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@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;