[ARM] Remove more reminants of 26-bit ARM support.

This removes include/asm-arm/proc-armv entirely, merging the
contents into the relevant include files in include/asm-arm.
We also update various files in arch/arm which reference
definitions in the now non-existent directory.

31 files changed, 1655 insertions, 1863 deletions

diff --git a/include/asm-arm/assembler.h b/include/asm-arm/assembler.h
index 677eedee6694..84ab93eb4643 100644
--- a/include/asm-arm/assembler.h
+++ b/include/asm-arm/assembler.h
@@ -1,18 +1,23 @@
 /*
- * linux/asm/assembler.h
+ *  linux/include/asm-arm/assembler.h
  *
- * This file contains arm architecture specific defines
- * for the different processors.
+ *  Copyright (C) 1996-2000 Russell King
  *
- * Do not include any C declarations in this file - it is included by
- * assembler source.
+ * 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.
+ *
+ *  This file contains arm architecture specific defines
+ *  for the different processors.
+ *
+ *  Do not include any C declarations in this file - it is included by
+ *  assembler source.
  */
 #ifndef __ASSEMBLY__
 #error "Only include this from assembly code"
 #endif
 
-#include <asm/proc/ptrace.h>
-#include <asm/proc/assembler.h>
+#include <asm/ptrace.h>
 
 /*
  * Endian independent macros for shifting bytes within registers.
@@ -36,3 +41,63 @@
 #define PLD(code...)
 #endif
 
+#define MODE_USR	USR_MODE
+#define MODE_FIQ	FIQ_MODE
+#define MODE_IRQ	IRQ_MODE
+#define MODE_SVC	SVC_MODE
+
+#define DEFAULT_FIQ	MODE_FIQ
+
+/*
+ * LOADREGS - ldm with PC in register list (eg, ldmfd sp!, {pc})
+ */
+#ifdef __STDC__
+#define LOADREGS(cond, base, reglist...)\
+	ldm##cond	base,reglist
+#else
+#define LOADREGS(cond, base, reglist...)\
+	ldm/**/cond	base,reglist
+#endif
+
+/*
+ * Build a return instruction for this processor type.
+ */
+#define RETINSTR(instr, regs...)\
+	instr	regs
+
+/*
+ * Save the current IRQ state and disable IRQs.  Note that this macro
+ * assumes FIQs are enabled, and that the processor is in SVC mode.
+ */
+	.macro	save_and_disable_irqs, oldcpsr, temp
+	mrs	\oldcpsr, cpsr
+	mov	\temp, #PSR_I_BIT | MODE_SVC
+	msr	cpsr_c, \temp
+	.endm
+
+/*
+ * Restore interrupt state previously stored in a register.  We don't
+ * guarantee that this will preserve the flags.
+ */
+	.macro	restore_irqs, oldcpsr
+	msr	cpsr_c, \oldcpsr
+	.endm
+
+/*
+ * These two are used to save LR/restore PC over a user-based access.
+ * The old 26-bit architecture requires that we do.  On 32-bit
+ * architecture, we can safely ignore this requirement.
+ */
+	.macro	save_lr
+	.endm
+
+	.macro	restore_pc
+	mov	pc, lr
+	.endm
+
+#define USER(x...)				\
+9999:	x;					\
+	.section __ex_table,"a";		\
+	.align	3;				\
+	.long	9999b,9001f;			\
+	.previous
diff --git a/include/asm-arm/atomic.h b/include/asm-arm/atomic.h
index ba9e4b72d821..e8e2cd1d69f1 100644
--- a/include/asm-arm/atomic.h
+++ b/include/asm-arm/atomic.h
@@ -27,7 +27,7 @@ typedef struct { volatile int counter; } atomic_t;
 #define ATOMIC_INIT(i)	{ (i) }
 
 #ifdef __KERNEL__
-#include <asm/proc/system.h>
+#include <asm/system.h>
 
 #define atomic_read(v)	((v)->counter)
 #define atomic_set(v,i)	(((v)->counter) = (i))
diff --git a/include/asm-arm/cacheflush.h b/include/asm-arm/cacheflush.h
index f5f2b2a3e199..30a47cba4d4b 100644
--- a/include/asm-arm/cacheflush.h
+++ b/include/asm-arm/cacheflush.h
@@ -1,7 +1,7 @@
 /*
  *  linux/include/asm-arm/cacheflush.h
  *
- *  Copyright (C) 2000-2002 Russell King
+ *  Copyright (C) 1999-2002 Russell King
  *
  * 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
@@ -12,6 +12,275 @@
 
 #include <linux/sched.h>
 #include <linux/mm.h>
-#include <asm/proc/cache.h>
+
+#include <asm/mman.h>
+#include <asm/glue.h>
+
+/*
+ *	Cache Model
+ *	===========
+ */
+#undef _CACHE
+#undef MULTI_CACHE
+
+#if defined(CONFIG_CPU_ARM610) || defined(CONFIG_CPU_ARM710)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE v3
+# endif
+#endif
+
+#if defined(CONFIG_CPU_ARM720T)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE v4
+# endif
+#endif
+
+#if defined(CONFIG_CPU_ARM920T) || defined(CONFIG_CPU_ARM922T) || \
+    defined(CONFIG_CPU_ARM1020)
+# define MULTI_CACHE 1
+#endif
+
+#if defined(CONFIG_CPU_ARM926T)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE arm926
+# endif
+#endif
+
+#if defined(CONFIG_CPU_SA110) || defined(CONFIG_CPU_SA1100)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE v4wb
+# endif
+#endif
+
+#if defined(CONFIG_CPU_XSCALE)
+# ifdef _CACHE
+#  define MULTI_CACHE 1
+# else
+#  define _CACHE xscale
+# endif
+#endif
+
+#if !defined(_CACHE) && !defined(MULTI_CACHE)
+#error Unknown cache maintainence model
+#endif
+
+/*
+ * This flag is used to indicate that the page pointed to by a pte
+ * is dirty and requires cleaning before returning it to the user.
+ */
+#define PG_dcache_dirty PG_arch_1
+
+/*
+ *	MM Cache Management
+ *	===================
+ *
+ *	The arch/arm/mm/cache-*.S and arch/arm/mm/proc-*.S files
+ *	implement these methods.
+ *
+ *	Start addresses are inclusive and end addresses are exclusive;
+ *	start addresses should be rounded down, end addresses up.
+ *
+ *	See linux/Documentation/cachetlb.txt for more information.
+ *	Please note that the implementation of these, and the required
+ *	effects are cache-type (VIVT/VIPT/PIPT) specific.
+ *
+ *	flush_cache_kern_all()
+ *
+ *		Unconditionally clean and invalidate the entire cache.
+ *
+ *	flush_cache_user_mm(mm)
+ *
+ *		Clean and invalidate all user space cache entries
+ *		before a change of page tables.
+ *
+ *	flush_cache_user_range(start, end, flags)
+ *
+ *		Clean and invalidate a range of cache entries in the
+ *		specified address space before a change of page tables.
+ *		- start - user start address (inclusive, page aligned)
+ *		- end   - user end address   (exclusive, page aligned)
+ *		- flags - vma->vm_flags field
+ *
+ *	coherent_kern_range(start, end)
+ *
+ *		Ensure coherency between the Icache and the Dcache in the
+ *		region described by start, end.  If you have non-snooping
+ *		Harvard caches, you need to implement this function.
+ *		- start  - virtual start address
+ *		- end    - virtual end address
+ *
+ *	DMA Cache Coherency
+ *	===================
+ *
+ *	dma_inv_range(start, end)
+ *
+ *		Invalidate (discard) the specified virtual address range.
+ *		May not write back any entries.  If 'start' or 'end'
+ *		are not cache line aligned, those lines must be written
+ *		back.
+ *		- start  - virtual start address
+ *		- end    - virtual end address
+ *
+ *	dma_clean_range(start, end)
+ *
+ *		Clean (write back) the specified virtual address range.
+ *		- start  - virtual start address
+ *		- end    - virtual end address
+ *
+ *	dma_flush_range(start, end)
+ *
+ *		Clean and invalidate the specified virtual address range.
+ *		- start  - virtual start address
+ *		- end    - virtual end address
+ */
+
+struct cpu_cache_fns {
+	void (*flush_kern_all)(void);
+	void (*flush_user_all)(void);
+	void (*flush_user_range)(unsigned long, unsigned long, unsigned int);
+
+	void (*coherent_kern_range)(unsigned long, unsigned long);
+	void (*flush_kern_dcache_page)(void *);
+
+	void (*dma_inv_range)(unsigned long, unsigned long);
+	void (*dma_clean_range)(unsigned long, unsigned long);
+	void (*dma_flush_range)(unsigned long, unsigned long);
+};
+
+/*
+ * Select the calling method
+ */
+#ifdef MULTI_CACHE
+
+extern struct cpu_cache_fns cpu_cache;
+
+#define __cpuc_flush_kern_all		cpu_cache.flush_kern_all
+#define __cpuc_flush_user_all		cpu_cache.flush_user_all
+#define __cpuc_flush_user_range		cpu_cache.flush_user_range
+#define __cpuc_coherent_kern_range	cpu_cache.coherent_kern_range
+#define __cpuc_flush_dcache_page	cpu_cache.flush_kern_dcache_page
+
+/*
+ * These are private to the dma-mapping API.  Do not use directly.
+ * Their sole purpose is to ensure that data held in the cache
+ * is visible to DMA, or data written by DMA to system memory is
+ * visible to the CPU.
+ */
+#define dmac_inv_range			cpu_cache.dma_inv_range
+#define dmac_clean_range		cpu_cache.dma_clean_range
+#define dmac_flush_range		cpu_cache.dma_flush_range
+
+#else
+
+#define __cpuc_flush_kern_all		__glue(_CACHE,_flush_kern_cache_all)
+#define __cpuc_flush_user_all		__glue(_CACHE,_flush_user_cache_all)
+#define __cpuc_flush_user_range		__glue(_CACHE,_flush_user_cache_range)
+#define __cpuc_coherent_kern_range	__glue(_CACHE,_coherent_kern_range)
+#define __cpuc_flush_dcache_page	__glue(_CACHE,_flush_kern_dcache_page)
+
+extern void __cpuc_flush_kern_all(void);
+extern void __cpuc_flush_user_all(void);
+extern void __cpuc_flush_user_range(unsigned long, unsigned long, unsigned int);
+extern void __cpuc_coherent_kern_range(unsigned long, unsigned long);
+extern void __cpuc_flush_dcache_page(void *);
+
+/*
+ * These are private to the dma-mapping API.  Do not use directly.
+ * Their sole purpose is to ensure that data held in the cache
+ * is visible to DMA, or data written by DMA to system memory is
+ * visible to the CPU.
+ */
+#define dmac_inv_range			__glue(_CACHE,_dma_inv_range)
+#define dmac_clean_range		__glue(_CACHE,_dma_clean_range)
+#define dmac_flush_range		__glue(_CACHE,_dma_flush_range)
+
+extern void dmac_inv_range(unsigned long, unsigned long);
+extern void dmac_clean_range(unsigned long, unsigned long);
+extern void dmac_flush_range(unsigned long, unsigned long);
+
+#endif
+
+/*
+ * Convert calls to our calling convention.
+ */
+#define flush_cache_all()		__cpuc_flush_kern_all()
+
+static inline void flush_cache_mm(struct mm_struct *mm)
+{
+	if (current->active_mm == mm)
+		__cpuc_flush_user_all();
+}
+
+static inline void
+flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
+{
+	if (current->active_mm == vma->vm_mm)
+		__cpuc_flush_user_range(start & PAGE_MASK, PAGE_ALIGN(end),
+					vma->vm_flags);
+}
+
+static inline void
+flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr)
+{
+	if (current->active_mm == vma->vm_mm) {
+		unsigned long addr = user_addr & PAGE_MASK;
+		__cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags);
+	}
+}
+
+/*
+ * Perform necessary cache operations to ensure that data previously
+ * stored within this range of addresses can be executed by the CPU.
+ */
+#define flush_icache_range(s,e)		__cpuc_coherent_kern_range(s,e)
+
+/*
+ * Perform necessary cache operations to ensure that the TLB will
+ * see data written in the specified area.
+ */
+#define clean_dcache_area(start,size)	cpu_dcache_clean_area(start, size)
+
+/*
+ * flush_dcache_page is used when the kernel has written to the page
+ * cache page at virtual address page->virtual.
+ *
+ * If this page isn't mapped (ie, page->mapping = NULL), or it has
+ * userspace mappings (page->mapping->i_mmap or page->mapping->i_mmap_shared)
+ * then we _must_ always clean + invalidate the dcache entries associated
+ * with the kernel mapping.
+ *
+ * Otherwise we can defer the operation, and clean the cache when we are
+ * about to change to user space.  This is the same method as used on SPARC64.
+ * See update_mmu_cache for the user space part.
+ */
+#define mapping_mapped(map)	(!list_empty(&(map)->i_mmap) || \
+				 !list_empty(&(map)->i_mmap_shared))
+
+extern void __flush_dcache_page(struct page *);
+
+static inline void flush_dcache_page(struct page *page)
+{
+	if (page->mapping && !mapping_mapped(page->mapping))
+		set_bit(PG_dcache_dirty, &page->flags);
+	else
+		__flush_dcache_page(page);
+}
+
+#define flush_icache_user_range(vma,page,addr,len) \
+	flush_dcache_page(page)
+
+/*
+ * We don't appear to need to do anything here.  In fact, if we did, we'd
+ * duplicate cache flushing elsewhere performed by flush_dcache_page().
+ */
+#define flush_icache_page(vma,page)	do { } while (0)
 
 #endif
diff --git a/include/asm-arm/proc-armv/domain.h b/include/asm-arm/domain.h
index 67f889162c31..87f9734a8a4a 100644
--- a/include/asm-arm/proc-armv/domain.h
+++ b/include/asm-arm/domain.h
@@ -1,5 +1,5 @@
 /*
- *  linux/include/asm-arm/proc-armv/domain.h
+ *  linux/include/asm-arm/domain.h
  *
  *  Copyright (C) 1999 Russell King.
  *
diff --git a/include/asm-arm/elf.h b/include/asm-arm/elf.h
index 536b2d6f2854..b67e06c0f588 100644
--- a/include/asm-arm/elf.h
+++ b/include/asm-arm/elf.h
@@ -7,7 +7,6 @@
 
 #include <asm/ptrace.h>
 #include <asm/user.h>
-#include <asm/proc/elf.h>
 #include <asm/procinfo.h>
 
 typedef unsigned long elf_greg_t;
@@ -42,6 +41,7 @@ typedef struct user_fp elf_fpregset_t;
 #define ELF_ARCH	EM_ARM
 
 #define USE_ELF_CORE_DUMP
+#define ELF_EXEC_PAGESIZE	4096
 
 /* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
    use of this is to invoke "./ld.so someprog" to test out a new version of
@@ -76,4 +76,29 @@ typedef struct user_fp elf_fpregset_t;
 extern char elf_platform[];
 #define ELF_PLATFORM	(elf_platform)
 
+#ifdef __KERNEL__
+
+/*
+ * 32-bit code is always OK.  Some cpus can do 26-bit, some can't.
+ */
+#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)
+
+#define ELF_26BIT_OK(x) \
+	(( (elf_hwcap & HWCAP_26BIT) && (x)->e_flags & EF_ARM_APCS26) || \
+	  ((x)->e_flags & EF_ARM_APCS26) == 0)
+
+/* Old NetWinder binaries were compiled in such a way that the iBCS
+   heuristic always trips on them.  Until these binaries become uncommon
+   enough not to care, don't trust the `ibcs' flag here.  In any case
+   there is no other ELF system currently supported by iBCS.
+   @@ Could print a warning message to encourage users to upgrade.  */
+#define SET_PERSONALITY(ex,ibcs2) \
+	set_personality(((ex).e_flags&EF_ARM_APCS26 ?PER_LINUX :PER_LINUX_32BIT))
+
+#endif
+
 #endif
diff --git a/include/asm-arm/proc-armv/locks.h b/include/asm-arm/locks.h
index 13248f903677..435ed505feda 100644
--- a/include/asm-arm/proc-armv/locks.h
+++ b/include/asm-arm/locks.h
@@ -1,5 +1,5 @@
 /*
- *  linux/include/asm-arm/proc-armv/locks.h
+ *  linux/include/asm-arm/locks.h
  *
  *  Copyright (C) 2000 Russell King
  *
diff --git a/include/asm-arm/memory.h b/include/asm-arm/memory.h
index 1b61a0e02c20..588c47d26338 100644
--- a/include/asm-arm/memory.h
+++ b/include/asm-arm/memory.h
@@ -15,6 +15,8 @@
 #include <linux/config.h>
 #include <asm/arch/memory.h>
 
+#ifndef __ASSEMBLY__
+
 /*
  * PFNs are used to describe any physical page; this means
  * PFN 0 == physical address 0.
@@ -120,3 +122,5 @@ static inline void *phys_to_virt(unsigned long x)
 #define page_to_bus(page)	(virt_to_bus(page_address(page)))
 
 #endif
+
+#endif
diff --git a/include/asm-arm/page.h b/include/asm-arm/page.h
index ca379e1f9184..94aeae2a4fb1 100644
--- a/include/asm-arm/page.h
+++ b/include/asm-arm/page.h
@@ -1,9 +1,27 @@
+/*
+ *  linux/include/asm-arm/page.h
+ *
+ *  Copyright (C) 1995-2003 Russell King
+ *
+ * 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 _ASMARM_PAGE_H
 #define _ASMARM_PAGE_H
 
 #include <linux/config.h>
 
+/* PAGE_SHIFT determines the page size */
+#define PAGE_SHIFT		12
+#define PAGE_SIZE		(1UL << PAGE_SHIFT)
+#define PAGE_MASK		(~(PAGE_SIZE-1))
+
 #ifdef __KERNEL__
+
+/* to align the pointer to the (next) page boundary */
+#define PAGE_ALIGN(addr)	(((addr)+PAGE_SIZE-1)&PAGE_MASK)
+
 #ifndef __ASSEMBLY__
 
 #include <asm/glue.h>
@@ -119,10 +137,12 @@ extern void copy_page(void *to, void *from);
  */
 typedef struct { unsigned long pte; } pte_t;
 typedef struct { unsigned long pmd; } pmd_t;
+typedef struct { unsigned long pgd[2]; } pgd_t;
 typedef struct { unsigned long pgprot; } pgprot_t;
 
 #define pte_val(x)      ((x).pte)
 #define pmd_val(x)      ((x).pmd)
+#define pgd_val(x)	((x).pgd[0])
 #define pgprot_val(x)   ((x).pgprot)
 
 #define __pte(x)        ((pte_t) { (x) } )
@@ -135,10 +155,12 @@ typedef struct { unsigned long pgprot; } pgprot_t;
  */
 typedef unsigned long pte_t;
 typedef unsigned long pmd_t;
+typedef unsigned long pgd_t[2];
 typedef unsigned long pgprot_t;
 
