Re: [PATCH] mm: mmu_gather: remove __tlb_reset_range() for force flush

[Yang Shi]

On 5/9/19 3:54 AM, Peter Zijlstra wrote:
> On Thu, May 09, 2019 at 12:38:13PM +0200, Peter Zijlstra wrote:
>
> > That's tlb->cleared_p*, and yes agreed. That is, right until some
> > architecture has level dependent TLBI instructions, at which point we'll
> > need to have them all set instead of cleared.
> > Anyway; am I correct in understanding that the actual problem is that
> > we've cleared freed_tables and the ARM64 tlb_flush() will then not
> > invalidate the cache and badness happens?
> >
> > Because so far nobody has actually provided a coherent description of
> > the actual problem we're trying to solve. But I'm thinking something
> > like the below ought to do.
> There's another 'fun' issue I think. For architectures like ARM that
> have range invalidation and care about VM_EXEC for I$ invalidation, the
> below doesn't quite work right either.
>
> I suspect we also have to force: tlb->vma_exec = 1.

Isn't the below code in tlb_flush enough to guarantee this?

...
} else if (tlb->end) {
ÂÂÂÂÂÂÂÂÂÂÂÂÂÂ struct vm_area_struct vma = {
ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ .vm_mm = tlb->mm,
ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ .vm_flags = (tlb->vma_exec ? VM_EXECÂÂÂ : 0) |
ÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂÂ (tlb->vma_huge ? VM_HUGETLB : 0),
ÂÂÂÂÂÂÂÂÂÂÂÂÂÂ };
...

> And I don't think there's an architecture that cares, but depending on
> details I can construct cases where any setting of tlb->vm_hugetlb is
> wrong, so that is _awesome_. But I suspect the sane thing for now is to
> force it 0.
>
> > diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
> > index 99740e1dd273..fe768f8d612e 100644
> > --- a/mm/mmu_gather.c
> > +++ b/mm/mmu_gather.c
> > @@ -244,15 +244,20 @@ void tlb_finish_mmu(struct mmu_gather *tlb,
> >   		unsigned long start, unsigned long end)
> >   {
> >   	/*
> > -	 * If there are parallel threads are doing PTE changes on same range
> > -	 * under non-exclusive lock(e.g., mmap_sem read-side) but defer TLB
> > -	 * flush by batching, a thread has stable TLB entry can fail to flush
> > -	 * the TLB by observing pte_none|!pte_dirty, for example so flush TLB
> > -	 * forcefully if we detect parallel PTE batching threads.
> > +	 * Sensible comment goes here..
> >   	 */
> > -	if (mm_tlb_flush_nested(tlb->mm)) {
> > -		__tlb_reset_range(tlb);
> > -		__tlb_adjust_range(tlb, start, end - start);
> > +	if (mm_tlb_flush_nested(tlb->mm) && !tlb->full_mm) {
> > +		/*
> > +		 * Since we're can't tell what we actually should have
> > +		 * flushed flush everything in the given range.
> > +		 */
> > +		tlb->start = start;
> > +		tlb->end = end;
> > +		tlb->freed_tables = 1;
> > +		tlb->cleared_ptes = 1;
> > +		tlb->cleared_pmds = 1;
> > +		tlb->cleared_puds = 1;
> > +		tlb->cleared_p4ds = 1;
> >   	}
> >   
> >   	tlb_flush_mmu(tlb);