unicore32 core architecture: mm related: fault handling

This patch implements fault handling of memory management.

Signed-off-by: Guan Xuetao <gxt@mprc.pku.edu.cn>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>

10 files changed, 2247 insertions, 0 deletions

diff --git a/arch/unicore32/include/asm/mmu.h b/arch/unicore32/include/asm/mmu.h
new file mode 100644
index 00000000000..66fa341dc2c
--- /dev/null
+++ b/arch/unicore32/include/asm/mmu.h
@@ -0,0 +1,17 @@
+/*
+ * linux/arch/unicore32/include/asm/mmu.h
+ *
+ * Code specific to PKUnity SoC and UniCore ISA
+ *
+ * Copyright (C) 2001-2010 GUAN Xue-tao
+ *
+ * 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 __UNICORE_MMU_H__
+#define __UNICORE_MMU_H__
+
+typedef	unsigned long mm_context_t;
+
+#endif
diff --git a/arch/unicore32/include/asm/mmu_context.h b/arch/unicore32/include/asm/mmu_context.h
new file mode 100644
index 00000000000..fb5e4c658f7
--- /dev/null
+++ b/arch/unicore32/include/asm/mmu_context.h
@@ -0,0 +1,87 @@
+/*
+ * linux/arch/unicore32/include/asm/mmu_context.h
+ *
+ * Code specific to PKUnity SoC and UniCore ISA
+ *
+ * Copyright (C) 2001-2010 GUAN Xue-tao
+ *
+ * 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 __UNICORE_MMU_CONTEXT_H__
+#define __UNICORE_MMU_CONTEXT_H__
+
+#include <linux/compiler.h>
+#include <linux/sched.h>
+#include <linux/io.h>
+
+#include <asm/cacheflush.h>
+#include <asm/cpu-single.h>
+
+#define init_new_context(tsk, mm)	0
+
+#define destroy_context(mm)		do { } while (0)
+
+/*
+ * This is called when "tsk" is about to enter lazy TLB mode.
+ *
+ * mm:  describes the currently active mm context
+ * tsk: task which is entering lazy tlb
+ * cpu: cpu number which is entering lazy tlb
+ *
+ * tsk->mm will be NULL
+ */
+static inline void
+enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+}
+
+/*
+ * This is the actual mm switch as far as the scheduler
+ * is concerned.  No registers are touched.  We avoid
+ * calling the CPU specific function when the mm hasn't
+ * actually changed.
+ */
+static inline void
+switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	  struct task_struct *tsk)
+{
+	unsigned int cpu = smp_processor_id();
+
+	if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next)) || prev != next)
+		cpu_switch_mm(next->pgd, next);
+}
+
+#define deactivate_mm(tsk, mm)	do { } while (0)
+#define activate_mm(prev, next)	switch_mm(prev, next, NULL)
+
+/*
+ * We are inserting a "fake" vma for the user-accessible vector page so
+ * gdb and friends can get to it through ptrace and /proc/<pid>/mem.
+ * But we also want to remove it before the generic code gets to see it
+ * during process exit or the unmapping of it would  cause total havoc.
+ * (the macro is used as remove_vma() is static to mm/mmap.c)
+ */
+#define arch_exit_mmap(mm) \
+do { \
+	struct vm_area_struct *high_vma = find_vma(mm, 0xffff0000); \
+	if (high_vma) { \
+		BUG_ON(high_vma->vm_next);  /* it should be last */ \
+		if (high_vma->vm_prev) \
+			high_vma->vm_prev->vm_next = NULL; \
+		else \
+			mm->mmap = NULL; \
+		rb_erase(&high_vma->vm_rb, &mm->mm_rb); \
+		mm->mmap_cache = NULL; \
+		mm->map_count--; \
+		remove_vma(high_vma); \
+	} \
+} while (0)
+
+static inline void arch_dup_mmap(struct mm_struct *oldmm,
+				 struct mm_struct *mm)
+{
+}
+
+#endif
diff --git a/arch/unicore32/include/asm/pgalloc.h b/arch/unicore32/include/asm/pgalloc.h
new file mode 100644
index 00000000000..0213e373a89
--- /dev/null
+++ b/arch/unicore32/include/asm/pgalloc.h
@@ -0,0 +1,110 @@
+/*
+ * linux/arch/unicore32/include/asm/pgalloc.h
+ *
+ * Code specific to PKUnity SoC and UniCore ISA
+ *
+ * Copyright (C) 2001-2010 GUAN Xue-tao
+ *
+ * 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 __UNICORE_PGALLOC_H__
+#define __UNICORE_PGALLOC_H__
+
+#include <asm/pgtable-hwdef.h>
+#include <asm/processor.h>
+#include <asm/cacheflush.h>
+#include <asm/tlbflush.h>
+
+#define check_pgt_cache()		do { } while (0)
+
+#define _PAGE_USER_TABLE	(PMD_TYPE_TABLE | PMD_PRESENT)
+#define _PAGE_KERNEL_TABLE	(PMD_TYPE_TABLE | PMD_PRESENT)
+
+extern pgd_t *get_pgd_slow(struct mm_struct *mm);
+extern void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd);
+
+#define pgd_alloc(mm)			get_pgd_slow(mm)
+#define pgd_free(mm, pgd)		free_pgd_slow(mm, pgd)
+
+#define PGALLOC_GFP	(GFP_KERNEL | __GFP_NOTRACK | __GFP_REPEAT | __GFP_ZERO)
+
+/*
+ * Allocate one PTE table.
