1 files changed, 199 insertions, 70 deletions

diff --git a/mm/slab_common.c b/mm/slab_common.c
index 58251ba63e4a..6c49dbb3769e 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -17,6 +17,7 @@
 #include <linux/uaccess.h>
 #include <linux/seq_file.h>
 #include <linux/proc_fs.h>
+#include <linux/debugfs.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm/page.h>
@@ -130,6 +131,9 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr,
 #ifdef CONFIG_MEMCG_KMEM
 
 LIST_HEAD(slab_root_caches);
+static DEFINE_SPINLOCK(memcg_kmem_wq_lock);
+
+static void kmemcg_cache_shutdown(struct percpu_ref *percpu_ref);
 
 void slab_init_memcg_params(struct kmem_cache *s)
 {
@@ -140,13 +144,18 @@ void slab_init_memcg_params(struct kmem_cache *s)
 }
 
 static int init_memcg_params(struct kmem_cache *s,
-		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
+			     struct kmem_cache *root_cache)
 {
 	struct memcg_cache_array *arr;
 
 	if (root_cache) {
+		int ret = percpu_ref_init(&s->memcg_params.refcnt,
+					  kmemcg_cache_shutdown,
+					  0, GFP_KERNEL);
+		if (ret)
+			return ret;
+
 		s->memcg_params.root_cache = root_cache;
-		s->memcg_params.memcg = memcg;
 		INIT_LIST_HEAD(&s->memcg_params.children_node);
 		INIT_LIST_HEAD(&s->memcg_params.kmem_caches_node);
 		return 0;
@@ -171,6 +180,8 @@ static void destroy_memcg_params(struct kmem_cache *s)
 {
 	if (is_root_cache(s))
 		kvfree(rcu_access_pointer(s->memcg_params.memcg_caches));
+	else
+		percpu_ref_exit(&s->memcg_params.refcnt);
 }
 
 static void free_memcg_params(struct rcu_head *rcu)
@@ -221,11 +232,13 @@ int memcg_update_all_caches(int num_memcgs)
 	return ret;
 }
 
-void memcg_link_cache(struct kmem_cache *s)
+void memcg_link_cache(struct kmem_cache *s, struct mem_cgroup *memcg)
 {
 	if (is_root_cache(s)) {
 		list_add(&s->root_caches_node, &slab_root_caches);
 	} else {
+		css_get(&memcg->css);
+		s->memcg_params.memcg = memcg;
 		list_add(&s->memcg_params.children_node,
 			 &s->memcg_params.root_cache->memcg_params.children);
 		list_add(&s->memcg_params.kmem_caches_node,
@@ -240,11 +253,13 @@ static void memcg_unlink_cache(struct kmem_cache *s)
 	} else {
 		list_del(&s->memcg_params.children_node);
 		list_del(&s->memcg_params.kmem_caches_node);
+		mem_cgroup_put(s->memcg_params.memcg);
+		WRITE_ONCE(s->memcg_params.memcg, NULL);
 	}
 }
 #else
 static inline int init_memcg_params(struct kmem_cache *s,
-		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
+				    struct kmem_cache *root_cache)
 {
 	return 0;
 }
@@ -384,7 +399,7 @@ static struct kmem_cache *create_cache(const char *name,
 	s->useroffset = useroffset;
 	s->usersize = usersize;
 
-	err = init_memcg_params(s, memcg, root_cache);
+	err = init_memcg_params(s, root_cache);
 	if (err)
 		goto out_free_cache;
 
@@ -394,7 +409,7 @@ static struct kmem_cache *create_cache(const char *name,
 
 	s->refcount = 1;
 	list_add(&s->list, &slab_caches);
-	memcg_link_cache(s);
+	memcg_link_cache(s, memcg);
 out:
 	if (err)
 		return ERR_PTR(err);
@@ -640,7 +655,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 	 * The memory cgroup could have been offlined while the cache
 	 * creation work was pending.
 	 */
-	if (memcg->kmem_state != KMEM_ONLINE || root_cache->memcg_params.dying)
+	if (memcg->kmem_state != KMEM_ONLINE)
 		goto out_unlock;
 
 	idx = memcg_cache_id(memcg);
@@ -677,7 +692,7 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg,
 	}
 
