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

* 'slab/for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/penberg/linux:
  slub: disallow changing cpu_partial from userspace for debug caches
  slub: add missed accounting
  slub: Extract get_freelist from __slab_alloc
  slub: Switch per cpu partial page support off for debugging
  slub: fix a possible memleak in __slab_alloc()
  slub: fix slub_max_order Documentation
  slub: add missed accounting
  slab: add taint flag outputting to debug paths.
  slub: add taint flag outputting to debug paths
  slab: introduce slab_max_order kernel parameter
  slab: rename slab_break_gfp_order to slab_max_order

4 files changed, 82 insertions, 42 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index c92b1532f05a..a8d389d72405 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2395,6 +2395,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	slram=		[HW,MTD]
 
+	slab_max_order=	[MM, SLAB]
+			Determines the maximum allowed order for slabs.
+			A high setting may cause OOMs due to memory
+			fragmentation.  Defaults to 1 for systems with
+			more than 32MB of RAM, 0 otherwise.
+
 	slub_debug[=options[,slabs]]	[MM, SLUB]
 			Enabling slub_debug allows one to determine the
 			culprit if slab objects become corrupted. Enabling
diff --git a/Documentation/vm/slub.txt b/Documentation/vm/slub.txt
index f464f47bc60d..2acdda9601b0 100644
--- a/Documentation/vm/slub.txt
+++ b/Documentation/vm/slub.txt
@@ -117,7 +117,7 @@ can be influenced by kernel parameters:
 
 slub_min_objects=x		(default 4)
 slub_min_order=x		(default 0)
-slub_max_order=x		(default 1)
+slub_max_order=x		(default 3 (PAGE_ALLOC_COSTLY_ORDER))
 
 slub_min_objects allows to specify how many objects must at least fit
 into one slab in order for the allocation order to be acceptable.
diff --git a/mm/slab.c b/mm/slab.c
index 2acfa0d90943..f0bd7857ab3b 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -481,11 +481,13 @@ EXPORT_SYMBOL(slab_buffer_size);
 #endif
 
 /*
- * Do not go above this order unless 0 objects fit into the slab.
+ * Do not go above this order unless 0 objects fit into the slab or
+ * overridden on the command line.
  */
-#define	BREAK_GFP_ORDER_HI	1
-#define	BREAK_GFP_ORDER_LO	0
-static int slab_break_gfp_order = BREAK_GFP_ORDER_LO;
+#define	SLAB_MAX_ORDER_HI	1
+#define	SLAB_MAX_ORDER_LO	0
+static int slab_max_order = SLAB_MAX_ORDER_LO;
+static bool slab_max_order_set __initdata;
 
 /*
  * Functions for storing/retrieving the cachep and or slab from the page
@@ -854,6 +856,17 @@ static int __init noaliencache_setup(char *s)
 }
 __setup("noaliencache", noaliencache_setup);
 
+static int __init slab_max_order_setup(char *str)
+{
+	get_option(&str, &slab_max_order);
+	slab_max_order = slab_max_order < 0 ? 0 :
+				min(slab_max_order, MAX_ORDER - 1);
+	slab_max_order_set = true;
+
+	return 1;
+}
+__setup("slab_max_order=", slab_max_order_setup);
+
 #ifdef CONFIG_NUMA
 /*
  * Special reaping functions for NUMA systems called from cache_reap().
@@ -1502,10 +1515,11 @@ void __init kmem_cache_init(void)
 
 	/*
 	 * Fragmentation resistance on low memory - only use bigger
-	 * page orders on machines with more than 32MB of memory.
+	 * page orders on machines with more than 32MB of memory if
+	 * not overridden on the command line.
 	 */
-	if (totalram_pages > (32 << 20) >> PAGE_SHIFT)
-		slab_break_gfp_order = BREAK_GFP_ORDER_HI;
+	if (!slab_max_order_set && totalram_pages > (32 << 20) >> PAGE_SHIFT)
+		slab_max_order = SLAB_MAX_ORDER_HI;
 
 	/* Bootstrap is tricky, because several objects are allocated
 	 * from caches that do not exist yet:
@@ -1932,8 +1946,8 @@ static void check_poison_obj(struct kmem_cache *cachep, void *objp)
 			/* Print header */
 			if (lines == 0) {
 				printk(KERN_ERR
-					"Slab corruption: %s start=%p, len=%d\n",
-					cachep->name, realobj, size);
+					"Slab corruption (%s): %s start=%p, len=%d\n",
+					print_tainted(), cachep->name, realobj, size);
 				print_objinfo(cachep, objp, 0);
 			}
 			/* Hexdump the affected line */
@@ -2117,7 +2131,7 @@ static size_t calculate_slab_order(struct kmem_cache *cachep,
 		 * Large number of objects is good, but very large slabs are
 		 * currently bad for the gfp()s.
 		 */
-		if (gfporder >= slab_break_gfp_order)
+		if (gfporder >= slab_max_order)
 			break;
 
