linux_dsm_epyc7002/arch/x86/include/asm/pgtable.h
Thomas Garnier 0483e1fa6e x86/mm: Implement ASLR for kernel memory regions
Randomizes the virtual address space of kernel memory regions for
x86_64. This first patch adds the infrastructure and does not randomize
any region. The following patches will randomize the physical memory
mapping, vmalloc and vmemmap regions.

This security feature mitigates exploits relying on predictable kernel
addresses. These addresses can be used to disclose the kernel modules
base addresses or corrupt specific structures to elevate privileges
bypassing the current implementation of KASLR. This feature can be
enabled with the CONFIG_RANDOMIZE_MEMORY option.

The order of each memory region is not changed. The feature looks at the
available space for the regions based on different configuration options
and randomizes the base and space between each. The size of the physical
memory mapping is the available physical memory. No performance impact
was detected while testing the feature.

Entropy is generated using the KASLR early boot functions now shared in
the lib directory (originally written by Kees Cook). Randomization is
done on PGD & PUD page table levels to increase possible addresses. The
physical memory mapping code was adapted to support PUD level virtual
addresses. This implementation on the best configuration provides 30,000
possible virtual addresses in average for each memory region.  An
additional low memory page is used to ensure each CPU can start with a
PGD aligned virtual address (for realmode).

x86/dump_pagetable was updated to correctly display each region.

Updated documentation on x86_64 memory layout accordingly.

Performance data, after all patches in the series:

Kernbench shows almost no difference (-+ less than 1%):

Before:

Average Optimal load -j 12 Run (std deviation): Elapsed Time 102.63 (1.2695)
User Time 1034.89 (1.18115) System Time 87.056 (0.456416) Percent CPU 1092.9
(13.892) Context Switches 199805 (3455.33) Sleeps 97907.8 (900.636)

After:

Average Optimal load -j 12 Run (std deviation): Elapsed Time 102.489 (1.10636)
User Time 1034.86 (1.36053) System Time 87.764 (0.49345) Percent CPU 1095
(12.7715) Context Switches 199036 (4298.1) Sleeps 97681.6 (1031.11)

Hackbench shows 0% difference on average (hackbench 90 repeated 10 times):

attemp,before,after 1,0.076,0.069 2,0.072,0.069 3,0.066,0.066 4,0.066,0.068
5,0.066,0.067 6,0.066,0.069 7,0.067,0.066 8,0.063,0.067 9,0.067,0.065
10,0.068,0.071 average,0.0677,0.0677

Signed-off-by: Thomas Garnier <thgarnie@google.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: Alexander Kuleshov <kuleshovmail@gmail.com>
Cc: Alexander Popov <alpopov@ptsecurity.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Baoquan He <bhe@redhat.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jan Beulich <JBeulich@suse.com>
Cc: Joerg Roedel <jroedel@suse.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lv Zheng <lv.zheng@intel.com>
Cc: Mark Salter <msalter@redhat.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Toshi Kani <toshi.kani@hpe.com>
Cc: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: kernel-hardening@lists.openwall.com
Cc: linux-doc@vger.kernel.org
Link: http://lkml.kernel.org/r/1466556426-32664-6-git-send-email-keescook@chromium.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-07-08 17:33:46 +02:00

