powerpc/mm/radix: Use ptep_get_and_clear_full when clearing pte for full mm
This helps us to do some optimization for application exit case, where we can skip the DD1 style pte update sequence. Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Tested-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
This commit is contained in:
parent
ca94573b9c
commit
f4894b80b1
|
@ -371,6 +371,23 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm,
|
||||||
return __pte(old);
|
return __pte(old);
|
||||||
}
|
}
|
||||||
|
|
||||||
|
#define __HAVE_ARCH_PTEP_GET_AND_CLEAR_FULL
|
||||||
|
static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm,
|
||||||
|
unsigned long addr,
|
||||||
|
pte_t *ptep, int full)
|
||||||
|
{
|
||||||
|
if (full && radix_enabled()) {
|
||||||
|
/*
|
||||||
|
* Let's skip the DD1 style pte update here. We know that
|
||||||
|
* this is a full mm pte clear and hence can be sure there is
|
||||||
|
* no parallel set_pte.
|
||||||
|
*/
|
||||||
|
return radix__ptep_get_and_clear_full(mm, addr, ptep, full);
|
||||||
|
}
|
||||||
|
return ptep_get_and_clear(mm, addr, ptep);
|
||||||
|
}
|
||||||
|
|
||||||
|
|
||||||
static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
|
static inline void pte_clear(struct mm_struct *mm, unsigned long addr,
|
||||||
pte_t * ptep)
|
pte_t * ptep)
|
||||||
{
|
{
|
||||||
|
|
|
@ -139,7 +139,7 @@ static inline unsigned long radix__pte_update(struct mm_struct *mm,
|
||||||
|
|
||||||
unsigned long new_pte;
|
unsigned long new_pte;
|
||||||
|
|
||||||
old_pte = __radix_pte_update(ptep, ~0, 0);
|
old_pte = __radix_pte_update(ptep, ~0ul, 0);
|
||||||
/*
|
/*
|
||||||
* new value of pte
|
* new value of pte
|
||||||
*/
|
*/
|
||||||
|
@ -157,6 +157,27 @@ static inline unsigned long radix__pte_update(struct mm_struct *mm,
|
||||||
return old_pte;
|
return old_pte;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
static inline pte_t radix__ptep_get_and_clear_full(struct mm_struct *mm,
|
||||||
|
unsigned long addr,
|
||||||
|
pte_t *ptep, int full)
|
||||||
|
{
|
||||||
|
unsigned long old_pte;
|
||||||
|
|
||||||
|
if (full) {
|
||||||
|
/*
|
||||||
|
* If we are trying to clear the pte, we can skip
|
||||||
|
* the DD1 pte update sequence and batch the tlb flush. The
|
||||||
|
* tlb flush batching is done by mmu gather code. We
|
||||||
|
* still keep the cmp_xchg update to make sure we get
|
||||||
|
* correct R/C bit which might be updated via Nest MMU.
|
||||||
|
*/
|
||||||
|
old_pte = __radix_pte_update(ptep, ~0ul, 0);
|
||||||
|
} else
|
||||||
|
old_pte = radix__pte_update(mm, addr, ptep, ~0ul, 0, 0);
|
||||||
|
|
||||||
|
return __pte(old_pte);
|
||||||
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* Set the dirty and/or accessed bits atomically in a linux PTE, this
|
* Set the dirty and/or accessed bits atomically in a linux PTE, this
|
||||||
* function doesn't need to invalidate tlb.
|
* function doesn't need to invalidate tlb.
|
||||||
|
|
Loading…
Reference in New Issue