[PATCH v2 3/4] mm/slub: Fix another circular locking dependency in slab_attr_store()

[Waiman Long]

It turns out that switching from slab_mutex to memcg_cache_ids_sem in
slab_attr_store() does not completely eliminate circular locking dependency
as shown by the following lockdep splat when the system is shut down:

[ 2095.079697] Chain exists of:
[ 2095.079697]   kn->count#278 --> memcg_cache_ids_sem --> slab_mutex
[ 2095.079697]
[ 2095.090278]  Possible unsafe locking scenario:
[ 2095.090278]
[ 2095.096227]        CPU0                    CPU1
[ 2095.100779]        ----                    ----
[ 2095.105331]   lock(slab_mutex);
[ 2095.108486]                                lock(memcg_cache_ids_sem);
[ 2095.114961]                                lock(slab_mutex);
[ 2095.120649]   lock(kn->count#278);
[ 2095.124068]
[ 2095.124068]  *** DEADLOCK ***

To eliminate this possibility, we have to use trylock to acquire
memcg_cache_ids_sem. Unlikely slab_mutex which can be acquired in
many places, the memcg_cache_ids_sem write lock is only acquired
in memcg_alloc_cache_id() to double the size of memcg_nr_cache_ids.
So the chance of successive calls to memcg_alloc_cache_id() within
a short time is pretty low. As a result, we can retry the read lock
acquisition a few times if the first attempt fails.

Signed-off-by: Waiman Long <longman@xxxxxxxxxx>
---
 include/linux/memcontrol.h |  1 +
 mm/memcontrol.c            |  5 +++++
 mm/slub.c                  | 25 +++++++++++++++++++++++--
 3 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index d275c72c4f8e..9285f14965b1 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -1379,6 +1379,7 @@ extern struct workqueue_struct *memcg_kmem_cache_wq;
 extern int memcg_nr_cache_ids;
 void memcg_get_cache_ids(void);
 void memcg_put_cache_ids(void);
+int  memcg_tryget_cache_ids(void);
 
 /*
  * Helper macro to loop through all memcg-specific caches. Callers must still
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 5beea03dd58a..9fa8535ff72a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -279,6 +279,11 @@ void memcg_get_cache_ids(void)
 	down_read(&memcg_cache_ids_sem);
 }
 
+int memcg_tryget_cache_ids(void)
+{
+	return down_read_trylock(&memcg_cache_ids_sem);
+}
+
 void memcg_put_cache_ids(void)
 {
 	up_read(&memcg_cache_ids_sem);
diff --git a/mm/slub.c b/mm/slub.c
index 44cb5215c17f..cf2114ca27f7 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -34,6 +34,7 @@
 #include <linux/prefetch.h>
 #include <linux/memcontrol.h>
 #include <linux/random.h>
+#include <linux/delay.h>
 
 #include <trace/events/kmem.h>
 
@@ -5572,6 +5573,7 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 	    !list_empty(&s->memcg_params.children)) {
 		struct kmem_cache *c, **pcaches;
 		int idx, max, cnt = 0;
+		int retries = 3;
 		size_t size, old = s->max_attr_size;
 		struct memcg_cache_array *arr;
 
@@ -5585,9 +5587,28 @@ static ssize_t slab_attr_store(struct kobject *kobj,
 			old = cmpxchg(&s->max_attr_size, size, len);
 		} while (old != size);
 
-		memcg_get_cache_ids();
-		max = memcg_nr_cache_ids;
+		/*
+		 * To avoid the following circular lock chain
+		 *
+		 *   kn->count#278 --> memcg_cache_ids_sem --> slab_mutex
+		 *
+		 * We need to use trylock to acquire memcg_cache_ids_sem.
+		 *
+		 * Since the write lock is acquired only in
+		 * memcg_alloc_cache_id() to double the size of
+		 * memcg_nr_cache_ids. The chance of successive
+		 * memcg_alloc_cache_id() calls within a short time is
+		 * very low except at the beginning where the number of
+		 * memory cgroups is low. So we retry a few times to get
+		 * the memcg_cache_ids_sem read lock.
+		 */
+		while (!memcg_tryget_cache_ids()) {
+			if (retries-- <= 0)
+				return -EBUSY;
+			msleep(100);
+		}
 
+		max = memcg_nr_cache_ids;
 		pcaches = kmalloc_array(max, sizeof(void *), GFP_KERNEL);
 		if (!pcaches) {
 			memcg_put_cache_ids();
-- 
2.18.1