+ */
+static inline pte_t *
+pte_alloc_one_kernel(struct mm_struct *mm, unsigned long addr)
+{
+	pte_t *pte;
+
+	pte = (pte_t *)__get_free_page(PGALLOC_GFP);
+	if (pte)
+		clean_dcache_area(pte, PTRS_PER_PTE * sizeof(pte_t));
+
+	return pte;
+}
+
+static inline pgtable_t
+pte_alloc_one(struct mm_struct *mm, unsigned long addr)
+{
+	struct page *pte;
+
+	pte = alloc_pages(PGALLOC_GFP, 0);
+	if (pte) {
+		if (!PageHighMem(pte)) {
+			void *page = page_address(pte);
+			clean_dcache_area(page, PTRS_PER_PTE * sizeof(pte_t));
+		}
+		pgtable_page_ctor(pte);
+	}
+
+	return pte;
+}
+
+/*
+ * Free one PTE table.
+ */
+static inline void pte_free_kernel(struct mm_struct *mm, pte_t *pte)
+{
+	if (pte)
+		free_page((unsigned long)pte);
+}
+
+static inline void pte_free(struct mm_struct *mm, pgtable_t pte)
+{
+	pgtable_page_dtor(pte);
+	__free_page(pte);
+}
+
+static inline void __pmd_populate(pmd_t *pmdp, unsigned long pmdval)
+{
+	set_pmd(pmdp, __pmd(pmdval));
+	flush_pmd_entry(pmdp);
+}
+
+/*
+ * Populate the pmdp entry with a pointer to the pte.  This pmd is part
+ * of the mm address space.
+ */
+static inline void
+pmd_populate_kernel(struct mm_struct *mm, pmd_t *pmdp, pte_t *ptep)
+{
+	unsigned long pte_ptr = (unsigned long)ptep;
+
+	/*
+	 * The pmd must be loaded with the physical
+	 * address of the PTE table
+	 */
+	__pmd_populate(pmdp, __pa(pte_ptr) | _PAGE_KERNEL_TABLE);
+}
+
+static inline void
+pmd_populate(struct mm_struct *mm, pmd_t *pmdp, pgtable_t ptep)
+{
+	__pmd_populate(pmdp,
+			page_to_pfn(ptep) << PAGE_SHIFT | _PAGE_USER_TABLE);
+}
+#define pmd_pgtable(pmd) pmd_page(pmd)
+
+#endif
diff --git a/arch/unicore32/include/asm/pgtable-hwdef.h b/arch/unicore32/include/asm/pgtable-hwdef.h
new file mode 100644
index 00000000000..7314e859cca
--- /dev/null
+++ b/arch/unicore32/include/asm/pgtable-hwdef.h
@@ -0,0 +1,55 @@
+/*
+ * linux/arch/unicore32/include/asm/pgtable-hwdef.h
+ *
+ * Code specific to PKUnity SoC and UniCore ISA
+ *
+ * Copyright (C) 2001-2010 GUAN Xue-tao
+ *
+ * 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 __UNICORE_PGTABLE_HWDEF_H__
+#define __UNICORE_PGTABLE_HWDEF_H__
+
+/*
+ * Hardware page table definitions.
+ *
+ * + Level 1 descriptor (PMD)
+ *   - common
+ */
+#define PMD_TYPE_MASK		(3 << 0)
+#define PMD_TYPE_TABLE		(0 << 0)
+/*#define PMD_TYPE_LARGE	(1 << 0) */
+#define PMD_TYPE_INVALID	(2 << 0)
+#define PMD_TYPE_SECT		(3 << 0)
+
+#define PMD_PRESENT		(1 << 2)
+#define PMD_YOUNG		(1 << 3)
+
+/*#define PMD_SECT_DIRTY	(1 << 4) */
+#define PMD_SECT_CACHEABLE	(1 << 5)
+#define PMD_SECT_EXEC		(1 << 6)
+#define PMD_SECT_WRITE		(1 << 7)
+#define PMD_SECT_READ		(1 << 8)
+
+/*
+ * + Level 2 descriptor (PTE)
+ *   - common
+ */
+#define PTE_TYPE_MASK		(3 << 0)
+#define PTE_TYPE_SMALL		(0 << 0)
+#define PTE_TYPE_MIDDLE		(1 << 0)
+#define PTE_TYPE_LARGE		(2 << 0)
+#define PTE_TYPE_INVALID	(3 << 0)
+
+#define PTE_PRESENT		(1 << 2)
+#define PTE_FILE		(1 << 3)	/* only when !PRESENT */
+#define PTE_YOUNG		(1 << 3)
+#define PTE_DIRTY		(1 << 4)
+#define PTE_CACHEABLE		(1 << 5)
+#define PTE_EXEC		(1 << 6)
+#define PTE_WRITE		(1 << 7)
+#define PTE_READ		(1 << 8)
+
+#endif
diff --git a/arch/unicore32/include/asm/pgtable.h b/arch/unicore32/include/asm/pgtable.h
new file mode 100644
index 00000000000..68b2f297ac9
--- /dev/null
+++ b/arch/unicore32/include/asm/pgtable.h
@@ -0,0 +1,317 @@
+/*
+ * linux/arch/unicore32/include/asm/pgtable.h
+ *
+ * Code specific to PKUnity SoC and UniCore ISA
+ *
+ * Copyright (C) 2001-2010 GUAN Xue-tao
+ *
+ * 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 __UNICORE_PGTABLE_H__
+#define __UNICORE_PGTABLE_H__
+
+#include <asm-generic/pgtable-nopmd.h>
+#include <asm/cpu-single.h>
+
+#include <asm/memory.h>
+#include <asm/pgtable-hwdef.h>
+
+/*
+ * Just any arbitrary offset to the start of the vmalloc VM area: the
+ * current 8MB value just means that there will be a 8MB "hole" after the
+ * physical memory until the kernel virtual memory starts.  That means that
+ * any out-of-bounds memory accesses will hopefully be caught.
