Merge branch 'linus' into cpumask-for-linus

Conflicts:
	arch/x86/kernel/cpu/common.c

mm/allocpercpu.c

@@ -120,7 +120,7 @@ void *__alloc_percpu(size_t size, size_t align)
 	 * on it.  Larger alignment should only be used for module
 	 * percpu sections on SMP for which this path isn't used.
 	 */
-	WARN_ON_ONCE(align > __alignof__(unsigned long long));
+	WARN_ON_ONCE(align > SMP_CACHE_BYTES);
 
 	if (unlikely(!pdata))
 		return NULL;

mm/backing-dev.c

@@ -2,11 +2,24 @@
 #include <linux/wait.h>
 #include <linux/backing-dev.h>
 #include <linux/fs.h>
+#include <linux/pagemap.h>
 #include <linux/sched.h>
 #include <linux/module.h>
 #include <linux/writeback.h>
 #include <linux/device.h>
 
+void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
+{
+}
+EXPORT_SYMBOL(default_unplug_io_fn);
+
+struct backing_dev_info default_backing_dev_info = {
+	.ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
+	.state		= 0,
+	.capabilities	= BDI_CAP_MAP_COPY,
+	.unplug_io_fn	= default_unplug_io_fn,
+};
+EXPORT_SYMBOL_GPL(default_backing_dev_info);
 
 static struct class *bdi_class;
 
@@ -166,9 +179,20 @@ static __init int bdi_class_init(void)
 	bdi_debug_init();
 	return 0;
 }
-
 postcore_initcall(bdi_class_init);
 
+static int __init default_bdi_init(void)
+{
+	int err;
+
+	err = bdi_init(&default_backing_dev_info);
+	if (!err)
+		bdi_register(&default_backing_dev_info, NULL, "default");
+
+	return err;
+}
+subsys_initcall(default_bdi_init);
+
 int bdi_register(struct backing_dev_info *bdi, struct device *parent,
 		const char *fmt, ...)
 {

mm/highmem.c

@@ -67,6 +67,25 @@ pte_t * pkmap_page_table;
 
 static DECLARE_WAIT_QUEUE_HEAD(pkmap_map_wait);
 
+/*
+ * Most architectures have no use for kmap_high_get(), so let's abstract
+ * the disabling of IRQ out of the locking in that case to save on a
+ * potential useless overhead.
+ */
+#ifdef ARCH_NEEDS_KMAP_HIGH_GET
+#define lock_kmap()             spin_lock_irq(&kmap_lock)
+#define unlock_kmap()           spin_unlock_irq(&kmap_lock)
+#define lock_kmap_any(flags)    spin_lock_irqsave(&kmap_lock, flags)
+#define unlock_kmap_any(flags)  spin_unlock_irqrestore(&kmap_lock, flags)
+#else
+#define lock_kmap()             spin_lock(&kmap_lock)
+#define unlock_kmap()           spin_unlock(&kmap_lock)
+#define lock_kmap_any(flags)    \
+		do { spin_lock(&kmap_lock); (void)(flags); } while (0)
+#define unlock_kmap_any(flags)  \
+		do { spin_unlock(&kmap_lock); (void)(flags); } while (0)
+#endif
+
 static void flush_all_zero_pkmaps(void)
 {
 	int i;
@@ -113,9 +132,9 @@ static void flush_all_zero_pkmaps(void)
  */
 void kmap_flush_unused(void)
 {
-	spin_lock(&kmap_lock);
+	lock_kmap();
 	flush_all_zero_pkmaps();
-	spin_unlock(&kmap_lock);
+	unlock_kmap();
 }
 
 static inline unsigned long map_new_virtual(struct page *page)
@@ -145,10 +164,10 @@ start:
 
 			__set_current_state(TASK_UNINTERRUPTIBLE);
 			add_wait_queue(&pkmap_map_wait, &wait);
-			spin_unlock(&kmap_lock);
+			unlock_kmap();
 			schedule();
 			remove_wait_queue(&pkmap_map_wait, &wait);
-			spin_lock(&kmap_lock);
+			lock_kmap();
 
