Merge branch 'akpm' (patches from Andrew)

Merge fixes from Andrew Morton:
 "22 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (22 commits)
  epoll: restrict EPOLLEXCLUSIVE to POLLIN and POLLOUT
  radix-tree: fix oops after radix_tree_iter_retry
  MAINTAINERS: trim the file triggers for ABI/API
  dax: dirty inode only if required
  thp: make deferred_split_scan() work again
  mm: replace vma_lock_anon_vma with anon_vma_lock_read/write
  ocfs2/dlm: clear refmap bit of recovery lock while doing local recovery cleanup
  um: asm/page.h: remove the pte_high member from struct pte_t
  mm, hugetlb: don't require CMA for runtime gigantic pages
  mm/hugetlb: fix gigantic page initialization/allocation
  mm: downgrade VM_BUG in isolate_lru_page() to warning
  mempolicy: do not try to queue pages from !vma_migratable()
  mm, vmstat: fix wrong WQ sleep when memory reclaim doesn't make any progress
  vmstat: make vmstat_update deferrable
  mm, vmstat: make quiet_vmstat lighter
  mm/Kconfig: correct description of DEFERRED_STRUCT_PAGE_INIT
  memblock: don't mark memblock_phys_mem_size() as __init
  dump_stack: avoid potential deadlocks
  mm: validate_mm browse_rb SMP race condition
  m32r: fix build failure due to SMP and MMU
  ...

MAINTAINERS

@@ -223,9 +223,7 @@ F:	drivers/scsi/aacraid/
 
 ABI/API
 L:	linux-api@vger.kernel.org
-F:	Documentation/ABI/
 F:	include/linux/syscalls.h
-F:	include/uapi/
 F:	kernel/sys_ni.c
 
 ABIT UGURU 1,2 HARDWARE MONITOR DRIVER

arch/m32r/Kconfig

@@ -276,6 +276,7 @@ source "kernel/Kconfig.preempt"
 
 config SMP
 	bool "Symmetric multi-processing support"
+	depends on MMU
 	---help---
 	  This enables support for systems with more than one CPU. If you have
 	  a system with only one CPU, say N. If you have a system with more

arch/um/include/asm/page.h

@@ -34,21 +34,18 @@ struct page;
 
 #if defined(CONFIG_3_LEVEL_PGTABLES) && !defined(CONFIG_64BIT)
 
-typedef struct { unsigned long pte_low, pte_high; } pte_t;
+typedef struct { unsigned long pte; } pte_t;
 typedef struct { unsigned long pmd; } pmd_t;
 typedef struct { unsigned long pgd; } pgd_t;
-#define pte_val(x) ((x).pte_low | ((unsigned long long) (x).pte_high << 32))
-
-#define pte_get_bits(pte, bits) ((pte).pte_low & (bits))
-#define pte_set_bits(pte, bits) ((pte).pte_low |= (bits))
-#define pte_clear_bits(pte, bits) ((pte).pte_low &= ~(bits))
-#define pte_copy(to, from) ({ (to).pte_high = (from).pte_high; \
-			      smp_wmb(); \
-			      (to).pte_low = (from).pte_low; })
-#define pte_is_zero(pte) (!((pte).pte_low & ~_PAGE_NEWPAGE) && !(pte).pte_high)
-#define pte_set_val(pte, phys, prot) \
-	({ (pte).pte_high = (phys) >> 32; \
-	   (pte).pte_low = (phys) | pgprot_val(prot); })
+#define pte_val(p) ((p).pte)
+
+#define pte_get_bits(p, bits) ((p).pte & (bits))
+#define pte_set_bits(p, bits) ((p).pte |= (bits))
+#define pte_clear_bits(p, bits) ((p).pte &= ~(bits))
+#define pte_copy(to, from) ({ (to).pte = (from).pte; })
+#define pte_is_zero(p) (!((p).pte & ~_PAGE_NEWPAGE))
+#define pte_set_val(p, phys, prot) \
+	({ (p).pte = (phys) | pgprot_val(prot); })
 
 #define pmd_val(x)	((x).pmd)
 #define __pmd(x) ((pmd_t) { (x) } )

arch/x86/mm/hugetlbpage.c

@@ -173,10 +173,10 @@ static __init int setup_hugepagesz(char *opt)
 }
 __setup("hugepagesz=", setup_hugepagesz);
 
-#ifdef CONFIG_CMA
+#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
 static __init int gigantic_pages_init(void)
 {
-	/* With CMA we can allocate gigantic pages at runtime */
+	/* With compaction or CMA we can allocate gigantic pages at runtime */
 	if (cpu_has_gbpages && !size_to_hstate(1UL << PUD_SHIFT))
 		hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT);
 	return 0;

fs/block_dev.c

@@ -1730,6 +1730,12 @@ static int blkdev_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	return __dax_fault(vma, vmf, blkdev_get_block, NULL);
 }
 
+static int blkdev_dax_pfn_mkwrite(struct vm_area_struct *vma,
+		struct vm_fault *vmf)
+{
+	return dax_pfn_mkwrite(vma, vmf);
+}
+
 static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 		pmd_t *pmd, unsigned int flags)
 {
@@ -1739,7 +1745,7 @@ static int blkdev_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 static const struct vm_operations_struct blkdev_dax_vm_ops = {
 	.fault		= blkdev_dax_fault,
 	.pmd_fault	= blkdev_dax_pmd_fault,
-	.pfn_mkwrite	= blkdev_dax_fault,
+	.pfn_mkwrite	= blkdev_dax_pfn_mkwrite,
 };
 
 static const struct vm_operations_struct blkdev_default_vm_ops = {

fs/dax.c

@@ -358,7 +358,8 @@ static int dax_radix_entry(struct address_space *mapping, pgoff_t index,
 	void *entry;
 
 	WARN_ON_ONCE(pmd_entry && !dirty);
-	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+	if (dirty)
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 
 	spin_lock_irq(&mapping->tree_lock);
 

fs/eventpoll.c

@@ -94,6 +94,11 @@
 /* Epoll private bits inside the event mask */
 #define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE)
 
+#define EPOLLINOUT_BITS (POLLIN | POLLOUT)
+
+#define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | POLLERR | POLLHUP | \
+				EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE)
+
 /* Maximum number of nesting allowed inside epoll sets */
 #define EP_MAX_NESTS 4
 
@@ -1068,7 +1073,22 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 	 * wait list.
 	 */
 	if (waitqueue_active(&ep->wq)) {
-		ewake = 1;
+		if ((epi->event.events & EPOLLEXCLUSIVE) &&
+					!((unsigned long)key & POLLFREE)) {
+			switch ((unsigned long)key & EPOLLINOUT_BITS) {
+			case POLLIN:
+				if (epi->event.events & POLLIN)
+					ewake = 1;
+				break;
+			case POLLOUT:
+				if (epi->event.events & POLLOUT)
+					ewake = 1;
+				break;
+			case 0:
+				ewake = 1;
+				break;
+			}
+		}
 		wake_up_locked(&ep->wq);
 	}
 	if (waitqueue_active(&ep->poll_wait))
@@ -1875,9 +1895,13 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	 * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation.
 	 * Also, we do not currently supported nested exclusive wakeups.
 	 */
-	if ((epds.events & EPOLLEXCLUSIVE) && (op == EPOLL_CTL_MOD ||
-		(op == EPOLL_CTL_ADD && is_file_epoll(tf.file))))
-		goto error_tgt_fput;
+	if (epds.events & EPOLLEXCLUSIVE) {
+		if (op == EPOLL_CTL_MOD)
+			goto error_tgt_fput;
+		if (op == EPOLL_CTL_ADD && (is_file_epoll(tf.file) ||
+				(epds.events & ~EPOLLEXCLUSIVE_OK_BITS)))
+			goto error_tgt_fput;
+	}
 
