aeed5fce37
Fix warning from pmd_bad() at bootup on a HIGHMEM64G HIGHPTE x86_32. That came from9fc34113f6x86: debug pmd_bad(); but we understand now that the typecasting was wrong for PAE in the previous version: pagetable pages above 4GB looked bad and stopped Arjan from booting. And revert thatcded932b75x86: fix pmd_bad and pud_bad to support huge pages. It was the wrong way round: we shouldn't weaken every pmd_bad and pud_bad check to let huge pages slip through - in part they check that we _don't_ have a huge page where it's not expected. Put the x86 pmd_bad() and pud_bad() definitions back to what they have long been: they can be improved (x86_32 should use PTE_MASK, to stop PAE thinking junk in the upper word is good; and x86_64 should follow x86_32's stricter comparison, to stop thinking any subset of required bits is good); but that should be a later patch. Fix Hans' good observation that follow_page() will never find pmd_huge() because that would have already failed the pmd_bad test: test pmd_huge in between the pmd_none and pmd_bad tests. Tighten x86's pmd_huge() check? No, once it's a hugepage entry, it can get quite far from a good pmd: for example, PROT_NONE leaves it with only ACCESSED of the KERN_PGTABLE bits. However... though follow_page() contains this and another test for huge pages, so it's nice to keep it working on them, where does it actually get called on a huge page? get_user_pages() checks is_vm_hugetlb_page(vma) to to call alternative hugetlb processing, as does unmap_vmas() and others. Signed-off-by: Hugh Dickins <hugh@veritas.com> Earlier-version-tested-by: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Jeff Chua <jeff.chua.linux@gmail.com> Cc: Hans Rosenfeld <hans.rosenfeld@amd.com> Cc: Arjan van de Ven <arjan@linux.intel.com> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
224 lines
6.6 KiB
C
224 lines
6.6 KiB
C
#ifndef _I386_PGTABLE_H
|
|
#define _I386_PGTABLE_H
|
|
|
|
|
|
/*
|
|
* The Linux memory management assumes a three-level page table setup. On
|
|
* the i386, we use that, but "fold" the mid level into the top-level page
|
|
* table, so that we physically have the same two-level page table as the
|
|
* i386 mmu expects.
|
|
*
|
|
* This file contains the functions and defines necessary to modify and use
|
|
* the i386 page table tree.
|
|
*/
|
|
#ifndef __ASSEMBLY__
|
|
#include <asm/processor.h>
|
|
#include <asm/fixmap.h>
|
|
#include <linux/threads.h>
|
|
#include <asm/paravirt.h>
|
|
|
|
#include <linux/bitops.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/list.h>
|
|
#include <linux/spinlock.h>
|
|
|
|
struct mm_struct;
|
|
struct vm_area_struct;
|
|
|
|
extern pgd_t swapper_pg_dir[1024];
|
|
|
|
static inline void pgtable_cache_init(void) { }
|
|
static inline void check_pgt_cache(void) { }
|
|
void paging_init(void);
|
|
|
|
|
|
/*
|
|
* The Linux x86 paging architecture is 'compile-time dual-mode', it
|
|
* implements both the traditional 2-level x86 page tables and the
|
|
* newer 3-level PAE-mode page tables.
|
|
*/
|
|
#ifdef CONFIG_X86_PAE
|
|
# include <asm/pgtable-3level-defs.h>
|
|
# define PMD_SIZE (1UL << PMD_SHIFT)
|
|
# define PMD_MASK (~(PMD_SIZE - 1))
|
|
#else
|
|
# include <asm/pgtable-2level-defs.h>
|
|
#endif
|
|
|
|
#define PGDIR_SIZE (1UL << PGDIR_SHIFT)
|
|
#define PGDIR_MASK (~(PGDIR_SIZE - 1))
|
|
|
|
/* Just any arbitrary offset to the start of the vmalloc VM area: the
|
|
* current 8MB value just means that there will be a 8MB "hole" after the
|
|
* physical memory until the kernel virtual memory starts. That means that
|
|
* any out-of-bounds memory accesses will hopefully be caught.
|
|
* The vmalloc() routines leaves a hole of 4kB between each vmalloced
|
|
* area for the same reason. ;)
|
|
*/
|
|
#define VMALLOC_OFFSET (8 * 1024 * 1024)
|
|
#define VMALLOC_START (((unsigned long)high_memory + 2 * VMALLOC_OFFSET - 1) \
|
|
& ~(VMALLOC_OFFSET - 1))
|
|
#ifdef CONFIG_X86_PAE
|
|
#define LAST_PKMAP 512
|
|
#else
|
|
#define LAST_PKMAP 1024
|
|
#endif
|
|
|
|
#define PKMAP_BASE ((FIXADDR_BOOT_START - PAGE_SIZE * (LAST_PKMAP + 1)) \
|
|
& PMD_MASK)
|
|
|
|
#ifdef CONFIG_HIGHMEM
|
|
# define VMALLOC_END (PKMAP_BASE - 2 * PAGE_SIZE)
|
|
#else
|
|
# define VMALLOC_END (FIXADDR_START - 2 * PAGE_SIZE)
|
|
#endif
|
|
|
|
/*
|
|
* Define this if things work differently on an i386 and an i486:
|
|
* it will (on an i486) warn about kernel memory accesses that are
|
|
* done without a 'access_ok(VERIFY_WRITE,..)'
