Merge branch 'stable-linux-3.4.y' into tilt-3.4-up

Conflicts:
	arch/arm/kernel/traps.c
	arch/arm/vfp/entry.S
	drivers/base/power/main.c
	drivers/net/tun.c
	include/linux/rpmsg.h
	net/mac80211/mlme.c

12 files changed, 238 insertions, 142 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 9aa46eb4471e..d328099afe74 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -700,8 +700,11 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		if (err) {
 			putback_lru_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
+			if (err == -ENOMEM) {
+				ret = COMPACT_PARTIAL;
+				goto out;
+			}
 		}
-
 	}
 
 out:
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ae8f708e3d75..a799df59d310 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2157,6 +2157,15 @@ static void hugetlb_vm_op_open(struct vm_area_struct *vma)
 		kref_get(&reservations->refs);
 }
 
+static void resv_map_put(struct vm_area_struct *vma)
+{
+	struct resv_map *reservations = vma_resv_map(vma);
+
+	if (!reservations)
+		return;
+	kref_put(&reservations->refs, resv_map_release);
+}
+
 static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 {
 	struct hstate *h = hstate_vma(vma);
@@ -2173,7 +2182,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma)
 		reserve = (end - start) -
 			region_count(&reservations->regions, start, end);
 
-		kref_put(&reservations->refs, resv_map_release);
+		resv_map_put(vma);
 
 		if (reserve) {
 			hugetlb_acct_memory(h, -reserve);
@@ -2383,6 +2392,22 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 {
 	mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
 	__unmap_hugepage_range(vma, start, end, ref_page);
+	/*
+	 * Clear this flag so that x86's huge_pmd_share page_table_shareable
+	 * test will fail on a vma being torn down, and not grab a page table
+	 * on its way out.  We're lucky that the flag has such an appropriate
+	 * name, and can in fact be safely cleared here. We could clear it
+	 * before the __unmap_hugepage_range above, but all that's necessary
+	 * is to clear it before releasing the i_mmap_mutex below.
+	 *
+	 * This works because in the contexts this is called, the VMA is
+	 * going to be destroyed. It is not vunerable to madvise(DONTNEED)
+	 * because madvise is not supported on hugetlbfs. The same applies
+	 * for direct IO. unmap_hugepage_range() is only being called just
+	 * before free_pgtables() so clearing VM_MAYSHARE will not cause
+	 * surprises later.
+	 */
+	vma->vm_flags &= ~VM_MAYSHARE;
 	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
 }
 
@@ -2949,9 +2974,14 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 		}
 	}
 	spin_unlock(&mm->page_table_lock);
-	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
-
+	/*
+	 * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare
+	 * may have cleared our pud entry and done put_page on the page table:
+	 * once we release i_mmap_mutex, another task can do the final put_page
+	 * and that page table be reused and filled with junk.
+	 */
 	flush_tlb_range(vma, start, end);
+	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
 }
 
 int hugetlb_reserve_pages(struct inode *inode,
@@ -2990,12 +3020,16 @@ int hugetlb_reserve_pages(struct inode *inode,
 		set_vma_resv_flags(vma, HPAGE_RESV_OWNER);
 	}
 
-	if (chg < 0)
-		return chg;
+	if (chg < 0) {
+		ret = chg;
+		goto out_err;
+	}
 
 	/* There must be enough pages in the subpool for the mapping */
-	if (hugepage_subpool_get_pages(spool, chg))
-		return -ENOSPC;
+	if (hugepage_subpool_get_pages(spool, chg)) {
+		ret = -ENOSPC;
+		goto out_err;
+	}
 
 	/*
 	 * Check enough hugepages are available for the reservation.
@@ -3004,7 +3038,7 @@ int hugetlb_reserve_pages(struct inode *inode,
 	ret = hugetlb_acct_memory(h, chg);
 	if (ret < 0) {
 		hugepage_subpool_put_pages(spool, chg);
-		return ret;
+		goto out_err;
 	}
 
