18 files changed, 77 insertions, 62 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 38df53f828e1..9bff63cf326e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2975,6 +2975,7 @@ F:	kernel/cpuset.c
 CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
 M:	Johannes Weiner <hannes@cmpxchg.org>
 M:	Michal Hocko <mhocko@kernel.org>
+M:	Vladimir Davydov <vdavydov@virtuozzo.com>
 L:	cgroups@vger.kernel.org
 L:	linux-mm@kvack.org
 S:	Maintained
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index d8117be729a2..730d394ce5f0 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -145,7 +145,7 @@ static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
 
 	gfp = massage_gfp_flags(dev, gfp);
 
-	if (IS_ENABLED(CONFIG_DMA_CMA) && !(gfp & GFP_ATOMIC))
+	if (IS_ENABLED(CONFIG_DMA_CMA) && gfpflags_allow_blocking(gfp))
 		page = dma_alloc_from_contiguous(dev,
 					count, get_order(size));
 	if (!page)
diff --git a/arch/sh/include/uapi/asm/unistd_64.h b/arch/sh/include/uapi/asm/unistd_64.h
index e6820c86e8c7..47ebd5b5ed55 100644
--- a/arch/sh/include/uapi/asm/unistd_64.h
+++ b/arch/sh/include/uapi/asm/unistd_64.h
@@ -278,7 +278,7 @@
 #define __NR_fsetxattr		256
 #define __NR_getxattr		257
 #define __NR_lgetxattr		258
-#define __NR_fgetxattr		269
+#define __NR_fgetxattr		259
 #define __NR_listxattr		260
 #define __NR_llistxattr		261
 #define __NR_flistxattr		262
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index 2804aed3f416..25425d3f2575 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -303,6 +303,10 @@ static int memory_subsys_offline(struct device *dev)
 	if (mem->state == MEM_OFFLINE)
 		return 0;
 
+	/* Can't offline block with non-present sections */
+	if (mem->section_count != sections_per_block)
+		return -EINVAL;
+
 	return memory_block_change_state(mem, MEM_OFFLINE, MEM_ONLINE);
 }
 
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
index 73c64daa0f55..60f03b78914e 100644
--- a/fs/exofs/inode.c
+++ b/fs/exofs/inode.c
@@ -592,10 +592,7 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
 			}
 			unlock_page(page);
 		}
-		if (PageDirty(page) || PageWriteback(page))
-			*uptodate = true;
-		else
-			*uptodate = PageUptodate(page);
+		*uptodate = PageUptodate(page);
 		EXOFS_DBGMSG2("index=0x%lx uptodate=%d\n", index, *uptodate);
 		return page;
 	} else {
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
index 5c0c6b58157f..9aebffb40505 100644
--- a/fs/nfs/objlayout/objio_osd.c
+++ b/fs/nfs/objlayout/objio_osd.c
@@ -476,10 +476,7 @@ static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
 		}
 		unlock_page(page);
 	}
-	if (PageDirty(page) || PageWriteback(page))
-		*uptodate = true;
-	else
-		*uptodate = PageUptodate(page);
+	*uptodate = PageUptodate(page);
 	dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate);
 	return page;
 }
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index a03f6f433075..3123408da935 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -367,13 +367,11 @@ static int ocfs2_mknod(struct inode *dir,
 		goto leave;
 	}
 
-	status = posix_acl_create(dir, &mode, &default_acl, &acl);
+	status = posix_acl_create(dir, &inode->i_mode, &default_acl, &acl);
 	if (status) {
 		mlog_errno(status);
 		goto leave;
 	}
-	/* update inode->i_mode after mask with "umask". */
-	inode->i_mode = mode;
 
 	handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb,
 							    S_ISDIR(mode),
diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
index d0a1f99e24e3..4894c6888bc6 100644
--- a/include/linux/kmemleak.h
+++ b/include/linux/kmemleak.h
@@ -25,7 +25,7 @@
 
