drm: radeon add a tcl state flush before accessing tcl vector space

Do a tcl state flush before accessing tcl vector space. This fixes some
more problems with flickering (bug #6637). drm may not be appropriate
place for this, since doing that flush there might both be overkill and
insufficient in some cases. However, it's hard to figure out when that
flush is needed, so this has to suffice. There does not seem to be a
performance penalty associated with it.

From: Roland Scheidegger (DRM CVS)
Signed-off-by: Dave Airlie <airlied@linux.ie>

drivers/char/drm/radeon_drv.h

@@ -38,7 +38,7 @@
 
 #define DRIVER_NAME		"radeon"
 #define DRIVER_DESC		"ATI Radeon"
-#define DRIVER_DATE		"20060225"
+#define DRIVER_DATE		"20060519"
 
 /* Interface history:
  *
@@ -884,6 +884,8 @@ extern int r300_do_cp_cmdbuf(drm_device_t * dev, DRMFILE filp,
 #define RADEON_PP_CUBIC_OFFSET_T1_0         0x1e00
 #define RADEON_PP_CUBIC_OFFSET_T2_0         0x1e14
 
+#define RADEON_SE_TCL_STATE_FLUSH           0x2284
+
 #define SE_VAP_CNTL__TCL_ENA_MASK                          0x00000001
 #define SE_VAP_CNTL__FORCE_W_TO_ONE_MASK                   0x00010000
 #define SE_VAP_CNTL__VF_MAX_VTX_NUM__SHIFT                 0x00000012

drivers/char/drm/radeon_state.c

@@ -2595,7 +2595,8 @@ static __inline__ int radeon_emit_vectors(drm_radeon_private_t *dev_priv,
 	int stride = header.vectors.stride;
 	RING_LOCALS;
 
-	BEGIN_RING(3 + sz);
+	BEGIN_RING(5 + sz);
+	OUT_RING_REG(RADEON_SE_TCL_STATE_FLUSH, 0);
 	OUT_RING(CP_PACKET0(RADEON_SE_TCL_VECTOR_INDX_REG, 0));
 	OUT_RING(start | (stride << RADEON_VEC_INDX_OCTWORD_STRIDE_SHIFT));
 	OUT_RING(CP_PACKET0_TABLE(RADEON_SE_TCL_VECTOR_DATA_REG, (sz - 1)));