 	/*
@@ -3021,6 +3055,10 @@ int hugetlb_reserve_pages(struct inode *inode,
 	if (!vma || vma->vm_flags & VM_MAYSHARE)
 		region_add(&inode->i_mapping->private_list, from, to);
 	return 0;
+out_err:
+	if (vma)
+		resv_map_put(vma);
+	return ret;
 }
 
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
diff --git a/mm/madvise.c b/mm/madvise.c
index 1ccbba5b6674..55f645c85a35 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -13,6 +13,7 @@
 #include <linux/hugetlb.h>
 #include <linux/sched.h>
 #include <linux/ksm.h>
+#include <linux/file.h>
 
 /*
  * Any behaviour which results in changes to the vma->vm_flags needs to
@@ -203,14 +204,16 @@ static long madvise_remove(struct vm_area_struct *vma,
 	struct address_space *mapping;
 	loff_t offset, endoff;
 	int error;
+	struct file *f;
 
 	*prev = NULL;	/* tell sys_madvise we drop mmap_sem */
 
 	if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB))
 		return -EINVAL;
 
-	if (!vma->vm_file || !vma->vm_file->f_mapping
-		|| !vma->vm_file->f_mapping->host) {
+	f = vma->vm_file;
+
+	if (!f || !f->f_mapping || !f->f_mapping->host) {
 			return -EINVAL;
 	}
 
@@ -224,9 +227,16 @@ static long madvise_remove(struct vm_area_struct *vma,
 	endoff = (loff_t)(end - vma->vm_start - 1)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
 
-	/* vmtruncate_range needs to take i_mutex */
+	/*
+	 * vmtruncate_range may need to take i_mutex.  We need to
+	 * explicitly grab a reference because the vma (and hence the
+	 * vma's reference to the file) can go away as soon as we drop
+	 * mmap_sem.
+	 */
+	get_file(f);
 	up_read(&current->mm->mmap_sem);
 	error = vmtruncate_range(mapping->host, offset, endoff);
+	fput(f);
 	down_read(&current->mm->mmap_sem);
 	return error;
 }
diff --git a/mm/memblock.c b/mm/memblock.c
index a44eab3157f8..280d3d7835d6 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -37,6 +37,8 @@ struct memblock memblock __initdata_memblock = {
 
 int memblock_debug __initdata_memblock;
 static int memblock_can_resize __initdata_memblock;
+static int memblock_memory_in_slab __initdata_memblock = 0;
+static int memblock_reserved_in_slab __initdata_memblock = 0;
 
 /* inline so we don't get a warning when pr_debug is compiled out */
 static inline const char *memblock_type_name(struct memblock_type *type)
@@ -141,30 +143,6 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
 					   MAX_NUMNODES);
 }
 
-/*
- * Free memblock.reserved.regions
- */
-int __init_memblock memblock_free_reserved_regions(void)
-{
-	if (memblock.reserved.regions == memblock_reserved_init_regions)
-		return 0;
-
-	return memblock_free(__pa(memblock.reserved.regions),
-		 sizeof(struct memblock_region) * memblock.reserved.max);
-}
-
-/*
- * Reserve memblock.reserved.regions
- */
-int __init_memblock memblock_reserve_reserved_regions(void)
-{
-	if (memblock.reserved.regions == memblock_reserved_init_regions)
-		return 0;
-
-	return memblock_reserve(__pa(memblock.reserved.regions),
-		 sizeof(struct memblock_region) * memblock.reserved.max);
-}
-
 static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
 {
 	type->total_size -= type->regions[r].size;
@@ -182,11 +160,42 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
 	}
 }
 
