drm/xe/migrate: support MEM_COPY instruction

Make this the default on xe2+ when doing a copy. This has a few
advantages over the exiting copy instruction:

1) It has a special PAGE_COPY mode that claims to be optimised for
page-in/page-out, which is the vast majority of current users.

2) It also has a simple BYTE_COPY mode that supports byte granularity
copying without any restrictions.

With 2) we can now easily skip the bounce buffer flow when copying
buffers with strange sizing/alignment, like for memory_access. But that
is left for the next patch.

v2 (Matt Brost):
- Use device info to check whether device should use the MEM_COPY
path. This should fit better with making this a configfs tunable.
- And with that also keep old path still functional on xe2 for possible
experimentation.
- Add a define for PAGE_COPY page-size.
v3 (Matt Brost):
- Fallback to an actual linear copy for pitch=1.
- Also update NVL.

BSpec: 57561
Signed-off-by: Matthew Auld <[e-mail]>
Cc: Matthew Brost <[e-mail]>
Reviewed-by: Matthew Brost <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

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

···
 #define   XY_FAST_COPY_BLT_D1_DST_TILE4	REG_BIT(30)
 #define   XE2_XY_FAST_COPY_BLT_MOCS_INDEX_MASK	GENMASK(23, 20)
 
+#define MEM_COPY_CMD (2 << 29 | 0x5a << 22 | 0x8)
+#define   MEM_COPY_PAGE_COPY_MODE REG_BIT(19)
+#define   MEM_COPY_MATRIX_COPY REG_BIT(17)
+#define   MEM_COPY_SRC_MOCS_INDEX_MASK	GENMASK(31, 28)
+#define   MEM_COPY_DST_MOCS_INDEX_MASK	GENMASK(6, 3)
+
 #define	PVC_MEM_SET_CMD		(2 << 29 | 0x5b << 22)
 #define   PVC_MEM_SET_CMD_LEN_DW	7
 #define   PVC_MEM_SET_MATRIX		REG_BIT(17)

drivers/gpu/drm/xe/xe_device_types.h

···
 		 * pcode mailbox commands.
 		 */
 		u8 has_mbx_power_limits:1;
+		/** @info.has_mem_copy_instr: Device supports MEM_COPY instruction */
+		u8 has_mem_copy_instr:1;
 		/** @info.has_pxp: Device has PXP support */
 		u8 has_pxp:1;
 		/** @info.has_range_tlb_inval: Has range based TLB invalidations */

