61c77326d1
In x86, access and dirty bits are set automatically by CPU when CPU accesses memory. When we go into the code path of below flush_tlb_fix_spurious_fault(), we already set dirty bit for pte and don't need flush tlb. This might mean tlb entry in some CPUs hasn't dirty bit set, but this doesn't matter. When the CPUs do page write, they will automatically check the bit and no software involved. On the other hand, flush tlb in below position is harmful. Test creates CPU number of threads, each thread writes to a same but random address in same vma range and we measure the total time. Under a 4 socket system, original time is 1.96s, while with the patch, the time is 0.8s. Under a 2 socket system, there is 20% time cut too. perf shows a lot of time are taking to send ipi/handle ipi for tlb flush. Signed-off-by: Shaohua Li <shaohua.li@intel.com> LKML-Reference: <20100816011655.GA362@sli10-desk.sh.intel.com> Acked-by: Suresh Siddha <suresh.b.siddha@intel.com> Cc: Andrea Archangeli <aarcange@redhat.com> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
354 lines
10 KiB
C
354 lines
10 KiB
C
#ifndef _ASM_GENERIC_PGTABLE_H
|
|
#define _ASM_GENERIC_PGTABLE_H
|
|
|
|
#ifndef __ASSEMBLY__
|
|
#ifdef CONFIG_MMU
|
|
|
|
#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. We return whether the PTE actually changed, which
|
|
* in turn instructs the caller to do things like update__mmu_cache.
|
|
* This used to be done in the caller, but sparc needs minor faults to
|
|
* force that call on sun4c so we changed this macro slightly
|
|
*/
|
|
#define ptep_set_access_flags(__vma, __address, __ptep, __entry, __dirty) \
|
|
({ \
|
|
int __changed = !pte_same(*(__ptep), __entry); \
|
|
if (__changed) { \
|
|
set_pte_at((__vma)->vm_mm, (__address), __ptep, __entry); \
|
|
flush_tlb_page(__vma, __address); \
|
|
} \
|
|
__changed; \
|
|
})
|
|
#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_GET_AND_CLEAR
|
|
#define ptep_get_and_clear(__mm, __address, __ptep) \
|
|
({ \
|
|
pte_t __pte = *(__ptep); \
|
|
pte_clear((__mm), (__address), (__ptep)); \
|
|
__pte; \
|
|
})
|
|
#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
|
|
|
|
/*
|
|
* Some architectures may be able to avoid expensive synchronization
|
|
* primitives when modifications are made to PTE's which are already
|
|
* not present, or in the process of an address space destruction.
|
|
*/
|
|
#ifndef __HAVE_ARCH_PTE_CLEAR_NOT_PRESENT_FULL
|
|
#define pte_clear_not_present_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) \
|
|
({ \
|
|
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
|
|
struct mm_struct;
|
|
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_DIRTY
|
|
#define page_test_dirty(page) (0)
|
|
#endif
|
|
|
|
#ifndef __HAVE_ARCH_PAGE_CLEAR_DIRTY
|
|
#define page_clear_dirty(page) do { } while (0)
|
|
#endif
|
|
|
|
#ifndef __HAVE_ARCH_PAGE_TEST_DIRTY
|
|
#define pte_maybe_dirty(pte) pte_dirty(pte)
|
|
#else
|
|
#define pte_maybe_dirty(pte) (1)
|
|
#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_MOVE_PTE
|
|
#define move_pte(pte, prot, old_addr, new_addr) (pte)
|
|
#endif
|
|
|
|
#ifndef flush_tlb_fix_spurious_fault
|
|
#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
|
|
#endif
|
|
|
|
#ifndef pgprot_noncached
|
|
#define pgprot_noncached(prot) (prot)
|
|
#endif
|
|
|
|
#ifndef pgprot_writecombine
|
|
#define pgprot_writecombine pgprot_noncached
|
|
#endif
|
|
|
|
/*
|
|
* 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.
|
|
*/
|
|
|
|
#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;
|
|
}
|
|
|
|
static inline pte_t __ptep_modify_prot_start(struct mm_struct *mm,
|
|
unsigned long addr,
|
|
pte_t *ptep)
|
|
{
|
|
/*
|
|
* Get the current pte state, but zero it out to make it
|
|
* non-present, preventing the hardware from asynchronously
|
|
* updating it.
|
|
*/
|
|
return ptep_get_and_clear(mm, addr, ptep);
|
|
}
|
|
|
|
static inline void __ptep_modify_prot_commit(struct mm_struct *mm,
|
|
unsigned long addr,
|
|
pte_t *ptep, pte_t pte)
|
|
{
|
|
/*
|
|
* The pte is non-present, so there's no hardware state to
|
|
* preserve.
|
|
*/
|
|
set_pte_at(mm, addr, ptep, pte);
|
|
}
|
|
|
|
#ifndef __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
|
|
/*
|
|
* Start a pte protection read-modify-write transaction, which
|
|
* protects against asynchronous hardware modifications to the pte.
|
|
* The intention is not to prevent the hardware from making pte
|
|
* updates, but to prevent any updates it may make from being lost.
|
|
*
|
|
* This does not protect against other software modifications of the
|
|
* pte; the appropriate pte lock must be held over the transation.
|
|
*
|
|
* Note that this interface is intended to be batchable, meaning that
|
|
* ptep_modify_prot_commit may not actually update the pte, but merely
|
|
* queue the update to be done at some later time. The update must be
|
|
* actually committed before the pte lock is released, however.
|
|
*/
|
|
static inline pte_t ptep_modify_prot_start(struct mm_struct *mm,
|
|
unsigned long addr,
|
|
pte_t *ptep)
|
|
{
|
|
return __ptep_modify_prot_start(mm, addr, ptep);
|
|
}
|
|
|
|
/*
|
|
* Commit an update to a pte, leaving any hardware-controlled bits in
|
|
* the PTE unmodified.
|
|
*/
|
|
static inline void ptep_modify_prot_commit(struct mm_struct *mm,
|
|
unsigned long addr,
|
|
pte_t *ptep, pte_t pte)
|
|
{
|
|
__ptep_modify_prot_commit(mm, addr, ptep, pte);
|
|
}
|
|
#endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
|
|
#endif /* CONFIG_MMU */
|
|
|
|
/*
|
|
* A facility to provide lazy MMU batching. This allows PTE updates and
|
|
* page invalidations to be delayed until a call to leave lazy MMU mode
|
|
* is issued. Some architectures may benefit from doing this, and it is
|
|
* beneficial for both shadow and direct mode hypervisors, which may batch
|
|
* the PTE updates which happen during this window. Note that using this
|
|
* interface requires that read hazards be removed from the code. A read
|
|
* hazard could result in the direct mode hypervisor case, since the actual
|
|
* write to the page tables may not yet have taken place, so reads though
|
|
* a raw PTE pointer after it has been modified are not guaranteed to be
|
|
* up to date. This mode can only be entered and left under the protection of
|
|
* the page table locks for all page tables which may be modified. In the UP
|
|
* case, this is required so that preemption is disabled, and in the SMP case,
|
|
* it must synchronize the delayed page table writes properly on other CPUs.
|
|
*/
|
|
#ifndef __HAVE_ARCH_ENTER_LAZY_MMU_MODE
|
|
#define arch_enter_lazy_mmu_mode() do {} while (0)
|
|
#define arch_leave_lazy_mmu_mode() do {} while (0)
|
|
#define arch_flush_lazy_mmu_mode() do {} while (0)
|
|
#endif
|
|
|
|
/*
|
|
* A facility to provide batching of the reload of page tables and
|
|
* other process state with the actual context switch code for
|
|
* paravirtualized guests. By convention, only one of the batched
|
|
* update (lazy) modes (CPU, MMU) should be active at any given time,
|
|
* entry should never be nested, and entry and exits should always be
|
|
* paired. This is for sanity of maintaining and reasoning about the
|
|
* kernel code. In this case, the exit (end of the context switch) is
|
|
* in architecture-specific code, and so doesn't need a generic
|
|
* definition.
|
|
*/
|
|
#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH
|
|
#define arch_start_context_switch(prev) do {} while (0)
|
|
#endif
|
|
|
|
#ifndef __HAVE_PFNMAP_TRACKING
|
|
/*
|
|
* Interface that can be used by architecture code to keep track of
|
|
* memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
|
|
*
|
|
* track_pfn_vma_new is called when a _new_ pfn mapping is being established
|
|
* for physical range indicated by pfn and size.
|
|
*/
|
|
static inline int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
|
|
unsigned long pfn, unsigned long size)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Interface that can be used by architecture code to keep track of
|
|
* memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
|
|
*
|
|
* track_pfn_vma_copy is called when vma that is covering the pfnmap gets
|
|
* copied through copy_page_range().
|
|
*/
|
|
static inline int track_pfn_vma_copy(struct vm_area_struct *vma)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Interface that can be used by architecture code to keep track of
|
|
* memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
|
|
*
|
|
* untrack_pfn_vma is called while unmapping a pfnmap for a region.
|
|
* untrack can be called for a specific region indicated by pfn and size or
|
|
* can be for the entire vma (in which case size can be zero).
|
|
*/
|
|
static inline void untrack_pfn_vma(struct vm_area_struct *vma,
|
|
unsigned long pfn, unsigned long size)
|
|
{
|
|
}
|
|
#else
|
|
extern int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
|
|
unsigned long pfn, unsigned long size);
|
|
extern int track_pfn_vma_copy(struct vm_area_struct *vma);
|
|
extern void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
|
|
unsigned long size);
|
|
#endif
|
|
|
|
#endif /* !__ASSEMBLY__ */
|
|
|
|
#endif /* _ASM_GENERIC_PGTABLE_H */
|