diff --git a/drivers/base/devres.c b/drivers/base/devres.c
index e038e2b..0bbb328 100644
--- a/drivers/base/devres.c
+++ b/drivers/base/devres.c
@@ -755,10 +755,32 @@
 
 	WARN_ON(devres_destroy(dev, devm_action_release, devm_action_match,
 			       &devres));
-
 }
 EXPORT_SYMBOL_GPL(devm_remove_action);
 
+/**
+ * devm_release_action() - release previously added custom action
+ * @dev: Device that owns the action
+ * @action: Function implementing the action
+ * @data: Pointer to data passed to @action implementation
+ *
+ * Releases and removes instance of @action previously added by
+ * devm_add_action().  Both action and data should match one of the
+ * existing entries.
+ */
+void devm_release_action(struct device *dev, void (*action)(void *), void *data)
+{
+	struct action_devres devres = {
+		.data = data,
+		.action = action,
+	};
+
+	WARN_ON(devres_release(dev, devm_action_release, devm_action_match,
+			       &devres));
+
+}
+EXPORT_SYMBOL_GPL(devm_release_action);
+
 /*
  * Managed kmalloc/kfree
  */
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 996d68f..8465d12 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -27,9 +27,8 @@
 	complete(&dev_dax->cmp);
 }
 
-static void dev_dax_percpu_exit(void *data)
+static void dev_dax_percpu_exit(struct percpu_ref *ref)
 {
-	struct percpu_ref *ref = data;
 	struct dev_dax *dev_dax = ref_to_dev_dax(ref);
 
 	dev_dbg(&dev_dax->dev, "%s\n", __func__);
@@ -466,18 +465,12 @@
 	if (rc)
 		return rc;
 
-	rc = devm_add_action_or_reset(dev, dev_dax_percpu_exit, &dev_dax->ref);
-	if (rc)
-		return rc;
-
 	dev_dax->pgmap.ref = &dev_dax->ref;
 	dev_dax->pgmap.kill = dev_dax_percpu_kill;
+	dev_dax->pgmap.cleanup = dev_dax_percpu_exit;
 	addr = devm_memremap_pages(dev, &dev_dax->pgmap);
-	if (IS_ERR(addr)) {
-		devm_remove_action(dev, dev_dax_percpu_exit, &dev_dax->ref);
-		percpu_ref_exit(&dev_dax->ref);
+	if (IS_ERR(addr))
 		return PTR_ERR(addr);
-	}
 
 	inode = dax_inode(dax_dev);
 	cdev = inode->i_cdev;
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 28cb44c..24d7fe7 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -303,11 +303,19 @@
 	NULL,
 };
 
-static void pmem_release_queue(void *q)
+static void __pmem_release_queue(struct percpu_ref *ref)
 {
+	struct request_queue *q;
+
+	q = container_of(ref, typeof(*q), q_usage_counter);
 	blk_cleanup_queue(q);
 }
 
+static void pmem_release_queue(void *ref)
+{
+	__pmem_release_queue(ref);
+}
+
 static void pmem_freeze_queue(struct percpu_ref *ref)
 {
 	struct request_queue *q;
@@ -399,12 +407,10 @@
 	if (!q)
 		return -ENOMEM;
 
-	if (devm_add_action_or_reset(dev, pmem_release_queue, q))
-		return -ENOMEM;
-
 	pmem->pfn_flags = PFN_DEV;
 	pmem->pgmap.ref = &q->q_usage_counter;
 	pmem->pgmap.kill = pmem_freeze_queue;
+	pmem->pgmap.cleanup = __pmem_release_queue;
 	if (is_nd_pfn(dev)) {
 		if (setup_pagemap_fsdax(dev, &pmem->pgmap))
 			return -ENOMEM;
@@ -425,6 +431,9 @@
 		pmem->pfn_flags |= PFN_MAP;
 		memcpy(&bb_res, &pmem->pgmap.res, sizeof(bb_res));
 	} else {
+		if (devm_add_action_or_reset(dev, pmem_release_queue,
+					&q->q_usage_counter))
+			return -ENOMEM;
 		addr = devm_memremap(dev, pmem->phys_addr,
 				pmem->size, ARCH_MEMREMAP_PMEM);
 		memcpy(&bb_res, &nsio->res, sizeof(bb_res));
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index 742928d..a98126a 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -20,12 +20,16 @@
 #include <linux/seq_buf.h>
 
 struct pci_p2pdma {
-	struct percpu_ref devmap_ref;
-	struct completion devmap_ref_done;
 	struct gen_pool *pool;
 	bool p2pmem_published;
 };
 
+struct p2pdma_pagemap {
+	struct dev_pagemap pgmap;
+	struct percpu_ref ref;
+	struct completion ref_done;
+};
+
 static ssize_t size_show(struct device *dev, struct device_attribute *attr,
 			 char *buf)
 {
@@ -74,41 +78,45 @@
 	.name = "p2pmem",
 };
 
+static struct p2pdma_pagemap *to_p2p_pgmap(struct percpu_ref *ref)
+{
+	return container_of(ref, struct p2pdma_pagemap, ref);
+}
+
 static void pci_p2pdma_percpu_release(struct percpu_ref *ref)
 {
-	struct pci_p2pdma *p2p =
-		container_of(ref, struct pci_p2pdma, devmap_ref);
+	struct p2pdma_pagemap *p2p_pgmap = to_p2p_pgmap(ref);
 
