linux-next.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Steven Rostedt <rostedt@goodmis.org>
To: Dave Hansen <dave@sr71.net>
Cc: sedat.dilek@gmail.com, Paul McKenney <paulmck@linux.vnet.ibm.com>,
	"Rafael J. Wysocki" <rjw@rjwysocki.net>,
	"Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
	linux-next <linux-next@vger.kernel.org>,
	LKML <linux-kernel@vger.kernel.org>,
	Stephen Rothwell <sfr@canb.auug.org.au>,
	Kristen Carlson Accardi <kristen@linux.intel.com>,
	"H. Peter Anvin" <hpa@linux.intel.com>,
	Rik van Riel <riel@redhat.com>, Mel Gorman <mgorman@suse.de>
Subject: Re: linux-next: Tree for Feb 4
Date: Thu, 5 Feb 2015 13:03:43 -0500	[thread overview]
Message-ID: <20150205130343.6ac0eda9@gandalf.local.home> (raw)
In-Reply-To: <54D3186F.7030500@sr71.net>

On Wed, 04 Feb 2015 23:14:55 -0800
Dave Hansen <dave@sr71.net> wrote:

> On 02/04/2015 05:53 PM, Sedat Dilek wrote:
> > The architecture-specific switch_mm() function can be called by offline
> > CPUs, but includes event tracing, which cannot be legally carried out
> > on offline CPUs.  This results in a lockdep-RCU splat.  This commit fixes
> > this splat by omitting the tracing when the CPU is offline.
> ...
> >>> >> >                 load_cr3(next->pgd);
> >>> >> > -               trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
> >>> >> > +               if (cpu_online(smp_processor_id()))
> >>> >> > +                       trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
> 
> Is this, perhaps, something that we should be doing in the generic trace
> code so that all of the trace users don't have to worry about it?  Also,
> this patch will add overhead to the code when tracing is off.  It would
> be best if we could manage to make the cpu_online() check only in the
> cases where the tracepoint is on.

Note, we can move the check into the code that enables or disables
trace points. I believe, the rcu part of a tracepoint is only the call
to the callbacks. The jump_label part should be safe outside of rcu.

In that case, instead, have this, which does exactly the same thing
without having any overhead of the branch when tracing is disabled:

(not tested)

Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
---
diff --git a/include/trace/events/tlb.h b/include/trace/events/tlb.h
index 13391d288107..040c1cdfe6d1 100644
--- a/include/trace/events/tlb.h
+++ b/include/trace/events/tlb.h
@@ -13,11 +13,13 @@
 	{ TLB_LOCAL_SHOOTDOWN,		"local shootdown" },		\
 	{ TLB_LOCAL_MM_SHOOTDOWN,	"local mm shootdown" }
 
-TRACE_EVENT(tlb_flush,
+TRACE_EVENT_CONDITION(tlb_flush,
 
 	TP_PROTO(int reason, unsigned long pages),
 	TP_ARGS(reason, pages),
 
+	TP_CONDITION(cpu_online(smp_processor_id()),
+
 	TP_STRUCT__entry(
 		__field(	  int, reason)
 		__field(unsigned long,  pages)

