diff mbox series

[v2,1/5] mm: Non-pmd-mappable, large folios for folio_add_new_anon_rmap()

Message ID 20230703135330.1865927-2-ryan.roberts@arm.com
State New
Headers
Series variable-order, large folios for anonymous memory |

Commit Message

Ryan Roberts July 3, 2023, 1:53 p.m. UTC 
  In preparation for FLEXIBLE_THP support, improve
folio_add_new_anon_rmap() to allow a non-pmd-mappable, large folio to be
passed to it. In this case, all contained pages are accounted using the
"small" pages scheme.

Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
---
 mm/rmap.c | 26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)

Comments

Yu Zhao July 3, 2023, 7:05 p.m. UTC | #1 
On Mon, Jul 3, 2023 at 7:53 AM Ryan Roberts <ryan.roberts@arm.com> wrote:
>
> In preparation for FLEXIBLE_THP support, improve
> folio_add_new_anon_rmap() to allow a non-pmd-mappable, large folio to be
> passed to it. In this case, all contained pages are accounted using the
> "small" pages scheme.

Nit: In this case, all *subpages*  are accounted using the *order-0
folio* (or base page) scheme.

> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>

Reviewed-by: Yu Zhao <yuzhao@google.com>

>  mm/rmap.c | 26 +++++++++++++++++++-------
>  1 file changed, 19 insertions(+), 7 deletions(-)
>
> diff --git a/mm/rmap.c b/mm/rmap.c
> index 1d8369549424..82ef5ba363d1 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -1278,31 +1278,43 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
>   * This means the inc-and-test can be bypassed.
>   * The folio does not have to be locked.
>   *
> - * If the folio is large, it is accounted as a THP.  As the folio
> + * If the folio is pmd-mappable, it is accounted as a THP.  As the folio
>   * is new, it's assumed to be mapped exclusively by a single process.
>   */
>  void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
>                 unsigned long address)
>  {
> -       int nr;
> +       int nr = folio_nr_pages(folio);
> +       int i;
> +       struct page *page;
>
> -       VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
> +       VM_BUG_ON_VMA(address < vma->vm_start ||
> +                       address + (nr << PAGE_SHIFT) > vma->vm_end, vma);
>         __folio_set_swapbacked(folio);
>
> -       if (likely(!folio_test_pmd_mappable(folio))) {
> +       if (!folio_test_large(folio)) {
>                 /* increment count (starts at -1) */
>                 atomic_set(&folio->_mapcount, 0);
> -               nr = 1;
> +               __page_set_anon_rmap(folio, &folio->page, vma, address, 1);
> +       } else if (!folio_test_pmd_mappable(folio)) {
> +               /* increment count (starts at 0) */
> +               atomic_set(&folio->_nr_pages_mapped, nr);
> +
> +               page = &folio->page;
> +               for (i = 0; i < nr; i++, page++, address += PAGE_SIZE) {
> +                       /* increment count (starts at -1) */
> +                       atomic_set(&page->_mapcount, 0);
> +                       __page_set_anon_rmap(folio, page, vma, address, 1);
> +               }

Nit: use folio_page(), e.g.,

  } else if (!folio_test_pmd_mappable(folio)) {
    int i;

    for (i = 0; i < nr; i++) {
      struct page *page = folio_page(folio, i);

      /* increment count (starts at -1) */
      atomic_set(&page->_mapcount, 0);
      __page_set_anon_rmap(folio, page, vma, address + PAGE_SIZE * i, 1);
    }
    /* increment count (starts at 0) */
    atomic_set(&folio->_nr_pages_mapped, nr);
  } else {

>         } else {
>                 /* increment count (starts at -1) */
>                 atomic_set(&folio->_entire_mapcount, 0);
>                 atomic_set(&folio->_nr_pages_mapped, COMPOUND_MAPPED);
> -               nr = folio_nr_pages(folio);
>                 __lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr);
> +               __page_set_anon_rmap(folio, &folio->page, vma, address, 1);
>         }
>
>         __lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr);
> -       __page_set_anon_rmap(folio, &folio->page, vma, address, 1);
>  }
Yin Fengwei July 4, 2023, 2:13 a.m. UTC | #2 
On 7/4/2023 3:05 AM, Yu Zhao wrote:
> On Mon, Jul 3, 2023 at 7:53 AM Ryan Roberts <ryan.roberts@arm.com> wrote:
>>
>> In preparation for FLEXIBLE_THP support, improve
>> folio_add_new_anon_rmap() to allow a non-pmd-mappable, large folio to be
>> passed to it. In this case, all contained pages are accounted using the
>> "small" pages scheme.
> 
> Nit: In this case, all *subpages*  are accounted using the *order-0
> folio* (or base page) scheme.
Matthew suggested not to use subpage with folio. Using page with folio:
https://lore.kernel.org/linux-mm/Y9qiS%2FIxZOMx62t6@casper.infradead.org/

