Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few misc bits

 - ocfs2

 - most(?) of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (125 commits)
  thp: fix comments of __pmd_trans_huge_lock()
  cgroup: remove unnecessary 0 check from css_from_id()
  cgroup: fix idr leak for the first cgroup root
  mm: memcontrol: fix documentation for compound parameter
  mm: memcontrol: remove BUG_ON in uncharge_list
  mm: fix build warnings in <linux/compaction.h>
  mm, thp: convert from optimistic swapin collapsing to conservative
  mm, thp: fix comment inconsistency for swapin readahead functions
  thp: update Documentation/{vm/transhuge,filesystems/proc}.txt
  shmem: split huge pages beyond i_size under memory pressure
  thp: introduce CONFIG_TRANSPARENT_HUGE_PAGECACHE
  khugepaged: add support of collapse for tmpfs/shmem pages
  shmem: make shmem_inode_info::lock irq-safe
  khugepaged: move up_read(mmap_sem) out of khugepaged_alloc_page()
  thp: extract khugepaged from mm/huge_memory.c
  shmem, thp: respect MADV_{NO,}HUGEPAGE for file mappings
  shmem: add huge pages support
  shmem: get_unmapped_area align huge page
  shmem: prepare huge= mount option and sysfs knob
  mm, rmap: account shmem thp pages
  ...

25 files changed, 198 insertions, 190 deletions

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 27c214941004..cee4cb99b8ce 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4178,7 +4178,8 @@ int extent_readpages(struct extent_io_tree *tree,
 		prefetchw(&page->flags);
 		list_del(&page->lru);
 		if (add_to_page_cache_lru(page, mapping,
-					page->index, GFP_NOFS)) {
+					page->index,
+					readahead_gfp_mask(mapping))) {
 			put_page(page);
 			continue;
 		}
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index d4890b6dc22d..579e41b350a2 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -3366,7 +3366,7 @@ readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 	struct page *page, *tpage;
 	unsigned int expected_index;
 	int rc;
-	gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
+	gfp_t gfp = readahead_gfp_mask(mapping);
 
 	INIT_LIST_HEAD(tmplist);
 
diff --git a/fs/dax.c b/fs/dax.c
index e207f8f9b700..432b9e6dd63b 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -819,16 +819,16 @@ static int dax_insert_mapping(struct address_space *mapping,
 }
 
 /**
- * __dax_fault - handle a page fault on a DAX file
+ * dax_fault - handle a page fault on a DAX file
  * @vma: The virtual memory area where the fault occurred
  * @vmf: The description of the fault
  * @get_block: The filesystem method used to translate file offsets to blocks
  *
  * When a page fault occurs, filesystems may call this helper in their
- * fault handler for DAX files. __dax_fault() assumes the caller has done all
+ * fault handler for DAX files. dax_fault() assumes the caller has done all
  * the necessary locking for the page fault to proceed successfully.
  */
-int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
+int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			get_block_t get_block)
 {
 	struct file *file = vma->vm_file;
@@ -913,33 +913,6 @@ int __dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		return VM_FAULT_SIGBUS | major;
 	return VM_FAULT_NOPAGE | major;
 }
-EXPORT_SYMBOL(__dax_fault);
-
-/**
- * dax_fault - handle a page fault on a DAX file
- * @vma: The virtual memory area where the fault occurred
- * @vmf: The description of the fault
- * @get_block: The filesystem method used to translate file offsets to blocks
- *
- * When a page fault occurs, filesystems may call this helper in their
- * fault handler for DAX files.
- */
-int dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
-	      get_block_t get_block)
-{
-	int result;
-	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
-
-	if (vmf->flags & FAULT_FLAG_WRITE) {
-		sb_start_pagefault(sb);
-		file_update_time(vma->vm_file);
-	}
-	result = __dax_fault(vma, vmf, get_block);
-	if (vmf->flags & FAULT_FLAG_WRITE)
-		sb_end_pagefault(sb);
-
-	return result;
-}
 EXPORT_SYMBOL_GPL(dax_fault);
 
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE)
@@ -967,7 +940,16 @@ static void __dax_dbg(struct buffer_head *bh, unsigned long address,
 
 #define dax_pmd_dbg(bh, address, reason)	__dax_dbg(bh, address, reason, "dax_pmd")
 
