[mirror_ubuntu-bionic-kernel.git] / include / asm-x86 / 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_FILE		6
#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_UNUSED2	10
#define _PAGE_BIT_UNUSED3	11
#define _PAGE_BIT_PAT_LARGE	12	/* On 2MB or 1GB pages */
#define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */

#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_UNUSED2	(_AT(pteval_t, 1) << _PAGE_BIT_UNUSED2)
#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)

#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

/* If _PAGE_PRESENT is clear, we use these: */
#define _PAGE_FILE	_PAGE_DIRTY	/* nonlinear file mapping,
					 * saved PTE; unset:swap */
#define _PAGE_PROTNONE	_PAGE_PSE	/* if the user mapped it with PROT_NONE;
					   pte_present gives true */

#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_MASK | _PAGE_PCD | _PAGE_PWT |		\
			 _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)

#ifdef CONFIG_X86_32
#define _PAGE_KERNEL_EXEC \
	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
#define _PAGE_KERNEL (_PAGE_KERNEL_EXEC | _PAGE_NX)

#ifndef __ASSEMBLY__
extern pteval_t __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
#endif	/* __ASSEMBLY__ */
#else
#define __PAGE_KERNEL_EXEC						\
	(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED)
#define __PAGE_KERNEL		(__PAGE_KERNEL_EXEC | _PAGE_NX)
#endif

#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_EXEC	(__PAGE_KERNEL_EXEC | _PAGE_PSE)

#ifdef CONFIG_X86_32
# define MAKE_GLOBAL(x)			__pgprot((x))
#else
# define MAKE_GLOBAL(x)			__pgprot((x) | _PAGE_GLOBAL)
#endif

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

/*         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

#ifndef __ASSEMBLY__

/*
 * 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 0;
}

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;
}

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_MASK)

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

#ifndef __ASSEMBLY__
#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_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)
#endif	/* CONFIG_PARAVIRT */

