linux-kernel - Re: [PATCH] gup: optimize longterm pin_user

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [day] [month] [year] [list]

Message-ID: <3678020c-8b67-4ad7-a859-59d301784883@arm.com>
Date: Fri, 30 May 2025 15:42:10 +0530
From: Dev Jain <dev.jain@....com>
To: lizhe.67@...edance.com
Cc: akpm@...ux-foundation.org, david@...hat.com, jgg@...pe.ca,
 jhubbard@...dia.com, linux-kernel@...r.kernel.org, linux-mm@...ck.org,
 muchun.song@...ux.dev, peterx@...hat.com, ryan.roberts@....com
Subject: Re: [PATCH] gup: optimize longterm pin_user_pages() for large folio


On 30/05/25 3:34 pm, lizhe.67@...edance.com wrote:
> On Fri, 30 May 2025 15:23:49 +0530, dev.jain@....com wrote:
>
>> On 30/05/25 2:53 pm, lizhe.67@...edance.com wrote:
>>> From: Li Zhe<lizhe.67@...edance.com>
>>>
>>> In the current implementation of the longterm pin_user_pages() function,
>>> we invoke the collect_longterm_unpinnable_folios() function. This function
>>> iterates through the list to check whether each folio belongs to the
>>> "longterm_unpinnabled" category. The folios in this list essentially
>>> correspond to a contiguous region of user-space addresses, with each folio
>>> representing a physical address in increments of PAGESIZE. If this
>>> user-space address range is mapped with large folio, we can optimize the
>>> performance of function pin_user_pages() by reducing the number of if-else
>>> branches and the frequency of memory accesses using READ_ONCE. This patch
>>> leverages this approach to achieve performance improvements.
>>>
>>> The performance test results obtained through the gup_test tool from the
>>> kernel source tree are as follows. We achieve an improvement of over 75%
>>> for large folio with pagesize=2M. For normal page, we have only observed
>>> a very slight degradation in performance.
>>
>> Thanks for the patch! I have no idea on GUP but in my limited understanding
>> the patch looks fine, let's wait for more comments.
>>
>> [----]
>>
>>>    }
>>>    
>>> +static struct folio *pofs_next_folio(struct folio *folio,
>>> +				struct pages_or_folios *pofs, long *index_ptr)
>>> +{
>>> +	long i = *index_ptr + 1;
>>> +	unsigned long nr_pages = folio_nr_pages(folio);
>>> +
>>> +	if (!pofs->has_folios)
>>> +		while ((i < pofs->nr_entries) &&
>>> +			/* Is this page part of this folio? */
>>> +			(folio_page_idx(folio, pofs->pages[i]) < nr_pages))
>>> +			i++;
>>> +
>>> +	if (unlikely(i == pofs->nr_entries))
>>> +		return NULL;
>>> +	*index_ptr = i;
>>> +
>>> +	return pofs_get_folio(pofs, i);
>>> +}
>>> +
>>>    /*
>>>     * Returns the number of collected folios. Return value is always >= 0.
>>>     */
>>> @@ -2324,16 +2343,12 @@ static void collect_longterm_unpinnable_folios(
>>>    		struct list_head *movable_folio_list,
>>>    		struct pages_or_folios *pofs)
>>>    {
>>> -	struct folio *prev_folio = NULL;
>>>    	bool drain_allow = true;
>>> -	unsigned long i;
>>> -
>>> -	for (i = 0; i < pofs->nr_entries; i++) {
>>> -		struct folio *folio = pofs_get_folio(pofs, i);
>>> +	long i = 0;
>>
>> Why not unsigned long?
> This is because I want to match the type of pages_or_folios->nr_entries.


Ah right, although I wonder why we are not using unsigned long in the first place...


>
> Thanks,
> Zhe