-int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
+/**
+ * dax_pmd_fault - handle a PMD fault on a DAX file
+ * @vma: The virtual memory area where the fault occurred
+ * @vmf: The description of the fault
+ * @get_block: The filesystem method used to translate file offsets to blocks
+ *
+ * When a page fault occurs, filesystems may call this helper in their
+ * pmd_fault handler for DAX files.
+ */
+int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		pmd_t *pmd, unsigned int flags, get_block_t get_block)
 {
 	struct file *file = vma->vm_file;
@@ -1119,7 +1101,7 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		 *
 		 * The PMD path doesn't have an equivalent to
 		 * dax_pfn_mkwrite(), though, so for a read followed by a
-		 * write we traverse all the way through __dax_pmd_fault()
+		 * write we traverse all the way through dax_pmd_fault()
 		 * twice.  This means we can just skip inserting a radix tree
 		 * entry completely on the initial read and just wait until
 		 * the write to insert a dirty entry.
@@ -1148,33 +1130,6 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	result = VM_FAULT_FALLBACK;
 	goto out;
 }
-EXPORT_SYMBOL_GPL(__dax_pmd_fault);
-
-/**
- * dax_pmd_fault - handle a PMD fault on a DAX file
- * @vma: The virtual memory area where the fault occurred
- * @vmf: The description of the fault
- * @get_block: The filesystem method used to translate file offsets to blocks
- *
- * When a page fault occurs, filesystems may call this helper in their
- * pmd_fault handler for DAX files.
- */
-int dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
-			pmd_t *pmd, unsigned int flags, get_block_t get_block)
-{
-	int result;
-	struct super_block *sb = file_inode(vma->vm_file)->i_sb;
-
-	if (flags & FAULT_FLAG_WRITE) {
-		sb_start_pagefault(sb);
-		file_update_time(vma->vm_file);
-	}
-	result = __dax_pmd_fault(vma, address, pmd, flags, get_block);
-	if (flags & FAULT_FLAG_WRITE)
-		sb_end_pagefault(sb);
-
-	return result;
-}
 EXPORT_SYMBOL_GPL(dax_pmd_fault);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index 868c02317b05..5efeefe17abb 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -51,7 +51,7 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	}
 	down_read(&ei->dax_sem);
 
-	ret = __dax_fault(vma, vmf, ext2_get_block);
+	ret = dax_fault(vma, vmf, ext2_get_block);
 
 	up_read(&ei->dax_sem);
 	if (vmf->flags & FAULT_FLAG_WRITE)
@@ -72,7 +72,7 @@ static int ext2_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	}
 	down_read(&ei->dax_sem);
 
-	ret = __dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block);
+	ret = dax_pmd_fault(vma, addr, pmd, flags, ext2_get_block);
 
 	up_read(&ei->dax_sem);
 	if (flags & FAULT_FLAG_WRITE)
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 4f615cdd22ca..261ac3734c58 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -202,7 +202,7 @@ static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (IS_ERR(handle))
 		result = VM_FAULT_SIGBUS;
 	else
-		result = __dax_fault(vma, vmf, ext4_dax_get_block);
+		result = dax_fault(vma, vmf, ext4_dax_get_block);
 
 	if (write) {
 		if (!IS_ERR(handle))
@@ -237,7 +237,7 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
 	if (IS_ERR(handle))
 		result = VM_FAULT_SIGBUS;
 	else
-		result = __dax_pmd_fault(vma, addr, pmd, flags,
+		result = dax_pmd_fault(vma, addr, pmd, flags,
 					 ext4_dax_get_block);
 
 	if (write) {
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index bfc7f4d30643..a81b829d56de 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -130,7 +130,7 @@ int ext4_mpage_readpages(struct address_space *mapping,
 			page = list_entry(pages->prev, struct page, lru);
 			list_del(&page->lru);
 			if (add_to_page_cache_lru(page, mapping, page->index,
-				  mapping_gfp_constraint(mapping, GFP_KERNEL)))
+				  readahead_gfp_mask(mapping)))
 				goto next_page;
 		}
 
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 8769e8349dff..ded224518978 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1002,7 +1002,8 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 			page = list_entry(pages->prev, struct page, lru);
 			list_del(&page->lru);
 			if (add_to_page_cache_lru(page, mapping,
-						  page->index, GFP_KERNEL))
+						  page->index,
+						  readahead_gfp_mask(mapping)))
 				goto next_page;
 		}
 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index fe7e83a45eff..6f9c9f6f5157 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -981,6 +981,42 @@ void inode_io_list_del(struct inode *inode)
 }
 
