Merge branch 'slab/next' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux

Pull SLAB changes from Pekka Enberg:
 "The patches from Joonsoo Kim switch mm/slab.c to use 'struct page' for
  slab internals similar to mm/slub.c.  This reduces memory usage and
  improves performance:

    https://lkml.org/lkml/2013/10/16/155

  Rest of the changes are bug fixes from various people"

* 'slab/next' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux: (21 commits)
  mm, slub: fix the typo in mm/slub.c
  mm, slub: fix the typo in include/linux/slub_def.h
  slub: Handle NULL parameter in kmem_cache_flags
  slab: replace non-existing 'struct freelist *' with 'void *'
  slab: fix to calm down kmemleak warning
  slub: proper kmemleak tracking if CONFIG_SLUB_DEBUG disabled
  slab: rename slab_bufctl to slab_freelist
  slab: remove useless statement for checking pfmemalloc
  slab: use struct page for slab management
  slab: replace free and inuse in struct slab with newly introduced active
  slab: remove SLAB_LIMIT
  slab: remove kmem_bufctl_t
  slab: change the management method of free objects of the slab
  slab: use __GFP_COMP flag for allocating slab pages
  slab: use well-defined macro, virt_to_slab()
  slab: overloading the RCU head over the LRU for RCU free
  slab: remove cachep in struct slab_rcu
  slab: remove nodeid in struct slab
  slab: remove colouroff in struct slab
  slab: change return type of kmem_getpages() to struct page
  ...

include/linux/mm_types.h

@@ -44,18 +44,22 @@ struct page {
 	/* First double word block */
 	unsigned long flags;		/* Atomic flags, some possibly
 					 * updated asynchronously */
-	struct address_space *mapping;	/* If low bit clear, points to
-					 * inode address_space, or NULL.
-					 * If page mapped as anonymous
-					 * memory, low bit is set, and
-					 * it points to anon_vma object:
-					 * see PAGE_MAPPING_ANON below.
-					 */
+	union {
+		struct address_space *mapping;	/* If low bit clear, points to
+						 * inode address_space, or NULL.
+						 * If page mapped as anonymous
+						 * memory, low bit is set, and
+						 * it points to anon_vma object:
+						 * see PAGE_MAPPING_ANON below.
+						 */
+		void *s_mem;			/* slab first object */
+	};
+
 	/* Second double word */
 	struct {
 		union {
 			pgoff_t index;		/* Our offset within mapping. */
-			void *freelist;		/* slub/slob first free object */
+			void *freelist;		/* sl[aou]b first free object */
 			bool pfmemalloc;	/* If set by the page allocator,
 						 * ALLOC_NO_WATERMARKS was set
 						 * and the low watermark was not
@@ -111,6 +115,7 @@ struct page {
 				};
 				atomic_t _count;		/* Usage count, see below. */
 			};
+			unsigned int active;	/* SLAB */
 		};
 	};
 
@@ -132,6 +137,9 @@ struct page {
 
 		struct list_head list;	/* slobs list of pages */
 		struct slab *slab_page; /* slab fields */
+		struct rcu_head rcu_head;	/* Used by SLAB
+						 * when destroying via RCU
+						 */
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
 		pgtable_t pmd_huge_pte; /* protected by page->ptl */
 #endif

include/linux/slab.h

@@ -53,7 +53,14 @@
  *  }
  *  rcu_read_unlock();
  *
- * See also the comment on struct slab_rcu in mm/slab.c.
+ * This is useful if we need to approach a kernel structure obliquely,
+ * from its address obtained without the usual locking. We can lock
+ * the structure to stabilize it and check it's still at the given address,
+ * only if we can be sure that the memory has not been meanwhile reused
+ * for some other kind of object (which our subsystem's lock might corrupt).
+ *
+ * rcu_read_lock before reading the address, then rcu_read_unlock after
+ * taking the spinlock within the structure expected at that address.
  */
 #define SLAB_DESTROY_BY_RCU	0x00080000UL	/* Defer freeing slabs to RCU */
 #define SLAB_MEM_SPREAD		0x00100000UL	/* Spread some memory over cpuset */

include/linux/slab_def.h

@@ -27,8 +27,8 @@ struct kmem_cache {
 
 	size_t colour;			/* cache colouring range */
 	unsigned int colour_off;	/* colour offset */
-	struct kmem_cache *slabp_cache;
-	unsigned int slab_size;
+	struct kmem_cache *freelist_cache;
+	unsigned int freelist_size;
 
