drm/xe/xe2: Update emit_pte to use compression enabled PAT index

For indirect accessed buffer use compression enabled PAT index.

v2:
 - Fix parameter name.

v3:
 - use a relevant define instead of fix number.

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

4 files changed, 18 insertions, 7 deletions

diff --git a/drivers/gpu/drm/xe/tests/xe_migrate.c b/drivers/gpu/drm/xe/tests/xe_migrate.c
index 47fcd6e6b777..d6c23441632a 100644
--- a/drivers/gpu/drm/xe/tests/xe_migrate.c
+++ b/drivers/gpu/drm/xe/tests/xe_migrate.c
@@ -330,7 +330,7 @@ static void xe_migrate_sanity_test(struct xe_migrate *m, struct kunit *test)
 	else
 		xe_res_first_sg(xe_bo_sg(pt), 0, pt->size, &src_it);
 
-	emit_pte(m, bb, NUM_KERNEL_PDE - 1, xe_bo_is_vram(pt),
+	emit_pte(m, bb, NUM_KERNEL_PDE - 1, xe_bo_is_vram(pt), false,
 		 &src_it, XE_PAGE_SIZE, pt);
 
 	run_sanity_job(m, xe, bb, bb->len, "Writing PTE for our fake PT", test);
diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
index 40f49e47d79e..48ada083d0b3 100644
--- a/drivers/gpu/drm/xe/xe_migrate.c
+++ b/drivers/gpu/drm/xe/xe_migrate.c
@@ -425,15 +425,24 @@ static u32 pte_update_size(struct xe_migrate *m,
 
 static void emit_pte(struct xe_migrate *m,
 		     struct xe_bb *bb, u32 at_pt,
-		     bool is_vram,
+		     bool is_vram, bool is_comp_pte,
 		     struct xe_res_cursor *cur,
 		     u32 size, struct xe_bo *bo)
 {
-	u16 pat_index = tile_to_xe(m->tile)->pat.idx[XE_CACHE_WB];
+	struct xe_device *xe = tile_to_xe(m->tile);
+
+	u16 pat_index;
 	u32 ptes;
 	u64 ofs = at_pt * XE_PAGE_SIZE;
 	u64 cur_ofs;
 
+	/* Indirect access needs compression enabled uncached PAT index */
+	if (GRAPHICS_VERx100(xe) >= 2000)
+		pat_index = is_comp_pte ? xe->pat.idx[XE_CACHE_NONE_COMPRESSION] :
+					  xe->pat.idx[XE_CACHE_NONE];
+	else
+		pat_index = xe->pat.idx[XE_CACHE_WB];
+
 	/*
 	 * FIXME: Emitting VRAM PTEs to L0 PTs is forbidden. Currently
 	 * we're only emitting VRAM PTEs during sanity tests, so when
@@ -720,19 +729,19 @@ struct dma_fence *xe_migrate_copy(struct xe_migrate *m,
 		}
 
 		if (!src_is_vram)
-			emit_pte(m, bb, src_L0_pt, src_is_vram, &src_it, src_L0,
+			emit_pte(m, bb, src_L0_pt, src_is_vram, true, &src_it, src_L0,
 				 src_bo);
 		else
 			xe_res_next(&src_it, src_L0);
 
 		if (!dst_is_vram)
-			emit_pte(m, bb, dst_L0_pt, dst_is_vram, &dst_it, src_L0,
+			emit_pte(m, bb, dst_L0_pt, dst_is_vram, true, &dst_it, src_L0,
 				 dst_bo);
 		else
 			xe_res_next(&dst_it, src_L0);
 
 		if (copy_system_ccs)
-			emit_pte(m, bb, ccs_pt, false, &ccs_it, ccs_size, src_bo);
+			emit_pte(m, bb, ccs_pt, false, false, &ccs_it, ccs_size, src_bo);
 
 		bb->cs[bb->len++] = MI_BATCH_BUFFER_END;
 		update_idx = bb->len;
@@ -965,7 +974,7 @@ struct dma_fence *xe_migrate_clear(struct xe_migrate *m,
 
 		/* Preemption is enabled again by the ring ops. */
 		if (!clear_vram) {
-			emit_pte(m, bb, clear_L0_pt, clear_vram, &src_it, clear_L0,
+			emit_pte(m, bb, clear_L0_pt, clear_vram, true, &src_it, clear_L0,
 				 bo);
 		} else {
 			xe_res_next(&src_it, clear_L0);
diff --git a/drivers/gpu/drm/xe/xe_pat.c b/drivers/gpu/drm/xe/xe_pat.c
index 1892ff81086f..1ff6bc79e7d4 100644
--- a/drivers/gpu/drm/xe/xe_pat.c
+++ b/drivers/gpu/drm/xe/xe_pat.c
@@ -387,6 +387,7 @@ void xe_pat_init_early(struct xe_device *xe)
 		xe->pat.idx[XE_CACHE_NONE] = 3;
 		xe->pat.idx[XE_CACHE_WT] = 15;
 		xe->pat.idx[XE_CACHE_WB] = 2;
+		xe->pat.idx[XE_CACHE_NONE_COMPRESSION] = 12; /*Applicable on xe2 and beyond */
 	} else if (xe->info.platform == XE_METEORLAKE) {
 		xe->pat.ops = &xelpg_pat_ops;
 		xe->pat.table = xelpg_pat_table;
diff --git a/drivers/gpu/drm/xe/xe_pt_types.h b/drivers/gpu/drm/xe/xe_pt_types.h
index 82cbf1ef8e57..cee70cb0f014 100644
--- a/drivers/gpu/drm/xe/xe_pt_types.h
+++ b/drivers/gpu/drm/xe/xe_pt_types.h
@@ -18,6 +18,7 @@ enum xe_cache_level {
 	XE_CACHE_NONE,
 	XE_CACHE_WT,
 	XE_CACHE_WB,
+	XE_CACHE_NONE_COMPRESSION, /*UC + COH_NONE + COMPRESSION */
 	__XE_CACHE_LEVEL_COUNT,
 };