Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Message-ID: <51d0b44e-c1d1-a8e0-50cb-df9386a0f039@oracle.com>
Date:   Fri, 22 Oct 2021 23:11:42 -0700
User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:91.0)
 Gecko/20100101 Thunderbird/91.2.0
Subject: Re: [PATCH v2] mm: Optimise put_pages_list()
Content-Language: en-US
To:     Matthew Wilcox <willy@infradead.org>
Cc:     Andrew Morton <akpm@linux-foundation.org>,
        Mel Gorman <mgorman@techsingularity.net>, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
References: <20211007192138.561673-1-willy@infradead.org>
 <cb85b8a6-b82f-3054-5d76-57af018d6b2a@oracle.com>
 <YXNhx/IYJGVR1ZOH@casper.infradead.org>
From:   Anthony Yznaga <anthony.yznaga@oracle.com>
In-Reply-To: <YXNhx/IYJGVR1ZOH@casper.infradead.org>
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?NlJHTitLVEZwSTg4eENxTytMb3orRWk0T2Y3cjdkV2lMUlZvajFlTlZjbDNH?=
 =?utf-8?B?cW5BVm52ZzN6cVhROTZOYWRVNDJkMTlCS3BKaHpPa1BFUFJ3cktmQjhZZmhh?=
 =?utf-8?B?QzQwMzJQRVE3MTJ0dXZNZXhmdkptQWd3b0NoNENPM3E0cXB4bzdzWEF3R2tw?=
 =?utf-8?B?bjVjR1hDUG1pRk1TNDNPeTBvbEdDV1p0NFFJczhZMEt2bXpTUkF4cG9jeXdx?=
 =?utf-8?B?dUJoSWo2a0VzOUwvMENUcjBiUHpKVG1aNjBuWmJ5bFc1S092ZVcvK25pTFAz?=
 =?utf-8?B?a1JhQ3FtTjJZd2FwcmFNckxURjMxajVIZEdXRGRDL0I2cDh2aFNXZ056U0tz?=
 =?utf-8?B?elpnWHBDRThKNk0xclQvYXBZZXhIVmhFdjZuU1NoM2NvdDdSVjRUbitibElZ?=
 =?utf-8?B?UzBodDVmM2lhaGVxY1lBSFRRNk8vYm44MlJaajN0aWIrZkZQZjJoUmlXTXJx?=
 =?utf-8?B?clpadE5ZQWI1YWJOa3pRcE05UWc4KzhFZzRXbFV0eGlCeVVJNTdEbTV5b3ln?=
 =?utf-8?B?bTZaZklWUHU2eVhHY0kxZ3NaTjhwdXgvYlJxcndaOEZrVzJwUG12aXlTazNV?=
 =?utf-8?B?UHBQS1FPQjNtTE85RU1ZZWFuN0FLVU5HM2xTcGtCbkdJMU1IbzhxeUlIOW5J?=
 =?utf-8?B?b29ZZWhJRnVJRjB0KzNhSXlpL3lYcngzdnJRNGVzclZOWVdXYmVjZVF3eUlB?=
 =?utf-8?B?YWZETkZBWEd1Tzc1M3F5L2wvQTgwNVpUT2E0NlZjSjl0d245WmdIa1p0MFZz?=
 =?utf-8?B?bkRSbG1sZEFhNnJ2K2hTNkJhYzZlV3Z4K1pHc0hYMUN3WnBnUkFEcklKdkdu?=
 =?utf-8?B?SFo0YVRWS2hyUWMrNEJqdEI0clhrdW9Db0VScGZlTDBkQzJLTXlNVmt1VEZX?=
 =?utf-8?B?QmNOL0VzUi9ZY1gxSUFjQXovZ2l2R2dmRSt1OXU1Y21HdUhkN24xb3ZCeVhk?=
 =?utf-8?B?OEFIQXFGYWF2aXplMk9BeE1WVmpoT2tySVlQYnQ3TEF3TG8xT0FtNHVxcVhv?=
 =?utf-8?B?MUZBbWVteFNLZGh5cGJ0N2JDQjVEM3BxeUdUd3FycEJyTDV3VDdwbXJOUzZt?=
 =?utf-8?B?bVlXMkduVHBlazBrWThJd3A4L3lSaHlRbnFSajBVbGh3Z0FMOS8rS3F2Wk1V?=
 =?utf-8?B?TVI4ZTBFSGJkT3pLWmxudXkxYjdrWUQ3NG5oZXg1WG1sWm9uVi82TDEyTUdz?=
 =?utf-8?B?eWx0T1d3NXFnWmN4bXRoRWs2WGtrYnJMREZJbFB3UmdqcmZ4VDgwRWdLdnBU?=
 =?utf-8?B?V2g4Z1lBVzdjYmcvcG9mdDFqalRTNXlMSXBuellSMi9YWHhKaDI3TFk5cHA1?=
