Merge branch 'slab/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux

Pull slab update from Pekka Enberg:
 "Highlights:

  - Fix for boot-time problems on some architectures due to
    init_lock_keys() not respecting kmalloc_caches boundaries
    (Christoph Lameter)

  - CONFIG_SLUB_CPU_PARTIAL requested by RT folks (Joonsoo Kim)

  - Fix for excessive slab freelist draining (Wanpeng Li)

  - SLUB and SLOB cleanups and fixes (various people)"

I ended up editing the branch, and this avoids two commits at the end
that were immediately reverted, and I instead just applied the oneliner
fix in between myself.

* 'slab/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux
  slub: Check for page NULL before doing the node_match check
  mm/slab: Give s_next and s_stop slab-specific names
  slob: Check for NULL pointer before calling ctor()
  slub: Make cpu partial slab support configurable
  slab: add kmalloc() to kernel API documentation
  slab: fix init_lock_keys
  slob: use DIV_ROUND_UP where possible
  slub: do not put a slab to cpu partial list when cpu_partial is 0
  mm/slub: Use node_nr_slabs and node_nr_objs in get_slabinfo
  mm/slub: Drop unnecessary nr_partials
  mm/slab: Fix /proc/slabinfo unwriteable for slab
  mm/slab: Sharing s_next and s_stop between slab and slub
  mm/slab: Fix drain freelist excessively
  slob: Rework #ifdeffery in slab.h
  mm, slab: moved kmem_cache_alloc_node comment to correct place

8 files changed, 121 insertions, 69 deletions

diff --git a/include/linux/slab.h b/include/linux/slab.h
index 0c621752caa6..6c5cc0ea8713 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -169,11 +169,7 @@ struct kmem_cache {
 	struct list_head list;	/* List of all slab caches on the system */
 };
 
-#define KMALLOC_MAX_SIZE (1UL << 30)
-
-#include <linux/slob_def.h>
-
-#else /* CONFIG_SLOB */
+#endif /* CONFIG_SLOB */
 
 /*
  * Kmalloc array related definitions
@@ -195,7 +191,9 @@ struct kmem_cache {
 #ifndef KMALLOC_SHIFT_LOW
 #define KMALLOC_SHIFT_LOW	5
 #endif
-#else
+#endif
+
+#ifdef CONFIG_SLUB
 /*
  * SLUB allocates up to order 2 pages directly and otherwise
  * passes the request to the page allocator.
@@ -207,6 +205,19 @@ struct kmem_cache {
 #endif
 #endif
 
+#ifdef CONFIG_SLOB
+/*
+ * SLOB passes all page size and larger requests to the page allocator.
+ * No kmalloc array is necessary since objects of different sizes can
+ * be allocated from the same page.
+ */
+#define KMALLOC_SHIFT_MAX	30
+#define KMALLOC_SHIFT_HIGH	PAGE_SHIFT
+#ifndef KMALLOC_SHIFT_LOW
+#define KMALLOC_SHIFT_LOW	3
+#endif
+#endif
+
 /* Maximum allocatable size */
 #define KMALLOC_MAX_SIZE	(1UL << KMALLOC_SHIFT_MAX)
 /* Maximum size for which we actually use a slab cache */
@@ -221,6 +232,7 @@ struct kmem_cache {
 #define KMALLOC_MIN_SIZE (1 << KMALLOC_SHIFT_LOW)
 #endif
 
+#ifndef CONFIG_SLOB
 extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1];
 #ifdef CONFIG_ZONE_DMA
 extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1];
@@ -275,13 +287,18 @@ static __always_inline int kmalloc_index(size_t size)
 	/* Will never be reached. Needed because the compiler may complain */
 	return -1;
 }
+#endif /* !CONFIG_SLOB */
 