980 lines
23 KiB
C

#ifndef _ASM_X86_PGTABLE_H
#define _ASM_X86_PGTABLE_H
#include <asm/page.h>
#include <asm/e820.h>
#include <asm/pgtable_types.h>
/*
* Macro to mark a page protection value as UC-
*/
#define pgprot_noncached(prot) \
((boot_cpu_data.x86 > 3) \
? (__pgprot(pgprot_val(prot) | \
cachemode2protval(_PAGE_CACHE_MODE_UC_MINUS))) \
: (prot))
#ifndef __ASSEMBLY__
#include <asm/x86_init.h>
void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
void ptdump_walk_pgd_level_checkwx(void);
#ifdef CONFIG_DEBUG_WX
#define debug_checkwx() ptdump_walk_pgd_level_checkwx()
#else
#define debug_checkwx() do { } while (0)
#endif
/*
* 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)]
__visible;
#define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
extern spinlock_t pgd_lock;
extern struct list_head pgd_list;
extern struct mm_struct *pgd_page_get_mm(struct page *page);
#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_pmd_at(mm, addr, pmdp, pmd) native_set_pmd_at(mm, addr, pmdp, pmd)
#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 pgd_val(x) native_pgd_val(x)
#define __pgd(x) native_make_pgd(x)
#ifndef __PAGETABLE_PUD_FOLDED
#define pud_val(x) native_pud_val(x)
#define __pud(x) native_make_pud(x)
#endif
#ifndef __PAGETABLE_PMD_FOLDED
#define pmd_val(x) native_pmd_val(x)
#define __pmd(x) native_make_pmd(x)
#endif
#define pte_val(x) native_pte_val(x)
#define __pte(x) native_make_pte(x)
#define arch_end_context_switch(prev) do {} while(0)
#endif /* CONFIG_PARAVIRT */
/*
* The following only work if pte_present() is true.
* Undefined behaviour if not..
*/
static inline int pte_dirty(pte_t pte)
{
return pte_flags(pte) & _PAGE_DIRTY;
}
static inline u32 read_pkru(void)
{
if (boot_cpu_has(X86_FEATURE_OSPKE))
return __read_pkru();
return 0;
}
static inline void write_pkru(u32 pkru)
{
if (boot_cpu_has(X86_FEATURE_OSPKE))
__write_pkru(pkru);
}
static inline int pte_young(pte_t pte)
{
return pte_flags(pte) & _PAGE_ACCESSED;
}
static inline int pmd_dirty(pmd_t pmd)
{
return pmd_flags(pmd) & _PAGE_DIRTY;
}
static inline int pmd_young(pmd_t pmd)
{
return pmd_flags(pmd) & _PAGE_ACCESSED;
}
static inline int pte_write(pte_t pte)
{
return pte_flags(pte) & _PAGE_RW;
}
static inline int pte_huge(pte_t pte)
{
return pte_flags(pte) & _PAGE_PSE;
}
static inline int pte_global(pte_t pte)
{
return pte_flags(pte) & _PAGE_GLOBAL;
}
static inline int pte_exec(pte_t pte)
{
return !(pte_flags(pte) & _PAGE_NX);
}
static inline int pte_special(pte_t pte)
{
return pte_flags(pte) & _PAGE_SPECIAL;
}
static inline unsigned long pte_pfn(pte_t pte)
{
return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
}
static inline unsigned long pmd_pfn(pmd_t pmd)
{
return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
}
static inline unsigned long pud_pfn(pud_t pud)
{
return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT;
}
#define pte_page(pte) pfn_to_page(pte_pfn(pte))
static inline int pmd_large(pmd_t pte)
{
return pmd_flags(pte) & _PAGE_PSE;
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
static inline int pmd_trans_huge(pmd_t pmd)
{
return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
}
#define has_transparent_hugepage has_transparent_hugepage
static inline int has_transparent_hugepage(void)
{
return boot_cpu_has(X86_FEATURE_PSE);
}
#ifdef __HAVE_ARCH_PTE_DEVMAP
static inline int pmd_devmap(pmd_t pmd)
{
return !!(pmd_val(pmd) & _PAGE_DEVMAP);
}
#endif
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
static inline pte_t pte_set_flags(pte_t pte, pteval_t set)
{
pteval_t v = native_pte_val(pte);
return native_make_pte(v | set);
}
static inline pte_t pte_clear_flags(pte_t pte, pteval_t clear)
{
pteval_t v = native_pte_val(pte);
return native_make_pte(v & ~clear);
}
static inline pte_t pte_mkclean(pte_t pte)
{
return pte_clear_flags(pte, _PAGE_DIRTY);
}
