Merge branch 'akpm' (patches from Andrew)

Merge yet more updates from Andrew Morton:

 - More MM work. 100ish more to go. Mike Rapoport's "mm: remove
   __ARCH_HAS_5LEVEL_HACK" series should fix the current ppc issue

 - Various other little subsystems

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (127 commits)
  lib/ubsan.c: fix gcc-10 warnings
  tools/testing/selftests/vm: remove duplicate headers
  selftests: vm: pkeys: fix multilib builds for x86
  selftests: vm: pkeys: use the correct page size on powerpc
  selftests/vm/pkeys: override access right definitions on powerpc
  selftests/vm/pkeys: test correct behaviour of pkey-0
  selftests/vm/pkeys: introduce a sub-page allocator
  selftests/vm/pkeys: detect write violation on a mapped access-denied-key page
  selftests/vm/pkeys: associate key on a mapped page and detect write violation
  selftests/vm/pkeys: associate key on a mapped page and detect access violation
  selftests/vm/pkeys: improve checks to determine pkey support
  selftests/vm/pkeys: fix assertion in test_pkey_alloc_exhaust()
  selftests/vm/pkeys: fix number of reserved powerpc pkeys
  selftests/vm/pkeys: introduce powerpc support
  selftests/vm/pkeys: introduce generic pkey abstractions
  selftests: vm: pkeys: use the correct huge page size
  selftests/vm/pkeys: fix alloc_random_pkey() to make it really random
  selftests/vm/pkeys: fix assertion in pkey_disable_set/clear()
  selftests/vm/pkeys: fix pkey_disable_clear()
  selftests: vm: pkeys: add helpers for pkey bits
  ...

14 files changed, 130 insertions, 76 deletions

diff --git a/arch/arm/include/asm/highmem.h b/arch/arm/include/asm/highmem.h
index eb4e4207cd3c..31811be38d78 100644
--- a/arch/arm/include/asm/highmem.h
+++ b/arch/arm/include/asm/highmem.h
@@ -10,8 +10,6 @@
 #define PKMAP_NR(virt)		(((virt) - PKMAP_BASE) >> PAGE_SHIFT)
 #define PKMAP_ADDR(nr)		(PKMAP_BASE + ((nr) << PAGE_SHIFT))
 
-#define kmap_prot		PAGE_KERNEL
-
 #define flush_cache_kmaps() \
 	do { \
 		if (cache_is_vivt()) \
@@ -20,9 +18,6 @@
 
 extern pte_t *pkmap_page_table;
 
-extern void *kmap_high(struct page *page);
-extern void kunmap_high(struct page *page);
-
 /*
  * The reason for kmap_high_get() is to ensure that the currently kmap'd
  * page usage count does not decrease to zero while we're using its
@@ -63,10 +58,6 @@ static inline void *kmap_high_get(struct page *page)
  * when CONFIG_HIGHMEM is not set.
  */
 #ifdef CONFIG_HIGHMEM
-extern void *kmap(struct page *page);
-extern void kunmap(struct page *page);
-extern void *kmap_atomic(struct page *page);
-extern void __kunmap_atomic(void *kvaddr);
 extern void *kmap_atomic_pfn(unsigned long pfn);
 #endif
 
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index befc8fcec98f..fba20607c53c 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -17,7 +17,6 @@
 
 #else
 
-#define __ARCH_USE_5LEVEL_HACK
 #include <asm-generic/pgtable-nopud.h>
 #include <asm/memory.h>
 #include <asm/pgtable-hwdef.h>
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index c9450982a155..d72b14c96670 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -24,6 +24,7 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp)
 {
 	unsigned long addr = (unsigned long)_addr;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pmd_t *pmd;
 	pte_t *pte;
 	pud_t *pud;
@@ -33,7 +34,11 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp)
 	if (unlikely(pgd_none(*pgd) || pgd_bad(*pgd)))
 		return 0;
 
-	pud = pud_offset(pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	if (unlikely(p4d_none(*p4d) || p4d_bad(*p4d)))
+		return 0;
+
+	pud = pud_offset(p4d, addr);
 	if (unlikely(pud_none(*pud) || pud_bad(*pud)))
 		return 0;
 
diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c
index d96a101e5504..0631a7b02678 100644
--- a/arch/arm/mach-sa1100/assabet.c
+++ b/arch/arm/mach-sa1100/assabet.c
@@ -633,7 +633,7 @@ static void __init map_sa1100_gpio_regs( void )
 	int prot = PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_DOMAIN(DOMAIN_IO);
 	pmd_t *pmd;
 
