i965: Actually emit PIPELINE_SELECT and 3DSTATE_VF_STATISTICS.

For platforms using hardware contexts (currently Gen6+), we failed to
emit PIPELINE_SELECT and 3DSTATE_VF_STATISTICS, instead emitting MI_NOOP
for both.

During one of the context initialization reordering patches, we
accidentally moved brw_init_state before we set brw->CMD_PIPELINE_SELECT
and brw->CMD_VF_STATISTICS.  So, when brw_init_state uploaded initial
GPU state (brw_init_state -> brw_upload_initial_gpu_state ->
brw_upload_invariant_state), these would be 0 (MI_NOOP).

Storing the commands in the context is not worthwhile.  We have many
generation checks in our state upload code, and for platforms with
hardware contexts, this only gets called once per GL context anyway.
The cost is negligable, and it's easy to botch context creation
ordering.

This may fix hangs on Gen6+ when using the media pipeline.

Cc: "10.0 10.1" <[email protected]>
Signed-off-by: Kenneth Graunke <[email protected]>
Reviewed-by: Eric Anholt <[email protected]>
Reviewed-by: Ben Widawsky <[email protected]>

3 files changed, 8 insertions, 15 deletions

diff --git a/src/mesa/drivers/dri/i965/brw_context.c b/src/mesa/drivers/dri/i965/brw_context.c
index 28118b967c5..cad83e24c88 100644
--- a/src/mesa/drivers/dri/i965/brw_context.c
+++ b/src/mesa/drivers/dri/i965/brw_context.c
@@ -718,14 +718,6 @@ brwCreateContext(gl_api api,
 
    brw_init_surface_formats(brw);
 
-   if (brw->is_g4x || brw->gen >= 5) {
-      brw->CMD_VF_STATISTICS = GM45_3DSTATE_VF_STATISTICS;
-      brw->CMD_PIPELINE_SELECT = CMD_PIPELINE_SELECT_GM45;
-  } else {
-      brw->CMD_VF_STATISTICS = GEN4_3DSTATE_VF_STATISTICS;
-      brw->CMD_PIPELINE_SELECT = CMD_PIPELINE_SELECT_965;
-   }
-
    brw->max_vs_threads = devinfo->max_vs_threads;
    brw->max_gs_threads = devinfo->max_gs_threads;
    brw->max_wm_threads = devinfo->max_wm_threads;
diff --git a/src/mesa/drivers/dri/i965/brw_context.h b/src/mesa/drivers/dri/i965/brw_context.h
index 1f7108f30e9..f30d42c552e 100644
--- a/src/mesa/drivers/dri/i965/brw_context.h
+++ b/src/mesa/drivers/dri/i965/brw_context.h
@@ -1172,11 +1172,6 @@ struct brw_context
     */
    int num_samples;
 
-   /* hw-dependent 3DSTATE_VF_STATISTICS opcode */
-   uint32_t CMD_VF_STATISTICS;
-   /* hw-dependent 3DSTATE_PIPELINE_SELECT opcode */
-   uint32_t CMD_PIPELINE_SELECT;
-
    /**
     * Platform specific constants containing the maximum number of threads
     * for each pipeline stage.
diff --git a/src/mesa/drivers/dri/i965/brw_misc_state.c b/src/mesa/drivers/dri/i965/brw_misc_state.c
index c8fb6f312d1..a6b108b6983 100644
--- a/src/mesa/drivers/dri/i965/brw_misc_state.c
+++ b/src/mesa/drivers/dri/i965/brw_misc_state.c
@@ -896,13 +896,17 @@ const struct brw_tracked_state brw_line_stipple = {
 void
 brw_upload_invariant_state(struct brw_context *brw)
 {
+   const bool is_965 = brw->gen == 4 && !brw->is_g4x;
+
    /* 3DSTATE_SIP, 3DSTATE_MULTISAMPLE, etc. are nonpipelined. */
    if (brw->gen == 6)
       intel_emit_post_sync_nonzero_flush(brw);
 
    /* Select the 3D pipeline (as opposed to media) */
+   const uint32_t _3DSTATE_PIPELINE_SELECT =
+      is_965 ? CMD_PIPELINE_SELECT_965 : CMD_PIPELINE_SELECT_GM45;
    BEGIN_BATCH(1);
-   OUT_BATCH(brw->CMD_PIPELINE_SELECT << 16 | 0);
+   OUT_BATCH(_3DSTATE_PIPELINE_SELECT << 16 | 0);
    ADVANCE_BATCH();
 
    if (brw->gen < 6) {
@@ -926,8 +930,10 @@ brw_upload_invariant_state(struct brw_context *brw)
       ADVANCE_BATCH();
    }
 
+   const uint32_t _3DSTATE_VF_STATISTICS =
+      is_965 ? GEN4_3DSTATE_VF_STATISTICS : GM45_3DSTATE_VF_STATISTICS;
    BEGIN_BATCH(1);
-   OUT_BATCH(brw->CMD_VF_STATISTICS << 16 |
+   OUT_BATCH(_3DSTATE_VF_STATISTICS << 16 |
 	     (unlikely(INTEL_DEBUG & DEBUG_STATS) ? 1 : 0));
    ADVANCE_BATCH();
 }