On 8/9/22 22:59, Waiman Long wrote:
A circular locking problem is reported by lockdep due to the following
circular locking dependency.
+--> cpu_hotplug_lock --> slab_mutex --> kn->active#126 --+
| |
+---------------------------------------------------------+
This sounded familiar and I've found a thread from January:
https://lore.kernel.org/all/388098b2c03fbf0a732834fc01b2d875c335bc49.1642170196.git.lucien.xin@xxxxxxxxx/
But that seemed to be specific to RHEL-8 RT kernel and not reproduced
with mainline. Is it different this time? Can you share the splats?
One way to break this circular locking chain is to avoid holding
cpu_hotplug_lock and slab_mutex while deleting the kobject in
sysfs_slab_unlink() which should be equivalent to doing a write_lock
and write_unlock pair of the kn->active virtual lock.
Since the kobject structures are not protected by slab_mutex or the
cpu_hotplug_lock, we can certainly release those locks before doing
the delete operation.
Move sysfs_slab_unlink() and sysfs_slab_release() to the newly
created kmem_cache_release() and call it outside the slab_mutex &
cpu_hotplug_lock critical sections.
Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
---
mm/slab_common.c | 48 +++++++++++++++++++++++++++++++-----------------
1 file changed, 31 insertions(+), 17 deletions(-)
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 17996649cfe3..9274fb03563e 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -392,6 +392,30 @@ kmem_cache_create(const char *name, unsigned int size, unsigned int align,
}
EXPORT_SYMBOL(kmem_cache_create);
+#ifdef SLAB_SUPPORTS_SYSFS
+/*
+ * For a given kmem_cache, kmem_cache_destroy() should only be called
+ * once or there will be a use-after-free problem. The actual deletion
+ * and release of the kobject does not need slab_mutex or cpu_hotplug_lock
+ * protection. So they are now done without holding those locks.
+ */
+static void kmem_cache_release(struct kmem_cache *s, bool workfn)
+{
+ if (!workfn)
+ sysfs_slab_unlink(s);
+
+ if (workfn || !(s->flags & SLAB_TYPESAFE_BY_RCU))
+ sysfs_slab_release(s);
+ else
+ schedule_work(&slab_caches_to_rcu_destroy_work);
+}
+#else
+static inline void kmem_cache_release(struct kmem_cache *s, bool workfn)
+{
+ slab_kmem_cache_release(s);
+}
+#endif
+
static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
{
LIST_HEAD(to_destroy);
@@ -418,11 +442,7 @@ static void slab_caches_to_rcu_destroy_workfn(struct work_struct *work)
list_for_each_entry_safe(s, s2, &to_destroy, list) {
debugfs_slab_release(s);
kfence_shutdown_cache(s);
-#ifdef SLAB_SUPPORTS_SYSFS
- sysfs_slab_release(s);
-#else
- slab_kmem_cache_release(s);
-#endif
+ kmem_cache_release(s, true);
}
}
@@ -437,20 +457,10 @@ static int shutdown_cache(struct kmem_cache *s)
list_del(&s->list);
if (s->flags & SLAB_TYPESAFE_BY_RCU) {
-#ifdef SLAB_SUPPORTS_SYSFS
- sysfs_slab_unlink(s);
-#endif
list_add_tail(&s->list, &slab_caches_to_rcu_destroy);
- schedule_work(&slab_caches_to_rcu_destroy_work);
} else {
kfence_shutdown_cache(s);
debugfs_slab_release(s);
-#ifdef SLAB_SUPPORTS_SYSFS
- sysfs_slab_unlink(s);
- sysfs_slab_release(s);
-#else
- slab_kmem_cache_release(s);
-#endif
}
return 0;
@@ -465,14 +475,16 @@ void slab_kmem_cache_release(struct kmem_cache *s)
void kmem_cache_destroy(struct kmem_cache *s)
{
+ int refcnt;
+
if (unlikely(!s) || !kasan_check_byte(s))
return;
cpus_read_lock();
mutex_lock(&slab_mutex);
- s->refcount--;
- if (s->refcount)
+ refcnt = --s->refcount;
+ if (refcnt)
goto out_unlock;
WARN(shutdown_cache(s),
@@ -481,6 +493,8 @@ void kmem_cache_destroy(struct kmem_cache *s)
out_unlock:
mutex_unlock(&slab_mutex);
cpus_read_unlock();
+ if (!refcnt)
+ kmem_cache_release(s, false);
}
EXPORT_SYMBOL(kmem_cache_destroy);
