[PATCH v3 11/21] mm/hugetlb: Allocate the vmemmap pages associated with each hugetlb page

[Muchun Song <songmuchun@xxxxxxxxxxxxx>]

When we free a hugetlb page to the buddy, we should allocate the vmemmap
pages associated with it. We can do that in the __free_hugepage().

Signed-off-by: Muchun Song <songmuchun@xxxxxxxxxxxxx>
---
 mm/hugetlb.c | 110 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 109 insertions(+), 1 deletion(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ded7f0fbde35..8295911fe76e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1307,6 +1307,8 @@ static void __free_hugepage(struct hstate *h, struct page *page);
  * reserve at least 2 pages as vmemmap areas.
  */
 #define RESERVE_VMEMMAP_NR	2U
+#define RESERVE_VMEMMAP_SIZE	(RESERVE_VMEMMAP_NR << PAGE_SHIFT)
+#define GFP_VMEMMAP_PAGE	(GFP_KERNEL | __GFP_NOFAIL | __GFP_MEMALLOC)
 
 #define page_huge_pte(page)	((page)->pmd_huge_pte)
 
@@ -1490,7 +1492,7 @@ static void __free_huge_page_pmd_vmemmap(struct hstate *h, pmd_t *pmd,
 					 struct list_head *free_pages)
 {
 	unsigned long next;
-	unsigned long start = addr + RESERVE_VMEMMAP_NR * PAGE_SIZE;
+	unsigned long start = addr + RESERVE_VMEMMAP_SIZE;
 	unsigned long end = addr + vmemmap_pages_size_per_hpage(h);
 	struct page *reuse = NULL;
 
@@ -1578,6 +1580,106 @@ static void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 	free_vmemmap_page_list(&free_pages);
 }
 
+static void __remap_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
+					  unsigned long start,
+					  unsigned int nr_remap,
+					  struct list_head *remap_pages)
+{
+	pgprot_t pgprot = PAGE_KERNEL;
+	void *from = (void *)page_private(reuse);
+	unsigned long addr, end = start + (nr_remap << PAGE_SHIFT);
+
+	for (addr = start; addr < end; addr += PAGE_SIZE) {
+		void *to;
+		struct page *page;
+		pte_t entry, old = *ptep;
+
+		page = list_first_entry_or_null(remap_pages, struct page, lru);
+		list_del(&page->lru);
+		to = page_to_virt(page);
+		copy_page(to, from);
+
+		/*
+		 * Make sure that any data that writes to the @to is made
+		 * visible to the physical page.
+		 */
+		flush_kernel_vmap_range(to, PAGE_SIZE);
+
+		prepare_vmemmap_page(page);
+
+		entry = mk_pte(page, pgprot);
+		set_pte_at(&init_mm, addr, ptep++, entry);
+
+		VM_BUG_ON(!pte_present(old) || pte_page(old) != reuse);
+	}
+}
+
+static void __remap_huge_page_pmd_vmemmap(struct hstate *h, pmd_t *pmd,
+					  unsigned long addr,
+					  struct list_head *remap_pages)
+{
+	unsigned long next;
+	unsigned long start = addr + RESERVE_VMEMMAP_NR * PAGE_SIZE;
+	unsigned long end = addr + vmemmap_pages_size_per_hpage(h);
+	struct page *reuse = NULL;
+
+	addr = start;
+	do {
+		unsigned int nr_pages;
+		pte_t *ptep;
+
+		ptep = pte_offset_kernel(pmd, addr);
+		if (!reuse) {
+			reuse = pte_page(ptep[-1]);
+			set_page_private(reuse, addr - PAGE_SIZE);
+		}
+
+		next = vmemmap_hpage_addr_end(addr, end);
+		nr_pages = (next - addr) >> PAGE_SHIFT;
+		__remap_huge_page_pte_vmemmap(reuse, ptep, addr, nr_pages,
+					      remap_pages);
+	} while (pmd++, addr = next, addr != end);
+
+	flush_tlb_kernel_range(start, end);
+}
+
+static inline void alloc_vmemmap_pages(struct hstate *h, struct list_head *list)
+{
+	int i;
+
+	for (i = 0; i < free_vmemmap_pages_per_hpage(h); i++) {
+		struct page *page;
+
+		/* This should not fail */
+		page = alloc_page(GFP_VMEMMAP_PAGE);
+		list_add_tail(&page->lru, list);
+	}
+}
+
+static void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+	pmd_t *pmd;
+	spinlock_t *ptl;
+	LIST_HEAD(remap_pages);
+
+	if (!free_vmemmap_pages_per_hpage(h))
+		return;
+
+	alloc_vmemmap_pages(h, &remap_pages);
+
+	pmd = vmemmap_to_pmd(head);
+	ptl = vmemmap_pmd_lock(pmd);
+	__remap_huge_page_pmd_vmemmap(h, pmd, (unsigned long)head,
+				      &remap_pages);
+	if (!freed_vmemmap_hpage_dec(pmd_page(*pmd))) {
+		/*
+		 * Todo:
+		 * Merge pte to huge pmd if it has ever been split.
+		 */
+	}
+	spin_unlock(ptl);
+}
+
 /*
  * As update_and_free_page() is be called from a non-task context(and hold
  * hugetlb_lock), we can defer the actual freeing in a workqueue to prevent
@@ -1653,6 +1755,10 @@ static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }
 
+static inline void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+}
+
 static inline void __update_and_free_page(struct hstate *h, struct page *page)
 {
 	__free_hugepage(h, page);
@@ -1685,6 +1791,8 @@ static void __free_hugepage(struct hstate *h, struct page *page)
 {
 	int i;
 
+	alloc_huge_page_vmemmap(h, page);
+
 	for (i = 0; i < pages_per_huge_page(h); i++) {
 		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
 				1 << PG_referenced | 1 << PG_dirty |
-- 
2.11.0