[Mesa-dev] [PATCH 2/2] mesa: Only flag _NEW_TEXTURE on texture updates when a texture changes.

[Eric Anholt]

There are three reasons left for this function flagging it:
Re-computing completeness (and therefore the number of levels),
binding a new current texture object, or you're doing some sort of
fixed function (and nobody cares).  For other cases, like rebinding a
shader, we no longer trigger the driver recomputing every piece of
texture state.

Improves a VS state change microbenchmark by 14.8284% +/- 1.02% (n=10)
on gen7.  On the other hand, it causes GPU hangs on nexuiz.  Any clue
why this might be insufficient?
---
 src/mesa/main/texstate.c |   34 ++++++++++++++++++++++++++--------
 1 files changed, 26 insertions(+), 8 deletions(-)

diff --git a/src/mesa/main/texstate.c b/src/mesa/main/texstate.c
index 2dbf530..86b8b3d 100644
--- a/src/mesa/main/texstate.c
+++ b/src/mesa/main/texstate.c
@@ -577,7 +577,6 @@ update_texture_state( struct gl_context *ctx )
     */
 
    /* TODO: only set this if there are actual changes */
-   ctx->NewState |= _NEW_TEXTURE;
 
    /*
     * Update texture unit state.
@@ -588,6 +587,7 @@ update_texture_state( struct gl_context *ctx )
       GLbitfield enabledFragTargets = 0x0;
       GLbitfield enabledTargets = 0x0;
       GLuint texIndex;
+      struct gl_texture_object *oldObj = texUnit->_Current;
 
       /* Get the bitmask of texture target enables.
        * enableBits will be a mask of the TEXTURE_*_BIT flags indicating
@@ -609,10 +609,18 @@ update_texture_state( struct gl_context *ctx )
 
       enabledTargets = enabledVertTargets | enabledFragTargets;
 
+      /* This is not flagged with _NEW_TEXTURE, because the test for changing of
+       * the _Current texture object will cover every case where _ReallyEnabled
+       * could have changed.
+       */
       texUnit->_ReallyEnabled = 0x0;
 
       if (enabledTargets == 0x0) {
          /* neither vertex nor fragment processing uses this unit */
+	 if (texUnit->_ReallyEnabled) {
+	    ctx->NewState |= _NEW_TEXTURE;
+	    texUnit->_ReallyEnabled = 0x0;
+	 }
          continue;
       }
 
@@ -626,6 +634,10 @@ update_texture_state( struct gl_context *ctx )
          if (enabledTargets & (1 << texIndex)) {
             struct gl_texture_object *texObj = texUnit->CurrentTex[texIndex];
             if (!texObj->_Complete) {
+	       /* While _Complete is only consumed by us, this call also updates
+		  _MaxLevel, which drivers do need to see.
+		*/
+	       ctx->NewState |= _NEW_TEXTURE;
                _mesa_test_texobj_completeness(ctx, texObj);
             }
             if (texObj->_Complete) {
@@ -652,22 +664,26 @@ update_texture_state( struct gl_context *ctx )
             _mesa_reference_texobj(&texUnit->_Current, texObj);
             texUnit->_ReallyEnabled = 1 << texTarget;
          }
-         else {
-            /* fixed-function: texture unit is really disabled */
-            continue;
-         }
       }
+
+      if (oldObj != texUnit->_Current)
+	 ctx->NewState |= _NEW_TEXTURE;
    }
 
 
    /* Determine which texture coordinate sets are actually needed */
    if (fprog) {
       const GLuint coordMask = (1 << MAX_TEXTURE_COORD_UNITS) - 1;
+      GLuint new_coord_units = ((fprog->InputsRead >> FRAG_ATTRIB_TEX0) &
+				coordMask);
       /* Note that this gets consumed by update_ffvs_texture_state(). */
-      ctx->Texture._EnabledCoordUnits
-         = (fprog->InputsRead >> FRAG_ATTRIB_TEX0) & coordMask;
+      if (ctx->Texture._EnabledCoordUnits != new_coord_units) {
+	 ctx->NewState |= _NEW_TEXTURE;
+	 ctx->Texture._EnabledCoordUnits = new_coord_units;
+      }
    }
    else {
+      ctx->NewState |= _NEW_TEXTURE;
       update_fffs_texture_state(ctx);
    }
 
@@ -675,8 +691,10 @@ update_texture_state( struct gl_context *ctx )
     * program.  Those state flags are only used in the case of fixed function
     * vertex shading, in the tnl pipeline or ff_vertex_shader.
     */
-   if (!vprog)
+   if (!vprog) {
+      ctx->NewState |= _NEW_TEXTURE;
       update_ffvs_texture_state(ctx);
+   }
 }
 
 
-- 
1.7.9