[PATCH v19 6/8] mm: hugetlb: set the PageHWPoison to the raw error page

[Muchun Song]

Because we reuse the first tail vmemmap page frame and remap it
with read-only, we cannot set the PageHWPosion on some tail pages.
So we can use the head[4].private (There are at least 128 struct
page structures associated with the optimized HugeTLB page, so
using head[4].private is safe) to record the real error page index
and set the raw error page PageHWPoison later.

We cannot have more poisoned tail pages. So a single slot is
sufficient. Why?

memory_failure()
    if (PageHuge(page))
        memory_failure_hugetlb()
            head = compound_head(page)
            if (TestSetPageHWPoison(head))
                return

Because we do not clear the HWPoison of the head page, we cannot
poison another tail page.

Note: some pages might miss their poisoning (even without this patch).

Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Reviewed-by: Oscar Salvador <osalvador@xxxxxxx>
Acked-by: David Rientjes <rientjes@xxxxxxxxxx>
Tested-by: Chen Huang <chenhuang5@xxxxxxxxxx>
Tested-by: Bodeddula Balasubramaniam <bodeddub@xxxxxxxxxx>
---
 include/linux/hugetlb.h |  3 ++
 mm/hugetlb.c            | 81 +++++++++++++++++++++++++++++++++++++++++++------
 2 files changed, 75 insertions(+), 9 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 09421f5f35e2..7f7a0e3405ae 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -42,6 +42,9 @@ enum {
 	SUBPAGE_INDEX_CGROUP_RSVD,	/* reuse page->private */
 	__MAX_CGROUP_SUBPAGE_INDEX = SUBPAGE_INDEX_CGROUP_RSVD,
 #endif
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+	SUBPAGE_INDEX_HWPOISON,		/* reuse page->private */
+#endif
 	__NR_USED_SUBPAGE,
 };
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e42b19337a8f..53f239818293 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1304,6 +1304,74 @@ static inline void destroy_compound_gigantic_page(struct page *page,
 						unsigned int order) { }
 #endif
 
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+static inline void hwpoison_subpage_deliver(struct hstate *h, struct page *head)
+{
+	struct page *page;
+
+	if (!PageHWPoison(head) || !free_vmemmap_pages_per_hpage(h))
+		return;
+
+	page = head + page_private(head + SUBPAGE_INDEX_HWPOISON);
+
+	/*
+	 * Move PageHWPoison flag from head page to the raw error page,
+	 * which makes any subpages rather than the error page reusable.
+	 */
+	if (page != head) {
+		SetPageHWPoison(page);
+		ClearPageHWPoison(head);
+	}
+}
+
+static inline void hwpoison_subpage_set(struct hstate *h, struct page *head,
+					struct page *page)
+{
+	if (!PageHWPoison(head))
+		return;
+
+	if (free_vmemmap_pages_per_hpage(h)) {
+		set_page_private(head + SUBPAGE_INDEX_HWPOISON, page - head);
+	} else if (page != head) {
+		/*
+		 * Move PageHWPoison flag from head page to the raw error page,
+		 * which makes any subpages rather than the error page reusable.
+		 */
+		SetPageHWPoison(page);
+		ClearPageHWPoison(head);
+	}
+}
+
+static inline void hwpoison_subpage_clear(struct hstate *h, struct page *head)
+{
+	if (!PageHWPoison(head) || !free_vmemmap_pages_per_hpage(h))
+		return;
+
+	set_page_private(head + SUBPAGE_INDEX_HWPOISON, 0);
+}
+#else
+static inline void hwpoison_subpage_deliver(struct hstate *h, struct page *head)
+{
+}
+
+static inline void hwpoison_subpage_set(struct hstate *h, struct page *head,
+					struct page *page)
+{
+	if (PageHWPoison(head) && page != head) {
+		/*
+		 * Move PageHWPoison flag from head page to the raw error page,
+		 * which makes any subpages rather than the error page reusable.
+		 */
+		SetPageHWPoison(page);
+		ClearPageHWPoison(head);
+	}
+}
+
+static inline void hwpoison_subpage_clear(struct hstate *h, struct page *head)
+{
+}
+#endif
+
 static int update_and_free_page_surplus(struct hstate *h, struct page *page,
 					bool acct_surplus)
 	__releases(&hugetlb_lock) __acquires(&hugetlb_lock)
@@ -1807,22 +1875,17 @@ int dissolve_free_huge_page(struct page *page)
 			goto retry;
 		}
 
-		/*
-		 * Move PageHWPoison flag from head page to the raw error page,
-		 * which makes any subpages rather than the error page reusable.
-		 */
-		if (PageHWPoison(head) && page != head) {
-			SetPageHWPoison(page);
-			ClearPageHWPoison(head);
-		}
+		hwpoison_subpage_set(h, head, page);
 		list_del(&head->lru);
 		ClearHPageFreed(page);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;
 		h->max_huge_pages--;
 		rc = update_and_free_page_surplus(h, head, false);
-		if (rc)
+		if (rc) {
 			h->max_huge_pages++;
+			hwpoison_subpage_clear(h, head);
+		}
 	}
 out:
 	spin_unlock(&hugetlb_lock);
-- 
2.11.0