Merge branch 'master' into for-next

Fast-forwarded to current state of Linus' tree as there are patches to be
applied for files that didn't exist on the old branch.

27 files changed, 170 insertions, 75 deletions

diff --git a/arch/arm/mm/cache-v4wb.S b/arch/arm/mm/cache-v4wb.S
index d3644db467b7..f40c69656d8d 100644
--- a/arch/arm/mm/cache-v4wb.S
+++ b/arch/arm/mm/cache-v4wb.S
@@ -32,7 +32,7 @@
 /*
  * This is the size at which it becomes more efficient to
  * clean the whole cache, rather than using the individual
- * cache line maintainence instructions.
+ * cache line maintenance instructions.
  *
  *  Size  Clean (ticks) Dirty (ticks)
  *   4096   21  20  21    53  55  54
diff --git a/arch/arm/mm/cache-v4wt.S b/arch/arm/mm/cache-v4wt.S
index 49c2b66cf3dd..a7b276dbda11 100644
--- a/arch/arm/mm/cache-v4wt.S
+++ b/arch/arm/mm/cache-v4wt.S
@@ -34,7 +34,7 @@
 /*
  * This is the size at which it becomes more efficient to
  * clean the whole cache, rather than using the individual
- * cache line maintainence instructions.
+ * cache line maintenance instructions.
  *
  * *** This needs benchmarking
  */
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 6136e68ce953..dc18d81ef8ce 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -96,7 +96,7 @@ ENDPROC(v7_flush_dcache_all)
  *	Flush the entire cache system.
  *  The data cache flush is now achieved using atomic clean / invalidates
  *  working outwards from L1 cache. This is done using Set/Way based cache
- *  maintainance instructions.
+ *  maintenance instructions.
  *  The instruction cache can still be invalidated back to the point of
  *  unification in a single instruction.
  *
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 4771dba61448..82a093cee09a 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -149,6 +149,7 @@ static int __init consistent_init(void)
 {
 	int ret = 0;
 	pgd_t *pgd;
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 	int i = 0;
@@ -156,7 +157,15 @@ static int __init consistent_init(void)
 
 	do {
 		pgd = pgd_offset(&init_mm, base);
-		pmd = pmd_alloc(&init_mm, pgd, base);
+
+		pud = pud_alloc(&init_mm, pgd, base);
+		if (!pud) {
+			printk(KERN_ERR "%s: no pud tables\n", __func__);
+			ret = -ENOMEM;
+			break;
+		}
+
+		pmd = pmd_alloc(&init_mm, pud, base);
 		if (!pmd) {
 			printk(KERN_ERR "%s: no pmd tables\n", __func__);
 			ret = -ENOMEM;
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 01210dba0221..7cab79179421 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -95,6 +95,7 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 {
 	spinlock_t *ptl;
 	pgd_t *pgd;
+	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 	int ret;
@@ -103,7 +104,11 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	if (pgd_none_or_clear_bad(pgd))
 		return 0;
 
-	pmd = pmd_offset(pgd, address);
+	pud = pud_offset(pgd, address);
+	if (pud_none_or_clear_bad(pud))
+		return 0;
+
+	pmd = pmd_offset(pud, address);
 	if (pmd_none_or_clear_bad(pmd))
 		return 0;
 
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index f10f9bac2206..bc0e1d88fd3b 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -76,9 +76,11 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 
 	printk(KERN_ALERT "pgd = %p\n", mm->pgd);
 	pgd = pgd_offset(mm, addr);
-	printk(KERN_ALERT "[%08lx] *pgd=%08lx", addr, pgd_val(*pgd));
+	printk(KERN_ALERT "[%08lx] *pgd=%08llx",
+			addr, (long long)pgd_val(*pgd));
 
 	do {
+		pud_t *pud;
 		pmd_t *pmd;
 		pte_t *pte;
 
@@ -90,9 +92,21 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 			break;
 		}
 
