Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <2937dc45-0b62-7c71-b846-942fa91cbb4e@amd.com>
Date:   Fri, 9 Sep 2022 13:32:51 -0400
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.11.0
Subject: Re: [PATCH v3 5/6] drm/sched: Use parent fence instead of finished
Content-Language: en-US
To:     Arvind Yadav <Arvind.Yadav@amd.com>, Christian.Koenig@amd.com,
        shashank.sharma@amd.com, amaranath.somalapuram@amd.com,
        Arunpravin.PaneerSelvam@amd.com, sumit.semwal@linaro.org,
        gustavo@padovan.org, airlied@linux.ie, daniel@ffwll.ch,
        linux-media@vger.kernel.org, dri-devel@lists.freedesktop.org,
        linaro-mm-sig@lists.linaro.org, linux-kernel@vger.kernel.org
References: <20220909170845.4946-1-Arvind.Yadav@amd.com>
 <20220909170845.4946-6-Arvind.Yadav@amd.com>
From:   Andrey Grodzovsky <andrey.grodzovsky@amd.com>
In-Reply-To: <20220909170845.4946-6-Arvind.Yadav@amd.com>
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
MIME-Version: 1.0
X-MS-Exchange-AntiSpam-MessageData-ChunkCount: 1
X-MS-Exchange-AntiSpam-MessageData-0: =?utf-8?B?RlloTjgrS25NRnNOOVFDMWdtUjM5SG1PS1A2L2w0WWN0UHVpVlVDKzlIZWZz?=
 =?utf-8?B?UGlrWXlWWGlUbnhpSGhuMU1YQ0paV1pVYXNQUkluWDJNUEk5elFYT2tZNG9E?=
 =?utf-8?B?RlNxQjlOVlIyNTBReDZCS1lYb05HcHBEbjl1UFZTZFFqYWJENlRiMEZvVGp3?=
 =?utf-8?B?MkU4MkRCUHR1aWw0aCtteXNvS1VLMXIvVXArZVFicHJMNTRhYTYvdTZOSkda?=
 =?utf-8?B?YWxZWktJR3Z1NTJSeDBPMVBUNXptUFJDY1BzVzVkYVdFUG0wRE5xRHdCb3F2?=
 =?utf-8?B?TUVvbkljZ3d3cE9iRzkrSGwrNGhvYksrQnpMTFVJYW4zMlJQbDFucys2N2hX?=
 =?utf-8?B?UEIxOVVEc0NDSlF6WFZmVEh0MnJidXRHSnh3UVNOVTd6Vms1YmVVZnp3NEVF?=
 =?utf-8?B?U1lZQ1MyQklicDFWLzdFK2k1bTJEZUtVbFlxQWtVcmdMRGtzODM2eWtvVFZ2?=
 =?utf-8?B?blkzSXVvTVo4bVBCOU9paUV5SDlabFJCOGNGT2RFNXFMa3V0TUsyTE16MDRl?=
 =?utf-8?B?WTh3RUR5RFVPMXZsZ0JXelgxOGVUQmhGZW1DbUROYW5HcEgrRVFmVzV5SHA1?=
 =?utf-8?B?T0V1RmpzTVNhV253d1R5QU43QkRHTUsvNitCTDltSTVmUExQU3NyN0NjZ0tJ?=
 =?utf-8?B?QWpOQlVhODRkMmNheXBQSGpWajk5TisreGl0ZGNKWVBIa0c0bnhLQzFzdkhz?=
 =?utf-8?B?WXEydlR1VzBTWFBndFluRkg3TkVIcFZscStsQ09CMDlzdElQTlBIS0hISys2?=
 =?utf-8?B?ZjVJRHkvdlNVU0R4NjNlY1UwZVlTRCt3UlU0YlIrNkdxbmNVYStmc0c5dnFR?=
 =?utf-8?B?QytHY3VicWFqUjVXa3NNZ3RPV1RVUlFQaXU2TFZEUTN2VFY3RkxlWjVJOHN4?=
 =?utf-8?B?byt0Q2FsbW5GQVNsQlJKdC9VRm10bjg2NWo4V0tYTEswR2EvUkFVNlRLaWdY?=
 =?utf-8?B?RHpJNU5qZVF3WWNVb0tDRFNmV00yUEtRb3psYzRrRDE5Y3UzN1J1Ry91SkRL?=
 =?utf-8?B?OUZVQXlRSVJvd0x6dDhDSE9hTGdlNlgrZkx0cVM4K3psSmdCc3hhb3hkcHM4?=
 =?utf-8?B?RlVTTTRyZjh5TU1tcUh4U1hRbWRMOXhrSW1mV2lmRzYzdnUrZ3d3b2Z4anAr?=
 =?utf-8?B?NE1CbXhTaXFDTERnSG9yUUVuVzRmTC9SdFovUWNTeHZQNXQrSFQ0R0NVS3hn?=
 =?utf-8?B?aFRTMUVtK0svQzkyKzh6WHRhYmZMMnVQTUVPUy9lT0lWMjBvRDM4bFMyRTJ5?=
 =?utf-8?B?WlRyVVFvd21KVzhSc2N6bHNnelA1c2lYM3dFTDMvTHlIb0VUb3U1TzVGODkx?=
 =?utf-8?B?TE1JODNtL0lFNGlsWEFJZE1jUk9uMEloZi92M3dqayt2MEc3aE8vaVJ6WmRX?=
 =?utf-8?B?WjZvYW1IeFhXdVMvUFQrRGRZZHZFU0dWS2p2dDVzR0NENm9CcndHdlpPNHBh?=
 =?utf-8?B?Y29HdkF0SlNZZEZ2U3VPcExBOExDMHlzV0NqdnlNNTBjYzErVVc2Q3J1NU84?=
 =?utf-8?B?OXQ5aDhKaFVveG5IaHpYZ1gvUE1CQnp1TjE4SVF6Z1UvNjk0Q0dxVkZaMmJD?=
 =?utf-8?B?RmlhMkpaeFBNOHAzdnlJT3hhYzZ0YTBYSnZ5WE5MNG1nU043TkR5YWxzSzRu?=
 =?utf-8?B?eEszMGJrWnZ0LzFhRmEyTHNUUTNscFF2VWl3SW0wY2w2cVVVS3lLNlV3Y1px?=
 =?utf-8?B?SlhhaUkrK0pudzNkZ2d0c09lVVdIdTVkU3NYbDFzQTRpcStLckdSVnVCaFRM?=
 =?utf-8?B?Q05FWGxxWHFVMVF6WkpiVzRObjZwL1BaQUkvQTJtMVIzUEZLcklsYVBQN2t0?=
 =?utf-8?B?bzVLUEtucDJOQmJSSEoySEFaTWo5bUN3YUdHUG5CNExnU2pnRGNUbHRXaXdw?=
 =?utf-8?B?WmpJcTVyYjgwUWdXeFc5UEFlS3pUMU43NWtIVm42TDRDSnpUeGQ1M1dLMms4?=
 =?utf-8?B?eWZGZUlZbGI5OFJHOTZReDhtVVJCbHFJQ3E2bTJFOTVEQjdNcGlNOGVyempk?=
 =?utf-8?B?Umk4bm0rWHFkWEIxazVIUjlnY1pCNE4xU1lPaUhpaXNoY2pXZjI5Z0gxRld4?=
 =?utf-8?B?QmFQUm9ycVN0REZyZ09odmw0SnRrd09wWEZVeHNPNzJLVHljaVJRcGRwMDJZ?=
 =?utf-8?B?NDQzRStzT1lPMWFINml0NnhHRzVnQ2JQb2FDeW9OUEdIT3h0Z3JFWkpBVnBY?=
 =?utf-8?Q?zxM8cj5PvJIsB/SR41H+d9lPkJhn7kB0cwK4oPtTnjXR?=
X-OriginatorOrg: amd.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 61905350-805d-4f56-bc69-08da92895398
X-MS-Exchange-CrossTenant-AuthSource: DM5PR12MB1947.namprd12.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 09 Sep 2022 17:32:53.8602
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: yeeEc/KHxXSBua6SMtPfnOxbHCV0fD5uldYIKQopCHpASCsQgiBPv38a1EubwXtMAg8dGFNHwnuTGb5y0a/5xg==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: MN2PR12MB4375
X-Spam-Status: No, score=-3.2 required=5.0 tests=BAYES_00,DKIM_SIGNED,
        DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,FORGED_SPF_HELO,NICE_REPLY_A,
        RCVD_IN_DNSWL_NONE,RCVD_IN_MSPIKE_H2,SPF_HELO_PASS,SPF_NONE,
        T_SCC_BODY_TEXT_LINE autolearn=ham autolearn_force=no version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on
        lindbergh.monkeyblade.net
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