 	/*
 	 * At this point it is safe to assume that the "private_data" contains
@@ -1950,8 +1974,10 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 		break;
 	case EPOLL_CTL_MOD:
 		if (epi) {
-			epds.events |= POLLERR | POLLHUP;
-			error = ep_modify(ep, epi, &epds);
+			if (!(epi->event.events & EPOLLEXCLUSIVE)) {
+				epds.events |= POLLERR | POLLHUP;
+				error = ep_modify(ep, epi, &epds);
+			}
 		} else
 			error = -ENOENT;
 		break;

fs/ocfs2/dlm/dlmrecovery.c

@@ -2367,6 +2367,8 @@ static void dlm_do_local_recovery_cleanup(struct dlm_ctxt *dlm, u8 dead_node)
 						break;
 					}
 				}
+				dlm_lockres_clear_refmap_bit(dlm, res,
+						dead_node);
 				spin_unlock(&res->spinlock);
 				continue;
 			}

include/linux/gfp.h

@@ -547,16 +547,16 @@ static inline bool pm_suspended_storage(void)
 }
 #endif /* CONFIG_PM_SLEEP */
 
-#ifdef CONFIG_CMA
-
+#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
 /* The below functions must be run on a range from a single zone. */
 extern int alloc_contig_range(unsigned long start, unsigned long end,
 			      unsigned migratetype);
 extern void free_contig_range(unsigned long pfn, unsigned nr_pages);
+#endif
 
+#ifdef CONFIG_CMA
 /* CMA stuff */
 extern void init_cma_reserved_pageblock(struct page *page);
-
 #endif
 
 #endif /* __LINUX_GFP_H */

include/linux/radix-tree.h

@@ -400,7 +400,7 @@ void **radix_tree_iter_retry(struct radix_tree_iter *iter)
  * @iter:	pointer to radix tree iterator
  * Returns:	current chunk size
  */
-static __always_inline unsigned
+static __always_inline long
 radix_tree_chunk_size(struct radix_tree_iter *iter)
 {
 	return iter->next_index - iter->index;
@@ -434,9 +434,9 @@ radix_tree_next_slot(void **slot, struct radix_tree_iter *iter, unsigned flags)
 			return slot + offset + 1;
 		}
 	} else {
-		unsigned size = radix_tree_chunk_size(iter) - 1;
+		long size = radix_tree_chunk_size(iter);
 
-		while (size--) {
+		while (--size > 0) {
 			slot++;
 			iter->index++;
 			if (likely(*slot))

include/linux/rmap.h

@@ -109,20 +109,6 @@ static inline void put_anon_vma(struct anon_vma *anon_vma)
 		__put_anon_vma(anon_vma);
 }
 
-static inline void vma_lock_anon_vma(struct vm_area_struct *vma)
-{
-	struct anon_vma *anon_vma = vma->anon_vma;
-	if (anon_vma)
-		down_write(&anon_vma->root->rwsem);
-}
-
-static inline void vma_unlock_anon_vma(struct vm_area_struct *vma)
-{
-	struct anon_vma *anon_vma = vma->anon_vma;
-	if (anon_vma)
-		up_write(&anon_vma->root->rwsem);
-}
-
 static inline void anon_vma_lock_write(struct anon_vma *anon_vma)
 {
 	down_write(&anon_vma->root->rwsem);

kernel/signal.c

@@ -3508,8 +3508,10 @@ static int sigsuspend(sigset_t *set)
 	current->saved_sigmask = current->blocked;
 	set_current_blocked(set);
 
-	__set_current_state(TASK_INTERRUPTIBLE);
-	schedule();
+	while (!signal_pending(current)) {
+		__set_current_state(TASK_INTERRUPTIBLE);
+		schedule();
+	}
 	set_restore_sigmask();
 	return -ERESTARTNOHAND;
 }

lib/dump_stack.c

@@ -25,6 +25,7 @@ static atomic_t dump_lock = ATOMIC_INIT(-1);
 
 asmlinkage __visible void dump_stack(void)
 {
+	unsigned long flags;
 	int was_locked;
 	int old;
 	int cpu;
@@ -33,9 +34,8 @@ asmlinkage __visible void dump_stack(void)
 	 * Permit this cpu to perform nested stack dumps while serialising
 	 * against other CPUs
 	 */
-	preempt_disable();
-
 retry:
+	local_irq_save(flags);
 	cpu = smp_processor_id();
 	old = atomic_cmpxchg(&dump_lock, -1, cpu);
 	if (old == -1) {
@@ -43,6 +43,7 @@ asmlinkage __visible void dump_stack(void)
 	} else if (old == cpu) {
 		was_locked = 1;
 	} else {
+		local_irq_restore(flags);
 		cpu_relax();
 		goto retry;
 	}
@@ -52,7 +53,7 @@ asmlinkage __visible void dump_stack(void)
 	if (!was_locked)
 		atomic_set(&dump_lock, -1);
 
