hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

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>
This commit is contained in:
GuanXuetao 2011-01-15 18:17:56 +08:00
parent b50f1704e9
commit 56372b0b2f
10 changed files with 2247 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

17
arch/unicore32/include/asm/mmu.h Normal file
View File

@ -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

87
arch/unicore32/include/asm/mmu_context.h Normal file
View File

@ -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

110
arch/unicore32/include/asm/pgalloc.h Normal file
View File

@ -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

55
arch/unicore32/include/asm/pgtable-hwdef.h Normal file
View File

@ -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

317
arch/unicore32/include/asm/pgtable.h Normal file
View File

@ -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__ */

523
arch/unicore32/mm/alignment.c Normal file
View File

@ -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))
#define COLS_FN_BITS(i) ((i>>14) & 31)
if ((instr & 0xe0000000) == CODING_COLS) {
unsigned int fn = COLS_FN_BITS(instr);
unsigned long val = 0;
if (COLS_L_BITS(instr)) {
get32t_unaligned_check(val, addr);
switch (fn) {
#define ASM_MTF(n) case n: \
__asm__ __volatile__("MTF %0, F" __stringify(n) \
: : "r"(val)); \
break;
ASM_MTF(0); ASM_MTF(1); ASM_MTF(2); ASM_MTF(3);
ASM_MTF(4); ASM_MTF(5); ASM_MTF(6); ASM_MTF(7);
ASM_MTF(8); ASM_MTF(9); ASM_MTF(10); ASM_MTF(11);
ASM_MTF(12); ASM_MTF(13); ASM_MTF(14); ASM_MTF(15);
ASM_MTF(16); ASM_MTF(17); ASM_MTF(18); ASM_MTF(19);
ASM_MTF(20); ASM_MTF(21); ASM_MTF(22); ASM_MTF(23);
ASM_MTF(24); ASM_MTF(25); ASM_MTF(26); ASM_MTF(27);
ASM_MTF(28); ASM_MTF(29); ASM_MTF(30); ASM_MTF(31);
#undef ASM_MTF
}
} else {
switch (fn) {
#define ASM_MFF(n) case n: \
__asm__ __volatile__("MFF %0, F" __stringify(n) \
: : "r"(val)); \
break;
ASM_MFF(0); ASM_MFF(1); ASM_MFF(2); ASM_MFF(3);
ASM_MFF(4); ASM_MFF(5); ASM_MFF(6); ASM_MFF(7);
ASM_MFF(8); ASM_MFF(9); ASM_MFF(10); ASM_MFF(11);
ASM_MFF(12); ASM_MFF(13); ASM_MFF(14); ASM_MFF(15);
ASM_MFF(16); ASM_MFF(17); ASM_MFF(18); ASM_MFF(19);
ASM_MFF(20); ASM_MFF(21); ASM_MFF(22); ASM_MFF(23);
ASM_MFF(24); ASM_MFF(25); ASM_MFF(26); ASM_MFF(27);
ASM_MFF(28); ASM_MFF(29); ASM_MFF(30); ASM_MFF(31);
#undef ASM_MFF
}
put32t_unaligned_check(val, addr);
}
return TYPE_COLS;
}
fault:
return TYPE_FAULT;
#endif
printk(KERN_ERR "Alignment trap: not handling instruction "
"%08lx at [<%08lx>]\n", instr, instrptr);
return 1;
}
/*
* This needs to be done after sysctl_init, otherwise sys/ will be
* overwritten. Actually, this shouldn't be in sys/ at all since
* it isn't a sysctl, and it doesn't contain sysctl information.
*/
static int __init alignment_init(void)
{
hook_fault_code(1, do_alignment, SIGBUS, BUS_ADRALN,
"alignment exception");
return 0;
}
fs_initcall(alignment_init);

24
arch/unicore32/mm/extable.c Normal file
View File

@ -0,0 +1,24 @@
/*
* linux/arch/unicore32/mm/extable.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.
*/
#include <linux/module.h>
#include <linux/uaccess.h>
int fixup_exception(struct pt_regs *regs)
{
const struct exception_table_entry *fixup;
fixup = search_exception_tables(instruction_pointer(regs));
if (fixup)
regs->UCreg_pc = fixup->fixup;
return fixup != NULL;
}

