Merge branch 'akpm' (second patch-bomb from Andrew)

Merge second patchbomb from Andrew Morton:
 - the rest of MM
 - misc fs fixes
 - add execveat() syscall
 - new ratelimit feature for fault-injection
 - decompressor updates
 - ipc/ updates
 - fallocate feature creep
 - fsnotify cleanups
 - a few other misc things

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (99 commits)
  cgroups: Documentation: fix trivial typos and wrong paragraph numberings
  parisc: percpu: update comments referring to __get_cpu_var
  percpu: update local_ops.txt to reflect this_cpu operations
  percpu: remove __get_cpu_var and __raw_get_cpu_var macros
  fsnotify: remove destroy_list from fsnotify_mark
  fsnotify: unify inode and mount marks handling
  fallocate: create FAN_MODIFY and IN_MODIFY events
  mm/cma: make kmemleak ignore CMA regions
  slub: fix cpuset check in get_any_partial
  slab: fix cpuset check in fallback_alloc
  shmdt: use i_size_read() instead of ->i_size
  ipc/shm.c: fix overly aggressive shmdt() when calls span multiple segments
  ipc/msg: increase MSGMNI, remove scaling
  ipc/sem.c: increase SEMMSL, SEMMNI, SEMOPM
  ipc/sem.c: change memory barrier in sem_lock() to smp_rmb()
  lib/decompress.c: consistency of compress formats for kernel image
  decompress_bunzip2: off by one in get_next_block()
  usr/Kconfig: make initrd compression algorithm selection not expert
  fault-inject: add ratelimit option
  ratelimit: add initialization macro
  ...

1 files changed, 134 insertions, 46 deletions

diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 839a48c..4d0a063 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -155,8 +155,6 @@
  *  (reason above)
  */
 #define ZS_SIZE_CLASS_DELTA	(PAGE_SIZE >> 8)
-#define ZS_SIZE_CLASSES		((ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / \
-					ZS_SIZE_CLASS_DELTA + 1)
 
 /*
  * We do not maintain any list for completely empty or full pages
@@ -171,6 +169,11 @@ enum fullness_group {
 };
 
 /*
+ * number of size_classes
+ */
+static int zs_size_classes;
+
+/*
  * We assign a page to ZS_ALMOST_EMPTY fullness group when:
  *	n <= N / f, where
  * n = number of allocated objects
@@ -214,7 +217,7 @@ struct link_free {
 };
 
 struct zs_pool {
-	struct size_class size_class[ZS_SIZE_CLASSES];
+	struct size_class **size_class;
 
 	gfp_t flags;	/* allocation flags used when growing pool */
 	atomic_long_t pages_allocated;
@@ -468,7 +471,7 @@ static enum fullness_group fix_fullness_group(struct zs_pool *pool,
 	if (newfg == currfg)
 		goto out;
 
-	class = &pool->size_class[class_idx];
+	class = pool->size_class[class_idx];
 	remove_zspage(page, class, currfg);
 	insert_zspage(page, class, newfg);
 	set_zspage_mapping(page, class_idx, newfg);
@@ -629,6 +632,7 @@ static void init_zspage(struct page *first_page, struct size_class *class)
 		struct page *next_page;
 		struct link_free *link;
 		unsigned int i = 1;
+		void *vaddr;
 
 		/*
 		 * page->index stores offset of first object starting
@@ -639,8 +643,8 @@ static void init_zspage(struct page *first_page, struct size_class *class)
 		if (page != first_page)
 			page->index = off;
 
-		link = (struct link_free *)kmap_atomic(page) +
-						off / sizeof(*link);
+		vaddr = kmap_atomic(page);
+		link = (struct link_free *)vaddr + off / sizeof(*link);
 
 		while ((off += class->size) < PAGE_SIZE) {
 			link->next = obj_location_to_handle(page, i++);
@@ -654,7 +658,7 @@ static void init_zspage(struct page *first_page, struct size_class *class)
 		 */
 		next_page = get_next_page(page);
 		link->next = obj_location_to_handle(next_page, 0);
-		kunmap_atomic(link);
+		kunmap_atomic(vaddr);
 		page = next_page;
 		off %= PAGE_SIZE;
 	}
@@ -784,7 +788,7 @@ static inline int __zs_cpu_up(struct mapping_area *area)
 	 */
 	if (area->vm_buf)
 		return 0;
-	area->vm_buf = (char *)__get_free_page(GFP_KERNEL);
+	area->vm_buf = kmalloc(ZS_MAX_ALLOC_SIZE, GFP_KERNEL);
 	if (!area->vm_buf)
 		return -ENOMEM;
 	return 0;
@@ -792,8 +796,7 @@ static inline int __zs_cpu_up(struct mapping_area *area)
 
 static inline void __zs_cpu_down(struct mapping_area *area)
 {
-	if (area->vm_buf)
-		free_page((unsigned long)area->vm_buf);
+	kfree(area->vm_buf);
 	area->vm_buf = NULL;
 }
 
