[PATCH 2/7] hugetlb, HWPOISON: move PG_HWPoison bit check

[Naoya Horiguchi <n-horiguchi@xxxxxxxxxxxxx>]

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@xxxxxxxxxxxxx>
Signed-off-by: Jun'ichi Nomura <j-nomura@xxxxxxxxxxxxx>
---
 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, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>