Re: suspicious RCU usage (perf)

2013-08-30 Thread Frederic Weisbecker
On Tue, Aug 27, 2013 at 02:16:29PM +0200, Peter Zijlstra wrote: > On Mon, Aug 26, 2013 at 03:03:04PM -0400, Steven Rostedt wrote: > > > Is there some path through sys_perf_open_event that might be > > > missing a capability check perhaps ? > > > > > > > That's a question for Ingo, Peter or Jiri.

Re: suspicious RCU usage (perf)

2013-08-30 Thread Frederic Weisbecker
On Fri, Aug 30, 2013 at 05:59:36PM +0200, Peter Zijlstra wrote: > On Fri, Aug 30, 2013 at 05:52:43PM +0200, Frederic Weisbecker wrote: > > On Tue, Aug 27, 2013 at 02:16:29PM +0200, Peter Zijlstra wrote: > > > On Mon, Aug 26, 2013 at 03:03:04PM -0400, Steven Rostedt wrote: > > > > > Is there some pa

Re: suspicious RCU usage (perf)

2013-08-30 Thread Peter Zijlstra
On Fri, Aug 30, 2013 at 05:52:43PM +0200, Frederic Weisbecker wrote: > On Tue, Aug 27, 2013 at 02:16:29PM +0200, Peter Zijlstra wrote: > > On Mon, Aug 26, 2013 at 03:03:04PM -0400, Steven Rostedt wrote: > > > > Is there some path through sys_perf_open_event that might be > > > > missing a capabilit

Re: suspicious RCU usage (perf)

2013-08-30 Thread Frederic Weisbecker
On Tue, Aug 27, 2013 at 02:16:29PM +0200, Peter Zijlstra wrote: > On Mon, Aug 26, 2013 at 03:03:04PM -0400, Steven Rostedt wrote: > > > Is there some path through sys_perf_open_event that might be > > > missing a capability check perhaps ? > > > > > > > That's a question for Ingo, Peter or Jiri.

Re: suspicious RCU usage (perf)

2013-08-27 Thread Dave Jones
On Tue, Aug 27, 2013 at 07:58:12AM -0600, David Ahern wrote: > On 8/27/13 7:10 AM, Steven Rostedt wrote: > > On Mon, 26 Aug 2013 15:49:24 -0400 > > Dave Jones wrote: > > > > > >> > Do you have /sys/kernel/debug with access permissions? > >> > >> Ah, yeah, that'll be it. Good catch. > >>

Re: suspicious RCU usage (perf)

2013-08-27 Thread David Ahern
On 8/27/13 7:10 AM, Steven Rostedt wrote: On Mon, 26 Aug 2013 15:49:24 -0400 Dave Jones wrote: > Do you have /sys/kernel/debug with access permissions? Ah, yeah, that'll be it. Good catch. Sorry for the false alarm Steve ;) Yeah, but it still does not explain how perf got started. Perf

Re: suspicious RCU usage (perf)

2013-08-27 Thread Steven Rostedt
On Mon, 26 Aug 2013 15:49:24 -0400 Dave Jones wrote: > > Do you have /sys/kernel/debug with access permissions? > > Ah, yeah, that'll be it. Good catch. > > Sorry for the false alarm Steve ;) Yeah, but it still does not explain how perf got started. Perf requires a sys_perf_event_open() call

Re: suspicious RCU usage (perf)

2013-08-27 Thread Peter Zijlstra
On Mon, Aug 26, 2013 at 03:03:04PM -0400, Steven Rostedt wrote: > > Is there some path through sys_perf_open_event that might be > > missing a capability check perhaps ? > > > > That's a question for Ingo, Peter or Jiri. Its not something I've looked at recently, git blames Jiri and fweisbec for

Re: suspicious RCU usage (perf)

2013-08-26 Thread Dave Jones
On Mon, Aug 26, 2013 at 01:43:15PM -0600, David Ahern wrote: > On 8/26/13 12:29 PM, Dave Jones wrote: > > On Mon, Aug 26, 2013 at 02:18:14PM -0400, Steven Rostedt wrote: > > > On Mon, 26 Aug 2013 13:50:12 -0400 > > > Dave Jones wrote: > > > > > > > > This was triggered as a regular u

Re: suspicious RCU usage (perf)

2013-08-26 Thread David Ahern
On 8/26/13 12:29 PM, Dave Jones wrote: On Mon, Aug 26, 2013 at 02:18:14PM -0400, Steven Rostedt wrote: > On Mon, 26 Aug 2013 13:50:12 -0400 > Dave Jones wrote: > > > > This was triggered as a regular user fwiw. > > I had not been running perf, or any other tracing. It was just left >

Re: suspicious RCU usage (perf)

2013-08-26 Thread Steven Rostedt
On Mon, 26 Aug 2013 14:29:07 -0400 Dave Jones wrote: > On Mon, Aug 26, 2013 at 02:18:14PM -0400, Steven Rostedt wrote: > > On Mon, 26 Aug 2013 13:50:12 -0400 > > Dave Jones wrote: > > > > > > This was triggered as a regular user fwiw. > > > I had not been running perf, or any other tracing

Re: suspicious RCU usage (perf)

2013-08-26 Thread Dave Jones
On Mon, Aug 26, 2013 at 02:18:14PM -0400, Steven Rostedt wrote: > On Mon, 26 Aug 2013 13:50:12 -0400 > Dave Jones wrote: > > > > This was triggered as a regular user fwiw. > > I had not been running perf, or any other tracing. It was just left > > fuzzing over the weekend with no interactio

Re: suspicious RCU usage (perf)

2013-08-26 Thread Steven Rostedt
On Mon, 26 Aug 2013 13:50:12 -0400 Dave Jones wrote: > > This was triggered as a regular user fwiw. > I had not been running perf, or any other tracing. It was just left > fuzzing over the weekend with no interaction at all. So you are telling me that ftrace was enabled by a regular user? If so,

Re: suspicious RCU usage (perf)

2013-08-26 Thread Dave Jones
On Mon, Aug 26, 2013 at 01:30:41PM -0400, Steven Rostedt wrote: > > On Mon, Aug 26, 2013 at 10:58:38AM -0400, Dave Jones wrote: > > > Another day, another rcu backtrace.. > > > This says rc6, but it's pretty darn close to rc7, I think it was running > > > a build from Friday. > > > > Could

Re: suspicious RCU usage (perf)

2013-08-26 Thread Steven Rostedt
On Mon, 26 Aug 2013 09:29:28 -0700 "Paul E. McKenney" wrote: > On Mon, Aug 26, 2013 at 10:58:38AM -0400, Dave Jones wrote: > > Another day, another rcu backtrace.. > > This says rc6, but it's pretty darn close to rc7, I think it was running > > a build from Friday. > > Could you please send your

Re: suspicious RCU usage (perf)

2013-08-26 Thread Paul E. McKenney
On Mon, Aug 26, 2013 at 10:58:38AM -0400, Dave Jones wrote: > Another day, another rcu backtrace.. > This says rc6, but it's pretty darn close to rc7, I think it was running > a build from Friday. Could you please send your .config? Also, were you running ftrace, perf, RCU event tracing, or what?