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

#ifndef _ASM_X86_PGTABLE_H
#define _ASM_X86_PGTABLE_H

#define USER_PTRS_PER_PGD	((TASK_SIZE-1)/PGDIR_SIZE+1)
#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 */

/*
 * Note: we use _AC(1, L) instead of _AC(1, UL) so that we get a
 * sign-extended value on 32-bit with all 1's in the upper word,
 * which preserves the upper pte values on 64-bit ptes:
 */
#define _PAGE_PRESENT	(_AC(1, L)<<_PAGE_BIT_PRESENT)
#define _PAGE_RW	(_AC(1, L)<<_PAGE_BIT_RW)
#define _PAGE_USER	(_AC(1, L)<<_PAGE_BIT_USER)
#define _PAGE_PWT	(_AC(1, L)<<_PAGE_BIT_PWT)
#define _PAGE_PCD	(_AC(1, L)<<_PAGE_BIT_PCD)
#define _PAGE_ACCESSED	(_AC(1, L)<<_PAGE_BIT_ACCESSED)
#define _PAGE_DIRTY	(_AC(1, L)<<_PAGE_BIT_DIRTY)
#define _PAGE_PSE	(_AC(1, L)<<_PAGE_BIT_PSE)	/* 2MB page */
#define _PAGE_GLOBAL	(_AC(1, L)<<_PAGE_BIT_GLOBAL)	/* Global TLB entry */
#define _PAGE_UNUSED1	(_AC(1, L)<<_PAGE_BIT_UNUSED1)
#define _PAGE_UNUSED2	(_AC(1, L)<<_PAGE_BIT_UNUSED2)
#define _PAGE_UNUSED3	(_AC(1, L)<<_PAGE_BIT_UNUSED3)
#define _PAGE_PAT	(_AC(1, L)<<_PAGE_BIT_PAT)
#define _PAGE_PAT_LARGE (_AC(1, L)<<_PAGE_BIT_PAT_LARGE)

#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
#define _PAGE_NX	(_AC(1, ULL) << _PAGE_BIT_NX)
#else
#define _PAGE_NX	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)

#define _PAGE_CHG_MASK	(PTE_MASK | _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_val(pte) & _PAGE_DIRTY;
}

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

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

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

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

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

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

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) & ~(pteval_t)_PAGE_DIRTY);
}

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

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

static inline pte_t pte_mkexec(pte_t pte)
{
	return __pte(pte_val(pte) & ~(pteval_t)_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) & ~(pteval_t)_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) & ~(pteval_t)_PAGE_GLOBAL);
}

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 & ~_PAGE_NX;
	val |= pgprot_val(newprot) & __supported_pte_mask;

	return __pte(val);
}

#define pte_pgprot(x) __pgprot(pte_val(x) & (0xfff | _PAGE_NX))

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

#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

#ifndef __ASSEMBLY__

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

/*
 * 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
#define ptep_set_access_flags(vma, address, ptep, entry, dirty)		\
({									\
	int __changed = !pte_same(*(ptep), entry);			\
	if (__changed && dirty) {					\
		*ptep = entry;						\
		pte_update_defer((vma)->vm_mm, (address), (ptep));	\
		flush_tlb_page(vma, address);				\
	}								\
	__changed;							\
})

#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
#define ptep_test_and_clear_young(vma, addr, ptep) ({			\
	int __ret = 0;							\
	if (pte_young(*(ptep)))						\
		__ret = test_and_clear_bit(_PAGE_BIT_ACCESSED,		\
					   &(ptep)->pte);		\
	if (__ret)							\
		pte_update((vma)->vm_mm, addr, ptep);			\
	__ret;								\
})

#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
#define ptep_clear_flush_young(vma, address, ptep)			\
({									\
	int __young;							\
	__young = ptep_test_and_clear_young((vma), (address), (ptep));	\
	if (__young)							\
		flush_tlb_page(vma, address);				\
	__young;							\
})

