From a8ffcd8bb0273d59600c6310a80b81206096c113 Mon Sep 17 00:00:00 2001
From: Ivan Nardi <12729895+IvanNardi@users.noreply.github.com>
Date: Wed, 24 Nov 2021 10:46:48 +0100
Subject: Rework how hostname/SNI info is saved (#1330)

Looking at `struct ndpi_flow_struct` the two bigger fields are
`host_server_name[240]` (mainly for HTTP hostnames and DNS domains) and
`protos.tls_quic.client_requested_server_name[256]`
(for TLS/QUIC SNIs).

This commit aims to reduce `struct ndpi_flow_struct` size, according to
two simple observations:
 1) maximum one of these two fields is used for each flow. So it seems safe
to merge them;
 2) even if hostnames/SNIs might be very long, in practice they are rarely
longer than a fews tens of bytes. So, using a (single) large buffer is a
waste of memory for all kinds of flows. If we need to truncate the name,
we keep the *last* characters, easing domain matching.

Analyzing some real traffic, it seems safe to assume that the vast
majority of hostnames/SNIs is shorter than 80 bytes.

Hostnames/SNIs are always converted to lowercase.

Attention was given so as to be sure that unit-tests outputs are not
affected by this change.

Because of a bug, TLS/QUIC SNI were always truncated to 64 bytes (the
*first* 64 ones): as a consequence, there were some "Suspicious DGA
domain name" and "TLS Certificate Mismatch" false positives.
---
 python/ndpi.py            | 7 +++----
 python/ndpi_typestruct.py | 2 +-
 2 files changed, 4 insertions(+), 5 deletions(-)

(limited to 'python')

diff --git a/python/ndpi.py b/python/ndpi.py
index a31a41a17..ba081acb9 100644
--- a/python/ndpi.py
+++ b/python/ndpi.py
@@ -986,8 +986,8 @@ struct ndpi_flow_struct {
   /* Place textual flow info here */
   char flow_extra_info[16];
 
-  /* HTTP host or DNS query */
-  uint8_t host_server_name[240];
+  char host_server_name[80];
+
   uint8_t initial_binary_bytes[8], initial_binary_bytes_len;
   uint8_t risk_checked;
   ndpi_risk risk; /* Issues found with this flow [bitmask of ndpi_risk] */
@@ -1051,8 +1051,7 @@ struct ndpi_flow_struct {
     struct {
       char ssl_version_str[12];
       uint16_t ssl_version, server_names_len;
-      char client_requested_server_name[64], *server_names,
-      *alpn, *tls_supported_versions, *issuerDN, *subjectDN;
+      char *server_names, *alpn, *tls_supported_versions, *issuerDN, *subjectDN;
       uint32_t notBefore, notAfter;
       char ja3_client[33], ja3_server[33];
       uint16_t server_cipher;
diff --git a/python/ndpi_typestruct.py b/python/ndpi_typestruct.py
index 09c1f7d7e..3909897ee 100644
--- a/python/ndpi_typestruct.py
+++ b/python/ndpi_typestruct.py
@@ -686,7 +686,7 @@ NDPIFlowStruct._fields_ = [
     ("num_processed_pkts", c_uint8),
     ("extra_packets_func", CFUNCTYPE(c_int, POINTER(NDPIDetectionModuleStruct), POINTER(NDPIFlowStruct))),
     ("l4", L4),
-    ("host_server_name", c_ubyte * 256),
+    ("host_server_name", c_char * 80),
     ("http", Http),
     ("stun", Stun),
     ("ftp_imap_pop_smtp", FtpImapPopSmtp),
-- 
cgit v1.2.3