On Wed, Jul 21, 2021 at 2:28 PM Kumar Kartikeya Dwivedi
<memxor@xxxxxxxxx> wrote:
>
> These eBPF tracepoint programs export data that is consumed by the
> helpers added in the previous commit.
>
> Also add support int the Makefile to generate a vmlinux.h header that
> would be used by other bpf.c files in later commits.
>
> Signed-off-by: Kumar Kartikeya Dwivedi <memxor@xxxxxxxxx>
> ---
> samples/bpf/Makefile | 25 ++++
> samples/bpf/xdp_sample.bpf.c | 215 +++++++++++++++++++++++++++++++++++
> samples/bpf/xdp_sample.bpf.h | 57 ++++++++++
> 3 files changed, 297 insertions(+)
> create mode 100644 samples/bpf/xdp_sample.bpf.c
> create mode 100644 samples/bpf/xdp_sample.bpf.h
>
[...]
> +
> +SEC("tp_btf/xdp_cpumap_kthread")
> +int BPF_PROG(tp_xdp_cpumap_kthread, int map_id, unsigned int processed,
> + unsigned int drops, int sched, struct xdp_cpumap_stats *xdp_stats)
> +{
> + // Using xdp_stats directly fails verification
nit: C++ style comment
> + u32 cpu = bpf_get_smp_processor_id();
> + struct datarec *rec;
> +
> + if (cpu < MAX_CPUS) {
tip: if you invert condition and exit early, the rest of your logic
will be less nested (same in few other places)
> + rec = &sample_data.cpumap_kthread_cnt[cpu];
> +
> + ATOMIC_ADD_NORMW(rec->processed, processed);
> + ATOMIC_ADD_NORMW(rec->dropped, drops);
> + ATOMIC_ADD_NORMW(rec->xdp_pass, xdp_stats->pass);
> + ATOMIC_ADD_NORMW(rec->xdp_drop, xdp_stats->drop);
> + ATOMIC_ADD_NORMW(rec->xdp_redirect, xdp_stats->redirect);
> + /* Count times kthread yielded CPU via schedule call */
> + if (sched)
> + ATOMIC_INC_NORMW(rec->issue);
> + }
> + return 0;
> +}
> +
[...]