+ * The vmalloc() routines leaves a hole of 4kB between each vmalloced
+ * area for the same reason. ;)
+ *
+ * Note that platforms may override VMALLOC_START, but they must provide
+ * VMALLOC_END.  VMALLOC_END defines the (exclusive) limit of this space,
+ * which may not overlap IO space.
+ */
+#ifndef VMALLOC_START
+#define VMALLOC_OFFSET		SZ_8M
+#define VMALLOC_START		(((unsigned long)high_memory + VMALLOC_OFFSET) \
+					& ~(VMALLOC_OFFSET-1))
+#define VMALLOC_END		(0xff000000UL)
+#endif
+
+#define PTRS_PER_PTE		1024
+#define PTRS_PER_PGD		1024
+
+/*
+ * PGDIR_SHIFT determines what a third-level page table entry can map
+ */
+#define PGDIR_SHIFT		22
+
+#ifndef __ASSEMBLY__
+extern void __pte_error(const char *file, int line, unsigned long val);
+extern void __pgd_error(const char *file, int line, unsigned long val);
+
+#define pte_ERROR(pte)		__pte_error(__FILE__, __LINE__, pte_val(pte))
+#define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd_val(pgd))
+#endif /* !__ASSEMBLY__ */
+
+#define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
+#define PGDIR_MASK		(~(PGDIR_SIZE-1))
+
+/*
+ * This is the lowest virtual address we can permit any user space
+ * mapping to be mapped at.  This is particularly important for
+ * non-high vector CPUs.
+ */
+#define FIRST_USER_ADDRESS	PAGE_SIZE
+
+#define FIRST_USER_PGD_NR	1
+#define USER_PTRS_PER_PGD	((TASK_SIZE/PGDIR_SIZE) - FIRST_USER_PGD_NR)
+
+/*
+ * section address mask and size definitions.
+ */
+#define SECTION_SHIFT		22
+#define SECTION_SIZE		(1UL << SECTION_SHIFT)
+#define SECTION_MASK		(~(SECTION_SIZE-1))
+
+#ifndef __ASSEMBLY__
+
+/*
+ * The pgprot_* and protection_map entries will be fixed up in runtime
+ * to include the cachable bits based on memory policy, as well as any
+ * architecture dependent bits.
+ */
+#define _PTE_DEFAULT		(PTE_PRESENT | PTE_YOUNG | PTE_CACHEABLE)
+
+extern pgprot_t pgprot_user;
+extern pgprot_t pgprot_kernel;
+
+#define PAGE_NONE		pgprot_user
+#define PAGE_SHARED		__pgprot(pgprot_val(pgprot_user | PTE_READ \
+								| PTE_WRITE)
+#define PAGE_SHARED_EXEC	__pgprot(pgprot_val(pgprot_user | PTE_READ \
+								| PTE_WRITE \
+								| PTE_EXEC)
+#define PAGE_COPY		__pgprot(pgprot_val(pgprot_user | PTE_READ)
+#define PAGE_COPY_EXEC		__pgprot(pgprot_val(pgprot_user | PTE_READ \
+								| PTE_EXEC)
+#define PAGE_READONLY		__pgprot(pgprot_val(pgprot_user | PTE_READ)
+#define PAGE_READONLY_EXEC	__pgprot(pgprot_val(pgprot_user | PTE_READ \
+								| PTE_EXEC)
+#define PAGE_KERNEL		pgprot_kernel
+#define PAGE_KERNEL_EXEC	__pgprot(pgprot_val(pgprot_kernel | PTE_EXEC))
+
+#define __PAGE_NONE		__pgprot(_PTE_DEFAULT)
+#define __PAGE_SHARED		__pgprot(_PTE_DEFAULT | PTE_READ \
+							| PTE_WRITE)
+#define __PAGE_SHARED_EXEC	__pgprot(_PTE_DEFAULT | PTE_READ \
+							| PTE_WRITE \
+							| PTE_EXEC)
+#define __PAGE_COPY		__pgprot(_PTE_DEFAULT | PTE_READ)
+#define __PAGE_COPY_EXEC	__pgprot(_PTE_DEFAULT | PTE_READ \
+							| PTE_EXEC)
+#define __PAGE_READONLY		__pgprot(_PTE_DEFAULT | PTE_READ)
+#define __PAGE_READONLY_EXEC	__pgprot(_PTE_DEFAULT | PTE_READ \
+							| PTE_EXEC)
+
+#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 UniCore hardware:
+ *  1) We cannot do execute protection
+ *  2) If we could do execute protection, then read is implied