 			/* Somebody else might have mapped it while we slept */
 			if (page_address(page))
@@ -184,29 +203,59 @@ void *kmap_high(struct page *page)
 	 * For highmem pages, we can't trust "virtual" until
 	 * after we have the lock.
 	 */
-	spin_lock(&kmap_lock);
+	lock_kmap();
 	vaddr = (unsigned long)page_address(page);
 	if (!vaddr)
 		vaddr = map_new_virtual(page);
 	pkmap_count[PKMAP_NR(vaddr)]++;
 	BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 2);
-	spin_unlock(&kmap_lock);
+	unlock_kmap();
 	return (void*) vaddr;
 }
 
 EXPORT_SYMBOL(kmap_high);
 
+#ifdef ARCH_NEEDS_KMAP_HIGH_GET
+/**
+ * kmap_high_get - pin a highmem page into memory
+ * @page: &struct page to pin
+ *
+ * Returns the page's current virtual memory address, or NULL if no mapping
+ * exists.  When and only when a non null address is returned then a
+ * matching call to kunmap_high() is necessary.
+ *
+ * This can be called from any context.
+ */
+void *kmap_high_get(struct page *page)
+{
+	unsigned long vaddr, flags;
+
+	lock_kmap_any(flags);
+	vaddr = (unsigned long)page_address(page);
+	if (vaddr) {
+		BUG_ON(pkmap_count[PKMAP_NR(vaddr)] < 1);
+		pkmap_count[PKMAP_NR(vaddr)]++;
+	}
+	unlock_kmap_any(flags);
+	return (void*) vaddr;
+}
+#endif
+
 /**
  * kunmap_high - map a highmem page into memory
  * @page: &struct page to unmap
+ *
+ * If ARCH_NEEDS_KMAP_HIGH_GET is not defined then this may be called
+ * only from user context.
  */
 void kunmap_high(struct page *page)
 {
 	unsigned long vaddr;
 	unsigned long nr;
+	unsigned long flags;
 	int need_wakeup;
 
-	spin_lock(&kmap_lock);
+	lock_kmap_any(flags);
 	vaddr = (unsigned long)page_address(page);
 	BUG_ON(!vaddr);
 	nr = PKMAP_NR(vaddr);
@@ -232,7 +281,7 @@ void kunmap_high(struct page *page)
 		 */
 		need_wakeup = waitqueue_active(&pkmap_map_wait);
 	}
-	spin_unlock(&kmap_lock);
+	unlock_kmap_any(flags);
 
 	/* do wake-up, if needed, race-free outside of the spin lock */
 	if (need_wakeup)

mm/memory.c

@@ -1665,9 +1665,10 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 	 * behaviour that some programs depend on. We mark the "original"
 	 * un-COW'ed pages by matching them up with "vma->vm_pgoff".
 	 */
-	if (addr == vma->vm_start && end == vma->vm_end)
+	if (addr == vma->vm_start && end == vma->vm_end) {
 		vma->vm_pgoff = pfn;
-	else if (is_cow_mapping(vma->vm_flags))
+		vma->vm_flags |= VM_PFN_AT_MMAP;
+	} else if (is_cow_mapping(vma->vm_flags))
 		return -EINVAL;
 
 	vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP;
@@ -1679,6 +1680,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
 		 * needed from higher level routine calling unmap_vmas
 		 */
 		vma->vm_flags &= ~(VM_IO | VM_RESERVED | VM_PFNMAP);
+		vma->vm_flags &= ~VM_PFN_AT_MMAP;
 		return -EINVAL;
 	}
 

mm/mmap.c

@@ -20,6 +20,7 @@
 #include <linux/fs.h>
 #include <linux/personality.h>
 #include <linux/security.h>
+#include <linux/ima.h>
 #include <linux/hugetlb.h>
 #include <linux/profile.h>
 #include <linux/module.h>
@@ -1047,6 +1048,9 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	}
 
 	error = security_file_mmap(file, reqprot, prot, flags, addr, 0);
+	if (error)
+		return error;
+	error = ima_file_mmap(file, prot);
 	if (error)
 		return error;
 

mm/page-writeback.c

@@ -66,7 +66,7 @@ static inline long sync_writeback_pages(void)
 /*
  * Start background writeback (via pdflush) at this percentage
  */
-int dirty_background_ratio = 5;
+int dirty_background_ratio = 10;
 
