[PATCH v2 6/6] spdx: add option to include only compiled kernel files

[<daniel.turull@ericsson.com>]

From: Daniel Turull <daniel.turull@ericsson.com>

When CVE_CHECK_KERNEL_CONFIG is enabled, only include the
source code (.c, .h) files that are used during compilation.

This enables an external tool to use the SPDX information to disregard
vulnerabilities that are not compiled.

CC: Joshua Watt <JPEWhacker@gmail.com>
CC: Peter Marko <peter.marko@siemens.com>
Signed-off-by: Daniel Turull <daniel.turull@ericsson.com>
---
 meta/classes/create-spdx-2.2.bbclass |  8 +++++++
 meta/lib/oe/spdx30_tasks.py          |  8 +++++++
 meta/lib/oe/spdx_common.py           | 34 ++++++++++++++++++++++++++++
 3 files changed, 50 insertions(+)

diff --git a/meta/classes/create-spdx-2.2.bbclass b/meta/classes/create-spdx-2.2.bbclass
index 7e8f8b9ff5..6bf0c70bd4 100644
--- a/meta/classes/create-spdx-2.2.bbclass
+++ b/meta/classes/create-spdx-2.2.bbclass
@@ -137,6 +137,10 @@ def add_package_files(d, doc, spdx_pkg, topdir, get_spdxid, get_types, *, archiv
     spdx_files = []
 
     file_counter = 1
+
+    check_kernel_compiled = bb.data.inherits_class("kernel", d) and d.getVar("CVE_CHECK_KERNEL_CONFIG") == "1"
+    if check_kernel_compiled:
+        kernel_sources = oe.spdx_common.get_kernel_compiled_files(d)
     for subdir, dirs, files in os.walk(topdir):
         dirs[:] = [d for d in dirs if d not in ignore_dirs]
         if subdir == str(topdir):
@@ -147,6 +151,10 @@ def add_package_files(d, doc, spdx_pkg, topdir, get_spdxid, get_types, *, archiv
             filename = str(filepath.relative_to(topdir))
 
             if not filepath.is_symlink() and filepath.is_file():
+                # When creating spdx for the kernel, we only include compiled files.
+                if check_kernel_compiled:
+                     if not oe.spdx_common.is_kernel_compiled(file, kernel_sources, d):
+                          break
                 spdx_file = oe.spdx.SPDXFile()
                 spdx_file.SPDXID = get_spdxid(file_counter)
                 for t in get_types(filepath):
diff --git a/meta/lib/oe/spdx30_tasks.py b/meta/lib/oe/spdx30_tasks.py
index ba965821f8..14f26773c5 100644
--- a/meta/lib/oe/spdx30_tasks.py
+++ b/meta/lib/oe/spdx30_tasks.py
@@ -156,6 +156,10 @@ def add_package_files(
         bb.note(f"Skip {topdir}")
         return spdx_files
 
+    check_kernel_compiled = bb.data.inherits_class("kernel", d) and d.getVar("CVE_CHECK_KERNEL_CONFIG") == "1"
+    if check_kernel_compiled:
+        kernel_sources = oe.spdx_common.get_kernel_compiled_files(d)
+
     for subdir, dirs, files in os.walk(topdir, onerror=walk_error):
         dirs[:] = [d for d in dirs if d not in ignore_dirs]
         if subdir == str(topdir):
@@ -167,6 +171,10 @@ def add_package_files(
             filepath = Path(subdir) / file
             if filepath.is_symlink() or not filepath.is_file():
                 continue
+            # When creating spdx for the kernel, we only include compiled files
+            if check_kernel_compiled:
+                 if not oe.spdx_common.is_kernel_compiled(file, kernel_sources, d):
+                      break
 
             filename = str(filepath.relative_to(topdir))
             file_purposes = get_purposes(filepath)
diff --git a/meta/lib/oe/spdx_common.py b/meta/lib/oe/spdx_common.py
index 4caefc7673..c87e3875c7 100644
--- a/meta/lib/oe/spdx_common.py
+++ b/meta/lib/oe/spdx_common.py
@@ -242,3 +242,37 @@ def fetch_data_to_uri(fd, name):
         uri = uri + "@" + fd.revision
 
     return uri
+
+def is_kernel_compiled(filename, kernel_sources, d):
+    """
+    Check if the file, is a kernel compiled file
+    """
+    import os
+
+    _, extension = os.path.splitext(filename)
+    # Special case, that we need to ignore, since this is not a source file
+    if filename.rfind(".mod.c") > 0:
+        return True
+    # We filter .c files and header files
+    if extension not in [".c", ".h"]:
+        return True
+    # Check that the c file is in the list
+    if filename in kernel_sources:
+        return True
+    return False
+
+def get_kernel_compiled_files(d):
+    """
+    Get results from the save_compiled files and include also header files
+    """
+    import json
+    import os
+    kfiles = []
+    with open(d.getVar('KERNEL_SRC_FILES'), 'r') as f:
+        for item in json.load(f):
+            kfile = os.path.basename(item['file'])
+            # Return also the correspondig header file
+            hfile = ".h".join(kfile.rsplit(".c", 1))
+            kfiles.append(kfile)
+            kfiles.append(hfile)
+    return kfiles