2005-04-17 06:20:36 +08:00
|
|
|
#ifndef _ASM_GENERIC_PGTABLE_H
|
|
|
|
#define _ASM_GENERIC_PGTABLE_H
|
|
|
|
|
2006-09-26 14:32:29 +08:00
|
|
|
#ifndef __ASSEMBLY__
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#ifndef __HAVE_ARCH_PTEP_ESTABLISH
|
|
|
|
/*
|
|
|
|
* Establish a new mapping:
|
|
|
|
* - flush the old one
|
|
|
|
* - update the page tables
|
|
|
|
* - inform the TLB about the new one
|
|
|
|
*
|
2005-10-30 09:16:41 +08:00
|
|
|
* We hold the mm semaphore for reading, and the pte lock.
|
2005-04-17 06:20:36 +08:00
|
|
|
*
|
|
|
|
* Note: the old pte is known to not be writable, so we don't need to
|
|
|
|
* worry about dirty bits etc getting lost.
|
|
|
|
*/
|
|
|
|
#ifndef __HAVE_ARCH_SET_PTE_ATOMIC
|
|
|
|
#define ptep_establish(__vma, __address, __ptep, __entry) \
|
|
|
|
do { \
|
|
|
|
set_pte_at((__vma)->vm_mm, (__address), __ptep, __entry); \
|
|
|
|
flush_tlb_page(__vma, __address); \
|
|
|
|
} while (0)
|
|
|
|
#else /* __HAVE_ARCH_SET_PTE_ATOMIC */
|
|
|
|
#define ptep_establish(__vma, __address, __ptep, __entry) \
|
|
|
|
do { \
|
|
|
|
set_pte_atomic(__ptep, __entry); \
|
|
|
|
flush_tlb_page(__vma, __address); \
|
|
|
|
} while (0)
|
|
|
|
#endif /* __HAVE_ARCH_SET_PTE_ATOMIC */
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
|
|
|
|
/*
|
|
|
|
* Largely same as above, but only sets the access flags (dirty,
|
|
|
|
* accessed, and writable). Furthermore, we know it always gets set
|
|
|
|
* to a "more permissive" setting, which allows most architectures
|
|
|
|
* to optimize this.
|
|
|
|
*/
|
|
|
|
#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
|
|
|
|
do { \
|
|
|
|
set_pte_at((__vma)->vm_mm, (__address), __ptep, __entry); \
|
|
|
|
flush_tlb_page(__vma, __address); \
|
|
|
|
} while (0)
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
|
|
|
|
#define ptep_test_and_clear_young(__vma, __address, __ptep) \
|
|
|
|
({ \
|
|
|
|
pte_t __pte = *(__ptep); \
|
|
|
|
int r = 1; \
|
|
|
|
if (!pte_young(__pte)) \
|
|
|
|
r = 0; \
|
|
|
|
else \
|
|
|
|
set_pte_at((__vma)->vm_mm, (__address), \
|
|
|
|
(__ptep), pte_mkold(__pte)); \
|
|
|
|
r; \
|
|
|
|
})
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
|
|
|
|
#define ptep_clear_flush_young(__vma, __address, __ptep) \
|
|
|
|
({ \
|
|
|
|
int __young; \
|
|
|
|
__young = ptep_test_and_clear_young(__vma, __address, __ptep); \
|
|
|
|
if (__young) \
|
|
|
|
flush_tlb_page(__vma, __address); \
|
|
|
|
__young; \
|
|
|
|
})
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY
|
|
|
|
#define ptep_test_and_clear_dirty(__vma, __address, __ptep) \
|
|
|
|
({ \
|
|
|
|
pte_t __pte = *__ptep; \
|
|
|
|
int r = 1; \
|
|
|
|
if (!pte_dirty(__pte)) \
|
|
|
|
r = 0; \
|
|
|
|
else \
|
|
|
|
set_pte_at((__vma)->vm_mm, (__address), (__ptep), \
|
|
|
|
pte_mkclean(__pte)); \
|
|
|
|
r; \
|
|
|
|
})
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PTEP_CLEAR_DIRTY_FLUSH
|
|
|
|
#define ptep_clear_flush_dirty(__vma, __address, __ptep) \
|
|
|
|
({ \
|
|
|
|
int __dirty; \
|
|
|
|
__dirty = ptep_test_and_clear_dirty(__vma, __address, __ptep); \
|
