Merge branch 'tracing/kmemtrace' into tracing/kmemtrace2

6 files changed, 124 insertions, 91 deletions

diff --git a/mm/Makefile b/mm/Makefile
index 3782eb66d4b3..c92e8af13206 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -28,6 +28,7 @@ obj-$(CONFIG_SLOB) += slob.o
 obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
 obj-$(CONFIG_SLAB) += slab.o
 obj-$(CONFIG_SLUB) += slub.o
+obj-$(CONFIG_FAILSLAB) += failslab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
diff --git a/mm/bounce.c b/mm/bounce.c
index bf0cf7c8387b..e590272fe7a8 100644
--- a/mm/bounce.c
+++ b/mm/bounce.c
@@ -198,8 +198,13 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 		/*
 		 * irk, bounce it
 		 */
-		if (!bio)
-			bio = bio_alloc(GFP_NOIO, (*bio_orig)->bi_vcnt);
+		if (!bio) {
+			unsigned int cnt = (*bio_orig)->bi_vcnt;
+
+			bio = bio_alloc(GFP_NOIO, cnt);
+			memset(bio->bi_io_vec, 0, cnt * sizeof(struct bio_vec));
+		}
+			
 
 		to = bio->bi_io_vec + i;
 
diff --git a/mm/failslab.c b/mm/failslab.c
new file mode 100644
index 000000000000..7c6ea6493f80
--- /dev/null
+++ b/mm/failslab.c
@@ -0,0 +1,59 @@
+#include <linux/fault-inject.h>
+
+static struct {
+	struct fault_attr attr;
+	u32 ignore_gfp_wait;
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+	struct dentry *ignore_gfp_wait_file;
+#endif
+} failslab = {
+	.attr = FAULT_ATTR_INITIALIZER,
+	.ignore_gfp_wait = 1,
+};
+
+bool should_failslab(size_t size, gfp_t gfpflags)
+{
+	if (gfpflags & __GFP_NOFAIL)
+		return false;
+
+        if (failslab.ignore_gfp_wait && (gfpflags & __GFP_WAIT))
+		return false;
+
+	return should_fail(&failslab.attr, size);
+}
+
+static int __init setup_failslab(char *str)
+{
+	return setup_fault_attr(&failslab.attr, str);
+}
+__setup("failslab=", setup_failslab);
+
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+
+static int __init failslab_debugfs_init(void)
+{
+	mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+	struct dentry *dir;
+	int err;
+
+	err = init_fault_attr_dentries(&failslab.attr, "failslab");
+	if (err)
+		return err;
+	dir = failslab.attr.dentries.dir;
+
+	failslab.ignore_gfp_wait_file =
+		debugfs_create_bool("ignore-gfp-wait", mode, dir,
+				      &failslab.ignore_gfp_wait);
+
+	if (!failslab.ignore_gfp_wait_file) {
+		err = -ENOMEM;
+		debugfs_remove(failslab.ignore_gfp_wait_file);
+		cleanup_fault_attr_dentries(&failslab.attr);
+	}
+
+	return err;
+}
+
+late_initcall(failslab_debugfs_init);
+
+#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
diff --git a/mm/memory.c b/mm/memory.c
index f01b7eed6e16..0a2010a9518c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3075,3 +3075,18 @@ void print_vma_addr(char *prefix, unsigned long ip)
 	}
 	up_read(&current->mm->mmap_sem);
 }
+
+#ifdef CONFIG_PROVE_LOCKING
+void might_fault(void)
+{
+	might_sleep();
+	/*
+	 * it would be nicer only to annotate paths which are not under
+	 * pagefault_disable, however that requires a larger audit and
+	 * providing helpers like get_user_atomic.
+	 */
+	if (!in_atomic() && current->mm)
+		might_lock_read(&current->mm->mmap_sem);
+}
+EXPORT_SYMBOL(might_fault);
+#endif
diff --git a/mm/slab.c b/mm/slab.c
index 7f72bb386a09..83075f36df7b 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2132,6 +2132,8 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep)
  *
  * @name must be valid until the cache is destroyed. This implies that
  * the module calling this has to destroy the cache before getting unloaded.
+ * Note that kmem_cache_name() is not guaranteed to return the same pointer,
+ * therefore applications must manage it themselves.
  *
  * The flags are
  *
@@ -2618,7 +2620,7 @@ static struct slab *alloc_slabmgmt(struct kmem_cache *cachep, void *objp,
 	if (OFF_SLAB(cachep)) {
 		/* Slab management obj is off-slab. */
 		slabp = kmem_cache_alloc_node(cachep->slabp_cache,
-					      local_flags & ~GFP_THISNODE, nodeid);
+					      local_flags, nodeid);
 		if (!slabp)
 			return NULL;
 	} else {
@@ -3006,7 +3008,7 @@ retry:
 		 * there must be at least one object available for
 		 * allocation.
 		 */
-		BUG_ON(slabp->inuse < 0 || slabp->inuse >= cachep->num);
+		BUG_ON(slabp->inuse >= cachep->num);
 
 		while (slabp->inuse < cachep->num && batchcount--) {
 			STATS_INC_ALLOCED(cachep);
@@ -3115,79 +3117,14 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
 #define cache_alloc_debugcheck_after(a,b,objp,d) (objp)
 #endif
 