-	pmd = pmd_offset(pud_offset(pgd_offset_k(virt), virt), virt);
+	pmd = pmd_offset(pud_offset(p4d_offset(pgd_offset_k(virt), virt), virt), virt);
 	*pmd = __pmd(phys | prot);
 	flush_pmd_entry(pmd);
 }
diff --git a/arch/arm/mm/dump.c b/arch/arm/mm/dump.c
index 7d6291f23251..677549d6854c 100644
--- a/arch/arm/mm/dump.c
+++ b/arch/arm/mm/dump.c
@@ -207,6 +207,7 @@ struct pg_level {
 static struct pg_level pg_level[] = {
 	{
 	}, { /* pgd */
+	}, { /* p4d */
 	}, { /* pud */
 	}, { /* pmd */
 		.bits	= section_bits,
@@ -308,7 +309,7 @@ static void walk_pte(struct pg_state *st, pmd_t *pmd, unsigned long start,
 
 	for (i = 0; i < PTRS_PER_PTE; i++, pte++) {
 		addr = start + i * PAGE_SIZE;
-		note_page(st, addr, 4, pte_val(*pte), domain);
+		note_page(st, addr, 5, pte_val(*pte), domain);
 	}
 }
 
@@ -350,14 +351,14 @@ static void walk_pmd(struct pg_state *st, pud_t *pud, unsigned long start)
 			addr += SECTION_SIZE;
 			pmd++;
 			domain = get_domain_name(pmd);
-			note_page(st, addr, 3, pmd_val(*pmd), domain);
+			note_page(st, addr, 4, pmd_val(*pmd), domain);
 		}
 	}
 }
 
-static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
+static void walk_pud(struct pg_state *st, p4d_t *p4d, unsigned long start)
 {
-	pud_t *pud = pud_offset(pgd, 0);
+	pud_t *pud = pud_offset(p4d, 0);
 	unsigned long addr;
 	unsigned i;
 
@@ -366,7 +367,23 @@ static void walk_pud(struct pg_state *st, pgd_t *pgd, unsigned long start)
 		if (!pud_none(*pud)) {
 			walk_pmd(st, pud, addr);
 		} else {
-			note_page(st, addr, 2, pud_val(*pud), NULL);
+			note_page(st, addr, 3, pud_val(*pud), NULL);
+		}
+	}
+}
+
+static void walk_p4d(struct pg_state *st, pgd_t *pgd, unsigned long start)
+{
+	p4d_t *p4d = p4d_offset(pgd, 0);
+	unsigned long addr;
+	unsigned i;
+
+	for (i = 0; i < PTRS_PER_P4D; i++, p4d++) {
+		addr = start + i * P4D_SIZE;
+		if (!p4d_none(*p4d)) {
+			walk_pud(st, p4d, addr);
+		} else {
+			note_page(st, addr, 2, p4d_val(*p4d), NULL);
 		}
 	}
 }
@@ -381,7 +398,7 @@ static void walk_pgd(struct pg_state *st, struct mm_struct *mm,
 	for (i = 0; i < PTRS_PER_PGD; i++, pgd++) {
 		addr = start + i * PGDIR_SIZE;
 		if (!pgd_none(*pgd)) {
-			walk_pud(st, pgd, addr);
+			walk_p4d(st, pgd, addr);
 		} else {
 			note_page(st, addr, 1, pgd_val(*pgd), NULL);
 		}
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index ae857f41f68d..489aaafa6ebd 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -91,6 +91,7 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 {
 	spinlock_t *ptl;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
@@ -100,7 +101,11 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	if (pgd_none_or_clear_bad(pgd))
 		return 0;
 
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (p4d_none_or_clear_bad(p4d))
+		return 0;
+
+	pud = pud_offset(p4d, address);
 	if (pud_none_or_clear_bad(pud))
 		return 0;
 
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 2dd5c41cbb8d..ff230e9affc4 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -43,19 +43,21 @@ void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr)
 	printk("%s[%08lx] *pgd=%08llx", lvl, addr, (long long)pgd_val(*pgd));
 
 	do {
+		p4d_t *p4d;
 		pud_t *pud;
 		pmd_t *pmd;
 		pte_t *pte;
 
-		if (pgd_none(*pgd))
+		p4d = p4d_offset(pgd, addr);
+		if (p4d_none(*p4d))
 			break;
 
-		if (pgd_bad(*pgd)) {
+		if (p4d_bad(*p4d)) {
 			pr_cont("(bad)");
 			break;
 		}
 
-		pud = pud_offset(pgd, addr);
+		pud = pud_offset(p4d, addr);
 		if (PTRS_PER_PUD != 1)
 			pr_cont(", *pud=%08llx", (long long)pud_val(*pud));
 
