[mirror_ubuntu-focal-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 */

/*
 * 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)

/* 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_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 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) & ~(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);
}

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_val(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

#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,
};

/*
 * 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
f2919232 JF	23	/*
	24	* Note: we use _AC(1, L) instead of _AC(1, UL) so that we get a
	25	* sign-extended value on 32-bit with all 1's in the upper word,
	26	* which preserves the upper pte values on 64-bit ptes:
	27	*/
61f38226 IM	28	#define _PAGE_PRESENT (_AC(1, L)<<_PAGE_BIT_PRESENT)
	29	#define _PAGE_RW (_AC(1, L)<<_PAGE_BIT_RW)
	30	#define _PAGE_USER (_AC(1, L)<<_PAGE_BIT_USER)
	31	#define _PAGE_PWT (_AC(1, L)<<_PAGE_BIT_PWT)
	32	#define _PAGE_PCD (_AC(1, L)<<_PAGE_BIT_PCD)
	33	#define _PAGE_ACCESSED (_AC(1, L)<<_PAGE_BIT_ACCESSED)
	34	#define _PAGE_DIRTY (_AC(1, L)<<_PAGE_BIT_DIRTY)
	35	#define _PAGE_PSE (_AC(1, L)<<_PAGE_BIT_PSE) /* 2MB page */
	36	#define _PAGE_GLOBAL (_AC(1, L)<<_PAGE_BIT_GLOBAL) /* Global TLB entry */
	37	#define _PAGE_UNUSED1 (_AC(1, L)<<_PAGE_BIT_UNUSED1)
	38	#define _PAGE_UNUSED2 (_AC(1, L)<<_PAGE_BIT_UNUSED2)
	39	#define _PAGE_UNUSED3 (_AC(1, L)<<_PAGE_BIT_UNUSED3)
9bf5a475 AK	40	#define _PAGE_PAT (_AC(1, L)<<_PAGE_BIT_PAT)
9bf5a475 AK	41	#define _PAGE_PAT_LARGE (_AC(1, L)<<_PAGE_BIT_PAT_LARGE)
6c386655 JF	42
	43	#if defined(CONFIG_X86_64) \|\| defined(CONFIG_X86_PAE)
	44	#define _PAGE_NX (_AC(1, ULL) << _PAGE_BIT_NX)
	45	#else
	46	#define _PAGE_NX 0
	47	#endif
	48
	49	/* If _PAGE_PRESENT is clear, we use these: */
3cbaeafe JP	50	#define _PAGE_FILE _PAGE_DIRTY /* nonlinear file mapping,
3cbaeafe JP	51	* saved PTE; unset:swap */
6c386655 JF	52	#define _PAGE_PROTNONE _PAGE_PSE /* if the user mapped it with PROT_NONE;
	53	pte_present gives true */
	54
3cbaeafe JP	55	#define _PAGE_TABLE (_PAGE_PRESENT \| _PAGE_RW \| _PAGE_USER \| \
	56	_PAGE_ACCESSED \| _PAGE_DIRTY)
	57	#define _KERNPG_TABLE (_PAGE_PRESENT \| _PAGE_RW \| _PAGE_ACCESSED \| \
	58	_PAGE_DIRTY)
6c386655	59
86aaf4fd	60	/* Set of bits not changed in pte_modify */
1c12c4cf VP	61	#define _PAGE_CHG_MASK (PTE_MASK \| _PAGE_PCD \| _PAGE_PWT \| \
1c12c4cf VP	62	_PAGE_ACCESSED \| _PAGE_DIRTY)
6c386655	63
2e5d9c85	64	#define _PAGE_CACHE_MASK (_PAGE_PCD \| _PAGE_PWT)
	65	#define _PAGE_CACHE_WB (0)
	66	#define _PAGE_CACHE_WC (_PAGE_PWT)
	67	#define _PAGE_CACHE_UC_MINUS (_PAGE_PCD)
	68	#define _PAGE_CACHE_UC (_PAGE_PCD \| _PAGE_PWT)
	69
6c386655	70	#define PAGE_NONE __pgprot(_PAGE_PROTNONE \| _PAGE_ACCESSED)
3cbaeafe JP	71	#define PAGE_SHARED __pgprot(_PAGE_PRESENT \| _PAGE_RW \| _PAGE_USER \| \
	72	_PAGE_ACCESSED \| _PAGE_NX)
	73
	74	#define PAGE_SHARED_EXEC __pgprot(_PAGE_PRESENT \| _PAGE_RW \| \
	75	_PAGE_USER \| _PAGE_ACCESSED)
	76	#define PAGE_COPY_NOEXEC __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	77	_PAGE_ACCESSED \| _PAGE_NX)
	78	#define PAGE_COPY_EXEC __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	79	_PAGE_ACCESSED)
6c386655	80	#define PAGE_COPY PAGE_COPY_NOEXEC