#endif	/* __ASSEMBLY__ */

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

#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.
 */
#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
6c386655 JF	1	#ifndef _ASM_X86_PGTABLE_H
	2	#define _ASM_X86_PGTABLE_H
	3
6c386655 JF	4	#define FIRST_USER_ADDRESS 0
6c386655 JF	5
43cdf5d6 JS	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) */
6c386655 JF	13	#define _PAGE_BIT_FILE 6
6c386655 JF	14	#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */
9bf5a475	15	#define _PAGE_BIT_PAT 7 /* on 4KB pages */
6c386655 JF	16	#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
	17	#define _PAGE_BIT_UNUSED1 9 /* available for programmer */
	18	#define _PAGE_BIT_UNUSED2 10
	19	#define _PAGE_BIT_UNUSED3 11
9bf5a475	20	#define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */
6c386655 JF	21	#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */
6c386655 JF	22
4226ab93 JF	23	#define _PAGE_PRESENT (_AT(pteval_t, 1) << _PAGE_BIT_PRESENT)
	24	#define _PAGE_RW (_AT(pteval_t, 1) << _PAGE_BIT_RW)
	25	#define _PAGE_USER (_AT(pteval_t, 1) << _PAGE_BIT_USER)
	26	#define _PAGE_PWT (_AT(pteval_t, 1) << _PAGE_BIT_PWT)
	27	#define _PAGE_PCD (_AT(pteval_t, 1) << _PAGE_BIT_PCD)
	28	#define _PAGE_ACCESSED (_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED)
	29	#define _PAGE_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY)
	30	#define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE)
	31	#define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
	32	#define _PAGE_UNUSED1 (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1)
	33	#define _PAGE_UNUSED2 (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED2)
	34	#define _PAGE_UNUSED3 (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED3)
	35	#define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT)
	36	#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
6c386655 JF	37
6c386655 JF	38	#if defined(CONFIG_X86_64) \|\| defined(CONFIG_X86_PAE)
4226ab93	39	#define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX)
6c386655	40	#else
4226ab93	41	#define _PAGE_NX (_AT(pteval_t, 0))
6c386655 JF	42	#endif
	43
	44	/* If _PAGE_PRESENT is clear, we use these: */
3cbaeafe JP	45	#define _PAGE_FILE _PAGE_DIRTY /* nonlinear file mapping,
3cbaeafe JP	46	* saved PTE; unset:swap */
6c386655 JF	47	#define _PAGE_PROTNONE _PAGE_PSE /* if the user mapped it with PROT_NONE;
	48	pte_present gives true */
	49
3cbaeafe JP	50	#define _PAGE_TABLE (_PAGE_PRESENT \| _PAGE_RW \| _PAGE_USER \| \
	51	_PAGE_ACCESSED \| _PAGE_DIRTY)
	52	#define _KERNPG_TABLE (_PAGE_PRESENT \| _PAGE_RW \| _PAGE_ACCESSED \| \
	53	_PAGE_DIRTY)
6c386655	54
86aaf4fd	55	/* Set of bits not changed in pte_modify */
1c12c4cf VP	56	#define _PAGE_CHG_MASK (PTE_MASK \| _PAGE_PCD \| _PAGE_PWT \| \
1c12c4cf VP	57	_PAGE_ACCESSED \| _PAGE_DIRTY)
6c386655	58
2e5d9c85	59	#define _PAGE_CACHE_MASK (_PAGE_PCD \| _PAGE_PWT)
	60	#define _PAGE_CACHE_WB (0)
	61	#define _PAGE_CACHE_WC (_PAGE_PWT)
	62	#define _PAGE_CACHE_UC_MINUS (_PAGE_PCD)
	63	#define _PAGE_CACHE_UC (_PAGE_PCD \| _PAGE_PWT)
	64
6c386655	65	#define PAGE_NONE __pgprot(_PAGE_PROTNONE \| _PAGE_ACCESSED)
3cbaeafe JP	66	#define PAGE_SHARED __pgprot(_PAGE_PRESENT \| _PAGE_RW \| _PAGE_USER \| \
	67	_PAGE_ACCESSED \| _PAGE_NX)
	68
	69	#define PAGE_SHARED_EXEC __pgprot(_PAGE_PRESENT \| _PAGE_RW \| \
	70	_PAGE_USER \| _PAGE_ACCESSED)
	71	#define PAGE_COPY_NOEXEC __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	72	_PAGE_ACCESSED \| _PAGE_NX)
	73	#define PAGE_COPY_EXEC __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	74	_PAGE_ACCESSED)
6c386655	75	#define PAGE_COPY PAGE_COPY_NOEXEC
