Static code analysis fixes by LinuxJedi · Pull Request #178 · wolfSSL/wolfPKCS11

LinuxJedi · 2026-04-07T13:40:43Z

Mostly fixes to missing flags or incorrect return codes. Also an endianness fix.

F-2032

F-2028

F-2029

F-2033

F-2034

F-2035

F-2037

F-2038

Copilot

Pull request overview

This PR addresses several static-analysis findings and PKCS#11 conformance issues by correcting return codes, recording key-generation metadata (CKA_LOCAL / CKA_KEY_GEN_MECHANISM), and adding regression tests (plus an HKDF length-cast fix).

Changes:

Fix PIN length handling to return CKR_PIN_LEN_RANGE and update tests accordingly.
Track locally-generated keys and key generation mechanisms for C_GenerateKey (including PBKDF2/PBE and random symmetric generation) and set derived sensitivity/extractability attributes.
Add new tests validating CKA_LOCAL / CKA_KEY_GEN_MECHANISM for AES and PBKDF2 key generation; adjust HKDF CKA_VALUE_LEN read to use CK_ULONG.

Reviewed changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 6 comments.

Show a summary per file

File	Description
`wolfpkcs11/internal.h`	Adds internal helper prototype and updates random-key generator signature to include mechanism.
`src/internal.c`	Implements helper to mark objects as locally generated and store key-gen mechanism; updates random key generation.
`src/crypto.c`	Updates digest return handling, verify-recover attribute check, key generation metadata/attrs, and HKDF length casting.
`src/slot.c`	Returns `CKR_PIN_LEN_RANGE` for invalid PIN lengths; propagates that return through token/PIN APIs.
`tests/pkcs11test.c`	Updates expected error codes for too-short/too-long PIN test cases.
`tests/include.am`	Adds new AES and PBKDF2 keygen attribute tests to the build.
`tests/aes_keygen_attrs_test.c`	New regression test for `CKA_LOCAL` / `CKA_KEY_GEN_MECHANISM` on AES key generation.
`tests/pbkdf2_keygen_attrs_test.c`	New regression test for `CKA_LOCAL` / `CKA_KEY_GEN_MECHANISM` and sensitivity/extractability-derived attributes on PBKDF2 keygen.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

src/crypto.c

wolfSSL-Fenrir-bot

Fenrir Automated Review — PR #178

Scan targets checked: wolfpkcs11-bugs, wolfpkcs11-compliance, wolfpkcs11-src

Findings: 1
1 finding(s) posted as inline comments (see file-level comments below)

This review was generated automatically by Fenrir. Findings are non-blocking.

src/crypto.c

LinuxJedi · 2026-04-07T14:52:50Z

ML-DSA tests will fail until #175 or #176 is merged.

Copilot

Pull request overview

Copilot reviewed 8 out of 8 changed files in this pull request and generated 5 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Copilot · 2026-04-07T14:59:52Z

src/crypto.c

-    return ret;
+    if (ret < 0)
+        return CKR_FUNCTION_FAILED;
+    return CKR_OK;


C_DigestKey() now returns CKR_OK for any non-negative value from WP11_Digest_Key(). However, WP11_Digest_Key() can return a non-zero CK_RV like CKR_FUNCTION_NOT_SUPPORTED (e.g., when WOLFPKCS11_NO_STORE is enabled), which should be propagated to the caller instead of being treated as success.

Suggested change

return CKR_OK;

return (CK_RV)ret;

Copilot · 2026-04-07T14:59:52Z

src/crypto.c

+                    rv = WP11_Object_GetAttr(pbkdf2Key, CKA_SENSITIVE,
+                                             &getVar, &getVarLen);
+                    if ((rv == CKR_OK) && (getVar == CK_TRUE)) {
+                        rv = WP11_Object_SetAttr(pbkdf2Key,
+                                                 CKA_ALWAYS_SENSITIVE,
+                                                 &trueVar, sizeof(CK_BBOOL));
+                    }
+                    if (rv == CKR_OK) {
+                        rv = WP11_Object_GetAttr(pbkdf2Key, CKA_EXTRACTABLE,
+                                                 &getVar, &getVarLen);
+                        if ((rv == CKR_OK) && (getVar == CK_FALSE)) {
+                            rv = WP11_Object_SetAttr(pbkdf2Key,
+                                                     CKA_NEVER_EXTRACTABLE,
+                                                     &trueVar,
+                                                     sizeof(CK_BBOOL));
+                        }
                    }


The PBKDF2/NSS-PBE keygen blocks duplicate the same initial-state logic that already exists in SetInitialStates() (CKA_ALWAYS_SENSITIVE/CKA_NEVER_EXTRACTABLE derivation). To avoid divergence between these early-return paths and the standard keygen path, consider calling SetInitialStates(pbkdf2Key/pbeKey) here instead of duplicating the attribute-get/set sequence.

Suggested change

rv = WP11_Object_GetAttr(pbkdf2Key, CKA_SENSITIVE,

&getVar, &getVarLen);

if ((rv == CKR_OK) && (getVar == CK_TRUE)) {

rv = WP11_Object_SetAttr(pbkdf2Key,

CKA_ALWAYS_SENSITIVE,

&trueVar, sizeof(CK_BBOOL));

}

if (rv == CKR_OK) {

rv = WP11_Object_GetAttr(pbkdf2Key, CKA_EXTRACTABLE,

&getVar, &getVarLen);

if ((rv == CKR_OK) && (getVar == CK_FALSE)) {

rv = WP11_Object_SetAttr(pbkdf2Key,

CKA_NEVER_EXTRACTABLE,

&trueVar,

sizeof(CK_BBOOL));

}

}

rv = SetInitialStates(pbkdf2Key);

Copilot · 2026-04-07T14:59:53Z

src/crypto.c

@@ -3892,7 +3895,9 @@ CK_RV C_Digest(CK_SESSION_HANDLE hSession, CK_BYTE_PTR pData,
                             session);
    *pulDigestLen = hashLen;



C_Digest() maps any negative return from WP11_Digest_Single() to CKR_FUNCTION_FAILED. WP11_Digest_Single can return BUFFER_E when the output buffer is too small, which should be surfaced as CKR_BUFFER_TOO_SMALL (similar to how C_GetAttributeValue maps BUFFER_E). Consider translating BUFFER_E to CKR_BUFFER_TOO_SMALL instead of collapsing it into CKR_FUNCTION_FAILED.