3cbaeafe JP	81	#define PAGE_READONLY __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	82	_PAGE_ACCESSED \| _PAGE_NX)
	83	#define PAGE_READONLY_EXEC __pgprot(_PAGE_PRESENT \| _PAGE_USER \| \
	84	_PAGE_ACCESSED)
6c386655 JF	85
	86	#ifdef CONFIG_X86_32
	87	#define _PAGE_KERNEL_EXEC \
	88	(_PAGE_PRESENT \| _PAGE_RW \| _PAGE_DIRTY \| _PAGE_ACCESSED)
	89	#define _PAGE_KERNEL (_PAGE_KERNEL_EXEC \| _PAGE_NX)
	90
	91	#ifndef __ASSEMBLY__
c93c82bb	92	extern pteval_t __PAGE_KERNEL, __PAGE_KERNEL_EXEC;
6c386655 JF	93	#endif /* __ASSEMBLY__ */
	94	#else
	95	#define __PAGE_KERNEL_EXEC \
	96	(_PAGE_PRESENT \| _PAGE_RW \| _PAGE_DIRTY \| _PAGE_ACCESSED)
	97	#define __PAGE_KERNEL (__PAGE_KERNEL_EXEC \| _PAGE_NX)
	98	#endif
	99
	100	#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW)
	101	#define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW)
d2e626f4	102	#define __PAGE_KERNEL_EXEC_NOCACHE (__PAGE_KERNEL_EXEC \| _PAGE_PCD \| _PAGE_PWT)
b310f381	103	#define __PAGE_KERNEL_WC (__PAGE_KERNEL \| _PAGE_CACHE_WC)
6c386655	104	#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL \| _PAGE_PCD \| _PAGE_PWT)
d546b67a	105	#define __PAGE_KERNEL_UC_MINUS (__PAGE_KERNEL \| _PAGE_PCD)
6c386655 JF	106	#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX \| _PAGE_USER)
	107	#define __PAGE_KERNEL_VSYSCALL_NOCACHE (__PAGE_KERNEL_VSYSCALL \| _PAGE_PCD \| _PAGE_PWT)
	108	#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL \| _PAGE_PSE)
	109	#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC \| _PAGE_PSE)
	110
	111	#ifdef CONFIG_X86_32
	112	# define MAKE_GLOBAL(x) __pgprot((x))
	113	#else
	114	# define MAKE_GLOBAL(x) __pgprot((x) \| _PAGE_GLOBAL)
	115	#endif
	116
	117	#define PAGE_KERNEL MAKE_GLOBAL(__PAGE_KERNEL)
	118	#define PAGE_KERNEL_RO MAKE_GLOBAL(__PAGE_KERNEL_RO)
	119	#define PAGE_KERNEL_EXEC MAKE_GLOBAL(__PAGE_KERNEL_EXEC)
	120	#define PAGE_KERNEL_RX MAKE_GLOBAL(__PAGE_KERNEL_RX)
b310f381	121	#define PAGE_KERNEL_WC MAKE_GLOBAL(__PAGE_KERNEL_WC)
6c386655	122	#define PAGE_KERNEL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_NOCACHE)
d546b67a	123	#define PAGE_KERNEL_UC_MINUS MAKE_GLOBAL(__PAGE_KERNEL_UC_MINUS)
d2e626f4	124	#define PAGE_KERNEL_EXEC_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_EXEC_NOCACHE)
6c386655 JF	125	#define PAGE_KERNEL_LARGE MAKE_GLOBAL(__PAGE_KERNEL_LARGE)
	126	#define PAGE_KERNEL_LARGE_EXEC MAKE_GLOBAL(__PAGE_KERNEL_LARGE_EXEC)
	127	#define PAGE_KERNEL_VSYSCALL MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL)
	128	#define PAGE_KERNEL_VSYSCALL_NOCACHE MAKE_GLOBAL(__PAGE_KERNEL_VSYSCALL_NOCACHE)
	129
	130	/* xwr */
	131	#define __P000 PAGE_NONE
	132	#define __P001 PAGE_READONLY
	133	#define __P010 PAGE_COPY
	134	#define __P011 PAGE_COPY
	135	#define __P100 PAGE_READONLY_EXEC
	136	#define __P101 PAGE_READONLY_EXEC
	137	#define __P110 PAGE_COPY_EXEC
	138	#define __P111 PAGE_COPY_EXEC
	139
	140	#define __S000 PAGE_NONE
	141	#define __S001 PAGE_READONLY
	142	#define __S010 PAGE_SHARED
	143	#define __S011 PAGE_SHARED
	144	#define __S100 PAGE_READONLY_EXEC
	145	#define __S101 PAGE_READONLY_EXEC
	146	#define __S110 PAGE_SHARED_EXEC
	147	#define __S111 PAGE_SHARED_EXEC
	148
4614139c	149	#ifndef __ASSEMBLY__
195466dc	150
8405b122 JF	151	/*
	152	* ZERO_PAGE is a global shared page that is always zero: used
	153	* for zero-mapped memory areas etc..
