From: Michal Hocko <mhocko@kernel.org>
To: christian.koenig@amd.com
Cc: kvm@vger.kernel.org, "Radim Krčmář" <rkrcmar@redhat.com>,
"Tetsuo Handa" <penguin-kernel@I-love.SAKURA.ne.jp>,
"Sudeep Dutt" <sudeep.dutt@intel.com>,
dri-devel@lists.freedesktop.org, linux-mm@kvack.org,
"Andrea Arcangeli" <aarcange@redhat.com>,
"Dimitri Sivanich" <sivanich@sgi.com>,
"Jason Gunthorpe" <jgg@ziepe.ca>,
linux-rdma@vger.kernel.org, amd-gfx@lists.freedesktop.org,
"David Airlie" <airlied@linux.ie>,
"Doug Ledford" <dledford@redhat.com>,
"David Rientjes" <rientjes@google.com>,
xen-devel@lists.xenproject.org, intel-gfx@lists.freedesktop.org,
"Leon Romanovsky" <leonro@mellanox.com>,
"Jérôme Glisse" <jglisse@redhat.com>,
"Rodrigo Vivi" <rodrigo.vivi@intel.com>,
"Boris Ostrovsky" <boris.ostrovsky@oracle.com>,
"Juergen Gross" <jgross@suse.com>,
"Mike Marciniszyn" <mike.marciniszyn@intel.com>,
"Dennis Dalessandro" <dennis.dalessandro@intel.com>,
LKML <linux-kernel@vger.kernel.org>,
"Ashutosh Dixit" <ashutosh.dixit@intel.com>,
"Alex Deucher" <alexander.deucher@amd.com>,
"Paolo Bonzini" <pbonzini@redhat.com>,
"Andrew Morton" <akpm@linux-foundation.org>,
"Felix Kuehling" <felix.kuehling@amd.com>
Subject: Re: [PATCH] mm, oom: distinguish blockable mode for mmu notifiers
Date: Fri, 24 Aug 2018 15:40:09 +0200 [thread overview]
Message-ID: <20180824134009.GS29735@dhcp22.suse.cz> (raw)
In-Reply-To: <86bd94d5-0ce8-c67f-07a5-ca9ebf399cdd@gmail.com>
On Fri 24-08-18 15:28:33, Christian König wrote:
> Am 24.08.2018 um 15:24 schrieb Michal Hocko:
> > On Fri 24-08-18 15:10:08, Christian König wrote:
> > > Am 24.08.2018 um 15:01 schrieb Michal Hocko:
> > > > On Fri 24-08-18 14:52:26, Christian König wrote:
> > > > > Am 24.08.2018 um 14:33 schrieb Michal Hocko:
> > > > [...]
> > > > > > Thiking about it some more, I can imagine that a notifier callback which
> > > > > > performs an allocation might trigger a memory reclaim and that in turn
> > > > > > might trigger a notifier to be invoked and recurse. But notifier
> > > > > > shouldn't really allocate memory. They are called from deep MM code
> > > > > > paths and this would be extremely deadlock prone. Maybe Jerome can come
> > > > > > up some more realistic scenario. If not then I would propose to simplify
> > > > > > the locking here. We have lockdep to catch self deadlocks and it is
> > > > > > always better to handle a specific issue rather than having a code
> > > > > > without a clear indication how it can recurse.
> > > > > Well I agree that we should probably fix that, but I have some concerns to
> > > > > remove the existing workaround.
> > > > >
> > > > > See we added that to get rid of a real problem in a customer environment and
> > > > > I don't want to that to show up again.
> > > > It would really help to know more about that case and fix it properly
> > > > rather than workaround it like this. Anyway, let me think how to handle
> > > > the non-blocking notifier invocation then. I was not able to come up
> > > > with anything remotely sane yet.
> > > With avoiding allocating memory in the write lock path I don't see an issue
> > > any more with that.
> > >
> > > All what the write lock path does now is adding items to a linked lists,
> > > arrays etc....
> > Can we change it to non-sleepable lock then?
>
> No, the write side doesn't sleep any more, but the read side does.
>
> See amdgpu_mn_invalidate_node() and that is where you actually need to
> handle the non-blocking flag correctly.
Ohh, right you are. We already handle that by bailing out before calling
amdgpu_mn_invalidate_node in !blockable mode. So does this looks good to
you?
