diff mbox series

[v17,5/9] mm: hugetlb: set the PageHWPoison to the raw error page

Message ID 20210225132130.26451-6-songmuchun@bytedance.com (mailing list archive)
State New, archived
Headers show
Series Free some vmemmap pages of HugeTLB page | expand

Commit Message

Muchun Song Feb. 25, 2021, 1:21 p.m. UTC 
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.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: David Rientjes <rientjes@google.com>
---
 mm/hugetlb.c | 80 ++++++++++++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 72 insertions(+), 8 deletions(-)

Comments

Education Directorate March 7, 2021, 8:18 a.m. UTC | #1 
On Thu, Feb 25, 2021 at 09:21:26PM +0800, Muchun Song wrote:
> 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.
>

Does the hardcoding of 4 come from HUGETLB_CGROUP_MIN_ORDER, if so
do we need to hardcode 4? Also, I am not sure about the comment
on safety and 128 struct pages

Balbir
Muchun Song March 7, 2021, 8:39 a.m. UTC | #2 
On Sun, Mar 7, 2021 at 4:19 PM Balbir Singh <bsingharora@gmail.com> wrote:
>
> On Thu, Feb 25, 2021 at 09:21:26PM +0800, Muchun Song wrote:
> > 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.
> >
>
> Does the hardcoding of 4 come from HUGETLB_CGROUP_MIN_ORDER, if so

Yes.

> do we need to hardcode 4? Also, I am not sure about the comment
> on safety and 128 struct pages

We can set head[4].private only if free_vmemmap_pages_per_hpage(h)
returns true. In this case, there are 128 struct page structures (we reserve
2 pages as vmemmap pages, so 2 * 4KB / sizeof(struct page) == 128) that
can be used. Instead of hardcode, I introduce another patch to make the
code more readable. Please refer to patch #8 in this series.

Thanks.

>
> Balbir
>
diff mbox series

Patch

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index b6e4e3f31ad2..bccb6907833f 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 + 4);
+
+	/*
+	 * 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 + 4, 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 + 4, 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(struct hstate *h, struct page *page)
 	__releases(&hugetlb_lock) __acquires(&hugetlb_lock)
 {
@@ -1357,6 +1425,8 @@  static int update_and_free_page(struct hstate *h, struct page *page)
 		return -ENOMEM;
 	}
 
+	hwpoison_subpage_deliver(h, page);
+
 	for (i = 0; i < pages_per_huge_page(h);
 	     i++, subpage = mem_map_next(subpage, page, i)) {
 		subpage->flags &= ~(1 << PG_locked | 1 << PG_error |
@@ -1801,14 +1871,7 @@  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);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;
@@ -1818,6 +1881,7 @@  int dissolve_free_huge_page(struct page *page)
 			h->surplus_huge_pages--;
 			h->surplus_huge_pages_node[nid]--;
 			h->max_huge_pages++;
+			hwpoison_subpage_clear(h, head);
 		}
 	}
 out: