drm/xe: Simplify GuC early initialization

Add a 2-stage GuC init. An early one for everything that is needed
for VF, and a full one that loads GuC and is allowed to do allocations.

Link: https://lore.kernel.org/r/20250619104858.418440-16-dev@lankhorst.se
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>

drivers/gpu/drm/xe/xe_gt.c

@@ -426,7 +426,7 @@ int xe_gt_init_early(struct xe_gt *gt)
 	 */
 	xe_gt_mmio_init(gt);
 
-	return 0;
+	return xe_uc_init_noalloc(&gt->uc);
 }
 
 static void dump_pat_on_error(struct xe_gt *gt)

drivers/gpu/drm/xe/xe_guc.c

@@ -627,21 +627,11 @@ static int xe_guc_realloc_post_hwconfig(struct xe_guc *guc)
 	return 0;
 }
 
-static int vf_guc_init(struct xe_guc *guc)
+static int vf_guc_init_noalloc(struct xe_guc *guc)
 {
 	struct xe_gt *gt = guc_to_gt(guc);
 	int err;
 
-	xe_guc_comm_init_early(guc);
-
-	err = xe_guc_ct_init(&guc->ct);
-	if (err)
-		return err;
-
-	err = xe_guc_relay_init(&guc->relay);
-	if (err)
-		return err;
-
 	err = xe_gt_sriov_vf_bootstrap(gt);
 	if (err)
 		return err;
@@ -653,6 +643,35 @@ static int vf_guc_init(struct xe_guc *guc)
 	return 0;
 }
 
+int xe_guc_init_noalloc(struct xe_guc *guc)
+{
+	struct xe_device *xe = guc_to_xe(guc);
+	struct xe_gt *gt = guc_to_gt(guc);
+	int ret;
+
+	xe_guc_comm_init_early(guc);
+
+	ret = xe_guc_ct_init_noalloc(&guc->ct);
+	if (ret)
+		goto out;
+
+	ret = xe_guc_relay_init(&guc->relay);
+	if (ret)
+		goto out;
+
+	if (IS_SRIOV_VF(xe)) {
+		ret = vf_guc_init_noalloc(guc);
+		if (ret)
+			goto out;
+	}
+
+	return 0;
+
+out:
+	xe_gt_err(gt, "GuC init failed with %pe\n", ERR_PTR(ret));
+	return ret;
+}
+
 int xe_guc_init(struct xe_guc *guc)
 {
 	struct xe_device *xe = guc_to_xe(guc);
@@ -662,13 +681,13 @@ int xe_guc_init(struct xe_guc *guc)
 	guc->fw.type = XE_UC_FW_TYPE_GUC;
 	ret = xe_uc_fw_init(&guc->fw);
 	if (ret)
-		goto out;
+		return ret;
 
 	if (!xe_uc_fw_is_enabled(&guc->fw))
 		return 0;
 
 	if (IS_SRIOV_VF(xe)) {
-		ret = vf_guc_init(guc);
+		ret = xe_guc_ct_init(&guc->ct);
 		if (ret)
 			goto out;
 		return 0;
@@ -690,10 +709,6 @@ int xe_guc_init(struct xe_guc *guc)
 	if (ret)
 		goto out;
 
-	ret = xe_guc_relay_init(&guc->relay);
-	if (ret)
-		goto out;
-
 	xe_uc_fw_change_status(&guc->fw, XE_UC_FIRMWARE_LOADABLE);
 
 	ret = devm_add_action_or_reset(xe->drm.dev, guc_fini_hw, guc);
@@ -702,8 +717,6 @@ int xe_guc_init(struct xe_guc *guc)
 
 	guc_init_params(guc);
 
-	xe_guc_comm_init_early(guc);
-
 	return 0;
 
 out:

drivers/gpu/drm/xe/xe_guc.h

@@ -26,6 +26,7 @@
 struct drm_printer;
 
 void xe_guc_comm_init_early(struct xe_guc *guc);
+int xe_guc_init_noalloc(struct xe_guc *guc);
 int xe_guc_init(struct xe_guc *guc);
 int xe_guc_init_post_hwconfig(struct xe_guc *guc);
 int xe_guc_post_load_init(struct xe_guc *guc);

drivers/gpu/drm/xe/xe_guc_ct.c

@@ -209,12 +209,10 @@ static void primelockdep(struct xe_guc_ct *ct)
 	fs_reclaim_release(GFP_KERNEL);
 }
 