-static int __init_memblock memblock_double_array(struct memblock_type *type)
+phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info(
+					phys_addr_t *addr)
+{
+	if (memblock.reserved.regions == memblock_reserved_init_regions)
+		return 0;
+
+	*addr = __pa(memblock.reserved.regions);
+
+	return PAGE_ALIGN(sizeof(struct memblock_region) *
+			  memblock.reserved.max);
+}
+
+/**
+ * memblock_double_array - double the size of the memblock regions array
+ * @type: memblock type of the regions array being doubled
+ * @new_area_start: starting address of memory range to avoid overlap with
+ * @new_area_size: size of memory range to avoid overlap with
+ *
+ * Double the size of the @type regions array. If memblock is being used to
+ * allocate memory for a new reserved regions array and there is a previously
+ * allocated memory range [@new_area_start,@new_area_start+@new_area_size]
+ * waiting to be reserved, ensure the memory used by the new array does
+ * not overlap.
+ *
+ * RETURNS:
+ * 0 on success, -1 on failure.
+ */
+static int __init_memblock memblock_double_array(struct memblock_type *type,
+						phys_addr_t new_area_start,
+						phys_addr_t new_area_size)
 {
 	struct memblock_region *new_array, *old_array;
+	phys_addr_t old_alloc_size, new_alloc_size;
 	phys_addr_t old_size, new_size, addr;
 	int use_slab = slab_is_available();
+	int *in_slab;
 
 	/* We don't allow resizing until we know about the reserved regions
 	 * of memory that aren't suitable for allocation
@@ -197,6 +206,18 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
 	/* Calculate new doubled size */
 	old_size = type->max * sizeof(struct memblock_region);
 	new_size = old_size << 1;
+	/*
+	 * We need to allocated new one align to PAGE_SIZE,
+	 *   so we can free them completely later.
+	 */
+	old_alloc_size = PAGE_ALIGN(old_size);
+	new_alloc_size = PAGE_ALIGN(new_size);
+
+	/* Retrieve the slab flag */
+	if (type == &memblock.memory)
+		in_slab = &memblock_memory_in_slab;
+	else
+		in_slab = &memblock_reserved_in_slab;
 
 	/* Try to find some space for it.
 	 *
@@ -212,14 +233,26 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
 	if (use_slab) {
 		new_array = kmalloc(new_size, GFP_KERNEL);
 		addr = new_array ? __pa(new_array) : 0;
-	} else
-		addr = memblock_find_in_range(0, MEMBLOCK_ALLOC_ACCESSIBLE, new_size, sizeof(phys_addr_t));
+	} else {
+		/* only exclude range when trying to double reserved.regions */
+		if (type != &memblock.reserved)
+			new_area_start = new_area_size = 0;
+
+		addr = memblock_find_in_range(new_area_start + new_area_size,
+						memblock.current_limit,
+						new_alloc_size, PAGE_SIZE);
+		if (!addr && new_area_size)
+			addr = memblock_find_in_range(0,
+					min(new_area_start, memblock.current_limit),
+					new_alloc_size, PAGE_SIZE);
+
+		new_array = addr ? __va(addr) : 0;
+	}
 	if (!addr) {
 		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
 		       memblock_type_name(type), type->max, type->max * 2);
 		return -1;
 	}
-	new_array = __va(addr);
 
 	memblock_dbg("memblock: %s array is doubled to %ld at [%#010llx-%#010llx]",
 		 memblock_type_name(type), type->max * 2, (u64)addr, (u64)addr + new_size - 1);
@@ -234,21 +267,23 @@ static int __init_memblock memblock_double_array(struct memblock_type *type)
 	type->regions = new_array;
 	type->max <<= 1;
 
