[deliverable/linux.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
#define _PAGE_BIT_RW		1
#define _PAGE_BIT_USER		2
#define _PAGE_BIT_PWT		3
#define _PAGE_BIT_PCD		4
#define _PAGE_BIT_ACCESSED	5
#define _PAGE_BIT_DIRTY		6
#define _PAGE_BIT_FILE		6
#define _PAGE_BIT_PSE		7	/* 4 MB (or 2MB) page */
#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_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)

#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_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_NOCACHE		(__PAGE_KERNEL | _PAGE_PCD | _PAGE_PWT)
#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_NOCACHE		MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
#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, 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
	7	#define _PAGE_BIT_PRESENT 0
	8	#define _PAGE_BIT_RW 1
	9	#define _PAGE_BIT_USER 2
	10	#define _PAGE_BIT_PWT 3
	11	#define _PAGE_BIT_PCD 4
	12	#define _PAGE_BIT_ACCESSED 5
	13	#define _PAGE_BIT_DIRTY 6
	14	#define _PAGE_BIT_FILE 6
	15	#define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */
	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
	20	#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */
	21
f2919232 JF	22	/*
	23	* Note: we use _AC(1, L) instead of _AC(1, UL) so that we get a
	24	* sign-extended value on 32-bit with all 1's in the upper word,
	25	* which preserves the upper pte values on 64-bit ptes:
	26	*/
61f38226 IM	27	#define _PAGE_PRESENT (_AC(1, L)<<_PAGE_BIT_PRESENT)
	28	#define _PAGE_RW (_AC(1, L)<<_PAGE_BIT_RW)
	29	#define _PAGE_USER (_AC(1, L)<<_PAGE_BIT_USER)
	30	#define _PAGE_PWT (_AC(1, L)<<_PAGE_BIT_PWT)
	31	#define _PAGE_PCD (_AC(1, L)<<_PAGE_BIT_PCD)
	32	#define _PAGE_ACCESSED (_AC(1, L)<<_PAGE_BIT_ACCESSED)
	33	#define _PAGE_DIRTY (_AC(1, L)<<_PAGE_BIT_DIRTY)
	34	#define _PAGE_PSE (_AC(1, L)<<_PAGE_BIT_PSE) /* 2MB page */
	35	#define _PAGE_GLOBAL (_AC(1, L)<<_PAGE_BIT_GLOBAL) /* Global TLB entry */
	36	#define _PAGE_UNUSED1 (_AC(1, L)<<_PAGE_BIT_UNUSED1)
	37	#define _PAGE_UNUSED2 (_AC(1, L)<<_PAGE_BIT_UNUSED2)
	38	#define _PAGE_UNUSED3 (_AC(1, L)<<_PAGE_BIT_UNUSED3)
6c386655 JF	39
	40	#if defined(CONFIG_X86_64) \|\| defined(CONFIG_X86_PAE)
	41	#define _PAGE_NX (_AC(1, ULL) << _PAGE_BIT_NX)
	42	#else
	43	#define _PAGE_NX 0
	44	#endif
	45
	46	/* If _PAGE_PRESENT is clear, we use these: */
	47	#define _PAGE_FILE _PAGE_DIRTY /* nonlinear file mapping, saved PTE; unset:swap */
	48	#define _PAGE_PROTNONE _PAGE_PSE /* if the user mapped it with PROT_NONE;
	49	pte_present gives true */
	50
	51	#define _PAGE_TABLE (_PAGE_PRESENT \| _PAGE_RW \| _PAGE_USER \| _PAGE_ACCESSED \| _PAGE_DIRTY)
	52	#define _KERNPG_TABLE (_PAGE_PRESENT \| _PAGE_RW \| _PAGE_ACCESSED \| _PAGE_DIRTY)
	53
	54	#define _PAGE_CHG_MASK (PTE_MASK \| _PAGE_ACCESSED \| _PAGE_DIRTY)
	55
	56	#define PAGE_NONE __pgprot(_PAGE_PROTNONE \| _PAGE_ACCESSED)
	57	#define PAGE_SHARED __pgprot(_PAGE_PRESENT \| _PAGE_RW \| _PAGE_USER \| _PAGE_ACCESSED \| _PAGE_NX)
	58
	59	#define PAGE_SHARED_EXEC __pgprot(_PAGE_PRESENT \| _PAGE_RW \| _PAGE_USER \| _PAGE_ACCESSED)
	60	#define PAGE_COPY_NOEXEC __pgprot(_PAGE_PRESENT \| _PAGE_USER \| _PAGE_ACCESSED \| _PAGE_NX)
