Re: [PATCH v3] cgroup/bpf: fast path skb BPF filtering

[Martin KaFai Lau <kafai@fb.com>]

On Thu, Dec 16, 2021 at 01:21:26PM +0000, Pavel Begunkov wrote:
> On 12/15/21 22:07, Stanislav Fomichev wrote:
> > On Wed, Dec 15, 2021 at 11:55 AM Pavel Begunkov <asml.silence@gmail.com> wrote:
> > > 
> > > On 12/15/21 19:15, Stanislav Fomichev wrote:
> > > > On Wed, Dec 15, 2021 at 10:54 AM Pavel Begunkov <asml.silence@gmail.com> wrote:
> > > > > 
> > > > > On 12/15/21 18:24, sdf@google.com wrote:
> [...]
> > > > > > I can probably do more experiments on my side once your patch is
> > > > > > accepted. I'm mostly concerned with getsockopt(TCP_ZEROCOPY_RECEIVE).
> > > > > > If you claim there is visible overhead for a direct call then there
> > > > > > should be visible benefit to using CGROUP_BPF_TYPE_ENABLED there as
> > > > > > well.
> > > > > 
> > > > > Interesting, sounds getsockopt might be performance sensitive to
> > > > > someone.
> > > > > 
> > > > > FWIW, I forgot to mention that for testing tx I'm using io_uring
> > > > > (for both zc and not) with good submission batching.
> > > > 
> > > > Yeah, last time I saw 2-3% as well, but it was due to kmalloc, see
> > > > more details in 9cacf81f8161, it was pretty visible under perf.
> > > > That's why I'm a bit skeptical of your claims of direct calls being
> > > > somehow visible in these 2-3% (even skb pulls/pushes are not 2-3%?).
> > > 
> > > migrate_disable/enable together were taking somewhat in-between
> > > 1% and 1.5% in profiling, don't remember the exact number. The rest
> > > should be from rcu_read_lock/unlock() in BPF_PROG_RUN_ARRAY_CG_FLAGS()
> > > and other extra bits on the way.
> > 
> > You probably have a preemptiple kernel and preemptible rcu which most
> > likely explains why you see the overhead and I won't (non-preemptible
> > kernel in our env, rcu_read_lock is essentially a nop, just a compiler
> > barrier).
> 
> Right. For reference tried out non-preemptible, perf shows the function
> taking 0.8% with a NIC and 1.2% with a dummy netdev.
> 
> 
> > > I'm skeptical I'll be able to measure inlining one function,
> > > variability between boots/runs is usually greater and would hide it.
> > 
> > Right, that's why I suggested to mirror what we do in set/getsockopt
> > instead of the new extra CGROUP_BPF_TYPE_ENABLED. But I'll leave it up
> > to you, Martin and the rest.
I also suggested to try to stay with one way for fullsock context in v2
but it is for code readability reason.

How about calling CGROUP_BPF_TYPE_ENABLED() just next to cgroup_bpf_enabled()
in BPF_CGROUP_RUN_PROG_*SOCKOPT_*() instead ?
It is because both cgroup_bpf_enabled() and CGROUP_BPF_TYPE_ENABLED()
want to check if there is bpf to run before proceeding everything else
and then I don't need to jump to the non-inline function itself to see
if there is other prog array empty check.

Stan, do you have concern on an extra inlined sock_cgroup_ptr()
when there is bpf prog to run for set/getsockopt()?  I think
it should be mostly noise from looking at
__cgroup_bpf_run_filter_*sockopt()?