Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:
 "Included in this update are both some long term fixes and some new
  features.

  Fixes:

   - An integer overflow in the calculation of ELF_ET_DYN_BASE.

   - Avoiding OOMs for high-order IOMMU allocations

   - SMP requires the data cache to be enabled for synchronisation
     primitives to work, so prevent the CPU_DCACHE_DISABLE option being
     visible on SMP builds.

   - A bug going back 10+ years in the noMMU ARM94* CPU support code,
     where it corrupts registers.  Found by folk getting Linux running
     on their cameras.

   - Versatile Express needs an errata workaround enabled for CPU
     hot-unplug to work.

  Features:

   - Clean up module linker by handling out of range relocations
     separately from relocation cases we don't handle.

   - Fix a long term bug in the pci_mmap_page_range() code, which we
     hope won't impact userspace (we hope there's no users of the
     existing broken interface.)

   - Don't map DMA coherent allocations when we don't have a MMU.

   - Drop experimental status for SMP_ON_UP.

   - Warn when DT doesn't specify ePAPR mandatory cache properties.

   - Add documentation concerning how we find the start of physical
     memory for AUTO_ZRELADDR kernels, detailing why we have chosen the
     mask and the implications of changing it.

   - Updates from Ard Biesheuvel to address some issues with large
     kernels (such as allyesconfig) failing to link.

   - Allow hibernation to work on modern (ARMv7) CPUs - this appears to
     have never worked in the past on these CPUs.

   - Enable IRQ_SHOW_LEVEL, which changes the /proc/interrupts output
     format (hopefully without userspace breaking...  let's hope that if
     it causes someone a problem, they tell us.)

   - Fix tegra-ahb DT offsets.

   - Rework ARM errata 643719 code (and ARMv7 flush_cache_louis()/
     flush_dcache_all()) code to be more efficient, and enable this
     errata workaround by default for ARMv7+SMP CPUs.  This complements
     the Versatile Express fix above.

   - Rework ARMv7 context code for errata 430973, so that only Cortex A8
     CPUs are impacted by the branch target buffer flush when this
     errata is enabled.  Also update the help text to indicate that all
     r1p* A8 CPUs are impacted.

   - Switch ARM to the generic show_mem() implementation, it conveys all
     the information which we were already reporting.

   - Prevent slow timer sources being used for udelay() - timers running
     at less than 1MHz are not useful for this, and can cause udelay()
     to return immediately, without any wait.  Using such a slow timer
     is silly.

   - VDSO support for 32-bit ARM, mainly for gettimeofday() using the
     ARM architected timer.

   - Perf support for Scorpion performance monitoring units"

vdso semantic conflict fixed up as per linux-next.

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (52 commits)
  ARM: update errata 430973 documentation to cover Cortex A8 r1p*
  ARM: ensure delay timer has sufficient accuracy for delays
  ARM: switch to use the generic show_mem() implementation
  ARM: proc-v7: avoid errata 430973 workaround for non-Cortex A8 CPUs
  ARM: enable ARM errata 643719 workaround by default
  ARM: cache-v7: optimise test for Cortex A9 r0pX devices
  ARM: cache-v7: optimise branches in v7_flush_cache_louis
  ARM: cache-v7: consolidate initialisation of cache level index
  ARM: cache-v7: shift CLIDR to extract appropriate field before masking
  ARM: cache-v7: use movw/movt instructions
  ARM: allow 16-bit instructions in ALT_UP()
  ARM: proc-arm94*.S: fix setup function
  ARM: vexpress: fix CPU hotplug with CT9x4 tile.
  ARM: 8276/1: Make CPU_DCACHE_DISABLE depend on !SMP
  ARM: 8335/1: Documentation: DT bindings: Tegra AHB: document the legacy base address
  ARM: 8334/1: amba: tegra-ahb: detect and correct bogus base address
  ARM: 8333/1: amba: tegra-ahb: fix register offsets in the macros
  ARM: 8339/1: Enable CONFIG_GENERIC_IRQ_SHOW_LEVEL
  ARM: 8338/1: kexec: Relax SMP validation to improve DT compatibility
  ARM: 8337/1: mm: Do not invoke OOM for higher order IOMMU DMA allocations
  ...

32 files changed, 256 insertions, 213 deletions

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 9b4f29e595a4..b7644310236b 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -738,7 +738,7 @@ config CPU_ICACHE_DISABLE
 
 config CPU_DCACHE_DISABLE
 	bool "Disable D-Cache (C-bit)"
-	depends on CPU_CP15
+	depends on CPU_CP15 && !SMP
 	help
 	  Say Y here to disable the processor data cache. Unless
 	  you have a reason not to or are unsure, say N.
@@ -825,6 +825,20 @@ config KUSER_HELPERS
 	  Say N here only if you are absolutely certain that you do not
 	  need these helpers; otherwise, the safe option is to say Y.
 
+config VDSO
+	bool "Enable VDSO for acceleration of some system calls"
+	depends on AEABI && MMU
+	default y if ARM_ARCH_TIMER
+	select GENERIC_TIME_VSYSCALL
+	help
+	  Place in the process address space an ELF shared object
+	  providing fast implementations of gettimeofday and
+	  clock_gettime.  Systems that implement the ARM architected
+	  timer will receive maximum benefit.
+
+	  You must have glibc 2.22 or later for programs to seamlessly
+	  take advantage of this.
+
 config DMA_CACHE_RWFO
 	bool "Enable read/write for ownership DMA cache maintenance"
 	depends on CPU_V6K && SMP
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 2c0c541c60ca..9769f1eefe3b 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -201,7 +201,7 @@ union offset_union {
  THUMB(	"1:	"ins"	%1, [%2]\n"	)		\
  THUMB(	"	add	%2, %2, #1\n"	)		\
 	"2:\n"						\
-	"	.pushsection .fixup,\"ax\"\n"		\
+	"	.pushsection .text.fixup,\"ax\"\n"	\
 	"	.align	2\n"				\
 	"3:	mov	%0, #1\n"			\
 	"	b	2b\n"				\
@@ -261,7 +261,7 @@ union offset_union {
 		"	mov	%1, %1, "NEXT_BYTE"\n"		\
 		"2:	"ins"	%1, [%2]\n"			\
 		"3:\n"						\
-		"	.pushsection .fixup,\"ax\"\n"		\
+		"	.pushsection .text.fixup,\"ax\"\n"	\
 		"	.align	2\n"				\
 		"4:	mov	%0, #1\n"			\
 		"	b	3b\n"				\
@@ -301,7 +301,7 @@ union offset_union {
 		"	mov	%1, %1, "NEXT_BYTE"\n"		\
 		"4:	"ins"	%1, [%2]\n"			\
 		"5:\n"						\
-		"	.pushsection .fixup,\"ax\"\n"		\
+		"	.pushsection .text.fixup,\"ax\"\n"	\
 		"	.align	2\n"				\
 		"6:	mov	%0, #1\n"			\
 		"	b	5b\n"				\
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 8f15f70622a6..e309c8f35af5 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -1647,6 +1647,7 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 	struct device_node *np;
 	struct resource res;
 	u32 cache_id, old_aux;
+	u32 cache_level = 2;
 
 	np = of_find_matching_node(NULL, l2x0_ids);
 	if (!np)
@@ -1679,6 +1680,12 @@ int __init l2x0_of_init(u32 aux_val, u32 aux_mask)
 	if (!of_property_read_bool(np, "cache-unified"))
 		pr_err("L2C: device tree omits to specify unified cache\n");
 
