diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 85e0c58bdfdf..9649ff0c63f8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -31,6 +31,7 @@ struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
void hugepage_put_subpool(struct hugepage_subpool *spool);
int PageHuge(struct page *page);
+int PageHeadHuge(struct page *page_head);
void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
@@ -103,6 +104,11 @@ static inline int PageHuge(struct page *page)
return 0;
}
+static inline int PageHeadHuge(struct page *page_head)
+{
+ return 0;
+}
+
static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
{
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 2130365d387d..dee6cf4e6d34 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -702,6 +702,23 @@ int PageHuge(struct page *page)
}
EXPORT_SYMBOL_GPL(PageHuge);
+/*
+ * PageHeadHuge() only returns true for hugetlbfs head page, but not for
+ * normal or transparent huge pages.
+ */
+int PageHeadHuge(struct page *page_head)
+{
+ compound_page_dtor *dtor;
+
+ if (!PageHead(page_head))
+ return 0;
+
+ dtor = get_compound_page_dtor(page_head);
+
+ return dtor == free_huge_page;
+}
+EXPORT_SYMBOL_GPL(PageHeadHuge);
+
pgoff_t __basepage_index(struct page *page)
{
struct page *page_head = compound_head(page);
diff --git a/mm/swap.c b/mm/swap.c
index 7a9f80d451f5..84b26aaabd03 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -82,19 +82,6 @@ static void __put_compound_page(struct page *page)
static void put_compound_page(struct page *page)
{
- /*
- * hugetlbfs pages cannot be split from under us. If this is a
- * hugetlbfs page, check refcount on head page and release the page if
- * the refcount becomes zero.
- */
- if (PageHuge(page)) {
- page = compound_head(page);
- if (put_page_testzero(page))
- __put_compound_page(page);
-
- return;
- }
-
if (unlikely(PageTail(page))) {
/* __split_huge_page_refcount can run under us */
struct page *page_head = compound_trans_head(page);
@@ -111,14 +98,31 @@ static void put_compound_page(struct page *page)
* still hot on arches that do not support
* this_cpu_cmpxchg_double().
*/
- if (PageSlab(page_head)) {
- if (PageTail(page)) {
+ if (PageSlab(page_head) || PageHeadHuge(page_head)) {
+ if (likely(PageTail(page))) {
+ /*
+ * __split_huge_page_refcount
+ * cannot race here.
+ */
+ VM_BUG_ON(!PageHead(page_head));
+ atomic_dec(&page->_mapcount);
if (put_page_testzero(page_head))
VM_BUG_ON(1);
-
- atomic_dec(&page->_mapcount);
- goto skip_lock_tail;
+ if (put_page_testzero(page_head))
+ __put_compound_page(page_head);
+ return;
} else
+ /*
+ * __split_huge_page_refcount
+ * run before us, "page" was a
+ * THP tail. The split
+ * page_head has been freed
+ * and reallocated as slab or
+ * hugetlbfs page of smaller
+ * order (only possible if
+ * reallocated as slab on
+ * x86).
+ */
goto skip_lock;
}
/*
@@ -132,8 +136,27 @@ static void put_compound_page(struct page *page)
/* __split_huge_page_refcount run before us */
compound_unlock_irqrestore(page_head, flags);
skip_lock:
- if (put_page_testzero(page_head))
- __put_single_page(page_head);
+ if (put_page_testzero(page_head)) {
+ /*
+ * The head page may have been
+ * freed and reallocated as a
+ * compound page of smaller
+ * order and then freed again.
+ * All we know is that it
+ * cannot have become: a THP
+ * page, a compound page of
+ * higher order, a tail page.
+ * That is because we still
+ * hold the refcount of the
+ * split THP tail and
+ * page_head was the THP head
+ * before the split.
+ */
+ if (PageHead(page_head))
+ __put_compound_page(page_head);
+ else
+ __put_single_page(page_head);
+ }
out_put_single:
if (put_page_testzero(page))
__put_single_page(page);
@@ -155,7 +178,6 @@ out_put_single:
VM_BUG_ON(atomic_read(&page->_count) != 0);
compound_unlock_irqrestore(page_head, flags);
-skip_lock_tail:
if (put_page_testzero(page_head)) {
if (PageHead(page_head))
__put_compound_page(page_head);
@@ -198,51 +220,52 @@ bool __get_page_tail(struct page *page)
* proper PT lock that already serializes against
* split_huge_page().
*/
+ unsigned long flags;
bool got = false;
- struct page *page_head;
+ struct page *page_head = compound_trans_head(page);
- /*
- * If this is a hugetlbfs page it cannot be split under us. Simply
- * increment refcount for the head page.
- */
- if (PageHuge(page)) {
- page_head = compound_head(page);
- atomic_inc(&page_head->_count);
- got = true;
- } else {
- unsigned long flags;
-
- page_head = compound_trans_head(page);
- if (likely(page != page_head &&
- get_page_unless_zero(page_head))) {
-
- /* Ref to put_compound_page() comment. */
- if (PageSlab(page_head)) {
- if (likely(PageTail(page))) {
- __get_page_tail_foll(page, false);
- return true;
- } else {
- put_page(page_head);
- return false;
- }
- }
-
- /*
- * page_head wasn't a dangling pointer but it
- * may not be a head page anymore by the time
- * we obtain the lock. That is ok as long as it
- * can't be freed from under us.
- */
- flags = compound_lock_irqsave(page_head);
- /* here __split_huge_page_refcount won't run anymore */
+ if (likely(page != page_head && get_page_unless_zero(page_head))) {
+ /* Ref to put_compound_page() comment. */
+ if (PageSlab(page_head) || PageHeadHuge(page_head)) {
if (likely(PageTail(page))) {
+ /*
+ * This is a hugetlbfs page or a slab
+ * page. __split_huge_page_refcount
+ * cannot race here.
+ */
+ VM_BUG_ON(!PageHead(page_head));
__get_page_tail_foll(page, false);
- got = true;
- }
- compound_unlock_irqrestore(page_head, flags);
- if (unlikely(!got))
+ return true;
+ } else {
+ /*
+ * __split_huge_page_refcount run
+ * before us, "page" was a THP
+ * tail. The split page_head has been
+ * freed and reallocated as slab or
+ * hugetlbfs page of smaller order
+ * (only possible if reallocated as
+ * slab on x86).
+ */
put_page(page_head);
+ return false;
+ }
}
+
+ /*
+ * page_head wasn't a dangling pointer but it
+ * may not be a head page anymore by the time
+ * we obtain the lock. That is ok as long as it
+ * can't be freed from under us.
+ */
+ flags = compound_lock_irqsave(page_head);
+ /* here __split_huge_page_refcount won't run anymore */
+ if (likely(PageTail(page))) {
+ __get_page_tail_foll(page, false);
+ got = true;
+ }
+ compound_unlock_irqrestore(page_head, flags);
+ if (unlikely(!got))
+ put_page(page_head);
}
return got;
}