This patch adds the OVS-eBPF datapath implementation for dpif-bpf. Three stages are added: parse, lookup, and actions. Each stages are tail called to the next stage. When executing multiple

The patch initializes the bpf datapath when bridge starts. The check_support could be avoided since we know what datapath bpf program supports what feature. Signed-off-by: Joe Stringer

From: Joe Stringer <joe@...> Add an implementation of the API between the userspace "Open vSwitch Datapath Protocol" and the BPF datapath. Signed-off-by: Joe Stringer

From: Joe Stringer <joe@...> Implement a new datapath interface for use with BPF datapaths. Like dpif-netlink, dpif-bpf is backed by an implementation which resides within the kernel. It uses

From: Joe Stringer <joe@...> Through libbpf, the patch adds support for loading bpf program and maps, pinning the program and map to /sys/fs/bpf/ovs/, managing the file descriptor of each loaded

From: Joe Stringer <joe@...> A flow missed by the match action table in ebpf triggers an upcall, which forwards the information to ovs-vswitchd using skb_perf_event_output helper function. The

From: Joe Stringer <joe@...> To receive packets, an eBPF program has to be attached to a netdev through tc ingress/egress, an XDP program has to be attached to a netdev's xdp hook point. The

From: Joe Stringer <joe@...> The patch add bpf installation guide and configuration for linking to libbpf library. Co-authored-by: William Tu <u9012063@...> Co-authored-by: Yifeng Sun

Existing OVS has three datapath types: Linux kernel (dpif-netlink), userspace (dpif-netdev), and Windows. This series add another type of OVS datapath: the eBPF datapath (dpif-bpf). eBPF stands for

I see. Thanks for the prompt reply! William

This will not work. '-coverage' flag will introduce some additional global functions called by the program, e.g., __llvm_gcov_init, __llvm_gcov_flush, etc. global memset functions are called from one

Hi, I'm trying to run coverage tests on my bpf program and it compiles fails. I guess BPF does not support '--coverage' flags? root@boxes:~/ovs# clang-4.0 -Wstrict-prototypes -Wall

Hi All, Thanks for attending the meeting today. As usual, here are my notes. === Discussion === Brenden: - working on fc28 packaging - pr available - includes some python3 fixes - not to be

Please join us tomorrow for our bi-weekly call. As usual, this meeting is open to everybody and completely optional. You might be interested to join if: You want to know what is going on in BPF

Argh, I see the issue. Working on a fix after checking the syzkaller reports. Thanks for the report!

Sebastiano Miano via iovisor-dev <iovisor-dev@...> wrote: Argh, this is likely an issue/bug due to the check xdp_map_invalid(), that was introduced in commit 7c3001313396 ("bpf: fix

Dear all, We have noticed that the bpf_redirect_map returns an error when it is called after a tail call. The xdp_redirect_map program (under sample/bpf) works fine, but if we modify it as shown in

All, Sorry about the timing of the announcement coming out immediately after the bi-weekly meeting. This is indeed something that we are doing across the entire spectrum of LF Projects and

FYI for the iovisor-dev subscribers. Alexei and I were given a heads up on this ahead of time and given a chance to find a service other than groups.io, but it seemed like a reasonable change that LF

Greetings IO Visor community! The Linux Foundation has connected with a new vendor called Groups.io, which provides mailing list services in a simple but modern interface. Groups.io offers all of the