From patchwork Fri May 31 13:01:26 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Marta Rybczynska X-Patchwork-Id: 44467 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from aws-us-west-2-korg-lkml-1.web.codeaurora.org (localhost.localdomain [127.0.0.1]) by smtp.lore.kernel.org (Postfix) with ESMTP id 863E9C25B7E for ; Fri, 31 May 2024 13:01:56 +0000 (UTC) Received: from mail-wm1-f50.google.com (mail-wm1-f50.google.com [209.85.128.50]) by mx.groups.io with SMTP id smtpd.web10.11231.1717160513278087009 for ; Fri, 31 May 2024 06:01:53 -0700 Authentication-Results: mx.groups.io; dkim=pass header.i=@gmail.com header.s=20230601 header.b=I0Qa4cSg; spf=pass (domain: gmail.com, ip: 209.85.128.50, mailfrom: rybczynska@gmail.com) Received: by mail-wm1-f50.google.com with SMTP id 5b1f17b1804b1-42125bfa28fso25723625e9.1 for ; Fri, 31 May 2024 06:01:53 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1717160511; x=1717765311; darn=lists.openembedded.org; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:from:to:cc:subject:date:message-id:reply-to; bh=iClhLgRmb25v4ePlqUp5SXqZQ4ZkyCuMz9K/oG4Cjnk=; b=I0Qa4cSgbJ7QbDgvH2vs+rcU15zbORaH6mbuw0RRc6rgiKRSGUxHlWLW9WRuyk/d7u gRbeDkCXiZdUIvFKPineSOW6xUPc9w3NYJ28aY75Ws/d+Vl8XzQcstq+pLYrQKx4j4hF +bQZDcxWLI50Lk9ood8tycVtegaGO2yfi9tI4RvWRgJ4i5aVD19XLm4gXKjRal97GzHV a56qELExSR70m6Pz/wtC6Qf4pOebxQeRsHM4KPkiKjp9wtqan/l5P2nBFuPeb6iyx38S F31Y8HW+guMgHKN0YkwBx6wykPTwN0QTOQ5fzdB6rsp8SElb+hRHvQOJQCdqFAfnSYkv +sWw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1717160511; x=1717765311; h=content-transfer-encoding:mime-version:message-id:date:subject:cc :to:from:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=iClhLgRmb25v4ePlqUp5SXqZQ4ZkyCuMz9K/oG4Cjnk=; b=toPLCRJdxEqaxLeFNh0Fg/En+V64AgTo8Mlt1yJsWxHBf1QShK1JiMxhXKWBNU65RL pPBTxuarX9RjGql7P/GGsbUS/+XuUK+4K/G1nsY2UMvNLwz74CzuItg1EDiQqcBsAKaQ uz1HbrL+ApdLEZ9xuxs97hFQaDcDl7uj/C+RViJlx2u9KyAtzVJG2I3qZ1tU26YCDbA6 xbC42J8HqKT8QqA0g3Q+aXrlKfTO/3t/mNLUs6rZvaRlgPo6QjH8+LW1Q90WoMij+QpZ O2D117iJKf+7NPcmd0n268zmqn5ap9NPUllW0P4JVPZrRHSkhMnTSkk3WWN7TGWjn9YX oVFw== X-Gm-Message-State: AOJu0Ywmi9e7iTOyDik4hG2h+P7u7iAfULhLayjz5hqGbAJWWyVuVwdv W6MYR9iNK6efmaePl9OTFOyJb1rfaHX6gMnM5/wvoYFt7dAEIIqKNgWLgg== X-Google-Smtp-Source: AGHT+IEotH7HKeTUA1cmaY0OJvJYpsde0zlMGs2DFKK2buVbr0HL43pcs9c9436lofxUZL4Mi1mpZQ== X-Received: by 2002:a05:600c:4515:b0:419:a3f:f4f6 with SMTP id 5b1f17b1804b1-4212e046d11mr17984035e9.8.1717160510597; Fri, 31 May 2024 06:01:50 -0700 (PDT) Received: from localhost.localdomain ([80.215.210.156]) by smtp.gmail.com with ESMTPSA id 5b1f17b1804b1-421270ad52dsm54599665e9.42.2024.05.31.06.01.49 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 31 May 2024 06:01:49 -0700 (PDT) From: Marta Rybczynska X-Google-Original-From: Marta Rybczynska To: openembedded-core@lists.openembedded.org Cc: Marta Rybczynska , Samantha Jalabert Subject: [RFC][OE-core 1/3] cve-check: enrich annotation of CVEs Date: Fri, 31 May 2024 15:01:26 +0200 Message-ID: <20240531130128.1258909-1-marta.rybczynska@syslinbit.com> X-Mailer: git-send-email 2.42.0 MIME-Version: 1.0 List-Id: X-Webhook-Received: from li982-79.members.linode.com [45.33.32.79] by aws-us-west-2-korg-lkml-1.web.codeaurora.org with HTTPS for ; Fri, 