[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20211029121558.GU2744544@nvidia.com>
Date: Fri, 29 Oct 2021 09:15:58 -0300
From: Jason Gunthorpe <jgg@...dia.com>
To: Shameerali Kolothum Thodi <shameerali.kolothum.thodi@...wei.com>
Cc: Alex Williamson <alex.williamson@...hat.com>,
Cornelia Huck <cohuck@...hat.com>,
Yishai Hadas <yishaih@...dia.com>,
"bhelgaas@...gle.com" <bhelgaas@...gle.com>,
"saeedm@...dia.com" <saeedm@...dia.com>,
"linux-pci@...r.kernel.org" <linux-pci@...r.kernel.org>,
"kvm@...r.kernel.org" <kvm@...r.kernel.org>,
"netdev@...r.kernel.org" <netdev@...r.kernel.org>,
"kuba@...nel.org" <kuba@...nel.org>,
"leonro@...dia.com" <leonro@...dia.com>,
"kwankhede@...dia.com" <kwankhede@...dia.com>,
"mgurtovoy@...dia.com" <mgurtovoy@...dia.com>,
"maorg@...dia.com" <maorg@...dia.com>,
"Dr. David Alan Gilbert" <dgilbert@...hat.com>
Subject: Re: [PATCH V2 mlx5-next 12/14] vfio/mlx5: Implement vfio_pci driver
for mlx5 devices
On Fri, Oct 29, 2021 at 10:32:03AM +0000, Shameerali Kolothum Thodi wrote:
> Just trying to follow the thread here. The above situation where MMIOs can be
> further poked in the !RUNNING state, do you mean poking through P2P or
> Guest/Qemu can still do that? I am just trying to see if the current uAPI fits well
> within the use case where we don't have any P2P scenario and the assigned dev
> is behind the IOMMU.
The way it is today any VFIO user can poke MMIO while in the !RUNNING
state, no P2P needed, just write to the mmap.
Jason
Powered by blists - more mailing lists