The huge page may be reallocated in soft_offline_page, because
MIGRATE_ISOLATE can not keep the page until after setting PG_hwpoison.
alloc_huge_page()
dequeue_huge_page_vma()
dequeue_huge_page_node()
If the huge page was reallocated, we need to try offline it again.
Signed-off-by: Xishi Qiu <qiuxi...@huawei.com>
---
mm/memory-failure.c | 21 ++++++++++++++++++---
1 files changed, 18 insertions(+), 3 deletions(-)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index b7c1716..f384249 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1505,8 +1505,11 @@ static int soft_offline_huge_page(struct page *page, int
flags)
if (ret > 0)
ret = -EIO;
} else {
+ ret = dequeue_hwpoisoned_huge_page(hpage);
+ /* If the page was reallocated, we need to try again. */
+ if (ret)
+ return -EAGAIN;
set_page_hwpoison_huge_page(hpage);
- dequeue_hwpoisoned_huge_page(hpage);
atomic_long_add(1 << compound_order(hpage),
&num_poisoned_pages);
}
@@ -1624,10 +1627,11 @@ static int __soft_offline_page(struct page *page, int
flags)
*/
int soft_offline_page(struct page *page, int flags)
{
- int ret;
+ int ret, retry_max = 3;
unsigned long pfn = page_to_pfn(page);
struct page *hpage = compound_trans_head(page);
+retry:
if (PageHWPoison(page)) {
pr_info("soft offline: %#lx page already poisoned\n", pfn);
return -EBUSY;
@@ -1663,8 +1667,15 @@ int soft_offline_page(struct page *page, int flags)
ret = __soft_offline_page(page, flags);
} else if (ret == 0) { /* for free pages */
if (PageHuge(page)) {
+ ret = dequeue_hwpoisoned_huge_page(hpage);
+ /* If the page was reallocated, we need to try again. */
+ if (ret) {
+ unset_migratetype_isolate(page,
+ MIGRATE_MOVABLE);
+ if (retry_max-- > 0)
+ goto retry;
+ }
set_page_hwpoison_huge_page(hpage);
- dequeue_hwpoisoned_huge_page(hpage);
atomic_long_add(1 << compound_order(hpage),
&num_poisoned_pages);
} else {
@@ -1673,5 +1684,9 @@ int soft_offline_page(struct page *page, int flags)
}
}
unset_migratetype_isolate(page, MIGRATE_MOVABLE);
+
+ if (ret == -EAGAIN && retry_max-- > 0)
+ goto retry;
+
return ret;
}
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
