Re: [dpdk-dev] [RFC] net/virtio: use real barriers for vDPA

2018-12-14 Thread Ilya Maximets
On 14.12.2018 18:01, Michael S. Tsirkin wrote: > On Fri, Dec 14, 2018 at 05:03:43PM +0300, Ilya Maximets wrote: >> On 14.12.2018 15:58, Michael S. Tsirkin wrote: >>> On Fri, Dec 14, 2018 at 03:37:04PM +0300, Ilya Maximets wrote: SMP barriers are OK for software vhost implementation, but vDPA i

Re: [dpdk-dev] [RFC] net/virtio: use real barriers for vDPA

2018-12-14 Thread Michael S. Tsirkin
On Fri, Dec 14, 2018 at 05:03:43PM +0300, Ilya Maximets wrote: > On 14.12.2018 15:58, Michael S. Tsirkin wrote: > > On Fri, Dec 14, 2018 at 03:37:04PM +0300, Ilya Maximets wrote: > >> SMP barriers are OK for software vhost implementation, but vDPA is a > >> DMA capable hardware and we have to use a

Re: [dpdk-dev] [RFC] net/virtio: use real barriers for vDPA

2018-12-14 Thread Ilya Maximets
On 14.12.2018 15:58, Michael S. Tsirkin wrote: > On Fri, Dec 14, 2018 at 03:37:04PM +0300, Ilya Maximets wrote: >> SMP barriers are OK for software vhost implementation, but vDPA is a >> DMA capable hardware and we have to use at least DMA barriers to >> ensure the memory ordering. >> >> This patch

Re: [dpdk-dev] [RFC] net/virtio: use real barriers for vDPA

2018-12-14 Thread Michael S. Tsirkin
On Fri, Dec 14, 2018 at 03:37:04PM +0300, Ilya Maximets wrote: > SMP barriers are OK for software vhost implementation, but vDPA is a > DMA capable hardware and we have to use at least DMA barriers to > ensure the memory ordering. > > This patch mimics the kernel virtio-net driver in part of choos

[dpdk-dev] [RFC] net/virtio: use real barriers for vDPA

2018-12-14 Thread Ilya Maximets
SMP barriers are OK for software vhost implementation, but vDPA is a DMA capable hardware and we have to use at least DMA barriers to ensure the memory ordering. This patch mimics the kernel virtio-net driver in part of choosing barriers we need. Fixes: a3f8150eac6d ("net/ifcvf: add ifcvf vDPA dr