+	if (of_property_read_u32(np, "cache-level", &cache_level))
+		pr_err("L2C: device tree omits to specify cache-level\n");
+
+	if (cache_level != 2)
+		pr_err("L2C: device tree specifies invalid cache level\n");
+
 	/* Read back current (default) hardware configuration */
 	if (data->save)
 		data->save(l2x0_base);
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index b966656d2c2d..a134d8a13d00 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -36,10 +36,10 @@ ENTRY(v7_invalidate_l1)
        mcr     p15, 2, r0, c0, c0, 0
        mrc     p15, 1, r0, c0, c0, 0
 
-       ldr     r1, =0x7fff
+       movw    r1, #0x7fff
        and     r2, r1, r0, lsr #13
 
-       ldr     r1, =0x3ff
+       movw    r1, #0x3ff
 
        and     r3, r1, r0, lsr #3      @ NumWays - 1
        add     r2, r2, #1              @ NumSets
@@ -90,21 +90,20 @@ ENDPROC(v7_flush_icache_all)
 ENTRY(v7_flush_dcache_louis)
 	dmb					@ ensure ordering with previous memory accesses
 	mrc	p15, 1, r0, c0, c0, 1		@ read clidr, r0 = clidr
-	ALT_SMP(ands	r3, r0, #(7 << 21))	@ extract LoUIS from clidr
-	ALT_UP(ands	r3, r0, #(7 << 27))	@ extract LoUU from clidr
+ALT_SMP(mov	r3, r0, lsr #20)		@ move LoUIS into position
+ALT_UP(	mov	r3, r0, lsr #26)		@ move LoUU into position
+	ands	r3, r3, #7 << 1 		@ extract LoU*2 field from clidr
+	bne	start_flush_levels		@ LoU != 0, start flushing
 #ifdef CONFIG_ARM_ERRATA_643719
-	ALT_SMP(mrceq	p15, 0, r2, c0, c0, 0)	@ read main ID register
-	ALT_UP(reteq	lr)			@ LoUU is zero, so nothing to do
-	ldreq	r1, =0x410fc090                 @ ID of ARM Cortex A9 r0p?
-	biceq	r2, r2, #0x0000000f             @ clear minor revision number
-	teqeq	r2, r1                          @ test for errata affected core and if so...
-	orreqs	r3, #(1 << 21)			@   fix LoUIS value (and set flags state to 'ne')
+ALT_SMP(mrc	p15, 0, r2, c0, c0, 0)		@ read main ID register
+ALT_UP(	ret	lr)				@ LoUU is zero, so nothing to do
+	movw	r1, #:lower16:(0x410fc090 >> 4)	@ ID of ARM Cortex A9 r0p?
+	movt	r1, #:upper16:(0x410fc090 >> 4)
+	teq	r1, r2, lsr #4			@ test for errata affected core and if so...
+	moveq	r3, #1 << 1			@   fix LoUIS value
+	beq	start_flush_levels		@   start flushing cache levels
 #endif
-	ALT_SMP(mov	r3, r3, lsr #20)	@ r3 = LoUIS * 2
-	ALT_UP(mov	r3, r3, lsr #26)	@ r3 = LoUU * 2
-	reteq	lr				@ return if level == 0
-	mov	r10, #0				@ r10 (starting level) = 0
-	b	flush_levels			@ start flushing cache levels
+	ret	lr
 ENDPROC(v7_flush_dcache_louis)
 
 /*
@@ -119,9 +118,10 @@ ENDPROC(v7_flush_dcache_louis)
 ENTRY(v7_flush_dcache_all)
 	dmb					@ ensure ordering with previous memory accesses
 	mrc	p15, 1, r0, c0, c0, 1		@ read clidr
-	ands	r3, r0, #0x7000000		@ extract loc from clidr
-	mov	r3, r3, lsr #23			@ left align loc bit field
+	mov	r3, r0, lsr #23			@ move LoC into position
+	ands	r3, r3, #7 << 1			@ extract LoC*2 from clidr
 	beq	finished			@ if loc is 0, then no need to clean
+start_flush_levels:
 	mov	r10, #0				@ start clean at cache level 0
 flush_levels:
 	add	r2, r10, r10, lsr #1		@ work out 3x current cache level
@@ -140,10 +140,10 @@ flush_levels:
 #endif
 	and	r2, r1, #7			@ extract the length of the cache lines
 	add	r2, r2, #4			@ add 4 (line length offset)
-	ldr	r4, =0x3ff
+	movw	r4, #0x3ff
 	ands	r4, r4, r1, lsr #3		@ find maximum number on the way size
 	clz	r5, r4				@ find bit position of way size increment
-	ldr	r7, =0x7fff
+	movw	r7, #0x7fff
 	ands	r7, r7, r1, lsr #13		@ extract max number of the index size
 loop1:
 	mov	r9, r7				@ create working copy of max index
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index e315dfe3af1b..09c5fe3d30c2 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -289,11 +289,11 @@ static void __dma_free_buffer(struct page *page, size_t size)
 
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
 				     pgprot_t prot, struct page **ret_page,
-				     const void *caller);
+				     const void *caller, bool want_vaddr);
 
 static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 				 pgprot_t prot, struct page **ret_page,
-				 const void *caller);
+				 const void *caller, bool want_vaddr);
 
 static void *
 __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot,
@@ -357,10 +357,10 @@ static int __init atomic_pool_init(void)
 
 	if (dev_get_cma_area(NULL))
 		ptr = __alloc_from_contiguous(NULL, atomic_pool_size, prot,
-					      &page, atomic_pool_init);
+					      &page, atomic_pool_init, true);
 	else
 		ptr = __alloc_remap_buffer(NULL, atomic_pool_size, gfp, prot,
-					   &page, atomic_pool_init);
+					   &page, atomic_pool_init, true);
 	if (ptr) {
 		int ret;
 
@@ -467,13 +467,15 @@ static void __dma_remap(struct page *page, size_t size, pgprot_t prot)
 
 static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 				 pgprot_t prot, struct page **ret_page,
-				 const void *caller)
+				 const void *caller, bool want_vaddr)
 {
 	struct page *page;
-	void *ptr;
+	void *ptr = NULL;
 	page = __dma_alloc_buffer(dev, size, gfp);
 	if (!page)
 		return NULL;
+	if (!want_vaddr)
+		goto out;
 
 	ptr = __dma_alloc_remap(page, size, gfp, prot, caller);
 	if (!ptr) {
@@ -481,6 +483,7 @@ static void *__alloc_remap_buffer(struct device *dev, size_t size, gfp_t gfp,
 		return NULL;
 	}
 
