Messages in this thread | | | Subject | Re: [PATCH v4 0/4] bpf: Introduce the new ability of eBPF programs to access hardware PMU counter | From | Alexei Starovoitov <> | Date | Wed, 29 Jul 2015 18:50:09 -0700 |
| |
On 7/29/15 5:08 PM, Daniel Borkmann wrote: > On 07/28/2015 01:17 PM, Kaixu Xia wrote: >> Previous patch v3 url: >> https://lkml.org/lkml/2015/7/23/203 > ... >> Kaixu Xia (3): >> bpf: Add new bpf map type to store the pointer to struct perf_event >> bpf: Implement function bpf_perf_event_read() that get the selected >> hardware PMU conuter >> samples/bpf: example of get selected PMU counter value >> >> Wang Nan (1): >> bpf: Make the bpf_prog_array_map more generic > > So kernel/bpf/ patches are usually going via netdev tree as main > development > happens there and to avoid cross tree conflicts, etc. Thus, please Cc also > netdev in the next iterations. > > Maybe when these patches are in a perfect shape at some point, perf folks > provide their Acked-by(s) to the series to give their consent, and then > this > should go via net-next? Or will this be organized differently?
In this case it looks that amount of kernel/bpf/ changes is higher than perf related. Also it looks like addition of bpf_perf_event_read() helper also won't affect anything on perf side, so in this case I think net-next tree is indeed a better fit.
| |