|
|
*/
|
|
#undef TEST_ACCESS_OK
|
|
|
|
/* The boot page tables (all created as a single array) */
|
|
extern unsigned long pg0[];
|
|
|
|
#define pte_present(x) ((x).pte_low & (_PAGE_PRESENT | _PAGE_PROTNONE))
|
|
|
|
/* To avoid harmful races, pmd_none(x) should check only the lower when PAE */
|
|
#define pmd_none(x) (!(unsigned long)pmd_val((x)))
|
|
#define pmd_present(x) (pmd_val((x)) & _PAGE_PRESENT)
|
|
#define pmd_bad(x) ((pmd_val(x) & (~PAGE_MASK & ~_PAGE_USER)) != _KERNPG_TABLE)
|
|
|
|
#define pages_to_mb(x) ((x) >> (20-PAGE_SHIFT))
|
|
|
|
#ifdef CONFIG_X86_PAE
|
|
# include <asm/pgtable-3level.h>
|
|
#else
|
|
# include <asm/pgtable-2level.h>
|
|
#endif
|
|
|
|
/*
|
|
* Macro to mark a page protection value as "uncacheable".
|
|
* On processors which do not support it, this is a no-op.
|
|
*/
|
|
#define pgprot_noncached(prot) \
|
|
((boot_cpu_data.x86 > 3) \
|
|
? (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT)) \
|
|
: (prot))
|
|
|
|
/*
|
|
* Conversion functions: convert a page and protection to a page entry,
|
|
* and a page entry and page directory to the page they refer to.
|
|
*/
|
|
#define mk_pte(page, pgprot) pfn_pte(page_to_pfn(page), (pgprot))
|
|
|
|
/*
|
|
* 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))
|
|
#define pgd_index_k(addr) pgd_index((addr))
|
|
|
|
/*
|
|
* 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))
|
|
|
|
static inline int pud_large(pud_t pud) { return 0; }
|
|
|
|
/*
|
|
* 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
|
|
*/
|
|
#define pmd_index(address) \
|
|
(((address) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
|
|
|
|
/*
|
|
* the pte page can be thought of an array like this: pte_t[PTRS_PER_PTE]
|
|
*
|
|
* this macro returns the index of the entry in the pte page which would
|
|
* control the given virtual address
|
|
*/
|
|
#define pte_index(address) \
|
|
(((address) >> PAGE_SHIFT) & (PTRS_PER_PTE - 1))
|
|
#define pte_offset_kernel(dir, address) \
|
|
((pte_t *)pmd_page_vaddr(*(dir)) + pte_index((address)))
|
|
|
|
#define pmd_page(pmd) (pfn_to_page(pmd_val((pmd)) >> PAGE_SHIFT))
|
|
|
|
#define pmd_page_vaddr(pmd) \
|
|
((unsigned long)__va(pmd_val((pmd)) & PAGE_MASK))
|
|
|
|
#if defined(CONFIG_HIGHPTE)
|
|
#define pte_offset_map(dir, address) \
|
|
((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), KM_PTE0) + \
|
|
pte_index((address)))
|
|
#define pte_offset_map_nested(dir, address) \
|
|
((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), KM_PTE1) + \
|
|
pte_index((address)))
|
|
#define pte_unmap(pte) kunmap_atomic((pte), KM_PTE0)
|
|
#define pte_unmap_nested(pte) kunmap_atomic((pte), KM_PTE1)
|
|
#else
|
|
#define pte_offset_map(dir, address) \
|
|
((pte_t *)page_address(pmd_page(*(dir))) + pte_index((address)))
|
|
#define pte_offset_map_nested(dir, address) pte_offset_map((dir), (address))
|
|
#define pte_unmap(pte) do { } while (0)
|
|
#define pte_unmap_nested(pte) do { } while (0)
|
|
#endif
|
|
|
|
/* Clear a kernel PTE and flush it from the TLB */
|
|
#define kpte_clear_flush(ptep, vaddr) \
|
|
do { \
|
|
pte_clear(&init_mm, (vaddr), (ptep)); \
|
|
__flush_tlb_one((vaddr)); \
|
|
} while (0)
|
|
|
|
/*
|
|
* The i386 doesn't have any external MMU info: the kernel page
|
|
* tables contain all the necessary information.
|
|
*/
|
|
#define update_mmu_cache(vma, address, pte) do { } while (0)
|
|
|
|
extern void native_pagetable_setup_start(pgd_t *base);
|
|
extern void native_pagetable_setup_done(pgd_t *base);
|
|
|
|
#ifndef CONFIG_PARAVIRT
|
|
static inline void __init paravirt_pagetable_setup_start(pgd_t *base)
|
|
{
|
|
native_pagetable_setup_start(base);
|
|
}
|
|
|
|
static inline void __init paravirt_pagetable_setup_done(pgd_t *base)
|
|
{
|
|
native_pagetable_setup_done(base);
|
|
}
|
|
#endif /* !CONFIG_PARAVIRT */
|
|
|
|
#endif /* !__ASSEMBLY__ */
|
|
|
|
/*
|
|
* kern_addr_valid() is (1) for FLATMEM and (0) for
|
|
* SPARSEMEM and DISCONTIGMEM
|
|
*/
|
|
#ifdef CONFIG_FLATMEM
|
|
#define kern_addr_valid(addr) (1)
|
|
#else
|
|
#define kern_addr_valid(kaddr) (0)
|
|
#endif
|
|
|
|
#define io_remap_pfn_range(vma, vaddr, pfn, size, prot) \
|
|
remap_pfn_range(vma, vaddr, pfn, size, prot)
|
|
|
|
#endif /* _I386_PGTABLE_H */
|