 /*
+ * mark an inode as under writeback on the sb
+ */
+void sb_mark_inode_writeback(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+	unsigned long flags;
+
+	if (list_empty(&inode->i_wb_list)) {
+		spin_lock_irqsave(&sb->s_inode_wblist_lock, flags);
+		if (list_empty(&inode->i_wb_list)) {
+			list_add_tail(&inode->i_wb_list, &sb->s_inodes_wb);
+			trace_sb_mark_inode_writeback(inode);
+		}
+		spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags);
+	}
+}
+
+/*
+ * clear an inode as under writeback on the sb
+ */
+void sb_clear_inode_writeback(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+	unsigned long flags;
+
+	if (!list_empty(&inode->i_wb_list)) {
+		spin_lock_irqsave(&sb->s_inode_wblist_lock, flags);
+		if (!list_empty(&inode->i_wb_list)) {
+			list_del_init(&inode->i_wb_list);
+			trace_sb_clear_inode_writeback(inode);
+		}
+		spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags);
+	}
+}
+
+/*
  * Redirty an inode: set its when-it-was dirtied timestamp and move it to the
  * furthest end of its superblock's dirty-inode list.
  *
@@ -2154,7 +2190,7 @@ EXPORT_SYMBOL(__mark_inode_dirty);
  */
 static void wait_sb_inodes(struct super_block *sb)
 {
-	struct inode *inode, *old_inode = NULL;
+	LIST_HEAD(sync_list);
 
 	/*
 	 * We need to be protected against the filesystem going from
@@ -2163,38 +2199,60 @@ static void wait_sb_inodes(struct super_block *sb)
 	WARN_ON(!rwsem_is_locked(&sb->s_umount));
 
 	mutex_lock(&sb->s_sync_lock);
-	spin_lock(&sb->s_inode_list_lock);
 
 	/*
-	 * Data integrity sync. Must wait for all pages under writeback,
-	 * because there may have been pages dirtied before our sync
-	 * call, but which had writeout started before we write it out.
-	 * In which case, the inode may not be on the dirty list, but
-	 * we still have to wait for that writeout.
+	 * Splice the writeback list onto a temporary list to avoid waiting on
+	 * inodes that have started writeback after this point.
+	 *
+	 * Use rcu_read_lock() to keep the inodes around until we have a
+	 * reference. s_inode_wblist_lock protects sb->s_inodes_wb as well as
+	 * the local list because inodes can be dropped from either by writeback
+	 * completion.
+	 */
+	rcu_read_lock();
+	spin_lock_irq(&sb->s_inode_wblist_lock);
+	list_splice_init(&sb->s_inodes_wb, &sync_list);
+
+	/*
+	 * Data integrity sync. Must wait for all pages under writeback, because
+	 * there may have been pages dirtied before our sync call, but which had
+	 * writeout started before we write it out.  In which case, the inode
+	 * may not be on the dirty list, but we still have to wait for that
+	 * writeout.
 	 */
-	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+	while (!list_empty(&sync_list)) {
+		struct inode *inode = list_first_entry(&sync_list, struct inode,
+						       i_wb_list);
 		struct address_space *mapping = inode->i_mapping;
 
+		/*
+		 * Move each inode back to the wb list before we drop the lock
+		 * to preserve consistency between i_wb_list and the mapping
+		 * writeback tag. Writeback completion is responsible to remove
+		 * the inode from either list once the writeback tag is cleared.
+		 */
+		list_move_tail(&inode->i_wb_list, &sb->s_inodes_wb);
+
+		/*
+		 * The mapping can appear untagged while still on-list since we
+		 * do not have the mapping lock. Skip it here, wb completion
+		 * will remove it.
+		 */
+		if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK))
+			continue;
+
+		spin_unlock_irq(&sb->s_inode_wblist_lock);
+
 		spin_lock(&inode->i_lock);
-		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
-		    (mapping->nrpages == 0)) {
+		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) {
 			spin_unlock(&inode->i_lock);
+
+			spin_lock_irq(&sb->s_inode_wblist_lock);
 			continue;
 		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
-		spin_unlock(&sb->s_inode_list_lock);
-
-		/*
-		 * We hold a reference to 'inode' so it couldn't have been
-		 * removed from s_inodes list while we dropped the
-		 * s_inode_list_lock.  We cannot iput the inode now as we can
-		 * be holding the last reference and we cannot iput it under
-		 * s_inode_list_lock. So we keep the reference and iput it
-		 * later.
-		 */
-		iput(old_inode);
-		old_inode = inode;
+		rcu_read_unlock();
 
 		/*
 		 * We keep the error status of individual mapping so that
@@ -2205,10 +2263,13 @@ static void wait_sb_inodes(struct super_block *sb)
 
 		cond_resched();
 
