gpu: nvgpu: gv11b: implement ecc scrubber

Check the availability of ecc units by checking
relevant ecc fuse and fuse overrides.

During gpu boot, initialize ecc units by scrubbing
individual ecc units available.  ECC initialization
should be done before gr initialization.

Following ecc units are scrubbed:
SM LRF
SM L1 DATA
SM L1 TAG
SM CBU
SM ICACHE

Bug 200339497

Change-Id: I54bf8cc1fce639a9993bf80984dafc28dca0dba3
Signed-off-by: Deepak Goyal <dgoyal@nvidia.com>
Signed-off-by: seshendra Gadagottu <sgadagottu@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1612734
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

2 files changed, 5 insertions, 1 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/gk20a.h b/drivers/gpu/nvgpu/gk20a/gk20a.h
index 2ae1b758..f1dc2f03 100644
--- a/drivers/gpu/nvgpu/gk20a/gk20a.h
+++ b/drivers/gpu/nvgpu/gk20a/gk20a.h
@@ -436,6 +436,7 @@ struct gpu_ops {
                 void (*init_gfxp_wfi_timeout_count)(struct gk20a *g);
                 unsigned long (*get_max_gfxp_wfi_timeout_count)
                                         (struct gk20a *g);
+                void (*ecc_init_scrub_reg)(struct gk20a *g);
         } gr;
         struct {
                 void (*init_hw)(struct gk20a *g);
diff --git a/drivers/gpu/nvgpu/gk20a/gr_gk20a.c b/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
index 99f85b57..ea4d1d24 100644
--- a/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
@@ -4478,7 +4478,10 @@ static int gk20a_init_gr_setup_hw(struct gk20a *g)
         if (g->ops.gr.enable_gpc_exceptions)
                 g->ops.gr.enable_gpc_exceptions(g);
 
-        /* TBD: ECC for L1/SM */
+        /* enable ECC for L1/SM */
+        if (g->ops.gr.ecc_init_scrub_reg)
+                g->ops.gr.ecc_init_scrub_reg(g);
+
         /* TBD: enable per BE exceptions */
 
         /* reset and enable exceptions */