 =?utf-8?B?di9IaFI1aXNLdlN4UUhSeFBRRXRDYmI4ZURLWCs0aVArR1E4OWRhTHI4bk84?=
 =?utf-8?B?SzMydHVVTUdRV0MwdjNGemlGS3lHTGlCcEg2SnUyOVlENXl0S0NhL0V0Y2hL?=
 =?utf-8?B?aVZCSzdDZ3RsYTR5SzJ2eXBZdVhWbEtJTHNjRDhxeStYUHJnTlNjd2tGeUZC?=
 =?utf-8?B?OTl4RmczNGRIeW5hUmhHUENycFhaMjR2RXNxRXdQQWNmOG04NmVtK25ZWmJ2?=
 =?utf-8?B?cFlnNTFYRWU5UmU3dUhMbmIxcVowa3pFZzNQcFgzM3lyRFNqVU1Za080TzlN?=
 =?utf-8?B?UDhNdzk3V0hBU2dXT3RxYk1oN3ZXcnoyZTlPKzQ1NENIdEJES3J4Zk1UMDNJ?=
 =?utf-8?B?TTViNnJsL0Z1ZzNsVVdkL0FXU3lzQTl4Mm9jUW9oU2wrbkhyUW82NTdsRVFK?=
 =?utf-8?B?Rm13VmVxN1ZMU2VLQVdrK2JDS1B0Q1paWHdSdU9hV3Q2UXhmZU5ySmVkMXVN?=
 =?utf-8?B?RUloMEIwWkkvb2w5a25FOURSeGZsOVpUclpIZE1BeXVwVGd2YXJ6UXh4UGR6?=
 =?utf-8?B?eHVybmE1UTlDMjRZM1o5bFE4dXM4bGk0VUgzRnM1anhnYk1lZnBibElGRDRI?=
 =?utf-8?B?S2xDeDZKNUF3cWtIUkhKZDZmbkVHYzNhUlFaOGhuS25EM0s0dDFWdzlVZXVy?=
 =?utf-8?B?aytxU2NGTmZEWVp5Uk02LzFWbzVhS1lwN0Rqc1lzcVZDcm5sR0VQM3VLcW5o?=
 =?utf-8?B?SlZLblZwZ0RBd3lYNkFFSllwWWh4azdJUXZXVnBoSHFsNVZyN1Vyd0Z0VlRP?=
 =?utf-8?B?clprSWlYVHJlUElkdE0xL1RCRmFXcnVVY2ZHY3E0WjU4UzRLUmxqRUhzNjZK?=
 =?utf-8?B?dk5MOTN0eTJMVHJtYnpLcWJTYjVjRTQwdk1rNWhGejlQVlcyWVhNWW5FV1Jz?=
 =?utf-8?B?b1p2RzdlaHV1aStVLzlhMGVDaGVnPT0=?=
X-OriginatorOrg: oracle.com
X-MS-Exchange-CrossTenant-Network-Message-Id: 9373bc46-ac9c-402c-6f05-08d995ebfe65
X-MS-Exchange-CrossTenant-AuthSource: BYAPR10MB2438.namprd10.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Internal
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 23 Oct 2021 06:11:46.8508
 (UTC)
X-MS-Exchange-CrossTenant-FromEntityHeader: Hosted
X-MS-Exchange-CrossTenant-Id: 4e2c6054-71cb-48f1-bd6c-3a9705aca71b
X-MS-Exchange-CrossTenant-MailboxType: HOSTED
X-MS-Exchange-CrossTenant-UserPrincipalName: mcpBzCJnurhQ90660o2XOhKmRrnY3T3BOwiUnpWkPiqH4dKc/4+EZ1c6CrLp5VTRLtsc+lwEzNVCeIba5+6GRiLtgvi+3aMWRkyTyqX/ieM=
X-MS-Exchange-Transport-CrossTenantHeadersStamped: SJ0PR10MB5647
X-Proofpoint-Virus-Version: vendor=nai engine=6300 definitions=10145 signatures=668683
X-Proofpoint-Spam-Details: rule=notspam policy=default score=0 adultscore=0 bulkscore=0 mlxscore=0
 phishscore=0 suspectscore=0 malwarescore=0 mlxlogscore=999 spamscore=0
 classifier=spam adjust=0 reason=mlx scancount=1 engine=8.12.0-2109230001
 definitions=main-2110230037
X-Proofpoint-ORIG-GUID: BpMVvysWJvLunymFVxxw5EAT7cwigkhL
X-Proofpoint-GUID: BpMVvysWJvLunymFVxxw5EAT7cwigkhL
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org


