This fixes the FIXME in migrate_vma_check_page().
Before migrating a page migration code will take a reference and check
there are no unexpected page references, failing the migration if there
are. When a thread faults on a migration entry it will take a temporary
reference to the page to wait for the page to become unlocked signifying
the migration entry has been removed.
This reference is dropped just prior to waiting on the page lock,
however the extra reference can cause migration failures so it is
desirable to avoid taking it.
As migration code already has a reference to the migrating page an extra
reference to wait on PG_locked is unnecessary so long as the reference
can't be dropped whilst setting up the wait.
When faulting on a migration entry the ptl is taken to check the
migration entry. Removing a migration entry also requires the ptl, and
migration code won't drop its page reference until after the migration
entry has been removed. Therefore retaining the ptl of a migration entry
is sufficient to ensure the page has a reference. Reworking
migration_entry_wait() to hold the ptl until the wait setup is complete
means the extra page reference is no longer needed.
Signed-off-by: Alistair Popple <[email protected]>
---
v3:
- Fix a build issue for CONFIG_MMU=n by only building
migration_entry_wait_on_locked() if CONFIG_MIGRATION=y
v2:
- Rebase to master with folios
- Avoid taking a pageref in pmd_migration_entry_wait() as well
---
include/linux/migrate.h | 2 +
mm/filemap.c | 87 +++++++++++++++++++++++++++++++++++++++++
mm/migrate.c | 33 ++--------------
3 files changed, 93 insertions(+), 29 deletions(-)
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 4850cc5bf813..54579902ec9f 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -40,6 +40,8 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page);
extern int migrate_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page, int extra_count);
+void migration_entry_wait_on_locked(struct folio *folio, pte_t *ptep,
+ spinlock_t *ptl);
void folio_migrate_flags(struct folio *newfolio, struct folio *folio);
void folio_migrate_copy(struct folio *newfolio, struct folio *folio);
int folio_migrate_mapping(struct address_space *mapping,
diff --git a/mm/filemap.c b/mm/filemap.c
index daa0e23a6ee6..a812e110df9c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1426,6 +1426,93 @@ static inline int folio_wait_bit_common(struct folio *folio, int bit_nr,
return wait->flags & WQ_FLAG_WOKEN ? 0 : -EINTR;
}
+#ifdef CONFIG_MIGRATION
+/**
+ * migration_entry_wait_on_locked - Wait for a migration entry to be removed
+ * @page: page referenced by the migration entry.
+ * @ptep: mapped pte pointer. This function will return with the ptep unmapped.
+ * @ptl: already locked ptl. This function will drop the lock.
+ *
+ * Wait for a migration entry referencing the given page to be removed. This is
+ * equivalent to put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE) except
+ * this can be called without taking a reference on the page. Instead this
+ * should be called while holding the ptl for the migration entry referencing
+ * the page.
+ *
+ * Returns after unmapping and unlocking the pte/ptl with pte_unmap_unlock().
+ *
+ * This follows the same logic as wait_on_page_bit_common() so see the comments
+ * there.
+ */
+void migration_entry_wait_on_locked(struct folio *folio, pte_t *ptep,
+ spinlock_t *ptl)
+{
+ struct wait_page_queue wait_page;
+ wait_queue_entry_t *wait = &wait_page.wait;
+ bool thrashing = false;
+ bool delayacct = false;
+ unsigned long pflags;
+ wait_queue_head_t *q;
+
+ q = folio_waitqueue(folio);
+ if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) {
+ if (!folio_test_swapbacked(folio)) {
+ delayacct_thrashing_start();
+ delayacct = true;
+ }
+ psi_memstall_enter(&pflags);
+ thrashing = true;
+ }
+
+ init_wait(wait);
+ wait->func = wake_page_function;
+ wait_page.folio = folio;
+ wait_page.bit_nr = PG_locked;
+ wait->flags = 0;
+
+ spin_lock_irq(&q->lock);
+ folio_set_waiters(folio);
+ if (!folio_trylock_flag(folio, PG_locked, wait))
+ __add_wait_queue_entry_tail(q, wait);
+ spin_unlock_irq(&q->lock);
+
+ /*
+ * If a migration entry exists for the page the migration path must hold
+ * a valid reference to the page, and it must take the ptl to remove the
+ * migration entry. So the page is valid until the ptl is dropped.