 #ifdef CONFIG_SLAB
 #include <linux/slab_def.h>
-#elif defined(CONFIG_SLUB)
+#endif
+
+#ifdef CONFIG_SLUB
 #include <linux/slub_def.h>
-#else
-#error "Unknown slab allocator"
+#endif
+
+#ifdef CONFIG_SLOB
+#include <linux/slob_def.h>
 #endif
 
 /*
@@ -291,6 +308,7 @@ static __always_inline int kmalloc_index(size_t size)
  */
 static __always_inline int kmalloc_size(int n)
 {
+#ifndef CONFIG_SLOB
 	if (n > 2)
 		return 1 << n;
 
@@ -299,10 +317,9 @@ static __always_inline int kmalloc_size(int n)
 
 	if (n == 2 && KMALLOC_MIN_SIZE <= 64)
 		return 192;
-
+#endif
 	return 0;
 }
-#endif /* !CONFIG_SLOB */
 
 /*
  * Setting ARCH_SLAB_MINALIGN in arch headers allows a different alignment.
@@ -356,9 +373,8 @@ int cache_show(struct kmem_cache *s, struct seq_file *m);
 void print_slabinfo_header(struct seq_file *m);
 
 /**
- * kmalloc_array - allocate memory for an array.
- * @n: number of elements.
- * @size: element size.
+ * kmalloc - allocate memory
+ * @size: how many bytes of memory are required.
  * @flags: the type of memory to allocate.
  *
  * The @flags argument may be one of:
@@ -405,6 +421,17 @@ void print_slabinfo_header(struct seq_file *m);
  * There are other flags available as well, but these are not intended
  * for general use, and so are not documented here. For a full list of
  * potential flags, always refer to linux/gfp.h.
+ *
+ * kmalloc is the normal method of allocating memory
+ * in the kernel.
+ */
+static __always_inline void *kmalloc(size_t size, gfp_t flags);
+
+/**
+ * kmalloc_array - allocate memory for an array.
+ * @n: number of elements.
+ * @size: element size.
+ * @flags: the type of memory to allocate (see kmalloc).
  */
 static inline void *kmalloc_array(size_t n, size_t size, gfp_t flags)
 {
@@ -428,7 +455,7 @@ static inline void *kcalloc(size_t n, size_t size, gfp_t flags)
 /**
  * kmalloc_node - allocate memory from a specific node
  * @size: how many bytes of memory are required.
- * @flags: the type of memory to allocate (see kcalloc).
+ * @flags: the type of memory to allocate (see kmalloc).
  * @node: node to allocate from.
  *
  * kmalloc() for non-local nodes, used to allocate from a specific node
diff --git a/include/linux/slob_def.h b/include/linux/slob_def.h
index f28e14a12e3f..095a5a4a8516 100644
--- a/include/linux/slob_def.h
+++ b/include/linux/slob_def.h
@@ -18,14 +18,6 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 	return __kmalloc_node(size, flags, node);
 }
 
-/**
- * kmalloc - allocate memory
- * @size: how many bytes of memory are required.
- * @flags: the type of memory to allocate (see kcalloc).
- *
- * kmalloc is the normal method of allocating memory
- * in the kernel.
- */
 static __always_inline void *kmalloc(size_t size, gfp_t flags)
 {
 	return __kmalloc_node(size, flags, NUMA_NO_NODE);
diff --git a/init/Kconfig b/init/Kconfig
index 54d3fa5ae723..247084be0590 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1596,6 +1596,17 @@ config SLOB
 
 endchoice
 
+config SLUB_CPU_PARTIAL
+	default y
+	depends on SLUB
+	bool "SLUB per cpu partial cache"
+	help
+	  Per cpu partial caches accellerate objects allocation and freeing
+	  that is local to a processor at the price of more indeterminism
+	  in the latency of the free. On overflow these caches will be cleared
+	  which requires the taking of locks that may cause latency spikes.
+	  Typically one would choose no for a realtime system.
+
 config MMAP_ALLOW_UNINITIALIZED
 	bool "Allow mmapped anonymous memory to be uninitialized"
 	depends on EXPERT && !MMU
diff --git a/mm/slab.c b/mm/slab.c
index 8ccd296c6d9c..35cb0c861508 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -565,7 +565,7 @@ static void init_node_lock_keys(int q)
 	if (slab_state < UP)
 		return;
 