 #define pte_val(x)      (x)
 #define pmd_val(x)      (x)
+#define pgd_val(x)	((x)[0])
 #define pgprot_val(x)   (x)
 
 #define __pte(x)        (x)
@@ -146,19 +168,6 @@ typedef unsigned long pgprot_t;
 #define __pgprot(x)     (x)
 
 #endif /* STRICT_MM_TYPECHECKS */
-#endif /* !__ASSEMBLY__ */
-#endif /* __KERNEL__ */
-
-#include <asm/proc/page.h>
-
-#define PAGE_SIZE		(1UL << PAGE_SHIFT)
-#define PAGE_MASK		(~(PAGE_SIZE-1))
-
-/* to align the pointer to the (next) page boundary */
-#define PAGE_ALIGN(addr)	(((addr)+PAGE_SIZE-1)&PAGE_MASK)
-
-#ifdef __KERNEL__
-#ifndef __ASSEMBLY__
 
 /* Pure 2^n version of get_order */
 static inline int get_order(unsigned long size)
diff --git a/include/asm-arm/param.h b/include/asm-arm/param.h
index 2bf8b1d793f6..c1ccdcbe2bd1 100644
--- a/include/asm-arm/param.h
+++ b/include/asm-arm/param.h
@@ -11,7 +11,6 @@
 #define __ASM_PARAM_H
 
 #include <asm/arch/param.h>	/* for HZ */
-#include <asm/proc/page.h>	/* for EXEC_PAGE_SIZE */
 
 #ifndef __KERNEL_HZ
 #define __KERNEL_HZ	100
@@ -25,6 +24,8 @@
 # define HZ		100
 #endif
 
+#define EXEC_PAGESIZE	4096
+
 #ifndef NGROUPS
 #define NGROUPS         32
 #endif
diff --git a/include/asm-arm/pgalloc.h b/include/asm-arm/pgalloc.h
index 81a7eccf2991..23eb321f4af2 100644
--- a/include/asm-arm/pgalloc.h
+++ b/include/asm-arm/pgalloc.h
@@ -11,7 +11,8 @@
 #define _ASMARM_PGALLOC_H
 
 #include <asm/processor.h>
-#include <asm/proc/pgalloc.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
 
 /*
  * Since we have only two-level page tables, these are trivial
@@ -28,4 +29,104 @@ extern void free_pgd_slow(pgd_t *pgd);
 
 #define check_pgt_cache()		do { } while (0)
 
+/*
+ * Allocate one PTE table.
+ *
+ * This actually allocates two hardware PTE tables, but we wrap this up
+ * into one table thus:
+ *
+ *  +------------+
+ *  |  h/w pt 0  |
+ *  +------------+
+ *  |  h/w pt 1  |
+ *  +------------+
+ *  | Linux pt 0 |
+ *  +------------+
+ *  | Linux pt 1 |
+ *  +------------+
+ */
+static inline pte_t *
+pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
+{
+	pte_t *pte;
+
+	pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
+	if (pte) {
+		clear_page(pte);
+		clean_dcache_area(pte, sizeof(pte_t) * PTRS_PER_PTE);
+		pte += PTRS_PER_PTE;
+	}
+
+	return pte;
+}
+
+static inline struct page *
+pte_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	struct page *pte;
+
+	pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
+	if (pte) {
+		void *page = page_address(pte);
+		clear_page(page);
+		clean_dcache_area(page, sizeof(pte_t) * PTRS_PER_PTE);
+	}
+
+	return pte;
+}
+
+/*
+ * Free one PTE table.
+ */
+static inline void pte_free_kernel(pte_t *pte)
+{
+	if (pte) {
+		pte -= PTRS_PER_PTE;
+		free_page((unsigned long)pte);
+	}
+}
+
+static inline void pte_free(struct page *pte)
+{
+	__free_page(pte);
+}
+
+/*
+ * Populate the pmdp entry with a pointer to the pte.  This pmd is part
+ * of the mm address space.
+ *
+ * Ensure that we always set both PMD entries.
+ */
+static inline void
+pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep)
+{
+	unsigned long pte_ptr = (unsigned long)ptep;
+	unsigned long pmdval;
+
+	BUG_ON(mm != &init_mm);
+
+	/*
+	 * The pmd must be loaded with the physical
+	 * address of the PTE table
+	 */
+	pte_ptr -= PTRS_PER_PTE * sizeof(void *);
+	pmdval = __pa(pte_ptr) | _PAGE_KERNEL_TABLE;
+	pmdp[0] = __pmd(pmdval);
+	pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t));
+	flush_pmd_entry(pmdp);
+}
+
+static inline void
+pmd_populate(struct mm_struct *mm, pmd_t *pmdp, struct page *ptep)
+{
+	unsigned long pmdval;
+
+	BUG_ON(mm == &init_mm);
+
+	pmdval = page_to_pfn(ptep) << PAGE_SHIFT | _PAGE_USER_TABLE;
+	pmdp[0] = __pmd(pmdval);
+	pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t));
+	flush_pmd_entry(pmdp);
+}
+
 #endif
diff --git a/include/asm-arm/pgtable.h b/include/asm-arm/pgtable.h
index e2ed74082ae1..473b238e6fbc 100644
--- a/include/asm-arm/pgtable.h
+++ b/include/asm-arm/pgtable.h
@@ -1,7 +1,7 @@
 /*
  *  linux/include/asm-arm/pgtable.h
  *
- *  Copyright (C) 2000-2002 Russell King
+ *  Copyright (C) 1995-2002 Russell King
  *
  * 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
@@ -16,15 +16,24 @@
 #include <asm/arch/vmalloc.h>
 
 /*
+ * We pull a couple of tricks here:
+ *  1. We wrap the PMD into the PGD.
+ *  2. We lie about the size of the PTE and PGD.
+ * Even though we have 256 PTE entries and 4096 PGD entries, we tell
+ * Linux that we actually have 512 PTE entries and 2048 PGD entries.
+ * Each "Linux" PGD entry is made up of two hardware PGD entries, and
+ * each PTE table is actually two hardware PTE tables.
+ */
+#define PTRS_PER_PTE		512
+#define PTRS_PER_PMD		1
+#define PTRS_PER_PGD		2048
+
+/*
  * PMD_SHIFT determines the size of the area a second-level page table can map
  * PGDIR_SHIFT determines what a third-level page table entry can map
  */
 #define PMD_SHIFT		20
-#ifdef CONFIG_CPU_32
 #define PGDIR_SHIFT		21
-#else
-#define PGDIR_SHIFT		20
-#endif
 
 #define LIBRARY_TEXT_START	0x0c000000
 
@@ -47,6 +56,117 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 #define USER_PTRS_PER_PGD	((TASK_SIZE/PGDIR_SIZE) - FIRST_USER_PGD_NR)
 
 /*
+ * Hardware page table definitions.
+ *
+ * + Level 1 descriptor (PMD)
+ *   - common
+ */
+#define PMD_TYPE_MASK		(3 << 0)
+#define PMD_TYPE_FAULT		(0 << 0)
+#define PMD_TYPE_TABLE		(1 << 0)
+#define PMD_TYPE_SECT		(2 << 0)
+#define PMD_BIT4		(1 << 4)
+#define PMD_DOMAIN(x)		((x) << 5)
+#define PMD_PROTECTION		(1 << 9)	/* v5 */
+/*
+ *   - section
+ */
+#define PMD_SECT_BUFFERABLE	(1 << 2)
+#define PMD_SECT_CACHEABLE	(1 << 3)
+#define PMD_SECT_AP_WRITE	(1 << 10)
+#define PMD_SECT_AP_READ	(1 << 11)
+#define PMD_SECT_TEX(x)		((x) << 12)	/* v5 */
+#define PMD_SECT_APX		(1 << 15)	/* v6 */
+#define PMD_SECT_S		(1 << 16)	/* v6 */
+#define PMD_SECT_nG		(1 << 17)	/* v6 */
+
+#define PMD_SECT_UNCACHED	(0)
+#define PMD_SECT_BUFFERED	(PMD_SECT_BUFFERABLE)
+#define PMD_SECT_WT		(PMD_SECT_CACHEABLE)
+#define PMD_SECT_WB		(PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
+#define PMD_SECT_MINICACHE	(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE)
+#define PMD_SECT_WBWA		(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
+
+/*
+ *   - coarse table (not used)
+ */
+
+/*
+ * + Level 2 descriptor (PTE)
+ *   - common
+ */
+#define PTE_TYPE_MASK		(3 << 0)
+#define PTE_TYPE_FAULT		(0 << 0)
+#define PTE_TYPE_LARGE		(1 << 0)
+#define PTE_TYPE_SMALL		(2 << 0)
+#define PTE_TYPE_EXT		(3 << 0)	/* v5 */
+#define PTE_BUFFERABLE		(1 << 2)
+#define PTE_CACHEABLE		(1 << 3)
+
+/*
+ *   - extended small page/tiny page
+ */
+#define PTE_EXT_AP_UNO_SRO	(0 << 4)
+#define PTE_EXT_AP_UNO_SRW	(1 << 4)
+#define PTE_EXT_AP_URO_SRW	(2 << 4)
+#define PTE_EXT_AP_URW_SRW	(3 << 4)
+#define PTE_EXT_TEX(x)		((x) << 6)	/* v5 */
+
+/*
+ *   - small page
+ */
+#define PTE_SMALL_AP_UNO_SRO	(0x00 << 4)
+#define PTE_SMALL_AP_UNO_SRW	(0x55 << 4)
+#define PTE_SMALL_AP_URO_SRW	(0xaa << 4)
+#define PTE_SMALL_AP_URW_SRW	(0xff << 4)
+#define PTE_AP_READ		PTE_SMALL_AP_URO_SRW
+#define PTE_AP_WRITE		PTE_SMALL_AP_UNO_SRW
+
+/*
+ * "Linux" PTE definitions.
+ *
+ * We keep two sets of PTEs - the hardware and the linux version.
+ * This allows greater flexibility in the way we map the Linux bits
+ * onto the hardware tables, and allows us to have YOUNG and DIRTY
+ * bits.
+ *
+ * The PTE table pointer refers to the hardware entries; the "Linux"
+ * entries are stored 1024 bytes below.
+ */
+#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)
+
+#ifndef __ASSEMBLY__
+
+#include <asm/domain.h>
+
+#define _PAGE_USER_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_USER))
+#define _PAGE_KERNEL_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_KERNEL))
+
+/*
+ * The following macros handle the cache and bufferable bits...
+ */
+#define _L_PTE_DEFAULT	L_PTE_PRESENT | L_PTE_YOUNG
+#define _L_PTE_READ	L_PTE_USER | L_PTE_EXEC | L_PTE_CACHEABLE | L_PTE_BUFFERABLE
+
+#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 PAGE_KERNEL     __pgprot(_L_PTE_DEFAULT | L_PTE_CACHEABLE | L_PTE_BUFFERABLE | L_PTE_DIRTY | L_PTE_WRITE | L_PTE_EXEC)
+
+#define _PAGE_CHG_MASK	(PAGE_MASK | L_PTE_DIRTY | L_PTE_YOUNG)
+
+#endif /* __ASSEMBLY__ */
+
+/*
  * The table below defines the page protection levels that we insert into our
  * Linux page table version.  These get translated into the best that the
  * architecture can perform.  Note that on most ARM hardware:
@@ -86,9 +206,82 @@ extern struct page *empty_zero_page;
 #define pte_none(pte)		(!pte_val(pte))
 #define pte_clear(ptep)		set_pte((ptep), __pte(0))
 #define pte_page(pte)		(pfn_to_page(pte_pfn(pte)))
+#define pte_offset_kernel(dir,addr)	(pmd_page_kernel(*(dir)) + __pte_index(addr))
+#define pte_offset_map(dir,addr)	(pmd_page_kernel(*(dir)) + __pte_index(addr))
+#define pte_offset_map_nested(dir,addr)	(pmd_page_kernel(*(dir)) + __pte_index(addr))
+#define pte_unmap(pte)		do { } while (0)
+#define pte_unmap_nested(pte)	do { } while (0)
+
+#define set_pte(ptep, pte)	cpu_set_pte(ptep,pte)
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+#define pte_present(pte)	(pte_val(pte) & L_PTE_PRESENT)
+#define pte_read(pte)		(pte_val(pte) & L_PTE_USER)
+#define pte_write(pte)		(pte_val(pte) & L_PTE_WRITE)
+#define pte_exec(pte)		(pte_val(pte) & L_PTE_EXEC)
+#define pte_dirty(pte)		(pte_val(pte) & L_PTE_DIRTY)
+#define pte_young(pte)		(pte_val(pte) & L_PTE_YOUNG)
+
+/*
+ * The following only works if pte_present() is not true.
+ */
+#define pte_file(pte)		(pte_val(pte) & L_PTE_FILE)
+#define pte_to_pgoff(x)		(pte_val(x) >> 2)
+#define pgoff_to_pte(x)		__pte(((x) << 2) | L_PTE_FILE)
+
+#define PTE_FILE_MAX_BITS	30
+
+#define PTE_BIT_FUNC(fn,op) \
+static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
+
+/*PTE_BIT_FUNC(rdprotect, &= ~L_PTE_USER);*/
+/*PTE_BIT_FUNC(mkread,    |= L_PTE_USER);*/
+PTE_BIT_FUNC(wrprotect, &= ~L_PTE_WRITE);
+PTE_BIT_FUNC(mkwrite,   |= L_PTE_WRITE);
+PTE_BIT_FUNC(exprotect, &= ~L_PTE_EXEC);
+PTE_BIT_FUNC(mkexec,    |= L_PTE_EXEC);
+PTE_BIT_FUNC(mkclean,   &= ~L_PTE_DIRTY);
+PTE_BIT_FUNC(mkdirty,   |= L_PTE_DIRTY);
+PTE_BIT_FUNC(mkold,     &= ~L_PTE_YOUNG);
+PTE_BIT_FUNC(mkyoung,   |= L_PTE_YOUNG);
+
+/*
+ * 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 pmd_none(pmd)		(!pmd_val(pmd))
 #define pmd_present(pmd)	(pmd_val(pmd))
+#define pmd_bad(pmd)		(pmd_val(pmd) & 2)
+
+#define set_pmd(pmdp,pmd)		\
+	do {				\
+		*pmdp = pmd;		\
+		flush_pmd_entry(pmdp);	\
+	} while (0)
+
+#define pmd_clear(pmdp)			\
+	do {				\
+		pmdp[0] = __pmd(0);	\
+		pmdp[1] = __pmd(0);	\
+		clean_pmd_entry(pmdp);	\
+	} while (0)
+
+static inline pte_t *pmd_page_kernel(pmd_t pmd)
+{
+	unsigned long ptr;
+
+	ptr = pmd_val(pmd) & ~(PTRS_PER_PTE * sizeof(void *) - 1);
+	ptr += PTRS_PER_PTE * sizeof(void *);
+
+	return __va(ptr);
+}
+
+#define pmd_page(pmd) virt_to_page(__va(pmd_val(pmd)))
 
 /*
  * Permanent address of a page. We never have highmem, so this is trivial.
@@ -129,8 +322,6 @@ extern struct page *empty_zero_page;
 /* Find an entry in the third-level page table.. */
 #define __pte_index(addr)	(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
 
-#include <asm/proc/pgtable.h>
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	pte_val(pte) = (pte_val(pte) & _PAGE_CHG_MASK) | pgprot_val(newprot);
@@ -164,6 +355,8 @@ extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
 
 typedef pte_t *pte_addr_t;
 
+#define pgtable_cache_init() do { } while (0)
+
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASMARM_PGTABLE_H */
diff --git a/include/asm-arm/proc-armv/assembler.h b/include/asm-arm/proc-armv/assembler.h
deleted file mode 100644
index 64916c820b33..000000000000
--- a/include/asm-arm/proc-armv/assembler.h
+++ /dev/null
@@ -1,74 +0,0 @@
-/*
- *  linux/asm-arm/proc-armv/assembler.h
- *
- *  Copyright (C) 1996-2000 Russell King
- *
- * 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.
- *
- *  This file contains ARM processor specifics for
- *  the ARM6 and better processors.
- */
-#define MODE_USR	USR_MODE
-#define MODE_FIQ	FIQ_MODE
-#define MODE_IRQ	IRQ_MODE
-#define MODE_SVC	SVC_MODE
-
-#define DEFAULT_FIQ	MODE_FIQ
-
-/*
- * LOADREGS - ldm with PC in register list (eg, ldmfd sp!, {pc})
- */
-#ifdef __STDC__
-#define LOADREGS(cond, base, reglist...)\
-	ldm##cond	base,reglist
-#else
-#define LOADREGS(cond, base, reglist...)\
-	ldm/**/cond	base,reglist
-#endif
-
-/*
- * Build a return instruction for this processor type.
- */
-#define RETINSTR(instr, regs...)\
-	instr	regs
-
-/*
- * Save the current IRQ state and disable IRQs.  Note that this macro
- * assumes FIQs are enabled, and that the processor is in SVC mode.
- */
-	.macro	save_and_disable_irqs, oldcpsr, temp
-	mrs	\oldcpsr, cpsr
-	mov	\temp, #PSR_I_BIT | MODE_SVC
-	msr	cpsr_c, \temp
-	.endm
-
-/*
- * Restore interrupt state previously stored in a register.  We don't
- * guarantee that this will preserve the flags.
- */
-	.macro	restore_irqs, oldcpsr
-	msr	cpsr_c, \oldcpsr
-	.endm
-
-/*
- * These two are used to save LR/restore PC over a user-based access.
- * The old 26-bit architecture requires that we do.  On 32-bit
- * architecture, we can safely ignore this requirement.
- */
-	.macro	save_lr
-	.endm
-
-	.macro	restore_pc
-	mov	pc, lr
-	.endm
-
-#define USER(x...)				\
-9999:	x;					\
-	.section __ex_table,"a";		\
-	.align	3;				\
-	.long	9999b,9001f;			\
-	.previous
-
-
diff --git a/include/asm-arm/proc-armv/cache.h b/include/asm-arm/proc-armv/cache.h
deleted file mode 100644
index 250a69e335ff..000000000000
--- a/include/asm-arm/proc-armv/cache.h
+++ /dev/null
@@ -1,278 +0,0 @@
-/*
- *  linux/include/asm-arm/proc-armv/cache.h
- *
- *  Copyright (C) 1999-2002 Russell King
- *
- * 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.
- */
-#include <asm/mman.h>
-#include <asm/glue.h>
-
-/*
- *	Cache Model
- *	===========
- */
-#undef _CACHE
-#undef MULTI_CACHE
-
-#if defined(CONFIG_CPU_ARM610) || defined(CONFIG_CPU_ARM710)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE v3
-# endif
-#endif
-
-#if defined(CONFIG_CPU_ARM720T)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE v4
-# endif
-#endif
-
-#if defined(CONFIG_CPU_ARM920T) || defined(CONFIG_CPU_ARM922T) || \
-    defined(CONFIG_CPU_ARM1020)
-# define MULTI_CACHE 1
-#endif
-
-#if defined(CONFIG_CPU_ARM926T)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE arm926
-# endif
-#endif
-
-#if defined(CONFIG_CPU_SA110) || defined(CONFIG_CPU_SA1100)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE v4wb
-# endif
-#endif
-
-#if defined(CONFIG_CPU_XSCALE)
-# ifdef _CACHE
-#  define MULTI_CACHE 1
-# else
-#  define _CACHE xscale
-# endif
-#endif
-
-#if !defined(_CACHE) && !defined(MULTI_CACHE)
-#error Unknown cache maintainence model
-#endif
-
-/*
- * This flag is used to indicate that the page pointed to by a pte
- * is dirty and requires cleaning before returning it to the user.
- */
-#define PG_dcache_dirty PG_arch_1
-
-/*
- *	MM Cache Management
- *	===================
- *
- *	The arch/arm/mm/cache-*.S and arch/arm/mm/proc-*.S files
- *	implement these methods.
- *
- *	Start addresses are inclusive and end addresses are exclusive;
- *	start addresses should be rounded down, end addresses up.
- *
- *	See linux/Documentation/cachetlb.txt for more information.
- *	Please note that the implementation of these, and the required
- *	effects are cache-type (VIVT/VIPT/PIPT) specific.
- *
- *	flush_cache_kern_all()
- *
- *		Unconditionally clean and invalidate the entire cache.
- *
- *	flush_cache_user_mm(mm)
- *
- *		Clean and invalidate all user space cache entries
- *		before a change of page tables.
- *
- *	flush_cache_user_range(start, end, flags)
- *
- *		Clean and invalidate a range of cache entries in the
- *		specified address space before a change of page tables.
- *		- start - user start address (inclusive, page aligned)
- *		- end   - user end address   (exclusive, page aligned)
- *		- flags - vma->vm_flags field
- *
- *	coherent_kern_range(start, end)
- *
- *		Ensure coherency between the Icache and the Dcache in the
- *		region described by start, end.  If you have non-snooping
- *		Harvard caches, you need to implement this function.
- *		- start  - virtual start address
- *		- end    - virtual end address
- *
- *	DMA Cache Coherency
- *	===================
- *
- *	dma_inv_range(start, end)
- *
- *		Invalidate (discard) the specified virtual address range.
- *		May not write back any entries.  If 'start' or 'end'
- *		are not cache line aligned, those lines must be written
- *		back.
- *		- start  - virtual start address
- *		- end    - virtual end address
- *
- *	dma_clean_range(start, end)
- *
- *		Clean (write back) the specified virtual address range.
- *		- start  - virtual start address
- *		- end    - virtual end address
- *
- *	dma_flush_range(start, end)
- *
- *		Clean and invalidate the specified virtual address range.
- *		- start  - virtual start address
- *		- end    - virtual end address
- */
-
-struct cpu_cache_fns {
-	void (*flush_kern_all)(void);
-	void (*flush_user_all)(void);
-	void (*flush_user_range)(unsigned long, unsigned long, unsigned int);
-
-	void (*coherent_kern_range)(unsigned long, unsigned long);
-	void (*flush_kern_dcache_page)(void *);
-
-	void (*dma_inv_range)(unsigned long, unsigned long);
-	void (*dma_clean_range)(unsigned long, unsigned long);
-	void (*dma_flush_range)(unsigned long, unsigned long);
-};
-
-/*
- * Select the calling method
- */
-#ifdef MULTI_CACHE
-
-extern struct cpu_cache_fns cpu_cache;
-
-#define __cpuc_flush_kern_all		cpu_cache.flush_kern_all
-#define __cpuc_flush_user_all		cpu_cache.flush_user_all
-#define __cpuc_flush_user_range		cpu_cache.flush_user_range
-#define __cpuc_coherent_kern_range	cpu_cache.coherent_kern_range
-#define __cpuc_flush_dcache_page	cpu_cache.flush_kern_dcache_page
-
-/*
- * These are private to the dma-mapping API.  Do not use directly.
- * Their sole purpose is to ensure that data held in the cache
- * is visible to DMA, or data written by DMA to system memory is
- * visible to the CPU.
- */
-#define dmac_inv_range			cpu_cache.dma_inv_range
-#define dmac_clean_range		cpu_cache.dma_clean_range
-#define dmac_flush_range		cpu_cache.dma_flush_range
-
-#else
-
-#define __cpuc_flush_kern_all		__glue(_CACHE,_flush_kern_cache_all)
-#define __cpuc_flush_user_all		__glue(_CACHE,_flush_user_cache_all)
-#define __cpuc_flush_user_range		__glue(_CACHE,_flush_user_cache_range)
-#define __cpuc_coherent_kern_range	__glue(_CACHE,_coherent_kern_range)
-#define __cpuc_flush_dcache_page	__glue(_CACHE,_flush_kern_dcache_page)
-
-extern void __cpuc_flush_kern_all(void);
-extern void __cpuc_flush_user_all(void);
-extern void __cpuc_flush_user_range(unsigned long, unsigned long, unsigned int);
-extern void __cpuc_coherent_kern_range(unsigned long, unsigned long);
-extern void __cpuc_flush_dcache_page(void *);
-
-/*
- * These are private to the dma-mapping API.  Do not use directly.
- * Their sole purpose is to ensure that data held in the cache
- * is visible to DMA, or data written by DMA to system memory is
- * visible to the CPU.
- */
-#define dmac_inv_range			__glue(_CACHE,_dma_inv_range)
-#define dmac_clean_range		__glue(_CACHE,_dma_clean_range)
-#define dmac_flush_range		__glue(_CACHE,_dma_flush_range)
-
-extern void dmac_inv_range(unsigned long, unsigned long);
-extern void dmac_clean_range(unsigned long, unsigned long);
-extern void dmac_flush_range(unsigned long, unsigned long);
-
-#endif
-
-/*
- * Convert calls to our calling convention.
- */
-#define flush_cache_all()		__cpuc_flush_kern_all()
-
-static inline void flush_cache_mm(struct mm_struct *mm)
-{
-	if (current->active_mm == mm)
-		__cpuc_flush_user_all();
-}
-
-static inline void
-flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
-{
-	if (current->active_mm == vma->vm_mm)
-		__cpuc_flush_user_range(start & PAGE_MASK, PAGE_ALIGN(end),
-					vma->vm_flags);
-}
-
-static inline void
-flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr)
-{
-	if (current->active_mm == vma->vm_mm) {
-		unsigned long addr = user_addr & PAGE_MASK;
-		__cpuc_flush_user_range(addr, addr + PAGE_SIZE, vma->vm_flags);
-	}
-}
-
-/*
- * Perform necessary cache operations to ensure that data previously
- * stored within this range of addresses can be executed by the CPU.
- */
-#define flush_icache_range(s,e)		__cpuc_coherent_kern_range(s,e)
-
-/*
- * Perform necessary cache operations to ensure that the TLB will
- * see data written in the specified area.
- */
-#define clean_dcache_area(start,size)	cpu_dcache_clean_area(start, size)
-
-/*
- * flush_dcache_page is used when the kernel has written to the page
- * cache page at virtual address page->virtual.
- *
- * If this page isn't mapped (ie, page->mapping = NULL), or it has
- * userspace mappings (page->mapping->i_mmap or page->mapping->i_mmap_shared)
- * then we _must_ always clean + invalidate the dcache entries associated
- * with the kernel mapping.
- *
- * Otherwise we can defer the operation, and clean the cache when we are
- * about to change to user space.  This is the same method as used on SPARC64.
- * See update_mmu_cache for the user space part.
- */
-#define mapping_mapped(map)	(!list_empty(&(map)->i_mmap) || \
-				 !list_empty(&(map)->i_mmap_shared))
-
-extern void __flush_dcache_page(struct page *);
-
-static inline void flush_dcache_page(struct page *page)
-{
-	if (page->mapping && !mapping_mapped(page->mapping))
-		set_bit(PG_dcache_dirty, &page->flags);
-	else
-		__flush_dcache_page(page);
-}
-
-#define flush_icache_user_range(vma,page,addr,len) \
-	flush_dcache_page(page)
-
-/*
- * We don't appear to need to do anything here.  In fact, if we did, we'd
- * duplicate cache flushing elsewhere performed by flush_dcache_page().
- */
-#define flush_icache_page(vma,page)	do { } while (0)
diff --git a/include/asm-arm/proc-armv/elf.h b/include/asm-arm/proc-armv/elf.h
deleted file mode 100644
index 1b8a0ac3b2b5..000000000000
--- a/include/asm-arm/proc-armv/elf.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * ELF definitions for 32-bit CPUs
- */
-
-#define ELF_EXEC_PAGESIZE	4096
-
-#ifdef __KERNEL__
-
-/*
- * 32-bit code is always OK.  Some cpus can do 26-bit, some can't.
- */
-#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)
-
-#define ELF_26BIT_OK(x) \
-	(( (elf_hwcap & HWCAP_26BIT) && (x)->e_flags & EF_ARM_APCS26) || \
-	  ((x)->e_flags & EF_ARM_APCS26) == 0)
-
-/* Old NetWinder binaries were compiled in such a way that the iBCS
-   heuristic always trips on them.  Until these binaries become uncommon
-   enough not to care, don't trust the `ibcs' flag here.  In any case
-   there is no other ELF system currently supported by iBCS.
-   @@ Could print a warning message to encourage users to upgrade.  */
-#define SET_PERSONALITY(ex,ibcs2) \
-	set_personality(((ex).e_flags&EF_ARM_APCS26 ?PER_LINUX :PER_LINUX_32BIT))
-
-#endif
diff --git a/include/asm-arm/proc-armv/page.h b/include/asm-arm/proc-armv/page.h
deleted file mode 100644
index 726b16df7195..000000000000
--- a/include/asm-arm/proc-armv/page.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/*
- *  linux/include/asm-arm/proc-armv/page.h
- *
- *  Copyright (C) 1995-2002 Russell King
- *
- * 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 __ASM_PROC_PAGE_H
-#define __ASM_PROC_PAGE_H
-
-/* PAGE_SHIFT determines the page size */
-#define PAGE_SHIFT	12
-
-#define EXEC_PAGESIZE   4096
-
-#ifndef __ASSEMBLY__
-#ifdef STRICT_MM_TYPECHECKS
-
-typedef struct {
-	unsigned long pgd0;
-	unsigned long pgd1;
-} pgd_t;
-
-#define pgd_val(x)	((x).pgd0)
-
-#else
-
-typedef unsigned long pgd_t[2];
-
-#define pgd_val(x)	((x)[0])
-
-#endif
-#endif /* __ASSEMBLY__ */
-
-#endif /* __ASM_PROC_PAGE_H */
diff --git a/include/asm-arm/proc-armv/pgalloc.h b/include/asm-arm/proc-armv/pgalloc.h
deleted file mode 100644
index 0e65ab7362e4..000000000000
--- a/include/asm-arm/proc-armv/pgalloc.h
+++ /dev/null
@@ -1,110 +0,0 @@
-/*
- *  linux/include/asm-arm/proc-armv/pgalloc.h
- *
- *  Copyright (C) 2001-2002 Russell King
- *
- * Page table allocation/freeing primitives for 32-bit ARM processors.
- */
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
-#include "pgtable.h"
-
-/*
- * Allocate one PTE table.
- *
- * This actually allocates two hardware PTE tables, but we wrap this up
- * into one table thus:
- *
- *  +------------+
- *  |  h/w pt 0  |
- *  +------------+
- *  |  h/w pt 1  |
- *  +------------+
- *  | Linux pt 0 |
- *  +------------+
- *  | Linux pt 1 |
- *  +------------+
- */
-static inline pte_t *
-pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
-{
-	pte_t *pte;
-
-	pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_REPEAT);
-	if (pte) {
-		clear_page(pte);
-		clean_dcache_area(pte, sizeof(pte_t) * PTRS_PER_PTE);
-		pte += PTRS_PER_PTE;
-	}
-
-	return pte;
-}
-
-static inline struct page *
-pte_alloc_one(struct mm_struct *mm, unsigned long addr)
-{
-	struct page *pte;
-
-	pte = alloc_pages(GFP_KERNEL|__GFP_REPEAT, 0);
-	if (pte) {
-		void *page = page_address(pte);
-		clear_page(page);
-		clean_dcache_area(page, sizeof(pte_t) * PTRS_PER_PTE);
-	}
-
-	return pte;
-}
-
-/*
- * Free one PTE table.
- */
-static inline void pte_free_kernel(pte_t *pte)
-{
-	if (pte) {
-		pte -= PTRS_PER_PTE;
-		free_page((unsigned long)pte);
-	}
-}
-
-static inline void pte_free(struct page *pte)
-{
-	__free_page(pte);
-}
-
-/*
- * Populate the pmdp entry with a pointer to the pte.  This pmd is part
- * of the mm address space.
- *
- * Ensure that we always set both PMD entries.
- */
-static inline void
-pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep)
-{
-	unsigned long pte_ptr = (unsigned long)ptep;
-	unsigned long pmdval;
-
-	BUG_ON(mm != &init_mm);
-
-	/*
-	 * The pmd must be loaded with the physical
-	 * address of the PTE table
-	 */
-	pte_ptr -= PTRS_PER_PTE * sizeof(void *);
-	pmdval = __pa(pte_ptr) | _PAGE_KERNEL_TABLE;
-	pmdp[0] = __pmd(pmdval);
-	pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t));
-	flush_pmd_entry(pmdp);
-}
-
-static inline void
-pmd_populate(struct mm_struct *mm, pmd_t *pmdp, struct page *ptep)
-{
-	unsigned long pmdval;
-
-	BUG_ON(mm == &init_mm);
-
-	pmdval = page_to_pfn(ptep) << PAGE_SHIFT | _PAGE_USER_TABLE;
-	pmdp[0] = __pmd(pmdval);
-	pmdp[1] = __pmd(pmdval + 256 * sizeof(pte_t));
-	flush_pmd_entry(pmdp);
-}
diff --git a/include/asm-arm/proc-armv/pgtable.h b/include/asm-arm/proc-armv/pgtable.h
deleted file mode 100644
index 4b1cb65443ae..000000000000
--- a/include/asm-arm/proc-armv/pgtable.h
+++ /dev/null
@@ -1,217 +0,0 @@
-/*
- *  linux/include/asm-arm/proc-armv/pgtable.h
- *
- *  Copyright (C) 1995-2002 Russell King
- *
- * 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.
- *
- *  12-Jan-1997	RMK	Altered flushing routines to use function pointers
- *			now possible to combine ARM6, ARM7 and StrongARM versions.
- *  17-Apr-1999	RMK	Now pass an area size to clean_cache_area and
- *			flush_icache_area.
- */
-#ifndef __ASM_PROC_PGTABLE_H
-#define __ASM_PROC_PGTABLE_H
-
-/*
- * We pull a couple of tricks here:
- *  1. We wrap the PMD into the PGD.
- *  2. We lie about the size of the PTE and PGD.
- * Even though we have 256 PTE entries and 4096 PGD entries, we tell
- * Linux that we actually have 512 PTE entries and 2048 PGD entries.
- * Each "Linux" PGD entry is made up of two hardware PGD entries, and
- * each PTE table is actually two hardware PTE tables.
- */
-#define PTRS_PER_PTE		512
-#define PTRS_PER_PMD		1
-#define PTRS_PER_PGD		2048
-
-/*
- * Hardware page table definitions.
- *
- * + Level 1 descriptor (PMD)
- *   - common
- */
-#define PMD_TYPE_MASK		(3 << 0)
-#define PMD_TYPE_FAULT		(0 << 0)
-#define PMD_TYPE_TABLE		(1 << 0)
-#define PMD_TYPE_SECT		(2 << 0)
-#define PMD_BIT4		(1 << 4)
-#define PMD_DOMAIN(x)		((x) << 5)
-#define PMD_PROTECTION		(1 << 9)	/* v5 */
-/*
- *   - section
- */
-#define PMD_SECT_BUFFERABLE	(1 << 2)
-#define PMD_SECT_CACHEABLE	(1 << 3)
-#define PMD_SECT_AP_WRITE	(1 << 10)
-#define PMD_SECT_AP_READ	(1 << 11)
-#define PMD_SECT_TEX(x)		((x) << 12)	/* v5 */
-#define PMD_SECT_APX		(1 << 15)	/* v6 */
-#define PMD_SECT_S		(1 << 16)	/* v6 */
-#define PMD_SECT_nG		(1 << 17)	/* v6 */
-
-#define PMD_SECT_UNCACHED	(0)
-#define PMD_SECT_BUFFERED	(PMD_SECT_BUFFERABLE)
-#define PMD_SECT_WT		(PMD_SECT_CACHEABLE)
-#define PMD_SECT_WB		(PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
-#define PMD_SECT_MINICACHE	(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE)
-#define PMD_SECT_WBWA		(PMD_SECT_TEX(1) | PMD_SECT_CACHEABLE | PMD_SECT_BUFFERABLE)
-
-/*
- *   - coarse table (not used)
- */
-
-/*
- * + Level 2 descriptor (PTE)
- *   - common
- */
-#define PTE_TYPE_MASK		(3 << 0)
-#define PTE_TYPE_FAULT		(0 << 0)
-#define PTE_TYPE_LARGE		(1 << 0)
-#define PTE_TYPE_SMALL		(2 << 0)
-#define PTE_TYPE_EXT		(3 << 0)	/* v5 */
-#define PTE_BUFFERABLE		(1 << 2)
-#define PTE_CACHEABLE		(1 << 3)
-
-/*
- *   - extended small page/tiny page
- */
-#define PTE_EXT_AP_UNO_SRO	(0 << 4)
-#define PTE_EXT_AP_UNO_SRW	(1 << 4)
-#define PTE_EXT_AP_URO_SRW	(2 << 4)
-#define PTE_EXT_AP_URW_SRW	(3 << 4)
-#define PTE_EXT_TEX(x)		((x) << 6)	/* v5 */
-
-/*
- *   - small page
- */
-#define PTE_SMALL_AP_UNO_SRO	(0x00 << 4)
-#define PTE_SMALL_AP_UNO_SRW	(0x55 << 4)
-#define PTE_SMALL_AP_URO_SRW	(0xaa << 4)
-#define PTE_SMALL_AP_URW_SRW	(0xff << 4)
-#define PTE_AP_READ		PTE_SMALL_AP_URO_SRW
-#define PTE_AP_WRITE		PTE_SMALL_AP_UNO_SRW
-
-/*
- * "Linux" PTE definitions.
- *
- * We keep two sets of PTEs - the hardware and the linux version.
- * This allows greater flexibility in the way we map the Linux bits
- * onto the hardware tables, and allows us to have YOUNG and DIRTY
- * bits.
- *
- * The PTE table pointer refers to the hardware entries; the "Linux"
- * entries are stored 1024 bytes below.
- */
-#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)
-
-#ifndef __ASSEMBLY__
-
-#include <asm/proc/domain.h>
-
-#define _PAGE_USER_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_USER))
-#define _PAGE_KERNEL_TABLE	(PMD_TYPE_TABLE | PMD_BIT4 | PMD_DOMAIN(DOMAIN_KERNEL))
-
-#define pmd_bad(pmd)		(pmd_val(pmd) & 2)
-
-#define set_pmd(pmdp,pmd)		\
-	do {				\
-		*pmdp = pmd;		\
-		flush_pmd_entry(pmdp);	\
-	} while (0)
-
-#define pmd_clear(pmdp)			\
-	do {				\
-		pmdp[0] = __pmd(0);	\
-		pmdp[1] = __pmd(0);	\
-		clean_pmd_entry(pmdp);	\
-	} while (0)
-
-static inline pte_t *pmd_page_kernel(pmd_t pmd)
-{
-	unsigned long ptr;
-
-	ptr = pmd_val(pmd) & ~(PTRS_PER_PTE * sizeof(void *) - 1);
-	ptr += PTRS_PER_PTE * sizeof(void *);
-
-	return __va(ptr);
-}
-
-#define pmd_page(pmd) virt_to_page(__va(pmd_val(pmd)))
-
-#define pte_offset_kernel(dir,addr)	(pmd_page_kernel(*(dir)) + __pte_index(addr))
-#define pte_offset_map(dir,addr)	(pmd_page_kernel(*(dir)) + __pte_index(addr))
-#define pte_offset_map_nested(dir,addr)	(pmd_page_kernel(*(dir)) + __pte_index(addr))
-#define pte_unmap(pte)			do { } while (0)
-#define pte_unmap_nested(pte)		do { } while (0)
-
-#define set_pte(ptep, pte)	cpu_set_pte(ptep,pte)
-
-/*
- * The following macros handle the cache and bufferable bits...
- */
-#define _L_PTE_DEFAULT	L_PTE_PRESENT | L_PTE_YOUNG
-#define _L_PTE_READ	L_PTE_USER | L_PTE_EXEC | L_PTE_CACHEABLE | L_PTE_BUFFERABLE
-
-#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 PAGE_KERNEL     __pgprot(_L_PTE_DEFAULT | L_PTE_CACHEABLE | L_PTE_BUFFERABLE | L_PTE_DIRTY | L_PTE_WRITE | L_PTE_EXEC)
-
-#define _PAGE_CHG_MASK	(PAGE_MASK | L_PTE_DIRTY | L_PTE_YOUNG)
-
-
-/*
- * The following only work if pte_present() is true.
- * Undefined behaviour if not..
- */
-#define pte_present(pte)		(pte_val(pte) & L_PTE_PRESENT)
-#define pte_read(pte)			(pte_val(pte) & L_PTE_USER)
-#define pte_write(pte)			(pte_val(pte) & L_PTE_WRITE)
-#define pte_exec(pte)			(pte_val(pte) & L_PTE_EXEC)
-#define pte_dirty(pte)			(pte_val(pte) & L_PTE_DIRTY)
-#define pte_young(pte)			(pte_val(pte) & L_PTE_YOUNG)
-#define pte_file(pte)			(pte_val(pte) & L_PTE_FILE)
-
-#define PTE_BIT_FUNC(fn,op)			\
-static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
-
-/*PTE_BIT_FUNC(rdprotect, &= ~L_PTE_USER);*/
-/*PTE_BIT_FUNC(mkread,    |= L_PTE_USER);*/
-PTE_BIT_FUNC(wrprotect, &= ~L_PTE_WRITE);
-PTE_BIT_FUNC(mkwrite,   |= L_PTE_WRITE);
-PTE_BIT_FUNC(exprotect, &= ~L_PTE_EXEC);
-PTE_BIT_FUNC(mkexec,    |= L_PTE_EXEC);
-PTE_BIT_FUNC(mkclean,   &= ~L_PTE_DIRTY);
-PTE_BIT_FUNC(mkdirty,   |= L_PTE_DIRTY);
-PTE_BIT_FUNC(mkold,     &= ~L_PTE_YOUNG);
-PTE_BIT_FUNC(mkyoung,   |= L_PTE_YOUNG);
-
-/*
- * 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 pgtable_cache_init() do { } while (0)
-
-#define pte_to_pgoff(x)	(pte_val(x) >> 2)
-#define pgoff_to_pte(x)	__pte(((x) << 2) | L_PTE_FILE)
-
-#define PTE_FILE_MAX_BITS	30
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* __ASM_PROC_PGTABLE_H */
diff --git a/include/asm-arm/proc-armv/processor.h b/include/asm-arm/proc-armv/processor.h
deleted file mode 100644
index 373ca267700c..000000000000
--- a/include/asm-arm/proc-armv/processor.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/*
- *  linux/include/asm-arm/proc-armv/processor.h
- *
- *  Copyright (C) 1996-1999 Russell King.
- *
- * 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.
- *
- *  Changelog:
- *   20-09-1996	RMK	Created
- *   26-09-1996	RMK	Added 'EXTRA_THREAD_STRUCT*'
- *   28-09-1996	RMK	Moved start_thread into the processor dependencies
- *   09-09-1998	PJB	Delete redundant `wp_works_ok'
- *   30-05-1999	PJB	Save sl across context switches
- *   31-07-1999	RMK	Added 'domain' stuff
- */
-#ifndef __ASM_PROC_PROCESSOR_H
-#define __ASM_PROC_PROCESSOR_H
-
-#include <asm/proc/domain.h>
-
-#define KERNEL_STACK_SIZE	PAGE_SIZE
-
-#define INIT_EXTRA_THREAD_INFO						\
-	.cpu_domain	= domain_val(DOMAIN_USER, DOMAIN_MANAGER) |	\
-			  domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) |	\
-			  domain_val(DOMAIN_IO, DOMAIN_CLIENT)
-
-#define start_thread(regs,pc,sp)					\
-({									\
-	unsigned long *stack = (unsigned long *)sp;			\
-	set_fs(USER_DS);						\
-	memzero(regs->uregs, sizeof(regs->uregs));			\
-	if (current->personality & ADDR_LIMIT_32BIT)			\
-		regs->ARM_cpsr = USR_MODE;				\
-	else								\
-		regs->ARM_cpsr = USR26_MODE;				\
-	if (elf_hwcap & HWCAP_THUMB && pc & 1)				\
-		regs->ARM_cpsr |= PSR_T_BIT;				\
-	regs->ARM_pc = pc & ~1;		/* pc */			\
-	regs->ARM_sp = sp;		/* sp */			\
-	regs->ARM_r2 = stack[2];	/* r2 (envp) */			\
-	regs->ARM_r1 = stack[1];	/* r1 (argv) */			\
-	regs->ARM_r0 = stack[0];	/* r0 (argc) */			\
-})
-
-#define KSTK_EIP(tsk)	(((unsigned long *)(4096+(unsigned long)(tsk)->thread_info))[1019])
-#define KSTK_ESP(tsk)	(((unsigned long *)(4096+(unsigned long)(tsk)->thread_info))[1017])
-
-#endif
diff --git a/include/asm-arm/proc-armv/ptrace.h b/include/asm-arm/proc-armv/ptrace.h
deleted file mode 100644
index d70d3724612a..000000000000
--- a/include/asm-arm/proc-armv/ptrace.h
+++ /dev/null
@@ -1,143 +0,0 @@
-/*
- *  linux/include/asm-arm/proc-armv/ptrace.h
- *
- *  Copyright (C) 1996-1999 Russell King
- *
- * 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 __ASM_PROC_PTRACE_H
-#define __ASM_PROC_PTRACE_H
-
-#include <linux/config.h>
-
-/*
- * PSR bits
- */
-#define USR26_MODE	0x00000000
-#define FIQ26_MODE	0x00000001
-#define IRQ26_MODE	0x00000002
-#define SVC26_MODE	0x00000003
-#define USR_MODE	0x00000010
-#define FIQ_MODE	0x00000011
-#define IRQ_MODE	0x00000012
-#define SVC_MODE	0x00000013
-#define ABT_MODE	0x00000017
-#define UND_MODE	0x0000001b
-#define SYSTEM_MODE	0x0000001f
-#define MODE32_BIT	0x00000010
-#define MODE_MASK	0x0000001f
-#define PSR_T_BIT	0x00000020
-#define PSR_F_BIT	0x00000040
-#define PSR_I_BIT	0x00000080
-#define PSR_J_BIT	0x01000000
-#define PSR_Q_BIT	0x08000000
-#define PSR_V_BIT	0x10000000
-#define PSR_C_BIT	0x20000000
-#define PSR_Z_BIT	0x40000000
-#define PSR_N_BIT	0x80000000
-#define PCMASK		0
-
-/*
- * Groups of PSR bits
- */
-#define PSR_f		0xff000000	/* Flags		*/
-#define PSR_s		0x00ff0000	/* Status		*/
-#define PSR_x		0x0000ff00	/* Extension		*/
-#define PSR_c		0x000000ff	/* Control		*/
-
-/*
- * CR1 bits
- */
-#define CR1_M		0x00000001	/* MMU			*/
-#define CR1_A		0x00000002	/* Alignment fault	*/
-#define CR1_C		0x00000004	/* Dcache		*/
-#define CR1_W		0x00000008	/* Write buffer		*/
-#define CR1_P		0x00000010	/* Prog32		*/
-#define CR1_D		0x00000020	/* Data32		*/
-#define CR1_L		0x00000040	/* Late abort		*/
-#define CR1_B		0x00000080	/* Big endian		*/
-#define CR1_S		0x00000100	/* System protection	*/
-#define CR1_R		0x00000200	/* ROM protection	*/
-#define CR1_F		0x00000400
-#define CR1_Z		0x00000800	/* BTB enable		*/
-#define CR1_I		0x00001000	/* Icache		*/
-#define CR1_V		0x00002000	/* Vector relocation	*/
-#define CR1_RR		0x00004000	/* Round Robin		*/
-
-#ifndef __ASSEMBLY__
-
-/* this struct defines the way the registers are stored on the
-   stack during a system call. */
-
-struct pt_regs {
-	long uregs[18];
-};
-
-#define ARM_cpsr	uregs[16]
-#define ARM_pc		uregs[15]
-#define ARM_lr		uregs[14]
-#define ARM_sp		uregs[13]
-#define ARM_ip		uregs[12]
-#define ARM_fp		uregs[11]
-#define ARM_r10		uregs[10]
-#define ARM_r9		uregs[9]
-#define ARM_r8		uregs[8]
-#define ARM_r7		uregs[7]
-#define ARM_r6		uregs[6]
-#define ARM_r5		uregs[5]
-#define ARM_r4		uregs[4]
-#define ARM_r3		uregs[3]
-#define ARM_r2		uregs[2]
-#define ARM_r1		uregs[1]
-#define ARM_r0		uregs[0]
-#define ARM_ORIG_r0	uregs[17]
-
-#ifdef __KERNEL__
-
-#define user_mode(regs)	\
-	(((regs)->ARM_cpsr & 0xf) == 0)
-
-#ifdef CONFIG_ARM_THUMB
-#define thumb_mode(regs) \
-	(((regs)->ARM_cpsr & PSR_T_BIT))
-#else
-#define thumb_mode(regs) (0)
-#endif
-
-#define processor_mode(regs) \
-	((regs)->ARM_cpsr & MODE_MASK)
-
-#define interrupts_enabled(regs) \
-	(!((regs)->ARM_cpsr & PSR_I_BIT))
-
-#define fast_interrupts_enabled(regs) \
-	(!((regs)->ARM_cpsr & PSR_F_BIT))
-
-#define condition_codes(regs) \
-	((regs)->ARM_cpsr & (PSR_V_BIT|PSR_C_BIT|PSR_Z_BIT|PSR_N_BIT))
-	
-/* Are the current registers suitable for user mode?
- * (used to maintain security in signal handlers)
- */
-static inline int valid_user_regs(struct pt_regs *regs)
-{
-	if (user_mode(regs) &&
-	    (regs->ARM_cpsr & (PSR_F_BIT|PSR_I_BIT)) == 0)
-		return 1;
-
-	/*
-	 * Force CPSR to something logical...
-	 */
-	regs->ARM_cpsr &= PSR_f | PSR_s | PSR_x | PSR_T_BIT | MODE32_BIT;
-
-	return 0;
-}
-
-#endif	/* __KERNEL__ */
-
-#endif	/* __ASSEMBLY__ */
-
-#endif
-
diff --git a/include/asm-arm/proc-armv/shmparam.h b/include/asm-arm/proc-armv/shmparam.h
deleted file mode 100644
index 5b692cc5b3e8..000000000000
--- a/include/asm-arm/proc-armv/shmparam.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- *  linux/include/asm-arm/proc-armv/shmparam.h
- *
- *  Copyright (C) 1996 Russell King
- *
- * 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.
- *
- *  definitions for the shared process memory on ARM v3 or v4
- *  processors
- */
-#ifndef __ASM_PROC_SHMPARAM_H
-#define __ASM_PROC_SHMPARAM_H
-
-#ifndef SHMMAX
-#define SHMMAX		0x01000000
-#endif
-
-#endif
diff --git a/include/asm-arm/proc-armv/system.h b/include/asm-arm/proc-armv/system.h
deleted file mode 100644
index 2179e2a175fe..000000000000
--- a/include/asm-arm/proc-armv/system.h
+++ /dev/null
@@ -1,215 +0,0 @@
-/*
- *  linux/include/asm-arm/proc-armv/system.h
- *
- *  Copyright (C) 1996 Russell King
- *
- * 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 __ASM_PROC_SYSTEM_H
-#define __ASM_PROC_SYSTEM_H
-
-#include <linux/config.h>
-
-#define set_cr(x)					\
-	__asm__ __volatile__(				\
-	"mcr	p15, 0, %0, c1, c0, 0	@ set CR"	\
-	: : "r" (x) : "cc")
-
-#define get_cr()					\
-	({						\
-	unsigned int __val;				\
-	__asm__ __volatile__(				\
-	"mrc	p15, 0, %0, c1, c0, 0	@ get CR"	\
-	: "=r" (__val) : : "cc");			\
-	__val;						\
-	})
-
-#define CR_M	(1 << 0)	/* MMU enable				*/
-#define CR_A	(1 << 1)	/* Alignment abort enable		*/
-#define CR_C	(1 << 2)	/* Dcache enable			*/
-#define CR_W	(1 << 3)	/* Write buffer enable			*/
-#define CR_P	(1 << 4)	/* 32-bit exception handler		*/
-#define CR_D	(1 << 5)	/* 32-bit data address range		*/
-#define CR_L	(1 << 6)	/* Implementation defined		*/
-#define CR_B	(1 << 7)	/* Big endian				*/
-#define CR_S	(1 << 8)	/* System MMU protection		*/
-#define CR_R	(1 << 9)	/* ROM MMU protection			*/
-#define CR_F	(1 << 10)	/* Implementation defined		*/
-#define CR_Z	(1 << 11)	/* Implementation defined		*/
-#define CR_I	(1 << 12)	/* Icache enable			*/
-#define CR_V	(1 << 13)	/* Vectors relocated to 0xffff0000	*/
-#define CR_RR	(1 << 14)	/* Round Robin cache replacement	*/
-#define CR_L4	(1 << 15)	/* LDR pc can set T bit			*/
-#define CR_DT	(1 << 16)
-#define CR_IT	(1 << 18)
-#define CR_ST	(1 << 19)
-#define CR_FI	(1 << 21)
-#define CR_U	(1 << 22)	/* Unaligned access operation		*/
-#define CR_XP	(1 << 23)	/* Extended page tables			*/
-#define CR_VE	(1 << 24)	/* Vectored interrupts			*/
-
-extern unsigned long cr_no_alignment;	/* defined in entry-armv.S */
-extern unsigned long cr_alignment;	/* defined in entry-armv.S */
-
-#if __LINUX_ARM_ARCH__ >= 4
-#define vectors_base()	((cr_alignment & CR_V) ? 0xffff0000 : 0)
-#else
-#define vectors_base()	(0)
-#endif
-
-/*
- * Save the current interrupt enable state & disable IRQs
- */
-#define local_irq_save(x)					\
-	({							\
-		unsigned long temp;				\
-		(void) (&temp == &x);				\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ local_irq_save\n"	\
-"	orr	%1, %0, #128\n"					\
-"	msr	cpsr_c, %1"					\
-	: "=r" (x), "=r" (temp)					\
-	:							\
-	: "memory", "cc");					\
-	})
-	
-/*
- * Enable IRQs
- */
-#define local_irq_enable()					\
-	({							\
-		unsigned long temp;				\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ local_irq_enable\n"	\
-"	bic	%0, %0, #128\n"					\
-"	msr	cpsr_c, %0"					\
-	: "=r" (temp)						\
-	:							\
-	: "memory", "cc");					\
-	})
-
-/*
- * Disable IRQs
- */
-#define local_irq_disable()					\
-	({							\
-		unsigned long temp;				\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ local_irq_disable\n"	\
-"	orr	%0, %0, #128\n"					\
-"	msr	cpsr_c, %0"					\
-	: "=r" (temp)						\
-	:							\
-	: "memory", "cc");					\
-	})
-
-/*
- * Enable FIQs
- */
-#define __stf()							\
-	({							\
-		unsigned long temp;				\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ stf\n"		\
-"	bic	%0, %0, #64\n"					\
-"	msr	cpsr_c, %0"					\
-	: "=r" (temp)						\
-	:							\
-	: "memory", "cc");					\
-	})
-
-/*
- * Disable FIQs
- */
-#define __clf()							\
-	({							\
-		unsigned long temp;				\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ clf\n"		\
-"	orr	%0, %0, #64\n"					\
-"	msr	cpsr_c, %0"					\
-	: "=r" (temp)						\
-	:							\
-	: "memory", "cc");					\
-	})
-
-/*
- * Save the current interrupt enable state.
- */
-#define local_save_flags(x)					\
-	({							\
-	__asm__ __volatile__(					\
-	"mrs	%0, cpsr		@ local_save_flags"	\
-	: "=r" (x) : : "memory", "cc");				\
-	})
-
-/*
- * restore saved IRQ & FIQ state
- */
-#define local_irq_restore(x)					\
-	__asm__ __volatile__(					\
-	"msr	cpsr_c, %0		@ local_irq_restore\n"	\
-	:							\
-	: "r" (x)						\
-	: "memory", "cc")
-
-#if defined(CONFIG_CPU_SA1100) || defined(CONFIG_CPU_SA110)
-/*
- * On the StrongARM, "swp" is terminally broken since it bypasses the
- * cache totally.  This means that the cache becomes inconsistent, and,
- * since we use normal loads/stores as well, this is really bad.
- * Typically, this causes oopsen in filp_close, but could have other,
- * more disasterous effects.  There are two work-arounds:
- *  1. Disable interrupts and emulate the atomic swap
- *  2. Clean the cache, perform atomic swap, flush the cache
- *
- * We choose (1) since its the "easiest" to achieve here and is not
- * dependent on the processor type.
- */
-#define swp_is_buggy
-#endif
-
-static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
-{
-	extern void __bad_xchg(volatile void *, int);
-	unsigned long ret;
-#ifdef swp_is_buggy
-	unsigned long flags;
-#endif
-
-	switch (size) {
-#ifdef swp_is_buggy
-		case 1:
-			local_irq_save(flags);
-			ret = *(volatile unsigned char *)ptr;
-			*(volatile unsigned char *)ptr = x;
-			local_irq_restore(flags);
-			break;
-
-		case 4:
-			local_irq_save(flags);
-			ret = *(volatile unsigned long *)ptr;
-			*(volatile unsigned long *)ptr = x;
-			local_irq_restore(flags);
-			break;
-#else
-		case 1:	__asm__ __volatile__ ("swpb %0, %1, [%2]"
-					: "=&r" (ret)
-					: "r" (x), "r" (ptr)
-					: "memory", "cc");
-			break;
-		case 4:	__asm__ __volatile__ ("swp %0, %1, [%2]"
-					: "=&r" (ret)
-					: "r" (x), "r" (ptr)
-					: "memory", "cc");
-			break;
-#endif
-		default: __bad_xchg(ptr, size), ret = 0;
-	}
-
-	return ret;
-}
-
-#endif
diff --git a/include/asm-arm/proc-armv/tlbflush.h b/include/asm-arm/proc-armv/tlbflush.h
deleted file mode 100644
index f51019309d59..000000000000
--- a/include/asm-arm/proc-armv/tlbflush.h
+++ /dev/null
@@ -1,410 +0,0 @@
-/*
- *  linux/include/asm-arm/proc-armv/tlbflush.h
- *
- *  Copyright (C) 1999-2003 Russell King
- *
- * 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.
- */
-#include <linux/config.h>
-#include <asm/glue.h>
-
-#define TLB_V3_PAGE	(1 << 0)
-#define TLB_V4_U_PAGE	(1 << 1)
-#define TLB_V4_D_PAGE	(1 << 2)
-#define TLB_V4_I_PAGE	(1 << 3)
-#define TLB_V6_U_PAGE	(1 << 4)
-#define TLB_V6_D_PAGE	(1 << 5)
-#define TLB_V6_I_PAGE	(1 << 6)
-
-#define TLB_V3_FULL	(1 << 8)
-#define TLB_V4_U_FULL	(1 << 9)
-#define TLB_V4_D_FULL	(1 << 10)
-#define TLB_V4_I_FULL	(1 << 11)
-#define TLB_V6_U_FULL	(1 << 12)
-#define TLB_V6_D_FULL	(1 << 13)
-#define TLB_V6_I_FULL	(1 << 14)
-
-#define TLB_V6_U_ASID	(1 << 16)
-#define TLB_V6_D_ASID	(1 << 17)
-#define TLB_V6_I_ASID	(1 << 18)
-
-#define TLB_DCLEAN	(1 << 30)
-#define TLB_WB		(1 << 31)
-
-/*
- *	MMU TLB Model
- *	=============
- *
- *	We have the following to choose from:
- *	  v3    - ARMv3
- *	  v4    - ARMv4 without write buffer
- *	  v4wb  - ARMv4 with write buffer without I TLB flush entry instruction
- *	  v4wbi - ARMv4 with write buffer with I TLB flush entry instruction
- *	  v6wbi - ARMv6 with write buffer with I TLB flush entry instruction
- */
-#undef _TLB
-#undef MULTI_TLB
-
-#define v3_tlb_flags	(TLB_V3_FULL | TLB_V3_PAGE)
-
-#if defined(CONFIG_CPU_ARM610) || defined(CONFIG_CPU_ARM710)
-# define v3_possible_flags	v3_tlb_flags
-# define v3_always_flags	v3_tlb_flags
-# ifdef _TLB
-#  define MULTI_TLB 1
-# else
-#  define _TLB v3
-# endif
-#else
-# define v3_possible_flags	0
-# define v3_always_flags	(-1UL)
-#endif
-
-#define v4_tlb_flags	(TLB_V4_U_FULL | TLB_V4_U_PAGE)
-
-#if defined(CONFIG_CPU_ARM720T)
-# define v4_possible_flags	v4_tlb_flags
-# define v4_always_flags	v4_tlb_flags
-# ifdef _TLB
-#  define MULTI_TLB 1
-# else
-#  define _TLB v4
-# endif
-#else
-# define v4_possible_flags	0
-# define v4_always_flags	(-1UL)
-#endif
-
-#define v4wbi_tlb_flags	(TLB_WB | TLB_DCLEAN | \
-			 TLB_V4_I_FULL | TLB_V4_D_FULL | \
-			 TLB_V4_I_PAGE | TLB_V4_D_PAGE)
-
-#if defined(CONFIG_CPU_ARM920T) || defined(CONFIG_CPU_ARM922T) || \
-    defined(CONFIG_CPU_ARM926T) || defined(CONFIG_CPU_ARM1020) || \
-    defined(CONFIG_CPU_XSCALE)
-# define v4wbi_possible_flags	v4wbi_tlb_flags
-# define v4wbi_always_flags	v4wbi_tlb_flags
-# ifdef _TLB
-#  define MULTI_TLB 1
-# else
-#  define _TLB v4wbi
-# endif
-#else
-# define v4wbi_possible_flags	0
-# define v4wbi_always_flags	(-1UL)
-#endif
-
-#define v4wb_tlb_flags	(TLB_WB | TLB_DCLEAN | \
-			 TLB_V4_I_FULL | TLB_V4_D_FULL | \
-			 TLB_V4_D_PAGE)
-
-#if defined(CONFIG_CPU_SA110) || defined(CONFIG_CPU_SA1100)
-# define v4wb_possible_flags	v4wb_tlb_flags
-# define v4wb_always_flags	v4wb_tlb_flags
-# ifdef _TLB
-#  define MULTI_TLB 1
-# else
-#  define _TLB v4wb
-# endif
-#else
-# define v4wb_possible_flags	0
-# define v4wb_always_flags	(-1UL)
-#endif
-
-#define v6wbi_tlb_flags (TLB_WB | TLB_DCLEAN | \
-			 TLB_V6_I_FULL | TLB_V6_D_FULL | \
-			 TLB_V6_I_PAGE | TLB_V6_D_PAGE | \
-			 TLB_V6_I_ASID | TLB_V6_D_ASID)
-
-#if defined(CONFIG_CPU_V6)
-# define v6wbi_possible_flags	v6wbi_tlb_flags
-# define v6wbi_always_flags	v6wbi_tlb_flags
-# ifdef _TLB
-#  define MULTI_TLB 1
-# else
-#  define _TLB v6wbi
-# endif
-#else
-# define v6wbi_possible_flags	0
-# define v6wbi_always_flags	(-1UL)
-#endif
-
-#ifndef _TLB
-#error Unknown TLB model
-#endif
-
-#ifndef __ASSEMBLY__
-
-struct cpu_tlb_fns {
-	void (*flush_user_range)(unsigned long, unsigned long, struct vm_area_struct *);
-	void (*flush_kern_range)(unsigned long, unsigned long);
-	unsigned long tlb_flags;
-};
-
-/*
- * Select the calling method
- */
-#ifdef MULTI_TLB
-
-#define __cpu_flush_user_tlb_range	cpu_tlb.flush_user_range
-#define __cpu_flush_kern_tlb_range	cpu_tlb.flush_kern_range
-
-#else
-
-#define __cpu_flush_user_tlb_range	__glue(_TLB,_flush_user_tlb_range)
-#define __cpu_flush_kern_tlb_range	__glue(_TLB,_flush_kern_tlb_range)
-
-extern void __cpu_flush_user_tlb_range(unsigned long, unsigned long, struct vm_area_struct *);
-extern void __cpu_flush_kern_tlb_range(unsigned long, unsigned long);
-
-#endif
-
-extern struct cpu_tlb_fns cpu_tlb;
-
-#define __cpu_tlb_flags			cpu_tlb.tlb_flags
-
-/*
- *	TLB Management
- *	==============
- *
- *	The arch/arm/mm/tlb-*.S files implement these methods.
- *
- *	The TLB specific code is expected to perform whatever tests it
- *	needs to determine if it should invalidate the TLB for each
- *	call.  Start addresses are inclusive and end addresses are
- *	exclusive; it is safe to round these addresses down.
- *
- *	flush_tlb_all()
- *
- *		Invalidate the entire TLB.
- *
- *	flush_tlb_mm(mm)
- *
- *		Invalidate all TLB entries in a particular address
- *		space.
- *		- mm	- mm_struct describing address space
- *
- *	flush_tlb_range(mm,start,end)
- *
- *		Invalidate a range of TLB entries in the specified
- *		address space.
- *		- mm	- mm_struct describing address space
- *		- start - start address (may not be aligned)
- *		- end	- end address (exclusive, may not be aligned)
- *
- *	flush_tlb_page(vaddr,vma)
- *
- *		Invalidate the specified page in the specified address range.
- *		- vaddr - virtual address (may not be aligned)
- *		- vma	- vma_struct describing address range
- *
- *	flush_kern_tlb_page(kaddr)
- *
- *		Invalidate the TLB entry for the specified page.  The address
- *		will be in the kernels virtual memory space.  Current uses
- *		only require the D-TLB to be invalidated.
- *		- kaddr - Kernel virtual memory address
- */
-
-/*
- * We optimise the code below by:
- *  - building a set of TLB flags that might be set in __cpu_tlb_flags
- *  - building a set of TLB flags that will always be set in __cpu_tlb_flags
- *  - if we're going to need __cpu_tlb_flags, access it once and only once
- *
- * This allows us to build optimal assembly for the single-CPU type case,
- * and as close to optimal given the compiler constrants for multi-CPU
- * case.  We could do better for the multi-CPU case if the compiler
- * implemented the "%?" method, but this has been discontinued due to too
- * many people getting it wrong.
- */
-#define possible_tlb_flags	(v3_possible_flags | \
-				 v4_possible_flags | \
-				 v4wbi_possible_flags | \
-				 v4wb_possible_flags | \
-				 v6wbi_possible_flags)
-
-#define always_tlb_flags	(v3_always_flags & \
-				 v4_always_flags & \
-				 v4wbi_always_flags & \
-				 v4wb_always_flags & \
-				 v6wbi_always_flags)
-
-#define tlb_flag(f)	((always_tlb_flags & (f)) || (__tlb_flag & possible_tlb_flags & (f)))
-
-static inline void flush_tlb_all(void)
-{
-	const int zero = 0;
-	const unsigned int __tlb_flag = __cpu_tlb_flags;
-
-	if (tlb_flag(TLB_WB))
-		asm("mcr%? p15, 0, %0, c7, c10, 4" : : "r" (zero));
-
-	if (tlb_flag(TLB_V3_FULL))
-		asm("mcr%? p15, 0, %0, c6, c0, 0" : : "r" (zero));
-	if (tlb_flag(TLB_V4_U_FULL | TLB_V6_U_FULL))
-		asm("mcr%? p15, 0, %0, c8, c7, 0" : : "r" (zero));
-	if (tlb_flag(TLB_V4_D_FULL | TLB_V6_D_FULL))
-		asm("mcr%? p15, 0, %0, c8, c6, 0" : : "r" (zero));
-	if (tlb_flag(TLB_V4_I_FULL | TLB_V6_I_FULL))
-		asm("mcr%? p15, 0, %0, c8, c5, 0" : : "r" (zero));
-}
-
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
-	const int zero = 0;
-	const int asid = ASID(mm);
-	const unsigned int __tlb_flag = __cpu_tlb_flags;
-
-	if (tlb_flag(TLB_WB))
-		asm("mcr%? p15, 0, %0, c7, c10, 4" : : "r" (zero));
-
-	if (mm == current->active_mm) {
-		if (tlb_flag(TLB_V3_FULL))
-			asm("mcr%? p15, 0, %0, c6, c0, 0" : : "r" (zero));
-		if (tlb_flag(TLB_V4_U_FULL))
-			asm("mcr%? p15, 0, %0, c8, c7, 0" : : "r" (zero));
-		if (tlb_flag(TLB_V4_D_FULL))
-			asm("mcr%? p15, 0, %0, c8, c6, 0" : : "r" (zero));
-		if (tlb_flag(TLB_V4_I_FULL))
-			asm("mcr%? p15, 0, %0, c8, c5, 0" : : "r" (zero));
-	}
-
-	if (tlb_flag(TLB_V6_U_ASID))
-		asm("mcr%? p15, 0, %0, c8, c7, 2" : : "r" (asid));
-	if (tlb_flag(TLB_V6_D_ASID))
-		asm("mcr%? p15, 0, %0, c8, c6, 2" : : "r" (asid));
-	if (tlb_flag(TLB_V6_I_ASID))
-		asm("mcr%? p15, 0, %0, c8, c5, 2" : : "r" (asid));
-}
-
-static inline void
-flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
-{
-	const int zero = 0;
-	const unsigned int __tlb_flag = __cpu_tlb_flags;
-
-	uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
-
-	if (tlb_flag(TLB_WB))
-		asm("mcr%? p15, 0, %0, c7, c10, 4" : : "r" (zero));
-
-	if (vma->vm_mm == current->active_mm) {
-		if (tlb_flag(TLB_V3_PAGE))
-			asm("mcr%? p15, 0, %0, c6, c0, 0" : : "r" (uaddr));
-		if (tlb_flag(TLB_V4_U_PAGE))
-			asm("mcr%? p15, 0, %0, c8, c7, 1" : : "r" (uaddr));
-		if (tlb_flag(TLB_V4_D_PAGE))
-			asm("mcr%? p15, 0, %0, c8, c6, 1" : : "r" (uaddr));
-		if (tlb_flag(TLB_V4_I_PAGE))
-			asm("mcr%? p15, 0, %0, c8, c5, 1" : : "r" (uaddr));
-		if (!tlb_flag(TLB_V4_I_PAGE) && tlb_flag(TLB_V4_I_FULL))
-			asm("mcr%? p15, 0, %0, c8, c5, 0" : : "r" (zero));
-	}
-
-	if (tlb_flag(TLB_V6_U_PAGE))
-		asm("mcr%? p15, 0, %0, c8, c7, 1" : : "r" (uaddr));
-	if (tlb_flag(TLB_V6_D_PAGE))
-		asm("mcr%? p15, 0, %0, c8, c6, 1" : : "r" (uaddr));
-	if (tlb_flag(TLB_V6_I_PAGE))
-		asm("mcr%? p15, 0, %0, c8, c5, 1" : : "r" (uaddr));
-}
-
-static inline void flush_tlb_kernel_page(unsigned long kaddr)
-{
-	const int zero = 0;
-	const unsigned int __tlb_flag = __cpu_tlb_flags;
-
-	kaddr &= PAGE_MASK;
-
-	if (tlb_flag(TLB_WB))
-		asm("mcr%? p15, 0, %0, c7, c10, 4" : : "r" (zero));
-
-	if (tlb_flag(TLB_V3_PAGE))
-		asm("mcr%? p15, 0, %0, c6, c0, 0" : : "r" (kaddr));
-	if (tlb_flag(TLB_V4_U_PAGE))
-		asm("mcr%? p15, 0, %0, c8, c7, 1" : : "r" (kaddr));
-	if (tlb_flag(TLB_V4_D_PAGE))
-		asm("mcr%? p15, 0, %0, c8, c6, 1" : : "r" (kaddr));
-	if (tlb_flag(TLB_V4_I_PAGE))
-		asm("mcr%? p15, 0, %0, c8, c5, 1" : : "r" (kaddr));
-	if (!tlb_flag(TLB_V4_I_PAGE) && tlb_flag(TLB_V4_I_FULL))
-		asm("mcr%? p15, 0, %0, c8, c5, 0" : : "r" (zero));
-
-	if (tlb_flag(TLB_V6_U_PAGE))
-		asm("mcr%? p15, 0, %0, c8, c7, 1" : : "r" (kaddr));
-	if (tlb_flag(TLB_V6_D_PAGE))
-		asm("mcr%? p15, 0, %0, c8, c6, 1" : : "r" (kaddr));
-	if (tlb_flag(TLB_V6_I_PAGE))
-		asm("mcr%? p15, 0, %0, c8, c5, 1" : : "r" (kaddr));
-}
-
-/*
- *	flush_pmd_entry
- *
- *	Flush a PMD entry (word aligned, or double-word aligned) to
- *	RAM if the TLB for the CPU we are running on requires this.
- *	This is typically used when we are creating PMD entries.
- *
- *	clean_pmd_entry
- *
- *	Clean (but don't drain the write buffer) if the CPU requires
- *	these operations.  This is typically used when we are removing
- *	PMD entries.
- */
-static inline void flush_pmd_entry(pmd_t *pmd)
-{
-	const unsigned int zero = 0;
-	const unsigned int __tlb_flag = __cpu_tlb_flags;
-
-	if (tlb_flag(TLB_DCLEAN))
-		asm("mcr%?	p15, 0, %0, c7, c10, 1	@ flush_pmd"
-			: : "r" (pmd));
-	if (tlb_flag(TLB_WB))
-		asm("mcr%?	p15, 0, %0, c7, c10, 4	@ flush_pmd"
-			: : "r" (zero));
-}
-
-static inline void clean_pmd_entry(pmd_t *pmd)
-{
-	const unsigned int __tlb_flag = __cpu_tlb_flags;
-
-	if (tlb_flag(TLB_DCLEAN))
-		asm("mcr%?	p15, 0, %0, c7, c10, 1	@ flush_pmd"
-			: : "r" (pmd));
-}
-
-#undef tlb_flag
-#undef always_tlb_flags
-#undef possible_tlb_flags
-
-/*
- * Convert calls to our calling convention.
- */
-#define flush_tlb_range(vma,start,end)	__cpu_flush_user_tlb_range(start,end,vma)
-#define flush_tlb_kernel_range(s,e)	__cpu_flush_kern_tlb_range(s,e)
-
-/*
- * if PG_dcache_dirty is set for the page, we need to ensure that any
- * cache entries for the kernels virtual memory range are written
- * back to the page.
- */
-extern void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, pte_t pte);
-
-/*
- * ARM processors do not cache TLB tables in RAM.
- */
-#define flush_tlb_pgtables(mm,start,end)	do { } while (0)
-
-/*
- * Old ARM MEMC stuff.  This supports the reversed mapping handling that
- * we have on the older 26-bit machines.  We don't have a MEMC chip, so...
- */
-#define memc_update_all()		do { } while (0)
-#define memc_update_mm(mm)		do { } while (0)
-#define memc_update_addr(mm,pte,log)	do { } while (0)
-#define memc_clear(mm,physaddr)		do { } while (0)
-
-#endif
diff --git a/include/asm-arm/proc-armv/uaccess.h b/include/asm-arm/proc-armv/uaccess.h
deleted file mode 100644
index b871c78160b1..000000000000
--- a/include/asm-arm/proc-armv/uaccess.h
+++ /dev/null
@@ -1,189 +0,0 @@
-/*
- *  linux/include/asm-arm/proc-armv/uaccess.h
- *
- * 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.
- */
-#include <asm/arch/memory.h>
-#include <asm/proc/domain.h>
-
-/*
- * Note that this is actually 0x1,0000,0000
- */
-#define KERNEL_DS	0x00000000
-#define USER_DS		TASK_SIZE
-
-static inline void set_fs (mm_segment_t fs)
-{
-	current_thread_info()->addr_limit = fs;
-	modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER);
-}
-
-/* We use 33-bit arithmetic here... */
-#define __range_ok(addr,size) ({ \
-	unsigned long flag, sum; \
-	__asm__("adds %1, %2, %3; sbcccs %1, %1, %0; movcc %0, #0" \
-		: "=&r" (flag), "=&r" (sum) \
-		: "r" (addr), "Ir" (size), "0" (current_thread_info()->addr_limit) \
-		: "cc"); \
-	flag; })
-
-#define __addr_ok(addr) ({ \
-	unsigned long flag; \
-	__asm__("cmp %2, %0; movlo %0, #0" \
-		: "=&r" (flag) \
-		: "0" (current_thread_info()->addr_limit), "r" (addr) \
-		: "cc"); \
-	(flag == 0); })
-
-#define __put_user_asm_byte(x,__pu_addr,err)			\
-	__asm__ __volatile__(					\
-	"1:	strbt	%1,[%2],#0\n"				\
-	"2:\n"							\
-	"	.section .fixup,\"ax\"\n"			\
-	"	.align	2\n"					\
-	"3:	mov	%0, %3\n"				\
-	"	b	2b\n"					\
-	"	.previous\n"					\
-	"	.section __ex_table,\"a\"\n"			\
-	"	.align	3\n"					\
-	"	.long	1b, 3b\n"				\
-	"	.previous"					\
-	: "+r" (err)						\
-	: "r" (x), "r" (__pu_addr), "i" (-EFAULT)		\
-	: "cc")
-
-#ifndef __ARMEB__
-#define __put_user_asm_half(x,__pu_addr,err)			\
-({								\
-	unsigned long __temp = (unsigned long)(x);		\
-	__put_user_asm_byte(__temp, __pu_addr, err);		\
-	__put_user_asm_byte(__temp >> 8, __pu_addr + 1, err);	\
-})
-#else
-#define __put_user_asm_half(x,__pu_addr,err)			\
-({								\
-	unsigned long __temp = (unsigned long)(x);		\
-	__put_user_asm_byte(__temp >> 8, __pu_addr, err);	\
-	__put_user_asm_byte(__temp, __pu_addr + 1, err);	\
-})
-#endif
-
-#define __put_user_asm_word(x,__pu_addr,err)			\
-	__asm__ __volatile__(					\
-	"1:	strt	%1,[%2],#0\n"				\
-	"2:\n"							\
-	"	.section .fixup,\"ax\"\n"			\
-	"	.align	2\n"					\
-	"3:	mov	%0, %3\n"				\
-	"	b	2b\n"					\
-	"	.previous\n"					\
-	"	.section __ex_table,\"a\"\n"			\
-	"	.align	3\n"					\
-	"	.long	1b, 3b\n"				\
-	"	.previous"					\
-	: "+r" (err)						\
-	: "r" (x), "r" (__pu_addr), "i" (-EFAULT)		\
-	: "cc")
-
-#ifndef __ARMEB__
-#define	__reg_oper0	"%R2"
-#define	__reg_oper1	"%Q2"
-#else
-#define	__reg_oper0	"%Q2"
-#define	__reg_oper1	"%R2"
-#endif
-
-#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"		\
-	"3:\n"							\
-	"	.section .fixup,\"ax\"\n"			\
-	"	.align	2\n"					\
-	"4:	mov	%0, %3\n"				\
-	"	b	3b\n"					\
-	"	.previous\n"					\
-	"	.section __ex_table,\"a\"\n"			\
-	"	.align	3\n"					\
-	"	.long	1b, 4b\n"				\
-	"	.long	2b, 4b\n"				\
-	"	.previous"					\
-	: "+r" (err), "+r" (__pu_addr)				\
-	: "r" (x), "i" (-EFAULT)				\
-	: "cc")
-
-#define __get_user_asm_byte(x,addr,err)				\
-	__asm__ __volatile__(					\
-	"1:	ldrbt	%1,[%2],#0\n"				\
-	"2:\n"							\
-	"	.section .fixup,\"ax\"\n"			\
-	"	.align	2\n"					\
-	"3:	mov	%0, %3\n"				\
-	"	mov	%1, #0\n"				\
-	"	b	2b\n"					\
-	"	.previous\n"					\
-	"	.section __ex_table,\"a\"\n"			\
-	"	.align	3\n"					\
-	"	.long	1b, 3b\n"				\
-	"	.previous"					\
-	: "+r" (err), "=&r" (x)					\
-	: "r" (addr), "i" (-EFAULT)				\
-	: "cc")
-
-#ifndef __ARMEB__
-#define __get_user_asm_half(x,__gu_addr,err)			\
-({								\
-	unsigned long __b1, __b2;				\
-	__get_user_asm_byte(__b1, __gu_addr, err);		\
-	__get_user_asm_byte(__b2, __gu_addr + 1, err);		\
-	(x) = __b1 | (__b2 << 8);				\
-})
-#else
-#define __get_user_asm_half(x,__gu_addr,err)			\
-({								\
-	unsigned long __b1, __b2;				\
-	__get_user_asm_byte(__b1, __gu_addr, err);		\
-	__get_user_asm_byte(__b2, __gu_addr + 1, err);		\
-	(x) = (__b1 << 8) | __b2;				\
-})
-#endif
-
-#define __get_user_asm_word(x,addr,err)				\
-	__asm__ __volatile__(					\
-	"1:	ldrt	%1,[%2],#0\n"				\
-	"2:\n"							\
-	"	.section .fixup,\"ax\"\n"			\
-	"	.align	2\n"					\
-	"3:	mov	%0, %3\n"				\
-	"	mov	%1, #0\n"				\
-	"	b	2b\n"					\
-	"	.previous\n"					\
-	"	.section __ex_table,\"a\"\n"			\
-	"	.align	3\n"					\
-	"	.long	1b, 3b\n"				\
-	"	.previous"					\
-	: "+r" (err), "=&r" (x)					\
-	: "r" (addr), "i" (-EFAULT)				\
-	: "cc")
-
-extern unsigned long __arch_copy_from_user(void *to, const void *from, unsigned long n);
-#define __do_copy_from_user(to,from,n)				\
-	(n) = __arch_copy_from_user(to,from,n)
-
-extern unsigned long __arch_copy_to_user(void *to, const void *from, unsigned long n);
-#define __do_copy_to_user(to,from,n)				\
-	(n) = __arch_copy_to_user(to,from,n)
-
-extern unsigned long __arch_clear_user(void *addr, unsigned long n);
-#define __do_clear_user(addr,sz)				\
-	(sz) = __arch_clear_user(addr,sz)
-
-extern unsigned long __arch_strncpy_from_user(char *to, const char *from, unsigned long count);
-#define __do_strncpy_from_user(dst,src,count,res)		\
-	(res) = __arch_strncpy_from_user(dst,src,count)
-
-extern unsigned long __arch_strnlen_user(const char *s, long n);
-#define __do_strnlen_user(s,n,res)					\
-	(res) = __arch_strnlen_user(s,n)
diff --git a/include/asm-arm/processor.h b/include/asm-arm/processor.h
index 181223a7329b..31c888ba601c 100644
--- a/include/asm-arm/processor.h
+++ b/include/asm-arm/processor.h
@@ -1,7 +1,7 @@
 /*
  *  linux/include/asm-arm/processor.h
  *
- *  Copyright (C) 1995 Russell King
+ *  Copyright (C) 1995-1999 Russell King
  *
  * 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
@@ -27,9 +27,10 @@
 #include <asm/ptrace.h>
 #include <asm/procinfo.h>
 #include <asm/arch/memory.h>
-#include <asm/proc/processor.h>
 #include <asm/types.h>
 
+#define KERNEL_STACK_SIZE	PAGE_SIZE
+
 union debug_insn {
 	u32	arm;
 	u16	thumb;
@@ -56,6 +57,24 @@ struct thread_struct {
 
 #define INIT_THREAD  {	}
 
+#define start_thread(regs,pc,sp)					\
+({									\
+	unsigned long *stack = (unsigned long *)sp;			\
+	set_fs(USER_DS);						\
+	memzero(regs->uregs, sizeof(regs->uregs));			\
+	if (current->personality & ADDR_LIMIT_32BIT)			\
+		regs->ARM_cpsr = USR_MODE;				\
+	else								\
+		regs->ARM_cpsr = USR26_MODE;				\
+	if (elf_hwcap & HWCAP_THUMB && pc & 1)				\
+		regs->ARM_cpsr |= PSR_T_BIT;				\
+	regs->ARM_pc = pc & ~1;		/* pc */			\
+	regs->ARM_sp = sp;		/* sp */			\
+	regs->ARM_r2 = stack[2];	/* r2 (envp) */			\
+	regs->ARM_r1 = stack[1];	/* r1 (argv) */			\
+	regs->ARM_r0 = stack[0];	/* r0 (argc) */			\
+})
+
 /* Forward declaration, a strange C thing */
 struct task_struct;
 
@@ -74,6 +93,9 @@ unsigned long get_wchan(struct task_struct *p);
  */
 extern int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags);
 
+#define KSTK_EIP(tsk)	(((unsigned long *)(4096+(unsigned long)(tsk)->thread_info))[1019])
+#define KSTK_ESP(tsk)	(((unsigned long *)(4096+(unsigned long)(tsk)->thread_info))[1017])
+
 /*
  * Prefetching support - only ARMv5.
  */
diff --git a/include/asm-arm/ptrace.h b/include/asm-arm/ptrace.h
index eaf50e3bd63e..162c456638db 100644
--- a/include/asm-arm/ptrace.h
+++ b/include/asm-arm/ptrace.h
@@ -1,6 +1,17 @@
+/*
+ *  linux/include/asm-arm/ptrace.h
+ *
+ *  Copyright (C) 1996-2003 Russell King
+ *
+ * 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 __ASM_ARM_PTRACE_H
 #define __ASM_ARM_PTRACE_H
 
+#include <linux/config.h>
+
 #define PTRACE_GETREGS		12
 #define PTRACE_SETREGS		13
 #define PTRACE_GETFPREGS	14
@@ -8,9 +19,112 @@
 
 #define PTRACE_OLDSETOPTIONS	21
 
-#include <asm/proc/ptrace.h>
+/*
+ * PSR bits
+ */
+#define USR26_MODE	0x00000000
+#define FIQ26_MODE	0x00000001
+#define IRQ26_MODE	0x00000002
+#define SVC26_MODE	0x00000003
+#define USR_MODE	0x00000010
+#define FIQ_MODE	0x00000011
+#define IRQ_MODE	0x00000012
+#define SVC_MODE	0x00000013
+#define ABT_MODE	0x00000017
+#define UND_MODE	0x0000001b
+#define SYSTEM_MODE	0x0000001f
+#define MODE32_BIT	0x00000010
+#define MODE_MASK	0x0000001f
+#define PSR_T_BIT	0x00000020
+#define PSR_F_BIT	0x00000040
+#define PSR_I_BIT	0x00000080
+#define PSR_J_BIT	0x01000000
+#define PSR_Q_BIT	0x08000000
+#define PSR_V_BIT	0x10000000
+#define PSR_C_BIT	0x20000000
+#define PSR_Z_BIT	0x40000000
+#define PSR_N_BIT	0x80000000
+#define PCMASK		0
+
+/*
+ * Groups of PSR bits
+ */
+#define PSR_f		0xff000000	/* Flags		*/
+#define PSR_s		0x00ff0000	/* Status		*/
+#define PSR_x		0x0000ff00	/* Extension		*/
+#define PSR_c		0x000000ff	/* Control		*/
 
 #ifndef __ASSEMBLY__
+
+/* this struct defines the way the registers are stored on the
+   stack during a system call. */
+
+struct pt_regs {
+	long uregs[18];
+};
+
+#define ARM_cpsr	uregs[16]
+#define ARM_pc		uregs[15]
+#define ARM_lr		uregs[14]
+#define ARM_sp		uregs[13]
+#define ARM_ip		uregs[12]
+#define ARM_fp		uregs[11]
+#define ARM_r10		uregs[10]
+#define ARM_r9		uregs[9]
+#define ARM_r8		uregs[8]
+#define ARM_r7		uregs[7]
+#define ARM_r6		uregs[6]
+#define ARM_r5		uregs[5]
+#define ARM_r4		uregs[4]
+#define ARM_r3		uregs[3]
+#define ARM_r2		uregs[2]
+#define ARM_r1		uregs[1]
+#define ARM_r0		uregs[0]
+#define ARM_ORIG_r0	uregs[17]
+
+#ifdef __KERNEL__
+
+#define user_mode(regs)	\
+	(((regs)->ARM_cpsr & 0xf) == 0)
+
+#ifdef CONFIG_ARM_THUMB
+#define thumb_mode(regs) \
+	(((regs)->ARM_cpsr & PSR_T_BIT))
+#else
+#define thumb_mode(regs) (0)
+#endif
+
+#define processor_mode(regs) \
+	((regs)->ARM_cpsr & MODE_MASK)
+
+#define interrupts_enabled(regs) \
+	(!((regs)->ARM_cpsr & PSR_I_BIT))
+
+#define fast_interrupts_enabled(regs) \
+	(!((regs)->ARM_cpsr & PSR_F_BIT))
+
+#define condition_codes(regs) \
+	((regs)->ARM_cpsr & (PSR_V_BIT|PSR_C_BIT|PSR_Z_BIT|PSR_N_BIT))
+	
+/* Are the current registers suitable for user mode?
+ * (used to maintain security in signal handlers)
+ */
+static inline int valid_user_regs(struct pt_regs *regs)
+{
+	if (user_mode(regs) &&
+	    (regs->ARM_cpsr & (PSR_F_BIT|PSR_I_BIT)) == 0)
+		return 1;
+
+	/*
+	 * Force CPSR to something logical...
+	 */
+	regs->ARM_cpsr &= PSR_f | PSR_s | PSR_x | PSR_T_BIT | MODE32_BIT;
+
+	return 0;
+}
+
+#endif	/* __KERNEL__ */
+
 #define pc_pointer(v) \
 	((v) & ~PCMASK)
 
diff --git a/include/asm-arm/semaphore.h b/include/asm-arm/semaphore.h
index 34412c203747..656120edc11b 100644
--- a/include/asm-arm/semaphore.h
+++ b/include/asm-arm/semaphore.h
@@ -10,7 +10,7 @@
 #include <linux/rwsem.h>
 
 #include <asm/atomic.h>
-#include <asm/proc/locks.h>
+#include <asm/locks.h>
 
 struct semaphore {
 	atomic_t count;
diff --git a/include/asm-arm/shmparam.h b/include/asm-arm/shmparam.h
index 4359852cc1ac..46d9944a7a14 100644
--- a/include/asm-arm/shmparam.h
+++ b/include/asm-arm/shmparam.h
@@ -1,8 +1,6 @@
 #ifndef _ASMARM_SHMPARAM_H
 #define _ASMARM_SHMPARAM_H
 
-#include <asm/proc/shmparam.h>
-
 /*
  * This should be the size of the virtually indexed cache/ways,
  * or page size, whichever is greater since the cache aliases
diff --git a/include/asm-arm/system.h b/include/asm-arm/system.h
index d000f45ed4e7..bb533f25fc7d 100644
--- a/include/asm-arm/system.h
+++ b/include/asm-arm/system.h
@@ -4,6 +4,45 @@
 #ifdef __KERNEL__
 
 #include <linux/config.h>
+
+#define CPU_ARCH_UNKNOWN	0
+#define CPU_ARCH_ARMv3		1
+#define CPU_ARCH_ARMv4		2
+#define CPU_ARCH_ARMv4T		3
+#define CPU_ARCH_ARMv5		4
+#define CPU_ARCH_ARMv5T		5
+#define CPU_ARCH_ARMv5TE	6
+#define CPU_ARCH_ARMv6		7
+
+/*
+ * CR1 bits (CP#15 CR1)
+ */
+#define CR_M	(1 << 0)	/* MMU enable				*/
+#define CR_A	(1 << 1)	/* Alignment abort enable		*/
+#define CR_C	(1 << 2)	/* Dcache enable			*/
+#define CR_W	(1 << 3)	/* Write buffer enable			*/
+#define CR_P	(1 << 4)	/* 32-bit exception handler		*/
+#define CR_D	(1 << 5)	/* 32-bit data address range		*/
+#define CR_L	(1 << 6)	/* Implementation defined		*/
+#define CR_B	(1 << 7)	/* Big endian				*/
+#define CR_S	(1 << 8)	/* System MMU protection		*/
+#define CR_R	(1 << 9)	/* ROM MMU protection			*/
+#define CR_F	(1 << 10)	/* Implementation defined		*/
+#define CR_Z	(1 << 11)	/* Implementation defined		*/
+#define CR_I	(1 << 12)	/* Icache enable			*/
+#define CR_V	(1 << 13)	/* Vectors relocated to 0xffff0000	*/
+#define CR_RR	(1 << 14)	/* Round Robin cache replacement	*/
+#define CR_L4	(1 << 15)	/* LDR pc can set T bit			*/
+#define CR_DT	(1 << 16)
+#define CR_IT	(1 << 18)
+#define CR_ST	(1 << 19)
+#define CR_FI	(1 << 21)
+#define CR_U	(1 << 22)	/* Unaligned access operation		*/
+#define CR_XP	(1 << 23)	/* Extended page tables			*/
+#define CR_VE	(1 << 24)	/* Vectored interrupts			*/
+
+#ifndef __ASSEMBLY__
+
 #include <linux/kernel.h>
 
 struct thread_info;
@@ -34,21 +73,30 @@ void hook_fault_code(int nr, int (*fn)(unsigned long, unsigned int,
 
 extern asmlinkage void __backtrace(void);
 
