Merge branch 'prep-for-5level'

Merge 5-level page table prep from Kirill Shutemov:
 "Here's relatively low-risk part of 5-level paging patchset. Merging it
  now will make x86 5-level paging enabling in v4.12 easier.

  The first patch is actually x86-specific: detect 5-level paging
  support. It boils down to single define.

  The rest of patchset converts Linux MMU abstraction from 4- to 5-level
  paging.

  Enabling of new abstraction in most cases requires adding single line
  of code in arch-specific code. The rest is taken care by asm-generic/.

  Changes to mm/ code are mostly mechanical: add support for new page
  table level -- p4d_t -- where we deal with pud_t now.

  v2:
   - fix build on microblaze (Michal);
   - comment for __ARCH_HAS_5LEVEL_HACK in kasan_populate_zero_shadow();
   - acks from Michal"

* emailed patches from Kirill A Shutemov <kirill.shutemov@linux.intel.com>:
  mm: introduce __p4d_alloc()
  mm: convert generic code to 5-level paging
  asm-generic: introduce <asm-generic/pgtable-nop4d.h>
  arch, mm: convert all architectures to use 5level-fixup.h
  asm-generic: introduce __ARCH_USE_5LEVEL_HACK
  asm-generic: introduce 5level-fixup.h
  x86/cpufeature: Add 5-level paging detection

1 files changed, 196 insertions, 34 deletions

diff --git a/mm/memory.c b/mm/memory.c
index a97a4cec2e1f..235ba51b2fbf 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -445,7 +445,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 	mm_dec_nr_pmds(tlb->mm);
 }
 
-static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
+static inline void free_pud_range(struct mmu_gather *tlb, p4d_t *p4d,
 				unsigned long addr, unsigned long end,
 				unsigned long floor, unsigned long ceiling)
 {
@@ -454,7 +454,7 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 	unsigned long start;
 
 	start = addr;
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
@@ -462,6 +462,39 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 		free_pmd_range(tlb, pud, addr, next, floor, ceiling);
 	} while (pud++, addr = next, addr != end);
 
+	start &= P4D_MASK;
+	if (start < floor)
+		return;
+	if (ceiling) {
+		ceiling &= P4D_MASK;
+		if (!ceiling)
+			return;
+	}
+	if (end - 1 > ceiling - 1)
+		return;
+
+	pud = pud_offset(p4d, start);
+	p4d_clear(p4d);
+	pud_free_tlb(tlb, pud, start);
+}
+
+static inline void free_p4d_range(struct mmu_gather *tlb, pgd_t *pgd,
+				unsigned long addr, unsigned long end,
+				unsigned long floor, unsigned long ceiling)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	unsigned long start;
+
+	start = addr;
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(p4d))
+			continue;
+		free_pud_range(tlb, p4d, addr, next, floor, ceiling);
+	} while (p4d++, addr = next, addr != end);
+
 	start &= PGDIR_MASK;
 	if (start < floor)
 		return;
@@ -473,9 +506,9 @@ static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd,
 	if (end - 1 > ceiling - 1)
 		return;
 
-	pud = pud_offset(pgd, start);
+	p4d = p4d_offset(pgd, start);
 	pgd_clear(pgd);
-	pud_free_tlb(tlb, pud, start);
+	p4d_free_tlb(tlb, p4d, start);
 }
 
 /*
@@ -539,7 +572,7 @@ void free_pgd_range(struct mmu_gather *tlb,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		free_pud_range(tlb, pgd, addr, next, floor, ceiling);
+		free_p4d_range(tlb, pgd, addr, next, floor, ceiling);
 	} while (pgd++, addr = next, addr != end);
 }
 
@@ -658,7 +691,8 @@ static void print_bad_pte(struct vm_area_struct *vma, unsigned long addr,
 			  pte_t pte, struct page *page)
 {
 	pgd_t *pgd = pgd_offset(vma->vm_mm, addr);
-	pud_t *pud = pud_offset(pgd, addr);
+	p4d_t *p4d = p4d_offset(pgd, addr);
+	pud_t *pud = pud_offset(p4d, addr);
 	pmd_t *pmd = pmd_offset(pud, addr);
 	struct address_space *mapping;
 	pgoff_t index;
@@ -1023,16 +1057,16 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
 }
 
 static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
-		pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
+		p4d_t *dst_p4d, p4d_t *src_p4d, struct vm_area_struct *vma,
 		unsigned long addr, unsigned long end)
 {
 	pud_t *src_pud, *dst_pud;
 	unsigned long next;
 
-	dst_pud = pud_alloc(dst_mm, dst_pgd, addr);
+	dst_pud = pud_alloc(dst_mm, dst_p4d, addr);
 	if (!dst_pud)
 		return -ENOMEM;
-	src_pud = pud_offset(src_pgd, addr);
+	src_pud = pud_offset(src_p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) {
@@ -1056,6 +1090,28 @@ static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src
 	return 0;
 }
 
