On Wed, Jul 08, 2015 at 11:06:57AM +0100, Peter Zijlstra wrote:

On Tue, Jul 07, 2015 at 06:24:22PM +0100, Will Deacon wrote:

quoted

When contended, architectures may be able to reduce the polling overhead
in ways which aren't expressible using a simple relax() primitive.

This patch allows architectures to override the use of
cpu_relax_lowlatency() in the qrwlock code and also implement their own
unlock macros in case explicit signalling is required to wake up a
`relaxed' CPU spinning on an unlock event.

No real objection, but could you do this _after_ you've converted
AARGH64 to use the normal qrwlock, such that you can show the benefit
with numbers?

Sure, although the biggest gain may be in the form of reduced power
consumption, which I can't easily measure on my development platform.

Will