7 files changed, 134 insertions, 158 deletions

diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index f76668305ac5..4cb51ace600d 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -13,11 +13,12 @@ DECLARE_EVENT_CLASS(kmem_alloc,
 
 	TP_PROTO(unsigned long call_site,
 		 const void *ptr,
+		 struct kmem_cache *s,
 		 size_t bytes_req,
 		 size_t bytes_alloc,
 		 gfp_t gfp_flags),
 
-	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags),
+	TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	call_site	)
@@ -25,6 +26,7 @@ DECLARE_EVENT_CLASS(kmem_alloc,
 		__field(	size_t,		bytes_req	)
 		__field(	size_t,		bytes_alloc	)
 		__field(	unsigned long,	gfp_flags	)
+		__field(	bool,		accounted	)
 	),
 
 	TP_fast_assign(
@@ -33,42 +35,47 @@ DECLARE_EVENT_CLASS(kmem_alloc,
 		__entry->bytes_req	= bytes_req;
 		__entry->bytes_alloc	= bytes_alloc;
 		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
+		__entry->accounted	= IS_ENABLED(CONFIG_MEMCG_KMEM) ?
+					  ((gfp_flags & __GFP_ACCOUNT) ||
+					  (s && s->flags & SLAB_ACCOUNT)) : false;
 	),
 
-	TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
+	TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s accounted=%s",
 		(void *)__entry->call_site,
 		__entry->ptr,
 		__entry->bytes_req,
 		__entry->bytes_alloc,
-		show_gfp_flags(__entry->gfp_flags))
+		show_gfp_flags(__entry->gfp_flags),
+		__entry->accounted ? "true" : "false")
 );
 
 DEFINE_EVENT(kmem_alloc, kmalloc,
 
-	TP_PROTO(unsigned long call_site, const void *ptr,
+	TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s,
 		 size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags),
 
-	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags)
+	TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags)
 );
 
 DEFINE_EVENT(kmem_alloc, kmem_cache_alloc,
 
-	TP_PROTO(unsigned long call_site, const void *ptr,
+	TP_PROTO(unsigned long call_site, const void *ptr, struct kmem_cache *s,
 		 size_t bytes_req, size_t bytes_alloc, gfp_t gfp_flags),
 
-	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags)
+	TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags)
 );
 
 DECLARE_EVENT_CLASS(kmem_alloc_node,
 
 	TP_PROTO(unsigned long call_site,
 		 const void *ptr,
+		 struct kmem_cache *s,
 		 size_t bytes_req,
 		 size_t bytes_alloc,
 		 gfp_t gfp_flags,
 		 int node),
 
-	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
+	TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags, node),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	call_site	)
@@ -77,6 +84,7 @@ DECLARE_EVENT_CLASS(kmem_alloc_node,
 		__field(	size_t,		bytes_alloc	)
 		__field(	unsigned long,	gfp_flags	)
 		__field(	int,		node		)
+		__field(	bool,		accounted	)
 	),
 
 	TP_fast_assign(
@@ -86,33 +94,37 @@ DECLARE_EVENT_CLASS(kmem_alloc_node,
 		__entry->bytes_alloc	= bytes_alloc;
 		__entry->gfp_flags	= (__force unsigned long)gfp_flags;
 		__entry->node		= node;
+		__entry->accounted	= IS_ENABLED(CONFIG_MEMCG_KMEM) ?
+					  ((gfp_flags & __GFP_ACCOUNT) ||
+					  (s && s->flags & SLAB_ACCOUNT)) : false;
 	),
 
-	TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
+	TP_printk("call_site=%pS ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d accounted=%s",
 		(void *)__entry->call_site,
 		__entry->ptr,
 		__entry->bytes_req,
 		__entry->bytes_alloc,
 		show_gfp_flags(__entry->gfp_flags),
-		__entry->node)
+		__entry->node,
+		__entry->accounted ? "true" : "false")
 );
 
 DEFINE_EVENT(kmem_alloc_node, kmalloc_node,
 
 	TP_PROTO(unsigned long call_site, const void *ptr,
-		 size_t bytes_req, size_t bytes_alloc,
+		 struct kmem_cache *s, size_t bytes_req, size_t bytes_alloc,
 		 gfp_t gfp_flags, int node),
 
-	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node)
+	TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags, node)
 );
 
