Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6

Conflicts:

	sound/core/memalloc.c

25 files changed, 536 insertions, 600 deletions

diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h
index 7b62351f097d..4d88425a4169 100644
--- a/arch/arm/include/asm/bug.h
+++ b/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
 
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 9073d9c6567e..de6c59f814a1 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/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
diff --git a/arch/arm/include/asm/cachetype.h b/arch/arm/include/asm/cachetype.h
new file mode 100644
index 000000000000..d3a4c2cb9f2f
--- /dev/null
+++ b/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
diff --git a/arch/arm/include/asm/cnt32_to_63.h b/arch/arm/include/asm/cnt32_to_63.h
deleted file mode 100644
index 480c873fa746..000000000000
--- a/arch/arm/include/asm/cnt32_to_63.h
+++ /dev/null
@@ -1,78 +0,0 @@
-/*
- *  include/asm/cnt32_to_63.h -- extend a 32-bit counter to 63 bits
- *
- *  Author:	Nicolas Pitre
- *  Created:	December 3, 2006
- *  Copyright:	MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation.
- */
-
-#ifndef __INCLUDE_CNT32_TO_63_H__
-#define __INCLUDE_CNT32_TO_63_H__
-
-#include <linux/compiler.h>
-#include <asm/types.h>
-#include <asm/byteorder.h>
-
-/*
- * Prototype: u64 cnt32_to_63(u32 cnt)
- * Many hardware clock counters are only 32 bits wide and therefore have
- * a relatively short period making wrap-arounds rather frequent.  This
- * is a problem when implementing sched_clock() for example, where a 64-bit
- * non-wrapping monotonic value is expected to be returned.
- *
- * To overcome that limitation, let's extend a 32-bit counter to 63 bits
- * in a completely lock free fashion. Bits 0 to 31 of the clock are provided
- * by the hardware while bits 32 to 62 are stored in memory.  The top bit in
- * memory is used to synchronize with the hardware clock half-period.  When
- * the top bit of both counters (hardware and in memory) differ then the
- * memory is updated with a new value, incrementing it when the hardware
- * counter wraps around.
- *
- * Because a word store in memory is atomic then the incremented value will
- * always be in synch with the top bit indicating to any potential concurrent
- * reader if the value in memory is up to date or not with regards to the
- * needed increment.  And any race in updating the value in memory is harmless
- * as the same value would simply be stored more than once.
- *
- * The only restriction for the algorithm to work properly is that this
- * code must be executed at least once per each half period of the 32-bit
- * counter to properly update the state bit in memory. This is usually not a
- * problem in practice, but if it is then a kernel timer could be scheduled
- * to manage for this code to be executed often enough.
- *
- * Note that the top bit (bit 63) in the returned value should be considered
- * as garbage.  It is not cleared here because callers are likely to use a
- * multiplier on the returned value which can get rid of the top bit
- * implicitly by making the multiplier even, therefore saving on a runtime
- * clear-bit instruction. Otherwise caller must remember to clear the top
- * bit explicitly.
- */
-
-/* this is used only to give gcc a clue about good code generation */
-typedef union {
-	struct {
-#if defined(__LITTLE_ENDIAN)
-		u32 lo, hi;
-#elif defined(__BIG_ENDIAN)
-		u32 hi, lo;
-#endif
-	};
-	u64 val;
-} cnt32_to_63_t;
-
-#define cnt32_to_63(cnt_lo) \
-({ \
-	static volatile u32 __m_cnt_hi = 0; \
-	cnt32_to_63_t __x; \
-	__x.hi = __m_cnt_hi; \
-	__x.lo = (cnt_lo); \
- 	if (unlikely((s32)(__x.hi ^ __x.lo) < 0)) \
-		__m_cnt_hi = __x.hi = (__x.hi ^ 0x80000000) + (__x.hi >> 31); \
-	__x.val; \
-})
-
-#endif
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
new file mode 100644
index 000000000000..7b9d27e749b8
--- /dev/null
+++ b/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
diff --git a/arch/arm/include/asm/dma-mapping.h b/arch/arm/include/asm/dma-mapping.h
index 7b95d2058395..1cb8602dd9d5 100644
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/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.
@@ -249,108 +324,34 @@ 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
  * @handle: DMA address of buffer
@@ -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
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index 4ca751627489..5be016980c19 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -3,7 +3,6 @@
 
 #include <asm/hwcap.h>
 
-#ifndef __ASSEMBLY__
 /*
  * ELF register definitions..
  */
@@ -17,12 +16,34 @@ typedef unsigned long elf_freg_t[3];
 typedef elf_greg_t elf_gregset_t[ELF_NGREG];
 
 typedef struct user_fp elf_fpregset_t;
-#endif
 
 #define EM_ARM	40
-#define EF_ARM_APCS26 0x08
-#define EF_ARM_SOFT_FLOAT 0x200
-#define EF_ARM_EABI_MASK 0xFF000000
+
+#define EF_ARM_EABI_MASK	0xff000000
+#define EF_ARM_EABI_UNKNOWN	0x00000000
+#define EF_ARM_EABI_VER1	0x01000000
+#define EF_ARM_EABI_VER2	0x02000000
+#define EF_ARM_EABI_VER3	0x03000000
+#define EF_ARM_EABI_VER4	0x04000000
+#define EF_ARM_EABI_VER5	0x05000000
+
+#define EF_ARM_BE8		0x00800000	/* ABI 4,5 */
+#define EF_ARM_LE8		0x00400000	/* ABI 4,5 */
+#define EF_ARM_MAVERICK_FLOAT	0x00000800	/* ABI 0 */
+#define EF_ARM_VFP_FLOAT	0x00000400	/* ABI 0 */
+#define EF_ARM_SOFT_FLOAT	0x00000200	/* ABI 0 */
+#define EF_ARM_OLD_ABI		0x00000100	/* ABI 0 */
+#define EF_ARM_NEW_ABI		0x00000080	/* ABI 0 */
+#define EF_ARM_ALIGN8		0x00000040	/* ABI 0 */
+#define EF_ARM_PIC		0x00000020	/* ABI 0 */
+#define EF_ARM_MAPSYMSFIRST	0x00000010	/* ABI 2 */
+#define EF_ARM_APCS_FLOAT	0x00000010	/* ABI 0, floats in fp regs */
+#define EF_ARM_DYNSYMSUSESEGIDX	0x00000008	/* ABI 2 */
+#define EF_ARM_APCS_26		0x00000008	/* ABI 0 */
+#define EF_ARM_SYMSARESORTED	0x00000004	/* ABI 1,2 */
+#define EF_ARM_INTERWORK	0x00000004	/* ABI 0 */
+#define EF_ARM_HASENTRY		0x00000002	/* All */
+#define EF_ARM_RELEXEC		0x00000001	/* All */
 
 #define R_ARM_NONE	0
 #define R_ARM_PC24	1
@@ -41,7 +62,6 @@ typedef struct user_fp elf_fpregset_t;
 #endif
 #define ELF_ARCH	EM_ARM
 
-#ifndef __ASSEMBLY__
 /*
  * This yields a string that ld.so will use to load implementation
  * specific libraries for optimization.  This is more specific in
@@ -59,25 +79,17 @@ typedef struct user_fp elf_fpregset_t;
 #define ELF_PLATFORM	(elf_platform)
 
 extern char elf_platform[];
-#endif
 
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- */
-#define elf_check_arch(x) ((x)->e_machine == EM_ARM && ELF_PROC_OK(x))
+struct elf32_hdr;
 
 /*
- * 32-bit code is always OK.  Some cpus can do 26-bit, some can't.
+ * This is used to ensure we don't load something for the wrong architecture.
  */
-#define ELF_PROC_OK(x)	(ELF_THUMB_OK(x) && ELF_26BIT_OK(x))
-
-#define ELF_THUMB_OK(x) \
-	((elf_hwcap & HWCAP_THUMB && ((x)->e_entry & 1) == 1) || \
-	 ((x)->e_entry & 3) == 0)
+extern int elf_check_arch(const struct elf32_hdr *);
+#define elf_check_arch elf_check_arch
 
-#define ELF_26BIT_OK(x) \
-	((elf_hwcap & HWCAP_26BIT && (x)->e_flags & EF_ARM_APCS26) || \
-	  ((x)->e_flags & EF_ARM_APCS26) == 0)
+extern int arm_elf_read_implies_exec(const struct elf32_hdr *, int);
+#define elf_read_implies_exec(ex,stk) arm_elf_read_implies_exec(&(ex), stk)
 
 #define USE_ELF_CORE_DUMP
 #define ELF_EXEC_PAGESIZE	4096
@@ -94,23 +106,7 @@ extern char elf_platform[];
    have no such handler.  */
 #define ELF_PLAT_INIT(_r, load_addr)	(_r)->ARM_r0 = 0
 
-/*
- * Since the FPA coprocessor uses CP1 and CP2, and iWMMXt uses CP0
- * and CP1, we only enable access to the iWMMXt coprocessor if the
- * binary is EABI or softfloat (and thus, guaranteed not to use
- * FPA instructions.)
- */
-#define SET_PERSONALITY(ex, ibcs2)					\
-	do {								\
-		if ((ex).e_flags & EF_ARM_APCS26) {			\
-			set_personality(PER_LINUX);			\
-		} else {						\
-			set_personality(PER_LINUX_32BIT);		\
-			if (elf_hwcap & HWCAP_IWMMXT && (ex).e_flags & (EF_ARM_EABI_MASK | EF_ARM_SOFT_FLOAT)) \
-				set_thread_flag(TIF_USING_IWMMXT);	\
-			else						\
-				clear_thread_flag(TIF_USING_IWMMXT);	\
-		}							\
-	} while (0)
+extern void elf_set_personality(const struct elf32_hdr *);
+#define SET_PERSONALITY(ex, ibcs2)	elf_set_personality(&(ex))
 
 #endif
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 6a332a9f099c..9ee743b95de8 100644
--- a/arch/arm/include/asm/futex.h
+++ b/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 */
diff --git a/arch/arm/include/asm/io.h b/arch/arm/include/asm/io.h
index 71934856fc22..a8094451be57 100644
--- a/arch/arm/include/asm/io.h
+++ b/arch/arm/include/asm/io.h
@@ -60,10 +60,9 @@ extern void __raw_readsl(const void __iomem *addr, void *data, int longlen);
 #define MT_DEVICE		0
 #define MT_DEVICE_NONSHARED	1
 #define MT_DEVICE_CACHED	2
-#define MT_DEVICE_IXP2000	3
-#define MT_DEVICE_WC		4
+#define MT_DEVICE_WC		3
 /*
- * types 5 onwards can be found in asm/mach/map.h and are undefined
+ * types 4 onwards can be found in asm/mach/map.h and are undefined
  * for ioremap
  */
 
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index d6786090d02c..a0009aa5d157 100644
--- a/arch/arm/include/asm/irq.h
+++ b/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
diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h
index a5d0d99ad387..bb8a19bd5822 100644
--- a/arch/arm/include/asm/kprobes.h
+++ b/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);
diff --git a/arch/arm/include/asm/mach/map.h b/arch/arm/include/asm/mach/map.h
index 9eb936e49cc3..cb1139ac1943 100644
--- a/arch/arm/include/asm/mach/map.h
+++ b/arch/arm/include/asm/mach/map.h
@@ -18,16 +18,13 @@ struct map_desc {
 	unsigned int type;
 };
 