+ */
+ if (ptep)
+ pte_unmap_unlock(ptep, ptl);
+ else
+ spin_unlock(ptl);
+
+ for (;;) {
+ unsigned int flags;
+
+ set_current_state(TASK_UNINTERRUPTIBLE);
+
+ /* Loop until we've been woken or interrupted */
+ flags = smp_load_acquire(&wait->flags);
+ if (!(flags & WQ_FLAG_WOKEN)) {
+ if (signal_pending_state(TASK_UNINTERRUPTIBLE, current))
+ break;
+
+ io_schedule();
+ continue;
+ }
+ break;
+ }
+
+ finish_wait(q, wait);
+
+ if (thrashing) {
+ if (delayacct)
+ delayacct_thrashing_end();
+ psi_memstall_leave(&pflags);
+ }
+}
+#endif
+
void folio_wait_bit(struct folio *folio, int bit_nr)
{
folio_wait_bit_common(folio, bit_nr, TASK_UNINTERRUPTIBLE, SHARED);
diff --git a/mm/migrate.c b/mm/migrate.c
index cf25b00f03c8..8d29a7903f9e 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -305,15 +305,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
page = pfn_swap_entry_to_page(entry);
page = compound_head(page);
- /*
- * Once page cache replacement of page migration started, page_count
- * is zero; but we must not call put_and_wait_on_page_locked() without
- * a ref. Use get_page_unless_zero(), and just fault again if it fails.
- */
- if (!get_page_unless_zero(page))
- goto out;
- pte_unmap_unlock(ptep, ptl);
- put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE);
+ migration_entry_wait_on_locked(page_folio(page), ptep, ptl);
return;
out:
pte_unmap_unlock(ptep, ptl);
@@ -344,10 +336,7 @@ void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd)
if (!is_pmd_migration_entry(*pmd))
goto unlock;
page = pfn_swap_entry_to_page(pmd_to_swp_entry(*pmd));
- if (!get_page_unless_zero(page))
- goto unlock;
- spin_unlock(ptl);
- put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE);
+ migration_entry_wait_on_locked(page_folio(page), NULL, ptl);
return;
unlock:
spin_unlock(ptl);
@@ -2484,22 +2473,8 @@ static bool migrate_vma_check_page(struct page *page)
return false;
/* Page from ZONE_DEVICE have one extra reference */
- if (is_zone_device_page(page)) {
- /*
- * Private page can never be pin as they have no valid pte and
- * GUP will fail for those. Yet if there is a pending migration
- * a thread might try to wait on the pte migration entry and
- * will bump the page reference count. Sadly there is no way to
- * differentiate a regular pin from migration wait. Hence to
- * avoid 2 racing thread trying to migrate back to CPU to enter
- * infinite loop (one stopping migration because the other is
- * waiting on pte migration entry). We always return true here.
- *
- * FIXME proper solution is to rework migration_entry_wait() so
- * it does not need to take a reference on page.
- */
- return is_device_private_page(page);
- }
+ if (is_zone_device_page(page))
+ extra++;
/* For file back page */
if (page_mapping(page))
--
2.30.2
Hi Alistair,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on linux/master]
[also build test WARNING on linus/master v5.16-rc1 next-20211115]
[cannot apply to hnaz-mm/master]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Alistair-Popple/mm-migrate-c-Rework-migration_entry_wait-to-not-take-a-pageref/20211115-185444
base: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git debe436e77c72fcee804fb867f275e6d31aa999c
config: i386-randconfig-r015-20211115 (attached as .config)
compiler: clang version 14.0.0 (https://github.com/llvm/llvm-project fbe72e41b99dc7994daac300d208a955be3e4a0a)
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# https://github.com/0day-ci/linux/commit/91a437ddc7606450e331059d80babe2d4c1163e0
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Alistair-Popple/mm-migrate-c-Rework-migration_entry_wait-to-not-take-a-pageref/20211115-185444
git checkout 91a437ddc7606450e331059d80babe2d4c1163e0
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross W=1 ARCH=i386
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <[email protected]>
All warnings (new ones prefixed by >>):
>> mm/filemap.c:1447:6: warning: no previous prototype for function 'migration_entry_wait_on_locked' [-Wmissing-prototypes]
void migration_entry_wait_on_locked(struct folio *folio, pte_t *ptep,
^
mm/filemap.c:1447:1: note: declare 'static' if the function is not intended to be used outside of this translation unit
void migration_entry_wait_on_locked(struct folio *folio, pte_t *ptep,
^
static
1 warning generated.
vim +/migration_entry_wait_on_locked +1447 mm/filemap.c
1428
1429 #ifdef CONFIG_MIGRATION
1430 /**
1431 * migration_entry_wait_on_locked - Wait for a migration entry to be removed
1432 * @page: page referenced by the migration entry.