 DEFINE_EVENT(kmem_alloc_node, kmem_cache_alloc_node,
 
 	TP_PROTO(unsigned long call_site, const void *ptr,
-		 size_t bytes_req, size_t bytes_alloc,
+		 struct kmem_cache *s, size_t bytes_req, size_t bytes_alloc,
 		 gfp_t gfp_flags, int node),
 
-	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node)
+	TP_ARGS(call_site, ptr, s, bytes_req, bytes_alloc, gfp_flags, node)
 );
 
 TRACE_EVENT(kfree,
diff --git a/mm/slab.c b/mm/slab.c
index f8cd00f4ba13..5e73e2d80222 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3230,7 +3230,7 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, size_t orig_
 	}
 	/* ___cache_alloc_node can fall back to other nodes */
 	ptr = ____cache_alloc_node(cachep, flags, nodeid);
-  out:
+out:
 	local_irq_restore(save_flags);
 	ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller);
 	init = slab_want_init_on_alloc(flags, cachep);
@@ -3259,7 +3259,7 @@ __do_cache_alloc(struct kmem_cache *cache, gfp_t flags)
 	if (!objp)
 		objp = ____cache_alloc_node(cache, flags, numa_mem_id());
 
-  out:
+out:
 	return objp;
 }
 #else
@@ -3406,9 +3406,10 @@ static __always_inline void __cache_free(struct kmem_cache *cachep, void *objp,
 {
 	bool init;
 
+	memcg_slab_free_hook(cachep, virt_to_slab(objp), &objp, 1);
+
 	if (is_kfence_address(objp)) {
 		kmemleak_free_recursive(objp, cachep->flags);
-		memcg_slab_free_hook(cachep, &objp, 1);
 		__kfence_free(objp);
 		return;
 	}
@@ -3441,7 +3442,6 @@ void ___cache_free(struct kmem_cache *cachep, void *objp,
 	check_irq_off();
 	kmemleak_free_recursive(objp, cachep->flags);
 	objp = cache_free_debugcheck(cachep, objp, caller);
-	memcg_slab_free_hook(cachep, &objp, 1);
 
 	/*
 	 * Skip calling cache_free_alien() when the platform is not numa.
@@ -3478,7 +3478,7 @@ void *__kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru,
 {
 	void *ret = slab_alloc(cachep, lru, flags, cachep->object_size, _RET_IP_);
 
-	trace_kmem_cache_alloc(_RET_IP_, ret,
+	trace_kmem_cache_alloc(_RET_IP_, ret, cachep,
 			       cachep->object_size, cachep->size, flags);
 
 	return ret;
@@ -3553,7 +3553,7 @@ error:
 	local_irq_enable();
 	cache_alloc_debugcheck_after_bulk(s, flags, i, p, _RET_IP_);
 	slab_post_alloc_hook(s, objcg, flags, i, p, false);
-	__kmem_cache_free_bulk(s, i, p);
+	kmem_cache_free_bulk(s, i, p);
 	return 0;
 }
 EXPORT_SYMBOL(kmem_cache_alloc_bulk);
@@ -3567,7 +3567,7 @@ kmem_cache_alloc_trace(struct kmem_cache *cachep, gfp_t flags, size_t size)
 	ret = slab_alloc(cachep, NULL, flags, size, _RET_IP_);
 
 	ret = kasan_kmalloc(cachep, ret, size, flags);
-	trace_kmalloc(_RET_IP_, ret,
+	trace_kmalloc(_RET_IP_, ret, cachep,
 		      size, cachep->size, flags);
 	return ret;
 }
@@ -3592,7 +3592,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 {
 	void *ret = slab_alloc_node(cachep, flags, nodeid, cachep->object_size, _RET_IP_);
 
-	trace_kmem_cache_alloc_node(_RET_IP_, ret,
+	trace_kmem_cache_alloc_node(_RET_IP_, ret, cachep,
 				    cachep->object_size, cachep->size,
 				    flags, nodeid);
 
@@ -3611,7 +3611,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *cachep,
 	ret = slab_alloc_node(cachep, flags, nodeid, size, _RET_IP_);
 
 	ret = kasan_kmalloc(cachep, ret, size, flags);
-	trace_kmalloc_node(_RET_IP_, ret,
+	trace_kmalloc_node(_RET_IP_, ret, cachep,
 			   size, cachep->size,
 			   flags, nodeid);
 	return ret;
@@ -3694,7 +3694,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
 	ret = slab_alloc(cachep, NULL, flags, size, caller);
 
 	ret = kasan_kmalloc(cachep, ret, size, flags);
-	trace_kmalloc(caller, ret,
+	trace_kmalloc(caller, ret, cachep,
 		      size, cachep->size, flags);
 
 	return ret;
diff --git a/mm/slab.h b/mm/slab.h
index db9fb5c8dae7..4ec82bec15ec 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -380,15 +380,6 @@ void slabinfo_show_stats(struct seq_file *m, struct kmem_cache *s);
 ssize_t slabinfo_write(struct file *file, const char __user *buffer,
 		       size_t count, loff_t *ppos);
 