3cbaeafe JP	76	#define PAGE_READONLY __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	77	_PAGE_ACCESSED \| _PAGE_NX)
	78	#define PAGE_READONLY_EXEC __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	79	_PAGE_ACCESSED)
6c386655 JF	80
	81	#ifdef CONFIG_X86_32
	82	#define _PAGE_KERNEL_EXEC \
	83	(_PAGE_PRESENT \| _PAGE_RW \| _PAGE_DIRTY \| _PAGE_ACCESSED)
	84	#define _PAGE_KERNEL (_PAGE_KERNEL_EXEC \| _PAGE_NX)
	85
	86	#ifndef __ASSEMBLY__
c93c82bb	87	extern pteval_t __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
6c386655 JF	88	#endif /* __ASSEMBLY__ */
	89	#else
	90	#define __PAGE_KERNEL_EXEC \
	91	(_PAGE_PRESENT \| _PAGE_RW \| _PAGE_DIRTY \| _PAGE_ACCESSED)
	92	#define __PAGE_KERNEL (__PAGE_KERNEL_EXEC \| _PAGE_NX)
	93	#endif
	94
	95	#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW)
	96	#define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW)
d2e626f4	97	#define __PAGE_KERNEL_EXEC_NOCACHE (__PAGE_KERNEL_EXEC \| _PAGE_PCD \| _PAGE_PWT)
b310f381	98	#define __PAGE_KERNEL_WC (__PAGE_KERNEL \| _PAGE_CACHE_WC)
6c386655	99	#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL \| _PAGE_PCD \| _PAGE_PWT)
d546b67a	100	#define __PAGE_KERNEL_UC_MINUS (__PAGE_KERNEL \| _PAGE_PCD)
6c386655 JF	101	#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX \| _PAGE_USER)
	102	#define __PAGE_KERNEL_VSYSCALL_NOCACHE (__PAGE_KERNEL_VSYSCALL \| _PAGE_PCD \| _PAGE_PWT)
	103	#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL \| _PAGE_PSE)
	104	#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC \| _PAGE_PSE)
	105
	106	#ifdef CONFIG_X86_32
	107	# define MAKE_GLOBAL(x) __pgprot((x))
	108	#else
	109	# define MAKE_GLOBAL(x) __pgprot((x) \| _PAGE_GLOBAL)
	110	#endif
	111
	112	#define PAGE_KERNEL MAKE_GLOBAL(__PAGE_KERNEL)
	113	#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO)
	114	#define PAGE_KERNEL_EXEC MAKE_GLOBAL(__PAGE_KERNEL_EXEC)
	115	#define PAGE_KERNEL_RX MAKE_GLOBAL(__PAGE_KERNEL_RX)
b310f381	116	#define PAGE_KERNEL_WC MAKE_GLOBAL(__PAGE_KERNEL_WC)
6c386655	117	#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
d546b67a	118	#define PAGE_KERNEL_UC_MINUS MAKE_GLOBAL(__PAGE_KERNEL_UC_MINUS)
d2e626f4	119	#define PAGE_KERNEL_EXEC_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_EXEC_NOCACHE)
6c386655 JF	120	#define PAGE_KERNEL_LARGE MAKE_GLOBAL(__PAGE_KERNEL_LARGE)
	121	#define PAGE_KERNEL_LARGE_EXEC MAKE_GLOBAL(__PAGE_KERNEL_LARGE_EXEC)
	122	#define PAGE_KERNEL_VSYSCALL MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL)
	123	#define PAGE_KERNEL_VSYSCALL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL_NOCACHE)
	124
	125	/* xwr */
	126	#define __P000 PAGE_NONE
	127	#define __P001 PAGE_READONLY
	128	#define __P010 PAGE_COPY
	129	#define __P011 PAGE_COPY
	130	#define __P100 PAGE_READONLY_EXEC
	131	#define __P101 PAGE_READONLY_EXEC
	132	#define __P110 PAGE_COPY_EXEC
	133	#define __P111 PAGE_COPY_EXEC
	134
	135	#define __S000 PAGE_NONE
	136	#define __S001 PAGE_READONLY
	137	#define __S010 PAGE_SHARED
	138	#define __S011 PAGE_SHARED
	139	#define __S100 PAGE_READONLY_EXEC
	140	#define __S101 PAGE_READONLY_EXEC
	141	#define __S110 PAGE_SHARED_EXEC
	142	#define __S111 PAGE_SHARED_EXEC
	143
4614139c	144	#ifndef __ASSEMBLY__
195466dc	145
8405b122 JF	146	/*
	147	* ZERO_PAGE is a global shared page that is always zero: used
	148	* for zero-mapped memory areas etc..
	149	*/
3cbaeafe	150	extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
8405b122 JF	151	#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
8405b122 JF	152
e3ed910d JF	153	extern spinlock_t pgd_lock;
e3ed910d JF	154	extern struct list_head pgd_list;
8405b122	155
4614139c JF	156	/*
	157	* The following only work if pte_present() is true.
