On Wed, May 18, 2016 at 04:10:37PM +0100, David Howells wrote: > (1) We could weaken the kernel memory model to for the benefit of arches > that have instructions that employ explicit acquire/release barriers - > but that may cause data races to occur based on assumptions we've > already made. Note, however, that powerpc already seems to have a > weaker memory model.
Linus always vehemently argues against weakening our memory model.