static inline pte_t pte_mkold(pte_t pte)
{
return pte_clear_flags(pte, _PAGE_ACCESSED);
}
static inline pte_t pte_wrprotect(pte_t pte)
{
return pte_clear_flags(pte, _PAGE_RW);
}
static inline pte_t pte_mkexec(pte_t pte)
{
return pte_clear_flags(pte, _PAGE_NX);
}
static inline pte_t pte_mkdirty(pte_t pte)
{
return pte_set_flags(pte, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
}
static inline pte_t pte_mkyoung(pte_t pte)
{
return pte_set_flags(pte, _PAGE_ACCESSED);
}
static inline pte_t pte_mkwrite(pte_t pte)
{
return pte_set_flags(pte, _PAGE_RW);
}
static inline pte_t pte_mkhuge(pte_t pte)
{
return pte_set_flags(pte, _PAGE_PSE);
}
static inline pte_t pte_clrhuge(pte_t pte)
{
return pte_clear_flags(pte, _PAGE_PSE);
}
static inline pte_t pte_mkglobal(pte_t pte)
{
return pte_set_flags(pte, _PAGE_GLOBAL);
}
static inline pte_t pte_clrglobal(pte_t pte)
{
return pte_clear_flags(pte, _PAGE_GLOBAL);
}
static inline pte_t pte_mkspecial(pte_t pte)
{
return pte_set_flags(pte, _PAGE_SPECIAL);
}
static inline pte_t pte_mkdevmap(pte_t pte)
{
return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP);
}
static inline pmd_t pmd_set_flags(pmd_t pmd, pmdval_t set)
{
pmdval_t v = native_pmd_val(pmd);
return __pmd(v | set);
}
static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
{
pmdval_t v = native_pmd_val(pmd);
return __pmd(v & ~clear);
}
static inline pmd_t pmd_mkold(pmd_t pmd)
{
return pmd_clear_flags(pmd, _PAGE_ACCESSED);
}
static inline pmd_t pmd_mkclean(pmd_t pmd)
{
return pmd_clear_flags(pmd, _PAGE_DIRTY);
}
static inline pmd_t pmd_wrprotect(pmd_t pmd)
{
return pmd_clear_flags(pmd, _PAGE_RW);
}
static inline pmd_t pmd_mkdirty(pmd_t pmd)
{
return pmd_set_flags(pmd, _PAGE_DIRTY | _PAGE_SOFT_DIRTY);
}
static inline pmd_t pmd_mkdevmap(pmd_t pmd)
{
return pmd_set_flags(pmd, _PAGE_DEVMAP);
}
static inline pmd_t pmd_mkhuge(pmd_t pmd)
{
return pmd_set_flags(pmd, _PAGE_PSE);
}
static inline pmd_t pmd_mkyoung(pmd_t pmd)
{
return pmd_set_flags(pmd, _PAGE_ACCESSED);
}
static inline pmd_t pmd_mkwrite(pmd_t pmd)
{
return pmd_set_flags(pmd, _PAGE_RW);
}
static inline pmd_t pmd_mknotpresent(pmd_t pmd)
{
return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE);
}
#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
static inline int pte_soft_dirty(pte_t pte)
{
return pte_flags(pte) & _PAGE_SOFT_DIRTY;
}
static inline int pmd_soft_dirty(pmd_t pmd)
{
return pmd_flags(pmd) & _PAGE_SOFT_DIRTY;
}
static inline pte_t pte_mksoft_dirty(pte_t pte)
{
return pte_set_flags(pte, _PAGE_SOFT_DIRTY);
}
static inline pmd_t pmd_mksoft_dirty(pmd_t pmd)
{
return pmd_set_flags(pmd, _PAGE_SOFT_DIRTY);
}
static inline pte_t pte_clear_soft_dirty(pte_t pte)
{
return pte_clear_flags(pte, _PAGE_SOFT_DIRTY);
}
static inline pmd_t pmd_clear_soft_dirty(pmd_t pmd)
{
return pmd_clear_flags(pmd, _PAGE_SOFT_DIRTY);
}
#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */
/*
* Mask out unsupported bits in a present pgprot. Non-present pgprots
* can use those bits for other purposes, so leave them be.
*/
static inline pgprotval_t massage_pgprot(pgprot_t pgprot)
{
pgprotval_t protval = pgprot_val(pgprot);
if (protval & _PAGE_PRESENT)
protval &= __supported_pte_mask;
return protval;
}
static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
{
return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) |
massage_pgprot(pgprot));
}
static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
{
return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) |
massage_pgprot(pgprot));
}
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 |= massage_pgprot(newprot) & ~_PAGE_CHG_MASK;
return __pte(val);
}
static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
{
pmdval_t val = pmd_val(pmd);
val &= _HPAGE_CHG_MASK;
val |= massage_pgprot(newprot) & ~_HPAGE_CHG_MASK;
return __pmd(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_flags(x))
