kevin/linux
1
Fork 0
Code
3a4d5c94e9
linux/arch/x86/include/asm/pgtable_64.h
Linus Torvalds 9063c61fd5 x86, 64-bit: Clean up user address masking 
The discussion about using "access_ok()" in get_user_pages_fast() (see
commit 7f81890687: "x86: don't use
'access_ok()' as a range check in get_user_pages_fast()" for details and
end result), made us notice that x86-64 was really being very sloppy
about virtual address checking.

So be way more careful and straightforward about masking x86-64 virtual
addresses:

 - All the VIRTUAL_MASK* variants now cover half of the address
   space, it's not like we can use the full mask on a signed
   integer, and the larger mask just invites mistakes when
   applying it to either half of the 48-bit address space.

 - /proc/kcore's kc_offset_to_vaddr() becomes a lot more
   obvious when it transforms a file offset into a
   (kernel-half) virtual address.

 - Unify/simplify the 32-bit and 64-bit USER_DS definition to
   be based on TASK_SIZE_MAX.

This cleanup and more careful/obvious user virtual address checking also
uncovered a buglet in the x86-64 implementation of strnlen_user(): it
would do an "access_ok()" check on the whole potential area, even if the
string itself was much shorter, and thus return an error even for valid
strings. Our sloppy checking had hidden this.

So this fixes 'strnlen_user()' to do this properly, the same way we
already handled user strings in 'strncpy_from_user()'.  Namely by just
checking the first byte, and then relying on fault handling for the
rest.  That always works, since we impose a guard page that cannot be
mapped at the end of the user space address space (and even if we
didn't, we'd have the address space hole).

Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2009-06-20 15:40:00 -07:00

174 lines
4.5 KiB
C
Raw Blame History

#ifndef _ASM_X86_PGTABLE_64_H
#define _ASM_X86_PGTABLE_64_H
#include <linux/const.h>
#include <asm/pgtable_64_types.h>
#ifndef __ASSEMBLY__
/*
* This file contains the functions and defines necessary to modify and use
* the x86-64 page table tree.
*/
#include <asm/processor.h>
#include <linux/bitops.h>
#include <linux/threads.h>
extern pud_t level3_kernel_pgt[512];
extern pud_t level3_ident_pgt[512];
extern pmd_t level2_kernel_pgt[512];
extern pmd_t level2_fixmap_pgt[512];
extern pmd_t level2_ident_pgt[512];
extern pgd_t init_level4_pgt[];
#define swapper_pg_dir init_level4_pgt
extern void paging_init(void);
#define pte_ERROR(e) \
printk("%s:%d: bad pte %p(%016lx).\n", \
__FILE__, __LINE__, &(e), pte_val(e))
#define pmd_ERROR(e) \
printk("%s:%d: bad pmd %p(%016lx).\n", \
__FILE__, __LINE__, &(e), pmd_val(e))
#define pud_ERROR(e) \
printk("%s:%d: bad pud %p(%016lx).\n", \
__FILE__, __LINE__, &(e), pud_val(e))
#define pgd_ERROR(e) \
printk("%s:%d: bad pgd %p(%016lx).\n", \
__FILE__, __LINE__, &(e), pgd_val(e))
struct mm_struct;
void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
pte_t *ptep)
{
*ptep = native_make_pte(0);
}
static inline void native_set_pte(pte_t *ptep, pte_t pte)
{
*ptep = pte;
}
static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
{
native_set_pte(ptep, pte);
}
static inline pte_t native_ptep_get_and_clear(pte_t *xp)
{
#ifdef CONFIG_SMP
return native_make_pte(xchg(&xp->pte, 0));
#else
/* native_local_ptep_get_and_clear,
but duplicated because of cyclic dependency */
pte_t ret = *xp;
native_pte_clear(NULL, 0, xp);
return ret;
#endif
}
static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
{
*pmdp = pmd;
}
static inline void native_pmd_clear(pmd_t *pmd)
{
native_set_pmd(pmd, native_make_pmd(0));
}
static inline void native_set_pud(pud_t *pudp, pud_t pud)
{
*pudp = pud;
}
static inline void native_pud_clear(pud_t *pud)
{
native_set_pud(pud, native_make_pud(0));
}
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
*pgdp = pgd;
}
static inline void native_pgd_clear(pgd_t *pgd)
{
native_set_pgd(pgd, native_make_pgd(0));
}
/*
* Conversion functions: convert a page and protection to a page entry,
* and a page entry and page directory to the page they refer to.
*/
/*
* Level 4 access.
*/
static inline int pgd_large(pgd_t pgd) { return 0; }
#define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE)
/* PUD - Level3 access */
/* PMD - Level 2 access */
#define pte_to_pgoff(pte) ((pte_val((pte)) & PHYSICAL_PAGE_MASK) >> PAGE_SHIFT)
#define pgoff_to_pte(off) ((pte_t) { .pte = ((off) << PAGE_SHIFT) | \
_PAGE_FILE })
#define PTE_FILE_MAX_BITS __PHYSICAL_MASK_SHIFT
/* PTE - Level 1 access. */
/* x86-64 always has all page tables mapped. */
#define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
#define pte_offset_map_nested(dir, address) pte_offset_kernel((dir), (address))
#define pte_unmap(pte) /* NOP */
#define pte_unmap_nested(pte) /* NOP */
#define update_mmu_cache(vma, address, pte) do { } while (0)
/* Encode and de-code a swap entry */
#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
#define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
#else
#define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1)
#define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1)
#endif
#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
#define __swp_type(x) (((x).val >> (_PAGE_BIT_PRESENT + 1)) \
& ((1U << SWP_TYPE_BITS) - 1))
#define __swp_offset(x) ((x).val >> SWP_OFFSET_SHIFT)
#define __swp_entry(type, offset) ((swp_entry_t) { \
((type) << (_PAGE_BIT_PRESENT + 1)) \
| ((offset) << SWP_OFFSET_SHIFT) })
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) })
#define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val })
extern int kern_addr_valid(unsigned long addr);
extern void cleanup_highmap(void);
#define HAVE_ARCH_UNMAPPED_AREA
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
#define pgtable_cache_init() do { } while (0)
#define check_pgt_cache() do { } while (0)
#define PAGE_AGP PAGE_KERNEL_NOCACHE
#define HAVE_PAGE_AGP 1
/* fs/proc/kcore.c */
#define kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK)
#define kc_offset_to_vaddr(o) ((o) | ~__VIRTUAL_MASK)
#define __HAVE_ARCH_PTE_SAME
#endif /* !__ASSEMBLY__ */
#endif /* _ASM_X86_PGTABLE_64_H */
View Git Blame Copy Permalink