mm: hugetlb: introduce nr_free_vmemmap_pages in the struct hstate

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.

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.

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Muchun Song <[email protected]>
Acked-by: Mike Kravetz <[email protected]>
Reviewed-by: Oscar Salvador <[email protected]>
Reviewed-by: Miaohe Lin <[email protected]>
Tested-by: Chen Huang <[email protected]>
Tested-by: Bodeddula Balasubramaniam <[email protected]>
Cc: Alexander Viro <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Anshuman Khandual <[email protected]>
Cc: Balbir Singh <[email protected]>
Cc: Barry Song <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: David Rientjes <[email protected]>
Cc: HORIGUCHI NAOYA <[email protected]>
Cc: "H. Peter Anvin" <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Joao Martins <[email protected]>
Cc: Joerg Roedel <[email protected]>
Cc: Jonathan Corbet <[email protected]>
Cc: Matthew Wilcox <[email protected]>
Cc: Michal Hocko <[email protected]>
Cc: Mina Almasry <[email protected]>
Cc: Oliver Neukum <[email protected]>
Cc: Paul E. McKenney <[email protected]>
Cc: Pawan Gupta <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Randy Dunlap <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Xiongchun Duan <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Author: Muchun Song

include/linux/hugetlb.h

@@ -608,6 +608,9 @@ 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];

mm/hugetlb.c

@@ -3585,6 +3585,7 @@ 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;
 }

mm/hugetlb_vmemmap.c

@@ -262,3 +262,36 @@ void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 
 	SetHPageVmemmapOptimized(head);
 }
+
+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;
+
+	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);
+}

mm/hugetlb_vmemmap.h

@@ -13,17 +13,15 @@
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
 int 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 int alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
@@ -35,6 +33,10 @@ static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }
 
+static inline void hugetlb_vmemmap_init(struct hstate *h)
+{
+}
+
 static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
 {
 	return 0;