0,0 → 1,463 |
#ifndef _ASM_X86_PGTABLE_DEFS_H |
#define _ASM_X86_PGTABLE_DEFS_H |
|
#include <linux/const.h> |
#include <asm/page_types.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_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_SOFTW1 9 /* available for programmer */ |
#define _PAGE_BIT_SOFTW2 10 /* " */ |
#define _PAGE_BIT_SOFTW3 11 /* " */ |
#define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */ |
#define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1 |
#define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1 |
#define _PAGE_BIT_SPLITTING _PAGE_BIT_SOFTW2 /* only valid on a PSE pmd */ |
#define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */ |
#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ |
#define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ |
|
/* |
* Swap offsets on configurations that allow automatic NUMA balancing use the |
* bits after _PAGE_BIT_GLOBAL. To uniquely distinguish NUMA hinting PTEs from |
* swap entries, we use the first bit after _PAGE_BIT_GLOBAL and shrink the |
* maximum possible swap space from 16TB to 8TB. |
*/ |
#define _PAGE_BIT_NUMA (_PAGE_BIT_GLOBAL+1) |
|
/* 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 _PAGE_BIT_GLOBAL |
/* - set: nonlinear file mapping, saved PTE; unset:swap */ |
#define _PAGE_BIT_FILE _PAGE_BIT_DIRTY |
|
#define _PAGE_PRESENT (_AT(pteval_t, 1) << _PAGE_BIT_PRESENT) |
#define _PAGE_RW (_AT(pteval_t, 1) << _PAGE_BIT_RW) |
#define _PAGE_USER (_AT(pteval_t, 1) << _PAGE_BIT_USER) |
#define _PAGE_PWT (_AT(pteval_t, 1) << _PAGE_BIT_PWT) |
#define _PAGE_PCD (_AT(pteval_t, 1) << _PAGE_BIT_PCD) |
#define _PAGE_ACCESSED (_AT(pteval_t, 1) << _PAGE_BIT_ACCESSED) |
#define _PAGE_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY) |
#define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE) |
#define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL) |
#define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1) |
#define _PAGE_SOFTW2 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2) |
#define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT) |
#define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) |
#define _PAGE_SPECIAL (_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL) |
#define _PAGE_CPA_TEST (_AT(pteval_t, 1) << _PAGE_BIT_CPA_TEST) |
#define _PAGE_SPLITTING (_AT(pteval_t, 1) << _PAGE_BIT_SPLITTING) |
#define __HAVE_ARCH_PTE_SPECIAL |
|
#ifdef CONFIG_KMEMCHECK |
#define _PAGE_HIDDEN (_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN) |
#else |
#define _PAGE_HIDDEN (_AT(pteval_t, 0)) |
#endif |
|
/* |
* The same hidden bit is used by kmemcheck, but since kmemcheck |
* works on kernel pages while soft-dirty engine on user space, |
* they do not conflict with each other. |
*/ |
|
#ifdef CONFIG_MEM_SOFT_DIRTY |
#define _PAGE_SOFT_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY) |
#else |
#define _PAGE_SOFT_DIRTY (_AT(pteval_t, 0)) |
#endif |
|
/* |
* _PAGE_NUMA distinguishes between a numa hinting minor fault and a page |
* that is not present. The hinting fault gathers numa placement statistics |
* (see pte_numa()). The bit is always zero when the PTE is not present. |
* |
* The bit picked must be always zero when the pmd is present and not |
* present, so that we don't lose information when we set it while |
* atomically clearing the present bit. |
*/ |
#ifdef CONFIG_NUMA_BALANCING |
#define _PAGE_NUMA (_AT(pteval_t, 1) << _PAGE_BIT_NUMA) |
#else |
#define _PAGE_NUMA (_AT(pteval_t, 0)) |
#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 6 and 7 are *not* involved |
* into swap entry computation, but bit 6 is used for nonlinear |
* file mapping, so we borrow bit 7 for soft dirty tracking. |
* |
* Please note that this bit must be treated as swap dirty page |
* mark if and only if the PTE has present bit clear! |