-	complete_all(&p2p->devmap_ref_done);
+	complete(&p2p_pgmap->ref_done);
 }
 
 static void pci_p2pdma_percpu_kill(struct percpu_ref *ref)
 {
-	/*
-	 * pci_p2pdma_add_resource() may be called multiple times
-	 * by a driver and may register the percpu_kill devm action multiple
-	 * times. We only want the first action to actually kill the
-	 * percpu_ref.
-	 */
-	if (percpu_ref_is_dying(ref))
-		return;
-
 	percpu_ref_kill(ref);
 }
 
+static void pci_p2pdma_percpu_cleanup(struct percpu_ref *ref)
+{
+	struct p2pdma_pagemap *p2p_pgmap = to_p2p_pgmap(ref);
+
+	wait_for_completion(&p2p_pgmap->ref_done);
+	percpu_ref_exit(&p2p_pgmap->ref);
+}
+
 static void pci_p2pdma_release(void *data)
 {
 	struct pci_dev *pdev = data;
+	struct pci_p2pdma *p2pdma = pdev->p2pdma;
 
-	if (!pdev->p2pdma)
+	if (!p2pdma)
 		return;
 
-	wait_for_completion(&pdev->p2pdma->devmap_ref_done);
-	percpu_ref_exit(&pdev->p2pdma->devmap_ref);
-
-	gen_pool_destroy(pdev->p2pdma->pool);
-	sysfs_remove_group(&pdev->dev.kobj, &p2pmem_group);
+	/* Flush and disable pci_alloc_p2p_mem() */
 	pdev->p2pdma = NULL;
+	synchronize_rcu();
+
+	gen_pool_destroy(p2pdma->pool);
+	sysfs_remove_group(&pdev->dev.kobj, &p2pmem_group);
 }
 
 static int pci_p2pdma_setup(struct pci_dev *pdev)
@@ -124,12 +132,6 @@
 	if (!p2p->pool)
 		goto out;
 
-	init_completion(&p2p->devmap_ref_done);
-	error = percpu_ref_init(&p2p->devmap_ref,
-			pci_p2pdma_percpu_release, 0, GFP_KERNEL);
-	if (error)
-		goto out_pool_destroy;
-
 	error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_release, pdev);
 	if (error)
 		goto out_pool_destroy;
@@ -163,6 +165,7 @@
 int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size,
 			    u64 offset)
 {
+	struct p2pdma_pagemap *p2p_pgmap;
 	struct dev_pagemap *pgmap;
 	void *addr;
 	int error;
@@ -185,18 +188,27 @@
 			return error;
 	}
 
-	pgmap = devm_kzalloc(&pdev->dev, sizeof(*pgmap), GFP_KERNEL);
-	if (!pgmap)
+	p2p_pgmap = devm_kzalloc(&pdev->dev, sizeof(*p2p_pgmap), GFP_KERNEL);
+	if (!p2p_pgmap)
 		return -ENOMEM;
 
+	init_completion(&p2p_pgmap->ref_done);
+	error = percpu_ref_init(&p2p_pgmap->ref,
+			pci_p2pdma_percpu_release, 0, GFP_KERNEL);
+	if (error)
+		goto pgmap_free;
+
+	pgmap = &p2p_pgmap->pgmap;
+
 	pgmap->res.start = pci_resource_start(pdev, bar) + offset;
 	pgmap->res.end = pgmap->res.start + size - 1;
 	pgmap->res.flags = pci_resource_flags(pdev, bar);
-	pgmap->ref = &pdev->p2pdma->devmap_ref;
+	pgmap->ref = &p2p_pgmap->ref;
 	pgmap->type = MEMORY_DEVICE_PCI_P2PDMA;
 	pgmap->pci_p2pdma_bus_offset = pci_bus_address(pdev, bar) -
 		pci_resource_start(pdev, bar);
 	pgmap->kill = pci_p2pdma_percpu_kill;
+	pgmap->cleanup = pci_p2pdma_percpu_cleanup;
 
 	addr = devm_memremap_pages(&pdev->dev, pgmap);
 	if (IS_ERR(addr)) {
@@ -204,19 +216,22 @@
 		goto pgmap_free;
 	}
 
-	error = gen_pool_add_virt(pdev->p2pdma->pool, (unsigned long)addr,
+	error = gen_pool_add_owner(pdev->p2pdma->pool, (unsigned long)addr,
 			pci_bus_address(pdev, bar) + offset,
-			resource_size(&pgmap->res), dev_to_node(&pdev->dev));
+			resource_size(&pgmap->res), dev_to_node(&pdev->dev),
+			&p2p_pgmap->ref);
 	if (error)
-		goto pgmap_free;
+		goto pages_free;
 
 	pci_info(pdev, "added peer-to-peer DMA memory %pR\n",
 		 &pgmap->res);
 
 	return 0;
 
