--- zzzz-none-000/linux-3.10.107/mm/slab_common.c	2017-06-27 09:49:32.000000000 +0000
+++ scorpion-7490-727/linux-3.10.107/mm/slab_common.c	2021-02-04 17:41:59.000000000 +0000
@@ -20,16 +20,61 @@
 #include <asm/page.h>
 #include <linux/memcontrol.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/kmem.h>
+
 #include "slab.h"
 
+#if defined(CONFIG_SLUB_AVM_ALLOC_LIST)
+#include <linux/proc_fs.h>
+#include <linux/sizes.h>
+#include <avm/sammel/simple_proc.h>
+#endif
+
 enum slab_state slab_state;
 LIST_HEAD(slab_caches);
 DEFINE_MUTEX(slab_mutex);
 struct kmem_cache *kmem_cache;
 
+/*
+ * Set of flags that will prevent slab merging
+ */
+#define SLAB_NEVER_MERGE (SLAB_RED_ZONE | SLAB_POISON | \
+			  SLAB_STORE_USER | SLAB_STORE_USER_LITE | \
+		SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \
+		SLAB_FAILSLAB)
+
+#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | SLAB_NOTRACK)
+
+/*
+ * Merge control. If this is set then no merging of slab caches will occur.
+ * (Could be removed. This was introduced to pacify the merge skeptics.)
+ */
+static int slab_nomerge;
+
+static int __init setup_slab_nomerge(char *str)
+{
+	slab_nomerge = 1;
+	return 1;
+}
+
+#ifdef CONFIG_SLUB
+__setup_param("slub_nomerge", slub_nomerge, setup_slab_nomerge, 0);
+#endif
+
+__setup("slab_nomerge", setup_slab_nomerge);
+
+/*
+ * Determine the size of a slab object
+ */
+unsigned int kmem_cache_size(struct kmem_cache *s)
+{
+	return s->object_size;
+}
+EXPORT_SYMBOL(kmem_cache_size);
+
 #ifdef CONFIG_DEBUG_VM
-static int kmem_cache_sanity_check(struct mem_cgroup *memcg, const char *name,
-				   size_t size)
+static int kmem_cache_sanity_check(const char *name, size_t size)
 {
 	struct kmem_cache *s = NULL;
 
@@ -54,62 +99,202 @@
 			       s->object_size);
 			continue;
 		}
-
-#if !defined(CONFIG_SLUB)
-		/*
-		 * For simplicity, we won't check this in the list of memcg
-		 * caches. We have control over memcg naming, and if there
-		 * aren't duplicates in the global list, there won't be any
-		 * duplicates in the memcg lists as well.
-		 */
-		if (!memcg && !strcmp(s->name, name)) {
-			pr_err("%s (%s): Cache name already exists.\n",
-			       __func__, name);
-			dump_stack();
-			s = NULL;
-			return -EINVAL;
-		}
-#endif
 	}
 
 	WARN_ON(strchr(name, ' '));	/* It confuses parsers */
 	return 0;
 }
 #else
-static inline int kmem_cache_sanity_check(struct mem_cgroup *memcg,
-					  const char *name, size_t size)
+static inline int kmem_cache_sanity_check(const char *name, size_t size)
 {
 	return 0;
 }
 #endif
 
+void __kmem_cache_free_bulk(struct kmem_cache *s, size_t nr, void **p)
+{
+	size_t i;
+
+	for (i = 0; i < nr; i++)
+		kmem_cache_free(s, p[i]);
+}
+
+int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr,
+								void **p)
+{
+	size_t i;
+
+	for (i = 0; i < nr; i++) {
+		void *x = p[i] = kmem_cache_alloc(s, flags);
+		if (!x) {
+			__kmem_cache_free_bulk(s, i, p);
+			return 0;
+		}
+	}
+	return i;
+}
+
 #ifdef CONFIG_MEMCG_KMEM
+void slab_init_memcg_params(struct kmem_cache *s)
+{
+	s->memcg_params.is_root_cache = true;
+	INIT_LIST_HEAD(&s->memcg_params.list);
+	RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL);
+}
+
+static int init_memcg_params(struct kmem_cache *s,
+		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
+{
+	struct memcg_cache_array *arr;
+
+	if (memcg) {
+		s->memcg_params.is_root_cache = false;
+		s->memcg_params.memcg = memcg;
+		s->memcg_params.root_cache = root_cache;
+		return 0;
+	}
+
+	slab_init_memcg_params(s);
+
+	if (!memcg_nr_cache_ids)
+		return 0;
+
+	arr = kzalloc(sizeof(struct memcg_cache_array) +
+		      memcg_nr_cache_ids * sizeof(void *),
+		      GFP_KERNEL);
+	if (!arr)
+		return -ENOMEM;
+
+	RCU_INIT_POINTER(s->memcg_params.memcg_caches, arr);
+	return 0;
+}
+
+static void destroy_memcg_params(struct kmem_cache *s)
+{
+	if (is_root_cache(s))
+		kfree(rcu_access_pointer(s->memcg_params.memcg_caches));
+}
+
+static int update_memcg_params(struct kmem_cache *s, int new_array_size)
+{
+	struct memcg_cache_array *old, *new;
+
+	if (!is_root_cache(s))
+		return 0;
+
+	new = kzalloc(sizeof(struct memcg_cache_array) +
+		      new_array_size * sizeof(void *), GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
+
+	old = rcu_dereference_protected(s->memcg_params.memcg_caches,
+					lockdep_is_held(&slab_mutex));
+	if (old)
+		memcpy(new->entries, old->entries,
+		       memcg_nr_cache_ids * sizeof(void *));
+
+	rcu_assign_pointer(s->memcg_params.memcg_caches, new);
+	if (old)
+		kfree_rcu(old, rcu);
+	return 0;
+}
+
 int memcg_update_all_caches(int num_memcgs)
 {
 	struct kmem_cache *s;
 	int ret = 0;
-	mutex_lock(&slab_mutex);
 
