Merge remote-tracking branch 'origin/dev'

Bumping version, noting changes since last release.

Signed-off-by: Mark Stemm <mark.stemm@gmail.com>

.clang-format

@@ -0,0 +1,16 @@
+---
+Language: Cpp
+BasedOnStyle: LLVM
+AccessModifierOffset: -8
+BreakBeforeBraces: Allman
+BreakConstructorInitializers: AfterColon
+ColumnLimit: 0
+ConstructorInitializerIndentWidth: 8
+ContinuationIndentWidth: 8
+DerivePointerAlignment: true
+IndentWidth: 8
+SortIncludes: false
+SpaceAfterTemplateKeyword: false
+SpaceBeforeCtorInitializerColon: false
+SpaceBeforeParens: Never
+UseTab: Always

.cmake-format

@@ -0,0 +1,119 @@
+# --------------------------
+# General Formatting Options
+# --------------------------
+# How wide to allow formatted cmake files
+line_width = 80
+
+# How many spaces to tab for indent
+tab_size = 2
+
+# If arglists are longer than this, break them always
+max_subargs_per_line = 3
+
+# If true, separate flow control names from their parentheses with a space
+separate_ctrl_name_with_space = False
+
+# If true, separate function names from parentheses with a space
+separate_fn_name_with_space = False
+
+# If a statement is wrapped to more than one line, than dangle the closing
+# parenthesis on it's own line
+dangle_parens = False
+
+# If the statement spelling length (including space and parenthesis is larger
+# than the tab width by more than this amoung, then force reject un-nested
+# layouts.
+max_prefix_chars = 2
+
+# If a candidate layout is wrapped horizontally but it exceeds this many lines,
+# then reject the layout.
+max_lines_hwrap = 2
+
+# What style line endings to use in the output.
+line_ending = 'unix'
+
+# Format command names consistently as 'lower' or 'upper' case
+command_case = 'canonical'
+
+# Format keywords consistently as 'lower' or 'upper' case
+keyword_case = 'unchanged'
+
+# Specify structure for custom cmake functions
+additional_commands = {
+  "pkg_find": {
+    "kwargs": {
+      "PKG": "*"
+    }
+  }
+}
+
+# A list of command names which should always be wrapped
+always_wrap = []
+
+# Specify the order of wrapping algorithms during successive reflow attempts
+algorithm_order = [0, 1, 2, 3, 4]
+
+# If true, the argument lists which are known to be sortable will be sorted
+# lexicographicall
+enable_sort = True
+
+# If true, the parsers may infer whether or not an argument list is sortable
+# (without annotation).
+autosort = False
+
+# If a comment line starts with at least this many consecutive hash characters,
+# then don't lstrip() them off. This allows for lazy hash rulers where the first
+# hash char is not separated by space
+hashruler_min_length = 10
+
+# A dictionary containing any per-command configuration overrides. Currently
+# only `command_case` is supported.
+per_command = {}
+
+
+# --------------------------
+# Comment Formatting Options
+# --------------------------
+# What character to use for bulleted lists
+bullet_char = '*'
+
+# What character to use as punctuation after numerals in an enumerated list
+enum_char = '.'
+
+# enable comment markup parsing and reflow
+enable_markup = True
+
+# If comment markup is enabled, don't reflow the first comment block in each
+# listfile. Use this to preserve formatting of your copyright/license
+# statements.
+first_comment_is_literal = False
+
+# If comment markup is enabled, don't reflow any comment block which matches
+# this (regex) pattern. Default is `None` (disabled).
+literal_comment_pattern = None
+
+# Regular expression to match preformat fences in comments
+# default=r'^\s*([`~]{3}[`~]*)(.*)$'
+fence_pattern = '^\\s*([`~]{3}[`~]*)(.*)$'
+
+# Regular expression to match rulers in comments
+# default=r'^\s*[^\w\s]{3}.*[^\w\s]{3}$'
+ruler_pattern = '^\\s*[^\\w\\s]{3}.*[^\\w\\s]{3}$'
+
+# If true, then insert a space between the first hash char and remaining hash
+# chars in a hash ruler, and normalize it's length to fill the column
+canonicalize_hashrulers = True
+
+
+# ---------------------------------
+# Miscellaneous Options
+# ---------------------------------
+# If true, emit the unicode byte-order mark (BOM) at the start of the file
+emit_byteorder_mark = False
+
+# Specify the encoding of the input file. Defaults to utf-8.
+input_encoding = 'utf-8'
+
+# Specify the encoding of the output file. Defaults to utf-8. Note that cmake
+# only claims to support utf-8 so be careful when using anything else
+output_encoding = 'utf-8'

.github/PULL_REQUEST_TEMPLATE.md

@@ -7,48 +7,66 @@
 -->
 
 **What type of PR is this?**
-> Uncomment only one ` /kind <>` line, hit enter to put that in a new line, and remove leading whitespaces from that line:
->
+
+> Uncomment one (or more) `/kind <>` lines:
+
 > /kind bug
+
 > /kind cleanup
+
 > /kind design
+
 > /kind documentation
+
 > /kind failing-test
+
 > /kind feature
+
 > /kind flaky-test
 
-> If contributing rules or changes to rules, please make sure to uncomment the appropriate kind
+> If contributing rules or changes to rules, please make sure to also uncomment one of the following line:
 
-> /kind rule/update
-> /kind rule/create
+> /kind rule-update
+
+> /kind rule-create
 
 **Any specific area of the project related to this PR?**
 
+> Uncomment one (or more) `/area <>` lines:
+
 > /area engine
+
 > /area rules
+
 > /area deployment
+
 > /area integrations
+
 > /area examples
 
 **What this PR does / why we need it**:
 
 **Which issue(s) this PR fixes**:
+
 <!--
 Automatically closes linked issue when PR is merged.
 Usage: `Fixes #<issue number>`, or `Fixes (paste link of issue)`.
 If PR is `kind/failing-tests` or `kind/flaky-test`, please post the related issues/tests in a comment and do not use `Fixes`.
 -->
+
 Fixes #
 
 **Special notes for your reviewer**:
 
 **Does this PR introduce a user-facing change?**:
+
 <!--
 If no, just write "NONE" in the release-note block below.
 If yes, a release note is required:
-Enter your extended release note in the block below. If the PR requires additional action from users switching to the new release, include the string "action required:".
+Enter your extended release note in the block below. If the PR requires additional action from users switching to the new release, prepend the string "action required:".
 For example, `action required: change the API interface of the rule engine`.
 -->
+
 ```release-note
 
 ```

.gitignore

@@ -12,10 +12,15 @@ test/results*.json.*
 
 userspace/falco/lua/re.lua
 userspace/falco/lua/lpeg.so
+userspace/engine/lua/lyaml
+userspace/engine/lua/lyaml.lua
 
 docker/event-generator/event_generator
 docker/event-generator/mysqld
 docker/event-generator/httpd
 docker/event-generator/sha1sum
 docker/event-generator/vipw
-.vscode/*
+
+.vscode/*
+
+.luacheckcache

.luacheckrc

@@ -0,0 +1,9 @@
+std = "min"
+cache = true
+include_files = {
+    "userspace/falco/lua/*.lua",
+    "userspace/engine/lua/*.lua",
+    "userspace/engine/lua/lyaml/*.lua",
+    "*.luacheckrc"
+}
+exclude_files = {"build"}

.travis.yml

@@ -36,6 +36,7 @@ script:
     - cd build
     - docker run --user $(id -u):$(id -g) -v /etc/passwd:/etc/passwd:ro -e MAKE_JOBS=4 -v $TRAVIS_BUILD_DIR/..:/source -v $TRAVIS_BUILD_DIR/build:/build falcosecurity/falco-builder cmake
     - docker run --user $(id -u):$(id -g) -v /etc/passwd:/etc/passwd:ro -e MAKE_JOBS=4 -v $TRAVIS_BUILD_DIR/..:/source -v $TRAVIS_BUILD_DIR/build:/build falcosecurity/falco-builder package
+    - docker run --user $(id -u):$(id -g) -v /etc/passwd:/etc/passwd:ro -e MAKE_JOBS=1 -v $TRAVIS_BUILD_DIR/..:/source -v $TRAVIS_BUILD_DIR/build:/build falcosecurity/falco-builder tests
     - docker run -v /boot:/boot:ro -v /var/run/docker.sock:/var/run/docker.sock -v /etc/passwd:/etc/passwd:ro -e MAKE_JOBS=4 -v $TRAVIS_BUILD_DIR/..:/source -v $TRAVIS_BUILD_DIR/build:/build falcosecurity/falco-tester
 notifications:
   webhooks:

.yamllint.conf

@@ -0,0 +1,8 @@
+extends: default
+
+rules:
+  indentation: disable
+  document-start: disable
+  comments: disable
+  line-length: disable
+  new-line-at-end-of-file: disable

CHANGELOG.md

@@ -2,6 +2,74 @@
 
 This file documents all notable changes to Falco. The release numbering uses [semantic versioning](http://semver.org).
 
+## v0.16.0
+
+Released 2019-07-12
+
+## Major Changes
+
+* Clean up error reporting to provide more meaningful error messages along with context when loading rules files. When run with -V, the results of the validation ("OK" or error message) are sent to standard output. [[#708](https://github.com/falcosecurity/falco/pull/708)]
+
+* Improve rule loading performance by optimizing lua parsing paths to avoid expensive pattern matches. [[#694](https://github.com/falcosecurity/falco/pull/694)]
+
+* Bump falco engine version to 4 to reflect new fields `ka.useragent`, others. [[#710](https://github.com/falcosecurity/falco/pull/710)] [[#681](https://github.com/falcosecurity/falco/pull/681)]
+
+* Add Catch2 as a unit testing framework. This will add additional coverage on top of the regression tests using Avocado. [[#687](https://github.com/falcosecurity/falco/pull/687)]
+
+## Minor Changes
+
+* Add SYSDIG_DIR Cmake option to specify location for sysdig source code when building falco. [[#677](https://github.com/falcosecurity/falco/pull/677)] [[#679](https://github.com/falcosecurity/falco/pull/679)] [[#702](https://github.com/falcosecurity/falco/pull/702)]
+
+* New field `ka.useragent` reports the useragent from k8s audit events. [[#709](https://github.com/falcosecurity/falco/pull/709)]
+
+* Add clang formatter for C++ syntax formatting. [[#701](https://github.com/falcosecurity/falco/pull/701)] [[#689](https://github.com/falcosecurity/falco/pull/689)]
+
+* Partial changes towards lua syntax formatting. No particular formatting enforced yet, though. [[#718](https://github.com/falcosecurity/falco/pull/718)]
+
+* Partial changes towards yaml syntax formatting. No particular formatting enforced yet, though. [[#714](https://github.com/falcosecurity/falco/pull/714)]
+
+* Add cmake syntax formatting. [[#703](https://github.com/falcosecurity/falco/pull/703)]
+
+* Token bucket unit tests and redesign. [[#692](https://github.com/falcosecurity/falco/pull/692)]
+
+* Update github PR template. [[#699](https://github.com/falcosecurity/falco/pull/699)]
+
+* Fix PR template for kind/rule-*. [[#697](https://github.com/falcosecurity/falco/pull/697)]
+
+## Bug Fixes
+
+* Remove an unused cmake file. [[#700](https://github.com/falcosecurity/falco/pull/700)]
+
+* Misc Cmake cleanups. [[#673](https://github.com/falcosecurity/falco/pull/673)]
+
+* Misc k8s install docs improvements. [[#671](https://github.com/falcosecurity/falco/pull/671)]
+
+## Rule Changes
+
+* Allow k8s.gcr.io/kube-proxy image to run privileged. [[#717](https://github.com/falcosecurity/falco/pull/717)]
+
+* Add runc to the list of possible container entrypoint parents. [[#712](https://github.com/falcosecurity/falco/pull/712)]
+
+* Skip Source RFC 1918 addresses when considering outbound connections. [[#685](https://github.com/falcosecurity/falco/pull/685)]
+
+* Add additional `user_XXX` placeholder macros to allow for easy customization of rule exceptions. [[#685](https://github.com/falcosecurity/falco/pull/685)]
+
+* Let weaveworks programs change namespaces. [[#685](https://github.com/falcosecurity/falco/pull/685)]
+
+* Add additional openshift images. [[#685](https://github.com/falcosecurity/falco/pull/685)]
+
+* Add openshift as a k8s binary. [[#678](https://github.com/falcosecurity/falco/pull/678)]
+
+* Add dzdo as a binary that can change users. [[#678](https://github.com/falcosecurity/falco/pull/678)]
+
+* Allow azure/calico binaries to change namespaces. [[#678](https://github.com/falcosecurity/falco/pull/678)]
+
+* Add back trusted_containers list for backport compatibility [[#675](https://github.com/falcosecurity/falco/pull/675)]
+
+* Add mkdirat as a syscall for mkdir operations. [[#667](https://github.com/falcosecurity/falco/pull/667)]
+
+* Add container id/repository to rules that can work with containers. [[#667](https://github.com/falcosecurity/falco/pull/667)]
+
 ## v0.15.3
 
 Released 2019-06-12

CMakeLists.txt

@@ -75,7 +75,10 @@ endif()
 
 set(CMD_MAKE make)
 
-set(SYSDIG_DIR "${PROJECT_SOURCE_DIR}/../sysdig")
+if(NOT SYSDIG_DIR)
+	set(SYSDIG_DIR "${PROJECT_SOURCE_DIR}/../sysdig")
+endif()
+
 # make luaJIT work on OS X
 if(APPLE)
 	set(CMAKE_EXE_LINKER_FLAGS "-pagezero_size 10000 -image_base 100000000")
@@ -304,7 +307,7 @@ else()
 		URL "http://s3.amazonaws.com/download.draios.com/dependencies/curl-7.61.0.tar.bz2"
 		URL_MD5 "31d0a9f48dc796a7db351898a1e5058a"
 		# END CHANGE for CVE-2017-8816, CVE-2017-8817, CVE-2017-8818, CVE-2018-1000007
-		CONFIGURE_COMMAND ./configure ${CURL_SSL_OPTION} --disable-shared --enable-optimize --disable-curldebug --disable-rt --enable-http --disable-ftp --disable-file --disable-ldap --disable-ldaps --disable-rtsp --disable-telnet --disable-tftp --disable-pop3 --disable-imap --disable-smb --disable-smtp --disable-gopher --disable-sspi --disable-ntlm-wb --disable-tls-srp --without-winssl --without-darwinssl --without-polarssl --without-cyassl --without-nss --without-axtls --without-ca-path --without-ca-bundle --without-libmetalink --without-librtmp --without-winidn --without-libidn --without-nghttp2 --without-libssh2 --disable-threaded-resolver
+		CONFIGURE_COMMAND ./configure ${CURL_SSL_OPTION} --disable-shared --enable-optimize --disable-curldebug --disable-rt --enable-http --disable-ftp --disable-file --disable-ldap --disable-ldaps --disable-rtsp --disable-telnet --disable-tftp --disable-pop3 --disable-imap --disable-smb --disable-smtp --disable-gopher --disable-sspi --disable-ntlm-wb --disable-tls-srp --without-winssl --without-darwinssl --without-polarssl --without-cyassl --without-nss --without-axtls --without-ca-path --without-ca-bundle --without-libmetalink --without-librtmp --without-winidn --without-libidn2 --without-libpsl --without-nghttp2 --without-libssh2 --disable-threaded-resolver --without-brotli
 		BUILD_COMMAND ${CMD_MAKE}
 		BUILD_IN_SOURCE 1
 		INSTALL_COMMAND "")
@@ -378,7 +381,6 @@ endif()
 # Libyaml
 #
 option(USE_BUNDLED_LIBYAML "Enable building of the bundled libyaml" ${USE_BUNDLED_DEPS})
-
 if(NOT USE_BUNDLED_LIBYAML)
 	# Note: to distinguish libyaml.a and yaml.a we specify a full
 	# file name here, so you'll have to arrange for static
@@ -398,6 +400,7 @@ else()
 	endif()
 
 	set(LIBYAML_SRC "${PROJECT_BINARY_DIR}/libyaml-prefix/src/libyaml/src")
+	set(LIBYAML_INCLUDE "${PROJECT_BINARY_DIR}/libyaml-prefix/src/libyaml/include")
 	set(LIBYAML_LIB "${LIBYAML_SRC}/.libs/libyaml.a")
 	message(STATUS "Using bundled libyaml in '${LIBYAML_SRC}'")
 	ExternalProject_Add(libyaml
@@ -413,7 +416,6 @@ endif()
 # lyaml
 #
 option(USE_BUNDLED_LYAML "Enable building of the bundled lyaml" ${USE_BUNDLED_DEPS})
-
 if(NOT USE_BUNDLED_LYAML)
 	# Note: to distinguish libyaml.a and yaml.a we specify a full
 	# file name here, so you'll have to arrange for static
@@ -435,14 +437,15 @@ else()
 	if(USE_BUNDLED_LIBYAML)
 		list(APPEND LYAML_DEPENDENCIES "libyaml")
 	endif()
+
 	ExternalProject_Add(lyaml
 		DEPENDS ${LYAML_DEPENDENCIES}
 		URL "http://s3.amazonaws.com/download.draios.com/dependencies/lyaml-release-v6.0.tar.gz"
-                URL_MD5 "dc3494689a0dce7cf44e7a99c72b1f30"
-                BUILD_COMMAND ${CMD_MAKE}
-                BUILD_IN_SOURCE 1
-		CONFIGURE_COMMAND ./configure --enable-static LIBS=-L../../../libyaml-prefix/src/libyaml/src/.libs CFLAGS=-I../../../libyaml-prefix/src/libyaml/include CPPFLAGS=-I../../../libyaml-prefix/src/libyaml/include LUA_INCLUDE=-I../../../luajit-prefix/src/luajit/src LUA=../../../luajit-prefix/src/luajit/src/luajit
-                INSTALL_COMMAND sh -c "cp -R ${PROJECT_BINARY_DIR}/lyaml-prefix/src/lyaml/lib/* ${PROJECT_SOURCE_DIR}/userspace/engine/lua")
+		URL_MD5 "dc3494689a0dce7cf44e7a99c72b1f30"
+		BUILD_COMMAND ${CMD_MAKE}
+		BUILD_IN_SOURCE 1
+		CONFIGURE_COMMAND ./configure --enable-static LIBS=-L${LIBYAML_SRC}/.libs CFLAGS=-I${LIBYAML_INCLUDE} CPPFLAGS=-I${LIBYAML_INCLUDE} LUA_INCLUDE=-I${LUAJIT_INCLUDE} LUA=${LUAJIT_SRC}/luajit
+		INSTALL_COMMAND sh -c "cp -R ${PROJECT_BINARY_DIR}/lyaml-prefix/src/lyaml/lib/* ${PROJECT_SOURCE_DIR}/userspace/engine/lua")
 endif()
 
 option(USE_BUNDLED_TBB "Enable building of the bundled tbb" ${USE_BUNDLED_DEPS})
@@ -586,7 +589,7 @@ else()
 		URL_MD5 "2fc42c182a0ed1b48ad77397f76bb3bc"
 		CONFIGURE_COMMAND ""
 		# TODO what if using system openssl, protobuf or cares?
-		BUILD_COMMAND HAS_SYSTEM_ZLIB=false LDFLAGS=-static PATH=${PROTOC_DIR}:$ENV{PATH} PKG_CONFIG_PATH=${OPENSSL_BUNDLE_DIR}:${PROTOBUF_SRC}:${CARES_SRC} make grpc_cpp_plugin static_cxx static_c
+		BUILD_COMMAND sh -c "CFLAGS=-Wno-implicit-fallthrough CXXFLAGS=\"-Wno-ignored-qualifiers -Wno-stringop-truncation\" HAS_SYSTEM_ZLIB=false LDFLAGS=-static PATH=${PROTOC_DIR}:$ENV{PATH} PKG_CONFIG_PATH=${OPENSSL_BUNDLE_DIR}:${PROTOBUF_SRC}:${CARES_SRC} make grpc_cpp_plugin static_cxx static_c"
 		BUILD_IN_SOURCE 1
 		BUILD_BYPRODUCTS ${GRPC_LIB} ${GRPCPP_LIB}
 		# TODO s390x support
@@ -603,8 +606,17 @@ add_subdirectory(test)
 add_subdirectory(rules)
 add_subdirectory(docker)
 
