Re: [RFC PATCH 00/16] x86/split_lock: Enable #AC exception for split locked accesses

[Peter Zijlstra]

On Thu, Jun 21, 2018 at 04:05:02PM -0700, Fenghua Yu wrote:

> But in a real case, when I enable #AC for split lock in kernel, reboot
> hits #AC because of split lock in firmware code and firmware handles #AC
> as fatal error and stops continuing to run.
> 
> It will take long time/forever for firmware to fix the split lock issue.
> Before the firmware issue is fixed, reboot or S4 cannot run if the feature
> is enabled by kernel.

Then it will take a long time / forever for people to use their machines
as they need. Don't you see that is a problem?

Either you take this real-time stuff serious and force BIOS monkeys to
get with the act, this includes no #AC but also very much force them
into abandoning SMM as a fail^Wfeature-platform.

Or it's all a joke and we'll continue to complain and shame..

> And if unlucky, I'm afraid the patch set even has no chance to be merged to
> upstream if maintainer's test machine has firmware split lock issue and the
> machine simply cannot reboot or go to S4 if the feature is enabled.

Well, then you'd better get those BIOS monkeys on board and fixing their
crap.