Re: [dpdk-dev] [PATCH v4 0/4] Enable hotplug in vfio

2018-10-15 Thread Thomas Monjalon
04/10/2018 11:11, Burakov, Anatoly: > On 04-Oct-18 7:44 AM, Jeff Guo wrote: > > As we may know that the process of hotplug is different between igb_uio > > and vfio. For igb_uio, it could use uevent notification and memory > > failure handle mechanism for hot-unplug. But for vfio, when device is be

Re: [dpdk-dev] [PATCH v4 0/4] Enable hotplug in vfio

2018-10-04 Thread Burakov, Anatoly
On 04-Oct-18 7:44 AM, Jeff Guo wrote: As we may know that the process of hotplug is different between igb_uio and vfio. For igb_uio, it could use uevent notification and memory failure handle mechanism for hot-unplug. But for vfio, when device is be hot-unplugged, the uevent can not be detected i

[dpdk-dev] [PATCH v4 0/4] Enable hotplug in vfio

2018-10-03 Thread Jeff Guo
As we may know that the process of hotplug is different between igb_uio and vfio. For igb_uio, it could use uevent notification and memory failure handle mechanism for hot-unplug. But for vfio, when device is be hot-unplugged, the uevent can not be detected immediately, because of the vfio kernel m