-#define CPU_ARCH_UNKNOWN	0
-#define CPU_ARCH_ARMv3		1
-#define CPU_ARCH_ARMv4		2
-#define CPU_ARCH_ARMv4T		3
-#define CPU_ARCH_ARMv5		4
-#define CPU_ARCH_ARMv5T		5
-#define CPU_ARCH_ARMv5TE	6
-#define CPU_ARCH_ARMv6		7
-
 extern int cpu_architecture(void);
 
-/*
- * Include processor dependent parts
- */
-#include <asm/proc/system.h>
+#define set_cr(x)					\
+	__asm__ __volatile__(				\
+	"mcr	p15, 0, %0, c1, c0, 0	@ set CR"	\
+	: : "r" (x) : "cc")
+
+#define get_cr()					\
+	({						\
+	unsigned int __val;				\
+	__asm__ __volatile__(				\
+	"mrc	p15, 0, %0, c1, c0, 0	@ get CR"	\
+	: "=r" (__val) : : "cc");			\
+	__val;						\
+	})
+
+extern unsigned long cr_no_alignment;	/* defined in entry-armv.S */
+extern unsigned long cr_alignment;	/* defined in entry-armv.S */
+
+#if __LINUX_ARM_ARCH__ >= 4
+#define vectors_base()	((cr_alignment & CR_V) ? 0xffff0000 : 0)
+#else
+#define vectors_base()	(0)
+#endif
 
 #define mb() __asm__ __volatile__ ("" : : : "memory")
 #define rmb() mb()
@@ -75,6 +123,102 @@ extern struct task_struct *__switch_to(struct task_struct *, struct thread_info
 		mb();								\
 	} while (0)
 
+/*
+ * Save the current interrupt enable state & disable IRQs
+ */
+#define local_irq_save(x)					\
+	({							\
+		unsigned long temp;				\
+		(void) (&temp == &x);				\
+	__asm__ __volatile__(					\
+	"mrs	%0, cpsr		@ local_irq_save\n"	\
+"	orr	%1, %0, #128\n"					\
+"	msr	cpsr_c, %1"					\
+	: "=r" (x), "=r" (temp)					\
+	:							\
+	: "memory", "cc");					\
+	})
+	
+/*
+ * Enable IRQs
+ */
+#define local_irq_enable()					\
+	({							\
+		unsigned long temp;				\
+	__asm__ __volatile__(					\
+	"mrs	%0, cpsr		@ local_irq_enable\n"	\
+"	bic	%0, %0, #128\n"					\
+"	msr	cpsr_c, %0"					\
+	: "=r" (temp)						\
+	:							\
+	: "memory", "cc");					\
+	})
+
+/*
+ * Disable IRQs
+ */
+#define local_irq_disable()					\
+	({							\
+		unsigned long temp;				\
+	__asm__ __volatile__(					\
+	"mrs	%0, cpsr		@ local_irq_disable\n"	\
+"	orr	%0, %0, #128\n"					\
+"	msr	cpsr_c, %0"					\
+	: "=r" (temp)						\
+	:							\
+	: "memory", "cc");					\
+	})
+
+/*
+ * Enable FIQs
+ */
+#define __stf()							\
+	({							\
+		unsigned long temp;				\
+	__asm__ __volatile__(					\
+	"mrs	%0, cpsr		@ stf\n"		\
+"	bic	%0, %0, #64\n"					\
+"	msr	cpsr_c, %0"					\
+	: "=r" (temp)						\
+	:							\
+	: "memory", "cc");					\
+	})
+
+/*
+ * Disable FIQs
+ */
+#define __clf()							\
+	({							\
+		unsigned long temp;				\
+	__asm__ __volatile__(					\
+	"mrs	%0, cpsr		@ clf\n"		\
+"	orr	%0, %0, #64\n"					\
+"	msr	cpsr_c, %0"					\
+	: "=r" (temp)						\
+	:							\
+	: "memory", "cc");					\
+	})
+
+/*
+ * Save the current interrupt enable state.
+ */
+#define local_save_flags(x)					\
+	({							\
+	__asm__ __volatile__(					\
+	"mrs	%0, cpsr		@ local_save_flags"	\
+	: "=r" (x) : : "memory", "cc");				\
+	})
+
+/*
+ * restore saved IRQ & FIQ state
+ */
+#define local_irq_restore(x)					\
+	__asm__ __volatile__(					\
+	"msr	cpsr_c, %0		@ local_irq_restore\n"	\
+	:							\
+	: "r" (x)						\
+	: "memory", "cc")
+
 #ifdef CONFIG_SMP
 #error SMP not supported
 
@@ -100,8 +244,67 @@ extern struct task_struct *__switch_to(struct task_struct *, struct thread_info
 	flags & PSR_I_BIT;		\
 })
 
+#if defined(CONFIG_CPU_SA1100) || defined(CONFIG_CPU_SA110)
+/*
+ * On the StrongARM, "swp" is terminally broken since it bypasses the
+ * cache totally.  This means that the cache becomes inconsistent, and,
+ * since we use normal loads/stores as well, this is really bad.
+ * Typically, this causes oopsen in filp_close, but could have other,
+ * more disasterous effects.  There are two work-arounds:
+ *  1. Disable interrupts and emulate the atomic swap
+ *  2. Clean the cache, perform atomic swap, flush the cache
+ *
+ * We choose (1) since its the "easiest" to achieve here and is not
+ * dependent on the processor type.
+ */
+#define swp_is_buggy
+#endif
+
+static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size)
+{
+	extern void __bad_xchg(volatile void *, int);
+	unsigned long ret;
+#ifdef swp_is_buggy
+	unsigned long flags;
+#endif
+
+	switch (size) {
+#ifdef swp_is_buggy
+		case 1:
+			local_irq_save(flags);
+			ret = *(volatile unsigned char *)ptr;
+			*(volatile unsigned char *)ptr = x;
+			local_irq_restore(flags);
+			break;
+
+		case 4:
+			local_irq_save(flags);
+			ret = *(volatile unsigned long *)ptr;
+			*(volatile unsigned long *)ptr = x;
+			local_irq_restore(flags);
+			break;
+#else
+		case 1:	__asm__ __volatile__ ("swpb %0, %1, [%2]"
+					: "=&r" (ret)
+					: "r" (x), "r" (ptr)
+					: "memory", "cc");
+			break;
+		case 4:	__asm__ __volatile__ ("swp %0, %1, [%2]"
+					: "=&r" (ret)
+					: "r" (x), "r" (ptr)
+					: "memory", "cc");
+			break;
+#endif
+		default: __bad_xchg(ptr, size), ret = 0;
+	}
+
+	return ret;
+}
+
 #endif /* CONFIG_SMP */
 
+#endif /* __ASSEMBLY__ */
+
 #endif /* __KERNEL__ */
 
 #endif
diff --git a/include/asm-arm/thread_info.h b/include/asm-arm/thread_info.h
index 60bec9ec8c79..642810a9ed84 100644
--- a/include/asm-arm/thread_info.h
+++ b/include/asm-arm/thread_info.h
@@ -18,9 +18,9 @@ struct task_struct;
 struct exec_domain;
 
 #include <asm/fpstate.h>
-#include <asm/proc/processor.h>
 #include <asm/ptrace.h>
 #include <asm/types.h>
+#include <asm/domain.h>
 
 typedef unsigned long mm_segment_t;
 
@@ -55,17 +55,19 @@ struct thread_info {
 	union fp_state		fpstate;
 };
 
-#define INIT_THREAD_INFO(tsk)				\
-{							\
-	.task		= &tsk,				\
-	.exec_domain	= &default_exec_domain,		\
-	.flags		= 0,				\
-	.preempt_count	= 1,				\
-	.addr_limit	= KERNEL_DS,			\
-	.restart_block	= {				\
-		.fn	= do_no_restart_syscall,	\
-	},						\
-	INIT_EXTRA_THREAD_INFO,				\
+#define INIT_THREAD_INFO(tsk)						\
+{									\
+	.task		= &tsk,						\
+	.exec_domain	= &default_exec_domain,				\
+	.flags		= 0,						\
+	.preempt_count	= 1,						\
+	.addr_limit	= KERNEL_DS,					\
+	.cpu_domain	= domain_val(DOMAIN_USER, DOMAIN_MANAGER) |	\
+			  domain_val(DOMAIN_KERNEL, DOMAIN_MANAGER) |	\
+			  domain_val(DOMAIN_IO, DOMAIN_CLIENT),		\
+	.restart_block	= {						\
+		.fn	= do_no_restart_syscall,			\
+	},								\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
diff --git a/include/asm-arm/tlbflush.h b/include/asm-arm/tlbflush.h
index 9011f00fca32..6fdcc6ffeb0c 100644
--- a/include/asm-arm/tlbflush.h
+++ b/include/asm-arm/tlbflush.h
@@ -1,7 +1,7 @@
 /*
  *  linux/include/asm-arm/tlbflush.h
  *
- *  Copyright (C) 2000-2002 Russell King
+ *  Copyright (C) 1999-2003 Russell King
  *
  * 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
@@ -10,6 +10,397 @@
 #ifndef _ASMARM_TLBFLUSH_H
 #define _ASMARM_TLBFLUSH_H
 
-#include <asm-arm/proc/tlbflush.h>
+#include <linux/config.h>
+#include <asm/glue.h>
+
+#define TLB_V3_PAGE	(1 << 0)
+#define TLB_V4_U_PAGE	(1 << 1)
+#define TLB_V4_D_PAGE	(1 << 2)
+#define TLB_V4_I_PAGE	(1 << 3)
+#define TLB_V6_U_PAGE	(1 << 4)
+#define TLB_V6_D_PAGE	(1 << 5)
+#define TLB_V6_I_PAGE	(1 << 6)
+
+#define TLB_V3_FULL	(1 << 8)
+#define TLB_V4_U_FULL	(1 << 9)
+#define TLB_V4_D_FULL	(1 << 10)
+#define TLB_V4_I_FULL	(1 << 11)
+#define TLB_V6_U_FULL	(1 << 12)
+#define TLB_V6_D_FULL	(1 << 13)
+#define TLB_V6_I_FULL	(1 << 14)
+
+#define TLB_V6_U_ASID	(1 << 16)
+#define TLB_V6_D_ASID	(1 << 17)
+#define TLB_V6_I_ASID	(1 << 18)
+
+#define TLB_DCLEAN	(1 << 30)
+#define TLB_WB		(1 << 31)
+
+/*
+ *	MMU TLB Model
+ *	=============
+ *
+ *	We have the following to choose from:
+ *	  v3    - ARMv3
+ *	  v4    - ARMv4 without write buffer
+ *	  v4wb  - ARMv4 with write buffer without I TLB flush entry instruction
+ *	  v4wbi - ARMv4 with write buffer with I TLB flush entry instruction
+ *	  v6wbi - ARMv6 with write buffer with I TLB flush entry instruction
+ */
+#undef _TLB
+#undef MULTI_TLB
+
+#define v3_tlb_flags	(TLB_V3_FULL | TLB_V3_PAGE)
+
+#if defined(CONFIG_CPU_ARM610) || defined(CONFIG_CPU_ARM710)
+# define v3_possible_flags	v3_tlb_flags
+# define v3_always_flags	v3_tlb_flags
+# ifdef _TLB
+#  define MULTI_TLB 1
+# else
+#  define _TLB v3
+# endif
+#else
+# define v3_possible_flags	0
+# define v3_always_flags	(-1UL)
+#endif
+
+#define v4_tlb_flags	(TLB_V4_U_FULL | TLB_V4_U_PAGE)
+
+#if defined(CONFIG_CPU_ARM720T)
+# define v4_possible_flags	v4_tlb_flags
+# define v4_always_flags	v4_tlb_flags
+# ifdef _TLB
+#  define MULTI_TLB 1
+# else
+#  define _TLB v4
+# endif
+#else
+# define v4_possible_flags	0
+# define v4_always_flags	(-1UL)
+#endif
+
+#define v4wbi_tlb_flags	(TLB_WB | TLB_DCLEAN | \
+			 TLB_V4_I_FULL | TLB_V4_D_FULL | \
+			 TLB_V4_I_PAGE | TLB_V4_D_PAGE)
+
+#if defined(CONFIG_CPU_ARM920T) || defined(CONFIG_CPU_ARM922T) || \
+    defined(CONFIG_CPU_ARM926T) || defined(CONFIG_CPU_ARM1020) || \
+    defined(CONFIG_CPU_XSCALE)
+# define v4wbi_possible_flags	v4wbi_tlb_flags
+# define v4wbi_always_flags	v4wbi_tlb_flags
+# ifdef _TLB
+#  define MULTI_TLB 1
+# else
+#  define _TLB v4wbi
+# endif
+#else
+# define v4wbi_possible_flags	0
+# define v4wbi_always_flags	(-1UL)
+#endif
+
+#define v4wb_tlb_flags	(TLB_WB | TLB_DCLEAN | \
+			 TLB_V4_I_FULL | TLB_V4_D_FULL | \
+			 TLB_V4_D_PAGE)
+
+#if defined(CONFIG_CPU_SA110) || defined(CONFIG_CPU_SA1100)
+# define v4wb_possible_flags	v4wb_tlb_flags
+# define v4wb_always_flags	v4wb_tlb_flags
+# ifdef _TLB
+#  define MULTI_TLB 1
+# else
+#  define _TLB v4wb
+# endif
+#else
+# define v4wb_possible_flags	0
+# define v4wb_always_flags	(-1UL)
+#endif
+
+#define v6wbi_tlb_flags (TLB_WB | TLB_DCLEAN | \
+			 TLB_V6_I_FULL | TLB_V6_D_FULL | \
+			 TLB_V6_I_PAGE | TLB_V6_D_PAGE | \
+			 TLB_V6_I_ASID | TLB_V6_D_ASID)
+
+#if defined(CONFIG_CPU_V6)
+# define v6wbi_possible_flags	v6wbi_tlb_flags
+# define v6wbi_always_flags	v6wbi_tlb_flags
+# ifdef _TLB
+#  define MULTI_TLB 1
+# else
+#  define _TLB v6wbi
+# endif
+#else
+# define v6wbi_possible_flags	0
+# define v6wbi_always_flags	(-1UL)
+#endif
+
+#ifndef _TLB
+#error Unknown TLB model
+#endif
+
+#ifndef __ASSEMBLY__
+
+struct cpu_tlb_fns {
+	void (*flush_user_range)(unsigned long, unsigned long, struct vm_area_struct *);
+	void (*flush_kern_range)(unsigned long, unsigned long);
+	unsigned long tlb_flags;
+};
+
+/*
+ * Select the calling method
+ */
+#ifdef MULTI_TLB
+
+#define __cpu_flush_user_tlb_range	cpu_tlb.flush_user_range
+#define __cpu_flush_kern_tlb_range	cpu_tlb.flush_kern_range
+
+#else
+
+#define __cpu_flush_user_tlb_range	__glue(_TLB,_flush_user_tlb_range)
+#define __cpu_flush_kern_tlb_range	__glue(_TLB,_flush_kern_tlb_range)
+
+extern void __cpu_flush_user_tlb_range(unsigned long, unsigned long, struct vm_area_struct *);
+extern void __cpu_flush_kern_tlb_range(unsigned long, unsigned long);
+
+#endif
+
+extern struct cpu_tlb_fns cpu_tlb;
+
+#define __cpu_tlb_flags			cpu_tlb.tlb_flags
+
+/*
+ *	TLB Management
+ *	==============
+ *
+ *	The arch/arm/mm/tlb-*.S files implement these methods.
+ *
+ *	The TLB specific code is expected to perform whatever tests it
+ *	needs to determine if it should invalidate the TLB for each
+ *	call.  Start addresses are inclusive and end addresses are
+ *	exclusive; it is safe to round these addresses down.
+ *
+ *	flush_tlb_all()
+ *
+ *		Invalidate the entire TLB.
+ *
+ *	flush_tlb_mm(mm)
+ *
+ *		Invalidate all TLB entries in a particular address
+ *		space.
+ *		- mm	- mm_struct describing address space
+ *
+ *	flush_tlb_range(mm,start,end)
+ *
+ *		Invalidate a range of TLB entries in the specified
+ *		address space.
+ *		- mm	- mm_struct describing address space
+ *		- start - start address (may not be aligned)
+ *		- end	- end address (exclusive, may not be aligned)
+ *
+ *	flush_tlb_page(vaddr,vma)
+ *
+ *		Invalidate the specified page in the specified address range.
+ *		- vaddr - virtual address (may not be aligned)
+ *		- vma	- vma_struct describing address range
+ *
+ *	flush_kern_tlb_page(kaddr)
+ *
+ *		Invalidate the TLB entry for the specified page.  The address
+ *		will be in the kernels virtual memory space.  Current uses
+ *		only require the D-TLB to be invalidated.
+ *		- kaddr - Kernel virtual memory address
+ */
+
+/*
+ * We optimise the code below by:
+ *  - building a set of TLB flags that might be set in __cpu_tlb_flags
+ *  - building a set of TLB flags that will always be set in __cpu_tlb_flags
+ *  - if we're going to need __cpu_tlb_flags, access it once and only once
+ *
+ * This allows us to build optimal assembly for the single-CPU type case,
+ * and as close to optimal given the compiler constrants for multi-CPU
+ * case.  We could do better for the multi-CPU case if the compiler
+ * implemented the "%?" method, but this has been discontinued due to too
+ * many people getting it wrong.
+ */
+#define possible_tlb_flags	(v3_possible_flags | \
+				 v4_possible_flags | \
+				 v4wbi_possible_flags | \
+				 v4wb_possible_flags | \
+				 v6wbi_possible_flags)
+
+#define always_tlb_flags	(v3_always_flags & \
+				 v4_always_flags & \
+				 v4wbi_always_flags & \
+				 v4wb_always_flags & \
+				 v6wbi_always_flags)
+
+#define tlb_flag(f)	((always_tlb_flags & (f)) || (__tlb_flag & possible_tlb_flags & (f)))
+
+static inline void flush_tlb_all(void)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_WB))
+		asm("mcr%? p15, 0, %0, c7, c10, 4" : : "r" (zero));
+
+	if (tlb_flag(TLB_V3_FULL))
+		asm("mcr%? p15, 0, %0, c6, c0, 0" : : "r" (zero));
+	if (tlb_flag(TLB_V4_U_FULL | TLB_V6_U_FULL))
+		asm("mcr%? p15, 0, %0, c8, c7, 0" : : "r" (zero));
+	if (tlb_flag(TLB_V4_D_FULL | TLB_V6_D_FULL))
+		asm("mcr%? p15, 0, %0, c8, c6, 0" : : "r" (zero));
+	if (tlb_flag(TLB_V4_I_FULL | TLB_V6_I_FULL))
+		asm("mcr%? p15, 0, %0, c8, c5, 0" : : "r" (zero));
+}
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+	const int zero = 0;
+	const int asid = ASID(mm);
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_WB))
+		asm("mcr%? p15, 0, %0, c7, c10, 4" : : "r" (zero));
+
+	if (mm == current->active_mm) {
+		if (tlb_flag(TLB_V3_FULL))
+			asm("mcr%? p15, 0, %0, c6, c0, 0" : : "r" (zero));
+		if (tlb_flag(TLB_V4_U_FULL))
+			asm("mcr%? p15, 0, %0, c8, c7, 0" : : "r" (zero));
+		if (tlb_flag(TLB_V4_D_FULL))
+			asm("mcr%? p15, 0, %0, c8, c6, 0" : : "r" (zero));
+		if (tlb_flag(TLB_V4_I_FULL))
+			asm("mcr%? p15, 0, %0, c8, c5, 0" : : "r" (zero));
+	}
+
+	if (tlb_flag(TLB_V6_U_ASID))
+		asm("mcr%? p15, 0, %0, c8, c7, 2" : : "r" (asid));
+	if (tlb_flag(TLB_V6_D_ASID))
+		asm("mcr%? p15, 0, %0, c8, c6, 2" : : "r" (asid));
+	if (tlb_flag(TLB_V6_I_ASID))
+		asm("mcr%? p15, 0, %0, c8, c5, 2" : : "r" (asid));
+}
+
+static inline void
+flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	uaddr = (uaddr & PAGE_MASK) | ASID(vma->vm_mm);
+
+	if (tlb_flag(TLB_WB))
+		asm("mcr%? p15, 0, %0, c7, c10, 4" : : "r" (zero));
+
+	if (vma->vm_mm == current->active_mm) {
+		if (tlb_flag(TLB_V3_PAGE))
+			asm("mcr%? p15, 0, %0, c6, c0, 0" : : "r" (uaddr));
+		if (tlb_flag(TLB_V4_U_PAGE))
+			asm("mcr%? p15, 0, %0, c8, c7, 1" : : "r" (uaddr));
+		if (tlb_flag(TLB_V4_D_PAGE))
+			asm("mcr%? p15, 0, %0, c8, c6, 1" : : "r" (uaddr));
+		if (tlb_flag(TLB_V4_I_PAGE))
+			asm("mcr%? p15, 0, %0, c8, c5, 1" : : "r" (uaddr));
+		if (!tlb_flag(TLB_V4_I_PAGE) && tlb_flag(TLB_V4_I_FULL))
+			asm("mcr%? p15, 0, %0, c8, c5, 0" : : "r" (zero));
+	}
+
+	if (tlb_flag(TLB_V6_U_PAGE))
+		asm("mcr%? p15, 0, %0, c8, c7, 1" : : "r" (uaddr));
+	if (tlb_flag(TLB_V6_D_PAGE))
+		asm("mcr%? p15, 0, %0, c8, c6, 1" : : "r" (uaddr));
+	if (tlb_flag(TLB_V6_I_PAGE))
+		asm("mcr%? p15, 0, %0, c8, c5, 1" : : "r" (uaddr));
+}
+
+static inline void flush_tlb_kernel_page(unsigned long kaddr)
+{
+	const int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	kaddr &= PAGE_MASK;
+
+	if (tlb_flag(TLB_WB))
+		asm("mcr%? p15, 0, %0, c7, c10, 4" : : "r" (zero));
+
+	if (tlb_flag(TLB_V3_PAGE))
+		asm("mcr%? p15, 0, %0, c6, c0, 0" : : "r" (kaddr));
+	if (tlb_flag(TLB_V4_U_PAGE))
+		asm("mcr%? p15, 0, %0, c8, c7, 1" : : "r" (kaddr));
+	if (tlb_flag(TLB_V4_D_PAGE))
+		asm("mcr%? p15, 0, %0, c8, c6, 1" : : "r" (kaddr));
+	if (tlb_flag(TLB_V4_I_PAGE))
+		asm("mcr%? p15, 0, %0, c8, c5, 1" : : "r" (kaddr));
+	if (!tlb_flag(TLB_V4_I_PAGE) && tlb_flag(TLB_V4_I_FULL))
+		asm("mcr%? p15, 0, %0, c8, c5, 0" : : "r" (zero));
+
+	if (tlb_flag(TLB_V6_U_PAGE))
+		asm("mcr%? p15, 0, %0, c8, c7, 1" : : "r" (kaddr));
+	if (tlb_flag(TLB_V6_D_PAGE))
+		asm("mcr%? p15, 0, %0, c8, c6, 1" : : "r" (kaddr));
+	if (tlb_flag(TLB_V6_I_PAGE))
+		asm("mcr%? p15, 0, %0, c8, c5, 1" : : "r" (kaddr));
+}
+
+/*
+ *	flush_pmd_entry
+ *
+ *	Flush a PMD entry (word aligned, or double-word aligned) to
+ *	RAM if the TLB for the CPU we are running on requires this.
+ *	This is typically used when we are creating PMD entries.
+ *
+ *	clean_pmd_entry
+ *
+ *	Clean (but don't drain the write buffer) if the CPU requires
+ *	these operations.  This is typically used when we are removing
+ *	PMD entries.
+ */
+static inline void flush_pmd_entry(pmd_t *pmd)
+{
+	const unsigned int zero = 0;
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_DCLEAN))
+		asm("mcr%?	p15, 0, %0, c7, c10, 1	@ flush_pmd"
+			: : "r" (pmd));
+	if (tlb_flag(TLB_WB))
+		asm("mcr%?	p15, 0, %0, c7, c10, 4	@ flush_pmd"
+			: : "r" (zero));
+}
+
+static inline void clean_pmd_entry(pmd_t *pmd)
+{
+	const unsigned int __tlb_flag = __cpu_tlb_flags;
+
+	if (tlb_flag(TLB_DCLEAN))
+		asm("mcr%?	p15, 0, %0, c7, c10, 1	@ flush_pmd"
+			: : "r" (pmd));
+}
+
+#undef tlb_flag
+#undef always_tlb_flags
+#undef possible_tlb_flags
+
+/*
+ * Convert calls to our calling convention.
+ */
+#define flush_tlb_range(vma,start,end)	__cpu_flush_user_tlb_range(start,end,vma)
+#define flush_tlb_kernel_range(s,e)	__cpu_flush_kern_tlb_range(s,e)
+
+/*
+ * if PG_dcache_dirty is set for the page, we need to ensure that any
+ * cache entries for the kernels virtual memory range are written
+ * back to the page.
+ */
+extern void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr, pte_t pte);
+
+/*
+ * ARM processors do not cache TLB tables in RAM.
+ */
+#define flush_tlb_pgtables(mm,start,end)	do { } while (0)
+
+#endif
 