1433 * @ptep: mapped pte pointer. This function will return with the ptep unmapped.
1434 * @ptl: already locked ptl. This function will drop the lock.
1435 *
1436 * Wait for a migration entry referencing the given page to be removed. This is
1437 * equivalent to put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE) except
1438 * this can be called without taking a reference on the page. Instead this
1439 * should be called while holding the ptl for the migration entry referencing
1440 * the page.
1441 *
1442 * Returns after unmapping and unlocking the pte/ptl with pte_unmap_unlock().
1443 *
1444 * This follows the same logic as wait_on_page_bit_common() so see the comments
1445 * there.
1446 */
> 1447 void migration_entry_wait_on_locked(struct folio *folio, pte_t *ptep,
1448 spinlock_t *ptl)
1449 {
1450 struct wait_page_queue wait_page;
1451 wait_queue_entry_t *wait = &wait_page.wait;
1452 bool thrashing = false;
1453 bool delayacct = false;
1454 unsigned long pflags;
1455 wait_queue_head_t *q;
1456
1457 q = folio_waitqueue(folio);
1458 if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) {
1459 if (!folio_test_swapbacked(folio)) {
1460 delayacct_thrashing_start();
1461 delayacct = true;
1462 }
1463 psi_memstall_enter(&pflags);
1464 thrashing = true;
1465 }
1466
1467 init_wait(wait);
1468 wait->func = wake_page_function;
1469 wait_page.folio = folio;
1470 wait_page.bit_nr = PG_locked;
1471 wait->flags = 0;
1472
1473 spin_lock_irq(&q->lock);
1474 folio_set_waiters(folio);
1475 if (!folio_trylock_flag(folio, PG_locked, wait))
1476 __add_wait_queue_entry_tail(q, wait);
1477 spin_unlock_irq(&q->lock);
1478
1479 /*
1480 * If a migration entry exists for the page the migration path must hold
1481 * a valid reference to the page, and it must take the ptl to remove the
1482 * migration entry. So the page is valid until the ptl is dropped.
1483 */
1484 if (ptep)
1485 pte_unmap_unlock(ptep, ptl);
1486 else
1487 spin_unlock(ptl);
1488
1489 for (;;) {
1490 unsigned int flags;
1491
1492 set_current_state(TASK_UNINTERRUPTIBLE);
1493
1494 /* Loop until we've been woken or interrupted */
1495 flags = smp_load_acquire(&wait->flags);
1496 if (!(flags & WQ_FLAG_WOKEN)) {
1497 if (signal_pending_state(TASK_UNINTERRUPTIBLE, current))
1498 break;
1499
1500 io_schedule();
1501 continue;
1502 }
1503 break;
1504 }
1505
1506 finish_wait(q, wait);
1507
1508 if (thrashing) {
1509 if (delayacct)
1510 delayacct_thrashing_end();
1511 psi_memstall_leave(&pflags);
1512 }
1513 }
1514 #endif
1515
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/[email protected]
On Mon, Nov 15, 2021 at 09:52:22PM +1100, Alistair Popple wrote:
> +#ifdef CONFIG_MIGRATION
> +/**
> + * migration_entry_wait_on_locked - Wait for a migration entry to be removed
> + * @page: page referenced by the migration entry.
This should be @folio (you can test by running 'make htmldocs', or even
'make W=1'
> + * @ptep: mapped pte pointer. This function will return with the ptep unmapped.
> + * @ptl: already locked ptl. This function will drop the lock.
> + *
> + * Wait for a migration entry referencing the given page to be removed. This is
> + * equivalent to put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE) except
> + * this can be called without taking a reference on the page. Instead this
> + * should be called while holding the ptl for the migration entry referencing
> + * the page.
