| Message ID | 20220907180144.555485-2-shy828301@gmail.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | [v2,1/2] mm: gup: fix the fast GUP race against THP collapse | expand |
On 07.09.22 20:01, Yang Shi wrote: > The IPI broadcast is used to serialize against fast-GUP, but fast-GUP > will move to use RCU instead of disabling local interrupts in fast-GUP. > Using an IPI is the old-styled way of serializing against fast-GUP > although it still works as expected now. > > And fast-GUP now fixed the potential race with THP collapse by checking > whether PMD is changed or not. So IPI broadcast in radix pmd collapse > flush is not necessary anymore. But it is still needed for hash TLB. > > Suggested-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> > Signed-off-by: Yang Shi <shy828301@gmail.com> > --- > arch/powerpc/mm/book3s64/radix_pgtable.c | 9 --------- > 1 file changed, 9 deletions(-) > > diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c > index 698274109c91..e712f80fe189 100644 > --- a/arch/powerpc/mm/book3s64/radix_pgtable.c > +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c > @@ -937,15 +937,6 @@ pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addre > pmd = *pmdp; > pmd_clear(pmdp); > > - /* > - * pmdp collapse_flush need to ensure that there are no parallel gup > - * walk after this call. This is needed so that we can have stable > - * page ref count when collapsing a page. We don't allow a collapse page > - * if we have gup taken on the page. We can ensure that by sending IPI > - * because gup walk happens with IRQ disabled. > - */ > - serialize_against_pte_lookup(vma->vm_mm); > - > radix__flush_tlb_collapsed_pmd(vma->vm_mm, address); > > return pmd; Makes sense to me Acked-by: David Hildenbrand <david@redhat.com>
On Wed, Sep 07, 2022 at 11:01:44AM -0700, Yang Shi wrote: > The IPI broadcast is used to serialize against fast-GUP, but fast-GUP > will move to use RCU instead of disabling local interrupts in fast-GUP. > Using an IPI is the old-styled way of serializing against fast-GUP > although it still works as expected now. > > And fast-GUP now fixed the potential race with THP collapse by checking > whether PMD is changed or not. So IPI broadcast in radix pmd collapse > flush is not necessary anymore. But it is still needed for hash TLB. > > Suggested-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> > Signed-off-by: Yang Shi <shy828301@gmail.com> Acked-by: Peter Xu <peterx@redhat.com>
diff --git a/arch/powerpc/mm/book3s64/radix_pgtable.c b/arch/powerpc/mm/book3s64/radix_pgtable.c index 698274109c91..e712f80fe189 100644 --- a/arch/powerpc/mm/book3s64/radix_pgtable.c +++ b/arch/powerpc/mm/book3s64/radix_pgtable.c @@ -937,15 +937,6 @@ pmd_t radix__pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long addre pmd = *pmdp; pmd_clear(pmdp); - /* - * pmdp collapse_flush need to ensure that there are no parallel gup - * walk after this call. This is needed so that we can have stable - * page ref count when collapsing a page. We don't allow a collapse page - * if we have gup taken on the page. We can ensure that by sending IPI - * because gup walk happens with IRQ disabled. - */ - serialize_against_pte_lookup(vma->vm_mm); - radix__flush_tlb_collapsed_pmd(vma->vm_mm, address); return pmd;
The IPI broadcast is used to serialize against fast-GUP, but fast-GUP will move to use RCU instead of disabling local interrupts in fast-GUP. Using an IPI is the old-styled way of serializing against fast-GUP although it still works as expected now. And fast-GUP now fixed the potential race with THP collapse by checking whether PMD is changed or not. So IPI broadcast in radix pmd collapse flush is not necessary anymore. But it is still needed for hash TLB. Suggested-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Signed-off-by: Yang Shi <shy828301@gmail.com> --- arch/powerpc/mm/book3s64/radix_pgtable.c | 9 --------- 1 file changed, 9 deletions(-)