On Thu, Jun 6, 2019 at 5:23 PM Andreas Steinmetz <ast@xxxxxxxx> wrote: > > On Sat, 2019-06-01 at 22:03 -0700, Alexei Starovoitov wrote: > > On Fri, May 31, 2019 at 3:55 PM Andreas Steinmetz <ast@xxxxxxxx> wrote: > > > I do have a working eBPF program (handcrafted assembler) that has about > > > 600 instructions. This programs takes more than 2 CPU seconds to load. > > > > > > In short, the eBPF program selects and redirects packets, does MSS > > > clamping and sends ICMPs where required for IPv4 and IPv6. The eBPF > > > program is part of a project that will be GPLed when sufficiently > > > ready. > > > > > > I am willing to cobble something testable together and post it > > > (attachment only) or send it directly, if somebody on this list is > > > willing to investigate, why the verifier is having lots of CPU for > > > breakfast. > > > > Please post it to the bpf mailing list if it's reproducible on the > > latest kernel. > > Will do, probably over the weekend - I have to do this as an attached tgz, > though. text only please. bpf mailing list doesn't accept tarballs.
