From: Jason Gunthorpe <jgg@ziepe.ca>
To: Jerome Glisse <jglisse@redhat.com>
Cc: linux-rdma@vger.kernel.org, linux-mm@kvack.org,
Ralph Campbell <rcampbell@nvidia.com>,
John Hubbard <jhubbard@nvidia.com>
Subject: Re: [RFC PATCH 00/11] mm/hmm: Various revisions from a locking/code review
Date: Fri, 24 May 2019 15:32:25 -0300 [thread overview]
Message-ID: <20190524183225.GI16845@ziepe.ca> (raw)
In-Reply-To: <20190524180321.GD3346@redhat.com>
On Fri, May 24, 2019 at 02:03:22PM -0400, Jerome Glisse wrote:
> On Fri, May 24, 2019 at 02:52:03PM -0300, Jason Gunthorpe wrote:
> > On Fri, May 24, 2019 at 01:01:49PM -0400, Jerome Glisse wrote:
> > > On Fri, May 24, 2019 at 01:59:31PM -0300, Jason Gunthorpe wrote:
> > > > On Fri, May 24, 2019 at 12:49:02PM -0400, Jerome Glisse wrote:
> > > > > On Fri, May 24, 2019 at 11:36:49AM -0300, Jason Gunthorpe wrote:
> > > > > > On Thu, May 23, 2019 at 12:34:25PM -0300, Jason Gunthorpe wrote:
> > > > > > > From: Jason Gunthorpe <jgg@mellanox.com>
> > > > > > >
> > > > > > > This patch series arised out of discussions with Jerome when looking at the
> > > > > > > ODP changes, particularly informed by use after free races we have already
> > > > > > > found and fixed in the ODP code (thanks to syzkaller) working with mmu
> > > > > > > notifiers, and the discussion with Ralph on how to resolve the lifetime model.
> > > > > >
> > > > > > So the last big difference with ODP's flow is how 'range->valid'
> > > > > > works.
> > > > > >
> > > > > > In ODP this was done using the rwsem umem->umem_rwsem which is
> > > > > > obtained for read in invalidate_start and released in invalidate_end.
> > > > > >
> > > > > > Then any other threads that wish to only work on a umem which is not
> > > > > > undergoing invalidation will obtain the write side of the lock, and
> > > > > > within that lock's critical section the virtual address range is known
> > > > > > to not be invalidating.
> > > > > >
> > > > > > I cannot understand how hmm gets to the same approach. It has
> > > > > > range->valid, but it is not locked by anything that I can see, so when
> > > > > > we test it in places like hmm_range_fault it seems useless..
> > > > > >
> > > > > > Jerome, how does this work?
> > > > > >
> > > > > > I have a feeling we should copy the approach from ODP and use an
> > > > > > actual lock here.
> > > > >
> > > > > range->valid is use as bail early if invalidation is happening in
> > > > > hmm_range_fault() to avoid doing useless work. The synchronization
> > > > > is explained in the documentation:
> > > >
> > > > That just says the hmm APIs handle locking. I asked how the apis
> > > > implement that locking internally.
> > > >
> > > > Are you trying to say that if I do this, hmm will still work completely
> > > > correctly?
> > >
> > > Yes it will keep working correctly. You would just be doing potentialy
> > > useless work.
> >
> > I don't see how it works correctly.
> >
> > Apply the comment out patch I showed and this trivially happens:
> >
> > CPU0 CPU1
> > hmm_invalidate_start()
> > ops->sync_cpu_device_pagetables()
> > device_lock()
> > // Wipe out page tables in device, enable faulting
> > device_unlock()
> >
> > DEVICE PAGE FAULT
> > device_lock()
> > hmm_range_register()
> > hmm_range_dma_map()
> > device_unlock()
> > hmm_invalidate_end()
>
> No in the above scenario hmm_range_register() will not mark the range
> as valid thus the driver will bailout after taking its lock and checking
> the range->valid value.
I see your confusion, I only asked about removing valid from hmm.c,
not the unlocked use of valid in your hmm.rst example. My mistake,
sorry for being unclear.
Here is the big 3 CPU ladder diagram that shows how 'valid' does not
work:
CPU0 CPU1 CPU2
DEVICE PAGE FAULT
range = hmm_range_register()
// Overlaps with range
hmm_invalidate_start()
range->valid = false
ops->sync_cpu_device_pagetables()
take_lock(driver->update);
// Wipe out page tables in device, enable faulting
release_lock(driver->update);
// Does not overlap with range
hmm_invalidate_start()
hmm_invalidate_end()
list_for_each
range->valid = true
device_lock()
// Note range->valid = true now
hmm_range_snapshot(&range);
take_lock(driver->update);
if (!hmm_range_valid(&range))
goto again
ESTABLISHE SPTES
device_unlock()
hmm_invalidate_end()
And I can make this more complicated (ie overlapping parallel
invalidates, etc) and show any 'bool' valid cannot work.
> > The mmu notifier spec says:
> >
> > * Invalidation of multiple concurrent ranges may be
> > * optionally permitted by the driver. Either way the
> > * establishment of sptes is forbidden in the range passed to
> > * invalidate_range_begin/end for the whole duration of the
> > * invalidate_range_begin/end critical section.