+# Add path for custom CMake modules used to build dependencies from Sysdig (libscap, libsinsp)
+list(APPEND CMAKE_MODULE_PATH
+	"${SYSDIG_DIR}/cmake/modules")
+
+# Add path for custom CMake modules
+list(APPEND CMAKE_MODULE_PATH
+	"${CMAKE_CURRENT_SOURCE_DIR}/cmake/modules")
+
 if(CMAKE_SYSTEM_NAME MATCHES "Linux")
 	add_subdirectory("${SYSDIG_DIR}/driver" "${PROJECT_BINARY_DIR}/driver")
+	include(FindMakedev)
 endif()
 add_subdirectory("${SYSDIG_DIR}/userspace/libscap" "${PROJECT_BINARY_DIR}/userspace/libscap")
 add_subdirectory("${SYSDIG_DIR}/userspace/libsinsp" "${PROJECT_BINARY_DIR}/userspace/libsinsp")
@@ -616,6 +628,7 @@ set(FALCO_BIN_DIR bin)
 add_subdirectory(scripts)
 add_subdirectory(userspace/engine)
 add_subdirectory(userspace/falco)
+add_subdirectory(tests)
 
 
 set(CPACK_PACKAGE_NAME "${PACKAGE_NAME}")

README.md

@@ -5,7 +5,7 @@
 
 #### Latest release
 
-**v0.15.3**
+**v0.16.0**
 Read the [change log](https://github.com/falcosecurity/falco/blob/dev/CHANGELOG.md)
 
 Dev Branch: [![Build Status](https://travis-ci.com/falcosecurity/falco.svg?branch=dev)](https://travis-ci.com/falcosecurity/falco)<br />

cmake/modules/Catch.cmake

@@ -0,0 +1,175 @@
+# Distributed under the OSI-approved BSD 3-Clause License.  See accompanying
+# file Copyright.txt or https://cmake.org/licensing for details.
+
+#[=======================================================================[.rst:
+Catch
+-----
+
+This module defines a function to help use the Catch test framework.
+
+The :command:`catch_discover_tests` discovers tests by asking the compiled test
+executable to enumerate its tests.  This does not require CMake to be re-run
+when tests change.  However, it may not work in a cross-compiling environment,
+and setting test properties is less convenient.
+
+This command is intended to replace use of :command:`add_test` to register
+tests, and will create a separate CTest test for each Catch test case.  Note
+that this is in some cases less efficient, as common set-up and tear-down logic
+cannot be shared by multiple test cases executing in the same instance.
+However, it provides more fine-grained pass/fail information to CTest, which is
+usually considered as more beneficial.  By default, the CTest test name is the
+same as the Catch name; see also ``TEST_PREFIX`` and ``TEST_SUFFIX``.
+
+.. command:: catch_discover_tests
+
+  Automatically add tests with CTest by querying the compiled test executable
+  for available tests::
+
+    catch_discover_tests(target
+                         [TEST_SPEC arg1...]
+                         [EXTRA_ARGS arg1...]
+                         [WORKING_DIRECTORY dir]
+                         [TEST_PREFIX prefix]
+                         [TEST_SUFFIX suffix]
+                         [PROPERTIES name1 value1...]
+                         [TEST_LIST var]
+    )
+
+  ``catch_discover_tests`` sets up a post-build command on the test executable
+  that generates the list of tests by parsing the output from running the test
+  with the ``--list-test-names-only`` argument.  This ensures that the full
+  list of tests is obtained.  Since test discovery occurs at build time, it is
+  not necessary to re-run CMake when the list of tests changes.
+  However, it requires that :prop_tgt:`CROSSCOMPILING_EMULATOR` is properly set
+  in order to function in a cross-compiling environment.
+
+  Additionally, setting properties on tests is somewhat less convenient, since
+  the tests are not available at CMake time.  Additional test properties may be
+  assigned to the set of tests as a whole using the ``PROPERTIES`` option.  If
+  more fine-grained test control is needed, custom content may be provided
+  through an external CTest script using the :prop_dir:`TEST_INCLUDE_FILES`
+  directory property.  The set of discovered tests is made accessible to such a
+  script via the ``<target>_TESTS`` variable.
+
+  The options are:
+
+  ``target``
+    Specifies the Catch executable, which must be a known CMake executable
+    target.  CMake will substitute the location of the built executable when
+    running the test.
+
+  ``TEST_SPEC arg1...``
+    Specifies test cases, wildcarded test cases, tags and tag expressions to
+    pass to the Catch executable with the ``--list-test-names-only`` argument.
+
+  ``EXTRA_ARGS arg1...``
+    Any extra arguments to pass on the command line to each test case.
+
+  ``WORKING_DIRECTORY dir``
+    Specifies the directory in which to run the discovered test cases.  If this
+    option is not provided, the current binary directory is used.
+
+  ``TEST_PREFIX prefix``
+    Specifies a ``prefix`` to be prepended to the name of each discovered test
+    case.  This can be useful when the same test executable is being used in
+    multiple calls to ``catch_discover_tests()`` but with different
+    ``TEST_SPEC`` or ``EXTRA_ARGS``.
+
+  ``TEST_SUFFIX suffix``
+    Similar to ``TEST_PREFIX`` except the ``suffix`` is appended to the name of
+    every discovered test case.  Both ``TEST_PREFIX`` and ``TEST_SUFFIX`` may
+    be specified.
+
+  ``PROPERTIES name1 value1...``
+    Specifies additional properties to be set on all tests discovered by this
+    invocation of ``catch_discover_tests``.
+
+  ``TEST_LIST var``
+    Make the list of tests available in the variable ``var``, rather than the
+    default ``<target>_TESTS``.  This can be useful when the same test
+    executable is being used in multiple calls to ``catch_discover_tests()``.
+    Note that this variable is only available in CTest.
+
+#]=======================================================================]
+
+#------------------------------------------------------------------------------
+function(catch_discover_tests TARGET)
+  cmake_parse_arguments(
+    ""
+    ""
+    "TEST_PREFIX;TEST_SUFFIX;WORKING_DIRECTORY;TEST_LIST"
+    "TEST_SPEC;EXTRA_ARGS;PROPERTIES"
+    ${ARGN}
+  )
+
+  if(NOT _WORKING_DIRECTORY)
+    set(_WORKING_DIRECTORY "${CMAKE_CURRENT_BINARY_DIR}")
+  endif()
+  if(NOT _TEST_LIST)
+    set(_TEST_LIST ${TARGET}_TESTS)
+  endif()
+
+  ## Generate a unique name based on the extra arguments
+  string(SHA1 args_hash "${_TEST_SPEC} ${_EXTRA_ARGS}")
+  string(SUBSTRING ${args_hash} 0 7 args_hash)
+
+  # Define rule to generate test list for aforementioned test executable
+  set(ctest_include_file "${CMAKE_CURRENT_BINARY_DIR}/${TARGET}_include-${args_hash}.cmake")
+  set(ctest_tests_file "${CMAKE_CURRENT_BINARY_DIR}/${TARGET}_tests-${args_hash}.cmake")
+  get_property(crosscompiling_emulator
+    TARGET ${TARGET}
+    PROPERTY CROSSCOMPILING_EMULATOR
+  )
+  add_custom_command(
+    TARGET ${TARGET} POST_BUILD
+    BYPRODUCTS "${ctest_tests_file}"
+    COMMAND "${CMAKE_COMMAND}"
+            -D "TEST_TARGET=${TARGET}"
+            -D "TEST_EXECUTABLE=$<TARGET_FILE:${TARGET}>"
+            -D "TEST_EXECUTOR=${crosscompiling_emulator}"
+            -D "TEST_WORKING_DIR=${_WORKING_DIRECTORY}"
+            -D "TEST_SPEC=${_TEST_SPEC}"
+            -D "TEST_EXTRA_ARGS=${_EXTRA_ARGS}"
+            -D "TEST_PROPERTIES=${_PROPERTIES}"
+            -D "TEST_PREFIX=${_TEST_PREFIX}"
+            -D "TEST_SUFFIX=${_TEST_SUFFIX}"
+            -D "TEST_LIST=${_TEST_LIST}"
+            -D "CTEST_FILE=${ctest_tests_file}"
+            -P "${_CATCH_DISCOVER_TESTS_SCRIPT}"
+    VERBATIM
+  )
+
+  file(WRITE "${ctest_include_file}"
+    "if(EXISTS \"${ctest_tests_file}\")\n"
+    "  include(\"${ctest_tests_file}\")\n"
+    "else()\n"
+    "  add_test(${TARGET}_NOT_BUILT-${args_hash} ${TARGET}_NOT_BUILT-${args_hash})\n"
+    "endif()\n"
+  )
+
+  if(NOT ${CMAKE_VERSION} VERSION_LESS "3.10.0") 
+    # Add discovered tests to directory TEST_INCLUDE_FILES
+    set_property(DIRECTORY
+      APPEND PROPERTY TEST_INCLUDE_FILES "${ctest_include_file}"
+    )
+  else()
+    # Add discovered tests as directory TEST_INCLUDE_FILE if possible
+    get_property(test_include_file_set DIRECTORY PROPERTY TEST_INCLUDE_FILE SET)
+    if (NOT ${test_include_file_set})
+      set_property(DIRECTORY
+        PROPERTY TEST_INCLUDE_FILE "${ctest_include_file}"
+      )
+    else()
+      message(FATAL_ERROR
+        "Cannot set more than one TEST_INCLUDE_FILE"
+      )
+    endif()
+  endif()
+
+endfunction()
+
+###############################################################################
+
+set(_CATCH_DISCOVER_TESTS_SCRIPT
+  ${CMAKE_CURRENT_LIST_DIR}/CatchAddTests.cmake
+)

cmake/modules/CatchAddTests.cmake

@@ -0,0 +1,78 @@
+# Distributed under the OSI-approved BSD 3-Clause License.  See accompanying
+# file Copyright.txt or https://cmake.org/licensing for details.
+
+set(prefix "${TEST_PREFIX}")
+set(suffix "${TEST_SUFFIX}")
+set(spec ${TEST_SPEC})
+set(extra_args ${TEST_EXTRA_ARGS})
+set(properties ${TEST_PROPERTIES})
+set(script)
+set(suite)
+set(tests)
+
+function(add_command NAME)
+  set(_args "")
+  foreach(_arg ${ARGN})
+    if(_arg MATCHES "[^-./:a-zA-Z0-9_]")
+      set(_args "${_args} [==[${_arg}]==]") # form a bracket_argument
+    else()
+      set(_args "${_args} ${_arg}")
+    endif()
+  endforeach()
+  set(script "${script}${NAME}(${_args})\n" PARENT_SCOPE)
+endfunction()
+
+# Run test executable to get list of available tests
+if(NOT EXISTS "${TEST_EXECUTABLE}")
+  message(FATAL_ERROR
+    "Specified test executable '${TEST_EXECUTABLE}' does not exist"
+  )
+endif()
+execute_process(
+  COMMAND ${TEST_EXECUTOR} "${TEST_EXECUTABLE}" ${spec} --list-test-names-only
+  OUTPUT_VARIABLE output
+  RESULT_VARIABLE result
+)
+# Catch --list-test-names-only reports the number of tests, so 0 is... surprising
+if(${result} EQUAL 0)
+  message(WARNING
+    "Test executable '${TEST_EXECUTABLE}' contains no tests!\n"
+  )
+elseif(${result} LESS 0)
+  message(FATAL_ERROR
+    "Error running test executable '${TEST_EXECUTABLE}':\n"
+    "  Result: ${result}\n"
+    "  Output: ${output}\n"
+  )
+endif()
+
+string(REPLACE "\n" ";" output "${output}")
+
+# Parse output
+foreach(line ${output})
+  set(test ${line})
+  # use escape commas to handle properly test cases with commans inside the name
+  string(REPLACE "," "\\," test_name ${test})
+  # ...and add to script
+  add_command(add_test
+    "${prefix}${test}${suffix}"
+    ${TEST_EXECUTOR}
+    "${TEST_EXECUTABLE}"
+    "${test_name}"
+    ${extra_args}
+  )
+  add_command(set_tests_properties
+    "${prefix}${test}${suffix}"
+    PROPERTIES
+    WORKING_DIRECTORY "${TEST_WORKING_DIR}"
+    ${properties}
+  )
+  list(APPEND tests "${prefix}${test}${suffix}")
+endforeach()
+
+# Create a list of all discovered tests, which users may use to e.g. set
+# properties on the tests
+add_command(set ${TEST_LIST} ${tests})
+
+# Write CTest script
+file(WRITE "${CTEST_FILE}" "${script}")

cmake/modules/DownloadCatch.cmake

@@ -0,0 +1,39 @@
+#
+# Copyright (C) 2016-2019 Draios Inc dba Sysdig.
+#
+# This file is part of falco .
+#
+# Licensed under the Apache License, Version 2.0 (the "License"); you may not
+# use this file except in compliance with the License. You may obtain a copy of
+# the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
+# WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
+# License for the specific language governing permissions and limitations under
+# the License.
+#
+include(ExternalProject)
+
+set(CATCH2_INCLUDE ${CMAKE_BINARY_DIR}/catch2-prefix/include)
+
+set(CATCH_EXTERNAL_URL
+    URL
+    https://github.com/catchorg/catch2/archive/v2.9.1.tar.gz
+    URL_HASH
+    MD5=4980778888fed635bf191d8a86f9f89c)
+
+ExternalProject_Add(
+  catch2
+  PREFIX ${CMAKE_BINARY_DIR}/catch2-prefix
+  ${CATCH_EXTERNAL_URL}
+  CONFIGURE_COMMAND ""
+  BUILD_COMMAND ""
+  INSTALL_COMMAND
+    ${CMAKE_COMMAND}
+    -E
+    copy
+    ${CMAKE_BINARY_DIR}/catch2-prefix/src/catch2/single_include/catch2/catch.hpp
+    ${CATCH2_INCLUDE}/catch.hpp)

cmake/modules/DownloadFakeIt.cmake

@@ -0,0 +1,39 @@
+#
+# Copyright (C) 2016-2019 Draios Inc dba Sysdig.
+#
+# This file is part of falco .
+#
+# Licensed under the Apache License, Version 2.0 (the "License"); you may not
+# use this file except in compliance with the License. You may obtain a copy of
+# the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
+# WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
+# License for the specific language governing permissions and limitations under
+# the License.
+#
+include(ExternalProject)
+
+set(FAKEIT_INCLUDE ${CMAKE_BINARY_DIR}/fakeit-prefix/include)
+
+set(FAKEIT_EXTERNAL_URL
+    URL
+    https://github.com/eranpeer/fakeit/archive/2.0.5.tar.gz
+    URL_HASH
+    MD5=d3d21b909cebaea5b780af5500bf384e)
+
+ExternalProject_Add(
+  fakeit-external
+  PREFIX ${CMAKE_BINARY_DIR}/fakeit-prefix
+  ${FAKEIT_EXTERNAL_URL}
+  CONFIGURE_COMMAND ""
+  BUILD_COMMAND ""
+  INSTALL_COMMAND
+    ${CMAKE_COMMAND}
+    -E
+    copy
+    ${CMAKE_BINARY_DIR}/fakeit-prefix/src/fakeit-external/single_header/catch/fakeit.hpp
+    ${FAKEIT_INCLUDE}/fakeit.hpp)

integrations/k8s-using-daemonset/README.md

@@ -29,7 +29,7 @@ service/falco-service created
 k8s-using-daemonset$
 ```
 
-The Daemon Set also relies on a Kubernetes ConfigMap to store the Falco configuration and make the configuration available to the Falco Pods. This allows you to manage custom configuration without rebuilding and redeploying the underlying Pods. In order to create the ConfigMap you'll need to first need to copy the required configuration from their location in this GitHub repo to the `k8s-with-rbac/falco-config/` directory (please note that you will need to create the /falco-config directory). Any modification of the configuration should be performed on these copies rather than the original files.
+The Daemon Set also relies on a Kubernetes ConfigMap to store the Falco configuration and make the configuration available to the Falco Pods. This allows you to manage custom configuration without rebuilding and redeploying the underlying Pods. In order to create the ConfigMap you'll first need to copy the required configuration from their location in this GitHub repo to the `k8s-with-rbac/falco-config/` directory (please note that you will need to create the /falco-config directory). Any modification of the configuration should be performed on these copies rather than the original files.
 