-		spin_lock(&sb->s_inode_list_lock);
+		iput(inode);
+
+		rcu_read_lock();
+		spin_lock_irq(&sb->s_inode_wblist_lock);
 	}
-	spin_unlock(&sb->s_inode_list_lock);
-	iput(old_inode);
+	spin_unlock_irq(&sb->s_inode_wblist_lock);
+	rcu_read_unlock();
 	mutex_unlock(&sb->s_sync_lock);
 }
 
diff --git a/fs/inode.c b/fs/inode.c
index 4ccbc21b30ce..e171f7b5f9e4 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -365,6 +365,7 @@ void inode_init_once(struct inode *inode)
 	INIT_HLIST_NODE(&inode->i_hash);
 	INIT_LIST_HEAD(&inode->i_devices);
 	INIT_LIST_HEAD(&inode->i_io_list);
+	INIT_LIST_HEAD(&inode->i_wb_list);
 	INIT_LIST_HEAD(&inode->i_lru);
 	address_space_init_once(&inode->i_data);
 	i_size_ordered_init(inode);
@@ -507,6 +508,7 @@ void clear_inode(struct inode *inode)
 	BUG_ON(!list_empty(&inode->i_data.private_list));
 	BUG_ON(!(inode->i_state & I_FREEING));
 	BUG_ON(inode->i_state & I_CLEAR);
+	BUG_ON(!list_empty(&inode->i_wb_list));
 	/* don't need i_lock here, no concurrent mods to i_state */
 	inode->i_state = I_FREEING | I_CLEAR;
 }
diff --git a/fs/mpage.c b/fs/mpage.c
index 37b28280ad04..2ca1f39c8cba 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -72,6 +72,8 @@ mpage_alloc(struct block_device *bdev,
 {
 	struct bio *bio;
 
+	/* Restrict the given (page cache) mask for slab allocations */
+	gfp_flags &= GFP_KERNEL;
 	bio = bio_alloc(gfp_flags, nr_vecs);
 
 	if (bio == NULL && (current->flags & PF_MEMALLOC)) {
@@ -363,7 +365,7 @@ mpage_readpages(struct address_space *mapping, struct list_head *pages,
 	sector_t last_block_in_bio = 0;
 	struct buffer_head map_bh;
 	unsigned long first_logical_block = 0;
-	gfp_t gfp = mapping_gfp_constraint(mapping, GFP_KERNEL);
+	gfp_t gfp = readahead_gfp_mask(mapping);
 
 	map_bh.b_state = 0;
 	map_bh.b_size = 0;
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index 4238eb28889f..1d67fcbf7160 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -1618,16 +1618,12 @@ static void o2net_start_connect(struct work_struct *work)
 
 	/* watch for racing with tearing a node down */
 	node = o2nm_get_node_by_num(o2net_num_from_nn(nn));
-	if (node == NULL) {
-		ret = 0;
+	if (node == NULL)
 		goto out;
-	}
 
 	mynode = o2nm_get_node_by_num(o2nm_this_node());
-	if (mynode == NULL) {
-		ret = 0;
+	if (mynode == NULL)
 		goto out;
-	}
 
 	spin_lock(&nn->nn_lock);
 	/*
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index 825136070d2c..e7b760deefae 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -347,26 +347,6 @@ static struct dentry *dlm_debugfs_root;
 #define DLM_DEBUGFS_PURGE_LIST			"purge_list"
 
 /* begin - utils funcs */
-static void dlm_debug_free(struct kref *kref)
-{
-	struct dlm_debug_ctxt *dc;
-
-	dc = container_of(kref, struct dlm_debug_ctxt, debug_refcnt);
-
-	kfree(dc);
-}
-
-static void dlm_debug_put(struct dlm_debug_ctxt *dc)
-{
-	if (dc)
-		kref_put(&dc->debug_refcnt, dlm_debug_free);
-}
-
-static void dlm_debug_get(struct dlm_debug_ctxt *dc)
-{
-	kref_get(&dc->debug_refcnt);
-}
-
 static int debug_release(struct inode *inode, struct file *file)
 {
 	free_page((unsigned long)file->private_data);
@@ -932,11 +912,9 @@ int dlm_debug_init(struct dlm_ctxt *dlm)
 		goto bail;
 	}
 
-	dlm_debug_get(dc);
 	return 0;
 
 bail:
-	dlm_debug_shutdown(dlm);
 	return -ENOMEM;
 }
 
@@ -949,7 +927,8 @@ void dlm_debug_shutdown(struct dlm_ctxt *dlm)
 		debugfs_remove(dc->debug_mle_dentry);
 		debugfs_remove(dc->debug_lockres_dentry);
 		debugfs_remove(dc->debug_state_dentry);
-		dlm_debug_put(dc);
+		kfree(dc);
+		dc = NULL;
 	}
 }
 
