Merge branches 'machtypes', 'core', 'ep93xx', 'ks8695', 'netdev' and 'sa1100' into devel

arch/arm/Kconfig

@@ -148,7 +148,6 @@ config ARCH_MAY_HAVE_PC_FDC
 
 config ZONE_DMA
 	bool
-	default y
 
 config GENERIC_ISA_DMA
 	bool
@@ -178,6 +177,11 @@ config OPROFILE_MPCORE
 config OPROFILE_ARM11_CORE
 	bool
 
+config OPROFILE_ARMV7
+	def_bool y
+	depends on CPU_V7 && !SMP
+	bool
+
 endif
 
 config VECTORS_BASE
@@ -245,6 +249,7 @@ config ARCH_CLPS7500
 	select TIMER_ACORN
 	select ISA
 	select NO_IOPORT
+	select ARCH_SPARSEMEM_ENABLE
 	help
 	  Support for the Cirrus Logic PS7500FE system-on-a-chip.
 
@@ -306,6 +311,7 @@ config ARCH_IOP13XX
 	select PLAT_IOP
 	select PCI
 	select ARCH_SUPPORTS_MSI
+	select VMSPLIT_1G
 	help
 	  Support for Intel's IOP13XX (XScale) family of processors.
 
@@ -350,6 +356,7 @@ config ARCH_IXP4XX
 	select GENERIC_GPIO
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
+	select ZONE_DMA if PCI
 	help
 	  Support for Intel's IXP4XX (XScale) family of processors.
 
@@ -464,6 +471,7 @@ config ARCH_RPC
 	select HAVE_PATA_PLATFORM
 	select ISA_DMA_API
 	select NO_IOPORT
+	select ARCH_SPARSEMEM_ENABLE
 	help
 	  On the Acorn Risc-PC, Linux can support the internal IDE disk and
 	  CD-ROM interface, serial and parallel port, and the floppy drive.
@@ -471,9 +479,7 @@ config ARCH_RPC
 config ARCH_SA1100
 	bool "SA1100-based"
 	select ISA
-	select ARCH_DISCONTIGMEM_ENABLE
 	select ARCH_SPARSEMEM_ENABLE
-	select ARCH_SELECT_MEMORY_MODEL
 	select ARCH_MTD_XIP
 	select GENERIC_GPIO
 	select GENERIC_TIME
@@ -497,6 +503,7 @@ config ARCH_SHARK
 	bool "Shark"
 	select ISA
 	select ISA_DMA
+	select ZONE_DMA
 	select PCI
 	help
 	  Support for the StrongARM based Digital DNARD machine, also known
@@ -504,6 +511,8 @@ config ARCH_SHARK
 
 config ARCH_LH7A40X
 	bool "Sharp LH7A40X"
+	select ARCH_DISCONTIGMEM_ENABLE if !LH7A40X_CONTIGMEM
+	select ARCH_SPARSEMEM_ENABLE if !LH7A40X_CONTIGMEM
 	help
 	  Say Y here for systems based on one of the Sharp LH7A40X
 	  System on a Chip processors.  These CPUs include an ARM922T
@@ -516,6 +525,7 @@ config ARCH_DAVINCI
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_GPIO
 	select HAVE_CLK
+	select ZONE_DMA
 	help
 	  Support for TI's DaVinci platform.
 
@@ -734,6 +744,29 @@ config SMP
 
 	  If you don't know what to do here, say N.
 
+choice
+	prompt "Memory split"
+	default VMSPLIT_3G
+	help
+	  Select the desired split between kernel and user memory.
+
+	  If you are not absolutely sure what you are doing, leave this
+	  option alone!
+
+	config VMSPLIT_3G
+		bool "3G/1G user/kernel split"
+	config VMSPLIT_2G
+		bool "2G/2G user/kernel split"
+	config VMSPLIT_1G
+		bool "1G/3G user/kernel split"
+endchoice
+
+config PAGE_OFFSET
+	hex
+	default 0x40000000 if VMSPLIT_1G
+	default 0x80000000 if VMSPLIT_2G
+	default 0xC0000000
+
 config NR_CPUS
 	int "Maximum number of CPUs (2-32)"
 	range 2 32
@@ -810,20 +843,18 @@ config OABI_COMPAT
 	  UNPREDICTABLE (in fact it can be predicted that it won't work
 	  at all). If in doubt say Y.
 
+# Discontigmem is deprecated
 config ARCH_DISCONTIGMEM_ENABLE
 	bool
-	default (ARCH_LH7A40X && !LH7A40X_CONTIGMEM)
-	help
-	  Say Y to support efficient handling of discontiguous physical memory,
-	  for architectures which are either NUMA (Non-Uniform Memory Access)
-	  or have huge holes in the physical address space for other reasons.
-	  See <file:Documentation/vm/numa> for more.
 
 config ARCH_SPARSEMEM_ENABLE
 	bool
 
+config ARCH_SPARSEMEM_DEFAULT
+	def_bool ARCH_SPARSEMEM_ENABLE
+
 config ARCH_SELECT_MEMORY_MODEL
-	bool
+	def_bool ARCH_DISCONTIGMEM_ENABLE && ARCH_SPARSEMEM_ENABLE
 
 config NODES_SHIFT
 	int
@@ -1000,9 +1031,9 @@ config ATAGS_PROC
 
 endmenu
 
-if (ARCH_SA1100 || ARCH_INTEGRATOR || ARCH_OMAP || ARCH_IMX || ARCH_PXA)
+menu "CPU Power Management"
 
-menu "CPU Frequency scaling"
+if (ARCH_SA1100 || ARCH_INTEGRATOR || ARCH_OMAP || ARCH_IMX || ARCH_PXA)
 
 source "drivers/cpufreq/Kconfig"
 
@@ -1042,10 +1073,12 @@ config CPU_FREQ_PXA
 	default y
 	select CPU_FREQ_DEFAULT_GOV_USERSPACE
 
-endmenu
-
 endif
 
+source "drivers/cpuidle/Kconfig"
+
+endmenu
+
 menu "Floating point emulation"
 
 comment "At least one emulation must be selected"
@@ -1197,6 +1230,8 @@ source "drivers/power/Kconfig"
 
 source "drivers/hwmon/Kconfig"
 
+source "drivers/thermal/Kconfig"
+
 source "drivers/watchdog/Kconfig"
 
 source "drivers/ssb/Kconfig"
@@ -1217,6 +1252,10 @@ source "drivers/usb/Kconfig"
 
 source "drivers/mmc/Kconfig"
 
+source "drivers/memstick/Kconfig"
+
+source "drivers/accessibility/Kconfig"
+
 source "drivers/leds/Kconfig"
 
 source "drivers/rtc/Kconfig"
@@ -1225,6 +1264,8 @@ source "drivers/dma/Kconfig"
 
 source "drivers/dca/Kconfig"
 
+source "drivers/auxdisplay/Kconfig"
+
 source "drivers/regulator/Kconfig"
 
 source "drivers/uio/Kconfig"

arch/arm/Makefile

@@ -47,7 +47,7 @@ comma = ,
 # Note that GCC does not numerically define an architecture version
 # macro, but instead defines a whole series of macros which makes
 # testing for a specific architecture or later rather impossible.
-arch-$(CONFIG_CPU_32v7)		:=-D__LINUX_ARM_ARCH__=7 $(call cc-option,-march=armv7a,-march=armv5t -Wa$(comma)-march=armv7a)
+arch-$(CONFIG_CPU_32v7)		:=-D__LINUX_ARM_ARCH__=7 $(call cc-option,-march=armv7-a,-march=armv5t -Wa$(comma)-march=armv7-a)
 arch-$(CONFIG_CPU_32v6)		:=-D__LINUX_ARM_ARCH__=6 $(call cc-option,-march=armv6,-march=armv5t -Wa$(comma)-march=armv6)
 # Only override the compiler option if ARMv6. The ARMv6K extensions are
 # always available in ARMv7

arch/arm/boot/compressed/Makefile

@@ -76,7 +76,7 @@ KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
 endif
 
 EXTRA_CFLAGS  := -fpic -fno-builtin
-EXTRA_AFLAGS  :=
+EXTRA_AFLAGS  := -Wa,-march=all
 
 # Supply ZRELADDR, INITRD_PHYS and PARAMS_PHYS to the decompressor via
 # linker symbols.  We only define initrd_phys and params_phys if the

arch/arm/boot/compressed/head.S

@@ -421,6 +421,7 @@ __setup_mmu:	sub	r3, r4, #16384		@ Page directory size
 		add	r1, r1, #1048576
 		str	r1, [r0]
 		mov	pc, lr
+ENDPROC(__setup_mmu)
 
 __armv4_mmu_cache_on:
 		mov	r12, lr
@@ -801,7 +802,7 @@ loop1:
 		add	r2, r2, #4		@ add 4 (line length offset)
 		ldr	r4, =0x3ff
 		ands	r4, r4, r1, lsr #3	@ find maximum number on the way size
-		.word	0xe16f5f14		@ clz r5, r4 - find bit position of way size increment
+		clz	r5, r4			@ find bit position of way size increment
 		ldr	r7, =0x7fff
 		ands	r7, r7, r1, lsr #13	@ extract max number of the index size
 loop2:

arch/arm/common/Kconfig

@@ -12,7 +12,8 @@ config ICST307
 
 config SA1111
 	bool
-	select DMABOUNCE
+	select DMABOUNCE if !ARCH_PXA
+	select ZONE_DMA if !ARCH_PXA
 
 config DMABOUNCE
 	bool

arch/arm/common/dmabounce.c

@@ -154,9 +154,7 @@ alloc_safe_buffer(struct dmabounce_device_info *device_info, void *ptr,
 #endif
 
 	write_lock_irqsave(&device_info->lock, flags);
-
 	list_add(&buf->node, &device_info->safe_buffers);
-
 	write_unlock_irqrestore(&device_info->lock, flags);
 
 	return buf;
@@ -205,8 +203,22 @@ free_safe_buffer(struct dmabounce_device_info *device_info, struct safe_buffer *
 
 /* ************************************************** */
 
-static inline dma_addr_t
-map_single(struct device *dev, void *ptr, size_t size,
+static struct safe_buffer *find_safe_buffer_dev(struct device *dev,
+		dma_addr_t dma_addr, const char *where)
+{
+	if (!dev || !dev->archdata.dmabounce)
+		return NULL;
+	if (dma_mapping_error(dev, dma_addr)) {
+		if (dev)
+			dev_err(dev, "Trying to %s invalid mapping\n", where);
+		else
+			pr_err("unknown device: Trying to %s invalid mapping\n", where);
+		return NULL;
+	}
+	return find_safe_buffer(dev->archdata.dmabounce, dma_addr);
+}
+
+static inline dma_addr_t map_single(struct device *dev, void *ptr, size_t size,
 		enum dma_data_direction dir)
 {
 	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
@@ -270,33 +282,21 @@ map_single(struct device *dev, void *ptr, size_t size,
 	return dma_addr;
 }
 
-static inline void
-unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-		enum dma_data_direction dir)
+static inline void unmap_single(struct device *dev, dma_addr_t dma_addr,
+		size_t size, enum dma_data_direction dir)
 {
-	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
-	struct safe_buffer *buf = NULL;
-
-	/*
-	 * Trying to unmap an invalid mapping
-	 */
-	if (dma_mapping_error(dev, dma_addr)) {
-		dev_err(dev, "Trying to unmap invalid mapping\n");
-		return;
-	}
-
-	if (device_info)
-		buf = find_safe_buffer(device_info, dma_addr);
+	struct safe_buffer *buf = find_safe_buffer_dev(dev, dma_addr, "unmap");
 
 	if (buf) {
 		BUG_ON(buf->size != size);
+		BUG_ON(buf->direction != dir);
 
 		dev_dbg(dev,
 			"%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
 			__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
 			buf->safe, buf->safe_dma_addr);
 
-		DO_STATS ( device_info->bounce_count++ );
+		DO_STATS(dev->archdata.dmabounce->bounce_count++);
 
 		if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) {
 			void *ptr = buf->ptr;
@@ -317,74 +317,7 @@ unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
 			dmac_clean_range(ptr, ptr + size);
 			outer_clean_range(__pa(ptr), __pa(ptr) + size);
 		}
-		free_safe_buffer(device_info, buf);
-	}
-}
-
-static int sync_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-			enum dma_data_direction dir)
-{
-	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
-	struct safe_buffer *buf = NULL;
-
-	if (device_info)
-		buf = find_safe_buffer(device_info, dma_addr);
-
-	if (buf) {
-		/*
-		 * Both of these checks from original code need to be
-		 * commented out b/c some drivers rely on the following:
-		 *
-		 * 1) Drivers may map a large chunk of memory into DMA space
-		 *    but only sync a small portion of it. Good example is
-		 *    allocating a large buffer, mapping it, and then
-		 *    breaking it up into small descriptors. No point
-		 *    in syncing the whole buffer if you only have to
-		 *    touch one descriptor.
-		 *
-		 * 2) Buffers that are mapped as DMA_BIDIRECTIONAL are
-		 *    usually only synced in one dir at a time.
-		 *
-		 * See drivers/net/eepro100.c for examples of both cases.
-		 *
-		 * -ds
-		 *
-		 * BUG_ON(buf->size != size);
-		 * BUG_ON(buf->direction != dir);
-		 */
-
-		dev_dbg(dev,
-			"%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
-			__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
-			buf->safe, buf->safe_dma_addr);
-
-		DO_STATS ( device_info->bounce_count++ );
-
-		switch (dir) {
-		case DMA_FROM_DEVICE:
-			dev_dbg(dev,
-				"%s: copy back safe %p to unsafe %p size %d\n",
-				__func__, buf->safe, buf->ptr, size);
-			memcpy(buf->ptr, buf->safe, size);
-			break;
-		case DMA_TO_DEVICE:
-			dev_dbg(dev,
-				"%s: copy out unsafe %p to safe %p, size %d\n",
-				__func__,buf->ptr, buf->safe, size);
-			memcpy(buf->safe, buf->ptr, size);
-			break;
-		case DMA_BIDIRECTIONAL:
-			BUG();	/* is this allowed?  what does it mean? */
-		default:
-			BUG();
-		}
-		/*
-		 * No need to sync the safe buffer - it was allocated
-		 * via the coherent allocators.
-		 */
-		return 0;
-	} else {
-		return 1;
+		free_safe_buffer(dev->archdata.dmabounce, buf);
 	}
 }
 
@@ -396,21 +329,29 @@ static int sync_single(struct device *dev, dma_addr_t dma_addr, size_t size,
  * substitute the safe buffer for the unsafe one.
  * (basically move the buffer from an unsafe area to a safe one)
  */
-dma_addr_t
-dma_map_single(struct device *dev, void *ptr, size_t size,
+dma_addr_t dma_map_single(struct device *dev, void *ptr, size_t size,
 		enum dma_data_direction dir)
 {
-	dma_addr_t dma_addr;
-
 	dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
 		__func__, ptr, size, dir);
 
-	BUG_ON(dir == DMA_NONE);
+	BUG_ON(!valid_dma_direction(dir));
 
-	dma_addr = map_single(dev, ptr, size, dir);
+	return map_single(dev, ptr, size, dir);
+}
+EXPORT_SYMBOL(dma_map_single);
 
-	return dma_addr;
+dma_addr_t dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir)
+{
+	dev_dbg(dev, "%s(page=%p,off=%#lx,size=%zx,dir=%x)\n",
+		__func__, page, offset, size, dir);
+
+	BUG_ON(!valid_dma_direction(dir));
+
+	return map_single(dev, page_address(page) + offset, size, dir);
 }
+EXPORT_SYMBOL(dma_map_page);
 
 /*
  * see if a mapped address was really a "safe" buffer and if so, copy
@@ -419,126 +360,76 @@ dma_map_single(struct device *dev, void *ptr, size_t size,
  * should be)
  */
 
-void
-dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
-			enum dma_data_direction dir)
+void dma_unmap_single(struct device *dev, dma_addr_t dma_addr, size_t size,
+		enum dma_data_direction dir)
 {
 	dev_dbg(dev, "%s(ptr=%p,size=%d,dir=%x)\n",
 		__func__, (void *) dma_addr, size, dir);
 
-	BUG_ON(dir == DMA_NONE);
-
 	unmap_single(dev, dma_addr, size, dir);
 }
+EXPORT_SYMBOL(dma_unmap_single);
 
-int
-dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-		enum dma_data_direction dir)
+int dmabounce_sync_for_cpu(struct device *dev, dma_addr_t addr,
+		unsigned long off, size_t sz, enum dma_data_direction dir)
 {
-	int i;
-
-	dev_dbg(dev, "%s(sg=%p,nents=%d,dir=%x)\n",
-		__func__, sg, nents, dir);
-
-	BUG_ON(dir == DMA_NONE);
-
-	for (i = 0; i < nents; i++, sg++) {
-		struct page *page = sg_page(sg);
-		unsigned int offset = sg->offset;
-		unsigned int length = sg->length;
-		void *ptr = page_address(page) + offset;
+	struct safe_buffer *buf;
 
-		sg->dma_address =
-			map_single(dev, ptr, length, dir);
-	}
+	dev_dbg(dev, "%s(dma=%#x,off=%#lx,sz=%zx,dir=%x)\n",
+		__func__, addr, off, sz, dir);
 
-	return nents;
-}
-
-void
-dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
-		enum dma_data_direction dir)
-{
-	int i;
+	buf = find_safe_buffer_dev(dev, addr, __func__);
+	if (!buf)
+		return 1;
 
-	dev_dbg(dev, "%s(sg=%p,nents=%d,dir=%x)\n",
-		__func__, sg, nents, dir);
+	BUG_ON(buf->direction != dir);
 
-	BUG_ON(dir == DMA_NONE);
+	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
+		__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
+		buf->safe, buf->safe_dma_addr);
 
-	for (i = 0; i < nents; i++, sg++) {
-		dma_addr_t dma_addr = sg->dma_address;
-		unsigned int length = sg->length;
+	DO_STATS(dev->archdata.dmabounce->bounce_count++);
 
-		unmap_single(dev, dma_addr, length, dir);
+	if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) {
+		dev_dbg(dev, "%s: copy back safe %p to unsafe %p size %d\n",
+			__func__, buf->safe + off, buf->ptr + off, sz);
+		memcpy(buf->ptr + off, buf->safe + off, sz);
 	}
+	return 0;
 }
+EXPORT_SYMBOL(dmabounce_sync_for_cpu);
 
-void dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t dma_addr,
-				   unsigned long offset, size_t size,
-				   enum dma_data_direction dir)
-{
-	dev_dbg(dev, "%s(dma=%#x,off=%#lx,size=%zx,dir=%x)\n",
-		__func__, dma_addr, offset, size, dir);
-
-	if (sync_single(dev, dma_addr, offset + size, dir))
-		dma_cache_maint(dma_to_virt(dev, dma_addr) + offset, size, dir);
-}
-EXPORT_SYMBOL(dma_sync_single_range_for_cpu);
-
-void dma_sync_single_range_for_device(struct device *dev, dma_addr_t dma_addr,
-				      unsigned long offset, size_t size,
-				      enum dma_data_direction dir)
-{
-	dev_dbg(dev, "%s(dma=%#x,off=%#lx,size=%zx,dir=%x)\n",
-		__func__, dma_addr, offset, size, dir);
-
-	if (sync_single(dev, dma_addr, offset + size, dir))
-		dma_cache_maint(dma_to_virt(dev, dma_addr) + offset, size, dir);
-}
-EXPORT_SYMBOL(dma_sync_single_range_for_device);
-
-void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nents,
-			enum dma_data_direction dir)
+int dmabounce_sync_for_device(struct device *dev, dma_addr_t addr,
+		unsigned long off, size_t sz, enum dma_data_direction dir)
 {
-	int i;
-
-	dev_dbg(dev, "%s(sg=%p,nents=%d,dir=%x)\n",
-		__func__, sg, nents, dir);
-
-	BUG_ON(dir == DMA_NONE);
+	struct safe_buffer *buf;
 
-	for (i = 0; i < nents; i++, sg++) {
-		dma_addr_t dma_addr = sg->dma_address;
-		unsigned int length = sg->length;
+	dev_dbg(dev, "%s(dma=%#x,off=%#lx,sz=%zx,dir=%x)\n",
+		__func__, addr, off, sz, dir);
 
-		sync_single(dev, dma_addr, length, dir);
-	}
-}
-
-void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nents,
-			enum dma_data_direction dir)
-{
-	int i;
+	buf = find_safe_buffer_dev(dev, addr, __func__);
+	if (!buf)
+		return 1;
 
-	dev_dbg(dev, "%s(sg=%p,nents=%d,dir=%x)\n",
-		__func__, sg, nents, dir);
+	BUG_ON(buf->direction != dir);
 
-	BUG_ON(dir == DMA_NONE);
+	dev_dbg(dev, "%s: unsafe buffer %p (dma=%#x) mapped to %p (dma=%#x)\n",
+		__func__, buf->ptr, virt_to_dma(dev, buf->ptr),
+		buf->safe, buf->safe_dma_addr);
 
-	for (i = 0; i < nents; i++, sg++) {
-		dma_addr_t dma_addr = sg->dma_address;
-		unsigned int length = sg->length;
+	DO_STATS(dev->archdata.dmabounce->bounce_count++);
 
-		sync_single(dev, dma_addr, length, dir);
+	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) {
+		dev_dbg(dev, "%s: copy out unsafe %p to safe %p, size %d\n",
+			__func__,buf->ptr + off, buf->safe + off, sz);
+		memcpy(buf->safe + off, buf->ptr + off, sz);
 	}
+	return 0;
 }
+EXPORT_SYMBOL(dmabounce_sync_for_device);
 
-static int
-dmabounce_init_pool(struct dmabounce_pool *pool, struct device *dev, const char *name,
-		    unsigned long size)
+static int dmabounce_init_pool(struct dmabounce_pool *pool, struct device *dev,
+		const char *name, unsigned long size)
 {
 	pool->size = size;
 	DO_STATS(pool->allocs = 0);
@@ -549,9 +440,8 @@ dmabounce_init_pool(struct dmabounce_pool *pool, struct device *dev, const char
 	return pool->pool ? 0 : -ENOMEM;
 }
 
-int
-dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size,
-			unsigned long large_buffer_size)
+int dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size,
+		unsigned long large_buffer_size)
 {
 	struct dmabounce_device_info *device_info;
 	int ret;
@@ -607,9 +497,9 @@ dmabounce_register_dev(struct device *dev, unsigned long small_buffer_size,
 	kfree(device_info);
 	return ret;
 }
+EXPORT_SYMBOL(dmabounce_register_dev);
 
-void
-dmabounce_unregister_dev(struct device *dev)
+void dmabounce_unregister_dev(struct device *dev)
 {
 	struct dmabounce_device_info *device_info = dev->archdata.dmabounce;
 
@@ -642,15 +532,6 @@ dmabounce_unregister_dev(struct device *dev)
 
 	dev_info(dev, "dmabounce: device unregistered\n");
 }
-
-
-EXPORT_SYMBOL(dma_map_single);
-EXPORT_SYMBOL(dma_unmap_single);
-EXPORT_SYMBOL(dma_map_sg);
-EXPORT_SYMBOL(dma_unmap_sg);
-EXPORT_SYMBOL(dma_sync_sg_for_cpu);
-EXPORT_SYMBOL(dma_sync_sg_for_device);
-EXPORT_SYMBOL(dmabounce_register_dev);
 EXPORT_SYMBOL(dmabounce_unregister_dev);
 
 MODULE_AUTHOR("Christopher Hoover <ch@hpl.hp.com>, Deepak Saxena <dsaxena@plexity.net>");

arch/arm/common/gic.c

@@ -27,9 +27,9 @@
 #include <linux/list.h>
 #include <linux/smp.h>
 #include <linux/cpumask.h>
+#include <linux/io.h>
 
 #include <asm/irq.h>
-#include <asm/io.h>
 #include <asm/mach/irq.h>
 #include <asm/hardware/gic.h>
 

arch/arm/common/locomo.c

@@ -24,9 +24,9 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/io.h>
 
 #include <mach/hardware.h>
-#include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/mach/irq.h>
 

arch/arm/common/sa1111.c

@@ -25,10 +25,10 @@
 #include <linux/spinlock.h>
 #include <linux/dma-mapping.h>
 #include <linux/clk.h>
+#include <linux/io.h>
 
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
-#include <asm/io.h>
 #include <asm/irq.h>
 #include <asm/mach/irq.h>
 #include <asm/sizes.h>

arch/arm/common/scoop.c

@@ -15,7 +15,7 @@
 #include <linux/string.h>
 #include <linux/slab.h>
 #include <linux/platform_device.h>
-#include <asm/io.h>
+#include <linux/io.h>
 #include <asm/gpio.h>
 #include <asm/hardware/scoop.h>
 

arch/arm/common/time-acorn.c

@@ -17,9 +17,9 @@
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/io.h>
 
 #include <mach/hardware.h>
-#include <asm/io.h>
 #include <asm/hardware/ioc.h>
 
 #include <asm/mach/time.h>

arch/arm/common/uengine.c

@@ -16,9 +16,9 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/string.h>
+#include <linux/io.h>
 #include <mach/hardware.h>
 #include <asm/hardware/uengine.h>
-#include <asm/io.h>
 
 #if defined(CONFIG_ARCH_IXP2000)
 #define IXP_UENGINE_CSR_VIRT_BASE	IXP2000_UENGINE_CSR_VIRT_BASE

arch/arm/common/via82c505.c

@@ -4,8 +4,8 @@
 #include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
+#include <linux/io.h>
 
-#include <asm/io.h>
 #include <asm/system.h>
 
 #include <asm/mach/pci.h>

arch/arm/common/vic.c

@@ -20,8 +20,8 @@
  */
 #include <linux/init.h>
 #include <linux/list.h>
+#include <linux/io.h>
 
-#include <asm/io.h>
 #include <asm/mach/irq.h>
 #include <asm/hardware/vic.h>
 

arch/arm/include/asm/bug.h

@@ -12,7 +12,7 @@ extern void __bug(const char *file, int line) __attribute__((noreturn));
 #else
 
 /* this just causes an oops */
-#define BUG()		(*(int *)0 = 0)
+#define BUG()		do { *(int *)0 = 0; } while (1)
 
 #endif
 

arch/arm/include/asm/cacheflush.h

@@ -444,94 +444,4 @@ static inline void flush_ioremap_region(unsigned long phys, void __iomem *virt,
 	dmac_inv_range(start, start + size);
 }
 
-#define __cacheid_present(val)			(val != read_cpuid(CPUID_ID))
-#define __cacheid_type_v7(val)			((val & (7 << 29)) == (4 << 29))
-
-#define __cacheid_vivt_prev7(val)		((val & (15 << 25)) != (14 << 25))
-#define __cacheid_vipt_prev7(val)		((val & (15 << 25)) == (14 << 25))
-#define __cacheid_vipt_nonaliasing_prev7(val)	((val & (15 << 25 | 1 << 23)) == (14 << 25))
-#define __cacheid_vipt_aliasing_prev7(val)	((val & (15 << 25 | 1 << 23)) == (14 << 25 | 1 << 23))
-
-#define __cacheid_vivt(val)			(__cacheid_type_v7(val) ? 0 : __cacheid_vivt_prev7(val))
-#define __cacheid_vipt(val)			(__cacheid_type_v7(val) ? 1 : __cacheid_vipt_prev7(val))
-#define __cacheid_vipt_nonaliasing(val)		(__cacheid_type_v7(val) ? 1 : __cacheid_vipt_nonaliasing_prev7(val))
-#define __cacheid_vipt_aliasing(val)		(__cacheid_type_v7(val) ? 0 : __cacheid_vipt_aliasing_prev7(val))
-#define __cacheid_vivt_asid_tagged_instr(val)	(__cacheid_type_v7(val) ? ((val & (3 << 14)) == (1 << 14)) : 0)
-
-#if defined(CONFIG_CPU_CACHE_VIVT) && !defined(CONFIG_CPU_CACHE_VIPT)
-/*
- * VIVT caches only
- */
-#define cache_is_vivt()			1
-#define cache_is_vipt()			0
-#define cache_is_vipt_nonaliasing()	0
-#define cache_is_vipt_aliasing()	0
-#define icache_is_vivt_asid_tagged()	0
-
-#elif !defined(CONFIG_CPU_CACHE_VIVT) && defined(CONFIG_CPU_CACHE_VIPT)
-/*
- * VIPT caches only
- */
-#define cache_is_vivt()			0
-#define cache_is_vipt()			1
-#define cache_is_vipt_nonaliasing()					\
-	({								\
-		unsigned int __val = read_cpuid(CPUID_CACHETYPE);	\
-		__cacheid_vipt_nonaliasing(__val);			\
-	})
-
-#define cache_is_vipt_aliasing()					\
-	({								\
-		unsigned int __val = read_cpuid(CPUID_CACHETYPE);	\
-		__cacheid_vipt_aliasing(__val);				\
-	})
-
-#define icache_is_vivt_asid_tagged()					\
-	({								\
-		unsigned int __val = read_cpuid(CPUID_CACHETYPE);	\
-		__cacheid_vivt_asid_tagged_instr(__val);		\
-	})
-
-#else
-/*
- * VIVT or VIPT caches.  Note that this is unreliable since ARM926
- * and V6 CPUs satisfy the "(val & (15 << 25)) == (14 << 25)" test.
- * There's no way to tell from the CacheType register what type (!)
- * the cache is.
- */
-#define cache_is_vivt()							\
-	({								\
-		unsigned int __val = read_cpuid(CPUID_CACHETYPE);	\
-		(!__cacheid_present(__val)) || __cacheid_vivt(__val);	\
-	})
-		
-#define cache_is_vipt()							\
-	({								\
-		unsigned int __val = read_cpuid(CPUID_CACHETYPE);	\
-		__cacheid_present(__val) && __cacheid_vipt(__val);	\
-	})
-
-#define cache_is_vipt_nonaliasing()					\
-	({								\
-		unsigned int __val = read_cpuid(CPUID_CACHETYPE);	\
-		__cacheid_present(__val) &&				\
-		 __cacheid_vipt_nonaliasing(__val);			\
-	})
-
-#define cache_is_vipt_aliasing()					\
-	({								\
-		unsigned int __val = read_cpuid(CPUID_CACHETYPE);	\
-		__cacheid_present(__val) &&				\
-		 __cacheid_vipt_aliasing(__val);			\
-	})
-
-#define icache_is_vivt_asid_tagged()					\
-	({								\
-		unsigned int __val = read_cpuid(CPUID_CACHETYPE);	\
-		__cacheid_present(__val) &&				\
-		 __cacheid_vivt_asid_tagged_instr(__val);		\
-	})
-
-#endif
-
 #endif

arch/arm/include/asm/cachetype.h

@@ -0,0 +1,52 @@
+#ifndef __ASM_ARM_CACHETYPE_H
+#define __ASM_ARM_CACHETYPE_H
+
+#define CACHEID_VIVT			(1 << 0)
+#define CACHEID_VIPT_NONALIASING	(1 << 1)
+#define CACHEID_VIPT_ALIASING		(1 << 2)
+#define CACHEID_VIPT			(CACHEID_VIPT_ALIASING|CACHEID_VIPT_NONALIASING)
+#define CACHEID_ASID_TAGGED		(1 << 3)
+
+extern unsigned int cacheid;
+
+#define cache_is_vivt()			cacheid_is(CACHEID_VIVT)
+#define cache_is_vipt()			cacheid_is(CACHEID_VIPT)
+#define cache_is_vipt_nonaliasing()	cacheid_is(CACHEID_VIPT_NONALIASING)
+#define cache_is_vipt_aliasing()	cacheid_is(CACHEID_VIPT_ALIASING)
+#define icache_is_vivt_asid_tagged()	cacheid_is(CACHEID_ASID_TAGGED)
+
+/*
+ * __LINUX_ARM_ARCH__ is the minimum supported CPU architecture
+ * Mask out support which will never be present on newer CPUs.
+ * - v6+ is never VIVT
+ * - v7+ VIPT never aliases
+ */
+#if __LINUX_ARM_ARCH__ >= 7
+#define __CACHEID_ARCH_MIN	(CACHEID_VIPT_NONALIASING | CACHEID_ASID_TAGGED)
+#elif __LINUX_ARM_ARCH__ >= 6
+#define	__CACHEID_ARCH_MIN	(~CACHEID_VIVT)
+#else
+#define __CACHEID_ARCH_MIN	(~0)
+#endif
+
+/*
+ * Mask out support which isn't configured
+ */
+#if defined(CONFIG_CPU_CACHE_VIVT) && !defined(CONFIG_CPU_CACHE_VIPT)
+#define __CACHEID_ALWAYS	(CACHEID_VIVT)
+#define __CACHEID_NEVER		(~CACHEID_VIVT)
+#elif !defined(CONFIG_CPU_CACHE_VIVT) && defined(CONFIG_CPU_CACHE_VIPT)
+#define __CACHEID_ALWAYS	(0)
+#define __CACHEID_NEVER		(CACHEID_VIVT)
+#else
+#define __CACHEID_ALWAYS	(0)
+#define __CACHEID_NEVER		(0)
+#endif
+
+static inline unsigned int __attribute__((pure)) cacheid_is(unsigned int mask)
+{
+	return (__CACHEID_ALWAYS & mask) |
+	       (~__CACHEID_NEVER & __CACHEID_ARCH_MIN & mask & cacheid);
+}
+
+#endif

arch/arm/include/asm/cputype.h

@@ -0,0 +1,64 @@
+#ifndef __ASM_ARM_CPUTYPE_H
+#define __ASM_ARM_CPUTYPE_H
+
+#include <linux/stringify.h>
+
+#define CPUID_ID	0
+#define CPUID_CACHETYPE	1
+#define CPUID_TCM	2
+#define CPUID_TLBTYPE	3
+
+#ifdef CONFIG_CPU_CP15
+#define read_cpuid(reg)							\
+	({								\
+		unsigned int __val;					\
+		asm("mrc	p15, 0, %0, c0, c0, " __stringify(reg)	\
+		    : "=r" (__val)					\
+		    :							\
+		    : "cc");						\
+		__val;							\
+	})
+#else
+extern unsigned int processor_id;
+#define read_cpuid(reg) (processor_id)
+#endif
+
+/*
+ * The CPU ID never changes at run time, so we might as well tell the
+ * compiler that it's constant.  Use this function to read the CPU ID
+ * rather than directly reading processor_id or read_cpuid() directly.
+ */
+static inline unsigned int __attribute_const__ read_cpuid_id(void)
+{
+	return read_cpuid(CPUID_ID);
+}
+
+static inline unsigned int __attribute_const__ read_cpuid_cachetype(void)
+{
+	return read_cpuid(CPUID_CACHETYPE);
+}
+
+/*
+ * Intel's XScale3 core supports some v6 features (supersections, L2)
+ * but advertises itself as v5 as it does not support the v6 ISA.  For
+ * this reason, we need a way to explicitly test for this type of CPU.
+ */
+#ifndef CONFIG_CPU_XSC3
+#define cpu_is_xsc3()	0
+#else
+static inline int cpu_is_xsc3(void)
+{
+	if ((read_cpuid_id() & 0xffffe000) == 0x69056000)
+		return 1;
+
+	return 0;
+}
+#endif
+
+#if !defined(CONFIG_CPU_XSCALE) && !defined(CONFIG_CPU_XSC3)
+#define	cpu_is_xscale()	0
+#else
+#define	cpu_is_xscale()	1
+#endif
+
+#endif

arch/arm/include/asm/dma-mapping.h

@@ -104,15 +104,14 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
  * Dummy noncoherent implementation.  We don't provide a dma_cache_sync
  * function so drivers using this API are highlighted with build warnings.
  */
-static inline void *
-dma_alloc_noncoherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp)
+static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
+		dma_addr_t *handle, gfp_t gfp)
 {
 	return NULL;
 }
 
-static inline void
-dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
-		     dma_addr_t handle)
+static inline void dma_free_noncoherent(struct device *dev, size_t size,
+		void *cpu_addr, dma_addr_t handle)
 {
 }
 
@@ -127,8 +126,7 @@ dma_free_noncoherent(struct device *dev, size_t size, void *cpu_addr,
  * return the CPU-viewed address, and sets @handle to be the
  * device-viewed address.
  */
-extern void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp);
+extern void *dma_alloc_coherent(struct device *, size_t, dma_addr_t *, gfp_t);
 
 /**
  * dma_free_coherent - free memory allocated by dma_alloc_coherent
@@ -143,9 +141,7 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gf
  * References to memory and mappings associated with cpu_addr/handle
  * during and after this call executing are illegal.
  */
-extern void
-dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
-		  dma_addr_t handle);
+extern void dma_free_coherent(struct device *, size_t, void *, dma_addr_t);
 
 /**
  * dma_mmap_coherent - map a coherent DMA allocation into user space
@@ -159,8 +155,8 @@ dma_free_coherent(struct device *dev, size_t size, void *cpu_addr,
  * into user space.  The coherent DMA buffer must not be freed by the
  * driver until the user space mapping has been released.
  */
-int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
-		      void *cpu_addr, dma_addr_t handle, size_t size);
+int dma_mmap_coherent(struct device *, struct vm_area_struct *,
+		void *, dma_addr_t, size_t);
 
 
 /**
@@ -174,14 +170,94 @@ int dma_mmap_coherent(struct device *dev, struct vm_area_struct *vma,
  * return the CPU-viewed address, and sets @handle to be the
  * device-viewed address.
  */
-extern void *
-dma_alloc_writecombine(struct device *dev, size_t size, dma_addr_t *handle, gfp_t gfp);
+extern void *dma_alloc_writecombine(struct device *, size_t, dma_addr_t *,
+		gfp_t);
 
 #define dma_free_writecombine(dev,size,cpu_addr,handle) \
 	dma_free_coherent(dev,size,cpu_addr,handle)
 
-int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
-			  void *cpu_addr, dma_addr_t handle, size_t size);
+int dma_mmap_writecombine(struct device *, struct vm_area_struct *,
+		void *, dma_addr_t, size_t);
+
+
+#ifdef CONFIG_DMABOUNCE
+/*
+ * For SA-1111, IXP425, and ADI systems  the dma-mapping functions are "magic"
+ * and utilize bounce buffers as needed to work around limited DMA windows.
+ *
+ * On the SA-1111, a bug limits DMA to only certain regions of RAM.
+ * On the IXP425, the PCI inbound window is 64MB (256MB total RAM)
+ * On some ADI engineering systems, PCI inbound window is 32MB (12MB total RAM)
+ *
+ * The following are helper functions used by the dmabounce subystem
+ *
+ */
+
+/**
+ * dmabounce_register_dev
+ *
+ * @dev: valid struct device pointer
+ * @small_buf_size: size of buffers to use with small buffer pool
+ * @large_buf_size: size of buffers to use with large buffer pool (can be 0)
+ *
+ * This function should be called by low-level platform code to register
+ * a device as requireing DMA buffer bouncing. The function will allocate
+ * appropriate DMA pools for the device.
+ *
+ */
+extern int dmabounce_register_dev(struct device *, unsigned long,
+		unsigned long);
+
+/**
+ * dmabounce_unregister_dev
+ *
+ * @dev: valid struct device pointer
+ *
+ * This function should be called by low-level platform code when device
+ * that was previously registered with dmabounce_register_dev is removed
+ * from the system.
+ *
+ */
+extern void dmabounce_unregister_dev(struct device *);
+
+/**
+ * dma_needs_bounce
+ *
+ * @dev: valid struct device pointer
+ * @dma_handle: dma_handle of unbounced buffer
+ * @size: size of region being mapped
+ *
+ * Platforms that utilize the dmabounce mechanism must implement
+ * this function.
+ *
+ * The dmabounce routines call this function whenever a dma-mapping
+ * is requested to determine whether a given buffer needs to be bounced
+ * or not. The function must return 0 if the buffer is OK for
+ * DMA access and 1 if the buffer needs to be bounced.
+ *
+ */
+extern int dma_needs_bounce(struct device*, dma_addr_t, size_t);
+
+/*
+ * The DMA API, implemented by dmabounce.c.  See below for descriptions.
+ */
+extern dma_addr_t dma_map_single(struct device *, void *, size_t,
+		enum dma_data_direction);
+extern dma_addr_t dma_map_page(struct device *, struct page *,
+		unsigned long, size_t, enum dma_data_direction);
+extern void dma_unmap_single(struct device *, dma_addr_t, size_t,
+		enum dma_data_direction);
+
+/*
+ * Private functions
+ */
+int dmabounce_sync_for_cpu(struct device *, dma_addr_t, unsigned long,
+		size_t, enum dma_data_direction);
+int dmabounce_sync_for_device(struct device *, dma_addr_t, unsigned long,
+		size_t, enum dma_data_direction);
+#else
+#define dmabounce_sync_for_cpu(dev,dma,off,sz,dir)	(1)
+#define dmabounce_sync_for_device(dev,dma,off,sz,dir)	(1)
 
 
 /**
@@ -198,19 +274,16 @@ int dma_mmap_writecombine(struct device *dev, struct vm_area_struct *vma,
  * can regain ownership by calling dma_unmap_single() or
  * dma_sync_single_for_cpu().
  */
-#ifndef CONFIG_DMABOUNCE
-static inline dma_addr_t
-dma_map_single(struct device *dev, void *cpu_addr, size_t size,
-	       enum dma_data_direction dir)
+static inline dma_addr_t dma_map_single(struct device *dev, void *cpu_addr,
+		size_t size, enum dma_data_direction dir)
 {
+	BUG_ON(!valid_dma_direction(dir));
+
 	if (!arch_is_coherent())
 		dma_cache_maint(cpu_addr, size, dir);
 
 	return virt_to_dma(dev, cpu_addr);
 }
-#else
-extern dma_addr_t dma_map_single(struct device *,void *, size_t, enum dma_data_direction);
-#endif
 
 /**
  * dma_map_page - map a portion of a page for streaming DMA
@@ -224,23 +297,25 @@ extern dma_addr_t dma_map_single(struct device *,void *, size_t, enum dma_data_d
  * or written back.
  *
  * The device owns this memory once this call has completed.  The CPU
- * can regain ownership by calling dma_unmap_page() or
- * dma_sync_single_for_cpu().
+ * can regain ownership by calling dma_unmap_page().
  */
-static inline dma_addr_t
-dma_map_page(struct device *dev, struct page *page,
-	     unsigned long offset, size_t size,
-	     enum dma_data_direction dir)
+static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
+	     unsigned long offset, size_t size, enum dma_data_direction dir)
 {
-	return dma_map_single(dev, page_address(page) + offset, size, dir);
+	BUG_ON(!valid_dma_direction(dir));
+
+	if (!arch_is_coherent())
+		dma_cache_maint(page_address(page) + offset, size, dir);
+
+	return page_to_dma(dev, page) + offset;
 }
 
 /**
  * dma_unmap_single - unmap a single buffer previously mapped
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
  * @handle: DMA address of buffer
- * @size: size of buffer to map
- * @dir: DMA transfer direction
+ * @size: size of buffer (same as passed to dma_map_single)
+ * @dir: DMA transfer direction (same as passed to dma_map_single)
  *
  * Unmap a single streaming mode DMA translation.  The handle and size
  * must match what was provided in the previous dma_map_single() call.
@@ -249,107 +324,33 @@ dma_map_page(struct device *dev, struct page *page,
  * After this call, reads by the CPU to the buffer are guaranteed to see
  * whatever the device wrote there.
  */
-#ifndef CONFIG_DMABOUNCE
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t handle, size_t size,
-		 enum dma_data_direction dir)
+static inline void dma_unmap_single(struct device *dev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir)
 {
 	/* nothing to do */
 }
-#else
-extern void dma_unmap_single(struct device *, dma_addr_t, size_t, enum dma_data_direction);
-#endif
+#endif /* CONFIG_DMABOUNCE */
 
 /**
  * dma_unmap_page - unmap a buffer previously mapped through dma_map_page()
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
  * @handle: DMA address of buffer
- * @size: size of buffer to map
- * @dir: DMA transfer direction
+ * @size: size of buffer (same as passed to dma_map_page)
+ * @dir: DMA transfer direction (same as passed to dma_map_page)
  *
- * Unmap a single streaming mode DMA translation.  The handle and size
- * must match what was provided in the previous dma_map_single() call.
+ * Unmap a page streaming mode DMA translation.  The handle and size
+ * must match what was provided in the previous dma_map_page() call.
  * All other usages are undefined.
  *
  * After this call, reads by the CPU to the buffer are guaranteed to see
  * whatever the device wrote there.
  */
-static inline void
-dma_unmap_page(struct device *dev, dma_addr_t handle, size_t size,
-	       enum dma_data_direction dir)
+static inline void dma_unmap_page(struct device *dev, dma_addr_t handle,
+		size_t size, enum dma_data_direction dir)
 {
 	dma_unmap_single(dev, handle, size, dir);
 }
 
-/**
- * dma_map_sg - map a set of SG buffers for streaming mode DMA
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @sg: list of buffers
- * @nents: number of buffers to map
- * @dir: DMA transfer direction
- *
- * Map a set of buffers described by scatterlist in streaming
- * mode for DMA.  This is the scatter-gather version of the
- * above dma_map_single interface.  Here the scatter gather list
- * elements are each tagged with the appropriate dma address
- * and length.  They are obtained via sg_dma_{address,length}(SG).
- *
- * NOTE: An implementation may be able to use a smaller number of
- *       DMA address/length pairs than there are SG table elements.
- *       (for example via virtual mapping capabilities)
- *       The routine returns the number of addr/length pairs actually
- *       used, at most nents.
- *
- * Device ownership issues as mentioned above for dma_map_single are
- * the same here.
- */
-#ifndef CONFIG_DMABOUNCE
-static inline int
-dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
-	   enum dma_data_direction dir)
-{
-	int i;
-
-	for (i = 0; i < nents; i++, sg++) {
-		char *virt;
-
-		sg->dma_address = page_to_dma(dev, sg_page(sg)) + sg->offset;
-		virt = sg_virt(sg);
-
-		if (!arch_is_coherent())
-			dma_cache_maint(virt, sg->length, dir);
-	}
-
-	return nents;
-}
-#else
-extern int dma_map_sg(struct device *, struct scatterlist *, int, enum dma_data_direction);
-#endif
-
-/**
- * dma_unmap_sg - unmap a set of SG buffers mapped by dma_map_sg
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @sg: list of buffers
- * @nents: number of buffers to map
- * @dir: DMA transfer direction
- *
- * Unmap a set of streaming mode DMA translations.
- * Again, CPU read rules concerning calls here are the same as for
- * dma_unmap_single() above.
- */
-#ifndef CONFIG_DMABOUNCE
-static inline void
-dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
-	     enum dma_data_direction dir)
-{
-
-	/* nothing to do */
-}
-#else
-extern void dma_unmap_sg(struct device *, struct scatterlist *, int, enum dma_data_direction);
-#endif
-
-
 /**
  * dma_sync_single_range_for_cpu
  * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
@@ -368,145 +369,52 @@ extern void dma_unmap_sg(struct device *, struct scatterlist *, int, enum dma_da
  * must first the perform a dma_sync_for_device, and then the
  * device again owns the buffer.
  */
-#ifndef CONFIG_DMABOUNCE
-static inline void
-dma_sync_single_range_for_cpu(struct device *dev, dma_addr_t handle,
-			      unsigned long offset, size_t size,
-			      enum dma_data_direction dir)
+static inline void dma_sync_single_range_for_cpu(struct device *dev,
+		dma_addr_t handle, unsigned long offset, size_t size,
+		enum dma_data_direction dir)
 {
-	if (!arch_is_coherent())
-		dma_cache_maint(dma_to_virt(dev, handle) + offset, size, dir);
+	BUG_ON(!valid_dma_direction(dir));
+
+	dmabounce_sync_for_cpu(dev, handle, offset, size, dir);
 }
 
-static inline void
-dma_sync_single_range_for_device(struct device *dev, dma_addr_t handle,
-				 unsigned long offset, size_t size,
-				 enum dma_data_direction dir)
+static inline void dma_sync_single_range_for_device(struct device *dev,
+		dma_addr_t handle, unsigned long offset, size_t size,
+		enum dma_data_direction dir)
 {
+	BUG_ON(!valid_dma_direction(dir));
+
+	if (!dmabounce_sync_for_device(dev, handle, offset, size, dir))
+		return;
+
 	if (!arch_is_coherent())
 		dma_cache_maint(dma_to_virt(dev, handle) + offset, size, dir);
 }
-#else
-extern void dma_sync_single_range_for_cpu(struct device *, dma_addr_t, unsigned long, size_t, enum dma_data_direction);
-extern void dma_sync_single_range_for_device(struct device *, dma_addr_t, unsigned long, size_t, enum dma_data_direction);
-#endif
 
-static inline void
-dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle, size_t size,
-			enum dma_data_direction dir)
+static inline void dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
 	dma_sync_single_range_for_cpu(dev, handle, 0, size, dir);
 }
 
-static inline void
-dma_sync_single_for_device(struct device *dev, dma_addr_t handle, size_t size,
-			   enum dma_data_direction dir)
+static inline void dma_sync_single_for_device(struct device *dev,
+		dma_addr_t handle, size_t size, enum dma_data_direction dir)
 {
 	dma_sync_single_range_for_device(dev, handle, 0, size, dir);
 }
 
