Re: [PATCH v3] kvm: mmu: lazy collapse small sptes into large sptes

2015-04-13 Thread Wanpeng Li
On Mon, Apr 13, 2015 at 11:06:25PM -0700, Andres Lagar-Cavilla wrote: >On Mon, Apr 13, 2015 at 10:25 PM, Wanpeng Li >wrote: >> Hi Andres, >> On Fri, Apr 10, 2015 at 11:05:26AM -0700, Andres Lagar-Cavilla wrote: >> [...] + if (sp->role.direct && + !kvm

Re: [PATCH v3] kvm: mmu: lazy collapse small sptes into large sptes

2015-04-13 Thread Andres Lagar-Cavilla
On Mon, Apr 13, 2015 at 10:25 PM, Wanpeng Li wrote: > Hi Andres, > On Fri, Apr 10, 2015 at 11:05:26AM -0700, Andres Lagar-Cavilla wrote: > [...] >>> + if (sp->role.direct && >>> + !kvm_is_reserved_pfn(pfn) && >>> + PageTransCompound(pfn_to_

Re: [PATCH v3] kvm: mmu: lazy collapse small sptes into large sptes

2015-04-13 Thread Wanpeng Li
Hi Andres, On Fri, Apr 10, 2015 at 11:05:26AM -0700, Andres Lagar-Cavilla wrote: [...] >> + if (sp->role.direct && >> + !kvm_is_reserved_pfn(pfn) && >> + PageTransCompound(pfn_to_page(pfn))) { > >Not your fault, but PageTransCompound is very

Re: [PATCH v3] kvm: mmu: lazy collapse small sptes into large sptes

2015-04-12 Thread Andres Lagar-Cavilla
On Sun, Apr 12, 2015 at 6:45 PM, Xiao Guangrong wrote: > > > On 04/11/2015 02:05 AM, Andres Lagar-Cavilla wrote: >> >> On Fri, Apr 3, 2015 at 12:40 AM, Wanpeng Li >> wrote: >>> >>> >>> There are two scenarios for the requirement of collapsing small sptes >>> into large sptes. >>> - dirty logging

Re: [PATCH v3] kvm: mmu: lazy collapse small sptes into large sptes

2015-04-12 Thread Wanpeng Li
On Mon, Apr 13, 2015 at 09:45:39AM +0800, Xiao Guangrong wrote: > > >On 04/11/2015 02:05 AM, Andres Lagar-Cavilla wrote: >>On Fri, Apr 3, 2015 at 12:40 AM, Wanpeng Li >>wrote: >>> >>>There are two scenarios for the requirement of collapsing small sptes >>>into large sptes. >>>- dirty logging trac

Re: [PATCH v3] kvm: mmu: lazy collapse small sptes into large sptes

2015-04-12 Thread Xiao Guangrong
On 04/11/2015 02:05 AM, Andres Lagar-Cavilla wrote: On Fri, Apr 3, 2015 at 12:40 AM, Wanpeng Li wrote: There are two scenarios for the requirement of collapsing small sptes into large sptes. - dirty logging tracks sptes in 4k granularity, so large sptes are split, the large sptes will be

Re: [PATCH v3] kvm: mmu: lazy collapse small sptes into large sptes

2015-04-07 Thread Paolo Bonzini
On 03/04/2015 09:40, Wanpeng Li wrote: > There are two scenarios for the requirement of collapsing small sptes > into large sptes. > - dirty logging tracks sptes in 4k granularity, so large sptes are split, > the large sptes will be reallocated in the destination machine and the > guest in th

[PATCH v3] kvm: mmu: lazy collapse small sptes into large sptes

2015-04-03 Thread Wanpeng Li
There are two scenarios for the requirement of collapsing small sptes into large sptes. - dirty logging tracks sptes in 4k granularity, so large sptes are split, the large sptes will be reallocated in the destination machine and the guest in the source machine will be destroyed when live migrat