+pages_free:
+	devm_memunmap_pages(&pdev->dev, pgmap);
 pgmap_free:
-	devm_kfree(&pdev->dev, pgmap);
+	devm_kfree(&pdev->dev, p2p_pgmap);
 	return error;
 }
 EXPORT_SYMBOL_GPL(pci_p2pdma_add_resource);
@@ -585,19 +600,30 @@
  */
 void *pci_alloc_p2pmem(struct pci_dev *pdev, size_t size)
 {
-	void *ret;
+	void *ret = NULL;
+	struct percpu_ref *ref;
 
+	/*
+	 * Pairs with synchronize_rcu() in pci_p2pdma_release() to
+	 * ensure pdev->p2pdma is non-NULL for the duration of the
+	 * read-lock.
+	 */
+	rcu_read_lock();
 	if (unlikely(!pdev->p2pdma))
-		return NULL;
+		goto out;
 
-	if (unlikely(!percpu_ref_tryget_live(&pdev->p2pdma->devmap_ref)))
-		return NULL;
+	ret = (void *)gen_pool_alloc_owner(pdev->p2pdma->pool, size,
+			(void **) &ref);
+	if (!ret)
+		goto out;
 
-	ret = (void *)gen_pool_alloc(pdev->p2pdma->pool, size);
-
-	if (unlikely(!ret))
-		percpu_ref_put(&pdev->p2pdma->devmap_ref);
-
+	if (unlikely(!percpu_ref_tryget_live(ref))) {
+		gen_pool_free(pdev->p2pdma->pool, (unsigned long) ret, size);
+		ret = NULL;
+		goto out;
+	}
+out:
+	rcu_read_unlock();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(pci_alloc_p2pmem);
@@ -610,8 +636,11 @@
  */
 void pci_free_p2pmem(struct pci_dev *pdev, void *addr, size_t size)
 {
-	gen_pool_free(pdev->p2pdma->pool, (uintptr_t)addr, size);
-	percpu_ref_put(&pdev->p2pdma->devmap_ref);
+	struct percpu_ref *ref;
+
+	gen_pool_free_owner(pdev->p2pdma->pool, (uintptr_t)addr, size,
+			(void **) &ref);
+	percpu_ref_put(ref);
 }
 EXPORT_SYMBOL_GPL(pci_free_p2pmem);
 
diff --git a/fs/ocfs2/dcache.c b/fs/ocfs2/dcache.c
index 2d01693..42a61ee 100644
--- a/fs/ocfs2/dcache.c
+++ b/fs/ocfs2/dcache.c
@@ -296,6 +296,18 @@
 
 out_attach:
 	spin_lock(&dentry_attach_lock);
+	if (unlikely(dentry->d_fsdata && !alias)) {
+		/* d_fsdata is set by a racing thread which is doing
+		 * the same thing as this thread is doing. Leave the racing
+		 * thread going ahead and we return here.
+		 */
+		spin_unlock(&dentry_attach_lock);
+		iput(dl->dl_inode);
+		ocfs2_lock_res_free(&dl->dl_lockres);
+		kfree(dl);
+		return 0;
+	}
+
 	dentry->d_fsdata = dl;
 	dl->dl_count++;
 	spin_unlock(&dentry_attach_lock);
diff --git a/include/linux/device.h b/include/linux/device.h
index e85264f..848fc71 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -713,6 +713,7 @@
 /* allows to add/remove a custom action to devres stack */
 int devm_add_action(struct device *dev, void (*action)(void *), void *data);
 void devm_remove_action(struct device *dev, void (*action)(void *), void *data);
+void devm_release_action(struct device *dev, void (*action)(void *), void *data);
 
 static inline int devm_add_action_or_reset(struct device *dev,
 					   void (*action)(void *), void *data)
diff --git a/include/linux/genalloc.h b/include/linux/genalloc.h
index dd0a452..a337313 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -75,6 +75,7 @@
 	struct list_head next_chunk;	/* next chunk in pool */
 	atomic_long_t avail;
 	phys_addr_t phys_addr;		/* physical starting address of memory chunk */
+	void *owner;			/* private data to retrieve at alloc time */
 	unsigned long start_addr;	/* start address of memory chunk */
 	unsigned long end_addr;		/* end address of memory chunk (inclusive) */
 	unsigned long bits[0];		/* bitmap for allocating memory chunk */
@@ -96,8 +97,15 @@
 
