linux/arch/x86/include/asm/pgtable_types.h

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _ASM_X86_PGTABLE_DEFS_H
#define _ASM_X86_PGTABLE_DEFS_H

#include <linux/const.h>
#include <linux/mem_encrypt.h>

#include <asm/page_types.h>

#define _PAGE_BIT_PRESENT
#define _PAGE_BIT_RW
#define _PAGE_BIT_USER
#define _PAGE_BIT_PWT
#define _PAGE_BIT_PCD
#define _PAGE_BIT_ACCESSED
#define _PAGE_BIT_DIRTY
#define _PAGE_BIT_PSE
#define _PAGE_BIT_PAT
#define _PAGE_BIT_GLOBAL
#define _PAGE_BIT_SOFTW1
#define _PAGE_BIT_SOFTW2
#define _PAGE_BIT_SOFTW3
#define _PAGE_BIT_PAT_LARGE
#define _PAGE_BIT_SOFTW4
#define _PAGE_BIT_SOFTW5
#define _PAGE_BIT_PKEY_BIT0
#define _PAGE_BIT_PKEY_BIT1
#define _PAGE_BIT_PKEY_BIT2
#define _PAGE_BIT_PKEY_BIT3
#define _PAGE_BIT_NX

#define _PAGE_BIT_SPECIAL
#define _PAGE_BIT_CPA_TEST
#define _PAGE_BIT_UFFD_WP
#define _PAGE_BIT_SOFT_DIRTY
#define _PAGE_BIT_DEVMAP

#ifdef CONFIG_X86_64
#define _PAGE_BIT_SAVED_DIRTY
#else
/* Shared with _PAGE_BIT_UFFD_WP which is not supported on 32 bit */
#define _PAGE_BIT_SAVED_DIRTY
#endif

/* If _PAGE_BIT_PRESENT is clear, we use these: */
/* - if the user mapped it with PROT_NONE; pte_present gives true */
#define _PAGE_BIT_PROTNONE

#define _PAGE_PRESENT
#define _PAGE_RW
#define _PAGE_USER
#define _PAGE_PWT
#define _PAGE_PCD
#define _PAGE_ACCESSED
#define _PAGE_DIRTY
#define _PAGE_PSE
#define _PAGE_GLOBAL
#define _PAGE_SOFTW1
#define _PAGE_SOFTW2
#define _PAGE_SOFTW3
#define _PAGE_PAT
#define _PAGE_PAT_LARGE
#define _PAGE_SPECIAL
#define _PAGE_CPA_TEST
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
#define _PAGE_PKEY_BIT0
#define _PAGE_PKEY_BIT1
#define _PAGE_PKEY_BIT2
#define _PAGE_PKEY_BIT3
#else
#define _PAGE_PKEY_BIT0
#define _PAGE_PKEY_BIT1
#define _PAGE_PKEY_BIT2
#define _PAGE_PKEY_BIT3
#endif

#define _PAGE_PKEY_MASK

#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
#define _PAGE_KNL_ERRATUM_MASK
#else
#define _PAGE_KNL_ERRATUM_MASK
#endif

#ifdef CONFIG_MEM_SOFT_DIRTY
#define _PAGE_SOFT_DIRTY
#else
#define _PAGE_SOFT_DIRTY
#endif

/*
 * Tracking soft dirty bit when a page goes to a swap is tricky.
 * We need a bit which can be stored in pte _and_ not conflict
 * with swap entry format. On x86 bits 1-4 are *not* involved
 * into swap entry computation, but bit 7 is used for thp migration,
 * so we borrow bit 1 for soft dirty tracking.
 *
 * Please note that this bit must be treated as swap dirty page
 * mark if and only if the PTE/PMD has present bit clear!
 */
#ifdef CONFIG_MEM_SOFT_DIRTY
#define _PAGE_SWP_SOFT_DIRTY
#else
#define _PAGE_SWP_SOFT_DIRTY
#endif

#ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
#define _PAGE_UFFD_WP
#define _PAGE_SWP_UFFD_WP
#else
#define _PAGE_UFFD_WP
#define _PAGE_SWP_UFFD_WP
#endif

