.prod.outlook.com ([fe80::1a0f:84e3:d6cd:e51%4]) with mapi id 15.20.9009.017; Fri, 8 Aug 2025 19:08:06 +0000 Date: Fri, 8 Aug 2025 12:07:51 -0700 From: Matthew Brost To: S Sebinraj CC: , Subject: Re: [PATCH] drm/xe: GPU frequency tracing support Message-ID: References: <20250808161920.3542415-1-s.sebinraj@intel.com> Content-Type: text/plain; charset="iso-8859-1" Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <20250808161920.3542415-1-s.sebinraj@intel.com> X-ClientProxiedBy: MW4P223CA0025.NAMP223.PROD.OUTLOOK.COM (2603:10b6:303:80::30) To BL3PR11MB6508.namprd11.prod.outlook.com (2603:10b6:208:38f::5) MIME-Version: 1.0 X-MS-PublicTrafficType: Email X-MS-TrafficTypeDiagnostic: BL3PR11MB6508:EE_|SN7PR11MB6922:EE_ X-MS-Office365-Filtering-Correlation-Id: 36c39cf0-11d3-459b-5043-08ddd6aee82a X-MS-Exchange-SenderADCheck: 1 X-MS-Exchange-AntiSpam-Relay: 0 X-Microsoft-Antispam: BCL:0;ARA:13230040|366016|1800799024|376014; X-Microsoft-Antispam-Message-Info: =?iso-8859-1?Q?iJvrK8tmQe04zZkq8XWS+WZJiEpioVBKUjwZkN5lJOiQzrOQG76i6JuRuV?= =?iso-8859-1?Q?Wuf6efI/z3adbqgb6AIQ30tB2kS5InnV+5Ls1VNhE8KQiVqC4y0JWzfU0w?= =?iso-8859-1?Q?fNeYX/v2YEvbNVjFM14tuW4QI6ry4qAEXy4GkYb9sU35HAPg+qhi/qYYtG?= =?iso-8859-1?Q?VS9/W2cpq5uIhM9Qm1+1eEyBf6cKbuMCuBR8yUodRlLM9+S88cFyzrFmV0?= =?iso-8859-1?Q?uTSN1OBhz+x+75KQvD+aPXQiO3tWv95QBvuFvxhiEWAhgDqJVmKGveNtAA?= =?iso-8859-1?Q?utrFgCPjBSw4eU0ehxipteS5qYCezzMj5QumY4RxvBa6WGiAZ63Ye0ZVPz?= =?iso-8859-1?Q?qlMVAwnIlHJ3xjWrPsLRIxbIj64xbtmf7ahzkrrb6In12hWFHhVmHK9ZfW?= =?iso-8859-1?Q?ffmK67j/5NPqOW0wLEzyXBPgdtnqJGXXmhenlER8FfhaYvSSpU77MigXpm?= =?iso-8859-1?Q?ym4+4ma8tRPoNO1ubT0Of4iqyCz3yu03aG9DT7ny6XUc2KSnZp8gIu8c/6?= =?iso-8859-1?Q?rYiLv3hfYB+1aLECDEgm9vgYFqcfcssdZeX0+etY5dpY9eH/LKFBYuh8kn?= =?iso-8859-1?Q?bYAHmq9f7/zO9eGCKKjYoQ+MInjj0N5UsEDpIW06wROzV2/irBRkJRp8fV?= =?iso-8859-1?Q?03h6V6vv9ucy/dwaLwn1Drz9Qg/wUdyNoaBPXH4DI9TBEmhyIytu5ozg02?= =?iso-8859-1?Q?4ZmFKlWzi0/EVfSpoGeKOadMelqxYzjshXQfPpjiQiWkmpMMjcNKgBQmIK?= =?iso-8859-1?Q?XdCYVcz8nVzqmu96L/FHoENo+JCjS3hsHMBq719eLZuKaye5QNd0RUX872?= =?iso-8859-1?Q?ykB1svlKrBht9DZ8nSUdbn+bmk/3tSEpprjv4zLJjM6bFNNCQFBGFjG3V9?= =?iso-8859-1?Q?CzF0mMgJIUMvY+w6pu/I1JqNtvUlKma6z3i0N1Rcd2QYqaE8JiPSj/DfoE?= =?iso-8859-1?Q?5EzxjreXpm+siRj0iVVy38DkmFcZeIDx0DxZlQV996dirpCL83amX9tHx7?= =?iso-8859-1?Q?c1FvE9LpZEiVV9xCinJn5Quau6fiNzpVFpIq9NpI0xetvttm29wCSjAXwg?= =?iso-8859-1?Q?3fKIqwhK+y5rh5m8Scb9EE/qQErG4y5IEYuACNUi0bC6JYF72CU6C4Gsbq?= =?iso-8859-1?Q?vk7QYpgCq2XvPLdrQ+OPUBaD5bL78x0lxv5X2gs4qCOws5QYHFxlrtFOHG?= =?iso-8859-1?Q?wzCOiyrUL+s5h/dStD6FlfcupfEIyEuRrjquY3EcYAW3e7JUcCA0ioAJZT?= =?iso-8859-1?Q?roOxAtaSwhPub8Ui36XDH+gBTBTT2XAL0A2HN6WrIRDxZJIQ/8dyR4Lqxu?= =?iso-8859-1?Q?pR2OcqHDYrGcpvTMmH/XVwXeqYpd5Lx4lIQHLW3bV9Hi1q0zbYaMIF/C21?= =?iso-8859-1?Q?BQSzhdZFmD8QhuvhoKvPUxheXU0dr6zO5M2tI2DQkvRqlYLUAy3D7LDh7x?= =?iso-8859-1?Q?HPZazNPtdEgsiLkjEFGN0P5QNcSXjXeDS8ddzD00fFVQ8na/+z/E5OsduJ?= =?iso-8859-1?Q?k=3D?= X-Forefront-Antispam-Report: CIP:255.255.255.255; CTRY:; LANG:en; SCL:1; SRV:; IPV:NLI; SFV:NSPM; H:BL3PR11MB6508.namprd11.prod.outlook.com; PTR:; CAT:NONE; SFS:(13230040)(366016)(1800799024)(376014); DIR:OUT; SFP:1101; X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1 X-MS-Exchange-AntiSpam-MessageData-0: =?iso-8859-1?Q?mpBaP+s4an++h8Ys2yDGKgrZeDMkCSIn8x5KBGlG8ZYljglID1Ghoj6EOB?= =?iso-8859-1?Q?FS1Ncea9FIU5FmReBO1X0iLIp39Juv3zau6Qu9en4lG+lgdZDCAaOXOI2X?= =?iso-8859-1?Q?WBN2y4iehLf+8o6TcnMZ6Ozz+1TLY8hO4WzugLLxB6zb1QENnBen6CBoCR?= =?iso-8859-1?Q?2bMeQweQJ1z9xsNsC5kJsbMCYufFDjtBPl8XjtV1m3+91oknOcQwnrKP8L?