> 
>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
> 
> Reviewed-by: Yu Zhao <yuzhao@google.com>
> 
>>  mm/rmap.c | 26 +++++++++++++++++++-------
>>  1 file changed, 19 insertions(+), 7 deletions(-)
>>
>> diff --git a/mm/rmap.c b/mm/rmap.c
>> index 1d8369549424..82ef5ba363d1 100644
>> --- a/mm/rmap.c
>> +++ b/mm/rmap.c
>> @@ -1278,31 +1278,43 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
>>   * This means the inc-and-test can be bypassed.
>>   * The folio does not have to be locked.
>>   *
>> - * If the folio is large, it is accounted as a THP.  As the folio
>> + * If the folio is pmd-mappable, it is accounted as a THP.  As the folio
>>   * is new, it's assumed to be mapped exclusively by a single process.
>>   */
>>  void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
>>                 unsigned long address)
>>  {
>> -       int nr;
>> +       int nr = folio_nr_pages(folio);
>> +       int i;
>> +       struct page *page;
>>
>> -       VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
>> +       VM_BUG_ON_VMA(address < vma->vm_start ||
>> +                       address + (nr << PAGE_SHIFT) > vma->vm_end, vma);
>>         __folio_set_swapbacked(folio);
>>
>> -       if (likely(!folio_test_pmd_mappable(folio))) {
>> +       if (!folio_test_large(folio)) {
>>                 /* increment count (starts at -1) */
>>                 atomic_set(&folio->_mapcount, 0);
>> -               nr = 1;
>> +               __page_set_anon_rmap(folio, &folio->page, vma, address, 1);
>> +       } else if (!folio_test_pmd_mappable(folio)) {
>> +               /* increment count (starts at 0) */
>> +               atomic_set(&folio->_nr_pages_mapped, nr);
>> +
>> +               page = &folio->page;
>> +               for (i = 0; i < nr; i++, page++, address += PAGE_SIZE) {
>> +                       /* increment count (starts at -1) */
>> +                       atomic_set(&page->_mapcount, 0);
>> +                       __page_set_anon_rmap(folio, page, vma, address, 1);
>> +               }
> 
> Nit: use folio_page(), e.g.,
> 
>   } else if (!folio_test_pmd_mappable(folio)) {
>     int i;
> 
>     for (i = 0; i < nr; i++) {
>       struct page *page = folio_page(folio, i);
> 
>       /* increment count (starts at -1) */
>       atomic_set(&page->_mapcount, 0);
>       __page_set_anon_rmap(folio, page, vma, address + PAGE_SIZE * i, 1);
>     }
>     /* increment count (starts at 0) */
>     atomic_set(&folio->_nr_pages_mapped, nr);
>   } else {
> 
>>         } else {
>>                 /* increment count (starts at -1) */
>>                 atomic_set(&folio->_entire_mapcount, 0);
>>                 atomic_set(&folio->_nr_pages_mapped, COMPOUND_MAPPED);
>> -               nr = folio_nr_pages(folio);
>>                 __lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr);
>> +               __page_set_anon_rmap(folio, &folio->page, vma, address, 1);
>>         }
>>
>>         __lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr);
>> -       __page_set_anon_rmap(folio, &folio->page, vma, address, 1);
>>  }
Yin Fengwei July 4, 2023, 2:14 a.m. UTC | #3 
On 7/3/2023 9:53 PM, Ryan Roberts wrote:
> In preparation for FLEXIBLE_THP support, improve
> folio_add_new_anon_rmap() to allow a non-pmd-mappable, large folio to be
> passed to it. In this case, all contained pages are accounted using the
> "small" pages scheme.
> 
> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Yin, Fengwei <fengwei.yin@intel.com>