 /*
  * dirty_background_bytes starts at 0 (disabled) so that it is a function of
@@ -83,7 +83,7 @@ int vm_highmem_is_dirtyable;
 /*
  * The generator of dirty data starts writeback at this percentage
  */
-int vm_dirty_ratio = 10;
+int vm_dirty_ratio = 20;
 
 /*
  * vm_dirty_bytes starts at 0 (disabled) so that it is a function of

mm/percpu.c

@@ -46,7 +46,8 @@
  * - define CONFIG_HAVE_DYNAMIC_PER_CPU_AREA
  *
  * - define __addr_to_pcpu_ptr() and __pcpu_ptr_to_addr() to translate
- *   regular address to percpu pointer and back
+ *   regular address to percpu pointer and back if they need to be
+ *   different from the default
  *
  * - use pcpu_setup_first_chunk() during percpu area initialization to
  *   setup the first chunk containing the kernel static percpu area
@@ -67,11 +68,24 @@
 #include <linux/workqueue.h>
 
 #include <asm/cacheflush.h>
+#include <asm/sections.h>
 #include <asm/tlbflush.h>
 
 #define PCPU_SLOT_BASE_SHIFT		5	/* 1-31 shares the same slot */
 #define PCPU_DFL_MAP_ALLOC		16	/* start a map with 16 ents */
 
+/* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */
+#ifndef __addr_to_pcpu_ptr
+#define __addr_to_pcpu_ptr(addr)					\
+	(void *)((unsigned long)(addr) - (unsigned long)pcpu_base_addr	\
+		 + (unsigned long)__per_cpu_start)
+#endif
+#ifndef __pcpu_ptr_to_addr
+#define __pcpu_ptr_to_addr(ptr)						\
+	(void *)((unsigned long)(ptr) + (unsigned long)pcpu_base_addr	\
+		 - (unsigned long)__per_cpu_start)
+#endif
+
 struct pcpu_chunk {
 	struct list_head	list;		/* linked to pcpu_slot lists */
 	struct rb_node		rb_node;	/* key is chunk->vm->addr */
@@ -1013,8 +1027,8 @@ EXPORT_SYMBOL_GPL(free_percpu);
  * @get_page_fn: callback to fetch page pointer
  * @static_size: the size of static percpu area in bytes
  * @reserved_size: the size of reserved percpu area in bytes
- * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto
  * @dyn_size: free size for dynamic allocation in bytes, -1 for auto
+ * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto
  * @base_addr: mapped address, NULL for auto
  * @populate_pte_fn: callback to allocate pagetable, NULL if unnecessary
  *
@@ -1039,14 +1053,14 @@ EXPORT_SYMBOL_GPL(free_percpu);
  * limited offset range for symbol relocations to guarantee module
  * percpu symbols fall inside the relocatable range.
  *
+ * @dyn_size, if non-negative, determines the number of bytes
+ * available for dynamic allocation in the first chunk.  Specifying
+ * non-negative value makes percpu leave alone the area beyond
+ * @static_size + @reserved_size + @dyn_size.
+ *
  * @unit_size, if non-negative, specifies unit size and must be
  * aligned to PAGE_SIZE and equal to or larger than @static_size +
- * @reserved_size + @dyn_size.
- *
- * @dyn_size, if non-negative, limits the number of bytes available
- * for dynamic allocation in the first chunk.  Specifying non-negative
- * value make percpu leave alone the area beyond @static_size +
- * @reserved_size + @dyn_size.
+ * @reserved_size + if non-negative, @dyn_size.
  *
  * Non-null @base_addr means that the caller already allocated virtual
  * region for the first chunk and mapped it.  percpu must not mess
@@ -1069,12 +1083,14 @@ EXPORT_SYMBOL_GPL(free_percpu);
  */
 size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
 				     size_t static_size, size_t reserved_size,
-				     ssize_t unit_size, ssize_t dyn_size,
+				     ssize_t dyn_size, ssize_t unit_size,
 				     void *base_addr,
 				     pcpu_populate_pte_fn_t populate_pte_fn)
 {
 	static struct vm_struct first_vm;
 	static int smap[2], dmap[2];
+	size_t size_sum = static_size + reserved_size +
+			  (dyn_size >= 0 ? dyn_size : 0);
 	struct pcpu_chunk *schunk, *dchunk = NULL;
 	unsigned int cpu;
 	int nr_pages;
@@ -1085,20 +1101,18 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
 		     ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC);
 	BUG_ON(!static_size);
 	if (unit_size >= 0) {
-		BUG_ON(unit_size < static_size + reserved_size +
-				   (dyn_size >= 0 ? dyn_size : 0));
+		BUG_ON(unit_size < size_sum);
 		BUG_ON(unit_size & ~PAGE_MASK);
-	} else {
-		BUG_ON(dyn_size >= 0);
+		BUG_ON(unit_size < PCPU_MIN_UNIT_SIZE);
+	} else
 		BUG_ON(base_addr);
-	}
 	BUG_ON(base_addr && populate_pte_fn);
 