-/*
- * Generic implementation of bulk operations
- * These are useful for situations in which the allocator cannot
- * perform optimizations. In that case segments of the object listed
- * may be allocated or freed using these operations.
- */
-void __kmem_cache_free_bulk(struct kmem_cache *, size_t, void **);
-int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
-
 static inline enum node_stat_item cache_vmstat_idx(struct kmem_cache *s)
 {
 	return (s->flags & SLAB_RECLAIM_ACCOUNT) ?
@@ -547,36 +538,22 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 	obj_cgroup_put(objcg);
 }
 
-static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
+static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
 					void **p, int objects)
 {
-	struct kmem_cache *s;
 	struct obj_cgroup **objcgs;
-	struct obj_cgroup *objcg;
-	struct slab *slab;
-	unsigned int off;
 	int i;
 
 	if (!memcg_kmem_enabled())
 		return;
 
-	for (i = 0; i < objects; i++) {
-		if (unlikely(!p[i]))
-			continue;
-
-		slab = virt_to_slab(p[i]);
-		/* we could be given a kmalloc_large() object, skip those */
-		if (!slab)
-			continue;
-
-		objcgs = slab_objcgs(slab);
-		if (!objcgs)
-			continue;
+	objcgs = slab_objcgs(slab);
+	if (!objcgs)
+		return;
 
-		if (!s_orig)
-			s = slab->slab_cache;
-		else
-			s = s_orig;
+	for (i = 0; i < objects; i++) {
+		struct obj_cgroup *objcg;
+		unsigned int off;
 
 		off = obj_to_index(s, slab, p[i]);
 		objcg = objcgs[off];
@@ -628,7 +605,7 @@ static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s,
 {
 }
 
-static inline void memcg_slab_free_hook(struct kmem_cache *s,
+static inline void memcg_slab_free_hook(struct kmem_cache *s, struct slab *slab,
 					void **p, int objects)
 {
 }
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 77c3adf40e50..17996649cfe3 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -26,13 +26,12 @@
 #include <linux/memcontrol.h>
 #include <linux/stackdepot.h>
 
-#define CREATE_TRACE_POINTS
-#include <trace/events/kmem.h>
-
 #include "internal.h"
-
 #include "slab.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/kmem.h>
+
 enum slab_state slab_state;
 LIST_HEAD(slab_caches);
 DEFINE_MUTEX(slab_mutex);
@@ -105,33 +104,6 @@ static inline int kmem_cache_sanity_check(const char *name, unsigned int size)
 }
 #endif
 
-void __kmem_cache_free_bulk(struct kmem_cache *s, size_t nr, void **p)
-{
-	size_t i;
-
-	for (i = 0; i < nr; i++) {
-		if (s)
-			kmem_cache_free(s, p[i]);
-		else
-			kfree(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;
-}
-
 /*
  * Figure out what the alignment of the objects will be given a set of
  * flags, a user specified alignment and the size of the objects.
@@ -959,7 +931,7 @@ EXPORT_SYMBOL(kmalloc_order);
 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);
+	trace_kmalloc(_RET_IP_, ret, NULL, size, PAGE_SIZE << order, flags);
 	return ret;
 }
 EXPORT_SYMBOL(kmalloc_order_trace);
diff --git a/mm/slob.c b/mm/slob.c
index f47811f09aca..2bd4f476c340 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -507,7 +507,7 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 		*m = size;
 		ret = (void *)m + minalign;
 
-		trace_kmalloc_node(caller, ret,
+		trace_kmalloc_node(caller, ret, NULL,
 				   size, size + minalign, gfp, node);
 	} else {
 		unsigned int order = get_order(size);
@@ -516,7 +516,7 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 			gfp |= __GFP_COMP;
 		ret = slob_new_pages(gfp, order, node);
 
-		trace_kmalloc_node(caller, ret,
+		trace_kmalloc_node(caller, ret, NULL,
 				   size, PAGE_SIZE << order, gfp, node);
 	}
 
