Re: [PATCH] mm: introduce MADV_CLR_HUGEPAGE

[Mike Rapoport]

On Mon, May 22, 2017 at 05:52:47PM +0200, Vlastimil Babka wrote:
> On 05/22/2017 04:29 PM, Mike Rapoport wrote:
> > On Mon, May 22, 2017 at 03:55:48PM +0200, Michal Hocko wrote:
> >> On Mon 22-05-17 16:36:00, Mike Rapoport wrote:
> >>> On Mon, May 22, 2017 at 02:42:43PM +0300, Kirill A. Shutemov wrote:
> >>>> On Mon, May 22, 2017 at 09:12:42AM +0300, Mike Rapoport wrote:
> >>>>> Currently applications can explicitly enable or disable THP for a memory
> >>>>> region using MADV_HUGEPAGE or MADV_NOHUGEPAGE. However, once either of
> >>>>> these advises is used, the region will always have
> >>>>> VM_HUGEPAGE/VM_NOHUGEPAGE flag set in vma->vm_flags.
> >>>>> The MADV_CLR_HUGEPAGE resets both these flags and allows managing THP in
> >>>>> the region according to system-wide settings.
> >>>>
> >>>> Seems reasonable. But could you describe an use-case when it's useful in
> >>>> real world.
> >>>
> >>> My use-case was combination of pre- and post-copy migration of containers
> >>> with CRIU.
> >>> In this case we populate a part of a memory region with data that was saved
> >>> during the pre-copy stage. Afterwards, the region is registered with
> >>> userfaultfd and we expect to get page faults for the parts of the region
> >>> that were not yet populated. However, khugepaged collapses the pages and
> >>> the page faults we would expect do not occur.
> >>
> >> I am not sure I undestand the problem. Do I get it right that the
> >> khugepaged will effectivelly corrupt the memory by collapsing a range
> >> which is not yet fully populated? If yes shouldn't that be fixed in
> >> khugepaged rather than adding yet another madvise command? Also how do
> >> you prevent on races? (say you VM_NOHUGEPAGE, khugepaged would be in the
> >> middle of the operation and sees a collapsable vma and you get the same
> >> result)
> > 
> > Probably I didn't explained it too well.
> > 
> > The range is intentionally not populated. When we combine pre- and
> > post-copy for process migration, we create memory pre-dump without stopping
> > the process, then we freeze the process without dumping the pages it has
> > dirtied between pre-dump and freeze, and then, during restore, we populate
> > the dirtied pages using userfaultfd.
> > 
> > When CRIU restores a process in such scenario, it does something like:
> > 
> > * mmap() memory region
> > * fill in the pages that were collected during the pre-dump
> > * do some other stuff
> > * register memory region with userfaultfd
> > * populate the missing memory on demand
> > 
> > khugepaged collapses the pages in the partially populated regions before we
> > have a chance to register these regions with userfaultfd, which would
> > prevent the collapse.
> > 
> > We could have used MADV_NOHUGEPAGE right after the mmap() call, and then
> > there would be no race because there would be nothing for khugepaged to
> > collapse at that point. But the problem is that we have no way to reset
> > *HUGEPAGE flags after the memory restore is complete.
> 
> Hmm, I wouldn't be that sure if this is indeed race-free. Check that
> this scenario is indeed impossible?
> 
> - you do the mmap
> - khugepaged will choose the process' mm to scan
> - khugepaged will get to the vma in question, it doesn't have
> MADV_NOHUGEPAGE yet
> - you set MADV_NOHUGEPAGE on the vma
> - you start populating the vma
> - khugepaged sees the vma is non-empty, collapses
> 
> unless I'm wrong, the racers will have mmap_sem for reading only when
> setting/checking the MADV_NOHUGEPAGE? Might be actually considered a bug.

madvise(MADV_*HUGEPAGE) takes mmap_sem for writing, so it is safe.
 
> However, can't you use prctl(PR_SET_THP_DISABLE) instead? "If arg2 has a
> nonzero value, the flag is set, otherwise it is cleared." says the
> manpage. Do it before the mmap and you avoid the race as well?

I've missed that one, thanks Vlastimil!