i965/gen9: Implement Push Constant Buffer workaround

This implements a workaround (exact excerpt as a comment in the code). The docs
specify [clearly, after you struggle for a while] that the offset isn't relative
to state base. This actually makes sense. This fixes hangs on SKL.

Buffer #0 is meant to be used for normal uniforms.
Buffer #1 is typically used for gather constants when using RS.
Buffer #1-#3 could be used to push a bunch of UBO data which would just be
  somewhere in memory, and not relative to the dynamic state.

NOTE: I've moved away from the ternary operator for the new gen9 conditions.
Admittedly it's probably not great to do this, but I really want to fix this all
up in the subsequent patch and doing it here makes that diff a lot nicer. I want
to split out the gen8/9 code to make the function a bit more readable, but to
keep this easily cherry-pickable I am doing this fix first. If we decide not to
merge the cleanup patch then I can revisit this.

Cc: "10.5 10.6" <[email protected]>
Signed-off-by: Ben Widawsky <[email protected]>
Reviewed-by: Anuj Phogat <[email protected]>
Tested-by: Valtteri Rantala <[email protected]>

1 files changed, 41 insertions, 7 deletions

diff --git a/src/mesa/drivers/dri/i965/gen7_vs_state.c b/src/mesa/drivers/dri/i965/gen7_vs_state.c
index 278b3ec6d21..4b17d06fa83 100644
--- a/src/mesa/drivers/dri/i965/gen7_vs_state.c
+++ b/src/mesa/drivers/dri/i965/gen7_vs_state.c
@@ -43,18 +43,52 @@ gen7_upload_constant_state(struct brw_context *brw,
    int dwords = brw->gen >= 8 ? 11 : 7;
    BEGIN_BATCH(dwords);
    OUT_BATCH(opcode << 16 | (dwords - 2));
-   OUT_BATCH(active ? stage_state->push_const_size : 0);
-   OUT_BATCH(0);
+
+   /* Workaround for SKL+ (we use option #2 until we have a need for more
+    * constant buffers). This comes from the documentation for 3DSTATE_CONSTANT_*
+    *
+    * The driver must ensure The following case does not occur without a flush
+    * to the 3D engine: 3DSTATE_CONSTANT_* with buffer 3 read length equal to
+    * zero committed followed by a 3DSTATE_CONSTANT_* with buffer 0 read length
+    * not equal to zero committed. Possible ways to avoid this condition
+    * include:
+    *     1. always force buffer 3 to have a non zero read length
+    *     2. always force buffer 0 to a zero read length
+    */
+   if (brw->gen >= 9 && active) {
+      OUT_BATCH(0);
+      OUT_BATCH(stage_state->push_const_size);
+   } else {
+      OUT_BATCH(active ? stage_state->push_const_size : 0);
+      OUT_BATCH(0);
+   }
    /* Pointer to the constant buffer.  Covered by the set of state flags
     * from gen6_prepare_wm_contants
     */
-   OUT_BATCH(active ? (stage_state->push_const_offset | mocs) : 0);
-   OUT_BATCH(0);
-   OUT_BATCH(0);
-   OUT_BATCH(0);
-   if (brw->gen >= 8) {
+   if (brw->gen >= 9 && active) {
+      OUT_BATCH(0);
+      OUT_BATCH(0);
+      OUT_BATCH(0);
+      OUT_BATCH(0);
+      /* XXX: When using buffers other than 0, you need to specify the
+       * graphics virtual address regardless of INSPM/debug bits
+       */
+      OUT_RELOC64(brw->batch.bo, I915_GEM_DOMAIN_RENDER, 0,
+                  stage_state->push_const_offset);
       OUT_BATCH(0);
       OUT_BATCH(0);
+   } else if (brw->gen>= 8) {
+      OUT_BATCH(active ? (stage_state->push_const_offset | mocs) : 0);
+      OUT_BATCH(0);
+      OUT_BATCH(0);
+      OUT_BATCH(0);
+      OUT_BATCH(0);
+      OUT_BATCH(0);
+      OUT_BATCH(0);
+      OUT_BATCH(0);
+   } else {
+      OUT_BATCH(active ? (stage_state->push_const_offset | mocs) : 0);
+      OUT_BATCH(0);
       OUT_BATCH(0);
       OUT_BATCH(0);
    }