r600g: use CP DMA for buffer clears on evergreen+

Lighter weight then using streamout.  Only evergreen
and newer asics support embedded data as src with
CP DMA.

Reviewed-by: Jerome Glisse <[email protected]>
Reviewed-by: Marek Olšák <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>

1 files changed, 42 insertions, 0 deletions

diff --git a/src/gallium/drivers/r600/evergreend.h b/src/gallium/drivers/r600/evergreend.h
index 53b68a44c9d..5d72432e630 100644
--- a/src/gallium/drivers/r600/evergreend.h
+++ b/src/gallium/drivers/r600/evergreend.h
@@ -118,6 +118,48 @@
 #define PKT3_PREDICATE(x)               (((x) >> 0) & 0x1)
 #define PKT0(index, count) (PKT_TYPE_S(0) | PKT0_BASE_INDEX_S(index) | PKT_COUNT_S(count))
 
+#define PKT3_CP_DMA					0x41
+/* 1. header
+ * 2. SRC_ADDR_LO [31:0] or DATA [31:0]
+ * 3. CP_SYNC [31] | SRC_SEL [30:29] | ENGINE [27] | DST_SEL [21:20] | SRC_ADDR_HI [7:0]
+ * 4. DST_ADDR_LO [31:0]
+ * 5. DST_ADDR_HI [7:0]
+ * 6. COMMAND [29:22] | BYTE_COUNT [20:0]
+ */
+#define PKT3_CP_DMA_CP_SYNC       (1 << 31)
+#define PKT3_CP_DMA_SRC_SEL(x)       ((x) << 29)
+/* 0 - SRC_ADDR
+ * 1 - GDS (program SAS to 1 as well)
+ * 2 - DATA
+ */
+#define PKT3_CP_DMA_DST_SEL(x)       ((x) << 20)
+/* 0 - DST_ADDR
+ * 1 - GDS (program DAS to 1 as well)
+ */
+/* COMMAND */
+#define PKT3_CP_DMA_CMD_SRC_SWAP(x) ((x) << 23)
+/* 0 - none
+ * 1 - 8 in 16
+ * 2 - 8 in 32
+ * 3 - 8 in 64
+ */
+#define PKT3_CP_DMA_CMD_DST_SWAP(x) ((x) << 24)
+/* 0 - none
+ * 1 - 8 in 16
+ * 2 - 8 in 32
+ * 3 - 8 in 64
+ */
+#define PKT3_CP_DMA_CMD_SAS       (1 << 26)
+/* 0 - memory
+ * 1 - register
+ */
+#define PKT3_CP_DMA_CMD_DAS       (1 << 27)
+/* 0 - memory
+ * 1 - register
+ */
+#define PKT3_CP_DMA_CMD_SAIC      (1 << 28)
+#define PKT3_CP_DMA_CMD_DAIC      (1 << 29)
+
 /* Registers */
 #define R_0084FC_CP_STRMOUT_CNTL		     0x000084FC
 #define   S_0084FC_OFFSET_UPDATE_DONE(x)		(((x) & 0x1) << 0)