479
arch/unicore32/mm/fault.c Normal file
View File

@ -0,0 +1,479 @@
/*
* linux/arch/unicore32/mm/fault.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.
*/
#include <linux/module.h>
#include <linux/signal.h>
#include <linux/mm.h>
#include <linux/hardirq.h>
#include <linux/init.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
#include <linux/page-flags.h>
#include <linux/sched.h>
#include <linux/io.h>
#include <asm/system.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
/*
* Fault status register encodings. We steal bit 31 for our own purposes.
*/
#define FSR_LNX_PF (1 << 31)
static inline int fsr_fs(unsigned int fsr)
{
/* xyabcde will be abcde+xy */
return (fsr & 31) + ((fsr & (3 << 5)) >> 5);
}
/*
* This is useful to dump out the page tables associated with
* 'addr' in mm 'mm'.
*/
void show_pte(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
if (!mm)
mm = &init_mm;
printk(KERN_ALERT "pgd = %p\n", mm->pgd);
pgd = pgd_offset(mm, addr);
printk(KERN_ALERT "[%08lx] *pgd=%08lx", addr, pgd_val(*pgd));
do {
pmd_t *pmd;
pte_t *pte;
if (pgd_none(*pgd))
break;
if (pgd_bad(*pgd)) {
printk("(bad)");
break;
}
pmd = pmd_offset((pud_t *) pgd, addr);
if (PTRS_PER_PMD != 1)
printk(", *pmd=%08lx", pmd_val(*pmd));
if (pmd_none(*pmd))
break;
if (pmd_bad(*pmd)) {
printk("(bad)");
break;
}
/* We must not map this if we have highmem enabled */
if (PageHighMem(pfn_to_page(pmd_val(*pmd) >> PAGE_SHIFT)))
break;
pte = pte_offset_map(pmd, addr);
printk(", *pte=%08lx", pte_val(*pte));
pte_unmap(pte);
} while (0);
printk("\n");
}
/*
* Oops. The kernel tried to access some page that wasn't present.
*/
static void __do_kernel_fault(struct mm_struct *mm, unsigned long addr,
unsigned int fsr, struct pt_regs *regs)
{
/*
* Are we prepared to handle this kernel fault?
*/
if (fixup_exception(regs))
return;
/*
* No handler, we'll have to terminate things with extreme prejudice.
*/
bust_spinlocks(1);
printk(KERN_ALERT
"Unable to handle kernel %s at virtual address %08lx\n",
(addr < PAGE_SIZE) ? "NULL pointer dereference" :
"paging request", addr);
show_pte(mm, addr);
die("Oops", regs, fsr);
bust_spinlocks(0);
do_exit(SIGKILL);
}
/*
* Something tried to access memory that isn't in our memory map..
* User mode accesses just cause a SIGSEGV
*/
static void __do_user_fault(struct task_struct *tsk, unsigned long addr,
unsigned int fsr, unsigned int sig, int code,
struct pt_regs *regs)
{
struct siginfo si;
tsk->thread.address = addr;
tsk->thread.error_code = fsr;
tsk->thread.trap_no = 14;
si.si_signo = sig;
si.si_errno = 0;
si.si_code = code;
si.si_addr = (void __user *)addr;
force_sig_info(sig, &si, tsk);
}
void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->active_mm;
/*
* If we are in kernel mode at this point, we
* have no context to handle this fault with.
*/
if (user_mode(regs))
__do_user_fault(tsk, addr, fsr, SIGSEGV, SEGV_MAPERR, regs);
else
__do_kernel_fault(mm, addr, fsr, regs);
}
#define VM_FAULT_BADMAP 0x010000
#define VM_FAULT_BADACCESS 0x020000
/*
* Check that the permissions on the VMA allow for the fault which occurred.
* If we encountered a write fault, we must have write permission, otherwise
* we allow any permission.
*/
static inline bool access_error(unsigned int fsr, struct vm_area_struct *vma)
{
unsigned int mask = VM_READ | VM_WRITE | VM_EXEC;
if (!(fsr ^ 0x12)) /* write? */
mask = VM_WRITE;
if (fsr & FSR_LNX_PF)
mask = VM_EXEC;
return vma->vm_flags & mask ? false : true;
}
static int __do_pf(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
struct task_struct *tsk)
{
struct vm_area_struct *vma;
int fault;
vma = find_vma(mm, addr);
fault = VM_FAULT_BADMAP;
if (unlikely(!vma))
goto out;
if (unlikely(vma->vm_start > addr))
goto check_stack;
/*
* Ok, we have a good vm_area for this
* memory access, so we can handle it.
*/
good_area:
if (access_error(fsr, vma)) {
fault = VM_FAULT_BADACCESS;
goto out;
}
/*
* If for any reason at all we couldn't handle the fault, make
* sure we exit gracefully rather than endlessly redo the fault.
*/
fault = handle_mm_fault(mm, vma, addr & PAGE_MASK,
(!(fsr ^ 0x12)) ? FAULT_FLAG_WRITE : 0);
if (unlikely(fault & VM_FAULT_ERROR))
return fault;
if (fault & VM_FAULT_MAJOR)
tsk->maj_flt++;
else
tsk->min_flt++;
return fault;
check_stack:
if (vma->vm_flags & VM_GROWSDOWN && !expand_stack(vma, addr))
goto good_area;
out:
return fault;
}
static int do_pf(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
struct task_struct *tsk;
struct mm_struct *mm;
int fault, sig, code;
tsk = current;
mm = tsk->mm;
/*
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
if (in_atomic() || !mm)
goto no_context;
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
* we can bug out early if this is from code which shouldn't.
*/
if (!down_read_trylock(&mm->mmap_sem)) {
if (!user_mode(regs)
&& !search_exception_tables(regs->UCreg_pc))
goto no_context;
down_read(&mm->mmap_sem);
} else {
/*
* The above down_read_trylock() might have succeeded in
* which case, we'll have missed the might_sleep() from
* down_read()
*/
might_sleep();
#ifdef CONFIG_DEBUG_VM
if (!user_mode(regs) &&
!search_exception_tables(regs->UCreg_pc))
goto no_context;
#endif
}
fault = __do_pf(mm, addr, fsr, tsk);
up_read(&mm->mmap_sem);
/*
* Handle the "normal" case first - VM_FAULT_MAJOR / VM_FAULT_MINOR
*/
if (likely(!(fault &
(VM_FAULT_ERROR | VM_FAULT_BADMAP | VM_FAULT_BADACCESS))))
return 0;
if (fault & VM_FAULT_OOM) {
/*
* We ran out of memory, call the OOM killer, and return to
* userspace (which will retry the fault, or kill us if we
* got oom-killed)
*/
pagefault_out_of_memory();
return 0;
}
/*
* If we are in kernel mode at this point, we
* have no context to handle this fault with.
*/
if (!user_mode(regs))
goto no_context;
if (fault & VM_FAULT_SIGBUS) {
/*
* We had some memory, but were unable to
* successfully fix up this page fault.
*/
sig = SIGBUS;
code = BUS_ADRERR;
} else {
/*
* Something tried to access memory that
* isn't in our memory map..
*/
sig = SIGSEGV;
code = fault == VM_FAULT_BADACCESS ? SEGV_ACCERR : SEGV_MAPERR;
}
__do_user_fault(tsk, addr, fsr, sig, code, regs);
return 0;
no_context:
__do_kernel_fault(mm, addr, fsr, regs);
return 0;
}
/*
* First Level Translation Fault Handler
*
* We enter here because the first level page table doesn't contain
* a valid entry for the address.
*
* If the address is in kernel space (>= TASK_SIZE), then we are
* probably faulting in the vmalloc() area.
*
* If the init_task's first level page tables contains the relevant
* entry, we copy the it to this task. If not, we send the process
* a signal, fixup the exception, or oops the kernel.
*
* NOTE! We MUST NOT take any locks for this case. We may be in an
* interrupt or a critical region, and should only copy the information
* from the master page table, nothing more.
*/
static int do_ifault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
unsigned int index;
pgd_t *pgd, *pgd_k;
pmd_t *pmd, *pmd_k;
if (addr < TASK_SIZE)
return do_pf(addr, fsr, regs);
if (user_mode(regs))
goto bad_area;
index = pgd_index(addr);
pgd = cpu_get_pgd() + index;
pgd_k = init_mm.pgd + index;
if (pgd_none(*pgd_k))
goto bad_area;
pmd_k = pmd_offset((pud_t *) pgd_k, addr);
