radeonsi: use TC L2 for CP DMA operations with shader resources on CIK

So that TC L2 doesn't need to be flushed.

The only problem is with index buffers, which don't use TC.
A simple solution is added that flushes TC L2 before a draw call (TC_L2_dirty).

Reviewed-by: Michel Dänzer <[email protected]>

1 files changed, 12 insertions, 0 deletions

diff --git a/src/gallium/drivers/radeon/r600_pipe_common.h b/src/gallium/drivers/radeon/r600_pipe_common.h
index a9416b686ed..60b8faeb29b 100644
--- a/src/gallium/drivers/radeon/r600_pipe_common.h
+++ b/src/gallium/drivers/radeon/r600_pipe_common.h
@@ -138,6 +138,18 @@ struct r600_resource {
 	 * the unsynchronized map flag and expect the driver to figure it out.
          */
 	struct util_range		valid_buffer_range;
+
+	/* For buffers only. This indicates that a write operation has been
+	 * performed by TC L2, but the cache hasn't been flushed.
+	 * Any hw block which doesn't use or bypasses TC L2 should check this
+	 * flag and flush the cache before using the buffer.
+	 *
+	 * For example, TC L2 must be flushed if a buffer which has been
+	 * modified by a shader store instruction is about to be used as
+	 * an index buffer. The reason is that VGT DMA index fetching doesn't
+	 * use TC L2.
+	 */
+	bool				TC_L2_dirty;
 };
 
 struct r600_transfer {