14 files changed, 211 insertions, 63 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index cd2c88e7a8f7..1f8fed94c2a4 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -952,3 +952,9 @@ config ARCH_HAS_BARRIERS
 	help
 	  This option allows the use of custom mandatory barriers
 	  included via the mach/barriers.h file.
+
+config ARCH_SUPPORTS_BIG_ENDIAN
+	bool
+	help
+	  This option specifies the architecture can support big endian
+	  operation.
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 80741992a9fc..3815a8262af0 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -38,9 +38,8 @@ ENTRY(v6_early_abort)
 	bne	do_DataAbort
 	bic	r1, r1, #1 << 11		@ clear bit 11 of FSR
 	ldr	r3, [r4]			@ read aborted ARM instruction
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	rev	r3, r3
-#endif
+ ARM_BE8(rev	r3, r3)
+
 	do_ldrd_abort tmp=ip, insn=r3
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 6f4585b89078..924036473b16 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -25,6 +25,7 @@
 #include <asm/cp15.h>
 #include <asm/system_info.h>
 #include <asm/unaligned.h>
+#include <asm/opcodes.h>
 
 #include "fault.h"
 
@@ -762,21 +763,25 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (thumb_mode(regs)) {
 		u16 *ptr = (u16 *)(instrptr & ~1);
 		fault = probe_kernel_address(ptr, tinstr);
+		tinstr = __mem_to_opcode_thumb16(tinstr);
 		if (!fault) {
 			if (cpu_architecture() >= CPU_ARCH_ARMv7 &&
 			    IS_T32(tinstr)) {
 				/* Thumb-2 32-bit */
 				u16 tinst2 = 0;
 				fault = probe_kernel_address(ptr + 1, tinst2);
-				instr = (tinstr << 16) | tinst2;
+				tinst2 = __mem_to_opcode_thumb16(tinst2);
+				instr = __opcode_thumb32_compose(tinstr, tinst2);
 				thumb2_32b = 1;
 			} else {
 				isize = 2;
 				instr = thumb2arm(tinstr);
 			}
 		}
-	} else
+	} else {
 		fault = probe_kernel_address(instrptr, instr);
+		instr = __mem_to_opcode_arm(instr);
+	}
 
 	if (fault) {
 		type = TYPE_FAULT;
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index f5e1a8471714..79f8b39801a8 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -159,7 +159,7 @@ EXPORT_SYMBOL(arm_coherent_dma_ops);
 
 static u64 get_coherent_dma_mask(struct device *dev)
 {
-	u64 mask = (u64)arm_dma_limit;
+	u64 mask = (u64)DMA_BIT_MASK(32);
 
 	if (dev) {
 		mask = dev->coherent_dma_mask;
@@ -173,10 +173,30 @@ static u64 get_coherent_dma_mask(struct device *dev)
 			return 0;
 		}
 
-		if ((~mask) & (u64)arm_dma_limit) {
-			dev_warn(dev, "coherent DMA mask %#llx is smaller "
-				 "than system GFP_DMA mask %#llx\n",
-				 mask, (u64)arm_dma_limit);
+		/*
+		 * If the mask allows for more memory than we can address,
+		 * and we actually have that much memory, then fail the
+		 * allocation.
+		 */
+		if (sizeof(mask) != sizeof(dma_addr_t) &&
+		    mask > (dma_addr_t)~0 &&
+		    dma_to_pfn(dev, ~0) > arm_dma_pfn_limit) {
+			dev_warn(dev, "Coherent DMA mask %#llx is larger than dma_addr_t allows\n",
+				 mask);
+			dev_warn(dev, "Driver did not use or check the return value from dma_set_coherent_mask()?\n");
+			return 0;
+		}
+
+		/*
+		 * Now check that the mask, when translated to a PFN,
+		 * fits within the allowable addresses which we can
+		 * allocate.
+		 */
+		if (dma_to_pfn(dev, mask) < arm_dma_pfn_limit) {
+			dev_warn(dev, "Coherent DMA mask %#llx (pfn %#lx-%#lx) covers a smaller range of system memory than the DMA zone pfn 0x0-%#lx\n",
+				 mask,
+				 dma_to_pfn(dev, 0), dma_to_pfn(dev, mask) + 1,
+				 arm_dma_pfn_limit + 1);
 			return 0;
 		}
 	}
@@ -687,7 +707,7 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 		    gfp_t gfp, struct dma_attrs *attrs)
 {
-	pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel);
+	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
 	void *memory;
 
