Re: [PATCH v3 08/14] mm: thp: enable thp migration in generic path

[Zi Yan]

On 9 Feb 2017, at 3:15, Naoya Horiguchi wrote:

> On Sun, Feb 05, 2017 at 11:12:46AM -0500, Zi Yan wrote:
>> From: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
>>
>> This patch adds thp migration's core code, including conversions
>> between a PMD entry and a swap entry, setting PMD migration entry,
>> removing PMD migration entry, and waiting on PMD migration entries.
>>
>> This patch makes it possible to support thp migration.
>> If you fail to allocate a destination page as a thp, you just split
>> the source thp as we do now, and then enter the normal page migration.
>> If you succeed to allocate destination thp, you enter thp migration.
>> Subsequent patches actually enable thp migration for each caller of
>> page migration by allowing its get_new_page() callback to
>> allocate thps.
>>
>> ChangeLog v1 -> v2:
>> - support pte-mapped thp, doubly-mapped thp
>>
>> Signed-off-by: Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>
>>
>> ChangeLog v2 -> v3:
>> - use page_vma_mapped_walk()
>>
>> Signed-off-by: Zi Yan <zi.yan@xxxxxxxxxxxxxx>
>> ---
>>  arch/x86/include/asm/pgtable_64.h |   2 +
>>  include/linux/swapops.h           |  70 +++++++++++++++++-
>>  mm/huge_memory.c                  | 151 ++++++++++++++++++++++++++++++++++----
>>  mm/migrate.c                      |  29 +++++++-
>>  mm/page_vma_mapped.c              |  13 +++-
>>  mm/pgtable-generic.c              |   3 +-
>>  mm/rmap.c                         |  14 +++-
>>  7 files changed, 259 insertions(+), 23 deletions(-)
>>
> ...
>> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
>> index 6893c47428b6..fd54bbdc16cf 100644
>> --- a/mm/huge_memory.c
>> +++ b/mm/huge_memory.c
>> @@ -1613,20 +1613,51 @@ int __zap_huge_pmd_locked(struct mmu_gather *tlb, struct vm_area_struct *vma,
>>  		atomic_long_dec(&tlb->mm->nr_ptes);
>>  		tlb_remove_page_size(tlb, pmd_page(orig_pmd), HPAGE_PMD_SIZE);
>>  	} else {
>> -		struct page *page = pmd_page(orig_pmd);
>> -		page_remove_rmap(page, true);
>> -		VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
>> -		VM_BUG_ON_PAGE(!PageHead(page), page);
>> -		if (PageAnon(page)) {
>> -			pgtable_t pgtable;
>> -			pgtable = pgtable_trans_huge_withdraw(tlb->mm, pmd);
>> -			pte_free(tlb->mm, pgtable);
>> -			atomic_long_dec(&tlb->mm->nr_ptes);
>> -			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
>> +		struct page *page;
>> +		int migration = 0;
>> +
>> +		if (!is_pmd_migration_entry(orig_pmd)) {
>> +			page = pmd_page(orig_pmd);
>> +			VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
>> +			VM_BUG_ON_PAGE(!PageHead(page), page);
>> +			page_remove_rmap(page, true);
>
>> +			if (PageAnon(page)) {
>> +				pgtable_t pgtable;
>> +
>> +				pgtable = pgtable_trans_huge_withdraw(tlb->mm,
>> +								      pmd);
>> +				pte_free(tlb->mm, pgtable);
>> +				atomic_long_dec(&tlb->mm->nr_ptes);
>> +				add_mm_counter(tlb->mm, MM_ANONPAGES,
>> +					       -HPAGE_PMD_NR);
>> +			} else {
>> +				if (arch_needs_pgtable_deposit())
>> +					zap_deposited_table(tlb->mm, pmd);
>> +				add_mm_counter(tlb->mm, MM_FILEPAGES,
>> +					       -HPAGE_PMD_NR);
>> +			}
>
> This block is exactly equal to the one in else block below,
> So you can factor out into some function.

Of course, I will do that.

>
>>  		} else {
>> -			if (arch_needs_pgtable_deposit())
>> -				zap_deposited_table(tlb->mm, pmd);
>> -			add_mm_counter(tlb->mm, MM_FILEPAGES, -HPAGE_PMD_NR);
>> +			swp_entry_t entry;
>> +
>> +			entry = pmd_to_swp_entry(orig_pmd);
>> +			page = pfn_to_page(swp_offset(entry));
>
>> +			if (PageAnon(page)) {
>> +				pgtable_t pgtable;
>> +
>> +				pgtable = pgtable_trans_huge_withdraw(tlb->mm,
>> +								      pmd);
>> +				pte_free(tlb->mm, pgtable);
>> +				atomic_long_dec(&tlb->mm->nr_ptes);
>> +				add_mm_counter(tlb->mm, MM_ANONPAGES,
>> +					       -HPAGE_PMD_NR);
>> +			} else {
>> +				if (arch_needs_pgtable_deposit())
>> +					zap_deposited_table(tlb->mm, pmd);
>> +				add_mm_counter(tlb->mm, MM_FILEPAGES,
>> +					       -HPAGE_PMD_NR);
>> +			}
>
>> +			free_swap_and_cache(entry); /* waring in failure? */
>> +			migration = 1;
>>  		}
>>  		tlb_remove_page_size(tlb, page, HPAGE_PMD_SIZE);
>>  	}
>> @@ -2634,3 +2665,97 @@ static int __init split_huge_pages_debugfs(void)
>>  }
>>  late_initcall(split_huge_pages_debugfs);
>>  #endif
>> +
>> +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
>> +void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
>> +		struct page *page)
>> +{
>> +	struct vm_area_struct *vma = pvmw->vma;
>> +	struct mm_struct *mm = vma->vm_mm;
>> +	unsigned long address = pvmw->address;
>> +	pmd_t pmdval;
>> +	swp_entry_t entry;
>> +
>> +	if (pvmw->pmd && !pvmw->pte) {
>> +		pmd_t pmdswp;
>> +
>> +		mmu_notifier_invalidate_range_start(mm, address,
>> +				address + HPAGE_PMD_SIZE);
>
> Don't you have to put mmu_notifier_invalidate_range_* outside this if block?

I think I need to add mmu_notifier_invalidate_page() in else block.

Because Kirill's page_vma_mapped_walk() iterates each PMD or PTE.
In set_pmd_migration_etnry(), if the page is PMD-mapped, it will be called once
with PMD, then mmu_notifier_invalidate_range_* can be used. On the other hand,
if the page is PTE-mapped, the function will be called 1~512 times depending
on how many PTEs are present. mmu_notifier_invalidate_range_* is not suitable.
mmu_notifier_invalidate_page() on the corresponding subpage should work.



--
Best Regards
Yan Zi

Attachment: signature.asc
Description: OpenPGP digital signature