On Thu, Dec 30, 2010 at 01:27:15PM +0200, Avi Kivity wrote: > On 12/30/2010 01:07 PM, Michael S. Tsirkin wrote: > >On Thu, Dec 30, 2010 at 12:37:18PM +0200, Avi Kivity wrote: > >> On 12/30/2010 12:32 PM, Michael S. Tsirkin wrote: > >> >On Thu, Dec 30, 2010 at 11:30:12AM +0200, Avi Kivity wrote: > >> >> On 12/30/2010 09:47 AM, Michael S. Tsirkin wrote: > >> >> >I am not really suggesting this. What I say is PBA is unimplemented > >> >> >let us not commit to an interface yet. > >> >> > >> >> What happens to a guest that tries to use PBA? > >> >> It's a mandatory part of MSI-X, no? > >> > > >> >Yes. Unfortunately the pending bit is in fact a communication channel > >> >used for function specific purposes when mask bit is set, > >> >and 0 when unset. The spec even seems to *require* this use: > >> > > >> >I refer to this: > >> > > >> > For MSI and MSI-X, while a vector is masked, the function is prohibited > >> > from sending the associated message, and the function must set the > >> > associated Pending bit whenever the function would otherwise send the > >> > message. When software unmasks a vector whose associated Pending bit is > >> > set, the function must schedule sending the associated message, and > >> > clear the Pending bit as soon as the message has been sent. Note that > >> > clearing the MSI-X Function Mask bit may result in many messages needing > >> > to be sent. > >> > > >> > > >> > If a masked vector has its Pending bit set, and the associated > >> > underlying interrupt events are somehow satisfied (usually by software > >> > though the exact manner is function-specific), the function must clear > >> > the Pending bit, to avoid sending a spurious interrupt message later > >> > when software unmasks the vector. However, if a subsequent interrupt > >> > event occurs while the vector is still masked, the function must again > >> > set the Pending bit. > >> > > >> > > >> > Software is permitted to mask one or more vectors indefinitely, and > >> > service their associated interrupt events strictly based on polling > >> > their Pending bits. A function must set and clear its Pending bits as > >> > necessary to support this âpure pollingâ mode of operation. > >> > > >> >For assigned devices, supporting this would require > >> >that the mask bits on the device are set if the mask bit in > >> >guest is set (otherwise pending bits are disabled). > >> > >> Can't this be done by setting the real mask bit when the guest reads > >> the virtual pending bit, then reading the real pending bit? > > > >Function specific is function-specific, but most likely not, > >by that time the pending bit in the device might be clear: > >'clear the Pending bit as soon as the message has been sent' > > But when we set the mask bit, it must change the pending bit back to > the function-specific condition? All it says is 'whenever the function would otherwise send a message'. So this is function-specific, generally functions only send a message once per event, they don't resend it assuming that it was queued and will eventually be handled. > >> >Existing code does not support PBA in assigned devices, so at least it's > >> >not a regression there, and the virtio spec says nothing about this so > >> >we should be fine. > >> > >> Why isn't it subject to the pci spec? > >> > >> If an interrupt condition exits, the bit should be set. > > > >I wish. But this is not what the spec says above. It says if vector is > >unmasked, bit must be cleared. > > If interrupt condition exists, and the vector is masked, the pending > bit is set. Otherwise the pending bit is clear. Better? 'whenever the function would otherwise send a message' does not seem to match this description: functions do not generally keep sending messages as long as condition is satisfied (if you think about this, the optimization of not masking immediately in hardware relies on this). > -- > error compiling committee.c: too many arguments to function -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