|
|
|
if (__dirty) \
|
|
|
|
flush_tlb_page(__vma, __address); \
|
|
|
|
__dirty; \
|
|
|
|
})
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR
|
|
|
|
#define ptep_get_and_clear(__mm, __address, __ptep) \
|
|
|
|
({ \
|
|
|
|
pte_t __pte = *(__ptep); \
|
|
|
|
pte_clear((__mm), (__address), (__ptep)); \
|
|
|
|
__pte; \
|
|
|
|
})
|
|
|
|
#endif
|
|
|
|
|
[PATCH] x86: ptep_clear optimization
Add a new accessor for PTEs, which passes the full hint from the mmu_gather
struct; this allows architectures with hardware pagetables to optimize away
atomic PTE operations when destroying an address space. Removing the
locked operation should allow better pipelining of memory access in this
loop. I measured an average savings of 30-35 cycles per zap_pte_range on
the first 500 destructions on Pentium-M, but I believe the optimization
would win more on older processors which still assert the bus lock on xchg
for an exclusive cacheline.
Update: I made some new measurements, and this saves exactly 26 cycles over
ptep_get_and_clear on Pentium M. On P4, with a PAE kernel, this saves 180
cycles per ptep_get_and_clear, for a whopping 92160 cycles savings for a
full address space destruction.
pte_clear_full is not yet used, but is provided for future optimizations
(in particular, when running inside of a hypervisor that queues page table
updates, the full hint allows us to avoid queueing unnecessary page table
update for an address space in the process of being destroyed.
This is not a huge win, but it does help a bit, and sets the stage for
further hypervisor optimization of the mm layer on all architectures.
Signed-off-by: Zachary Amsden <zach@vmware.com>
Cc: Christoph Lameter <christoph@lameter.com>
Cc: <linux-mm@kvack.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2005-09-04 06:55:04 +08:00
|
|
|
#ifndef __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
|
|
|
|
#define ptep_get_and_clear_full(__mm, __address, __ptep, __full) \
|
|
|
|
({ \
|
|
|
|
pte_t __pte; \
|
|
|
|
__pte = ptep_get_and_clear((__mm), (__address), (__ptep)); \
|
|
|
|
__pte; \
|
|
|
|
})
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PTE_CLEAR_FULL
|
|
|
|
#define pte_clear_full(__mm, __address, __ptep, __full) \
|
|
|
|
do { \
|
|
|
|
pte_clear((__mm), (__address), (__ptep)); \
|
|
|
|
} while (0)
|
|
|
|
#endif
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
|
|
|
|
#define ptep_clear_flush(__vma, __address, __ptep) \
|
|
|
|
({ \
|
|
|
|
pte_t __pte; \
|
|
|
|
__pte = ptep_get_and_clear((__vma)->vm_mm, __address, __ptep); \
|
|
|
|
flush_tlb_page(__vma, __address); \
|
|
|
|
__pte; \
|
|
|
|
})
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PTEP_SET_WRPROTECT
|
2005-11-07 16:59:43 +08:00
|
|
|
struct mm_struct;
|
2005-04-17 06:20:36 +08:00
|
|
|
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep)
|
|
|
|
{
|
|
|
|
pte_t old_pte = *ptep;
|
|
|
|
set_pte_at(mm, address, ptep, pte_wrprotect(old_pte));
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PTE_SAME
|
|
|
|