#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);
}

#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
	4	#define USER_PTRS_PER_PGD ((TASK_SIZE-1)/PGDIR_SIZE+1)
	5	#define FIRST_USER_ADDRESS 0
	6
43cdf5d6 JS	7	#define _PAGE_BIT_PRESENT 0 /* is present */
	8	#define _PAGE_BIT_RW 1 /* writeable */
	9	#define _PAGE_BIT_USER 2 /* userspace addressable */
	10	#define _PAGE_BIT_PWT 3 /* page write through */
	11	#define _PAGE_BIT_PCD 4 /* page cache disabled */
	12	#define _PAGE_BIT_ACCESSED 5 /* was accessed (raised by CPU) */
	13	#define _PAGE_BIT_DIRTY 6 /* was written to (raised by CPU) */
6c386655 JF	14	#define _PAGE_BIT_FILE 6
6c386655 JF	15	#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */
9bf5a475	16	#define _PAGE_BIT_PAT 7 /* on 4KB pages */
6c386655 JF	17	#define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */
	18	#define _PAGE_BIT_UNUSED1 9 /* available for programmer */
	19	#define _PAGE_BIT_UNUSED2 10
	20	#define _PAGE_BIT_UNUSED3 11
9bf5a475	21	#define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */
6c386655 JF	22	#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */
6c386655 JF	23
f2919232 JF	24	/*
	25	* Note: we use _AC(1, L) instead of _AC(1, UL) so that we get a
	26	* sign-extended value on 32-bit with all 1's in the upper word,
	27	* which preserves the upper pte values on 64-bit ptes:
	28	*/
61f38226 IM	29	#define _PAGE_PRESENT (_AC(1, L)<<_PAGE_BIT_PRESENT)
	30	#define _PAGE_RW (_AC(1, L)<<_PAGE_BIT_RW)
	31	#define _PAGE_USER (_AC(1, L)<<_PAGE_BIT_USER)
	32	#define _PAGE_PWT (_AC(1, L)<<_PAGE_BIT_PWT)
	33	#define _PAGE_PCD (_AC(1, L)<<_PAGE_BIT_PCD)
	34	#define _PAGE_ACCESSED (_AC(1, L)<<_PAGE_BIT_ACCESSED)
	35	#define _PAGE_DIRTY (_AC(1, L)<<_PAGE_BIT_DIRTY)
	36	#define _PAGE_PSE (_AC(1, L)<<_PAGE_BIT_PSE) /* 2MB page */
	37	#define _PAGE_GLOBAL (_AC(1, L)<<_PAGE_BIT_GLOBAL) /* Global TLB entry */
	38	#define _PAGE_UNUSED1 (_AC(1, L)<<_PAGE_BIT_UNUSED1)
	39	#define _PAGE_UNUSED2 (_AC(1, L)<<_PAGE_BIT_UNUSED2)
	40	#define _PAGE_UNUSED3 (_AC(1, L)<<_PAGE_BIT_UNUSED3)
9bf5a475 AK	41	#define _PAGE_PAT (_AC(1, L)<<_PAGE_BIT_PAT)
9bf5a475 AK	42	#define _PAGE_PAT_LARGE (_AC(1, L)<<_PAGE_BIT_PAT_LARGE)
6c386655 JF	43
	44	#if defined(CONFIG_X86_64) \|\| defined(CONFIG_X86_PAE)
	45	#define _PAGE_NX (_AC(1, ULL) << _PAGE_BIT_NX)
	46	#else
	47	#define _PAGE_NX 0
	48	#endif
	49
	50	/* If _PAGE_PRESENT is clear, we use these: */
3cbaeafe JP	51	#define _PAGE_FILE _PAGE_DIRTY /* nonlinear file mapping,
3cbaeafe JP	52	* saved PTE; unset:swap */
6c386655 JF	53	#define _PAGE_PROTNONE _PAGE_PSE /* if the user mapped it with PROT_NONE;
	54	pte_present gives true */
	55
3cbaeafe JP	56	#define _PAGE_TABLE (_PAGE_PRESENT \| _PAGE_RW \| _PAGE_USER \| \
	57	_PAGE_ACCESSED \| _PAGE_DIRTY)
	58	#define _KERNPG_TABLE (_PAGE_PRESENT \| _PAGE_RW \| _PAGE_ACCESSED \| \
	59	_PAGE_DIRTY)
6c386655 JF	60
	61	#define _PAGE_CHG_MASK (PTE_MASK \| _PAGE_ACCESSED \| _PAGE_DIRTY)
	62
2e5d9c85	63	#define _PAGE_CACHE_MASK (_PAGE_PCD \| _PAGE_PWT)
	64	#define _PAGE_CACHE_WB (0)
	65	#define _PAGE_CACHE_WC (_PAGE_PWT)
	66	#define _PAGE_CACHE_UC_MINUS (_PAGE_PCD)
	67	#define _PAGE_CACHE_UC (_PAGE_PCD \| _PAGE_PWT)
	68
6c386655	69	#define PAGE_NONE __pgprot(_PAGE_PROTNONE \| _PAGE_ACCESSED)
3cbaeafe JP	70	#define PAGE_SHARED __pgprot(_PAGE_PRESENT \| _PAGE_RW \| _PAGE_USER \| \
	71	_PAGE_ACCESSED \| _PAGE_NX)
	72
	73	#define PAGE_SHARED_EXEC __pgprot(_PAGE_PRESENT \| _PAGE_RW \| \
	74	_PAGE_USER \| _PAGE_ACCESSED)
	75	#define PAGE_COPY_NOEXEC __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	76	_PAGE_ACCESSED \| _PAGE_NX)
	77	#define PAGE_COPY_EXEC __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	78	_PAGE_ACCESSED)
6c386655	79	#define PAGE_COPY PAGE_COPY_NOEXEC
3cbaeafe JP	80	#define PAGE_READONLY __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	81	_PAGE_ACCESSED \| _PAGE_NX)
	82	#define PAGE_READONLY_EXEC __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	83	_PAGE_ACCESSED)
6c386655 JF	84
	85	#ifdef CONFIG_X86_32
	86	#define _PAGE_KERNEL_EXEC \
	87	(_PAGE_PRESENT \| _PAGE_RW \| _PAGE_DIRTY \| _PAGE_ACCESSED)
	88	#define _PAGE_KERNEL (_PAGE_KERNEL_EXEC \| _PAGE_NX)
	89
	90	#ifndef __ASSEMBLY__
c93c82bb	91	extern pteval_t __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
6c386655 JF	92	#endif /* __ASSEMBLY__ */
	93	#else
	94	#define __PAGE_KERNEL_EXEC \
	95	(_PAGE_PRESENT \| _PAGE_RW \| _PAGE_DIRTY \| _PAGE_ACCESSED)
	96	#define __PAGE_KERNEL (__PAGE_KERNEL_EXEC \| _PAGE_NX)
	97	#endif
	98
	99	#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW)
	100	#define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW)
d2e626f4	101	#define __PAGE_KERNEL_EXEC_NOCACHE (__PAGE_KERNEL_EXEC \| _PAGE_PCD \| _PAGE_PWT)
b310f381	102	#define __PAGE_KERNEL_WC (__PAGE_KERNEL \| _PAGE_CACHE_WC)
6c386655	103	#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL \| _PAGE_PCD \| _PAGE_PWT)
d546b67a	104	#define __PAGE_KERNEL_UC_MINUS (__PAGE_KERNEL \| _PAGE_PCD)
6c386655 JF	105	#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX \| _PAGE_USER)
	106	#define __PAGE_KERNEL_VSYSCALL_NOCACHE (__PAGE_KERNEL_VSYSCALL \| _PAGE_PCD \| _PAGE_PWT)
	107	#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL \| _PAGE_PSE)
	108	#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC \| _PAGE_PSE)
	109
	110	#ifdef CONFIG_X86_32
	111	# define MAKE_GLOBAL(x) __pgprot((x))
	112	#else
	113	# define MAKE_GLOBAL(x) __pgprot((x) \| _PAGE_GLOBAL)
	114	#endif
	115
	116	#define PAGE_KERNEL MAKE_GLOBAL(__PAGE_KERNEL)
	117	#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO)
	118	#define PAGE_KERNEL_EXEC MAKE_GLOBAL(__PAGE_KERNEL_EXEC)
	119	#define PAGE_KERNEL_RX MAKE_GLOBAL(__PAGE_KERNEL_RX)
b310f381	120	#define PAGE_KERNEL_WC MAKE_GLOBAL(__PAGE_KERNEL_WC)
6c386655	121	#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
d546b67a	122	#define PAGE_KERNEL_UC_MINUS MAKE_GLOBAL(__PAGE_KERNEL_UC_MINUS)
d2e626f4	123	#define PAGE_KERNEL_EXEC_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_EXEC_NOCACHE)
6c386655 JF	124	#define PAGE_KERNEL_LARGE MAKE_GLOBAL(__PAGE_KERNEL_LARGE)
	125	#define PAGE_KERNEL_LARGE_EXEC MAKE_GLOBAL(__PAGE_KERNEL_LARGE_EXEC)
	126	#define PAGE_KERNEL_VSYSCALL MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL)
	127	#define PAGE_KERNEL_VSYSCALL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL_NOCACHE)
	128
	129	/* xwr */
	130	#define __P000 PAGE_NONE
	131	#define __P001 PAGE_READONLY
	132	#define __P010 PAGE_COPY
	133	#define __P011 PAGE_COPY
	134	#define __P100 PAGE_READONLY_EXEC
	135	#define __P101 PAGE_READONLY_EXEC
	136	#define __P110 PAGE_COPY_EXEC
	137	#define __P111 PAGE_COPY_EXEC
	138
	139	#define __S000 PAGE_NONE
	140	#define __S001 PAGE_READONLY