-	/* If we use SLAB that's it, we are done */
-	if (use_slab)
-		return 0;
-
-	/* Add the new reserved region now. Should not fail ! */
-	BUG_ON(memblock_reserve(addr, new_size));
-
-	/* If the array wasn't our static init one, then free it. We only do
-	 * that before SLAB is available as later on, we don't know whether
-	 * to use kfree or free_bootmem_pages(). Shouldn't be a big deal
-	 * anyways
+	/* Free old array. We needn't free it if the array is the
+	 * static one
 	 */
-	if (old_array != memblock_memory_init_regions &&
-	    old_array != memblock_reserved_init_regions)
-		memblock_free(__pa(old_array), old_size);
+	if (*in_slab)
+		kfree(old_array);
+	else if (old_array != memblock_memory_init_regions &&
+		 old_array != memblock_reserved_init_regions)
+		memblock_free(__pa(old_array), old_alloc_size);
+
+	/* Reserve the new array if that comes from the memblock.
+	 * Otherwise, we needn't do it
+	 */
+	if (!use_slab)
+		BUG_ON(memblock_reserve(addr, new_alloc_size));
+
+	/* Update slab flag */
+	*in_slab = use_slab;
 
 	return 0;
 }
@@ -387,7 +422,7 @@ repeat:
 	 */
 	if (!insert) {
 		while (type->cnt + nr_new > type->max)
-			if (memblock_double_array(type) < 0)
+			if (memblock_double_array(type, obase, size) < 0)
 				return -ENOMEM;
 		insert = true;
 		goto repeat;
@@ -438,7 +473,7 @@ static int __init_memblock memblock_isolate_range(struct memblock_type *type,
 
 	/* we'll create at most two more regions */
 	while (type->cnt + 2 > type->max)
-		if (memblock_double_array(type) < 0)
+		if (memblock_double_array(type, base, size) < 0)
 			return -ENOMEM;
 
 	for (i = 0; i < type->cnt; i++) {
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index c99ad4e6b88c..9299eea77f72 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -345,14 +345,14 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
  * Also when FAIL is set do a force kill because something went
  * wrong earlier.
  */
-static void kill_procs(struct list_head *to_kill, int doit, int trapno,
+static void kill_procs(struct list_head *to_kill, int forcekill, int trapno,
 			  int fail, struct page *page, unsigned long pfn,
 			  int flags)
 {
 	struct to_kill *tk, *next;
 
 	list_for_each_entry_safe (tk, next, to_kill, nd) {
-		if (doit) {
+		if (forcekill) {
 			/*
 			 * In case something went wrong with munmapping
 			 * make sure the process doesn't catch the
@@ -858,7 +858,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	struct address_space *mapping;
 	LIST_HEAD(tokill);
 	int ret;
-	int kill = 1;
+	int kill = 1, forcekill;
 	struct page *hpage = compound_head(p);
 	struct page *ppage;
 
@@ -888,7 +888,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * be called inside page lock (it's recommended but not enforced).
 	 */
 	mapping = page_mapping(hpage);
-	if (!PageDirty(hpage) && mapping &&
+	if (!(flags & MF_MUST_KILL) && !PageDirty(hpage) && mapping &&
 	    mapping_cap_writeback_dirty(mapping)) {
 		if (page_mkclean(hpage)) {
 			SetPageDirty(hpage);
@@ -965,12 +965,14 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * Now that the dirty bit has been propagated to the
 	 * struct page and all unmaps done we can decide if
 	 * killing is needed or not.  Only kill when the page
-	 * was dirty, otherwise the tokill list is merely
+	 * was dirty or the process is not restartable,
+	 * otherwise the tokill list is merely
 	 * freed.  When there was a problem unmapping earlier
 	 * use a more force-full uncatchable kill to prevent
 	 * any accesses to the poisoned memory.
 	 */
-	kill_procs(&tokill, !!PageDirty(ppage), trapno,
+	forcekill = PageDirty(ppage) || (flags & MF_MUST_KILL);
+	kill_procs(&tokill, forcekill, trapno,
 		      ret != SWAP_SUCCESS, p, pfn, flags);
 
 	return ret;
@@ -1431,8 +1433,8 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	/* Keep page count to indicate a given hugepage is isolated. */
 