	61	#define PAGE_COPY_EXEC __pgprot(_PAGE_PRESENT \| _PAGE_USER \| _PAGE_ACCESSED)
	62	#define PAGE_COPY PAGE_COPY_NOEXEC
	63	#define PAGE_READONLY __pgprot(_PAGE_PRESENT \| _PAGE_USER \| _PAGE_ACCESSED \| _PAGE_NX)
	64	#define PAGE_READONLY_EXEC __pgprot(_PAGE_PRESENT \| _PAGE_USER \| _PAGE_ACCESSED)
	65
	66	#ifdef CONFIG_X86_32
	67	#define _PAGE_KERNEL_EXEC \
	68	(_PAGE_PRESENT \| _PAGE_RW \| _PAGE_DIRTY \| _PAGE_ACCESSED)
	69	#define _PAGE_KERNEL (_PAGE_KERNEL_EXEC \| _PAGE_NX)
	70
	71	#ifndef __ASSEMBLY__
c93c82bb	72	extern pteval_t __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
6c386655 JF	73	#endif /* __ASSEMBLY__ */
	74	#else
	75	#define __PAGE_KERNEL_EXEC \
	76	(_PAGE_PRESENT \| _PAGE_RW \| _PAGE_DIRTY \| _PAGE_ACCESSED)
	77	#define __PAGE_KERNEL (__PAGE_KERNEL_EXEC \| _PAGE_NX)
	78	#endif
	79
	80	#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW)
	81	#define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW)
d2e626f4	82	#define __PAGE_KERNEL_EXEC_NOCACHE (__PAGE_KERNEL_EXEC \| _PAGE_PCD \| _PAGE_PWT)
6c386655 JF	83	#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL \| _PAGE_PCD \| _PAGE_PWT)
	84	#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX \| _PAGE_USER)
	85	#define __PAGE_KERNEL_VSYSCALL_NOCACHE (__PAGE_KERNEL_VSYSCALL \| _PAGE_PCD \| _PAGE_PWT)
	86	#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL \| _PAGE_PSE)
	87	#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC \| _PAGE_PSE)
	88
	89	#ifdef CONFIG_X86_32
	90	# define MAKE_GLOBAL(x) __pgprot((x))
	91	#else
	92	# define MAKE_GLOBAL(x) __pgprot((x) \| _PAGE_GLOBAL)
	93	#endif
	94
	95	#define PAGE_KERNEL MAKE_GLOBAL(__PAGE_KERNEL)
	96	#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO)
	97	#define PAGE_KERNEL_EXEC MAKE_GLOBAL(__PAGE_KERNEL_EXEC)
	98	#define PAGE_KERNEL_RX MAKE_GLOBAL(__PAGE_KERNEL_RX)
	99	#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
d2e626f4	100	#define PAGE_KERNEL_EXEC_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_EXEC_NOCACHE)
6c386655 JF	101	#define PAGE_KERNEL_LARGE MAKE_GLOBAL(__PAGE_KERNEL_LARGE)
	102	#define PAGE_KERNEL_LARGE_EXEC MAKE_GLOBAL(__PAGE_KERNEL_LARGE_EXEC)
	103	#define PAGE_KERNEL_VSYSCALL MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL)
	104	#define PAGE_KERNEL_VSYSCALL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL_NOCACHE)
	105
	106	/* xwr */
	107	#define __P000 PAGE_NONE
	108	#define __P001 PAGE_READONLY
	109	#define __P010 PAGE_COPY
	110	#define __P011 PAGE_COPY
	111	#define __P100 PAGE_READONLY_EXEC
	112	#define __P101 PAGE_READONLY_EXEC
	113	#define __P110 PAGE_COPY_EXEC
	114	#define __P111 PAGE_COPY_EXEC
	115
	116	#define __S000 PAGE_NONE
	117	#define __S001 PAGE_READONLY
	118	#define __S010 PAGE_SHARED
	119	#define __S011 PAGE_SHARED
	120	#define __S100 PAGE_READONLY_EXEC
	121	#define __S101 PAGE_READONLY_EXEC
	122	#define __S110 PAGE_SHARED_EXEC
	123	#define __S111 PAGE_SHARED_EXEC
	124
4614139c	125	#ifndef __ASSEMBLY__
195466dc	126
8405b122 JF	127	/*
	128	* ZERO_PAGE is a global shared page that is always zero: used
	129	* for zero-mapped memory areas etc..
