From: Tejun Heo <tj@kernel.org>
To: Oleg Nesterov <oleg@redhat.com>
Cc: torvalds@linux-foundation.org, jannh@google.com,
paulmck@linux.vnet.ibm.com, bcrl@kvack.org,
viro@zeniv.linux.org.uk, kent.overstreet@gmail.com,
security@kernel.org, linux-kernel@vger.kernel.org,
kernel-team@fb.com
Subject: Re: [PATCH 8/8] fs/aio: Use rcu_work instead of explicit rcu and work item
Date: Wed, 21 Mar 2018 09:40:00 -0700 [thread overview]
Message-ID: <20180321164000.GC2149215@devbig577.frc2.facebook.com> (raw)
In-Reply-To: <20180321155812.GA9382@redhat.com>
Hey, Oleg.
On Wed, Mar 21, 2018 at 04:58:13PM +0100, Oleg Nesterov wrote:
> > - struct rcu_head free_rcu;
> > - struct work_struct free_work; /* see free_ioctx() */
> > + struct rcu_work free_rwork; /* see free_ioctx() */
>
> IIUC, you can't easily share rcu_work's, thus every kioctx needs its own
> ->free_rwork and this looks sub-optimal.
>
> What do you think about the (untested) patch below?
>
> Oleg.
>
>
> --- a/fs/aio.c
> +++ b/fs/aio.c
> @@ -115,8 +115,10 @@ struct kioctx {
> struct page **ring_pages;
> long nr_pages;
>
> - struct rcu_head free_rcu;
> - struct work_struct free_work; /* see free_ioctx() */
> + union {
> + struct rcu_head free_rcu;
> + struct llist_node free_llist;
> + };
It really depends on how much we want to optimize. Do you think it
matters enough?
Thanks.
--
tejun
next prev parent reply other threads:[~2018-03-21 16:40 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-03-14 19:41 [PATCHSET v2] percpu_ref, RCU: Audit RCU usages in percpu_ref users Tejun Heo
2018-03-14 19:45 ` [PATCH 1/8] fs/aio: Add explicit RCU grace period when freeing kioctx Tejun Heo
2018-03-14 19:45 ` [PATCH 2/8] fs/aio: Use RCU accessors for kioctx_table->table[] Tejun Heo
2018-03-14 19:45 ` [PATCH 3/8] RDMAVT: Fix synchronization around percpu_ref Tejun Heo
2018-03-15 22:24 ` Jason Gunthorpe
2018-03-14 19:45 ` [PATCH 4/8] HMM: Remove superflous RCU protection around radix tree lookup Tejun Heo
2018-03-14 19:45 ` Tejun Heo
2018-03-26 14:54 ` Tejun Heo
2018-03-26 14:54 ` Tejun Heo
2018-03-27 16:12 ` Jerome Glisse
2018-03-27 16:12 ` Jerome Glisse
2018-03-14 19:45 ` [PATCH 5/8] percpu_ref: Update doc to dissuade users from depending on internal RCU grace periods Tejun Heo
2018-03-19 17:10 ` Tejun Heo
2018-03-14 19:45 ` [PATCH 6/8] RCU, workqueue: Implement rcu_work Tejun Heo
2018-03-14 20:13 ` Paul E. McKenney
2018-03-16 6:01 ` Lai Jiangshan
2018-03-19 16:45 ` Tejun Heo
2018-03-20 10:04 ` Lai Jiangshan
2018-03-14 19:45 ` [PATCH 7/8] cgroup: Use rcu_work instead of explicit rcu and work item Tejun Heo
2018-03-14 19:45 ` [PATCH 8/8] fs/aio: " Tejun Heo
2018-03-19 17:12 ` Tejun Heo
2018-03-21 15:58 ` Oleg Nesterov
2018-03-21 16:40 ` Tejun Heo [this message]
2018-03-21 17:17 ` Oleg Nesterov
2018-03-21 17:53 ` Tejun Heo
2018-03-22 11:24 ` Oleg Nesterov
2018-03-26 15:04 ` Tejun Heo
2018-03-27 14:28 ` Oleg Nesterov
2018-03-27 15:55 ` Tejun Heo
2018-03-29 16:49 ` Oleg Nesterov
2018-03-29 17:41 ` Tejun Heo
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=20180321164000.GC2149215@devbig577.frc2.facebook.com \
--to=tj@kernel.org \
--cc=bcrl@kvack.org \
--cc=jannh@google.com \
--cc=kent.overstreet@gmail.com \
--cc=kernel-team@fb.com \
--cc=linux-kernel@vger.kernel.org \
--cc=oleg@redhat.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=security@kernel.org \
--cc=torvalds@linux-foundation.org \
--cc=viro@zeniv.linux.org.uk \
/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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.