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 1EA09CA0EC3 for ; Tue, 12 Sep 2023 06:23:16 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id CFB4C10E321; Tue, 12 Sep 2023 06:23:15 +0000 (UTC) Received: from mgamail.intel.com (mgamail.intel.com [134.134.136.20]) by gabe.freedesktop.org (Postfix) with ESMTPS id 1D33410E321 for ; Tue, 12 Sep 2023 06:23:13 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1694499793; x=1726035793; h=message-id:date:subject:to:cc:references:from: in-reply-to:mime-version; bh=1x2fU+Ili4lqxaKhuxWTzeHEHTRwAaIVCyBoL9ncOFA=; b=G+Cbca7NF+JLM3bAbZpqOaToVKGobrkBBIl2X8L3d02o7InrVGpakwXQ FXGzPA+nbhSdQQKmESaEIss36JZz296yTsJ4sno/WtR6eLxNu8b/BuS0H n04qs5Uy2EonD2wlgvwjFWJvvPKGOvMvvOpt8JA+jf0P8CAzHXNAZfnJ6 fS6Vp5QRx6Ihe/tfwYyxFUSP3VAOhD3V65hdZMsyte83FMJFkEojEI9Ho IRrJ1O2HUzI0ZkT5lDlum6Mt3wvBUhrPS+bqokFgUC8DYzaT6uDJKAbMX 4GvOvc06PqFpbSo0e2aXzb9M7SXaijLXeeG7TSG7xyzlM7PRz0sq3Rycb g==; X-IronPort-AV: E=McAfee;i="6600,9927,10830"; a="368543145" X-IronPort-AV: E=Sophos;i="6.02,245,1688454000"; d="scan'208,217";a="368543145" Received: from orsmga008.jf.intel.com ([10.7.209.65]) by orsmga101.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 11 Sep 2023 23:23:02 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10830"; a="772872842" X-IronPort-AV: E=Sophos;i="6.02,245,1688454000"; d="scan'208,217";a="772872842" Received: from fmsmsx602.amr.corp.intel.com ([10.18.126.82]) by orsmga008.jf.intel.com with ESMTP/TLS/AES256-GCM-SHA384; 11 Sep 2023 23:23:02 -0700 Received: from fmsmsx612.amr.corp.intel.com (10.18.126.92) by fmsmsx602.amr.corp.intel.com (10.18.126.82) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.32; Mon, 11 Sep 2023 23:23:02 -0700 Received: from fmsmsx610.amr.corp.intel.com (10.18.126.90) by fmsmsx612.amr.corp.intel.com (10.18.126.92) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.32; Mon, 11 Sep 2023 23:23:01 -0700 Received: from fmsedg602.ED.cps.intel.com (10.1.192.136) by fmsmsx610.amr.corp.intel.com (10.18.126.90) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256) id 15.1.2507.32 via Frontend Transport; Mon, 11 Sep 2023 23:23:01 -0700 Received: from NAM10-DM6-obe.outbound.protection.outlook.com (104.47.58.107) by edgegateway.intel.com (192.55.55.71) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.1.2507.32; Mon, 11 Sep 2023 23:23:01 -0700 ARC-Seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=oGPb12qrCe9dXpGm9RUC3xkq4oDWvj5M1/n+l4i9frhQkg3WRYggWdnrIQl3OyCUHK5s7cXXpuoKPwc4kzDbqOb0PtHMC3WxVVj9q1DpdwGyv7PnvFvQDk8S+z0JuqaeQVd8GH5Bo5oNmhUqXRJqAdSB79NeAD7Etttd8nnEac/1b2atkR6JuWNBB+kncdcmi2XO4qCfSv4AHzZK/Zjy++mk4a2vGuUUwSrA60qS7iWhqDLbfLCrxsBlunEDwGOBsyQ2k31cyLYlK5iTmcIjR3EU9yFvZwam8ZTbONmGHzJV7S8OhZsnF4Xk2DCYjUwqG0SSTAZWkiv1mPn0PPh8XQ== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector9901; 