> >
> > And I understand "establishment of sptes is forbidden" means
> > "hmm_range_dmap_map() must fail with EAGAIN".
>
> No it means that secondary page table entry (SPTE) must not
> materialize thus what hmm_range_dmap_map() is doing if fine and safe
> as long as the driver do not use the result to populate the device
> page table if there was an invalidation for the range.
Okay, so we agree, if there is an invalidate_start/end critical region
then it is OK to *call* hmm_range_dmap_map(), however the driver must
not *use* the result, and you are expecting this bit:
take_lock(driver->update);
if (!hmm_range_valid(&range)) {
goto again
In your hmm.rst to prevent the pfns from being used by the driver?
I think the above ladder shows that hmm_range_valid can return true
during a invalidate_start/end critical region, so this is a problem.
I still think the best solution is to move device_lock() into mirror
and have hmm manage it for the driver as ODP does. It is certainly the
simplest solution to understand.
Jason
next prev parent reply other threads:[~2019-05-24 18:32 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-05-23 15:34 [RFC PATCH 00/11] mm/hmm: Various revisions from a locking/code review Jason Gunthorpe
2019-05-23 15:34 ` [RFC PATCH 01/11] mm/hmm: Fix use after free with struct hmm in the mmu notifiers Jason Gunthorpe
2019-06-06 23:54 ` Ira Weiny
2019-06-07 14:17 ` Jason Gunthorpe
2019-05-23 15:34 ` [RFC PATCH 02/11] mm/hmm: Use hmm_mirror not mm as an argument for hmm_register_range Jason Gunthorpe
2019-05-23 18:22 ` Christoph Hellwig
2019-05-23 15:34 ` [RFC PATCH 03/11] mm/hmm: Hold a mmgrab from hmm to mm Jason Gunthorpe
2019-05-23 15:34 ` [RFC PATCH 04/11] mm/hmm: Simplify hmm_get_or_create and make it reliable Jason Gunthorpe
2019-05-23 23:38 ` Ralph Campbell
2019-05-24 1:23 ` Jason Gunthorpe
2019-05-24 17:06 ` Ralph Campbell
2019-05-23 15:34 ` [RFC PATCH 05/11] mm/hmm: Improve locking around hmm->dead Jason Gunthorpe
2019-05-24 13:40 ` Jason Gunthorpe
2019-05-23 15:34 ` [RFC PATCH 06/11] mm/hmm: Remove duplicate condition test before wait_event_timeout Jason Gunthorpe
2019-05-23 15:34 ` [RFC PATCH 07/11] mm/hmm: Delete hmm_mirror_mm_is_alive() Jason Gunthorpe
2019-05-23 15:34 ` [RFC PATCH 08/11] mm/hmm: Use lockdep instead of comments Jason Gunthorpe
2019-06-07 19:33 ` Souptick Joarder
2019-06-07 19:39 ` Jason Gunthorpe
2019-06-07 21:02 ` Souptick Joarder
2019-06-08 1:15 ` Jason Gunthorpe
2019-05-23 15:34 ` [RFC PATCH 09/11] mm/hmm: Remove racy protection against double-unregistration Jason Gunthorpe
2019-06-07 19:38 ` Souptick Joarder
2019-06-07 19:37 ` Jason Gunthorpe
2019-06-07 19:55 ` Souptick Joarder
2019-05-23 15:34 ` [RFC PATCH 10/11] mm/hmm: Poison hmm_range during unregister Jason Gunthorpe
2019-06-07 20:13 ` Souptick Joarder
2019-06-07 20:18 ` Jason Gunthorpe
2019-05-23 15:34 ` [RFC PATCH 11/11] mm/hmm: Do not use list*_rcu() for hmm->ranges Jason Gunthorpe
2019-06-07 20:22 ` Souptick Joarder
2019-05-23 19:04 ` [RFC PATCH 00/11] mm/hmm: Various revisions from a locking/code review John Hubbard
2019-05-23 19:37 ` Jason Gunthorpe
2019-05-23 20:59 ` Jerome Glisse
2019-05-24 13:35 ` Jason Gunthorpe
2019-05-24 14:36 ` Jason Gunthorpe
2019-05-24 16:49 ` Jerome Glisse
2019-05-24 16:59 ` Jason Gunthorpe
2019-05-24 17:01 ` Jerome Glisse
2019-05-24 17:52 ` Jason Gunthorpe
2019-05-24 18:03 ` Jerome Glisse
2019-05-24 18:32 ` Jason Gunthorpe [this message]
2019-05-24 18:46 ` Jerome Glisse
2019-05-24 22:09 ` Jason Gunthorpe
2019-05-27 19:58 ` Jason Gunthorpe
2019-05-24 17:47 ` Ralph Campbell
2019-05-24 17:51 ` Jerome Glisse
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190524183225.GI16845@ziepe.ca \
--to=jgg@ziepe.ca \
--cc=jglisse@redhat.com \
--cc=jhubbard@nvidia.com \
--cc=linux-mm@kvack.org \
--cc=linux-rdma@vger.kernel.org \
--cc=rcampbell@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).