= =?iso-8859-1?Q?M8QMzWTFgioTQji2F+b8f1ZJFLe+eohRwACZD39RdeQe5Y7Qcp+R3NDush?= =?iso-8859-1?Q?gPS+lqqFXUtVhd9yRLm5y9VeuiOH4oY5xdqsPOknSII+zYwT2v1ZXO/ZXR?= =?iso-8859-1?Q?K8jMeUbntLRF+wfoHDZInUOb7iZiNYNQI8Q4O52REOlTI6HkkZKrQOEVG0?= =?iso-8859-1?Q?vVTBl+CH2v0BRq3a/dbWlio9PZ9NFFq2iAkMN8aI1HqYU2Dkr9hI6O76Z2?= =?iso-8859-1?Q?4lI3Tb5v2EMltxDvzJybzTtOn9I+DqcmwgL+ZiOjl+Kixy1Nml98HxUKbU?= =?iso-8859-1?Q?IMhr4t2/8MlzkkFfDP6uE8AyG3fRp86qa4G3YP6MTcXnN353/nrmMtIrrx?= =?iso-8859-1?Q?f/LqL4BfpH3G9vuxcFJhlrVXBxf+h0oJUG5QWOe1Jm/YqdwAlt2XM31lnp?= =?iso-8859-1?Q?vX7wvVE2KK9WfGayhQ6gov4Nog/2iRe5ANUKEmK1V5C5k8LfWlvgXNP8YH?= =?iso-8859-1?Q?qg9ZAU6e4tw1JKnjHqcOmMgKd2YzVGxC62FbFYObfMPARZUYdvkpzsvfCn?= =?iso-8859-1?Q?RNpZ81JL0ovsk8/oCmBfMyHZw05uaC/rXE6/lM6tS+4NU0fxCgL2a1DMCs?= =?iso-8859-1?Q?myrQooH5XqFpV5GBF/p+mhv97tRFeAofCGOCH9JyEyFByW/oPC4Hq8AD0U?= =?iso-8859-1?Q?JC+qm6PAAuDzrQxbItq+isvt1/yFd9Rb50BLEzFM4rdNV+7yTDkS7tm9sI?= =?iso-8859-1?Q?SBntNi/wNfnajoA6VbyvXpYcA1llCe6Bymr06qR0pUp2XfsfmBM62G8AgY?= =?iso-8859-1?Q?UxwS26XVp6mg8eLv4dcXuYn1HDFV59NRXG/jvilWALfikM28kf2jSJF+uD?= =?iso-8859-1?Q?lbcT7JnMRW+oO3+03mtIwkVTROglYbmbtp+smkW8yTqsnPSgUx8a5w+Cao?= =?iso-8859-1?Q?afHfybTO9hGsepNQi+eFFuBylJ0C3C+hnXuYAt4v/XP+tGTb0FklLJMXUq?= =?iso-8859-1?Q?S28NKY9b7g6ztG/3GS7hdm4YROqyEtf0WukO+SXcuJDmDLhWQYa4SQuH0G?= =?iso-8859-1?Q?uWQDboH6wZNOe/r6+N+FO8ozYBNyhRC4+0/tyl+ExQJyagnFHFrWY2pYLn?= =?iso-8859-1?Q?PxsuasCrOUP1mPRPISHeFlGvWDN5D8WlBm9rWUyP33wdqXfC7Th9zx0yYv?= =?iso-8859-1?Q?rOqzpQiNXHGeY9VDjUGN8dbiXeBJ/QX4bz35NSWx1ZQ8N9dGR5zdQDvCpV?= =?iso-8859-1?Q?h87skiGNLrmkbRESEcu3oFxyJhae7yWGaQ5eGeNhAzeFNMy47lfDVePcNw?= =?iso-8859-1?Q?bR6bCfr+XCd0fm9UPMTs1qP3OzuginUxxPIgSMQXWeiSuQderwT3q3xGLC?= =?iso-8859-1?Q?OsFSotnXphT0PEZTrkLck9straJMd20Mn6Cxmt+oICav4Ysbupc4EfxhcQ?= =?iso-8859-1?Q?WNCLf9AXHc5pcTO/HhE7m0Y0naiK1ruT+Aao/KNii9j0WmtiwMR+utKw?= =?iso-8859-1?Q?=3D=3D?= X-MS-Exchange-CrossTenant-Network-Message-Id: 36c39cf0-11d3-459b-5043-08ddd6aee82a X-MS-Exchange-CrossTenant-AuthSource: BL3PR11MB6508.namprd11.prod.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-OriginalArrivalTime: 08 Aug 2025 19:08:06.6463 (UTC) X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted X-MS-Exchange-CrossTenant-Id: 46c98d88-e344-4ed4-8496-4ed7712e255d X-MS-Exchange-CrossTenant-MailboxType: HOSTED X-MS-Exchange-CrossTenant-UserPrincipalName: hlRV8ER9geblCWJsjaN2QRRmbwODl/hCVrxtbQPzh3HyyuCEtfGC1vRCToBx2vZt0fdS6sNBr8bxiD54gw2TtA== X-MS-Exchange-Transport-CrossTenantHeadersStamped: SN7PR11MB6922 X-OriginatorOrg: intel.com 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 Fri, Aug 08, 2025 at 09:49:20PM +0530, S Sebinraj wrote: > A periodic GPU frequency monitoring and tracing program for the > Xe driver. The implementation provides periodic sampling of > GPU frequency through the Linux ftrace infrastructure. > > Key features: > - Periodic GPU frequency sampling with configurable intervals > - Immediate frequency change reporting via tracepoints > - Integration with Linux ftrace subsystem under 'power' events > - Per-GT (Graphics Technology) monitoring support > - Dedicated workqueue for non-blocking frequency sampling > - Configurable via CONFIG_DRM_XE_GPUFREQTRACER kernel option > - The monitoring interval can be configured at runtime via the sysfs > (default 5sec). > > The sysfs entry is at: > /sys/module/xe/parameters/gpufreq_monitoring_interval_ms > > The tracepoint is exposed at: > /sys/kernel/debug/tracing/events/power/gpu_frequency > > Format: {unsigned int state, unsigned int gpu_id} > - state: GPU frequency in KHz > - gpu_id: GPU clock domain identifier > > This enables userspace tools and system monitoring applications to track > GPU frequency changes for power management analysis, performance tuning, > and debugging purposes. > > Signed-off-by: S Sebinraj > --- > drivers/gpu/drm/xe/Kconfig | 22 ++ > drivers/gpu/drm/xe/Makefile | 3 + > drivers/gpu/drm/xe/xe_device.c | 20 ++ > drivers/gpu/drm/xe/xe_device_types.h | 6 + > .../xe/xe_gpufreqtracer/xe_gpufreqtracer.c | 289 ++++++++++++++++++ > .../xe/xe_gpufreqtracer/xe_gpufreqtracer.h | 73 +++++ > .../xe_gpufreqtracer/xe_gpufreqtracer_trace.h | 48 +++ > drivers/gpu/drm/xe/xe_module.c | 40 +++ > drivers/gpu/drm/xe/xe_module.h | 3 + > 9 files changed, 504 insertions(+) > create mode 100644 drivers/gpu/drm/xe/xe_gpufreqtracer/xe_gpufreqtracer.c > create mode 100644 drivers/gpu/drm/xe/xe_gpufreqtracer/xe_gpufreqtracer.h > create mode 100644 drivers/gpu/drm/xe/xe_gpufreqtracer/xe_gpufreqtracer_trace.h > > diff --git a/drivers/gpu/drm/xe/Kconfig b/drivers/gpu/drm/xe/Kconfig > index 714d5702dfd7..a2c99c0a01a4 100644 > --- a/drivers/gpu/drm/xe/Kconfig > +++ b/drivers/gpu/drm/xe/Kconfig > @@ -129,6 +129,28 @@ config DRM_XE_FORCE_PROBE > > Use "!*" to block the probe of the driver for all known devices. > > +config DRM_XE_GPUFREQTRACER > + bool "Enable XE GPU frequency tracing" > + depends on DRM_XE I think you are missing a ftrace dependency too. No point enabling this feature if ftrace is disabled. Off the top of head, I'm unsure what dependecy for ftrace is. Matt > + default n > + help > + Enable GPU frequency tracing support for Intel XE driver. > + This adds an ftrace tracepoint that reports GPU frequency changes > + at periodic boundaries (default 5 secs, configurable via the > + gpufreq_monitoring_interval_ms module parameter) and > + on direct frequency change events. > + > + The monitoring interval can be configured at runtime via the sysfs module parameter: > + /sys/module/xe/parameters/gpufreq_monitoring_interval_ms > + > + The tracepoint will be available at: > + /sys/kernel/debug/tracing/events/power/gpu_frequency > + > + Format: {unsigned int state, unsigned int gpu_id} > + Where state is the frequency in KHz and gpu_id is the GPU clock domain. > + > + If unsure, say N. > + > menu "drm/Xe Debugging" > depends on DRM_XE > depends on EXPERT > diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile > index 8e0c3412a757..7bbaac7de867 100644 > --- a/drivers/gpu/drm/xe/Makefile > +++ b/drivers/gpu/drm/xe/Makefile > @@ -170,6 +170,9 @@ xe-$(CONFIG_PCI_IOV) += \ > xe_sriov_pf.o \ > xe_sriov_pf_service.o > > +# GPU frequency tracer > +xe-$(CONFIG_DRM_XE_GPUFREQTRACER) += xe_gpufreqtracer/xe_gpufreqtracer.o > + > # include helpers for tests even when XE is built-in > ifdef CONFIG_DRM_XE_KUNIT_TEST > xe-y += tests/xe_kunit_helpers.o > diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c > index 57edbc63da6f..cfc81d4c7c82 100644 > --- a/drivers/gpu/drm/xe/xe_device.c > +++ b/drivers/gpu/drm/xe/xe_device.c > @@ -34,6 +34,7 @@ > #include "xe_exec_queue.h" > #include "xe_force_wake.h" > #include "xe_ggtt.h" > +#include "xe_gpufreqtracer/xe_gpufreqtracer.h" > #include "xe_gsc_proxy.h" > #include "xe_gt.h" > #include "xe_gt_mcr.h" > @@ -896,6 +897,21 @@ int xe_device_probe(struct xe_device *xe) > if (err) > return err; > > +#ifdef CONFIG_DRM_XE_GPUFREQTRACER > + err = xe_gpufreqtracer_init(xe); > + if (err) > + return err; > + > + /* Start periodic monitoring on all GTs using global module parameter */ > + for_each_gt(gt, xe, id) { > + err = xe_gpufreqtracer_start_monitoring(gt); > + if (err) { > + drm_err(&xe->drm, "xe_gpufreqtracer: failed to start monitoring for GT%u, err=%d\n", > + gt->info.id, err); > + } > + } > +#endif > + > err = xe_oa_init(xe); > if (err) > return err; > @@ -959,6 +975,10 @@ void xe_device_remove(struct xe_device *xe) > > xe_nvm_fini(xe); > > +#ifdef CONFIG_DRM_XE_GPUFREQTRACER > + xe_gpufreqtracer_fini(xe); > +#endif > + > drm_dev_unplug(&xe->drm); > > xe_bo_pci_dev_remove_all(xe); > diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h > index 01e8fa0d2f9f..760db7cd25d3 100644 > --- a/drivers/gpu/drm/xe/xe_device_types.h > +++ b/drivers/gpu/drm/xe/xe_device_types.h > @@ -35,6 +35,7 @@ struct dram_info; > struct intel_display; > struct intel_dg_nvm_dev; > struct xe_ggtt; > +struct xe_gpufreqtracer_data; > struct xe_i2c; > struct xe_pat_ops; > struct xe_pxp; > @@ -529,6 +530,11 @@ struct xe_device { > /** @oa: oa observation subsystem */ > struct xe_oa oa; > > +#ifdef CONFIG_DRM_XE_GPUFREQTRACER > + /** @gpufreqtracer_data: GPU frequency tracer data */ > + struct xe_gpufreqtracer_data *gpufreqtracer_data; > +#endif > + > /** @pxp: Encapsulate Protected Xe Path support */ > struct xe_pxp *pxp; > > diff --git a/drivers/gpu/drm/xe/xe_gpufreqtracer/xe_gpufreqtracer.c b/drivers/gpu/drm/xe/xe_gpufreqtracer/xe_gpufreqtracer.c > new file mode 100644 > index 000000000000..6d1941b4a5f3 > --- /dev/null > +++ b/drivers/gpu/drm/xe/xe_gpufreqtracer/xe_gpufreqtracer.c > @@ -0,0 +1,289 @@ > +// SPDX-License-Identifier: GPL-2.0 > +/* > + * Copyright © 2024 Intel Corporation > + */ > + > +#include "xe_gpufreqtracer.h" > + > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > +#include > + > +#include "xe_device.h" > +#include "xe_gt.h" > +#include "xe_gt_types.h" > +#include "xe_guc_pc.h" > +#include "xe_module.h" > + > +#define CREATE_TRACE_POINTS > +#include "xe_gpufreqtracer_trace.h" > + > +/** > + * struct xe_gpufreqtracer_gt_data - Per-GT frequency monitoring data > + * @gt: Reference to the GT > + * @timer: Timer for periodic monitoring > + * @work: Work item for frequency sampling > + * @last_frequency: Last reported frequency to avoid duplicate reports > + * @monitoring_active: Whether monitoring is currently active > + */ > +struct xe_gpufreqtracer_gt_data { > + struct xe_gt *gt; > + struct timer_list timer; > + struct work_struct work; > + atomic_t last_frequency; > + atomic_t monitoring_active; > +}; > + > +/** > + * struct xe_gpufreqtracer_data - Per-device frequency tracer data > + * @xe: Reference to the XE device > + * @gt_data: Array of per-GT monitoring data > + */ > +struct xe_gpufreqtracer_data { > + struct xe_device *xe; > + struct xe_gpufreqtracer_gt_data *gt_data; > +}; > + > + > +/** > + * xe_gpufreqtracer_sample_work - Worker function to sample GPU frequency. > + * @work: Pointer to the work_struct representing the scheduled work. > + * > + * This function is executed in a workqueue context to periodically sample > + * the GPU frequency and perform any necessary tracing or logging operations. > + * It is part of the GPU frequency tracer subsystem. > + */ > +static void xe_gpufreqtracer_sample_work(struct work_struct *work) > +{ > + struct xe_gpufreqtracer_gt_data *gt_data = > + container_of(work, struct xe_gpufreqtracer_gt_data, work); > + struct xe_gt *gt = gt_data->gt; > + struct xe_guc_pc *pc = >->uc.guc.pc; > + u32 current_freq, last_freq; > + > + if (!atomic_read(>_data->monitoring_active)) { > + drm_warn(>_to_xe(gt)->drm, "monitoring not active for GT%u, exiting", > + gt->info.id); > + return; > + } > + > + current_freq = xe_guc_pc_get_act_freq(pc) * 1000; /* Convert MHz to KHz */ > + last_freq = atomic_read(>_data->last_frequency); > + > + /* Only report if frequency has changed or this is the first sample */ > + if (current_freq != last_freq) { > + drm_dbg(>_to_xe(gt)->drm, "GT%u frequency changed, tracing %u KHz", > + gt->info.id, current_freq); > + trace_gpu_frequency(current_freq, gt->info.id); > + atomic_set(>_data->last_frequency, current_freq); > + } > +} > + > +/** > + * xe_gpufreqtracer_timer_callback - Timer callback for GPU frequency tracer > + * @timer: Pointer to the timer_list structure associated with this callback > + * > + * This function is invoked when the timer associated with the GPU frequency tracer expires. > + * It is responsible for handling periodic tasks related to GPU frequency tracing, such as > + * sampling or logging frequency data. > + */ > +static void xe_gpufreqtracer_timer_callback(struct timer_list *timer) > +{ > + struct xe_gpufreqtracer_gt_data *gt_data = > + container_of(timer, struct xe_gpufreqtracer_gt_data, timer); > + > + if (atomic_read(>_data->monitoring_active)) { > + queue_work(system_highpri_wq, >_data->work); > + mod_timer(>_data->timer, jiffies + > + msecs_to_jiffies(xe_modparam.gpufreq_monitoring_interval_ms)); > + } else { > + drm_warn(>_to_xe(gt_data->gt)->drm, "timer callback for GT%u but monitoring inactive", > + gt_data->gt->info.id); > + } > +} > + > +/** > + * xe_gpufreqtracer_init - Initialize GPU frequency tracer for a device > + * @xe: The XE device > + * > + * Sets up the frequency tracer infrastructure for all GTs in the device. > + * > + * Return: 0 on success, negative error code on failure > + */ > +int xe_gpufreqtracer_init(struct xe_device *xe) > +{ > + struct xe_gpufreqtracer_data *tracer_data; > + struct xe_gt *gt; > + u8 tile_id; > + int ret = 0; > + > + tracer_data = kzalloc(sizeof(*tracer_data), GFP_KERNEL); > + if (!tracer_data) > + return -ENOMEM; > + > + tracer_data->xe = xe; > + > + /* Allocate GT data array based on actual GT count */ > + tracer_data->gt_data = kcalloc(xe->info.gt_count, > + sizeof(*tracer_data->gt_data), > + GFP_KERNEL); > + if (!tracer_data->gt_data) { > + ret = -ENOMEM; > + goto err_free_tracer; > + } > + > + /* Initialize per-GT data */ > + for_each_gt(gt, xe, tile_id) { > + struct xe_gpufreqtracer_gt_data *gt_data = > + &tracer_data->gt_data[gt->info.id]; > + > + drm_dbg(&xe->drm, "initializing GT%u (tile %u)", gt->info.id, tile_id); > + > + gt_data->gt = gt; > + atomic_set(>_data->monitoring_active, 0); > + atomic_set(>_data->last_frequency, 0); > + > + INIT_WORK(>_data->work, xe_gpufreqtracer_sample_work); > + timer_setup(>_data->timer, xe_gpufreqtracer_timer_callback, 0); > + > + drm_dbg(&xe->drm, "GT%u initialized with global interval=%u ms", > + gt->info.id, xe_modparam.gpufreq_monitoring_interval_ms); > + } > + > + xe->gpufreqtracer_data = tracer_data; > + return 0; > + > +err_free_tracer: > + drm_err(&xe->drm, "initialization failed, freeing tracer data"); > + kfree(tracer_data); > + return ret; > +} > + > +/** > + * xe_gpufreqtracer_fini - Cleanup GPU frequency tracer for a device > + * @xe: The XE device > + * > + * Stops all monitoring and cleans