31 May 2024 13:01:56 -0000 X-Groupsio-URL: https://lists.openembedded.org/g/openembedded-core/message/200074 Previously the information passed between different function of the cve-check class included only tables of patched, unpatched, ignored vulnerabilities and the general status of the recipe. The VEX work requires more information, and we need to pass them between different functions, so that it can be enriched as the analysis progresses. Instead of multiple tables, use a single one with annotations for each CVE encountered. For example, a patched CVE will have: {"abbrev-status": "Patched", "status": "version-not-in-range"} abbrev-status contains the general status (Patched, Unpatched, Ignored and Unknown that will be added in the VEX code) status contains more detailed information that can come from CVE_STATUS and the analysis. Additional fields of the annotation include for example the name of the patch file fixing a given CVE. Signed-off-by: Marta Rybczynska Signed-off-by: Samantha Jalabert --- meta/classes/cve-check.bbclass | 208 +++++++++++++++++---------------- meta/lib/oe/cve_check.py | 12 +- 2 files changed, 113 insertions(+), 107 deletions(-) diff --git a/meta/classes/cve-check.bbclass b/meta/classes/cve-check.bbclass index 56ba8bceef..7257fa121e 100644 --- a/meta/classes/cve-check.bbclass +++ b/meta/classes/cve-check.bbclass @@ -187,10 +187,10 @@ python do_cve_check () { patched_cves = get_patched_cves(d) except FileNotFoundError: bb.fatal("Failure in searching patches") - ignored, patched, unpatched, status = check_cves(d, patched_cves) - if patched or unpatched or (d.getVar("CVE_CHECK_COVERAGE") == "1" and status): - cve_data = get_cve_info(d, patched + unpatched + ignored) - cve_write_data(d, patched, unpatched, ignored, cve_data, status) + cve_data, status = check_cves(d, patched_cves) + if len(cve_data) or (d.getVar("CVE_CHECK_COVERAGE") == "1" and status): + get_cve_info(d, cve_data) + cve_write_data(d, cve_data, status) else: bb.note("No CVE database found, skipping CVE check") @@ -292,7 +292,51 @@ ROOTFS_POSTPROCESS_COMMAND:prepend = "${@'cve_check_write_rootfs_manifest ' if d do_rootfs[recrdeptask] += "${@'do_cve_check' if d.getVar('CVE_CHECK_CREATE_MANIFEST') == '1' else ''}" do_populate_sdk[recrdeptask] += "${@'do_cve_check' if d.getVar('CVE_CHECK_CREATE_MANIFEST') == '1' else ''}" -def check_cves(d, patched_cves): +def cve_is_ignored(d, cve_data, cve): + if cve not in cve_data: + return False + if cve_data[cve]['abbrev-status'] == "Ignored": + return True + return False + +def cve_is_patched(d, cve_data, cve): + if cve not in cve_data: + return False + if cve_data[cve]['abbrev-status'] == "Patched": + return True + return False + +def cve_update(d, cve_data, cve, entry): + # If no entry, just add it + if cve not in cve_data: + cve_data[cve] = entry + return + # If we are updating, there might be change in the status + bb.debug("Trying CVE entry update for %s from %s to %s" % (cve, cve_data[cve]['abbrev-status'], entry['abbrev-status'])) + if cve_data[cve]['abbrev-status'] == "Unknown": + cve_data[cve] = entry + return + if cve_data[cve]['abbrev-status'] == entry['abbrev-status']: + return + # Update like in {'abbrev-status': 'Patched', 'status': 