 		/*
@@ -3042,8 +3056,9 @@ static void check_slabp(struct kmem_cache *cachep, struct slab *slabp)
 	if (entries != cachep->num - slabp->inuse) {
 bad:
 		printk(KERN_ERR "slab: Internal list corruption detected in "
-				"cache '%s'(%d), slabp %p(%d). Hexdump:\n",
-			cachep->name, cachep->num, slabp, slabp->inuse);
+			"cache '%s'(%d), slabp %p(%d). Tainted(%s). Hexdump:\n",
+			cachep->name, cachep->num, slabp, slabp->inuse,
+			print_tainted());
 		print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1, slabp,
 			sizeof(*slabp) + cachep->num * sizeof(kmem_bufctl_t),
 			1);
diff --git a/mm/slub.c b/mm/slub.c
index d99acbf14e01..5d37b5e44140 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -570,7 +570,7 @@ static void slab_bug(struct kmem_cache *s, char *fmt, ...)
 	va_end(args);
 	printk(KERN_ERR "========================================"
 			"=====================================\n");
-	printk(KERN_ERR "BUG %s: %s\n", s->name, buf);
+	printk(KERN_ERR "BUG %s (%s): %s\n", s->name, print_tainted(), buf);
 	printk(KERN_ERR "----------------------------------------"
 			"-------------------------------------\n\n");
 }
@@ -1901,11 +1901,14 @@ static void unfreeze_partials(struct kmem_cache *s)
 			}
 
 			if (l != m) {
-				if (l == M_PARTIAL)
+				if (l == M_PARTIAL) {
 					remove_partial(n, page);
-				else
+					stat(s, FREE_REMOVE_PARTIAL);
+				} else {
 					add_partial(n, page,
 						DEACTIVATE_TO_TAIL);
+					stat(s, FREE_ADD_PARTIAL);
+				}
 
 				l = m;
 			}
@@ -2124,6 +2127,37 @@ static inline void *new_slab_objects(struct kmem_cache *s, gfp_t flags,
 }
 
 /*
+ * Check the page->freelist of a page and either transfer the freelist to the per cpu freelist
+ * or deactivate the page.
+ *
+ * The page is still frozen if the return value is not NULL.
+ *
+ * If this function returns NULL then the page has been unfrozen.
+ */
+static inline void *get_freelist(struct kmem_cache *s, struct page *page)
+{
+	struct page new;
+	unsigned long counters;
+	void *freelist;
+
+	do {
+		freelist = page->freelist;
+		counters = page->counters;
+		new.counters = counters;
+		VM_BUG_ON(!new.frozen);
+
+		new.inuse = page->objects;
+		new.frozen = freelist != NULL;
+
+	} while (!cmpxchg_double_slab(s, page,
+		freelist, counters,
+		NULL, new.counters,
+		"get_freelist"));
+
+	return freelist;
+}
+
+/*
  * Slow path. The lockless freelist is empty or we need to perform
  * debugging duties.
  *
@@ -2144,8 +2178,6 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node,
 {
 	void **object;
 	unsigned long flags;
-	struct page new;
-	unsigned long counters;
 
 	local_irq_save(flags);
 #ifdef CONFIG_PREEMPT
@@ -2166,31 +2198,14 @@ redo:
 		goto new_slab;
 	}
 
-	stat(s, ALLOC_SLOWPATH);
-
-	do {
-		object = c->page->freelist;
-		counters = c->page->counters;
-		new.counters = counters;
-		VM_BUG_ON(!new.frozen);
-
-		/*
-		 * If there is no object left then we use this loop to
-		 * deactivate the slab which is simple since no objects
-		 * are left in the slab and therefore we do not need to
-		 * put the page back onto the partial list.
-		 *
-		 * If there are objects left then we retrieve them
-		 * and use them to refill the per cpu queue.
-		 */
+	/* must check again c->freelist in case of cpu migration or IRQ */
+	object = c->freelist;
+	if (object)
+		goto load_freelist;
 
-		new.inuse = c->page->objects;
-		new.frozen = object != NULL;
+	stat(s, ALLOC_SLOWPATH);
 
-	} while (!__cmpxchg_double_slab(s, c->page,
-			object, counters,
-			NULL, new.counters,
-			"__slab_alloc"));
+	object = get_freelist(s, c->page);
 
 	if (!object) {
 		c->page = NULL;
@@ -3028,7 +3043,9 @@ static int kmem_cache_open(struct kmem_cache *s,
 	 *    per node list when we run out of per cpu objects. We only fetch 50%
 	 *    to keep some capacity around for frees.
 	 */
-	if (s->size >= PAGE_SIZE)
+	if (kmem_cache_debug(s))
+		s->cpu_partial = 0;
+	else if (s->size >= PAGE_SIZE)
 		s->cpu_partial = 2;
 	else if (s->size >= 1024)
 		s->cpu_partial = 6;
@@ -4637,6 +4654,8 @@ 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))
+		return -EINVAL;
 
 	s->cpu_partial = objects;
 	flush_all(s);