drm/xe/xe2: Updates on XY_CTRL_SURF_COPY_BLT

- The XY_CTRL_SURF_COPY_BLT instruction operating on ccs data expects
size in pages of main memory for which CCS data should be copied.
- The bitfield representing copy size in XY_CTRL_SURF_COPY_BLT has
shifted one bit higher in the instruction.

v2:
 - Fix the num_pages for ccs size calculation.
 - Address nits (Thomas)

v3:
- Use FIELD_PREP and FIELD_FIT instead of shifts and numbers.(Matt)

Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Reviewed-by: Matt Roper <matthew.d.roper@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

drivers/gpu/drm/xe/regs/xe_gpu_commands.h

@@ -11,13 +11,12 @@
 #define XY_CTRL_SURF_COPY_BLT		((2 << 29) | (0x48 << 22) | 3)
 #define   SRC_ACCESS_TYPE_SHIFT		21
 #define   DST_ACCESS_TYPE_SHIFT		20
-#define   CCS_SIZE_MASK			0x3FF
-#define   CCS_SIZE_SHIFT		8
+#define   CCS_SIZE_MASK			GENMASK(17, 8)
+#define   XE2_CCS_SIZE_MASK		GENMASK(18, 9)
 #define   XY_CTRL_SURF_MOCS_MASK	GENMASK(31, 26)
 #define   XE2_XY_CTRL_SURF_MOCS_INDEX_MASK	GENMASK(31, 28)
 #define   NUM_CCS_BYTES_PER_BLOCK	256
 #define   NUM_BYTES_PER_CCS_BYTE(_xe)	(GRAPHICS_VER(_xe) >= 20 ? 512 : 256)
-#define   NUM_CCS_BLKS_PER_XFER		1024
 
 #define XY_FAST_COLOR_BLT_CMD		(2 << 29 | 0x44 << 22)
 #define   XY_FAST_COLOR_BLT_DEPTH_32	(2 << 19)

drivers/gpu/drm/xe/xe_migrate.c

@@ -526,21 +526,30 @@ static void emit_copy_ccs(struct xe_gt *gt, struct xe_bb *bb,
 	struct xe_device *xe = gt_to_xe(gt);
 	u32 *cs = bb->cs + bb->len;
 	u32 num_ccs_blks;
+	u32 num_pages;
+	u32 ccs_copy_size;
 	u32 mocs;
 
-	num_ccs_blks = DIV_ROUND_UP(xe_device_ccs_bytes(gt_to_xe(gt), size),
-				    NUM_CCS_BYTES_PER_BLOCK);
-	xe_gt_assert(gt, num_ccs_blks <= NUM_CCS_BLKS_PER_XFER);
+	if (GRAPHICS_VERx100(xe) >= 2000) {
+		num_pages = DIV_ROUND_UP(size, XE_PAGE_SIZE);
+		xe_gt_assert(gt, FIELD_FIT(XE2_CCS_SIZE_MASK, num_pages - 1));
 
-	if (GRAPHICS_VERx100(xe) >= 2000)
+		ccs_copy_size = REG_FIELD_PREP(XE2_CCS_SIZE_MASK, num_pages - 1);
 		mocs = FIELD_PREP(XE2_XY_CTRL_SURF_MOCS_INDEX_MASK, gt->mocs.uc_index);
-	else
+
+	} else {
+		num_ccs_blks = DIV_ROUND_UP(xe_device_ccs_bytes(gt_to_xe(gt), size),
+					    NUM_CCS_BYTES_PER_BLOCK);
+		xe_gt_assert(gt, FIELD_FIT(CCS_SIZE_MASK, num_ccs_blks - 1));
+
+		ccs_copy_size = REG_FIELD_PREP(CCS_SIZE_MASK, num_ccs_blks - 1);
 		mocs = FIELD_PREP(XY_CTRL_SURF_MOCS_MASK, gt->mocs.uc_index);
+	}
 
 	*cs++ = XY_CTRL_SURF_COPY_BLT |
 		(src_is_indirect ? 0x0 : 0x1) << SRC_ACCESS_TYPE_SHIFT |
 		(dst_is_indirect ? 0x0 : 0x1) << DST_ACCESS_TYPE_SHIFT |
-		((num_ccs_blks - 1) & CCS_SIZE_MASK) << CCS_SIZE_SHIFT;
+		ccs_copy_size;
 	*cs++ = lower_32_bits(src_ofs);
 	*cs++ = upper_32_bits(src_ofs) | mocs;
 	*cs++ = lower_32_bits(dst_ofs);