tools: add sbom information for submodules

Conflicts:
- protobuf-c submodule version and hash changed to v1.4.0
- removed pytest dependency

This adds SBOM information for submodules, which are not managed
by Espressif. Meaning there is no fork for them in the espressif
namespace. Other submodules should add sbom.yml manifest file to
the root of their git repository.

The SBOM information for submodules is stored in the .gitmodules file.
Each SBOM related variable has the "sbom-" prefix and the following
variables may be used:

sbom-version:
   submodule version

sbom-cpe:
   CPE record if available in NVD. This will be used by the SBOM
   tool to check for possible submodule vulnerabilities. The
   version in the CPE can be replaced with the "{}" placeholder,
   which will be replaced by the "sbom-version" value from above.

sbom-supplier:
   Person or organization who is providing the submodule.
   It has to start with "Person:" or "Organization:" prefix
   as required by the SPDX-2.2 standard.

sbom-url:
   URL to the project if exists, e.g. github.

sbom-description:
   Project description.

sbom-hash:
   Submodule SHA as recorded in the git-tree. This field is used by
   CI to check that the submodule checkout hash and info in .gitmodules
   are in sync. IOW if submodule is updated and it has SBOM info in
   .gitmodules, the .gitmodules has to be updated too. The test is
   part of this commit. The checkout has of the submodule can be found
   by using "git submodule status".

Example for micro-ecc submodule
---8<---
[submodule "components/bootloader/subproject/components/micro-ecc/micro-ecc"]
	path = components/bootloader/subproject/components/micro-ecc/micro-ecc
	url = ../../kmackay/micro-ecc.git
	sbom-version = 1.0
	sbom-cpe = cpe:2.3🅰️micro-ecc_project:micro-ecc:{}:*:*:*:*:*:*:*
	sbom-supplier = Person: Ken MacKay
	sbom-url = https://github.com/kmackay/micro-ecc
	sbom-description = A small and fast ECDH and ECDSA implementation for 8-bit, 32-bit, and 64-bit processors
	sbom-hash = d037ec89546fad14b5c4d5456c2e23a71e554966
---8<---

Signed-off-by: Frantisek Hrbata <frantisek.hrbata@espressif.com>

.gitlab/ci/host-test.yml

@@ -273,6 +273,13 @@ test_mkuf2:
     - cd ${IDF_PATH}/tools/test_mkuf2
     - ./test_mkuf2.py
 
+test_sbom:
+  extends:
+    - .host_test_template
+    - .rules:patterns:sbom
+  script:
+    - python ${IDF_PATH}/tools/test_sbom/test_submodules.py
+
 test_autocomplete:
   extends: .host_test_template
   image: $CI_DOCKER_REGISTRY/linux-shells:1

.gitlab/ci/rules.yml

@@ -48,6 +48,9 @@
   - "tools/tools.json"
   - "tools/ci/test_build_system*.sh"
 
+.patterns-sbom: &patterns-sbom
+  - "tools/test_sbom/*"
+
 .patterns-custom_test: &patterns-custom_test
   - "tools/ci/python_packages/gitlab_api.py"
   - "tools/ci/python_packages/tiny_test_fw/**/*"
@@ -256,6 +259,14 @@
     - <<: *if-dev-push
       changes: *patterns-sonarqube-files
 
+.rules:patterns:sbom:
+  rules:
+    - <<: *if-protected
+    - <<: *if-dev-push
+      changes: *patterns-sbom
+    - <<: *if-dev-push
+      changes: *patterns-submodule
+
 # !!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
 # DO NOT place comments or maintain any code from this line
 #

