[Intel-xe] [PATCH 3/4] drm/xe/xe2: Set tile y bits in XY_FAST_COPY_BLT

[Lucas De Marchi]

From: Haridhar Kalvala <haridhar.kalvala at intel.com>

Set bits 30 and 31 of XY_FAST_COPY_BLT for xe2 platforms. Its setting
Tile-Y for source and destination.

Bspec: 57567
Cc: Matt Roper <matthew.d.roper at intel.com>
Signed-off-by: Haridhar Kalvala <haridhar.kalvala at intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi at intel.com>
---
 drivers/gpu/drm/xe/regs/xe_gpu_commands.h | 2 ++
 drivers/gpu/drm/xe/xe_migrate.c           | 9 ++++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/regs/xe_gpu_commands.h b/drivers/gpu/drm/xe/regs/xe_gpu_commands.h
index 1fdf2e4f1c9f..cc7b56763f10 100644
--- a/drivers/gpu/drm/xe/regs/xe_gpu_commands.h
+++ b/drivers/gpu/drm/xe/regs/xe_gpu_commands.h
@@ -57,6 +57,8 @@
 
 #define XY_FAST_COPY_BLT_CMD		(2 << 29 | 0x42 << 22)
 #define   XY_FAST_COPY_BLT_DEPTH_32	(3<<24)
+#define   XY_FAST_COPY_BLT_D1_SRC_TILE4	REG_BIT(31)
+#define   XY_FAST_COPY_BLT_D1_DST_TILE4	REG_BIT(30)
 
 #define	PVC_MEM_SET_CMD		(2 << 29 | 0x5b << 22)
 #define   PVC_MEM_SET_CMD_LEN_DW	7
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 2e6ce2daf414..b682d34bc1e5 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -543,12 +543,19 @@ static void emit_copy(struct xe_gt *gt, struct xe_bb *bb,
 		      u64 src_ofs, u64 dst_ofs, unsigned int size,
 		      unsigned int pitch)
 {
+	struct xe_device *xe = gt_to_xe(gt);
+
 	xe_gt_assert(gt, size / pitch <= S16_MAX);
 	xe_gt_assert(gt, pitch / 4 <= S16_MAX);
 	xe_gt_assert(gt, pitch <= U16_MAX);
 
 	bb->cs[bb->len++] = XY_FAST_COPY_BLT_CMD | (10 - 2);
-	bb->cs[bb->len++] = XY_FAST_COPY_BLT_DEPTH_32 | pitch;
+	if (GRAPHICS_VER(xe) >= 20)
+		bb->cs[bb->len++] = XY_FAST_COPY_BLT_DEPTH_32 | pitch |
+				    XY_FAST_COPY_BLT_D1_SRC_TILE4 |
+				    XY_FAST_COPY_BLT_D1_DST_TILE4;
+	else
+		bb->cs[bb->len++] = XY_FAST_COPY_BLT_DEPTH_32 | pitch;
 	bb->cs[bb->len++] = 0;
 	bb->cs[bb->len++] = (size / pitch) << 16 | pitch / 4;
 	bb->cs[bb->len++] = lower_32_bits(dst_ofs);
-- 
2.40.1