Re: Virtualizing MSI-X on IMS via VFIO

From: Jacob Pan <jacob.jun.pan@intel.com>
To: "Tian, Kevin" <kevin.tian@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>,
	Alex Williamson <alex.williamson@redhat.com>,
	Jason Gunthorpe <jgg@nvidia.com>,
	"Dey, Megha" <megha.dey@intel.com>,
	"Raj, Ashok" <ashok.raj@intel.com>,
	"Jiang, Dave" <dave.jiang@intel.com>,
	"Liu, Yi L" <yi.l.liu@intel.com>,
	"Lu, Baolu" <baolu.lu@intel.com>,
	"Williams, Dan J" <dan.j.williams@intel.com>,
	"Luck, Tony" <tony.luck@intel.com>,
	"Kumar, Sanjay K" <sanjay.k.kumar@intel.com>,
	LKML <linux-kernel@vger.kernel.org>, KVM <kvm@vger.kernel.org>,
	Kirti Wankhede <kwankhede@nvidia.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Marc Zyngier <maz@kernel.org>, Bjorn Helgaas <helgaas@kernel.org>,
	jacob.jun.pan@intel.com
Subject: Re: Virtualizing MSI-X on IMS via VFIO
Date: Thu, 24 Jun 2021 10:03:16 -0700	[thread overview]
Message-ID: <20210624100316.1c1c4c6f@jacob-builder> (raw)
In-Reply-To: <MWHPR11MB1886E14C57689A253D9B40C08C079@MWHPR11MB1886.namprd11.prod.outlook.com>

Hi Kevin,

On Wed, 23 Jun 2021 19:41:24 -0700, "Tian, Kevin" <kevin.tian@intel.com>
wrote:

> > > 1)  Fix the lost interrupt issue in existing MSI virtualization flow;
> > >  
> >
> > That _cannot_ be fixed without a hypercall. See my reply to Alex.  
> 
> The lost interrupt issue was caused due to resizing based on stale
> impression of vector exhaustion.

Is it possible to mitigate the lost interrupt by always injecting an IRQ
after unmask? Either in VFIO layer, or let QEMU do that after the second
VFIO_DEVICE_SET_IRQS in step 4.b of your original email.

After all, spurious interrupts should be tolerated and unmasking MSI-x
should be rare. I am not suggesting this as an alternative to the real fix,
just a stop gap.

Thanks,

Jacob