Re: trace_hardirqs_on/off vs. extra stack frames

2018-12-21 Thread Benjamin Herrenschmidt
On Thu, 2018-12-20 at 21:02 -0500, Steven Rostedt wrote: > On Fri, 21 Dec 2018 12:11:35 +1100 > Benjamin Herrenschmidt wrote: > > > Hi Steven ! > > > > I'm trying to untangle something, and I need your help :-) > > > > In commit 3cb5f1a3e58c0bd70d47d9907cc5c65192281dee, you added a summy > >

Re: trace_hardirqs_on/off vs. extra stack frames

2018-12-20 Thread Steven Rostedt
On Fri, 21 Dec 2018 12:11:35 +1100 Benjamin Herrenschmidt wrote: > Hi Steven ! > > I'm trying to untangle something, and I need your help :-) > > In commit 3cb5f1a3e58c0bd70d47d9907cc5c65192281dee, you added a summy > stack frame around the assembly calls to trace_hardirqs_on/off on the >

trace_hardirqs_on/off vs. extra stack frames

2018-12-20 Thread Benjamin Herrenschmidt
Hi Steven ! I'm trying to untangle something, and I need your help :-) In commit 3cb5f1a3e58c0bd70d47d9907cc5c65192281dee, you added a summy stack frame around the assembly calls to trace_hardirqs_on/off on the ground that when using the latency tracer (irqsoff), you might poke at CALLER_ADDR1