Re: [PATCH 3/3] KVM: x86: improve reexecute_instruction

2012-12-03 Thread Marcelo Tosatti
On Mon, Dec 03, 2012 at 04:33:01PM +0800, Xiao Guangrong wrote: > Hi Marcelo, > > Thanks for your patience. I was reading your reply over and over again, i > would > like to argue it more :). > Please see below. > > On 11/29/2012 08:21 AM, Marcelo Tosatti wrote: > > > > > https://lkml.org/lkml

Re: [PATCH 3/3] KVM: x86: improve reexecute_instruction

2012-12-03 Thread Xiao Guangrong
Hi Marcelo, Thanks for your patience. I was reading your reply over and over again, i would like to argue it more :). Please see below. On 11/29/2012 08:21 AM, Marcelo Tosatti wrote: > > https://lkml.org/lkml/2012/11/17/75 > > Does unshadowing work with large sptes at reexecute_instruction? Th

Re: [PATCH 3/3] KVM: x86: improve reexecute_instruction

2012-11-28 Thread Marcelo Tosatti
On Thu, Nov 29, 2012 at 07:16:50AM +0800, Xiao Guangrong wrote: > On 11/29/2012 06:40 AM, Xiao Guangrong wrote: > > On 11/29/2012 05:57 AM, Marcelo Tosatti wrote: > >> On Wed, Nov 28, 2012 at 10:59:35PM +0800, Xiao Guangrong wrote: > >>> On 11/28/2012 10:12 PM, Gleb Natapov wrote: > On Tue, No

Re: [PATCH 3/3] KVM: x86: improve reexecute_instruction

2012-11-28 Thread Marcelo Tosatti
On Thu, Nov 29, 2012 at 06:40:51AM +0800, Xiao Guangrong wrote: > On 11/29/2012 05:57 AM, Marcelo Tosatti wrote: > > On Wed, Nov 28, 2012 at 10:59:35PM +0800, Xiao Guangrong wrote: > >> On 11/28/2012 10:12 PM, Gleb Natapov wrote: > >>> On Tue, Nov 27, 2012 at 11:30:24AM +0800, Xiao Guangrong wrote:

Re: [PATCH 3/3] KVM: x86: improve reexecute_instruction

2012-11-28 Thread Xiao Guangrong
On 11/29/2012 06:40 AM, Xiao Guangrong wrote: > On 11/29/2012 05:57 AM, Marcelo Tosatti wrote: >> On Wed, Nov 28, 2012 at 10:59:35PM +0800, Xiao Guangrong wrote: >>> On 11/28/2012 10:12 PM, Gleb Natapov wrote: On Tue, Nov 27, 2012 at 11:30:24AM +0800, Xiao Guangrong wrote: > On 11/27/2012

Re: [PATCH 3/3] KVM: x86: improve reexecute_instruction

2012-11-28 Thread Xiao Guangrong
On 11/29/2012 05:57 AM, Marcelo Tosatti wrote: > On Wed, Nov 28, 2012 at 10:59:35PM +0800, Xiao Guangrong wrote: >> On 11/28/2012 10:12 PM, Gleb Natapov wrote: >>> On Tue, Nov 27, 2012 at 11:30:24AM +0800, Xiao Guangrong wrote: On 11/27/2012 06:41 AM, Marcelo Tosatti wrote: >> >>

Re: [PATCH 3/3] KVM: x86: improve reexecute_instruction

2012-11-28 Thread Marcelo Tosatti
On Wed, Nov 28, 2012 at 10:59:35PM +0800, Xiao Guangrong wrote: > On 11/28/2012 10:12 PM, Gleb Natapov wrote: > > On Tue, Nov 27, 2012 at 11:30:24AM +0800, Xiao Guangrong wrote: > >> On 11/27/2012 06:41 AM, Marcelo Tosatti wrote: > >> > > -return false; > +again: > +

Re: [PATCH 3/3] KVM: x86: improve reexecute_instruction

2012-11-28 Thread Xiao Guangrong
On 11/28/2012 10:12 PM, Gleb Natapov wrote: > On Tue, Nov 27, 2012 at 11:30:24AM +0800, Xiao Guangrong wrote: >> On 11/27/2012 06:41 AM, Marcelo Tosatti wrote: >> - return false; +again: + page_fault_count = ACCESS_ONCE(vcpu->kvm->arch.page_fault_count); + + /*

Re: [PATCH 3/3] KVM: x86: improve reexecute_instruction

2012-11-28 Thread Gleb Natapov
On Tue, Nov 27, 2012 at 11:30:24AM +0800, Xiao Guangrong wrote: > On 11/27/2012 06:41 AM, Marcelo Tosatti wrote: > > >> > >> - return false; > >> +again: > >> + page_fault_count = ACCESS_ONCE(vcpu->kvm->arch.page_fault_count); > >> + > >> + /* > >> + * if emulation was due to access to shadow

Re: [PATCH 3/3] KVM: x86: improve reexecute_instruction

2012-11-27 Thread Xiao Guangrong
On 11/28/2012 07:42 AM, Marcelo Tosatti wrote: > On Tue, Nov 27, 2012 at 11:30:24AM +0800, Xiao Guangrong wrote: >> On 11/27/2012 06:41 AM, Marcelo Tosatti wrote: >> - return false; +again: + page_fault_count = ACCESS_ONCE(vcpu->kvm->arch.page_fault_count); + + /* >

Re: [PATCH 3/3] KVM: x86: improve reexecute_instruction

2012-11-27 Thread Marcelo Tosatti
On Tue, Nov 27, 2012 at 11:30:24AM +0800, Xiao Guangrong wrote: > On 11/27/2012 06:41 AM, Marcelo Tosatti wrote: > > >> > >> - return false; > >> +again: > >> + page_fault_count = ACCESS_ONCE(vcpu->kvm->arch.page_fault_count); > >> + > >> + /* > >> + * if emulation was due to access to shadow

Re: [PATCH 3/3] KVM: x86: improve reexecute_instruction

2012-11-26 Thread Xiao Guangrong
On 11/27/2012 06:41 AM, Marcelo Tosatti wrote: >> >> -return false; >> +again: >> +page_fault_count = ACCESS_ONCE(vcpu->kvm->arch.page_fault_count); >> + >> +/* >> + * if emulation was due to access to shadowed page table >> + * and it failed try to unshadow page and re-enter t

Re: [PATCH 3/3] KVM: x86: improve reexecute_instruction

2012-11-26 Thread Marcelo Tosatti
On Tue, Nov 20, 2012 at 07:59:53AM +0800, Xiao Guangrong wrote: > The current reexecute_instruction can not well detect the failed instruction > emulation. It allows guest to retry all the instructions except it accesses > on error pfn. > > For example, some cases are nested-write-protect - if the