+	mutex_lock(&slab_mutex);
 	list_for_each_entry(s, &slab_caches, list) {
-		if (!is_root_cache(s))
-			continue;
-
-		ret = memcg_update_cache_size(s, num_memcgs);
+		ret = update_memcg_params(s, num_memcgs);
 		/*
-		 * See comment in memcontrol.c, memcg_update_cache_size:
 		 * Instead of freeing the memory, we'll just leave the caches
 		 * up to this point in an updated state.
 		 */
 		if (ret)
-			goto out;
+			break;
 	}
-
-	memcg_update_array_size(num_memcgs);
-out:
 	mutex_unlock(&slab_mutex);
 	return ret;
 }
-#endif
+#else
+static inline int init_memcg_params(struct kmem_cache *s,
+		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
+{
+	return 0;
+}
+
+static inline void destroy_memcg_params(struct kmem_cache *s)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
+/*
+ * Find a mergeable slab cache
+ */
+int slab_unmergeable(struct kmem_cache *s)
+{
+	if (slab_nomerge || (s->flags & SLAB_NEVER_MERGE))
+		return 1;
+
+	if (!is_root_cache(s))
+		return 1;
+
+	if (s->ctor)
+		return 1;
+
+	/*
+	 * We may have set a slab to be unmergeable during bootstrap.
+	 */
+	if (s->refcount < 0)
+		return 1;
+
+	return 0;
+}
+
+struct kmem_cache *find_mergeable(size_t size, size_t align,
+		unsigned long flags, const char *name, void (*ctor)(void *))
+{
+	struct kmem_cache *s;
+
+	if (slab_nomerge || (flags & SLAB_NEVER_MERGE))
+		return NULL;
+
+	if (ctor)
+		return NULL;
+
+	size = ALIGN(size, sizeof(void *));
+	align = calculate_alignment(flags, align, size);
+	size = ALIGN(size, align);
+	flags = kmem_cache_flags(size, flags, name, NULL);
+
+	list_for_each_entry_reverse(s, &slab_caches, list) {
+		if (slab_unmergeable(s))
+			continue;
+
+		if (size > s->size)
+			continue;
+
+		if ((flags & SLAB_MERGE_SAME) != (s->flags & SLAB_MERGE_SAME))
+			continue;
+		/*
+		 * Check if alignment is compatible.
+		 * Courtesy of Adrian Drzewiecki
+		 */
+		if ((s->size & ~(align - 1)) != s->size)
+			continue;
+
+		if (s->size - size >= sizeof(void *))
+			continue;
+
+		if (IS_ENABLED(CONFIG_SLAB) && align &&
+			(align > s->align || s->align % align))
+			continue;
+
+		return s;
+	}
+	return NULL;
+}
 
 /*
  * Figure out what the alignment of the objects will be given a set of
@@ -138,6 +323,45 @@
 	return ALIGN(align, sizeof(void *));
 }
 
+static struct kmem_cache *create_cache(const char *name,
+		size_t object_size, size_t size, size_t align,
+		unsigned long flags, void (*ctor)(void *),
+		struct mem_cgroup *memcg, struct kmem_cache *root_cache)
+{
+	struct kmem_cache *s;
+	int err;
+
+	err = -ENOMEM;
+	s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
+	if (!s)
+		goto out;
+
+	s->name = name;
+	s->object_size = object_size;
+	s->size = size;
+	s->align = align;
+	s->ctor = ctor;
+
+	err = init_memcg_params(s, memcg, root_cache);
+	if (err)
+		goto out_free_cache;
+
+	err = __kmem_cache_create(s, flags);
+	if (err)
+		goto out_free_cache;
+
+	s->refcount = 1;
+	list_add(&s->list, &slab_caches);
+out:
+	if (err)
+		return ERR_PTR(err);
+	return s;
+
+out_free_cache:
+	destroy_memcg_params(s);
+	kmem_cache_free(kmem_cache, s);
+	goto out;
+}
 
 /*
  * kmem_cache_create - Create a cache.
@@ -163,20 +387,24 @@
  * cacheline.  This can be beneficial if you're counting cycles as closely
  * as davem.
  */
-
 struct kmem_cache *
-kmem_cache_create_memcg(struct mem_cgroup *memcg, const char *name, size_t size,
-			size_t align, unsigned long flags, void (*ctor)(void *),
-			struct kmem_cache *parent_cache)
+kmem_cache_create(const char *name, size_t size, size_t align,
+		  unsigned long flags, void (*ctor)(void *))
 {
 	struct kmem_cache *s = NULL;
-	int err = 0;
+	const char *cache_name;
+	int err;
 
 	get_online_cpus();
+	get_online_mems();
+	memcg_get_cache_ids();
+
 	mutex_lock(&slab_mutex);
 
-	if (!kmem_cache_sanity_check(memcg, name, size) == 0)
-		goto out_locked;
+	err = kmem_cache_sanity_check(name, size);
+	if (err) {
+		goto out_unlock;
+	}
 
 	/*
 	 * Some allocators will constraint the set of valid flags to a subset
@@ -186,47 +414,32 @@
 	 */
 	flags &= CACHE_CREATE_MASK;
 
-	s = __kmem_cache_alias(memcg, name, size, align, flags, ctor);
+	s = __kmem_cache_alias(name, size, align, flags, ctor);
 	if (s)
-		goto out_locked;
+		goto out_unlock;
 
