[PATCH RFC 1/1] nvme-multipath: Add debugfs entry for showing multipath info

[Nilay Shroff]

NVMe native multipath supports different io policies for selecting 
I/O path, however, we don't have any visibility about which path is 
being selected by multipath code for forwarding I/O. This patch helps 
add that visibility by adding a debugfs file for each head disk node 
on the system. It creates a file named "multipath" under 
"/sys/kernel/debug/block/nvmeXnY/". This file shows the information 
about current selected "io-policy" as well as it prints a "table" 
showing information about each online node and it's respective I/O 
path, controller name, ana-state and optionally queue depth of each 
path (if selected io-policy is queue-depth).

Signed-off-by: Nilay Shroff <nilay at linux.ibm.com>
---
 drivers/nvme/host/multipath.c | 90 +++++++++++++++++++++++++++++++++++
 drivers/nvme/host/nvme.h      |  1 +
 2 files changed, 91 insertions(+)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 91d9eb3c22ef..143d4b279b43 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -6,6 +6,7 @@
 #include <linux/backing-dev.h>
 #include <linux/moduleparam.h>
 #include <linux/vmalloc.h>
+#include <linux/debugfs.h>
 #include <trace/events/block.h>
 #include "nvme.h"
 
@@ -628,6 +629,91 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 			ctrl->subsys->instance, head->instance);
 	return 0;
 }
+static void nvme_mpath_numa_show(struct seq_file *m, struct nvme_ns_head *head)
+{
+	int node;
+	struct nvme_ns *ns;
+
+	seq_printf(m, "%-4s  %-12s  %-6s  %s\n",
+			"node", "current-path", "ctrl", "ana-state");
+
+	for_each_online_node(node) {
+		ns = srcu_dereference(head->current_path[node], &head->srcu);
+		if (ns)
+			seq_printf(m, "%-4d  %-12s  %-6s  %s\n",
+					node, ns->disk->disk_name,
+					dev_name(ns->ctrl->device),
+					nvme_ana_state_names[ns->ana_state]);
+	}
+}
+
+static void nvme_mpath_rr_show(struct seq_file *m, struct nvme_ns_head *head)
+{
+	int node;
+	struct nvme_ns *ns;
+
+	seq_printf(m, "%-4s  %-12s  %-6s  %s\n",
+			"node", "rr-path", "ctrl", "ana-state");
+
+	for_each_online_node(node) {
+		list_for_each_entry_rcu(ns, &head->list, siblings) {
+			seq_printf(m, "%-4d  %-12s  %-6s  %s\n",
+					node, ns->disk->disk_name,
+					dev_name(ns->ctrl->device),
+					nvme_ana_state_names[ns->ana_state]);
+		}
+	}
+}
+
+static void nvme_mpath_qd_show(struct seq_file *m, struct nvme_ns_head *head)
+{
+	int node;
+	struct nvme_ns *ns;
+
+	seq_printf(m, "%-4s  %-12s  %-6s  %-10s  %s\n",
+			"node", "path", "ctrl", "qdepth", "ana-state");
+
+	for_each_online_node(node) {
+		list_for_each_entry_rcu(ns, &head->list, siblings) {
+			seq_printf(m, "%-4d  %-12s  %-6s  %-10d  %s\n",
+					node, ns->disk->disk_name,
+					dev_name(ns->ctrl->device),
+					atomic_read(&ns->ctrl->nr_active),
+					nvme_ana_state_names[ns->ana_state]);
+
+		}
+	}
+}
+
+static int nvme_mpath_show(struct seq_file *m, void *p)
+{
+	struct nvme_ns_head *head = m->private;
+	int iopolicy = READ_ONCE(head->subsys->iopolicy);
+
+	seq_printf(m, "io-policy: %s\n", nvme_iopolicy_names[iopolicy]);
+
+	seq_puts(m, "io-path:\n");
+	seq_puts(m, "--------\n");
+
+	if (iopolicy == NVME_IOPOLICY_NUMA)
+		nvme_mpath_numa_show(m, head);
+	else if (iopolicy == NVME_IOPOLICY_RR)
+		nvme_mpath_rr_show(m, head);
+	else if (iopolicy == NVME_IOPOLICY_QD)
+		nvme_mpath_qd_show(m, head);
+
+	return 0;
+}
+
+static int nvme_mpath_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, nvme_mpath_show, inode->i_private);
+}
+static const struct file_operations nvme_mpath_fops = {
+	.open = nvme_mpath_open,
+	.read = seq_read,
+	.release = single_release
+};
 
 static void nvme_mpath_set_live(struct nvme_ns *ns)
 {
@@ -650,6 +736,9 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 			return;
 		}
 		nvme_add_ns_head_cdev(head);
+		head->debugfs = debugfs_create_file("multipath", 0400,
+					head->disk->queue->debugfs_dir, head,
+					&nvme_mpath_fops);
 	}
 
 	mutex_lock(&head->lock);
@@ -969,6 +1058,7 @@ void nvme_mpath_shutdown_disk(struct nvme_ns_head *head)
 		return;
 	kblockd_schedule_work(&head->requeue_work);
 	if (test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
+		debugfs_remove(head->debugfs);
 		nvme_cdev_del(&head->cdev, &head->cdev_device);
 		del_gendisk(head->disk);
 	}
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index f900e44243ae..5b4c0b70cedf 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -493,6 +493,7 @@ struct nvme_ns_head {
 	struct work_struct	requeue_work;
 	struct mutex		lock;
 	unsigned long		flags;
+	struct dentry		*debugfs;
 #define NVME_NSHEAD_DISK_LIVE	0
 	struct nvme_ns __rcu	*current_path[];
 #endif
-- 
2.45.2