Re: Closing on the CR2 leak bug

2014-03-04 Thread Steven Rostedt
On Tue, 04 Mar 2014 15:44:26 -0800 "H. Peter Anvin" wrote: > On 03/04/2014 03:41 PM, Steven Rostedt wrote: > > > > The only other issue is if perf traces from function context and traces > > the trace_do_page_fault() call. But other than that, sure, take Jiri's > > patch. > > > > Is there a

Re: Closing on the CR2 leak bug

2014-03-04 Thread H. Peter Anvin
On 03/04/2014 03:41 PM, Steven Rostedt wrote: > > The only other issue is if perf traces from function context and traces > the trace_do_page_fault() call. But other than that, sure, take Jiri's > patch. > Is there a known codepath on which that can happen? -hpa -- To unsubscribe from

Re: Closing on the CR2 leak bug

2014-03-04 Thread Steven Rostedt
On Tue, 04 Mar 2014 14:34:00 -0800 "H. Peter Anvin" wrote: > So we need to get something into x86/urgent for the CR2 bug. > > It seems like a no-brainer to do the hoisting patch, for which I prefer > the version proposed by Jiri Olsa which reads %cr2 and then passes it to > __do_page_fault() in

Closing on the CR2 leak bug

2014-03-04 Thread H. Peter Anvin
So we need to get something into x86/urgent for the CR2 bug. It seems like a no-brainer to do the hoisting patch, for which I prefer the version proposed by Jiri Olsa which reads %cr2 and then passes it to __do_page_fault() in a GPR:

Closing on the CR2 leak bug

2014-03-04 Thread H. Peter Anvin
So we need to get something into x86/urgent for the CR2 bug. It seems like a no-brainer to do the hoisting patch, for which I prefer the version proposed by Jiri Olsa which reads %cr2 and then passes it to __do_page_fault() in a GPR:

Re: Closing on the CR2 leak bug

2014-03-04 Thread Steven Rostedt
On Tue, 04 Mar 2014 14:34:00 -0800 H. Peter Anvin h...@zytor.com wrote: So we need to get something into x86/urgent for the CR2 bug. It seems like a no-brainer to do the hoisting patch, for which I prefer the version proposed by Jiri Olsa which reads %cr2 and then passes it to

Re: Closing on the CR2 leak bug

2014-03-04 Thread H. Peter Anvin
On 03/04/2014 03:41 PM, Steven Rostedt wrote: The only other issue is if perf traces from function context and traces the trace_do_page_fault() call. But other than that, sure, take Jiri's patch. Is there a known codepath on which that can happen? -hpa -- To unsubscribe from this

Re: Closing on the CR2 leak bug

2014-03-04 Thread Steven Rostedt
On Tue, 04 Mar 2014 15:44:26 -0800 H. Peter Anvin h...@zytor.com wrote: On 03/04/2014 03:41 PM, Steven Rostedt wrote: The only other issue is if perf traces from function context and traces the trace_do_page_fault() call. But other than that, sure, take Jiri's patch. Is there a