-/* types 0-4 are defined in asm/io.h */
-#define MT_CACHECLEAN		5
-#define MT_MINICLEAN		6
-#define MT_LOW_VECTORS		7
-#define MT_HIGH_VECTORS		8
-#define MT_MEMORY		9
-#define MT_ROM			10
-
-#define MT_NONSHARED_DEVICE	MT_DEVICE_NONSHARED
-#define MT_IXP2000_DEVICE	MT_DEVICE_IXP2000
+/* types 0-3 are defined in asm/io.h */
+#define MT_CACHECLEAN		4
+#define MT_MINICLEAN		5
+#define MT_LOW_VECTORS		6
+#define MT_HIGH_VECTORS		7
+#define MT_MEMORY		8
+#define MT_ROM			9
 
 #ifdef CONFIG_MMU
 extern void iotable_init(struct map_desc *, int);
diff --git a/arch/arm/include/asm/mach/udc_pxa2xx.h b/arch/arm/include/asm/mach/udc_pxa2xx.h
index 270902c353fd..f3eabf1ecec3 100644
--- a/arch/arm/include/asm/mach/udc_pxa2xx.h
+++ b/arch/arm/include/asm/mach/udc_pxa2xx.h
@@ -18,8 +18,7 @@ struct pxa2xx_udc_mach_info {
 	/* Boards following the design guidelines in the developer's manual,
 	 * with on-chip GPIOs not Lubbock's weird hardware, can have a sane
 	 * VBUS IRQ and omit the methods above.  Store the GPIO number
-	 * here; for GPIO 0, also mask in one of the pxa_gpio_mode() bits.
-	 * Note that sometimes the signals go through inverters...
+	 * here.  Note that sometimes the signals go through inverters...
 	 */
 	bool	gpio_vbus_inverted;
 	u16	gpio_vbus;			/* high == vbus present */
diff --git a/arch/arm/include/asm/mc146818rtc.h b/arch/arm/include/asm/mc146818rtc.h
index e1ca48a9e973..6b884d2b0b69 100644
--- a/arch/arm/include/asm/mc146818rtc.h
+++ b/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))
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index bf7c737c9226..809ff9ab853a 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -13,30 +13,27 @@
 #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.
@@ -44,13 +41,6 @@
 #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.
  */
@@ -147,17 +137,11 @@
 
 #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.
  *
diff --git a/arch/arm/include/asm/mmu_context.h b/arch/arm/include/asm/mmu_context.h
index a301e446007f..0559f37c2a27 100644
--- a/arch/arm/include/asm/mmu_context.h
+++ b/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>
 
diff --git a/arch/arm/include/asm/page.h b/arch/arm/include/asm/page.h
index cf2e2680daaa..bed1c0a00368 100644
--- a/arch/arm/include/asm/page.h
+++ b/arch/arm/include/asm/page.h
@@ -184,8 +184,9 @@ typedef struct page *pgtable_t;
 
 #endif /* !__ASSEMBLY__ */
 
-#define VM_DATA_DEFAULT_FLAGS	(VM_READ | VM_WRITE | VM_EXEC | \
-				 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
+#define VM_DATA_DEFAULT_FLAGS \
+	(((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \
+	 VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
 /*
  * With EABI on ARMv5 and above we must have 64-bit aligned slab pointers.
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index 8e21ef15bd74..110295c5461d 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -164,14 +164,30 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 #define L_PTE_PRESENT		(1 << 0)
 #define L_PTE_FILE		(1 << 1)	/* only when !PRESENT */
 #define L_PTE_YOUNG		(1 << 1)
-#define L_PTE_BUFFERABLE	(1 << 2)	/* matches PTE */
-#define L_PTE_CACHEABLE		(1 << 3)	/* matches PTE */
-#define L_PTE_USER		(1 << 4)
-#define L_PTE_WRITE		(1 << 5)
-#define L_PTE_EXEC		(1 << 6)
-#define L_PTE_DIRTY		(1 << 7)
+#define L_PTE_BUFFERABLE	(1 << 2)	/* obsolete, matches PTE */
+#define L_PTE_CACHEABLE		(1 << 3)	/* obsolete, matches PTE */
+#define L_PTE_DIRTY		(1 << 6)
+#define L_PTE_WRITE		(1 << 7)
+#define L_PTE_USER		(1 << 8)
+#define L_PTE_EXEC		(1 << 9)
 #define L_PTE_SHARED		(1 << 10)	/* shared(v6), coherent(xsc3) */
 
+/*
+ * These are the memory types, defined to be compatible with
+ * pre-ARMv6 CPUs cacheable and bufferable bits:   XXCB
+ */
+#define L_PTE_MT_UNCACHED	(0x00 << 2)	/* 0000 */
+#define L_PTE_MT_BUFFERABLE	(0x01 << 2)	/* 0001 */
+#define L_PTE_MT_WRITETHROUGH	(0x02 << 2)	/* 0010 */
+#define L_PTE_MT_WRITEBACK	(0x03 << 2)	/* 0011 */
+#define L_PTE_MT_MINICACHE	(0x06 << 2)	/* 0110 (sa1100, xscale) */
+#define L_PTE_MT_WRITEALLOC	(0x07 << 2)	/* 0111 */
+#define L_PTE_MT_DEV_SHARED	(0x04 << 2)	/* 0100 */
+#define L_PTE_MT_DEV_NONSHARED	(0x0c << 2)	/* 1100 */
+#define L_PTE_MT_DEV_WC		(0x09 << 2)	/* 1001 */
+#define L_PTE_MT_DEV_CACHED	(0x0b << 2)	/* 1011 */
+#define L_PTE_MT_MASK		(0x0f << 2)
+
 #ifndef __ASSEMBLY__
 
 /*
@@ -180,23 +196,30 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
  * as well as any architecture dependent bits like global/ASID and SMP
  * shared mapping bits.
  */
-#define _L_PTE_DEFAULT	L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_CACHEABLE | L_PTE_BUFFERABLE
-#define _L_PTE_READ	L_PTE_USER | L_PTE_EXEC
+#define _L_PTE_DEFAULT	L_PTE_PRESENT | L_PTE_YOUNG
 
 extern pgprot_t		pgprot_user;
 extern pgprot_t		pgprot_kernel;
 
-#define PAGE_NONE	pgprot_user
-#define PAGE_COPY	__pgprot(pgprot_val(pgprot_user) | _L_PTE_READ)
-#define PAGE_SHARED	__pgprot(pgprot_val(pgprot_user) | _L_PTE_READ | \
-				 L_PTE_WRITE)
-#define PAGE_READONLY	__pgprot(pgprot_val(pgprot_user) | _L_PTE_READ)
-#define PAGE_KERNEL	pgprot_kernel
-
-#define __PAGE_NONE	__pgprot(_L_PTE_DEFAULT)
-#define __PAGE_COPY	__pgprot(_L_PTE_DEFAULT | _L_PTE_READ)
-#define __PAGE_SHARED	__pgprot(_L_PTE_DEFAULT | _L_PTE_READ | L_PTE_WRITE)
-#define __PAGE_READONLY	__pgprot(_L_PTE_DEFAULT | _L_PTE_READ)
+#define _MOD_PROT(p, b)	__pgprot(pgprot_val(p) | (b))
+
+#define PAGE_NONE		pgprot_user
+#define PAGE_SHARED		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_WRITE)
+#define PAGE_SHARED_EXEC	_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_WRITE | L_PTE_EXEC)
+#define PAGE_COPY		_MOD_PROT(pgprot_user, L_PTE_USER)
+#define PAGE_COPY_EXEC		_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_EXEC)
+#define PAGE_READONLY		_MOD_PROT(pgprot_user, L_PTE_USER)
+#define PAGE_READONLY_EXEC	_MOD_PROT(pgprot_user, L_PTE_USER | L_PTE_EXEC)
+#define PAGE_KERNEL		pgprot_kernel
+#define PAGE_KERNEL_EXEC	_MOD_PROT(pgprot_kernel, L_PTE_EXEC)
+
+#define __PAGE_NONE		__pgprot(_L_PTE_DEFAULT)
+#define __PAGE_SHARED		__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_WRITE)
+#define __PAGE_SHARED_EXEC	__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_WRITE | L_PTE_EXEC)
+#define __PAGE_COPY		__pgprot(_L_PTE_DEFAULT | L_PTE_USER)
+#define __PAGE_COPY_EXEC	__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_EXEC)
+#define __PAGE_READONLY		__pgprot(_L_PTE_DEFAULT | L_PTE_USER)
+#define __PAGE_READONLY_EXEC	__pgprot(_L_PTE_DEFAULT | L_PTE_USER | L_PTE_EXEC)
 
 #endif /* __ASSEMBLY__ */
 
@@ -212,19 +235,19 @@ extern pgprot_t		pgprot_kernel;
 #define __P001  __PAGE_READONLY
 #define __P010  __PAGE_COPY
 #define __P011  __PAGE_COPY
-#define __P100  __PAGE_READONLY
-#define __P101  __PAGE_READONLY
-#define __P110  __PAGE_COPY
-#define __P111  __PAGE_COPY
+#define __P100  __PAGE_READONLY_EXEC
+#define __P101  __PAGE_READONLY_EXEC
+#define __P110  __PAGE_COPY_EXEC
+#define __P111  __PAGE_COPY_EXEC
 
 #define __S000  __PAGE_NONE
 #define __S001  __PAGE_READONLY
 #define __S010  __PAGE_SHARED
 #define __S011  __PAGE_SHARED
-#define __S100  __PAGE_READONLY
-#define __S101  __PAGE_READONLY
-#define __S110  __PAGE_SHARED
-#define __S111  __PAGE_SHARED
+#define __S100  __PAGE_READONLY_EXEC
+#define __S101  __PAGE_READONLY_EXEC
+#define __S110  __PAGE_SHARED_EXEC
+#define __S111  __PAGE_SHARED_EXEC
 
 #ifndef __ASSEMBLY__
 /*
@@ -286,8 +309,10 @@ static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
 /*
  * Mark the prot value as uncacheable and unbufferable.
  */
-#define pgprot_noncached(prot)	__pgprot(pgprot_val(prot) & ~(L_PTE_CACHEABLE | L_PTE_BUFFERABLE))
-#define pgprot_writecombine(prot) __pgprot(pgprot_val(prot) & ~L_PTE_CACHEABLE)
+#define pgprot_noncached(prot) \
+	__pgprot((pgprot_val(prot) & ~L_PTE_MT_MASK) | L_PTE_MT_UNCACHED)
+#define pgprot_writecombine(prot) \
+	__pgprot((pgprot_val(prot) & ~L_PTE_MT_MASK) | L_PTE_MT_BUFFERABLE)
 
 #define pmd_none(pmd)		(!pmd_val(pmd))
 #define pmd_present(pmd)	(pmd_val(pmd))
@@ -320,11 +345,6 @@ 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.
  */
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index b415c0e85458..73192618f1c2 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/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);
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index 7bbf105463f1..a65413ba121d 100644
--- a/arch/arm/include/asm/setup.h
+++ b/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.
  */
diff --git a/arch/arm/include/asm/sparsemem.h b/arch/arm/include/asm/sparsemem.h
index 277158191a0d..00098615c6f0 100644
--- a/arch/arm/include/asm/sparsemem.h
+++ b/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
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 514af792a598..7aad78420f18 100644
--- a/arch/arm/include/asm/system.h
+++ b/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)
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index e56fa48e4ae7..68b9ec82a37f 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/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))
 
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index d0f51ff900b5..e98ec60b3400 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/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"					\
diff --git a/arch/arm/include/asm/vga.h b/arch/arm/include/asm/vga.h
index 6a3cd2a2f670..250a4dd00630 100644
--- a/arch/arm/include/asm/vga.h
+++ b/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))