-int xe_guc_ct_init(struct xe_guc_ct *ct)
+int xe_guc_ct_init_noalloc(struct xe_guc_ct *ct)
 {
 	struct xe_device *xe = ct_to_xe(ct);
 	struct xe_gt *gt = ct_to_gt(ct);
-	struct xe_tile *tile = gt_to_tile(gt);
-	struct xe_bo *bo;
 	int err;
 
 	xe_gt_assert(gt, !(guc_ct_size() % PAGE_SIZE));
@@ -240,6 +238,23 @@ int xe_guc_ct_init(struct xe_guc_ct *ct)
 
 	primelockdep(ct);
 
+	err = drmm_add_action_or_reset(&xe->drm, guc_ct_fini, ct);
+	if (err)
+		return err;
+
+	xe_gt_assert(gt, ct->state == XE_GUC_CT_STATE_NOT_INITIALIZED);
+	ct->state = XE_GUC_CT_STATE_DISABLED;
+	return 0;
+}
+ALLOW_ERROR_INJECTION(xe_guc_ct_init_noalloc, ERRNO); /* See xe_pci_probe() */
+
+int xe_guc_ct_init(struct xe_guc_ct *ct)
+{
+	struct xe_device *xe = ct_to_xe(ct);
+	struct xe_gt *gt = ct_to_gt(ct);
+	struct xe_tile *tile = gt_to_tile(gt);
+	struct xe_bo *bo;
+
 	bo = xe_managed_bo_create_pin_map(xe, tile, guc_ct_size(),
 					  XE_BO_FLAG_SYSTEM |
 					  XE_BO_FLAG_GGTT |
@@ -249,13 +264,6 @@ int xe_guc_ct_init(struct xe_guc_ct *ct)
 		return PTR_ERR(bo);
 
 	ct->bo = bo;
-
-	err = drmm_add_action_or_reset(&xe->drm, guc_ct_fini, ct);
-	if (err)
-		return err;
-
-	xe_gt_assert(gt, ct->state == XE_GUC_CT_STATE_NOT_INITIALIZED);
-	ct->state = XE_GUC_CT_STATE_DISABLED;
 	return 0;
 }
 ALLOW_ERROR_INJECTION(xe_guc_ct_init, ERRNO); /* See xe_pci_probe() */

drivers/gpu/drm/xe/xe_guc_ct.h

@@ -11,6 +11,7 @@
 struct drm_printer;
 struct xe_device;
 
+int xe_guc_ct_init_noalloc(struct xe_guc_ct *ct);
 int xe_guc_ct_init(struct xe_guc_ct *ct);
 int xe_guc_ct_enable(struct xe_guc_ct *ct);
 void xe_guc_ct_disable(struct xe_guc_ct *ct);

drivers/gpu/drm/xe/xe_uc.c

@@ -33,6 +33,22 @@ uc_to_xe(struct xe_uc *uc)
 }
 
 /* Should be called once at driver load only */
+int xe_uc_init_noalloc(struct xe_uc *uc)
+{
+	int ret;
+
+	ret = xe_guc_init_noalloc(&uc->guc);
+	if (ret)
+		goto err;
+
+	/* HuC and GSC have no early dependencies and will be initialized during xe_uc_init(). */
+	return 0;
+
+err:
+	xe_gt_err(uc_to_gt(uc), "Failed to early initialize uC (%pe)\n", ERR_PTR(ret));
+	return ret;
+}
+
 int xe_uc_init(struct xe_uc *uc)
 {
 	int ret;

drivers/gpu/drm/xe/xe_uc.h

@@ -8,6 +8,7 @@
 
 struct xe_uc;
 
+int xe_uc_init_noalloc(struct xe_uc *uc);
 int xe_uc_init(struct xe_uc *uc);
 int xe_uc_init_hwconfig(struct xe_uc *uc);
 int xe_uc_init_post_hwconfig(struct xe_uc *uc);