@@ -405,6 +407,7 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 {
 	unsigned int index;
 	pgd_t *pgd, *pgd_k;
+	p4d_t *p4d, *p4d_k;
 	pud_t *pud, *pud_k;
 	pmd_t *pmd, *pmd_k;
 
@@ -419,13 +422,16 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 	pgd = cpu_get_pgd() + index;
 	pgd_k = init_mm.pgd + index;
 
-	if (pgd_none(*pgd_k))
+	p4d = p4d_offset(pgd, addr);
+	p4d_k = p4d_offset(pgd_k, addr);
+
+	if (p4d_none(*p4d_k))
 		goto bad_area;
-	if (!pgd_present(*pgd))
-		set_pgd(pgd, *pgd_k);
+	if (!p4d_present(*p4d))
+		set_p4d(p4d, *p4d_k);
 
-	pud = pud_offset(pgd, addr);
-	pud_k = pud_offset(pgd_k, addr);
+	pud = pud_offset(p4d, addr);
+	pud_k = pud_offset(p4d_k, addr);
 
 	if (pud_none(*pud_k))
 		goto bad_area;
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index a76f8ace9ce6..e013f6b81328 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -31,36 +31,13 @@ static inline pte_t get_fixmap_pte(unsigned long vaddr)
 	return *ptep;
 }
 
-void *kmap(struct page *page)
-{
-	might_sleep();
-	if (!PageHighMem(page))
-		return page_address(page);
-	return kmap_high(page);
-}
-EXPORT_SYMBOL(kmap);
-
-void kunmap(struct page *page)
-{
-	BUG_ON(in_interrupt());
-	if (!PageHighMem(page))
-		return;
-	kunmap_high(page);
-}
-EXPORT_SYMBOL(kunmap);
-
-void *kmap_atomic(struct page *page)
+void *kmap_atomic_high_prot(struct page *page, pgprot_t prot)
 {
 	unsigned int idx;
 	unsigned long vaddr;
 	void *kmap;
 	int type;
 
-	preempt_disable();
-	pagefault_disable();
-	if (!PageHighMem(page))
-		return page_address(page);
-
 #ifdef CONFIG_DEBUG_HIGHMEM
 	/*
 	 * There is no cache coherency issue when non VIVT, so force the
@@ -90,13 +67,13 @@ void *kmap_atomic(struct page *page)
 	 * in place, so the contained TLB flush ensures the TLB is updated
 	 * with the new mapping.
 	 */
-	set_fixmap_pte(idx, mk_pte(page, kmap_prot));
+	set_fixmap_pte(idx, mk_pte(page, prot));
 
 	return (void *)vaddr;
 }
-EXPORT_SYMBOL(kmap_atomic);
+EXPORT_SYMBOL(kmap_atomic_high_prot);
 
-void __kunmap_atomic(void *kvaddr)
+void kunmap_atomic_high(void *kvaddr)
 {
 	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
 	int idx, type;
@@ -118,10 +95,8 @@ void __kunmap_atomic(void *kvaddr)
 		/* this address was obtained through kmap_high_get() */
 		kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)]));
 	}
-	pagefault_enable();
-	preempt_enable();
 }
-EXPORT_SYMBOL(__kunmap_atomic);
+EXPORT_SYMBOL(kunmap_atomic_high);
 
 void *kmap_atomic_pfn(unsigned long pfn)
 {
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index a033f6134a64..cd54411ef1b8 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -68,7 +68,8 @@ static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 static void idmap_add_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 	unsigned long prot)
 {
-	pud_t *pud = pud_offset(pgd, addr);
+	p4d_t *p4d = p4d_offset(pgd, addr);
+	pud_t *pud = pud_offset(p4d, addr);
 	unsigned long next;
 
 	do {
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 4e43455fab84..01e18e43b174 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -519,7 +519,7 @@ static inline void section_update(unsigned long addr, pmdval_t mask,
 {
 	pmd_t *pmd;
 
-	pmd = pmd_offset(pud_offset(pgd_offset(mm, addr), addr), addr);
+	pmd = pmd_offset(pud_offset(p4d_offset(pgd_offset(mm, addr), addr), addr), addr);
 