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=Z3I6giHkjt71AdihnbKyu7jw9C6YO+XOkkzo5Z5OlsM=; b=ZLb26eVqrv+zZvxIWQ2IiqxyD3SxL6bEa5ta+YUoFEi72R5T2yCQGyugR/ZJpaqdVvBYGqPEi4I0SoDBZnIh5wHI2PprryY4CuViOWax/puVr2uH1htvkoPWfR77eyBm+8lFzS74sLa5P5glORRG3b6Ygh1f1BrVAcOLzOmVt3Xl5TKVtSYQiOchyWneZFUeC6nIzCBo5txf+9TAmVLsuzptEvRT5w1QblSYzxchAoy6mgEfpppRNnChUPeh9EEZ24JcAThY1vT7WnadEy4rpqNxg9SQqaBlIdL2i6k/eWRrJkNVw7JN5y/Ydf/YUh2T6mgSb8fHZJImtsW0jrCnXQ== 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 MW4PR11MB7056.namprd11.prod.outlook.com (2603:10b6:303:21a::12) by CH0PR11MB5409.namprd11.prod.outlook.com (2603:10b6:610:d0::7) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.6768.38; Tue, 12 Sep 2023 06:22:59 +0000 Received: from MW4PR11MB7056.namprd11.prod.outlook.com ([fe80::1ed2:437d:1d6c:da25]) by MW4PR11MB7056.namprd11.prod.outlook.com ([fe80::1ed2:437d:1d6c:da25%6]) with mapi id 15.20.6768.029; Tue, 12 Sep 2023 06:22:59 +0000 Content-Type: multipart/alternative; boundary="------------Y3D3DugAC4kYfNKOfzudsKKL" Message-ID: Date: Tue, 12 Sep 2023 11:52:49 +0530 User-Agent: Mozilla Thunderbird To: Tejas Upadhyay , References: <20230831090536.2949934-1-tejas.upadhyay@intel.com> <20230831090536.2949934-8-tejas.upadhyay@intel.com> Content-Language: en-US From: "Ghimiray, Himal Prasad" In-Reply-To: <20230831090536.2949934-8-tejas.upadhyay@intel.com> X-ClientProxiedBy: PN2PR01CA0113.INDPRD01.PROD.OUTLOOK.COM (2603:1096:c01:27::28) To MW4PR11MB7056.namprd11.prod.outlook.com (2603:10b6:303:21a::12) MIME-Version: 1.0 X-MS-PublicTrafficType: Email X-MS-TrafficTypeDiagnostic: MW4PR11MB7056:EE_|CH0PR11MB5409:EE_ X-MS-Office365-Filtering-Correlation-Id: da695895-7681-463e-7473-08dbb358b5cb X-MS-Exchange-SenderADCheck: 1 X-MS-Exchange-AntiSpam-Relay: 0 X-Microsoft-Antispam: BCL:0; X-Microsoft-Antispam-Message-Info: 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 X-Forefront-Antispam-Report: CIP:255.255.255.255; CTRY:; LANG:en; SCL:1; SRV:; IPV:NLI; SFV:NSPM; H:MW4PR11MB7056.namprd11.prod.outlook.com; PTR:; CAT:NONE; SFS:(13230031)(346002)(39860400002)(396003)(366004)(376002)(136003)(451199024)(1800799009)(186009)(31686004)(6666004)(6486002)(6506007)(53546011)(33964004)(36756003)(82960400001)(86362001)(31696002)(38100700002)(26005)(107886003)(2616005)(30864003)(2906002)(6512007)(478600001)(83380400001)(4326008)(5660300002)(316002)(8676002)(8936002)(41300700001)(66476007)(66556008)(66946007)(45980500001)(43740500002); DIR:OUT; SFP:1102; X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1 X-MS-Exchange-AntiSpam-MessageData-0: =?utf-8?B?d2p6eU1xcDVYL3ZUcFdMWWF1S1Q5emE1a2h3aXRUNFIrT3QrUGFJTWZaVEc0?= =?utf-8?B?dGIvMmR6bVpXWGhvRnRQcVZwdUdlNDU5TnEzZnRKWlJPSnJRUkdTU2JPcHRO?= =?utf-8?B?RW14M3AzQW9EMUh0Sk9oQTRONW9sbmtNMmtwWXd5NGQrN2RHY05rT04wdzgz?