'version-not-in-range'} to {'abbrev-status': 'Unpatched', 'status': 'version-in-range'} + if entry['abbrev-status'] == "Unpatched" and cve_data[cve]['abbrev-status'] == "Patched": + if entry['status'] == "version-in-range" and cve_data[cve]['status'] == "version-not-in-range": + # New result from the scan, vulnerable + cve_data[cve] = entry + bb.debug("CVE entry %s update from Patched to Unpatched from the scan result" % cve) + return + if entry['abbrev-status'] == "Patched" and cve_data[cve]['abbrev-status'] == "Unpatched": + if entry['status'] == "version-not-in-range" and cve_data[cve]['status'] == "version-in-range": + # Range does not match the scan, but we already have a vulnerable match, ignore + bb.debug("CVE entry %s update from Patched to Unpatched from the scan result - not applying" % cve) + return + # If we have an "Ignored", it has a priority + if cve_data[cve]['abbrev-status'] == "Ignored": + bb.debug("CVE %s not updating because Ignored" % cve) + return + bb.warn("Unhandled CVE entry update for %s from %s to %s" % (cve, cve_data[cve], entry)) + +def check_cves(d, cve_data): """ Connect to the NVD database and find unpatched cves. """ @@ -302,28 +346,19 @@ def check_cves(d, patched_cves): real_pv = d.getVar("PV") suffix = d.getVar("CVE_VERSION_SUFFIX") - cves_unpatched = [] - cves_ignored = [] cves_status = [] cves_in_recipe = False # CVE_PRODUCT can contain more than one product (eg. curl/libcurl) products = d.getVar("CVE_PRODUCT").split() # If this has been unset then we're not scanning for CVEs here (for example, image recipes) if not products: - return ([], [], [], []) + return ([], []) pv = d.getVar("CVE_VERSION").split("+git")[0] # If the recipe has been skipped/ignored we return empty lists if pn in d.getVar("CVE_CHECK_SKIP_RECIPE").split(): bb.note("Recipe has been skipped by cve-check") - return ([], [], [], []) - - # Convert CVE_STATUS into ignored CVEs and check validity - cve_ignore = [] - for cve in (d.getVarFlags("CVE_STATUS") or {}): - decoded_status, _, _ = decode_cve_status(d, cve) - if decoded_status == "Ignored": - cve_ignore.append(cve) + return ([], []) import sqlite3 db_file = d.expand("file:${CVE_CHECK_DB_FILE}?mode=ro") @@ -342,11 +377,10 @@ def check_cves(d, patched_cves): for cverow in cve_cursor: cve = cverow[0] - if cve in cve_ignore: + if cve_is_ignored(d, cve_data, cve): bb.note("%s-%s ignores %s" % (product, pv, cve)) - cves_ignored.append(cve) continue - elif cve in patched_cves: + elif cve_is_patched(d, cve_data, cve): bb.note("%s has been patched" % (cve)) continue # Write status once only for each product @@ -362,7 +396,7 @@ def check_cves(d, patched_cves): for row in product_cursor: (_, _, _, version_start, operator_start, version_end, operator_end) = row #bb.debug(2, "Evaluating row " + str(row)) - if cve in cve_ignore: + if cve_is_ignored(d, cve_data, cve): ignored = True version_start = convert_cve_version(version_start) @@ -401,16 +435,16 @@ def check_cves(d, patched_cves): if vulnerable: if ignored: bb.note("%s is ignored in %s-%s" % (cve, pn, real_pv)) - cves_ignored.append(cve) + cve_update(d, cve_data, cve, {"abbrev-status": "Ignored"}) else: bb.note("%s-%s is vulnerable to %s" % (pn, real_pv, cve)) - cves_unpatched.append(cve) + cve_update(d, cve_data, cve, {"abbrev-status": "Unpatched", "status": "version-in-range"}) break product_cursor.close() if not vulnerable: bb.note("%s-%s is not vulnerable to %s" % (pn, real_pv, cve)) - patched_cves.add(cve) + cve_update(d, cve_data, cve, {"abbrev-status": "Patched", "status": "version-not-in-range"}) cve_cursor.close() if not cves_in_product: @@ -418,48 +452,45 @@ def check_cves(d, patched_cves): cves_status.append([product, False]) conn.close() - diff_ignore = list(set(cve_ignore) - set(cves_ignored)) - if diff_ignore: - oe.qa.handle_error("cve_status_not_in_db", "Found CVE (%s) with CVE_STATUS set that are not found in database for this component" % " ".join(diff_ignore), d) if not cves_in_recipe: bb.note("No CVE records for products in recipe %s" % (pn)) - return (list(cves_ignored), list(patched_cves), cves_unpatched, cves_status) + return (cve_data, cves_status) -def get_cve_info(d, cves): +def get_cve_info(d, cve_data): """ Get CVE information from the database. """ import sqlite3 - cve_data = {} db_file = d.expand("file:${CVE_CHECK_DB_FILE}?mode=ro") conn = sqlite3.connect(db_file, uri=True) - for cve in cves: + for cve in cve_data: cursor = conn.execute("SELECT * FROM NVD WHERE ID IS ?", (cve,)) for row in cursor: - cve_data[row[0]] = {} - cve_data[row[0]]["summary"] = row[1] - cve_data[row[0]]["scorev2"] = row[2] - cve_data[row[0]]["scorev3"] = row[3] - cve_data[row[0]]["modified"] = row[4] - cve_data[row[0]]["vector"] = row[5] - cve_data[row[0]]["vectorString"] = row[6] + # The CVE itdelf has been added already + if row[0] not in cve_data: + bb.note("CVE record %s not present" % row[0]) + continue + #cve_data[row[0]] = {} + cve_data[row[0]]["NVD-summary"] = row[1] + cve_data[row[0]]["NVD-scorev2"] = row[2] + cve_data[row[0]]["NVD-scorev3"] = row[3] + cve_data[row[0]]["NVD-modified"] = row[4] + cve_data[row[0]]["NVD-vector"] = row[5] + cve_data[row[0]]["NVD-vectorString"] = row[6] cursor.close() conn.close() - return cve_data -def cve_write_data_text(d, patched, unpatched, ignored, cve_data): +def cve_write_data_text(d, cve_data): """ Write CVE information in WORKDIR; and to CVE_CHECK_DIR, and CVE manifest if enabled. """ - from oe.cve_check import decode_cve_status - cve_file = d.getVar("CVE_CHECK_LOG") fdir_name = d.getVar("FILE_DIRNAME") layer = fdir_name.split("/")[-3] @@ -476,7 +507,7 @@ def cve_write_data_text(d, patched, unpatched, ignored, cve_data): return # Early exit, the text format does not report packages without CVEs - if not patched+unpatched+ignored: + if not len(cve_data): return nvd_link = "https://nvd.nist.gov/vuln/detail/" @@ -485,36 +516,27 @@ def cve_write_data_text(d, patched, unpatched, ignored, cve_data): bb.utils.mkdirhier(os.path.dirname(cve_file)) for cve in sorted(cve_data): - is_patched = cve in patched - is_ignored = cve in ignored - - status = "Unpatched" - if (is_patched or is_ignored) and not report_all: - continue - if is_ignored: - status = "Ignored" - elif is_patched: - status = "Patched" - else: - # default value of status is Unpatched - unpatched_cves.append(cve) - write_string += "LAYER: %s\n" % layer write_string += "PACKAGE NAME: %s\n" % d.getVar("PN") write_string += "PACKAGE