Beyond Crash-to-Patch: Patch Evolution for Linux Kernel Repair

2026-04-04

AI Summary

This work addresses a critical limitation in existing automated Linux kernel repair approaches, which typically overlook the essential evolution of patches through multiple rounds of community review on mailing lists, thereby struggling to produce high-quality fixes that adhere to kernel development norms. To bridge this gap, the paper introduces PatchAdvisor, the first framework to systematically model the evolutionary trajectory of kernel patches by explicitly integrating reviewer feedback into the repair process. PatchAdvisor leverages retrieval-augmented generation and a fine-tuned diagnostic advisor to guide a coding agent, moving beyond the conventional “crash-to-patch” direct mapping paradigm. Evaluated on a time-preserving syzbot test suite, the approach substantially outperforms both unguided and retrieval-only baselines, achieving significant improvements in both alignment with community review expectations and end-to-end patch quality.

Abstract

Linux kernel bug repair is typically approached as a direct mapping from crash reports to code patches. In practice, however, kernel fixes undergo iterative revision on mailing lists before acceptance, with reviewer feedback shaping correctness, concurrency handling, and API compliance. This iterative refinement process encodes valuable repair knowledge that existing automated approaches overlook. We present a large-scale study of kernel patch evolution, reconstructing 6946 syzbot-linked bug-fix lifecycles that connect crash reports, reproducers, mailing-list discussions, revision histories, and merged fixes. Our analysis confirms that accepted repairs are frequently non-local and governed by reviewer-enforced constraints not present in bug reports. Building on these insights, we develop PatchAdvisor, a repair framework that integrates retrieval-based memory with a fine-tuned diagnostic advisor to guide a coding agent toward reviewer-aligned patches. Evaluation on temporally held-out syzbot cases demonstrates that leveraging patch-evolution history yields measurable gains in both reviewer-aligned refinement signals and end-to-end repair quality compared to unguided and retrieval-only baselines.

Problem

• Linux kernel repair
• patch evolution
• crash-to-patch
• reviewer feedback
• automated program repair

Innovation

• patch evolution
• Linux kernel repair
• reviewer feedback
• retrieval-based memory
• automated program repair