 	/*
-	 * Since readers won't lock (see cache_from_memcg_idx()), we need a
+	 * Since readers won't lock (see memcg_kmem_get_cache()), we need a
 	 * barrier here to ensure nobody will see the kmem_cache partially
 	 * initialized.
 	 */
@@ -691,74 +706,95 @@ out_unlock:
 	put_online_cpus();
 }
 
-static void kmemcg_deactivate_workfn(struct work_struct *work)
+static void kmemcg_workfn(struct work_struct *work)
 {
 	struct kmem_cache *s = container_of(work, struct kmem_cache,
-					    memcg_params.deact_work);
+					    memcg_params.work);
 
 	get_online_cpus();
 	get_online_mems();
 
 	mutex_lock(&slab_mutex);
-
-	s->memcg_params.deact_fn(s);
-
+	s->memcg_params.work_fn(s);
 	mutex_unlock(&slab_mutex);
 
 	put_online_mems();
 	put_online_cpus();
-
-	/* done, put the ref from slab_deactivate_memcg_cache_rcu_sched() */
-	css_put(&s->memcg_params.memcg->css);
 }
 
-static void kmemcg_deactivate_rcufn(struct rcu_head *head)
+static void kmemcg_rcufn(struct rcu_head *head)
 {
 	struct kmem_cache *s = container_of(head, struct kmem_cache,
-					    memcg_params.deact_rcu_head);
+					    memcg_params.rcu_head);
 
 	/*
-	 * We need to grab blocking locks.  Bounce to ->deact_work.  The
+	 * We need to grab blocking locks.  Bounce to ->work.  The
 	 * work item shares the space with the RCU head and can't be
 	 * initialized eariler.
 	 */
-	INIT_WORK(&s->memcg_params.deact_work, kmemcg_deactivate_workfn);
-	queue_work(memcg_kmem_cache_wq, &s->memcg_params.deact_work);
+	INIT_WORK(&s->memcg_params.work, kmemcg_workfn);
+	queue_work(memcg_kmem_cache_wq, &s->memcg_params.work);
 }
 
-/**
- * slab_deactivate_memcg_cache_rcu_sched - schedule deactivation after a
- *					   sched RCU grace period
- * @s: target kmem_cache
- * @deact_fn: deactivation function to call
- *
- * Schedule @deact_fn to be invoked with online cpus, mems and slab_mutex
- * held after a sched RCU grace period.  The slab is guaranteed to stay
- * alive until @deact_fn is finished.  This is to be used from
- * __kmemcg_cache_deactivate().
- */
-void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s,
-					   void (*deact_fn)(struct kmem_cache *))
+static void kmemcg_cache_shutdown_fn(struct kmem_cache *s)
 {
-	if (WARN_ON_ONCE(is_root_cache(s)) ||
-	    WARN_ON_ONCE(s->memcg_params.deact_fn))
-		return;
+	WARN_ON(shutdown_cache(s));
+}
+
+static void kmemcg_cache_shutdown(struct percpu_ref *percpu_ref)
+{
+	struct kmem_cache *s = container_of(percpu_ref, struct kmem_cache,
+					    memcg_params.refcnt);
+	unsigned long flags;
 
+	spin_lock_irqsave(&memcg_kmem_wq_lock, flags);
 	if (s->memcg_params.root_cache->memcg_params.dying)
+		goto unlock;
+
+	s->memcg_params.work_fn = kmemcg_cache_shutdown_fn;
+	INIT_WORK(&s->memcg_params.work, kmemcg_workfn);
+	queue_work(memcg_kmem_cache_wq, &s->memcg_params.work);
+
+unlock:
+	spin_unlock_irqrestore(&memcg_kmem_wq_lock, flags);
+}
+
+static void kmemcg_cache_deactivate_after_rcu(struct kmem_cache *s)
+{
+	__kmemcg_cache_deactivate_after_rcu(s);
+	percpu_ref_kill(&s->memcg_params.refcnt);
+}
+
+static void kmemcg_cache_deactivate(struct kmem_cache *s)
+{
+	if (WARN_ON_ONCE(is_root_cache(s)))
 		return;
 
