Re: [patch] perf wrong enabled time after attach/enable/enable

From: Vince Weaver
Date: Fri Aug 04 2017 - 09:36:05 EST


On Fri, 4 Aug 2017, Peter Zijlstra wrote:

> Testing if userspace rdpmc reads are supported... NEW BEHAVIOR
> Testing if rdpmc fallback works on sw events... PASSED
> Testing if userspace rdpmc reads give expected results... PASSED
>
> is that 'NEW BEHAVIOR' thing something I should worry about?

no, sorry, I've been working on cleaning up the outputs of the tests to be
less confusing.

NEW BEHAVIOR here means it has the "new" (since Linux 3.12) cap_usr_rdpmc
bit layout.

Vince