From: Peter Zijlstra <peterz@infradead.org>
To: Waiman Long <longman@redhat.com>
Cc: "Ingo Molnar" <mingo@redhat.com>, "Will Deacon" <will@kernel.org>,
"Boqun Feng" <boqun.feng@gmail.com>,
linux-kernel@vger.kernel.org, john.p.donnelly@oracle.com,
"Hillf Danton" <hdanton@sina.com>,
"Mukesh Ojha" <quic_mojha@quicinc.com>,
"Ting11 Wang 王婷" <wangting11@xiaomi.com>
Subject: Re: [PATCH v3 2/5] locking/rwsem: Limit # of null owner retries for handoff writer
Date: Mon, 24 Oct 2022 15:31:17 +0200 [thread overview]
Message-ID: <Y1aTpYba1Wwly48+@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20221017211356.333862-3-longman@redhat.com>
On Mon, Oct 17, 2022 at 05:13:53PM -0400, Waiman Long wrote:
> Commit 91d2a812dfb9 ("locking/rwsem: Make handoff writer optimistically
> spin on owner") assumes that when the owner field is changed to NULL,
> the lock will become free soon. That assumption may not be correct
> especially if the handoff writer doing the spinning is a RT task which
> may preempt another task from completing its action of either freeing
> the rwsem or properly setting up owner.
I'm confused again -- rwsem_*_owner() has
lockdep_assert_preemption_disabled(). But more specifically; why can the
RT task preempt a lock-op like that?
next prev parent reply other threads:[~2022-10-24 20:26 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-17 21:13 [PATCH v3 0/5] lockinig/rwsem: Fix rwsem bugs & enable true lock handoff Waiman Long
2022-10-17 21:13 ` [PATCH v3 1/5] locking/rwsem: Prevent non-first waiter from spinning in down_write() slowpath Waiman Long
2022-10-24 13:17 ` Peter Zijlstra
2022-10-24 13:50 ` Waiman Long
2022-10-17 21:13 ` [PATCH v3 2/5] locking/rwsem: Limit # of null owner retries for handoff writer Waiman Long
2022-10-24 13:31 ` Peter Zijlstra [this message]
2022-10-24 15:55 ` Waiman Long
2022-10-25 11:22 ` Peter Zijlstra
2022-10-25 11:48 ` Peter Zijlstra
2022-10-25 19:55 ` Waiman Long
2022-10-25 20:14 ` Peter Zijlstra
2022-10-26 1:44 ` Waiman Long
[not found] ` <20221025145843.2953-1-hdanton@sina.com>
2022-10-25 19:00 ` Waiman Long
2022-10-17 21:13 ` [PATCH v3 3/5] locking/rwsem: Change waiter->hanodff_set to a handoff_state enum Waiman Long
2022-10-17 21:13 ` [PATCH v3 4/5] locking/rwsem: Enable direct rwsem lock handoff Waiman Long
2022-10-17 21:13 ` [PATCH v3 5/5] locking/rwsem: Update handoff lock events tracking Waiman Long
[not found] ` <20221018111424.1007-1-hdanton@sina.com>
2022-10-18 14:13 ` [PATCH v3 4/5] locking/rwsem: Enable direct rwsem lock handoff Mukesh Ojha
2022-10-18 17:37 ` Waiman Long
[not found] ` <20221018235138.1088-1-hdanton@sina.com>
2022-10-19 0:39 ` Waiman Long
[not found] ` <20221019022934.1166-1-hdanton@sina.com>
2022-10-19 2:49 ` Waiman Long
[not found] ` <20221019070559.1220-1-hdanton@sina.com>
2022-10-19 15:02 ` Waiman Long
2022-10-24 16:18 ` Waiman Long
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=Y1aTpYba1Wwly48+@hirez.programming.kicks-ass.net \
--to=peterz@infradead.org \
--cc=boqun.feng@gmail.com \
--cc=hdanton@sina.com \
--cc=john.p.donnelly@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=longman@redhat.com \
--cc=mingo@redhat.com \
--cc=quic_mojha@quicinc.com \
--cc=wangting11@xiaomi.com \
--cc=will@kernel.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).