-	s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
-	if (s) {
-		s->object_size = s->size = size;
-		s->align = calculate_alignment(flags, align, size);
-		s->ctor = ctor;
-
-		if (memcg_register_cache(memcg, s, parent_cache)) {
-			kmem_cache_free(kmem_cache, s);
-			err = -ENOMEM;
-			goto out_locked;
-		}
-
-		s->name = kstrdup(name, GFP_KERNEL);
-		if (!s->name) {
-			kmem_cache_free(kmem_cache, s);
-			err = -ENOMEM;
-			goto out_locked;
-		}
-
-		err = __kmem_cache_create(s, flags);
-		if (!err) {
-			s->refcount = 1;
-			list_add(&s->list, &slab_caches);
-			memcg_cache_list_add(memcg, s);
-		} else {
-			kfree(s->name);
-			kmem_cache_free(kmem_cache, s);
-		}
-	} else
+	cache_name = kstrdup_const(name, GFP_KERNEL);
+	if (!cache_name) {
 		err = -ENOMEM;
+		goto out_unlock;
+	}
 
-out_locked:
+	s = create_cache(cache_name, size, size,
+			 calculate_alignment(flags, align, size),
+			 flags, ctor, NULL, NULL);
+	if (IS_ERR(s)) {
+		err = PTR_ERR(s);
+		kfree_const(cache_name);
+	}
+
+out_unlock:
 	mutex_unlock(&slab_mutex);
+
+	memcg_put_cache_ids();
+	put_online_mems();
 	put_online_cpus();
 
 	if (err) {
-
 		if (flags & SLAB_PANIC)
 			panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n",
 				name, err);
@@ -235,55 +448,320 @@
 				name, err);
 			dump_stack();
 		}
-
 		return NULL;
 	}
-
 	return s;
 }
+EXPORT_SYMBOL(kmem_cache_create);
 
