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

From: Salvatore Bonaccorso <carnil@debian.org>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Jeremi Piotrowski <jpiotrowski@linux.microsoft.com>,
	Dusty Mabe <dustymabe@redhat.com>, Stefan Roese <sr@denx.de>,
	linux-kernel@vger.kernel.org, linux-pci@vger.kernel.org,
	Bjorn Helgaas <bhelgaas@google.com>,
	Michal Simek <michal.simek@xilinx.com>,
	Marek Vasut <marex@denx.de>,
	x86@kernel.org, maz@kernel.org,
	Andrew Cooper <andrew.cooper3@citrix.com>,
	Juergen Gross <jgross@suse.com>,
	Noah Meyerhans <noahm@debian.org>
Subject: Re: [tip: irq/urgent] PCI/MSI: Mask MSI-X vectors only on success
Date: Fri, 29 Apr 2022 08:37:30 +0200	[thread overview]
Message-ID: <YmuHqi5K/P8QWYyO@eldamar.lan> (raw)
In-Reply-To: <YmrgO09bqePgiJJd@eldamar.lan>

Hi Thomas,

On Thu, Apr 28, 2022 at 08:43:10PM +0200, Salvatore Bonaccorso wrote:
> 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).

To confirm: Noah tested the patch on various different Xen (and other
VM configurations) and works well.

Regards,
Salvatore