-	preempt_enable();
+	local_irq_restore(flags);
 }
 #else
 asmlinkage __visible void dump_stack(void)

mm/Kconfig

@@ -624,7 +624,7 @@ config ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	bool
 
 config DEFERRED_STRUCT_PAGE_INIT
-	bool "Defer initialisation of struct pages to kswapd"
+	bool "Defer initialisation of struct pages to kthreads"
 	default n
 	depends on ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
 	depends on MEMORY_HOTPLUG
@@ -633,9 +633,10 @@ config DEFERRED_STRUCT_PAGE_INIT
 	  single thread. On very large machines this can take a considerable
 	  amount of time. If this option is set, large machines will bring up
 	  a subset of memmap at boot and then initialise the rest in parallel
-	  when kswapd starts. This has a potential performance impact on
-	  processes running early in the lifetime of the systemm until kswapd
-	  finishes the initialisation.
+	  by starting one-off "pgdatinitX" kernel thread for each node X. This
+	  has a potential performance impact on processes running early in the
+	  lifetime of the system until these kthreads finish the
+	  initialisation.
 
 config IDLE_PAGE_TRACKING
 	bool "Enable idle page tracking"

mm/backing-dev.c

@@ -989,7 +989,7 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout)
 		 * here rather than calling cond_resched().
 		 */
 		if (current->flags & PF_WQ_WORKER)
-			schedule_timeout(1);
+			schedule_timeout_uninterruptible(1);
 		else
 			cond_resched();
 

mm/huge_memory.c

@@ -3482,7 +3482,7 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 
 	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
 	/* Take pin on all head pages to avoid freeing them under us */
-	list_for_each_safe(pos, next, &list) {
+	list_for_each_safe(pos, next, &pgdata->split_queue) {
 		page = list_entry((void *)pos, struct page, mapping);
 		page = compound_head(page);
 		if (get_page_unless_zero(page)) {

mm/hugetlb.c

@@ -1001,7 +1001,7 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
 		((node = hstate_next_node_to_free(hs, mask)) || 1);	\
 		nr_nodes--)
 
-#if defined(CONFIG_CMA) && defined(CONFIG_X86_64)
+#if defined(CONFIG_X86_64) && ((defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA))
 static void destroy_compound_gigantic_page(struct page *page,
 					unsigned int order)
 {
@@ -1214,8 +1214,8 @@ void free_huge_page(struct page *page)
 
 	set_page_private(page, 0);
 	page->mapping = NULL;
-	BUG_ON(page_count(page));
-	BUG_ON(page_mapcount(page));
+	VM_BUG_ON_PAGE(page_count(page), page);
+	VM_BUG_ON_PAGE(page_mapcount(page), page);
 	restore_reserve = PagePrivate(page);
 	ClearPagePrivate(page);
 
@@ -1286,6 +1286,7 @@ static void prep_compound_gigantic_page(struct page *page, unsigned int order)
 		set_page_count(p, 0);
 		set_compound_head(p, page);
 	}
+	atomic_set(compound_mapcount_ptr(page), -1);
 }
 
 /*

mm/memblock.c

@@ -1448,7 +1448,7 @@ void __init __memblock_free_late(phys_addr_t base, phys_addr_t size)
  * Remaining API functions
  */
 
-phys_addr_t __init memblock_phys_mem_size(void)
+phys_addr_t __init_memblock memblock_phys_mem_size(void)
 {
 	return memblock.memory.total_size;
 }

mm/mempolicy.c

@@ -548,8 +548,7 @@ static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr,
 			goto retry;
 		}
 
