The previous code would emit a full set of state during the first EmitState on

a new cmdbuf, to ensure that state wasn't lost across UNLOCK/LOCK pairs (in the
case of context switching).  This was rather inefficient.  Instead, after
flushing a cmdbuf, mark the state as needing to be saved on UNLOCK.  Then, at
the beginning of flushing a cmdbuf, if we actually have lost the context, go
back and emit a new cmdbuf with the full set of state, before continuing with
the cmdbuf flush.  Also, remove the dirty/clean atom lists, since atoms are
emitted in a fixed order these days, and go with a simpler single list.

Provides a 14% improvement in ipers performance in my tests, along with other
apps.

1 files changed, 7 insertions, 2 deletions

diff --git a/src/mesa/drivers/dri/r200/r200_ioctl.h b/src/mesa/drivers/dri/r200/r200_ioctl.h
index 1503df70754..57474d7a052 100644
--- a/src/mesa/drivers/dri/r200/r200_ioctl.h
+++ b/src/mesa/drivers/dri/r200/r200_ioctl.h
@@ -117,6 +117,9 @@ extern GLboolean r200IsGartMemory( r200ContextPtr rmesa, const GLvoid *pointer,
 extern GLuint r200GartOffsetFromVirtual( r200ContextPtr rmesa, 
 					 const GLvoid *pointer );
 
+void r200SaveHwState( r200ContextPtr rmesa );
+void r200SetUpAtomList( r200ContextPtr rmesa );
+
 /* ================================================================
  * Helper macros:
  */
@@ -135,7 +138,8 @@ do {						\
 #define R200_STATECHANGE( rmesa, ATOM )			\
 do {								\
    R200_NEWPRIM( rmesa );					\
-   move_to_head( &(rmesa->hw.dirty), &(rmesa->hw.ATOM));	\
+   rmesa->hw.ATOM.dirty = GL_TRUE;				\
+   rmesa->hw.is_dirty = GL_TRUE;				\
 } while (0)
 
 #define R200_DB_STATE( ATOM )			        \
@@ -149,7 +153,8 @@ static __inline int R200_DB_STATECHANGE(
    if (memcmp(atom->cmd, atom->lastcmd, atom->cmd_size*4)) {
       int *tmp;
       R200_NEWPRIM( rmesa );
-      move_to_head( &(rmesa->hw.dirty), atom );
+      atom->dirty = GL_TRUE;
+      rmesa->hw.is_dirty = GL_TRUE;
       tmp = atom->cmd; 
       atom->cmd = atom->lastcmd;
       atom->lastcmd = tmp;