-struct kmem_cache *
-kmem_cache_create(const char *name, size_t size, size_t align,
-		  unsigned long flags, void (*ctor)(void *))
+static int shutdown_cache(struct kmem_cache *s,
+		struct list_head *release, bool *need_rcu_barrier)
 {
-	return kmem_cache_create_memcg(NULL, name, size, align, flags, ctor, NULL);
+	if (__kmem_cache_shutdown(s) != 0)
+		return -EBUSY;
+
+	if (s->flags & SLAB_DESTROY_BY_RCU)
+		*need_rcu_barrier = true;
+
+	list_move(&s->list, release);
+	return 0;
+}
+
+static void release_caches(struct list_head *release, bool need_rcu_barrier)
+{
+	struct kmem_cache *s, *s2;
+
+	if (need_rcu_barrier)
+		rcu_barrier();
+
+	list_for_each_entry_safe(s, s2, release, list) {
+#ifdef SLAB_SUPPORTS_SYSFS
+		sysfs_slab_remove(s);
+#else
+		slab_kmem_cache_release(s);
+#endif
+	}
+}
+
+#ifdef CONFIG_MEMCG_KMEM
+/*
+ * memcg_create_kmem_cache - Create a cache for a memory cgroup.
+ * @memcg: The memory cgroup the new cache is for.
+ * @root_cache: The parent of the new cache.
+ *
+ * This function attempts to create a kmem cache that will serve allocation
+ * requests going from @memcg to @root_cache. The new cache inherits properties
+ * from its parent.
+ */
+void memcg_create_kmem_cache(struct mem_cgroup *memcg,
+			     struct kmem_cache *root_cache)
+{
+	static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */
+	struct cgroup_subsys_state *css = &memcg->css;
+	struct memcg_cache_array *arr;
+	struct kmem_cache *s = NULL;
+	char *cache_name;
+	int idx;
+
+	get_online_cpus();
+	get_online_mems();
+
+	mutex_lock(&slab_mutex);
+
+	/*
+	 * The memory cgroup could have been deactivated while the cache
+	 * creation work was pending.
+	 */
+	if (!memcg_kmem_is_active(memcg))
+		goto out_unlock;
+
+	idx = memcg_cache_id(memcg);
+	arr = rcu_dereference_protected(root_cache->memcg_params.memcg_caches,
+					lockdep_is_held(&slab_mutex));
+
+	/*
+	 * Since per-memcg caches are created asynchronously on first
+	 * allocation (see memcg_kmem_get_cache()), several threads can try to
+	 * create the same cache, but only one of them may succeed.
+	 */
+	if (arr->entries[idx])
+		goto out_unlock;
+
+	cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf));
+	cache_name = kasprintf(GFP_KERNEL, "%s(%llu:%s)", root_cache->name,
+			       css->serial_nr, memcg_name_buf);
+	if (!cache_name)
+		goto out_unlock;
+
+	s = create_cache(cache_name, root_cache->object_size,
+			 root_cache->size, root_cache->align,
+			 root_cache->flags, root_cache->ctor,
+			 memcg, root_cache);
+	/*
+	 * If we could not create a memcg cache, do not complain, because
+	 * that's not critical at all as we can always proceed with the root
+	 * cache.
+	 */
+	if (IS_ERR(s)) {
+		kfree(cache_name);
+		goto out_unlock;
+	}
+
+	list_add(&s->memcg_params.list, &root_cache->memcg_params.list);
+
+	/*
+	 * Since readers won't lock (see cache_from_memcg_idx()), we need a
+	 * barrier here to ensure nobody will see the kmem_cache partially
+	 * initialized.
+	 */
+	smp_wmb();
+	arr->entries[idx] = s;
+
+out_unlock:
+	mutex_unlock(&slab_mutex);
+
+	put_online_mems();
+	put_online_cpus();
+}
+
+void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
+{
+	int idx;
+	struct memcg_cache_array *arr;
+	struct kmem_cache *s, *c;
+
+	idx = memcg_cache_id(memcg);
+
+	get_online_cpus();
+	get_online_mems();
+
+	mutex_lock(&slab_mutex);
+	list_for_each_entry(s, &slab_caches, list) {
+		if (!is_root_cache(s))
+			continue;
+
+		arr = rcu_dereference_protected(s->memcg_params.memcg_caches,
+						lockdep_is_held(&slab_mutex));
+		c = arr->entries[idx];
+		if (!c)
+			continue;
+
+		__kmem_cache_shrink(c, true);
+		arr->entries[idx] = NULL;
+	}
+	mutex_unlock(&slab_mutex);
+
+	put_online_mems();
+	put_online_cpus();
+}
+
+static int __shutdown_memcg_cache(struct kmem_cache *s,
+		struct list_head *release, bool *need_rcu_barrier)
+{
+	BUG_ON(is_root_cache(s));
+
+	if (shutdown_cache(s, release, need_rcu_barrier))
+		return -EBUSY;
+
+	list_del(&s->memcg_params.list);
+	return 0;
+}
+
+void memcg_destroy_kmem_caches(struct mem_cgroup *memcg)
+{
+	LIST_HEAD(release);
+	bool need_rcu_barrier = false;
+	struct kmem_cache *s, *s2;
+
+	get_online_cpus();
+	get_online_mems();
+
+	mutex_lock(&slab_mutex);
+	list_for_each_entry_safe(s, s2, &slab_caches, list) {
+		if (is_root_cache(s) || s->memcg_params.memcg != memcg)
+			continue;
+		/*
+		 * 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_memcg_cache(s, &release, &need_rcu_barrier));
+	}
+	mutex_unlock(&slab_mutex);
+
+	put_online_mems();
+	put_online_cpus();
+
+	release_caches(&release, need_rcu_barrier);
+}
+
+static int shutdown_memcg_caches(struct kmem_cache *s,
+		struct list_head *release, bool *need_rcu_barrier)
+{
+	struct memcg_cache_array *arr;
+	struct kmem_cache *c, *c2;
+	LIST_HEAD(busy);
+	int i;
+
+	BUG_ON(!is_root_cache(s));
+
+	/*
+	 * First, shutdown active caches, i.e. caches that belong to online
+	 * memory cgroups.
+	 */
+	arr = rcu_dereference_protected(s->memcg_params.memcg_caches,
+					lockdep_is_held(&slab_mutex));
+	for_each_memcg_cache_index(i) {
+		c = arr->entries[i];
+		if (!c)
+			continue;
+		if (__shutdown_memcg_cache(c, release, need_rcu_barrier))
+			/*
+			 * The cache still has objects. Move it to a temporary
+			 * list so as not to try to destroy it for a second
+			 * time while iterating over inactive caches below.
+			 */
+			list_move(&c->memcg_params.list, &busy);
+		else
+			/*
+			 * The cache is empty and will be destroyed soon. Clear
+			 * the pointer to it in the memcg_caches array so that
+			 * it will never be accessed even if the root cache
+			 * stays alive.
+			 */
+			arr->entries[i] = NULL;
+	}
+
+	/*
+	 * Second, shutdown all caches left from memory cgroups that are now
+	 * offline.
+	 */
+	list_for_each_entry_safe(c, c2, &s->memcg_params.list,
+				 memcg_params.list)
+		__shutdown_memcg_cache(c, release, need_rcu_barrier);
+
+	list_splice(&busy, &s->memcg_params.list);
+
+	/*
+	 * A cache being destroyed must be empty. In particular, this means
+	 * that all per memcg caches attached to it must be empty too.
+	 */
+	if (!list_empty(&s->memcg_params.list))
+		return -EBUSY;
+	return 0;
+}
+#else
+static inline int shutdown_memcg_caches(struct kmem_cache *s,
+		struct list_head *release, bool *need_rcu_barrier)
+{
+	return 0;
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
+void slab_kmem_cache_release(struct kmem_cache *s)
+{
+	destroy_memcg_params(s);
+	kfree_const(s->name);
+	kmem_cache_free(kmem_cache, s);
 }
-EXPORT_SYMBOL(kmem_cache_create);
 
 void kmem_cache_destroy(struct kmem_cache *s)
 {
-	/* Destroy all the children caches if we aren't a memcg cache */
-	kmem_cache_destroy_memcg_children(s);
+	LIST_HEAD(release);
+	bool need_rcu_barrier = false;
+	int err;
+
+	if (unlikely(!s))
+		return;
 
 	get_online_cpus();
+	get_online_mems();
+
 	mutex_lock(&slab_mutex);
+
 	s->refcount--;
-	if (!s->refcount) {
-		list_del(&s->list);
+	if (s->refcount)
+		goto out_unlock;
 
-		if (!__kmem_cache_shutdown(s)) {
-			mutex_unlock(&slab_mutex);
-			if (s->flags & SLAB_DESTROY_BY_RCU)
-				rcu_barrier();
-
-			memcg_release_cache(s);
-			kfree(s->name);
-			kmem_cache_free(kmem_cache, s);
-		} else {
-			list_add(&s->list, &slab_caches);
-			mutex_unlock(&slab_mutex);
-			printk(KERN_ERR "kmem_cache_destroy %s: Slab cache still has objects\n",
-				s->name);
-			dump_stack();
-		}
-	} else {
-		mutex_unlock(&slab_mutex);
+	err = shutdown_memcg_caches(s, &release, &need_rcu_barrier);
+	if (!err)
+		err = shutdown_cache(s, &release, &need_rcu_barrier);
+
+	if (err) {
+		pr_err("kmem_cache_destroy %s: "
+		       "Slab cache still has objects\n", s->name);
+		dump_stack();
 	}
+out_unlock:
+	mutex_unlock(&slab_mutex);
+
+	put_online_mems();
 	put_online_cpus();
+
+	release_caches(&release, need_rcu_barrier);
 }
 EXPORT_SYMBOL(kmem_cache_destroy);
 