#define pmd_pgprot(x) __pgprot(pmd_flags(x))
#define pud_pgprot(x) __pgprot(pud_flags(x))
#define canon_pgprot(p) __pgprot(massage_pgprot(p))
static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
enum page_cache_mode pcm,
enum page_cache_mode new_pcm)
{
/*
* PAT type is always WB for untracked ranges, so no need to check.
*/
if (x86_platform.is_untracked_pat_range(paddr, paddr + size))
return 1;
/*
* Certain new memtypes are not allowed with certain
* requested memtype:
* - request is uncached, return cannot be write-back
* - request is write-combine, return cannot be write-back
* - request is write-through, return cannot be write-back
* - request is write-through, return cannot be write-combine
*/
if ((pcm == _PAGE_CACHE_MODE_UC_MINUS &&
new_pcm == _PAGE_CACHE_MODE_WB) ||
(pcm == _PAGE_CACHE_MODE_WC &&
new_pcm == _PAGE_CACHE_MODE_WB) ||
(pcm == _PAGE_CACHE_MODE_WT &&
new_pcm == _PAGE_CACHE_MODE_WB) ||
(pcm == _PAGE_CACHE_MODE_WT &&
new_pcm == _PAGE_CACHE_MODE_WC)) {
return 0;
}
return 1;
}
pmd_t *populate_extra_pmd(unsigned long vaddr);
pte_t *populate_extra_pte(unsigned long vaddr);
#endif /* __ASSEMBLY__ */
#ifdef CONFIG_X86_32
# include <asm/pgtable_32.h>
#else
# include <asm/pgtable_64.h>
#endif
#ifndef __ASSEMBLY__
#include <linux/mm_types.h>
#include <linux/mmdebug.h>
#include <linux/log2.h>
static inline int pte_none(pte_t pte)
{
return !pte.pte;
}
#define __HAVE_ARCH_PTE_SAME
static inline int pte_same(pte_t a, pte_t b)
{
return a.pte == b.pte;
}
static inline int pte_present(pte_t a)
{
return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
}
#ifdef __HAVE_ARCH_PTE_DEVMAP
static inline int pte_devmap(pte_t a)
{
return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP;
}
#endif
#define pte_accessible pte_accessible
static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
{
if (pte_flags(a) & _PAGE_PRESENT)
return true;
if ((pte_flags(a) & _PAGE_PROTNONE) &&
mm_tlb_flush_pending(mm))
return true;
return false;
}
static inline int pte_hidden(pte_t pte)
{
return pte_flags(pte) & _PAGE_HIDDEN;
}
static inline int pmd_present(pmd_t pmd)
{
/*
* Checking for _PAGE_PSE is needed too because
* split_huge_page will temporarily clear the present bit (but
* the _PAGE_PSE flag will remain set at all times while the
* _PAGE_PRESENT bit is clear).
*/
return pmd_flags(pmd) & (_PAGE_PRESENT | _PAGE_PROTNONE | _PAGE_PSE);
}
#ifdef CONFIG_NUMA_BALANCING
/*
* These work without NUMA balancing but the kernel does not care. See the
* comment in include/asm-generic/pgtable.h
*/
static inline int pte_protnone(pte_t pte)
{
return (pte_flags(pte) & (_PAGE_PROTNONE | _PAGE_PRESENT))
== _PAGE_PROTNONE;
}
static inline int pmd_protnone(pmd_t pmd)
{
return (pmd_flags(pmd) & (_PAGE_PROTNONE | _PAGE_PRESENT))
== _PAGE_PROTNONE;
}
#endif /* CONFIG_NUMA_BALANCING */
static inline int pmd_none(pmd_t pmd)
{
/* Only check low word on 32-bit platforms, since it might be
out of sync with upper half. */
return (unsigned long)native_pmd_val(pmd) == 0;
}
static inline unsigned long pmd_page_vaddr(pmd_t pmd)
{
return (unsigned long)__va(pmd_val(pmd) & pmd_pfn_mask(pmd));
}
/*
* Currently stuck as a macro due to indirect forward reference to
* linux/mmzone.h's __section_mem_map_addr() definition:
*/
#define pmd_page(pmd) \
pfn_to_page((pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT)
/*
* the pmd page can be thought of an array like this: pmd_t[PTRS_PER_PMD]
*
* this macro returns the index of the entry in the pmd page which would
* control the given virtual address
*/
static inline unsigned long pmd_index(unsigned long address)
{
return (address >> PMD_SHIFT) & (PTRS_PER_PMD - 1);
}
/*
* Conversion functions: convert a page and protection to a page entry,
* and a page entry and page directory to the page they refer to.
*
* (Currently stuck as a macro because of indirect forward reference
