From: Hannes Reinecke <hare@suse.de>
Date: Tue, 24 Aug 2021 16:57:42 +0200
Subject: nvme-multipath: revalidate paths during rescan
Patch-mainline: v5.15-rc1
Git-commit: e7d65803e2bb5bc739548b67a5fc72c626cf7e3b
References: bsc#1187211

When triggering a rescan due to a namespace resize we will be
receiving AENs on every controller, triggering a rescan of all
attached namespaces. If multipath is active only the current path and
the ns_head disk will be updated, the other paths will still refer to
the old size until AENs for the remaining controllers are received.

If I/O comes in before that it might be routed to one of the old
paths, triggering an I/O failure with 'access beyond end of device'.
With this patch the old paths are skipped from multipath path
selection until the controller serving these paths has been rescanned.

Signed-off-by: Hannes Reinecke <hare@suse.de>
[dwagner: - introduce NVME_NS_READY flag instead of NVME_NS_INVALIDATE
          - use 'revalidate' instead of 'invalidate' which
	    follows the zoned device code path.
	  - clear NVME_NS_READY before clearing current_path]
Signed-off-by: Daniel Wagner <dwagner@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/core.c      |    5 +++++
 drivers/nvme/host/multipath.c |   17 ++++++++++++++++-
 drivers/nvme/host/nvme.h      |    5 +++++
 3 files changed, 26 insertions(+), 1 deletion(-)

--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1946,12 +1946,15 @@ static void __nvme_revalidate_disk(struc
 	else
 		ns->pi_type = 0;
 
+	set_bit(NVME_NS_READY, &ns->flags);
+
 	if (iob)
 		blk_queue_chunk_sectors(ns->queue, rounddown_pow_of_two(iob));
 	nvme_update_disk_info(disk, ns, id);
 #ifdef CONFIG_NVME_MULTIPATH
 	if (ns->head->disk) {
 		nvme_update_disk_info(ns->head->disk, ns, id);
+		nvme_mpath_revalidate_paths(ns);
 		blk_queue_stack_limits(ns->head->disk->queue, ns->queue);
 		nvme_mpath_update_disk_size(ns->head->disk);
 	}
@@ -3764,6 +3767,8 @@ static void nvme_ns_remove(struct nvme_n
 	if (test_and_set_bit(NVME_NS_REMOVING, &ns->flags))
 		return;
 
+	clear_bit(NVME_NS_READY, &ns->flags);
+
 	nvme_fault_inject_fini(&ns->fault_inject);
 
 	mutex_lock(&ns->ctrl->subsys->lock);
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -168,6 +168,21 @@ void nvme_mpath_clear_ctrl_paths(struct
 	mutex_unlock(&ctrl->scan_lock);
 }
 
+void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
+{
+	struct nvme_ns_head *head = ns->head;
+	sector_t capacity = get_capacity(head->disk);
+	int node;
+
+	list_for_each_entry_rcu(ns, &head->list, siblings) {
+		if (capacity != get_capacity(ns->disk))
+			clear_bit(NVME_NS_READY, &ns->flags);
+	}
+
+	for_each_node(node)
+		rcu_assign_pointer(head->current_path[node], NULL);
+}
+
 static bool nvme_path_is_disabled(struct nvme_ns *ns)
 {
 	/*
@@ -179,7 +194,7 @@ static bool nvme_path_is_disabled(struct
 	    ns->ctrl->state != NVME_CTRL_DELETING)
 		return true;
 	if (test_bit(NVME_NS_ANA_PENDING, &ns->flags) ||
-	    test_bit(NVME_NS_REMOVING, &ns->flags))
+	    !test_bit(NVME_NS_READY, &ns->flags))
 		return true;
 	return false;
 }
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -423,6 +423,7 @@ struct nvme_ns {
 #define NVME_NS_REMOVING	0
 #define NVME_NS_DEAD     	1
 #define NVME_NS_ANA_PENDING	2
+#define NVME_NS_READY		4
 
 	struct nvme_fault_inject fault_inject;
 
@@ -650,6 +651,7 @@ void nvme_mpath_init_ctrl(struct nvme_ct
 void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
 void nvme_mpath_stop(struct nvme_ctrl *ctrl);
 bool nvme_mpath_clear_current_path(struct nvme_ns *ns);
+void nvme_mpath_revalidate_paths(struct nvme_ns *ns);
 void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl);
 struct nvme_ns *nvme_find_path(struct nvme_ns_head *head);
 
@@ -723,6 +725,9 @@ static inline bool nvme_mpath_clear_curr
 {
 	return false;
 }
+static inline void nvme_mpath_revalidate_paths(struct nvme_ns *ns)
+{
+}
 static inline void nvme_mpath_clear_ctrl_paths(struct nvme_ctrl *ctrl)
 {
 }