drm/xe: Add callback support for driver remove

xe device probe uses devm cleanup in most places. However there are a
few cases where this is not possible: when the driver interacts with
component add/del. In that case, the resource group would be cleanup
while the entire device resources are in the process of cleanup.  One
example is the xe_gsc_proxy and display using that to interact with mei
and audio.

Add a callback-based remove so the exception doesn't make the probe
use multiple error handling styles.

v2: Change internal API to mimic the devm API. This will make it easier
    to migrate in future when devm can be used.

Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250213192909.996148-1-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>

drivers/gpu/drm/xe/xe_device.c

@@ -65,6 +65,12 @@
 
 #include <generated/xe_wa_oob.h>
 
+struct xe_device_remove_action {
+	struct list_head node;
+	void (*action)(void *);
+	void *data;
+};
+
 static int xe_file_open(struct drm_device *dev, struct drm_file *file)
 {
 	struct xe_device *xe = to_xe_device(dev);
@@ -746,6 +752,9 @@ int xe_device_probe(struct xe_device *xe)
 	u8 last_gt;
 	u8 id;
 
+	xe->probing = true;
+	INIT_LIST_HEAD(&xe->remove_action_list);
+
 	xe_pat_init_early(xe);
 
 	err = xe_sriov_init(xe);
@@ -886,6 +895,8 @@ int xe_device_probe(struct xe_device *xe)
 
 	xe_vsec_init(xe);
 
+	xe->probing = false;
+
 	return devm_add_action_or_reset(xe->drm.dev, xe_device_sanitize, xe);
 
 err_fini_display:
@@ -907,6 +918,61 @@ int xe_device_probe(struct xe_device *xe)
 	return err;
 }
 
+/**
+ * xe_device_call_remove_actions - Call the remove actions
+ * @xe: xe device instance
+ *
+ * This is only to be used by xe_pci and xe_device to call the remove actions
+ * while removing the driver or handling probe failures.
+ */
+void xe_device_call_remove_actions(struct xe_device *xe)
+{
+	struct xe_device_remove_action *ra, *tmp;
+
+	list_for_each_entry_safe(ra, tmp, &xe->remove_action_list, node) {
+		ra->action(ra->data);
+		list_del(&ra->node);
+		kfree(ra);
+	}
+
+	xe->probing = false;
+}
+
+/**
+ * xe_device_add_action_or_reset - Add an action to run on driver removal
+ * @xe: xe device instance
+ * @action: Function that should be called on device remove
+ * @data: Pointer to data passed to @action implementation
+ *
+ * This adds a custom action to the list of remove callbacks executed on device
+ * remove, before any dev or drm managed resources are removed.  This is only
+ * needed if the action leads to component_del()/component_master_del() since
+ * that is not compatible with devres cleanup.
+ *
+ * Returns: 0 on success or a negative error code on failure, in which case
+ * @action is already called.
+ */
+int xe_device_add_action_or_reset(struct xe_device *xe,
+				  void (*action)(void *), void *data)
+{
+	struct xe_device_remove_action *ra;
+
+	drm_WARN_ON(&xe->drm, !xe->probing);
+
+	ra = kmalloc(sizeof(*ra), GFP_KERNEL);
+	if (!ra) {
+		action(data);
+		return -ENOMEM;
+	}
+
+	INIT_LIST_HEAD(&ra->node);
+	ra->action = action;
+	ra->data = data;
+	list_add(&ra->node, &xe->remove_action_list);
+
+	return 0;
+}
+
 static void xe_device_remove_display(struct xe_device *xe)
 {
 	xe_display_unregister(xe);
@@ -932,6 +998,8 @@ void xe_device_remove(struct xe_device *xe)
 
 	for_each_gt(gt, xe, id)
 		xe_gt_remove(gt);
+
+	xe_device_call_remove_actions(xe);
 }
 
 void xe_device_shutdown(struct xe_device *xe)

drivers/gpu/drm/xe/xe_device.h

@@ -45,6 +45,9 @@ struct xe_device *xe_device_create(struct pci_dev *pdev,
 				   const struct pci_device_id *ent);
 int xe_device_probe_early(struct xe_device *xe);
 int xe_device_probe(struct xe_device *xe);
+int xe_device_add_action_or_reset(struct xe_device *xe,
+				  void (*action)(void *), void *data);
+void xe_device_call_remove_actions(struct xe_device *xe);
 void xe_device_remove(struct xe_device *xe);
 void xe_device_shutdown(struct xe_device *xe);
 

drivers/gpu/drm/xe/xe_device_types.h

@@ -428,6 +428,20 @@ struct xe_device {
 	/** @tiles: device tiles */
 	struct xe_tile tiles[XE_MAX_TILES_PER_DEVICE];
 
+	/**
+	 * @remove_action_list: list of actions to execute on device remove.
+	 * Use xe_device_add_remove_action() for that. Actions can only be added
+	 * during probe and are executed during the call from PCI subsystem to
+	 * remove the driver from the device.
+	 */
+	struct list_head remove_action_list;
+
+	/**
+	 * @probing: cover the section in which @remove_action_list can be used
+	 * to post cleaning actions
+	 */
+	bool probing;
+
 	/**
 	 * @mem_access: keep track of memory access in the device, possibly
 	 * triggering additional actions when they occur.

drivers/gpu/drm/xe/xe_pci.c

@@ -900,8 +900,10 @@ static int xe_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return err;
 
 	err = xe_device_probe(xe);
-	if (err)
+	if (err) {
+		xe_device_call_remove_actions(xe);
 		return err;
+	}
 
 	err = xe_pm_init(xe);
 	if (err)