[PATCH v3 05/13] libmultipath: Add support for mpath_device management

Add support to add or remove a mpath_device as a path.

NVMe has almost like-for-like equivalents here:
- nvme_mpath_clear_current_path() -> mpath_clear_current_path()
- nvme_mpath_add_sysfs_link() -> mpath_add_sysfs_link()
- nvme_mpath_remove_sysfs_link() -> mpath_remove_sysfs_link()
- nvme_mpath_revalidate_paths() -> mpath_revalidate_paths()

mpath_revalidate_paths() has a CB arg for NVMe specific handling.

The functionality in mpath_clear_paths() and mpath_synchronize() have the
same pattern which is frequently used in the NVMe code.

Helper mpath_call_for_device() is added to allow a driver run a callback
on any path available. It is intended to be used for occasions when the
NVMe drivers accesses the list of paths outside its multipath code, like
NVMe sysfs.c

Signed-off-by: John Garry <[email protected]>
---
 include/linux/multipath.h |  17 ++++
 lib/multipath.c           | 185 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 202 insertions(+)

diff --git a/include/linux/multipath.h b/include/linux/multipath.h
index 57d13eb1450cd..ec4325b77cf8c 100644
--- a/include/linux/multipath.h
+++ b/include/linux/multipath.h
@@ -20,10 +20,13 @@ enum mpath_access_state {
 	MPATH_STATE_OTHER
 };
 
+#define MPATH_DEVICE_SYSFS_ATTR_LINK      0
+
 struct mpath_device {
 	struct mpath_head	*mpath_head;
 	struct list_head	siblings;
 	struct gendisk		*disk;
+	unsigned long		flags;
 	int			numa_node;
 	atomic_t		*nr_active;
 	enum mpath_access_state access_state;
@@ -89,6 +92,20 @@ static inline enum mpath_iopolicy_e mpath_read_iopolicy(
 void mpath_synchronize(struct mpath_head *mpath_head);
 int mpath_set_iopolicy(const char *str, enum mpath_iopolicy_e *iopolicy);
 int mpath_get_iopolicy(char *buf, int iopolicy);
+bool mpath_clear_current_path(struct mpath_device *mpath_device);
+void mpath_synchronize(struct mpath_head *mpath_head);
+void mpath_add_device(struct mpath_device *mpath_device,
+		struct mpath_head *mpath_head, struct gendisk *disk,
+		int numa_node, atomic_t *nr_active);
+bool mpath_delete_device(struct mpath_device *mpath_device);
+bool mpath_head_devices_empty(struct mpath_head *mpath_head);
+int mpath_call_for_device(struct mpath_head *mpath_head,
+			int (*cb)(struct mpath_device *mpath_device));
+void mpath_clear_paths(struct mpath_head *mpath_head);
+void mpath_revalidate_paths(struct mpath_head *mpath_head,
+	void (*not_ready_cb)(struct mpath_device *mpath_device));
+void mpath_add_sysfs_link(struct mpath_head *mpath_head);
+void mpath_remove_sysfs_link(struct mpath_device *mpath_device);
 int mpath_get_head(struct mpath_head *mpath_head);
 void mpath_put_head(struct mpath_head *mpath_head);
 int mpath_head_init(struct mpath_head *mpath_head);
diff --git a/lib/multipath.c b/lib/multipath.c
index 81e737c1ce469..007aa34796569 100644
--- a/lib/multipath.c
+++ b/lib/multipath.c
@@ -50,6 +50,118 @@ void mpath_synchronize(struct mpath_head *mpath_head)
 }
 EXPORT_SYMBOL_GPL(mpath_synchronize);
 
