[PATCH 0/5] Important fixes for KVM-AMD

[Joerg Roedel <joerg.roedel@amd.com>]

Hi Avi, Marcelo,

here is a set of patches which fix problems in kvm-amd. Patch 1 fixes a
stupid problem with the event-reinjection introduced by me in my
previous patchset.  Patch 2 was a helper to find the bug patch 3 fixes.
I kept it in the patchset because it may be helpful in the future to
debug other problems too. Patch 3 is the most important fix because it
makes kvm-amd on 32 bit hosts work again.  Without this patch the first
vmrum fails with exit-reason VMEXIT_INVALID. Patch 4 fixes the Xen 4.0
shipped with SLES11 in nested svm. The last patch in this series fixes a
potential l2-guest breakout scenario because it may be possible for the
l2-guest to issue hypercalls directly to the host if the l1-hypervisor
does not intercept VMMCALL.

Thanks,

	Joerg

Diffstat:

 arch/x86/include/asm/msr-index.h |    2 +
 arch/x86/kvm/svm.c               |  108 ++++++++++++++++++++++++++++++++++++--
 arch/x86/kvm/x86.c               |    2 +-
 3 files changed, 106 insertions(+), 6 deletions(-)

Shortlog:

Joerg Roedel (5):
      KVM: X86: Fix stupid bug in exception reinjection path
      KVM: SVM: Dump vmcb contents on failed vmrun
      KVM: SVM: Fix wrong intercept masks on 32 bit
      KVM: SVM: Allow EFER.LMSLE to be set with nested svm
      KVM: SVM: Don't allow nested guest to VMMCALL into host