[mirror_ubuntu-bionic-kernel.git] / arch / x86 / include / asm / pgtable.h

#ifndef _ASM_X86_PGTABLE_H
#define _ASM_X86_PGTABLE_H

#define FIRST_USER_ADDRESS	0

#define _PAGE_BIT_PRESENT	0	/* is present */
#define _PAGE_BIT_RW		1	/* writeable */
#define _PAGE_BIT_USER		2	/* userspace addressable */
#define _PAGE_BIT_PWT		3	/* page write through */
#define _PAGE_BIT_PCD		4	/* page cache disabled */
#define _PAGE_BIT_ACCESSED	5	/* was accessed (raised by CPU) */
#define _PAGE_BIT_DIRTY		6	/* was written to (raised by CPU) */
#define _PAGE_BIT_PSE		7	/* 4 MB (or 2MB) page */
#define _PAGE_BIT_PAT		7	/* on 4KB pages */
#define _PAGE_BIT_GLOBAL	8	/* Global TLB entry PPro+ */
#define _PAGE_BIT_UNUSED1	9	/* available for programmer */
#define _PAGE_BIT_IOMAP		10	/* flag used to indicate IO mapping */
#define _PAGE_BIT_UNUSED3	11
#define _PAGE_BIT_PAT_LARGE	12	/* On 2MB or 1GB pages */
#define _PAGE_BIT_SPECIAL	_PAGE_BIT_UNUSED1
#define _PAGE_BIT_CPA_TEST	_PAGE_BIT_UNUSED1
#define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */

/* If _PAGE_BIT_PRESENT is clear, we use these: */
/* - if the user mapped it with PROT_NONE; pte_present gives true */
#define _PAGE_BIT_PROTNONE	_PAGE_BIT_GLOBAL
/* - set: nonlinear file mapping, saved PTE; unset:swap */
#define _PAGE_BIT_FILE		_PAGE_BIT_DIRTY

#define _PAGE_PRESENT	(_AT(pteval_t, 1) << _PAGE_BIT_PRESENT)
#define _PAGE_RW	(_AT(pteval_t, 1) << _PAGE_BIT_RW)
#define _PAGE_USER	(_AT(pteval_t, 1) << _PAGE_BIT_USER)
#define _PAGE_PWT	(_AT(pteval_t, 1) << _PAGE_BIT_PWT)
#define _PAGE_PCD	(_AT(pteval_t, 1) << _PAGE_BIT_PCD)
#define _PAGE_ACCESSED	(_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED)
#define _PAGE_DIRTY	(_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
#define _PAGE_PSE	(_AT(pteval_t, 1) << _PAGE_BIT_PSE)
#define _PAGE_GLOBAL	(_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
#define _PAGE_UNUSED1	(_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1)
#define _PAGE_IOMAP	(_AT(pteval_t, 1) << _PAGE_BIT_IOMAP)
#define _PAGE_UNUSED3	(_AT(pteval_t, 1) << _PAGE_BIT_UNUSED3)
#define _PAGE_PAT	(_AT(pteval_t, 1) << _PAGE_BIT_PAT)
#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
#define _PAGE_SPECIAL	(_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
#define _PAGE_CPA_TEST	(_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
#define __HAVE_ARCH_PTE_SPECIAL

#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
#define _PAGE_NX	(_AT(pteval_t, 1) << _PAGE_BIT_NX)
#else
#define _PAGE_NX	(_AT(pteval_t, 0))
#endif

#define _PAGE_FILE	(_AT(pteval_t, 1) << _PAGE_BIT_FILE)
#define _PAGE_PROTNONE	(_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)

#define _PAGE_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |	\
			 _PAGE_ACCESSED | _PAGE_DIRTY)
#define _KERNPG_TABLE	(_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED |	\
			 _PAGE_DIRTY)

/* Set of bits not changed in pte_modify */
#define _PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |		\
			 _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY)

#define _PAGE_CACHE_MASK	(_PAGE_PCD | _PAGE_PWT)
#define _PAGE_CACHE_WB		(0)
#define _PAGE_CACHE_WC		(_PAGE_PWT)
#define _PAGE_CACHE_UC_MINUS	(_PAGE_PCD)
#define _PAGE_CACHE_UC		(_PAGE_PCD | _PAGE_PWT)

#define PAGE_NONE	__pgprot(_PAGE_PROTNONE | _PAGE_ACCESSED)
#define PAGE_SHARED	__pgprot(_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \
				 _PAGE_ACCESSED | _PAGE_NX)

#define PAGE_SHARED_EXEC	__pgprot(_PAGE_PRESENT | _PAGE_RW |	\
					 _PAGE_USER | _PAGE_ACCESSED)
#define PAGE_COPY_NOEXEC	__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
					 _PAGE_ACCESSED | _PAGE_NX)
#define PAGE_COPY_EXEC		__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
					 _PAGE_ACCESSED)
#define PAGE_COPY		PAGE_COPY_NOEXEC
#define PAGE_READONLY		__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
					 _PAGE_ACCESSED | _PAGE_NX)
#define PAGE_READONLY_EXEC	__pgprot(_PAGE_PRESENT | _PAGE_USER |	\
					 _PAGE_ACCESSED)

#define __PAGE_KERNEL_EXEC						\
	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_GLOBAL)
#define __PAGE_KERNEL		(__PAGE_KERNEL_EXEC | _PAGE_NX)

