Re: [PATCH 1/3] KVM: x86: use native MSR ops for SPEC_CTRL

On Fri, Feb 23, 2018 at 06:35:30PM +0100, Paolo Bonzini wrote: > On 23/02/2018 18:22, Konrad Rzeszutek Wilk wrote: > > On Fri, Feb 23, 2018 at 10:37:49AM +0100, Paolo Bonzini wrote: > >> On 22/02/2018 18:07, Konrad Rzeszutek Wilk wrote: > Having a paravirt indirect call in the IBRS restore

Re: [PATCH 1/3] KVM: x86: use native MSR ops for SPEC_CTRL

On Fri, Feb 23, 2018 at 06:35:30PM +0100, Paolo Bonzini wrote: > On 23/02/2018 18:22, Konrad Rzeszutek Wilk wrote: > > On Fri, Feb 23, 2018 at 10:37:49AM +0100, Paolo Bonzini wrote: > >> On 22/02/2018 18:07, Konrad Rzeszutek Wilk wrote: > Having a paravirt indirect call in the IBRS restore

Re: [PATCH 1/3] KVM: x86: use native MSR ops for SPEC_CTRL

On 23/02/2018 18:22, Konrad Rzeszutek Wilk wrote: > On Fri, Feb 23, 2018 at 10:37:49AM +0100, Paolo Bonzini wrote: >> On 22/02/2018 18:07, Konrad Rzeszutek Wilk wrote: Having a paravirt indirect call in the IBRS restore path is not a good idea, since we are trying to protect from

Re: [PATCH 1/3] KVM: x86: use native MSR ops for SPEC_CTRL

On 23/02/2018 18:22, Konrad Rzeszutek Wilk wrote: > On Fri, Feb 23, 2018 at 10:37:49AM +0100, Paolo Bonzini wrote: >> On 22/02/2018 18:07, Konrad Rzeszutek Wilk wrote: Having a paravirt indirect call in the IBRS restore path is not a good idea, since we are trying to protect from

Re: [PATCH 1/3] KVM: x86: use native MSR ops for SPEC_CTRL

On Fri, Feb 23, 2018 at 10:37:49AM +0100, Paolo Bonzini wrote: > On 22/02/2018 18:07, Konrad Rzeszutek Wilk wrote: > >> Having a paravirt indirect call in the IBRS restore path is not a > >> good idea, since we are trying to protect from speculative execution > >> of bogus indirect branch targets.

Re: [PATCH 1/3] KVM: x86: use native MSR ops for SPEC_CTRL

On Fri, Feb 23, 2018 at 10:37:49AM +0100, Paolo Bonzini wrote: > On 22/02/2018 18:07, Konrad Rzeszutek Wilk wrote: > >> Having a paravirt indirect call in the IBRS restore path is not a > >> good idea, since we are trying to protect from speculative execution > >> of bogus indirect branch targets.

Re: [PATCH 1/3] KVM: x86: use native MSR ops for SPEC_CTRL

On 22/02/2018 18:07, Konrad Rzeszutek Wilk wrote: >> Having a paravirt indirect call in the IBRS restore path is not a >> good idea, since we are trying to protect from speculative execution >> of bogus indirect branch targets. It is also slower, so use >> native_wrmsrl on the vmentry path too. >

Re: [PATCH 1/3] KVM: x86: use native MSR ops for SPEC_CTRL

On 22/02/2018 18:07, Konrad Rzeszutek Wilk wrote: >> Having a paravirt indirect call in the IBRS restore path is not a >> good idea, since we are trying to protect from speculative execution >> of bogus indirect branch targets. It is also slower, so use >> native_wrmsrl on the vmentry path too. >

Re: [PATCH 1/3] KVM: x86: use native MSR ops for SPEC_CTRL

On Wed, Feb 21, 2018 at 10:41:35PM +0100, Paolo Bonzini wrote: > Having a paravirt indirect call in the IBRS restore path is not a > good idea, since we are trying to protect from speculative execution > of bogus indirect branch targets. It is also slower, so use > native_wrmsrl on the vmentry

Re: [PATCH 1/3] KVM: x86: use native MSR ops for SPEC_CTRL

On Wed, Feb 21, 2018 at 10:41:35PM +0100, Paolo Bonzini wrote: > Having a paravirt indirect call in the IBRS restore path is not a > good idea, since we are trying to protect from speculative execution > of bogus indirect branch targets. It is also slower, so use > native_wrmsrl on the vmentry

Re: [PATCH 1/3] KVM: x86: use native MSR ops for SPEC_CTRL

On Wed, Feb 21, 2018 at 1:41 PM, Paolo Bonzini wrote: > Having a paravirt indirect call in the IBRS restore path is not a > good idea, since we are trying to protect from speculative execution > of bogus indirect branch targets. It is also slower, so use > native_wrmsrl on

Re: [PATCH 1/3] KVM: x86: use native MSR ops for SPEC_CTRL

On Wed, Feb 21, 2018 at 1:41 PM, Paolo Bonzini wrote: > Having a paravirt indirect call in the IBRS restore path is not a > good idea, since we are trying to protect from speculative execution > of bogus indirect branch targets. It is also slower, so use > native_wrmsrl on the vmentry path too.