Re: [PATCH 1/3] mm: tracking shared dirty pages

[Peter Zijlstra <a.p.zijlstra@chello.nl>]

On Thu, 2006-05-25 at 09:21 -0700, Christoph Lameter wrote:
> On Thu, 25 May 2006, Peter Zijlstra wrote:
> 
> > @@ -1446,12 +1447,13 @@ static int do_wp_page(struct mm_struct *
> >  
> > -	if (unlikely(vma->vm_flags & VM_SHARED)) {
> > +	if (vma->vm_flags & VM_SHARED) {
> 
> You add this unlikely later again it seems. Why remove in the first place?

I'm not sure I follow you, are you suggesting that we'll find the
condition to be unlikely still, even with most of the shared mappings
trapping this branch?

> > +static int page_mkclean_one(struct page *page, struct vm_area_struct *vma)
> > +	entry = pte_mkclean(pte_wrprotect(*pte));
> > +	ptep_establish(vma, address, pte, entry);
> 
> > +	update_mmu_cache(vma, address, entry);
> 
> You only changed protections on an estisting pte and ptep_establish 
> already flushed the tlb. No need to call update_mmu_cache. See how 
> change_protection() in mm/mprotect.c does it.

OK, will check.

> > +	lazy_mmu_prot_update(entry);
> 
> Needed.

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/