> From: Zhao, Yu [mailto:yu.zhao@xxxxxxxxx] > Sent: 18 December 2008 02:14 > To: Fischer, Anna > Cc: Jesse Barnes; linux-pci@xxxxxxxxxxxxxxx; Chiang, Alexander; > Helgaas, Bjorn; grundler@xxxxxxxxxxxxxxxx; greg@xxxxxxxxx; > mingo@xxxxxxx; matthew@xxxxxx; randy.dunlap@xxxxxxxxxx; > rdreier@xxxxxxxxx; horms@xxxxxxxxxxxx; yinghai@xxxxxxxxxx; linux- > kernel@xxxxxxxxxxxxxxx; kvm@xxxxxxxxxxxxxxx; > virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx > Subject: Re: [PATCH 0/13 v7] PCI: Linux kernel SR-IOV support > > Fischer, Anna wrote: > > I have two minor comments on this topic. > > > > 1) Currently the PF driver is called before the kernel initializes > VFs and > > their resources, and the current API does not allow the PF driver to > > detect that easily if the allocation of the VFs and their resources > > has succeeded or not. It would be quite useful if the PF driver gets > > notified when the VFs have been created successfully as it might have > > to do further device-specific work *after* IOV has been enabled. > > If the VF allocation fails in the PCI layer, then the SR-IOV core will > invokes the callback again to notify the PF driver with zero VF count. > The PF driver does not have to concern about this even the PCI layer > code fails (and actually it's very rare). Yes, this is good. > And I'm not sure why the PF driver wants to do further work *after* the > VF is allocated. Does this mean PF driver have to set up some internal > resources related to SR-IOV/VF? If yes, I suggest the PF driver do it > before VF allocation. The design philosophy of SR-IOV/VF is that VF is > treated as hot-plug device, which means it should be immediately usable > by VF driver (e.g. VF driver is pre-loaded) after it appears in the PCI > subsystem. If that is not the purpose, then PF driver should handle it > not depending on the SR-IOV, right? Yes, you are right. In fact I was assuming in this case that the PF driver might have to allocate VF specific resources before a PF <-> VF communication can be established but this can be done before the VF PCI device appears, so I was wrong with this. The current API is sufficient to handle all of this, so I am withdrawing my concern here ;-) > If you could elaborate your SR-IOV PF/VF h/w specific requirement, it > would be help for me to answer this question :-) > > > 2) Configuration of SR-IOV: the current API allows to enable/disable > > VFs from userspace via SYSFS. At the moment I am not quite clear what > > exactly is supposed to control these capabilities. This could be > > Linux tools or, on a virtualized system, hypervisor control tools. > > This depends on user application, you know, which depends on the usage > environment (i.e. native, KVM or Xen). > > > One thing I am missing though is an in-kernel API for this which I > > think might be useful. After all the PF driver controls the device, > > and, for example, when a device error occurs (e.g. a hardware failure > > which only the PF driver will be able to detect, not Linux), then the > > PF driver might have to de-allocate all resources, shut down VFs and > > reset the device, or something like that. In that case the PF driver > > needs to have a way to notify the Linux SR-IOV code about this and > > initiate cleaning up of VFs and their resources. At the moment, this > > would have to go through userspace, I believe, and I think that is > not > > an optimal solution. Yu, do you have an opinion on how this would be > > realized? > > Yes, the PF driver can use pci_iov_unregister to disable SR-IOV in case > the fatal error occurs. This function also sends notification to user > level through 'uevent' so user application can aware the change. If pci_iov_unregister is accessible for kernel drivers than this is in fact all we need. Thanks for the clarification. I think the patchset looks very good. Acked-by: Anna Fischer <anna.fischer@xxxxxx> -- To unsubscribe from this list: send the line "unsubscribe linux-pci" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
