lkml.org 
[lkml]   [2013]   [Jul]   [18]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH] mm/hugetlb: per-vma instantiation mutexes
On Tue, Jul 16, 2013 at 08:01:46PM +1000, David Gibson wrote:
> On Tue, Jul 16, 2013 at 02:34:24PM +0900, Joonsoo Kim wrote:
> > On Mon, Jul 15, 2013 at 09:51:21PM -0400, Rik van Riel wrote:
> > > On 07/15/2013 03:24 AM, David Gibson wrote:
> > > >On Sun, Jul 14, 2013 at 08:16:44PM -0700, Davidlohr Bueso wrote:
> > >
> > > >>>Reading the existing comment, this change looks very suspicious to me.
> > > >>>A per-vma mutex is just not going to provide the necessary exclusion, is
> > > >>>it? (But I recall next to nothing about these regions and
> > > >>>reservations.)
> > > >
> > > >A per-VMA lock is definitely wrong. I think it handles one form of
> > > >the race, between threads sharing a VM on a MAP_PRIVATE mapping.
> > > >However another form of the race can and does occur between different
> > > >MAP_SHARED VMAs in the same or different processes. I think there may
> > > >be edge cases involving mremap() and MAP_PRIVATE that will also be
> > > >missed by a per-VMA lock.
> > > >
> > > >Note that the libhugetlbfs testsuite contains tests for both PRIVATE
> > > >and SHARED variants of the race.
> > >
> > > Can we get away with simply using a mutex in the file?
> > > Say vma->vm_file->mapping->i_mmap_mutex?
> >
> > I totally agree with this approach :)
> >
> > >
> > > That might help with multiple processes initializing
> > > multiple shared memory segments at the same time, and
> > > should not hurt the case of a process mapping its own
> > > hugetlbfs area.
> > >
> > > It might have the potential to hurt when getting private
> > > copies on a MAP_PRIVATE area, though. I have no idea
> > > how common it is for multiple processes to MAP_PRIVATE
> > > the same hugetlbfs file, though...
> >
> > Currently, getting private copies on a MAP_PRIVATE area is also
> > serialized by hugetlb_instantiation_mutex.
> > How do we get worse with your approach?
> >
> > BTW, we have one race problem related to hugetlb_instantiation_mutex.
> > It is not right protection for region structure handling. We map the
> > area without holding a hugetlb_instantiation_mutex, so there is
> > race condition between mapping a new area and faulting the other area.
> > Am I missing?
>
> The hugetlb_instantiation_mutex has nothing to do with protecting
> region structures. It exists only to address one very specific and
> frequently misunderstood race.

Yes, it was introduced for that purpose, but, currently, it is also
used for protecting region structure. You can see below comment in
mm/hugetlb.c

* The region data structures are protected by a combination of the mmap_sem
* and the hugetlb_instantion_mutex. To access or modify a region the caller
* must either hold the mmap_sem for write, or the mmap_sem for read and
* the hugetlb_instantiation mutex:
*
* down_write(&mm->mmap_sem);
* or
* down_read(&mm->mmap_sem);
* mutex_lock(&hugetlb_instantiation_mutex);
*/

Thanks.

>
> --
> David Gibson | I'll have my music baroque, and my code
> david AT gibson.dropbear.id.au | minimalist, thank you. NOT _the_ _other_
> | _way_ _around_!
> http://www.ozlabs.org/~dgibson




\
 
 \ /
  Last update: 2013-07-18 09:41    [W:0.053 / U:10.408 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site