	141	#define __S010 PAGE_SHARED
	142	#define __S011 PAGE_SHARED
	143	#define __S100 PAGE_READONLY_EXEC
	144	#define __S101 PAGE_READONLY_EXEC
	145	#define __S110 PAGE_SHARED_EXEC
	146	#define __S111 PAGE_SHARED_EXEC
	147
4614139c	148	#ifndef __ASSEMBLY__
195466dc	149
8405b122 JF	150	/*
	151	* ZERO_PAGE is a global shared page that is always zero: used
	152	* for zero-mapped memory areas etc..
	153	*/
3cbaeafe	154	extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
8405b122 JF	155	#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
8405b122 JF	156
e3ed910d JF	157	extern spinlock_t pgd_lock;
e3ed910d JF	158	extern struct list_head pgd_list;
8405b122	159
4614139c JF	160	/*
	161	* The following only work if pte_present() is true.
	162	* Undefined behaviour if not..
	163	*/
3cbaeafe JP	164	static inline int pte_dirty(pte_t pte)
	165	{
	166	return pte_val(pte) & _PAGE_DIRTY;
	167	}
	168
	169	static inline int pte_young(pte_t pte)
	170	{
	171	return pte_val(pte) & _PAGE_ACCESSED;
	172	}
	173
	174	static inline int pte_write(pte_t pte)
	175	{
	176	return pte_val(pte) & _PAGE_RW;
	177	}
	178
	179	static inline int pte_file(pte_t pte)
	180	{
	181	return pte_val(pte) & _PAGE_FILE;
	182	}
	183
	184	static inline int pte_huge(pte_t pte)
	185	{
	186	return pte_val(pte) & _PAGE_PSE;
4614139c JF	187	}
4614139c JF	188
3cbaeafe JP	189	static inline int pte_global(pte_t pte)
	190	{
	191	return pte_val(pte) & _PAGE_GLOBAL;
	192	}
	193
	194	static inline int pte_exec(pte_t pte)
	195	{
	196	return !(pte_val(pte) & _PAGE_NX);
	197	}
	198
	199	static inline int pmd_large(pmd_t pte)
	200	{
	201	return (pmd_val(pte) & (_PAGE_PSE \| _PAGE_PRESENT)) ==
	202	(_PAGE_PSE \| _PAGE_PRESENT);
	203	}
	204
	205	static inline pte_t pte_mkclean(pte_t pte)
	206	{
	207	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_DIRTY);
	208	}
	209
	210	static inline pte_t pte_mkold(pte_t pte)
	211	{
	212	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_ACCESSED);
	213	}
	214
	215	static inline pte_t pte_wrprotect(pte_t pte)
	216	{
	217	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_RW);
	218	}
	219
	220	static inline pte_t pte_mkexec(pte_t pte)
	221	{
	222	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_NX);
	223	}
	224
	225	static inline pte_t pte_mkdirty(pte_t pte)
	226	{
	227	return __pte(pte_val(pte) \| _PAGE_DIRTY);
	228	}
	229
	230	static inline pte_t pte_mkyoung(pte_t pte)
	231	{
	232	return __pte(pte_val(pte) \| _PAGE_ACCESSED);
	233	}
	234
	235	static inline pte_t pte_mkwrite(pte_t pte)
	236	{
	237	return __pte(pte_val(pte) \| _PAGE_RW);
	238	}
	239
	240	static inline pte_t pte_mkhuge(pte_t pte)
	241	{
	242	return __pte(pte_val(pte) \| _PAGE_PSE);
	243	}
	244
	245	static inline pte_t pte_clrhuge(pte_t pte)
	246	{
	247	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_PSE);
	248	}
	249
	250	static inline pte_t pte_mkglobal(pte_t pte)
	251	{
	252	return __pte(pte_val(pte) \| _PAGE_GLOBAL);
253	}
254
255	static inline pte_t pte_clrglobal(pte_t pte)
256	{
257	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_GLOBAL);
258	}
4614139c	259
6fdc05d4 JF	260	extern pteval_t __supported_pte_mask;
	261
	262	static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
	263	{
	264	return __pte((((phys_addr_t)page_nr << PAGE_SHIFT) \|
	265	pgprot_val(pgprot)) & __supported_pte_mask);
	266	}
	267