-#ifdef CONFIG_FAILSLAB
-
-static struct failslab_attr {
-
-	struct fault_attr attr;
-
-	u32 ignore_gfp_wait;
-#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
-	struct dentry *ignore_gfp_wait_file;
-#endif
-
-} failslab = {
-	.attr = FAULT_ATTR_INITIALIZER,
-	.ignore_gfp_wait = 1,
-};
-
-static int __init setup_failslab(char *str)
-{
-	return setup_fault_attr(&failslab.attr, str);
-}
-__setup("failslab=", setup_failslab);
-
-static int should_failslab(struct kmem_cache *cachep, gfp_t flags)
+static bool slab_should_failslab(struct kmem_cache *cachep, gfp_t flags)
 {
 	if (cachep == &cache_cache)
-		return 0;
-	if (flags & __GFP_NOFAIL)
-		return 0;
-	if (failslab.ignore_gfp_wait && (flags & __GFP_WAIT))
-		return 0;
+		return false;
 
-	return should_fail(&failslab.attr, obj_size(cachep));
+	return should_failslab(obj_size(cachep), flags);
 }
 
-#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
-
-static int __init failslab_debugfs(void)
-{
-	mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
-	struct dentry *dir;
-	int err;
-
-	err = init_fault_attr_dentries(&failslab.attr, "failslab");
-	if (err)
-		return err;
-	dir = failslab.attr.dentries.dir;
-
-	failslab.ignore_gfp_wait_file =
-		debugfs_create_bool("ignore-gfp-wait", mode, dir,
-				      &failslab.ignore_gfp_wait);
-
-	if (!failslab.ignore_gfp_wait_file) {
-		err = -ENOMEM;
-		debugfs_remove(failslab.ignore_gfp_wait_file);
-		cleanup_fault_attr_dentries(&failslab.attr);
-	}
-
-	return err;
-}
-
-late_initcall(failslab_debugfs);
-
-#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
-
-#else /* CONFIG_FAILSLAB */
-
-static inline int should_failslab(struct kmem_cache *cachep, gfp_t flags)
-{
-	return 0;
-}
-
-#endif /* CONFIG_FAILSLAB */
-
 static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 {
 	void *objp;
@@ -3390,7 +3327,7 @@ __cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
 	unsigned long save_flags;
 	void *ptr;
 
-	if (should_failslab(cachep, flags))
+	if (slab_should_failslab(cachep, flags))
 		return NULL;
 
 	cache_alloc_debugcheck_before(cachep, flags);
@@ -3466,7 +3403,7 @@ __cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
 	unsigned long save_flags;
 	void *objp;
 
-	if (should_failslab(cachep, flags))
+	if (slab_should_failslab(cachep, flags))
 		return NULL;
 
 	cache_alloc_debugcheck_before(cachep, flags);
diff --git a/mm/slub.c b/mm/slub.c
index 7bf8cf8ec082..4fac7bbb029a 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -25,6 +25,7 @@
 #include <linux/kallsyms.h>
 #include <linux/memory.h>
 #include <linux/math64.h>
+#include <linux/fault-inject.h>
 
 /*
  * Lock order:
@@ -154,6 +155,10 @@
 #define ARCH_SLAB_MINALIGN __alignof__(unsigned long long)
 #endif
 
+#define OO_SHIFT	16
+#define OO_MASK		((1 << OO_SHIFT) - 1)
+#define MAX_OBJS_PER_PAGE	65535 /* since page.objects is u16 */
+
 /* Internal SLUB flags */
 #define __OBJECT_POISON		0x80000000 /* Poison object */
 #define __SYSFS_ADD_DEFERRED	0x40000000 /* Not yet visible via sysfs */
@@ -291,7 +296,7 @@ static inline struct kmem_cache_order_objects oo_make(int order,
 						unsigned long size)
 {
 	struct kmem_cache_order_objects x = {
-		(order << 16) + (PAGE_SIZE << order) / size
+		(order << OO_SHIFT) + (PAGE_SIZE << order) / size
 	};
 
 	return x;
@@ -299,12 +304,12 @@ static inline struct kmem_cache_order_objects oo_make(int order,
 
 static inline int oo_order(struct kmem_cache_order_objects x)
 {
-	return x.x >> 16;
+	return x.x >> OO_SHIFT;
 }
 
 static inline int oo_objects(struct kmem_cache_order_objects x)
 {
-	return x.x & ((1 << 16) - 1);
+	return x.x & OO_MASK;
 }
 