 ```
 k8s-using-daemonset$ mkdir -p k8s-with-rbac/falco-config

rules/falco_rules.yaml

@@ -59,7 +59,7 @@
 - macro: rename
   condition: evt.type in (rename, renameat)
 - macro: mkdir
-  condition: evt.type = mkdir
+  condition: evt.type in (mkdir, mkdirat)
 - macro: remove
   condition: evt.type in (rmdir, unlink, unlinkat)
 
@@ -159,7 +159,7 @@
   items: [docker, dockerd, exe, docker-compose, docker-entrypoi, docker-runc-cur, docker-current, dockerd-current]
 
 - list: k8s_binaries
-  items: [hyperkube, skydns, kube2sky, exechealthz, weave-net, loopback, bridge, openshift-sdn]
+  items: [hyperkube, skydns, kube2sky, exechealthz, weave-net, loopback, bridge, openshift-sdn, openshift]
 
 - list: lxd_binaries
   items: [lxd, lxcfs]
@@ -243,7 +243,7 @@
 # A canonical set of processes that run other programs with different
 # privileges or as a different user.
 - list: userexec_binaries
-  items: [sudo, su, suexec, critical-stack]
+  items: [sudo, su, suexec, critical-stack, dzdo]
 
 - list: known_setuid_binaries
   items: [
@@ -311,13 +311,17 @@
      (fd.ip != "0.0.0.0" and fd.net != "127.0.0.0/8") and
      (evt.rawres >= 0 or evt.res = EINPROGRESS))
 
+# RFC1918 addresses were assigned for private network usage
+- list: rfc_1918_addresses
+  items: ['"10.0.0.0/8"', '"172.16.0.0/12"', '"192.168.0.0/16"']
+
 - macro: outbound
   condition: >
     (((evt.type = connect and evt.dir=<) or
       (evt.type in (sendto,sendmsg) and evt.dir=< and
        fd.l4proto != tcp and fd.connected=false and fd.name_changed=true)) and
      (fd.typechar = 4 or fd.typechar = 6) and
-     (fd.ip != "0.0.0.0" and fd.net != "127.0.0.0/8") and
+     (fd.ip != "0.0.0.0" and fd.net != "127.0.0.0/8" and not fd.snet in (rfc_1918_addresses)) and
      (evt.rawres >= 0 or evt.res = EINPROGRESS))
 
 # Very similar to inbound/outbound, but combines the tests together
@@ -348,7 +352,7 @@
 - rule: Disallowed SSH Connection
   desc: Detect any new ssh connection to a host other than those in an allowed group of hosts
   condition: (inbound_outbound) and ssh_port and not allowed_ssh_hosts
-  output: Disallowed SSH Connection (command=%proc.cmdline connection=%fd.name user=%user.name)
+  output: Disallowed SSH Connection (command=%proc.cmdline connection=%fd.name user=%user.name container_id=%container.id image=%container.image.repository)
   priority: NOTICE
   tags: [network, mitre_remote_service]
 
@@ -379,7 +383,7 @@
     ((fd.sip in (allowed_outbound_destination_ipaddrs)) or
      (fd.snet in (allowed_outbound_destination_networks)) or
      (fd.sip.name in (allowed_outbound_destination_domains)))
-  output: Disallowed outbound connection destination (command=%proc.cmdline connection=%fd.name user=%user.name)
+  output: Disallowed outbound connection destination (command=%proc.cmdline connection=%fd.name user=%user.name container_id=%container.id image=%container.image.repository)
   priority: NOTICE
   tags: [network]
 
@@ -402,7 +406,7 @@
     ((fd.cip in (allowed_inbound_source_ipaddrs)) or
      (fd.cnet in (allowed_inbound_source_networks)) or
      (fd.cip.name in (allowed_inbound_source_domains)))
-  output: Disallowed inbound connection source (command=%proc.cmdline connection=%fd.name user=%user.name)
+  output: Disallowed inbound connection source (command=%proc.cmdline connection=%fd.name user=%user.name container_id=%container.id image=%container.image.repository)
   priority: NOTICE
   tags: [network]
 
@@ -440,7 +444,7 @@
      fd.directory in (shell_config_directories)) and
     not proc.name in (shell_binaries)
   output: >
-    a shell configuration file has been modified (user=%user.name command=%proc.cmdline file=%fd.name)
+    a shell configuration file has been modified (user=%user.name command=%proc.cmdline file=%fd.name container_id=%container.id image=%container.image.repository)
   priority:
     WARNING
   tag: [file, mitre_persistence]
@@ -462,7 +466,7 @@
      fd.directory in (shell_config_directories)) and
     (not proc.name in (shell_binaries))
   output: >
-    a shell configuration file was read by a non-shell program (user=%user.name command=%proc.cmdline file=%fd.name)
+    a shell configuration file was read by a non-shell program (user=%user.name command=%proc.cmdline file=%fd.name container_id=%container.id image=%container.image.repository)
   priority:
     WARNING
   tag: [file, mitre_discovery]
@@ -906,7 +910,7 @@
   condition: >
     open_write and access_repositories and not package_mgmt_procs
   output: >
-    Repository files get updated (user=%user.name command=%proc.cmdline file=%fd.name)
+    Repository files get updated (user=%user.name command=%proc.cmdline file=%fd.name container_id=%container.id image=%container.image.repository)
   priority:
     NOTICE
   tags: [filesystem, mitre_persistence]
@@ -921,7 +925,7 @@
     and not python_running_ms_oms
   output: >
     File below a known binary directory opened for writing (user=%user.name
-    command=%proc.cmdline file=%fd.name parent=%proc.pname pcmdline=%proc.pcmdline gparent=%proc.aname[2])
+    command=%proc.cmdline file=%fd.name parent=%proc.pname pcmdline=%proc.pcmdline gparent=%proc.aname[2] container_id=%container.id image=%container.image.repository)
   priority: ERROR
   tags: [filesystem, mitre_persistence]
 
@@ -979,7 +983,7 @@
     and not user_known_write_monitored_dir_conditions
   output: >
     File below a monitored directory opened for writing (user=%user.name
-    command=%proc.cmdline file=%fd.name parent=%proc.pname pcmdline=%proc.pcmdline gparent=%proc.aname[2])
+    command=%proc.cmdline file=%fd.name parent=%proc.pname pcmdline=%proc.pcmdline gparent=%proc.aname[2] container_id=%container.id image=%container.image.repository)
   priority: ERROR
   tags: [filesystem, mitre_persistence]
 
@@ -998,7 +1002,7 @@
      (not proc.name in (ssh_binaries)))
   output: >
     ssh-related file/directory read by non-ssh program (user=%user.name
-    command=%proc.cmdline file=%fd.name parent=%proc.pname pcmdline=%proc.pcmdline)
+    command=%proc.cmdline file=%fd.name parent=%proc.pname pcmdline=%proc.pcmdline container_id=%container.id image=%container.image.repository)
   priority: ERROR
   tags: [filesystem, mitre_discovery]
 
@@ -1148,6 +1152,10 @@
 - macro: user_known_write_etc_conditions
   condition: proc.name=confd
 
+# This is a placeholder for user to extend the whitelist for write below etc rule
+- macro: user_known_write_below_etc_activities
+  condition: (never_true)
+
 - macro: write_etc_common
   condition: >
     etc_dir and evt.dir = < and open_write
@@ -1245,11 +1253,12 @@
     and not checkpoint_writing_state
     and not jboss_in_container_writing_passwd
     and not etcd_manager_updating_dns
+    and not user_known_write_below_etc_activities
 
 - rule: Write below etc
   desc: an attempt to write to any file below /etc
   condition: write_etc_common
-  output: "File below /etc opened for writing (user=%user.name command=%proc.cmdline parent=%proc.pname pcmdline=%proc.pcmdline file=%fd.name program=%proc.name gparent=%proc.aname[2] ggparent=%proc.aname[3] gggparent=%proc.aname[4])"
+  output: "File below /etc opened for writing (user=%user.name command=%proc.cmdline parent=%proc.pname pcmdline=%proc.pcmdline file=%fd.name program=%proc.name gparent=%proc.aname[2] ggparent=%proc.aname[3] gggparent=%proc.aname[4] container_id=%container.id image=%container.image.repository)"
   priority: ERROR
   tags: [filesystem, mitre_persistence]
 
@@ -1308,6 +1317,10 @@
 - macro: user_known_write_root_conditions
   condition: fd.name=/root/.bash_history
 
+# This is a placeholder for user to extend the whitelist for write below root rule
+- macro: user_known_write_below_root_activities
+  condition: (never_true)
+
 - rule: Write below root
   desc: an attempt to write to any file directly below / or /root
   condition: >
@@ -1329,7 +1342,8 @@
     and not rancher_writing_root
     and not known_root_conditions
     and not user_known_write_root_conditions
-  output: "File below / or /root opened for writing (user=%user.name command=%proc.cmdline parent=%proc.pname file=%fd.name program=%proc.name)"
+    and not user_known_write_below_root_activities
+  output: "File below / or /root opened for writing (user=%user.name command=%proc.cmdline parent=%proc.pname file=%fd.name program=%proc.name container_id=%container.id image=%container.image.repository)"
   priority: ERROR
   tags: [filesystem, mitre_persistence]
 
@@ -1344,7 +1358,7 @@
   condition: sensitive_files and open_read and server_procs and not proc_is_new and proc.name!="sshd"
   output: >
     Sensitive file opened for reading by trusted program after startup (user=%user.name
-    command=%proc.cmdline parent=%proc.pname file=%fd.name parent=%proc.pname gparent=%proc.aname[2])
+    command=%proc.cmdline parent=%proc.pname file=%fd.name parent=%proc.pname gparent=%proc.aname[2] container_id=%container.id image=%container.image.repository)
   priority: WARNING
   tags: [filesystem, mitre_credential_access]
 
@@ -1394,7 +1408,7 @@
     and not runuser_reading_pam
   output: >
     Sensitive file opened for reading by non-trusted program (user=%user.name program=%proc.name
-    command=%proc.cmdline file=%fd.name parent=%proc.pname gparent=%proc.aname[2] ggparent=%proc.aname[3] gggparent=%proc.aname[4])
+    command=%proc.cmdline file=%fd.name parent=%proc.pname gparent=%proc.aname[2] ggparent=%proc.aname[3] gggparent=%proc.aname[4] container_id=%container.id image=%container.image.repository)
   priority: WARNING
   tags: [filesystem, mitre_credential_access, mitre_discovery]
 
@@ -1407,7 +1421,7 @@
     and not ansible_running_python
     and not python_running_chef
     and not exe_running_docker_save
-  output: "Rpm database opened for writing by a non-rpm program (command=%proc.cmdline file=%fd.name parent=%proc.pname pcmdline=%proc.pcmdline)"
+  output: "Rpm database opened for writing by a non-rpm program (command=%proc.cmdline file=%fd.name parent=%proc.pname pcmdline=%proc.pcmdline container_id=%container.id image=%container.image.repository)"
   priority: ERROR
   tags: [filesystem, software_mgmt, mitre_persistence]
 
@@ -1442,7 +1456,7 @@
     and not postgres_running_wal_e
   output: >
     Database-related program spawned process other than itself (user=%user.name
-    program=%proc.cmdline parent=%proc.pname)
+    program=%proc.cmdline parent=%proc.pname container_id=%container.id image=%container.image.repository)
   priority: NOTICE
   tags: [process, database, mitre_execution]
 
@@ -1451,7 +1465,7 @@
   condition: (bin_dir_rename) and modify and not package_mgmt_procs and not exe_running_docker_save
   output: >
     File below known binary directory renamed/removed (user=%user.name command=%proc.cmdline
-    pcmdline=%proc.pcmdline operation=%evt.type file=%fd.name %evt.args)
+    pcmdline=%proc.pcmdline operation=%evt.type file=%fd.name %evt.args container_id=%container.id image=%container.image.repository)
   priority: ERROR
   tags: [filesystem, mitre_persistence]
 
@@ -1460,7 +1474,7 @@
   condition: mkdir and bin_dir_mkdir and not package_mgmt_procs
   output: >
     Directory below known binary directory created (user=%user.name
-    command=%proc.cmdline directory=%evt.arg.path)
+    command=%proc.cmdline directory=%evt.arg.path container_id=%container.id image=%container.image.repository)
   priority: ERROR
   tags: [filesystem, mitre_persistence]
 
@@ -1470,6 +1484,18 @@
 - list: user_known_change_thread_namespace_binaries
   items: []
 
+- macro: user_known_change_thread_namespace_activities
+  condition: (never_true)
+
+- list: network_plugin_binaries
+  items: [aws-cni, azure-vnet]
+
+- macro: calico_node
+  condition: (container.image.repository endswith calico/node and proc.name=calico-node)
+
+- macro: weaveworks_scope
+  condition: (container.image.repository endswith weaveworks/scope and proc.name=scope)
+
 - rule: Change thread namespace
   desc: >
     an attempt to change a program/thread\'s namespace (commonly done
@@ -1477,7 +1503,7 @@
   condition: >
     evt.type = setns
     and not proc.name in (docker_binaries, k8s_binaries, lxd_binaries, sysdigcloud_binaries,
-                          sysdig, nsenter, calico, oci-umount)
+                          sysdig, nsenter, calico, oci-umount, network_plugin_binaries)
     and not proc.name in (user_known_change_thread_namespace_binaries)
     and not proc.name startswith "runc"
     and not proc.cmdline startswith "containerd"
@@ -1487,9 +1513,12 @@
     and not kubelet_running_loopback
     and not rancher_agent
     and not rancher_network_manager
+    and not calico_node
+    and not weaveworks_scope
+    and not user_known_change_thread_namespace_activities
   output: >
     Namespace change (setns) by unexpected program (user=%user.name command=%proc.cmdline
-    parent=%proc.pname %container.info)
+    parent=%proc.pname %container.info container_id=%container.id image=%container.image.repository)
   priority: NOTICE
   tags: [process]
 
@@ -1635,35 +1664,38 @@
   output: >
     Shell spawned by untrusted binary (user=%user.name shell=%proc.name parent=%proc.pname
     cmdline=%proc.cmdline pcmdline=%proc.pcmdline gparent=%proc.aname[2] ggparent=%proc.aname[3]
-    aname[4]=%proc.aname[4] aname[5]=%proc.aname[5] aname[6]=%proc.aname[6] aname[7]=%proc.aname[7])
+    aname[4]=%proc.aname[4] aname[5]=%proc.aname[5] aname[6]=%proc.aname[6] aname[7]=%proc.aname[7] container_id=%container.id image=%container.image.repository)
   priority: DEBUG
   tags: [shell, mitre_execution]
 
 - macro: allowed_openshift_registry_root
   condition: >
     (container.image.repository startswith openshift3/ or
+     container.image.repository startswith registry.redhat.io/openshift3/ or
      container.image.repository startswith registry.access.redhat.com/openshift3/)
 
 # Source: https://docs.openshift.com/enterprise/3.2/install_config/install/disconnected_install.html
 - macro: openshift_image
   condition: >
     (allowed_openshift_registry_root and
-      (container.image.repository contains logging-deployment or
-       container.image.repository contains logging-elasticsearch or
-       container.image.repository contains logging-kibana or
-       container.image.repository contains logging-fluentd or
-       container.image.repository contains logging-auth-proxy or
-       container.image.repository contains metrics-deployer or
-       container.image.repository contains metrics-hawkular-metrics or
-       container.image.repository contains metrics-cassandra or
-       container.image.repository contains metrics-heapster or
-       container.image.repository contains ose-haproxy-router or
-       container.image.repository contains ose-deployer or
-       container.image.repository contains ose-sti-builder or
-       container.image.repository contains ose-docker-builder or
-       container.image.repository contains ose-pod or
-       container.image.repository contains ose-docker-registry or
-       container.image.repository contains image-inspector))
+      (container.image.repository endswith /logging-deployment or
+       container.image.repository endswith /logging-elasticsearch or
+       container.image.repository endswith /logging-kibana or
+       container.image.repository endswith /logging-fluentd or
+       container.image.repository endswith /logging-auth-proxy or
+       container.image.repository endswith /metrics-deployer or
+       container.image.repository endswith /metrics-hawkular-metrics or
+       container.image.repository endswith /metrics-cassandra or
+       container.image.repository endswith /metrics-heapster or
+       container.image.repository endswith /ose-haproxy-router or
+       container.image.repository endswith /ose-deployer or
+       container.image.repository endswith /ose-sti-builder or
+       container.image.repository endswith /ose-docker-builder or
+       container.image.repository endswith /ose-pod or
+       container.image.repository endswith /ose-node or
+       container.image.repository endswith /ose-docker-registry or
+       container.image.repository endswith /prometheus-node-exporter or
+       container.image.repository endswith /image-inspector))
 
 # These images are allowed both to run with --privileged and to mount
 # sensitive paths from the host filesystem.
@@ -1675,6 +1707,13 @@
 - list: trusted_images
   items: []
 
+# NOTE: This macro is only provided for backwards compatibility with
+# older local falco rules files that may have been appending to
+# trusted_images. To make customizations, it's better to add containers to
+# user_trusted_containers, user_privileged_containers or user_sensitive_mount_containers.
+- macro: trusted_containers
+  condition: (container.image.repository in (trusted_images))
+
 # Add conditions to this macro (probably in a separate file,
 # overwriting this macro) to specify additional containers that are
 # trusted and therefore allowed to run privileged *and* with sensitive
@@ -1687,10 +1726,10 @@
 # In this file, it just takes one of the images in trusted_containers
 # and repeats it.
 - macro: user_trusted_containers
-  condition: (container.image.repository=sysdig/agent)
+  condition: (container.image.repository endswith sysdig/agent)
 
 - list: sematext_images
-  items: [sematext/sematext-agent-docker, sematext/agent, sematext/logagent,
+  items: [docker.io/sematext/sematext-agent-docker, docker.io/sematext/agent, docker.io/sematext/logagent,
           registry.access.redhat.com/sematext/sematext-agent-docker,
           registry.access.redhat.com/sematext/agent,
           registry.access.redhat.com/sematext/logagent]
@@ -1698,10 +1737,10 @@
 # These container images are allowed to run with --privileged
 - list: falco_privileged_images
   items: [
-    sysdig/agent, sysdig/falco, sysdig/sysdig,
-    gcr.io/google_containers/kube-proxy, calico/node,
-    rook/toolbox, cloudnativelabs/kube-router, mesosphere/mesos-slave,
-    docker/ucp-agent, sematext_images
+    docker.io/sysdig/agent, docker.io/sysdig/falco, docker.io/sysdig/sysdig,
+    gcr.io/google_containers/kube-proxy, docker.io/calico/node,
+    docker.io/rook/toolbox, docker.io/cloudnativelabs/kube-router, docker.io/mesosphere/mesos-slave,
+    docker.io/docker/ucp-agent, sematext_images, k8s.gcr.io/kube-proxy
     ]
 
 - macro: falco_privileged_containers
@@ -1719,8 +1758,7 @@
 # In this file, it just takes one of the images in falco_privileged_images
 # and repeats it.
 - macro: user_privileged_containers
-  condition: (container.image.repository=sysdig/agent)
-
+  condition: (container.image.repository endswith sysdig/agent)
 
 - list: rancher_images
   items: [
@@ -1732,11 +1770,11 @@
 # host filesystem.
 - list: falco_sensitive_mount_images
   items: [
-    sysdig/agent, sysdig/falco, sysdig/sysdig,
+    docker.io/sysdig/agent, docker.io/sysdig/falco, docker.io/sysdig/sysdig,
     gcr.io/google_containers/hyperkube,
-    gcr.io/google_containers/kube-proxy, calico/node,
-    rook/toolbox, cloudnativelabs/kube-router, consul,
-    datadog/docker-dd-agent, datadog/agent, docker/ucp-agent, gliderlabs/logspout
+    gcr.io/google_containers/kube-proxy, docker.io/calico/node,
+    docker.io/rook/toolbox, docker.io/cloudnativelabs/kube-router, docker.io/consul,
+    docker.io/datadog/docker-dd-agent, docker.io/datadog/agent, docker.io/docker/ucp-agent, docker.io/gliderlabs/logspout
     ]
 
 - macro: falco_sensitive_mount_containers
@@ -1756,7 +1794,7 @@
 # In this file, it just takes one of the images in falco_sensitive_mount_images
 # and repeats it.
 - macro: user_sensitive_mount_containers
-  condition: (container.image.repository=sysdig/agent)
+  condition: (container.image.repository = docker.io/sysdig/agent)
 
 - rule: Launch Privileged Container
   desc: Detect the initial process started in a privileged container. Exceptions are made for known trusted images.
@@ -1794,7 +1832,7 @@
 # when we lose events and lose track of state.
 