On 10/22/21 6:13 PM, Matthew Wilcox wrote:
> On Fri, Oct 22, 2021 at 04:26:59PM -0700, Anthony Yznaga wrote:
>> On 10/7/21 12:21 PM, Matthew Wilcox (Oracle) wrote:
>>> Instead of calling put_page() one page at a time, pop pages off
>>> the list if their refcount was too high and pass the remainder to
>>> put_unref_page_list().  This should be a speed improvement, but I have
>>> no measurements to support that.  Current callers do not care about
>>> performance, but I hope to add some which do.
>>>
>>> Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
>>> ---
>>> v2:
>>>    - Handle compound pages (Mel)
>>>    - Comment why we don't need to handle PageLRU
>>>    - Added call to __ClearPageWaiters(), matching that in release_pages()
>>>
>>>    mm/swap.c | 23 ++++++++++++++++-------
>>>    1 file changed, 16 insertions(+), 7 deletions(-)
>>>
>>> diff --git a/mm/swap.c b/mm/swap.c
>>> index af3cad4e5378..9f334d503fd2 100644
>>> --- a/mm/swap.c
>>> +++ b/mm/swap.c
>>> @@ -134,18 +134,27 @@ EXPORT_SYMBOL(__put_page);
>>>     * put_pages_list() - release a list of pages
>>>     * @pages: list of pages threaded on page->lru
>>>     *
>>> - * Release a list of pages which are strung together on page.lru.  Currently
>>> - * used by read_cache_pages() and related error recovery code.
>>> + * Release a list of pages which are strung together on page.lru.
>>>     */
>>>    void put_pages_list(struct list_head *pages)
>>>    {
>>> -	while (!list_empty(pages)) {
>>> -		struct page *victim;
>>> +	struct page *page, *next;
>>> -		victim = lru_to_page(pages);
>>> -		list_del(&victim->lru);
>>> -		put_page(victim);
>>> +	list_for_each_entry_safe(page, next, pages, lru) {
>>> +		if (!put_page_testzero(page)) {
>>> +			list_del(&page->lru);
>>> +			continue;
>>> +		}
>>
>> I know that compound pages are not currently passed to put_pages_list(),
>> but I assume the put_page_testzero() should only be done on the head
>> page similar to release_pages()?
> Fun fact about pages: You can't put a tail page on an LRU list.  Why?
>
> struct page {
> ...
>          union {
>                  struct {        /* Page cache and anonymous pages */
>                          struct list_head lru;
> ...
>                  struct {        /* Tail pages of compound page */
>                          unsigned long compound_head;    /* Bit zero is set */
>
> so if you try to put a tail page on the LRU list, it becomes no longer
> a tail page.

Ah, makes sense.  Thanks!

In that case here's my r-b:

Reviewed-by: Anthony Yznaga <anthony.yznaga@oracle.com>

Anthony