drivers/gpu/drm/xe/xe_migrate.c

···
 }
 
 #define EMIT_COPY_DW 10
-static void emit_copy(struct xe_gt *gt, struct xe_bb *bb,
-		      u64 src_ofs, u64 dst_ofs, unsigned int size,
-		      unsigned int pitch)
+static void emit_xy_fast_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);
 	u32 mocs = 0;
···
 	bb->cs[bb->len++] = pitch | mocs;
 	bb->cs[bb->len++] = lower_32_bits(src_ofs);
 	bb->cs[bb->len++] = upper_32_bits(src_ofs);
+}
+
+#define PAGE_COPY_MODE_PS SZ_256 /* hw uses 256 bytes as the page-size */
+static void emit_mem_copy(struct xe_gt *gt, struct xe_bb *bb, u64 src_ofs,
+			  u64 dst_ofs, unsigned int size, unsigned int pitch)
+{
+	u32 mode, copy_type, width;
+
+	xe_gt_assert(gt, IS_ALIGNED(size, pitch));
+	xe_gt_assert(gt, pitch <= U16_MAX);
+	xe_gt_assert(gt, pitch);
+	xe_gt_assert(gt, size);
+
+	if (IS_ALIGNED(size, PAGE_COPY_MODE_PS) &&
+	    IS_ALIGNED(lower_32_bits(src_ofs), PAGE_COPY_MODE_PS) &&
+	    IS_ALIGNED(lower_32_bits(dst_ofs), PAGE_COPY_MODE_PS)) {
+		mode = MEM_COPY_PAGE_COPY_MODE;
+		copy_type = 0; /* linear copy */
+		width = size / PAGE_COPY_MODE_PS;
+	} else if (pitch > 1) {
+		xe_gt_assert(gt, size / pitch <= U16_MAX);
+		mode = 0; /* BYTE_COPY */
+		copy_type = MEM_COPY_MATRIX_COPY;
+		width = pitch;
+	} else {
+		mode = 0; /* BYTE_COPY */
+		copy_type = 0; /* linear copy */
+		width = size;
+	}
+
+	xe_gt_assert(gt, width <= U16_MAX);
+
+	bb->cs[bb->len++] = MEM_COPY_CMD | mode | copy_type;
+	bb->cs[bb->len++] = width - 1;
+	bb->cs[bb->len++] = size / pitch - 1; /* ignored by hw for page-copy/linear above */
+	bb->cs[bb->len++] = pitch - 1;
+	bb->cs[bb->len++] = pitch - 1;
+	bb->cs[bb->len++] = lower_32_bits(src_ofs);
+	bb->cs[bb->len++] = upper_32_bits(src_ofs);
+	bb->cs[bb->len++] = lower_32_bits(dst_ofs);
+	bb->cs[bb->len++] = upper_32_bits(dst_ofs);
+	bb->cs[bb->len++] = FIELD_PREP(MEM_COPY_SRC_MOCS_INDEX_MASK, gt->mocs.uc_index) |
+			    FIELD_PREP(MEM_COPY_DST_MOCS_INDEX_MASK, gt->mocs.uc_index);
+}
+
+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);
+
+	if (xe->info.has_mem_copy_instr)
+		emit_mem_copy(gt, bb, src_ofs, dst_ofs, size, pitch);
+	else
+		emit_xy_fast_copy(gt, bb, src_ofs, dst_ofs, size, pitch);
 }
 
 static u64 xe_migrate_batch_base(struct xe_migrate *m, bool usm)

drivers/gpu/drm/xe/xe_pci.c

···
 	.has_display = true,
 	.has_flat_ccs = 1,
 	.has_pxp = true,
+	.has_mem_copy_instr = true,
 	.max_gt_per_tile = 2,
 	.needs_scratch = true,
 	.va_bits = 48,
···
 	.has_heci_cscfi = 1,
 	.has_late_bind = true,
 	.has_sriov = true,
+	.has_mem_copy_instr = true,
 	.max_gt_per_tile = 2,
 	.needs_scratch = true,
 	.subplatforms = (const struct xe_subplatform_desc[]) {
···
 	.has_display = true,
 	.has_flat_ccs = 1,
 	.has_sriov = true,
+	.has_mem_copy_instr = true,
 	.max_gt_per_tile = 2,
 	.needs_scratch = true,
 	.needs_shared_vf_gt_wq = true,
···
 	.dma_mask_size = 46,
 	.has_display = true,
 	.has_flat_ccs = 1,
+	.has_mem_copy_instr = true,
 	.max_gt_per_tile = 2,
 	.require_force_probe = true,
 	.va_bits = 48,
···
 	xe->info.has_pxp = desc->has_pxp;
 	xe->info.has_sriov = xe_configfs_primary_gt_allowed(to_pci_dev(xe->drm.dev)) &&
 		desc->has_sriov;
+	xe->info.has_mem_copy_instr = desc->has_mem_copy_instr;
 	xe->info.skip_guc_pc = desc->skip_guc_pc;
 	xe->info.skip_mtcfg = desc->skip_mtcfg;
 	xe->info.skip_pcode = desc->skip_pcode;

drivers/gpu/drm/xe/xe_pci_types.h

···
 	u8 has_late_bind:1;
 	u8 has_llc:1;
 	u8 has_mbx_power_limits:1;
+	u8 has_mem_copy_instr:1;
 	u8 has_pxp:1;
 	u8 has_sriov:1;
 	u8 needs_scratch:1;