crypto_sign_secp256k1: fix hashing heuristics

[RomarQ]

Should address #251

When the payload (Call, Extension, Extension::Implicit) is bigger than 256 bytes, the function crypto_sign_secp256k1 also needs to hash it with BLAKE2B, and then KECCAK_256.

Polkadot-SDK reference code

Unfortunately, didn't yet have the time to test the fix, since my old nano S display seems broken.

🔗 zboto Link

[gemini-code-assist]

Summary of Changes

Hello @RomarQ, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request addresses a critical issue in the crypto_sign_secp256k1 function where payloads larger than 256 bytes were not being signed correctly. The fix introduces a conditional hashing step: if the payload exceeds this size, it is first hashed with BLAKE2B, and then the resulting digest is hashed with KECCAK_256. This ensures compliance with the specific hashing heuristics required by the Polkadot runtime for large extrinsic payloads, thereby resolving signing failures for such transactions.

Highlights

• Conditional Hashing Logic: Implemented a new logic within crypto_sign_secp256k1 to conditionally apply a BLAKE2B hash to the message before the mandatory KECCAK_256 hash. This pre-hashing occurs only when the message length exceeds MAX_SIGN_SIZE (256 bytes), aligning with the Polkadot runtime's extrinsic hashing requirements for larger payloads.
• Buffer Size Adjustment: The size of the messageDigest buffer was adjusted to BLAKE2B_DIGEST_SIZE to correctly store the output of the BLAKE2B hash, which then becomes the input for the KECCAK_256 hash.
• Code Refactoring: The declaration of the zxerr_t error variable was refactored and moved to an earlier point in the crypto_sign_secp256k1 function, improving code organization.

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in issue comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request correctly identifies the need to hash large payloads with BLAKE2b before the final keccak256 hash, as per Polkadot's specification. However, the current implementation introduces a critical issue by performing an in-place keccak256 hash, which is unsafe with the Ledger SDK and can lead to invalid signatures. My review includes a critical comment with a suggested code change to resolve this by using a separate buffer for the intermediate hash, ensuring the cryptographic operations are performed correctly.