= =?utf-8?B?WHVsb0EvSGJLQ1hrYlBORmtTNDlxOVZFSWZLWEkvU1pqL3NEaVNFelF1TmtU?= =?utf-8?B?aWgveHNHb1g2RkJ1UVlPSFNseHJObElwMC93YmFQajR6SW1FbkFWTVUwTkNu?= =?utf-8?B?VU9jZXg1MkZaR3oyNmYzbmh0NE95MnFEbU5EMVQxeFF3L3NrLzcwNENMdjVn?= =?utf-8?B?clVCVG9FTitYc3RNY09CbEVuT0U0SFVmaE1jdjhkQ1VEQnJ4VXhTZy9FMGJR?= =?utf-8?B?S1VsNUdWbVdZOWhwSFl4NGhlRktFNDRjMWpvZHRoYkhUQXdzSGlNTW1BL0pO?= =?utf-8?B?S2NVK0tvTzNrdURsK1Q1RnBtMjNGdmlOMExYQnZYQXc2eXIzYUp1RFhxWmNq?= =?utf-8?B?cFYrdEFLb2h3dGp5VWVIR3hZUHJLN3JKUmNyWnY3YTdZYVBUL3B6UUxMZFV3?= =?utf-8?B?Z2ZxSDVJVFpjZitlc3g2dGRXc0E3VG5ldmxCdzVxUGZsMXpPWFovYVhZaWxN?= =?utf-8?B?d3IyTE92RVVNZ09xS3lmN1pXclNWSnpQZDkrcXcyQVRSN3E3ekZzTW9kMFBk?= =?utf-8?B?TW1icmVhV2tlY1JTOXZBWGkyY2JzcDNRNkdaQm9KaTQwOHZSNmg2ekIybDhy?= =?utf-8?B?UE9MRjVSb0xkY3BvRFhrTEdHTUlxNW9WQ0YwUjkzdk96WHoxOXNLTFpRRy90?= =?utf-8?B?ZWo0U014QUU1Nkdqb1RmdU9OQXV1Uk54OWJTRVdPeEZzb09zTGpWZWJ6UGlj?= =?utf-8?B?cWg2My94K2JYNTNBVjd4MjNnOTBsRzJHSDU3d1ByMy9aWGI2VmMyd2liZ21R?= =?utf-8?B?elU5Tkh0WE0wbUF3VERUeEh4Uk9yTU1QUUlJSUZXZW1Ld0l0WmRFdXdmY2t3?= =?utf-8?B?U2FqUWowM1AxUnJpbzVERFdhUnlmdERZMERjclAwQWc0bXZXOWsvVExNbDUr?= =?utf-8?B?aWhUSDd6dGxnSlU5cjIvbU5rZ0sxU0M3U0RDbXBpbVllV0poRUdWZlo0WlZX?= =?utf-8?B?a2tNb21hMStySWpGWE4xNmNuYXhUR3V0MEZCUkVDT0lrUkk3d0dGS1VESlkv?= =?utf-8?B?TG9IZ2VnZDJTWmRDelNDcWZtN01MNEV3RmlJZWpQMTN2KzB6Qm43cmF6ZWpx?= =?utf-8?B?YjNGeXIzWHh3N1hDemhaRzVrWkVHOEtUenRUcjZLckw2WmtiQ3A5TFVOUnBv?= =?utf-8?B?WEpYZ2ZJQitWZm4zenJLaDI4VEp3YlhpdlRWa2JWN1VsSVNyNTNkQ01ac2sx?= =?utf-8?B?bzRQWWNQaXpPM2Zrd0szMklaNThCejI3R215aUZzSkxyZWRkb3gyaDljSnRU?= =?utf-8?B?RExqTmQ1aUpBRVpOeFU1Z3doZHpCakJPNS9pSEpYakdJZkZMdnNkbkg2L3F6?= =?utf-8?B?OW5NZG1yekFNU2Nya2VHZC82dk9FeEtHY2VWZFRCY1VOU2NBZXVqbVpUcnoy?= =?utf-8?B?OTdrM0xwWFhPRDlqbXVGOXdYTFZPUmFROHVSYWI5UElyT0Eva282ZTFsZE1C?= =?utf-8?B?SW9yWEY3a21nbFF3UDBGZ01sdXN0U1owTkxkV0w2bUF6VFE5eXZrc05iYTVa?= =?utf-8?B?ajJVcXp1dFFLSFFyNEZJYXZONlpiWGRaWGlEamszejhCODlTNkZaQ05rMEZX?= =?utf-8?B?NHEwUVcvbGYvZnFDcm55d1ZON09SYVBQb1R4YlYrWkNXYmpzVVJxdTJQM015?= =?utf-8?B?SWFmWXAvMng4OFNXWXJTbXE5My9TYmJML1VjM2Q0RzlTd2JDM2FnUTFlNm5E?= =?utf-8?B?aHlMRDliNGo0eTJoNENHV2xtakxIdHllak5UZ1A0VmtEZmpaSHlUbHlBWHJx?= =?utf-8?B?aUtRQ3R3ZXhkRFJnT1JBT002bGN3elp1ektBL043YWVWMGFtRkh0OHJVZ1ZI?= =?utf-8?B?SjNuQWRocHZZSktVRmJVMGRHRXRyVXp2TUVMblhxUXdJV0F6V1ZPN1QvdHBU?= =?utf-8?B?dzJhK0FvWDlUem9MSGI0VXNjK21CQWdZdWRIUnU3OHNKTlVTL1hQRmQyRXRv?= =?utf-8?B?dUVyaHRoYVVBaXUzLzV4OUsxcndPUGpqOC9DanVSUWZxTXVwVms0cUNGYlE3?= =?utf-8?Q?3DMWK0no86/P5Kj1IiBkQq0=3D?