drm/xe/migrate: Remove unneeded emit_pte() when copying CCS only

In xe_migrate_copy(), when copy_only_ccs is true, we only need two
emit_pte() calls one for the BO and one for the raw CCS storage.
However, the current implementation issues three emit_pte() calls,
resulting in an unnecessary PTE programming job.

This fix removes the redundant emit_pte() call to avoid programming
the same PTEs twice and reducing overhead during CCS-only migration.

v2: Preserve correct behavior on DG2, which requires both CCS and
page copies.

Signed-off-by: Sanjay Yadav <sanjay.kumar.yadav@intel.com>
Suggested-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Link: https://lore.kernel.org/r/20250904161423.2448727-1-sanjay.kumar.yadav@intel.com

diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 861d9d0633d198f0b2a6da63fedc9c38b9599605..3f0c8832120f33d6a2b61db7eb53f604453d3c15 100644 (file)
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -842,11 +842,15 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
                batch_size += pte_update_size(m, pte_flags, src, &src_it, &src_L0,
                                              &src_L0_ofs, &src_L0_pt, 0, 0,
                                              avail_pts);
-
-               pte_flags = dst_is_vram ? PTE_UPDATE_FLAG_IS_VRAM : 0;
-               batch_size += pte_update_size(m, pte_flags, dst, &dst_it, &src_L0,
-                                             &dst_L0_ofs, &dst_L0_pt, 0,
-                                             avail_pts, avail_pts);
+               if (copy_only_ccs) {
+                       dst_L0_ofs = src_L0_ofs;
+               } else {
+                       pte_flags = dst_is_vram ? PTE_UPDATE_FLAG_IS_VRAM : 0;
+                       batch_size += pte_update_size(m, pte_flags, dst,
+                                                     &dst_it, &src_L0,
+                                                     &dst_L0_ofs, &dst_L0_pt,
+                                                     0, avail_pts, avail_pts);
+               }
 
                if (copy_system_ccs) {
                        xe_assert(xe, type_device);
@@ -876,7 +880,7 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 
                if (dst_is_vram && xe_migrate_allow_identity(src_L0, &dst_it))
                        xe_res_next(&dst_it, src_L0);
-               else
+               else if (!copy_only_ccs)
                        emit_pte(m, bb, dst_L0_pt, dst_is_vram, copy_system_ccs,
                                 &dst_it, src_L0, dst);