On Thu, Aug 09, 2018 at 10:27:46AM +1000, Benjamin Herrenschmidt wrote:

On Mon, 2018-07-30 at 18:38 +0200, Christoph Hellwig wrote:

quoted

The requirement to disable local irqs over kmap_atomic is long gone,
so remove those calls.

Really ? I'm trying to verify that and getting lost in a mess of macros
from hell in the per-cpu stuff but if you look at our implementation
of kmap_atomic_prot(), all it does is a preempt_disable(), and then
it uses kmap_atomic_idx_push():

	int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1;

Note the use of __this_cpu_inc_return(), not this_cpu_inc_return(),
ie this is the non-interrupt safe version...

Looks like the powerpc variant indeed isn't save.

I did look a bit more through the code and history, and it seems
like we remove the need to disable irqs when called from process
context a while ago, but we still require disabling irqs when called
from irq context.  Given that this code can also be called from
irq context we'll have to keep the local_irq_save.