[PATCH v6 10/16] mm/hugetlb: Allocate the vmemmap pages associated with each hugetlb page

[Muchun Song]

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         |   2 +
 mm/hugetlb_vmemmap.c | 102 +++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/hugetlb_vmemmap.h |   5 +++
 3 files changed, 109 insertions(+)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 41056b4230f1..3fafa39fcac6 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1382,6 +1382,8 @@ 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 |
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index f6ba288966d4..d6a1b06c1322 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -95,6 +95,7 @@
 #define pr_fmt(fmt)	"HugeTLB vmemmap: " fmt
 
 #include <linux/bootmem_info.h>
+#include <linux/delay.h>
 #include "hugetlb_vmemmap.h"
 
 /*
@@ -108,6 +109,8 @@
 #define RESERVE_VMEMMAP_NR		2U
 #define RESERVE_VMEMMAP_SIZE		(RESERVE_VMEMMAP_NR << PAGE_SHIFT)
 #define TAIL_PAGE_REUSE			-1
+#define GFP_VMEMMAP_PAGE		\
+	(GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_HIGH)
 
 #ifndef VMEMMAP_HPAGE_SHIFT
 #define VMEMMAP_HPAGE_SHIFT		HPAGE_SHIFT
@@ -159,6 +162,105 @@ static pmd_t *vmemmap_to_pmd(unsigned long page)
 	return pmd_offset(pud, page);
 }
 
+static void __remap_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
+					  unsigned long start,
+					  unsigned long end,
+					  struct list_head *remap_pages)
+{
+	pgprot_t pgprot = PAGE_KERNEL;
+	void *from = page_to_virt(reuse);
+	unsigned long addr;
+
+	for (addr = start; addr < end; addr += PAGE_SIZE) {
+		void *to;
+		struct page *page;
+		pte_t entry, old = *ptep;
+
+		page = list_first_entry(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(pmd_t *pmd, unsigned long start,
+					  unsigned long end,
+					  struct list_head *vmemmap_pages)
+{
+	unsigned long next, addr = start;
+	struct page *reuse = NULL;
+
+	do {
+		pte_t *ptep;
+
+		ptep = pte_offset_kernel(pmd, addr);
+		if (!reuse)
+			reuse = pte_page(ptep[TAIL_PAGE_REUSE]);
+
+		next = vmemmap_hpage_addr_end(addr, end);
+		__remap_huge_page_pte_vmemmap(reuse, ptep, addr, next,
+					      vmemmap_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)
+{
+	unsigned int nr = free_vmemmap_pages_per_hpage(h);
+
+	while (nr--) {
+		struct page *page;
+
+retry:
+		page = alloc_page(GFP_VMEMMAP_PAGE);
+		if (unlikely(!page)) {
+			msleep(100);
+			/*
+			 * We should retry infinitely, because we cannot
+			 * handle allocation failures. Once we allocate
+			 * vmemmap pages successfully, then we can free
+			 * a HugeTLB page.
+			 */
+			goto retry;
+		}
+		list_add_tail(&page->lru, list);
+	}
+}
+
+void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+	pmd_t *pmd;
+	unsigned long start, end;
+	unsigned long vmemmap_addr = (unsigned long)head;
+	LIST_HEAD(map_pages);
+
+	if (!free_vmemmap_pages_per_hpage(h))
+		return;
+
+	alloc_vmemmap_pages(h, &map_pages);
+
+	pmd = vmemmap_to_pmd(vmemmap_addr);
+	BUG_ON(!pmd);
+
+	start = vmemmap_addr + RESERVE_VMEMMAP_SIZE;
+	end = vmemmap_addr + vmemmap_pages_size_per_hpage(h);
+	__remap_huge_page_pmd_vmemmap(pmd, start, end, &map_pages);
+}
+
 static inline void free_vmemmap_page_list(struct list_head *list)
 {
 	struct page *page, *next;
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 293897b9f1d8..7887095488f4 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -12,6 +12,7 @@
 
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
 void __init hugetlb_vmemmap_init(struct hstate *h);
+void alloc_huge_page_vmemmap(struct hstate *h, struct page *head);
 void free_huge_page_vmemmap(struct hstate *h, struct page *head);
 
 static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
@@ -23,6 +24,10 @@ static inline void hugetlb_vmemmap_init(struct hstate *h)
 {
 }
 
+static inline void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+}
+
 static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }
-- 
2.11.0