[PATCH v2 03/13] libmultipath: Add path selection support

[John Garry <john.g.garry@oracle.com>]

Add code for path selection.

NVMe ANA is abstracted into enum mpath_access_state. The motivation here is
so that SCSI ALUA can be used. Callbacks .is_disabled, .is_optimized,
.get_access_state are added to get the path access state.

Path selection modes round-robin, NUMA, and queue-depth are added, same
as NVMe supports.

NVMe has almost like-for-like equivalents here:
- __mpath_find_path() -> __nvme_find_path()
- mpath_find_path() -> nvme_find_path()

and similar for all introduced callee functions.

Functions mpath_set_iopolicy() and mpath_get_iopolicy() are added for
setting default iopolicy.

A separate mpath_iopolicy structure is introduced. There is no iopolicy
member included in the mpath_head structure as it may not suit NVMe, where
iopolicy is per-subsystem and not per namespace.

Signed-off-by: John Garry <john.g.garry@oracle.com>
---
 include/linux/multipath.h |  37 ++++++
 lib/multipath.c           | 248 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 285 insertions(+)

diff --git a/include/linux/multipath.h b/include/linux/multipath.h
index 3e2a513059cde..13d810148a96a 100644
--- a/include/linux/multipath.h
+++ b/include/linux/multipath.h
@@ -7,13 +7,36 @@
 
 extern const struct block_device_operations mpath_ops;
 
+enum mpath_iopolicy_e {
+	MPATH_IOPOLICY_NUMA,
+	MPATH_IOPOLICY_RR,
+	MPATH_IOPOLICY_QD,
+};
+
+struct mpath_iopolicy {
+	enum mpath_iopolicy_e	iopolicy;
+};
+
+enum mpath_access_state {
+	MPATH_STATE_OPTIMIZED,
+	MPATH_STATE_NONOPTIMIZED,
+	MPATH_STATE_OTHER
+};
+
 struct mpath_device {
 	struct mpath_head	*mpath_head;
 	struct list_head	siblings;
 	struct gendisk		*disk;
+	int			numa_node;
+	enum mpath_access_state access_state;
 };
 
 struct mpath_head_template {
+	bool (*is_disabled)(struct mpath_device *);
+	bool (*is_optimized)(struct mpath_device *);
+	int (*get_nr_active)(struct mpath_device *);
+	enum mpath_iopolicy_e (*get_iopolicy)(struct mpath_head *);
+	const struct attribute_group **device_groups;
 };
 
 #define MPATH_HEAD_DISK_LIVE 			0
@@ -45,6 +68,14 @@ static inline struct mpath_head *mpath_gendisk_to_head(struct gendisk *disk)
 	return mpath_bd_device_to_head(disk_to_dev(disk));
 }
 
+static inline enum mpath_iopolicy_e mpath_read_iopolicy(
+			struct mpath_iopolicy *mpath_iopolicy)
+{
+	return READ_ONCE(mpath_iopolicy->iopolicy);
+}
+void mpath_synchronize(struct mpath_head *mpath_head);
+int mpath_set_iopolicy(const char *val, int *iopolicy);
+int mpath_get_iopolicy(char *buf, int iopolicy);
 int mpath_get_head(struct mpath_head *mpath_head);
 void mpath_put_head(struct mpath_head *mpath_head);
 struct mpath_head *mpath_alloc_head(void);
@@ -63,4 +94,10 @@ static inline bool is_mpath_disk(struct gendisk *disk)
 	return false;
 	#endif
 }
+
+static inline bool mpath_qd_iopolicy(struct mpath_iopolicy *mpath_iopolicy)
+{
+	return mpath_read_iopolicy(mpath_iopolicy) == MPATH_IOPOLICY_QD;
+}
+
 #endif // _LIBMULTIPATH_H
diff --git a/lib/multipath.c b/lib/multipath.c
index 726d9bec13553..fa211420b72c3 100644
--- a/lib/multipath.c
+++ b/lib/multipath.c
@@ -6,8 +6,242 @@
 #include <linux/module.h>
 #include <linux/multipath.h>
 
+static struct mpath_device *mpath_find_path(struct mpath_head *mpath_head);
+
 static struct workqueue_struct *mpath_wq;
 
