[PATCH 1/2] nvme: add 'fail_if_no_path' sysfs attribute

[Hannes Reinecke]

In some setups like RAID or cluster we need to return an I/O error
once all paths are unavailable to allow the upper layers to start
their own error recovery (like redirecting I/O to other mirrors).
This patch adds a sysfs attribute 'fail_if_no_path' to allow the
admin to enable that behaviour instead of the current 'queue until
a path becomes available' policy.

Signed-off-by: Hannes Reinecke <hare at suse.de>
---
 drivers/nvme/host/core.c      |  5 ++++
 drivers/nvme/host/multipath.c | 43 +++++++++++++++++++++++++++++++++--
 drivers/nvme/host/nvme.h      |  2 ++
 3 files changed, 48 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 4de6a3a13575..2fb3ecc0c53b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3464,6 +3464,7 @@ static struct attribute *nvme_ns_id_attrs[] = {
 #ifdef CONFIG_NVME_MULTIPATH
 	&dev_attr_ana_grpid.attr,
 	&dev_attr_ana_state.attr,
+	&dev_attr_fail_if_no_path.attr,
 #endif
 	NULL,
 };
@@ -3494,6 +3495,10 @@ 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_fail_if_no_path.attr) {
+		if (dev_to_disk(dev)->fops == &nvme_bdev_ops)
+			return 0;
+	}
 #endif
 	return a->mode;
 }
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 0696319adaf6..d5773ea105b1 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -283,10 +283,18 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 			continue;
 		switch (ns->ctrl->state) {
 		case NVME_CTRL_LIVE:
+			if (!test_bit(NVME_NSHEAD_FAIL_IF_NO_PATH,
+				      &head->flags))
+				return true;
+			if (ns->ana_state != NVME_ANA_INACCESSIBLE &&
+			    ns->ana_state != NVME_ANA_PERSISTENT_LOSS)
+				return true;
 		case NVME_CTRL_RESETTING:
-		case NVME_CTRL_CONNECTING:
 			/* fallthru */
-			return true;
+		case NVME_CTRL_CONNECTING:
+			if (!test_bit(NVME_NSHEAD_FAIL_IF_NO_PATH,
+				      &head->flags))
+				return true;
 		default:
 			break;
 		}
@@ -641,6 +649,37 @@ static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr,
 }
 DEVICE_ATTR_RO(ana_state);
 
+static ssize_t fail_if_no_path_show(struct device *dev,
+		struct device_attribute *attr, char *buf)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	struct nvme_ns_head *head = disk->private_data;
+
+	return sprintf(buf, "%d\n",
+		       test_bit(NVME_NSHEAD_FAIL_IF_NO_PATH, &head->flags) ?
+		       1 : 0);
+}
+
+static ssize_t fail_if_no_path_store(struct device *dev,
+		struct device_attribute *attr, const char *buf, size_t count)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	struct nvme_ns_head *head = disk->private_data;
+	int fail_if_no_path, err;
+
+	err = kstrtoint(buf, 10, &fail_if_no_path);
+	if (err)
+		return -EINVAL;
+
+	if (fail_if_no_path <= 0)
+		clear_bit(NVME_NSHEAD_FAIL_IF_NO_PATH, &head->flags);
+	else
+		set_bit(NVME_NSHEAD_FAIL_IF_NO_PATH, &head->flags);
+	return count;
+}
+DEVICE_ATTR(fail_if_no_path, S_IRUGO | S_IWUSR,
+	fail_if_no_path_show, fail_if_no_path_store);
+
 static int nvme_lookup_ana_group_desc(struct nvme_ctrl *ctrl,
 		struct nvme_ana_group_desc *desc, void *data)
 {
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 07b34175c6ce..3d2513f8194d 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -418,6 +418,7 @@ struct nvme_ns_head {
 	struct mutex		lock;
 	unsigned long		flags;
 #define NVME_NSHEAD_DISK_LIVE	0
+#define NVME_NSHEAD_FAIL_IF_NO_PATH	1
 	struct nvme_ns __rcu	*current_path[];
 #endif
 };
@@ -694,6 +695,7 @@ 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_fail_if_no_path;
 extern struct device_attribute subsys_attr_iopolicy;
 
 #else
-- 
2.29.2