+static inline int copy_p4d_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+		pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma,
+		unsigned long addr, unsigned long end)
+{
+	p4d_t *src_p4d, *dst_p4d;
+	unsigned long next;
+
+	dst_p4d = p4d_alloc(dst_mm, dst_pgd, addr);
+	if (!dst_p4d)
+		return -ENOMEM;
+	src_p4d = p4d_offset(src_pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(src_p4d))
+			continue;
+		if (copy_pud_range(dst_mm, src_mm, dst_p4d, src_p4d,
+						vma, addr, next))
+			return -ENOMEM;
+	} while (dst_p4d++, src_p4d++, addr = next, addr != end);
+	return 0;
+}
+
 int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		struct vm_area_struct *vma)
 {
@@ -1111,7 +1167,7 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(src_pgd))
 			continue;
-		if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd,
+		if (unlikely(copy_p4d_range(dst_mm, src_mm, dst_pgd, src_pgd,
 					    vma, addr, next))) {
 			ret = -ENOMEM;
 			break;
@@ -1267,14 +1323,14 @@ next:
 }
 
 static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
-				struct vm_area_struct *vma, pgd_t *pgd,
+				struct vm_area_struct *vma, p4d_t *p4d,
 				unsigned long addr, unsigned long end,
 				struct zap_details *details)
 {
 	pud_t *pud;
 	unsigned long next;
 
-	pud = pud_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
 		if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
@@ -1295,6 +1351,25 @@ next:
 	return addr;
 }
 
+static inline unsigned long zap_p4d_range(struct mmu_gather *tlb,
+				struct vm_area_struct *vma, pgd_t *pgd,
+				unsigned long addr, unsigned long end,
+				struct zap_details *details)
+{
+	p4d_t *p4d;
+	unsigned long next;
+
+	p4d = p4d_offset(pgd, addr);
+	do {
+		next = p4d_addr_end(addr, end);
+		if (p4d_none_or_clear_bad(p4d))
+			continue;
+		next = zap_pud_range(tlb, vma, p4d, addr, next, details);
+	} while (p4d++, addr = next, addr != end);
+
+	return addr;
+}
+
 void unmap_page_range(struct mmu_gather *tlb,
 			     struct vm_area_struct *vma,
 			     unsigned long addr, unsigned long end,
@@ -1310,7 +1385,7 @@ void unmap_page_range(struct mmu_gather *tlb,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		next = zap_pud_range(tlb, vma, pgd, addr, next, details);
+		next = zap_p4d_range(tlb, vma, pgd, addr, next, details);
 	} while (pgd++, addr = next, addr != end);
 	tlb_end_vma(tlb, vma);
 }
@@ -1465,16 +1540,24 @@ EXPORT_SYMBOL_GPL(zap_vma_ptes);
 pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
 			spinlock_t **ptl)
 {
-	pgd_t *pgd = pgd_offset(mm, addr);
-	pud_t *pud = pud_alloc(mm, pgd, addr);
-	if (pud) {
-		pmd_t *pmd = pmd_alloc(mm, pud, addr);
-		if (pmd) {
-			VM_BUG_ON(pmd_trans_huge(*pmd));
-			return pte_alloc_map_lock(mm, pmd, addr, ptl);
-		}
-	}
-	return NULL;
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset(mm, addr);
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return NULL;
+	pud = pud_alloc(mm, p4d, addr);
+	if (!pud)
+		return NULL;
+	pmd = pmd_alloc(mm, pud, addr);
+	if (!pmd)
+		return NULL;
+
+	VM_BUG_ON(pmd_trans_huge(*pmd));
+	return pte_alloc_map_lock(mm, pmd, addr, ptl);
 }
 
 /*
@@ -1740,7 +1823,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
 	return 0;
 }
 
-static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
+static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d,
 			unsigned long addr, unsigned long end,
 			unsigned long pfn, pgprot_t prot)
 {
@@ -1748,7 +1831,7 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
 	unsigned long next;
 
 	pfn -= addr >> PAGE_SHIFT;
-	pud = pud_alloc(mm, pgd, addr);
+	pud = pud_alloc(mm, p4d, addr);
 	if (!pud)
 		return -ENOMEM;
 	do {
@@ -1760,6 +1843,26 @@ static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd,
 	return 0;
 }
 
+static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
+			unsigned long addr, unsigned long end,
+			unsigned long pfn, pgprot_t prot)
+{
+	p4d_t *p4d;
+	unsigned long next;
+
+	pfn -= addr >> PAGE_SHIFT;
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return -ENOMEM;
+	do {
+		next = p4d_addr_end(addr, end);
+		if (remap_pud_range(mm, p4d, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot))
+			return -ENOMEM;
+	} while (p4d++, addr = next, addr != end);
+	return 0;
+}
+
 /**
  * remap_pfn_range - remap kernel memory to userspace
  * @vma: user vma to map to
@@ -1816,7 +1919,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 	flush_cache_range(vma, addr, end);
 	do {
 		next = pgd_addr_end(addr, end);
-		err = remap_pud_range(mm, pgd, addr, next,
+		err = remap_p4d_range(mm, pgd, addr, next,
 				pfn + (addr >> PAGE_SHIFT), prot);
 		if (err)
 			break;
@@ -1932,7 +2035,7 @@ static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud,
 	return err;
 }
 
