[PATCH] nvme-multipath: revalidate zones for namespace heads

[Yao Sang]

Zoned multipath namespace heads get BLK_FEAT_ZONED and their limits are
refreshed from the paths, but the zone state for the head disk is never
initialized.  The previous nr_zones assignment only updated a single
field and did not allocate or populate the block layer's per-zone state.

That leaves the head disk without valid zone condition information.  Code
using the head device, such as bdev_zone_is_seq(), can then treat a
sequential zone as non-sequential and submit regular writes to it.

Add a small helper to run blk_revalidate_disk_zones() for a live zoned
namespace head after the path limits have been committed and when a path
becomes live.  Return the error to the namespace update path, and keep the
live path transition as a warning-only update.  Drop the nr_zones copy, as
blk_revalidate_disk_zones() updates it together with the rest of the zoned
disk state.

Signed-off-by: Yao Sang <sangyao at kylinos.cn>
---
The failure was found with xfstests xfs/643 and xfs/646 on an NVMe
ZNS multipath namespace. Tracing showed regular REQ_OP_WRITE I/O being
submitted to sequential zones through the multipath head.

The head queue had the zoned limits stacked from the path, but the head
gendisk had not gone through blk_revalidate_disk_zones(). That left the
block layer per-zone state missing on the head disk, so users of the head
device could treat sequential zones as non-sequential.

The fix keeps the existing limit stacking and revalidates zones for the
live namespace head, so nr_zones, zone conditions and zone write plug state
are initialized together.

tested with:
- xfstests: xfs/643, xfs/646
- blktests: nvme/005, nvme/057, nvme/058
- blktests: zbd/011, zbd/012, zbd/013, block/004
  zbd/001, zbd/002, zbd/003, zbd/004,
  zbd/005, zbd/006

 drivers/nvme/host/core.c      |  4 ++++
 drivers/nvme/host/multipath.c | 24 ++++++++++++++++++++----
 drivers/nvme/host/nvme.h      |  9 +++++++++
 3 files changed, 33 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index efaddab8296e..0e28b83156c0 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2589,11 +2589,15 @@ static int nvme_update_ns_info(struct nvme_ns *ns, struct nvme_ns_info *info)
 		lim.max_write_streams = ns_lim->max_write_streams;
 		lim.write_stream_granularity = ns_lim->write_stream_granularity;
 		ret = queue_limits_commit_update(ns->head->disk->queue, &lim);
+		if (ret)
+			goto unfreeze_head_queue;
 
 		set_capacity_and_notify(ns->head->disk, get_capacity(ns->disk));
 		set_disk_ro(ns->head->disk, nvme_ns_is_readonly(ns, info));
 		nvme_mpath_revalidate_paths(ns->head);
+		ret = nvme_mpath_revalidate_zones(ns->head);
 
+unfreeze_head_queue:
 		blk_mq_unfreeze_queue(ns->head->disk->queue, memflags);
 	}
 
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 96337ae2b552..0a94a9af5fe8 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -285,6 +285,25 @@ void nvme_mpath_revalidate_paths(struct nvme_ns_head *head)
 	kblockd_schedule_work(&head->requeue_work);
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+int nvme_mpath_revalidate_zones(struct nvme_ns_head *head)
+{
+	struct gendisk *disk = head->disk;
+	int ret;
+
+	if (!disk || !blk_queue_is_zoned(disk->queue) ||
+	    !test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags))
+		return 0;
+
+	ret = blk_revalidate_disk_zones(disk);
+	if (ret)
+		dev_warn_ratelimited(disk_to_dev(disk),
+				     "failed to revalidate zoned namespace head: %d\n",
+				     ret);
+	return ret;
+}
+#endif /* CONFIG_BLK_DEV_ZONED */
+
 static bool nvme_path_is_disabled(struct nvme_ns *ns)
 {
 	enum nvme_ctrl_state state = nvme_ctrl_state(ns->ctrl);
@@ -812,6 +831,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 	mutex_unlock(&head->lock);
 
 	synchronize_srcu(&head->srcu);
+	nvme_mpath_revalidate_zones(head);
 	kblockd_schedule_work(&head->requeue_work);
 }
 
@@ -1368,10 +1388,6 @@ void nvme_mpath_add_disk(struct nvme_ns *ns, __le32 anagrpid)
 		nvme_mpath_set_live(ns);
 	}
 
-#ifdef CONFIG_BLK_DEV_ZONED
-	if (blk_queue_is_zoned(ns->queue) && ns->head->disk)
-		ns->head->disk->nr_zones = ns->disk->nr_zones;
-#endif
 }
 
 void nvme_mpath_remove_disk(struct nvme_ns_head *head)
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index b367c67dcb37..60cad6959562 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -1181,6 +1181,15 @@ static inline bool nvme_mpath_queue_if_no_path(struct nvme_ns_head *head)
 }
 #endif /* CONFIG_NVME_MULTIPATH */
 
+#if defined(CONFIG_NVME_MULTIPATH) && defined(CONFIG_BLK_DEV_ZONED)
+int nvme_mpath_revalidate_zones(struct nvme_ns_head *head);
+#else
+static inline int nvme_mpath_revalidate_zones(struct nvme_ns_head *head)
+{
+	return 0;
+}
+#endif
+
 int nvme_ns_get_unique_id(struct nvme_ns *ns, u8 id[16],
 		enum blk_unique_id type);
 
-- 
2.25.1