drm/r100/kms: Emit cache flush to the end of command buffer. (v2)

Cache flush is required in case CPU is accessing rendered data.

This fixes glean/readPixSanity test case and random rendering
errors in sauerbraten and warzone2100.

v2 Fix comment ordering in r100_fence_ring_emit and remove extra
   defines added in first version.
Signed-off-by: Pauli Nieminen <suokkos@gmail.com>
Reviewed-by: Jerome Glisse <jglisse@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>

drivers/gpu/drm/radeon/r100.c

@@ -354,11 +354,17 @@ u32 r100_get_vblank_counter(struct radeon_device *rdev, int crtc)
 		return RREG32(RADEON_CRTC2_CRNT_FRAME);
 }
 
+/* Who ever call radeon_fence_emit should call ring_lock and ask
+ * for enough space (today caller are ib schedule and buffer move) */
 void r100_fence_ring_emit(struct radeon_device *rdev,
 			  struct radeon_fence *fence)
 {
-	/* Who ever call radeon_fence_emit should call ring_lock and ask
-	 * for enough space (today caller are ib schedule and buffer move) */
+	/* We have to make sure that caches are flushed before
+	 * CPU might read something from VRAM. */
+	radeon_ring_write(rdev, PACKET0(RADEON_RB3D_DSTCACHE_CTLSTAT, 0));
+	radeon_ring_write(rdev, RADEON_RB3D_DC_FLUSH_ALL);
+	radeon_ring_write(rdev, PACKET0(RADEON_RB3D_ZCACHE_CTLSTAT, 0));
+	radeon_ring_write(rdev, RADEON_RB3D_ZC_FLUSH_ALL);
 	/* Wait until IDLE & CLEAN */
 	radeon_ring_write(rdev, PACKET0(0x1720, 0));
 	radeon_ring_write(rdev, (1 << 16) | (1 << 17));