Remove classification "by-ip" from protocol stack (#1743)

Basically:
* "classification by-ip" (i.e. `flow->guessed_protocol_id_by_ip` is
NEVER returned in the protocol stack (i.e.
`flow->detected_protocol_stack[]`);
* if the application is interested into such information, it can access
`ndpi_protocol->protocol_by_ip` itself.

There are mainly 4 points in the code that set the "classification
by-ip" in the protocol stack:  the generic `ndpi_set_detected_protocol()`/
`ndpi_detection_giveup()` functions and the HTTP/STUN  dissectors.

In the unit tests output, a print about `ndpi_protocol->protocol_by_ip`
has been added for each flow: the huge diff of this commit is mainly due
to that.

Strictly speaking, this change is NOT an API/ABI breakage, but there are
important differences in the classification results. For examples:
* TLS flows without the initial handshake (or without a matching
SNI/certificate) are simply classified as `TLS`;
* similar for HTTP or QUIC flows;
* DNS flows without a matching request domain are simply classified as
`DNS`; we don't have `DNS/Google` anymore just because the server is
8.8.8.8 (that was an outrageous behaviour...);
* flows previusoly classified only "by-ip" are now classified as
`NDPI_PROTOCOL_UNKNOWN`.

See #1425 for other examples of why adding the "classification by-ip" in
the protocol stack is a bad idea.

Please, note that IPV6 is not supported :(  (long standing issue in nDPI) i.e.
`ndpi_protocol->protocol_by_ip` wil be always `NDPI_PROTOCOL_UNKNOWN` for
IPv6 flows.

Define `NDPI_CONFIDENCE_MATCH_BY_IP` has been removed.

Close #1687
This commit is contained in:
Ivan Nardi 2022-09-20 22:24:47 +02:00 committed by GitHub
parent 174cd739db
commit a7c2734b38
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
379 changed files with 9022 additions and 9061 deletions

View file

@ -737,7 +737,7 @@ void extcap_capture() {
void printCSVHeader() {
if(!csv_fp) return;
fprintf(csv_fp, "#flow_id,protocol,first_seen,last_seen,duration,src_ip,src_port,dst_ip,dst_port,ndpi_proto_num,ndpi_proto,server_name_sni,");
fprintf(csv_fp, "#flow_id,protocol,first_seen,last_seen,duration,src_ip,src_port,dst_ip,dst_port,ndpi_proto_num,ndpi_proto,proto_by_ip,server_name_sni,");
fprintf(csv_fp, "c_to_s_pkts,c_to_s_bytes,c_to_s_goodput_bytes,s_to_c_pkts,s_to_c_bytes,s_to_c_goodput_bytes,");
fprintf(csv_fp, "data_ratio,str_data_ratio,c_to_s_goodput_ratio,s_to_c_goodput_ratio,");
@ -1284,9 +1284,11 @@ static void printFlow(u_int32_t id, struct ndpi_flow_info *flow, u_int16_t threa
ndpi_protocol2id(ndpi_thread_info[thread_id].workflow->ndpi_struct,
flow->detected_protocol, buf, sizeof(buf)));
fprintf(csv_fp, "%s,%s,",
fprintf(csv_fp, "%s,%s,%s,",
ndpi_protocol2name(ndpi_thread_info[thread_id].workflow->ndpi_struct,
flow->detected_protocol, buf, sizeof(buf)),
ndpi_get_proto_name(ndpi_thread_info[thread_id].workflow->ndpi_struct,
flow->detected_protocol.protocol_by_ip),
flow->host_server_name);
fprintf(csv_fp, "%u,%llu,%llu,", flow->src2dst_packets,
@ -1401,11 +1403,14 @@ static void printFlow(u_int32_t id, struct ndpi_flow_info *flow, u_int16_t threa
if(flow->tunnel_type != ndpi_no_tunnel)
fprintf(out, "%s:", ndpi_tunnel2str(flow->tunnel_type));
fprintf(out, "%s/%s]",
fprintf(out, "%s/%s][IP: %u/%s]",
ndpi_protocol2id(ndpi_thread_info[thread_id].workflow->ndpi_struct,
flow->detected_protocol, buf, sizeof(buf)),
ndpi_protocol2name(ndpi_thread_info[thread_id].workflow->ndpi_struct,
flow->detected_protocol, buf1, sizeof(buf1)));
flow->detected_protocol, buf1, sizeof(buf1)),
flow->detected_protocol.protocol_by_ip,
ndpi_get_proto_name(ndpi_thread_info[thread_id].workflow->ndpi_struct,
flow->detected_protocol.protocol_by_ip));
fprintf(out, "[%s]",
ndpi_is_encrypted_proto(ndpi_thread_info[thread_id].workflow->ndpi_struct,