	130	*/
	131	extern unsigned long empty_zero_page[PAGE_SIZE/sizeof(unsigned long)];
	132	#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
	133
e3ed910d JF	134	extern spinlock_t pgd_lock;
e3ed910d JF	135	extern struct list_head pgd_list;
8405b122	136
4614139c JF	137	/*
	138	* The following only work if pte_present() is true.
	139	* Undefined behaviour if not..
	140	*/
	141	static inline int pte_dirty(pte_t pte) { return pte_val(pte) & _PAGE_DIRTY; }
	142	static inline int pte_young(pte_t pte) { return pte_val(pte) & _PAGE_ACCESSED; }
	143	static inline int pte_write(pte_t pte) { return pte_val(pte) & _PAGE_RW; }
	144	static inline int pte_file(pte_t pte) { return pte_val(pte) & _PAGE_FILE; }
	145	static inline int pte_huge(pte_t pte) { return pte_val(pte) & _PAGE_PSE; }
a5a5dc31	146	static inline int pte_global(pte_t pte) { return pte_val(pte) & _PAGE_GLOBAL; }
4c3c4b45	147	static inline int pte_exec(pte_t pte) { return !(pte_val(pte) & _PAGE_NX); }
4614139c JF	148
	149	static inline int pmd_large(pmd_t pte) {
	150	return (pmd_val(pte) & (_PAGE_PSE\|_PAGE_PRESENT)) ==
	151	(_PAGE_PSE\|_PAGE_PRESENT);
	152	}
	153
aaa0e890 AK	154	static inline pte_t pte_mkclean(pte_t pte) { return __pte(pte_val(pte) & ~(pteval_t)_PAGE_DIRTY); }
	155	static inline pte_t pte_mkold(pte_t pte) { return __pte(pte_val(pte) & ~(pteval_t)_PAGE_ACCESSED); }
	156	static inline pte_t pte_wrprotect(pte_t pte) { return __pte(pte_val(pte) & ~(pteval_t)_PAGE_RW); }
	157	static inline pte_t pte_mkexec(pte_t pte) { return __pte(pte_val(pte) & ~(pteval_t)_PAGE_NX); }
4614139c JF	158	static inline pte_t pte_mkdirty(pte_t pte) { return __pte(pte_val(pte) \| _PAGE_DIRTY); }
	159	static inline pte_t pte_mkyoung(pte_t pte) { return __pte(pte_val(pte) \| _PAGE_ACCESSED); }
	160	static inline pte_t pte_mkwrite(pte_t pte) { return __pte(pte_val(pte) \| _PAGE_RW); }
	161	static inline pte_t pte_mkhuge(pte_t pte) { return __pte(pte_val(pte) \| _PAGE_PSE); }
aaa0e890	162	static inline pte_t pte_clrhuge(pte_t pte) { return __pte(pte_val(pte) & ~(pteval_t)_PAGE_PSE); }
a5a5dc31	163	static inline pte_t pte_mkglobal(pte_t pte) { return __pte(pte_val(pte) \| _PAGE_GLOBAL); }
aaa0e890	164	static inline pte_t pte_clrglobal(pte_t pte) { return __pte(pte_val(pte) & ~(pteval_t)_PAGE_GLOBAL); }
4614139c	165
6fdc05d4 JF	166	extern pteval_t __supported_pte_mask;
	167
	168	static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
	169	{
	170	return __pte((((phys_addr_t)page_nr << PAGE_SHIFT) \|
	171	pgprot_val(pgprot)) & __supported_pte_mask);
	172	}
	173
	174	static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
	175	{
	176	return __pmd((((phys_addr_t)page_nr << PAGE_SHIFT) \|
	177	pgprot_val(pgprot)) & __supported_pte_mask);
	178	}
	179
38472311 IM	180	static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
	181	{
	182	pteval_t val = pte_val(pte);
	183
	184	/*
	185	* Chop off the NX bit (if present), and add the NX portion of
	186	* the newprot (if present):
	187	*/
	188	val &= _PAGE_CHG_MASK & ~_PAGE_NX;
	189	val \|= pgprot_val(newprot) & __supported_pte_mask;
	190
	191	return __pte(val);
	192	}
	193
c6ca18eb AK	194	#define pte_pgprot(x) __pgprot(pte_val(x) & (0xfff \| _PAGE_NX))
c6ca18eb AK	195
1e8e23bc AK	196	#define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
1e8e23bc AK	197
4891645e JF	198	#ifdef CONFIG_PARAVIRT
	199	#include <asm/paravirt.h>
	200	#else /* !CONFIG_PARAVIRT */
	201	#define set_pte(ptep, pte) native_set_pte(ptep, pte)
	202	#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte)
	203
	204	#define set_pte_present(mm, addr, ptep, pte) \
	205	native_set_pte_present(mm, addr, ptep, pte)
	206	#define set_pte_atomic(ptep, pte) \
	207	native_set_pte_atomic(ptep, pte)
	208
	209	#define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd)
	210
	211	#ifndef __PAGETABLE_PUD_FOLDED
	212	#define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd)
	213	#define pgd_clear(pgd) native_pgd_clear(pgd)
	214	#endif
	215
	216	#ifndef set_pud
	217	# define set_pud(pudp, pud) native_set_pud(pudp, pud)
	218	#endif
	219
	220	#ifndef __PAGETABLE_PMD_FOLDED
	221	#define pud_clear(pud) native_pud_clear(pud)
	222	#endif
	223
	224	#define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep)
	225	#define pmd_clear(pmd) native_pmd_clear(pmd)
	226
	227	#define pte_update(mm, addr, ptep) do { } while (0)
	228	#define pte_update_defer(mm, addr, ptep) do { } while (0)
	229	#endif /* CONFIG_PARAVIRT */
	230
4614139c JF	231	#endif /* __ASSEMBLY__ */
4614139c JF	232
96a388de TG	233	#ifdef CONFIG_X86_32
	234	# include "pgtable_32.h"
	235	#else
	236	# include "pgtable_64.h"
	237	#endif
6c386655	238
195466dc JF	239	#ifndef __ASSEMBLY__
195466dc JF	240
30551bb3 TG	241	enum {
	242	PG_LEVEL_NONE,
	243	PG_LEVEL_4K,
	244	PG_LEVEL_2M,
86f03989	245	PG_LEVEL_1G,
30551bb3 TG	246	};
30551bb3 TG	247
0a663088 TG	248	/*
	249	* Helper function that returns the kernel pagetable entry controlling
	250	* the virtual address 'address'. NULL means no pagetable entry present.
	251	* NOTE: the return type is pte_t but if the pmd is PSE then we return it
	252	* as a pte too.