 #ifdef CONFIG_ARM_LPAE
 	pmd[0] = __pmd((pmd_val(pmd[0]) & mask) | prot);
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 72286f9a4d30..75529d76d28c 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -142,12 +142,14 @@ static void unmap_area_sections(unsigned long virt, unsigned long size)
 {
 	unsigned long addr = virt, end = virt + (size & ~(SZ_1M - 1));
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmdp;
 
 	flush_cache_vunmap(addr, end);
 	pgd = pgd_offset_k(addr);
-	pud = pud_offset(pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	pmdp = pmd_offset(pud, addr);
 	do {
 		pmd_t pmd = *pmdp;
@@ -190,6 +192,7 @@ remap_area_sections(unsigned long virt, unsigned long pfn,
 {
 	unsigned long addr = virt, end = virt + size;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -200,7 +203,8 @@ remap_area_sections(unsigned long virt, unsigned long pfn,
 	unmap_area_sections(virt, size);
 
 	pgd = pgd_offset_k(addr);
-	pud = pud_offset(pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	pmd = pmd_offset(pud, addr);
 	do {
 		pmd[0] = __pmd(__pfn_to_phys(pfn) | type->prot_sect);
@@ -222,6 +226,7 @@ remap_area_supersections(unsigned long virt, unsigned long pfn,
 {
 	unsigned long addr = virt, end = virt + size;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 
@@ -232,7 +237,8 @@ remap_area_supersections(unsigned long virt, unsigned long pfn,
 	unmap_area_sections(virt, size);
 
 	pgd = pgd_offset_k(virt);
-	pud = pud_offset(pgd, addr);
+	p4d = p4d_offset(pgd, addr);
+	pud = pud_offset(p4d, addr);
 	pmd = pmd_offset(pud, addr);
 	do {
 		unsigned long super_pmd_val, i;
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 88c121ac14b3..4f1f72b75890 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -38,7 +38,7 @@ static inline pte_t get_top_pte(unsigned long va)
 
 static inline pmd_t *pmd_off_k(unsigned long virt)
 {
-	return pmd_offset(pud_offset(pgd_offset_k(virt), virt), virt);
+	return pmd_offset(pud_offset(p4d_offset(pgd_offset_k(virt), virt), virt), virt);
 }
 
 struct mem_type {
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index ec8d0008bfa1..c425288f1a86 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -357,7 +357,8 @@ static pte_t *pte_offset_late_fixmap(pmd_t *dir, unsigned long addr)
 static inline pmd_t * __init fixmap_pmd(unsigned long addr)
 {
 	pgd_t *pgd = pgd_offset_k(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);
 
 	return pmd;
@@ -801,12 +802,12 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 	} while (pmd++, addr = next, addr != end);
 }
 
-static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
+static void __init alloc_init_pud(p4d_t *p4d, unsigned long addr,
 				  unsigned long end, phys_addr_t phys,
 				  const struct mem_type *type,
 				  void *(*alloc)(unsigned long sz), bool ng)
 {
-	pud_t *pud = pud_offset(pgd, addr);
+	pud_t *pud = pud_offset(p4d, addr);
 	unsigned long next;
 
 	do {
@@ -816,6 +817,21 @@ static void __init alloc_init_pud(pgd_t *pgd, unsigned long addr,
 	} while (pud++, addr = next, addr != end);
 }
 
+static void __init alloc_init_p4d(pgd_t *pgd, unsigned long addr,
+				  unsigned long end, phys_addr_t phys,
+				  const struct mem_type *type,
+				  void *(*alloc)(unsigned long sz), bool ng)
+{
+	p4d_t *p4d = p4d_offset(pgd, addr);
+	unsigned long next;
+
+	do {
+		next = p4d_addr_end(addr, end);
+		alloc_init_pud(p4d, addr, next, phys, type, alloc, ng);
+		phys += next - addr;
+	} while (p4d++, addr = next, addr != end);
+}
+
 #ifndef CONFIG_ARM_LPAE
 static void __init create_36bit_mapping(struct mm_struct *mm,
 					struct map_desc *md,
@@ -863,7 +879,8 @@ static void __init create_36bit_mapping(struct mm_struct *mm,
 	pgd = pgd_offset(mm, addr);
 	end = addr + length;
 	do {
-		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);
 		int i;
 
@@ -914,7 +931,7 @@ static void __init __create_mapping(struct mm_struct *mm, struct map_desc *md,
 	do {
 		unsigned long next = pgd_addr_end(addr, end);
 