-	for (i = 1; i < PAGE_SHIFT + MAX_ORDER; i++) {
+	for (i = 1; i <= KMALLOC_SHIFT_HIGH; i++) {
 		struct kmem_cache_node *n;
 		struct kmem_cache *cache = kmalloc_caches[i];
 
@@ -1180,6 +1180,12 @@ static int init_cache_node_node(int node)
 	return 0;
 }
 
+static inline int slabs_tofree(struct kmem_cache *cachep,
+						struct kmem_cache_node *n)
+{
+	return (n->free_objects + cachep->num - 1) / cachep->num;
+}
+
 static void __cpuinit cpuup_canceled(long cpu)
 {
 	struct kmem_cache *cachep;
@@ -1241,7 +1247,7 @@ free_array_cache:
 		n = cachep->node[node];
 		if (!n)
 			continue;
-		drain_freelist(cachep, n, n->free_objects);
+		drain_freelist(cachep, n, slabs_tofree(cachep, n));
 	}
 }
 
@@ -1408,7 +1414,7 @@ static int __meminit drain_cache_node_node(int node)
 		if (!n)
 			continue;
 
-		drain_freelist(cachep, n, n->free_objects);
+		drain_freelist(cachep, n, slabs_tofree(cachep, n));
 
 		if (!list_empty(&n->slabs_full) ||
 		    !list_empty(&n->slabs_partial)) {
@@ -2532,7 +2538,7 @@ static int __cache_shrink(struct kmem_cache *cachep)
 		if (!n)
 			continue;
 
-		drain_freelist(cachep, n, n->free_objects);
+		drain_freelist(cachep, n, slabs_tofree(cachep, n));
 
 		ret += !list_empty(&n->slabs_full) ||
 			!list_empty(&n->slabs_partial);
@@ -3338,18 +3344,6 @@ done:
 	return obj;
 }
 
-/**
- * kmem_cache_alloc_node - Allocate an object on the specified node
- * @cachep: The cache to allocate from.
- * @flags: See kmalloc().
- * @nodeid: node number of the target node.
- * @caller: return address of caller, used for debug information
- *
- * Identical to kmem_cache_alloc but it will allocate memory on the given
- * node, which can improve the performance for cpu bound structures.
- *
- * Fallback to other node is possible if __GFP_THISNODE is not set.
- */
 static __always_inline void *
 slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 		   unsigned long caller)
@@ -3643,6 +3637,17 @@ EXPORT_SYMBOL(kmem_cache_alloc_trace);
 #endif
 
 #ifdef CONFIG_NUMA
+/**
+ * kmem_cache_alloc_node - Allocate an object on the specified node
+ * @cachep: The cache to allocate from.
+ * @flags: See kmalloc().
+ * @nodeid: node number of the target node.
+ *
+ * Identical to kmem_cache_alloc but it will allocate memory on the given
+ * node, which can improve the performance for cpu bound structures.
+ *
+ * Fallback to other node is possible if __GFP_THISNODE is not set.
+ */
 void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 {
 	void *ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_);
@@ -4431,20 +4436,10 @@ static int leaks_show(struct seq_file *m, void *p)
 	return 0;
 }
 
-static void *s_next(struct seq_file *m, void *p, loff_t *pos)
-{
-	return seq_list_next(p, &slab_caches, pos);
-}
-
-static void s_stop(struct seq_file *m, void *p)
-{
-	mutex_unlock(&slab_mutex);
-}
-
 static const struct seq_operations slabstats_op = {
 	.start = leaks_start,
-	.next = s_next,
-	.stop = s_stop,
+	.next = slab_next,
+	.stop = slab_stop,
 	.show = leaks_show,
 };
 
diff --git a/mm/slab.h b/mm/slab.h
index f96b49e4704e..620ceeddbe1a 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -271,3 +271,6 @@ struct kmem_cache_node {
 #endif
 
