[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>
This commit is contained in:
parent
fa5b08d5f8
commit
a600388d28
|
@ -101,6 +101,22 @@ do { \
|
|||
})
|
||||
#endif
|
||||
|
||||
#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
|
||||
|
||||
#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
|
||||
#define ptep_clear_flush(__vma, __address, __ptep) \
|
||||
({ \
|
||||
|
|
|
@ -260,6 +260,18 @@ static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned
|
|||
return test_and_clear_bit(_PAGE_BIT_ACCESSED, &ptep->pte_low);
|
||||
}
|
||||
|
||||
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) {
|
||||
pte = *ptep;
|
||||
*ptep = __pte(0);
|
||||
} else {
|
||||
pte = ptep_get_and_clear(mm, addr, ptep);
|
||||
}
|
||||
return pte;
|
||||
}
|
||||
|
||||
static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
|
||||
{
|
||||
clear_bit(_PAGE_BIT_RW, &ptep->pte_low);
|
||||
|
@ -417,6 +429,7 @@ extern void noexec_setup(const char *str);
|
|||
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG
|
||||
#define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_DIRTY
|
||||
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR
|
||||
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
|
||||
#define __HAVE_ARCH_PTEP_SET_WRPROTECT
|
||||
#define __HAVE_ARCH_PTE_SAME
|
||||
#include <asm-generic/pgtable.h>
|
||||
|
|
|
@ -562,7 +562,8 @@ static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
|
|||
page->index > details->last_index))
|
||||
continue;
|
||||
}
|
||||
ptent = ptep_get_and_clear(tlb->mm, addr, pte);
|
||||
ptent = ptep_get_and_clear_full(tlb->mm, addr, pte,
|
||||
tlb->fullmm);
|
||||
tlb_remove_tlb_entry(tlb, pte, addr);
|
||||
if (unlikely(!page))
|
||||
continue;
|
||||
|
@ -590,7 +591,7 @@ static void zap_pte_range(struct mmu_gather *tlb, pmd_t *pmd,
|
|||
continue;
|
||||
if (!pte_file(ptent))
|
||||
free_swap_and_cache(pte_to_swp_entry(ptent));
|
||||
pte_clear(tlb->mm, addr, pte);
|
||||
pte_clear_full(tlb->mm, addr, pte, tlb->fullmm);
|
||||
} while (pte++, addr += PAGE_SIZE, addr != end);
|
||||
pte_unmap(pte - 1);
|
||||
}
|
||||
|
|
Loading…
Reference in New Issue