From: Jerome Glisse <jglisse@redhat.com>
To: Jason Gunthorpe <jgg@ziepe.ca>
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 12:49:02 -0400 [thread overview]
Message-ID: <20190524164902.GA3346@redhat.com> (raw)
In-Reply-To: <20190524143649.GA14258@ziepe.ca>
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:
Locking within the sync_cpu_device_pagetables() callback is the most important
aspect the driver must respect in order to keep things properly synchronized.
The usage pattern is::
int driver_populate_range(...)
{
struct hmm_range range;
...
range.start = ...;
range.end = ...;
range.pfns = ...;
range.flags = ...;
range.values = ...;
range.pfn_shift = ...;
hmm_range_register(&range);
/*
* Just wait for range to be valid, safe to ignore return value as we
* will use the return value of hmm_range_snapshot() below under the
* mmap_sem to ascertain the validity of the range.
*/
hmm_range_wait_until_valid(&range, TIMEOUT_IN_MSEC);
again:
down_read(&mm->mmap_sem);
ret = hmm_range_snapshot(&range);
if (ret) {
up_read(&mm->mmap_sem);
if (ret == -EAGAIN) {
/*
* No need to check hmm_range_wait_until_valid() return value
* on retry we will get proper error with hmm_range_snapshot()
*/
hmm_range_wait_until_valid(&range, TIMEOUT_IN_MSEC);
goto again;
}
hmm_range_unregister(&range);
return ret;
}
take_lock(driver->update);
if (!hmm_range_valid(&range)) {
release_lock(driver->update);
up_read(&mm->mmap_sem);
goto again;
}
// Use pfns array content to update device page table
hmm_range_unregister(&range);
release_lock(driver->update);
up_read(&mm->mmap_sem);
return 0;
}
The driver->update lock is the same lock that the driver takes inside its
sync_cpu_device_pagetables() callback. That lock must be held before calling
hmm_range_valid() to avoid any race with a concurrent CPU page table update.
Cheers,
Jérôme
next prev parent reply other threads:[~2019-05-24 16:49 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 [this message]
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
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=20190524164902.GA3346@redhat.com \
--to=jglisse@redhat.com \
--cc=jgg@ziepe.ca \
--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).