+void mpath_add_device(struct mpath_device *mpath_device,
+		struct mpath_head *mpath_head, struct gendisk *disk,
+		int numa_node, atomic_t *nr_active)
+{
+	mpath_device->mpath_head = mpath_head;
+	mpath_device->disk = disk;
+	mpath_device->numa_node = numa_node;
+	mpath_device->nr_active = nr_active;
+	mutex_lock(&mpath_head->lock);
+	list_add_tail_rcu(&mpath_device->siblings, &mpath_head->dev_list);
+	mutex_unlock(&mpath_head->lock);
+}
+EXPORT_SYMBOL_GPL(mpath_add_device);
+
+bool mpath_delete_device(struct mpath_device *mpath_device)
+{
+	bool empty;
+
+	mutex_lock(&mpath_device->mpath_head->lock);
+	list_del_rcu(&mpath_device->siblings);
+	empty = list_empty(&mpath_device->mpath_head->dev_list);
+	mutex_unlock(&mpath_device->mpath_head->lock);
+
+	return empty;
+}
+EXPORT_SYMBOL_GPL(mpath_delete_device);
+
+bool mpath_head_devices_empty(struct mpath_head *mpath_head)
+{
+	bool empty;
+
+	mutex_lock(&mpath_head->lock);
+	empty = list_empty(&mpath_head->dev_list);
+	mutex_unlock(&mpath_head->lock);
+
+	return empty;
+}
+EXPORT_SYMBOL_GPL(mpath_head_devices_empty);
+
+int mpath_call_for_device(struct mpath_head *mpath_head,
+			int (*cb)(struct mpath_device *mpath_device))
+{
+	struct mpath_device *mpath_device;
+	int ret = -EWOULDBLOCK, srcu_idx;
+
+	srcu_idx = srcu_read_lock(&mpath_head->srcu);
+	mpath_device = mpath_find_path(mpath_head);
+	if (mpath_device)
+		ret = cb(mpath_device);
+	srcu_read_unlock(&mpath_head->srcu, srcu_idx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mpath_call_for_device);
+
+bool mpath_clear_current_path(struct mpath_device *mpath_device)
+{
+	struct mpath_head *mpath_head = mpath_device->mpath_head;
+	bool changed = false;
+	int node;
+
+	for_each_node(node) {
+		if (mpath_device ==
+			rcu_access_pointer(mpath_head->current_path[node])) {
+			rcu_assign_pointer(mpath_head->current_path[node],
+				NULL);
+			changed = true;
+		}
+	}
+
+	return changed;
+}
+EXPORT_SYMBOL_GPL(mpath_clear_current_path);
+
+static void mpath_revalidate_paths_iter(struct mpath_head *mpath_head,
+	void (*not_ready_cb)(struct mpath_device *mpath_device))
+{
+	sector_t capacity = get_capacity(mpath_head->disk);
+	struct mpath_device *mpath_device;
+	int srcu_idx;
+
+	if (!not_ready_cb)
+		return;
+
+	srcu_idx = srcu_read_lock(&mpath_head->srcu);
+	list_for_each_entry_srcu(mpath_device, &mpath_head->dev_list, siblings,
+				 srcu_read_lock_held(&mpath_head->srcu)) {
+		if (capacity != get_capacity(mpath_device->disk))
+			not_ready_cb(mpath_device);
+	}
+	srcu_read_unlock(&mpath_head->srcu, srcu_idx);
+}
+
+void mpath_clear_paths(struct mpath_head *mpath_head)
+{
+	int node;
+
+	for_each_node(node)
+		rcu_assign_pointer(mpath_head->current_path[node], NULL);
+}
+EXPORT_SYMBOL_GPL(mpath_clear_paths);
+
+void mpath_revalidate_paths(struct mpath_head *mpath_head,
+	void (*not_ready_cb)(struct mpath_device *mpath_device))
+{
+	mpath_revalidate_paths_iter(mpath_head, not_ready_cb);
+	mpath_clear_paths(mpath_head);
+
+	mpath_schedule_requeue_work(mpath_head);
+}
+EXPORT_SYMBOL_GPL(mpath_revalidate_paths);
+
 static bool mpath_path_is_disabled(struct mpath_head *mpath_head,
 				struct mpath_device *mpath_device)
 {
@@ -475,6 +587,8 @@ void mpath_device_set_live(struct mpath_device *mpath_device)
 		queue_work(mpath_wq, &mpath_head->partition_scan_work);
 	}
 