-int slab_is_available(void)
+/**
+ * kmem_cache_shrink - Shrink a cache.
+ * @cachep: The cache to shrink.
+ *
+ * Releases as many slabs as possible for a cache.
+ * To help debugging, a zero exit status indicates all slabs were released.
+ */
+int kmem_cache_shrink(struct kmem_cache *cachep)
+{
+	int ret;
+
+	get_online_cpus();
+	get_online_mems();
+	ret = __kmem_cache_shrink(cachep, false);
+	put_online_mems();
+	put_online_cpus();
+	return ret;
+}
+EXPORT_SYMBOL(kmem_cache_shrink);
+
+bool slab_is_available(void)
 {
 	return slab_state >= UP;
 }
@@ -298,6 +776,9 @@
 	s->name = name;
 	s->size = s->object_size = size;
 	s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
+
+	slab_init_memcg_params(s);
+
 	err = __kmem_cache_create(s, flags);
 
 	if (err)
@@ -375,7 +856,7 @@
 {
 	int index;
 
-	if (size > KMALLOC_MAX_SIZE) {
+	if (unlikely(size > KMALLOC_MAX_SIZE)) {
 		WARN_ON_ONCE(!(flags & __GFP_NOWARN));
 		return NULL;
 	}
@@ -397,25 +878,45 @@
 }
 
 /*
- * Create the kmalloc array. Some of the regular kmalloc arrays
- * may already have been created because they were needed to
- * enable allocations for slab creation.
+ * kmalloc_info[] is to make slub_debug=,kmalloc-xx option work at boot time.
+ * kmalloc_index() supports up to 2^26=64MB, so the final entry of the table is
+ * kmalloc-67108864.
  */
-void __init create_kmalloc_caches(unsigned long flags)
+static struct {
+	const char *name;
+	unsigned long size;
+} const kmalloc_info[] __initconst = {
+	{NULL,                      0},		{"kmalloc-96",             96},
+	{"kmalloc-192",           192},		{"kmalloc-8",               8},
+	{"kmalloc-16",             16},		{"kmalloc-32",             32},
+	{"kmalloc-64",             64},		{"kmalloc-128",           128},
+	{"kmalloc-256",           256},		{"kmalloc-512",           512},
+	{"kmalloc-1024",         1024},		{"kmalloc-2048",         2048},
+	{"kmalloc-4096",         4096},		{"kmalloc-8192",         8192},
+	{"kmalloc-16384",       16384},		{"kmalloc-32768",       32768},
+	{"kmalloc-65536",       65536},		{"kmalloc-131072",     131072},
+	{"kmalloc-262144",     262144},		{"kmalloc-524288",     524288},
+	{"kmalloc-1048576",   1048576},		{"kmalloc-2097152",   2097152},
+	{"kmalloc-4194304",   4194304},		{"kmalloc-8388608",   8388608},
+	{"kmalloc-16777216", 16777216},		{"kmalloc-33554432", 33554432},
+	{"kmalloc-67108864", 67108864}
+};
+
+/*
+ * Patch up the size_index table if we have strange large alignment
+ * requirements for the kmalloc array. This is only the case for
+ * MIPS it seems. The standard arches will not generate any code here.
+ *
+ * Largest permitted alignment is 256 bytes due to the way we
+ * handle the index determination for the smaller caches.
+ *
+ * Make sure that nothing crazy happens if someone starts tinkering
+ * around with ARCH_KMALLOC_MINALIGN
+ */
+void __init setup_kmalloc_cache_index_table(void)
 {
 	int i;
 
-	/*
-	 * Patch up the size_index table if we have strange large alignment
-	 * requirements for the kmalloc array. This is only the case for
-	 * MIPS it seems. The standard arches will not generate any code here.
-	 *
-	 * Largest permitted alignment is 256 bytes due to the way we
-	 * handle the index determination for the smaller caches.
-	 *
-	 * Make sure that nothing crazy happens if someone starts tinkering
-	 * around with ARCH_KMALLOC_MINALIGN
-	 */
 	BUILD_BUG_ON(KMALLOC_MIN_SIZE > 256 ||
 		(KMALLOC_MIN_SIZE & (KMALLOC_MIN_SIZE - 1)));
 
@@ -446,11 +947,26 @@
 		for (i = 128 + 8; i <= 192; i += 8)
 			size_index[size_index_elem(i)] = 8;
 	}
+}
+
+static void __init new_kmalloc_cache(int idx, unsigned long flags)
+{
+	kmalloc_caches[idx] = create_kmalloc_cache(kmalloc_info[idx].name,
+					kmalloc_info[idx].size, flags);
+}
+
+/*
+ * Create the kmalloc array. Some of the regular kmalloc arrays
+ * may already have been created because they were needed to
+ * enable allocations for slab creation.
+ */
+void __init create_kmalloc_caches(unsigned long flags)
+{
+	int i;
+
 	for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) {
-		if (!kmalloc_caches[i]) {
-			kmalloc_caches[i] = create_kmalloc_cache(NULL,
-							1 << i, flags);
-		}
+		if (!kmalloc_caches[i])
+			new_kmalloc_cache(i, flags);
 
 		/*
 		 * Caches that are not of the two-to-the-power-of size.
@@ -458,27 +974,14 @@
 		 * earlier power of two caches
 		 */
 		if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[1] && i == 6)
-			kmalloc_caches[1] = create_kmalloc_cache(NULL, 96, flags);
-
+			new_kmalloc_cache(1, flags);
 		if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[2] && i == 7)
-			kmalloc_caches[2] = create_kmalloc_cache(NULL, 192, flags);
+			new_kmalloc_cache(2, flags);
 	}
 