 	if (unit_size >= 0)
 		pcpu_unit_pages = unit_size >> PAGE_SHIFT;
 	else
 		pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_SIZE >> PAGE_SHIFT,
-					PFN_UP(static_size + reserved_size));
+					PFN_UP(size_sum));
 
 	pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
 	pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size;
@@ -1224,3 +1238,89 @@ size_t __init pcpu_setup_first_chunk(pcpu_get_page_fn_t get_page_fn,
 	pcpu_base_addr = (void *)pcpu_chunk_addr(schunk, 0, 0);
 	return pcpu_unit_size;
 }
+
+/*
+ * Embedding first chunk setup helper.
+ */
+static void *pcpue_ptr __initdata;
+static size_t pcpue_size __initdata;
+static size_t pcpue_unit_size __initdata;
+
+static struct page * __init pcpue_get_page(unsigned int cpu, int pageno)
+{
+	size_t off = (size_t)pageno << PAGE_SHIFT;
+
+	if (off >= pcpue_size)
+		return NULL;
+
+	return virt_to_page(pcpue_ptr + cpu * pcpue_unit_size + off);
+}
+
+/**
+ * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
+ * @static_size: the size of static percpu area in bytes
+ * @reserved_size: the size of reserved percpu area in bytes
+ * @dyn_size: free size for dynamic allocation in bytes, -1 for auto
+ * @unit_size: unit size in bytes, must be multiple of PAGE_SIZE, -1 for auto
+ *
+ * This is a helper to ease setting up embedded first percpu chunk and
+ * can be called where pcpu_setup_first_chunk() is expected.
+ *
+ * If this function is used to setup the first chunk, it is allocated
+ * as a contiguous area using bootmem allocator and used as-is without
+ * being mapped into vmalloc area.  This enables the first chunk to
+ * piggy back on the linear physical mapping which often uses larger
+ * page size.
+ *
+ * When @dyn_size is positive, dynamic area might be larger than
+ * specified to fill page alignment.  Also, when @dyn_size is auto,
+ * @dyn_size does not fill the whole first chunk but only what's
+ * necessary for page alignment after static and reserved areas.
+ *
+ * If the needed size is smaller than the minimum or specified unit
+ * size, the leftover is returned to the bootmem allocator.
+ *
+ * RETURNS:
+ * The determined pcpu_unit_size which can be used to initialize
+ * percpu access on success, -errno on failure.
+ */
+ssize_t __init pcpu_embed_first_chunk(size_t static_size, size_t reserved_size,
+				      ssize_t dyn_size, ssize_t unit_size)
+{
+	unsigned int cpu;
+
+	/* determine parameters and allocate */
+	pcpue_size = PFN_ALIGN(static_size + reserved_size +
+			       (dyn_size >= 0 ? dyn_size : 0));
+	if (dyn_size != 0)
+		dyn_size = pcpue_size - static_size - reserved_size;
+
+	if (unit_size >= 0) {
+		BUG_ON(unit_size < pcpue_size);
+		pcpue_unit_size = unit_size;
+	} else
+		pcpue_unit_size = max_t(size_t, pcpue_size, PCPU_MIN_UNIT_SIZE);
+
+	pcpue_ptr = __alloc_bootmem_nopanic(
+					num_possible_cpus() * pcpue_unit_size,
+					PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+	if (!pcpue_ptr)
+		return -ENOMEM;
+
+	/* return the leftover and copy */
+	for_each_possible_cpu(cpu) {
+		void *ptr = pcpue_ptr + cpu * pcpue_unit_size;
+
+		free_bootmem(__pa(ptr + pcpue_size),
+			     pcpue_unit_size - pcpue_size);
+		memcpy(ptr, __per_cpu_load, static_size);
+	}
+
+	/* we're ready, commit */
+	pr_info("PERCPU: Embedded %zu pages at %p, static data %zu bytes\n",
+		pcpue_size >> PAGE_SHIFT, pcpue_ptr, static_size);
+
+	return pcpu_setup_first_chunk(pcpue_get_page, static_size,
+				      reserved_size, dyn_size,
+				      pcpue_unit_size, pcpue_ptr, NULL);
+}