 #endif
diff --git a/include/asm-arm/uaccess.h b/include/asm-arm/uaccess.h
index 23bf0cbc1c76..634980801347 100644
--- a/include/asm-arm/uaccess.h
+++ b/include/asm-arm/uaccess.h
@@ -1,3 +1,10 @@
+/*
+ *  linux/include/asm-arm/uaccess.h
+ *
+ * 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 _ASMARM_UACCESS_H
 #define _ASMARM_UACCESS_H
 
@@ -6,6 +13,8 @@
  */
 #include <linux/sched.h>
 #include <asm/errno.h>
+#include <asm/arch/memory.h>
+#include <asm/domain.h>
 
 #define VERIFY_READ 0
 #define VERIFY_WRITE 1
@@ -30,11 +39,39 @@ struct exception_table_entry
 
 extern int fixup_exception(struct pt_regs *regs);
 
+/*
+ * Note that this is actually 0x1,0000,0000
+ */
+#define KERNEL_DS	0x00000000
+#define USER_DS		TASK_SIZE
+
 #define get_ds()	(KERNEL_DS)
 #define get_fs()	(current_thread_info()->addr_limit)
+
+static inline void set_fs (mm_segment_t fs)
+{
+	current_thread_info()->addr_limit = fs;
+	modify_domain(DOMAIN_KERNEL, fs ? DOMAIN_CLIENT : DOMAIN_MANAGER);
+}
+
 #define segment_eq(a,b)	((a) == (b))
 
-#include <asm/proc/uaccess.h>
+#define __addr_ok(addr) ({ \
+	unsigned long flag; \
+	__asm__("cmp %2, %0; movlo %0, #0" \
+		: "=&r" (flag) \
+		: "0" (current_thread_info()->addr_limit), "r" (addr) \
+		: "cc"); \
+	(flag == 0); })
+
+/* We use 33-bit arithmetic here... */
+#define __range_ok(addr,size) ({ \
+	unsigned long flag, sum; \
+	__asm__("adds %1, %2, %3; sbcccs %1, %1, %0; movcc %0, #0" \
+		: "=&r" (flag), "=&r" (sum) \
+		: "r" (addr), "Ir" (size), "0" (current_thread_info()->addr_limit) \
+		: "cc"); \
+	flag; })
 
 #define access_ok(type,addr,size)	(__range_ok(addr,size) == 0)
 
@@ -125,17 +162,71 @@ do {									\
 	(x) = (__typeof__(*(ptr)))__gu_val;				\
 } while (0)
 
+#define __get_user_asm_byte(x,addr,err)				\
+	__asm__ __volatile__(					\
+	"1:	ldrbt	%1,[%2],#0\n"				\
+	"2:\n"							\
+	"	.section .fixup,\"ax\"\n"			\
+	"	.align	2\n"					\
+	"3:	mov	%0, %3\n"				\
+	"	mov	%1, #0\n"				\
+	"	b	2b\n"					\
+	"	.previous\n"					\
+	"	.section __ex_table,\"a\"\n"			\
+	"	.align	3\n"					\
+	"	.long	1b, 3b\n"				\
+	"	.previous"					\
+	: "+r" (err), "=&r" (x)					\
+	: "r" (addr), "i" (-EFAULT)				\
+	: "cc")
+
+#ifndef __ARMEB__
+#define __get_user_asm_half(x,__gu_addr,err)			\
+({								\
+	unsigned long __b1, __b2;				\
+	__get_user_asm_byte(__b1, __gu_addr, err);		\
+	__get_user_asm_byte(__b2, __gu_addr + 1, err);		\
+	(x) = __b1 | (__b2 << 8);				\
+})
+#else
+#define __get_user_asm_half(x,__gu_addr,err)			\
+({								\
+	unsigned long __b1, __b2;				\
+	__get_user_asm_byte(__b1, __gu_addr, err);		\
+	__get_user_asm_byte(__b2, __gu_addr + 1, err);		\
+	(x) = (__b1 << 8) | __b2;				\
+})
+#endif
+
+#define __get_user_asm_word(x,addr,err)				\
+	__asm__ __volatile__(					\
+	"1:	ldrt	%1,[%2],#0\n"				\
+	"2:\n"							\
+	"	.section .fixup,\"ax\"\n"			\
+	"	.align	2\n"					\
+	"3:	mov	%0, %3\n"				\
+	"	mov	%1, #0\n"				\
+	"	b	2b\n"					\
+	"	.previous\n"					\
+	"	.section __ex_table,\"a\"\n"			\
+	"	.align	3\n"					\
+	"	.long	1b, 3b\n"				\
+	"	.previous"					\
+	: "+r" (err), "=&r" (x)					\
+	: "r" (addr), "i" (-EFAULT)				\
+	: "cc")
+
 extern int __put_user_1(void *, unsigned int);
 extern int __put_user_2(void *, unsigned int);
 extern int __put_user_4(void *, unsigned int);
 extern int __put_user_8(void *, unsigned long long);
 extern int __put_user_bad(void);
 
-#define __put_user_x(__r1,__p,__e,__s,__i...)				\
+#define __put_user_x(__r1,__p,__e,__s)					\
 	   __asm__ __volatile__ ("bl	__put_user_" #__s		\
 		: "=&r" (__e)						\
 		: "0" (__p), "r" (__r1)					\
-		: __i, "cc")
+		: "ip", "lr", "cc")
 
 #define put_user(x,p)							\
 	({								\
@@ -144,16 +235,16 @@ extern int __put_user_bad(void);
 		register int __e asm("r0");				\
 		switch (sizeof(*(__p))) {				\
 		case 1:							\
-			__put_user_x(__r1, __p, __e, 1, "ip", "lr");	\
+			__put_user_x(__r1, __p, __e, 1);		\
 			break;						\
 		case 2:							\
-			__put_user_x(__r1, __p, __e, 2, "ip", "lr");	\
+			__put_user_x(__r1, __p, __e, 2);		\
 			break;						\
 		case 4:							\
-			__put_user_x(__r1, __p, __e, 4, "ip", "lr");	\
+			__put_user_x(__r1, __p, __e, 4);		\
 			break;						\
 		case 8:							\
-			__put_user_x(__r1, __p, __e, 8, "ip", "lr");	\
+			__put_user_x(__r1, __p, __e, 8);		\
 			break;						\
 		default: __e = __put_user_bad(); break;			\
 		}							\
@@ -186,10 +277,93 @@ do {									\
 	}								\
 } while (0)
 
+#define __put_user_asm_byte(x,__pu_addr,err)			\
+	__asm__ __volatile__(					\
+	"1:	strbt	%1,[%2],#0\n"				\
+	"2:\n"							\
+	"	.section .fixup,\"ax\"\n"			\
+	"	.align	2\n"					\
+	"3:	mov	%0, %3\n"				\
+	"	b	2b\n"					\
+	"	.previous\n"					\
+	"	.section __ex_table,\"a\"\n"			\
+	"	.align	3\n"					\
+	"	.long	1b, 3b\n"				\
+	"	.previous"					\
+	: "+r" (err)						\
+	: "r" (x), "r" (__pu_addr), "i" (-EFAULT)		\
+	: "cc")
+
+#ifndef __ARMEB__
+#define __put_user_asm_half(x,__pu_addr,err)			\
+({								\
+	unsigned long __temp = (unsigned long)(x);		\
+	__put_user_asm_byte(__temp, __pu_addr, err);		\
+	__put_user_asm_byte(__temp >> 8, __pu_addr + 1, err);	\
+})
+#else
+#define __put_user_asm_half(x,__pu_addr,err)			\
+({								\
+	unsigned long __temp = (unsigned long)(x);		\
+	__put_user_asm_byte(__temp >> 8, __pu_addr, err);	\
+	__put_user_asm_byte(__temp, __pu_addr + 1, err);	\
+})
+#endif
+
+#define __put_user_asm_word(x,__pu_addr,err)			\
+	__asm__ __volatile__(					\
+	"1:	strt	%1,[%2],#0\n"				\
+	"2:\n"							\
+	"	.section .fixup,\"ax\"\n"			\
+	"	.align	2\n"					\
+	"3:	mov	%0, %3\n"				\
+	"	b	2b\n"					\
+	"	.previous\n"					\
+	"	.section __ex_table,\"a\"\n"			\
+	"	.align	3\n"					\
+	"	.long	1b, 3b\n"				\
+	"	.previous"					\
+	: "+r" (err)						\
+	: "r" (x), "r" (__pu_addr), "i" (-EFAULT)		\
+	: "cc")
+
+#ifndef __ARMEB__
+#define	__reg_oper0	"%R2"
+#define	__reg_oper1	"%Q2"
+#else
+#define	__reg_oper0	"%Q2"
+#define	__reg_oper1	"%R2"
+#endif
+
+#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"		\
+	"3:\n"							\
+	"	.section .fixup,\"ax\"\n"			\
+	"	.align	2\n"					\
+	"4:	mov	%0, %3\n"				\
+	"	b	3b\n"					\
+	"	.previous\n"					\
+	"	.section __ex_table,\"a\"\n"			\
+	"	.align	3\n"					\
+	"	.long	1b, 4b\n"				\
+	"	.long	2b, 4b\n"				\
+	"	.previous"					\
+	: "+r" (err), "+r" (__pu_addr)				\
+	: "r" (x), "i" (-EFAULT)				\
+	: "cc")
+
+extern unsigned long __arch_copy_from_user(void *to, const void *from, unsigned long n);
+extern unsigned long __arch_copy_to_user(void *to, const void *from, unsigned long n);
+extern unsigned long __arch_clear_user(void *addr, unsigned long n);
+extern unsigned long __arch_strncpy_from_user(char *to, const char *from, unsigned long count);
+extern unsigned long __arch_strnlen_user(const char *s, long n);
+
 static __inline__ unsigned long copy_from_user(void *to, const void *from, unsigned long n)
 {
 	if (access_ok(VERIFY_READ, from, n))
-		__do_copy_from_user(to, from, n);
+		n = __arch_copy_from_user(to, from, n);
 	else /* security hole - plug it */
 		memzero(to, n);
 	return n;
@@ -197,49 +371,44 @@ static __inline__ unsigned long copy_from_user(void *to, const void *from, unsig
 
 static __inline__ unsigned long __copy_from_user(void *to, const void *from, unsigned long n)
 {
-	__do_copy_from_user(to, from, n);
-	return n;
+	return __arch_copy_from_user(to, from, n);
 }
 
 static __inline__ unsigned long copy_to_user(void *to, const void *from, unsigned long n)
 {
 	if (access_ok(VERIFY_WRITE, to, n))
-		__do_copy_to_user(to, from, n);
+		n = __arch_copy_to_user(to, from, n);
 	return n;
 }
 
 static __inline__ unsigned long __copy_to_user(void *to, const void *from, unsigned long n)
 {
-	__do_copy_to_user(to, from, n);
-	return n;
+	return __arch_copy_to_user(to, from, n);
 }
 
 static __inline__ unsigned long clear_user (void *to, unsigned long n)
 {
 	if (access_ok(VERIFY_WRITE, to, n))
-		__do_clear_user(to, n);
+		n = __arch_clear_user(to, n);
 	return n;
 }
 
 static __inline__ unsigned long __clear_user (void *to, unsigned long n)
 {
-	__do_clear_user(to, n);
-	return n;
+	return __arch_clear_user(to, n);
 }
 
 static __inline__ long strncpy_from_user (char *dst, const char *src, long count)
 {
 	long res = -EFAULT;
 	if (access_ok(VERIFY_READ, src, 1))
-		__do_strncpy_from_user(dst, src, count, res);
+		res = __arch_strncpy_from_user(dst, src, count);
 	return res;
 }
 
 static __inline__ long __strncpy_from_user (char *dst, const char *src, long count)
 {
-	long res;
-	__do_strncpy_from_user(dst, src, count, res);
-	return res;
+	return __arch_strncpy_from_user(dst, src, count);
 }
 
 #define strlen_user(s)	strnlen_user(s, ~0UL >> 1)
@@ -249,7 +418,7 @@ static inline long strnlen_user(const char *s, long n)
 	unsigned long res = 0;
 
 	if (__addr_ok(s))
-		__do_strnlen_user(s, n, res);
+		res = __arch_strnlen_user(s, n);
 
 	return res;
 }