[$] What's brewing in CXL
Compute Express Link (CXL) is a technology designed to enhance memory management in data centers. It allows for the provision of memory nodes to CPUs but has faced challenges since its introduction in 2021. The CXL standard is rapidly evolving, with ongoing developments in error handling and accelerator support.
- ▪CXL provides memory over the PCIe bus but generally has worse latency than remote NUMA nodes.
- ▪The kernel's management of CXL memory is complicated by firmware interactions and the hot-plug nature of CXL memory.
- ▪Error handling for CXL is evolving, with kernel panics occurring in error-handling paths due to firmware behavior.
Opening excerpt (first ~120 words) tap to expand
We're bad at marketing We can admit it, marketing is not our strong suit. Our strength is writing the kind of articles that developers, administrators, and free-software supporters depend on to know what is going on in the Linux world. Please subscribe today to help us keep doing that, and so we don’t have to get good at marketing. By Jonathan CorbetMay 19, 2026 LSFMM+BPF Compute Express Link (CXL) is a technology intended to enable the provision of "memory nodes" in data centers that provide (possibly shared) memory to nearby CPUs. It has, Dan Williams said at the beginning of his memory-management-track session on the topic at the 2026 Linux Storage, Filesystem, Memory Management, and BPF Summit, "been making memory-management problems worse since 2021".
…
Excerpt limited to ~120 words for fair-use compliance. The full article is at LWN.net (Linux Weekly News).