> ---
>  mm/rmap.c | 26 +++++++++++++++++++-------
>  1 file changed, 19 insertions(+), 7 deletions(-)
> 
> diff --git a/mm/rmap.c b/mm/rmap.c
> index 1d8369549424..82ef5ba363d1 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -1278,31 +1278,43 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
>   * This means the inc-and-test can be bypassed.
>   * The folio does not have to be locked.
>   *
> - * If the folio is large, it is accounted as a THP.  As the folio
> + * If the folio is pmd-mappable, it is accounted as a THP.  As the folio
>   * is new, it's assumed to be mapped exclusively by a single process.
>   */
>  void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
>  		unsigned long address)
>  {
> -	int nr;
> +	int nr = folio_nr_pages(folio);
> +	int i;
> +	struct page *page;
>  
> -	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
> +	VM_BUG_ON_VMA(address < vma->vm_start ||
> +			address + (nr << PAGE_SHIFT) > vma->vm_end, vma);
>  	__folio_set_swapbacked(folio);
>  
> -	if (likely(!folio_test_pmd_mappable(folio))) {
> +	if (!folio_test_large(folio)) {
>  		/* increment count (starts at -1) */
>  		atomic_set(&folio->_mapcount, 0);
> -		nr = 1;
> +		__page_set_anon_rmap(folio, &folio->page, vma, address, 1);
> +	} else if (!folio_test_pmd_mappable(folio)) {
> +		/* increment count (starts at 0) */
> +		atomic_set(&folio->_nr_pages_mapped, nr);
> +
> +		page = &folio->page;
> +		for (i = 0; i < nr; i++, page++, address += PAGE_SIZE) {
> +			/* increment count (starts at -1) */
> +			atomic_set(&page->_mapcount, 0);
> +			__page_set_anon_rmap(folio, page, vma, address, 1);
> +		}
>  	} else {
>  		/* increment count (starts at -1) */
>  		atomic_set(&folio->_entire_mapcount, 0);
>  		atomic_set(&folio->_nr_pages_mapped, COMPOUND_MAPPED);
> -		nr = folio_nr_pages(folio);
>  		__lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr);
> +		__page_set_anon_rmap(folio, &folio->page, vma, address, 1);
>  	}
>  
>  	__lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr);
> -	__page_set_anon_rmap(folio, &folio->page, vma, address, 1);
>  }
>  
>  /**
Ryan Roberts July 4, 2023, 11:19 a.m. UTC | #4 
On 04/07/2023 03:13, Yin, Fengwei wrote:
> 
> 
> On 7/4/2023 3:05 AM, Yu Zhao wrote:
>> On Mon, Jul 3, 2023 at 7:53 AM Ryan Roberts <ryan.roberts@arm.com> wrote:
>>>
>>> In preparation for FLEXIBLE_THP support, improve
>>> folio_add_new_anon_rmap() to allow a non-pmd-mappable, large folio to be
>>> passed to it. In this case, all contained pages are accounted using the
>>> "small" pages scheme.
>>
>> Nit: In this case, all *subpages*  are accounted using the *order-0
>> folio* (or base page) scheme.
> Matthew suggested not to use subpage with folio. Using page with folio:
> https://lore.kernel.org/linux-mm/Y9qiS%2FIxZOMx62t6@casper.infradead.org/

OK, I'll change this to "In this case, all contained pages are accounted using
the *order-0 folio* (or base page) scheme."

> 
>>
>>> Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
>>
>> Reviewed-by: Yu Zhao <yuzhao@google.com>

Thanks!

>>
>>>  mm/rmap.c | 26 +++++++++++++++++++-------
>>>  1 file changed, 19 insertions(+), 7 deletions(-)
>>>
>>> diff --git a/mm/rmap.c b/mm/rmap.c
>>> index 1d8369549424..82ef5ba363d1 100644
>>> --- a/mm/rmap.c
>>> +++ b/mm/rmap.c
>>> @@ -1278,31 +1278,43 @@ void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
>>>   * This means the inc-and-test can be bypassed.
>>>   * The folio does not have to be locked.
>>>   *
>>> - * If the folio is large, it is accounted as a THP.  As the folio
>>> + * If the folio is pmd-mappable, it is accounted as a THP.  As the folio
>>>   * is new, it's assumed to be mapped exclusively by a single process.
>>>   */
>>>  void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
>>>                 unsigned long address)
>>>  {
>>> -       int nr;
>>> +       int nr = folio_nr_pages(folio);
>>> +       int i;
>>> +       struct page *page;
>>>
>>> -       VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
>>> +       VM_BUG_ON_VMA(address < vma->vm_start ||
>>> +                       address + (nr << PAGE_SHIFT) > vma->vm_end, vma);
>>>         __folio_set_swapbacked(folio);
>>>
>>> -       if (likely(!folio_test_pmd_mappable(folio))) {
>>> +       if (!folio_test_large(folio)) {
>>>                 /* increment count (starts at -1) */
>>>                 atomic_set(&folio->_mapcount, 0);
>>> -               nr = 1;
>>> +               __page_set_anon_rmap(folio, &folio->page, vma, address, 1);
>>> +       } else if (!folio_test_pmd_mappable(folio)) {
>>> +               /* increment count (starts at 0) */
>>> +               atomic_set(&folio->_nr_pages_mapped, nr);
>>> +
>>> +               page = &folio->page;
>>> +               for (i = 0; i < nr; i++, page++, address += PAGE_SIZE) {
>>> +                       /* increment count (starts at -1) */
>>> +                       atomic_set(&page->_mapcount, 0);
>>> +                       __page_set_anon_rmap(folio, page, vma, address, 1);
>>> +               }
>>
>> Nit: use folio_page(), e.g.,

