drm/xe/xe2: Set tile y type in XY_FAST_COPY_BLT to Tile4

Set bits 30 and 31 of XY_FAST_COPY_BLT's dword1 for XeHP and above.

Destination or source being Y-Major is selected on dword0 and there's
nothing to set on dword1. According to the bspec for Xe2,
"Behavior is undefined when programmed the value 0". Also for XeHP,
the only value allowed in those bits is 0b11, not being possible to
select "Legacy Tile-Y" anymore, only the newer Tile4.

So, unconditionally set those bits for graphics IP 12.50 and above.

v2: Reword commit message and extend it to graphics version >= 12.50
    (Matt Roper)

Bspec: 57567
Cc: Matt Roper <matthew.d.roper@intel.com>
Signed-off-by: Haridhar Kalvala <haridhar.kalvala@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Link: https://lore.kernel.org/r/20230929213640.3189912-4-lucas.demarchi@intel.comSigned-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

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

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_VERx100(xe) >= 1250)
+		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);