 #ifdef CONFIG_DEBUG_KMEMLEAK
 
-extern void kmemleak_init(void) __ref;
+extern void kmemleak_init(void) __init;
 extern void kmemleak_alloc(const void *ptr, size_t size, int min_count,
 			   gfp_t gfp) __ref;
 extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 0adedca24c5b..0e1b1540597a 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -99,7 +99,7 @@ static inline int try_stop_cpus(const struct cpumask *cpumask,
  * grabbing every spinlock (and more).  So the "read" side to such a
  * lock is anything which disables preemption.
  */
-#if defined(CONFIG_STOP_MACHINE) && defined(CONFIG_SMP)
+#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU)
 
 /**
  * stop_machine: freeze the machine on all CPUs and run this function
@@ -118,7 +118,7 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus);
 
 int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 				   const struct cpumask *cpus);
-#else	 /* CONFIG_STOP_MACHINE && CONFIG_SMP */
+#else	/* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
 
 static inline int stop_machine(cpu_stop_fn_t fn, void *data,
 				 const struct cpumask *cpus)
@@ -137,5 +137,5 @@ static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 	return stop_machine(fn, data, cpus);
 }
 
-#endif	/* CONFIG_STOP_MACHINE && CONFIG_SMP */
+#endif	/* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
 #endif	/* _LINUX_STOP_MACHINE */
diff --git a/init/Kconfig b/init/Kconfig
index c24b6f767bf0..235c7a2c0d20 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -2030,13 +2030,6 @@ config INIT_ALL_POSSIBLE
 	  it was better to provide this option than to break all the archs
 	  and have several arch maintainers pursuing me down dark alleys.
 
-config STOP_MACHINE
-	bool
-	default y
-	depends on (SMP && MODULE_UNLOAD) || HOTPLUG_CPU
-	help
-	  Need stop_machine() primitive.
-
 source "block/Kconfig"
 
 config PREEMPT_NOTIFIERS
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 867bc20e1ef1..a3bbaee77c58 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -531,7 +531,7 @@ static int __init cpu_stop_init(void)
 }
 early_initcall(cpu_stop_init);
 
-#ifdef CONFIG_STOP_MACHINE
+#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU)
 
 static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
 {
@@ -631,4 +631,4 @@ int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 	return ret ?: done.ret;
 }
 
-#endif	/* CONFIG_STOP_MACHINE */
+#endif	/* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 8ed2ffd963c5..7340353f8aea 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -957,8 +957,9 @@ EXPORT_SYMBOL(congestion_wait);
  * jiffies for either a BDI to exit congestion of the given @sync queue
  * or a write to complete.
  *
- * In the absence of zone congestion, cond_resched() is called to yield
- * the processor if necessary but otherwise does not sleep.
+ * In the absence of zone congestion, a short sleep or a cond_resched is
+ * performed to yield the processor and to allow other subsystems to make
+ * a forward progress.
  *
  * The return value is 0 if the sleep is for the full timeout. Otherwise,
  * it is the number of jiffies that were still remaining when the function
@@ -978,7 +979,19 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout)
 	 */
 	if (atomic_read(&nr_wb_congested[sync]) == 0 ||
 	    !test_bit(ZONE_CONGESTED, &zone->flags)) {
-		cond_resched();
+
+		/*
+		 * Memory allocation/reclaim might be called from a WQ
+		 * context and the current implementation of the WQ
+		 * concurrency control doesn't recognize that a particular
+		 * WQ is congested if the worker thread is looping without
+		 * ever sleeping. Therefore we have to do a short sleep
+		 * here rather than calling cond_resched().
+		 */
+		if (current->flags & PF_WQ_WORKER)
+			schedule_timeout(1);
+		else
+			cond_resched();
 