 - macro: container_entrypoint
-  condition: (not proc.pname exists or proc.pname in (runc:[0:PARENT], runc:[1:CHILD], docker-runc, exe))
+  condition: (not proc.pname exists or proc.pname in (runc:[0:PARENT], runc:[1:CHILD], runc, docker-runc, exe))
 
 - rule: Launch Sensitive Mount Container
   desc: >
@@ -1837,7 +1875,7 @@
 - rule: System user interactive
   desc: an attempt to run interactive commands by a system (i.e. non-login) user
   condition: spawned_process and system_users and interactive
-  output: "System user ran an interactive command (user=%user.name command=%proc.cmdline)"
+  output: "System user ran an interactive command (user=%user.name command=%proc.cmdline container_id=%container.id image=%container.image.repository)"
   priority: INFO
   tags: [users, mitre_remote_access_tools]
 
@@ -1849,7 +1887,7 @@
     and container_entrypoint
   output: >
     A shell was spawned in a container with an attached terminal (user=%user.name %container.info
-    shell=%proc.name parent=%proc.pname cmdline=%proc.cmdline terminal=%proc.tty)
+    shell=%proc.name parent=%proc.pname cmdline=%proc.cmdline terminal=%proc.tty container_id=%container.id image=%container.image.repository)
   priority: NOTICE
   tags: [container, shell, mitre_execution]
 
@@ -1923,7 +1961,7 @@
     and not login_doing_dns_lookup
   output: >
     Known system binary sent/received network traffic
-    (user=%user.name command=%proc.cmdline connection=%fd.name)
+    (user=%user.name command=%proc.cmdline connection=%fd.name container_id=%container.id image=%container.image.repository)
   priority: NOTICE
   tags: [network, mitre_exfiltration]
 
@@ -1949,7 +1987,7 @@
     proc.env icontains HTTP_PROXY
   output: >
     Program run with disallowed HTTP_PROXY environment variable
-    (user=%user.name command=%proc.cmdline env=%proc.env parent=%proc.pname)
+    (user=%user.name command=%proc.cmdline env=%proc.env parent=%proc.pname container_id=%container.id image=%container.image.repository)
   priority: NOTICE
   tags: [host, users]
 
@@ -1972,7 +2010,7 @@
      and interpreted_procs)
   output: >
     Interpreted program received/listened for network traffic
-    (user=%user.name command=%proc.cmdline connection=%fd.name)
+    (user=%user.name command=%proc.cmdline connection=%fd.name container_id=%container.id image=%container.image.repository)
   priority: NOTICE
   tags: [network, mitre_exfiltration]
 
@@ -1983,7 +2021,7 @@
      and interpreted_procs)
   output: >
     Interpreted program performed outgoing network connection
-    (user=%user.name command=%proc.cmdline connection=%fd.name)
+    (user=%user.name command=%proc.cmdline connection=%fd.name container_id=%container.id image=%container.image.repository)
   priority: NOTICE
   tags: [network, mitre_exfiltration]
 
@@ -2024,7 +2062,7 @@
   condition: (inbound_outbound) and do_unexpected_udp_check and fd.l4proto=udp and not expected_udp_traffic
   output: >
     Unexpected UDP Traffic Seen
-    (user=%user.name command=%proc.cmdline connection=%fd.name proto=%fd.l4proto evt=%evt.type %evt.args)
+    (user=%user.name command=%proc.cmdline connection=%fd.name proto=%fd.l4proto evt=%evt.type %evt.args container_id=%container.id image=%container.image.repository)
   priority: NOTICE
   tags: [network, mitre_exfiltration]
 
@@ -2084,7 +2122,7 @@
     and not user_known_non_sudo_setuid_conditions
   output: >
     Unexpected setuid call by non-sudo, non-root program (user=%user.name cur_uid=%user.uid parent=%proc.pname
-    command=%proc.cmdline uid=%evt.arg.uid)
+    command=%proc.cmdline uid=%evt.arg.uid container_id=%container.id image=%container.image.repository)
   priority: NOTICE
   tags: [users, mitre_privilege_escalation]
 
@@ -2128,7 +2166,7 @@
     and not proc.name in (dev_creation_binaries)
     and not fd.name in (allowed_dev_files)
     and not fd.name startswith /dev/tty
-  output: "File created below /dev by untrusted program (user=%user.name command=%proc.cmdline file=%fd.name)"
+  output: "File created below /dev by untrusted program (user=%user.name command=%proc.cmdline file=%fd.name container_id=%container.id image=%container.image.repository)"
   priority: ERROR
   tags: [filesystem, mitre_persistence]
 
@@ -2189,7 +2227,7 @@
 - rule: Unexpected K8s NodePort Connection
   desc: Detect attempts to use K8s NodePorts from a container
   condition: (inbound_outbound) and fd.sport >= 30000 and fd.sport <= 32767 and container and not nodeport_containers
-  output: Unexpected K8s NodePort Connection (command=%proc.cmdline connection=%fd.name)
+  output: Unexpected K8s NodePort Connection (command=%proc.cmdline connection=%fd.name container_id=%container.id image=%container.image.repository)
   priority: NOTICE
   tags: [network, k8s, container, mitre_port_knocking]
 
@@ -2215,7 +2253,7 @@
   condition: >
     spawned_process and container and
     ((proc.name = "nc" and (proc.args contains "-e" or proc.args contains "-c")) or
-     (proc.name = "ncat" and (proc.args contains "--sh-exec" or proc.args contains "--exec" or proc.args contains "-e " 
+     (proc.name = "ncat" and (proc.args contains "--sh-exec" or proc.args contains "--exec" or proc.args contains "-e "
                               or proc.args contains "-c " or proc.args contains "--lua-exec"))
     )
   output: >
@@ -2299,12 +2337,19 @@
 - macro: access_log_files
   condition: (fd.directory in (log_directories) or fd.filename in (log_files))
 
+# a placeholder for whitelist log files that could be cleared. Recommend the macro as (fd.name startswith "/var/log/app1*")
+- macro: allowed_clear_log_files
+  condition: (never_true)
+
 - rule: Clear Log Activities
   desc: Detect clearing of critical log files
   condition: >
-    open_write and access_log_files and evt.arg.flags contains "O_TRUNC"
+    open_write and
+    access_log_files and
+    evt.arg.flags contains "O_TRUNC" and
+    not allowed_clear_log_files
   output: >
-    Log files were tampered (user=%user.name command=%proc.cmdline file=%fd.name)
+    Log files were tampered (user=%user.name command=%proc.cmdline file=%fd.name container_id=%container.id image=%container.image.repository)
   priority:
     WARNING
   tags: [file, mitre_defense_evasion]
@@ -2319,7 +2364,7 @@
   desc: Detect process running to clear bulk data from disk
   condition: spawned_process and clear_data_procs
   output: >
-    Bulk data has been removed from disk (user=%user.name command=%proc.cmdline file=%fd.name)
+    Bulk data has been removed from disk (user=%user.name command=%proc.cmdline file=%fd.name container_id=%container.id image=%container.image.repository)
   priority:
     WARNING
   tags: [process, mitre_persistence]
@@ -2387,7 +2432,6 @@
   priority: NOTICE
   tags: [network, process, mitre_lateral_movement, mitre_exfiltration]
 
-
 - rule: Create Symlink Over Sensitive Files
   desc: Detect symlink created over sensitive files
   condition: >

scripts/CMakeLists.txt

@@ -18,6 +18,10 @@
 configure_file(debian/postinst.in debian/postinst)
 configure_file(debian/prerm.in debian/prerm)
 
+if(NOT SYSDIG_DIR)
+	set(SYSDIG_DIR "${PROJECT_SOURCE_DIR}/../sysdig")
+endif()
+
 file(COPY "${PROJECT_SOURCE_DIR}/scripts/debian/falco"
 	DESTINATION "${PROJECT_BINARY_DIR}/scripts/debian")
 

test/falco_test.py

@@ -41,6 +41,9 @@ class FalcoTest(Test):
         build_dir = os.path.join('/build', build_type)
         self.falcodir = self.params.get('falcodir', '/', default=os.path.join(self.basedir, build_dir))
 
+        self.stdout_is = self.params.get('stdout_is', '*', default='')
+        self.stderr_is = self.params.get('stderr_is', '*', default='')
+
         self.stdout_contains = self.params.get('stdout_contains', '*', default='')
 
         if not isinstance(self.stdout_contains, list):
@@ -83,8 +86,21 @@ class FalcoTest(Test):
         if not isinstance(self.rules_file, list):
             self.rules_file = [self.rules_file]
 
+        self.validate_rules_file = self.params.get('validate_rules_file', '*', default=False)
+
+        if self.validate_rules_file == False:
+            self.validate_rules_file = []
+        else:
+            if not isinstance(self.validate_rules_file, list):
+                self.validate_rules_file = [self.validate_rules_file]
+
         self.rules_args = ""
 
+        for file in self.validate_rules_file:
+            if not os.path.isabs(file):
+                file = os.path.join(self.basedir, file)
+            self.rules_args = self.rules_args + "-V " + file + " "
+
         for file in self.rules_file:
             if not os.path.isabs(file):
                 file = os.path.join(self.basedir, file)
@@ -433,6 +449,15 @@ class FalcoTest(Test):
 
         res = self.falco_proc.run(timeout=180, sig=9)
 
+        if self.stdout_is != '':
+            print(self.stdout_is)
+            if self.stdout_is != res.stdout:
+                self.fail("Stdout was not exactly {}".format(self.stdout_is))
+
+        if self.stderr_is != '':
+            if self.stderr_is != res.stdout:
+                self.fail("Stdout was not exactly {}".format(self.stderr_is))
+
         for pattern in self.stderr_contains:
             match = re.search(pattern, res.stderr)
             if match is None:

test/falco_tests.yaml

@@ -238,6 +238,199 @@ trace_files: !mux
       - rules/endswith.yaml
     trace_file: trace_files/cat_write.scap
 
+  invalid_not_yaml:
+    exit_status: 1
+    stdout_is: |+
+      Rules content is not yaml
+      ---
+      This is not yaml
+      ---
+    validate_rules_file:
+      - rules/invalid_not_yaml.yaml
+    trace_file: trace_files/cat_write.scap
+
+  invalid_not_array:
+    exit_status: 1
+    stdout_is: |+
+      Rules content is not yaml array of objects
+      ---
+      foo: bar
+      ---
+    validate_rules_file:
+      - rules/invalid_not_array.yaml
+    trace_file: trace_files/cat_write.scap
+
+  invalid_array_item_not_object:
+    exit_status: 1
+    stdout_is: |+
+      Unexpected element of type string. Each element should be a yaml associative array.
+      ---
+      - foo
+      ---
+    validate_rules_file:
+      - rules/invalid_array_item_not_object.yaml
+    trace_file: trace_files/cat_write.scap
+
+  invalid_unexpected object:
+    exit_status: 1
+    stdout_is: |+
+      Unknown rule object: {foo="bar"}
+      ---
+      - foo: bar
+      ---
+    validate_rules_file:
+      - rules/invalid_unexpected_object.yaml
+    trace_file: trace_files/cat_write.scap
+
+  invalid_engine_version_not_number:
+    exit_status: 1
+    stdout_is: |+
+      Value of required_engine_version must be a number
+      ---
+      - required_engine_version: not-a-number
+      ---
+    validate_rules_file:
+      - rules/invalid_engine_version_not_number.yaml
+    trace_file: trace_files/cat_write.scap
+
+  invalid_yaml_parse_error:
+    exit_status: 1
+    stdout_is: |+
+      mapping values are not allowed in this context
+      ---
+      this : is : not : yaml
+      ---
+    validate_rules_file:
+      - rules/invalid_yaml_parse_error.yaml
+    trace_file: trace_files/cat_write.scap
+
+  invalid_list_without_items:
+    exit_status: 1
+    stdout_is: |+
+      List must have property items
+      ---
+      - list: bad_list
+        no_items: foo
+      ---
+    validate_rules_file:
+      - rules/invalid_list_without_items.yaml
+    trace_file: trace_files/cat_write.scap
+
+  invalid_macro_without_condition:
+    exit_status: 1
+    stdout_is: |+
+      Macro must have property condition
+      ---
+      - macro: bad_macro
+        nope: 1
+      ---
+    validate_rules_file:
+      - rules/invalid_macro_without_condition.yaml
+    trace_file: trace_files/cat_write.scap
+
+  invalid_rule_without_output:
+    exit_status: 1
+    stdout_is: |+
+      Rule must have property output
+      ---
+      - rule: no output rule
+        desc: some desc
+        condition: evt.type=fork
+        priority: INFO
+      ---
+    validate_rules_file:
+      - rules/invalid_rule_without_output.yaml
+    trace_file: trace_files/cat_write.scap
+
+  invalid_append_rule_without_condition:
+    exit_status: 1
+    stdout_is: |+
+      Rule must have property condition
+      ---
+      - rule: no condition rule
+        append: true
+      ---
+    validate_rules_file:
+      - rules/invalid_append_rule_without_condition.yaml
+    trace_file: trace_files/cat_write.scap
+
+  invalid_append_macro_dangling:
+    exit_status: 1
+    stdout_is: |+
+      Macro dangling append has 'append' key but no macro by that name already exists
+      ---
+      - macro: dangling append
+        condition: and evt.type=execve
+        append: true
+      ---
+    validate_rules_file:
+      - rules/invalid_append_macro_dangling.yaml
+    trace_file: trace_files/cat_write.scap
+
+  invalid_list_append_dangling:
+    exit_status: 1
+    stdout_is: |+
+      List my_list has 'append' key but no list by that name already exists
+      ---
+      - list: my_list
+        items: [not-cat]
+        append: true
+      ---
+    validate_rules_file:
+      - rules/list_append_failure.yaml
+    trace_file: trace_files/cat_write.scap
+
+  invalid_rule_append_dangling:
+    exit_status: 1
+    stdout_is: |+
+      Rule my_rule has 'append' key but no rule by that name already exists
+      ---
+      - rule: my_rule
+        condition: evt.type=open
+        append: true
+      ---
+    validate_rules_file:
+      - rules/rule_append_failure.yaml
+    trace_file: trace_files/cat_write.scap
+
+  invalid_missing_rule_name:
+    exit_status: 1
+    stdout_is: |+
+      Rule name is empty
+      ---
+      - rule:
+        desc: some desc
+        condition: evt.type=execve
+        output: some output
+      ---
+    validate_rules_file:
+      - rules/invalid_missing_rule_name.yaml
+    trace_file: trace_files/cat_write.scap
+
+  invalid_missing_list_name:
+    exit_status: 1
+    stdout_is: |+
+      List name is empty
+      ---
+      - list:
+        items: [foo]
+      ---
+    validate_rules_file:
+      - rules/invalid_missing_list_name.yaml
+    trace_file: trace_files/cat_write.scap
+
+  invalid_missing_macro_name:
+    exit_status: 1
+    stdout_is: |+
+      Macro name is empty
+      ---
+      - macro:
+        condition: evt.type=execve
+      ---
+    validate_rules_file:
+      - rules/invalid_missing_macro_name.yaml
+    trace_file: trace_files/cat_write.scap
+
   invalid_rule_output:
     exit_status: 1
     stderr_contains: "Runtime error: Error loading rules:.* Invalid output format 'An open was seen %not_a_real_field': 'invalid formatting token not_a_real_field'. Exiting."
@@ -601,7 +794,7 @@ trace_files: !mux
 
   list_append_failure:
     exit_status: 1
-    stderr_contains: "List my_list has 'append' key but no list by that name already exists. Exiting"
+    stderr_contains: "List my_list has 'append' key but no list by that name already exists"
     rules_file:
       - rules/list_append_failure.yaml
     trace_file: trace_files/cat_write.scap
@@ -621,7 +814,7 @@ trace_files: !mux
 
   macro_append_failure:
     exit_status: 1
-    stderr_contains: "Macro my_macro has 'append' key but no macro by that name already exists. Exiting"
+    stderr_contains: "Macro my_macro has 'append' key but no macro by that name already exists"
     rules_file:
       - rules/macro_append_failure.yaml
     trace_file: trace_files/cat_write.scap
@@ -641,7 +834,7 @@ trace_files: !mux
 
   rule_append_failure:
     exit_status: 1
-    stderr_contains: "Rule my_rule has 'append' key but no rule by that name already exists. Exiting"
+    stderr_contains: "Rule my_rule has 'append' key but no rule by that name already exists"
     rules_file:
       - rules/rule_append_failure.yaml
     trace_file: trace_files/cat_write.scap

test/rules/invalid_append_macro_dangling.yaml

@@ -0,0 +1,3 @@
+- macro: dangling append
+  condition: and evt.type=execve
+  append: true

test/rules/invalid_append_rule_without_condition.yaml

@@ -0,0 +1,2 @@
+- rule: no condition rule
+  append: true

test/rules/invalid_array_item_not_object.yaml

@@ -0,0 +1 @@
+- foo

test/rules/invalid_condition_not_rule.yaml

@@ -0,0 +1,5 @@
+- rule: condition not rule
+  condition:
+  desc: some desc
+  output: some output
+  priority: INFO

test/rules/invalid_engine_version_not_number.yaml

@@ -0,0 +1,34 @@
+#
+# Copyright (C) 2016-2018 Draios Inc dba Sysdig.
+#
+# This file is part of falco.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+#
+
+- required_engine_version: not-a-number
+
+- list: cat_binaries
+  items: [cat]
+
+- list: cat_capable_binaries
+  items: [cat_binaries]
+
+- macro: is_cat
+  condition: proc.name in (cat_capable_binaries)
+
+- rule: open_from_cat
+  desc: A process named cat does an open
+  condition: evt.type=open and is_cat
+  output: "An open was seen (command=%proc.cmdline)"
+  priority: WARNING

test/rules/invalid_list_without_items.yaml

@@ -0,0 +1,5 @@
+- list: good_list
+  items: [foo]
+
+- list: bad_list
+  no_items: foo