@@ -969,7 +948,6 @@ int dlm_create_debugfs_subroot(struct dlm_ctxt *dlm)
 		mlog_errno(-ENOMEM);
 		goto bail;
 	}
-	kref_init(&dlm->dlm_debug_ctxt->debug_refcnt);
 
 	return 0;
 bail:
diff --git a/fs/ocfs2/dlm/dlmdebug.h b/fs/ocfs2/dlm/dlmdebug.h
index 1f27c4812d1a..5ced5482e7d3 100644
--- a/fs/ocfs2/dlm/dlmdebug.h
+++ b/fs/ocfs2/dlm/dlmdebug.h
@@ -30,7 +30,6 @@ void dlm_print_one_mle(struct dlm_master_list_entry *mle);
 #ifdef CONFIG_DEBUG_FS
 
 struct dlm_debug_ctxt {
-	struct kref debug_refcnt;
 	struct dentry *debug_state_dentry;
 	struct dentry *debug_lockres_dentry;
 	struct dentry *debug_mle_dentry;
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 1eaa9100c889..83d576f6a287 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -1635,7 +1635,6 @@ int ocfs2_create_new_inode_locks(struct inode *inode)
 	int ret;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	BUG_ON(!inode);
 	BUG_ON(!ocfs2_inode_is_new(inode));
 
 	mlog(0, "Inode %llu\n", (unsigned long long)OCFS2_I(inode)->ip_blkno);
@@ -1665,10 +1664,8 @@ int ocfs2_create_new_inode_locks(struct inode *inode)
 	}
 
 	ret = ocfs2_create_new_lock(osb, &OCFS2_I(inode)->ip_open_lockres, 0, 0);
-	if (ret) {
+	if (ret)
 		mlog_errno(ret);
-		goto bail;
-	}
 
 bail:
 	return ret;
@@ -1680,8 +1677,6 @@ int ocfs2_rw_lock(struct inode *inode, int write)
 	struct ocfs2_lock_res *lockres;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	BUG_ON(!inode);
-
 	mlog(0, "inode %llu take %s RW lock\n",
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
 	     write ? "EXMODE" : "PRMODE");
@@ -1724,8 +1719,6 @@ int ocfs2_open_lock(struct inode *inode)
 	struct ocfs2_lock_res *lockres;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	BUG_ON(!inode);
-
 	mlog(0, "inode %llu take PRMODE open lock\n",
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno);
 
@@ -1749,8 +1742,6 @@ int ocfs2_try_open_lock(struct inode *inode, int write)
 	struct ocfs2_lock_res *lockres;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
-	BUG_ON(!inode);
-
 	mlog(0, "inode %llu try to take %s open lock\n",
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
 	     write ? "EXMODE" : "PRMODE");
@@ -2328,8 +2319,6 @@ int ocfs2_inode_lock_full_nested(struct inode *inode,
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct buffer_head *local_bh = NULL;
 
-	BUG_ON(!inode);
-
 	mlog(0, "inode %llu, take %s META lock\n",
 	     (unsigned long long)OCFS2_I(inode)->ip_blkno,
 	     ex ? "EXMODE" : "PRMODE");
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index d8f3fc8d2551..50cc55047443 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -145,22 +145,15 @@ int ocfs2_drop_inode(struct inode *inode);
 struct inode *ocfs2_ilookup(struct super_block *sb, u64 feoff);
 struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 feoff, unsigned flags,
 			 int sysfile_type);
-int ocfs2_inode_init_private(struct inode *inode);
 int ocfs2_inode_revalidate(struct dentry *dentry);
 void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
 			  int create_ino);
-void ocfs2_read_inode(struct inode *inode);
-void ocfs2_read_inode2(struct inode *inode, void *opaque);
-ssize_t ocfs2_rw_direct(int rw, struct file *filp, char *buf,
-			size_t size, loff_t *offp);
 void ocfs2_sync_blockdev(struct super_block *sb);
 void ocfs2_refresh_inode(struct inode *inode,
 			 struct ocfs2_dinode *fe);
 int ocfs2_mark_inode_dirty(handle_t *handle,
 			   struct inode *inode,
 			   struct buffer_head *bh);
-struct buffer_head *ocfs2_bread(struct inode *inode,
-				int block, int *err, int reada);
 
 void ocfs2_set_inode_flags(struct inode *inode);
 void ocfs2_get_inode_flags(struct ocfs2_inode_info *oi);
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index e607419cdfa4..a244f14c6b87 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -1159,10 +1159,8 @@ static int ocfs2_force_read_journal(struct inode *inode)
 	int status = 0;
 	int i;
 	u64 v_blkno, p_blkno, p_blocks, num_blocks;
-#define CONCURRENT_JOURNAL_FILL 32ULL
-	struct buffer_head *bhs[CONCURRENT_JOURNAL_FILL];
-
-	memset(bhs, 0, sizeof(struct buffer_head *) * CONCURRENT_JOURNAL_FILL);
+	struct buffer_head *bh = NULL;
+	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 
 	num_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
 	v_blkno = 0;
@@ -1174,29 +1172,32 @@ static int ocfs2_force_read_journal(struct inode *inode)
 			goto bail;
 		}
 