mm/readahead.c

@@ -17,19 +17,6 @@
 #include <linux/pagevec.h>
 #include <linux/pagemap.h>
 
-void default_unplug_io_fn(struct backing_dev_info *bdi, struct page *page)
-{
-}
-EXPORT_SYMBOL(default_unplug_io_fn);
-
-struct backing_dev_info default_backing_dev_info = {
-	.ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
-	.state		= 0,
-	.capabilities	= BDI_CAP_MAP_COPY,
-	.unplug_io_fn	= default_unplug_io_fn,
-};
-EXPORT_SYMBOL_GPL(default_backing_dev_info);
-
 /*
  * Initialise a struct file's readahead state.  Assumes that the caller has
  * memset *ra to zero.
@@ -233,18 +220,6 @@ unsigned long max_sane_readahead(unsigned long nr)
 		+ node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2);
 }
 
-static int __init readahead_init(void)
-{
-	int err;
-
-	err = bdi_init(&default_backing_dev_info);
-	if (!err)
-		bdi_register(&default_backing_dev_info, NULL, "default");
-
-	return err;
-}
-subsys_initcall(readahead_init);
-
 /*
  * Submit IO for the read-ahead request in file_ra_state.
  */

mm/shmem.c

@@ -28,6 +28,7 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/swap.h>
+#include <linux/ima.h>
 
 static struct vfsmount *shm_mnt;
 
@@ -2665,6 +2666,7 @@ int shmem_zero_setup(struct vm_area_struct *vma)
 	if (IS_ERR(file))
 		return PTR_ERR(file);
 
+	ima_shm_check(file);
 	if (vma->vm_file)
 		fput(vma->vm_file);
 	vma->vm_file = file;

mm/slob.c

@@ -126,9 +126,9 @@ static LIST_HEAD(free_slob_medium);
 static LIST_HEAD(free_slob_large);
 
 /*
- * slob_page: True for all slob pages (false for bigblock pages)
+ * is_slob_page: True for all slob pages (false for bigblock pages)
  */
-static inline int slob_page(struct slob_page *sp)
+static inline int is_slob_page(struct slob_page *sp)
 {
 	return PageSlobPage((struct page *)sp);
 }
@@ -143,6 +143,11 @@ static inline void clear_slob_page(struct slob_page *sp)
 	__ClearPageSlobPage((struct page *)sp);
 }
 
+static inline struct slob_page *slob_page(const void *addr)
+{
+	return (struct slob_page *)virt_to_page(addr);
+}
+
 /*
  * slob_page_free: true for pages on free_slob_pages list.
  */
@@ -230,7 +235,7 @@ static int slob_last(slob_t *s)
 	return !((unsigned long)slob_next(s) & ~PAGE_MASK);
 }
 
-static void *slob_new_page(gfp_t gfp, int order, int node)
+static void *slob_new_pages(gfp_t gfp, int order, int node)
 {
 	void *page;
 
@@ -247,12 +252,17 @@ static void *slob_new_page(gfp_t gfp, int order, int node)
 	return page_address(page);
 }
 
+static void slob_free_pages(void *b, int order)
+{
+	free_pages((unsigned long)b, order);
+}
+
 /*
  * Allocate a slob block within a given slob_page sp.
  */
 static void *slob_page_alloc(struct slob_page *sp, size_t size, int align)
 {
-	slob_t *prev, *cur, *aligned = 0;
+	slob_t *prev, *cur, *aligned = NULL;
 	int delta = 0, units = SLOB_UNITS(size);
 
 	for (prev = NULL, cur = sp->free; ; prev = cur, cur = slob_next(cur)) {
@@ -349,10 +359,10 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
 