*/ |
#ifdef CONFIG_MEM_SOFT_DIRTY |
#define _PAGE_SWP_SOFT_DIRTY _PAGE_PSE |
#else |
#define _PAGE_SWP_SOFT_DIRTY (_AT(pteval_t, 0)) |
#endif |
|
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE) |
#define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX) |
#else |
#define _PAGE_NX (_AT(pteval_t, 0)) |
#endif |
|
#define _PAGE_FILE (_AT(pteval_t, 1) << _PAGE_BIT_FILE) |
#define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) |
|
#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_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ |
_PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ |
_PAGE_SOFT_DIRTY | _PAGE_NUMA) |
#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_NUMA) |
|
/* |
* 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_CACHE_MASK (_PAGE_PAT | _PAGE_PCD | _PAGE_PWT) |
#define _PAGE_NOCACHE (cachemode2protval(_PAGE_CACHE_MODE_UC)) |
|
#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) |
|
#define __PAGE_KERNEL_EXEC \ |
(_PAGE_PRESENT | _PAGE_RW | _PAGE_DIRTY | _PAGE_ACCESSED | _PAGE_GLOBAL) |
#define __PAGE_KERNEL (__PAGE_KERNEL_EXEC | _PAGE_NX) |
|
#define __PAGE_KERNEL_RO (__PAGE_KERNEL & ~_PAGE_RW) |
#define __PAGE_KERNEL_RX (__PAGE_KERNEL_EXEC & ~_PAGE_RW) |
#define __PAGE_KERNEL_NOCACHE (__PAGE_KERNEL | _PAGE_NOCACHE) |
#define __PAGE_KERNEL_VSYSCALL (__PAGE_KERNEL_RX | _PAGE_USER) |
#define __PAGE_KERNEL_VVAR (__PAGE_KERNEL_RO | _PAGE_USER) |
#define __PAGE_KERNEL_LARGE (__PAGE_KERNEL | _PAGE_PSE) |
#define __PAGE_KERNEL_LARGE_EXEC (__PAGE_KERNEL_EXEC | _PAGE_PSE) |
|
#define __PAGE_KERNEL_IO (__PAGE_KERNEL) |
#define __PAGE_KERNEL_IO_NOCACHE (__PAGE_KERNEL_NOCACHE) |
|
#define PAGE_KERNEL __pgprot(__PAGE_KERNEL) |
#define PAGE_KERNEL_RO __pgprot(__PAGE_KERNEL_RO) |
#define PAGE_KERNEL_EXEC __pgprot(__PAGE_KERNEL_EXEC) |
#define PAGE_KERNEL_RX __pgprot(__PAGE_KERNEL_RX) |
#define PAGE_KERNEL_NOCACHE __pgprot(__PAGE_KERNEL_NOCACHE) |
#define PAGE_KERNEL_LARGE __pgprot(__PAGE_KERNEL_LARGE) |
#define PAGE_KERNEL_LARGE_EXEC __pgprot(__PAGE_KERNEL_LARGE_EXEC) |
#define PAGE_KERNEL_VSYSCALL __pgprot(__PAGE_KERNEL_VSYSCALL) |
#define PAGE_KERNEL_VVAR __pgprot(__PAGE_KERNEL_VVAR) |
|
#define PAGE_KERNEL_IO __pgprot(__PAGE_KERNEL_IO) |
#define PAGE_KERNEL_IO_NOCACHE __pgprot(__PAGE_KERNEL_IO_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 |
|
/* |
* early identity mapping pte attrib macros. |
*/ |
#ifdef CONFIG_X86_64 |
#define __PAGE_KERNEL_IDENT_LARGE_EXEC __PAGE_KERNEL_LARGE_EXEC |
#else |
#define PTE_IDENT_ATTR 0x003 /* PRESENT+RW */ |
#define PDE_IDENT_ATTR 0x063 /* PRESENT+RW+DIRTY+ACCESSED */ |
#define PGD_IDENT_ATTR 0x001 /* PRESENT (no other attributes) */ |
#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> |
|
/* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */ |
#define PTE_PFN_MASK ((pteval_t)PHYSICAL_PAGE_MASK) |
|
/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */ |
#define PTE_FLAGS_MASK (~PTE_PFN_MASK) |
|
typedef struct pgprot { pgprotval_t pgprot; } pgprot_t; |
|
typedef struct { pgdval_t pgd; } pgd_t; |
|
static inline pgd_t native_make_pgd(pgdval_t val) |
{ |
return (pgd_t) { val }; |
} |
|
static inline pgdval_t native_pgd_val(pgd_t pgd) |
{ |
return pgd.pgd; |
} |
|
static inline pgdval_t pgd_flags(pgd_t pgd) |
{ |
return native_pgd_val(pgd) & PTE_FLAGS_MASK; |
} |
|
#if PAGETABLE_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 pudval_t native_pud_val(pud_t pud) |
{ |
return native_pgd_val(pud.pgd); |
} |
#endif |
|
#if PAGETABLE_LEVELS > 2 |
typedef struct { pmdval_t pmd; } pmd_t; |
|
static inline pmd_t native_make_pmd(pmdval_t val) |
{ |
return (pmd_t) { val }; |
} |
|
static inline pmdval_t native_pmd_val(pmd_t pmd) |
{ |
return pmd.pmd; |
} |
#else |
#include <asm-generic/pgtable-nopmd.h> |
|
static inline pmdval_t native_pmd_val(pmd_t pmd) |
{ |
return native_pgd_val(pmd.pud.pgd); |
