From: Linus Torvalds <torvalds@linux-foundation.org>
To: Mateusz Guzik <mjguzik@gmail.com>
Cc: Christian Brauner <brauner@kernel.org>,
kernel test robot <oliver.sang@intel.com>,
oe-lkp@lists.linux.dev, lkp@intel.com,
Linux Memory Management List <linux-mm@kvack.org>,
linux-kernel@vger.kernel.org, ying.huang@intel.com,
feng.tang@intel.com, fengwei.yin@intel.com
Subject: Re: [linux-next:master] [lockref] d042dae6ad: unixbench.throughput -33.7% regression
Date: Tue, 2 Jul 2024 10:28:04 -0700 [thread overview]
Message-ID: <CAHk-=wgVzKtRnvDXAzueJTbgfo1o12Lw6DH97PzRe1cGA_b1oA@mail.gmail.com> (raw)
In-Reply-To: <CAGudoHGuTP-nv=zwXdQs38OEqb=BD=i-vA-9xjZ0UOyvWuXP_w@mail.gmail.com>
On Tue, 2 Jul 2024 at 10:03, Mateusz Guzik <mjguzik@gmail.com> wrote:
>
> I was thinking a different approach.
>
> A lookup variant which resolves everything and returns the dentry + an
> information whether this is rcu mode.
That would work equally.
But the end result ends up being very similar: you need to hook into
that final complete_walk() -> try_to_unlazy() -> legitimize_path() and
check a flag whether you actually then do "get_lockref_or_dead()" or
not.
It really *shouldn't* be too bad, but this is just so subtle code that
it just takes a lot of care. Even if the patch itself ends up not
necessarily being very large.
As mentioned, I've looked at it, but it always ended up being _just_
scary enough that I never really started doing it.
Linus
next prev parent reply other threads:[~2024-07-02 17:28 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-27 2:41 kernel test robot
2024-06-27 6:25 ` Mateusz Guzik
2024-06-27 7:00 ` Mateusz Guzik
2024-06-27 16:32 ` Linus Torvalds
2024-06-27 16:55 ` Mateusz Guzik
2024-06-27 16:57 ` Linus Torvalds
2024-06-27 17:20 ` Mateusz Guzik
2024-06-27 17:23 ` Linus Torvalds
2024-07-02 7:19 ` Mateusz Guzik
2024-07-02 12:10 ` Mateusz Guzik
2024-07-02 16:47 ` Linus Torvalds
2024-07-02 17:02 ` Mateusz Guzik
2024-07-02 17:28 ` Linus Torvalds [this message]
2024-07-02 17:46 ` Mateusz Guzik
2024-07-02 17:58 ` Mateusz Guzik
2024-07-02 18:41 ` Linus Torvalds
2024-07-02 20:33 ` Mateusz Guzik
2024-07-02 20:42 ` Linus Torvalds
2024-07-02 21:15 ` Mateusz Guzik
2024-07-02 22:14 ` Linus Torvalds
2024-07-03 13:53 ` Mateusz Guzik
2024-07-03 14:08 ` Christian Brauner
2024-07-03 14:11 ` Mateusz Guzik
2024-07-03 16:47 ` Linus Torvalds
2024-07-03 8:34 ` Christian Brauner
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='CAHk-=wgVzKtRnvDXAzueJTbgfo1o12Lw6DH97PzRe1cGA_b1oA@mail.gmail.com' \
--to=torvalds@linux-foundation.org \
--cc=brauner@kernel.org \
--cc=feng.tang@intel.com \
--cc=fengwei.yin@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lkp@intel.com \
--cc=mjguzik@gmail.com \
--cc=oe-lkp@lists.linux.dev \
--cc=oliver.sang@intel.com \
--cc=ying.huang@intel.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