[0/6] RFC: KVM: SVM: Allow L1's AVIC to co-exist with nesting

Message

Maxim Levitsky Dec. 9, 2021, 11:54 a.m. UTC

This patch series aims to lift long standing restriction of
using AVIC only when nested virtualization is not exposed
to the guest.

Notes about specific patches:

Patch 1 addresses the fact that AVIC appears to be disabled
in CPUID on several Milan systems I am tesing on.
This adds a workaround (with a big warning and a kernel taint) to enable
it anyway if you really know what you are doing.

It is possible that those systems have the AVIC disabled as a workaround
for the AVIC errata #1235 which might be already fixed but OEM might
not yet re-enabled it out of caution.

Patch 6 adds the AVIC co-existance itself, and was tested with a modification
of the ipi_stress unit test which I soon post upstream which made one
of vCPUs enter nested guest and receive the IPI while nested guest is running.

It was tested on a Zen3 (Milan) machine. On Zen2 machines I have errata #1235
makes my test fail quite fast.

Best regards,
	Maxim Levitsky

Maxim Levitsky (6):
  KVM: SVM: allow to force AVIC to be enabled
  KVM: x86: add a tracepoint for APICv/AVIC interrupt delivery
  KVM: SVM: fix AVIC race of host->guest IPI delivery vs AVIC inhibition
  KVM: SVM: fix races in the AVIC incomplete IPI delivery to vCPUs
  KVM: x86: never clear irr_pending in kvm_apic_update_apicv
  KVM: SVM: allow AVIC to co-exist with a nested guest running

 arch/x86/include/asm/kvm-x86-ops.h |  1 +
 arch/x86/include/asm/kvm_host.h    |  7 +++++-
 arch/x86/kvm/lapic.c               |  6 ++++-
 arch/x86/kvm/svm/avic.c            | 35 +++++++++++++++++++++++-----
 arch/x86/kvm/svm/nested.c          | 13 ++++++-----
 arch/x86/kvm/svm/svm.c             | 37 +++++++++++++++++++-----------
 arch/x86/kvm/svm/svm.h             |  1 +
 arch/x86/kvm/trace.h               | 24 +++++++++++++++++++
 arch/x86/kvm/x86.c                 | 17 ++++++++++++--
 9 files changed, 111 insertions(+), 30 deletions(-)