= X-MS-Exchange-CrossTenant-Network-Message-Id: da695895-7681-463e-7473-08dbb358b5cb X-MS-Exchange-CrossTenant-AuthSource: MW4PR11MB7056.namprd11.prod.outlook.com X-MS-Exchange-CrossTenant-AuthAs: Internal X-MS-Exchange-CrossTenant-OriginalArrivalTime: 12 Sep 2023 06:22:59.5018 (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: lndFRADk1xRvV8SSs0QsU4kuo4XvV957oNf4+9HO9VMnyQoPuimQxSJSv5wJJLt/wKvwvm2wXPHCmr/QehAwCsMueWmO3d+EtjIXdph0v1Q= X-MS-Exchange-Transport-CrossTenantHeadersStamped: CH0PR11MB5409 X-OriginatorOrg: intel.com Subject: Re: [Intel-xe] [PATCH 7/7] drm/xe: Implement fdinfo memory stats printing 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" --------------Y3D3DugAC4kYfNKOfzudsKKL Content-Type: text/plain; charset="UTF-8"; format=flowed Content-Transfer-Encoding: 8bit On 31-08-2023 14:35, Tejas Upadhyay wrote: > Use the newly added drm_print_memory_stats helper to show memory > utilisation of our objects in drm/driver specific fdinfo output. > > To collect the stats we walk the per memory regions object lists > and accumulate object size into the respective drm_memory_stats > categories. > > Objects with multiple possible placements are reported in multiple > regions for total and shared sizes, while other categories are > counted only for the currently active region. > > Signed-off-by: Tejas Upadhyay > --- > drivers/gpu/drm/xe/xe_bo.h | 11 +++ > drivers/gpu/drm/xe/xe_drm_client.c | 103 ++++++++++++++++++++++++++++- > 2 files changed, 113 insertions(+), 1 deletion(-) > > diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h > index 0823dda0f31b..538a9ec7f4c3 100644 > --- a/drivers/gpu/drm/xe/xe_bo.h > +++ b/drivers/gpu/drm/xe/xe_bo.h > @@ -6,6 +6,8 @@ > #ifndef _XE_BO_H_ > #define _XE_BO_H_ > > +#include > + > #include "xe_bo_types.h" > #include "xe_macros.h" > #include "xe_vm_types.h" > @@ -258,6 +260,15 @@ static inline size_t xe_bo_ccs_pages_start(struct xe_bo *bo) > return PAGE_ALIGN(bo->ttm.base.size); > } > > +static inline bool xe_bo_has_pages(struct xe_bo *bo) > +{ > + if ((bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm)) || > + xe_bo_is_vram(bo)) > + return true; > + > + return false; > +} > + > void __xe_bo_release_dummy(struct kref *kref); > > /** > diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c > index 00b28a08909f..28b4c8e608f8 100644 > --- a/drivers/gpu/drm/xe/xe_drm_client.c > +++ b/drivers/gpu/drm/xe/xe_drm_client.c > @@ -4,10 +4,12 @@ > */ > > #include > +#include > #include > #include > #include > > +#include "xe_bo.h" > #include "xe_bo_types.h" > #include "xe_device_types.h" > #include "xe_drm_client.h" > @@ -110,6 +112,105 @@ bool xe_drm_client_remove_bo(struct xe_bo *bo) > return true; > } > > +static void bo_meminfo(struct xe_bo *bo, > + struct drm_memory_stats stats[TTM_NUM_MEM_TYPES]) > +{ > + u64 sz = bo->size; > + u32 mem_type; > + > + if (bo->placement.placement) > + mem_type = bo->placement.placement->mem_type; > + else > + mem_type = XE_PL_TT; > + > + if (bo->ttm.base.handle_count > 1) > + stats[mem_type].shared += sz; > + else > + stats[mem_type].private += sz; > + > + if (xe_bo_has_pages(bo)) { > + stats[mem_type].resident += sz; > + > + if (!dma_resv_test_signaled(bo->ttm.base.resv, > + dma_resv_usage_rw(true) | > + DMA_RESV_USAGE_BOOKKEEP)) > + stats[mem_type].active += sz; > + else if (mem_type == XE_PL_SYSTEM) > + stats[mem_type].purgeable += sz; > + } > +} > + > +static void show_meminfo(struct drm_printer *p, struct drm_file *file) > +{ > + struct drm_memory_stats stats[TTM_NUM_MEM_TYPES] = {}; > + struct xe_file *xef = file->driver_priv; > + struct ttm_device *bdev = &xef->xe->ttm; > + struct ttm_resource_manager *man; > + struct xe_drm_client *client; > + struct list_head *pos; > + struct xe_bo *bo; > + unsigned int id; > + char name[16]; > + u32 mem_type; > + int ret = 0; > + > + client = xef->client; > + > + /* Public objects. */ > + spin_lock(&file->table_lock); > + idr_for_each_entry(&file->object_idr, bo, id) > + bo_meminfo(bo, stats); > + spin_unlock(&file->table_lock); > + > + /* Internal objects. */ > + rcu_read_lock(); > + list_for_each_rcu(pos, &client->bos_list) { > + bo = xe_bo_get(list_entry(pos, typeof(*bo), > + client_link)); > + if (!bo) > + continue; > + bo_meminfo(bo, stats); > + xe_bo_put(bo); > + } > + rcu_read_unlock(); > + for (mem_type = XE_PL_SYSTEM; mem_type < TTM_NUM_MEM_TYPES; ++mem_type) { can avoid this switch case with something like const char* mem_type_to_name []  = { "system",  /*XE_PL_STOLEN */ "gtt", "vram0" "vram1" NULL, NULL, "stolen", }, > + > + switch (mem_type) { > + case XE_PL_SYSTEM: > + sprintf(name, "system"); > + break; > + case XE_PL_TT: > + sprintf(name, "gtt"); > + break; > + case XE_PL_VRAM0: > + sprintf(name, "vram%d", mem_type - XE_PL_VRAM0); > + break; > + case XE_PL_VRAM1: > + sprintf(name, "vram%d", mem_type - XE_PL_VRAM0); > + break; > + case XE_PL_STOLEN: > + sprintf(name, "stolen"); > + break; > + default: > + ret = -EINVAL; > + break; > + } > + > + if (ret == -EINVAL) > + continue; if (! mem_type_to_name[mem_type]) continue; > + > + man = ttm_manager_type(bdev, mem_type); I assume on single tile platform man will be null for vram1 ? Please confirm. > + > + if (man) { > + drm_print_memory_stats(p, > + &stats[mem_type], > + DRM_GEM_OBJECT_RESIDENT | > + DRM_GEM_OBJECT_PURGEABLE, > + name); instead of name can use mem_type_to_name[mem_type]. Will leave it up to decide whether to use switch-case or const char*. Ensure DRM_GEM_OBJECT_PURGEABLE is not reported for vram0 and vram1. BR Himal Ghimiray > + } > + } > +} > + > /** > * xe_drm_client_fdinfo() - Callback for fdinfo interface > * @p: The drm_printer ptr > @@ -122,6 +223,6 @@ bool xe_drm_client_remove_bo(struct xe_bo *bo) > */ > void xe_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file) > { > - /* show_meminfo() will be developed here */ > + show_meminfo(p, file); > } > #endif --------------Y3D3DugAC4kYfNKOfzudsKKL Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: 8bit