pmd = pmd_offset((pud_t *) pgd, addr);
if (pmd_none(*pmd_k))
goto bad_area;
set_pmd(pmd, *pmd_k);
flush_pmd_entry(pmd);
return 0;
bad_area:
do_bad_area(addr, fsr, regs);
return 0;
}
/*
* This abort handler always returns "fault".
*/
static int do_bad(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
return 1;
}
static int do_good(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
unsigned int res1, res2;
printk("dabt exception but no error!\n");
__asm__ __volatile__(
"mff %0,f0\n"
"mff %1,f1\n"
: "=r"(res1), "=r"(res2)
:
: "memory");
printk(KERN_EMERG "r0 :%08x r1 :%08x\n", res1, res2);
panic("shut up\n");
return 0;
}
static struct fsr_info {
int (*fn) (unsigned long addr, unsigned int fsr, struct pt_regs *regs);
int sig;
int code;
const char *name;
} fsr_info[] = {
/*
* The following are the standard Unicore-I and UniCore-II aborts.
*/
{ do_good, SIGBUS, 0, "no error" },
{ do_bad, SIGBUS, BUS_ADRALN, "alignment exception" },
{ do_bad, SIGBUS, BUS_OBJERR, "external exception" },
{ do_bad, SIGBUS, 0, "burst operation" },
{ do_bad, SIGBUS, 0, "unknown 00100" },
{ do_ifault, SIGSEGV, SEGV_MAPERR, "2nd level pt non-exist"},
{ do_bad, SIGBUS, 0, "2nd lvl large pt non-exist" },
{ do_bad, SIGBUS, 0, "invalid pte" },
{ do_pf, SIGSEGV, SEGV_MAPERR, "page miss" },
{ do_bad, SIGBUS, 0, "middle page miss" },
{ do_bad, SIGBUS, 0, "large page miss" },
{ do_pf, SIGSEGV, SEGV_MAPERR, "super page (section) miss" },
{ do_bad, SIGBUS, 0, "unknown 01100" },
{ do_bad, SIGBUS, 0, "unknown 01101" },
{ do_bad, SIGBUS, 0, "unknown 01110" },
{ do_bad, SIGBUS, 0, "unknown 01111" },
{ do_bad, SIGBUS, 0, "addr: up 3G or IO" },
{ do_pf, SIGSEGV, SEGV_ACCERR, "read unreadable addr" },
{ do_pf, SIGSEGV, SEGV_ACCERR, "write unwriteable addr"},
{ do_pf, SIGSEGV, SEGV_ACCERR, "exec unexecutable addr"},
{ do_bad, SIGBUS, 0, "unknown 10100" },
{ do_bad, SIGBUS, 0, "unknown 10101" },
{ do_bad, SIGBUS, 0, "unknown 10110" },
{ do_bad, SIGBUS, 0, "unknown 10111" },
{ do_bad, SIGBUS, 0, "unknown 11000" },
{ do_bad, SIGBUS, 0, "unknown 11001" },
{ do_bad, SIGBUS, 0, "unknown 11010" },
{ do_bad, SIGBUS, 0, "unknown 11011" },
{ do_bad, SIGBUS, 0, "unknown 11100" },
{ do_bad, SIGBUS, 0, "unknown 11101" },
{ do_bad, SIGBUS, 0, "unknown 11110" },
{ do_bad, SIGBUS, 0, "unknown 11111" }
};
void __init hook_fault_code(int nr,
int (*fn) (unsigned long, unsigned int, struct pt_regs *),
int sig, int code, const char *name)
{
if (nr < 0 || nr >= ARRAY_SIZE(fsr_info))
BUG();
fsr_info[nr].fn = fn;
fsr_info[nr].sig = sig;
fsr_info[nr].code = code;
fsr_info[nr].name = name;
}
/*
* Dispatch a data abort to the relevant handler.
*/
asmlinkage void do_DataAbort(unsigned long addr, unsigned int fsr,
struct pt_regs *regs)
{
const struct fsr_info *inf = fsr_info + fsr_fs(fsr);
struct siginfo info;
if (!inf->fn(addr, fsr & ~FSR_LNX_PF, regs))
return;
printk(KERN_ALERT "Unhandled fault: %s (0x%03x) at 0x%08lx\n",
inf->name, fsr, addr);
info.si_signo = inf->sig;
info.si_errno = 0;
info.si_code = inf->code;
info.si_addr = (void __user *)addr;
uc32_notify_die("", regs, &info, fsr, 0);
}
asmlinkage void do_PrefetchAbort(unsigned long addr,
unsigned int ifsr, struct pt_regs *regs)
{
const struct fsr_info *inf = fsr_info + fsr_fs(ifsr);
struct siginfo info;
if (!inf->fn(addr, ifsr | FSR_LNX_PF, regs))
return;
printk(KERN_ALERT "Unhandled prefetch abort: %s (0x%03x) at 0x%08lx\n",
inf->name, ifsr, addr);
info.si_signo = inf->sig;
info.si_errno = 0;
info.si_code = inf->code;
info.si_addr = (void __user *)addr;
uc32_notify_die("", regs, &info, ifsr, 0);
}

