gpu: nvgpu: fix ppc broadcast address split

In gr_gk20a_split_ppc_broadcast_addr() we convert a PPC broadcast address to
its corresponding unicast address list
But we consider gr.pe_count_per_gpc instead of actual number of PPCs and that
leads to generating incorrect list of addresses

Fix this by using gr.gpc_ppc_count[gpc_num] which gives correct number of
PPC count

Jira NVGPUT-117

Change-Id: If7e7c19244b90cb3c405dcba4ae7a86c782972f7
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1767838
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Konsta Holtta <kholtta@nvidia.com>
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

1 files changed, 1 insertions, 1 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/gr_gk20a.c b/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
index 074a74c0..7a65f353 100644
--- a/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
@@ -6297,7 +6297,7 @@ int gr_gk20a_split_ppc_broadcast_addr(struct gk20a *g, u32 addr,
 
     nvgpu_log(g, gpu_dbg_fn | gpu_dbg_gpu_dbg, "addr=0x%x", addr);
 
-    for (ppc_num = 0; ppc_num < g->gr.pe_count_per_gpc; ppc_num++)
+    for (ppc_num = 0; ppc_num < g->gr.gpc_ppc_count[gpc_num]; ppc_num++)
             priv_addr_table[(*t)++] = pri_ppc_addr(g, pri_ppccs_addr_mask(addr),
                                                    gpc_num, ppc_num);