.gitmodules

@@ -2,6 +2,26 @@
 # All the relative URL paths are intended to be GitHub ones
 # For Espressif's public projects please use '../../espressif/proj', not a '../proj'
 #
+# Submodules SBOM information
+# ---------------------------
+# Submodules, which are used directly and not forked into espressif namespace should
+# contain SBOM information here. Other submodules should have the SBOM manifest file
+# included in the root of their project's repository.
+#
+# The sbom-hash entry records the submodule's checkout SHA as presented in git-tree
+# commit object. For example spiffs submodule
+#
+# $ git ls-tree HEAD components/spiffs/spiffs
+# 160000 commit 0dbb3f71c5f6fae3747a9d935372773762baf852	components/spiffs/spiffs
+#
+# The hash can be also obtained with git submodule command
+#
+# $ git submodule status components/spiffs/spiffs
+# 0dbb3f71c5f6fae3747a9d935372773762baf852 components/spiffs/spiffs (0.2-255-g0dbb3f71c5f6)
+#
+# The submodule SHA recorded here has to match with SHA, which is presented in git-tree.
+# This is checked by CI. Also please don't forget to update the submodule version
+# if you are changing the sbom-hash. This is important for SBOM generation.
 
 [submodule "components/esptool_py/esptool"]
 	path = components/esptool_py/esptool
@@ -14,6 +34,12 @@
 [submodule "components/bootloader/subproject/components/micro-ecc/micro-ecc"]
 	path = components/bootloader/subproject/components/micro-ecc/micro-ecc
 	url = ../../kmackay/micro-ecc.git
+	sbom-version = 1.0
+	sbom-cpe = cpe:2.3:a:micro-ecc_project:micro-ecc:{}:*:*:*:*:*:*:*
+	sbom-supplier = Person: Ken MacKay
+	sbom-url = https://github.com/kmackay/micro-ecc
+	sbom-description = A small and fast ECDH and ECDSA implementation for 8-bit, 32-bit, and 64-bit processors
+	sbom-hash = d037ec89546fad14b5c4d5456c2e23a71e554966
 
 [submodule "components/coap/libcoap"]
 	path = components/coap/libcoap
@@ -30,10 +56,21 @@
 [submodule "components/spiffs/spiffs"]
 	path = components/spiffs/spiffs
 	url = ../../pellepl/spiffs.git
+	sbom-version = 0.2-255-g0dbb3f71c5f6
+	sbom-supplier = Person: Peter Andersson
+	sbom-url = https://github.com/pellepl/spiffs
+	sbom-description = Wear-leveled SPI flash file system for embedded devices
+	sbom-hash = 0dbb3f71c5f6fae3747a9d935372773762baf852
 
 [submodule "components/json/cJSON"]
 	path = components/json/cJSON
 	url = ../../DaveGamble/cJSON.git
+	sbom-version = 1.7.15
+	sbom-cpe = cpe:2.3:a:cjson_project:cjson:{}:*:*:*:*:*:*:*
+	sbom-supplier = Person: Dave Gamble
+	sbom-url = https://github.com/DaveGamble/cJSON
+	sbom-description = Ultralightweight JSON parser in ANSI C
+	sbom-hash = d348621ca93571343a56862df7de4ff3bc9b5667
 
 [submodule "components/mbedtls/mbedtls"]
 	path = components/mbedtls/mbedtls
@@ -58,10 +95,21 @@
 [submodule "components/protobuf-c/protobuf-c"]
 	path = components/protobuf-c/protobuf-c
 	url = ../../protobuf-c/protobuf-c.git
+	sbom-version = 1.4.0
+	sbom-cpe = cpe:2.3:a:protobuf-c_project:protobuf-c:{}:*:*:*:*:*:*:*
+	sbom-supplier = Organization: protobuf-c community <https://groups.google.com/g/protobuf-c>
+	sbom-url = https://github.com/protobuf-c/protobuf-c
+	sbom-description = Protocol Buffers implementation in C
+	sbom-hash = f224ab2eeb648a818eb20687d7150a285442c907
 
 [submodule "components/unity/unity"]
 	path = components/unity/unity
 	url = ../../ThrowTheSwitch/Unity.git
+	sbom-version = v2.4.3-51-g7d2bf62b7e6a
+	sbom-supplier = Organization: ThrowTheSwitch community <http://www.throwtheswitch.org>
+	sbom-url = https://github.com/ThrowTheSwitch/Unity
+	sbom-description = Simple Unit Testing for C
+	sbom-hash = 7d2bf62b7e6afaf38153041a9d53c21aeeca9a25
 