 	/* Kmalloc array is now usable */
 	slab_state = UP;
 
-	for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
-		struct kmem_cache *s = kmalloc_caches[i];
-		char *n;
-
-		if (s) {
-			n = kasprintf(GFP_NOWAIT, "kmalloc-%d", kmalloc_size(i));
-
-			BUG_ON(!n);
-			s->name = n;
-		}
-	}
-
 #ifdef CONFIG_ZONE_DMA
 	for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) {
 		struct kmem_cache *s = kmalloc_caches[i];
@@ -497,9 +1000,48 @@
 }
 #endif /* !CONFIG_SLOB */
 
+/*
+ * To avoid unnecessary overhead, we pass through large allocation requests
+ * directly to the page allocator. We use __GFP_COMP, because we will need to
+ * know the allocation order to free the pages properly in kfree.
+ */
+void *kmalloc_order(size_t size, gfp_t flags, unsigned int order)
+{
+	void *ret;
+	struct page *page;
+
+	flags |= __GFP_COMP;
+	page = alloc_kmem_pages(flags, order);
+	ret = page ? page_address(page) : NULL;
+#if defined(CONFIG_AVM_PAGE_TRACE)
+	if (likely(page))
+		avm_set_page_current_pc(page, _RET_IP_);
+#endif
+	kmemleak_alloc(ret, size, 1, flags);
+	kasan_kmalloc_large(ret, size);
+	return ret;
+}
+EXPORT_SYMBOL(kmalloc_order);
+
+#ifdef CONFIG_TRACING
+void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order)
+{
+	void *ret = kmalloc_order(size, flags, order);
+	trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags);
+	return ret;
+}
+EXPORT_SYMBOL(kmalloc_order_trace);
+#endif
 
 #ifdef CONFIG_SLABINFO
-void print_slabinfo_header(struct seq_file *m)
+
+#ifdef CONFIG_SLAB
+#define SLABINFO_RIGHTS (S_IWUSR | S_IRUSR)
+#else
+#define SLABINFO_RIGHTS S_IRUSR
+#endif
+
+static void print_slabinfo_header(struct seq_file *m)
 {
 	/*
 	 * Output format version, so at least we can change it
@@ -522,23 +1064,18 @@
 	seq_putc(m, '\n');
 }
 
-static void *s_start(struct seq_file *m, loff_t *pos)
+void *slab_start(struct seq_file *m, loff_t *pos)
 {
-	loff_t n = *pos;
-
 	mutex_lock(&slab_mutex);
-	if (!n)
-		print_slabinfo_header(m);
-
 	return seq_list_start(&slab_caches, *pos);
 }
 
-static void *s_next(struct seq_file *m, void *p, loff_t *pos)
+void *slab_next(struct seq_file *m, void *p, loff_t *pos)
 {
 	return seq_list_next(p, &slab_caches, pos);
 }
 
-static void s_stop(struct seq_file *m, void *p)
+void slab_stop(struct seq_file *m, void *p)
 {
 	mutex_unlock(&slab_mutex);
 }
@@ -548,16 +1085,11 @@
 {
 	struct kmem_cache *c;
 	struct slabinfo sinfo;
-	int i;
 
 	if (!is_root_cache(s))
 		return;
 
-	for_each_memcg_cache_index(i) {
-		c = cache_from_memcg(s, i);
-		if (!c)
-			continue;
-
+	for_each_memcg_cache(c, s) {
 		memset(&sinfo, 0, sizeof(sinfo));
 		get_slabinfo(c, &sinfo);
 
@@ -569,7 +1101,7 @@
 	}
 }
 
-int cache_show(struct kmem_cache *s, struct seq_file *m)
+static void cache_show(struct kmem_cache *s, struct seq_file *m)
 {
 	struct slabinfo sinfo;
 
@@ -588,17 +1120,32 @@
 		   sinfo.active_slabs, sinfo.num_slabs, sinfo.shared_avail);
 	slabinfo_show_stats(m, s);
 	seq_putc(m, '\n');
+}
+
+static int slab_show(struct seq_file *m, void *p)
+{
+	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
+
+	if (p == slab_caches.next)
+		print_slabinfo_header(m);
+	if (is_root_cache(s))
+		cache_show(s, m);
 	return 0;
 }
 
-static int s_show(struct seq_file *m, void *p)
+#ifdef CONFIG_MEMCG_KMEM
+int memcg_slab_show(struct seq_file *m, void *p)
 {
 	struct kmem_cache *s = list_entry(p, struct kmem_cache, list);
+	struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m));
 
-	if (!is_root_cache(s))
-		return 0;
-	return cache_show(s, m);
+	if (p == slab_caches.next)
+		print_slabinfo_header(m);
+	if (!is_root_cache(s) && s->memcg_params.memcg == memcg)
+		cache_show(s, m);
+	return 0;
 }
+#endif
 