 	list_add(&hpage->lru, &pagelist);
-	ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0,
-				true);
+	ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, false,
+				MIGRATE_SYNC);
 	if (ret) {
 		struct page *page1, *page2;
 		list_for_each_entry_safe(page1, page2, &pagelist, lru)
@@ -1561,7 +1563,7 @@ int soft_offline_page(struct page *page, int flags)
 					    page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
 		ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
-							0, MIGRATE_SYNC);
+							false, MIGRATE_SYNC);
 		if (ret) {
 			putback_lru_pages(&pagelist);
 			pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index b19569137529..bf5b485ecd31 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -607,27 +607,6 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 	return first;
 }
 
-/* Apply policy to a single VMA */
-static int policy_vma(struct vm_area_struct *vma, struct mempolicy *new)
-{
-	int err = 0;
-	struct mempolicy *old = vma->vm_policy;
-
-	pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
-		 vma->vm_start, vma->vm_end, vma->vm_pgoff,
-		 vma->vm_ops, vma->vm_file,
-		 vma->vm_ops ? vma->vm_ops->set_policy : NULL);
-
-	if (vma->vm_ops && vma->vm_ops->set_policy)
-		err = vma->vm_ops->set_policy(vma, new);
-	if (!err) {
-		mpol_get(new);
-		vma->vm_policy = new;
-		mpol_put(old);
-	}
-	return err;
-}
-
 /* Step 2: apply policy to a range and do splits. */
 static int mbind_range(struct mm_struct *mm, unsigned long start,
 		       unsigned long end, struct mempolicy *new_pol)
@@ -676,9 +655,23 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 			if (err)
 				goto out;
 		}
-		err = policy_vma(vma, new_pol);
-		if (err)
-			goto out;
+
+		/*
+		 * Apply policy to a single VMA. The reference counting of
+		 * policy for vma_policy linkages has already been handled by
+		 * vma_merge and split_vma as necessary. If this is a shared
+		 * policy then ->set_policy will increment the reference count
+		 * for an sp node.
+		 */
+		pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
+			vma->vm_start, vma->vm_end, vma->vm_pgoff,
+			vma->vm_ops, vma->vm_file,
+			vma->vm_ops ? vma->vm_ops->set_policy : NULL);
+		if (vma->vm_ops && vma->vm_ops->set_policy) {
+			err = vma->vm_ops->set_policy(vma, new_pol);
+			if (err)
+				goto out;
+		}
 	}
 
  out:
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 9a611d3a1848..862b60822d9f 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -33,6 +33,24 @@
 void __mmu_notifier_release(struct mm_struct *mm)
 {
 	struct mmu_notifier *mn;
+	struct hlist_node *n;
+
+	/*
+	 * RCU here will block mmu_notifier_unregister until
+	 * ->release returns.
+	 */
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist)
+		/*
+		 * if ->release runs before mmu_notifier_unregister it
+		 * must be handled as it's the only way for the driver
+		 * to flush all existing sptes and stop the driver
+		 * from establishing any more sptes before all the
+		 * pages in the mm are freed.
+		 */
+		if (mn->ops->release)
+			mn->ops->release(mn, mm);
+	rcu_read_unlock();
 
 	spin_lock(&mm->mmu_notifier_mm->lock);
 	while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) {
@@ -46,23 +64,6 @@ void __mmu_notifier_release(struct mm_struct *mm)
 		 * mmu_notifier_unregister to return.
 		 */
 		hlist_del_init_rcu(&mn->hlist);
-		/*
-		 * RCU here will block mmu_notifier_unregister until
-		 * ->release returns.
-		 */
-		rcu_read_lock();
-		spin_unlock(&mm->mmu_notifier_mm->lock);
-		/*
-		 * if ->release runs before mmu_notifier_unregister it
-		 * must be handled as it's the only way for the driver
-		 * to flush all existing sptes and stop the driver
-		 * from establishing any more sptes before all the
-		 * pages in the mm are freed.
-		 */
-		if (mn->ops->release)
-			mn->ops->release(mn, mm);
-		rcu_read_unlock();
-		spin_lock(&mm->mmu_notifier_mm->lock);
 	}
 	spin_unlock(&mm->mmu_notifier_mm->lock);
 