Suggested change

if (ret == BUFFER_E)

return CKR_BUFFER_TOO_SMALL;

Copilot · 2026-04-07T14:59:53Z

src/crypto.c

@@ -4027,7 +4036,9 @@ CK_RV C_DigestFinal(CK_SESSION_HANDLE hSession, CK_BYTE_PTR pDigest,
    ret = WP11_Digest_Final(pDigest, &hashLen, session);
    *pulDigestLen = hashLen;



C_DigestFinal() maps BUFFER_E (returned when the caller-provided digest buffer is too small) to CKR_FUNCTION_FAILED. This loses the PKCS#11-required CKR_BUFFER_TOO_SMALL signal; please translate BUFFER_E to CKR_BUFFER_TOO_SMALL (and only use CKR_FUNCTION_FAILED for true internal failures).

Suggested change

if (ret == BUFFER_E)

return CKR_BUFFER_TOO_SMALL;

Copilot · 2026-04-07T14:59:53Z

src/slot.c

    if (pinLen > WP11_MAX_PIN_LEN)
 #endif
-        return CKR_PIN_INCORRECT;
+        return CKR_PIN_LEN_RANGE;


checkPinLen() now returns CKR_PIN_LEN_RANGE, but some callers (e.g., C_Login and the ulOldLen check in C_SetPIN) still discard the return code and hardcode CKR_PIN_INCORRECT. This makes PIN-length failures inconsistent across APIs. Consider either propagating CKR_PIN_LEN_RANGE consistently everywhere checkPinLen() is used, or changing checkPinLen() to return only CKR_OK/CKR_GENERAL_ERROR and letting each API choose its CKR_* mapping.

Suggested change

return CKR_PIN_LEN_RANGE;

return CKR_PIN_INCORRECT;

LinuxJedi added 8 commits April 7, 2026 13:55

Fix op check

fd1520f

F-2032

Fix HKDF endianess issue

65c4089

F-2028

Fix return codes

665c4c1

F-2029

Set CKA_LOCAL for symmetric keys

148e1d6

F-2033

Add mechanism to symmetric keys

33efd26

F-2034

Fix pin length error handling

dc5bd0d

F-2035

Add mechanism to NSS generated keys

c8d6a4d

F-2037

Add correct flags for PBKDF2 keys

99ebafd

F-2038

LinuxJedi requested review from Copilot and wolfSSL-Fenrir-bot April 7, 2026 13:40

Copilot started reviewing on behalf of LinuxJedi April 7, 2026 13:45 View session

Copilot AI reviewed Apr 7, 2026

View reviewed changes

src/crypto.c Show resolved Hide resolved

src/crypto.c Show resolved Hide resolved

src/crypto.c Show resolved Hide resolved

src/crypto.c Show resolved Hide resolved

src/crypto.c Outdated Show resolved Hide resolved

src/crypto.c Outdated Show resolved Hide resolved

wolfSSL-Fenrir-bot reviewed Apr 7, 2026

View reviewed changes

src/crypto.c Show resolved Hide resolved

Copilot AI review requested due to automatic review settings April 7, 2026 14:46

LinuxJedi force-pushed the f-fixes7 branch from 6768e2f to 9892076 Compare April 7, 2026 14:46

Copilot started reviewing on behalf of LinuxJedi April 7, 2026 14:51 View session

Copilot AI reviewed Apr 7, 2026

View reviewed changes

Fix build issues and findings

9ff0150

LinuxJedi force-pushed the f-fixes7 branch from 9892076 to 9ff0150 Compare April 7, 2026 15:05

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Static code analysis fixes#178

Static code analysis fixes#178
LinuxJedi wants to merge 9 commits intowolfSSL:masterfrom
LinuxJedi:f-fixes7

LinuxJedi commented Apr 7, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

wolfSSL-Fenrir-bot left a comment

Uh oh!

Uh oh!

LinuxJedi commented Apr 7, 2026

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Apr 7, 2026

Uh oh!

Copilot AI Apr 7, 2026

Uh oh!

Copilot AI Apr 7, 2026

Uh oh!

Copilot AI Apr 7, 2026

Uh oh!

Copilot AI Apr 7, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

		@@ -3892,7 +3895,9 @@ CK_RV C_Digest(CK_SESSION_HANDLE hSession, CK_BYTE_PTR pData,
		session);
		*pulDigestLen = hashLen;

		@@ -4027,7 +4036,9 @@ CK_RV C_DigestFinal(CK_SESSION_HANDLE hSession, CK_BYTE_PTR pDigest,
		ret = WP11_Digest_Final(pDigest, &hashLen, session);
		*pulDigestLen = hashLen;

Conversation

LinuxJedi commented Apr 7, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

wolfSSL-Fenrir-bot left a comment

Choose a reason for hiding this comment

Fenrir Automated Review — PR #178

Uh oh!

Uh oh!

LinuxJedi commented Apr 7, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Copilot AI Apr 7, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 7, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 7, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 7, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Apr 7, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants