Merge branch 'akpm' (patches from Andrew)

Merge slub bulk allocator updates from Andrew Morton:
 "This missed the merge window because I was waiting for some repairs to
  come in.  Nothing actually uses the bulk allocator yet and the changes
  to other code paths are pretty small.  And the net guys are waiting
  for this so they can start merging the client code"

More comments from Jesper Dangaard Brouer:
 "The kmem_cache_alloc_bulk() call, in mm/slub.c, were included in
  previous kernel.  The present version contains a bug.  Vladimir
  Davydov noticed it contained a bug, when kernel is compiled with
  CONFIG_MEMCG_KMEM (see commit 03ec0ed57ffc: "slub: fix kmem cgroup
  bug in kmem_cache_alloc_bulk").  Plus the mem cgroup counterpart in
  kmem_cache_free_bulk() were missing (see commit 033745189b1b "slub:
  add missing kmem cgroup support to kmem_cache_free_bulk").

  I don't consider the fix stable-material because there are no in-tree
  users of the API.

  But with known bugs (for memcg) I cannot start using the API in the
  net-tree"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  slab/slub: adjust kmem_cache_alloc_bulk API
  slub: add missing kmem cgroup support to kmem_cache_free_bulk
  slub: fix kmem cgroup bug in kmem_cache_alloc_bulk
  slub: optimize bulk slowpath free by detached freelist
  slub: support for bulk free with SLUB freelists

5 files changed, 181 insertions, 75 deletions

diff --git a/mm/slab.c b/mm/slab.c
index e0819fa96559..4765c97ce690 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3419,7 +3419,7 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
 }
 EXPORT_SYMBOL(kmem_cache_free_bulk);
 
-bool 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 size,
 								void **p)
 {
 	return __kmem_cache_alloc_bulk(s, flags, size, p);
diff --git a/mm/slab.h b/mm/slab.h
index 27492eb678f7..7b6087197997 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -170,7 +170,7 @@ ssize_t slabinfo_write(struct file *file, const char __user *buffer,
  * may be allocated or freed using these operations.
  */
 void __kmem_cache_free_bulk(struct kmem_cache *, size_t, void **);
-bool __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
+int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **);
 
 #ifdef CONFIG_MEMCG_KMEM
 /*
diff --git a/mm/slab_common.c b/mm/slab_common.c
index d88e97c10a2e..3c6a86b4ec25 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -112,7 +112,7 @@ void __kmem_cache_free_bulk(struct kmem_cache *s, size_t nr, void **p)
 		kmem_cache_free(s, p[i]);
 }
 
-bool __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr,
+int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr,
 								void **p)
 {
 	size_t i;
@@ -121,10 +121,10 @@ bool __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr,
 		void *x = p[i] = kmem_cache_alloc(s, flags);
 		if (!x) {
 			__kmem_cache_free_bulk(s, i, p);
-			return false;
+			return 0;
 		}
 	}
-	return true;
+	return i;
 }
 
 #ifdef CONFIG_MEMCG_KMEM
diff --git a/mm/slob.c b/mm/slob.c
index 0d7e5df74d1f..17e8f8cc7c53 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -617,7 +617,7 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
 }
 EXPORT_SYMBOL(kmem_cache_free_bulk);
 
-bool 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 size,
 								void **p)
 {
 	return __kmem_cache_alloc_bulk(s, flags, size, p);
diff --git a/mm/slub.c b/mm/slub.c
index a0c1365f6426..46997517406e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1065,11 +1065,15 @@ bad:
 	return 0;
 }
 
+/* Supports checking bulk free of a constructed freelist */
 static noinline struct kmem_cache_node *free_debug_processing(
-	struct kmem_cache *s, struct page *page, void *object,
+	struct kmem_cache *s, struct page *page,
+	void *head, void *tail, int bulk_cnt,
 	unsigned long addr, unsigned long *flags)
 {
 	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
+	void *object = head;
+	int cnt = 0;
 
 	spin_lock_irqsave(&n->list_lock, *flags);
 	slab_lock(page);
@@ -1077,6 +1081,9 @@ static noinline struct kmem_cache_node *free_debug_processing(
 	if (!check_slab(s, page))
 		goto fail;
 
