2008-10-23 13:26:29 +08:00
|
|
|
#ifndef _ASM_X86_PGTABLE_64_H
|
|
|
|
#define _ASM_X86_PGTABLE_64_H
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2007-05-08 15:31:11 +08:00
|
|
|
#include <linux/const.h>
|
2009-02-09 10:50:52 +08:00
|
|
|
#include <asm/pgtable_64_types.h>
|
|
|
|
|
2007-05-03 01:27:06 +08:00
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* This file contains the functions and defines necessary to modify and use
|
|
|
|
* the x86-64 page table tree.
|
|
|
|
*/
|
|
|
|
#include <asm/processor.h>
|
2007-10-19 14:40:25 +08:00
|
|
|
#include <linux/bitops.h>
|
2005-04-17 06:20:36 +08:00
|
|
|
#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];
|
2008-07-09 06:06:50 +08:00
|
|
|
extern pmd_t level2_fixmap_pgt[512];
|
|
|
|
extern pmd_t level2_ident_pgt[512];
|
2005-04-17 06:20:36 +08:00
|
|
|
extern pgd_t init_level4_pgt[];
|
|
|
|
|
Revert "[PATCH] x86: __pa and __pa_symbol address space separation"
This was broken. It adds complexity, for no good reason. Rather than
separate __pa() and __pa_symbol(), we should deprecate __pa_symbol(),
and preferably __pa() too - and just use "virt_to_phys()" instead, which
is more readable and has nicer semantics.
However, right now, just undo the separation, and make __pa_symbol() be
the exact same as __pa(). That fixes the bugs this patch introduced,
and we can do the fairly obvious cleanups later.
Do the new __phys_addr() function (which is now the actual workhorse for
the unified __pa()/__pa_symbol()) as a real external function, that way
all the potential issues with compile/link-time optimizations of
constant symbol addresses go away, and we can also, if we choose to, add
more sanity-checking of the argument.
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Vivek Goyal <vgoyal@in.ibm.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2007-05-07 23:44:24 +08:00
|
|
|
#define swapper_pg_dir init_level4_pgt
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
extern void paging_init(void);
|
|
|
|
|
2008-03-23 16:03:11 +08:00
|
|
|
#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))
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-01-30 20:32:58 +08:00
|
|
|
struct mm_struct;
|
|
|
|
|
2008-06-25 12:19:22 +08:00
|
|
|
void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte);
|
|
|
|
|
|
|
|
|
2008-01-30 20:32:58 +08:00
|
|
|
static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr,
|
|
|
|
pte_t *ptep)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-01-30 20:32:58 +08:00
|
|
|
*ptep = native_make_pte(0);
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-01-30 20:32:58 +08:00
|
|
|
static inline void native_set_pte(pte_t *ptep, pte_t pte)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-01-30 20:32:58 +08:00
|
|
|
*ptep = pte;
|
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-01-30 20:34:01 +08:00
|
|
|
static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte)
|
|
|
|
{
|
|
|
|
native_set_pte(ptep, pte);
|
|
|
|
}
|
|
|
|
|
2011-01-14 07:46:41 +08:00
|
|
|
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));
|
|
|
|
}
|
|
|
|
|
2008-01-30 20:32:58 +08:00
|
|
|
static inline pte_t native_ptep_get_and_clear(pte_t *xp)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-01-30 20:32:58 +08:00
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
return native_make_pte(xchg(&xp->pte, 0));
|
|
|
|
#else
|
2008-03-23 16:03:11 +08:00
|
|
|
/* native_local_ptep_get_and_clear,
|
|
|
|
but duplicated because of cyclic dependency */
|
2008-01-30 20:32:58 +08:00
|
|
|
pte_t ret = *xp;
|
|
|
|
native_pte_clear(NULL, 0, xp);
|
|
|
|
return ret;
|
|
|
|
#endif
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2011-01-14 07:46:41 +08:00
|
|
|
static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2011-01-14 07:46:41 +08:00
|
|
|
#ifdef CONFIG_SMP
|
|
|
|
return native_make_pmd(xchg(&xp->pmd, 0));
|
|
|
|
#else
|
|
|
|
/* native_local_pmdp_get_and_clear,
|
|
|
|
but duplicated because of cyclic dependency */
|
|
|
|
pmd_t ret = *xp;
|
|
|
|
native_pmd_clear(xp);
|
|
|
|
return ret;
|
|
|
|
#endif
|
2008-01-30 20:32:58 +08:00
|
|
|
}
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-01-30 20:32:58 +08:00
|
|
|
static inline void native_set_pud(pud_t *pudp, pud_t pud)
|
2005-04-17 06:20:36 +08:00
|
|
|
{
|
2008-01-30 20:32:58 +08:00
|
|
|
*pudp = pud;
|
2005-04-17 06:20:36 +08:00
|
|
|
}
|
|
|
|
|
2008-01-30 20:32:58 +08:00
|
|
|
static inline void native_pud_clear(pud_t *pud)
|
|
|
|
{
|
|
|
|
native_set_pud(pud, native_make_pud(0));
