summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
-rw-r--r--include/linux/pagemap.h2
-rw-r--r--mm/filemap.c87
-rw-r--r--mm/huge_memory.c6
-rw-r--r--mm/migrate.c12
-rw-r--r--mm/vmscan.c10
5 files changed, 84 insertions, 33 deletions
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 226f96f0dee0..e2d7039af6a3 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -537,6 +537,8 @@ static inline int wait_on_page_locked_killable(struct page *page)
return wait_on_page_bit_killable(compound_head(page), PG_locked);
}
+extern void put_and_wait_on_page_locked(struct page *page);
+
/*
* Wait for a page to complete writeback
*/
diff --git a/mm/filemap.c b/mm/filemap.c
index 81adec8ee02c..d2df272152f5 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -981,7 +981,14 @@ static int wake_page_function(wait_queue_entry_t *wait, unsigned mode, int sync,
if (wait_page->bit_nr != key->bit_nr)
return 0;
- /* Stop walking if it's locked */
+ /*
+ * Stop walking if it's locked.
+ * Is this safe if put_and_wait_on_page_locked() is in use?
+ * Yes: the waker must hold a reference to this page, and if PG_locked
+ * has now already been set by another task, that task must also hold
+ * a reference to the *same usage* of this page; so there is no need
+ * to walk on to wake even the put_and_wait_on_page_locked() callers.
+ */
if (test_bit(key->bit_nr, &key->page->flags))
return -1;
@@ -1049,25 +1056,44 @@ static void wake_up_page(struct page *page, int bit)
wake_up_page_bit(page, bit);
}
+/*
+ * A choice of three behaviors for wait_on_page_bit_common():
+ */
+enum behavior {
+ EXCLUSIVE, /* Hold ref to page and take the bit when woken, like
+ * __lock_page() waiting on then setting PG_locked.
+ */
+ SHARED, /* Hold ref to page and check the bit when woken, like
+ * wait_on_page_writeback() waiting on PG_writeback.
+ */
+ DROP, /* Drop ref to page before wait, no check when woken,
+ * like put_and_wait_on_page_locked() on PG_locked.
+ */
+};
+
static inline int wait_on_page_bit_common(wait_queue_head_t *q,
- struct page *page, int bit_nr, int state, bool lock)
+ struct page *page, int bit_nr, int state, enum behavior behavior)
{
struct wait_page_queue wait_page;
wait_queue_entry_t *wait = &wait_page.wait;
+ bool bit_is_set;
bool thrashing = false;
+ bool delayacct = false;
unsigned long pflags;
int ret = 0;
if (bit_nr == PG_locked &&
!PageUptodate(page) && PageWorkingset(page)) {
- if (!PageSwapBacked(page))
+ if (!PageSwapBacked(page)) {
delayacct_thrashing_start();
+ delayacct = true;
+ }
psi_memstall_enter(&pflags);
thrashing = true;
}
init_wait(wait);
- wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0;
+ wait->flags = behavior == EXCLUSIVE ? WQ_FLAG_EXCLUSIVE : 0;
wait->func = wake_page_function;
wait_page.page = page;
wait_page.bit_nr = bit_nr;
@@ -1084,14 +1110,17 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
spin_unlock_irq(&q->lock);
- if (likely(test_bit(bit_nr, &page->flags))) {
+ bit_is_set = test_bit(bit_nr, &page->flags);
+ if (behavior == DROP)
+ put_page(page);
+
+ if (likely(bit_is_set))
io_schedule();
- }
- if (lock) {
+ if (behavior == EXCLUSIVE) {
if (!test_and_set_bit_lock(bit_nr, &page->flags))
break;
- } else {
+ } else if (behavior == SHARED) {
if (!test_bit(bit_nr, &page->flags))
break;
}
@@ -1100,12 +1129,23 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
ret = -EINTR;
break;
}
+
+ if (behavior == DROP) {
+ /*
+ * We can no longer safely access page->flags:
+ * even if CONFIG_MEMORY_HOTREMOVE is not enabled,
+ * there is a risk of waiting forever on a page reused
+ * for something that keeps it locked indefinitely.
+ * But best check for -EINTR above before breaking.