up tracer resources. > + */ > +void xe_gpufreqtracer_fini(struct xe_device *xe) > +{ > + struct xe_gpufreqtracer_data *tracer_data = xe->gpufreqtracer_data; > + struct xe_gt *gt; > + u8 tile_id; > + > + if (!tracer_data) { > + drm_warn(&xe->drm, "no tracer data found, nothing to cleanup"); > + return; > + } > + > + /* Stop all monitoring */ > + for_each_gt(gt, xe, tile_id) { > + drm_dbg(&xe->drm, "stopping monitoring for GT%u", gt->info.id); > + xe_gpufreqtracer_stop_monitoring(gt); > + } > + > + kfree(tracer_data->gt_data); > + kfree(tracer_data); > + xe->gpufreqtracer_data = NULL; > +} > + > +/** > + * xe_gpufreqtracer_report_frequency_change - Report frequency change directly > + * @gt: The GT instance > + * @frequency_khz: The new frequency in KHz > + * > + * Reports a frequency change immediately through the tracepoint. > + */ > +void xe_gpufreqtracer_report_frequency_change(struct xe_gt *gt, u32 frequency_khz) > +{ > + drm_dbg(>_to_xe(gt)->drm, "direct frequency report for GT%u: %u KHz", > + gt->info.id, frequency_khz); > + > + if (frequency_khz > 0) { > + trace_gpu_frequency(frequency_khz, gt->info.id); > + drm_dbg(>_to_xe(gt)->drm, "traced frequency change for GT%u", gt->info.id); > + } > +} > + > +/** > + * xe_gpufreqtracer_start_monitoring - Start periodic frequency monitoring > + * @gt: The GT instance > + * > + * Starts periodic sampling of GPU frequency for the specified GT using the global > + * monitoring interval from module parameters. > + * > + * Return: 0 on success, negative error code on failure > + */ > +int xe_gpufreqtracer_start_monitoring(struct xe_gt *gt) > +{ > + struct xe_gpufreqtracer_data *tracer_data = gt_to_xe(gt)->gpufreqtracer_data; > + struct xe_gpufreqtracer_gt_data *gt_data; > + > + if (!tracer_data) { > + drm_warn(>_to_xe(gt)->drm, "no tracer data for GT%u, not supported", gt->info.id); > + return -EOPNOTSUPP; > + } > + > + if (gt->info.id >= gt_to_xe(gt)->info.gt_count) { > + drm_err(>_to_xe(gt)->drm, "invalid GT ID %u, max supported is %u", > + gt->info.id, gt_to_xe(gt)->info.gt_count - 1); > + return -EINVAL; > + } > + > + gt_data = &tracer_data->gt_data[gt->info.id]; > + > + if (atomic_read(>_data->monitoring_active)) { > + drm_warn(>_to_xe(gt)->drm, "monitoring already active for GT%u", gt->info.id); > + return -EALREADY; > + } > + > + atomic_set(>_data->monitoring_active, 1); > + atomic_set(>_data->last_frequency, 0); > + > + /* Start the timer using global interval */ > + mod_timer(>_data->timer, jiffies + > + msecs_to_jiffies(xe_modparam.gpufreq_monitoring_interval_ms)); > + > + drm_dbg(>_to_xe(gt)->drm, "monitoring started for GT%u with interval %u ms", > + gt->info.id, xe_modparam.gpufreq_monitoring_interval_ms); > + > + return 0; > +} > + > +/** > + * xe_gpufreqtracer_stop_monitoring - Stop periodic frequency monitoring > + * @gt: The GT instance > + * > + * Stops periodic sampling of GPU frequency for the specified GT. > + */ > +void xe_gpufreqtracer_stop_monitoring(struct xe_gt *gt) > +{ > + struct xe_gpufreqtracer_data *tracer_data = gt_to_xe(gt)->gpufreqtracer_data; > + struct xe_gpufreqtracer_gt_data *gt_data; > + > + if (!tracer_data || gt->info.id >= gt_to_xe(gt)->info.gt_count) { > + drm_err(>_to_xe(gt)->drm, "invalid tracer data or GT ID %u for stop request", > + gt->info.id); > + return; > + } > + > + gt_data = &tracer_data->gt_data[gt->info.id]; > + > + if (!atomic_read(>_data->monitoring_active)) { > + drm_warn(>_to_xe(gt)->drm, "monitoring not active