+next_object:
+	cnt++;
+
 	if (!check_valid_pointer(s, page, object)) {
 		slab_err(s, page, "Invalid object pointer 0x%p", object);
 		goto fail;
@@ -1107,8 +1114,19 @@ static noinline struct kmem_cache_node *free_debug_processing(
 	if (s->flags & SLAB_STORE_USER)
 		set_track(s, object, TRACK_FREE, addr);
 	trace(s, page, object, 0);
+	/* Freepointer not overwritten by init_object(), SLAB_POISON moved it */
 	init_object(s, object, SLUB_RED_INACTIVE);
+
+	/* Reached end of constructed freelist yet? */
+	if (object != tail) {
+		object = get_freepointer(s, object);
+		goto next_object;
+	}
 out:
+	if (cnt != bulk_cnt)
+		slab_err(s, page, "Bulk freelist count(%d) invalid(%d)\n",
+			 bulk_cnt, cnt);
+
 	slab_unlock(page);
 	/*
 	 * Keep node_lock to preserve integrity
@@ -1212,7 +1230,8 @@ static inline int alloc_debug_processing(struct kmem_cache *s,
 	struct page *page, void *object, unsigned long addr) { return 0; }
 
 static inline struct kmem_cache_node *free_debug_processing(
-	struct kmem_cache *s, struct page *page, void *object,
+	struct kmem_cache *s, struct page *page,
+	void *head, void *tail, int bulk_cnt,
 	unsigned long addr, unsigned long *flags) { return NULL; }
 
 static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
@@ -1273,14 +1292,21 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s,
 	return memcg_kmem_get_cache(s, flags);
 }
 
-static inline void slab_post_alloc_hook(struct kmem_cache *s,
-					gfp_t flags, void *object)
+static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
+					size_t size, void **p)
 {
+	size_t i;
+
 	flags &= gfp_allowed_mask;
-	kmemcheck_slab_alloc(s, flags, object, slab_ksize(s));
-	kmemleak_alloc_recursive(object, s->object_size, 1, s->flags, flags);
+	for (i = 0; i < size; i++) {
+		void *object = p[i];
+
+		kmemcheck_slab_alloc(s, flags, object, slab_ksize(s));
+		kmemleak_alloc_recursive(object, s->object_size, 1,
+					 s->flags, flags);
+		kasan_slab_alloc(s, object);
+	}
 	memcg_kmem_put_cache(s);
-	kasan_slab_alloc(s, object);
 }
 
 static inline void slab_free_hook(struct kmem_cache *s, void *x)
@@ -1308,6 +1334,29 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x)
 	kasan_slab_free(s, x);
 }
 
+static inline void slab_free_freelist_hook(struct kmem_cache *s,
+					   void *head, void *tail)
+{
+/*
+ * Compiler cannot detect this function can be removed if slab_free_hook()
+ * evaluates to nothing.  Thus, catch all relevant config debug options here.
+ */
+#if defined(CONFIG_KMEMCHECK) ||		\
+	defined(CONFIG_LOCKDEP)	||		\
+	defined(CONFIG_DEBUG_KMEMLEAK) ||	\
+	defined(CONFIG_DEBUG_OBJECTS_FREE) ||	\
+	defined(CONFIG_KASAN)
+
+	void *object = head;
+	void *tail_obj = tail ? : head;
+
+	do {
+		slab_free_hook(s, object);
+	} while ((object != tail_obj) &&
+		 (object = get_freepointer(s, object)));
+#endif
+}
+
 static void setup_object(struct kmem_cache *s, struct page *page,
 				void *object)
 {
@@ -2433,7 +2482,7 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 static __always_inline void *slab_alloc_node(struct kmem_cache *s,
 		gfp_t gfpflags, int node, unsigned long addr)
 {
-	void **object;
+	void *object;
 	struct kmem_cache_cpu *c;
 	struct page *page;
 	unsigned long tid;
@@ -2512,7 +2561,7 @@ redo:
 	if (unlikely(gfpflags & __GFP_ZERO) && object)
 		memset(object, 0, s->object_size);
 