+ out:
 	*ret_page = page;
 	return ptr;
 }
@@ -523,12 +526,12 @@ static int __free_from_pool(void *start, size_t size)
 
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
 				     pgprot_t prot, struct page **ret_page,
-				     const void *caller)
+				     const void *caller, bool want_vaddr)
 {
 	unsigned long order = get_order(size);
 	size_t count = size >> PAGE_SHIFT;
 	struct page *page;
-	void *ptr;
+	void *ptr = NULL;
 
 	page = dma_alloc_from_contiguous(dev, count, order);
 	if (!page)
@@ -536,6 +539,9 @@ static void *__alloc_from_contiguous(struct device *dev, size_t size,
 
 	__dma_clear_buffer(page, size);
 
+	if (!want_vaddr)
+		goto out;
+
 	if (PageHighMem(page)) {
 		ptr = __dma_alloc_remap(page, size, GFP_KERNEL, prot, caller);
 		if (!ptr) {
@@ -546,17 +552,21 @@ static void *__alloc_from_contiguous(struct device *dev, size_t size,
 		__dma_remap(page, size, prot);
 		ptr = page_address(page);
 	}
+
+ out:
 	*ret_page = page;
 	return ptr;
 }
 
 static void __free_from_contiguous(struct device *dev, struct page *page,
-				   void *cpu_addr, size_t size)
+				   void *cpu_addr, size_t size, bool want_vaddr)
 {
-	if (PageHighMem(page))
-		__dma_free_remap(cpu_addr, size);
-	else
-		__dma_remap(page, size, PAGE_KERNEL);
+	if (want_vaddr) {
+		if (PageHighMem(page))
+			__dma_free_remap(cpu_addr, size);
+		else
+			__dma_remap(page, size, PAGE_KERNEL);
+	}
 	dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT);
 }
 
@@ -574,12 +584,12 @@ static inline pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot)
 
 #define nommu() 1
 
-#define __get_dma_pgprot(attrs, prot)	__pgprot(0)
-#define __alloc_remap_buffer(dev, size, gfp, prot, ret, c)	NULL
+#define __get_dma_pgprot(attrs, prot)				__pgprot(0)
+#define __alloc_remap_buffer(dev, size, gfp, prot, ret, c, wv)	NULL
 #define __alloc_from_pool(size, ret_page)			NULL
-#define __alloc_from_contiguous(dev, size, prot, ret, c)	NULL
+#define __alloc_from_contiguous(dev, size, prot, ret, c, wv)	NULL
 #define __free_from_pool(cpu_addr, size)			0
-#define __free_from_contiguous(dev, page, cpu_addr, size)	do { } while (0)
+#define __free_from_contiguous(dev, page, cpu_addr, size, wv)	do { } while (0)
 #define __dma_free_remap(cpu_addr, size)			do { } while (0)
 
 #endif	/* CONFIG_MMU */
@@ -599,11 +609,13 @@ static void *__alloc_simple_buffer(struct device *dev, size_t size, gfp_t gfp,
 
 
 static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
-			 gfp_t gfp, pgprot_t prot, bool is_coherent, const void *caller)
+			 gfp_t gfp, pgprot_t prot, bool is_coherent,
+			 struct dma_attrs *attrs, const void *caller)
 {
 	u64 mask = get_coherent_dma_mask(dev);
 	struct page *page = NULL;
 	void *addr;
+	bool want_vaddr;
 
 #ifdef CONFIG_DMA_API_DEBUG
 	u64 limit = (mask + 1) & ~mask;
@@ -631,20 +643,21 @@ static void *__dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 
 	*handle = DMA_ERROR_CODE;
 	size = PAGE_ALIGN(size);
+	want_vaddr = !dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs);
 
 	if (is_coherent || nommu())
 		addr = __alloc_simple_buffer(dev, size, gfp, &page);
 	else if (!(gfp & __GFP_WAIT))
 		addr = __alloc_from_pool(size, &page);
 	else if (!dev_get_cma_area(dev))
-		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller);
+		addr = __alloc_remap_buffer(dev, size, gfp, prot, &page, caller, want_vaddr);
 	else
-		addr = __alloc_from_contiguous(dev, size, prot, &page, caller);
+		addr = __alloc_from_contiguous(dev, size, prot, &page, caller, want_vaddr);
 
-	if (addr)
+	if (page)
 		*handle = pfn_to_dma(dev, page_to_pfn(page));
 
-	return addr;
+	return want_vaddr ? addr : page;
 }
 
 /*
@@ -661,7 +674,7 @@ void *arm_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 		return memory;
 
 	return __dma_alloc(dev, size, handle, gfp, prot, false,
-			   __builtin_return_address(0));
+			   attrs, __builtin_return_address(0));
 }
 
 static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
@@ -674,7 +687,7 @@ static void *arm_coherent_dma_alloc(struct device *dev, size_t size,
 		return memory;
 
 	return __dma_alloc(dev, size, handle, gfp, prot, true,
-			   __builtin_return_address(0));
+			   attrs, __builtin_return_address(0));
 }
 
 /*
@@ -715,6 +728,7 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 			   bool is_coherent)
 {
 	struct page *page = pfn_to_page(dma_to_pfn(dev, handle));
+	bool want_vaddr = !dma_get_attr(DMA_ATTR_NO_KERNEL_MAPPING, attrs);
 
 	if (dma_release_from_coherent(dev, get_order(size), cpu_addr))
 		return;
@@ -726,14 +740,15 @@ static void __arm_dma_free(struct device *dev, size_t size, void *cpu_addr,
 	} else if (__free_from_pool(cpu_addr, size)) {
 		return;
 	} else if (!dev_get_cma_area(dev)) {
-		__dma_free_remap(cpu_addr, size);
+		if (want_vaddr)
+			__dma_free_remap(cpu_addr, size);
 		__dma_free_buffer(page, size);
 	} else {
 		/*
 		 * Non-atomic allocations cannot be freed with IRQs disabled
 		 */
 		WARN_ON(irqs_disabled());
-		__free_from_contiguous(dev, page, cpu_addr, size);
+		__free_from_contiguous(dev, page, cpu_addr, size, want_vaddr);
 	}
 }
 
@@ -1135,13 +1150,28 @@ static struct page **__iommu_alloc_buffer(struct device *dev, size_t size,
 	gfp |= __GFP_NOWARN | __GFP_HIGHMEM;
 
 	while (count) {
-		int j, order = __fls(count);
+		int j, order;
+
+		for (order = __fls(count); order > 0; --order) {
+			/*
+			 * We do not want OOM killer to be invoked as long
+			 * as we can fall back to single pages, so we force
+			 * __GFP_NORETRY for orders higher than zero.
+			 */
+			pages[i] = alloc_pages(gfp | __GFP_NORETRY, order);
+			if (pages[i])
+				break;
+		}
 
