KVM: x86: Defer the MMU unload to the normal path on an global INVPCID
authorSean Christopherson <seanjc@google.com>
Fri, 5 Mar 2021 01:10:58 +0000 (17:10 -0800)
committerPaolo Bonzini <pbonzini@redhat.com>
Mon, 15 Mar 2021 08:42:22 +0000 (04:42 -0400)
commitf66c53b3b94f658590e1012bf6d922f8b7e01bda
tree6fd546463edb4ae2f30d2168d9b2826095ed2457
parentc805f5d5585ab5e0cdac6b1ccf7086eb120fb7db
KVM: x86: Defer the MMU unload to the normal path on an global INVPCID

Defer unloading the MMU after a INVPCID until the instruction emulation
has completed, i.e. until after RIP has been updated.

On VMX, this is a benign bug as VMX doesn't touch the MMU when skipping
an emulated instruction.  However, on SVM, if nrip is disabled, the
emulator is used to skip an instruction, which would lead to fireworks
if the emulator were invoked without a valid MMU.

Fixes: eb4b248e152d ("kvm: vmx: Support INVPCID in shadow paging mode")
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210305011101.3597423-15-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
arch/x86/kvm/x86.c