  parent reply	other threads:[~2015-02-05 18:03 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-02-04  8:35 linux-next: Tree for Feb 4 Stephen Rothwell
2015-02-04 12:26 ` Sedat Dilek
2015-02-04 15:16   ` Jens Axboe
2015-02-04 15:21     ` Sedat Dilek
2015-02-04 15:31       ` Jens Axboe
2015-02-04 15:36         ` Sedat Dilek
2015-02-04 15:58           ` Martin K. Petersen
2015-02-04 16:06             ` Sedat Dilek
2015-02-05  3:17               ` Martin K. Petersen
2015-02-05  3:41                 ` Sedat Dilek
2015-02-05 19:46                 ` Sedat Dilek
2015-02-06 15:24                   ` Sedat Dilek
2015-02-04 20:18 ` Sedat Dilek
2015-02-04 21:54   ` Rafael J. Wysocki
2015-02-04 21:53     ` Paul E. McKenney
2015-02-04 22:59       ` Rafael J. Wysocki
2015-02-04 23:51         ` Paul E. McKenney
2015-02-04 23:58           ` Sedat Dilek
2015-02-05  0:10           ` Paul E. McKenney
2015-02-05  0:30             ` Sedat Dilek
2015-02-05  0:57               ` Paul E. McKenney
2015-02-05  1:18                 ` Sedat Dilek
2015-02-05  1:51                   ` Paul E. McKenney
2015-02-05  1:53                     ` Sedat Dilek
2015-02-05  2:12                       ` Sedat Dilek
2015-02-05  4:13                         ` Paul E. McKenney
2015-02-05  7:14                       ` Dave Hansen
2015-02-05 14:37                         ` Paul E. McKenney
2015-02-05 14:57                         ` Sedat Dilek
2015-02-05 16:58                           ` Paul E. McKenney
2015-02-05 18:03                         ` Steven Rostedt [this message]
2015-02-05 18:08                           ` Steven Rostedt
2015-02-05 18:11                             ` Dave Hansen
2015-02-05 18:34                               ` Paul E. McKenney
2015-02-05 18:35                                 ` Dave Hansen
2015-02-05 18:45                                   ` Paul E. McKenney
2015-02-05 19:25                                     ` Sedat Dilek
2015-02-05 19:33                                       ` Paul E. McKenney
2015-02-05 19:42                                         ` Sedat Dilek
2015-02-05 19:58                                       ` Steven Rostedt
2015-02-05 20:07                                         ` Sedat Dilek
2015-02-05 20:22                                           ` Steven Rostedt
2015-02-05 20:50                                             ` Sedat Dilek
2015-02-05 21:45                                               ` Sedat Dilek
2015-02-05 22:09                                                 ` Steven Rostedt
2015-02-05 22:16                                                   ` Sedat Dilek
2015-02-05 23:11                                                     ` Steven Rostedt
2015-02-05 23:53                                                       ` Sedat Dilek
2015-02-06  0:03                                                         ` Sedat Dilek
2015-02-06  0:12                                                         ` Steven Rostedt
2015-02-06  0:14                                                           ` Sedat Dilek
2015-02-04 22:38     ` Sedat Dilek
2015-02-04 23:25       ` Rafael J. Wysocki
2015-02-04 23:54         ` Sedat Dilek
2015-02-04 22:46     ` Sedat Dilek
2015-02-04 23:30       ` Rafael J. Wysocki
2015-02-04 23:48         ` Sedat Dilek
  -- strict thread matches above, loose matches on Subject: below --
2022-02-04  4:14 Stephen Rothwell
2021-02-04  9:13 Stephen Rothwell
2020-02-04  4:19 Stephen Rothwell
2019-02-04  5:35 Stephen Rothwell
2016-02-04  3:48 Stephen Rothwell
2014-02-04  5:07 Stephen Rothwell
     [not found] ` <CAP=VYLpgLC_4yuPtQH_yAd8S9cqQAVu2uB2=Wf3q_zgY4uzkLw@mail.gmail.com>
2014-02-04 22:23   ` Stephen Rothwell
2014-02-05  0:41 ` Stephen Rothwell
2013-02-04  7:39 Stephen Rothwell
2013-02-04 13:56 ` James Hogan
2013-02-04 20:33   ` Stephen Rothwell

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=20150205130343.6ac0eda9@gandalf.local.home \
    --to=rostedt@goodmis.org \
    --cc=dave@sr71.net \
    --cc=hpa@linux.intel.com \
    --cc=kristen@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-next@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=rafael.j.wysocki@intel.com \
    --cc=riel@redhat.com \
    --cc=rjw@rjwysocki.net \
    --cc=sedat.dilek@gmail.com \
    --cc=sfr@canb.auug.org.au \
    /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).