 	/* Not enough space: must allocate a new page */
 	if (!b) {
-		b = slob_new_page(gfp & ~__GFP_ZERO, 0, node);
+		b = slob_new_pages(gfp & ~__GFP_ZERO, 0, node);
 		if (!b)
-			return 0;
-		sp = (struct slob_page *)virt_to_page(b);
+			return NULL;
+		sp = slob_page(b);
 		set_slob_page(sp);
 
 		spin_lock_irqsave(&slob_lock, flags);
@@ -384,7 +394,7 @@ static void slob_free(void *block, int size)
 		return;
 	BUG_ON(!size);
 
-	sp = (struct slob_page *)virt_to_page(block);
+	sp = slob_page(block);
 	units = SLOB_UNITS(size);
 
 	spin_lock_irqsave(&slob_lock, flags);
@@ -393,10 +403,11 @@ static void slob_free(void *block, int size)
 		/* Go directly to page allocator. Do not pass slob allocator */
 		if (slob_page_free(sp))
 			clear_slob_page_free(sp);
+		spin_unlock_irqrestore(&slob_lock, flags);
 		clear_slob_page(sp);
 		free_slob_page(sp);
 		free_page((unsigned long)b);
-		goto out;
+		return;
 	}
 
 	if (!slob_page_free(sp)) {
@@ -476,7 +487,7 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node)
 	} else {
 		void *ret;
 
-		ret = slob_new_page(gfp | __GFP_COMP, get_order(size), node);
+		ret = slob_new_pages(gfp | __GFP_COMP, get_order(size), node);
 		if (ret) {
 			struct page *page;
 			page = virt_to_page(ret);
@@ -494,8 +505,8 @@ void kfree(const void *block)
 	if (unlikely(ZERO_OR_NULL_PTR(block)))
 		return;
 
-	sp = (struct slob_page *)virt_to_page(block);
-	if (slob_page(sp)) {
+	sp = slob_page(block);
+	if (is_slob_page(sp)) {
 		int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
 		unsigned int *m = (unsigned int *)(block - align);
 		slob_free(m, *m + align);
@@ -513,8 +524,8 @@ size_t ksize(const void *block)
 	if (unlikely(block == ZERO_SIZE_PTR))
 		return 0;
 
-	sp = (struct slob_page *)virt_to_page(block);
-	if (slob_page(sp)) {
+	sp = slob_page(block);
+	if (is_slob_page(sp)) {
 		int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
 		unsigned int *m = (unsigned int *)(block - align);
 		return SLOB_UNITS(*m) * SLOB_UNIT;
@@ -573,7 +584,7 @@ void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
 	if (c->size < PAGE_SIZE)
 		b = slob_alloc(c->size, flags, c->align, node);
 	else
-		b = slob_new_page(flags, get_order(c->size), node);
+		b = slob_new_pages(flags, get_order(c->size), node);
 
 	if (c->ctor)
 		c->ctor(b);
@@ -587,7 +598,7 @@ static void __kmem_cache_free(void *b, int size)
 	if (size < PAGE_SIZE)
 		slob_free(b, size);
 	else
-		free_pages((unsigned long)b, get_order(size));
+		slob_free_pages(b, get_order(size));
 }
 
 static void kmem_rcu_free(struct rcu_head *head)

mm/slub.c

@@ -374,14 +374,8 @@ static struct track *get_track(struct kmem_cache *s, void *object,
 static void set_track(struct kmem_cache *s, void *object,
 			enum track_item alloc, unsigned long addr)
 {
-	struct track *p;
+	struct track *p = get_track(s, object, alloc);
 
