[PATCH v3 14/21] mm/hugetlb: Support freeing vmemmap pages of gigantic page

[Muchun Song <songmuchun@xxxxxxxxxxxxx>]

The gigantic page is allocated by bootmem, if we want to free the
unused vmemmap pages. We also should allocate the page table. So
we also allocate page tables from bootmem.

Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
---
 include/linux/hugetlb.h |  3 +++
 mm/hugetlb.c            | 71 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 74 insertions(+)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index afb9b18771c4..f8ca4d251aa8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -506,6 +506,9 @@ struct hstate {
 struct huge_bootmem_page {
 	struct list_head list;
 	struct hstate *hstate;
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+	pte_t *vmemmap_pte;
+#endif
 };
 
 struct page *alloc_huge_page(struct vm_area_struct *vma,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9b1ac52d9fdd..ec0d33d2c426 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1419,6 +1419,62 @@ static void vmemmap_pgtable_free(struct hstate *h, struct page *page)
 		pte_free_kernel(&init_mm, page_to_virt(pgtable));
 }
 
+static unsigned long __init gather_vmemmap_pgtable_prealloc(void)
+{
+	struct huge_bootmem_page *m, *tmp;
+	unsigned long nr_free = 0;
+
+	list_for_each_entry_safe(m, tmp, &huge_boot_pages, list) {
+		struct hstate *h = m->hstate;
+		unsigned int nr = pgtable_pages_to_prealloc_per_hpage(h);
+		unsigned int pgtable_size;
+
+		if (!nr)
+			continue;
+
+		pgtable_size = nr << PAGE_SHIFT;
+		m->vmemmap_pte = memblock_alloc_try_nid(pgtable_size,
+				PAGE_SIZE, 0, MEMBLOCK_ALLOC_ACCESSIBLE,
+				NUMA_NO_NODE);
+		if (!m->vmemmap_pte) {
+			nr_free++;
+			list_del(&m->list);
+			memblock_free_early(__pa(m), huge_page_size(h));
+		}
+	}
+
+	return nr_free;
+}
+
+static void __init gather_vmemmap_pgtable_init(struct huge_bootmem_page *m,
+					       struct page *page)
+{
+	int i;
+	struct hstate *h = m->hstate;
+	unsigned long pte = (unsigned long)m->vmemmap_pte;
+	unsigned int nr = pgtable_pages_to_prealloc_per_hpage(h);
+
+	if (!nr)
+		return;
+
+	vmemmap_pgtable_init(page);
+
+	for (i = 0; i < nr; i++, pte += PAGE_SIZE) {
+		pgtable_t pgtable = virt_to_page(pte);
+
+		__ClearPageReserved(pgtable);
+		vmemmap_pgtable_deposit(page, pgtable);
+	}
+
+	/*
+	 * If we had gigantic hugepages allocated at boot time, we need
+	 * to restore the 'stolen' pages to totalram_pages in order to
+	 * fix confusing memory reports from free(1) and another
+	 * side-effects, like CommitLimit going negative.
+	 */
+	adjust_managed_page_count(page, nr);
+}
+
 static void __init hugetlb_vmemmap_init(struct hstate *h)
 {
 	unsigned int order = huge_page_order(h);
@@ -1752,6 +1808,16 @@ static inline void vmemmap_pgtable_free(struct hstate *h, struct page *page)
 {
 }
 
+static inline unsigned long gather_vmemmap_pgtable_prealloc(void)
+{
+	return 0;
+}
+
+static inline void gather_vmemmap_pgtable_init(struct huge_bootmem_page *m,
+					       struct page *page)
+{
+}
+
 static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }
@@ -3013,6 +3079,7 @@ static void __init gather_bootmem_prealloc(void)
 		WARN_ON(page_count(page) != 1);
 		prep_compound_huge_page(page, h->order);
 		WARN_ON(PageReserved(page));
+		gather_vmemmap_pgtable_init(m, page);
 		prep_new_huge_page(h, page, page_to_nid(page));
 		put_page(page); /* free it into the hugepage allocator */
 
@@ -3065,6 +3132,10 @@ static void __init hugetlb_hstate_alloc_pages(struct hstate *h)
 			break;
 		cond_resched();
 	}
+
+	if (hstate_is_gigantic(h))
+		i -= gather_vmemmap_pgtable_prealloc();
+
 	if (i < h->max_huge_pages) {
 		char buf[32];
 
-- 
2.11.0