+ *  3) write implies read permissions
+ */
+#define __P000  __PAGE_NONE
+#define __P001  __PAGE_READONLY
+#define __P010  __PAGE_COPY
+#define __P011  __PAGE_COPY
+#define __P100  __PAGE_READONLY_EXEC
+#define __P101  __PAGE_READONLY_EXEC
+#define __P110  __PAGE_COPY_EXEC
+#define __P111  __PAGE_COPY_EXEC
+
+#define __S000  __PAGE_NONE
+#define __S001  __PAGE_READONLY
+#define __S010  __PAGE_SHARED
+#define __S011  __PAGE_SHARED
+#define __S100  __PAGE_READONLY_EXEC
+#define __S101  __PAGE_READONLY_EXEC
+#define __S110  __PAGE_SHARED_EXEC
+#define __S111  __PAGE_SHARED_EXEC
+
+#ifndef __ASSEMBLY__
+/*
+ * ZERO_PAGE is a global shared page that is always zero: used
+ * for zero-mapped memory areas etc..
+ */
+extern struct page *empty_zero_page;
+#define ZERO_PAGE(vaddr)		(empty_zero_page)
+
+#define pte_pfn(pte)			(pte_val(pte) >> PAGE_SHIFT)
+#define pfn_pte(pfn, prot)		(__pte(((pfn) << PAGE_SHIFT) \
+						| pgprot_val(prot)))
+
+#define pte_none(pte)			(!pte_val(pte))
+#define pte_clear(mm, addr, ptep)	set_pte(ptep, __pte(0))
+#define pte_page(pte)			(pfn_to_page(pte_pfn(pte)))
+#define pte_offset_kernel(dir, addr)	(pmd_page_vaddr(*(dir)) \
+						+ __pte_index(addr))
+
+#define pte_offset_map(dir, addr)	(pmd_page_vaddr(*(dir)) \
+						+ __pte_index(addr))
+#define pte_unmap(pte)			do { } while (0)
+
+#define set_pte(ptep, pte)	cpu_set_pte(ptep, pte)
+
+#define set_pte_at(mm, addr, ptep, pteval)	\
+	do {					\
+		set_pte(ptep, pteval);          \
+	} while (0)
+
+/*
+ * The following only work if pte_present() is true.
+ * Undefined behaviour if not..
+ */
+#define pte_present(pte)	(pte_val(pte) & PTE_PRESENT)
+#define pte_write(pte)		(pte_val(pte) & PTE_WRITE)
+#define pte_dirty(pte)		(pte_val(pte) & PTE_DIRTY)
+#define pte_young(pte)		(pte_val(pte) & PTE_YOUNG)
+#define pte_exec(pte)		(pte_val(pte) & PTE_EXEC)
+#define pte_special(pte)	(0)
+
+#define PTE_BIT_FUNC(fn, op) \
+static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
+
+PTE_BIT_FUNC(wrprotect, &= ~PTE_WRITE);
+PTE_BIT_FUNC(mkwrite,   |= PTE_WRITE);
+PTE_BIT_FUNC(mkclean,   &= ~PTE_DIRTY);
+PTE_BIT_FUNC(mkdirty,   |= PTE_DIRTY);
+PTE_BIT_FUNC(mkold,     &= ~PTE_YOUNG);
+PTE_BIT_FUNC(mkyoung,   |= PTE_YOUNG);
+
+static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
+
+/*
+ * Mark the prot value as uncacheable.
+ */
+#define pgprot_noncached(prot)		\
+	__pgprot(pgprot_val(prot) & ~PTE_CACHEABLE)
+#define pgprot_writecombine(prot)	\
+	__pgprot(pgprot_val(prot) & ~PTE_CACHEABLE)
+#define pgprot_dmacoherent(prot)	\
+	__pgprot(pgprot_val(prot) & ~PTE_CACHEABLE)
+
+#define pmd_none(pmd)		(!pmd_val(pmd))
+#define pmd_present(pmd)	(pmd_val(pmd) & PMD_PRESENT)
+#define pmd_bad(pmd)		(((pmd_val(pmd) &		\
+				(PMD_PRESENT | PMD_TYPE_MASK))	\
+				!= (PMD_PRESENT | PMD_TYPE_TABLE)))
+
+#define set_pmd(pmdpd, pmdval)		\
+	do {				\
+		*(pmdpd) = pmdval;	\
+	} while (0)
+
+#define pmd_clear(pmdp)			\
+	do {				\
+		set_pmd(pmdp, __pmd(0));\
+		clean_pmd_entry(pmdp);	\
+	} while (0)
+
+#define pmd_page_vaddr(pmd) ((pte_t *)__va(pmd_val(pmd) & PAGE_MASK))
+#define pmd_page(pmd)		pfn_to_page(__phys_to_pfn(pmd_val(pmd)))
+
+/*
+ * Conversion functions: convert a page and protection to a page entry,
+ * and a page entry and page directory to the page they refer to.
