Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few hotfixes

 - various misc updates

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (108 commits)
  mm, memory_hotplug: move movable_node to the hotplug proper
  mm, memory_hotplug: drop CONFIG_MOVABLE_NODE
  mm, memory_hotplug: drop artificial restriction on online/offline
  mm: memcontrol: account slab stats per lruvec
  mm: memcontrol: per-lruvec stats infrastructure
  mm: memcontrol: use generic mod_memcg_page_state for kmem pages
  mm: memcontrol: use the node-native slab memory counters
  mm: vmstat: move slab statistics from zone to node counters
  mm/zswap.c: delete an error message for a failed memory allocation in zswap_dstmem_prepare()
  mm/zswap.c: improve a size determination in zswap_frontswap_init()
  mm/zswap.c: delete an error message for a failed memory allocation in zswap_pool_create()
  mm/swapfile.c: sort swap entries before free
  mm/oom_kill: count global and memory cgroup oom kills
  mm: per-cgroup memory reclaim stats
  mm: kmemleak: treat vm_struct as alternative reference to vmalloc'ed objects
  mm: kmemleak: factor object reference updating out of scan_block()
  mm: kmemleak: slightly reduce the size of some structures on 64-bit architectures
  mm, mempolicy: don't check cpuset seqlock where it doesn't matter
  mm, cpuset: always use seqlock when changing task's nodemask
  mm, mempolicy: simplify rebinding mempolicies when updating cpusets
  ...

11 files changed, 24 insertions, 66 deletions

diff --git a/fs/dax.c b/fs/dax.c
index 33d05aa02aad..cd8fced592d0 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1213,7 +1213,7 @@ static int dax_iomap_pte_fault(struct vm_fault *vmf,
 	case IOMAP_MAPPED:
 		if (iomap.flags & IOMAP_F_NEW) {
 			count_vm_event(PGMAJFAULT);
-			mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT);
+			count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
 			major = VM_FAULT_MAJOR;
 		}
 		error = dax_insert_mapping(mapping, iomap.bdev, iomap.dax_dev,
diff --git a/fs/dcache.c b/fs/dcache.c
index a9f995f6859e..a140fe1dbb1a 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -3546,8 +3546,6 @@ __setup("dhash_entries=", set_dhash_entries);
 
 static void __init dcache_init_early(void)
 {
-	unsigned int loop;
-
 	/* If hashes are distributed across NUMA nodes, defer
 	 * hash allocation until vmalloc space is available.
 	 */
@@ -3559,24 +3557,19 @@ static void __init dcache_init_early(void)
 					sizeof(struct hlist_bl_head),
 					dhash_entries,
 					13,
-					HASH_EARLY,
+					HASH_EARLY | HASH_ZERO,
 					&d_hash_shift,
 					&d_hash_mask,
 					0,
 					0);
-
-	for (loop = 0; loop < (1U << d_hash_shift); loop++)
-		INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
 }
 
 static void __init dcache_init(void)
 {
-	unsigned int loop;
-
-	/* 
+	/*
 	 * A constructor could be added for stable state like the lists,
 	 * but it is probably not worth it because of the cache nature
-	 * of the dcache. 
+	 * of the dcache.
 	 */
 	dentry_cache = KMEM_CACHE(dentry,
 		SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT);
@@ -3590,14 +3583,11 @@ static void __init dcache_init(void)
 					sizeof(struct hlist_bl_head),
 					dhash_entries,
 					13,
-					0,
+					HASH_ZERO,
 					&d_hash_shift,
 					&d_hash_mask,
 					0,
 					0);
-
-	for (loop = 0; loop < (1U << d_hash_shift); loop++)
-		INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
 }
 
 /* SLAB cache for __getname() consumers */
diff --git a/fs/file.c b/fs/file.c
index 1c2972e3a405..1fc7fbbb4510 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -30,21 +30,6 @@ unsigned int sysctl_nr_open_min = BITS_PER_LONG;
 unsigned int sysctl_nr_open_max =
 	__const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG;
 
