file_analysis/Analyzer: Limit maximum number of violations

Just the same as for protocol analyzers, prevent from violation event overload.

NEWS

@@ -119,6 +119,9 @@ Changed Functionality
 
 - The number of analyzer violation events that can be raised by protocol
   analyzer instances is now capped by the const ``max_analyzer_violation_events``.
+
+- The number of analyzer violation events that can be raised by protocol and
+  file analyzer instances is now capped by the const ``max_analyzer_violation_events``.
   Its default is 1000 and the main purpose is to prevent analyzers from
   scheduling too many ``analyzer_violation_info`` events before the
   DPD ``max_violations`` script-level logic has a chance to run and disable

src/file_analysis/Analyzer.cc

@@ -7,8 +7,8 @@
 #include "zeek/file_analysis/File.h"
 #include "zeek/file_analysis/Manager.h"
 
-// For analyzer_violation_info
+#include "const.bif.netvar_h" // for max_analyzer_violations
-#include "event.bif.netvar_h"
+#include "event.bif.netvar_h" // for analyzer_violation_info
 
 namespace zeek::file_analysis
 	{
@@ -38,6 +38,12 @@ Analyzer::Analyzer(RecordValPtr arg_args, File* arg_file)
 	{
 	}
 
+const char* Analyzer::GetAnalyzerName() const
+	{
+	assert(tag);
+	return file_mgr->GetComponentName(tag).c_str();
+	}
+
 void Analyzer::AnalyzerConfirmation(zeek::Tag arg_tag)
 	{
 	if ( analyzer_confirmed )
@@ -60,6 +66,16 @@ void Analyzer::AnalyzerConfirmation(zeek::Tag arg_tag)
 
 void Analyzer::AnalyzerViolation(const char* reason, const char* data, int len, zeek::Tag arg_tag)
 	{
+	++analyzer_violations;
+
+	if ( analyzer_violations > BifConst::max_analyzer_violations )
+		{
+		if ( analyzer_violations == BifConst::max_analyzer_violations + 1 )
+			Weird("too_many_analyzer_violations");
+
+		return;
+		}
+
 	if ( ! analyzer_violation_info )
 		return;
 
@@ -78,4 +94,9 @@ void Analyzer::AnalyzerViolation(const char* reason, const char* data, int len,
 	event_mgr.Enqueue(analyzer_violation_info, tval, info);
 	}
 
+void Analyzer::Weird(const char* name, const char* addl)
+	{
+	zeek::reporter->Weird(GetFile(), name, addl, GetAnalyzerName());
+	}
+
 	} // namespace zeek::file_analysis

src/file_analysis/Analyzer.h

@@ -83,6 +83,11 @@ public:
 	 */
 	zeek::Tag Tag() const { return tag; }
 
+	/**
+	 * @return the name of the analyzer.
+	 */
+	const char* GetAnalyzerName() const;
+
 	/**
 	 * Returns the analyzer instance's internal ID. These IDs are unique
 	 * across all analyzers instantiated and can thus be used to
@@ -165,6 +170,12 @@ public:
 	virtual void AnalyzerViolation(const char* reason, const char* data = nullptr, int len = 0,
 	                               zeek::Tag tag = zeek::Tag());
 
+	/**
+	 * Convenience function that forwards directly to the corresponding
+	 * reporter->Weird(file, ...).
+	 */
+	void Weird(const char* name, const char* addl = "");
+
 protected:
 	/**
 	 * Constructor.  Only derived classes are meant to be instantiated.
@@ -195,6 +206,8 @@ private:
 	bool skip;
 	bool analyzer_confirmed;
 
+	uint64_t analyzer_violations = 0;
+
 	static ID id_counter;
 	};
 

testing/btest/Baseline/plugins.file/output

@@ -8,14 +8,15 @@ analyzer_confirmation_info, Files::ANALYZER_FOO, FCceqBvpMfirSN0Ri
 foo_piece, FCceqBvpMfirSN0Ri, The National Center 
 foo_piece, FCceqBvpMfirSN0Ri, net, consult your lo
 foo_piece, FCceqBvpMfirSN0Ri, most everything else
+analyzer_violation_info, Files::ANALYZER_FOO, FCceqBvpMfirSN0Ri, test violation 3, most everything 
 foo_piece, FCceqBvpMfirSN0Ri, low:\x0a\x0a   /Mac       
 foo_piece, FCceqBvpMfirSN0Ri, es and directories o
-analyzer_violation_info, Files::ANALYZER_FOO, FCceqBvpMfirSN0Ri, test violation 5, es and directori
 foo_piece, FCceqBvpMfirSN0Ri, r example, here is a
+analyzer_violation_info, Files::ANALYZER_FOO, FCceqBvpMfirSN0Ri, test violation 6, r example, here 
 foo_piece, FCceqBvpMfirSN0Ri, application, StuffIt
 foo_piece, FCceqBvpMfirSN0Ri, tion BinHex by doubl
 foo_piece, FCceqBvpMfirSN0Ri, laced, or are going 
+analyzer_violation_info, Files::ANALYZER_FOO, FCceqBvpMfirSN0Ri, test violation 9, laced, or are go
 foo_piece, FCceqBvpMfirSN0Ri, sers several documen
-analyzer_violation_info, Files::ANALYZER_FOO, FCceqBvpMfirSN0Ri, test violation 10, sers several doc
 foo_piece, FCceqBvpMfirSN0Ri, er or can be printed
 foo_piece, FCceqBvpMfirSN0Ri,  \x0a\x0aBug reports shoul

testing/btest/Baseline/plugins.file/weird.log

@@ -0,0 +1,11 @@
+### BTest baseline data generated by btest-diff. Do not edit. Use "btest -U/-u" to update. Requires BTest >= 0.63.
+#separator \x09
+#set_separator	,
+#empty_field	(empty)
+#unset_field	-
+#path	weird
+#open XXXX-XX-XX-XX-XX-XX
+#fields	ts	uid	id.orig_h	id.orig_p	id.resp_h	id.resp_p	name	addl	notice	peer	source
+#types	time	string	addr	port	addr	port	string	string	bool	string	string
+XXXXXXXXXX.XXXXXX	-	-	-	-	-	too_many_analyzer_violations	FCceqBvpMfirSN0Ri	F	zeek	FOO
+#close XXXX-XX-XX-XX-XX-XX

testing/btest/plugins/file-plugin/src/Foo.cc

@@ -25,7 +25,7 @@ bool Foo::DeliverStream(const u_char* data, uint64_t len)
 	AnalyzerConfirmation();
 	zeek::event_mgr.Enqueue(foo_piece, GetFile()->ToVal(),
 	                        zeek::make_intrusive<zeek::StringVal>(new zeek::String(data, len, 0)));
-	if ( ++i % 5 == 0 )
+	if ( ++i % 3 == 0 )
 		{
 		uint64_t threshold = 16;
 		AnalyzerViolation(zeek::util::fmt("test violation %d", i),

testing/btest/plugins/file.zeek

@@ -5,6 +5,10 @@
 # @TEST-EXEC: echo === >>output
 # @TEST-EXEC: ZEEK_PLUGIN_PATH=`pwd` zeek -r $TRACES/ftp/retr.trace %INPUT >>output
 # @TEST-EXEC: TEST_DIFF_CANONIFIER= btest-diff output
+# @TEST-EXEC: btest-diff weird.log
+
+# Suppress AnalyzerViolation() after the third one and create a weird.log.
+redef max_analyzer_violations = 3;
 
 event file_new(f: fa_file)
 	{