 };
+
+void *slab_next(struct seq_file *m, void *p, loff_t *pos);
+void slab_stop(struct seq_file *m, void *p);
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 2d414508e9ec..538bade6df7d 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -497,6 +497,13 @@ void __init create_kmalloc_caches(unsigned long flags)
 
 
 #ifdef CONFIG_SLABINFO
+
+#ifdef CONFIG_SLAB
+#define SLABINFO_RIGHTS (S_IWUSR | S_IRUSR)
+#else
+#define SLABINFO_RIGHTS S_IRUSR
+#endif
+
 void print_slabinfo_header(struct seq_file *m)
 {
 	/*
@@ -531,12 +538,12 @@ static void *s_start(struct seq_file *m, loff_t *pos)
 	return seq_list_start(&slab_caches, *pos);
 }
 
-static void *s_next(struct seq_file *m, void *p, loff_t *pos)
+void *slab_next(struct seq_file *m, void *p, loff_t *pos)
 {
 	return seq_list_next(p, &slab_caches, pos);
 }
 
-static void s_stop(struct seq_file *m, void *p)
+void slab_stop(struct seq_file *m, void *p)
 {
 	mutex_unlock(&slab_mutex);
 }
@@ -613,8 +620,8 @@ static int s_show(struct seq_file *m, void *p)
  */
 static const struct seq_operations slabinfo_op = {
 	.start = s_start,
-	.next = s_next,
-	.stop = s_stop,
+	.next = slab_next,
+	.stop = slab_stop,
 	.show = s_show,
 };
 
@@ -633,7 +640,8 @@ static const struct file_operations proc_slabinfo_operations = {
 
 static int __init slab_proc_init(void)
 {
-	proc_create("slabinfo", S_IRUSR, NULL, &proc_slabinfo_operations);
+	proc_create("slabinfo", SLABINFO_RIGHTS, NULL,
+						&proc_slabinfo_operations);
 	return 0;
 }
 module_init(slab_proc_init);
diff --git a/mm/slob.c b/mm/slob.c
index eeed4a05a2ef..91bd3f2dd2f0 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -122,7 +122,7 @@ static inline void clear_slob_page_free(struct page *sp)
 }
 
 #define SLOB_UNIT sizeof(slob_t)
-#define SLOB_UNITS(size) (((size) + SLOB_UNIT - 1)/SLOB_UNIT)
+#define SLOB_UNITS(size) DIV_ROUND_UP(size, SLOB_UNIT)
 
 /*
  * struct slob_rcu is inserted at the tail of allocated slob blocks, which
@@ -554,7 +554,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
 					    flags, node);
 	}
 
-	if (c->ctor)
+	if (b && c->ctor)
 		c->ctor(b);
 
 	kmemleak_alloc_recursive(b, c->size, 1, c->flags, flags);
diff --git a/mm/slub.c b/mm/slub.c
index 57707f01bcfb..3b482c863002 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -123,6 +123,15 @@ static inline int kmem_cache_debug(struct kmem_cache *s)
 #endif
 }
 
+static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
+{
+#ifdef CONFIG_SLUB_CPU_PARTIAL
+	return !kmem_cache_debug(s);
+#else
+	return false;
+#endif
+}
+
 /*
  * Issues still to be resolved:
  *
@@ -1573,7 +1582,8 @@ static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
 			put_cpu_partial(s, page, 0);
 			stat(s, CPU_PARTIAL_NODE);
 		}
-		if (kmem_cache_debug(s) || available > s->cpu_partial / 2)
+		if (!kmem_cache_has_cpu_partial(s)
+			|| available > s->cpu_partial / 2)
 			break;
 
