Linux Kernel Journey
KernelScript tackles the growing complexity of eBPF projects by unifying kernel‑side programs, userspace loaders, and kernel modules into a single codebase, using annotations to let the compiler generate the necessary glue code, thereby reducing boilerplate and improving team productivity.
By combining low‑overhead eBPF data collection with AI‑driven diagnosis and an agent‑based execution layer, the authors present a three‑tier system that shifts mobile optimization from peak performance to sustained energy efficiency, achieving sub‑1% monitoring overhead and up to 20% power savings in real‑world video workloads.
The article introduces bpftime for GPU, a tool that extends eBPF's programmable, low‑overhead observation capabilities into GPU kernels, explains its implementation pipeline, compares its performance against Nsight and NVBit, and outlines future enhancements for GPU profiling.
This article provides an in‑depth technical walkthrough of the eBPF loader implementation, explains two signature schemes, details map creation, hash calculation, CO‑RE relocation handling, the use_loader mode, kernel‑side verification via Hornet LSM, and discusses the advantages, limitations, and TOCTOU concerns.
The article argues that heavy container‑ or micro‑VM‑based sandboxes mis‑solve AI agent security, because the real threat is prompt injection at the application layer, and demonstrates that a policy‑first approach using Linux Landlock, seccomp and per‑tool isolation—embodied in the open‑source Sandlock sandbox—delivers strong protection without root or heavyweight isolation.
EROFS is a security‑focused, high‑performance read‑only Linux kernel file system designed for immutable scenarios such as container images, OS partitions, and AI model distribution, offering block‑aligned storage, minimal metadata, native compression, and host‑side page‑cache sharing to improve startup speed and reduce storage overhead.
The article argues that despite the AI boom, Linux kernel engineers still face fundamental performance and memory challenges, and that most AI‑related kernel papers have little impact on mainline development because of cultural and procedural gaps between academia and the kernel community.
This tutorial explains how to use eBPF and bpftrace to monitor the Intel NPU kernel driver on Lunar Lake and Meteor Lake CPUs, mapping Level Zero API calls to kernel ioctls, tracking memory allocation, IPC communication, and identifying performance bottlenecks through detailed function‑call statistics.
This article explains the fundamentals of CUDA performance tuning, covering GPU architectures from Kepler to Volta, the role of SMX, warp schedulers, registers and memory hierarchies, and provides practical guidance on launch configuration, latency hiding, and thread‑block sizing to maximize throughput.
This article explains the technical principles behind Linux kernel tracing, covering static tracepoints and dynamic kprobes, demonstrating their use with ftrace and perf, and detailing the underlying macro implementations and low‑level mechanisms that make kernel source tracking possible.