533
arch/unicore32/mm/mmu.c Normal file
View File

@ -0,0 +1,533 @@
/*
* linux/arch/unicore32/mm/mmu.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.
*/
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/init.h>
#include <linux/mman.h>
#include <linux/nodemask.h>
#include <linux/memblock.h>
#include <linux/fs.h>
#include <linux/bootmem.h>
#include <linux/io.h>
#include <asm/cputype.h>
#include <asm/sections.h>
#include <asm/setup.h>
#include <asm/sizes.h>
#include <asm/tlb.h>
#include <mach/map.h>
#include "mm.h"
DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
/*
* empty_zero_page is a special page that is used for
* zero-initialized data and COW.
*/
struct page *empty_zero_page;
EXPORT_SYMBOL(empty_zero_page);
/*
* The pmd table for the upper-most set of pages.
*/
pmd_t *top_pmd;
pgprot_t pgprot_user;
EXPORT_SYMBOL(pgprot_user);
pgprot_t pgprot_kernel;
EXPORT_SYMBOL(pgprot_kernel);
static int __init noalign_setup(char *__unused)
{
cr_alignment &= ~CR_A;
cr_no_alignment &= ~CR_A;
set_cr(cr_alignment);
return 1;
}
__setup("noalign", noalign_setup);
void adjust_cr(unsigned long mask, unsigned long set)
{
unsigned long flags;
mask &= ~CR_A;
set &= mask;
local_irq_save(flags);
cr_no_alignment = (cr_no_alignment & ~mask) | set;
cr_alignment = (cr_alignment & ~mask) | set;
set_cr((get_cr() & ~mask) | set);
local_irq_restore(flags);
}
struct map_desc {
unsigned long virtual;
unsigned long pfn;
unsigned long length;
unsigned int type;
};
#define PROT_PTE_DEVICE (PTE_PRESENT | PTE_YOUNG | \
PTE_DIRTY | PTE_READ | PTE_WRITE)
#define PROT_SECT_DEVICE (PMD_TYPE_SECT | PMD_PRESENT | \
PMD_SECT_READ | PMD_SECT_WRITE)
static struct mem_type mem_types[] = {
[MT_DEVICE] = { /* Strongly ordered */
.prot_pte = PROT_PTE_DEVICE,
.prot_l1 = PMD_TYPE_TABLE | PMD_PRESENT,
.prot_sect = PROT_SECT_DEVICE,
},
/*
* MT_KUSER: pte for vecpage -- cacheable,
* and sect for unigfx mmap -- noncacheable
*/
[MT_KUSER] = {
.prot_pte = PTE_PRESENT | PTE_YOUNG | PTE_DIRTY |
PTE_CACHEABLE | PTE_READ | PTE_EXEC,
.prot_l1 = PMD_TYPE_TABLE | PMD_PRESENT,
.prot_sect = PROT_SECT_DEVICE,
},
[MT_HIGH_VECTORS] = {
.prot_pte = PTE_PRESENT | PTE_YOUNG | PTE_DIRTY |
PTE_CACHEABLE | PTE_READ | PTE_WRITE |
PTE_EXEC,
.prot_l1 = PMD_TYPE_TABLE | PMD_PRESENT,
},
[MT_MEMORY] = {
.prot_pte = PTE_PRESENT | PTE_YOUNG | PTE_DIRTY |
PTE_WRITE | PTE_EXEC,
.prot_l1 = PMD_TYPE_TABLE | PMD_PRESENT,
.prot_sect = PMD_TYPE_SECT | PMD_PRESENT | PMD_SECT_CACHEABLE |
PMD_SECT_READ | PMD_SECT_WRITE | PMD_SECT_EXEC,
},
[MT_ROM] = {
.prot_sect = PMD_TYPE_SECT | PMD_PRESENT | PMD_SECT_CACHEABLE |
PMD_SECT_READ,
},
};
const struct mem_type *get_mem_type(unsigned int type)
{
return type < ARRAY_SIZE(mem_types) ? &mem_types[type] : NULL;
}
EXPORT_SYMBOL(get_mem_type);
/*
* Adjust the PMD section entries according to the CPU in use.
*/
static void __init build_mem_type_table(void)
{
pgprot_user = __pgprot(PTE_PRESENT | PTE_YOUNG | PTE_CACHEABLE);
pgprot_kernel = __pgprot(PTE_PRESENT | PTE_YOUNG |
PTE_DIRTY | PTE_READ | PTE_WRITE |
PTE_EXEC | PTE_CACHEABLE);
}
#define vectors_base() (vectors_high() ? 0xffff0000 : 0)
static void __init *early_alloc(unsigned long sz)
{
void *ptr = __va(memblock_alloc(sz, sz));
memset(ptr, 0, sz);
return ptr;
}
static pte_t * __init early_pte_alloc(pmd_t *pmd, unsigned long addr,
unsigned long prot)
{
if (pmd_none(*pmd)) {
pte_t *pte = early_alloc(PTRS_PER_PTE * sizeof(pte_t));
__pmd_populate(pmd, __pa(pte) | prot);
}
BUG_ON(pmd_bad(*pmd));
return pte_offset_kernel(pmd, addr);
}
static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
unsigned long end, unsigned long pfn,
const struct mem_type *type)
{
pte_t *pte = early_pte_alloc(pmd, addr, type->prot_l1);
do {
set_pte(pte, pfn_pte(pfn, __pgprot(type->prot_pte)));
pfn++;
} while (pte++, addr += PAGE_SIZE, addr != end);
}
static void __init alloc_init_section(pgd_t *pgd, unsigned long addr,
unsigned long end, unsigned long phys,
const struct mem_type *type)
{
pmd_t *pmd = pmd_offset((pud_t *)pgd, addr);
/*
* Try a section mapping - end, addr and phys must all be aligned
* to a section boundary.
*/
if (((addr | end | phys) & ~SECTION_MASK) == 0) {
pmd_t *p = pmd;
do {
set_pmd(pmd, __pmd(phys | type->prot_sect));
phys += SECTION_SIZE;
} while (pmd++, addr += SECTION_SIZE, addr != end);
