From aa073586f1c4a936d3a64ef7cca7b77482d38b1a Mon Sep 17 00:00:00 2001
From: Mark Stemm <mark.stemm@sysdig.com>
Date: Thu, 5 Oct 2017 17:20:54 -0700
Subject: [PATCH] Add ability to filter events by priority/cleanups

Clean up the handling of priority levels within rules. It used to be a
mix of strings handled in various places. Now, in falco_common.h there's
a consistent type for priority-as-number as well as a list of
priority-as-string values. Priorities are passed around as numbers
instead of strings. It's still permissive about capitalization.

Also add the ability to load rules by severity. New falco
config option "priority=<val>"/-o priority=<val> specifies the minimum
priority level of rules that will be loaded.

Add unit tests for same. The test suppresses INFO notifications for a
rule/trace file combination that would otherwise generate them.
---
 falco.yaml                           |  6 ++++
 test/falco_test.py                   |  5 ++--
 test/falco_tests.yaml                | 15 ++++++++++
 userspace/engine/falco_common.cpp    | 10 +++++++
 userspace/engine/falco_common.h      | 16 +++++++++++
 userspace/engine/falco_engine.cpp    | 10 +++++--
 userspace/engine/falco_engine.h      |  6 +++-
 userspace/engine/lua/rule_loader.lua | 42 +++++++++++++++++++---------
 userspace/engine/rules.cpp           |  6 ++--
 userspace/engine/rules.h             |  5 +++-
 userspace/falco/configuration.cpp    | 13 +++++++++
 userspace/falco/configuration.h      |  2 ++
 userspace/falco/falco.cpp            |  4 ++-
 userspace/falco/falco_outputs.cpp    |  7 +++--
 userspace/falco/falco_outputs.h      |  2 +-
 userspace/falco/lua/output.lua       | 34 ++++++----------------
 16 files changed, 132 insertions(+), 51 deletions(-)

diff --git a/falco.yaml b/falco.yaml
index d407b75b..1dbfcd47 100644
--- a/falco.yaml
+++ b/falco.yaml
@@ -15,6 +15,12 @@ log_syslog: true
 # "alert", "critical", "error", "warning", "notice", "info", "debug".
 log_level: info
 
+# Minimum rule priority level to load and run. All rules having a
+# priority more severe than this level will be loaded/run.  Can be one
+# of "emergency", "alert", "critical", "error", "warning", "notice",
+# "info", "debug".
+priority: debug
+
 # A throttling mechanism implemented as a token bucket limits the
 # rate of falco notifications. This throttling is controlled by the following configuration
 # options:
diff --git a/test/falco_test.py b/test/falco_test.py
index 7aaf3595..8b9cf615 100644
--- a/test/falco_test.py
+++ b/test/falco_test.py
@@ -30,6 +30,7 @@ class FalcoTest(Test):
             self.trace_file = os.path.join(self.basedir, self.trace_file)
 
         self.json_output = self.params.get('json_output', '*', default=False)
+        self.priority = self.params.get('priority', '*', default='debug')
         self.rules_file = self.params.get('rules_file', '*', default=os.path.join(self.basedir, '../rules/falco_rules.yaml'))
 
         if not isinstance(self.rules_file, list):
@@ -347,8 +348,8 @@ class FalcoTest(Test):
             trace_arg = "-e {}".format(self.trace_file)
 
         # Run falco
-        cmd = '{} {} {} -c {} {} -o json_output={} -v'.format(
-            self.falco_binary_path, self.rules_args, self.disabled_args, self.conf_file, trace_arg, self.json_output)
+        cmd = '{} {} {} -c {} {} -o json_output={} -o priority={} -v'.format(
+            self.falco_binary_path, self.rules_args, self.disabled_args, self.conf_file, trace_arg, self.json_output, self.priority)
 
         for tag in self.disable_tags:
             cmd += ' -T {}'.format(tag)
diff --git a/test/falco_tests.yaml b/test/falco_tests.yaml
index 0449b1f0..485e87fb 100644
--- a/test/falco_tests.yaml
+++ b/test/falco_tests.yaml
@@ -129,6 +129,21 @@ trace_files: !mux
       - rules/double_rule.yaml
     trace_file: trace_files/cat_write.scap
 
