linux-kernel - Re: [RFC PATCH] membarrier: handle nohz_full with expedited thread registration

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue, 17 Jan 2017 18:29:23 -0500
From:   Steven Rostedt <rostedt@...dmis.org>
To:     Mathieu Desnoyers <mathieu.desnoyers@...icios.com>
Cc:     fweisbec <fweisbec@...il.com>,
        Linus Torvalds <torvalds@...ux-foundation.org>,
        "Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
        linux-kernel <linux-kernel@...r.kernel.org>,
        Josh Triplett <josh@...htriplett.org>,
        KOSAKI Motohiro <kosaki.motohiro@...fujitsu.com>,
        Nicholas Miell <nmiell@...cast.net>,
        Ingo Molnar <mingo@...hat.com>,
        One Thousand Gnomes <gnomes@...rguk.ukuu.org.uk>,
        Lai Jiangshan <laijs@...fujitsu.com>,
        Stephen Hemminger <stephen@...workplumber.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Peter Zijlstra <peterz@...radead.org>,
        David Howells <dhowells@...hat.com>,
        bobby prani <bobby.prani@...il.com>,
        Michael Kerrisk <mtk.manpages@...il.com>,
        Shuah Khan <shuahkh@....samsung.com>,
        Andrew Morton <akpm@...ux-foundation.org>
Subject: Re: [RFC PATCH] membarrier: handle nohz_full with expedited thread
 registration

On Tue, 17 Jan 2017 21:56:38 +0000 (UTC)
Mathieu Desnoyers <mathieu.desnoyers@...icios.com> wrote:

> One goal here is to ensure we don't disturb threads that do not wish to receive
> those IPIs, so holding the rq lock while we send the IPI still seems to be safer.

What type of IPI is being sent? Be careful because IPIs can take the rq
lock, and if you are expecting the IPI to finish while holding the rq
lock you may introduce a deadlock.

-- Steve