 extern struct gen_pool *gen_pool_create(int, int);
 extern phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long);
-extern int gen_pool_add_virt(struct gen_pool *, unsigned long, phys_addr_t,
-			     size_t, int);
+extern int gen_pool_add_owner(struct gen_pool *, unsigned long, phys_addr_t,
+			     size_t, int, void *);
+
+static inline int gen_pool_add_virt(struct gen_pool *pool, unsigned long addr,
+		phys_addr_t phys, size_t size, int nid)
+{
+	return gen_pool_add_owner(pool, addr, phys, size, nid, NULL);
+}
+
 /**
  * gen_pool_add - add a new chunk of special memory to the pool
  * @pool: pool to add new memory chunk to
@@ -116,12 +124,47 @@
 	return gen_pool_add_virt(pool, addr, -1, size, nid);
 }
 extern void gen_pool_destroy(struct gen_pool *);
-extern unsigned long gen_pool_alloc(struct gen_pool *, size_t);
-extern unsigned long gen_pool_alloc_algo(struct gen_pool *, size_t,
-		genpool_algo_t algo, void *data);
+unsigned long gen_pool_alloc_algo_owner(struct gen_pool *pool, size_t size,
+		genpool_algo_t algo, void *data, void **owner);
+
+static inline unsigned long gen_pool_alloc_owner(struct gen_pool *pool,
+		size_t size, void **owner)
+{
+	return gen_pool_alloc_algo_owner(pool, size, pool->algo, pool->data,
+			owner);
+}
+
+static inline unsigned long gen_pool_alloc_algo(struct gen_pool *pool,
+		size_t size, genpool_algo_t algo, void *data)
+{
+	return gen_pool_alloc_algo_owner(pool, size, algo, data, NULL);
+}
+
+/**
+ * gen_pool_alloc - allocate special memory from the pool
+ * @pool: pool to allocate from
+ * @size: number of bytes to allocate from the pool
+ *
+ * Allocate the requested number of bytes from the specified pool.
+ * Uses the pool allocation function (with first-fit algorithm by default).
+ * Can not be used in NMI handler on architectures without
+ * NMI-safe cmpxchg implementation.
+ */
+static inline unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
+{
+	return gen_pool_alloc_algo(pool, size, pool->algo, pool->data);
+}
+
 extern void *gen_pool_dma_alloc(struct gen_pool *pool, size_t size,
 		dma_addr_t *dma);
-extern void gen_pool_free(struct gen_pool *, unsigned long, size_t);
+extern void gen_pool_free_owner(struct gen_pool *pool, unsigned long addr,
+		size_t size, void **owner);
+static inline void gen_pool_free(struct gen_pool *pool, unsigned long addr,
+                size_t size)
+{
+	gen_pool_free_owner(pool, addr, size, NULL);
+}
+
 extern void gen_pool_for_each_chunk(struct gen_pool *,
 	void (*)(struct gen_pool *, struct gen_pool_chunk *, void *), void *);
 extern size_t gen_pool_avail(struct gen_pool *);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index edf9e8f..1dcb763 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -117,9 +117,12 @@
 struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
 
+	/* Legacy local VM stats */
+	struct lruvec_stat __percpu *lruvec_stat_local;
+
+	/* Subtree VM stats (batched updates) */
 	struct lruvec_stat __percpu *lruvec_stat_cpu;
 	atomic_long_t		lruvec_stat[NR_VM_NODE_STAT_ITEMS];
-	atomic_long_t		lruvec_stat_local[NR_VM_NODE_STAT_ITEMS];
 
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 
@@ -265,17 +268,18 @@
 	atomic_t		moving_account;
 	struct task_struct	*move_lock_task;
 
-	/* memory.stat */
+	/* Legacy local VM stats and events */
+	struct memcg_vmstats_percpu __percpu *vmstats_local;
+
+	/* Subtree VM stats and events (batched updates) */
 	struct memcg_vmstats_percpu __percpu *vmstats_percpu;
 
 	MEMCG_PADDING(_pad2_);
 
 	atomic_long_t		vmstats[MEMCG_NR_STAT];
-	atomic_long_t		vmstats_local[MEMCG_NR_STAT];
-
 	atomic_long_t		vmevents[NR_VM_EVENT_ITEMS];
-	atomic_long_t		vmevents_local[NR_VM_EVENT_ITEMS];
 
+	/* memory.events */
 	atomic_long_t		memory_events[MEMCG_NR_MEMORY_EVENTS];
 
 	unsigned long		socket_pressure;
@@ -567,7 +571,11 @@
 static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg,
 						   int idx)
 {
-	long x = atomic_long_read(&memcg->vmstats_local[idx]);
+	long x = 0;
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		x += per_cpu(memcg->vmstats_local->stat[idx], cpu);
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;
@@ -641,13 +649,15 @@
 						    enum node_stat_item idx)
 {
 	struct mem_cgroup_per_node *pn;
-	long x;
+	long x = 0;
+	int cpu;
 
 	if (mem_cgroup_disabled())
 		return node_page_state(lruvec_pgdat(lruvec), idx);
 
 	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	x = atomic_long_read(&pn->lruvec_stat_local[idx]);
+	for_each_possible_cpu(cpu)
+		x += per_cpu(pn->lruvec_stat_local->count[idx], cpu);
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index f062866..1732dea 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -81,6 +81,7 @@
  * @res: physical address range covered by @ref
  * @ref: reference count that pins the devm_memremap_pages() mapping
  * @kill: callback to transition @ref to the dead state
+ * @cleanup: callback to wait for @ref to be idle and reap it
  * @dev: host device of the mapping for debug
  * @data: private data pointer for page_free()
  * @type: memory type: see MEMORY_* in memory_hotplug.h
@@ -92,6 +93,7 @@
 	struct resource res;
 	struct percpu_ref *ref;
 	void (*kill)(struct percpu_ref *ref);
+	void (*cleanup)(struct percpu_ref *ref);
 	struct device *dev;
 	void *data;
 	enum memory_type type;
@@ -100,6 +102,7 @@
 
 #ifdef CONFIG_ZONE_DEVICE
 void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap);
+void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap);
 struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 		struct dev_pagemap *pgmap);
 