-		if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
-			migrate_page_add(page, qp->pagelist, flags);
+		migrate_page_add(page, qp->pagelist, flags);
 	}
 	pte_unmap_unlock(pte - 1, ptl);
 	cond_resched();
@@ -625,7 +624,7 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end,
 	unsigned long endvma = vma->vm_end;
 	unsigned long flags = qp->flags;
 
-	if (vma->vm_flags & VM_PFNMAP)
+	if (!vma_migratable(vma))
 		return 1;
 
 	if (endvma > end)
@@ -644,16 +643,13 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end,
 
 	if (flags & MPOL_MF_LAZY) {
 		/* Similar to task_numa_work, skip inaccessible VMAs */
-		if (vma_migratable(vma) &&
-			vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))
+		if (vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))
 			change_prot_numa(vma, start, endvma);
 		return 1;
 	}
 
-	if ((flags & MPOL_MF_STRICT) ||
-	    ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
-	     vma_migratable(vma)))
-		/* queue pages from current vma */
+	/* queue pages from current vma */
+	if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
 		return 0;
 	return 1;
 }

mm/mmap.c

@@ -390,8 +390,9 @@ static long vma_compute_subtree_gap(struct vm_area_struct *vma)
 }
 
 #ifdef CONFIG_DEBUG_VM_RB
-static int browse_rb(struct rb_root *root)
+static int browse_rb(struct mm_struct *mm)
 {
+	struct rb_root *root = &mm->mm_rb;
 	int i = 0, j, bug = 0;
 	struct rb_node *nd, *pn = NULL;
 	unsigned long prev = 0, pend = 0;
@@ -414,12 +415,14 @@ static int browse_rb(struct rb_root *root)
 				  vma->vm_start, vma->vm_end);
 			bug = 1;
 		}
+		spin_lock(&mm->page_table_lock);
 		if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) {
 			pr_emerg("free gap %lx, correct %lx\n",
 			       vma->rb_subtree_gap,
 			       vma_compute_subtree_gap(vma));
 			bug = 1;
 		}
+		spin_unlock(&mm->page_table_lock);
 		i++;
 		pn = nd;
 		prev = vma->vm_start;
@@ -456,12 +459,16 @@ static void validate_mm(struct mm_struct *mm)
 	struct vm_area_struct *vma = mm->mmap;
 
 	while (vma) {
+		struct anon_vma *anon_vma = vma->anon_vma;
 		struct anon_vma_chain *avc;
 
-		vma_lock_anon_vma(vma);
-		list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
-			anon_vma_interval_tree_verify(avc);
-		vma_unlock_anon_vma(vma);
+		if (anon_vma) {
+			anon_vma_lock_read(anon_vma);
+			list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
+				anon_vma_interval_tree_verify(avc);
+			anon_vma_unlock_read(anon_vma);
+		}
+
 		highest_address = vma->vm_end;
 		vma = vma->vm_next;
 		i++;
@@ -475,7 +482,7 @@ static void validate_mm(struct mm_struct *mm)
 			  mm->highest_vm_end, highest_address);
 		bug = 1;
 	}
-	i = browse_rb(&mm->mm_rb);
+	i = browse_rb(mm);
 	if (i != mm->map_count) {
 		if (i != -1)
 			pr_emerg("map_count %d rb %d\n", mm->map_count, i);
@@ -2142,32 +2149,27 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns
 int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	int error;
+	int error = 0;
 
 	if (!(vma->vm_flags & VM_GROWSUP))
 		return -EFAULT;
 
-	/*
-	 * We must make sure the anon_vma is allocated
-	 * so that the anon_vma locking is not a noop.
-	 */
+	/* Guard against wrapping around to address 0. */
+	if (address < PAGE_ALIGN(address+4))
+		address = PAGE_ALIGN(address+4);
+	else
+		return -ENOMEM;
+
+	/* We must make sure the anon_vma is allocated. */
 	if (unlikely(anon_vma_prepare(vma)))
 		return -ENOMEM;
-	vma_lock_anon_vma(vma);
 
