> -----Original Message----- > From: David Marchand <david.march...@redhat.com> > Sent: Thursday, June 25, 2020 15:33 > To: Harman Kalra <hka...@marvell.com>; Jerin Jacob Kollanukkaran > <jer...@marvell.com> > Cc: Wang, Haiyue <haiyue.w...@intel.com>; dev <dev@dpdk.org>; Burakov, Anatoly > <anatoly.bura...@intel.com>; Thomas Monjalon <tho...@monjalon.net>; Andrew > Rybchenko > <arybche...@solarflare.com>; Maxime Coquelin <maxime.coque...@redhat.com> > Subject: Re: [dpdk-dev] [PATCH v16 2/2] eal: support for VFIO-PCI VF token > > On Mon, Jun 22, 2020 at 10:40 PM Harman Kalra <hka...@marvell.com> wrote: > > > > On Wed, Jun 17, 2020 at 02:33:21PM +0800, Haiyue Wang wrote: > > > The kernel module vfio-pci introduces the VF token to enable SR-IOV > > > support since 5.7. > > > > > > The VF token can be set by a vfio-pci based PF driver and must be known > > > by the vfio-pci based VF driver in order to gain access to the device. > > > > > > Signed-off-by: Haiyue Wang <haiyue.w...@intel.com> > > > Acked-by: Anatoly Burakov <anatoly.bura...@intel.com> > > > Acked-by: Andrew Rybchenko <arybche...@solarflare.com> > > > --- > > > > Tested-by: Harman Kalra <hka...@marvell.com> > > Thanks for the test Harman. > > I can see no complaint on using a single token for all devices, which
Yeah, not the best, but may meet with the most needed: create VFs by vfio-pci ;-) Since devarg was a private option for ALL kind of devices, and have to break the ABI policy to implement the design, so I drop this revision, choose to use it as a global option as "vfio-intr" option does. > is the only concern I would have with the last revision. > If everyone is ok with this choice, I will take this for -rc1. > > > -- > David Marchand