@@ -881,14 +884,10 @@ static struct notifier_block zs_cpu_nb = {
 	.notifier_call = zs_cpu_notifier
 };
 
-static void zs_exit(void)
+static void zs_unregister_cpu_notifier(void)
 {
 	int cpu;
 
-#ifdef CONFIG_ZPOOL
-	zpool_unregister_driver(&zs_zpool_driver);
-#endif
-
 	cpu_notifier_register_begin();
 
 	for_each_online_cpu(cpu)
@@ -898,31 +897,74 @@ static void zs_exit(void)
 	cpu_notifier_register_done();
 }
 
-static int zs_init(void)
+static int zs_register_cpu_notifier(void)
 {
-	int cpu, ret;
+	int cpu, uninitialized_var(ret);
 
 	cpu_notifier_register_begin();
 
 	__register_cpu_notifier(&zs_cpu_nb);
 	for_each_online_cpu(cpu) {
 		ret = zs_cpu_notifier(NULL, CPU_UP_PREPARE, (void *)(long)cpu);
-		if (notifier_to_errno(ret)) {
-			cpu_notifier_register_done();
-			goto fail;
-		}
+		if (notifier_to_errno(ret))
+			break;
 	}
 
 	cpu_notifier_register_done();
+	return notifier_to_errno(ret);
+}
+
+static void init_zs_size_classes(void)
+{
+	int nr;
 
+	nr = (ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) / ZS_SIZE_CLASS_DELTA + 1;
+	if ((ZS_MAX_ALLOC_SIZE - ZS_MIN_ALLOC_SIZE) % ZS_SIZE_CLASS_DELTA)
+		nr += 1;
+
+	zs_size_classes = nr;
+}
+
+static void __exit zs_exit(void)
+{
 #ifdef CONFIG_ZPOOL
-	zpool_register_driver(&zs_zpool_driver);
+	zpool_unregister_driver(&zs_zpool_driver);
 #endif
+	zs_unregister_cpu_notifier();
+}
 
+static int __init zs_init(void)
+{
+	int ret = zs_register_cpu_notifier();
+
+	if (ret) {
+		zs_unregister_cpu_notifier();
+		return ret;
+	}
+
+	init_zs_size_classes();
+
+#ifdef CONFIG_ZPOOL
+	zpool_register_driver(&zs_zpool_driver);
+#endif
 	return 0;
-fail:
-	zs_exit();
-	return notifier_to_errno(ret);
+}
+
+static unsigned int get_maxobj_per_zspage(int size, int pages_per_zspage)
+{
+	return pages_per_zspage * PAGE_SIZE / size;
+}
+
+static bool can_merge(struct size_class *prev, int size, int pages_per_zspage)
+{
+	if (prev->pages_per_zspage != pages_per_zspage)
+		return false;
+
+	if (get_maxobj_per_zspage(prev->size, prev->pages_per_zspage)
+		!= get_maxobj_per_zspage(size, pages_per_zspage))
+		return false;
+
+	return true;
 }
 
 /**
@@ -937,33 +979,71 @@ fail:
  */
 struct zs_pool *zs_create_pool(gfp_t flags)
 {
-	int i, ovhd_size;
+	int i;
 	struct zs_pool *pool;
+	struct size_class *prev_class = NULL;
 
-	ovhd_size = roundup(sizeof(*pool), PAGE_SIZE);
-	pool = kzalloc(ovhd_size, GFP_KERNEL);
+	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
 	if (!pool)
 		return NULL;
 
-	for (i = 0; i < ZS_SIZE_CLASSES; i++) {
+	pool->size_class = kcalloc(zs_size_classes, sizeof(struct size_class *),
+			GFP_KERNEL);
+	if (!pool->size_class) {
+		kfree(pool);
+		return NULL;
+	}
+
+	/*
+	 * Iterate reversly, because, size of size_class that we want to use
+	 * for merging should be larger or equal to current size.
+	 */
+	for (i = zs_size_classes - 1; i >= 0; i--) {
 		int size;
+		int pages_per_zspage;
 		struct size_class *class;
 
 		size = ZS_MIN_ALLOC_SIZE + i * ZS_SIZE_CLASS_DELTA;
 		if (size > ZS_MAX_ALLOC_SIZE)
 			size = ZS_MAX_ALLOC_SIZE;
+		pages_per_zspage = get_pages_per_zspage(size);
+
+		/*
+		 * size_class is used for normal zsmalloc operation such
+		 * as alloc/free for that size. Although it is natural that we
+		 * have one size_class for each size, there is a chance that we
+		 * can get more memory utilization if we use one size_class for
+		 * many different sizes whose size_class have same
+		 * characteristics. So, we makes size_class point to
+		 * previous size_class if possible.
+		 */
+		if (prev_class) {
+			if (can_merge(prev_class, size, pages_per_zspage)) {
+				pool->size_class[i] = prev_class;
+				continue;
+			}
+		}
+
+		class = kzalloc(sizeof(struct size_class), GFP_KERNEL);
+		if (!class)
+			goto err;
 