-		pmd = pmd_offset(pgd, addr);
+		pud = pud_offset(pgd, addr);
+		if (PTRS_PER_PUD != 1)
+			printk(", *pud=%08lx", pud_val(*pud));
+
+		if (pud_none(*pud))
+			break;
+
+		if (pud_bad(*pud)) {
+			printk("(bad)");
+			break;
+		}
+
+		pmd = pmd_offset(pud, addr);
 		if (PTRS_PER_PMD != 1)
-			printk(", *pmd=%08lx", pmd_val(*pmd));
+			printk(", *pmd=%08llx", (long long)pmd_val(*pmd));
 
 		if (pmd_none(*pmd))
 			break;
@@ -107,8 +121,9 @@ void show_pte(struct mm_struct *mm, unsigned long addr)
 			break;
 
 		pte = pte_offset_map(pmd, addr);
-		printk(", *pte=%08lx", pte_val(*pte));
-		printk(", *ppte=%08lx", pte_val(pte[PTE_HWTABLE_PTRS]));
+		printk(", *pte=%08llx", (long long)pte_val(*pte));
+		printk(", *ppte=%08llx",
+		       (long long)pte_val(pte[PTE_HWTABLE_PTRS]));
 		pte_unmap(pte);
 	} while(0);
 
@@ -388,6 +403,7 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 {
 	unsigned int index;
 	pgd_t *pgd, *pgd_k;
+	pud_t *pud, *pud_k;
 	pmd_t *pmd, *pmd_k;
 
 	if (addr < TASK_SIZE)
@@ -406,12 +422,19 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
 
 	if (pgd_none(*pgd_k))
 		goto bad_area;
-
 	if (!pgd_present(*pgd))
 		set_pgd(pgd, *pgd_k);
 
-	pmd_k = pmd_offset(pgd_k, addr);
-	pmd   = pmd_offset(pgd, addr);
+	pud = pud_offset(pgd, addr);
+	pud_k = pud_offset(pgd_k, addr);
+
+	if (pud_none(*pud_k))
+		goto bad_area;
+	if (!pud_present(*pud))
+		set_pud(pud, *pud_k);
+
+	pmd = pmd_offset(pud, addr);
+	pmd_k = pmd_offset(pud_k, addr);
 
 	/*
 	 * On ARM one Linux PGD entry contains two hardware entries (see page
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index 57299446f787..2be9139a4ef3 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -4,10 +4,10 @@
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 
-static void idmap_add_pmd(pgd_t *pgd, unsigned long addr, unsigned long end,
+static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 	unsigned long prot)
 {
-	pmd_t *pmd = pmd_offset(pgd, addr);
+	pmd_t *pmd = pmd_offset(pud, addr);
 
 	addr = (addr & PMD_MASK) | prot;
 	pmd[0] = __pmd(addr);
@@ -16,6 +16,18 @@ static void idmap_add_pmd(pgd_t *pgd, unsigned long addr, unsigned long end,
 	flush_pmd_entry(pmd);
 }
 
+static void idmap_add_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
+	unsigned long prot)
+{
+	pud_t *pud = pud_offset(pgd, addr);
+	unsigned long next;
+
+	do {
+		next = pud_addr_end(addr, end);
+		idmap_add_pmd(pud, addr, next, prot);
+	} while (pud++, addr = next, addr != end);
+}
+
 void identity_mapping_add(pgd_t *pgd, unsigned long addr, unsigned long end)
 {
 	unsigned long prot, next;
@@ -27,17 +39,28 @@ void identity_mapping_add(pgd_t *pgd, unsigned long addr, unsigned long end)
 	pgd += pgd_index(addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		idmap_add_pmd(pgd, addr, next, prot);
+		idmap_add_pud(pgd, addr, next, prot);
 	} while (pgd++, addr = next, addr != end);
 }
 
