The general thrust of it is that you provide the kernel with some bytecode, which it verifies, then executes in kernel context. There are multiple ways to get BPF bytecode into the kernel, but I’m going to talk about bpftrace , which provides an awk like language for writing BPF programs. Rooted profilingSpiderMonkey is a precisely rooted JS engine, so we have a Rooted type, that informs the GC about C++ object pointers. Until I started learning bpftrace, at which point I realized I probably could make this work. @call_counts[$filename,$lineno]++ }uprobe here is a “user probe” which accesses a function symbol in the program (as opposed to a kprobe , which is a kernel probe).