[PATCH v10 09/11] mm/hugetlb: Introduce nr_free_vmemmap_pages in the struct hstate

[Muchun Song]

All the infrastructure is ready, so we introduce nr_free_vmemmap_pages
field in the hstate to indicate how many vmemmap pages associated with
a HugeTLB page that can be freed to buddy allocator. And initialize it
in the hugetlb_vmemmap_init(). This patch is actual enablement of the
feature.

Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
Acked-by: Mike Kravetz <mike.kravetz@xxxxxxxxxx>
Reviewed-by: Oscar Salvador <osalvador@xxxxxxx>
---
 include/linux/hugetlb.h |  3 +++
 mm/hugetlb.c            |  1 +
 mm/hugetlb_vmemmap.c    | 33 +++++++++++++++++++++++++++++++++
 mm/hugetlb_vmemmap.h    | 10 ++++++----
 4 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 7f47f0eeca3b..66d82ae7b712 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 fea8a96dd718..6c02f49959fd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3326,6 +3326,7 @@ void __init hugetlb_add_hstate(unsigned int order)
 	h->next_nid_to_free = first_memory_node;
 	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
 					huge_page_size(h)/1024);
+	hugetlb_vmemmap_init(h);
 
 	parsed_hstate = h;
 }
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 9e9bd458a3f5..3ebfe1706c77 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -166,6 +166,8 @@
  * (last) level. So this type of HugeTLB page can be optimized only when its
  * size of the struct page structs is greater than 2 pages.
  */
+#define pr_fmt(fmt)	"HugeTLB: " fmt
+
 #include "hugetlb_vmemmap.h"
 
 /*
@@ -182,6 +184,12 @@ bool hugetlb_free_vmemmap_enabled;
 
 static int __init early_hugetlb_free_vmemmap_param(char *buf)
 {
+	/* We cannot optimize if a "struct page" crosses page boundaries. */
+	if ((!is_power_of_2(sizeof(struct page)))) {
+		pr_warn("cannot free vmemmap pages because \"struct page\" crosses page boundaries\n");
+		return 0;
+	}
+
 	if (!buf)
 		return -EINVAL;
 
@@ -220,3 +228,28 @@ void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 	vmemmap_remap_free(vmemmap_addr + RESERVE_VMEMMAP_SIZE,
 			   free_vmemmap_pages_size_per_hpage(h));
 }
+
+void __init hugetlb_vmemmap_init(struct hstate *h)
+{
+	unsigned int nr_pages = pages_per_huge_page(h);
+	unsigned int vmemmap_pages;
+
+	if (!hugetlb_free_vmemmap_enabled)
+		return;
+
+	vmemmap_pages = (nr_pages * sizeof(struct page)) >> PAGE_SHIFT;
+	/*
+	 * The head page and the first tail page are not to be freed to buddy
+	 * allocator, the other pages will map to the first tail page, so they
+	 * can be freed.
+	 *
+	 * Could RESERVE_VMEMMAP_NR be greater than @vmemmap_pages? It is true
+	 * on some architectures (e.g. aarch64). See Documentation/arm64/
+	 * hugetlbpage.rst for more details.
+	 */
+	if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR))
+		h->nr_free_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR;
+
+	pr_info("can free %d vmemmap pages for %s\n", h->nr_free_vmemmap_pages,
+		h->name);
+}
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index b2c8d2f11d48..8fd9ae113dbd 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -13,17 +13,15 @@
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
 void alloc_huge_page_vmemmap(struct hstate *h, struct page *head);
 void free_huge_page_vmemmap(struct hstate *h, struct page *head);
+void hugetlb_vmemmap_init(struct hstate *h);
 
 /*
  * How many vmemmap pages associated with a HugeTLB page that can be freed
  * to the buddy allocator.
- *
- * Todo: Returns zero for now, which means the feature is disabled. We will
- * enable it once all the infrastructure is there.
  */
 static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
 {
-	return 0;
+	return h->nr_free_vmemmap_pages;
 }
 #else
 static inline void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
@@ -38,5 +36,9 @@ static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
 {
 	return 0;
 }
+
+static inline void hugetlb_vmemmap_init(struct hstate *h)
+{
+}
 #endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
 #endif /* _LINUX_HUGETLB_VMEMMAP_H */
-- 
2.11.0