-	if (s->offset)
-		p = object + s->offset + sizeof(void *);
-	else
-		p = object + s->inuse;
-
-	p += alloc;
 	if (addr) {
 		p->addr = addr;
 		p->cpu = smp_processor_id();
@@ -1335,7 +1329,7 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 		n = get_node(s, zone_to_nid(zone));
 
 		if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
-				n->nr_partial > n->min_partial) {
+				n->nr_partial > s->min_partial) {
 			page = get_partial_node(n);
 			if (page)
 				return page;
@@ -1387,7 +1381,7 @@ static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail)
 		slab_unlock(page);
 	} else {
 		stat(c, DEACTIVATE_EMPTY);
-		if (n->nr_partial < n->min_partial) {
+		if (n->nr_partial < s->min_partial) {
 			/*
 			 * Adding an empty slab to the partial slabs in order
 			 * to avoid page allocator overhead. This slab needs
@@ -1724,7 +1718,7 @@ static __always_inline void slab_free(struct kmem_cache *s,
 	c = get_cpu_slab(s, smp_processor_id());
 	debug_check_no_locks_freed(object, c->objsize);
 	if (!(s->flags & SLAB_DEBUG_OBJECTS))
-		debug_check_no_obj_freed(object, s->objsize);
+		debug_check_no_obj_freed(object, c->objsize);
 	if (likely(page == c->page && c->node >= 0)) {
 		object[c->offset] = c->freelist;
 		c->freelist = object;
@@ -1844,6 +1838,7 @@ static inline int calculate_order(int size)
 	int order;
 	int min_objects;
 	int fraction;
+	int max_objects;
 
 	/*
 	 * Attempt to find best configuration for a slab. This
@@ -1856,6 +1851,9 @@ static inline int calculate_order(int size)
 	min_objects = slub_min_objects;
 	if (!min_objects)
 		min_objects = 4 * (fls(nr_cpu_ids) + 1);
+	max_objects = (PAGE_SIZE << slub_max_order)/size;
+	min_objects = min(min_objects, max_objects);
+
 	while (min_objects > 1) {
 		fraction = 16;
 		while (fraction >= 4) {
@@ -1865,7 +1863,7 @@ static inline int calculate_order(int size)
 				return order;
 			fraction /= 2;
 		}
-		min_objects /= 2;
+		min_objects --;
 	}
 
 	/*
@@ -1928,17 +1926,6 @@ static void
 init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
 {
 	n->nr_partial = 0;
-
-	/*
-	 * The larger the object size is, the more pages we want on the partial
-	 * list to avoid pounding the page allocator excessively.
-	 */
-	n->min_partial = ilog2(s->size);
-	if (n->min_partial < MIN_PARTIAL)
-		n->min_partial = MIN_PARTIAL;
-	else if (n->min_partial > MAX_PARTIAL)
-		n->min_partial = MAX_PARTIAL;
-
 	spin_lock_init(&n->list_lock);
 	INIT_LIST_HEAD(&n->partial);
 #ifdef CONFIG_SLUB_DEBUG
@@ -2181,6 +2168,15 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
 }
 #endif
 
+static void set_min_partial(struct kmem_cache *s, unsigned long min)
+{
+	if (min < MIN_PARTIAL)
+		min = MIN_PARTIAL;
+	else if (min > MAX_PARTIAL)
+		min = MAX_PARTIAL;
+	s->min_partial = min;
+}
+
 /*
  * calculate_sizes() determines the order and the distribution of data within
  * a slab object.
@@ -2319,6 +2315,11 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
 	if (!calculate_sizes(s, -1))
 		goto error;
 
+	/*
+	 * The larger the object size is, the more pages we want on the partial
+	 * list to avoid pounding the page allocator excessively.
+	 */
+	set_min_partial(s, ilog2(s->size));
 	s->refcount = 1;
 #ifdef CONFIG_NUMA
 	s->remote_node_defrag_ratio = 1000;
@@ -2475,7 +2476,7 @@ EXPORT_SYMBOL(kmem_cache_destroy);
  *		Kmalloc subsystem
  *******************************************************************/
 
-struct kmem_cache kmalloc_caches[PAGE_SHIFT + 1] __cacheline_aligned;
+struct kmem_cache kmalloc_caches[SLUB_PAGE_SHIFT] __cacheline_aligned;
 EXPORT_SYMBOL(kmalloc_caches);
 
 static int __init setup_slub_min_order(char *str)
@@ -2537,7 +2538,7 @@ panic:
 }
 
