Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "16 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm/devm_memremap_pages: fix final page put race
  PCI/P2PDMA: track pgmap references per resource, not globally
  lib/genalloc: introduce chunk owners
  PCI/P2PDMA: fix the gen_pool_add_virt() failure path
  mm/devm_memremap_pages: introduce devm_memunmap_pages
  drivers/base/devres: introduce devm_release_action()
  mm/vmscan.c: fix trying to reclaim unevictable LRU page
  coredump: fix race condition between collapse_huge_page() and core dumping
  mm/mlock.c: change count_mm_mlocked_page_nr return type
  mm: mmu_gather: remove __tlb_reset_range() for force flush
  fs/ocfs2: fix race in ocfs2_dentry_attach_lock()
  mm/vmscan.c: fix recent_rotated history
  mm/mlock.c: mlockall error for flag MCL_ONFAULT
  scripts/decode_stacktrace.sh: prefix addr2line with $CROSS_COMPILE
  mm/list_lru.c: fix memory leak in __memcg_init_list_lru_node
  mm: memcontrol: don't batch updates of local VM stats and events

5 files changed, 80 insertions, 14 deletions

diff --git a/include/linux/device.h b/include/linux/device.h
index e85264fb6616..848fc71c6ba6 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -713,6 +713,7 @@ void __iomem *devm_of_iomap(struct device *dev,
 /* 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 dd0a452373e7..a337313e064f 100644
--- a/include/linux/genalloc.h
+++ b/include/linux/genalloc.h
@@ -75,6 +75,7 @@ struct gen_pool_chunk {
 	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 @@ struct genpool_data_fixed {
 
 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 @@ static inline int gen_pool_add(struct gen_pool *pool, unsigned long addr,
 	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 edf9e8f32d70..1dcb763bb610 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -117,9 +117,12 @@ struct memcg_shrinker_map {
 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 @@ struct mem_cgroup {
 	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(struct mem_cgroup *memcg, int idx)
 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 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 						    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 f0628660d541..1732dea030b2 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -81,6 +81,7 @@ typedef void (*dev_page_free_t)(struct page *page, void *data);
  * @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 dev_pagemap {
 	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 @@ struct dev_pagemap {
 
 #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 @@ static inline void *devm_memremap_pages(struct device *dev,
 	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 a3fda9f024c3..4a7944078cc3 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -54,6 +54,10 @@ static inline void mmdrop(struct mm_struct *mm)
  * 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