OASIS Open Mailing List Archives  ·  All Lists  ·  virtio  ·  2023-06

virtio — archive

[Date Prev]  |  [Thread Prev]  |  [Thread Next]  |  [Date Next]   —  [Date Index]  |  [Thread Index]  |  [Month Index]  |  [List Home]

[PATCH requirements 0/7] virtio net new features requirements


> From: Michael S. Tsirkin <[email protected]> > Sent: Tuesday, June 6, 2023 6:42 PM > > +## 3.6 Header data split for the receive virtqueue 1. The device > > +should be able to DMA the packet header and data to two different > > + memory locations, this enables driver and networking stack to perform > zero > > + copy to application buffer(s). > > what is header here? which layer? > Usually L2 to L4. To be defined further. > > +2. The driver should be able to configure maximum header buffer size per > > + virtqueue. > > +3. The header buffer to be in a physically contiguous memory per > > +virtqueue > > this is a requirement why? > Because fetching individual buffer memory pointer is sub-optimal. > > +4. The device should be able to indicate header data split in the receive > > + completion. > > +5. The device should be able to zero pad the header buffer when the > received > > + header is shorter than cpu cache line size. > > weirdly specific. > how does device even know the cache line? > A driver can tell how much padding to be done by keeping the cache line specific details in the driver, but only telling about padding size.

[Date Prev]  |  [Thread Prev]  |  [Thread Next]  |  [Date Next]   —  [Date Index]  |  [Thread Index]  |  [Month Index]  |  [List Home]