diff --git a/mm/slub.c b/mm/slub.c
index bd2efae..b07a1ca 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -81,10 +81,14 @@
  * PageActive 		The slab is used as a cpu cache. Allocations
  * 			may be performed from the slab. The slab is not
  * 			on any slab list and cannot be moved onto one.
+ * 			The cpu slab may be equipped with an additioanl
+ * 			lockless_freelist that allows lockless access to
+ * 			free objects in addition to the regular freelist
+ * 			that requires the slab lock.
  *
  * PageError		Slab requires special handling due to debug
  * 			options set. This moves	slab handling out of
- * 			the fast path.
+ * 			the fast path and disables lockless freelists.
  */
 
 static inline int SlabDebug(struct page *page)
@@ -1014,6 +1018,7 @@
 	set_freepointer(s, last, NULL);
 
 	page->freelist = start;
+	page->lockless_freelist = NULL;
 	page->inuse = 0;
 out:
 	if (flags & __GFP_WAIT)
@@ -1276,6 +1281,23 @@
  */
 static void deactivate_slab(struct kmem_cache *s, struct page *page, int cpu)
 {
+	/*
+	 * Merge cpu freelist into freelist. Typically we get here
+	 * because both freelists are empty. So this is unlikely
+	 * to occur.
+	 */
+	while (unlikely(page->lockless_freelist)) {
+		void **object;
+
+		/* Retrieve object from cpu_freelist */
+		object = page->lockless_freelist;
+		page->lockless_freelist = page->lockless_freelist[page->offset];
+
+		/* And put onto the regular freelist */
+		object[page->offset] = page->freelist;
+		page->freelist = object;
+		page->inuse--;
+	}
 	s->cpu_slab[cpu] = NULL;
 	ClearPageActive(page);
 
@@ -1322,47 +1344,46 @@
 }
 
 /*
- * slab_alloc is optimized to only modify two cachelines on the fast path
- * (aside from the stack):
+ * Slow path. The lockless freelist is empty or we need to perform
+ * debugging duties.
  *
- * 1. The page struct
- * 2. The first cacheline of the object to be allocated.
+ * Interrupts are disabled.
  *
- * The only other cache lines that are read (apart from code) is the
- * per cpu array in the kmem_cache struct.
+ * Processing is still very fast if new objects have been freed to the
+ * regular freelist. In that case we simply take over the regular freelist
+ * as the lockless freelist and zap the regular freelist.
  *
- * Fastpath is not possible if we need to get a new slab or have
- * debugging enabled (which means all slabs are marked with SlabDebug)
+ * If that is not working then we fall back to the partial lists. We take the
+ * first element of the freelist as the object to allocate now and move the
+ * rest of the freelist to the lockless freelist.
+ *
+ * And if we were unable to get a new slab from the partial slab lists then
+ * we need to allocate a new slab. This is slowest path since we may sleep.
  */
-static void *slab_alloc(struct kmem_cache *s,
-				gfp_t gfpflags, int node, void *addr)
+static void *__slab_alloc(struct kmem_cache *s,
+		gfp_t gfpflags, int node, void *addr, struct page *page)
 {
-	struct page *page;
 	void **object;
-	unsigned long flags;
-	int cpu;
+	int cpu = smp_processor_id();
 
-	local_irq_save(flags);
-	cpu = smp_processor_id();
-	page = s->cpu_slab[cpu];
 	if (!page)
 		goto new_slab;
 
 	slab_lock(page);
 	if (unlikely(node != -1 && page_to_nid(page) != node))
 		goto another_slab;
-redo:
+load_freelist:
 	object = page->freelist;
 	if (unlikely(!object))
 		goto another_slab;
 	if (unlikely(SlabDebug(page)))
 		goto debug;
 
