Re: [PATCH 2/5] perf core: Set event's default overflow_handler

[Peter Zijlstra]

On Wed, Mar 23, 2016 at 06:13:49PM +0000, Will Deacon wrote:

> > Will, why does it matter what the overflow handler is for this stuff?
> 
> Because ptrace registers an overflow handler for raising a SIGTRAP and
> ptrace users (e.g. GDB) expect to handle the single-stepping themselves.
> Perf, on the other hand, will livelock if the kernel doesn't do the
> stepping.

Ah makes sense.

> FWIW, I hate this whole thing. The only users of the perf side just seem
> to be people running whacky test cases and then pointing out the places
> where we're not identical to x86 :(

Yeah, its not my favourite part either. The whole breakpoint thing
doesn't quite behave like a regular PMU so its all a bit 'special'.