+	mpath_add_sysfs_link(mpath_head);
+
 	mutex_lock(&mpath_head->lock);
 	if (mpath_path_is_optimized(mpath_head, mpath_device)) {
 		int node, srcu_idx;
@@ -491,6 +605,77 @@ void mpath_device_set_live(struct mpath_device *mpath_device)
 }
 EXPORT_SYMBOL_GPL(mpath_device_set_live);
 
+void mpath_add_sysfs_link(struct mpath_head *mpath_head)
+{
+	struct device *target;
+	struct device *source;
+	int rc, srcu_idx;
+	struct kobject *mpath_gd_kobj;
+	struct mpath_device *mpath_device;
+
+	/*
+	 * Ensure head disk node is already added otherwise we may get invalid
+	 * kobj for head disk node
+	 */
+	if (!test_bit(GD_ADDED, &mpath_head->disk->state))
+		return;
+
+	mpath_gd_kobj = &disk_to_dev(mpath_head->disk)->kobj;
+	srcu_idx = srcu_read_lock(&mpath_head->srcu);
+
+	list_for_each_entry_srcu(mpath_device, &mpath_head->dev_list, siblings,
+				 srcu_read_lock_held(&mpath_head->srcu)) {
+		if (!test_bit(GD_ADDED, &mpath_device->disk->state))
+			continue;
+
+		if (test_and_set_bit(MPATH_DEVICE_SYSFS_ATTR_LINK,
+					&mpath_device->flags))
+			continue;
+
+		target = disk_to_dev(mpath_device->disk);
+		source = disk_to_dev(mpath_head->disk);
+		/*
+		 * Create sysfs link from head gendisk kobject @kobj to the
+		 * ns path gendisk kobject @target->kobj.
+		 */
+		rc = sysfs_add_link_to_group(mpath_gd_kobj, "multipath",
+				&target->kobj, dev_name(target));
+
+		if (unlikely(rc)) {
+			dev_err(disk_to_dev(mpath_head->disk),
+					"failed to create link to %s rc=%d\n",
+					dev_name(target), rc);
+			clear_bit(MPATH_DEVICE_SYSFS_ATTR_LINK,
+					&mpath_device->flags);
+		} else {
+			dev_info(source, "Created multipath sysfs link to %s\n",
+					mpath_device->disk->disk_name);
+		}
+	}
+
+	srcu_read_unlock(&mpath_head->srcu, srcu_idx);
+}
+EXPORT_SYMBOL_GPL(mpath_add_sysfs_link);
+
+void mpath_remove_sysfs_link(struct mpath_device *mpath_device)
+{
+	struct device *target;
+	struct kobject *mpath_gd_kobj;
+	struct mpath_head *mpath_head = mpath_device->mpath_head;
+
+	if (!test_bit(MPATH_DEVICE_SYSFS_ATTR_LINK, &mpath_device->flags))
+		return;
+
+	target = disk_to_dev(mpath_device->disk);
+	mpath_gd_kobj = &disk_to_dev(mpath_head->disk)->kobj;
+
+	sysfs_remove_link_from_group(mpath_gd_kobj, "multipath",
+			dev_name(target));
+
+	clear_bit(MPATH_DEVICE_SYSFS_ATTR_LINK, &mpath_device->flags);
+}
+EXPORT_SYMBOL_GPL(mpath_remove_sysfs_link);
+
 int mpath_head_init(struct mpath_head *mpath_head)
 {
 	INIT_LIST_HEAD(&mpath_head->dev_list);
-- 
2.43.7