* to linux/mm.h:page_to_nid())
*/
#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
/*
* the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
*
* this function returns the index of the entry in the pte page which would
* control the given virtual address
*/
static inline unsigned long pte_index(unsigned long address)
{
return (address >> PAGE_SHIFT) & (PTRS_PER_PTE - 1);
}
static inline pte_t *pte_offset_kernel(pmd_t *pmd, unsigned long address)
{
return (pte_t *)pmd_page_vaddr(*pmd) + pte_index(address);
}
static inline int pmd_bad(pmd_t pmd)
{
return (pmd_flags(pmd) & ~_PAGE_USER) != _KERNPG_TABLE;
}
static inline unsigned long pages_to_mb(unsigned long npg)
{
return npg >> (20 - PAGE_SHIFT);
}
#if CONFIG_PGTABLE_LEVELS > 2
static inline int pud_none(pud_t pud)
{
return native_pud_val(pud) == 0;
}
static inline int pud_present(pud_t pud)
{
return pud_flags(pud) & _PAGE_PRESENT;
}
static inline unsigned long pud_page_vaddr(pud_t pud)
{
return (unsigned long)__va(pud_val(pud) & pud_pfn_mask(pud));
}
/*
* Currently stuck as a macro due to indirect forward reference to
* linux/mmzone.h's __section_mem_map_addr() definition:
*/
#define pud_page(pud) \
pfn_to_page((pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT)
/* Find an entry in the second-level page table.. */
static inline pmd_t *pmd_offset(pud_t *pud, unsigned long address)
{
return (pmd_t *)pud_page_vaddr(*pud) + pmd_index(address);
}
static inline int pud_large(pud_t pud)
{
return (pud_val(pud) & (_PAGE_PSE | _PAGE_PRESENT)) ==
(_PAGE_PSE | _PAGE_PRESENT);
}
static inline int pud_bad(pud_t pud)
{
return (pud_flags(pud) & ~(_KERNPG_TABLE | _PAGE_USER)) != 0;
}
#else
static inline int pud_large(pud_t pud)
{
return 0;
}
#endif /* CONFIG_PGTABLE_LEVELS > 2 */
#if CONFIG_PGTABLE_LEVELS > 3
static inline int pgd_present(pgd_t pgd)
{
return pgd_flags(pgd) & _PAGE_PRESENT;
}
static inline unsigned long pgd_page_vaddr(pgd_t pgd)
{
return (unsigned long)__va((unsigned long)pgd_val(pgd) & PTE_PFN_MASK);
}
/*
* Currently stuck as a macro due to indirect forward reference to
* linux/mmzone.h's __section_mem_map_addr() definition:
*/
#define pgd_page(pgd) pfn_to_page(pgd_val(pgd) >> PAGE_SHIFT)
/* to find an entry in a page-table-directory. */
static inline unsigned long pud_index(unsigned long address)
{
return (address >> PUD_SHIFT) & (PTRS_PER_PUD - 1);
}
static inline pud_t *pud_offset(pgd_t *pgd, unsigned long address)
{
return (pud_t *)pgd_page_vaddr(*pgd) + pud_index(address);
}
static inline int pgd_bad(pgd_t pgd)
{
return (pgd_flags(pgd) & ~_PAGE_USER) != _KERNPG_TABLE;
}
static inline int pgd_none(pgd_t pgd)
{
return !native_pgd_val(pgd);
}
#endif /* CONFIG_PGTABLE_LEVELS > 3 */
#endif /* __ASSEMBLY__ */
/*
* the pgd page can be thought of an array like this: pgd_t[PTRS_PER_PGD]
*
* this macro returns the index of the entry in the pgd page which would
* control the given virtual address
*/
#define pgd_index(address) (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
/*
* pgd_offset() returns a (pgd_t *)
* pgd_index() is used get the offset into the pgd page's array of pgd_t's;
*/
#define pgd_offset(mm, address) ((mm)->pgd + pgd_index((address)))
/*
* a shortcut which implies the use of the kernel's pgd, instead
* of a process's
*/
#define pgd_offset_k(address) pgd_offset(&init_mm, (address))
#define KERNEL_PGD_BOUNDARY pgd_index(PAGE_OFFSET)
#define KERNEL_PGD_PTRS (PTRS_PER_PGD - KERNEL_PGD_BOUNDARY)
#ifndef __ASSEMBLY__
extern int direct_gbpages;
void init_mem_mapping(void);
void early_alloc_pgt_buf(void);
#ifdef CONFIG_X86_64
/* Realmode trampoline initialization. */
extern pgd_t trampoline_pgd_entry;
static inline void __meminit init_trampoline_default(void)
{
/* Default trampoline pgd value */
trampoline_pgd_entry = init_level4_pgt[pgd_index(__PAGE_OFFSET)];
}
