Messages in this thread | | | Date | Tue, 3 Feb 2009 10:57:44 +0900 | From | MinChan Kim <> | Subject | Re: [PATCH] fix mlocked page counter mismatch |
| |
> > Thank you for testing. > > I did test this on 29-rc3 on a 4 socket x dual core x86_64 platform and > it seems to resolve the statistics miscount. How do you want to > proceed. Do you want to repost with this version of patch? Or shall I?
I will repost this patch with your ACK and tested-by if you allow it.
> > Regards, > Lee > > > > > > > > > > Index: linux-2.6.29-rc3/mm/rmap.c > > > =================================================================== > > > --- linux-2.6.29-rc3.orig/mm/rmap.c 2009-01-30 14:13:56.000000000 -0500 > > > +++ linux-2.6.29-rc3/mm/rmap.c 2009-02-02 11:27:11.000000000 -0500 > > > @@ -1072,7 +1072,8 @@ static int try_to_unmap_file(struct page > > > spin_lock(&mapping->i_mmap_lock); > > > vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) { > > > if (MLOCK_PAGES && unlikely(unlock)) { > > > - if (!(vma->vm_flags & VM_LOCKED)) > > > + if (!((vma->vm_flags & VM_LOCKED) && > > > + page_mapped_in_vma(page, vma))) > > > continue; /* must visit all vmas */ > > > ret = SWAP_MLOCK; > > > } else { > > > > >
-- Kinds Regards MinChan Kim
| |