[PATCH 2/2] nvme: add 'queue_if_no_path' semantics

[Hannes Reinecke]

Currently namespaces behave differently depending on the 'CMIC'
setting. If CMIC is zero, the device is removed once the last path
goes away. If CMIC has the multipath bit set, the device is retained
even if the last path is removed.
This is okay for fabrics, where one can do an explicit disconnect
to remove the device, but for nvme-pci this induces a regression
with PCI hotplug.
When the NVMe device is opened (eg by MD), the NVMe device is not
removed after a PCI hot-remove. Hence MD will not be notified about
the event, and will continue to consider this device as operational.
Consequently, upon PCI hot-add the device shows up as a new NVMe
device, and MD will fail to reattach the device.
So this patch adds NVME_NSHEAD_QUEUE_IF_NO_PATH flag to the nshead
to restore the original behaviour for non-fabrics NVMe devices.

Signed-off-by: Hannes Reinecke <hare at suse.de>
---
 drivers/nvme/host/core.c      | 10 +++++++++-
 drivers/nvme/host/multipath.c | 38 ++++++++++++++++++++++++++++++++++++++
 drivers/nvme/host/nvme.h      |  2 ++
 3 files changed, 49 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 4459a40b057c..e21c32ea4b51 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -475,8 +475,11 @@ static void nvme_free_ns_head(struct kref *ref)
 		container_of(ref, struct nvme_ns_head, ref);
 
 #ifdef CONFIG_NVME_MULTIPATH
-	if (head->disk)
+	if (head->disk) {
+		if (test_bit(NVME_NSHEAD_QUEUE_IF_NO_PATH, &head->flags))
+			nvme_mpath_remove_disk(head);
 		put_disk(head->disk);
+	}
 #endif
 	ida_simple_remove(&head->subsys->ns_ida, head->instance);
 	cleanup_srcu_struct(&head->srcu);
@@ -3357,6 +3360,7 @@ static struct attribute *nvme_ns_id_attrs[] = {
 #ifdef CONFIG_NVME_MULTIPATH
 	&dev_attr_ana_grpid.attr,
 	&dev_attr_ana_state.attr,
+	&dev_attr_queue_if_no_path.attr,
 #endif
 	NULL,
 };
@@ -3387,6 +3391,10 @@ static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
 		if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl))
 			return 0;
 	}
+	if (a == &dev_attr_queue_if_no_path.attr) {
+		if (dev_to_disk(dev)->fops == &nvme_fops)
+			return 0;
+	}
 #endif
 	return a->mode;
 }
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 55045291b4de..bbdad5917112 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -381,6 +381,9 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	/* set to a default value for 512 until disk is validated */
 	blk_queue_logical_block_size(q, 512);
 	blk_set_stacking_limits(&q->limits);
+	/* Enable queue_if_no_path semantics for fabrics */
+	if (ctrl->ops->flags & NVME_F_FABRICS)
+		set_bit(NVME_NSHEAD_QUEUE_IF_NO_PATH, &head->flags);
 
 	/* we need to propagate up the VMC settings */
 	if (ctrl->vwc & NVME_CTRL_VWC_PRESENT)
@@ -640,6 +643,37 @@ static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr,
 }
 DEVICE_ATTR_RO(ana_state);
 
+static ssize_t queue_if_no_path_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct nvme_ns_head *head = nvme_get_ns_from_dev(dev)->head;
+
+	return sprintf(buf, "%s\n",
+		       test_bit(NVME_NSHEAD_QUEUE_IF_NO_PATH, &head->flags) ?
+		       "on" : "off");
+}
+
+static ssize_t queue_if_no_path_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct nvme_ns_head *head = nvme_get_ns_from_dev(dev)->head;
+	int err;
+	bool queue_if_no_path;
+
+	err = kstrtobool(buf, &queue_if_no_path);
+	if (err)
+		return -EINVAL;
+
+	if (queue_if_no_path)
+		set_bit(NVME_NSHEAD_QUEUE_IF_NO_PATH, &head->flags);
+	else
+		clear_bit(NVME_NSHEAD_QUEUE_IF_NO_PATH, &head->flags);
+
+	return count;
+}
+DEVICE_ATTR(queue_if_no_path, S_IRUGO | S_IWUSR,
+	queue_if_no_path_show, queue_if_no_path_store);
+
 static int nvme_lookup_ana_group_desc(struct nvme_ctrl *ctrl,
 		struct nvme_ana_group_desc *desc, void *data)
 {
@@ -682,6 +716,10 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 {
 	if (!head->disk)
 		return;
+	if (test_bit(NVME_NSHEAD_QUEUE_IF_NO_PATH, &head->flags)) {
+		kblockd_schedule_work(&head->requeue_work);
+		return;
+	}
 	if (head->disk->flags & GENHD_FL_UP)
 		del_gendisk(head->disk);
 	blk_set_queue_dying(head->disk->queue);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b6180bb3361d..94ae06cdc934 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -411,6 +411,7 @@ struct nvme_ns_head {
 	struct mutex		lock;
 	unsigned long		flags;
 #define NVME_NSHEAD_DISK_LIVE	0
+#define NVME_NSHEAD_QUEUE_IF_NO_PATH 1
 	struct nvme_ns __rcu	*current_path[];
 #endif
 };
@@ -684,6 +685,7 @@ static inline void nvme_trace_bio_complete(struct request *req,
 
 extern struct device_attribute dev_attr_ana_grpid;
 extern struct device_attribute dev_attr_ana_state;
+extern struct device_attribute dev_attr_queue_if_no_path;
 extern struct device_attribute subsys_attr_iopolicy;
 
 #else
-- 
2.16.4