All of lore.kernel.org
 help / color / mirror / Atom feed
From: Steven Rostedt <rostedt@goodmis.org>
To: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
	Andi Kleen <andi@firstfloor.org>, Jiri Olsa <jolsa@redhat.com>,
	linux-kernel@vger.kernel.org, Ingo Molnar <mingo@kernel.org>,
	Josh Triplett <josh@joshtriplett.org>,
	Jan Stancek <jstancek@redhat.com>
Subject: Re: [BUG] msr-trace.h:42 suspicious rcu_dereference_check() usage!
Date: Mon, 21 Nov 2016 13:24:38 -0500	[thread overview]
Message-ID: <20161121132438.2440d82f@gandalf.local.home> (raw)
In-Reply-To: <20161121125501.768ae998@gandalf.local.home>


Paul,


On Mon, 21 Nov 2016 12:55:01 -0500
Steven Rostedt <rostedt@goodmis.org> wrote:

> On Mon, 21 Nov 2016 18:18:53 +0100
> Peter Zijlstra <peterz@infradead.org> wrote:
> 
> > Its not ftrace as such though, its RCU, ftrace simply uses RCU to avoid
> > locking, as one does.  
> 
> Just to be clear, as ftrace in the kernel mostly represents function
> tracing, which doesn't use RCU. This is a tracepoint feature.
> 
> > 
> > Biggest objection would be that the rcu_irq_enter_irqson() thing does
> > POPF and rcu_irq_exit_irqson() does again. So wrapping every tracepoint
> > with that is quite a few cycles.  
> 
> Agree. Even though this ends up being a whack-a-mole(TM) fix, I'm not
> concerned enough to put a heavy weight rcu idle code in for all
> tracepoints.
> 
> Although, what about a percpu flag that can be checked in the
> tracepoint code to see if it should enable RCU or not?
> 
> Hmm, I wonder if "rcu_is_watching()" is light enough to have in all
> tracepoints?

Is it possible to make rcu_is_watching() an inlined call to prevent the
overhead of doing a function call? This way we could use this in the
fast path of the tracepoint.

-- Steve

  reply	other threads:[~2016-11-21 18:24 UTC|newest]

Thread overview: 48+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-11-21  0:53 [BUG] msr-trace.h:42 suspicious rcu_dereference_check() usage! Jiri Olsa
2016-11-21  9:02 ` Paul E. McKenney
2016-11-21  9:43   ` Peter Zijlstra
2016-11-21 11:00     ` Paul E. McKenney
2016-11-21  9:28 ` Peter Zijlstra
2016-11-21  9:34   ` Jiri Olsa
2016-11-21  9:42     ` Peter Zijlstra
2016-11-21 11:22       ` Jiri Olsa
2016-11-21 11:31         ` Peter Zijlstra
2016-11-21 12:49           ` Jiri Olsa
2016-11-21 12:58     ` Peter Zijlstra
2016-11-21 14:15       ` Steven Rostedt
2016-11-21 14:37         ` Peter Zijlstra
2016-11-21 15:35           ` Borislav Petkov
2016-11-21 15:41             ` Peter Zijlstra
2016-11-21 16:06               ` Borislav Petkov
2016-11-29 13:16                 ` Borislav Petkov
2016-11-29 13:59                   ` Thomas Gleixner
2016-11-30  8:48                     ` Borislav Petkov
2016-11-30  8:54                       ` Thomas Gleixner
2016-11-30  9:07                         ` Borislav Petkov
2016-11-30  9:14                           ` Thomas Gleixner
2016-11-29 14:04                   ` Jiri Olsa
2016-11-21 14:20       ` Steven Rostedt
2016-11-21 17:06   ` Andi Kleen
2016-11-21 17:18     ` Peter Zijlstra
2016-11-21 17:45       ` Andi Kleen
2016-11-21 18:01         ` Steven Rostedt
2016-11-21 18:06           ` Andi Kleen
2016-11-21 18:22             ` Steven Rostedt
2016-11-21 18:37               ` Andi Kleen
2016-11-21 19:06                 ` Steven Rostedt
2016-11-21 19:15                 ` Steven Rostedt
2016-11-21 20:44                   ` Andi Kleen
2016-11-22  8:19                     ` Paul E. McKenney
2016-11-22 14:39                 ` Steven Rostedt
2016-11-22 19:05                   ` Andi Kleen
2016-11-24  2:06                 ` Steven Rostedt
2016-11-28 21:48                   ` Andi Kleen
2016-11-28 22:46                     ` Steven Rostedt
2016-11-28 23:10                       ` Andi Kleen
2016-11-21 17:55       ` Steven Rostedt
2016-11-21 18:24         ` Steven Rostedt [this message]
2016-11-21 20:12           ` Paul E. McKenney
2017-02-23 12:24   ` Jiri Olsa
2017-02-23 17:11     ` Andi Kleen
2017-02-23 17:28     ` Peter Zijlstra
2017-02-23 17:56       ` Borislav Petkov

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=20161121132438.2440d82f@gandalf.local.home \
    --to=rostedt@goodmis.org \
    --cc=andi@firstfloor.org \
    --cc=jolsa@redhat.com \
    --cc=josh@joshtriplett.org \
    --cc=jstancek@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=peterz@infradead.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 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.