-have_object:
-	page->inuse++;
-	page->freelist = object[page->offset];
+	object = page->freelist;
+	page->lockless_freelist = object[page->offset];
+	page->inuse = s->objects;
+	page->freelist = NULL;
 	slab_unlock(page);
-	local_irq_restore(flags);
 	return object;
 
 another_slab:
@@ -1370,11 +1391,11 @@
 
 new_slab:
 	page = get_partial(s, gfpflags, node);
-	if (likely(page)) {
+	if (page) {
 have_slab:
 		s->cpu_slab[cpu] = page;
 		SetPageActive(page);
-		goto redo;
+		goto load_freelist;
 	}
 
 	page = new_slab(s, gfpflags, node);
@@ -1397,7 +1418,7 @@
 				discard_slab(s, page);
 				page = s->cpu_slab[cpu];
 				slab_lock(page);
-				goto redo;
+				goto load_freelist;
 			}
 			/* New slab does not fit our expectations */
 			flush_slab(s, s->cpu_slab[cpu], cpu);
@@ -1405,16 +1426,52 @@
 		slab_lock(page);
 		goto have_slab;
 	}
-	local_irq_restore(flags);
 	return NULL;
 debug:
+	object = page->freelist;
 	if (!alloc_object_checks(s, page, object))
 		goto another_slab;
 	if (s->flags & SLAB_STORE_USER)
 		set_track(s, object, TRACK_ALLOC, addr);
 	trace(s, page, object, 1);
 	init_object(s, object, 1);
-	goto have_object;
+
+	page->inuse++;
+	page->freelist = object[page->offset];
+	slab_unlock(page);
+	return object;
+}
+
+/*
+ * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc)
+ * have the fastpath folded into their functions. So no function call
+ * overhead for requests that can be satisfied on the fastpath.
+ *
+ * The fastpath works by first checking if the lockless freelist can be used.
+ * If not then __slab_alloc is called for slow processing.
+ *
+ * Otherwise we can simply pick the next object from the lockless free list.
+ */
+static void __always_inline *slab_alloc(struct kmem_cache *s,
+				gfp_t gfpflags, int node, void *addr)
+{
+	struct page *page;
+	void **object;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	page = s->cpu_slab[smp_processor_id()];
+	if (unlikely(!page || !page->lockless_freelist ||
+			(node != -1 && page_to_nid(page) != node)))
+
+		object = __slab_alloc(s, gfpflags, node, addr, page);
+
+	else {
+		object = page->lockless_freelist;
+		page->lockless_freelist = object[page->offset];
+	}
+	local_irq_restore(flags);
+	return object;
 }
 
 void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
@@ -1432,20 +1489,19 @@
 #endif
 
 /*
- * The fastpath only writes the cacheline of the page struct and the first
- * cacheline of the object.
+ * Slow patch handling. This may still be called frequently since objects
+ * have a longer lifetime than the cpu slabs in most processing loads.
  *
- * We read the cpu_slab cacheline to check if the slab is the per cpu
- * slab for this processor.
+ * So we still attempt to reduce cache line usage. Just take the slab
+ * lock and free the item. If there is no additional partial page
+ * handling required then we can return immediately.
  */
-static void slab_free(struct kmem_cache *s, struct page *page,
+static void __slab_free(struct kmem_cache *s, struct page *page,
 					void *x, void *addr)
 {
 	void *prior;
 	void **object = (void *)x;
-	unsigned long flags;
 
-	local_irq_save(flags);
 	slab_lock(page);
 
 	if (unlikely(SlabDebug(page)))
@@ -1475,7 +1531,6 @@
 
 out_unlock:
 	slab_unlock(page);
-	local_irq_restore(flags);
 	return;
 
 slab_empty:
@@ -1487,7 +1542,6 @@
 
 	slab_unlock(page);
 	discard_slab(s, page);
-	local_irq_restore(flags);
 	return;
 
 debug:
@@ -1502,6 +1556,34 @@
 	goto checks_ok;
 }
 
+/*
+ * Fastpath with forced inlining to produce a kfree and kmem_cache_free that
+ * can perform fastpath freeing without additional function calls.
+ *
+ * The fastpath is only possible if we are freeing to the current cpu slab
+ * of this processor. This typically the case if we have just allocated
+ * the item before.
+ *
+ * If fastpath is not possible then fall back to __slab_free where we deal
+ * with all sorts of special processing.
+ */
+static void __always_inline slab_free(struct kmem_cache *s,
+			struct page *page, void *x, void *addr)
+{
+	void **object = (void *)x;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	if (likely(page == s->cpu_slab[smp_processor_id()] &&
+						!SlabDebug(page))) {
+		object[page->offset] = page->lockless_freelist;
+		page->lockless_freelist = object;
+	} else
+		__slab_free(s, page, x, addr);
+
+	local_irq_restore(flags);
+}
+
 void kmem_cache_free(struct kmem_cache *s, void *x)
 {
 	struct page *page;