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index e55508b39496..48fa152231be 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -180,11 +180,15 @@ void amdgpu_mn_unlock(struct amdgpu_mn *mn)
*/
static int amdgpu_mn_read_lock(struct amdgpu_mn *amn, bool blockable)
{
- if (blockable)
- mutex_lock(&amn->read_lock);
- else if (!mutex_trylock(&amn->read_lock))
- return -EAGAIN;
-
+ /*
+ * We can take sleepable lock even on !blockable mode because
+ * read_lock is only ever take from this path and the notifier
+ * lock never really sleeps. In fact the only reason why the
+ * later is sleepable is because the notifier itself might sleep
+ * in amdgpu_mn_invalidate_node but blockable mode is handled
+ * before calling into that path.
+ */
+ mutex_lock(&amn->read_lock);
if (atomic_inc_return(&amn->recursion) == 1)
down_read_non_owner(&amn->lock);
mutex_unlock(&amn->read_lock);
--
Michal Hocko
SUSE Labs
next prev parent reply other threads:[~2018-08-24 13:40 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-07-16 11:50 [PATCH] mm, oom: distinguish blockable mode for mmu notifiers Michal Hocko
2018-07-16 23:12 ` Andrew Morton
2018-07-17 4:03 ` Leon Romanovsky
2018-07-17 8:12 ` Michal Hocko
2018-07-20 23:01 ` Andrew Morton
2018-07-23 8:43 ` Michal Hocko
2018-07-19 9:12 ` Michal Hocko
2018-07-21 0:09 ` Andrew Morton
2018-07-23 7:03 ` Michal Hocko
2018-07-23 7:11 ` Michal Hocko
2018-07-23 8:11 ` Michal Hocko
2018-07-24 14:17 ` Michal Hocko
2018-07-24 19:53 ` Andrew Morton
2018-07-25 6:17 ` Michal Hocko
2018-07-24 21:07 ` David Rientjes
2018-07-25 6:13 ` Michal Hocko
2018-08-24 10:54 ` Tetsuo Handa
2018-08-24 11:32 ` Michal Hocko
2018-08-24 11:43 ` Christian König
2018-08-24 11:52 ` Michal Hocko
2018-08-24 11:57 ` Christian König
2018-08-24 12:03 ` Michal Hocko
2018-08-24 12:18 ` Christian König
2018-08-24 12:33 ` Michal Hocko
2018-08-24 12:52 ` Christian König
2018-08-24 13:01 ` Michal Hocko
2018-08-24 13:10 ` Christian König
2018-08-24 13:24 ` Michal Hocko
2018-08-24 13:28 ` Christian König
2018-08-24 13:40 ` Michal Hocko [this message]
2018-08-24 13:44 ` Christian König
2018-08-24 13:52 ` Michal Hocko
2018-08-26 8:40 ` Tetsuo Handa
2018-08-27 7:41 ` Christian König
2018-09-06 22:46 ` Tetsuo Handa
2018-08-24 15:08 ` Jerome Glisse
2018-08-24 11:36 ` Michal Hocko
2018-08-24 13:02 ` Tetsuo Handa
2018-08-24 13:32 ` Michal Hocko
2018-08-24 14:52 ` Tetsuo Handa
2018-08-24 15:12 ` Jerome Glisse
2018-08-24 16:40 ` Michal Hocko
2018-08-24 17:33 ` Jerome Glisse
2018-08-24 16:38 ` Michal Hocko
2018-08-24 14:40 ` 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=20180824134009.GS29735@dhcp22.suse.cz \
--to=mhocko@kernel.org \
--cc=aarcange@redhat.com \
--cc=airlied@linux.ie \
--cc=akpm@linux-foundation.org \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=ashutosh.dixit@intel.com \
--cc=boris.ostrovsky@oracle.com \
--cc=christian.koenig@amd.com \
--cc=dennis.dalessandro@intel.com \
--cc=dledford@redhat.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=felix.kuehling@amd.com \
--cc=intel-gfx@lists.freedesktop.org \
--cc=jgg@ziepe.ca \
--cc=jglisse@redhat.com \
--cc=jgross@suse.com \
--cc=kvm@vger.kernel.org \
--cc=leonro@mellanox.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-rdma@vger.kernel.org \
--cc=mike.marciniszyn@intel.com \
--cc=pbonzini@redhat.com \
--cc=penguin-kernel@I-love.SAKURA.ne.jp \
--cc=rientjes@google.com \
--cc=rkrcmar@redhat.com \
--cc=rodrigo.vivi@intel.com \
--cc=sivanich@sgi.com \
--cc=sudeep.dutt@intel.com \
--cc=xen-devel@lists.xenproject.org \
/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).