#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
#define _PAGE_NX
#define _PAGE_DEVMAP
#define _PAGE_SOFTW4
#else
#define _PAGE_NX
#define _PAGE_DEVMAP
#define _PAGE_SOFTW4
#endif

/*
 * The hardware requires shadow stack to be Write=0,Dirty=1. However,
 * there are valid cases where the kernel might create read-only PTEs that
 * are dirty (e.g., fork(), mprotect(), uffd-wp(), soft-dirty tracking). In
 * this case, the _PAGE_SAVED_DIRTY bit is used instead of the HW-dirty bit,
 * to avoid creating a wrong "shadow stack" PTEs. Such PTEs have
 * (Write=0,SavedDirty=1,Dirty=0) set.
 */
#define _PAGE_SAVED_DIRTY

#define _PAGE_DIRTY_BITS

#define _PAGE_PROTNONE

/*
 * Set of bits not changed in pte_modify.  The pte's
 * protection key is treated like _PAGE_RW, for
 * instance, and is *not* included in this mask since
 * pte_modify() does modify it.
 */
#define _COMMON_PAGE_CHG_MASK
#define _PAGE_CHG_MASK
#define _HPAGE_CHG_MASK

/*
 * The cache modes defined here are used to translate between pure SW usage
 * and the HW defined cache mode bits and/or PAT entries.
 *
 * The resulting bits for PWT, PCD and PAT should be chosen in a way
 * to have the WB mode at index 0 (all bits clear). This is the default
 * right now and likely would break too much if changed.
 */
#ifndef __ASSEMBLY__
enum page_cache_mode {
	_PAGE_CACHE_MODE_WB       = 0,
	_PAGE_CACHE_MODE_WC       = 1,
	_PAGE_CACHE_MODE_UC_MINUS = 2,
	_PAGE_CACHE_MODE_UC       = 3,
	_PAGE_CACHE_MODE_WT       = 4,
	_PAGE_CACHE_MODE_WP       = 5,

	_PAGE_CACHE_MODE_NUM      = 8
};
#endif

#define _PAGE_CC
#define _PAGE_ENC

#define _PAGE_CACHE_MASK
#define _PAGE_LARGE_CACHE_MASK

#define _PAGE_NOCACHE
#define _PAGE_CACHE_WP

#define __PP
#define __RW
#define _USR
#define ___A
#define ___D
#define ___G
#define __NX

#define _ENC
#define __WP
#define __NC
#define _PSE

#define pgprot_val(x)
#define __pgprot(x)
#define __pg(x)

#define PAGE_NONE
#define PAGE_SHARED
#define PAGE_SHARED_EXEC
#define PAGE_COPY_NOEXEC
#define PAGE_COPY_EXEC
#define PAGE_COPY
#define PAGE_READONLY
#define PAGE_READONLY_EXEC

#define __PAGE_KERNEL
#define __PAGE_KERNEL_EXEC

/*
 * Page tables needs to have Write=1 in order for any lower PTEs to be
 * writable. This includes shadow stack memory (Write=0, Dirty=1)
 */
#define _KERNPG_TABLE_NOENC
#define _KERNPG_TABLE
#define _PAGE_TABLE_NOENC
#define _PAGE_TABLE

#define __PAGE_KERNEL_RO
#define __PAGE_KERNEL_ROX
#define __PAGE_KERNEL
#define __PAGE_KERNEL_EXEC
#define __PAGE_KERNEL_NOCACHE
#define __PAGE_KERNEL_VVAR
#define __PAGE_KERNEL_LARGE
#define __PAGE_KERNEL_LARGE_EXEC
#define __PAGE_KERNEL_WP


#define __PAGE_KERNEL_IO
#define __PAGE_KERNEL_IO_NOCACHE


#ifndef __ASSEMBLY__

#define __PAGE_KERNEL_ENC
#define __PAGE_KERNEL_ENC_WP
#define __PAGE_KERNEL_NOENC
#define __PAGE_KERNEL_NOENC_WP

