i965: Upload invariant state once at the start of the batch on Gen4-5.

We want to emit invariant state at the start of a render batch.  In the
past, this more or less happened: a new batch flagged BRW_NEW_CONTEXT
(because we don't have hardware contexts), which triggered the
brw_invariant_state atom.  So, it would be emitted before any 3D
drawing.  (Technically, there might be some BLT commands in the batch
because Gen4-5 have a single combined render/BLT ring, but that should
be harmless).

With the advent of BLORP, this broke.  The first item in a batch might
be a BLORP operation, which bypasses the normal draw upload path.  So,
we need to ensure invariant state happens first.  To do that, we just
upload it when creating a new batch.  On Gen6+ we'd need to worry about
whether it's a RENDER or BLT batch, but because we have a combined ring,
this approach should work fine on Gen4-5.

Seems to fix GPU hangs when playing hardware accelerated video with
mpv -hwdec=vaapi on Ironlake.

Cc: [email protected]
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103529
Reviewed-by: Jason Ekstrand <[email protected]>

4 files changed, 3 insertions, 13 deletions

diff --git a/src/mesa/drivers/dri/i965/brw_misc_state.c b/src/mesa/drivers/dri/i965/brw_misc_state.c
index fd96485d574..94d5c9783db 100644
--- a/src/mesa/drivers/dri/i965/brw_misc_state.c
+++ b/src/mesa/drivers/dri/i965/brw_misc_state.c
@@ -560,15 +560,6 @@ brw_upload_invariant_state(struct brw_context *brw)
    ADVANCE_BATCH();
 }
 
-const struct brw_tracked_state brw_invariant_state = {
-   .dirty = {
-      .mesa = 0,
-      .brw = BRW_NEW_BLORP |
-             BRW_NEW_CONTEXT,
-   },
-   .emit = brw_upload_invariant_state
-};
-
 /**
  * Define the base addresses which some state is referenced from.
  *
diff --git a/src/mesa/drivers/dri/i965/brw_state.h b/src/mesa/drivers/dri/i965/brw_state.h
index cf13eca3438..ad508950f78 100644
--- a/src/mesa/drivers/dri/i965/brw_state.h
+++ b/src/mesa/drivers/dri/i965/brw_state.h
@@ -51,7 +51,6 @@ extern const struct brw_tracked_state brw_wm_pull_constants;
 extern const struct brw_tracked_state brw_cs_pull_constants;
 extern const struct brw_tracked_state brw_constant_buffer;
 extern const struct brw_tracked_state brw_curbe_offsets;
-extern const struct brw_tracked_state brw_invariant_state;
 extern const struct brw_tracked_state brw_binding_table_pointers;
 extern const struct brw_tracked_state brw_depthbuffer;
 extern const struct brw_tracked_state brw_recalculate_urb_fence;
diff --git a/src/mesa/drivers/dri/i965/genX_state_upload.c b/src/mesa/drivers/dri/i965/genX_state_upload.c
index d4b0de850c9..112f48181b0 100644
--- a/src/mesa/drivers/dri/i965/genX_state_upload.c
+++ b/src/mesa/drivers/dri/i965/genX_state_upload.c
@@ -5366,8 +5366,6 @@ genX(init_atoms)(struct brw_context *brw)
 
       /* Command packets:
        */
-      &brw_invariant_state,
-
       &brw_binding_table_pointers,
       &genX(blend_constant_color),
 
diff --git a/src/mesa/drivers/dri/i965/intel_batchbuffer.c b/src/mesa/drivers/dri/i965/intel_batchbuffer.c
index bbe13f34cef..3412b1d0a5f 100644
--- a/src/mesa/drivers/dri/i965/intel_batchbuffer.c
+++ b/src/mesa/drivers/dri/i965/intel_batchbuffer.c
@@ -601,8 +601,10 @@ brw_new_batch(struct brw_context *brw)
     * would otherwise be stored in the context (which for all intents and
     * purposes means everything).
     */
-   if (brw->hw_ctx == 0)
+   if (brw->hw_ctx == 0) {
       brw->ctx.NewDriverState |= BRW_NEW_CONTEXT;
+      brw_upload_invariant_state(brw);
+   }
 
    brw->ctx.NewDriverState |= BRW_NEW_BATCH;