bpf, flow_dissector: Introduce BPF_FLOW_DISSECTOR_CONTINUE retcode for bpf progs

Currently, attaching BPF_PROG_TYPE_FLOW_DISSECTOR programs completely
replaces the flow-dissector logic with custom dissection logic. This
forces implementors to write programs that handle dissection for any
flows expected in the namespace.

It makes sense for flow-dissector BPF programs to just augment the
dissector with custom logic (e.g. dissecting certain flows or custom
protocols), while enjoying the broad capabilities of the standard
dissector for any other traffic.

Introduce BPF_FLOW_DISSECTOR_CONTINUE retcode. Flow-dissector BPF
programs may return this to indicate no dissection was made, and
fallback to the standard dissector is requested.

Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Stanislav Fomichev <sdf@google.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Link: https://lore.kernel.org/bpf/20220821113519.116765-3-shmulik.ladkani@gmail.com

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 934a2a8..7f87012 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5861,6 +5861,11 @@ enum bpf_ret_code {
         *    represented by BPF_REDIRECT above).
         */
        BPF_LWT_REROUTE = 128,
+       /* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR
+        *   to indicate that no custom dissection was performed, and
+        *   fallback to standard dissector is requested.
+        */
+       BPF_FLOW_DISSECTOR_CONTINUE = 129,
 };
 
 struct bpf_sock {

diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index a01817f..990429c 100644 (file)
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1022,11 +1022,14 @@ bool __skb_flow_dissect(const struct net *net,
                        prog = READ_ONCE(run_array->items[0].prog);
                        result = bpf_flow_dissect(prog, &ctx, n_proto, nhoff,
                                                  hlen, flags);
+                       if (result == BPF_FLOW_DISSECTOR_CONTINUE)
+                               goto dissect_continue;
                        __skb_flow_bpf_to_target(&flow_keys, flow_dissector,
                                                 target_container);
                        rcu_read_unlock();
                        return result == BPF_OK;
                }
+dissect_continue:
                rcu_read_unlock();
        }
 

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 1d6085e..f38814f 100644 (file)
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5861,6 +5861,11 @@ enum bpf_ret_code {
         *    represented by BPF_REDIRECT above).
         */
        BPF_LWT_REROUTE = 128,
+       /* BPF_FLOW_DISSECTOR_CONTINUE: used by BPF_PROG_TYPE_FLOW_DISSECTOR
+        *   to indicate that no custom dissection was performed, and
+        *   fallback to standard dissector is requested.
+        */
+       BPF_FLOW_DISSECTOR_CONTINUE = 129,
 };
 
 struct bpf_sock {