summaryrefslogtreecommitdiffstats
path: root/mm/huge_memory.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/huge_memory.c')
-rw-r--r--mm/huge_memory.c39
1 files changed, 31 insertions, 8 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index a84909cf20d3..86975dec0ba1 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1426,8 +1426,11 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
*/
if (unlikely(pmd_trans_migrating(*vmf->pmd))) {
page = pmd_page(*vmf->pmd);
+ if (!get_page_unless_zero(page))
+ goto out_unlock;
spin_unlock(vmf->ptl);
wait_on_page_locked(page);
+ put_page(page);
goto out;
}
@@ -1459,9 +1462,12 @@ int do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
/* Migration could have started since the pmd_trans_migrating check */
if (!page_locked) {
+ page_nid = -1;
+ if (!get_page_unless_zero(page))
+ goto out_unlock;
spin_unlock(vmf->ptl);
wait_on_page_locked(page);
- page_nid = -1;
+ put_page(page);
goto out;
}
@@ -1569,8 +1575,8 @@ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
get_page(page);
spin_unlock(ptl);
split_huge_page(page);
- put_page(page);
unlock_page(page);
+ put_page(page);
goto out_unlocked;
}
@@ -2197,7 +2203,7 @@ static void __split_huge_page_tail(struct page *head, int tail,
* atomic_set() here would be safe on all archs (and not only on x86),
* it's safer to use atomic_inc()/atomic_add().
*/
- if (PageAnon(head)) {
+ if (PageAnon(head) && !PageSwapCache(head)) {
page_ref_inc(page_tail);
} else {
/* Additional pin to radix tree */
@@ -2208,6 +2214,7 @@ static void __split_huge_page_tail(struct page *head, int tail,
page_tail->flags |= (head->flags &
((1L << PG_referenced) |
(1L << PG_swapbacked) |
+ (1L << PG_swapcache) |
(1L << PG_mlocked) |
(1L << PG_uptodate) |
(1L << PG_active) |
@@ -2270,7 +2277,11 @@ static void __split_huge_page(struct page *page, struct list_head *list,
ClearPageCompound(head);
/* See comment in __split_huge_page_tail() */
if (PageAnon(head)) {
- page_ref_inc(head);
+ /* Additional pin to radix tree of swap cache */
+ if (PageSwapCache(head))
+ page_ref_add(head, 2);
+ else
+ page_ref_inc(head);
} else {
/* Additional pin to radix tree */
page_ref_add(head, 2);
@@ -2379,6 +2390,21 @@ int page_trans_huge_mapcount(struct page *page, int *total_mapcount)
return ret;
}
+/* Racy check whether the huge page can be split */
+bool can_split_huge_page(struct page *page, int *pextra_pins)
+{
+ int extra_pins;
+
+ /* Additional pins from radix tree */
+ if (PageAnon(page))
+ extra_pins = PageSwapCache(page) ? HPAGE_PMD_NR : 0;
+ else
+ extra_pins = HPAGE_PMD_NR;
+ if (pextra_pins)
+ *pextra_pins = extra_pins;
+ return total_mapcount(page) == page_count(page) - extra_pins - 1;
+}
+
/*
* This function splits huge page into normal pages. @page can point to any
* subpage of huge page to split. Split doesn't change the position of @page.
@@ -2426,7 +2452,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
ret = -EBUSY;
goto out;
}
- extra_pins = 0;
mapping = NULL;
anon_vma_lock_write(anon_vma);
} else {
@@ -2438,8 +2463,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
goto out;
}
- /* Addidional pins from radix tree */
- extra_pins = HPAGE_PMD_NR;
anon_vma = NULL;
i_mmap_lock_read(mapping);
}
@@ -2448,7 +2471,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
* Racy check if we can split the page, before freeze_page() will
* split PMDs
*/
- if (total_mapcount(head) != page_count(head) - extra_pins - 1) {
+ if (!can_split_huge_page(head, &extra_pins)) {
ret = -EBUSY;
goto out_unlock;
}