#define __pgprot_mask

#define PAGE_KERNEL
#define PAGE_KERNEL_NOENC
#define PAGE_KERNEL_RO
#define PAGE_KERNEL_EXEC
#define PAGE_KERNEL_EXEC_NOENC
#define PAGE_KERNEL_ROX
#define PAGE_KERNEL_NOCACHE
#define PAGE_KERNEL_LARGE
#define PAGE_KERNEL_LARGE_EXEC
#define PAGE_KERNEL_VVAR

#define PAGE_KERNEL_IO
#define PAGE_KERNEL_IO_NOCACHE

#endif	/* __ASSEMBLY__ */

/*
 * early identity mapping  pte attrib macros.
 */
#ifdef CONFIG_X86_64
#define __PAGE_KERNEL_IDENT_LARGE_EXEC
#else
#define PTE_IDENT_ATTR
#define PDE_IDENT_ATTR
#define PGD_IDENT_ATTR
#endif

#ifdef CONFIG_X86_32
# include <asm/pgtable_32_types.h>
#else
# include <asm/pgtable_64_types.h>
#endif

#ifndef __ASSEMBLY__

#include <linux/types.h>

/* Extracts the PFN from a (pte|pmd|pud|pgd)val_t of a 4KB page */
#define PTE_PFN_MASK

/*
 *  Extracts the flags from a (pte|pmd|pud|pgd)val_t
 *  This includes the protection key value.
 */
#define PTE_FLAGS_MASK

typedef struct pgprot { pgprotval_t pgprot; } pgprot_t;

typedef struct { pgdval_t pgd; } pgd_t;

static inline pgprot_t pgprot_nx(pgprot_t prot)
{
	return __pgprot(pgprot_val(prot) | _PAGE_NX);
}
#define pgprot_nx

#ifdef CONFIG_X86_PAE

/*
 * PHYSICAL_PAGE_MASK might be non-constant when SME is compiled in, so we can't
 * use it here.
 */

#define PGD_PAE_PAGE_MASK
#define PGD_PAE_PHYS_MASK

/*
 * PAE allows Base Address, P, PWT, PCD and AVL bits to be set in PGD entries.
 * All other bits are Reserved MBZ
 */
#define PGD_ALLOWED_BITS

#else
/* No need to mask any bits for !PAE */
#define PGD_ALLOWED_BITS
#endif

static inline pgd_t native_make_pgd(pgdval_t val)
{
	return (pgd_t) { val & PGD_ALLOWED_BITS };
}

static inline pgdval_t native_pgd_val(pgd_t pgd)
{
	return pgd.pgd & PGD_ALLOWED_BITS;
}

static inline pgdval_t pgd_flags(pgd_t pgd)
{
	return native_pgd_val(pgd) & PTE_FLAGS_MASK;
}

#if CONFIG_PGTABLE_LEVELS > 4
typedef struct { p4dval_t p4d; } p4d_t;

static inline p4d_t native_make_p4d(pudval_t val)
{
	return (p4d_t) { val };
}

static inline p4dval_t native_p4d_val(p4d_t p4d)
{
	return p4d.p4d;
}
#else
#include <asm-generic/pgtable-nop4d.h>

static inline p4d_t native_make_p4d(pudval_t val)
{
	return (p4d_t) { .pgd = native_make_pgd((pgdval_t)val) };
}

static inline p4dval_t native_p4d_val(p4d_t p4d)
{
	return native_pgd_val(p4d.pgd);
}
#endif

#if CONFIG_PGTABLE_LEVELS > 3
typedef struct { pudval_t pud; } pud_t;

static inline pud_t native_make_pud(pmdval_t val)
{
	return (pud_t) { val };
}

static inline pudval_t native_pud_val(pud_t pud)
{
	return pud.pud;
}
#else
#include <asm-generic/pgtable-nopud.h>

static inline pud_t native_make_pud(pudval_t val)
{
	return (pud_t) { .p4d.pgd = native_make_pgd(val) };
}

static inline pudval_t native_pud_val(pud_t pud)
{
	return native_pgd_val(pud.p4d.pgd);
}
#endif