@@ -284,16 +285,13 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
 {
 	BUG_ON(atomic_read(&mm->mm_count) <= 0);
 
-	spin_lock(&mm->mmu_notifier_mm->lock);
 	if (!hlist_unhashed(&mn->hlist)) {
-		hlist_del_rcu(&mn->hlist);
-
 		/*
 		 * RCU here will force exit_mmap to wait ->release to finish
 		 * before freeing the pages.
 		 */
 		rcu_read_lock();
-		spin_unlock(&mm->mmu_notifier_mm->lock);
+
 		/*
 		 * exit_mmap will block in mmu_notifier_release to
 		 * guarantee ->release is called before freeing the
@@ -302,8 +300,11 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
 		if (mn->ops->release)
 			mn->ops->release(mn, mm);
 		rcu_read_unlock();
-	} else
+
+		spin_lock(&mm->mmu_notifier_mm->lock);
+		hlist_del_rcu(&mn->hlist);
 		spin_unlock(&mm->mmu_notifier_mm->lock);
+	}
 
 	/*
 	 * Wait any running method to finish, of course including
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 1983fb1c7026..218e6f95d44f 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -105,27 +105,35 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end)
 		__free_pages_bootmem(pfn_to_page(i), 0);
 }
 
+static unsigned long __init __free_memory_core(phys_addr_t start,
+				 phys_addr_t end)
+{
+	unsigned long start_pfn = PFN_UP(start);
+	unsigned long end_pfn = min_t(unsigned long,
+				      PFN_DOWN(end), max_low_pfn);
+
+	if (start_pfn > end_pfn)
+		return 0;
+
+	__free_pages_memory(start_pfn, end_pfn);
+
+	return end_pfn - start_pfn;
+}
+
 unsigned long __init free_low_memory_core_early(int nodeid)
 {
 	unsigned long count = 0;
-	phys_addr_t start, end;
+	phys_addr_t start, end, size;
 	u64 i;
 
-	/* free reserved array temporarily so that it's treated as free area */
-	memblock_free_reserved_regions();
-
-	for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL) {
-		unsigned long start_pfn = PFN_UP(start);
-		unsigned long end_pfn = min_t(unsigned long,
-					      PFN_DOWN(end), max_low_pfn);
-		if (start_pfn < end_pfn) {
-			__free_pages_memory(start_pfn, end_pfn);
-			count += end_pfn - start_pfn;
-		}
-	}
+	for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL)
+		count += __free_memory_core(start, end);
+
+	/* free range that is used for reserved array if we allocate it */
+	size = get_allocated_memblock_reserved_regions_info(&start);
+	if (size)
+		count += __free_memory_core(start, start + size);
 
-	/* put region array back? */
-	memblock_reserve_reserved_regions();
 	return count;
 }
 
diff --git a/mm/shmem.c b/mm/shmem.c
index e281f0658cb8..2910f0d58c46 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1365,6 +1365,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	struct splice_pipe_desc spd = {
 		.pages = pages,
 		.partial = partial,
+		.nr_pages_max = PIPE_DEF_BUFFERS,
 		.flags = flags,
 		.ops = &page_cache_pipe_buf_ops,
 		.spd_release = spd_release_page,
@@ -1453,7 +1454,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	if (spd.nr_pages)
 		error = splice_to_pipe(pipe, &spd);
 