test/rules/invalid_macro_comple_error.yaml

@@ -0,0 +1,2 @@
+- macro: macro with comp error
+  condition: gak

test/rules/invalid_macro_without_condition.yaml

@@ -0,0 +1,6 @@
+- macro: bad_macro
+  nope: 1
+
+- macro: good_macro
+  condition: evt.type=execve
+

test/rules/invalid_missing_list_name.yaml

@@ -0,0 +1,2 @@
+- list:
+  items: [foo]

test/rules/invalid_missing_macro_name.yaml

@@ -0,0 +1,2 @@
+- macro:
+  condition: evt.type=execve

test/rules/invalid_missing_rule_name.yaml

@@ -0,0 +1,4 @@
+- rule:
+  desc: some desc
+  condition: evt.type=execve
+  output: some output

test/rules/invalid_not_array.yaml

@@ -0,0 +1 @@
+foo: bar

test/rules/invalid_not_yaml.yaml

@@ -0,0 +1 @@
+This is not yaml

test/rules/invalid_rule_without_output.yaml

@@ -0,0 +1,4 @@
+- rule: no output rule
+  desc: some desc
+  condition: evt.type=fork
+  priority: INFO

test/rules/invalid_unexpected_object.yaml

@@ -0,0 +1 @@
+- foo: bar

test/rules/invalid_yaml_parse_error.yaml

@@ -0,0 +1 @@
+this : is : not : yaml

tests/CMakeLists.txt

@@ -0,0 +1,49 @@
+#
+# Copyright (C) 2016-2019 Draios Inc dba Sysdig.
+#
+# This file is part of falco .
+#
+# Licensed under the Apache License, Version 2.0 (the "License"); you may not
+# use this file except in compliance with the License. You may obtain a copy of
+# the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
+# WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
+# License for the specific language governing permissions and limitations under
+# the License.
+#
+set(FALCO_TESTS_SOURCES test_base.cpp engine/test_token_bucket.cpp)
+
+set(FALCO_TESTED_LIBRARIES falco_engine)
+
+option(FALCO_BUILD_TESTS "Determines whether to build tests." ON)
+
+if(FALCO_BUILD_TESTS)
+  enable_testing()
+  if(NOT TARGET catch)
+    include(DownloadCatch)
+  endif()
+
+  if(NOT TARGET fakeit)
+    include(DownloadFakeIt)
+  endif()
+
+  add_executable(falco_test ${FALCO_TESTS_SOURCES})
+
+  target_link_libraries(falco_test PUBLIC ${FALCO_TESTED_LIBRARIES})
+  target_include_directories(
+    falco_test
+    PUBLIC "${CATCH2_INCLUDE}"
+           "${FAKEIT_INCLUDE}"
+           "${PROJECT_SOURCE_DIR}/userspace/engine")
+
+  include(CMakeParseArguments)
+  include(CTest)
+  include(Catch)
+  catch_discover_tests(falco_test)
+
+  add_custom_target(tests COMMAND ${CMAKE_CTEST_COMMAND} DEPENDS falco_test)
+endif()

tests/engine/test_token_bucket.cpp

@@ -0,0 +1,83 @@
+/*
+Copyright (C) 2016-2019 Draios Inc dba Sysdig.
+
+This file is part of falco.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+*/
+
+#include "token_bucket.h"
+#include <catch.hpp>
+
+using namespace Catch::literals;
+
+TEST_CASE("token bucket default ctor", "[token_bucket]")
+{
+	auto tb = new token_bucket();
+
+	REQUIRE(tb->get_tokens() == 1);
+
+	SECTION("initialising with specific time, rate 2 tokens/sec")
+	{
+		auto max = 2.0;
+		uint64_t now = 1;
+		tb->init(1.0, max, now);
+		REQUIRE(tb->get_last_seen() == now);
+		REQUIRE(tb->get_tokens() == max);
+	}
+}
+
+TEST_CASE("token bucket ctor with custom timer", "[token_bucket]")
+{
+	auto t = []() -> uint64_t { return 22; };
+	auto tb = new token_bucket(t);
+
+	REQUIRE(tb->get_tokens() == 1);
+	REQUIRE(tb->get_last_seen() == 22);
+}
+
+TEST_CASE("token bucket with 2 tokens/sec rate, max 10 tokens", "[token_bucket]")
+{
+	auto tb = new token_bucket();
+	tb->init(2.0, 10, 1);
+
+	SECTION("claiming 5 tokens")
+	{
+		bool claimed = tb->claim(5, 1000000001);
+		REQUIRE(tb->get_last_seen() == 1000000001);
+		REQUIRE(tb->get_tokens() == 5.0_a);
+		REQUIRE(claimed);
+
+		SECTION("claiming all the 7 remaining tokens")
+		{
+			bool claimed = tb->claim(7, 2000000001);
+			REQUIRE(tb->get_last_seen() == 2000000001);
+			REQUIRE(tb->get_tokens() == 0.0_a);
+			REQUIRE(claimed);
+
+			SECTION("claiming 1 token more than the 2 available fails")
+			{
+				bool claimed = tb->claim(3, 3000000001);
+				REQUIRE(tb->get_last_seen() == 3000000001);
+				REQUIRE(tb->get_tokens() == 2.0_a);
+				REQUIRE_FALSE(claimed);
+			}
+		}
+	}
+}
+
+TEST_CASE("token bucket default initialization", "[token_bucket]")
+{
+	token_bucket tb;
+	REQUIRE(tb.get_tokens() == 1);
+}

tests/test_base.cpp

@@ -0,0 +1,24 @@
+/*
+Copyright (C) 2016-2019 Draios Inc dba Sysdig.
+
+This file is part of falco.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+*/
+#define CATCH_CONFIG_MAIN
+#define CATCH_CONFIG_CONSOLE_WIDTH 300
+#include <catch.hpp>
+
+TEST_CASE("all test cases reside in other .cpp files (empty)", "[multi-file:1]")
+{
+}

userspace/engine/CMakeLists.txt

@@ -14,17 +14,12 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-#
-include_directories("${PROJECT_SOURCE_DIR}/../sysdig/userspace/libsinsp/third-party/jsoncpp")
-include_directories("${PROJECT_SOURCE_DIR}/../sysdig/userspace/libscap")
-include_directories("${PROJECT_SOURCE_DIR}/../sysdig/userspace/libsinsp")
-include_directories("${PROJECT_BINARY_DIR}/userspace/engine")
-include_directories("${LUAJIT_INCLUDE}")
-include_directories("${NJSON_INCLUDE}")
-include_directories("${CURL_INCLUDE_DIR}")
-include_directories("${TBB_INCLUDE_DIR}")
 
-add_library(falco_engine STATIC
+if(NOT SYSDIG_DIR)
+	set(SYSDIG_DIR "${PROJECT_SOURCE_DIR}/../sysdig")
+endif()
+
+set(FALCO_ENGINE_SOURCE_FILES
 	rules.cpp
 	falco_common.cpp
 	falco_engine.cpp
@@ -33,10 +28,18 @@ add_library(falco_engine STATIC
 	token_bucket.cpp
 	formats.cpp)
 
+add_library(falco_engine STATIC ${FALCO_ENGINE_SOURCE_FILES})
+
 target_include_directories(falco_engine PUBLIC
 	"${LUAJIT_INCLUDE}"
 	"${NJSON_INCLUDE}"
-	"${PROJECT_BINARY_DIR}/userspace/engine")
+	"${CURL_INCLUDE_DIR}"
+	"${TBB_INCLUDE_DIR}"
+	"${SYSDIG_DIR}/userspace/libsinsp/third-party/jsoncpp"
+	"${SYSDIG_DIR}/userspace/libscap"
+	"${SYSDIG_DIR}/userspace/libsinsp"
+	"${PROJECT_BINARY_DIR}/userspace/engine"
+	)
 
 target_link_libraries(falco_engine
   "${FALCO_SINSP_LIBRARY}"

userspace/engine/falco_engine.cpp

@@ -93,21 +93,21 @@ void falco_engine::list_fields(bool names_only)
 		if(!names_only)
 		{
 			printf("\n----------------------\n");
-			printf("Field Class: %s (%s)\n\n", chk_field.name.c_str(), chk_field.desc.c_str());
+			printf("Field Class: %s (%s)\n\n", chk_field.m_name.c_str(), chk_field.m_desc.c_str());
 		}
 
-		for(auto &field : chk_field.fields)
+		for(auto &field : chk_field.m_fields)
 		{
 			uint32_t l, m;
 
-			printf("%s", field.name.c_str());
+			printf("%s", field.m_name.c_str());
 
 			if(names_only)
 			{
 				printf("\n");
 				continue;
 			}
-			uint32_t namelen = field.name.size();
+			uint32_t namelen = field.m_name.size();
 
 			if(namelen >= DESCRIPTION_TEXT_START)
 			{
@@ -120,7 +120,7 @@ void falco_engine::list_fields(bool names_only)
 				printf(" ");
 			}
 
-			size_t desclen = field.desc.size();
+			size_t desclen = field.m_desc.size();
 
 			for(l = 0; l < desclen; l++)
 			{
@@ -134,7 +134,7 @@ void falco_engine::list_fields(bool names_only)
 					}
 				}
 
-				printf("%c", field.desc.at(l));
+				printf("%c", field.m_desc.at(l));
 			}
 
 			printf("\n");

userspace/engine/falco_engine_version.h

@@ -19,9 +19,9 @@ limitations under the License.
 
 // The version of rules/filter fields/etc supported by this falco
 // engine.
-#define FALCO_ENGINE_VERSION (3)
+#define FALCO_ENGINE_VERSION (4)
 
 // This is the result of running "falco --list -N | sha256sum" and
 // represents the fields supported by this version of falco. It's used
 // at build time to detect a changed set of fields.
-#define FALCO_FIELDS_CHECKSUM "fb82780f268b91fb888876e6ac1142b5acca08e05b3a82c4b1b524ca88fa83d9"
+#define FALCO_FIELDS_CHECKSUM "ceb069d9f9b2d4ebcc5de39bddc53b7af2e6b8f072edc293668fd6ac4e532413"

userspace/engine/json_evt.cpp

@@ -19,8 +19,8 @@ limitations under the License.
 
 #include <ctype.h>
 
-#include "utils.h"
 #include "uri.h"
+#include "utils.h"
 
 #include "falco_common.h"
 #include "json_evt.h"
@@ -30,7 +30,6 @@ using namespace std;
 
 json_event::json_event()
 {
-
 }
 
 json_event::~json_event()
@@ -60,7 +59,7 @@ std::string json_event_filter_check::def_format(const json &j, std::string &fiel
 
 std::string json_event_filter_check::json_as_string(const json &j)
 {
-	if (j.type() == json::value_t::string)
+	if(j.type() == json::value_t::string)
 	{
 		return j;
 	}
@@ -70,30 +69,55 @@ std::string json_event_filter_check::json_as_string(const json &j)
 	}
 }
 
+json_event_filter_check::field_info::field_info():
+	m_idx_mode(IDX_NONE), m_idx_type(IDX_NUMERIC)
+{
+}
+
+json_event_filter_check::field_info::field_info(std::string name,
+						std::string desc):
+	m_name(name),
+	m_desc(desc),
+	m_idx_mode(IDX_NONE), m_idx_type(IDX_NUMERIC)
+{
+}
+
+json_event_filter_check::field_info::field_info(std::string name,
+						std::string desc,
+						index_mode mode):
+	m_name(name),
+	m_desc(desc),
+	m_idx_mode(mode), m_idx_type(IDX_NUMERIC)
+{
+}
+
+json_event_filter_check::field_info::field_info(std::string name,
+						std::string desc,
+						index_mode mode,
+						index_type itype):
+	m_name(name),
+	m_desc(desc),
+	m_idx_mode(mode), m_idx_type(itype)
+{
+}
+
+json_event_filter_check::field_info::~field_info()
+{
+}
+
 json_event_filter_check::alias::alias()
-	: m_idx_mode(IDX_NONE), m_idx_type(IDX_NUMERIC)
 {
 }
 
-json_event_filter_check::alias::alias(nlohmann::json::json_pointer ptr)
-	: m_jptr(ptr), m_format(def_format),
-	  m_idx_mode(IDX_NONE), m_idx_type(IDX_NUMERIC)
+json_event_filter_check::alias::alias(nlohmann::json::json_pointer ptr):
+	m_jptr(ptr), m_format(def_format)
 {
 }
 
 json_event_filter_check::alias::alias(nlohmann::json::json_pointer ptr,
-				      format_t format)
-	: m_jptr(ptr), m_format(format),
-	  m_idx_mode(IDX_NONE), m_idx_type(IDX_NUMERIC)
-{
-}
-
-json_event_filter_check::alias::alias(nlohmann::json::json_pointer ptr,
-				      format_t format,
-				      index_mode mode,
-				      index_type itype)
-	: m_jptr(ptr), m_format(format),
-	  m_idx_mode(mode), m_idx_type(itype)
+				      format_t format):
+	m_jptr(ptr),
+	m_format(format)
 {
 }
 
@@ -101,8 +125,8 @@ json_event_filter_check::alias::~alias()
 {
 }
 
-json_event_filter_check::json_event_filter_check()
-	: m_format(def_format)
+json_event_filter_check::json_event_filter_check():
+	m_format(def_format)
 {
 }
 
@@ -118,18 +142,25 @@ int32_t json_event_filter_check::parse_field_name(const char *str, bool alloc_st
 
 	size_t idx_len = 0;
 
-	for(auto &pair : m_aliases)
+	for(auto &info : m_info.m_fields)
 	{
-		// What follows the match must not be alphanumeric or a dot
-		if(strncmp(pair.first.c_str(), str, pair.first.size()) == 0 &&
-		   !isalnum((int) str[pair.first.size()]) &&
-		   str[pair.first.size()] != '.' &&
-		   pair.first.size() > match_len)
+		if(m_aliases.find(info.m_name) == m_aliases.end())
 		{
-			m_jptr = pair.second.m_jptr;
-			m_field = pair.first;
-			m_format = pair.second.m_format;
-			match_len = pair.first.size();
+			throw falco_exception("Could not find alias for field name " + info.m_name);
+		}
+
+		auto &al = m_aliases[info.m_name];
+
+		// What follows the match must not be alphanumeric or a dot
+		if(strncmp(info.m_name.c_str(), str, info.m_name.size()) == 0 &&
+		   !isalnum((int)str[info.m_name.size()]) &&
+		   str[info.m_name.size()] != '.' &&
+		   info.m_name.size() > match_len)
+		{
+			m_jptr = al.m_jptr;
+			m_field = info.m_name;
+			m_format = al.m_format;
+			match_len = info.m_name.size();
 
 			const char *start = str + m_field.size();
 
@@ -141,24 +172,24 @@ int32_t json_event_filter_check::parse_field_name(const char *str, bool alloc_st
 
 				if(end != NULL)
 				{
-					m_idx = string(start, end-start);
+					m_idx = string(start, end - start);
 				}
 
 				idx_len = (end - start + 2);
 			}
 
-			if(m_idx.empty() && pair.second.m_idx_mode == alias::IDX_REQUIRED)
+			if(m_idx.empty() && info.m_idx_mode == IDX_REQUIRED)
 			{
 				throw falco_exception(string("When parsing filtercheck ") + string(str) + string(": ") + m_field + string(" requires an index but none provided"));
 			}
 
-			if(!m_idx.empty() && pair.second.m_idx_mode == alias::IDX_NONE)
+			if(!m_idx.empty() && info.m_idx_mode == IDX_NONE)
 			{
 				throw falco_exception(string("When parsing filtercheck ") + string(str) + string(": ") + m_field + string(" forbids an index but one provided"));
 			}
 
 			if(!m_idx.empty() &&
-			   pair.second.m_idx_type == alias::IDX_NUMERIC &&
+			   info.m_idx_type == IDX_NUMERIC &&
 			   m_idx.find_first_not_of("0123456789") != string::npos)
 			{
 				throw falco_exception(string("When parsing filtercheck ") + string(str) + string(": ") + m_field + string(" requires a numeric index"));
@@ -169,14 +200,14 @@ int32_t json_event_filter_check::parse_field_name(const char *str, bool alloc_st
 	return match_len + idx_len;
 }
 
-void json_event_filter_check::add_filter_value(const char* str, uint32_t len, uint32_t i)
+void json_event_filter_check::add_filter_value(const char *str, uint32_t len, uint32_t i)
 {
 	m_values.push_back(string(str));
 }
 
 bool json_event_filter_check::compare(gen_event *evt)
 {
-	json_event *jevt = (json_event *) evt;
+	json_event *jevt = (json_event *)evt;
 
 	std::string value = extract(jevt);
 
@@ -197,7 +228,7 @@ bool json_event_filter_check::compare(gen_event *evt)
 	case CO_IN:
 		for(auto &val : m_values)
 		{
-			if (value == val)
+			if(value == val)
 			{
 				return true;
 			}
@@ -240,11 +271,12 @@ json_event_filter_check::check_info &json_event_filter_check::get_fields()
 	return m_info;
 }
 
-uint8_t* json_event_filter_check::extract(gen_event *evt, uint32_t* len, bool sanitize_strings)
+uint8_t *json_event_filter_check::extract(gen_event *evt, uint32_t *len, bool sanitize_strings)
 {
-	json_event *jevt = (json_event *) evt;
+	json_event *jevt = (json_event *)evt;
 
-	try {
+	try
+	{
 		const json &j = jevt->jevt().at(m_jptr);
 
 		// Only format when the value was actually found in
@@ -258,7 +290,7 @@ uint8_t* json_event_filter_check::extract(gen_event *evt, uint32_t* len, bool sa
 
 	*len = m_tstr.size();
 
-	return (uint8_t *) m_tstr.c_str();
+	return (uint8_t *)m_tstr.c_str();
 }
 
 std::string json_event_filter_check::extract(json_event *evt)
@@ -271,7 +303,7 @@ std::string json_event_filter_check::extract(json_event *evt)
 
 	if(res != NULL)
 	{
-		ret.assign((const char *) res, len);
+		ret.assign((const char *)res, len);
 	}
 
 	return ret;
@@ -287,18 +319,15 @@ jevt_filter_check::jevt_filter_check()
 {
 	m_info = {"jevt",
 		  "generic ways to access json events",
-		  {
-			  {s_jevt_time_field, "json event timestamp as a string that includes the nanosecond part"},
-			  {s_jevt_time_iso_8601_field, "json event timestamp in ISO 8601 format, including nanoseconds and time zone offset (in UTC)"},
-			  {s_jevt_rawtime_field, "absolute event timestamp, i.e. nanoseconds from epoch."},
-			  {s_jevt_value_field, "General way to access single property from json object. The syntax is [<json pointer expression>]. The property is returned as a string"},
-			  {s_jevt_obj_field, "The entire json object, stringified"}
-		  }};
+		  {{s_jevt_time_field, "json event timestamp as a string that includes the nanosecond part"},
+		   {s_jevt_time_iso_8601_field, "json event timestamp in ISO 8601 format, including nanoseconds and time zone offset (in UTC)"},
+		   {s_jevt_rawtime_field, "absolute event timestamp, i.e. nanoseconds from epoch."},
+		   {s_jevt_value_field, "General way to access single property from json object. The syntax is [<json pointer expression>]. The property is returned as a string", IDX_REQUIRED, IDX_KEY},
+		   {s_jevt_obj_field, "The entire json object, stringified"}}};
 }
 
 jevt_filter_check::~jevt_filter_check()
 {
-
 }
 
 int32_t jevt_filter_check::parse_field_name(const char *str, bool alloc_state, bool needed_for_filtering)
@@ -332,55 +361,56 @@ int32_t jevt_filter_check::parse_field_name(const char *str, bool alloc_state, b
 		const char *end;
 