-	slab_post_alloc_hook(s, gfpflags, object);
+	slab_post_alloc_hook(s, gfpflags, 1, &object);
 
 	return object;
 }
@@ -2583,10 +2632,11 @@ EXPORT_SYMBOL(kmem_cache_alloc_node_trace);
  * handling required then we can return immediately.
  */
 static void __slab_free(struct kmem_cache *s, struct page *page,
-			void *x, unsigned long addr)
+			void *head, void *tail, int cnt,
+			unsigned long addr)
+
 {
 	void *prior;
-	void **object = (void *)x;
 	int was_frozen;
 	struct page new;
 	unsigned long counters;
@@ -2596,7 +2646,8 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 	stat(s, FREE_SLOWPATH);
 
 	if (kmem_cache_debug(s) &&
-		!(n = free_debug_processing(s, page, x, addr, &flags)))
+	    !(n = free_debug_processing(s, page, head, tail, cnt,
+					addr, &flags)))
 		return;
 
 	do {
@@ -2606,10 +2657,10 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 		}
 		prior = page->freelist;
 		counters = page->counters;
-		set_freepointer(s, object, prior);
+		set_freepointer(s, tail, prior);
 		new.counters = counters;
 		was_frozen = new.frozen;
-		new.inuse--;
+		new.inuse -= cnt;
 		if ((!new.inuse || !prior) && !was_frozen) {
 
 			if (kmem_cache_has_cpu_partial(s) && !prior) {
@@ -2640,7 +2691,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 
 	} while (!cmpxchg_double_slab(s, page,
 		prior, counters,
-		object, new.counters,
+		head, new.counters,
 		"__slab_free"));
 
 	if (likely(!n)) {
@@ -2705,15 +2756,20 @@ slab_empty:
  *
  * If fastpath is not possible then fall back to __slab_free where we deal
  * with all sorts of special processing.
+ *
+ * Bulk free of a freelist with several objects (all pointing to the
+ * same page) possible by specifying head and tail ptr, plus objects
+ * count (cnt). Bulk free indicated by tail pointer being set.
  */
-static __always_inline void slab_free(struct kmem_cache *s,
-			struct page *page, void *x, unsigned long addr)
+static __always_inline void slab_free(struct kmem_cache *s, struct page *page,
+				      void *head, void *tail, int cnt,
+				      unsigned long addr)
 {
-	void **object = (void *)x;
+	void *tail_obj = tail ? : head;
 	struct kmem_cache_cpu *c;
 	unsigned long tid;
 
-	slab_free_hook(s, x);
+	slab_free_freelist_hook(s, head, tail);
 
 redo:
 	/*
@@ -2732,19 +2788,19 @@ redo:
 	barrier();
 
 	if (likely(page == c->page)) {
-		set_freepointer(s, object, c->freelist);
+		set_freepointer(s, tail_obj, c->freelist);
 
 		if (unlikely(!this_cpu_cmpxchg_double(
 				s->cpu_slab->freelist, s->cpu_slab->tid,
 				c->freelist, tid,
-				object, next_tid(tid)))) {
+				head, next_tid(tid)))) {
 
 			note_cmpxchg_failure("slab_free", s, tid);
 			goto redo;
 		}
 		stat(s, FREE_FASTPATH);
 	} else
-		__slab_free(s, page, x, addr);
+		__slab_free(s, page, head, tail_obj, cnt, addr);
 
 }
 
@@ -2753,59 +2809,116 @@ void kmem_cache_free(struct kmem_cache *s, void *x)
 	s = cache_from_obj(s, x);
 	if (!s)
 		return;
-	slab_free(s, virt_to_head_page(x), x, _RET_IP_);
+	slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_);
 	trace_kmem_cache_free(_RET_IP_, x);
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
-/* Note that interrupts must be enabled when calling this function. */
-void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
-{
-	struct kmem_cache_cpu *c;
+struct detached_freelist {
 	struct page *page;
-	int i;
+	void *tail;
+	void *freelist;
+	int cnt;
+};
 
-	local_irq_disable();
-	c = this_cpu_ptr(s->cpu_slab);
+/*
+ * This function progressively scans the array with free objects (with
+ * a limited look ahead) and extract objects belonging to the same
+ * page.  It builds a detached freelist directly within the given
+ * page/objects.  This can happen without any need for
+ * synchronization, because the objects are owned by running process.
+ * The freelist is build up as a single linked list in the objects.
+ * The idea is, that this detached freelist can then be bulk
+ * transferred to the real freelist(s), but only requiring a single
+ * synchronization primitive.  Look ahead in the array is limited due
+ * to performance reasons.
+ */
+static 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;
 
-	for (i = 0; i < size; i++) {
-		void *object = p[i];
+	/* Always re-init detached_freelist */
+	df->page = NULL;
 
