Received-SPF: pass (google.com: domain of linux-ext4-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Message-ID: <82ed845d-2534-490c-f9b9-a875e0283cc9@amd.com>
Date:   Fri, 1 Apr 2022 16:08:35 -0400
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:91.0) Gecko/20100101
 Thunderbird/91.7.0
Subject: Re: [PATCH v2 1/3] mm: add vm_normal_lru_pages for LRU handled pages
 only
Content-Language: en-US
To:     Christoph Hellwig <hch@lst.de>, Alex Sierra <alex.sierra@amd.com>
Cc:     jgg@nvidia.com, david@redhat.com, linux-mm@kvack.org,
        rcampbell@nvidia.com, linux-ext4@vger.kernel.org,
        linux-xfs@vger.kernel.org, amd-gfx@lists.freedesktop.org,
        dri-devel@lists.freedesktop.org, jglisse@redhat.com,
        apopple@nvidia.com, willy@infradead.org, akpm@linux-foundation.org
References: <20220330212537.12186-1-alex.sierra@amd.com>
 <20220330212537.12186-2-alex.sierra@amd.com> <20220331085341.GA22102@lst.de>
From:   Felix Kuehling <felix.kuehling@amd.com>
Organization: AMD Inc.
In-Reply-To: <20220331085341.GA22102@lst.de>
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?NTJ0MkYweHNDV3F5L1JjZkh4QmR3c3ZrbDlhbUtJbGI5RlR0K3c4RU1jV2ls?=
 =?utf-8?B?UDFzM0ZCNFM1UlpPNk9yRkg3VWQ5NTNNK0RydEYzWFpqZmxINWs5dEFKMDlS?=
 =?utf-8?B?S1NPdjk1cCs5Snk4dDRNZk1JamltMVNHeTN3WmE5dmorUkNFR2drVHpyOVVt?=
 =?utf-8?B?Qmlka0RyU29YRlFkTE1yandRS0xEb3RxTFJnWmFpSDhqUmN3VHlXbG9Sb1kr?=
 =?utf-8?B?ZzhEWlEyemlpeTdYMjVtd2xhS0NpZGZNTkZPNDZBQlFKT0liQnp6aGRyVWdZ?=
 =?utf-8?B?bDQ4OEVjSGxUN0NiOGhGeVdFYk05QzNjOW9LRTNOcXVzQUVSNlV4NjFyYkVr?=
 =?utf-8?B?K3JzeExqZVllN0JMQ1pKRjZLMW5GNW9Od0hWWVBqRmFKRHhSUzJRdDMxMmMw?=
 =?utf-8?B?VlhzMk15anl6elRSakdoeGVsaWI0ajM2cUx2d3NQZERNbm80THdRekE4UVFO?=
 =?utf-8?B?OW84bFlsV1hPU1ViUGZXVmlSNURnb0tNdTVBZTZyZ1FqSWNvQm51b2pJL1h5?=
 =?utf-8?B?ZWY4bFRXWTkva1F4dzRzdmtWcFRpQ2dxUkJiTEpqaFdTeThMbU9nVGd1aFRh?=
 =?utf-8?B?RG5nK0JDbGh5WXpGR1AybXVhZ0Vrd3VWUGUwYzlxR0I1SG5aMEJGaE1pYWZS?=
 =?utf-8?B?S2JrbzhIWU8rUk04TnpuTUMwdEFvM3YvZ0Y1ZEljNThqNDJmK0VQTks4NFBH?=
 =?utf-8?B?STRpZzYwdUlJZ0FkbXh0Wk9paFhxQW9ZbjVJSmVkVDZXWlBpSnNOeTlzYUUz?=
 =?utf-8?B?QWJITVFwb29oNDFscG1YZUJGZzArQmhacEpTVC9RdXNZbFRkMStTT3RKbFRn?=
 =?utf-8?B?clRxWHBTZ0h1NVUvOWxpSUNGNnBZZXJkZWRjTEJPYWNRSjRHV1pjWjdIN3h5?=
 =?utf-8?B?TW9mcm1QSDdNaVRVV1lVL21RNTdSQk5EQ0szRXpQb2lXd01rNnRyZ2Jvc1JC?=
 =?utf-8?B?QTFDS0w5MjlCSkN3VUNiM08wYmhZdVA2aEorMDh6UEFxbG9oZWJGZjFOWG9G?=
 =?utf-8?B?WUdJb3JScTMrYTAwMlZTc1FiNWhUVVkrMS96cjMxclNSaVZtQmR2S0N0M3Fk?=
 =?utf-8?B?UWNVaVV3NkkvRVdxYTM0MGVVOFI1RmFucTd1UDVmQkJHenArSkR6aDNxL3Bw?=
 =?utf-8?B?M1QvOHU2SDQzczhmWWRMUUlad0ZSUW9SOTZFNmdRemVQVW40ODFJMlF2YkE5?=
 =?utf-8?B?UFlJeTU3RGpoSnlMclR3eFBwTUlTMUJwSkM5eTdwYU0wZ2x0UzNxaXQ1QUs1?=
 =?utf-8?B?R09KbkNXWEI5ZGhLRGVyTUpoMEVqdzB6Y3V3WnM0WXZqMEhZOWcvMnlnTlN0?=
 =?utf-8?B?RlV6YjB4dlhQbVltNTR4UHJCeEZwUFRxWTFBOFVIVTJpWS9YUXdSVUV4MFd1?=
 =?utf-8?B?UmlRQ0NKZ3ZYakFVM0hVRnNIak9JTE1qVlBtZGxsZklPd1hJVWlUTFJUcFZW?=
 =?utf-8?B?VERHZjdscHZUQXQzaHNLWHdOdUkzQXo4bUttcXpKdU9vQjZva1ZpZnBVTEFY?=
 =?utf-8?B?V1M3WnVVd0Z1dlJHdUMyUHUzMVVuTTNWcVFtZkN0K2xDbHJHdytBSmNHODZN?=
 =?utf-8?B?V2JKa25kV0F2NVFvZnJmTWxJdXBTRllYKy9DT3ozSGRkUmFrbC82c3RmcTJv?=
 =?utf-8?B?akVDK3ByRExkVDNwVHBSU0NnUzdwaWptdVI3SG9uQUZyNk9FNGN1eWNkZjZ6?=
 =?utf-8?B?UGVVc2lSa1hWUFdRTjhBWHdicDRONk5rMGZWSmliOVpDZzhJOGpyMHo4WnpQ?=
 =?utf-8?B?RDFIL0kwREdmaUhISit4ZE8zN3JMT3VOeENFbmg1UEViQzFsWnBLRWRMY1U5?=
 =?utf-8?B?T2JuUkxFMmIrNGhBaGh5MXJZTE9HVUlOSHNVVnZGQmJsWmk2S2kzTWdnbUMv?=
 =?utf-8?B?NDN5TnBuTXIxcE9ZaVhvM01TaGdzRmVJUlA4QVBTYitYamdXdXhBVGVaZzYz?=
 =?utf-8?B?UktKQ2RGQTdjRUdkVVZYK3BISjdRbExnb3JldGkzaE9ZWXFYN3dNNzRaZHRT?=
 =?utf-8?B?TVRFblRSV0VLYzIwbGNkWHR5ZnlLR0w1ZnNRTDVHWFVhdnM1MmZIbncrbS9i?=
 =?utf-8?B?TnN2TFRnTDdvSmt0WUwwQ0FvS0h4Skt2ZVJyWXgvdStXUXVreExVVmRHQ29B?=
 =?utf-8?B?dEpSUmJOZEJwZ3c2UjhWeStta2ZOVTJWeDBKOXhFUnE3L0V0QkpDVjFmVmxj?=
 =?utf-8?B?T3JGeU5rcVlmVFlkUlpQUlZUMXBtbWRtR0pnYnZ3K0lTZ3Fpdk1kWDNVdDBJ?=
 =?utf-8?B?UTJnRkR6LzVXcHBGWnZsMVQwWnNJNHB2RTNJd0J3RVc5ckhKT1k2SmYwLzBj?=
 =?utf-8?B?M0FFMXFQejJMcDNxT1o1bmFaY21Pck1HMEZISzhIUzFsUGJLZUtKZz09?=
X-OriginatorOrg: amd.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 102534fd-ee60-456f-de85-08da141b67f2
X-MS-Exchange-CrossTenant-AuthSource: BN9PR12MB5115.namprd12.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 01 Apr 2022 20:08:36.9019
 (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: tgg9i3FXs7OVQZRpagmfav/jVdJhxfdMXZ0Lzw1pzFR9DGk1PlIApNS5TuwI71ExHTpRNg3Uo8WUqDr97Z4w3Q==
X-MS-Exchange-Transport-CrossTenantHeadersStamped: BN8PR12MB2929
X-Spam-Status: No, score=-2.1 required=5.0 tests=BAYES_00,DKIM_SIGNED,
        DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,NICE_REPLY_A,RCVD_IN_MSPIKE_H2,
        SPF_HELO_PASS,SPF_PASS,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-ext4.vger.kernel.org>
X-Mailing-List: linux-ext4@vger.kernel.org