Yep, will change for v3.

>>
>>   } else if (!folio_test_pmd_mappable(folio)) {
>>     int i;
>>
>>     for (i = 0; i < nr; i++) {
>>       struct page *page = folio_page(folio, i);
>>
>>       /* increment count (starts at -1) */
>>       atomic_set(&page->_mapcount, 0);
>>       __page_set_anon_rmap(folio, page, vma, address + PAGE_SIZE * i, 1);
>>     }
>>     /* increment count (starts at 0) */
>>     atomic_set(&folio->_nr_pages_mapped, nr);
>>   } else {
>>
>>>         } else {
>>>                 /* increment count (starts at -1) */
>>>                 atomic_set(&folio->_entire_mapcount, 0);
>>>                 atomic_set(&folio->_nr_pages_mapped, COMPOUND_MAPPED);
>>> -               nr = folio_nr_pages(folio);
>>>                 __lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr);
>>> +               __page_set_anon_rmap(folio, &folio->page, vma, address, 1);
>>>         }
>>>
>>>         __lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr);
>>> -       __page_set_anon_rmap(folio, &folio->page, vma, address, 1);
>>>  }
diff mbox series

Patch

diff --git a/mm/rmap.c b/mm/rmap.c
index 1d8369549424..82ef5ba363d1 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1278,31 +1278,43 @@  void page_add_anon_rmap(struct page *page, struct vm_area_struct *vma,
  * This means the inc-and-test can be bypassed.
  * The folio does not have to be locked.
  *
- * If the folio is large, it is accounted as a THP.  As the folio
+ * If the folio is pmd-mappable, it is accounted as a THP.  As the folio
  * is new, it's assumed to be mapped exclusively by a single process.
  */
 void folio_add_new_anon_rmap(struct folio *folio, struct vm_area_struct *vma,
 		unsigned long address)
 {
-	int nr;
+	int nr = folio_nr_pages(folio);
+	int i;
+	struct page *page;
 
-	VM_BUG_ON_VMA(address < vma->vm_start || address >= vma->vm_end, vma);
+	VM_BUG_ON_VMA(address < vma->vm_start ||
+			address + (nr << PAGE_SHIFT) > vma->vm_end, vma);
 	__folio_set_swapbacked(folio);
 
-	if (likely(!folio_test_pmd_mappable(folio))) {
+	if (!folio_test_large(folio)) {
 		/* increment count (starts at -1) */
 		atomic_set(&folio->_mapcount, 0);
-		nr = 1;
+		__page_set_anon_rmap(folio, &folio->page, vma, address, 1);
+	} else if (!folio_test_pmd_mappable(folio)) {
+		/* increment count (starts at 0) */
+		atomic_set(&folio->_nr_pages_mapped, nr);
+
+		page = &folio->page;
+		for (i = 0; i < nr; i++, page++, address += PAGE_SIZE) {
+			/* increment count (starts at -1) */
+			atomic_set(&page->_mapcount, 0);
+			__page_set_anon_rmap(folio, page, vma, address, 1);
+		}
 	} else {
 		/* increment count (starts at -1) */
 		atomic_set(&folio->_entire_mapcount, 0);
 		atomic_set(&folio->_nr_pages_mapped, COMPOUND_MAPPED);
-		nr = folio_nr_pages(folio);
 		__lruvec_stat_mod_folio(folio, NR_ANON_THPS, nr);
+		__page_set_anon_rmap(folio, &folio->page, vma, address, 1);
 	}
 
 	__lruvec_stat_mod_folio(folio, NR_ANON_MAPPED, nr);
-	__page_set_anon_rmap(folio, &folio->page, vma, address, 1);
 }
 
 /**