 		// What follows must be [<json pointer expression>]
-		if (*(str + s_jevt_value_field.size()) != '[' ||
-		    ((end = strchr(str + 1, ']')) == NULL))
+		if(*(str + s_jevt_value_field.size()) != '[' ||
+		   ((end = strchr(str + 1, ']')) == NULL))
 
 		{
 			throw falco_exception(string("Could not parse filtercheck field \"") + str + "\". Did not have expected format with 'jevt.value[<json pointer>]'");
 		}
 
-		try {
-			m_jptr = json::json_pointer(string(str + (s_jevt_value_field.size()+1), (end-str-(s_jevt_value_field.size()+1))));
+		try
+		{
+			m_jptr = json::json_pointer(string(str + (s_jevt_value_field.size() + 1), (end - str - (s_jevt_value_field.size() + 1))));
 		}
-		catch (json::parse_error& e)
+		catch(json::parse_error &e)
 		{
 			throw falco_exception(string("Could not parse filtercheck field \"") + str + "\". Invalid json selector (" + e.what() + ")");
 		}
 
 		// The +1 accounts for the closing ']'
-		m_field = string(str, end-str + 1);
+		m_field = string(str, end - str + 1);
 		return (end - str + 1);
 	}
 
 	return 0;
 }
 
-uint8_t* jevt_filter_check::extract(gen_event *evt, uint32_t* len, bool sanitize_stings)
+uint8_t *jevt_filter_check::extract(gen_event *evt, uint32_t *len, bool sanitize_stings)
 {
 	if(m_field == s_jevt_rawtime_field)
 	{
 		m_tstr = to_string(evt->get_ts());
 		*len = m_tstr.size();
-		return (uint8_t *) m_tstr.c_str();
+		return (uint8_t *)m_tstr.c_str();
 	}
 	else if(m_field == s_jevt_time_field)
 	{
 		sinsp_utils::ts_to_string(evt->get_ts(), &m_tstr, false, true);
 		*len = m_tstr.size();
-		return (uint8_t *) m_tstr.c_str();
+		return (uint8_t *)m_tstr.c_str();
 	}
 	else if(m_field == s_jevt_time_iso_8601_field)
 	{
 		sinsp_utils::ts_to_iso_8601(evt->get_ts(), &m_tstr);
 		*len = m_tstr.size();
-		return (uint8_t *) m_tstr.c_str();
+		return (uint8_t *)m_tstr.c_str();
 	}
 	else if(m_field == s_jevt_obj_field)
 	{
-		json_event *jevt = (json_event *) evt;
+		json_event *jevt = (json_event *)evt;
 		m_tstr = jevt->jevt().dump();
 		*len = m_tstr.size();
-		return (uint8_t *) m_tstr.c_str();
+		return (uint8_t *)m_tstr.c_str();
 	}
 
 	return json_event_filter_check::extract(evt, len, sanitize_stings);
@@ -390,7 +420,7 @@ json_event_filter_check *jevt_filter_check::allocate_new()
 {
 	jevt_filter_check *chk = new jevt_filter_check();
 
-	return (json_event_filter_check *) chk;
+	return (json_event_filter_check *)chk;
 }
 
 std::string k8s_audit_filter_check::index_image(const json &j, std::string &field, std::string &idx)
@@ -399,8 +429,9 @@ std::string k8s_audit_filter_check::index_image(const json &j, std::string &fiel
 
 	string image;
 
-	try {
-		image  = j[idx_num].at("image");
+	try
+	{
+		image = j[idx_num].at("image");
 	}
 	catch(json::out_of_range &e)
 	{
@@ -442,7 +473,6 @@ std::string k8s_audit_filter_check::index_has_name(const json &j, std::string &f
 	return string("false");
 }
 
-
 std::string k8s_audit_filter_check::index_query_param(const json &j, std::string &field, std::string &idx)
 {
 	string uri = j;
@@ -461,7 +491,7 @@ std::string k8s_audit_filter_check::index_query_param(const json &j, std::string
 	{
 		std::vector<std::string> param_parts = sinsp_split(part, '=');
 
-		if(param_parts.size() == 2 && uri::decode(param_parts[0], true)==idx)
+		if(param_parts.size() == 2 && uri::decode(param_parts[0], true) == idx)
 		{
 			return uri::decode(param_parts[1]);
 		}
@@ -470,7 +500,6 @@ std::string k8s_audit_filter_check::index_query_param(const json &j, std::string
 	return string("<NA>");
 }
 
-
 std::string k8s_audit_filter_check::index_generic(const json &j, std::string &field, std::string &idx)
 {
 	json item;
@@ -483,7 +512,8 @@ std::string k8s_audit_filter_check::index_generic(const json &j, std::string &fi
 	{
 		uint64_t idx_num = (idx.empty() ? 0 : stoi(idx));
 
-		try {
+		try
+		{
 			item = j[idx_num];
 		}
 		catch(json::out_of_range &e)
@@ -501,7 +531,7 @@ std::string k8s_audit_filter_check::index_select(const json &j, std::string &fie
 
 	// Use the suffix of the field to determine which property to
 	// select from each object.
-	std::string prop = field.substr(field.find_last_of(".")+1);
+	std::string prop = field.substr(field.find_last_of(".") + 1);
 
 	std::string ret;
 
@@ -514,7 +544,8 @@ std::string k8s_audit_filter_check::index_select(const json &j, std::string &fie
 				ret += " ";
 			}
 
-			try {
+			try
+			{
 				ret += json_event_filter_check::json_as_string(obj.at(prop));
 			}
 			catch(json::out_of_range &e)
@@ -525,7 +556,8 @@ std::string k8s_audit_filter_check::index_select(const json &j, std::string &fie
 	}
 	else
 	{
-		try {
+		try
+		{
 			ret = j[stoi(idx)].at(prop);
 		}
 		catch(json::out_of_range &e)
@@ -545,7 +577,8 @@ std::string k8s_audit_filter_check::index_privileged(const json &j, std::string
 
 	if(!idx.empty())
 	{
-		try {
+		try
+		{
 			privileged = j[stoi(idx)].at(jpriv);
 		}
 		catch(json::out_of_range &e)
@@ -556,7 +589,8 @@ std::string k8s_audit_filter_check::index_privileged(const json &j, std::string
 	{
 		for(auto &container : j)
 		{
-			try {
+			try
+			{
 				if(container.at(jpriv))
 				{
 					privileged = true;
@@ -593,46 +627,43 @@ k8s_audit_filter_check::k8s_audit_filter_check()
 {
 	m_info = {"ka",
 		  "Access K8s Audit Log Events",
-		  {
-			  {"ka.auditid", "The unique id of the audit event"},
-			  {"ka.stage", "Stage of the request (e.g. RequestReceived, ResponseComplete, etc.)"},
-			  {"ka.auth.decision", "The authorization decision"},
-			  {"ka.auth.reason", "The authorization reason"},
-			  {"ka.user.name", "The user name performing the request"},
-			  {"ka.user.groups", "The groups to which the user belongs"},
-			  {"ka.impuser.name", "The impersonated user name"},
-			  {"ka.verb", "The action being performed"},
-			  {"ka.uri", "The request URI as sent from client to server"},
-			  {"ka.uri.param", "The value of a given query parameter in the uri (e.g. when uri=/foo?key=val, ka.uri.param[key] is val)."},
-			  {"ka.target.name", "The target object name"},
-			  {"ka.target.namespace", "The target object namespace"},
-			  {"ka.target.resource", "The target object resource"},
-			  {"ka.target.subresource", "The target object subresource"},
-			  {"ka.req.binding.subjects", "When the request object refers to a cluster role binding, the subject (e.g. account/users) being linked by the binding"},
-			  {"ka.req.binding.subject.has_name", "When the request object refers to a cluster role binding, return true if a subject with the provided name exists"},
-			  {"ka.req.binding.role", "When the request object refers to a cluster role binding, the role being linked by the binding"},
-			  {"ka.req.configmap.name", "If the request object refers to a configmap, the configmap name"},
-			  {"ka.req.configmap.obj", "If the request object refers to a configmap, the entire configmap object"},
-			  {"ka.req.container.image", "When the request object refers to a container, the container's images. Can be indexed (e.g. ka.req.container.image[0]). Without any index, returns the first image"},
-			  {"ka.req.container.image.repository", "The same as req.container.image, but only the repository part (e.g. sysdig/falco)"},
-			  {"ka.req.container.host_network", "When the request object refers to a container, the value of the hostNetwork flag."},
-			  {"ka.req.container.privileged", "When the request object refers to a container, whether or not any container is run privileged. With an index, return whether or not the ith container is run privileged."},
-			  {"ka.req.role.rules", "When the request object refers to a role/cluster role, the rules associated with the role"},
-			  {"ka.req.role.rules.apiGroups", "When the request object refers to a role/cluster role, the api groups associated with the role's rules. With an index, return only the api groups from the ith rule. Without an index, return all api groups concatenated"},
-			  {"ka.req.role.rules.nonResourceURLs", "When the request object refers to a role/cluster role, the non resource urls associated with the role's rules. With an index, return only the non resource urls from the ith rule. Without an index, return all non resource urls concatenated"},
-			  {"ka.req.role.rules.verbs", "When the request object refers to a role/cluster role, the verbs associated with the role's rules. With an index, return only the verbs from the ith rule. Without an index, return all verbs concatenated"},
-			  {"ka.req.role.rules.resources", "When the request object refers to a role/cluster role, the resources associated with the role's rules. With an index, return only the resources from the ith rule. Without an index, return all resources concatenated"},
-			  {"ka.req.service.type", "When the request object refers to a service, the service type"},
-			  {"ka.req.service.ports", "When the request object refers to a service, the service's ports. Can be indexed (e.g. ka.req.service.ports[0]). Without any index, returns all ports"},
-			  {"ka.req.volume.hostpath", "If the request object contains volume definitions, whether or not a hostPath volume exists that mounts the specified path from the host (...hostpath[/etc]=true if a volume mounts /etc from the host). The index can be a glob, in which case all volumes are considered to find any path matching the specified glob (...hostpath[/usr/*] would match either /usr/local or /usr/bin)"},
-			  {"ka.resp.name", "The response object name"},
-			  {"ka.response.code", "The response code"},
-			  {"ka.response.reason", "The response reason (usually present only for failures)"}
-		  }};
+		  {{"ka.auditid", "The unique id of the audit event"},
+		   {"ka.stage", "Stage of the request (e.g. RequestReceived, ResponseComplete, etc.)"},
+		   {"ka.auth.decision", "The authorization decision"},
+		   {"ka.auth.reason", "The authorization reason"},
+		   {"ka.user.name", "The user name performing the request"},
+		   {"ka.user.groups", "The groups to which the user belongs"},
+		   {"ka.impuser.name", "The impersonated user name"},
+		   {"ka.verb", "The action being performed"},
+		   {"ka.uri", "The request URI as sent from client to server"},
+		   {"ka.uri.param", "The value of a given query parameter in the uri (e.g. when uri=/foo?key=val, ka.uri.param[key] is val).", IDX_REQUIRED, IDX_KEY},
+		   {"ka.target.name", "The target object name"},
+		   {"ka.target.namespace", "The target object namespace"},
+		   {"ka.target.resource", "The target object resource"},
+		   {"ka.target.subresource", "The target object subresource"},
+		   {"ka.req.binding.subjects", "When the request object refers to a cluster role binding, the subject (e.g. account/users) being linked by the binding"},
+		   {"ka.req.binding.subject.has_name", "When the request object refers to a cluster role binding, return true if a subject with the provided name exists", IDX_REQUIRED, IDX_KEY},
+		   {"ka.req.binding.role", "When the request object refers to a cluster role binding, the role being linked by the binding"},
+		   {"ka.req.configmap.name", "If the request object refers to a configmap, the configmap name"},
+		   {"ka.req.configmap.obj", "If the request object refers to a configmap, the entire configmap object"},
+		   {"ka.req.container.image", "When the request object refers to a container, the container's images. Can be indexed (e.g. ka.req.container.image[0]). Without any index, returns the first image", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.container.image.repository", "The same as req.container.image, but only the repository part (e.g. sysdig/falco)", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.container.host_network", "When the request object refers to a container, the value of the hostNetwork flag."},
+		   {"ka.req.container.privileged", "When the request object refers to a container, whether or not any container is run privileged. With an index, return whether or not the ith container is run privileged.", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.role.rules", "When the request object refers to a role/cluster role, the rules associated with the role"},
+		   {"ka.req.role.rules.apiGroups", "When the request object refers to a role/cluster role, the api groups associated with the role's rules. With an index, return only the api groups from the ith rule. Without an index, return all api groups concatenated", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.role.rules.nonResourceURLs", "When the request object refers to a role/cluster role, the non resource urls associated with the role's rules. With an index, return only the non resource urls from the ith rule. Without an index, return all non resource urls concatenated", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.role.rules.verbs", "When the request object refers to a role/cluster role, the verbs associated with the role's rules. With an index, return only the verbs from the ith rule. Without an index, return all verbs concatenated", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.role.rules.resources", "When the request object refers to a role/cluster role, the resources associated with the role's rules. With an index, return only the resources from the ith rule. Without an index, return all resources concatenated", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.service.type", "When the request object refers to a service, the service type"},
+		   {"ka.req.service.ports", "When the request object refers to a service, the service's ports. Can be indexed (e.g. ka.req.service.ports[0]). Without any index, returns all ports", IDX_ALLOWED, IDX_NUMERIC},
+		   {"ka.req.volume.hostpath", "If the request object contains volume definitions, whether or not a hostPath volume exists that mounts the specified path from the host (...hostpath[/etc]=true if a volume mounts /etc from the host). The index can be a glob, in which case all volumes are considered to find any path matching the specified glob (...hostpath[/usr/*] would match either /usr/local or /usr/bin)", IDX_REQUIRED, IDX_KEY},
+		   {"ka.resp.name", "The response object name"},
+		   {"ka.response.code", "The response code"},
+		   {"ka.response.reason", "The response reason (usually present only for failures)"},
+		   {"ka.useragent", "The useragent of the client who made the request to the apiserver"}}};
 
 	{
-		using a = alias;
-
 		m_aliases = {
 			{"ka.auditid", {"/auditID"_json_pointer}},
 			{"ka.stage", {"/stage"_json_pointer}},
@@ -643,45 +674,44 @@ k8s_audit_filter_check::k8s_audit_filter_check()
 			{"ka.impuser.name", {"/impersonatedUser/username"_json_pointer}},
 			{"ka.verb", {"/verb"_json_pointer}},
 			{"ka.uri", {"/requestURI"_json_pointer}},
-			{"ka.uri.param", {"/requestURI"_json_pointer, index_query_param, a::IDX_REQUIRED, a::IDX_KEY}},
+			{"ka.uri.param", {"/requestURI"_json_pointer, index_query_param}},
 			{"ka.target.name", {"/objectRef/name"_json_pointer}},
 			{"ka.target.namespace", {"/objectRef/namespace"_json_pointer}},
 			{"ka.target.resource", {"/objectRef/resource"_json_pointer}},
 			{"ka.target.subresource", {"/objectRef/subresource"_json_pointer}},
 			{"ka.req.binding.subjects", {"/requestObject/subjects"_json_pointer}},
-			{"ka.req.binding.subject.has_name", {"/requestObject/subjects"_json_pointer, index_has_name, a::IDX_REQUIRED, a::IDX_KEY}},
+			{"ka.req.binding.subject.has_name", {"/requestObject/subjects"_json_pointer, index_has_name}},
 			{"ka.req.binding.role", {"/requestObject/roleRef/name"_json_pointer}},
 			{"ka.req.configmap.name", {"/objectRef/name"_json_pointer}},
 			{"ka.req.configmap.obj", {"/requestObject/data"_json_pointer}},
-			{"ka.req.container.image", {"/requestObject/spec/containers"_json_pointer, index_image, a::IDX_ALLOWED, a::IDX_NUMERIC}},
-			{"ka.req.container.image.repository", {"/requestObject/spec/containers"_json_pointer, index_image, a::IDX_ALLOWED, a::IDX_NUMERIC}},
+			{"ka.req.container.image", {"/requestObject/spec/containers"_json_pointer, index_image}},
+			{"ka.req.container.image.repository", {"/requestObject/spec/containers"_json_pointer, index_image}},
 			{"ka.req.container.host_network", {"/requestObject/spec/hostNetwork"_json_pointer}},
-			{"ka.req.container.privileged", {"/requestObject/spec/containers"_json_pointer, index_privileged, a::IDX_ALLOWED, a::IDX_NUMERIC}},
+			{"ka.req.container.privileged", {"/requestObject/spec/containers"_json_pointer, index_privileged}},
 			{"ka.req.role.rules", {"/requestObject/rules"_json_pointer}},
-			{"ka.req.role.rules.apiGroups", {"/requestObject/rules"_json_pointer, index_select, a::IDX_ALLOWED, a::IDX_NUMERIC}},
-			{"ka.req.role.rules.nonResourceURLs", {"/requestObject/rules"_json_pointer, index_select, a::IDX_ALLOWED, a::IDX_NUMERIC}},
-			{"ka.req.role.rules.resources", {"/requestObject/rules"_json_pointer, index_select, a::IDX_ALLOWED, a::IDX_NUMERIC}},
-			{"ka.req.role.rules.verbs", {"/requestObject/rules"_json_pointer, index_select, a::IDX_ALLOWED, a::IDX_NUMERIC}},
+			{"ka.req.role.rules.apiGroups", {"/requestObject/rules"_json_pointer, index_select}},
+			{"ka.req.role.rules.nonResourceURLs", {"/requestObject/rules"_json_pointer, index_select}},
+			{"ka.req.role.rules.resources", {"/requestObject/rules"_json_pointer, index_select}},
+			{"ka.req.role.rules.verbs", {"/requestObject/rules"_json_pointer, index_select}},
 			{"ka.req.service.type", {"/requestObject/spec/type"_json_pointer}},
-			{"ka.req.service.ports", {"/requestObject/spec/ports"_json_pointer, index_generic, a::IDX_ALLOWED, a::IDX_NUMERIC}},
-			{"ka.req.volume.hostpath", {"/requestObject/spec/volumes"_json_pointer, check_hostpath_vols, a::IDX_REQUIRED, a::IDX_KEY}},
+			{"ka.req.service.ports", {"/requestObject/spec/ports"_json_pointer, index_generic}},
+			{"ka.req.volume.hostpath", {"/requestObject/spec/volumes"_json_pointer, check_hostpath_vols}},
 			{"ka.resp.name", {"/responseObject/metadata/name"_json_pointer}},
 			{"ka.response.code", {"/responseStatus/code"_json_pointer}},
-			{"ka.response.reason", {"/responseStatus/reason"_json_pointer}}
-		};
+			{"ka.response.reason", {"/responseStatus/reason"_json_pointer}},
+			{"ka.useragent", {"/userAgent"_json_pointer}}};
 	}
 }
 
 k8s_audit_filter_check::~k8s_audit_filter_check()
 {
-
 }
 
 json_event_filter_check *k8s_audit_filter_check::allocate_new()
 {
 	k8s_audit_filter_check *chk = new k8s_audit_filter_check();
 
