[PATCH v4 1/2] nvme-multipath: fix path state evaluation for failfast and ANA

[Krishna Iyer]

nvme_available_path() has two problems that keep I/O queued when it
should be failed:

1. When fast_io_fail_tmo expires, NVME_CTRL_FAILFAST_EXPIRED is set and
   the path is skipped, but the function still falls through to
   nvme_mpath_queue_if_no_path(). If delayed_removal_secs is configured
   the I/O is requeued indefinitely, defeating fast_io_fail_tmo. Only
   fall through to queue_if_no_path when there really are no paths;
   if a path exists but its failfast timer has expired, fail instead.

2. A LIVE controller counts as a usable path regardless of the namespace
   ANA state. A path whose ANA state is inaccessible or persistent-loss
   cannot serve I/O, so it should not count as available. ANA change is
   transient and bounded by ANATT, so keep queueing while it resolves.

Also kick the requeue work from nvme_update_ns_ana_state() when a path
does not transition to live, so parked I/O is re-evaluated when an ANA
transition leaves the namespace inaccessible.

Move nvme_state_is_live() above nvme_available_path() so it can be used
there.

Assisted-by: Claude:claude-fable-5
Signed-off-by: Krishna Iyer <kiyer@xxxxxxxxx>
---
 drivers/nvme/host/multipath.c | 26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 11871f5f18c2..0d6c05f0808b 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -509,9 +509,15 @@ inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
 	}
 }
 
+static inline bool nvme_state_is_live(enum nvme_ana_state state)
+{
+	return state == NVME_ANA_OPTIMIZED || state == NVME_ANA_NONOPTIMIZED;
+}
+
 static bool nvme_available_path(struct nvme_ns_head *head)
 	__must_hold_shared(&head->srcu)
 {
+	bool failfast = false;
 	struct nvme_ns *ns;
 
 	if (!test_bit(NVME_NSHEAD_DISK_LIVE, &head->flags))
@@ -519,10 +525,16 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 
 	list_for_each_entry_srcu(ns, &head->list, siblings,
 				 srcu_read_lock_held(&head->srcu)) {
-		if (test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ns->ctrl->flags))
+		if (test_bit(NVME_CTRL_FAILFAST_EXPIRED, &ns->ctrl->flags)) {
+			failfast = true;
 			continue;
+		}
 		switch (nvme_ctrl_state(ns->ctrl)) {
 		case NVME_CTRL_LIVE:
+			if (!nvme_state_is_live(ns->ana_state) &&
+			    ns->ana_state != NVME_ANA_CHANGE)
+				continue;
+			return true;
 		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
 			return true;
@@ -531,6 +543,9 @@ static bool nvme_available_path(struct nvme_ns_head *head)
 		}
 	}
 
+	if (failfast)
+		return false;
+
 	/*
 	 * If "head->delayed_removal_secs" is configured (i.e., non-zero), do
 	 * not immediately fail I/O. Instead, requeue the I/O for the configured
@@ -887,11 +902,6 @@ static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
 	return 0;
 }
 
-static inline bool nvme_state_is_live(enum nvme_ana_state state)
-{
-	return state == NVME_ANA_OPTIMIZED || state == NVME_ANA_NONOPTIMIZED;
-}
-
 static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 		struct nvme_ns *ns)
 {
@@ -926,8 +936,10 @@ static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
 		 * is not live but still create the sysfs link to this path from
 		 * head node if head node of the path has already come alive.
 		 */
-		if (test_bit(NVME_NSHEAD_DISK_LIVE, &ns->head->flags))
+		if (test_bit(NVME_NSHEAD_DISK_LIVE, &ns->head->flags)) {
 			nvme_mpath_add_sysfs_link(ns->head);
+			kblockd_schedule_work(&ns->head->requeue_work);
+		}
 	}
 }
 
-- 
2.54.0