Messages in this thread | | | Date | Mon, 21 Nov 2016 14:06:41 -0500 | From | Steven Rostedt <> | Subject | Re: [BUG] msr-trace.h:42 suspicious rcu_dereference_check() usage! |
| |
On Mon, 21 Nov 2016 10:37:00 -0800 Andi Kleen <andi@firstfloor.org> wrote:
> Ok so how should tracing in idle code work then in your opinion?
As I suggested already. If we can get a light weight rcu_is_watching() then we can do the rcu_idle work when needed, and not when we don't need it. Sure this will add more branches, but that's still cheaper than popf.
-- Steve
| |