VERSION: %s%s\n" % (d.getVar("EXTENDPE"), d.getVar("PV")) write_string += "CVE: %s\n" % cve - write_string += "CVE STATUS: %s\n" % status - _, detail, description = decode_cve_status(d, cve) - if detail: - write_string += "CVE DETAIL: %s\n" % detail - if description: - write_string += "CVE DESCRIPTION: %s\n" % description - write_string += "CVE SUMMARY: %s\n" % cve_data[cve]["summary"] - write_string += "CVSS v2 BASE SCORE: %s\n" % cve_data[cve]["scorev2"] - write_string += "CVSS v3 BASE SCORE: %s\n" % cve_data[cve]["scorev3"] - write_string += "VECTOR: %s\n" % cve_data[cve]["vector"] - write_string += "VECTORSTRING: %s\n" % cve_data[cve]["vectorString"] + write_string += "CVE STATUS: %s\n" % cve_data[cve]["abbrev-status"] + + if 'status' in cve_data[cve]: + write_string += "CVE DETAIL: %s\n" % cve_data[cve]["status"] + if 'justification' in cve_data[cve]: + write_string += "CVE DESCRIPTION: %s\n" % cve_data[cve]["justification"] + + if "NVD-summary" in cve_data[cve]: + write_string += "CVE SUMMARY: %s\n" % cve_data[cve]["NVD-summary"] + write_string += "CVSS v2 BASE SCORE: %s\n" % cve_data[cve]["NVD-scorev2"] + write_string += "CVSS v3 BASE SCORE: %s\n" % cve_data[cve]["NVD-scorev3"] + write_string += "VECTOR: %s\n" % cve_data[cve]["NVD-vector"] + write_string += "VECTORSTRING: %s\n" % cve_data[cve]["NVD-vectorString"] + write_string += "MORE INFORMATION: %s%s\n\n" % (nvd_link, cve) + if cve_data[cve]["abbrev-status"] == "Unpatched": + unpatched_cves.append(cve) if unpatched_cves and d.getVar("CVE_CHECK_SHOW_WARNINGS") == "1": bb.warn("Found unpatched CVE (%s), for more information check %s" % (" ".join(unpatched_cves),cve_file)) @@ -566,13 +588,11 @@ def cve_check_write_json_output(d, output, direct_file, deploy_file, manifest_fi with open(index_path, "a+") as f: f.write("%s\n" % fragment_path) -def cve_write_data_json(d, patched, unpatched, ignored, cve_data, cve_status): +def cve_write_data_json(d, cve_data, cve_status): """ Prepare CVE data for the JSON format, then write it. """ - from oe.cve_check import decode_cve_status - output = {"version":"1", "package": []} nvd_link = "https://nvd.nist.gov/vuln/detail/" @@ -590,8 +610,6 @@ def cve_write_data_json(d, patched, unpatched, ignored, cve_data, cve_status): if include_layers and layer not in include_layers: return - unpatched_cves = [] - product_data = [] for s in cve_status: p = {"product": s[0], "cvesInRecord": "Yes"} @@ -606,39 +624,29 @@ def cve_write_data_json(d, patched, unpatched, ignored, cve_data, cve_status): "version" : package_version, "products": product_data } + cve_list = [] for cve in sorted(cve_data): - is_patched = cve in patched - is_ignored = cve in ignored - status = "Unpatched" - if (is_patched or is_ignored) and not report_all: - continue - if is_ignored: - status = "Ignored" - elif is_patched: - status = "Patched" - else: - # default value of status is Unpatched - unpatched_cves.append(cve) - issue_link = "%s%s" % (nvd_link, cve) cve_item = { "id" : cve, - "summary" : cve_data[cve]["summary"], - "scorev2" : cve_data[cve]["scorev2"], - "scorev3" : cve_data[cve]["scorev3"], - "vector" : cve_data[cve]["vector"], - "vectorString" : cve_data[cve]["vectorString"], - "status" : status, - "link": issue_link + "status" : cve_data[cve]["abbrev-status"], + "link": issue_link, } - _, detail, description = decode_cve_status(d, cve) - if detail: - cve_item["detail"] = detail - if description: - cve_item["description"] = description + if 'NVD-summary' in cve_data[cve]: + cve_item["summary"] = cve_data[cve]["NVD-summary"] + cve_item["scorev2"] = cve_data[cve]["NVD-scorev2"] + cve_item["scorev3"] = cve_data[cve]["NVD-scorev3"] + cve_item["vector"] = cve_data[cve]["NVD-vector"] + cve_item["vectorString"] = cve_data[cve]["NVD-vectorString"] + if 'status' in cve_data[cve]: + cve_item["detail"] = cve_data[cve]["status"] + if 'justification' in cve_data[cve]: + cve_item["description"] = cve_data[cve]["justification"] + if 'resource' in cve_data[cve]: + cve_item["patch-file"] = cve_data[cve]["resource"] cve_list.append(cve_item) package_data["issue"] = cve_list @@ -650,12 +658,12 @@ def cve_write_data_json(d, patched, unpatched, ignored, cve_data, cve_status): cve_check_write_json_output(d, output, direct_file, deploy_file, manifest_file) -def cve_write_data(d, patched, unpatched, ignored, cve_data, status): +def cve_write_data(d, cve_data, status): """ Write CVE data in each enabled format. """ if d.getVar("CVE_CHECK_FORMAT_TEXT") == "1": - cve_write_data_text(d, patched, unpatched, ignored, cve_data) + cve_write_data_text(d, cve_data) if d.getVar("CVE_CHECK_FORMAT_JSON") == "1": - cve_write_data_json(d, patched, unpatched, ignored, cve_data, status) + cve_write_data_json(d, cve_data, status) diff --git a/meta/lib/oe/cve_check.py b/meta/lib/oe/cve_check.py index ed5c714cb8..6aba90183a 100644 --- a/meta/lib/oe/cve_check.py +++ b/meta/lib/oe/cve_check.py @@ -88,7 +88,7 @@ def get_patched_cves(d): # (cve_match regular expression) cve_file_name_match = re.compile(r".*(CVE-\d{4}-\d+)", re.IGNORECASE) - patched_cves = set() + patched_cves = {} patches = oe.patch.src_patches(d) bb.debug(2, "Scanning %d patches for CVEs" % len(patches)) for url in patches: @@ -98,7 +98,7 @@ def get_patched_cves(d): fname_match = cve_file_name_match.search(patch_file) if fname_match: cve = fname_match.group(1).upper() - patched_cves.add(cve) + patched_cves[cve] = {"abbrev-status": "Patched", "status": "fix-file-included", "resource": patch_file} bb.debug(2, "Found %s from patch file name %s" % (cve, patch_file)) # Remote patches won't be present and compressed patches won't be @@ -124,7 +124,7 @@ def get_patched_cves(d): cves = patch_text[match.start()+5:match.end()] for cve in cves.split(): bb.debug(2, "Patch %s solves %s" % (patch_file, cve)) - patched_cves.add(cve) + patched_cves[cve] = {"abbrev-status": "Patched", "status": "fix-file-included", "resource": patch_file} text_match = True if not fname_match and not text_match: @@ -132,10 +132,8 @@ def get_patched_cves(d): # Search for additional patched CVEs for cve in (d.getVarFlags("CVE_STATUS") or {}): - decoded_status, _, _ = decode_cve_status(d, cve) - if decoded_status == "Patched": - bb.debug(2, "CVE %s is additionally patched" % cve) - patched_cves.add(cve) + decoded_status, detail, description = decode_cve_status(d, cve) + patched_cves[cve] = {"abbrev-status": decoded_status, "status": detail, "justification": description} return patched_cves