[PATCH 5.4 107/178] nvme: don't protect ns mutation with ns->head->lock

[Sasha Levin]

From: Sagi Grimberg <sagi@xxxxxxxxxxx>

[ Upstream commit e164471dcf19308d154adb69e7760d8ba426a77f ]

Right now ns->head->lock is protecting namespace mutation
which is wrong and unneeded. Move it to only protect
against head mutations. While we're at it, remove unnecessary
ns->head reference as we already have head pointer.

The problem with this is that the head->lock spans
mpath disk node I/O that may block under some conditions (if
for example the controller is disconnecting or the path
became inaccessible), The locking scheme does not allow any
other path to enable itself, preventing blocked I/O to complete
and forward-progress from there.

This is a preparation patch for the fix in a subsequent patch
where the disk I/O will also be done outside the head->lock.

Fixes: 0d0b660f214d ("nvme: add ANA support")
Signed-off-by: Anton Eidelman <anton@xxxxxxxxxxxxxxxxx>
Signed-off-by: Sagi Grimberg <sagi@xxxxxxxxxxx>
Signed-off-by: Christoph Hellwig <hch@xxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
---
 drivers/nvme/host/multipath.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 0f08c15553a64..18f0a05c74b56 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -414,11 +414,10 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 {
 	struct nvme_ns_head *head = ns->head;
 
-	lockdep_assert_held(&ns->head->lock);
-
 	if (!head->disk)
 		return;
 
+	mutex_lock(&head->lock);
 	if (!(head->disk->flags & GENHD_FL_UP))
 		device_add_disk(&head->subsys->dev, head->disk,
 				nvme_ns_id_attr_groups);
@@ -431,9 +430,10 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 			__nvme_find_path(head, node);
 		srcu_read_unlock(&head->srcu, srcu_idx);
 	}
+	mutex_unlock(&head->lock);
 
-	synchronize_srcu(&ns->head->srcu);
-	kblockd_schedule_work(&ns->head->requeue_work);
+	synchronize_srcu(&head->srcu);
+	kblockd_schedule_work(&head->requeue_work);
 }
 
 static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
@@ -484,14 +484,12 @@ static inline bool nvme_state_is_live(enum nvme_ana_state state)
 static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 		struct nvme_ns *ns)
 {
-	mutex_lock(&ns->head->lock);
 	ns->ana_grpid = le32_to_cpu(desc->grpid);
 	ns->ana_state = desc->state;
 	clear_bit(NVME_NS_ANA_PENDING, &ns->flags);
 
 	if (nvme_state_is_live(ns->ana_state))
 		nvme_mpath_set_live(ns);
-	mutex_unlock(&ns->head->lock);
 }
 
 static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
@@ -670,10 +668,8 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
 			nvme_update_ns_ana_state(&desc, ns);
 		}
 	} else {
-		mutex_lock(&ns->head->lock);
 		ns->ana_state = NVME_ANA_OPTIMIZED; 
 		nvme_mpath_set_live(ns);
-		mutex_unlock(&ns->head->lock);
 	}
 
 	if (bdi_cap_stable_pages_required(ns->queue->backing_dev_info)) {
-- 
2.25.1