gpu: nvgpu: More robust recovery

gpu: nvgpu: More robust recovery

Make recovery a more straightforward process. When we detect a fault,
trigger MMU fault, and wait for it to trigger, and complete recovery.
Also reset engines before aborting channel to ensure no stray sync
point increments can happen.

Change-Id: Iac685db6534cb64fe62d9fb452391f43100f2999
Signed-off-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-on: http://git-master/r/709060
(cherry picked from commit 95c62ffd9ac30a0d2eb88d033dcc6e6ff25efd6f)
Reviewed-on: http://git-master/r/707443