+ */
+#define mk_pte(page, prot)	pfn_pte(page_to_pfn(page), prot)
+
+/* to find an entry in a page-table-directory */
+#define pgd_index(addr)		((addr) >> PGDIR_SHIFT)
+
+#define pgd_offset(mm, addr)	((mm)->pgd+pgd_index(addr))
+
+/* to find an entry in a kernel page-table-directory */
+#define pgd_offset_k(addr)	pgd_offset(&init_mm, addr)
+
+/* Find an entry in the third-level page table.. */
+#define __pte_index(addr)	(((addr) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
+
+static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
+{
+	const unsigned long mask = PTE_EXEC | PTE_WRITE | PTE_READ;
+	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
+	return pte;
+}
+
+extern pgd_t swapper_pg_dir[PTRS_PER_PGD];
+
+/*
+ * Encode and decode a swap entry.  Swap entries are stored in the Linux
+ * page tables as follows:
+ *
+ *   3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
+ *   1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ *   <--------------- offset --------------> <--- type --> 0 0 0 0 0
+ *
+ * This gives us up to 127 swap files and 32GB per swap file.  Note that
+ * the offset field is always non-zero.
+ */
+#define __SWP_TYPE_SHIFT	5
+#define __SWP_TYPE_BITS		7
+#define __SWP_TYPE_MASK		((1 << __SWP_TYPE_BITS) - 1)
+#define __SWP_OFFSET_SHIFT	(__SWP_TYPE_BITS + __SWP_TYPE_SHIFT)
+
+#define __swp_type(x)		(((x).val >> __SWP_TYPE_SHIFT)		\
+				& __SWP_TYPE_MASK)
+#define __swp_offset(x)		((x).val >> __SWP_OFFSET_SHIFT)
+#define __swp_entry(type, offset) ((swp_entry_t) {			\
+				((type) << __SWP_TYPE_SHIFT) |		\
+				((offset) << __SWP_OFFSET_SHIFT) })
+
+#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
+#define __swp_entry_to_pte(swp)	((pte_t) { (swp).val })
+
+/*
+ * It is an error for the kernel to have more swap files than we can
+ * encode in the PTEs.  This ensures that we know when MAX_SWAPFILES
+ * is increased beyond what we presently support.
+ */
+#define MAX_SWAPFILES_CHECK()	\
+	BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS)
+
+/*
+ * Encode and decode a file entry.  File entries are stored in the Linux
+ * page tables as follows:
+ *
+ *   3 3 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1
+ *   1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0 9 8 7 6 5 4 3 2 1 0
+ *   <----------------------- offset ----------------------> 1 0 0 0
+ */
+#define pte_file(pte)		(pte_val(pte) & PTE_FILE)
+#define pte_to_pgoff(x)		(pte_val(x) >> 4)
+#define pgoff_to_pte(x)		__pte(((x) << 4) | PTE_FILE)
+
+#define PTE_FILE_MAX_BITS	28
+
+/* Needs to be defined here and not in linux/mm.h, as it is arch dependent */
+/* FIXME: this is not correct */
+#define kern_addr_valid(addr)	(1)
+
+#include <asm-generic/pgtable.h>
+
+/*
+ * remap a physical page `pfn' of size `size' with page protection `prot'
+ * into virtual address `from'
+ */
+#define io_remap_pfn_range(vma, from, pfn, size, prot)	\
+		remap_pfn_range(vma, from, pfn, size, prot)
+
+#define pgtable_cache_init() do { } while (0)
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* __UNICORE_PGTABLE_H__ */
diff --git a/arch/unicore32/mm/alignment.c b/arch/unicore32/mm/alignment.c
new file mode 100644
index 00000000000..28f576d733e
--- /dev/null
+++ b/arch/unicore32/mm/alignment.c
@@ -0,0 +1,523 @@
+/*
+ * linux/arch/unicore32/mm/alignment.c
+ *
+ * Code specific to PKUnity SoC and UniCore ISA
+ *
+ * Copyright (C) 2001-2010 GUAN Xue-tao
+ *
+ * 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.
+ */
+/*
+ * TODO:
+ *  FPU ldm/stm not handling
+ */
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/uaccess.h>
+
+#include <asm/tlbflush.h>
+#include <asm/unaligned.h>
+
+#define CODING_BITS(i)	(i & 0xe0000120)
+
+#define LDST_P_BIT(i)	(i & (1 << 28))	/* Preindex             */
+#define LDST_U_BIT(i)	(i & (1 << 27))	/* Add offset           */
+#define LDST_W_BIT(i)	(i & (1 << 25))	/* Writeback            */
+#define LDST_L_BIT(i)	(i & (1 << 24))	/* Load                 */
+
+#define LDST_P_EQ_U(i)	((((i) ^ ((i) >> 1)) & (1 << 27)) == 0)
+
+#define LDSTH_I_BIT(i)	(i & (1 << 26))	/* half-word immed      */
+#define LDM_S_BIT(i)	(i & (1 << 26))	/* write ASR from BSR */
+#define LDM_H_BIT(i)	(i & (1 << 6))	/* select r0-r15 or r16-r31 */
+
+#define RN_BITS(i)	((i >> 19) & 31)	/* Rn                   */
+#define RD_BITS(i)	((i >> 14) & 31)	/* Rd                   */
+#define RM_BITS(i)	(i & 31)	/* Rm                   */
+
+#define REGMASK_BITS(i)	(((i & 0x7fe00) >> 3) | (i & 0x3f))
+#define OFFSET_BITS(i)	(i & 0x03fff)
+
+#define SHIFT_BITS(i)	((i >> 9) & 0x1f)
+#define SHIFT_TYPE(i)	(i & 0xc0)
+#define SHIFT_LSL	0x00
+#define SHIFT_LSR	0x40
+#define SHIFT_ASR	0x80
+#define SHIFT_RORRRX	0xc0
+
+union offset_union {
+	unsigned long un;
+	signed long sn;
+};
+
+#define TYPE_ERROR	0
+#define TYPE_FAULT	1
+#define TYPE_LDST	2
+#define TYPE_DONE	3
+#define TYPE_SWAP  4
+#define TYPE_COLS  5		/* Coprocessor load/store */
+
+#define get8_unaligned_check(val, addr, err)		\
+	__asm__(					\
+	"1:	ldb.u	%1, [%2], #1\n"			\
+	"2:\n"						\
+	"	.pushsection .fixup,\"ax\"\n"		\
+	"	.align	2\n"				\
+	"3:	mov	%0, #1\n"			\
+	"	b	2b\n"				\
+	"	.popsection\n"				\
+	"	.pushsection __ex_table,\"a\"\n"		\
+	"	.align	3\n"				\
+	"	.long	1b, 3b\n"			\
+	"	.popsection\n"				\
+	: "=r" (err), "=&r" (val), "=r" (addr)		\
+	: "0" (err), "2" (addr))
+
+#define get8t_unaligned_check(val, addr, err)		\
+	__asm__(					\
+	"1:	ldb.u	%1, [%2], #1\n"			\
+	"2:\n"						\
+	"	.pushsection .fixup,\"ax\"\n"		\
+	"	.align	2\n"				\
+	"3:	mov	%0, #1\n"			\
+	"	b	2b\n"				\
+	"	.popsection\n"				\
+	"	.pushsection __ex_table,\"a\"\n"		\
+	"	.align	3\n"				\
+	"	.long	1b, 3b\n"			\
+	"	.popsection\n"				\
+	: "=r" (err), "=&r" (val), "=r" (addr)		\
+	: "0" (err), "2" (addr))
+
+#define get16_unaligned_check(val, addr)			\
+	do {							\
+		unsigned int err = 0, v, a = addr;		\
+		get8_unaligned_check(val, a, err);		\
+		get8_unaligned_check(v, a, err);		\
+		val |= v << 8;					\
+		if (err)					\
+			goto fault;				\
+	} while (0)
+
+#define put16_unaligned_check(val, addr)			\
+	do {							\
+		unsigned int err = 0, v = val, a = addr;	\
+		__asm__(					\
+		"1:	stb.u	%1, [%2], #1\n"			\
+		"	mov	%1, %1 >> #8\n"			\
+		"2:	stb.u	%1, [%2]\n"			\
+		"3:\n"						\
+		"	.pushsection .fixup,\"ax\"\n"		\
+		"	.align	2\n"				\
+		"4:	mov	%0, #1\n"			\
+		"	b	3b\n"				\
+		"	.popsection\n"				\
+		"	.pushsection __ex_table,\"a\"\n"		\
+		"	.align	3\n"				\
+		"	.long	1b, 4b\n"			\
+		"	.long	2b, 4b\n"			\
+		"	.popsection\n"				\
+		: "=r" (err), "=&r" (v), "=&r" (a)		\
+		: "0" (err), "1" (v), "2" (a));			\
+		if (err)					\
+			goto fault;				\
+	} while (0)
+
+#define __put32_unaligned_check(ins, val, addr)			\
+	do {							\
+		unsigned int err = 0, v = val, a = addr;	\
+		__asm__(					\
+		"1:	"ins"	%1, [%2], #1\n"			\
+		"	mov	%1, %1 >> #8\n"			\
+		"2:	"ins"	%1, [%2], #1\n"			\
+		"	mov	%1, %1 >> #8\n"			\
+		"3:	"ins"	%1, [%2], #1\n"			\
+		"	mov	%1, %1 >> #8\n"			\
+		"4:	"ins"	%1, [%2]\n"			\
+		"5:\n"						\
+		"	.pushsection .fixup,\"ax\"\n"		\
+		"	.align	2\n"				\
+		"6:	mov	%0, #1\n"			\
+		"	b	5b\n"				\
+		"	.popsection\n"				\
+		"	.pushsection __ex_table,\"a\"\n"		\
+		"	.align	3\n"				\
+		"	.long	1b, 6b\n"			\
+		"	.long	2b, 6b\n"			\
+		"	.long	3b, 6b\n"			\
+		"	.long	4b, 6b\n"			\
+		"	.popsection\n"				\
+		: "=r" (err), "=&r" (v), "=&r" (a)		\
+		: "0" (err), "1" (v), "2" (a));			\