-		if (p_blocks > CONCURRENT_JOURNAL_FILL)
-			p_blocks = CONCURRENT_JOURNAL_FILL;
-
-		/* We are reading journal data which should not
-		 * be put in the uptodate cache */
-		status = ocfs2_read_blocks_sync(OCFS2_SB(inode->i_sb),
-						p_blkno, p_blocks, bhs);
-		if (status < 0) {
-			mlog_errno(status);
-			goto bail;
-		}
+		for (i = 0; i < p_blocks; i++, p_blkno++) {
+			bh = __find_get_block(osb->sb->s_bdev, p_blkno,
+					osb->sb->s_blocksize);
+			/* block not cached. */
+			if (!bh)
+				continue;
+
+			brelse(bh);
+			bh = NULL;
+			/* We are reading journal data which should not
+			 * be put in the uptodate cache.
+			 */
+			status = ocfs2_read_blocks_sync(osb, p_blkno, 1, &bh);
+			if (status < 0) {
+				mlog_errno(status);
+				goto bail;
+			}
 
-		for(i = 0; i < p_blocks; i++) {
-			brelse(bhs[i]);
-			bhs[i] = NULL;
+			brelse(bh);
+			bh = NULL;
 		}
 
 		v_blkno += p_blocks;
 	}
 
 bail:
-	for(i = 0; i < CONCURRENT_JOURNAL_FILL; i++)
-		brelse(bhs[i]);
 	return status;
 }
 
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 13219ed73e1d..52c07346bea3 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -735,8 +735,6 @@ static void __exit ocfs2_stack_glue_exit(void)
 {
 	memset(&locking_max_version, 0,
 	       sizeof(struct ocfs2_protocol_version));
-	locking_max_version.pv_major = 0;
-	locking_max_version.pv_minor = 0;
 	ocfs2_sysfs_exit();
 	if (ocfs2_table_header)
 		unregister_sysctl_table(ocfs2_table_header);
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 3971146228d3..603b28d6f008 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -2072,7 +2072,6 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	osb->osb_dx_seed[3] = le32_to_cpu(di->id2.i_super.s_uuid_hash);
 
 	osb->sb = sb;
-	/* Save off for ocfs2_rw_direct */
 	osb->s_sectsize_bits = blksize_bits(sector_size);
 	BUG_ON(!osb->s_sectsize_bits);
 
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index a44caabb0fc2..8f2fa94cc4f6 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -80,7 +80,7 @@ static int orangefs_readpages(struct file *file,
 		if (!add_to_page_cache(page,
 				       mapping,
 				       page->index,
-				       GFP_KERNEL)) {
+				       readahead_gfp_mask(mapping))) {
 			ret = read_one_page(page);
 			gossip_debug(GOSSIP_INODE_DEBUG,
 				"failure adding page to cache, read_one_page returned: %d\n",
diff --git a/fs/pipe.c b/fs/pipe.c
index 0d3f5165cb0b..4b32928f5426 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -21,6 +21,7 @@
 #include <linux/audit.h>
 #include <linux/syscalls.h>
 #include <linux/fcntl.h>
+#include <linux/memcontrol.h>
 
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
@@ -137,6 +138,22 @@ static void anon_pipe_buf_release(struct pipe_inode_info *pipe,
 		put_page(page);
 }
 
+static int anon_pipe_buf_steal(struct pipe_inode_info *pipe,
+			       struct pipe_buffer *buf)
+{
+	struct page *page = buf->page;
+
+	if (page_count(page) == 1) {
+		if (memcg_kmem_enabled()) {
+			memcg_kmem_uncharge(page, 0);
+			__ClearPageKmemcg(page);
+		}
+		__SetPageLocked(page);
+		return 0;
+	}
+	return 1;
+}
+
 /**
  * generic_pipe_buf_steal - attempt to take ownership of a &pipe_buffer
  * @pipe:	the pipe that the buffer belongs to
@@ -219,7 +236,7 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = {
 	.can_merge = 1,
 	.confirm = generic_pipe_buf_confirm,
 	.release = anon_pipe_buf_release,
-	.steal = generic_pipe_buf_steal,
+	.steal = anon_pipe_buf_steal,
 	.get = generic_pipe_buf_get,
 };
 