flush_pmd_entry(p);
} else {
/*
* No need to loop; pte's aren't interested in the
* individual L1 entries.
*/
alloc_init_pte(pmd, addr, end, __phys_to_pfn(phys), type);
}
}
/*
* Create the page directory entries and any necessary
* page tables for the mapping specified by `md'. We
* are able to cope here with varying sizes and address
* offsets, and we take full advantage of sections.
*/
static void __init create_mapping(struct map_desc *md)
{
unsigned long phys, addr, length, end;
const struct mem_type *type;
pgd_t *pgd;
if (md->virtual != vectors_base() && md->virtual < TASK_SIZE) {
printk(KERN_WARNING "BUG: not creating mapping for "
"0x%08llx at 0x%08lx in user region\n",
__pfn_to_phys((u64)md->pfn), md->virtual);
return;
}
if ((md->type == MT_DEVICE || md->type == MT_ROM) &&
md->virtual >= PAGE_OFFSET && md->virtual < VMALLOC_END) {
printk(KERN_WARNING "BUG: mapping for 0x%08llx at 0x%08lx "
"overlaps vmalloc space\n",
__pfn_to_phys((u64)md->pfn), md->virtual);
}
type = &mem_types[md->type];
addr = md->virtual & PAGE_MASK;
phys = (unsigned long)__pfn_to_phys(md->pfn);
length = PAGE_ALIGN(md->length + (md->virtual & ~PAGE_MASK));
if (type->prot_l1 == 0 && ((addr | phys | length) & ~SECTION_MASK)) {
printk(KERN_WARNING "BUG: map for 0x%08lx at 0x%08lx can not "
"be mapped using pages, ignoring.\n",
__pfn_to_phys(md->pfn), addr);
return;
}
pgd = pgd_offset_k(addr);
end = addr + length;
do {
unsigned long next = pgd_addr_end(addr, end);
alloc_init_section(pgd, addr, next, phys, type);
phys += next - addr;
addr = next;
} while (pgd++, addr != end);
}
static void * __initdata vmalloc_min = (void *)(VMALLOC_END - SZ_128M);
/*
* vmalloc=size forces the vmalloc area to be exactly 'size'
* bytes. This can be used to increase (or decrease) the vmalloc
* area - the default is 128m.
*/
static int __init early_vmalloc(char *arg)
{
unsigned long vmalloc_reserve = memparse(arg, NULL);
if (vmalloc_reserve < SZ_16M) {
vmalloc_reserve = SZ_16M;
printk(KERN_WARNING
"vmalloc area too small, limiting to %luMB\n",
vmalloc_reserve >> 20);
}
if (vmalloc_reserve > VMALLOC_END - (PAGE_OFFSET + SZ_32M)) {
vmalloc_reserve = VMALLOC_END - (PAGE_OFFSET + SZ_32M);
printk(KERN_WARNING
"vmalloc area is too big, limiting to %luMB\n",
vmalloc_reserve >> 20);
}
vmalloc_min = (void *)(VMALLOC_END - vmalloc_reserve);
return 0;
}
early_param("vmalloc", early_vmalloc);
static phys_addr_t lowmem_limit __initdata = SZ_1G;
static void __init sanity_check_meminfo(void)
{
int i, j;
lowmem_limit = __pa(vmalloc_min - 1) + 1;
memblock_set_current_limit(lowmem_limit);
for (i = 0, j = 0; i < meminfo.nr_banks; i++) {
struct membank *bank = &meminfo.bank[j];
*bank = meminfo.bank[i];
j++;
}
meminfo.nr_banks = j;
}
static inline void prepare_page_table(void)
{
unsigned long addr;
phys_addr_t end;
/*
* Clear out all the mappings below the kernel image.
*/
for (addr = 0; addr < MODULES_VADDR; addr += PGDIR_SIZE)
pmd_clear(pmd_off_k(addr));
for ( ; addr < PAGE_OFFSET; addr += PGDIR_SIZE)
pmd_clear(pmd_off_k(addr));
/*
* Find the end of the first block of lowmem.
*/
end = memblock.memory.regions[0].base + memblock.memory.regions[0].size;
if (end >= lowmem_limit)
end = lowmem_limit;
/*
* Clear out all the kernel space mappings, except for the first
* memory bank, up to the end of the vmalloc region.
*/
for (addr = __phys_to_virt(end);
addr < VMALLOC_END; addr += PGDIR_SIZE)
pmd_clear(pmd_off_k(addr));
}
/*
* Reserve the special regions of memory
*/
void __init uc32_mm_memblock_reserve(void)
{
/*
* Reserve the page tables. These are already in use,
* and can only be in node 0.
*/
memblock_reserve(__pa(swapper_pg_dir), PTRS_PER_PGD * sizeof(pgd_t));
#ifdef CONFIG_PUV3_UNIGFX
/*
* These should likewise go elsewhere. They pre-reserve the
* screen/video memory region at the 48M~64M of main system memory.
*/
memblock_reserve(PKUNITY_UNIGFX_MMAP_BASE, PKUNITY_UNIGFX_MMAP_SIZE);
memblock_reserve(PKUNITY_UVC_MMAP_BASE, PKUNITY_UVC_MMAP_SIZE);
#endif
}
/*
* Set up device the mappings. Since we clear out the page tables for all
* mappings above VMALLOC_END, we will remove any debug device mappings.
* This means you have to be careful how you debug this function, or any
* called function. This means you can't use any function or debugging