-	splice_shrink_spd(pipe, &spd);
+	splice_shrink_spd(&spd);
 
 	if (error > 0) {
 		*ppos += error;
diff --git a/mm/slub.c b/mm/slub.c
index 80848cd3901c..71de9b5685fa 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1514,15 +1514,19 @@ static inline void *acquire_slab(struct kmem_cache *s,
 		freelist = page->freelist;
 		counters = page->counters;
 		new.counters = counters;
-		if (mode)
+		if (mode) {
 			new.inuse = page->objects;
+			new.freelist = NULL;
+		} else {
+			new.freelist = freelist;
+		}
 
 		VM_BUG_ON(new.frozen);
 		new.frozen = 1;
 
 	} while (!__cmpxchg_double_slab(s, page,
 			freelist, counters,
-			NULL, new.counters,
+			new.freelist, new.counters,
 			"lock and freeze"));
 
 	remove_partial(n, page);
@@ -1564,7 +1568,6 @@ static void *get_partial_node(struct kmem_cache *s,
 			object = t;
 			available =  page->objects - page->inuse;
 		} else {
-			page->freelist = t;
 			available = put_cpu_partial(s, page, 0);
 			stat(s, CPU_PARTIAL_NODE);
 		}
diff --git a/mm/swapfile.c b/mm/swapfile.c
index fafc26d1b1dc..38186d96a72b 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1924,24 +1924,20 @@ static unsigned long read_swap_header(struct swap_info_struct *p,
 
 	/*
 	 * Find out how many pages are allowed for a single swap
-	 * device. There are three limiting factors: 1) the number
+	 * device. There are two limiting factors: 1) the number
 	 * of bits for the swap offset in the swp_entry_t type, and
 	 * 2) the number of bits in the swap pte as defined by the
-	 * the different architectures, and 3) the number of free bits
-	 * in an exceptional radix_tree entry. In order to find the
+	 * different architectures. In order to find the
 	 * largest possible bit mask, a swap entry with swap type 0
 	 * and swap offset ~0UL is created, encoded to a swap pte,
 	 * decoded to a swp_entry_t again, and finally the swap
 	 * offset is extracted. This will mask all the bits from
 	 * the initial ~0UL mask that can't be encoded in either
 	 * the swp_entry_t or the architecture definition of a
-	 * swap pte.  Then the same is done for a radix_tree entry.
+	 * swap pte.
 	 */
 	maxpages = swp_offset(pte_to_swp_entry(
-			swp_entry_to_pte(swp_entry(0, ~0UL))));
-	maxpages = swp_offset(radix_to_swp_entry(
-			swp_to_radix_entry(swp_entry(0, maxpages)))) + 1;
-
+			swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
 	if (maxpages > swap_header->info.last_page) {
 		maxpages = swap_header->info.last_page + 1;
 		/* p->max is an unsigned int: don't overflow it */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 33dc256033b5..be5bc0af2e76 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -722,7 +722,7 @@ static enum page_references page_check_references(struct page *page,
 		return PAGEREF_RECLAIM;
 
 	if (referenced_ptes) {
-		if (PageAnon(page))
+		if (PageSwapBacked(page))
 			return PAGEREF_ACTIVATE;
 		/*
 		 * All mapped pages start out with page table
@@ -3013,7 +3013,10 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 		 * them before going back to sleep.
 		 */
 		set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);
-		schedule();
+
+		if (!kthread_should_stop())
+			schedule();
+
 		set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold);
 	} else {
 		if (remaining)
@@ -3279,14 +3282,17 @@ int kswapd_run(int nid)
 }
 
 /*
- * Called by memory hotplug when all memory in a node is offlined.
+ * Called by memory hotplug when all memory in a node is offlined.  Caller must
+ * hold lock_memory_hotplug().
  */
 void kswapd_stop(int nid)
 {
 	struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
 
-	if (kswapd)
+	if (kswapd) {
 		kthread_stop(kswapd);
+		NODE_DATA(nid)->kswapd = NULL;
+	}
 }
 
 static int __init kswapd_init(void)