| Subject | Re: [RFC][PATCH 1/5] x86: Remove const_udelay() caring about which cpu var it uses | From | Steven Rostedt <> | Date | Mon, 19 Sep 2011 19:31:32 -0400 |
| |
On Mon, 2011-09-19 at 16:51 -0500, Christoph Lameter wrote: > On Mon, 19 Sep 2011, Steven Rostedt wrote: > > > The __const_udelay() code originally used raw_smp_processor_id() > > in its calculations for a delaying. Probably because if it were > > to migrate, it would take much longer to do so than the requested > > delay. > > > > Switch from this_cpu_read() to __this_cpu_read() to document that > > the read is racy and we do not care. > > Is preemption disabled by all callers to __const_udelay?
Nope, because I triggered a splat with it :-) From lots of places.
-- Steve
|