Skip to contentSkip to conversation

mm/rmap.c: Avoid double faults migrating device private pages

PATCH Applied Alistair Popple 2 participants 2 messages Oct 18, 2021

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

PATCH 1/1 mm/rmap.c: Avoid double faults migrating device private pages

During migration special page table entries are installed for each page being migrated. These entries store the pfn and associated permissions of ptes mapping the page being migarted.

Device-private pages use special swap pte entries to distinguish read-only vs. writeable pages which the migration code checks when creating migration entries. Normally this follows a fast path in migrate_vma_collect_pmd() which correctly copies the permissions of device-private pages over to migration entries when migrating pages back to the CPU.

However the slow-path falls back to using try_to_migrate() which unconditionally creates read-only migration entries for device-private pages. This leads to unnecessary double faults on the CPU as the new pages are always mapped read-only even when they could be mapped writeable. Fix this by correctly copying device-private permissions in try_to_migrate_one().

---
 mm/rmap.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)
mm/rmap.c +6 -2
index b9eb5c12f3fe..271de8118cdd 100644
@@ -1804,6 +1804,7 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma,
 		update_hiwater_rss(mm);
 
 		if (is_zone_device_page(page)) {
+			unsigned long pfn = page_to_pfn(page);
 			swp_entry_t entry;
 			pte_t swp_pte;
 
@@ -1812,8 +1813,11 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma,
 			 * pte. do_swap_page() will wait until the migration
 			 * pte is removed and then restart fault handling.
 			 */
-			entry = make_readable_migration_entry(
-							page_to_pfn(page));
+			entry = pte_to_swp_entry(pteval);
+			if (is_writable_device_private_entry(entry))
+				entry = make_writable_migration_entry(pfn);
+			else
+				entry = make_readable_migration_entry(pfn);
 			swp_pte = swp_entry_to_pte(entry);
 
 			/*
Signature · 1 line
2.30.2
Reviewed-by on v1 1/1
#1 lore raw
Quoted 3 lines · Alistair Popple

During migration special page table entries are installed for each page being migrated. These entries store the pfn and associated permissions of ptes mapping the page being migarted.

s/migarted/migrated/

Quoted 15 lines

Device-private pages use special swap pte entries to distinguish read-only vs. writeable pages which the migration code checks when creating migration entries. Normally this follows a fast path in migrate_vma_collect_pmd() which correctly copies the permissions of device-private pages over to migration entries when migrating pages back to the CPU.

However the slow-path falls back to using try_to_migrate() which unconditionally creates read-only migration entries for device-private pages. This leads to unnecessary double faults on the CPU as the new pages are always mapped read-only even when they could be mapped writeable. Fix this by correctly copying device-private permissions in try_to_migrate_one().

Quoted 5 lines
---
  mm/rmap.c | 8 ++++++--
  1 file changed, 6 insertions(+), 2 deletions(-)

Looks very clearly correct to me.

thanks,

Signature · 2 lines
John Hubbard
NVIDIA
Quoted 28 lines
mm/rmap.c +6 -2
index b9eb5c12f3fe..271de8118cdd 100644
@@ -1804,6 +1804,7 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma,
  		update_hiwater_rss(mm);
 
  		if (is_zone_device_page(page)) {
+			unsigned long pfn = page_to_pfn(page);
  			swp_entry_t entry;
  			pte_t swp_pte;
 
@@ -1812,8 +1813,11 @@ static bool try_to_migrate_one(struct page *page, struct vm_area_struct *vma,
  			 * pte. do_swap_page() will wait until the migration
  			 * pte is removed and then restart fault handling.
  			 */
-			entry = make_readable_migration_entry(
-							page_to_pfn(page));
+			entry = pte_to_swp_entry(pteval);
+			if (is_writable_device_private_entry(entry))
+				entry = make_writable_migration_entry(pfn);
+			else
+				entry = make_readable_migration_entry(pfn);
  			swp_pte = swp_entry_to_pte(entry);
 
  			/*