From: Naoya Horiguchi on
In order to handle metadatum correctly, we should check whether the hugepage
we are going to access is HWPOISONed *before* incrementing mapcount,
adding the hugepage into pagecache or constructing anon_vma.
This patch also adds retry code when there is a race between
alloc_huge_page() and memory failure.

Signed-off-by: Naoya Horiguchi <n-horiguchi(a)ah.jp.nec.com>
Signed-off-by: Jun'ichi Nomura <j-nomura(a)ce.jp.nec.com>
---
mm/hugetlb.c | 34 +++++++++++++++++++++-------------
1 files changed, 21 insertions(+), 13 deletions(-)

diff --git v2.6.35-rc3-hwpoison/mm/hugetlb.c v2.6.35-rc3-hwpoison/mm/hugetlb.c
index a26c24a..5c77a73 100644
--- v2.6.35-rc3-hwpoison/mm/hugetlb.c
+++ v2.6.35-rc3-hwpoison/mm/hugetlb.c
@@ -2490,8 +2490,15 @@ retry:
int err;
struct inode *inode = mapping->host;

- err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
+ lock_page(page);
+ if (unlikely(PageHWPoison(page))) {
+ unlock_page(page);
+ goto retry;
+ }
+ err = add_to_page_cache_locked(page, mapping,
+ idx, GFP_KERNEL);
if (err) {
+ unlock_page(page);
put_page(page);
if (err == -EEXIST)
goto retry;
@@ -2504,6 +2511,10 @@ retry:
page_dup_rmap(page);
} else {
lock_page(page);
+ if (unlikely(PageHWPoison(page))) {
+ unlock_page(page);
+ goto retry;
+ }
if (unlikely(anon_vma_prepare(vma))) {
ret = VM_FAULT_OOM;
goto backout_unlocked;
@@ -2511,22 +2522,19 @@ retry:
hugepage_add_new_anon_rmap(page, vma, address);
}
} else {
+ /*
+ * If memory error occurs between mmap() and fault, some process
+ * don't have hwpoisoned swap entry for errored virtual address.
+ * So we need to block hugepage fault by PG_hwpoison bit check.
+ */
+ if (unlikely(PageHWPoison(page))) {
+ ret = VM_FAULT_HWPOISON;
+ goto backout_unlocked;
+ }
page_dup_rmap(page);
}

/*
- * Since memory error handler replaces pte into hwpoison swap entry
- * at the time of error handling, a process which reserved but not have
- * the mapping to the error hugepage does not have hwpoison swap entry.
- * So we need to block accesses from such a process by checking
- * PG_hwpoison bit here.
- */
- if (unlikely(PageHWPoison(page))) {
- ret = VM_FAULT_HWPOISON;
- goto backout_unlocked;
- }
-
- /*
* If we are going to COW a private mapping later, we examine the
* pending reservations for this page now. This will ensure that
* any allocations necessary to record that reservation occur outside
--
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/