#define pte_same(A,B) (pte_val(A) == pte_val(B))
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PAGE_TEST_AND_CLEAR_DIRTY
|
|
|
|
#define page_test_and_clear_dirty(page) (0)
|
2005-06-22 08:15:13 +08:00
|
|
|
#define pte_maybe_dirty(pte) pte_dirty(pte)
|
|
|
|
#else
|
|
|
|
#define pte_maybe_dirty(pte) (1)
|
2005-04-17 06:20:36 +08:00
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PAGE_TEST_AND_CLEAR_YOUNG
|
|
|
|
#define page_test_and_clear_young(page) (0)
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_PGD_OFFSET_GATE
|
|
|
|
#define pgd_offset_gate(mm, addr) pgd_offset(mm, addr)
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef __HAVE_ARCH_LAZY_MMU_PROT_UPDATE
|
|
|
|
#define lazy_mmu_prot_update(pte) do { } while (0)
|
|
|
|
#endif
|
|
|
|
|
2006-06-02 08:47:25 +08:00
|
|
|
#ifndef __HAVE_ARCH_MOVE_PTE
|
2005-09-28 12:45:18 +08:00
|
|
|
#define move_pte(pte, prot, old_addr, new_addr) (pte)
|
|
|
|
#endif
|
|
|
|
|
2005-04-17 06:20:36 +08:00
|
|
|
/*
|
2005-04-20 04:29:17 +08:00
|
|
|
* When walking page tables, get the address of the next boundary,
|
|
|
|
* or the end address of the range if that comes earlier. Although no
|
|
|
|
* vma end wraps to 0, rounded up __boundary may wrap to 0 throughout.
|
2005-04-17 06:20:36 +08:00
|
|
|
*/
|
|
|
|
|
|
|
|
#define pgd_addr_end(addr, end) \
|
|
|
|
({ unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK; \
|
|
|
|
(__boundary - 1 < (end) - 1)? __boundary: (end); \
|
|
|
|
})
|
|
|
|
|
|
|
|
#ifndef pud_addr_end
|
|
|
|
#define pud_addr_end(addr, end) \
|
|
|
|
({ unsigned long __boundary = ((addr) + PUD_SIZE) & PUD_MASK; \
|
|
|
|
(__boundary - 1 < (end) - 1)? __boundary: (end); \
|
|
|
|
})
|
|
|
|
#endif
|
|
|
|
|
|
|
|
#ifndef pmd_addr_end
|
|
|
|
#define pmd_addr_end(addr, end) \
|
|
|
|
({ unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK; \
|
|
|
|
(__boundary - 1 < (end) - 1)? __boundary: (end); \
|
|
|
|
})
|
|
|
|
#endif
|
|
|
|
|
|
|
|
/*
|
|
|
|
* When walking page tables, we usually want to skip any p?d_none entries;
|
|
|
|
* and any p?d_bad entries - reporting the error before resetting to none.
|
|
|
|
* Do the tests inline, but report and clear the bad entry in mm/memory.c.
|
|
|
|
*/
|
|
|
|
void pgd_clear_bad(pgd_t *);
|
|
|
|
void pud_clear_bad(pud_t *);
|
|
|
|
void pmd_clear_bad(pmd_t *);
|
|
|
|
|
|
|
|
static inline int pgd_none_or_clear_bad(pgd_t *pgd)
|
|
|
|
{
|
|
|
|
if (pgd_none(*pgd))
|
|
|
|
return 1;
|
|
|
|
if (unlikely(pgd_bad(*pgd))) {
|
|
|
|
pgd_clear_bad(pgd);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int pud_none_or_clear_bad(pud_t *pud)
|
|
|
|
{
|
|
|
|
if (pud_none(*pud))
|
|
|
|
return 1;
|
|
|
|
if (unlikely(pud_bad(*pud))) {
|
|
|
|
pud_clear_bad(pud);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline int pmd_none_or_clear_bad(pmd_t *pmd)
|
|
|
|
{
|
|
|
|
if (pmd_none(*pmd))
|
|
|
|
return 1;
|
|
|
|
if (unlikely(pmd_bad(*pmd))) {
|
|
|
|
pmd_clear_bad(pmd);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
#endif /* !__ASSEMBLY__ */
|
|
|
|
|
|
|
|
#endif /* _ASM_GENERIC_PGTABLE_H */
|