Re: [RFC PATCH v3 09/35] mm: Track the freepage migratetype of pages accurately

[Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com>]

(2013/09/03 17:45), Srivatsa S. Bhat wrote:
> On 09/03/2013 12:08 PM, Yasuaki Ishimatsu wrote:
>> (2013/08/30 22:16), Srivatsa S. Bhat wrote:
>>> Due to the region-wise ordering of the pages in the buddy allocator's
>>> free lists, whenever we want to delete a free pageblock from a free list
>>> (for ex: when moving blocks of pages from one list to the other), we need
>>> to be able to tell the buddy allocator exactly which migratetype it
>>> belongs
>>> to. For that purpose, we can use the page's freepage migratetype
>>> (which is
>>> maintained in the page's ->index field).
>>>
>>> So, while splitting up higher order pages into smaller ones as part of
>>> buddy
>>> operations, keep the new head pages updated with the correct freepage
>>> migratetype information (because we depend on tracking this info
>>> accurately,
>>> as outlined above).
>>>
>>> Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
>>> ---
>>>
>>>    mm/page_alloc.c |    7 +++++++
>>>    1 file changed, 7 insertions(+)
>>>
>>> diff --git a/mm/page_alloc.c b/mm/page_alloc.c
>>> index 398b62c..b4b1275 100644
>>> --- a/mm/page_alloc.c
>>> +++ b/mm/page_alloc.c
>>> @@ -947,6 +947,13 @@ static inline void expand(struct zone *zone,
>>> struct page *page,
>>>            add_to_freelist(&page[size], &area->free_list[migratetype]);
>>>            area->nr_free++;
>>>            set_page_order(&page[size], high);
>>> +
>>> +        /*
>>> +         * Freepage migratetype is tracked using the index field of the
>>> +         * first page of the block. So we need to update the new first
>>> +         * page, when changing the page order.
>>> +         */
>>> +        set_freepage_migratetype(&page[size], migratetype);
>>>        }
>>>    }
>>>
>>>
>>
>> It this patch a bug fix patch?
>> If so, I want you to split the patch from the patch-set.
>>
>
> No, its not a bug-fix. We need to take care of this only when using the
> sorted-buddy design to maintain the freelists, which is introduced only in
> this patchset. So mainline doesn't need this patch.
>
> In mainline, we can delete a page from a buddy freelist by simply calling
> list_del() by passing a pointer to page->lru. It doesn't matter which freelist
> the page was belonging to. However, in the sorted-buddy design introduced
> in this patchset, we also need to know which particular freelist we are
> deleting that page from, because apart from breaking the ->lru link from
> the linked-list, we also need to update certain other things such as the
> region->page_block pointer etc, which are part of that particular freelist.
> Thus, it becomes essential to know which freelist we are deleting the page
> from. And for that, we need this patch to maintain that information accurately
> even during buddy operations such as splitting buddy pages in expand().

I may be wrong because I do not know this part clearly.

Original code is here:

---
static inline void expand(struct zone *zone, struct page *page,
	int low, int high, struct free_area *area,
	int migratetype)
{
...
		list_add(&page[size].lru, &area->free_list[migratetype]);
		area->nr_free++;
		set_page_order(&page[size], high);
---

It seems that migratietype of page[size] page is changed. So even if not
applying your patch, I think migratetype of the page should be changed.

thanks,
Yasuaki Ishimatsu

>
> Regards,
> Srivatsa S. Bhat
>


--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>