@@ -227,7 +244,7 @@ static const struct pipe_buf_operations packet_pipe_buf_ops = {
 	.can_merge = 0,
 	.confirm = generic_pipe_buf_confirm,
 	.release = anon_pipe_buf_release,
-	.steal = generic_pipe_buf_steal,
+	.steal = anon_pipe_buf_steal,
 	.get = generic_pipe_buf_get,
 };
 
@@ -405,7 +422,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 			int copied;
 
 			if (!page) {
-				page = alloc_page(GFP_HIGHUSER);
+				page = alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT);
 				if (unlikely(!page)) {
 					ret = ret ? : -ENOMEM;
 					break;
@@ -611,7 +628,7 @@ struct pipe_inode_info *alloc_pipe_info(void)
 {
 	struct pipe_inode_info *pipe;
 
-	pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL);
+	pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL_ACCOUNT);
 	if (pipe) {
 		unsigned long pipe_bufs = PIPE_DEF_BUFFERS;
 		struct user_struct *user = get_current_user();
@@ -619,7 +636,9 @@ struct pipe_inode_info *alloc_pipe_info(void)
 		if (!too_many_pipe_buffers_hard(user)) {
 			if (too_many_pipe_buffers_soft(user))
 				pipe_bufs = 1;
-			pipe->bufs = kzalloc(sizeof(struct pipe_buffer) * pipe_bufs, GFP_KERNEL);
+			pipe->bufs = kcalloc(pipe_bufs,
+					     sizeof(struct pipe_buffer),
+					     GFP_KERNEL_ACCOUNT);
 		}
 
 		if (pipe->bufs) {
@@ -1010,7 +1029,8 @@ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long nr_pages)
 	if (nr_pages < pipe->nrbufs)
 		return -EBUSY;
 
-	bufs = kcalloc(nr_pages, sizeof(*bufs), GFP_KERNEL | __GFP_NOWARN);
+	bufs = kcalloc(nr_pages, sizeof(*bufs),
+		       GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
 	if (unlikely(!bufs))
 		return -ENOMEM;
 
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 83720460c5bc..cf301a9ef512 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -105,6 +105,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 		"AnonHugePages:  %8lu kB\n"
+		"ShmemHugePages: %8lu kB\n"
+		"ShmemPmdMapped: %8lu kB\n"
 #endif
 #ifdef CONFIG_CMA
 		"CmaTotal:       %8lu kB\n"
@@ -162,8 +164,9 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		, atomic_long_read(&num_poisoned_pages) << (PAGE_SHIFT - 10)
 #endif
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		, K(global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
-		   HPAGE_PMD_NR)
+		, K(global_page_state(NR_ANON_THPS) * HPAGE_PMD_NR)
+		, K(global_page_state(NR_SHMEM_THPS) * HPAGE_PMD_NR)
+		, K(global_page_state(NR_SHMEM_PMDMAPPED) * HPAGE_PMD_NR)
 #endif
 #ifdef CONFIG_CMA
 		, K(totalcma_pages)
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 4648c7f63ae2..187d84ef9de9 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -448,6 +448,7 @@ struct mem_size_stats {
 	unsigned long referenced;
 	unsigned long anonymous;
 	unsigned long anonymous_thp;
+	unsigned long shmem_thp;
 	unsigned long swap;
 	unsigned long shared_hugetlb;
 	unsigned long private_hugetlb;
@@ -576,7 +577,12 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
 	page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
 	if (IS_ERR_OR_NULL(page))
 		return;
-	mss->anonymous_thp += HPAGE_PMD_SIZE;
+	if (PageAnon(page))
+		mss->anonymous_thp += HPAGE_PMD_SIZE;
+	else if (PageSwapBacked(page))
+		mss->shmem_thp += HPAGE_PMD_SIZE;
+	else
+		VM_BUG_ON_PAGE(1, page);
 	smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd));
 }
 #else
@@ -770,6 +776,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   "Referenced:     %8lu kB\n"
 		   "Anonymous:      %8lu kB\n"
 		   "AnonHugePages:  %8lu kB\n"
+		   "ShmemPmdMapped: %8lu kB\n"
 		   "Shared_Hugetlb: %8lu kB\n"
 		   "Private_Hugetlb: %7lu kB\n"
 		   "Swap:           %8lu kB\n"
@@ -787,6 +794,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   mss.referenced >> 10,
 		   mss.anonymous >> 10,
 		   mss.anonymous_thp >> 10,
+		   mss.shmem_thp >> 10,
 		   mss.shared_hugetlb >> 10,
 		   mss.private_hugetlb >> 10,
 		   mss.swap >> 10,
diff --git a/fs/super.c b/fs/super.c
index d78b9847e6cb..5806ffd45563 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -206,6 +206,8 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 	mutex_init(&s->s_sync_lock);
 	INIT_LIST_HEAD(&s->s_inodes);
 	spin_lock_init(&s->s_inode_list_lock);
+	INIT_LIST_HEAD(&s->s_inodes_wb);
+	spin_lock_init(&s->s_inode_wblist_lock);
 