+		if (err)					\
+			goto fault;				\
+	} while (0)
+
+#define get32_unaligned_check(val, addr)			\
+	do {							\
+		unsigned int err = 0, v, a = addr;		\
+		get8_unaligned_check(val, a, err);		\
+		get8_unaligned_check(v, a, err);		\
+		val |= v << 8;					\
+		get8_unaligned_check(v, a, err);		\
+		val |= v << 16;					\
+		get8_unaligned_check(v, a, err);		\
+		val |= v << 24;					\
+		if (err)					\
+			goto fault;				\
+	} while (0)
+
+#define put32_unaligned_check(val, addr)			\
+	__put32_unaligned_check("stb.u", val, addr)
+
+#define get32t_unaligned_check(val, addr)			\
+	do {							\
+		unsigned int err = 0, v, a = addr;		\
+		get8t_unaligned_check(val, a, err);		\
+		get8t_unaligned_check(v, a, err);		\
+		val |= v << 8;					\
+		get8t_unaligned_check(v, a, err);		\
+		val |= v << 16;					\
+		get8t_unaligned_check(v, a, err);		\
+		val |= v << 24;					\
+		if (err)					\
+			goto fault;				\
+	} while (0)
+
+#define put32t_unaligned_check(val, addr)			\
+	__put32_unaligned_check("stb.u", val, addr)
+
+static void
+do_alignment_finish_ldst(unsigned long addr, unsigned long instr,
+			 struct pt_regs *regs, union offset_union offset)
+{
+	if (!LDST_U_BIT(instr))
+		offset.un = -offset.un;
+
+	if (!LDST_P_BIT(instr))
+		addr += offset.un;
+
+	if (!LDST_P_BIT(instr) || LDST_W_BIT(instr))
+		regs->uregs[RN_BITS(instr)] = addr;
+}
+
+static int
+do_alignment_ldrhstrh(unsigned long addr, unsigned long instr,
+		      struct pt_regs *regs)
+{
+	unsigned int rd = RD_BITS(instr);
+
+	/* old value 0x40002120, can't judge swap instr correctly */
+	if ((instr & 0x4b003fe0) == 0x40000120)
+		goto swp;
+
+	if (LDST_L_BIT(instr)) {
+		unsigned long val;
+		get16_unaligned_check(val, addr);
+
+		/* signed half-word? */
+		if (instr & 0x80)
+			val = (signed long)((signed short)val);
+
+		regs->uregs[rd] = val;
+	} else
+		put16_unaligned_check(regs->uregs[rd], addr);
+
+	return TYPE_LDST;
+
+swp:
+	/* only handle swap word
+	 * for swap byte should not active this alignment exception */
+	get32_unaligned_check(regs->uregs[RD_BITS(instr)], addr);
+	put32_unaligned_check(regs->uregs[RM_BITS(instr)], addr);
+	return TYPE_SWAP;
+
+fault:
+	return TYPE_FAULT;
+}
+
+static int
+do_alignment_ldrstr(unsigned long addr, unsigned long instr,
+		    struct pt_regs *regs)
+{
+	unsigned int rd = RD_BITS(instr);
+
+	if (!LDST_P_BIT(instr) && LDST_W_BIT(instr))
+		goto trans;
+
+	if (LDST_L_BIT(instr))
+		get32_unaligned_check(regs->uregs[rd], addr);
+	else
+		put32_unaligned_check(regs->uregs[rd], addr);
+	return TYPE_LDST;
+
+trans:
+	if (LDST_L_BIT(instr))
+		get32t_unaligned_check(regs->uregs[rd], addr);
+	else
+		put32t_unaligned_check(regs->uregs[rd], addr);
+	return TYPE_LDST;
+
+fault:
+	return TYPE_FAULT;
+}
+
+/*
+ * LDM/STM alignment handler.
+ *
+ * There are 4 variants of this instruction:
+ *
+ * B = rn pointer before instruction, A = rn pointer after instruction
+ *              ------ increasing address ----->
+ *	        |    | r0 | r1 | ... | rx |    |
+ * PU = 01             B                    A
+ * PU = 11        B                    A
+ * PU = 00        A                    B
+ * PU = 10             A                    B
+ */
+static int
+do_alignment_ldmstm(unsigned long addr, unsigned long instr,
+		    struct pt_regs *regs)
+{
+	unsigned int rd, rn, pc_correction, reg_correction, nr_regs, regbits;
+	unsigned long eaddr, newaddr;
+
+	if (LDM_S_BIT(instr))
+		goto bad;
+
+	pc_correction = 4;	/* processor implementation defined */
+
+	/* count the number of registers in the mask to be transferred */
+	nr_regs = hweight16(REGMASK_BITS(instr)) * 4;
+
+	rn = RN_BITS(instr);
+	newaddr = eaddr = regs->uregs[rn];
+
+	if (!LDST_U_BIT(instr))
+		nr_regs = -nr_regs;
+	newaddr += nr_regs;
+	if (!LDST_U_BIT(instr))
+		eaddr = newaddr;
+
+	if (LDST_P_EQ_U(instr))	/* U = P */
+		eaddr += 4;
+
+	/*
+	 * This is a "hint" - we already have eaddr worked out by the
+	 * processor for us.
