acpi/hmat: Fix lockdep warning for hmem_register_resource()

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.

Split out the target update section of hmat_register_target() so that
hmat_callback() only envokes that section instead of attempt to register
hmem devices that it does not need to.

[ dj: Fix up comment to be closer to 80cols. (Jonathan) ]

Fixes: cf8741ac57 ("ACPI: NUMA: HMAT: Register "soft reserved" memory as an "hmem" device")
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Tested-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Reviewed-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Link: https://patch.msgid.link/20251105235115.85062-3-dave.jiang@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
This commit is contained in:
Dave Jiang
2025-11-05 16:51:15 -07:00
parent b6cfddd26e
commit 214291cbaa

View File

@@ -874,10 +874,32 @@ static void hmat_register_target_devices(struct memory_target *target)
}
}
static void hmat_register_target(struct memory_target *target)
static void hmat_hotplug_target(struct memory_target *target)
{
int nid = pxm_to_node(target->memory_pxm);
/*
* Skip offline nodes. This can happen when memory marked EFI_MEMORY_SP,
* "specific purpose", is applied to all the memory in a proximity
* domain leading to * the node being marked offline / unplugged, or if
* memory-only "hotplug" node is offline.
*/
if (nid == NUMA_NO_NODE || !node_online(nid))
return;
guard(mutex)(&target_lock);
if (target->registered)
return;
hmat_register_target_initiators(target);
hmat_register_target_cache(target);
hmat_register_target_perf(target, ACCESS_COORDINATE_LOCAL);
hmat_register_target_perf(target, ACCESS_COORDINATE_CPU);
target->registered = true;
}
static void hmat_register_target(struct memory_target *target)
{
/*
* Devices may belong to either an offline or online
* node, so unconditionally add them.
@@ -895,25 +917,7 @@ static void hmat_register_target(struct memory_target *target)
}
mutex_unlock(&target_lock);
/*
* Skip offline nodes. This can happen when memory
* marked EFI_MEMORY_SP, "specific purpose", is applied
* to all the memory in a proximity domain leading to
* the node being marked offline / unplugged, or if
* memory-only "hotplug" node is offline.
*/
if (nid == NUMA_NO_NODE || !node_online(nid))
return;
mutex_lock(&target_lock);
if (!target->registered) {
hmat_register_target_initiators(target);
hmat_register_target_cache(target);
hmat_register_target_perf(target, ACCESS_COORDINATE_LOCAL);
hmat_register_target_perf(target, ACCESS_COORDINATE_CPU);
target->registered = true;
}
mutex_unlock(&target_lock);
hmat_hotplug_target(target);
}
static void hmat_register_targets(void)
@@ -939,7 +943,7 @@ static int hmat_callback(struct notifier_block *self,
if (!target)
return NOTIFY_OK;
hmat_register_target(target);
hmat_hotplug_target(target);
return NOTIFY_OK;
}