#define __PAGE_KERNEL_RO		(__PAGE_KERNEL & ~_PAGE_RW)
#define __PAGE_KERNEL_RX		(__PAGE_KERNEL_EXEC & ~_PAGE_RW)
#define __PAGE_KERNEL_EXEC_NOCACHE	(__PAGE_KERNEL_EXEC | _PAGE_PCD | _PAGE_PWT)
#define __PAGE_KERNEL_WC		(__PAGE_KERNEL | _PAGE_CACHE_WC)
#define __PAGE_KERNEL_NOCACHE		(__PAGE_KERNEL | _PAGE_PCD | _PAGE_PWT)
#define __PAGE_KERNEL_UC_MINUS		(__PAGE_KERNEL | _PAGE_PCD)
#define __PAGE_KERNEL_VSYSCALL		(__PAGE_KERNEL_RX | _PAGE_USER)
#define __PAGE_KERNEL_VSYSCALL_NOCACHE	(__PAGE_KERNEL_VSYSCALL | _PAGE_PCD | _PAGE_PWT)
#define __PAGE_KERNEL_LARGE		(__PAGE_KERNEL | _PAGE_PSE)
#define __PAGE_KERNEL_LARGE_NOCACHE	(__PAGE_KERNEL | _PAGE_CACHE_UC | _PAGE_PSE)
#define __PAGE_KERNEL_LARGE_EXEC	(__PAGE_KERNEL_EXEC | _PAGE_PSE)

#define __PAGE_KERNEL_IO		(__PAGE_KERNEL | _PAGE_IOMAP)
#define __PAGE_KERNEL_IO_NOCACHE	(__PAGE_KERNEL_NOCACHE | _PAGE_IOMAP)
#define __PAGE_KERNEL_IO_UC_MINUS	(__PAGE_KERNEL_UC_MINUS | _PAGE_IOMAP)
#define __PAGE_KERNEL_IO_WC		(__PAGE_KERNEL_WC | _PAGE_IOMAP)

#define PAGE_KERNEL			__pgprot(__PAGE_KERNEL)
#define PAGE_KERNEL_RO			__pgprot(__PAGE_KERNEL_RO)
#define PAGE_KERNEL_EXEC		__pgprot(__PAGE_KERNEL_EXEC)
#define PAGE_KERNEL_RX			__pgprot(__PAGE_KERNEL_RX)
#define PAGE_KERNEL_WC			__pgprot(__PAGE_KERNEL_WC)
#define PAGE_KERNEL_NOCACHE		__pgprot(__PAGE_KERNEL_NOCACHE)
#define PAGE_KERNEL_UC_MINUS		__pgprot(__PAGE_KERNEL_UC_MINUS)
#define PAGE_KERNEL_EXEC_NOCACHE	__pgprot(__PAGE_KERNEL_EXEC_NOCACHE)
#define PAGE_KERNEL_LARGE		__pgprot(__PAGE_KERNEL_LARGE)
#define PAGE_KERNEL_LARGE_NOCACHE	__pgprot(__PAGE_KERNEL_LARGE_NOCACHE)
#define PAGE_KERNEL_LARGE_EXEC		__pgprot(__PAGE_KERNEL_LARGE_EXEC)
#define PAGE_KERNEL_VSYSCALL		__pgprot(__PAGE_KERNEL_VSYSCALL)
#define PAGE_KERNEL_VSYSCALL_NOCACHE	__pgprot(__PAGE_KERNEL_VSYSCALL_NOCACHE)

#define PAGE_KERNEL_IO			__pgprot(__PAGE_KERNEL_IO)
#define PAGE_KERNEL_IO_NOCACHE		__pgprot(__PAGE_KERNEL_IO_NOCACHE)
#define PAGE_KERNEL_IO_UC_MINUS		__pgprot(__PAGE_KERNEL_IO_UC_MINUS)
#define PAGE_KERNEL_IO_WC		__pgprot(__PAGE_KERNEL_IO_WC)

/*         xwr */
#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

/*
 * early identity mapping  pte attrib macros.
 */
#ifdef CONFIG_X86_64
#define __PAGE_KERNEL_IDENT_LARGE_EXEC	__PAGE_KERNEL_LARGE_EXEC
#else
/*
 * For PDE_IDENT_ATTR include USER bit. As the PDE and PTE protection
 * bits are combined, this will alow user to access the high address mapped
 * VDSO in the presence of CONFIG_COMPAT_VDSO
 */
#define PTE_IDENT_ATTR	 0x003		/* PRESENT+RW */
#define PDE_IDENT_ATTR	 0x067		/* PRESENT+RW+USER+DIRTY+ACCESSED */
#define PGD_IDENT_ATTR	 0x001		/* PRESENT (no other attributes) */
#endif

/*
 * Macro to mark a page protection value as UC-
 */
#define pgprot_noncached(prot)					\
	((boot_cpu_data.x86 > 3)				\
	 ? (__pgprot(pgprot_val(prot) | _PAGE_CACHE_UC_MINUS))	\
	 : (prot))

#ifndef __ASSEMBLY__

#define pgprot_writecombine	pgprot_writecombine
extern pgprot_t pgprot_writecombine(pgprot_t prot);

/*
 * ZERO_PAGE is a global shared page that is always zero: used
 * for zero-mapped memory areas etc..
 */
extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))

extern spinlock_t pgd_lock;
extern struct list_head pgd_list;

/*
 * The following only work if pte_present() is true.
 * Undefined behaviour if not..
 */
static inline int pte_dirty(pte_t pte)
{
	return pte_flags(pte) & _PAGE_DIRTY;
}

static inline int pte_young(pte_t pte)
{
	return pte_flags(pte) & _PAGE_ACCESSED;
}

static inline int pte_write(pte_t pte)
{
	return pte_flags(pte) & _PAGE_RW;
}

static inline int pte_file(pte_t pte)
{
	return pte_flags(pte) & _PAGE_FILE;
}

static inline int pte_huge(pte_t pte)
{
	return pte_flags(pte) & _PAGE_PSE;
}

static inline int pte_global(pte_t pte)
{
	return pte_flags(pte) & _PAGE_GLOBAL;
}

static inline int pte_exec(pte_t pte)
{
	return !(pte_flags(pte) & _PAGE_NX);
}

static inline int pte_special(pte_t pte)
{
	return pte_flags(pte) & _PAGE_SPECIAL;
}

static inline unsigned long pte_pfn(pte_t pte)
{
	return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
}