@@ -118,6 +121,11 @@
 	return ERR_PTR(-ENXIO);
 }
 
+static inline void devm_memunmap_pages(struct device *dev,
+		struct dev_pagemap *pgmap)
+{
+}
+
 static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
 		struct dev_pagemap *pgmap)
 {
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index a3fda9f..4a79440 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -54,6 +54,10 @@
  * followed by taking the mmap_sem for writing before modifying the
  * vmas or anything the coredump pretends not to change from under it.
  *
+ * It also has to be called when mmgrab() is used in the context of
+ * the process, but then the mm_count refcount is transferred outside
+ * the context of the process to run down_write() on that pinned mm.
+ *
  * NOTE: find_extend_vma() called from GUP context is the only place
  * that can modify the "mm" (notably the vm_start/end) under mmap_sem
  * for reading and outside the context of the process, so it is also
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 1490e63..6e19707 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -95,6 +95,7 @@
 	pgmap->kill(pgmap->ref);
 	for_each_device_pfn(pfn, pgmap)
 		put_page(pfn_to_page(pfn));
+	pgmap->cleanup(pgmap->ref);
 
 	/* pages are dead and unused, undo the arch mapping */
 	align_start = res->start & ~(SECTION_SIZE - 1);
@@ -133,8 +134,8 @@
  * 2/ The altmap field may optionally be initialized, in which case altmap_valid
  *    must be set to true
  *
- * 3/ pgmap->ref must be 'live' on entry and will be killed at
- *    devm_memremap_pages_release() time, or if this routine fails.
+ * 3/ pgmap->ref must be 'live' on entry and will be killed and reaped
+ *    at devm_memremap_pages_release() time, or if this routine fails.
  *
  * 4/ res is expected to be a host memory range that could feasibly be
  *    treated as a "System RAM" range, i.e. not a device mmio range, but
@@ -156,8 +157,10 @@
 	pgprot_t pgprot = PAGE_KERNEL;
 	int error, nid, is_ram;
 
-	if (!pgmap->ref || !pgmap->kill)
+	if (!pgmap->ref || !pgmap->kill || !pgmap->cleanup) {
+		WARN(1, "Missing reference count teardown definition\n");
 		return ERR_PTR(-EINVAL);
+	}
 
 	align_start = res->start & ~(SECTION_SIZE - 1);
 	align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
@@ -168,14 +171,16 @@
 	if (conflict_pgmap) {
 		dev_WARN(dev, "Conflicting mapping in same section\n");
 		put_dev_pagemap(conflict_pgmap);
-		return ERR_PTR(-ENOMEM);
+		error = -ENOMEM;
+		goto err_array;
 	}
 
 	conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL);
 	if (conflict_pgmap) {
 		dev_WARN(dev, "Conflicting mapping in same section\n");
 		put_dev_pagemap(conflict_pgmap);
-		return ERR_PTR(-ENOMEM);
+		error = -ENOMEM;
+		goto err_array;
 	}
 
 	is_ram = region_intersects(align_start, align_size,
@@ -267,10 +272,18 @@
 	pgmap_array_delete(res);
  err_array:
 	pgmap->kill(pgmap->ref);
+	pgmap->cleanup(pgmap->ref);
+
 	return ERR_PTR(error);
 }
 EXPORT_SYMBOL_GPL(devm_memremap_pages);
 
+void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap)
+{
+	devm_release_action(dev, devm_memremap_pages_release, pgmap);
+}
+EXPORT_SYMBOL_GPL(devm_memunmap_pages);
+
 unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
 {
 	/* number of pfns from base where pfn_to_page() is valid */
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 7e85d1e..770c769 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -168,20 +168,21 @@
 EXPORT_SYMBOL(gen_pool_create);
 
 /**
- * gen_pool_add_virt - add a new chunk of special memory to the pool
+ * gen_pool_add_owner- add a new chunk of special memory to the pool
  * @pool: pool to add new memory chunk to
  * @virt: virtual starting address of memory chunk to add to pool
  * @phys: physical starting address of memory chunk to add to pool
  * @size: size in bytes of the memory chunk to add to pool
  * @nid: node id of the node the chunk structure and bitmap should be
  *       allocated on, or -1
+ * @owner: private data the publisher would like to recall at alloc time
  *
  * Add a new chunk of special memory to the specified pool.
  *
  * Returns 0 on success or a -ve errno on failure.
  */
-int gen_pool_add_virt(struct gen_pool *pool, unsigned long virt, phys_addr_t phys,
-		 size_t size, int nid)
+int gen_pool_add_owner(struct gen_pool *pool, unsigned long virt, phys_addr_t phys,
+		 size_t size, int nid, void *owner)
 {
 	struct gen_pool_chunk *chunk;
 	int nbits = size >> pool->min_alloc_order;
@@ -195,6 +196,7 @@
 	chunk->phys_addr = phys;
 	chunk->start_addr = virt;
 	chunk->end_addr = virt + size - 1;
+	chunk->owner = owner;
 	atomic_long_set(&chunk->avail, size);
 
 	spin_lock(&pool->lock);
@@ -203,7 +205,7 @@
 
 	return 0;
 }
-EXPORT_SYMBOL(gen_pool_add_virt);
+EXPORT_SYMBOL(gen_pool_add_owner);
 
 /**
  * gen_pool_virt_to_phys - return the physical address of memory
@@ -260,35 +262,20 @@
 EXPORT_SYMBOL(gen_pool_destroy);
 
