Marc Zyngier 57c841f131 arm/arm64: KVM: Handle out-of-RAM cache maintenance as a NOP
So far, our handling of cache maintenance by VA has been pretty
simple: Either the access is in the guest RAM and generates a S2
fault, which results in the page being mapped RW, or we go down
the io_mem_abort() path, and nuke the guest.

The first one is fine, but the second one is extremely weird.
Treating the CM as an I/O is wrong, and nothing in the ARM ARM
indicates that we should generate a fault for something that
cannot end-up in the cache anyway (even if the guest maps it,
it will keep on faulting at stage-2 for emulation).

So let's just skip this instruction, and let the guest get away
with it.

Reviewed-by: Christoffer Dall <christoffer.dall@linaro.org>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
2016-02-29 18:34:15 +00:00
..
2015-11-04 14:47:13 -08:00
2016-01-12 20:46:53 +02:00
2014-04-18 11:40:33 +02:00
2015-10-28 19:09:17 +00:00
2012-09-17 13:42:21 +01:00
2015-11-27 11:09:59 -08:00
2015-11-04 14:47:13 -08:00
2014-11-05 09:03:25 +01:00
2015-07-27 11:08:42 +01:00
2012-09-17 13:42:21 +01:00
2012-09-17 13:42:04 +01:00
2015-09-16 16:53:39 +02:00
2014-09-25 15:35:41 +01:00
2016-01-15 17:56:32 -08:00
2012-09-17 13:41:56 +01:00
2015-11-04 14:47:13 -08:00
2012-09-17 13:42:19 +01:00
2015-05-19 15:27:42 +01:00
2015-10-29 16:55:15 +00:00
2014-11-28 10:24:59 +00:00
2015-10-12 17:46:36 +01:00
2014-07-10 11:06:00 +01:00
2015-10-14 13:51:41 +01:00
2015-10-14 13:51:41 +01:00
2012-09-17 13:42:09 +01:00
2012-09-17 13:42:09 +01:00