* method which may touch any device, otherwise the kernel _will_ crash.
*/
static void __init devicemaps_init(void)
{
struct map_desc map;
unsigned long addr;
void *vectors;
/*
* Allocate the vector page early.
*/
vectors = early_alloc(PAGE_SIZE);
for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE)
pmd_clear(pmd_off_k(addr));
/*
* Create a mapping for UniGFX VRAM
*/
#ifdef CONFIG_PUV3_UNIGFX
map.pfn = __phys_to_pfn(PKUNITY_UNIGFX_MMAP_BASE);
map.virtual = KUSER_UNIGFX_BASE;
map.length = PKUNITY_UNIGFX_MMAP_SIZE;
map.type = MT_KUSER;
create_mapping(&map);
#endif
/*
* Create a mapping for the machine vectors at the high-vectors
* location (0xffff0000). If we aren't using high-vectors, also
* create a mapping at the low-vectors virtual address.
*/
map.pfn = __phys_to_pfn(virt_to_phys(vectors));
map.virtual = VECTORS_BASE;
map.length = PAGE_SIZE;
map.type = MT_HIGH_VECTORS;
create_mapping(&map);
/*
* Create a mapping for the kuser page at the special
* location (0xbfff0000) to the same vectors location.
*/
map.pfn = __phys_to_pfn(virt_to_phys(vectors));
map.virtual = KUSER_VECPAGE_BASE;
map.length = PAGE_SIZE;
map.type = MT_KUSER;
create_mapping(&map);
/*
* Finally flush the caches and tlb to ensure that we're in a
* consistent state wrt the writebuffer. This also ensures that
* any write-allocated cache lines in the vector page are written
* back. After this point, we can start to touch devices again.
*/
local_flush_tlb_all();
flush_cache_all();
}
static void __init map_lowmem(void)
{
struct memblock_region *reg;
/* Map all the lowmem memory banks. */
for_each_memblock(memory, reg) {
phys_addr_t start = reg->base;
phys_addr_t end = start + reg->size;
struct map_desc map;
if (end > lowmem_limit)
end = lowmem_limit;
if (start >= end)
break;
map.pfn = __phys_to_pfn(start);
map.virtual = __phys_to_virt(start);
map.length = end - start;
map.type = MT_MEMORY;
create_mapping(&map);
}
}
/*
* paging_init() sets up the page tables, initialises the zone memory
* maps, and sets up the zero page, bad page and bad page tables.
*/
void __init paging_init(void)
{
void *zero_page;
build_mem_type_table();
sanity_check_meminfo();
prepare_page_table();
map_lowmem();
devicemaps_init();
top_pmd = pmd_off_k(0xffff0000);
/* allocate the zero page. */
zero_page = early_alloc(PAGE_SIZE);
bootmem_init();
empty_zero_page = virt_to_page(zero_page);
__flush_dcache_page(NULL, empty_zero_page);
}
/*
* In order to soft-boot, we need to insert a 1:1 mapping in place of
* the user-mode pages. This will then ensure that we have predictable
* results when turning the mmu off
*/
void setup_mm_for_reboot(char mode)
{
unsigned long base_pmdval;
pgd_t *pgd;
int i;
/*
* We need to access to user-mode page tables here. For kernel threads
* we don't have any user-mode mappings so we use the context that we
* "borrowed".
*/
pgd = current->active_mm->pgd;
base_pmdval = PMD_SECT_WRITE | PMD_SECT_READ | PMD_TYPE_SECT;
for (i = 0; i < FIRST_USER_PGD_NR + USER_PTRS_PER_PGD; i++, pgd++) {
unsigned long pmdval = (i << PGDIR_SHIFT) | base_pmdval;
pmd_t *pmd;
pmd = pmd_off(pgd, i << PGDIR_SHIFT);
set_pmd(pmd, __pmd(pmdval));
flush_pmd_entry(pmd);
}
local_flush_tlb_all();
}
/*
* Take care of architecture specific things when placing a new PTE into
* a page table, or changing an existing PTE. Basically, there are two
* things that we need to take care of:
*
* 1. If PG_dcache_clean is not set for the page, we need to ensure
* that any cache entries for the kernels virtual memory
* range are written back to the page.
* 2. If we have multiple shared mappings of the same space in
* an object, we need to deal with the cache aliasing issues.
*
* Note that the pte lock will be held.
*/
void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
pte_t *ptep)
{
unsigned long pfn = pte_pfn(*ptep);
struct address_space *mapping;
struct page *page;
if (!pfn_valid(pfn))
return;
/*
* The zero page is never written to, so never has any dirty
* cache lines, and therefore never needs to be flushed.
*/
page = pfn_to_page(pfn);
if (page == ZERO_PAGE(0))
return;
mapping = page_mapping(page);
if (!test_and_set_bit(PG_dcache_clean, &page->flags))
__flush_dcache_page(mapping, page);
if (mapping)
if (vma->vm_flags & VM_EXEC)
__flush_icache_all();
}

102
arch/unicore32/mm/pgd.c Normal file
View File

@ -0,0 +1,102 @@
/*
* linux/arch/unicore32/mm/pgd.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.
*/
#include <linux/mm.h>
#include <linux/gfp.h>
#include <linux/highmem.h>
#include <asm/pgalloc.h>
#include <asm/page.h>
#include <asm/tlbflush.h>
#include "mm.h"
#define FIRST_KERNEL_PGD_NR (FIRST_USER_PGD_NR + USER_PTRS_PER_PGD)
/*
* need to get a 4k page for level 1
*/
pgd_t *get_pgd_slow(struct mm_struct *mm)
{
pgd_t *new_pgd, *init_pgd;
pmd_t *new_pmd, *init_pmd;
pte_t *new_pte, *init_pte;
new_pgd = (pgd_t *)__get_free_pages(GFP_KERNEL, 0);
if (!new_pgd)
goto no_pgd;
memset(new_pgd, 0, FIRST_KERNEL_PGD_NR * sizeof(pgd_t));
/*
* Copy over the kernel and IO PGD entries
*/
init_pgd = pgd_offset_k(0);
memcpy(new_pgd + FIRST_KERNEL_PGD_NR, init_pgd + FIRST_KERNEL_PGD_NR,
(PTRS_PER_PGD - FIRST_KERNEL_PGD_NR) * sizeof(pgd_t));
clean_dcache_area(new_pgd, PTRS_PER_PGD * sizeof(pgd_t));
if (!vectors_high()) {
/*
* On UniCore, first page must always be allocated since it
* contains the machine vectors.
*/
new_pmd = pmd_alloc(mm, (pud_t *)new_pgd, 0);
if (!new_pmd)
goto no_pmd;
new_pte = pte_alloc_map(mm, new_pmd, 0);
if (!new_pte)
goto no_pte;
init_pmd = pmd_offset((pud_t *)init_pgd, 0);
init_pte = pte_offset_map(init_pmd, 0);
set_pte(new_pte, *init_pte);
pte_unmap(init_pte);
pte_unmap(new_pte);
}
return new_pgd;
no_pte:
pmd_free(mm, new_pmd);
no_pmd:
free_pages((unsigned long)new_pgd, 0);
no_pgd:
return NULL;
}
void free_pgd_slow(struct mm_struct *mm, pgd_t *pgd)
{
pmd_t *pmd;
pgtable_t pte;
if (!pgd)
return;
/* pgd is always present and good */
pmd = pmd_off(pgd, 0);
if (pmd_none(*pmd))
goto free;
if (pmd_bad(*pmd)) {
pmd_ERROR(*pmd);
pmd_clear(pmd);
goto free;
}
pte = pmd_pgtable(*pmd);
pmd_clear(pmd);
pte_free(mm, pte);
pmd_free(mm, pmd);
free:
free_pages((unsigned long) pgd, 0);
}