What exactly is the scenario which this patch fixes in more detail please  ?

Andrey

On 2022-09-09 13:08, Arvind Yadav wrote:
> Using the parent fence instead of the finished fence
> to get the job status. This change is to avoid GPU
> scheduler timeout error which can cause GPU reset.
>
> Signed-off-by: Arvind Yadav <Arvind.Yadav@amd.com>
> ---
>
> changes in v1,v2 - Enable signaling for finished fence in sche_main()
> is removed
>
> ---
>   drivers/gpu/drm/scheduler/sched_main.c | 4 ++--
>   1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c
> index e0ab14e0fb6b..2ac28ad11432 100644
> --- a/drivers/gpu/drm/scheduler/sched_main.c
> +++ b/drivers/gpu/drm/scheduler/sched_main.c
> @@ -829,7 +829,7 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
>   	job = list_first_entry_or_null(&sched->pending_list,
>   				       struct drm_sched_job, list);
>   
> -	if (job && dma_fence_is_signaled(&job->s_fence->finished)) {
> +	if (job && dma_fence_is_signaled(job->s_fence->parent)) {
>   		/* remove job from pending_list */
>   		list_del_init(&job->list);
>   
> @@ -841,7 +841,7 @@ drm_sched_get_cleanup_job(struct drm_gpu_scheduler *sched)
>   
>   		if (next) {
>   			next->s_fence->scheduled.timestamp =
> -				job->s_fence->finished.timestamp;
> +				job->s_fence->parent->timestamp;
>   			/* start TO timer for next job */
>   			drm_sched_start_timeout(sched);
>   		}