On Tue, Jun 07, 2022 at 07:37:10PM +1200, Barry Song wrote:
> On Mon, Jun 6, 2022 at 9:25 PM Barry Song <21cnbao@xxxxxxxxx> wrote:
> > On Wed, May 18, 2022 at 4:49 PM Yu Zhao <yuzhao@xxxxxxxxxx> wrote:
> > > diff --git a/mm/rmap.c b/mm/rmap.c
> > > index fedb82371efe..7cb7ef29088a 100644
> > > --- a/mm/rmap.c
> > > +++ b/mm/rmap.c
> > > @@ -73,6 +73,7 @@
> > > #include <linux/page_idle.h>
> > > #include <linux/memremap.h>
> > > #include <linux/userfaultfd_k.h>
> > > +#include <linux/mm_inline.h>
> > >
> > > #include <asm/tlbflush.h>
> > >
> > > @@ -821,6 +822,12 @@ static bool folio_referenced_one(struct folio *folio,
> > > }
> > >
> > > if (pvmw.pte) {
> > > + if (lru_gen_enabled() && pte_young(*pvmw.pte) &&
> > > + !(vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ))) {
> > > + lru_gen_look_around(&pvmw);
> > > + referenced++;
> > > + }
> > > +
> > > if (ptep_clear_flush_young_notify(vma, address,
> >
> > Hello, Yu.
> > look_around() is calling ptep_test_and_clear_young(pvmw->vma, addr, pte + i)
> > only without flush and notify. for flush, there is a tlb operation for arm64:
> > static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
> > unsigned long address, pte_t *ptep)
> > {
> > int young = ptep_test_and_clear_young(vma, address, ptep);
> >
> > if (young) {
> > /*
> > * We can elide the trailing DSB here since the worst that can
> > * happen is that a CPU continues to use the young entry in its
> > * TLB and we mistakenly reclaim the associated page. The
> > * window for such an event is bounded by the next
> > * context-switch, which provides a DSB to complete the TLB
> > * invalidation.
> > */
> > flush_tlb_page_nosync(vma, address);
> > }
> >
> > return young;
> > }
> >
> > Does it mean the current kernel is over cautious? is it
> > safe to call ptep_test_and_clear_young() only?
>
> I can't really explain why we are getting a random app/java vm crash in monkey
> test by using ptep_test_and_clear_young() only in lru_gen_look_around() on an
> armv8-a machine without hardware PTE young support.
>
> Moving to ptep_clear_flush_young() in look_around can make the random
> hang disappear according to zhanyuan(Cc-ed).
>
> On x86, ptep_clear_flush_young() is exactly ptep_test_and_clear_young()
> after
> 'commit b13b1d2d8692 ("x86/mm: In the PTE swapout page reclaim case clear
> the accessed bit instead of flushing the TLB")'
>
> But on arm64, they are different. according to Will's comments in this
> thread which
> tried to make arm64 same with x86,
> https://www.mail-archive.com/linux-kernel@xxxxxxxxxxxxxxx/msg1793881.html
>
> "
> This is blindly copied from x86 and isn't true for us: we don't invalidate
> the TLB on context switch. That means our window for keeping the stale
> entries around is potentially much bigger and might not be a great idea.
>
> If we roll a TLB invalidation routine without the trailing DSB, what sort of
> performance does that get you?
> "
> We shouldn't think ptep_clear_flush_young() is safe enough in LRU to
> clear PTE young? Any comments from Will?
Given that this issue is specific to the multi-gen LRU work, I think Yu is
the best person to comment. However, looking quickly at your analysis above,
I wonder if the code is relying on this sequence:
ptep_test_and_clear_young(vma, address, ptep);
ptep_clear_flush_young(vma, address, ptep);
to invalidate the TLB. On arm64, that won't be the case, as the invalidation
in ptep_clear_flush_young() is predicated on the pte being young (and this
patches the generic implementation in mm/pgtable-generic.c. In fact, that
second function call is always going to be a no-op unless the pte became
young again in the middle.
Will