-
-/**
- * dma_sync_sg_for_cpu
- * @dev: valid struct device pointer, or NULL for ISA and EISA-like devices
- * @sg: list of buffers
- * @nents: number of buffers to map
- * @dir: DMA transfer direction
- *
- * Make physical memory consistent for a set of streaming
- * mode DMA translations after a transfer.
- *
- * The same as dma_sync_single_for_* but for a scatter-gather list,
- * same rules and usage.
- */
-#ifndef CONFIG_DMABOUNCE
-static inline void
-dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg, int nents,
-		    enum dma_data_direction dir)
-{
-	int i;
-
-	for (i = 0; i < nents; i++, sg++) {
-		char *virt = sg_virt(sg);
-		if (!arch_is_coherent())
-			dma_cache_maint(virt, sg->length, dir);
-	}
-}
-
-static inline void
-dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg, int nents,
-		       enum dma_data_direction dir)
-{
-	int i;
-
-	for (i = 0; i < nents; i++, sg++) {
-		char *virt = sg_virt(sg);
-		if (!arch_is_coherent())
-			dma_cache_maint(virt, sg->length, dir);
-	}
-}
-#else
-extern void dma_sync_sg_for_cpu(struct device*, struct scatterlist*, int, enum dma_data_direction);
-extern void dma_sync_sg_for_device(struct device*, struct scatterlist*, int, enum dma_data_direction);
-#endif
-
-#ifdef CONFIG_DMABOUNCE
 /*
- * For SA-1111, IXP425, and ADI systems  the dma-mapping functions are "magic"
- * and utilize bounce buffers as needed to work around limited DMA windows.
- *
- * On the SA-1111, a bug limits DMA to only certain regions of RAM.
- * On the IXP425, the PCI inbound window is 64MB (256MB total RAM)
- * On some ADI engineering systems, PCI inbound window is 32MB (12MB total RAM)
- *
- * The following are helper functions used by the dmabounce subystem
- *
- */
-
-/**
- * dmabounce_register_dev
- *
- * @dev: valid struct device pointer
- * @small_buf_size: size of buffers to use with small buffer pool
- * @large_buf_size: size of buffers to use with large buffer pool (can be 0)
- *
- * This function should be called by low-level platform code to register
- * a device as requireing DMA buffer bouncing. The function will allocate
- * appropriate DMA pools for the device.
- *
- */
-extern int dmabounce_register_dev(struct device *, unsigned long, unsigned long);
-
-/**
- * dmabounce_unregister_dev
- *
- * @dev: valid struct device pointer
- *
- * This function should be called by low-level platform code when device
- * that was previously registered with dmabounce_register_dev is removed
- * from the system.
- *
+ * The scatter list versions of the above methods.
  */
-extern void dmabounce_unregister_dev(struct device *);
+extern int dma_map_sg(struct device *, struct scatterlist *, int,
+		enum dma_data_direction);
+extern void dma_unmap_sg(struct device *, struct scatterlist *, int,
+		enum dma_data_direction);
+extern void dma_sync_sg_for_cpu(struct device *, struct scatterlist *, int,
+		enum dma_data_direction);
+extern void dma_sync_sg_for_device(struct device *, struct scatterlist *, int,
+		enum dma_data_direction);
 
-/**
- * dma_needs_bounce
- *
- * @dev: valid struct device pointer
- * @dma_handle: dma_handle of unbounced buffer
- * @size: size of region being mapped
- *
- * Platforms that utilize the dmabounce mechanism must implement
- * this function.
- *
- * The dmabounce routines call this function whenever a dma-mapping
- * is requested to determine whether a given buffer needs to be bounced
- * or not. The function must return 0 if the buffer is OK for
- * DMA access and 1 if the buffer needs to be bounced.
- *
- */
-extern int dma_needs_bounce(struct device*, dma_addr_t, size_t);
-#endif /* CONFIG_DMABOUNCE */
 
 #endif /* __KERNEL__ */
 #endif

arch/arm/include/asm/futex.h

@@ -1,6 +1,124 @@
-#ifndef _ASM_FUTEX_H
-#define _ASM_FUTEX_H
+#ifndef _ASM_ARM_FUTEX_H
+#define _ASM_ARM_FUTEX_H
+
+#ifdef __KERNEL__
+
+#ifdef CONFIG_SMP
 
 #include <asm-generic/futex.h>
 
-#endif
+#else /* !SMP, we can work around lack of atomic ops by disabling preemption */
+
+#include <linux/futex.h>
+#include <linux/preempt.h>
+#include <linux/uaccess.h>
+#include <asm/errno.h>
+
+#define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
+	__asm__ __volatile__(					\
+	"1:	ldrt	%1, [%2]\n"				\
+	"	" insn "\n"					\
+	"2:	strt	%0, [%2]\n"				\
+	"	mov	%0, #0\n"				\
+	"3:\n"							\
+	"	.section __ex_table,\"a\"\n"			\
+	"	.align	3\n"					\
+	"	.long	1b, 4f, 2b, 4f\n"			\
+	"	.previous\n"					\
+	"	.section .fixup,\"ax\"\n"			\
+	"4:	mov	%0, %4\n"				\
+	"	b	3b\n"					\
+	"	.previous"					\
+	: "=&r" (ret), "=&r" (oldval)				\
+	: "r" (uaddr), "r" (oparg), "Ir" (-EFAULT)		\
+	: "cc", "memory")
+
+static inline int
+futex_atomic_op_inuser (int encoded_op, int __user *uaddr)
+{
+	int op = (encoded_op >> 28) & 7;
+	int cmp = (encoded_op >> 24) & 15;
+	int oparg = (encoded_op << 8) >> 20;
+	int cmparg = (encoded_op << 20) >> 20;
+	int oldval = 0, ret;
+
+	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
+		oparg = 1 << oparg;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+		return -EFAULT;
+
+	pagefault_disable();	/* implies preempt_disable() */
+
+	switch (op) {
+	case FUTEX_OP_SET:
+		__futex_atomic_op("mov	%0, %3", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ADD:
+		__futex_atomic_op("add	%0, %1, %3", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_OR:
+		__futex_atomic_op("orr	%0, %1, %3", ret, oldval, uaddr, oparg);
+		break;
+	case FUTEX_OP_ANDN:
+		__futex_atomic_op("and	%0, %1, %3", ret, oldval, uaddr, ~oparg);
+		break;
+	case FUTEX_OP_XOR:
+		__futex_atomic_op("eor	%0, %1, %3", ret, oldval, uaddr, oparg);
+		break;
+	default:
+		ret = -ENOSYS;
+	}
+
+	pagefault_enable();	/* subsumes preempt_enable() */
+
+	if (!ret) {
+		switch (cmp) {
+		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
+		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
+		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
+		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
+		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
+		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
+		default: ret = -ENOSYS;
+		}
+	}
+	return ret;
+}
+
+static inline int
+futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
+{
+	int val;
+
+	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(int)))
+		return -EFAULT;
+
+	pagefault_disable();	/* implies preempt_disable() */
+
+	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
+	"1:	ldrt	%0, [%3]\n"
+	"	teq	%0, %1\n"
+	"2:	streqt	%2, [%3]\n"
+	"3:\n"
+	"	.section __ex_table,\"a\"\n"
+	"	.align	3\n"
+	"	.long	1b, 4f, 2b, 4f\n"
+	"	.previous\n"
+	"	.section .fixup,\"ax\"\n"
+	"4:	mov	%0, %4\n"
+	"	b	3b\n"
+	"	.previous"
+	: "=&r" (val)
+	: "r" (oldval), "r" (newval), "r" (uaddr), "Ir" (-EFAULT)
+	: "cc", "memory");
+
+	pagefault_enable();	/* subsumes preempt_enable() */
+
+	return val;
+}
+
+#endif /* !SMP */
+
+#endif /* __KERNEL__ */
+#endif /* _ASM_ARM_FUTEX_H */

arch/arm/include/asm/irq.h

@@ -22,6 +22,10 @@
 #ifndef __ASSEMBLY__
 struct irqaction;
 extern void migrate_irqs(void);
+
+extern void asm_do_IRQ(unsigned int, struct pt_regs *);
+void init_IRQ(void);
+
 #endif
 
 #endif

arch/arm/include/asm/kprobes.h

@@ -61,7 +61,6 @@ struct kprobe_ctlblk {
 void arch_remove_kprobe(struct kprobe *);
 void kretprobe_trampoline(void);
 
-int kprobe_trap_handler(struct pt_regs *regs, unsigned int instr);
 int kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr);
 int kprobe_exceptions_notify(struct notifier_block *self,
 			     unsigned long val, void *data);

arch/arm/include/asm/mc146818rtc.h

@@ -4,8 +4,8 @@
 #ifndef _ASM_MC146818RTC_H
 #define _ASM_MC146818RTC_H
 
+#include <linux/io.h>
 #include <mach/irqs.h>
-#include <asm/io.h>
 
 #ifndef RTC_PORT
 #define RTC_PORT(x)	(0x70 + (x))

arch/arm/include/asm/memory.h

@@ -13,43 +13,33 @@
 #ifndef __ASM_ARM_MEMORY_H
 #define __ASM_ARM_MEMORY_H
 
+#include <linux/compiler.h>
+#include <linux/const.h>
+#include <mach/memory.h>
+#include <asm/sizes.h>
+
 /*
  * Allow for constants defined here to be used from assembly code
  * by prepending the UL suffix only with actual C code compilation.
  */
-#ifndef __ASSEMBLY__
-#define UL(x) (x##UL)
-#else
-#define UL(x) (x)
-#endif
-
-#include <linux/compiler.h>
-#include <mach/memory.h>
-#include <asm/sizes.h>
+#define UL(x) _AC(x, UL)
 
 #ifdef CONFIG_MMU
 
-#ifndef TASK_SIZE
 /*
+ * PAGE_OFFSET - the virtual address of the start of the kernel image
  * TASK_SIZE - the maximum size of a user space task.
  * TASK_UNMAPPED_BASE - the lower boundary of the mmap VM area
  */
-#define TASK_SIZE		UL(0xbf000000)
-#define TASK_UNMAPPED_BASE	UL(0x40000000)
-#endif
+#define PAGE_OFFSET		UL(CONFIG_PAGE_OFFSET)
+#define TASK_SIZE		(UL(CONFIG_PAGE_OFFSET) - UL(0x01000000))
+#define TASK_UNMAPPED_BASE	(UL(CONFIG_PAGE_OFFSET) / 3)
 
 /*
  * The maximum size of a 26-bit user space task.
  */
 #define TASK_SIZE_26		UL(0x04000000)
 
-/*
- * Page offset: 3GB
- */
-#ifndef PAGE_OFFSET
-#define PAGE_OFFSET		UL(0xc0000000)
-#endif
-
 /*
  * The module space lives between the addresses given by TASK_SIZE
  * and PAGE_OFFSET - it must be within 32MB of the kernel text.
@@ -147,16 +137,10 @@
 
 #ifndef arch_adjust_zones
 #define arch_adjust_zones(node,size,holes) do { } while (0)
+#elif !defined(CONFIG_ZONE_DMA)
+#error "custom arch_adjust_zones() requires CONFIG_ZONE_DMA"
 #endif
 
-/*
- * Amount of memory reserved for the vmalloc() area, and minimum
- * address for vmalloc mappings.
- */
-extern unsigned long vmalloc_reserve;
-
-#define VMALLOC_MIN		(void *)(VMALLOC_END - vmalloc_reserve)
-
 /*
  * PFNs are used to describe any physical page; this means
  * PFN 0 == physical address 0.

arch/arm/include/asm/mmu_context.h

@@ -15,6 +15,7 @@
 
 #include <linux/compiler.h>
 #include <asm/cacheflush.h>
+#include <asm/cachetype.h>
 #include <asm/proc-fns.h>
 #include <asm-generic/mm_hooks.h>
 

arch/arm/include/asm/pgtable.h

@@ -319,11 +319,6 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 
 #define pmd_page(pmd) virt_to_page(__va(pmd_val(pmd)))
 
-/*
- * Permanent address of a page. We never have highmem, so this is trivial.
- */
-#define pages_to_mb(x)		((x) >> (20 - PAGE_SHIFT))
-
 /*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.

arch/arm/include/asm/ptrace.h

@@ -54,7 +54,6 @@
 #define PSR_C_BIT	0x20000000
 #define PSR_Z_BIT	0x40000000
 #define PSR_N_BIT	0x80000000
-#define PCMASK		0
 
 /*
  * Groups of PSR bits
@@ -139,11 +138,7 @@ static inline int valid_user_regs(struct pt_regs *regs)
 	return 0;
 }
 
-#define pc_pointer(v) \
-	((v) & ~PCMASK)
-
-#define instruction_pointer(regs) \
-	(pc_pointer((regs)->ARM_pc))
+#define instruction_pointer(regs)	(regs)->ARM_pc
 
 #ifdef CONFIG_SMP
 extern unsigned long profile_pc(struct pt_regs *regs);

arch/arm/include/asm/setup.h

@@ -209,6 +209,17 @@ struct meminfo {
 	struct membank bank[NR_BANKS];
 };
 
+#define for_each_nodebank(iter,mi,no)			\
+	for (iter = 0; iter < mi->nr_banks; iter++)	\
+		if (mi->bank[iter].node == no)
+
+#define bank_pfn_start(bank)	__phys_to_pfn((bank)->start)
+#define bank_pfn_end(bank)	__phys_to_pfn((bank)->start + (bank)->size)
+#define bank_pfn_size(bank)	((bank)->size >> PAGE_SHIFT)
+#define bank_phys_start(bank)	(bank)->start
+#define bank_phys_end(bank)	((bank)->start + (bank)->size)
+#define bank_phys_size(bank)	(bank)->size
+
 /*
  * Early command line parameters.
  */

arch/arm/include/asm/sparsemem.h

@@ -3,8 +3,22 @@
 
 #include <asm/memory.h>
 
-#define MAX_PHYSADDR_BITS	32
-#define MAX_PHYSMEM_BITS	32
-#define SECTION_SIZE_BITS	NODE_MEM_SIZE_BITS
+/*
+ * Two definitions are required for sparsemem:
+ *
+ * MAX_PHYSMEM_BITS: The number of physical address bits required
+ *   to address the last byte of memory.
+ *
+ * SECTION_SIZE_BITS: The number of physical address bits to cover
+ *   the maximum amount of memory in a section.
+ *
+ * Eg, if you have 2 banks of up to 64MB at 0x80000000, 0x84000000,
+ * then MAX_PHYSMEM_BITS is 32, SECTION_SIZE_BITS is 26.
+ *
+ * Define these in your mach/memory.h.
+ */
+#if !defined(SECTION_SIZE_BITS) || !defined(MAX_PHYSMEM_BITS)
+#error Sparsemem is not supported on this platform
+#endif
 
 #endif

arch/arm/include/asm/system.h

@@ -43,11 +43,6 @@
 #define CR_XP	(1 << 23)	/* Extended page tables			*/
 #define CR_VE	(1 << 24)	/* Vectored interrupts			*/
 
-#define CPUID_ID	0
-#define CPUID_CACHETYPE	1
-#define CPUID_TCM	2
-#define CPUID_TLBTYPE	3
-
 /*
  * This is used to ensure the compiler did actually allocate the register we
  * asked it for some inline assembly sequences.  Apparently we can't trust
@@ -61,36 +56,8 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/linkage.h>
-#include <linux/stringify.h>
 #include <linux/irqflags.h>
 
-#ifdef CONFIG_CPU_CP15
-#define read_cpuid(reg)							\
-	({								\
-		unsigned int __val;					\
-		asm("mrc	p15, 0, %0, c0, c0, " __stringify(reg)	\
-		    : "=r" (__val)					\
-		    :							\
-		    : "cc");						\
-		__val;							\
-	})
-#else
-extern unsigned int processor_id;
-#define read_cpuid(reg) (processor_id)
-#endif
-
-/*
- * The CPU ID never changes at run time, so we might as well tell the
- * compiler that it's constant.  Use this function to read the CPU ID
- * rather than directly reading processor_id or read_cpuid() directly.
- */
-static inline unsigned int read_cpuid_id(void) __attribute_const__;
-
-static inline unsigned int read_cpuid_id(void)
-{
-	return read_cpuid(CPUID_ID);
-}
-
 #define __exception	__attribute__((section(".exception.text")))
 
 struct thread_info;
@@ -131,31 +98,6 @@ extern void cpu_init(void);
 void arm_machine_restart(char mode);
 extern void (*arm_pm_restart)(char str);
 
-/*
- * Intel's XScale3 core supports some v6 features (supersections, L2)
- * but advertises itself as v5 as it does not support the v6 ISA.  For
- * this reason, we need a way to explicitly test for this type of CPU.
- */
-#ifndef CONFIG_CPU_XSC3
-#define cpu_is_xsc3()	0
-#else
-static inline int cpu_is_xsc3(void)
-{
-	extern unsigned int processor_id;
-
-	if ((processor_id & 0xffffe000) == 0x69056000)
-		return 1;
-
-	return 0;
-}
-#endif
-
-#if !defined(CONFIG_CPU_XSCALE) && !defined(CONFIG_CPU_XSC3)
-#define	cpu_is_xscale()	0
-#else
-#define	cpu_is_xscale()	1
-#endif
-
 #define UDBG_UNDEFINED	(1 << 0)
 #define UDBG_SYSCALL	(1 << 1)
 #define UDBG_BADABORT	(1 << 2)

arch/arm/include/asm/thread_info.h

@@ -98,7 +98,7 @@ static inline struct thread_info *current_thread_info(void)
 }
 
 #define thread_saved_pc(tsk)	\
-	((unsigned long)(pc_pointer(task_thread_info(tsk)->cpu_context.pc)))
+	((unsigned long)(task_thread_info(tsk)->cpu_context.pc))
 #define thread_saved_fp(tsk)	\
 	((unsigned long)(task_thread_info(tsk)->cpu_context.fp))
 

arch/arm/include/asm/uaccess.h

@@ -225,7 +225,7 @@ do {									\
 
 #define __get_user_asm_byte(x,addr,err)				\
 	__asm__ __volatile__(					\
-	"1:	ldrbt	%1,[%2],#0\n"				\
+	"1:	ldrbt	%1,[%2]\n"				\
 	"2:\n"							\
 	"	.section .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -261,7 +261,7 @@ do {									\
 