-		alloc_init_pud(pgd, addr, next, phys, type, alloc, ng);
+		alloc_init_p4d(pgd, addr, next, phys, type, alloc, ng);
 
 		phys += next - addr;
 		addr = next;
@@ -950,7 +967,13 @@ void __init create_mapping_late(struct mm_struct *mm, struct map_desc *md,
 				bool ng)
 {
 #ifdef CONFIG_ARM_LPAE
-	pud_t *pud = pud_alloc(mm, pgd_offset(mm, md->virtual), md->virtual);
+	p4d_t *p4d;
+	pud_t *pud;
+
+	p4d = p4d_alloc(mm, pgd_offset(mm, md->virtual), md->virtual);
+	if (!WARN_ON(!p4d))
+		return;
+	pud = pud_alloc(mm, p4d, md->virtual);
 	if (WARN_ON(!pud))
 		return;
 	pmd_alloc(mm, pud, 0);
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index 478bd2c6aa50..c5e1b27046a8 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -30,6 +30,7 @@
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *new_pgd, *init_pgd;
+	p4d_t *new_p4d, *init_p4d;
 	pud_t *new_pud, *init_pud;
 	pmd_t *new_pmd, *init_pmd;
 	pte_t *new_pte, *init_pte;
@@ -53,8 +54,12 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 	/*
 	 * Allocate PMD table for modules and pkmap mappings.
 	 */
-	new_pud = pud_alloc(mm, new_pgd + pgd_index(MODULES_VADDR),
+	new_p4d = p4d_alloc(mm, new_pgd + pgd_index(MODULES_VADDR),
 			    MODULES_VADDR);
+	if (!new_p4d)
+		goto no_p4d;
+
+	new_pud = pud_alloc(mm, new_p4d, MODULES_VADDR);
 	if (!new_pud)
 		goto no_pud;
 
@@ -69,7 +74,11 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 		 * contains the machine vectors. The vectors are always high
 		 * with LPAE.
 		 */
-		new_pud = pud_alloc(mm, new_pgd, 0);
+		new_p4d = p4d_alloc(mm, new_pgd, 0);
+		if (!new_p4d)
+			goto no_p4d;
+
+		new_pud = pud_alloc(mm, new_p4d, 0);
 		if (!new_pud)
 			goto no_pud;
 
@@ -91,7 +100,8 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 		pmd_val(*new_pmd) |= PMD_DOMAIN(DOMAIN_VECTORS);
 #endif
 
-		init_pud = pud_offset(init_pgd, 0);
+		init_p4d = p4d_offset(init_pgd, 0);
+		init_pud = pud_offset(init_p4d, 0);
 		init_pmd = pmd_offset(init_pud, 0);
 		init_pte = pte_offset_map(init_pmd, 0);
 		set_pte_ext(new_pte + 0, init_pte[0], 0);
@@ -108,6 +118,8 @@ no_pte:
 no_pmd:
 	pud_free(mm, new_pud);
 no_pud:
+	p4d_free(mm, new_p4d);
+no_p4d:
 	__pgd_free(new_pgd);
 no_pgd:
 	return NULL;
@@ -116,6 +128,7 @@ no_pgd:
 void pgd_free(struct mm_struct *mm, pgd_t *pgd_base)
 {
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
 	pgtable_t pte;
@@ -127,7 +140,11 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd_base)
 	if (pgd_none_or_clear_bad(pgd))
 		goto no_pgd;
 
-	pud = pud_offset(pgd, 0);
+	p4d = p4d_offset(pgd, 0);
+	if (p4d_none_or_clear_bad(p4d))
+		goto no_p4d;
+
+	pud = pud_offset(p4d, 0);
 	if (pud_none_or_clear_bad(pud))
 		goto no_pud;
 
@@ -144,8 +161,11 @@ no_pmd:
 	pmd_free(mm, pmd);
 	mm_dec_nr_pmds(mm);
 no_pud:
-	pgd_clear(pgd);
+	p4d_clear(p4d);
 	pud_free(mm, pud);
+no_p4d:
+	pgd_clear(pgd);
+	p4d_free(mm, p4d);
 no_pgd:
 #ifdef CONFIG_ARM_LPAE
 	/*
@@ -156,15 +176,21 @@ no_pgd:
 			continue;
 		if (pgd_val(*pgd) & L_PGD_SWAPPER)
 			continue;
-		pud = pud_offset(pgd, 0);
+		p4d = p4d_offset(pgd, 0);
+		if (p4d_none_or_clear_bad(p4d))
+			continue;
+		pud = pud_offset(p4d, 0);
 		if (pud_none_or_clear_bad(pud))
 			continue;
 		pmd = pmd_offset(pud, 0);
 		pud_clear(pud);
 		pmd_free(mm, pmd);
 		mm_dec_nr_pmds(mm);
-		pgd_clear(pgd);
+		p4d_clear(p4d);
 		pud_free(mm, pud);
+		mm_dec_nr_puds(mm);
+		pgd_clear(pgd);
+		p4d_free(mm, p4d);
 	}
 #endif
 	__pgd_free(pgd_base);