On 31-08-2023 14:35, Tejas Upadhyay wrote:
Use the newly added drm_print_memory_stats helper to show memory
utilisation of our objects in drm/driver specific fdinfo output.

To collect the stats we walk the per memory regions object lists
and accumulate object size into the respective drm_memory_stats
categories.

Objects with multiple possible placements are reported in multiple
regions for total and shared sizes, while other categories are
counted only for the currently active region.

Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
---
 drivers/gpu/drm/xe/xe_bo.h         |  11 +++
 drivers/gpu/drm/xe/xe_drm_client.c | 103 ++++++++++++++++++++++++++++-
 2 files changed, 113 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_bo.h b/drivers/gpu/drm/xe/xe_bo.h
index 0823dda0f31b..538a9ec7f4c3 100644
--- a/drivers/gpu/drm/xe/xe_bo.h
+++ b/drivers/gpu/drm/xe/xe_bo.h
@@ -6,6 +6,8 @@
 #ifndef _XE_BO_H_
 #define _XE_BO_H_
 
+#include <drm/ttm/ttm_tt.h>
+
 #include "xe_bo_types.h"
 #include "xe_macros.h"
 #include "xe_vm_types.h"
@@ -258,6 +260,15 @@ static inline size_t xe_bo_ccs_pages_start(struct xe_bo *bo)
 	return PAGE_ALIGN(bo->ttm.base.size);
 }
 
+static inline bool xe_bo_has_pages(struct xe_bo *bo)
+{
+	if ((bo->ttm.ttm && ttm_tt_is_populated(bo->ttm.ttm)) ||
+	    xe_bo_is_vram(bo))
+		return true;
+
+	return false;
+}
+
 void __xe_bo_release_dummy(struct kref *kref);
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c
index 00b28a08909f..28b4c8e608f8 100644
--- a/drivers/gpu/drm/xe/xe_drm_client.c
+++ b/drivers/gpu/drm/xe/xe_drm_client.c
@@ -4,10 +4,12 @@
  */
 
 #include <drm/drm_print.h>
+#include <drm/xe_drm.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 
+#include "xe_bo.h"
 #include "xe_bo_types.h"
 #include "xe_device_types.h"
 #include "xe_drm_client.h"
@@ -110,6 +112,105 @@ bool xe_drm_client_remove_bo(struct xe_bo *bo)
 	return true;
 }
 