|
|
|
|
}
|
2005-09-04 06:55:06 +08:00
|
|
|
|
2008-01-30 20:32:58 +08:00
|
|
|
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
|
|
|
|
{
|
|
|
|
*pgdp = pgd;
|
|
|
|
}
|
2005-11-07 16:59:43 +08:00
|
|
|
|
2008-03-23 16:03:11 +08:00
|
|
|
static inline void native_pgd_clear(pgd_t *pgd)
|
2005-09-04 06:55:06 +08:00
|
|
|
{
|
2008-01-30 20:32:58 +08:00
|
|
|
native_set_pgd(pgd, native_make_pgd(0));
|
2005-09-04 06:55:06 +08:00
|
|
|
}
|
|
|
|
|
2010-05-19 17:42:14 +08:00
|
|
|
extern void sync_global_pgds(unsigned long start, unsigned long end);
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
2008-02-19 23:18:32 +08:00
|
|
|
static inline int pgd_large(pgd_t pgd) { return 0; }
|
2008-06-25 12:19:05 +08:00
|
|
|
#define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* PUD - Level3 access */
|
|
|
|
|
|
|
|
/* PMD - Level 2 access */
|
2008-03-23 16:03:11 +08:00
|
|
|
#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 })
|
2005-04-17 06:20:36 +08:00
|
|
|
#define PTE_FILE_MAX_BITS __PHYSICAL_MASK_SHIFT
|
|
|
|
|
|
|
|
/* PTE - Level 1 access. */
|
|
|
|
|
|
|
|
/* x86-64 always has all page tables mapped. */
|
2008-03-23 16:03:11 +08:00
|
|
|
#define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
|
2010-08-10 08:19:03 +08:00
|
|
|
#define pte_unmap(pte) ((void)(pte))/* NOP */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
MM: Pass a PTE pointer to update_mmu_cache() rather than the PTE itself
On VIVT ARM, when we have multiple shared mappings of the same file
in the same MM, we need to ensure that we have coherency across all
copies. We do this via make_coherent() by making the pages
uncacheable.
This used to work fine, until we allowed highmem with highpte - we
now have a page table which is mapped as required, and is not available
for modification via update_mmu_cache().
Ralf Beache suggested getting rid of the PTE value passed to
update_mmu_cache():
On MIPS update_mmu_cache() calls __update_tlb() which walks pagetables
to construct a pointer to the pte again. Passing a pte_t * is much
more elegant. Maybe we might even replace the pte argument with the
pte_t?
Ben Herrenschmidt would also like the pte pointer for PowerPC:
Passing the ptep in there is exactly what I want. I want that
-instead- of the PTE value, because I have issue on some ppc cases,
for I$/D$ coherency, where set_pte_at() may decide to mask out the
_PAGE_EXEC.
So, pass in the mapped page table pointer into update_mmu_cache(), and
remove the PTE value, updating all implementations and call sites to
suit.
Includes a fix from Stephen Rothwell:
sparc: fix fallout from update_mmu_cache API change
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
2009-12-19 00:40:18 +08:00
|
|
|
#define update_mmu_cache(vma, address, ptep) do { } while (0)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
/* Encode and de-code a swap entry */
|
2008-12-16 19:35:24 +08:00
|
|
|
#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) })
|
2008-03-23 16:03:11 +08:00
|
|
|
#define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) })
|
2008-01-30 20:32:57 +08:00
|
|
|
#define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val })
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-03-23 16:03:11 +08:00
|
|
|
extern int kern_addr_valid(unsigned long addr);
|
2008-02-16 00:29:12 +08:00
|
|
|
extern void cleanup_highmap(void);
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#define HAVE_ARCH_UNMAPPED_AREA
|
2008-01-30 20:31:07 +08:00
|
|
|
#define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#define pgtable_cache_init() do { } while (0)
|
2007-09-22 03:09:41 +08:00
|
|
|
#define check_pgt_cache() do { } while (0)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#define PAGE_AGP PAGE_KERNEL_NOCACHE
|
|
|
|
#define HAVE_PAGE_AGP 1
|
|
|
|
|
|
|
|
/* fs/proc/kcore.c */
|
|
|
|
#define kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK)
|
x86, 64-bit: Clean up user address masking
The discussion about using "access_ok()" in get_user_pages_fast() (see
commit 7f8189068726492950bf1a2dcfd9b51314560abf: "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>
2009-06-21 06:40:00 +08:00
|
|
|
#define kc_offset_to_vaddr(o) ((o) | ~__VIRTUAL_MASK)
|
2005-04-17 06:20:36 +08:00
|
|
|
|
|
|
|
#define __HAVE_ARCH_PTE_SAME
|
2011-01-14 07:46:40 +08:00
|
|
|
|
2007-05-03 01:27:06 +08:00
|
|
|
#endif /* !__ASSEMBLY__ */
|
2005-04-17 06:20:36 +08:00
|
|
|
|
2008-10-23 13:26:29 +08:00
|
|
|
#endif /* _ASM_X86_PGTABLE_64_H */
|