gpu: nvgpu: return error for handled intr only

In gk20a_gr_handle_fecs_error(), we always return error
value and that triggers recovery in each case

Return error only if we need to trigger recovery
(depending on case)
Otherwise, clear the interrupt and return success

Bug 200156699

Change-Id: I117f3702b751e8bbc1cd3834b1b72b6533e246f9
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: http://git-master/r/1001694
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>

1 files changed, 3 insertions, 1 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/gr_gk20a.c b/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
index a96bc4e1..4d3f5068 100644
--- a/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
@@ -4885,6 +4885,7 @@ int gk20a_gr_handle_fecs_error(struct gk20a *g, struct channel_gk20a *ch,
                                           struct gr_gk20a_isr_data *isr_data)
 {
         u32 gr_fecs_intr = gk20a_readl(g, gr_fecs_host_int_status_r());
+        int ret = 0;
 
         gk20a_dbg_fn("");
 
@@ -4897,10 +4898,11 @@ int gk20a_gr_handle_fecs_error(struct gk20a *g, struct channel_gk20a *ch,
                           "firmware method error 0x%08x for offset 0x%04x",
                           gk20a_readl(g, gr_fecs_ctxsw_mailbox_r(6)),
                           isr_data->data_lo);
+                ret = -1;
         }
 
         gk20a_writel(g, gr_fecs_host_int_clear_r(), gr_fecs_intr);
-        return -EINVAL;
+        return ret;
 }
 
 static int gk20a_gr_handle_class_error(struct gk20a *g,