Webinar: BPF Hardware Offload Deep Dive

Sep 25, 2018 - 11:00 a.m. EDT, Registration required

Watch the Replay Now

Presented by Jakub Kicinski

The first version of eBPF hardware offload was merged into the Linux kernel in October 2016 and became part of Linux v4.9. For the last two years the project has been growing and evolving to integrate more closely with the core kernel infrastructure and enable more advanced use cases. This talk will explain the internals of the kernel architecture of the offload and how it allows seamless execution of unmodified eBPF datapaths in HW.

Agenda
1. Short intro to NFP HW
2. Mapping eBPF onto NFP hardware
3. Integrating with kernel verifier for program offload
4. Offload of eBPF maps
5. Split hardware/driver processing

Three common questions will be answered during the webinar:
Question 1: How does the BPF programming model fit into a network flow processor?
Question 2: What are the benefits of hardware acceleration?
Question 3: How is the offload integrated into the upstreamed Linux kernel and how do you use it?

About the Presenter
Jakub Kicinski is a long term Linux kernel contributor, who has been leading the kernel team at Netronome for the last two years. Jakub’s major contributions include creation of BPF hardware offload mechanisms in the kernel and bpftool user space utility, as well as work on Linux kernel side of Open vSwitch offload.