# ifdef CONFIG_RANDOMIZE_MEMORY
void __meminit init_trampoline(void);
# else
# define init_trampoline init_trampoline_default
# endif
#else
static inline void init_trampoline(void) { }
#endif
/* 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 pmd_t native_local_pmdp_get_and_clear(pmd_t *pmdp)
{
pmd_t res = *pmdp;
native_pmd_clear(pmdp);
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);
}
static inline void native_set_pmd_at(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp , pmd_t pmd)
{
native_set_pmd(pmdp, pmd);
}
#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.
*/
#define pte_update(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.
*/
struct vm_area_struct;
#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);
}
#define flush_tlb_fix_spurious_fault(vma, address) do { } while (0)
#define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot))
#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
extern int pmdp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
pmd_t entry, int dirty);
#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
extern int pmdp_test_and_clear_young(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmdp);
#define __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
extern int pmdp_clear_flush_young(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp);
#define __HAVE_ARCH_PMD_WRITE
static inline int pmd_write(pmd_t pmd)
{
return pmd_flags(pmd) & _PAGE_RW;
}
#define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR
static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr,
pmd_t *pmdp)
{
return native_pmdp_get_and_clear(pmdp);
}
#define __HAVE_ARCH_PMDP_SET_WRPROTECT
static inline void pmdp_set_wrprotect(struct mm_struct *mm,
unsigned long addr, pmd_t *pmdp)
{
clear_bit(_PAGE_BIT_RW, (unsigned long *)pmdp);
}
/*
* 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));
}
#define PTE_SHIFT ilog2(PTRS_PER_PTE)
static inline int page_level_shift(enum pg_level level)
{
return (PAGE_SHIFT - PTE_SHIFT) + level * PTE_SHIFT;
}
static inline unsigned long page_level_size(enum pg_level level)
{
return 1UL << page_level_shift(level);
}
static inline unsigned long page_level_mask(enum pg_level level)
{
return ~(page_level_size(level) - 1);
}
/*
* The x86 doesn't have any external MMU info: the kernel page
* tables contain all the necessary information.
*/
static inline void update_mmu_cache(struct vm_area_struct *vma,
unsigned long addr, pte_t *ptep)
{
}
static inline void update_mmu_cache_pmd(struct vm_area_struct *vma,
unsigned long addr, pmd_t *pmd)
{
}
#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
static inline pte_t pte_swp_mksoft_dirty(pte_t pte)
{
return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY);
}
static inline int pte_swp_soft_dirty(pte_t pte)
{
return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY;
}
static inline pte_t pte_swp_clear_soft_dirty(pte_t pte)
{
return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY);
}
#endif
#define PKRU_AD_BIT 0x1
#define PKRU_WD_BIT 0x2
#define PKRU_BITS_PER_PKEY 2
static inline bool __pkru_allows_read(u32 pkru, u16 pkey)
{
int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY;
return !(pkru & (PKRU_AD_BIT << pkru_pkey_bits));
}
static inline bool __pkru_allows_write(u32 pkru, u16 pkey)
{
int pkru_pkey_bits = pkey * PKRU_BITS_PER_PKEY;
/*
* Access-disable disables writes too so we need to check
* both bits here.
*/
return !(pkru & ((PKRU_AD_BIT|PKRU_WD_BIT) << pkru_pkey_bits));
}
static inline u16 pte_flags_pkey(unsigned long pte_flags)
{
#ifdef CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS
/* ifdef to avoid doing 59-bit shift on 32-bit values */
return (pte_flags & _PAGE_PKEY_MASK) >> _PAGE_BIT_PKEY_BIT0;
#else
return 0;
#endif
}
#include <asm-generic/pgtable.h>
#endif /* __ASSEMBLY__ */
#endif /* _ASM_X86_PGTABLE_H */