On 2022-03-31 04:53, Christoph Hellwig wrote:
>> -	page = vm_normal_page(vma, addr, pte);
>> +	page = vm_normal_lru_page(vma, addr, pte);
> Why can't this deal with ZONE_DEVICE pages?  It certainly has
> nothing do with a LRU I think.  In fact being able to have
> stats that count say the number of device pages here would
> probably be useful at some point.

Maybe at some point. However, this is in a function called 
"can_gather_numa_stats". There are no meaningful NUMA stats for device 
pages. I agree that the name "vm_normal_lru_page" is not optimal in this 
case.


>
> In general I find the vm_normal_lru_page vs vm_normal_page
> API highly confusing.  An explicit check for zone device pages
> in the dozen or so spots that care has a much better documentation
> value, especially if accompanied by comments where it isn't entirely
> obvious.

OK. We can do that. It would solve the function naming problem, and we'd 
have more visibility of device page handling in more places in the 
kernel, which has educational value.

Regards,
   Felix


>
>>   		page = follow_page(vma, addr,
>> -				FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE);
>> +				FOLL_GET | FOLL_MIGRATION | FOLL_REMOTE | FOLL_LRU);
> Overly long line here.
>
>> +/*
>> + * NOTE: Technically this should goto check_pfn label. However, page->_mapcount
>> + * is never incremented for device pages that are mmap through DAX mechanism
>> + * using pmem driver mounted into ext4 filesystem. When these pages are unmap,
>> + * zap_pte_range is called and vm_normal_page return a valid page with
>> + * page_mapcount() = 0, before page_remove_rmap is called.
>> + */
> Please properly indent comments.
>
>> + * zone, as long as the pte's are present and vm_normal_lru_page() succeeds. These
>>    * pages also get pinned.
> Another overly long line here.