On Mon, 2015-03-23 at 15:08 -0600, Alex Williamson wrote:
>
> I don't know what you're doing on POWER, I thought groups were
> equivalent to PEs, but on x86 we learn about isolation of PCI functions
> by standard PCI properties. Devices need to tell us that they're
> isolated via ACS capabilities
On Mon, 2015-03-23 at 17:07 -0300, casca...@linux.vnet.ibm.com wrote:
>
> I agree with you here. I think the bigger issue is that we are not
> making sure VFIO is secure, allowing functions to be assigned
> separately to different guests, even when we cannot guarantee we can
> safely reset a singl
On Mon, Mar 23, 2015 at 06:40:34AM -0600, Alex Williamson wrote:
>On Mon, 2015-03-23 at 15:40 +1100, Gavin Shan wrote:
>> On Sun, Mar 22, 2015 at 10:06:01PM -0600, Alex Williamson wrote:
>> >On Mon, 2015-03-23 at 14:56 +1100, Gavin Shan wrote:
>> >> On Sun, Mar 22, 2015 at 09:34:33PM -0600, Alex Wi
On Mon, 2015-03-23 at 17:07 -0300, casca...@linux.vnet.ibm.com wrote:
> On Mon, Mar 23, 2015 at 06:40:34AM -0600, Alex Williamson wrote:
> > On Mon, 2015-03-23 at 15:40 +1100, Gavin Shan wrote:
> > > On Sun, Mar 22, 2015 at 10:06:01PM -0600, Alex Williamson wrote:
> > > >On Mon, 2015-03-23 at 14:56
On Mon, Mar 23, 2015 at 06:40:34AM -0600, Alex Williamson wrote:
> On Mon, 2015-03-23 at 15:40 +1100, Gavin Shan wrote:
> > On Sun, Mar 22, 2015 at 10:06:01PM -0600, Alex Williamson wrote:
> > >On Mon, 2015-03-23 at 14:56 +1100, Gavin Shan wrote:
> > >> On Sun, Mar 22, 2015 at 09:34:33PM -0600, Ale
On Mon, 2015-03-23 at 15:40 +1100, Gavin Shan wrote:
> On Sun, Mar 22, 2015 at 10:06:01PM -0600, Alex Williamson wrote:
> >On Mon, 2015-03-23 at 14:56 +1100, Gavin Shan wrote:
> >> On Sun, Mar 22, 2015 at 09:34:33PM -0600, Alex Williamson wrote:
> >> >On Mon, 2015-03-23 at 14:02 +1100, Gavin Shan w
On Sun, Mar 22, 2015 at 10:06:01PM -0600, Alex Williamson wrote:
>On Mon, 2015-03-23 at 14:56 +1100, Gavin Shan wrote:
>> On Sun, Mar 22, 2015 at 09:34:33PM -0600, Alex Williamson wrote:
>> >On Mon, 2015-03-23 at 14:02 +1100, Gavin Shan wrote:
>> >> The patch adds one more parameter ("probe") to pc
On Mon, 2015-03-23 at 14:56 +1100, Gavin Shan wrote:
> On Sun, Mar 22, 2015 at 09:34:33PM -0600, Alex Williamson wrote:
> >On Mon, 2015-03-23 at 14:02 +1100, Gavin Shan wrote:
> >> The patch adds one more parameter ("probe") to pci_set_pcie_reset_state(),
> >> which allows to check if one particula
On Sun, Mar 22, 2015 at 09:34:33PM -0600, Alex Williamson wrote:
>On Mon, 2015-03-23 at 14:02 +1100, Gavin Shan wrote:
>> The patch adds one more parameter ("probe") to pci_set_pcie_reset_state(),
>> which allows to check if one particular PCI device can be resetted by the
>> function. The function
On Mon, 2015-03-23 at 14:02 +1100, Gavin Shan wrote:
> The patch adds one more parameter ("probe") to pci_set_pcie_reset_state(),
> which allows to check if one particular PCI device can be resetted by the
> function. The function will be reused to support PCI device specific methods
> maintained i
The patch adds one more parameter ("probe") to pci_set_pcie_reset_state(),
which allows to check if one particular PCI device can be resetted by the
function. The function will be reused to support PCI device specific methods
maintained in pci_dev_reset_methods[] in subsequent patch.
Cc: Brian Kin
11 matches
Mail list logo
