pgtable.h

来自「Linux Kernel 2.6.9 for OMAP1710」· C头文件 代码 · 共 423 行

/*
 *  linux/include/asm-arm/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.
 */
#ifndef _ASMARM_PGTABLE_H
#define _ASMARM_PGTABLE_H

#include <asm/memory.h>
#include <asm/proc-fns.h>
#include <asm/arch/vmalloc.h>

/*
 * Hardware-wise, we have a two level page table structure, where the first
 * level has 4096 entries, and the second level has 256 entries.  Each entry
 * is one 32-bit word.  Most of the bits in the second level entry are used
 * by hardware, and there aren't any "accessed" and "dirty" bits.
 *
 * Linux on the other hand has a three level page table structure, which can
 * be wrapped to fit a two level page table structure easily - using the PGD
 * and PTE only.  However, Linux also expects one "PTE" table per page, and
 * at least a "dirty" bit.
 *
 * Therefore, we tweak the implementation slightly - we tell Linux that we
 * have 2048 entries in the first level, each of which is 8 bytes (iow, two
 * hardware pointers to the second level.)  The second level contains two
 * hardware PTE tables arranged contiguously, followed by Linux versions
 * which contain the state information Linux needs.  We, therefore, end up
 * with 512 entries in the "PTE" level.
 *
 * This leads to the page tables having the following layout:
 *
 *    pgd             pte
 * |        |
 * +--------+ +0
 * |        |-----> +------------+ +0
 * +- - - - + +4    |  h/w pt 0  |
 * |        |-----> +------------+ +1024
 * +--------+ +8    |  h/w pt 1  |
 * |        |       +------------+ +2048
 * +- - - - +       | Linux pt 0 |
 * |        |       +------------+ +3072
 * +--------+       | Linux pt 1 |
 * |        |       +------------+ +4096
 *
 * See L_PTE_xxx below for definitions of bits in the "Linux pt", and
 * PTE_xxx for definitions of bits appearing in the "h/w pt".
 *
 * PMD_xxx definitions refer to bits in the first level page table.
 *
 * The "dirty" bit is emulated by only granting hardware write permission
 * iff the page is marked "writable" and "dirty" in the Linux PTE.  This
 * means that a write to a clean page will cause a permission fault, and
 * the Linux MM layer will mark the page dirty via handle_pte_fault().
 * For the hardware to notice the permission change, the TLB entry must
 * be flushed, and ptep_establish() does that for us.
 *
 * The "accessed" or "young" bit is emulated by a similar method; we only
 * allow accesses to the page if the "young" bit is set.  Accesses to the
 * page will cause a fault, and handle_pte_fault() will set the young bit
 * for us as long as the page is marked present in the corresponding Linux
 * PTE entry.  Again, ptep_establish() will ensure that the TLB is up to
 * date.
 *
 * However, when the "young" bit is cleared, we deny access to the page
 * by clearing the hardware PTE.  Currently Linux does not flush the TLB
 * for us in this case, which means the TLB will retain the transation
 * until either the TLB entry is evicted under pressure, or a context
 * switch which changes the user space mapping occurs.
 */
#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
#define PGDIR_SHIFT		21

#define LIBRARY_TEXT_START	0x0c000000

#ifndef __ASSEMBLY__
extern void __pte_error(const char *file, int line, unsigned long val);
extern void __pmd_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 pmd_ERROR(pmd)		__pmd_error(__FILE__, __LINE__, pmd_val(pmd))
#define pgd_ERROR(pgd)		__pgd_error(__FILE__, __LINE__, pgd_val(pgd))
#endif /* !__ASSEMBLY__ */

#define PMD_SIZE		(1UL << PMD_SHIFT)
#define PMD_MASK		(~(PMD_SIZE-1))
#define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
#define PGDIR_MASK		(~(PGDIR_SIZE-1))

#define FIRST_USER_PGD_NR	1
#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_MASK		(3 << 4)
#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_MASK	(0xff << 4)
#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)

/*
 * "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 | L_PTE_CACHEABLE | L_PTE_BUFFERABLE
#define _L_PTE_READ	L_PTE_USER | L_PTE_EXEC

extern pgprot_t		pgprot_kernel;

#define PAGE_NONE       __pgprot(_L_PTE_DEFAULT)
#define PAGE_COPY       __pgprot(_L_PTE_DEFAULT | _L_PTE_READ)
#define PAGE_SHARED     __pgprot(_L_PTE_DEFAULT | _L_PTE_READ | L_PTE_WRITE)
#define PAGE_READONLY   __pgprot(_L_PTE_DEFAULT | _L_PTE_READ)
#define PAGE_KERNEL	pgprot_kernel

#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:
 *  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
#define __P101  PAGE_READONLY
#define __P110  PAGE_COPY
#define __P111  PAGE_COPY

#define __S000  PAGE_NONE
#define __S001  PAGE_READONLY
#define __S010  PAGE_SHARED
#define __S011  PAGE_SHARED
#define __S100  PAGE_READONLY
#define __S101  PAGE_READONLY
#define __S110  PAGE_SHARED
#define __S111  PAGE_SHARED

#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(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 copy_pmd(pmdpd,pmdps)		\
	do {				\
		pmdpd[0] = pmdps[0];	\
		pmdpd[1] = pmdps[1];	\
		flush_pmd_entry(pmdpd);	\
	} 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.
 */
#define pages_to_mb(x)		((x) >> (20 - PAGE_SHIFT))

/*
 * Conversion functions: convert a page and protection to a page entry,
 * and a page entry and page directory to the page they refer to.
 */
#define mk_pte(page,prot)	pfn_pte(page_to_pfn(page),prot)

/*
 * The "pgd_xxx()" functions here are trivial for a folded two-level
 * setup: the pgd is never bad, and a pmd always exists (as it's folded
 * into the pgd entry)
 */
#define pgd_none(pgd)		(0)
#define pgd_bad(pgd)		(0)
#define pgd_present(pgd)	(1)
#define pgd_clear(pgdp)		do { } while (0)
#define set_pgd(pgd,pgdp)	do { } while (0)

#define page_pte_prot(page,prot)	mk_pte(page, prot)
#define page_pte(page)		mk_pte(page, __pgprot(0))

/* 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 second-level page table.. */
#define pmd_offset(dir, addr)	((pmd_t *)(dir))

/* 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 = L_PTE_EXEC | L_PTE_WRITE | L_PTE_USER;
	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.
 *
 * We support up to 32GB of swap on 4k machines
 */
#define __swp_type(x)		(((x).val >> 2) & 0x7f)
#define __swp_offset(x)		((x).val >> 9)
#define __swp_entry(type,offset) ((swp_entry_t) { ((type) << 2) | ((offset) << 9) })
#define __pte_to_swp_entry(pte)	((swp_entry_t) { pte_val(pte) })
#define __swp_entry_to_pte(swp)	((pte_t) { (swp).val })

/* 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>

/*
* We provide our own get_unmapped_area to cope with VIPT caches.
 */
#define HAVE_ARCH_UNMAPPED_AREA

/*

 * remap a physical address `phys' of size `size' with page protection `prot'
 * into virtual address `from'
 */
#define io_remap_page_range(vma,from,phys,size,prot) \
		remap_page_range(vma,from,phys,size,prot)

#define pgtable_cache_init() do { } while (0)

#endif /* !__ASSEMBLY__ */

#endif /* _ASMARM_PGTABLE_H */