 #ifdef CONFIG_SMP
-static void idmap_del_pmd(pgd_t *pgd, unsigned long addr, unsigned long end)
+static void idmap_del_pmd(pud_t *pud, unsigned long addr, unsigned long end)
 {
-	pmd_t *pmd = pmd_offset(pgd, addr);
+	pmd_t *pmd = pmd_offset(pud, addr);
 	pmd_clear(pmd);
 }
 
+static void idmap_del_pud(pgd_t *pgd, unsigned long addr, unsigned long end)
+{
+	pud_t *pud = pud_offset(pgd, addr);
+	unsigned long next;
+
+	do {
+		next = pud_addr_end(addr, end);
+		idmap_del_pmd(pud, addr, next);
+	} while (pud++, addr = next, addr != end);
+}
+
 void identity_mapping_del(pgd_t *pgd, unsigned long addr, unsigned long end)
 {
 	unsigned long next;
@@ -45,7 +68,7 @@ void identity_mapping_del(pgd_t *pgd, unsigned long addr, unsigned long end)
 	pgd += pgd_index(addr);
 	do {
 		next = pgd_addr_end(addr, end);
-		idmap_del_pmd(pgd, addr, next);
+		idmap_del_pud(pgd, addr, next);
 	} while (pgd++, addr = next, addr != end);
 }
 #endif
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index cddd684364da..e5f6fc428348 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -78,7 +78,7 @@ __tagtable(ATAG_INITRD2, parse_tag_initrd2);
  */
 struct meminfo meminfo;
 
-void show_mem(void)
+void show_mem(unsigned int filter)
 {
 	int free = 0, total = 0, reserved = 0;
 	int shared = 0, cached = 0, slab = 0, i;
@@ -350,7 +350,7 @@ void __init bootmem_init(void)
 	 */
 	arm_bootmem_free(min, max_low, max_high);
 
-	high_memory = __va((max_low << PAGE_SHIFT) - 1) + 1;
+	high_memory = __va(((phys_addr_t)max_low << PAGE_SHIFT) - 1) + 1;
 
 	/*
 	 * This doesn't seem to be used by the Linux memory manager any
@@ -398,8 +398,8 @@ free_memmap(unsigned long start_pfn, unsigned long end_pfn)
 	 * Convert to physical addresses, and
 	 * round start upwards and end downwards.
 	 */
-	pg = PAGE_ALIGN(__pa(start_pg));
-	pgend = __pa(end_pg) & PAGE_MASK;
+	pg = (unsigned long)PAGE_ALIGN(__pa(start_pg));
+	pgend = (unsigned long)__pa(end_pg) & PAGE_MASK;
 
 	/*
 	 * If there are free pages between these,
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index 36960df5fb76..d2384106af9c 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -7,7 +7,7 @@ extern pmd_t *top_pmd;
 
 static inline pmd_t *pmd_off(pgd_t *pgd, unsigned long virt)
 {
-	return pmd_offset(pgd, virt);
+	return pmd_offset(pud_offset(pgd, virt), virt);
 }
 
 static inline pmd_t *pmd_off_k(unsigned long virt)
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index afe209e1e1f8..74be05f3e03a 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -7,6 +7,7 @@
 #include <linux/shm.h>
 #include <linux/sched.h>
 #include <linux/io.h>
+#include <linux/personality.h>
 #include <linux/random.h>
 #include <asm/cputype.h>
 #include <asm/system.h>
@@ -82,7 +83,8 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	        mm->cached_hole_size = 0;
 	}
 	/* 8 bits of randomness in 20 address space bits */
-	if (current->flags & PF_RANDOMIZE)
+	if ((current->flags & PF_RANDOMIZE) &&
+	    !(current->personality & ADDR_NO_RANDOMIZE))
 		addr += (get_random_int() % (1 << 8)) << PAGE_SHIFT;
 
