----- Original Message ----- > From: "Konrad Rzeszutek Wilk" <konrad.wilk@xxxxxxxxxx> > To: "Paolo Bonzini" <pbonzini@xxxxxxxxxx> > Cc: linux-kernel@xxxxxxxxxxxxxxx, kvm@xxxxxxxxxxxxxxx, "Jim Mattson" <jmattson@xxxxxxxxxx>, "Wanpeng Li" > <wanpeng.li@xxxxxxxxxxx> > Sent: Wednesday, December 13, 2017 4:59:47 PM > Subject: Re: [PATCH] KVM: vmx: shadow more fields that are read/written on every vmexits > > On Wed, Dec 13, 2017 at 01:13:56PM +0100, Paolo Bonzini wrote: > > Compared to when VMCS shadowing was added to KVM, we are reading/writing > > a few more fields: the PML index, the interrupt status and the preemption > > timer value. The first two are because we are exposing more features > > to nested guests, the preemption timer is simply because we have grown > > a new optimization. Adding them to the shadow VMCS field lists reduces > > the cost of a vmexit by about 1000 clock cycles for each field that exists > > on bare metal. > > > > On the other hand, the guest BNDCFGS and TSC offset are not written on > > fast paths, so remove them. > > Which guest types? Linux? What about Windows Hyper-V /VMWare and such? Only KVM, but I don't see why any other hypervisor would have to write them more than once per MSR access. VMWRITEs do have a (small but visible) cost. > Does it hurt to have them retained? It does cost a little, though another patch I posted decreases that cost. Paolo
