On Mon, Mar 09, 2020 at 12:45:34PM +0100, Auger Eric wrote:
> >> - for_each_present_cpu(cpu) {
> >> + for (cpu = 0; cpu < nr_cpus; cpu++) {
> >
> > You don't mention this change in the changelog.
> Hey, you can see the changelog is pretty long already & accurate. But
> you're right I missed that one and listing those changes too would have
> avoided me to put those changes in that patch.
>
> What's wrong with
> > using for_each_present_cpu() here?
> As you encouraged me to move the alloc into the it, I tried to do so but
> then discovered this was feasible for such kind of issue. At init time,
> CPUs have nott booted yet.
They may not have booted, but for_each_present_cpu() should still work
because the present mask is initialized at setup() time before the unit
test even starts.
Thanks,
drew