 	if (dma_alloc_from_coherent(dev, size, handle, &memory))
@@ -700,7 +720,7 @@ void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
 	dma_addr_t *handle, gfp_t gfp, struct dma_attrs *attrs)
 {
-	pgprot_t prot = __get_dma_pgprot(attrs, pgprot_kernel);
+	pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL);
 	void *memory;
 
 	if (dma_alloc_from_coherent(dev, size, handle, &memory))
@@ -1007,8 +1027,27 @@ void arm_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
  */
 int dma_supported(struct device *dev, u64 mask)
 {
-	if (mask < (u64)arm_dma_limit)
+	unsigned long limit;
+
+	/*
+	 * If the mask allows for more memory than we can address,
+	 * and we actually have that much memory, then we must
+	 * indicate that DMA to this device is not supported.
+	 */
+	if (sizeof(mask) != sizeof(dma_addr_t) &&
+	    mask > (dma_addr_t)~0 &&
+	    dma_to_pfn(dev, ~0) > arm_dma_pfn_limit)
+		return 0;
+
+	/*
+	 * Translate the device's DMA mask to a PFN limit.  This
+	 * PFN number includes the page which we can DMA to.
+	 */
+	limit = dma_to_pfn(dev, mask);
+
+	if (limit < arm_dma_pfn_limit)
 		return 0;
+
 	return 1;
 }
 EXPORT_SYMBOL(dma_supported);
@@ -1232,7 +1271,8 @@ __iommu_create_mapping(struct device *dev, struct page **pages, size_t size)
 				break;
 
 		len = (j - i) << PAGE_SHIFT;
-		ret = iommu_map(mapping->domain, iova, phys, len, 0);
+		ret = iommu_map(mapping->domain, iova, phys, len,
+				IOMMU_READ|IOMMU_WRITE);
 		if (ret < 0)
 			goto fail;
 		iova += len;
@@ -1431,6 +1471,27 @@ static int arm_iommu_get_sgtable(struct device *dev, struct sg_table *sgt,
 					 GFP_KERNEL);
 }
 
+static int __dma_direction_to_prot(enum dma_data_direction dir)
+{
+	int prot;
+
+	switch (dir) {
+	case DMA_BIDIRECTIONAL:
+		prot = IOMMU_READ | IOMMU_WRITE;
+		break;
+	case DMA_TO_DEVICE:
+		prot = IOMMU_READ;
+		break;
+	case DMA_FROM_DEVICE:
+		prot = IOMMU_WRITE;
+		break;
+	default:
+		prot = 0;
+	}
+
+	return prot;
+}
+
 /*
  * Map a part of the scatter-gather list into contiguous io address space
  */
@@ -1444,6 +1505,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 	int ret = 0;
 	unsigned int count;
 	struct scatterlist *s;
+	int prot;
 
 	size = PAGE_ALIGN(size);
 	*handle = DMA_ERROR_CODE;
@@ -1460,7 +1522,9 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 			!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs))
 			__dma_page_cpu_to_dev(sg_page(s), s->offset, s->length, dir);
 
-		ret = iommu_map(mapping->domain, iova, phys, len, 0);
+		prot = __dma_direction_to_prot(dir);
+
+		ret = iommu_map(mapping->domain, iova, phys, len, prot);
 		if (ret < 0)
 			goto fail;
 		count += len >> PAGE_SHIFT;
@@ -1665,19 +1729,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	if (dma_addr == DMA_ERROR_CODE)
 		return dma_addr;
 
-	switch (dir) {
-	case DMA_BIDIRECTIONAL:
-		prot = IOMMU_READ | IOMMU_WRITE;
-		break;
-	case DMA_TO_DEVICE:
-		prot = IOMMU_READ;
-		break;
-	case DMA_FROM_DEVICE:
-		prot = IOMMU_WRITE;
-		break;
-	default:
-		prot = 0;
-	}
+	prot = __dma_direction_to_prot(dir);
 
 	ret = iommu_map(mapping->domain, dma_addr, page_to_phys(page), len, prot);
 	if (ret < 0)
diff --git a/arch/arm/mm/extable.c b/arch/arm/mm/extable.c
index 9d285626bc7d..312e15e6d00b 100644
--- a/arch/arm/mm/extable.c
+++ b/arch/arm/mm/extable.c
@@ -9,8 +9,13 @@ int fixup_exception(struct pt_regs *regs)
 	const struct exception_table_entry *fixup;
 
 	fixup = search_exception_tables(instruction_pointer(regs));
-	if (fixup)
+	if (fixup) {
 		regs->ARM_pc = fixup->fixup;
+#ifdef CONFIG_THUMB2_KERNEL
+		/* Clear the IT state to avoid nasty surprises in the fixup */
+		regs->ARM_cpsr &= ~PSR_IT_MASK;
+#endif
+	}
 
 	return fixup != NULL;
 }
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 2a5907b5c8d2..ff379ac115df 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -65,7 +65,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	return ret;
 }
 
-#if USE_SPLIT_PTLOCKS
+#if USE_SPLIT_PTE_PTLOCKS
 /*
  * If we are using split PTE locks, then we need to take the page
  * lock here.  Otherwise we are using shared mm->page_table_lock
@@ -84,10 +84,10 @@ static inline void do_pte_unlock(spinlock_t *ptl)
 {
 	spin_unlock(ptl);
 }
-#else /* !USE_SPLIT_PTLOCKS */
+#else /* !USE_SPLIT_PTE_PTLOCKS */
 static inline void do_pte_lock(spinlock_t *ptl) {}
 static inline void do_pte_unlock(spinlock_t *ptl) {}
-#endif /* USE_SPLIT_PTLOCKS */
+#endif /* USE_SPLIT_PTE_PTLOCKS */
 
 static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	unsigned long pfn)
diff --git a/arch/arm/mm/idmap.c b/arch/arm/mm/idmap.c
index 83cb3ac27095..8e0e52eb76b5 100644
--- a/arch/arm/mm/idmap.c
+++ b/arch/arm/mm/idmap.c
@@ -10,6 +10,7 @@
 #include <asm/system_info.h>
 
 pgd_t *idmap_pgd;
+phys_addr_t (*arch_virt_to_idmap) (unsigned long x);
 
 #ifdef CONFIG_ARM_LPAE
 static void idmap_add_pmd(pud_t *pud, unsigned long addr, unsigned long end,
@@ -67,8 +68,9 @@ static void identity_mapping_add(pgd_t *pgd, const char *text_start,
 	unsigned long addr, end;
 	unsigned long next;
 
-	addr = virt_to_phys(text_start);
-	end = virt_to_phys(text_end);
+	addr = virt_to_idmap(text_start);
+	end = virt_to_idmap(text_end);
+	pr_info("Setting up static identity map for 0x%lx - 0x%lx\n", addr, end);
 
 	prot |= PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AF;
 
@@ -90,8 +92,6 @@ static int __init init_static_idmap(void)
 	if (!idmap_pgd)
 		return -ENOMEM;
 
-	pr_info("Setting up static identity map for 0x%p - 0x%p\n",
-		__idmap_text_start, __idmap_text_end);
 	identity_mapping_add(idmap_pgd, __idmap_text_start,
 			     __idmap_text_end, 0);
 
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index febaee7ca57b..3e8f106ee5fe 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -17,7 +17,6 @@
 #include <linux/nodemask.h>
 #include <linux/initrd.h>
 #include <linux/of_fdt.h>
-#include <linux/of_reserved_mem.h>
 #include <linux/highmem.h>
 #include <linux/gfp.h>
 #include <linux/memblock.h>
@@ -77,14 +76,6 @@ static int __init parse_tag_initrd2(const struct tag *tag)
 
 __tagtable(ATAG_INITRD2, parse_tag_initrd2);
 
-#ifdef CONFIG_OF_FLATTREE
-void __init early_init_dt_setup_initrd_arch(u64 start, u64 end)
-{
-	phys_initrd_start = start;
-	phys_initrd_size = end - start;
-}
-#endif /* CONFIG_OF_FLATTREE */
-
 /*
  * This keeps memory configuration data used by a couple memory
  * initialization functions, as well as show_mem() for the skipping
@@ -218,6 +209,7 @@ EXPORT_SYMBOL(arm_dma_zone_size);
  * so a successful GFP_DMA allocation will always satisfy this.
  */
 phys_addr_t arm_dma_limit;
+unsigned long arm_dma_pfn_limit;
 
 static void __init arm_adjust_dma_zone(unsigned long *size, unsigned long *hole,
 	unsigned long dma_size)
@@ -240,6 +232,7 @@ void __init setup_dma_zone(const struct machine_desc *mdesc)
 		arm_dma_limit = PHYS_OFFSET + arm_dma_zone_size - 1;
 	} else
 		arm_dma_limit = 0xffffffff;
+	arm_dma_pfn_limit = arm_dma_limit >> PAGE_SHIFT;
 #endif
 }
 
@@ -351,6 +344,11 @@ void __init arm_memblock_init(struct meminfo *mi,
 	memblock_reserve(__pa(_stext), _end - _stext);
 #endif
 #ifdef CONFIG_BLK_DEV_INITRD
+	/* FDT scan will populate initrd_start */
+	if (initrd_start) {
+		phys_initrd_start = __virt_to_phys(initrd_start);
+		phys_initrd_size = initrd_end - initrd_start;
+	}
 	if (phys_initrd_size &&
 	    !memblock_is_region_memory(phys_initrd_start, phys_initrd_size)) {
 		pr_err("INITRD: 0x%08llx+0x%08lx is not a memory region - disabling initrd\n",
@@ -379,8 +377,6 @@ void __init arm_memblock_init(struct meminfo *mi,
 	if (mdesc->reserve)
 		mdesc->reserve();
 
-	early_init_dt_scan_reserved_mem();
-
 	/*
 	 * reserve memory for DMA contigouos allocations,
 	 * must come from DMA area inside low memory
@@ -424,12 +420,10 @@ void __init bootmem_init(void)
 	 * This doesn't seem to be used by the Linux memory manager any
 	 * more, but is used by ll_rw_block.  If we can get rid of it, we
 	 * also get rid of some of the stuff above as well.
-	 *
-	 * Note: max_low_pfn and max_pfn reflect the number of _pages_ in
-	 * the system, not the maximum PFN.
 	 */
-	max_low_pfn = max_low - PHYS_PFN_OFFSET;
-	max_pfn = max_high - PHYS_PFN_OFFSET;
+	min_low_pfn = min;
+	max_low_pfn = max_low;
+	max_pfn = max_high;
 }
 
 /*
@@ -535,7 +529,7 @@ static inline void free_area_high(unsigned long pfn, unsigned long end)
 static void __init free_highpages(void)
 {
 #ifdef CONFIG_HIGHMEM
-	unsigned long max_low = max_low_pfn + PHYS_PFN_OFFSET;
+	unsigned long max_low = max_low_pfn;
 	struct memblock_region *mem, *res;
 
 	/* set highmem page free */
diff --git a/arch/arm/mm/mm.h b/arch/arm/mm/mm.h
index d5a4e9ad8f0f..d5a982d15a88 100644
--- a/arch/arm/mm/mm.h
+++ b/arch/arm/mm/mm.h
@@ -81,8 +81,10 @@ extern __init void add_static_vm_early(struct static_vm *svm);
 
 #ifdef CONFIG_ZONE_DMA
 extern phys_addr_t arm_dma_limit;
+extern unsigned long arm_dma_pfn_limit;
 #else
 #define arm_dma_limit ((phys_addr_t)~0)
+#define arm_dma_pfn_limit (~0ul >> PAGE_SHIFT)
 #endif
 
 extern phys_addr_t arm_lowmem_limit;
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 0c6356255fe3..d27158c38eb0 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -202,13 +202,11 @@ int valid_phys_addr_range(phys_addr_t addr, size_t size)
 }
 
 /*
- * We don't use supersection mappings for mmap() on /dev/mem, which
- * means that we can't map the memory area above the 4G barrier into
- * userspace.
+ * Do not allow /dev/mem mappings beyond the supported physical range.
  */
 int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
 {
-	return !(pfn + (size >> PAGE_SHIFT) > 0x00100000);
+	return (pfn + (size >> PAGE_SHIFT)) <= (1 + (PHYS_MASK >> PAGE_SHIFT));
 }
 
 #ifdef CONFIG_STRICT_DEVMEM
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index b1d17eeb59b8..78eeeca78f5a 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -28,6 +28,8 @@
 #include <asm/highmem.h>
 #include <asm/system_info.h>
 #include <asm/traps.h>
+#include <asm/procinfo.h>
+#include <asm/memory.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -1315,6 +1317,86 @@ static void __init map_lowmem(void)
 	}
 }
 
+#ifdef CONFIG_ARM_LPAE
+/*
+ * early_paging_init() recreates boot time page table setup, allowing machines
+ * to switch over to a high (>4G) address space on LPAE systems
+ */
+void __init early_paging_init(const struct machine_desc *mdesc,
+			      struct proc_info_list *procinfo)
+{
+	pmdval_t pmdprot = procinfo->__cpu_mm_mmu_flags;
+	unsigned long map_start, map_end;
+	pgd_t *pgd0, *pgdk;
+	pud_t *pud0, *pudk, *pud_start;
+	pmd_t *pmd0, *pmdk;
+	phys_addr_t phys;
+	int i;
+
+	if (!(mdesc->init_meminfo))
+		return;
+
+	/* remap kernel code and data */
+	map_start = init_mm.start_code;
+	map_end   = init_mm.brk;
+
+	/* get a handle on things... */
+	pgd0 = pgd_offset_k(0);
+	pud_start = pud0 = pud_offset(pgd0, 0);
+	pmd0 = pmd_offset(pud0, 0);
+
+	pgdk = pgd_offset_k(map_start);
+	pudk = pud_offset(pgdk, map_start);
+	pmdk = pmd_offset(pudk, map_start);
+
+	mdesc->init_meminfo();
+
+	/* Run the patch stub to update the constants */
+	fixup_pv_table(&__pv_table_begin,
+		(&__pv_table_end - &__pv_table_begin) << 2);
+
+	/*
+	 * Cache cleaning operations for self-modifying code
+	 * We should clean the entries by MVA but running a
+	 * for loop over every pv_table entry pointer would
+	 * just complicate the code.
+	 */
+	flush_cache_louis();
+	dsb();
+	isb();
+
+	/* remap level 1 table */
+	for (i = 0; i < PTRS_PER_PGD; pud0++, i++) {
+		set_pud(pud0,
+			__pud(__pa(pmd0) | PMD_TYPE_TABLE | L_PGD_SWAPPER));
+		pmd0 += PTRS_PER_PMD;
+	}
+
+	/* remap pmds for kernel mapping */
+	phys = __pa(map_start) & PMD_MASK;
+	do {
+		*pmdk++ = __pmd(phys | pmdprot);
+		phys += PMD_SIZE;
+	} while (phys < map_end);
+
+	flush_cache_all();
+	cpu_switch_mm(pgd0, &init_mm);
+	cpu_set_ttbr(1, __pa(pgd0) + TTBR1_OFFSET);
+	local_flush_bp_all();
+	local_flush_tlb_all();
+}
+
+#else
+
+void __init early_paging_init(const struct machine_desc *mdesc,
+			      struct proc_info_list *procinfo)
+{
+	if (mdesc->init_meminfo)
+		mdesc->init_meminfo();
+}
+
+#endif
+
 /*
  * paging_init() sets up the page tables, initialises the zone memory
  * maps, and sets up the zero page, bad page and bad page tables.
diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 34d4ab217bab..5c668b7a31f9 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -296,6 +296,15 @@ void __init sanity_check_meminfo(void)
 }
 
 /*
+ * early_paging_init() recreates boot time page table setup, allowing machines
+ * to switch over to a high (>4G) address space on LPAE systems
+ */
+void __init early_paging_init(const struct machine_desc *mdesc,
+			      struct proc_info_list *procinfo)
+{
+}
+
+/*
  * paging_init() sets up the page tables, initialises the zone memory
  * maps, and sets up the zero page, bad page and bad page tables.
  */
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 1128064fddcb..45dc29f85d56 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -220,9 +220,7 @@ __v6_setup:
 #endif /* CONFIG_MMU */
 	adr	r5, v6_crval
 	ldmia	r5, {r5, r6}
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	orr	r6, r6, #1 << 25		@ big-endian page tables
-#endif
+ ARM_BE8(orr	r6, r6, #1 << 25)		@ big-endian page tables
 	mrc	p15, 0, r0, c1, c0, 0		@ read control register
 	bic	r0, r0, r5			@ clear bits them
 	orr	r0, r0, r6			@ set them
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index c63d9bdee51e..60920f62fdf5 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -367,9 +367,7 @@ __v7_setup:
 #endif
 	adr	r5, v7_crval
 	ldmia	r5, {r5, r6}
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	orr	r6, r6, #1 << 25		@ big-endian page tables
-#endif
+ ARM_BE8(orr	r6, r6, #1 << 25)		@ big-endian page tables
 #ifdef CONFIG_SWP_EMULATE
 	orr     r5, r5, #(1 << 10)              @ set SW bit in "clear"
 	bic     r6, r6, #(1 << 10)              @ clear it in "mmuset"