-static void *alloc_fdmem(size_t size)
-{
-	/*
-	 * Very large allocations can stress page reclaim, so fall back to
-	 * vmalloc() if the allocation size will be considered "large" by the VM.
-	 */
-	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
-		void *data = kmalloc(size, GFP_KERNEL_ACCOUNT |
-				     __GFP_NOWARN | __GFP_NORETRY);
-		if (data != NULL)
-			return data;
-	}
-	return __vmalloc(size, GFP_KERNEL_ACCOUNT, PAGE_KERNEL);
-}
-
 static void __free_fdtable(struct fdtable *fdt)
 {
 	kvfree(fdt->fd);
@@ -131,13 +116,14 @@ static struct fdtable * alloc_fdtable(unsigned int nr)
 	if (!fdt)
 		goto out;
 	fdt->max_fds = nr;
-	data = alloc_fdmem(nr * sizeof(struct file *));
+	data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT);
 	if (!data)
 		goto out_fdt;
 	fdt->fd = data;
 
-	data = alloc_fdmem(max_t(size_t,
-				 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES));
+	data = kvmalloc(max_t(size_t,
+				 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES),
+				 GFP_KERNEL_ACCOUNT);
 	if (!data)
 		goto out_arr;
 	fdt->open_fds = data;
diff --git a/fs/inode.c b/fs/inode.c
index ab3b9a795c0b..5cbc8e6e9390 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1915,8 +1915,6 @@ __setup("ihash_entries=", set_ihash_entries);
  */
 void __init inode_init_early(void)
 {
-	unsigned int loop;
-
 	/* If hashes are distributed across NUMA nodes, defer
 	 * hash allocation until vmalloc space is available.
 	 */
@@ -1928,20 +1926,15 @@ void __init inode_init_early(void)
 					sizeof(struct hlist_head),
 					ihash_entries,
 					14,
-					HASH_EARLY,
+					HASH_EARLY | HASH_ZERO,
 					&i_hash_shift,
 					&i_hash_mask,
 					0,
 					0);
-
-	for (loop = 0; loop < (1U << i_hash_shift); loop++)
-		INIT_HLIST_HEAD(&inode_hashtable[loop]);
 }
 
 void __init inode_init(void)
 {
-	unsigned int loop;
-
 	/* inode slab cache */
 	inode_cachep = kmem_cache_create("inode_cache",
 					 sizeof(struct inode),
@@ -1959,14 +1952,11 @@ void __init inode_init(void)
 					sizeof(struct hlist_head),
 					ihash_entries,
 					14,
-					0,
+					HASH_ZERO,
 					&i_hash_shift,
 					&i_hash_mask,
 					0,
 					0);
-
-	for (loop = 0; loop < (1U << i_hash_shift); loop++)
-		INIT_HLIST_HEAD(&inode_hashtable[loop]);
 }
 
 void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev)
diff --git a/fs/namespace.c b/fs/namespace.c
index f70914a859a4..81f934b5d571 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -3239,7 +3239,6 @@ static void __init init_mount_tree(void)
 
 void __init mnt_init(void)
 {
-	unsigned u;
 	int err;
 
 	mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount),
@@ -3248,22 +3247,17 @@ void __init mnt_init(void)
 	mount_hashtable = alloc_large_system_hash("Mount-cache",
 				sizeof(struct hlist_head),
 				mhash_entries, 19,
-				0,
+				HASH_ZERO,
 				&m_hash_shift, &m_hash_mask, 0, 0);
 	mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache",
 				sizeof(struct hlist_head),
 				mphash_entries, 19,
-				0,
+				HASH_ZERO,
 				&mp_hash_shift, &mp_hash_mask, 0, 0);
 
 	if (!mount_hashtable || !mountpoint_hashtable)
 		panic("Failed to allocate mount hash table\n");
 