	158	* Undefined behaviour if not..
	159	*/
3cbaeafe JP	160	static inline int pte_dirty(pte_t pte)
3cbaeafe JP	161	{
a15af1c9	162	return pte_flags(pte) & _PAGE_DIRTY;
3cbaeafe JP	163	}
	164
	165	static inline int pte_young(pte_t pte)
	166	{
a15af1c9	167	return pte_flags(pte) & _PAGE_ACCESSED;
3cbaeafe JP	168	}
	169
	170	static inline int pte_write(pte_t pte)
	171	{
a15af1c9	172	return pte_flags(pte) & _PAGE_RW;
3cbaeafe JP	173	}
	174
	175	static inline int pte_file(pte_t pte)
	176	{
a15af1c9	177	return pte_flags(pte) & _PAGE_FILE;
3cbaeafe JP	178	}
	179
	180	static inline int pte_huge(pte_t pte)
	181	{
a15af1c9	182	return pte_flags(pte) & _PAGE_PSE;
4614139c JF	183	}
4614139c JF	184
3cbaeafe JP	185	static inline int pte_global(pte_t pte)
3cbaeafe JP	186	{
a15af1c9	187	return pte_flags(pte) & _PAGE_GLOBAL;
3cbaeafe JP	188	}
	189
	190	static inline int pte_exec(pte_t pte)
	191	{
a15af1c9	192	return !(pte_flags(pte) & _PAGE_NX);
3cbaeafe JP	193	}
3cbaeafe JP	194
7e675137 NP	195	static inline int pte_special(pte_t pte)
	196	{
	197	return 0;
	198	}
	199
3cbaeafe JP	200	static inline int pmd_large(pmd_t pte)
	201	{
	202	return (pmd_val(pte) & (_PAGE_PSE \| _PAGE_PRESENT)) ==
	203	(_PAGE_PSE \| _PAGE_PRESENT);
	204	}
	205
	206	static inline pte_t pte_mkclean(pte_t pte)
	207	{
4226ab93	208	return __pte(pte_val(pte) & ~_PAGE_DIRTY);
3cbaeafe JP	209	}
	210
	211	static inline pte_t pte_mkold(pte_t pte)
	212	{
4226ab93	213	return __pte(pte_val(pte) & ~_PAGE_ACCESSED);
3cbaeafe JP	214	}
	215
	216	static inline pte_t pte_wrprotect(pte_t pte)
	217	{
4226ab93	218	return __pte(pte_val(pte) & ~_PAGE_RW);
3cbaeafe JP	219	}
	220
	221	static inline pte_t pte_mkexec(pte_t pte)
	222	{
4226ab93	223	return __pte(pte_val(pte) & ~_PAGE_NX);
3cbaeafe JP	224	}
	225
	226	static inline pte_t pte_mkdirty(pte_t pte)
	227	{
	228	return __pte(pte_val(pte) \| _PAGE_DIRTY);
	229	}
	230
	231	static inline pte_t pte_mkyoung(pte_t pte)
	232	{
	233	return __pte(pte_val(pte) \| _PAGE_ACCESSED);
	234	}
	235
	236	static inline pte_t pte_mkwrite(pte_t pte)
	237	{
	238	return __pte(pte_val(pte) \| _PAGE_RW);
	239	}
	240
	241	static inline pte_t pte_mkhuge(pte_t pte)
	242	{
	243	return __pte(pte_val(pte) \| _PAGE_PSE);
	244	}
	245
	246	static inline pte_t pte_clrhuge(pte_t pte)
	247	{
4226ab93	248	return __pte(pte_val(pte) & ~_PAGE_PSE);
3cbaeafe JP	249	}
	250
	251	static inline pte_t pte_mkglobal(pte_t pte)
	252	{
	253	return __pte(pte_val(pte) \| _PAGE_GLOBAL);
	254	}
	255
	256	static inline pte_t pte_clrglobal(pte_t pte)
	257	{
4226ab93	258	return __pte(pte_val(pte) & ~_PAGE_GLOBAL);
3cbaeafe	259	}
4614139c	260
7e675137 NP	261	static inline pte_t pte_mkspecial(pte_t pte)
	262	{
	263	return pte;
	264	}
	265
6fdc05d4 JF	266	extern pteval_t __supported_pte_mask;
	267
	268	static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
	269	{
	270	return __pte((((phys_addr_t)page_nr << PAGE_SHIFT) \|
	271	pgprot_val(pgprot)) & __supported_pte_mask);
	272	}
	273
	274	static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
	275	{
	276	return __pmd((((phys_addr_t)page_nr << PAGE_SHIFT) \|
	277	pgprot_val(pgprot)) & __supported_pte_mask);
	278	}
	279
38472311 IM	280	static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
	281	{
	282	pteval_t val = pte_val(pte);
	283
	284	/*
	285	* Chop off the NX bit (if present), and add the NX portion of
	286	* the newprot (if present):
	287	*/
1c12c4cf VP	288	val &= _PAGE_CHG_MASK;
1c12c4cf VP	289	val \|= pgprot_val(newprot) & (~_PAGE_CHG_MASK) & __supported_pte_mask;
38472311 IM	290
	291	return __pte(val);
	292	}
	293
1c12c4cf VP	294	/* mprotect needs to preserve PAT bits when updating vm_page_prot */
	295	#define pgprot_modify pgprot_modify
