From: Mike Galbraith <efault@gmx.de>
To: Vlastimil Babka <vbabka@suse.cz>,
Thomas Gleixner <tglx@linutronix.de>,
LKML <linux-kernel@vger.kernel.org>
Cc: linux-rt-users@vger.kernel.org,
Mel Gorman <mgorman@techsingularity.net>,
Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Subject: Re: [rfc/patch] mm/slub: restore/expand unfreeze_partials() local exclusion scope
Date: Sat, 24 Jul 2021 04:25:53 +0200 [thread overview]
Message-ID: <23b626c719b6b269fc30e29041b8db3b4f8b60f8.camel@gmx.de> (raw)
In-Reply-To: <5be1a703-9a0a-4115-1d69-634e5e8ecefd@suse.cz>
On Sat, 2021-07-24 at 00:39 +0200, Vlastimil Babka wrote:
> On 7/21/21 11:33 AM, Mike Galbraith wrote:
> > On Wed, 2021-07-21 at 10:44 +0200, Vlastimil Babka wrote:
> > >
> > > So this doesn't look like our put_cpu_partial() preempted a
> > > __slab_alloc() on the same cpu, right?
> >
> > No, likely it was the one preempted by someone long gone, but we'll
> > never know without setting a trap.
> >
> > > BTW did my ugly patch work?
> >
> > Nope. I guess you missed my reporting it to have been a -ENOBOOT, and
>
> Indeed, I misunderstood it as you talking about your patch.
>
> > that cutting it in half, ie snagging only __slab_free() does boot, and
> > seems to cure all of the RT fireworks.
>
> OK, so depending on drain=1 makes this apply only to put_cpu_partial()
> called from __slab_free and not get_partial_node(). One notable
> difference is that in __slab_free we don't have n->list_lock locked and
> in get_partial_node() we do. I guess in case your list_lock is made raw
> again by another patch, that explains a local_lock can't nest under it.
> If not, then I would expect this to work (I don't think they ever nest
> in the opposite order, also lockdep should tell us instead of
> -ENOBOOT?), but might be missing something...
RT used to convert list_lock to raw_spinlock_t, but no longer does.
Whatever is going on, box does not emit a single sign of life with the
full patch.
> I'd rather not nest those locks in any case. I just need to convince
> myself that the scenario the half-fix fixes is indeed the only one
> that's needed and we're not leaving there other races that are just
> harder to trigger...
Yup. I can only state with confidence that the trouble I was able to
easily reproduce was fixed up by serializing __slab_free(). Hopefully
you'll find that's the only hole in need of plugging.
-Mike
next prev parent reply other threads:[~2021-07-24 2:26 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-08 9:42 [ANNOUNCE] v5.13-rt1 Thomas Gleixner
2021-07-09 5:20 ` [patch] mm/slub: Fix kmem_cache_alloc_bulk() error path Mike Galbraith
2021-07-09 5:20 ` [patch] mm/slub: Replace do_slab_free() local_lock_irqsave/restore() calls in PREEMPT_RT scope Mike Galbraith
2021-07-09 5:21 ` [rfc/patch] mm/slub: restore/expand unfreeze_partials() local exclusion scope Mike Galbraith
2021-07-09 5:25 ` Mike Galbraith
2021-07-09 19:28 ` Thomas Gleixner
2021-07-10 1:12 ` Mike Galbraith
2021-07-15 16:34 ` Mike Galbraith
2021-07-17 14:58 ` [patch] v2 " Mike Galbraith
2021-07-18 7:58 ` Vlastimil Babka
2021-07-18 8:11 ` Mike Galbraith
2021-07-18 15:43 ` Mike Galbraith
2021-07-18 21:19 ` Vlastimil Babka
2021-07-19 4:01 ` Mike Galbraith
2021-07-19 13:15 ` Mike Galbraith
2021-07-20 2:46 ` kernel test robot
2021-07-20 8:56 ` [rfc/patch] " Vlastimil Babka
2021-07-20 11:26 ` Mike Galbraith
2021-07-21 4:56 ` Mike Galbraith
2021-07-21 8:44 ` Vlastimil Babka
2021-07-21 9:33 ` Mike Galbraith
2021-07-23 22:39 ` Vlastimil Babka
2021-07-24 2:25 ` Mike Galbraith [this message]
2021-07-25 14:09 ` Mike Galbraith
2021-07-25 14:16 ` Vlastimil Babka
2021-07-25 15:02 ` Mike Galbraith
2021-07-25 16:27 ` Vlastimil Babka
2021-07-25 19:12 ` Vlastimil Babka
2021-07-25 19:34 ` Vlastimil Babka
2021-07-26 10:04 ` Mike Galbraith
2021-07-26 17:00 ` Mike Galbraith
2021-07-26 21:26 ` Vlastimil Babka
2021-07-27 4:09 ` Mike Galbraith
2021-07-28 16:59 ` Vlastimil Babka
2021-07-29 4:51 ` Mike Galbraith
2021-07-29 9:51 ` Vlastimil Babka
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=23b626c719b6b269fc30e29041b8db3b4f8b60f8.camel@gmx.de \
--to=efault@gmx.de \
--cc=bigeasy@linutronix.de \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-rt-users@vger.kernel.org \
--cc=mgorman@techsingularity.net \
--cc=tglx@linutronix.de \
--cc=vbabka@suse.cz \
/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).