+static void bo_meminfo(struct xe_bo *bo,
+		       struct drm_memory_stats stats[TTM_NUM_MEM_TYPES])
+{
+	u64 sz = bo->size;
+	u32 mem_type;
+
+	if (bo->placement.placement)
+		mem_type = bo->placement.placement->mem_type;
+	else
+		mem_type = XE_PL_TT;
+
+	if (bo->ttm.base.handle_count > 1)
+		stats[mem_type].shared += sz;
+	else
+		stats[mem_type].private += sz;
+
+	if (xe_bo_has_pages(bo)) {
+		stats[mem_type].resident += sz;
+
+		if (!dma_resv_test_signaled(bo->ttm.base.resv,
+					    dma_resv_usage_rw(true) |
+					    DMA_RESV_USAGE_BOOKKEEP))
+			stats[mem_type].active += sz;
+		else if (mem_type == XE_PL_SYSTEM)
+			stats[mem_type].purgeable += sz;
+	}
+}
+
+static void show_meminfo(struct drm_printer *p, struct drm_file *file)
+{
+	struct drm_memory_stats stats[TTM_NUM_MEM_TYPES] = {};
+	struct xe_file *xef = file->driver_priv;
+	struct ttm_device *bdev = &xef->xe->ttm;
+	struct ttm_resource_manager *man;
+	struct xe_drm_client *client;
+	struct list_head *pos;
+	struct xe_bo *bo;
+	unsigned int id;
+	char name[16];
+	u32 mem_type;
+	int ret = 0;
+
+	client = xef->client;
+
+	/* Public objects. */
+	spin_lock(&file->table_lock);
+	idr_for_each_entry(&file->object_idr, bo, id)
+		bo_meminfo(bo, stats);
+	spin_unlock(&file->table_lock);
+
+	/* Internal objects. */
+	rcu_read_lock();
+	list_for_each_rcu(pos, &client->bos_list) {
+		bo = xe_bo_get(list_entry(pos, typeof(*bo),
+					  client_link));
+		if (!bo)
+			continue;
+		bo_meminfo(bo, stats);
+		xe_bo_put(bo);
+	}
+	rcu_read_unlock();
+	for (mem_type = XE_PL_SYSTEM; mem_type < TTM_NUM_MEM_TYPES; ++mem_type) {

can avoid this switch case with something like

const char* mem_type_to_name []  = {

"system",  /*XE_PL_STOLEN */

"gtt",

"vram0"

"vram1"

NULL,

NULL,

"stolen",

}, 

+
+		switch (mem_type) {
+		case XE_PL_SYSTEM:
+			sprintf(name, "system");
+			break;
+		case XE_PL_TT:
+			sprintf(name, "gtt");
+			break;
+		case XE_PL_VRAM0:
+			sprintf(name, "vram%d", mem_type - XE_PL_VRAM0);
+			break;
+		case XE_PL_VRAM1:
+			sprintf(name, "vram%d", mem_type - XE_PL_VRAM0);
+			break;
+		case XE_PL_STOLEN:
+			sprintf(name, "stolen");
+			break;
+		default:
+			ret = -EINVAL;
+			break;
+		}
+
+		if (ret == -EINVAL)
+			continue;

if (! mem_type_to_name[mem_type])

continue;

+
+		man = ttm_manager_type(bdev, mem_type);
I assume on single tile platform man will be null for vram1 ? Please confirm.
+
+		if (man) {
+			drm_print_memory_stats(p,
+					       &stats[mem_type],
+					       DRM_GEM_OBJECT_RESIDENT |
+					       DRM_GEM_OBJECT_PURGEABLE,
+					       name);

instead of name can use mem_type_to_name[mem_type].

Will leave it up to decide whether to use switch-case or const char*.

Ensure DRM_GEM_OBJECT_PURGEABLE is not reported for vram0 and vram1.

BR

Himal Ghimiray 

+		}
+	}
+}
+
 /**
  * xe_drm_client_fdinfo() - Callback for fdinfo interface
  * @p: The drm_printer ptr
@@ -122,6 +223,6 @@ bool xe_drm_client_remove_bo(struct xe_bo *bo)
  */
 void xe_drm_client_fdinfo(struct drm_printer *p, struct drm_file *file)
 {
-	/* show_meminfo() will be developed here */
+	show_meminfo(p, file);
 }
 #endif
--------------Y3D3DugAC4kYfNKOfzudsKKL--