+  multiple_rules_suppress_info:
+    detect: True
+    detect_level:
+      - WARNING
+      - ERROR
+    priority: WARNING
+    detect_counts:
+      - open_from_cat: 8
+      - exec_from_cat: 1
+      - access_from_cat: 0
+    rules_file:
+      - rules/single_rule.yaml
+      - rules/double_rule.yaml
+    trace_file: trace_files/cat_write.scap
+
   multiple_rules_overriding:
     detect: False
     rules_file:
diff --git a/userspace/engine/falco_common.cpp b/userspace/engine/falco_common.cpp
index ac427a12..ffbbb2ef 100644
--- a/userspace/engine/falco_common.cpp
+++ b/userspace/engine/falco_common.cpp
@@ -21,6 +21,16 @@ along with falco.  If not, see <http://www.gnu.org/licenses/>.
 #include "config_falco_engine.h"
 #include "falco_common.h"
 
+std::vector<std::string> falco_common::priority_names = {
+	"Emergency",
+	"Alert",
+	"Critical",
+	"Error",
+	"Warning",
+	"Notice",
+	"Informational",
+	"Debug"};
+
 falco_common::falco_common()
 {
 	m_ls = lua_open();
diff --git a/userspace/engine/falco_common.h b/userspace/engine/falco_common.h
index 075e18fc..c7bcd82e 100644
--- a/userspace/engine/falco_common.h
+++ b/userspace/engine/falco_common.h
@@ -74,6 +74,22 @@ public:
 
 	void set_inspector(sinsp *inspector);
 
+        // Priority levels, as a vector of strings
+	static std::vector<std::string> priority_names;
+
+	// Same as numbers/indices into the above vector
+	enum priority_type
+	{
+		PRIORITY_EMERGENCY = 0,
+		PRIORITY_ALERT = 1,
+		PRIORITY_CRITICAL = 2,
+		PRIORITY_ERROR = 3,
+		PRIORITY_WARNING = 4,
+		PRIORITY_NOTICE = 5,
+		PRIORITY_INFORMATIONAL = 6,
+		PRIORITY_DEBUG = 7
+	};
+
 protected:
 	lua_State *m_ls;
 
diff --git a/userspace/engine/falco_engine.cpp b/userspace/engine/falco_engine.cpp
index ea00514b..fb7beb6d 100644
--- a/userspace/engine/falco_engine.cpp
+++ b/userspace/engine/falco_engine.cpp
@@ -41,6 +41,7 @@ using namespace std;
 
 falco_engine::falco_engine(bool seed_rng)
 	: m_rules(NULL), m_next_ruleset_id(0),
+	  m_min_priority(falco_common::PRIORITY_DEBUG),
 	  m_sampling_ratio(1), m_sampling_multiplier(0),
 	  m_replace_container_info(false)
 {
@@ -89,7 +90,7 @@ void falco_engine::load_rules(const string &rules_content, bool verbose, bool al
 	bool json_output = false;
 	falco_formats::init(m_inspector, m_ls, json_output);
 
-	m_rules->load_rules(rules_content, verbose, all_events, m_extra, m_replace_container_info);
+	m_rules->load_rules(rules_content, verbose, all_events, m_extra, m_replace_container_info, m_min_priority);
 }
 
 void falco_engine::load_rules_file(const string &rules_filename, bool verbose, bool all_events)
@@ -134,6 +135,11 @@ void falco_engine::enable_rule_by_tag(const set<string> &tags, bool enabled)
 	enable_rule_by_tag(tags, enabled, m_default_ruleset);
 }
 
+void falco_engine::set_min_priority(falco_common::priority_type priority)
+{
+	m_min_priority = priority;
+}
+
 uint16_t falco_engine::find_ruleset_id(const std::string &ruleset)
 {
 	auto it = m_known_rulesets.lower_bound(ruleset);
@@ -178,7 +184,7 @@ unique_ptr<falco_engine::rule_result> falco_engine::process_event(sinsp_evt *ev,
 		res->evt = ev;
 		const char *p =  lua_tostring(m_ls, -3);
 		res->rule = p;
-		res->priority = lua_tostring(m_ls, -2);
+		res->priority_num = (falco_common::priority_type) lua_tonumber(m_ls, -2);
 		res->format = lua_tostring(m_ls, -1);
 		lua_pop(m_ls, 3);
 	}
diff --git a/userspace/engine/falco_engine.h b/userspace/engine/falco_engine.h
index d06c45e7..55695bea 100644
--- a/userspace/engine/falco_engine.h
+++ b/userspace/engine/falco_engine.h
@@ -67,10 +67,13 @@ public:
 	// Wrapper that assumes the default ruleset
 	void enable_rule_by_tag(const std::set<std::string> &tags, bool enabled);
 
