diff --git a/include/linux/slab.h b/include/linux/slab.h
index d6393413ef097d4ca13c21a3a8fdb51c01ae79fd..e4f5d7f88c16601a4d1d8f3f2acf1c53610b44c3 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -457,6 +457,10 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
  * kmalloc is the normal method of allocating memory
  * for objects smaller than page size in the kernel.
  *
+ * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN
+ * bytes. For @size of power of two bytes, the alignment is also guaranteed
+ * to be at least to the size.
+ *
  * The @flags argument may be one of:
  *
  * %GFP_USER - Allocate memory on behalf of user.  May sleep.
diff --git a/mm/slab_common.c b/mm/slab_common.c
index a94b9981eb172702f8a84e8d5cd69d4b624a289e..9b8d6a9f1e976288ced559f310e119957ed10970 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -970,10 +970,19 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name,
 		unsigned int useroffset, unsigned int usersize)
 {
 	int err;
+	unsigned int align = ARCH_KMALLOC_MINALIGN;
 
 	s->name = name;
 	s->size = s->object_size = size;
-	s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size);
+
+	/*
+	 * For power of two sizes, guarantee natural alignment for kmalloc
+	 * caches, regardless of SL*B debugging options.
+	 */
+	if (is_power_of_2(size))
+		align = max(align, size);
+	s->align = calculate_alignment(flags, align, size);
+
 	s->useroffset = useroffset;
 	s->usersize = usersize;
 
diff --git a/mm/slob.c b/mm/slob.c
index 307c2c9feb441d99789f031b9bdc6eaf46234618..fdf284009be9238d8370cda3000e619d90ecf21e 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -215,7 +215,7 @@ static void slob_free_pages(void *b, int order)
 /*
  * Allocate a slob block within a given slob_page sp.
  */
-static void *slob_page_alloc(struct page *sp, size_t size, int align)
+static void *slob_page_alloc(struct page *sp, size_t size, int align, int align_offset)
 {
 	slob_t *prev, *cur, *aligned = NULL;
 	int delta = 0, units = SLOB_UNITS(size);
@@ -223,8 +223,17 @@ static void *slob_page_alloc(struct page *sp, size_t size, int align)
 	for (prev = NULL, cur = sp->freelist; ; prev = cur, cur = slob_next(cur)) {
 		slobidx_t avail = slob_units(cur);
 
+		/*
+		 * 'aligned' will hold the address of the slob block so that the
+		 * address 'aligned'+'align_offset' is aligned according to the
+		 * 'align' parameter. This is for kmalloc() which prepends the
+		 * allocated block with its size, so that the block itself is
+		 * aligned when needed.
+		 */
 		if (align) {
-			aligned = (slob_t *)ALIGN((unsigned long)cur, align);
+			aligned = (slob_t *)
+				(ALIGN((unsigned long)cur + align_offset, align)
+				 - align_offset);
 			delta = aligned - cur;
 		}
 		if (avail >= units + delta) { /* room enough? */
@@ -266,7 +275,8 @@ static void *slob_page_alloc(struct page *sp, size_t size, int align)
 /*
  * slob_alloc: entry point into the slob allocator.
  */
-static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
+static void *slob_alloc(size_t size, gfp_t gfp, int align, int node,
+							int align_offset)
 {
 	struct page *sp;
 	struct list_head *prev;
@@ -298,7 +308,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
 
 		/* Attempt to alloc */
 		prev = sp->lru.prev;
-		b = slob_page_alloc(sp, size, align);
+		b = slob_page_alloc(sp, size, align, align_offset);
 		if (!b)
 			continue;
 
@@ -326,7 +336,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
 		INIT_LIST_HEAD(&sp->lru);
 		set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE));
 		set_slob_page_free(sp, slob_list);
-		b = slob_page_alloc(sp, size, align);
+		b = slob_page_alloc(sp, size, align, align_offset);
 		BUG_ON(!b);
 		spin_unlock_irqrestore(&slob_lock, flags);
 	}
@@ -428,7 +438,7 @@ static __always_inline void *
 __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 {
 	unsigned int *m;
-	int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
+	int minalign = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
 	void *ret;
 
 	gfp &= gfp_allowed_mask;
@@ -436,19 +446,28 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
 	fs_reclaim_acquire(gfp);
 	fs_reclaim_release(gfp);
 
-	if (size < PAGE_SIZE - align) {
+	if (size < PAGE_SIZE - minalign) {
+		int align = minalign;
+
+		/*
+		 * For power of two sizes, guarantee natural alignment for
+		 * kmalloc()'d objects.
+		 */
+		if (is_power_of_2(size))
+			align = max(minalign, (int) size);
+
 		if (!size)
 			return ZERO_SIZE_PTR;
 
-		m = slob_alloc(size + align, gfp, align, node);
+		m = slob_alloc(size + minalign, gfp, align, node, minalign);
 
 		if (!m)
 			return NULL;
 		*m = size;
-		ret = (void *)m + align;
+		ret = (void *)m + minalign;
 
 		trace_kmalloc_node(caller, ret,
-				   size, size + align, gfp, node);
+				   size, size + minalign, gfp, node);
 	} else {
 		unsigned int order = get_order(size);
 
@@ -544,7 +563,7 @@ static void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
 	fs_reclaim_release(flags);
 
 	if (c->size < PAGE_SIZE) {
-		b = slob_alloc(c->size, flags, c->align, node);
+		b = slob_alloc(c->size, flags, c->align, node, 0);
 		trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size,
 					    SLOB_UNITS(c->size) * SLOB_UNIT,
 					    flags, node);