 #define __get_user_asm_word(x,addr,err)				\
 	__asm__ __volatile__(					\
-	"1:	ldrt	%1,[%2],#0\n"				\
+	"1:	ldrt	%1,[%2]\n"				\
 	"2:\n"							\
 	"	.section .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -306,7 +306,7 @@ do {									\
 
 #define __put_user_asm_byte(x,__pu_addr,err)			\
 	__asm__ __volatile__(					\
-	"1:	strbt	%1,[%2],#0\n"				\
+	"1:	strbt	%1,[%2]\n"				\
 	"2:\n"							\
 	"	.section .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -339,7 +339,7 @@ do {									\
 
 #define __put_user_asm_word(x,__pu_addr,err)			\
 	__asm__ __volatile__(					\
-	"1:	strt	%1,[%2],#0\n"				\
+	"1:	strt	%1,[%2]\n"				\
 	"2:\n"							\
 	"	.section .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -365,7 +365,7 @@ do {									\
 #define __put_user_asm_dword(x,__pu_addr,err)			\
 	__asm__ __volatile__(					\
 	"1:	strt	" __reg_oper1 ", [%1], #4\n"		\
-	"2:	strt	" __reg_oper0 ", [%1], #0\n"		\
+	"2:	strt	" __reg_oper0 ", [%1]\n"		\
 	"3:\n"							\
 	"	.section .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\

arch/arm/include/asm/vga.h

@@ -1,8 +1,8 @@
 #ifndef ASMARM_VGA_H
 #define ASMARM_VGA_H
 
+#include <linux/io.h>
 #include <mach/hardware.h>
-#include <asm/io.h>
 
 #define VGA_MAP_MEM(x,s)	(PCIMEM_BASE + (x))
 

arch/arm/kernel/armksyms.c

@@ -13,11 +13,11 @@
 #include <linux/delay.h>
 #include <linux/in6.h>
 #include <linux/syscalls.h>
+#include <linux/uaccess.h>
+#include <linux/io.h>
 
 #include <asm/checksum.h>
-#include <asm/io.h>
 #include <asm/system.h>
-#include <asm/uaccess.h>
 #include <asm/ftrace.h>
 
 /*

arch/arm/kernel/bios32.c

@@ -10,8 +10,8 @@
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/init.h>
+#include <linux/io.h>
 
-#include <asm/io.h>
 #include <asm/mach-types.h>
 #include <asm/mach/pci.h>
 

arch/arm/kernel/crunch.c

@@ -15,9 +15,9 @@
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/init.h>
+#include <linux/io.h>
 #include <mach/ep93xx-regs.h>
 #include <asm/thread_notify.h>
-#include <asm/io.h>
 
 struct crunch_state *crunch_owner;
 

arch/arm/kernel/debug.S

@@ -89,10 +89,12 @@
 ENTRY(printhex8)
 		mov	r1, #8
 		b	printhex
+ENDPROC(printhex8)
 
 ENTRY(printhex4)
 		mov	r1, #4
 		b	printhex
+ENDPROC(printhex4)
 
 ENTRY(printhex2)
 		mov	r1, #2
@@ -110,6 +112,7 @@ printhex:	adr	r2, hexbuf
 		bne	1b
 		mov	r0, r2
 		b	printascii
+ENDPROC(printhex2)
 
 		.ltorg
 
@@ -127,11 +130,13 @@ ENTRY(printascii)
 		teqne	r1, #0
 		bne	1b
 		mov	pc, lr
+ENDPROC(printascii)
 
 ENTRY(printch)
 		addruart r3
 		mov	r1, r0
 		mov	r0, #0
 		b	1b
+ENDPROC(printch)
 
 hexbuf:		.space 16

arch/arm/kernel/dma-isa.c

@@ -19,10 +19,9 @@
 #include <linux/ioport.h>
 #include <linux/init.h>
 #include <linux/dma-mapping.h>
+#include <linux/io.h>
 
 #include <asm/dma.h>
-#include <asm/io.h>
-
 #include <asm/mach/dma.h>
 
 #define ISA_DMA_MODE_READ	0x44

arch/arm/kernel/entry-armv.S

@@ -76,14 +76,17 @@
 __pabt_invalid:
 	inv_entry BAD_PREFETCH
 	b	common_invalid
+ENDPROC(__pabt_invalid)
 
 __dabt_invalid:
 	inv_entry BAD_DATA
 	b	common_invalid
+ENDPROC(__dabt_invalid)
 
 __irq_invalid:
 	inv_entry BAD_IRQ
 	b	common_invalid
+ENDPROC(__irq_invalid)
 
 __und_invalid:
 	inv_entry BAD_UNDEFINSTR
@@ -107,6 +110,7 @@ common_invalid:
 
 	mov	r0, sp
 	b	bad_mode
+ENDPROC(__und_invalid)
 
 /*
  * SVC mode handlers
@@ -192,6 +196,7 @@ __dabt_svc:
 	ldr	r0, [sp, #S_PSR]
 	msr	spsr_cxsf, r0
 	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+ENDPROC(__dabt_svc)
 
 	.align	5
 __irq_svc:
@@ -223,6 +228,7 @@ __irq_svc:
 	bleq	trace_hardirqs_on
 #endif
 	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+ENDPROC(__irq_svc)
 
 	.ltorg
 
@@ -272,6 +278,7 @@ __und_svc:
 	ldr	lr, [sp, #S_PSR]		@ Get SVC cpsr
 	msr	spsr_cxsf, lr
 	ldmia	sp, {r0 - pc}^			@ Restore SVC registers
+ENDPROC(__und_svc)
 
 	.align	5
 __pabt_svc:
@@ -313,6 +320,7 @@ __pabt_svc:
 	ldr	r0, [sp, #S_PSR]
 	msr	spsr_cxsf, r0
 	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+ENDPROC(__pabt_svc)
 
 	.align	5
 .LCcralign:
@@ -412,6 +420,7 @@ __dabt_usr:
 	mov	r2, sp
 	adr	lr, ret_from_exception
 	b	do_DataAbort
+ENDPROC(__dabt_usr)
 
 	.align	5
 __irq_usr:
@@ -441,6 +450,7 @@ __irq_usr:
 
 	mov	why, #0
 	b	ret_to_user
+ENDPROC(__irq_usr)
 
 	.ltorg
 
@@ -474,6 +484,7 @@ __und_usr:
 #else
 	b	__und_usr_unknown
 #endif
+ENDPROC(__und_usr)
 
 	@
 	@ fallthrough to call_fpe
@@ -642,6 +653,7 @@ __und_usr_unknown:
 	mov	r0, sp
 	adr	lr, ret_from_exception
 	b	do_undefinstr
+ENDPROC(__und_usr_unknown)
 
 	.align	5
 __pabt_usr:
@@ -666,6 +678,8 @@ ENTRY(ret_from_exception)
 	get_thread_info tsk
 	mov	why, #0
 	b	ret_to_user
+ENDPROC(__pabt_usr)
+ENDPROC(ret_from_exception)
 
 /*
  * Register switch for ARMv3 and ARMv4 processors
@@ -702,6 +716,7 @@ ENTRY(__switch_to)
 	bl	atomic_notifier_call_chain
 	mov	r0, r5
 	ldmia	r4, {r4 - sl, fp, sp, pc}	@ Load all regs saved previously
+ENDPROC(__switch_to)
 
 	__INIT
 
@@ -1029,6 +1044,7 @@ vector_\name:
 	mov	r0, sp
 	ldr	lr, [pc, lr, lsl #2]
 	movs	pc, lr			@ branch to handler in SVC mode
+ENDPROC(vector_\name)
 	.endm
 
 	.globl	__stubs_start

arch/arm/kernel/entry-common.S

@@ -77,6 +77,7 @@ no_work_pending:
 	mov	r0, r0
 	add	sp, sp, #S_FRAME_SIZE - S_PC
 	movs	pc, lr				@ return & move spsr_svc into cpsr
+ENDPROC(ret_to_user)
 
 /*
  * This is how we return from a fork.
@@ -92,7 +93,7 @@ ENTRY(ret_from_fork)
 	mov	r0, #1				@ trace exit [IP = 1]
 	bl	syscall_trace
 	b	ret_slow_syscall
-	
+ENDPROC(ret_from_fork)
 
 	.equ NR_syscalls,0
 #define CALL(x) .equ NR_syscalls,NR_syscalls+1
@@ -269,6 +270,7 @@ ENTRY(vector_swi)
 	eor	r0, scno, #__NR_SYSCALL_BASE	@ put OS number back
 	bcs	arm_syscall	
 	b	sys_ni_syscall			@ not private func
+ENDPROC(vector_swi)
 
 	/*
 	 * This is the really slow path.  We're going to be doing
@@ -326,7 +328,6 @@ ENTRY(sys_call_table)
  */
 @ r0 = syscall number
 @ r8 = syscall table
-		.type	sys_syscall, #function
 sys_syscall:
 		bic	scno, r0, #__NR_OABI_SYSCALL_BASE
 		cmp	scno, #__NR_syscall - __NR_SYSCALL_BASE
@@ -338,53 +339,65 @@ sys_syscall:
 		movlo	r3, r4
 		ldrlo	pc, [tbl, scno, lsl #2]
 		b	sys_ni_syscall
+ENDPROC(sys_syscall)
 
 sys_fork_wrapper:
 		add	r0, sp, #S_OFF
 		b	sys_fork
+ENDPROC(sys_fork_wrapper)
 
 sys_vfork_wrapper:
 		add	r0, sp, #S_OFF
 		b	sys_vfork
+ENDPROC(sys_vfork_wrapper)
 
 sys_execve_wrapper:
 		add	r3, sp, #S_OFF
 		b	sys_execve
+ENDPROC(sys_execve_wrapper)
 
 sys_clone_wrapper:
 		add	ip, sp, #S_OFF
 		str	ip, [sp, #4]
 		b	sys_clone
+ENDPROC(sys_clone_wrapper)
 
 sys_sigsuspend_wrapper:
 		add	r3, sp, #S_OFF
 		b	sys_sigsuspend
+ENDPROC(sys_sigsuspend_wrapper)
 
 sys_rt_sigsuspend_wrapper:
 		add	r2, sp, #S_OFF
 		b	sys_rt_sigsuspend
+ENDPROC(sys_rt_sigsuspend_wrapper)
 
 sys_sigreturn_wrapper:
 		add	r0, sp, #S_OFF
 		b	sys_sigreturn
+ENDPROC(sys_sigreturn_wrapper)
 
 sys_rt_sigreturn_wrapper:
 		add	r0, sp, #S_OFF
 		b	sys_rt_sigreturn
+ENDPROC(sys_rt_sigreturn_wrapper)
 
 sys_sigaltstack_wrapper:
 		ldr	r2, [sp, #S_OFF + S_SP]
 		b	do_sigaltstack
+ENDPROC(sys_sigaltstack_wrapper)
 
 sys_statfs64_wrapper:
 		teq	r1, #88
 		moveq	r1, #84
 		b	sys_statfs64
+ENDPROC(sys_statfs64_wrapper)
 
 sys_fstatfs64_wrapper:
 		teq	r1, #88
 		moveq	r1, #84
 		b	sys_fstatfs64
+ENDPROC(sys_fstatfs64_wrapper)
 
 /*
  * Note: off_4k (r5) is always units of 4K.  If we can't do the requested
@@ -402,11 +415,14 @@ sys_mmap2:
 		str	r5, [sp, #4]
 		b	do_mmap2
 #endif
+ENDPROC(sys_mmap2)
 
 ENTRY(pabort_ifar)
 		mrc	p15, 0, r0, cr6, cr0, 2
 ENTRY(pabort_noifar)
 		mov	pc, lr
+ENDPROC(pabort_ifar)
+ENDPROC(pabort_noifar)
 
 #ifdef CONFIG_OABI_COMPAT
 
@@ -417,26 +433,31 @@ ENTRY(pabort_noifar)
 sys_oabi_pread64:
 		stmia	sp, {r3, r4}
 		b	sys_pread64
+ENDPROC(sys_oabi_pread64)
 
 sys_oabi_pwrite64:
 		stmia	sp, {r3, r4}
 		b	sys_pwrite64
+ENDPROC(sys_oabi_pwrite64)
 
 sys_oabi_truncate64:
 		mov	r3, r2
 		mov	r2, r1
 		b	sys_truncate64
+ENDPROC(sys_oabi_truncate64)
 
 sys_oabi_ftruncate64:
 		mov	r3, r2
 		mov	r2, r1
 		b	sys_ftruncate64
+ENDPROC(sys_oabi_ftruncate64)
 
 sys_oabi_readahead:
 		str	r3, [sp]
 		mov	r3, r2
 		mov	r2, r1
 		b	sys_readahead
+ENDPROC(sys_oabi_readahead)
 
 /*
  * Let's declare a second syscall table for old ABI binaries

arch/arm/kernel/fiq.c

@@ -45,7 +45,6 @@
 #include <asm/fiq.h>
 #include <asm/irq.h>
 #include <asm/system.h>
-#include <asm/uaccess.h>
 
 static unsigned long no_fiq_insn;
 

arch/arm/kernel/head-common.S

@@ -36,7 +36,6 @@ __switch_data:
  *  r2  = atags pointer
  *  r9  = processor ID
  */
-	.type	__mmap_switched, %function
 __mmap_switched:
 	adr	r3, __switch_data + 4
 
@@ -59,6 +58,7 @@ __mmap_switched:
 	bic	r4, r0, #CR_A			@ Clear 'A' bit
 	stmia	r7, {r0, r4}			@ Save control register values
 	b	start_kernel
+ENDPROC(__mmap_switched)
 
 /*
  * Exception handling.  Something went wrong and we can't proceed.  We
@@ -69,8 +69,6 @@ __mmap_switched:
  * and hope for the best (useful if bootloader fails to pass a proper
  * machine ID for example).
  */
-
-	.type	__error_p, %function
 __error_p:
 #ifdef CONFIG_DEBUG_LL
 	adr	r0, str_p1
@@ -84,8 +82,8 @@ str_p1:	.asciz	"\nError: unrecognized/unsupported processor variant (0x"
 str_p2:	.asciz	").\n"
 	.align
 #endif
+ENDPROC(__error_p)
 
-	.type	__error_a, %function
 __error_a:
 #ifdef CONFIG_DEBUG_LL
 	mov	r4, r1				@ preserve machine ID
@@ -115,13 +113,14 @@ __error_a:
 	adr	r0, str_a3
 	bl	printascii
 	b	__error
+ENDPROC(__error_a)
+
 str_a1:	.asciz	"\nError: unrecognized/unsupported machine ID (r1 = 0x"
 str_a2:	.asciz	").\n\nAvailable machine support:\n\nID (hex)\tNAME\n"
 str_a3:	.asciz	"\nPlease check your kernel config and/or bootloader.\n"
 	.align
 #endif
 
-	.type	__error, %function
 __error:
 #ifdef CONFIG_ARCH_RPC
 /*
@@ -138,6 +137,7 @@ __error:
 #endif
 1:	mov	r0, r0
 	b	1b
+ENDPROC(__error)
 
 
 /*
@@ -153,7 +153,6 @@ __error:
  *	r5 = proc_info pointer in physical address space
  *	r9 = cpuid (preserved)
  */
-	.type	__lookup_processor_type, %function
 __lookup_processor_type:
 	adr	r3, 3f
 	ldmda	r3, {r5 - r7}
@@ -169,6 +168,7 @@ __lookup_processor_type:
 	blo	1b
 	mov	r5, #0				@ unknown processor
 2:	mov	pc, lr
+ENDPROC(__lookup_processor_type)
 
 /*
  * This provides a C-API version of the above function.
@@ -179,6 +179,7 @@ ENTRY(lookup_processor_type)
 	bl	__lookup_processor_type
 	mov	r0, r5
 	ldmfd	sp!, {r4 - r7, r9, pc}
+ENDPROC(lookup_processor_type)
 
 /*
  * Look in <asm/procinfo.h> and arch/arm/kernel/arch.[ch] for
@@ -201,7 +202,6 @@ ENTRY(lookup_processor_type)
  *  r3, r4, r6 corrupted
  *  r5 = mach_info pointer in physical address space
  */
-	.type	__lookup_machine_type, %function
 __lookup_machine_type:
 	adr	r3, 3b
 	ldmia	r3, {r4, r5, r6}
@@ -216,6 +216,7 @@ __lookup_machine_type:
 	blo	1b
 	mov	r5, #0				@ unknown machine
 2:	mov	pc, lr
+ENDPROC(__lookup_machine_type)
 
