[PATCH 3/3] nvme-multipath: stuck partition scan on inaccessible paths

[Hannes Reinecke <hare@kernel.org>]

When a path is switched to 'inaccessible' during partition scan
triggered via device_add_disk() and we only have one path the
system will be stuck as nvme_available_path() will always return
'true'. So I/O will never be completed and the system is stuck
in device_add_disk():

    [<0>] folio_wait_bit_common+0x12a/0x310
    [<0>] filemap_read_folio+0x97/0xd0
    [<0>] do_read_cache_folio+0x108/0x390
    [<0>] read_part_sector+0x31/0xa0
    [<0>] read_lba+0xc5/0x160
    [<0>] efi_partition+0xd9/0x8f0
    [<0>] bdev_disk_changed+0x23d/0x6d0
    [<0>] blkdev_get_whole+0x78/0xc0
    [<0>] bdev_open+0x2c6/0x3b0
    [<0>] bdev_file_open_by_dev+0xcb/0x120
    [<0>] disk_scan_partitions+0x5d/0x100
    [<0>] device_add_disk+0x402/0x420
    [<0>] nvme_mpath_set_live+0x4f/0x1f0 [nvme_core]
    [<0>] nvme_mpath_add_disk+0x107/0x120 [nvme_core]
    [<0>] nvme_alloc_ns+0xac6/0xe60 [nvme_core]
    [<0>] nvme_scan_ns+0x2dd/0x3e0 [nvme_core]
    [<0>] nvme_scan_work+0x1a3/0x490 [nvme_core]

This patch introduces a flag NVME_NSHEAD_FAIL_ON_LAST_PATH to
cause nvme_available_path() to always return NULL, and with
that I/O to be failed if the last path is unavailable. But
we also need to requeue all pending I/Os whenever we have
changed the ANA state as now even inaccessible ANA states
influence I/O behaviour.

Signed-off-by: Hannes Reinecke <hare@kernel.org>
---
 drivers/nvme/host/multipath.c | 15 +++++++++++++++
 drivers/nvme/host/nvme.h      |  1 +
 2 files changed, 16 insertions(+)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index f72c5a6a2d8e..0373b4043eea 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -422,6 +422,10 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 	struct nvme_ns *ns;
 
 	if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags))
+	    return NULL;
+
+	if (test_bit(NVME_NSHEAD_FAIL_ON_LAST_PATH, &head->flags) &&
+	    list_is_singular(&head->list))
 		return NULL;
 
 	list_for_each_entry_rcu(ns, &head->list, siblings) {
@@ -646,8 +650,15 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 	 * head.
 	 */
 	if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
+		/*
+		 * Disable queueing to ensure I/O is not retried on unusable
+		 * paths, which would cause the system to be stuck during
+		 * partition scan.
+		 */
+		set_bit(NVME_NSHEAD_FAIL_ON_LAST_PATH, &head->flags);
 		rc = device_add_disk(&head->subsys->dev, head->disk,
 				     nvme_ns_attr_groups);
+		clear_bit(NVME_NSHEAD_FAIL_ON_LAST_PATH, &head->flags);
 		if (rc) {
 			clear_bit(NVME_NSHEAD_DISK_LIVE, &head->flags);
 			return;
@@ -737,6 +748,10 @@ static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 	if (nvme_state_is_live(ns->ana_state) &&
 	    nvme_ctrl_state(ns->ctrl) == NVME_CTRL_LIVE)
 		nvme_mpath_set_live(ns);
+	else {
+		synchronize_srcu(&ns->head->srcu);
+		kblockd_schedule_work(&ns->head->requeue_work);
+	}
 }
 
 static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 50515ad0f9d6..6aef38eba293 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -493,6 +493,7 @@ struct nvme_ns_head {
 	struct mutex		lock;
 	unsigned long		flags;
 #define NVME_NSHEAD_DISK_LIVE	0
+#define NVME_NSHEAD_FAIL_ON_LAST_PATH	1
 	struct nvme_ns __rcu	*current_path[];
 #endif
 };
-- 
2.35.3