Re: RFC: vfio-pci API for PCI bus/slot (hot) resets

2013-08-02 Thread Benjamin Herrenschmidt
On Fri, 2013-08-02 at 17:37 -0600, Alex Williamson wrote: > > Yes. > > > > We have that similar issue with error handling, when the driver doesn't > > have the right hooks, we simulate an unplug, reset, then replug. > > > > Maybe we could provide generic helpers to do that... > > Devices going

Re: RFC: vfio-pci API for PCI bus/slot (hot) resets

2013-08-02 Thread Alex Williamson
On Sat, 2013-08-03 at 09:15 +1000, Benjamin Herrenschmidt wrote: > On Fri, 2013-08-02 at 16:49 -0600, Bjorn Helgaas wrote: > > [+cc linux-pci] > > > > On Fri, Aug 2, 2013 at 3:28 PM, Benjamin Herrenschmidt > > wrote: > > > > > Right. Another use case is, I know of devices that need a fundamental

Re: RFC: vfio-pci API for PCI bus/slot (hot) resets

2013-08-02 Thread Benjamin Herrenschmidt
On Fri, 2013-08-02 at 16:49 -0600, Bjorn Helgaas wrote: > [+cc linux-pci] > > On Fri, Aug 2, 2013 at 3:28 PM, Benjamin Herrenschmidt > wrote: > > > Right. Another use case is, I know of devices that need a fundamental > > reset (PERST) after applying a FW update. > > This is a tangent from the

Re: RFC: vfio-pci API for PCI bus/slot (hot) resets

2013-08-02 Thread Bjorn Helgaas
[+cc linux-pci] On Fri, Aug 2, 2013 at 3:28 PM, Benjamin Herrenschmidt wrote: > Right. Another use case is, I know of devices that need a fundamental > reset (PERST) after applying a FW update. This is a tangent from the real discussion here, but the question of resetting a device after a firmw

Re: RFC: vfio-pci API for PCI bus/slot (hot) resets

2013-08-02 Thread Benjamin Herrenschmidt
On Fri, 2013-08-02 at 10:36 -0600, Alex Williamson wrote: > > Also in some cases, at least for us, we have a problem where the scope > > of the reset can be larger than the group ... in this case I think we > > need to forbid the reset. > > Interesting, I would have ventured to guess that resets

Re: RFC: vfio-pci API for PCI bus/slot (hot) resets

2013-08-02 Thread Alex Williamson
On Fri, 2013-08-02 at 15:10 +1000, Benjamin Herrenschmidt wrote: > On Thu, 2013-08-01 at 16:18 -0600, Alex Williamson wrote: > > vfio-pci needs to support an interface to do hot resets (PCI parent > > bridge secondary bus reset). We need this to support reset of > > co-assigned devices where one

Re: RFC: vfio-pci API for PCI bus/slot (hot) resets

2013-08-01 Thread Benjamin Herrenschmidt
On Thu, 2013-08-01 at 16:18 -0600, Alex Williamson wrote: > vfio-pci needs to support an interface to do hot resets (PCI parent > bridge secondary bus reset). We need this to support reset of > co-assigned devices where one or more of the devices does not support > function level reset. In parti

RFC: vfio-pci API for PCI bus/slot (hot) resets

2013-08-01 Thread Alex Williamson
vfio-pci needs to support an interface to do hot resets (PCI parent bridge secondary bus reset). We need this to support reset of co-assigned devices where one or more of the devices does not support function level reset. In particular, discrete graphics cards typically have no reset options oth