[RFC PATCH v2 04/30] mm: add new helper functions to allocate one PMD page with 512 PTE pages.

[Zi Yan <zi.yan@sent.com>]

From: Zi Yan <ziy@nvidia.com>

This prepares for PUD THP support, which allocates 512 of such PMD pages
when creating a PUD THP. These page table pages will be withdrawn during
THP split.

Signed-off-by: Zi Yan <ziy@nvidia.com>
---
 arch/x86/include/asm/pgalloc.h | 60 ++++++++++++++++++++++++++++++++++
 arch/x86/mm/pgtable.c          | 25 ++++++++++++++
 include/linux/huge_mm.h        |  3 ++
 3 files changed, 88 insertions(+)

diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index 62ad61d6fefc..b24284522973 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -52,6 +52,19 @@ extern pgd_t *pgd_alloc(struct mm_struct *);
 extern void pgd_free(struct mm_struct *mm, pgd_t *pgd);
 
 extern pgtable_t pte_alloc_one(struct mm_struct *);
+extern pgtable_t pte_alloc_order(struct mm_struct *mm, unsigned long address,
+		int order);
+
+static inline void pte_free_order(struct mm_struct *mm, struct page *pte,
+		int order)
+{
+	int i;
+
+	for (i = 0; i < (1<<order); i++) {
+		pgtable_pte_page_dtor(&pte[i]);
+		__free_page(&pte[i]);
+	}
+}
 
 extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte);
 
@@ -87,6 +100,53 @@ static inline void pmd_populate(struct mm_struct *mm, pmd_t *pmd,
 #define pmd_pgtable(pmd) pmd_page(pmd)
 
 #if CONFIG_PGTABLE_LEVELS > 2
+static inline pmd_t *pmd_alloc_one_page_with_ptes(struct mm_struct *mm, unsigned long addr)
+{
+	pgtable_t pte_pgtables;
+	pmd_t *pmd;
+	spinlock_t *pmd_ptl;
+	int i;
+
+	pte_pgtables = pte_alloc_order(mm, addr,
+		HPAGE_PUD_ORDER - HPAGE_PMD_ORDER);
+	if (!pte_pgtables)
+		return NULL;
+
+	pmd = pmd_alloc_one(mm, addr);
+	if (unlikely(!pmd)) {
+		pte_free_order(mm, pte_pgtables,
+			HPAGE_PUD_ORDER - HPAGE_PMD_ORDER);
+		return NULL;
+	}
+	pmd_ptl = pmd_lock(mm, pmd);
+
+	for (i = 0; i < (1<<(HPAGE_PUD_ORDER - HPAGE_PMD_ORDER)); i++)
+		pgtable_trans_huge_deposit(mm, pmd, pte_pgtables + i);
+
+	spin_unlock(pmd_ptl);
+
+	return pmd;
+}
+
+static inline void pmd_free_page_with_ptes(struct mm_struct *mm, pmd_t *pmd)
+{
+	spinlock_t *pmd_ptl;
+	int i;
+
+	BUG_ON((unsigned long)pmd & (PAGE_SIZE-1));
+	pmd_ptl = pmd_lock(mm, pmd);
+
+	for (i = 0; i < (1<<(HPAGE_PUD_ORDER - HPAGE_PMD_ORDER)); i++) {
+		pgtable_t pte_pgtable;
+
+		pte_pgtable = pgtable_trans_huge_withdraw(mm, pmd);
+		pte_free(mm, pte_pgtable);
+	}
+
+	spin_unlock(pmd_ptl);
+	pmd_free(mm, pmd);
+}
+
 extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd);
 
 static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index dfd82f51ba66..7be73aee6183 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -33,6 +33,31 @@ pgtable_t pte_alloc_one(struct mm_struct *mm)
 	return __pte_alloc_one(mm, __userpte_alloc_gfp);
 }
 
+pgtable_t pte_alloc_order(struct mm_struct *mm, unsigned long address, int order)
+{
+	struct page *pte;
+	int i;
+
+	pte = alloc_pages(__userpte_alloc_gfp, order);
+	if (!pte)
+		return NULL;
+	split_page(pte, order);
+	for (i = 1; i < (1 << order); i++)
+		set_page_private(pte + i, 0);
+
+	for (i = 0; i < (1<<order); i++) {
+		if (!pgtable_pte_page_ctor(&pte[i])) {
+			__free_page(&pte[i]);
+			while (--i >= 0) {
+				pgtable_pte_page_dtor(&pte[i]);
+				__free_page(&pte[i]);
+			}
+			return NULL;
+		}
+	}
+	return pte;
+}
+
 static int __init setup_userpte(char *arg)
 {
 	if (!arg)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 8a8bc46a2432..e9d228d4fc69 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -115,6 +115,9 @@ extern struct kobj_attribute shmem_enabled_attr;
 #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
 #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
 
+#define HPAGE_PUD_ORDER (HPAGE_PUD_SHIFT-PAGE_SHIFT)
+#define HPAGE_PUD_NR (1<<HPAGE_PUD_ORDER)
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define HPAGE_PMD_SHIFT PMD_SHIFT
 #define HPAGE_PMD_SIZE	((1UL) << HPAGE_PMD_SHIFT)
-- 
2.28.0