 	}
@@ -1884,6 +1894,7 @@ redo:
 static void unfreeze_partials(struct kmem_cache *s,
 		struct kmem_cache_cpu *c)
 {
+#ifdef CONFIG_SLUB_CPU_PARTIAL
 	struct kmem_cache_node *n = NULL, *n2 = NULL;
 	struct page *page, *discard_page = NULL;
 
@@ -1938,6 +1949,7 @@ static void unfreeze_partials(struct kmem_cache *s,
 		discard_slab(s, page);
 		stat(s, FREE_SLAB);
 	}
+#endif
 }
 
 /*
@@ -1951,10 +1963,14 @@ static void unfreeze_partials(struct kmem_cache *s,
  */
 static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 {
+#ifdef CONFIG_SLUB_CPU_PARTIAL
 	struct page *oldpage;
 	int pages;
 	int pobjects;
 
+	if (!s->cpu_partial)
+		return;
+
 	do {
 		pages = 0;
 		pobjects = 0;
@@ -1987,6 +2003,7 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
 		page->next = oldpage;
 
 	} while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage);
+#endif
 }
 
 static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
@@ -2358,7 +2375,7 @@ redo:
 
 	object = c->freelist;
 	page = c->page;
-	if (unlikely(!object || !node_match(page, node)))
+	if (unlikely(!object || !page || !node_match(page, node)))
 		object = __slab_alloc(s, gfpflags, node, addr, c);
 
 	else {
@@ -2495,7 +2512,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 		new.inuse--;
 		if ((!new.inuse || !prior) && !was_frozen) {
 
-			if (!kmem_cache_debug(s) && !prior)
+			if (kmem_cache_has_cpu_partial(s) && !prior)
 
 				/*
 				 * Slab was on no list before and will be partially empty
@@ -2550,8 +2567,9 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
 	 * Objects left in the slab. If it was not on the partial list before
 	 * then add it.
 	 */
-	if (kmem_cache_debug(s) && unlikely(!prior)) {
-		remove_full(s, page);
+	if (!kmem_cache_has_cpu_partial(s) && unlikely(!prior)) {
+		if (kmem_cache_debug(s))
+			remove_full(s, page);
 		add_partial(n, page, DEACTIVATE_TO_TAIL);
 		stat(s, FREE_ADD_PARTIAL);
 	}
@@ -3059,7 +3077,7 @@ static int kmem_cache_open(struct kmem_cache *s, unsigned long flags)
 	 *    per node list when we run out of per cpu objects. We only fetch 50%
 	 *    to keep some capacity around for frees.
 	 */
-	if (kmem_cache_debug(s))
+	if (!kmem_cache_has_cpu_partial(s))
 		s->cpu_partial = 0;
 	else if (s->size >= PAGE_SIZE)
 		s->cpu_partial = 2;
@@ -4456,7 +4474,7 @@ static ssize_t cpu_partial_store(struct kmem_cache *s, const char *buf,
 	err = strict_strtoul(buf, 10, &objects);
 	if (err)
 		return err;
-	if (objects && kmem_cache_debug(s))
+	if (objects && !kmem_cache_has_cpu_partial(s))
 		return -EINVAL;
 
 	s->cpu_partial = objects;
@@ -5269,7 +5287,6 @@ __initcall(slab_sysfs_init);
 #ifdef CONFIG_SLABINFO
 void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo)
 {
-	unsigned long nr_partials = 0;
 	unsigned long nr_slabs = 0;
 	unsigned long nr_objs = 0;
 	unsigned long nr_free = 0;
@@ -5281,9 +5298,8 @@ void get_slabinfo(struct kmem_cache *s, struct slabinfo *sinfo)
 		if (!n)
 			continue;
 
-		nr_partials += n->nr_partial;
-		nr_slabs += atomic_long_read(&n->nr_slabs);
-		nr_objs += atomic_long_read(&n->total_objects);
+		nr_slabs += node_nr_slabs(n);
+		nr_objs += node_nr_objs(n);
 		nr_free += count_partial(n, count_free);
 	}