[PATCH 2/2] nvme: fix unmatched id's under delayed path deletion

[Keith Busch]

From: Keith Busch <kbusch at kernel.org>

The NVMe controller is allowed to reuse an NSID for a new namespace after
deleting the previous namespace that had been using it. The delayed removal may
have the stale namespace head in the subsystem list pending the timer, which
would cause the scan to falsely report an ID mismatch error for the new
namespace. Flush the pending removal work and retry to resolve this.

Signed-off-by: Keith Busch <kbusch at kernel.org>
---
 drivers/nvme/host/core.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 3de52f1d27234..e731d3182f095 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -3966,6 +3966,7 @@ static int nvme_global_check_duplicate_ids(struct nvme_subsystem *this,
 
 static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info)
 {
+	bool retry = IS_ENABLED(CONFIG_NVME_MULTIPATH);
 	struct nvme_ctrl *ctrl = ns->ctrl;
 	struct nvme_ns_head *head = NULL;
 	int ret;
@@ -4008,6 +4009,7 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info)
 		ctrl->quirks |= NVME_QUIRK_BOGUS_NID;
 	}
 
+again:
 	mutex_lock(&ctrl->subsys->lock);
 	head = nvme_find_ns_head(ctrl, info->nsid);
 	if (!head) {
@@ -4033,6 +4035,22 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info)
 			goto out_put_ns_head;
 		}
 		if (!nvme_ns_ids_equal(&head->ids, &info->ids)) {
+			/*
+			 * A newly created namespace can reuse an NSID that was
+			 * previously deleted. If the head has no active paths,
+			 * it is pending delayed removal and still occupying
+			 * this NSID in the subsystem list. Flush the removal
+			 * work to clear the stale head and retry.
+			 */
+			if (retry && list_empty(&head->list)) {
+				mutex_unlock(&ctrl->subsys->lock);
+				flush_delayed_work(&head->remove_work);
+				nvme_put_ns_head(head);
+				retry = false;
+				goto again;
+			}
+
+			WARN_ONCE(list_empty(&head->list));
 			dev_err(ctrl->device,
 				"IDs don't match for shared namespace %d\n",
 					info->nsid);
-- 
2.47.3