for GT%u, nothing to stop", > + gt->info.id); > + return; > + } > + > + atomic_set(>_data->monitoring_active, 0); > + > + timer_delete_sync(>_data->timer); > + cancel_work_sync(>_data->work); > +} > diff --git a/drivers/gpu/drm/xe/xe_gpufreqtracer/xe_gpufreqtracer.h b/drivers/gpu/drm/xe/xe_gpufreqtracer/xe_gpufreqtracer.h > new file mode 100644 > index 000000000000..6f0f88aec2ea > --- /dev/null > +++ b/drivers/gpu/drm/xe/xe_gpufreqtracer/xe_gpufreqtracer.h > @@ -0,0 +1,73 @@ > +/* SPDX-License-Identifier: GPL-2.0 */ > +/* > + * Copyright © 2024 Intel Corporation > + */ > + > +#ifndef _XE_GPUFREQTRACER_H_ > +#define _XE_GPUFREQTRACER_H_ > + > +#include > + > +struct xe_device; > +struct xe_gt; > + > +#ifdef CONFIG_DRM_XE_GPUFREQTRACER > + > +/* > + * Initialize the GPU frequency tracer for a device > + */ > +int xe_gpufreqtracer_init(struct xe_device *xe); > + > +/* > + * Cleanup the GPU frequency tracer for a device > + */ > +void xe_gpufreqtracer_fini(struct xe_device *xe); > + > +/* > + * Report a GPU frequency change directly > + * @gt: The GT instance > + * @frequency_khz: The new frequency in KHz > + */ > +void xe_gpufreqtracer_report_frequency_change(struct xe_gt *gt, u32 frequency_khz); > + > +/* > + * Start periodic frequency monitoring for a GT > + * @gt: The GT instance > + * > + * Uses the global module parameter for monitoring interval. > + */ > +int xe_gpufreqtracer_start_monitoring(struct xe_gt *gt); > + > +/* > + * Stop periodic frequency monitoring for a GT > + * @gt: The GT instance > + */ > +void xe_gpufreqtracer_stop_monitoring(struct xe_gt *gt); > + > +#else /* CONFIG_DRM_XE_GPUFREQTRACER */ > + > +static inline int xe_gpufreqtracer_init(struct xe_device *xe) > +{ > + return 0; > +} > + > +static inline void xe_gpufreqtracer_fini(struct xe_device *xe) > +{ > +} > + > +static inline void xe_gpufreqtracer_report_frequency_change(struct xe_gt *gt, u32 frequency_khz) > +{ > +} > + > +static inline int xe_gpufreqtracer_start_monitoring(struct xe_gt *gt) > +{ > + return 0; > +} > + > +static inline void xe_gpufreqtracer_stop_monitoring(struct xe_gt *gt) > +{ > +} > + > +#endif /* CONFIG_DRM_XE_GPUFREQTRACER */ > + > +#endif /* _XE_GPUFREQTRACER_H_ */ > diff --git a/drivers/gpu/drm/xe/xe_gpufreqtracer/xe_gpufreqtracer_trace.h b/drivers/gpu/drm/xe/xe_gpufreqtracer/xe_gpufreqtracer_trace.h > new file mode 100644 > index 000000000000..8dfb6c442630 > --- /dev/null > +++ b/drivers/gpu/drm/xe/xe_gpufreqtracer/xe_gpufreqtracer_trace.h > @@ -0,0 +1,48 @@ > +/* SPDX-License-Identifier: GPL-2.0 */ > +/* > + * Copyright © 2024 Intel Corporation > + */ > + > +#undef TRACE_SYSTEM > +#define TRACE_SYSTEM power > + > +#if !defined(_XE_GPUFREQTRACER_TRACE_H) || defined(TRACE_HEADER_MULTI_READ) > +#define _XE_GPUFREQTRACER_TRACE_H > + > +#include > + > +/* > + * Tracepoint for GPU frequency changes > + * This tracepoint is exposed at /sys/kernel/debug/tracing/events/power/gpu_frequency > + * > + * location: /d/events/power/gpu_frequency > + * format: {unsigned int state, unsigned int gpu_id} > + * where state holds the frequency(in Khz) and the gpu_id holds the GPU clock domain. > + */ > + > +TRACE_EVENT(gpu_frequency, > + TP_PROTO(unsigned int state, unsigned int gpu_id), > + > + TP_ARGS(state, gpu_id), > + > + TP_STRUCT__entry( > + __field(unsigned int, state) > + __field(unsigned int, gpu_id) > + ), > + > + TP_fast_assign( > + __entry->state = state; > + __entry->gpu_id = gpu_id; > + ), > + > + TP_printk("state=%u