 #ifdef CONFIG_SLUB_DEBUG
@@ -693,7 +698,7 @@ static int check_object(struct kmem_cache *s, struct page *page,
 	if (!check_valid_pointer(s, page, get_freepointer(s, p))) {
 		object_err(s, page, p, "Freepointer corrupt");
 		/*
-		 * No choice but to zap it and thus loose the remainder
+		 * No choice but to zap it and thus lose the remainder
 		 * of the free objects in this slab. May cause
 		 * another error because the object count is now wrong.
 		 */
@@ -765,8 +770,8 @@ static int on_freelist(struct kmem_cache *s, struct page *page, void *search)
 	}
 
 	max_objects = (PAGE_SIZE << compound_order(page)) / s->size;
-	if (max_objects > 65535)
-		max_objects = 65535;
+	if (max_objects > MAX_OBJS_PER_PAGE)
+		max_objects = MAX_OBJS_PER_PAGE;
 
 	if (page->objects != max_objects) {
 		slab_err(s, page, "Wrong number of objects. Found %d but "
@@ -1592,6 +1597,11 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
 	unsigned long flags;
 	unsigned int objsize;
 
+	might_sleep_if(gfpflags & __GFP_WAIT);
+
+	if (should_failslab(s->objsize, gfpflags))
+		return NULL;
+
 	local_irq_save(flags);
 	c = get_cpu_slab(s, smp_processor_id());
 	objsize = c->objsize;
@@ -1766,7 +1776,7 @@ void kmem_cache_free(struct kmem_cache *s, void *x)
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
-/* Figure out on which slab object the object resides */
+/* Figure out on which slab page the object resides */
 static struct page *get_object_page(const void *x)
 {
 	struct page *page = virt_to_head_page(x);
@@ -1838,8 +1848,8 @@ static inline int slab_order(int size, int min_objects,
 	int rem;
 	int min_order = slub_min_order;
 
-	if ((PAGE_SIZE << min_order) / size > 65535)
-		return get_order(size * 65535) - 1;
+	if ((PAGE_SIZE << min_order) / size > MAX_OBJS_PER_PAGE)
+		return get_order(size * MAX_OBJS_PER_PAGE) - 1;
 
 	for (order = max(min_order,
 				fls(min_objects * size - 1) - PAGE_SHIFT);
@@ -2104,8 +2114,7 @@ static inline int alloc_kmem_cache_cpus(struct kmem_cache *s, gfp_t flags)
  * when allocating for the kmalloc_node_cache. This is used for bootstrapping
  * memory on a fresh node that has no slab structures yet.
  */
-static struct kmem_cache_node *early_kmem_cache_node_alloc(gfp_t gfpflags,
-							   int node)
+static void early_kmem_cache_node_alloc(gfp_t gfpflags, int node)
 {
 	struct page *page;
 	struct kmem_cache_node *n;
@@ -2143,7 +2152,6 @@ static struct kmem_cache_node *early_kmem_cache_node_alloc(gfp_t gfpflags,
 	local_irq_save(flags);
 	add_partial(n, page, 0);
 	local_irq_restore(flags);
-	return n;
 }
 
 static void free_kmem_cache_nodes(struct kmem_cache *s)
@@ -2175,8 +2183,7 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
 			n = &s->local_node;
 		else {
 			if (slab_state == DOWN) {
-				n = early_kmem_cache_node_alloc(gfpflags,
-								node);
+				early_kmem_cache_node_alloc(gfpflags, node);
 				continue;
 			}
 			n = kmem_cache_alloc_node(kmalloc_caches,
@@ -3176,8 +3183,12 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 		s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *)));
 		up_write(&slub_lock);
 
-		if (sysfs_slab_alias(s, name))
+		if (sysfs_slab_alias(s, name)) {
+			down_write(&slub_lock);
+			s->refcount--;
+			up_write(&slub_lock);
 			goto err;
+		}
 		return s;
 	}
 
@@ -3187,8 +3198,13 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 				size, align, flags, ctor)) {
 			list_add(&s->list, &slab_caches);
 			up_write(&slub_lock);
-			if (sysfs_slab_add(s))
+			if (sysfs_slab_add(s)) {
+				down_write(&slub_lock);
+				list_del(&s->list);
+				up_write(&slub_lock);
+				kfree(s);
 				goto err;
+			}
 			return s;
 		}
 		kfree(s);
@@ -4412,7 +4428,7 @@ static void sysfs_slab_remove(struct kmem_cache *s)
 
 /*
  * Need to buffer aliases during bootup until sysfs becomes
- * available lest we loose that information.
+ * available lest we lose that information.
  */
 struct saved_alias {
 	struct kmem_cache *s;