 	if (list_lru_init_memcg(&s->s_dentry_lru))
 		goto fail;
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 2d97952e341a..85959d8324df 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -257,10 +257,9 @@ out:
  * fatal_signal_pending()s, and the mmap_sem must be released before
  * returning it.
  */
-int handle_userfault(struct vm_area_struct *vma, unsigned long address,
-		     unsigned int flags, unsigned long reason)
+int handle_userfault(struct fault_env *fe, unsigned long reason)
 {
-	struct mm_struct *mm = vma->vm_mm;
+	struct mm_struct *mm = fe->vma->vm_mm;
 	struct userfaultfd_ctx *ctx;
 	struct userfaultfd_wait_queue uwq;
 	int ret;
@@ -269,7 +268,7 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 	BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
 
 	ret = VM_FAULT_SIGBUS;
-	ctx = vma->vm_userfaultfd_ctx.ctx;
+	ctx = fe->vma->vm_userfaultfd_ctx.ctx;
 	if (!ctx)
 		goto out;
 
@@ -302,17 +301,17 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 	 * without first stopping userland access to the memory. For
 	 * VM_UFFD_MISSING userfaults this is enough for now.
 	 */
-	if (unlikely(!(flags & FAULT_FLAG_ALLOW_RETRY))) {
+	if (unlikely(!(fe->flags & FAULT_FLAG_ALLOW_RETRY))) {
 		/*
 		 * Validate the invariant that nowait must allow retry
 		 * to be sure not to return SIGBUS erroneously on
 		 * nowait invocations.
 		 */
-		BUG_ON(flags & FAULT_FLAG_RETRY_NOWAIT);
+		BUG_ON(fe->flags & FAULT_FLAG_RETRY_NOWAIT);
 #ifdef CONFIG_DEBUG_VM
 		if (printk_ratelimit()) {
 			printk(KERN_WARNING
-			       "FAULT_FLAG_ALLOW_RETRY missing %x\n", flags);
+			       "FAULT_FLAG_ALLOW_RETRY missing %x\n", fe->flags);
 			dump_stack();
 		}
 #endif
@@ -324,7 +323,7 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 	 * and wait.
 	 */
 	ret = VM_FAULT_RETRY;
-	if (flags & FAULT_FLAG_RETRY_NOWAIT)
+	if (fe->flags & FAULT_FLAG_RETRY_NOWAIT)
 		goto out;
 
 	/* take the reference before dropping the mmap_sem */
@@ -332,10 +331,11 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 
 	init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
 	uwq.wq.private = current;
-	uwq.msg = userfault_msg(address, flags, reason);
+	uwq.msg = userfault_msg(fe->address, fe->flags, reason);
 	uwq.ctx = ctx;
 
-	return_to_userland = (flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
+	return_to_userland =
+		(fe->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) ==
 		(FAULT_FLAG_USER|FAULT_FLAG_KILLABLE);
 
 	spin_lock(&ctx->fault_pending_wqh.lock);
@@ -353,7 +353,7 @@ int handle_userfault(struct vm_area_struct *vma, unsigned long address,
 			  TASK_KILLABLE);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 
-	must_wait = userfaultfd_must_wait(ctx, address, flags, reason);
+	must_wait = userfaultfd_must_wait(ctx, fe->address, fe->flags, reason);
 	up_read(&mm->mmap_sem);
 
 	if (likely(must_wait && !ACCESS_ONCE(ctx->released) &&
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 47fc63295422..1b3dc9dd8861 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1551,7 +1551,7 @@ xfs_filemap_page_mkwrite(
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
-		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault);
+		ret = dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault);
 	} else {
 		ret = block_page_mkwrite(vma, vmf, xfs_get_blocks);
 		ret = block_page_mkwrite_return(ret);
@@ -1585,7 +1585,7 @@ xfs_filemap_fault(
 		 * changes to xfs_get_blocks_direct() to map unwritten extent
 		 * ioend for conversion on read-only mappings.
 		 */
-		ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault);
+		ret = dax_fault(vma, vmf, xfs_get_blocks_dax_fault);
 	} else
 		ret = filemap_fault(vma, vmf);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
@@ -1622,7 +1622,7 @@ xfs_filemap_pmd_fault(
 	}
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault);
+	ret = dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (flags & FAULT_FLAG_WRITE)