 #ifdef CONFIG_ZONE_DMA
-static struct kmem_cache *kmalloc_caches_dma[PAGE_SHIFT + 1];
+static struct kmem_cache *kmalloc_caches_dma[SLUB_PAGE_SHIFT];
 
 static void sysfs_add_func(struct work_struct *w)
 {
@@ -2658,7 +2659,7 @@ void *__kmalloc(size_t size, gfp_t flags)
 {
 	struct kmem_cache *s;
 
-	if (unlikely(size > PAGE_SIZE))
+	if (unlikely(size > SLUB_MAX_SIZE))
 		return kmalloc_large(size, flags);
 
 	s = get_slab(size, flags);
@@ -2686,7 +2687,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
 {
 	struct kmem_cache *s;
 
-	if (unlikely(size > PAGE_SIZE))
+	if (unlikely(size > SLUB_MAX_SIZE))
 		return kmalloc_large_node(size, flags, node);
 
 	s = get_slab(size, flags);
@@ -2986,7 +2987,7 @@ void __init kmem_cache_init(void)
 		caches++;
 	}
 
-	for (i = KMALLOC_SHIFT_LOW; i <= PAGE_SHIFT; i++) {
+	for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) {
 		create_kmalloc_cache(&kmalloc_caches[i],
 			"kmalloc", 1 << i, GFP_KERNEL);
 		caches++;
@@ -3023,7 +3024,7 @@ void __init kmem_cache_init(void)
 	slab_state = UP;
 
 	/* Provide the correct kmalloc names now that the caches are up */
-	for (i = KMALLOC_SHIFT_LOW; i <= PAGE_SHIFT; i++)
+	for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++)
 		kmalloc_caches[i]. name =
 			kasprintf(GFP_KERNEL, "kmalloc-%d", 1 << i);
 
@@ -3223,7 +3224,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
 {
 	struct kmem_cache *s;
 
-	if (unlikely(size > PAGE_SIZE))
+	if (unlikely(size > SLUB_MAX_SIZE))
 		return kmalloc_large(size, gfpflags);
 
 	s = get_slab(size, gfpflags);
@@ -3239,7 +3240,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 {
 	struct kmem_cache *s;
 
-	if (unlikely(size > PAGE_SIZE))
+	if (unlikely(size > SLUB_MAX_SIZE))
 		return kmalloc_large_node(size, gfpflags, node);
 
 	s = get_slab(size, gfpflags);
@@ -3836,6 +3837,26 @@ static ssize_t order_show(struct kmem_cache *s, char *buf)
 }
 SLAB_ATTR(order);
 
+static ssize_t min_partial_show(struct kmem_cache *s, char *buf)
+{
+	return sprintf(buf, "%lu\n", s->min_partial);
+}
+
+static ssize_t min_partial_store(struct kmem_cache *s, const char *buf,
+				 size_t length)
+{
+	unsigned long min;
+	int err;
+
+	err = strict_strtoul(buf, 10, &min);
+	if (err)
+		return err;
+
+	set_min_partial(s, min);
+	return length;
+}
+SLAB_ATTR(min_partial);
+
 static ssize_t ctor_show(struct kmem_cache *s, char *buf)
 {
 	if (s->ctor) {
@@ -4151,6 +4172,7 @@ static struct attribute *slab_attrs[] = {
 	&object_size_attr.attr,
 	&objs_per_slab_attr.attr,
 	&order_attr.attr,
+	&min_partial_attr.attr,
 	&objects_attr.attr,
 	&objects_partial_attr.attr,
 	&total_objects_attr.attr,

mm/vmscan.c

@@ -1262,7 +1262,6 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	 * Move the pages to the [file or anon] inactive list.
 	 */
 	pagevec_init(&pvec, 1);
-	pgmoved = 0;
 	lru = LRU_BASE + file * LRU_FILE;
 
 	spin_lock_irq(&zone->lru_lock);
@@ -1274,6 +1273,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	 */
 	reclaim_stat->recent_rotated[!!file] += pgmoved;
 
+	pgmoved = 0;
 	while (!list_empty(&l_inactive)) {
 		page = lru_to_page(&l_inactive);
 		prefetchw_prev_lru_page(page, &l_inactive, flags);