	296	static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
	297	{
	298	pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK;
	299	pgprotval_t addbits = pgprot_val(newprot);
	300	return __pgprot(preservebits \| addbits);
	301	}
	302
a15af1c9	303	#define pte_pgprot(x) __pgprot(pte_flags(x) & ~PTE_MASK)
c6ca18eb	304
1e8e23bc AK	305	#define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
1e8e23bc AK	306
f0970c13	307	#ifndef __ASSEMBLY__
	308	#define __HAVE_PHYS_MEM_ACCESS_PROT
	309	struct file;
	310	pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
	311	unsigned long size, pgprot_t vma_prot);
	312	int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
	313	unsigned long size, pgprot_t *vma_prot);
	314	#endif
	315
d494a961 JF	316	/* Install a pte for a particular vaddr in kernel space. */
	317	void set_pte_vaddr(unsigned long vaddr, pte_t pte);
	318
4891645e JF	319	#ifdef CONFIG_PARAVIRT
	320	#include <asm/paravirt.h>
	321	#else /* !CONFIG_PARAVIRT */
	322	#define set_pte(ptep, pte) native_set_pte(ptep, pte)
	323	#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte)
	324
	325	#define set_pte_present(mm, addr, ptep, pte) \
	326	native_set_pte_present(mm, addr, ptep, pte)
	327	#define set_pte_atomic(ptep, pte) \
	328	native_set_pte_atomic(ptep, pte)
	329
	330	#define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd)
	331
	332	#ifndef __PAGETABLE_PUD_FOLDED
	333	#define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd)
	334	#define pgd_clear(pgd) native_pgd_clear(pgd)
	335	#endif
	336
	337	#ifndef set_pud
	338	# define set_pud(pudp, pud) native_set_pud(pudp, pud)
	339	#endif
	340
	341	#ifndef __PAGETABLE_PMD_FOLDED
	342	#define pud_clear(pud) native_pud_clear(pud)
	343	#endif
	344
	345	#define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep)
	346	#define pmd_clear(pmd) native_pmd_clear(pmd)
	347
	348	#define pte_update(mm, addr, ptep) do { } while (0)
	349	#define pte_update_defer(mm, addr, ptep) do { } while (0)
	350	#endif /* CONFIG_PARAVIRT */
	351
4614139c JF	352	#endif /* __ASSEMBLY__ */
4614139c JF	353
96a388de TG	354	#ifdef CONFIG_X86_32
	355	# include "pgtable_32.h"
	356	#else
	357	# include "pgtable_64.h"
	358	#endif
6c386655	359
68db065c JF	360	#define KERNEL_PGD_BOUNDARY pgd_index(PAGE_OFFSET)
	361	#define KERNEL_PGD_PTRS (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)
	362
195466dc JF	363	#ifndef __ASSEMBLY__
195466dc JF	364
30551bb3 TG	365	enum {
	366	PG_LEVEL_NONE,
	367	PG_LEVEL_4K,
	368	PG_LEVEL_2M,
86f03989	369	PG_LEVEL_1G,
ce0c0e50	370	PG_LEVEL_NUM
30551bb3 TG	371	};
30551bb3 TG	372
65280e61 TG	373	#ifdef CONFIG_PROC_FS
	374	extern void update_page_count(int level, unsigned long pages);
	375	#else
	376	static inline void update_page_count(int level, unsigned long pages) { }
	377	#endif
ce0c0e50	378
0a663088 TG	379	/*
	380	* Helper function that returns the kernel pagetable entry controlling
	381	* the virtual address 'address'. NULL means no pagetable entry present.
	382	* NOTE: the return type is pte_t but if the pmd is PSE then we return it
	383	* as a pte too.
	384	*/
da7bfc50	385	extern pte_t lookup_address(unsigned long address, unsigned int level);
0a663088	386
4891645e JF	387	/* local pte updates need not use xchg for locking */
	388	static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
	389	{
	390	pte_t res = *ptep;
	391
	392	/* Pure native function needs no input for mm, addr */
	393	native_pte_clear(NULL, 0, ptep);
	394	return res;
	395	}
	396
	397	static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
	398	pte_t *ptep , pte_t pte)
	399	{
	400	native_set_pte(ptep, pte);
	401	}
	402
195466dc JF	403	#ifndef CONFIG_PARAVIRT
	404	/*
