[PATCH v5 03/28] of: dynamic: Fix overlayed devices not probing because of fw_devlink

[Herve Codina]

From: Saravana Kannan <saravanak@xxxxxxxxxx>

When an overlay is applied, if the target device has already probed
successfully and bound to a device, then some of the fw_devlink logic
that ran when the device was probed needs to be rerun. This allows newly
created dangling consumers of the overlayed device tree nodes to be
moved to become consumers of the target device.

Fixes: 1a50d9403fb9 ("treewide: Fix probing of devices in DT overlays")
Reported-by: Herve Codina <herve.codina@xxxxxxxxxxx>
Closes: https://lore.kernel.org/lkml/CAMuHMdXEnSD4rRJ-o90x4OprUacN_rJgyo8x6=9F9rZ+-KzjOg@xxxxxxxxxxxxxx/
Closes: https://lore.kernel.org/all/20240221095137.616d2aaa@xxxxxxxxxxx/
Closes: https://lore.kernel.org/lkml/20240312151835.29ef62a0@xxxxxxxxxxx/
Signed-off-by: Saravana Kannan <saravanak@xxxxxxxxxx>
Link: https://lore.kernel.org/lkml/20240411235623.1260061-3-saravanak@xxxxxxxxxx/
[Herve: Rebase on top of recent kernel and use get_device_from_fwnode()]
[Herve: Add the call to driver_deferred_probe_trigger()]
Signed-off-by: Herve Codina <herve.codina@xxxxxxxxxxx>
---
 drivers/base/core.c    | 83 +++++++++++++++++++++++++++++++++++++-----
 drivers/of/overlay.c   | 15 ++++++++
 include/linux/fwnode.h |  1 +
 3 files changed, 90 insertions(+), 9 deletions(-)

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 33c0ff2b162d..726e4af9b1a6 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -235,6 +235,79 @@ static void __fw_devlink_pickup_dangling_consumers(struct fwnode_handle *fwnode,
 		__fw_devlink_pickup_dangling_consumers(child, new_sup);
 }
 
+static void fw_devlink_pickup_dangling_consumers(struct device *dev)
+{
+	struct fwnode_handle *child;
+
+	guard(mutex)(&fwnode_link_lock);
+
+	fwnode_for_each_available_child_node(dev->fwnode, child)
+		__fw_devlink_pickup_dangling_consumers(child, dev->fwnode);
+	__fw_devlink_link_to_consumers(dev);
+}
+
+/**
+ * fw_devlink_refresh_fwnode - Recheck the tree under this firmware node
+ * @fwnode: The fwnode under which the fwnode tree has changed
+ *
+ * This function is mainly meant to adjust the supplier/consumer dependencies
+ * after a fwnode tree overlay has occurred.
+ */
+void fw_devlink_refresh_fwnode(struct fwnode_handle *fwnode)
+{
+	struct device *dev;
+
+	/*
+	 * Find the closest ancestor fwnode that has been converted to a device
+	 * that can bind to a driver (bus device).
+	 */
+	fwnode_handle_get(fwnode);
+	do {
+		if (fwnode->flags & FWNODE_FLAG_NOT_DEVICE)
+			continue;
+
+		dev = get_device_from_fwnode(fwnode);
+		if (!dev)
+			continue;
+
+		if (dev->bus)
+			break;
+
+		put_device(dev);
+	} while ((fwnode = fwnode_get_next_parent(fwnode)));
+
+	/*
+	 * If none of the ancestor fwnodes have (yet) been converted to a device
+	 * that can bind to a driver, there's nothing to fix up.
+	 */
+	if (!fwnode)
+		return;
+
+	WARN(device_is_bound(dev) && dev->links.status != DL_DEV_DRIVER_BOUND,
+	     "Don't multithread overlaying and probing the same device!\n");
+
+	/*
+	 * If the device has already bound to a driver, then we need to redo
+	 * some of the work that was done after the device was bound to a
+	 * driver. If the device hasn't bound to a driver, running thing too
+	 * soon would incorrectly pick up consumers that it shouldn't.
+	 */
+	if (dev->links.status == DL_DEV_DRIVER_BOUND) {
+		fw_devlink_pickup_dangling_consumers(dev);
+		/*
+		 * Some of dangling consumers could have been put previously in
+		 * the deferred probe list due to the unavailability of their
+		 * suppliers. Those consumers have been picked up and some of
+		 * their suppliers links have been update. Time to re-try their
+		 * probe sequence.
+		 */
+		driver_deferred_probe_trigger();
+	}
+
+	put_device(dev);
+	fwnode_handle_put(fwnode);
+}
+
 static DEFINE_MUTEX(device_links_lock);
 DEFINE_STATIC_SRCU(device_links_srcu);
 
@@ -1312,16 +1385,8 @@ void device_links_driver_bound(struct device *dev)
 	 * child firmware node.
 	 */
 	if (dev->fwnode && dev->fwnode->dev == dev) {
-		struct fwnode_handle *child;
-
 		fwnode_links_purge_suppliers(dev->fwnode);
-
-		guard(mutex)(&fwnode_link_lock);
-
-		fwnode_for_each_available_child_node(dev->fwnode, child)
-			__fw_devlink_pickup_dangling_consumers(child,
-							       dev->fwnode);
-		__fw_devlink_link_to_consumers(dev);
+		fw_devlink_pickup_dangling_consumers(dev);
 	}
 	device_remove_file(dev, &dev_attr_waiting_for_supplier);
 
diff --git a/drivers/of/overlay.c b/drivers/of/overlay.c
index c1c5686fc7b1..4e45f3414c2c 100644
--- a/drivers/of/overlay.c
+++ b/drivers/of/overlay.c
@@ -185,6 +185,15 @@ static int overlay_notify(struct overlay_changeset *ovcs,
 	return 0;
 }
 
+static void overlay_fw_devlink_refresh(struct overlay_changeset *ovcs)
+{
+	for (int i = 0; i < ovcs->count; i++) {
+		struct device_node *np = ovcs->fragments[i].target;
+
+		fw_devlink_refresh_fwnode(of_fwnode_handle(np));
+	}
+}
+
 /*
  * The values of properties in the "/__symbols__" node are paths in
  * the ovcs->overlay_root.  When duplicating the properties, the paths
@@ -951,6 +960,12 @@ static int of_overlay_apply(struct overlay_changeset *ovcs,
 		pr_err("overlay apply changeset entry notify error %d\n", ret);
 	/* notify failure is not fatal, continue */
 
+	/*
+	 * Needs to happen after changeset notify to give the listeners a chance
+	 * to finish creating all the devices they need to create.
+	 */
+	overlay_fw_devlink_refresh(ovcs);
+
 	ret_tmp = overlay_notify(ovcs, OF_OVERLAY_POST_APPLY);
 	if (ret_tmp)
 		if (!ret)
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 097be89487bf..a921ca2fe940 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -228,6 +228,7 @@ int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup,
 		    u8 flags);
 void fwnode_links_purge(struct fwnode_handle *fwnode);
 void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode);
+void fw_devlink_refresh_fwnode(struct fwnode_handle *fwnode);
 bool fw_devlink_is_strict(void);
 
 #endif
-- 
2.53.0