+ */
+ break;
+ }
}
finish_wait(q, wait);
if (thrashing) {
- if (!PageSwapBacked(page))
+ if (delayacct)
delayacct_thrashing_end();
psi_memstall_leave(&pflags);
}
@@ -1124,18 +1164,37 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q,
void wait_on_page_bit(struct page *page, int bit_nr)
{
wait_queue_head_t *q = page_waitqueue(page);
- wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, false);
+ wait_on_page_bit_common(q, page, bit_nr, TASK_UNINTERRUPTIBLE, SHARED);
}
EXPORT_SYMBOL(wait_on_page_bit);
int wait_on_page_bit_killable(struct page *page, int bit_nr)
{
wait_queue_head_t *q = page_waitqueue(page);
- return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, false);
+ return wait_on_page_bit_common(q, page, bit_nr, TASK_KILLABLE, SHARED);
}
EXPORT_SYMBOL(wait_on_page_bit_killable);
/**
+ * put_and_wait_on_page_locked - Drop a reference and wait for it to be unlocked
+ * @page: The page to wait for.
+ *
+ * The caller should hold a reference on @page. They expect the page to
+ * become unlocked relatively soon, but do not wish to hold up migration
+ * (for example) by holding the reference while waiting for the page to
+ * come unlocked. After this function returns, the caller should not
+ * dereference @page.
+ */
+void put_and_wait_on_page_locked(struct page *page)
+{
+ wait_queue_head_t *q;
+
+ page = compound_head(page);
+ q = page_waitqueue(page);
+ wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, DROP);
+}
+
+/**
* add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
* @page: Page defining the wait queue of interest
* @waiter: Waiter to add to the queue
@@ -1264,7 +1323,8 @@ void __lock_page(struct page *__page)
{
struct page *page = compound_head(__page);
wait_queue_head_t *q = page_waitqueue(page);
- wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE, true);
+ wait_on_page_bit_common(q, page, PG_locked, TASK_UNINTERRUPTIBLE,
+ EXCLUSIVE);
}
EXPORT_SYMBOL(__lock_page);
@@ -1272,7 +1332,8 @@ int __lock_page_killable(struct page *__page)
{
struct page *page = compound_head(__page);
wait_queue_head_t *q = page_waitqueue(page);
- return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE, true);
+ return wait_on_page_bit_common(q, page, PG_locked, TASK_KILLABLE,
+ EXCLUSIVE);
}
EXPORT_SYMBOL_GPL(__lock_page_killable);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index da6682bb69aa..0c0e18409fde 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1490,8 +1490,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
if (!get_page_unless_zero(page))
goto out_unlock;
spin_unlock(vmf->ptl);
- wait_on_page_locked(page);
- put_page(page);
+ put_and_wait_on_page_locked(page);
goto out;
}
@@ -1527,8 +1526,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
if (!get_page_unless_zero(page))
goto out_unlock;
spin_unlock(vmf->ptl);
- wait_on_page_locked(page);
- put_page(page);
+ put_and_wait_on_page_locked(page);
goto out;
}
diff --git a/mm/migrate.c b/mm/migrate.c
index f7e4bfdc13b7..acda06f99754 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -327,16 +327,13 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
/*
* Once page cache replacement of page migration started, page_count
- * *must* be zero. And, we don't want to call wait_on_page_locked()
- * against a page without get_page().
- * So, we use get_page_unless_zero(), here. Even failed, page fault
- * will occur again.
+ * 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);
- wait_on_page_locked(page);
- put_page(page);
+ put_and_wait_on_page_locked(page);
return;
out:
pte_unmap_unlock(ptep, ptl);
@@ -370,8 +367,7 @@ void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd)
if (!get_page_unless_zero(page))
goto unlock;
spin_unlock(ptl);
- wait_on_page_locked(page);
- put_page(page);
+ put_and_wait_on_page_locked(page);
return;
unlock:
spin_unlock(ptl);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index bd8971a29204..a714c4f800e9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1460,14 +1460,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
count_memcg_page_event(page, PGLAZYFREED);
} else if (!mapping || !__remove_mapping(mapping, page, true))
goto keep_locked;
- /*
- * At this point, we have no other references and there is
- * no way to pick any more up (removed from LRU, removed
- * from pagecache). Can use non-atomic bitops now (and
- * we obviously don't have to worry about waking up a process
- * waiting on the page lock, because there are no references.
- */
- __ClearPageLocked(page);
+
+ unlock_page(page);
free_it:
nr_reclaimed++;