	253	*/
	254	extern pte_t lookup_address(unsigned long address, int level);
	255
4891645e JF	256	/* local pte updates need not use xchg for locking */
	257	static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
	258	{
	259	pte_t res = *ptep;
	260
	261	/* Pure native function needs no input for mm, addr */
	262	native_pte_clear(NULL, 0, ptep);
	263	return res;
	264	}
	265
	266	static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
	267	pte_t *ptep , pte_t pte)
	268	{
	269	native_set_pte(ptep, pte);
	270	}
	271
195466dc JF	272	#ifndef CONFIG_PARAVIRT
	273	/*
	274	* Rules for using pte_update - it must be called after any PTE update which
	275	* has not been done using the set_pte / clear_pte interfaces. It is used by
	276	* shadow mode hypervisors to resynchronize the shadow page tables. Kernel PTE
	277	* updates should either be sets, clears, or set_pte_atomic for P->P
	278	* transitions, which means this hook should only be called for user PTEs.
	279	* This hook implies a P->P protection or access change has taken place, which
	280	* requires a subsequent TLB flush. The notification can optionally be delayed
	281	* until the TLB flush event by using the pte_update_defer form of the
	282	* interface, but care must be taken to assure that the flush happens while
	283	* still holding the same page table lock so that the shadow and primary pages
	284	* do not become out of sync on SMP.
	285	*/
	286	#define pte_update(mm, addr, ptep) do { } while (0)
	287	#define pte_update_defer(mm, addr, ptep) do { } while (0)
	288	#endif
	289
195466dc JF	290	/*
	291	* We only update the dirty/accessed state if we set
	292	* the dirty bit by hand in the kernel, since the hardware
	293	* will do the accessed bit for us, and we don't want to
	294	* race with other CPU's that might be updating the dirty
	295	* bit at the same time.
	296	*/
	297	#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
	298	#define ptep_set_access_flags(vma, address, ptep, entry, dirty) \
	299	({ \
	300	int __changed = !pte_same(*(ptep), entry); \
	301	if (__changed && dirty) { \
	302	*ptep = entry; \
	303	pte_update_defer((vma)->vm_mm, (address), (ptep)); \
	304	flush_tlb_page(vma, address); \
	305	} \
	306	__changed; \
	307	})
	308
	309	#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
	310	#define ptep_test_and_clear_young(vma, addr, ptep) ({ \
	311	int __ret = 0; \
	312	if (pte_young(*(ptep))) \
	313	__ret = test_and_clear_bit(_PAGE_BIT_ACCESSED, \
	314	&(ptep)->pte); \
	315	if (__ret) \
	316	pte_update((vma)->vm_mm, addr, ptep); \
	317	__ret; \
	318	})
	319
	320	#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
	321	#define ptep_clear_flush_young(vma, address, ptep) \
	322	({ \
	323	int __young; \
	324	__young = ptep_test_and_clear_young((vma), (address), (ptep)); \
	325	if (__young) \
	326	flush_tlb_page(vma, address); \
	327	__young; \
	328	})
	329
	330	#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
	331	static inline pte_t ptep_get_and_clear(struct mm_struct mm, unsigned long addr, pte_t ptep)
	332	{
	333	pte_t pte = native_ptep_get_and_clear(ptep);
	334	pte_update(mm, addr, ptep);
	335	return pte;
	336	}
	337
	338	#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
	339	static inline pte_t ptep_get_and_clear_full(struct mm_struct mm, unsigned long addr, pte_t ptep, int full)
	340	{
	341	pte_t pte;
	342	if (full) {
	343	/*
	344	* Full address destruction in progress; paravirt does not
	345	* care about updates and native needs no locking
	346	*/
	347	pte = native_local_ptep_get_and_clear(ptep);
	348	} else {
	349	pte = ptep_get_and_clear(mm, addr, ptep);
	350	}
	351	return pte;
	352	}
	353
354	#define __HAVE_ARCH_PTEP_SET_WRPROTECT
355	static inline void ptep_set_wrprotect(struct mm_struct mm, unsigned long addr, pte_t ptep)
356	{
d8d89827	357	clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
195466dc JF	358	pte_update(mm, addr, ptep);
	359	}
	360
195466dc JF	361	#include <asm-generic/pgtable.h>
	362	#endif /* __ASSEMBLY__ */
	363
6c386655	364	#endif /* _ASM_X86_PGTABLE_H */