gpu: nvgpu: gv100: fix PMA list alignment in ctxsw buffer

GV100 ucode is changed so that it expects LIST_nv_perf_pma_ctx_reg list in
ctxsw buffer to be 256 byte aligned but same change is not applied to other
chip ucodes

ADD new HAL (*add_ctxsw_reg_perf_pma) to configure PMA register list and
define a common HAL gr_gk20a_add_ctxsw_reg_perf_pma() for all other
chips except GV100

Define a separate HAL for GV100 gr_gv100_add_ctxsw_reg_perf_pma() and fix
the required alignment in this function

Bug 1998067

Change-Id: Ie172fe90e2cdbac2509f2ece953cd8552e66fc56
Signed-off-by: Deepak Nibade <dnibade@nvidia.com>
Reviewed-on: https://git-master.nvidia.com/r/1676655
Reviewed-by: svc-mobile-coverity <svc-mobile-coverity@nvidia.com>
GVS: Gerrit_Virtual_Submit
Reviewed-by: Vijayakumar Subbu <vsubbu@nvidia.com>
Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com>
Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>

3 files changed, 18 insertions, 1 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/gk20a.h b/drivers/gpu/nvgpu/gk20a/gk20a.h
index 4ab1cd1b..f64a2b96 100644
--- a/drivers/gpu/nvgpu/gk20a/gk20a.h
+++ b/drivers/gpu/nvgpu/gk20a/gk20a.h
@@ -456,6 +456,10 @@ struct gpu_ops {
                                 u32 *count, u32 *offset,
                                 u32 max_cnt, u32 base,
                                 u32 num_fbpas, u32 stride, u32 mask);
+                int (*add_ctxsw_reg_perf_pma)(struct ctxsw_buf_offset_map_entry *map,
+                                        struct aiv_list_gk20a *regs,
+                                        u32 *count, u32 *offset,
+                                        u32 max_cnt, u32 base, u32 mask);
         } 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 bec33293..9d85a5ef 100644
--- a/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
@@ -7568,6 +7568,15 @@ static int add_ctxsw_buffer_map_entries_gpcs(struct gk20a *g,
         return 0;
 }
 
+int gr_gk20a_add_ctxsw_reg_perf_pma(struct ctxsw_buf_offset_map_entry *map,
+        struct aiv_list_gk20a *regs,
+        u32 *count, u32 *offset,
+        u32 max_cnt, u32 base, u32 mask)
+{
+        return add_ctxsw_buffer_map_entries(map, regs,
+                        count, offset, max_cnt, base, mask);
+}
+
 /*
  *            PM CTXSW BUFFER LAYOUT :
  *|---------------------------------------------|0x00 <----PM CTXSW BUFFER BASE
@@ -7671,7 +7680,7 @@ static int gr_gk20a_create_hwpm_ctxsw_buffer_offset_map(struct gk20a *g)
                 goto cleanup;
 
         /* Add entries from _LIST_nv_perf_pma_ctx_reg*/
-        if (add_ctxsw_buffer_map_entries(map, &g->gr.ctx_vars.ctxsw_regs.perf_pma,
+        if (g->ops.gr.add_ctxsw_reg_perf_pma(map, &g->gr.ctx_vars.ctxsw_regs.perf_pma,
                                 &count, &offset, hwpm_ctxsw_reg_count_max, 0, ~0))
                 goto cleanup;
 
diff --git a/drivers/gpu/nvgpu/gk20a/gr_gk20a.h b/drivers/gpu/nvgpu/gk20a/gr_gk20a.h
index 5ac363e1..54833028 100644
--- a/drivers/gpu/nvgpu/gk20a/gr_gk20a.h
+++ b/drivers/gpu/nvgpu/gk20a/gr_gk20a.h
@@ -817,4 +817,8 @@ int gr_gk20a_add_ctxsw_reg_pm_fbpa(struct gk20a *g,
                                 u32 *count, u32 *offset,
                                 u32 max_cnt, u32 base,
                                 u32 num_fbpas, u32 stride, u32 mask);
+int gr_gk20a_add_ctxsw_reg_perf_pma(struct ctxsw_buf_offset_map_entry *map,
+        struct aiv_list_gk20a *regs,
+        u32 *count, u32 *offset,
+        u32 max_cnt, u32 base, u32 mask);
 #endif /*__GR_GK20A_H__*/