 full_search:
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index ff7b43b5885a..6cf76b3b68d1 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -533,7 +533,7 @@ static void __init *early_alloc(unsigned long sz)
 static pte_t * __init early_pte_alloc(pmd_t *pmd, unsigned long addr, unsigned long prot)
 {
 	if (pmd_none(*pmd)) {
-		pte_t *pte = early_alloc(2 * PTRS_PER_PTE * sizeof(pte_t));
+		pte_t *pte = early_alloc(PTE_HWTABLE_OFF + PTE_HWTABLE_SIZE);
 		__pmd_populate(pmd, __pa(pte), prot);
 	}
 	BUG_ON(pmd_bad(*pmd));
@@ -551,11 +551,11 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
-static void __init alloc_init_section(pgd_t *pgd, unsigned long addr,
+static void __init alloc_init_section(pud_t *pud, unsigned long addr,
 				      unsigned long end, phys_addr_t phys,
 				      const struct mem_type *type)
 {
-	pmd_t *pmd = pmd_offset(pgd, addr);
+	pmd_t *pmd = pmd_offset(pud, addr);
 
 	/*
 	 * Try a section mapping - end, addr and phys must all be aligned
@@ -584,6 +584,19 @@ static void __init alloc_init_section(pgd_t *pgd, unsigned long addr,
 	}
 }
 
+static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
+	unsigned long phys, const struct mem_type *type)
+{
+	pud_t *pud = pud_offset(pgd, addr);
+	unsigned long next;
+
+	do {
+		next = pud_addr_end(addr, end);
+		alloc_init_section(pud, addr, next, phys, type);
+		phys += next - addr;
+	} while (pud++, addr = next, addr != end);
+}
+
 static void __init create_36bit_mapping(struct map_desc *md,
 					const struct mem_type *type)
 {
@@ -592,13 +605,13 @@ static void __init create_36bit_mapping(struct map_desc *md,
 	pgd_t *pgd;
 
 	addr = md->virtual;
-	phys = (unsigned long)__pfn_to_phys(md->pfn);
+	phys = __pfn_to_phys(md->pfn);
 	length = PAGE_ALIGN(md->length);
 
 	if (!(cpu_architecture() >= CPU_ARCH_ARMv6 || cpu_is_xsc3())) {
 		printk(KERN_ERR "MM: CPU does not support supersection "
 		       "mapping for 0x%08llx at 0x%08lx\n",
-		       __pfn_to_phys((u64)md->pfn), addr);
+		       (long long)__pfn_to_phys((u64)md->pfn), addr);
 		return;
 	}
 
@@ -611,14 +624,14 @@ static void __init create_36bit_mapping(struct map_desc *md,
 	if (type->domain) {
 		printk(KERN_ERR "MM: invalid domain in supersection "
 		       "mapping for 0x%08llx at 0x%08lx\n",
-		       __pfn_to_phys((u64)md->pfn), addr);
+		       (long long)__pfn_to_phys((u64)md->pfn), addr);
 		return;
 	}
 
 	if ((addr | length | __pfn_to_phys(md->pfn)) & ~SUPERSECTION_MASK) {
-		printk(KERN_ERR "MM: cannot create mapping for "
-		       "0x%08llx at 0x%08lx invalid alignment\n",
-		       __pfn_to_phys((u64)md->pfn), addr);
+		printk(KERN_ERR "MM: cannot create mapping for 0x%08llx"
+		       " at 0x%08lx invalid alignment\n",
+		       (long long)__pfn_to_phys((u64)md->pfn), addr);
 		return;
 	}
 
@@ -631,7 +644,8 @@ static void __init create_36bit_mapping(struct map_desc *md,
 	pgd = pgd_offset_k(addr);
 	end = addr + length;
 	do {
-		pmd_t *pmd = pmd_offset(pgd, addr);
+		pud_t *pud = pud_offset(pgd, addr);
+		pmd_t *pmd = pmd_offset(pud, addr);
 		int i;
 
 		for (i = 0; i < 16; i++)
@@ -652,22 +666,23 @@ static void __init create_36bit_mapping(struct map_desc *md,
  */
 static void __init create_mapping(struct map_desc *md)
 {
-	unsigned long phys, addr, length, end;
+	unsigned long addr, length, end;
+	phys_addr_t phys;
 	const struct mem_type *type;
 	pgd_t *pgd;
 
 	if (md->virtual != vectors_base() && md->virtual < TASK_SIZE) {
-		printk(KERN_WARNING "BUG: not creating mapping for "
-		       "0x%08llx at 0x%08lx in user region\n",
-		       __pfn_to_phys((u64)md->pfn), md->virtual);
+		printk(KERN_WARNING "BUG: not creating mapping for 0x%08llx"
+		       " at 0x%08lx in user region\n",
+		       (long long)__pfn_to_phys((u64)md->pfn), md->virtual);
 		return;
 	}
 
 	if ((md->type == MT_DEVICE || md->type == MT_ROM) &&
 	    md->virtual >= PAGE_OFFSET && md->virtual < VMALLOC_END) {
-		printk(KERN_WARNING "BUG: mapping for 0x%08llx at 0x%08lx "
-		       "overlaps vmalloc space\n",
-		       __pfn_to_phys((u64)md->pfn), md->virtual);
+		printk(KERN_WARNING "BUG: mapping for 0x%08llx"
+		       " at 0x%08lx overlaps vmalloc space\n",
+		       (long long)__pfn_to_phys((u64)md->pfn), md->virtual);
 	}
 
 	type = &mem_types[md->type];
@@ -681,13 +696,13 @@ static void __init create_mapping(struct map_desc *md)
 	}
 
 	addr = md->virtual & PAGE_MASK;
-	phys = (unsigned long)__pfn_to_phys(md->pfn);
+	phys = __pfn_to_phys(md->pfn);
 	length = PAGE_ALIGN(md->length + (md->virtual & ~PAGE_MASK));
 
 	if (type->prot_l1 == 0 && ((addr | phys | length) & ~SECTION_MASK)) {
-		printk(KERN_WARNING "BUG: map for 0x%08lx at 0x%08lx can not "
+		printk(KERN_WARNING "BUG: map for 0x%08llx at 0x%08lx can not "
 		       "be mapped using pages, ignoring.\n",
-		       __pfn_to_phys(md->pfn), addr);
+		       (long long)__pfn_to_phys(md->pfn), addr);
 		return;
 	}
 
@@ -696,7 +711,7 @@ static void __init create_mapping(struct map_desc *md)
 	do {
 		unsigned long next = pgd_addr_end(addr, end);
 
-		alloc_init_section(pgd, addr, next, phys, type);
+		alloc_init_pud(pgd, addr, next, phys, type);
 
 		phys += next - addr;
 		addr = next;
@@ -794,9 +809,10 @@ static void __init sanity_check_meminfo(void)
 		 */
 		if (__va(bank->start) >= vmalloc_min ||
 		    __va(bank->start) < (void *)PAGE_OFFSET) {
-			printk(KERN_NOTICE "Ignoring RAM at %.8lx-%.8lx "
+			printk(KERN_NOTICE "Ignoring RAM at %.8llx-%.8llx "
 			       "(vmalloc region overlap).\n",
-			       bank->start, bank->start + bank->size - 1);
+			       (unsigned long long)bank->start,
+			       (unsigned long long)bank->start + bank->size - 1);
 			continue;
 		}
 
@@ -807,10 +823,11 @@ static void __init sanity_check_meminfo(void)
 		if (__va(bank->start + bank->size) > vmalloc_min ||
 		    __va(bank->start + bank->size) < __va(bank->start)) {
 			unsigned long newsize = vmalloc_min - __va(bank->start);
-			printk(KERN_NOTICE "Truncating RAM at %.8lx-%.8lx "
-			       "to -%.8lx (vmalloc region overlap).\n",
-			       bank->start, bank->start + bank->size - 1,
-			       bank->start + newsize - 1);
+			printk(KERN_NOTICE "Truncating RAM at %.8llx-%.8llx "
+			       "to -%.8llx (vmalloc region overlap).\n",
+			       (unsigned long long)bank->start,
+			       (unsigned long long)bank->start + bank->size - 1,
+			       (unsigned long long)bank->start + newsize - 1);
 			bank->size = newsize;
 		}
 #endif
diff --git a/arch/arm/mm/pgd.c b/arch/arm/mm/pgd.c
index 709244c66fa3..b2027c154b2a 100644
--- a/arch/arm/mm/pgd.c
+++ b/arch/arm/mm/pgd.c
@@ -23,6 +23,7 @@
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *new_pgd, *init_pgd;
+	pud_t *new_pud, *init_pud;
 	pmd_t *new_pmd, *init_pmd;
 	pte_t *new_pte, *init_pte;
 
@@ -46,7 +47,11 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 		 * On ARM, first page must always be allocated since it
 		 * contains the machine vectors.
 		 */
-		new_pmd = pmd_alloc(mm, new_pgd, 0);
+		new_pud = pud_alloc(mm, new_pgd, 0);
+		if (!new_pud)
+			goto no_pud;
+
+		new_pmd = pmd_alloc(mm, new_pud, 0);
 		if (!new_pmd)
 			goto no_pmd;
 
@@ -54,7 +59,8 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 		if (!new_pte)
 			goto no_pte;
 
-		init_pmd = pmd_offset(init_pgd, 0);
+		init_pud = pud_offset(init_pgd, 0);
+		init_pmd = pmd_offset(init_pud, 0);
 		init_pte = pte_offset_map(init_pmd, 0);
 		set_pte_ext(new_pte, *init_pte, 0);
 		pte_unmap(init_pte);
@@ -66,6 +72,8 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 no_pte:
 	pmd_free(mm, new_pmd);
 no_pmd:
+	pud_free(mm, new_pud);
+no_pud:
 	free_pages((unsigned long)new_pgd, 2);
 no_pgd:
 	return NULL;
@@ -74,6 +82,7 @@ no_pgd:
 void pgd_free(struct mm_struct *mm, pgd_t *pgd_base)
 {
 	pgd_t *pgd;
+	pud_t *pud;
 	pmd_t *pmd;
 	pgtable_t pte;
 
@@ -84,7 +93,11 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd_base)
 	if (pgd_none_or_clear_bad(pgd))
 		goto no_pgd;
 
-	pmd = pmd_offset(pgd, 0);
+	pud = pud_offset(pgd, 0);
+	if (pud_none_or_clear_bad(pud))
+		goto no_pud;
+
+	pmd = pmd_offset(pud, 0);
 	if (pmd_none_or_clear_bad(pmd))
 		goto no_pmd;
 
@@ -92,8 +105,11 @@ void pgd_free(struct mm_struct *mm, pgd_t *pgd_base)
 	pmd_clear(pmd);
 	pte_free(mm, pte);
 no_pmd:
-	pgd_clear(pgd);
+	pud_clear(pud);
 	pmd_free(mm, pmd);
+no_pud:
+	pgd_clear(pgd);
+	pud_free(mm, pud);
 no_pgd:
 	free_pages((unsigned long) pgd_base, 2);
 }
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index 226e3d8351c2..6c4e7fd6c8af 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -64,7 +64,7 @@
 /*
  * This is the size at which it becomes more efficient to
  * clean the whole cache, rather than using the individual
- * cache line maintainence instructions.
+ * cache line maintenance instructions.
  */
 #define CACHE_DLIMIT	32768
 
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index 86d9c2cf0bce..4ce947c19623 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -64,7 +64,7 @@
 /*
  * This is the size at which it becomes more efficient to
  * clean the whole cache, rather than using the individual
- * cache line maintainence instructions.
+ * cache line maintenance instructions.
  */
 #define CACHE_DLIMIT	32768
 
diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S
index 83d3dd34f846..c8884c5413a2 100644
--- a/arch/arm/mm/proc-arm1022.S
+++ b/arch/arm/mm/proc-arm1022.S
@@ -53,7 +53,7 @@
 /*
  * This is the size at which it becomes more efficient to
  * clean the whole cache, rather than using the individual
- * cache line maintainence instructions.
+ * cache line maintenance instructions.
  */
 #define CACHE_DLIMIT	32768
 
diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S
index 686043ee7281..413684660aad 100644
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -53,7 +53,7 @@
 /*
  * This is the size at which it becomes more efficient to
  * clean the whole cache, rather than using the individual
- * cache line maintainence instructions.
+ * cache line maintenance instructions.
  */
 #define CACHE_DLIMIT	32768
 
diff --git a/arch/arm/mm/proc-arm720.S b/arch/arm/mm/proc-arm720.S
index 665266da143c..7a06e5964f59 100644
--- a/arch/arm/mm/proc-arm720.S
+++ b/arch/arm/mm/proc-arm720.S
@@ -63,7 +63,7 @@ ENTRY(cpu_arm720_proc_fin)
 /*
  * Function: arm720_proc_do_idle(void)
  * Params  : r0 = unused
- * Purpose : put the processer in proper idle mode
+ * Purpose : put the processor in proper idle mode
  */
 ENTRY(cpu_arm720_do_idle)
 		mov	pc, lr
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 219980ec8b6e..bf8a1d1cccb6 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -53,7 +53,7 @@
 /*
  * This is the size at which it becomes more efficient to
  * clean the whole cache, rather than using the individual
- * cache line maintainence instructions.
+ * cache line maintenance instructions.
  */
 #define CACHE_DLIMIT	65536
 
@@ -390,7 +390,7 @@ ENTRY(cpu_arm920_set_pte_ext)
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl	cpu_arm920_suspend_size
 .equ	cpu_arm920_suspend_size, 4 * 3
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_arm920_do_suspend)
 	stmfd	sp!, {r4 - r7, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ PID
diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S
index 36154b1e792a..95ba1fc56e4d 100644
--- a/arch/arm/mm/proc-arm922.S
+++ b/arch/arm/mm/proc-arm922.S
@@ -54,7 +54,7 @@
 /*
  * This is the size at which it becomes more efficient to
  * clean the whole cache, rather than using the individual
- * cache line maintainence instructions.  (I think this should
+ * cache line maintenance instructions.  (I think this should
  * be 32768).
  */
 #define CACHE_DLIMIT	8192
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index 89c5e0009c4c..541e4774eea1 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -77,7 +77,7 @@
 /*
  * This is the size at which it becomes more efficient to
  * clean the whole cache, rather than using the individual
- * cache line maintainence instructions.
+ * cache line maintenance instructions.
  */
 #define CACHE_DLIMIT	8192
 
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index 6a4bdb2c94a7..0ed85d930c09 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -404,7 +404,7 @@ ENTRY(cpu_arm926_set_pte_ext)
 /* Suspend/resume support: taken from arch/arm/plat-s3c24xx/sleep.S */
 .globl	cpu_arm926_suspend_size
 .equ	cpu_arm926_suspend_size, 4 * 3
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_arm926_do_suspend)
 	stmfd	sp!, {r4 - r7, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ PID
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index e32fa499194c..34261f9486b9 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -85,7 +85,7 @@
 
 /*
  * Sanity check the PTE configuration for the code below - which makes
- * certain assumptions about how these bits are layed out.
+ * certain assumptions about how these bits are laid out.
  */
 #ifdef CONFIG_MMU
 #if L_PTE_SHARED != PTE_EXT_SHARED
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 74483d1977fe..184a9c997e36 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -171,7 +171,7 @@ ENTRY(cpu_sa1100_set_pte_ext)
 