#if CONFIG_PGTABLE_LEVELS > 2
static inline pmd_t native_make_pmd(pmdval_t val)
{
	return (pmd_t) { .pmd = val };
}

static inline pmdval_t native_pmd_val(pmd_t pmd)
{
	return pmd.pmd;
}
#else
#include <asm-generic/pgtable-nopmd.h>

static inline pmd_t native_make_pmd(pmdval_t val)
{
	return (pmd_t) { .pud.p4d.pgd = native_make_pgd(val) };
}

static inline pmdval_t native_pmd_val(pmd_t pmd)
{
	return native_pgd_val(pmd.pud.p4d.pgd);
}
#endif

static inline p4dval_t p4d_pfn_mask(p4d_t p4d)
{
	/* No 512 GiB huge pages yet */
	return PTE_PFN_MASK;
}

static inline p4dval_t p4d_flags_mask(p4d_t p4d)
{
	return ~p4d_pfn_mask(p4d);
}

static inline p4dval_t p4d_flags(p4d_t p4d)
{
	return native_p4d_val(p4d) & p4d_flags_mask(p4d);
}

static inline pudval_t pud_pfn_mask(pud_t pud)
{
	if (native_pud_val(pud) & _PAGE_PSE)
		return PHYSICAL_PUD_PAGE_MASK;
	else
		return PTE_PFN_MASK;
}

static inline pudval_t pud_flags_mask(pud_t pud)
{
	return ~pud_pfn_mask(pud);
}

static inline pudval_t pud_flags(pud_t pud)
{
	return native_pud_val(pud) & pud_flags_mask(pud);
}

static inline pmdval_t pmd_pfn_mask(pmd_t pmd)
{
	if (native_pmd_val(pmd) & _PAGE_PSE)
		return PHYSICAL_PMD_PAGE_MASK;
	else
		return PTE_PFN_MASK;
}

static inline pmdval_t pmd_flags_mask(pmd_t pmd)
{
	return ~pmd_pfn_mask(pmd);
}

static inline pmdval_t pmd_flags(pmd_t pmd)
{
	return native_pmd_val(pmd) & pmd_flags_mask(pmd);
}

static inline pte_t native_make_pte(pteval_t val)
{
	return (pte_t) { .pte = val };
}

static inline pteval_t native_pte_val(pte_t pte)
{
	return pte.pte;
}

static inline pteval_t pte_flags(pte_t pte)
{
	return native_pte_val(pte) & PTE_FLAGS_MASK;
}

#define __pte2cm_idx
#define __cm_idx2pte

unsigned long cachemode2protval(enum page_cache_mode pcm);

static inline pgprotval_t protval_4k_2_large(pgprotval_t val)
{
	return (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
		((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
}
static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot)
{
	return __pgprot(protval_4k_2_large(pgprot_val(pgprot)));
}
static inline pgprotval_t protval_large_2_4k(pgprotval_t val)
{
	return (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) |
		((val & _PAGE_PAT_LARGE) >>
		 (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT));
}
static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot)
{
	return __pgprot(protval_large_2_4k(pgprot_val(pgprot)));
}


typedef struct page *pgtable_t;

extern pteval_t __supported_pte_mask;
extern pteval_t __default_kernel_pte_mask;

#define pgprot_writecombine
extern pgprot_t pgprot_writecombine(pgprot_t prot);

#define pgprot_writethrough
extern pgprot_t pgprot_writethrough(pgprot_t prot);

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

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

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

#ifdef CONFIG_X86_32
extern void native_pagetable_init(void);
#else
#define native_pagetable_init
#endif

enum pg_level {
	PG_LEVEL_NONE,
	PG_LEVEL_4K,
	PG_LEVEL_2M,
	PG_LEVEL_1G,
	PG_LEVEL_512G,
	PG_LEVEL_256T,
	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);
extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
				    unsigned int *level);
pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
				  unsigned int *level, bool *nx, bool *rw);
extern pmd_t *lookup_pmd_address(unsigned long address);
extern phys_addr_t slow_virt_to_phys(void *__address);
extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn,
					  unsigned long address,
					  unsigned numpages,
					  unsigned long page_flags);
extern int __init kernel_unmap_pages_in_pgd(pgd_t *pgd, unsigned long address,
					    unsigned long numpages);
#endif	/* !__ASSEMBLY__ */

#endif /* _ASM_X86_PGTABLE_DEFS_H */