BACKPORT: slub: make sysfs directories for memcg sub-caches optional

SLUB creates a per-cache directory under /sys/kernel/slab which hosts a
bunch of debug files.  Usually, there aren't that many caches on a
system and this doesn't really matter; however, if memcg is in use, each
cache can have per-cgroup sub-caches.  SLUB creates the same directories
for these sub-caches under /sys/kernel/slab/$CACHE/cgroup.

Unfortunately, because there can be a lot of cgroups, active or
draining, the product of the numbers of caches, cgroups and files in
each directory can reach a very high number - hundreds of thousands is
commonplace.  Millions and beyond aren't difficult to reach either.

What's under /sys/kernel/slab is primarily for debugging and the
information and control on the a root cache already cover its
sub-caches.  While having a separate directory for each sub-cache can be
helpful for development, it doesn't make much sense to pay this amount
of overhead by default.

This patch introduces a boot parameter slub_memcg_sysfs which determines
whether to create sysfs directories for per-memcg sub-caches.  It also
adds CONFIG_SLUB_MEMCG_SYSFS_ON which determines the boot parameter's
default value and defaults to 0.

(cherry picked from commit 1663f26df3df7df3720306ca67f5ea8296d68fa1)
[akpm@linux-foundation.org: kset_unregister(NULL) is legal]
Link: http://lkml.kernel.org/r/20170204145203.GB26958@mtj.duckdns.org
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Bug: 113130132
Change-Id: I36b3b65ad583527c57518aa9f73a97ebd68d01b2
Signed-off-by: Minchan Kim <minchan@google.com>

3 files changed, 46 insertions, 2 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 44b5687..6d6e3c1 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -3986,6 +3986,14 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			last alloc / free. For more information see
 			Documentation/vm/slub.txt.
 
+	slub_memcg_sysfs=       [MM, SLUB]
+			Determines whether to enable sysfs directories for
+			memory cgroup sub-caches. 1 to enable, 0 to disable.
+			The default is determined by CONFIG_SLUB_MEMCG_SYSFS_ON.
+			Enabling this can lead to a very high number of debug
+			directories and files being created under
+			/sys/kernel/slub.
+
 	slub_max_order= [MM, SLUB]
 			Determines the maximum allowed order for slabs.
 			A high setting may cause OOMs due to memory
diff --git a/init/Kconfig b/init/Kconfig
index ead5f45..4ca610d 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1898,6 +1898,20 @@ config SLUB_DEBUG
 	  SLUB sysfs support. /sys/slab will not exist and there will be
 	  no support for cache validation etc.
 
+config SLUB_MEMCG_SYSFS_ON
+	default n
+	bool "Enable memcg SLUB sysfs support by default" if EXPERT
+	depends on SLUB && SYSFS && MEMCG
+	help
+	  SLUB creates a directory under /sys/kernel/slab for each
+	  allocation cache to host info and debug files. If memory
+	  cgroup is enabled, each cache can have per memory cgroup
+	  caches. SLUB can create the same sysfs directories for these
+	  caches under /sys/kernel/slab/CACHE/cgroup but it can lead
+	  to a very high number of debug files being created. This is
+	  controlled by slub_memcg_sysfs boot parameter and this
+	  config option determines the parameter's default value.
+
 config COMPAT_BRK
 	bool "Disable heap randomization"
 	default y
diff --git a/mm/slub.c b/mm/slub.c
index e0ce5de..b5468c2 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4667,6 +4667,22 @@ enum slab_stat_type {
 #define SO_OBJECTS	(1 << SL_OBJECTS)
 #define SO_TOTAL	(1 << SL_TOTAL)
 
+#ifdef CONFIG_MEMCG
+static bool memcg_sysfs_enabled = IS_ENABLED(CONFIG_SLUB_MEMCG_SYSFS_ON);
+
+static int __init setup_slub_memcg_sysfs(char *str)
+{
+	int v;
+
+	if (get_option(&str, &v) > 0)
+		memcg_sysfs_enabled = v;
+
+	return 1;
+}
+
+__setup("slub_memcg_sysfs=", setup_slub_memcg_sysfs);
+#endif
+
 static ssize_t show_slab_objects(struct kmem_cache *s,
 			    char *buf, unsigned long flags)
 {
@@ -5572,8 +5588,14 @@ static int sysfs_slab_add(struct kmem_cache *s)
 {
 	int err;
 	const char *name;
+	struct kset *kset = cache_kset(s);
 	int unmergeable = slab_unmergeable(s);
 
+	if (!kset) {
+		kobject_init(&s->kobj, &slab_ktype);
+		return 0;
+	}
+
 	if (unmergeable) {
 		/*
 		 * Slabcache can never be merged so we can use the name proper.
@@ -5590,7 +5612,7 @@ static int sysfs_slab_add(struct kmem_cache *s)
 		name = create_unique_id(s);
 	}
 
-	s->kobj.kset = cache_kset(s);
+	s->kobj.kset = kset;
 	err = kobject_init_and_add(&s->kobj, &slab_ktype, NULL, "%s", name);
 	if (err)
 		goto out;
@@ -5600,7 +5622,7 @@ static int sysfs_slab_add(struct kmem_cache *s)
 		goto out_del_kobj;
 
 #ifdef CONFIG_MEMCG
-	if (is_root_cache(s)) {
+	if (is_root_cache(s) && memcg_sysfs_enabled) {
 		s->memcg_kset = kset_create_and_add("cgroup", NULL, &s->kobj);
 		if (!s->memcg_kset) {
 			err = -ENOMEM;