-static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
+static int apply_to_pud_range(struct mm_struct *mm, p4d_t *p4d,
 				     unsigned long addr, unsigned long end,
 				     pte_fn_t fn, void *data)
 {
@@ -1940,7 +2043,7 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
 	unsigned long next;
 	int err;
 
-	pud = pud_alloc(mm, pgd, addr);
+	pud = pud_alloc(mm, p4d, addr);
 	if (!pud)
 		return -ENOMEM;
 	do {
@@ -1952,6 +2055,26 @@ static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd,
 	return err;
 }
 
+static int apply_to_p4d_range(struct mm_struct *mm, pgd_t *pgd,
+				     unsigned long addr, unsigned long end,
+				     pte_fn_t fn, void *data)
+{
+	p4d_t *p4d;
+	unsigned long next;
+	int err;
+
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return -ENOMEM;
+	do {
+		next = p4d_addr_end(addr, end);
+		err = apply_to_pud_range(mm, p4d, addr, next, fn, data);
+		if (err)
+			break;
+	} while (p4d++, addr = next, addr != end);
+	return err;
+}
+
 /*
  * Scan a region of virtual memory, filling in page tables as necessary
  * and calling a provided function on each leaf page table.
@@ -1970,7 +2093,7 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 	pgd = pgd_offset(mm, addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		err = apply_to_pud_range(mm, pgd, addr, next, fn, data);
+		err = apply_to_p4d_range(mm, pgd, addr, next, fn, data);
 		if (err)
 			break;
 	} while (pgd++, addr = next, addr != end);
@@ -3653,11 +3776,15 @@ static int __handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 	};
 	struct mm_struct *mm = vma->vm_mm;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	int ret;
 
 	pgd = pgd_offset(mm, address);
+	p4d = p4d_alloc(mm, pgd, address);
+	if (!p4d)
+		return VM_FAULT_OOM;
 
-	vmf.pud = pud_alloc(mm, pgd, address);
+	vmf.pud = pud_alloc(mm, p4d, address);
 	if (!vmf.pud)
 		return VM_FAULT_OOM;
 	if (pud_none(*vmf.pud) && transparent_hugepage_enabled(vma)) {
@@ -3779,12 +3906,35 @@ int handle_mm_fault(struct vm_area_struct *vma, unsigned long address,
 }
 EXPORT_SYMBOL_GPL(handle_mm_fault);
 
+#ifndef __PAGETABLE_P4D_FOLDED
+/*
+ * Allocate p4d page table.
+ * We've already handled the fast-path in-line.
+ */
+int __p4d_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
+{
+	p4d_t *new = p4d_alloc_one(mm, address);
+	if (!new)
+		return -ENOMEM;
+
+	smp_wmb(); /* See comment in __pte_alloc */
+
+	spin_lock(&mm->page_table_lock);
+	if (pgd_present(*pgd))		/* Another has populated it */
+		p4d_free(mm, new);
+	else
+		pgd_populate(mm, pgd, new);
+	spin_unlock(&mm->page_table_lock);
+	return 0;
+}
+#endif /* __PAGETABLE_P4D_FOLDED */
+
 #ifndef __PAGETABLE_PUD_FOLDED
 /*
  * Allocate page upper directory.
  * We've already handled the fast-path in-line.
  */
-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)
 {
 	pud_t *new = pud_alloc_one(mm, address);
 	if (!new)
@@ -3793,10 +3943,17 @@ int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address)
 	smp_wmb(); /* See comment in __pte_alloc */
 
 	spin_lock(&mm->page_table_lock);
-	if (pgd_present(*pgd))		/* Another has populated it */
+#ifndef __ARCH_HAS_5LEVEL_HACK
+	if (p4d_present(*p4d))		/* Another has populated it */
 		pud_free(mm, new);
 	else
-		pgd_populate(mm, pgd, new);
+		p4d_populate(mm, p4d, new);
+#else
+	if (pgd_present(*p4d))		/* Another has populated it */
+		pud_free(mm, new);
+	else
+		pgd_populate(mm, p4d, new);
+#endif /* __ARCH_HAS_5LEVEL_HACK */
 	spin_unlock(&mm->page_table_lock);
 	return 0;
 }
@@ -3839,6 +3996,7 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 		pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *ptep;
@@ -3847,7 +4005,11 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
 	if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd)))
 		goto out;
 
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (p4d_none(*p4d) || unlikely(p4d_bad(*p4d)))
+		goto out;
+
+	pud = pud_offset(p4d, address);
 	if (pud_none(*pud) || unlikely(pud_bad(*pud)))
 		goto out;