On Sat, 23 Jun 2018, Fenghua Yu wrote:
> On Sun, Jun 24, 2018 at 02:55:08AM +0200, Thomas Gleixner wrote:
> > On Sat, 23 Jun 2018, Fenghua Yu wrote:
> > > On Sat, Jun 23, 2018 at 11:17:03AM +0200, Thomas Gleixner wrote:
> > > > On Fri, 22 Jun 2018, Fenghua Yu wrote:
> > It's not treated as failure. The firmware simply does not have an handler
> > for #AC installed and dies. I hope you yelled at the firmware people
> > already.
>
> I think firmware does handle the split lock in its #AC handler because
> firmware shows the following log and system hangs:
>
> !!!! IA32 Exception Type - 11(#AC - Alignment Check) CPU Apic ID - 00000014!
> !
> ExceptionData - 00000000
> EIP - 6A9DB6C3, CS - 00000010, EFLAGS - 00010006
> ...
They even have a handler which makes the thing die, but never bothered to
enable #AC in the first place. So the handler is there to catch the case
that an operating system dares to enable #AC. Thank god, I don't have to
review that source code.
Thanks,
tglx