 /*
  * This provides a C-API version of the above function.
@@ -226,6 +227,7 @@ ENTRY(lookup_machine_type)
 	bl	__lookup_machine_type
 	mov	r0, r5
 	ldmfd	sp!, {r4 - r6, pc}
+ENDPROC(lookup_machine_type)
 
 /* Determine validity of the r2 atags pointer.  The heuristic requires
  * that the pointer be aligned, in the first 16k of physical RAM and
@@ -239,8 +241,6 @@ ENTRY(lookup_machine_type)
  *  r2 either valid atags pointer, or zero
  *  r5, r6 corrupted
  */
-
-	.type	__vet_atags, %function
 __vet_atags:
 	tst	r2, #0x3			@ aligned?
 	bne	1f
@@ -257,3 +257,4 @@ __vet_atags:
 
 1:	mov	r2, #0
 	mov	pc, lr
+ENDPROC(__vet_atags)

arch/arm/kernel/head-nommu.S

@@ -33,7 +33,6 @@
  *
  */
 	.section ".text.head", "ax"
-	.type	stext, %function
 ENTRY(stext)
 	msr	cpsr_c, #PSR_F_BIT | PSR_I_BIT | SVC_MODE @ ensure svc mode
 						@ and irqs disabled
@@ -53,11 +52,11 @@ ENTRY(stext)
 						@ the initialization is done
 	adr	lr, __after_proc_init		@ return (PIC) address
 	add	pc, r10, #PROCINFO_INITFUNC
+ENDPROC(stext)
 
 /*
  * Set the Control Register and Read the process ID.
  */
-	.type	__after_proc_init, %function
 __after_proc_init:
 #ifdef CONFIG_CPU_CP15
 	mrc	p15, 0, r0, c1, c0, 0		@ read control reg
@@ -85,6 +84,7 @@ __after_proc_init:
 
 	mov	pc, r13				@ clear the BSS and jump
 						@ to start_kernel
+ENDPROC(__after_proc_init)
 	.ltorg
 
 #include "head-common.S"

arch/arm/kernel/head.S

@@ -75,7 +75,6 @@
  * circumstances, zImage) is for.
  */
 	.section ".text.head", "ax"
-	.type	stext, %function
 ENTRY(stext)
 	msr	cpsr_c, #PSR_F_BIT | PSR_I_BIT | SVC_MODE @ ensure svc mode
 						@ and irqs disabled
@@ -100,9 +99,9 @@ ENTRY(stext)
 						@ mmu has been enabled
 	adr	lr, __enable_mmu		@ return (PIC) address
 	add	pc, r10, #PROCINFO_INITFUNC
+ENDPROC(stext)
 
 #if defined(CONFIG_SMP)
-	.type   secondary_startup, #function
 ENTRY(secondary_startup)
 	/*
 	 * Common entry point for secondary CPUs.
@@ -128,6 +127,7 @@ ENTRY(secondary_startup)
 	adr	lr, __enable_mmu		@ return address
 	add	pc, r10, #PROCINFO_INITFUNC	@ initialise processor
 						@ (return control reg)
+ENDPROC(secondary_startup)
 
 	/*
 	 * r6  = &secondary_data
@@ -136,6 +136,7 @@ ENTRY(__secondary_switched)
 	ldr	sp, [r7, #4]			@ get secondary_data.stack
 	mov	fp, #0
 	b	secondary_start_kernel
+ENDPROC(__secondary_switched)
 
 	.type	__secondary_data, %object
 __secondary_data:
@@ -151,7 +152,6 @@ __secondary_data:
  * this is just loading the page table pointer and domain access
  * registers.
  */
-	.type	__enable_mmu, %function
 __enable_mmu:
 #ifdef CONFIG_ALIGNMENT_TRAP
 	orr	r0, r0, #CR_A
@@ -174,6 +174,7 @@ __enable_mmu:
 	mcr	p15, 0, r5, c3, c0, 0		@ load domain access register
 	mcr	p15, 0, r4, c2, c0, 0		@ load page table pointer
 	b	__turn_mmu_on
+ENDPROC(__enable_mmu)
 
 /*
  * Enable the MMU.  This completely changes the structure of the visible
@@ -187,7 +188,6 @@ __enable_mmu:
  * other registers depend on the function called upon completion
  */
 	.align	5
-	.type	__turn_mmu_on, %function
 __turn_mmu_on:
 	mov	r0, r0
 	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
@@ -195,7 +195,7 @@ __turn_mmu_on:
 	mov	r3, r3
 	mov	r3, r3
 	mov	pc, r13
-
+ENDPROC(__turn_mmu_on)
 
 
 /*
@@ -211,7 +211,6 @@ __turn_mmu_on:
  *  r0, r3, r6, r7 corrupted
  *  r4 = physical page table address
  */
-	.type	__create_page_tables, %function
 __create_page_tables:
 	pgtbl	r4				@ page table address
 
@@ -325,6 +324,7 @@ __create_page_tables:
 #endif
 #endif
 	mov	pc, lr
+ENDPROC(__create_page_tables)
 	.ltorg
 
 #include "head-common.S"

arch/arm/kernel/init_task.c

@@ -8,8 +8,8 @@
 #include <linux/init.h>
 #include <linux/init_task.h>
 #include <linux/mqueue.h>
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
 #include <asm/pgtable.h>
 
 static struct fs_struct init_fs = INIT_FS;

arch/arm/kernel/io.c

@@ -1,7 +1,6 @@
 #include <linux/module.h>
 #include <linux/types.h>
-
-#include <asm/io.h>
+#include <linux/io.h>
 
 /*
  * Copy data from IO memory space to "real" memory space.

arch/arm/kernel/kprobes-decode.c

@@ -488,7 +488,7 @@ static void __kprobes simulate_ldm1stm1(struct kprobe *p, struct pt_regs *regs)
 
 	if (!ubit)
 		addr -= reg_count;
-	addr += (!pbit ^ !ubit);
+	addr += (!pbit == !ubit);
 
 	reg_bit_vector = insn & 0xffff;
 	while (reg_bit_vector) {
@@ -503,7 +503,7 @@ static void __kprobes simulate_ldm1stm1(struct kprobe *p, struct pt_regs *regs)
 	if (wbit) {
 		if (!ubit)
 			addr -= reg_count;
-		addr -= (!pbit ^ !ubit);
+		addr -= (!pbit == !ubit);
 		regs->uregs[rn] = (long)addr;
 	}
 }

arch/arm/kernel/kprobes.c

@@ -200,9 +200,12 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 	}
 }
 
-int kprobe_trap_handler(struct pt_regs *regs, unsigned int instr)
+static int __kprobes kprobe_trap_handler(struct pt_regs *regs, unsigned int instr)
 {
+	unsigned long flags;
+	local_irq_save(flags);
 	kprobe_handler(regs);
+	local_irq_restore(flags);
 	return 0;
 }
 

arch/arm/kernel/machine_kexec.c

@@ -6,10 +6,10 @@
 #include <linux/kexec.h>
 #include <linux/delay.h>
 #include <linux/reboot.h>
+#include <linux/io.h>
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
-#include <asm/io.h>
 #include <asm/cacheflush.h>
 #include <asm/mach-types.h>
 

arch/arm/kernel/process.c

@@ -28,12 +28,12 @@
 #include <linux/pm.h>
 #include <linux/tick.h>
 #include <linux/utsname.h>
+#include <linux/uaccess.h>
 
 #include <asm/leds.h>
 #include <asm/processor.h>
 #include <asm/system.h>
 #include <asm/thread_notify.h>
-#include <asm/uaccess.h>
 #include <asm/mach/time.h>
 
 static const char *processor_modes[] = {
@@ -267,35 +267,6 @@ void show_regs(struct pt_regs * regs)
 	__backtrace();
 }
 
-void show_fpregs(struct user_fp *regs)
-{
-	int i;
-
-	for (i = 0; i < 8; i++) {
-		unsigned long *p;
-		char type;
-
-		p = (unsigned long *)(regs->fpregs + i);
-
-		switch (regs->ftype[i]) {
-			case 1: type = 'f'; break;
-			case 2: type = 'd'; break;
-			case 3: type = 'e'; break;
-			default: type = '?'; break;
-		}
-		if (regs->init_flag)
-			type = '?';
-
-		printk("  f%d(%c): %08lx %08lx %08lx%c",
-			i, type, p[0], p[1], p[2], i & 1 ? '\n' : ' ');
-	}
-			
-
-	printk("FPSR: %08lx FPCR: %08lx\n",
-		(unsigned long)regs->fpsr,
-		(unsigned long)regs->fpcr);
-}
-
 /*
  * Free current thread data structures etc..
  */
@@ -414,7 +385,7 @@ unsigned long get_wchan(struct task_struct *p)
 	do {
 		if (fp < stack_start || fp > stack_end)
 			return 0;
-		lr = pc_pointer (((unsigned long *)fp)[-1]);
+		lr = ((unsigned long *)fp)[-1];
 		if (!in_sched_functions(lr))
 			return lr;
 		fp = *(unsigned long *) (fp - 12);

arch/arm/kernel/ptrace.c

@@ -18,8 +18,8 @@
 #include <linux/security.h>
 #include <linux/init.h>
 #include <linux/signal.h>
+#include <linux/uaccess.h>
 
-#include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/system.h>
 #include <asm/traps.h>
@@ -126,7 +126,7 @@ ptrace_getrn(struct task_struct *child, unsigned long insn)
 
 	val = get_user_reg(child, reg);
 	if (reg == 15)
-		val = pc_pointer(val + 8);
+		val += 8;
 
 	return val;
 }
@@ -278,8 +278,7 @@ get_branch_address(struct task_struct *child, unsigned long pc, unsigned long in
 				else
 					base -= aluop2;
 			}
-			if (read_u32(child, base, &alt) == 0)
-				alt = pc_pointer(alt);
+			read_u32(child, base, &alt);
 		}
 		break;
 
@@ -305,8 +304,7 @@ get_branch_address(struct task_struct *child, unsigned long pc, unsigned long in
 
 			base = ptrace_getrn(child, insn);
 
-			if (read_u32(child, base + nr_regs, &alt) == 0)
-				alt = pc_pointer(alt);
+			read_u32(child, base + nr_regs, &alt);
 			break;
 		}
 		break;

arch/arm/kernel/setup.c

@@ -26,11 +26,13 @@
 #include <linux/fs.h>
 
 #include <asm/cpu.h>
+#include <asm/cputype.h>
 #include <asm/elf.h>
 #include <asm/procinfo.h>
 #include <asm/setup.h>
 #include <asm/mach-types.h>
 #include <asm/cacheflush.h>
+#include <asm/cachetype.h>
 #include <asm/tlbflush.h>
 
 #include <asm/mach/arch.h>
@@ -59,13 +61,14 @@ __setup("fpe=", fpe_setup);
 
 extern void paging_init(struct meminfo *, struct machine_desc *desc);
 extern void reboot_setup(char *str);
-extern int root_mountflags;
-extern void _stext, _text, _etext, __data_start, _edata, _end;
+extern void _text, _etext, __data_start, _edata, _end;
 
 unsigned int processor_id;
 EXPORT_SYMBOL(processor_id);
 unsigned int __machine_arch_type;
 EXPORT_SYMBOL(__machine_arch_type);
+unsigned int cacheid;
+EXPORT_SYMBOL(cacheid);
 
 unsigned int __atags_pointer __initdata;
 
@@ -81,8 +84,6 @@ EXPORT_SYMBOL(system_serial_high);
 unsigned int elf_hwcap;
 EXPORT_SYMBOL(elf_hwcap);
 
-unsigned long __initdata vmalloc_reserve = 128 << 20;
-
 
 #ifdef MULTI_CPU
 struct processor processor;
@@ -111,9 +112,6 @@ static struct stack stacks[NR_CPUS];
 char elf_platform[ELF_PLATFORM_SIZE];
 EXPORT_SYMBOL(elf_platform);
 
-unsigned long phys_initrd_start __initdata = 0;
-unsigned long phys_initrd_size __initdata = 0;
-
 static struct meminfo meminfo __initdata = { 0, };
 static const char *cpu_name;
 static const char *machine_name;
@@ -178,63 +176,6 @@ static struct resource io_res[] = {
 #define lp1 io_res[1]
 #define lp2 io_res[2]
 
-static const char *cache_types[16] = {
-	"write-through",
-	"write-back",
-	"write-back",
-	"undefined 3",
-	"undefined 4",
-	"undefined 5",
-	"write-back",
-	"write-back",
-	"undefined 8",
-	"undefined 9",
-	"undefined 10",
-	"undefined 11",
-	"undefined 12",
-	"undefined 13",
-	"write-back",
-	"undefined 15",
-};
-
-static const char *cache_clean[16] = {
-	"not required",
-	"read-block",
-	"cp15 c7 ops",
-	"undefined 3",
-	"undefined 4",
-	"undefined 5",
-	"cp15 c7 ops",
-	"cp15 c7 ops",
-	"undefined 8",
-	"undefined 9",
-	"undefined 10",
-	"undefined 11",
-	"undefined 12",
-	"undefined 13",
-	"cp15 c7 ops",
-	"undefined 15",
-};
-
-static const char *cache_lockdown[16] = {
-	"not supported",
-	"not supported",
-	"not supported",
-	"undefined 3",
-	"undefined 4",
-	"undefined 5",
-	"format A",
-	"format B",
-	"undefined 8",
-	"undefined 9",
-	"undefined 10",
-	"undefined 11",
-	"undefined 12",
-	"undefined 13",
-	"format C",
-	"undefined 15",
-};
-
 static const char *proc_arch[] = {
 	"undefined/unknown",
 	"3",
@@ -255,61 +196,19 @@ static const char *proc_arch[] = {
 	"?(17)",
 };
 
-#define CACHE_TYPE(x)	(((x) >> 25) & 15)
-#define CACHE_S(x)	((x) & (1 << 24))
-#define CACHE_DSIZE(x)	(((x) >> 12) & 4095)	/* only if S=1 */
-#define CACHE_ISIZE(x)	((x) & 4095)
-
-#define CACHE_SIZE(y)	(((y) >> 6) & 7)
-#define CACHE_ASSOC(y)	(((y) >> 3) & 7)
-#define CACHE_M(y)	((y) & (1 << 2))
-#define CACHE_LINE(y)	((y) & 3)
-
-static inline void dump_cache(const char *prefix, int cpu, unsigned int cache)
-{
-	unsigned int mult = 2 + (CACHE_M(cache) ? 1 : 0);
-
-	printk("CPU%u: %s: %d bytes, associativity %d, %d byte lines, %d sets\n",
-		cpu, prefix,
-		mult << (8 + CACHE_SIZE(cache)),
-		(mult << CACHE_ASSOC(cache)) >> 1,
-		8 << CACHE_LINE(cache),
-		1 << (6 + CACHE_SIZE(cache) - CACHE_ASSOC(cache) -
-			CACHE_LINE(cache)));
-}
-
-static void __init dump_cpu_info(int cpu)
-{
-	unsigned int info = read_cpuid(CPUID_CACHETYPE);
-
-	if (info != processor_id) {
-		printk("CPU%u: D %s %s cache\n", cpu, cache_is_vivt() ? "VIVT" : "VIPT",
-		       cache_types[CACHE_TYPE(info)]);
-		if (CACHE_S(info)) {
-			dump_cache("I cache", cpu, CACHE_ISIZE(info));
-			dump_cache("D cache", cpu, CACHE_DSIZE(info));
-		} else {
-			dump_cache("cache", cpu, CACHE_ISIZE(info));
-		}
-	}
-
-	if (arch_is_coherent())
-		printk("Cache coherency enabled\n");
-}
-
 int cpu_architecture(void)
 {
 	int cpu_arch;
 
-	if ((processor_id & 0x0008f000) == 0) {
+	if ((read_cpuid_id() & 0x0008f000) == 0) {
 		cpu_arch = CPU_ARCH_UNKNOWN;
-	} else if ((processor_id & 0x0008f000) == 0x00007000) {
-		cpu_arch = (processor_id & (1 << 23)) ? CPU_ARCH_ARMv4T : CPU_ARCH_ARMv3;
-	} else if ((processor_id & 0x00080000) == 0x00000000) {
-		cpu_arch = (processor_id >> 16) & 7;
+	} else if ((read_cpuid_id() & 0x0008f000) == 0x00007000) {
+		cpu_arch = (read_cpuid_id() & (1 << 23)) ? CPU_ARCH_ARMv4T : CPU_ARCH_ARMv3;
+	} else if ((read_cpuid_id() & 0x00080000) == 0x00000000) {
+		cpu_arch = (read_cpuid_id() >> 16) & 7;
 		if (cpu_arch)
 			cpu_arch += CPU_ARCH_ARMv3;
-	} else if ((processor_id & 0x000f0000) == 0x000f0000) {
+	} else if ((read_cpuid_id() & 0x000f0000) == 0x000f0000) {
 		unsigned int mmfr0;
 