-		pages[i] = alloc_pages(gfp, order);
-		while (!pages[i] && order)
-			pages[i] = alloc_pages(gfp, --order);
-		if (!pages[i])
-			goto error;
+		if (!pages[i]) {
+			/*
+			 * Fall back to single page allocation.
+			 * Might invoke OOM killer as last resort.
+			 */
+			pages[i] = alloc_pages(gfp, 0);
+			if (!pages[i])
+				goto error;
+		}
 
 		if (order) {
 			split_page(pages[i], order);
@@ -1206,7 +1236,7 @@ __iommu_alloc_remap(struct page **pages, size_t size, gfp_t gfp, pgprot_t prot,
 static dma_addr_t
 __iommu_create_mapping(struct device *dev, struct page **pages, size_t size)
 {
-	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	dma_addr_t dma_addr, iova;
 	int i, ret = DMA_ERROR_CODE;
@@ -1242,7 +1272,7 @@ fail:
 
 static int __iommu_remove_mapping(struct device *dev, dma_addr_t iova, size_t size)
 {
-	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 
 	/*
 	 * add optional in-page offset from iova to size and align
@@ -1457,7 +1487,7 @@ static int __map_sg_chunk(struct device *dev, struct scatterlist *sg,
 			  enum dma_data_direction dir, struct dma_attrs *attrs,
 			  bool is_coherent)
 {
-	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova, iova_base;
 	int ret = 0;
 	unsigned int count;
@@ -1678,7 +1708,7 @@ static dma_addr_t arm_coherent_iommu_map_page(struct device *dev, struct page *p
 	     unsigned long offset, size_t size, enum dma_data_direction dir,
 	     struct dma_attrs *attrs)
 {
-	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t dma_addr;
 	int ret, prot, len = PAGE_ALIGN(size + offset);
 
@@ -1731,7 +1761,7 @@ static void arm_coherent_iommu_unmap_page(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir,
 		struct dma_attrs *attrs)
 {
-	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
 	int offset = handle & ~PAGE_MASK;
 	int len = PAGE_ALIGN(size + offset);
@@ -1756,7 +1786,7 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle,
 		size_t size, enum dma_data_direction dir,
 		struct dma_attrs *attrs)
 {
-	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
 	struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
 	int offset = handle & ~PAGE_MASK;
@@ -1775,7 +1805,7 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle,
 static void arm_iommu_sync_single_for_cpu(struct device *dev,
 		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
-	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
 	struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
 	unsigned int offset = handle & ~PAGE_MASK;
@@ -1789,7 +1819,7 @@ static void arm_iommu_sync_single_for_cpu(struct device *dev,
 static void arm_iommu_sync_single_for_device(struct device *dev,
 		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
-	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	dma_addr_t iova = handle & PAGE_MASK;
 	struct page *page = phys_to_page(iommu_iova_to_phys(mapping->domain, iova));
 	unsigned int offset = handle & ~PAGE_MASK;
@@ -1950,7 +1980,7 @@ static int __arm_iommu_attach_device(struct device *dev,
 		return err;
 
 	kref_get(&mapping->kref);
-	dev->archdata.mapping = mapping;
+	to_dma_iommu_mapping(dev) = mapping;
 
 	pr_debug("Attached IOMMU controller to %s device.\n", dev_name(dev));
 	return 0;
@@ -1995,7 +2025,7 @@ static void __arm_iommu_detach_device(struct device *dev)
 
 	iommu_detach_device(mapping->domain, dev);
 	kref_put(&mapping->kref, release_iommu_mapping);
-	dev->archdata.mapping = NULL;
+	to_dma_iommu_mapping(dev) = NULL;
 
 	pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev));
 }
@@ -2053,7 +2083,7 @@ static bool arm_setup_iommu_dma_ops(struct device *dev, u64 dma_base, u64 size,
 
 static void arm_teardown_iommu_dma_ops(struct device *dev)
 {
-	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
+	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 
 	if (!mapping)
 		return;
diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c
index 3d0e9aed4b40..be92fa0f2f35 100644
--- a/arch/arm/mm/init.c
+++ b/arch/arm/mm/init.c
@@ -86,55 +86,6 @@ static int __init parse_tag_initrd2(const struct tag *tag)
 
 __tagtable(ATAG_INITRD2, parse_tag_initrd2);
 
-/*
- * This keeps memory configuration data used by a couple memory
- * initialization functions, as well as show_mem() for the skipping
- * of holes in the memory map.  It is populated by arm_add_memory().
- */
-void show_mem(unsigned int filter)
-{
-	int free = 0, total = 0, reserved = 0;
-	int shared = 0, cached = 0, slab = 0;
-	struct memblock_region *reg;
-
-	printk("Mem-info:\n");
-	show_free_areas(filter);
-
-	for_each_memblock (memory, reg) {
-		unsigned int pfn1, pfn2;
-		struct page *page, *end;
-
-		pfn1 = memblock_region_memory_base_pfn(reg);
-		pfn2 = memblock_region_memory_end_pfn(reg);
-
-		page = pfn_to_page(pfn1);
-		end  = pfn_to_page(pfn2 - 1) + 1;
-
-		do {
-			total++;
-			if (PageReserved(page))
-				reserved++;
-			else if (PageSwapCache(page))
-				cached++;
-			else if (PageSlab(page))
-				slab++;
-			else if (!page_count(page))
-				free++;
-			else
-				shared += page_count(page) - 1;
-			pfn1++;
-			page = pfn_to_page(pfn1);
-		} while (pfn1 < pfn2);
-	}
-
-	printk("%d pages of RAM\n", total);
-	printk("%d free pages\n", free);
-	printk("%d reserved pages\n", reserved);
-	printk("%d slab pages\n", slab);
-	printk("%d pages shared\n", shared);
-	printk("%d pages swap cached\n", cached);
-}
-
 static void __init find_limits(unsigned long *min, unsigned long *max_low,
 			       unsigned long *max_high)
 {
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index 86ee5d47ce3c..aa0519eed698 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -507,7 +507,7 @@ cpu_arm1020_name:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 	.type	__arm1020_proc_info,#object
 __arm1020_proc_info:
@@ -519,7 +519,7 @@ __arm1020_proc_info:
 	.long   PMD_TYPE_SECT | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__arm1020_setup
+	initfn	__arm1020_setup, __arm1020_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index a6331d78601f..bff4c7f70fd6 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -465,7 +465,7 @@ arm1020e_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 	.type	__arm1020e_proc_info,#object
 __arm1020e_proc_info:
@@ -479,7 +479,7 @@ __arm1020e_proc_info:
 		PMD_BIT4 | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__arm1020e_setup
+	initfn	__arm1020e_setup, __arm1020e_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_EDSP
diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S
index a126b7a59928..dbb2413fe04d 100644
--- a/arch/arm/mm/proc-arm1022.S
+++ b/arch/arm/mm/proc-arm1022.S
@@ -448,7 +448,7 @@ arm1022_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 	.type	__arm1022_proc_info,#object
 __arm1022_proc_info:
@@ -462,7 +462,7 @@ __arm1022_proc_info:
 		PMD_BIT4 | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__arm1022_setup
+	initfn	__arm1022_setup, __arm1022_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_EDSP
diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S
index fc294067e977..0b37b2cef9d3 100644
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -442,7 +442,7 @@ arm1026_crval:
 	string	cpu_arm1026_name, "ARM1026EJ-S"
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 	.type	__arm1026_proc_info,#object
 __arm1026_proc_info:
@@ -456,7 +456,7 @@ __arm1026_proc_info:
 		PMD_BIT4 | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__arm1026_setup
+	initfn	__arm1026_setup, __arm1026_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_JAVA
diff --git a/arch/arm/mm/proc-arm720.S b/arch/arm/mm/proc-arm720.S
index 2baa66b3ac9b..3651cd70e418 100644
--- a/arch/arm/mm/proc-arm720.S
+++ b/arch/arm/mm/proc-arm720.S
@@ -186,7 +186,7 @@ arm720_crval:
  * See <asm/procinfo.h> for a definition of this structure.
  */
 	
