Re: [PATCH net-next 1/2] bpf: enable non-root eBPF programs

On 10/6/15 10:56 AM, Eric Dumazet wrote:

On Tue, 2015-10-06 at 10:50 -0700, Alexei Starovoitov wrote:

quoted

was also thinking that we can do it only in paths that actually
have multiple protocol layers, since today bpf is mainly used with
tcpdump(raw_socket) and new af_packet fanout both have cb cleared
on RX, because it just came out of alloc_skb and no layers were called,
and on TX we can clear 20 bytes in dev_queue_xmit_nit().
af_unix/netlink also have clean skb. Need to analyze tun and sctp...
but it feels overly fragile to save a branch in sk_filter,
so planning to go with
if(unlikely(prog->cb_access)) memset in sk_filter().

This will break TCP use of sk_filter().
skb->cb[] contains useful data in TCP layer.

oops. thanks for catching. In case of sk_filter on top of tcp sock,
it shouldn't be looking at cb at all.
I'm thinking to send a patch to get rid of cb access for socket filters
all together until better solution found.