wasi_thread_start

    fn wasi_thread_start(tid: i32, arg: *Instance) callconv(.c) void {
        comptime assert(!builtin.single_threaded);
        __set_stack_pointer(arg.thread.memory.ptr + arg.stack_offset);
        __wasm_init_tls(arg.thread.memory.ptr + arg.tls_offset);
        @atomicStore(u32, &WasiThreadImpl.tls_thread_id, @intCast(tid), .seq_cst);

        // Finished bootstrapping, call user's procedure.
        arg.call_back(arg.raw_ptr);

        switch (arg.thread.state.swap(.completed, .seq_cst)) {
            .running => {
                // reset the Thread ID
                asm volatile (
                    \\ local.get %[ptr]
                    \\ i32.const 0
                    \\ i32.atomic.store 0
                    :
                    : [ptr] "r" (&arg.thread.tid.raw),
                );

                // Wake the main thread listening to this thread
                asm volatile (
                    \\ local.get %[ptr]
                    \\ i32.const 1 # waiters
                    \\ memory.atomic.notify 0
                    \\ drop # no need to know the waiters
                    :
                    : [ptr] "r" (&arg.thread.tid.raw),
                );
            },
            .completed => unreachable,
            .detached => {
                // restore the original stack pointer so we can free the memory
                // without having to worry about freeing the stack
                __set_stack_pointer(arg.original_stack_pointer);
                // Ensure a copy so we don't free the allocator reference itself
                var allocator = arg.thread.allocator;
                allocator.free(arg.thread.memory);
            },
        }
    }