 		/* Revised CPUID format. Read the Memory Model Feature
@@ -330,6 +229,34 @@ int cpu_architecture(void)
 	return cpu_arch;
 }
 
+static void __init cacheid_init(void)
+{
+	unsigned int cachetype = read_cpuid_cachetype();
+	unsigned int arch = cpu_architecture();
+
+	if (arch >= CPU_ARCH_ARMv7) {
+		cacheid = CACHEID_VIPT_NONALIASING;
+		if ((cachetype & (3 << 14)) == 1 << 14)
+			cacheid |= CACHEID_ASID_TAGGED;
+	} else if (arch >= CPU_ARCH_ARMv6) {
+		if (cachetype & (1 << 23))
+			cacheid = CACHEID_VIPT_ALIASING;
+		else
+			cacheid = CACHEID_VIPT_NONALIASING;
+	} else {
+		cacheid = CACHEID_VIVT;
+	}
+
+	printk("CPU: %s data cache, %s instruction cache\n",
+		cache_is_vivt() ? "VIVT" :
+		cache_is_vipt_aliasing() ? "VIPT aliasing" :
+		cache_is_vipt_nonaliasing() ? "VIPT nonaliasing" : "unknown",
+		cache_is_vivt() ? "VIVT" :
+		icache_is_vivt_asid_tagged() ? "VIVT ASID tagged" :
+		cache_is_vipt_aliasing() ? "VIPT aliasing" :
+		cache_is_vipt_nonaliasing() ? "VIPT nonaliasing" : "unknown");
+}
+
 /*
  * These functions re-use the assembly code in head.S, which
  * already provide the required functionality.
@@ -346,10 +273,10 @@ static void __init setup_processor(void)
 	 * types.  The linker builds this table for us from the
 	 * entries in arch/arm/mm/proc-*.S
 	 */
-	list = lookup_processor_type(processor_id);
+	list = lookup_processor_type(read_cpuid_id());
 	if (!list) {
 		printk("CPU configuration botched (ID %08x), unable "
-		       "to continue.\n", processor_id);
+		       "to continue.\n", read_cpuid_id());
 		while (1);
 	}
 
@@ -369,7 +296,7 @@ static void __init setup_processor(void)
 #endif
 
 	printk("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n",
-	       cpu_name, processor_id, (int)processor_id & 15,
+	       cpu_name, read_cpuid_id(), read_cpuid_id() & 15,
 	       proc_arch[cpu_architecture()], cr_alignment);
 
 	sprintf(init_utsname()->machine, "%s%c", list->arch_name, ENDIANNESS);
@@ -379,14 +306,14 @@ static void __init setup_processor(void)
 	elf_hwcap &= ~HWCAP_THUMB;
 #endif
 
+	cacheid_init();
 	cpu_proc_init();
 }
 
 /*
  * cpu_init - initialise one CPU.
  *
- * cpu_init dumps the cache information, initialises SMP specific
- * information, and sets up the per-CPU stacks.
+ * cpu_init sets up the per-CPU stacks.
  */
 void cpu_init(void)
 {
@@ -398,9 +325,6 @@ void cpu_init(void)
 		BUG();
 	}
 
-	if (system_state == SYSTEM_BOOTING)
-		dump_cpu_info(cpu);
-
 	/*
 	 * setup stacks for re-entrant exception handlers
 	 */
@@ -443,20 +367,6 @@ static struct machine_desc * __init setup_machine(unsigned int nr)
 	return list;
 }
 
-static void __init early_initrd(char **p)
-{
-	unsigned long start, size;
-
-	start = memparse(*p, p);
-	if (**p == ',') {
-		size = memparse((*p) + 1, p);
-
-		phys_initrd_start = start;
-		phys_initrd_size = size;
-	}
-}
-__early_param("initrd=", early_initrd);
-
 static void __init arm_add_memory(unsigned long start, unsigned long size)
 {
 	struct membank *bank;
@@ -502,17 +412,6 @@ static void __init early_mem(char **p)
 }
 __early_param("mem=", early_mem);
 
-/*
- * vmalloc=size forces the vmalloc area to be exactly 'size'
- * bytes. This can be used to increase (or decrease) the vmalloc
- * area - the default is 128m.
- */
-static void __init early_vmalloc(char **arg)
-{
-	vmalloc_reserve = memparse(*arg, arg);
-}
-__early_param("vmalloc=", early_vmalloc);
-
 /*
  * Initial parsing of the command line.
  */
@@ -527,12 +426,12 @@ static void __init parse_cmdline(char **cmdline_p, char *from)
 			struct early_params *p;
 
 			for (p = &__early_begin; p < &__early_end; p++) {
-				int len = strlen(p->arg);
+				int arglen = strlen(p->arg);
 
-				if (memcmp(from, p->arg, len) == 0) {
+				if (memcmp(from, p->arg, arglen) == 0) {
 					if (to != command_line)
 						to -= 1;
-					from += len;
+					from += arglen;
 					p->fn(&from);
 
 					while (*from != ' ' && *from != '\0')
@@ -579,18 +478,13 @@ request_standard_resources(struct meminfo *mi, struct machine_desc *mdesc)
 	kernel_data.end     = virt_to_phys(&_end - 1);
 
 	for (i = 0; i < mi->nr_banks; i++) {
-		unsigned long virt_start, virt_end;
-
 		if (mi->bank[i].size == 0)
 			continue;
 
-		virt_start = __phys_to_virt(mi->bank[i].start);
-		virt_end   = virt_start + mi->bank[i].size - 1;
-
 		res = alloc_bootmem_low(sizeof(*res));
 		res->name  = "System RAM";
-		res->start = __virt_to_phys(virt_start);
-		res->end   = __virt_to_phys(virt_end);
+		res->start = mi->bank[i].start;
+		res->end   = mi->bank[i].start + mi->bank[i].size - 1;
 		res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 
 		request_resource(&iomem_resource, res);
@@ -694,26 +588,6 @@ static int __init parse_tag_ramdisk(const struct tag *tag)
 
 __tagtable(ATAG_RAMDISK, parse_tag_ramdisk);
 
-static int __init parse_tag_initrd(const struct tag *tag)
-{
-	printk(KERN_WARNING "ATAG_INITRD is deprecated; "
-		"please update your bootloader.\n");
-	phys_initrd_start = __virt_to_phys(tag->u.initrd.start);
-	phys_initrd_size = tag->u.initrd.size;
-	return 0;
-}
-
-__tagtable(ATAG_INITRD, parse_tag_initrd);
-
-static int __init parse_tag_initrd2(const struct tag *tag)
-{
-	phys_initrd_start = tag->u.initrd.start;
-	phys_initrd_size = tag->u.initrd.size;
-	return 0;
-}
-
-__tagtable(ATAG_INITRD2, parse_tag_initrd2);
-
 static int __init parse_tag_serialnr(const struct tag *tag)
 {
 	system_serial_low = tag->u.serialnr.low;
@@ -901,28 +775,12 @@ static const char *hwcap_str[] = {
 	NULL
 };
 
-static void
-c_show_cache(struct seq_file *m, const char *type, unsigned int cache)
-{
-	unsigned int mult = 2 + (CACHE_M(cache) ? 1 : 0);
-
-	seq_printf(m, "%s size\t\t: %d\n"
-		      "%s assoc\t\t: %d\n"
-		      "%s line length\t: %d\n"
-		      "%s sets\t\t: %d\n",
-		type, mult << (8 + CACHE_SIZE(cache)),
-		type, (mult << CACHE_ASSOC(cache)) >> 1,
-		type, 8 << CACHE_LINE(cache),
-		type, 1 << (6 + CACHE_SIZE(cache) - CACHE_ASSOC(cache) -
-			    CACHE_LINE(cache)));
-}
-
 static int c_show(struct seq_file *m, void *v)
 {
 	int i;
 
 	seq_printf(m, "Processor\t: %s rev %d (%s)\n",
-		   cpu_name, (int)processor_id & 15, elf_platform);
+		   cpu_name, read_cpuid_id() & 15, elf_platform);
 
 #if defined(CONFIG_SMP)
 	for_each_online_cpu(i) {
@@ -949,47 +807,26 @@ static int c_show(struct seq_file *m, void *v)
 		if (elf_hwcap & (1 << i))
 			seq_printf(m, "%s ", hwcap_str[i]);
 
-	seq_printf(m, "\nCPU implementer\t: 0x%02x\n", processor_id >> 24);
+	seq_printf(m, "\nCPU implementer\t: 0x%02x\n", read_cpuid_id() >> 24);
 	seq_printf(m, "CPU architecture: %s\n", proc_arch[cpu_architecture()]);
 
-	if ((processor_id & 0x0008f000) == 0x00000000) {
+	if ((read_cpuid_id() & 0x0008f000) == 0x00000000) {
 		/* pre-ARM7 */
-		seq_printf(m, "CPU part\t: %07x\n", processor_id >> 4);
+		seq_printf(m, "CPU part\t: %07x\n", read_cpuid_id() >> 4);
 	} else {
-		if ((processor_id & 0x0008f000) == 0x00007000) {
+		if ((read_cpuid_id() & 0x0008f000) == 0x00007000) {
 			/* ARM7 */
 			seq_printf(m, "CPU variant\t: 0x%02x\n",
-				   (processor_id >> 16) & 127);
+				   (read_cpuid_id() >> 16) & 127);
 		} else {
 			/* post-ARM7 */
 			seq_printf(m, "CPU variant\t: 0x%x\n",
-				   (processor_id >> 20) & 15);
+				   (read_cpuid_id() >> 20) & 15);
 		}
 		seq_printf(m, "CPU part\t: 0x%03x\n",
-			   (processor_id >> 4) & 0xfff);
-	}
-	seq_printf(m, "CPU revision\t: %d\n", processor_id & 15);
-
-	{
-		unsigned int cache_info = read_cpuid(CPUID_CACHETYPE);
-		if (cache_info != processor_id) {
-			seq_printf(m, "Cache type\t: %s\n"
-				      "Cache clean\t: %s\n"
-				      "Cache lockdown\t: %s\n"
-				      "Cache format\t: %s\n",
-				   cache_types[CACHE_TYPE(cache_info)],
-				   cache_clean[CACHE_TYPE(cache_info)],
-				   cache_lockdown[CACHE_TYPE(cache_info)],
-				   CACHE_S(cache_info) ? "Harvard" : "Unified");
-
-			if (CACHE_S(cache_info)) {
-				c_show_cache(m, "I", CACHE_ISIZE(cache_info));
-				c_show_cache(m, "D", CACHE_DSIZE(cache_info));
-			} else {
-				c_show_cache(m, "Cache", CACHE_ISIZE(cache_info));
-			}
-		}
+			   (read_cpuid_id() >> 4) & 0xfff);
 	}
+	seq_printf(m, "CPU revision\t: %d\n", read_cpuid_id() & 15);
 
 	seq_puts(m, "\n");
 

arch/arm/kernel/signal.c

@@ -11,11 +11,11 @@
 #include <linux/signal.h>
 #include <linux/personality.h>
 #include <linux/freezer.h>
+#include <linux/uaccess.h>
 
 #include <asm/elf.h>
 #include <asm/cacheflush.h>
 #include <asm/ucontext.h>
-#include <asm/uaccess.h>
 #include <asm/unistd.h>
 
 #include "ptrace.h"

arch/arm/kernel/sys_arm.c

@@ -27,8 +27,7 @@
 #include <linux/file.h>
 #include <linux/utsname.h>
 #include <linux/ipc.h>
-
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 extern unsigned long do_mremap(unsigned long addr, unsigned long old_len,
 			       unsigned long new_len, unsigned long flags,

arch/arm/kernel/sys_oabi-compat.c

@@ -82,7 +82,7 @@
 #include <linux/socket.h>
 #include <linux/net.h>
 #include <linux/ipc.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 struct oldabi_stat64 {
 	unsigned long long st_dev;

arch/arm/kernel/time.c

@@ -59,7 +59,7 @@ unsigned long profile_pc(struct pt_regs *regs)
 
 	if (in_lock_functions(pc)) {
 		fp = regs->ARM_fp;
-		pc = pc_pointer(((unsigned long *)fp)[-1]);
+		pc = ((unsigned long *)fp)[-1];
 	}
 
 	return pc;

arch/arm/kernel/traps.c

@@ -19,15 +19,13 @@
 #include <linux/kallsyms.h>
 #include <linux/delay.h>
 #include <linux/init.h>
-#include <linux/kprobes.h>
+#include <linux/uaccess.h>
 
 #include <asm/atomic.h>
 #include <asm/cacheflush.h>
 #include <asm/system.h>
-#include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/traps.h>
-#include <asm/io.h>
 
 #include "ptrace.h"
 #include "signal.h"
@@ -69,7 +67,8 @@ void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long
  */
 static int verify_stack(unsigned long sp)
 {
-	if (sp < PAGE_OFFSET || (sp > (unsigned long)high_memory && high_memory != 0))
+	if (sp < PAGE_OFFSET ||
+	    (sp > (unsigned long)high_memory && high_memory != NULL))
 		return -EFAULT;
 
 	return 0;
@@ -328,17 +327,6 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 		get_user(instr, (u32 __user *)pc);
 	}
 
-#ifdef CONFIG_KPROBES
-	/*
-	 * It is possible to have recursive kprobes, so we can't call
-	 * the kprobe trap handler with the undef_lock held.
-	 */
-	if (instr == KPROBE_BREAKPOINT_INSTRUCTION && !user_mode(regs)) {
-		kprobe_trap_handler(regs, instr);
-		return;
-	}
-#endif
-
 	if (call_undef_hook(regs, instr) == 0)
 		return;
 

arch/arm/kernel/xscale-cp0.c

@@ -14,8 +14,8 @@
 #include <linux/signal.h>
 #include <linux/sched.h>
 #include <linux/init.h>
+#include <linux/io.h>
 #include <asm/thread_notify.h>
-#include <asm/io.h>
 
 static inline void dsp_save_state(u32 *state)
 {

arch/arm/lib/ashldi3.S

@@ -47,3 +47,5 @@ ENTRY(__aeabi_llsl)
 	mov	al, al, lsl r2
 	mov	pc, lr
 
+ENDPROC(__ashldi3)
+ENDPROC(__aeabi_llsl)

arch/arm/lib/ashrdi3.S

@@ -47,3 +47,5 @@ ENTRY(__aeabi_lasr)
 	mov	ah, ah, asr r2
 	mov	pc, lr
 
+ENDPROC(__ashrdi3)
+ENDPROC(__aeabi_lasr)

arch/arm/lib/backtrace.S

@@ -30,6 +30,8 @@ ENTRY(c_backtrace)
 
 #if !defined(CONFIG_FRAME_POINTER) || !defined(CONFIG_PRINTK)
 		mov	pc, lr
+ENDPROC(__backtrace)
+ENDPROC(c_backtrace)
 #else
 		stmfd	sp!, {r4 - r8, lr}	@ Save an extra register so we have a location...
 		movs	frame, r0		@ if frame pointer is zero
@@ -103,6 +105,8 @@ for_each_frame:	tst	frame, mask		@ Check for address exceptions
 		mov	r1, frame
 		bl	printk
 no_frame:	ldmfd	sp!, {r4 - r8, pc}
+ENDPROC(__backtrace)
+ENDPROC(c_backtrace)
 		
 		.section __ex_table,"a"
 		.align	3

arch/arm/lib/changebit.S

@@ -19,3 +19,5 @@ ENTRY(_change_bit_be)
 		eor	r0, r0, #0x18		@ big endian byte ordering
 ENTRY(_change_bit_le)
 	bitop	eor
+ENDPROC(_change_bit_be)
+ENDPROC(_change_bit_le)

arch/arm/lib/clear_user.S

@@ -41,9 +41,10 @@ USER(		strplt	r2, [r0], #4)
 USER(		strnebt	r2, [r0], #1)
 USER(		strnebt	r2, [r0], #1)
 		tst	r1, #1			@ x1 x0 x1 x0 x1 x0 x1
-USER(		strnebt	r2, [r0], #1)
+USER(		strnebt	r2, [r0])
 		mov	r0, #0
 		ldmfd	sp!, {r1, pc}
+ENDPROC(__clear_user)
 
 		.section .fixup,"ax"
 		.align	0

arch/arm/lib/clearbit.S

@@ -20,3 +20,5 @@ ENTRY(_clear_bit_be)
 		eor	r0, r0, #0x18		@ big endian byte ordering
 ENTRY(_clear_bit_le)
 	bitop	bic
+ENDPROC(_clear_bit_be)
+ENDPROC(_clear_bit_le)

arch/arm/lib/copy_from_user.S

@@ -87,6 +87,8 @@ ENTRY(__copy_from_user)
 
 #include "copy_template.S"
 
+ENDPROC(__copy_from_user)
+
 	.section .fixup,"ax"
 	.align 0
 	copy_abort_preamble

arch/arm/lib/copy_page.S

@@ -44,3 +44,4 @@ ENTRY(copy_page)
 	PLD(	ldmeqia r1!, {r3, r4, ip, lr}	)
 	PLD(	beq	2b			)
 		ldmfd	sp!, {r4, pc}			@	3
+ENDPROC(copy_page)

arch/arm/lib/copy_to_user.S

@@ -90,6 +90,8 @@ ENTRY(__copy_to_user)
 
 #include "copy_template.S"
 
+ENDPROC(__copy_to_user)
+
 	.section .fixup,"ax"
 	.align 0
 	copy_abort_preamble

arch/arm/lib/csumipv6.S

@@ -29,4 +29,5 @@ ENTRY(__csum_ipv6_magic)
 		adcs	r0, r0, r2
 		adcs	r0, r0, #0
 		ldmfd	sp!, {pc}
+ENDPROC(__csum_ipv6_magic)
 

arch/arm/lib/csumpartial.S

@@ -139,3 +139,4 @@ ENTRY(csum_partial)
 		tst	len, #0x1c
 		bne	4b
 		b	.Lless4
+ENDPROC(csum_partial)

arch/arm/lib/csumpartialcopy.S

@@ -18,13 +18,11 @@
  */
 
 		.macro	save_regs
-		mov	ip, sp
-		stmfd	sp!, {r1, r4 - r8, fp, ip, lr, pc}
-		sub	fp, ip, #4
+		stmfd	sp!, {r1, r4 - r8, lr}
 		.endm
 
 		.macro	load_regs
-		ldmfd	sp, {r1, r4 - r8, fp, sp, pc}
+		ldmfd	sp!, {r1, r4 - r8, pc}
 		.endm
 
 		.macro	load1b, reg1
@@ -50,5 +48,6 @@
 		.endm
 
 #define FN_ENTRY	ENTRY(csum_partial_copy_nocheck)
+#define FN_EXIT		ENDPROC(csum_partial_copy_nocheck)
 
 #include "csumpartialcopygeneric.S"

arch/arm/lib/csumpartialcopygeneric.S

@@ -329,3 +329,4 @@ FN_ENTRY
 		adcs	sum, sum, r4, push #24
 		mov	r5, r4, get_byte_1
 		b	.Lexit
+FN_EXIT

arch/arm/lib/csumpartialcopyuser.S

@@ -18,13 +18,11 @@
 		.text
 
 		.macro	save_regs
-		mov	ip, sp
-		stmfd	sp!, {r1 - r2, r4 - r8, fp, ip, lr, pc}
-		sub	fp, ip, #4
+		stmfd	sp!, {r1, r2, r4 - r8, lr}
 		.endm
 
 		.macro	load_regs
-		ldmfd	sp, {r1, r2, r4-r8, fp, sp, pc}
+		ldmfd	sp!, {r1, r2, r4 - r8, pc}
 		.endm
 
 		.macro	load1b,	reg1
@@ -82,6 +80,7 @@
  */
 
 #define FN_ENTRY	ENTRY(csum_partial_copy_from_user)
+#define FN_EXIT		ENDPROC(csum_partial_copy_from_user)
 
 #include "csumpartialcopygeneric.S"
 

arch/arm/lib/delay.S

@@ -60,3 +60,6 @@ ENTRY(__delay)
 #endif
 		bhi	__delay
 		mov	pc, lr
+ENDPROC(__udelay)
+ENDPROC(__const_udelay)
+ENDPROC(__delay)

arch/arm/lib/div64.S

@@ -198,3 +198,4 @@ ENTRY(__do_div64)
 	mov	xh, #0
 	ldr	pc, [sp], #8
 
+ENDPROC(__do_div64)

arch/arm/lib/findbit.S

@@ -33,6 +33,7 @@ ENTRY(_find_first_zero_bit_le)
 		blo	1b
 3:		mov	r0, r1			@ no free bits
 		mov	pc, lr
+ENDPROC(_find_first_zero_bit_le)
 
 /*
  * Purpose  : Find next 'zero' bit
@@ -50,6 +51,7 @@ ENTRY(_find_next_zero_bit_le)
 		orr	r2, r2, #7		@ if zero, then no bits here
 		add	r2, r2, #1		@ align bit pointer
 		b	2b			@ loop for next bit
+ENDPROC(_find_next_zero_bit_le)
 
 /*
  * Purpose  : Find a 'one' bit
@@ -67,6 +69,7 @@ ENTRY(_find_first_bit_le)
 		blo	1b
 3:		mov	r0, r1			@ no free bits
 		mov	pc, lr
+ENDPROC(_find_first_bit_le)
 
 /*
  * Purpose  : Find next 'one' bit
@@ -83,6 +86,7 @@ ENTRY(_find_next_bit_le)
 		orr	r2, r2, #7		@ if zero, then no bits here
 		add	r2, r2, #1		@ align bit pointer
 		b	2b			@ loop for next bit
+ENDPROC(_find_next_bit_le)
 
 #ifdef __ARMEB__
 
@@ -99,6 +103,7 @@ ENTRY(_find_first_zero_bit_be)
 		blo	1b
 3:		mov	r0, r1			@ no free bits
 		mov	pc, lr
+ENDPROC(_find_first_zero_bit_be)
 
 ENTRY(_find_next_zero_bit_be)
 		teq	r1, #0
@@ -113,6 +118,7 @@ ENTRY(_find_next_zero_bit_be)
 		orr	r2, r2, #7		@ if zero, then no bits here
 		add	r2, r2, #1		@ align bit pointer
 		b	2b			@ loop for next bit
+ENDPROC(_find_next_zero_bit_be)
 
 ENTRY(_find_first_bit_be)
 		teq	r1, #0
@@ -127,6 +133,7 @@ ENTRY(_find_first_bit_be)
 		blo	1b
 3:		mov	r0, r1			@ no free bits
 		mov	pc, lr
+ENDPROC(_find_first_bit_be)
 
 ENTRY(_find_next_bit_be)
 		teq	r1, #0
@@ -140,6 +147,7 @@ ENTRY(_find_next_bit_be)
 		orr	r2, r2, #7		@ if zero, then no bits here
 		add	r2, r2, #1		@ align bit pointer
 		b	2b			@ loop for next bit
+ENDPROC(_find_next_bit_be)
 
 #endif
 

arch/arm/lib/getuser.S

@@ -26,16 +26,16 @@
  * Note that ADDR_LIMIT is either 0 or 0xc0000000.
  * Note also that it is intended that __get_user_bad is not global.
  */
+#include <linux/linkage.h>
 #include <asm/errno.h>
 
-	.global	__get_user_1
-__get_user_1:
+ENTRY(__get_user_1)
 1:	ldrbt	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
+ENDPROC(__get_user_1)
 
-	.global	__get_user_2
-__get_user_2:
+ENTRY(__get_user_2)
 2:	ldrbt	r2, [r0], #1
 3:	ldrbt	r3, [r0]
 #ifndef __ARMEB__
@@ -45,17 +45,19 @@ __get_user_2:
 #endif
 	mov	r0, #0
 	mov	pc, lr
+ENDPROC(__get_user_2)
 
-	.global	__get_user_4
-__get_user_4:
+ENTRY(__get_user_4)
 4:	ldrt	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
+ENDPROC(__get_user_4)
 
 __get_user_bad:
 	mov	r2, #0
 	mov	r0, #-EFAULT
 	mov	pc, lr
+ENDPROC(__get_user_bad)
 
 .section __ex_table, "a"
 	.long	1b, __get_user_bad

arch/arm/lib/io-readsb.S

@@ -120,3 +120,4 @@ ENTRY(__raw_readsb)
 		strgtb	r3, [r1]
 
 		ldmfd	sp!, {r4 - r6, pc}
+ENDPROC(__raw_readsb)

arch/arm/lib/io-readsl.S

@@ -76,3 +76,4 @@ ENTRY(__raw_readsl)
 8:		mov	r3, ip, get_byte_0
 		strb	r3, [r1, #0]
 		mov	pc, lr
+ENDPROC(__raw_readsl)

arch/arm/lib/io-readsw-armv4.S

@@ -128,3 +128,4 @@ ENTRY(__raw_readsw)
    _BE_ONLY_(	movne	ip, ip, lsr #24		)
 		strneb	ip, [r1]
 		ldmfd	sp!, {r4, pc}
+ENDPROC(__raw_readsw)

arch/arm/lib/io-writesb.S

@@ -91,3 +91,4 @@ ENTRY(__raw_writesb)
 		strgtb	r3, [r0]
 
 		ldmfd	sp!, {r4, r5, pc}
+ENDPROC(__raw_writesb)

arch/arm/lib/io-writesl.S

@@ -64,3 +64,4 @@ ENTRY(__raw_writesl)
 		str	ip, [r0]
 		bne	6b
 		mov	pc, lr
+ENDPROC(__raw_writesl)

arch/arm/lib/io-writesw-armv4.S

@@ -94,3 +94,4 @@ ENTRY(__raw_writesw)
 3:		movne	ip, r3, lsr #8
 		strneh	ip, [r0]
 		mov	pc, lr
+ENDPROC(__raw_writesw)

arch/arm/lib/lib1funcs.S

@@ -230,6 +230,8 @@ ENTRY(__aeabi_uidiv)
 	mov	r0, r0, lsr r2
 	mov	pc, lr
 
+ENDPROC(__udivsi3)
+ENDPROC(__aeabi_uidiv)
 
 ENTRY(__umodsi3)
 
@@ -245,6 +247,7 @@ ENTRY(__umodsi3)
 
 	mov	pc, lr
 
+ENDPROC(__umodsi3)
 
 ENTRY(__divsi3)
 ENTRY(__aeabi_idiv)
@@ -284,6 +287,8 @@ ENTRY(__aeabi_idiv)
 	rsbmi	r0, r0, #0
 	mov	pc, lr
 
+ENDPROC(__divsi3)
+ENDPROC(__aeabi_idiv)
 
 ENTRY(__modsi3)
 
@@ -305,6 +310,8 @@ ENTRY(__modsi3)
 	rsbmi	r0, r0, #0
 	mov	pc, lr
 
+ENDPROC(__modsi3)
+
 #ifdef CONFIG_AEABI
 
 ENTRY(__aeabi_uidivmod)
@@ -316,6 +323,8 @@ ENTRY(__aeabi_uidivmod)
 	sub	r1, r1, r3
 	mov	pc, lr
 
+ENDPROC(__aeabi_uidivmod)
+
 ENTRY(__aeabi_idivmod)
 
 	stmfd	sp!, {r0, r1, ip, lr}
@@ -325,6 +334,8 @@ ENTRY(__aeabi_idivmod)
 	sub	r1, r1, r3
 	mov	pc, lr
 
+ENDPROC(__aeabi_idivmod)
+
 #endif
 
 Ldiv0:

arch/arm/lib/lshrdi3.S

@@ -47,3 +47,5 @@ ENTRY(__aeabi_llsr)
 	mov	ah, ah, lsr r2
 	mov	pc, lr
 
+ENDPROC(__lshrdi3)
+ENDPROC(__aeabi_llsr)

arch/arm/lib/memchr.S

@@ -23,3 +23,4 @@ ENTRY(memchr)
 	sub	r0, r0, #1
 2:	movne	r0, #0
 	mov	pc, lr
+ENDPROC(memchr)

arch/arm/lib/memcpy.S

@@ -57,3 +57,4 @@ ENTRY(memcpy)
 
 #include "copy_template.S"
 
+ENDPROC(memcpy)

arch/arm/lib/memmove.S

@@ -196,3 +196,4 @@ ENTRY(memmove)
 
 18:		backward_copy_shift	push=24	pull=8
 
+ENDPROC(memmove)

arch/arm/lib/memset.S

@@ -124,3 +124,4 @@ ENTRY(memset)
 	tst	r2, #1
 	strneb	r1, [r0], #1
 	mov	pc, lr
+ENDPROC(memset)

arch/arm/lib/memzero.S

@@ -122,3 +122,4 @@ ENTRY(__memzero)
 	tst	r1, #1			@ 1 a byte left over
 	strneb	r2, [r0], #1		@ 1
 	mov	pc, lr			@ 1
+ENDPROC(__memzero)

arch/arm/lib/muldi3.S

@@ -43,3 +43,5 @@ ENTRY(__aeabi_lmul)
 	adc	xh, xh, ip, lsr #16
 	mov	pc, lr
 
+ENDPROC(__muldi3)
+ENDPROC(__aeabi_lmul)

arch/arm/lib/putuser.S

@@ -26,16 +26,16 @@
  * Note that ADDR_LIMIT is either 0 or 0xc0000000
  * Note also that it is intended that __put_user_bad is not global.
  */
+#include <linux/linkage.h>
 #include <asm/errno.h>
 
-	.global	__put_user_1
-__put_user_1:
+ENTRY(__put_user_1)
 1:	strbt	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
+ENDPROC(__put_user_1)
 
-	.global	__put_user_2
-__put_user_2:
+ENTRY(__put_user_2)
 	mov	ip, r2, lsr #8
 #ifndef __ARMEB__
 2:	strbt	r2, [r0], #1
@@ -46,23 +46,25 @@ __put_user_2:
 #endif
 	mov	r0, #0
 	mov	pc, lr
+ENDPROC(__put_user_2)
 
-	.global	__put_user_4
-__put_user_4:
+ENTRY(__put_user_4)
 4:	strt	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
+ENDPROC(__put_user_4)
 
-	.global	__put_user_8
-__put_user_8:
+ENTRY(__put_user_8)
 5:	strt	r2, [r0], #4
 6:	strt	r3, [r0]
 	mov	r0, #0
 	mov	pc, lr
+ENDPROC(__put_user_8)
 
 __put_user_bad:
 	mov	r0, #-EFAULT
 	mov	pc, lr
+ENDPROC(__put_user_bad)
 
 .section __ex_table, "a"
 	.long	1b, __put_user_bad

arch/arm/lib/setbit.S

@@ -20,3 +20,5 @@ ENTRY(_set_bit_be)
 		eor	r0, r0, #0x18		@ big endian byte ordering
 ENTRY(_set_bit_le)
 	bitop	orr
+ENDPROC(_set_bit_be)
+ENDPROC(_set_bit_le)

arch/arm/lib/sha1.S

@@ -185,6 +185,8 @@ ENTRY(sha_transform)
 
 	ldmfd	sp!, {r4 - r8, pc}
 
+ENDPROC(sha_transform)
+
 .L_sha_K:
 	.word	0x5a827999, 0x6ed9eba1, 0x8f1bbcdc, 0xca62c1d6
 
@@ -204,3 +206,4 @@ ENTRY(sha_init)
 	stmia	r0, {r1, r2, r3, ip, lr}
 	ldr	pc, [sp], #4
 
+ENDPROC(sha_init)

arch/arm/lib/strchr.S

@@ -24,3 +24,4 @@ ENTRY(strchr)
 		movne	r0, #0
 		subeq	r0, r0, #1
 		mov	pc, lr
+ENDPROC(strchr)

arch/arm/lib/strncpy_from_user.S

@@ -31,6 +31,7 @@ USER(	ldrplbt	r3, [r1], #1)
 	sub	r1, r1, #1	@ take NUL character out of count
 2:	sub	r0, r1, ip
 	mov	pc, lr
+ENDPROC(__strncpy_from_user)
 
 	.section .fixup,"ax"
 	.align	0

arch/arm/lib/strnlen_user.S

@@ -31,6 +31,7 @@ USER(	ldrbt	r3, [r0], #1)
 	add	r0, r0, #1
 2:	sub	r0, r0, r2
 	mov	pc, lr
+ENDPROC(__strnlen_user)
 
 	.section .fixup,"ax"
 	.align	0

arch/arm/lib/strrchr.S

@@ -23,3 +23,4 @@ ENTRY(strrchr)
 		bne	1b
 		mov	r0, r3
 		mov	pc, lr
+ENDPROC(strrchr)

arch/arm/lib/testchangebit.S

@@ -16,3 +16,5 @@ ENTRY(_test_and_change_bit_be)
 		eor	r0, r0, #0x18		@ big endian byte ordering
 ENTRY(_test_and_change_bit_le)
 	testop	eor, strb
+ENDPROC(_test_and_change_bit_be)
+ENDPROC(_test_and_change_bit_le)

arch/arm/lib/testclearbit.S

@@ -16,3 +16,5 @@ ENTRY(_test_and_clear_bit_be)
 		eor	r0, r0, #0x18		@ big endian byte ordering
 ENTRY(_test_and_clear_bit_le)
 	testop	bicne, strneb
+ENDPROC(_test_and_clear_bit_be)
+ENDPROC(_test_and_clear_bit_le)