On Fri, Apr 18, 2014 at 12:19:28AM -0400, Paolo Bonzini wrote:
Il 16/04/2014 18:52, Marcelo Tosatti ha scritto:
How about handling VM-entry error due to invalid state with
vmx-emulation_required = true;
continue to main vcpu loop;
What would reset it to false though? None of the places
Il 20/04/2014 22:13, Marcelo Tosatti ha scritto:
The same code which resets it to false inside the
handle_invalid_guest_state loop (so you would stop emulating
at the same point as you do with this patch).
So (barring any bugs where we fail to set vmx-emulation_required to
true) the
Il 16/04/2014 18:52, Marcelo Tosatti ha scritto:
How about handling VM-entry error due to invalid state with
vmx-emulation_required = true;
continue to main vcpu loop;
What would reset it to false though? None of the places that call
emulation_required() is a hot path right now, and this
On Thu, Mar 27, 2014 at 12:30:34PM +0100, Paolo Bonzini wrote:
About 25% of the time spent in emulation of invalid guest state
is wasted in checking whether emulation is required for the next
instruction. However, this almost never changes except when a
segment register (or TR or LDTR)
About 25% of the time spent in emulation of invalid guest state
is wasted in checking whether emulation is required for the next
instruction. However, this almost never changes except when a
segment register (or TR or LDTR) changes, or when there is a mode
transition (i.e. CR0 changes).
In fact,