 [submodule "examples/build_system/cmake/import_lib/main/lib/tinyxml2"]
 	path = examples/build_system/cmake/import_lib/main/lib/tinyxml2
@@ -90,6 +138,11 @@
 [submodule "components/cmock/CMock"]
 	path = components/cmock/CMock
 	url = ../../ThrowTheSwitch/CMock.git
+	sbom-version = v2.5.2-2-geeecc49ce8af
+	sbom-supplier = Organization: ThrowTheSwitch community <http://www.throwtheswitch.org>
+	sbom-url = https://github.com/ThrowTheSwitch/CMock
+	sbom-description = CMock - Mock/stub generator for C
+	sbom-hash = eeecc49ce8af123cf8ad40efdb9673e37b56230f
 
 [submodule "components/openthread/openthread"]
 	path = components/openthread/openthread

tools/test_sbom/test_submodules.py

@@ -0,0 +1,73 @@
+# SPDX-FileCopyrightText: 2023 Espressif Systems (Shanghai) CO LTD
+# SPDX-License-Identifier: Apache-2.0
+import os
+from subprocess import PIPE, run
+from typing import Dict, List
+
+
+def run_cmd(cmd: List[str]) -> str:
+    """Simple helper to run command and return it's stdout."""
+    proc = run(cmd, stdout=PIPE, stderr=PIPE, check=True, universal_newlines=True)
+    return proc.stdout.strip()
+
+
+def get_gitwdir() -> str:
+    """Return absolute path to the current git working tree."""
+    return run_cmd(['git', 'rev-parse', '--show-toplevel'])
+
+
+def get_submodules_info() -> List[Dict[str,str]]:
+    """Return list of submodules, where each submodule is represented
+    as dictionary with name, path and hash keys."""
+    cmd = ['git', 'submodule', '--quiet', 'foreach','echo "$name,$sm_path,$sha1"']
+    out = run_cmd(cmd)
+    submodules = []
+    for line in out.splitlines():
+        name, sm_path, sha1 = line.split(',')
+        submodules += [{'name': name, 'path': sm_path, 'hash': sha1}]
+
+    return submodules
+
+
+def get_submodules_config() -> Dict[str,str]:
+    """Return dictionary, where key is variable name and value
+    is variable value in git's --list(dot) format. Only variables
+    starting with "submodule." are returned and this prefix is removed
+    to make it simple to match against the submodule info dictionary."""
+    gitmodules_fn = os.path.join(get_gitwdir(), '.gitmodules')
+    gitmodules_data = run_cmd(['git', 'config', '--list', '--file', gitmodules_fn])
+    prefix = 'submodule.'
+    config = {}
+    for line in gitmodules_data.splitlines():
+        var, val = line.split('=', maxsplit=1)
+        if not var.startswith(prefix):
+            continue
+        # remove "submodule." prefix
+        var = var[len(prefix):]
+        config[var] = val
+
+    return config
+
+
+def test_sha() -> None:
+    """ Check that submodule SHA1 in git-tree and .gitmodules match
+    if sbom-hash variable is available in the .gitmodules file.
+    """
+    submodules = get_submodules_info()
+    config = get_submodules_config()
+
+    for submodule in submodules:
+        sbom_hash = config.get(submodule['name'] + '.sbom-hash')
+        if not sbom_hash:
+            continue
+        msg = (f'Submodule \"{submodule["name"]}\" SHA \"{submodule["hash"]}\" in git '
+               f'tree does not match SHA \"{sbom_hash}\" recorded in .gitmodules. '
+               f'Please update \"sbom-hash\" in .gitmodules for \"{submodule["name"]}\" '
+               f'and also please do not forget to update version and other submodule '
+               f'information if necessary. It is important to keep this information '
+               f'up-to-date for SBOM generation.')
+        assert submodule['hash'] == sbom_hash, msg
+
+
+if __name__ == '__main__':
+    test_sha()