+	// Only load rules having this priority or more severe.
+	void set_min_priority(falco_common::priority_type priority);
+
 	struct rule_result {
 		sinsp_evt *evt;
 		std::string rule;
-		std::string priority;
+		falco_common::priority_type priority_num;
 		std::string format;
 	};
 
@@ -158,6 +161,7 @@ private:
 	uint16_t m_next_ruleset_id;
 	std::map<string, uint16_t> m_known_rulesets;
 	std::unique_ptr<sinsp_evttype_filter> m_evttype_filter;
+	falco_common::priority_type m_min_priority;
 
 	//
 	// Here's how the sampling ratio and multiplier influence
diff --git a/userspace/engine/lua/rule_loader.lua b/userspace/engine/lua/rule_loader.lua
index 1d9c60dd..8fc44b68 100644
--- a/userspace/engine/lua/rule_loader.lua
+++ b/userspace/engine/lua/rule_loader.lua
@@ -58,6 +58,17 @@ function map(f, arr)
    return res
 end
 
+priorities = {"Emergency", "Alert", "Critical", "Error", "Warning", "Notice", "Informational", "Debug"}
+
+local function priority_num_for(s)
+   s = string.lower(s)
+   for i,v in ipairs(priorities) do
+      if (string.find(string.lower(v), "^"..s)) then
+	 return i - 1 -- (numbers start at 0, lua indices start at 1)
+      end
+   end
+   error("Invalid priority level: "..s)
+end
 
 --[[
    Take a filter AST and set it up in the libsinsp runtime, using the filter API.
@@ -171,7 +182,7 @@ function table.tostring( tbl )
 end
 
 
-function load_rules(rules_content, rules_mgr, verbose, all_events, extra, replace_container_info)
+function load_rules(rules_content, rules_mgr, verbose, all_events, extra, replace_container_info, min_priority)
 
    compiler.set_verbose(verbose)
    compiler.set_all_events(all_events)
@@ -293,18 +304,23 @@ function load_rules(rules_content, rules_mgr, verbose, all_events, extra, replac
 	       end
 	    end
 
-	    -- Note that we can overwrite rules, but the rules are still
-	    -- loaded in the order in which they first appeared,
-	    -- potentially across multiple files.
-	    if state.rules_by_name[v['rule']] == nil then
-	       state.ordered_rule_names[#state.ordered_rule_names+1] = v['rule']
+	    -- Convert the priority-as-string to a priority-as-number now
+	    v['priority_num'] = priority_num_for(v['priority'])
+
+	    if v['priority_num'] <= min_priority then
+	       -- Note that we can overwrite rules, but the rules are still
+	       -- loaded in the order in which they first appeared,
+	       -- potentially across multiple files.
+	       if state.rules_by_name[v['rule']] == nil then
+		  state.ordered_rule_names[#state.ordered_rule_names+1] = v['rule']
+	       end
+
+	       -- The output field might be a folded-style, which adds a
+	       -- newline to the end. Remove any trailing newlines.
+	       v['output'] = compiler.trim(v['output'])
+
+	       state.rules_by_name[v['rule']] = v
 	    end
-
-	    -- The output field might be a folded-style, which adds a
-	    -- newline to the end. Remove any trailing newlines.
-	    v['output'] = compiler.trim(v['output'])
-
-	    state.rules_by_name[v['rule']] = v
 	 end
       else
 	 error ("Unknown rule object: "..table.tostring(v))
@@ -504,7 +520,7 @@ function on_event(evt_, rule_id)
    -- Prefix output with '*' so formatting is permissive
    output = "*"..rule.output
 
-   return rule.rule, rule.priority, output
+   return rule.rule, rule.priority_num, output
 end
 
 function print_stats()
diff --git a/userspace/engine/rules.cpp b/userspace/engine/rules.cpp
index cec545ec..c54d3839 100644
--- a/userspace/engine/rules.cpp
+++ b/userspace/engine/rules.cpp
@@ -145,7 +145,8 @@ void falco_rules::enable_rule(string &rule, bool enabled)
 
