Driver core: Add offline/online device operations

In some cases, graceful hot-removal of devices is not possible,
although in principle the devices in question support hotplug.
For example, that may happen for the last CPU in the system or
for memory modules holding kernel memory.

In those cases it is nice to be able to check if the given device
can be gracefully hot-removed before triggering a removal procedure
that cannot be aborted or reversed.  Unfortunately, however, the
kernel currently doesn't provide any support for that.

To address that deficiency, introduce support for offline and
online operations that can be performed on devices, respectively,
before a hot-removal and in case when it is necessary (or convenient)
to put a device back online after a successful offline (that has not
been followed by removal).  The idea is that the offline will fail
whenever the given device cannot be gracefully removed from the
system and it will not be allowed to use the device after a
successful offline (until a subsequent online) in analogy with the
existing CPU offline/online mechanism.

For now, the offline and online operations are introduced at the
bus type level, as that should be sufficient for the most urgent use
cases (CPUs and memory modules).  In the future, however, the
approach may be extended to cover some more complicated device
offline/online scenarios involving device drivers etc.

The lock_device_hotplug() and unlock_device_hotplug() functions are
introduced because subsequent patches need to put larger pieces of
code under device_hotplug_lock to prevent race conditions between
device offline and removal from happening.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Toshi Kani <toshi.kani@hp.com>

1 files changed, 130 insertions, 0 deletions

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 016312437577..60c975686089 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -403,6 +403,36 @@ static ssize_t store_uevent(struct device *dev, struct device_attribute *attr,
 static struct device_attribute uevent_attr =
 	__ATTR(uevent, S_IRUGO | S_IWUSR, show_uevent, store_uevent);
 
+static ssize_t show_online(struct device *dev, struct device_attribute *attr,
+			   char *buf)
+{
+	bool val;
+
+	lock_device_hotplug();
+	val = !dev->offline;
+	unlock_device_hotplug();
+	return sprintf(buf, "%u\n", val);
+}
+
+static ssize_t store_online(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
+{
+	bool val;
+	int ret;
+
+	ret = strtobool(buf, &val);
+	if (ret < 0)
+		return ret;
+
+	lock_device_hotplug();
+	ret = val ? device_online(dev) : device_offline(dev);
+	unlock_device_hotplug();
+	return ret < 0 ? ret : count;
+}
+
+static struct device_attribute online_attr =
+	__ATTR(online, S_IRUGO | S_IWUSR, show_online, store_online);
+
 static int device_add_attributes(struct device *dev,
 				 struct device_attribute *attrs)
 {
@@ -516,6 +546,12 @@ static int device_add_attrs(struct device *dev)
 	if (error)
 		goto err_remove_type_groups;
 
+	if (device_supports_offline(dev) && !dev->offline_disabled) {
+		error = device_create_file(dev, &online_attr);
+		if (error)
+			goto err_remove_type_groups;
+	}
+
 	return 0;
 
  err_remove_type_groups:
@@ -536,6 +572,7 @@ static void device_remove_attrs(struct device *dev)
 	struct class *class = dev->class;
 	const struct device_type *type = dev->type;
 
+	device_remove_file(dev, &online_attr);
 	device_remove_groups(dev, dev->groups);
 
 	if (type)
@@ -1431,6 +1468,99 @@ EXPORT_SYMBOL_GPL(put_device);
 EXPORT_SYMBOL_GPL(device_create_file);
 EXPORT_SYMBOL_GPL(device_remove_file);
 
+static DEFINE_MUTEX(device_hotplug_lock);
+
+void lock_device_hotplug(void)
+{
+	mutex_lock(&device_hotplug_lock);
+}
+
+void unlock_device_hotplug(void)
+{
+	mutex_unlock(&device_hotplug_lock);
+}
+
+static int device_check_offline(struct device *dev, void *not_used)
+{
+	int ret;
+
+	ret = device_for_each_child(dev, NULL, device_check_offline);
+	if (ret)
+		return ret;
+
+	return device_supports_offline(dev) && !dev->offline ? -EBUSY : 0;
+}
+
+/**
+ * device_offline - Prepare the device for hot-removal.
+ * @dev: Device to be put offline.
+ *
+ * Execute the device bus type's .offline() callback, if present, to prepare
+ * the device for a subsequent hot-removal.  If that succeeds, the device must
+ * not be used until either it is removed or its bus type's .online() callback
+ * is executed.
+ *
+ * Call under device_hotplug_lock.
+ */
+int device_offline(struct device *dev)
+{
+	int ret;
+
+	if (dev->offline_disabled)
+		return -EPERM;
+
+	ret = device_for_each_child(dev, NULL, device_check_offline);
+	if (ret)
+		return ret;
+
+	device_lock(dev);
+	if (device_supports_offline(dev)) {
+		if (dev->offline) {
+			ret = 1;
+		} else {
+			ret = dev->bus->offline(dev);
+			if (!ret) {
+				kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
+				dev->offline = true;
+			}
+		}
+	}
+	device_unlock(dev);
+
+	return ret;
+}
+
+/**
+ * device_online - Put the device back online after successful device_offline().
+ * @dev: Device to be put back online.
+ *
+ * If device_offline() has been successfully executed for @dev, but the device
+ * has not been removed subsequently, execute its bus type's .online() callback
+ * to indicate that the device can be used again.
+ *
+ * Call under device_hotplug_lock.
+ */
+int device_online(struct device *dev)
+{
+	int ret = 0;
+
+	device_lock(dev);
+	if (device_supports_offline(dev)) {
+		if (dev->offline) {
+			ret = dev->bus->online(dev);
+			if (!ret) {
+				kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+				dev->offline = false;
+			}
+		} else {
+			ret = 1;
+		}
+	}
+	device_unlock(dev);
+
+	return ret;
+}
+
 struct root_device {
 	struct device dev;
 	struct module *owner;