The tool won't tell you to update these page references to be folio
references ... so I will ;-)
> +++ b/mm/migrate.c
> @@ -305,15 +305,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
> page = pfn_swap_entry_to_page(entry);
> page = compound_head(page);
I think this whole function should be folio-based. That is:
- struct page *page;
+ struct folio *folio;
and
folio = page_folio(pfn_swap_entry_to_page(entry));
Hi Alistair,
Thank you for the patch! Perhaps something to improve:
[auto build test WARNING on linux/master]
[also build test WARNING on linus/master v5.16-rc1 next-20211115]
[cannot apply to hnaz-mm/master]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Alistair-Popple/mm-migrate-c-Rework-migration_entry_wait-to-not-take-a-pageref/20211115-185444
base: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git debe436e77c72fcee804fb867f275e6d31aa999c
config: nios2-defconfig (attached as .config)
compiler: nios2-linux-gcc (GCC) 11.2.0
reproduce (this is a W=1 build):
wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
chmod +x ~/bin/make.cross
# https://github.com/0day-ci/linux/commit/91a437ddc7606450e331059d80babe2d4c1163e0
git remote add linux-review https://github.com/0day-ci/linux
git fetch --no-tags linux-review Alistair-Popple/mm-migrate-c-Rework-migration_entry_wait-to-not-take-a-pageref/20211115-185444
git checkout 91a437ddc7606450e331059d80babe2d4c1163e0
# save the attached .config to linux build tree
COMPILER_INSTALL_PATH=$HOME/0day COMPILER=gcc-11.2.0 make.cross ARCH=nios2
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <[email protected]>
All warnings (new ones prefixed by >>):
>> mm/filemap.c:1447:6: warning: no previous prototype for 'migration_entry_wait_on_locked' [-Wmissing-prototypes]
1447 | void migration_entry_wait_on_locked(struct folio *folio, pte_t *ptep,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
vim +/migration_entry_wait_on_locked +1447 mm/filemap.c
1428
1429 #ifdef CONFIG_MIGRATION
1430 /**
1431 * migration_entry_wait_on_locked - Wait for a migration entry to be removed
1432 * @page: page referenced by the migration entry.
1433 * @ptep: mapped pte pointer. This function will return with the ptep unmapped.
1434 * @ptl: already locked ptl. This function will drop the lock.
1435 *
1436 * Wait for a migration entry referencing the given page to be removed. This is
1437 * equivalent to put_and_wait_on_page_locked(page, TASK_UNINTERRUPTIBLE) except
1438 * this can be called without taking a reference on the page. Instead this
1439 * should be called while holding the ptl for the migration entry referencing
1440 * the page.
1441 *
1442 * Returns after unmapping and unlocking the pte/ptl with pte_unmap_unlock().
1443 *
1444 * This follows the same logic as wait_on_page_bit_common() so see the comments
1445 * there.
1446 */
> 1447 void migration_entry_wait_on_locked(struct folio *folio, pte_t *ptep,
1448 spinlock_t *ptl)
1449 {
1450 struct wait_page_queue wait_page;
1451 wait_queue_entry_t *wait = &wait_page.wait;
1452 bool thrashing = false;
1453 bool delayacct = false;
1454 unsigned long pflags;
1455 wait_queue_head_t *q;
1456
1457 q = folio_waitqueue(folio);
1458 if (!folio_test_uptodate(folio) && folio_test_workingset(folio)) {
1459 if (!folio_test_swapbacked(folio)) {
1460 delayacct_thrashing_start();
1461 delayacct = true;
1462 }
1463 psi_memstall_enter(&pflags);
1464 thrashing = true;
1465 }
1466
1467 init_wait(wait);
1468 wait->func = wake_page_function;
1469 wait_page.folio = folio;
1470 wait_page.bit_nr = PG_locked;
1471 wait->flags = 0;
1472
1473 spin_lock_irq(&q->lock);
1474 folio_set_waiters(folio);
1475 if (!folio_trylock_flag(folio, PG_locked, wait))
1476 __add_wait_queue_entry_tail(q, wait);
1477 spin_unlock_irq(&q->lock);
1478
1479 /*
1480 * If a migration entry exists for the page the migration path must hold
1481 * a valid reference to the page, and it must take the ptl to remove the
1482 * migration entry. So the page is valid until the ptl is dropped.
1483 */
1484 if (ptep)
1485 pte_unmap_unlock(ptep, ptl);
1486 else
1487 spin_unlock(ptl);
1488
1489 for (;;) {
1490 unsigned int flags;
1491
1492 set_current_state(TASK_UNINTERRUPTIBLE);
1493
1494 /* Loop until we've been woken or interrupted */
1495 flags = smp_load_acquire(&wait->flags);
1496 if (!(flags & WQ_FLAG_WOKEN)) {
1497 if (signal_pending_state(TASK_UNINTERRUPTIBLE, current))
1498 break;
1499
1500 io_schedule();
1501 continue;
1502 }
1503 break;
1504 }
1505
1506 finish_wait(q, wait);
1507
1508 if (thrashing) {
1509 if (delayacct)
1510 delayacct_thrashing_end();
1511 psi_memstall_leave(&pflags);
1512 }
1513 }
1514 #endif
1515
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/[email protected]