	268	static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
	269	{
	270	return __pmd((((phys_addr_t)page_nr << PAGE_SHIFT) \|
	271	pgprot_val(pgprot)) & __supported_pte_mask);
	272	}
	273
38472311 IM	274	static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
	275	{
	276	pteval_t val = pte_val(pte);
	277
	278	/*
	279	* Chop off the NX bit (if present), and add the NX portion of
	280	* the newprot (if present):
	281	*/
	282	val &= _PAGE_CHG_MASK & ~_PAGE_NX;
	283	val \|= pgprot_val(newprot) & __supported_pte_mask;
	284
	285	return __pte(val);
	286	}
	287
c6ca18eb AK	288	#define pte_pgprot(x) __pgprot(pte_val(x) & (0xfff \| _PAGE_NX))
c6ca18eb AK	289
1e8e23bc AK	290	#define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
1e8e23bc AK	291
4891645e JF	292	#ifdef CONFIG_PARAVIRT
	293	#include <asm/paravirt.h>
	294	#else /* !CONFIG_PARAVIRT */
	295	#define set_pte(ptep, pte) native_set_pte(ptep, pte)
	296	#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte)
	297
	298	#define set_pte_present(mm, addr, ptep, pte) \
	299	native_set_pte_present(mm, addr, ptep, pte)
	300	#define set_pte_atomic(ptep, pte) \
	301	native_set_pte_atomic(ptep, pte)
	302
	303	#define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd)
	304
	305	#ifndef __PAGETABLE_PUD_FOLDED
	306	#define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd)
	307	#define pgd_clear(pgd) native_pgd_clear(pgd)
	308	#endif
	309
	310	#ifndef set_pud
	311	# define set_pud(pudp, pud) native_set_pud(pudp, pud)
	312	#endif
	313
	314	#ifndef __PAGETABLE_PMD_FOLDED
	315	#define pud_clear(pud) native_pud_clear(pud)
	316	#endif
	317
	318	#define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep)
	319	#define pmd_clear(pmd) native_pmd_clear(pmd)
	320
	321	#define pte_update(mm, addr, ptep) do { } while (0)
	322	#define pte_update_defer(mm, addr, ptep) do { } while (0)
	323	#endif /* CONFIG_PARAVIRT */
	324
4614139c JF	325	#endif /* __ASSEMBLY__ */
4614139c JF	326
96a388de TG	327	#ifdef CONFIG_X86_32
	328	# include "pgtable_32.h"
	329	#else
	330	# include "pgtable_64.h"
	331	#endif
6c386655	332
195466dc JF	333	#ifndef __ASSEMBLY__
195466dc JF	334
30551bb3 TG	335	enum {
	336	PG_LEVEL_NONE,
	337	PG_LEVEL_4K,
	338	PG_LEVEL_2M,
86f03989	339	PG_LEVEL_1G,
30551bb3 TG	340	};
30551bb3 TG	341
0a663088 TG	342	/*
	343	* Helper function that returns the kernel pagetable entry controlling
	344	* the virtual address 'address'. NULL means no pagetable entry present.
	345	* NOTE: the return type is pte_t but if the pmd is PSE then we return it
	346	* as a pte too.
	347	*/
da7bfc50	348	extern pte_t lookup_address(unsigned long address, unsigned int level);
0a663088	349
4891645e JF	350	/* local pte updates need not use xchg for locking */
	351	static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
	352	{
	353	pte_t res = *ptep;
	354
	355	/* Pure native function needs no input for mm, addr */
	356	native_pte_clear(NULL, 0, ptep);
	357	return res;
	358	}
	359
	360	static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
	361	pte_t *ptep , pte_t pte)
	362	{
	363	native_set_pte(ptep, pte);
	364	}
	365
195466dc JF	366	#ifndef CONFIG_PARAVIRT
	367	/*
	368	* Rules for using pte_update - it must be called after any PTE update which
	369	* has not been done using the set_pte / clear_pte interfaces. It is used by
	370	* shadow mode hypervisors to resynchronize the shadow page tables. Kernel PTE
