driver core: shut down devices asynchronously

Add code to allow asynchronous shutdown of devices, ensuring that each
device is shut down before its parents & suppliers.

Only devices with drivers that have async_shutdown_enable enabled will be
shut down asynchronously.

This can dramatically reduce system shutdown/reboot time on systems that
have multiple devices that take many seconds to shut down (like certain
NVMe drives). On one system tested, the shutdown time went from 11 minutes
without this patch to 55 seconds with the patch.

Signed-off-by: Stuart Hayes <stuart.w.hayes@gmail.com>
Signed-off-by: David Jeffery <djeffery@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Tested-by: Keith Busch <kbusch@kernel.org>
Link: https://lore.kernel.org/r/20240822202805.6379-4-stuart.w.hayes@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/base/base.h

@@ -10,6 +10,7 @@
  * shared outside of the drivers/base/ directory.
  *
  */
+#include <linux/async.h>
 #include <linux/notifier.h>
 
 /**
@@ -97,6 +98,8 @@ struct driver_private {
  *	the device; typically because it depends on another driver getting
  *	probed first.
  * @async_driver - pointer to device driver awaiting probe via async_probe
+ * @shutdown_after - used during device shutdown to ensure correct shutdown
+ *	ordering.
  * @device - pointer back to the struct device that this structure is
  * associated with.
  * @dead - This device is currently either in the process of or has been
@@ -114,6 +117,7 @@ struct device_private {
 	struct list_head deferred_probe;
 	const struct device_driver *async_driver;
 	char *deferred_probe_reason;
+	async_cookie_t shutdown_after;
 	struct device *device;
 	u8 dead:1;
 };

drivers/base/core.c

@@ -9,6 +9,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/async.h>
 #include <linux/blkdev.h>
 #include <linux/cleanup.h>
 #include <linux/cpufreq.h>
@@ -3524,6 +3525,7 @@ static int device_private_init(struct device *dev)
 	klist_init(&dev->p->klist_children, klist_children_get,
 		   klist_children_put);
 	INIT_LIST_HEAD(&dev->p->deferred_probe);
+	dev->p->shutdown_after = 0;
 	return 0;
 }
 
@@ -4779,6 +4781,8 @@ int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid)
 }
 EXPORT_SYMBOL_GPL(device_change_owner);
 
+static ASYNC_DOMAIN(sd_domain);
+
 static void shutdown_one_device(struct device *dev)
 {
 	/* hold lock to avoid race with probe/release */
@@ -4814,12 +4818,34 @@ static void shutdown_one_device(struct device *dev)
 		put_device(dev->parent);
 }
 
+/**
+ * shutdown_one_device_async
+ * @data: the pointer to the struct device to be shutdown
+ * @cookie: not used
+ *
+ * Shuts down one device, after waiting for shutdown_after to complete.
+ * shutdown_after should be set to the cookie of the last child or consumer
+ * of this device to be shutdown (if any), or to the cookie of the previous
+ * device to be shut down for devices that don't enable asynchronous shutdown.
+ */
+static void shutdown_one_device_async(void *data, async_cookie_t cookie)
+{
+	struct device *dev = data;
+
+	async_synchronize_cookie_domain(dev->p->shutdown_after + 1, &sd_domain);
+
+	shutdown_one_device(dev);
+}
+
 /**
  * device_shutdown - call ->shutdown() on each device to shutdown.
  */
 void device_shutdown(void)
 {
 	struct device *dev, *parent;
+	async_cookie_t cookie = 0;
+	struct device_link *link;
+	int idx;
 
 	wait_for_device_probe();
 	device_block_probing();
@@ -4850,11 +4876,37 @@ void device_shutdown(void)
 		list_del_init(&dev->kobj.entry);
 		spin_unlock(&devices_kset->list_lock);
 
-		shutdown_one_device(dev);
+
+		/*
+		 * Set cookie for devices that will be shut down synchronously
+		 */
+		if (!dev->driver || !dev->driver->async_shutdown_enable)
+			dev->p->shutdown_after = cookie;
+
+		get_device(dev);
+		get_device(parent);
+
+		cookie = async_schedule_domain(shutdown_one_device_async,
+					       dev, &sd_domain);
+		/*
+		 * Ensure parent & suppliers wait for this device to shut down
+		 */
+		if (parent) {
+			parent->p->shutdown_after = cookie;
+			put_device(parent);
+		}
+
+		idx = device_links_read_lock();
+		list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
+				device_links_read_lock_held())
+			link->supplier->p->shutdown_after = cookie;
+		device_links_read_unlock(idx);
+		put_device(dev);
 
 		spin_lock(&devices_kset->list_lock);
 	}
 	spin_unlock(&devices_kset->list_lock);
+	async_synchronize_full_domain(&sd_domain);
 }
 
 /*

include/linux/device/driver.h

@@ -56,6 +56,7 @@ enum probe_type {
  * @mod_name:	Used for built-in modules.
  * @suppress_bind_attrs: Disables bind/unbind via sysfs.
  * @probe_type:	Type of the probe (synchronous or asynchronous) to use.
+ * @async_shutdown_enable: Enables devices to be shutdown asynchronously.
  * @of_match_table: The open firmware table.
  * @acpi_match_table: The ACPI match table.
  * @probe:	Called to query the existence of a specific device,
@@ -102,6 +103,7 @@ struct device_driver {
 
 	bool suppress_bind_attrs;	/* disables bind/unbind via sysfs */
 	enum probe_type probe_type;
+	bool async_shutdown_enable;
 
 	const struct of_device_id	*of_match_table;
 	const struct acpi_device_id	*acpi_match_table;