} |
#endif |
|
static inline pudval_t pud_flags(pud_t pud) |
{ |
return native_pud_val(pud) & PTE_FLAGS_MASK; |
} |
|
static inline pmdval_t pmd_flags(pmd_t pmd) |
{ |
return native_pmd_val(pmd) & PTE_FLAGS_MASK; |
} |
|
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; |
} |
|
#ifdef CONFIG_NUMA_BALANCING |
/* Set of bits that distinguishes present, prot_none and numa ptes */ |
#define _PAGE_NUMA_MASK (_PAGE_NUMA|_PAGE_PROTNONE|_PAGE_PRESENT) |
static inline pteval_t ptenuma_flags(pte_t pte) |
{ |
return pte_flags(pte) & _PAGE_NUMA_MASK; |
} |
|
static inline pmdval_t pmdnuma_flags(pmd_t pmd) |
{ |
return pmd_flags(pmd) & _PAGE_NUMA_MASK; |
} |
#endif /* CONFIG_NUMA_BALANCING */ |
|
#define pgprot_val(x) ((x).pgprot) |
#define __pgprot(x) ((pgprot_t) { (x) } ) |
|
extern uint16_t __cachemode2pte_tbl[_PAGE_CACHE_MODE_NUM]; |
extern uint8_t __pte2cachemode_tbl[8]; |
|
#define __pte2cm_idx(cb) \ |
((((cb) >> (_PAGE_BIT_PAT - 2)) & 4) | \ |
(((cb) >> (_PAGE_BIT_PCD - 1)) & 2) | \ |
(((cb) >> _PAGE_BIT_PWT) & 1)) |
#define __cm_idx2pte(i) \ |
((((i) & 4) << (_PAGE_BIT_PAT - 2)) | \ |
(((i) & 2) << (_PAGE_BIT_PCD - 1)) | \ |
(((i) & 1) << _PAGE_BIT_PWT)) |
|
static inline unsigned long cachemode2protval(enum page_cache_mode pcm) |
{ |
if (likely(pcm == 0)) |
return 0; |
return __cachemode2pte_tbl[pcm]; |
} |
static inline pgprot_t cachemode2pgprot(enum page_cache_mode pcm) |
{ |
return __pgprot(cachemode2protval(pcm)); |
} |
static inline enum page_cache_mode pgprot2cachemode(pgprot_t pgprot) |
{ |
unsigned long masked; |
|
masked = pgprot_val(pgprot) & _PAGE_CACHE_MASK; |
if (likely(masked == 0)) |
return 0; |
return __pte2cachemode_tbl[__pte2cm_idx(masked)]; |
} |
static inline pgprot_t pgprot_4k_2_large(pgprot_t pgprot) |
{ |
pgprot_t new; |
unsigned long val; |
|
val = pgprot_val(pgprot); |
pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | |
((val & _PAGE_PAT) << (_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); |
return new; |
} |
static inline pgprot_t pgprot_large_2_4k(pgprot_t pgprot) |
{ |
pgprot_t new; |
unsigned long val; |
|
val = pgprot_val(pgprot); |
pgprot_val(new) = (val & ~(_PAGE_PAT | _PAGE_PAT_LARGE)) | |
((val & _PAGE_PAT_LARGE) >> |
(_PAGE_BIT_PAT_LARGE - _PAGE_BIT_PAT)); |
return new; |
} |
|
|
typedef struct page *pgtable_t; |
|
extern pteval_t __supported_pte_mask; |
extern void set_nx(void); |
extern int nx_enabled; |
|
#define pgprot_writecombine pgprot_writecombine |
extern pgprot_t pgprot_writecombine(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); |
int phys_mem_access_prot_allowed(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 paging_init |
#endif |
|
struct seq_file; |
extern void arch_report_meminfo(struct seq_file *m); |
|
enum pg_level { |
PG_LEVEL_NONE, |
PG_LEVEL_4K, |
PG_LEVEL_2M, |
PG_LEVEL_1G, |
PG_LEVEL_NUM |
}; |
|
#ifdef CONFIG_PROC_FS |
extern void update_page_count(int level, unsigned long pages); |
#else |
static inline void update_page_count(int level, unsigned long pages) { } |
#endif |
|
/* |
* Helper function that returns the kernel pagetable entry controlling |
* the virtual address 'address'. NULL means no pagetable entry present. |
* NOTE: the return type is pte_t but if the pmd is PSE then we return it |
* as a pte too. |
*/ |
extern pte_t *lookup_address(unsigned long address, unsigned int *level); |
extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address, |
unsigned int *level); |
extern pmd_t *lookup_pmd_address(unsigned long address); |
extern phys_addr_t slow_virt_to_phys(void *__address); |
extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address, |
unsigned numpages, unsigned long page_flags); |
void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address, |
unsigned numpages); |
#endif /* !__ASSEMBLY__ */ |
|
#endif /* _ASM_X86_PGTABLE_DEFS_H */ |