On Fri, Jan 8, 2021 at 10:10 AM Eric Dumazet <edumazet@xxxxxxxxxx> wrote: > > On Fri, Jan 8, 2021 at 7:03 PM Stanislav Fomichev <sdf@xxxxxxxxxx> wrote: > > > > Add custom implementation of getsockopt hook for TCP_ZEROCOPY_RECEIVE. > > We skip generic hooks for TCP_ZEROCOPY_RECEIVE and have a custom > > call in do_tcp_getsockopt using the on-stack data. This removes > > 3% overhead for locking/unlocking the socket. > > > > Without this patch: > > 3.38% 0.07% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt > > | > > --3.30%--__cgroup_bpf_run_filter_getsockopt > > | > > --0.81%--__kmalloc > > > > With the patch applied: > > 0.52% 0.12% tcp_mmap [kernel.kallsyms] [k] __cgroup_bpf_run_filter_getsockopt_kern > > > > > OK but we are adding yet another indirect call. > > Can you add a patch on top of it adding INDIRECT_CALL_INET() avoidance ? Sure, but do you think it will bring any benefit? We don't have any indirect avoidance in __sys_getsockopt for the sock->ops->getsockopt() call. If we add it for this new bpf_bypass_getsockopt, we might as well add it for sock->ops->getsockopt? And we need some new INDIRECT_CALL_INET2 such that f2 doesn't get disabled when ipv6 is disabled :-/