	154	*/
3cbaeafe	155	extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
8405b122 JF	156	#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
8405b122 JF	157
e3ed910d JF	158	extern spinlock_t pgd_lock;
e3ed910d JF	159	extern struct list_head pgd_list;
8405b122	160
4614139c JF	161	/*
	162	* The following only work if pte_present() is true.
	163	* Undefined behaviour if not..
	164	*/
3cbaeafe JP	165	static inline int pte_dirty(pte_t pte)
	166	{
	167	return pte_val(pte) & _PAGE_DIRTY;
	168	}
	169
	170	static inline int pte_young(pte_t pte)
	171	{
	172	return pte_val(pte) & _PAGE_ACCESSED;
	173	}
	174
	175	static inline int pte_write(pte_t pte)
	176	{
	177	return pte_val(pte) & _PAGE_RW;
	178	}
	179
	180	static inline int pte_file(pte_t pte)
	181	{
	182	return pte_val(pte) & _PAGE_FILE;
	183	}
	184
	185	static inline int pte_huge(pte_t pte)
	186	{
	187	return pte_val(pte) & _PAGE_PSE;
4614139c JF	188	}
4614139c JF	189
3cbaeafe JP	190	static inline int pte_global(pte_t pte)
	191	{
	192	return pte_val(pte) & _PAGE_GLOBAL;
	193	}
	194
	195	static inline int pte_exec(pte_t pte)
	196	{
	197	return !(pte_val(pte) & _PAGE_NX);
	198	}
	199
7e675137 NP	200	static inline int pte_special(pte_t pte)
	201	{
	202	return 0;
	203	}
	204
3cbaeafe JP	205	static inline int pmd_large(pmd_t pte)
	206	{
	207	return (pmd_val(pte) & (_PAGE_PSE \| _PAGE_PRESENT)) ==
	208	(_PAGE_PSE \| _PAGE_PRESENT);
	209	}
	210
	211	static inline pte_t pte_mkclean(pte_t pte)
	212	{
	213	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_DIRTY);
	214	}
	215
	216	static inline pte_t pte_mkold(pte_t pte)
	217	{
	218	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_ACCESSED);
	219	}
	220
	221	static inline pte_t pte_wrprotect(pte_t pte)
	222	{
	223	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_RW);
	224	}
	225
	226	static inline pte_t pte_mkexec(pte_t pte)
	227	{
	228	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_NX);
	229	}
	230
	231	static inline pte_t pte_mkdirty(pte_t pte)
	232	{
	233	return __pte(pte_val(pte) \| _PAGE_DIRTY);
	234	}
	235
	236	static inline pte_t pte_mkyoung(pte_t pte)
	237	{
	238	return __pte(pte_val(pte) \| _PAGE_ACCESSED);
	239	}
	240
	241	static inline pte_t pte_mkwrite(pte_t pte)
	242	{
	243	return __pte(pte_val(pte) \| _PAGE_RW);
	244	}
	245
	246	static inline pte_t pte_mkhuge(pte_t pte)
	247	{
	248	return __pte(pte_val(pte) \| _PAGE_PSE);
	249	}
	250
	251	static inline pte_t pte_clrhuge(pte_t pte)
	252	{
	253	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_PSE);
	254	}
	255
	256	static inline pte_t pte_mkglobal(pte_t pte)
	257	{
	258	return __pte(pte_val(pte) \| _PAGE_GLOBAL);
	259	}
	260
	261	static inline pte_t pte_clrglobal(pte_t pte)
	262	{
	263	return __pte(pte_val(pte) & ~(pteval_t)_PAGE_GLOBAL);
	264	}
4614139c	265
7e675137 NP	266	static inline pte_t pte_mkspecial(pte_t pte)
	267	{
	268	return pte;
	269	}
	270
6fdc05d4 JF	271	extern pteval_t __supported_pte_mask;
	272
	273	static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
	274	{
	275	return __pte((((phys_addr_t)page_nr << PAGE_SHIFT) \|
	276	pgprot_val(pgprot)) & __supported_pte_mask);
	277	}
	278
	279	static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
	280	{
	281	return __pmd((((phys_addr_t)page_nr << PAGE_SHIFT) \|
