Re: [RFC PATCH] sys_membarrier(): system/process-wide memory barrier (x86) (v12)

[Steven Rostedt]

On Tue, 17 Mar 2015 04:44:11 -0700
"Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx> wrote:

> On Tue, Mar 17, 2015 at 07:40:56AM +0100, Peter Zijlstra wrote:
> > On Mon, Mar 16, 2015 at 10:26:11PM -0400, Steven Rostedt wrote:
> > > As I recently found out that this_cpu_read/write() is not that nice on
> > > all architectures,
> > 
> > In fact, they only really work well on x86. Aargh64 seems to have a semi
> > usable version, but mostly its quite horrible indeed.
> 
> Yeah, if you are in a preempt-disabled region, __this_cpu_read() and
> __this_cpu_write() generate much better code on most platforms.
> 

I was just having this discussion with Christoph. I originally switched
to using this_cpu_ptr(), but I'll try __this_cpu* instead. I think
Christoph recommended that too.

-- Steve
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/