-		class = &pool->size_class[i];
 		class->size = size;
 		class->index = i;
+		class->pages_per_zspage = pages_per_zspage;
 		spin_lock_init(&class->lock);
-		class->pages_per_zspage = get_pages_per_zspage(size);
+		pool->size_class[i] = class;
 
+		prev_class = class;
 	}
 
 	pool->flags = flags;
 
 	return pool;
+
+err:
+	zs_destroy_pool(pool);
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(zs_create_pool);
 
@@ -971,9 +1051,15 @@ void zs_destroy_pool(struct zs_pool *pool)
 {
 	int i;
 
-	for (i = 0; i < ZS_SIZE_CLASSES; i++) {
+	for (i = 0; i < zs_size_classes; i++) {
 		int fg;
-		struct size_class *class = &pool->size_class[i];
+		struct size_class *class = pool->size_class[i];
+
+		if (!class)
+			continue;
+
+		if (class->index != i)
+			continue;
 
 		for (fg = 0; fg < _ZS_NR_FULLNESS_GROUPS; fg++) {
 			if (class->fullness_list[fg]) {
@@ -981,7 +1067,10 @@ void zs_destroy_pool(struct zs_pool *pool)
 					class->size, fg);
 			}
 		}
+		kfree(class);
 	}
+
+	kfree(pool->size_class);
 	kfree(pool);
 }
 EXPORT_SYMBOL_GPL(zs_destroy_pool);
@@ -999,8 +1088,8 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size)
 {
 	unsigned long obj;
 	struct link_free *link;
-	int class_idx;
 	struct size_class *class;
+	void *vaddr;
 
 	struct page *first_page, *m_page;
 	unsigned long m_objidx, m_offset;
@@ -1008,9 +1097,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size)
 	if (unlikely(!size || size > ZS_MAX_ALLOC_SIZE))
 		return 0;
 
-	class_idx = get_size_class_index(size);
-	class = &pool->size_class[class_idx];
-	BUG_ON(class_idx != class->index);
+	class = pool->size_class[get_size_class_index(size)];
 
 	spin_lock(&class->lock);
 	first_page = find_get_zspage(class);
@@ -1031,11 +1118,11 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size)
 	obj_handle_to_location(obj, &m_page, &m_objidx);
 	m_offset = obj_idx_to_offset(m_page, m_objidx, class->size);
 
-	link = (struct link_free *)kmap_atomic(m_page) +
-					m_offset / sizeof(*link);
+	vaddr = kmap_atomic(m_page);
+	link = (struct link_free *)vaddr + m_offset / sizeof(*link);
 	first_page->freelist = link->next;
 	memset(link, POISON_INUSE, sizeof(*link));
-	kunmap_atomic(link);
+	kunmap_atomic(vaddr);
 
 	first_page->inuse++;
 	/* Now move the zspage to another fullness group, if required */
@@ -1051,6 +1138,7 @@ void zs_free(struct zs_pool *pool, unsigned long obj)
 	struct link_free *link;
 	struct page *first_page, *f_page;
 	unsigned long f_objidx, f_offset;
+	void *vaddr;
 
 	int class_idx;
 	struct size_class *class;
@@ -1063,16 +1151,16 @@ void zs_free(struct zs_pool *pool, unsigned long obj)
 	first_page = get_first_page(f_page);
 
 	get_zspage_mapping(first_page, &class_idx, &fullness);
-	class = &pool->size_class[class_idx];
+	class = pool->size_class[class_idx];
 	f_offset = obj_idx_to_offset(f_page, f_objidx, class->size);
 
 	spin_lock(&class->lock);
 
 	/* Insert this object in containing zspage's freelist */
-	link = (struct link_free *)((unsigned char *)kmap_atomic(f_page)
-							+ f_offset);
+	vaddr = kmap_atomic(f_page);
+	link = (struct link_free *)(vaddr + f_offset);
 	link->next = first_page->freelist;
-	kunmap_atomic(link);
+	kunmap_atomic(vaddr);
 	first_page->freelist = (void *)obj;
 
 	first_page->inuse--;
@@ -1124,7 +1212,7 @@ void *zs_map_object(struct zs_pool *pool, unsigned long handle,
 
 	obj_handle_to_location(handle, &page, &obj_idx);
 	get_zspage_mapping(get_first_page(page), &class_idx, &fg);
-	class = &pool->size_class[class_idx];
+	class = pool->size_class[class_idx];
 	off = obj_idx_to_offset(page, obj_idx, class->size);
 
 	area = &get_cpu_var(zs_map_area);
@@ -1158,7 +1246,7 @@ void zs_unmap_object(struct zs_pool *pool, unsigned long handle)
 
 	obj_handle_to_location(handle, &page, &obj_idx);
 	get_zspage_mapping(get_first_page(page), &class_idx, &fg);
-	class = &pool->size_class[class_idx];
+	class = pool->size_class[class_idx];
 	off = obj_idx_to_offset(page, obj_idx, class->size);
 
 	area = this_cpu_ptr(&zs_map_area);