	371	* updates should either be sets, clears, or set_pte_atomic for P->P
	372	* transitions, which means this hook should only be called for user PTEs.
	373	* This hook implies a P->P protection or access change has taken place, which
	374	* requires a subsequent TLB flush. The notification can optionally be delayed
	375	* until the TLB flush event by using the pte_update_defer form of the
	376	* interface, but care must be taken to assure that the flush happens while
	377	* still holding the same page table lock so that the shadow and primary pages
	378	* do not become out of sync on SMP.
	379	*/
	380	#define pte_update(mm, addr, ptep) do { } while (0)
	381	#define pte_update_defer(mm, addr, ptep) do { } while (0)
	382	#endif
	383
195466dc JF	384	/*
	385	* We only update the dirty/accessed state if we set
	386	* the dirty bit by hand in the kernel, since the hardware
	387	* will do the accessed bit for us, and we don't want to
	388	* race with other CPU's that might be updating the dirty
	389	* bit at the same time.
	390	*/
	391	#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
	392	#define ptep_set_access_flags(vma, address, ptep, entry, dirty) \
	393	({ \
	394	int __changed = !pte_same(*(ptep), entry); \
	395	if (__changed && dirty) { \
	396	*ptep = entry; \
	397	pte_update_defer((vma)->vm_mm, (address), (ptep)); \
	398	flush_tlb_page(vma, address); \
	399	} \
	400	__changed; \
	401	})
	402
	403	#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
	404	#define ptep_test_and_clear_young(vma, addr, ptep) ({ \
	405	int __ret = 0; \
	406	if (pte_young(*(ptep))) \
	407	__ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, \
	408	&(ptep)->pte); \
	409	if (__ret) \
	410	pte_update((vma)->vm_mm, addr, ptep); \
	411	__ret; \
	412	})
	413
	414	#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
	415	#define ptep_clear_flush_young(vma, address, ptep) \
	416	({ \
	417	int __young; \
	418	__young = ptep_test_and_clear_young((vma), (address), (ptep)); \
	419	if (__young) \
	420	flush_tlb_page(vma, address); \
	421	__young; \
	422	})
	423
	424	#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
3cbaeafe JP	425	static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
3cbaeafe JP	426	pte_t *ptep)
195466dc JF	427	{
	428	pte_t pte = native_ptep_get_and_clear(ptep);
	429	pte_update(mm, addr, ptep);
	430	return pte;
	431	}
	432
	433	#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
3cbaeafe JP	434	static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
	435	unsigned long addr, pte_t *ptep,
	436	int full)
195466dc JF	437	{
	438	pte_t pte;
	439	if (full) {
	440	/*
	441	* Full address destruction in progress; paravirt does not
	442	* care about updates and native needs no locking
	443	*/
	444	pte = native_local_ptep_get_and_clear(ptep);
	445	} else {
	446	pte = ptep_get_and_clear(mm, addr, ptep);
	447	}
	448	return pte;
	449	}
	450
	451	#define __HAVE_ARCH_PTEP_SET_WRPROTECT
3cbaeafe JP	452	static inline void ptep_set_wrprotect(struct mm_struct *mm,
3cbaeafe JP	453	unsigned long addr, pte_t *ptep)
195466dc	454	{
d8d89827	455	clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
195466dc JF	456	pte_update(mm, addr, ptep);
	457	}
	458
195466dc JF	459	#include <asm-generic/pgtable.h>
	460	#endif /* __ASSEMBLY__ */
	461
6c386655	462	#endif /* _ASM_X86_PGTABLE_H */