From a7c2734b387f6817088593f7c4e78d01dd6e0b74 Mon Sep 17 00:00:00 2001 From: Ivan Nardi <12729895+IvanNardi@users.noreply.github.com> Date: Tue, 20 Sep 2022 22:24:47 +0200 Subject: 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 --- src/lib/protocols/http.c | 14 ++------------ 1 file changed, 2 insertions(+), 12 deletions(-) (limited to 'src/lib/protocols/http.c') diff --git a/src/lib/protocols/http.c b/src/lib/protocols/http.c index 6fd70d9b6..b50967a3c 100644 --- a/src/lib/protocols/http.c +++ b/src/lib/protocols/http.c @@ -335,22 +335,12 @@ static void ndpi_int_http_add_connection(struct ndpi_detection_module_struct *nd struct ndpi_flow_struct *flow, u_int16_t http_protocol, ndpi_protocol_category_t category) { - u_int16_t master_protocol, app_protocol; + u_int16_t master_protocol; #ifdef HTTP_DEBUG printf("=> %s()\n", __FUNCTION__); #endif - app_protocol = flow->guessed_protocol_id_by_ip; - /* If no custom protocol has been detected */ - if((app_protocol == NDPI_PROTOCOL_UNKNOWN) - || ((http_protocol != NDPI_PROTOCOL_HTTP) && - (http_protocol != NDPI_PROTOCOL_HTTP_CONNECT) && - (http_protocol != NDPI_PROTOCOL_HTTP_PROXY)) - ) - app_protocol = http_protocol; - - // ndpi_int_reset_protocol(flow); master_protocol = NDPI_PROTOCOL_HTTP; if(flow->detected_protocol_stack[1] != NDPI_PROTOCOL_UNKNOWN) master_protocol = flow->detected_protocol_stack[1]; @@ -363,7 +353,7 @@ static void ndpi_int_http_add_connection(struct ndpi_detection_module_struct *nd sub-protocol via the (content-matched) subprotocols logic (i.e. MPEGDASH, SOAP, ....) */ if(flow->detected_protocol_stack[1] == 0) - ndpi_set_detected_protocol(ndpi_struct, flow, app_protocol, + ndpi_set_detected_protocol(ndpi_struct, flow, http_protocol, master_protocol, NDPI_CONFIDENCE_DPI); -- cgit v1.2.3