diff mbox series

[v2] mm/migrate_device: Try to handle swapcache pages

Message ID 20230531044018.17893-1-mpenttil@redhat.com
State New
Headers
Series [v2] mm/migrate_device: Try to handle swapcache pages |

Commit Message

Mika Penttilä May 31, 2023, 4:40 a.m. UTC 
  From: Mika Penttilä <mpenttil@redhat.com>

Migrating file pages and swapcache pages into device memory is not supported.
The decision is done based on page_mapping(). For now, swapcache pages are not migrated.

Things can however be improved, for swapcache pages. Try to get rid of the swap cache,
and if successful, go ahead as with other anonymous pages.

Cc: Alistair Popple <apopple@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Ralph Campbell <rcampbell@nvidia.com>
Cc: Huang Ying <ying.huang@intel.com>
Signed-off-by: Mika Penttilä <mpenttil@redhat.com>
---

v2:
  - use folio_test_anon() (Huang, Ying)

 
 mm/migrate_device.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

Comments

Huang, Ying May 31, 2023, 7:24 a.m. UTC | #1 
mpenttil@redhat.com writes:

> From: Mika Penttilä <mpenttil@redhat.com>
>
> Migrating file pages and swapcache pages into device memory is not supported.
> The decision is done based on page_mapping(). For now, swapcache pages are not migrated.
>
> Things can however be improved, for swapcache pages. Try to get rid of the swap cache,
> and if successful, go ahead as with other anonymous pages.
>
> Cc: Alistair Popple <apopple@nvidia.com>
> Cc: John Hubbard <jhubbard@nvidia.com>
> Cc: Ralph Campbell <rcampbell@nvidia.com>
> Cc: Huang Ying <ying.huang@intel.com>
> Signed-off-by: Mika Penttilä <mpenttil@redhat.com>
> ---
>
> v2:
>   - use folio_test_anon() (Huang, Ying)
>
>  
>  mm/migrate_device.c | 24 ++++++++++++++++++------
>  1 file changed, 18 insertions(+), 6 deletions(-)
>
> diff --git a/mm/migrate_device.c b/mm/migrate_device.c
> index d30c9de60b0d..829bbc526758 100644
> --- a/mm/migrate_device.c
> +++ b/mm/migrate_device.c
> @@ -747,13 +747,25 @@ static void __migrate_device_pages(unsigned long *src_pfns,
>  
>  		if (is_device_private_page(newpage) ||
>  		    is_device_coherent_page(newpage)) {
> -			/*
> -			 * For now only support anonymous memory migrating to
> -			 * device private or coherent memory.
> -			 */
> +
>  			if (mapping) {
> -				src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
> -				continue;
> +				struct folio *folio;
> +
> +				folio = page_folio(page);
> +
> +				/*
> +				 * For now only support anonymous memory migrating to
> +				 * device private or coherent memory.
> +				 *
> +				 * Try to get rid of swap cache if possible.

I think we can delete the following 2 lines of comments.  They add
nothing except what code says already.

Otherwise looks good to me.

Reviewed-by: "Huang, Ying" <ying.huang@intel.com>

> +				 * page is here file or swapcache page, could be shmem also
> +				 * folio_test_anon() filters out file and shmem
> +				 *
> +				 */
> +				if (!folio_test_anon(folio) || !folio_free_swap(folio)) {
> +					src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
> +					continue;
> +				}
>  			}
>  		} else if (is_zone_device_page(newpage)) {
>  			/*
Alistair Popple June 1, 2023, 12:25 p.m. UTC | #2 
"Huang, Ying" <ying.huang@intel.com> writes:

> mpenttil@redhat.com writes:
>
>> From: Mika Penttilä <mpenttil@redhat.com>
>>
>> Migrating file pages and swapcache pages into device memory is not supported.
>> The decision is done based on page_mapping(). For now, swapcache pages are not migrated.
>>
>> Things can however be improved, for swapcache pages. Try to get rid of the swap cache,
>> and if successful, go ahead as with other anonymous pages.
>>
>> Cc: Alistair Popple <apopple@nvidia.com>
>> Cc: John Hubbard <jhubbard@nvidia.com>
>> Cc: Ralph Campbell <rcampbell@nvidia.com>
>> Cc: Huang Ying <ying.huang@intel.com>
>> Signed-off-by: Mika Penttilä <mpenttil@redhat.com>
>> ---
>>
>> v2:
>>   - use folio_test_anon() (Huang, Ying)
>>
>>  
>>  mm/migrate_device.c | 24 ++++++++++++++++++------
>>  1 file changed, 18 insertions(+), 6 deletions(-)
>>
>> diff --git a/mm/migrate_device.c b/mm/migrate_device.c
>> index d30c9de60b0d..829bbc526758 100644
>> --- a/mm/migrate_device.c
>> +++ b/mm/migrate_device.c
>> @@ -747,13 +747,25 @@ static void __migrate_device_pages(unsigned long *src_pfns,
>>  
>>  		if (is_device_private_page(newpage) ||
>>  		    is_device_coherent_page(newpage)) {
>> -			/*
>> -			 * For now only support anonymous memory migrating to
>> -			 * device private or coherent memory.
>> -			 */
>> +
>>  			if (mapping) {
>> -				src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
>> -				continue;
>> +				struct folio *folio;
>> +
>> +				folio = page_folio(page);
>> +
>> +				/*
>> +				 * For now only support anonymous memory migrating to
>> +				 * device private or coherent memory.
>> +				 *
>> +				 * Try to get rid of swap cache if possible.
>
> I think we can delete the following 2 lines of comments.  They add
> nothing except what code says already.

They are also a bit confusing, because a private file-backed mapping is
treated as anonymous so folio_test_anon() won't filter those
out. 

I will test this tomorrow but the change looks good so please add:

Reviewed-by: Alistair Popple <apopple@nvidia.com>

> Otherwise looks good to me.
>
> Reviewed-by: "Huang, Ying" <ying.huang@intel.com>
>
>> +				 * page is here file or swapcache page, could be shmem also
>> +				 * folio_test_anon() filters out file and shmem
>> +				 *
>> +				 */
>> +				if (!folio_test_anon(folio) || !folio_free_swap(folio)) {
>> +					src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
>> +					continue;
>> +				}
>>  			}
>>  		} else if (is_zone_device_page(newpage)) {
>>  			/*
diff mbox series

Patch

diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index d30c9de60b0d..829bbc526758 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -747,13 +747,25 @@  static void __migrate_device_pages(unsigned long *src_pfns,
 
 		if (is_device_private_page(newpage) ||
 		    is_device_coherent_page(newpage)) {
-			/*
-			 * For now only support anonymous memory migrating to
-			 * device private or coherent memory.
-			 */
+
 			if (mapping) {
-				src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
-				continue;
+				struct folio *folio;
+
+				folio = page_folio(page);
+
+				/*
+				 * For now only support anonymous memory migrating to
+				 * device private or coherent memory.
+				 *
+				 * Try to get rid of swap cache if possible.
+				 * page is here file or swapcache page, could be shmem also
+				 * folio_test_anon() filters out file and shmem
+				 *
+				 */
+				if (!folio_test_anon(folio) || !folio_free_swap(folio)) {
+					src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
+					continue;
+				}
 			}
 		} else if (is_zone_device_page(newpage)) {
 			/*