-		BUG_ON(!object);
-		/* kmem cache debug support */
-		s = cache_from_obj(s, object);
-		if (unlikely(!s))
-			goto exit;
-		slab_free_hook(s, object);
+	do {
+		object = p[--size];
+	} while (!object && size);
 
-		page = virt_to_head_page(object);
+	if (!object)
+		return 0;
 
-		if (c->page == page) {
-			/* Fastpath: local CPU free */
-			set_freepointer(s, object, c->freelist);
-			c->freelist = object;
-		} else {
-			c->tid = next_tid(c->tid);
-			local_irq_enable();
-			/* Slowpath: overhead locked cmpxchg_double_slab */
-			__slab_free(s, page, object, _RET_IP_);
-			local_irq_disable();
-			c = this_cpu_ptr(s->cpu_slab);
+	/* Start new detached freelist */
+	set_freepointer(s, object, NULL);
+	df->page = virt_to_head_page(object);
+	df->tail = object;
+	df->freelist = object;
+	p[size] = NULL; /* mark object processed */
+	df->cnt = 1;
+
+	while (size) {
+		object = p[--size];
+		if (!object)
+			continue; /* Skip processed objects */
+
+		/* df->page is always set at this point */
+		if (df->page == virt_to_head_page(object)) {
+			/* Opportunity build freelist */
+			set_freepointer(s, object, df->freelist);
+			df->freelist = object;
+			df->cnt++;
+			p[size] = NULL; /* mark object processed */
+
+			continue;
 		}
+
+		/* Limit look ahead search */
+		if (!--lookahead)
+			break;
+
+		if (!first_skipped_index)
+			first_skipped_index = size + 1;
 	}
-exit:
-	c->tid = next_tid(c->tid);
-	local_irq_enable();
+
+	return first_skipped_index;
+}
+
+
+/* Note that interrupts must be enabled when calling this function. */
+void kmem_cache_free_bulk(struct kmem_cache *orig_s, size_t size, void **p)
+{
+	if (WARN_ON(!size))
+		return;
+
+	do {
+		struct detached_freelist df;
+		struct kmem_cache *s;
+
+		/* Support for memcg */
+		s = cache_from_obj(orig_s, p[size - 1]);
+
+		size = build_detached_freelist(s, size, p, &df);
+		if (unlikely(!df.page))
+			continue;
+
+		slab_free(s, df.page, df.freelist, df.tail, df.cnt, _RET_IP_);
+	} while (likely(size));
 }
 EXPORT_SYMBOL(kmem_cache_free_bulk);
 
 /* Note that interrupts must be enabled when calling this function. */
-bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
-			   void **p)
+int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
+			  void **p)
 {
 	struct kmem_cache_cpu *c;
 	int i;
 
+	/* memcg and kmem_cache debug support */
+	s = slab_pre_alloc_hook(s, flags);
+	if (unlikely(!s))
+		return false;
 	/*
 	 * Drain objects in the per cpu slab, while disabling local
 	 * IRQs, which protects against PREEMPT and interrupts
@@ -2830,17 +2943,8 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 			c = this_cpu_ptr(s->cpu_slab);
 			continue; /* goto for-loop */
 		}
-
-		/* kmem_cache debug support */
-		s = slab_pre_alloc_hook(s, flags);
-		if (unlikely(!s))
-			goto error;
-
 		c->freelist = get_freepointer(s, object);
 		p[i] = object;
-
-		/* kmem_cache debug support */
-		slab_post_alloc_hook(s, flags, object);
 	}
 	c->tid = next_tid(c->tid);
 	local_irq_enable();
@@ -2853,12 +2957,14 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size,
 			memset(p[j], 0, s->object_size);
 	}
 
-	return true;
-
+	/* memcg and kmem_cache debug support */
+	slab_post_alloc_hook(s, flags, size, p);
+	return i;
 error:
-	__kmem_cache_free_bulk(s, i, p);
 	local_irq_enable();
-	return false;
+	slab_post_alloc_hook(s, flags, i, p);
+	__kmem_cache_free_bulk(s, i, p);
+	return 0;
 }
 EXPORT_SYMBOL(kmem_cache_alloc_bulk);
 
@@ -3523,7 +3629,7 @@ void kfree(const void *x)
 		__free_kmem_pages(page, compound_order(page));
 		return;
 	}
-	slab_free(page->slab_cache, page, object, _RET_IP_);
+	slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_);
 }
 EXPORT_SYMBOL(kfree);