Prev: [PATCH] CRED: Fix a race in creds_are_invalid() in credentials debugging
Next: [PATCH 09/13] via: Rationalize vt1636 detection
From: Mel Gorman on 21 Apr 2010 05:30
On Tue, Apr 20, 2010 at 04:33:07PM -0700, Andrew Morton wrote:
> On Tue, 20 Apr 2010 18:44:07 +0100
> Mel Gorman <mel(a)csn.ul.ie> wrote:
>
> > Ordinarily, application using hugetlbfs will create mappings with
> > reserves. For shared mappings, these pages are reserved before mmap()
> > returns success and for private mappings, the caller process is
> > guaranteed and a child process that cannot get the pages gets killed
> > with sigbus.
> >
> > An application that uses MAP_NORESERVE gets no reservations and mmap()
> > will always succeed at the risk the page will not be available at fault
> > time. This might be used for example on very large sparse mappings where the
> > developer is confident the necessary huge pages exist to satisfy all faults
> > even though the whole mapping cannot be backed by huge pages. Unfortunately,
> > if an allocation does fail, VM_FAULT_OOM is returned to the fault handler
> > which proceeds to trigger the OOM-killer. This is unhelpful.
> >
> > This patch alters hugetlbfs to kill a process that uses MAP_NORESERVE
> > where huge pages were not available with SIGBUS instead of triggering
> > the OOM killer.
> >
> > This patch if accepted should also be considered a -stable candidate.
>
> Why? The changelog doesn't convey much seriousness?
>

Because even without hugetlbfs mounted, a user using mmap() can trivially
trigger the OOM-killer because VM_FAULT_OOM is returned (will provide example
program if you like, it's a whopping 24 lines long). It could be considered
a DOS available to an unprivileged user.

> > Signed-off-by: Mel Gorman <mel(a)csn.ul.ie>
> > ---
> > mm/hugetlb.c | 2 +-
> > 1 files changed, 1 insertions(+), 1 deletions(-)
> >
> > diff --git a/mm/hugetlb.c b/mm/hugetlb.c
> > index 6034dc9..af2d907 100644
> > --- a/mm/hugetlb.c
> > +++ b/mm/hugetlb.c
> > @@ -1038,7 +1038,7 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
> > page = alloc_buddy_huge_page(h, vma, addr);
> > if (!page) {
> > hugetlb_put_quota(inode->i_mapping, chg);
> > - return ERR_PTR(-VM_FAULT_OOM);
> > + return ERR_PTR(-VM_FAULT_SIGBUS);
> > }
> > }
> >
>
> This affects hugetlb_cow() as well?
>

Yes. I feel there is a failure case in there, but I didn't create one.
It would need a fairly specific target in terms of the faulting application
and the hugepage pool size. The hugetlb_no_page path is much easier to hit
but both might as well be closed.

--
Mel Gorman
Part-time Phd Student Linux Technology Center
University of Limerick IBM Dublin Software Lab
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
 | 
Pages: 1
Prev: [PATCH] CRED: Fix a race in creds_are_invalid() in credentials debugging
Next: [PATCH 09/13] via: Rationalize vt1636 detection