 .globl	cpu_sa1100_suspend_size
 .equ	cpu_sa1100_suspend_size, 4*4
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_sa1100_do_suspend)
 	stmfd	sp!, {r4 - r7, lr}
 	mrc	p15, 0, r4, c3, c0, 0		@ domain ID
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 832b6bdc192c..7c99cb4c8e4f 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -124,7 +124,7 @@ ENTRY(cpu_v6_set_pte_ext)
 /* Suspend/resume support: taken from arch/arm/mach-s3c64xx/sleep.S */
 .globl	cpu_v6_suspend_size
 .equ	cpu_v6_suspend_size, 4 * 8
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_v6_do_suspend)
 	stmfd	sp!, {r4 - r11, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
@@ -132,7 +132,7 @@ ENTRY(cpu_v6_do_suspend)
 	mrc	p15, 0, r6, c3, c0, 0	@ Domain ID
 	mrc	p15, 0, r7, c2, c0, 0	@ Translation table base 0
 	mrc	p15, 0, r8, c2, c0, 1	@ Translation table base 1
-	mrc	p15, 0, r9, c1, c0, 1	@ auxillary control register
+	mrc	p15, 0, r9, c1, c0, 1	@ auxiliary control register
 	mrc	p15, 0, r10, c1, c0, 2	@ co-processor access control
 	mrc	p15, 0, r11, c1, c0, 0	@ control register
 	stmia	r0, {r4 - r11}
@@ -151,7 +151,7 @@ ENTRY(cpu_v6_do_resume)
 	mcr	p15, 0, r6, c3, c0, 0	@ Domain ID
 	mcr	p15, 0, r7, c2, c0, 0	@ Translation table base 0
 	mcr	p15, 0, r8, c2, c0, 1	@ Translation table base 1
-	mcr	p15, 0, r9, c1, c0, 1	@ auxillary control register
+	mcr	p15, 0, r9, c1, c0, 1	@ auxiliary control register
 	mcr	p15, 0, r10, c1, c0, 2	@ co-processor access control
 	mcr	p15, 0, ip, c2, c0, 2	@ TTB control register
 	mcr	p15, 0, ip, c7, c5, 4	@ ISB
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 262fa88a7439..babfba09c89f 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -211,7 +211,7 @@ cpu_v7_name:
 /* Suspend/resume support: derived from arch/arm/mach-s5pv210/sleep.S */
 .globl	cpu_v7_suspend_size
 .equ	cpu_v7_suspend_size, 4 * 8
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_v7_do_suspend)
 	stmfd	sp!, {r4 - r11, lr}
 	mrc	p15, 0, r4, c13, c0, 0	@ FCSE/PID
@@ -237,7 +237,7 @@ ENTRY(cpu_v7_do_resume)
 	mcr	p15, 0, r7, c2, c0, 0	@ TTB 0
 	mcr	p15, 0, r8, c2, c0, 1	@ TTB 1
 	mcr	p15, 0, ip, c2, c0, 2	@ TTB control register
-	mcr	p15, 0, r10, c1, c0, 1	@ Auxillary control register
+	mcr	p15, 0, r10, c1, c0, 1	@ Auxiliary control register
 	mcr	p15, 0, r11, c1, c0, 2	@ Co-processor access control
 	ldr	r4, =PRRR		@ PRRR
 	ldr	r5, =NMRR		@ NMRR
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index 63d8b2044e84..596213699f37 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -417,7 +417,7 @@ ENTRY(cpu_xsc3_set_pte_ext)
 
 .globl	cpu_xsc3_suspend_size
 .equ	cpu_xsc3_suspend_size, 4 * 8
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_xsc3_do_suspend)
 	stmfd	sp!, {r4 - r10, lr}
 	mrc	p14, 0, r4, c6, c0, 0	@ clock configuration, for turbo mode
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index 086038cd86ab..ce233bcbf506 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -518,7 +518,7 @@ ENTRY(cpu_xscale_set_pte_ext)
 
 .globl	cpu_xscale_suspend_size
 .equ	cpu_xscale_suspend_size, 4 * 7
-#ifdef CONFIG_PM
+#ifdef CONFIG_PM_SLEEP
 ENTRY(cpu_xscale_do_suspend)
 	stmfd	sp!, {r4 - r10, lr}
 	mrc	p14, 0, r4, c6, c0, 0	@ clock configuration, for turbo mode