@@ -616,12 +616,12 @@ static void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
 
 	if (c->size < PAGE_SIZE) {
 		b = slob_alloc(c->size, flags, c->align, node, 0);
-		trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size,
+		trace_kmem_cache_alloc_node(_RET_IP_, b, NULL, c->object_size,
 					    SLOB_UNITS(c->size) * SLOB_UNIT,
 					    flags, node);
 	} else {
 		b = slob_new_pages(flags, get_order(c->size), node);
-		trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size,
+		trace_kmem_cache_alloc_node(_RET_IP_, b, NULL, c->object_size,
 					    PAGE_SIZE << get_order(c->size),
 					    flags, node);
 	}
@@ -692,16 +692,33 @@ void kmem_cache_free(struct kmem_cache *c, void *b)
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
-void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
+void kmem_cache_free_bulk(struct kmem_cache *s, size_t nr, void **p)
 {
-	__kmem_cache_free_bulk(s, size, p);
+	size_t i;
+
+	for (i = 0; i < nr; i++) {
+		if (s)
+			kmem_cache_free(s, p[i]);
+		else
+			kfree(p[i]);
+	}
 }
 EXPORT_SYMBOL(kmem_cache_free_bulk);
 
-int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
+int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr,
 								void **p)
 {
-	return __kmem_cache_alloc_bulk(s, flags, size, 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;
 }
 EXPORT_SYMBOL(kmem_cache_alloc_bulk);
 
diff --git a/mm/slub.c b/mm/slub.c
index b1281b8654bd..862dbd9af4f5 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3257,7 +3257,7 @@ void *__kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru,
 {
 	void *ret = slab_alloc(s, lru, gfpflags, _RET_IP_, s->object_size);
 
-	trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size,
+	trace_kmem_cache_alloc(_RET_IP_, ret, s, s->object_size,
 				s->size, gfpflags);
 
 	return ret;
@@ -3280,7 +3280,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_lru);
 void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
 {
 	void *ret = slab_alloc(s, NULL, gfpflags, _RET_IP_, size);
-	trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags);
+	trace_kmalloc(_RET_IP_, ret, s, size, s->size, gfpflags);
 	ret = kasan_kmalloc(s, ret, size, gfpflags);
 	return ret;
 }
@@ -3292,7 +3292,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
 {
 	void *ret = slab_alloc_node(s, NULL, gfpflags, node, _RET_IP_, s->object_size);
 
-	trace_kmem_cache_alloc_node(_RET_IP_, ret,
+	trace_kmem_cache_alloc_node(_RET_IP_, ret, s,
 				    s->object_size, s->size, gfpflags, node);
 
 	return ret;
@@ -3306,7 +3306,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *s,
 {
 	void *ret = slab_alloc_node(s, NULL, gfpflags, node, _RET_IP_, size);
 
-	trace_kmalloc_node(_RET_IP_, ret,
+	trace_kmalloc_node(_RET_IP_, ret, s,
 			   size, s->size, gfpflags, node);
 
 	ret = kasan_kmalloc(s, ret, size, gfpflags);
@@ -3464,9 +3464,6 @@ static __always_inline void do_slab_free(struct kmem_cache *s,
 	struct kmem_cache_cpu *c;
 	unsigned long tid;
 
-	/* memcg_slab_free_hook() is already called for bulk free. */
-	if (!tail)
-		memcg_slab_free_hook(s, &head, 1);
 redo:
 	/*
 	 * Determine the currently cpus per cpu slab.
@@ -3526,9 +3523,10 @@ redo:
 }
 
 static __always_inline void slab_free(struct kmem_cache *s, struct slab *slab,
-				      void *head, void *tail, int cnt,
+				      void *head, void *tail, void **p, int cnt,
 				      unsigned long addr)
 {
+	memcg_slab_free_hook(s, slab, p, cnt);
 	/*
 	 * With KASAN enabled slab_free_freelist_hook modifies the freelist
 	 * to remove objects, whose reuse must be delayed.
@@ -3550,7 +3548,7 @@ void kmem_cache_free(struct kmem_cache *s, void *x)
 	if (!s)
 		return;
 	trace_kmem_cache_free(_RET_IP_, x, s->name);
-	slab_free(s, virt_to_slab(x), x, NULL, 1, _RET_IP_);
+	slab_free(s, virt_to_slab(x), x, NULL, &x, 1, _RET_IP_);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
@@ -3591,88 +3589,67 @@ static inline
 int build_detached_freelist(struct kmem_cache *s, size_t size,
 			    void **p, struct detached_freelist *df)
 {
-	size_t first_skipped_index = 0;
 	int lookahead = 3;
 	void *object;
 	struct folio *folio;
-	struct slab *slab;
-
-	/* Always re-init detached_freelist */
-	df->slab = NULL;
-
-	do {
-		object = p[--size];
-		/* Do we need !ZERO_OR_NULL_PTR(object) here? (for kfree) */
-	} while (!object && size);
-
-	if (!object)
-		return 0;
+	size_t same;
 
