[PATCH v14 4/8] mm: hugetlb: alloc the vmemmap pages associated with each HugeTLB page

@@ -2981,6 +2981,8 @@ static inline void print_vma_addr(char *prefix, unsigned long rip)
 
 void vmemmap_remap_free(unsigned long start, unsigned long end,
 			unsigned long reuse);
+int vmemmap_remap_alloc(unsigned long start, unsigned long end,
+			unsigned long reuse, gfp_t gfp_mask);
 
 void *sparse_buffer_alloc(unsigned long size);
 struct page * __populate_section_memmap(unsigned long pfn,

@@ -1397,16 +1397,26 @@ static void __free_huge_page(struct page *page)
 		h->resv_huge_pages++;
 
 	if (HPageTemporary(page)) {
-		list_del(&page->lru);
 		ClearHPageTemporary(page);
+
+		if (alloc_huge_page_vmemmap(h, page, GFP_ATOMIC)) {
+			h->surplus_huge_pages++;
+			h->surplus_huge_pages_node[nid]++;
+			goto enqueue;
+		}
+		list_del(&page->lru);
 		update_and_free_page(h, page);
 	} else if (h->surplus_huge_pages_node[nid]) {
+		if (alloc_huge_page_vmemmap(h, page, GFP_ATOMIC))
+			goto enqueue;
+
 		/* remove the page from active list */
 		list_del(&page->lru);
 		update_and_free_page(h, page);
 		h->surplus_huge_pages--;
 		h->surplus_huge_pages_node[nid]--;
 	} else {
+enqueue:
 		arch_clear_hugepage_flags(page);
 		enqueue_huge_page(h, page);
 	}

@@ -1693,6 +1703,10 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
 			struct page *page =
 				list_entry(h->hugepage_freelists[node].next,
 					  struct page, lru);
+
+			if (alloc_huge_page_vmemmap(h, page, GFP_ATOMIC))
+				break;
+
 			list_del(&page->lru);
 			h->free_huge_pages--;
 			h->free_huge_pages_node[node]--;

@@ -1760,6 +1774,9 @@ int dissolve_free_huge_page(struct page *page)
 			goto retry;
 		}
 
+		if (alloc_huge_page_vmemmap(h, head, GFP_ATOMIC))
+			goto out;
+
 		/*
 		 * Move PageHWPoison flag from head page to the raw error page,
 		 * which makes any subpages rather than the error page reusable.

@@ -169,6 +169,8 @@
  * (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"
 
 /*

@@ -198,6 +200,34 @@ static inline unsigned long free_vmemmap_pages_size_per_hpage(struct hstate *h)
 	return (unsigned long)free_vmemmap_pages_per_hpage(h) << PAGE_SHIFT;
 }
 
+int alloc_huge_page_vmemmap(struct hstate *h, struct page *head, gfp_t gfp_mask)
+{
+	int ret;
+	unsigned long vmemmap_addr = (unsigned long)head;
+	unsigned long vmemmap_end, vmemmap_reuse;
+
+	if (!free_vmemmap_pages_per_hpage(h))
+		return 0;
+
+	vmemmap_addr += RESERVE_VMEMMAP_SIZE;
+	vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h);
+	vmemmap_reuse = vmemmap_addr - PAGE_SIZE;
+
+	/*
+	 * The pages which the vmemmap virtual address range [@vmemmap_addr,
+	 * @vmemmap_end) are mapped to are freed to the buddy allocator, and
+	 * the range is mapped to the page which @vmemmap_reuse is mapped to.
+	 * When a HugeTLB page is freed to the buddy allocator, previously
+	 * discarded vmemmap pages must be allocated and remapping.
+	 */
+	ret = vmemmap_remap_alloc(vmemmap_addr, vmemmap_end, vmemmap_reuse,
+				  gfp_mask | __GFP_NOWARN | __GFP_THISNODE);
+	if (ret == -ENOMEM)
+		pr_info("cannot alloc vmemmap pages\n");
+
+	return ret;
+}
+
 void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 	unsigned long vmemmap_addr = (unsigned long)head;