 	/*
 	 * vma->vm_start/vm_end cannot change under us because the caller
 	 * is required to hold the mmap_sem in read mode.  We need the
 	 * anon_vma lock to serialize against concurrent expand_stacks.
-	 * Also guard against wrapping around to address 0.
 	 */
-	if (address < PAGE_ALIGN(address+4))
-		address = PAGE_ALIGN(address+4);
-	else {
-		vma_unlock_anon_vma(vma);
-		return -ENOMEM;
-	}
-	error = 0;
+	anon_vma_lock_write(vma->anon_vma);
 
 	/* Somebody else might have raced and expanded it already */
 	if (address > vma->vm_end) {
@@ -2185,7 +2187,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 				 * updates, but we only hold a shared mmap_sem
 				 * lock here, so we need to protect against
 				 * concurrent vma expansions.
-				 * vma_lock_anon_vma() doesn't help here, as
+				 * anon_vma_lock_write() doesn't help here, as
 				 * we don't guarantee that all growable vmas
 				 * in a mm share the same root anon vma.
 				 * So, we reuse mm->page_table_lock to guard
@@ -2208,7 +2210,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 			}
 		}
 	}
-	vma_unlock_anon_vma(vma);
+	anon_vma_unlock_write(vma->anon_vma);
 	khugepaged_enter_vma_merge(vma, vma->vm_flags);
 	validate_mm(mm);
 	return error;
@@ -2224,25 +2226,21 @@ int expand_downwards(struct vm_area_struct *vma,
 	struct mm_struct *mm = vma->vm_mm;
 	int error;
 
-	/*
-	 * We must make sure the anon_vma is allocated
-	 * so that the anon_vma locking is not a noop.
-	 */
-	if (unlikely(anon_vma_prepare(vma)))
-		return -ENOMEM;
-
 	address &= PAGE_MASK;
 	error = security_mmap_addr(address);
 	if (error)
 		return error;
 
-	vma_lock_anon_vma(vma);
+	/* We must make sure the anon_vma is allocated. */
+	if (unlikely(anon_vma_prepare(vma)))
+		return -ENOMEM;
 
 	/*
 	 * vma->vm_start/vm_end cannot change under us because the caller
 	 * is required to hold the mmap_sem in read mode.  We need the
 	 * anon_vma lock to serialize against concurrent expand_stacks.
 	 */
+	anon_vma_lock_write(vma->anon_vma);
 
 	/* Somebody else might have raced and expanded it already */
 	if (address < vma->vm_start) {
@@ -2260,7 +2258,7 @@ int expand_downwards(struct vm_area_struct *vma,
 				 * updates, but we only hold a shared mmap_sem
 				 * lock here, so we need to protect against
 				 * concurrent vma expansions.
-				 * vma_lock_anon_vma() doesn't help here, as
+				 * anon_vma_lock_write() doesn't help here, as
 				 * we don't guarantee that all growable vmas
 				 * in a mm share the same root anon vma.
 				 * So, we reuse mm->page_table_lock to guard
@@ -2281,7 +2279,7 @@ int expand_downwards(struct vm_area_struct *vma,
 			}
 		}
 	}
-	vma_unlock_anon_vma(vma);
+	anon_vma_unlock_write(vma->anon_vma);
 	khugepaged_enter_vma_merge(vma, vma->vm_flags);
 	validate_mm(mm);
 	return error;

mm/page_alloc.c

@@ -6620,7 +6620,7 @@ bool is_pageblock_removable_nolock(struct page *page)
 	return !has_unmovable_pages(zone, page, 0, true);
 }
 
-#ifdef CONFIG_CMA
+#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)
 
 static unsigned long pfn_max_align_down(unsigned long pfn)
 {

mm/vmscan.c

@@ -1443,7 +1443,7 @@ int isolate_lru_page(struct page *page)
 	int ret = -EBUSY;
 