+	object = p[--size];
 	folio = virt_to_folio(object);
 	if (!s) {
 		/* Handle kalloc'ed objects */
 		if (unlikely(!folio_test_slab(folio))) {
 			free_large_kmalloc(folio, object);
-			p[size] = NULL; /* mark object processed */
+			df->slab = NULL;
 			return size;
 		}
 		/* Derive kmem_cache from object */
-		slab = folio_slab(folio);
-		df->s = slab->slab_cache;
+		df->slab = folio_slab(folio);
+		df->s = df->slab->slab_cache;
 	} else {
-		slab = folio_slab(folio);
+		df->slab = folio_slab(folio);
 		df->s = cache_from_obj(s, object); /* Support for memcg */
 	}
 
-	if (is_kfence_address(object)) {
-		slab_free_hook(df->s, object, false);
-		__kfence_free(object);
-		p[size] = NULL; /* mark object processed */
-		return size;
-	}
-
 	/* Start new detached freelist */
-	df->slab = slab;
-	set_freepointer(df->s, object, NULL);
 	df->tail = object;
 	df->freelist = object;
-	p[size] = NULL; /* mark object processed */
 	df->cnt = 1;
 
+	if (is_kfence_address(object))
+		return size;
+
+	set_freepointer(df->s, object, NULL);
+
+	same = size;
 	while (size) {
 		object = p[--size];
-		if (!object)
-			continue; /* Skip processed objects */
-
 		/* df->slab is always set at this point */
 		if (df->slab == virt_to_slab(object)) {
 			/* Opportunity build freelist */
 			set_freepointer(df->s, object, df->freelist);
 			df->freelist = object;
 			df->cnt++;
-			p[size] = NULL; /* mark object processed */
-
+			same--;
+			if (size != same)
+				swap(p[size], p[same]);
 			continue;
 		}
 
 		/* Limit look ahead search */
 		if (!--lookahead)
 			break;
-
-		if (!first_skipped_index)
-			first_skipped_index = size + 1;
 	}
 
-	return first_skipped_index;
+	return same;
 }
 
 /* Note that interrupts must be enabled when calling this function. */
 void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
 {
-	if (WARN_ON(!size))
+	if (!size)
 		return;
 
-	memcg_slab_free_hook(s, p, size);
 	do {
 		struct detached_freelist df;
 
@@ -3680,7 +3657,8 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
 		if (!df.slab)
 			continue;
 
-		slab_free(df.s, df.slab, df.freelist, df.tail, df.cnt, _RET_IP_);
+		slab_free(df.s, df.slab, df.freelist, df.tail, &p[size], df.cnt,
+			  _RET_IP_);
 	} while (likely(size));
 }
 EXPORT_SYMBOL(kmem_cache_free_bulk);
@@ -3760,7 +3738,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 error:
 	slub_put_cpu_ptr(s->cpu_slab);
 	slab_post_alloc_hook(s, objcg, flags, i, p, false);
-	__kmem_cache_free_bulk(s, i, p);
+	kmem_cache_free_bulk(s, i, p);
 	return 0;
 }
 EXPORT_SYMBOL(kmem_cache_alloc_bulk);
@@ -4441,7 +4419,7 @@ void *__kmalloc(size_t size, gfp_t flags)
 
 	ret = slab_alloc(s, NULL, flags, _RET_IP_, size);
 
-	trace_kmalloc(_RET_IP_, ret, size, s->size, flags);
+	trace_kmalloc(_RET_IP_, ret, s, size, s->size, flags);
 
 	ret = kasan_kmalloc(s, ret, size, flags);
 
@@ -4475,7 +4453,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
 	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
 		ret = kmalloc_large_node(size, flags, node);
 