 		/* In case we scheduled, work out time remaining */
 		ret = timeout - (jiffies - start);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 827bb02a43a4..ef6963b577fd 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -372,8 +372,10 @@ retry_locked:
 		spin_unlock(&resv->lock);
 
 		trg = kmalloc(sizeof(*trg), GFP_KERNEL);
-		if (!trg)
+		if (!trg) {
+			kfree(nrg);
 			return -ENOMEM;
+		}
 
 		spin_lock(&resv->lock);
 		list_add(&trg->link, &resv->region_cache);
@@ -483,8 +485,16 @@ static long region_del(struct resv_map *resv, long f, long t)
 retry:
 	spin_lock(&resv->lock);
 	list_for_each_entry_safe(rg, trg, head, link) {
-		if (rg->to <= f)
+		/*
+		 * Skip regions before the range to be deleted.  file_region
+		 * ranges are normally of the form [from, to).  However, there
+		 * may be a "placeholder" entry in the map which is of the form
+		 * (from, to) with from == to.  Check for placeholder entries
+		 * at the beginning of the range to be deleted.
+		 */
+		if (rg->to <= f && (rg->to != rg->from || rg->to != f))
 			continue;
+
 		if (rg->from >= t)
 			break;
 
@@ -1886,7 +1896,10 @@ struct page *alloc_huge_page(struct vm_area_struct *vma,
 		page = __alloc_buddy_huge_page_with_mpol(h, vma, addr);
 		if (!page)
 			goto out_uncharge_cgroup;
-
+		if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) {
+			SetPagePrivate(page);
+			h->resv_huge_pages--;
+		}
 		spin_lock(&hugetlb_lock);
 		list_move(&page->lru, &h->hugepage_activelist);
 		/* Fall through */
@@ -3693,12 +3706,12 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
 			return VM_FAULT_HWPOISON_LARGE |
 				VM_FAULT_SET_HINDEX(hstate_index(h));
+	} else {
+		ptep = huge_pte_alloc(mm, address, huge_page_size(h));
+		if (!ptep)
+			return VM_FAULT_OOM;
 	}
 
-	ptep = huge_pte_alloc(mm, address, huge_page_size(h));
-	if (!ptep)
-		return VM_FAULT_OOM;
-
 	mapping = vma->vm_file->f_mapping;
 	idx = vma_hugecache_offset(h, vma, address);
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c92a65b2b4ab..e234c21a5e6c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2128,7 +2128,7 @@ done_restock:
 	 */
 	do {
 		if (page_counter_read(&memcg->memory) > memcg->high) {
-			current->memcg_nr_pages_over_high += nr_pages;
+			current->memcg_nr_pages_over_high += batch;
 			set_notify_resume(current);
 			break;
 		}
@@ -5512,11 +5512,11 @@ void mem_cgroup_uncharge_list(struct list_head *page_list)
  * mem_cgroup_replace_page - migrate a charge to another page
  * @oldpage: currently charged page
  * @newpage: page to transfer the charge to
- * @lrucare: either or both pages might be on the LRU already
  *
  * Migrate the charge from @oldpage to @newpage.
  *
  * Both pages must be locked, @newpage->mapping must be set up.
+ * Either or both pages might be on the LRU already.
  */
 void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage)
 {
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index d13a33918fa2..c12680993ff3 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -608,6 +608,8 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p,
 			continue;
 		if (unlikely(p->flags & PF_KTHREAD))
 			continue;
+		if (is_global_init(p))
+			continue;
 		if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN)
 			continue;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 17a3c66639a9..9d666df5ef95 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -3647,8 +3647,9 @@ static void show_migration_types(unsigned char type)
 {
 	static const char types[MIGRATE_TYPES] = {
 		[MIGRATE_UNMOVABLE]	= 'U',
-		[MIGRATE_RECLAIMABLE]	= 'E',
 		[MIGRATE_MOVABLE]	= 'M',
+		[MIGRATE_RECLAIMABLE]	= 'E',
+		[MIGRATE_HIGHATOMIC]	= 'H',
 #ifdef CONFIG_CMA
 		[MIGRATE_CMA]		= 'C',
 #endif
diff --git a/mm/shmem.c b/mm/shmem.c
index 9187eee4128b..2afcdbbdb685 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -843,14 +843,14 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 		list_add_tail(&info->swaplist, &shmem_swaplist);
 
 	if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
-		swap_shmem_alloc(swap);
-		shmem_delete_from_page_cache(page, swp_to_radix_entry(swap));
-
 		spin_lock(&info->lock);
-		info->swapped++;
 		shmem_recalc_inode(inode);
+		info->swapped++;
 		spin_unlock(&info->lock);
 