-		.section ".proc.info.init", #alloc, #execinstr
+		.section ".proc.info.init", #alloc
 
 .macro arm720_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cpu_flush:req
 		.type	__\name\()_proc_info,#object
@@ -203,7 +203,7 @@ __\name\()_proc_info:
 			PMD_BIT4 | \
 			PMD_SECT_AP_WRITE | \
 			PMD_SECT_AP_READ
-		b	\cpu_flush				@ cpu_flush
+		initfn	\cpu_flush, __\name\()_proc_info	@ cpu_flush
 		.long	cpu_arch_name				@ arch_name
 		.long	cpu_elf_name				@ elf_name
 		.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB	@ elf_hwcap
diff --git a/arch/arm/mm/proc-arm740.S b/arch/arm/mm/proc-arm740.S
index ac1ea6b3bce4..024fb7732407 100644
--- a/arch/arm/mm/proc-arm740.S
+++ b/arch/arm/mm/proc-arm740.S
@@ -132,14 +132,14 @@ __arm740_setup:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 	.type	__arm740_proc_info,#object
 __arm740_proc_info:
 	.long	0x41807400
 	.long	0xfffffff0
 	.long	0
 	.long	0
-	b	__arm740_setup
+	initfn	__arm740_setup, __arm740_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_26BIT
diff --git a/arch/arm/mm/proc-arm7tdmi.S b/arch/arm/mm/proc-arm7tdmi.S
index bf6ba4bc30ff..25472d94426d 100644
--- a/arch/arm/mm/proc-arm7tdmi.S
+++ b/arch/arm/mm/proc-arm7tdmi.S
@@ -76,7 +76,7 @@ __arm7tdmi_setup:
 
 		.align
 
-		.section ".proc.info.init", #alloc, #execinstr
+		.section ".proc.info.init", #alloc
 
 .macro arm7tdmi_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, \
 	extra_hwcaps=0
@@ -86,7 +86,7 @@ __\name\()_proc_info:
 		.long	\cpu_mask
 		.long	0
 		.long	0
-		b	__arm7tdmi_setup
+		initfn	__arm7tdmi_setup, __\name\()_proc_info
 		.long	cpu_arch_name
 		.long	cpu_elf_name
 		.long	HWCAP_SWP | HWCAP_26BIT | ( \extra_hwcaps )
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 22bf8dde4f84..7a14bd4414c9 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -448,7 +448,7 @@ arm920_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 	.type	__arm920_proc_info,#object
 __arm920_proc_info:
@@ -464,7 +464,7 @@ __arm920_proc_info:
 		PMD_BIT4 | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__arm920_setup
+	initfn	__arm920_setup, __arm920_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB
diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S
index 0c6d5ac5a6d4..edccfcdcd551 100644
--- a/arch/arm/mm/proc-arm922.S
+++ b/arch/arm/mm/proc-arm922.S
@@ -426,7 +426,7 @@ arm922_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 	.type	__arm922_proc_info,#object
 __arm922_proc_info:
@@ -442,7 +442,7 @@ __arm922_proc_info:
 		PMD_BIT4 | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__arm922_setup
+	initfn	__arm922_setup, __arm922_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index c32d073282ea..ede8c54ab4aa 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -494,7 +494,7 @@ arm925_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 .macro arm925_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cache
 	.type	__\name\()_proc_info,#object
@@ -510,7 +510,7 @@ __\name\()_proc_info:
 		PMD_BIT4 | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__arm925_setup
+	initfn	__arm925_setup, __\name\()_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index 252b2503038d..fb827c633693 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -474,7 +474,7 @@ arm926_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 	.type	__arm926_proc_info,#object
 __arm926_proc_info:
@@ -490,7 +490,7 @@ __arm926_proc_info:
 		PMD_BIT4 | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__arm926_setup
+	initfn	__arm926_setup, __arm926_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP|HWCAP_JAVA
diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S
index e5212d489377..ee5b66f847c4 100644
--- a/arch/arm/mm/proc-arm940.S
+++ b/arch/arm/mm/proc-arm940.S
@@ -297,26 +297,16 @@ __arm940_setup:
 	mcr	p15, 0, r0, c6,	c0, 1
 
 	ldr	r0, =(CONFIG_DRAM_BASE & 0xFFFFF000) @ base[31:12] of RAM
-	ldr	r1, =(CONFIG_DRAM_SIZE >> 12)	@ size of RAM (must be >= 4KB)
-	mov	r2, #10				@ 11 is the minimum (4KB)
-1:	add	r2, r2, #1			@ area size *= 2
-	mov	r1, r1, lsr #1
-	bne	1b				@ count not zero r-shift
-	orr	r0, r0, r2, lsl #1		@ the area register value
-	orr	r0, r0, #1			@ set enable bit
-	mcr	p15, 0, r0, c6,	c1, 0		@ set area 1, RAM
-	mcr	p15, 0, r0, c6,	c1, 1
+	ldr	r7, =CONFIG_DRAM_SIZE >> 12	@ size of RAM (must be >= 4KB)
+	pr_val	r3, r0, r7, #1
+	mcr	p15, 0, r3, c6,	c1, 0		@ set area 1, RAM
+	mcr	p15, 0, r3, c6,	c1, 1
 