-		trace_kmalloc_node(_RET_IP_, ret,
+		trace_kmalloc_node(_RET_IP_, ret, NULL,
 				   size, PAGE_SIZE << get_order(size),
 				   flags, node);
 
@@ -4489,7 +4467,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
 
 	ret = slab_alloc_node(s, NULL, flags, node, _RET_IP_, size);
 
-	trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node);
+	trace_kmalloc_node(_RET_IP_, ret, s, size, s->size, flags, node);
 
 	ret = kasan_kmalloc(s, ret, size, flags);
 
@@ -4581,7 +4559,7 @@ void kfree(const void *x)
 		return;
 	}
 	slab = folio_slab(folio);
-	slab_free(slab->slab_cache, slab, object, NULL, 1, _RET_IP_);
+	slab_free(slab->slab_cache, slab, object, NULL, &object, 1, _RET_IP_);
 }
 EXPORT_SYMBOL(kfree);
 
@@ -4890,6 +4868,9 @@ __kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
 
 	s = find_mergeable(size, align, flags, name, ctor);
 	if (s) {
+		if (sysfs_slab_alias(s, name))
+			return NULL;
+
 		s->refcount++;
 
 		/*
@@ -4898,11 +4879,6 @@ __kmem_cache_alias(const char *name, unsigned int size, unsigned int align,
 		 */
 		s->object_size = max(s->object_size, size);
 		s->inuse = max(s->inuse, ALIGN(size, sizeof(void *)));
-
-		if (sysfs_slab_alias(s, name)) {
-			s->refcount--;
-			s = NULL;
-		}
 	}
 
 	return s;
@@ -4948,7 +4924,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
 	ret = slab_alloc(s, NULL, gfpflags, caller, size);
 
 	/* Honor the call site pointer we received. */
-	trace_kmalloc(caller, ret, size, s->size, gfpflags);
+	trace_kmalloc(caller, ret, s, size, s->size, gfpflags);
 
 	return ret;
 }
@@ -4964,7 +4940,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 	if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) {
 		ret = kmalloc_large_node(size, gfpflags, node);
 
-		trace_kmalloc_node(caller, ret,
+		trace_kmalloc_node(caller, ret, NULL,
 				   size, PAGE_SIZE << get_order(size),
 				   gfpflags, node);
 
@@ -4979,7 +4955,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 	ret = slab_alloc_node(s, NULL, gfpflags, node, caller, size);
 
 	/* Honor the call site pointer we received. */
-	trace_kmalloc_node(caller, ret, size, s->size, gfpflags, node);
+	trace_kmalloc_node(caller, ret, s, size, s->size, gfpflags, node);
 
 	return ret;
 }
diff --git a/tools/vm/slabinfo.c b/tools/vm/slabinfo.c
index 9b68658b6bb8..5b98f3ee58a5 100644
--- a/tools/vm/slabinfo.c
+++ b/tools/vm/slabinfo.c
@@ -233,6 +233,24 @@ static unsigned long read_slab_obj(struct slabinfo *s, const char *name)
 	return l;
 }
 
+static unsigned long read_debug_slab_obj(struct slabinfo *s, const char *name)
+{
+	char x[128];
+	FILE *f;
+	size_t l;
+
+	snprintf(x, 128, "/sys/kernel/debug/slab/%s/%s", s->name, name);
+	f = fopen(x, "r");
+	if (!f) {
+		buffer[0] = 0;
+		l = 0;
+	} else {
+		l = fread(buffer, 1, sizeof(buffer), f);
+		buffer[l] = 0;
+		fclose(f);
+	}
+	return l;
+}
 
 /*
  * Put a size string together
@@ -409,14 +427,18 @@ static void show_tracking(struct slabinfo *s)
 {
 	printf("\n%s: Kernel object allocation\n", s->name);
 	printf("-----------------------------------------------------------------------\n");
-	if (read_slab_obj(s, "alloc_calls"))
+	if (read_debug_slab_obj(s, "alloc_traces"))
+		printf("%s", buffer);
+	else if (read_slab_obj(s, "alloc_calls"))
 		printf("%s", buffer);
 	else
 		printf("No Data\n");
 
 	printf("\n%s: Kernel object freeing\n", s->name);
 	printf("------------------------------------------------------------------------\n");
-	if (read_slab_obj(s, "free_calls"))
+	if (read_debug_slab_obj(s, "free_traces"))
+		printf("%s", buffer);
+	else if (read_slab_obj(s, "free_calls"))
 		printf("%s", buffer);
 	else
 		printf("No Data\n");