 /*
  * slabinfo_op - iterator that generates /proc/slabinfo
@@ -614,10 +1161,10 @@
  * + further values on SMP and with statistics enabled
  */
 static const struct seq_operations slabinfo_op = {
-	.start = s_start,
-	.next = s_next,
-	.stop = s_stop,
-	.show = s_show,
+	.start = slab_start,
+	.next = slab_next,
+	.stop = slab_stop,
+	.show = slab_show,
 };
 
 static int slabinfo_open(struct inode *inode, struct file *file)
@@ -635,8 +1182,339 @@
 
 static int __init slab_proc_init(void)
 {
-	proc_create("slabinfo", S_IRUSR, NULL, &proc_slabinfo_operations);
+	proc_create("slabinfo", SLABINFO_RIGHTS, NULL,
+						&proc_slabinfo_operations);
 	return 0;
 }
 module_init(slab_proc_init);
 #endif /* CONFIG_SLABINFO */
+
+static __always_inline void *__do_krealloc(const void *p, size_t new_size,
+					   gfp_t flags)
+{
+	void *ret;
+	size_t ks = 0;
+
+	if (p)
+		ks = ksize(p);
+
+	if (ks >= new_size) {
+		kasan_krealloc((void *)p, new_size);
+		return (void *)p;
+	}
+
+	ret = kmalloc_track_caller(new_size, flags);
+	if (ret && p)
+		memcpy(ret, p, ks);
+
+	return ret;
+}
+
+/**
+ * __krealloc - like krealloc() but don't free @p.
+ * @p: object to reallocate memory for.
+ * @new_size: how many bytes of memory are required.
+ * @flags: the type of memory to allocate.
+ *
+ * This function is like krealloc() except it never frees the originally
+ * allocated buffer. Use this if you don't want to free the buffer immediately
+ * like, for example, with RCU.
+ */
+void *__krealloc(const void *p, size_t new_size, gfp_t flags)
+{
+	if (unlikely(!new_size))
+		return ZERO_SIZE_PTR;
+
+	return __do_krealloc(p, new_size, flags);
+
+}
+EXPORT_SYMBOL(__krealloc);
+
+/**
+ * krealloc - reallocate memory. The contents will remain unchanged.
+ * @p: object to reallocate memory for.
+ * @new_size: how many bytes of memory are required.
+ * @flags: the type of memory to allocate.
+ *
+ * The contents of the object pointed to are preserved up to the
+ * lesser of the new and old sizes.  If @p is %NULL, krealloc()
+ * behaves exactly like kmalloc().  If @new_size is 0 and @p is not a
+ * %NULL pointer, the object pointed to is freed.
+ */
+void *krealloc(const void *p, size_t new_size, gfp_t flags)
+{
+	void *ret;
+
+	if (unlikely(!new_size)) {
+		kfree(p);
+		return ZERO_SIZE_PTR;
+	}
+
+	ret = __do_krealloc(p, new_size, flags);
+	if (ret && p != ret)
+		kfree(p);
+
+	return ret;
+}
+EXPORT_SYMBOL(krealloc);
+
+/**
+ * kzfree - like kfree but zero memory
+ * @p: object to free memory of
+ *
+ * The memory of the object @p points to is zeroed before freed.
+ * If @p is %NULL, kzfree() does nothing.
+ *
+ * Note: this function zeroes the whole allocated buffer which can be a good
+ * deal bigger than the requested buffer size passed to kmalloc(). So be
+ * careful when using this function in performance sensitive code.
+ */
+void kzfree(const void *p)
+{
+	size_t ks;
+	void *mem = (void *)p;
+
+	if (unlikely(ZERO_OR_NULL_PTR(mem)))
+		return;
+	ks = ksize(mem);
+	memset(mem, 0, ks);
+	kfree(mem);
+}
+EXPORT_SYMBOL(kzfree);
+
+/* Tracepoints definitions. */
+EXPORT_TRACEPOINT_SYMBOL(kmalloc);
+EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc);
+EXPORT_TRACEPOINT_SYMBOL(kmalloc_node);
+EXPORT_TRACEPOINT_SYMBOL(kmem_cache_alloc_node);
+EXPORT_TRACEPOINT_SYMBOL(kfree);
+EXPORT_TRACEPOINT_SYMBOL(kmem_cache_free);
+
+#if defined(CONFIG_SLUB_AVM_ALLOC_LIST)
+/**
+ */
+static char *human_time(char *buf, int len, unsigned long secs)
+{
+	unsigned long seconds, minutes, hours;
+
+	seconds = secs % 60;
+	secs /= 60;
+	minutes = secs % 60;
+	secs /= 60;
+	hours = secs % 24;
+	if (hours) {
+		snprintf(buf, len, "%lu h %2lu min %2lu s", hours, minutes,
+			 seconds);
+	} else if (minutes) {
+		snprintf(buf, len, "%2lu min %2lu s", minutes, seconds);
+	} else {
+		snprintf(buf, len, "%2lu s", seconds);
+	}
+	return buf;
+}
+
+/**
+ * @brief show memory-usage-caller for cachepool
+ * @param cachep cachepool
+ * @param m seq-pointer
+ * @param threshsize only cache-pool-memory-usage greater this
+ * return void
+ */
+#define local_print(seq, args...)                                       \
+	do {								\
+		if (seq) {                                              \
+			seq_printf(seq, args);                          \
+		} else {                                                \
+			pr_err(args);                                   \
+		}							\
+	} while (0)
+
+static void show_cache_toplist(struct kmem_cache *cachep, struct seq_file *m,
+			     struct _slab_avm_topalloclist *toplist,
+			     unsigned long threshsize)
+{
+	unsigned int i;
+	char tmp[128];
+
+	cache_avm_topalloc_list(toplist, cachep, 0);
