gpu: nvgpu: recover on first interrupt reported for mmu nack

In case of mmu nack error interrupt is received twice through SM
reported mmu nack interrupt and mmu fault in undertermined order.
Recover on the first received interrupt to avoid semaphore release
and skip doing a second recovery.

Also fix NULL pointer dereference in function
gv11b_fifo_reset_pbdma_and_eng_faulted when channel reference is
invalid in teardown path.

Bug 200382235

Change-Id: I361a5725d7b6355ebf02b2870727f647fbd7a37e
Signed-off-by: Aparna Das <aparnad@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1739804
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

2 files changed, 4 insertions, 0 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/channel_gk20a.c b/drivers/gpu/nvgpu/gk20a/channel_gk20a.c
index 551e8b04..4e6837ef 100644
--- a/drivers/gpu/nvgpu/gk20a/channel_gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/channel_gk20a.c
@@ -684,6 +684,8 @@ struct channel_gk20a *gk20a_open_new_channel(struct gk20a *g,
         ch->subctx_id = 0;
         ch->runqueue_sel = 0;
 
+        ch->mmu_nack_handled = false;
+
         /* The channel is *not* runnable at this point. It still needs to have
          * an address space bound and allocate a gpfifo and grctx. */
 
diff --git a/drivers/gpu/nvgpu/gk20a/channel_gk20a.h b/drivers/gpu/nvgpu/gk20a/channel_gk20a.h
index f95184be..aa37db62 100644
--- a/drivers/gpu/nvgpu/gk20a/channel_gk20a.h
+++ b/drivers/gpu/nvgpu/gk20a/channel_gk20a.h
@@ -295,6 +295,8 @@ struct channel_gk20a {
 
         /* Any operating system specific data. */
         void *os_priv;
+
+        bool mmu_nack_handled;
 };
 
 static inline struct channel_gk20a *