 	ldr	r0, =(CONFIG_FLASH_MEM_BASE & 0xFFFFF000) @ base[31:12] of FLASH
-	ldr	r1, =(CONFIG_FLASH_SIZE >> 12)	@ size of FLASH (must be >= 4KB)
-	mov	r2, #10				@ 11 is the minimum (4KB)
-1:	add	r2, r2, #1			@ area size *= 2
-	mov	r1, r1, lsr #1
-	bne	1b				@ count not zero r-shift
-	orr	r0, r0, r2, lsl #1		@ the area register value
-	orr	r0, r0, #1			@ set enable bit
-	mcr	p15, 0, r0, c6,	c2, 0		@ set area 2, ROM/FLASH
-	mcr	p15, 0, r0, c6,	c2, 1
+	ldr	r7, =CONFIG_FLASH_SIZE		@ size of FLASH (must be >= 4KB)
+	pr_val	r3, r0, r6, #1
+	mcr	p15, 0, r3, c6,	c2, 0		@ set area 2, ROM/FLASH
+	mcr	p15, 0, r3, c6,	c2, 1
 
 	mov	r0, #0x06
 	mcr	p15, 0, r0, c2, c0, 0		@ Region 1&2 cacheable
@@ -354,14 +344,14 @@ __arm940_setup:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 	.type	__arm940_proc_info,#object
 __arm940_proc_info:
 	.long	0x41009400
 	.long	0xff00fff0
 	.long	0
-	b	__arm940_setup
+	initfn	__arm940_setup, __arm940_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB
diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S
index b3dd9b2d0b8e..7361837edc31 100644
--- a/arch/arm/mm/proc-arm946.S
+++ b/arch/arm/mm/proc-arm946.S
@@ -343,24 +343,14 @@ __arm946_setup:
 	mcr	p15, 0, r0, c6,	c0, 0		@ set region 0, default
 
 	ldr	r0, =(CONFIG_DRAM_BASE & 0xFFFFF000) @ base[31:12] of RAM
-	ldr	r1, =(CONFIG_DRAM_SIZE >> 12)	@ size of RAM (must be >= 4KB)
-	mov	r2, #10				@ 11 is the minimum (4KB)
-1:	add	r2, r2, #1			@ area size *= 2
-	mov	r1, r1, lsr #1
-	bne	1b				@ count not zero r-shift
-	orr	r0, r0, r2, lsl #1		@ the region register value
-	orr	r0, r0, #1			@ set enable bit
-	mcr	p15, 0, r0, c6,	c1, 0		@ set region 1, RAM
+	ldr	r7, =CONFIG_DRAM_SIZE		@ size of RAM (must be >= 4KB)
+	pr_val	r3, r0, r7, #1
+	mcr	p15, 0, r3, c6, c1, 0
 
 	ldr	r0, =(CONFIG_FLASH_MEM_BASE & 0xFFFFF000) @ base[31:12] of FLASH
-	ldr	r1, =(CONFIG_FLASH_SIZE >> 12)	@ size of FLASH (must be >= 4KB)
-	mov	r2, #10				@ 11 is the minimum (4KB)
-1:	add	r2, r2, #1			@ area size *= 2
-	mov	r1, r1, lsr #1
-	bne	1b				@ count not zero r-shift
-	orr	r0, r0, r2, lsl #1		@ the region register value
-	orr	r0, r0, #1			@ set enable bit
-	mcr	p15, 0, r0, c6,	c2, 0		@ set region 2, ROM/FLASH
+	ldr	r7, =CONFIG_FLASH_SIZE		@ size of FLASH (must be >= 4KB)
+	pr_val	r3, r0, r7, #1
+	mcr	p15, 0, r3, c6, c2, 0
 
 	mov	r0, #0x06
 	mcr	p15, 0, r0, c2, c0, 0		@ region 1,2 d-cacheable
@@ -409,14 +399,14 @@ __arm946_setup:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 	.type	__arm946_proc_info,#object
 __arm946_proc_info:
 	.long	0x41009460
 	.long	0xff00fff0
 	.long	0
 	.long	0
-	b	__arm946_setup
+	initfn	__arm946_setup, __arm946_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB
diff --git a/arch/arm/mm/proc-arm9tdmi.S b/arch/arm/mm/proc-arm9tdmi.S
index 8227322bbb8f..7fac8c612134 100644
--- a/arch/arm/mm/proc-arm9tdmi.S
+++ b/arch/arm/mm/proc-arm9tdmi.S
@@ -70,7 +70,7 @@ __arm9tdmi_setup:
 
 		.align
 
-		.section ".proc.info.init", #alloc, #execinstr
+		.section ".proc.info.init", #alloc
 