-	for (u = 0; u <= m_hash_mask; u++)
-		INIT_HLIST_HEAD(&mount_hashtable[u]);
-	for (u = 0; u <= mp_hash_mask; u++)
-		INIT_HLIST_HEAD(&mountpoint_hashtable[u]);
-
 	kernfs_init();
 
 	err = sysfs_init();
diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c
index 0c3905e0542e..6719c0be674d 100644
--- a/fs/ncpfs/mmap.c
+++ b/fs/ncpfs/mmap.c
@@ -89,7 +89,7 @@ static int ncp_file_mmap_fault(struct vm_fault *vmf)
 	 * -- nyc
 	 */
 	count_vm_event(PGMAJFAULT);
-	mem_cgroup_count_vm_event(vmf->vma->vm_mm, PGMAJFAULT);
+	count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
 	return VM_FAULT_MAJOR;
 }
 
diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c
index 564c504d6efd..74a21f6695c8 100644
--- a/fs/ocfs2/cluster/netdebug.c
+++ b/fs/ocfs2/cluster/netdebug.c
@@ -426,6 +426,7 @@ static int sc_fop_release(struct inode *inode, struct file *file)
 	struct o2net_sock_container *dummy_sc = sd->dbg_sock;
 
 	o2net_debug_del_sc(dummy_sc);
+	kfree(dummy_sc);
 	return seq_release_private(inode, file);
 }
 
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 382401d3e88f..1a1e0078ab38 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -136,7 +136,7 @@ struct inode *ocfs2_ilookup(struct super_block *sb, u64 blkno)
 struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
 			 int sysfile_type)
 {
-	int rc = 0;
+	int rc = -ESTALE;
 	struct inode *inode = NULL;
 	struct super_block *sb = osb->sb;
 	struct ocfs2_find_inode_args args;
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 44d178b8d1aa..5bb4a89f9045 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -25,6 +25,8 @@
 #ifndef _OCFS2_FS_H
 #define _OCFS2_FS_H
 
+#include <linux/magic.h>
+
 /* Version */
 #define OCFS2_MAJOR_REV_LEVEL		0
 #define OCFS2_MINOR_REV_LEVEL          	90
@@ -56,9 +58,6 @@
 #define OCFS2_MIN_BLOCKSIZE		512
 #define OCFS2_MAX_BLOCKSIZE		OCFS2_MIN_CLUSTERSIZE
 
-/* Filesystem magic number */
-#define OCFS2_SUPER_MAGIC		0x7461636f
-
 /* Object signatures */
 #define OCFS2_SUPER_BLOCK_SIGNATURE	"OCFSV2"
 #define OCFS2_INODE_SIGNATURE		"INODE01"
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 820359096c7a..d6c350ba25b9 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -631,7 +631,7 @@ static struct attribute *ocfs2_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group ocfs2_attr_group = {
+static const struct attribute_group ocfs2_attr_group = {
 	.attrs = ocfs2_attrs,
 };
 
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 6148ccd6cccf..cadcd12a3d35 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -214,6 +214,7 @@ static inline struct uffd_msg userfault_msg(unsigned long address,
  * hugepmd ranges.
  */
 static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
+					 struct vm_area_struct *vma,
 					 unsigned long address,
 					 unsigned long flags,
 					 unsigned long reason)
@@ -224,7 +225,7 @@ static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
 
 	VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
 
-	pte = huge_pte_offset(mm, address);
+	pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
 	if (!pte)
 		goto out;
 
@@ -243,6 +244,7 @@ out:
 }
 #else
 static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
+					 struct vm_area_struct *vma,
 					 unsigned long address,
 					 unsigned long flags,
 					 unsigned long reason)
@@ -448,7 +450,8 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 		must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags,
 						  reason);
 	else
-		must_wait = userfaultfd_huge_must_wait(ctx, vmf->address,
+		must_wait = userfaultfd_huge_must_wait(ctx, vmf->vma,
+						       vmf->address,
 						       vmf->flags, reason);
 	up_read(&mm->mmap_sem);
 
@@ -1114,11 +1117,6 @@ static ssize_t userfaultfd_read(struct file *file, char __user *buf,
 static void __wake_userfault(struct userfaultfd_ctx *ctx,
 			     struct userfaultfd_wake_range *range)
 {
-	unsigned long start, end;
-
-	start = range->start;
-	end = range->start + range->len;
-
 	spin_lock(&ctx->fault_pending_wqh.lock);
 	/* wake all in the range and autoremove */
 	if (waitqueue_active(&ctx->fault_pending_wqh))