gpu: nvgpu: optimize map calls in patch smpc

Copy the necessary ctx patching prologues and epilogues from patch_write
to gr_gk20a_exec_ctx_ops next to mapping of gr ctx, around a loop that
applies patches multiple times, in order to optimize the number of
maps/unmaps on the channel's patch context.

Bug 200075565

Change-Id: I7125be5c778192d639f0bbed1731bb900c7015da
Signed-off-by: Konsta Holtta <kholtta@nvidia.com>
(cherry picked from commit TODO-FILL-THIS-WHEN-MERGED)
Reviewed-on: http://git-master/r/839203
Reviewed-by: Terje Bergstrom <tbergstrom@nvidia.com>
Tested-by: Terje Bergstrom <tbergstrom@nvidia.com>

1 files changed, 6 insertions, 1 deletions

diff --git a/drivers/gpu/nvgpu/gk20a/gr_gk20a.c b/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
index adb4b276..34ad1771 100644
--- a/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
+++ b/drivers/gpu/nvgpu/gk20a/gr_gk20a.c
@@ -648,7 +648,6 @@ int gr_gk20a_ctx_patch_write(struct gk20a *g,
                 if (!ch_ctx->patch_ctx.mem.cpu_va) {
                         int err;
                         gk20a_dbg_info("per-write ctx patch begin?");
-                        /* yes, gr_gk20a_ctx_patch_smpc causes this one */
                         err = gr_gk20a_ctx_patch_write_begin(g, ch_ctx);
                         if (err)
                                 return err;
@@ -6759,6 +6758,9 @@ int gr_gk20a_exec_ctx_ops(struct channel_gk20a *ch,
                 err = -ENOMEM;
                 goto cleanup;
         }
+        err = gr_gk20a_ctx_patch_write_begin(g, ch_ctx);
+        if (err)
+                goto cleanup;
 
         g->ops.mm.l2_flush(g, true);
 
@@ -6863,6 +6865,9 @@ int gr_gk20a_exec_ctx_ops(struct channel_gk20a *ch,
         if (offsets)
                 kfree(offsets);
 
+        if (ch_ctx->patch_ctx.mem.cpu_va)
+                gr_gk20a_ctx_patch_write_end(g, ch_ctx);
+
         if (ctx_ptr)
                 vunmap(ctx_ptr);