The following lockdep splat was observed while kernel auto-online a CXL
memory region:
======================================================
WARNING: possible circular locking dependency detected
6.17.0djtest+ #53 Tainted: G W
------------------------------------------------------
systemd-udevd/3334 is trying to acquire lock:
ffffffff90346188 (hmem_resource_lock){+.+.}-{4:4}, at:
hmem_register_resource+0x31/0x50
but task is already holding lock:
ffffffff90338890 ((node_chain).rwsem){++++}-{4:4}, at:
blocking_notifier_call_chain+0x2e/0x70
which lock already depends on the new lock.
[..]
Chain exists of:
hmem_resource_lock --> mem_hotplug_lock --> (node_chain).rwsem
Possible unsafe locking scenario:
CPU0 CPU1
---- ----
rlock((node_chain).rwsem);
lock(mem_hotplug_lock);
lock((node_chain).rwsem);
lock(hmem_resource_lock);
The lock ordering can cause potential deadlock. There are instances
where hmem_resource_lock is taken after (node_chain).rwsem, and vice
versa.
Remove registering of target devices from the hmat_callback(). By the
time the hmat hotplug notifier is being called, there should not be
hmem targets that still need to be registered.
Fixes: cf8741ac57ed ("ACPI: NUMA: HMAT: Register "soft reserved" memory as an
"hmem" device")
Link:
https://lore.kernel.org/nvdimm/[email protected]/
Suggested-by: Dan Williams <[email protected]>
Signed-off-by: Dave Jiang <[email protected]>
---
v2:
- Drop target registering in hmat_callback instead. (Dan)
---
drivers/acpi/numa/hmat.c | 10 ++++++----
1 file changed, 6 insertions(+), 4 deletions(-)
diff --git a/drivers/acpi/numa/hmat.c b/drivers/acpi/numa/hmat.c
index 5a36d57289b4..5084ae1688f6 100644
--- a/drivers/acpi/numa/hmat.c
+++ b/drivers/acpi/numa/hmat.c
@@ -874,7 +874,8 @@ static void hmat_register_target_devices(struct
memory_target *target)
}
}
-static void hmat_register_target(struct memory_target *target)
+static void hmat_register_target(struct memory_target *target,
+ bool register_devices)
{
int nid = pxm_to_node(target->memory_pxm);
@@ -882,7 +883,8 @@ static void hmat_register_target(struct memory_target
*target)
* Devices may belong to either an offline or online
* node, so unconditionally add them.
*/
- hmat_register_target_devices(target);
+ if (register_devices)
+ hmat_register_target_devices(target);
/*
* Register generic port perf numbers. The nid may not be
@@ -921,7 +923,7 @@ static void hmat_register_targets(void)
struct memory_target *target;
list_for_each_entry(target, &targets, node)
- hmat_register_target(target);
+ hmat_register_target(target, true);
}
static int hmat_callback(struct notifier_block *self,
@@ -939,7 +941,7 @@ static int hmat_callback(struct notifier_block *self,
if (!target)
return NOTIFY_OK;
- hmat_register_target(target);
+ hmat_register_target(target, false);
return NOTIFY_OK;
}
base-commit: 3a8660878839faadb4f1a6dd72c3179c1df56787
--
2.51.0
