On Wed, May 28, 2014 at 12:08:57PM +0300, Adrian Hunter wrote:
> On 05/28/2014 11:55 AM, Peter Zijlstra wrote:
> > On Wed, May 28, 2014 at 11:45:04AM +0300, Adrian Hunter wrote:
> >> perf tools like 'perf report' can aggregate samples by comm
> >> strings, which generally works.  However, there are other
> >> potential use-cases.  For example, to pair up 'calls'
> >> with 'returns' accurately (from branch events like Intel BTS)
> >> it is necessary to identify whether the process has exec'd.
> >> Although a comm event is generated when an 'exec' happens
> >> it is also generated whenever the comm string is changed
> >> on a whim (e.g. by prctl PR_SET_NAME).  This patch adds a
> >> flag to the comm event to differentiate one case from the
> >> other.
> >>
> >> In order to determine whether the kernel supports the new
> >> flag, a selection bit named 'exec' is added to struct
> >> perf_event_attr.  The bit does nothing but will cause
> >> perf_event_open() to fail if the bit is set on kernels
> >> that do not have it defined.
> >>
> > 
> >> --- a/include/uapi/linux/perf_event.h
> >> +++ b/include/uapi/linux/perf_event.h
> >> @@ -302,8 +302,8 @@ struct perf_event_attr {
> >>  				exclude_callchain_kernel : 1, /* exclude kernel callchains */
> >>  				exclude_callchain_user   : 1, /* exclude user callchains */
> >>  				mmap2          :  1, /* include mmap with inode data     */
> >> -
> >> -				__reserved_1   : 40;
> >> +				exec           :  1, /* flag comm events that are due to an exec */
> >> +				__reserved_1   : 39;
> >>  
> > 
> > Yah.. that's just sad :-(
> > 
> > the only capabilities mask we have is in the mmap() page, so without
> > mmap()ing we have no way to test that.
> > 
> > Would it make sense to call it comm_exec?
> 
> Yes, that is better.  Do you want me to resend the patch?

Nah, I'll frob it. Thanks!