Hi,
On 6.6.2023 10.46, David Hildenbrand wrote:
On 06.06.23 09:44, David Hildenbrand wrote:
On 06.06.23 07:01, mpenttil@xxxxxxxxxx wrote:
From: Mika Penttilä <mpenttil@xxxxxxxxxx>
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@xxxxxxxxxx>
Cc: John Hubbard <jhubbard@xxxxxxxxxx>
Cc: Ralph Campbell <rcampbell@xxxxxxxxxx>
Cc: "Huang, Ying" <ying.huang@xxxxxxxxx>
Reviewed-by: "Huang, Ying" <ying.huang@xxxxxxxxx>
Reviewed-by: Alistair Popple <apopple@xxxxxxxxxx>
Signed-off-by: Mika Penttilä <mpenttil@xxxxxxxxxx>
---
v3:
- Adjust comments
- Add Reviewed-bys
v2:
- use folio_test_anon() (Huang, Ying)
mm/migrate_device.c | 22 ++++++++++++++++------
1 file changed, 16 insertions(+), 6 deletions(-)
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index d30c9de60b0d..f76ebccfe067 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -747,13 +747,23 @@ 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.
+ *
+ */
+ if (!folio_test_anon(folio) ||
!folio_free_swap(folio)) {
+ src_pfns[i] &= ~MIGRATE_PFN_MIGRATE;
+ continue;
I'm pretty sure the folio has to be locked in order to call
folio_free_swap().
Oh, staring at the bigger context, I assume we locked the folios via
migrate_device_range(), correct?
Yes either that, or when migrating via virtual addresses
migrate_vma_collect_pmd() has trylock_page() and we migrate only pages
which succeed locking.
--Mika
