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

From: Peter Zijlstra
Date: Thu Mar 24 2016 - 06:43:08 EST

On Thu, Mar 24, 2016 at 09:58:02AM +0000, Will Deacon wrote:
> On Wed, Mar 23, 2016 at 08:29:38PM +0100, Peter Zijlstra wrote:
> Not sure... I can imagine kgdb, for example, wanting to handle the stepping
> itself. You also need to play clever tricks if you want to step through
> LL/SC atomics, which the code here doesn't even try to handle (because
> it involves disassembling the instructions and applying a bunch of
> heuristics), so I imagine most debuggers wanting to take care of the step
> themselves.

Fair enough... right, a whole host of tricky this.