Re: [PATCH v2 5/5] x86/pti: Do not enable PTI on fixed Intel processors

[Alan Cox]

> > static int in_order_cpu(void)
> > {
> > 	/* Processors with CPU id etc */
> > 	if (x86_match_cpu(cpu_in_order))
> > 		return 1;
> > 	/* Other rules here */
> > 	return 0;
> > }  
> 
> Why does in-order vs out-of-order matter?
> 
> There are leaky SP3 gadgets which satisfy in-order requirements, so long
> as the processor is capable of speculating 3 instructions past an
> unresolved branch.
> 
> What would (at a guess) save an in-order speculative processor from
> being vulnerable is if memory reads are issued and resolve in program
> order, but in that case, it is not the in-order property of the
> processor which makes it safe.

Fair point - I should rename it cpu_speculates(). The atoms in that
list don't speculate.

Alan
[My Cyrix 6x86 had a different kind of meltdown problem....]