#define pte_page(pte)	pfn_to_page(pte_pfn(pte))

static inline int pmd_large(pmd_t pte)
{
	return (pmd_val(pte) & (_PAGE_PSE | _PAGE_PRESENT)) ==
		(_PAGE_PSE | _PAGE_PRESENT);
}

static inline pte_t pte_mkclean(pte_t pte)
{
	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
}

static inline pte_t pte_mkold(pte_t pte)
{
	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
}

static inline pte_t pte_wrprotect(pte_t pte)
{
	return __pte(pte_val(pte) & ~_PAGE_RW);
}

static inline pte_t pte_mkexec(pte_t pte)
{
	return __pte(pte_val(pte) & ~_PAGE_NX);
}

static inline pte_t pte_mkdirty(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_DIRTY);
}

static inline pte_t pte_mkyoung(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_ACCESSED);
}

static inline pte_t pte_mkwrite(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_RW);
}

static inline pte_t pte_mkhuge(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_PSE);
}

static inline pte_t pte_clrhuge(pte_t pte)
{
	return __pte(pte_val(pte) & ~_PAGE_PSE);
}

static inline pte_t pte_mkglobal(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_GLOBAL);
}

static inline pte_t pte_clrglobal(pte_t pte)
{
	return __pte(pte_val(pte) & ~_PAGE_GLOBAL);
}

static inline pte_t pte_mkspecial(pte_t pte)
{
	return __pte(pte_val(pte) | _PAGE_SPECIAL);
}

extern pteval_t __supported_pte_mask;

static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
{
	return __pte((((phys_addr_t)page_nr << PAGE_SHIFT) |
		      pgprot_val(pgprot)) & __supported_pte_mask);
}

static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
{
	return __pmd((((phys_addr_t)page_nr << PAGE_SHIFT) |
		      pgprot_val(pgprot)) & __supported_pte_mask);
}

static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
{
	pteval_t val = pte_val(pte);

	/*
	 * Chop off the NX bit (if present), and add the NX portion of
	 * the newprot (if present):
	 */
	val &= _PAGE_CHG_MASK;
	val |= pgprot_val(newprot) & (~_PAGE_CHG_MASK) & __supported_pte_mask;

	return __pte(val);
}

/* mprotect needs to preserve PAT bits when updating vm_page_prot */
#define pgprot_modify pgprot_modify
static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
{
	pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK;
	pgprotval_t addbits = pgprot_val(newprot);
	return __pgprot(preservebits | addbits);
}

#define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK)

#define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)

static inline int is_new_memtype_allowed(unsigned long flags,
						unsigned long new_flags)
{
	/*
	 * Certain new memtypes are not allowed with certain
	 * requested memtype:
	 * - request is uncached, return cannot be write-back
	 * - request is write-combine, return cannot be write-back
	 */
	if ((flags == _PAGE_CACHE_UC_MINUS &&
	     new_flags == _PAGE_CACHE_WB) ||
	    (flags == _PAGE_CACHE_WC &&
	     new_flags == _PAGE_CACHE_WB)) {
		return 0;
	}

	return 1;
}

#ifndef __ASSEMBLY__
/* Indicate that x86 has its own track and untrack pfn vma functions */
#define __HAVE_PFNMAP_TRACKING

#define __HAVE_PHYS_MEM_ACCESS_PROT
struct file;
pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
                              unsigned long size, pgprot_t vma_prot);
int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
                              unsigned long size, pgprot_t *vma_prot);
#endif

/* Install a pte for a particular vaddr in kernel space. */
void set_pte_vaddr(unsigned long vaddr, pte_t pte);

#ifdef CONFIG_X86_32
extern void native_pagetable_setup_start(pgd_t *base);
extern void native_pagetable_setup_done(pgd_t *base);
#else
static inline void native_pagetable_setup_start(pgd_t *base) {}
static inline void native_pagetable_setup_done(pgd_t *base) {}
#endif

struct seq_file;
extern void arch_report_meminfo(struct seq_file *m);

#ifdef CONFIG_PARAVIRT
#include <asm/paravirt.h>
#else  /* !CONFIG_PARAVIRT */
#define set_pte(ptep, pte)		native_set_pte(ptep, pte)
#define set_pte_at(mm, addr, ptep, pte)	native_set_pte_at(mm, addr, ptep, pte)

#define set_pte_present(mm, addr, ptep, pte)				\
	native_set_pte_present(mm, addr, ptep, pte)
#define set_pte_atomic(ptep, pte)					\
	native_set_pte_atomic(ptep, pte)

#define set_pmd(pmdp, pmd)		native_set_pmd(pmdp, pmd)

#ifndef __PAGETABLE_PUD_FOLDED
#define set_pgd(pgdp, pgd)		native_set_pgd(pgdp, pgd)
#define pgd_clear(pgd)			native_pgd_clear(pgd)
#endif

#ifndef set_pud
# define set_pud(pudp, pud)		native_set_pud(pudp, pud)
#endif

#ifndef __PAGETABLE_PMD_FOLDED
#define pud_clear(pud)			native_pud_clear(pud)
#endif

#define pte_clear(mm, addr, ptep)	native_pte_clear(mm, addr, ptep)
#define pmd_clear(pmd)			native_pmd_clear(pmd)

#define pte_update(mm, addr, ptep)              do { } while (0)
#define pte_update_defer(mm, addr, ptep)        do { } while (0)

static inline void __init paravirt_pagetable_setup_start(pgd_t *base)
{
	native_pagetable_setup_start(base);
}

static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
{
	native_pagetable_setup_done(base);
}
#endif	/* CONFIG_PARAVIRT */

#endif	/* __ASSEMBLY__ */

#ifdef CONFIG_X86_32
# include "pgtable_32.h"
#else
# include "pgtable_64.h"
#endif

/*
 * the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
 *
 * this macro returns the index of the entry in the pgd page which would
 * control the given virtual address
 */
#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))

/*
 * pgd_offset() returns a (pgd_t *)
 * pgd_index() is used get the offset into the pgd page's array of pgd_t's;
 */
#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
/*
 * a shortcut which implies the use of the kernel's pgd, instead
 * of a process's
 */
#define pgd_offset_k(address) pgd_offset(&init_mm, (address))


