hugetlb: introduce pud_huge

Straight forward extensions for huge pages located in the PUD instead of
PMDs.

Signed-off-by: Andi Kleen <ak@suse.de>
Signed-off-by: Nick Piggin <npiggin@suse.de>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

9 files changed, 75 insertions, 5 deletions

diff --git a/arch/ia64/mm/hugetlbpage.c b/arch/ia64/mm/hugetlbpage.c
index 6170f097d25..c45fc7f5a97 100644
--- a/arch/ia64/mm/hugetlbpage.c
+++ b/arch/ia64/mm/hugetlbpage.c
@@ -107,6 +107,12 @@ int pmd_huge(pmd_t pmd)
 {
 	return 0;
 }
+
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address, pmd_t *pmd, int write)
 {
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index c94dc71af98..63db7adce71 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -369,6 +369,11 @@ int pmd_huge(pmd_t pmd)
 	return 0;
 }
 
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd, int write)
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index 9162dc84f77..f28c43d2f61 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -120,6 +120,11 @@ int pmd_huge(pmd_t pmd)
 	return !!(pmd_val(pmd) & _SEGMENT_ENTRY_LARGE);
 }
 
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmdp, int write)
 {
diff --git a/arch/sh/mm/hugetlbpage.c b/arch/sh/mm/hugetlbpage.c
index 2f9dbe0ef4a..9304117039c 100644
--- a/arch/sh/mm/hugetlbpage.c
+++ b/arch/sh/mm/hugetlbpage.c
@@ -79,6 +79,11 @@ int pmd_huge(pmd_t pmd)
 	return 0;
 }
 
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {
diff --git a/arch/sparc64/mm/hugetlbpage.c b/arch/sparc64/mm/hugetlbpage.c
index 1307b23f6a7..f27d10369e0 100644
--- a/arch/sparc64/mm/hugetlbpage.c
+++ b/arch/sparc64/mm/hugetlbpage.c
@@ -295,6 +295,11 @@ int pmd_huge(pmd_t pmd)
 	return 0;
 }
 
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 			     pmd_t *pmd, int write)
 {
diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c
index 52476fde899..a4789e87a31 100644
--- a/arch/x86/mm/hugetlbpage.c
+++ b/arch/x86/mm/hugetlbpage.c
@@ -189,6 +189,11 @@ int pmd_huge(pmd_t pmd)
 	return 0;
 }
 
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd, int write)
@@ -209,6 +214,11 @@ int pmd_huge(pmd_t pmd)
 	return !!(pmd_val(pmd) & _PAGE_PSE);
 }
 
+int pud_huge(pud_t pud)
+{
+	return 0;
+}
+
 struct page *
 follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 		pmd_t *pmd, int write)
@@ -217,9 +227,22 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 
 	page = pte_page(*(pte_t *)pmd);
 	if (page)
-		page += ((address & ~HPAGE_MASK) >> PAGE_SHIFT);
+		page += ((address & ~PMD_MASK) >> PAGE_SHIFT);
 	return page;
 }
+
+struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+		pud_t *pud, int write)
+{
+	struct page *page;
+
+	page = pte_page(*(pte_t *)pud);
+	if (page)
+		page += ((address & ~PUD_MASK) >> PAGE_SHIFT);
+	return page;
+}
+
 #endif
 
 /* x86_64 also uses this file */
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 58c0de32e7f..b2c17f62cac 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -50,7 +50,10 @@ struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
 			      int write);
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 				pmd_t *pmd, int write);
+struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
+				pud_t *pud, int write);
 int pmd_huge(pmd_t pmd);
+int pud_huge(pud_t pmd);
 void hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot);
 
@@ -78,8 +81,10 @@ static inline unsigned long hugetlb_total_pages(void)
 #define hugetlb_report_meminfo(buf)		0
 #define hugetlb_report_node_meminfo(n, buf)	0
 #define follow_huge_pmd(mm, addr, pmd, write)	NULL
+#define follow_huge_pud(mm, addr, pud, write)	NULL
 #define prepare_hugepage_range(file, addr, len)	(-EINVAL)
 #define pmd_huge(x)	0
+#define pud_huge(x)	0
 #define is_hugepage_only_range(mm, addr, len)	0
 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
 #define hugetlb_fault(mm, vma, addr, write)	({ BUG(); 0; })
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0c74c14dd2f..107c1ce223c 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1996,6 +1996,15 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	return ret;
 }
 
+/* Can be overriden by architectures */
+__attribute__((weak)) struct page *
+follow_huge_pud(struct mm_struct *mm, unsigned long address,
+	       pud_t *pud, int write)
+{
+	BUG();
+	return NULL;
+}
+
 int follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			struct page **pages, struct vm_area_struct **vmas,
 			unsigned long *position, int *length, int i,
diff --git a/mm/memory.c b/mm/memory.c
index 02fc6b1047b..262e3eb6601 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -998,19 +998,24 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 		goto no_page_table;
 
 	pud = pud_offset(pgd, address);
-	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
+	if (pud_none(*pud))
+		goto no_page_table;
+	if (pud_huge(*pud)) {
+		BUG_ON(flags & FOLL_GET);
+		page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
+		goto out;
+	}
+	if (unlikely(pud_bad(*pud)))
 		goto no_page_table;
-	
+
 	pmd = pmd_offset(pud, address);
 	if (pmd_none(*pmd))
 		goto no_page_table;
-
 	if (pmd_huge(*pmd)) {
 		BUG_ON(flags & FOLL_GET);
 		page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
 		goto out;
 	}
-
 	if (unlikely(pmd_bad(*pmd)))
 		goto no_page_table;
 
@@ -1567,6 +1572,8 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 	unsigned long next;
 	int err;
 
+	BUG_ON(pud_huge(*pud));
+
 	pmd = pmd_alloc(mm, pud, addr);
 	if (!pmd)
 		return -ENOMEM;