Re: [PATCH v2 00/13] SMM implementation for KVM

["Radim Krčmář" <rkrcmar@redhat.com>]

I found a corner case that doesn't fit any specific patch:

We allow INIT while in SMM.  This brings some security complications as
we also don't reset hflags (another long standing bug?), but we don't
really need to because INIT in SMM is against the spec anyway;
APM May 2013 2:10.3.3 Exceptions and Interrupts,
  • INIT—The processor does not recognize INIT while in SMM.

SDM April 2015: 34.5.1  Initial SMM Execution Environment,
  Maskable hardware interrupts, exceptions, NMI interrupts, SMI
  interrupts, A20M interrupts, single-step traps, breakpoint traps, and
  INIT operations are inhibited when the processor enters SMM.

And there is no mention of an exception for INIT.
(Some extra old experiments say that INIT could be enabled, but that is
 not applicable now,  http://www.rcollins.org/ddj/Mar97/Mar97.html)

I think that INIT received before RSM should be delivered after.