Re: [PATCH 2/3] KVM: x86: introduce KVM_MEM_PCI_HOLE memory

2020-08-06 Thread Jim Mattson
On Wed, Aug 5, 2020 at 5:18 PM Michael S. Tsirkin wrote: > > On Wed, Aug 05, 2020 at 10:05:40AM -0700, Jim Mattson wrote: > > On Tue, Jul 28, 2020 at 7:38 AM Vitaly Kuznetsov > > wrote: > > > > > > PCIe config space can (depending on the configuration) be quite big but > > > usually is sparsely

Re: [PATCH 2/3] KVM: x86: introduce KVM_MEM_PCI_HOLE memory

2020-08-06 Thread Vitaly Kuznetsov
Jim Mattson writes: > On Tue, Jul 28, 2020 at 7:38 AM Vitaly Kuznetsov wrote: >> >> PCIe config space can (depending on the configuration) be quite big but >> usually is sparsely populated. Guest may scan it by accessing individual >> device's page which, when device is missing, is supposed to h

Re: [PATCH 2/3] KVM: x86: introduce KVM_MEM_PCI_HOLE memory

2020-08-06 Thread Vitaly Kuznetsov
Andrew Jones writes: > On Tue, Jul 28, 2020 at 04:37:40PM +0200, Vitaly Kuznetsov wrote: >> PCIe config space can (depending on the configuration) be quite big but >> usually is sparsely populated. Guest may scan it by accessing individual >> device's page which, when device is missing, is suppos

Re: [PATCH 2/3] KVM: x86: introduce KVM_MEM_PCI_HOLE memory

2020-08-05 Thread Michael S. Tsirkin
On Wed, Aug 05, 2020 at 10:05:40AM -0700, Jim Mattson wrote: > On Tue, Jul 28, 2020 at 7:38 AM Vitaly Kuznetsov wrote: > > > > PCIe config space can (depending on the configuration) be quite big but > > usually is sparsely populated. Guest may scan it by accessing individual > > device's page whic

Re: [PATCH 2/3] KVM: x86: introduce KVM_MEM_PCI_HOLE memory

2020-08-05 Thread Andrew Jones
On Tue, Jul 28, 2020 at 04:37:40PM +0200, Vitaly Kuznetsov wrote: > PCIe config space can (depending on the configuration) be quite big but > usually is sparsely populated. Guest may scan it by accessing individual > device's page which, when device is missing, is supposed to have 'pci > hole' sema

Re: [PATCH 2/3] KVM: x86: introduce KVM_MEM_PCI_HOLE memory

2020-08-05 Thread Jim Mattson
On Tue, Jul 28, 2020 at 7:38 AM Vitaly Kuznetsov wrote: > > PCIe config space can (depending on the configuration) be quite big but > usually is sparsely populated. Guest may scan it by accessing individual > device's page which, when device is missing, is supposed to have 'pci > hole' semantics:

[PATCH 2/3] KVM: x86: introduce KVM_MEM_PCI_HOLE memory

2020-07-28 Thread Vitaly Kuznetsov
PCIe config space can (depending on the configuration) be quite big but usually is sparsely populated. Guest may scan it by accessing individual device's page which, when device is missing, is supposed to have 'pci hole' semantics: reads return '0xff' and writes get discarded. Compared to the alrea