 void falco_rules::load_rules(const string &rules_content,
 			     bool verbose, bool all_events,
-			     string &extra, bool replace_container_info)
+			     string &extra, bool replace_container_info,
+			     falco_common::priority_type min_priority)
 {
 	lua_getglobal(m_ls, m_lua_load_rules.c_str());
 	if(lua_isfunction(m_ls, -1))
@@ -221,7 +222,8 @@ void falco_rules::load_rules(const string &rules_content,
 		lua_pushboolean(m_ls, (all_events ? 1 : 0));
 		lua_pushstring(m_ls, extra.c_str());
 		lua_pushboolean(m_ls, (replace_container_info ? 1 : 0));
-		if(lua_pcall(m_ls, 6, 0, 0) != 0)
+		lua_pushnumber(m_ls, min_priority);
+		if(lua_pcall(m_ls, 7, 0, 0) != 0)
 		{
 			const char* lerr = lua_tostring(m_ls, -1);
 			string err = "Error loading rules:" + string(lerr);
diff --git a/userspace/engine/rules.h b/userspace/engine/rules.h
index 1770aacc..964c5072 100644
--- a/userspace/engine/rules.h
+++ b/userspace/engine/rules.h
@@ -24,6 +24,8 @@ along with falco.  If not, see <http://www.gnu.org/licenses/>.
 
 #include "lua_parser.h"
 
+#include "falco_common.h"
+
 class falco_engine;
 
 class falco_rules
@@ -32,7 +34,8 @@ class falco_rules
 	falco_rules(sinsp* inspector, falco_engine *engine, lua_State *ls);
 	~falco_rules();
 	void load_rules(const string &rules_content, bool verbose, bool all_events,
-			std::string &extra, bool replace_container_info);
+			std::string &extra, bool replace_container_info,
+			falco_common::priority_type min_priority);
 	void describe_rule(string *rule);
 
 	static void init(lua_State *ls);
diff --git a/userspace/falco/configuration.cpp b/userspace/falco/configuration.cpp
index 74d828a0..08eb3f5c 100644
--- a/userspace/falco/configuration.cpp
+++ b/userspace/falco/configuration.cpp
@@ -108,6 +108,19 @@ void falco_configuration::init(string conf_filename, list<string> &cmdline_optio
 	m_notifications_rate = m_config->get_scalar<uint32_t>("outputs", "rate", 1);
 	m_notifications_max_burst = m_config->get_scalar<uint32_t>("outputs", "max_burst", 1000);
 
+	string priority = m_config->get_scalar<string>("priority", "debug");
+	vector<string>::iterator it;
+
+	auto comp = [priority] (string &s) {
+		return (strcasecmp(s.c_str(), priority.c_str()) == 0);
+	};
+
+	if((it = std::find_if(falco_common::priority_names.begin(), falco_common::priority_names.end(), comp)) == falco_common::priority_names.end())
+	{
+		throw invalid_argument("Unknown priority \"" + priority + "\"--must be one of emergency, alert, critical, error, warning, notice, informational, debug");
+	}
+	m_min_priority = (falco_common::priority_type) (it - falco_common::priority_names.begin());
+
 	falco_logger::log_stderr = m_config->get_scalar<bool>("log_stderr", false);
 	falco_logger::log_syslog = m_config->get_scalar<bool>("log_syslog", true);
 }
diff --git a/userspace/falco/configuration.h b/userspace/falco/configuration.h
index 42f3b681..ff9999d6 100644
--- a/userspace/falco/configuration.h
+++ b/userspace/falco/configuration.h
@@ -146,6 +146,8 @@ class falco_configuration
 	std::vector<falco_outputs::output_config> m_outputs;
 	uint32_t m_notifications_rate;
 	uint32_t m_notifications_max_burst;
+
+	falco_common::priority_type m_min_priority;
  private:
 	void init_cmdline_options(std::list<std::string> &cmdline_options);
 
diff --git a/userspace/falco/falco.cpp b/userspace/falco/falco.cpp
index 690271ab..75f01e5a 100644
--- a/userspace/falco/falco.cpp
+++ b/userspace/falco/falco.cpp
@@ -212,7 +212,7 @@ uint64_t do_inspect(falco_engine *engine,
 		unique_ptr<falco_engine::rule_result> res = engine->process_event(ev);
 		if(res)
 		{
-			outputs->handle_event(res->evt, res->rule, res->priority, res->format);
+			outputs->handle_event(res->evt, res->rule, res->priority_num, res->format);
 		}
 
 		num_evts++;
@@ -461,6 +461,8 @@ int falco_init(int argc, char **argv)
 			config.m_rules_filenames = rules_filenames;
 		}
 