 .macro arm9tdmi_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req
 		.type	__\name\()_proc_info, #object
@@ -79,7 +79,7 @@ __\name\()_proc_info:
 		.long	\cpu_mask
 		.long	0
 		.long	0
-		b	__arm9tdmi_setup
+		initfn	__arm9tdmi_setup, __\name\()_proc_info
 		.long	cpu_arch_name
 		.long	cpu_elf_name
 		.long	HWCAP_SWP | HWCAP_THUMB | HWCAP_26BIT
diff --git a/arch/arm/mm/proc-fa526.S b/arch/arm/mm/proc-fa526.S
index c494886892ba..4001b73af4ee 100644
--- a/arch/arm/mm/proc-fa526.S
+++ b/arch/arm/mm/proc-fa526.S
@@ -190,7 +190,7 @@ fa526_cr1_set:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 	.type	__fa526_proc_info,#object
 __fa526_proc_info:
@@ -206,7 +206,7 @@ __fa526_proc_info:
 		PMD_BIT4 | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__fa526_setup
+	initfn	__fa526_setup, __fa526_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP | HWCAP_HALF
diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index 03a1b75f2e16..e494d6d6acbe 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -584,7 +584,7 @@ feroceon_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 .macro feroceon_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cache:req
 	.type	__\name\()_proc_info,#object
@@ -601,7 +601,8 @@ __\name\()_proc_info:
 		PMD_BIT4 | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__feroceon_setup
+	initfn	__feroceon_setup, __\name\()_proc_info
+	.long __feroceon_setup
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 082b9f2f7e90..c671f345266a 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -331,3 +331,31 @@ ENTRY(\name\()_tlb_fns)
 	.globl	\x
 	.equ	\x, \y
 .endm
+
+.macro	initfn, func, base
+	.long	\func - \base
+.endm
+
+	/*
+	 * Macro to calculate the log2 size for the protection region
+	 * registers. This calculates rd = log2(size) - 1.  tmp must
+	 * not be the same register as rd.
+	 */
+.macro	pr_sz, rd, size, tmp
+	mov	\tmp, \size, lsr #12
+	mov	\rd, #11
+1:	movs	\tmp, \tmp, lsr #1
+	addne	\rd, \rd, #1
+	bne	1b
+.endm
+
+	/*
+	 * Macro to generate a protection region register value
+	 * given a pre-masked address, size, and enable bit.
+	 * Corrupts size.
+	 */
+.macro	pr_val, dest, addr, size, enable
+	pr_sz	\dest, \size, \size		@ calculate log2(size) - 1
+	orr	\dest, \addr, \dest, lsl #1	@ mask in the region size
+	orr	\dest, \dest, \enable
+.endm
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index 53d393455f13..d65edf717bf7 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -427,7 +427,7 @@ mohawk_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 	.type	__88sv331x_proc_info,#object
 __88sv331x_proc_info:
@@ -443,7 +443,7 @@ __88sv331x_proc_info:
 		PMD_BIT4 | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__mohawk_setup
+	initfn	__mohawk_setup, __88sv331x_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
diff --git a/arch/arm/mm/proc-sa110.S b/arch/arm/mm/proc-sa110.S
index 8008a0461cf5..ee2ce496239f 100644
--- a/arch/arm/mm/proc-sa110.S
+++ b/arch/arm/mm/proc-sa110.S
@@ -199,7 +199,7 @@ sa110_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 	.type	__sa110_proc_info,#object
 __sa110_proc_info:
@@ -213,7 +213,7 @@ __sa110_proc_info:
 	.long   PMD_TYPE_SECT | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__sa110_setup
+	initfn	__sa110_setup, __sa110_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_26BIT | HWCAP_FAST_MULT
diff --git a/arch/arm/mm/proc-sa1100.S b/arch/arm/mm/proc-sa1100.S
index 89f97ac648a9..222d5836f666 100644
--- a/arch/arm/mm/proc-sa1100.S
+++ b/arch/arm/mm/proc-sa1100.S
@@ -242,7 +242,7 @@ sa1100_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 .macro sa1100_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req
 	.type	__\name\()_proc_info,#object
@@ -257,7 +257,7 @@ __\name\()_proc_info:
 	.long   PMD_TYPE_SECT | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__sa1100_setup
+	initfn	__sa1100_setup, __\name\()_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_26BIT | HWCAP_FAST_MULT
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index d0390f4b3f18..06d890a2342b 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -264,7 +264,7 @@ v6_crval:
 	string	cpu_elf_name, "v6"
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 	/*
 	 * Match any ARMv6 processor core.
@@ -287,7 +287,7 @@ __v6_proc_info:
 		PMD_SECT_XN | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__v6_setup
+	initfn	__v6_setup, __v6_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	/* See also feat_v6_fixup() for HWCAP_TLS */
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index ed448d8a596b..10405b8d31af 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -37,15 +37,18 @@
  *	It is assumed that:
  *	- we are not using split page tables
  */
-ENTRY(cpu_v7_switch_mm)
+ENTRY(cpu_ca8_switch_mm)
 #ifdef CONFIG_MMU
 	mov	r2, #0
-	mmid	r1, r1				@ get mm->context.id
-	ALT_SMP(orr	r0, r0, #TTB_FLAGS_SMP)
-	ALT_UP(orr	r0, r0, #TTB_FLAGS_UP)
 #ifdef CONFIG_ARM_ERRATA_430973
 	mcr	p15, 0, r2, c7, c5, 6		@ flush BTAC/BTB
 #endif
+#endif
+ENTRY(cpu_v7_switch_mm)
+#ifdef CONFIG_MMU
+	mmid	r1, r1				@ get mm->context.id
+	ALT_SMP(orr	r0, r0, #TTB_FLAGS_SMP)
+	ALT_UP(orr	r0, r0, #TTB_FLAGS_UP)
 #ifdef CONFIG_PID_IN_CONTEXTIDR
 	mrc	p15, 0, r2, c13, c0, 1		@ read current context ID
 	lsr	r2, r2, #8			@ extract the PID
@@ -61,6 +64,7 @@ ENTRY(cpu_v7_switch_mm)
 #endif
 	bx	lr
 ENDPROC(cpu_v7_switch_mm)
+ENDPROC(cpu_ca8_switch_mm)
 
 /*
  *	cpu_v7_set_pte_ext(ptep, pte)
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 8b4ee5e81c14..3d1054f11a8a 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -153,6 +153,21 @@ ENDPROC(cpu_v7_do_resume)
 #endif
 
 /*
+ * Cortex-A8
+ */
+	globl_equ	cpu_ca8_proc_init,	cpu_v7_proc_init
+	globl_equ	cpu_ca8_proc_fin,	cpu_v7_proc_fin
+	globl_equ	cpu_ca8_reset,		cpu_v7_reset
+	globl_equ	cpu_ca8_do_idle,	cpu_v7_do_idle
+	globl_equ	cpu_ca8_dcache_clean_area, cpu_v7_dcache_clean_area
+	globl_equ	cpu_ca8_set_pte_ext,	cpu_v7_set_pte_ext
+	globl_equ	cpu_ca8_suspend_size,	cpu_v7_suspend_size
+#ifdef CONFIG_ARM_CPU_SUSPEND
+	globl_equ	cpu_ca8_do_suspend,	cpu_v7_do_suspend
+	globl_equ	cpu_ca8_do_resume,	cpu_v7_do_resume
+#endif
+
+/*
  * Cortex-A9 processor functions
  */
 	globl_equ	cpu_ca9mp_proc_init,	cpu_v7_proc_init
@@ -451,7 +466,10 @@ __v7_setup_stack:
 
 	@ define struct processor (see <asm/proc-fns.h> and proc-macros.S)
 	define_processor_functions v7, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
+#ifndef CONFIG_ARM_LPAE
+	define_processor_functions ca8, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
 	define_processor_functions ca9mp, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
+#endif
 #ifdef CONFIG_CPU_PJ4B
 	define_processor_functions pj4b, dabort=v7_early_abort, pabort=v7_pabort, suspend=1
 #endif
@@ -462,19 +480,19 @@ __v7_setup_stack:
 	string	cpu_elf_name, "v7"
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 	/*
 	 * Standard v7 proc info content
 	 */
-.macro __v7_proc initfunc, mm_mmuflags = 0, io_mmuflags = 0, hwcaps = 0, proc_fns = v7_processor_functions
+.macro __v7_proc name, initfunc, mm_mmuflags = 0, io_mmuflags = 0, hwcaps = 0, proc_fns = v7_processor_functions
 	ALT_SMP(.long	PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \
 			PMD_SECT_AF | PMD_FLAGS_SMP | \mm_mmuflags)
 	ALT_UP(.long	PMD_TYPE_SECT | PMD_SECT_AP_WRITE | PMD_SECT_AP_READ | \
 			PMD_SECT_AF | PMD_FLAGS_UP | \mm_mmuflags)
 	.long	PMD_TYPE_SECT | PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ | PMD_SECT_AF | \io_mmuflags
-	W(b)	\initfunc
+	initfn	\initfunc, \name
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP | HWCAP_HALF | HWCAP_THUMB | HWCAP_FAST_MULT | \
@@ -494,7 +512,7 @@ __v7_setup_stack:
 __v7_ca5mp_proc_info:
 	.long	0x410fc050
 	.long	0xff0ffff0
-	__v7_proc __v7_ca5mp_setup
+	__v7_proc __v7_ca5mp_proc_info, __v7_ca5mp_setup
 	.size	__v7_ca5mp_proc_info, . - __v7_ca5mp_proc_info
 
