Re: [tip: irq/urgent] PCI/MSI: Mask MSI-X vectors only on success

[Salvatore Bonaccorso <carnil@debian.org>]

Hi Thomas,

On Thu, Apr 28, 2022 at 03:48:03PM +0200, Thomas Gleixner wrote:
> On Wed, Apr 27 2022 at 19:35, Thomas Gleixner wrote:
> > On Wed, Apr 27 2022 at 09:59, Salvatore Bonaccorso wrote:
> > XEN guests do not use the common PCI mask/unmask machinery which would
> > unmask the interrupt on request_irq().
> >
> > So I assume that the following happens:
> >
> > Guest                     Hypervisor
> >
> > msix_capabilities_init()
> >         ....
> >         alloc_irq()
> >            xen_magic()  -> alloc_msix_interrupt()
> >                            request_irq()
> >
> >         msix_mask_all() -> trap
> >                              do_magic()
> > request_irq()
> >    unmask()
> >      xen_magic()
> >        unmask_evtchn()  -> do_more_magic()
> >
> > So I assume further that msix_mask_all() actually is able to mask the
> > interrupts in the hardware (ctrl word of the vector table) despite the
> > hypervisor having allocated and requested the interrupt already.
> >
> > Nothing in XEN_HVM handles PCI/MSI[-X] mask/unmask in the guest, so I
> > really have to ask why XEN_HVM does not disable PCI/MSI[-X] masking like
> > XEN_PV does. I can only assume the answer is voodoo...
> >
> > Maybe the XEN people have some more enlightened answers to that.
> 
> So I was talking to Juergen about this and he agrees, that for the case
> where a XEN HVM guest uses the PIRQ/Eventchannel mechanism PCI/MSI[-X]
> masking should be disabled like it is done for XEN PV.
> 
> Why the hypervisor grants the mask write is still mysterious, but I
> leave that to the folks who can master the XEN voodoo.
> 
> I'll send out a patch in minute.

Thank you. We are having Noah Meyerhans now testing the patch and he
will report back if it works (Cc'ed here now).

Regards,
Salvatore