[PATCH v3 05/10] KVM: x86: Restrict writeback of VCPU state

Do not write nmi_pending, sipi_vector, and mpstate unless we at least go through a reset. And TSC as well as KVM wallclocks should only be written on full sync, otherwise we risk to drop some time on during state read-modify-write. Signed-off-by: Jan Kiszka jan.kis...@siemens.com --- kvm.h

Re: [PATCH v3 05/10] KVM: x86: Restrict writeback of VCPU state

On Wed, Feb 24, 2010 at 03:17:53PM +0100, Jan Kiszka wrote: Do not write nmi_pending, sipi_vector, and mpstate unless we at least go through a reset. And TSC as well as KVM wallclocks should only be written on full sync, otherwise we risk to drop some time on during state read-modify-write.

Re: [PATCH v3 05/10] KVM: x86: Restrict writeback of VCPU state

Marcelo Tosatti wrote: On Wed, Feb 24, 2010 at 03:17:53PM +0100, Jan Kiszka wrote: Do not write nmi_pending, sipi_vector, and mpstate unless we at least go through a reset. And TSC as well as KVM wallclocks should only be written on full sync, otherwise we risk to drop some time on during