+		swap_shmem_alloc(swap);
+		shmem_delete_from_page_cache(page, swp_to_radix_entry(swap));
+
 		mutex_unlock(&shmem_swaplist_mutex);
 		BUG_ON(page_mapped(page));
 		swap_writepage(page, wbc);
@@ -1078,7 +1078,7 @@ repeat:
 	if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&
 	    ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
 		error = -EINVAL;
-		goto failed;
+		goto unlock;
 	}
 
 	if (page && sgp == SGP_WRITE)
@@ -1246,11 +1246,15 @@ clear:
 	/* Perhaps the file has been truncated since we checked */
 	if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&
 	    ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
+		if (alloced) {
+			ClearPageDirty(page);
+			delete_from_page_cache(page);
+			spin_lock(&info->lock);
+			shmem_recalc_inode(inode);
+			spin_unlock(&info->lock);
+		}
 		error = -EINVAL;
-		if (alloced)
-			goto trunc;
-		else
-			goto failed;
+		goto unlock;
 	}
 	*pagep = page;
 	return 0;
@@ -1258,23 +1262,13 @@ clear:
 	/*
 	 * Error recovery.
 	 */
-trunc:
-	info = SHMEM_I(inode);
-	ClearPageDirty(page);
-	delete_from_page_cache(page);
-	spin_lock(&info->lock);
-	info->alloced--;
-	inode->i_blocks -= BLOCKS_PER_PAGE;
-	spin_unlock(&info->lock);
 decused:
-	sbinfo = SHMEM_SB(inode->i_sb);
 	if (sbinfo->max_blocks)
 		percpu_counter_add(&sbinfo->used_blocks, -1);
 unacct:
 	shmem_unacct_blocks(info->flags, 1);
 failed:
-	if (swap.val && error != -EINVAL &&
-	    !shmem_confirm_swap(mapping, index, swap))
+	if (swap.val && !shmem_confirm_swap(mapping, index, swap))
 		error = -EEXIST;
 unlock:
 	if (page) {
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 879a2be23325..0d5712b0206c 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -921,8 +921,8 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat,
 #ifdef CONFIG_PROC_FS
 static char * const migratetype_names[MIGRATE_TYPES] = {
 	"Unmovable",
-	"Reclaimable",
 	"Movable",
+	"Reclaimable",
 	"HighAtomic",
 #ifdef CONFIG_CMA
 	"CMA",
@@ -1379,6 +1379,7 @@ static const struct file_operations proc_vmstat_file_operations = {
 #endif /* CONFIG_PROC_FS */
 
 #ifdef CONFIG_SMP
+static struct workqueue_struct *vmstat_wq;
 static DEFINE_PER_CPU(struct delayed_work, vmstat_work);
 int sysctl_stat_interval __read_mostly = HZ;
 static cpumask_var_t cpu_stat_off;
@@ -1391,7 +1392,7 @@ static void vmstat_update(struct work_struct *w)
 		 * to occur in the future. Keep on running the
 		 * update worker thread.
 		 */
-		schedule_delayed_work_on(smp_processor_id(),
+		queue_delayed_work_on(smp_processor_id(), vmstat_wq,
 			this_cpu_ptr(&vmstat_work),
 			round_jiffies_relative(sysctl_stat_interval));
 	} else {
@@ -1460,7 +1461,7 @@ static void vmstat_shepherd(struct work_struct *w)
 		if (need_update(cpu) &&
 			cpumask_test_and_clear_cpu(cpu, cpu_stat_off))
 
-			schedule_delayed_work_on(cpu,
+			queue_delayed_work_on(cpu, vmstat_wq,
 				&per_cpu(vmstat_work, cpu), 0);
 
 	put_online_cpus();
@@ -1549,6 +1550,7 @@ static int __init setup_vmstat(void)
 
 	start_shepherd_timer();
 	cpu_notifier_register_done();
+	vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations);