For HugeTLB page, there are more metadata to save in the struct page.
But the head struct page cannot meet our needs, so we have to abuse
other tail struct page to store the metadata. In order to avoid
conflicts caused by subsequent use of more tail struct pages, we can
gather these discrete indexes of tail struct page. In this case, it
will be easier to add a new tail page index later.
There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct
page structs that can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP,
so add a BUILD_BUG_ON to catch invalid usage of the tail struct page.
Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Reviewed-by: Oscar Salvador <osalvador@xxxxxxx>
---
include/linux/hugetlb.h | 13 +++++++++++++
include/linux/hugetlb_cgroup.h | 15 +++++++++------
mm/hugetlb.c | 35 +++++++++++++++++++++++++++--------
mm/hugetlb_vmemmap.c | 8 ++++++++
4 files changed, 57 insertions(+), 14 deletions(-)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 66d82ae7b712..7295f6b3d55e 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -28,6 +28,19 @@ typedef struct { unsigned long pd; } hugepd_t;
#include <linux/shm.h>
#include <asm/tlbflush.h>
+enum {
+ SUBPAGE_INDEX_ACTIVE = 1, /* reuse page flags of PG_private */
+ SUBPAGE_INDEX_TEMPORARY, /* reuse page->mapping */
+#ifdef CONFIG_CGROUP_HUGETLB
+ SUBPAGE_INDEX_CGROUP = SUBPAGE_INDEX_TEMPORARY,/* reuse page->private */
+ SUBPAGE_INDEX_CGROUP_RSVD, /* reuse page->private */
+#endif
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+ SUBPAGE_INDEX_HWPOISON, /* reuse page->private */
+#endif
+ NR_USED_SUBPAGE,
+};
+
struct hugepage_subpool {
spinlock_t lock;
long count;
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index 2ad6e92f124a..3d3c1c49efe4 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -24,8 +24,9 @@ struct file_region;
/*
* Minimum page order trackable by hugetlb cgroup.
* At least 4 pages are necessary for all the tracking information.
- * The second tail page (hpage[2]) is the fault usage cgroup.
- * The third tail page (hpage[3]) is the reservation usage cgroup.
+ * The second tail page (hpage[SUBPAGE_INDEX_CGROUP]) is the fault
+ * usage cgroup. The third tail page (hpage[SUBPAGE_INDEX_CGROUP_RSVD])
+ * is the reservation usage cgroup.
*/
#define HUGETLB_CGROUP_MIN_ORDER 2
@@ -66,9 +67,9 @@ __hugetlb_cgroup_from_page(struct page *page, bool rsvd)
if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
return NULL;
if (rsvd)
- return (struct hugetlb_cgroup *)page[3].private;
+ return (void *)page_private(page + SUBPAGE_INDEX_CGROUP_RSVD);
else
- return (struct hugetlb_cgroup *)page[2].private;
+ return (void *)page_private(page + SUBPAGE_INDEX_CGROUP);
}
static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
@@ -90,9 +91,11 @@ static inline int __set_hugetlb_cgroup(struct page *page,
if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
return -1;
if (rsvd)
- page[3].private = (unsigned long)h_cg;
+ set_page_private(page + SUBPAGE_INDEX_CGROUP_RSVD,
+ (unsigned long)h_cg);
else
- page[2].private = (unsigned long)h_cg;
+ set_page_private(page + SUBPAGE_INDEX_CGROUP,
+ (unsigned long)h_cg);
return 0;
}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f19e841236d7..2764af5fa0b3 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1356,6 +1356,7 @@ static inline void __update_and_free_page(struct hstate *h, struct page *page)
schedule_work(&hpage_update_work);
}
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
static inline void hwpoison_subpage_deliver(struct hstate *h, struct page *head)
{
struct page *page;
@@ -1363,7 +1364,7 @@ static inline void hwpoison_subpage_deliver(struct hstate *h, struct page *head)
if (!PageHWPoison(head) || !free_vmemmap_pages_per_hpage(h))
return;
- page = head + page_private(head + 4);
+ page = head + page_private(head + SUBPAGE_INDEX_HWPOISON);
/*
* Move PageHWPoison flag from head page to the raw error page,
@@ -1382,7 +1383,7 @@ static inline void hwpoison_subpage_set(struct hstate *h, struct page *head,
return;
if (free_vmemmap_pages_per_hpage(h)) {
- set_page_private(head + 4, page - head);
+ set_page_private(head + SUBPAGE_INDEX_HWPOISON, page - head);
} else if (page != head) {
/*
* Move PageHWPoison flag from head page to the raw error page,
@@ -1392,6 +1393,24 @@ static inline void hwpoison_subpage_set(struct hstate *h, struct page *head,
ClearPageHWPoison(head);
}
}
+#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);
+ }
+}
+#endif
static void update_and_free_page(struct hstate *h, struct page *page)
{
@@ -1459,20 +1478,20 @@ struct hstate *size_to_hstate(unsigned long size)
bool page_huge_active(struct page *page)
{
VM_BUG_ON_PAGE(!PageHuge(page), page);
- return PageHead(page) && PagePrivate(&page[1]);
+ return PageHead(page) && PagePrivate(&page[SUBPAGE_INDEX_ACTIVE]);
}
/* never called for tail page */
static void set_page_huge_active(struct page *page)
{
VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
- SetPagePrivate(&page[1]);
+ SetPagePrivate(&page[SUBPAGE_INDEX_ACTIVE]);
}
static void clear_page_huge_active(struct page *page)
{
VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
- ClearPagePrivate(&page[1]);
+ ClearPagePrivate(&page[SUBPAGE_INDEX_ACTIVE]);
}
/*
@@ -1484,17 +1503,17 @@ static inline bool PageHugeTemporary(struct page *page)
if (!PageHuge(page))
return false;
- return (unsigned long)page[2].mapping == -1U;
+ return (unsigned long)page[SUBPAGE_INDEX_TEMPORARY].mapping == -1U;
}
static inline void SetPageHugeTemporary(struct page *page)
{
- page[2].mapping = (void *)-1U;
+ page[SUBPAGE_INDEX_TEMPORARY].mapping = (void *)-1U;
}
static inline void ClearPageHugeTemporary(struct page *page)
{
- page[2].mapping = NULL;
+ page[SUBPAGE_INDEX_TEMPORARY].mapping = NULL;
}
static void __free_huge_page(struct page *page)
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 7dcb4aa1e512..6b8f7bb2273e 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -242,6 +242,14 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
unsigned int nr_pages = pages_per_huge_page(h);
unsigned int vmemmap_pages;
+ /*
+ * There are only (RESERVE_VMEMMAP_SIZE / sizeof(struct page)) struct
+ * page structs that can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP,
+ * so add a BUILD_BUG_ON to catch invalid usage of the tail struct page.
+ */
+ BUILD_BUG_ON(NR_USED_SUBPAGE >=
+ RESERVE_VMEMMAP_SIZE / sizeof(struct page));
+
if (!hugetlb_free_vmemmap_enabled)
return;
--
2.11.0