 /**
- * gen_pool_alloc - allocate special memory from the pool
- * @pool: pool to allocate from
- * @size: number of bytes to allocate from the pool
- *
- * Allocate the requested number of bytes from the specified pool.
- * Uses the pool allocation function (with first-fit algorithm by default).
- * Can not be used in NMI handler on architectures without
- * NMI-safe cmpxchg implementation.
- */
-unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
-{
-	return gen_pool_alloc_algo(pool, size, pool->algo, pool->data);
-}
-EXPORT_SYMBOL(gen_pool_alloc);
-
-/**
- * gen_pool_alloc_algo - allocate special memory from the pool
+ * gen_pool_alloc_algo_owner - allocate special memory from the pool
  * @pool: pool to allocate from
  * @size: number of bytes to allocate from the pool
  * @algo: algorithm passed from caller
  * @data: data passed to algorithm
+ * @owner: optionally retrieve the chunk owner
  *
  * Allocate the requested number of bytes from the specified pool.
  * Uses the pool allocation function (with first-fit algorithm by default).
  * Can not be used in NMI handler on architectures without
  * NMI-safe cmpxchg implementation.
  */
-unsigned long gen_pool_alloc_algo(struct gen_pool *pool, size_t size,
-		genpool_algo_t algo, void *data)
+unsigned long gen_pool_alloc_algo_owner(struct gen_pool *pool, size_t size,
+		genpool_algo_t algo, void *data, void **owner)
 {
 	struct gen_pool_chunk *chunk;
 	unsigned long addr = 0;
@@ -299,6 +286,9 @@
 	BUG_ON(in_nmi());
 #endif
 
+	if (owner)
+		*owner = NULL;
+
 	if (size == 0)
 		return 0;
 
@@ -326,12 +316,14 @@
 		addr = chunk->start_addr + ((unsigned long)start_bit << order);
 		size = nbits << order;
 		atomic_long_sub(size, &chunk->avail);
+		if (owner)
+			*owner = chunk->owner;
 		break;
 	}
 	rcu_read_unlock();
 	return addr;
 }
-EXPORT_SYMBOL(gen_pool_alloc_algo);
+EXPORT_SYMBOL(gen_pool_alloc_algo_owner);
 
 /**
  * gen_pool_dma_alloc - allocate special memory from the pool for DMA usage
@@ -367,12 +359,14 @@
  * @pool: pool to free to
  * @addr: starting address of memory to free back to pool
  * @size: size in bytes of memory to free
+ * @owner: private data stashed at gen_pool_add() time
  *
  * Free previously allocated special memory back to the specified
  * pool.  Can not be used in NMI handler on architectures without
  * NMI-safe cmpxchg implementation.
  */
-void gen_pool_free(struct gen_pool *pool, unsigned long addr, size_t size)
+void gen_pool_free_owner(struct gen_pool *pool, unsigned long addr, size_t size,
+		void **owner)
 {
 	struct gen_pool_chunk *chunk;
 	int order = pool->min_alloc_order;
@@ -382,6 +376,9 @@
 	BUG_ON(in_nmi());
 #endif
 
+	if (owner)
+		*owner = NULL;
+
 	nbits = (size + (1UL << order) - 1) >> order;
 	rcu_read_lock();
 	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
@@ -392,6 +389,8 @@
 			BUG_ON(remain);
 			size = nbits << order;
 			atomic_long_add(size, &chunk->avail);
+			if (owner)
+				*owner = chunk->owner;
 			rcu_read_unlock();
 			return;
 		}
@@ -399,7 +398,7 @@
 	rcu_read_unlock();
 	BUG();
 }
-EXPORT_SYMBOL(gen_pool_free);
+EXPORT_SYMBOL(gen_pool_free_owner);
 
 /**
  * gen_pool_for_each_chunk - call func for every chunk of generic memory pool
diff --git a/mm/hmm.c b/mm/hmm.c
index c5d840e..f702a38 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -1354,9 +1354,8 @@
 	complete(&devmem->completion);
 }
 
-static void hmm_devmem_ref_exit(void *data)
+static void hmm_devmem_ref_exit(struct percpu_ref *ref)
 {
-	struct percpu_ref *ref = data;
 	struct hmm_devmem *devmem;
 
 	devmem = container_of(ref, struct hmm_devmem, ref);
@@ -1433,10 +1432,6 @@
 	if (ret)
 		return ERR_PTR(ret);
 
-	ret = devm_add_action_or_reset(device, hmm_devmem_ref_exit, &devmem->ref);
-	if (ret)
-		return ERR_PTR(ret);
-
 	size = ALIGN(size, PA_SECTION_SIZE);
 	addr = min((unsigned long)iomem_resource.end,
 		   (1UL << MAX_PHYSMEM_BITS) - 1);
@@ -1475,6 +1470,7 @@
 	devmem->pagemap.ref = &devmem->ref;
 	devmem->pagemap.data = devmem;
 	devmem->pagemap.kill = hmm_devmem_ref_kill;
+	devmem->pagemap.cleanup = hmm_devmem_ref_exit;
 
 	result = devm_memremap_pages(devmem->device, &devmem->pagemap);
 	if (IS_ERR(result))
@@ -1512,11 +1508,6 @@
 	if (ret)
 		return ERR_PTR(ret);
 