-	return (json_event_filter_check *) chk;
+	return (json_event_filter_check *)chk;
 }
 
 json_event_filter::json_event_filter()
@@ -736,9 +766,9 @@ std::list<json_event_filter_check::check_info> &json_event_filter_factory::get_f
 	return m_info;
 }
 
-json_event_formatter::json_event_formatter(json_event_filter_factory &json_factory, std::string &format)
-	: m_format(format),
-	  m_json_factory(json_factory)
+json_event_formatter::json_event_formatter(json_event_filter_factory &json_factory, std::string &format):
+	m_format(format),
+	m_json_factory(json_factory)
 {
 	parse_format();
 }
@@ -751,7 +781,7 @@ std::string json_event_formatter::tostring(json_event *ev)
 {
 	std::string ret;
 
-	std::list<std::pair<std::string,std::string>> resolved;
+	std::list<std::pair<std::string, std::string>> resolved;
 
 	resolve_tokens(ev, resolved);
 
@@ -767,7 +797,7 @@ std::string json_event_formatter::tojson(json_event *ev)
 {
 	nlohmann::json ret;
 
-	std::list<std::pair<std::string,std::string>> resolved;
+	std::list<std::pair<std::string, std::string>> resolved;
 
 	resolve_tokens(ev, resolved);
 
@@ -802,11 +832,11 @@ void json_event_formatter::parse_format()
 		{
 			// Skip the %
 			tformat.erase(0, 1);
-			json_event_filter_check *chk = (json_event_filter_check *) m_json_factory.new_filtercheck(tformat.c_str());
+			json_event_filter_check *chk = (json_event_filter_check *)m_json_factory.new_filtercheck(tformat.c_str());
 
 			if(!chk)
 			{
-				throw falco_exception(string ("Could not parse format string \"") + m_format + "\": unknown filtercheck field " + tformat);
+				throw falco_exception(string("Could not parse format string \"") + m_format + "\": unknown filtercheck field " + tformat);
 			}
 
 			size = chk->parsed_size();
@@ -826,7 +856,7 @@ void json_event_formatter::parse_format()
 			// Empty fields are only allowed at the beginning of the string
 			if(m_tokens.size() > 0)
 			{
-				throw falco_exception(string ("Could not parse format string \"" + m_format + "\": empty filtercheck field"));
+				throw falco_exception(string("Could not parse format string \"" + m_format + "\": empty filtercheck field"));
 			}
 			continue;
 		}
@@ -838,7 +868,7 @@ void json_event_formatter::parse_format()
 	}
 }
 
-void json_event_formatter::resolve_tokens(json_event *ev, std::list<std::pair<std::string,std::string>> &resolved)
+void json_event_formatter::resolve_tokens(json_event *ev, std::list<std::pair<std::string, std::string>> &resolved)
 {
 	for(auto tok : m_tokens)
 	{

userspace/engine/json_evt.h

@@ -62,19 +62,40 @@ protected:
 class json_event_filter_check : public gen_event_filter_check
 {
 public:
+	enum index_mode {
+		IDX_REQUIRED,
+		IDX_ALLOWED,
+		IDX_NONE
+	};
+
+	enum index_type {
+		IDX_KEY,
+		IDX_NUMERIC
+	};
 
 	// A struct describing a single filtercheck field ("ka.user")
 	struct field_info {
-		std::string name;
-		std::string desc;
+		std::string m_name;
+		std::string m_desc;
+
+		index_mode m_idx_mode;
+		index_type m_idx_type;
+		// The variants allow for brace-initialization either
+		// with just the name/desc or additionally with index
+		// information
+		field_info();
+		field_info(std::string name, std::string desc);
+		field_info(std::string name, std::string desc, index_mode mode);
+		field_info(std::string name, std::string desc, index_mode mode, index_type itype);
+		virtual ~field_info();
 	};
 
 	// A struct describing a group of filtercheck fields ("ka")
 	struct check_info {
-		std::string name;
-		std::string desc;
+		std::string m_name;
+		std::string m_desc;
 
-		std::list<field_info> fields;
+		std::list<field_info> m_fields;
 	};
 
 	json_event_filter_check();
@@ -115,28 +136,12 @@ protected:
 	typedef std::function<std::string (const nlohmann::json &, std::string &field, std::string &idx)> format_t;
 
 	struct alias {
-
-		// Whether this alias requires an index, allows an
-		// index, or should not have an index.
-		enum index_mode {
-			IDX_REQUIRED,
-			IDX_ALLOWED,
-			IDX_NONE
-		};
-
-		enum index_type {
-			IDX_KEY,
-			IDX_NUMERIC
-		};
-
 		// The variants allow for brace-initialization either
 		// with just the pointer or with both the pointer and
 		// a format function.
 		alias();
 	        alias(nlohmann::json::json_pointer ptr);
 	        alias(nlohmann::json::json_pointer ptr, format_t format);
-	        alias(nlohmann::json::json_pointer ptr, format_t format, index_mode mode);
-	        alias(nlohmann::json::json_pointer ptr, format_t format, index_mode mode, index_type itype);
 		virtual ~alias();
 
 		// A json pointer used to extract a referenced value
@@ -149,10 +154,6 @@ protected:
 		// indexing, searches, etc.) or string reformatting to
 		// trim unnecessary parts of the value.
 		format_t m_format;
-
-		index_mode m_idx_mode;
-
-		index_type m_idx_type;
 	};
 
 	// This map defines the aliases defined by this filter check

userspace/engine/lua/compiler.lua

@@ -62,12 +62,12 @@ function expand_macros(ast, defs, changed)
    elseif ast.type == "Filter" then
       if (ast.value.type == "Macro") then
          if (defs[ast.value.value] == nil) then
-            error("Undefined macro '".. ast.value.value .. "' used in filter.")
+	    return false, "Undefined macro '".. ast.value.value .. "' used in filter."
          end
 	 defs[ast.value.value].used = true
          ast.value = copy_ast_obj(defs[ast.value.value].ast)
          changed = true
-	 return changed
+	 return true, changed
       end
       return expand_macros(ast.value, defs, changed)
 
@@ -75,7 +75,7 @@ function expand_macros(ast, defs, changed)
 
       if (ast.left.type == "Macro") then
          if (defs[ast.left.value] == nil) then
-            error("Undefined macro '".. ast.left.value .. "' used in filter.")
+	    return false, "Undefined macro '".. ast.left.value .. "' used in filter."
          end
 	 defs[ast.left.value].used = true
          ast.left = copy_ast_obj(defs[ast.left.value].ast)
@@ -84,21 +84,27 @@ function expand_macros(ast, defs, changed)
 
       if (ast.right.type == "Macro") then
          if (defs[ast.right.value] == nil) then
-            error("Undefined macro ".. ast.right.value .. " used in filter.")
+	    return false, "Undefined macro ".. ast.right.value .. " used in filter."
          end
 	 defs[ast.right.value].used = true
          ast.right = copy_ast_obj(defs[ast.right.value].ast)
          changed = true
       end
 
-      local changed_left = expand_macros(ast.left, defs, false)
-      local changed_right = expand_macros(ast.right, defs, false)
-      return changed or changed_left or changed_right
+      local status, changed_left = expand_macros(ast.left, defs, false)
+      if status == false then
+	 return false, changed_left
+      end
+      local status, changed_right = expand_macros(ast.right, defs, false)
+      if status == false then
+	 return false, changed_right
+      end
+      return true, changed or changed_left or changed_right
 
    elseif ast.type == "UnaryBoolOp" then
       if (ast.argument.type == "Macro") then
          if (defs[ast.argument.value] == nil) then
-            error("Undefined macro ".. ast.argument.value .. " used in filter.")
+	    return false, "Undefined macro ".. ast.argument.value .. " used in filter."
          end
 	 defs[ast.argument.value].used = true
          ast.argument = copy_ast_obj(defs[ast.argument.value].ast)
@@ -106,7 +112,7 @@ function expand_macros(ast, defs, changed)
       end
       return expand_macros(ast.argument, defs, changed)
    end
-   return changed
+   return true, changed
 end
 
 function get_macros(ast, set)
@@ -152,16 +158,35 @@ end
 function compiler.expand_lists_in(source, list_defs)
 
    for name, def in pairs(list_defs) do
-      local begin_name_pat = "^("..name..")([%s(),=])"
-      local mid_name_pat = "([%s(),=])("..name..")([%s(),=])"
-      local end_name_pat = "([%s(),=])("..name..")$"
 
-      source, subcount1 = string.gsub(source, begin_name_pat, table.concat(def.items, ", ").."%2")
-      source, subcount2 = string.gsub(source, mid_name_pat, "%1"..table.concat(def.items, ", ").."%3")
-      source, subcount3 = string.gsub(source, end_name_pat, "%1"..table.concat(def.items, ", "))
+      local bpos = string.find(source, name, 1, true)
 
-      if (subcount1 + subcount2 + subcount3) > 0 then
+      while bpos ~= nil do
 	 def.used = true
+
+	 local epos = bpos + string.len(name)
+
+	 -- The characters surrounding the name must be delimiters of beginning/end of string
+	 if (bpos == 1 or string.match(string.sub(source, bpos-1, bpos-1), "[%s(),=]")) and (epos > string.len(source) or string.match(string.sub(source, epos, epos), "[%s(),=]")) then
+	    new_source = ""
+
+	    if bpos > 1 then
+	       new_source = new_source..string.sub(source, 1, bpos-1)
+	    end
+
+	    sub = table.concat(def.items, ", ")
+
+	    new_source = new_source..sub
+
+	    if epos <= string.len(source) then
+	       new_source = new_source..string.sub(source, epos, string.len(source))
+	    end
+
+	    source = new_source
+	    bpos = bpos + (string.len(sub)-string.len(name))
+	 end
+
+	 bpos = string.find(source, name, bpos+1, true)
       end
    end
 
@@ -176,7 +201,7 @@ function compiler.compile_macro(line, macro_defs, list_defs)
 
    if (error_msg) then
       msg = "Compilation error when compiling \""..line.."\": ".. error_msg
-      error(msg)
+      return false, msg
    end
 
    -- Simply as a validation step, try to expand all macros in this
@@ -187,14 +212,18 @@ function compiler.compile_macro(line, macro_defs, list_defs)
    if (ast.type == "Rule") then
       -- Line is a filter, so expand macro references
       repeat
-	 expanded  = expand_macros(ast_copy, macro_defs, false)
+	 status, expanded = expand_macros(ast_copy, macro_defs, false)
+	 if status == false then
+	    msg = "Compilation error when compiling \""..line.."\": ".. expanded
+	    return false, msg
+	 end
       until expanded == false
 
    else
-      error("Unexpected top-level AST type: "..ast.type)
+      return false, "Unexpected top-level AST type: "..ast.type
    end
 
-   return ast
+   return true, ast
 end
 
 --[[
@@ -208,22 +237,25 @@ function compiler.compile_filter(name, source, macro_defs, list_defs)
 
    if (error_msg) then
       msg = "Compilation error when compiling \""..source.."\": "..error_msg
-      error(msg)
+      return false, msg
    end
 
    if (ast.type == "Rule") then
       -- Line is a filter, so expand macro references
       repeat
-	 expanded  = expand_macros(ast, macro_defs, false)
+	 status, expanded  = expand_macros(ast, macro_defs, false)
+	 if status == false then
+	    return false, expanded
+	 end
       until expanded == false
 
    else
-      error("Unexpected top-level AST type: "..ast.type)
+      return false, "Unexpected top-level AST type: "..ast.type
    end
 
    filters = get_filters(ast)
 
-   return ast, filters
+   return true, ast, filters
 end
 
 

userspace/engine/lua/parser.lua

@@ -152,22 +152,6 @@ local function rel (left, sep, right)
    return left * sep * right / function(e1, op, e2) return { type = "BinaryRelOp", operator = op, left = e1, right = e2 } end
 end
 
-local function fix_str (str)
-  str = string.gsub(str, "\\a", "\a")
-  str = string.gsub(str, "\\b", "\b")
-  str = string.gsub(str, "\\f", "\f")
-  str = string.gsub(str, "\\n", "\n")
-  str = string.gsub(str, "\\r", "\r")
-  str = string.gsub(str, "\\t", "\t")
-  str = string.gsub(str, "\\v", "\v")
-  str = string.gsub(str, "\\\n", "\n")
-  str = string.gsub(str, "\\\r", "\n")
-  str = string.gsub(str, "\\'", "'")
-  str = string.gsub(str, '\\"', '"')
-  str = string.gsub(str, '\\\\', '\\')
-  return str
-end
-
 -- grammar
 
 
@@ -243,7 +227,7 @@ local G = {
           (digit^1 * V"Expo");
   Number = C(V"Hex" + V"Float" + V"Int") /
            function (n) return tonumber(n) end;
-  String = (P'"' * C(((P'\\' * P(1)) + (P(1) - P'"'))^0) * P'"' +  P"'" * C(((P"\\" * P(1)) + (P(1) - P"'"))^0) * P"'")  / function (s) return fix_str(s) end;
+  String = (P'"' * C(((P'\\' * P(1)) + (P(1) - P'"'))^0) * P'"' +  P"'" * C(((P"\\" * P(1)) + (P(1) - P"'"))^0) * P"'");
   BareString = C(((P(1) - S' (),='))^1);
 
   OrOp = kw("or") / "or";

userspace/engine/lua/rule_loader.lua

@@ -59,17 +59,13 @@ 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
+-- Permissive for case and for common abbreviations.
+priorities = {
+   Emergency=0, Alert=1, Critical=2, Error=3, Warning=4, Notice=5, Informational=5, Debug=7,
+   EMERGENCY=0, ALERT=1, CRITICAL=2, ERROR=3, WARNING=4, NOTICE=5, INFORMATIONAL=5, DEBUG=7,
+   INFO=5
+}
 
 --[[
    Take a filter AST and set it up in the libsinsp runtime, using the filter API.
@@ -183,6 +179,71 @@ function table.tostring( tbl )
   return "{" .. table.concat( result, "," ) .. "}"
 end
 
+-- Split rules_content by lines and also remember the line numbers for
+-- each top -level object. Returns a table of lines and a table of
+-- line numbers for objects.
+
+function split_lines(rules_content)
+   lines = {}
+   indices = {}
+
+   idx = 1
+   last_pos = 1
+   pos = string.find(rules_content, "\n", 1, true)
+
+   while pos ~= nil do
+      line = string.sub(rules_content, last_pos, pos-1)
+      if line ~= "" then
+	 lines[#lines+1] = line
+	 if string.sub(line, 1, 1) == '-' then
+	    indices[#indices+1] = idx
+	 end
+
+	 idx = idx + 1
+      end
+
+      last_pos = pos+1
+      pos = string.find(rules_content, "\n", pos+1, true)
+   end
+
+   if last_pos < string.len(rules_content) then
+      line = string.sub(rules_content, last_pos)
+      lines[#lines+1] = line
+      if string.sub(line, 1, 1) == '-' then
+	 indices[#indices+1] = idx
+      end
+
+      idx = idx + 1
+   end
+
+   -- Add a final index for last line in document
+   indices[#indices+1] = idx
+
+   return lines, indices
+end
+
+function get_context(rules_lines, row, num_lines)
+
+   local ret = "---\n"
+
+   idx = row
+   while (idx < (row + num_lines) and idx <= #rules_lines) do
+      ret = ret..rules_lines[idx].."\n"
+      idx = idx + 1
+   end
+
+   ret = ret.."---"
+
+   return ret
+
+end
+
+function build_error(rules_lines, row, num_lines, err)
+
+   local ret = err.."\n"..get_context(rules_lines, row, num_lines)
+
+   return ret
+end
 
 function load_rules(sinsp_lua_parser,
 		    json_lua_parser,
@@ -194,16 +255,45 @@ function load_rules(sinsp_lua_parser,
 		    replace_container_info,
 		    min_priority)
 
-   local rules = yaml.load(rules_content)
    local required_engine_version = 0
 
+   local lines, indices = split_lines(rules_content)
+
+   local status, rules = pcall(yaml.load, rules_content)
+
+   if status == false then
+      local pat = "^([%d]+):([%d]+): "
+      -- rules is actually an error string
+
+      local row = 0
+      local col = 0
+
+      row, col = string.match(rules, pat)
+      if row ~= nil and col ~= nil then
+	 rules = string.gsub(rules, pat, "")
+      end
+
+      row = tonumber(row)
+      col = tonumber(col)
+
+      return false, build_error(lines, row, 3, rules)
+   end
+
    if rules == nil then
       -- An empty rules file is acceptable
-      return required_engine_version
+      return true, required_engine_version
    end
 
    if type(rules) ~= "table" then
-      error("Rules content \""..rules_content.."\" is not yaml")
+      return false, build_error(lines, 1, 1, "Rules content is not yaml")
+   end
+
+   -- Look for non-numeric indices--implies that document is not array
+   -- of objects.
+   for key, val in pairs(rules) do
+      if type(key) ~= "number" then
+	 return false, build_error(lines, 1, 1, "Rules content is not yaml array of objects")
+      end
    end
 
    -- Iterate over yaml list. In this pass, all we're doing is
@@ -213,17 +303,25 @@ function load_rules(sinsp_lua_parser,
    for i,v in ipairs(rules) do
 
       if (not (type(v) == "table")) then
-	 error ("Unexpected element of type " ..type(v)..". Each element should be a yaml associative array.")
+	 return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), "Unexpected element of type " ..type(v)..". Each element should be a yaml associative array.")
       end
 
       if (v['required_engine_version']) then
 	 required_engine_version = v['required_engine_version']
+	 if type(required_engine_version) ~= "number" then
+	    return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), "Value of required_engine_version must be a number")
+	 end
+
 	 if falco_rules.engine_version(rules_mgr) < v['required_engine_version'] then
-	    error("Rules require engine version "..v['required_engine_version']..", but engine version is "..falco_rules.engine_version(rules_mgr))
+	    return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), "Rules require engine version "..v['required_engine_version']..", but engine version is "..falco_rules.engine_version(rules_mgr))
 	 end
 
       elseif (v['macro']) then
 
+	 if (v['macro'] == nil or type(v['macro']) == "table") then
+	    return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), "Macro name is empty")
+	 end
+
 	 if v['source'] == nil then
 	    v['source'] = "syscall"
 	 end
@@ -232,9 +330,9 @@ function load_rules(sinsp_lua_parser,
 	    state.ordered_macro_names[#state.ordered_macro_names+1] = v['macro']
 	 end
 
