lkml.org 
[lkml]   [2013]   [Nov]   [13]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: perf/tracepoint yet another lockup
On Tue, 12 Nov 2013, Peter Zijlstra wrote:

> On Mon, Nov 11, 2013 at 05:28:21PM -0500, Vince Weaver wrote:
> > So are all tracepoints unsafe? Or just a subset?
>
> No, most should be fine. But finding the special ones seems interesting
> :/
>
> Disabling them all for now sure seems like the safe option.

Update on this, it was a false positive. It seems like the other crashes
I was seeing were also caused by tracepoint 24, the fuzzer just found them
via another code path I wasn't checking.

So from what I can tell the only troublesome tracepoint I've come across
is the original irq_vectors/irq_work_exit problem.

Vince



\
 
 \ /
  Last update: 2013-11-14 00:01    [W:0.033 / U:1.496 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site