-	ret = devm_add_action_or_reset(device, hmm_devmem_ref_exit,
-			&devmem->ref);
-	if (ret)
-		return ERR_PTR(ret);
-
 	devmem->pfn_first = devmem->resource->start >> PAGE_SHIFT;
 	devmem->pfn_last = devmem->pfn_first +
 			   (resource_size(devmem->resource) >> PAGE_SHIFT);
@@ -1529,6 +1520,7 @@
 	devmem->pagemap.ref = &devmem->ref;
 	devmem->pagemap.data = devmem;
 	devmem->pagemap.kill = hmm_devmem_ref_kill;
+	devmem->pagemap.cleanup = hmm_devmem_ref_exit;
 
 	result = devm_memremap_pages(devmem->device, &devmem->pagemap);
 	if (IS_ERR(result))
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index a335f7c..0f74199 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1004,6 +1004,9 @@
 	 * handled by the anon_vma lock + PG_lock.
 	 */
 	down_write(&mm->mmap_sem);
+	result = SCAN_ANY_PROCESS;
+	if (!mmget_still_valid(mm))
+		goto out;
 	result = hugepage_vma_revalidate(mm, address, &vma);
 	if (result)
 		goto out;
diff --git a/mm/list_lru.c b/mm/list_lru.c
index e4709fd..927d85b 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -354,7 +354,7 @@
 	}
 	return 0;
 fail:
-	__memcg_destroy_list_lru_node(memcg_lrus, begin, i - 1);
+	__memcg_destroy_list_lru_node(memcg_lrus, begin, i);
 	return -ENOMEM;
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ca0bc6e..ba9138a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -691,11 +691,12 @@
 	if (mem_cgroup_disabled())
 		return;
 
+	__this_cpu_add(memcg->vmstats_local->stat[idx], val);
+
 	x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]);
 	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
 		struct mem_cgroup *mi;
 
-		atomic_long_add(x, &memcg->vmstats_local[idx]);
 		for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
 			atomic_long_add(x, &mi->vmstats[idx]);
 		x = 0;
@@ -745,11 +746,12 @@
 	__mod_memcg_state(memcg, idx, val);
 
 	/* Update lruvec */
+	__this_cpu_add(pn->lruvec_stat_local->count[idx], val);
+
 	x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
 	if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
 		struct mem_cgroup_per_node *pi;
 
-		atomic_long_add(x, &pn->lruvec_stat_local[idx]);
 		for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
 			atomic_long_add(x, &pi->lruvec_stat[idx]);
 		x = 0;
@@ -771,11 +773,12 @@
 	if (mem_cgroup_disabled())
 		return;
 
+	__this_cpu_add(memcg->vmstats_local->events[idx], count);
+
 	x = count + __this_cpu_read(memcg->vmstats_percpu->events[idx]);
 	if (unlikely(x > MEMCG_CHARGE_BATCH)) {
 		struct mem_cgroup *mi;
 
-		atomic_long_add(x, &memcg->vmevents_local[idx]);
 		for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
 			atomic_long_add(x, &mi->vmevents[idx]);
 		x = 0;
@@ -790,7 +793,12 @@
 
 static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
 {
-	return atomic_long_read(&memcg->vmevents_local[event]);
+	long x = 0;
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		x += per_cpu(memcg->vmstats_local->events[event], cpu);
+	return x;
 }
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
@@ -2191,11 +2199,9 @@
 			long x;
 
 			x = this_cpu_xchg(memcg->vmstats_percpu->stat[i], 0);
-			if (x) {
-				atomic_long_add(x, &memcg->vmstats_local[i]);
+			if (x)
 				for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
 					atomic_long_add(x, &memcg->vmstats[i]);
-			}
 
 			if (i >= NR_VM_NODE_STAT_ITEMS)
 				continue;
@@ -2205,12 +2211,10 @@
 
 				pn = mem_cgroup_nodeinfo(memcg, nid);
 				x = this_cpu_xchg(pn->lruvec_stat_cpu->count[i], 0);
-				if (x) {
-					atomic_long_add(x, &pn->lruvec_stat_local[i]);
+				if (x)
 					do {
 						atomic_long_add(x, &pn->lruvec_stat[i]);
 					} while ((pn = parent_nodeinfo(pn, nid)));
-				}
 			}
 		}
 
@@ -2218,11 +2222,9 @@
 			long x;
 
 			x = this_cpu_xchg(memcg->vmstats_percpu->events[i], 0);
-			if (x) {
-				atomic_long_add(x, &memcg->vmevents_local[i]);
+			if (x)
 				for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
 					atomic_long_add(x, &memcg->vmevents[i]);
-			}
 		}
 	}
 
@@ -4483,8 +4485,15 @@
 	if (!pn)
 		return 1;
 
+	pn->lruvec_stat_local = alloc_percpu(struct lruvec_stat);
+	if (!pn->lruvec_stat_local) {
+		kfree(pn);
+		return 1;
+	}
+
 	pn->lruvec_stat_cpu = alloc_percpu(struct lruvec_stat);
 	if (!pn->lruvec_stat_cpu) {
+		free_percpu(pn->lruvec_stat_local);
 		kfree(pn);
 		return 1;
 	}
@@ -4506,6 +4515,7 @@
 		return;
 
 	free_percpu(pn->lruvec_stat_cpu);
+	free_percpu(pn->lruvec_stat_local);
 	kfree(pn);
 }
 
