[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CALCETrX3KOOhNP14CcZ60W9ys3F6hC+oH2xyF9a2OPOO_Lqv3Q@mail.gmail.com>
Date: Mon, 25 Jun 2018 16:30:39 -0700
From: Andy Lutomirski <luto@...nel.org>
To: Steven Rostedt <rostedt@...dmis.org>
Cc: Andrew Lutomirski <luto@...nel.org>,
"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
joel@...lfernandes.org, Byungchul Park <byungchul.park@....com>,
byungchul park <max.byungchul.park@...il.com>,
Lai Jiangshan <jiangshanlai@...il.com>,
Josh Triplett <josh@...htriplett.org>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
LKML <linux-kernel@...r.kernel.org>, kernel-team@....com
Subject: Re: [RFC 2/2] rcu: Remove ->dynticks_nmi_nesting from struct rcu_dynticks
On Mon, Jun 25, 2018 at 3:16 PM Steven Rostedt <rostedt@...dmis.org> wrote:
>
> On Mon, 25 Jun 2018 13:47:45 -0700
> Andy Lutomirski <luto@...nel.org> wrote:
>
> >
> > As a straightforward example, NMI and MCE can nest inside each other.
>
> But I'm not sure how stable the machine becomes when MCE's start
> interrupting NMIs. Also, can MCE callbacks use RCU?
>
> > IIRC we treat #DB somewhat NMI-ish-ly as well.
>
> And #DB is something I think we finally said shouldn't be done in NMIs,
> IIRC.
>
No one ever applied the patch to make it so, so we still support it.
Powered by blists - more mailing lists