+static const char *mpath_iopolicy_names[] = {
+	[MPATH_IOPOLICY_NUMA]	= "numa",
+	[MPATH_IOPOLICY_RR]	= "round-robin",
+	[MPATH_IOPOLICY_QD]	= "queue-depth",
+};
+
+int mpath_set_iopolicy(const char *val, int *iopolicy)
+{
+	if (!val)
+		return -EINVAL;
+	if (!strncmp(val, "numa", 4))
+		*iopolicy = MPATH_IOPOLICY_NUMA;
+	else if (!strncmp(val, "round-robin", 11))
+		*iopolicy = MPATH_IOPOLICY_RR;
+	else if (!strncmp(val, "queue-depth", 11))
+		*iopolicy = MPATH_IOPOLICY_QD;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mpath_set_iopolicy);
+
+int mpath_get_iopolicy(char *buf, int iopolicy)
+{
+	return sprintf(buf, "%s\n", mpath_iopolicy_names[iopolicy]);
+}
+EXPORT_SYMBOL_GPL(mpath_get_iopolicy);
+
+
+void mpath_synchronize(struct mpath_head *mpath_head)
+{
+	synchronize_srcu(&mpath_head->srcu);
+}
+EXPORT_SYMBOL_GPL(mpath_synchronize);
+
+static bool mpath_path_is_disabled(struct mpath_head *mpath_head,
+				struct mpath_device *mpath_device)
+{
+	return mpath_head->mpdt->is_disabled(mpath_device);
+}
+
+static struct mpath_device *__mpath_find_path(struct mpath_head *mpath_head,
+					int node)
+{
+	int found_distance = INT_MAX, fallback_distance = INT_MAX, distance;
+	struct mpath_device *found = NULL, *fallback = NULL, *mpath_device;
+
+	list_for_each_entry_srcu(mpath_device, &mpath_head->dev_list, siblings,
+		srcu_read_lock_held(&mpath_head->srcu)) {
+		if (mpath_path_is_disabled(mpath_head, mpath_device))
+			continue;
+
+		if (mpath_device->numa_node != NUMA_NO_NODE &&
+		    (mpath_head->mpdt->get_iopolicy(mpath_head) ==
+			MPATH_IOPOLICY_NUMA))
+			distance = node_distance(node,
+					mpath_device->numa_node);
+		else
+			distance = LOCAL_DISTANCE;
+
+		switch(mpath_device->access_state) {
+		case MPATH_STATE_OPTIMIZED:
+		    if (distance < found_distance) {
+			    found_distance = distance;
+			    found = mpath_device;
+		    }
+		    break;
+		case MPATH_STATE_NONOPTIMIZED:
+		    if (distance < fallback_distance) {
+			    fallback_distance = distance;
+			    fallback = mpath_device;
+		    }
+		    break;
+		default:
+		    break;
+		}
+	}
+
+	if (!found)
+		found = fallback;
+
+	if (found)
+		rcu_assign_pointer(mpath_head->current_path[node], found);
+
+	return found;
+}
+
+static struct mpath_device *mpath_next_dev(struct mpath_head *mpath_head,
+				struct mpath_device *mpath_dev)
+{
+	mpath_dev = list_next_or_null_rcu(&mpath_head->dev_list,
+			&mpath_dev->siblings, struct mpath_device,
+			siblings);
+
+	if (mpath_dev)
+		return mpath_dev;
+	return list_first_or_null_rcu(&mpath_head->dev_list,
+				struct mpath_device, siblings);
+}
+
+static struct mpath_device *mpath_round_robin_path(
+				struct mpath_head *mpath_head)
+{
+	struct mpath_device *mpath_device, *found = NULL;
+	int node = numa_node_id();
+	enum mpath_access_state access_state_old;
+	struct mpath_device *old =
+			srcu_dereference(mpath_head->current_path[node],
+				&mpath_head->srcu);
+
+	if (unlikely(!old))
+		return __mpath_find_path(mpath_head, node);
+
+	if (list_is_singular(&mpath_head->dev_list)) {
+		if (mpath_path_is_disabled(mpath_head, old))
+			return NULL;
+		return old;
+	}
+
+	for (mpath_device = mpath_next_dev(mpath_head, old);
+	    mpath_device && mpath_device != old;
+	    mpath_device = mpath_next_dev(mpath_head, mpath_device)) {
+
+		if (mpath_path_is_disabled(mpath_head, mpath_device))
+			continue;
+		if (mpath_device->access_state == MPATH_STATE_OPTIMIZED) {
+			found = mpath_device;
+			goto out;
+		}
+		if (mpath_device->access_state == MPATH_STATE_NONOPTIMIZED)
+			found = mpath_device;
+	}
+
+	/*