#define KERNEL_PGD_BOUNDARY	pgd_index(PAGE_OFFSET)
#define KERNEL_PGD_PTRS		(PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)

#ifndef __ASSEMBLY__

enum {
	PG_LEVEL_NONE,
	PG_LEVEL_4K,
	PG_LEVEL_2M,
	PG_LEVEL_1G,
	PG_LEVEL_NUM
};

#ifdef CONFIG_PROC_FS
extern void update_page_count(int level, unsigned long pages);
#else
static inline void update_page_count(int level, unsigned long pages) { }
#endif

/*
 * Helper function that returns the kernel pagetable entry controlling
 * the virtual address 'address'. NULL means no pagetable entry present.
 * NOTE: the return type is pte_t but if the pmd is PSE then we return it
 * as a pte too.
 */
extern pte_t *lookup_address(unsigned long address, unsigned int *level);

/* local pte updates need not use xchg for locking */
static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
{
	pte_t res = *ptep;

	/* Pure native function needs no input for mm, addr */
	native_pte_clear(NULL, 0, ptep);
	return res;
}

static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
				     pte_t *ptep , pte_t pte)
{
	native_set_pte(ptep, pte);
}

#ifndef CONFIG_PARAVIRT
/*
 * Rules for using pte_update - it must be called after any PTE update which
 * has not been done using the set_pte / clear_pte interfaces.  It is used by
 * shadow mode hypervisors to resynchronize the shadow page tables.  Kernel PTE
 * updates should either be sets, clears, or set_pte_atomic for P->P
 * transitions, which means this hook should only be called for user PTEs.
 * This hook implies a P->P protection or access change has taken place, which
 * requires a subsequent TLB flush.  The notification can optionally be delayed
 * until the TLB flush event by using the pte_update_defer form of the
 * interface, but care must be taken to assure that the flush happens while
 * still holding the same page table lock so that the shadow and primary pages
 * do not become out of sync on SMP.
 */
#define pte_update(mm, addr, ptep)		do { } while (0)
#define pte_update_defer(mm, addr, ptep)	do { } while (0)
#endif

/*
 * We only update the dirty/accessed state if we set
 * the dirty bit by hand in the kernel, since the hardware
 * will do the accessed bit for us, and we don't want to
 * race with other CPU's that might be updating the dirty
 * bit at the same time.
 */
struct vm_area_struct;

#define  __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
extern int ptep_set_access_flags(struct vm_area_struct *vma,
				 unsigned long address, pte_t *ptep,
				 pte_t entry, int dirty);

#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
extern int ptep_test_and_clear_young(struct vm_area_struct *vma,
				     unsigned long addr, pte_t *ptep);

#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
extern int ptep_clear_flush_young(struct vm_area_struct *vma,
				  unsigned long address, pte_t *ptep);

#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
				       pte_t *ptep)
{
	pte_t pte = native_ptep_get_and_clear(ptep);
	pte_update(mm, addr, ptep);
	return pte;
}

#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
					    unsigned long addr, pte_t *ptep,
					    int full)
{
	pte_t pte;
	if (full) {
		/*
		 * Full address destruction in progress; paravirt does not
		 * care about updates and native needs no locking
		 */
		pte = native_local_ptep_get_and_clear(ptep);
	} else {
		pte = ptep_get_and_clear(mm, addr, ptep);
	}
	return pte;
}

#define __HAVE_ARCH_PTEP_SET_WRPROTECT
static inline void ptep_set_wrprotect(struct mm_struct *mm,
				      unsigned long addr, pte_t *ptep)
{
	clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
	pte_update(mm, addr, ptep);
}

/*
 * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
 *
 *  dst - pointer to pgd range anwhere on a pgd page
 *  src - ""
 *  count - the number of pgds to copy.
 *
 * dst and src can be on the same page, but the range must not overlap,
 * and must not cross a page boundary.
 */
static inline void clone_pgd_range(pgd_t *dst, pgd_t *src, int count)
{
       memcpy(dst, src, count * sizeof(pgd_t));
}


