Linus Torvalds used Claude Code to develop a new Linux kernel feature
Linus Torvalds has been on record supporting AI for Linux kernel debugging. Now he’s taken it a step further: he used Claude Code to help develop a new kernel feature, not just find bugs in existing code.
What Torvalds Actually Did
In a recent patch message, Torvalds wrote:
“The code, the test programs, the review behind the list above and the first draft of this text were done with an LLM coding assistant (Claude Code) under my direction. The measurements were run on my machine.”
The work was for a branch called noref-filemap-read-with-llm. Michael Larabel of Phoronix noted that a new kernel branch appearing in Torvalds’ main repository is itself unusual.
The Technical Idea
The branch explores a page cache optimization. The existing approach tracks every reader with a reference count, which creates heavy CPU locking under load. Torvalds’ idea uses Linux’s Read-Copy-Update (RCU) synchronization mechanism instead, allowing lockless reads through deferred memory freeing and reference-free copy. The framing: a folio removed from the page cache returns to the page allocator only after an RCU grace period.
Status
The patches are publicly viewable in the kernel repository. There’s no confirmed decision yet on whether they’ll be merged into the upcoming 7.4 kernel.
I’m founder of BizStack at Cagri Sarigoz LLC and a passionate advocate for entrepreneurs.
With over 14 years in tech, marketing, and AI, including my role as Head of SEO at CitizenShipper and co-founder of TaleBot at Intale AI, I’m dedicated to sharing genuine, useful product insights and tips.
At BizStack, I aim to cut through the digital noise to provide clear, actionable advice.
And more than all else, I’m a father to a (always) little girl and a husband.
Contact me at [email protected] for assistance.