@@ -11,8 +11,16 @@
 #include <linux/hugetlb.h>
 
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+int alloc_huge_page_vmemmap(struct hstate *h, struct page *head,
+			    gfp_t gfp_mask);
 void free_huge_page_vmemmap(struct hstate *h, struct page *head);
 #else
+static inline int alloc_huge_page_vmemmap(struct hstate *h, struct page *head,
+					  gfp_t gfp_mask)
+{
+	return 0;
+}
+
 static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }

@@ -40,7 +40,8 @@
  * @remap_pte:		called for each non-empty PTE (lowest-level) entry.
  * @reuse_page:		the page which is reused for the tail vmemmap pages.
  * @reuse_addr:		the virtual address of the @reuse_page page.
- * @vmemmap_pages:	the list head of the vmemmap pages that can be freed.
+ * @vmemmap_pages:	the list head of the vmemmap pages that can be freed
+ *			or is mapped from.
  */
 struct vmemmap_remap_walk {
 	void (*remap_pte)(pte_t *pte, unsigned long addr,

@@ -237,6 +238,78 @@ void vmemmap_remap_free(unsigned long start, unsigned long end,
 	free_vmemmap_page_list(&vmemmap_pages);
 }
 
+static void vmemmap_restore_pte(pte_t *pte, unsigned long addr,
+				struct vmemmap_remap_walk *walk)
+{
+	pgprot_t pgprot = PAGE_KERNEL;
+	struct page *page;
+	void *to;
+
+	BUG_ON(pte_page(*pte) != walk->reuse_page);
+
+	page = list_first_entry(walk->vmemmap_pages, struct page, lru);
+	list_del(&page->lru);
+	to = page_to_virt(page);
+	copy_page(to, (void *)walk->reuse_addr);
+
+	set_pte_at(&init_mm, addr, pte, mk_pte(page, pgprot));
+}
+
+static int alloc_vmemmap_page_list(unsigned long start, unsigned long end,
+				   gfp_t gfp_mask, struct list_head *list)
+{
+	unsigned long addr;
+	int nid = page_to_nid((const void *)start);
+	struct page *page, *next;
+
+	for (addr = start; addr < end; addr += PAGE_SIZE) {
+		page = alloc_pages_node(nid, gfp_mask, 0);
+		if (!page)
+			goto out;
+		list_add_tail(&page->lru, list);
+	}
+
+	return 0;
+out:
+	list_for_each_entry_safe(page, next, list, lru)
+		__free_pages(page, 0);
+	return -ENOMEM;
+}
+
+/**
+ * vmemmap_remap_alloc - remap the vmemmap virtual address range [@start, end)
+ *			 to the page which is from the @vmemmap_pages
+ *			 respectively.
+ * @start:	start address of the vmemmap virtual address range that we want
+ *		to remap.
+ * @end:	end address of the vmemmap virtual address range that we want to
+ *		remap.
+ * @reuse:	reuse address.
+ * @gpf_mask:	GFP flag for allocating vmemmap pages.
+ */
+int vmemmap_remap_alloc(unsigned long start, unsigned long end,
+			unsigned long reuse, gfp_t gfp_mask)
+{
+	LIST_HEAD(vmemmap_pages);
+	struct vmemmap_remap_walk walk = {
+		.remap_pte	= vmemmap_restore_pte,
+		.reuse_addr	= reuse,
+		.vmemmap_pages	= &vmemmap_pages,
+	};
+
+	/* See the comment in the vmemmap_remap_free(). */
+	BUG_ON(start - reuse != PAGE_SIZE);
+
+	might_sleep_if(gfpflags_allow_blocking(gfp_mask));
+
+	if (alloc_vmemmap_page_list(start, end, gfp_mask, &vmemmap_pages))
+		return -ENOMEM;
+
+	vmemmap_remap_range(reuse, end, &walk);
+
+	return 0;
+}
+
 /*
  * Allocate a block of memory to be used to back the virtual memory map
  * or to back the page tables that are used to create the mapping.