[PATCH 45/46] mm/memory-tiers: unregister empty tiers outside memory_tier_lock
From: David Hildenbrand (Arm)
Date: Mon Oct 26 2026 - 19:38:39 EST
When offlining a node's last memory empties its tier,
clear_node_memory_tier() calls device_unregister() while holding
memory_tier_lock. A concurrent sysfs read can hold a kernfs active
reference and block in nodelist_show() on that mutex. device_unregister()
then waits in kernfs_drain() for the read to finish and release its active
reference, while the reader waits for the offlining task to release the
mutex.
Return the node's former tier from clear_node_memory_tier(), making the
helper more similar to set_node_memory_tier(), which also returns a
memory_tier pointer. Let the caller unlink an empty tier under
memory_tier_lock before rebuilding demotion targets, then unregister its
device after dropping the lock.
Fixes: 9832fb87834e ("mm/demotion: expose memory tier details via sysfs")
Cc: stable@xxxxxxxxxxxxxxx
Reported-by: Josef Bacik <josef@xxxxxxxxxxxxxx>
Signed-off-by: David Hildenbrand (Arm) <david@xxxxxxxxxx>
---
mm/memory-tiers.c | 29 +++++++++++++----------------
1 file changed, 13 insertions(+), 16 deletions(-)
diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c
index 25e121851b586..8eda313cf6192 100644
--- a/mm/memory-tiers.c
+++ b/mm/memory-tiers.c
@@ -572,21 +572,14 @@ static struct memory_tier *set_node_memory_tier(int node)
return memtier;
}
-static void destroy_memory_tier(struct memory_tier *memtier)
+static struct memory_tier *clear_node_memory_tier(int node)
{
- list_del(&memtier->list);
- device_unregister(&memtier->dev);
-}
-
-static bool clear_node_memory_tier(int node)
-{
- bool cleared = false;
pg_data_t *pgdat;
struct memory_tier *memtier;
pgdat = NODE_DATA(node);
if (!pgdat)
- return false;
+ return NULL;
/*
* Make sure that anybody looking at NODE_DATA who finds
@@ -604,14 +597,10 @@ static bool clear_node_memory_tier(int node)
synchronize_rcu();
memtype = node_memory_types[node].memtype;
node_clear(node, memtype->nodes);
- if (nodes_empty(memtype->nodes)) {
+ if (nodes_empty(memtype->nodes))
list_del_init(&memtype->tier_sibling);
- if (list_empty(&memtier->memory_types))
- destroy_memory_tier(memtier);
- }
- cleared = true;
}
- return cleared;
+ return memtier;
}
static void release_memtype(struct kref *kref)
@@ -884,13 +873,21 @@ static int __meminit memtier_hotplug_callback(struct notifier_block *self,
{
struct memory_tier *memtier;
struct node_notify *nn = _arg;
+ bool empty = false;
switch (action) {
case NODE_REMOVED_LAST_MEMORY:
mutex_lock(&memory_tier_lock);
- if (clear_node_memory_tier(nn->nid))
+ memtier = clear_node_memory_tier(nn->nid);
+ if (memtier) {
+ empty = list_empty(&memtier->memory_types);
+ if (empty)
+ list_del(&memtier->list);
establish_demotion_targets();
+ }
mutex_unlock(&memory_tier_lock);
+ if (empty)
+ device_unregister(&memtier->dev);
break;
case NODE_ADDED_FIRST_MEMORY:
mutex_lock(&memory_tier_lock);
--
2.43.0