	282	pgprot_val(pgprot)) & __supported_pte_mask);
	283	}
	284
38472311 IM	285	static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
	286	{
	287	pteval_t val = pte_val(pte);
	288
	289	/*
	290	* Chop off the NX bit (if present), and add the NX portion of
	291	* the newprot (if present):
	292	*/
1c12c4cf VP	293	val &= _PAGE_CHG_MASK;
1c12c4cf VP	294	val \|= pgprot_val(newprot) & (~_PAGE_CHG_MASK) & __supported_pte_mask;
38472311 IM	295
	296	return __pte(val);
	297	}
	298
1c12c4cf VP	299	/* mprotect needs to preserve PAT bits when updating vm_page_prot */
	300	#define pgprot_modify pgprot_modify
	301	static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
	302	{
	303	pgprotval_t preservebits = pgprot_val(oldprot) & _PAGE_CHG_MASK;
	304	pgprotval_t addbits = pgprot_val(newprot);
	305	return __pgprot(preservebits \| addbits);
	306	}
	307
ba23cef5	308	#define pte_pgprot(x) __pgprot(pte_val(x) & ~PTE_MASK)
c6ca18eb	309
1e8e23bc AK	310	#define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
1e8e23bc AK	311
f0970c13	312	#ifndef __ASSEMBLY__
	313	#define __HAVE_PHYS_MEM_ACCESS_PROT
	314	struct file;
	315	pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
	316	unsigned long size, pgprot_t vma_prot);
	317	int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
	318	unsigned long size, pgprot_t *vma_prot);
	319	#endif
	320
4891645e JF	321	#ifdef CONFIG_PARAVIRT
	322	#include <asm/paravirt.h>
	323	#else /* !CONFIG_PARAVIRT */
	324	#define set_pte(ptep, pte) native_set_pte(ptep, pte)
	325	#define set_pte_at(mm, addr, ptep, pte) native_set_pte_at(mm, addr, ptep, pte)
	326
	327	#define set_pte_present(mm, addr, ptep, pte) \
	328	native_set_pte_present(mm, addr, ptep, pte)
	329	#define set_pte_atomic(ptep, pte) \
	330	native_set_pte_atomic(ptep, pte)
	331
	332	#define set_pmd(pmdp, pmd) native_set_pmd(pmdp, pmd)
	333
	334	#ifndef __PAGETABLE_PUD_FOLDED
	335	#define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd)
	336	#define pgd_clear(pgd) native_pgd_clear(pgd)
	337	#endif
	338
	339	#ifndef set_pud
	340	# define set_pud(pudp, pud) native_set_pud(pudp, pud)
	341	#endif
	342
	343	#ifndef __PAGETABLE_PMD_FOLDED
	344	#define pud_clear(pud) native_pud_clear(pud)
	345	#endif
	346
	347	#define pte_clear(mm, addr, ptep) native_pte_clear(mm, addr, ptep)
	348	#define pmd_clear(pmd) native_pmd_clear(pmd)
	349
	350	#define pte_update(mm, addr, ptep) do { } while (0)
	351	#define pte_update_defer(mm, addr, ptep) do { } while (0)
	352	#endif /* CONFIG_PARAVIRT */
	353
4614139c JF	354	#endif /* __ASSEMBLY__ */
4614139c JF	355
96a388de TG	356	#ifdef CONFIG_X86_32
	357	# include "pgtable_32.h"
	358	#else
	359	# include "pgtable_64.h"
	360	#endif
6c386655	361
68db065c JF	362	#define KERNEL_PGD_BOUNDARY pgd_index(PAGE_OFFSET)
	363	#define KERNEL_PGD_PTRS (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)
	364
195466dc JF	365	#ifndef __ASSEMBLY__
195466dc JF	366
30551bb3 TG	367	enum {
	368	PG_LEVEL_NONE,
	369	PG_LEVEL_4K,
	370	PG_LEVEL_2M,
86f03989	371	PG_LEVEL_1G,
30551bb3 TG	372	};
30551bb3 TG	373
0a663088 TG	374	/*
	375	* Helper function that returns the kernel pagetable entry controlling
	376	* the virtual address 'address'. NULL means no pagetable entry present.
	377	* NOTE: the return type is pte_t but if the pmd is PSE then we return it
	378	* as a pte too.
