mm: convert generic code to 5-level paging

Convert all non-architecture-specific code to 5-level paging. It's mostly mechanical adding handling one more page table level in places where we deal with pud_t. Signed-off-by: Kirill A. Shutemov <[email protected]> Acked-by: Michal Hocko <[email protected]> Signed-off-by: Linus Torvalds <[email protected]>
mrcsosa · Mar 9, 2017 · c2febaf · c2febaf
1 parent 048456d
commit c2febaf
Show file tree

Hide file tree

Showing 23 changed files with 595 additions and 120 deletions.
diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c
@@ -219,15 +219,20 @@ static int atomic_pte_lookup(struct vm_area_struct *vma, unsigned long vaddr,
 	int write, unsigned long *paddr, int *pageshift)
 {
 	pgd_t *pgdp;
-	pmd_t *pmdp;
+	p4d_t *p4dp;
 	pud_t *pudp;
+	pmd_t *pmdp;
 	pte_t pte;
 
 	pgdp = pgd_offset(vma->vm_mm, vaddr);
 	if (unlikely(pgd_none(*pgdp)))
 		goto err;
 
-	pudp = pud_offset(pgdp, vaddr);
+	p4dp = p4d_offset(pgdp, vaddr);
+	if (unlikely(p4d_none(*p4dp)))
+		goto err;
+
+	pudp = pud_offset(p4dp, vaddr);
 	if (unlikely(pud_none(*pudp)))
 		goto err;
 

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
@@ -267,6 +267,7 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
 {
 	struct mm_struct *mm = ctx->mm;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd, _pmd;
 	pte_t *pte;
@@ -277,7 +278,10 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
 	pgd = pgd_offset(mm, address);
 	if (!pgd_present(*pgd))
 		goto out;
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (!p4d_present(*p4d))
+		goto out;
+	pud = pud_offset(p4d, address);
 	if (!pud_present(*pud))
 		goto out;
 	pmd = pmd_offset(pud, address);

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
@@ -10,9 +10,9 @@
 #include <linux/bug.h>
 #include <linux/errno.h>
 
-#if 4 - defined(__PAGETABLE_PUD_FOLDED) - defined(__PAGETABLE_PMD_FOLDED) != \
-	CONFIG_PGTABLE_LEVELS
-#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{PUD,PMD}_FOLDED
+#if 5 - defined(__PAGETABLE_P4D_FOLDED) - defined(__PAGETABLE_PUD_FOLDED) - \
+	defined(__PAGETABLE_PMD_FOLDED) != CONFIG_PGTABLE_LEVELS
+#error CONFIG_PGTABLE_LEVELS is not consistent with __PAGETABLE_{P4D,PUD,PMD}_FOLDED
 #endif
 
 /*
@@ -424,6 +424,13 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
 })
 
+#ifndef p4d_addr_end
+#define p4d_addr_end(addr, end)						\
+({	unsigned long __boundary = ((addr) + P4D_SIZE) & P4D_MASK;	\
+	(__boundary - 1 < (end) - 1)? __boundary: (end);		\
+})
+#endif
+
 #ifndef pud_addr_end
 #define pud_addr_end(addr, end)						\
 ({	unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK;	\
@@ -444,6 +451,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
  * Do the tests inline, but report and clear the bad entry in mm/memory.c.
  */
 void pgd_clear_bad(pgd_t *);
+void p4d_clear_bad(p4d_t *);
 void pud_clear_bad(pud_t *);
 void pmd_clear_bad(pmd_t *);
 
@@ -458,6 +466,17 @@ static inline int pgd_none_or_clear_bad(pgd_t *pgd)
 	return 0;
 }
 
+static inline int p4d_none_or_clear_bad(p4d_t *p4d)
+{
+	if (p4d_none(*p4d))
+		return 1;
+	if (unlikely(p4d_bad(*p4d))) {
+		p4d_clear_bad(p4d);
+		return 1;
+	}
+	return 0;
+}
+
 static inline int pud_none_or_clear_bad(pud_t *pud)
 {
 	if (pud_none(*pud))
@@ -844,11 +863,30 @@ static inline int pmd_protnone(pmd_t pmd)
 #endif /* CONFIG_MMU */
 
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+
+#ifndef __PAGETABLE_P4D_FOLDED
+int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot);
+int p4d_clear_huge(p4d_t *p4d);
+#else
+static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
+{
+	return 0;
+}
+static inline int p4d_clear_huge(p4d_t *p4d)
+{
+	return 0;
+}
+#endif /* !__PAGETABLE_P4D_FOLDED */
+
 int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
 int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
 int pud_clear_huge(pud_t *pud);
 int pmd_clear_huge(pmd_t *pmd);
 #else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
+static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
+{
+	return 0;
+}
 static inline int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
 {
 	return 0;
@@ -857,6 +895,10 @@ static inline int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
 {
 	return 0;
 }
+static inline int p4d_clear_huge(p4d_t *p4d)
+{
+	return 0;
+}
 static inline int pud_clear_huge(pud_t *pud)
 {
 	return 0;

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
@@ -122,7 +122,7 @@ struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
 				pud_t *pud, int flags);
 int pmd_huge(pmd_t pmd);
-int pud_huge(pud_t pmd);
+int pud_huge(pud_t pud);
 unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot);
 
@@ -197,6 +197,9 @@ static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
 #ifndef pgd_huge
 #define pgd_huge(x)	0
 #endif
+#ifndef p4d_huge
+#define p4d_huge(x)	0
+#endif
 