+	if ((toplist->sum_count == 0) ||
+	    ((toplist->sum_count * cachep->object_size) < threshsize)) {
+		return;
+	}
+	for (i = 0; i < ARRAY_SIZE(toplist->entry); i++) {
+		struct _slab_avm_alloc_entry *p = &toplist->entry[i];
+		unsigned long long avg = p->sum_time;
+
+		if ((i == 0) ||
+		    (p->count * cachep->object_size) > threshsize / 4) {
+			if (i == 0) {
+				local_print(m, "%s: %5lu KiB\n", cachep->name,
+					    (cachep->object_size * toplist->sum_count) >> 10);
+			}
+			do_div(avg, (p->count * HZ));
+			local_print(m, " \t%6u entries (%5u KiB - avg-time %s) %pS\n",
+				p->count,
+				(cachep->object_size * p->count) >> 10,
+				    human_time(tmp, sizeof(tmp), (unsigned long)avg),
+				(void *)p->caller);
+		} else {
+			break;
+		}
+	}
+	if (toplist->ignored) {
+		if (i) {
+			local_print(m, "... but %d callers ignored (too much different callers)\n",
+				toplist->ignored);
+		}
+	}
+}
+/**
+ * @brief show all memory-usage-caller
+ * @param m seq-pointer
+ * @param threshsize only cachep greater this
+ * return void
+ */
+static void proc_show_slab_allocator(struct seq_file *m,
+				     struct _slab_avm_topalloclist *ptoplist,
+					  unsigned long threshsize)
+{
+	struct kmem_cache *cachep = NULL;
+	struct slabinfo sinfo;
+	unsigned long sum = 0;
+	unsigned int init = 0;
+
+	list_for_each_entry(cachep, &slab_caches, list) {
+
+		if (threshsize && (init == 0)) {
+			local_print(m, "show all cache-pools greater %lu KiB:\n", threshsize >> 10);
+			init = 1;
+		}
+		memset(&sinfo, 0, sizeof(sinfo));
+		get_slabinfo(cachep, &sinfo);
+		memcg_accumulate_slabinfo(cachep, &sinfo);
+		if ((sinfo.active_objs * cachep->object_size) >= threshsize) {
+			show_cache_toplist(cachep, m, ptoplist, threshsize);
+		}
+		sum += sinfo.active_objs * cachep->object_size;
+	}
+	local_print(m, "slab-pools use %lu MiB (netto)\n", sum >> 20);
+}
+
+static struct _slab_avm_topalloclist local_toplist;
+unsigned int slab_track_time;
+
+#ifdef CONFIG_SLABINFO
+
+#define SKIP_SPACES(p)	  { while ((*p == ' ') || (*p == '\t')) p++; }
+#define SKIP_NONSPACES(p) { while (*p && (*p != ' ') && (*p != '\t')) p++; }
+
+/**
+ * print out /proc/slabinfo per printk
+ */
+static void __show_slab(void)
+{
+	unsigned int active_objs;
+	char *ptxt;
+	void *p;
+	loff_t pos;
+	char buf[512 + 1];
+	struct seq_file seq;
+
+	memset(&seq, 0, sizeof(seq));
+	seq.size = sizeof(buf) - 1;
+	seq.buf  = buf;
+	pos = 0;
+
+	print_slabinfo_header(&seq);
+	p = seq_list_start(&slab_caches, pos);
+
+	seq.buf[seq.count] = 0;
+	pr_err("%s", seq.buf), seq.count = 0;
+	for (;;) {
+		struct kmem_cache *s;
+
+		if (!p || IS_ERR(p)) {
+			break;
+		}
+		s = list_entry(p, struct kmem_cache, list);
+		if (is_root_cache(s)) {
+			cache_show(s, &seq);
+			seq.buf[seq.count] = 0;
+			/*--- only if active_objs exist: ---*/
+			ptxt = seq.buf;
+			SKIP_NONSPACES(ptxt);
+			SKIP_SPACES(ptxt);
+			sscanf(ptxt, "%u", &active_objs);
+			if (active_objs) {
+				pr_err("%s", seq.buf);
+			}
+		}
+		seq.count = 0;
+		p = seq_list_next(p, &slab_caches, &pos);
+	}
+}
+#endif /* CONFIG_SLABINFO */
+
+/**
+ * @brief show slabinfo and all heavy memory-usage-caller
+ * use kernel-printk
+ * used in oom-notifier
+ */
+void show_slab(void)
+{
+	if (!mutex_trylock(&slab_mutex)) {
+		return;
+	}
+#ifdef CONFIG_SLABINFO
+	__show_slab();
+#endif /* CONFIG_SLABINFO */
+	proc_show_slab_allocator(NULL, &local_toplist, SZ_1M);
+	mutex_unlock(&slab_mutex);
+}
+
+/**
+ * @brief show allocator-statistic
+ * @param m seq-pointer
+ * @param priv
+ * return void
+ */
+static void lproc_slab_allocators(struct seq_file *m, void *priv __maybe_unused)
+{
+	struct _slab_avm_topalloclist *ptoplist;
+
+	ptoplist = kzalloc(sizeof(struct _slab_avm_topalloclist), GFP_KERNEL);
+	if (ptoplist == NULL) {
+		return;
+		}
+		mutex_lock(&slab_mutex);
+	proc_show_slab_allocator(m, ptoplist, 0);
+		mutex_unlock(&slab_mutex);
+	kfree(ptoplist);
+	}
+
+
+/**
+ * @brief delayed slab_allocator-trace on timer-context
+ */
+static void slab_allocator_on(unsigned long data __maybe_unused)
+{
+	pr_err("start slab_allocator-trace now  (use cat /proc/slab_allocators)\n");
+	slab_track_time = 1;
+}
+
+static DEFINE_TIMER(slab_allocator_timer, slab_allocator_on, 0, 0);
+/**
+ * @brief install /proc/slab_allocators
+ * return 0 
+ */
+int __init avm_proc_slaballocator(void)
+{
+	/*--- pr_err("%s()\n", __func__); ---*/
+	add_simple_proc_file("slab_allocators", NULL,
+			     lproc_slab_allocators, NULL);
+
+	mod_timer(&slab_allocator_timer, jiffies + 45 * HZ);
+	return 0;
+}
+late_initcall(avm_proc_slaballocator);
+#endif/*--- #if defined(CONFIG_SLUB_AVM_ALLOC_LIST) ---*/