+	 */
+	if (addr != eaddr) {
+		printk(KERN_ERR "LDMSTM: PC = %08lx, instr = %08lx, "
+		       "addr = %08lx, eaddr = %08lx\n",
+		       instruction_pointer(regs), instr, addr, eaddr);
+		show_regs(regs);
+	}
+
+	if (LDM_H_BIT(instr))
+		reg_correction = 0x10;
+	else
+		reg_correction = 0x00;
+
+	for (regbits = REGMASK_BITS(instr), rd = 0; regbits;
+	     regbits >>= 1, rd += 1)
+		if (regbits & 1) {
+			if (LDST_L_BIT(instr))
+				get32_unaligned_check(regs->
+					uregs[rd + reg_correction], eaddr);
+			else
+				put32_unaligned_check(regs->
+					uregs[rd + reg_correction], eaddr);
+			eaddr += 4;
+		}
+
+	if (LDST_W_BIT(instr))
+		regs->uregs[rn] = newaddr;
+	return TYPE_DONE;
+
+fault:
+	regs->UCreg_pc -= pc_correction;
+	return TYPE_FAULT;
+
+bad:
+	printk(KERN_ERR "Alignment trap: not handling ldm with s-bit set\n");
+	return TYPE_ERROR;
+}
+
+static int
+do_alignment(unsigned long addr, unsigned int error_code, struct pt_regs *regs)
+{
+	union offset_union offset;
+	unsigned long instr, instrptr;
+	int (*handler) (unsigned long addr, unsigned long instr,
+			struct pt_regs *regs);
+	unsigned int type;
+
+	instrptr = instruction_pointer(regs);
+	if (instrptr >= PAGE_OFFSET)
+		instr = *(unsigned long *)instrptr;
+	else {
+		__asm__ __volatile__(
+				"ldw.u	%0, [%1]\n"
+				: "=&r"(instr)
+				: "r"(instrptr));
+	}
+
+	regs->UCreg_pc += 4;
+
+	switch (CODING_BITS(instr)) {
+	case 0x40000120:	/* ldrh or strh */
+		if (LDSTH_I_BIT(instr))
+			offset.un = (instr & 0x3e00) >> 4 | (instr & 31);
+		else
+			offset.un = regs->uregs[RM_BITS(instr)];
+		handler = do_alignment_ldrhstrh;
+		break;
+
+	case 0x60000000:	/* ldr or str immediate */
+	case 0x60000100:	/* ldr or str immediate */
+	case 0x60000020:	/* ldr or str immediate */
+	case 0x60000120:	/* ldr or str immediate */
+		offset.un = OFFSET_BITS(instr);
+		handler = do_alignment_ldrstr;
+		break;
+
+	case 0x40000000:	/* ldr or str register */
+		offset.un = regs->uregs[RM_BITS(instr)];
+		{
+			unsigned int shiftval = SHIFT_BITS(instr);
+
+			switch (SHIFT_TYPE(instr)) {
+			case SHIFT_LSL:
+				offset.un <<= shiftval;
+				break;
+
+			case SHIFT_LSR:
+				offset.un >>= shiftval;
+				break;
+
+			case SHIFT_ASR:
+				offset.sn >>= shiftval;
+				break;
+
+			case SHIFT_RORRRX:
+				if (shiftval == 0) {
+					offset.un >>= 1;
+					if (regs->UCreg_asr & PSR_C_BIT)
+						offset.un |= 1 << 31;
+				} else
+					offset.un = offset.un >> shiftval |
+					    offset.un << (32 - shiftval);
+				break;
+			}
+		}
+		handler = do_alignment_ldrstr;
+		break;
+
+	case 0x80000000:	/* ldm or stm */
+	case 0x80000020:	/* ldm or stm */
+		handler = do_alignment_ldmstm;
+		break;
+
+	default:
+		goto bad;
+	}
+
+	type = handler(addr, instr, regs);
+
+	if (type == TYPE_ERROR || type == TYPE_FAULT)
+		goto bad_or_fault;
+
+	if (type == TYPE_LDST)
+		do_alignment_finish_ldst(addr, instr, regs, offset);
+
+	return 0;
+
+bad_or_fault:
+	if (type == TYPE_ERROR)
+		goto bad;
+	regs->UCreg_pc -= 4;
+	/*
+	 * We got a fault - fix it up, or die.
+	 */
+	do_bad_area(addr, error_code, regs);
+	return 0;
+
+bad:
+	/*
+	 * Oops, we didn't handle the instruction.
+	 * However, we must handle fpu instr firstly.
+	 */
+#ifdef CONFIG_UNICORE_FPU_F64
+	/* handle co.load/store */
+#define CODING_COLS                0xc0000000
+#define COLS_OFFSET_BITS(i)	(i & 0x1FF)
+#define COLS_L_BITS(i)		(i & (1<<24))<