@@ -4516,6 +4526,7 @@
 	for_each_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->vmstats_percpu);
+	free_percpu(memcg->vmstats_local);
 	kfree(memcg);
 }
 
@@ -4544,6 +4555,10 @@
 	if (memcg->id.id < 0)
 		goto fail;
 
+	memcg->vmstats_local = alloc_percpu(struct memcg_vmstats_percpu);
+	if (!memcg->vmstats_local)
+		goto fail;
+
 	memcg->vmstats_percpu = alloc_percpu(struct memcg_vmstats_percpu);
 	if (!memcg->vmstats_percpu)
 		goto fail;
diff --git a/mm/mlock.c b/mm/mlock.c
index 080f3b3..a90099da4 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -636,11 +636,11 @@
  * is also counted.
  * Return value: previously mlocked page counts
  */
-static int count_mm_mlocked_page_nr(struct mm_struct *mm,
+static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm,
 		unsigned long start, size_t len)
 {
 	struct vm_area_struct *vma;
-	int count = 0;
+	unsigned long count = 0;
 
 	if (mm == NULL)
 		mm = current->mm;
@@ -797,7 +797,8 @@
 	unsigned long lock_limit;
 	int ret;
 
-	if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)))
+	if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) ||
+	    flags == MCL_ONFAULT)
 		return -EINVAL;
 
 	if (!can_do_mlock())
diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c
index 99740e1..8c943a6 100644
--- a/mm/mmu_gather.c
+++ b/mm/mmu_gather.c
@@ -245,14 +245,28 @@
 {
 	/*
 	 * If there are parallel threads are doing PTE changes on same range
-	 * under non-exclusive lock(e.g., mmap_sem read-side) but defer TLB
-	 * flush by batching, a thread has stable TLB entry can fail to flush
-	 * the TLB by observing pte_none|!pte_dirty, for example so flush TLB
-	 * forcefully if we detect parallel PTE batching threads.
+	 * under non-exclusive lock (e.g., mmap_sem read-side) but defer TLB
+	 * flush by batching, one thread may end up seeing inconsistent PTEs
+	 * and result in having stale TLB entries.  So flush TLB forcefully
+	 * if we detect parallel PTE batching threads.
+	 *
+	 * However, some syscalls, e.g. munmap(), may free page tables, this
+	 * needs force flush everything in the given range. Otherwise this
+	 * may result in having stale TLB entries for some architectures,
+	 * e.g. aarch64, that could specify flush what level TLB.
 	 */
 	if (mm_tlb_flush_nested(tlb->mm)) {
+		/*
+		 * The aarch64 yields better performance with fullmm by
+		 * avoiding multiple CPUs spamming TLBI messages at the
+		 * same time.
+		 *
+		 * On x86 non-fullmm doesn't yield significant difference
+		 * against fullmm.
+		 */
+		tlb->fullmm = 1;
 		__tlb_reset_range(tlb);
-		__tlb_adjust_range(tlb, start, end - start);
+		tlb->freed_tables = 1;
 	}
 
 	tlb_flush_mmu(tlb);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7acd0af..7889f58 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1505,7 +1505,7 @@
 
 	list_for_each_entry_safe(page, next, page_list, lru) {
 		if (page_is_file_cache(page) && !PageDirty(page) &&
-		    !__PageMovable(page)) {
+		    !__PageMovable(page) && !PageUnevictable(page)) {
 			ClearPageActive(page);
 			list_move(&page->lru, &clean_pages);
 		}
@@ -1953,8 +1953,8 @@
 	if (global_reclaim(sc))
 		__count_vm_events(item, nr_reclaimed);
 	__count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
-	reclaim_stat->recent_rotated[0] = stat.nr_activate[0];
-	reclaim_stat->recent_rotated[1] = stat.nr_activate[1];
+	reclaim_stat->recent_rotated[0] += stat.nr_activate[0];
+	reclaim_stat->recent_rotated[1] += stat.nr_activate[1];
 
 	move_pages_to_lru(lruvec, &page_list);
 
diff --git a/scripts/decode_stacktrace.sh b/scripts/decode_stacktrace.sh
index bcdd45d..a7a3620 100755
--- a/scripts/decode_stacktrace.sh
+++ b/scripts/decode_stacktrace.sh
@@ -73,7 +73,7 @@
 	if [[ "${cache[$module,$address]+isset}" == "isset" ]]; then
 		local code=${cache[$module,$address]}
 	else
-		local code=$(addr2line -i -e "$objfile" "$address")
+		local code=$(${CROSS_COMPILE}addr2line -i -e "$objfile" "$address")
 		cache[$module,$address]=$code
 	fi
 
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index 280015c..076df22 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -100,7 +100,9 @@
 {
 	struct dev_pagemap *pgmap = _pgmap;
 
+	WARN_ON(!pgmap || !pgmap->ref || !pgmap->kill || !pgmap->cleanup);
 	pgmap->kill(pgmap->ref);
+	pgmap->cleanup(pgmap->ref);
 }
 
 void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)