	405	* Rules for using pte_update - it must be called after any PTE update which
	406	* has not been done using the set_pte / clear_pte interfaces. It is used by
	407	* shadow mode hypervisors to resynchronize the shadow page tables. Kernel PTE
	408	* updates should either be sets, clears, or set_pte_atomic for P->P
	409	* transitions, which means this hook should only be called for user PTEs.
	410	* This hook implies a P->P protection or access change has taken place, which
	411	* requires a subsequent TLB flush. The notification can optionally be delayed
	412	* until the TLB flush event by using the pte_update_defer form of the
	413	* interface, but care must be taken to assure that the flush happens while
	414	* still holding the same page table lock so that the shadow and primary pages
	415	* do not become out of sync on SMP.
	416	*/
	417	#define pte_update(mm, addr, ptep) do { } while (0)
	418	#define pte_update_defer(mm, addr, ptep) do { } while (0)
	419	#endif
	420
195466dc JF	421	/*
	422	* We only update the dirty/accessed state if we set
	423	* the dirty bit by hand in the kernel, since the hardware
	424	* will do the accessed bit for us, and we don't want to
	425	* race with other CPU's that might be updating the dirty
	426	* bit at the same time.
	427	*/
	428	#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
ee5aa8d3 JF	429	extern int ptep_set_access_flags(struct vm_area_struct *vma,
	430	unsigned long address, pte_t *ptep,
	431	pte_t entry, int dirty);
195466dc JF	432
195466dc JF	433	#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
f9fbf1a3 JF	434	extern int ptep_test_and_clear_young(struct vm_area_struct *vma,
f9fbf1a3 JF	435	unsigned long addr, pte_t *ptep);
195466dc JF	436
195466dc JF	437	#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
c20311e1 JF	438	extern int ptep_clear_flush_young(struct vm_area_struct *vma,
c20311e1 JF	439	unsigned long address, pte_t *ptep);
195466dc JF	440
195466dc JF	441	#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
3cbaeafe JP	442	static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
3cbaeafe JP	443	pte_t *ptep)
195466dc JF	444	{
	445	pte_t pte = native_ptep_get_and_clear(ptep);
	446	pte_update(mm, addr, ptep);
	447	return pte;
	448	}
	449
	450	#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
3cbaeafe JP	451	static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
	452	unsigned long addr, pte_t *ptep,
	453	int full)
195466dc JF	454	{
	455	pte_t pte;
	456	if (full) {
	457	/*
	458	* Full address destruction in progress; paravirt does not
	459	* care about updates and native needs no locking
	460	*/
	461	pte = native_local_ptep_get_and_clear(ptep);
	462	} else {
	463	pte = ptep_get_and_clear(mm, addr, ptep);
	464	}
	465	return pte;
	466	}
	467
	468	#define __HAVE_ARCH_PTEP_SET_WRPROTECT
3cbaeafe JP	469	static inline void ptep_set_wrprotect(struct mm_struct *mm,
3cbaeafe JP	470	unsigned long addr, pte_t *ptep)
195466dc	471	{
d8d89827	472	clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
195466dc JF	473	pte_update(mm, addr, ptep);
	474	}
	475
85958b46 JF	476	/*
	477	* clone_pgd_range(pgd_t dst, pgd_t src, int count);
	478	*
	479	* dst - pointer to pgd range anwhere on a pgd page
	480	* src - ""
	481	* count - the number of pgds to copy.
	482	*
	483	* dst and src can be on the same page, but the range must not overlap,
	484	* and must not cross a page boundary.
	485	*/
	486	static inline void clone_pgd_range(pgd_t dst, pgd_t src, int count)
	487	{
	488	memcpy(dst, src, count * sizeof(pgd_t));
	489	}
	490
	491
195466dc JF	492	#include <asm-generic/pgtable.h>
	493	#endif /* __ASSEMBLY__ */
	494
6c386655	495	#endif /* _ASM_X86_PGTABLE_H */