-	/* pin memcg so that @s doesn't get destroyed in the middle */
-	css_get(&s->memcg_params.memcg->css);
+	__kmemcg_cache_deactivate(s);
+	s->flags |= SLAB_DEACTIVATED;
+
+	/*
+	 * memcg_kmem_wq_lock is used to synchronize memcg_params.dying
+	 * flag and make sure that no new kmem_cache deactivation tasks
+	 * are queued (see flush_memcg_workqueue() ).
+	 */
+	spin_lock_irq(&memcg_kmem_wq_lock);
+	if (s->memcg_params.root_cache->memcg_params.dying)
+		goto unlock;
 
-	s->memcg_params.deact_fn = deact_fn;
-	call_rcu(&s->memcg_params.deact_rcu_head, kmemcg_deactivate_rcufn);
+	s->memcg_params.work_fn = kmemcg_cache_deactivate_after_rcu;
+	call_rcu(&s->memcg_params.rcu_head, kmemcg_rcufn);
+unlock:
+	spin_unlock_irq(&memcg_kmem_wq_lock);
 }
 
-void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
+void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg,
+				  struct mem_cgroup *parent)
 {
 	int idx;
 	struct memcg_cache_array *arr;
 	struct kmem_cache *s, *c;
+	unsigned int nr_reparented;
 
 	idx = memcg_cache_id(memcg);
 
@@ -773,30 +809,20 @@ void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
 		if (!c)
 			continue;
 
-		__kmemcg_cache_deactivate(c);
+		kmemcg_cache_deactivate(c);
 		arr->entries[idx] = NULL;
 	}
-	mutex_unlock(&slab_mutex);
-
-	put_online_mems();
-	put_online_cpus();
-}
-
-void memcg_destroy_kmem_caches(struct mem_cgroup *memcg)
-{
-	struct kmem_cache *s, *s2;
-
-	get_online_cpus();
-	get_online_mems();
-
-	mutex_lock(&slab_mutex);
-	list_for_each_entry_safe(s, s2, &memcg->kmem_caches,
-				 memcg_params.kmem_caches_node) {
-		/*
-		 * The cgroup is about to be freed and therefore has no charges
-		 * left. Hence, all its caches must be empty by now.
-		 */
-		BUG_ON(shutdown_cache(s));
+	nr_reparented = 0;
+	list_for_each_entry(s, &memcg->kmem_caches,
+			    memcg_params.kmem_caches_node) {
+		WRITE_ONCE(s->memcg_params.memcg, parent);
+		css_put(&memcg->css);
+		nr_reparented++;
+	}
+	if (nr_reparented) {
+		list_splice_init(&memcg->kmem_caches,
+				 &parent->kmem_caches);
+		css_get_many(&parent->css, nr_reparented);
 	}
 	mutex_unlock(&slab_mutex);
 
@@ -861,16 +887,15 @@ static int shutdown_memcg_caches(struct kmem_cache *s)
 
 static void flush_memcg_workqueue(struct kmem_cache *s)
 {
-	mutex_lock(&slab_mutex);
+	spin_lock_irq(&memcg_kmem_wq_lock);
 	s->memcg_params.dying = true;
-	mutex_unlock(&slab_mutex);
+	spin_unlock_irq(&memcg_kmem_wq_lock);
 
 	/*
-	 * SLUB deactivates the kmem_caches through call_rcu. Make
+	 * SLAB and SLUB deactivate the kmem_caches through call_rcu. Make
 	 * sure all registered rcu callbacks have been invoked.
 	 */
-	if (IS_ENABLED(CONFIG_SLUB))
-		rcu_barrier();
+	rcu_barrier();
 
 	/*
 	 * SLAB and SLUB create memcg kmem_caches through workqueue and SLUB
@@ -997,7 +1022,7 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name,
 
 	create_boot_cache(s, name, size, flags, useroffset, usersize);
 	list_add(&s->list, &slab_caches);
-	memcg_link_cache(s);
+	memcg_link_cache(s, NULL);
 	s->refcount = 1;
 	return s;
 }
@@ -1498,6 +1523,64 @@ static int __init slab_proc_init(void)
 	return 0;
 }
 module_init(slab_proc_init);
+
+#if defined(CONFIG_DEBUG_FS) && defined(CONFIG_MEMCG_KMEM)
+/*
+ * Display information about kmem caches that have child memcg caches.
+ */
+static int memcg_slabinfo_show(struct seq_file *m, void *unused)
+{
+	struct kmem_cache *s, *c;
+	struct slabinfo sinfo;
+
+	mutex_lock(&slab_mutex);
+	seq_puts(m, "# <name> <css_id[:dead|deact]> <active_objs> <num_objs>");
+	seq_puts(m, " <active_slabs> <num_slabs>\n");
+	list_for_each_entry(s, &slab_root_caches, root_caches_node) {
+		/*
+		 * Skip kmem caches that don't have any memcg children.
+		 */
+		if (list_empty(&s->memcg_params.children))
+			continue;
+
+		memset(&sinfo, 0, sizeof(sinfo));
+		get_slabinfo(s, &sinfo);
+		seq_printf(m, "%-17s root       %6lu %6lu %6lu %6lu\n",
+			   cache_name(s), sinfo.active_objs, sinfo.num_objs,
+			   sinfo.active_slabs, sinfo.num_slabs);
+
+		for_each_memcg_cache(c, s) {
+			struct cgroup_subsys_state *css;
+			char *status = "";
+
+			css = &c->memcg_params.memcg->css;
+			if (!(css->flags & CSS_ONLINE))
+				status = ":dead";
+			else if (c->flags & SLAB_DEACTIVATED)
+				status = ":deact";
+
+			memset(&sinfo, 0, sizeof(sinfo));
+			get_slabinfo(c, &sinfo);
+			seq_printf(m, "%-17s %4d%-6s %6lu %6lu %6lu %6lu\n",
+				   cache_name(c), css->id, status,
+				   sinfo.active_objs, sinfo.num_objs,
+				   sinfo.active_slabs, sinfo.num_slabs);
+		}
+	}
+	mutex_unlock(&slab_mutex);
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(memcg_slabinfo);
+
+static int __init memcg_slabinfo_init(void)
+{
+	debugfs_create_file("memcg_slabinfo", S_IFREG | S_IRUGO,
+			    NULL, NULL, &memcg_slabinfo_fops);
+	return 0;
+}
+
+late_initcall(memcg_slabinfo_init);
+#endif /* CONFIG_DEBUG_FS && CONFIG_MEMCG_KMEM */
 #endif /* CONFIG_SLAB || CONFIG_SLUB_DEBUG */
 
 static __always_inline void *__do_krealloc(const void *p, size_t new_size,
@@ -1597,6 +1680,52 @@ void kzfree(const void *p)
 }
 EXPORT_SYMBOL(kzfree);
 
+/**
+ * ksize - get the actual amount of memory allocated for a given object
+ * @objp: Pointer to the object
+ *
+ * kmalloc may internally round up allocations and return more memory
+ * than requested. ksize() can be used to determine the actual amount of
+ * memory allocated. The caller may use this additional memory, even though
+ * a smaller amount of memory was initially specified with the kmalloc call.
+ * The caller must guarantee that objp points to a valid object previously
+ * allocated with either kmalloc() or kmem_cache_alloc(). The object
+ * must not be freed during the duration of the call.
+ *
+ * Return: size of the actual memory used by @objp in bytes
+ */
+size_t ksize(const void *objp)
+{
+	size_t size;
+
+	if (WARN_ON_ONCE(!objp))
+		return 0;
+	/*
+	 * We need to check that the pointed to object is valid, and only then
+	 * unpoison the shadow memory below. We use __kasan_check_read(), to
+	 * generate a more useful report at the time ksize() is called (rather
+	 * than later where behaviour is undefined due to potential
+	 * use-after-free or double-free).
+	 *
+	 * If the pointed to memory is invalid we return 0, to avoid users of
+	 * ksize() writing to and potentially corrupting the memory region.
+	 *
+	 * We want to perform the check before __ksize(), to avoid potentially
+	 * crashing in __ksize() due to accessing invalid metadata.
+	 */
+	if (unlikely(objp == ZERO_SIZE_PTR) || !__kasan_check_read(objp, 1))
+		return 0;
+
+	size = __ksize(objp);
+	/*
+	 * We assume that ksize callers could use whole allocated area,
+	 * so we need to unpoison this area.
+	 */
+	kasan_unpoison_shadow(objp, size);
+	return size;
+}
+EXPORT_SYMBOL(ksize);
+
 /* Tracepoints definitions. */
 EXPORT_TRACEPOINT_SYMBOL(kmalloc);
 EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);