#include <asm-generic/pgtable.h>
#endif	/* __ASSEMBLY__ */

#endif /* _ASM_X86_PGTABLE_H */
Commit	Line	Data
	1	#ifndef _ASM_X86_PGTABLE_H
	2	#define _ASM_X86_PGTABLE_H
	3
	4	#define FIRST_USER_ADDRESS 0
	5
	6	#define _PAGE_BIT_PRESENT 0 /* is present */
	7	#define _PAGE_BIT_RW 1 /* writeable */
	8	#define _PAGE_BIT_USER 2 /* userspace addressable */
	9	#define _PAGE_BIT_PWT 3 /* page write through */
	10	#define _PAGE_BIT_PCD 4 /* page cache disabled */
	11	#define _PAGE_BIT_ACCESSED 5 /* was accessed (raised by CPU) */
	12	#define _PAGE_BIT_DIRTY 6 /* was written to (raised by CPU) */
	13	#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */
	14	#define _PAGE_BIT_PAT 7 /* on 4KB pages */
	15	#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
	16	#define _PAGE_BIT_UNUSED1 9 /* available for programmer */
	17	#define _PAGE_BIT_IOMAP 10 /* flag used to indicate IO mapping */
	18	#define _PAGE_BIT_UNUSED3 11
	19	#define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */
	20	#define _PAGE_BIT_SPECIAL _PAGE_BIT_UNUSED1
	21	#define _PAGE_BIT_CPA_TEST _PAGE_BIT_UNUSED1
	22	#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */
	23
	24	/* If _PAGE_BIT_PRESENT is clear, we use these: */
	25	/* - if the user mapped it with PROT_NONE; pte_present gives true */
	26	#define _PAGE_BIT_PROTNONE _PAGE_BIT_GLOBAL
	27	/* - set: nonlinear file mapping, saved PTE; unset:swap */
	28	#define _PAGE_BIT_FILE _PAGE_BIT_DIRTY
	29
	30	#define _PAGE_PRESENT (_AT(pteval_t, 1) << _PAGE_BIT_PRESENT)
	31	#define _PAGE_RW (_AT(pteval_t, 1) << _PAGE_BIT_RW)
	32	#define _PAGE_USER (_AT(pteval_t, 1) << _PAGE_BIT_USER)
	33	#define _PAGE_PWT (_AT(pteval_t, 1) << _PAGE_BIT_PWT)
	34	#define _PAGE_PCD (_AT(pteval_t, 1) << _PAGE_BIT_PCD)
	35	#define _PAGE_ACCESSED (_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED)
	36	#define _PAGE_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
	37	#define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE)
	38	#define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
	39	#define _PAGE_UNUSED1 (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1)
	40	#define _PAGE_IOMAP (_AT(pteval_t, 1) << _PAGE_BIT_IOMAP)
	41	#define _PAGE_UNUSED3 (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED3)
	42	#define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT)
	43	#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
	44	#define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
	45	#define _PAGE_CPA_TEST (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST)
	46	#define __HAVE_ARCH_PTE_SPECIAL
	47
	48	#if defined(CONFIG_X86_64) \|\| defined(CONFIG_X86_PAE)
	49	#define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX)
	50	#else
	51	#define _PAGE_NX (_AT(pteval_t, 0))
	52	#endif
	53
	54	#define _PAGE_FILE (_AT(pteval_t, 1) << _PAGE_BIT_FILE)
	55	#define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
	56
	57	#define _PAGE_TABLE (_PAGE_PRESENT \| _PAGE_RW \| _PAGE_USER \| \
	58	_PAGE_ACCESSED \| _PAGE_DIRTY)
	59	#define _KERNPG_TABLE (_PAGE_PRESENT \| _PAGE_RW \| _PAGE_ACCESSED \| \
	60	_PAGE_DIRTY)
	61
	62	/* Set of bits not changed in pte_modify */
	63	#define _PAGE_CHG_MASK (PTE_PFN_MASK \| _PAGE_PCD \| _PAGE_PWT \| \
	64	_PAGE_SPECIAL \| _PAGE_ACCESSED \| _PAGE_DIRTY)
	65
	66	#define _PAGE_CACHE_MASK (_PAGE_PCD \| _PAGE_PWT)
	67	#define _PAGE_CACHE_WB (0)
	68	#define _PAGE_CACHE_WC (_PAGE_PWT)
	69	#define _PAGE_CACHE_UC_MINUS (_PAGE_PCD)
	70	#define _PAGE_CACHE_UC (_PAGE_PCD \| _PAGE_PWT)
	71
	72	#define PAGE_NONE __pgprot(_PAGE_PROTNONE \| _PAGE_ACCESSED)
	73	#define PAGE_SHARED __pgprot(_PAGE_PRESENT \| _PAGE_RW \| _PAGE_USER \| \
	74	_PAGE_ACCESSED \| _PAGE_NX)
	75
	76	#define PAGE_SHARED_EXEC __pgprot(_PAGE_PRESENT \| _PAGE_RW \| \
	77	_PAGE_USER \| _PAGE_ACCESSED)
	78	#define PAGE_COPY_NOEXEC __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	79	_PAGE_ACCESSED \| _PAGE_NX)
	80	#define PAGE_COPY_EXEC __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	81	_PAGE_ACCESSED)
	82	#define PAGE_COPY PAGE_COPY_NOEXEC
	83	#define PAGE_READONLY __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	84	_PAGE_ACCESSED \| _PAGE_NX)
	85	#define PAGE_READONLY_EXEC __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	86	_PAGE_ACCESSED)
	87
	88	#define __PAGE_KERNEL_EXEC \
	89	(_PAGE_PRESENT \| _PAGE_RW \| _PAGE_DIRTY \| _PAGE_ACCESSED \| _PAGE_GLOBAL)
	90	#define __PAGE_KERNEL (__PAGE_KERNEL_EXEC \| _PAGE_NX)
	91
	92	#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW)
	93	#define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW)
	94	#define __PAGE_KERNEL_EXEC_NOCACHE (__PAGE_KERNEL_EXEC \| _PAGE_PCD \| _PAGE_PWT)
	95	#define __PAGE_KERNEL_WC (__PAGE_KERNEL \| _PAGE_CACHE_WC)
	96	#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL \| _PAGE_PCD \| _PAGE_PWT)
	97	#define __PAGE_KERNEL_UC_MINUS (__PAGE_KERNEL \| _PAGE_PCD)
	98	#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX \| _PAGE_USER)
	99	#define __PAGE_KERNEL_VSYSCALL_NOCACHE (__PAGE_KERNEL_VSYSCALL \| _PAGE_PCD \| _PAGE_PWT)
	100	#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL \| _PAGE_PSE)
	101	#define __PAGE_KERNEL_LARGE_NOCACHE (__PAGE_KERNEL \| _PAGE_CACHE_UC \| _PAGE_PSE)
	102	#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC \| _PAGE_PSE)
	103
	104	#define __PAGE_KERNEL_IO (__PAGE_KERNEL \| _PAGE_IOMAP)
	105	#define __PAGE_KERNEL_IO_NOCACHE (__PAGE_KERNEL_NOCACHE \| _PAGE_IOMAP)
	106	#define __PAGE_KERNEL_IO_UC_MINUS (__PAGE_KERNEL_UC_MINUS \| _PAGE_IOMAP)
	107	#define __PAGE_KERNEL_IO_WC (__PAGE_KERNEL_WC \| _PAGE_IOMAP)
	108
	109	#define PAGE_KERNEL __pgprot(__PAGE_KERNEL)
	110	#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO)
	111	#define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC)
	112	#define PAGE_KERNEL_RX __pgprot(__PAGE_KERNEL_RX)
	113	#define PAGE_KERNEL_WC __pgprot(__PAGE_KERNEL_WC)
	114	#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE)
	115	#define PAGE_KERNEL_UC_MINUS __pgprot(__PAGE_KERNEL_UC_MINUS)
	116	#define PAGE_KERNEL_EXEC_NOCACHE __pgprot(__PAGE_KERNEL_EXEC_NOCACHE)
	117	#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE)
	118	#define PAGE_KERNEL_LARGE_NOCACHE __pgprot(__PAGE_KERNEL_LARGE_NOCACHE)
	119	#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC)
	120	#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL)
	121	#define PAGE_KERNEL_VSYSCALL_NOCACHE __pgprot(__PAGE_KERNEL_VSYSCALL_NOCACHE)
	122
	123	#define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO)
	124	#define PAGE_KERNEL_IO_NOCACHE __pgprot(__PAGE_KERNEL_IO_NOCACHE)
	125	#define PAGE_KERNEL_IO_UC_MINUS __pgprot(__PAGE_KERNEL_IO_UC_MINUS)
	126	#define PAGE_KERNEL_IO_WC __pgprot(__PAGE_KERNEL_IO_WC)
	127
	128	/* xwr */
	129	#define __P000 PAGE_NONE
	130	#define __P001 PAGE_READONLY
	131	#define __P010 PAGE_COPY
	132	#define __P011 PAGE_COPY
	133	#define __P100 PAGE_READONLY_EXEC
	134	#define __P101 PAGE_READONLY_EXEC
	135	#define __P110 PAGE_COPY_EXEC
	136	#define __P111 PAGE_COPY_EXEC
	137
	138	#define __S000 PAGE_NONE
	139	#define __S001 PAGE_READONLY
	140	#define __S010 PAGE_SHARED
	141	#define __S011 PAGE_SHARED
	142	#define __S100 PAGE_READONLY_EXEC
	143	#define __S101 PAGE_READONLY_EXEC
	144	#define __S110 PAGE_SHARED_EXEC
	145	#define __S111 PAGE_SHARED_EXEC
	146
	147	/*
	148	* early identity mapping pte attrib macros.
	149	*/
	150	#ifdef CONFIG_X86_64
	151	#define __PAGE_KERNEL_IDENT_LARGE_EXEC __PAGE_KERNEL_LARGE_EXEC
	152	#else
	153	/*
	154	* For PDE_IDENT_ATTR include USER bit. As the PDE and PTE protection
	155	* bits are combined, this will alow user to access the high address mapped
	156	* VDSO in the presence of CONFIG_COMPAT_VDSO
	157	*/
	158	#define PTE_IDENT_ATTR 0x003 /* PRESENT+RW */
	159	#define PDE_IDENT_ATTR 0x067 /* PRESENT+RW+USER+DIRTY+ACCESSED */
	160	#define PGD_IDENT_ATTR 0x001 /* PRESENT (no other attributes) */
	161	#endif
	162
	163	/*
	164	* Macro to mark a page protection value as UC-
	165	*/
	166	#define pgprot_noncached(prot) \
	167	((boot_cpu_data.x86 > 3) \
	168	? (__pgprot(pgprot_val(prot) \| _PAGE_CACHE_UC_MINUS)) \
	169	: (prot))
	170
	171	#ifndef __ASSEMBLY__
	172
	173	#define pgprot_writecombine pgprot_writecombine
	174	extern pgprot_t pgprot_writecombine(pgprot_t prot);
	175
	176	/*
	177	* ZERO_PAGE is a global shared page that is always zero: used
	178	* for zero-mapped memory areas etc..
	179	*/
	180	extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
	181	#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
	182
	183	extern spinlock_t pgd_lock;
	184	extern struct list_head pgd_list;
	185
	186	/*
	187	* The following only work if pte_present() is true.
	188	* Undefined behaviour if not..
	189	*/
	190	static inline int pte_dirty(pte_t pte)
	191	{
	192	return pte_flags(pte) & _PAGE_DIRTY;
	193	}
	194
	195	static inline int pte_young(pte_t pte)
	196	{
	197	return pte_flags(pte) & _PAGE_ACCESSED;
	198	}
	199
	200	static inline int pte_write(pte_t pte)
	201	{
	202	return pte_flags(pte) & _PAGE_RW;
	203	}
	204
	205	static inline int pte_file(pte_t pte)
	206	{
	207	return pte_flags(pte) & _PAGE_FILE;
	208	}
	209
	210	static inline int pte_huge(pte_t pte)
	211	{
	212	return pte_flags(pte) & _PAGE_PSE;
	213	}
	214
	215	static inline int pte_global(pte_t pte)
	216	{
	217	return pte_flags(pte) & _PAGE_GLOBAL;
	218	}
	219
	220	static inline int pte_exec(pte_t pte)
	221	{
	222	return !(pte_flags(pte) & _PAGE_NX);
	223	}
	224
	225	static inline int pte_special(pte_t pte)
	226	{
	227	return pte_flags(pte) & _PAGE_SPECIAL;
	228	}
	229
	230	static inline unsigned long pte_pfn(pte_t pte)
	231	{
	232	return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
	233	}
	234
	235	#define pte_page(pte) pfn_to_page(pte_pfn(pte))
	236
	237	static inline int pmd_large(pmd_t pte)
	238	{
	239	return (pmd_val(pte) & (_PAGE_PSE \| _PAGE_PRESENT)) ==
	240	(_PAGE_PSE \| _PAGE_PRESENT);
	241	}
	242
	243	static inline pte_t pte_mkclean(pte_t pte)
	244	{
	245	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
	246	}
	247
	248	static inline pte_t pte_mkold(pte_t pte)
	249	{
	250	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
	251	}
	252
	253	static inline pte_t pte_wrprotect(pte_t pte)
	254	{
	255	return __pte(pte_val(pte) & ~_PAGE_RW);
	256	}
	257
	258	static inline pte_t pte_mkexec(pte_t pte)
	259	{
	260	return __pte(pte_val(pte) & ~_PAGE_NX);
	261	}
	262
	263	static inline pte_t pte_mkdirty(pte_t pte)
	264	{
	265	return __pte(pte_val(pte) \| _PAGE_DIRTY);
	266	}
	267
	268	static inline pte_t pte_mkyoung(pte_t pte)
	269	{
	270	return __pte(pte_val(pte) \| _PAGE_ACCESSED);
	271	}
	272
	273	static inline pte_t pte_mkwrite(pte_t pte)
	274	{
	275	return __pte(pte_val(pte) \| _PAGE_RW);
	276	}
	277
	278	static inline pte_t pte_mkhuge(pte_t pte)
	279	{
	280	return __pte(pte_val(pte) \| _PAGE_PSE);
	281	}
	282
	283	static inline pte_t pte_clrhuge(pte_t pte)
	284	{
	285	return __pte(pte_val(pte) & ~_PAGE_PSE);
	286	}
	287
	288	static inline pte_t pte_mkglobal(pte_t pte)
	289	{
	290	return __pte(pte_val(pte) \| _PAGE_GLOBAL);
	291	}
	292
	293	static inline pte_t pte_clrglobal(pte_t pte)
	294	{
	295	return __pte(pte_val(pte) & ~_PAGE_GLOBAL);
	296	}
	297
	298	static inline pte_t pte_mkspecial(pte_t pte)
	299	{
	300	return __pte(pte_val(pte) \| _PAGE_SPECIAL);
	301	}
	302
	303	extern pteval_t __supported_pte_mask;
	304
	305	static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
	306	{
	307	return __pte((((phys_addr_t)page_nr << PAGE_SHIFT) \|
	308	pgprot_val(pgprot)) & __supported_pte_mask);
	309	}
	310
	311	static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
	312	{
	313	return __pmd((((phys_addr_t)page_nr << PAGE_SHIFT) \|
	314	pgprot_val(pgprot)) & __supported_pte_mask);
	315	}
	316
	317	static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
	318	{
	319	pteval_t val = pte_val(pte);
	320
	321	/*
	322	* Chop off the NX bit (if present), and add the NX portion of
	323	* the newprot (if present):
	324	*/
	325	val &= _PAGE_CHG_MASK;
	326	val \|= pgprot_val(newprot) & (~_PAGE_CHG_MASK) & __supported_pte_mask;
	327
	328	return __pte(val);
	329	}
	330
	331	/* mprotect needs to preserve PAT bits when updating vm_page_prot */
	332	#define pgprot_modify pgprot_modify
	333	static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
	334	{
	335	pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK;
	336	pgprotval_t addbits = pgprot_val(newprot);
	337	return __pgprot(preservebits \| addbits);
	338	}
	339
	340	#define pte_pgprot(x) __pgprot(pte_flags(x) & PTE_FLAGS_MASK)
	341
	342	#define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
	343
	344	static inline int is_new_memtype_allowed(unsigned long flags,
	345	unsigned long new_flags)
	346	{
	347	/*
	348	* Certain new memtypes are not allowed with certain
	349	* requested memtype:
	350	* - request is uncached, return cannot be write-back
	351	* - request is write-combine, return cannot be write-back
	352	*/
	353	if ((flags == _PAGE_CACHE_UC_MINUS &&
	354	new_flags == _PAGE_CACHE_WB) \|\|
	355	(flags == _PAGE_CACHE_WC &&
	356	new_flags == _PAGE_CACHE_WB)) {
	357	return 0;
	358	}
	359
	360	return 1;
	361	}
	362
	363	#ifndef __ASSEMBLY__
	364	/* Indicate that x86 has its own track and untrack pfn vma functions */
	365	#define __HAVE_PFNMAP_TRACKING
	366
	367	#define __HAVE_PHYS_MEM_ACCESS_PROT
	368	struct file;
	369	pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
	370	unsigned long size, pgprot_t vma_prot);
	371	int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
	372	unsigned long size, pgprot_t *vma_prot);
	373	#endif
	374
	375	/* Install a pte for a particular vaddr in kernel space. */
	376	void set_pte_vaddr(unsigned long vaddr, pte_t pte);
	377
	378	#ifdef CONFIG_X86_32
	379	extern void native_pagetable_setup_start(pgd_t *base);
	380	extern void native_pagetable_setup_done(pgd_t *base);
	381	#else
	382	static inline void native_pagetable_setup_start(pgd_t *base) {}
	383	static inline void native_pagetable_setup_done(pgd_t *base) {}
	384	#endif
	385
	386	struct seq_file;
	387	extern void arch_report_meminfo(struct seq_file *m);
	388
	389	#ifdef CONFIG_PARAVIRT
	390	#include <asm/paravirt.h>
	391	#else /* !CONFIG_PARAVIRT */
	392	#define set_pte(ptep, pte) native_set_pte(ptep, pte)
	393	#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte)
	394
	395	#define set_pte_present(mm, addr, ptep, pte) \
	396	native_set_pte_present(mm, addr, ptep, pte)
	397	#define set_pte_atomic(ptep, pte) \
	398	native_set_pte_atomic(ptep, pte)
	399
	400	#define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd)
	401
	402	#ifndef __PAGETABLE_PUD_FOLDED
	403	#define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd)
	404	#define pgd_clear(pgd) native_pgd_clear(pgd)
	405	#endif
	406
	407	#ifndef set_pud
	408	# define set_pud(pudp, pud) native_set_pud(pudp, pud)
	409	#endif
	410
	411	#ifndef __PAGETABLE_PMD_FOLDED
	412	#define pud_clear(pud) native_pud_clear(pud)
	413	#endif
	414
	415	#define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep)
	416	#define pmd_clear(pmd) native_pmd_clear(pmd)
	417
	418	#define pte_update(mm, addr, ptep) do { } while (0)
	419	#define pte_update_defer(mm, addr, ptep) do { } while (0)
	420
	421	static inline void __init paravirt_pagetable_setup_start(pgd_t *base)
	422	{
	423	native_pagetable_setup_start(base);
	424	}
	425
	426	static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
	427	{
	428	native_pagetable_setup_done(base);
	429	}
	430	#endif /* CONFIG_PARAVIRT */
	431
	432	#endif /* __ASSEMBLY__ */
	433
	434	#ifdef CONFIG_X86_32
	435	# include "pgtable_32.h"
	436	#else
	437	# include "pgtable_64.h"
	438	#endif
	439
	440	/*
	441	* the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
	442	*
	443	* this macro returns the index of the entry in the pgd page which would
	444	* control the given virtual address
	445	*/
	446	#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
	447
	448	/*
	449	* pgd_offset() returns a (pgd_t *)
	450	* pgd_index() is used get the offset into the pgd page's array of pgd_t's;
	451	*/
	452	#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
	453	/*
	454	* a shortcut which implies the use of the kernel's pgd, instead
	455	* of a process's
	456	*/
	457	#define pgd_offset_k(address) pgd_offset(&init_mm, (address))
	458
	459
	460	#define KERNEL_PGD_BOUNDARY pgd_index(PAGE_OFFSET)
	461	#define KERNEL_PGD_PTRS (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)
	462
	463	#ifndef __ASSEMBLY__
	464
	465	enum {
	466	PG_LEVEL_NONE,
	467	PG_LEVEL_4K,
	468	PG_LEVEL_2M,
	469	PG_LEVEL_1G,
	470	PG_LEVEL_NUM
	471	};
	472
	473	#ifdef CONFIG_PROC_FS
	474	extern void update_page_count(int level, unsigned long pages);
	475	#else
	476	static inline void update_page_count(int level, unsigned long pages) { }
	477	#endif
	478
	479	/*
	480	* Helper function that returns the kernel pagetable entry controlling
	481	* the virtual address 'address'. NULL means no pagetable entry present.
	482	* NOTE: the return type is pte_t but if the pmd is PSE then we return it
	483	* as a pte too.
	484	*/
	485	extern pte_t lookup_address(unsigned long address, unsigned int level);
	486
	487	/* local pte updates need not use xchg for locking */
	488	static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
	489	{
	490	pte_t res = *ptep;
	491
	492	/* Pure native function needs no input for mm, addr */
	493	native_pte_clear(NULL, 0, ptep);
	494	return res;
	495	}
	496
	497	static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
	498	pte_t *ptep , pte_t pte)
	499	{
	500	native_set_pte(ptep, pte);
	501	}
	502
	503	#ifndef CONFIG_PARAVIRT
	504	/*
	505	* Rules for using pte_update - it must be called after any PTE update which
	506	* has not been done using the set_pte / clear_pte interfaces. It is used by
	507	* shadow mode hypervisors to resynchronize the shadow page tables. Kernel PTE
	508	* updates should either be sets, clears, or set_pte_atomic for P->P
	509	* transitions, which means this hook should only be called for user PTEs.
	510	* This hook implies a P->P protection or access change has taken place, which
	511	* requires a subsequent TLB flush. The notification can optionally be delayed
	512	* until the TLB flush event by using the pte_update_defer form of the
	513	* interface, but care must be taken to assure that the flush happens while
	514	* still holding the same page table lock so that the shadow and primary pages
	515	* do not become out of sync on SMP.
	516	*/
	517	#define pte_update(mm, addr, ptep) do { } while (0)
	518	#define pte_update_defer(mm, addr, ptep) do { } while (0)
	519	#endif
	520
	521	/*
	522	* We only update the dirty/accessed state if we set
	523	* the dirty bit by hand in the kernel, since the hardware
	524	* will do the accessed bit for us, and we don't want to
	525	* race with other CPU's that might be updating the dirty
	526	* bit at the same time.
	527	*/
	528	struct vm_area_struct;
	529
	530	#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
	531	extern int ptep_set_access_flags(struct vm_area_struct *vma,
	532	unsigned long address, pte_t *ptep,
	533	pte_t entry, int dirty);
	534
	535	#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
	536	extern int ptep_test_and_clear_young(struct vm_area_struct *vma,
	537	unsigned long addr, pte_t *ptep);
	538
	539	#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
	540	extern int ptep_clear_flush_young(struct vm_area_struct *vma,
	541	unsigned long address, pte_t *ptep);
	542
	543	#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
	544	static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
	545	pte_t *ptep)
	546	{
	547	pte_t pte = native_ptep_get_and_clear(ptep);
	548	pte_update(mm, addr, ptep);
	549	return pte;
	550	}
	551
	552	#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
	553	static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
	554	unsigned long addr, pte_t *ptep,
	555	int full)
	556	{
	557	pte_t pte;
	558	if (full) {
	559	/*
	560	* Full address destruction in progress; paravirt does not
	561	* care about updates and native needs no locking
	562	*/
	563	pte = native_local_ptep_get_and_clear(ptep);
	564	} else {
	565	pte = ptep_get_and_clear(mm, addr, ptep);
	566	}
	567	return pte;
	568	}
	569
	570	#define __HAVE_ARCH_PTEP_SET_WRPROTECT
	571	static inline void ptep_set_wrprotect(struct mm_struct *mm,
	572	unsigned long addr, pte_t *ptep)
	573	{
	574	clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
	575	pte_update(mm, addr, ptep);
	576	}
	577
	578	/*
	579	* clone_pgd_range(pgd_t dst, pgd_t src, int count);
	580	*
	581	* dst - pointer to pgd range anwhere on a pgd page
	582	* src - ""
	583	* count - the number of pgds to copy.
	584	*
	585	* dst and src can be on the same page, but the range must not overlap,
	586	* and must not cross a page boundary.
	587	*/
	588	static inline void clone_pgd_range(pgd_t dst, pgd_t src, int count)
	589	{
	590	memcpy(dst, src, count * sizeof(pgd_t));
	591	}
	592
	593
	594	#include <asm-generic/pgtable.h>
	595	#endif /* __ASSEMBLY__ */
	596
	597	#endif /* _ASM_X86_PGTABLE_H */