-	 for i, field in ipairs({'condition'}) do
+	 for j, field in ipairs({'condition'}) do
 	    if (v[field] == nil) then
-	       error ("Missing "..field.." in macro with name "..v['macro'])
+	       return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), "Macro must have property "..field)
 	    end
 	 end
 
@@ -247,7 +345,7 @@ function load_rules(sinsp_lua_parser,
 
 	 if append then
 	    if state.macros_by_name[v['macro']] == nil then
-	       error ("Macro " ..v['macro'].. " has 'append' key but no macro by that name already exists")
+	       return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), "Macro " ..v['macro'].. " has 'append' key but no macro by that name already exists")
 	    end
 
 	    state.macros_by_name[v['macro']]['condition'] = state.macros_by_name[v['macro']]['condition'] .. " " .. v['condition']
@@ -258,13 +356,17 @@ function load_rules(sinsp_lua_parser,
 
       elseif (v['list']) then
 
+	 if (v['list'] == nil or type(v['list']) == "table") then
+	    return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), "List name is empty")
+	 end
+
 	 if state.lists_by_name[v['list']] == nil then
 	    state.ordered_list_names[#state.ordered_list_names+1] = v['list']
 	 end
 
-	 for i, field in ipairs({'items'}) do
+	 for j, field in ipairs({'items'}) do
 	    if (v[field] == nil) then
-	       error ("Missing "..field.." in list with name "..v['list'])
+	       return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), "List must have property "..field)
 	    end
 	 end
 
@@ -277,10 +379,10 @@ function load_rules(sinsp_lua_parser,
 
 	 if append then
 	    if state.lists_by_name[v['list']] == nil then
-	       error ("List " ..v['list'].. " has 'append' key but no list by that name already exists")
+	       return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), "List " ..v['list'].. " has 'append' key but no list by that name already exists")
 	    end
 
-	    for i, elem in ipairs(v['items']) do
+	    for j, elem in ipairs(v['items']) do
 	       table.insert(state.lists_by_name[v['list']]['items'], elem)
 	    end
 	 else
@@ -290,7 +392,7 @@ function load_rules(sinsp_lua_parser,
       elseif (v['rule']) then
 
 	 if (v['rule'] == nil or type(v['rule']) == "table") then
-	    error ("Missing name in rule")
+	    return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), "Rule name is empty")
 	 end
 
 	 -- By default, if a rule's condition refers to an unknown
@@ -313,15 +415,15 @@ function load_rules(sinsp_lua_parser,
 	 if append then
 
 	    -- For append rules, all you need is the condition
-	    for i, field in ipairs({'condition'}) do
+	    for j, field in ipairs({'condition'}) do
 	       if (v[field] == nil) then
-		  error ("Missing "..field.." in rule with name "..v['rule'])
+		  return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), "Rule must have property "..field)
 	       end
 	    end
 
 	    if state.rules_by_name[v['rule']] == nil then
 	       if state.skipped_rules_by_name[v['rule']] == nil then
-		  error ("Rule " ..v['rule'].. " has 'append' key but no rule by that name already exists")
+		  return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), "Rule " ..v['rule'].. " has 'append' key but no rule by that name already exists")
 	       end
 	    else
 	       state.rules_by_name[v['rule']]['condition'] = state.rules_by_name[v['rule']]['condition'] .. " " .. v['condition']
@@ -329,14 +431,18 @@ function load_rules(sinsp_lua_parser,
 
 	 else
 
-	    for i, field in ipairs({'condition', 'output', 'desc', 'priority'}) do
+	    for j, field in ipairs({'condition', 'output', 'desc', 'priority'}) do
 	       if (v[field] == nil) then
-		  error ("Missing "..field.." in rule with name "..v['rule'])
+		  return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), "Rule must have property "..field)
 	       end
 	    end
 
 	    -- Convert the priority-as-string to a priority-as-number now
-	    v['priority_num'] = priority_num_for(v['priority'])
+	    v['priority_num'] = priorities[v['priority']]
+
+	    if v['priority_num'] == nil then
+	       error("Invalid priority level: "..v['priority'])
+	    end
 
 	    if v['priority_num'] <= min_priority then
 	       -- Note that we can overwrite rules, but the rules are still
@@ -356,7 +462,7 @@ function load_rules(sinsp_lua_parser,
 	    end
 	 end
       else
-	 error ("Unknown rule object: "..table.tostring(v))
+	 return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), "Unknown rule object: "..table.tostring(v))
       end
    end
 
@@ -393,7 +499,11 @@ function load_rules(sinsp_lua_parser,
 
       local v = state.macros_by_name[name]
 
-      local ast = compiler.compile_macro(v['condition'], state.macros, state.lists)
+      local status, ast = compiler.compile_macro(v['condition'], state.macros, state.lists)
+
+      if status == false then
+	 return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), ast)
+      end
 
       if v['source'] == "syscall" then
 	 if not all_events then
@@ -413,8 +523,12 @@ function load_rules(sinsp_lua_parser,
 	 warn_evttypes = v['warn_evttypes']
       end
 
-      local filter_ast, filters = compiler.compile_filter(v['rule'], v['condition'],
-							  state.macros, state.lists)
+      local status, filter_ast, filters = compiler.compile_filter(v['rule'], v['condition'],
+								  state.macros, state.lists)
+
+      if status == false then
+	 return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), filter_ast)
+      end
 
       local evtttypes = {}
       local syscallnums = {}
@@ -433,10 +547,32 @@ function load_rules(sinsp_lua_parser,
       for filter, _ in pairs(filters) do
 	 found = false
 
-	 for pat, _ in pairs(defined_filters) do
-	    if string.match(filter, pat) ~= nil then
-	       found = true
-	       break
+	 if defined_noarg_filters[filter] ~= nil then
+	    found = true
+	 else
+	    bracket_idx = string.find(filter, "[", 1, true)
+
+	    if bracket_idx ~= nil then
+	       subfilter = string.sub(filter, 1, bracket_idx-1)
+
+	       if defined_arg_filters[subfilter] ~= nil then
+		  found = true
+	       end
+	    end
+
+	    if not found then
+	       dot_idx = string.find(filter, ".", 1, true)
+
+	       while dot_idx ~= nil do
+		  subfilter = string.sub(filter, 1, dot_idx-1)
+
+		  if defined_arg_filters[subfilter] ~= nil then
+		     found = true
+		     break
+		  end
+
+		  dot_idx = string.find(filter, ".", dot_idx+1, true)
+	       end
 	    end
 	 end
 
@@ -529,7 +665,7 @@ function load_rules(sinsp_lua_parser,
 	 formatter = formats.formatter(v['source'], v['output'])
 	 formats.free_formatter(v['source'], formatter)
       else
-	 error ("Unexpected type in load_rule: "..filter_ast.type)
+	 return false, build_error(lines, indices[i], (indices[i+1]-indices[i]), "Unexpected type in load_rule: "..filter_ast.type)
       end
 
       ::next_rule::
@@ -552,7 +688,7 @@ function load_rules(sinsp_lua_parser,
 
    io.flush()
 
-   return required_engine_version
+   return true, required_engine_version
 end
 
 local rule_fmt = "%-50s %s"

userspace/engine/rules.cpp

@@ -323,12 +323,12 @@ void falco_rules::load_rules(const string &rules_content,
 
 		lua_setglobal(m_ls, m_lua_ignored_syscalls.c_str());
 
-		// Create a table containing all filtercheck names.
-		lua_newtable(m_ls);
-
 		vector<const filter_check_info*> fc_plugins;
 		sinsp::get_filtercheck_fields_info(&fc_plugins);
 
+		set<string> no_argument_filters;
+		set<string> argument_filters;
+
 		for(uint32_t j = 0; j < fc_plugins.size(); j++)
 		{
 			const filter_check_info* fci = fc_plugins[j];
@@ -350,45 +350,71 @@ void falco_rules::load_rules(const string &rules_content,
 
 				// Some filters can work with or without an argument
 				std::set<string> flexible_filters = {
-					"^proc.aname",
-					"^proc.apid"
+					"proc.aname",
+					"proc.apid"
 				};
 
-				std::list<string> fields;
-				std::string field_base = string("^") + fld->m_name;
-
 				if(fld->m_flags & EPF_REQUIRES_ARGUMENT ||
-				   flexible_filters.find(field_base) != flexible_filters.end())
+				   flexible_filters.find(fld->m_name) != flexible_filters.end())
 				{
-					fields.push_back(field_base + "[%[%.]");
+					argument_filters.insert(fld->m_name);
 				}
 
 				if(!(fld->m_flags & EPF_REQUIRES_ARGUMENT) ||
-				   flexible_filters.find(field_base) != flexible_filters.end())
+				   flexible_filters.find(fld->m_name) != flexible_filters.end())
 				{
-					fields.push_back(field_base + "$");
-				}
-
-				for(auto &field : fields)
-				{
-					lua_pushstring(m_ls, field.c_str());
-					lua_pushnumber(m_ls, 1);
-					lua_settable(m_ls, -3);
+					no_argument_filters.insert(fld->m_name);
 				}
 			}
 		}
 
 		for(auto &chk_field : m_engine->json_factory().get_fields())
 		{
-			for(auto &field : chk_field.fields)
+			for(auto &field : chk_field.m_fields)
 			{
-				lua_pushstring(m_ls, field.name.c_str());
-				lua_pushnumber(m_ls, 1);
-				lua_settable(m_ls, -3);
+				switch(field.m_idx_mode)
+				{
+				case json_event_filter_check::IDX_REQUIRED:
+					argument_filters.insert(field.m_name);
+					break;
+				case json_event_filter_check::IDX_ALLOWED:
+					argument_filters.insert(field.m_name);
+					no_argument_filters.insert(field.m_name);
+					break;
+				case json_event_filter_check::IDX_NONE:
+					no_argument_filters.insert(field.m_name);
+					break;
+				default:
+					break;
+				}
 			}
 		}
 
-		lua_setglobal(m_ls, m_lua_defined_filters.c_str());
+		// Create tables containing all filtercheck
+		// names. They are split into names that require
+		// arguments and ones that do not.
+
+		lua_newtable(m_ls);
+
+		for(auto &field : argument_filters)
+		{
+			lua_pushstring(m_ls, field.c_str());
+			lua_pushnumber(m_ls, 1);
+			lua_settable(m_ls, -3);
+		}
+
+		lua_setglobal(m_ls, m_lua_defined_arg_filters.c_str());
+
+		lua_newtable(m_ls);
+
+		for(auto &field : no_argument_filters)
+		{
+			lua_pushstring(m_ls, field.c_str());
+			lua_pushnumber(m_ls, 1);
+			lua_settable(m_ls, -3);
+		}
+
+		lua_setglobal(m_ls, m_lua_defined_noarg_filters.c_str());
 
 		lua_pushlightuserdata(m_ls, m_sinsp_lua_parser);
 		lua_pushlightuserdata(m_ls, m_json_lua_parser);
@@ -399,15 +425,30 @@ void falco_rules::load_rules(const string &rules_content,
 		lua_pushstring(m_ls, extra.c_str());
 		lua_pushboolean(m_ls, (replace_container_info ? 1 : 0));
 		lua_pushnumber(m_ls, min_priority);
-		if(lua_pcall(m_ls, 9, 1, 0) != 0)
+		if(lua_pcall(m_ls, 9, 2, 0) != 0)
 		{
 			const char* lerr = lua_tostring(m_ls, -1);
+
 			string err = "Error loading rules: " + string(lerr);
+
 			throw falco_exception(err);
 		}
 
-		required_engine_version = lua_tonumber(m_ls, -1);
-		lua_pop(m_ls, 1);
+		// Either returns (true, required_engine_version), or (false, error string)
+		bool successful = lua_toboolean(m_ls, -2);
+
+		if(successful)
+		{
+			required_engine_version = lua_tonumber(m_ls, -1);
+		}
+		else
+		{
+			std::string err = lua_tostring(m_ls, -1);
+			throw falco_exception(err);
+		}
+
+		lua_pop(m_ls, 4);
+
 	} else {
 		throw falco_exception("No function " + m_lua_load_rules + " found in lua rule module");
 	}

userspace/engine/rules.h

@@ -67,7 +67,8 @@ class falco_rules
 	string m_lua_load_rules = "load_rules";
 	string m_lua_ignored_syscalls = "ignored_syscalls";
 	string m_lua_ignored_events = "ignored_events";
-	string m_lua_defined_filters = "defined_filters";
+	string m_lua_defined_arg_filters = "defined_arg_filters";
+	string m_lua_defined_noarg_filters = "defined_noarg_filters";
 	string m_lua_events = "events";
 	string m_lua_syscalls = "syscalls";
 	string m_lua_describe_rule = "describe_rule";

userspace/engine/token_bucket.cpp

@@ -18,13 +18,20 @@ limitations under the License.
 */
 
 #include <cstddef>
+#include <functional>
 #include <sys/time.h>
 
-#include "utils.h"
 #include "token_bucket.h"
+#include "utils.h"
 
-token_bucket::token_bucket()
+token_bucket::token_bucket():
+	token_bucket(sinsp_utils::get_current_time_ns)
 {
+}
+
+token_bucket::token_bucket(std::function<uint64_t()> timer)
+{
+	m_timer = timer;
 	init(1, 1);
 }
 
@@ -37,20 +44,12 @@ void token_bucket::init(double rate, double max_tokens, uint64_t now)
 	m_rate = rate;
 	m_max_tokens = max_tokens;
 	m_tokens = max_tokens;
-
-	if(now == 0)
-	{
-		now = sinsp_utils::get_current_time_ns();
-	}
-
-	m_last_seen = now;
+	m_last_seen = now == 0 ? m_timer() : now;
 }
 
 bool token_bucket::claim()
 {
-	uint64_t now = sinsp_utils::get_current_time_ns();
-
-	return claim(1, now);
+	return claim(1, m_timer());
 }
 
 bool token_bucket::claim(double tokens, uint64_t now)

userspace/engine/token_bucket.h

@@ -20,6 +20,7 @@ limitations under the License.
 #pragma once
 
 #include <cstdint>
+#include <functional>
 
 // A simple token bucket that accumulates tokens at a fixed rate and allows
 // for limited bursting in the form of "banked" tokens.
@@ -27,6 +28,7 @@ class token_bucket
 {
 public:
 	token_bucket();
+	token_bucket(std::function<uint64_t()> timer);
 	virtual ~token_bucket();
 
 	//
@@ -52,6 +54,7 @@ public:
 	uint64_t get_last_seen();
 
 private:
+	std::function<uint64_t()> m_timer;
 
 	//
 	// The number of tokens generated per second.
@@ -75,4 +78,3 @@ private:
 	//
 	uint64_t m_last_seen;
 };
-

userspace/falco/CMakeLists.txt

@@ -15,23 +15,11 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 #
-include_directories("${PROJECT_SOURCE_DIR}/../sysdig/userspace/libsinsp/third-party/jsoncpp")
-include_directories("${LUAJIT_INCLUDE}")
+if(NOT SYSDIG_DIR)
+	set(SYSDIG_DIR "${PROJECT_SOURCE_DIR}/../sysdig")
+endif()
 
-include_directories("${PROJECT_SOURCE_DIR}/../sysdig/userspace/libscap")
-include_directories("${PROJECT_SOURCE_DIR}/../sysdig/userspace/libsinsp")
-include_directories("${PROJECT_SOURCE_DIR}/../sysdig/userspace/sysdig")
-include_directories("${PROJECT_SOURCE_DIR}/userspace/engine")
-include_directories("${PROJECT_BINARY_DIR}/userspace/falco")
-include_directories("${PROJECT_BINARY_DIR}/driver/src")
-include_directories("${CURL_INCLUDE_DIR}")
-include_directories("${TBB_INCLUDE_DIR}")
-include_directories("${NJSON_INCLUDE}")
-include_directories("${YAMLCPP_INCLUDE_DIR}")
-include_directories("${CIVETWEB_INCLUDE_DIR}")
-include_directories("${DRAIOS_DEPENDENCIES_DIR}/yaml-${DRAIOS_YAML_VERSION}/target/include")
-
-configure_file("${PROJECT_SOURCE_DIR}/../sysdig/userspace/sysdig/config_sysdig.h.in" config_sysdig.h)
+configure_file("${SYSDIG_DIR}/userspace/sysdig/config_sysdig.h.in" config_sysdig.h)
 
 add_executable(falco
 	configuration.cpp
@@ -40,12 +28,21 @@ add_executable(falco
 	event_drops.cpp
 	statsfilewriter.cpp
 	falco.cpp
-	"${PROJECT_SOURCE_DIR}/../sysdig/userspace/sysdig/fields_info.cpp"
+	"${SYSDIG_DIR}/userspace/sysdig/fields_info.cpp"
 	webserver.cpp)
 
+target_include_directories(falco PUBLIC
+	"${SYSDIG_DIR}/userspace/sysdig"
+	"${PROJECT_SOURCE_DIR}/userspace/engine"
+	"${PROJECT_BINARY_DIR}/userspace/falco"
+	"${PROJECT_BINARY_DIR}/driver/src"
+	"${YAMLCPP_INCLUDE_DIR}"
+	"${CIVETWEB_INCLUDE_DIR}"
+	"${DRAIOS_DEPENDENCIES_DIR}/yaml-${DRAIOS_YAML_VERSION}/target/include")
+
 target_link_libraries(falco falco_engine sinsp)
 target_link_libraries(falco
-        "${LIBYAML_LIB}"
+	"${LIBYAML_LIB}"
 	"${YAMLCPP_LIB}"
 	"${CIVETWEB_LIB}")
 

userspace/falco/falco.cpp

@@ -716,7 +716,17 @@ int falco_init(int argc, char **argv)
 			}
 			for(auto file : validate_rules_filenames)
 			{
-				engine->load_rules_file(file, verbose, all_events);
+				// Only include the prefix if there is more than one file
+				std::string prefix = (validate_rules_filenames.size() > 1 ? file + ": " : "");
+				try {
+					engine->load_rules_file(file, verbose, all_events);
+				}
+				catch(falco_exception &e)
+				{
+					printf("%s%s\n", prefix.c_str(), e.what());
+					throw;
+				}
+				printf("%sOk\n", prefix.c_str());
 			}
 			falco_logger::log(LOG_INFO, "Ok\n");
 			goto exit;