+	 * The loop above skips the current path for round-robin semantics.
+	 * Fall back to the current path if either:
+	 *  - no other optimized path found and current is optimized,
+	 *  - no other usable path found and current is usable.
+	 */
+	access_state_old = old->access_state;
+	if (!mpath_path_is_disabled(mpath_head, old) &&
+	    (access_state_old == MPATH_STATE_OPTIMIZED ||
+	    (!found && access_state_old == MPATH_STATE_NONOPTIMIZED)))
+		return old;
+
+	if (!found)
+		return NULL;
+out:
+	rcu_assign_pointer(mpath_head->current_path[node], found);
+
+	return found;
+}
+
+static struct mpath_device *mpath_queue_depth_path(
+				struct mpath_head *mpath_head)
+{
+	struct mpath_device *best_opt = NULL, *mpath_device;
+	struct mpath_device *best_nonopt = NULL;
+	unsigned int min_depth_opt = UINT_MAX, min_depth_nonopt = UINT_MAX;
+	unsigned int depth;
+	int (*get_nr_active)(struct mpath_device *) =
+				mpath_head->mpdt->get_nr_active;
+
+	list_for_each_entry_srcu(mpath_device, &mpath_head->dev_list, siblings,
+				 srcu_read_lock_held(&mpath_head->srcu)) {
+
+		if (mpath_path_is_disabled(mpath_head, mpath_device))
+			continue;
+
+		depth = get_nr_active(mpath_device);
+
+		switch (mpath_device->access_state) {
+		case MPATH_STATE_OPTIMIZED:
+			if (depth < min_depth_opt) {
+				min_depth_opt = depth;
+				best_opt = mpath_device;
+			}
+			break;
+		case MPATH_STATE_NONOPTIMIZED:
+			if (depth < min_depth_nonopt) {
+				min_depth_nonopt = depth;
+				best_nonopt = mpath_device;
+			}
+			break;
+		default:
+			break;
+		}
+
+		if (min_depth_opt == 0)
+			return best_opt;
+	}
+
+	return best_opt ? best_opt : best_nonopt;
+}
+
+static inline bool mpath_path_is_optimized(struct mpath_head *mpath_head,
+				struct mpath_device *mpath_device)
+{
+	return mpath_head->mpdt->is_optimized(mpath_device);
+}
+
+static struct mpath_device *mpath_numa_path(struct mpath_head *mpath_head)
+{
+	int node = numa_node_id();
+	struct mpath_device *mpath_device;
+
+	mpath_device = srcu_dereference(mpath_head->current_path[node],
+					&mpath_head->srcu);
+	if (unlikely(!mpath_device))
+		return __mpath_find_path(mpath_head, node);
+	if (unlikely(!mpath_path_is_optimized(mpath_head, mpath_device)))
+		return __mpath_find_path(mpath_head, node);
+	return mpath_device;
+}
+
+__maybe_unused
+static struct mpath_device *mpath_find_path(struct mpath_head *mpath_head)
+{
+	enum mpath_iopolicy_e iopolicy =
+			mpath_head->mpdt->get_iopolicy(mpath_head);
+
+	switch (iopolicy) {
+	case MPATH_IOPOLICY_QD:
+		return mpath_queue_depth_path(mpath_head);
+	case MPATH_IOPOLICY_RR:
+		return mpath_round_robin_path(mpath_head);
+	default:
+		return mpath_numa_path(mpath_head);
+	}
+}
+
 static void mpath_free_head(struct kref *ref)
 {
 	struct mpath_head *mpath_head =
@@ -71,6 +305,7 @@ void mpath_remove_disk(struct mpath_head *mpath_head)
 	if (test_and_clear_bit(MPATH_HEAD_DISK_LIVE, &mpath_head->flags)) {
 		struct gendisk *disk = mpath_head->disk;
 
+		mpath_synchronize(mpath_head);
 		del_gendisk(disk);
 	}
 }
@@ -121,6 +356,19 @@ void mpath_device_set_live(struct mpath_device *mpath_device)
 		}
 		queue_work(mpath_wq, &mpath_head->partition_scan_work);
 	}
+
+	mutex_lock(&mpath_head->lock);
+	if (mpath_path_is_optimized(mpath_head, mpath_device)) {
+		int node, srcu_idx;
+
+		srcu_idx = srcu_read_lock(&mpath_head->srcu);
+		for_each_online_node(node)
+			__mpath_find_path(mpath_head, node);
+		srcu_read_unlock(&mpath_head->srcu, srcu_idx);
+	}
+	mutex_unlock(&mpath_head->lock);
+
+	mpath_synchronize(mpath_head);
 }
 EXPORT_SYMBOL_GPL(mpath_device_set_live);
 
-- 
2.43.5