PortGPT: Towards Automated Backporting Using Large Language Models

TL;DR

PORTGPT leverages large language models with tool-enhanced reasoning to automate patch backporting, significantly improving success rates over existing methods and contributing patches to the Linux kernel.

Contribution

This paper introduces PORTGPT, a novel LLM-based system that automates complex patch backporting with tool integration, surpassing prior automated approaches.

Findings

89.15% success rate on existing datasets

62.33% success rate on complex cases

Contributed 9 patches to Linux kernel community

Abstract

Patch backporting, the process of migrating mainline security patches to older branches, is an essential task in maintaining popular open-source projects (e.g., Linux kernel). However, manual backporting can be labor-intensive, while existing automated methods, which heavily rely on predefined syntax or semantic rules, often lack agility for complex patches. In this paper, we introduce PORTGPT, an LLM-agent for end-to-end automation of patch backporting in real-world scenarios. PORTGPT enhances an LLM with tools to access code on-demand, summarize Git history, and revise patches autonomously based on feedback (e.g., from compilers), hence, simulating human-like reasoning and verification. PORTGPT achieved an 89.15% success rate on existing datasets (1815 cases), and 62.33% on our own dataset of 146 complex cases, both outperforms state-of-the-art of backporting tools. We contributed 9 backported patches from PORTGPT to the Linux kernel community and all patches are now merged.