[RFC PATCH 05/24] mm/hugetlb: Introduce nr_free_vmemmap_pages in the struct hstate

[Muchun Song <songmuchun@bytedance.com>]

If the size of hugetlb page is 2MB, we need 512 struct page structures
(8 pages) to be associated with it. As far as I know, we only use the
first 3 struct page structures and only read the compound_dtor members
of the remaining struct page structures. For tail page, the value of
compound_dtor is the same. So we can reuse first tail page. We map the
virtual addresses of the remaining 6 tail pages to the first tail page,
and then free these 6 pages. Therefore, we need to reserve at least 2
pages as vmemmap areas.

So we introduce a new nr_free_vmemmap_pages field in the hstate to
indicate how many vmemmap pages associated with a hugetlb page that we
can free to buddy system.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 include/linux/hugetlb.h |  3 +++
 mm/hugetlb.c            | 35 +++++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d5cc5f802dd4..eed3dd3bd626 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -492,6 +492,9 @@ struct hstate {
 	unsigned int nr_huge_pages_node[MAX_NUMNODES];
 	unsigned int free_huge_pages_node[MAX_NUMNODES];
 	unsigned int surplus_huge_pages_node[MAX_NUMNODES];
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+	unsigned int nr_free_vmemmap_pages;
+#endif
 #ifdef CONFIG_CGROUP_HUGETLB
 	/* cgroup control files */
 	struct cftype cgroup_files_dfl[7];
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 81a41aa080a5..f1b2b733b49b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1292,6 +1292,39 @@ static inline void destroy_compound_gigantic_page(struct page *page,
 						unsigned int order) { }
 #endif
 
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+#define RESERVE_VMEMMAP_NR	2U
+
+static inline unsigned int nr_free_vmemmap(struct hstate *h)
+{
+	return h->nr_free_vmemmap_pages;
+}
+
+static void __init hugetlb_vmemmap_init(struct hstate *h)
+{
+	unsigned int order = huge_page_order(h);
+	unsigned int vmemmap_pages;
+
+	vmemmap_pages = ((1 << order) * sizeof(struct page)) >> PAGE_SHIFT;
+	/*
+	 * The head page and the first tail page not free to buddy system,
+	 * the others page will map to the first tail page. So there are
+	 * (@vmemmap_pages - RESERVE_VMEMMAP_NR) pages can be freed.
+	 */
+	if (vmemmap_pages > RESERVE_VMEMMAP_NR)
+		h->nr_free_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR;
+	else
+		h->nr_free_vmemmap_pages = 0;
+
+	pr_info("HugeTLB: can free %d vmemmap pages for %s\n",
+		h->nr_free_vmemmap_pages, h->name);
+}
+#else
+static inline void hugetlb_vmemmap_init(struct hstate *h)
+{
+}
+#endif
+
 static void update_and_free_page(struct hstate *h, struct page *page)
 {
 	int i;
@@ -3285,6 +3318,8 @@ void __init hugetlb_add_hstate(unsigned int order)
 	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
 					huge_page_size(h)/1024);
 
+	hugetlb_vmemmap_init(h);
+
 	parsed_hstate = h;
 }
 
-- 
2.20.1