	379	*/
da7bfc50	380	extern pte_t lookup_address(unsigned long address, unsigned int level);
0a663088	381
4891645e JF	382	/* local pte updates need not use xchg for locking */
	383	static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
	384	{
	385	pte_t res = *ptep;
	386
	387	/* Pure native function needs no input for mm, addr */
	388	native_pte_clear(NULL, 0, ptep);
	389	return res;
	390	}
	391
	392	static inline void native_set_pte_at(struct mm_struct *mm, unsigned long addr,
	393	pte_t *ptep , pte_t pte)
	394	{
	395	native_set_pte(ptep, pte);
	396	}
	397
195466dc JF	398	#ifndef CONFIG_PARAVIRT
	399	/*
	400	* Rules for using pte_update - it must be called after any PTE update which
	401	* has not been done using the set_pte / clear_pte interfaces. It is used by
	402	* shadow mode hypervisors to resynchronize the shadow page tables. Kernel PTE
	403	* updates should either be sets, clears, or set_pte_atomic for P->P
	404	* transitions, which means this hook should only be called for user PTEs.
	405	* This hook implies a P->P protection or access change has taken place, which
	406	* requires a subsequent TLB flush. The notification can optionally be delayed
	407	* until the TLB flush event by using the pte_update_defer form of the
	408	* interface, but care must be taken to assure that the flush happens while
	409	* still holding the same page table lock so that the shadow and primary pages
	410	* do not become out of sync on SMP.
	411	*/
	412	#define pte_update(mm, addr, ptep) do { } while (0)
	413	#define pte_update_defer(mm, addr, ptep) do { } while (0)
	414	#endif
	415
195466dc JF	416	/*
	417	* We only update the dirty/accessed state if we set
	418	* the dirty bit by hand in the kernel, since the hardware
	419	* will do the accessed bit for us, and we don't want to
	420	* race with other CPU's that might be updating the dirty
	421	* bit at the same time.
	422	*/
	423	#define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
ee5aa8d3 JF	424	extern int ptep_set_access_flags(struct vm_area_struct *vma,
	425	unsigned long address, pte_t *ptep,
	426	pte_t entry, int dirty);
195466dc JF	427
195466dc JF	428	#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
f9fbf1a3 JF	429	extern int ptep_test_and_clear_young(struct vm_area_struct *vma,
f9fbf1a3 JF	430	unsigned long addr, pte_t *ptep);
195466dc JF	431
195466dc JF	432	#define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
c20311e1 JF	433	extern int ptep_clear_flush_young(struct vm_area_struct *vma,
c20311e1 JF	434	unsigned long address, pte_t *ptep);
195466dc JF	435
195466dc JF	436	#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
3cbaeafe JP	437	static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
3cbaeafe JP	438	pte_t *ptep)
195466dc JF	439	{
	440	pte_t pte = native_ptep_get_and_clear(ptep);
	441	pte_update(mm, addr, ptep);
	442	return pte;
	443	}
	444
	445	#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
3cbaeafe JP	446	static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
	447	unsigned long addr, pte_t *ptep,
	448	int full)
195466dc JF	449	{
	450	pte_t pte;
	451	if (full) {
	452	/*
	453	* Full address destruction in progress; paravirt does not
	454	* care about updates and native needs no locking
	455	*/
	456	pte = native_local_ptep_get_and_clear(ptep);
	457	} else {
	458	pte = ptep_get_and_clear(mm, addr, ptep);
	459	}
	460	return pte;
	461	}
	462
	463	#define __HAVE_ARCH_PTEP_SET_WRPROTECT
3cbaeafe JP	464	static inline void ptep_set_wrprotect(struct mm_struct *mm,
3cbaeafe JP	465	unsigned long addr, pte_t *ptep)
195466dc	466	{
d8d89827	467	clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
195466dc JF	468	pte_update(mm, addr, ptep);
	469	}
	470
85958b46 JF	471	/*
	472	* clone_pgd_range(pgd_t dst, pgd_t src, int count);
	473	*
	474	* dst - pointer to pgd range anwhere on a pgd page
	475	* src - ""
	476	* count - the number of pgds to copy.
	477	*
	478	* dst and src can be on the same page, but the range must not overlap,
	479	* and must not cross a page boundary.
	480	*/
	481	static inline void clone_pgd_range(pgd_t dst, pgd_t src, int count)
	482	{
	483	memcpy(dst, src, count * sizeof(pgd_t));
	484	}
	485
	486
195466dc JF	487	#include <asm-generic/pgtable.h>
	488	#endif /* __ASSEMBLY__ */
	489
6c386655	490	#endif /* _ASM_X86_PGTABLE_H */