 #ifndef pgd_write
 static inline int pgd_write(pgd_t pgd)

diff --git a/include/linux/kasan.h b/include/linux/kasan.h
@@ -18,6 +18,7 @@ extern unsigned char kasan_zero_page[PAGE_SIZE];
 extern pte_t kasan_zero_pte[PTRS_PER_PTE];
 extern pmd_t kasan_zero_pmd[PTRS_PER_PMD];
 extern pud_t kasan_zero_pud[PTRS_PER_PUD];
+extern p4d_t kasan_zero_p4d[PTRS_PER_P4D];
 
 void kasan_populate_zero_shadow(const void *shadow_start,
 				const void *shadow_end);

diff --git a/include/linux/mm.h b/include/linux/mm.h
@@ -1560,14 +1560,24 @@ static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
 	return ptep;
 }
 
+#ifdef __PAGETABLE_P4D_FOLDED
+static inline int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd,
+						unsigned long address)
+{
+	return 0;
+}
+#else
+int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
+#endif
+
 #ifdef __PAGETABLE_PUD_FOLDED
-static inline int __pud_alloc(struct mm_struct *mm, pgd_t *pgd,
+static inline int __pud_alloc(struct mm_struct *mm, p4d_t *p4d,
 						unsigned long address)
 {
 	return 0;
 }
 #else
-int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address);
+int __pud_alloc(struct mm_struct *mm, p4d_t *p4d, unsigned long address);
 #endif
 
 #if defined(__PAGETABLE_PMD_FOLDED) || !defined(CONFIG_MMU)
@@ -1621,10 +1631,18 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);
 #if defined(CONFIG_MMU) && !defined(__ARCH_HAS_4LEVEL_HACK)
 
 #ifndef __ARCH_HAS_5LEVEL_HACK
-static inline pud_t *pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+static inline p4d_t *p4d_alloc(struct mm_struct *mm, pgd_t *pgd,
+		unsigned long address)
+{
+	return (unlikely(pgd_none(*pgd)) && __p4d_alloc(mm, pgd, address)) ?
+		NULL : p4d_offset(pgd, address);
+}
+
+static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d,
+		unsigned long address)
 {
-	return (unlikely(pgd_none(*pgd)) && __pud_alloc(mm, pgd, address))?
-		NULL: pud_offset(pgd, address);
+	return (unlikely(p4d_none(*p4d)) && __pud_alloc(mm, p4d, address)) ?
+		NULL : pud_offset(p4d, address);
 }
 #endif /* !__ARCH_HAS_5LEVEL_HACK */
 
@@ -2388,7 +2406,8 @@ void sparse_mem_maps_populate_node(struct page **map_map,
 
 struct page *sparse_mem_map_populate(unsigned long pnum, int nid);
 pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
-pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node);
+p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
+pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
 pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
 pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node);
 void *vmemmap_alloc_block(unsigned long size, int node);

diff --git a/lib/ioremap.c b/lib/ioremap.c
@@ -14,6 +14,7 @@
 #include <asm/pgtable.h>
 
 #ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
+static int __read_mostly ioremap_p4d_capable;
 static int __read_mostly ioremap_pud_capable;
 static int __read_mostly ioremap_pmd_capable;
 static int __read_mostly ioremap_huge_disabled;
@@ -35,6 +36,11 @@ void __init ioremap_huge_init(void)
 	}
 }
 
+static inline int ioremap_p4d_enabled(void)
+{
+	return ioremap_p4d_capable;
+}
+
 static inline int ioremap_pud_enabled(void)
 {
 	return ioremap_pud_capable;
@@ -46,6 +52,7 @@ static inline int ioremap_pmd_enabled(void)
 }
 
 #else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
+static inline int ioremap_p4d_enabled(void) { return 0; }
 static inline int ioremap_pud_enabled(void) { return 0; }
 static inline int ioremap_pmd_enabled(void) { return 0; }
 #endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
@@ -94,14 +101,14 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
 	return 0;
 }
 
-static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr,
+static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
 		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
 {
 	pud_t *pud;
 	unsigned long next;
 
 	phys_addr -= addr;
-	pud = pud_alloc(&init_mm, pgd, addr);
+	pud = pud_alloc(&init_mm, p4d, addr);
 	if (!pud)
 		return -ENOMEM;
 	do {
@@ -120,6 +127,32 @@ static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr,
 	return 0;
 }
 
+static inline int ioremap_p4d_range(pgd_t *pgd, unsigned long addr,
+		unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
+{
+	p4d_t *p4d;
+	unsigned long next;
+
+	phys_addr -= addr;
+	p4d = p4d_alloc(&init_mm, pgd, addr);
+	if (!p4d)
+		return -ENOMEM;
+	do {
+		next = p4d_addr_end(addr, end);
+
+		if (ioremap_p4d_enabled() &&
+		    ((next - addr) == P4D_SIZE) &&
+		    IS_ALIGNED(phys_addr + addr, P4D_SIZE)) {
+			if (p4d_set_huge(p4d, phys_addr + addr, prot))
+				continue;
+		}
+
+		if (ioremap_pud_range(p4d, addr, next, phys_addr + addr, prot))
+			return -ENOMEM;
+	} while (p4d++, addr = next, addr != end);
+	return 0;
+}
+
 int ioremap_page_range(unsigned long addr,
 		       unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
 {
@@ -135,7 +168,7 @@ int ioremap_page_range(unsigned long addr,
 	pgd = pgd_offset_k(addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		err = ioremap_pud_range(pgd, addr, next, phys_addr+addr, prot);
+		err = ioremap_p4d_range(pgd, addr, next, phys_addr+addr, prot);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);