 	VM_BUG_ON_PAGE(!page_count(page), page);
-	VM_BUG_ON_PAGE(PageTail(page), page);
+	WARN_RATELIMIT(PageTail(page), "trying to isolate tail page");
 
 	if (PageLRU(page)) {
 		struct zone *zone = page_zone(page);

mm/vmstat.c

@@ -1396,10 +1396,15 @@ static void vmstat_update(struct work_struct *w)
 		 * Counters were updated so we expect more updates
 		 * to occur in the future. Keep on running the
 		 * update worker thread.
+		 * If we were marked on cpu_stat_off clear the flag
+		 * so that vmstat_shepherd doesn't schedule us again.
 		 */
-		queue_delayed_work_on(smp_processor_id(), vmstat_wq,
-			this_cpu_ptr(&vmstat_work),
-			round_jiffies_relative(sysctl_stat_interval));
+		if (!cpumask_test_and_clear_cpu(smp_processor_id(),
+						cpu_stat_off)) {
+			queue_delayed_work_on(smp_processor_id(), vmstat_wq,
+				this_cpu_ptr(&vmstat_work),
+				round_jiffies_relative(sysctl_stat_interval));
+		}
 	} else {
 		/*
 		 * We did not update any counters so the app may be in
@@ -1417,18 +1422,6 @@ static void vmstat_update(struct work_struct *w)
  * until the diffs stay at zero. The function is used by NOHZ and can only be
  * invoked when tick processing is not active.
  */
-void quiet_vmstat(void)
-{
-	if (system_state != SYSTEM_RUNNING)
-		return;
-
-	do {
-		if (!cpumask_test_and_set_cpu(smp_processor_id(), cpu_stat_off))
-			cancel_delayed_work(this_cpu_ptr(&vmstat_work));
-
-	} while (refresh_cpu_vm_stats(false));
-}
-
 /*
  * Check if the diffs for a certain cpu indicate that
  * an update is needed.
@@ -1452,6 +1445,30 @@ static bool need_update(int cpu)
 	return false;
 }
 
+void quiet_vmstat(void)
+{
+	if (system_state != SYSTEM_RUNNING)
+		return;
+
+	/*
+	 * If we are already in hands of the shepherd then there
+	 * is nothing for us to do here.
+	 */
+	if (cpumask_test_and_set_cpu(smp_processor_id(), cpu_stat_off))
+		return;
+
+	if (!need_update(smp_processor_id()))
+		return;
+
+	/*
+	 * Just refresh counters and do not care about the pending delayed
+	 * vmstat_update. It doesn't fire that often to matter and canceling
+	 * it would be too expensive from this path.
+	 * vmstat_shepherd will take care about that for us.
+	 */
+	refresh_cpu_vm_stats(false);
+}
+
 
 /*
  * Shepherd worker thread that checks the
@@ -1469,18 +1486,25 @@ static void vmstat_shepherd(struct work_struct *w)
 
 	get_online_cpus();
 	/* Check processors whose vmstat worker threads have been disabled */
-	for_each_cpu(cpu, cpu_stat_off)
-		if (need_update(cpu) &&
-			cpumask_test_and_clear_cpu(cpu, cpu_stat_off))
-
-			queue_delayed_work_on(cpu, vmstat_wq,
-				&per_cpu(vmstat_work, cpu), 0);
+	for_each_cpu(cpu, cpu_stat_off) {
+		struct delayed_work *dw = &per_cpu(vmstat_work, cpu);
 
+		if (need_update(cpu)) {
+			if (cpumask_test_and_clear_cpu(cpu, cpu_stat_off))
+				queue_delayed_work_on(cpu, vmstat_wq, dw, 0);
+		} else {
+			/*
+			 * Cancel the work if quiet_vmstat has put this
+			 * cpu on cpu_stat_off because the work item might
+			 * be still scheduled
+			 */
+			cancel_delayed_work(dw);
+		}
+	}
 	put_online_cpus();
 
 	schedule_delayed_work(&shepherd,
 		round_jiffies_relative(sysctl_stat_interval));
-
 }
 
 static void __init start_shepherd_timer(void)
@@ -1488,7 +1512,7 @@ static void __init start_shepherd_timer(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		INIT_DELAYED_WORK(per_cpu_ptr(&vmstat_work, cpu),
+		INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu),
 			vmstat_update);
 
 	if (!alloc_cpumask_var(&cpu_stat_off, GFP_KERNEL))