+		engine->set_min_priority(config.m_min_priority);
+
 		for (auto filename : config.m_rules_filenames)
 		{
 			engine->load_rules_file(filename, verbose, all_events);
diff --git a/userspace/falco/falco_outputs.cpp b/userspace/falco/falco_outputs.cpp
index 69c3b271..49cfcdf1 100644
--- a/userspace/falco/falco_outputs.cpp
+++ b/userspace/falco/falco_outputs.cpp
@@ -105,7 +105,7 @@ void falco_outputs::add_output(output_config oc)
 
 }
 
-void falco_outputs::handle_event(sinsp_evt *ev, string &rule, string &priority, string &format)
+void falco_outputs::handle_event(sinsp_evt *ev, string &rule, falco_common::priority_type priority, string &format)
 {
 	if(!m_notifications_tb.claim())
 	{
@@ -119,10 +119,11 @@ void falco_outputs::handle_event(sinsp_evt *ev, string &rule, string &priority,
 	{
 		lua_pushlightuserdata(m_ls, ev);
 		lua_pushstring(m_ls, rule.c_str());
-		lua_pushstring(m_ls, priority.c_str());
+		lua_pushstring(m_ls, falco_common::priority_names[priority].c_str());
+		lua_pushnumber(m_ls, priority);
 		lua_pushstring(m_ls, format.c_str());
 
-		if(lua_pcall(m_ls, 4, 0, 0) != 0)
+		if(lua_pcall(m_ls, 5, 0, 0) != 0)
 		{
 			const char* lerr = lua_tostring(m_ls, -1);
 			string err = "Error invoking function output: " + string(lerr);
diff --git a/userspace/falco/falco_outputs.h b/userspace/falco/falco_outputs.h
index a1cd2876..7f3f1281 100644
--- a/userspace/falco/falco_outputs.h
+++ b/userspace/falco/falco_outputs.h
@@ -49,7 +49,7 @@ public:
 	// ev is an event that has matched some rule. Pass the event
 	// to all configured outputs.
 	//
-	void handle_event(sinsp_evt *ev, std::string &rule, std::string &priority, std::string &format);
+	void handle_event(sinsp_evt *ev, std::string &rule, falco_common::priority_type priority, std::string &format);
 
 private:
 	bool m_initialized;
diff --git a/userspace/falco/lua/output.lua b/userspace/falco/lua/output.lua
index a6aa42fb..f4d571f3 100644
--- a/userspace/falco/lua/output.lua
+++ b/userspace/falco/lua/output.lua
@@ -18,13 +18,9 @@
 
 local mod = {}
 
-levels = {"Emergency", "Alert", "Critical", "Error", "Warning", "Notice", "Informational", "Debug"}
-
-mod.levels = levels
-
 local outputs = {}
 
-function mod.stdout(level, msg)
+function mod.stdout(priority, priority_num, msg)
    print (msg)
 end
 
@@ -41,17 +37,17 @@ function mod.file_validate(options)
 
 end
 
-function mod.file(level, msg, options)
+function mod.file(priority, priority_num, msg, options)
    file = io.open(options.filename, "a+")
    file:write(msg, "\n")
    file:close()
 end
 
-function mod.syslog(level, msg, options)
-   falco.syslog(level, msg)
+function mod.syslog(priority, priority_num, msg, options)
+   falco.syslog(priority_num, msg)
 end
 
-function mod.program(level, msg, options)
+function mod.program(priority, priority_num, msg, options)
    -- XXX Ideally we'd check that the program ran
    -- successfully. However, the luajit we're using returns true even
    -- when the shell can't run the program.
@@ -62,31 +58,19 @@ function mod.program(level, msg, options)
    file:close()
 end
 
-local function level_of(s)
-   s = string.lower(s)
-   for i,v in ipairs(levels) do
-      if (string.find(string.lower(v), "^"..s)) then
-	 return i - 1 -- (syslog levels start at 0, lua indices start at 1)
-      end
-   end
-   error("Invalid severity level: "..s)
-end
-
-function output_event(event, rule, priority, format)
-   local level = level_of(priority)
-
+function output_event(event, rule, priority, priority_num, format)
    -- If format starts with a *, remove it, as we're adding our own
    -- prefix here.
    if format:sub(1,1) == "*" then
       format = format:sub(2)
    end
 
-   format = "*%evt.time: "..levels[level+1].." "..format
+   format = "*%evt.time: "..priority.." "..format
 
-   msg = formats.format_event(event, rule, levels[level+1], format)
+   msg = formats.format_event(event, rule, priority, format)
 
    for index,o in ipairs(outputs) do
-      o.output(level, msg, o.config)
+      o.output(priority, priority_num, msg, o.config)
    end
 end