 	/* constructor func */
 	void (*ctor)(void *obj);

include/linux/slub_def.h

@@ -11,7 +11,7 @@
 enum stat_item {
 	ALLOC_FASTPATH,		/* Allocation from cpu slab */
 	ALLOC_SLOWPATH,		/* Allocation by getting a new cpu slab */
-	FREE_FASTPATH,		/* Free to cpu slub */
+	FREE_FASTPATH,		/* Free to cpu slab */
 	FREE_SLOWPATH,		/* Freeing not to cpu slab */
 	FREE_FROZEN,		/* Freeing to frozen slab */
 	FREE_ADD_PARTIAL,	/* Freeing moves slab to partial list */

mm/slub.c

@@ -155,7 +155,7 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
 /*
  * Maximum number of desirable partial slabs.
  * The existence of more partial slabs makes kmem_cache_shrink
- * sort the partial list by the number of objects in the.
+ * sort the partial list by the number of objects in use.
  */
 #define MAX_PARTIAL 10
 
@@ -933,6 +933,16 @@ static void trace(struct kmem_cache *s, struct page *page, void *object,
  * Hooks for other subsystems that check memory allocations. In a typical
  * production configuration these hooks all should produce no code at all.
  */
+static inline void kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags)
+{
+	kmemleak_alloc(ptr, size, 1, flags);
+}
+
+static inline void kfree_hook(const void *x)
+{
+	kmemleak_free(x);
+}
+
 static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
 {
 	flags &= gfp_allowed_mask;
@@ -1217,8 +1227,8 @@ static unsigned long kmem_cache_flags(unsigned long object_size,
 	/*
 	 * Enable debugging if selected on the kernel commandline.
 	 */
-	if (slub_debug && (!slub_debug_slabs ||
-		!strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs))))
+	if (slub_debug && (!slub_debug_slabs || (name &&
+		!strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs)))))
 		flags |= slub_debug;
 
 	return flags;
@@ -1260,13 +1270,30 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node,
 static inline void dec_slabs_node(struct kmem_cache *s, int node,
 							int objects) {}
 
+static inline void kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags)
+{
+	kmemleak_alloc(ptr, size, 1, flags);
+}
+
+static inline void kfree_hook(const void *x)
+{
+	kmemleak_free(x);
+}
+
 static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
 							{ return 0; }
 
 static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
-		void *object) {}
+		void *object)
+{
+	kmemleak_alloc_recursive(object, s->object_size, 1, s->flags,
+		flags & gfp_allowed_mask);
+}
 
-static inline void slab_free_hook(struct kmem_cache *s, void *x) {}
+static inline void slab_free_hook(struct kmem_cache *s, void *x)
+{
+	kmemleak_free_recursive(x, s->flags);
+}
 
 #endif /* CONFIG_SLUB_DEBUG */
 
@@ -2829,8 +2856,8 @@ static struct kmem_cache *kmem_cache_node;
  * slab on the node for this slabcache. There are no concurrent accesses
  * possible.
  *
- * Note that this function only works on the kmalloc_node_cache
- * when allocating for the kmalloc_node_cache. This is used for bootstrapping
+ * Note that this function only works on the kmem_cache_node
+ * when allocating for the kmem_cache_node. This is used for bootstrapping
  * memory on a fresh node that has no slab structures yet.
  */
 static void early_kmem_cache_node_alloc(int node)
@@ -3272,7 +3299,7 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 	if (page)
 		ptr = page_address(page);
 
-	kmemleak_alloc(ptr, size, 1, flags);
+	kmalloc_large_node_hook(ptr, size, flags);
 	return ptr;
 }
 
@@ -3336,7 +3363,7 @@ void kfree(const void *x)
 	page = virt_to_head_page(x);
 	if (unlikely(!PageSlab(page))) {
 		BUG_ON(!PageCompound(page));
-		kmemleak_free(x);
+		kfree_hook(x);
 		__free_memcg_kmem_pages(page, compound_order(page));
 		return;
 	}