gpu_id=%u", __entry->state, __entry->gpu_id) > +); > + > +#endif /* _XE_GPUFREQTRACER_TRACE_H */ > + > +/* This part must be outside protection */ > +#undef TRACE_INCLUDE_PATH > +#undef TRACE_INCLUDE_FILE > +#define TRACE_INCLUDE_PATH xe_gpufreqtracer > +#define TRACE_INCLUDE_FILE xe_gpufreqtracer_trace > +#include > diff --git a/drivers/gpu/drm/xe/xe_module.c b/drivers/gpu/drm/xe/xe_module.c > index d08338fc3bc1..2252d0f762bd 100644 > --- a/drivers/gpu/drm/xe/xe_module.c > +++ b/drivers/gpu/drm/xe/xe_module.c > @@ -18,6 +18,13 @@ > #include "xe_observation.h" > #include "xe_sched_job.h" > > +#ifdef CONFIG_DRM_XE_GPUFREQTRACER > +/* GPU frequency monitoring interval constants (in milliseconds) */ > +#define XE_GPUFREQ_MONITORING_MIN_INTERVAL_MS 100 > +#define XE_GPUFREQ_MONITORING_MAX_INTERVAL_MS 10000 > +#define XE_GPUFREQ_MONITORING_DEFAULT_INTERVAL_MS 5000 > +#endif > + > #if IS_ENABLED(CONFIG_DRM_XE_DEBUG) > #define DEFAULT_GUC_LOG_LEVEL 3 > #else > @@ -41,6 +48,9 @@ struct xe_modparam xe_modparam = { > #endif > .wedged_mode = DEFAULT_WEDGED_MODE, > .svm_notifier_size = DEFAULT_SVM_NOTIFIER_SIZE, > +#ifdef CONFIG_DRM_XE_GPUFREQTRACER > + .gpufreq_monitoring_interval_ms = XE_GPUFREQ_MONITORING_DEFAULT_INTERVAL_MS, > +#endif > /* the rest are 0 by default */ > }; > > @@ -93,6 +103,16 @@ MODULE_PARM_DESC(wedged_mode, > "Module's default policy for the wedged mode (0=never, 1=upon-critical-errors, 2=upon-any-hang " > "[default=" __stringify(DEFAULT_WEDGED_MODE) "])"); > > +#ifdef CONFIG_DRM_XE_GPUFREQTRACER > +module_param_named(gpufreq_monitoring_interval_ms, > + xe_modparam.gpufreq_monitoring_interval_ms, uint, 0644); > +MODULE_PARM_DESC(gpufreq_monitoring_interval_ms, > + "GPU frequency monitoring interval in milliseconds (" > + __stringify(XE_GPUFREQ_MONITORING_MIN_INTERVAL_MS) "-" > + __stringify(XE_GPUFREQ_MONITORING_MAX_INTERVAL_MS) ", default: " > + __stringify(XE_GPUFREQ_MONITORING_DEFAULT_INTERVAL_MS) ")"); > +#endif > + > static int xe_check_nomodeset(void) > { > if (drm_firmware_drivers_only()) > @@ -101,6 +121,21 @@ static int xe_check_nomodeset(void) > return 0; > } > > +#ifdef CONFIG_DRM_XE_GPUFREQTRACER > +static int xe_validate_module_params(void) > +{ > + /* Validate GPU frequency monitoring interval */ > + if (xe_modparam.gpufreq_monitoring_interval_ms < XE_GPUFREQ_MONITORING_MIN_INTERVAL_MS || > + xe_modparam.gpufreq_monitoring_interval_ms > XE_GPUFREQ_MONITORING_MAX_INTERVAL_MS) { > + /* xe: gpufreq_monitoring_interval_ms %u out of range [100, 10000], */ > + /* using default 5000ms */ > + xe_modparam.gpufreq_monitoring_interval_ms = > + XE_GPUFREQ_MONITORING_DEFAULT_INTERVAL_MS; > + } > + return 0; > +} > +#endif > + > struct init_funcs { > int (*init)(void); > void (*exit)(void); > @@ -110,6 +145,11 @@ static const struct init_funcs init_funcs[] = { > { > .init = xe_check_nomodeset, > }, > +#ifdef CONFIG_DRM_XE_GPUFREQTRACER > + { > + .init = xe_validate_module_params, > + }, > +#endif > { > .init = xe_configfs_init, > .exit = xe_configfs_exit, > diff --git a/drivers/gpu/drm/xe/xe_module.h b/drivers/gpu/drm/xe/xe_module.h > index 5a3bfea8b7b4..fd60de38d24d 100644 > --- a/drivers/gpu/drm/xe/xe_module.h > +++ b/drivers/gpu/drm/xe/xe_module.h > @@ -23,6 +23,9 @@ struct xe_modparam { > #endif > int wedged_mode; > u32 svm_notifier_size; > +#ifdef CONFIG_DRM_XE_GPUFREQTRACER > + u32 gpufreq_monitoring_interval_ms; > +#endif > }; > > extern struct xe_modparam xe_modparam; > -- > 2.34.1 >