 	/*
@@ -504,9 +522,19 @@ __v7_ca5mp_proc_info:
 __v7_ca9mp_proc_info:
 	.long	0x410fc090
 	.long	0xff0ffff0
-	__v7_proc __v7_ca9mp_setup, proc_fns = ca9mp_processor_functions
+	__v7_proc __v7_ca9mp_proc_info, __v7_ca9mp_setup, proc_fns = ca9mp_processor_functions
 	.size	__v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info
 
+	/*
+	 * ARM Ltd. Cortex A8 processor.
+	 */
+	.type	__v7_ca8_proc_info, #object
+__v7_ca8_proc_info:
+	.long	0x410fc080
+	.long	0xff0ffff0
+	__v7_proc __v7_ca8_proc_info, __v7_setup, proc_fns = ca8_processor_functions
+	.size	__v7_ca8_proc_info, . - __v7_ca8_proc_info
+
 #endif	/* CONFIG_ARM_LPAE */
 
 	/*
@@ -517,7 +545,7 @@ __v7_ca9mp_proc_info:
 __v7_pj4b_proc_info:
 	.long	0x560f5800
 	.long	0xff0fff00
-	__v7_proc __v7_pj4b_setup, proc_fns = pj4b_processor_functions
+	__v7_proc __v7_pj4b_proc_info, __v7_pj4b_setup, proc_fns = pj4b_processor_functions
 	.size	__v7_pj4b_proc_info, . - __v7_pj4b_proc_info
 #endif
 
@@ -528,7 +556,7 @@ __v7_pj4b_proc_info:
 __v7_cr7mp_proc_info:
 	.long	0x410fc170
 	.long	0xff0ffff0
-	__v7_proc __v7_cr7mp_setup
+	__v7_proc __v7_cr7mp_proc_info, __v7_cr7mp_setup
 	.size	__v7_cr7mp_proc_info, . - __v7_cr7mp_proc_info
 
 	/*
@@ -538,7 +566,7 @@ __v7_cr7mp_proc_info:
 __v7_ca7mp_proc_info:
 	.long	0x410fc070
 	.long	0xff0ffff0
-	__v7_proc __v7_ca7mp_setup
+	__v7_proc __v7_ca7mp_proc_info, __v7_ca7mp_setup
 	.size	__v7_ca7mp_proc_info, . - __v7_ca7mp_proc_info
 
 	/*
@@ -548,7 +576,7 @@ __v7_ca7mp_proc_info:
 __v7_ca12mp_proc_info:
 	.long	0x410fc0d0
 	.long	0xff0ffff0
-	__v7_proc __v7_ca12mp_setup
+	__v7_proc __v7_ca12mp_proc_info, __v7_ca12mp_setup
 	.size	__v7_ca12mp_proc_info, . - __v7_ca12mp_proc_info
 
 	/*
@@ -558,7 +586,7 @@ __v7_ca12mp_proc_info:
 __v7_ca15mp_proc_info:
 	.long	0x410fc0f0
 	.long	0xff0ffff0
-	__v7_proc __v7_ca15mp_setup
+	__v7_proc __v7_ca15mp_proc_info, __v7_ca15mp_setup
 	.size	__v7_ca15mp_proc_info, . - __v7_ca15mp_proc_info
 
 	/*
@@ -568,7 +596,7 @@ __v7_ca15mp_proc_info:
 __v7_b15mp_proc_info:
 	.long	0x420f00f0
 	.long	0xff0ffff0
-	__v7_proc __v7_b15mp_setup
+	__v7_proc __v7_b15mp_proc_info, __v7_b15mp_setup
 	.size	__v7_b15mp_proc_info, . - __v7_b15mp_proc_info
 
 	/*
@@ -578,7 +606,7 @@ __v7_b15mp_proc_info:
 __v7_ca17mp_proc_info:
 	.long	0x410fc0e0
 	.long	0xff0ffff0
-	__v7_proc __v7_ca17mp_setup
+	__v7_proc __v7_ca17mp_proc_info, __v7_ca17mp_setup
 	.size	__v7_ca17mp_proc_info, . - __v7_ca17mp_proc_info
 
 	/*
@@ -594,7 +622,7 @@ __krait_proc_info:
 	 * do support them. They also don't indicate support for fused multiply
 	 * instructions even though they actually do support them.
 	 */
-	__v7_proc __v7_setup, hwcaps = HWCAP_IDIV | HWCAP_VFPv4
+	__v7_proc __krait_proc_info, __v7_setup, hwcaps = HWCAP_IDIV | HWCAP_VFPv4
 	.size	__krait_proc_info, . - __krait_proc_info
 
 	/*
@@ -604,5 +632,5 @@ __krait_proc_info:
 __v7_proc_info:
 	.long	0x000f0000		@ Required ID value
 	.long	0x000f0000		@ Mask for ID
-	__v7_proc __v7_setup
+	__v7_proc __v7_proc_info, __v7_setup
 	.size	__v7_proc_info, . - __v7_proc_info
diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S
index d1e68b553d3b..e08e1f2bab76 100644
--- a/arch/arm/mm/proc-v7m.S
+++ b/arch/arm/mm/proc-v7m.S
@@ -135,7 +135,7 @@ __v7m_setup_stack_top:
 	string cpu_elf_name "v7m"
 	string cpu_v7m_name "ARMv7-M"
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 	/*
 	 * Match any ARMv7-M processor core.
@@ -146,7 +146,7 @@ __v7m_proc_info:
 	.long	0x000f0000		@ Mask for ID
 	.long   0			@ proc_info_list.__cpu_mm_mmu_flags
 	.long   0			@ proc_info_list.__cpu_io_mmu_flags
-	b	__v7m_setup		@ proc_info_list.__cpu_flush
+	initfn	__v7m_setup, __v7m_proc_info	@ proc_info_list.__cpu_flush
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index f8acdfece036..293dcc2c441f 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -499,7 +499,7 @@ xsc3_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 .macro xsc3_proc_info name:req, cpu_val:req, cpu_mask:req
 	.type	__\name\()_proc_info,#object
@@ -514,7 +514,7 @@ __\name\()_proc_info:
 	.long	PMD_TYPE_SECT | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__xsc3_setup
+	initfn	__xsc3_setup, __\name\()_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index afa2b3c4df4a..b6bbfdb6dfdc 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -612,7 +612,7 @@ xscale_crval:
 
 	.align
 
-	.section ".proc.info.init", #alloc, #execinstr
+	.section ".proc.info.init", #alloc
 
 .macro xscale_proc_info name:req, cpu_val:req, cpu_mask:req, cpu_name:req, cache
 	.type	__\name\()_proc_info,#object
@@ -627,7 +627,7 @@ __\name\()_proc_info:
 	.long	PMD_TYPE_SECT | \
 		PMD_SECT_AP_WRITE | \
 		PMD_SECT_AP_READ
-	b	__xscale_setup
+	initfn	__xscale_setup, __\name\()_proc_info
 	.long	cpu_arch_name
 	.long	cpu_elf_name
 	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP